fix(tools): address PR review — remove _extract_raw_output, BudgetConfig everywhere, read_file hardening

- Remove _extract_raw_output: persist content verbatim (fixes size mismatch bug) - Drop import aliases: import from budget_config directly, one canonical name - BudgetConfig param on maybe_persist_tool_result and enforce_turn_budget - read_file: limit=None signature, pre-read guard fires only when limit omitted (256KB) - Unify binary extensions: file_operations.py imports from binary_extensions.py - Exclude .pdf and .svg from binary set (text-based, agents may inspect) - Remove redundant outer try/except in eval path (internal fallback handles it) - Fix broken tests: update assertion strings for new persistence format - Module-level constants: _PRE_READ_MAX_BYTES, _DEFAULT_READ_LIMIT - Remove redundant pathlib import (Path already at module level) - Update spec.md with IMPLEMENTED annotations and design decisions
feat(budget): make tool result persistence thresholds configurable
2026-04-08 00:22:08 -07:00 · 2026-04-07 22:31:06 -07:00 · 2026-04-07 22:21:27 -07:00
185 changed files with 2795 additions and 15667 deletions
@@ -81,14 +81,6 @@
 # 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
 # =============================================================================
@@ -8,9 +8,6 @@ on:
  release:
    types: [published]

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

-      # 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)
+      - name: Build image
        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
@@ -61,28 +51,26 @@ jobs:
          username: ${{ secrets.DOCKERHUB_USERNAME }}
          password: ${{ secrets.DOCKERHUB_TOKEN }}

-      - name: Push multi-arch image (main branch)
+      - name: Push 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 multi-arch image (release)
+      - name: Push 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 ascii-guard
-        run: python -m pip install ascii-guard==2.3.0 pyyaml==6.0.3
+      - name: Install Python dependencies
+        run: python -m pip install ascii-guard pyyaml

      - 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@ef8a148080ab6020fd15196c2084a2eea5ff2d25  # v22
-      - uses: DeterminateSystems/magic-nix-cache-action@565684385bcd71bad329742eefe8d12f2e765b39  # v13
+      - uses: DeterminateSystems/nix-installer-action@main
+      - uses: DeterminateSystems/magic-nix-cache-action@main
      - name: Check flake
        if: runner.os == 'Linux'
        run: nix flake check --print-build-logs
@@ -1,8 +1,5 @@
 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 \
@@ -1,346 +0,0 @@
-# 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)
@@ -163,17 +163,6 @@ 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.

@@ -181,10 +170,9 @@ 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.
    """
-    normalized = _normalize_base_url_text(base_url)
-    if not normalized:
+    if not base_url:
        return False  # No base_url = direct Anthropic API
-    normalized = normalized.rstrip("/").lower()
+    normalized = base_url.rstrip("/").lower()
    if "anthropic.com" in normalized:
        return False  # Direct Anthropic API — OAuth applies
    return True  # Any other endpoint is a third-party proxy
@@ -194,13 +182,12 @@ 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 *** of Anthropic's native x-api-key header.
+    require Authorization: Bearer instead of Anthropic's native x-api-key header.
    MiniMax's global and China Anthropic-compatible endpoints follow this pattern.
    """
-    normalized = _normalize_base_url_text(base_url)
-    if not normalized:
+    if not base_url:
        return False
-    normalized = normalized.rstrip("/").lower()
+    normalized = base_url.rstrip("/").lower()
    return normalized.startswith(("https://api.minimax.io/anthropic", "https://api.minimaxi.com/anthropic"))


@@ -216,14 +203,13 @@ 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 normalized_base_url:
-        kwargs["base_url"] = normalized_base_url
+    if base_url:
+        kwargs["base_url"] = base_url

-    if _requires_bearer_auth(normalized_base_url):
+    if _requires_bearer_auth(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.
@@ -956,18 +942,12 @@ 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 = []
@@ -1122,15 +1102,7 @@ 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.
-                # 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"))
-                    ]
+                # Consecutive assistant messages — merge text content
                prev_blocks = fixed[-1]["content"]
                curr_blocks = m["content"]
                if isinstance(prev_blocks, list) and isinstance(curr_blocks, list):
@@ -1148,79 +1120,6 @@ 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


@@ -1234,53 +1133,28 @@ def build_anthropic_kwargs(
    is_oauth: bool = False,
    preserve_dots: bool = False,
    context_length: Optional[int] = None,
-    base_url: str | None = None,
 ) -> Dict[str, Any]:
    """Build kwargs for anthropic.messages.create().

-    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 *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.

    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).
    """
-    system, anthropic_messages = convert_messages_to_anthropic(messages, base_url=base_url)
+    system, anthropic_messages = convert_messages_to_anthropic(messages)
    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 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.
+    # Clamp to context window if the user set a lower context_length
+    # (e.g. custom endpoint with limited capacity).
    if context_length and effective_max_tokens > context_length:
        effective_max_tokens = max(context_length - 1, 1)

@@ -1350,9 +1224,9 @@ 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 and MiniMax models do NOT support extended thinking — skip entirely.
+    # Haiku models do NOT support extended thinking at all — skip entirely.
    if reasoning_config and isinstance(reasoning_config, dict):
-        if reasoning_config.get("enabled") is not False and "haiku" not in model.lower() and "minimax" not in model.lower():
+        if reasoning_config.get("enabled") is not False and "haiku" not in model.lower():
            effort = str(reasoning_config.get("effort", "medium")).lower()
            budget = THINKING_BUDGET.get(effort, 8000)
            if _supports_adaptive_thinking(model):
@@ -59,48 +59,13 @@ 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",
-    "minimax-cn": "MiniMax-M2.7",
+    "minimax": "MiniMax-M2.7-highspeed",
+    "minimax-cn": "MiniMax-M2.7-highspeed",
    "anthropic": "claude-haiku-4-5-20251001",
    "ai-gateway": "google/gemini-3-flash",
    "opencode-zen": "gemini-3-flash",
@@ -127,7 +92,6 @@ 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"
@@ -141,23 +105,6 @@ _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:
@@ -629,19 +576,11 @@ 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.
-
-    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.
-    """
+    """Read a valid, non-expired Codex OAuth access token from Hermes auth store."""
    pool_present, entry = _select_pool_entry("openai-codex")
    if pool_present:
        token = _pool_runtime_api_key(entry)
-        if token:
-            return token
+        return token or None

    try:
        from hermes_cli.auth import _read_codex_tokens
@@ -695,14 +634,12 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
            if not api_key:
                continue

-            base_url = _to_openai_base_url(
-                _pool_runtime_base_url(entry, pconfig.inference_base_url) or pconfig.inference_base_url
-            )
+            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/1.3"}
+                extra["default_headers"] = {"User-Agent": "KimiCLI/1.0"}
            elif "api.githubcopilot.com" in base_url.lower():
                from hermes_cli.models import copilot_default_headers

@@ -714,14 +651,12 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
        if not api_key:
            continue

-        base_url = _to_openai_base_url(
-            str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
-        )
+        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/1.3"}
+            extra["default_headers"] = {"User-Agent": "KimiCLI/1.0"}
        elif "api.githubcopilot.com" in base_url.lower():
            from hermes_cli.models import copilot_default_headers

@@ -778,7 +713,7 @@ def _try_openrouter() -> Tuple[Optional[OpenAI], Optional[str]]:
                   default_headers=_OR_HEADERS), _OPENROUTER_MODEL


-def _try_nous(vision: bool = False) -> Tuple[Optional[OpenAI], Optional[str]]:
+def _try_nous() -> Tuple[Optional[OpenAI], Optional[str]]:
    nous = _read_nous_auth()
    if not nous:
        return None, None
@@ -790,13 +725,12 @@ def _try_nous(vision: bool = False) -> Tuple[Optional[OpenAI], Optional[str]]:
    else:
        model = _NOUS_MODEL
    # Free-tier users can't use paid auxiliary models — use the free
-    # models instead: mimo-v2-omni for vision, mimo-v2-pro for text tasks.
+    # multimodal model instead so vision/browser-vision still works.
    try:
        from hermes_cli.models import check_nous_free_tier
        if check_nous_free_tier():
-            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")
+            model = _NOUS_FREE_TIER_VISION_MODEL
+            logger.debug("Free-tier Nous account — using %s for auxiliary/vision", model)
    except Exception:
        pass
    return (
@@ -902,13 +836,9 @@ 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 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
+        if not codex_token:
+            return None, None
+        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:
@@ -1047,32 +977,6 @@ 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,
@@ -1137,7 +1041,7 @@ 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", "")):
+            and main_provider not in ("auto", "custom", "")):
        client, resolved = resolve_provider_client(main_provider, main_model)
        if client is not None:
            logger.info("Auxiliary auto-detect: using main provider %s (%s)",
@@ -1195,7 +1099,7 @@ 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/1.3"}
+        async_kwargs["default_headers"] = {"User-Agent": "KimiCLI/1.0"}
    return AsyncOpenAI(**async_kwargs), model


@@ -1234,7 +1138,17 @@ def resolve_provider_client(
        (client, resolved_model) or (None, None) if auth is unavailable.
    """
    # Normalise aliases
-    provider = _normalize_aux_provider(provider)
+    provider = (provider or "auto").strip().lower()
+    if provider == "codex":
+        provider = "openai-codex"
+    if provider == "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", ""):
+            provider = main_prov
+        else:
+            provider = "custom"

    # ── Auto: try all providers in priority order ────────────────────
    if provider == "auto":
@@ -1315,13 +1229,7 @@ def resolve_provider_client(
                )
                return None, None
            final_model = model or _read_main_model() or "gpt-4o-mini"
-            extra = {}
-            if "api.kimi.com" in custom_base.lower():
-                extra["default_headers"] = {"User-Agent": "KimiCLI/1.3"}
-            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)
+            client = OpenAI(api_key=custom_key, base_url=custom_base)
            return (_to_async_client(client, final_model) if async_mode
                    else (client, final_model))
        # Try custom first, then codex, then API-key providers
@@ -1390,9 +1298,7 @@ def resolve_provider_client(
                         provider, ", ".join(tried_sources))
            return None, None

-        base_url = _to_openai_base_url(
-            str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
-        )
+        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
@@ -1400,7 +1306,7 @@ def resolve_provider_client(
        # Provider-specific headers
        headers = {}
        if "api.kimi.com" in base_url.lower():
-            headers["User-Agent"] = "KimiCLI/1.3"
+            headers["User-Agent"] = "KimiCLI/1.0"
        elif "api.githubcopilot.com" in base_url.lower():
            from hermes_cli.models import copilot_default_headers

@@ -1469,11 +1375,24 @@ 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:
-    return _normalize_aux_provider(provider, for_vision=True)
+    provider = (provider or "auto").strip().lower()
+    if provider == "codex":
+        return "openai-codex"
+    if provider == "main":
+        # Resolve to actual main provider — named custom providers and
+        # non-aggregator providers need to pass through as their real name.
+        main_prov = _read_main_provider()
+        if main_prov and main_prov not in ("auto", "main", ""):
+            return main_prov
+        return "custom"
+    return provider


 def _resolve_strict_vision_backend(provider: str) -> Tuple[Optional[Any], Optional[str]]:
@@ -1481,7 +1400,7 @@ def _resolve_strict_vision_backend(provider: str) -> Tuple[Optional[Any], Option
    if provider == "openrouter":
        return _try_openrouter()
    if provider == "nous":
-        return _try_nous(vision=True)
+        return _try_nous()
    if provider == "openai-codex":
        return _try_codex()
    if provider == "anthropic":
@@ -1514,26 +1433,17 @@ def _preferred_main_vision_provider() -> Optional[str]:
 def get_available_vision_backends() -> List[str]:
    """Return the currently available vision backends in auto-selection 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.
+    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.
    """
-    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
+    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)]


 def resolve_vision_provider_client(
@@ -1578,39 +1488,16 @@ def resolve_vision_provider_client(
        return "custom", client, final_model

    if requested == "auto":
-        # 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)
+        ordered = list(_VISION_AUTO_PROVIDER_ORDER)
+        preferred = _preferred_main_vision_provider()
+        if preferred in ordered:
+            ordered.remove(preferred)
+            ordered.insert(0, preferred)

-        # Fall back through aggregators.
-        for candidate in _VISION_AUTO_PROVIDER_ORDER:
-            if candidate == main_provider:
-                continue  # already tried above
+        for candidate in ordered:
            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

@@ -2125,18 +2012,7 @@ 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.
-        #
-        # ── 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)
+        if _is_payment_error(first_err):
            fb_client, fb_model, fb_label = _try_payment_fallback(
                resolved_provider, task)
            if fb_client is not None:
@@ -154,15 +154,12 @@ class ContextCompressor:

    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 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.
+        Walks backward from the end, protecting the most recent
+        ``protect_tail_count`` messages. Older tool results get their
+        content replaced with a placeholder string.

        Returns (pruned_messages, pruned_count).
        """
@@ -171,29 +168,7 @@ class ContextCompressor:

        result = [m.copy() for m in messages]
        pruned = 0
-
-        # 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
+        prune_boundary = len(result) - protect_tail_count

        for i in range(prune_boundary):
            msg = result[i]
@@ -224,39 +199,30 @@ 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
-        ``_CONTENT_MAX`` 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 3000 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 enough content for the summarizer
+            # Tool results: keep more content than before (3000 chars)
            if role == "tool":
                tool_id = msg.get("tool_call_id", "")
-                if len(content) > self._CONTENT_MAX:
-                    content = content[:self._CONTENT_HEAD] + "\n...[truncated]...\n" + content[-self._CONTENT_TAIL:]
+                if len(content) > 3000:
+                    content = content[:2000] + "\n...[truncated]...\n" + content[-800:]
                parts.append(f"[TOOL RESULT {tool_id}]: {content}")
                continue

            # Assistant messages: include tool call names AND arguments
            if role == "assistant":
-                if len(content) > self._CONTENT_MAX:
-                    content = content[:self._CONTENT_HEAD] + "\n...[truncated]...\n" + content[-self._CONTENT_TAIL:]
+                if len(content) > 3000:
+                    content = content[:2000] + "\n...[truncated]...\n" + content[-800:]
                tool_calls = msg.get("tool_calls", [])
                if tool_calls:
                    tc_parts = []
@@ -266,8 +232,8 @@ class ContextCompressor:
                            name = fn.get("name", "?")
                            args = fn.get("arguments", "")
                            # Truncate long arguments but keep enough for context
-                            if len(args) > self._TOOL_ARGS_MAX:
-                                args = args[:self._TOOL_ARGS_HEAD] + "..."
+                            if len(args) > 500:
+                                args = args[:400] + "..."
                            tc_parts.append(f"  {name}({args})")
                        else:
                            fn = getattr(tc, "function", None)
@@ -278,8 +244,8 @@ class ContextCompressor:
                continue

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

        return "\n\n".join(parts)
@@ -344,9 +310,6 @@ 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."""
@@ -385,9 +348,6 @@ 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."""
@@ -558,20 +518,13 @@ 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.

-        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.
+        Never cuts inside a tool_call/result group. Falls back to the old
+        ``protect_last_n`` if the budget would protect fewer messages.
        """
        if token_budget is None:
            token_budget = self.tail_token_budget
        n = len(messages)
-        # 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)
+        min_tail = self.protect_last_n
        accumulated = 0
        cut_idx = n  # start from beyond the end

@@ -584,21 +537,21 @@ 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
-            # 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:
+            if accumulated + msg_tokens > token_budget and (n - i) >= min_tail:
                break
            accumulated += msg_tokens
            cut_idx = i

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

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

        # Align to avoid splitting tool groups
        cut_idx = self._align_boundary_backward(messages, cut_idx)
@@ -623,13 +576,12 @@ Write only the summary body. Do not include any preamble or prefix."""
        up so the API never receives mismatched IDs.
        """
        n_messages = len(messages)
-        # 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 n_messages <= self.protect_first_n + self.protect_last_n + 1:
            if not self.quiet_mode:
                logger.warning(
                    "Cannot compress: only %d messages (need > %d)",
-                    n_messages, _min_for_compress,
+                    n_messages,
+                    self.protect_first_n + self.protect_last_n + 1,
                )
            return messages

@@ -637,8 +589,7 @@ 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,
-            protect_tail_tokens=self.tail_token_budget,
+            messages, protect_tail_count=self.protect_last_n * 3,
        )
        if pruned_count and not self.quiet_mode:
            logger.info("Pre-compression: pruned %d old tool result(s)", pruned_count)
@@ -18,14 +18,12 @@ 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,
    _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,
    read_credential_pool,
    write_credential_pool,
@@ -66,10 +64,10 @@ SUPPORTED_POOL_STRATEGIES = {
 }

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

 # Pool key prefix for custom OpenAI-compatible endpoints.
 # Custom endpoints all share provider='custom' but are keyed by their
@@ -513,13 +511,6 @@ 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,
@@ -605,35 +596,6 @@ 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()
-                        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")
-                    return synced
            self._mark_exhausted(entry, None)
            return None

@@ -1122,9 +1084,7 @@ 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 == "kimi-coding":
-            base_url = _resolve_kimi_base_url(token, pconfig.inference_base_url, env_url)
-        elif provider == "zai":
+        if provider == "zai":
            base_url = _resolve_zai_base_url(token, pconfig.inference_base_url, env_url)
        changed |= _upsert_entry(
            entries,
@@ -1,792 +0,0 @@
-"""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)
-
-    @property
-    def is_transient(self) -> bool:
-        """Error is expected to resolve on retry (with or without backoff)."""
-        return self.reason in (
-            FailoverReason.rate_limit,
-            FailoverReason.overloaded,
-            FailoverReason.server_error,
-            FailoverReason.timeout,
-            FailoverReason.unknown,
-        )
-
-
-# ── 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,
-        )
-
-    # 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
-    if any(p in error_msg for p in _AUTH_PATTERNS):
-        return result_fn(
-            FailoverReason.auth,
-            retryable=True,
-            should_rotate_credential=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]
@@ -26,14 +26,12 @@ _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",
 })


@@ -115,15 +113,8 @@ DEFAULT_CONTEXT_LENGTHS = {
    "llama": 131072,
    # Qwen
    "qwen": 131072,
-    # 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,
+    # MiniMax
+    "minimax": 204800,
    # GLM
    "glm": 202752,
    # Kimi
@@ -136,7 +127,7 @@ DEFAULT_CONTEXT_LENGTHS = {
    "deepseek-ai/DeepSeek-V3.2": 65536,
    "moonshotai/Kimi-K2.5": 262144,
    "moonshotai/Kimi-K2-Thinking": 262144,
-    "MiniMaxAI/MiniMax-M2.5": 1048576,
+    "MiniMaxAI/MiniMax-M2.5": 204800,
    "XiaomiMiMo/MiMo-V2-Flash": 32768,
    "mimo-v2-pro": 1048576,
    "mimo-v2-omni": 1048576,
@@ -189,7 +180,6 @@ _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",
@@ -197,7 +187,6 @@ _URL_TO_PROVIDER: Dict[str, str] = {
    "api.githubcopilot.com": "copilot",
    "models.github.ai": "copilot",
    "api.fireworks.ai": "fireworks",
-    "opencode.ai": "opencode-go",
 }


@@ -603,49 +592,6 @@ 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).

@@ -665,59 +611,6 @@ 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
@@ -153,7 +153,6 @@ 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",
@@ -204,30 +204,6 @@ 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"
@@ -349,13 +325,6 @@ 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
@@ -1,242 +0,0 @@
-"""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)
@@ -1,57 +0,0 @@
-"""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
@@ -159,10 +159,7 @@ class SubdirectoryHintTracker:

    def _is_valid_subdir(self, path: Path) -> bool:
        """Check if path is a valid directory to scan for hints."""
-        try:
-            if not path.is_dir():
-                return False
-        except OSError:
+        if not path.is_dir():
            return False
        if path in self._loaded_dirs:
            return False
@@ -175,10 +172,7 @@ class SubdirectoryHintTracker:
        found_hints = []
        for filename in _HINT_FILENAMES:
            hint_path = directory / filename
-            try:
-                if not hint_path.is_file():
-                    continue
-            except OSError:
+            if not hint_path.is_file():
                continue
            try:
                content = hint_path.read_text(encoding="utf-8").strip()
@@ -48,25 +48,6 @@ 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)
 # =============================================================================
@@ -136,8 +117,7 @@ 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: "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.
+  # sudo_password: ""  # Enable sudo commands (pipes via sudo -S) - SECURITY WARNING: plaintext!

 # -----------------------------------------------------------------------------
 # OPTION 2: SSH remote execution
@@ -228,18 +208,13 @@ terminal:
 #
 # SECURITY WARNING: Password stored in plaintext!
 #
-# INTERACTIVE PROMPT: If sudo_password is unset and the CLI is running,
+# INTERACTIVE PROMPT: If no sudo_password is set 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)
@@ -470,16 +445,6 @@ 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
@@ -679,14 +644,10 @@ platform_toolsets:
 # Voice Transcription (Speech-to-Text)
 # =============================================================================
 # Automatically transcribe voice messages on messaging platforms.
-# 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.
+# Requires OPENAI_API_KEY in .env (uses OpenAI Whisper API directly).
 stt:
  enabled: true
-  # provider: "local"          # auto-detected if omitted
  model: "whisper-1"  # whisper-1 (cheapest) | gpt-4o-mini-transcribe | gpt-4o-transcribe
-  # mistral:
-  #   model: "voxtral-mini-latest"  # voxtral-mini-latest | voxtral-mini-2602

 # =============================================================================
 # Response Pacing (Messaging Platforms)
@@ -612,11 +612,6 @@ def _run_cleanup():
        pass
    # Shut down memory provider (on_session_end + shutdown_all) at actual
    # session boundary — NOT per-turn inside run_conversation().
-    try:
-        from hermes_cli.plugins import invoke_hook as _invoke_hook
-        _invoke_hook("on_session_finalize", session_id=_active_agent_ref.session_id if _active_agent_ref else None, platform="cli")
-    except Exception:
-        pass
    try:
        if _active_agent_ref and hasattr(_active_agent_ref, 'shutdown_memory_provider'):
            _active_agent_ref.shutdown_memory_provider(
@@ -760,10 +755,7 @@ def _setup_worktree(repo_root: str = None) -> Optional[Dict[str, str]]:
 def _cleanup_worktree(info: Dict[str, str] = None) -> None:
    """Remove a worktree and its branch on exit.

