security(approval): close 4 pattern gaps found by source-grounded audit

Four gaps in DANGEROUS_PATTERNS found by running 10 targeted tests that each mapped to a specific pattern in approval.py and checked whether the documented defense actually held. 1. **Heredoc script injection** — `python3 << 'EOF'` bypasses the existing `-e`/`-c` flag pattern. Adds pattern for interpreter + `<<` covering python{2,3}, perl, ruby, node. 2. **PID expansion self-termination** — `kill -9 $(pgrep hermes)` is opaque to the existing `pkill|killall` + name pattern because command substitution is not expanded at detection time. Adds structural patterns matching `kill` + `$(pgrep` and backtick variants. 3. **Git destructive operations** — `git reset --hard`, `push --force`, `push -f`, `clean -f*`, and `branch -D` were entirely absent. Note: `branch -d` also triggers because IGNORECASE is global — acceptable since -d is still a delete, just a safe one, and the prompt is only a confirmation, not a hard block. 4. **chmod +x then execute** — two-step social engineering where a script containing dangerous commands is first written to disk (not checked by write_file), then made executable and run as `./script`. Pattern catches `chmod +x ... [;&|]+ ./` combos. Does not solve the deeper architectural issue (write_file not checking content) — that is called out in the PR description as a known limitation. Tests: 23 new cases across 4 test classes, all in test_approval.py: - TestHeredocScriptExecution (7 cases, incl. regressions for -c) - TestPgrepKillExpansion (5 cases, incl. safe kill PID negative) - TestGitDestructiveOps (8 cases, incl. safe git status/push negatives) - TestChmodExecuteCombo (3 cases, incl. safe chmod-only negative) Full suite: 146 passed, 0 failed.
fix(auxiliary): skip anthropic in fallback chain when not explicitly configured
2026-04-10 05:06:00 -07:00 · 2026-04-10 05:05:56 -07:00 · 2026-04-10 05:05:56 -07:00 · 2026-04-10 05:05:56 -07:00 · 2026-04-10 05:05:26 -07:00 · 2026-04-10 05:05:22 -07:00
354 changed files with 32221 additions and 7797 deletions
@@ -81,6 +81,14 @@
 # HF_TOKEN=
 # OPENCODE_GO_BASE_URL=https://opencode.ai/zen/go/v1  # Override default base URL

+# =============================================================================
+# LLM PROVIDER (Qwen OAuth)
+# =============================================================================
+# Qwen OAuth reuses your local Qwen CLI login (qwen auth qwen-oauth).
+# No API key needed — credentials come from ~/.qwen/oauth_creds.json.
+# Optional base URL override:
+# HERMES_QWEN_BASE_URL=https://portal.qwen.ai/v1
+
 # =============================================================================
 # TOOL API KEYS
 # =============================================================================
@@ -8,6 +8,9 @@ on:
  release:
    types: [published]

+permissions:
+  contents: read
+
 concurrency:
  group: docker-${{ github.ref }}
  cancel-in-progress: true
@@ -17,22 +20,29 @@ jobs:
    # Only run on the upstream repository, not on forks
    if: github.repository == 'NousResearch/hermes-agent'
    runs-on: ubuntu-latest
-    timeout-minutes: 30
+    timeout-minutes: 60
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
        with:
          submodules: recursive

+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v3

-      - name: Build image
+      # Build amd64 only so we can `load` the image for smoke testing.
+      # `load: true` cannot export a multi-arch manifest to the local daemon.
+      # The multi-arch build follows on push to main / release.
+      - name: Build image (amd64, smoke test)
        uses: docker/build-push-action@v6
        with:
          context: .
          file: Dockerfile
          load: true
+          platforms: linux/amd64
          tags: nousresearch/hermes-agent:test
          cache-from: type=gha
          cache-to: type=gha,mode=max
@@ -51,26 +61,28 @@ jobs:
          username: ${{ secrets.DOCKERHUB_USERNAME }}
          password: ${{ secrets.DOCKERHUB_TOKEN }}

-      - name: Push image (main branch)
+      - name: Push multi-arch image (main branch)
        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
        uses: docker/build-push-action@v6
        with:
          context: .
          file: Dockerfile
          push: true
+          platforms: linux/amd64,linux/arm64
          tags: |
            nousresearch/hermes-agent:latest
            nousresearch/hermes-agent:${{ github.sha }}
          cache-from: type=gha
          cache-to: type=gha,mode=max

-      - name: Push image (release)
+      - name: Push multi-arch image (release)
        if: github.event_name == 'release'
        uses: docker/build-push-action@v6
        with:
          context: .
          file: Dockerfile
          push: true
+          platforms: linux/amd64,linux/arm64
          tags: |
            nousresearch/hermes-agent:latest
            nousresearch/hermes-agent:${{ github.event.release.tag_name }}
@@ -27,8 +27,8 @@ jobs:
        with:
          python-version: '3.11'

-      - name: Install Python dependencies
-        run: python -m pip install ascii-guard pyyaml
+      - name: Install ascii-guard
+        run: python -m pip install ascii-guard==2.3.0 pyyaml==6.0.3

      - name: Extract skill metadata for dashboard
        run: python3 website/scripts/extract-skills.py
@@ -27,8 +27,8 @@ jobs:
    timeout-minutes: 30
    steps:
      - uses: actions/checkout@v4
-      - uses: DeterminateSystems/nix-installer-action@main
-      - uses: DeterminateSystems/magic-nix-cache-action@main
+      - uses: DeterminateSystems/nix-installer-action@ef8a148080ab6020fd15196c2084a2eea5ff2d25  # v22
+      - uses: DeterminateSystems/magic-nix-cache-action@565684385bcd71bad329742eefe8d12f2e765b39  # v13
      - name: Check flake
        if: runner.os == 'Linux'
        run: nix flake check --print-build-logs
@@ -1,5 +1,8 @@
 FROM debian:13.4

+# Disable Python stdout buffering to ensure logs are printed immediately
+ENV PYTHONUNBUFFERED=1
+
 # Install system dependencies in one layer, clear APT cache
 RUN apt-get update && \
    apt-get install -y --no-install-recommends \
@@ -10,7 +13,8 @@ COPY . /opt/hermes
 WORKDIR /opt/hermes