-    Preserves the worktree only if it has unpushed commits (real work
-    that hasn't been pushed to any remote).  Uncommitted changes alone
-    (untracked files, test artifacts) are not enough to keep it — agent
-    work lives in commits/PRs, not the working tree.
+    If the worktree has uncommitted changes, warn and keep it.
    """
    global _active_worktree
    info = info or _active_worktree
@@ -779,27 +771,23 @@ def _cleanup_worktree(info: Dict[str, str] = None) -> None:
    if not Path(wt_path).exists():
        return

-    # Check for unpushed commits — commits reachable from HEAD but not
-    # from any remote branch.  These represent real work the agent did
-    # but didn't push.
-    has_unpushed = False
+    # Check for uncommitted changes
    try:
-        result = subprocess.run(
-            ["git", "log", "--oneline", "HEAD", "--not", "--remotes"],
+        status = subprocess.run(
+            ["git", "status", "--porcelain"],
            capture_output=True, text=True, timeout=10, cwd=wt_path,
        )
-        has_unpushed = bool(result.stdout.strip())
+        has_changes = bool(status.stdout.strip())
    except Exception:
-        has_unpushed = True  # Assume unpushed on error — don't delete
+        has_changes = True  # Assume dirty on error — don't delete

-    if has_unpushed:
-        print(f"\n\033[33m⚠ Worktree has unpushed commits, keeping: {wt_path}\033[0m")
-        print(f"  To clean up manually: git worktree remove --force {wt_path}")
+    if has_changes:
+        print(f"\n\033[33m⚠ Worktree has uncommitted changes, keeping: {wt_path}\033[0m")
+        print(f"  To clean up manually: git worktree remove {wt_path}")
        _active_worktree = None
        return

-    # Remove worktree (even if working tree is dirty — uncommitted
-    # changes without unpushed commits are just artifacts)
+    # Remove worktree
    try:
        subprocess.run(
            ["git", "worktree", "remove", wt_path, "--force"],
@@ -808,7 +796,7 @@ def _cleanup_worktree(info: Dict[str, str] = None) -> None:
    except Exception as e:
        logger.debug("Failed to remove worktree: %s", e)

-    # Delete the branch
+    # Delete the branch (only if it was never pushed / has no upstream)
    try:
        subprocess.run(
            ["git", "branch", "-D", branch],
@@ -822,27 +810,19 @@ def _cleanup_worktree(info: Dict[str, str] = None) -> None:


 def _prune_stale_worktrees(repo_root: str, max_age_hours: int = 24) -> None:
-    """Remove stale worktrees and orphaned branches on startup.
+    """Remove worktrees older than max_age_hours that have no uncommitted changes.

-    Age-based tiers:
-    - Under max_age_hours (24h): skip — session may still be active.
-    - 24h–72h: remove if no unpushed commits.
-    - Over 72h: force remove regardless (nothing should sit this long).
-
-    Also prunes orphaned ``hermes/*`` and ``pr-*`` local branches that
-    have no corresponding worktree.
+    Runs silently on startup to clean up after crashed/killed sessions.
    """
    import subprocess
    import time

    worktrees_dir = Path(repo_root) / ".worktrees"
    if not worktrees_dir.exists():
-        _prune_orphaned_branches(repo_root)
        return

    now = time.time()
-    soft_cutoff = now - (max_age_hours * 3600)       # 24h default
-    hard_cutoff = now - (max_age_hours * 3 * 3600)   # 72h default
+    cutoff = now - (max_age_hours * 3600)

    for entry in worktrees_dir.iterdir():
        if not entry.is_dir() or not entry.name.startswith("hermes-"):
@@ -851,24 +831,21 @@ def _prune_stale_worktrees(repo_root: str, max_age_hours: int = 24) -> None:
        # Check age
        try:
            mtime = entry.stat().st_mtime
-            if mtime > soft_cutoff:
+            if mtime > cutoff:
                continue  # Too recent — skip
        except Exception:
            continue

-        force = mtime <= hard_cutoff  # Over 72h — force remove
-
-        if not force:
-            # 24h–72h tier: only remove if no unpushed commits
-            try:
-                result = subprocess.run(
-                    ["git", "log", "--oneline", "HEAD", "--not", "--remotes"],
-                    capture_output=True, text=True, timeout=5, cwd=str(entry),
-                )
-                if result.stdout.strip():
-                    continue  # Has unpushed commits — skip
-            except Exception:
-                continue  # Can't check — skip
+        # Check for uncommitted changes
+        try:
+            status = subprocess.run(
+                ["git", "status", "--porcelain"],
+                capture_output=True, text=True, timeout=5, cwd=str(entry),
+            )
+            if status.stdout.strip():
+                continue  # Has changes — skip
+        except Exception:
+            continue  # Can't check — skip

        # Safe to remove
        try:
@@ -887,81 +864,10 @@ def _prune_stale_worktrees(repo_root: str, max_age_hours: int = 24) -> None:
                    ["git", "branch", "-D", branch],
                    capture_output=True, text=True, timeout=10, cwd=repo_root,
                )
-            logger.debug("Pruned stale worktree: %s (force=%s)", entry.name, force)
+            logger.debug("Pruned stale worktree: %s", entry.name)
        except Exception as e:
            logger.debug("Failed to prune worktree %s: %s", entry.name, e)

-    _prune_orphaned_branches(repo_root)
-
-
-def _prune_orphaned_branches(repo_root: str) -> None:
-    """Delete local ``hermes/hermes-*`` and ``pr-*`` branches with no worktree.
-
-    These are auto-generated by ``hermes -w`` sessions and PR review
-    workflows respectively.  Once their worktree is gone they serve no
-    purpose and just accumulate.
-    """
-    import subprocess
-
-    try:
-        result = subprocess.run(
-            ["git", "branch", "--format=%(refname:short)"],
-            capture_output=True, text=True, timeout=10, cwd=repo_root,
-        )
-        if result.returncode != 0:
-            return
-        all_branches = [b.strip() for b in result.stdout.strip().split("\n") if b.strip()]
-    except Exception:
-        return
-
-    # Collect branches that are actively checked out in a worktree
-    active_branches: set = set()
-    try:
-        wt_result = subprocess.run(
-            ["git", "worktree", "list", "--porcelain"],
-            capture_output=True, text=True, timeout=10, cwd=repo_root,
-        )
-        for line in wt_result.stdout.split("\n"):
-            if line.startswith("branch refs/heads/"):
-                active_branches.add(line.split("branch refs/heads/", 1)[-1].strip())
-    except Exception:
-        return  # Can't determine active branches — bail
-
-    # Also protect the currently checked-out branch and main
-    try:
-        head_result = subprocess.run(
-            ["git", "branch", "--show-current"],
-            capture_output=True, text=True, timeout=5, cwd=repo_root,
-        )
-        current = head_result.stdout.strip()
-        if current:
-            active_branches.add(current)
-    except Exception:
-        pass
-    active_branches.add("main")
-
-    orphaned = [
-        b for b in all_branches
-        if b not in active_branches
-        and (b.startswith("hermes/hermes-") or b.startswith("pr-"))
-    ]
-
-    if not orphaned:
-        return
-
-    # Delete in batches
-    for i in range(0, len(orphaned), 50):
-        batch = orphaned[i:i + 50]
-        try:
-            subprocess.run(
-                ["git", "branch", "-D"] + batch,
-                capture_output=True, text=True, timeout=30, cwd=repo_root,
-            )
-        except Exception as e:
-            logger.debug("Failed to prune orphaned branches: %s", e)
-
-    logger.debug("Pruned %d orphaned branches", len(orphaned))
-
 # ============================================================================
 # ASCII Art & Branding
 # ============================================================================
@@ -1546,7 +1452,6 @@ class HermesCLI:
        self._clarify_deadline = 0
        self._sudo_state = None
        self._sudo_deadline = 0
-        self._modal_input_snapshot = None
        self._approval_state = None
        self._approval_deadline = 0
        self._approval_lock = threading.Lock()
@@ -1603,12 +1508,7 @@ class HermesCLI:
        return f"[{('█' * filled) + ('░' * max(0, width - filled))}]"

    def _get_status_bar_snapshot(self) -> Dict[str, Any]:
-        # Prefer the agent's model name — it updates on fallback.
-        # self.model reflects the originally configured model and never
-        # changes mid-session, so the TUI would show a stale name after
-        # _try_activate_fallback() switches provider/model.
-        agent = getattr(self, "agent", None)
-        model_name = (getattr(agent, "model", None) or self.model or "unknown")
+        model_name = self.model or "unknown"
        model_short = model_name.split("/")[-1] if "/" in model_name else model_name
        if model_short.endswith(".gguf"):
            model_short = model_short[:-5]
@@ -1634,6 +1534,7 @@ class HermesCLI:
            "compressions": 0,
        }

+        agent = getattr(self, "agent", None)
        if not agent:
            return snapshot

@@ -3413,22 +3314,6 @@ class HermesCLI:
        flush_tool_summary()
        print()
    
-    def _notify_session_boundary(self, event_type: str) -> None:
-        """Fire a session-boundary plugin hook (on_session_finalize or on_session_reset).
-
-        Non-blocking — errors are caught and logged.  Safe to call from any
-        lifecycle point (shutdown, /new, /reset).
-        """
-        try:
-            from hermes_cli.plugins import invoke_hook as _invoke_hook
-            _invoke_hook(
-                event_type,
-                session_id=self.agent.session_id if self.agent else None,
-                platform=getattr(self, "platform", None) or "cli",
-            )
-        except Exception:
-            pass
-
    def new_session(self, silent=False):
        """Start a fresh session with a new session ID and cleared agent state."""
        if self.agent and self.conversation_history:
@@ -3436,10 +3321,6 @@ class HermesCLI:
                self.agent.flush_memories(self.conversation_history)
            except (Exception, KeyboardInterrupt):
                pass
-            self._notify_session_boundary("on_session_finalize")
-        elif self.agent:
-            # First session or empty history — still finalize the old session
-            self._notify_session_boundary("on_session_finalize")

        old_session_id = self.session_id
        if self._session_db and old_session_id:
@@ -3484,7 +3365,6 @@ class HermesCLI:
                    )
                except Exception:
                    pass
-            self._notify_session_boundary("on_session_reset")

        if not silent:
            print("(^_^)v New session started!")
@@ -4008,7 +3888,59 @@ class HermesCLI:

        print("  To change model or provider, use: hermes model")

-
+    def _handle_prompt_command(self, cmd: str):
+        """Handle the /prompt command to view or set system prompt."""
+        parts = cmd.split(maxsplit=1)
+        
+        if len(parts) > 1:
+            # Set new prompt
+            new_prompt = parts[1].strip()
+            
+            if new_prompt.lower() == "clear":
+                self.system_prompt = ""
+                self.agent = None  # Force re-init
+                if save_config_value("agent.system_prompt", ""):
+                    print("(^_^)b System prompt cleared (saved to config)")
+                else:
+                    print("(^_^) System prompt cleared (session only)")
+            else:
+                self.system_prompt = new_prompt
+                self.agent = None  # Force re-init
+                if save_config_value("agent.system_prompt", new_prompt):
+                    print("(^_^)b System prompt set (saved to config)")
+                else:
+                    print("(^_^) System prompt set (session only)")
+                print(f"  \"{new_prompt[:60]}{'...' if len(new_prompt) > 60 else ''}\"")
+        else:
+            # Show current prompt
+            print()
+            print("+" + "-" * 50 + "+")
+            print("|" + " " * 15 + "(^_^) System Prompt" + " " * 15 + "|")
+            print("+" + "-" * 50 + "+")
+            print()
+            if self.system_prompt:
+                # Word wrap the prompt for display
+                words = self.system_prompt.split()
+                lines = []
+                current_line = ""
+                for word in words:
+                    if len(current_line) + len(word) + 1 <= 50:
+                        current_line += (" " if current_line else "") + word
+                    else:
+                        lines.append(current_line)
+                        current_line = word
+                if current_line:
+                    lines.append(current_line)
+                for line in lines:
+                    print(f"  {line}")
+            else:
+                print("  (no custom prompt set - using default)")
+            print()
+            print("  Usage:")
+            print("    /prompt <text>  - Set a custom system prompt")
+            print("    /prompt clear   - Remove custom prompt")
+            print("    /personality    - Use a predefined personality")
+            print()
    

    @staticmethod
@@ -4508,7 +4440,9 @@ class HermesCLI:
            self._handle_model_switch(cmd_original)
        elif canonical == "provider":
            self._show_model_and_providers()
-
+        elif canonical == "prompt":
+            # Use original case so prompt text isn't lowercased
+            self._handle_prompt_command(cmd_original)
        elif canonical == "personality":
            # Use original case (handler lowercases the personality name itself)
            self._handle_personality_command(cmd_original)
@@ -4619,13 +4553,13 @@ class HermesCLI:
                            if output:
                                self.console.print(_rich_text_from_ansi(output))
                            else:
-                                self.console.print("[dim]Command returned no output[/]")
+                                ChatConsole().print("[dim]Command returned no output[/]")
                        except subprocess.TimeoutExpired:
-                            self.console.print("[bold red]Quick command timed out (30s)[/]")
+                            ChatConsole().print("[bold red]Quick command timed out (30s)[/]")
                        except Exception as e:
-                            self.console.print(f"[bold red]Quick command error: {e}[/]")
+                            ChatConsole().print(f"[bold red]Quick command error: {e}[/]")
                    else:
-                        self.console.print(f"[bold red]Quick command '{base_cmd}' has no command defined[/]")
+                        ChatConsole().print(f"[bold red]Quick command '{base_cmd}' has no command defined[/]")
                elif qcmd.get("type") == "alias":
                    target = qcmd.get("target", "").strip()
                    if target:
@@ -4634,9 +4568,9 @@ class HermesCLI:
                        aliased_command = f"{target} {user_args}".strip()
                        return self.process_command(aliased_command)
                    else:
-                        self.console.print(f"[bold red]Quick command '{base_cmd}' has no target defined[/]")
+                        ChatConsole().print(f"[bold red]Quick command '{base_cmd}' has no target defined[/]")
                else:
-                    self.console.print(f"[bold red]Quick command '{base_cmd}' has unsupported type (supported: 'exec', 'alias')[/]")
+                    ChatConsole().print(f"[bold red]Quick command '{base_cmd}' has unsupported type (supported: 'exec', 'alias')[/]")
            # Check for plugin-registered slash commands
            elif base_cmd.lstrip("/") in _get_plugin_cmd_handler_names():
                from hermes_cli.plugins import get_plugin_command_handler
@@ -5359,27 +5293,12 @@ class HermesCLI:
            print(f"  ❌ Compression failed: {e}")

    def _show_usage(self):
-        """Show rate limits (if available) and session token usage."""
+        """Show cumulative token usage for the current session."""
        if not self.agent:
            print("(._.) No active agent -- send a message first.")
            return

        agent = self.agent
-        calls = agent.session_api_calls
-
-        if calls == 0:
-            print("(._.) No API calls made yet in this session.")
-            return
-
-        # ── Rate limits (shown first when available) ────────────────
-        rl_state = agent.get_rate_limit_state()
-        if rl_state and rl_state.has_data:
-            from agent.rate_limit_tracker import format_rate_limit_display
-            print()
-            print(format_rate_limit_display(rl_state))
-            print()
-
-        # ── Session token usage ─────────────────────────────────────
        input_tokens = getattr(agent, "session_input_tokens", 0) or 0
        output_tokens = getattr(agent, "session_output_tokens", 0) or 0
        cache_read_tokens = getattr(agent, "session_cache_read_tokens", 0) or 0
@@ -5387,7 +5306,13 @@ class HermesCLI:
        prompt = agent.session_prompt_tokens
        completion = agent.session_completion_tokens
        total = agent.session_total_tokens
+        calls = agent.session_api_calls

+        if calls == 0:
+            print("(._.) No API calls made yet in this session.")
+            return
+
+        # Current context window state
        compressor = agent.context_compressor
        last_prompt = compressor.last_prompt_tokens
        ctx_len = compressor.context_length
@@ -6165,7 +6090,6 @@ class HermesCLI:
        timeout = 45
        response_queue = queue.Queue()

-        self._capture_modal_input_snapshot()
        self._sudo_state = {
            "response_queue": response_queue,
        }
@@ -6178,7 +6102,6 @@ class HermesCLI:
                result = response_queue.get(timeout=1)
                self._sudo_state = None
                self._sudo_deadline = 0
-                self._restore_modal_input_snapshot()
                self._invalidate()
                if result:
                    _cprint(f"\n{_DIM}  ✓ Password received (cached for session){_RST}")
@@ -6193,7 +6116,6 @@ class HermesCLI:

        self._sudo_state = None
        self._sudo_deadline = 0
-        self._restore_modal_input_snapshot()
        self._invalidate()
        _cprint(f"\n{_DIM}  ⏱ Timeout — continuing without sudo{_RST}")
        return ""
@@ -6366,33 +6288,6 @@ class HermesCLI:
    def _secret_capture_callback(self, var_name: str, prompt: str, metadata=None) -> dict:
        return prompt_for_secret(self, var_name, prompt, metadata)

-    def _capture_modal_input_snapshot(self) -> None:
-        """Temporarily clear the input buffer and save the user's in-progress draft."""
-        if self._modal_input_snapshot is not None or not getattr(self, "_app", None):
-            return
-        try:
-            buf = self._app.current_buffer
-            self._modal_input_snapshot = {
-                "text": buf.text,
-                "cursor_position": buf.cursor_position,
-            }
-            buf.reset()
-        except Exception:
-            self._modal_input_snapshot = None
-
-    def _restore_modal_input_snapshot(self) -> None:
-        """Restore any draft text that was present before a modal prompt opened."""
-        snapshot = self._modal_input_snapshot
-        self._modal_input_snapshot = None
-        if not snapshot or not getattr(self, "_app", None):
-            return
-        try:
-            buf = self._app.current_buffer
-            buf.text = snapshot.get("text", "")
-            buf.cursor_position = min(snapshot.get("cursor_position", 0), len(buf.text))
-        except Exception:
-            pass
-
    def _submit_secret_response(self, value: str) -> None:
        if not self._secret_state:
            return
@@ -7120,7 +7015,6 @@ class HermesCLI:
        # Sudo password prompt state (similar mechanism to clarify)
        self._sudo_state = None         # dict with response_queue when active
        self._sudo_deadline = 0
-        self._modal_input_snapshot = None

        # Dangerous command approval state (similar mechanism to clarify)
        self._approval_state = None     # dict with command, description, choices, selected, response_queue
@@ -7192,6 +7086,7 @@ class HermesCLI:
                text = event.app.current_buffer.text
                self._sudo_state["response_queue"].put(text)
                self._sudo_state = None
+                event.app.current_buffer.reset()
                event.app.invalidate()
                return

@@ -7396,6 +7291,7 @@ class HermesCLI:
            if self._sudo_state:
                self._sudo_state["response_queue"].put("")
                self._sudo_state = None
+                event.app.current_buffer.reset()
                event.app.invalidate()
                return

@@ -574,16 +574,12 @@ def remove_job(job_id: str) -> bool:
    return False


-def mark_job_run(job_id: str, success: bool, error: Optional[str] = None,
-                 delivery_error: Optional[str] = None):
+def mark_job_run(job_id: str, success: bool, 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):
@@ -592,8 +588,6 @@ 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", "bluebubbles",
+    "wecom", "sms", "email", "webhook",
 })

 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", "bluebubbles"):
+        for platform_name in ("matrix", "telegram", "discord", "slack"):
            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) -> Optional[str]:
+def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> None:
    """
    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) -> Option
    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":
-            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
+            logger.warning(
+                "Job '%s' deliver=%s but no concrete delivery target could be resolved",
+                job["id"],
+                job.get("deliver", "local"),
+            )
+        return

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

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

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

    # 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
@@ -311,7 +307,7 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option

            if adapter_ok:
                logger.info("Job '%s': delivered to %s:%s via live adapter", job["id"], platform_name, chat_id)
-                return None
+                return
        except Exception as e:
            logger.warning(
                "Job '%s': live adapter delivery to %s:%s failed (%s), falling back to standalone",
@@ -333,17 +329,13 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
            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:
-        msg = f"delivery to {platform_name}:{chat_id} failed: {e}"
-        logger.error("Job '%s': %s", job["id"], msg)
-        return msg
+        logger.error("Job '%s': delivery to %s:%s failed: %s", job["id"], platform_name, chat_id, e)
+        return

    if result and result.get("error"):
-        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
+        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)


 _SCRIPT_TIMEOUT = 120  # seconds
@@ -586,9 +578,11 @@ 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 config.yaml
+        # Reasoning config from env or config.yaml
        from hermes_constants import parse_reasoning_effort
-        effort = str(_cfg.get("agent", {}).get("reasoning_effort", "")).strip()
+        effort = os.getenv("HERMES_REASONING_EFFORT", "")
+        if not effort:
+            effort = str(_cfg.get("agent", {}).get("reasoning_effort", "")).strip()
        reasoning_config = parse_reasoning_effort(effort)

        # Prefill messages from env or config.yaml
@@ -874,15 +868,13 @@ 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:
-                        delivery_error = _deliver_result(job, deliver_content, adapters=adapters, loop=loop)
+                        _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, delivery_error=delivery_error)
+                mark_job_run(job["id"], success, error)
                executed += 1

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

  inputs = {
-    nixpkgs.url = "github:NixOS/nixpkgs/nixos-unstable";
+    nixpkgs.url = "github:NixOS/nixpkgs/nixos-24.11";
    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", "bluebubbles"):
+    for plat_name in ("telegram", "whatsapp", "signal", "email", "sms"):
        if plat_name not in platforms:
            platforms[plat_name] = _build_from_sessions(plat_name)

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


@dataclass
@@ -288,9 +287,6 @@ 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]:
@@ -716,13 +712,6 @@ 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:
@@ -952,29 +941,6 @@ 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:
@@ -298,7 +298,6 @@ 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",
@@ -408,10 +407,6 @@ 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)
    
@@ -1,828 +0,0 @@
-"""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,
-        )
-        return True
-
-    async def disconnect(self) -> None:
-        if self.client:
-            await self.client.aclose()
-            self.client = None
-        if self._runner:
-            await self._runner.cleanup()
-            self._runner = None
-        self._mark_disconnected()
-
-    # ------------------------------------------------------------------
-    # 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")
@@ -455,9 +455,6 @@ 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."""
@@ -777,7 +774,7 @@ class DiscordAdapter(BasePlatformAdapter):
            message_ids = []
            reference = None

-            if reply_to and self._reply_to_mode != "off":
+            if reply_to:
                try:
                    ref_msg = await channel.fetch_message(int(reply_to))
                    reference = ref_msg
@@ -785,10 +782,7 @@ class DiscordAdapter(BasePlatformAdapter):
                    logger.debug("Could not fetch reply-to message: %s", e)

            for i, chunk in enumerate(chunks):
-                if self._reply_to_mode == "all":
-                    chunk_reference = reference
-                else:  # "first" (default) or "off"
-                    chunk_reference = reference if i == 0 else None
+                chunk_reference = reference if i == 0 else None
                try:
                    msg = await channel.send(
                        content=chunk,
@@ -1767,9 +1761,8 @@ 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).
-        # For forum threads, inherit the parent forum's topic.
-        chat_topic = self._get_effective_topic(interaction.channel, is_thread=is_thread)
+        # Get channel topic (if available)
+        chat_topic = getattr(interaction.channel, "topic", None)

        source = self.build_source(
            chat_id=str(interaction.channel_id),
@@ -1843,10 +1836,6 @@ 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,
@@ -1854,7 +1843,6 @@ 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(
@@ -2140,15 +2128,6 @@ 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"))
@@ -2316,10 +2295,8 @@ 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).
-        # 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)
+        # Get channel topic (if available - TextChannels have topics, DMs/threads don't)
+        chat_topic = getattr(message.channel, "topic", None)