 # Install Python and Node dependencies in one layer, no cache
-RUN pip install --no-cache-dir -e ".[all]" --break-system-packages && \
+RUN pip install --no-cache-dir uv --break-system-packages && \
+    uv pip install --system --break-system-packages --no-cache -e ".[all]" && \
    npm install --prefer-offline --no-audit && \
    npx playwright install --with-deps chromium --only-shell && \
    cd /opt/hermes/scripts/whatsapp-bridge && \
@@ -33,8 +33,10 @@ Use any model you want — [Nous Portal](https://portal.nousresearch.com), [Open
 curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
 ```

-Works on Linux, macOS, and WSL2. The installer handles everything — Python, Node.js, dependencies, and the `hermes` command. No prerequisites except git.
+Works on Linux, macOS, WSL2, and Android via Termux. The installer handles the platform-specific setup for you.

+> **Android / Termux:** The tested manual path is documented in the [Termux guide](https://hermes-agent.nousresearch.com/docs/getting-started/termux). On Termux, Hermes installs a curated `.[termux]` extra because the full `.[all]` extra currently pulls Android-incompatible voice dependencies.
+>
 > **Windows:** Native Windows is not supported. Please install [WSL2](https://learn.microsoft.com/en-us/windows/wsl/install) and run the command above.

 After installation:
@@ -0,0 +1,346 @@
+# Hermes Agent v0.8.0 (v2026.4.8)
+
+**Release Date:** April 8, 2026
+
+> The intelligence release — background task auto-notifications, free MiMo v2 Pro on Nous Portal, live model switching across all platforms, self-optimized GPT/Codex guidance, native Google AI Studio, smart inactivity timeouts, approval buttons, MCP OAuth 2.1, and 209 merged PRs with 82 resolved issues.
+
+---
+
+## ✨ Highlights
+
+- **Background Process Auto-Notifications (`notify_on_complete`)** — Background tasks can now automatically notify the agent when they finish. Start a long-running process (AI model training, test suites, deployments, builds) and the agent gets notified on completion — no polling needed. The agent can keep working on other things and pick up results when they land. ([#5779](https://github.com/NousResearch/hermes-agent/pull/5779))
+
+- **Free Xiaomi MiMo v2 Pro on Nous Portal** — Nous Portal now supports the free-tier Xiaomi MiMo v2 Pro model for auxiliary tasks (compression, vision, summarization), with free-tier model gating and pricing display in model selection. ([#6018](https://github.com/NousResearch/hermes-agent/pull/6018), [#5880](https://github.com/NousResearch/hermes-agent/pull/5880))
+
+- **Live Model Switching (`/model` Command)** — Switch models and providers mid-session from CLI, Telegram, Discord, Slack, or any gateway platform. Aggregator-aware resolution keeps you on OpenRouter/Nous when possible, with automatic cross-provider fallback when needed. Interactive model pickers on Telegram and Discord with inline buttons. ([#5181](https://github.com/NousResearch/hermes-agent/pull/5181), [#5742](https://github.com/NousResearch/hermes-agent/pull/5742))
+
+- **Self-Optimized GPT/Codex Tool-Use Guidance** — The agent diagnosed and patched 5 failure modes in GPT and Codex tool calling through automated behavioral benchmarking, dramatically improving reliability on OpenAI models. Includes execution discipline guidance and thinking-only prefill continuation for structured reasoning. ([#6120](https://github.com/NousResearch/hermes-agent/pull/6120), [#5414](https://github.com/NousResearch/hermes-agent/pull/5414), [#5931](https://github.com/NousResearch/hermes-agent/pull/5931))
+
+- **Google AI Studio (Gemini) Native Provider** — Direct access to Gemini models through Google's AI Studio API. Includes automatic models.dev registry integration for real-time context length detection across any provider. ([#5577](https://github.com/NousResearch/hermes-agent/pull/5577))
+
+- **Inactivity-Based Agent Timeouts** — Gateway and cron timeouts now track actual tool activity instead of wall-clock time. Long-running tasks that are actively working will never be killed — only truly idle agents time out. ([#5389](https://github.com/NousResearch/hermes-agent/pull/5389), [#5440](https://github.com/NousResearch/hermes-agent/pull/5440))
+
+- **Approval Buttons on Slack & Telegram** — Dangerous command approval via native platform buttons instead of typing `/approve`. Slack gets thread context preservation; Telegram gets emoji reactions for approval status. ([#5890](https://github.com/NousResearch/hermes-agent/pull/5890), [#5975](https://github.com/NousResearch/hermes-agent/pull/5975))
+
+- **MCP OAuth 2.1 PKCE + OSV Malware Scanning** — Full standards-compliant OAuth for MCP server authentication, plus automatic malware scanning of MCP extension packages via the OSV vulnerability database. ([#5420](https://github.com/NousResearch/hermes-agent/pull/5420), [#5305](https://github.com/NousResearch/hermes-agent/pull/5305))
+
+- **Centralized Logging & Config Validation** — Structured logging to `~/.hermes/logs/` (agent.log + errors.log) with the `hermes logs` command for tailing and filtering. Config structure validation catches malformed YAML at startup before it causes cryptic failures. ([#5430](https://github.com/NousResearch/hermes-agent/pull/5430), [#5426](https://github.com/NousResearch/hermes-agent/pull/5426))
+
+- **Plugin System Expansion** — Plugins can now register CLI subcommands, receive request-scoped API hooks with correlation IDs, prompt for required env vars during install, and hook into session lifecycle events (finalize/reset). ([#5295](https://github.com/NousResearch/hermes-agent/pull/5295), [#5427](https://github.com/NousResearch/hermes-agent/pull/5427), [#5470](https://github.com/NousResearch/hermes-agent/pull/5470), [#6129](https://github.com/NousResearch/hermes-agent/pull/6129))
+
+- **Matrix Tier 1 & Platform Hardening** — Matrix gets reactions, read receipts, rich formatting, and room management. Discord adds channel controls and ignored channels. Signal gets full MEDIA: tag delivery. Mattermost gets file attachments. Comprehensive reliability fixes across all platforms. ([#5275](https://github.com/NousResearch/hermes-agent/pull/5275), [#5975](https://github.com/NousResearch/hermes-agent/pull/5975), [#5602](https://github.com/NousResearch/hermes-agent/pull/5602))
+
+- **Security Hardening Pass** — Consolidated SSRF protections, timing attack mitigations, tar traversal prevention, credential leakage guards, cron path traversal hardening, and cross-session isolation. Terminal workdir sanitization across all backends. ([#5944](https://github.com/NousResearch/hermes-agent/pull/5944), [#5613](https://github.com/NousResearch/hermes-agent/pull/5613), [#5629](https://github.com/NousResearch/hermes-agent/pull/5629))
+
+---
+
+## 🏗️ Core Agent & Architecture
+
+### Provider & Model Support
+- **Native Google AI Studio (Gemini) provider** with models.dev integration for automatic context length detection ([#5577](https://github.com/NousResearch/hermes-agent/pull/5577))
+- **`/model` command — full provider+model system overhaul** — live switching across CLI and all gateway platforms with aggregator-aware resolution ([#5181](https://github.com/NousResearch/hermes-agent/pull/5181))
+- **Interactive model picker for Telegram and Discord** — inline button-based model selection ([#5742](https://github.com/NousResearch/hermes-agent/pull/5742))
+- **Nous Portal free-tier model gating** with pricing display in model selection ([#5880](https://github.com/NousResearch/hermes-agent/pull/5880))
+- **Model pricing display** for OpenRouter and Nous Portal providers ([#5416](https://github.com/NousResearch/hermes-agent/pull/5416))
+- **xAI (Grok) prompt caching** via `x-grok-conv-id` header ([#5604](https://github.com/NousResearch/hermes-agent/pull/5604))
+- **Grok added to tool-use enforcement models** for direct xAI usage ([#5595](https://github.com/NousResearch/hermes-agent/pull/5595))
+- **MiniMax TTS provider** (speech-2.8) ([#4963](https://github.com/NousResearch/hermes-agent/pull/4963))
+- **Non-agentic model warning** — warns users when loading Hermes LLM models not designed for tool use ([#5378](https://github.com/NousResearch/hermes-agent/pull/5378))
+- **Ollama Cloud auth, /model switch persistence**, and alias tab completion ([#5269](https://github.com/NousResearch/hermes-agent/pull/5269))
+- **Preserve dots in OpenCode Go model names** (minimax-m2.7, glm-4.5, kimi-k2.5) ([#5597](https://github.com/NousResearch/hermes-agent/pull/5597))
+- **MiniMax models 404 fix** — strip /v1 from Anthropic base URL for OpenCode Go ([#4918](https://github.com/NousResearch/hermes-agent/pull/4918))
+- **Provider credential reset windows** honored in pooled failover ([#5188](https://github.com/NousResearch/hermes-agent/pull/5188))
+- **OAuth token sync** between credential pool and credentials file ([#4981](https://github.com/NousResearch/hermes-agent/pull/4981))
+- **Stale OAuth credentials** no longer block OpenRouter users on auto-detect ([#5746](https://github.com/NousResearch/hermes-agent/pull/5746))
+- **Codex OAuth credential pool disconnect** + expired token import fix ([#5681](https://github.com/NousResearch/hermes-agent/pull/5681))
+- **Codex pool entry sync** from `~/.codex/auth.json` on exhaustion — @GratefulDave ([#5610](https://github.com/NousResearch/hermes-agent/pull/5610))
+- **Auxiliary client payment fallback** — retry with next provider on 402 ([#5599](https://github.com/NousResearch/hermes-agent/pull/5599))
+- **Auxiliary client resolves named custom providers** and 'main' alias ([#5978](https://github.com/NousResearch/hermes-agent/pull/5978))
+- **Use mimo-v2-pro** for non-vision auxiliary tasks on Nous free tier ([#6018](https://github.com/NousResearch/hermes-agent/pull/6018))
+- **Vision auto-detection** tries main provider first ([#6041](https://github.com/NousResearch/hermes-agent/pull/6041))
+- **Provider re-ordering and Quick Install** — @austinpickett ([#4664](https://github.com/NousResearch/hermes-agent/pull/4664))
+- **Nous OAuth access_token** no longer used as inference API key — @SHL0MS ([#5564](https://github.com/NousResearch/hermes-agent/pull/5564))
+- **HERMES_PORTAL_BASE_URL env var** respected during Nous login — @benbarclay ([#5745](https://github.com/NousResearch/hermes-agent/pull/5745))
+- **Env var overrides** for Nous portal/inference URLs ([#5419](https://github.com/NousResearch/hermes-agent/pull/5419))
+- **Z.AI endpoint auto-detect** via probe and cache ([#5763](https://github.com/NousResearch/hermes-agent/pull/5763))
+- **MiniMax context lengths, model catalog, thinking guard, aux model, and config base_url** corrections ([#6082](https://github.com/NousResearch/hermes-agent/pull/6082))
+- **Community provider/model resolution fixes** — salvaged 4 community PRs + MiniMax aux URL ([#5983](https://github.com/NousResearch/hermes-agent/pull/5983))
+
+### Agent Loop & Conversation
+- **Self-optimized GPT/Codex tool-use guidance** via automated behavioral benchmarking — agent self-diagnosed and patched 5 failure modes ([#6120](https://github.com/NousResearch/hermes-agent/pull/6120))
+- **GPT/Codex execution discipline guidance** in system prompts ([#5414](https://github.com/NousResearch/hermes-agent/pull/5414))
+- **Thinking-only prefill continuation** for structured reasoning responses ([#5931](https://github.com/NousResearch/hermes-agent/pull/5931))
+- **Accept reasoning-only responses** without retries — set content to "(empty)" instead of infinite retry ([#5278](https://github.com/NousResearch/hermes-agent/pull/5278))
+- **Jittered retry backoff** — exponential backoff with jitter for API retries ([#6048](https://github.com/NousResearch/hermes-agent/pull/6048))
+- **Smart thinking block signature management** — preserve and manage Anthropic thinking signatures across turns ([#6112](https://github.com/NousResearch/hermes-agent/pull/6112))
+- **Coerce tool call arguments** to match JSON Schema types — fixes models that send strings instead of numbers/booleans ([#5265](https://github.com/NousResearch/hermes-agent/pull/5265))
+- **Save oversized tool results to file** instead of destructive truncation ([#5210](https://github.com/NousResearch/hermes-agent/pull/5210))
+- **Sandbox-aware tool result persistence** ([#6085](https://github.com/NousResearch/hermes-agent/pull/6085))
+- **Streaming fallback** improved after edit failures ([#6110](https://github.com/NousResearch/hermes-agent/pull/6110))
+- **Codex empty-output gaps** covered in fallback + normalizer + auxiliary client ([#5724](https://github.com/NousResearch/hermes-agent/pull/5724), [#5730](https://github.com/NousResearch/hermes-agent/pull/5730), [#5734](https://github.com/NousResearch/hermes-agent/pull/5734))
+- **Codex stream output backfill** from output_item.done events ([#5689](https://github.com/NousResearch/hermes-agent/pull/5689))
+- **Stream consumer creates new message** after tool boundaries ([#5739](https://github.com/NousResearch/hermes-agent/pull/5739))
+- **Codex validation aligned** with normalization for empty stream output ([#5940](https://github.com/NousResearch/hermes-agent/pull/5940))
+- **Bridge tool-calls** in copilot-acp adapter ([#5460](https://github.com/NousResearch/hermes-agent/pull/5460))
+- **Filter transcript-only roles** from chat-completions payload ([#4880](https://github.com/NousResearch/hermes-agent/pull/4880))
+- **Context compaction failures fixed** on temperature-restricted models — @MadKangYu ([#5608](https://github.com/NousResearch/hermes-agent/pull/5608))
+- **Sanitize tool_calls for all strict APIs** (Fireworks, Mistral, etc.) — @lumethegreat ([#5183](https://github.com/NousResearch/hermes-agent/pull/5183))
+
+### Memory & Sessions
+- **Supermemory memory provider** — new memory plugin with multi-container, search_mode, identity template, and env var override ([#5737](https://github.com/NousResearch/hermes-agent/pull/5737), [#5933](https://github.com/NousResearch/hermes-agent/pull/5933))
+- **Shared thread sessions** by default — multi-user thread support across gateway platforms ([#5391](https://github.com/NousResearch/hermes-agent/pull/5391))
+- **Subagent sessions linked to parent** and hidden from session list ([#5309](https://github.com/NousResearch/hermes-agent/pull/5309))
+- **Profile-scoped memory isolation** and clone support ([#4845](https://github.com/NousResearch/hermes-agent/pull/4845))
+- **Thread gateway user_id to memory plugins** for per-user scoping ([#5895](https://github.com/NousResearch/hermes-agent/pull/5895))
+- **Honcho plugin drift overhaul** + plugin CLI registration system ([#5295](https://github.com/NousResearch/hermes-agent/pull/5295))
+- **Honcho holographic prompt and trust score** rendering preserved ([#4872](https://github.com/NousResearch/hermes-agent/pull/4872))
+- **Honcho doctor fix** — use recall_mode instead of memory_mode — @techguysimon ([#5645](https://github.com/NousResearch/hermes-agent/pull/5645))
+- **RetainDB** — API routes, write queue, dialectic, agent model, file tools fixes ([#5461](https://github.com/NousResearch/hermes-agent/pull/5461))
+- **Hindsight memory plugin overhaul** + memory setup wizard fixes ([#5094](https://github.com/NousResearch/hermes-agent/pull/5094))
+- **mem0 API v2 compat**, prefetch context fencing, secret redaction ([#5423](https://github.com/NousResearch/hermes-agent/pull/5423))
+- **mem0 env vars merged** with mem0.json instead of either/or ([#4939](https://github.com/NousResearch/hermes-agent/pull/4939))
+- **Clean user message** used for all memory provider operations ([#4940](https://github.com/NousResearch/hermes-agent/pull/4940))
+- **Silent memory flush failure** on /new and /resume fixed — @ryanautomated ([#5640](https://github.com/NousResearch/hermes-agent/pull/5640))
+- **OpenViking atexit safety net** for session commit ([#5664](https://github.com/NousResearch/hermes-agent/pull/5664))
+- **OpenViking tenant-scoping headers** for multi-tenant servers ([#4936](https://github.com/NousResearch/hermes-agent/pull/4936))
+- **ByteRover brv query** runs synchronously before LLM call ([#4831](https://github.com/NousResearch/hermes-agent/pull/4831))
+
+---
+
+## 📱 Messaging Platforms (Gateway)
+
+### Gateway Core
+- **Inactivity-based agent timeout** — replaces wall-clock timeout with smart activity tracking; long-running active tasks never killed ([#5389](https://github.com/NousResearch/hermes-agent/pull/5389))
+- **Approval buttons for Slack & Telegram** + Slack thread context preservation ([#5890](https://github.com/NousResearch/hermes-agent/pull/5890))
+- **Live-stream /update output** + forward interactive prompts to user ([#5180](https://github.com/NousResearch/hermes-agent/pull/5180))
+- **Infinite timeout support** + periodic notifications + actionable error messages ([#4959](https://github.com/NousResearch/hermes-agent/pull/4959))
+- **Duplicate message prevention** — gateway dedup + partial stream guard ([#4878](https://github.com/NousResearch/hermes-agent/pull/4878))
+- **Webhook delivery_info persistence** + full session id in /status ([#5942](https://github.com/NousResearch/hermes-agent/pull/5942))
+- **Tool preview truncation** respects tool_preview_length in all/new progress modes ([#5937](https://github.com/NousResearch/hermes-agent/pull/5937))
+- **Short preview truncation** restored for all/new tool progress modes ([#4935](https://github.com/NousResearch/hermes-agent/pull/4935))
+- **Update-pending state** written atomically to prevent corruption ([#4923](https://github.com/NousResearch/hermes-agent/pull/4923))
+- **Approval session key isolated** per turn ([#4884](https://github.com/NousResearch/hermes-agent/pull/4884))
+- **Active-session guard bypass** for /approve, /deny, /stop, /new ([#4926](https://github.com/NousResearch/hermes-agent/pull/4926), [#5765](https://github.com/NousResearch/hermes-agent/pull/5765))
+- **Typing indicator paused** during approval waits ([#5893](https://github.com/NousResearch/hermes-agent/pull/5893))
+- **Caption check** uses exact line-by-line match instead of substring (all platforms) ([#5939](https://github.com/NousResearch/hermes-agent/pull/5939))
+- **MEDIA: tags stripped** from streamed gateway messages ([#5152](https://github.com/NousResearch/hermes-agent/pull/5152))
+- **MEDIA: tags extracted** from cron delivery before sending ([#5598](https://github.com/NousResearch/hermes-agent/pull/5598))
+- **Profile-aware service units** + voice transcription cleanup ([#5972](https://github.com/NousResearch/hermes-agent/pull/5972))
+- **Thread-safe PairingStore** with atomic writes — @CharlieKerfoot ([#5656](https://github.com/NousResearch/hermes-agent/pull/5656))
+- **Sanitize media URLs** in base platform logs — @WAXLYY ([#5631](https://github.com/NousResearch/hermes-agent/pull/5631))
+- **Reduce Telegram fallback IP activation log noise** — @MadKangYu ([#5615](https://github.com/NousResearch/hermes-agent/pull/5615))
+- **Cron static method wrappers** to prevent self-binding ([#5299](https://github.com/NousResearch/hermes-agent/pull/5299))
+- **Stale 'hermes login' replaced** with 'hermes auth' + credential removal re-seeding fix ([#5670](https://github.com/NousResearch/hermes-agent/pull/5670))
+
+### Telegram
+- **Group topics skill binding** for supergroup forum topics ([#4886](https://github.com/NousResearch/hermes-agent/pull/4886))
+- **Emoji reactions** for approval status and notifications ([#5975](https://github.com/NousResearch/hermes-agent/pull/5975))
+- **Duplicate message delivery prevented** on send timeout ([#5153](https://github.com/NousResearch/hermes-agent/pull/5153))
+- **Command names sanitized** to strip invalid characters ([#5596](https://github.com/NousResearch/hermes-agent/pull/5596))
+- **Per-platform disabled skills** respected in Telegram menu and gateway dispatch ([#4799](https://github.com/NousResearch/hermes-agent/pull/4799))
+- **/approve and /deny** routed through running-agent guard ([#4798](https://github.com/NousResearch/hermes-agent/pull/4798))
+
+### Discord
+- **Channel controls** — ignored_channels and no_thread_channels config options ([#5975](https://github.com/NousResearch/hermes-agent/pull/5975))
+- **Skills registered as native slash commands** via shared gateway logic ([#5603](https://github.com/NousResearch/hermes-agent/pull/5603))
+- **/approve, /deny, /queue, /background, /btw** registered as native slash commands ([#4800](https://github.com/NousResearch/hermes-agent/pull/4800), [#5477](https://github.com/NousResearch/hermes-agent/pull/5477))
+- **Unnecessary members intent** removed on startup + token lock leak fix ([#5302](https://github.com/NousResearch/hermes-agent/pull/5302))
+
+### Slack
+- **Thread engagement** — auto-respond in bot-started and mentioned threads ([#5897](https://github.com/NousResearch/hermes-agent/pull/5897))
+- **mrkdwn in edit_message** + thread replies without @mentions ([#5733](https://github.com/NousResearch/hermes-agent/pull/5733))
+
+### Matrix
+- **Tier 1 feature parity** — reactions, read receipts, rich formatting, room management ([#5275](https://github.com/NousResearch/hermes-agent/pull/5275))
+- **MATRIX_REQUIRE_MENTION and MATRIX_AUTO_THREAD** support ([#5106](https://github.com/NousResearch/hermes-agent/pull/5106))
+- **Comprehensive reliability** — encrypted media, auth recovery, cron E2EE, Synapse compat ([#5271](https://github.com/NousResearch/hermes-agent/pull/5271))
+- **CJK input, E2EE, and reconnect** fixes ([#5665](https://github.com/NousResearch/hermes-agent/pull/5665))
+
+### Signal
+- **Full MEDIA: tag delivery** — send_image_file, send_voice, and send_video implemented ([#5602](https://github.com/NousResearch/hermes-agent/pull/5602))
+
+### Mattermost
+- **File attachments** — set message type to DOCUMENT when post has file attachments — @nericervin ([#5609](https://github.com/NousResearch/hermes-agent/pull/5609))
+
+### Feishu
+- **Interactive card approval buttons** ([#6043](https://github.com/NousResearch/hermes-agent/pull/6043))
+- **Reconnect and ACL** fixes ([#5665](https://github.com/NousResearch/hermes-agent/pull/5665))
+
+### Webhooks
+- **`{__raw__}` template token** and thread_id passthrough for forum topics ([#5662](https://github.com/NousResearch/hermes-agent/pull/5662))
+
+---
+
+## 🖥️ CLI & User Experience
+
+### Interactive CLI
+- **Defer response content** until reasoning block completes ([#5773](https://github.com/NousResearch/hermes-agent/pull/5773))
+- **Ghost status-bar lines cleared** on terminal resize ([#4960](https://github.com/NousResearch/hermes-agent/pull/4960))
+- **Normalise \r\n and \r line endings** in pasted text ([#4849](https://github.com/NousResearch/hermes-agent/pull/4849))
+- **ChatConsole errors, curses scroll, skin-aware banner, git state** banner fixes ([#5974](https://github.com/NousResearch/hermes-agent/pull/5974))
+- **Native Windows image paste** support ([#5917](https://github.com/NousResearch/hermes-agent/pull/5917))
+- **--yolo and other flags** no longer silently dropped when placed before 'chat' subcommand ([#5145](https://github.com/NousResearch/hermes-agent/pull/5145))
+
+### Setup & Configuration
+- **Config structure validation** — detect malformed YAML at startup with actionable error messages ([#5426](https://github.com/NousResearch/hermes-agent/pull/5426))
+- **Centralized logging** to `~/.hermes/logs/` — agent.log (INFO+), errors.log (WARNING+) with `hermes logs` command ([#5430](https://github.com/NousResearch/hermes-agent/pull/5430))
+- **Docs links added** to setup wizard sections ([#5283](https://github.com/NousResearch/hermes-agent/pull/5283))
+- **Doctor diagnostics** — sync provider checks, config migration, WAL and mem0 diagnostics ([#5077](https://github.com/NousResearch/hermes-agent/pull/5077))
+- **Timeout debug logging** and user-facing diagnostics improved ([#5370](https://github.com/NousResearch/hermes-agent/pull/5370))
+- **Reasoning effort unified** to config.yaml only ([#6118](https://github.com/NousResearch/hermes-agent/pull/6118))
+- **Permanent command allowlist** loaded on startup ([#5076](https://github.com/NousResearch/hermes-agent/pull/5076))
+- **`hermes auth remove`** now clears env-seeded credentials permanently ([#5285](https://github.com/NousResearch/hermes-agent/pull/5285))
+- **Bundled skills synced to all profiles** during update ([#5795](https://github.com/NousResearch/hermes-agent/pull/5795))
+- **`hermes update` no longer kills** freshly-restarted gateway service ([#5448](https://github.com/NousResearch/hermes-agent/pull/5448))
+- **Subprocess.run() timeouts** added to all gateway CLI commands ([#5424](https://github.com/NousResearch/hermes-agent/pull/5424))
+- **Actionable error message** when Codex refresh token is reused — @tymrtn ([#5612](https://github.com/NousResearch/hermes-agent/pull/5612))
+- **Google-workspace skill scripts** can now run directly — @xinbenlv ([#5624](https://github.com/NousResearch/hermes-agent/pull/5624))
+
+### Cron System
+- **Inactivity-based cron timeout** — replaces wall-clock; active tasks run indefinitely ([#5440](https://github.com/NousResearch/hermes-agent/pull/5440))
+- **Pre-run script injection** for data collection and change detection ([#5082](https://github.com/NousResearch/hermes-agent/pull/5082))
+- **Delivery failure tracking** in job status ([#6042](https://github.com/NousResearch/hermes-agent/pull/6042))
+- **Delivery guidance** in cron prompts — stops send_message thrashing ([#5444](https://github.com/NousResearch/hermes-agent/pull/5444))
+- **MEDIA files delivered** as native platform attachments ([#5921](https://github.com/NousResearch/hermes-agent/pull/5921))
+- **[SILENT] suppression** works anywhere in response — @auspic7 ([#5654](https://github.com/NousResearch/hermes-agent/pull/5654))
+- **Cron path traversal** hardening ([#5147](https://github.com/NousResearch/hermes-agent/pull/5147))
+
+---
+
+## 🔧 Tool System
+
+### Terminal & Execution
+- **Execute_code on remote backends** — code execution now works on Docker, SSH, Modal, and other remote terminal backends ([#5088](https://github.com/NousResearch/hermes-agent/pull/5088))
+- **Exit code context** for common CLI tools in terminal results — helps agent understand what went wrong ([#5144](https://github.com/NousResearch/hermes-agent/pull/5144))
+- **Progressive subdirectory hint discovery** — agent learns project structure as it navigates ([#5291](https://github.com/NousResearch/hermes-agent/pull/5291))
+- **notify_on_complete for background processes** — get notified when long-running tasks finish ([#5779](https://github.com/NousResearch/hermes-agent/pull/5779))
+- **Docker env config** — explicit container environment variables via docker_env config ([#4738](https://github.com/NousResearch/hermes-agent/pull/4738))
+- **Approval metadata included** in terminal tool results ([#5141](https://github.com/NousResearch/hermes-agent/pull/5141))
+- **Workdir parameter sanitized** in terminal tool across all backends ([#5629](https://github.com/NousResearch/hermes-agent/pull/5629))
+- **Detached process crash recovery** state corrected ([#6101](https://github.com/NousResearch/hermes-agent/pull/6101))
+- **Agent-browser paths with spaces** preserved — @Vasanthdev2004 ([#6077](https://github.com/NousResearch/hermes-agent/pull/6077))
+- **Portable base64 encoding** for image reading on macOS — @CharlieKerfoot ([#5657](https://github.com/NousResearch/hermes-agent/pull/5657))
+
+### Browser
+- **Switch managed browser provider** from Browserbase to Browser Use — @benbarclay ([#5750](https://github.com/NousResearch/hermes-agent/pull/5750))
+- **Firecrawl cloud browser** provider — @alt-glitch ([#5628](https://github.com/NousResearch/hermes-agent/pull/5628))
+- **JS evaluation** via browser_console expression parameter ([#5303](https://github.com/NousResearch/hermes-agent/pull/5303))
+- **Windows browser** fixes ([#5665](https://github.com/NousResearch/hermes-agent/pull/5665))
+
+### MCP
+- **MCP OAuth 2.1 PKCE** — full standards-compliant OAuth client support ([#5420](https://github.com/NousResearch/hermes-agent/pull/5420))
+- **OSV malware check** for MCP extension packages ([#5305](https://github.com/NousResearch/hermes-agent/pull/5305))
+- **Prefer structuredContent over text** + no_mcp sentinel ([#5979](https://github.com/NousResearch/hermes-agent/pull/5979))
+- **Unknown toolsets warning suppressed** for MCP server names ([#5279](https://github.com/NousResearch/hermes-agent/pull/5279))
+
+### Web & Files
+- **.zip document support** + auto-mount cache dirs into remote backends ([#4846](https://github.com/NousResearch/hermes-agent/pull/4846))
+- **Redact query secrets** in send_message errors — @WAXLYY ([#5650](https://github.com/NousResearch/hermes-agent/pull/5650))
+
+### Delegation
+- **Credential pool sharing** + workspace path hints for subagents ([#5748](https://github.com/NousResearch/hermes-agent/pull/5748))
+
+### ACP (VS Code / Zed / JetBrains)
+- **Aggregate ACP improvements** — auth compat, protocol fixes, command ads, delegation, SSE events ([#5292](https://github.com/NousResearch/hermes-agent/pull/5292))
+
+---
+
+## 🧩 Skills Ecosystem
+
+### Skills System
+- **Skill config interface** — skills can declare required config.yaml settings, prompted during setup, injected at load time ([#5635](https://github.com/NousResearch/hermes-agent/pull/5635))
+- **Plugin CLI registration system** — plugins register their own CLI subcommands without touching main.py ([#5295](https://github.com/NousResearch/hermes-agent/pull/5295))
+- **Request-scoped API hooks** with tool call correlation IDs for plugins ([#5427](https://github.com/NousResearch/hermes-agent/pull/5427))
+- **Session lifecycle hooks** — on_session_finalize and on_session_reset for CLI + gateway ([#6129](https://github.com/NousResearch/hermes-agent/pull/6129))
+- **Prompt for required env vars** during plugin install — @kshitijk4poor ([#5470](https://github.com/NousResearch/hermes-agent/pull/5470))
+- **Plugin name validation** — reject names that resolve to plugins root ([#5368](https://github.com/NousResearch/hermes-agent/pull/5368))
+- **pre_llm_call plugin context** moved to user message to preserve prompt cache ([#5146](https://github.com/NousResearch/hermes-agent/pull/5146))
+
+### New & Updated Skills
+- **popular-web-designs** — 54 production website design systems ([#5194](https://github.com/NousResearch/hermes-agent/pull/5194))
+- **p5js creative coding** — @SHL0MS ([#5600](https://github.com/NousResearch/hermes-agent/pull/5600))
+- **manim-video** — mathematical and technical animations — @SHL0MS ([#4930](https://github.com/NousResearch/hermes-agent/pull/4930))
+- **llm-wiki** — Karpathy's LLM Wiki skill ([#5635](https://github.com/NousResearch/hermes-agent/pull/5635))
+- **gitnexus-explorer** — codebase indexing and knowledge serving ([#5208](https://github.com/NousResearch/hermes-agent/pull/5208))
+- **research-paper-writing** — AI-Scientist & GPT-Researcher patterns — @SHL0MS ([#5421](https://github.com/NousResearch/hermes-agent/pull/5421))
+- **blogwatcher** updated to JulienTant's fork ([#5759](https://github.com/NousResearch/hermes-agent/pull/5759))
+- **claude-code skill** comprehensive rewrite v2.0 + v2.2 ([#5155](https://github.com/NousResearch/hermes-agent/pull/5155), [#5158](https://github.com/NousResearch/hermes-agent/pull/5158))
+- **Code verification skills** consolidated into one ([#4854](https://github.com/NousResearch/hermes-agent/pull/4854))
+- **Manim CE reference docs** expanded — geometry, animations, LaTeX — @leotrs ([#5791](https://github.com/NousResearch/hermes-agent/pull/5791))
+- **Manim-video references** — design thinking, updaters, paper explainer, decorations, production quality — @SHL0MS ([#5588](https://github.com/NousResearch/hermes-agent/pull/5588), [#5408](https://github.com/NousResearch/hermes-agent/pull/5408))
+
+---
+
+## 🔒 Security & Reliability
+
+### Security Hardening
+- **Consolidated security** — SSRF protections, timing attack mitigations, tar traversal prevention, credential leakage guards ([#5944](https://github.com/NousResearch/hermes-agent/pull/5944))
+- **Cross-session isolation** + cron path traversal hardening ([#5613](https://github.com/NousResearch/hermes-agent/pull/5613))
+- **Workdir parameter sanitized** in terminal tool across all backends ([#5629](https://github.com/NousResearch/hermes-agent/pull/5629))
+- **Approval 'once' session escalation** prevented + cron delivery platform validation ([#5280](https://github.com/NousResearch/hermes-agent/pull/5280))
+- **Profile-scoped Google Workspace OAuth tokens** protected ([#4910](https://github.com/NousResearch/hermes-agent/pull/4910))
+
+### Reliability
+- **Aggressive worktree and branch cleanup** to prevent accumulation ([#6134](https://github.com/NousResearch/hermes-agent/pull/6134))
+- **O(n²) catastrophic backtracking** in redact regex fixed — 100x improvement on large outputs ([#4962](https://github.com/NousResearch/hermes-agent/pull/4962))
+- **Runtime stability fixes** across core, web, delegate, and browser tools ([#4843](https://github.com/NousResearch/hermes-agent/pull/4843))
+- **API server streaming fix** + conversation history support ([#5977](https://github.com/NousResearch/hermes-agent/pull/5977))
+- **OpenViking API endpoint paths** and response parsing corrected ([#5078](https://github.com/NousResearch/hermes-agent/pull/5078))
+
+---
+
+## 🐛 Notable Bug Fixes
+
+- **9 community bugfixes salvaged** — gateway, cron, deps, macOS launchd in one batch ([#5288](https://github.com/NousResearch/hermes-agent/pull/5288))
+- **Batch core bug fixes** — model config, session reset, alias fallback, launchctl, delegation, atomic writes ([#5630](https://github.com/NousResearch/hermes-agent/pull/5630))
+- **Batch gateway/platform fixes** — matrix E2EE, CJK input, Windows browser, Feishu reconnect + ACL ([#5665](https://github.com/NousResearch/hermes-agent/pull/5665))
+- **Stale test skips removed**, regex backtracking, file search bug, and test flakiness ([#4969](https://github.com/NousResearch/hermes-agent/pull/4969))
+- **Nix flake** — read version, regen uv.lock, add hermes_logging — @alt-glitch ([#5651](https://github.com/NousResearch/hermes-agent/pull/5651))
+- **Lowercase variable redaction** regression tests ([#5185](https://github.com/NousResearch/hermes-agent/pull/5185))
+
+---
+
+## 🧪 Testing
+
+- **57 failing CI tests repaired** across 14 files ([#5823](https://github.com/NousResearch/hermes-agent/pull/5823))
+- **Test suite re-architecture** + CI failure fixes — @alt-glitch ([#5946](https://github.com/NousResearch/hermes-agent/pull/5946))
+- **Codebase-wide lint cleanup** — unused imports, dead code, and inefficient patterns ([#5821](https://github.com/NousResearch/hermes-agent/pull/5821))
+- **browser_close tool removed** — auto-cleanup handles it ([#5792](https://github.com/NousResearch/hermes-agent/pull/5792))
+
+---
+
+## 📚 Documentation
+
+- **Comprehensive documentation audit** — fix stale info, expand thin pages, add depth ([#5393](https://github.com/NousResearch/hermes-agent/pull/5393))
+- **40+ discrepancies fixed** between documentation and codebase ([#5818](https://github.com/NousResearch/hermes-agent/pull/5818))
+- **13 features documented** from last week's PRs ([#5815](https://github.com/NousResearch/hermes-agent/pull/5815))
+- **Guides section overhaul** — fix existing + add 3 new tutorials ([#5735](https://github.com/NousResearch/hermes-agent/pull/5735))
+- **Salvaged 4 docs PRs** — docker setup, post-update validation, local LLM guide, signal-cli install ([#5727](https://github.com/NousResearch/hermes-agent/pull/5727))
+- **Discord configuration reference** ([#5386](https://github.com/NousResearch/hermes-agent/pull/5386))
+- **Community FAQ entries** for common workflows and troubleshooting ([#4797](https://github.com/NousResearch/hermes-agent/pull/4797))
+- **WSL2 networking guide** for local model servers ([#5616](https://github.com/NousResearch/hermes-agent/pull/5616))
+- **Honcho CLI reference** + plugin CLI registration docs ([#5308](https://github.com/NousResearch/hermes-agent/pull/5308))
+- **Obsidian Headless setup** for servers in llm-wiki ([#5660](https://github.com/NousResearch/hermes-agent/pull/5660))
+- **Hermes Mod visual skin editor** added to skins page ([#6095](https://github.com/NousResearch/hermes-agent/pull/6095))
+
+---
+
+## 👥 Contributors
+
+### Core
+- **@teknium1** — 179 PRs
+
+### Top Community Contributors
+- **@SHL0MS** (7 PRs) — p5js creative coding skill, manim-video skill + 5 reference expansions, research-paper-writing, Nous OAuth fix, manim font fix
+- **@alt-glitch** (3 PRs) — Firecrawl cloud browser provider, test re-architecture + CI fixes, Nix flake fixes
+- **@benbarclay** (2 PRs) — Browser Use managed provider switch, Nous portal base URL fix
+- **@CharlieKerfoot** (2 PRs) — macOS portable base64 encoding, thread-safe PairingStore
+- **@WAXLYY** (2 PRs) — send_message secret redaction, gateway media URL sanitization
+- **@MadKangYu** (2 PRs) — Telegram log noise reduction, context compaction fix for temperature-restricted models
+
+### All Contributors
+@alt-glitch, @austinpickett, @auspic7, @benbarclay, @CharlieKerfoot, @GratefulDave, @kshitijk4poor, @leotrs, @lumethegreat, @MadKangYu, @nericervin, @ryanautomated, @SHL0MS, @techguysimon, @tymrtn, @Vasanthdev2004, @WAXLYY, @xinbenlv
+
+---
+
+**Full Changelog**: [v2026.4.3...v2026.4.8](https://github.com/NousResearch/hermes-agent/compare/v2026.4.3...v2026.4.8)
@@ -36,6 +36,7 @@ from acp.schema import (
    SessionCapabilities,
    SessionForkCapabilities,
    SessionListCapabilities,
+    SessionResumeCapabilities,
    SessionInfo,
    TextContentBlock,
    UnstructuredCommandInput,
@@ -245,9 +246,11 @@ class HermesACPAgent(acp.Agent):
            protocol_version=acp.PROTOCOL_VERSION,
            agent_info=Implementation(name="hermes-agent", version=HERMES_VERSION),
            agent_capabilities=AgentCapabilities(
+                load_session=True,
                session_capabilities=SessionCapabilities(
                    fork=SessionForkCapabilities(),
                    list=SessionListCapabilities(),
+                    resume=SessionResumeCapabilities(),
                ),
            ),
            auth_methods=auth_methods,
@@ -451,14 +454,13 @@ class HermesACPAgent(acp.Agent):
            await conn.session_update(session_id, update)

        usage = None
-        usage_data = result.get("usage")
-        if usage_data and isinstance(usage_data, dict):
+        if any(result.get(key) is not None for key in ("prompt_tokens", "completion_tokens", "total_tokens")):
            usage = Usage(
-                input_tokens=usage_data.get("prompt_tokens", 0),
-                output_tokens=usage_data.get("completion_tokens", 0),
-                total_tokens=usage_data.get("total_tokens", 0),
-                thought_tokens=usage_data.get("reasoning_tokens"),
-                cached_read_tokens=usage_data.get("cached_tokens"),
+                input_tokens=result.get("prompt_tokens", 0),
+                output_tokens=result.get("completion_tokens", 0),
+                total_tokens=result.get("total_tokens", 0),
+                thought_tokens=result.get("reasoning_tokens"),
+                cached_read_tokens=result.get("cache_read_tokens"),
            )

        stop_reason = "cancelled" if state.cancel_event and state.cancel_event.is_set() else "end_turn"
@@ -74,8 +74,11 @@ def _get_anthropic_max_output(model: str) -> int:
    model IDs (claude-sonnet-4-5-20250929) and variant suffixes (:1m, :fast)
    resolve correctly.  Longest-prefix match wins to avoid e.g. "claude-3-5"
    matching before "claude-3-5-sonnet".
+
+    Normalizes dots to hyphens so that model names like
+    ``anthropic/claude-opus-4.6`` match the ``claude-opus-4-6`` table key.
    """
-    m = model.lower()
+    m = model.lower().replace(".", "-")
    best_key = ""
    best_val = _ANTHROPIC_DEFAULT_OUTPUT_LIMIT
    for key, val in _ANTHROPIC_OUTPUT_LIMITS.items():
@@ -95,6 +98,15 @@ _COMMON_BETAS = [
    "interleaved-thinking-2025-05-14",
    "fine-grained-tool-streaming-2025-05-14",
 ]
+# MiniMax's Anthropic-compatible endpoints fail tool-use requests when
+# the fine-grained tool streaming beta is present.  Omit it so tool calls
+# fall back to the provider's default response path.
+_TOOL_STREAMING_BETA = "fine-grained-tool-streaming-2025-05-14"
+
+# Fast mode beta — enables the ``speed: "fast"`` request parameter for
+# significantly higher output token throughput on Opus 4.6 (~2.5x).
+# See https://platform.claude.com/docs/en/build-with-claude/fast-mode
+_FAST_MODE_BETA = "fast-mode-2026-02-01"

 # Additional beta headers required for OAuth/subscription auth.
 # Matches what Claude Code (and pi-ai / OpenCode) send.
@@ -163,6 +175,17 @@ def _is_oauth_token(key: str) -> bool:
    return True


+def _normalize_base_url_text(base_url) -> str:
+    """Normalize SDK/base transport URL values to a plain string for inspection.
+
+    Some client objects expose ``base_url`` as an ``httpx.URL`` instead of a raw
+    string.  Provider/auth detection should accept either shape.
+    """
+    if not base_url:
+        return ""
+    return str(base_url).strip()
+
+
 def _is_third_party_anthropic_endpoint(base_url: str | None) -> bool:
    """Return True for non-Anthropic endpoints using the Anthropic Messages API.

@@ -170,9 +193,10 @@ def _is_third_party_anthropic_endpoint(base_url: str | None) -> bool:
    with their own API keys via x-api-key, not Anthropic OAuth tokens. OAuth
    detection should be skipped for these endpoints.
    """
-    if not base_url:
+    normalized = _normalize_base_url_text(base_url)
+    if not normalized:
        return False  # No base_url = direct Anthropic API
-    normalized = base_url.rstrip("/").lower()
+    normalized = normalized.rstrip("/").lower()
    if "anthropic.com" in normalized:
        return False  # Direct Anthropic API — OAuth applies
    return True  # Any other endpoint is a third-party proxy
@@ -182,15 +206,29 @@ def _requires_bearer_auth(base_url: str | None) -> bool:
    """Return True for Anthropic-compatible providers that require Bearer auth.

    Some third-party /anthropic endpoints implement Anthropic's Messages API but
-    require Authorization: Bearer instead of Anthropic's native x-api-key header.
+    require Authorization: Bearer *** of Anthropic's native x-api-key header.
    MiniMax's global and China Anthropic-compatible endpoints follow this pattern.
    """
-    if not base_url:
+    normalized = _normalize_base_url_text(base_url)
+    if not normalized:
        return False
-    normalized = base_url.rstrip("/").lower()
+    normalized = normalized.rstrip("/").lower()
    return normalized.startswith(("https://api.minimax.io/anthropic", "https://api.minimaxi.com/anthropic"))


+def _common_betas_for_base_url(base_url: str | None) -> list[str]:
+    """Return the beta headers that are safe for the configured endpoint.
+
+    MiniMax's Anthropic-compatible endpoints (Bearer-auth) reject requests
+    that include Anthropic's ``fine-grained-tool-streaming`` beta — every
+    tool-use message triggers a connection error.  Strip that beta for
+    Bearer-auth endpoints while keeping all other betas intact.
+    """
+    if _requires_bearer_auth(base_url):
+        return [b for b in _COMMON_BETAS if b != _TOOL_STREAMING_BETA]
+    return _COMMON_BETAS
+
+
 def build_anthropic_client(api_key: str, base_url: str = None):
    """Create an Anthropic client, auto-detecting setup-tokens vs API keys.

@@ -203,13 +241,15 @@ def build_anthropic_client(api_key: str, base_url: str = None):
        )
    from httpx import Timeout

+    normalized_base_url = _normalize_base_url_text(base_url)
    kwargs = {
        "timeout": Timeout(timeout=900.0, connect=10.0),
    }
-    if base_url:
-        kwargs["base_url"] = base_url
+    if normalized_base_url:
+        kwargs["base_url"] = normalized_base_url
+    common_betas = _common_betas_for_base_url(normalized_base_url)

-    if _requires_bearer_auth(base_url):
+    if _requires_bearer_auth(normalized_base_url):
        # Some Anthropic-compatible providers (e.g. MiniMax) expect the API key in
        # Authorization: Bearer even for regular API keys. Route those endpoints
        # through auth_token so the SDK sends Bearer auth instead of x-api-key.
@@ -217,21 +257,21 @@ def build_anthropic_client(api_key: str, base_url: str = None):
        # not use Anthropic's sk-ant-api prefix and would otherwise be misread as
        # Anthropic OAuth/setup tokens.
        kwargs["auth_token"] = api_key
-        if _COMMON_BETAS:
-            kwargs["default_headers"] = {"anthropic-beta": ",".join(_COMMON_BETAS)}
+        if common_betas:
+            kwargs["default_headers"] = {"anthropic-beta": ",".join(common_betas)}
    elif _is_third_party_anthropic_endpoint(base_url):
        # Third-party proxies (Azure AI Foundry, AWS Bedrock, etc.) use their
        # own API keys with x-api-key auth. Skip OAuth detection — their keys
        # don't follow Anthropic's sk-ant-* prefix convention and would be
        # misclassified as OAuth tokens.
        kwargs["api_key"] = api_key
-        if _COMMON_BETAS:
-            kwargs["default_headers"] = {"anthropic-beta": ",".join(_COMMON_BETAS)}
+        if common_betas:
+            kwargs["default_headers"] = {"anthropic-beta": ",".join(common_betas)}
    elif _is_oauth_token(api_key):
        # OAuth access token / setup-token → Bearer auth + Claude Code identity.
        # Anthropic routes OAuth requests based on user-agent and headers;
        # without Claude Code's fingerprint, requests get intermittent 500s.
-        all_betas = _COMMON_BETAS + _OAUTH_ONLY_BETAS
+        all_betas = common_betas + _OAUTH_ONLY_BETAS
        kwargs["auth_token"] = api_key
        kwargs["default_headers"] = {
            "anthropic-beta": ",".join(all_betas),
@@ -241,8 +281,8 @@ def build_anthropic_client(api_key: str, base_url: str = None):
    else:
        # Regular API key → x-api-key header + common betas
        kwargs["api_key"] = api_key
-        if _COMMON_BETAS:
-            kwargs["default_headers"] = {"anthropic-beta": ",".join(_COMMON_BETAS)}
+        if common_betas:
+            kwargs["default_headers"] = {"anthropic-beta": ",".join(common_betas)}

    return _anthropic_sdk.Anthropic(**kwargs)

@@ -471,35 +511,6 @@ def _prefer_refreshable_claude_code_token(env_token: str, creds: Optional[Dict[s
    return None


-def get_anthropic_token_source(token: Optional[str] = None) -> str:
-    """Best-effort source classification for an Anthropic credential token."""
-    token = (token or "").strip()
-    if not token:
-        return "none"
-
-    env_token = os.getenv("ANTHROPIC_TOKEN", "").strip()
-    if env_token and env_token == token:
-        return "anthropic_token_env"
-
-    cc_env_token = os.getenv("CLAUDE_CODE_OAUTH_TOKEN", "").strip()
-    if cc_env_token and cc_env_token == token:
-        return "claude_code_oauth_token_env"
-
-    creds = read_claude_code_credentials()
-    if creds and creds.get("accessToken") == token:
-        return str(creds.get("source") or "claude_code_credentials")
-
-    managed_key = read_claude_managed_key()
-    if managed_key and managed_key == token:
-        return "claude_json_primary_api_key"
-
-    api_key = os.getenv("ANTHROPIC_API_KEY", "").strip()
-    if api_key and api_key == token:
-        return "anthropic_api_key_env"
-
-    return "unknown"
-
-
 def resolve_anthropic_token() -> Optional[str]:
    """Resolve an Anthropic token from all available sources.

@@ -706,21 +717,6 @@ def run_hermes_oauth_login_pure() -> Optional[Dict[str, Any]]:
    }


-def _save_hermes_oauth_credentials(access_token: str, refresh_token: str, expires_at_ms: int) -> None:
-    """Save OAuth credentials to ~/.hermes/.anthropic_oauth.json."""
-    data = {
-        "accessToken": access_token,
-        "refreshToken": refresh_token,
-        "expiresAt": expires_at_ms,
-    }
-    try:
-        _HERMES_OAUTH_FILE.parent.mkdir(parents=True, exist_ok=True)
-        _HERMES_OAUTH_FILE.write_text(json.dumps(data, indent=2), encoding="utf-8")
-        _HERMES_OAUTH_FILE.chmod(0o600)
-    except (OSError, IOError) as e:
-        logger.debug("Failed to save Hermes OAuth credentials: %s", e)
-
-
 def read_hermes_oauth_credentials() -> Optional[Dict[str, Any]]:
    """Read Hermes-managed OAuth credentials from ~/.hermes/.anthropic_oauth.json."""
    if _HERMES_OAUTH_FILE.exists():
@@ -769,39 +765,6 @@ def _sanitize_tool_id(tool_id: str) -> str:
    return sanitized or "tool_0"


-def _convert_openai_image_part_to_anthropic(part: Dict[str, Any]) -> Optional[Dict[str, Any]]:
-    """Convert an OpenAI-style image block to Anthropic's image source format."""
-    image_data = part.get("image_url", {})
-    url = image_data.get("url", "") if isinstance(image_data, dict) else str(image_data)
-    if not isinstance(url, str) or not url.strip():
-        return None
-    url = url.strip()
-
-    if url.startswith("data:"):
-        header, sep, data = url.partition(",")
-        if sep and ";base64" in header:
-            media_type = header[5:].split(";", 1)[0] or "image/png"
-            return {
-                "type": "image",
-                "source": {
-                    "type": "base64",
-                    "media_type": media_type,
-                    "data": data,
-                },
-            }
-
-    if url.startswith(("http://", "https://")):
-        return {
-            "type": "image",
-            "source": {
-                "type": "url",
-                "url": url,
-            },
-        }
-
-    return None
-
-
 def convert_tools_to_anthropic(tools: List[Dict]) -> List[Dict]:
    """Convert OpenAI tool definitions to Anthropic format."""
    if not tools:
@@ -942,12 +905,18 @@ def _convert_content_to_anthropic(content: Any) -> Any:

 def convert_messages_to_anthropic(
    messages: List[Dict],
+    base_url: str | None = None,
 ) -> Tuple[Optional[Any], List[Dict]]:
    """Convert OpenAI-format messages to Anthropic format.

    Returns (system_prompt, anthropic_messages).
    System messages are extracted since Anthropic takes them as a separate param.
    system_prompt is a string or list of content blocks (when cache_control present).
+
+    When *base_url* is provided and points to a third-party Anthropic-compatible
+    endpoint, all thinking block signatures are stripped.  Signatures are
+    Anthropic-proprietary — third-party endpoints cannot validate them and will
+    reject them with HTTP 400 "Invalid signature in thinking block".
    """
    system = None
    result = []
@@ -1102,7 +1071,15 @@ def convert_messages_to_anthropic(
                        curr_content = [{"type": "text", "text": curr_content}]
                    fixed[-1]["content"] = prev_content + curr_content
            else:
-                # Consecutive assistant messages — merge text content
+                # Consecutive assistant messages — merge text content.
+                # Drop thinking blocks from the *second* message: their
+                # signature was computed against a different turn boundary
+                # and becomes invalid once merged.
+                if isinstance(m["content"], list):
+                    m["content"] = [
+                        b for b in m["content"]
+                        if not (isinstance(b, dict) and b.get("type") in ("thinking", "redacted_thinking"))
+                    ]
                prev_blocks = fixed[-1]["content"]
                curr_blocks = m["content"]
                if isinstance(prev_blocks, list) and isinstance(curr_blocks, list):
@@ -1120,6 +1097,79 @@ def convert_messages_to_anthropic(
            fixed.append(m)
    result = fixed

+    # ── Thinking block signature management ──────────────────────────
+    # Anthropic signs thinking blocks against the full turn content.
+    # Any upstream mutation (context compression, session truncation,
+    # orphan stripping, message merging) invalidates the signature,
+    # causing HTTP 400 "Invalid signature in thinking block".
+    #
+    # Signatures are Anthropic-proprietary.  Third-party endpoints
+    # (MiniMax, Azure AI Foundry, self-hosted proxies) cannot validate
+    # them and will reject them outright.  When targeting a third-party
+    # endpoint, strip ALL thinking/redacted_thinking blocks from every
+    # assistant message — the third-party will generate its own
+    # thinking blocks if it supports extended thinking.
+    #
+    # For direct Anthropic (strategy following clawdbot/OpenClaw):
+    # 1. Strip thinking/redacted_thinking from all assistant messages
+    #    EXCEPT the last one — preserves reasoning continuity on the
+    #    current tool-use chain while avoiding stale signature errors.
+    # 2. Downgrade unsigned thinking blocks (no signature) to text —
+    #    Anthropic can't validate them and will reject them.
+    # 3. Strip cache_control from thinking/redacted_thinking blocks —
+    #    cache markers can interfere with signature validation.
+    _THINKING_TYPES = frozenset(("thinking", "redacted_thinking"))
+    _is_third_party = _is_third_party_anthropic_endpoint(base_url)
+
+    last_assistant_idx = None
+    for i in range(len(result) - 1, -1, -1):
+        if result[i].get("role") == "assistant":
+            last_assistant_idx = i
+            break
+
+    for idx, m in enumerate(result):
+        if m.get("role") != "assistant" or not isinstance(m.get("content"), list):
+            continue
+
+        if _is_third_party or idx != last_assistant_idx:
+            # Third-party endpoint: strip ALL thinking blocks from every
+            # assistant message — signatures are Anthropic-proprietary.
+            # Direct Anthropic: strip from non-latest assistant messages only.
+            stripped = [
+                b for b in m["content"]
+                if not (isinstance(b, dict) and b.get("type") in _THINKING_TYPES)
+            ]
+            m["content"] = stripped or [{"type": "text", "text": "(thinking elided)"}]
+        else:
+            # Latest assistant on direct Anthropic: keep signed thinking
+            # blocks for reasoning continuity; downgrade unsigned ones to
+            # plain text.
+            new_content = []
+            for b in m["content"]:
+                if not isinstance(b, dict) or b.get("type") not in _THINKING_TYPES:
+                    new_content.append(b)
+                    continue
+                if b.get("type") == "redacted_thinking":
+                    # Redacted blocks use 'data' for the signature payload
+                    if b.get("data"):
+                        new_content.append(b)
+                    # else: drop — no data means it can't be validated
+                elif b.get("signature"):
+                    # Signed thinking block — keep it
+                    new_content.append(b)
+                else:
+                    # Unsigned thinking — downgrade to text so it's not lost
+                    thinking_text = b.get("thinking", "")
+                    if thinking_text:
+                        new_content.append({"type": "text", "text": thinking_text})
+            m["content"] = new_content or [{"type": "text", "text": "(empty)"}]
+
+        # Strip cache_control from any remaining thinking/redacted_thinking
+        # blocks — cache markers interfere with signature validation.
+        for b in m["content"]:
+            if isinstance(b, dict) and b.get("type") in _THINKING_TYPES:
+                b.pop("cache_control", None)
+
    return system, result


@@ -1133,28 +1183,58 @@ def build_anthropic_kwargs(
    is_oauth: bool = False,
    preserve_dots: bool = False,
    context_length: Optional[int] = None,
+    base_url: str | None = None,
+    fast_mode: bool = False,
 ) -> Dict[str, Any]:
    """Build kwargs for anthropic.messages.create().

-    When *max_tokens* is None, the model's native output limit is used
-    (e.g. 128K for Opus 4.6, 64K for Sonnet 4.6).  If *context_length*
-    is provided, the effective limit is clamped so it doesn't exceed
-    the context window.
+    Naming note — two distinct concepts, easily confused:
+      max_tokens     = OUTPUT token cap for a single response.
+                       Anthropic's API calls this "max_tokens" but it only
+                       limits the *output*.  Anthropic's own native SDK
+                       renamed it "max_output_tokens" for clarity.
+      context_length = TOTAL context window (input tokens + output tokens).
+                       The API enforces: input_tokens + max_tokens ≤ context_length.
+                       Stored on the ContextCompressor; reduced on overflow errors.
+
+    When *max_tokens* is None the model's native output ceiling is used
+    (e.g. 128K for Opus 4.6, 64K for Sonnet 4.6).
+
+    When *context_length* is provided and the model's native output ceiling
+    exceeds it (e.g. a local endpoint with an 8K window), the output cap is
+    clamped to context_length − 1.  This only kicks in for unusually small
+    context windows; for full-size models the native output cap is always
+    smaller than the context window so no clamping happens.
+    NOTE: this clamping does not account for prompt size — if the prompt is
+    large, Anthropic may still reject the request.  The caller must detect
+    "max_tokens too large given prompt" errors and retry with a smaller cap
+    (see parse_available_output_tokens_from_error + _ephemeral_max_output_tokens).

    When *is_oauth* is True, applies Claude Code compatibility transforms:
    system prompt prefix, tool name prefixing, and prompt sanitization.

    When *preserve_dots* is True, model name dots are not converted to hyphens
    (for Alibaba/DashScope anthropic-compatible endpoints: qwen3.5-plus).
+
+    When *base_url* points to a third-party Anthropic-compatible endpoint,
+    thinking block signatures are stripped (they are Anthropic-proprietary).
+
+    When *fast_mode* is True, adds ``speed: "fast"`` and the fast-mode beta
+    header for ~2.5x faster output throughput on Opus 4.6.  Currently only
+    supported on native Anthropic endpoints (not third-party compatible ones).
    """
-    system, anthropic_messages = convert_messages_to_anthropic(messages)
+    system, anthropic_messages = convert_messages_to_anthropic(messages, base_url=base_url)
    anthropic_tools = convert_tools_to_anthropic(tools) if tools else []

    model = normalize_model_name(model, preserve_dots=preserve_dots)
+    # effective_max_tokens = output cap for this call (≠ total context window)
    effective_max_tokens = max_tokens or _get_anthropic_max_output(model)

-    # Clamp to context window if the user set a lower context_length
-    # (e.g. custom endpoint with limited capacity).
+    # Clamp output cap to fit inside the total context window.
+    # Only matters for small custom endpoints where context_length < native
+    # output ceiling.  For standard Anthropic models context_length (e.g.
+    # 200K) is always larger than the output ceiling (e.g. 128K), so this
+    # branch is not taken.
    if context_length and effective_max_tokens > context_length:
        effective_max_tokens = max(context_length - 1, 1)

@@ -1224,9 +1304,9 @@ def build_anthropic_kwargs(
    # Map reasoning_config to Anthropic's thinking parameter.
    # Claude 4.6 models use adaptive thinking + output_config.effort.
    # Older models use manual thinking with budget_tokens.
-    # Haiku models do NOT support extended thinking at all — skip entirely.
+    # Haiku and MiniMax models do NOT support extended thinking — skip entirely.
    if reasoning_config and isinstance(reasoning_config, dict):
-        if reasoning_config.get("enabled") is not False and "haiku" not in model.lower():
+        if reasoning_config.get("enabled") is not False and "haiku" not in model.lower() and "minimax" not in model.lower():
            effort = str(reasoning_config.get("effort", "medium")).lower()
            budget = THINKING_BUDGET.get(effort, 8000)
            if _supports_adaptive_thinking(model):
@@ -1240,6 +1320,20 @@ def build_anthropic_kwargs(
                kwargs["temperature"] = 1
                kwargs["max_tokens"] = max(effective_max_tokens, budget + 4096)

+    # ── Fast mode (Opus 4.6 only) ────────────────────────────────────
+    # Adds speed:"fast" + the fast-mode beta header for ~2.5x output speed.
+    # Only for native Anthropic endpoints — third-party providers would
+    # reject the unknown beta header and speed parameter.
+    if fast_mode and not _is_third_party_anthropic_endpoint(base_url):
+        kwargs["speed"] = "fast"
+        # Build extra_headers with ALL applicable betas (the per-request
+        # extra_headers override the client-level anthropic-beta header).
+        betas = list(_common_betas_for_base_url(base_url))
+        if is_oauth:
+            betas.extend(_OAUTH_ONLY_BETAS)
+        betas.append(_FAST_MODE_BETA)
+        kwargs["extra_headers"] = {"anthropic-beta": ",".join(betas)}
+
    return kwargs


@@ -1301,4 +1395,4 @@ def normalize_anthropic_response(
            reasoning_details=reasoning_details or None,
        ),
        finish_reason,
-    )
+    )
@@ -59,13 +59,48 @@ from hermes_constants import OPENROUTER_BASE_URL

 logger = logging.getLogger(__name__)

+_PROVIDER_ALIASES = {
+    "google": "gemini",
+    "google-gemini": "gemini",
+    "google-ai-studio": "gemini",
+    "glm": "zai",
+    "z-ai": "zai",
+    "z.ai": "zai",
+    "zhipu": "zai",
+    "kimi": "kimi-coding",
+    "moonshot": "kimi-coding",
+    "minimax-china": "minimax-cn",
+    "minimax_cn": "minimax-cn",
+    "claude": "anthropic",
+    "claude-code": "anthropic",
+}
+
+
+def _normalize_aux_provider(provider: Optional[str], *, for_vision: bool = False) -> str:
+    normalized = (provider or "auto").strip().lower()
+    if normalized.startswith("custom:"):
+        suffix = normalized.split(":", 1)[1].strip()
+        if not suffix:
+            return "custom"
+        normalized = suffix if not for_vision else "custom"
+    if normalized == "codex":
+        return "openai-codex"
+    if normalized == "main":
+        # Resolve to the user's actual main provider so named custom providers
+        # and non-aggregator providers (DeepSeek, Alibaba, etc.) work correctly.
+        main_prov = _read_main_provider()
+        if main_prov and main_prov not in ("auto", "main", ""):
+            return main_prov
+        return "custom"
+    return _PROVIDER_ALIASES.get(normalized, normalized)
+
 # Default auxiliary models for direct API-key providers (cheap/fast for side tasks)
 _API_KEY_PROVIDER_AUX_MODELS: Dict[str, str] = {
    "gemini": "gemini-3-flash-preview",
    "zai": "glm-4.5-flash",
    "kimi-coding": "kimi-k2-turbo-preview",
-    "minimax": "MiniMax-M2.7-highspeed",
-    "minimax-cn": "MiniMax-M2.7-highspeed",
+    "minimax": "MiniMax-M2.7",
+    "minimax-cn": "MiniMax-M2.7",
    "anthropic": "claude-haiku-4-5-20251001",
    "ai-gateway": "google/gemini-3-flash",
    "opencode-zen": "gemini-3-flash",
@@ -92,6 +127,7 @@ auxiliary_is_nous: bool = False
 _OPENROUTER_MODEL = "google/gemini-3-flash-preview"
 _NOUS_MODEL = "google/gemini-3-flash-preview"
 _NOUS_FREE_TIER_VISION_MODEL = "xiaomi/mimo-v2-omni"
+_NOUS_FREE_TIER_AUX_MODEL = "xiaomi/mimo-v2-pro"
 _NOUS_DEFAULT_BASE_URL = "https://inference-api.nousresearch.com/v1"
 _ANTHROPIC_DEFAULT_BASE_URL = "https://api.anthropic.com"
 _AUTH_JSON_PATH = get_hermes_home() / "auth.json"
@@ -105,6 +141,23 @@ _CODEX_AUX_MODEL = "gpt-5.2-codex"
 _CODEX_AUX_BASE_URL = "https://chatgpt.com/backend-api/codex"


+def _to_openai_base_url(base_url: str) -> str:
+    """Normalize an Anthropic-style base URL to OpenAI-compatible format.
+
+    Some providers (MiniMax, MiniMax-CN) expose an ``/anthropic`` endpoint for
+    the Anthropic Messages API and a separate ``/v1`` endpoint for OpenAI chat
+    completions.  The auxiliary client uses the OpenAI SDK, so it must hit the
+    ``/v1`` surface.  Passing the raw ``inference_base_url`` causes requests to
+    land on ``/anthropic/chat/completions`` — a 404.
+    """
+    url = str(base_url or "").strip().rstrip("/")
+    if url.endswith("/anthropic"):
+        rewritten = url[: -len("/anthropic")] + "/v1"
+        logger.debug("Auxiliary client: rewrote base URL %s → %s", url, rewritten)
+        return rewritten
+    return url
+
+
 def _select_pool_entry(provider: str) -> Tuple[bool, Optional[Any]]:
    """Return (pool_exists_for_provider, selected_entry)."""
    try:
@@ -576,11 +629,19 @@ def _nous_base_url() -> str:


 def _read_codex_access_token() -> Optional[str]:
-    """Read a valid, non-expired Codex OAuth access token from Hermes auth store."""
+    """Read a valid, non-expired Codex OAuth access token from Hermes auth store.
+
+    If a credential pool exists but currently has no selectable runtime entry
+    (for example all pool slots are marked exhausted), fall back to the
+    profile's auth.json token instead of hard-failing. This keeps explicit
+    fallback-to-Codex working when the pool state is stale but the stored OAuth
+    token is still valid.
+    """
    pool_present, entry = _select_pool_entry("openai-codex")
    if pool_present:
        token = _pool_runtime_api_key(entry)
-        return token or None
+        if token:
+            return token

    try:
        from hermes_cli.auth import _read_codex_tokens
@@ -626,6 +687,15 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
        if pconfig.auth_type != "api_key":
            continue
        if provider_id == "anthropic":
+            # Only try anthropic when the user has explicitly configured it.
+            # Without this gate, Claude Code credentials get silently used
+            # as auxiliary fallback when the user's primary provider fails.
+            try:
+                from hermes_cli.auth import is_provider_explicitly_configured
+                if not is_provider_explicitly_configured("anthropic"):
+                    continue
+            except ImportError:
+                pass
            return _try_anthropic()

        pool_present, entry = _select_pool_entry(provider_id)
@@ -634,12 +704,14 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
            if not api_key:
                continue

-            base_url = _pool_runtime_base_url(entry, pconfig.inference_base_url) or pconfig.inference_base_url
+            base_url = _to_openai_base_url(
+                _pool_runtime_base_url(entry, pconfig.inference_base_url) or pconfig.inference_base_url
+            )
            model = _API_KEY_PROVIDER_AUX_MODELS.get(provider_id, "default")
            logger.debug("Auxiliary text client: %s (%s) via pool", pconfig.name, model)
            extra = {}
            if "api.kimi.com" in base_url.lower():
-                extra["default_headers"] = {"User-Agent": "KimiCLI/1.0"}
+                extra["default_headers"] = {"User-Agent": "KimiCLI/1.30.0"}
            elif "api.githubcopilot.com" in base_url.lower():
                from hermes_cli.models import copilot_default_headers

@@ -651,12 +723,14 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
        if not api_key:
            continue

-        base_url = str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
+        base_url = _to_openai_base_url(
+            str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
+        )
        model = _API_KEY_PROVIDER_AUX_MODELS.get(provider_id, "default")
        logger.debug("Auxiliary text client: %s (%s)", pconfig.name, model)
        extra = {}
        if "api.kimi.com" in base_url.lower():
-            extra["default_headers"] = {"User-Agent": "KimiCLI/1.0"}
+            extra["default_headers"] = {"User-Agent": "KimiCLI/1.30.0"}
        elif "api.githubcopilot.com" in base_url.lower():
            from hermes_cli.models import copilot_default_headers

@@ -713,7 +787,7 @@ def _try_openrouter() -> Tuple[Optional[OpenAI], Optional[str]]:
                   default_headers=_OR_HEADERS), _OPENROUTER_MODEL


-def _try_nous() -> Tuple[Optional[OpenAI], Optional[str]]:
+def _try_nous(vision: bool = False) -> Tuple[Optional[OpenAI], Optional[str]]:
    nous = _read_nous_auth()
    if not nous:
        return None, None
@@ -725,12 +799,13 @@ def _try_nous() -> Tuple[Optional[OpenAI], Optional[str]]:
    else:
        model = _NOUS_MODEL
    # Free-tier users can't use paid auxiliary models — use the free
-    # multimodal model instead so vision/browser-vision still works.
+    # models instead: mimo-v2-omni for vision, mimo-v2-pro for text tasks.
    try:
        from hermes_cli.models import check_nous_free_tier
        if check_nous_free_tier():
-            model = _NOUS_FREE_TIER_VISION_MODEL
-            logger.debug("Free-tier Nous account — using %s for auxiliary/vision", model)
+            model = _NOUS_FREE_TIER_VISION_MODEL if vision else _NOUS_FREE_TIER_AUX_MODEL
+            logger.debug("Free-tier Nous account — using %s for auxiliary/%s",
+                         model, "vision" if vision else "text")
    except Exception:
        pass
    return (
@@ -836,9 +911,13 @@ def _try_codex() -> Tuple[Optional[Any], Optional[str]]:
    pool_present, entry = _select_pool_entry("openai-codex")
    if pool_present:
        codex_token = _pool_runtime_api_key(entry)
-        if not codex_token:
-            return None, None
-        base_url = _pool_runtime_base_url(entry, _CODEX_AUX_BASE_URL) or _CODEX_AUX_BASE_URL
+        if codex_token:
+            base_url = _pool_runtime_base_url(entry, _CODEX_AUX_BASE_URL) or _CODEX_AUX_BASE_URL
+        else:
+            codex_token = _read_codex_access_token()
+            if not codex_token:
+                return None, None
+            base_url = _CODEX_AUX_BASE_URL
    else:
        codex_token = _read_codex_access_token()
        if not codex_token:
@@ -897,40 +976,6 @@ def _try_anthropic() -> Tuple[Optional[Any], Optional[str]]:
    return AnthropicAuxiliaryClient(real_client, model, token, base_url, is_oauth=is_oauth), model


-def _resolve_forced_provider(forced: str) -> Tuple[Optional[OpenAI], Optional[str]]:
-    """Resolve a specific forced provider.  Returns (None, None) if creds missing."""
-    if forced == "openrouter":
-        client, model = _try_openrouter()
-        if client is None:
-            logger.warning("auxiliary.provider=openrouter but OPENROUTER_API_KEY not set")
-        return client, model
-
-    if forced == "nous":
-        client, model = _try_nous()
-        if client is None:
-            logger.warning("auxiliary.provider=nous but Nous Portal not configured (run: hermes auth)")
-        return client, model
-
-    if forced == "codex":
-        client, model = _try_codex()
-        if client is None:
-            logger.warning("auxiliary.provider=codex but no Codex OAuth token found (run: hermes model)")
-        return client, model
-
-    if forced == "main":
-        # "main" = skip OpenRouter/Nous, use the main chat model's credentials.
-        for try_fn in (_try_custom_endpoint, _try_codex, _resolve_api_key_provider):
-            client, model = try_fn()
-            if client is not None:
-                return client, model
-        logger.warning("auxiliary.provider=main but no main endpoint credentials found")
-        return None, None
-
-    # Unknown provider name — fall through to auto
-    logger.warning("Unknown auxiliary.provider=%r, falling back to auto", forced)
-    return None, None
-
-
 _AUTO_PROVIDER_LABELS = {
    "_try_openrouter": "openrouter",
    "_try_nous": "nous",
@@ -977,6 +1022,32 @@ def _is_payment_error(exc: Exception) -> bool:
    return False


+def _is_connection_error(exc: Exception) -> bool:
+    """Detect connection/network errors that warrant provider fallback.
+
+    Returns True for errors indicating the provider endpoint is unreachable
+    (DNS failure, connection refused, TLS errors, timeouts).  These are
+    distinct from API errors (4xx/5xx) which indicate the provider IS
+    reachable but returned an error.
+    """
+    from openai import APIConnectionError, APITimeoutError
+
+    if isinstance(exc, (APIConnectionError, APITimeoutError)):
+        return True
+    # urllib3 / httpx / httpcore connection errors
+    err_type = type(exc).__name__
+    if any(kw in err_type for kw in ("Connection", "Timeout", "DNS", "SSL")):
+        return True
+    err_lower = str(exc).lower()
+    if any(kw in err_lower for kw in (
+        "connection refused", "name or service not known",
+        "no route to host", "network is unreachable",
+        "timed out", "connection reset",
+    )):
+        return True
+    return False
+
+
 def _try_payment_fallback(
    failed_provider: str,
    task: str = None,
@@ -1041,7 +1112,7 @@ def _resolve_auto() -> Tuple[Optional[OpenAI], Optional[str]]:
    main_model = _read_main_model()
    if (main_provider and main_model
            and main_provider not in _AGGREGATOR_PROVIDERS
-            and main_provider not in ("auto", "custom", "")):
+            and main_provider not in ("auto", "")):
        client, resolved = resolve_provider_client(main_provider, main_model)
        if client is not None:
            logger.info("Auxiliary auto-detect: using main provider %s (%s)",
@@ -1099,7 +1170,7 @@ def _to_async_client(sync_client, model: str):

        async_kwargs["default_headers"] = copilot_default_headers()
    elif "api.kimi.com" in base_lower:
-        async_kwargs["default_headers"] = {"User-Agent": "KimiCLI/1.0"}
+        async_kwargs["default_headers"] = {"User-Agent": "KimiCLI/1.30.0"}
    return AsyncOpenAI(**async_kwargs), model


@@ -1138,11 +1209,7 @@ def resolve_provider_client(
        (client, resolved_model) or (None, None) if auth is unavailable.
    """
    # Normalise aliases
-    provider = (provider or "auto").strip().lower()
-    if provider == "codex":
-        provider = "openai-codex"
-    if provider == "main":
-        provider = "custom"
+    provider = _normalize_aux_provider(provider)

    # ── Auto: try all providers in priority order ────────────────────
    if provider == "auto":
@@ -1223,7 +1290,13 @@ def resolve_provider_client(
                )
                return None, None
            final_model = model or _read_main_model() or "gpt-4o-mini"
-            client = OpenAI(api_key=custom_key, base_url=custom_base)
+            extra = {}
+            if "api.kimi.com" in custom_base.lower():
+                extra["default_headers"] = {"User-Agent": "KimiCLI/1.30.0"}
+            elif "api.githubcopilot.com" in custom_base.lower():
+                from hermes_cli.models import copilot_default_headers
+                extra["default_headers"] = copilot_default_headers()
+            client = OpenAI(api_key=custom_key, base_url=custom_base, **extra)
            return (_to_async_client(client, final_model) if async_mode
                    else (client, final_model))
        # Try custom first, then codex, then API-key providers
@@ -1238,6 +1311,28 @@ def resolve_provider_client(
                       "but no endpoint credentials found")
        return None, None

+    # ── Named custom providers (config.yaml custom_providers list) ───
+    try:
+        from hermes_cli.runtime_provider import _get_named_custom_provider
+        custom_entry = _get_named_custom_provider(provider)
+        if custom_entry:
+            custom_base = custom_entry.get("base_url", "").strip()
+            custom_key = custom_entry.get("api_key", "").strip() or "no-key-required"
+            if custom_base:
+                final_model = model or _read_main_model() or "gpt-4o-mini"
+                client = OpenAI(api_key=custom_key, base_url=custom_base)
+                logger.debug(
+                    "resolve_provider_client: named custom provider %r (%s)",
+                    provider, final_model)
+                return (_to_async_client(client, final_model) if async_mode
+                        else (client, final_model))
+            logger.warning(
+                "resolve_provider_client: named custom provider %r has no base_url",
+                provider)
+            return None, None
+    except ImportError:
+        pass
+
    # ── API-key providers from PROVIDER_REGISTRY ─────────────────────
    try:
        from hermes_cli.auth import PROVIDER_REGISTRY, resolve_api_key_provider_credentials
@@ -1270,7 +1365,9 @@ def resolve_provider_client(
                         provider, ", ".join(tried_sources))
            return None, None

-        base_url = str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
+        base_url = _to_openai_base_url(
+            str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
+        )

        default_model = _API_KEY_PROVIDER_AUX_MODELS.get(provider, "")
        final_model = model or default_model
@@ -1278,7 +1375,7 @@ def resolve_provider_client(
        # Provider-specific headers
        headers = {}
        if "api.kimi.com" in base_url.lower():
-            headers["User-Agent"] = "KimiCLI/1.0"
+            headers["User-Agent"] = "KimiCLI/1.30.0"
        elif "api.githubcopilot.com" in base_url.lower():
            from hermes_cli.models import copilot_default_headers

@@ -1347,19 +1444,11 @@ def get_async_text_auxiliary_client(task: str = ""):
 _VISION_AUTO_PROVIDER_ORDER = (
    "openrouter",
    "nous",
-    "openai-codex",
-    "anthropic",
-    "custom",
 )


 def _normalize_vision_provider(provider: Optional[str]) -> str:
-    provider = (provider or "auto").strip().lower()
-    if provider == "codex":
-        return "openai-codex"
-    if provider == "main":
-        return "custom"
-    return provider
+    return _normalize_aux_provider(provider, for_vision=True)


 def _resolve_strict_vision_backend(provider: str) -> Tuple[Optional[Any], Optional[str]]:
@@ -1367,7 +1456,7 @@ def _resolve_strict_vision_backend(provider: str) -> Tuple[Optional[Any], Option
    if provider == "openrouter":
        return _try_openrouter()
    if provider == "nous":
-        return _try_nous()
+        return _try_nous(vision=True)
    if provider == "openai-codex":
        return _try_codex()
    if provider == "anthropic":
@@ -1381,36 +1470,29 @@ def _strict_vision_backend_available(provider: str) -> bool:
    return _resolve_strict_vision_backend(provider)[0] is not None


-def _preferred_main_vision_provider() -> Optional[str]:
-    """Return the selected main provider when it is also a supported vision backend."""
-    try:
-        from hermes_cli.config import load_config
-
-        config = load_config()
-        model_cfg = config.get("model", {})
-        if isinstance(model_cfg, dict):
-            provider = _normalize_vision_provider(model_cfg.get("provider", ""))
-            if provider in _VISION_AUTO_PROVIDER_ORDER:
-                return provider
-    except Exception:
-        pass
-    return None
-
-
 def get_available_vision_backends() -> List[str]:
    """Return the currently available vision backends in auto-selection order.

-    This is the single source of truth for setup, tool gating, and runtime
-    auto-routing of vision tasks. The selected main provider is preferred when
-    it is also a known-good vision backend; otherwise Hermes falls back through
-    the standard conservative order.
+    Order: active provider → OpenRouter → Nous → stop.  This is the single
+    source of truth for setup, tool gating, and runtime auto-routing of
+    vision tasks.
    """
-    ordered = list(_VISION_AUTO_PROVIDER_ORDER)
-    preferred = _preferred_main_vision_provider()
-    if preferred in ordered:
-        ordered.remove(preferred)
-        ordered.insert(0, preferred)
-    return [provider for provider in ordered if _strict_vision_backend_available(provider)]
+    available: List[str] = []
+    # 1. Active provider — if the user configured a provider, try it first.
+    main_provider = _read_main_provider()
+    if main_provider and main_provider not in ("auto", ""):
+        if main_provider in _VISION_AUTO_PROVIDER_ORDER:
+            if _strict_vision_backend_available(main_provider):
+                available.append(main_provider)
+        else:
+            client, _ = resolve_provider_client(main_provider, _read_main_model())
+            if client is not None:
+                available.append(main_provider)
+    # 2. OpenRouter, 3. Nous — skip if already covered by main provider.
+    for p in _VISION_AUTO_PROVIDER_ORDER:
+        if p not in available and _strict_vision_backend_available(p):
+            available.append(p)
+    return available


 def resolve_vision_provider_client(
@@ -1455,16 +1537,39 @@ def resolve_vision_provider_client(
        return "custom", client, final_model

    if requested == "auto":
-        ordered = list(_VISION_AUTO_PROVIDER_ORDER)
-        preferred = _preferred_main_vision_provider()
-        if preferred in ordered:
-            ordered.remove(preferred)
-            ordered.insert(0, preferred)
+        # Vision auto-detection order:
+        #   1. Active provider + model (user's main chat config)
+        #   2. OpenRouter  (known vision-capable default model)
+        #   3. Nous Portal (known vision-capable default model)
+        #   4. Stop
+        main_provider = _read_main_provider()
+        main_model = _read_main_model()
+        if main_provider and main_provider not in ("auto", ""):
+            if main_provider in _VISION_AUTO_PROVIDER_ORDER:
+                # Known strict backend — use its defaults.
+                sync_client, default_model = _resolve_strict_vision_backend(main_provider)
+                if sync_client is not None:
+                    return _finalize(main_provider, sync_client, default_model)
+            else:
+                # Exotic provider (DeepSeek, Alibaba, named custom, etc.)
+                rpc_client, rpc_model = resolve_provider_client(
+                    main_provider, main_model)
+                if rpc_client is not None:
+                    logger.info(
+                        "Vision auto-detect: using active provider %s (%s)",
+                        main_provider, rpc_model or main_model,
+                    )
+                    return _finalize(
+                        main_provider, rpc_client, rpc_model or main_model)

-        for candidate in ordered:
+        # Fall back through aggregators.
+        for candidate in _VISION_AUTO_PROVIDER_ORDER:
+            if candidate == main_provider:
+                continue  # already tried above
            sync_client, default_model = _resolve_strict_vision_backend(candidate)
            if sync_client is not None:
                return _finalize(candidate, sync_client, default_model)
+
        logger.debug("Auxiliary vision client: none available")
        return None, None, None

@@ -1478,18 +1583,6 @@ def resolve_vision_provider_client(
    return requested, client, final_model


-def get_vision_auxiliary_client() -> Tuple[Optional[OpenAI], Optional[str]]:
-    """Return (client, default_model_slug) for vision/multimodal auxiliary tasks."""
-    _, client, final_model = resolve_vision_provider_client(async_mode=False)
-    return client, final_model
-
-
-def get_async_vision_auxiliary_client():
-    """Return (async_client, model_slug) for async vision consumers."""
-    _, client, final_model = resolve_vision_provider_client(async_mode=True)
-    return client, final_model
-
-
 def get_auxiliary_extra_body() -> dict:
    """Return extra_body kwargs for auxiliary API calls.
    
@@ -1979,7 +2072,18 @@ def call_llm(
        # try alternative providers instead of giving up.  This handles the
        # common case where a user runs out of OpenRouter credits but has
        # Codex OAuth or another provider available.
-        if _is_payment_error(first_err):
+        #
+        # ── Connection error fallback ────────────────────────────────
+        # When a provider endpoint is unreachable (DNS failure, connection
+        # refused, timeout), try alternative providers.  This handles stale
+        # Codex/OAuth tokens that authenticate but whose endpoint is down,
+        # and providers the user never configured that got picked up by
+        # the auto-detection chain.
+        should_fallback = _is_payment_error(first_err) or _is_connection_error(first_err)
+        if should_fallback:
+            reason = "payment error" if _is_payment_error(first_err) else "connection error"
+            logger.info("Auxiliary %s: %s on %s (%s), trying fallback",
+                        task or "call", reason, resolved_provider, first_err)
            fb_client, fb_model, fb_label = _try_payment_fallback(
                resolved_provider, task)
            if fb_client is not None:
@@ -1,114 +0,0 @@
-"""BuiltinMemoryProvider — wraps MEMORY.md / USER.md as a MemoryProvider.
-
-Always registered as the first provider. Cannot be disabled or removed.
-This is the existing Hermes memory system exposed through the provider
-interface for compatibility with the MemoryManager.
-
-The actual storage logic lives in tools/memory_tool.py (MemoryStore).
-This provider is a thin adapter that delegates to MemoryStore and
-exposes the memory tool schema.
-"""
-
-from __future__ import annotations
-
-import json
-import logging
-from typing import Any, Dict, List
-
-from agent.memory_provider import MemoryProvider
-from tools.registry import tool_error
-
-logger = logging.getLogger(__name__)
-
-
-class BuiltinMemoryProvider(MemoryProvider):
-    """Built-in file-backed memory (MEMORY.md + USER.md).
-
-    Always active, never disabled by other providers. The `memory` tool
-    is handled by run_agent.py's agent-level tool interception (not through
-    the normal registry), so get_tool_schemas() returns an empty list —
-    the memory tool is already wired separately.
-    """
-
-    def __init__(
-        self,
-        memory_store=None,
-        memory_enabled: bool = False,
-        user_profile_enabled: bool = False,
-    ):
-        self._store = memory_store
-        self._memory_enabled = memory_enabled
-        self._user_profile_enabled = user_profile_enabled
-
-    @property
-    def name(self) -> str:
-        return "builtin"
-
-    def is_available(self) -> bool:
-        """Built-in memory is always available."""
-        return True
-
-    def initialize(self, session_id: str, **kwargs) -> None:
-        """Load memory from disk if not already loaded."""
-        if self._store is not None:
-            self._store.load_from_disk()
-
-    def system_prompt_block(self) -> str:
-        """Return MEMORY.md and USER.md content for the system prompt.
-
-        Uses the frozen snapshot captured at load time. This ensures the
-        system prompt stays stable throughout a session (preserving the
-        prompt cache), even though the live entries may change via tool calls.
-        """
-        if not self._store:
-            return ""
-
-        parts = []
-        if self._memory_enabled:
-            mem_block = self._store.format_for_system_prompt("memory")
-            if mem_block:
-                parts.append(mem_block)
-        if self._user_profile_enabled:
-            user_block = self._store.format_for_system_prompt("user")
-            if user_block:
-                parts.append(user_block)
-
-        return "\n\n".join(parts)
-
-    def prefetch(self, query: str, *, session_id: str = "") -> str:
-        """Built-in memory doesn't do query-based recall — it's injected via system_prompt_block."""
-        return ""
-
-    def sync_turn(self, user_content: str, assistant_content: str, *, session_id: str = "") -> None:
-        """Built-in memory doesn't auto-sync turns — writes happen via the memory tool."""
-
-    def get_tool_schemas(self) -> List[Dict[str, Any]]:
-        """Return empty list.
-
-        The `memory` tool is an agent-level intercepted tool, handled
-        specially in run_agent.py before normal tool dispatch. It's not
-        part of the standard tool registry. We don't duplicate it here.
-        """
-        return []
-
-    def handle_tool_call(self, tool_name: str, args: Dict[str, Any], **kwargs) -> str:
-        """Not used — the memory tool is intercepted in run_agent.py."""
-        return tool_error("Built-in memory tool is handled by the agent loop")
-
-    def shutdown(self) -> None:
-        """No cleanup needed — files are saved on every write."""
-
-    # -- Property access for backward compatibility --------------------------
-
-    @property
-    def store(self):
-        """Access the underlying MemoryStore for legacy code paths."""
-        return self._store
-
-    @property
-    def memory_enabled(self) -> bool:
-        return self._memory_enabled
-
-    @property
-    def user_profile_enabled(self) -> bool:
-        return self._user_profile_enabled
@@ -114,7 +114,6 @@ class ContextCompressor:

        self.last_prompt_tokens = 0
        self.last_completion_tokens = 0
-        self.last_total_tokens = 0

        self.summary_model = summary_model_override or ""

@@ -126,40 +125,27 @@ class ContextCompressor:
        """Update tracked token usage from API response."""
        self.last_prompt_tokens = usage.get("prompt_tokens", 0)
        self.last_completion_tokens = usage.get("completion_tokens", 0)
-        self.last_total_tokens = usage.get("total_tokens", 0)

    def should_compress(self, prompt_tokens: int = None) -> bool:
        """Check if context exceeds the compression threshold."""
        tokens = prompt_tokens if prompt_tokens is not None else self.last_prompt_tokens
        return tokens >= self.threshold_tokens

-    def should_compress_preflight(self, messages: List[Dict[str, Any]]) -> bool:
-        """Quick pre-flight check using rough estimate (before API call)."""
-        rough_estimate = estimate_messages_tokens_rough(messages)
-        return rough_estimate >= self.threshold_tokens
-
-    def get_status(self) -> Dict[str, Any]:
-        """Get current compression status for display/logging."""
-        return {
-            "last_prompt_tokens": self.last_prompt_tokens,
-            "threshold_tokens": self.threshold_tokens,
-            "context_length": self.context_length,
-            "usage_percent": min(100, (self.last_prompt_tokens / self.context_length * 100)) if self.context_length else 0,
-            "compression_count": self.compression_count,
-        }
-
    # ------------------------------------------------------------------
    # Tool output pruning (cheap pre-pass, no LLM call)
    # ------------------------------------------------------------------

    def _prune_old_tool_results(
        self, messages: List[Dict[str, Any]], protect_tail_count: int,
+        protect_tail_tokens: int | None = None,
    ) -> tuple[List[Dict[str, Any]], int]:
        """Replace old tool result contents with a short placeholder.

-        Walks backward from the end, protecting the most recent
-        ``protect_tail_count`` messages. Older tool results get their
-        content replaced with a placeholder string.
+        Walks backward from the end, protecting the most recent messages that
+        fall within ``protect_tail_tokens`` (when provided) OR the last
+        ``protect_tail_count`` messages (backward-compatible default).
+        When both are given, the token budget takes priority and the message
+        count acts as a hard minimum floor.

        Returns (pruned_messages, pruned_count).
        """
@@ -168,7 +154,29 @@ class ContextCompressor:

        result = [m.copy() for m in messages]
        pruned = 0
-        prune_boundary = len(result) - protect_tail_count
+
+        # Determine the prune boundary
+        if protect_tail_tokens is not None and protect_tail_tokens > 0:
+            # Token-budget approach: walk backward accumulating tokens
+            accumulated = 0
+            boundary = len(result)
+            min_protect = min(protect_tail_count, len(result) - 1)
+            for i in range(len(result) - 1, -1, -1):
+                msg = result[i]
+                content_len = len(msg.get("content") or "")
+                msg_tokens = content_len // _CHARS_PER_TOKEN + 10
+                for tc in msg.get("tool_calls") or []:
+                    if isinstance(tc, dict):
+                        args = tc.get("function", {}).get("arguments", "")
+                        msg_tokens += len(args) // _CHARS_PER_TOKEN
+                if accumulated + msg_tokens > protect_tail_tokens and (len(result) - i) >= min_protect:
+                    boundary = i
+                    break
+                accumulated += msg_tokens
+                boundary = i
+            prune_boundary = max(boundary, len(result) - min_protect)
+        else:
+            prune_boundary = len(result) - protect_tail_count

        for i in range(prune_boundary):
            msg = result[i]
@@ -199,30 +207,39 @@ class ContextCompressor:
        budget = int(content_tokens * _SUMMARY_RATIO)
        return max(_MIN_SUMMARY_TOKENS, min(budget, self.max_summary_tokens))

+    # Truncation limits for the summarizer input.  These bound how much of
+    # each message the summary model sees — the budget is the *summary*
+    # model's context window, not the main model's.
+    _CONTENT_MAX = 6000       # total chars per message body
+    _CONTENT_HEAD = 4000      # chars kept from the start
+    _CONTENT_TAIL = 1500      # chars kept from the end
+    _TOOL_ARGS_MAX = 1500     # tool call argument chars
+    _TOOL_ARGS_HEAD = 1200    # kept from the start of tool args
+
    def _serialize_for_summary(self, turns: List[Dict[str, Any]]) -> str:
        """Serialize conversation turns into labeled text for the summarizer.

-        Includes tool call arguments and result content (up to 3000 chars
-        per message) so the summarizer can preserve specific details like
-        file paths, commands, and outputs.
+        Includes tool call arguments and result content (up to
+        ``_CONTENT_MAX`` chars per message) so the summarizer can preserve
+        specific details like file paths, commands, and outputs.
        """
        parts = []
        for msg in turns:
            role = msg.get("role", "unknown")
            content = msg.get("content") or ""

-            # Tool results: keep more content than before (3000 chars)
+            # Tool results: keep enough content for the summarizer
            if role == "tool":
                tool_id = msg.get("tool_call_id", "")
-                if len(content) > 3000:
-                    content = content[:2000] + "\n...[truncated]...\n" + content[-800:]
+                if len(content) > self._CONTENT_MAX:
+                    content = content[:self._CONTENT_HEAD] + "\n...[truncated]...\n" + content[-self._CONTENT_TAIL:]
                parts.append(f"[TOOL RESULT {tool_id}]: {content}")
                continue

            # Assistant messages: include tool call names AND arguments
            if role == "assistant":
-                if len(content) > 3000:
-                    content = content[:2000] + "\n...[truncated]...\n" + content[-800:]
+                if len(content) > self._CONTENT_MAX:
+                    content = content[:self._CONTENT_HEAD] + "\n...[truncated]...\n" + content[-self._CONTENT_TAIL:]
                tool_calls = msg.get("tool_calls", [])
                if tool_calls:
                    tc_parts = []
@@ -232,8 +249,8 @@ class ContextCompressor:
                            name = fn.get("name", "?")
                            args = fn.get("arguments", "")
                            # Truncate long arguments but keep enough for context
-                            if len(args) > 500:
-                                args = args[:400] + "..."
+                            if len(args) > self._TOOL_ARGS_MAX:
+                                args = args[:self._TOOL_ARGS_HEAD] + "..."
                            tc_parts.append(f"  {name}({args})")
                        else:
                            fn = getattr(tc, "function", None)
@@ -244,8 +261,8 @@ class ContextCompressor:
                continue

            # User and other roles
-            if len(content) > 3000:
-                content = content[:2000] + "\n...[truncated]...\n" + content[-800:]
+            if len(content) > self._CONTENT_MAX:
+                content = content[:self._CONTENT_HEAD] + "\n...[truncated]...\n" + content[-self._CONTENT_TAIL:]
            parts.append(f"[{role.upper()}]: {content}")

        return "\n\n".join(parts)
@@ -310,6 +327,9 @@ Update the summary using this exact structure. PRESERVE all existing information
 ## Critical Context
 [Any specific values, error messages, configuration details, or data that would be lost without explicit preservation]

+## Tools & Patterns
+[Which tools were used, how they were used effectively, and any tool-specific discoveries. Accumulate across compactions.]
+
 Target ~{summary_budget} tokens. Be specific — include file paths, command outputs, error messages, and concrete values rather than vague descriptions.

 Write only the summary body. Do not include any preamble or prefix."""
@@ -348,6 +368,9 @@ Use this exact structure:
 ## Critical Context
 [Any specific values, error messages, configuration details, or data that would be lost without explicit preservation]

+## Tools & Patterns
+[Which tools were used, how they were used effectively, and any tool-specific discoveries (e.g., preferred flags, working invocations, successful command patterns)]
+
 Target ~{summary_budget} tokens. Be specific — include file paths, command outputs, error messages, and concrete values rather than vague descriptions. The goal is to prevent the next assistant from repeating work or losing important details.

 Write only the summary body. Do not include any preamble or prefix."""
@@ -518,13 +541,20 @@ Write only the summary body. Do not include any preamble or prefix."""
        derived from ``summary_target_ratio * context_length``, so it
        scales automatically with the model's context window.

-        Never cuts inside a tool_call/result group. Falls back to the old
-        ``protect_last_n`` if the budget would protect fewer messages.
+        Token budget is the primary criterion.  A hard minimum of 3 messages
+        is always protected, but the budget is allowed to exceed by up to
+        1.5x to avoid cutting inside an oversized message (tool output, file
+        read, etc.).  If even the minimum 3 messages exceed 1.5x the budget
+        the cut is placed right after the head so compression still runs.
+
+        Never cuts inside a tool_call/result group.
        """
        if token_budget is None:
            token_budget = self.tail_token_budget
        n = len(messages)
-        min_tail = self.protect_last_n
+        # Hard minimum: always keep at least 3 messages in the tail
+        min_tail = min(3, n - head_end - 1) if n - head_end > 1 else 0
+        soft_ceiling = int(token_budget * 1.5)
        accumulated = 0
        cut_idx = n  # start from beyond the end

@@ -537,21 +567,21 @@ Write only the summary body. Do not include any preamble or prefix."""
                if isinstance(tc, dict):
                    args = tc.get("function", {}).get("arguments", "")
                    msg_tokens += len(args) // _CHARS_PER_TOKEN
-            if accumulated + msg_tokens > token_budget and (n - i) >= min_tail:
+            # Stop once we exceed the soft ceiling (unless we haven't hit min_tail yet)
+            if accumulated + msg_tokens > soft_ceiling and (n - i) >= min_tail:
                break
            accumulated += msg_tokens
            cut_idx = i

-        # Ensure we protect at least protect_last_n messages
+        # Ensure we protect at least min_tail messages
        fallback_cut = n - min_tail
        if cut_idx > fallback_cut:
            cut_idx = fallback_cut

        # If the token budget would protect everything (small conversations),
-        # fall back to the fixed protect_last_n approach so compression can
-        # still remove middle turns.
+        # force a cut after the head so compression can still remove middle turns.
        if cut_idx <= head_end:
-            cut_idx = fallback_cut
+            cut_idx = max(fallback_cut, head_end + 1)

        # Align to avoid splitting tool groups
        cut_idx = self._align_boundary_backward(messages, cut_idx)
@@ -576,12 +606,13 @@ Write only the summary body. Do not include any preamble or prefix."""
        up so the API never receives mismatched IDs.
        """
        n_messages = len(messages)
-        if n_messages <= self.protect_first_n + self.protect_last_n + 1:
+        # Only need head + 3 tail messages minimum (token budget decides the real tail size)
+        _min_for_compress = self.protect_first_n + 3 + 1
+        if n_messages <= _min_for_compress:
            if not self.quiet_mode:
                logger.warning(
                    "Cannot compress: only %d messages (need > %d)",
-                    n_messages,
-                    self.protect_first_n + self.protect_last_n + 1,
+                    n_messages, _min_for_compress,
                )
            return messages

@@ -589,7 +620,8 @@ Write only the summary body. Do not include any preamble or prefix."""

        # Phase 1: Prune old tool results (cheap, no LLM call)
        messages, pruned_count = self._prune_old_tool_results(
-            messages, protect_tail_count=self.protect_last_n * 3,
+            messages, protect_tail_count=self.protect_last_n,
+            protect_tail_tokens=self.tail_token_budget,
        )
        if pruned_count and not self.quiet_mode:
            logger.info("Pre-compression: pruned %d old tool result(s)", pruned_count)
@@ -642,33 +674,43 @@ Write only the summary body. Do not include any preamble or prefix."""
                )
            compressed.append(msg)

-        _merge_summary_into_tail = False
-        if summary:
-            last_head_role = messages[compress_start - 1].get("role", "user") if compress_start > 0 else "user"
-            first_tail_role = messages[compress_end].get("role", "user") if compress_end < n_messages else "user"
-            # Pick a role that avoids consecutive same-role with both neighbors.
-            # Priority: avoid colliding with head (already committed), then tail.
-            if last_head_role in ("assistant", "tool"):
-                summary_role = "user"
-            else:
-                summary_role = "assistant"
-            # If the chosen role collides with the tail AND flipping wouldn't
-            # collide with the head, flip it.
-            if summary_role == first_tail_role:
-                flipped = "assistant" if summary_role == "user" else "user"
-                if flipped != last_head_role:
-                    summary_role = flipped
-                else:
-                    # Both roles would create consecutive same-role messages
-                    # (e.g. head=assistant, tail=user — neither role works).
-                    # Merge the summary into the first tail message instead
-                    # of inserting a standalone message that breaks alternation.
-                    _merge_summary_into_tail = True
-            if not _merge_summary_into_tail:
-                compressed.append({"role": summary_role, "content": summary})
-        else:
+        # If LLM summary failed, insert a static fallback so the model
+        # knows context was lost rather than silently dropping everything.
+        if not summary:
            if not self.quiet_mode:
-                logger.debug("No summary model available — middle turns dropped without summary")
+                logger.warning("Summary generation failed — inserting static fallback context marker")
+            n_dropped = compress_end - compress_start
+            summary = (
+                f"{SUMMARY_PREFIX}\n"
+                f"Summary generation was unavailable. {n_dropped} conversation turns were "
+                f"removed to free context space but could not be summarized. The removed "
+                f"turns contained earlier work in this session. Continue based on the "
+                f"recent messages below and the current state of any files or resources."
+            )
+
+        _merge_summary_into_tail = False
+        last_head_role = messages[compress_start - 1].get("role", "user") if compress_start > 0 else "user"
+        first_tail_role = messages[compress_end].get("role", "user") if compress_end < n_messages else "user"
+        # Pick a role that avoids consecutive same-role with both neighbors.
+        # Priority: avoid colliding with head (already committed), then tail.
+        if last_head_role in ("assistant", "tool"):
+            summary_role = "user"
+        else:
+            summary_role = "assistant"
+        # If the chosen role collides with the tail AND flipping wouldn't
+        # collide with the head, flip it.
+        if summary_role == first_tail_role:
+            flipped = "assistant" if summary_role == "user" else "user"
+            if flipped != last_head_role:
+                summary_role = flipped
+            else:
+                # Both roles would create consecutive same-role messages
+                # (e.g. head=assistant, tail=user — neither role works).
+                # Merge the summary into the first tail message instead
+                # of inserting a standalone message that breaks alternation.
+                _merge_summary_into_tail = True
+        if not _merge_summary_into_tail:
+            compressed.append({"role": summary_role, "content": summary})

        for i in range(compress_end, n_messages):
            msg = messages[i].copy()
@@ -18,13 +18,18 @@ import hermes_cli.auth as auth_mod
 from hermes_cli.auth import (
    CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
    DEFAULT_AGENT_KEY_MIN_TTL_SECONDS,
+    KIMI_CODE_BASE_URL,
    PROVIDER_REGISTRY,
+    _auth_store_lock,
    _codex_access_token_is_expiring,
    _decode_jwt_claims,
    _import_codex_cli_tokens,
    _load_auth_store,
    _load_provider_state,
+    _resolve_kimi_base_url,
    _resolve_zai_base_url,
+    _save_auth_store,
+    _save_provider_state,
    read_credential_pool,
    write_credential_pool,
 )
@@ -64,10 +69,10 @@ SUPPORTED_POOL_STRATEGIES = {
 }

 # Cooldown before retrying an exhausted credential.
-# 429 (rate-limited) cools down faster since quotas reset frequently.
-# 402 (billing/quota) and other codes use a longer default.
+# 429 (rate-limited) and 402 (billing/quota) both cool down after 1 hour.
+# Provider-supplied reset_at timestamps override these defaults.
 EXHAUSTED_TTL_429_SECONDS = 60 * 60          # 1 hour
-EXHAUSTED_TTL_DEFAULT_SECONDS = 24 * 60 * 60 # 24 hours
+EXHAUSTED_TTL_DEFAULT_SECONDS = 60 * 60      # 1 hour

 # Pool key prefix for custom OpenAI-compatible endpoints.
 # Custom endpoints all share provider='custom' but are keyed by their
@@ -477,6 +482,67 @@ class CredentialPool:
            logger.debug("Failed to sync from ~/.codex/auth.json: %s", exc)
        return entry

+    def _sync_device_code_entry_to_auth_store(self, entry: PooledCredential) -> None:
+        """Write refreshed pool entry tokens back to auth.json providers.
+
+        After a pool-level refresh, the pool entry has fresh tokens but
+        auth.json's ``providers.<id>`` still holds the pre-refresh state.
+        On the next ``load_pool()``, ``_seed_from_singletons()`` reads that
+        stale state and can overwrite the fresh pool entry — potentially
+        re-seeding a consumed single-use refresh token.
+
+        Applies to any OAuth provider whose singleton lives in auth.json
+        (currently Nous and OpenAI Codex).
+        """
+        if entry.source != "device_code":
+            return
+        try:
+            with _auth_store_lock():
+                auth_store = _load_auth_store()
+                if self.provider == "nous":
+                    state = _load_provider_state(auth_store, "nous")
+                    if state is None:
+                        return
+                    state["access_token"] = entry.access_token
+                    if entry.refresh_token:
+                        state["refresh_token"] = entry.refresh_token
+                    if entry.expires_at:
+                        state["expires_at"] = entry.expires_at
+                    if entry.agent_key:
+                        state["agent_key"] = entry.agent_key
+                    if entry.agent_key_expires_at:
+                        state["agent_key_expires_at"] = entry.agent_key_expires_at
+                    for extra_key in ("obtained_at", "expires_in", "agent_key_id",
+                                      "agent_key_expires_in", "agent_key_reused",
+                                      "agent_key_obtained_at"):
+                        val = entry.extra.get(extra_key)
+                        if val is not None:
+                            state[extra_key] = val
+                    if entry.inference_base_url:
+                        state["inference_base_url"] = entry.inference_base_url
+                    _save_provider_state(auth_store, "nous", state)
+
+                elif self.provider == "openai-codex":
+                    state = _load_provider_state(auth_store, "openai-codex")
+                    if not isinstance(state, dict):
+                        return
+                    tokens = state.get("tokens")
+                    if not isinstance(tokens, dict):
+                        return
+                    tokens["access_token"] = entry.access_token
+                    if entry.refresh_token:
+                        tokens["refresh_token"] = entry.refresh_token
+                    if entry.last_refresh:
+                        state["last_refresh"] = entry.last_refresh
+                    _save_provider_state(auth_store, "openai-codex", state)
+
+                else:
+                    return
+
+                _save_auth_store(auth_store)
+        except Exception as exc:
+            logger.debug("Failed to sync %s pool entry back to auth store: %s", self.provider, exc)
+
    def _refresh_entry(self, entry: PooledCredential, *, force: bool) -> Optional[PooledCredential]:
        if entry.auth_type != AUTH_TYPE_OAUTH or not entry.refresh_token:
            if force:
@@ -511,6 +577,13 @@ class CredentialPool:
                    except Exception as wexc:
                        logger.debug("Failed to write refreshed token to credentials file: %s", wexc)
            elif self.provider == "openai-codex":
+                # Proactively sync from ~/.codex/auth.json before refresh.
+                # The Codex CLI (or another Hermes profile) may have already
+                # consumed our refresh_token.  Syncing first avoids a
+                # "refresh_token_reused" error when the CLI has a newer pair.
+                synced = self._sync_codex_entry_from_cli(entry)
+                if synced is not entry:
+                    entry = synced
                refreshed = auth_mod.refresh_codex_oauth_pure(
                    entry.access_token,
                    entry.refresh_token,
@@ -596,6 +669,37 @@ class CredentialPool:
                    # Credentials file had a valid (non-expired) token — use it directly
                    logger.debug("Credentials file has valid token, using without refresh")
                    return synced
+            # For openai-codex: the refresh_token may have been consumed by
+            # the Codex CLI between our proactive sync and the refresh call.
+            # Re-sync and retry once.
+            if self.provider == "openai-codex":
+                synced = self._sync_codex_entry_from_cli(entry)
+                if synced.refresh_token != entry.refresh_token:
+                    logger.debug("Retrying Codex refresh with synced token from ~/.codex/auth.json")
+                    try:
+                        refreshed = auth_mod.refresh_codex_oauth_pure(
+                            synced.access_token,
+                            synced.refresh_token,
+                        )
+                        updated = replace(
+                            synced,
+                            access_token=refreshed["access_token"],
+                            refresh_token=refreshed["refresh_token"],
+                            last_refresh=refreshed.get("last_refresh"),
+                            last_status=STATUS_OK,
+                            last_status_at=None,
+                            last_error_code=None,
+                        )
+                        self._replace_entry(synced, updated)
+                        self._persist()
+                        self._sync_device_code_entry_to_auth_store(updated)
+                        return updated
+                    except Exception as retry_exc:
+                        logger.debug("Codex retry refresh also failed: %s", retry_exc)
+                elif not self._entry_needs_refresh(synced):
+                    logger.debug("Codex CLI has valid token, using without refresh")
+                    self._sync_device_code_entry_to_auth_store(synced)
+                    return synced
            self._mark_exhausted(entry, None)
            return None

@@ -610,6 +714,10 @@ class CredentialPool:
        )
        self._replace_entry(entry, updated)
        self._persist()
+        # Sync refreshed tokens back to auth.json providers so that
+        # _seed_from_singletons() on the next load_pool() sees fresh state
+        # instead of re-seeding stale/consumed tokens.
+        self._sync_device_code_entry_to_auth_store(updated)
        return updated

    def _entry_needs_refresh(self, entry: PooledCredential) -> bool:
@@ -631,17 +739,6 @@ class CredentialPool:
            return False
        return False

-    def mark_used(self, entry_id: Optional[str] = None) -> None:
-        """Increment request_count for tracking. Used by least_used strategy."""
-        target_id = entry_id or self._current_id
-        if not target_id:
-            return
-        with self._lock:
-            for idx, entry in enumerate(self._entries):
-                if entry.id == target_id:
-                    self._entries[idx] = replace(entry, request_count=entry.request_count + 1)
-                    return
-
    def select(self) -> Optional[PooledCredential]:
        with self._lock:
            return self._select_unlocked()
@@ -803,11 +900,6 @@ class CredentialPool:
            else:
                self._active_leases[credential_id] = count - 1

-    def active_lease_count(self, credential_id: str) -> int:
-        """Return the number of active leases for a credential."""
-        with self._lock:
-            return self._active_leases.get(credential_id, 0)
-
    def try_refresh_current(self) -> Optional[PooledCredential]:
        with self._lock:
            return self._try_refresh_current_unlocked()
@@ -967,6 +1059,17 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
    auth_store = _load_auth_store()

    if provider == "anthropic":
+        # Only auto-discover external credentials (Claude Code, Hermes PKCE)
+        # when the user has explicitly configured anthropic as their provider.
+        # Without this gate, auxiliary client fallback chains silently read
+        # ~/.claude/.credentials.json without user consent.  See PR #4210.
+        try:
+            from hermes_cli.auth import is_provider_explicitly_configured
+            if not is_provider_explicitly_configured("anthropic"):
+                return changed, active_sources
+        except ImportError:
+            pass
+
        from agent.anthropic_adapter import read_claude_code_credentials, read_hermes_oauth_credentials

        for source_name, creds in (
@@ -974,6 +1077,13 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
            ("claude_code", read_claude_code_credentials()),
        ):
            if creds and creds.get("accessToken"):
+                # Check if user explicitly removed this source
+                try:
+                    from hermes_cli.auth import is_source_suppressed
+                    if is_source_suppressed(provider, source_name):
+                        continue
+                except ImportError:
+                    pass
                active_sources.add(source_name)
                changed |= _upsert_entry(
                    entries,
@@ -1084,7 +1194,9 @@ def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool
        active_sources.add(source)
        auth_type = AUTH_TYPE_OAUTH if provider == "anthropic" and not token.startswith("sk-ant-api") else AUTH_TYPE_API_KEY
        base_url = env_url or pconfig.inference_base_url
-        if provider == "zai":
+        if provider == "kimi-coding":
+            base_url = _resolve_kimi_base_url(token, pconfig.inference_base_url, env_url)
+        elif provider == "zai":
            base_url = _resolve_zai_base_url(token, pconfig.inference_base_url, env_url)
        changed |= _upsert_entry(
            entries,
@@ -67,26 +67,6 @@ def _get_skin():
        return None


-def get_skin_faces(key: str, default: list) -> list:
-    """Get spinner face list from active skin, falling back to default."""
-    skin = _get_skin()
-    if skin:
-        faces = skin.get_spinner_list(key)
-        if faces:
-            return faces
-    return default
-
-
-def get_skin_verbs() -> list:
-    """Get thinking verbs from active skin."""
-    skin = _get_skin()
-    if skin:
-        verbs = skin.get_spinner_list("thinking_verbs")
-        if verbs:
-            return verbs
-    return KawaiiSpinner.THINKING_VERBS
-
-
 def get_skin_tool_prefix() -> str:
    """Get tool output prefix character from active skin."""
    skin = _get_skin()
@@ -723,46 +703,6 @@ class KawaiiSpinner:
        return False


-# =========================================================================
-# Kawaii face arrays (used by AIAgent._execute_tool_calls for spinner text)
-# =========================================================================
-
-KAWAII_SEARCH = [
-    "♪(´ε` )", "(｡◕‿◕｡)", "ヾ(＾∇＾)", "(◕ᴗ◕✿)", "( ˘▽˘)っ",
-    "٩(◕‿◕｡)۶", "(✿◠‿◠)", "♪～(´ε｀ )", "(ノ´ヮ`)ノ*:・゚✧", "＼(◎o◎)／",
-]
-KAWAII_READ = [
-    "φ(゜▽゜*)♪", "( ˘▽˘)っ", "(⌐■_■)", "٩(｡•́‿•̀｡)۶", "(◕‿◕✿)",
-    "ヾ(＠⌒ー⌒＠)ノ", "(✧ω✧)", "♪(๑ᴖ◡ᴖ๑)♪", "(≧◡≦)", "( ´ ▽ ` )ノ",
-]
-KAWAII_TERMINAL = [
-    "ヽ(>∀<☆)ノ", "(ノ°∀°)ノ", "٩(^ᴗ^)۶", "ヾ(⌐■_■)ノ♪", "(•̀ᴗ•́)و",
-    "┗(＾0＾)┓", "(｀・ω・´)", "＼(￣▽￣)／", "(ง •̀_•́)ง", "ヽ(´▽`)/",
-]
-KAWAII_BROWSER = [
-    "(ノ°∀°)ノ", "(☞゚ヮ゚)☞", "( ͡° ͜ʖ ͡°)", "┌( ಠ_ಠ)┘", "(⊙_⊙)？",
-    "ヾ(•ω•`)o", "(￣ω￣)", "( ˇωˇ )", "(ᵔᴥᵔ)", "＼(◎o◎)／",
-]
-KAWAII_CREATE = [
-    "✧*。٩(ˊᗜˋ*)و✧", "(ﾉ◕ヮ◕)ﾉ*:・ﾟ✧", "ヽ(>∀<☆)ノ", "٩(♡ε♡)۶", "(◕‿◕)♡",
-    "✿◕ ‿ ◕✿", "(*≧▽≦)", "ヾ(＾-＾)ノ", "(☆▽☆)", "°˖✧◝(⁰▿⁰)◜✧˖°",
-]
-KAWAII_SKILL = [
-    "ヾ(＠⌒ー⌒＠)ノ", "(๑˃ᴗ˂)ﻭ", "٩(◕‿◕｡)۶", "(✿╹◡╹)", "ヽ(・∀・)ノ",
-    "(ノ´ヮ`)ノ*:・ﾟ✧", "♪(๑ᴖ◡ᴖ๑)♪", "(◠‿◠)", "٩(ˊᗜˋ*)و", "(＾▽＾)",
-    "ヾ(＾∇＾)", "(★ω★)/", "٩(｡•́‿•̀｡)۶", "(◕ᴗ◕✿)", "＼(◎o◎)／",
-    "(✧ω✧)", "ヽ(>∀<☆)ノ", "( ˘▽˘)っ", "(≧◡≦) ♡", "ヾ(￣▽￣)",
-]
-KAWAII_THINK = [
-    "(っ°Д°;)っ", "(；′⌒`)", "(・_・ヾ", "( ´_ゝ`)", "(￣ヘ￣)",
-    "(。-`ω´-)", "( ˘︹˘ )", "(¬_¬)", "ヽ(ー_ー )ノ", "(；一_一)",
-]
-KAWAII_GENERIC = [
-    "♪(´ε` )", "(◕‿◕✿)", "ヾ(＾∇＾)", "٩(◕‿◕｡)۶", "(✿◠‿◠)",
-    "(ノ´ヮ`)ノ*:・ﾟ✧", "ヽ(>∀<☆)ノ", "(☆▽☆)", "( ˘▽˘)っ", "(≧◡≦)",
-]
-
-
 # =========================================================================
 # Cute tool message (completion line that replaces the spinner)
 # =========================================================================
@@ -970,22 +910,6 @@ _SKY_BLUE = "\033[38;5;117m"
 _ANSI_RESET = "\033[0m"


-def honcho_session_url(workspace: str, session_name: str) -> str:
-    """Build a Honcho app URL for a session."""
-    from urllib.parse import quote
-    return (
-        f"https://app.honcho.dev/explore"
-        f"?workspace={quote(workspace, safe='')}"
-        f"&view=sessions"
-        f"&session={quote(session_name, safe='')}"
-    )
-
-
-def _osc8_link(url: str, text: str) -> str:
-    """OSC 8 terminal hyperlink (clickable in iTerm2, Ghostty, WezTerm, etc.)."""
-    return f"\033]8;;{url}\033\\{text}\033]8;;\033\\"
-
-
 # =========================================================================
 # Context pressure display (CLI user-facing warnings)
 # =========================================================================
@@ -0,0 +1,808 @@
+"""API error classification for smart failover and recovery.
+
+Provides a structured taxonomy of API errors and a priority-ordered
+classification pipeline that determines the correct recovery action
+(retry, rotate credential, fallback to another provider, compress
+context, or abort).
+
+Replaces scattered inline string-matching with a centralized classifier
+that the main retry loop in run_agent.py consults for every API failure.
+"""
+
+from __future__ import annotations
+
+import enum
+import logging
+import re
+from dataclasses import dataclass, field
+from typing import Any, Dict, Optional
+
+logger = logging.getLogger(__name__)
+
+
+# ── Error taxonomy ──────────────────────────────────────────────────────
+
+class FailoverReason(enum.Enum):
+    """Why an API call failed — determines recovery strategy."""
+
+    # Authentication / authorization
+    auth = "auth"                        # Transient auth (401/403) — refresh/rotate
+    auth_permanent = "auth_permanent"    # Auth failed after refresh — abort
+
+    # Billing / quota
+    billing = "billing"                  # 402 or confirmed credit exhaustion — rotate immediately
+    rate_limit = "rate_limit"            # 429 or quota-based throttling — backoff then rotate
+
+    # Server-side
+    overloaded = "overloaded"            # 503/529 — provider overloaded, backoff
+    server_error = "server_error"        # 500/502 — internal server error, retry
+
+    # Transport
+    timeout = "timeout"                  # Connection/read timeout — rebuild client + retry
+
+    # Context / payload
+    context_overflow = "context_overflow"  # Context too large — compress, not failover
+    payload_too_large = "payload_too_large"  # 413 — compress payload
+
+    # Model
+    model_not_found = "model_not_found"  # 404 or invalid model — fallback to different model
+
+    # Request format
+    format_error = "format_error"        # 400 bad request — abort or strip + retry
+
+    # Provider-specific
+    thinking_signature = "thinking_signature"  # Anthropic thinking block sig invalid
+    long_context_tier = "long_context_tier"    # Anthropic "extra usage" tier gate
+
+    # Catch-all
+    unknown = "unknown"                  # Unclassifiable — retry with backoff
+
+
+# ── Classification result ───────────────────────────────────────────────
+
+@dataclass
+class ClassifiedError:
+    """Structured classification of an API error with recovery hints."""
+
+    reason: FailoverReason
+    status_code: Optional[int] = None
+    provider: Optional[str] = None
+    model: Optional[str] = None
+    message: str = ""
+    error_context: Dict[str, Any] = field(default_factory=dict)
+
+    # Recovery action hints — the retry loop checks these instead of
+    # re-classifying the error itself.
+    retryable: bool = True
+    should_compress: bool = False
+    should_rotate_credential: bool = False
+    should_fallback: bool = False
+
+    @property
+    def is_auth(self) -> bool:
+        return self.reason in (FailoverReason.auth, FailoverReason.auth_permanent)
+
+
+
+# ── Provider-specific patterns ──────────────────────────────────────────
+
+# Patterns that indicate billing exhaustion (not transient rate limit)
+_BILLING_PATTERNS = [
+    "insufficient credits",
+    "insufficient_quota",
+    "credit balance",
+    "credits have been exhausted",
+    "top up your credits",
+    "payment required",
+    "billing hard limit",
+    "exceeded your current quota",
+    "account is deactivated",
+    "plan does not include",
+]
+
+# Patterns that indicate rate limiting (transient, will resolve)
+_RATE_LIMIT_PATTERNS = [
+    "rate limit",
+    "rate_limit",
+    "too many requests",
+    "throttled",
+    "requests per minute",
+    "tokens per minute",
+    "requests per day",
+    "try again in",
+    "please retry after",
+    "resource_exhausted",
+]
+
+# Usage-limit patterns that need disambiguation (could be billing OR rate_limit)
+_USAGE_LIMIT_PATTERNS = [
+    "usage limit",
+    "quota",
+    "limit exceeded",
+    "key limit exceeded",
+]
+
+# Patterns confirming usage limit is transient (not billing)
+_USAGE_LIMIT_TRANSIENT_SIGNALS = [
+    "try again",
+    "retry",
+    "resets at",
+    "reset in",
+    "wait",
+    "requests remaining",
+    "periodic",
+    "window",
+]
+
+# Payload-too-large patterns detected from message text (no status_code attr).
+# Proxies and some backends embed the HTTP status in the error message.
+_PAYLOAD_TOO_LARGE_PATTERNS = [
+    "request entity too large",
+    "payload too large",
+    "error code: 413",
+]
+
+# Context overflow patterns
+_CONTEXT_OVERFLOW_PATTERNS = [
+    "context length",
+    "context size",
+    "maximum context",
+    "token limit",
+    "too many tokens",
+    "reduce the length",
+    "exceeds the limit",
+    "context window",
+    "prompt is too long",
+    "prompt exceeds max length",
+    "max_tokens",
+    "maximum number of tokens",
+    # Chinese error messages (some providers return these)
+    "超过最大长度",
+    "上下文长度",
+]
+
+# Model not found patterns
+_MODEL_NOT_FOUND_PATTERNS = [
+    "is not a valid model",
+    "invalid model",
+    "model not found",
+    "model_not_found",
+    "does not exist",
+    "no such model",
+    "unknown model",
+    "unsupported model",
+]
+
+# Auth patterns (non-status-code signals)
+_AUTH_PATTERNS = [
+    "invalid api key",
+    "invalid_api_key",
+    "authentication",
+    "unauthorized",
+    "forbidden",
+    "invalid token",
+    "token expired",
+    "token revoked",
+    "access denied",
+]
+
+# Anthropic thinking block signature patterns
+_THINKING_SIG_PATTERNS = [
+    "signature",  # Combined with "thinking" check
+]
+
+# Transport error type names
+_TRANSPORT_ERROR_TYPES = frozenset({
+    "ReadTimeout", "ConnectTimeout", "PoolTimeout",
+    "ConnectError", "RemoteProtocolError",
+    "ConnectionError", "ConnectionResetError",
+    "ConnectionAbortedError", "BrokenPipeError",
+    "TimeoutError", "ReadError",
+    "ServerDisconnectedError",
+    # OpenAI SDK errors (not subclasses of Python builtins)
+    "APIConnectionError",
+    "APITimeoutError",
+})
+
+# Server disconnect patterns (no status code, but transport-level)
+_SERVER_DISCONNECT_PATTERNS = [
+    "server disconnected",
+    "peer closed connection",
+    "connection reset by peer",
+    "connection was closed",
+    "network connection lost",
+    "unexpected eof",
+    "incomplete chunked read",
+]
+
+
+# ── Classification pipeline ─────────────────────────────────────────────
+
+def classify_api_error(
+    error: Exception,
+    *,
+    provider: str = "",
+    model: str = "",
+    approx_tokens: int = 0,
+    context_length: int = 200000,
+    num_messages: int = 0,
+) -> ClassifiedError:
+    """Classify an API error into a structured recovery recommendation.
+
+    Priority-ordered pipeline:
+      1. Special-case provider-specific patterns (thinking sigs, tier gates)
+      2. HTTP status code + message-aware refinement
+      3. Error code classification (from body)
+      4. Message pattern matching (billing vs rate_limit vs context vs auth)
+      5. Transport error heuristics
+      6. Server disconnect + large session → context overflow
+      7. Fallback: unknown (retryable with backoff)
+
+    Args:
+        error: The exception from the API call.
+        provider: Current provider name (e.g. "openrouter", "anthropic").
+        model: Current model slug.
+        approx_tokens: Approximate token count of the current context.
+        context_length: Maximum context length for the current model.
+
+    Returns:
+        ClassifiedError with reason and recovery action hints.
+    """
+    status_code = _extract_status_code(error)
+    error_type = type(error).__name__
+    body = _extract_error_body(error)
+    error_code = _extract_error_code(body)
+
+    # Build a comprehensive error message string for pattern matching.
+    # str(error) alone may not include the body message (e.g. OpenAI SDK's
+    # APIStatusError.__str__ returns the first arg, not the body).  Append
+    # the body message so patterns like "try again" in 402 disambiguation
+    # are detected even when only present in the structured body.
+    #
+    # Also extract metadata.raw — OpenRouter wraps upstream provider errors
+    # inside {"error": {"message": "Provider returned error", "metadata":
+    # {"raw": "<actual error JSON>"}}} and the real error message (e.g.
+    # "context length exceeded") is only in the inner JSON.
+    _raw_msg = str(error).lower()
+    _body_msg = ""
+    _metadata_msg = ""
+    if isinstance(body, dict):
+        _err_obj = body.get("error", {})
+        if isinstance(_err_obj, dict):
+            _body_msg = (_err_obj.get("message") or "").lower()
+            # Parse metadata.raw for wrapped provider errors
+            _metadata = _err_obj.get("metadata", {})
+            if isinstance(_metadata, dict):
+                _raw_json = _metadata.get("raw") or ""
+                if isinstance(_raw_json, str) and _raw_json.strip():
+                    try:
+                        import json
+                        _inner = json.loads(_raw_json)
+                        if isinstance(_inner, dict):
+                            _inner_err = _inner.get("error", {})
+                            if isinstance(_inner_err, dict):
+                                _metadata_msg = (_inner_err.get("message") or "").lower()
+                    except (json.JSONDecodeError, TypeError):
+                        pass
+        if not _body_msg:
+            _body_msg = (body.get("message") or "").lower()
+    # Combine all message sources for pattern matching
+    parts = [_raw_msg]
+    if _body_msg and _body_msg not in _raw_msg:
+        parts.append(_body_msg)
+    if _metadata_msg and _metadata_msg not in _raw_msg and _metadata_msg not in _body_msg:
+        parts.append(_metadata_msg)
+    error_msg = " ".join(parts)
+    provider_lower = (provider or "").strip().lower()
+    model_lower = (model or "").strip().lower()
+
+    def _result(reason: FailoverReason, **overrides) -> ClassifiedError:
+        defaults = {
+            "reason": reason,
+            "status_code": status_code,
+            "provider": provider,
+            "model": model,
+            "message": _extract_message(error, body),
+        }
+        defaults.update(overrides)
+        return ClassifiedError(**defaults)
+
+    # ── 1. Provider-specific patterns (highest priority) ────────────
+
+    # Anthropic thinking block signature invalid (400).
+    # Don't gate on provider — OpenRouter proxies Anthropic errors, so the
+    # provider may be "openrouter" even though the error is Anthropic-specific.
+    # The message pattern ("signature" + "thinking") is unique enough.
+    if (
+        status_code == 400
+        and "signature" in error_msg
+        and "thinking" in error_msg
+    ):
+        return _result(
+            FailoverReason.thinking_signature,
+            retryable=True,
+            should_compress=False,
+        )
+
+    # Anthropic long-context tier gate (429 "extra usage" + "long context")
+    if (
+        status_code == 429
+        and "extra usage" in error_msg
+        and "long context" in error_msg
+    ):
+        return _result(
+            FailoverReason.long_context_tier,
+            retryable=True,
+            should_compress=True,
+        )
+
+    # ── 2. HTTP status code classification ──────────────────────────
+
+    if status_code is not None:
+        classified = _classify_by_status(
+            status_code, error_msg, error_code, body,
+            provider=provider_lower, model=model_lower,
+            approx_tokens=approx_tokens, context_length=context_length,
+            num_messages=num_messages,
+            result_fn=_result,
+        )
+        if classified is not None:
+            return classified
+
+    # ── 3. Error code classification ────────────────────────────────
+
+    if error_code:
+        classified = _classify_by_error_code(error_code, error_msg, _result)
+        if classified is not None:
+            return classified
+
+    # ── 4. Message pattern matching (no status code) ────────────────
+
+    classified = _classify_by_message(
+        error_msg, error_type,
+        approx_tokens=approx_tokens,
+        context_length=context_length,
+        result_fn=_result,
+    )
+    if classified is not None:
+        return classified
+
+    # ── 5. Server disconnect + large session → context overflow ─────
+    # Must come BEFORE generic transport error catch — a disconnect on
+    # a large session is more likely context overflow than a transient
+    # transport hiccup.  Without this ordering, RemoteProtocolError
+    # always maps to timeout regardless of session size.
+
+    is_disconnect = any(p in error_msg for p in _SERVER_DISCONNECT_PATTERNS)
+    if is_disconnect and not status_code:
+        is_large = approx_tokens > context_length * 0.6 or approx_tokens > 120000 or num_messages > 200
+        if is_large:
+            return _result(
+                FailoverReason.context_overflow,
+                retryable=True,
+                should_compress=True,
+            )
+        return _result(FailoverReason.timeout, retryable=True)
+
+    # ── 6. Transport / timeout heuristics ───────────────────────────
+
+    if error_type in _TRANSPORT_ERROR_TYPES or isinstance(error, (TimeoutError, ConnectionError, OSError)):
+        return _result(FailoverReason.timeout, retryable=True)
+
+    # ── 7. Fallback: unknown ────────────────────────────────────────
+
+    return _result(FailoverReason.unknown, retryable=True)
+
+
+# ── Status code classification ──────────────────────────────────────────
+
+def _classify_by_status(
+    status_code: int,
+    error_msg: str,
+    error_code: str,
+    body: dict,
+    *,
+    provider: str,
+    model: str,
+    approx_tokens: int,
+    context_length: int,
+    num_messages: int = 0,
+    result_fn,
+) -> Optional[ClassifiedError]:
+    """Classify based on HTTP status code with message-aware refinement."""
+
+    if status_code == 401:
+        # Not retryable on its own — credential pool rotation and
+        # provider-specific refresh (Codex, Anthropic, Nous) run before
+        # the retryability check in run_agent.py.  If those succeed, the
+        # loop `continue`s.  If they fail, retryable=False ensures we
+        # hit the client-error abort path (which tries fallback first).
+        return result_fn(
+            FailoverReason.auth,
+            retryable=False,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+
+    if status_code == 403:
+        # OpenRouter 403 "key limit exceeded" is actually billing
+        if "key limit exceeded" in error_msg or "spending limit" in error_msg:
+            return result_fn(
+                FailoverReason.billing,
+                retryable=False,
+                should_rotate_credential=True,
+                should_fallback=True,
+            )
+        return result_fn(
+            FailoverReason.auth,
+            retryable=False,
+            should_fallback=True,
+        )
+
+    if status_code == 402:
+        return _classify_402(error_msg, result_fn)
+
+    if status_code == 404:
+        if any(p in error_msg for p in _MODEL_NOT_FOUND_PATTERNS):
+            return result_fn(
+                FailoverReason.model_not_found,
+                retryable=False,
+                should_fallback=True,
+            )
+        # Generic 404 — could be model or endpoint
+        return result_fn(
+            FailoverReason.model_not_found,
+            retryable=False,
+            should_fallback=True,
+        )
+
+    if status_code == 413:
+        return result_fn(
+            FailoverReason.payload_too_large,
+            retryable=True,
+            should_compress=True,
+        )
+
+    if status_code == 429:
+        # Already checked long_context_tier above; this is a normal rate limit
+        return result_fn(
+            FailoverReason.rate_limit,
+            retryable=True,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+
+    if status_code == 400:
+        return _classify_400(
+            error_msg, error_code, body,
+            provider=provider, model=model,
+            approx_tokens=approx_tokens,
+            context_length=context_length,
+            num_messages=num_messages,
+            result_fn=result_fn,
+        )
+
+    if status_code in (500, 502):
+        return result_fn(FailoverReason.server_error, retryable=True)
+
+    if status_code in (503, 529):
+        return result_fn(FailoverReason.overloaded, retryable=True)
+
+    # Other 4xx — non-retryable
+    if 400 <= status_code < 500:
+        return result_fn(
+            FailoverReason.format_error,
+            retryable=False,
+            should_fallback=True,
+        )
+
+    # Other 5xx — retryable
+    if 500 <= status_code < 600:
+        return result_fn(FailoverReason.server_error, retryable=True)
+
+    return None
+
+
+def _classify_402(error_msg: str, result_fn) -> ClassifiedError:
+    """Disambiguate 402: billing exhaustion vs transient usage limit.
+
+    The key insight from OpenClaw: some 402s are transient rate limits
+    disguised as payment errors.  "Usage limit, try again in 5 minutes"
+    is NOT a billing problem — it's a periodic quota that resets.
+    """
+    # Check for transient usage-limit signals first
+    has_usage_limit = any(p in error_msg for p in _USAGE_LIMIT_PATTERNS)
+    has_transient_signal = any(p in error_msg for p in _USAGE_LIMIT_TRANSIENT_SIGNALS)
+
+    if has_usage_limit and has_transient_signal:
+        # Transient quota — treat as rate limit, not billing
+        return result_fn(
+            FailoverReason.rate_limit,
+            retryable=True,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+
+    # Confirmed billing exhaustion
+    return result_fn(
+        FailoverReason.billing,
+        retryable=False,
+        should_rotate_credential=True,
+        should_fallback=True,
+    )
+
+
+def _classify_400(
+    error_msg: str,
+    error_code: str,
+    body: dict,
+    *,
+    provider: str,
+    model: str,
+    approx_tokens: int,
+    context_length: int,
+    num_messages: int = 0,
+    result_fn,
+) -> ClassifiedError:
+    """Classify 400 Bad Request — context overflow, format error, or generic."""
+
+    # Context overflow from 400
+    if any(p in error_msg for p in _CONTEXT_OVERFLOW_PATTERNS):
+        return result_fn(
+            FailoverReason.context_overflow,
+            retryable=True,
+            should_compress=True,
+        )
+
+    # Some providers return model-not-found as 400 instead of 404 (e.g. OpenRouter).
+    if any(p in error_msg for p in _MODEL_NOT_FOUND_PATTERNS):
+        return result_fn(
+            FailoverReason.model_not_found,
+            retryable=False,
+            should_fallback=True,
+        )
+
+    # Some providers return rate limit / billing errors as 400 instead of 429/402.
+    # Check these patterns before falling through to format_error.
+    if any(p in error_msg for p in _RATE_LIMIT_PATTERNS):
+        return result_fn(
+            FailoverReason.rate_limit,
+            retryable=True,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+    if any(p in error_msg for p in _BILLING_PATTERNS):
+        return result_fn(
+            FailoverReason.billing,
+            retryable=False,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+
+    # Generic 400 + large session → probable context overflow
+    # Anthropic sometimes returns a bare "Error" message when context is too large
+    err_body_msg = ""
+    if isinstance(body, dict):
+        err_obj = body.get("error", {})
+        if isinstance(err_obj, dict):
+            err_body_msg = (err_obj.get("message") or "").strip().lower()
+        # Responses API (and some providers) use flat body: {"message": "..."}
+        if not err_body_msg:
+            err_body_msg = (body.get("message") or "").strip().lower()
+    is_generic = len(err_body_msg) < 30 or err_body_msg in ("error", "")
+    is_large = approx_tokens > context_length * 0.4 or approx_tokens > 80000 or num_messages > 80
+
+    if is_generic and is_large:
+        return result_fn(
+            FailoverReason.context_overflow,
+            retryable=True,
+            should_compress=True,
+        )
+
+    # Non-retryable format error
+    return result_fn(
+        FailoverReason.format_error,
+        retryable=False,
+        should_fallback=True,
+    )
+
+
+# ── Error code classification ───────────────────────────────────────────
+
+def _classify_by_error_code(
+    error_code: str, error_msg: str, result_fn,
+) -> Optional[ClassifiedError]:
+    """Classify by structured error codes from the response body."""
+    code_lower = error_code.lower()
+
+    if code_lower in ("resource_exhausted", "throttled", "rate_limit_exceeded"):
+        return result_fn(
+            FailoverReason.rate_limit,
+            retryable=True,
+            should_rotate_credential=True,
+        )
+
+    if code_lower in ("insufficient_quota", "billing_not_active", "payment_required"):
+        return result_fn(
+            FailoverReason.billing,
+            retryable=False,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+
+    if code_lower in ("model_not_found", "model_not_available", "invalid_model"):
+        return result_fn(
+            FailoverReason.model_not_found,
+            retryable=False,
+            should_fallback=True,
+        )
+
+    if code_lower in ("context_length_exceeded", "max_tokens_exceeded"):
+        return result_fn(
+            FailoverReason.context_overflow,
+            retryable=True,
+            should_compress=True,
+        )
+
+    return None
+
+
+# ── Message pattern classification ──────────────────────────────────────
+
+def _classify_by_message(
+    error_msg: str,
+    error_type: str,
+    *,
+    approx_tokens: int,
+    context_length: int,
+    result_fn,
+) -> Optional[ClassifiedError]:
+    """Classify based on error message patterns when no status code is available."""
+
+    # Payload-too-large patterns (from message text when no status_code)
+    if any(p in error_msg for p in _PAYLOAD_TOO_LARGE_PATTERNS):
+        return result_fn(
+            FailoverReason.payload_too_large,
+            retryable=True,
+            should_compress=True,
+        )
+
+    # Usage-limit patterns need the same disambiguation as 402: some providers
+    # surface "usage limit" errors without an HTTP status code.  A transient
+    # signal ("try again", "resets at", …) means it's a periodic quota, not
+    # billing exhaustion.
+    has_usage_limit = any(p in error_msg for p in _USAGE_LIMIT_PATTERNS)
+    if has_usage_limit:
+        has_transient_signal = any(p in error_msg for p in _USAGE_LIMIT_TRANSIENT_SIGNALS)
+        if has_transient_signal:
+            return result_fn(
+                FailoverReason.rate_limit,
+                retryable=True,
+                should_rotate_credential=True,
+                should_fallback=True,
+            )
+        return result_fn(
+            FailoverReason.billing,
+            retryable=False,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+
+    # Billing patterns
+    if any(p in error_msg for p in _BILLING_PATTERNS):
+        return result_fn(
+            FailoverReason.billing,
+            retryable=False,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+
+    # Rate limit patterns
+    if any(p in error_msg for p in _RATE_LIMIT_PATTERNS):
+        return result_fn(
+            FailoverReason.rate_limit,
+            retryable=True,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+
+    # Context overflow patterns
+    if any(p in error_msg for p in _CONTEXT_OVERFLOW_PATTERNS):
+        return result_fn(
+            FailoverReason.context_overflow,
+            retryable=True,
+            should_compress=True,
+        )
+
+    # Auth patterns
+    # Auth errors should NOT be retried directly — the credential is invalid and
+    # retrying with the same key will always fail.  Set retryable=False so the
+    # caller triggers credential rotation (should_rotate_credential=True) or
+    # provider fallback rather than an immediate retry loop.
+    if any(p in error_msg for p in _AUTH_PATTERNS):
+        return result_fn(
+            FailoverReason.auth,
+            retryable=False,
+            should_rotate_credential=True,
+            should_fallback=True,
+        )
+
+    # Model not found patterns
+    if any(p in error_msg for p in _MODEL_NOT_FOUND_PATTERNS):
+        return result_fn(
+            FailoverReason.model_not_found,
+            retryable=False,
+            should_fallback=True,
+        )
+
+    return None
+
+
+# ── Helpers ─────────────────────────────────────────────────────────────
+
+def _extract_status_code(error: Exception) -> Optional[int]:
+    """Walk the error and its cause chain to find an HTTP status code."""
+    current = error
+    for _ in range(5):  # Max depth to prevent infinite loops
+        code = getattr(current, "status_code", None)
+        if isinstance(code, int):
+            return code
+        # Some SDKs use .status instead of .status_code
+        code = getattr(current, "status", None)
+        if isinstance(code, int) and 100 <= code < 600:
+            return code
+        # Walk cause chain
+        cause = getattr(current, "__cause__", None) or getattr(current, "__context__", None)
+        if cause is None or cause is current:
+            break
+        current = cause
+    return None
+
+
+def _extract_error_body(error: Exception) -> dict:
+    """Extract the structured error body from an SDK exception."""
+    body = getattr(error, "body", None)
+    if isinstance(body, dict):
+        return body
+    # Some errors have .response.json()
+    response = getattr(error, "response", None)
+    if response is not None:
+        try:
+            json_body = response.json()
+            if isinstance(json_body, dict):
+                return json_body
+        except Exception:
+            pass
+    return {}
+
+
+def _extract_error_code(body: dict) -> str:
+    """Extract an error code string from the response body."""
+    if not body:
+        return ""
+    error_obj = body.get("error", {})
+    if isinstance(error_obj, dict):
+        code = error_obj.get("code") or error_obj.get("type") or ""
+        if isinstance(code, str) and code.strip():
+            return code.strip()
+    # Top-level code
+    code = body.get("code") or body.get("error_code") or ""
+    if isinstance(code, (str, int)):
+        return str(code).strip()
+    return ""
+
+
+def _extract_message(error: Exception, body: dict) -> str:
+    """Extract the most informative error message."""
+    # Try structured body first
+    if body:
+        error_obj = body.get("error", {})
+        if isinstance(error_obj, dict):
+            msg = error_obj.get("message", "")
+            if isinstance(msg, str) and msg.strip():
+                return msg.strip()[:500]
+        msg = body.get("message", "")
+        if isinstance(msg, str) and msg.strip():
+            return msg.strip()[:500]
+    # Fallback to str(error)
+    return str(error)[:500]
@@ -39,15 +39,6 @@ def _has_known_pricing(model_name: str, provider: str = None, base_url: str = No
    return has_known_pricing(model_name, provider=provider, base_url=base_url)


-def _get_pricing(model_name: str) -> Dict[str, float]:
-    """Look up pricing for a model. Uses fuzzy matching on model name.
-
-    Returns _DEFAULT_PRICING (zero cost) for unknown/custom models —
-    we can't assume costs for self-hosted endpoints, local inference, etc.
-    """
-    return get_pricing(model_name)
-
-
 def _estimate_cost(
    session_or_model: Dict[str, Any] | str,
    input_tokens: int = 0,
@@ -134,11 +134,6 @@ class MemoryManager:
        """All registered providers in order."""
        return list(self._providers)

-    @property
-    def provider_names(self) -> List[str]:
-        """Names of all registered providers."""
-        return [p.name for p in self._providers]
-
    def get_provider(self, name: str) -> Optional[MemoryProvider]:
        """Get a provider by name, or None if not registered."""
        for p in self._providers:
@@ -26,12 +26,14 @@ _PROVIDER_PREFIXES: frozenset[str] = frozenset({
    "openrouter", "nous", "openai-codex", "copilot", "copilot-acp",
    "gemini", "zai", "kimi-coding", "minimax", "minimax-cn", "anthropic", "deepseek",
    "opencode-zen", "opencode-go", "ai-gateway", "kilocode", "alibaba",
+    "qwen-oauth",
    "custom", "local",
    # Common aliases
    "google", "google-gemini", "google-ai-studio",
    "glm", "z-ai", "z.ai", "zhipu", "github", "github-copilot",
    "github-models", "kimi", "moonshot", "claude", "deep-seek",
    "opencode", "zen", "go", "vercel", "kilo", "dashscope", "aliyun", "qwen",
+    "qwen-portal",
 })


@@ -113,10 +115,32 @@ DEFAULT_CONTEXT_LENGTHS = {
    "llama": 131072,
    # Qwen
    "qwen": 131072,
-    # MiniMax
-    "minimax": 204800,
+    # MiniMax (lowercase — lookup lowercases model names at line 973)
+    "minimax-m1-256k": 1000000,
+    "minimax-m1-128k": 1000000,
+    "minimax-m1-80k": 1000000,
+    "minimax-m1-40k": 1000000,
+    "minimax-m1": 1000000,
+    "minimax-m2.5": 1048576,
+    "minimax-m2.7": 1048576,
+    "minimax": 1048576,
    # GLM
    "glm": 202752,
+    # xAI Grok — xAI /v1/models does not return context_length metadata,
+    # so these hardcoded fallbacks prevent Hermes from probing-down to
+    # the default 128k when the user points at https://api.x.ai/v1
+    # via a custom provider. Values sourced from models.dev (2026-04).
+    # Keys use substring matching (longest-first), so e.g. "grok-4.20"
+    # matches "grok-4.20-0309-reasoning" / "-non-reasoning" / "-multi-agent-0309".
+    "grok-code-fast": 256000,   # grok-code-fast-1
+    "grok-4-1-fast": 2000000,   # grok-4-1-fast-(non-)reasoning
+    "grok-2-vision": 8192,      # grok-2-vision, -1212, -latest
+    "grok-4-fast": 2000000,     # grok-4-fast-(non-)reasoning
+    "grok-4.20": 2000000,       # grok-4.20-0309-(non-)reasoning, -multi-agent-0309
+    "grok-4": 256000,           # grok-4, grok-4-0709
+    "grok-3": 131072,           # grok-3, grok-3-mini, grok-3-fast, grok-3-mini-fast
+    "grok-2": 131072,           # grok-2, grok-2-1212, grok-2-latest
+    "grok": 131072,             # catch-all (grok-beta, unknown grok-*)
    # Kimi
    "kimi": 262144,
    # Arcee
@@ -127,7 +151,7 @@ DEFAULT_CONTEXT_LENGTHS = {
    "deepseek-ai/DeepSeek-V3.2": 65536,
    "moonshotai/Kimi-K2.5": 262144,
    "moonshotai/Kimi-K2-Thinking": 262144,
-    "MiniMaxAI/MiniMax-M2.5": 204800,
+    "MiniMaxAI/MiniMax-M2.5": 1048576,
    "XiaomiMiMo/MiMo-V2-Flash": 32768,
    "mimo-v2-pro": 1048576,
    "mimo-v2-omni": 1048576,
@@ -180,6 +204,7 @@ _URL_TO_PROVIDER: Dict[str, str] = {
    "api.minimax": "minimax",
    "dashscope.aliyuncs.com": "alibaba",
    "dashscope-intl.aliyuncs.com": "alibaba",
+    "portal.qwen.ai": "qwen-oauth",
    "openrouter.ai": "openrouter",
    "generativelanguage.googleapis.com": "gemini",
    "inference-api.nousresearch.com": "nous",
@@ -187,6 +212,7 @@ _URL_TO_PROVIDER: Dict[str, str] = {
    "api.githubcopilot.com": "copilot",
    "models.github.ai": "copilot",
    "api.fireworks.ai": "fireworks",
+    "opencode.ai": "opencode-go",
 }


@@ -592,6 +618,49 @@ def parse_context_limit_from_error(error_msg: str) -> Optional[int]:
    return None


+def parse_available_output_tokens_from_error(error_msg: str) -> Optional[int]:
+    """Detect an "output cap too large" error and return how many output tokens are available.
+
+    Background — two distinct context errors exist:
+      1. "Prompt too long"  — the INPUT itself exceeds the context window.
+           Fix: compress history and/or halve context_length.
+      2. "max_tokens too large" — input is fine, but input + requested_output > window.
+           Fix: reduce max_tokens (the output cap) for this call.
+           Do NOT touch context_length — the window hasn't shrunk.
+
+    Anthropic's API returns errors like:
+      "max_tokens: 32768 > context_window: 200000 - input_tokens: 190000 = available_tokens: 10000"
+
+    Returns the number of output tokens that would fit (e.g. 10000 above), or None if
+    the error does not look like a max_tokens-too-large error.
+    """
+    error_lower = error_msg.lower()
+
+    # Must look like an output-cap error, not a prompt-length error.
+    is_output_cap_error = (
+        "max_tokens" in error_lower
+        and ("available_tokens" in error_lower or "available tokens" in error_lower)
+    )
+    if not is_output_cap_error:
+        return None
+
+    # Extract the available_tokens figure.
+    # Anthropic format: "… = available_tokens: 10000"
+    patterns = [
+        r'available_tokens[:\s]+(\d+)',
+        r'available\s+tokens[:\s]+(\d+)',
+        # fallback: last number after "=" in expressions like "200000 - 190000 = 10000"
+        r'=\s*(\d+)\s*$',
+    ]
+    for pattern in patterns:
+        match = re.search(pattern, error_lower)
+        if match:
+            tokens = int(match.group(1))
+            if tokens >= 1:
+                return tokens
+    return None
+
+
 def _model_id_matches(candidate_id: str, lookup_model: str) -> bool:
    """Return True if *candidate_id* (from server) matches *lookup_model* (configured).

@@ -611,6 +680,59 @@ def _model_id_matches(candidate_id: str, lookup_model: str) -> bool:
    return False


+def query_ollama_num_ctx(model: str, base_url: str) -> Optional[int]:
+    """Query an Ollama server for the model's context length.
+
+    Returns the model's maximum context from GGUF metadata via ``/api/show``,
+    or the explicit ``num_ctx`` from the Modelfile if set.  Returns None if
+    the server is unreachable or not Ollama.
+
+    This is the value that should be passed as ``num_ctx`` in Ollama chat
+    requests to override the default 2048.
+    """
+    import httpx
+
+    bare_model = _strip_provider_prefix(model)
+    server_url = base_url.rstrip("/")
+    if server_url.endswith("/v1"):
+        server_url = server_url[:-3]
+
+    try:
+        server_type = detect_local_server_type(base_url)
+    except Exception:
+        return None
+    if server_type != "ollama":
+        return None
+
+    try:
+        with httpx.Client(timeout=3.0) as client:
+            resp = client.post(f"{server_url}/api/show", json={"name": bare_model})
+            if resp.status_code != 200:
+                return None
+            data = resp.json()
+
+            # Prefer explicit num_ctx from Modelfile parameters (user override)
+            params = data.get("parameters", "")
+            if "num_ctx" in params:
+                for line in params.split("\n"):
+                    if "num_ctx" in line:
+                        parts = line.strip().split()
+                        if len(parts) >= 2:
+                            try:
+                                return int(parts[-1])
+                            except ValueError:
+                                pass
+
+            # Fall back to GGUF model_info context_length (training max)
+            model_info = data.get("model_info", {})
+            for key, value in model_info.items():
+                if "context_length" in key and isinstance(value, (int, float)):
+                    return int(value)
+    except Exception:
+        pass
+    return None
+
+
 def _query_local_context_length(model: str, base_url: str) -> Optional[int]:
    """Query a local server for the model's context length."""
    import httpx
@@ -135,9 +135,6 @@ class ProviderInfo:
    doc: str = ""                   # documentation URL
    model_count: int = 0

-    def has_api_url(self) -> bool:
-        return bool(self.api)
-

 # ---------------------------------------------------------------------------
 # Provider ID mapping: Hermes ↔ models.dev
@@ -153,6 +150,7 @@ PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
    "minimax-cn": "minimax-cn",
    "deepseek": "deepseek",
    "alibaba": "alibaba",
+    "qwen-oauth": "alibaba",
    "copilot": "github-copilot",
    "ai-gateway": "vercel",
    "opencode-zen": "opencode",
@@ -633,43 +631,6 @@ def get_provider_info(provider_id: str) -> Optional[ProviderInfo]:
    return _parse_provider_info(mdev_id, raw)


-def list_all_providers() -> Dict[str, ProviderInfo]:
-    """Return all providers from models.dev as {provider_id: ProviderInfo}.
-
-    Returns the full catalog — 109+ providers.  For providers that have
-    a Hermes alias, both the models.dev ID and the Hermes ID are included.
-    """
-    data = fetch_models_dev()
-    result: Dict[str, ProviderInfo] = {}
-
-    for pid, pdata in data.items():
-        if isinstance(pdata, dict):
-            info = _parse_provider_info(pid, pdata)
-            result[pid] = info
-
-    return result
-
-
-def get_providers_for_env_var(env_var: str) -> List[str]:
-    """Reverse lookup: find all providers that use a given env var.
-
-    Useful for auto-detection: "user has ANTHROPIC_API_KEY set, which
-    providers does that enable?"
-
-    Returns list of models.dev provider IDs.
-    """
-    data = fetch_models_dev()
-    matches: List[str] = []
-
-    for pid, pdata in data.items():
-        if isinstance(pdata, dict):
-            env = pdata.get("env", [])
-            if isinstance(env, list) and env_var in env:
-                matches.append(pid)
-
-    return matches
-
-
 # ---------------------------------------------------------------------------
 # Model-level queries (rich ModelInfo)
 # ---------------------------------------------------------------------------
@@ -707,74 +668,3 @@ def get_model_info(
    return None


-def get_model_info_any_provider(model_id: str) -> Optional[ModelInfo]:
-    """Search all providers for a model by ID.
-
-    Useful when you have a full slug like "anthropic/claude-sonnet-4.6" or
-    a bare name and want to find it anywhere.  Checks Hermes-mapped providers
-    first, then falls back to all models.dev providers.
-    """
-    data = fetch_models_dev()
-
-    # Try Hermes-mapped providers first (more likely what the user wants)
-    for hermes_id, mdev_id in PROVIDER_TO_MODELS_DEV.items():
-        pdata = data.get(mdev_id)
-        if not isinstance(pdata, dict):
-            continue
-        models = pdata.get("models", {})
-        if not isinstance(models, dict):
-            continue
-
-        raw = models.get(model_id)
-        if isinstance(raw, dict):
-            return _parse_model_info(model_id, raw, mdev_id)
-
-        # Case-insensitive
-        model_lower = model_id.lower()
-        for mid, mdata in models.items():
-            if mid.lower() == model_lower and isinstance(mdata, dict):
-                return _parse_model_info(mid, mdata, mdev_id)
-
-    # Fall back to ALL providers
-    for pid, pdata in data.items():
-        if pid in _get_reverse_mapping():
-            continue  # already checked
-        if not isinstance(pdata, dict):
-            continue
-        models = pdata.get("models", {})
-        if not isinstance(models, dict):
-            continue
-
-        raw = models.get(model_id)
-        if isinstance(raw, dict):
-            return _parse_model_info(model_id, raw, pid)
-
-    return None
-
-
-def list_provider_model_infos(provider_id: str) -> List[ModelInfo]:
-    """Return all models for a provider as ModelInfo objects.
-
-    Filters out deprecated models by default.
-    """
-    mdev_id = PROVIDER_TO_MODELS_DEV.get(provider_id, provider_id)
-
-    data = fetch_models_dev()
-    pdata = data.get(mdev_id)
-    if not isinstance(pdata, dict):
-        return []
-
-    models = pdata.get("models", {})
-    if not isinstance(models, dict):
-        return []
-
-    result: List[ModelInfo] = []
-    for mid, mdata in models.items():
-        if not isinstance(mdata, dict):
-            continue
-        status = mdata.get("status", "")
-        if status == "deprecated":
-            continue
-        result.append(_parse_model_info(mid, mdata, mdev_id))
-
-    return result
@@ -40,7 +40,7 @@ _CONTEXT_THREAT_PATTERNS = [
    (r'disregard\s+(your|all|any)\s+(instructions|rules|guidelines)', "disregard_rules"),
    (r'act\s+as\s+(if|though)\s+you\s+(have\s+no|don\'t\s+have)\s+(restrictions|limits|rules)', "bypass_restrictions"),
    (r'<!--[^>]*(?:ignore|override|system|secret|hidden)[^>]*-->', "html_comment_injection"),
-    (r'<\s*div\s+style\s*=\s*["\'].*display\s*:\s*none', "hidden_div"),
+    (r'<\s*div\s+style\s*=\s*["\'][\s\S]*?display\s*:\s*none', "hidden_div"),
    (r'translate\s+.*\s+into\s+.*\s+and\s+(execute|run|eval)', "translate_execute"),
    (r'curl\s+[^\n]*\$\{?\w*(KEY|TOKEN|SECRET|PASSWORD|CREDENTIAL|API)', "exfil_curl"),
    (r'cat\s+[^\n]*(\.env|credentials|\.netrc|\.pgpass)', "read_secrets"),
@@ -204,6 +204,30 @@ OPENAI_MODEL_EXECUTION_GUIDANCE = (
    "the result.\n"
    "</tool_persistence>\n"
    "\n"
+    "<mandatory_tool_use>\n"
+    "NEVER answer these from memory or mental computation — ALWAYS use a tool:\n"
+    "- Arithmetic, math, calculations → use terminal or execute_code\n"
+    "- Hashes, encodings, checksums → use terminal (e.g. sha256sum, base64)\n"
+    "- Current time, date, timezone → use terminal (e.g. date)\n"
+    "- System state: OS, CPU, memory, disk, ports, processes → use terminal\n"
+    "- File contents, sizes, line counts → use read_file, search_files, or terminal\n"
+    "- Git history, branches, diffs → use terminal\n"
+    "- Current facts (weather, news, versions) → use web_search\n"
+    "Your memory and user profile describe the USER, not the system you are "
+    "running on. The execution environment may differ from what the user profile "
+    "says about their personal setup.\n"
+    "</mandatory_tool_use>\n"
+    "\n"
+    "<act_dont_ask>\n"
+    "When a question has an obvious default interpretation, act on it immediately "
+    "instead of asking for clarification. Examples:\n"
+    "- 'Is port 443 open?' → check THIS machine (don't ask 'open where?')\n"
+    "- 'What OS am I running?' → check the live system (don't use user profile)\n"
+    "- 'What time is it?' → run `date` (don't guess)\n"
+    "Only ask for clarification when the ambiguity genuinely changes what tool "
+    "you would call.\n"
+    "</act_dont_ask>\n"
+    "\n"
    "<prerequisite_checks>\n"
    "- Before taking an action, check whether prerequisite discovery, lookup, or "
    "context-gathering steps are needed.\n"
@@ -325,6 +349,13 @@ PLATFORM_HINTS = {
        "only — no markdown, no formatting. SMS messages are limited to ~1600 "
        "characters, so be brief and direct."
    ),
+    "bluebubbles": (
+        "You are chatting via iMessage (BlueBubbles). iMessage does not render "
+        "markdown formatting — use plain text. Keep responses concise as they "
+        "appear as text messages. You can send media files natively: include "
+        "MEDIA:/absolute/path/to/file in your response. Images (.jpg, .png, "
+        ".heic) appear as photos and other files arrive as attachments."
+    ),
 }

 CONTEXT_FILE_MAX_CHARS = 20_000
@@ -460,17 +491,6 @@ def _parse_skill_file(skill_file: Path) -> tuple[bool, dict, str]:
        return True, {}, ""


-def _read_skill_conditions(skill_file: Path) -> dict:
-    """Extract conditional activation fields from SKILL.md frontmatter."""
-    try:
-        raw = skill_file.read_text(encoding="utf-8")[:2000]
-        frontmatter, _ = parse_frontmatter(raw)
-        return extract_skill_conditions(frontmatter)
-    except Exception as e:
-        logger.debug("Failed to read skill conditions from %s: %s", skill_file, e)
-        return {}
-
-
 def _skill_should_show(
    conditions: dict,
    available_tools: "set[str] | None",
@@ -0,0 +1,242 @@
+"""Rate limit tracking for inference API responses.
+
+Captures x-ratelimit-* headers from provider responses and provides
+formatted display for the /usage slash command.  Currently supports
+the Nous Portal header format (also used by OpenRouter and OpenAI-compatible
+APIs that follow the same convention).
+
+Header schema (12 headers total):
+    x-ratelimit-limit-requests          RPM cap
+    x-ratelimit-limit-requests-1h       RPH cap
+    x-ratelimit-limit-tokens            TPM cap
+    x-ratelimit-limit-tokens-1h         TPH cap
+    x-ratelimit-remaining-requests      requests left in minute window
+    x-ratelimit-remaining-requests-1h   requests left in hour window
+    x-ratelimit-remaining-tokens        tokens left in minute window
+    x-ratelimit-remaining-tokens-1h     tokens left in hour window
+    x-ratelimit-reset-requests          seconds until minute request window resets
+    x-ratelimit-reset-requests-1h       seconds until hour request window resets
+    x-ratelimit-reset-tokens            seconds until minute token window resets
+    x-ratelimit-reset-tokens-1h         seconds until hour token window resets
+"""
+
+from __future__ import annotations
+
+import time
+from dataclasses import dataclass, field
+from typing import Any, Dict, Mapping, Optional
+
+
+@dataclass
+class RateLimitBucket:
+    """One rate-limit window (e.g. requests per minute)."""
+
+    limit: int = 0
+    remaining: int = 0
+    reset_seconds: float = 0.0
+    captured_at: float = 0.0  # time.time() when this was captured
+
+    @property
+    def used(self) -> int:
+        return max(0, self.limit - self.remaining)
+
+    @property
+    def usage_pct(self) -> float:
+        if self.limit <= 0:
+            return 0.0
+        return (self.used / self.limit) * 100.0
+
+    @property
+    def remaining_seconds_now(self) -> float:
+        """Estimated seconds remaining until reset, adjusted for elapsed time."""
+        elapsed = time.time() - self.captured_at
+        return max(0.0, self.reset_seconds - elapsed)
+
+
+@dataclass
+class RateLimitState:
+    """Full rate-limit state parsed from response headers."""
+
+    requests_min: RateLimitBucket = field(default_factory=RateLimitBucket)
+    requests_hour: RateLimitBucket = field(default_factory=RateLimitBucket)
+    tokens_min: RateLimitBucket = field(default_factory=RateLimitBucket)
+    tokens_hour: RateLimitBucket = field(default_factory=RateLimitBucket)
+    captured_at: float = 0.0  # when the headers were captured
+    provider: str = ""
+
+    @property
+    def has_data(self) -> bool:
+        return self.captured_at > 0
+
+    @property
+    def age_seconds(self) -> float:
+        if not self.has_data:
+            return float("inf")
+        return time.time() - self.captured_at
+
+
+def _safe_int(value: Any, default: int = 0) -> int:
+    try:
+        return int(float(value))
+    except (TypeError, ValueError):
+        return default
+
+
+def _safe_float(value: Any, default: float = 0.0) -> float:
+    try:
+        return float(value)
+    except (TypeError, ValueError):
+        return default
+
+
+def parse_rate_limit_headers(
+    headers: Mapping[str, str],
+    provider: str = "",
+) -> Optional[RateLimitState]:
+    """Parse x-ratelimit-* headers into a RateLimitState.
+
+    Returns None if no rate limit headers are present.
+    """
+    # Quick check: at least one rate limit header must exist
+    has_any = any(k.lower().startswith("x-ratelimit-") for k in headers)
+    if not has_any:
+        return None
+
+    now = time.time()
+
+    def _bucket(resource: str, suffix: str = "") -> RateLimitBucket:
+        # e.g. resource="requests", suffix="" -> per-minute
+        #      resource="tokens", suffix="-1h" -> per-hour
+        tag = f"{resource}{suffix}"
+        return RateLimitBucket(
+            limit=_safe_int(headers.get(f"x-ratelimit-limit-{tag}")),
+            remaining=_safe_int(headers.get(f"x-ratelimit-remaining-{tag}")),
+            reset_seconds=_safe_float(headers.get(f"x-ratelimit-reset-{tag}")),
+            captured_at=now,
+        )
+
+    return RateLimitState(
+        requests_min=_bucket("requests"),
+        requests_hour=_bucket("requests", "-1h"),
+        tokens_min=_bucket("tokens"),
+        tokens_hour=_bucket("tokens", "-1h"),
+        captured_at=now,
+        provider=provider,
+    )
+
+
+# ── Formatting ──────────────────────────────────────────────────────────
+
+
+def _fmt_count(n: int) -> str:
+    """Human-friendly number: 7999856 -> '8.0M', 33599 -> '33.6K', 799 -> '799'."""
+    if n >= 1_000_000:
+        return f"{n / 1_000_000:.1f}M"
+    if n >= 10_000:
+        return f"{n / 1_000:.1f}K"
+    if n >= 1_000:
+        return f"{n / 1_000:.1f}K"
+    return str(n)
+
+
+def _fmt_seconds(seconds: float) -> str:
+    """Seconds -> human-friendly duration: '58s', '2m 14s', '58m 57s', '1h 2m'."""
+    s = max(0, int(seconds))
+    if s < 60:
+        return f"{s}s"
+    if s < 3600:
+        m, sec = divmod(s, 60)
+        return f"{m}m {sec}s" if sec else f"{m}m"
+    h, remainder = divmod(s, 3600)
+    m = remainder // 60
+    return f"{h}h {m}m" if m else f"{h}h"
+
+
+def _bar(pct: float, width: int = 20) -> str:
+    """ASCII progress bar: [████████░░░░░░░░░░░░] 40%."""
+    filled = int(pct / 100.0 * width)
+    filled = max(0, min(width, filled))
+    empty = width - filled
+    return f"[{'█' * filled}{'░' * empty}]"
+
+
+def _bucket_line(label: str, bucket: RateLimitBucket, label_width: int = 14) -> str:
+    """Format one bucket as a single line."""
+    if bucket.limit <= 0:
+        return f"  {label:<{label_width}}  (no data)"
+
+    pct = bucket.usage_pct
+    used = _fmt_count(bucket.used)
+    limit = _fmt_count(bucket.limit)
+    remaining = _fmt_count(bucket.remaining)
+    reset = _fmt_seconds(bucket.remaining_seconds_now)
+
+    bar = _bar(pct)
+    return f"  {label:<{label_width}} {bar} {pct:5.1f}%  {used}/{limit} used  ({remaining} left, resets in {reset})"
+
+
+def format_rate_limit_display(state: RateLimitState) -> str:
+    """Format rate limit state for terminal/chat display."""
+    if not state.has_data:
+        return "No rate limit data yet — make an API request first."
+
+    age = state.age_seconds
+    if age < 5:
+        freshness = "just now"
+    elif age < 60:
+        freshness = f"{int(age)}s ago"
+    else:
+        freshness = f"{_fmt_seconds(age)} ago"
+
+    provider_label = state.provider.title() if state.provider else "Provider"
+
+    lines = [
+        f"{provider_label} Rate Limits (captured {freshness}):",
+        "",
+        _bucket_line("Requests/min", state.requests_min),
+        _bucket_line("Requests/hr", state.requests_hour),
+        "",
+        _bucket_line("Tokens/min", state.tokens_min),
+        _bucket_line("Tokens/hr", state.tokens_hour),
+    ]
+
+    # Add warnings if any bucket is getting hot
+    warnings = []
+    for label, bucket in [
+        ("requests/min", state.requests_min),
+        ("requests/hr", state.requests_hour),
+        ("tokens/min", state.tokens_min),
+        ("tokens/hr", state.tokens_hour),
+    ]:
+        if bucket.limit > 0 and bucket.usage_pct >= 80:
+            reset = _fmt_seconds(bucket.remaining_seconds_now)
+            warnings.append(f"  ⚠ {label} at {bucket.usage_pct:.0f}% — resets in {reset}")
+
+    if warnings:
+        lines.append("")
+        lines.extend(warnings)
+
+    return "\n".join(lines)
+
+
+def format_rate_limit_compact(state: RateLimitState) -> str:
+    """One-line compact summary for status bars / gateway messages."""
+    if not state.has_data:
+        return "No rate limit data."
+
+    rm = state.requests_min
+    tm = state.tokens_min
+    rh = state.requests_hour
+    th = state.tokens_hour
+
+    parts = []
+    if rm.limit > 0:
+        parts.append(f"RPM: {rm.remaining}/{rm.limit}")
+    if rh.limit > 0:
+        parts.append(f"RPH: {_fmt_count(rh.remaining)}/{_fmt_count(rh.limit)} (resets {_fmt_seconds(rh.remaining_seconds_now)})")
+    if tm.limit > 0:
+        parts.append(f"TPM: {_fmt_count(tm.remaining)}/{_fmt_count(tm.limit)}")
+    if th.limit > 0:
+        parts.append(f"TPH: {_fmt_count(th.remaining)}/{_fmt_count(th.limit)} (resets {_fmt_seconds(th.remaining_seconds_now)})")
+
+    return " | ".join(parts)
@@ -0,0 +1,57 @@
+"""Retry utilities — jittered backoff for decorrelated retries.
+
+Replaces fixed exponential backoff with jittered delays to prevent
+thundering-herd retry spikes when multiple sessions hit the same
+rate-limited provider concurrently.
+"""
+
+import random
+import threading
+import time
+
+# Monotonic counter for jitter seed uniqueness within the same process.
+# Protected by a lock to avoid race conditions in concurrent retry paths
+# (e.g. multiple gateway sessions retrying simultaneously).
+_jitter_counter = 0
+_jitter_lock = threading.Lock()
+
+
+def jittered_backoff(
+    attempt: int,
+    *,
+    base_delay: float = 5.0,
+    max_delay: float = 120.0,
+    jitter_ratio: float = 0.5,
+) -> float:
+    """Compute a jittered exponential backoff delay.
+
+    Args:
+        attempt: 1-based retry attempt number.
+        base_delay: Base delay in seconds for attempt 1.
+        max_delay: Maximum delay cap in seconds.
+        jitter_ratio: Fraction of computed delay to use as random jitter
+            range.  0.5 means jitter is uniform in [0, 0.5 * delay].
+
+    Returns:
+        Delay in seconds: min(base * 2^(attempt-1), max_delay) + jitter.
+
+    The jitter decorrelates concurrent retries so multiple sessions
+    hitting the same provider don't all retry at the same instant.
+    """
+    global _jitter_counter
+    with _jitter_lock:
+        _jitter_counter += 1
+        tick = _jitter_counter
+
+    exponent = max(0, attempt - 1)
+    if exponent >= 63 or base_delay <= 0:
+        delay = max_delay
+    else:
+        delay = min(base_delay * (2 ** exponent), max_delay)
+
+    # Seed from time + counter for decorrelation even with coarse clocks.
+    seed = (time.time_ns() ^ (tick * 0x9E3779B9)) & 0xFFFFFFFF
+    rng = random.Random(seed)
+    jitter = rng.uniform(0, jitter_ratio * delay)
+
+    return delay + jitter
@@ -159,7 +159,10 @@ class SubdirectoryHintTracker:

    def _is_valid_subdir(self, path: Path) -> bool:
        """Check if path is a valid directory to scan for hints."""
-        if not path.is_dir():
+        try:
+            if not path.is_dir():
+                return False
+        except OSError:
            return False
        if path in self._loaded_dirs:
            return False
@@ -172,7 +175,10 @@ class SubdirectoryHintTracker:
        found_hints = []
        for filename in _HINT_FILENAMES:
            hint_path = directory / filename
-            if not hint_path.is_file():
+            try:
+                if not hint_path.is_file():
+                    continue
+            except OSError:
                continue
            try:
                content = hint_path.read_text(encoding="utf-8").strip()
@@ -595,30 +595,6 @@ def get_pricing(
    }


-def estimate_cost_usd(
-    model: str,
-    input_tokens: int,
-    output_tokens: int,
-    *,
-    provider: Optional[str] = None,
-    base_url: Optional[str] = None,
-    api_key: Optional[str] = None,
-) -> float:
-    """Backward-compatible helper for legacy callers.
-
-    This uses non-cached input/output only. New code should call
-    `estimate_usage_cost()` with canonical usage buckets.
-    """
-    result = estimate_usage_cost(
-        model,
-        CanonicalUsage(input_tokens=input_tokens, output_tokens=output_tokens),
-        provider=provider,
-        base_url=base_url,
-        api_key=api_key,
-    )
-    return float(result.amount_usd or _ZERO)
-
-
 def format_duration_compact(seconds: float) -> str:
    if seconds < 60:
        return f"{seconds:.0f}s"
@@ -1158,7 +1158,7 @@ def main(
        providers_order (str): Comma-separated list of OpenRouter providers to try in order (e.g. "anthropic,openai,google")
        provider_sort (str): Sort providers by "price", "throughput", or "latency" (OpenRouter only)
        max_tokens (int): Maximum tokens for model responses (optional, uses model default if not set)
-        reasoning_effort (str): OpenRouter reasoning effort level: "xhigh", "high", "medium", "low", "minimal", "none" (default: "medium")
+        reasoning_effort (str): OpenRouter reasoning effort level: "none", "minimal", "low", "medium", "high", "xhigh" (default: "medium")
        reasoning_disabled (bool): Completely disable reasoning/thinking tokens (default: False)
        prefill_messages_file (str): Path to JSON file containing prefill messages (list of {role, content} dicts)
        max_samples (int): Only process the first N samples from the dataset (optional, processes all if not set)
@@ -1227,7 +1227,7 @@ def main(
        print("🧠 Reasoning: DISABLED (effort=none)")
    elif reasoning_effort:
        # Use specified effort level
-        valid_efforts = ["xhigh", "high", "medium", "low", "minimal", "none"]
+        valid_efforts = ["none", "minimal", "low", "medium", "high", "xhigh"]
        if reasoning_effort not in valid_efforts:
            print(f"❌ Error: --reasoning_effort must be one of: {', '.join(valid_efforts)}")
            return
@@ -48,6 +48,25 @@ model:
  # api_key: "your-key-here"  # Uncomment to set here instead of .env
  base_url: "https://openrouter.ai/api/v1"

+  # ── Token limits — two settings, easy to confuse ──────────────────────────
+  #
+  # context_length: TOTAL context window (input + output tokens combined).
+  #   Controls when Hermes compresses history and validates requests.
+  #   Leave unset — Hermes auto-detects the correct value from the provider.
+  #   Set manually only when auto-detection is wrong (e.g. a local server with
+  #   a custom num_ctx, or a proxy that doesn't expose /v1/models).
+  #
+  # context_length: 131072
+  #
+  # max_tokens: OUTPUT cap — maximum tokens the model may generate per response.
+  #   Unrelated to how long your conversation history can be.
+  #   The OpenAI-standard name "max_tokens" is a misnomer; Anthropic's native
+  #   API has since renamed it "max_output_tokens" for clarity.
+  #   Leave unset to use the model's native output ceiling (recommended).
+  #   Set only if you want to deliberately limit individual response length.
+  #
+  # max_tokens: 8192
+
 # =============================================================================
 # OpenRouter Provider Routing (only applies when using OpenRouter)
 # =============================================================================
@@ -117,7 +136,8 @@ terminal:
  timeout: 180
  docker_mount_cwd_to_workspace: false  # SECURITY: off by default. Opt in to mount the launch cwd into Docker /workspace.
  lifetime_seconds: 300
-  # sudo_password: ""  # Enable sudo commands (pipes via sudo -S) - SECURITY WARNING: plaintext!
+  # sudo_password: "hunter2"  # Optional: pipe a sudo password via sudo -S. SECURITY WARNING: plaintext.
+  # sudo_password: ""         # Explicit empty password: try empty and never open the interactive sudo prompt.

 # -----------------------------------------------------------------------------
 # OPTION 2: SSH remote execution
@@ -208,13 +228,18 @@ terminal:
 #
 # SECURITY WARNING: Password stored in plaintext!
 #
-# INTERACTIVE PROMPT: If no sudo_password is set and the CLI is running,
+# INTERACTIVE PROMPT: If sudo_password is unset and the CLI is running,
 # you'll be prompted to enter your password when sudo is needed:
 # - 45-second timeout (auto-skips if no input)
 # - Press Enter to skip (command fails gracefully)
 # - Password is hidden while typing
 # - Password is cached for the session
 #
+# EMPTY PASSWORDS: Setting sudo_password to an explicit empty string is different
+# from leaving it unset. Hermes will try an empty password via `sudo -S` and
+# will not open the interactive prompt. This is useful for passwordless sudo,
+# Touch ID sudo setups, and environments where prompting is just noise.
+#
 # ALTERNATIVES:
 # - SSH backend: Configure passwordless sudo on the remote server
 # - Containers: Run as root inside the container (no sudo needed)
@@ -445,6 +470,16 @@ agent:
  # Higher = more room for complex tasks, but costs more tokens
  # Recommended: 20-30 for focused tasks, 50-100 for open exploration
  max_turns: 60
+
+  # Inactivity timeout for gateway agent runs (seconds, 0 = unlimited).
+  # The agent can run indefinitely when actively calling tools or receiving
+  # API responses.  Only fires after the agent has been idle for this duration.
+  # gateway_timeout: 1800
+
+  # Staged warning: send a warning before escalating to full timeout.
+  # Fires once per run when inactivity reaches this threshold (seconds).
+  # Set to 0 to disable the warning.
+  # gateway_timeout_warning: 900
  
  # Enable verbose logging
  verbose: false
@@ -644,10 +679,18 @@ platform_toolsets:
 # Voice Transcription (Speech-to-Text)
 # =============================================================================
 # Automatically transcribe voice messages on messaging platforms.
-# Requires OPENAI_API_KEY in .env (uses OpenAI Whisper API directly).
+# Providers: local (free, faster-whisper) | groq (free tier) | openai (Whisper API) | mistral (Voxtral Transcribe)
+# Set the corresponding API key in .env: GROQ_API_KEY, OPENAI_API_KEY, or MISTRAL_API_KEY.
 stt:
  enabled: true
-  model: "whisper-1"  # whisper-1 (cheapest) | gpt-4o-mini-transcribe | gpt-4o-transcribe
+  # provider: "local"          # auto-detected if omitted
+  local:
+    model: "base"              # tiny | base | small | medium | large-v3 | turbo
+    # language: ""             # auto-detect; set to "en", "es", "fr", etc. to force
+  openai:
+    model: "whisper-1"         # whisper-1 | gpt-4o-mini-transcribe | gpt-4o-transcribe
+  # mistral:
+  #   model: "voxtral-mini-latest"  # voxtral-mini-latest | voxtral-mini-2602

 # =============================================================================
 # Response Pacing (Messaging Platforms)
@@ -0,0 +1,15 @@
+# Termux / Android dependency constraints for Hermes Agent.
+#
+# Usage:
+#   python -m pip install -e '.[termux]' -c constraints-termux.txt
+#
+# These pins keep the tested Android install path stable when upstream packages
+# move faster than Termux-compatible wheels / sdists.
+
+ipython<10
+jedi>=0.18.1,<0.20
+parso>=0.8.4,<0.9
+stack-data>=0.6,<0.7
+pexpect>4.3,<5
+matplotlib-inline>=0.1.7,<0.2
+asttokens>=2.1,<3
@@ -574,12 +574,16 @@ def remove_job(job_id: str) -> bool:
    return False


-def mark_job_run(job_id: str, success: bool, error: Optional[str] = None):
+def mark_job_run(job_id: str, success: bool, error: Optional[str] = None,
+                 delivery_error: Optional[str] = None):
    """
    Mark a job as having been run.
    
    Updates last_run_at, last_status, increments completed count,
    computes next_run_at, and auto-deletes if repeat limit reached.
+
+    ``delivery_error`` is tracked separately from the agent error — a job
+    can succeed (agent produced output) but fail delivery (platform down).
    """
    jobs = load_jobs()
    for i, job in enumerate(jobs):
@@ -588,6 +592,8 @@ def mark_job_run(job_id: str, success: bool, error: Optional[str] = None):
            job["last_run_at"] = now
            job["last_status"] = "ok" if success else "error"
            job["last_error"] = error if not success else None
+            # Track delivery failures separately — cleared on successful delivery
+            job["last_delivery_error"] = delivery_error
            
            # Increment completed count
            if job.get("repeat"):
@@ -44,7 +44,7 @@ logger = logging.getLogger(__name__)
 _KNOWN_DELIVERY_PLATFORMS = frozenset({
    "telegram", "discord", "slack", "whatsapp", "signal",
    "matrix", "mattermost", "homeassistant", "dingtalk", "feishu",
-    "wecom", "sms", "email", "webhook",
+    "wecom", "sms", "email", "webhook", "bluebubbles",
 })

 from cron.jobs import get_due_jobs, mark_job_run, save_job_output, advance_next_run
@@ -91,7 +91,7 @@ def _resolve_delivery_target(job: dict) -> Optional[dict]:
            }
        # Origin missing (e.g. job created via API/script) — try each
        # platform's home channel as a fallback instead of silently dropping.
-        for platform_name in ("matrix", "telegram", "discord", "slack"):
+        for platform_name in ("matrix", "telegram", "discord", "slack", "bluebubbles"):
            chat_id = os.getenv(f"{platform_name.upper()}_HOME_CHANNEL", "")
            if chat_id:
                logger.info(
@@ -196,7 +196,7 @@ def _send_media_via_adapter(adapter, chat_id: str, media_files: list, metadata:
            logger.warning("Job '%s': failed to send media %s: %s", job.get("id", "?"), media_path, e)


-def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> None:
+def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Optional[str]:
    """
    Deliver job output to the configured target (origin chat, specific platform, etc.).

@@ -204,16 +204,16 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> None:
    use the live adapter first — this supports E2EE rooms (e.g. Matrix) where
    the standalone HTTP path cannot encrypt.  Falls back to standalone send if
    the adapter path fails or is unavailable.
+
+    Returns None on success, or an error string on failure.
    """
    target = _resolve_delivery_target(job)
    if not target:
        if job.get("deliver", "local") != "local":
-            logger.warning(
-                "Job '%s' deliver=%s but no concrete delivery target could be resolved",
-                job["id"],
-                job.get("deliver", "local"),
-            )
-        return
+            msg = f"no delivery target resolved for deliver={job.get('deliver', 'local')}"
+            logger.warning("Job '%s': %s", job["id"], msg)
+            return msg
+        return None  # local-only jobs don't deliver — not a failure

    platform_name = target["platform"]
    chat_id = target["chat_id"]
@@ -236,22 +236,26 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> None:
        "wecom": Platform.WECOM,
        "email": Platform.EMAIL,
        "sms": Platform.SMS,
+        "bluebubbles": Platform.BLUEBUBBLES,
    }
    platform = platform_map.get(platform_name.lower())
    if not platform:
-        logger.warning("Job '%s': unknown platform '%s' for delivery", job["id"], platform_name)
-        return
+        msg = f"unknown platform '{platform_name}'"
+        logger.warning("Job '%s': %s", job["id"], msg)
+        return msg

    try:
        config = load_gateway_config()
    except Exception as e:
-        logger.error("Job '%s': failed to load gateway config for delivery: %s", job["id"], e)
-        return
+        msg = f"failed to load gateway config: {e}"
+        logger.error("Job '%s': %s", job["id"], msg)
+        return msg

    pconfig = config.platforms.get(platform)
    if not pconfig or not pconfig.enabled:
-        logger.warning("Job '%s': platform '%s' not configured/enabled", job["id"], platform_name)
-        return
+        msg = f"platform '{platform_name}' not configured/enabled"
+        logger.warning("Job '%s': %s", job["id"], msg)
+        return msg

    # Optionally wrap the content with a header/footer so the user knows this
    # is a cron delivery.  Wrapping is on by default; set cron.wrap_response: false
@@ -307,7 +311,7 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> None:

            if adapter_ok:
                logger.info("Job '%s': delivered to %s:%s via live adapter", job["id"], platform_name, chat_id)
-                return
+                return None
        except Exception as e:
            logger.warning(
                "Job '%s': live adapter delivery to %s:%s failed (%s), falling back to standalone",
@@ -329,16 +333,55 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> None:
            future = pool.submit(asyncio.run, _send_to_platform(platform, pconfig, chat_id, cleaned_delivery_content, thread_id=thread_id, media_files=media_files))
            result = future.result(timeout=30)
    except Exception as e:
-        logger.error("Job '%s': delivery to %s:%s failed: %s", job["id"], platform_name, chat_id, e)
-        return
+        msg = f"delivery to {platform_name}:{chat_id} failed: {e}"
+        logger.error("Job '%s': %s", job["id"], msg)
+        return msg

    if result and result.get("error"):
-        logger.error("Job '%s': delivery error: %s", job["id"], result["error"])
-    else:
-        logger.info("Job '%s': delivered to %s:%s", job["id"], platform_name, chat_id)
+        msg = f"delivery error: {result['error']}"
+        logger.error("Job '%s': %s", job["id"], msg)
+        return msg
+
+    logger.info("Job '%s': delivered to %s:%s", job["id"], platform_name, chat_id)
+    return None


-_SCRIPT_TIMEOUT = 120  # seconds
+_DEFAULT_SCRIPT_TIMEOUT = 120  # seconds
+# Backward-compatible module override used by tests and emergency monkeypatches.
+_SCRIPT_TIMEOUT = _DEFAULT_SCRIPT_TIMEOUT
+
+
+def _get_script_timeout() -> int:
+    """Resolve cron pre-run script timeout from module/env/config with a safe default."""
+    if _SCRIPT_TIMEOUT != _DEFAULT_SCRIPT_TIMEOUT:
+        try:
+            timeout = int(float(_SCRIPT_TIMEOUT))
+            if timeout > 0:
+                return timeout
+        except Exception:
+            logger.warning("Invalid patched _SCRIPT_TIMEOUT=%r; using env/config/default", _SCRIPT_TIMEOUT)
+
+    env_value = os.getenv("HERMES_CRON_SCRIPT_TIMEOUT", "").strip()
+    if env_value:
+        try:
+            timeout = int(float(env_value))
+            if timeout > 0:
+                return timeout
+        except Exception:
+            logger.warning("Invalid HERMES_CRON_SCRIPT_TIMEOUT=%r; using config/default", env_value)
+
+    try:
+        cfg = load_config() or {}
+        cron_cfg = cfg.get("cron", {}) if isinstance(cfg, dict) else {}
+        configured = cron_cfg.get("script_timeout_seconds")
+        if configured is not None:
+            timeout = int(float(configured))
+            if timeout > 0:
+                return timeout
+    except Exception as exc:
+        logger.debug("Failed to load cron script timeout from config: %s", exc)
+
+    return _DEFAULT_SCRIPT_TIMEOUT


 def _run_job_script(script_path: str) -> tuple[bool, str]:
@@ -385,12 +428,14 @@ def _run_job_script(script_path: str) -> tuple[bool, str]:
    if not path.is_file():
        return False, f"Script path is not a file: {path}"

+    script_timeout = _get_script_timeout()
+
    try:
        result = subprocess.run(
            [sys.executable, str(path)],
            capture_output=True,
            text=True,
-            timeout=_SCRIPT_TIMEOUT,
+            timeout=script_timeout,
            cwd=str(path.parent),
        )
        stdout = (result.stdout or "").strip()
@@ -414,7 +459,7 @@ def _run_job_script(script_path: str) -> tuple[bool, str]:
        return True, stdout

    except subprocess.TimeoutExpired:
-        return False, f"Script timed out after {_SCRIPT_TIMEOUT}s: {path}"
+        return False, f"Script timed out after {script_timeout}s: {path}"
    except Exception as exc:
        return False, f"Script execution failed: {exc}"

@@ -578,11 +623,9 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
        except Exception as e:
            logger.warning("Job '%s': failed to load config.yaml, using defaults: %s", job_id, e)

-        # Reasoning config from env or config.yaml
+        # Reasoning config from config.yaml
        from hermes_constants import parse_reasoning_effort
-        effort = os.getenv("HERMES_REASONING_EFFORT", "")
-        if not effort:
-            effort = str(_cfg.get("agent", {}).get("reasoning_effort", "")).strip()
+        effort = str(_cfg.get("agent", {}).get("reasoning_effort", "")).strip()
        reasoning_config = parse_reasoning_effort(effort)

        # Prefill messages from env or config.yaml
@@ -640,6 +683,24 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
            },
        )

+        fallback_model = _cfg.get("fallback_providers") or _cfg.get("fallback_model") or None
+        credential_pool = None
+        runtime_provider = str(turn_route["runtime"].get("provider") or "").strip().lower()
+        if runtime_provider:
+            try:
+                from agent.credential_pool import load_pool
+                pool = load_pool(runtime_provider)
+                if pool.has_credentials():
+                    credential_pool = pool
+                    logger.info(
+                        "Job '%s': loaded credential pool for provider %s with %d entries",
+                        job_id,
+                        runtime_provider,
+                        len(pool.entries()),
+                    )
+            except Exception as e:
+                logger.debug("Job '%s': failed to load credential pool for %s: %s", job_id, runtime_provider, e)
+
        agent = AIAgent(
            model=turn_route["model"],
            api_key=turn_route["runtime"].get("api_key"),
@@ -651,6 +712,8 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
            max_iterations=max_iterations,
            reasoning_config=reasoning_config,
            prefill_messages=prefill_messages,
+            fallback_model=fallback_model,
+            credential_pool=credential_pool,
            providers_allowed=pr.get("only"),
            providers_ignored=pr.get("ignore"),
            providers_order=pr.get("order"),
@@ -868,13 +931,15 @@ def tick(verbose: bool = True, adapters=None, loop=None) -> int:
                    logger.info("Job '%s': agent returned %s — skipping delivery", job["id"], SILENT_MARKER)
                    should_deliver = False

+                delivery_error = None
                if should_deliver:
                    try:
-                        _deliver_result(job, deliver_content, adapters=adapters, loop=loop)
+                        delivery_error = _deliver_result(job, deliver_content, adapters=adapters, loop=loop)
                    except Exception as de:
+                        delivery_error = str(de)
                        logger.error("Delivery failed for job %s: %s", job["id"], de)

-                mark_job_run(job["id"], success, error)
+                mark_job_run(job["id"], success, error, delivery_error=delivery_error)
                executed += 1

            except Exception as e:
@@ -21,6 +21,8 @@ from dataclasses import dataclass, field
 from typing import Any, Dict, List, Optional, Set

 from model_tools import handle_function_call
+from tools.terminal_tool import get_active_env
+from tools.tool_result_storage import maybe_persist_tool_result, enforce_turn_budget

 # Thread pool for running sync tool calls that internally use asyncio.run()
 # (e.g., the Modal/Docker/Daytona terminal backends). Running them in a separate
@@ -138,6 +140,7 @@ class HermesAgentLoop:
        temperature: float = 1.0,
        max_tokens: Optional[int] = None,
        extra_body: Optional[Dict[str, Any]] = None,
+        budget_config: Optional["BudgetConfig"] = None,
    ):
        """
        Initialize the agent loop.
@@ -154,7 +157,11 @@ class HermesAgentLoop:
            extra_body: Extra parameters passed to the OpenAI client's create() call.
                        Used for OpenRouter provider preferences, transforms, etc.
                        e.g. {"provider": {"ignore": ["DeepInfra"]}}
+            budget_config: Tool result persistence budget. Controls per-tool
+                        thresholds, per-turn aggregate budget, and preview size.
+                        If None, uses DEFAULT_BUDGET (current hardcoded values).
        """
+        from tools.budget_config import DEFAULT_BUDGET
        self.server = server
        self.tool_schemas = tool_schemas
        self.valid_tool_names = valid_tool_names
@@ -163,6 +170,7 @@ class HermesAgentLoop:
        self.temperature = temperature
        self.max_tokens = max_tokens
        self.extra_body = extra_body
+        self.budget_config = budget_config or DEFAULT_BUDGET

    async def run(self, messages: List[Dict[str, Any]]) -> AgentResult:
        """
@@ -446,8 +454,15 @@ class HermesAgentLoop:
                        except (json.JSONDecodeError, TypeError):
                            pass

-                    # Add tool response to conversation
                    tc_id = tc.get("id", "") if isinstance(tc, dict) else tc.id
+                    tool_result = maybe_persist_tool_result(
+                        content=tool_result,
+                        tool_name=tool_name,
+                        tool_use_id=tc_id,
+                        env=get_active_env(self.task_id),
+                        config=self.budget_config,
+                    )
+
                    messages.append(
                        {
                            "role": "tool",
@@ -456,6 +471,14 @@ class HermesAgentLoop:
                        }
                    )

+                num_tcs = len(assistant_msg.tool_calls)
+                if num_tcs > 0:
+                    enforce_turn_budget(
+                        messages[-num_tcs:],
+                        env=get_active_env(self.task_id),
+                        config=self.budget_config,
+                    )
+
                turn_elapsed = _time.monotonic() - turn_start
                logger.info(
                    "[%s] turn %d: api=%.1fs, %d tools, turn_total=%.1fs",
@@ -1048,6 +1048,7 @@ class AgenticOPDEnv(HermesAgentBaseEnv):
                    temperature=0.0,
                    max_tokens=self.config.max_token_length,
                    extra_body=self.config.extra_body,
+                    budget_config=self.config.build_budget_config(),
                )
                result = await agent.run(messages)

@@ -44,7 +44,7 @@ import tempfile
 import time
 import uuid
 from collections import defaultdict
-from pathlib import Path
+from pathlib import Path, PurePosixPath, PureWindowsPath
 from typing import Any, Dict, List, Optional, Tuple, Union

 # Ensure repo root is on sys.path for imports
@@ -148,6 +148,62 @@ MODAL_INCOMPATIBLE_TASKS = {
 # Tar extraction helper
 # =============================================================================

+def _normalize_tar_member_parts(member_name: str) -> list:
+    """Return safe path components for a tar member or raise ValueError."""
+    normalized_name = member_name.replace("\\", "/")
+    posix_path = PurePosixPath(normalized_name)
+    windows_path = PureWindowsPath(member_name)
+
+    if (
+        not normalized_name
+        or posix_path.is_absolute()
+        or windows_path.is_absolute()
+        or windows_path.drive
+    ):
+        raise ValueError(f"Unsafe archive member path: {member_name}")
+
+    parts = [part for part in posix_path.parts if part not in ("", ".")]
+    if not parts or any(part == ".." for part in parts):
+        raise ValueError(f"Unsafe archive member path: {member_name}")
+    return parts
+
+
+def _safe_extract_tar(tar: tarfile.TarFile, target_dir: Path) -> None:
+    """Extract a tar archive without allowing traversal or link entries."""
+    target_dir.mkdir(parents=True, exist_ok=True)
+    target_root = target_dir.resolve()
+
+    for member in tar.getmembers():
+        parts = _normalize_tar_member_parts(member.name)
+        target = target_dir.joinpath(*parts)
+        target_real = target.resolve(strict=False)
+
+        try:
+            target_real.relative_to(target_root)
+        except ValueError as exc:
+            raise ValueError(f"Unsafe archive member path: {member.name}") from exc
+
+        if member.isdir():
+            target_real.mkdir(parents=True, exist_ok=True)
+            continue
+
+        if not member.isfile():
+            raise ValueError(f"Unsupported archive member type: {member.name}")
+
+        target_real.parent.mkdir(parents=True, exist_ok=True)
+        extracted = tar.extractfile(member)
+        if extracted is None:
+            raise ValueError(f"Cannot read archive member: {member.name}")
+
+        with extracted, open(target_real, "wb") as dst:
+            shutil.copyfileobj(extracted, dst)
+
+        try:
+            os.chmod(target_real, member.mode & 0o777)
+        except OSError:
+            pass
+
+
 def _extract_base64_tar(b64_data: str, target_dir: Path):
    """Extract a base64-encoded tar.gz archive into target_dir."""
    if not b64_data:
@@ -155,7 +211,7 @@ def _extract_base64_tar(b64_data: str, target_dir: Path):
    raw = base64.b64decode(b64_data)
    buf = io.BytesIO(raw)
    with tarfile.open(fileobj=buf, mode="r:gz") as tar:
-        tar.extractall(path=str(target_dir))
+        _safe_extract_tar(tar, target_dir)


 # =============================================================================
@@ -485,6 +541,7 @@ class TerminalBench2EvalEnv(HermesAgentBaseEnv):
                        temperature=self.config.agent_temperature,
                        max_tokens=self.config.max_token_length,
                        extra_body=self.config.extra_body,
+                        budget_config=self.config.build_budget_config(),
                    )
                    result = await agent.run(messages)
            else:
@@ -497,6 +554,7 @@ class TerminalBench2EvalEnv(HermesAgentBaseEnv):
                    temperature=self.config.agent_temperature,
                    max_tokens=self.config.max_token_length,
                    extra_body=self.config.extra_body,
+                    budget_config=self.config.build_budget_config(),
                )
                result = await agent.run(messages)

@@ -549,6 +549,7 @@ class YCBenchEvalEnv(HermesAgentBaseEnv):
                temperature=self.config.agent_temperature,
                max_tokens=self.config.max_token_length,
                extra_body=self.config.extra_body,
+                budget_config=self.config.build_budget_config(),
            )
            result = await agent.run(messages)

@@ -62,6 +62,11 @@ from atroposlib.type_definitions import Item

 from environments.agent_loop import AgentResult, HermesAgentLoop
 from environments.tool_context import ToolContext
+from tools.budget_config import (
+    DEFAULT_RESULT_SIZE_CHARS,
+    DEFAULT_TURN_BUDGET_CHARS,
+    DEFAULT_PREVIEW_SIZE_CHARS,
+)

 # Import hermes-agent toolset infrastructure
 from model_tools import get_tool_definitions
@@ -160,6 +165,32 @@ class HermesAgentEnvConfig(BaseEnvConfig):
        "Options: hermes, mistral, llama3_json, qwen, deepseek_v3, etc.",
    )

+    # --- Tool result budget ---
+    # Defaults imported from tools.budget_config (single source of truth).
+    default_result_size_chars: int = Field(
+        default=DEFAULT_RESULT_SIZE_CHARS,
+        description="Default per-tool threshold (chars) for persisting large results "
+        "to sandbox. Results exceeding this are written to /tmp/hermes-results/ "
+        "and replaced with a preview. Per-tool registry values take precedence "
+        "unless overridden via tool_result_overrides.",
+    )
+    turn_budget_chars: int = Field(
+        default=DEFAULT_TURN_BUDGET_CHARS,
+        description="Aggregate char budget per assistant turn. If all tool results "
+        "in a single turn exceed this, the largest are persisted to disk first.",
+    )
+    preview_size_chars: int = Field(
+        default=DEFAULT_PREVIEW_SIZE_CHARS,
+        description="Size of the inline preview shown after a tool result is persisted.",
+    )
+    tool_result_overrides: Optional[Dict[str, int]] = Field(
+        default=None,
+        description="Per-tool threshold overrides (chars). Keys are tool names, "
+        "values are char thresholds. Overrides both the default and registry "
+        "per-tool values. Example: {'terminal': 10000, 'search_files': 5000}. "
+        "Note: read_file is pinned to infinity and cannot be overridden.",
+    )
+
    # --- Provider-specific parameters ---
    # Passed as extra_body to the OpenAI client's chat.completions.create() call.
    # Useful for OpenRouter provider preferences, transforms, route settings, etc.
@@ -176,6 +207,16 @@ class HermesAgentEnvConfig(BaseEnvConfig):
        "transforms, and other provider-specific settings.",
    )

+    def build_budget_config(self):
+        """Build a BudgetConfig from env config fields."""
+        from tools.budget_config import BudgetConfig
+        return BudgetConfig(
+            default_result_size=self.default_result_size_chars,
+            turn_budget=self.turn_budget_chars,
+            preview_size=self.preview_size_chars,
+            tool_overrides=dict(self.tool_result_overrides) if self.tool_result_overrides else {},
+        )
+

 class HermesAgentBaseEnv(BaseEnv):
    """
@@ -490,6 +531,7 @@ class HermesAgentBaseEnv(BaseEnv):
                        temperature=self.config.agent_temperature,
                        max_tokens=self.config.max_token_length,
                        extra_body=self.config.extra_body,
+                        budget_config=self.config.build_budget_config(),
                    )
                    result = await agent.run(messages)
            except NotImplementedError:
@@ -507,6 +549,7 @@ class HermesAgentBaseEnv(BaseEnv):
                    temperature=self.config.agent_temperature,
                    max_tokens=self.config.max_token_length,
                    extra_body=self.config.extra_body,
+                    budget_config=self.config.build_budget_config(),
                )
                result = await agent.run(messages)
        else:
@@ -520,6 +563,7 @@ class HermesAgentBaseEnv(BaseEnv):
                temperature=self.config.agent_temperature,
                max_tokens=self.config.max_token_length,
                extra_body=self.config.extra_body,
+                budget_config=self.config.build_budget_config(),
            )
            result = await agent.run(messages)

@@ -472,6 +472,7 @@ class WebResearchEnv(HermesAgentBaseEnv):
                    temperature=0.0,  # Deterministic for eval
                    max_tokens=self.config.max_token_length,
                    extra_body=self.config.extra_body,
+                    budget_config=self.config.build_budget_config(),
                )
                result = await agent.run(messages)

@@ -22,16 +22,16 @@
    },
    "nixpkgs": {
      "locked": {
-        "lastModified": 1751274312,
-        "narHash": "sha256-/bVBlRpECLVzjV19t5KMdMFWSwKLtb5RyXdjz3LJT+g=",
+        "lastModified": 1775036866,
+        "narHash": "sha256-ZojAnPuCdy657PbTq5V0Y+AHKhZAIwSIT2cb8UgAz/U=",
        "owner": "NixOS",
        "repo": "nixpkgs",
-        "rev": "50ab793786d9de88ee30ec4e4c24fb4236fc2674",
+        "rev": "6201e203d09599479a3b3450ed24fa81537ebc4e",
        "type": "github"
      },
      "original": {
        "owner": "NixOS",
-        "ref": "nixos-24.11",
+        "ref": "nixos-unstable",
        "repo": "nixpkgs",
        "type": "github"
      }
@@ -2,7 +2,7 @@
  description = "Hermes Agent - AI agent framework by Nous Research";

  inputs = {
-    nixpkgs.url = "github:NixOS/nixpkgs/nixos-24.11";
+    nixpkgs.url = "github:NixOS/nixpkgs/nixos-unstable";
    flake-parts = {
      url = "github:hercules-ci/flake-parts";
      inputs.nixpkgs-lib.follows = "nixpkgs";
@@ -77,7 +77,7 @@ def build_channel_directory(adapters: Dict[Any, Any]) -> Dict[str, Any]:
            logger.warning("Channel directory: failed to build %s: %s", platform.value, e)

    # Telegram, WhatsApp & Signal can't enumerate chats -- pull from session history
-    for plat_name in ("telegram", "whatsapp", "signal", "email", "sms"):
+    for plat_name in ("telegram", "whatsapp", "signal", "email", "sms", "bluebubbles"):
        if plat_name not in platforms:
            platforms[plat_name] = _build_from_sessions(plat_name)

@@ -63,6 +63,7 @@ class Platform(Enum):
    WEBHOOK = "webhook"
    FEISHU = "feishu"
    WECOM = "wecom"
+    BLUEBUBBLES = "bluebubbles"


@dataclass
@@ -287,6 +288,9 @@ class GatewayConfig:
            # WeCom uses extra dict for bot credentials
            elif platform == Platform.WECOM and config.extra.get("bot_id"):
                connected.append(platform)
+            # BlueBubbles uses extra dict for local server config
+            elif platform == Platform.BLUEBUBBLES and config.extra.get("server_url") and config.extra.get("password"):
+                connected.append(platform)
        return connected
    
    def get_home_channel(self, platform: Platform) -> Optional[HomeChannel]:
@@ -528,6 +532,8 @@ def load_gateway_config() -> GatewayConfig:
                    bridged["reply_prefix"] = platform_cfg["reply_prefix"]
                if "require_mention" in platform_cfg:
                    bridged["require_mention"] = platform_cfg["require_mention"]
+                if "free_response_channels" in platform_cfg:
+                    bridged["free_response_channels"] = platform_cfg["free_response_channels"]
                if "mention_patterns" in platform_cfg:
                    bridged["mention_patterns"] = platform_cfg["mention_patterns"]
                if not bridged:
@@ -542,6 +548,19 @@ def load_gateway_config() -> GatewayConfig:
                    plat_data["extra"] = extra
                extra.update(bridged)

+            # Slack settings → env vars (env vars take precedence)
+            slack_cfg = yaml_cfg.get("slack", {})
+            if isinstance(slack_cfg, dict):
+                if "require_mention" in slack_cfg and not os.getenv("SLACK_REQUIRE_MENTION"):
+                    os.environ["SLACK_REQUIRE_MENTION"] = str(slack_cfg["require_mention"]).lower()
+                if "allow_bots" in slack_cfg and not os.getenv("SLACK_ALLOW_BOTS"):
+                    os.environ["SLACK_ALLOW_BOTS"] = str(slack_cfg["allow_bots"]).lower()
+                frc = slack_cfg.get("free_response_channels")
+                if frc is not None and not os.getenv("SLACK_FREE_RESPONSE_CHANNELS"):
+                    if isinstance(frc, list):
+                        frc = ",".join(str(v) for v in frc)
+                    os.environ["SLACK_FREE_RESPONSE_CHANNELS"] = str(frc)
+
            # Discord settings → env vars (env vars take precedence)
            discord_cfg = yaml_cfg.get("discord", {})
            if isinstance(discord_cfg, dict):
@@ -556,6 +575,24 @@ def load_gateway_config() -> GatewayConfig:
                    os.environ["DISCORD_AUTO_THREAD"] = str(discord_cfg["auto_thread"]).lower()
                if "reactions" in discord_cfg and not os.getenv("DISCORD_REACTIONS"):
                    os.environ["DISCORD_REACTIONS"] = str(discord_cfg["reactions"]).lower()
+                # ignored_channels: channels where bot never responds (even when mentioned)
+                ic = discord_cfg.get("ignored_channels")
+                if ic is not None and not os.getenv("DISCORD_IGNORED_CHANNELS"):
+                    if isinstance(ic, list):
+                        ic = ",".join(str(v) for v in ic)
+                    os.environ["DISCORD_IGNORED_CHANNELS"] = str(ic)
+                # allowed_channels: if set, bot ONLY responds in these channels (whitelist)
+                ac = discord_cfg.get("allowed_channels")
+                if ac is not None and not os.getenv("DISCORD_ALLOWED_CHANNELS"):
+                    if isinstance(ac, list):
+                        ac = ",".join(str(v) for v in ac)
+                    os.environ["DISCORD_ALLOWED_CHANNELS"] = str(ac)
+                # no_thread_channels: channels where bot responds directly without creating thread
+                ntc = discord_cfg.get("no_thread_channels")
+                if ntc is not None and not os.getenv("DISCORD_NO_THREAD_CHANNELS"):
+                    if isinstance(ntc, list):
+                        ntc = ",".join(str(v) for v in ntc)
+                    os.environ["DISCORD_NO_THREAD_CHANNELS"] = str(ntc)

            # Telegram settings → env vars (env vars take precedence)
            telegram_cfg = yaml_cfg.get("telegram", {})
@@ -570,6 +607,8 @@ def load_gateway_config() -> GatewayConfig:
                    if isinstance(frc, list):
                        frc = ",".join(str(v) for v in frc)
                    os.environ["TELEGRAM_FREE_RESPONSE_CHATS"] = str(frc)
+                if "reactions" in telegram_cfg and not os.getenv("TELEGRAM_REACTIONS"):
+                    os.environ["TELEGRAM_REACTIONS"] = str(telegram_cfg["reactions"]).lower()

            whatsapp_cfg = yaml_cfg.get("whatsapp", {})
            if isinstance(whatsapp_cfg, dict):
@@ -698,6 +737,13 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
            name=os.getenv("DISCORD_HOME_CHANNEL_NAME", "Home"),
        )
    
+    # Reply threading mode for Discord (off/first/all)
+    discord_reply_mode = os.getenv("DISCORD_REPLY_TO_MODE", "").lower()
+    if discord_reply_mode in ("off", "first", "all"):
+        if Platform.DISCORD not in config.platforms:
+            config.platforms[Platform.DISCORD] = PlatformConfig()
+        config.platforms[Platform.DISCORD].reply_to_mode = discord_reply_mode
+    
    # WhatsApp (typically uses different auth mechanism)
    whatsapp_enabled = os.getenv("WHATSAPP_ENABLED", "").lower() in ("true", "1", "yes")
    if whatsapp_enabled:
@@ -861,6 +907,9 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
                pass
        if api_server_host:
            config.platforms[Platform.API_SERVER].extra["host"] = api_server_host
+        api_server_model_name = os.getenv("API_SERVER_MODEL_NAME", "")
+        if api_server_model_name:
+            config.platforms[Platform.API_SERVER].extra["model_name"] = api_server_model_name

    # Webhook platform
    webhook_enabled = os.getenv("WEBHOOK_ENABLED", "").lower() in ("true", "1", "yes")
@@ -927,6 +976,29 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
                name=os.getenv("WECOM_HOME_CHANNEL_NAME", "Home"),
            )

+    # BlueBubbles (iMessage)
+    bluebubbles_server_url = os.getenv("BLUEBUBBLES_SERVER_URL")
+    bluebubbles_password = os.getenv("BLUEBUBBLES_PASSWORD")
+    if bluebubbles_server_url and bluebubbles_password:
+        if Platform.BLUEBUBBLES not in config.platforms:
+            config.platforms[Platform.BLUEBUBBLES] = PlatformConfig()
+        config.platforms[Platform.BLUEBUBBLES].enabled = True
+        config.platforms[Platform.BLUEBUBBLES].extra.update({
+            "server_url": bluebubbles_server_url.rstrip("/"),
+            "password": bluebubbles_password,
+            "webhook_host": os.getenv("BLUEBUBBLES_WEBHOOK_HOST", "127.0.0.1"),
+            "webhook_port": int(os.getenv("BLUEBUBBLES_WEBHOOK_PORT", "8645")),
+            "webhook_path": os.getenv("BLUEBUBBLES_WEBHOOK_PATH", "/bluebubbles-webhook"),
+            "send_read_receipts": os.getenv("BLUEBUBBLES_SEND_READ_RECEIPTS", "true").lower() in ("true", "1", "yes"),
+        })
+    bluebubbles_home = os.getenv("BLUEBUBBLES_HOME_CHANNEL")
+    if bluebubbles_home and Platform.BLUEBUBBLES in config.platforms:
+        config.platforms[Platform.BLUEBUBBLES].home_channel = HomeChannel(
+            platform=Platform.BLUEBUBBLES,
+            chat_id=bluebubbles_home,
+            name=os.getenv("BLUEBUBBLES_HOME_CHANNEL_NAME", "Home"),
+        )
+
    # Session settings
    idle_minutes = os.getenv("SESSION_IDLE_MINUTES")
    if idle_minutes:
@@ -124,53 +124,6 @@ class DeliveryRouter:
        self.adapters = adapters or {}
        self.output_dir = get_hermes_home() / "cron" / "output"
    
-    def resolve_targets(
-        self,
-        deliver: Union[str, List[str]],
-        origin: Optional[SessionSource] = None
-    ) -> List[DeliveryTarget]:
-        """
-        Resolve delivery specification to concrete targets.
-        
-        Args:
-            deliver: Delivery spec - "origin", "telegram", ["local", "discord"], etc.
-            origin: The source where the request originated (for "origin" target)
-        
-        Returns:
-            List of resolved delivery targets
-        """
-        if isinstance(deliver, str):
-            deliver = [deliver]
-        
-        targets = []