        # Build source
        source = self.build_source(
@@ -2382,7 +2359,7 @@ class DiscordAdapter(BasePlatformAdapter):
                        ext or "unknown", content_type,
                    )
                else:
-                    MAX_DOC_BYTES = 32 * 1024 * 1024
+                    MAX_DOC_BYTES = 20 * 1024 * 1024
                    if att.size and att.size > MAX_DOC_BYTES:
                        logger.warning(
                            "[Discord] Document too large (%s bytes), skipping: %s",
@@ -2406,9 +2383,9 @@ 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 plain-text documents (capped at 100 KB)
+                            # Inject text content for .txt/.md files (capped at 100 KB)
                            MAX_TEXT_INJECT_BYTES = 100 * 1024
-                            if ext in (".md", ".txt", ".log") and len(raw_bytes) <= MAX_TEXT_INJECT_BYTES:
+                            if ext in (".md", ".txt") and len(raw_bytes) <= MAX_TEXT_INJECT_BYTES:
                                try:
                                    text_content = raw_bytes.decode("utf-8")
                                    display_name = att.filename or f"document{ext}"
@@ -20,7 +20,6 @@ from __future__ import annotations
 import asyncio
 import hashlib
 import hmac
-import itertools
 import json
 import logging
 import mimetypes
@@ -1053,9 +1052,6 @@ 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
@@ -1398,104 +1394,6 @@ 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,
@@ -1922,52 +1820,6 @@ 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:
@@ -647,11 +647,7 @@ class SignalAdapter(BasePlatformAdapter):

        if result is not None:
            self._track_sent_timestamp(result)
-            # 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=True)
        return SendResult(success=False, error="RPC send failed")

    def _track_sent_timestamp(self, rpc_result) -> None:
@@ -841,11 +837,6 @@ 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 +14,7 @@ import logging
 import os
 import re
 import time
-from typing import Dict, Optional, Any, Tuple
+from typing import Dict, Optional, Any

 try:
    from slack_bolt.async_app import AsyncApp
@@ -95,12 +95,6 @@ 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

    async def connect(self) -> bool:
        """Connect to Slack via Socket Mode."""
@@ -187,14 +181,6 @@ 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):
@@ -769,135 +755,6 @@ 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)
@@ -924,21 +781,10 @@ class SlackAdapter(BasePlatformAdapter):
            return

        text = event.get("text", "")
+        user_id = event.get("user", "")
        channel_id = event.get("channel", "")
        ts = event.get("ts", "")
-        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", "")
-        )
+        team_id = event.get("team", "")

        # Track which workspace owns this channel
        if team_id and channel_id:
@@ -946,8 +792,6 @@ class SlackAdapter(BasePlatformAdapter):

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

        # Build thread_ts for session keying.
@@ -956,7 +800,7 @@ 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") or assistant_meta.get("thread_ts")  # None for top-level DMs
+            thread_ts = event.get("thread_ts")  # None for top-level DMs
        else:
            thread_ts = event.get("thread_ts") or ts  # ts fallback for channels

@@ -184,8 +184,6 @@ 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", "")
@@ -923,11 +921,12 @@ class GatewayRunner:

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

-        Reads agent.reasoning_effort from config.yaml. Valid: "xhigh",
-        "high", "medium", "low", "minimal", "none". Returns None to use
-        default (medium).
+        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).
        """
        from hermes_constants import parse_reasoning_effort
        effort = ""
@@ -940,6 +939,8 @@ 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)
@@ -1075,7 +1076,6 @@ 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(
@@ -1086,8 +1086,7 @@ 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",
-                       "BLUEBUBBLES_ALLOW_ALL_USERS")
+                       "WECOM_ALLOW_ALL_USERS")
        )
        if not _any_allowlist and not _allow_all:
            logger.warning(
@@ -1485,14 +1484,6 @@ 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'):
@@ -1658,13 +1649,6 @@ 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:
@@ -1703,7 +1687,6 @@ 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",
@@ -1718,7 +1701,6 @@ 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)
@@ -1792,11 +1774,8 @@ class GatewayRunner:
        """
        source = event.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):
+        # Check if user is authorized
+        if 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":
@@ -3298,15 +3277,6 @@ 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 "",
@@ -3320,7 +3290,7 @@ 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()
@@ -3331,18 +3301,9 @@ class GatewayRunner:
            header = "✨ Session reset! Starting fresh."
        else:
            # No existing session, just create one
-            new_entry = self.session_store.get_or_create_session(source, force_new=True)
+            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
@@ -5280,28 +5241,19 @@ class GatewayRunner:

        agent = self._running_agents.get(session_key)
        if agent and hasattr(agent, "session_total_tokens") and agent.session_api_calls > 0:
-            lines = []
-
-            # Rate limits first (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
-            lines.append("📊 **Session Token Usage**")
-            lines.append(f"Prompt (input): {agent.session_prompt_tokens:,}")
-            lines.append(f"Completion (output): {agent.session_completion_tokens:,}")
-            lines.append(f"Total: {agent.session_total_tokens:,}")
-            lines.append(f"API calls: {agent.session_api_calls}")
+            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}",
+            ]
            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
@@ -5543,7 +5495,7 @@ 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.BLUEBUBBLES, Platform.LOCAL,
+        Platform.FEISHU, Platform.WECOM, Platform.LOCAL,
    })

    async def _handle_update_command(self, event: MessageEvent) -> str:
@@ -6183,7 +6135,6 @@ class GatewayRunner:
                                text=synth_text,
                                message_type=MessageType.TEXT,
                                source=_source,
-                                internal=True,
                            )
                            logger.info(
                                "Process %s finished — injecting agent notification for session %s",
@@ -6334,15 +6285,7 @@ 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".
-        #
-        # 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")
+        _raw_tp = user_config.get("display", {}).get("tool_progress")
        if _raw_tp is False:
            _raw_tp = "off"
        progress_mode = (
@@ -6446,18 +6389,6 @@ 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)
@@ -7152,9 +7083,6 @@ 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)
@@ -7187,25 +7115,6 @@ 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
@@ -193,7 +193,6 @@ _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>``
@@ -74,8 +74,6 @@ 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:
@@ -140,19 +138,12 @@ class GatewayStreamConsumer:
                    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 = ""
@@ -165,17 +156,9 @@ class GatewayStreamConsumer:
                    self._last_edit_time = time.monotonic()

                if got_done:
-                    # 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)
+                    # Final edit without cursor
+                    if self._accumulated and self._message_id:
+                        await self._send_or_edit(self._accumulated)
                    return

                # Tool boundary: the should_edit block above already flushed
@@ -186,8 +169,6 @@ class GatewayStreamConsumer:
                    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

@@ -226,86 +207,6 @@ class GatewayStreamConsumer:
        # Strip trailing whitespace/newlines but preserve leading content
        return cleaned.rstrip()

-    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.
@@ -331,16 +232,14 @@ class GatewayStreamConsumer:
                        self._last_sent_text = text
                    else:
                        # If an edit fails mid-stream (especially Telegram flood control),
-                        # stop progressive edits and send only the missing tail once the
-                        # final response is available.
+                        # stop progressive edits and let the normal final send path deliver
+                        # the complete answer instead of leaving the user with a partial.
                        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 = True
+                        self._already_sent = False
                else:
                    # Editing not supported — skip intermediate updates.
-                    # The final response will be sent by the fallback path.
+                    # The final response will be sent by the normal path.
                    pass
            else:
                # First message — send new
@@ -353,17 +252,6 @@ 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__ = "0.8.0"
-__release_date__ = "2026.4.8"
+__version__ = "0.7.0"
+__release_date__ = "2026.4.3"
@@ -67,16 +67,12 @@ 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


 # =============================================================================
@@ -116,12 +112,6 @@ 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",
@@ -250,7 +240,7 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
 # Kimi Code Endpoint Detection
 # =============================================================================

-# Kimi Code (kimi.com/code) issues keys prefixed "sk-kimi-" that only work
+# Kimi Code (platform.kimi.ai) 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.
@@ -827,7 +817,6 @@ 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",
@@ -957,176 +946,6 @@ 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
 # =============================================================================
@@ -2253,8 +2072,6 @@ 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
@@ -3017,15 +2834,12 @@ 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:
@@ -3059,6 +2873,9 @@ 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.")
@@ -3070,15 +2887,6 @@ 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", "qwen-oauth"}
+_OAUTH_CAPABLE_PROVIDERS = {"anthropic", "nous", "openai-codex"}


 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", "qwen-oauth"} else AUTH_TYPE_API_KEY
+            requested_type = AUTH_TYPE_OAUTH if provider in {"anthropic", "nous", "openai-codex"} else AUTH_TYPE_API_KEY

    pool = load_pool(provider)

@@ -250,26 +250,6 @@ 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.")


@@ -295,16 +295,10 @@ 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
-        rounded = round(val)
-        if abs(val - rounded) < 0.05:
-            return f"{rounded}M"
-        return f"{val:.1f}M"
+        return f"{val:g}M"
    elif tokens >= 1_000:
        val = tokens / 1_000
-        rounded = round(val)
-        if abs(val - rounded) < 0.05:
-            return f"{rounded}K"
-        return f"{val:.1f}K"
+        return f"{val:g}K"
    return str(tokens)


@@ -87,7 +87,8 @@ 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",
@@ -128,7 +129,7 @@ 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 and rate limits for the current session", "Info"),
+    CommandDef("usage", "Show token usage for the current session", "Info"),
    CommandDef("insights", "Show usage insights and analytics", "Info",
               args_hint="[days]"),
    CommandDef("platforms", "Show gateway/messaging platform status", "Info",
@@ -39,7 +39,6 @@ _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",
@@ -158,14 +157,7 @@ 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.
-
-    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.
-    """
-    if is_managed():
-        return
+    """Set directory to owner-only access (0700). No-op on Windows."""
    try:
        os.chmod(path, 0o700)
    except (OSError, NotImplementedError):
@@ -173,13 +165,7 @@ def _secure_dir(path):


 def _secure_file(path):
-    """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
+    """Set file to owner-only read/write (0600). No-op on Windows."""
    try:
        if os.path.exists(str(path)):
            os.chmod(path, 0o600)
@@ -231,10 +217,6 @@ DEFAULT_CONFIG = {
        # (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": {
@@ -397,7 +379,6 @@ 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)
    },

@@ -432,7 +413,7 @@ DEFAULT_CONFIG = {
    
    "stt": {
        "enabled": True,
-        "provider": "local",  # "local" (free, faster-whisper) | "groq" | "openai" (Whisper API) | "mistral" (Voxtral Transcribe)
+        "provider": "local",  # "local" (free, faster-whisper) | "groq" | "openai" (Whisper API)
        "local": {
            "model": "base",  # tiny, base, small, medium, large-v3
            "language": "",  # auto-detect by default; set to "en", "es", "fr", etc. to force
@@ -440,9 +421,6 @@ DEFAULT_CONFIG = {
        "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": {
@@ -569,7 +547,7 @@ DEFAULT_CONFIG = {
    },

    # Config schema version - bump this when adding new required fields
-    "_config_version": 13,
+    "_config_version": 12,
 }

 # =============================================================================
@@ -746,14 +724,6 @@ 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",
@@ -1005,13 +975,6 @@ 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, "
@@ -1125,27 +1088,6 @@ 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)",
@@ -1217,7 +1159,7 @@ OPTIONAL_ENV_VARS = {
        "category": "setting",
    },
    "SUDO_PASSWORD": {
-        "description": "Sudo password for terminal commands requiring root access; set to an explicit empty string to try empty without prompting",
+        "description": "Sudo password for terminal commands requiring root access",
        "prompt": "Sudo password",
        "url": None,
        "password": True,
@@ -1701,21 +1643,6 @@ 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
-
    if current_ver < latest_ver and not quiet:
        print(f"Config version: {current_ver} → {latest_ver}")
    
@@ -93,21 +93,6 @@ 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
@@ -812,83 +812,69 @@ def run_doctor(args):
        check_warn("No GITHUB_TOKEN", f"(60 req/hr rate limit — set in {_DHH}/.env for better rates)")

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

-    _active_memory_provider = ""
    try:
-        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
+        from plugins.memory.honcho.client import HonchoClientConfig, resolve_config_path
+        hcfg = HonchoClientConfig.from_global_config()
+        _honcho_cfg_path = resolve_config_path()

-    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()
+        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 _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()
+    # =========================================================================
+    # 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():
                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_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))
+                    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))

    # =========================================================================
    # Profiles
@@ -1,337 +0,0 @@
-"""
-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 _key_present(name: str) -> str:
-    """Return 'set' or 'not set' for an env var."""
-    return "set" if os.getenv(name) else "not set"
-
-
-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)
@@ -1588,34 +1588,6 @@ _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."},
-        ],
-    },
 ]


@@ -918,7 +918,6 @@ 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",
@@ -948,7 +947,6 @@ 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)"),
    ]
@@ -1045,8 +1043,6 @@ 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":
@@ -1363,56 +1359,6 @@ 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.

@@ -1474,11 +1420,7 @@ def _model_flow_custom(config):
            f"Hermes will still save it."
        )
        if probe.get("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}")
+            print(f"  If this server expects /v1, try base URL: {probe['suggested_base_url']}")

    # Select model — use probe results when available, fall back to manual input
    model_name = ""
@@ -2643,12 +2585,6 @@ 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
@@ -4730,22 +4666,6 @@ 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
@@ -84,7 +84,6 @@ _PASSTHROUGH_PROVIDERS: frozenset[str] = frozenset({
    "minimax",
    "minimax-cn",
    "alibaba",
-    "qwen-oauth",
    "huggingface",
    "openai-codex",
    "custom",
@@ -537,11 +537,8 @@ 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 "/" not in raw_input and is_aggregator(current_provider):
+                if colon_pos > 0 and is_aggregator(current_provider):
                    left = raw_input[:colon_pos].strip().lower()
                    right = raw_input[colon_pos + 1:].strip()
                    if left and right:
@@ -733,7 +730,6 @@ 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] = []
@@ -754,16 +750,9 @@ def list_authenticated_providers(
        if not isinstance(pdata, dict):
            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
+        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)
@@ -802,12 +791,12 @@ 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 _load_auth_store
-                store = _load_auth_store()
-                if store and (pid in store.get("providers", {}) or pid in store.get("credential_pool", {})):
+                from hermes_cli.auth import _read_auth_store
+                store = _read_auth_store()
+                if store and pid in store:
                    has_creds = True
-            except Exception as exc:
-                logger.debug("Auth store check failed for %s: %s", pid, exc)
+            except Exception:
+                pass
        if not has_creds:
            continue

@@ -144,22 +144,18 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
        "kimi-k2-0905-preview",
    ],
    "minimax": [
-        "MiniMax-M1",
-        "MiniMax-M1-40k",
-        "MiniMax-M1-80k",
-        "MiniMax-M1-128k",
-        "MiniMax-M1-256k",
-        "MiniMax-M2.5",
        "MiniMax-M2.7",
+        "MiniMax-M2.7-highspeed",
+        "MiniMax-M2.5",
+        "MiniMax-M2.5-highspeed",
+        "MiniMax-M2.1",
    ],
    "minimax-cn": [
-        "MiniMax-M1",
-        "MiniMax-M1-40k",
-        "MiniMax-M1-80k",
-        "MiniMax-M1-128k",
-        "MiniMax-M1-256k",
-        "MiniMax-M2.5",
        "MiniMax-M2.7",
+        "MiniMax-M2.7-highspeed",
+        "MiniMax-M2.5",
+        "MiniMax-M2.5-highspeed",
+        "MiniMax-M2.1",
    ],
    "anthropic": [
        "claude-opus-4-6",
@@ -483,7 +479,6 @@ _PROVIDER_LABELS = {
    "ai-gateway": "AI Gateway",
    "kilocode": "Kilo Code",
    "alibaba": "Alibaba Cloud (DashScope)",
-    "qwen-oauth": "Qwen OAuth (Portal)",
    "huggingface": "Hugging Face",
    "custom": "Custom endpoint",
 }
@@ -523,7 +518,6 @@ _PROVIDER_ALIASES = {
    "aliyun": "alibaba",
    "qwen": "alibaba",
    "alibaba-cloud": "alibaba",
-    "qwen-portal": "qwen-oauth",
    "hf": "huggingface",
    "hugging-face": "huggingface",
    "huggingface-hub": "huggingface",
@@ -769,7 +763,6 @@ 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",
    ]
@@ -1532,7 +1525,7 @@ def probe_api_models(

    return {
        "models": None,
-        "probed_url": tried[0] if tried else normalized.rstrip("/") + "/models",
+        "probed_url": tried[-1] if tried else normalized.rstrip("/") + "/models",
        "resolved_base_url": normalized,
        "suggested_base_url": alternate_base if alternate_base != normalized else None,
        "used_fallback": False,
@@ -61,8 +61,6 @@ 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", "dump", "config", "pairing", "skills", "tools",
+    "status", "cron", "doctor", "config", "pairing", "skills", "tools",
    "mcp", "sessions", "insights", "version", "update", "uninstall",
    "profile", "plugins", "honcho", "acp",
 })
@@ -1007,7 +1007,7 @@ _hermes_completion() {

    # Top-level subcommands
    if [[ "$COMP_CWORD" == 1 ]]; then
-        local commands="chat model gateway setup status cron doctor dump config skills tools mcp sessions profile update version"
+        local commands="chat model gateway setup status cron doctor config skills tools mcp sessions profile update version"
        COMPREPLY=($(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 dump config skills tools mcp sessions profile update version)' \\
+        '1:command:(chat model gateway setup status cron doctor config skills tools mcp sessions profile update version)' \\
        '*::arg:->args'

    case $words[1] in
@@ -58,12 +58,6 @@ 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",
@@ -14,13 +14,11 @@ 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,
    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,
@@ -150,9 +148,6 @@ 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()
@@ -168,16 +163,6 @@ 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
@@ -696,24 +681,6 @@ 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 {
@@ -757,15 +724,7 @@ def resolve_runtime_provider(
    pconfig = PROVIDER_REGISTRY.get(provider)
    if pconfig and pconfig.auth_type == "api_key":
        creds = resolve_api_key_provider_credentials(provider)
-        # 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("/")
+        base_url = creds.get("base_url", "").rstrip("/")
        api_mode = "chat_completions"
        if provider == "copilot":
            api_mode = _copilot_runtime_api_mode(model_cfg, creds.get("api_key", ""))
@@ -105,8 +105,8 @@ _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-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"],
+    "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"],
    "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"],
@@ -2167,71 +2167,6 @@ 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")
@@ -2286,7 +2221,6 @@ _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),
 ]

@@ -2330,7 +2264,6 @@ 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:
@@ -2350,8 +2283,6 @@ 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()
@@ -2522,8 +2453,6 @@ 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
@@ -2572,120 +2501,9 @@ _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"
@@ -2698,12 +2516,12 @@ 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 preview what would be imported before making any changes.")
+    print_info("Hermes can import your settings, memories, skills, and API keys.")
    print()

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

@@ -2712,71 +2530,34 @@ def _offer_openclaw_migration(hermes_home: Path) -> bool:
    if not config_path.exists():
        save_config(load_config())

-    # Load the migration module
+    # Dynamically load the migration script
    try:
-        mod = _load_openclaw_migration_module()
-        if mod is None:
+        spec = importlib.util.spec_from_file_location(
+            "openclaw_to_hermes", _OPENCLAW_SCRIPT
+        )
+        if spec is None or spec.loader 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

-    # ── Phase 1: Dry-run preview ──
-    try:
+        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
        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=False,  # preserve existing Hermes config
+            overwrite=True,
            migrate_secrets=True,
            output_dir=None,
            selected_options=selected,
@@ -2788,7 +2569,7 @@ def _offer_openclaw_migration(hermes_home: Path) -> bool:
        logger.debug("OpenClaw migration error", exc_info=True)
        return False

-    # Print final summary
+    # Print summary
    summary = report.get("summary", {})
    migrated = summary.get("migrated", 0)
    skipped = summary.get("skipped", 0)
@@ -2799,7 +2580,7 @@ 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 (use hermes claw migrate --overwrite to force).")
+        print_info(f"Skipped {conflicts} item(s) that already exist in Hermes.")
    if skipped:
        print_info(f"Skipped {skipped} item(s) (not found or unchanged).")
    if errors:
@@ -23,7 +23,6 @@ PLATFORMS = {
    "slack":    "💼 Slack",
    "whatsapp": "📱 WhatsApp",
    "signal":   "📡 Signal",
-    "bluebubbles": "💬 BlueBubbles",
    "email":    "📧 Email",
    "homeassistant": "🏠 Home Assistant",
    "mattermost": "💬 Mattermost",
@@ -153,14 +153,12 @@ 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, get_qwen_auth_status
+        from hermes_cli.auth import get_nous_auth_status, get_codex_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(
@@ -191,21 +189,6 @@ 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
    # =========================================================================
@@ -302,7 +285,6 @@ 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():
@@ -126,7 +126,6 @@ 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"},
@@ -1235,10 +1235,10 @@ class SessionDB:
        self._execute_write(_do)

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

-        Child sessions are orphaned (parent_session_id set to NULL) rather
-        than cascade-deleted, so they remain accessible independently.
+        Child sessions (subagent runs, compression continuations) are deleted
+        first to satisfy the ``parent_session_id`` foreign key constraint.
        Returns True if the session was found and deleted.
        """
        def _do(conn):
@@ -1247,12 +1247,15 @@ class SessionDB:
            )
            if cursor.fetchone()[0] == 0:
                return False
-            # Orphan child sessions so FK constraint is satisfied
-            conn.execute(
-                "UPDATE sessions SET parent_session_id = NULL "
-                "WHERE parent_session_id = ?",
+            # Delete child sessions first (FK constraint)
+            child_ids = [r[0] for r in conn.execute(
+                "SELECT id FROM sessions 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
@@ -1261,9 +1264,9 @@ 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 outside
-        the prune window are orphaned (parent_session_id set to NULL) rather
-        than cascade-deleted.
+        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.
        """
        cutoff = time.time() - (older_than_days * 86400)

@@ -1281,16 +1284,17 @@ class SessionDB:
                )
            session_ids = set(row["id"] for row in cursor.fetchall())

-            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),
-            )
+            # 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

            for sid in session_ids:
                conn.execute("DELETE FROM messages WHERE session_id = ?", (sid,))
@@ -464,11 +464,7 @@
      addToSystemPackages = mkOption {
        type = types.bool;
        default = false;
-        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.
-        '';
+        description = "Add hermes CLI to environment.systemPackages.";
      };

      # ── OCI Container (opt-in) ──────────────────────────────────────────
@@ -549,12 +545,8 @@
      })

      # ── 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 ───────────────────────────────────────────────────
@@ -569,7 +561,7 @@

      # ── Activation: link config + auth + documents ────────────────────
      {
-        system.activationScripts."hermes-agent-setup" = lib.stringAfter ([ "users" ] ++ lib.optional (config.system.activationScripts ? setupSecrets) "setupSecrets") ''
+        system.activationScripts."hermes-agent-setup" = lib.stringAfter [ "users" "setupSecrets" ] ''
          # Ensure directories exist (activation runs before tmpfiles)
          mkdir -p ${cfg.stateDir}/.hermes
          mkdir -p ${cfg.stateDir}/home
@@ -609,7 +601,7 @@
          # 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 ${cfg.group} -m 0640 /dev/null "$ENV_FILE"
+            install -o ${cfg.user} -g ${cfg.group} -m 0600 /dev/null "$ENV_FILE"
            cat > "$ENV_FILE" <<'HERMES_NIX_ENV_EOF'
 ${envFileContent}
 HERMES_NIX_ENV_EOF
@@ -14,7 +14,7 @@
      };

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

      runtimePath = pkgs.lib.makeBinPath runtimeDeps;
@@ -6,68 +6,14 @@
  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;
@@ -75,7 +21,6 @@ let
      (lib.composeManyExtensions [
        pyproject-build-systems.overlays.default
        overlay
-        pythonPackageOverrides
      ]);
 in
 pythonSet.mkVirtualEnv "hermes-agent-env" {
@@ -1803,34 +1803,30 @@ 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()
@@ -2458,15 +2454,6 @@ 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",
            "",
@@ -2488,14 +2475,7 @@ 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",
-        ])
-
-        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 cron` to recreate scheduled tasks (see archive/cron-config.json)",
            "- Run `hermes gateway install` if you need the gateway service",
            "- Review `~/.hermes/config.yaml` for any adjustments",
            "",
@@ -1,12 +1,11 @@
 # Hindsight Memory Provider

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

 ## Requirements

 - **Cloud:** API key from [ui.hindsight.vectorize.io](https://ui.hindsight.vectorize.io)
- **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.
+- **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.