-        seen_platforms = set()
-        
-        for target_str in deliver:
-            target = DeliveryTarget.parse(target_str, origin)
-            
-            # Resolve home channel if needed
-            if target.chat_id is None and target.platform != Platform.LOCAL:
-                home = self.config.get_home_channel(target.platform)
-                if home:
-                    target.chat_id = home.chat_id
-                else:
-                    # No home channel configured, skip this platform
-                    continue
-            
-            # Deduplicate
-            key = (target.platform, target.chat_id, target.thread_id)
-            if key not in seen_platforms:
-                seen_platforms.add(key)
-                targets.append(target)
-        
-        # Always include local if configured
-        if self.config.always_log_local:
-            local_key = (Platform.LOCAL, None, None)
-            if local_key not in seen_platforms:
-                targets.append(DeliveryTarget(platform=Platform.LOCAL))
-        
-        return targets
-    
    async def deliver(
        self,
        content: str,
@@ -299,19 +252,5 @@ class DeliveryRouter:
        return await adapter.send(target.chat_id, content, metadata=send_metadata or None)


-def parse_deliver_spec(
-    deliver: Optional[Union[str, List[str]]],
-    origin: Optional[SessionSource] = None,
-    default: str = "origin"
-) -> Union[str, List[str]]:
-    """
-    Normalize a delivery specification.
-    
-    If None or empty, returns the default.
-    """
-    if not deliver:
-        return default
-    return deliver
-


@@ -20,9 +20,12 @@ Requires:
 """

 import asyncio
+import hashlib
+import hmac
 import json
 import logging
 import os
+import re
 import sqlite3
 import time
 import uuid
@@ -281,6 +284,24 @@ def _make_request_fingerprint(body: Dict[str, Any], keys: List[str]) -> str:
    return sha256(repr(subset).encode("utf-8")).hexdigest()


+def _derive_chat_session_id(
+    system_prompt: Optional[str],
+    first_user_message: str,
+) -> str:
+    """Derive a stable session ID from the conversation's first user message.
+
+    OpenAI-compatible frontends (Open WebUI, LibreChat, etc.) send the full
+    conversation history with every request.  The system prompt and first user
+    message are constant across all turns of the same conversation, so hashing
+    them produces a deterministic session ID that lets the API server reuse
+    the same Hermes session (and therefore the same Docker container sandbox
+    directory) across turns.
+    """
+    seed = f"{system_prompt or ''}\n{first_user_message}"
+    digest = hashlib.sha256(seed.encode("utf-8")).hexdigest()[:16]
+    return f"api-{digest}"
+
+
 class APIServerAdapter(BasePlatformAdapter):
    """
    OpenAI-compatible HTTP API server adapter.
@@ -298,6 +319,9 @@ class APIServerAdapter(BasePlatformAdapter):
        self._cors_origins: tuple[str, ...] = self._parse_cors_origins(
            extra.get("cors_origins", os.getenv("API_SERVER_CORS_ORIGINS", "")),
        )
+        self._model_name: str = self._resolve_model_name(
+            extra.get("model_name", os.getenv("API_SERVER_MODEL_NAME", "")),
+        )
        self._app: Optional["web.Application"] = None
        self._runner: Optional["web.AppRunner"] = None
        self._site: Optional["web.TCPSite"] = None
@@ -323,6 +347,26 @@ class APIServerAdapter(BasePlatformAdapter):

        return tuple(str(item).strip() for item in items if str(item).strip())

+    @staticmethod
+    def _resolve_model_name(explicit: str) -> str:
+        """Derive the advertised model name for /v1/models.
+
+        Priority:
+        1. Explicit override (config extra or API_SERVER_MODEL_NAME env var)
+        2. Active profile name (so each profile advertises a distinct model)
+        3. Fallback: "hermes-agent"
+        """
+        if explicit and explicit.strip():
+            return explicit.strip()
+        try:
+            from hermes_cli.profiles import get_active_profile_name
+            profile = get_active_profile_name()
+            if profile and profile not in ("default", "custom"):
+                return profile
+        except Exception:
+            pass
+        return "hermes-agent"
+
    def _cors_headers_for_origin(self, origin: str) -> Optional[Dict[str, str]]:
        """Return CORS headers for an allowed browser origin."""
        if not origin or not self._cors_origins:
@@ -370,7 +414,7 @@ class APIServerAdapter(BasePlatformAdapter):
        auth_header = request.headers.get("Authorization", "")
        if auth_header.startswith("Bearer "):
            token = auth_header[7:].strip()
-            if token == self._api_key:
+            if hmac.compare_digest(token, self._api_key):
                return None  # Auth OK

        return web.json_response(
@@ -467,12 +511,12 @@ class APIServerAdapter(BasePlatformAdapter):
            "object": "list",
            "data": [
                {
-                    "id": "hermes-agent",
+                    "id": self._model_name,
                    "object": "model",
                    "created": int(time.time()),
                    "owned_by": "hermes",
                    "permission": [],
-                    "root": "hermes-agent",
+                    "root": self._model_name,
                    "parent": None,
                }
            ],
@@ -530,8 +574,32 @@ class APIServerAdapter(BasePlatformAdapter):

        # Allow caller to continue an existing session by passing X-Hermes-Session-Id.
        # When provided, history is loaded from state.db instead of from the request body.
+        #
+        # Security: session continuation exposes conversation history, so it is
+        # only allowed when the API key is configured and the request is
+        # authenticated.  Without this gate, any unauthenticated client could
+        # read arbitrary session history by guessing/enumerating session IDs.
        provided_session_id = request.headers.get("X-Hermes-Session-Id", "").strip()
        if provided_session_id:
+            if not self._api_key:
+                logger.warning(
+                    "Session continuation via X-Hermes-Session-Id rejected: "
+                    "no API key configured.  Set API_SERVER_KEY to enable "
+                    "session continuity."
+                )
+                return web.json_response(
+                    _openai_error(
+                        "Session continuation requires API key authentication. "
+                        "Configure API_SERVER_KEY to enable this feature."
+                    ),
+                    status=403,
+                )
+            # Sanitize: reject control characters that could enable header injection.
+            if re.search(r'[\r\n\x00]', provided_session_id):
+                return web.json_response(
+                    {"error": {"message": "Invalid session ID", "type": "invalid_request_error"}},
+                    status=400,
+                )
            session_id = provided_session_id
            try:
                db = self._ensure_session_db()
@@ -541,11 +609,20 @@ class APIServerAdapter(BasePlatformAdapter):
                logger.warning("Failed to load session history for %s: %s", session_id, e)
                history = []
        else:
-            session_id = str(uuid.uuid4())
+            # Derive a stable session ID from the conversation fingerprint so
+            # that consecutive messages from the same Open WebUI (or similar)
+            # conversation map to the same Hermes session.  The first user
+            # message + system prompt are constant across all turns.
+            first_user = ""
+            for cm in conversation_messages:
+                if cm.get("role") == "user":
+                    first_user = cm.get("content", "")
+                    break
+            session_id = _derive_chat_session_id(system_prompt, first_user)
            # history already set from request body above

        completion_id = f"chatcmpl-{uuid.uuid4().hex[:29]}"
-        model_name = body.get("model", "hermes-agent")
+        model_name = body.get("model", self._model_name)
        created = int(time.time())

        if stream:
@@ -563,8 +640,10 @@ class APIServerAdapter(BasePlatformAdapter):
                if delta is not None:
                    _stream_q.put(delta)

-            def _on_tool_progress(name, preview, args):
+            def _on_tool_progress(event_type, name, preview, args, **kwargs):
                """Inject tool progress into the SSE stream for Open WebUI."""
+                if event_type != "tool.started":
+                    return  # Only show tool start events in chat stream
                if name.startswith("_"):
                    return  # Skip internal events (_thinking)
                from agent.display import get_tool_emoji
@@ -815,9 +894,29 @@ class APIServerAdapter(BasePlatformAdapter):
        else:
            return web.json_response(_openai_error("'input' must be a string or array"), status=400)

-        # Reconstruct conversation history from previous_response_id
+        # Accept explicit conversation_history from the request body.
+        # This lets stateless clients supply their own history instead of
+        # relying on server-side response chaining via previous_response_id.
+        # Precedence: explicit conversation_history > previous_response_id.
        conversation_history: List[Dict[str, str]] = []
-        if previous_response_id:
+        raw_history = body.get("conversation_history")
+        if raw_history:
+            if not isinstance(raw_history, list):
+                return web.json_response(
+                    _openai_error("'conversation_history' must be an array of message objects"),
+                    status=400,
+                )
+            for i, entry in enumerate(raw_history):
+                if not isinstance(entry, dict) or "role" not in entry or "content" not in entry:
+                    return web.json_response(
+                        _openai_error(f"conversation_history[{i}] must have 'role' and 'content' fields"),
+                        status=400,
+                    )
+                conversation_history.append({"role": str(entry["role"]), "content": str(entry["content"])})
+            if previous_response_id:
+                logger.debug("Both conversation_history and previous_response_id provided; using conversation_history")
+
+        if not conversation_history and previous_response_id:
            stored = self._response_store.get(previous_response_id)
            if stored is None:
                return web.json_response(_openai_error(f"Previous response not found: {previous_response_id}"), status=404)
@@ -900,7 +999,7 @@ class APIServerAdapter(BasePlatformAdapter):
            "object": "response",
            "status": "completed",
            "created_at": created_at,
-            "model": body.get("model", "hermes-agent"),
+            "model": body.get("model", self._model_name),
            "output": output_items,
            "usage": {
                "input_tokens": usage.get("input_tokens", 0),
@@ -1295,6 +1394,7 @@ class APIServerAdapter(BasePlatformAdapter):
            result = agent.run_conversation(
                user_message=user_message,
                conversation_history=conversation_history,
+                task_id="default",
            )
            usage = {
                "input_tokens": getattr(agent, "session_prompt_tokens", 0) or 0,
@@ -1403,14 +1503,49 @@ class APIServerAdapter(BasePlatformAdapter):

        instructions = body.get("instructions")
        previous_response_id = body.get("previous_response_id")
+
+        # Accept explicit conversation_history from the request body.
+        # Precedence: explicit conversation_history > previous_response_id.
        conversation_history: List[Dict[str, str]] = []
-        if previous_response_id:
+        raw_history = body.get("conversation_history")
+        if raw_history:
+            if not isinstance(raw_history, list):
+                return web.json_response(
+                    _openai_error("'conversation_history' must be an array of message objects"),
+                    status=400,
+                )
+            for i, entry in enumerate(raw_history):
+                if not isinstance(entry, dict) or "role" not in entry or "content" not in entry:
+                    return web.json_response(
+                        _openai_error(f"conversation_history[{i}] must have 'role' and 'content' fields"),
+                        status=400,
+                    )
+                conversation_history.append({"role": str(entry["role"]), "content": str(entry["content"])})
+            if previous_response_id:
+                logger.debug("Both conversation_history and previous_response_id provided; using conversation_history")
+
+        if not conversation_history and previous_response_id:
            stored = self._response_store.get(previous_response_id)
            if stored:
                conversation_history = list(stored.get("conversation_history", []))
                if instructions is None:
                    instructions = stored.get("instructions")

+        # When input is a multi-message array, extract all but the last
+        # message as conversation history (the last becomes user_message).
+        # Only fires when no explicit history was provided.
+        if not conversation_history and isinstance(raw_input, list) and len(raw_input) > 1:
+            for msg in raw_input[:-1]:
+                if isinstance(msg, dict) and msg.get("role") and msg.get("content"):
+                    content = msg["content"]
+                    if isinstance(content, list):
+                        # Flatten multi-part content blocks to text
+                        content = " ".join(
+                            part.get("text", "") for part in content
+                            if isinstance(part, dict) and part.get("type") == "text"
+                        )
+                    conversation_history.append({"role": msg["role"], "content": str(content)})
+
        session_id = body.get("session_id") or run_id
        ephemeral_system_prompt = instructions

@@ -1426,6 +1561,7 @@ class APIServerAdapter(BasePlatformAdapter):
                    r = agent.run_conversation(
                        user_message=user_message,
                        conversation_history=conversation_history,
+                        task_id="default",
                    )
                    u = {
                        "input_tokens": getattr(agent, "session_prompt_tokens", 0) or 0,
@@ -1594,9 +1730,17 @@ class APIServerAdapter(BasePlatformAdapter):
            await self._site.start()

            self._mark_connected()
+            if not self._api_key:
+                logger.warning(
+                    "[%s] ⚠️  No API key configured (API_SERVER_KEY / platforms.api_server.key). "
+                    "All requests will be accepted without authentication. "
+                    "Set an API key for production deployments to prevent "
+                    "unauthorized access to sessions, responses, and cron jobs.",
+                    self.name,
+                )
            logger.info(
-                "[%s] API server listening on http://%s:%d",
-                self.name, self._host, self._port,
+                "[%s] API server listening on http://%s:%d (model: %s)",
+                self.name, self._host, self._port, self._model_name,
            )
            return True

@@ -10,18 +10,142 @@ import logging
 import os
 import random
 import re
+import subprocess
+import sys
 import uuid
 from abc import ABC, abstractmethod
 from urllib.parse import urlsplit

 logger = logging.getLogger(__name__)
+
+
+def _detect_macos_system_proxy() -> str | None:
+    """Read the macOS system HTTP(S) proxy via ``scutil --proxy``.
+
+    Returns an ``http://host:port`` URL string if an HTTP or HTTPS proxy is
+    enabled, otherwise *None*.  Falls back silently on non-macOS or on any
+    subprocess error.
+    """
+    if sys.platform != "darwin":
+        return None
+    try:
+        out = subprocess.check_output(
+            ["scutil", "--proxy"], timeout=3, text=True, stderr=subprocess.DEVNULL,
+        )
+    except Exception:
+        return None
+
+    props: dict[str, str] = {}
+    for line in out.splitlines():
+        line = line.strip()
+        if " : " in line:
+            key, _, val = line.partition(" : ")
+            props[key.strip()] = val.strip()
+
+    # Prefer HTTPS, fall back to HTTP
+    for enable_key, host_key, port_key in (
+        ("HTTPSEnable", "HTTPSProxy", "HTTPSPort"),
+        ("HTTPEnable", "HTTPProxy", "HTTPPort"),
+    ):
+        if props.get(enable_key) == "1":
+            host = props.get(host_key)
+            port = props.get(port_key)
+            if host and port:
+                return f"http://{host}:{port}"
+    return None
+
+
+def resolve_proxy_url(platform_env_var: str | None = None) -> str | None:
+    """Return a proxy URL from env vars, or macOS system proxy.
+
+    Check order:
+      0. *platform_env_var* (e.g. ``DISCORD_PROXY``) — highest priority
+      1. HTTPS_PROXY / HTTP_PROXY / ALL_PROXY (and lowercase variants)
+      2. macOS system proxy via ``scutil --proxy`` (auto-detect)
+
+    Returns *None* if no proxy is found.
+    """
+    if platform_env_var:
+        value = (os.environ.get(platform_env_var) or "").strip()
+        if value:
+            return value
+    for key in ("HTTPS_PROXY", "HTTP_PROXY", "ALL_PROXY",
+                "https_proxy", "http_proxy", "all_proxy"):
+        value = (os.environ.get(key) or "").strip()
+        if value:
+            return value
+    return _detect_macos_system_proxy()
+
+
+def proxy_kwargs_for_bot(proxy_url: str | None) -> dict:
+    """Build kwargs for ``commands.Bot()`` / ``discord.Client()`` with proxy.
+
+    Returns:
+      - SOCKS URL  → ``{"connector": ProxyConnector(..., rdns=True)}``
+      - HTTP URL   → ``{"proxy": url}``
+      - *None*     → ``{}``
+
+    ``rdns=True`` forces remote DNS resolution through the proxy — required
+    by many SOCKS implementations (Shadowrocket, Clash) and essential for
+    bypassing DNS pollution behind the GFW.
+    """
+    if not proxy_url:
+        return {}
+    if proxy_url.lower().startswith("socks"):
+        try:
+            from aiohttp_socks import ProxyConnector
+
+            connector = ProxyConnector.from_url(proxy_url, rdns=True)
+            return {"connector": connector}
+        except ImportError:
+            logger.warning(
+                "aiohttp_socks not installed — SOCKS proxy %s ignored. "
+                "Run: pip install aiohttp-socks",
+                proxy_url,
+            )
+            return {}
+    return {"proxy": proxy_url}
+
+
+def proxy_kwargs_for_aiohttp(proxy_url: str | None) -> tuple[dict, dict]:
+    """Build kwargs for standalone ``aiohttp.ClientSession`` with proxy.
+
+    Returns ``(session_kwargs, request_kwargs)`` where:
+      - SOCKS → ``({"connector": ProxyConnector(...)}, {})``
+      - HTTP  → ``({}, {"proxy": url})``
+      - None  → ``({}, {})``
+
+    Usage::
+
+        sess_kw, req_kw = proxy_kwargs_for_aiohttp(proxy_url)
+        async with aiohttp.ClientSession(**sess_kw) as session:
+            async with session.get(url, **req_kw) as resp:
+                ...
+    """
+    if not proxy_url:
+        return {}, {}
+    if proxy_url.lower().startswith("socks"):
+        try:
+            from aiohttp_socks import ProxyConnector
+
+            connector = ProxyConnector.from_url(proxy_url, rdns=True)
+            return {"connector": connector}, {}
+        except ImportError:
+            logger.warning(
+                "aiohttp_socks not installed — SOCKS proxy %s ignored. "
+                "Run: pip install aiohttp-socks",
+                proxy_url,
+            )
+            return {}, {}
+    return {}, {"proxy": proxy_url}
+
+
 from dataclasses import dataclass, field
 from datetime import datetime
 from pathlib import Path
 from typing import Dict, List, Optional, Any, Callable, Awaitable, Tuple
 from enum import Enum

-import sys
 from pathlib import Path as _Path
 sys.path.insert(0, str(_Path(__file__).resolve().parents[2]))

@@ -92,6 +216,23 @@ def get_image_cache_dir() -> Path:
    return IMAGE_CACHE_DIR


+def _looks_like_image(data: bytes) -> bool:
+    """Return True if *data* starts with a known image magic-byte sequence."""
+    if len(data) < 4:
+        return False
+    if data[:8] == b"\x89PNG\r\n\x1a\n":
+        return True
+    if data[:3] == b"\xff\xd8\xff":
+        return True
+    if data[:6] in (b"GIF87a", b"GIF89a"):
+        return True
+    if data[:2] == b"BM":
+        return True
+    if data[:4] == b"RIFF" and len(data) >= 12 and data[8:12] == b"WEBP":
+        return True
+    return False
+
+
 def cache_image_from_bytes(data: bytes, ext: str = ".jpg") -> str:
    """
    Save raw image bytes to the cache and return the absolute file path.
@@ -102,7 +243,17 @@ def cache_image_from_bytes(data: bytes, ext: str = ".jpg") -> str:

    Returns:
        Absolute path to the cached image file as a string.
+
+    Raises:
+        ValueError: If *data* does not look like a valid image (e.g. an HTML
+            error page returned by the upstream server).
    """
+    if not _looks_like_image(data):
+        snippet = data[:80].decode("utf-8", errors="replace")
+        raise ValueError(
+            f"Refusing to cache non-image data as {ext} "
+            f"(starts with: {snippet!r})"
+        )
    cache_dir = get_image_cache_dir()
    filename = f"img_{uuid.uuid4().hex[:12]}{ext}"
    filepath = cache_dir / filename
@@ -124,7 +275,14 @@ async def cache_image_from_url(url: str, ext: str = ".jpg", retries: int = 2) ->

    Returns:
        Absolute path to the cached image file as a string.
+
+    Raises:
+        ValueError: If the URL targets a private/internal network (SSRF protection).
    """
+    from tools.url_safety import is_safe_url
+    if not is_safe_url(url):
+        raise ValueError(f"Blocked unsafe URL (SSRF protection): {_safe_url_for_log(url)}")
+
    import asyncio
    import httpx
    import logging as _logging
@@ -232,7 +390,14 @@ async def cache_audio_from_url(url: str, ext: str = ".ogg", retries: int = 2) ->

    Returns:
        Absolute path to the cached audio file as a string.
+
+    Raises:
+        ValueError: If the URL targets a private/internal network (SSRF protection).
    """
+    from tools.url_safety import is_safe_url
+    if not is_safe_url(url):
+        raise ValueError(f"Blocked unsafe URL (SSRF protection): {_safe_url_for_log(url)}")
+
    import asyncio
    import httpx
    import logging as _logging
@@ -284,6 +449,7 @@ SUPPORTED_DOCUMENT_TYPES = {
    ".pdf": "application/pdf",
    ".md": "text/markdown",
    ".txt": "text/plain",
+    ".log": "text/plain",
    ".zip": "application/zip",
    ".docx": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
    ".xlsx": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
@@ -363,6 +529,14 @@ class MessageType(Enum):
    COMMAND = "command"  # /command style


+class ProcessingOutcome(Enum):
+    """Result classification for message-processing lifecycle hooks."""
+
+    SUCCESS = "success"
+    FAILURE = "failure"
+    CANCELLED = "cancelled"
+
+
@dataclass
 class MessageEvent:
    """
@@ -393,6 +567,10 @@ class MessageEvent:
    # Auto-loaded skill for topic/channel bindings (e.g., Telegram DM Topics)
    auto_skill: Optional[str] = None
    
+    # Internal flag — set for synthetic events (e.g. background process
+    # completion notifications) that must bypass user authorization checks.
+    internal: bool = False
+
    # Timestamps
    timestamp: datetime = field(default_factory=datetime.now)
    
@@ -482,6 +660,7 @@ class BasePlatformAdapter(ABC):
        # Gateway shutdown cancels these so an old gateway instance doesn't keep
        # working on a task after --replace or manual restarts.
        self._background_tasks: set[asyncio.Task] = set()
+        self._expected_cancelled_tasks: set[asyncio.Task] = set()
        # Chats where auto-TTS on voice input is disabled (set by /voice off)
        self._auto_tts_disabled_chats: set = set()
        # Chats where typing indicator is paused (e.g. during approval waits).
@@ -990,7 +1169,7 @@ class BasePlatformAdapter(ABC):
    async def on_processing_start(self, event: MessageEvent) -> None:
        """Hook called when background processing begins."""

-    async def on_processing_complete(self, event: MessageEvent, success: bool) -> None:
+    async def on_processing_complete(self, event: MessageEvent, outcome: ProcessingOutcome) -> None:
        """Hook called when background processing completes."""

    async def _run_processing_hook(self, hook_name: str, *args: Any, **kwargs: Any) -> None:
@@ -1105,6 +1284,22 @@ class BasePlatformAdapter(ABC):
            logger.error("[%s] Fallback send also failed: %s", self.name, fallback_result.error)
        return fallback_result

+    @staticmethod
+    def _merge_caption(existing_text: Optional[str], new_text: str) -> str:
+        """Merge a new caption into existing text, avoiding duplicates.
+
+        Uses line-by-line exact match (not substring) to prevent false positives
+        where a shorter caption is silently dropped because it appears as a
+        substring of a longer one (e.g. "Meeting" inside "Meeting agenda").
+        Whitespace is normalised for comparison.
+        """
+        if not existing_text:
+            return new_text
+        existing_captions = [c.strip() for c in existing_text.split("\n\n")]
+        if new_text.strip() not in existing_captions:
+            return f"{existing_text}\n\n{new_text}".strip()
+        return existing_text
+
    async def handle_message(self, event: MessageEvent) -> None:
        """
        Process an incoming message.
@@ -1135,7 +1330,7 @@ class BasePlatformAdapter(ABC):
            # session lifecycle and its cleanup races with the running task
            # (see PR #4926).
            cmd = event.get_command()
-            if cmd in ("approve", "deny", "status", "stop", "new", "reset"):
+            if cmd in ("approve", "deny", "status", "stop", "new", "reset", "background"):
                logger.debug(
                    "[%s] Command '/%s' bypassing active-session guard for %s",
                    self.name, cmd, session_key,
@@ -1164,10 +1359,7 @@ class BasePlatformAdapter(ABC):
                    existing.media_urls.extend(event.media_urls)
                    existing.media_types.extend(event.media_types)
                    if event.text:
-                        if not existing.text:
-                            existing.text = event.text
-                        elif event.text not in existing.text:
-                            existing.text = f"{existing.text}\n\n{event.text}".strip()
+                        existing.text = self._merge_caption(existing.text, event.text)
                else:
                    self._pending_messages[session_key] = event
                return  # Don't interrupt now - will run after current task completes
@@ -1196,6 +1388,7 @@ class BasePlatformAdapter(ABC):
            return
        if hasattr(task, "add_done_callback"):
            task.add_done_callback(self._background_tasks.discard)
+            task.add_done_callback(self._expected_cancelled_tasks.discard)
    
    @staticmethod
    def _get_human_delay() -> float:
@@ -1424,7 +1617,11 @@ class BasePlatformAdapter(ABC):

            # Determine overall success for the processing hook
            processing_ok = delivery_succeeded if delivery_attempted else not bool(response)
-            await self._run_processing_hook("on_processing_complete", event, processing_ok)
+            await self._run_processing_hook(
+                "on_processing_complete",
+                event,
+                ProcessingOutcome.SUCCESS if processing_ok else ProcessingOutcome.FAILURE,
+            )

            # Check if there's a pending message that was queued during our processing
            if session_key in self._pending_messages:
@@ -1443,10 +1640,14 @@ class BasePlatformAdapter(ABC):
                return  # Already cleaned up
                
        except asyncio.CancelledError:
-            await self._run_processing_hook("on_processing_complete", event, False)
+            current_task = asyncio.current_task()
+            outcome = ProcessingOutcome.CANCELLED
+            if current_task is None or current_task not in self._expected_cancelled_tasks:
+                outcome = ProcessingOutcome.FAILURE
+            await self._run_processing_hook("on_processing_complete", event, outcome)
            raise
        except Exception as e:
-            await self._run_processing_hook("on_processing_complete", event, False)
+            await self._run_processing_hook("on_processing_complete", event, ProcessingOutcome.FAILURE)
            logger.error("[%s] Error handling message: %s", self.name, e, exc_info=True)
            # Send the error to the user so they aren't left with radio silence
            try:
@@ -1490,10 +1691,12 @@ class BasePlatformAdapter(ABC):
        """
        tasks = [task for task in self._background_tasks if not task.done()]
        for task in tasks:
+            self._expected_cancelled_tasks.add(task)
            task.cancel()
        if tasks:
            await asyncio.gather(*tasks, return_exceptions=True)
        self._background_tasks.clear()
+        self._expected_cancelled_tasks.clear()
        self._pending_messages.clear()
        self._active_sessions.clear()

@@ -0,0 +1,936 @@
+"""BlueBubbles iMessage platform adapter.
+
+Uses the local BlueBubbles macOS server for outbound REST sends and inbound
+webhooks.  Supports text messaging, media attachments (images, voice, video,
+documents), tapback reactions, typing indicators, and read receipts.
+
+Architecture based on PR #5869 (benjaminsehl) with inbound attachment
+downloading from PR #4588 (YuhangLin).
+"""
+
+import asyncio
+import json
+import logging
+import os
+import re
+import uuid
+from datetime import datetime
+from typing import Any, Dict, List, Optional
+from urllib.parse import quote
+
+import httpx
+
+from gateway.config import Platform, PlatformConfig
+from gateway.platforms.base import (
+    BasePlatformAdapter,
+    MessageEvent,
+    MessageType,
+    SendResult,
+    cache_image_from_bytes,
+    cache_audio_from_bytes,
+    cache_document_from_bytes,
+)
+
+logger = logging.getLogger(__name__)
+
+# ---------------------------------------------------------------------------
+# Constants
+# ---------------------------------------------------------------------------
+
+DEFAULT_WEBHOOK_HOST = "127.0.0.1"
+DEFAULT_WEBHOOK_PORT = 8645
+DEFAULT_WEBHOOK_PATH = "/bluebubbles-webhook"
+MAX_TEXT_LENGTH = 4000
+
+# Tapback reaction codes (BlueBubbles associatedMessageType values)
+_TAPBACK_ADDED = {
+    2000: "love", 2001: "like", 2002: "dislike",
+    2003: "laugh", 2004: "emphasize", 2005: "question",
+}
+_TAPBACK_REMOVED = {
+    3000: "love", 3001: "like", 3002: "dislike",
+    3003: "laugh", 3004: "emphasize", 3005: "question",
+}
+
+# Webhook event types that carry user messages
+_MESSAGE_EVENTS = {"new-message", "message", "updated-message"}
+
+# Log redaction patterns
+_PHONE_RE = re.compile(r"\+?\d{7,15}")
+_EMAIL_RE = re.compile(r"[\w.+-]+@[\w-]+\.[\w.]+")
+
+
+def _redact(text: str) -> str:
+    """Redact phone numbers and emails from log output."""
+    text = _PHONE_RE.sub("[REDACTED]", text)
+    text = _EMAIL_RE.sub("[REDACTED]", text)
+    return text
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+def check_bluebubbles_requirements() -> bool:
+    try:
+        import aiohttp  # noqa: F401
+        import httpx as _httpx  # noqa: F401
+    except ImportError:
+        return False
+    return True
+
+
+def _normalize_server_url(raw: str) -> str:
+    value = (raw or "").strip()
+    if not value:
+        return ""
+    if not re.match(r"^https?://", value, flags=re.I):
+        value = f"http://{value}"
+    return value.rstrip("/")
+
+
+def _strip_markdown(text: str) -> str:
+    """Strip common markdown formatting for iMessage plain-text delivery."""
+    text = re.sub(r"\*\*(.+?)\*\*", r"\1", text, flags=re.DOTALL)
+    text = re.sub(r"\*(.+?)\*", r"\1", text, flags=re.DOTALL)
+    text = re.sub(r"__(.+?)__", r"\1", text, flags=re.DOTALL)
+    text = re.sub(r"_(.+?)_", r"\1", text, flags=re.DOTALL)
+    text = re.sub(r"```[a-zA-Z0-9_+-]*\n?", "", text)
+    text = re.sub(r"`(.+?)`", r"\1", text)
+    text = re.sub(r"^#{1,6}\s+", "", text, flags=re.MULTILINE)
+    text = re.sub(r"\[([^\]]+)\]\(([^\)]+)\)", r"\1", text)
+    text = re.sub(r"\n{3,}", "\n\n", text)
+    return text.strip()
+
+
+# ---------------------------------------------------------------------------
+# Adapter
+# ---------------------------------------------------------------------------
+
+class BlueBubblesAdapter(BasePlatformAdapter):
+    platform = Platform.BLUEBUBBLES
+    MAX_MESSAGE_LENGTH = MAX_TEXT_LENGTH
+
+    def __init__(self, config: PlatformConfig):
+        super().__init__(config, Platform.BLUEBUBBLES)
+        extra = config.extra or {}
+        self.server_url = _normalize_server_url(
+            extra.get("server_url") or os.getenv("BLUEBUBBLES_SERVER_URL", "")
+        )
+        self.password = extra.get("password") or os.getenv("BLUEBUBBLES_PASSWORD", "")
+        self.webhook_host = (
+            extra.get("webhook_host")
+            or os.getenv("BLUEBUBBLES_WEBHOOK_HOST", DEFAULT_WEBHOOK_HOST)
+        )
+        self.webhook_port = int(
+            extra.get("webhook_port")
+            or os.getenv("BLUEBUBBLES_WEBHOOK_PORT", str(DEFAULT_WEBHOOK_PORT))
+        )
+        self.webhook_path = (
+            extra.get("webhook_path")
+            or os.getenv("BLUEBUBBLES_WEBHOOK_PATH", DEFAULT_WEBHOOK_PATH)
+        )
+        if not str(self.webhook_path).startswith("/"):
+            self.webhook_path = f"/{self.webhook_path}"
+        self.send_read_receipts = bool(extra.get("send_read_receipts", True))
+        self.client: Optional[httpx.AsyncClient] = None
+        self._runner = None
+        self._private_api_enabled: Optional[bool] = None
+        self._helper_connected: bool = False
+        self._guid_cache: Dict[str, str] = {}
+
+    # ------------------------------------------------------------------
+    # API helpers
+    # ------------------------------------------------------------------
+
+    def _api_url(self, path: str) -> str:
+        sep = "&" if "?" in path else "?"
+        return f"{self.server_url}{path}{sep}password={quote(self.password, safe='')}"
+
+    async def _api_get(self, path: str) -> Dict[str, Any]:
+        assert self.client is not None
+        res = await self.client.get(self._api_url(path))
+        res.raise_for_status()
+        return res.json()
+
+    async def _api_post(self, path: str, payload: Dict[str, Any]) -> Dict[str, Any]:
+        assert self.client is not None
+        res = await self.client.post(self._api_url(path), json=payload)
+        res.raise_for_status()
+        return res.json()
+
+    # ------------------------------------------------------------------
+    # Lifecycle
+    # ------------------------------------------------------------------
+
+    async def connect(self) -> bool:
+        if not self.server_url or not self.password:
+            logger.error(
+                "[bluebubbles] BLUEBUBBLES_SERVER_URL and BLUEBUBBLES_PASSWORD are required"
+            )
+            return False
+        from aiohttp import web
+
+        self.client = httpx.AsyncClient(timeout=30.0)
+        try:
+            await self._api_get("/api/v1/ping")
+            info = await self._api_get("/api/v1/server/info")
+            server_data = (info or {}).get("data", {})
+            self._private_api_enabled = bool(server_data.get("private_api"))
+            self._helper_connected = bool(server_data.get("helper_connected"))
+            logger.info(
+                "[bluebubbles] connected to %s (private_api=%s, helper=%s)",
+                self.server_url,
+                self._private_api_enabled,
+                self._helper_connected,
+            )
+        except Exception as exc:
+            logger.error(
+                "[bluebubbles] cannot reach server at %s: %s", self.server_url, exc
+            )
+            if self.client:
+                await self.client.aclose()
+                self.client = None
+            return False
+
+        app = web.Application()
+        app.router.add_get("/health", lambda _: web.Response(text="ok"))
+        app.router.add_post(self.webhook_path, self._handle_webhook)
+        self._runner = web.AppRunner(app)
+        await self._runner.setup()
+        site = web.TCPSite(self._runner, self.webhook_host, self.webhook_port)
+        await site.start()
+        self._mark_connected()
+        logger.info(
+            "[bluebubbles] webhook listening on http://%s:%s%s",
+            self.webhook_host,
+            self.webhook_port,
+            self.webhook_path,
+        )
+
+        # Register webhook with BlueBubbles server
+        # This is required for the server to know where to send events
+        await self._register_webhook()
+
+        return True
+
+    async def disconnect(self) -> None:
+        # Unregister webhook before cleaning up
+        await self._unregister_webhook()
+
+        if self.client:
+            await self.client.aclose()
+            self.client = None
+        if self._runner:
+            await self._runner.cleanup()
+            self._runner = None
+        self._mark_disconnected()
+
+    @property
+    def _webhook_url(self) -> str:
+        """Compute the external webhook URL for BlueBubbles registration."""
+        host = self.webhook_host
+        if host in ("0.0.0.0", "127.0.0.1", "localhost", "::"):
+            host = "localhost"
+        return f"http://{host}:{self.webhook_port}{self.webhook_path}"
+
+    async def _find_registered_webhooks(self, url: str) -> list:
+        """Return list of BB webhook entries matching *url*."""
+        try:
+            res = await self._api_get("/api/v1/webhook")
+            data = res.get("data")
+            if isinstance(data, list):
+                return [wh for wh in data if wh.get("url") == url]
+        except Exception:
+            pass
+        return []
+
+    async def _register_webhook(self) -> bool:
+        """Register this webhook URL with the BlueBubbles server.
+
+        BlueBubbles requires webhooks to be registered via API before
+        it will send events.  Checks for an existing registration first
+        to avoid duplicates (e.g. after a crash without clean shutdown).
+        """
+        if not self.client:
+            return False
+
+        webhook_url = self._webhook_url
+
+        # Crash resilience — reuse an existing registration if present
+        existing = await self._find_registered_webhooks(webhook_url)
+        if existing:
+            logger.info(
+                "[bluebubbles] webhook already registered: %s", webhook_url
+            )
+            return True
+
+        payload = {
+            "url": webhook_url,
+            "events": ["new-message", "updated-message", "message"],
+        }
+
+        try:
+            res = await self._api_post("/api/v1/webhook", payload)
+            status = res.get("status", 0)
+            if 200 <= status < 300:
+                logger.info(
+                    "[bluebubbles] webhook registered with server: %s",
+                    webhook_url,
+                )
+                return True
+            else:
+                logger.warning(
+                    "[bluebubbles] webhook registration returned status %s: %s",
+                    status,
+                    res.get("message"),
+                )
+                return False
+        except Exception as exc:
+            logger.warning(
+                "[bluebubbles] failed to register webhook with server: %s",
+                exc,
+            )
+            return False
+
+    async def _unregister_webhook(self) -> bool:
+        """Unregister this webhook URL from the BlueBubbles server.
+
+        Removes *all* matching registrations to clean up any duplicates
+        left by prior crashes.
+        """
+        if not self.client:
+            return False
+
+        webhook_url = self._webhook_url
+        removed = False
+
+        try:
+            for wh in await self._find_registered_webhooks(webhook_url):
+                wh_id = wh.get("id")
+                if wh_id:
+                    res = await self.client.delete(
+                        self._api_url(f"/api/v1/webhook/{wh_id}")
+                    )
+                    res.raise_for_status()
+                    removed = True
+            if removed:
+                logger.info(
+                    "[bluebubbles] webhook unregistered: %s", webhook_url
+                )
+        except Exception as exc:
+            logger.debug(
+                "[bluebubbles] failed to unregister webhook (non-critical): %s",
+                exc,
+            )
+        return removed
+
+    # ------------------------------------------------------------------
+    # Chat GUID resolution
+    # ------------------------------------------------------------------
+
+    async def _resolve_chat_guid(self, target: str) -> Optional[str]:
+        """Resolve an email/phone to a BlueBubbles chat GUID.
+
+        If *target* already contains a semicolon (raw GUID format like
+        ``iMessage;-;user@example.com``), it is returned as-is.  Otherwise
+        the adapter queries the BlueBubbles chat list and matches on
+        ``chatIdentifier`` or participant address.
+        """
+        target = (target or "").strip()
+        if not target:
+            return None
+        # Already a raw GUID
+        if ";" in target:
+            return target
+        if target in self._guid_cache:
+            return self._guid_cache[target]
+        try:
+            payload = await self._api_post(
+                "/api/v1/chat/query",
+                {"limit": 100, "offset": 0, "with": ["participants"]},
+            )
+            for chat in payload.get("data", []) or []:
+                guid = chat.get("guid") or chat.get("chatGuid")
+                identifier = chat.get("chatIdentifier") or chat.get("identifier")
+                if identifier == target:
+                    if guid:
+                        self._guid_cache[target] = guid
+                    return guid
+                for part in chat.get("participants", []) or []:
+                    if (part.get("address") or "").strip() == target and guid:
+                        self._guid_cache[target] = guid
+                        return guid
+        except Exception:
+            pass
+        return None
+
+    async def _create_chat_for_handle(
+        self, address: str, message: str
+    ) -> SendResult:
+        """Create a new chat by sending the first message to *address*."""
+        payload = {
+            "addresses": [address],
+            "message": message,
+            "tempGuid": f"temp-{datetime.utcnow().timestamp()}",
+        }
+        try:
+            res = await self._api_post("/api/v1/chat/new", payload)
+            data = res.get("data") or {}
+            msg_id = data.get("guid") or data.get("messageGuid") or "ok"
+            return SendResult(success=True, message_id=str(msg_id), raw_response=res)
+        except Exception as exc:
+            return SendResult(success=False, error=str(exc))
+
+    # ------------------------------------------------------------------
+    # Text sending
+    # ------------------------------------------------------------------
+
+    async def send(
+        self,
+        chat_id: str,
+        content: str,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        text = _strip_markdown(content or "")
+        if not text:
+            return SendResult(success=False, error="BlueBubbles send requires text")
+        chunks = self.truncate_message(text, max_length=self.MAX_MESSAGE_LENGTH)
+        last = SendResult(success=True)
+        for chunk in chunks:
+            guid = await self._resolve_chat_guid(chat_id)
+            if not guid:
+                # If the target looks like an address, try creating a new chat
+                if self._private_api_enabled and (
+                    "@" in chat_id or re.match(r"^\+\d+", chat_id)
+                ):
+                    return await self._create_chat_for_handle(chat_id, chunk)
+                return SendResult(
+                    success=False,
+                    error=f"BlueBubbles chat not found for target: {chat_id}",
+                )
+            payload: Dict[str, Any] = {
+                "chatGuid": guid,
+                "tempGuid": f"temp-{datetime.utcnow().timestamp()}",
+                "message": chunk,
+            }
+            if reply_to and self._private_api_enabled and self._helper_connected:
+                payload["method"] = "private-api"
+                payload["selectedMessageGuid"] = reply_to
+                payload["partIndex"] = 0
+            try:
+                res = await self._api_post("/api/v1/message/text", payload)
+                data = res.get("data") or {}
+                msg_id = data.get("guid") or data.get("messageGuid") or "ok"
+                last = SendResult(
+                    success=True, message_id=str(msg_id), raw_response=res
+                )
+            except Exception as exc:
+                return SendResult(success=False, error=str(exc))
+        return last
+
+    # ------------------------------------------------------------------
+    # Media sending (outbound)
+    # ------------------------------------------------------------------
+
+    async def _send_attachment(
+        self,
+        chat_id: str,
+        file_path: str,
+        filename: Optional[str] = None,
+        caption: Optional[str] = None,
+        is_audio_message: bool = False,
+    ) -> SendResult:
+        """Send a file attachment via BlueBubbles multipart upload."""
+        if not self.client:
+            return SendResult(success=False, error="Not connected")
+        if not os.path.isfile(file_path):
+            return SendResult(success=False, error=f"File not found: {file_path}")
+
+        guid = await self._resolve_chat_guid(chat_id)
+        if not guid:
+            return SendResult(success=False, error=f"Chat not found: {chat_id}")
+
+        fname = filename or os.path.basename(file_path)
+        try:
+            with open(file_path, "rb") as f:
+                files = {"attachment": (fname, f, "application/octet-stream")}
+                data: Dict[str, str] = {
+                    "chatGuid": guid,
+                    "name": fname,
+                    "tempGuid": uuid.uuid4().hex,
+                }
+                if is_audio_message:
+                    data["isAudioMessage"] = "true"
+                res = await self.client.post(
+                    self._api_url("/api/v1/message/attachment"),
+                    files=files,
+                    data=data,
+                    timeout=120,
+                )
+                res.raise_for_status()
+                result = res.json()
+
+            if caption:
+                await self.send(chat_id, caption)
+
+            if result.get("status") == 200:
+                rdata = result.get("data") or {}
+                msg_id = rdata.get("guid") if isinstance(rdata, dict) else None
+                return SendResult(
+                    success=True, message_id=msg_id, raw_response=result
+                )
+            return SendResult(
+                success=False,
+                error=result.get("message", "Attachment upload failed"),
+            )
+        except Exception as e:
+            return SendResult(success=False, error=str(e))
+
+    async def send_image(
+        self,
+        chat_id: str,
+        image_url: str,
+        caption: Optional[str] = None,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        try:
+            from gateway.platforms.base import cache_image_from_url
+
+            local_path = await cache_image_from_url(image_url)
+            return await self._send_attachment(chat_id, local_path, caption=caption)
+        except Exception:
+            return await super().send_image(chat_id, image_url, caption, reply_to)
+
+    async def send_image_file(
+        self,
+        chat_id: str,
+        image_path: str,
+        caption: Optional[str] = None,
+        reply_to: Optional[str] = None,
+        **kwargs,
+    ) -> SendResult:
+        return await self._send_attachment(chat_id, image_path, caption=caption)
+
+    async def send_voice(
+        self,
+        chat_id: str,
+        audio_path: str,
+        caption: Optional[str] = None,
+        reply_to: Optional[str] = None,
+        **kwargs,
+    ) -> SendResult:
+        return await self._send_attachment(
+            chat_id, audio_path, caption=caption, is_audio_message=True
+        )
+
+    async def send_video(
+        self,
+        chat_id: str,
+        video_path: str,
+        caption: Optional[str] = None,
+        reply_to: Optional[str] = None,
+        **kwargs,
+    ) -> SendResult:
+        return await self._send_attachment(chat_id, video_path, caption=caption)
+
+    async def send_document(
+        self,
+        chat_id: str,
+        file_path: str,
+        caption: Optional[str] = None,
+        file_name: Optional[str] = None,
+        reply_to: Optional[str] = None,
+        **kwargs,
+    ) -> SendResult:
+        return await self._send_attachment(
+            chat_id, file_path, filename=file_name, caption=caption
+        )
+
+    async def send_animation(
+        self,
+        chat_id: str,
+        animation_url: str,
+        caption: Optional[str] = None,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        return await self.send_image(
+            chat_id, animation_url, caption, reply_to, metadata
+        )
+
+    # ------------------------------------------------------------------
+    # Typing indicators
+    # ------------------------------------------------------------------
+
+    async def send_typing(self, chat_id: str, metadata=None) -> None:
+        if not self._private_api_enabled or not self._helper_connected or not self.client:
+            return
+        try:
+            guid = await self._resolve_chat_guid(chat_id)
+            if guid:
+                encoded = quote(guid, safe="")
+                await self.client.post(
+                    self._api_url(f"/api/v1/chat/{encoded}/typing"), timeout=5
+                )
+        except Exception:
+            pass
+
+    async def stop_typing(self, chat_id: str) -> None:
+        if not self._private_api_enabled or not self._helper_connected or not self.client:
+            return
+        try:
+            guid = await self._resolve_chat_guid(chat_id)
+            if guid:
+                encoded = quote(guid, safe="")
+                await self.client.delete(
+                    self._api_url(f"/api/v1/chat/{encoded}/typing"), timeout=5
+                )
+        except Exception:
+            pass
+
+    # ------------------------------------------------------------------
+    # Read receipts
+    # ------------------------------------------------------------------
+
+    async def mark_read(self, chat_id: str) -> bool:
+        if not self._private_api_enabled or not self._helper_connected or not self.client:
+            return False
+        try:
+            guid = await self._resolve_chat_guid(chat_id)
+            if guid:
+                encoded = quote(guid, safe="")
+                await self.client.post(
+                    self._api_url(f"/api/v1/chat/{encoded}/read"), timeout=5
+                )
+                return True
+        except Exception:
+            pass
+        return False
+
+    # ------------------------------------------------------------------
+    # Tapback reactions
+    # ------------------------------------------------------------------
+
+    async def send_reaction(
+        self,
+        chat_id: str,
+        message_guid: str,
+        reaction: str,
+        part_index: int = 0,
+    ) -> SendResult:
+        """Send a tapback reaction (requires Private API helper)."""
+        if not self._private_api_enabled or not self._helper_connected:
+            return SendResult(
+                success=False, error="Private API helper not connected"
+            )
+        guid = await self._resolve_chat_guid(chat_id)
+        if not guid:
+            return SendResult(success=False, error=f"Chat not found: {chat_id}")
+        try:
+            res = await self._api_post(
+                "/api/v1/message/react",
+                {
+                    "chatGuid": guid,
+                    "selectedMessageGuid": message_guid,
+                    "reaction": reaction,
+                    "partIndex": part_index,
+                },
+            )
+            return SendResult(success=True, raw_response=res)
+        except Exception as exc:
+            return SendResult(success=False, error=str(exc))
+
+    # ------------------------------------------------------------------
+    # Chat info
+    # ------------------------------------------------------------------
+
+    async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
+        is_group = ";+;" in (chat_id or "")
+        info: Dict[str, Any] = {
+            "name": chat_id,
+            "type": "group" if is_group else "dm",
+        }
+        try:
+            guid = await self._resolve_chat_guid(chat_id)
+            if guid:
+                encoded = quote(guid, safe="")
+                res = await self._api_get(
+                    f"/api/v1/chat/{encoded}?with=participants"
+                )
+                data = (res or {}).get("data", {})
+                display_name = (
+                    data.get("displayName")
+                    or data.get("chatIdentifier")
+                    or chat_id
+                )
+                participants = []
+                for p in data.get("participants", []) or []:
+                    addr = (p.get("address") or "").strip()
+                    if addr:
+                        participants.append(addr)
+                info["name"] = display_name
+                if participants:
+                    info["participants"] = participants
+        except Exception:
+            pass
+        return info
+
+    def format_message(self, content: str) -> str:
+        return _strip_markdown(content)
+
+    # ------------------------------------------------------------------
+    # Inbound attachment downloading (from #4588)
+    # ------------------------------------------------------------------
+
+    async def _download_attachment(
+        self, att_guid: str, att_meta: Dict[str, Any]
+    ) -> Optional[str]:
+        """Download an attachment from BlueBubbles and cache it locally.
+
+        Returns the local file path on success, None on failure.
+        """
+        if not self.client:
+            return None
+        try:
+            encoded = quote(att_guid, safe="")
+            resp = await self.client.get(
+                self._api_url(f"/api/v1/attachment/{encoded}/download"),
+                timeout=60,
+                follow_redirects=True,
+            )
+            resp.raise_for_status()
+            data = resp.content
+
+            mime = (att_meta.get("mimeType") or "").lower()
+            transfer_name = att_meta.get("transferName", "")
+
+            if mime.startswith("image/"):
+                ext_map = {
+                    "image/jpeg": ".jpg",
+                    "image/png": ".png",
+                    "image/gif": ".gif",
+                    "image/webp": ".webp",
+                    "image/heic": ".jpg",
+                    "image/heif": ".jpg",
+                    "image/tiff": ".jpg",
+                }
+                ext = ext_map.get(mime, ".jpg")
+                return cache_image_from_bytes(data, ext)
+
+            if mime.startswith("audio/"):
+                ext_map = {
+                    "audio/mp3": ".mp3",
+                    "audio/mpeg": ".mp3",
+                    "audio/ogg": ".ogg",
+                    "audio/wav": ".wav",
+                    "audio/x-caf": ".mp3",
+                    "audio/mp4": ".m4a",
+                    "audio/aac": ".m4a",
+                }
+                ext = ext_map.get(mime, ".mp3")
+                return cache_audio_from_bytes(data, ext)
+
+            # Videos, documents, and everything else
+            filename = transfer_name or f"file_{uuid.uuid4().hex[:8]}"
+            return cache_document_from_bytes(data, filename)
+
+        except Exception as exc:
+            logger.warning(
+                "[bluebubbles] failed to download attachment %s: %s",
+                _redact(att_guid),
+                exc,
+            )
+            return None
+
+    # ------------------------------------------------------------------
+    # Webhook handling
+    # ------------------------------------------------------------------
+
+    def _extract_payload_record(
+        self, payload: Dict[str, Any]
+    ) -> Optional[Dict[str, Any]]:
+        data = payload.get("data")
+        if isinstance(data, dict):
+            return data
+        if isinstance(data, list):
+            for item in data:
+                if isinstance(item, dict):
+                    return item
+        if isinstance(payload.get("message"), dict):
+            return payload.get("message")
+        return payload if isinstance(payload, dict) else None
+
+    @staticmethod
+    def _value(*candidates: Any) -> Optional[str]:
+        for candidate in candidates:
+            if isinstance(candidate, str) and candidate.strip():
+                return candidate.strip()
+        return None
+
+    async def _handle_webhook(self, request):
+        from aiohttp import web
+
+        token = (
+            request.query.get("password")
+            or request.query.get("guid")
+            or request.headers.get("x-password")
+            or request.headers.get("x-guid")
+            or request.headers.get("x-bluebubbles-guid")
+        )
+        if token != self.password:
+            return web.json_response({"error": "unauthorized"}, status=401)
+        try:
+            raw = await request.read()
+            body = raw.decode("utf-8", errors="replace")
+            try:
+                payload = json.loads(body)
+            except Exception:
+                from urllib.parse import parse_qs
+
+                form = parse_qs(body)
+                payload_str = (
+                    form.get("payload")
+                    or form.get("data")
+                    or form.get("message")
+                    or [""]
+                )[0]
+                payload = json.loads(payload_str) if payload_str else {}
+        except Exception as exc:
+            logger.error("[bluebubbles] webhook parse error: %s", exc)
+            return web.json_response({"error": "invalid payload"}, status=400)
+
+        event_type = self._value(payload.get("type"), payload.get("event")) or ""
+        # Only process message events; silently acknowledge everything else
+        if event_type and event_type not in _MESSAGE_EVENTS:
+            return web.Response(text="ok")
+
+        record = self._extract_payload_record(payload) or {}
+        is_from_me = bool(
+            record.get("isFromMe")
+            or record.get("fromMe")
+            or record.get("is_from_me")
+        )
+        if is_from_me:
+            return web.Response(text="ok")
+
+        # Skip tapback reactions delivered as messages
+        assoc_type = record.get("associatedMessageType")
+        if isinstance(assoc_type, int) and assoc_type in {
+            **_TAPBACK_ADDED,
+            **_TAPBACK_REMOVED,
+        }:
+            return web.Response(text="ok")
+
+        text = (
+            self._value(
+                record.get("text"), record.get("message"), record.get("body")
+            )
+            or ""
+        )
+
+        # --- Inbound attachment handling ---
+        attachments = record.get("attachments") or []
+        media_urls: List[str] = []
+        media_types: List[str] = []
+        msg_type = MessageType.TEXT
+
+        for att in attachments:
+            att_guid = att.get("guid", "")
+            if not att_guid:
+                continue
+            cached = await self._download_attachment(att_guid, att)
+            if cached:
+                mime = (att.get("mimeType") or "").lower()
+                media_urls.append(cached)
+                media_types.append(mime)
+                if mime.startswith("image/"):
+                    msg_type = MessageType.PHOTO
+                elif mime.startswith("audio/") or (att.get("uti") or "").endswith(
+                    "caf"
+                ):
+                    msg_type = MessageType.VOICE
+                elif mime.startswith("video/"):
+                    msg_type = MessageType.VIDEO
+                else:
+                    msg_type = MessageType.DOCUMENT
+
+        # With multiple attachments, prefer PHOTO if any images present
+        if len(media_urls) > 1:
+            mime_prefixes = {(m or "").split("/")[0] for m in media_types}
+            if "image" in mime_prefixes:
+                msg_type = MessageType.PHOTO
+
+        if not text and media_urls:
+            text = "(attachment)"
+        # --- End attachment handling ---
+
+        chat_guid = self._value(
+            record.get("chatGuid"),
+            payload.get("chatGuid"),
+            record.get("chat_guid"),
+            payload.get("chat_guid"),
+            payload.get("guid"),
+        )
+        chat_identifier = self._value(
+            record.get("chatIdentifier"),
+            record.get("identifier"),
+            payload.get("chatIdentifier"),
+            payload.get("identifier"),
+        )
+        sender = (
+            self._value(
+                record.get("handle", {}).get("address")
+                if isinstance(record.get("handle"), dict)
+                else None,
+                record.get("sender"),
+                record.get("from"),
+                record.get("address"),
+            )
+            or chat_identifier
+            or chat_guid
+        )
+        if not (chat_guid or chat_identifier) and sender:
+            chat_identifier = sender
+        if not sender or not (chat_guid or chat_identifier) or not text:
+            return web.json_response({"error": "missing message fields"}, status=400)
+
+        session_chat_id = chat_guid or chat_identifier
+        is_group = bool(record.get("isGroup")) or (";+;" in (chat_guid or ""))
+        source = self.build_source(
+            chat_id=session_chat_id,
+            chat_name=chat_identifier or sender,
+            chat_type="group" if is_group else "dm",
+            user_id=sender,
+            user_name=sender,
+            chat_id_alt=chat_identifier,
+        )
+        event = MessageEvent(
+            text=text,
+            message_type=msg_type,
+            source=source,
+            raw_message=payload,
+            message_id=self._value(
+                record.get("guid"),
+                record.get("messageGuid"),
+                record.get("id"),
+            ),
+            reply_to_message_id=self._value(
+                record.get("threadOriginatorGuid"),
+                record.get("associatedMessageGuid"),
+            ),
+            media_urls=media_urls,
+            media_types=media_types,
+        )
+        task = asyncio.create_task(self.handle_message(event))
+        self._background_tasks.add(task)
+        task.add_done_callback(self._background_tasks.discard)
+
+        # Fire-and-forget read receipt
+        if self.send_read_receipts and session_chat_id:
+            asyncio.create_task(self.mark_read(session_chat_id))
+
+        return web.Response(text="ok")
+
@@ -20,6 +20,7 @@ Configuration in config.yaml:
 import asyncio
 import logging
 import os
+import re
 import time
 import uuid
 from datetime import datetime, timezone
@@ -54,6 +55,8 @@ MAX_MESSAGE_LENGTH = 20000
 DEDUP_WINDOW_SECONDS = 300
 DEDUP_MAX_SIZE = 1000
 RECONNECT_BACKOFF = [2, 5, 10, 30, 60]
+_SESSION_WEBHOOKS_MAX = 500
+_DINGTALK_WEBHOOK_RE = re.compile(r'^https://api\.dingtalk\.com/')


 def check_dingtalk_requirements() -> bool:
@@ -195,9 +198,15 @@ class DingTalkAdapter(BasePlatformAdapter):
        chat_id = conversation_id or sender_id
        chat_type = "group" if is_group else "dm"

-        # Store session webhook for reply routing
+        # Store session webhook for reply routing (validate origin to prevent SSRF)
        session_webhook = getattr(message, "session_webhook", None) or ""
-        if session_webhook and chat_id:
+        if session_webhook and chat_id and _DINGTALK_WEBHOOK_RE.match(session_webhook):
+            if len(self._session_webhooks) >= _SESSION_WEBHOOKS_MAX:
+                # Evict oldest entry to cap memory growth
+                try:
+                    self._session_webhooks.pop(next(iter(self._session_webhooks)))
+                except StopIteration:
+                    pass
            self._session_webhooks[chat_id] = session_webhook

        source = self.build_source(
@@ -49,12 +49,14 @@ from gateway.platforms.base import (
    BasePlatformAdapter,
    MessageEvent,
    MessageType,
+    ProcessingOutcome,
    SendResult,
    cache_image_from_url,
    cache_audio_from_url,
    cache_document_from_bytes,
    SUPPORTED_DOCUMENT_TYPES,
 )
+from tools.url_safety import is_safe_url


 def _clean_discord_id(entry: str) -> str:
@@ -421,6 +423,7 @@ class DiscordAdapter(BasePlatformAdapter):

    # Discord message limits
    MAX_MESSAGE_LENGTH = 2000
+    _SPLIT_THRESHOLD = 1900  # near the 2000-char split point

    # Auto-disconnect from voice channel after this many seconds of inactivity
    VOICE_TIMEOUT = 300
@@ -432,6 +435,11 @@ class DiscordAdapter(BasePlatformAdapter):
        self._allowed_user_ids: set = set()  # For button approval authorization
        # Voice channel state (per-guild)
        self._voice_clients: Dict[int, Any] = {}  # guild_id -> VoiceClient
+        # Text batching: merge rapid successive messages (Telegram-style)
+        self._text_batch_delay_seconds = float(os.getenv("HERMES_DISCORD_TEXT_BATCH_DELAY_SECONDS", "0.6"))
+        self._text_batch_split_delay_seconds = float(os.getenv("HERMES_DISCORD_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0"))
+        self._pending_text_batches: Dict[str, MessageEvent] = {}
+        self._pending_text_batch_tasks: Dict[str, asyncio.Task] = {}
        self._voice_text_channels: Dict[int, int] = {}  # guild_id -> text_channel_id
        self._voice_timeout_tasks: Dict[int, asyncio.Task] = {}  # guild_id -> timeout task
        # Phase 2: voice listening
@@ -454,6 +462,9 @@ class DiscordAdapter(BasePlatformAdapter):
        self._seen_messages: Dict[str, float] = {}
        self._SEEN_TTL = 300   # 5 minutes
        self._SEEN_MAX = 2000  # prune threshold
+        # Reply threading mode: "off" (no replies), "first" (reply on first
+        # chunk only, default), "all" (reply-reference on every chunk).
+        self._reply_to_mode: str = getattr(config, 'reply_to_mode', 'first') or 'first'

    async def connect(self) -> bool:
        """Connect to Discord and start receiving events."""
@@ -525,10 +536,17 @@ class DiscordAdapter(BasePlatformAdapter):
            intents.members = any(not entry.isdigit() for entry in self._allowed_user_ids)
            intents.voice_states = True

-            # Create bot
+            # Resolve proxy (DISCORD_PROXY > generic env vars > macOS system proxy)
+            from gateway.platforms.base import resolve_proxy_url, proxy_kwargs_for_bot
+            proxy_url = resolve_proxy_url(platform_env_var="DISCORD_PROXY")
+            if proxy_url:
+                logger.info("[%s] Using proxy for Discord: %s", self.name, proxy_url)
+
+            # Create bot — proxy= for HTTP, connector= for SOCKS
            self._client = commands.Bot(
                command_prefix="!",  # Not really used, we handle raw messages
                intents=intents,
+                **proxy_kwargs_for_bot(proxy_url),
            )
            adapter_self = self  # capture for closure

@@ -737,14 +755,17 @@ class DiscordAdapter(BasePlatformAdapter):
        if hasattr(message, "add_reaction"):
            await self._add_reaction(message, "👀")

-    async def on_processing_complete(self, event: MessageEvent, success: bool) -> None:
+    async def on_processing_complete(self, event: MessageEvent, outcome: ProcessingOutcome) -> None:
        """Swap the in-progress reaction for a final success/failure reaction."""
        if not self._reactions_enabled():
            return
        message = event.raw_message
        if hasattr(message, "add_reaction"):
            await self._remove_reaction(message, "👀")
-            await self._add_reaction(message, "✅" if success else "❌")
+            if outcome == ProcessingOutcome.SUCCESS:
+                await self._add_reaction(message, "✅")
+            elif outcome == ProcessingOutcome.FAILURE:
+                await self._add_reaction(message, "❌")

    async def send(
        self,
@@ -753,18 +774,34 @@ class DiscordAdapter(BasePlatformAdapter):
        reply_to: Optional[str] = None,
        metadata: Optional[Dict[str, Any]] = None
    ) -> SendResult:
-        """Send a message to a Discord channel."""
+        """Send a message to a Discord channel or thread.
+
+        When metadata contains a thread_id, the message is sent to that
+        thread instead of the parent channel identified by chat_id.
+        """
        if not self._client:
            return SendResult(success=False, error="Not connected")

        try:
-            # Get the channel
-            channel = self._client.get_channel(int(chat_id))
-            if not channel:
-                channel = await self._client.fetch_channel(int(chat_id))
+            # Determine target channel: thread_id in metadata takes precedence.
+            thread_id = None
+            if metadata and metadata.get("thread_id"):
+                thread_id = metadata["thread_id"]

-            if not channel:
-                return SendResult(success=False, error=f"Channel {chat_id} not found")
+            if thread_id:
+                # Fetch the thread directly — threads are addressed by their own ID.
+                channel = self._client.get_channel(int(thread_id))
+                if not channel:
+                    channel = await self._client.fetch_channel(int(thread_id))
+                if not channel:
+                    return SendResult(success=False, error=f"Thread {thread_id} not found")
+            else:
+                # Get the parent channel
+                channel = self._client.get_channel(int(chat_id))
+                if not channel:
+                    channel = await self._client.fetch_channel(int(chat_id))
+                if not channel:
+                    return SendResult(success=False, error=f"Channel {chat_id} not found")

            # Format and split message if needed
            formatted = self.format_message(content)
@@ -773,7 +810,7 @@ class DiscordAdapter(BasePlatformAdapter):
            message_ids = []
            reference = None

-            if reply_to:
+            if reply_to and self._reply_to_mode != "off":
                try:
                    ref_msg = await channel.fetch_message(int(reply_to))
                    reference = ref_msg
@@ -781,7 +818,10 @@ class DiscordAdapter(BasePlatformAdapter):
                    logger.debug("Could not fetch reply-to message: %s", e)

            for i, chunk in enumerate(chunks):
-                chunk_reference = reference if i == 0 else None
+                if self._reply_to_mode == "all":
+                    chunk_reference = reference
+                else:  # "first" (default) or "off"
+                    chunk_reference = reference if i == 0 else None
                try:
                    msg = await channel.send(
                        content=chunk,
@@ -1224,9 +1264,8 @@ class DiscordAdapter(BasePlatformAdapter):
        try:
            await asyncio.to_thread(VoiceReceiver.pcm_to_wav, pcm_data, wav_path)

-            from tools.transcription_tools import transcribe_audio, get_stt_model_from_config
-            stt_model = get_stt_model_from_config()
-            result = await asyncio.to_thread(transcribe_audio, wav_path, model=stt_model)
+            from tools.transcription_tools import transcribe_audio
+            result = await asyncio.to_thread(transcribe_audio, wav_path)

            if not result.get("success"):
                return
@@ -1285,6 +1324,10 @@ class DiscordAdapter(BasePlatformAdapter):
        if not self._client:
            return SendResult(success=False, error="Not connected")

+        if not is_safe_url(image_url):
+            logger.warning("[%s] Blocked unsafe image URL during Discord send_image", self.name)
+            return await super().send_image(chat_id, image_url, caption, reply_to, metadata=metadata)
+
        try:
            import aiohttp

@@ -1296,8 +1339,11 @@ class DiscordAdapter(BasePlatformAdapter):

            # Download the image and send as a Discord file attachment
            # (Discord renders attachments inline, unlike plain URLs)
-            async with aiohttp.ClientSession() as session:
-                async with session.get(image_url, timeout=aiohttp.ClientTimeout(total=30)) as resp:
+            from gateway.platforms.base import resolve_proxy_url, proxy_kwargs_for_aiohttp
+            _proxy = resolve_proxy_url(platform_env_var="DISCORD_PROXY")
+            _sess_kw, _req_kw = proxy_kwargs_for_aiohttp(_proxy)
+            async with aiohttp.ClientSession(**_sess_kw) as session:
+                async with session.get(image_url, timeout=aiohttp.ClientTimeout(total=30), **_req_kw) as resp:
                    if resp.status != 200:
                        raise Exception(f"Failed to download image: HTTP {resp.status}")

@@ -1574,7 +1620,7 @@ class DiscordAdapter(BasePlatformAdapter):
            await self._run_simple_slash(interaction, f"/model {name}".strip())

        @tree.command(name="reasoning", description="Show or change reasoning effort")
-        @discord.app_commands.describe(effort="Reasoning effort: xhigh, high, medium, low, minimal, or none.")
+        @discord.app_commands.describe(effort="Reasoning effort: none, minimal, low, medium, high, or xhigh.")
        async def slash_reasoning(interaction: discord.Interaction, effort: str = ""):
            await self._run_simple_slash(interaction, f"/reasoning {effort}".strip())

@@ -1756,8 +1802,9 @@ class DiscordAdapter(BasePlatformAdapter):
            if hasattr(interaction.channel, "guild") and interaction.channel.guild:
                chat_name = f"{interaction.channel.guild.name} / #{chat_name}"

-        # Get channel topic (if available)
-        chat_topic = getattr(interaction.channel, "topic", None)
+        # Get channel topic (if available).
+        # For forum threads, inherit the parent forum's topic.
+        chat_topic = self._get_effective_topic(interaction.channel, is_thread=is_thread)

        source = self.build_source(
            chat_id=str(interaction.channel_id),
@@ -1831,6 +1878,10 @@ class DiscordAdapter(BasePlatformAdapter):

        chat_name = f"{guild_name} / {thread_name}" if guild_name else thread_name

+        # Inherit forum topic when the thread was created inside a forum channel.
+        _chan = getattr(interaction, "channel", None)
+        chat_topic = self._get_effective_topic(_chan, is_thread=True) if _chan else None
+
        source = self.build_source(
            chat_id=thread_id,
            chat_name=chat_name,
@@ -1838,6 +1889,7 @@ class DiscordAdapter(BasePlatformAdapter):
            user_id=str(interaction.user.id),
            user_name=interaction.user.display_name,
            thread_id=thread_id,
+            chat_topic=chat_topic,
        )

        event = MessageEvent(
@@ -2123,6 +2175,15 @@ class DiscordAdapter(BasePlatformAdapter):
                return True
        return False

+    def _get_effective_topic(self, channel: Any, is_thread: bool = False) -> Optional[str]:
+        """Return the channel topic, falling back to the parent forum's topic for forum threads."""
+        topic = getattr(channel, "topic", None)
+        if not topic and is_thread:
+            parent = getattr(channel, "parent", None)
+            if parent and self._is_forum_parent(parent):
+                topic = getattr(parent, "topic", None)
+        return topic
+
    def _format_thread_chat_name(self, thread: Any) -> str:
        """Build a readable chat name for thread-like Discord channels, including forum context when available."""
        thread_name = getattr(thread, "name", None) or str(getattr(thread, "id", "thread"))
@@ -2188,9 +2249,12 @@ class DiscordAdapter(BasePlatformAdapter):
        # UNLESS the channel is in the free-response list or the message is
        # in a thread where the bot has already participated.
        #
-        # Config (all settable via discord.* in config.yaml):
+        # Config (all settable via discord.* in config.yaml or DISCORD_* env vars):
        #   discord.require_mention: Require @mention in server channels (default: true)
        #   discord.free_response_channels: Channel IDs where bot responds without mention
+        #   discord.ignored_channels: Channel IDs where bot NEVER responds (even when mentioned)
+        #   discord.allowed_channels: If set, bot ONLY responds in these channels (whitelist)
+        #   discord.no_thread_channels: Channel IDs where bot responds directly without creating thread
        #   discord.auto_thread: Auto-create thread on @mention in channels (default: true)

        thread_id = None
@@ -2201,9 +2265,27 @@ class DiscordAdapter(BasePlatformAdapter):
            parent_channel_id = self._get_parent_channel_id(message.channel)

        if not isinstance(message.channel, discord.DMChannel):
+            channel_ids = {str(message.channel.id)}
+            if parent_channel_id:
+                channel_ids.add(parent_channel_id)
+
+            # Check allowed channels - if set, only respond in these channels
+            allowed_channels_raw = os.getenv("DISCORD_ALLOWED_CHANNELS", "")
+            if allowed_channels_raw:
+                allowed_channels = {ch.strip() for ch in allowed_channels_raw.split(",") if ch.strip()}
+                if not (channel_ids & allowed_channels):
+                    logger.debug("[%s] Ignoring message in non-allowed channel: %s", self.name, channel_ids)
+                    return
+
+            # Check ignored channels - never respond even when mentioned
+            ignored_channels_raw = os.getenv("DISCORD_IGNORED_CHANNELS", "")
+            ignored_channels = {ch.strip() for ch in ignored_channels_raw.split(",") if ch.strip()}
+            if channel_ids & ignored_channels:
+                logger.debug("[%s] Ignoring message in ignored channel: %s", self.name, channel_ids)
+                return
+
            free_channels_raw = os.getenv("DISCORD_FREE_RESPONSE_CHANNELS", "")
            free_channels = {ch.strip() for ch in free_channels_raw.split(",") if ch.strip()}
-            channel_ids = {str(message.channel.id)}
            if parent_channel_id:
                channel_ids.add(parent_channel_id)

@@ -2225,10 +2307,14 @@ class DiscordAdapter(BasePlatformAdapter):
        # Auto-thread: when enabled, automatically create a thread for every
        # @mention in a text channel so each conversation is isolated (like Slack).
        # Messages already inside threads or DMs are unaffected.
+        # no_thread_channels: channels where bot responds directly without thread.
        auto_threaded_channel = None
        if not is_thread and not isinstance(message.channel, discord.DMChannel):
+            no_thread_channels_raw = os.getenv("DISCORD_NO_THREAD_CHANNELS", "")
+            no_thread_channels = {ch.strip() for ch in no_thread_channels_raw.split(",") if ch.strip()}
+            skip_thread = bool(channel_ids & no_thread_channels)
            auto_thread = os.getenv("DISCORD_AUTO_THREAD", "true").lower() in ("true", "1", "yes")
-            if auto_thread:
+            if auto_thread and not skip_thread:
                thread = await self._auto_create_thread(message)
                if thread:
                    is_thread = True
@@ -2275,8 +2361,10 @@ class DiscordAdapter(BasePlatformAdapter):
            if hasattr(message.channel, "guild") and message.channel.guild:
                chat_name = f"{message.channel.guild.name} / #{chat_name}"

-        # Get channel topic (if available - TextChannels have topics, DMs/threads don't)
-        chat_topic = getattr(message.channel, "topic", None)
+        # Get channel topic (if available - TextChannels have topics, DMs/threads don't).
+        # For threads whose parent is a forum channel, inherit the parent's topic
+        # so forum descriptions (e.g. project instructions) appear in the session context.
+        chat_topic = self._get_effective_topic(message.channel, is_thread=is_thread)

        # Build source
        source = self.build_source(
@@ -2339,7 +2427,7 @@ class DiscordAdapter(BasePlatformAdapter):
                        ext or "unknown", content_type,
                    )
                else:
-                    MAX_DOC_BYTES = 20 * 1024 * 1024
+                    MAX_DOC_BYTES = 32 * 1024 * 1024
                    if att.size and att.size > MAX_DOC_BYTES:
                        logger.warning(
                            "[Discord] Document too large (%s bytes), skipping: %s",
@@ -2348,10 +2436,14 @@ class DiscordAdapter(BasePlatformAdapter):
                    else:
                        try:
                            import aiohttp
-                            async with aiohttp.ClientSession() as session:
+                            from gateway.platforms.base import resolve_proxy_url, proxy_kwargs_for_aiohttp
+                            _proxy = resolve_proxy_url(platform_env_var="DISCORD_PROXY")
+                            _sess_kw, _req_kw = proxy_kwargs_for_aiohttp(_proxy)
+                            async with aiohttp.ClientSession(**_sess_kw) as session:
                                async with session.get(
                                    att.url,
                                    timeout=aiohttp.ClientTimeout(total=30),
+                                    **_req_kw,
                                ) as resp:
                                    if resp.status != 200:
                                        raise Exception(f"HTTP {resp.status}")
@@ -2363,9 +2455,9 @@ class DiscordAdapter(BasePlatformAdapter):
                            media_urls.append(cached_path)
                            media_types.append(doc_mime)
                            logger.info("[Discord] Cached user document: %s", cached_path)
-                            # Inject text content for .txt/.md files (capped at 100 KB)
+                            # Inject text content for plain-text documents (capped at 100 KB)
                            MAX_TEXT_INJECT_BYTES = 100 * 1024
-                            if ext in (".md", ".txt") and len(raw_bytes) <= MAX_TEXT_INJECT_BYTES:
+                            if ext in (".md", ".txt", ".log") and len(raw_bytes) <= MAX_TEXT_INJECT_BYTES:
                                try:
                                    text_content = raw_bytes.decode("utf-8")
                                    display_name = att.filename or f"document{ext}"
@@ -2409,7 +2501,80 @@ class DiscordAdapter(BasePlatformAdapter):
        if thread_id:
            self._track_thread(thread_id)

-        await self.handle_message(event)
+        # Only batch plain text messages — commands, media, etc. dispatch
+        # immediately since they won't be split by the Discord client.
+        if msg_type == MessageType.TEXT and self._text_batch_delay_seconds > 0:
+            self._enqueue_text_event(event)
+        else:
+            await self.handle_message(event)
+
+    # ------------------------------------------------------------------
+    # Text message aggregation (handles Discord client-side splits)
+    # ------------------------------------------------------------------
+
+    def _text_batch_key(self, event: MessageEvent) -> str:
+        """Session-scoped key for text message batching."""
+        from gateway.session import build_session_key
+        return build_session_key(
+            event.source,
+            group_sessions_per_user=self.config.extra.get("group_sessions_per_user", True),
+            thread_sessions_per_user=self.config.extra.get("thread_sessions_per_user", False),
+        )
+
+    def _enqueue_text_event(self, event: MessageEvent) -> None:
+        """Buffer a text event and reset the flush timer.
+
+        When Discord splits a long user message at 2000 chars, the chunks
+        arrive within a few hundred milliseconds.  This merges them into
+        a single event before dispatching.
+        """
+        key = self._text_batch_key(event)
+        existing = self._pending_text_batches.get(key)
+        chunk_len = len(event.text or "")
+        if existing is None:
+            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
+            self._pending_text_batches[key] = event
+        else:
+            if event.text:
+                existing.text = f"{existing.text}\n{event.text}" if existing.text else event.text
+            existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
+            if event.media_urls:
+                existing.media_urls.extend(event.media_urls)
+                existing.media_types.extend(event.media_types)
+
+        prior_task = self._pending_text_batch_tasks.get(key)
+        if prior_task and not prior_task.done():
+            prior_task.cancel()
+        self._pending_text_batch_tasks[key] = asyncio.create_task(
+            self._flush_text_batch(key)
+        )
+
+    async def _flush_text_batch(self, key: str) -> None:
+        """Wait for the quiet period then dispatch the aggregated text.
+
+        Uses a longer delay when the latest chunk is near Discord's 2000-char
+        split point, since a continuation chunk is almost certain.
+        """
+        current_task = asyncio.current_task()
+        try:
+            pending = self._pending_text_batches.get(key)
+            last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
+            if last_len >= self._SPLIT_THRESHOLD:
+                delay = self._text_batch_split_delay_seconds
+            else:
+                delay = self._text_batch_delay_seconds
+            await asyncio.sleep(delay)
+            event = self._pending_text_batches.pop(key, None)
+            if not event:
+                return
+            logger.info(
+                "[Discord] Flushing text batch %s (%d chars)",
+                key, len(event.text or ""),
+            )
+            await self.handle_message(event)
+        finally:
+            if self._pending_text_batch_tasks.get(key) is current_task:
+                self._pending_text_batch_tasks.pop(key, None)


 # ---------------------------------------------------------------------------
@@ -195,7 +195,11 @@ def _extract_attachments(

        ext = Path(filename).suffix.lower()
        if ext in _IMAGE_EXTS:
-            cached_path = cache_image_from_bytes(payload, ext)
+            try:
+                cached_path = cache_image_from_bytes(payload, ext)
+            except ValueError:
+                logger.debug("Skipping non-image attachment %s (invalid magic bytes)", filename)
+                continue
            attachments.append({
                "path": cached_path,
                "filename": filename,
@@ -20,6 +20,7 @@ from __future__ import annotations
 import asyncio
 import hashlib
 import hmac
+import itertools
 import json
 import logging
 import mimetypes
@@ -263,6 +264,7 @@ class FeishuAdapterSettings:
    bot_name: str
    dedup_cache_size: int
    text_batch_delay_seconds: float
+    text_batch_split_delay_seconds: float
    text_batch_max_messages: int
    text_batch_max_chars: int
    media_batch_delay_seconds: float
@@ -971,7 +973,8 @@ def _run_official_feishu_ws_client(ws_client: Any, adapter: Any) -> None:
        return await original_connect(*args, **kwargs)

    def _configure_with_overrides(conf: Any) -> Any:
-        assert original_configure is not None
+        if original_configure is None:
+            raise RuntimeError("Feishu _configure_with_overrides called but original_configure is None")
        result = original_configure(conf)
        _apply_runtime_ws_overrides()
        return result
@@ -1013,6 +1016,10 @@ class FeishuAdapter(BasePlatformAdapter):
    """Feishu/Lark bot adapter."""

    MAX_MESSAGE_LENGTH = 8000
+    # Threshold for detecting Feishu client-side message splits.
+    # When a chunk is near the ~4096-char practical limit, a continuation
+    # is almost certain.
+    _SPLIT_THRESHOLD = 4000

    # =========================================================================
    # Lifecycle — init / settings / connect / disconnect
@@ -1052,6 +1059,9 @@ class FeishuAdapter(BasePlatformAdapter):
        self._media_batch_state = FeishuBatchState()
        self._pending_media_batches = self._media_batch_state.events
        self._pending_media_batch_tasks = self._media_batch_state.tasks
+        # Exec approval button state (approval_id → {session_key, message_id, chat_id})
+        self._approval_state: Dict[int, Dict[str, str]] = {}
+        self._approval_counter = itertools.count(1)
        self._load_seen_message_ids()

    @staticmethod
@@ -1101,6 +1111,9 @@ class FeishuAdapter(BasePlatformAdapter):
            text_batch_delay_seconds=float(
                os.getenv("HERMES_FEISHU_TEXT_BATCH_DELAY_SECONDS", str(_DEFAULT_TEXT_BATCH_DELAY_SECONDS))
            ),
+            text_batch_split_delay_seconds=float(
+                os.getenv("HERMES_FEISHU_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0")
+            ),
            text_batch_max_messages=max(
                1,
                int(os.getenv("HERMES_FEISHU_TEXT_BATCH_MAX_MESSAGES", str(_DEFAULT_TEXT_BATCH_MAX_MESSAGES))),
@@ -1148,6 +1161,7 @@ class FeishuAdapter(BasePlatformAdapter):
        self._bot_name = settings.bot_name
        self._dedup_cache_size = settings.dedup_cache_size
        self._text_batch_delay_seconds = settings.text_batch_delay_seconds
+        self._text_batch_split_delay_seconds = settings.text_batch_split_delay_seconds
        self._text_batch_max_messages = settings.text_batch_max_messages
        self._text_batch_max_chars = settings.text_batch_max_chars
        self._media_batch_delay_seconds = settings.media_batch_delay_seconds
@@ -1394,6 +1408,104 @@ class FeishuAdapter(BasePlatformAdapter):
            logger.error("[Feishu] Failed to edit message %s: %s", message_id, exc, exc_info=True)
            return SendResult(success=False, error=str(exc))

+    async def send_exec_approval(
+        self, chat_id: str, command: str, session_key: str,
+        description: str = "dangerous command",
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        """Send an interactive card with approval buttons.
+
+        The buttons carry ``hermes_action`` in their value dict so that
+        ``_handle_card_action_event`` can intercept them and call
+        ``resolve_gateway_approval()`` to unblock the waiting agent thread.
+        """
+        if not self._client:
+            return SendResult(success=False, error="Not connected")
+
+        try:
+            approval_id = next(self._approval_counter)
+            cmd_preview = command[:3000] + "..." if len(command) > 3000 else command
+
+            def _btn(label: str, action_name: str, btn_type: str = "default") -> dict:
+                return {
+                    "tag": "button",
+                    "text": {"tag": "plain_text", "content": label},
+                    "type": btn_type,
+                    "value": {"hermes_action": action_name, "approval_id": approval_id},
+                }
+
+            card = {
+                "config": {"wide_screen_mode": True},
+                "header": {
+                    "title": {"content": "⚠️ Command Approval Required", "tag": "plain_text"},
+                    "template": "orange",
+                },
+                "elements": [
+                    {
+                        "tag": "markdown",
+                        "content": f"```\n{cmd_preview}\n```\n**Reason:** {description}",
+                    },
+                    {
+                        "tag": "action",
+                        "actions": [
+                            _btn("✅ Allow Once", "approve_once", "primary"),
+                            _btn("✅ Session", "approve_session"),
+                            _btn("✅ Always", "approve_always"),
+                            _btn("❌ Deny", "deny", "danger"),
+                        ],
+                    },
+                ],
+            }
+
+            payload = json.dumps(card, ensure_ascii=False)
+            response = await self._feishu_send_with_retry(
+                chat_id=chat_id,
+                msg_type="interactive",
+                payload=payload,
+                reply_to=None,
+                metadata=metadata,
+            )
+
+            result = self._finalize_send_result(response, "send_exec_approval failed")
+            if result.success:
+                self._approval_state[approval_id] = {
+                    "session_key": session_key,
+                    "message_id": result.message_id or "",
+                    "chat_id": chat_id,
+                }
+            return result
+        except Exception as exc:
+            logger.warning("[Feishu] send_exec_approval failed: %s", exc)
+            return SendResult(success=False, error=str(exc))
+
+    async def _update_approval_card(
+        self, message_id: str, label: str, user_name: str, choice: str,
+    ) -> None:
+        """Replace the approval card with a resolved status card."""
+        if not self._client or not message_id:
+            return
+        icon = "❌" if choice == "deny" else "✅"
+        card = {
+            "config": {"wide_screen_mode": True},
+            "header": {
+                "title": {"content": f"{icon} {label}", "tag": "plain_text"},
+                "template": "red" if choice == "deny" else "green",
+            },
+            "elements": [
+                {
+                    "tag": "markdown",
+                    "content": f"{icon} **{label}** by {user_name}",
+                },
+            ],
+        }
+        try:
+            payload = json.dumps(card, ensure_ascii=False)
+            body = self._build_update_message_body(msg_type="interactive", content=payload)
+            request = self._build_update_message_request(message_id=message_id, request_body=body)
+            await asyncio.to_thread(self._client.im.v1.message.update, request)
+        except Exception as exc:
+            logger.warning("[Feishu] Failed to update approval card %s: %s", message_id, exc)
+
    async def send_voice(
        self,
        chat_id: str,
@@ -1820,6 +1932,52 @@ class FeishuAdapter(BasePlatformAdapter):
        action = getattr(event, "action", None)
        action_tag = str(getattr(action, "tag", "") or "button")
        action_value = getattr(action, "value", {}) or {}
+
+        # --- Exec approval button intercept ---
+        hermes_action = action_value.get("hermes_action") if isinstance(action_value, dict) else None
+        if hermes_action:
+            approval_id = action_value.get("approval_id")
+            state = self._approval_state.pop(approval_id, None)
+            if not state:
+                logger.debug("[Feishu] Approval %s already resolved or unknown", approval_id)
+                return
+
+            choice_map = {
+                "approve_once": "once",
+                "approve_session": "session",
+                "approve_always": "always",
+                "deny": "deny",
+            }
+            choice = choice_map.get(hermes_action, "deny")
+
+            label_map = {
+                "once": "Approved once",
+                "session": "Approved for session",
+                "always": "Approved permanently",
+                "deny": "Denied",
+            }
+            label = label_map.get(choice, "Resolved")
+
+            # Resolve sender name for the status card
+            sender_id = SimpleNamespace(open_id=open_id, user_id=None, union_id=None)
+            sender_profile = await self._resolve_sender_profile(sender_id)
+            user_name = sender_profile.get("user_name") or open_id
+
+            # Resolve the approval — unblocks the agent thread
+            try:
+                from tools.approval import resolve_gateway_approval
+                count = resolve_gateway_approval(state["session_key"], choice)
+                logger.info(
+                    "Feishu button resolved %d approval(s) for session %s (choice=%s, user=%s)",
+                    count, state["session_key"], choice, user_name,
+                )
+            except Exception as exc:
+                logger.error("Failed to resolve gateway approval from Feishu button: %s", exc)
+
+            # Update the card to show the decision
+            await self._update_approval_card(state.get("message_id", ""), label, user_name, choice)
+            return
+
        synthetic_text = f"/card {action_tag}"
        if action_value:
            try:
@@ -2065,10 +2223,7 @@ class FeishuAdapter(BasePlatformAdapter):
        existing.media_urls.extend(event.media_urls)
        existing.media_types.extend(event.media_types)
        if event.text:
-            if not existing.text:
-                existing.text = event.text
-            elif event.text not in existing.text.split("\n\n"):
-                existing.text = f"{existing.text}\n\n{event.text}"
+            existing.text = self._merge_caption(existing.text, event.text)
        existing.timestamp = event.timestamp
        if event.message_id:
            existing.message_id = event.message_id
@@ -2112,6 +2267,10 @@ class FeishuAdapter(BasePlatformAdapter):
        default_ext: str,
        preferred_name: str,
    ) -> tuple[str, str]:
+        from tools.url_safety import is_safe_url
+        if not is_safe_url(file_url):
+            raise ValueError(f"Blocked unsafe URL (SSRF protection): {file_url[:80]}")
+
        import httpx

        async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:
@@ -2329,8 +2488,10 @@ class FeishuAdapter(BasePlatformAdapter):
    async def _enqueue_text_event(self, event: MessageEvent) -> None:
        """Debounce rapid Feishu text bursts into a single MessageEvent."""
        key = self._text_batch_key(event)
+        chunk_len = len(event.text or "")
        existing = self._pending_text_batches.get(key)
        if existing is None:
+            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
            self._pending_text_batches[key] = event
            self._pending_text_batch_counts[key] = 1
            self._schedule_text_batch_flush(key)
@@ -2355,6 +2516,7 @@ class FeishuAdapter(BasePlatformAdapter):
            return

        existing.text = next_text
+        existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
        existing.timestamp = event.timestamp
        if event.message_id:
            existing.message_id = event.message_id
@@ -2381,10 +2543,22 @@ class FeishuAdapter(BasePlatformAdapter):
        task_map[key] = asyncio.create_task(flush_fn(key))

    async def _flush_text_batch(self, key: str) -> None:
-        """Flush a pending text batch after the quiet period."""
+        """Flush a pending text batch after the quiet period.
+
+        Uses a longer delay when the latest chunk is near Feishu's ~4096-char
+        split point, since a continuation chunk is almost certain.
+        """
        current_task = asyncio.current_task()
        try:
-            await asyncio.sleep(self._text_batch_delay_seconds)
+            # Adaptive delay: if the latest chunk is near the split threshold,
+            # a continuation is almost certain — wait longer.
+            pending = self._pending_text_batches.get(key)
+            last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
+            if last_len >= self._SPLIT_THRESHOLD:
+                delay = self._text_batch_split_delay_seconds
+            else:
+                delay = self._text_batch_delay_seconds
+            await asyncio.sleep(delay)
            await self._flush_text_batch_now(key)
        finally:
            if self._pending_text_batch_tasks.get(key) is current_task:
@@ -40,6 +40,7 @@ from gateway.platforms.base import (
    BasePlatformAdapter,
    MessageEvent,
    MessageType,
+    ProcessingOutcome,
    SendResult,
 )

@@ -120,6 +121,11 @@ def check_matrix_requirements() -> bool:
 class MatrixAdapter(BasePlatformAdapter):
    """Gateway adapter for Matrix (any homeserver)."""

+    # Threshold for detecting Matrix client-side message splits.
+    # When a chunk is near the ~4000-char practical limit, a continuation
+    # is almost certain.
+    _SPLIT_THRESHOLD = 3900
+
    def __init__(self, config: PlatformConfig):
        super().__init__(config, Platform.MATRIX)

@@ -172,6 +178,13 @@ class MatrixAdapter(BasePlatformAdapter):
            "MATRIX_REACTIONS", "true"
        ).lower() not in ("false", "0", "no")

+        # Text batching: merge rapid successive messages (Telegram-style).
+        # Matrix clients split long messages around 4000 chars.
+        self._text_batch_delay_seconds = float(os.getenv("HERMES_MATRIX_TEXT_BATCH_DELAY_SECONDS", "0.6"))
+        self._text_batch_split_delay_seconds = float(os.getenv("HERMES_MATRIX_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0"))
+        self._pending_text_batches: Dict[str, MessageEvent] = {}
+        self._pending_text_batch_tasks: Dict[str, asyncio.Task] = {}
+
    def _is_duplicate_event(self, event_id) -> bool:
        """Return True if this event was already processed. Tracks the ID otherwise."""
        if not event_id:
@@ -586,6 +599,11 @@ class MatrixAdapter(BasePlatformAdapter):
        metadata: Optional[Dict[str, Any]] = None,
    ) -> SendResult:
        """Download an image URL and upload it to Matrix."""
+        from tools.url_safety import is_safe_url
+        if not is_safe_url(image_url):
+            logger.warning("Matrix: blocked unsafe image URL (SSRF protection)")
+            return await super().send_image(chat_id, image_url, caption, reply_to, metadata=metadata)
+
        try:
            # Try aiohttp first (always available), fall back to httpx
            try:
@@ -1083,7 +1101,81 @@ class MatrixAdapter(BasePlatformAdapter):
        # Acknowledge receipt so the room shows as read (fire-and-forget).
        self._background_read_receipt(room.room_id, event.event_id)

-        await self.handle_message(msg_event)
+        # Only batch plain text messages — commands dispatch immediately.
+        if msg_type == MessageType.TEXT and self._text_batch_delay_seconds > 0:
+            self._enqueue_text_event(msg_event)
+        else:
+            await self.handle_message(msg_event)
+
+    # ------------------------------------------------------------------
+    # Text message aggregation (handles Matrix client-side splits)
+    # ------------------------------------------------------------------
+
+    def _text_batch_key(self, event: MessageEvent) -> str:
+        """Session-scoped key for text message batching."""
+        from gateway.session import build_session_key
+        return build_session_key(
+            event.source,
+            group_sessions_per_user=self.config.extra.get("group_sessions_per_user", True),
+            thread_sessions_per_user=self.config.extra.get("thread_sessions_per_user", False),
+        )
+
+    def _enqueue_text_event(self, event: MessageEvent) -> None:
+        """Buffer a text event and reset the flush timer.
+
+        When a Matrix client splits a long message, the chunks arrive within
+        a few hundred milliseconds.  This merges them into a single event
+        before dispatching.
+        """
+        key = self._text_batch_key(event)
+        existing = self._pending_text_batches.get(key)
+        chunk_len = len(event.text or "")
+        if existing is None:
+            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
+            self._pending_text_batches[key] = event
+        else:
+            if event.text:
+                existing.text = f"{existing.text}\n{event.text}" if existing.text else event.text
+            existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
+            # Merge any media that might be attached
+            if event.media_urls:
+                existing.media_urls.extend(event.media_urls)
+                existing.media_types.extend(event.media_types)
+
+        # Cancel any pending flush and restart the timer
+        prior_task = self._pending_text_batch_tasks.get(key)
+        if prior_task and not prior_task.done():
+            prior_task.cancel()
+        self._pending_text_batch_tasks[key] = asyncio.create_task(
+            self._flush_text_batch(key)
+        )
+
+    async def _flush_text_batch(self, key: str) -> None:
+        """Wait for the quiet period then dispatch the aggregated text.
+
+        Uses a longer delay when the latest chunk is near Matrix's ~4000-char
+        split point, since a continuation chunk is almost certain.
+        """
+        current_task = asyncio.current_task()
+        try:
+            pending = self._pending_text_batches.get(key)
+            last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
+            if last_len >= self._SPLIT_THRESHOLD:
+                delay = self._text_batch_split_delay_seconds
+            else:
+                delay = self._text_batch_delay_seconds
+            await asyncio.sleep(delay)
+            event = self._pending_text_batches.pop(key, None)
+            if not event:
+                return
+            logger.info(
+                "[Matrix] Flushing text batch %s (%d chars)",
+                key, len(event.text or ""),
+            )
+            await self.handle_message(event)
+        finally:
+            if self._pending_text_batch_tasks.get(key) is current_task:
+                self._pending_text_batch_tasks.pop(key, None)

    async def _on_room_message_media(self, room: Any, event: Any) -> None:
        """Handle incoming media messages (images, audio, video, files)."""
@@ -1388,7 +1480,7 @@ class MatrixAdapter(BasePlatformAdapter):
            await self._send_reaction(room_id, msg_id, "\U0001f440")

    async def on_processing_complete(
-        self, event: MessageEvent, success: bool,
+        self, event: MessageEvent, outcome: ProcessingOutcome,
    ) -> None:
        """Replace eyes with checkmark (success) or cross (failure)."""
        if not self._reactions_enabled:
@@ -1397,11 +1489,15 @@ class MatrixAdapter(BasePlatformAdapter):
        room_id = event.source.chat_id
        if not msg_id or not room_id:
            return
+        if outcome == ProcessingOutcome.CANCELLED:
+            return
        # Note: Matrix doesn't support removing a specific reaction easily
        # without tracking the reaction event_id. We send the new reaction;
        # the eyes stays (acceptable UX — both are visible).
        await self._send_reaction(
-            room_id, msg_id, "\u2705" if success else "\u274c",
+            room_id,
+            msg_id,
+            "\u2705" if outcome == ProcessingOutcome.SUCCESS else "\u274c",
        )

    async def _on_reaction(self, room: Any, event: Any) -> None:
@@ -407,6 +407,11 @@ class MattermostAdapter(BasePlatformAdapter):
        kind: str = "file",
    ) -> SendResult:
        """Download a URL and upload it as a file attachment."""
+        from tools.url_safety import is_safe_url
+        if not is_safe_url(url):
+            logger.warning("Mattermost: blocked unsafe URL (SSRF protection)")
+            return await self.send(chat_id, f"{caption or ''}\n{url}".strip(), reply_to)
+
        import asyncio
        import aiohttp

@@ -647,7 +647,11 @@ class SignalAdapter(BasePlatformAdapter):

        if result is not None:
            self._track_sent_timestamp(result)
-            return SendResult(success=True)
+            # Use the timestamp from the RPC result as a pseudo message_id.
+            # Signal doesn't have real message IDs, but the stream consumer
+            # needs a truthy value to follow its edit→fallback path correctly.
+            _msg_id = str(result.get("timestamp", "")) if isinstance(result, dict) else None
+            return SendResult(success=True, message_id=_msg_id or None)
        return SendResult(success=False, error="RPC send failed")

    def _track_sent_timestamp(self, rpc_result) -> None:
@@ -837,6 +841,11 @@ class SignalAdapter(BasePlatformAdapter):
            except asyncio.CancelledError:
                pass

+    async def stop_typing(self, chat_id: str) -> None:
+        """Public interface for stopping typing — called by base adapter's
+        _keep_typing finally block to clean up platform-level typing tasks."""
+        await self._stop_typing_indicator(chat_id)
+
    # ------------------------------------------------------------------
    # Chat Info
    # ------------------------------------------------------------------
@@ -14,7 +14,8 @@ import logging
 import os
 import re
 import time
-from typing import Dict, Optional, Any
+from dataclasses import dataclass, field
+from typing import Dict, Optional, Any, Tuple

 try:
    from slack_bolt.async_app import AsyncApp
@@ -45,6 +46,14 @@ from gateway.platforms.base import (
 logger = logging.getLogger(__name__)


+@dataclass
+class _ThreadContextCache:
+    """Cache entry for fetched thread context."""
+    content: str
+    fetched_at: float = field(default_factory=time.monotonic)
+    message_count: int = 0
+
+
 def check_slack_requirements() -> bool:
    """Check if Slack dependencies are available."""
    return SLACK_AVAILABLE
@@ -95,6 +104,15 @@ class SlackAdapter(BasePlatformAdapter):
        # respond to ALL subsequent messages in that thread automatically.
        self._mentioned_threads: set = set()
        self._MENTIONED_THREADS_MAX = 5000
+        # Assistant thread metadata keyed by (channel_id, thread_ts). Slack's
+        # AI Assistant lifecycle events can arrive before/alongside message
+        # events, and they carry the user/thread identity needed for stable
+        # session + memory scoping.
+        self._assistant_threads: Dict[Tuple[str, str], Dict[str, str]] = {}
+        self._ASSISTANT_THREADS_MAX = 5000
+        # Cache for _fetch_thread_context results: cache_key → _ThreadContextCache
+        self._thread_context_cache: Dict[str, _ThreadContextCache] = {}
+        self._THREAD_CACHE_TTL = 60.0

    async def connect(self) -> bool:
        """Connect to Slack via Socket Mode."""
@@ -181,6 +199,14 @@ class SlackAdapter(BasePlatformAdapter):
            async def handle_app_mention(event, say):
                pass

+            @self._app.event("assistant_thread_started")
+            async def handle_assistant_thread_started(event, say):
+                await self._handle_assistant_thread_lifecycle_event(event)
+
+            @self._app.event("assistant_thread_context_changed")
+            async def handle_assistant_thread_context_changed(event, say):
+                await self._handle_assistant_thread_lifecycle_event(event)
+
            # Register slash command handler
            @self._app.command("/hermes")
            async def handle_hermes_command(ack, command):
@@ -267,6 +293,7 @@ class SlackAdapter(BasePlatformAdapter):
                kwargs = {
                    "channel": chat_id,
                    "text": chunk,
+                    "mrkdwn": True,
                }
                if thread_ts:
                    kwargs["thread_ts"] = thread_ts
@@ -309,9 +336,7 @@ class SlackAdapter(BasePlatformAdapter):
        if not self._app:
            return SendResult(success=False, error="Not connected")
        try:
-            # Convert standard markdown → Slack mrkdwn
            formatted = self.format_message(content)
-
            await self._get_client(chat_id).chat_update(
                channel=chat_id,
                ts=message_id,
@@ -443,13 +468,36 @@ class SlackAdapter(BasePlatformAdapter):
        text = re.sub(r'(`[^`]+`)', lambda m: _ph(m.group(0)), text)

        # 3) Convert markdown links [text](url) → <url|text>
+        def _convert_markdown_link(m):
+            label = m.group(1)
+            url = m.group(2).strip()
+            if url.startswith('<') and url.endswith('>'):
+                url = url[1:-1].strip()
+            return _ph(f'<{url}|{label}>')
+
        text = re.sub(
-            r'\[([^\]]+)\]\(([^)]+)\)',
-            lambda m: _ph(f'<{m.group(2)}|{m.group(1)}>'),
+            r'\[([^\]]+)\]\(([^()]*(?:\([^()]*\)[^()]*)*)\)',
+            _convert_markdown_link,
            text,
        )

-        # 4) Convert headers (## Title) → *Title* (bold)
+        # 4) Protect existing Slack entities/manual links so escaping and later
+        #    formatting passes don't break them.
+        text = re.sub(
+            r'(<(?:[@#!]|(?:https?|mailto|tel):)[^>\n]+>)',
+            lambda m: _ph(m.group(1)),
+            text,
+        )
+
+        # 5) Protect blockquote markers before escaping
+        text = re.sub(r'^(>+\s)', lambda m: _ph(m.group(0)), text, flags=re.MULTILINE)
+
+        # 6) Escape Slack control characters in remaining plain text.
+        # Unescape first so already-escaped input doesn't get double-escaped.
+        text = text.replace('&amp;', '&').replace('&lt;', '<').replace('&gt;', '>')
+        text = text.replace('&', '&amp;').replace('<', '&lt;').replace('>', '&gt;')
+
+        # 7) Convert headers (## Title) → *Title* (bold)
        def _convert_header(m):
            inner = m.group(1).strip()
            # Strip redundant bold markers inside a header
@@ -460,34 +508,39 @@ class SlackAdapter(BasePlatformAdapter):
            r'^#{1,6}\s+(.+)$', _convert_header, text, flags=re.MULTILINE
        )

-        # 5) Convert bold: **text** → *text* (Slack bold)
+        # 8) Convert bold+italic: ***text*** → *_text_* (Slack bold wrapping italic)
+        text = re.sub(
+            r'\*\*\*(.+?)\*\*\*',
+            lambda m: _ph(f'*_{m.group(1)}_*'),
+            text,
+        )
+
+        # 9) Convert bold: **text** → *text* (Slack bold)
        text = re.sub(
            r'\*\*(.+?)\*\*',
            lambda m: _ph(f'*{m.group(1)}*'),
            text,
        )

-        # 6) Convert italic: _text_ stays as _text_ (already Slack italic)
-        #    Single *text* → _text_ (Slack italic)
+        # 10) Convert italic: _text_ stays as _text_ (already Slack italic)
+        #     Single *text* → _text_ (Slack italic)
        text = re.sub(
            r'(?<!\*)\*([^*\n]+)\*(?!\*)',
            lambda m: _ph(f'_{m.group(1)}_'),
            text,
        )

-        # 7) Convert strikethrough: ~~text~~ → ~text~
+        # 11) Convert strikethrough: ~~text~~ → ~text~
        text = re.sub(
            r'~~(.+?)~~',
            lambda m: _ph(f'~{m.group(1)}~'),
            text,
        )

-        # 8) Convert blockquotes: > text → > text (same syntax, just ensure
-        #    no extra escaping happens to the > character)
-        # Slack uses the same > prefix, so this is a no-op for content.
+        # 12) Blockquotes: > prefix is already protected by step 5 above.

-        # 9) Restore placeholders in reverse order
-        for key in reversed(list(placeholders.keys())):
+        # 13) Restore placeholders in reverse order
+        for key in reversed(placeholders):
            text = text.replace(key, placeholders[key])

        return text
@@ -595,6 +648,11 @@ class SlackAdapter(BasePlatformAdapter):
        if not self._app:
            return SendResult(success=False, error="Not connected")

+        from tools.url_safety import is_safe_url
+        if not is_safe_url(image_url):
+            logger.warning("[Slack] Blocked unsafe image URL (SSRF protection)")
+            return await super().send_image(chat_id, image_url, caption, reply_to, metadata=metadata)
+
        try:
            import httpx

@@ -750,6 +808,135 @@ class SlackAdapter(BasePlatformAdapter):

    # ----- Internal handlers -----

+    def _assistant_thread_key(self, channel_id: str, thread_ts: str) -> Optional[Tuple[str, str]]:
+        """Return a stable cache key for Slack assistant thread metadata."""
+        if not channel_id or not thread_ts:
+            return None
+        return (str(channel_id), str(thread_ts))
+
+    def _extract_assistant_thread_metadata(self, event: dict) -> Dict[str, str]:
+        """Extract Slack Assistant thread identity data from an event payload."""
+        assistant_thread = event.get("assistant_thread") or {}
+        context = assistant_thread.get("context") or event.get("context") or {}
+
+        channel_id = (
+            assistant_thread.get("channel_id")
+            or event.get("channel")
+            or context.get("channel_id")
+            or ""
+        )
+        thread_ts = (
+            assistant_thread.get("thread_ts")
+            or event.get("thread_ts")
+            or event.get("message_ts")
+            or ""
+        )
+        user_id = (
+            assistant_thread.get("user_id")
+            or event.get("user")
+            or context.get("user_id")
+            or ""
+        )
+        team_id = (
+            event.get("team")
+            or event.get("team_id")
+            or assistant_thread.get("team_id")
+            or ""
+        )
+        context_channel_id = context.get("channel_id") or ""
+
+        return {
+            "channel_id": str(channel_id) if channel_id else "",
+            "thread_ts": str(thread_ts) if thread_ts else "",
+            "user_id": str(user_id) if user_id else "",
+            "team_id": str(team_id) if team_id else "",
+            "context_channel_id": str(context_channel_id) if context_channel_id else "",
+        }
+
+    def _cache_assistant_thread_metadata(self, metadata: Dict[str, str]) -> None:
+        """Remember assistant thread identity data for later message events."""
+        channel_id = metadata.get("channel_id", "")
+        thread_ts = metadata.get("thread_ts", "")
+        key = self._assistant_thread_key(channel_id, thread_ts)
+        if not key:
+            return
+
+        existing = self._assistant_threads.get(key, {})
+        merged = dict(existing)
+        merged.update({k: v for k, v in metadata.items() if v})
+        self._assistant_threads[key] = merged
+
+        # Evict oldest entries when the cache exceeds the limit
+        if len(self._assistant_threads) > self._ASSISTANT_THREADS_MAX:
+            excess = len(self._assistant_threads) - self._ASSISTANT_THREADS_MAX // 2
+            for old_key in list(self._assistant_threads)[:excess]:
+                del self._assistant_threads[old_key]
+
+        team_id = merged.get("team_id", "")
+        if team_id and channel_id:
+            self._channel_team[channel_id] = team_id
+
+    def _lookup_assistant_thread_metadata(
+        self,
+        event: dict,
+        channel_id: str = "",
+        thread_ts: str = "",
+    ) -> Dict[str, str]:
+        """Load cached assistant-thread metadata that matches the current event."""
+        metadata = self._extract_assistant_thread_metadata(event)
+        if channel_id and not metadata.get("channel_id"):
+            metadata["channel_id"] = channel_id
+        if thread_ts and not metadata.get("thread_ts"):
+            metadata["thread_ts"] = thread_ts
+
+        key = self._assistant_thread_key(
+            metadata.get("channel_id", ""),
+            metadata.get("thread_ts", ""),
+        )
+        cached = self._assistant_threads.get(key, {}) if key else {}
+        if cached:
+            merged = dict(cached)
+            merged.update({k: v for k, v in metadata.items() if v})
+            return merged
+        return metadata
+
+    def _seed_assistant_thread_session(self, metadata: Dict[str, str]) -> None:
+        """Prime the session store so assistant threads get stable user scoping."""
+        session_store = getattr(self, "_session_store", None)
+        if not session_store:
+            return
+
+        channel_id = metadata.get("channel_id", "")
+        thread_ts = metadata.get("thread_ts", "")
+        user_id = metadata.get("user_id", "")
+        if not channel_id or not thread_ts or not user_id:
+            return
+
+        source = self.build_source(
+            chat_id=channel_id,
+            chat_name=channel_id,
+            chat_type="dm",
+            user_id=user_id,
+            thread_id=thread_ts,
+            chat_topic=metadata.get("context_channel_id") or None,
+        )
+
+        try:
+            session_store.get_or_create_session(source)
+        except Exception:
+            logger.debug(
+                "[Slack] Failed to seed assistant thread session for %s/%s",
+                channel_id,
+                thread_ts,
+                exc_info=True,
+            )
+
+    async def _handle_assistant_thread_lifecycle_event(self, event: dict) -> None:
+        """Handle Slack Assistant lifecycle events that carry user/thread identity."""
+        metadata = self._extract_assistant_thread_metadata(event)
+        self._cache_assistant_thread_metadata(metadata)
+        self._seed_assistant_thread_session(metadata)
+
    async def _handle_slack_message(self, event: dict) -> None:
        """Handle an incoming Slack message event."""
        # Dedup: Slack Socket Mode can redeliver events after reconnects (#4777)
@@ -766,9 +953,26 @@ class SlackAdapter(BasePlatformAdapter):
                    if v > cutoff
                }

-        # Ignore bot messages (including our own)
+        # Bot message filtering (SLACK_ALLOW_BOTS / config allow_bots):
+        #   "none"     — ignore all bot messages (default, backward-compatible)
+        #   "mentions" — accept bot messages only when they @mention us
+        #   "all"      — accept all bot messages (except our own)
        if event.get("bot_id") or event.get("subtype") == "bot_message":
-            return
+            allow_bots = self.config.extra.get("allow_bots", "")
+            if not allow_bots:
+                allow_bots = os.getenv("SLACK_ALLOW_BOTS", "none")
+            allow_bots = str(allow_bots).lower().strip()
+            if allow_bots == "none":
+                return
+            elif allow_bots == "mentions":
+                text_check = event.get("text", "")
+                if self._bot_user_id and f"<@{self._bot_user_id}>" not in text_check:
+                    return
+            # "all" falls through to process the message
+            # Always ignore our own messages to prevent echo loops
+            msg_user = event.get("user", "")
+            if msg_user and self._bot_user_id and msg_user == self._bot_user_id:
+                return

        # Ignore message edits and deletions
        subtype = event.get("subtype")
@@ -776,10 +980,21 @@ class SlackAdapter(BasePlatformAdapter):
            return

        text = event.get("text", "")
-        user_id = event.get("user", "")
        channel_id = event.get("channel", "")
        ts = event.get("ts", "")
-        team_id = event.get("team", "")
+        assistant_meta = self._lookup_assistant_thread_metadata(
+            event,
+            channel_id=channel_id,
+            thread_ts=event.get("thread_ts", ""),
+        )
+        user_id = event.get("user") or assistant_meta.get("user_id", "")
+        if not channel_id:
+            channel_id = assistant_meta.get("channel_id", "")
+        team_id = (
+            event.get("team")
+            or event.get("team_id")
+            or assistant_meta.get("team_id", "")
+        )

        # Track which workspace owns this channel
        if team_id and channel_id:
@@ -787,7 +1002,9 @@ class SlackAdapter(BasePlatformAdapter):

        # Determine if this is a DM or channel message
        channel_type = event.get("channel_type", "")
-        is_dm = channel_type == "im"
+        if not channel_type and channel_id.startswith("D"):
+            channel_type = "im"
+        is_dm = channel_type in ("im", "mpim")  # Both 1:1 and group DMs

        # Build thread_ts for session keying.
        # In channels: fall back to ts so each top-level @mention starts a
@@ -795,11 +1012,13 @@ class SlackAdapter(BasePlatformAdapter):
        # In DMs: only use the real thread_ts — top-level DMs should share
        #   one continuous session, threaded DMs get their own session.
        if is_dm:
-            thread_ts = event.get("thread_ts")  # None for top-level DMs
+            thread_ts = event.get("thread_ts") or assistant_meta.get("thread_ts")  # None for top-level DMs
        else:
            thread_ts = event.get("thread_ts") or ts  # ts fallback for channels

        # In channels, respond if:
+        #   0. Channel is in free_response_channels, OR require_mention is
+        #      disabled — always process regardless of mention.
        #   1. The bot is @mentioned in this message, OR
        #   2. The message is a reply in a thread the bot started/participated in, OR
        #   3. The message is in a thread where the bot was previously @mentioned, OR
@@ -809,24 +1028,29 @@ class SlackAdapter(BasePlatformAdapter):
        event_thread_ts = event.get("thread_ts")
        is_thread_reply = bool(event_thread_ts and event_thread_ts != ts)

-        if not is_dm and bot_uid and not is_mentioned:
-            reply_to_bot_thread = (
-                is_thread_reply and event_thread_ts in self._bot_message_ts
-            )
-            in_mentioned_thread = (
-                event_thread_ts is not None
-                and event_thread_ts in self._mentioned_threads
-            )
-            has_session = (
-                is_thread_reply
-                and self._has_active_session_for_thread(
-                    channel_id=channel_id,
-                    thread_ts=event_thread_ts,
-                    user_id=user_id,
+        if not is_dm and bot_uid:
+            if channel_id in self._slack_free_response_channels():
+                pass  # Free-response channel — always process
+            elif not self._slack_require_mention():
+                pass  # Mention requirement disabled globally for Slack
+            elif not is_mentioned:
+                reply_to_bot_thread = (
+                    is_thread_reply and event_thread_ts in self._bot_message_ts
                )
-            )
-            if not reply_to_bot_thread and not in_mentioned_thread and not has_session:
-                return
+                in_mentioned_thread = (
+                    event_thread_ts is not None
+                    and event_thread_ts in self._mentioned_threads
+                )
+                has_session = (
+                    is_thread_reply
+                    and self._has_active_session_for_thread(
+                        channel_id=channel_id,
+                        thread_ts=event_thread_ts,
+                        user_id=user_id,
+                    )
+                )
+                if not reply_to_bot_thread and not in_mentioned_thread and not has_session:
+                    return

        if is_mentioned:
            # Strip the bot mention from the text
@@ -967,14 +1191,19 @@ class SlackAdapter(BasePlatformAdapter):
            reply_to_message_id=thread_ts if thread_ts != ts else None,
        )

-        # Add 👀 reaction to acknowledge receipt
-        await self._add_reaction(channel_id, ts, "eyes")
+        # Only react when bot is directly addressed (DM or @mention).
+        # In listen-all channels (require_mention=false), reacting to every
+        # casual message would be noisy.
+        _should_react = is_dm or is_mentioned
+
+        if _should_react:
+            await self._add_reaction(channel_id, ts, "eyes")

        await self.handle_message(msg_event)

-        # Replace 👀 with ✅ when done
-        await self._remove_reaction(channel_id, ts, "eyes")
-        await self._add_reaction(channel_id, ts, "white_check_mark")
+        if _should_react:
+            await self._remove_reaction(channel_id, ts, "eyes")
+            await self._add_reaction(channel_id, ts, "white_check_mark")

    # ----- Approval button support (Block Kit) -----

@@ -1068,6 +1297,20 @@ class SlackAdapter(BasePlatformAdapter):
        msg_ts = message.get("ts", "")
        channel_id = body.get("channel", {}).get("id", "")
        user_name = body.get("user", {}).get("name", "unknown")
+        user_id = body.get("user", {}).get("id", "")
+
+        # Only authorized users may click approval buttons.  Button clicks
+        # bypass the normal message auth flow in gateway/run.py, so we must
+        # check here as well.
+        allowed_csv = os.getenv("SLACK_ALLOWED_USERS", "").strip()
+        if allowed_csv:
+            allowed_ids = {uid.strip() for uid in allowed_csv.split(",") if uid.strip()}
+            if "*" not in allowed_ids and user_id not in allowed_ids:
+                logger.warning(
+                    "[Slack] Unauthorized approval click by %s (%s) — ignoring",
+                    user_name, user_id,
+                )
+                return

        # Map action_id to approval choice
        choice_map = {
@@ -1078,10 +1321,9 @@ class SlackAdapter(BasePlatformAdapter):
        }
        choice = choice_map.get(action_id, "deny")

-        # Prevent double-clicks
-        if self._approval_resolved.get(msg_ts, False):
+        # Prevent double-clicks — atomic pop; first caller gets False, others get True (default)
+        if self._approval_resolved.pop(msg_ts, True):
            return
-        self._approval_resolved[msg_ts] = True

        # Update the message to show the decision and remove buttons
        label_map = {
@@ -1136,8 +1378,7 @@ class SlackAdapter(BasePlatformAdapter):
        except Exception as exc:
            logger.error("Failed to resolve gateway approval from Slack button: %s", exc)

-        # Clean up stale approval state
-        self._approval_resolved.pop(msg_ts, None)
+        # (approval state already consumed by atomic pop above)

    # ----- Thread context fetching -----

@@ -1148,57 +1389,104 @@ class SlackAdapter(BasePlatformAdapter):
        """Fetch recent thread messages to provide context when the bot is
        mentioned mid-thread for the first time.

-        Returns a formatted string with thread history, or empty string on
-        failure or if the thread is empty (just the parent message).
+        This method is only called when there is NO active session for the
+        thread (guarded at the call site by _has_active_session_for_thread).
+        That guard ensures thread messages are prepended only on the very
+        first turn — after that the session history already holds them, so
+        there is no duplication across subsequent turns.
+
+        Results are cached for _THREAD_CACHE_TTL seconds per thread to avoid
+        hammering conversations.replies (Tier 3, ~50 req/min).
+
+        Returns a formatted string with prior thread history, or empty string
+        on failure or if the thread has no prior messages.
        """
+        cache_key = f"{channel_id}:{thread_ts}"
+        now = time.monotonic()
+        cached = self._thread_context_cache.get(cache_key)
+        if cached and (now - cached.fetched_at) < self._THREAD_CACHE_TTL:
+            return cached.content
+
        try:
            client = self._get_client(channel_id)
-            result = await client.conversations_replies(
-                channel=channel_id,
-                ts=thread_ts,
-                limit=limit + 1,  # +1 because it includes the current message
-                inclusive=True,
-            )
+
+            # Retry with exponential backoff for Tier-3 rate limits (429).
+            result = None
+            for attempt in range(3):
+                try:
+                    result = await client.conversations_replies(
+                        channel=channel_id,
+                        ts=thread_ts,
+                        limit=limit + 1,  # +1 because it includes the current message
+                        inclusive=True,
+                    )
+                    break
+                except Exception as exc:
+                    # Check for rate-limit error from slack_sdk
+                    err_str = str(exc).lower()
+                    is_rate_limit = (
+                        "ratelimited" in err_str
+                        or "429" in err_str
+                        or "rate_limited" in err_str
+                    )
+                    if is_rate_limit and attempt < 2:
+                        retry_after = 1.0 * (2 ** attempt)  # 1s, 2s
+                        logger.warning(
+                            "[Slack] conversations.replies rate limited; retrying in %.1fs (attempt %d/3)",
+                            retry_after, attempt + 1,
+                        )
+                        await asyncio.sleep(retry_after)
+                        continue
+                    raise
+
+            if result is None:
+                return ""
+
            messages = result.get("messages", [])
            if not messages:
                return ""

+            bot_uid = self._team_bot_user_ids.get(team_id, self._bot_user_id)
            context_parts = []
            for msg in messages:
                msg_ts = msg.get("ts", "")
-                # Skip the current message (the one that triggered this fetch)
+                # Exclude the current triggering message — it will be delivered
+                # as the user message itself, so including it here would duplicate it.
                if msg_ts == current_ts:
                    continue
-                # Skip bot messages from ourselves
+                # Exclude our own bot messages to avoid circular context.
                if msg.get("bot_id") or msg.get("subtype") == "bot_message":
                    continue

-                msg_user = msg.get("user", "unknown")
                msg_text = msg.get("text", "").strip()
                if not msg_text:
                    continue

                # Strip bot mentions from context messages
-                bot_uid = self._team_bot_user_ids.get(team_id, self._bot_user_id)
                if bot_uid:
                    msg_text = msg_text.replace(f"<@{bot_uid}>", "").strip()

-                # Mark the thread parent
+                msg_user = msg.get("user", "unknown")
                is_parent = msg_ts == thread_ts
                prefix = "[thread parent] " if is_parent else ""
-
-                # Resolve user name (cached)
                name = await self._resolve_user_name(msg_user, chat_id=channel_id)
                context_parts.append(f"{prefix}{name}: {msg_text}")

-            if not context_parts:
-                return ""
+            content = ""
+            if context_parts:
+                content = (
+                    "[Thread context — prior messages in this thread (not yet in conversation history):]\n"
+                    + "\n".join(context_parts)
+                    + "\n[End of thread context]\n\n"
+                )

-            return (
-                "[Thread context — previous messages in this thread:]\n"
-                + "\n".join(context_parts)
-                + "\n[End of thread context]\n\n"
+            self._thread_context_cache[cache_key] = _ThreadContextCache(
+                content=content,
+                fetched_at=now,
+                message_count=len(context_parts),
            )
+            return content
+
        except Exception as e:
            logger.warning("[Slack] Failed to fetch thread context: %s", e)
            return ""
@@ -1308,6 +1596,18 @@ class SlackAdapter(BasePlatformAdapter):
                    )
                    response.raise_for_status()

+                    # Slack may return an HTML sign-in/redirect page
+                    # instead of actual media bytes (e.g. expired token,
+                    # restricted file access).  Detect this early so we
+                    # don't cache bogus data and confuse downstream tools.
+                    ct = response.headers.get("content-type", "")
+                    if "text/html" in ct:
+                        raise ValueError(
+                            "Slack returned HTML instead of media "
+                            f"(content-type: {ct}); "
+                            "check bot token scopes and file permissions"
+                        )
+
                    if audio:
                        from gateway.platforms.base import cache_audio_from_bytes
                        return cache_audio_from_bytes(response.content, ext)
@@ -1354,3 +1654,30 @@ class SlackAdapter(BasePlatformAdapter):
                        continue
                    raise
        raise last_exc
+
+    # ── Channel mention gating ─────────────────────────────────────────────
+
+    def _slack_require_mention(self) -> bool:
+        """Return whether channel messages require an explicit bot mention.
+
+        Uses explicit-false parsing (like Discord/Matrix) rather than
+        truthy parsing, since the safe default is True (gating on).
+        Unrecognised or empty values keep gating enabled.
+        """
+        configured = self.config.extra.get("require_mention")
+        if configured is not None:
+            if isinstance(configured, str):
+                return configured.lower() not in ("false", "0", "no", "off")
+            return bool(configured)
+        return os.getenv("SLACK_REQUIRE_MENTION", "true").lower() not in ("false", "0", "no", "off")
+
+    def _slack_free_response_channels(self) -> set:
+        """Return channel IDs where no @mention is required."""
+        raw = self.config.extra.get("free_response_channels")
+        if raw is None:
+            raw = os.getenv("SLACK_FREE_RESPONSE_CHANNELS", "")
+        if isinstance(raw, list):
+            return {str(part).strip() for part in raw if str(part).strip()}
+        if isinstance(raw, str) and raw.strip():
+            return {part.strip() for part in raw.split(",") if part.strip()}
+        return set()
@@ -60,6 +60,7 @@ from gateway.platforms.base import (
    BasePlatformAdapter,
    MessageEvent,
    MessageType,
+    ProcessingOutcome,
    SendResult,
    cache_image_from_bytes,
    cache_audio_from_bytes,
@@ -121,6 +122,9 @@ class TelegramAdapter(BasePlatformAdapter):
    
    # Telegram message limits
    MAX_MESSAGE_LENGTH = 4096
+    # Threshold for detecting Telegram client-side message splits.
+    # When a chunk is near this limit, a continuation is almost certain.
+    _SPLIT_THRESHOLD = 4000
    MEDIA_GROUP_WAIT_SECONDS = 0.8
    
    def __init__(self, config: PlatformConfig):
@@ -140,6 +144,7 @@ class TelegramAdapter(BasePlatformAdapter):
        # Buffer rapid text messages so Telegram client-side splits of long
        # messages are aggregated into a single MessageEvent.
        self._text_batch_delay_seconds = float(os.getenv("HERMES_TELEGRAM_TEXT_BATCH_DELAY_SECONDS", "0.6"))
+        self._text_batch_split_delay_seconds = float(os.getenv("HERMES_TELEGRAM_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0"))
        self._pending_text_batches: Dict[str, MessageEvent] = {}
        self._pending_text_batch_tasks: Dict[str, asyncio.Task] = {}
        self._token_lock_identity: Optional[str] = None
@@ -513,6 +518,36 @@ class TelegramAdapter(BasePlatformAdapter):

            # Build the application
            builder = Application.builder().token(self.config.token)
+
+            # PTB defaults (pool_timeout=1s) are too aggressive on flaky networks and
+            # can trigger "Pool timeout: All connections in the connection pool are occupied"
+            # during reconnect/bootstrap. Use safer defaults and allow env overrides.
+            def _env_int(name: str, default: int) -> int:
+                try:
+                    return int(os.getenv(name, str(default)))
+                except (TypeError, ValueError):
+                    return default
+
+            def _env_float(name: str, default: float) -> float:
+                try:
+                    return float(os.getenv(name, str(default)))
+                except (TypeError, ValueError):
+                    return default
+
+            request_kwargs = {
+                "connection_pool_size": _env_int("HERMES_TELEGRAM_HTTP_POOL_SIZE", 512),
+                "pool_timeout": _env_float("HERMES_TELEGRAM_HTTP_POOL_TIMEOUT", 8.0),
+                "connect_timeout": _env_float("HERMES_TELEGRAM_HTTP_CONNECT_TIMEOUT", 10.0),
+                "read_timeout": _env_float("HERMES_TELEGRAM_HTTP_READ_TIMEOUT", 20.0),
+                "write_timeout": _env_float("HERMES_TELEGRAM_HTTP_WRITE_TIMEOUT", 20.0),
+            }
+
+            proxy_configured = any(
+                (os.getenv(k) or "").strip()
+                for k in ("HTTPS_PROXY", "HTTP_PROXY", "ALL_PROXY", "https_proxy", "http_proxy", "all_proxy")
+            )
+            disable_fallback = (os.getenv("HERMES_TELEGRAM_DISABLE_FALLBACK_IPS", "").strip().lower() in ("1", "true", "yes", "on"))
+
            fallback_ips = self._fallback_ips()
            if not fallback_ips:
                fallback_ips = await discover_fallback_ips()
@@ -521,16 +556,32 @@ class TelegramAdapter(BasePlatformAdapter):
                    self.name,
                    ", ".join(fallback_ips),
                )
-            if fallback_ips:
+
+            if fallback_ips and not proxy_configured and not disable_fallback:
                logger.info(
                    "[%s] Telegram fallback IPs active: %s",
                    self.name,
                    ", ".join(fallback_ips),
                )
-                transport = TelegramFallbackTransport(fallback_ips)
-                request = HTTPXRequest(httpx_kwargs={"transport": transport})
-                get_updates_request = HTTPXRequest(httpx_kwargs={"transport": transport})
-                builder = builder.request(request).get_updates_request(get_updates_request)
+                # Keep request/update pools separate to reduce contention during
+                # polling reconnect + bot API bootstrap/delete_webhook calls.
+                request = HTTPXRequest(
+                    **request_kwargs,
+                    httpx_kwargs={"transport": TelegramFallbackTransport(fallback_ips)},
+                )
+                get_updates_request = HTTPXRequest(
+                    **request_kwargs,
+                    httpx_kwargs={"transport": TelegramFallbackTransport(fallback_ips)},
+                )
+            else:
+                if proxy_configured:
+                    logger.info("[%s] Proxy configured; skipping Telegram fallback-IP transport", self.name)
+                elif disable_fallback:
+                    logger.info("[%s] Telegram fallback-IP transport disabled via env", self.name)
+                request = HTTPXRequest(**request_kwargs)
+                get_updates_request = HTTPXRequest(**request_kwargs)
+
+            builder = builder.request(request).get_updates_request(get_updates_request)
            self._app = builder.build()
            self._bot = self._app.bot
            
@@ -1398,6 +1449,15 @@ class TelegramAdapter(BasePlatformAdapter):
                    await query.answer(text="Invalid approval data.")
                    return

+                # Only authorized users may click approval buttons.
+                caller_id = str(getattr(query.from_user, "id", ""))
+                allowed_csv = os.getenv("TELEGRAM_ALLOWED_USERS", "").strip()
+                if allowed_csv:
+                    allowed_ids = {uid.strip() for uid in allowed_csv.split(",") if uid.strip()}
+                    if "*" not in allowed_ids and caller_id not in allowed_ids:
+                        await query.answer(text="⛔ You are not authorized to approve commands.")
+                        return
+
                session_key = self._approval_state.pop(approval_id, None)
                if not session_key:
                    await query.answer(text="This approval has already been resolved.")
@@ -1632,7 +1692,12 @@ class TelegramAdapter(BasePlatformAdapter):
        """
        if not self._bot:
            return SendResult(success=False, error="Not connected")
-        
+
+        from tools.url_safety import is_safe_url
+        if not is_safe_url(image_url):
+            logger.warning("[%s] Blocked unsafe image URL (SSRF protection)", self.name)
+            return await super().send_image(chat_id, image_url, caption, reply_to, metadata=metadata)
+
        try:
            # Telegram can send photos directly from URLs (up to ~5MB)
            _photo_thread = metadata.get("thread_id") if metadata else None
@@ -2146,12 +2211,15 @@ class TelegramAdapter(BasePlatformAdapter):
        """
        key = self._text_batch_key(event)
        existing = self._pending_text_batches.get(key)
+        chunk_len = len(event.text or "")
        if existing is None:
+            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
            self._pending_text_batches[key] = event
        else:
            # Append text from the follow-up chunk
            if event.text:
                existing.text = f"{existing.text}\n{event.text}" if existing.text else event.text
+            existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
            # Merge any media that might be attached
            if event.media_urls:
                existing.media_urls.extend(event.media_urls)
@@ -2166,10 +2234,22 @@ class TelegramAdapter(BasePlatformAdapter):
        )

    async def _flush_text_batch(self, key: str) -> None:
-        """Wait for the quiet period then dispatch the aggregated text."""
+        """Wait for the quiet period then dispatch the aggregated text.
+
+        Uses a longer delay when the latest chunk is near Telegram's 4096-char
+        split point, since a continuation chunk is almost certain.
+        """
        current_task = asyncio.current_task()
        try:
-            await asyncio.sleep(self._text_batch_delay_seconds)
+            # Adaptive delay: if the latest chunk is near Telegram's 4096-char
+            # split point, a continuation is almost certain — wait longer.
+            pending = self._pending_text_batches.get(key)
+            last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
+            if last_len >= self._SPLIT_THRESHOLD:
+                delay = self._text_batch_split_delay_seconds
+            else:
+                delay = self._text_batch_delay_seconds
+            await asyncio.sleep(delay)
            event = self._pending_text_batches.pop(key, None)
            if not event:
                return
@@ -2222,10 +2302,7 @@ class TelegramAdapter(BasePlatformAdapter):
            existing.media_urls.extend(event.media_urls)
            existing.media_types.extend(event.media_types)
            if event.text:
-                if not existing.text:
-                    existing.text = event.text
-                elif event.text not in existing.text:
-                    existing.text = f"{existing.text}\n\n{event.text}".strip()
+                existing.text = self._merge_caption(existing.text, event.text)

        prior_task = self._pending_photo_batch_tasks.get(batch_key)
        if prior_task and not prior_task.done():
@@ -2415,11 +2492,7 @@ class TelegramAdapter(BasePlatformAdapter):
            existing.media_urls.extend(event.media_urls)
            existing.media_types.extend(event.media_types)
            if event.text:
-                if existing.text:
-                    if event.text not in existing.text.split("\n\n"):
-                        existing.text = f"{existing.text}\n\n{event.text}"
-                else:
-                    existing.text = event.text
+                existing.text = self._merge_caption(existing.text, event.text)

        prior_task = self._media_group_tasks.get(media_group_id)
        if prior_task:
@@ -2675,3 +2748,50 @@ class TelegramAdapter(BasePlatformAdapter):
            auto_skill=topic_skill,
            timestamp=message.date,
        )
+
+    # ── Message reactions (processing lifecycle) ──────────────────────────
+
+    def _reactions_enabled(self) -> bool:
+        """Check if message reactions are enabled via config/env."""
+        return os.getenv("TELEGRAM_REACTIONS", "false").lower() not in ("false", "0", "no")
+
+    async def _set_reaction(self, chat_id: str, message_id: str, emoji: str) -> bool:
+        """Set a single emoji reaction on a Telegram message."""
+        if not self._bot:
+            return False
+        try:
+            await self._bot.set_message_reaction(
+                chat_id=int(chat_id),
+                message_id=int(message_id),
+                reaction=emoji,
+            )
+            return True
+        except Exception as e:
+            logger.debug("[%s] set_message_reaction failed (%s): %s", self.name, emoji, e)
+            return False
+
+    async def on_processing_start(self, event: MessageEvent) -> None:
+        """Add an in-progress reaction when message processing begins."""
+        if not self._reactions_enabled():
+            return
+        chat_id = getattr(event.source, "chat_id", None)
+        message_id = getattr(event, "message_id", None)
+        if chat_id and message_id:
+            await self._set_reaction(chat_id, message_id, "\U0001f440")
+
+    async def on_processing_complete(self, event: MessageEvent, outcome: ProcessingOutcome) -> None:
+        """Swap the in-progress reaction for a final success/failure reaction.
+
+        Unlike Discord (additive reactions), Telegram's set_message_reaction
+        replaces all existing reactions in one call — no remove step needed.
+        """
+        if not self._reactions_enabled():
+            return
+        chat_id = getattr(event.source, "chat_id", None)
+        message_id = getattr(event, "message_id", None)
+        if chat_id and message_id and outcome != ProcessingOutcome.CANCELLED:
+            await self._set_reaction(
+                chat_id,
+                message_id,
+                "\u2705" if outcome == ProcessingOutcome.SUCCESS else "\u274c",
+            )
@@ -45,11 +45,9 @@ _SEED_FALLBACK_IPS: list[str] = ["149.154.167.220"]


 def _resolve_proxy_url() -> str | None:
-    for key in ("HTTPS_PROXY", "HTTP_PROXY", "ALL_PROXY", "https_proxy", "http_proxy", "all_proxy"):
-        value = (os.environ.get(key) or "").strip()
-        if value:
-            return value
-    return None
+    # Delegate to shared implementation (env vars + macOS system proxy detection)
+    from gateway.platforms.base import resolve_proxy_url
+    return resolve_proxy_url()


 class TelegramFallbackTransport(httpx.AsyncBaseTransport):
@@ -112,7 +110,8 @@ class TelegramFallbackTransport(httpx.AsyncBaseTransport):
                logger.warning("[Telegram] Fallback IP %s failed: %s", ip, exc)
                continue

-        assert last_error is not None
+        if last_error is None:
+            raise RuntimeError("All Telegram fallback IPs exhausted but no error was recorded")
        raise last_error

    async def aclose(self) -> None:
@@ -76,8 +76,17 @@ class WebhookAdapter(BasePlatformAdapter):
        self._routes: Dict[str, dict] = dict(self._static_routes)
        self._runner = None

-        # Delivery info keyed by session chat_id — consumed by send()
+        # Delivery info keyed by session chat_id.
+        #
+        # Read by every send() invocation for the chat_id (status messages
+        # AND the final response).  Cleaned up via TTL on each POST so the
+        # dict stays bounded — see _prune_delivery_info().  Do NOT pop on
+        # send(), or interim status messages (e.g. fallback notifications,
+        # context-pressure warnings) will consume the entry before the
+        # final response arrives, causing the response to silently fall
+        # back to the "log" deliver type.
        self._delivery_info: Dict[str, dict] = {}
+        self._delivery_info_created: Dict[str, float] = {}

        # Reference to gateway runner for cross-platform delivery (set externally)
        self.gateway_runner = None
@@ -160,10 +169,14 @@ class WebhookAdapter(BasePlatformAdapter):
    ) -> SendResult:
        """Deliver the agent's response to the configured destination.

-        chat_id is ``webhook:{route}:{delivery_id}`` — we pop the delivery
-        info stored during webhook receipt so it doesn't leak memory.
+        chat_id is ``webhook:{route}:{delivery_id}``.  The delivery info
+        stored during webhook receipt is read with ``.get()`` (not popped)
+        so that interim status messages emitted before the final response
+        — fallback-model notifications, context-pressure warnings, etc. —
+        do not consume the entry and silently downgrade the final response
+        to the ``log`` deliver type.  TTL cleanup happens on POST.
        """
-        delivery = self._delivery_info.pop(chat_id, {})
+        delivery = self._delivery_info.get(chat_id, {})
        deliver_type = delivery.get("deliver", "log")

        if deliver_type == "log":
@@ -173,13 +186,22 @@ class WebhookAdapter(BasePlatformAdapter):
        if deliver_type == "github_comment":
            return await self._deliver_github_comment(content, delivery)

-        # Cross-platform delivery (telegram, discord, etc.)
+        # Cross-platform delivery — any platform with a gateway adapter
        if self.gateway_runner and deliver_type in (
            "telegram",
            "discord",
            "slack",
            "signal",
            "sms",
+            "whatsapp",
+            "matrix",
+            "mattermost",
+            "homeassistant",
+            "email",
+            "dingtalk",
+            "feishu",
+            "wecom",
+            "bluebubbles",
        ):
            return await self._deliver_cross_platform(
                deliver_type, content, delivery
@@ -190,6 +212,23 @@ class WebhookAdapter(BasePlatformAdapter):
            success=False, error=f"Unknown deliver type: {deliver_type}"
        )

+    def _prune_delivery_info(self, now: float) -> None:
+        """Drop delivery_info entries older than the idempotency TTL.
+
+        Mirrors the cleanup pattern used for ``_seen_deliveries``.  Called
+        on each POST so the dict size is bounded by ``rate_limit * TTL``
+        even if many webhooks fire and never receive a final response.
+        """
+        cutoff = now - self._idempotency_ttl
+        stale = [
+            k
+            for k, t in self._delivery_info_created.items()
+            if t < cutoff
+        ]
+        for k in stale:
+            self._delivery_info.pop(k, None)
+            self._delivery_info_created.pop(k, None)
+
    async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
        return {"name": chat_id, "type": "webhook"}

@@ -232,7 +271,7 @@ class WebhookAdapter(BasePlatformAdapter):
                ", ".join(self._dynamic_routes.keys()) or "(none)",
            )
        except Exception as e:
-            logger.warning("[webhook] Failed to reload dynamic routes: %s", e)
+            logger.error("[webhook] Failed to reload dynamic routes: %s", e)

    async def _handle_webhook(self, request: "web.Request") -> "web.Response":
        """POST /webhooks/{route_name} — receive and process a webhook event."""
@@ -382,7 +421,9 @@ class WebhookAdapter(BasePlatformAdapter):
        # same route get independent agent runs (not queued/interrupted).
        session_chat_id = f"webhook:{route_name}:{delivery_id}"

-        # Store delivery info for send() — consumed (popped) on delivery
+        # Store delivery info for send().  Read by every send() invocation
+        # for this chat_id (interim status messages and the final response),
+        # so we do NOT pop on send.  TTL-based cleanup keeps the dict bounded.
        deliver_config = {
            "deliver": route_config.get("deliver", "log"),
            "deliver_extra": self._render_delivery_extra(
@@ -391,6 +432,8 @@ class WebhookAdapter(BasePlatformAdapter):
            "payload": payload,
        }
        self._delivery_info[session_chat_id] = deliver_config
+        self._delivery_info_created[session_chat_id] = now
+        self._prune_delivery_info(now)

        # Build source and event
        source = self.build_source(
@@ -143,6 +143,9 @@ class WeComAdapter(BasePlatformAdapter):
    """WeCom AI Bot adapter backed by a persistent WebSocket connection."""

    MAX_MESSAGE_LENGTH = MAX_MESSAGE_LENGTH
+    # Threshold for detecting WeCom client-side message splits.
+    # When a chunk is near the 4000-char limit, a continuation is almost certain.
+    _SPLIT_THRESHOLD = 3900

    def __init__(self, config: PlatformConfig):
        super().__init__(config, Platform.WECOM)
@@ -172,6 +175,13 @@ class WeComAdapter(BasePlatformAdapter):
        self._seen_messages: Dict[str, float] = {}
        self._reply_req_ids: Dict[str, str] = {}

+        # Text batching: merge rapid successive messages (Telegram-style).
+        # WeCom clients split long messages around 4000 chars.
+        self._text_batch_delay_seconds = float(os.getenv("HERMES_WECOM_TEXT_BATCH_DELAY_SECONDS", "0.6"))
+        self._text_batch_split_delay_seconds = float(os.getenv("HERMES_WECOM_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0"))
+        self._pending_text_batches: Dict[str, MessageEvent] = {}
+        self._pending_text_batch_tasks: Dict[str, asyncio.Task] = {}
+
    # ------------------------------------------------------------------
    # Connection lifecycle
    # ------------------------------------------------------------------
@@ -519,7 +529,82 @@ class WeComAdapter(BasePlatformAdapter):
            timestamp=datetime.now(tz=timezone.utc),
        )

-        await self.handle_message(event)
+        # Only batch plain text messages — commands, media, etc. dispatch
+        # immediately since they won't be split by the WeCom client.
+        if message_type == MessageType.TEXT and self._text_batch_delay_seconds > 0:
+            self._enqueue_text_event(event)
+        else:
+            await self.handle_message(event)
+
+    # ------------------------------------------------------------------
+    # Text message aggregation (handles WeCom client-side splits)
+    # ------------------------------------------------------------------
+
+    def _text_batch_key(self, event: MessageEvent) -> str:
+        """Session-scoped key for text message batching."""
+        from gateway.session import build_session_key
+        return build_session_key(
+            event.source,
+            group_sessions_per_user=self.config.extra.get("group_sessions_per_user", True),
+            thread_sessions_per_user=self.config.extra.get("thread_sessions_per_user", False),
+        )
+
+    def _enqueue_text_event(self, event: MessageEvent) -> None:
+        """Buffer a text event and reset the flush timer.
+
+        When WeCom splits a long user message at 4000 chars, the chunks
+        arrive within a few hundred milliseconds.  This merges them into
+        a single event before dispatching.
+        """
+        key = self._text_batch_key(event)
+        existing = self._pending_text_batches.get(key)
+        chunk_len = len(event.text or "")
+        if existing is None:
+            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
+            self._pending_text_batches[key] = event
+        else:
+            if event.text:
+                existing.text = f"{existing.text}\n{event.text}" if existing.text else event.text
+            existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
+            # Merge any media that might be attached
+            if event.media_urls:
+                existing.media_urls.extend(event.media_urls)
+                existing.media_types.extend(event.media_types)
+
+        # Cancel any pending flush and restart the timer
+        prior_task = self._pending_text_batch_tasks.get(key)
+        if prior_task and not prior_task.done():
+            prior_task.cancel()
+        self._pending_text_batch_tasks[key] = asyncio.create_task(
+            self._flush_text_batch(key)
+        )
+
+    async def _flush_text_batch(self, key: str) -> None:
+        """Wait for the quiet period then dispatch the aggregated text.
+
+        Uses a longer delay when the latest chunk is near WeCom's 4000-char
+        split point, since a continuation chunk is almost certain.
+        """
+        current_task = asyncio.current_task()
+        try:
+            pending = self._pending_text_batches.get(key)
+            last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
+            if last_len >= self._SPLIT_THRESHOLD:
+                delay = self._text_batch_split_delay_seconds
+            else:
+                delay = self._text_batch_delay_seconds
+            await asyncio.sleep(delay)
+            event = self._pending_text_batches.pop(key, None)
+            if not event:
+                return
+            logger.info(
+                "[WeCom] Flushing text batch %s (%d chars)",
+                key, len(event.text or ""),
+            )
+            await self.handle_message(event)
+        finally:
+            if self._pending_text_batch_tasks.get(key) is current_task:
+                self._pending_text_batch_tasks.pop(key, None)

    @staticmethod
    def _extract_text(body: Dict[str, Any]) -> Tuple[str, Optional[str]]:
@@ -611,7 +696,11 @@ class WeComAdapter(BasePlatformAdapter):

            if kind == "image":
                ext = self._detect_image_ext(raw)
-                return cache_image_from_bytes(raw, ext), self._mime_for_ext(ext, fallback="image/jpeg")
+                try:
+                    return cache_image_from_bytes(raw, ext), self._mime_for_ext(ext, fallback="image/jpeg")
+                except ValueError as exc:
+                    logger.warning("[%s] Rejected non-image bytes: %s", self.name, exc)
+                    return None

            filename = str(media.get("filename") or media.get("name") or "wecom_file")
            return cache_document_from_bytes(raw, filename), mimetypes.guess_type(filename)[0] or "application/octet-stream"
@@ -637,7 +726,11 @@ class WeComAdapter(BasePlatformAdapter):
        content_type = str(headers.get("content-type") or "").split(";", 1)[0].strip() or "application/octet-stream"
        if kind == "image":
            ext = self._guess_extension(url, content_type, fallback=self._detect_image_ext(raw))
-            return cache_image_from_bytes(raw, ext), content_type or self._mime_for_ext(ext, fallback="image/jpeg")
+            try:
+                return cache_image_from_bytes(raw, ext), content_type or self._mime_for_ext(ext, fallback="image/jpeg")
+            except ValueError as exc:
+                logger.warning("[%s] Rejected non-image bytes from %s: %s", self.name, url, exc)
+                return None

        filename = self._guess_filename(url, headers.get("content-disposition"), content_type)
        return cache_document_from_bytes(raw, filename), content_type
@@ -910,6 +1003,10 @@ class WeComAdapter(BasePlatformAdapter):
        url: str,
        max_bytes: int,
    ) -> Tuple[bytes, Dict[str, str]]:
+        from tools.url_safety import is_safe_url
+        if not is_safe_url(url):
+            raise ValueError(f"Blocked unsafe URL (SSRF protection): {url[:80]}")
+
        if not HTTPX_AVAILABLE:
            raise RuntimeError("httpx is required for WeCom media download")

@@ -184,6 +184,8 @@ if _config_path.exists():
            # Env var from .env takes precedence (already in os.environ).
            if "gateway_timeout" in _agent_cfg and "HERMES_AGENT_TIMEOUT" not in os.environ:
                os.environ["HERMES_AGENT_TIMEOUT"] = str(_agent_cfg["gateway_timeout"])
+            if "gateway_timeout_warning" in _agent_cfg and "HERMES_AGENT_TIMEOUT_WARNING" not in os.environ:
+                os.environ["HERMES_AGENT_TIMEOUT_WARNING"] = str(_agent_cfg["gateway_timeout_warning"])
        # Timezone: bridge config.yaml → HERMES_TIMEZONE env var.
        # HERMES_TIMEZONE from .env takes precedence (already in os.environ).
        _tz_cfg = _cfg.get("timezone", "")
@@ -512,12 +514,6 @@ class GatewayRunner:
        self._agent_cache: Dict[str, tuple] = {}
        self._agent_cache_lock = _threading.Lock()

-        # Track active fallback model/provider when primary is rate-limited.
-        # Set after an agent run where fallback was activated; cleared when
-        # the primary model succeeds again or the user switches via /model.
-        self._effective_model: Optional[str] = None
-        self._effective_provider: Optional[str] = None
-
        # Per-session model overrides from /model command.
        # Key: session_key, Value: dict with model/provider/api_key/base_url/api_mode
        self._session_model_overrides: Dict[str, Dict[str, str]] = {}
@@ -921,12 +917,11 @@ class GatewayRunner:

    @staticmethod
    def _load_reasoning_config() -> dict | None:
-        """Load reasoning effort from config with env fallback.
+        """Load reasoning effort from config.yaml.

-        Checks agent.reasoning_effort in config.yaml first, then
-        HERMES_REASONING_EFFORT as a fallback. Valid: "xhigh", "high",
-        "medium", "low", "minimal", "none". Returns None to use default
-        (medium).
+        Reads agent.reasoning_effort from config.yaml. Valid: "none",
+        "minimal", "low", "medium", "high", "xhigh". Returns None to use
+        default (medium).
        """
        from hermes_constants import parse_reasoning_effort
        effort = ""
@@ -939,8 +934,6 @@ class GatewayRunner:
                effort = str(cfg.get("agent", {}).get("reasoning_effort", "") or "").strip()
        except Exception:
            pass
-        if not effort:
-            effort = os.getenv("HERMES_REASONING_EFFORT", "")
        result = parse_reasoning_effort(effort)
        if effort and effort.strip() and result is None:
            logger.warning("Unknown reasoning_effort '%s', using default (medium)", effort)
@@ -1076,6 +1069,7 @@ class GatewayRunner:
                       "MATRIX_ALLOWED_USERS", "DINGTALK_ALLOWED_USERS",
                       "FEISHU_ALLOWED_USERS",
                       "WECOM_ALLOWED_USERS",
+                       "BLUEBUBBLES_ALLOWED_USERS",
                       "GATEWAY_ALLOWED_USERS")
        )
        _allow_all = os.getenv("GATEWAY_ALLOW_ALL_USERS", "").lower() in ("true", "1", "yes") or any(
@@ -1086,7 +1080,8 @@ class GatewayRunner:
                       "SMS_ALLOW_ALL_USERS", "MATTERMOST_ALLOW_ALL_USERS",
                       "MATRIX_ALLOW_ALL_USERS", "DINGTALK_ALLOW_ALL_USERS",
                       "FEISHU_ALLOW_ALL_USERS",
-                       "WECOM_ALLOW_ALL_USERS")
+                       "WECOM_ALLOW_ALL_USERS",
+                       "BLUEBUBBLES_ALLOW_ALL_USERS")
        )
        if not _any_allowlist and not _allow_all:
            logger.warning(
@@ -1484,6 +1479,14 @@ class GatewayRunner:
                logger.debug("Interrupted running agent for session %s during shutdown", session_key[:20])
            except Exception as e:
                logger.debug("Failed interrupting agent during shutdown: %s", e)
+            # Fire plugin on_session_finalize hook before memory shutdown
+            try:
+                from hermes_cli.plugins import invoke_hook as _invoke_hook
+                _invoke_hook("on_session_finalize",
+                             session_id=getattr(agent, 'session_id', None),
+                             platform="gateway")
+            except Exception:
+                pass
            # Shut down memory provider at actual session boundary
            try:
                if hasattr(agent, 'shutdown_memory_provider'):
@@ -1649,6 +1652,13 @@ class GatewayRunner:
            adapter.gateway_runner = self  # For cross-platform delivery
            return adapter

+        elif platform == Platform.BLUEBUBBLES:
+            from gateway.platforms.bluebubbles import BlueBubblesAdapter, check_bluebubbles_requirements
+            if not check_bluebubbles_requirements():
+                logger.warning("BlueBubbles: aiohttp/httpx missing or BLUEBUBBLES_SERVER_URL/BLUEBUBBLES_PASSWORD not configured")
+                return None
+            return BlueBubblesAdapter(config)
+
        return None
    
    def _is_user_authorized(self, source: SessionSource) -> bool:
@@ -1687,6 +1697,7 @@ class GatewayRunner:
            Platform.DINGTALK: "DINGTALK_ALLOWED_USERS",
            Platform.FEISHU: "FEISHU_ALLOWED_USERS",
            Platform.WECOM: "WECOM_ALLOWED_USERS",
+            Platform.BLUEBUBBLES: "BLUEBUBBLES_ALLOWED_USERS",
        }
        platform_allow_all_map = {
            Platform.TELEGRAM: "TELEGRAM_ALLOW_ALL_USERS",
@@ -1701,6 +1712,7 @@ class GatewayRunner:
            Platform.DINGTALK: "DINGTALK_ALLOW_ALL_USERS",
            Platform.FEISHU: "FEISHU_ALLOW_ALL_USERS",
            Platform.WECOM: "WECOM_ALLOW_ALL_USERS",
+            Platform.BLUEBUBBLES: "BLUEBUBBLES_ALLOW_ALL_USERS",
        }

        # Per-platform allow-all flag (e.g., DISCORD_ALLOW_ALL_USERS=true)
@@ -1774,8 +1786,11 @@ class GatewayRunner:
        """
        source = event.source

-        # Check if user is authorized
-        if not self._is_user_authorized(source):
+        # Internal events (e.g. background-process completion notifications)
+        # are system-generated and must skip user authorization.
+        if getattr(event, "internal", False):
+            pass
+        elif not self._is_user_authorized(source):
            logger.warning("Unauthorized user: %s (%s) on %s", source.user_id, source.user_name, source.platform.value)
            # In DMs: offer pairing code. In groups: silently ignore.
            if source.chat_type == "dm" and self._get_unauthorized_dm_behavior(source.platform) == "pair":
@@ -1976,6 +1991,11 @@ class GatewayRunner:
                    return await self._handle_approve_command(event)
                return await self._handle_deny_command(event)

+            # /background must bypass the running-agent guard — it starts a
+            # parallel task and must never interrupt the active conversation.
+            if _cmd_def_inner and _cmd_def_inner.name == "background":
+                return await self._handle_background_command(event)
+
            if event.message_type == MessageType.PHOTO:
                logger.debug("PRIORITY photo follow-up for session %s — queueing without interrupt", _quick_key[:20])
                adapter = self.adapters.get(source.platform)
@@ -1987,10 +2007,7 @@ class GatewayRunner:
                            existing.media_urls.extend(event.media_urls)
                            existing.media_types.extend(event.media_types)
                            if event.text:
-                                if not existing.text:
-                                    existing.text = event.text
-                                elif event.text not in existing.text:
-                                    existing.text = f"{existing.text}\n\n{event.text}".strip()
+                                existing.text = BasePlatformAdapter._merge_caption(existing.text, event.text)
                        else:
                            adapter._pending_messages[_quick_key] = event
                    else:
@@ -3280,6 +3297,15 @@ class GatewayRunner:
        # the configured default instead of the previously switched model.
        self._session_model_overrides.pop(session_key, None)

+        # Fire plugin on_session_finalize hook (session boundary)
+        try:
+            from hermes_cli.plugins import invoke_hook as _invoke_hook
+            _old_sid = old_entry.session_id if old_entry else None
+            _invoke_hook("on_session_finalize", session_id=_old_sid,
+                         platform=source.platform.value if source.platform else "")
+        except Exception:
+            pass
+
        # Emit session:end hook (session is ending)
        await self.hooks.emit("session:end", {
            "platform": source.platform.value if source.platform else "",
@@ -3293,7 +3319,7 @@ class GatewayRunner:
            "user_id": source.user_id,
            "session_key": session_key,
        })
-        
+
        # Resolve session config info to surface to the user
        try:
            session_info = self._format_session_info()
@@ -3304,9 +3330,18 @@ class GatewayRunner:
            header = "✨ Session reset! Starting fresh."
        else:
            # No existing session, just create one
-            self.session_store.get_or_create_session(source, force_new=True)
+            new_entry = self.session_store.get_or_create_session(source, force_new=True)
            header = "✨ New session started!"

+        # Fire plugin on_session_reset hook (new session guaranteed to exist)
+        try:
+            from hermes_cli.plugins import invoke_hook as _invoke_hook
+            _new_sid = new_entry.session_id if new_entry else None
+            _invoke_hook("on_session_reset", session_id=_new_sid,
+                         platform=source.platform.value if source.platform else "")
+        except Exception:
+            pass
+
        if session_info:
            return f"{header}\n\n{session_info}"
        return header
@@ -3345,25 +3380,36 @@ class GatewayRunner:
        """Handle /status command."""
        source = event.source
        session_entry = self.session_store.get_or_create_session(source)
-        
+
        connected_platforms = [p.value for p in self.adapters.keys()]
-        
+
        # Check if there's an active agent
        session_key = session_entry.session_key
        is_running = session_key in self._running_agents
-        
+
+        title = None
+        if self._session_db:
+            try:
+                title = self._session_db.get_session_title(session_entry.session_id)
+            except Exception:
+                title = None
+
        lines = [
            "📊 **Hermes Gateway Status**",
            "",
-            f"**Session ID:** `{session_entry.session_id[:12]}...`",
+            f"**Session ID:** `{session_entry.session_id}`",
+        ]
+        if title:
+            lines.append(f"**Title:** {title}")
+        lines.extend([
            f"**Created:** {session_entry.created_at.strftime('%Y-%m-%d %H:%M')}",
            f"**Last Activity:** {session_entry.updated_at.strftime('%Y-%m-%d %H:%M')}",
            f"**Tokens:** {session_entry.total_tokens:,}",
            f"**Agent Running:** {'Yes ⚡' if is_running else 'No'}",
            "",
            f"**Connected Platforms:** {', '.join(connected_platforms)}",
-        ]
-        
+        ])
+
        return "\n".join(lines)
    
    async def _handle_stop_command(self, event: MessageEvent) -> str:
@@ -3499,6 +3545,7 @@ class GatewayRunner:
        current_base_url = ""
        current_api_key = ""
        user_provs = None
+        custom_provs = None
        config_path = _hermes_home / "config.yaml"
        try:
            if config_path.exists():
@@ -3510,6 +3557,7 @@ class GatewayRunner:
                    current_provider = model_cfg.get("provider", current_provider)
                    current_base_url = model_cfg.get("base_url", "")
                user_provs = cfg.get("providers")
+                custom_provs = cfg.get("custom_providers")
        except Exception:
            pass

@@ -3537,6 +3585,7 @@ class GatewayRunner:
                    providers = list_authenticated_providers(
                        current_provider=current_provider,
                        user_providers=user_provs,
+                        custom_providers=custom_provs,
                        max_models=50,
                    )
                except Exception:
@@ -3564,6 +3613,8 @@ class GatewayRunner:
                            current_api_key=_cur_api_key,
                            is_global=False,
                            explicit_provider=provider_slug,
+                            user_providers=user_provs,
+                            custom_providers=custom_provs,
                        )
                        if not result.success:
                            return f"Error: {result.error_message}"
@@ -3642,6 +3693,7 @@ class GatewayRunner:
                providers = list_authenticated_providers(
                    current_provider=current_provider,
                    user_providers=user_provs,
+                    custom_providers=custom_provs,
                    max_models=5,
                )
                for p in providers:
@@ -3671,6 +3723,8 @@ class GatewayRunner:
            current_api_key=current_api_key,
            is_global=persist_global,
            explicit_provider=explicit_provider,
+            user_providers=user_provs,
+            custom_providers=custom_provs,
        )

        if not result.success:
@@ -4793,7 +4847,7 @@ class GatewayRunner:

        Usage:
            /reasoning              Show current effort level and display state
-            /reasoning <level>      Set reasoning effort (none, low, medium, high, xhigh)
+            /reasoning <level>      Set reasoning effort (none, minimal, low, medium, high, xhigh)
            /reasoning show|on      Show model reasoning in responses
            /reasoning hide|off     Hide model reasoning from responses
        """
@@ -4838,7 +4892,7 @@ class GatewayRunner:
                "🧠 **Reasoning Settings**\n\n"
                f"**Effort:** `{level}`\n"
                f"**Display:** {display_state}\n\n"
-                "_Usage:_ `/reasoning <none|low|medium|high|xhigh|show|hide>`"
+                "_Usage:_ `/reasoning <none|minimal|low|medium|high|xhigh|show|hide>`"
            )

        # Display toggle
@@ -4856,12 +4910,12 @@ class GatewayRunner:
        effort = args.strip()
        if effort == "none":
            parsed = {"enabled": False}
-        elif effort in ("xhigh", "high", "medium", "low", "minimal"):
+        elif effort in ("minimal", "low", "medium", "high", "xhigh"):
            parsed = {"enabled": True, "effort": effort}
        else:
            return (
                f"⚠️ Unknown argument: `{effort}`\n\n"
-                "**Valid levels:** none, low, minimal, medium, high, xhigh\n"
+                "**Valid levels:** none, minimal, low, medium, high, xhigh\n"
                "**Display:** show, hide"
            )

@@ -4872,14 +4926,21 @@ class GatewayRunner:
            return f"🧠 ✓ Reasoning effort set to `{effort}` (this session only)"

    async def _handle_yolo_command(self, event: MessageEvent) -> str:
-        """Handle /yolo — toggle dangerous command approval bypass."""
-        current = bool(os.environ.get("HERMES_YOLO_MODE"))
+        """Handle /yolo — toggle dangerous command approval bypass for this session only."""
+        from tools.approval import (
+            disable_session_yolo,
+            enable_session_yolo,
+            is_session_yolo_enabled,
+        )
+
+        session_key = self._session_key_for_source(event.source)
+        current = is_session_yolo_enabled(session_key)
        if current:
-            os.environ.pop("HERMES_YOLO_MODE", None)
-            return "⚠️ YOLO mode **OFF** — dangerous commands will require approval."
+            disable_session_yolo(session_key)
+            return "⚠️ YOLO mode **OFF** for this session — dangerous commands will require approval."
        else:
-            os.environ["HERMES_YOLO_MODE"] = "1"
-            return "⚡ YOLO mode **ON** — all commands auto-approved. Use with caution."
+            enable_session_yolo(session_key)
+            return "⚡ YOLO mode **ON** for this session — all commands auto-approved. Use with caution."

    async def _handle_verbose_command(self, event: MessageEvent) -> str:
        """Handle /verbose command — cycle tool progress display mode.
@@ -4913,8 +4974,8 @@ class GatewayRunner:
        cycle = ["off", "new", "all", "verbose"]
        descriptions = {
            "off": "⚙️ Tool progress: **OFF** — no tool activity shown.",
-            "new": "⚙️ Tool progress: **NEW** — shown when tool changes (short previews).",
-            "all": "⚙️ Tool progress: **ALL** — every tool call shown (short previews).",
+            "new": "⚙️ Tool progress: **NEW** — shown when tool changes (preview length: `display.tool_preview_length`, default 40).",
+            "all": "⚙️ Tool progress: **ALL** — every tool call shown (preview length: `display.tool_preview_length`, default 40).",
            "verbose": "⚙️ Tool progress: **VERBOSE** — every tool call with full arguments.",
        }

@@ -5227,28 +5288,86 @@ class GatewayRunner:
        )

    async def _handle_usage_command(self, event: MessageEvent) -> str:
-        """Handle /usage command -- show token usage for the session's last agent run."""
+        """Handle /usage command -- show token usage for the current session.
+
+        Checks both _running_agents (mid-turn) and _agent_cache (between turns)
+        so that rate limits, cost estimates, and detailed token breakdowns are
+        available whenever the user asks, not only while the agent is running.
+        """
        source = event.source
        session_key = self._session_key_for_source(source)

+        # Try running agent first (mid-turn), then cached agent (between turns)
        agent = self._running_agents.get(session_key)
+        if not agent or agent is _AGENT_PENDING_SENTINEL:
+            _cache_lock = getattr(self, "_agent_cache_lock", None)
+            _cache = getattr(self, "_agent_cache", None)
+            if _cache_lock and _cache is not None:
+                with _cache_lock:
+                    cached = _cache.get(session_key)
+                    if cached:
+                        agent = cached[0]
+
        if agent and hasattr(agent, "session_total_tokens") and agent.session_api_calls > 0:
-            lines = [
-                "📊 **Session Token Usage**",
-                f"Prompt (input): {agent.session_prompt_tokens:,}",
-                f"Completion (output): {agent.session_completion_tokens:,}",
-                f"Total: {agent.session_total_tokens:,}",
-                f"API calls: {agent.session_api_calls}",
-            ]
+            lines = []
+
+            # Rate limits (when available from provider headers)
+            rl_state = agent.get_rate_limit_state()
+            if rl_state and rl_state.has_data:
+                from agent.rate_limit_tracker import format_rate_limit_compact
+                lines.append(f"⏱️ **Rate Limits:** {format_rate_limit_compact(rl_state)}")
+                lines.append("")
+
+            # Session token usage — detailed breakdown matching CLI
+            input_tokens = getattr(agent, "session_input_tokens", 0) or 0
+            output_tokens = getattr(agent, "session_output_tokens", 0) or 0
+            cache_read = getattr(agent, "session_cache_read_tokens", 0) or 0
+            cache_write = getattr(agent, "session_cache_write_tokens", 0) or 0
+
+            lines.append("📊 **Session Token Usage**")
+            lines.append(f"Model: `{agent.model}`")
+            lines.append(f"Input tokens: {input_tokens:,}")
+            if cache_read:
+                lines.append(f"Cache read tokens: {cache_read:,}")
+            if cache_write:
+                lines.append(f"Cache write tokens: {cache_write:,}")
+            lines.append(f"Output tokens: {output_tokens:,}")
+            lines.append(f"Total: {agent.session_total_tokens:,}")
+            lines.append(f"API calls: {agent.session_api_calls}")
+
+            # Cost estimation
+            try:
+                from agent.usage_pricing import CanonicalUsage, estimate_usage_cost
+                cost_result = estimate_usage_cost(
+                    agent.model,
+                    CanonicalUsage(
+                        input_tokens=input_tokens,
+                        output_tokens=output_tokens,
+                        cache_read_tokens=cache_read,
+                        cache_write_tokens=cache_write,
+                    ),
+                    provider=getattr(agent, "provider", None),
+                    base_url=getattr(agent, "base_url", None),
+                )
+                if cost_result.amount_usd is not None:
+                    prefix = "~" if cost_result.status == "estimated" else ""
+                    lines.append(f"Cost: {prefix}${float(cost_result.amount_usd):.4f}")
+                elif cost_result.status == "included":
+                    lines.append("Cost: included")
+            except Exception:
+                pass
+
+            # Context window and compressions
            ctx = agent.context_compressor
            if ctx.last_prompt_tokens:
                pct = min(100, ctx.last_prompt_tokens / ctx.context_length * 100) if ctx.context_length else 0
                lines.append(f"Context: {ctx.last_prompt_tokens:,} / {ctx.context_length:,} ({pct:.0f}%)")
            if ctx.compression_count:
                lines.append(f"Compressions: {ctx.compression_count}")
+
            return "\n".join(lines)

-        # No running agent -- check session history for a rough count
+        # No agent at all -- check session history for a rough count
        session_entry = self.session_store.get_or_create_session(source)
        history = self.session_store.load_transcript(session_entry.session_id)
        if history:
@@ -5259,7 +5378,7 @@ class GatewayRunner:
                f"📊 **Session Info**\n"
                f"Messages: {len(msgs)}\n"
                f"Estimated context: ~{approx:,} tokens\n"
-                f"_(Detailed usage available during active conversations)_"
+                f"_(Detailed usage available after the first agent response)_"
            )
        return "No usage data available for this session."

@@ -5487,7 +5606,7 @@ class GatewayRunner:
        Platform.TELEGRAM, Platform.DISCORD, Platform.SLACK, Platform.WHATSAPP,
        Platform.SIGNAL, Platform.MATTERMOST, Platform.MATRIX,
        Platform.HOMEASSISTANT, Platform.EMAIL, Platform.SMS, Platform.DINGTALK,
-        Platform.FEISHU, Platform.WECOM, Platform.LOCAL,
+        Platform.FEISHU, Platform.WECOM, Platform.BLUEBUBBLES, Platform.LOCAL,
    })

    async def _handle_update_command(self, event: MessageEvent) -> str:
@@ -5986,16 +6105,14 @@ class GatewayRunner:
                return f"{disabled_note}\n\n{user_text}"
            return disabled_note

-        from tools.transcription_tools import transcribe_audio, get_stt_model_from_config
+        from tools.transcription_tools import transcribe_audio
        import asyncio

-        stt_model = get_stt_model_from_config()
-
        enriched_parts = []
        for path in audio_paths:
            try:
                logger.debug("Transcribing user voice: %s", path)
-                result = await asyncio.to_thread(transcribe_audio, path, model=stt_model)
+                result = await asyncio.to_thread(transcribe_audio, path)
                if result["success"]:
                    transcript = result["transcript"]
                    enriched_parts.append(
@@ -6036,6 +6153,11 @@ class GatewayRunner:

        if enriched_parts:
            prefix = "\n\n".join(enriched_parts)
+            # Strip the empty-content placeholder from the Discord adapter
+            # when we successfully transcribed the audio — it's redundant.
+            _placeholder = "(The user sent a message with no text content)"
+            if user_text and user_text.strip() == _placeholder:
+                return prefix
            if user_text:
                return f"{prefix}\n\n{user_text}"
            return prefix
@@ -6122,6 +6244,7 @@ class GatewayRunner:
                                text=synth_text,
                                message_type=MessageType.TEXT,
                                source=_source,
+                                internal=True,
                            )
                            logger.info(
                                "Process %s finished — injecting agent notification for session %s",
@@ -6221,6 +6344,32 @@ class GatewayRunner:
        )
        return hashlib.sha256(blob.encode()).hexdigest()[:16]

+    def _apply_session_model_override(
+        self, session_key: str, model: str, runtime_kwargs: dict
+    ) -> tuple:
+        """Apply /model session overrides if present, returning (model, runtime_kwargs).
+
+        The gateway /model command stores per-session overrides in
+        ``_session_model_overrides``.  These must take precedence over
+        config.yaml defaults so the switched model is actually used for
+        subsequent messages.  Fields with ``None`` values are skipped so
+        partial overrides don't clobber valid config defaults.
+        """
+        override = self._session_model_overrides.get(session_key)
+        if not override:
+            return model, runtime_kwargs
+        model = override.get("model", model)
+        for key in ("provider", "api_key", "base_url", "api_mode"):
+            val = override.get(key)
+            if val is not None:
+                runtime_kwargs[key] = val
+        return model, runtime_kwargs
+
+    def _is_intentional_model_switch(self, session_key: str, agent_model: str) -> bool:
+        """Return True if *agent_model* matches an active /model session override."""
+        override = self._session_model_overrides.get(session_key)
+        return override is not None and override.get("model") == agent_model
+
    def _evict_cached_agent(self, session_key: str) -> None:
        """Remove a cached agent for a session (called on /new, /model, etc)."""
        _lock = getattr(self, "_agent_cache_lock", None)
@@ -6272,7 +6421,15 @@ class GatewayRunner:
        # Falls back to env vars for backward compatibility.
        # YAML 1.1 parses bare `off` as boolean False — normalise before
        # the `or` chain so it doesn't silently fall through to "all".
-        _raw_tp = user_config.get("display", {}).get("tool_progress")
+        #
+        # Per-platform overrides (display.tool_progress_overrides) take
+        # priority over the global setting — e.g. Signal users can set
+        # tool_progress to "off" while keeping Telegram on "all".
+        _display_cfg = user_config.get("display", {})
+        _overrides = _display_cfg.get("tool_progress_overrides", {})
+        _raw_tp = _overrides.get(platform_key)
+        if _raw_tp is None:
+            _raw_tp = _display_cfg.get("tool_progress")
        if _raw_tp is False:
            _raw_tp = "off"
        progress_mode = (
@@ -6327,10 +6484,15 @@ class GatewayRunner:
                progress_queue.put(msg)
                return
            
-            # "all" / "new" modes: short preview, always truncated (40 chars)
+            # "all" / "new" modes: short preview, respects tool_preview_length
+            # config (defaults to 40 chars when unset to keep gateway messages
+            # compact — unlike CLI spinners, these persist as permanent messages).
            if preview:
-                if len(preview) > 40:
-                    preview = preview[:37] + "..."
+                from agent.display import get_tool_preview_max_len
+                _pl = get_tool_preview_max_len()
+                _cap = _pl if _pl > 0 else 40
+                if len(preview) > _cap:
+                    preview = preview[:_cap - 3] + "..."
                msg = f"{emoji} {tool_name}: \"{preview}\""
            else:
                msg = f"{emoji} {tool_name}..."
@@ -6371,6 +6533,18 @@ class GatewayRunner:
            if not adapter:
                return

+            # Skip tool progress for platforms that don't support message
+            # editing (e.g. iMessage/BlueBubbles) — each progress update
+            # would become a separate message bubble, which is noisy.
+            from gateway.platforms.base import BasePlatformAdapter as _BaseAdapter
+            if type(adapter).edit_message is _BaseAdapter.edit_message:
+                while not progress_queue.empty():
+                    try:
+                        progress_queue.get_nowait()
+                    except Exception:
+                        break
+                return
+
            progress_lines = []      # Accumulated tool lines
            progress_msg_id = None   # ID of the progress message to edit
            can_edit = True          # False once an edit fails (platform doesn't support it)
@@ -6573,6 +6747,11 @@ class GatewayRunner:
                    "tools": [],
                }

+            # /model overrides take precedence over config.yaml defaults.
+            model, runtime_kwargs = self._apply_session_model_override(
+                session_key, model, runtime_kwargs
+            )
+
            pr = self._provider_routing
            reasoning_config = self._load_reasoning_config()
            self._reasoning_config = reasoning_config
@@ -7065,6 +7244,9 @@ class GatewayRunner:
            # Default 1800s (30 min inactivity).  0 = unlimited.
            _agent_timeout_raw = float(os.getenv("HERMES_AGENT_TIMEOUT", 1800))
            _agent_timeout = _agent_timeout_raw if _agent_timeout_raw > 0 else None
+            _agent_warning_raw = float(os.getenv("HERMES_AGENT_TIMEOUT_WARNING", 900))
+            _agent_warning = _agent_warning_raw if _agent_warning_raw > 0 else None
+            _warning_fired = False
            loop = asyncio.get_event_loop()
            _executor_task = asyncio.ensure_future(
                loop.run_in_executor(None, run_sync)
@@ -7097,6 +7279,25 @@ class GatewayRunner:
                            _idle_secs = _act.get("seconds_since_activity", 0.0)
                        except Exception:
                            pass
+                    # Staged warning: fire once before escalating to full timeout.
+                    if (not _warning_fired and _agent_warning is not None
+                            and _idle_secs >= _agent_warning):
+                        _warning_fired = True
+                        _warn_adapter = self.adapters.get(source.platform)
+                        if _warn_adapter:
+                            _elapsed_warn = int(_agent_warning // 60) or 1
+                            _remaining_mins = int((_agent_timeout - _agent_warning) // 60) or 1
+                            try:
+                                await _warn_adapter.send(
+                                    source.chat_id,
+                                    f"⚠️ No activity for {_elapsed_warn} min. "
+                                    f"If the agent does not respond soon, it will "
+                                    f"be timed out in {_remaining_mins} min. "
+                                    f"You can continue waiting or use /reset.",
+                                    metadata=_status_thread_metadata,
+                                )
+                            except Exception as _warn_err:
+                                logger.debug("Inactivity warning send error: %s", _warn_err)
                    if _idle_secs >= _agent_timeout:
                        _inactivity_timeout = True
                        break
@@ -7170,16 +7371,10 @@ class GatewayRunner:
            _agent = agent_holder[0]
            if _agent is not None and hasattr(_agent, 'model'):
                _cfg_model = _resolve_gateway_model()
-                if _agent.model != _cfg_model:
-                    self._effective_model = _agent.model
-                    self._effective_provider = getattr(_agent, 'provider', None)
+                if _agent.model != _cfg_model and not self._is_intentional_model_switch(session_key, _agent.model):
                    # Fallback activated — evict cached agent so the next
                    # message starts fresh and retries the primary model.
                    self._evict_cached_agent(session_key)
-                else:
-                    # Primary model worked — clear any stale fallback state
-                    self._effective_model = None
-                    self._effective_provider = None

            # Check if we were interrupted OR have a queued message (/queue).
            result = result_holder[0]
@@ -7387,7 +7582,7 @@ async def start_gateway(config: Optional[GatewayConfig] = None, replace: bool =
    # setups (each profile using a distinct HERMES_HOME) will naturally
    # allow concurrent instances without tripping this guard.
    import time as _time
-    from gateway.status import get_running_pid, remove_pid_file
+    from gateway.status import get_running_pid, remove_pid_file, terminate_pid
    existing_pid = get_running_pid()
    if existing_pid is not None and existing_pid != os.getpid():
        if replace:
@@ -7396,10 +7591,10 @@ async def start_gateway(config: Optional[GatewayConfig] = None, replace: bool =
                existing_pid,
            )
            try:
-                os.kill(existing_pid, signal.SIGTERM)
+                terminate_pid(existing_pid, force=False)
            except ProcessLookupError:
                pass  # Already gone
-            except PermissionError:
+            except (PermissionError, OSError):
                logger.error(
                    "Permission denied killing PID %d. Cannot replace.",
                    existing_pid,
@@ -7419,9 +7614,9 @@ async def start_gateway(config: Optional[GatewayConfig] = None, replace: bool =
                    existing_pid,
                )
                try:
-                    os.kill(existing_pid, signal.SIGKILL)
+                    terminate_pid(existing_pid, force=True)
                    _time.sleep(0.5)
-                except (ProcessLookupError, PermissionError):
+                except (ProcessLookupError, PermissionError, OSError):
                    pass
            remove_pid_file()
            # Also release all scoped locks left by the old process.
@@ -32,9 +32,6 @@ def _now() -> datetime:
 # PII redaction helpers
 # ---------------------------------------------------------------------------

-_PHONE_RE = re.compile(r"^\+?\d[\d\-\s]{6,}$")
-
-
 def _hash_id(value: str) -> str:
    """Deterministic 12-char hex hash of an identifier."""
    return hashlib.sha256(value.encode("utf-8")).hexdigest()[:12]
@@ -58,10 +55,6 @@ def _hash_chat_id(value: str) -> str:
    return _hash_id(value)


-def _looks_like_phone(value: str) -> bool:
-    """Return True if *value* looks like a phone number (E.164 or similar)."""
-    return bool(_PHONE_RE.match(value.strip()))
-
 from .config import (
    Platform,
    GatewayConfig,
@@ -144,15 +137,6 @@ class SessionSource:
            chat_id_alt=data.get("chat_id_alt"),
        )
    
-    @classmethod
-    def local_cli(cls) -> "SessionSource":
-        """Create a source representing the local CLI."""
-        return cls(
-            platform=Platform.LOCAL,
-            chat_id="cli",
-            chat_name="CLI terminal",
-            chat_type="dm",
-        )


@dataclass
@@ -193,6 +177,7 @@ _PII_SAFE_PLATFORMS = frozenset({
    Platform.WHATSAPP,
    Platform.SIGNAL,
    Platform.TELEGRAM,
+    Platform.BLUEBUBBLES,
 })
 """Platforms where user IDs can be safely redacted (no in-message mention system
 that requires raw IDs).  Discord is excluded because mentions use ``<@user_id>``
@@ -509,8 +494,7 @@ class SessionStore:
    """
    
    def __init__(self, sessions_dir: Path, config: GatewayConfig,
-                 has_active_processes_fn=None,
-                 on_auto_reset=None):
+                 has_active_processes_fn=None):
        self.sessions_dir = sessions_dir
        self.config = config
        self._entries: Dict[str, SessionEntry] = {}
@@ -769,41 +753,6 @@ class SessionStore:
            except Exception as e:
                print(f"[gateway] Warning: Failed to create SQLite session: {e}")

-        # Seed new DM thread sessions with parent DM session history.
-        # When a bot reply creates a Slack thread and the user responds in it,
-        # the thread gets a new session (keyed by thread_ts).  Without seeding,
-        # the thread session starts with zero context — the user's original
-        # question and the bot's answer are invisible.  Fix: copy the parent
-        # DM session's transcript into the new thread session so context carries
-        # over while still keeping threads isolated from each other.
-        if (
-            source.chat_type == "dm"
-            and source.thread_id
-            and entry.created_at == entry.updated_at  # brand-new session
-            and not was_auto_reset
-        ):
-            parent_source = SessionSource(
-                platform=source.platform,
-                chat_id=source.chat_id,
-                chat_type="dm",
-                user_id=source.user_id,
-                # no thread_id — this is the parent DM session
-            )
-            parent_key = self._generate_session_key(parent_source)
-            with self._lock:
-                parent_entry = self._entries.get(parent_key)
-            if parent_entry and parent_entry.session_id != entry.session_id:
-                try:
-                    parent_history = self.load_transcript(parent_entry.session_id)
-                    if parent_history:
-                        self.rewrite_transcript(entry.session_id, parent_history)
-                        logger.info(
-                            "[Session] Seeded DM thread session %s with %d messages from parent %s",
-                            entry.session_id, len(parent_history), parent_entry.session_id,
-                        )
-                except Exception as e:
-                    logger.warning("[Session] Failed to seed thread session: %s", e)
-
        return entry

    def update_session(
@@ -14,6 +14,8 @@ concurrently under distinct configurations).
 import hashlib
 import json
 import os
+import signal
+import subprocess
 import sys
 from datetime import datetime, timezone
 from pathlib import Path
@@ -23,6 +25,7 @@ from typing import Any, Optional
 _GATEWAY_KIND = "hermes-gateway"
 _RUNTIME_STATUS_FILE = "gateway_state.json"
 _LOCKS_DIRNAME = "gateway-locks"
+_IS_WINDOWS = sys.platform == "win32"


 def _get_pid_path() -> Path:
@@ -49,6 +52,33 @@ def _utc_now_iso() -> str:
    return datetime.now(timezone.utc).isoformat()


+def terminate_pid(pid: int, *, force: bool = False) -> None:
+    """Terminate a PID with platform-appropriate force semantics.
+
+    POSIX uses SIGTERM/SIGKILL. Windows uses taskkill /T /F for true force-kill
+    because os.kill(..., SIGTERM) is not equivalent to a tree-killing hard stop.
+    """
+    if force and _IS_WINDOWS:
+        try:
+            result = subprocess.run(
+                ["taskkill", "/PID", str(pid), "/T", "/F"],
+                capture_output=True,
+                text=True,
+                timeout=10,
+            )
+        except FileNotFoundError:
+            os.kill(pid, signal.SIGTERM)
+            return
+
+        if result.returncode != 0:
+            details = (result.stderr or result.stdout or "").strip()
+            raise OSError(details or f"taskkill failed for PID {pid}")
+        return
+
+    sig = signal.SIGTERM if not force else getattr(signal, "SIGKILL", signal.SIGTERM)
+    os.kill(pid, sig)
+
+
 def _scope_hash(identity: str) -> str:
    return hashlib.sha256(identity.encode("utf-8")).hexdigest()[:16]

@@ -74,6 +74,8 @@ class GatewayStreamConsumer:
        self._edit_supported = True  # Disabled on first edit failure (Signal/Email/HA)
        self._last_edit_time = 0.0
        self._last_sent_text = ""   # Track last-sent text to skip redundant edits
+        self._fallback_final_send = False
+        self._fallback_prefix = ""

    @property
    def already_sent(self) -> bool:
@@ -134,16 +136,50 @@ class GatewayStreamConsumer:

                if should_edit and self._accumulated:
                    # Split overflow: if accumulated text exceeds the platform
-                    # limit, finalize the current message and start a new one.
+                    # limit, split into properly sized chunks.
+                    if (
+                        len(self._accumulated) > _safe_limit
+                        and self._message_id is None
+                    ):
+                        # No existing message to edit (first message or after a
+                        # segment break).  Use truncate_message — the same
+                        # helper the non-streaming path uses — to split with
+                        # proper word/code-fence boundaries and chunk
+                        # indicators like "(1/2)".
+                        chunks = self.adapter.truncate_message(
+                            self._accumulated, _safe_limit
+                        )
+                        for chunk in chunks:
+                            await self._send_new_chunk(chunk, self._message_id)
+                        self._accumulated = ""
+                        self._last_sent_text = ""
+                        self._last_edit_time = time.monotonic()
+                        if got_done:
+                            return
+                        if got_segment_break:
+                            self._message_id = None
+                            self._fallback_final_send = False
+                            self._fallback_prefix = ""
+                        continue
+
+                    # Existing message: edit it with the first chunk, then
+                    # start a new message for the overflow remainder.
                    while (
                        len(self._accumulated) > _safe_limit
                        and self._message_id is not None
+                        and self._edit_supported
                    ):
                        split_at = self._accumulated.rfind("\n", 0, _safe_limit)
                        if split_at < _safe_limit // 2:
                            split_at = _safe_limit
                        chunk = self._accumulated[:split_at]
                        await self._send_or_edit(chunk)
+                        if self._fallback_final_send:
+                            # Edit failed while attempting to split an oversized
+                            # message. Keep the full accumulated text intact so
+                            # the fallback final-send path can deliver the
+                            # remaining continuation without dropping content.
+                            break
                        self._accumulated = self._accumulated[split_at:].lstrip("\n")
                        self._message_id = None
                        self._last_sent_text = ""
@@ -156,19 +192,38 @@ class GatewayStreamConsumer:
                    self._last_edit_time = time.monotonic()

                if got_done:
-                    # Final edit without cursor
-                    if self._accumulated and self._message_id:
-                        await self._send_or_edit(self._accumulated)
+                    # Final edit without cursor. If progressive editing failed
+                    # mid-stream, send a single continuation/fallback message
+                    # here instead of letting the base gateway path send the
+                    # full response again.
+                    if self._accumulated:
+                        if self._fallback_final_send:
+                            await self._send_fallback_final(self._accumulated)
+                        elif self._message_id:
+                            await self._send_or_edit(self._accumulated)
+                        elif not self._already_sent:
+                            await self._send_or_edit(self._accumulated)
                    return

-                # Tool boundary: the should_edit block above already flushed
-                # accumulated text without a cursor.  Reset state so the next
-                # text chunk creates a fresh message below any tool-progress
-                # messages the gateway sent in between.
-                if got_segment_break:
+                # Tool boundary: reset message state so the next text chunk
+                # creates a fresh message below any tool-progress messages.
+                #
+                # Exception: when _message_id is "__no_edit__" the platform
+                # never returned a real message ID (e.g. Signal, webhook with
+                # github_comment delivery).  Resetting to None would re-enter
+                # the "first send" path on every tool boundary and post one
+                # platform message per tool call — that is what caused 155
+                # comments under a single PR.  Instead, keep all state so the
+                # full continuation is delivered once via _send_fallback_final.
+                # (When editing fails mid-stream due to flood control the id is
+                # a real string like "msg_1", not "__no_edit__", so that case
+                # still resets and creates a fresh segment as intended.)
+                if got_segment_break and self._message_id != "__no_edit__":
                    self._message_id = None
                    self._accumulated = ""
                    self._last_sent_text = ""
+                    self._fallback_final_send = False
+                    self._fallback_prefix = ""

                await asyncio.sleep(0.05)  # Small yield to not busy-loop

@@ -207,6 +262,114 @@ class GatewayStreamConsumer:
        # Strip trailing whitespace/newlines but preserve leading content
        return cleaned.rstrip()

+    async def _send_new_chunk(self, text: str, reply_to_id: Optional[str]) -> Optional[str]:
+        """Send a new message chunk, optionally threaded to a previous message.
+
+        Returns the message_id so callers can thread subsequent chunks.
+        """
+        text = self._clean_for_display(text)
+        if not text.strip():
+            return reply_to_id
+        try:
+            meta = dict(self.metadata) if self.metadata else {}
+            result = await self.adapter.send(
+                chat_id=self.chat_id,
+                content=text,
+                reply_to=reply_to_id,
+                metadata=meta,
+            )
+            if result.success and result.message_id:
+                self._message_id = str(result.message_id)
+                self._already_sent = True
+                self._last_sent_text = text
+                return str(result.message_id)
+            else:
+                self._edit_supported = False
+                return reply_to_id
+        except Exception as e:
+            logger.error("Stream send chunk error: %s", e)
+            return reply_to_id
+
+    def _visible_prefix(self) -> str:
+        """Return the visible text already shown in the streamed message."""
+        prefix = self._last_sent_text or ""
+        if self.cfg.cursor and prefix.endswith(self.cfg.cursor):
+            prefix = prefix[:-len(self.cfg.cursor)]
+        return self._clean_for_display(prefix)
+
+    def _continuation_text(self, final_text: str) -> str:
+        """Return only the part of final_text the user has not already seen."""
+        prefix = self._fallback_prefix or self._visible_prefix()
+        if prefix and final_text.startswith(prefix):
+            return final_text[len(prefix):].lstrip()
+        return final_text
+
+    @staticmethod
+    def _split_text_chunks(text: str, limit: int) -> list[str]:
+        """Split text into reasonably sized chunks for fallback sends."""
+        if len(text) <= limit:
+            return [text]
+        chunks: list[str] = []
+        remaining = text
+        while len(remaining) > limit:
+            split_at = remaining.rfind("\n", 0, limit)
+            if split_at < limit // 2:
+                split_at = limit
+            chunks.append(remaining[:split_at])
+            remaining = remaining[split_at:].lstrip("\n")
+        if remaining:
+            chunks.append(remaining)
+        return chunks
+
+    async def _send_fallback_final(self, text: str) -> None:
+        """Send the final continuation after streaming edits stop working."""
+        final_text = self._clean_for_display(text)
+        continuation = self._continuation_text(final_text)
+        self._fallback_final_send = False
+        if not continuation.strip():
+            # Nothing new to send — the visible partial already matches final text.
+            self._already_sent = True
+            return
+
+        raw_limit = getattr(self.adapter, "MAX_MESSAGE_LENGTH", 4096)
+        safe_limit = max(500, raw_limit - 100)
+        chunks = self._split_text_chunks(continuation, safe_limit)
+
+        last_message_id: Optional[str] = None
+        last_successful_chunk = ""
+        sent_any_chunk = False
+        for chunk in chunks:
+            result = await self.adapter.send(
+                chat_id=self.chat_id,
+                content=chunk,
+                metadata=self.metadata,
+            )
+            if not result.success:
+                if sent_any_chunk:
+                    # Some continuation text already reached the user. Suppress
+                    # the base gateway final-send path so we don't resend the
+                    # full response and create another duplicate.
+                    self._already_sent = True
+                    self._message_id = last_message_id
+                    self._last_sent_text = last_successful_chunk
+                    self._fallback_prefix = ""
+                    return
+                # No fallback chunk reached the user — allow the normal gateway
+                # final-send path to try one more time.
+                self._already_sent = False
+                self._message_id = None
+                self._last_sent_text = ""
+                self._fallback_prefix = ""
+                return
+            sent_any_chunk = True
+            last_successful_chunk = chunk
+            last_message_id = result.message_id or last_message_id
+
+        self._message_id = last_message_id
+        self._already_sent = True
+        self._last_sent_text = chunks[-1]
+        self._fallback_prefix = ""
+
    async def _send_or_edit(self, text: str) -> None:
        """Send or edit the streaming message."""
        # Strip MEDIA: directives so they don't appear as visible text.
@@ -232,14 +395,16 @@ class GatewayStreamConsumer:
                        self._last_sent_text = text
                    else:
                        # If an edit fails mid-stream (especially Telegram flood control),
-                        # stop progressive edits and let the normal final send path deliver
-                        # the complete answer instead of leaving the user with a partial.
+                        # stop progressive edits and send only the missing tail once the
+                        # final response is available.
                        logger.debug("Edit failed, disabling streaming for this adapter")
+                        self._fallback_prefix = self._visible_prefix()
+                        self._fallback_final_send = True
                        self._edit_supported = False
-                        self._already_sent = False
+                        self._already_sent = True