 ## Setup

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

-### Cloud
+### Cloud Mode

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

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

-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.
+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.

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

 | Key | Default | Description |
 |-----|---------|-------------|
-| `mode` | `cloud` | `cloud`, `local_embedded`, or `local_external` |
-| `api_url` | `https://api.hindsight.vectorize.io` | API URL (cloud and local_external modes) |
+| `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) |

-### Memory Bank
+### Memory

 | Key | Default | Description |
 |-----|---------|-------------|
 | `bank_id` | `hermes` | Memory bank name |
-| `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 |
+| `budget` | `mid` | Recall thoroughness: `low` / `mid` / `high` |

 ### 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

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

 | Key | Default | Description |
 |-----|---------|-------------|
-| `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`) |
+| `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`) |

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

@@ -123,12 +92,7 @@ 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_embedded`, `local_external`) |
-
-## Client Version
-
-Requires `hindsight-client >= 0.4.22`. The plugin auto-upgrades on session start if an older version is detected.
+| `HINDSIGHT_MODE` | Override mode (`cloud` / `local`) |
@@ -23,30 +23,24 @@ 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",
 }


@@ -148,6 +142,7 @@ 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"
@@ -192,7 +187,6 @@ 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
@@ -200,31 +194,6 @@ 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:
@@ -234,7 +203,7 @@ class HindsightMemoryProvider(MemoryProvider):
        try:
            cfg = _load_config()
            mode = cfg.get("mode", "cloud")
-            if mode in ("local", "local_embedded", "local_external"):
+            if mode == "local":
                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", ""))
@@ -258,306 +227,68 @@ 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": "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": "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": "api_key", "description": "Hindsight Cloud API key", "secret": True, "env_var": "HINDSIGHT_API_KEY", "url": "https://ui.hindsight.vectorize.io", "when": {"mode": "cloud"}},
-            # 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": "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"}},
            {"key": "bank_id", "description": "Memory bank name", "default": "hermes"},
-            {"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": "budget", "description": "Recall thoroughness", "default": "mid", "choices": ["low", "mid", "high"]},
            {"key": "memory_mode", "description": "Memory integration mode", "default": "hybrid", "choices": ["hybrid", "context", "tools"]},
-            {"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"},
+            {"key": "prefetch_method", "description": "Auto-recall method", "default": "recall", "choices": ["recall", "reflect"]},
        ]

    def _get_client(self):
        """Return the cached Hindsight client (created once, reused)."""
        if self._client is None:
-            if self._mode == "local_embedded":
+            if self._mode == "local":
                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
-                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(
+                self._client = HindsightEmbedded(
                    profile=self._config.get("profile", "hermes"),
-                    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_provider=self._config.get("llm_provider", ""),
+                    llm_api_key=self._config.get("llmApiKey") 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")
-        # "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_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
        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("recall_budget") or self._config.get("budget") or banks.get("budget", "mid")
+        budget = 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("recall_prefetch_method", "recall")
+        prefetch_method = self._config.get("prefetch_method", "recall")
        self._prefetch_method = prefetch_method if prefetch_method in ("recall", "reflect") else "recall"

-        # 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)
+        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)

        # 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_embedded":
+        if self._mode == "local":
            def _start_daemon():
                import traceback
                log_dir = get_hermes_home() / "logs"
@@ -579,12 +310,9 @@ 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("llm_api_key") or os.environ.get("HINDSIGHT_LLM_API_KEY", "")
+                    current_key = self._config.get("llmApiKey") 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 = {}
@@ -595,24 +323,20 @@ class HindsightMemoryProvider(MemoryProvider):
                                saved[k.strip()] = v.strip()

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

                    if config_changed:
                        # Write updated profile .env
                        profile_env.parent.mkdir(parents=True, exist_ok=True)
-                        env_lines = (
-                            f"HINDSIGHT_API_LLM_PROVIDER={daemon_provider}\n"
+                        profile_env.write_text(
+                            f"HINDSIGHT_API_LLM_PROVIDER={current_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")
@@ -653,118 +377,47 @@ 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 ""
-        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}"
+        return f"## Hindsight Memory\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:
-                    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 ""
+                    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 ""
                if text:
                    with self._prefetch_lock:
                        self._prefetch_result = text
            except Exception as e:
-                logger.debug("Hindsight prefetch failed: %s", e, exc_info=True)
+                logger.debug("Hindsight prefetch failed: %s", e)

        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).
-
-        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) + "]"
+        """Retain conversation turn in background (non-blocking)."""
+        combined = f"User: {user_content}\nAssistant: {assistant_content}"

        def _sync():
            try:
                client = self._get_client()
-                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,
+                _run_sync(client.aretain(
+                    bank_id=self._bank_id, content=combined, context="conversation"
                ))
-                logger.debug("Hindsight retain succeeded")
            except Exception as e:
-                logger.warning("Hindsight sync failed: %s", e, exc_info=True)
+                logger.warning("Hindsight sync failed: %s", e)

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

        elif tool_name == "hindsight_recall":
@@ -808,26 +455,15 @@ class HindsightMemoryProvider(MemoryProvider):
            if not query:
                return tool_error("Missing required parameter: query")
            try:
-                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)
+                resp = _run_sync(client.arecall(
+                    bank_id=self._bank_id, query=query, budget=self._budget
+                ))
                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, exc_info=True)
+                logger.warning("hindsight_recall failed: %s", e)
                return tool_error(f"Failed to search memory: {e}")

        elif tool_name == "hindsight_reflect":
@@ -835,28 +471,24 @@ 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, exc_info=True)
+                logger.warning("hindsight_reflect failed: %s", e)
                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_embedded":
+                if self._mode == "local":
                    # Use the public close() API. The RuntimeError from
                    # aiohttp's "attached to a different loop" is expected
                    # and harmless — the daemon keeps running independently.
@@ -2,7 +2,9 @@ name: hindsight
 version: 1.0.0
 description: "Hindsight — long-term memory with knowledge graph, entity resolution, and multi-strategy retrieval."
 pip_dependencies:
-  - "hindsight-client>=0.4.22"
-requires_env: []
+  - hindsight-client
+  - hindsight-all
+requires_env:
+  - HINDSIGHT_API_KEY
 hooks:
  - on_session_end
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"

 [project]
 name = "hermes-agent"
-version = "0.8.0"
+version = "0.7.0"
 description = "The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere"
 readme = "README.md"
 requires-python = ">=3.11"
@@ -62,7 +62,6 @@ 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"]
 dingtalk = ["dingtalk-stream>=0.1.0,<1"]
 feishu = ["lark-oapi>=1.5.3,<2"]
 rl = [
@@ -95,7 +94,6 @@ all = [
  "hermes-agent[voice]",
  "hermes-agent[dingtalk]",
  "hermes-agent[feishu]",
-  "hermes-agent[mistral]",
 ]

 [project.scripts]
@@ -66,7 +66,7 @@ from model_tools import (
    handle_function_call,
    check_toolset_requirements,
 )
-from tools.terminal_tool import cleanup_vm, get_active_env, is_persistent_env
+from tools.terminal_tool import cleanup_vm, get_active_env
 from tools.tool_result_storage import maybe_persist_tool_result, enforce_turn_budget
 from tools.interrupt import set_interrupt as _set_interrupt
 from tools.browser_tool import cleanup_browser
@@ -76,8 +76,6 @@ from hermes_constants import OPENROUTER_BASE_URL

 # Agent internals extracted to agent/ package for modularity
 from agent.memory_manager import build_memory_context_block
-from agent.retry_utils import jittered_backoff
-from agent.error_classifier import classify_api_error, FailoverReason
 from agent.prompt_builder import (
    DEFAULT_AGENT_IDENTITY, PLATFORM_HINTS,
    MEMORY_GUIDANCE, SESSION_SEARCH_GUIDANCE, SKILLS_GUIDANCE,
@@ -87,9 +85,7 @@ from agent.model_metadata import (
    fetch_model_metadata,
    estimate_tokens_rough, estimate_messages_tokens_rough, estimate_request_tokens_rough,
    get_next_probe_tier, parse_context_limit_from_error,
-    parse_available_output_tokens_from_error,
    save_context_length, is_local_endpoint,
-    query_ollama_num_ctx,
 )
 from agent.context_compressor import ContextCompressor
 from agent.subdirectory_hints import SubdirectoryHintTracker
@@ -415,27 +411,6 @@ def _strip_budget_warnings_from_history(messages: list) -> None:
 # =========================================================================


-# =========================================================================
-# Qwen Portal headers — mimics QwenCode CLI for portal.qwen.ai compatibility.
-# Extracted as a module-level helper so both __init__ and
-# _apply_client_headers_for_base_url can share it.
-# =========================================================================
-_QWEN_CODE_VERSION = "0.14.1"
-
-
-def _qwen_portal_headers() -> dict:
-    """Return default HTTP headers required by Qwen Portal API."""
-    import platform as _plat
-
-    _ua = f"QwenCode/{_QWEN_CODE_VERSION} ({_plat.system().lower()}; {_plat.machine()})"
-    return {
-        "User-Agent": _ua,
-        "X-DashScope-CacheControl": "enable",
-        "X-DashScope-UserAgent": _ua,
-        "X-DashScope-AuthType": "qwen-oauth",
-    }
-
-
 class AIAgent:
    """
    AI Agent with tool calling capabilities.
@@ -444,13 +419,6 @@ class AIAgent:
    for AI models that support function calling.
    """

-    # ── Class-level context pressure dedup (survives across instances) ──
-    # The gateway creates a new AIAgent per message, so instance-level flags
-    # reset every time.  This dict tracks {session_id: (warn_level, timestamp)}
-    # to suppress duplicate warnings within a cooldown window.
-    _context_pressure_last_warned: dict = {}
-    _CONTEXT_PRESSURE_COOLDOWN = 300  # seconds between re-warning same session
-
    @property
    def base_url(self) -> str:
        return self._base_url
@@ -682,8 +650,7 @@ class AIAgent:
        # Context pressure warnings: notify the USER (not the LLM) as context
        # fills up.  Purely informational — displayed in CLI output and sent via
        # status_callback for gateway platforms.  Does NOT inject into messages.
-        # Tiered: fires at 85% and again at 95% of compaction threshold.
-        self._context_pressure_warned_at = 0.0  # highest tier already shown
+        self._context_pressure_warned = False

        # Activity tracking — updated on each API call, tool execution, and
        # stream chunk.  Used by the gateway timeout handler to report what the
@@ -694,10 +661,6 @@ class AIAgent:
        self._current_tool: str | None = None
        self._api_call_count: int = 0

-        # Rate limit tracking — updated from x-ratelimit-* response headers
-        # after each API call.  Accessed by /usage slash command.
-        self._rate_limit_state: Optional["RateLimitState"] = None
-
        # Centralized logging — agent.log (INFO+) and errors.log (WARNING+)
        # both live under ~/.hermes/logs/.  Idempotent, so gateway mode
        # (which creates a new AIAgent per message) won't duplicate handlers.
@@ -791,8 +754,6 @@ class AIAgent:
                    client_kwargs["default_headers"] = {
                        "User-Agent": "KimiCLI/1.3",
                    }
-                elif "portal.qwen.ai" in effective_base.lower():
-                    client_kwargs["default_headers"] = _qwen_portal_headers()
            else:
                # No explicit creds — use the centralized provider router
                from agent.auxiliary_client import resolve_provider_client
@@ -1199,33 +1160,6 @@ class AIAgent:
        self.session_cost_status = "unknown"
        self.session_cost_source = "none"
        
-        # ── Ollama num_ctx injection ──
-        # Ollama defaults to 2048 context regardless of the model's capabilities.
-        # When running against an Ollama server, detect the model's max context
-        # and pass num_ctx on every chat request so the full window is used.
-        # User override: set model.ollama_num_ctx in config.yaml to cap VRAM use.
-        self._ollama_num_ctx: int | None = None
-        _ollama_num_ctx_override = None
-        if isinstance(_model_cfg, dict):
-            _ollama_num_ctx_override = _model_cfg.get("ollama_num_ctx")
-        if _ollama_num_ctx_override is not None:
-            try:
-                self._ollama_num_ctx = int(_ollama_num_ctx_override)
-            except (TypeError, ValueError):
-                logger.debug("Invalid ollama_num_ctx config value: %r", _ollama_num_ctx_override)
-        if self._ollama_num_ctx is None and self.base_url and is_local_endpoint(self.base_url):
-            try:
-                _detected = query_ollama_num_ctx(self.model, self.base_url)
-                if _detected and _detected > 0:
-                    self._ollama_num_ctx = _detected
-            except Exception as exc:
-                logger.debug("Ollama num_ctx detection failed: %s", exc)
-        if self._ollama_num_ctx and not self.quiet_mode:
-            logger.info(
-                "Ollama num_ctx: will request %d tokens (model max from /api/show)",
-                self._ollama_num_ctx,
-            )
-
        if not self.quiet_mode:
            if compression_enabled:
                print(f"📊 Context limit: {self.context_compressor.context_length:,} tokens (compress at {int(compression_threshold*100)}% = {self.context_compressor.threshold_tokens:,})")
@@ -1701,25 +1635,9 @@ class AIAgent:
        return None

    def _cleanup_task_resources(self, task_id: str) -> None:
-        """Clean up VM and browser resources for a given task.
-
-        Skips ``cleanup_vm`` when the active terminal environment is marked
-        persistent (``persistent_filesystem=True``) so that long-lived sandbox
-        containers survive between turns. The idle reaper in
-        ``terminal_tool._cleanup_inactive_envs`` still tears them down once
-        ``terminal.lifetime_seconds`` is exceeded. Non-persistent backends are
-        torn down per-turn as before to prevent resource leakage (the original
-        intent of this hook for the Morph backend, see commit fbd3a2fd).
-        """
+        """Clean up VM and browser resources for a given task."""
        try:
-            if is_persistent_env(task_id):
-                if self.verbose_logging:
-                    logging.debug(
-                        f"Skipping per-turn cleanup_vm for persistent env {task_id}; "
-                        f"idle reaper will handle it."
-                    )
-            else:
-                cleanup_vm(task_id)
+            cleanup_vm(task_id)
        except Exception as e:
            if self.verbose_logging:
                logging.warning(f"Failed to cleanup VM for task {task_id}: {e}")
@@ -2551,29 +2469,6 @@ class AIAgent:
        self._last_activity_ts = time.time()
        self._last_activity_desc = desc

-    def _capture_rate_limits(self, http_response: Any) -> None:
-        """Parse x-ratelimit-* headers from an HTTP response and cache the state.
-
-        Called after each streaming API call.  The httpx Response object is
-        available on the OpenAI SDK Stream via ``stream.response``.
-        """
-        if http_response is None:
-            return
-        headers = getattr(http_response, "headers", None)
-        if not headers:
-            return
-        try:
-            from agent.rate_limit_tracker import parse_rate_limit_headers
-            state = parse_rate_limit_headers(headers, provider=self.provider)
-            if state is not None:
-                self._rate_limit_state = state
-        except Exception:
-            pass  # Never let header parsing break the agent loop
-
-    def get_rate_limit_state(self):
-        """Return the last captured RateLimitState, or None."""
-        return self._rate_limit_state
-
    def get_activity_summary(self) -> dict:
        """Return a snapshot of the agent's current activity for diagnostics.

@@ -4156,8 +4051,6 @@ class AIAgent:
            self._client_kwargs["default_headers"] = copilot_default_headers()
        elif "api.kimi.com" in normalized:
            self._client_kwargs["default_headers"] = {"User-Agent": "KimiCLI/1.3"}
-        elif "portal.qwen.ai" in normalized:
-            self._client_kwargs["default_headers"] = _qwen_portal_headers()
        else:
            self._client_kwargs.pop("default_headers", None)

@@ -4428,11 +4321,6 @@ class AIAgent:
            self._touch_activity("waiting for provider response (streaming)")
            stream = request_client_holder["client"].chat.completions.create(**stream_kwargs)

-            # Capture rate limit headers from the initial HTTP response.
-            # The OpenAI SDK Stream object exposes the underlying httpx
-            # response via .response before any chunks are consumed.
-            self._capture_rate_limits(getattr(stream, "response", None))
-
            content_parts: list = []
            tool_calls_acc: dict = {}
            tool_gen_notified: set = set()
@@ -4786,25 +4674,18 @@ class AIAgent:
                    self._close_request_openai_client(request_client, reason="stream_request_complete")

        _stream_stale_timeout_base = float(os.getenv("HERMES_STREAM_STALE_TIMEOUT", 180.0))
-        # Local providers (Ollama, oMLX, llama-cpp) can take 300+ seconds
-        # for prefill on large contexts.  Disable the stale detector unless
-        # the user explicitly set HERMES_STREAM_STALE_TIMEOUT.
-        if _stream_stale_timeout_base == 180.0 and self.base_url and is_local_endpoint(self.base_url):
-            _stream_stale_timeout = float("inf")
-            logger.debug("Local provider detected (%s) — stale stream timeout disabled", self.base_url)
+        # Scale the stale timeout for large contexts: slow models (like Opus)
+        # can legitimately think for minutes before producing the first token
+        # when the context is large.  Without this, the stale detector kills
+        # healthy connections during the model's thinking phase, producing
+        # spurious RemoteProtocolError ("peer closed connection").
+        _est_tokens = sum(len(str(v)) for v in api_kwargs.get("messages", [])) // 4
+        if _est_tokens > 100_000:
+            _stream_stale_timeout = max(_stream_stale_timeout_base, 300.0)
+        elif _est_tokens > 50_000:
+            _stream_stale_timeout = max(_stream_stale_timeout_base, 240.0)
        else:
-            # Scale the stale timeout for large contexts: slow models (like Opus)
-            # can legitimately think for minutes before producing the first token
-            # when the context is large.  Without this, the stale detector kills
-            # healthy connections during the model's thinking phase, producing
-            # spurious RemoteProtocolError ("peer closed connection").
-            _est_tokens = sum(len(str(v)) for v in api_kwargs.get("messages", [])) // 4
-            if _est_tokens > 100_000:
-                _stream_stale_timeout = max(_stream_stale_timeout_base, 300.0)
-            elif _est_tokens > 50_000:
-                _stream_stale_timeout = max(_stream_stale_timeout_base, 240.0)
-            else:
-                _stream_stale_timeout = _stream_stale_timeout_base
+            _stream_stale_timeout = _stream_stale_timeout_base

        t = threading.Thread(target=_call, daemon=True)
        t.start()
@@ -4960,7 +4841,7 @@ class AIAgent:
                effective_key = (fb_client.api_key or resolve_anthropic_token() or "") if fb_provider == "anthropic" else (fb_client.api_key or "")
                self.api_key = effective_key
                self._anthropic_api_key = effective_key
-                self._anthropic_base_url = fb_base_url
+                self._anthropic_base_url = getattr(fb_client, "base_url", None)
                self._anthropic_client = build_anthropic_client(effective_key, self._anthropic_base_url)
                self._is_anthropic_oauth = _is_oauth_token(effective_key)
                self.client = None
@@ -4969,21 +4850,9 @@ class AIAgent:
                # Swap OpenAI client and config in-place
                self.api_key = fb_client.api_key
                self.client = fb_client
-                # Preserve provider-specific headers that
-                # resolve_provider_client() may have baked into
-                # fb_client via the default_headers kwarg.  The OpenAI
-                # SDK stores these in _custom_headers.  Without this,
-                # subsequent request-client rebuilds (via
-                # _create_request_openai_client) drop the headers,
-                # causing 403s from providers like Kimi Coding that
-                # require a User-Agent sentinel.
-                fb_headers = getattr(fb_client, "_custom_headers", None)
-                if not fb_headers:
-                    fb_headers = getattr(fb_client, "default_headers", None)
                self._client_kwargs = {
                    "api_key": fb_client.api_key,
                    "base_url": fb_base_url,
-                    **({"default_headers": dict(fb_headers)} if fb_headers else {}),
                }

            # Re-evaluate prompt caching for the new provider/model
@@ -5328,97 +5197,24 @@ class AIAgent:
        base = (getattr(self, "base_url", "") or "").lower()
        return "dashscope" in base or "aliyuncs" in base or "opencode.ai/zen/go" in base

-    def _is_qwen_portal(self) -> bool:
-        """Return True when the base URL targets Qwen Portal."""
-        return "portal.qwen.ai" in self._base_url_lower
-
-    def _qwen_prepare_chat_messages(self, api_messages: list) -> list:
-        prepared = copy.deepcopy(api_messages)
-        if not prepared:
-            return prepared
-
-        for msg in prepared:
-            if not isinstance(msg, dict):
-                continue
-            content = msg.get("content")
-            if isinstance(content, str):
-                msg["content"] = [{"type": "text", "text": content}]
-            elif isinstance(content, list):
-                # Normalize: convert bare strings to text dicts, keep dicts as-is.
-                # deepcopy already created independent copies, no need for dict().
-                normalized_parts = []
-                for part in content:
-                    if isinstance(part, str):
-                        normalized_parts.append({"type": "text", "text": part})
-                    elif isinstance(part, dict):
-                        normalized_parts.append(part)
-                if normalized_parts:
-                    msg["content"] = normalized_parts
-
-        # Inject cache_control on the last part of the system message.
-        for msg in prepared:
-            if isinstance(msg, dict) and msg.get("role") == "system":
-                content = msg.get("content")
-                if isinstance(content, list) and content and isinstance(content[-1], dict):
-                    content[-1]["cache_control"] = {"type": "ephemeral"}
-                break
-
-        return prepared
-
-    def _qwen_prepare_chat_messages_inplace(self, messages: list) -> None:
-        """In-place variant — mutates an already-copied message list."""
-        if not messages:
-            return
-
-        for msg in messages:
-            if not isinstance(msg, dict):
-                continue
-            content = msg.get("content")
-            if isinstance(content, str):
-                msg["content"] = [{"type": "text", "text": content}]
-            elif isinstance(content, list):
-                normalized_parts = []
-                for part in content:
-                    if isinstance(part, str):
-                        normalized_parts.append({"type": "text", "text": part})
-                    elif isinstance(part, dict):
-                        normalized_parts.append(part)
-                if normalized_parts:
-                    msg["content"] = normalized_parts
-
-        for msg in messages:
-            if isinstance(msg, dict) and msg.get("role") == "system":
-                content = msg.get("content")
-                if isinstance(content, list) and content and isinstance(content[-1], dict):
-                    content[-1]["cache_control"] = {"type": "ephemeral"}
-                break
-
    def _build_api_kwargs(self, api_messages: list) -> dict:
        """Build the keyword arguments dict for the active API mode."""
        if self.api_mode == "anthropic_messages":
            from agent.anthropic_adapter import build_anthropic_kwargs
            anthropic_messages = self._prepare_anthropic_messages_for_api(api_messages)
-            # Pass context_length (total input+output window) so the adapter can
-            # clamp max_tokens (output cap) when the user configured a smaller
-            # context window than the model's native output limit.
+            # Pass context_length so the adapter can clamp max_tokens if the
+            # user configured a smaller context window than the model's output limit.
            ctx_len = getattr(self, "context_compressor", None)
            ctx_len = ctx_len.context_length if ctx_len else None
-            # _ephemeral_max_output_tokens is set for one call when the API
-            # returns "max_tokens too large given prompt" — it caps output to
-            # the available window space without touching context_length.
-            ephemeral_out = getattr(self, "_ephemeral_max_output_tokens", None)
-            if ephemeral_out is not None:
-                self._ephemeral_max_output_tokens = None  # consume immediately
            return build_anthropic_kwargs(
                model=self.model,
                messages=anthropic_messages,
                tools=self.tools,
-                max_tokens=ephemeral_out if ephemeral_out is not None else self.max_tokens,
+                max_tokens=self.max_tokens,
                reasoning_config=self.reasoning_config,
                is_oauth=self._is_anthropic_oauth,
                preserve_dots=self._anthropic_preserve_dots(),
                context_length=ctx_len,
-                base_url=getattr(self, "_anthropic_base_url", None),
            )

        if self.api_mode == "codex_responses":
@@ -5512,17 +5308,6 @@ class AIAgent:
                            tool_call.pop("call_id", None)
                            tool_call.pop("response_item_id", None)

-        # Qwen portal: normalize content to list-of-dicts, inject cache_control.
-        # Must run AFTER codex sanitization so we transform the final messages.
-        # If sanitization already deepcopied, reuse that copy (in-place).
-        if self._is_qwen_portal():
-            if sanitized_messages is api_messages:
-                # No sanitization was done — we need our own copy.
-                sanitized_messages = self._qwen_prepare_chat_messages(sanitized_messages)
-            else:
-                # Already a deepcopy — transform in place to avoid a second deepcopy.
-                self._qwen_prepare_chat_messages_inplace(sanitized_messages)
-
        # GPT-5 and Codex models respond better to 'developer' than 'system'
        # for instruction-following.  Swap the role at the API boundary so
        # internal message representation stays uniform ("system").
@@ -5555,17 +5340,11 @@ class AIAgent:
            "messages": sanitized_messages,
            "timeout": float(os.getenv("HERMES_API_TIMEOUT", 1800.0)),
        }
-        if self._is_qwen_portal():
-            api_kwargs["metadata"] = {
-                "sessionId": self.session_id or "hermes",
-                "promptId": str(uuid.uuid4()),
-            }
        if self.tools:
            api_kwargs["tools"] = self.tools

        if self.max_tokens is not None:
-            if not self._is_qwen_portal():
-                api_kwargs.update(self._max_tokens_param(self.max_tokens))
+            api_kwargs.update(self._max_tokens_param(self.max_tokens))
        elif self._is_openrouter_url() and "claude" in (self.model or "").lower():
            # OpenRouter translates requests to Anthropic's Messages API,
            # which requires max_tokens as a mandatory field.  When we omit
@@ -5621,18 +5400,6 @@ class AIAgent:
        if _is_nous:
            extra_body["tags"] = ["product=hermes-agent"]

-        # Ollama num_ctx: override the 2048 default so the model actually
-        # uses the context window it was trained for.  Passed via the OpenAI
-        # SDK's extra_body → options.num_ctx, which Ollama's OpenAI-compat
-        # endpoint forwards to the runner as --ctx-size.
-        if self._ollama_num_ctx:
-            options = extra_body.get("options", {})
-            options["num_ctx"] = self._ollama_num_ctx
-            extra_body["options"] = options
-
-        if self._is_qwen_portal():
-            extra_body["vl_high_resolution_images"] = True
-
        if extra_body:
            api_kwargs["extra_body"] = extra_body

@@ -5948,7 +5715,7 @@ class AIAgent:
                    tools=[memory_tool_def],
                    temperature=0.3,
                    max_tokens=5120,
-                    # timeout resolved from auxiliary.flush_memories.timeout config
+                    timeout=30.0,
                )
            except RuntimeError:
                _aux_available = False
@@ -5980,10 +5747,7 @@ class AIAgent:
                    "temperature": 0.3,
                    **self._max_tokens_param(5120),
                }
-                from agent.auxiliary_client import _get_task_timeout
-                response = self._ensure_primary_openai_client(reason="flush_memories").chat.completions.create(
-                    **api_kwargs, timeout=_get_task_timeout("flush_memories")
-                )
+                response = self._ensure_primary_openai_client(reason="flush_memories").chat.completions.create(**api_kwargs, timeout=30.0)

            # Extract tool calls from the response, handling all API formats
            tool_calls = []
@@ -6090,15 +5854,6 @@ class AIAgent:
            except Exception as e:
                logger.warning("Session DB compression split failed — new session will NOT be indexed: %s", e)

-        # Warn on repeated compressions (quality degrades with each pass)
-        _cc = self.context_compressor.compression_count
-        if _cc >= 2:
-            self._vprint(
-                f"{self.log_prefix}⚠️  Session compressed {_cc} times — "
-                f"accuracy may degrade. Consider /new to start fresh.",
-                force=True,
-            )
-
        # Update token estimate after compaction so pressure calculations
        # use the post-compression count, not the stale pre-compression one.
        _compressed_est = (
@@ -6111,16 +5866,12 @@ class AIAgent:
        # Only reset the pressure warning if compression actually brought
        # us below the warning level (85% of threshold).  When compression
        # can't reduce enough (e.g. threshold is very low, or system prompt
-        # alone exceeds the warning level), keep the tier set to prevent
+        # alone exceeds the warning level), keep the flag set to prevent
        # spamming the user with repeated warnings every loop iteration.
        if self.context_compressor.threshold_tokens > 0:
            _post_progress = _compressed_est / self.context_compressor.threshold_tokens
            if _post_progress < 0.85:
-                self._context_pressure_warned_at = 0.0
-                # Clear class-level dedup for this session so a fresh
-                # warning cycle can start if context grows again.
-                _sid = self.session_id or "default"
-                AIAgent._context_pressure_last_warned.pop(_sid, None)
+                self._context_pressure_warned = False

        # Clear the file-read dedup cache.  After compression the original
        # read content is summarised away — if the model re-reads the same
@@ -7302,7 +7053,6 @@ class AIAgent:
        length_continue_retries = 0
        truncated_response_prefix = ""
        compression_attempts = 0
-        _turn_exit_reason = "unknown"  # Diagnostic: why the loop ended
        
        # Clear any stale interrupt state at start
        self.clear_interrupt()
@@ -7327,7 +7077,6 @@ class AIAgent:
            # Check for interrupt request (e.g., user sent new message)
            if self._interrupt_requested:
                interrupted = True
-                _turn_exit_reason = "interrupted_by_user"
                if not self.quiet_mode:
                    self._safe_print("\n⚡ Breaking out of tool loop due to interrupt...")
                break
@@ -7336,7 +7085,6 @@ class AIAgent:
            self._api_call_count = api_call_count
            self._touch_activity(f"starting API call #{api_call_count}")
            if not self.iteration_budget.consume():
-                _turn_exit_reason = "budget_exhausted"
                if not self.quiet_mode:
                    self._safe_print(f"\n⚠️  Iteration budget exhausted ({self.iteration_budget.used}/{self.iteration_budget.max_total} iterations used)")
                break
@@ -7502,7 +7250,6 @@ class AIAgent:
            codex_auth_retry_attempted=False
            anthropic_auth_retry_attempted=False
            nous_auth_retry_attempted=False
-            thinking_sig_retry_attempted = False
            has_retried_429 = False
            restart_with_compressed_messages = False
            restart_with_length_continuation = False
@@ -7718,8 +7465,7 @@ class AIAgent:
                            }
                        
                        # Longer backoff for rate limiting (likely cause of None choices)
-                        # Jittered exponential: 5s base, 120s cap + random jitter
-                        wait_time = jittered_backoff(retry_count, base_delay=5.0, max_delay=120.0)
+                        wait_time = min(5 * (2 ** (retry_count - 1)), 120)  # 5s, 10s, 20s, 40s, 80s, 120s
                        self._vprint(f"{self.log_prefix}⏳ Retrying in {wait_time}s (extended backoff for possible rate limit)...", force=True)
                        logging.warning(f"Invalid API response (retry {retry_count}/{max_retries}): {', '.join(error_details)} | Provider: {provider_name}")
                        
@@ -8041,25 +7787,6 @@ class AIAgent:

                    status_code = getattr(api_error, "status_code", None)
                    error_context = self._extract_api_error_context(api_error)
-
-                    # ── Classify the error for structured recovery decisions ──
-                    _compressor = getattr(self, "context_compressor", None)
-                    _ctx_len = getattr(_compressor, "context_length", 200000) if _compressor else 200000
-                    classified = classify_api_error(
-                        api_error,
-                        provider=getattr(self, "provider", "") or "",
-                        model=getattr(self, "model", "") or "",
-                        approx_tokens=approx_tokens,
-                        context_length=_ctx_len,
-                        num_messages=len(api_messages) if api_messages else 0,
-                    )
-                    logger.debug(
-                        "Error classified: reason=%s status=%s retryable=%s compress=%s rotate=%s fallback=%s",
-                        classified.reason.value, classified.status_code,
-                        classified.retryable, classified.should_compress,
-                        classified.should_rotate_credential, classified.should_fallback,
-                    )
-
                    recovered_with_pool, has_retried_429 = self._recover_with_credential_pool(
                        status_code=status_code,
                        has_retried_429=has_retried_429,
@@ -8111,35 +7838,8 @@ class AIAgent:
                        print(f"{self.log_prefix}     • Check ANTHROPIC_API_KEY in {_dhh}/.env for API keys or legacy token values")
                        print(f"{self.log_prefix}     • For API keys: verify at https://console.anthropic.com/settings/keys")
                        print(f"{self.log_prefix}     • For Claude Code: run 'claude /login' to refresh, then retry")
-                        print(f"{self.log_prefix}     • Legacy cleanup: hermes config set ANTHROPIC_TOKEN \"\"")
-                        print(f"{self.log_prefix}     • Clear stale keys: hermes config set ANTHROPIC_API_KEY \"\"")
-
-                    # ── Thinking block signature recovery ─────────────────
-                    # Anthropic signs thinking blocks against the full turn
-                    # content.  Any upstream mutation (context compression,
-                    # session truncation, message merging) invalidates the
-                    # signature → HTTP 400.  Recovery: strip reasoning_details
-                    # from all messages so the next retry sends no thinking
-                    # blocks at all.  One-shot — don't retry infinitely.
-                    if (
-                        classified.reason == FailoverReason.thinking_signature
-                        and not thinking_sig_retry_attempted
-                    ):
-                        thinking_sig_retry_attempted = True
-                        for _m in messages:
-                            if isinstance(_m, dict):
-                                _m.pop("reasoning_details", None)
-                        self._vprint(
-                            f"{self.log_prefix}⚠️  Thinking block signature invalid — "
-                            f"stripped all thinking blocks, retrying...",
-                            force=True,
-                        )
-                        logging.warning(
-                            "%sThinking block signature recovery: stripped "
-                            "reasoning_details from %d messages",
-                            self.log_prefix, len(messages),
-                        )
-                        continue
+                        print(f"{self.log_prefix}     • Clear stale keys: hermes config set ANTHROPIC_TOKEN \"\"")
+                        print(f"{self.log_prefix}     • Legacy cleanup: hermes config set ANTHROPIC_API_KEY \"\"")

                    retry_count += 1
                    elapsed_time = time.time() - api_start_time
@@ -8196,7 +7896,14 @@ class AIAgent:
                    # is NOT a transient rate limit — retrying or switching
                    # credentials won't help.  Reduce context to 200k (the
                    # standard tier) and compress.
-                    if classified.reason == FailoverReason.long_context_tier:
+                    # Only applies to Sonnet — Opus 1M is general access.
+                    _is_long_context_tier_error = (
+                        status_code == 429
+                        and "extra usage" in error_msg
+                        and "long context" in error_msg
+                        and "sonnet" in self.model.lower()
+                    )
+                    if _is_long_context_tier_error:
                        _reduced_ctx = 200000
                        compressor = self.context_compressor
                        old_ctx = compressor.context_length
@@ -8241,9 +7948,13 @@ class AIAgent:
                    # When a fallback model is configured, switch immediately instead
                    # of burning through retries with exponential backoff -- the
                    # primary provider won't recover within the retry window.
-                    is_rate_limited = classified.reason in (
-                        FailoverReason.rate_limit,
-                        FailoverReason.billing,
+                    is_rate_limited = (
+                        status_code == 429
+                        or "rate limit" in error_msg
+                        or "too many requests" in error_msg
+                        or "rate_limit" in error_msg
+                        or "usage limit" in error_msg
+                        or "quota" in error_msg
                    )
                    if is_rate_limited and self._fallback_index < len(self._fallback_chain):
                        # Don't eagerly fallback if credential pool rotation may
@@ -8259,7 +7970,10 @@ class AIAgent:
                                continue

                    is_payload_too_large = (
-                        classified.reason == FailoverReason.payload_too_large
+                        status_code == 413
+                        or 'request entity too large' in error_msg
+                        or 'payload too large' in error_msg
+                        or 'error code: 413' in error_msg
                    )

                    if is_payload_too_large:
@@ -8303,59 +8017,69 @@ class AIAgent:
                            }

                    # Check for context-length errors BEFORE generic 4xx handler.
-                    # The classifier detects context overflow from: explicit error
-                    # messages, generic 400 + large session heuristic (#1630), and
-                    # server disconnect + large session pattern (#2153).
-                    is_context_length_error = (
-                        classified.reason == FailoverReason.context_overflow
-                    )
+                    # Local backends (LM Studio, Ollama, llama.cpp) often return
+                    # HTTP 400 with messages like "Context size has been exceeded"
+                    # which must trigger compression, not an immediate abort.
+                    is_context_length_error = any(phrase in error_msg for phrase in [
+                        'context length', 'context size', 'maximum context',
+                        'token limit', 'too many tokens', 'reduce the length',
+                        'exceeds the limit', 'context window',
+                        'request entity too large',  # OpenRouter/Nous 413 safety net
+                        'prompt is too long',  # Anthropic: "prompt is too long: N tokens > M maximum"
+                        'prompt exceeds max length',  # Z.AI / GLM: generic 400 overflow wording
+                    ])
+
+                    # Fallback heuristic: Anthropic sometimes returns a generic
+                    # 400 invalid_request_error with just "Error" as the message
+                    # when the context is too large.  If the error message is very
+                    # short/generic AND the session is large, treat it as a
+                    # probable context-length error and attempt compression rather
+                    # than aborting.  This prevents an infinite failure loop where
+                    # each failed message gets persisted, making the session even
+                    # larger. (#1630)
+                    if not is_context_length_error and status_code == 400:
+                        ctx_len = getattr(getattr(self, 'context_compressor', None), 'context_length', 200000)
+                        is_large_session = approx_tokens > ctx_len * 0.4 or len(api_messages) > 80
+                        is_generic_error = len(error_msg.strip()) < 30  # e.g. just "error"
+                        if is_large_session and is_generic_error:
+                            is_context_length_error = True
+                            self._vprint(
+                                f"{self.log_prefix}⚠️  Generic 400 with large session "
+                                f"(~{approx_tokens:,} tokens, {len(api_messages)} msgs) — "
+                                f"treating as probable context overflow.",
+                                force=True,
+                            )
+
+                    # Server disconnects on large sessions are often caused by
+                    # the request exceeding the provider's context/payload limit
+                    # without a proper HTTP error response.  Treat these as
+                    # context-length errors to trigger compression rather than
+                    # burning through retries that will all fail the same way.
+                    # This breaks the death spiral: disconnect → no token data
+                    # → no compression → bigger session → more disconnects.
+                    # (#2153)
+                    if not is_context_length_error and not status_code:
+                        _is_server_disconnect = (
+                            'server disconnected' in error_msg
+                            or 'peer closed connection' in error_msg
+                            or error_type in ('ReadError', 'RemoteProtocolError', 'ServerDisconnectedError')
+                        )
+                        if _is_server_disconnect:
+                            ctx_len = getattr(getattr(self, 'context_compressor', None), 'context_length', 200000)
+                            _is_large = approx_tokens > ctx_len * 0.6 or len(api_messages) > 200
+                            if _is_large:
+                                is_context_length_error = True
+                                self._vprint(
+                                    f"{self.log_prefix}⚠️  Server disconnected with large session "
+                                    f"(~{approx_tokens:,} tokens, {len(api_messages)} msgs) — "
+                                    f"treating as context-length error, attempting compression.",
+                                    force=True,
+                                )

                    if is_context_length_error:
                        compressor = self.context_compressor
                        old_ctx = compressor.context_length

-                        # ── Distinguish two very different errors ───────────
-                        # 1. "Prompt too long": the INPUT exceeds the context window.
-                        #    Fix: reduce context_length + compress history.
-                        # 2. "max_tokens too large": input is fine, but
-                        #    input_tokens + requested max_tokens > context_window.
-                        #    Fix: reduce max_tokens (the OUTPUT cap) for this call.
-                        #    Do NOT shrink context_length — the window is unchanged.
-                        #
-                        # Note: max_tokens = output token cap (one response).
-                        #       context_length = total window (input + output combined).
-                        available_out = parse_available_output_tokens_from_error(error_msg)
-                        if available_out is not None:
-                            # Error is purely about the output cap being too large.
-                            # Cap output to the available space and retry without
-                            # touching context_length or triggering compression.
-                            safe_out = max(1, available_out - 64)  # small safety margin
-                            self._ephemeral_max_output_tokens = safe_out
-                            self._vprint(
-                                f"{self.log_prefix}⚠️  Output cap too large for current prompt — "
-                                f"retrying with max_tokens={safe_out:,} "
-                                f"(available_tokens={available_out:,}; context_length unchanged at {old_ctx:,})",
-                                force=True,
-                            )
-                            # Still count against compression_attempts so we don't
-                            # loop forever if the error keeps recurring.
-                            compression_attempts += 1
-                            if compression_attempts > max_compression_attempts:
-                                self._vprint(f"{self.log_prefix}❌ Max compression attempts ({max_compression_attempts}) reached.", force=True)
-                                self._vprint(f"{self.log_prefix}   💡 Try /new to start a fresh conversation, or /compress to retry compression.", force=True)
-                                logging.error(f"{self.log_prefix}Context compression failed after {max_compression_attempts} attempts.")
-                                self._persist_session(messages, conversation_history)
-                                return {
-                                    "messages": messages,
-                                    "completed": False,
-                                    "api_calls": api_call_count,
-                                    "error": f"Context length exceeded: max compression attempts ({max_compression_attempts}) reached.",
-                                    "partial": True
-                                }
-                            restart_with_compressed_messages = True
-                            break
-
-                        # Error is about the INPUT being too large — reduce context_length.
                        # Try to parse the actual limit from the error message
                        parsed_limit = parse_context_limit_from_error(error_msg)
                        if parsed_limit and parsed_limit < old_ctx:
@@ -8422,30 +8146,35 @@ class AIAgent:
                                "partial": True
                            }

-                    # Check for non-retryable client errors.  The classifier
-                    # already accounts for 413, 429, 529 (transient), context
-                    # overflow, and generic-400 heuristics.  Local validation
-                    # errors (ValueError, TypeError) are programming bugs.
+                    # Check for non-retryable client errors (4xx HTTP status codes).
+                    # These indicate a problem with the request itself (bad model ID,
+                    # invalid API key, forbidden, etc.) and will never succeed on retry.
+                    # Note: 413 and context-length errors are excluded — handled above.
+                    # 429 (rate limit) is transient and MUST be retried with backoff.
+                    # 529 (Anthropic overloaded) is also transient.
+                    # Also catch local validation errors (ValueError, TypeError) — these
+                    # are programming bugs, not transient failures.
+                    # Exclude UnicodeEncodeError — it's a ValueError subclass but is
+                    # handled separately by the surrogate sanitization path above.
+                    _RETRYABLE_STATUS_CODES = {413, 429, 529}
                    is_local_validation_error = (
                        isinstance(api_error, (ValueError, TypeError))
                        and not isinstance(api_error, UnicodeEncodeError)
                    )
-                    is_client_error = (
-                        is_local_validation_error
-                        or (
-                            not classified.retryable
-                            and not classified.should_compress
-                            and classified.reason not in (
-                                FailoverReason.rate_limit,
-                                FailoverReason.billing,
-                                FailoverReason.overloaded,
-                                FailoverReason.context_overflow,
-                                FailoverReason.payload_too_large,
-                                FailoverReason.long_context_tier,
-                                FailoverReason.thinking_signature,
-                            )
-                        )
-                    ) and not is_context_length_error
+                    # Detect generic 400s from Anthropic OAuth (transient server-side failures).
+                    # Real invalid_request_error responses include a descriptive message;
+                    # transient ones contain only "Error" or are empty. (ref: issue #1608)
+                    _err_body = getattr(api_error, "body", None) or {}
+                    _err_message = (_err_body.get("error", {}).get("message", "") if isinstance(_err_body, dict) else "")
+                    _is_generic_400 = (status_code == 400 and _err_message.strip().lower() in ("error", ""))
+                    is_client_status_error = isinstance(status_code, int) and 400 <= status_code < 500 and status_code not in _RETRYABLE_STATUS_CODES and not _is_generic_400
+                    is_client_error = (is_local_validation_error or is_client_status_error or any(phrase in error_msg for phrase in [
+                        'error code: 401', 'error code: 403',
+                        'error code: 404', 'error code: 422',
+                        'is not a valid model', 'invalid model', 'model not found',
+                        'invalid api key', 'invalid_api_key', 'authentication',
+                        'unauthorized', 'forbidden', 'not found',
+                    ])) and not is_context_length_error

                    if is_client_error:
                        # Try fallback before aborting — a different provider
@@ -8465,7 +8194,7 @@ class AIAgent:
                        self._vprint(f"{self.log_prefix}   🔌 Provider: {_provider}  Model: {_model}", force=True)
                        self._vprint(f"{self.log_prefix}   🌐 Endpoint: {_base}", force=True)
                        # Actionable guidance for common auth errors
-                        if classified.is_auth or classified.reason == FailoverReason.billing:
+                        if status_code in (401, 403) or "unauthorized" in error_msg or "forbidden" in error_msg or "permission" in error_msg:
                            if _provider == "openai-codex" and status_code == 401:
                                self._vprint(f"{self.log_prefix}   💡 Codex OAuth token was rejected (HTTP 401). Your token may have been", force=True)
                                self._vprint(f"{self.log_prefix}      refreshed by another client (Codex CLI, VS Code). To fix:", force=True)
@@ -8593,7 +8322,7 @@ class AIAgent:
                                    _retry_after = min(int(_ra_raw), 120)  # Cap at 2 minutes
                                except (TypeError, ValueError):
                                    pass
-                    wait_time = _retry_after if _retry_after else jittered_backoff(retry_count, base_delay=2.0, max_delay=60.0)
+                    wait_time = _retry_after if _retry_after else min(2 ** retry_count, 60)
                    if is_rate_limited:
                        self._emit_status(f"⏱️ Rate limit reached. Waiting {wait_time}s before retry (attempt {retry_count + 1}/{max_retries})...")
                    else:
@@ -8625,7 +8354,6 @@ class AIAgent:
            