                else:
                    # Editing not supported — skip intermediate updates.
-                    # The final response will be sent by the normal path.
+                    # The final response will be sent by the fallback path.
                    pass
            else:
                # First message — send new
@@ -252,6 +417,17 @@ class GatewayStreamConsumer:
                    self._message_id = result.message_id
                    self._already_sent = True
                    self._last_sent_text = text
+                elif result.success:
+                    # Platform accepted the message but returned no message_id
+                    # (e.g. Signal).  Can't edit without an ID — switch to
+                    # fallback mode: suppress intermediate deltas, send only
+                    # the missing tail once the final response is ready.
+                    self._already_sent = True
+                    self._edit_supported = False
+                    self._fallback_prefix = self._clean_for_display(text)
+                    self._fallback_final_send = True
+                    # Sentinel prevents re-entering this branch on every delta
+                    self._message_id = "__no_edit__"
                else:
                    # Initial send failed — disable streaming for this session
                    self._edit_supported = False
@@ -11,5 +11,5 @@ Provides subcommands for:
 - hermes cron          - Manage cron jobs
 """

-__version__ = "0.7.0"
-__release_date__ = "2026.4.3"
+__version__ = "0.8.0"
+__release_date__ = "2026.4.8"
@@ -37,7 +37,7 @@ from typing import Any, Dict, List, Optional
 import httpx
 import yaml

-from hermes_cli.config import get_hermes_home, get_config_path
+from hermes_cli.config import get_hermes_home, get_config_path, read_raw_config
 from hermes_constants import OPENROUTER_BASE_URL

 logger = logging.getLogger(__name__)
@@ -67,12 +67,15 @@ DEFAULT_AGENT_KEY_MIN_TTL_SECONDS = 30 * 60  # 30 minutes
 ACCESS_TOKEN_REFRESH_SKEW_SECONDS = 120       # refresh 2 min before expiry
 DEVICE_AUTH_POLL_INTERVAL_CAP_SECONDS = 1     # poll at most every 1s
 DEFAULT_CODEX_BASE_URL = "https://chatgpt.com/backend-api/codex"
+DEFAULT_QWEN_BASE_URL = "https://portal.qwen.ai/v1"
 DEFAULT_GITHUB_MODELS_BASE_URL = "https://api.githubcopilot.com"
 DEFAULT_COPILOT_ACP_BASE_URL = "acp://copilot"
-DEFAULT_GEMINI_BASE_URL = "https://generativelanguage.googleapis.com/v1beta/openai"
 CODEX_OAUTH_CLIENT_ID = "app_EMoamEEZ73f0CkXaXp7hrann"
 CODEX_OAUTH_TOKEN_URL = "https://auth.openai.com/oauth/token"
 CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS = 120
+QWEN_OAUTH_CLIENT_ID = "f0304373b74a44d2b584a3fb70ca9e56"
+QWEN_OAUTH_TOKEN_URL = "https://chat.qwen.ai/api/v1/oauth2/token"
+QWEN_ACCESS_TOKEN_REFRESH_SKEW_SECONDS = 120


 # =============================================================================
@@ -112,6 +115,12 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
        auth_type="oauth_external",
        inference_base_url=DEFAULT_CODEX_BASE_URL,
    ),
+    "qwen-oauth": ProviderConfig(
+        id="qwen-oauth",
+        name="Qwen OAuth",
+        auth_type="oauth_external",
+        inference_base_url=DEFAULT_QWEN_BASE_URL,
+    ),
    "copilot": ProviderConfig(
        id="copilot",
        name="GitHub Copilot",
@@ -240,7 +249,7 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
 # Kimi Code Endpoint Detection
 # =============================================================================

-# Kimi Code (platform.kimi.ai) issues keys prefixed "sk-kimi-" that only work
+# Kimi Code (kimi.com/code) issues keys prefixed "sk-kimi-" that only work
 # on api.kimi.com/coding/v1.  Legacy keys from platform.moonshot.ai work on
 # api.moonshot.ai/v1 (the default).  Auto-detect when user hasn't set
 # KIMI_BASE_URL explicitly.
@@ -695,6 +704,27 @@ def write_credential_pool(provider_id: str, entries: List[Dict[str, Any]]) -> Pa
        return _save_auth_store(auth_store)


+def suppress_credential_source(provider_id: str, source: str) -> None:
+    """Mark a credential source as suppressed so it won't be re-seeded."""
+    with _auth_store_lock():
+        auth_store = _load_auth_store()
+        suppressed = auth_store.setdefault("suppressed_sources", {})
+        provider_list = suppressed.setdefault(provider_id, [])
+        if source not in provider_list:
+            provider_list.append(source)
+        _save_auth_store(auth_store)
+
+
+def is_source_suppressed(provider_id: str, source: str) -> bool:
+    """Check if a credential source has been suppressed by the user."""
+    try:
+        auth_store = _load_auth_store()
+        suppressed = auth_store.get("suppressed_sources", {})
+        return source in suppressed.get(provider_id, [])
+    except Exception:
+        return False
+
+
 def get_provider_auth_state(provider_id: str) -> Optional[Dict[str, Any]]:
    """Return persisted auth state for a provider, or None."""
    auth_store = _load_auth_store()
@@ -707,6 +737,57 @@ def get_active_provider() -> Optional[str]:
    return auth_store.get("active_provider")


+def is_provider_explicitly_configured(provider_id: str) -> bool:
+    """Return True only if the user has explicitly configured this provider.
+
+    Checks:
+      1. active_provider in auth.json matches
+      2. model.provider in config.yaml matches
+      3. Provider-specific env vars are set (e.g. ANTHROPIC_API_KEY)
+
+    This is used to gate auto-discovery of external credentials (e.g.
+    Claude Code's ~/.claude/.credentials.json) so they are never used
+    without the user's explicit choice.  See PR #4210 for the same
+    pattern applied to the setup wizard gate.
+    """
+    normalized = (provider_id or "").strip().lower()
+
+    # 1. Check auth.json active_provider
+    try:
+        auth_store = _load_auth_store()
+        active = (auth_store.get("active_provider") or "").strip().lower()
+        if active and active == normalized:
+            return True
+    except Exception:
+        pass
+
+    # 2. Check config.yaml model.provider
+    try:
+        from hermes_cli.config import load_config
+        cfg = load_config()
+        model_cfg = cfg.get("model")
+        if isinstance(model_cfg, dict):
+            cfg_provider = (model_cfg.get("provider") or "").strip().lower()
+            if cfg_provider == normalized:
+                return True
+    except Exception:
+        pass
+
+    # 3. Check provider-specific env vars
+    # Exclude CLAUDE_CODE_OAUTH_TOKEN — it's set by Claude Code itself,
+    # not by the user explicitly configuring anthropic in Hermes.
+    _IMPLICIT_ENV_VARS = {"CLAUDE_CODE_OAUTH_TOKEN"}
+    pconfig = PROVIDER_REGISTRY.get(normalized)
+    if pconfig and pconfig.auth_type == "api_key":
+        for env_var in pconfig.api_key_env_vars:
+            if env_var in _IMPLICIT_ENV_VARS:
+                continue
+            if has_usable_secret(os.getenv(env_var, "")):
+                return True
+
+    return False
+
+
 def clear_provider_auth(provider_id: Optional[str] = None) -> bool:
    """
    Clear auth state for a provider. Used by `hermes logout`.
@@ -817,6 +898,7 @@ def resolve_provider(
        "github-copilot-acp": "copilot-acp", "copilot-acp-agent": "copilot-acp",
        "aigateway": "ai-gateway", "vercel": "ai-gateway", "vercel-ai-gateway": "ai-gateway",
        "opencode": "opencode-zen", "zen": "opencode-zen",
+        "qwen-portal": "qwen-oauth", "qwen-cli": "qwen-oauth", "qwen-oauth": "qwen-oauth",
        "hf": "huggingface", "hugging-face": "huggingface", "huggingface-hub": "huggingface",
        "go": "opencode-go", "opencode-go-sub": "opencode-go",
        "kilo": "kilocode", "kilo-code": "kilocode", "kilo-gateway": "kilocode",
@@ -946,6 +1028,176 @@ def _codex_access_token_is_expiring(access_token: Any, skew_seconds: int) -> boo
    return float(exp) <= (time.time() + max(0, int(skew_seconds)))


+def _qwen_cli_auth_path() -> Path:
+    return Path.home() / ".qwen" / "oauth_creds.json"
+
+
+def _read_qwen_cli_tokens() -> Dict[str, Any]:
+    auth_path = _qwen_cli_auth_path()
+    if not auth_path.exists():
+        raise AuthError(
+            "Qwen CLI credentials not found. Run 'qwen auth qwen-oauth' first.",
+            provider="qwen-oauth",
+            code="qwen_auth_missing",
+        )
+    try:
+        data = json.loads(auth_path.read_text(encoding="utf-8"))
+    except Exception as exc:
+        raise AuthError(
+            f"Failed to read Qwen CLI credentials from {auth_path}: {exc}",
+            provider="qwen-oauth",
+            code="qwen_auth_read_failed",
+        ) from exc
+    if not isinstance(data, dict):
+        raise AuthError(
+            f"Invalid Qwen CLI credentials in {auth_path}.",
+            provider="qwen-oauth",
+            code="qwen_auth_invalid",
+        )
+    return data
+
+
+def _save_qwen_cli_tokens(tokens: Dict[str, Any]) -> Path:
+    auth_path = _qwen_cli_auth_path()
+    auth_path.parent.mkdir(parents=True, exist_ok=True)
+    tmp_path = auth_path.with_suffix(".tmp")
+    tmp_path.write_text(json.dumps(tokens, indent=2, sort_keys=True) + "\n", encoding="utf-8")
+    os.chmod(tmp_path, stat.S_IRUSR | stat.S_IWUSR)
+    tmp_path.replace(auth_path)
+    return auth_path
+
+
+def _qwen_access_token_is_expiring(expiry_date_ms: Any, skew_seconds: int = QWEN_ACCESS_TOKEN_REFRESH_SKEW_SECONDS) -> bool:
+    try:
+        expiry_ms = int(expiry_date_ms)
+    except Exception:
+        return True
+    return (time.time() + max(0, int(skew_seconds))) * 1000 >= expiry_ms
+
+
+def _refresh_qwen_cli_tokens(tokens: Dict[str, Any], timeout_seconds: float = 20.0) -> Dict[str, Any]:
+    refresh_token = str(tokens.get("refresh_token", "") or "").strip()
+    if not refresh_token:
+        raise AuthError(
+            "Qwen OAuth refresh token missing. Re-run 'qwen auth qwen-oauth'.",
+            provider="qwen-oauth",
+            code="qwen_refresh_token_missing",
+        )
+
+    try:
+        response = httpx.post(
+            QWEN_OAUTH_TOKEN_URL,
+            headers={
+                "Content-Type": "application/x-www-form-urlencoded",
+                "Accept": "application/json",
+            },
+            data={
+                "grant_type": "refresh_token",
+                "refresh_token": refresh_token,
+                "client_id": QWEN_OAUTH_CLIENT_ID,
+            },
+            timeout=timeout_seconds,
+        )
+    except Exception as exc:
+        raise AuthError(
+            f"Qwen OAuth refresh failed: {exc}",
+            provider="qwen-oauth",
+            code="qwen_refresh_failed",
+        ) from exc
+
+    if response.status_code >= 400:
+        body = response.text.strip()
+        raise AuthError(
+            "Qwen OAuth refresh failed. Re-run 'qwen auth qwen-oauth'."
+            + (f" Response: {body}" if body else ""),
+            provider="qwen-oauth",
+            code="qwen_refresh_failed",
+        )
+
+    try:
+        payload = response.json()
+    except Exception as exc:
+        raise AuthError(
+            f"Qwen OAuth refresh returned invalid JSON: {exc}",
+            provider="qwen-oauth",
+            code="qwen_refresh_invalid_json",
+        ) from exc
+
+    if not isinstance(payload, dict) or not str(payload.get("access_token", "") or "").strip():
+        raise AuthError(
+            "Qwen OAuth refresh response missing access_token.",
+            provider="qwen-oauth",
+            code="qwen_refresh_invalid_response",
+        )
+
+    expires_in = payload.get("expires_in")
+    try:
+        expires_in_seconds = int(expires_in)
+    except Exception:
+        expires_in_seconds = 6 * 60 * 60
+
+    refreshed = {
+        "access_token": str(payload.get("access_token", "") or "").strip(),
+        "refresh_token": str(payload.get("refresh_token", refresh_token) or refresh_token).strip(),
+        "token_type": str(payload.get("token_type", tokens.get("token_type", "Bearer")) or "Bearer").strip() or "Bearer",
+        "resource_url": str(payload.get("resource_url", tokens.get("resource_url", "portal.qwen.ai")) or "portal.qwen.ai").strip(),
+        "expiry_date": int(time.time() * 1000) + max(1, expires_in_seconds) * 1000,
+    }
+    _save_qwen_cli_tokens(refreshed)
+    return refreshed
+
+
+def resolve_qwen_runtime_credentials(
+    *,
+    force_refresh: bool = False,
+    refresh_if_expiring: bool = True,
+    refresh_skew_seconds: int = QWEN_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
+) -> Dict[str, Any]:
+    tokens = _read_qwen_cli_tokens()
+    access_token = str(tokens.get("access_token", "") or "").strip()
+    should_refresh = bool(force_refresh)
+    if not should_refresh and refresh_if_expiring:
+        should_refresh = _qwen_access_token_is_expiring(tokens.get("expiry_date"), refresh_skew_seconds)
+    if should_refresh:
+        tokens = _refresh_qwen_cli_tokens(tokens)
+        access_token = str(tokens.get("access_token", "") or "").strip()
+    if not access_token:
+        raise AuthError(
+            "Qwen OAuth access token missing. Re-run 'qwen auth qwen-oauth'.",
+            provider="qwen-oauth",
+            code="qwen_access_token_missing",
+        )
+
+    base_url = os.getenv("HERMES_QWEN_BASE_URL", "").strip().rstrip("/") or DEFAULT_QWEN_BASE_URL
+    return {
+        "provider": "qwen-oauth",
+        "base_url": base_url,
+        "api_key": access_token,
+        "source": "qwen-cli",
+        "expires_at_ms": tokens.get("expiry_date"),
+        "auth_file": str(_qwen_cli_auth_path()),
+    }
+
+
+def get_qwen_auth_status() -> Dict[str, Any]:
+    auth_path = _qwen_cli_auth_path()
+    try:
+        creds = resolve_qwen_runtime_credentials(refresh_if_expiring=False)
+        return {
+            "logged_in": True,
+            "auth_file": str(auth_path),
+            "source": creds.get("source"),
+            "api_key": creds.get("api_key"),
+            "expires_at_ms": creds.get("expires_at_ms"),
+        }
+    except AuthError as exc:
+        return {
+            "logged_in": False,
+            "auth_file": str(auth_path),
+            "error": str(exc),
+        }
+
+
 # =============================================================================
 # SSH / remote session detection
 # =============================================================================
@@ -2072,6 +2324,8 @@ def get_auth_status(provider_id: Optional[str] = None) -> Dict[str, Any]:
        return get_nous_auth_status()
    if target == "openai-codex":
        return get_codex_auth_status()
+    if target == "qwen-oauth":
+        return get_qwen_auth_status()
    if target == "copilot-acp":
        return get_external_process_provider_status(target)
    # API-key providers
@@ -2159,33 +2413,6 @@ def resolve_external_process_provider_credentials(provider_id: str) -> Dict[str,
    }


-# =============================================================================
-# External credential detection
-# =============================================================================
-
-def detect_external_credentials() -> List[Dict[str, Any]]:
-    """Scan for credentials from other CLI tools that Hermes can reuse.
-
-    Returns a list of dicts, each with:
-      - provider: str   -- Hermes provider id (e.g. "openai-codex")
-      - path: str       -- filesystem path where creds were found
-      - label: str      -- human-friendly description for the setup UI
-    """
-    found: List[Dict[str, Any]] = []
-
-    # Codex CLI: ~/.codex/auth.json (importable, not shared)
-    cli_tokens = _import_codex_cli_tokens()
-    if cli_tokens:
-        codex_path = Path.home() / ".codex" / "auth.json"
-        found.append({
-            "provider": "openai-codex",
-            "path": str(codex_path),
-            "label": f"Codex CLI credentials found ({codex_path}) — run `hermes auth` to create a separate session",
-        })
-
-    return found
-
-
 # =============================================================================
 # CLI Commands — login / logout
 # =============================================================================
@@ -2214,14 +2441,7 @@ def _update_config_for_provider(
    config_path = get_config_path()
    config_path.parent.mkdir(parents=True, exist_ok=True)

-    config: Dict[str, Any] = {}
-    if config_path.exists():
-        try:
-            loaded = yaml.safe_load(config_path.read_text()) or {}
-            if isinstance(loaded, dict):
-                config = loaded
-        except Exception:
-            config = {}
+    config = read_raw_config()

    current_model = config.get("model")
    if isinstance(current_model, dict):
@@ -2258,12 +2478,8 @@ def _reset_config_provider() -> Path:
    if not config_path.exists():
        return config_path

-    try:
-        config = yaml.safe_load(config_path.read_text()) or {}
-    except Exception:
-        return config_path
-
-    if not isinstance(config, dict):
+    config = read_raw_config()
+    if not config:
        return config_path

    model = config.get("model")
@@ -2409,7 +2625,7 @@ def _prompt_model_selection(
            custom = input("Enter model name: ").strip()
            return custom if custom else None
        return None
-    except (ImportError, NotImplementedError):
+    except (ImportError, NotImplementedError, OSError, subprocess.SubprocessError):
        pass

    # Fallback: numbered list
@@ -2845,12 +3061,15 @@ def _login_nous(args, pconfig: ProviderConfig) -> None:
            _save_provider_state(auth_store, "nous", auth_state)
            saved_to = _save_auth_store(auth_store)

-        config_path = _update_config_for_provider("nous", inference_base_url)
        print()
        print("Login successful!")
        print(f"  Auth state: {saved_to}")
-        print(f"  Config updated: {config_path} (model.provider=nous)")

+        # Resolve model BEFORE writing provider to config.yaml so we never
+        # leave the config in a half-updated state (provider=nous but model
+        # still set to the previous provider's model, e.g. opus from
+        # OpenRouter).  The auth.json active_provider was already set above.
+        selected_model = None
        try:
            runtime_key = auth_state.get("agent_key") or auth_state.get("access_token")
            if not isinstance(runtime_key, str) or not runtime_key:
@@ -2884,9 +3103,6 @@ def _login_nous(args, pconfig: ProviderConfig) -> None:
                    unavailable_models=unavailable_models,
                    portal_url=_portal,
                )
-                if selected_model:
-                    _save_model_choice(selected_model)
-                    print(f"Default model set to: {selected_model}")
            elif unavailable_models:
                _url = (_portal or DEFAULT_NOUS_PORTAL_URL).rstrip("/")
                print("No free models currently available.")
@@ -2898,6 +3114,15 @@ def _login_nous(args, pconfig: ProviderConfig) -> None:
            print()
            print(f"Login succeeded, but could not fetch available models. Reason: {message}")

+        # Write provider + model atomically so config is never mismatched.
+        config_path = _update_config_for_provider(
+            "nous", inference_base_url, default_model=selected_model,
+        )
+        if selected_model:
+            _save_model_choice(selected_model)
+            print(f"Default model set to: {selected_model}")
+        print(f"  Config updated: {config_path} (model.provider=nous)")
+
    except KeyboardInterrupt:
        print("\nLogin cancelled.")
        raise SystemExit(130)
@@ -32,7 +32,7 @@ from hermes_constants import OPENROUTER_BASE_URL


 # Providers that support OAuth login in addition to API keys.
-_OAUTH_CAPABLE_PROVIDERS = {"anthropic", "nous", "openai-codex"}
+_OAUTH_CAPABLE_PROVIDERS = {"anthropic", "nous", "openai-codex", "qwen-oauth"}


 def _get_custom_provider_names() -> list:
@@ -147,7 +147,7 @@ def auth_add_command(args) -> None:
        if provider.startswith(CUSTOM_POOL_PREFIX):
            requested_type = AUTH_TYPE_API_KEY
        else:
-            requested_type = AUTH_TYPE_OAUTH if provider in {"anthropic", "nous", "openai-codex"} else AUTH_TYPE_API_KEY
+            requested_type = AUTH_TYPE_OAUTH if provider in {"anthropic", "nous", "openai-codex", "qwen-oauth"} else AUTH_TYPE_API_KEY

    pool = load_pool(provider)

@@ -250,6 +250,26 @@ def auth_add_command(args) -> None:
        print(f'Added {provider} OAuth credential #{len(pool.entries())}: "{entry.label}"')
        return

+    if provider == "qwen-oauth":
+        creds = auth_mod.resolve_qwen_runtime_credentials(refresh_if_expiring=False)
+        label = (getattr(args, "label", None) or "").strip() or label_from_token(
+            creds["api_key"],
+            _oauth_default_label(provider, len(pool.entries()) + 1),
+        )
+        entry = PooledCredential(
+            provider=provider,
+            id=uuid.uuid4().hex[:6],
+            label=label,
+            auth_type=AUTH_TYPE_OAUTH,
+            priority=0,
+            source=f"{SOURCE_MANUAL}:qwen_cli",
+            access_token=creds["api_key"],
+            base_url=creds.get("base_url"),
+        )
+        pool.add_entry(entry)
+        print(f'Added {provider} OAuth credential #{len(pool.entries())}: "{entry.label}"')
+        return
+
    raise SystemExit(f"`hermes auth add {provider}` is not implemented for auth type {requested_type} yet.")


@@ -327,8 +347,11 @@ def auth_remove_command(args) -> None:
            print("Cleared Hermes Anthropic OAuth credentials")

    elif removed.source == "claude_code" and provider == "anthropic":
-        print("Note: Claude Code credentials live in ~/.claude/.credentials.json")
-        print("      Remove them manually if you want to deauthorize Claude Code.")
+        from hermes_cli.auth import suppress_credential_source
+        suppress_credential_source(provider, "claude_code")
+        print("Suppressed claude_code credential — it will not be re-seeded.")
+        print("Note: Claude Code credentials still live in ~/.claude/.credentials.json")
+        print("Run `hermes auth add anthropic` to re-enable if needed.")


 def auth_reset_command(args) -> None:
@@ -5,6 +5,7 @@ Pure display functions with no HermesCLI state dependency.

 import json
 import logging
+import os
 import shutil
 import subprocess
 import threading
@@ -89,12 +90,6 @@ HERMES_CADUCEUS = """[#CD7F32]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣀⡀⠀⣀⣀
 [#B8860B]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠳⠈⣡⠞⠁⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
 [#B8860B]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]"""

-COMPACT_BANNER = """
-[bold #FFD700]╔══════════════════════════════════════════════════════════════╗[/]
-[bold #FFD700]║[/]  [#FFBF00]⚕ NOUS HERMES[/] [dim #B8860B]- AI Agent Framework[/]              [bold #FFD700]║[/]
-[bold #FFD700]║[/]  [#CD7F32]Messenger of the Digital Gods[/]    [dim #B8860B]Nous Research[/]   [bold #FFD700]║[/]
-[bold #FFD700]╚══════════════════════════════════════════════════════════════╝[/]
-"""


 # =========================================================================
@@ -189,6 +184,79 @@ def check_for_updates() -> Optional[int]:
    return behind


+def _resolve_repo_dir() -> Optional[Path]:
+    """Return the active Hermes git checkout, or None if this isn't a git install."""
+    hermes_home = get_hermes_home()
+    repo_dir = hermes_home / "hermes-agent"
+    if not (repo_dir / ".git").exists():
+        repo_dir = Path(__file__).parent.parent.resolve()
+    return repo_dir if (repo_dir / ".git").exists() else None
+
+
+def _git_short_hash(repo_dir: Path, rev: str) -> Optional[str]:
+    """Resolve a git revision to an 8-character short hash."""
+    try:
+        result = subprocess.run(
+            ["git", "rev-parse", "--short=8", rev],
+            capture_output=True,
+            text=True,
+            timeout=5,
+            cwd=str(repo_dir),
+        )
+    except Exception:
+        return None
+    if result.returncode != 0:
+        return None
+    value = (result.stdout or "").strip()
+    return value or None
+
+
+def get_git_banner_state(repo_dir: Optional[Path] = None) -> Optional[dict]:
+    """Return upstream/local git hashes for the startup banner."""
+    repo_dir = repo_dir or _resolve_repo_dir()
+    if repo_dir is None:
+        return None
+
+    upstream = _git_short_hash(repo_dir, "origin/main")
+    local = _git_short_hash(repo_dir, "HEAD")
+    if not upstream or not local:
+        return None
+
+    ahead = 0
+    try:
+        result = subprocess.run(
+            ["git", "rev-list", "--count", "origin/main..HEAD"],
+            capture_output=True,
+            text=True,
+            timeout=5,
+            cwd=str(repo_dir),
+        )
+        if result.returncode == 0:
+            ahead = int((result.stdout or "0").strip() or "0")
+    except Exception:
+        ahead = 0
+
+    return {"upstream": upstream, "local": local, "ahead": max(ahead, 0)}
+
+
+def format_banner_version_label() -> str:
+    """Return the version label shown in the startup banner title."""
+    base = f"Hermes Agent v{VERSION} ({RELEASE_DATE})"
+    state = get_git_banner_state()
+    if not state:
+        return base
+
+    upstream = state["upstream"]
+    local = state["local"]
+    ahead = int(state.get("ahead") or 0)
+
+    if ahead <= 0 or upstream == local:
+        return f"{base} · upstream {upstream}"
+
+    carried_word = "commit" if ahead == 1 else "commits"
+    return f"{base} · upstream {upstream} · local {local} (+{ahead} carried {carried_word})"
+
+
 # =========================================================================
 # Non-blocking update check
 # =========================================================================
@@ -221,10 +289,16 @@ def _format_context_length(tokens: int) -> str:
    """Format a token count for display (e.g. 128000 → '128K', 1048576 → '1M')."""
    if tokens >= 1_000_000:
        val = tokens / 1_000_000
-        return f"{val:g}M"
+        rounded = round(val)
+        if abs(val - rounded) < 0.05:
+            return f"{rounded}M"
+        return f"{val:.1f}M"
    elif tokens >= 1_000:
        val = tokens / 1_000
-        return f"{val:g}K"
+        rounded = round(val)
+        if abs(val - rounded) < 0.05:
+            return f"{rounded}K"
+        return f"{val:.1f}K"
    return str(tokens)


@@ -448,7 +522,7 @@ def build_welcome_banner(console: Console, model: str, cwd: str,
    border_color = _skin_color("banner_border", "#CD7F32")
    outer_panel = Panel(
        layout_table,
-        title=f"[bold {title_color}]{agent_name} v{VERSION} ({RELEASE_DATE})[/]",
+        title=f"[bold {title_color}]{format_banner_version_label()}[/]",
        border_style=border_color,
        padding=(0, 2),
    )
@@ -1,140 +0,0 @@
-"""Shared curses-based multi-select checklist for Hermes CLI.
-
-Used by both ``hermes tools`` and ``hermes skills`` to present a
-toggleable list of items.  Falls back to a numbered text UI when
-curses is unavailable (Windows without curses, piped stdin, etc.).
-"""
-
-import sys
-from typing import List, Set
-
-from hermes_cli.colors import Colors, color
-
-
-def curses_checklist(
-    title: str,
-    items: List[str],
-    pre_selected: Set[int],
-) -> Set[int]:
-    """Multi-select checklist.  Returns set of **selected** indices.
-
-    Args:
-        title: Header text shown at the top of the checklist.
-        items: Display labels for each row.
-        pre_selected: Indices that start checked.
-
-    Returns:
-        The indices the user confirmed as checked.  On cancel (ESC/q),
-        returns ``pre_selected`` unchanged.
-    """
-    # Safety: return defaults when stdin is not a terminal.
-    if not sys.stdin.isatty():
-        return set(pre_selected)
-
-    try:
-        import curses
-        selected = set(pre_selected)
-        result = [None]
-
-        def _ui(stdscr):
-            curses.curs_set(0)
-            if curses.has_colors():
-                curses.start_color()
-                curses.use_default_colors()
-                curses.init_pair(1, curses.COLOR_GREEN, -1)
-                curses.init_pair(2, curses.COLOR_YELLOW, -1)
-                curses.init_pair(3, 8, -1)  # dim gray
-            cursor = 0
-            scroll_offset = 0
-
-            while True:
-                stdscr.clear()
-                max_y, max_x = stdscr.getmaxyx()
-
-                # Header
-                try:
-                    hattr = curses.A_BOLD | (curses.color_pair(2) if curses.has_colors() else 0)
-                    stdscr.addnstr(0, 0, title, max_x - 1, hattr)
-                    stdscr.addnstr(
-                        1, 0,
-                        "  ↑↓ navigate  SPACE toggle  ENTER confirm  ESC cancel",
-                        max_x - 1, curses.A_DIM,
-                    )
-                except curses.error:
-                    pass
-
-                # Scrollable item list
-                visible_rows = max_y - 3
-                if cursor < scroll_offset:
-                    scroll_offset = cursor
-                elif cursor >= scroll_offset + visible_rows:
-                    scroll_offset = cursor - visible_rows + 1
-
-                for draw_i, i in enumerate(
-                    range(scroll_offset, min(len(items), scroll_offset + visible_rows))
-                ):
-                    y = draw_i + 3
-                    if y >= max_y - 1:
-                        break
-                    check = "✓" if i in selected else " "
-                    arrow = "→" if i == cursor else " "
-                    line = f" {arrow} [{check}] {items[i]}"
-
-                    attr = curses.A_NORMAL
-                    if i == cursor:
-                        attr = curses.A_BOLD
-                        if curses.has_colors():
-                            attr |= curses.color_pair(1)
-                    try:
-                        stdscr.addnstr(y, 0, line, max_x - 1, attr)
-                    except curses.error:
-                        pass
-
-                stdscr.refresh()
-                key = stdscr.getch()
-
-                if key in (curses.KEY_UP, ord("k")):
-                    cursor = (cursor - 1) % len(items)
-                elif key in (curses.KEY_DOWN, ord("j")):
-                    cursor = (cursor + 1) % len(items)
-                elif key == ord(" "):
-                    selected.symmetric_difference_update({cursor})
-                elif key in (curses.KEY_ENTER, 10, 13):
-                    result[0] = set(selected)
-                    return
-                elif key in (27, ord("q")):
-                    result[0] = set(pre_selected)
-                    return
-
-        curses.wrapper(_ui)
-        return result[0] if result[0] is not None else set(pre_selected)
-
-    except Exception:
-        pass  # fall through to numbered fallback
-
-    # ── Numbered text fallback ────────────────────────────────────────────
-    selected = set(pre_selected)
-    print(color(f"\n  {title}", Colors.YELLOW))
-    print(color("  Toggle by number, Enter to confirm.\n", Colors.DIM))
-
-    while True:
-        for i, label in enumerate(items):
-            check = "✓" if i in selected else " "
-            print(f"    {i + 1:3}. [{check}] {label}")
-        print()
-
-        try:
-            raw = input(color("  Number to toggle, 's' to save, 'q' to cancel: ", Colors.DIM)).strip()
-        except (KeyboardInterrupt, EOFError):
-            return set(pre_selected)
-
-        if raw.lower() == "s" or raw == "":
-            return selected
-        if raw.lower() == "q":
-            return set(pre_selected)
-        try:
-            idx = int(raw) - 1
-            if 0 <= idx < len(items):
-                selected.symmetric_difference_update({idx})
-        except ValueError:
-            print(color("  Invalid input", Colors.DIM))
@@ -16,8 +16,18 @@ from collections.abc import Callable, Mapping
 from dataclasses import dataclass
 from typing import Any

-from prompt_toolkit.auto_suggest import AutoSuggest, Suggestion
-from prompt_toolkit.completion import Completer, Completion
+# prompt_toolkit is an optional CLI dependency — only needed for
+# SlashCommandCompleter and SlashCommandAutoSuggest.  Gateway and test
+# environments that lack it must still be able to import this module
+# for resolve_command, gateway_help_lines, and COMMAND_REGISTRY.
+try:
+    from prompt_toolkit.auto_suggest import AutoSuggest, Suggestion
+    from prompt_toolkit.completion import Completer, Completion
+except ImportError:  # pragma: no cover
+    AutoSuggest = object  # type: ignore[assignment,misc]
+    Completer = object    # type: ignore[assignment,misc]
+    Suggestion = None     # type: ignore[assignment]
+    Completion = None     # type: ignore[assignment]


 # ---------------------------------------------------------------------------
@@ -87,8 +97,7 @@ COMMAND_REGISTRY: list[CommandDef] = [
    CommandDef("model", "Switch model for this session", "Configuration", args_hint="[model] [--global]"),
    CommandDef("provider", "Show available providers and current provider",
               "Configuration"),
-    CommandDef("prompt", "View/set custom system prompt", "Configuration",
-               cli_only=True, args_hint="[text]", subcommands=("clear",)),
+
    CommandDef("personality", "Set a predefined personality", "Configuration",
               args_hint="[name]"),
    CommandDef("statusbar", "Toggle the context/model status bar", "Configuration",
@@ -100,7 +109,10 @@ COMMAND_REGISTRY: list[CommandDef] = [
               "Configuration"),
    CommandDef("reasoning", "Manage reasoning effort and display", "Configuration",
               args_hint="[level|show|hide]",
-               subcommands=("none", "low", "minimal", "medium", "high", "xhigh", "show", "hide", "on", "off")),
+               subcommands=("none", "minimal", "low", "medium", "high", "xhigh", "show", "hide", "on", "off")),
+    CommandDef("fast", "Toggle fast mode — OpenAI Priority Processing / Anthropic Fast Mode (Normal/Fast)", "Configuration",
+               cli_only=True, args_hint="[normal|fast|status]",
+               subcommands=("normal", "fast", "status", "on", "off")),
    CommandDef("skin", "Show or change the display skin/theme", "Configuration",
               cli_only=True, args_hint="[name]"),
    CommandDef("voice", "Toggle voice mode", "Configuration",
@@ -129,13 +141,15 @@ COMMAND_REGISTRY: list[CommandDef] = [
    CommandDef("commands", "Browse all commands and skills (paginated)", "Info",
               gateway_only=True, args_hint="[page]"),
    CommandDef("help", "Show available commands", "Info"),
-    CommandDef("usage", "Show token usage for the current session", "Info"),
+    CommandDef("usage", "Show token usage and rate limits for the current session", "Info"),
    CommandDef("insights", "Show usage insights and analytics", "Info",
               args_hint="[days]"),
    CommandDef("platforms", "Show gateway/messaging platform status", "Info",
               cli_only=True, aliases=("gateway",)),
    CommandDef("paste", "Check clipboard for an image and attach it", "Info",
               cli_only=True),
+    CommandDef("image", "Attach a local image file for your next prompt", "Info",
+               cli_only=True, args_hint="<path>"),
    CommandDef("update", "Update Hermes Agent to the latest version", "Info",
               gateway_only=True),

@@ -170,12 +184,6 @@ def resolve_command(name: str) -> CommandDef | None:
    return _COMMAND_LOOKUP.get(name.lower().lstrip("/"))


-def register_plugin_command(cmd: CommandDef) -> None:
-    """Append a plugin-defined command to the registry and refresh lookups."""
-    COMMAND_REGISTRY.append(cmd)
-    rebuild_lookups()
-
-
 def rebuild_lookups() -> None:
    """Rebuild all derived lookup dicts from the current COMMAND_REGISTRY.

@@ -293,14 +301,8 @@ def _resolve_config_gates() -> set[str]:
    if not gated:
        return set()
    try:
-        import yaml
-        from hermes_constants import get_hermes_home
-        config_path = str(get_hermes_home() / "config.yaml")
-        if os.path.exists(config_path):
-            with open(config_path, encoding="utf-8") as f:
-                cfg = yaml.safe_load(f) or {}
-        else:
-            cfg = {}
+        from hermes_cli.config import read_raw_config
+        cfg = read_raw_config()
    except Exception:
        return set()
    result: set[str] = set()
@@ -644,8 +646,18 @@ class SlashCommandCompleter(Completer):
    def __init__(
        self,
        skill_commands_provider: Callable[[], Mapping[str, dict[str, Any]]] | None = None,
+        command_filter: Callable[[str], bool] | None = None,
    ) -> None:
        self._skill_commands_provider = skill_commands_provider
+        self._command_filter = command_filter
+
+    def _command_allowed(self, slash_command: str) -> bool:
+        if self._command_filter is None:
+            return True
+        try:
+            return bool(self._command_filter(slash_command))
+        except Exception:
+            return True

    def _iter_skill_commands(self) -> Mapping[str, dict[str, Any]]:
        if self._skill_commands_provider is None:
@@ -923,7 +935,7 @@ class SlashCommandCompleter(Completer):
                return

            # Static subcommand completions
-            if " " not in sub_text and base_cmd in SUBCOMMANDS:
+            if " " not in sub_text and base_cmd in SUBCOMMANDS and self._command_allowed(base_cmd):
                for sub in SUBCOMMANDS[base_cmd]:
                    if sub.startswith(sub_lower) and sub != sub_lower:
                        yield Completion(
@@ -936,6 +948,8 @@ class SlashCommandCompleter(Completer):
        word = text[1:]

        for cmd, desc in COMMANDS.items():
+            if not self._command_allowed(cmd):
+                continue
            cmd_name = cmd[1:]
            if cmd_name.startswith(word):
                yield Completion(
@@ -994,6 +1008,8 @@ class SlashCommandAutoSuggest(AutoSuggest):
            # Still typing the command name: /upd → suggest "ate"
            word = text[1:].lower()
            for cmd in COMMANDS:
+                if self._completer is not None and not self._completer._command_allowed(cmd):
+                    continue
                cmd_name = cmd[1:]  # strip leading /
                if cmd_name.startswith(word) and cmd_name != word:
                    return Suggestion(cmd_name[len(word):])
@@ -1004,6 +1020,8 @@ class SlashCommandAutoSuggest(AutoSuggest):
        sub_lower = sub_text.lower()

        # Static subcommands
+        if self._completer is not None and not self._completer._command_allowed(base_cmd):
+            return None
        if base_cmd in SUBCOMMANDS and SUBCOMMANDS[base_cmd]:
            if " " not in sub_text:
                for sub in SUBCOMMANDS[base_cmd]:
@@ -39,6 +39,7 @@ _EXTRA_ENV_KEYS = frozenset({
    "DINGTALK_CLIENT_ID", "DINGTALK_CLIENT_SECRET",
    "FEISHU_APP_ID", "FEISHU_APP_SECRET", "FEISHU_ENCRYPT_KEY", "FEISHU_VERIFICATION_TOKEN",
    "WECOM_BOT_ID", "WECOM_SECRET",
+    "BLUEBUBBLES_SERVER_URL", "BLUEBUBBLES_PASSWORD",
    "TERMINAL_ENV", "TERMINAL_SSH_KEY", "TERMINAL_SSH_PORT",
    "WHATSAPP_MODE", "WHATSAPP_ENABLED",
    "MATTERMOST_HOME_CHANNEL", "MATTERMOST_REPLY_MODE",
@@ -157,15 +158,39 @@ def get_project_root() -> Path:
    return Path(__file__).parent.parent.resolve()

 def _secure_dir(path):
-    """Set directory to owner-only access (0700). No-op on Windows."""
+    """Set directory to owner-only access (0700 by default). No-op on Windows.
+
+    Skipped in managed mode — the NixOS module sets group-readable
+    permissions (0750) so interactive users in the hermes group can
+    share state with the gateway service.
+
+    The mode can be overridden via the HERMES_HOME_MODE environment variable
+    (e.g. HERMES_HOME_MODE=0701) for deployments where a web server (nginx,
+    caddy, etc.) needs to traverse HERMES_HOME to reach a served subdirectory.
+    The execute-only bit on a directory permits cd-through without exposing
+    directory listings.
+    """
+    if is_managed():
+        return
    try:
-        os.chmod(path, 0o700)
+        mode_str = os.environ.get("HERMES_HOME_MODE", "").strip()
+        mode = int(mode_str, 8) if mode_str else 0o700
+    except ValueError:
+        mode = 0o700
+    try:
+        os.chmod(path, mode)
    except (OSError, NotImplementedError):
        pass


 def _secure_file(path):
-    """Set file to owner-only read/write (0600). No-op on Windows."""
+    """Set file to owner-only read/write (0600). No-op on Windows.
+
+    Skipped in managed mode — the NixOS activation script sets
+    group-readable permissions (0640) on config files.
+    """
+    if is_managed():
+        return
    try:
        if os.path.exists(str(path)):
            os.chmod(path, 0o600)
@@ -183,14 +208,44 @@ def _ensure_default_soul_md(home: Path) -> None:


 def ensure_hermes_home():
-    """Ensure ~/.hermes directory structure exists with secure permissions."""
+    """Ensure ~/.hermes directory structure exists with secure permissions.
+
+    In managed mode (NixOS), dirs are created by the activation script with
+    setgid + group-writable (2770). We skip mkdir and set umask(0o007) so
+    any files created (e.g. SOUL.md) are group-writable (0660).
+    """
    home = get_hermes_home()
-    home.mkdir(parents=True, exist_ok=True)
-    _secure_dir(home)
+    if is_managed():
+        old_umask = os.umask(0o007)
+        try:
+            _ensure_hermes_home_managed(home)
+        finally:
+            os.umask(old_umask)
+    else:
+        home.mkdir(parents=True, exist_ok=True)
+        _secure_dir(home)
+        for subdir in ("cron", "sessions", "logs", "memories"):
+            d = home / subdir
+            d.mkdir(parents=True, exist_ok=True)
+            _secure_dir(d)
+        _ensure_default_soul_md(home)
+
+
+def _ensure_hermes_home_managed(home: Path):
+    """Managed-mode variant: verify dirs exist (activation creates them), seed SOUL.md."""
+    if not home.is_dir():
+        raise RuntimeError(
+            f"HERMES_HOME {home} does not exist. "
+            "Run 'sudo nixos-rebuild switch' first."
+        )
    for subdir in ("cron", "sessions", "logs", "memories"):
        d = home / subdir
-        d.mkdir(parents=True, exist_ok=True)
-        _secure_dir(d)
+        if not d.is_dir():
+            raise RuntimeError(
+                f"{d} does not exist. "
+                "Run 'sudo nixos-rebuild switch' first."
+            )
+    # Inside umask(0o007) scope — SOUL.md will be created as 0660
    _ensure_default_soul_md(home)


@@ -211,12 +266,17 @@ DEFAULT_CONFIG = {
        # tools or receiving API responses.  Only fires when the agent has
        # been completely idle for this duration.  0 = unlimited.
        "gateway_timeout": 1800,
+        "service_tier": "",
        # Tool-use enforcement: injects system prompt guidance that tells the
        # model to actually call tools instead of describing intended actions.
        # Values: "auto" (default — applies to gpt/codex models), true/false
        # (force on/off for all models), or a list of model-name substrings
        # to match (e.g. ["gpt", "codex", "gemini", "qwen"]).
        "tool_use_enforcement": "auto",
+        # Staged inactivity warning: send a warning to the user at this
+        # threshold before escalating to a full timeout.  The warning fires
+        # once per run and does not interrupt the agent.  0 = disable warning.
+        "gateway_timeout_warning": 900,
    },
    
    "terminal": {
@@ -379,6 +439,7 @@ DEFAULT_CONFIG = {
        "show_cost": False,       # Show $ cost in the status bar (off by default)
        "skin": "default",
        "tool_progress_command": False,  # Enable /verbose command in messaging gateway
+        "tool_progress_overrides": {},  # Per-platform overrides: {"signal": "off", "telegram": "all"}
        "tool_preview_length": 0,  # Max chars for tool call previews (0 = no limit, show full paths/commands)
    },

@@ -413,13 +474,17 @@ DEFAULT_CONFIG = {
    
    "stt": {
        "enabled": True,
-        "provider": "local",  # "local" (free, faster-whisper) | "groq" | "openai" (Whisper API)
+        "provider": "local",  # "local" (free, faster-whisper) | "groq" | "openai" (Whisper API) | "mistral" (Voxtral Transcribe)
        "local": {
            "model": "base",  # tiny, base, small, medium, large-v3
+            "language": "",  # auto-detect by default; set to "en", "es", "fr", etc. to force
        },
        "openai": {
            "model": "whisper-1",  # whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe
        },
+        "mistral": {
+            "model": "voxtral-mini-latest",  # voxtral-mini-latest, voxtral-mini-2602
+        },
    },

    "voice": {
@@ -487,6 +552,7 @@ DEFAULT_CONFIG = {
    "discord": {
        "require_mention": True,       # Require @mention to respond in server channels
        "free_response_channels": "",  # Comma-separated channel IDs where bot responds without mention
+        "allowed_channels": "",        # If set, bot ONLY responds in these channel IDs (whitelist)
        "auto_thread": True,           # Auto-create threads on @mention in channels (like Slack)
        "reactions": True,             # Add 👀/✅/❌ reactions to messages during processing
    },
@@ -546,7 +612,7 @@ DEFAULT_CONFIG = {
    },

    # Config schema version - bump this when adding new required fields
-    "_config_version": 12,
+    "_config_version": 14,
 }

 # =============================================================================
@@ -723,6 +789,14 @@ OPTIONAL_ENV_VARS = {
        "category": "provider",
        "advanced": True,
    },
+    "HERMES_QWEN_BASE_URL": {
+        "description": "Qwen Portal base URL override (default: https://portal.qwen.ai/v1)",
+        "prompt": "Qwen Portal base URL (leave empty for default)",
+        "url": None,
+        "password": False,
+        "category": "provider",
+        "advanced": True,
+    },
    "OPENCODE_ZEN_API_KEY": {
        "description": "OpenCode Zen API key (pay-as-you-go access to curated models)",
        "prompt": "OpenCode Zen API key",
@@ -974,6 +1048,13 @@ OPTIONAL_ENV_VARS = {
        "password": False,
        "category": "messaging",
    },
+    "DISCORD_REPLY_TO_MODE": {
+        "description": "Discord reply threading mode: 'off' (no reply references), 'first' (reply on first message only, default), 'all' (reply on every chunk)",
+        "prompt": "Discord reply mode (off/first/all)",
+        "url": None,
+        "password": False,
+        "category": "messaging",
+    },
    "SLACK_BOT_TOKEN": {
        "description": "Slack bot token (xoxb-). Get from OAuth & Permissions after installing your app. "
                       "Required scopes: chat:write, app_mentions:read, channels:history, groups:history, "
@@ -1087,6 +1168,27 @@ OPTIONAL_ENV_VARS = {
        "category": "messaging",
        "advanced": True,
    },
+    "BLUEBUBBLES_SERVER_URL": {
+        "description": "BlueBubbles server URL for iMessage integration (e.g. http://192.168.1.10:1234)",
+        "prompt": "BlueBubbles server URL",
+        "url": "https://bluebubbles.app/",
+        "password": False,
+        "category": "messaging",
+    },
+    "BLUEBUBBLES_PASSWORD": {
+        "description": "BlueBubbles server password (from BlueBubbles Server → Settings → API)",
+        "prompt": "BlueBubbles server password",
+        "url": None,
+        "password": True,
+        "category": "messaging",
+    },
+    "BLUEBUBBLES_ALLOWED_USERS": {
+        "description": "Comma-separated iMessage addresses (email or phone) allowed to use the bot",
+        "prompt": "Allowed iMessage addresses (comma-separated)",
+        "url": None,
+        "password": False,
+        "category": "messaging",
+    },
    "GATEWAY_ALLOW_ALL_USERS": {
        "description": "Allow all users to interact with messaging bots (true/false). Default: false.",
        "prompt": "Allow all users (true/false)",
@@ -1127,6 +1229,14 @@ OPTIONAL_ENV_VARS = {
        "category": "messaging",
        "advanced": True,
    },
+    "API_SERVER_MODEL_NAME": {
+        "description": "Model name advertised on /v1/models. Defaults to the profile name (or 'hermes-agent' for the default profile). Useful for multi-user setups with OpenWebUI.",
+        "prompt": "API server model name",
+        "url": None,
+        "password": False,
+        "category": "messaging",
+        "advanced": True,
+    },
    "WEBHOOK_ENABLED": {
        "description": "Enable the webhook platform adapter for receiving events from GitHub, GitLab, etc.",
        "prompt": "Enable webhooks (true/false)",
@@ -1158,7 +1268,7 @@ OPTIONAL_ENV_VARS = {
        "category": "setting",
    },
    "SUDO_PASSWORD": {
-        "description": "Sudo password for terminal commands requiring root access",
+        "description": "Sudo password for terminal commands requiring root access; set to an explicit empty string to try empty without prompting",
        "prompt": "Sudo password",
        "url": None,
        "password": True,
@@ -1642,6 +1752,71 @@ def migrate_config(interactive: bool = True, quiet: bool = False) -> Dict[str, A
                        ep = providers_dict[key]
                        print(f"    → {key}: {ep.get('api', '')}")

+    # ── Version 12 → 13: clear dead LLM_MODEL / OPENAI_MODEL from .env ──
+    # These env vars were written by the old setup wizard but nothing reads
+    # them anymore (config.yaml is the sole source of truth since March 2026).
+    # Stale entries cause user confusion — see issue report.
+    if current_ver < 13:
+        for dead_var in ("LLM_MODEL", "OPENAI_MODEL"):
+            try:
+                old_val = get_env_value(dead_var)
+                if old_val:
+                    save_env_value(dead_var, "")
+                    if not quiet:
+                        print(f"  ✓ Cleared {dead_var} from .env (no longer used — config.yaml is source of truth)")
+            except Exception:
+                pass
+
+    # ── Version 13 → 14: migrate legacy flat stt.model to provider section ──
+    # Old configs (and cli-config.yaml.example) had a flat `stt.model` key
+    # that was provider-agnostic.  When the provider was "local" this caused
+    # OpenAI model names (e.g. "whisper-1") to be fed to faster-whisper,
+    # crashing with "Invalid model size".  Move the value into the correct
+    # provider-specific section and remove the flat key.
+    if current_ver < 14:
+        # Read raw config (no defaults merged) to check what the user actually
+        # wrote, then apply changes to the merged config for saving.
+        raw = read_raw_config()
+        raw_stt = raw.get("stt", {})
+        if isinstance(raw_stt, dict) and "model" in raw_stt:
+            legacy_model = raw_stt["model"]
+            provider = raw_stt.get("provider", "local")
+            config = load_config()
+            stt = config.get("stt", {})
+            # Remove the legacy flat key
+            stt.pop("model", None)
+            # Place it in the appropriate provider section only if the
+            # user didn't already set a model there
+            if provider in ("local", "local_command"):
+                # Don't migrate an OpenAI model name into the local section
+                _local_models = {
+                    "tiny.en", "tiny", "base.en", "base", "small.en", "small",
+                    "medium.en", "medium", "large-v1", "large-v2", "large-v3",
+                    "large", "distil-large-v2", "distil-medium.en",
+                    "distil-small.en", "distil-large-v3", "distil-large-v3.5",
+                    "large-v3-turbo", "turbo",
+                }
+                if legacy_model in _local_models:
+                    # Check raw config — only set if user didn't already
+                    # have a nested local.model
+                    raw_local = raw_stt.get("local", {})
+                    if not isinstance(raw_local, dict) or "model" not in raw_local:
+                        local_cfg = stt.setdefault("local", {})
+                        local_cfg["model"] = legacy_model
+                # else: drop it — it was an OpenAI model name, local section
+                # already defaults to "base" via DEFAULT_CONFIG
+            else:
+                # Cloud provider — put it in that provider's section only
+                # if user didn't already set a nested model
+                raw_provider = raw_stt.get(provider, {})
+                if not isinstance(raw_provider, dict) or "model" not in raw_provider:
+                    provider_cfg = stt.setdefault(provider, {})
+                    provider_cfg["model"] = legacy_model
+            config["stt"] = stt
+            save_config(config)
+            if not quiet:
+                print(f"  ✓ Migrated legacy stt.model to provider-specific config")
+
    if current_ver < latest_ver and not quiet:
        print(f"Config version: {current_ver} → {latest_ver}")
    
@@ -31,13 +31,6 @@ logger = logging.getLogger(__name__)

 # OAuth device code flow constants (same client ID as opencode/Copilot CLI)
 COPILOT_OAUTH_CLIENT_ID = "Ov23li8tweQw6odWQebz"
-COPILOT_DEVICE_CODE_URL = "https://github.com/login/device/code"
-COPILOT_ACCESS_TOKEN_URL = "https://github.com/login/oauth/access_token"
-
-# Copilot API constants
-COPILOT_TOKEN_EXCHANGE_URL = "https://api.github.com/copilot_internal/v2/token"
-COPILOT_API_BASE_URL = "https://api.githubcopilot.com"
-
 # Token type prefixes
 _CLASSIC_PAT_PREFIX = "ghp_"
 _SUPPORTED_PREFIXES = ("gho_", "github_pat_", "ghu_")
@@ -50,11 +43,6 @@ _DEVICE_CODE_POLL_INTERVAL = 5  # seconds
 _DEVICE_CODE_POLL_SAFETY_MARGIN = 3  # seconds


-def is_classic_pat(token: str) -> bool:
-    """Check if a token is a classic PAT (ghp_*), which Copilot doesn't support."""
-    return token.strip().startswith(_CLASSIC_PAT_PREFIX)
-
-
 def validate_copilot_token(token: str) -> tuple[bool, str]:
    """Validate that a token is usable with the Copilot API.

@@ -285,6 +273,7 @@ def copilot_request_headers(
    headers: dict[str, str] = {
        "Editor-Version": "vscode/1.104.1",
        "User-Agent": "HermesAgent/1.0",
+        "Copilot-Integration-Id": "vscode-chat",
        "Openai-Intent": "conversation-edits",
        "x-initiator": "agent" if is_agent_turn else "user",
    }
@@ -93,6 +93,21 @@ def cron_list(show_all: bool = False):
        script = job.get("script")
        if script:
            print(f"    Script:    {script}")
+
+        # Execution history
+        last_status = job.get("last_status")
+        if last_status:
+            last_run = job.get("last_run_at", "?")
+            if last_status == "ok":
+                status_display = color("ok", Colors.GREEN)
+            else:
+                status_display = color(f"{last_status}: {job.get('last_error', '?')}", Colors.RED)
+            print(f"    Last run:  {last_run}  {status_display}")
+
+        delivery_err = job.get("last_delivery_error")
+        if delivery_err:
+            print(f"    {color('⚠ Delivery failed:', Colors.YELLOW)} {delivery_err}")
+
        print()

    from hermes_cli.gateway import find_gateway_pids
@@ -54,6 +54,32 @@ _PROVIDER_ENV_HINTS = (
 )


+from hermes_constants import is_termux as _is_termux
+
+
+def _python_install_cmd() -> str:
+    return "python -m pip install" if _is_termux() else "uv pip install"
+
+
+def _system_package_install_cmd(pkg: str) -> str:
+    if _is_termux():
+        return f"pkg install {pkg}"
+    if sys.platform == "darwin":
+        return f"brew install {pkg}"
+    return f"sudo apt install {pkg}"
+
+
+def _termux_browser_setup_steps(node_installed: bool) -> list[str]:
+    steps: list[str] = []
+    step = 1
+    if not node_installed:
+        steps.append(f"{step}) pkg install nodejs")
+        step += 1
+    steps.append(f"{step}) npm install -g agent-browser")
+    steps.append(f"{step + 1}) agent-browser install")
+    return steps
+
+
 def _has_provider_env_config(content: str) -> bool:
    """Return True when ~/.hermes/.env contains provider auth/base URL settings."""
    return any(key in content for key in _PROVIDER_ENV_HINTS)
@@ -200,7 +226,7 @@ def run_doctor(args):
            check_ok(name)
        except ImportError:
            check_fail(name, "(missing)")
-            issues.append(f"Install {name}: uv pip install {module}")
+            issues.append(f"Install {name}: {_python_install_cmd()} {module}")
    
    for module, name in optional_packages:
        try:
@@ -503,7 +529,7 @@ def run_doctor(args):
        check_ok("ripgrep (rg)", "(faster file search)")
    else:
        check_warn("ripgrep (rg) not found", "(file search uses grep fallback)")
-        check_info("Install for faster search: sudo apt install ripgrep")
+        check_info(f"Install for faster search: {_system_package_install_cmd('ripgrep')}")
    
    # Docker (optional)
    terminal_env = os.getenv("TERMINAL_ENV", "local")
@@ -526,7 +552,10 @@ def run_doctor(args):
        if shutil.which("docker"):
            check_ok("docker", "(optional)")
        else:
-            check_warn("docker not found", "(optional)")
+            if _is_termux():
+                check_info("Docker backend is not available inside Termux (expected on Android)")
+            else:
+                check_warn("docker not found", "(optional)")
    
    # SSH (if using ssh backend)
    if terminal_env == "ssh":
@@ -574,9 +603,23 @@ def run_doctor(args):
        if agent_browser_path.exists():
            check_ok("agent-browser (Node.js)", "(browser automation)")
        else:
-            check_warn("agent-browser not installed", "(run: npm install)")
+            if _is_termux():
+                check_info("agent-browser is not installed (expected in the tested Termux path)")
+                check_info("Install it manually later with: npm install -g agent-browser && agent-browser install")
+                check_info("Termux browser setup:")
+                for step in _termux_browser_setup_steps(node_installed=True):
+                    check_info(step)
+            else:
+                check_warn("agent-browser not installed", "(run: npm install)")
    else:
-        check_warn("Node.js not found", "(optional, needed for browser tools)")
+        if _is_termux():
+            check_info("Node.js not found (browser tools are optional in the tested Termux path)")
+            check_info("Install Node.js on Termux with: pkg install nodejs")
+            check_info("Termux browser setup:")
+            for step in _termux_browser_setup_steps(node_installed=False):
+                check_info(step)
+        else:
+            check_warn("Node.js not found", "(optional, needed for browser tools)")
    
    # npm audit for all Node.js packages
    if shutil.which("npm"):
@@ -709,7 +752,7 @@ def run_doctor(args):
                _url = (_base.rstrip("/") + "/models") if _base else _default_url
                _headers = {"Authorization": f"Bearer {_key}"}
                if "api.kimi.com" in _url.lower():
-                    _headers["User-Agent"] = "KimiCLI/1.0"
+                    _headers["User-Agent"] = "KimiCLI/1.30.0"
                _resp = httpx.get(
                    _url,
                    headers=_headers,
@@ -739,8 +782,9 @@ def run_doctor(args):
                __import__("tinker_atropos")
                check_ok("tinker-atropos", "(RL training backend)")
            except ImportError:
-                check_warn("tinker-atropos found but not installed", "(run: uv pip install -e ./tinker-atropos)")
-                issues.append("Install tinker-atropos: uv pip install -e ./tinker-atropos")
+                install_cmd = f"{_python_install_cmd()} -e ./tinker-atropos"
+                check_warn("tinker-atropos found but not installed", f"(run: {install_cmd})")
+                issues.append(f"Install tinker-atropos: {install_cmd}")
        else:
            check_warn("tinker-atropos requires Python 3.11+", f"(current: {py_version.major}.{py_version.minor})")
    else:
@@ -812,69 +856,83 @@ def run_doctor(args):
        check_warn("No GITHUB_TOKEN", f"(60 req/hr rate limit — set in {_DHH}/.env for better rates)")

    # =========================================================================
-    # Honcho memory
+    # Memory Provider (only check the active provider, if any)
    # =========================================================================
    print()
-    print(color("◆ Honcho Memory", Colors.CYAN, Colors.BOLD))
+    print(color("◆ Memory Provider", Colors.CYAN, Colors.BOLD))

+    _active_memory_provider = ""
    try:
-        from plugins.memory.honcho.client import HonchoClientConfig, resolve_config_path
-        hcfg = HonchoClientConfig.from_global_config()
-        _honcho_cfg_path = resolve_config_path()
+        import yaml as _yaml
+        _mem_cfg_path = HERMES_HOME / "config.yaml"
+        if _mem_cfg_path.exists():
+            with open(_mem_cfg_path) as _f:
+                _raw_cfg = _yaml.safe_load(_f) or {}
+            _active_memory_provider = (_raw_cfg.get("memory") or {}).get("provider", "")
+    except Exception:
+        pass

-        if not _honcho_cfg_path.exists():
-            check_warn("Honcho config not found", "run: hermes memory setup")
-        elif not hcfg.enabled:
-            check_info(f"Honcho disabled (set enabled: true in {_honcho_cfg_path} to activate)")
-        elif not (hcfg.api_key or hcfg.base_url):
-            check_fail("Honcho API key or base URL not set", "run: hermes memory setup")
-            issues.append("No Honcho API key — run 'hermes memory setup'")
-        else:
-            from plugins.memory.honcho.client import get_honcho_client, reset_honcho_client
-            reset_honcho_client()
-            try:
-                get_honcho_client(hcfg)
-                check_ok(
-                    "Honcho connected",
-                    f"workspace={hcfg.workspace_id} mode={hcfg.recall_mode} freq={hcfg.write_frequency}",
-                )
-            except Exception as _e:
-                check_fail("Honcho connection failed", str(_e))
-                issues.append(f"Honcho unreachable: {_e}")
-    except ImportError:
-        check_warn("honcho-ai not installed", "pip install honcho-ai")
-    except Exception as _e:
-        check_warn("Honcho check failed", str(_e))
+    if not _active_memory_provider:
+        check_ok("Built-in memory active", "(no external provider configured — this is fine)")
+    elif _active_memory_provider == "honcho":
+        try:
+            from plugins.memory.honcho.client import HonchoClientConfig, resolve_config_path
+            hcfg = HonchoClientConfig.from_global_config()
+            _honcho_cfg_path = resolve_config_path()

-    # =========================================================================
-    # Mem0 memory
-    # =========================================================================
-    print()
-    print(color("◆ Mem0 Memory", Colors.CYAN, Colors.BOLD))
-
-    try:
-        from plugins.memory.mem0 import _load_config as _load_mem0_config
-        mem0_cfg = _load_mem0_config()
-        mem0_key = mem0_cfg.get("api_key", "")
-        if mem0_key:
-            check_ok("Mem0 API key configured")
-            check_info(f"user_id={mem0_cfg.get('user_id', '?')}  agent_id={mem0_cfg.get('agent_id', '?')}")
-            # Check if mem0.json exists but is missing api_key (the bug we fixed)
-            mem0_json = HERMES_HOME / "mem0.json"
-            if mem0_json.exists():
+            if not _honcho_cfg_path.exists():
+                check_warn("Honcho config not found", "run: hermes memory setup")
+            elif not hcfg.enabled:
+                check_info(f"Honcho disabled (set enabled: true in {_honcho_cfg_path} to activate)")
+            elif not (hcfg.api_key or hcfg.base_url):
+                check_fail("Honcho API key or base URL not set", "run: hermes memory setup")
+                issues.append("No Honcho API key — run 'hermes memory setup'")
+            else:
+                from plugins.memory.honcho.client import get_honcho_client, reset_honcho_client
+                reset_honcho_client()
                try:
-                    import json as _json
-                    file_cfg = _json.loads(mem0_json.read_text())
-                    if not file_cfg.get("api_key") and mem0_key:
-                        check_info("api_key from .env (not in mem0.json) — this is fine")
-                except Exception:
-                    pass
-        else:
-            check_warn("Mem0 not configured", "(set MEM0_API_KEY in .env or run hermes memory setup)")
-    except ImportError:
-        check_warn("Mem0 plugin not loadable", "(optional)")
-    except Exception as _e:
-        check_warn("Mem0 check failed", str(_e))
+                    get_honcho_client(hcfg)
+                    check_ok(
+                        "Honcho connected",
+                        f"workspace={hcfg.workspace_id} mode={hcfg.recall_mode} freq={hcfg.write_frequency}",
+                    )
+                except Exception as _e:
+                    check_fail("Honcho connection failed", str(_e))
+                    issues.append(f"Honcho unreachable: {_e}")
+        except ImportError:
+            check_fail("honcho-ai not installed", "pip install honcho-ai")
+            issues.append("Honcho is set as memory provider but honcho-ai is not installed")
+        except Exception as _e:
+            check_warn("Honcho check failed", str(_e))
+    elif _active_memory_provider == "mem0":
+        try:
+            from plugins.memory.mem0 import _load_config as _load_mem0_config
+            mem0_cfg = _load_mem0_config()
+            mem0_key = mem0_cfg.get("api_key", "")
+            if mem0_key:
+                check_ok("Mem0 API key configured")
+                check_info(f"user_id={mem0_cfg.get('user_id', '?')}  agent_id={mem0_cfg.get('agent_id', '?')}")
+            else:
+                check_fail("Mem0 API key not set", "(set MEM0_API_KEY in .env or run hermes memory setup)")
+                issues.append("Mem0 is set as memory provider but API key is missing")
+        except ImportError:
+            check_fail("Mem0 plugin not loadable", "pip install mem0ai")
+            issues.append("Mem0 is set as memory provider but mem0ai is not installed")
+        except Exception as _e:
+            check_warn("Mem0 check failed", str(_e))
+    else:
+        # Generic check for other memory providers (openviking, hindsight, etc.)
+        try:
+            from plugins.memory import load_memory_provider
+            _provider = load_memory_provider(_active_memory_provider)
+            if _provider and _provider.is_available():
+                check_ok(f"{_active_memory_provider} provider active")
+            elif _provider:
+                check_warn(f"{_active_memory_provider} configured but not available", "run: hermes memory status")
+            else:
+                check_warn(f"{_active_memory_provider} plugin not found", "run: hermes memory setup")
+        except Exception as _e:
+            check_warn(f"{_active_memory_provider} check failed", str(_e))

    # =========================================================================
    # Profiles
@@ -0,0 +1,332 @@
+"""
+Dump command for hermes CLI.
+
+Outputs a compact, plain-text summary of the user's Hermes setup
+that can be copy-pasted into Discord/GitHub/Telegram for support context.
+No ANSI colors, no checkmarks — just data.
+"""
+
+import json
+import os
+import platform
+import subprocess
+import sys
+from pathlib import Path
+
+from hermes_cli.config import get_hermes_home, get_env_path, get_project_root, load_config
+from hermes_constants import display_hermes_home
+
+
+def _get_git_commit(project_root: Path) -> str:
+    """Return short git commit hash, or '(unknown)'."""
+    try:
+        result = subprocess.run(
+            ["git", "rev-parse", "--short=8", "HEAD"],
+            capture_output=True, text=True, timeout=5,
+            cwd=str(project_root),
+        )
+        if result.returncode == 0:
+            return result.stdout.strip()
+    except Exception:
+        pass
+    return "(unknown)"
+
+
+def _redact(value: str) -> str:
+    """Redact all but first 4 and last 4 chars."""
+    if not value:
+        return ""
+    if len(value) < 12:
+        return "***"
+    return value[:4] + "..." + value[-4:]
+
+
+def _gateway_status() -> str:
+    """Return a short gateway status string."""
+    if sys.platform.startswith("linux"):
+        try:
+            from hermes_cli.gateway import get_service_name
+            svc = get_service_name()
+        except Exception:
+            svc = "hermes-gateway"
+        try:
+            r = subprocess.run(
+                ["systemctl", "--user", "is-active", svc],
+                capture_output=True, text=True, timeout=5,
+            )
+            return "running (systemd)" if r.stdout.strip() == "active" else "stopped"
+        except Exception:
+            return "unknown"
+    elif sys.platform == "darwin":
+        try:
+            from hermes_cli.gateway import get_launchd_label
+            r = subprocess.run(
+                ["launchctl", "list", get_launchd_label()],
+                capture_output=True, text=True, timeout=5,
+            )
+            return "loaded (launchd)" if r.returncode == 0 else "not loaded"
+        except Exception:
+            return "unknown"
+    return "N/A"
+
+
+def _count_skills(hermes_home: Path) -> int:
+    """Count installed skills."""
+    skills_dir = hermes_home / "skills"
+    if not skills_dir.is_dir():
+        return 0
+    count = 0
+    for item in skills_dir.rglob("SKILL.md"):
+        count += 1
+    return count
+
+
+def _count_mcp_servers(config: dict) -> int:
+    """Count configured MCP servers."""
+    mcp = config.get("mcp", {})
+    servers = mcp.get("servers", {})
+    return len(servers)
+
+
+def _cron_summary(hermes_home: Path) -> str:
+    """Return cron jobs summary."""
+    jobs_file = hermes_home / "cron" / "jobs.json"
+    if not jobs_file.exists():
+        return "0"
+    try:
+        with open(jobs_file, encoding="utf-8") as f:
+            data = json.load(f)
+        jobs = data.get("jobs", [])
+        active = sum(1 for j in jobs if j.get("enabled", True))
+        return f"{active} active / {len(jobs)} total"
+    except Exception:
+        return "(error reading)"
+
+
+def _configured_platforms() -> list[str]:
+    """Return list of configured messaging platform names."""
+    checks = {
+        "telegram": "TELEGRAM_BOT_TOKEN",
+        "discord": "DISCORD_BOT_TOKEN",
+        "slack": "SLACK_BOT_TOKEN",
+        "whatsapp": "WHATSAPP_ENABLED",
+        "signal": "SIGNAL_HTTP_URL",
+        "email": "EMAIL_ADDRESS",
+        "sms": "TWILIO_ACCOUNT_SID",
+        "matrix": "MATRIX_HOMESERVER_URL",
+        "mattermost": "MATTERMOST_URL",
+        "homeassistant": "HASS_TOKEN",
+        "dingtalk": "DINGTALK_CLIENT_ID",
+        "feishu": "FEISHU_APP_ID",
+        "wecom": "WECOM_BOT_ID",
+    }
+    return [name for name, env in checks.items() if os.getenv(env)]
+
+
+def _memory_provider(config: dict) -> str:
+    """Return the active memory provider name."""
+    mem = config.get("memory", {})
+    provider = mem.get("provider", "")
+    return provider if provider else "built-in"
+
+
+def _get_model_and_provider(config: dict) -> tuple[str, str]:
+    """Extract model and provider from config."""
+    model_cfg = config.get("model", "")
+    if isinstance(model_cfg, dict):
+        model = model_cfg.get("default") or model_cfg.get("model") or model_cfg.get("name") or "(not set)"
+        provider = model_cfg.get("provider") or "(auto)"
+    elif isinstance(model_cfg, str):
+        model = model_cfg or "(not set)"
+        provider = "(auto)"
+    else:
+        model = "(not set)"
+        provider = "(auto)"
+    return model, provider
+
+
+def _config_overrides(config: dict) -> dict[str, str]:
+    """Find non-default config values worth reporting.
+    
+    Returns a flat dict of dotpath -> value for interesting overrides.
+    """
+    from hermes_cli.config import DEFAULT_CONFIG
+
+    overrides = {}
+
+    # Sections with interesting user-facing overrides
+    interesting_paths = [
+        ("agent", "max_turns"),
+        ("agent", "gateway_timeout"),
+        ("agent", "tool_use_enforcement"),
+        ("terminal", "backend"),
+        ("terminal", "docker_image"),
+        ("terminal", "persistent_shell"),
+        ("browser", "allow_private_urls"),
+        ("compression", "enabled"),
+        ("compression", "threshold"),
+        ("display", "streaming"),
+        ("display", "skin"),
+        ("display", "show_reasoning"),
+        ("smart_model_routing", "enabled"),
+        ("privacy", "redact_pii"),
+        ("tts", "provider"),
+    ]
+
+    for section, key in interesting_paths:
+        default_section = DEFAULT_CONFIG.get(section, {})
+        user_section = config.get(section, {})
+        if not isinstance(default_section, dict) or not isinstance(user_section, dict):
+            continue
+        default_val = default_section.get(key)
+        user_val = user_section.get(key)
+        if user_val is not None and user_val != default_val:
+            overrides[f"{section}.{key}"] = str(user_val)
+
+    # Toolsets (if different from default)
+    default_toolsets = DEFAULT_CONFIG.get("toolsets", [])
+    user_toolsets = config.get("toolsets", [])
+    if user_toolsets != default_toolsets:
+        overrides["toolsets"] = str(user_toolsets)
+
+    # Fallback providers
+    fallbacks = config.get("fallback_providers", [])
+    if fallbacks:
+        overrides["fallback_providers"] = str(fallbacks)
+
+    return overrides
+
+
+def run_dump(args):
+    """Output a compact, copy-pasteable setup summary."""
+    show_keys = getattr(args, "show_keys", False)
+
+    # Load env from .env file so key checks work
+    from dotenv import load_dotenv
+    env_path = get_env_path()
+    if env_path.exists():
+        try:
+            load_dotenv(env_path, encoding="utf-8")
+        except UnicodeDecodeError:
+            load_dotenv(env_path, encoding="latin-1")
+    # Also try project .env as dev fallback
+    load_dotenv(get_project_root() / ".env", override=False, encoding="utf-8")
+
+    project_root = get_project_root()
+    hermes_home = get_hermes_home()
+
+    try:
+        from hermes_cli import __version__, __release_date__
+    except ImportError:
+        __version__ = "(unknown)"
+        __release_date__ = ""
+
+    commit = _get_git_commit(project_root)
+
+    try:
+        config = load_config()
+    except Exception:
+        config = {}
+
+    model, provider = _get_model_and_provider(config)
+
+    # Profile
+    try:
+        from hermes_cli.profiles import get_active_profile_name
+        profile = get_active_profile_name() or "(default)"
+    except Exception:
+        profile = "(default)"
+
+    # Terminal backend
+    terminal_cfg = config.get("terminal", {})
+    backend = terminal_cfg.get("backend", "local")
+
+    # OpenAI SDK version
+    try:
+        import openai
+        openai_ver = openai.__version__
+    except ImportError:
+        openai_ver = "not installed"
+
+    # OS info
+    os_info = f"{platform.system()} {platform.release()} {platform.machine()}"
+
+    lines = []
+    lines.append("--- hermes dump ---")
+    ver_str = f"{__version__}"
+    if __release_date__:
+        ver_str += f" ({__release_date__})"
+    ver_str += f" [{commit}]"
+    lines.append(f"version:          {ver_str}")
+    lines.append(f"os:               {os_info}")
+    lines.append(f"python:           {sys.version.split()[0]}")
+    lines.append(f"openai_sdk:       {openai_ver}")
+    lines.append(f"profile:          {profile}")
+    lines.append(f"hermes_home:      {display_hermes_home()}")
+    lines.append(f"model:            {model}")
+    lines.append(f"provider:         {provider}")
+    lines.append(f"terminal:         {backend}")
+
+    # API keys
+    lines.append("")
+    lines.append("api_keys:")
+    api_keys = [
+        ("OPENROUTER_API_KEY", "openrouter"),
+        ("OPENAI_API_KEY", "openai"),
+        ("ANTHROPIC_API_KEY", "anthropic"),
+        ("ANTHROPIC_TOKEN", "anthropic_token"),
+        ("NOUS_API_KEY", "nous"),
+        ("GLM_API_KEY", "glm/zai"),
+        ("ZAI_API_KEY", "zai"),
+        ("KIMI_API_KEY", "kimi"),
+        ("MINIMAX_API_KEY", "minimax"),
+        ("DEEPSEEK_API_KEY", "deepseek"),
+        ("DASHSCOPE_API_KEY", "dashscope"),
+        ("HF_TOKEN", "huggingface"),
+        ("AI_GATEWAY_API_KEY", "ai_gateway"),
+        ("OPENCODE_ZEN_API_KEY", "opencode_zen"),
+        ("OPENCODE_GO_API_KEY", "opencode_go"),
+        ("KILOCODE_API_KEY", "kilocode"),
+        ("FIRECRAWL_API_KEY", "firecrawl"),
+        ("TAVILY_API_KEY", "tavily"),
+        ("BROWSERBASE_API_KEY", "browserbase"),
+        ("FAL_KEY", "fal"),
+        ("ELEVENLABS_API_KEY", "elevenlabs"),
+        ("GITHUB_TOKEN", "github"),
+    ]
+
+    for env_var, label in api_keys:
+        val = os.getenv(env_var, "")
+        if show_keys and val:
+            display = _redact(val)
+        else:
+            display = "set" if val else "not set"
+        lines.append(f"  {label:<20} {display}")
+
+    # Features summary
+    lines.append("")
+    lines.append("features:")
+
+    toolsets = config.get("toolsets", ["hermes-cli"])
+    lines.append(f"  toolsets:           {', '.join(toolsets) if toolsets else '(default)'}")
+    lines.append(f"  mcp_servers:        {_count_mcp_servers(config)}")
+    lines.append(f"  memory_provider:    {_memory_provider(config)}")
+    lines.append(f"  gateway:            {_gateway_status()}")
+
+    platforms = _configured_platforms()
+    lines.append(f"  platforms:          {', '.join(platforms) if platforms else 'none'}")
+    lines.append(f"  cron_jobs:          {_cron_summary(hermes_home)}")
+    lines.append(f"  skills:             {_count_skills(hermes_home)}")
+
+    # Config overrides (non-default values)
+    overrides = _config_overrides(config)
+    if overrides:
+        lines.append("")
+        lines.append("config_overrides:")
+        for key, val in overrides.items():
+            lines.append(f"  {key}: {val}")
+
+    lines.append("--- end dump ---")
+
+    output = "\n".join(lines)
+    print(output)
@@ -14,6 +14,7 @@ from pathlib import Path

 PROJECT_ROOT = Path(__file__).parent.parent.resolve()

+from gateway.status import terminate_pid
 from hermes_cli.config import get_env_value, get_hermes_home, save_env_value, is_managed, managed_error
 # display_hermes_home is imported lazily at call sites to avoid ImportError
 # when hermes_constants is cached from a pre-update version during `hermes update`.
@@ -39,7 +40,7 @@ def _get_service_pids() -> set:
    pids: set = set()

    # --- systemd (Linux): user and system scopes ---
-    if is_linux():
+    if supports_systemd_services():
        for scope_args in [["systemctl", "--user"], ["systemctl"]]:
            try:
                result = subprocess.run(
@@ -162,7 +163,7 @@ def kill_gateway_processes(force: bool = False, exclude_pids: set | None = None)
    """Kill any running gateway processes. Returns count killed.

    Args:
-        force: Use SIGKILL instead of SIGTERM.
+        force: Use the platform's force-kill mechanism instead of graceful terminate.
        exclude_pids: PIDs to skip (e.g. service-managed PIDs that were just
            restarted and should not be killed).
    """
@@ -171,10 +172,7 @@ def kill_gateway_processes(force: bool = False, exclude_pids: set | None = None)
    
    for pid in pids:
        try:
-            if force and not is_windows():
-                os.kill(pid, signal.SIGKILL)
-            else:
-                os.kill(pid, signal.SIGTERM)
+            terminate_pid(pid, force=force)
            killed += 1
        except ProcessLookupError:
            # Process already gone
@@ -182,6 +180,8 @@ def kill_gateway_processes(force: bool = False, exclude_pids: set | None = None)
        except PermissionError:
            print(f"⚠ Permission denied to kill PID {pid}")
    
+        except OSError as exc:
+            print(f"Failed to kill PID {pid}: {exc}")
    return killed


@@ -225,6 +225,14 @@ def stop_profile_gateway() -> bool:
 def is_linux() -> bool:
    return sys.platform.startswith('linux')

+
+from hermes_constants import is_termux
+
+
+def supports_systemd_services() -> bool:
+    return is_linux() and not is_termux()
+
+
 def is_macos() -> bool:
    return sys.platform == 'darwin'

@@ -267,6 +275,34 @@ def _profile_suffix() -> str:
    return hashlib.sha256(str(home).encode()).hexdigest()[:8]


+def _profile_arg(hermes_home: str | None = None) -> str:
+    """Return ``--profile <name>`` only when HERMES_HOME is a named profile.
+
+    For ``~/.hermes/profiles/<name>``, returns ``"--profile <name>"``.
+    For the default profile or hash-based custom paths, returns the empty string.
+
+    Args:
+        hermes_home: Optional explicit HERMES_HOME path. Defaults to the current
+            ``get_hermes_home()`` value. Should be passed when generating a
+            service definition for a different user (e.g. system service).
+    """
+    import re
+    from pathlib import Path as _Path
+    home = Path(hermes_home or str(get_hermes_home())).resolve()
+    default = (_Path.home() / ".hermes").resolve()
+    if home == default:
+        return ""
+    profiles_root = (default / "profiles").resolve()
+    try:
+        rel = home.relative_to(profiles_root)
+        parts = rel.parts
+        if len(parts) == 1 and re.match(r"^[a-z0-9][a-z0-9_-]{0,63}$", parts[0]):
+            return f"--profile {parts[0]}"
+    except ValueError:
+        pass
+    return ""
+
+
 def get_service_name() -> str:
    """Derive a systemd service name scoped to this HERMES_HOME.

@@ -280,8 +316,6 @@ def get_service_name() -> str:
    return f"{_SERVICE_BASE}-{suffix}"


-SERVICE_NAME = _SERVICE_BASE  # backward-compat for external importers; prefer get_service_name()
-

 def get_systemd_unit_path(system: bool = False) -> Path:
    name = get_service_name()
@@ -449,13 +483,15 @@ def install_linux_gateway_from_setup(force: bool = False) -> tuple[str | None, b


 def get_systemd_linger_status() -> tuple[bool | None, str]:
-    """Return whether systemd user lingering is enabled for the current user.
+    """Return systemd linger status for the current user.

    Returns:
        (True, "") when linger is enabled.
        (False, "") when linger is disabled.
        (None, detail) when the status could not be determined.
    """
+    if is_termux():
+        return None, "not supported in Termux"
    if not is_linux():
        return None, "not supported on this platform"

@@ -553,17 +589,6 @@ def get_python_path() -> str:
            return str(venv_python)
    return sys.executable

-def get_hermes_cli_path() -> str:
-    """Get the path to the hermes CLI."""
-    # Check if installed via pip
-    import shutil
-    hermes_bin = shutil.which("hermes")
-    if hermes_bin:
-        return hermes_bin
-    
-    # Fallback to direct module execution
-    return f"{get_python_path()} -m hermes_cli.main"
-

 # =============================================================================
 # Systemd (Linux)
@@ -580,6 +605,24 @@ def _build_user_local_paths(home: Path, path_entries: list[str]) -> list[str]:
    return [p for p in candidates if p not in path_entries and Path(p).exists()]


+def _remap_path_for_user(path: str, target_home_dir: str) -> str:
+    """Remap *path* from the current user's home to *target_home_dir*.
+
+    If *path* lives under ``Path.home()`` the corresponding prefix is swapped
+    to *target_home_dir*; otherwise the path is returned unchanged.
+
+      /root/.hermes/hermes-agent  -> /home/alice/.hermes/hermes-agent
+      /opt/hermes                 -> /opt/hermes  (kept as-is)
+    """
+    current_home = Path.home().resolve()
+    resolved = Path(path).resolve()
+    try:
+        relative = resolved.relative_to(current_home)
+        return str(Path(target_home_dir) / relative)
+    except ValueError:
+        return str(resolved)
+
+
 def _hermes_home_for_target_user(target_home_dir: str) -> str:
    """Remap the current HERMES_HOME to the equivalent under a target user's home.

@@ -626,6 +669,16 @@ def generate_systemd_unit(system: bool = False, run_as_user: str | None = None)
    if system:
        username, group_name, home_dir = _system_service_identity(run_as_user)
        hermes_home = _hermes_home_for_target_user(home_dir)
+        profile_arg = _profile_arg(hermes_home)
+        # Remap all paths that may resolve under the calling user's home
+        # (e.g. /root/) to the target user's home so the service can
+        # actually access them.
+        python_path = _remap_path_for_user(python_path, home_dir)
+        working_dir = _remap_path_for_user(working_dir, home_dir)
+        venv_dir = _remap_path_for_user(venv_dir, home_dir)
+        venv_bin = _remap_path_for_user(venv_bin, home_dir)
+        node_bin = _remap_path_for_user(node_bin, home_dir)
+        path_entries = [_remap_path_for_user(p, home_dir) for p in path_entries]
        path_entries.extend(_build_user_local_paths(Path(home_dir), path_entries))
        path_entries.extend(common_bin_paths)
        sane_path = ":".join(path_entries)
@@ -640,7 +693,7 @@ StartLimitBurst=5
 Type=simple
 User={username}
 Group={group_name}
-ExecStart={python_path} -m hermes_cli.main gateway run --replace
+ExecStart={python_path} -m hermes_cli.main{f" {profile_arg}" if profile_arg else ""} gateway run --replace
 WorkingDirectory={working_dir}
 Environment="HOME={home_dir}"
 Environment="USER={username}"
@@ -661,6 +714,7 @@ WantedBy=multi-user.target
 """

    hermes_home = str(get_hermes_home().resolve())
+    profile_arg = _profile_arg(hermes_home)
    path_entries.extend(_build_user_local_paths(Path.home(), path_entries))
    path_entries.extend(common_bin_paths)
    sane_path = ":".join(path_entries)
@@ -672,7 +726,7 @@ StartLimitBurst=5

 [Service]
 Type=simple
-ExecStart={python_path} -m hermes_cli.main gateway run --replace
+ExecStart={python_path} -m hermes_cli.main{f" {profile_arg}" if profile_arg else ""} gateway run --replace
 WorkingDirectory={working_dir}
 Environment="PATH={sane_path}"
 Environment="VIRTUAL_ENV={venv_dir}"
@@ -736,7 +790,7 @@ def _print_linger_enable_warning(username: str, detail: str | None = None) -> No

 def _ensure_linger_enabled() -> None:
    """Enable linger when possible so the user gateway survives logout."""
-    if not is_linux():
+    if is_termux() or not is_linux():
        return

    import getpass
@@ -965,6 +1019,7 @@ def generate_launchd_plist() -> str:
    log_dir = get_hermes_home() / "logs"
    log_dir.mkdir(parents=True, exist_ok=True)
    label = get_launchd_label()
+    profile_arg = _profile_arg(hermes_home)
    # Build a sane PATH for the launchd plist.  launchd provides only a
    # minimal default (/usr/bin:/bin:/usr/sbin:/sbin) which misses Homebrew,
    # nvm, cargo, etc.  We prepend venv/bin and node_modules/.bin (matching
@@ -986,21 +1041,32 @@ def generate_launchd_plist() -> str:
        dict.fromkeys(priority_dirs + [p for p in os.environ.get("PATH", "").split(":") if p])
    )

+    # Build ProgramArguments array, including --profile when using a named profile
+    prog_args = [
+        f"<string>{python_path}</string>",
+        "<string>-m</string>",
+        "<string>hermes_cli.main</string>",
+    ]
+    if profile_arg:
+        for part in profile_arg.split():
+            prog_args.append(f"<string>{part}</string>")
+    prog_args.extend([
+        "<string>gateway</string>",
+        "<string>run</string>",
+        "<string>--replace</string>",
+    ])
+    prog_args_xml = "\n        ".join(prog_args)
+
    return f"""<?xml version="1.0" encoding="UTF-8"?>
 <!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
 <plist version="1.0">
 <dict>
    <key>Label</key>
    <string>{label}</string>
-    
+
    <key>ProgramArguments</key>
    <array>
-        <string>{python_path}</string>
-        <string>-m</string>
-        <string>hermes_cli.main</string>
-        <string>gateway</string>
-        <string>run</string>
-        <string>--replace</string>
+        {prog_args_xml}
    </array>
    
    <key>WorkingDirectory</key>
@@ -1130,7 +1196,19 @@ def launchd_start():

 def launchd_stop():
    label = get_launchd_label()
-    subprocess.run(["launchctl", "kill", "SIGTERM", f"{_launchd_domain()}/{label}"], check=True, timeout=30)
+    target = f"{_launchd_domain()}/{label}"
+    # bootout unloads the service definition so KeepAlive doesn't respawn
+    # the process.  A plain `kill SIGTERM` only signals the process — launchd
+    # immediately restarts it because KeepAlive.SuccessfulExit = false.
+    # `hermes gateway start` re-bootstraps when it detects the job is unloaded.
+    try:
+        subprocess.run(["launchctl", "bootout", target], check=True, timeout=90)
+    except subprocess.CalledProcessError as e:
+        if e.returncode in (3, 113):
+            pass  # Already unloaded — nothing to stop.
+        else:
+            raise
+    _wait_for_gateway_exit(timeout=10.0, force_after=5.0)
    print("✓ Service stopped")

 def _wait_for_gateway_exit(timeout: float = 10.0, force_after: float = 5.0):
@@ -1142,7 +1220,7 @@ def _wait_for_gateway_exit(timeout: float = 10.0, force_after: float = 5.0):

    Args:
        timeout: Total seconds to wait before giving up.
-        force_after: Seconds of graceful waiting before sending SIGKILL.
+        force_after: Seconds of graceful waiting before escalating to force-kill.
    """
    import time
    from gateway.status import get_running_pid
@@ -1159,15 +1237,15 @@ def _wait_for_gateway_exit(timeout: float = 10.0, force_after: float = 5.0):
        if not force_sent and time.monotonic() >= force_deadline:
            # Grace period expired — force-kill the specific PID.
            try:
-                os.kill(pid, signal.SIGKILL)
+                terminate_pid(pid, force=True)
                print(f"⚠ Gateway PID {pid} did not exit gracefully; sent SIGKILL")
-            except (ProcessLookupError, PermissionError):
+            except (ProcessLookupError, PermissionError, OSError):
                return  # Already gone or we can't touch it.
            force_sent = True

        time.sleep(0.3)

-    # Timed out even after SIGKILL.
+    # Timed out even after force-kill.
    remaining_pid = get_running_pid()
    if remaining_pid is not None:
        print(f"⚠ Gateway PID {remaining_pid} still running after {timeout}s — restart may fail")
@@ -1546,6 +1624,34 @@ _PLATFORMS = [
             "help": "Chat ID for scheduled results and notifications."},
        ],
    },
+    {
+        "key": "bluebubbles",
+        "label": "BlueBubbles (iMessage)",
+        "emoji": "💬",
+        "token_var": "BLUEBUBBLES_SERVER_URL",
+        "setup_instructions": [
+            "1. Install BlueBubbles on a Mac that will act as your iMessage server:",
+            "   https://bluebubbles.app/",
+            "2. Complete the BlueBubbles setup wizard — sign in with your Apple ID",
+            "3. In BlueBubbles Settings → API, note the Server URL and password",
+            "4. The server URL is typically http://<your-mac-ip>:1234",
+            "5. Hermes connects via the BlueBubbles REST API and receives",
+            "   incoming messages via a local webhook",
+            "6. To authorize users, use DM pairing: hermes pairing generate bluebubbles",
+            "   Share the code — the user sends it via iMessage to get approved",
+        ],
+        "vars": [
+            {"name": "BLUEBUBBLES_SERVER_URL", "prompt": "BlueBubbles server URL (e.g. http://192.168.1.10:1234)", "password": False,
+             "help": "The URL shown in BlueBubbles Settings → API."},
+            {"name": "BLUEBUBBLES_PASSWORD", "prompt": "BlueBubbles server password", "password": True,
+             "help": "The password shown in BlueBubbles Settings → API."},
+            {"name": "BLUEBUBBLES_ALLOWED_USERS", "prompt": "Pre-authorized phone numbers or iMessage IDs (comma-separated, or leave empty for DM pairing)", "password": False,
+             "is_allowlist": True,
+             "help": "Optional — pre-authorize specific users. Leave empty to use DM pairing instead (recommended)."},
+            {"name": "BLUEBUBBLES_HOME_CHANNEL", "prompt": "Home channel (phone number or iMessage ID for cron/notifications, or empty)", "password": False,
+             "help": "Phone number or Apple ID to deliver cron results and notifications to."},
+        ],
+    },
 ]


@@ -1731,7 +1837,7 @@ def _setup_whatsapp():

 def _is_service_installed() -> bool:
    """Check if the gateway is installed as a system service."""
-    if is_linux():
+    if supports_systemd_services():
        return get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()
    elif is_macos():
        return get_launchd_plist_path().exists()
@@ -1740,7 +1846,7 @@ def _is_service_installed() -> bool:

 def _is_service_running() -> bool:
    """Check if the gateway service is currently running."""
-    if is_linux():
+    if supports_systemd_services():
        user_unit_exists = get_systemd_unit_path(system=False).exists()
        system_unit_exists = get_systemd_unit_path(system=True).exists()

@@ -1913,7 +2019,7 @@ def gateway_setup():
    service_installed = _is_service_installed()
    service_running = _is_service_running()

-    if is_linux() and has_conflicting_systemd_units():
+    if supports_systemd_services() and has_conflicting_systemd_units():
        print_systemd_scope_conflict_warning()
        print()

@@ -1923,7 +2029,7 @@ def gateway_setup():
        print_warning("Gateway service is installed but not running.")
        if prompt_yes_no("  Start it now?", True):
            try:
-                if is_linux():
+                if supports_systemd_services():
                    systemd_start()
                elif is_macos():
                    launchd_start()
@@ -1974,7 +2080,7 @@ def gateway_setup():
        if service_running:
            if prompt_yes_no("  Restart the gateway to pick up changes?", True):
                try:
-                    if is_linux():
+                    if supports_systemd_services():
                        systemd_restart()
                    elif is_macos():
                        launchd_restart()
@@ -1986,7 +2092,7 @@ def gateway_setup():
        elif service_installed:
            if prompt_yes_no("  Start the gateway service?", True):
                try:
-                    if is_linux():
+                    if supports_systemd_services():
                        systemd_start()
                    elif is_macos():
                        launchd_start()
@@ -1994,13 +2100,13 @@ def gateway_setup():
                    print_error(f"  Start failed: {e}")
        else:
            print()
-            if is_linux() or is_macos():
-                platform_name = "systemd" if is_linux() else "launchd"
+            if supports_systemd_services() or is_macos():
+                platform_name = "systemd" if supports_systemd_services() else "launchd"
                if prompt_yes_no(f"  Install the gateway as a {platform_name} service? (runs in background, starts on boot)", True):
                    try:
                        installed_scope = None
                        did_install = False
-                        if is_linux():
+                        if supports_systemd_services():
                            installed_scope, did_install = install_linux_gateway_from_setup(force=False)
                        else:
                            launchd_install(force=False)
@@ -2008,7 +2114,7 @@ def gateway_setup():
                        print()
                        if did_install and prompt_yes_no("  Start the service now?", True):
                            try:
-                                if is_linux():
+                                if supports_systemd_services():
                                    systemd_start(system=installed_scope == "system")
                                else:
                                    launchd_start()
@@ -2019,12 +2125,18 @@ def gateway_setup():
                        print_info("  You can try manually: hermes gateway install")
                else:
                    print_info("  You can install later: hermes gateway install")
-                    if is_linux():
+                    if supports_systemd_services():
                        print_info("  Or as a boot-time service: sudo hermes gateway install --system")
                    print_info("  Or run in foreground:  hermes gateway")
            else:
-                print_info("  Service install not supported on this platform.")
-                print_info("  Run in foreground: hermes gateway")
+                if is_termux():
+                    from hermes_constants import display_hermes_home as _dhh
+                    print_info("  Termux does not use systemd/launchd services.")
+                    print_info("  Run in foreground: hermes gateway")
+                    print_info(f"  Or start it manually in the background (best effort): nohup hermes gateway >{_dhh()}/logs/gateway.log 2>&1 &")
+                else:
+                    print_info("  Service install not supported on this platform.")
+                    print_info("  Run in foreground: hermes gateway")
    else:
        print()
        print_info("No platforms configured. Run 'hermes gateway setup' when ready.")
@@ -2060,7 +2172,11 @@ def gateway_command(args):
        force = getattr(args, 'force', False)
        system = getattr(args, 'system', False)
        run_as_user = getattr(args, 'run_as_user', None)
-        if is_linux():
+        if is_termux():
+            print("Gateway service installation is not supported on Termux.")
+            print("Run manually: hermes gateway")
+            sys.exit(1)
+        if supports_systemd_services():
            systemd_install(force=force, system=system, run_as_user=run_as_user)
        elif is_macos():
            launchd_install(force)
@@ -2074,7 +2190,11 @@ def gateway_command(args):
            managed_error("uninstall gateway service (managed by NixOS)")
            return
        system = getattr(args, 'system', False)
-        if is_linux():
+        if is_termux():
+            print("Gateway service uninstall is not supported on Termux because there is no managed service to remove.")
+            print("Stop manual runs with: hermes gateway stop")
+            sys.exit(1)
+        if supports_systemd_services():
            systemd_uninstall(system=system)
        elif is_macos():
            launchd_uninstall()
@@ -2084,7 +2204,11 @@ def gateway_command(args):
    
    elif subcmd == "start":
        system = getattr(args, 'system', False)
-        if is_linux():
+        if is_termux():
+            print("Gateway service start is not supported on Termux because there is no system service manager.")
+            print("Run manually: hermes gateway")
+            sys.exit(1)
+        if supports_systemd_services():
            systemd_start(system=system)
        elif is_macos():
            launchd_start()
@@ -2099,7 +2223,7 @@ def gateway_command(args):
        if stop_all:
            # --all: kill every gateway process on the machine
            service_available = False
-            if is_linux() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
+            if supports_systemd_services() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
                try:
                    systemd_stop(system=system)
                    service_available = True
@@ -2120,7 +2244,7 @@ def gateway_command(args):
        else:
            # Default: stop only the current profile's gateway
            service_available = False
-            if is_linux() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
+            if supports_systemd_services() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
                try:
                    systemd_stop(system=system)
                    service_available = True
@@ -2148,7 +2272,7 @@ def gateway_command(args):
        system = getattr(args, 'system', False)
        service_configured = False
        
-        if is_linux() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
+        if supports_systemd_services() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
            service_configured = True
            try:
                systemd_restart(system=system)
@@ -2165,7 +2289,7 @@ def gateway_command(args):
        
        if not service_available:
            # systemd/launchd restart failed — check if linger is the issue
-            if is_linux():
+            if supports_systemd_services():
                linger_ok, _detail = get_systemd_linger_status()
                if linger_ok is not True:
                    import getpass
@@ -2202,7 +2326,7 @@ def gateway_command(args):
        system = getattr(args, 'system', False)
        
        # Check for service first
-        if is_linux() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
+        if supports_systemd_services() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
            systemd_status(deep, system=system)
        elif is_macos() and get_launchd_plist_path().exists():
            launchd_status(deep)
@@ -2219,9 +2343,13 @@ def gateway_command(args):
                    for line in runtime_lines:
                        print(f"  {line}")
                print()
-                print("To install as a service:")
-                print("  hermes gateway install")
-                print("  sudo hermes gateway install --system")
+                if is_termux():
+                    print("Termux note:")
+                    print("  Android may stop background jobs when Termux is suspended")
+                else:
+                    print("To install as a service:")
+                    print("  hermes gateway install")
+                    print("  sudo hermes gateway install --system")
            else:
                print("✗ Gateway is not running")
                runtime_lines = _runtime_health_lines()
@@ -2233,5 +2361,8 @@ def gateway_command(args):
                print()
                print("To start:")
                print("  hermes gateway          # Run in foreground")
-                print("  hermes gateway install  # Install as user service")
-                print("  sudo hermes gateway install --system  # Install as boot-time system service")
+                if is_termux():
+                    print("  nohup hermes gateway > ~/.hermes/logs/gateway.log 2>&1 &  # Best-effort background start")
+                else:
+                    print("  hermes gateway install  # Install as user service")
+                    print("  sudo hermes gateway install --system  # Install as boot-time system service")
@@ -646,6 +646,7 @@ def cmd_chat(args):
        "verbose": args.verbose,
        "quiet": getattr(args, "quiet", False),
        "query": args.query,
+        "image": getattr(args, "image", None),
        "resume": getattr(args, "resume", None),
        "worktree": getattr(args, "worktree", False),
        "checkpoints": getattr(args, "checkpoints", False),
@@ -857,7 +858,6 @@ def cmd_whatsapp(args):

 def cmd_setup(args):
    """Interactive setup wizard."""
-    _require_tty("setup")
    from hermes_cli.setup import run_setup_wizard
    run_setup_wizard(args)

@@ -918,6 +918,7 @@ def select_provider_and_model(args=None):
        "openrouter": "OpenRouter",
        "nous": "Nous Portal",
        "openai-codex": "OpenAI Codex",
+        "qwen-oauth": "Qwen OAuth",
        "copilot-acp": "GitHub Copilot ACP",
        "copilot": "GitHub Copilot",
        "anthropic": "Anthropic",
@@ -947,6 +948,7 @@ def select_provider_and_model(args=None):
        ("openrouter", "OpenRouter (100+ models, pay-per-use)"),
        ("anthropic", "Anthropic (Claude models — API key or Claude Code)"),
        ("openai-codex", "OpenAI Codex"),
+        ("qwen-oauth", "Qwen OAuth (reuses local Qwen CLI login)"),
        ("copilot", "GitHub Copilot (uses GITHUB_TOKEN or gh auth token)"),
        ("huggingface", "Hugging Face Inference Providers (20+ open models)"),
    ]
@@ -965,10 +967,11 @@ def select_provider_and_model(args=None):
        ("alibaba", "Alibaba Cloud / DashScope Coding (Qwen + multi-provider)"),
    ]

-    # Add user-defined custom providers from config.yaml
-    custom_providers_cfg = config.get("custom_providers") or []
-    _custom_provider_map = {}  # key → {name, base_url, api_key}
-    if isinstance(custom_providers_cfg, list):
+    def _named_custom_provider_map(cfg) -> dict[str, dict[str, str]]:
+        custom_providers_cfg = cfg.get("custom_providers") or []
+        custom_provider_map = {}
+        if not isinstance(custom_providers_cfg, list):
+            return custom_provider_map
        for entry in custom_providers_cfg:
            if not isinstance(entry, dict):
                continue
@@ -977,16 +980,23 @@ def select_provider_and_model(args=None):
            if not name or not base_url:
                continue
            key = "custom:" + name.lower().replace(" ", "-")
-            short_url = base_url.replace("https://", "").replace("http://", "").rstrip("/")
-            saved_model = entry.get("model", "")
-            model_hint = f" — {saved_model}" if saved_model else ""
-            top_providers.append((key, f"{name} ({short_url}){model_hint}"))
-            _custom_provider_map[key] = {
+            custom_provider_map[key] = {
                "name": name,
                "base_url": base_url,
                "api_key": entry.get("api_key", ""),
-                "model": saved_model,
+                "model": entry.get("model", ""),
            }
+        return custom_provider_map
+
+    # Add user-defined custom providers from config.yaml
+    _custom_provider_map = _named_custom_provider_map(config)  # key → {name, base_url, api_key}
+    for key, provider_info in _custom_provider_map.items():
+        name = provider_info["name"]
+        base_url = provider_info["base_url"]
+        short_url = base_url.replace("https://", "").replace("http://", "").rstrip("/")
+        saved_model = provider_info.get("model", "")
+        model_hint = f" — {saved_model}" if saved_model else ""
+        top_providers.append((key, f"{name} ({short_url}){model_hint}"))

    top_keys = {k for k, _ in top_providers}
    extended_keys = {k for k, _ in extended_providers}
@@ -1043,14 +1053,23 @@ def select_provider_and_model(args=None):
        _model_flow_nous(config, current_model, args=args)
    elif selected_provider == "openai-codex":
        _model_flow_openai_codex(config, current_model)
+    elif selected_provider == "qwen-oauth":
+        _model_flow_qwen_oauth(config, current_model)
    elif selected_provider == "copilot-acp":
        _model_flow_copilot_acp(config, current_model)
    elif selected_provider == "copilot":
        _model_flow_copilot(config, current_model)
    elif selected_provider == "custom":
        _model_flow_custom(config)
-    elif selected_provider.startswith("custom:") and selected_provider in _custom_provider_map:
-        _model_flow_named_custom(config, _custom_provider_map[selected_provider])
+    elif selected_provider.startswith("custom:"):
+        provider_info = _named_custom_provider_map(load_config()).get(selected_provider)
+        if provider_info is None:
+            print(
+                "Warning: the selected saved custom provider is no longer available. "
+                "It may have been removed from config.yaml. No change."
+            )
+            return
+        _model_flow_named_custom(config, provider_info)
    elif selected_provider == "remove-custom":
        _remove_custom_provider(config)
    elif selected_provider == "anthropic":