            # If the API call was interrupted, skip response processing
            if interrupted:
-                _turn_exit_reason = "interrupted_during_api_call"
                break

            if restart_with_compressed_messages:
@@ -8645,7 +8373,6 @@ class AIAgent:
            # (e.g. repeated context-length errors that exhausted retry_count),
            # the `response` variable is still None. Break out cleanly.
            if response is None:
-                _turn_exit_reason = "all_retries_exhausted_no_response"
                print(f"{self.log_prefix}❌ All API retries exhausted with no successful response.")
                self._persist_session(messages, conversation_history)
                break
@@ -9052,34 +8779,13 @@ class AIAgent:
                    # compaction fires, not the raw context window.
                    # Does not inject into messages — just prints to CLI output
                    # and fires status_callback for gateway platforms.
-                    # Tiered: 85% (orange) and 95% (red/critical).
                    if _compressor.threshold_tokens > 0:
                        _compaction_progress = _real_tokens / _compressor.threshold_tokens
-                        # Determine the warning tier for this progress level
-                        _warn_tier = 0.0
-                        if _compaction_progress >= 0.95:
-                            _warn_tier = 0.95
-                        elif _compaction_progress >= 0.85:
-                            _warn_tier = 0.85
-                        if _warn_tier > self._context_pressure_warned_at:
-                            # Class-level dedup: check if this session was already
-                            # warned at this tier within the cooldown window.
-                            _sid = self.session_id or "default"
-                            _last = AIAgent._context_pressure_last_warned.get(_sid)
-                            _now = time.time()
-                            if _last is None or _last[0] < _warn_tier or (_now - _last[1]) >= self._CONTEXT_PRESSURE_COOLDOWN:
-                                self._context_pressure_warned_at = _warn_tier
-                                AIAgent._context_pressure_last_warned[_sid] = (_warn_tier, _now)
-                                self._emit_context_pressure(_compaction_progress, _compressor)
-                                # Evict stale entries (older than 2x cooldown)
-                                _cutoff = _now - self._CONTEXT_PRESSURE_COOLDOWN * 2
-                                AIAgent._context_pressure_last_warned = {
-                                    k: v for k, v in AIAgent._context_pressure_last_warned.items()
-                                    if v[1] > _cutoff
-                                }
+                        if _compaction_progress >= 0.85 and not self._context_pressure_warned:
+                            self._context_pressure_warned = True
+                            self._emit_context_pressure(_compaction_progress, _compressor)

                    if self.compression_enabled and _compressor.should_compress(_real_tokens):
-                        self._safe_print("  ⟳ compacting context…")
                        messages, active_system_prompt = self._compress_context(
                            messages, system_message,
                            approx_tokens=self.context_compressor.last_prompt_tokens,
@@ -9109,7 +8815,6 @@ class AIAgent:
                        # instead of wasting API calls on retries that won't help.
                        fallback = getattr(self, '_last_content_with_tools', None)
                        if fallback:
-                            _turn_exit_reason = "fallback_prior_turn_content"
                            logger.debug("Empty follow-up after tool calls — using prior turn content as final response")
                            self._last_content_with_tools = None
                            self._empty_content_retries = 0
@@ -9155,28 +8860,8 @@ class AIAgent:
                            self._save_session_log(messages)
                            continue

-                        # ── Empty response retry (no reasoning) ──────
-                        # Model returned nothing — no content, no
-                        # structured reasoning, no tool calls.  Common
-                        # with open models (transient provider issues,
-                        # rate limits, sampling flukes).  Silently retry
-                        # up to 3 times before giving up.  Skip when
-                        # content has inline <think> tags (model chose
-                        # to reason, just no visible text).
-                        _truly_empty = not final_response.strip()
-                        if _truly_empty and not _has_structured and self._empty_content_retries < 3:
-                            self._empty_content_retries += 1
-                            self._vprint(
-                                f"{self.log_prefix}↻ Empty response (no content or reasoning) "
-                                f"— retrying ({self._empty_content_retries}/3)",
-                                force=True,
-                            )
-                            continue
-
-                        # Exhausted prefill attempts, empty retries, or
-                        # structured reasoning with no content —
-                        # fall through to "(empty)" terminal.
-                        _turn_exit_reason = "empty_response_exhausted"
+                        # Exhausted prefill attempts or no structured
+                        # reasoning — fall through to "(empty)" terminal.
                        reasoning_text = self._extract_reasoning(assistant_message)
                        assistant_msg = self._build_assistant_message(assistant_message, finish_reason)
                        assistant_msg["content"] = "(empty)"
@@ -9186,7 +8871,7 @@ class AIAgent:
                            reasoning_preview = reasoning_text[:500] + "..." if len(reasoning_text) > 500 else reasoning_text
                            self._vprint(f"{self.log_prefix}ℹ️  Reasoning-only response (no visible content). Reasoning: {reasoning_preview}")
                        else:
-                            self._vprint(f"{self.log_prefix}ℹ️  Empty response (no content or reasoning) after 3 retries.")
+                            self._vprint(f"{self.log_prefix}ℹ️  Empty response (no content or reasoning).")

                        final_response = "(empty)"
                        break
@@ -9248,7 +8933,6 @@ class AIAgent:

                    messages.append(final_msg)
                    
-                    _turn_exit_reason = f"text_response(finish_reason={finish_reason})"
                    if not self.quiet_mode:
                        self._safe_print(f"🎉 Conversation completed after {api_call_count} OpenAI-compatible API call(s)")
                    break
@@ -9298,7 +8982,6 @@ class AIAgent:

                # If we're near the limit, break to avoid infinite loops
                if api_call_count >= self.max_iterations - 1:
-                    _turn_exit_reason = f"error_near_max_iterations({error_msg[:80]})"
                    final_response = f"I apologize, but I encountered repeated errors: {error_msg}"
                    # Append as assistant so the history stays valid for
                    # session resume (avoids consecutive user messages).
@@ -9309,7 +8992,6 @@ class AIAgent:
            api_call_count >= self.max_iterations
            or self.iteration_budget.remaining <= 0
        ):
-            _turn_exit_reason = f"max_iterations_reached({api_call_count}/{self.max_iterations})"
            if self.iteration_budget.remaining <= 0 and not self.quiet_mode:
                print(f"\n⚠️  Iteration budget exhausted ({self.iteration_budget.used}/{self.iteration_budget.max_total} iterations used)")
            final_response = self._handle_max_iterations(messages, api_call_count)
@@ -9326,49 +9008,6 @@ class AIAgent:
        # Persist session to both JSON log and SQLite
        self._persist_session(messages, conversation_history)

-        # ── Turn-exit diagnostic log ─────────────────────────────────────
-        # Always logged at INFO so agent.log captures WHY every turn ended.
-        # When the last message is a tool result (agent was mid-work), log
-        # at WARNING — this is the "just stops" scenario users report.
-        _last_msg_role = messages[-1].get("role") if messages else None
-        _last_tool_name = None
-        if _last_msg_role == "tool":
-            # Walk back to find the assistant message with the tool call
-            for _m in reversed(messages):
-                if _m.get("role") == "assistant" and _m.get("tool_calls"):
-                    _tcs = _m["tool_calls"]
-                    if _tcs and isinstance(_tcs[0], dict):
-                        _last_tool_name = _tcs[-1].get("function", {}).get("name")
-                    break
-
-        _turn_tool_count = sum(
-            1 for m in messages
-            if isinstance(m, dict) and m.get("role") == "assistant" and m.get("tool_calls")
-        )
-        _resp_len = len(final_response) if final_response else 0
-        _budget_used = self.iteration_budget.used if self.iteration_budget else 0
-        _budget_max = self.iteration_budget.max_total if self.iteration_budget else 0
-
-        _diag_msg = (
-            "Turn ended: reason=%s model=%s api_calls=%d/%d budget=%d/%d "
-            "tool_turns=%d last_msg_role=%s response_len=%d session=%s"
-        )
-        _diag_args = (
-            _turn_exit_reason, self.model, api_call_count, self.max_iterations,
-            _budget_used, _budget_max,
-            _turn_tool_count, _last_msg_role, _resp_len,
-            self.session_id or "none",
-        )
-
-        if _last_msg_role == "tool" and not interrupted:
-            # Agent was mid-work — this is the "just stops" case.
-            logger.warning(
-                "Turn ended with pending tool result (agent may appear stuck). "
-                + _diag_msg + " last_tool=%s",
-                *_diag_args, _last_tool_name,
-            )
-        else:
-            logger.info(_diag_msg, *_diag_args)

        # Plugin hook: post_llm_call
        # Fired once per turn after the tool-calling loop completes.
@@ -249,6 +249,7 @@ Type these during an interactive chat session.
 /config              Show config (CLI)
 /model [name]        Show or change model
 /provider            Show provider info
+/prompt [text]       View/set system prompt (CLI)
 /personality [name]  Set personality
 /reasoning [level]   Set reasoning (none|low|medium|high|xhigh|show|hide)
 /verbose             Cycle: off → new → all → verbose
@@ -1276,258 +1276,6 @@ class TestRoleAlternation:
        assert [m["role"] for m in result] == ["user", "assistant", "user"]


-# ---------------------------------------------------------------------------
-# Thinking block signature management
-# ---------------------------------------------------------------------------
-
-
-class TestThinkingBlockSignatureManagement:
-    """Tests for the thinking block handling strategy:
-    strip from old turns, preserve latest signed, downgrade unsigned."""
-
-    def test_thinking_stripped_from_non_last_assistant(self):
-        """Thinking blocks are removed from all assistant messages except the last."""
-        messages = [
-            {
-                "role": "assistant",
-                "content": "",
-                "tool_calls": [
-                    {"id": "tc_1", "function": {"name": "tool1", "arguments": "{}"}},
-                ],
-                "reasoning_details": [
-                    {"type": "thinking", "thinking": "Old reasoning.", "signature": "sig_old"},
-                ],
-            },
-            {"role": "tool", "tool_call_id": "tc_1", "content": "result 1"},
-            {
-                "role": "assistant",
-                "content": "",
-                "tool_calls": [
-                    {"id": "tc_2", "function": {"name": "tool2", "arguments": "{}"}},
-                ],
-                "reasoning_details": [
-                    {"type": "thinking", "thinking": "Latest reasoning.", "signature": "sig_new"},
-                ],
-            },
-            {"role": "tool", "tool_call_id": "tc_2", "content": "result 2"},
-        ]
-        _, result = convert_messages_to_anthropic(messages)
-
-        # Find both assistant messages
-        assistants = [m for m in result if m["role"] == "assistant"]
-        assert len(assistants) == 2
-
-        # First (non-last) assistant: no thinking blocks
-        first_types = [b.get("type") for b in assistants[0]["content"]]
-        assert "thinking" not in first_types
-        assert "redacted_thinking" not in first_types
-        assert "tool_use" in first_types  # tool_use should survive
-
-        # Last assistant: thinking block preserved with signature
-        last_blocks = assistants[1]["content"]
-        thinking_blocks = [b for b in last_blocks if b.get("type") == "thinking"]
-        assert len(thinking_blocks) == 1
-        assert thinking_blocks[0]["thinking"] == "Latest reasoning."
-        assert thinking_blocks[0]["signature"] == "sig_new"
-
-    def test_signed_thinking_preserved_on_last_turn(self):
-        """A signed thinking block on the last assistant message is kept."""
-        messages = [
-            {
-                "role": "assistant",
-                "content": "The answer is 42.",
-                "reasoning_details": [
-                    {"type": "thinking", "thinking": "Deep thought.", "signature": "sig_valid"},
-                ],
-            },
-        ]
-        _, result = convert_messages_to_anthropic(messages)
-        blocks = result[0]["content"]
-        thinking = [b for b in blocks if b.get("type") == "thinking"]
-        assert len(thinking) == 1
-        assert thinking[0]["signature"] == "sig_valid"
-
-    def test_unsigned_thinking_downgraded_to_text_on_last_turn(self):
-        """Unsigned thinking blocks on the last turn become text blocks."""
-        messages = [
-            {
-                "role": "assistant",
-                "content": "Response text.",
-                "reasoning_details": [
-                    {"type": "thinking", "thinking": "Unsigned reasoning."},
-                    # No 'signature' field
-                ],
-            },
-        ]
-        _, result = convert_messages_to_anthropic(messages)
-        blocks = result[0]["content"]
-
-        # No thinking blocks should remain
-        assert not any(b.get("type") == "thinking" for b in blocks)
-        # The reasoning text should be preserved as a text block
-        text_contents = [b.get("text", "") for b in blocks if b.get("type") == "text"]
-        assert "Unsigned reasoning." in text_contents
-
-    def test_redacted_thinking_with_data_preserved(self):
-        """Redacted thinking with 'data' field is kept on last turn."""
-        messages = [
-            {
-                "role": "assistant",
-                "content": "Response.",
-                "reasoning_details": [
-                    {"type": "redacted_thinking", "data": "opaque_signature_data"},
-                ],
-            },
-        ]
-        _, result = convert_messages_to_anthropic(messages)
-        blocks = result[0]["content"]
-        redacted = [b for b in blocks if b.get("type") == "redacted_thinking"]
-        assert len(redacted) == 1
-        assert redacted[0]["data"] == "opaque_signature_data"
-
-    def test_redacted_thinking_without_data_dropped(self):
-        """Redacted thinking without 'data' is dropped — can't be validated."""
-        messages = [
-            {
-                "role": "assistant",
-                "content": "Response.",
-                "reasoning_details": [
-                    {"type": "redacted_thinking"},
-                    # No 'data' field
-                ],
-            },
-        ]
-        _, result = convert_messages_to_anthropic(messages)
-        blocks = result[0]["content"]
-        assert not any(b.get("type") == "redacted_thinking" for b in blocks)
-
-    def test_cache_control_stripped_from_thinking_blocks(self):
-        """cache_control markers are removed from thinking/redacted_thinking blocks."""
-        messages = [
-            {
-                "role": "assistant",
-                "content": "",
-                "tool_calls": [
-                    {"id": "tc_1", "function": {"name": "t", "arguments": "{}"}},
-                ],
-                "reasoning_details": [
-                    {
-                        "type": "thinking",
-                        "thinking": "Reasoning.",
-                        "signature": "sig_1",
-                        "cache_control": {"type": "ephemeral"},
-                    },
-                ],
-            },
-            {"role": "tool", "tool_call_id": "tc_1", "content": "result"},
-        ]
-        _, result = convert_messages_to_anthropic(messages)
-        assistant = next(m for m in result if m["role"] == "assistant")
-        for block in assistant["content"]:
-            if block.get("type") in ("thinking", "redacted_thinking"):
-                assert "cache_control" not in block
-
-    def test_thinking_stripped_from_merged_consecutive_assistants(self):
-        """When consecutive assistants are merged, second one's thinking is dropped."""
-        messages = [
-            {
-                "role": "assistant",
-                "content": "First response.",
-                "reasoning_details": [
-                    {"type": "thinking", "thinking": "First thought.", "signature": "sig_1"},
-                ],
-            },
-            {
-                "role": "assistant",
-                "content": "Second response.",
-                "reasoning_details": [
-                    {"type": "thinking", "thinking": "Second thought.", "signature": "sig_2"},
-                ],
-            },
-        ]
-        _, result = convert_messages_to_anthropic(messages)
-
-        # Should be merged into one assistant message
-        assistants = [m for m in result if m["role"] == "assistant"]
-        assert len(assistants) == 1
-
-        # Only the first thinking block should remain (signed, on the last/only assistant)
-        blocks = assistants[0]["content"]
-        thinking = [b for b in blocks if b.get("type") == "thinking"]
-        assert len(thinking) == 1
-        assert thinking[0]["thinking"] == "First thought."
-
-    def test_empty_content_after_strip_gets_placeholder(self):
-        """If stripping thinking leaves an empty message, a placeholder is added."""
-        messages = [
-            {
-                "role": "assistant",
-                "content": "",
-                "reasoning_details": [
-                    {"type": "thinking", "thinking": "Only thinking, no text."},
-                    # Unsigned — will be downgraded, but content was empty string
-                ],
-            },
-            {"role": "user", "content": "Next message."},
-            {"role": "assistant", "content": "Final."},
-        ]
-        _, result = convert_messages_to_anthropic(messages)
-        # First assistant is non-last, so thinking is stripped completely.
-        # The original content was empty and thinking was unsigned → placeholder
-        first_assistant = result[0]
-        assert first_assistant["role"] == "assistant"
-        assert len(first_assistant["content"]) >= 1
-
-    def test_multi_turn_conversation_preserves_only_last(self):
-        """Full multi-turn conversation: only last assistant keeps thinking."""
-        messages = [
-            {"role": "user", "content": "Question 1"},
-            {
-                "role": "assistant",
-                "content": "Answer 1",
-                "reasoning_details": [
-                    {"type": "thinking", "thinking": "Thought 1", "signature": "sig_1"},
-                ],
-            },
-            {"role": "user", "content": "Question 2"},
-            {
-                "role": "assistant",
-                "content": "Answer 2",
-                "reasoning_details": [
-                    {"type": "thinking", "thinking": "Thought 2", "signature": "sig_2"},
-                ],
-            },
-            {"role": "user", "content": "Question 3"},
-            {
-                "role": "assistant",
-                "content": "Answer 3",
-                "reasoning_details": [
-                    {"type": "thinking", "thinking": "Thought 3", "signature": "sig_3"},
-                ],
-            },
-        ]
-        _, result = convert_messages_to_anthropic(messages)
-
-        assistants = [m for m in result if m["role"] == "assistant"]
-        assert len(assistants) == 3
-
-        # First two: no thinking blocks
-        for a in assistants[:2]:
-            assert not any(
-                b.get("type") in ("thinking", "redacted_thinking")
-                for b in a["content"]
-                if isinstance(b, dict)
-            )
-
-        # Last one: thinking preserved
-        last_thinking = [
-            b for b in assistants[2]["content"]
-            if isinstance(b, dict) and b.get("type") == "thinking"
-        ]
-        assert len(last_thinking) == 1
-        assert last_thinking[0]["signature"] == "sig_3"
-
-
 # ---------------------------------------------------------------------------
 # Tool choice
 # ---------------------------------------------------------------------------
@@ -77,20 +77,6 @@ class TestReadCodexAccessToken:
        result = _read_codex_access_token()
        assert result == "tok-123"

-    def test_pool_without_selected_entry_falls_back_to_auth_store(self, tmp_path, monkeypatch):
-        hermes_home = tmp_path / "hermes"
-        hermes_home.mkdir(parents=True, exist_ok=True)
-        monkeypatch.setenv("HERMES_HOME", str(hermes_home))
-
-        valid_jwt = "eyJhbGciOiJSUzI1NiJ9.eyJleHAiOjk5OTk5OTk5OTl9.sig"
-        with patch("agent.auxiliary_client._select_pool_entry", return_value=(True, None)), \
-             patch("hermes_cli.auth._read_codex_tokens", return_value={
-                 "tokens": {"access_token": valid_jwt, "refresh_token": "refresh"}
-             }):
-            result = _read_codex_access_token()
-
-        assert result == valid_jwt
-
    def test_missing_returns_none(self, tmp_path, monkeypatch):
        hermes_home = tmp_path / "hermes"
        hermes_home.mkdir(parents=True, exist_ok=True)
@@ -252,24 +238,6 @@ class TestAnthropicOAuthFlag:
        assert mock_build.call_args.args[0] == "sk-ant-oat01-pooled"


-class TestTryCodex:
-    def test_pool_without_selected_entry_falls_back_to_auth_store(self):
-        with (
-            patch("agent.auxiliary_client._select_pool_entry", return_value=(True, None)),
-            patch("agent.auxiliary_client._read_codex_access_token", return_value="codex-auth-token"),
-            patch("agent.auxiliary_client.OpenAI") as mock_openai,
-        ):
-            mock_openai.return_value = MagicMock()
-            from agent.auxiliary_client import _try_codex
-
-            client, model = _try_codex()
-
-        assert client is not None
-        assert model == "gpt-5.2-codex"
-        assert mock_openai.call_args.kwargs["api_key"] == "codex-auth-token"
-        assert mock_openai.call_args.kwargs["base_url"] == "https://chatgpt.com/backend-api/codex"
-
-
 class TestExpiredCodexFallback:
    """Test that expired Codex tokens don't block the auto chain."""

@@ -503,23 +471,6 @@ class TestExplicitProviderRouting:
            client, model = resolve_provider_client("zai")
            assert client is not None

-    def test_explicit_google_alias_uses_gemini_credentials(self):
-        """provider='google' should route through the gemini API-key provider."""
-        with (
-            patch("hermes_cli.auth.resolve_api_key_provider_credentials", return_value={
-                "api_key": "gemini-key",
-                "base_url": "https://generativelanguage.googleapis.com/v1beta/openai",
-            }),
-            patch("agent.auxiliary_client.OpenAI") as mock_openai,
-        ):
-            mock_openai.return_value = MagicMock()
-            client, model = resolve_provider_client("google", model="gemini-3.1-pro-preview")
-
-        assert client is not None
-        assert model == "gemini-3.1-pro-preview"
-        assert mock_openai.call_args.kwargs["api_key"] == "gemini-key"
-        assert mock_openai.call_args.kwargs["base_url"] == "https://generativelanguage.googleapis.com/v1beta/openai"
-
    def test_explicit_unknown_returns_none(self, monkeypatch):
        """Unknown provider should return None."""
        client, model = resolve_provider_client("nonexistent-provider")
@@ -673,15 +624,12 @@ class TestVisionClientFallback:
        assert client is None
        assert model is None

-    def test_vision_auto_includes_active_provider_when_configured(self, monkeypatch):
-        """Active provider appears in available backends when credentials exist."""
-        monkeypatch.setenv("ANTHROPIC_API_KEY", "***")
+    def test_vision_auto_includes_anthropic_when_configured(self, monkeypatch):
+        monkeypatch.setenv("ANTHROPIC_API_KEY", "sk-ant-api03-key")
        with (
            patch("agent.auxiliary_client._read_nous_auth", return_value=None),
-            patch("agent.auxiliary_client._read_main_provider", return_value="anthropic"),
-            patch("agent.auxiliary_client._read_main_model", return_value="claude-sonnet-4"),
            patch("agent.anthropic_adapter.build_anthropic_client", return_value=MagicMock()),
-            patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="***"),
+            patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="sk-ant-api03-key"),
        ):
            backends = get_available_vision_backends()

@@ -754,51 +702,88 @@ class TestAuxiliaryPoolAwareness:
        assert call_kwargs["base_url"] == "https://api.githubcopilot.com"
        assert call_kwargs["default_headers"]["Editor-Version"]

-    def test_vision_auto_uses_active_provider_as_fallback(self, monkeypatch):
-        """When no OpenRouter/Nous available, vision auto falls back to active provider."""
-        monkeypatch.setenv("ANTHROPIC_API_KEY", "***")
+    def test_vision_auto_uses_anthropic_when_no_higher_priority_backend(self, monkeypatch):
+        monkeypatch.setenv("ANTHROPIC_API_KEY", "sk-ant-api03-key")
        with (
            patch("agent.auxiliary_client._read_nous_auth", return_value=None),
-            patch("agent.auxiliary_client._read_main_provider", return_value="anthropic"),
-            patch("agent.auxiliary_client._read_main_model", return_value="claude-sonnet-4"),
            patch("agent.anthropic_adapter.build_anthropic_client", return_value=MagicMock()),
-            patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="***"),
+            patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="sk-ant-api03-key"),
        ):
            client, model = get_vision_auxiliary_client()

        assert client is not None
        assert client.__class__.__name__ == "AnthropicAuxiliaryClient"
+        assert model == "claude-haiku-4-5-20251001"

-    def test_vision_auto_prefers_active_provider_over_openrouter(self, monkeypatch):
-        """Active provider is tried before OpenRouter in vision auto."""
+    def test_selected_anthropic_provider_is_preferred_for_vision_auto(self, monkeypatch):
        monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
-        monkeypatch.setenv("ANTHROPIC_API_KEY", "***")
+        monkeypatch.setenv("ANTHROPIC_API_KEY", "sk-ant-api03-key")
+
+        def fake_load_config():
+            return {"model": {"provider": "anthropic", "default": "claude-sonnet-4-6"}}

        with (
            patch("agent.auxiliary_client._read_nous_auth", return_value=None),
-            patch("agent.auxiliary_client._read_main_provider", return_value="anthropic"),
-            patch("agent.auxiliary_client._read_main_model", return_value="claude-sonnet-4"),
            patch("agent.anthropic_adapter.build_anthropic_client", return_value=MagicMock()),
-            patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="***"),
+            patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="sk-ant-api03-key"),
+            patch("agent.auxiliary_client.OpenAI") as mock_openai,
+            patch("hermes_cli.config.load_config", fake_load_config),
+        ):
+            client, model = get_vision_auxiliary_client()
+
+        assert client is not None
+        assert client.__class__.__name__ == "AnthropicAuxiliaryClient"
+        assert model == "claude-haiku-4-5-20251001"
+
+    def test_selected_codex_provider_short_circuits_vision_auto(self, monkeypatch):
+        def fake_load_config():
+            return {"model": {"provider": "openai-codex", "default": "gpt-5.2-codex"}}
+
+        codex_client = MagicMock()
+        with (
+            patch("hermes_cli.config.load_config", fake_load_config),
+            patch("agent.auxiliary_client._try_codex", return_value=(codex_client, "gpt-5.2-codex")) as mock_codex,
+            patch("agent.auxiliary_client._try_openrouter") as mock_openrouter,
+            patch("agent.auxiliary_client._try_nous") as mock_nous,
+            patch("agent.auxiliary_client._try_anthropic") as mock_anthropic,
+            patch("agent.auxiliary_client._try_custom_endpoint") as mock_custom,
        ):
            provider, client, model = resolve_vision_provider_client()

-        # Active provider should win over OpenRouter
-        assert provider == "anthropic"
+        assert provider == "openai-codex"
+        assert client is codex_client
+        assert model == "gpt-5.2-codex"
+        mock_codex.assert_called_once()
+        mock_openrouter.assert_not_called()
+        mock_nous.assert_not_called()
+        mock_anthropic.assert_not_called()
+        mock_custom.assert_not_called()

-    def test_vision_auto_uses_named_custom_as_active_provider(self, monkeypatch):
-        """Named custom provider works as active provider fallback in vision auto."""
+    def test_vision_auto_includes_codex(self, codex_auth_dir):
+        """Codex supports vision (gpt-5.3-codex), so auto mode should use it."""
+        with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
+             patch("agent.auxiliary_client.OpenAI"):
+            client, model = get_vision_auxiliary_client()
+        from agent.auxiliary_client import CodexAuxiliaryClient
+        assert isinstance(client, CodexAuxiliaryClient)
+        assert model == "gpt-5.2-codex"
+
+    def test_vision_auto_falls_back_to_custom_endpoint(self, monkeypatch):
+        """Custom endpoint is used as fallback in vision auto mode.
+
+        Many local models (Qwen-VL, LLaVA, etc.) support vision.
+        When no OpenRouter/Nous/Codex is available, try the custom endpoint.
+        """
        monkeypatch.delenv("OPENROUTER_API_KEY", raising=False)
        monkeypatch.delenv("ANTHROPIC_API_KEY", raising=False)
        with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
             patch("agent.auxiliary_client._select_pool_entry", return_value=(False, None)), \
-             patch("agent.auxiliary_client._read_main_provider", return_value="custom:local"), \
-             patch("agent.auxiliary_client._read_main_model", return_value="my-local-model"), \
-             patch("agent.auxiliary_client.resolve_provider_client",
-                   return_value=(MagicMock(), "my-local-model")) as mock_resolve:
-            provider, client, model = resolve_vision_provider_client()
-        assert client is not None
-        assert provider == "custom:local"
+             patch("agent.auxiliary_client._read_codex_access_token", return_value=None), \
+             patch("agent.auxiliary_client._resolve_custom_runtime",
+                   return_value=("http://localhost:1234/v1", "local-key")), \
+             patch("agent.auxiliary_client.OpenAI") as mock_openai:
+            client, model = get_vision_auxiliary_client()
+        assert client is not None  # Custom endpoint picked up as fallback

    def test_vision_direct_endpoint_override(self, monkeypatch):
        monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
@@ -837,31 +822,6 @@ class TestAuxiliaryPoolAwareness:
        assert model == "google/gemini-3-flash-preview"
        assert client is not None

-    def test_vision_config_google_provider_uses_gemini_credentials(self, monkeypatch):
-        config = {
-            "auxiliary": {
-                "vision": {
-                    "provider": "google",
-                    "model": "gemini-3.1-pro-preview",
-                }
-            }
-        }
-        monkeypatch.setattr("hermes_cli.config.load_config", lambda: config)
-        with (
-            patch("hermes_cli.auth.resolve_api_key_provider_credentials", return_value={
-                "api_key": "gemini-key",
-                "base_url": "https://generativelanguage.googleapis.com/v1beta/openai",
-            }),
-            patch("agent.auxiliary_client.OpenAI") as mock_openai,
-        ):
-            resolved_provider, client, model = resolve_vision_provider_client()
-
-        assert resolved_provider == "gemini"
-        assert client is not None
-        assert model == "gemini-3.1-pro-preview"
-        assert mock_openai.call_args.kwargs["api_key"] == "gemini-key"
-        assert mock_openai.call_args.kwargs["base_url"] == "https://generativelanguage.googleapis.com/v1beta/openai"
-
    def test_vision_forced_main_uses_custom_endpoint(self, monkeypatch):
        """When explicitly forced to 'main', vision CAN use custom endpoint."""
        config = {
@@ -886,14 +846,7 @@ class TestAuxiliaryPoolAwareness:
        monkeypatch.setenv("AUXILIARY_VISION_PROVIDER", "main")
        monkeypatch.delenv("OPENAI_BASE_URL", raising=False)
        monkeypatch.delenv("OPENAI_API_KEY", raising=False)
-        # Clear client cache to avoid stale entries from previous tests
-        from agent.auxiliary_client import _client_cache
-        _client_cache.clear()
        with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
-             patch("agent.auxiliary_client._read_main_provider", return_value=""), \
-             patch("agent.auxiliary_client._read_main_model", return_value=""), \
-             patch("agent.auxiliary_client._select_pool_entry", return_value=(False, None)), \
-             patch("agent.auxiliary_client._resolve_custom_runtime", return_value=(None, None)), \
             patch("agent.auxiliary_client._read_codex_access_token", return_value=None), \
             patch("agent.auxiliary_client._resolve_api_key_provider", return_value=(None, None)):
            client, model = get_vision_auxiliary_client()
@@ -324,10 +324,7 @@ class TestCompressWithClient:
        with patch("agent.context_compressor.get_model_context_length", return_value=100000):
            c = ContextCompressor(model="test", quiet_mode=True, protect_first_n=2, protect_last_n=2)

-        # Last head message (index 1) is "assistant" → summary should be "user".
-        # With min_tail=3, tail = last 3 messages (indices 5-7).
-        # head_last=assistant, tail_first=assistant → summary_role="user", no collision.
-        # Need 8 messages: min_for_compress = 2+3+1 = 6, must have > 6.
+        # Last head message (index 1) is "assistant" → summary should be "user"
        msgs = [
            {"role": "user", "content": "msg 0"},
            {"role": "assistant", "content": "msg 1"},
@@ -335,8 +332,6 @@ class TestCompressWithClient:
            {"role": "assistant", "content": "msg 3"},
            {"role": "user", "content": "msg 4"},
            {"role": "assistant", "content": "msg 5"},
-            {"role": "user", "content": "msg 6"},
-            {"role": "assistant", "content": "msg 7"},
        ]
        with patch("agent.context_compressor.call_llm", return_value=mock_response):
            result = c.compress(msgs)
@@ -465,10 +460,8 @@ class TestCompressWithClient:
            c = ContextCompressor(model="test", quiet_mode=True, protect_first_n=2, protect_last_n=2)

        # Head: [system, user]        → last head = user
-        # Tail: [assistant, user, assistant] → first tail = assistant
+        # Tail: [assistant, user]     → first tail = assistant
        # summary_role="assistant" collides with tail, "user" collides with head → merge
-        # With min_tail=3, tail = last 3 messages (indices 5-7).
-        # Need 8 messages: min_for_compress = 2+3+1 = 6, must have > 6.
        msgs = [
            {"role": "system", "content": "system prompt"},
            {"role": "user", "content": "msg 1"},
@@ -477,7 +470,6 @@ class TestCompressWithClient:
            {"role": "assistant", "content": "msg 4"},   # compressed
            {"role": "assistant", "content": "msg 5"},   # tail start
            {"role": "user", "content": "msg 6"},
-            {"role": "assistant", "content": "msg 7"},
        ]
        with patch("agent.context_compressor.call_llm", return_value=mock_response):
            result = c.compress(msgs)
@@ -489,7 +481,7 @@ class TestCompressWithClient:
            if r1 in ("user", "assistant") and r2 in ("user", "assistant"):
                assert r1 != r2, f"consecutive {r1} at indices {i-1},{i}"

-        # The summary should be merged into the first tail message (assistant at index 5)
+        # The summary should be merged into the first tail message (assistant)
        first_tail = [m for m in result if "msg 5" in (m.get("content") or "")]
        assert len(first_tail) == 1
        assert "summary text" in first_tail[0]["content"]
@@ -504,18 +496,14 @@ class TestCompressWithClient:
        with patch("agent.context_compressor.get_model_context_length", return_value=100000):
            c = ContextCompressor(model="test", quiet_mode=True, protect_first_n=2, protect_last_n=2)

-        # Head=assistant, Tail=assistant → summary_role="user", no collision.
-        # With min_tail=3, tail = last 3 messages (indices 5-7).
-        # Need 8 messages: min_for_compress = 2+3+1 = 6, must have > 6.
+        # Head=assistant, Tail=assistant → summary_role="user", no collision
        msgs = [
            {"role": "user", "content": "msg 0"},
            {"role": "assistant", "content": "msg 1"},
            {"role": "user", "content": "msg 2"},
            {"role": "assistant", "content": "msg 3"},
-            {"role": "user", "content": "msg 4"},
-            {"role": "assistant", "content": "msg 5"},
-            {"role": "user", "content": "msg 6"},
-            {"role": "assistant", "content": "msg 7"},
+            {"role": "assistant", "content": "msg 4"},
+            {"role": "user", "content": "msg 5"},
        ]
        with patch("agent.context_compressor.call_llm", return_value=mock_response):
            result = c.compress(msgs)
@@ -612,158 +600,3 @@ class TestSummaryTargetRatio:
        with patch("agent.context_compressor.get_model_context_length", return_value=100_000):
            c = ContextCompressor(model="test", quiet_mode=True)
        assert c.protect_last_n == 20
-
-
-class TestTokenBudgetTailProtection:
-    """Tests for token-budget-based tail protection (PR #6240).
-
-    The core change: tail protection is now based on a token budget rather
-    than a fixed message count.  This prevents large tool outputs from
-    blocking compaction.
-    """
-
-    @pytest.fixture()
-    def budget_compressor(self):
-        """Compressor with known token budget for tail protection tests."""
-        with patch("agent.context_compressor.get_model_context_length", return_value=200_000):
-            c = ContextCompressor(
-                model="test/model",
-                threshold_percent=0.50,  # 100K threshold
-                protect_first_n=2,
-                protect_last_n=20,
-                quiet_mode=True,
-            )
-            return c
-
-    def test_large_tool_outputs_no_longer_block_compaction(self, budget_compressor):
-        """The motivating scenario: 20 messages with large tool outputs should
-        NOT prevent compaction.  With message-count tail protection they would
-        all be protected, leaving nothing to summarize."""
-        c = budget_compressor
-        messages = [
-            {"role": "user", "content": "Start task"},
-            {"role": "assistant", "content": "On it"},
-        ]
-        # Add 20 messages with large tool outputs (~5K chars each ≈ 1250 tokens)
-        for i in range(10):
-            messages.append({
-                "role": "assistant", "content": None,
-                "tool_calls": [{"function": {"name": f"tool_{i}", "arguments": "{}"}}],
-            })
-            messages.append({
-                "role": "tool", "content": "x" * 5000,
-                "tool_call_id": f"call_{i}",
-            })
-        # Add 3 recent small messages
-        messages.append({"role": "user", "content": "What's the status?"})
-        messages.append({"role": "assistant", "content": "Here's what I found..."})
-        messages.append({"role": "user", "content": "Continue"})
-
-        # The tail cut should NOT protect all 20 tool messages
-        head_end = c.protect_first_n
-        cut = c._find_tail_cut_by_tokens(messages, head_end)
-        tail_size = len(messages) - cut
-        # With token budget, the tail should be much smaller than 20+
-        assert tail_size < 20, f"Tail {tail_size} messages — large tool outputs are blocking compaction"
-        # But at least 3 (hard minimum)
-        assert tail_size >= 3
-
-    def test_min_tail_always_3_messages(self, budget_compressor):
-        """Even with a tiny token budget, at least 3 messages are protected."""
-        c = budget_compressor
-        # Override to a tiny budget
-        c.tail_token_budget = 10
-        messages = [
-            {"role": "user", "content": "hello"},
-            {"role": "assistant", "content": "hi"},
-            {"role": "user", "content": "do something"},
-            {"role": "assistant", "content": "working on it"},
-            {"role": "user", "content": "more work"},
-            {"role": "assistant", "content": "done"},
-            {"role": "user", "content": "thanks"},
-        ]
-        head_end = 2
-        cut = c._find_tail_cut_by_tokens(messages, head_end)
-        tail_size = len(messages) - cut
-        assert tail_size >= 3, f"Tail is only {tail_size} messages, min should be 3"
-
-    def test_soft_ceiling_allows_oversized_message(self, budget_compressor):
-        """The 1.5x soft ceiling allows an oversized message to be included
-        rather than splitting it."""
-        c = budget_compressor
-        # Set a small budget — 500 tokens
-        c.tail_token_budget = 500
-        messages = [
-            {"role": "user", "content": "hello"},
-            {"role": "assistant", "content": "hi"},
-            {"role": "user", "content": "read the file"},
-            # This message is ~600 tokens (> budget of 500, but < 1.5x = 750)
-            {"role": "assistant", "content": "a" * 2400},
-            {"role": "user", "content": "short"},
-            {"role": "assistant", "content": "short reply"},
-            {"role": "user", "content": "continue"},
-        ]
-        head_end = 2
-        cut = c._find_tail_cut_by_tokens(messages, head_end)
-        # The oversized message at index 3 should NOT be the cut point
-        # because 1.5x ceiling = 750 tokens and accumulated would be ~610
-        # (short msgs + oversized msg) which is < 750
-        tail_size = len(messages) - cut
-        assert tail_size >= 3
-
-    def test_small_conversation_still_compresses(self, budget_compressor):
-        """With the new min of 8 messages (head=2 + 3 + 1 guard + 2 middle),
-        a small but compressible conversation should still compress."""
-        c = budget_compressor
-        # 9 messages: head(2) + 4 middle + 3 tail = compressible
-        messages = []
-        for i in range(9):
-            role = "user" if i % 2 == 0 else "assistant"
-            messages.append({"role": role, "content": f"Message {i}"})
-
-        # Should not early-return (needs > protect_first_n + 3 + 1 = 6)
-        # Mock the summary generation to avoid real API call
-        with patch.object(c, "_generate_summary", return_value="Summary of conversation"):
-            result = c.compress(messages, current_tokens=90_000)
-        # Should have compressed (fewer messages than original)
-        assert len(result) < len(messages)
-
-    def test_prune_with_token_budget(self, budget_compressor):
-        """_prune_old_tool_results with protect_tail_tokens respects the budget."""
-        c = budget_compressor
-        messages = [
-            {"role": "user", "content": "start"},
-            {"role": "assistant", "content": None,
-             "tool_calls": [{"function": {"name": "read_file", "arguments": '{"path": "big.txt"}'}}]},
-            {"role": "tool", "content": "x" * 10000, "tool_call_id": "c1"},  # ~2500 tokens
-            {"role": "assistant", "content": None,
-             "tool_calls": [{"function": {"name": "read_file", "arguments": '{"path": "small.txt"}'}}]},
-            {"role": "tool", "content": "y" * 10000, "tool_call_id": "c2"},  # ~2500 tokens
-            {"role": "user", "content": "short recent message"},
-            {"role": "assistant", "content": "short reply"},
-        ]
-        # With a 1000-token budget, only the last couple messages should be protected
-        result, pruned = c._prune_old_tool_results(
-            messages, protect_tail_count=2, protect_tail_tokens=1000,
-        )
-        # At least one old tool result should have been pruned
-        assert pruned >= 1
-
-    def test_prune_without_token_budget_uses_message_count(self, budget_compressor):
-        """Without protect_tail_tokens, falls back to message-count behavior."""
-        c = budget_compressor
-        messages = [
-            {"role": "user", "content": "start"},
-            {"role": "assistant", "content": None,
-             "tool_calls": [{"function": {"name": "tool", "arguments": "{}"}}]},
-            {"role": "tool", "content": "x" * 5000, "tool_call_id": "c1"},
-            {"role": "user", "content": "recent"},
-            {"role": "assistant", "content": "reply"},
-        ]
-        # protect_tail_count=3 means last 3 messages protected
-        result, pruned = c._prune_old_tool_results(
-            messages, protect_tail_count=3,
-        )
-        # Tool at index 2 is outside the protected tail (last 3 = indices 2,3,4)
-        # so it might or might not be pruned depending on boundary
-        assert isinstance(pruned, int)
@@ -214,42 +214,6 @@ def test_exhausted_entry_resets_after_ttl(tmp_path, monkeypatch):
    assert entry.last_status == "ok"