@@ -1123,10 +1142,10 @@ def _model_flow_openrouter(config, current_model=""):
        print()

    from hermes_cli.models import model_ids, get_pricing_for_provider
-    openrouter_models = model_ids()
+    openrouter_models = model_ids(force_refresh=True)

    # Fetch live pricing (non-blocking — returns empty dict on failure)
-    pricing = get_pricing_for_provider("openrouter")
+    pricing = get_pricing_for_provider("openrouter", force_refresh=True)

    selected = _prompt_model_selection(openrouter_models, current_model=current_model, pricing=pricing)
    if selected:
@@ -1359,6 +1378,56 @@ def _model_flow_openai_codex(config, current_model=""):



+_DEFAULT_QWEN_PORTAL_MODELS = [
+    "qwen3-coder-plus",
+    "qwen3-coder",
+]
+
+
+def _model_flow_qwen_oauth(_config, current_model=""):
+    """Qwen OAuth provider: reuse local Qwen CLI login, then pick model."""
+    from hermes_cli.auth import (
+        get_qwen_auth_status,
+        resolve_qwen_runtime_credentials,
+        _prompt_model_selection,
+        _save_model_choice,
+        _update_config_for_provider,
+        DEFAULT_QWEN_BASE_URL,
+    )
+    from hermes_cli.models import fetch_api_models
+
+    status = get_qwen_auth_status()
+    if not status.get("logged_in"):
+        print("Not logged into Qwen CLI OAuth.")
+        print("Run: qwen auth qwen-oauth")
+        auth_file = status.get("auth_file")
+        if auth_file:
+            print(f"Expected credentials file: {auth_file}")
+        if status.get("error"):
+            print(f"Error: {status.get('error')}")
+        return
+
+    # Try live model discovery, fall back to curated list.
+    models = None
+    try:
+        creds = resolve_qwen_runtime_credentials(refresh_if_expiring=True)
+        models = fetch_api_models(creds["api_key"], creds["base_url"])
+    except Exception:
+        pass
+    if not models:
+        models = list(_DEFAULT_QWEN_PORTAL_MODELS)
+
+    default = current_model or (models[0] if models else "qwen3-coder-plus")
+    selected = _prompt_model_selection(models, current_model=default)
+    if selected:
+        _save_model_choice(selected)
+        _update_config_for_provider("qwen-oauth", DEFAULT_QWEN_BASE_URL)
+        print(f"Default model set to: {selected} (via Qwen OAuth)")
+    else:
+        print("No change.")
+
+
+
 def _model_flow_custom(config):
    """Custom endpoint: collect URL, API key, and model name.

@@ -1420,7 +1489,11 @@ def _model_flow_custom(config):
            f"Hermes will still save it."
        )
        if probe.get("suggested_base_url"):
-            print(f"  If this server expects /v1, try base URL: {probe['suggested_base_url']}")
+            suggested = probe["suggested_base_url"]
+            if suggested.endswith("/v1"):
+                print(f"  If this server expects /v1 in the path, try base URL: {suggested}")
+            else:
+                print(f"  If /v1 should not be in the base URL, try: {suggested}")

    # Select model — use probe results when available, fall back to manual input
    model_name = ""
@@ -1600,7 +1673,7 @@ def _remove_custom_provider(config):
        )
        idx = menu.show()
        print()
-    except (ImportError, NotImplementedError):
+    except (ImportError, NotImplementedError, OSError, subprocess.SubprocessError):
        for i, c in enumerate(choices, 1):
            print(f"  {i}. {c}")
        print()
@@ -1681,7 +1754,7 @@ def _model_flow_named_custom(config, provider_info):
                print("Cancelled.")
                return
            model_name = models[idx]
-        except (ImportError, NotImplementedError):
+        except (ImportError, NotImplementedError, OSError, subprocess.SubprocessError):
            for i, m in enumerate(models, 1):
                print(f"  {i}. {m}")
            print(f"  {len(models) + 1}. Cancel")
@@ -1753,7 +1826,10 @@ def _set_reasoning_effort(config, effort: str) -> None:

 def _prompt_reasoning_effort_selection(efforts, current_effort=""):
    """Prompt for a reasoning effort. Returns effort, 'none', or None to keep current."""
-    ordered = list(dict.fromkeys(str(effort).strip().lower() for effort in efforts if str(effort).strip()))
+    deduped = list(dict.fromkeys(str(effort).strip().lower() for effort in efforts if str(effort).strip()))
+    canonical_order = ("minimal", "low", "medium", "high", "xhigh")
+    ordered = [effort for effort in canonical_order if effort in deduped]
+    ordered.extend(effort for effort in deduped if effort not in canonical_order)
    if not ordered:
        return None

@@ -1799,7 +1875,7 @@ def _prompt_reasoning_effort_selection(efforts, current_effort=""):
        if idx == len(ordered):
            return "none"
        return None
-    except (ImportError, NotImplementedError):
+    except (ImportError, NotImplementedError, OSError, subprocess.SubprocessError):
        pass

    print("Select reasoning effort:")
@@ -2585,6 +2661,12 @@ def cmd_doctor(args):
    run_doctor(args)


+def cmd_dump(args):
+    """Dump setup summary for support/debugging."""
+    from hermes_cli.dump import run_dump
+    run_dump(args)
+
+
 def cmd_config(args):
    """Configuration management."""
    from hermes_cli.config import config_command
@@ -2954,33 +3036,19 @@ def _restore_stashed_changes(
        print("\nYour stashed changes are preserved — nothing is lost.")
        print(f"  Stash ref: {stash_ref}")

-        # Ask before resetting (if interactive)
-        do_reset = True
-        if prompt_user:
-            print("\nReset working tree to clean state so Hermes can run?")
-            print("  (You can re-apply your changes later with: git stash apply)")
-            print("[Y/n] ", end="", flush=True)
-            response = input().strip().lower()
-            if response not in ("", "y", "yes"):
-                do_reset = False
-
-        if do_reset:
-            subprocess.run(
-                git_cmd + ["reset", "--hard", "HEAD"],
-                cwd=cwd,
-                capture_output=True,
-            )
-            print("Working tree reset to clean state.")
-        else:
-            print("Working tree left as-is (may have conflict markers).")
-            print("Resolve conflicts manually, then run: git stash drop")
-
-        print(f"Restore your changes with: git stash apply {stash_ref}")
-        # In non-interactive mode (gateway /update), don't abort — the code
-        # update itself succeeded, only the stash restore had conflicts.
-        # Aborting would report the entire update as failed.
-        if prompt_user:
-            sys.exit(1)
+        # Always reset to clean state — leaving conflict markers in source
+        # files makes hermes completely unrunnable (SyntaxError on import).
+        # The user's changes are safe in the stash for manual recovery.
+        subprocess.run(
+            git_cmd + ["reset", "--hard", "HEAD"],
+            cwd=cwd,
+            capture_output=True,
+        )
+        print("Working tree reset to clean state.")
+        print(f"Restore your changes later with: git stash apply {stash_ref}")
+        # Don't sys.exit — the code update itself succeeded, only the stash
+        # restore had conflicts.  Let cmd_update continue with pip install,
+        # skill sync, and gateway restart.
        return False

    stash_selector = _resolve_stash_selector(git_cmd, cwd, stash_ref)
@@ -3696,7 +3764,7 @@ def cmd_update(args):
        # running gateway needs restarting to pick up the new code.
        try:
            from hermes_cli.gateway import (
-                is_macos, is_linux, _ensure_user_systemd_env,
+                is_macos, supports_systemd_services, _ensure_user_systemd_env,
                find_gateway_pids,
                _get_service_pids,
            )
@@ -3707,7 +3775,7 @@ def cmd_update(args):

            # --- Systemd services (Linux) ---
            # Discover all hermes-gateway* units (default + profiles)
-            if is_linux():
+            if supports_systemd_services():
                try:
                    _ensure_user_systemd_env()
                except Exception:
@@ -4224,6 +4292,10 @@ For more help on a command:
        "-q", "--query",
        help="Single query (non-interactive mode)"
    )
+    chat_parser.add_argument(
+        "--image",
+        help="Optional local image path to attach to a single query"
+    )
    chat_parser.add_argument(
        "-m", "--model",
        help="Model to use (e.g., anthropic/claude-sonnet-4)"
@@ -4414,12 +4486,12 @@ For more help on a command:
        "setup",
        help="Interactive setup wizard",
        description="Configure Hermes Agent with an interactive wizard. "
-                    "Run a specific section: hermes setup model|terminal|gateway|tools|agent"
+                    "Run a specific section: hermes setup model|tts|terminal|gateway|tools|agent"
    )
    setup_parser.add_argument(
        "section",
        nargs="?",
-        choices=["model", "terminal", "gateway", "tools", "agent"],
+        choices=["model", "tts", "terminal", "gateway", "tools", "agent"],
        default=None,
        help="Run a specific setup section instead of the full wizard"
    )
@@ -4666,6 +4738,22 @@ For more help on a command:
        help="Attempt to fix issues automatically"
    )
    doctor_parser.set_defaults(func=cmd_doctor)
+
+    # =========================================================================
+    # dump command
+    # =========================================================================
+    dump_parser = subparsers.add_parser(
+        "dump",
+        help="Dump setup summary for support/debugging",
+        description="Output a compact, plain-text summary of your Hermes setup "
+                    "that can be copy-pasted into Discord/GitHub for support context"
+    )
+    dump_parser.add_argument(
+        "--show-keys",
+        action="store_true",
+        help="Show redacted API key prefixes (first/last 4 chars) instead of just set/not set"
+    )
+    dump_parser.set_defaults(func=cmd_dump)
    
    # =========================================================================
    # config command
@@ -84,6 +84,7 @@ _PASSTHROUGH_PROVIDERS: frozenset[str] = frozenset({
    "minimax",
    "minimax-cn",
    "alibaba",
+    "qwen-oauth",
    "huggingface",
    "openai-codex",
    "custom",
@@ -331,31 +332,3 @@ def normalize_model_for_provider(model_input: str, target_provider: str) -> str:
 # Batch / convenience helpers
 # ---------------------------------------------------------------------------

-def model_display_name(model_id: str) -> str:
-    """Return a short, human-readable display name for a model id.
-
-    Strips the vendor prefix (if any) for a cleaner display in menus
-    and status bars, while preserving dots for readability.
-
-    Examples::
-
-        >>> model_display_name("anthropic/claude-sonnet-4.6")
-        'claude-sonnet-4.6'
-        >>> model_display_name("claude-sonnet-4-6")
-        'claude-sonnet-4-6'
-    """
-    return _strip_vendor_prefix((model_id or "").strip())
-
-
-def is_aggregator_provider(provider: str) -> bool:
-    """Check if a provider is an aggregator that needs vendor/model format."""
-    return (provider or "").strip().lower() in _AGGREGATOR_PROVIDERS
-
-
-def vendor_for_model(model_name: str) -> str:
-    """Return the vendor slug for a model, or ``""`` if unknown.
-
-    Convenience wrapper around :func:`detect_vendor` that never returns
-    ``None``.
-    """
-    return detect_vendor(model_name) or ""
@@ -25,6 +25,7 @@ from dataclasses import dataclass
 from typing import List, NamedTuple, Optional

 from hermes_cli.providers import (
+    custom_provider_slug,
    determine_api_mode,
    get_label,
    is_aggregator,
@@ -336,6 +337,7 @@ def resolve_alias(
 def get_authenticated_provider_slugs(
    current_provider: str = "",
    user_providers: dict = None,
+    custom_providers: list | None = None,
 ) -> list[str]:
    """Return slugs of providers that have credentials.

@@ -346,6 +348,7 @@ def get_authenticated_provider_slugs(
        providers = list_authenticated_providers(
            current_provider=current_provider,
            user_providers=user_providers,
+            custom_providers=custom_providers,
            max_models=0,
        )
        return [p["slug"] for p in providers]
@@ -383,6 +386,7 @@ def switch_model(
    is_global: bool = False,
    explicit_provider: str = "",
    user_providers: dict = None,
+    custom_providers: list | None = None,
 ) -> ModelSwitchResult:
    """Core model-switching pipeline shared between CLI and gateway.

@@ -416,6 +420,7 @@ def switch_model(
        is_global: Whether to persist the switch.
        explicit_provider: From --provider flag (empty = no explicit provider).
        user_providers: The ``providers:`` dict from config.yaml (for user endpoints).
+        custom_providers: The ``custom_providers:`` list from config.yaml.

    Returns:
        ModelSwitchResult with all information the caller needs.
@@ -436,7 +441,11 @@ def switch_model(
    # =================================================================
    if explicit_provider:
        # Resolve the provider
-        pdef = resolve_provider_full(explicit_provider, user_providers)
+        pdef = resolve_provider_full(
+            explicit_provider,
+            user_providers,
+            custom_providers,
+        )
        if pdef is None:
            _switch_err = (
                f"Unknown provider '{explicit_provider}'. "
@@ -516,6 +525,7 @@ def switch_model(
                authed = get_authenticated_provider_slugs(
                    current_provider=current_provider,
                    user_providers=user_providers,
+                    custom_providers=custom_providers,
                )
                fallback_result = _resolve_alias_fallback(raw_input, authed)
                if fallback_result is not None:
@@ -537,8 +547,11 @@ def switch_model(
                    )
            else:
                # --- Step c: On aggregator, convert vendor:model to vendor/model ---
+                # Only convert when there's no slash — a slash means the name
+                # is already in vendor/model format and the colon is a variant
+                # tag (:free, :extended, :fast) that must be preserved.
                colon_pos = raw_input.find(":")
-                if colon_pos > 0 and is_aggregator(current_provider):
+                if colon_pos > 0 and "/" not in raw_input and is_aggregator(current_provider):
                    left = raw_input[:colon_pos].strip().lower()
                    right = raw_input[colon_pos + 1:].strip()
                    if left and right:
@@ -587,6 +600,14 @@ def switch_model(

    provider_changed = target_provider != current_provider
    provider_label = get_label(target_provider)
+    if target_provider.startswith("custom:"):
+        custom_pdef = resolve_provider_full(
+            target_provider,
+            user_providers,
+            custom_providers,
+        )
+        if custom_pdef is not None:
+            provider_label = custom_pdef.name

    # --- Resolve credentials ---
    api_key = current_api_key
@@ -705,6 +726,7 @@ def switch_model(
 def list_authenticated_providers(
    current_provider: str = "",
    user_providers: dict = None,
+    custom_providers: list | None = None,
    max_models: int = 8,
 ) -> List[dict]:
    """Detect which providers have credentials and list their curated models.
@@ -730,6 +752,7 @@ def list_authenticated_providers(
        fetch_models_dev,
        get_provider_info as _mdev_pinfo,
    )
+    from hermes_cli.auth import PROVIDER_REGISTRY
    from hermes_cli.models import OPENROUTER_MODELS, _PROVIDER_MODELS

    results: List[dict] = []
@@ -750,9 +773,16 @@ def list_authenticated_providers(
        if not isinstance(pdata, dict):
            continue

-        env_vars = pdata.get("env", [])
-        if not isinstance(env_vars, list):
-            continue
+        # Prefer auth.py PROVIDER_REGISTRY for env var names — it's our
+        # source of truth.  models.dev can have wrong mappings (e.g.
+        # minimax-cn → MINIMAX_API_KEY instead of MINIMAX_CN_API_KEY).
+        pconfig = PROVIDER_REGISTRY.get(hermes_id)
+        if pconfig and pconfig.api_key_env_vars:
+            env_vars = list(pconfig.api_key_env_vars)
+        else:
+            env_vars = pdata.get("env", [])
+            if not isinstance(env_vars, list):
+                continue

        # Check if any env var is set
        has_creds = any(os.environ.get(ev) for ev in env_vars)
@@ -791,12 +821,12 @@ def list_authenticated_providers(
        if overlay.auth_type in ("oauth_device_code", "oauth_external", "external_process"):
            # These use auth stores, not env vars — check for auth.json entries
            try:
-                from hermes_cli.auth import _read_auth_store
-                store = _read_auth_store()
-                if store and pid in store:
+                from hermes_cli.auth import _load_auth_store
+                store = _load_auth_store()
+                if store and (pid in store.get("providers", {}) or pid in store.get("credential_pool", {})):
                    has_creds = True
-            except Exception:
-                pass
+            except Exception as exc:
+                logger.debug("Auth store check failed for %s: %s", pid, exc)
        if not has_creds:
            continue

@@ -842,80 +872,46 @@ def list_authenticated_providers(
                "api_url": api_url,
            })

+    # --- 4. Saved custom providers from config ---
+    if custom_providers and isinstance(custom_providers, list):
+        for entry in custom_providers:
+            if not isinstance(entry, dict):
+                continue
+
+            display_name = (entry.get("name") or "").strip()
+            api_url = (
+                entry.get("base_url", "")
+                or entry.get("url", "")
+                or entry.get("api", "")
+                or ""
+            ).strip()
+            if not display_name or not api_url:
+                continue
+
+            slug = custom_provider_slug(display_name)
+            if slug in seen_slugs:
+                continue
+
+            models_list = []
+            default_model = (entry.get("model") or "").strip()
+            if default_model:
+                models_list.append(default_model)
+
+            results.append({
+                "slug": slug,
+                "name": display_name,
+                "is_current": slug == current_provider,
+                "is_user_defined": True,
+                "models": models_list,
+                "total_models": len(models_list),
+                "source": "user-config",
+                "api_url": api_url,
+            })
+            seen_slugs.add(slug)
+
    # Sort: current provider first, then by model count descending
    results.sort(key=lambda r: (not r["is_current"], -r["total_models"]))

    return results


-# ---------------------------------------------------------------------------
-# Fuzzy suggestions
-# ---------------------------------------------------------------------------
-
-def suggest_models(raw_input: str, limit: int = 3) -> List[str]:
-    """Return fuzzy model suggestions for a (possibly misspelled) input."""
-    query = raw_input.strip()
-    if not query:
-        return []
-
-    results = search_models_dev(query, limit=limit)
-    suggestions: list[str] = []
-    for r in results:
-        mid = r.get("model_id", "")
-        if mid:
-            suggestions.append(mid)
-
-    return suggestions[:limit]
-
-
-# ---------------------------------------------------------------------------
-# Custom provider switch
-# ---------------------------------------------------------------------------
-
-def switch_to_custom_provider() -> CustomAutoResult:
-    """Handle bare '/model --provider custom' — resolve endpoint and auto-detect model."""
-    from hermes_cli.runtime_provider import (
-        resolve_runtime_provider,
-        _auto_detect_local_model,
-    )
-
-    try:
-        runtime = resolve_runtime_provider(requested="custom")
-    except Exception as e:
-        return CustomAutoResult(
-            success=False,
-            error_message=f"Could not resolve custom endpoint: {e}",
-        )
-
-    cust_base = runtime.get("base_url", "")
-    cust_key = runtime.get("api_key", "")
-
-    if not cust_base or "openrouter.ai" in cust_base:
-        return CustomAutoResult(
-            success=False,
-            error_message=(
-                "No custom endpoint configured. "
-                "Set model.base_url in config.yaml, or set OPENAI_BASE_URL "
-                "in .env, or run: hermes setup -> Custom OpenAI-compatible endpoint"
-            ),
-        )
-
-    detected_model = _auto_detect_local_model(cust_base)
-    if not detected_model:
-        return CustomAutoResult(
-            success=False,
-            base_url=cust_base,
-            api_key=cust_key,
-            error_message=(
-                f"Custom endpoint at {cust_base} is reachable but no single "
-                f"model was auto-detected. Specify the model explicitly: "
-                f"/model <model-name> --provider custom"
-            ),
-        )
-
-    return CustomAutoResult(
-        success=True,
-        model=detected_model,
-        base_url=cust_base,
-        api_key=cust_key,
-    )
@@ -20,22 +20,20 @@ COPILOT_EDITOR_VERSION = "vscode/1.104.1"
 COPILOT_REASONING_EFFORTS_GPT5 = ["minimal", "low", "medium", "high"]
 COPILOT_REASONING_EFFORTS_O_SERIES = ["low", "medium", "high"]

-# Backward-compatible aliases for the earlier GitHub Models-backed Copilot work.
-GITHUB_MODELS_BASE_URL = COPILOT_BASE_URL
-GITHUB_MODELS_CATALOG_URL = COPILOT_MODELS_URL

+# Fallback OpenRouter snapshot used when the live catalog is unavailable.
 # (model_id, display description shown in menus)
 OPENROUTER_MODELS: list[tuple[str, str]] = [
    ("anthropic/claude-opus-4.6",       "recommended"),
    ("anthropic/claude-sonnet-4.6",     ""),
-    ("qwen/qwen3.6-plus:free", "free"),
+    ("qwen/qwen3.6-plus",               ""),
    ("anthropic/claude-sonnet-4.5",     ""),
    ("anthropic/claude-haiku-4.5",      ""),
    ("openai/gpt-5.4",                  ""),
    ("openai/gpt-5.4-mini",             ""),
    ("xiaomi/mimo-v2-pro",               ""),
    ("openai/gpt-5.3-codex",            ""),
-    ("google/gemini-3-pro-preview",     ""),
+    ("google/gemini-3-pro-image-preview", ""),
    ("google/gemini-3-flash-preview",   ""),
    ("google/gemini-3.1-pro-preview",     ""),
    ("google/gemini-3.1-flash-lite-preview",   ""),
@@ -47,7 +45,7 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
    ("z-ai/glm-5.1",                    ""),
    ("z-ai/glm-5-turbo",                ""),
    ("moonshotai/kimi-k2.5",            ""),
-    ("x-ai/grok-4.20-beta",             ""),
+    ("x-ai/grok-4.20",                  ""),
    ("nvidia/nemotron-3-super-120b-a12b",      ""),
    ("nvidia/nemotron-3-super-120b-a12b:free", "free"),
    ("arcee-ai/trinity-large-preview:free", "free"),
@@ -56,6 +54,8 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
    ("openai/gpt-5.4-nano",             ""),
 ]

+_openrouter_catalog_cache: list[tuple[str, str]] | None = None
+
 _PROVIDER_MODELS: dict[str, list[str]] = {
    "nous": [
        "anthropic/claude-opus-4.6",
@@ -144,18 +144,22 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
        "kimi-k2-0905-preview",
    ],
    "minimax": [
-        "MiniMax-M2.7",
-        "MiniMax-M2.7-highspeed",
+        "MiniMax-M1",
+        "MiniMax-M1-40k",
+        "MiniMax-M1-80k",
+        "MiniMax-M1-128k",
+        "MiniMax-M1-256k",
        "MiniMax-M2.5",
-        "MiniMax-M2.5-highspeed",
-        "MiniMax-M2.1",
+        "MiniMax-M2.7",
    ],
    "minimax-cn": [
-        "MiniMax-M2.7",
-        "MiniMax-M2.7-highspeed",
+        "MiniMax-M1",
+        "MiniMax-M1-40k",
+        "MiniMax-M1-80k",
+        "MiniMax-M1-128k",
+        "MiniMax-M1-256k",
        "MiniMax-M2.5",
-        "MiniMax-M2.5-highspeed",
-        "MiniMax-M2.1",
+        "MiniMax-M2.7",
    ],
    "anthropic": [
        "claude-opus-4-6",
@@ -412,12 +416,6 @@ _FREE_TIER_CACHE_TTL: int = 180  # seconds (3 minutes)
 _free_tier_cache: tuple[bool, float] | None = None  # (result, timestamp)


-def clear_nous_free_tier_cache() -> None:
-    """Invalidate the cached free-tier result (e.g. after login/logout)."""
-    global _free_tier_cache
-    _free_tier_cache = None
-
-
 def check_nous_free_tier() -> bool:
    """Check if the current Nous Portal user is on a free (unpaid) tier.

@@ -479,6 +477,7 @@ _PROVIDER_LABELS = {
    "ai-gateway": "AI Gateway",
    "kilocode": "Kilo Code",
    "alibaba": "Alibaba Cloud (DashScope)",
+    "qwen-oauth": "Qwen OAuth (Portal)",
    "huggingface": "Hugging Face",
    "custom": "Custom endpoint",
 }
@@ -518,25 +517,91 @@ _PROVIDER_ALIASES = {
    "aliyun": "alibaba",
    "qwen": "alibaba",
    "alibaba-cloud": "alibaba",
+    "qwen-portal": "qwen-oauth",
    "hf": "huggingface",
    "hugging-face": "huggingface",
    "huggingface-hub": "huggingface",
 }


-def model_ids() -> list[str]:
+def _openrouter_model_is_free(pricing: Any) -> bool:
+    """Return True when both prompt and completion pricing are zero."""
+    if not isinstance(pricing, dict):
+        return False
+    try:
+        return float(pricing.get("prompt", "0")) == 0 and float(pricing.get("completion", "0")) == 0
+    except (TypeError, ValueError):
+        return False
+
+
+def fetch_openrouter_models(
+    timeout: float = 8.0,
+    *,
+    force_refresh: bool = False,
+) -> list[tuple[str, str]]:
+    """Return the curated OpenRouter picker list, refreshed from the live catalog when possible."""
+    global _openrouter_catalog_cache
+
+    if _openrouter_catalog_cache is not None and not force_refresh:
+        return list(_openrouter_catalog_cache)
+
+    fallback = list(OPENROUTER_MODELS)
+    preferred_ids = [mid for mid, _ in fallback]
+
+    try:
+        req = urllib.request.Request(
+            "https://openrouter.ai/api/v1/models",
+            headers={"Accept": "application/json"},
+        )
+        with urllib.request.urlopen(req, timeout=timeout) as resp:
+            payload = json.loads(resp.read().decode())
+    except Exception:
+        return list(_openrouter_catalog_cache or fallback)
+
+    live_items = payload.get("data", [])
+    if not isinstance(live_items, list):
+        return list(_openrouter_catalog_cache or fallback)
+
+    live_by_id: dict[str, dict[str, Any]] = {}
+    for item in live_items:
+        if not isinstance(item, dict):
+            continue
+        mid = str(item.get("id") or "").strip()
+        if not mid:
+            continue
+        live_by_id[mid] = item
+
+    curated: list[tuple[str, str]] = []
+    for preferred_id in preferred_ids:
+        live_item = live_by_id.get(preferred_id)
+        if live_item is None:
+            continue
+        desc = "free" if _openrouter_model_is_free(live_item.get("pricing")) else ""
+        curated.append((preferred_id, desc))
+
+    if not curated:
+        return list(_openrouter_catalog_cache or fallback)
+
+    first_id, _ = curated[0]
+    curated[0] = (first_id, "recommended")
+    _openrouter_catalog_cache = curated
+    return list(curated)
+
+
+def model_ids(*, force_refresh: bool = False) -> list[str]:
    """Return just the OpenRouter model-id strings."""
-    return [mid for mid, _ in OPENROUTER_MODELS]
+    return [mid for mid, _ in fetch_openrouter_models(force_refresh=force_refresh)]


-def menu_labels() -> list[str]:
+def menu_labels(*, force_refresh: bool = False) -> list[str]:
    """Return display labels like 'anthropic/claude-opus-4.6 (recommended)'."""
    labels = []
-    for mid, desc in OPENROUTER_MODELS:
+    for mid, desc in fetch_openrouter_models(force_refresh=force_refresh):
        labels.append(f"{mid} ({desc})" if desc else mid)
    return labels


+
 # ---------------------------------------------------------------------------
 # Pricing helpers — fetch live pricing from OpenRouter-compatible /v1/models
 # ---------------------------------------------------------------------------
@@ -569,31 +634,6 @@ def _format_price_per_mtok(per_token_str: str) -> str:
    return f"${per_m:.2f}"


-def format_pricing_label(pricing: dict[str, str] | None) -> str:
-    """Build a compact pricing label like 'in $3 · out $15 · cache $0.30/Mtok'.
-
-    Returns empty string when pricing is unavailable.
-    """
-    if not pricing:
-        return ""
-    prompt_price = pricing.get("prompt", "")
-    completion_price = pricing.get("completion", "")
-    if not prompt_price and not completion_price:
-        return ""
-    inp = _format_price_per_mtok(prompt_price)
-    out = _format_price_per_mtok(completion_price)
-    if inp == "free" and out == "free":
-        return "free"
-    cache_read = pricing.get("input_cache_read", "")
-    cache_str = _format_price_per_mtok(cache_read) if cache_read else ""
-    if inp == out and not cache_str:
-        return f"{inp}/Mtok"
-    parts = [f"in {inp}", f"out {out}"]
-    if cache_str and cache_str != "?" and cache_str != inp:
-        parts.append(f"cache {cache_str}")
-    return " · ".join(parts) + "/Mtok"
-
-
 def format_model_pricing_table(
    models: list[tuple[str, str]],
    pricing_map: dict[str, dict[str, str]],
@@ -721,13 +761,14 @@ def _resolve_nous_pricing_credentials() -> tuple[str, str]:
    return ("", "")


-def get_pricing_for_provider(provider: str) -> dict[str, dict[str, str]]:
+def get_pricing_for_provider(provider: str, *, force_refresh: bool = False) -> dict[str, dict[str, str]]:
    """Return live pricing for providers that support it (openrouter, nous)."""
    normalized = normalize_provider(provider)
    if normalized == "openrouter":
        return fetch_models_with_pricing(
            api_key=_resolve_openrouter_api_key(),
            base_url="https://openrouter.ai/api",
+            force_refresh=force_refresh,
        )
    if normalized == "nous":
        api_key, base_url = _resolve_nous_pricing_credentials()
@@ -740,6 +781,7 @@ def get_pricing_for_provider(provider: str) -> dict[str, dict[str, str]]:
            return fetch_models_with_pricing(
                api_key=api_key,
                base_url=stripped,
+                force_refresh=force_refresh,
            )
    return {}

@@ -763,6 +805,7 @@ def list_available_providers() -> list[dict[str, str]]:
        "openrouter", "nous", "openai-codex", "copilot", "copilot-acp",
        "gemini", "huggingface",
        "zai", "kimi-coding", "minimax", "minimax-cn", "kilocode", "anthropic", "alibaba",
+        "qwen-oauth",
        "opencode-zen", "opencode-go",
        "ai-gateway", "deepseek", "custom",
    ]
@@ -847,7 +890,11 @@ def _get_custom_base_url() -> str:
    return ""


-def curated_models_for_provider(provider: Optional[str]) -> list[tuple[str, str]]:
+def curated_models_for_provider(
+    provider: Optional[str],
+    *,
+    force_refresh: bool = False,
+) -> list[tuple[str, str]]:
    """Return ``(model_id, description)`` tuples for a provider's model list.

    Tries to fetch the live model list from the provider's API first,
@@ -856,7 +903,7 @@ def curated_models_for_provider(provider: Optional[str]) -> list[tuple[str, str]
    """
    normalized = normalize_provider(provider)
    if normalized == "openrouter":
-        return list(OPENROUTER_MODELS)
+        return fetch_openrouter_models(force_refresh=force_refresh)

    # Try live API first (Codex, Nous, etc. all support /models)
    live = provider_model_ids(normalized)
@@ -975,12 +1022,12 @@ def _find_openrouter_slug(model_name: str) -> Optional[str]:
        return None

    # Exact match (already has provider/ prefix)
-    for mid, _ in OPENROUTER_MODELS:
+    for mid in model_ids():
        if name_lower == mid.lower():
            return mid

    # Try matching just the model part (after the /)
-    for mid, _ in OPENROUTER_MODELS:
+    for mid in model_ids():
        if "/" in mid:
            _, model_part = mid.split("/", 1)
            if name_lower == model_part.lower():
@@ -1010,6 +1057,79 @@ def provider_label(provider: Optional[str]) -> str:
    return _PROVIDER_LABELS.get(normalized, original or "OpenRouter")


+# Models that support OpenAI Priority Processing (service_tier="priority").
+# See https://openai.com/api-priority-processing/ for the canonical list.
+# Only the bare model slug is stored (no vendor prefix).
+_PRIORITY_PROCESSING_MODELS: frozenset[str] = frozenset({
+    "gpt-5.4",
+    "gpt-5.4-mini",
+    "gpt-5.2",
+    "gpt-5.1",
+    "gpt-5",
+    "gpt-5-mini",
+    "gpt-4.1",
+    "gpt-4.1-mini",
+    "gpt-4.1-nano",
+    "gpt-4o",
+    "gpt-4o-mini",
+    "o3",
+    "o4-mini",
+})
+
+# Models that support Anthropic Fast Mode (speed="fast").
+# See https://platform.claude.com/docs/en/build-with-claude/fast-mode
+# Currently only Claude Opus 4.6.  Both hyphen and dot variants are stored
+# to handle native Anthropic (claude-opus-4-6) and OpenRouter (claude-opus-4.6).
+_ANTHROPIC_FAST_MODE_MODELS: frozenset[str] = frozenset({
+    "claude-opus-4-6",
+    "claude-opus-4.6",
+})
+
+
+def _strip_vendor_prefix(model_id: str) -> str:
+    """Strip vendor/ prefix from a model ID (e.g. 'anthropic/claude-opus-4-6' -> 'claude-opus-4-6')."""
+    raw = str(model_id or "").strip().lower()
+    if "/" in raw:
+        raw = raw.split("/", 1)[1]
+    return raw
+
+
+def model_supports_fast_mode(model_id: Optional[str]) -> bool:
+    """Return whether Hermes should expose the /fast toggle for this model."""
+    raw = _strip_vendor_prefix(str(model_id or ""))
+    if raw in _PRIORITY_PROCESSING_MODELS:
+        return True
+    # Anthropic fast mode — strip date suffixes (e.g. claude-opus-4-6-20260401)
+    # and OpenRouter variant tags (:fast, :beta) for matching.
+    base = raw.split(":")[0]
+    return base in _ANTHROPIC_FAST_MODE_MODELS
+
+
+def _is_anthropic_fast_model(model_id: Optional[str]) -> bool:
+    """Return True if the model supports Anthropic's fast mode (speed='fast')."""
+    raw = _strip_vendor_prefix(str(model_id or ""))
+    base = raw.split(":")[0]
+    return base in _ANTHROPIC_FAST_MODE_MODELS
+
+
+def resolve_fast_mode_overrides(model_id: Optional[str]) -> dict[str, Any] | None:
+    """Return request_overrides for fast/priority mode, or None if unsupported.
+
+    Returns provider-appropriate overrides:
+    - OpenAI models: ``{"service_tier": "priority"}`` (Priority Processing)
+    - Anthropic models: ``{"speed": "fast"}`` (Anthropic Fast Mode beta)
+
+    The overrides are injected into the API request kwargs by
+    ``_build_api_kwargs`` in run_agent.py — each API path handles its own
+    keys (service_tier for OpenAI/Codex, speed for Anthropic Messages).
+    """
+    if not model_supports_fast_mode(model_id):
+        return None
+    if _is_anthropic_fast_model(model_id):
+        return {"speed": "fast"}
+    return {"service_tier": "priority"}
+
+
 def _resolve_copilot_catalog_api_key() -> str:
    """Best-effort GitHub token for fetching the Copilot model catalog."""
    try:
@@ -1021,7 +1141,7 @@ def _resolve_copilot_catalog_api_key() -> str:
        return ""


-def provider_model_ids(provider: Optional[str]) -> list[str]:
+def provider_model_ids(provider: Optional[str], *, force_refresh: bool = False) -> list[str]:
    """Return the best known model catalog for a provider.

    Tries live API endpoints for providers that support them (Codex, Nous),
@@ -1029,7 +1149,7 @@ def provider_model_ids(provider: Optional[str]) -> list[str]:
    """
    normalized = normalize_provider(provider)
    if normalized == "openrouter":
-        return model_ids()
+        return model_ids(force_refresh=force_refresh)
    if normalized == "openai-codex":
        from hermes_cli.codex_models import get_codex_model_ids

@@ -1525,7 +1645,7 @@ def probe_api_models(

    return {
        "models": None,
-        "probed_url": tried[-1] if tried else normalized.rstrip("/") + "/models",
+        "probed_url": tried[0] if tried else normalized.rstrip("/") + "/models",
        "resolved_base_url": normalized,
        "suggested_base_url": alternate_base if alternate_base != normalized else None,
        "used_fallback": False,
@@ -61,6 +61,8 @@ VALID_HOOKS: Set[str] = {
    "post_api_request",
    "on_session_start",
    "on_session_end",
+    "on_session_finalize",
+    "on_session_reset",
 }

 ENTRY_POINTS_GROUP = "hermes_agent.plugins"
@@ -102,7 +102,7 @@ _RESERVED_NAMES = frozenset({
 # Hermes subcommands that cannot be used as profile names/aliases
 _HERMES_SUBCOMMANDS = frozenset({
    "chat", "model", "gateway", "setup", "whatsapp", "login", "logout",
-    "status", "cron", "doctor", "config", "pairing", "skills", "tools",
+    "status", "cron", "doctor", "dump", "config", "pairing", "skills", "tools",
    "mcp", "sessions", "insights", "version", "update", "uninstall",
    "profile", "plugins", "honcho", "acp",
 })
@@ -1007,7 +1007,7 @@ _hermes_completion() {

    # Top-level subcommands
    if [[ "$COMP_CWORD" == 1 ]]; then
-        local commands="chat model gateway setup status cron doctor config skills tools mcp sessions profile update version"
+        local commands="chat model gateway setup status cron doctor dump config skills tools mcp sessions profile update version"
        COMPREPLY=($(compgen -W "$commands" -- "$cur"))
    fi
 }
@@ -1032,7 +1032,7 @@ _hermes() {
    _arguments \\
        '-p[Profile name]:profile:($profiles)' \\
        '--profile[Profile name]:profile:($profiles)' \\
-        '1:command:(chat model gateway setup status cron doctor config skills tools mcp sessions profile update version)' \\
+        '1:command:(chat model gateway setup status cron doctor dump config skills tools mcp sessions profile update version)' \\
        '*::arg:->args'

    case $words[1] in
@@ -58,6 +58,12 @@ HERMES_OVERLAYS: Dict[str, HermesOverlay] = {
        auth_type="oauth_external",
        base_url_override="https://chatgpt.com/backend-api/codex",
    ),
+    "qwen-oauth": HermesOverlay(
+        transport="openai_chat",
+        auth_type="oauth_external",
+        base_url_override="https://portal.qwen.ai/v1",
+        base_url_env_var="HERMES_QWEN_BASE_URL",
+    ),
    "copilot-acp": HermesOverlay(
        transport="codex_responses",
        auth_type="external_process",
@@ -142,10 +148,6 @@ class ProviderDef:
    doc: str = ""
    source: str = ""                      # "models.dev", "hermes", "user-config"

-    @property
-    def is_user_defined(self) -> bool:
-        return self.source == "user-config"
-

 # -- Aliases ------------------------------------------------------------------
 # Maps human-friendly / legacy names to canonical provider IDs.
@@ -256,12 +258,6 @@ def normalize_provider(name: str) -> str:
    return ALIASES.get(key, key)


-def get_overlay(provider_id: str) -> Optional[HermesOverlay]:
-    """Get Hermes overlay for a provider, if one exists."""
-    canonical = normalize_provider(provider_id)
-    return HERMES_OVERLAYS.get(canonical)
-
-
 def get_provider(name: str) -> Optional[ProviderDef]:
    """Look up a provider by id or alias, merging all data sources.

@@ -344,37 +340,6 @@ def get_label(provider_id: str) -> str:
    return canonical


-# For direct import compat, expose as module-level dict
-# Built on demand by get_label() calls
-LABELS: Dict[str, str] = {
-    # Static entries for backward compat — get_label() is the proper API
-    "openrouter": "OpenRouter",
-    "nous": "Nous Portal",
-    "openai-codex": "OpenAI Codex",
-    "copilot-acp": "GitHub Copilot ACP",
-    "github-copilot": "GitHub Copilot",
-    "anthropic": "Anthropic",
-    "zai": "Z.AI / GLM",
-    "kimi-for-coding": "Kimi / Moonshot",
-    "minimax": "MiniMax",
-    "minimax-cn": "MiniMax (China)",
-    "deepseek": "DeepSeek",
-    "alibaba": "Alibaba Cloud (DashScope)",
-    "vercel": "Vercel AI Gateway",
-    "opencode": "OpenCode Zen",
-    "opencode-go": "OpenCode Go",
-    "kilo": "Kilo Gateway",
-    "huggingface": "Hugging Face",
-    "local": "Local endpoint",
-    "custom": "Custom endpoint",
-    # Legacy Hermes IDs (point to same providers)
-    "ai-gateway": "Vercel AI Gateway",
-    "kilocode": "Kilo Gateway",
-    "copilot": "GitHub Copilot",
-    "kimi-coding": "Kimi / Moonshot",
-    "opencode-zen": "OpenCode Zen",
-}
-

 def is_aggregator(provider: str) -> bool:
    """Return True when the provider is a multi-model aggregator."""
@@ -446,9 +411,64 @@ def resolve_user_provider(name: str, user_config: Dict[str, Any]) -> Optional[Pr
    )


+def custom_provider_slug(display_name: str) -> str:
+    """Build a canonical slug for a custom_providers entry.
+
+    Matches the convention used by runtime_provider and credential_pool
+    (``custom:<normalized-name>``).  Centralised here so all call-sites
+    produce identical slugs.
+    """
+    return "custom:" + display_name.strip().lower().replace(" ", "-")
+
+
+def resolve_custom_provider(
+    name: str,
+    custom_providers: Optional[List[Dict[str, Any]]],
+) -> Optional[ProviderDef]:
+    """Resolve a provider from the user's config.yaml ``custom_providers`` list."""
+    if not custom_providers or not isinstance(custom_providers, list):
+        return None
+
+    requested = (name or "").strip().lower()
+    if not requested:
+        return None
+
+    for entry in custom_providers:
+        if not isinstance(entry, dict):
+            continue
+
+        display_name = (entry.get("name") or "").strip()
+        api_url = (
+            entry.get("base_url", "")
+            or entry.get("url", "")
+            or entry.get("api", "")
+            or ""
+        ).strip()
+        if not display_name or not api_url:
+            continue
+
+        slug = custom_provider_slug(display_name)
+        if requested not in {display_name.lower(), slug}:
+            continue
+
+        return ProviderDef(
+            id=slug,
+            name=display_name,
+            transport="openai_chat",
+            api_key_env_vars=(),
+            base_url=api_url,
+            is_aggregator=False,
+            auth_type="api_key",
+            source="user-config",
+        )
+
+    return None
+
+
 def resolve_provider_full(
    name: str,
    user_providers: Optional[Dict[str, Any]] = None,
+    custom_providers: Optional[List[Dict[str, Any]]] = None,
 ) -> Optional[ProviderDef]:
    """Full resolution chain: built-in → models.dev → user config.

@@ -457,6 +477,7 @@ def resolve_provider_full(
    Args:
        name: Provider name or alias.
        user_providers: The ``providers:`` dict from config.yaml (optional).
+        custom_providers: The ``custom_providers:`` list from config.yaml (optional).

    Returns:
        ProviderDef if found, else None.
@@ -479,6 +500,11 @@ def resolve_provider_full(
        if user_pdef is not None:
            return user_pdef

+    # 2b. Saved custom providers from config
+    custom_pdef = resolve_custom_provider(name, custom_providers)
+    if custom_pdef is not None:
+        return custom_pdef
+
    # 3. Try models.dev directly (for providers not in our ALIASES)
    try:
        from agent.models_dev import get_provider_info as _mdev_provider
@@ -14,11 +14,14 @@ from agent.credential_pool import CredentialPool, PooledCredential, get_custom_p
 from hermes_cli.auth import (
    AuthError,
    DEFAULT_CODEX_BASE_URL,
+    DEFAULT_QWEN_BASE_URL,
    PROVIDER_REGISTRY,
+    _agent_key_is_usable,
    format_auth_error,
    resolve_provider,
    resolve_nous_runtime_credentials,
    resolve_codex_runtime_credentials,
+    resolve_qwen_runtime_credentials,
    resolve_api_key_provider_credentials,
    resolve_external_process_provider_credentials,
    has_usable_secret,
@@ -148,6 +151,9 @@ def _resolve_runtime_from_pool_entry(
    if provider == "openai-codex":
        api_mode = "codex_responses"
        base_url = base_url or DEFAULT_CODEX_BASE_URL
+    elif provider == "qwen-oauth":
+        api_mode = "chat_completions"
+        base_url = base_url or DEFAULT_QWEN_BASE_URL
    elif provider == "anthropic":
        api_mode = "anthropic_messages"
        cfg_provider = str(model_cfg.get("provider") or "").strip().lower()
@@ -163,6 +169,16 @@ def _resolve_runtime_from_pool_entry(
        api_mode = _copilot_runtime_api_mode(model_cfg, getattr(entry, "runtime_api_key", ""))
    else:
        configured_provider = str(model_cfg.get("provider") or "").strip().lower()
+        # Honour model.base_url from config.yaml when the configured provider
+        # matches this provider — same pattern as the Anthropic branch above.
+        # Only override when the pool entry has no explicit base_url (i.e. it
+        # fell back to the hardcoded default).  Env var overrides win (#6039).
+        pconfig = PROVIDER_REGISTRY.get(provider)
+        pool_url_is_default = pconfig and base_url.rstrip("/") == pconfig.inference_base_url.rstrip("/")
+        if configured_provider == provider and pool_url_is_default:
+            cfg_base_url = str(model_cfg.get("base_url") or "").strip().rstrip("/")
+            if cfg_base_url:
+                base_url = cfg_base_url
        configured_mode = _parse_api_mode(model_cfg.get("api_mode"))
        if configured_mode and _provider_supports_explicit_api_mode(provider, configured_provider):
            api_mode = configured_mode
@@ -629,6 +645,21 @@ def resolve_runtime_provider(
                getattr(entry, "runtime_api_key", None)
                or getattr(entry, "access_token", "")
            )
+        # For Nous, the pool entry's runtime_api_key is the agent_key — a
+        # short-lived inference credential (~30 min TTL).  The pool doesn't
+        # refresh it during selection (that would trigger network calls in
+        # non-runtime contexts like `hermes auth list`).  If the key is
+        # expired, clear pool_api_key so we fall through to
+        # resolve_nous_runtime_credentials() which handles refresh + mint.
+        if provider == "nous" and entry is not None and pool_api_key:
+            min_ttl = max(60, int(os.getenv("HERMES_NOUS_MIN_KEY_TTL_SECONDS", "1800")))
+            nous_state = {
+                "agent_key": getattr(entry, "agent_key", None),
+                "agent_key_expires_at": getattr(entry, "agent_key_expires_at", None),
+            }
+            if not _agent_key_is_usable(nous_state, min_ttl):
+                logger.debug("Nous pool entry agent_key expired/missing, falling through to runtime resolution")
+                pool_api_key = ""
        if entry is not None and pool_api_key:
            return _resolve_runtime_from_pool_entry(
                provider=provider,
@@ -681,6 +712,24 @@ def resolve_runtime_provider(
            logger.info("Auto-detected Codex provider but credentials failed; "
                        "falling through to next provider.")

+    if provider == "qwen-oauth":
+        try:
+            creds = resolve_qwen_runtime_credentials()
+            return {
+                "provider": "qwen-oauth",
+                "api_mode": "chat_completions",
+                "base_url": creds.get("base_url", "").rstrip("/"),
+                "api_key": creds.get("api_key", ""),
+                "source": creds.get("source", "qwen-cli"),
+                "expires_at_ms": creds.get("expires_at_ms"),
+                "requested_provider": requested_provider,
+            }
+        except AuthError:
+            if requested_provider != "auto":
+                raise
+            logger.info("Qwen OAuth credentials failed; "
+                        "falling through to next provider.")
+
    if provider == "copilot-acp":
        creds = resolve_external_process_provider_credentials(provider)
        return {
@@ -724,7 +773,15 @@ def resolve_runtime_provider(
    pconfig = PROVIDER_REGISTRY.get(provider)
    if pconfig and pconfig.auth_type == "api_key":
        creds = resolve_api_key_provider_credentials(provider)
-        base_url = creds.get("base_url", "").rstrip("/")
+        # Honour model.base_url from config.yaml when the configured provider
+        # matches this provider — mirrors the Anthropic path above.  Without
+        # this, users who set model.base_url to e.g. api.minimaxi.com/anthropic
+        # (China endpoint) still get the hardcoded api.minimax.io default (#6039).
+        cfg_provider = str(model_cfg.get("provider") or "").strip().lower()
+        cfg_base_url = ""
+        if cfg_provider == provider:
+            cfg_base_url = (model_cfg.get("base_url") or "").strip().rstrip("/")
+        base_url = cfg_base_url or creds.get("base_url", "").rstrip("/")
        api_mode = "chat_completions"
        if provider == "copilot":
            api_mode = _copilot_runtime_api_mode(model_cfg, creds.get("api_key", ""))
@@ -16,6 +16,7 @@ import logging
 import os
 import shutil
 import sys
+import copy
 from pathlib import Path
 from typing import Optional, Dict, Any

@@ -105,8 +106,8 @@ _DEFAULT_PROVIDER_MODELS = {
    ],
    "zai": ["glm-5", "glm-4.7", "glm-4.5", "glm-4.5-flash"],
    "kimi-coding": ["kimi-k2.5", "kimi-k2-thinking", "kimi-k2-turbo-preview"],
-    "minimax": ["MiniMax-M2.7", "MiniMax-M2.7-highspeed", "MiniMax-M2.5", "MiniMax-M2.5-highspeed", "MiniMax-M2.1"],
-    "minimax-cn": ["MiniMax-M2.7", "MiniMax-M2.7-highspeed", "MiniMax-M2.5", "MiniMax-M2.5-highspeed", "MiniMax-M2.1"],
+    "minimax": ["MiniMax-M1", "MiniMax-M1-40k", "MiniMax-M1-80k", "MiniMax-M1-128k", "MiniMax-M1-256k", "MiniMax-M2.5", "MiniMax-M2.7"],
+    "minimax-cn": ["MiniMax-M1", "MiniMax-M1-40k", "MiniMax-M1-80k", "MiniMax-M1-128k", "MiniMax-M1-256k", "MiniMax-M2.5", "MiniMax-M2.7"],
    "ai-gateway": ["anthropic/claude-opus-4.6", "anthropic/claude-sonnet-4.6", "openai/gpt-5", "google/gemini-3-flash"],
    "kilocode": ["anthropic/claude-opus-4.6", "anthropic/claude-sonnet-4.6", "openai/gpt-5.4", "google/gemini-3-pro-preview", "google/gemini-3-flash-preview"],
    "opencode-zen": ["gpt-5.4", "gpt-5.3-codex", "claude-sonnet-4-6", "gemini-3-flash", "glm-5", "kimi-k2.5", "minimax-m2.7"],
@@ -172,150 +173,10 @@ def _setup_copilot_reasoning_selection(
        _set_reasoning_effort(config, "none")


-def _setup_provider_model_selection(config, provider_id, current_model, prompt_choice, prompt_fn):
-    """Model selection for API-key providers with live /models detection.
-
-    Tries the provider's /models endpoint first.  Falls back to a
-    hardcoded default list with a warning if the endpoint is unreachable.
-    Always offers a 'Custom model' escape hatch.
-    """
-    from hermes_cli.auth import PROVIDER_REGISTRY, resolve_api_key_provider_credentials
-    from hermes_cli.config import get_env_value
-    from hermes_cli.models import (
-        copilot_model_api_mode,
-        fetch_api_models,
-        fetch_github_model_catalog,
-        normalize_copilot_model_id,
-        normalize_opencode_model_id,
-        opencode_model_api_mode,
-    )
-
-    pconfig = PROVIDER_REGISTRY[provider_id]
-    is_copilot_catalog_provider = provider_id in {"copilot", "copilot-acp"}
-
-    # Resolve API key and base URL for the probe
-    if is_copilot_catalog_provider:
-        api_key = ""
-        if provider_id == "copilot":
-            creds = resolve_api_key_provider_credentials(provider_id)
-            api_key = creds.get("api_key", "")
-            base_url = creds.get("base_url", "") or pconfig.inference_base_url
-        else:
-            try:
-                creds = resolve_api_key_provider_credentials("copilot")
-                api_key = creds.get("api_key", "")
-            except Exception:
-                pass
-            base_url = pconfig.inference_base_url
-        catalog = fetch_github_model_catalog(api_key)
-        current_model = normalize_copilot_model_id(
-            current_model,
-            catalog=catalog,
-            api_key=api_key,
-        ) or current_model
-    else:
-        api_key = ""
-        for ev in pconfig.api_key_env_vars:
-            api_key = get_env_value(ev) or os.getenv(ev, "")
-            if api_key:
-                break
-        base_url_env = pconfig.base_url_env_var or ""
-        base_url = (get_env_value(base_url_env) if base_url_env else "") or pconfig.inference_base_url
-        catalog = None
-
-    # Try live /models endpoint
-    if is_copilot_catalog_provider and catalog:
-        live_models = [item.get("id", "") for item in catalog if item.get("id")]
-    else:
-        live_models = fetch_api_models(api_key, base_url)
-
-    if live_models:
-        provider_models = live_models
-        print_info(f"Found {len(live_models)} model(s) from {pconfig.name} API")
-    else:
-        fallback_provider_id = "copilot" if provider_id == "copilot-acp" else provider_id
-        provider_models = _DEFAULT_PROVIDER_MODELS.get(fallback_provider_id, [])
-        if provider_models:
-            print_warning(
-                f"Could not auto-detect models from {pconfig.name} API — showing defaults.\n"
-                f"    Use \"Custom model\" if the model you expect isn't listed."
-            )
-
-    if provider_id in {"opencode-zen", "opencode-go"}:
-        provider_models = [normalize_opencode_model_id(provider_id, mid) for mid in provider_models]
-        current_model = normalize_opencode_model_id(provider_id, current_model)
-        provider_models = list(dict.fromkeys(mid for mid in provider_models if mid))
-
-    model_choices = list(provider_models)
-    model_choices.append("Custom model")
-    model_choices.append(f"Keep current ({current_model})")
-
-    keep_idx = len(model_choices) - 1
-    model_idx = prompt_choice("Select default model:", model_choices, keep_idx)
-
-    selected_model = current_model
-
-    if model_idx < len(provider_models):
-        selected_model = provider_models[model_idx]
-        if is_copilot_catalog_provider:
-            selected_model = normalize_copilot_model_id(
-                selected_model,
-                catalog=catalog,
-                api_key=api_key,
-            ) or selected_model
-        elif provider_id in {"opencode-zen", "opencode-go"}:
-            selected_model = normalize_opencode_model_id(provider_id, selected_model)
-        _set_default_model(config, selected_model)
-    elif model_idx == len(provider_models):
-        custom = prompt_fn("Enter model name")
-        if custom:
-            if is_copilot_catalog_provider:
-                selected_model = normalize_copilot_model_id(
-                    custom,
-                    catalog=catalog,
-                    api_key=api_key,
-                ) or custom
-            elif provider_id in {"opencode-zen", "opencode-go"}:
-                selected_model = normalize_opencode_model_id(provider_id, custom)
-            else:
-                selected_model = custom
-            _set_default_model(config, selected_model)
-    else:
-        # "Keep current" selected — validate it's compatible with the new
-        # provider.  OpenRouter-formatted names (containing "/") won't work
-        # on direct-API providers and would silently break the gateway.
-        if "/" in (current_model or "") and provider_models:
-            print_warning(
-                f"Current model \"{current_model}\" looks like an OpenRouter model "
-                f"and won't work with {pconfig.name}. "
-                f"Switching to {provider_models[0]}."
-            )
-            selected_model = provider_models[0]
-            _set_default_model(config, provider_models[0])
-
-    if provider_id == "copilot" and selected_model:
-        model_cfg = _model_config_dict(config)
-        model_cfg["api_mode"] = copilot_model_api_mode(
-            selected_model,
-            catalog=catalog,
-            api_key=api_key,
-        )
-        config["model"] = model_cfg
-        _setup_copilot_reasoning_selection(
-            config,
-            selected_model,
-            prompt_choice,
-            catalog=catalog,
-            api_key=api_key,
-        )
-    elif provider_id in {"opencode-zen", "opencode-go"} and selected_model:
-        model_cfg = _model_config_dict(config)
-        model_cfg["api_mode"] = opencode_model_api_mode(provider_id, selected_model)
-        config["model"] = model_cfg
-

 # Import config helpers
 from hermes_cli.config import (
+    DEFAULT_CONFIG,
    get_hermes_home,
    get_config_path,
    get_env_path,
@@ -421,10 +282,22 @@ def _curses_prompt_choice(question: str, choices: list, default: int = 0) -> int
                curses.init_pair(1, curses.COLOR_GREEN, -1)
                curses.init_pair(2, curses.COLOR_YELLOW, -1)
            cursor = default
+            scroll_offset = 0

            while True:
                stdscr.clear()
                max_y, max_x = stdscr.getmaxyx()
+
+                # Rows available for list items: rows 2..(max_y-2) inclusive.
+                visible = max(1, max_y - 3)
+
+                # Scroll the viewport so the cursor is always visible.
+                if cursor < scroll_offset:
+                    scroll_offset = cursor
+                elif cursor >= scroll_offset + visible:
+                    scroll_offset = cursor - visible + 1
+                scroll_offset = max(0, min(scroll_offset, max(0, len(choices) - visible)))
+
                try:
                    stdscr.addnstr(
                        0,
@@ -436,12 +309,12 @@ def _curses_prompt_choice(question: str, choices: list, default: int = 0) -> int
                except curses.error:
                    pass

-                for i, choice in enumerate(choices):
-                    y = i + 2
+                for row, i in enumerate(range(scroll_offset, min(scroll_offset + visible, len(choices)))):
+                    y = row + 2
                    if y >= max_y - 1:
                        break
                    arrow = "→" if i == cursor else " "
-                    line = f" {arrow}  {choice}"
+                    line = f" {arrow}  {choices[i]}"
                    attr = curses.A_NORMAL
                    if i == cursor:
                        attr = curses.A_BOLD
@@ -909,8 +782,10 @@ def setup_model_provider(config: dict, *, quick: bool = False):
    # changes with stale values (#4172).
    _refreshed = load_config()
    config["model"] = _refreshed.get("model", config.get("model"))
-    if _refreshed.get("custom_providers"):
+    if "custom_providers" in _refreshed:
        config["custom_providers"] = _refreshed["custom_providers"]
+    else:
+        config.pop("custom_providers", None)

    # Derive the selected provider for downstream steps (vision setup).
    selected_provider = None
@@ -994,8 +869,6 @@ def setup_model_provider(config: dict, *, quick: bool = False):
                strategy_value = ["fill_first", "round_robin", "random"][strategy_idx]
                _set_credential_pool_strategy(config, selected_provider, strategy_value)
                print_success(f"Saved {selected_provider} rotation strategy: {strategy_value}")
-            else:
-                _set_credential_pool_strategy(config, selected_provider, "fill_first")
        except Exception as exc:
            logger.debug("Could not configure same-provider fallback in setup: %s", exc)

@@ -2155,6 +2028,71 @@ def _setup_whatsapp():
        print_info("or personal self-chat) and pair via QR code.")


+def _setup_bluebubbles():
+    """Configure BlueBubbles iMessage gateway."""
+    print_header("BlueBubbles (iMessage)")
+    existing = get_env_value("BLUEBUBBLES_SERVER_URL")
+    if existing:
+        print_info("BlueBubbles: already configured")
+        if not prompt_yes_no("Reconfigure BlueBubbles?", False):
+            return
+
+    print_info("Connects Hermes to iMessage via BlueBubbles — a free, open-source")
+    print_info("macOS server that bridges iMessage to any device.")
+    print_info("   Requires a Mac running BlueBubbles Server v1.0.0+")
+    print_info("   Download: https://bluebubbles.app/")
+    print()
+    print_info("In BlueBubbles Server → Settings → API, note your Server URL and Password.")
+    print()
+
+    server_url = prompt("BlueBubbles server URL (e.g. http://192.168.1.10:1234)")
+    if not server_url:
+        print_warning("Server URL is required — skipping BlueBubbles setup")
+        return
+    save_env_value("BLUEBUBBLES_SERVER_URL", server_url.rstrip("/"))
+
+    password = prompt("BlueBubbles server password", password=True)
+    if not password:
+        print_warning("Password is required — skipping BlueBubbles setup")
+        return
+    save_env_value("BLUEBUBBLES_PASSWORD", password)
+    print_success("BlueBubbles credentials saved")
+
+    print()
+    print_info("🔒 Security: Restrict who can message your bot")
+    print_info("   Use iMessage addresses: email (user@icloud.com) or phone (+15551234567)")
+    print()
+    allowed_users = prompt("Allowed iMessage addresses (comma-separated, leave empty for open access)")
+    if allowed_users:
+        save_env_value("BLUEBUBBLES_ALLOWED_USERS", allowed_users.replace(" ", ""))
+        print_success("BlueBubbles allowlist configured")
+    else:
+        print_info("⚠️  No allowlist set — anyone who can iMessage you can use the bot!")
+
+    print()
+    print_info("📬 Home Channel: phone or email for cron job delivery and notifications.")
+    print_info("   You can also set this later with /set-home in your iMessage chat.")
+    home_channel = prompt("Home channel address (leave empty to set later)")
+    if home_channel:
+        save_env_value("BLUEBUBBLES_HOME_CHANNEL", home_channel)
+
+    print()
+    print_info("Advanced settings (defaults are fine for most setups):")
+    if prompt_yes_no("Configure webhook listener settings?", False):
+        webhook_port = prompt("Webhook listener port (default: 8645)")
+        if webhook_port:
+            try:
+                save_env_value("BLUEBUBBLES_WEBHOOK_PORT", str(int(webhook_port)))
+                print_success(f"Webhook port set to {webhook_port}")
+            except ValueError:
+                print_warning("Invalid port number, using default 8645")
+
+    print()
+    print_info("Requires the BlueBubbles Private API helper for typing indicators,")
+    print_info("read receipts, and tapback reactions. Basic messaging works without it.")
+    print_info("   Install: https://docs.bluebubbles.app/helper-bundle/installation")
+
+
 def _setup_webhooks():
    """Configure webhook integration."""
    print_header("Webhooks")
@@ -2209,6 +2147,7 @@ _GATEWAY_PLATFORMS = [
    ("Matrix", "MATRIX_ACCESS_TOKEN", _setup_matrix),
    ("Mattermost", "MATTERMOST_TOKEN", _setup_mattermost),
    ("WhatsApp", "WHATSAPP_ENABLED", _setup_whatsapp),
+    ("BlueBubbles (iMessage)", "BLUEBUBBLES_SERVER_URL", _setup_bluebubbles),
    ("Webhooks (GitHub, GitLab, etc.)", "WEBHOOK_ENABLED", _setup_webhooks),
 ]

@@ -2252,6 +2191,7 @@ def setup_gateway(config: dict):
        or get_env_value("MATRIX_ACCESS_TOKEN")
        or get_env_value("MATRIX_PASSWORD")
        or get_env_value("WHATSAPP_ENABLED")
+        or get_env_value("BLUEBUBBLES_SERVER_URL")
        or get_env_value("WEBHOOK_ENABLED")
    )
    if any_messaging:
@@ -2271,6 +2211,8 @@ def setup_gateway(config: dict):
            missing_home.append("Discord")
        if get_env_value("SLACK_BOT_TOKEN") and not get_env_value("SLACK_HOME_CHANNEL"):
            missing_home.append("Slack")
+        if get_env_value("BLUEBUBBLES_SERVER_URL") and not get_env_value("BLUEBUBBLES_HOME_CHANNEL"):
+            missing_home.append("BlueBubbles")

        if missing_home:
            print()
@@ -2441,6 +2383,8 @@ def _get_section_config_summary(config: dict, section_key: str) -> Optional[str]
            platforms.append("WhatsApp")
        if get_env_value("SIGNAL_ACCOUNT"):
            platforms.append("Signal")
+        if get_env_value("BLUEBUBBLES_SERVER_URL"):
+            platforms.append("BlueBubbles")
        if platforms:
            return ", ".join(platforms)
        return None  # No platforms configured — section must run
@@ -2489,9 +2433,120 @@ _OPENCLAW_SCRIPT = (
 )


+def _load_openclaw_migration_module():
+    """Load the openclaw_to_hermes migration script as a module.
+
+    Returns the loaded module, or None if the script can't be loaded.
+    """
+    if not _OPENCLAW_SCRIPT.exists():
+        return None
+
+    spec = importlib.util.spec_from_file_location(
+        "openclaw_to_hermes", _OPENCLAW_SCRIPT
+    )
+    if spec is None or spec.loader is None:
+        return None
+
+    mod = importlib.util.module_from_spec(spec)
+    # Register in sys.modules so @dataclass can resolve the module
+    # (Python 3.11+ requires this for dynamically loaded modules)
+    import sys as _sys
+    _sys.modules[spec.name] = mod
+    try:
+        spec.loader.exec_module(mod)
+    except Exception:
+        _sys.modules.pop(spec.name, None)
+        raise
+    return mod
+
+
+# Item kinds that represent high-impact changes warranting explicit warnings.
+# Gateway tokens/channels can hijack messaging platforms from the old agent.
+# Config values may have different semantics between OpenClaw and Hermes.
+# Instruction/context files (.md) can contain incompatible setup procedures.
+_HIGH_IMPACT_KIND_KEYWORDS = {
+    "gateway": "⚠ Gateway/messaging — this will configure Hermes to use your OpenClaw messaging channels",
+    "telegram": "⚠ Telegram — this will point Hermes at your OpenClaw Telegram bot",
+    "slack": "⚠ Slack — this will point Hermes at your OpenClaw Slack workspace",
+    "discord": "⚠ Discord — this will point Hermes at your OpenClaw Discord bot",
+    "whatsapp": "⚠ WhatsApp — this will point Hermes at your OpenClaw WhatsApp connection",
+    "config": "⚠ Config values — OpenClaw settings may not map 1:1 to Hermes equivalents",
+    "soul": "⚠ Instruction file — may contain OpenClaw-specific setup/restart procedures",
+    "memory": "⚠ Memory/context file — may reference OpenClaw-specific infrastructure",
+    "context": "⚠ Context file — may contain OpenClaw-specific instructions",
+}
+
+
+def _print_migration_preview(report: dict):
+    """Print a detailed dry-run preview of what migration would do.
+
+    Groups items by category and adds explicit warnings for high-impact
+    changes like gateway token takeover and config value differences.
+    """
+    items = report.get("items", [])
+    if not items:
+        print_info("Nothing to migrate.")
+        return
+
+    migrated_items = [i for i in items if i.get("status") == "migrated"]
+    conflict_items = [i for i in items if i.get("status") == "conflict"]
+    skipped_items = [i for i in items if i.get("status") == "skipped"]
+
+    warnings_shown = set()
+
+    if migrated_items:
+        print(color("  Would import:", Colors.GREEN))
+        for item in migrated_items:
+            kind = item.get("kind", "unknown")
+            dest = item.get("destination", "")
+            if dest:
+                dest_short = str(dest).replace(str(Path.home()), "~")
+                print(f"      {kind:<22s} → {dest_short}")
+            else:
+                print(f"      {kind}")
+
+            # Check for high-impact items and collect warnings
+            kind_lower = kind.lower()
+            dest_lower = str(dest).lower()
+            for keyword, warning in _HIGH_IMPACT_KIND_KEYWORDS.items():
+                if keyword in kind_lower or keyword in dest_lower:
+                    warnings_shown.add(warning)
+        print()
+
+    if conflict_items:
+        print(color("  Would overwrite (conflicts with existing Hermes config):", Colors.YELLOW))
+        for item in conflict_items:
+            kind = item.get("kind", "unknown")
+            reason = item.get("reason", "already exists")
+            print(f"      {kind:<22s}  {reason}")
+        print()
+
+    if skipped_items:
+        print(color("  Would skip:", Colors.DIM))
+        for item in skipped_items:
+            kind = item.get("kind", "unknown")
+            reason = item.get("reason", "")
+            print(f"      {kind:<22s}  {reason}")
+        print()
+
+    # Print collected warnings
+    if warnings_shown:
+        print(color("  ── Warnings ──", Colors.YELLOW))
+        for warning in sorted(warnings_shown):
+            print(color(f"    {warning}", Colors.YELLOW))
+        print()
+        print(color("  Note: OpenClaw config values may have different semantics in Hermes.", Colors.YELLOW))
+        print(color("  For example, OpenClaw's tool_call_execution: \"auto\" ≠ Hermes's yolo mode.", Colors.YELLOW))
+        print(color("  Instruction files (.md) from OpenClaw may contain incompatible procedures.", Colors.YELLOW))
+        print()
+
+
 def _offer_openclaw_migration(hermes_home: Path) -> bool:
    """Detect ~/.openclaw and offer to migrate during first-time setup.

+    Runs a dry-run first to show the user exactly what would be imported,
+    overwritten, or taken over. Only executes after explicit confirmation.
+
    Returns True if migration ran successfully, False otherwise.
    """
    openclaw_dir = Path.home() / ".openclaw"
@@ -2504,12 +2559,12 @@ def _offer_openclaw_migration(hermes_home: Path) -> bool:
    print()
    print_header("OpenClaw Installation Detected")
    print_info(f"Found OpenClaw data at {openclaw_dir}")
-    print_info("Hermes can import your settings, memories, skills, and API keys.")
+    print_info("Hermes can preview what would be imported before making any changes.")
    print()

-    if not prompt_yes_no("Would you like to import from OpenClaw?", default=True):
+    if not prompt_yes_no("Would you like to see what can be imported?", default=True):
        print_info(
-            "Skipping migration. You can run it later via the openclaw-migration skill."
+            "Skipping migration. You can run it later with: hermes claw migrate --dry-run"
        )
        return False

@@ -2518,34 +2573,71 @@ def _offer_openclaw_migration(hermes_home: Path) -> bool:
    if not config_path.exists():
        save_config(load_config())

-    # Dynamically load the migration script
+    # Load the migration module
    try:
-        spec = importlib.util.spec_from_file_location(
-            "openclaw_to_hermes", _OPENCLAW_SCRIPT
-        )
-        if spec is None or spec.loader is None:
+        mod = _load_openclaw_migration_module()
+        if mod is None:
            print_warning("Could not load migration script.")
            return False
+    except Exception as e:
+        print_warning(f"Could not load migration script: {e}")
+        logger.debug("OpenClaw migration module load error", exc_info=True)
+        return False

-        mod = importlib.util.module_from_spec(spec)
-        # Register in sys.modules so @dataclass can resolve the module
-        # (Python 3.11+ requires this for dynamically loaded modules)
-        import sys as _sys
-        _sys.modules[spec.name] = mod
-        try:
-            spec.loader.exec_module(mod)
-        except Exception:
-            _sys.modules.pop(spec.name, None)
-            raise
-
-        # Run migration with the "full" preset, execute mode, no overwrite
+    # ── Phase 1: Dry-run preview ──
+    try:
        selected = mod.resolve_selected_options(None, None, preset="full")
+        dry_migrator = mod.Migrator(
+            source_root=openclaw_dir.resolve(),
+            target_root=hermes_home.resolve(),
+            execute=False,  # dry-run — no files modified
+            workspace_target=None,
+            overwrite=True,  # show everything including conflicts
+            migrate_secrets=True,
+            output_dir=None,
+            selected_options=selected,
+            preset_name="full",
+        )
+        preview_report = dry_migrator.migrate()
+    except Exception as e:
+        print_warning(f"Migration preview failed: {e}")
+        logger.debug("OpenClaw migration preview error", exc_info=True)
+        return False
+
+    # Display the full preview
+    preview_summary = preview_report.get("summary", {})
+    preview_count = preview_summary.get("migrated", 0)
+
+    if preview_count == 0:
+        print()
+        print_info("Nothing to import from OpenClaw.")
+        return False
+
+    print()
+    print_header(f"Migration Preview — {preview_count} item(s) would be imported")
+    print_info("No changes have been made yet. Review the list below:")
+    print()
+    _print_migration_preview(preview_report)
+
+    # ── Phase 2: Confirm and execute ──
+    if not prompt_yes_no("Proceed with migration?", default=False):
+        print_info(
+            "Migration cancelled. You can run it later with: hermes claw migrate"
+        )
+        print_info(
+            "Use --dry-run to preview again, or --preset minimal for a lighter import."
+        )
+        return False
+
+    # Execute the migration — overwrite=False so existing Hermes configs are
+    # preserved. The user saw the preview; conflicts are skipped by default.
+    try:
        migrator = mod.Migrator(
            source_root=openclaw_dir.resolve(),
            target_root=hermes_home.resolve(),
            execute=True,
            workspace_target=None,
-            overwrite=True,
+            overwrite=False,  # preserve existing Hermes config
            migrate_secrets=True,
            output_dir=None,
            selected_options=selected,
@@ -2557,7 +2649,7 @@ def _offer_openclaw_migration(hermes_home: Path) -> bool:
        logger.debug("OpenClaw migration error", exc_info=True)
        return False

-    # Print summary
+    # Print final summary
    summary = report.get("summary", {})
    migrated = summary.get("migrated", 0)
    skipped = summary.get("skipped", 0)
@@ -2568,7 +2660,7 @@ def _offer_openclaw_migration(hermes_home: Path) -> bool:
    if migrated:
        print_success(f"Imported {migrated} item(s) from OpenClaw.")
    if conflicts:
-        print_info(f"Skipped {conflicts} item(s) that already exist in Hermes.")
+        print_info(f"Skipped {conflicts} item(s) that already exist in Hermes (use hermes claw migrate --overwrite to force).")
    if skipped:
        print_info(f"Skipped {skipped} item(s) (not found or unchanged).")
    if errors:
@@ -2613,6 +2705,7 @@ def run_setup_wizard(args):
    Supports full, quick, and section-specific setup:
      hermes setup           — full or quick (auto-detected)
      hermes setup model     — just model/provider
+      hermes setup tts       — just text-to-speech
      hermes setup terminal  — just terminal backend
      hermes setup gateway   — just messaging platforms
      hermes setup tools     — just tool configuration
@@ -2624,6 +2717,11 @@ def run_setup_wizard(args):
        return
    ensure_hermes_home()

+    reset_requested = bool(getattr(args, "reset", False))
+    if reset_requested:
+        save_config(copy.deepcopy(DEFAULT_CONFIG))
+        print_success("Configuration reset to defaults.")
+
    config = load_config()
    hermes_home = get_hermes_home()

@@ -2724,18 +2822,13 @@ def run_setup_wizard(args):
        menu_choices = [
            "Quick Setup - configure missing items only",
            "Full Setup - reconfigure everything",
-            "---",
            "Model & Provider",
            "Terminal Backend",
            "Messaging Platforms (Gateway)",
            "Tools",
            "Agent Settings",
-            "---",
            "Exit",
        ]
-
-        # Separator indices (not selectable, but prompt_choice doesn't filter them,
-        # so we handle them below)
        choice = prompt_choice("What would you like to do?", menu_choices, 0)

        if choice == 0:
@@ -2745,18 +2838,14 @@ def run_setup_wizard(args):
        elif choice == 1:
            # Full setup — fall through to run all sections
            pass
-        elif choice in (2, 8):
-            # Separator — treat as exit
+        elif choice == 7:
            print_info("Exiting. Run 'hermes setup' again when ready.")
            return
-        elif choice == 9:
-            print_info("Exiting. Run 'hermes setup' again when ready.")
-            return
-        elif 3 <= choice <= 7:
+        elif 2 <= choice <= 6:
            # Individual section — map by key, not by position.
            # SETUP_SECTIONS includes TTS but the returning-user menu skips it,
-            # so positional indexing (choice - 3) would dispatch the wrong section.
-            section_key = RETURNING_USER_MENU_SECTION_KEYS[choice - 3]
+            # so positional indexing (choice - 2) would dispatch the wrong section.
+            section_key = RETURNING_USER_MENU_SECTION_KEYS[choice - 2]
            section = next((s for s in SETUP_SECTIONS if s[0] == section_key), None)
            if section:
                _, label, func = section
@@ -23,6 +23,7 @@ PLATFORMS = {
    "slack":    "💼 Slack",
    "whatsapp": "📱 WhatsApp",
    "signal":   "📡 Signal",
+    "bluebubbles": "💬 BlueBubbles",
    "email":    "📧 Email",
    "homeassistant": "🏠 Home Assistant",
    "mattermost": "💬 Mattermost",
@@ -79,6 +79,9 @@ def _effective_provider_label() -> str:
    return provider_label(effective)


+from hermes_constants import is_termux as _is_termux
+
+
 def show_status(args):
    """Show status of all Hermes Agent components."""
    show_all = getattr(args, 'all', False)
@@ -153,12 +156,14 @@ def show_status(args):
    print(color("◆ Auth Providers", Colors.CYAN, Colors.BOLD))

    try:
-        from hermes_cli.auth import get_nous_auth_status, get_codex_auth_status
+        from hermes_cli.auth import get_nous_auth_status, get_codex_auth_status, get_qwen_auth_status
        nous_status = get_nous_auth_status()
        codex_status = get_codex_auth_status()
+        qwen_status = get_qwen_auth_status()
    except Exception:
        nous_status = {}
        codex_status = {}
+        qwen_status = {}

    nous_logged_in = bool(nous_status.get("logged_in"))
    print(
@@ -189,6 +194,21 @@ def show_status(args):
    if codex_status.get("error") and not codex_logged_in:
        print(f"    Error:      {codex_status.get('error')}")

+    qwen_logged_in = bool(qwen_status.get("logged_in"))
+    print(
+        f"  {'Qwen OAuth':<12}  {check_mark(qwen_logged_in)} "
+        f"{'logged in' if qwen_logged_in else 'not logged in (run: qwen auth qwen-oauth)'}"
+    )
+    qwen_auth_file = qwen_status.get("auth_file")
+    if qwen_auth_file:
+        print(f"    Auth file:  {qwen_auth_file}")
+    qwen_exp = qwen_status.get("expires_at_ms")
+    if qwen_exp:
+        from datetime import datetime, timezone
+        print(f"    Access exp: {datetime.fromtimestamp(int(qwen_exp) / 1000, tz=timezone.utc).isoformat()}")
+    if qwen_status.get("error") and not qwen_logged_in:
+        print(f"    Error:      {qwen_status.get('error')}")
+
    # =========================================================================
    # Nous Subscription Features
    # =========================================================================
@@ -285,6 +305,7 @@ def show_status(args):
        "DingTalk": ("DINGTALK_CLIENT_ID", None),
        "Feishu": ("FEISHU_APP_ID", "FEISHU_HOME_CHANNEL"),
        "WeCom": ("WECOM_BOT_ID", "WECOM_HOME_CHANNEL"),
+        "BlueBubbles": ("BLUEBUBBLES_SERVER_URL", "BLUEBUBBLES_HOME_CHANNEL"),
    }
    
    for name, (token_var, home_var) in platforms.items():
@@ -307,7 +328,25 @@ def show_status(args):
    print()
    print(color("◆ Gateway Service", Colors.CYAN, Colors.BOLD))
    
-    if sys.platform.startswith('linux'):
+    if _is_termux():
+        try:
+            from hermes_cli.gateway import find_gateway_pids
+            gateway_pids = find_gateway_pids()
+        except Exception:
+            gateway_pids = []
+        is_running = bool(gateway_pids)
+        print(f"  Status:       {check_mark(is_running)} {'running' if is_running else 'stopped'}")
+        print("  Manager:      Termux / manual process")
+        if gateway_pids:
+            rendered = ", ".join(str(pid) for pid in gateway_pids[:3])
+            if len(gateway_pids) > 3:
+                rendered += ", ..."
+            print(f"  PID(s):       {rendered}")
+        else:
+            print("  Start with:   hermes gateway")
+            print("  Note:         Android may stop background jobs when Termux is suspended")
+
+    elif sys.platform.startswith('linux'):
        try:
            from hermes_cli.gateway import get_service_name
            _gw_svc = get_service_name()
@@ -321,7 +360,7 @@ def show_status(args):
                timeout=5
            )
            is_active = result.stdout.strip() == "active"
-        except subprocess.TimeoutExpired:
+        except (FileNotFoundError, subprocess.TimeoutExpired):
            is_active = False
        print(f"  Status:       {check_mark(is_active)} {'running' if is_active else 'stopped'}")
        print("  Manager:      systemd (user)")
@@ -126,6 +126,7 @@ PLATFORMS = {
    "slack":    {"label": "💼 Slack",      "default_toolset": "hermes-slack"},
    "whatsapp": {"label": "📱 WhatsApp",   "default_toolset": "hermes-whatsapp"},
    "signal":   {"label": "📡 Signal",     "default_toolset": "hermes-signal"},
+    "bluebubbles": {"label": "💙 BlueBubbles", "default_toolset": "hermes-bluebubbles"},
    "homeassistant": {"label": "🏠 Home Assistant", "default_toolset": "hermes-homeassistant"},
    "email":    {"label": "📧 Email",      "default_toolset": "hermes-email"},
    "matrix":   {"label": "💬 Matrix",     "default_toolset": "hermes-matrix"},
@@ -554,6 +555,7 @@ def _get_platform_tools(
    # MCP servers are expected to be available on all platforms by default.
    # If the platform explicitly lists one or more MCP server names, treat that
    # as an allowlist. Otherwise include every globally enabled MCP server.
+    # Special sentinel: "no_mcp" in the toolset list disables all MCP servers.
    mcp_servers = config.get("mcp_servers") or {}
    enabled_mcp_servers = {
        name
@@ -561,10 +563,15 @@ def _get_platform_tools(
        if isinstance(server_cfg, dict)
        and _parse_enabled_flag(server_cfg.get("enabled", True), default=True)
    }
-    explicit_mcp_servers = explicit_passthrough & enabled_mcp_servers
-    enabled_toolsets.update(explicit_passthrough - enabled_mcp_servers)
+    # Allow "no_mcp" sentinel to opt out of all MCP servers for this platform
+    if "no_mcp" in toolset_names:
+        explicit_mcp_servers = set()
+        enabled_toolsets.update(explicit_passthrough - enabled_mcp_servers - {"no_mcp"})
+    else:
+        explicit_mcp_servers = explicit_passthrough & enabled_mcp_servers
+        enabled_toolsets.update(explicit_passthrough - enabled_mcp_servers)
    if include_default_mcp_servers:
-        if explicit_mcp_servers:
+        if explicit_mcp_servers or "no_mcp" in toolset_names:
            enabled_toolsets.update(explicit_mcp_servers)
        else:
            enabled_toolsets.update(enabled_mcp_servers)
@@ -6,6 +6,8 @@ Provides options for:
 - Keep data: Remove code but keep ~/.hermes/ (configs, sessions, logs)
 """

+import os
+import platform
 import shutil
 import subprocess
 from pathlib import Path
@@ -122,6 +124,10 @@ def uninstall_gateway_service():
    
    if platform.system() != "Linux":
        return False
+
+    prefix = os.getenv("PREFIX", "")
+    if os.getenv("TERMUX_VERSION") or "com.termux/files/usr" in prefix:
+        return False
    
    try:
        from hermes_cli.gateway import get_service_name
@@ -72,13 +72,13 @@ def display_hermes_home() -> str:
        return str(home)


-VALID_REASONING_EFFORTS = ("xhigh", "high", "medium", "low", "minimal")
+VALID_REASONING_EFFORTS = ("minimal", "low", "medium", "high", "xhigh")


 def parse_reasoning_effort(effort: str) -> dict | None:
    """Parse a reasoning effort level into a config dict.

-    Valid levels: "xhigh", "high", "medium", "low", "minimal", "none".
+    Valid levels: "none", "minimal", "low", "medium", "high", "xhigh".
    Returns None when the input is empty or unrecognized (caller uses default).
    Returns {"enabled": False} for "none".
    Returns {"enabled": True, "effort": <level>} for valid effort levels.
@@ -93,13 +93,19 @@ def parse_reasoning_effort(effort: str) -> dict | None:
    return None


+def is_termux() -> bool:
+    """Return True when running inside a Termux (Android) environment.
+
+    Checks ``TERMUX_VERSION`` (set by Termux) or the Termux-specific
+    ``PREFIX`` path.  Import-safe — no heavy deps.
+    """
+    prefix = os.getenv("PREFIX", "")
+    return bool(os.getenv("TERMUX_VERSION") or "com.termux/files/usr" in prefix)
+
+
 OPENROUTER_BASE_URL = "https://openrouter.ai/api/v1"
 OPENROUTER_MODELS_URL = f"{OPENROUTER_BASE_URL}/models"
-OPENROUTER_CHAT_URL = f"{OPENROUTER_BASE_URL}/chat/completions"

 AI_GATEWAY_BASE_URL = "https://ai-gateway.vercel.sh/v1"
-AI_GATEWAY_MODELS_URL = f"{AI_GATEWAY_BASE_URL}/models"
-AI_GATEWAY_CHAT_URL = f"{AI_GATEWAY_BASE_URL}/chat/completions"

 NOUS_API_BASE_URL = "https://inference-api.nousresearch.com/v1"
-NOUS_API_CHAT_URL = f"{NOUS_API_BASE_URL}/chat/completions"
@@ -13,6 +13,7 @@ secrets are never written to disk.
 """

 import logging
+import os
 from logging.handlers import RotatingFileHandler
 from pathlib import Path
 from typing import Optional
@@ -177,6 +178,38 @@ def setup_verbose_logging() -> None:
 # Internal helpers
 # ---------------------------------------------------------------------------

+class _ManagedRotatingFileHandler(RotatingFileHandler):
+    """RotatingFileHandler that ensures group-writable perms in managed mode.
+
+    In managed mode (NixOS), the stateDir uses setgid (2770) so new files
+    inherit the hermes group. However, both _open() (initial creation) and
+    doRollover() create files via open(), which uses the process umask —
+    typically 0022, producing 0644. This subclass applies chmod 0660 after
+    both operations so the gateway and interactive users can share log files.
+    """
+
+    def __init__(self, *args, **kwargs):
+        from hermes_cli.config import is_managed
+        self._managed = is_managed()
+        super().__init__(*args, **kwargs)
+
+    def _chmod_if_managed(self):
+        if self._managed:
+            try:
+                os.chmod(self.baseFilename, 0o660)
+            except OSError:
+                pass
+
+    def _open(self):
+        stream = super()._open()
+        self._chmod_if_managed()
+        return stream
+
+    def doRollover(self):
+        super().doRollover()
+        self._chmod_if_managed()
+
+
 def _add_rotating_handler(
    logger: logging.Logger,
    path: Path,
@@ -198,7 +231,7 @@ def _add_rotating_handler(
            return  # already attached

    path.parent.mkdir(parents=True, exist_ok=True)
-    handler = RotatingFileHandler(
+    handler = _ManagedRotatingFileHandler(
        str(path), maxBytes=max_bytes, backupCount=backup_count,
    )
    handler.setLevel(level)
@@ -520,72 +520,6 @@ class SessionDB:
            )
        self._execute_write(_do)

-    def set_token_counts(
-        self,
-        session_id: str,
-        input_tokens: int = 0,
-        output_tokens: int = 0,
-        model: str = None,
-        cache_read_tokens: int = 0,
-        cache_write_tokens: int = 0,
-        reasoning_tokens: int = 0,
-        estimated_cost_usd: Optional[float] = None,
-        actual_cost_usd: Optional[float] = None,
-        cost_status: Optional[str] = None,
-        cost_source: Optional[str] = None,
-        pricing_version: Optional[str] = None,
-        billing_provider: Optional[str] = None,
-        billing_base_url: Optional[str] = None,
-        billing_mode: Optional[str] = None,
-    ) -> None:
-        """Set token counters to absolute values (not increment).
-
-        Use this when the caller provides cumulative totals from a completed
-        conversation run (e.g. the gateway, where the cached agent's
-        session_prompt_tokens already reflects the running total).
-        """
-        def _do(conn):
-            conn.execute(
-                """UPDATE sessions SET
-                   input_tokens = ?,
-                   output_tokens = ?,
-                   cache_read_tokens = ?,
-                   cache_write_tokens = ?,
-                   reasoning_tokens = ?,
-                   estimated_cost_usd = ?,
-                   actual_cost_usd = CASE
-                       WHEN ? IS NULL THEN actual_cost_usd
-                       ELSE ?
-                   END,
-                   cost_status = COALESCE(?, cost_status),
-                   cost_source = COALESCE(?, cost_source),
-                   pricing_version = COALESCE(?, pricing_version),
-                   billing_provider = COALESCE(billing_provider, ?),
-                   billing_base_url = COALESCE(billing_base_url, ?),
-                   billing_mode = COALESCE(billing_mode, ?),
-                   model = COALESCE(model, ?)
-                   WHERE id = ?""",
-                (
-                    input_tokens,
-                    output_tokens,
-                    cache_read_tokens,
-                    cache_write_tokens,
-                    reasoning_tokens,
-                    estimated_cost_usd,
-                    actual_cost_usd,
-                    actual_cost_usd,
-                    cost_status,
-                    cost_source,
-                    pricing_version,
-                    billing_provider,
-                    billing_base_url,
-                    billing_mode,
-                    model,
-                    session_id,
-                ),
-            )
-        self._execute_write(_do)
-
    def get_session(self, session_id: str) -> Optional[Dict[str, Any]]:
        """Get a session by ID."""
        with self._lock:
@@ -944,7 +878,8 @@ class SessionDB:
                try:
                    msg["tool_calls"] = json.loads(msg["tool_calls"])
                except (json.JSONDecodeError, TypeError):
-                    pass
+                    logger.warning("Failed to deserialize tool_calls in get_messages, falling back to []")
+                    msg["tool_calls"] = []
            result.append(msg)
        return result

@@ -972,7 +907,8 @@ class SessionDB:
                try:
                    msg["tool_calls"] = json.loads(row["tool_calls"])
                except (json.JSONDecodeError, TypeError):
-                    pass
+                    logger.warning("Failed to deserialize tool_calls in conversation replay, falling back to []")
+                    msg["tool_calls"] = []
            # Restore reasoning fields on assistant messages so providers
            # that replay reasoning (OpenRouter, OpenAI, Nous) receive
            # coherent multi-turn reasoning context.
@@ -983,12 +919,14 @@ class SessionDB:
                    try:
                        msg["reasoning_details"] = json.loads(row["reasoning_details"])
                    except (json.JSONDecodeError, TypeError):
-                        pass
+                        logger.warning("Failed to deserialize reasoning_details, falling back to None")
+                        msg["reasoning_details"] = None
                if row["codex_reasoning_items"]:
                    try:
                        msg["codex_reasoning_items"] = json.loads(row["codex_reasoning_items"])
                    except (json.JSONDecodeError, TypeError):
-                        pass
+                        logger.warning("Failed to deserialize codex_reasoning_items, falling back to None")
+                        msg["codex_reasoning_items"] = None
            messages.append(msg)
        return messages

@@ -1235,10 +1173,10 @@ class SessionDB:
        self._execute_write(_do)

    def delete_session(self, session_id: str) -> bool:
-        """Delete a session, its child sessions, and all their messages.
+        """Delete a session and all its messages.

-        Child sessions (subagent runs, compression continuations) are deleted
-        first to satisfy the ``parent_session_id`` foreign key constraint.
+        Child sessions are orphaned (parent_session_id set to NULL) rather
+        than cascade-deleted, so they remain accessible independently.
        Returns True if the session was found and deleted.
        """
        def _do(conn):
@@ -1247,15 +1185,12 @@ class SessionDB:
            )
            if cursor.fetchone()[0] == 0:
                return False
-            # Delete child sessions first (FK constraint)
-            child_ids = [r[0] for r in conn.execute(
-                "SELECT id FROM sessions WHERE parent_session_id = ?",
+            # Orphan child sessions so FK constraint is satisfied
+            conn.execute(
+                "UPDATE sessions SET parent_session_id = NULL "
+                "WHERE parent_session_id = ?",
                (session_id,),
-            ).fetchall()]
-            for cid in child_ids:
-                conn.execute("DELETE FROM messages WHERE session_id = ?", (cid,))
-                conn.execute("DELETE FROM sessions WHERE id = ?", (cid,))
-            # Delete the session itself
+            )
            conn.execute("DELETE FROM messages WHERE session_id = ?", (session_id,))
            conn.execute("DELETE FROM sessions WHERE id = ?", (session_id,))
            return True
@@ -1264,9 +1199,9 @@ class SessionDB:
    def prune_sessions(self, older_than_days: int = 90, source: str = None) -> int:
        """Delete sessions older than N days. Returns count of deleted sessions.

-        Only prunes ended sessions (not active ones).  Child sessions whose
-        parents are being pruned are deleted first to satisfy the
-        ``parent_session_id`` foreign key constraint.
+        Only prunes ended sessions (not active ones).  Child sessions outside
+        the prune window are orphaned (parent_session_id set to NULL) rather
+        than cascade-deleted.
        """
        cutoff = time.time() - (older_than_days * 86400)

@@ -1284,17 +1219,16 @@ class SessionDB:
                )
            session_ids = set(row["id"] for row in cursor.fetchall())

-            # Delete children first whose parents are in the prune set
-            # (avoids FK constraint errors)
-            for sid in list(session_ids):
-                child_ids = [r[0] for r in conn.execute(
-                    "SELECT id FROM sessions WHERE parent_session_id = ?",
-                    (sid,),
-                ).fetchall()]
-                for cid in child_ids:
-                    conn.execute("DELETE FROM messages WHERE session_id = ?", (cid,))
-                    conn.execute("DELETE FROM sessions WHERE id = ?", (cid,))
-                    session_ids.discard(cid)  # don't double-delete
+            if not session_ids:
+                return 0
+
+            # Orphan any sessions whose parent is about to be deleted
+            placeholders = ",".join("?" * len(session_ids))
+            conn.execute(
+                f"UPDATE sessions SET parent_session_id = NULL "
+                f"WHERE parent_session_id IN ({placeholders})",
+                list(session_ids),
+            )

            for sid in session_ids:
                conn.execute("DELETE FROM messages WHERE session_id = ?", (sid,))
@@ -89,13 +89,6 @@ def get_timezone() -> Optional[ZoneInfo]:
    return _cached_tz


-def get_timezone_name() -> str:
-    """Return the IANA name of the configured timezone, or empty string."""
-    if not _cache_resolved:
-        get_timezone()  # populates cache
-    return _cached_tz_name or ""
-
-
 def now() -> datetime:
    """
    Return the current time as a timezone-aware datetime.
@@ -110,9 +103,3 @@ def now() -> datetime:
    return datetime.now().astimezone()


-def reset_cache() -> None:
-    """Clear the cached timezone. Used by tests and after config changes."""
-    global _cached_tz, _cached_tz_name, _cache_resolved
-    _cached_tz = None
-    _cached_tz_name = None
-    _cache_resolved = False
@@ -464,7 +464,11 @@
      addToSystemPackages = mkOption {
        type = types.bool;
        default = false;
-        description = "Add hermes CLI to environment.systemPackages.";
+        description = ''
+          Add the hermes CLI to environment.systemPackages and export
+          HERMES_HOME system-wide (via environment.variables) so interactive
+          shells share state with the gateway service.
+        '';
      };

      # ── OCI Container (opt-in) ──────────────────────────────────────────
@@ -545,29 +549,51 @@
      })

      # ── Host CLI ──────────────────────────────────────────────────────
+      # Add the hermes CLI to system PATH and export HERMES_HOME system-wide
+      # so interactive shells share state (sessions, skills, cron) with the
+      # gateway service instead of creating a separate ~/.hermes/.
      (lib.mkIf cfg.addToSystemPackages {
        environment.systemPackages = [ cfg.package ];
+        environment.variables.HERMES_HOME = "${cfg.stateDir}/.hermes";
      })

      # ── Directories ───────────────────────────────────────────────────
      {
        systemd.tmpfiles.rules = [
-          "d ${cfg.stateDir}                0750 ${cfg.user} ${cfg.group} - -"
-          "d ${cfg.stateDir}/.hermes        0750 ${cfg.user} ${cfg.group} - -"
+          "d ${cfg.stateDir}                2770 ${cfg.user} ${cfg.group} - -"
+          "d ${cfg.stateDir}/.hermes        2770 ${cfg.user} ${cfg.group} - -"
+          "d ${cfg.stateDir}/.hermes/cron   2770 ${cfg.user} ${cfg.group} - -"
+          "d ${cfg.stateDir}/.hermes/sessions 2770 ${cfg.user} ${cfg.group} - -"
+          "d ${cfg.stateDir}/.hermes/logs   2770 ${cfg.user} ${cfg.group} - -"
+          "d ${cfg.stateDir}/.hermes/memories 2770 ${cfg.user} ${cfg.group} - -"
          "d ${cfg.stateDir}/home           0750 ${cfg.user} ${cfg.group} - -"
-          "d ${cfg.workingDirectory}         0750 ${cfg.user} ${cfg.group} - -"
+          "d ${cfg.workingDirectory}         2770 ${cfg.user} ${cfg.group} - -"
        ];
      }

      # ── Activation: link config + auth + documents ────────────────────
      {
-        system.activationScripts."hermes-agent-setup" = lib.stringAfter [ "users" "setupSecrets" ] ''
+        system.activationScripts."hermes-agent-setup" = lib.stringAfter ([ "users" ] ++ lib.optional (config.system.activationScripts ? setupSecrets) "setupSecrets") ''
          # Ensure directories exist (activation runs before tmpfiles)
          mkdir -p ${cfg.stateDir}/.hermes
          mkdir -p ${cfg.stateDir}/home
          mkdir -p ${cfg.workingDirectory}
          chown ${cfg.user}:${cfg.group} ${cfg.stateDir} ${cfg.stateDir}/.hermes ${cfg.stateDir}/home ${cfg.workingDirectory}
-          chmod 0750 ${cfg.stateDir} ${cfg.stateDir}/.hermes ${cfg.stateDir}/home ${cfg.workingDirectory}
+          chmod 2770 ${cfg.stateDir} ${cfg.stateDir}/.hermes ${cfg.workingDirectory}
+          chmod 0750 ${cfg.stateDir}/home
+
+          # Create subdirs, set setgid + group-writable, migrate existing files.
+          # Nix-managed files (config.yaml, .env, .managed) stay 0640/0644.
+          find ${cfg.stateDir}/.hermes -maxdepth 1 \
+            \( -name "*.db" -o -name "*.db-wal" -o -name "*.db-shm" -o -name "SOUL.md" \) \
+            -exec chmod g+rw {} + 2>/dev/null || true
+          for _subdir in cron sessions logs memories; do
+            mkdir -p "${cfg.stateDir}/.hermes/$_subdir"
+            chown ${cfg.user}:${cfg.group} "${cfg.stateDir}/.hermes/$_subdir"
+            chmod 2770 "${cfg.stateDir}/.hermes/$_subdir"
+            find "${cfg.stateDir}/.hermes/$_subdir" -type f \
+              -exec chmod g+rw {} + 2>/dev/null || true
+          done

          # Merge Nix settings into existing config.yaml.
          # Preserves user-added keys (skills, streaming, etc.); Nix keys win.
@@ -601,7 +627,7 @@
          # so this is the single source of truth for both native and container mode.
          ${lib.optionalString (cfg.environment != {} || cfg.environmentFiles != []) ''
            ENV_FILE="${cfg.stateDir}/.hermes/.env"
-            install -o ${cfg.user} -g ${cfg.group} -m 0600 /dev/null "$ENV_FILE"
+            install -o ${cfg.user} -g ${cfg.group} -m 0640 /dev/null "$ENV_FILE"
            cat > "$ENV_FILE" <<'HERMES_NIX_ENV_EOF'
 ${envFileContent}
 HERMES_NIX_ENV_EOF
@@ -654,6 +680,10 @@ HERMES_NIX_ENV_EOF
            Restart = cfg.restart;
            RestartSec = cfg.restartSec;

+            # Shared-state: files created by the gateway should be group-writable
+            # so interactive users in the hermes group can read/write them.
+            UMask = "0007";
+
            # Hardening
            NoNewPrivileges = true;
            ProtectSystem = "strict";
@@ -14,7 +14,7 @@
      };

      runtimeDeps = with pkgs; [
-        nodejs_20 ripgrep git openssh ffmpeg
+        nodejs_20 ripgrep git openssh ffmpeg tirith
      ];

      runtimePath = pkgs.lib.makeBinPath runtimeDeps;
@@ -6,14 +6,68 @@
  uv2nix,
  pyproject-nix,
  pyproject-build-systems,
+  stdenv,
 }:
 let
  workspace = uv2nix.lib.workspace.loadWorkspace { workspaceRoot = ./..; };
+  hacks = callPackage pyproject-nix.build.hacks { };

  overlay = workspace.mkPyprojectOverlay {
    sourcePreference = "wheel";
  };

+  isAarch64Darwin = stdenv.hostPlatform.system == "aarch64-darwin";
+
+  # Keep the workspace locked through uv2nix, but supply the local voice stack
+  # from nixpkgs so wheel-only transitive artifacts do not break evaluation.
+  mkPrebuiltPassthru = dependencies: {
+    inherit dependencies;
+    optional-dependencies = { };
+    dependency-groups = { };
+  };
+
+  mkPrebuiltOverride = final: from: dependencies:
+    hacks.nixpkgsPrebuilt {
+      inherit from;
+      prev = {
+        nativeBuildInputs = [ final.pyprojectHook ];
+        passthru = mkPrebuiltPassthru dependencies;
+      };
+    };
+
+  pythonPackageOverrides = final: _prev:
+    if isAarch64Darwin then {
+      numpy = mkPrebuiltOverride final python311.pkgs.numpy { };
+
+      av = mkPrebuiltOverride final python311.pkgs.av { };
+
+      humanfriendly = mkPrebuiltOverride final python311.pkgs.humanfriendly { };
+
+      coloredlogs = mkPrebuiltOverride final python311.pkgs.coloredlogs {
+        humanfriendly = [ ];
+      };
+
+      onnxruntime = mkPrebuiltOverride final python311.pkgs.onnxruntime {
+        coloredlogs = [ ];
+        numpy = [ ];
+        packaging = [ ];
+      };
+
+      ctranslate2 = mkPrebuiltOverride final python311.pkgs.ctranslate2 {
+        numpy = [ ];
+        pyyaml = [ ];
+      };
+
+      faster-whisper = mkPrebuiltOverride final python311.pkgs.faster-whisper {
+        av = [ ];
+        ctranslate2 = [ ];
+        huggingface-hub = [ ];
+        onnxruntime = [ ];
+        tokenizers = [ ];
+        tqdm = [ ];
+      };
+    } else {};
+
  pythonSet =
    (callPackage pyproject-nix.build.packages {
      python = python311;
@@ -21,6 +75,7 @@ let
      (lib.composeManyExtensions [
        pyproject-build-systems.overlays.default
        overlay
+        pythonPackageOverrides
      ]);
 in
 pythonSet.mkVirtualEnv "hermes-agent-env" {
@@ -1803,30 +1803,34 @@ class Migrator:
    def migrate_cron_jobs(self, config: Optional[Dict[str, Any]] = None) -> None:
        config = config or self.load_openclaw_config()
        cron = config.get("cron") or {}
-        if not cron:
-            self.record("cron-jobs", None, None, "skipped", "No cron configuration found")
-            return
-
-        # Archive the full cron config
-        if self.archive_dir and self.execute:
-            self.archive_dir.mkdir(parents=True, exist_ok=True)
-            dest = self.archive_dir / "cron-config.json"
-            dest.write_text(json.dumps(cron, indent=2, ensure_ascii=False) + "\n", encoding="utf-8")
-            self.record("cron-jobs", "openclaw.json cron.*", str(dest), "archived",
-                        "Cron config archived. Use 'hermes cron' to recreate jobs manually.")
-        else:
-            self.record("cron-jobs", "openclaw.json cron.*", "archive/cron-config.json",
-                        "archived", "Would archive cron config")
-
-        # Also check for cron store files
        cron_store = self.source_root / "cron"
+        found_any = False
+
+        # Archive the full cron config when present
+        if cron:
+            found_any = True
+            if self.archive_dir and self.execute:
+                self.archive_dir.mkdir(parents=True, exist_ok=True)
+                dest = self.archive_dir / "cron-config.json"
+                dest.write_text(json.dumps(cron, indent=2, ensure_ascii=False) + "\n", encoding="utf-8")
+                self.record("cron-jobs", "openclaw.json cron.*", str(dest), "archived",
+                            "Cron config archived. Use 'hermes cron' to recreate jobs manually.")
+            else:
+                self.record("cron-jobs", "openclaw.json cron.*", "archive/cron-config.json",
+                            "archived", "Would archive cron config")
+
+        # Also check for cron store files even when config.cron is missing
        if cron_store.is_dir() and self.archive_dir:
+            found_any = True
            dest_cron = self.archive_dir / "cron-store"
            if self.execute:
                shutil.copytree(cron_store, dest_cron, dirs_exist_ok=True)
            self.record("cron-jobs", str(cron_store), str(dest_cron), "archived",
                        "Cron job store archived")

+        if not found_any:
+            self.record("cron-jobs", None, None, "skipped", "No cron configuration found")
+
    # ── Hooks ─────────────────────────────────────────────────
    def migrate_hooks_config(self, config: Optional[Dict[str, Any]] = None) -> None:
        config = config or self.load_openclaw_config()
@@ -2454,6 +2458,15 @@ class Migrator:
                notes.append(f"- **{item.kind}**: {item.reason}")
            notes.append("")

+        has_cron_config_archive = any(
+            i.kind == "cron-jobs" and i.status == "archived" and i.destination and i.destination.endswith("cron-config.json")
+            for i in self.items
+        )
+        has_cron_store_archive = any(
+            i.kind == "cron-jobs" and i.status == "archived" and i.destination and i.destination.endswith("cron-store")
+            for i in self.items
+        )
+
        notes.extend([
            "## IMPORTANT: Archive the OpenClaw Directory",
            "",
@@ -2475,7 +2488,14 @@ class Migrator:
            "- Run `hermes claw cleanup` to archive the OpenClaw directory (prevents state confusion)",
            "- Run `hermes setup` to configure any remaining settings",
            "- Run `hermes mcp list` to verify MCP servers were imported correctly",
-            "- Run `hermes cron` to recreate scheduled tasks (see archive/cron-config.json)",
+        ])
+
+        if has_cron_config_archive:
+            notes.append("- Run `hermes cron` to recreate scheduled tasks (see archive/cron-config.json)")
+        elif has_cron_store_archive:
+            notes.append("- Run `hermes cron` to recreate scheduled tasks (see archived cron-store)")
+
+        notes.extend([
            "- Run `hermes gateway install` if you need the gateway service",
            "- Review `~/.hermes/config.yaml` for any adjustments",
            "",
@@ -1,11 +1,12 @@
 # Hindsight Memory Provider

-Long-term memory with knowledge graph, entity resolution, and multi-strategy retrieval. Supports cloud and local (embedded) modes.
+Long-term memory with knowledge graph, entity resolution, and multi-strategy retrieval. Supports cloud, local embedded, and local external modes.

 ## Requirements

 - **Cloud:** API key from [ui.hindsight.vectorize.io](https://ui.hindsight.vectorize.io)
- **Local:** API key for a supported LLM provider (OpenAI, Anthropic, Gemini, Groq, MiniMax, or Ollama). Embeddings and reranking run locally — no additional API keys needed.
+- **Local Embedded:** API key for a supported LLM provider (OpenAI, Anthropic, Gemini, Groq, OpenRouter, MiniMax, Ollama, or any OpenAI-compatible endpoint). Embeddings and reranking run locally — no additional API keys needed.
+- **Local External:** A running Hindsight instance (Docker or self-hosted) reachable over HTTP.

 ## Setup

@@ -21,17 +22,28 @@ hermes config set memory.provider hindsight
 echo "HINDSIGHT_API_KEY=your-key" >> ~/.hermes/.env
 ```

-### Cloud Mode
+### Cloud

 Connects to the Hindsight Cloud API. Requires an API key from [ui.hindsight.vectorize.io](https://ui.hindsight.vectorize.io).

-### Local Mode
+### Local Embedded

-Runs an embedded Hindsight server with built-in PostgreSQL. Requires an LLM API key (e.g. Groq, OpenAI, Anthropic) for memory extraction and synthesis. The daemon starts automatically in the background on first use and stops after 5 minutes of inactivity.
+Hermes spins up a local Hindsight daemon with built-in PostgreSQL. Requires an LLM API key for memory extraction and synthesis. The daemon starts automatically in the background on first use and stops after 5 minutes of inactivity.
+
+Supports any OpenAI-compatible LLM endpoint (llama.cpp, vLLM, LM Studio, etc.) — pick `openai_compatible` as the provider and enter the base URL.

 Daemon startup logs: `~/.hermes/logs/hindsight-embed.log`
 Daemon runtime logs: `~/.hindsight/profiles/<profile>.log`

+To open the Hindsight web UI (local embedded mode only):
+```bash
+hindsight-embed -p hermes ui start
+```
+
+### Local External
+
+Points the plugin at an existing Hindsight instance you're already running (Docker, self-hosted, etc.). No daemon management — just a URL and an optional API key.
+
 ## Config

 Config file: `~/.hermes/hindsight/config.json`
@@ -40,39 +52,58 @@ Config file: `~/.hermes/hindsight/config.json`

 | Key | Default | Description |
 |-----|---------|-------------|
-| `mode` | `cloud` | `cloud` or `local` |
-| `api_url` | `https://api.hindsight.vectorize.io` | API URL (cloud mode) |
-| `api_url` | `http://localhost:8888` | API URL (local mode, unused — daemon manages its own port) |
+| `mode` | `cloud` | `cloud`, `local_embedded`, or `local_external` |
+| `api_url` | `https://api.hindsight.vectorize.io` | API URL (cloud and local_external modes) |

-### Memory
+### Memory Bank

 | Key | Default | Description |
 |-----|---------|-------------|
 | `bank_id` | `hermes` | Memory bank name |
-| `budget` | `mid` | Recall thoroughness: `low` / `mid` / `high` |
+| `bank_mission` | — | Reflect mission (identity/framing for reflect reasoning). Applied via Banks API. |
+| `bank_retain_mission` | — | Retain mission (steers what gets extracted). Applied via Banks API. |
+
+### Recall
+
+| Key | Default | Description |
+|-----|---------|-------------|
+| `recall_budget` | `mid` | Recall thoroughness: `low` / `mid` / `high` |
+| `recall_prefetch_method` | `recall` | Auto-recall method: `recall` (raw facts) or `reflect` (LLM synthesis) |
+| `recall_max_tokens` | `4096` | Maximum tokens for recall results |
+| `recall_max_input_chars` | `800` | Maximum input query length for auto-recall |
+| `recall_prompt_preamble` | — | Custom preamble for recalled memories in context |
+| `recall_tags` | — | Tags to filter when searching memories |
+| `recall_tags_match` | `any` | Tag matching mode: `any` / `all` / `any_strict` / `all_strict` |
+| `auto_recall` | `true` | Automatically recall memories before each turn |
+
+### Retain
+
+| Key | Default | Description |
+|-----|---------|-------------|
+| `auto_retain` | `true` | Automatically retain conversation turns |
+| `retain_async` | `true` | Process retain asynchronously on the Hindsight server |
+| `retain_every_n_turns` | `1` | Retain every N turns (1 = every turn) |
+| `retain_context` | `conversation between Hermes Agent and the User` | Context label for retained memories |
+| `tags` | — | Tags applied when storing memories |

 ### Integration

 | Key | Default | Description |
 |-----|---------|-------------|
 | `memory_mode` | `hybrid` | How memories are integrated into the agent |
-| `prefetch_method` | `recall` | Method for automatic context injection |

 **memory_mode:**
 - `hybrid` — automatic context injection + tools available to the LLM
 - `context` — automatic injection only, no tools exposed
 - `tools` — tools only, no automatic injection

-**prefetch_method:**
- `recall` — injects raw memory facts (fast)
- `reflect` — injects LLM-synthesized summary (slower, more coherent)
-
-### Local Mode LLM
+### Local Embedded LLM

 | Key | Default | Description |
 |-----|---------|-------------|
-| `llm_provider` | `openai` | LLM provider: `openai`, `anthropic`, `gemini`, `groq`, `minimax`, `ollama` |
-| `llm_model` | per-provider | Model name (e.g. `gpt-4o-mini`, `openai/gpt-oss-120b`) |
+| `llm_provider` | `openai` | `openai`, `anthropic`, `gemini`, `groq`, `openrouter`, `minimax`, `ollama`, `lmstudio`, `openai_compatible` |
+| `llm_model` | per-provider | Model name (e.g. `gpt-4o-mini`, `qwen/qwen3.5-9b`) |
+| `llm_base_url` | — | Endpoint URL for `openai_compatible` (e.g. `http://192.168.1.10:8080/v1`) |

 The LLM API key is stored in `~/.hermes/.env` as `HINDSIGHT_LLM_API_KEY`.

@@ -92,7 +123,12 @@ Available in `hybrid` and `tools` memory modes:
 |----------|-------------|
 | `HINDSIGHT_API_KEY` | API key for Hindsight Cloud |
 | `HINDSIGHT_LLM_API_KEY` | LLM API key for local mode |
+| `HINDSIGHT_API_LLM_BASE_URL` | LLM Base URL for local mode (e.g. OpenRouter) |
 | `HINDSIGHT_API_URL` | Override API endpoint |
 | `HINDSIGHT_BANK_ID` | Override bank name |
 | `HINDSIGHT_BUDGET` | Override recall budget |
-| `HINDSIGHT_MODE` | Override mode (`cloud` / `local`) |
+| `HINDSIGHT_MODE` | Override mode (`cloud`, `local_embedded`, `local_external`) |
+
+## Client Version
+
+Requires `hindsight-client >= 0.4.22`. The plugin auto-upgrades on session start if an older version is detected.
@@ -23,24 +23,30 @@ import json
 import logging
 import os
 import threading
+
+from hermes_constants import get_hermes_home
 from typing import Any, Dict, List

 from agent.memory_provider import MemoryProvider
+from hermes_constants import get_hermes_home
 from tools.registry import tool_error

 logger = logging.getLogger(__name__)

 _DEFAULT_API_URL = "https://api.hindsight.vectorize.io"
 _DEFAULT_LOCAL_URL = "http://localhost:8888"
+_MIN_CLIENT_VERSION = "0.4.22"
 _VALID_BUDGETS = {"low", "mid", "high"}
 _PROVIDER_DEFAULT_MODELS = {
    "openai": "gpt-4o-mini",
    "anthropic": "claude-haiku-4-5",
    "gemini": "gemini-2.5-flash",
    "groq": "openai/gpt-oss-120b",
+    "openrouter": "qwen/qwen3.5-9b",
    "minimax": "MiniMax-M2.7",
    "ollama": "gemma3:12b",
    "lmstudio": "local-model",
+    "openai_compatible": "your-model-name",
 }


@@ -142,7 +148,6 @@ def _load_config() -> dict:
      3. Environment variables
    """
    from pathlib import Path
-    from hermes_constants import get_hermes_home

    # Profile-scoped path (preferred)
    profile_path = get_hermes_home() / "hindsight" / "config.json"
@@ -187,6 +192,7 @@ class HindsightMemoryProvider(MemoryProvider):
        self._bank_id = "hermes"
        self._budget = "mid"
        self._mode = "cloud"
+        self._llm_base_url = ""
        self._memory_mode = "hybrid"  # "context", "tools", or "hybrid"
        self._prefetch_method = "recall"  # "recall" or "reflect"
        self._client = None
@@ -194,6 +200,31 @@ class HindsightMemoryProvider(MemoryProvider):
        self._prefetch_lock = threading.Lock()
        self._prefetch_thread = None
        self._sync_thread = None
+        self._session_id = ""
+
+        # Tags
+        self._tags: list[str] | None = None
+        self._recall_tags: list[str] | None = None
+        self._recall_tags_match = "any"
+
+        # Retain controls
+        self._auto_retain = True
+        self._retain_every_n_turns = 1
+        self._retain_context = "conversation between Hermes Agent and the User"
+        self._turn_counter = 0
+        self._session_turns: list[str] = []  # accumulates ALL turns for the session
+
+        # Recall controls
+        self._auto_recall = True
+        self._recall_max_tokens = 4096
+        self._recall_types: list[str] | None = None
+        self._recall_prompt_preamble = ""
+        self._recall_max_input_chars = 800
+
+        # Bank
+        self._bank_mission = ""
+        self._bank_retain_mission: str | None = None
+        self._retain_async = True

    @property
    def name(self) -> str:
@@ -203,7 +234,7 @@ class HindsightMemoryProvider(MemoryProvider):
        try:
            cfg = _load_config()
            mode = cfg.get("mode", "cloud")
-            if mode == "local":
+            if mode in ("local", "local_embedded", "local_external"):
                return True
            has_key = bool(cfg.get("apiKey") or os.environ.get("HINDSIGHT_API_KEY", ""))
            has_url = bool(cfg.get("api_url") or os.environ.get("HINDSIGHT_API_URL", ""))
@@ -227,68 +258,306 @@ class HindsightMemoryProvider(MemoryProvider):
        existing.update(values)
        config_path.write_text(json.dumps(existing, indent=2))

+    def post_setup(self, hermes_home: str, config: dict) -> None:
+        """Custom setup wizard — installs only the deps needed for the selected mode."""
+        import getpass
+        import subprocess
+        import shutil
+        import sys
+        from pathlib import Path
+
+        from hermes_cli.config import save_config
+
+        from hermes_cli.memory_setup import _curses_select
+
+        print("\n  Configuring Hindsight memory:\n")
+
+        # Step 1: Mode selection
+        mode_items = [
+            ("Cloud", "Hindsight Cloud API (lightweight, just needs an API key)"),
+            ("Local Embedded", "Run Hindsight locally (downloads ~200MB, needs LLM key)"),
+            ("Local External", "Connect to an existing Hindsight instance"),
+        ]
+        mode_idx = _curses_select("  Select mode", mode_items, default=0)
+        mode = ["cloud", "local_embedded", "local_external"][mode_idx]
+
+        provider_config: dict = {"mode": mode}
+        env_writes: dict = {}
+
+        # Step 2: Install/upgrade deps for selected mode
+        _MIN_CLIENT_VERSION = "0.4.22"
+        cloud_dep = f"hindsight-client>={_MIN_CLIENT_VERSION}"
+        local_dep = "hindsight-all"
+        if mode == "local_embedded":
+            deps_to_install = [local_dep]
+        elif mode == "local_external":
+            deps_to_install = [cloud_dep]
+        else:
+            deps_to_install = [cloud_dep]
+
+        print(f"\n  Checking dependencies...")
+        uv_path = shutil.which("uv")
+        if not uv_path:
+            print("  ⚠ uv not found — install it: curl -LsSf https://astral.sh/uv/install.sh | sh")
+            print(f"  Then run manually: uv pip install --python {sys.executable} {' '.join(deps_to_install)}")
+        else:
+            try:
+                subprocess.run(
+                    [uv_path, "pip", "install", "--python", sys.executable, "--quiet", "--upgrade"] + deps_to_install,
+                    check=True, timeout=120, capture_output=True,
+                )
+                print(f"  ✓ Dependencies up to date")
+            except Exception as e:
+                print(f"  ⚠ Install failed: {e}")
+                print(f"  Run manually: uv pip install --python {sys.executable} {' '.join(deps_to_install)}")
+
+        # Step 3: Mode-specific config
+        if mode == "cloud":
+            print(f"\n  Get your API key at https://ui.hindsight.vectorize.io\n")
+            existing_key = os.environ.get("HINDSIGHT_API_KEY", "")
+            if existing_key:
+                masked = f"...{existing_key[-4:]}" if len(existing_key) > 4 else "set"
+                sys.stdout.write(f"  API key (current: {masked}, blank to keep): ")
+                sys.stdout.flush()
+                api_key = getpass.getpass(prompt="") if sys.stdin.isatty() else sys.stdin.readline().strip()
+            else:
+                sys.stdout.write("  API key: ")
+                sys.stdout.flush()
+                api_key = getpass.getpass(prompt="") if sys.stdin.isatty() else sys.stdin.readline().strip()
+            if api_key:
+                env_writes["HINDSIGHT_API_KEY"] = api_key
+
+            val = input(f"  API URL [{_DEFAULT_API_URL}]: ").strip()
+            if val:
+                provider_config["api_url"] = val
+
+        elif mode == "local_external":
+            val = input(f"  Hindsight API URL [{_DEFAULT_LOCAL_URL}]: ").strip()
+            provider_config["api_url"] = val or _DEFAULT_LOCAL_URL
+
+            sys.stdout.write("  API key (optional, blank to skip): ")
+            sys.stdout.flush()
+            api_key = getpass.getpass(prompt="") if sys.stdin.isatty() else sys.stdin.readline().strip()
+            if api_key:
+                env_writes["HINDSIGHT_API_KEY"] = api_key
+
+        else:  # local_embedded
+            providers_list = list(_PROVIDER_DEFAULT_MODELS.keys())
+            llm_items = [
+                (p, f"default model: {_PROVIDER_DEFAULT_MODELS[p]}")
+                for p in providers_list
+            ]
+            llm_idx = _curses_select("  Select LLM provider", llm_items, default=0)
+            llm_provider = providers_list[llm_idx]
+
+            provider_config["llm_provider"] = llm_provider
+
+            if llm_provider == "openai_compatible":
+                val = input("  LLM endpoint URL (e.g. http://192.168.1.10:8080/v1): ").strip()
+                if val:
+                    provider_config["llm_base_url"] = val
+            elif llm_provider == "openrouter":
+                provider_config["llm_base_url"] = "https://openrouter.ai/api/v1"
+
+            default_model = _PROVIDER_DEFAULT_MODELS.get(llm_provider, "gpt-4o-mini")
+            val = input(f"  LLM model [{default_model}]: ").strip()
+            provider_config["llm_model"] = val or default_model
+
+            sys.stdout.write("  LLM API key: ")
+            sys.stdout.flush()
+            llm_key = getpass.getpass(prompt="") if sys.stdin.isatty() else sys.stdin.readline().strip()
+            if llm_key:
+                env_writes["HINDSIGHT_LLM_API_KEY"] = llm_key
+
+        # Step 4: Save everything
+        provider_config["bank_id"] = "hermes"
+        provider_config["recall_budget"] = "mid"
+        bank_id = "hermes"
+        config["memory"]["provider"] = "hindsight"
+        save_config(config)
+
+        self.save_config(provider_config, hermes_home)
+
+        if env_writes:
+            env_path = Path(hermes_home) / ".env"
+            env_path.parent.mkdir(parents=True, exist_ok=True)
+            existing_lines = []
+            if env_path.exists():
+                existing_lines = env_path.read_text().splitlines()
+            updated_keys = set()
+            new_lines = []
+            for line in existing_lines:
+                key_match = line.split("=", 1)[0].strip() if "=" in line and not line.startswith("#") else None
+                if key_match and key_match in env_writes:
+                    new_lines.append(f"{key_match}={env_writes[key_match]}")
+                    updated_keys.add(key_match)
+                else:
+                    new_lines.append(line)
+            for k, v in env_writes.items():
+                if k not in updated_keys:
+                    new_lines.append(f"{k}={v}")
+            env_path.write_text("\n".join(new_lines) + "\n")
+
+        print(f"\n  ✓ Hindsight memory configured ({mode} mode)")
+        if env_writes:
+            print(f"  API keys saved to .env")
+        print(f"\n  Start a new session to activate.\n")
+
    def get_config_schema(self):
        return [
-            {"key": "mode", "description": "Cloud API or local embedded mode", "default": "cloud", "choices": ["cloud", "local"]},
-            {"key": "api_url", "description": "Hindsight API URL", "default": _DEFAULT_API_URL, "when": {"mode": "cloud"}},
+            {"key": "mode", "description": "Connection mode", "default": "cloud", "choices": ["cloud", "local_embedded", "local_external"]},
+            # Cloud mode
+            {"key": "api_url", "description": "Hindsight Cloud API URL", "default": _DEFAULT_API_URL, "when": {"mode": "cloud"}},
            {"key": "api_key", "description": "Hindsight Cloud API key", "secret": True, "env_var": "HINDSIGHT_API_KEY", "url": "https://ui.hindsight.vectorize.io", "when": {"mode": "cloud"}},
-            {"key": "llm_provider", "description": "LLM provider for local mode", "default": "openai", "choices": ["openai", "anthropic", "gemini", "groq", "minimax", "ollama"], "when": {"mode": "local"}},
-            {"key": "llm_api_key", "description": "LLM API key for local Hindsight", "secret": True, "env_var": "HINDSIGHT_LLM_API_KEY", "when": {"mode": "local"}},
-            {"key": "llm_model", "description": "LLM model for local mode", "default": "gpt-4o-mini", "default_from": {"field": "llm_provider", "map": _PROVIDER_DEFAULT_MODELS}, "when": {"mode": "local"}},
+            # Local external mode
+            {"key": "api_url", "description": "Hindsight API URL", "default": _DEFAULT_LOCAL_URL, "when": {"mode": "local_external"}},
+            {"key": "api_key", "description": "API key (optional)", "secret": True, "env_var": "HINDSIGHT_API_KEY", "when": {"mode": "local_external"}},
+            # Local embedded mode
+            {"key": "llm_provider", "description": "LLM provider", "default": "openai", "choices": ["openai", "anthropic", "gemini", "groq", "openrouter", "minimax", "ollama", "lmstudio", "openai_compatible"], "when": {"mode": "local_embedded"}},
+            {"key": "llm_base_url", "description": "Endpoint URL (e.g. http://192.168.1.10:8080/v1)", "default": "", "when": {"mode": "local_embedded", "llm_provider": "openai_compatible"}},
+            {"key": "llm_api_key", "description": "LLM API key (optional for openai_compatible)", "secret": True, "env_var": "HINDSIGHT_LLM_API_KEY", "when": {"mode": "local_embedded"}},
+            {"key": "llm_model", "description": "LLM model", "default": "gpt-4o-mini", "default_from": {"field": "llm_provider", "map": _PROVIDER_DEFAULT_MODELS}, "when": {"mode": "local_embedded"}},
            {"key": "bank_id", "description": "Memory bank name", "default": "hermes"},
-            {"key": "budget", "description": "Recall thoroughness", "default": "mid", "choices": ["low", "mid", "high"]},
+            {"key": "bank_mission", "description": "Mission/purpose description for the memory bank"},
+            {"key": "bank_retain_mission", "description": "Custom extraction prompt for memory retention"},
+            {"key": "recall_budget", "description": "Recall thoroughness", "default": "mid", "choices": ["low", "mid", "high"]},
            {"key": "memory_mode", "description": "Memory integration mode", "default": "hybrid", "choices": ["hybrid", "context", "tools"]},
-            {"key": "prefetch_method", "description": "Auto-recall method", "default": "recall", "choices": ["recall", "reflect"]},
+            {"key": "recall_prefetch_method", "description": "Auto-recall method", "default": "recall", "choices": ["recall", "reflect"]},
+            {"key": "tags", "description": "Tags applied when storing memories (comma-separated)", "default": ""},
+            {"key": "recall_tags", "description": "Tags to filter when searching memories (comma-separated)", "default": ""},
+            {"key": "recall_tags_match", "description": "Tag matching mode for recall", "default": "any", "choices": ["any", "all", "any_strict", "all_strict"]},
+            {"key": "auto_recall", "description": "Automatically recall memories before each turn", "default": True},
+            {"key": "auto_retain", "description": "Automatically retain conversation turns", "default": True},
+            {"key": "retain_every_n_turns", "description": "Retain every N turns (1 = every turn)", "default": 1},
+            {"key": "retain_async","description": "Process retain asynchronously on the Hindsight server", "default": True},
+            {"key": "retain_context", "description": "Context label for retained memories", "default": "conversation between Hermes Agent and the User"},
+            {"key": "recall_max_tokens", "description": "Maximum tokens for recall results", "default": 4096},
+            {"key": "recall_max_input_chars", "description": "Maximum input query length for auto-recall", "default": 800},
+            {"key": "recall_prompt_preamble", "description": "Custom preamble for recalled memories in context"},
        ]

    def _get_client(self):
        """Return the cached Hindsight client (created once, reused)."""
        if self._client is None:
-            if self._mode == "local":
+            if self._mode == "local_embedded":
                from hindsight import HindsightEmbedded
-                # Disable __del__ on the class to prevent "attached to a
-                # different loop" errors during GC — we handle cleanup in
-                # shutdown() instead.
                HindsightEmbedded.__del__ = lambda self: None
-                self._client = HindsightEmbedded(
+                llm_provider = self._config.get("llm_provider", "")
+                if llm_provider in ("openai_compatible", "openrouter"):
+                    llm_provider = "openai"
+                logger.debug("Creating HindsightEmbedded client (profile=%s, provider=%s)",
+                             self._config.get("profile", "hermes"), llm_provider)
+                kwargs = dict(
                    profile=self._config.get("profile", "hermes"),
-                    llm_provider=self._config.get("llm_provider", ""),
-                    llm_api_key=self._config.get("llmApiKey") or os.environ.get("HINDSIGHT_LLM_API_KEY", ""),
+                    llm_provider=llm_provider,
+                    llm_api_key=self._config.get("llmApiKey") or self._config.get("llm_api_key") or os.environ.get("HINDSIGHT_LLM_API_KEY", ""),
                    llm_model=self._config.get("llm_model", ""),
                )
+                if self._llm_base_url:
+                    kwargs["llm_base_url"] = self._llm_base_url
+                self._client = HindsightEmbedded(**kwargs)
            else:
                from hindsight_client import Hindsight
                kwargs = {"base_url": self._api_url, "timeout": 30.0}
                if self._api_key:
                    kwargs["api_key"] = self._api_key
+                logger.debug("Creating Hindsight cloud client (url=%s, has_key=%s)",
+                             self._api_url, bool(self._api_key))
                self._client = Hindsight(**kwargs)
        return self._client

    def initialize(self, session_id: str, **kwargs) -> None:
+        self._session_id = session_id
+
+        # Check client version and auto-upgrade if needed
+        try:
+            from importlib.metadata import version as pkg_version
+            from packaging.version import Version
+            installed = pkg_version("hindsight-client")
+            if Version(installed) < Version(_MIN_CLIENT_VERSION):
+                logger.warning("hindsight-client %s is outdated (need >=%s), attempting upgrade...",
+                               installed, _MIN_CLIENT_VERSION)
+                import shutil, subprocess, sys
+                uv_path = shutil.which("uv")
+                if uv_path:
+                    try:
+                        subprocess.run(
+                            [uv_path, "pip", "install", "--python", sys.executable,
+                             "--quiet", "--upgrade", f"hindsight-client>={_MIN_CLIENT_VERSION}"],
+                            check=True, timeout=120, capture_output=True,
+                        )
+                        logger.info("hindsight-client upgraded to >=%s", _MIN_CLIENT_VERSION)
+                    except Exception as e:
+                        logger.warning("Auto-upgrade failed: %s. Run: uv pip install 'hindsight-client>=%s'",
+                                       e, _MIN_CLIENT_VERSION)
+                else:
+                    logger.warning("uv not found. Run: pip install 'hindsight-client>=%s'", _MIN_CLIENT_VERSION)
+        except Exception:
+            pass  # packaging not available or other issue — proceed anyway
+
        self._config = _load_config()
        self._mode = self._config.get("mode", "cloud")
-        self._api_key = self._config.get("apiKey") or os.environ.get("HINDSIGHT_API_KEY", "")
-        default_url = _DEFAULT_LOCAL_URL if self._mode == "local" else _DEFAULT_API_URL
+        # "local" is a legacy alias for "local_embedded"
+        if self._mode == "local":
+            self._mode = "local_embedded"
+        self._api_key = self._config.get("apiKey") or self._config.get("api_key") or os.environ.get("HINDSIGHT_API_KEY", "")
+        default_url = _DEFAULT_LOCAL_URL if self._mode in ("local_embedded", "local_external") else _DEFAULT_API_URL
        self._api_url = self._config.get("api_url") or os.environ.get("HINDSIGHT_API_URL", default_url)
+        self._llm_base_url = self._config.get("llm_base_url", "")

        banks = self._config.get("banks", {}).get("hermes", {})
        self._bank_id = self._config.get("bank_id") or banks.get("bankId", "hermes")
-        budget = self._config.get("budget") or banks.get("budget", "mid")
+        budget = self._config.get("recall_budget") or self._config.get("budget") or banks.get("budget", "mid")
        self._budget = budget if budget in _VALID_BUDGETS else "mid"

        memory_mode = self._config.get("memory_mode", "hybrid")
        self._memory_mode = memory_mode if memory_mode in ("context", "tools", "hybrid") else "hybrid"

-        prefetch_method = self._config.get("prefetch_method", "recall")
+        prefetch_method = self._config.get("recall_prefetch_method", "recall")
        self._prefetch_method = prefetch_method if prefetch_method in ("recall", "reflect") else "recall"

-        logger.info("Hindsight initialized: mode=%s, api_url=%s, bank=%s, budget=%s, memory_mode=%s, prefetch_method=%s",
-                     self._mode, self._api_url, self._bank_id, self._budget, self._memory_mode, self._prefetch_method)
+        # Bank options
+        self._bank_mission = self._config.get("bank_mission", "")
+        self._bank_retain_mission = self._config.get("bank_retain_mission") or None
+
+        # Tags
+        self._tags = self._config.get("tags") or None
+        self._recall_tags = self._config.get("recall_tags") or None
+        self._recall_tags_match = self._config.get("recall_tags_match", "any")
+
+        # Retain controls
+        self._auto_retain = self._config.get("auto_retain", True)
+        self._retain_every_n_turns = max(1, int(self._config.get("retain_every_n_turns", 1)))
+        self._retain_context = self._config.get("retain_context", "conversation between Hermes Agent and the User")
+
+        # Recall controls
+        self._auto_recall = self._config.get("auto_recall", True)
+        self._recall_max_tokens = int(self._config.get("recall_max_tokens", 4096))
+        self._recall_types = self._config.get("recall_types") or None
+        self._recall_prompt_preamble = self._config.get("recall_prompt_preamble", "")
+        self._recall_max_input_chars = int(self._config.get("recall_max_input_chars", 800))
+        self._retain_async = self._config.get("retain_async", True)
+
+        _client_version = "unknown"
+        try:
+            from importlib.metadata import version as pkg_version
+            _client_version = pkg_version("hindsight-client")
+        except Exception:
+            pass
+        logger.info("Hindsight initialized: mode=%s, api_url=%s, bank=%s, budget=%s, memory_mode=%s, prefetch_method=%s, client=%s",
+                     self._mode, self._api_url, self._bank_id, self._budget, self._memory_mode, self._prefetch_method, _client_version)
+        logger.debug("Hindsight config: auto_retain=%s, auto_recall=%s, retain_every_n=%d, "
+                     "retain_async=%s, retain_context=%s, "
+                     "recall_max_tokens=%d, recall_max_input_chars=%d, tags=%s, recall_tags=%s",
+                     self._auto_retain, self._auto_recall, self._retain_every_n_turns,
+                     self._retain_async, self._retain_context,
+                     self._recall_max_tokens, self._recall_max_input_chars,
+                     self._tags, self._recall_tags)

        # For local mode, start the embedded daemon in the background so it
        # doesn't block the chat. Redirect stdout/stderr to a log file to
        # prevent rich startup output from spamming the terminal.
-        if self._mode == "local":
+        if self._mode == "local_embedded":
            def _start_daemon():
                import traceback
                log_dir = get_hermes_home() / "logs"
@@ -310,9 +579,12 @@ class HindsightMemoryProvider(MemoryProvider):
                    # If the config changed and the daemon is running, stop it.
                    from pathlib import Path as _Path
                    profile_env = _Path.home() / ".hindsight" / "profiles" / f"{profile}.env"
-                    current_key = self._config.get("llmApiKey") or os.environ.get("HINDSIGHT_LLM_API_KEY", "")
+                    current_key = self._config.get("llm_api_key") or os.environ.get("HINDSIGHT_LLM_API_KEY", "")
                    current_provider = self._config.get("llm_provider", "")
                    current_model = self._config.get("llm_model", "")
+                    current_base_url = self._config.get("llm_base_url") or os.environ.get("HINDSIGHT_API_LLM_BASE_URL", "")
+                    # Map openai_compatible/openrouter → openai for the daemon (OpenAI wire format)
+                    daemon_provider = "openai" if current_provider in ("openai_compatible", "openrouter") else current_provider

                    # Read saved profile config
                    saved = {}
@@ -323,20 +595,24 @@ class HindsightMemoryProvider(MemoryProvider):
                                saved[k.strip()] = v.strip()

                    config_changed = (
-                        saved.get("HINDSIGHT_API_LLM_PROVIDER") != current_provider or
+                        saved.get("HINDSIGHT_API_LLM_PROVIDER") != daemon_provider or
                        saved.get("HINDSIGHT_API_LLM_MODEL") != current_model or
-                        saved.get("HINDSIGHT_API_LLM_API_KEY") != current_key
+                        saved.get("HINDSIGHT_API_LLM_API_KEY") != current_key or
+                        saved.get("HINDSIGHT_API_LLM_BASE_URL", "") != current_base_url
                    )

                    if config_changed:
                        # Write updated profile .env
                        profile_env.parent.mkdir(parents=True, exist_ok=True)
-                        profile_env.write_text(
-                            f"HINDSIGHT_API_LLM_PROVIDER={current_provider}\n"
+                        env_lines = (
+                            f"HINDSIGHT_API_LLM_PROVIDER={daemon_provider}\n"
                            f"HINDSIGHT_API_LLM_API_KEY={current_key}\n"
                            f"HINDSIGHT_API_LLM_MODEL={current_model}\n"
                            f"HINDSIGHT_API_LOG_LEVEL=info\n"
                        )
+                        if current_base_url:
+                            env_lines += f"HINDSIGHT_API_LLM_BASE_URL={current_base_url}\n"
+                        profile_env.write_text(env_lines)
                        if client._manager.is_running(profile):
                            with open(log_path, "a") as f:
                                f.write("\n=== Config changed, restarting daemon ===\n")
@@ -377,47 +653,118 @@ class HindsightMemoryProvider(MemoryProvider):

    def prefetch(self, query: str, *, session_id: str = "") -> str:
        if self._prefetch_thread and self._prefetch_thread.is_alive():
+            logger.debug("Prefetch: waiting for background thread to complete")
            self._prefetch_thread.join(timeout=3.0)
        with self._prefetch_lock:
            result = self._prefetch_result
            self._prefetch_result = ""
        if not result:
+            logger.debug("Prefetch: no results available")
            return ""
-        return f"## Hindsight Memory\n{result}"
+        logger.debug("Prefetch: returning %d chars of context", len(result))
+        header = self._recall_prompt_preamble or (
+            "# Hindsight Memory (persistent cross-session context)\n"
+            "Use this to answer questions about the user and prior sessions. "
+            "Do not call tools to look up information that is already present here."
+        )
+        return f"{header}\n\n{result}"

    def queue_prefetch(self, query: str, *, session_id: str = "") -> None:
        if self._memory_mode == "tools":
+            logger.debug("Prefetch: skipped (tools-only mode)")
            return
+        if not self._auto_recall:
+            logger.debug("Prefetch: skipped (auto_recall disabled)")
+            return
+        # Truncate query to max chars
+        if self._recall_max_input_chars and len(query) > self._recall_max_input_chars:
+            query = query[:self._recall_max_input_chars]
+
        def _run():
            try:
                client = self._get_client()
                if self._prefetch_method == "reflect":
+                    logger.debug("Prefetch: calling reflect (bank=%s, query_len=%d)", self._bank_id, len(query))
                    resp = _run_sync(client.areflect(bank_id=self._bank_id, query=query, budget=self._budget))
                    text = resp.text or ""
                else:
-                    resp = _run_sync(client.arecall(bank_id=self._bank_id, query=query, budget=self._budget))
-                    text = "\n".join(r.text for r in resp.results if r.text) if resp.results else ""
+                    recall_kwargs: dict = {
+                        "bank_id": self._bank_id, "query": query,
+                        "budget": self._budget, "max_tokens": self._recall_max_tokens,
+                    }
+                    if self._recall_tags:
+                        recall_kwargs["tags"] = self._recall_tags
+                        recall_kwargs["tags_match"] = self._recall_tags_match
+                    if self._recall_types:
+                        recall_kwargs["types"] = self._recall_types
+                    logger.debug("Prefetch: calling recall (bank=%s, query_len=%d, budget=%s)",
+                                 self._bank_id, len(query), self._budget)
+                    resp = _run_sync(client.arecall(**recall_kwargs))
+                    num_results = len(resp.results) if resp.results else 0
+                    logger.debug("Prefetch: recall returned %d results", num_results)
+                    text = "\n".join(f"- {r.text}" for r in resp.results if r.text) if resp.results else ""
                if text:
                    with self._prefetch_lock:
                        self._prefetch_result = text
            except Exception as e:
-                logger.debug("Hindsight prefetch failed: %s", e)
+                logger.debug("Hindsight prefetch failed: %s", e, exc_info=True)

        self._prefetch_thread = threading.Thread(target=_run, daemon=True, name="hindsight-prefetch")
        self._prefetch_thread.start()

    def sync_turn(self, user_content: str, assistant_content: str, *, session_id: str = "") -> None:
-        """Retain conversation turn in background (non-blocking)."""
-        combined = f"User: {user_content}\nAssistant: {assistant_content}"
+        """Retain conversation turn in background (non-blocking).
+
+        Respects retain_every_n_turns for batching.
+        """
+        if not self._auto_retain:
+            logger.debug("sync_turn: skipped (auto_retain disabled)")
+            return
+
+        from datetime import datetime, timezone
+        now = datetime.now(timezone.utc).isoformat()
+
+        messages = [
+            {"role": "user", "content": user_content, "timestamp": now},
+            {"role": "assistant", "content": assistant_content, "timestamp": now},
+        ]
+
+        turn = json.dumps(messages)
+        self._session_turns.append(turn)
+        self._turn_counter += 1
+
+        # Only retain every N turns
+        if self._turn_counter % self._retain_every_n_turns != 0:
+            logger.debug("sync_turn: buffered turn %d (will retain at turn %d)",
+                         self._turn_counter, self._turn_counter + (self._retain_every_n_turns - self._turn_counter % self._retain_every_n_turns))
+            return
+
+        logger.debug("sync_turn: retaining %d turns, total session content %d chars",
+                     len(self._session_turns), sum(len(t) for t in self._session_turns))
+        # Send the ENTIRE session as a single JSON array (document_id deduplicates).
+        # Each element in _session_turns is a JSON string of that turn's messages.
+        content = "[" + ",".join(self._session_turns) + "]"

        def _sync():
            try:
                client = self._get_client()
-                _run_sync(client.aretain(
-                    bank_id=self._bank_id, content=combined, context="conversation"
+                item: dict = {
+                    "content": content,
+                    "context": self._retain_context,
+                }
+                if self._tags:
+                    item["tags"] = self._tags
+                logger.debug("Hindsight retain: bank=%s, doc=%s, async=%s, content_len=%d, num_turns=%d",
+                             self._bank_id, self._session_id, self._retain_async, len(content), len(self._session_turns))
+                _run_sync(client.aretain_batch(
+                    bank_id=self._bank_id,
+                    items=[item],
+                    document_id=self._session_id,
+                    retain_async=self._retain_async,
                ))
+                logger.debug("Hindsight retain succeeded")
            except Exception as e:
-                logger.warning("Hindsight sync failed: %s", e)
+                logger.warning("Hindsight sync failed: %s", e, exc_info=True)

        if self._sync_thread and self._sync_thread.is_alive():
            self._sync_thread.join(timeout=5.0)
@@ -442,12 +789,18 @@ class HindsightMemoryProvider(MemoryProvider):
                return tool_error("Missing required parameter: content")
            context = args.get("context")
            try:
-                _run_sync(client.aretain(
-                    bank_id=self._bank_id, content=content, context=context
-                ))
+                retain_kwargs: dict = {
+                    "bank_id": self._bank_id, "content": content, "context": context,
+                }
+                if self._tags:
+                    retain_kwargs["tags"] = self._tags
+                logger.debug("Tool hindsight_retain: bank=%s, content_len=%d, context=%s",
+                             self._bank_id, len(content), context)
+                _run_sync(client.aretain(**retain_kwargs))
+                logger.debug("Tool hindsight_retain: success")
                return json.dumps({"result": "Memory stored successfully."})
            except Exception as e:
-                logger.warning("hindsight_retain failed: %s", e)
+                logger.warning("hindsight_retain failed: %s", e, exc_info=True)
                return tool_error(f"Failed to store memory: {e}")

        elif tool_name == "hindsight_recall":
@@ -455,15 +808,26 @@ class HindsightMemoryProvider(MemoryProvider):
            if not query:
                return tool_error("Missing required parameter: query")
            try:
-                resp = _run_sync(client.arecall(
-                    bank_id=self._bank_id, query=query, budget=self._budget
-                ))
+                recall_kwargs: dict = {
+                    "bank_id": self._bank_id, "query": query, "budget": self._budget,
+                    "max_tokens": self._recall_max_tokens,
+                }
+                if self._recall_tags:
+                    recall_kwargs["tags"] = self._recall_tags
+                    recall_kwargs["tags_match"] = self._recall_tags_match
+                if self._recall_types:
+                    recall_kwargs["types"] = self._recall_types
+                logger.debug("Tool hindsight_recall: bank=%s, query_len=%d, budget=%s",
+                             self._bank_id, len(query), self._budget)
+                resp = _run_sync(client.arecall(**recall_kwargs))
+                num_results = len(resp.results) if resp.results else 0
+                logger.debug("Tool hindsight_recall: %d results", num_results)
                if not resp.results:
                    return json.dumps({"result": "No relevant memories found."})
                lines = [f"{i}. {r.text}" for i, r in enumerate(resp.results, 1)]
                return json.dumps({"result": "\n".join(lines)})
            except Exception as e:
-                logger.warning("hindsight_recall failed: %s", e)
+                logger.warning("hindsight_recall failed: %s", e, exc_info=True)
                return tool_error(f"Failed to search memory: {e}")

        elif tool_name == "hindsight_reflect":
@@ -471,24 +835,28 @@ class HindsightMemoryProvider(MemoryProvider):
            if not query:
                return tool_error("Missing required parameter: query")
            try:
+                logger.debug("Tool hindsight_reflect: bank=%s, query_len=%d, budget=%s",
+                             self._bank_id, len(query), self._budget)
                resp = _run_sync(client.areflect(
                    bank_id=self._bank_id, query=query, budget=self._budget
                ))
+                logger.debug("Tool hindsight_reflect: response_len=%d", len(resp.text or ""))
                return json.dumps({"result": resp.text or "No relevant memories found."})
            except Exception as e:
-                logger.warning("hindsight_reflect failed: %s", e)
+                logger.warning("hindsight_reflect failed: %s", e, exc_info=True)
                return tool_error(f"Failed to reflect: {e}")

        return tool_error(f"Unknown tool: {tool_name}")

    def shutdown(self) -> None:
+        logger.debug("Hindsight shutdown: waiting for background threads")
        global _loop, _loop_thread
        for t in (self._prefetch_thread, self._sync_thread):
            if t and t.is_alive():
                t.join(timeout=5.0)
        if self._client is not None:
            try:
-                if self._mode == "local":
+                if self._mode == "local_embedded":
                    # Use the public close() API. The RuntimeError from
                    # aiohttp's "attached to a different loop" is expected
                    # and harmless — the daemon keeps running independently.
@@ -2,9 +2,7 @@ name: hindsight
 version: 1.0.0
 description: "Hindsight — long-term memory with knowledge graph, entity resolution, and multi-strategy retrieval."
 pip_dependencies:
-  - hindsight-client
-  - hindsight-all
-requires_env:
-  - HINDSIGHT_API_KEY
+  - "hindsight-client>=0.4.22"
+requires_env: []
 hooks:
  - on_session_end
@@ -17,7 +17,7 @@ Or manually:

 ```bash
 hermes config set memory.provider supermemory
-echo 'SUPERMEMORY_API_KEY=your-key-here' >> ~/.hermes/.env
+echo 'SUPERMEMORY_API_KEY=***' >> ~/.hermes/.env
 ```

 ## Config
@@ -26,15 +26,23 @@ Config file: `$HERMES_HOME/supermemory.json`

 | Key | Default | Description |
 |-----|---------|-------------|
-| `container_tag` | `hermes` | Container tag used for search and writes |
+| `container_tag` | `hermes` | Container tag used for search and writes. Supports `{identity}` template for profile-scoped tags (e.g. `hermes-{identity}` → `hermes-coder`). |
 | `auto_recall` | `true` | Inject relevant memory context before turns |
 | `auto_capture` | `true` | Store cleaned user-assistant turns after each response |
 | `max_recall_results` | `10` | Max recalled items to format into context |
 | `profile_frequency` | `50` | Include profile facts on first turn and every N turns |
 | `capture_mode` | `all` | Skip tiny or trivial turns by default |
+| `search_mode` | `hybrid` | Search mode: `hybrid` (profile + memories), `memories` (memories only), `documents` (documents only) |
 | `entity_context` | built-in default | Extraction guidance passed to Supermemory |
 | `api_timeout` | `5.0` | Timeout for SDK and ingest requests |

+### Environment Variables
+
+| Variable | Description |
+|----------|-------------|
+| `SUPERMEMORY_API_KEY` | API key (required) |
+| `SUPERMEMORY_CONTAINER_TAG` | Override container tag (takes priority over config file) |
+
 ## Tools

 | Tool | Description |
@@ -52,3 +60,40 @@ When enabled, Hermes can:
 - store cleaned conversation turns after each completed response
 - ingest the full session on session end for richer graph updates
 - expose explicit tools for search, store, forget, and profile access
+
+## Profile-Scoped Containers
+
+Use `{identity}` in the `container_tag` to scope memories per Hermes profile:
+
+```json
+{
+  "container_tag": "hermes-{identity}"
+}
+```
+
+For a profile named `coder`, this resolves to `hermes-coder`. The default profile resolves to `hermes-default`. Without `{identity}`, all profiles share the same container.
+
+## Multi-Container Mode
+
+For advanced setups (e.g. OpenClaw-style multi-workspace), you can enable custom container tags so the agent can read/write across multiple named containers:
+
+```json
+{
+  "container_tag": "hermes",
+  "enable_custom_container_tags": true,
+  "custom_containers": ["project-alpha", "project-beta", "shared-knowledge"],
+  "custom_container_instructions": "Use project-alpha for coding tasks, project-beta for research, and shared-knowledge for team-wide facts."
+}
+```
+
+When enabled:
+- `supermemory_search`, `supermemory_store`, `supermemory_forget`, and `supermemory_profile` accept an optional `container_tag` parameter
+- The tag must be in the whitelist: primary container + `custom_containers`
+- Automatic operations (turn sync, prefetch, memory write mirroring, session ingest) always use the **primary** container only
+- Custom container instructions are injected into the system prompt
+
+## Support
+
+- [Supermemory Discord](https://supermemory.link/discord)
+- [support@supermemory.com](mailto:support@supermemory.com)
+- [supermemory.ai](https://supermemory.ai)
@@ -26,6 +26,8 @@ _DEFAULT_CONTAINER_TAG = "hermes"
 _DEFAULT_MAX_RECALL_RESULTS = 10
 _DEFAULT_PROFILE_FREQUENCY = 50
 _DEFAULT_CAPTURE_MODE = "all"
+_DEFAULT_SEARCH_MODE = "hybrid"
+_VALID_SEARCH_MODES = ("hybrid", "memories", "documents")
 _DEFAULT_API_TIMEOUT = 5.0
 _MIN_CAPTURE_LENGTH = 10
 _MAX_ENTITY_CONTEXT_LENGTH = 1500
@@ -59,8 +61,12 @@ def _default_config() -> dict:
        "max_recall_results": _DEFAULT_MAX_RECALL_RESULTS,
        "profile_frequency": _DEFAULT_PROFILE_FREQUENCY,
        "capture_mode": _DEFAULT_CAPTURE_MODE,
+        "search_mode": _DEFAULT_SEARCH_MODE,
        "entity_context": _DEFAULT_ENTITY_CONTEXT,
        "api_timeout": _DEFAULT_API_TIMEOUT,
+        "enable_custom_container_tags": False,
+        "custom_containers": [],
+        "custom_container_instructions": "",
    }


@@ -100,7 +106,10 @@ def _load_supermemory_config(hermes_home: str) -> dict:
        except Exception:
            logger.debug("Failed to parse %s", config_path, exc_info=True)

-    config["container_tag"] = _sanitize_tag(str(config.get("container_tag", _DEFAULT_CONTAINER_TAG)))
+    # Keep raw container_tag — template variables like {identity} are resolved
+    # in initialize(), and _sanitize_tag runs AFTER resolution.
+    raw_tag = str(config.get("container_tag", _DEFAULT_CONTAINER_TAG)).strip()
+    config["container_tag"] = raw_tag if raw_tag else _DEFAULT_CONTAINER_TAG
    config["auto_recall"] = _as_bool(config.get("auto_recall"), True)
    config["auto_capture"] = _as_bool(config.get("auto_capture"), True)
    try:
@@ -112,11 +121,23 @@ def _load_supermemory_config(hermes_home: str) -> dict:
    except Exception:
        config["profile_frequency"] = _DEFAULT_PROFILE_FREQUENCY
    config["capture_mode"] = "everything" if config.get("capture_mode") == "everything" else "all"
+    raw_search_mode = str(config.get("search_mode", _DEFAULT_SEARCH_MODE)).strip().lower()
+    config["search_mode"] = raw_search_mode if raw_search_mode in _VALID_SEARCH_MODES else _DEFAULT_SEARCH_MODE
    config["entity_context"] = _clamp_entity_context(str(config.get("entity_context", _DEFAULT_ENTITY_CONTEXT)))
    try:
        config["api_timeout"] = max(0.5, min(15.0, float(config.get("api_timeout", _DEFAULT_API_TIMEOUT))))
    except Exception:
        config["api_timeout"] = _DEFAULT_API_TIMEOUT
+
+    # Multi-container support
+    config["enable_custom_container_tags"] = _as_bool(config.get("enable_custom_container_tags"), False)
+    raw_containers = config.get("custom_containers", [])
+    if isinstance(raw_containers, list):
+        config["custom_containers"] = [_sanitize_tag(str(t)) for t in raw_containers if t]
+    else:
+        config["custom_containers"] = []
+    config["custom_container_instructions"] = str(config.get("custom_container_instructions", "")).strip()
+
    return config


@@ -240,28 +261,41 @@ def _is_trivial_message(text: str) -> bool:


 class _SupermemoryClient:
-    def __init__(self, api_key: str, timeout: float, container_tag: str):
+    def __init__(self, api_key: str, timeout: float, container_tag: str, search_mode: str = "hybrid"):
        from supermemory import Supermemory

        self._api_key = api_key
        self._container_tag = container_tag
+        self._search_mode = search_mode if search_mode in _VALID_SEARCH_MODES else _DEFAULT_SEARCH_MODE
        self._timeout = timeout
        self._client = Supermemory(api_key=api_key, timeout=timeout, max_retries=0)

-    def add_memory(self, content: str, metadata: Optional[dict] = None, *, entity_context: str = "") -> dict:
-        kwargs = {
+    def add_memory(self, content: str, metadata: Optional[dict] = None, *,
+                   entity_context: str = "", container_tag: Optional[str] = None,
+                   custom_id: Optional[str] = None) -> dict:
+        tag = container_tag or self._container_tag
+        kwargs: dict[str, Any] = {
            "content": content.strip(),
-            "container_tags": [self._container_tag],
+            "container_tags": [tag],
        }
        if metadata:
            kwargs["metadata"] = metadata
        if entity_context:
            kwargs["entity_context"] = _clamp_entity_context(entity_context)
+        if custom_id:
+            kwargs["custom_id"] = custom_id
        result = self._client.documents.add(**kwargs)
        return {"id": getattr(result, "id", "")}

-    def search_memories(self, query: str, *, limit: int = 5) -> list[dict]:
-        response = self._client.search.memories(q=query, container_tag=self._container_tag, limit=limit)
+    def search_memories(self, query: str, *, limit: int = 5,
+                        container_tag: Optional[str] = None,
+                        search_mode: Optional[str] = None) -> list[dict]:
+        tag = container_tag or self._container_tag
+        mode = search_mode or self._search_mode
+        kwargs: dict[str, Any] = {"q": query, "container_tag": tag, "limit": limit}
+        if mode in _VALID_SEARCH_MODES:
+            kwargs["search_mode"] = mode
+        response = self._client.search.memories(**kwargs)
        results = []
        for item in (getattr(response, "results", None) or []):
            results.append({
@@ -273,8 +307,10 @@ class _SupermemoryClient:
            })
        return results

-    def get_profile(self, query: Optional[str] = None) -> dict:
-        kwargs = {"container_tag": self._container_tag}
+    def get_profile(self, query: Optional[str] = None, *,
+                    container_tag: Optional[str] = None) -> dict:
+        tag = container_tag or self._container_tag
+        kwargs: dict[str, Any] = {"container_tag": tag}
        if query:
            kwargs["q"] = query
        response = self._client.profile(**kwargs)
@@ -296,18 +332,19 @@ class _SupermemoryClient:
                    })
        return {"static": static, "dynamic": dynamic, "search_results": search_results}

-    def forget_memory(self, memory_id: str) -> None:
-        self._client.memories.forget(container_tag=self._container_tag, id=memory_id)
+    def forget_memory(self, memory_id: str, *, container_tag: Optional[str] = None) -> None:
+        tag = container_tag or self._container_tag
+        self._client.memories.forget(container_tag=tag, id=memory_id)

-    def forget_by_query(self, query: str) -> dict:
-        results = self.search_memories(query, limit=5)
+    def forget_by_query(self, query: str, *, container_tag: Optional[str] = None) -> dict:
+        results = self.search_memories(query, limit=5, container_tag=container_tag)
        if not results:
            return {"success": False, "message": "No matching memory found to forget."}
        target = results[0]
        memory_id = target.get("id", "")
        if not memory_id:
            return {"success": False, "message": "Best matching memory has no id."}
-        self.forget_memory(memory_id)
+        self.forget_memory(memory_id, container_tag=container_tag)
        preview = (target.get("memory") or "")[:100]
        return {"success": True, "message": f'Forgot: "{preview}"', "id": memory_id}

@@ -398,11 +435,17 @@ class SupermemoryMemoryProvider(MemoryProvider):
        self._max_recall_results = _DEFAULT_MAX_RECALL_RESULTS
        self._profile_frequency = _DEFAULT_PROFILE_FREQUENCY
        self._capture_mode = _DEFAULT_CAPTURE_MODE
+        self._search_mode = _DEFAULT_SEARCH_MODE
        self._entity_context = _DEFAULT_ENTITY_CONTEXT
        self._api_timeout = _DEFAULT_API_TIMEOUT
        self._hermes_home = ""
        self._write_enabled = True
        self._active = False
+        # Multi-container support
+        self._enable_custom_containers = False
+        self._custom_containers: List[str] = []
+        self._custom_container_instructions = ""
+        self._allowed_containers: List[str] = []

    @property
    def name(self) -> str:
@@ -419,16 +462,11 @@ class SupermemoryMemoryProvider(MemoryProvider):
            return False

    def get_config_schema(self):
+        # Only prompt for the API key during `hermes memory setup`.
+        # All other options are documented for $HERMES_HOME/supermemory.json
+        # or the SUPERMEMORY_CONTAINER_TAG env var.
        return [
            {"key": "api_key", "description": "Supermemory API key", "secret": True, "required": True, "env_var": "SUPERMEMORY_API_KEY", "url": "https://supermemory.ai"},
-            {"key": "container_tag", "description": "Container tag for reads and writes", "default": _DEFAULT_CONTAINER_TAG},
-            {"key": "auto_recall", "description": "Enable automatic recall before each turn", "default": "true", "choices": ["true", "false"]},
-            {"key": "auto_capture", "description": "Enable automatic capture after each completed turn", "default": "true", "choices": ["true", "false"]},
-            {"key": "max_recall_results", "description": "Maximum recalled items to inject", "default": str(_DEFAULT_MAX_RECALL_RESULTS)},
-            {"key": "profile_frequency", "description": "Include profile facts on first turn and every N turns", "default": str(_DEFAULT_PROFILE_FREQUENCY)},
-            {"key": "capture_mode", "description": "Capture mode", "default": _DEFAULT_CAPTURE_MODE, "choices": ["all", "everything"]},
-            {"key": "entity_context", "description": "Extraction guidance passed to Supermemory", "default": _DEFAULT_ENTITY_CONTEXT},
-            {"key": "api_timeout", "description": "Timeout in seconds for SDK and ingest calls", "default": str(_DEFAULT_API_TIMEOUT)},
        ]

    def save_config(self, values, hermes_home):
@@ -446,14 +484,29 @@ class SupermemoryMemoryProvider(MemoryProvider):
        self._turn_count = 0
        self._config = _load_supermemory_config(self._hermes_home)
        self._api_key = os.environ.get("SUPERMEMORY_API_KEY", "")
-        self._container_tag = self._config["container_tag"]
+
+        # Resolve container tag: env var > config > default.
+        # Supports {identity} template for profile-scoped containers.
+        env_tag = os.environ.get("SUPERMEMORY_CONTAINER_TAG", "").strip()
+        raw_tag = env_tag or self._config["container_tag"]
+        identity = kwargs.get("agent_identity", "default")
+        self._container_tag = _sanitize_tag(raw_tag.replace("{identity}", identity))
+
        self._auto_recall = self._config["auto_recall"]
        self._auto_capture = self._config["auto_capture"]
        self._max_recall_results = self._config["max_recall_results"]
        self._profile_frequency = self._config["profile_frequency"]
        self._capture_mode = self._config["capture_mode"]
+        self._search_mode = self._config["search_mode"]
        self._entity_context = self._config["entity_context"]
        self._api_timeout = self._config["api_timeout"]
+
+        # Multi-container setup
+        self._enable_custom_containers = self._config["enable_custom_container_tags"]
+        self._custom_containers = self._config["custom_containers"]
+        self._custom_container_instructions = self._config["custom_container_instructions"]
+        self._allowed_containers = [self._container_tag] + list(self._custom_containers)
+
        agent_context = kwargs.get("agent_context", "")
        self._write_enabled = agent_context not in ("cron", "flush", "subagent")
        self._active = bool(self._api_key)
@@ -464,6 +517,7 @@ class SupermemoryMemoryProvider(MemoryProvider):
                    api_key=self._api_key,
                    timeout=self._api_timeout,
                    container_tag=self._container_tag,
+                    search_mode=self._search_mode,
                )
            except Exception:
                logger.warning("Supermemory initialization failed", exc_info=True)
@@ -476,11 +530,18 @@ class SupermemoryMemoryProvider(MemoryProvider):
    def system_prompt_block(self) -> str:
        if not self._active:
            return ""
-        return (
-            "# Supermemory\n"
-            f"Active. Container: {self._container_tag}.\n"
-            "Use supermemory_search, supermemory_store, supermemory_forget, and supermemory_profile for explicit memory operations."
-        )
+        lines = [
+            "# Supermemory",
+            f"Active. Container: {self._container_tag}.",
+            "Use supermemory_search, supermemory_store, supermemory_forget, and supermemory_profile for explicit memory operations.",
+        ]
+        if self._enable_custom_containers and self._custom_containers:
+            tags_str = ", ".join(self._allowed_containers)
+            lines.append(f"\nMulti-container mode enabled. Available containers: {tags_str}.")
+            lines.append("Pass an optional container_tag to supermemory_search, supermemory_store, supermemory_forget, and supermemory_profile to target a specific container.")
+            if self._custom_container_instructions:
+                lines.append(f"\n{self._custom_container_instructions}")
+        return "\n".join(lines)

    def prefetch(self, query: str, *, session_id: str = "") -> str:
        if not self._active or not self._auto_recall or not self._client or not query.strip():
@@ -582,22 +643,62 @@ class SupermemoryMemoryProvider(MemoryProvider):
                thread.join(timeout=5.0)
            setattr(self, attr_name, None)

+    def _resolve_tool_container_tag(self, args: dict) -> Optional[str]:
+        """Validate and resolve container_tag from tool call args.
+
+        Returns None (use primary) if multi-container is disabled or no tag provided.
+        Returns the validated tag if it's in the allowed list.
+        Raises ValueError if the tag is not whitelisted.
+        """
+        if not self._enable_custom_containers:
+            return None
+        tag = str(args.get("container_tag") or "").strip()
+        if not tag:
+            return None
+        sanitized = _sanitize_tag(tag)
+        if sanitized not in self._allowed_containers:
+            raise ValueError(
+                f"Container tag '{sanitized}' is not allowed. "
+                f"Allowed: {', '.join(self._allowed_containers)}"
+            )
+        return sanitized
+
    def get_tool_schemas(self) -> List[Dict[str, Any]]:
-        return [STORE_SCHEMA, SEARCH_SCHEMA, FORGET_SCHEMA, PROFILE_SCHEMA]
+        if not self._enable_custom_containers:
+            return [STORE_SCHEMA, SEARCH_SCHEMA, FORGET_SCHEMA, PROFILE_SCHEMA]
+
+        # When multi-container is enabled, add optional container_tag to relevant tools
+        container_param = {
+            "type": "string",
+            "description": f"Optional container tag. Allowed: {', '.join(self._allowed_containers)}. Defaults to primary ({self._container_tag}).",
+        }
+        schemas = []
+        for base in [STORE_SCHEMA, SEARCH_SCHEMA, FORGET_SCHEMA, PROFILE_SCHEMA]:
+            schema = json.loads(json.dumps(base))  # deep copy
+            schema["parameters"]["properties"]["container_tag"] = container_param
+            schemas.append(schema)
+        return schemas

    def _tool_store(self, args: dict) -> str:
        content = str(args.get("content") or "").strip()
        if not content:
            return tool_error("content is required")
+        try:
+            tag = self._resolve_tool_container_tag(args)
+        except ValueError as exc:
+            return tool_error(str(exc))
        metadata = args.get("metadata") or {}
        if not isinstance(metadata, dict):
            metadata = {}
        metadata.setdefault("type", _detect_category(content))
        metadata["source"] = "hermes_tool"
        try:
-            result = self._client.add_memory(content, metadata=metadata, entity_context=self._entity_context)
+            result = self._client.add_memory(content, metadata=metadata, entity_context=self._entity_context, container_tag=tag)
            preview = content[:80] + ("..." if len(content) > 80 else "")
-            return json.dumps({"saved": True, "id": result.get("id", ""), "preview": preview})
+            resp: dict[str, Any] = {"saved": True, "id": result.get("id", ""), "preview": preview}
+            if tag:
+                resp["container_tag"] = tag
+            return json.dumps(resp)
        except Exception as exc:
            return tool_error(f"Failed to store memory: {exc}")

@@ -605,22 +706,29 @@ class SupermemoryMemoryProvider(MemoryProvider):
        query = str(args.get("query") or "").strip()
        if not query:
            return tool_error("query is required")
+        try:
+            tag = self._resolve_tool_container_tag(args)
+        except ValueError as exc:
+            return tool_error(str(exc))
        try:
            limit = max(1, min(20, int(args.get("limit", 5) or 5)))
        except Exception:
            limit = 5
        try:
-            results = self._client.search_memories(query, limit=limit)
+            results = self._client.search_memories(query, limit=limit, container_tag=tag)
            formatted = []
            for item in results:
-                entry = {"id": item.get("id", ""), "content": item.get("memory", "")}
+                entry: dict[str, Any] = {"id": item.get("id", ""), "content": item.get("memory", "")}
                if item.get("similarity") is not None:
                    try:
                        entry["similarity"] = round(float(item["similarity"]) * 100)
                    except Exception:
                        pass
                formatted.append(entry)
-            return json.dumps({"results": formatted, "count": len(formatted)})
+            resp: dict[str, Any] = {"results": formatted, "count": len(formatted)}
+            if tag:
+                resp["container_tag"] = tag
+            return json.dumps(resp)
        except Exception as exc:
            return tool_error(f"Search failed: {exc}")

@@ -629,28 +737,39 @@ class SupermemoryMemoryProvider(MemoryProvider):
        query = str(args.get("query") or "").strip()
        if not memory_id and not query:
            return tool_error("Provide either id or query")
+        try:
+            tag = self._resolve_tool_container_tag(args)
+        except ValueError as exc:
+            return tool_error(str(exc))
        try:
            if memory_id:
-                self._client.forget_memory(memory_id)
+                self._client.forget_memory(memory_id, container_tag=tag)
                return json.dumps({"forgotten": True, "id": memory_id})
-            return json.dumps(self._client.forget_by_query(query))
+            return json.dumps(self._client.forget_by_query(query, container_tag=tag))
        except Exception as exc:
            return tool_error(f"Forget failed: {exc}")

    def _tool_profile(self, args: dict) -> str:
        query = str(args.get("query") or "").strip() or None
        try:
-            profile = self._client.get_profile(query=query)
+            tag = self._resolve_tool_container_tag(args)
+        except ValueError as exc:
+            return tool_error(str(exc))
+        try:
+            profile = self._client.get_profile(query=query, container_tag=tag)
            sections = []
            if profile["static"]:
                sections.append("## User Profile (Persistent)\n" + "\n".join(f"- {item}" for item in profile["static"]))
            if profile["dynamic"]:
                sections.append("## Recent Context\n" + "\n".join(f"- {item}" for item in profile["dynamic"]))
-            return json.dumps({
+            resp: dict[str, Any] = {
                "profile": "\n\n".join(sections),
                "static_count": len(profile["static"]),
                "dynamic_count": len(profile["dynamic"]),
-            })
+            }
+            if tag:
+                resp["container_tag"] = tag
+            return json.dumps(resp)
        except Exception as exc:
            return tool_error(f"Profile failed: {exc}")

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"

 [project]
 name = "hermes-agent"
-version = "0.7.0"
+version = "0.8.0"
 description = "The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere"
 readme = "README.md"
 requires-python = ">=3.11"
@@ -62,6 +62,18 @@ mcp = ["mcp>=1.2.0,<2"]
 homeassistant = ["aiohttp>=3.9.0,<4"]
 sms = ["aiohttp>=3.9.0,<4"]
 acp = ["agent-client-protocol>=0.9.0,<1.0"]
+mistral = ["mistralai>=2.3.0,<3"]
+termux = [
+  # Tested Android / Termux path: keeps the core CLI feature-rich while
+  # avoiding extras that currently depend on non-Android wheels (notably
+  # faster-whisper -> ctranslate2 via the voice extra).
+  "hermes-agent[cron]",
+  "hermes-agent[cli]",
+  "hermes-agent[pty]",
+  "hermes-agent[mcp]",
+  "hermes-agent[honcho]",
+  "hermes-agent[acp]",
+]
 dingtalk = ["dingtalk-stream>=0.1.0,<1"]
 feishu = ["lark-oapi>=1.5.3,<2"]
 rl = [
@@ -94,6 +106,7 @@ all = [
  "hermes-agent[voice]",
  "hermes-agent[dingtalk]",
  "hermes-agent[feishu]",
+  "hermes-agent[mistral]",
 ]

 [project.scripts]
--- a/Show More
+++ b/Show More