-def test_exhausted_402_entry_resets_after_one_hour(tmp_path, monkeypatch):
-    """402-exhausted credentials recover after 1 hour, not 24."""
-    monkeypatch.setenv("HERMES_HOME", str(tmp_path / "hermes"))
-    _write_auth_store(
-        tmp_path,
-        {
-            "version": 1,
-            "credential_pool": {
-                "openrouter": [
-                    {
-                        "id": "cred-1",
-                        "label": "primary",
-                        "auth_type": "api_key",
-                        "priority": 0,
-                        "source": "manual",
-                        "access_token": "***",
-                        "base_url": "https://openrouter.ai/api/v1",
-                        "last_status": "exhausted",
-                        "last_status_at": time.time() - 3700,  # ~1h2m ago
-                        "last_error_code": 402,
-                    }
-                ]
-            },
-        },
-    )
-
-    from agent.credential_pool import load_pool
-
-    pool = load_pool("openrouter")
-    entry = pool.select()
-
-    assert entry is not None
-    assert entry.id == "cred-1"
-    assert entry.last_status == "ok"
-
-
 def test_explicit_reset_timestamp_overrides_default_429_ttl(tmp_path, monkeypatch):
    monkeypatch.setenv("HERMES_HOME", str(tmp_path / "hermes"))
    _write_auth_store(
@@ -1,782 +0,0 @@
-"""Tests for agent.error_classifier — structured API error classification."""
-
-import pytest
-from agent.error_classifier import (
-    ClassifiedError,
-    FailoverReason,
-    classify_api_error,
-    _extract_status_code,
-    _extract_error_body,
-    _extract_error_code,
-    _classify_402,
-)
-
-
-# ── Helper: mock API errors ────────────────────────────────────────────
-
-class MockAPIError(Exception):
-    """Simulates an OpenAI SDK APIStatusError."""
-    def __init__(self, message, status_code=None, body=None):
-        super().__init__(message)
-        self.status_code = status_code
-        self.body = body or {}
-
-
-class MockTransportError(Exception):
-    """Simulates a transport-level error with a specific type name."""
-    pass
-
-
-class ReadTimeout(MockTransportError):
-    pass
-
-
-class ConnectError(MockTransportError):
-    pass
-
-
-class RemoteProtocolError(MockTransportError):
-    pass
-
-
-class ServerDisconnectedError(MockTransportError):
-    pass
-
-
-# ── Test: FailoverReason enum ──────────────────────────────────────────
-
-class TestFailoverReason:
-    def test_all_reasons_have_string_values(self):
-        for reason in FailoverReason:
-            assert isinstance(reason.value, str)
-
-    def test_enum_members_exist(self):
-        expected = {
-            "auth", "auth_permanent", "billing", "rate_limit",
-            "overloaded", "server_error", "timeout",
-            "context_overflow", "payload_too_large",
-            "model_not_found", "format_error",
-            "thinking_signature", "long_context_tier", "unknown",
-        }
-        actual = {r.value for r in FailoverReason}
-        assert expected == actual
-
-
-# ── Test: ClassifiedError ──────────────────────────────────────────────
-
-class TestClassifiedError:
-    def test_is_auth_property(self):
-        e1 = ClassifiedError(reason=FailoverReason.auth)
-        assert e1.is_auth is True
-
-        e2 = ClassifiedError(reason=FailoverReason.auth_permanent)
-        assert e2.is_auth is True
-
-        e3 = ClassifiedError(reason=FailoverReason.billing)
-        assert e3.is_auth is False
-
-    def test_is_transient_property(self):
-        transient_reasons = [
-            FailoverReason.rate_limit,
-            FailoverReason.overloaded,
-            FailoverReason.server_error,
-            FailoverReason.timeout,
-            FailoverReason.unknown,
-        ]
-        for reason in transient_reasons:
-            e = ClassifiedError(reason=reason)
-            assert e.is_transient is True, f"{reason} should be transient"
-
-        non_transient = [
-            FailoverReason.auth,
-            FailoverReason.billing,
-            FailoverReason.model_not_found,
-            FailoverReason.format_error,
-        ]
-        for reason in non_transient:
-            e = ClassifiedError(reason=reason)
-            assert e.is_transient is False, f"{reason} should NOT be transient"
-
-    def test_defaults(self):
-        e = ClassifiedError(reason=FailoverReason.unknown)
-        assert e.retryable is True
-        assert e.should_compress is False
-        assert e.should_rotate_credential is False
-        assert e.should_fallback is False
-        assert e.status_code is None
-        assert e.message == ""
-
-
-# ── Test: Status code extraction ───────────────────────────────────────
-
-class TestExtractStatusCode:
-    def test_from_status_code_attr(self):
-        e = MockAPIError("fail", status_code=429)
-        assert _extract_status_code(e) == 429
-
-    def test_from_status_attr(self):
-        class ErrWithStatus(Exception):
-            status = 503
-        assert _extract_status_code(ErrWithStatus()) == 503
-
-    def test_from_cause_chain(self):
-        inner = MockAPIError("inner", status_code=401)
-        outer = Exception("outer")
-        outer.__cause__ = inner
-        assert _extract_status_code(outer) == 401
-
-    def test_none_when_missing(self):
-        assert _extract_status_code(Exception("generic")) is None
-
-    def test_rejects_non_http_status(self):
-        """Integers outside 100-599 on .status should be ignored."""
-        class ErrWeirdStatus(Exception):
-            status = 42
-        assert _extract_status_code(ErrWeirdStatus()) is None
-
-
-# ── Test: Error body extraction ────────────────────────────────────────
-
-class TestExtractErrorBody:
-    def test_from_body_attr(self):
-        e = MockAPIError("fail", body={"error": {"message": "bad"}})
-        assert _extract_error_body(e) == {"error": {"message": "bad"}}
-
-    def test_empty_when_no_body(self):
-        assert _extract_error_body(Exception("generic")) == {}
-
-
-# ── Test: Error code extraction ────────────────────────────────────────
-
-class TestExtractErrorCode:
-    def test_from_nested_error_code(self):
-        body = {"error": {"code": "rate_limit_exceeded"}}
-        assert _extract_error_code(body) == "rate_limit_exceeded"
-
-    def test_from_nested_error_type(self):
-        body = {"error": {"type": "invalid_request_error"}}
-        assert _extract_error_code(body) == "invalid_request_error"
-
-    def test_from_top_level_code(self):
-        body = {"code": "model_not_found"}
-        assert _extract_error_code(body) == "model_not_found"
-
-    def test_empty_when_no_code(self):
-        assert _extract_error_code({}) == ""
-        assert _extract_error_code({"error": {"message": "oops"}}) == ""
-
-
-# ── Test: 402 disambiguation ───────────────────────────────────────────
-
-class TestClassify402:
-    """The critical 402 billing vs rate_limit disambiguation."""
-
-    def test_billing_exhaustion(self):
-        """Plain 402 = billing."""
-        result = _classify_402(
-            "payment required",
-            lambda reason, **kw: ClassifiedError(reason=reason, **kw),
-        )
-        assert result.reason == FailoverReason.billing
-        assert result.should_rotate_credential is True
-
-    def test_transient_usage_limit(self):
-        """402 with 'usage limit' + 'try again' = rate limit, not billing."""
-        result = _classify_402(
-            "usage limit exceeded. try again in 5 minutes",
-            lambda reason, **kw: ClassifiedError(reason=reason, **kw),
-        )
-        assert result.reason == FailoverReason.rate_limit
-        assert result.should_rotate_credential is True
-
-    def test_quota_with_retry(self):
-        """402 with 'quota' + 'retry' = rate limit."""
-        result = _classify_402(
-            "quota exceeded, please retry after the window resets",
-            lambda reason, **kw: ClassifiedError(reason=reason, **kw),
-        )
-        assert result.reason == FailoverReason.rate_limit
-
-    def test_quota_without_retry(self):
-        """402 with just 'quota' but no transient signal = billing."""
-        result = _classify_402(
-            "quota exceeded",
-            lambda reason, **kw: ClassifiedError(reason=reason, **kw),
-        )
-        assert result.reason == FailoverReason.billing
-
-    def test_insufficient_credits(self):
-        result = _classify_402(
-            "insufficient credits to complete request",
-            lambda reason, **kw: ClassifiedError(reason=reason, **kw),
-        )
-        assert result.reason == FailoverReason.billing
-
-
-# ── Test: Full classification pipeline ─────────────────────────────────
-
-class TestClassifyApiError:
-    """End-to-end classification tests."""
-
-    # ── Auth errors ──
-
-    def test_401_classified_as_auth(self):
-        e = MockAPIError("Unauthorized", status_code=401)
-        result = classify_api_error(e, provider="openrouter")
-        assert result.reason == FailoverReason.auth
-        assert result.should_rotate_credential is True
-        # 401 is non-retryable on its own — credential rotation runs
-        # before the retryability check in the agent loop.
-        assert result.retryable is False
-        assert result.should_fallback is True
-
-    def test_403_classified_as_auth(self):
-        e = MockAPIError("Forbidden", status_code=403)
-        result = classify_api_error(e, provider="anthropic")
-        assert result.reason == FailoverReason.auth
-        assert result.should_fallback is True
-
-    def test_403_key_limit_classified_as_billing(self):
-        """OpenRouter 403 'key limit exceeded' is billing, not auth."""
-        e = MockAPIError("Key limit exceeded for this key", status_code=403)
-        result = classify_api_error(e, provider="openrouter")
-        assert result.reason == FailoverReason.billing
-        assert result.should_rotate_credential is True
-        assert result.should_fallback is True
-
-    def test_403_spending_limit_classified_as_billing(self):
-        e = MockAPIError("spending limit reached", status_code=403)
-        result = classify_api_error(e, provider="openrouter")
-        assert result.reason == FailoverReason.billing
-
-    # ── Billing ──
-
-    def test_402_plain_billing(self):
-        e = MockAPIError("Payment Required", status_code=402)
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.billing
-        assert result.retryable is False
-
-    def test_402_transient_usage_limit(self):
-        e = MockAPIError("usage limit exceeded, try again later", status_code=402)
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.rate_limit
-        assert result.retryable is True
-
-    # ── Rate limit ──
-
-    def test_429_rate_limit(self):
-        e = MockAPIError("Too Many Requests", status_code=429)
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.rate_limit
-        assert result.should_fallback is True
-
-    # ── Server errors ──
-
-    def test_500_server_error(self):
-        e = MockAPIError("Internal Server Error", status_code=500)
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.server_error
-        assert result.retryable is True
-
-    def test_502_server_error(self):
-        e = MockAPIError("Bad Gateway", status_code=502)
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.server_error
-
-    def test_503_overloaded(self):
-        e = MockAPIError("Service Unavailable", status_code=503)
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.overloaded
-
-    def test_529_anthropic_overloaded(self):
-        e = MockAPIError("Overloaded", status_code=529)
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.overloaded
-
-    # ── Model not found ──
-
-    def test_404_model_not_found(self):
-        e = MockAPIError("model not found", status_code=404)
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.model_not_found
-        assert result.should_fallback is True
-        assert result.retryable is False
-
-    def test_404_generic(self):
-        e = MockAPIError("Not Found", status_code=404)
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.model_not_found
-
-    # ── Payload too large ──
-
-    def test_413_payload_too_large(self):
-        e = MockAPIError("Request Entity Too Large", status_code=413)
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.payload_too_large
-        assert result.should_compress is True
-
-    # ── Context overflow ──
-
-    def test_400_context_length(self):
-        e = MockAPIError("context length exceeded: 250000 > 200000", status_code=400)
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.context_overflow
-        assert result.should_compress is True
-
-    def test_400_too_many_tokens(self):
-        e = MockAPIError("This model's maximum context is 128000 tokens, too many tokens", status_code=400)
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.context_overflow
-
-    def test_400_prompt_too_long(self):
-        e = MockAPIError("prompt is too long: 300000 tokens > 200000 maximum", status_code=400)
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.context_overflow
-
-    def test_400_generic_large_session(self):
-        """Generic 400 with large session → context overflow heuristic."""
-        e = MockAPIError(
-            "Error",
-            status_code=400,
-            body={"error": {"message": "Error"}},
-        )
-        result = classify_api_error(e, approx_tokens=100000, context_length=200000)
-        assert result.reason == FailoverReason.context_overflow
-
-    def test_400_generic_small_session_is_format_error(self):
-        """Generic 400 with small session → format error, not context overflow."""
-        e = MockAPIError(
-            "Error",
-            status_code=400,
-            body={"error": {"message": "Error"}},
-        )
-        result = classify_api_error(e, approx_tokens=1000, context_length=200000)
-        assert result.reason == FailoverReason.format_error
-
-    # ── Server disconnect + large session ──
-
-    def test_disconnect_large_session_context_overflow(self):
-        """Server disconnect with large session → context overflow."""
-        e = Exception("server disconnected without sending complete message")
-        result = classify_api_error(e, approx_tokens=150000, context_length=200000)
-        assert result.reason == FailoverReason.context_overflow
-        assert result.should_compress is True
-
-    def test_disconnect_small_session_timeout(self):
-        """Server disconnect with small session → timeout."""
-        e = Exception("server disconnected without sending complete message")
-        result = classify_api_error(e, approx_tokens=5000, context_length=200000)
-        assert result.reason == FailoverReason.timeout
-
-    # ── Provider-specific: Anthropic thinking signature ──
-
-    def test_anthropic_thinking_signature(self):
-        e = MockAPIError(
-            "thinking block has invalid signature",
-            status_code=400,
-        )
-        result = classify_api_error(e, provider="anthropic")
-        assert result.reason == FailoverReason.thinking_signature
-        assert result.retryable is True
-
-    def test_non_anthropic_400_with_signature_not_classified_as_thinking(self):
-        """400 with 'signature' but from non-Anthropic → format error."""
-        e = MockAPIError("invalid signature", status_code=400)
-        result = classify_api_error(e, provider="openrouter", approx_tokens=0)
-        # Without "thinking" in the message, it shouldn't be thinking_signature
-        assert result.reason != FailoverReason.thinking_signature
-
-    # ── Provider-specific: Anthropic long-context tier ──
-
-    def test_anthropic_long_context_tier(self):
-        e = MockAPIError(
-            "Extra usage is required for long context requests over 200k tokens",
-            status_code=429,
-        )
-        result = classify_api_error(e, provider="anthropic", model="claude-sonnet-4")
-        assert result.reason == FailoverReason.long_context_tier
-        assert result.should_compress is True
-
-    def test_normal_429_not_long_context(self):
-        """Normal 429 without 'extra usage' + 'long context' → rate_limit."""
-        e = MockAPIError("Too Many Requests", status_code=429)
-        result = classify_api_error(e, provider="anthropic")
-        assert result.reason == FailoverReason.rate_limit
-
-    # ── Transport errors ──
-
-    def test_read_timeout(self):
-        e = ReadTimeout("Read timed out")
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.timeout
-        assert result.retryable is True
-
-    def test_connect_error(self):
-        e = ConnectError("Connection refused")
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.timeout
-
-    def test_connection_error_builtin(self):
-        e = ConnectionError("Connection reset by peer")
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.timeout
-
-    def test_timeout_error_builtin(self):
-        e = TimeoutError("timed out")
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.timeout
-
-    # ── Error code classification ──
-
-    def test_error_code_resource_exhausted(self):
-        e = MockAPIError(
-            "Resource exhausted",
-            body={"error": {"code": "resource_exhausted", "message": "Too many requests"}},
-        )
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.rate_limit
-
-    def test_error_code_model_not_found(self):
-        e = MockAPIError(
-            "Model not available",
-            body={"error": {"code": "model_not_found"}},
-        )
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.model_not_found
-
-    def test_error_code_context_length_exceeded(self):
-        e = MockAPIError(
-            "Context too large",
-            body={"error": {"code": "context_length_exceeded"}},
-        )
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.context_overflow
-
-    # ── Message-only patterns (no status code) ──
-
-    def test_message_billing_pattern(self):
-        e = Exception("insufficient credits to complete this request")
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.billing
-
-    def test_message_rate_limit_pattern(self):
-        e = Exception("rate limit reached for this model")
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.rate_limit
-
-    def test_message_auth_pattern(self):
-        e = Exception("invalid api key provided")
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.auth
-
-    def test_message_model_not_found_pattern(self):
-        e = Exception("gpt-99 is not a valid model")
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.model_not_found
-
-    def test_message_context_overflow_pattern(self):
-        e = Exception("maximum context length exceeded")
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.context_overflow
-
-    # ── Unknown / fallback ──
-
-    def test_generic_exception_is_unknown(self):
-        e = Exception("something weird happened")
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.unknown
-        assert result.retryable is True
-
-    # ── Format error ──
-
-    def test_400_descriptive_format_error(self):
-        """400 with descriptive message (not context overflow) → format error."""
-        e = MockAPIError(
-            "Invalid value for parameter 'temperature': must be between 0 and 2",
-            status_code=400,
-            body={"error": {"message": "Invalid value for parameter 'temperature': must be between 0 and 2"}},
-        )
-        result = classify_api_error(e, approx_tokens=1000)
-        assert result.reason == FailoverReason.format_error
-        assert result.retryable is False
-
-    def test_422_format_error(self):
-        e = MockAPIError("Unprocessable Entity", status_code=422)
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.format_error
-        assert result.retryable is False
-
-    def test_400_flat_body_descriptive_not_context_overflow(self):
-        """Responses API flat body with descriptive error + large session → format error.
-
-        The Codex Responses API returns errors in flat body format:
-        {"message": "...", "type": "..."} without an "error" wrapper.
-        A descriptive 400 must NOT be misclassified as context overflow
-        just because the session is large.
-        """
-        e = MockAPIError(
-            "Invalid 'input[index].name': string does not match pattern.",
-            status_code=400,
-            body={"message": "Invalid 'input[index].name': string does not match pattern.",
-                  "type": "invalid_request_error"},
-        )
-        result = classify_api_error(e, approx_tokens=200000, context_length=400000, num_messages=500)
-        assert result.reason == FailoverReason.format_error
-        assert result.retryable is False
-
-    def test_400_flat_body_generic_large_session_still_context_overflow(self):
-        """Flat body with generic 'Error' message + large session → context overflow.
-
-        Regression: the flat-body fallback must not break the existing heuristic
-        for genuinely generic errors from providers that use flat bodies.
-        """
-        e = MockAPIError(
-            "Error",
-            status_code=400,
-            body={"message": "Error"},
-        )
-        result = classify_api_error(e, approx_tokens=100000, context_length=200000)
-        assert result.reason == FailoverReason.context_overflow
-
-    # ── Peer closed + large session ──
-
-    def test_peer_closed_large_session(self):
-        e = Exception("peer closed connection without sending complete message")
-        result = classify_api_error(e, approx_tokens=130000, context_length=200000)
-        assert result.reason == FailoverReason.context_overflow
-
-    # ── Chinese error messages ──
-
-    def test_chinese_context_overflow(self):
-        e = MockAPIError("超过最大长度限制", status_code=400)
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.context_overflow
-
-    # ── Result metadata ──
-
-    def test_provider_and_model_in_result(self):
-        e = MockAPIError("fail", status_code=500)
-        result = classify_api_error(e, provider="openrouter", model="gpt-5")
-        assert result.provider == "openrouter"
-        assert result.model == "gpt-5"
-        assert result.status_code == 500
-
-    def test_message_extracted(self):
-        e = MockAPIError(
-            "outer",
-            status_code=500,
-            body={"error": {"message": "Internal server error occurred"}},
-        )
-        result = classify_api_error(e)
-        assert result.message == "Internal server error occurred"
-
-
-# ── Test: Adversarial / edge cases (from live testing) ─────────────────
-
-class TestAdversarialEdgeCases:
-    """Edge cases discovered during live testing with real SDK objects."""
-
-    def test_empty_exception_message(self):
-        result = classify_api_error(Exception(""))
-        assert result.reason == FailoverReason.unknown
-        assert result.retryable is True
-
-    def test_500_with_none_body(self):
-        e = MockAPIError("fail", status_code=500, body=None)
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.server_error
-
-    def test_non_dict_body(self):
-        """Some providers return strings instead of JSON."""
-        class StringBodyError(Exception):
-            status_code = 400
-            body = "just a string"
-        result = classify_api_error(StringBodyError("bad"))
-        assert result.reason == FailoverReason.format_error
-
-    def test_list_body(self):
-        class ListBodyError(Exception):
-            status_code = 500
-            body = [{"error": "something"}]
-        result = classify_api_error(ListBodyError("server error"))
-        assert result.reason == FailoverReason.server_error
-
-    def test_circular_cause_chain(self):
-        """Must not infinite-loop on circular __cause__."""
-        e = Exception("circular")
-        e.__cause__ = e
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.unknown
-
-    def test_three_level_cause_chain(self):
-        inner = MockAPIError("inner", status_code=429)
-        middle = Exception("middle")
-        middle.__cause__ = inner
-        outer = RuntimeError("outer")
-        outer.__cause__ = middle
-        result = classify_api_error(outer)
-        assert result.status_code == 429
-        assert result.reason == FailoverReason.rate_limit
-
-    def test_400_with_rate_limit_text(self):
-        """Some providers send rate limits as 400 instead of 429."""
-        e = MockAPIError(
-            "rate limit policy",
-            status_code=400,
-            body={"error": {"message": "rate limit exceeded on this model"}},
-        )
-        result = classify_api_error(e, provider="openrouter")
-        assert result.reason == FailoverReason.rate_limit
-
-    def test_400_with_billing_text(self):
-        """Some providers send billing errors as 400."""
-        e = MockAPIError(
-            "billing",
-            status_code=400,
-            body={"error": {"message": "insufficient credits for this request"}},
-        )
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.billing
-
-    def test_200_with_error_body(self):
-        """200 status with error in body — should be unknown, not crash."""
-        class WeirdSuccess(Exception):
-            status_code = 200
-            body = {"error": {"message": "loading"}}
-        result = classify_api_error(WeirdSuccess("model loading"))
-        assert result.reason == FailoverReason.unknown
-
-    def test_ollama_context_size_exceeded(self):
-        e = MockAPIError(
-            "Error",
-            status_code=400,
-            body={"error": {"message": "context size has been exceeded"}},
-        )
-        result = classify_api_error(e, provider="ollama")
-        assert result.reason == FailoverReason.context_overflow
-
-    def test_connection_refused_error(self):
-        e = ConnectionRefusedError("Connection refused: localhost:11434")
-        result = classify_api_error(e, provider="ollama")
-        assert result.reason == FailoverReason.timeout
-
-    def test_body_message_enrichment(self):
-        """Body message must be included in pattern matching even when
-        str(error) doesn't contain it (OpenAI SDK APIStatusError)."""
-        e = MockAPIError(
-            "Usage limit",  # str(e) = "usage limit"
-            status_code=402,
-            body={"error": {"message": "Usage limit reached, try again in 5 minutes"}},
-        )
-        result = classify_api_error(e)
-        # "try again" is only in body, not in str(e)
-        assert result.reason == FailoverReason.rate_limit
-
-    def test_disconnect_pattern_ordering(self):
-        """Disconnect + large session must beat generic transport catch."""
-        class FakeRemoteProtocol(Exception):
-            pass
-        # Type name isn't in _TRANSPORT_ERROR_TYPES but message has disconnect pattern
-        e = Exception("peer closed connection without sending complete message")
-        result = classify_api_error(e, approx_tokens=150000, context_length=200000)
-        assert result.reason == FailoverReason.context_overflow
-        assert result.should_compress is True
-
-    def test_credit_balance_too_low(self):
-        e = MockAPIError(
-            "Credits low",
-            status_code=402,
-            body={"error": {"message": "Your credit balance is too low"}},
-        )
-        result = classify_api_error(e, provider="anthropic")
-        assert result.reason == FailoverReason.billing
-
-    def test_deepseek_402_chinese(self):
-        """Chinese billing message should still match billing patterns."""
-        # "余额不足" doesn't match English billing patterns, but 402 defaults to billing
-        e = MockAPIError("余额不足", status_code=402)
-        result = classify_api_error(e, provider="deepseek")
-        assert result.reason == FailoverReason.billing
-
-    def test_openrouter_wrapped_context_overflow_in_metadata_raw(self):
-        """OpenRouter wraps provider errors in metadata.raw JSON string."""
-        e = MockAPIError(
-            "Provider returned error",
-            status_code=400,
-            body={
-                "error": {
-                    "message": "Provider returned error",
-                    "code": 400,
-                    "metadata": {
-                        "raw": '{"error":{"message":"context length exceeded: 50000 > 32768"}}'
-                    }
-                }
-            },
-        )
-        result = classify_api_error(e, provider="openrouter", approx_tokens=10000)
-        assert result.reason == FailoverReason.context_overflow
-        assert result.should_compress is True
-
-    def test_openrouter_wrapped_rate_limit_in_metadata_raw(self):
-        e = MockAPIError(
-            "Provider returned error",
-            status_code=400,
-            body={
-                "error": {
-                    "message": "Provider returned error",
-                    "metadata": {
-                        "raw": '{"error":{"message":"Rate limit exceeded. Please retry after 30s."}}'
-                    }
-                }
-            },
-        )
-        result = classify_api_error(e, provider="openrouter")
-        assert result.reason == FailoverReason.rate_limit
-
-    def test_thinking_signature_via_openrouter(self):
-        """Thinking signature errors proxied through OpenRouter must be caught."""
-        e = MockAPIError(
-            "thinking block has invalid signature",
-            status_code=400,
-        )
-        # provider is openrouter, not anthropic — old code missed this
-        result = classify_api_error(e, provider="openrouter", model="anthropic/claude-sonnet-4")
-        assert result.reason == FailoverReason.thinking_signature
-
-    def test_generic_400_large_by_message_count(self):
-        """Many small messages (>80) should trigger context overflow heuristic."""
-        e = MockAPIError(
-            "Error",
-            status_code=400,
-            body={"error": {"message": "Error"}},
-        )
-        # Low token count but high message count
-        result = classify_api_error(
-            e, approx_tokens=5000, context_length=200000, num_messages=100,
-        )
-        assert result.reason == FailoverReason.context_overflow
-
-    def test_disconnect_large_by_message_count(self):
-        """Server disconnect with 200+ messages should trigger context overflow."""
-        e = Exception("server disconnected without sending complete message")
-        result = classify_api_error(
-            e, approx_tokens=5000, context_length=200000, num_messages=250,
-        )
-        assert result.reason == FailoverReason.context_overflow
-
-    def test_openrouter_wrapped_model_not_found_in_metadata_raw(self):
-        e = MockAPIError(
-            "Provider returned error",
-            status_code=400,
-            body={
-                "error": {
-                    "message": "Provider returned error",
-                    "metadata": {
-                        "raw": '{"error":{"message":"The model gpt-99 does not exist"}}'
-                    }
-                }
-            },
-        )
-        result = classify_api_error(e, provider="openrouter")
-        assert result.reason == FailoverReason.model_not_found
@@ -1,42 +0,0 @@
-"""Tests for MiniMax auxiliary client URL normalization.
-
-MiniMax and MiniMax-CN set inference_base_url to the /anthropic path.
-The auxiliary client uses the OpenAI SDK, which needs /v1 instead.
-"""
-
-import sys
-import os
-
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", ".."))
-
-from agent.auxiliary_client import _to_openai_base_url
-
-
-class TestToOpenaiBaseUrl:
-    def test_minimax_global_anthropic_suffix_replaced(self):
-        assert _to_openai_base_url("https://api.minimax.io/anthropic") == "https://api.minimax.io/v1"
-
-    def test_minimax_cn_anthropic_suffix_replaced(self):
-        assert _to_openai_base_url("https://api.minimaxi.com/anthropic") == "https://api.minimaxi.com/v1"
-
-    def test_trailing_slash_stripped_before_replace(self):
-        assert _to_openai_base_url("https://api.minimax.io/anthropic/") == "https://api.minimax.io/v1"
-
-    def test_v1_url_unchanged(self):
-        assert _to_openai_base_url("https://api.openai.com/v1") == "https://api.openai.com/v1"
-
-    def test_openrouter_url_unchanged(self):
-        assert _to_openai_base_url("https://openrouter.ai/api/v1") == "https://openrouter.ai/api/v1"
-
-    def test_anthropic_domain_unchanged(self):
-        """api.anthropic.com doesn't end with /anthropic — should be untouched."""
-        assert _to_openai_base_url("https://api.anthropic.com") == "https://api.anthropic.com"
-
-    def test_anthropic_in_subpath_unchanged(self):
-        assert _to_openai_base_url("https://example.com/anthropic/extra") == "https://example.com/anthropic/extra"
-
-    def test_empty_string(self):
-        assert _to_openai_base_url("") == ""
-
-    def test_none(self):
-        assert _to_openai_base_url(None) == ""
@@ -1,105 +0,0 @@
-"""Tests for MiniMax provider hardening — context lengths, thinking guard, catalog."""
-
-
-class TestMinimaxContextLengths:
-    """Verify per-model context length entries for MiniMax models."""
-
-    def test_m1_variants_have_1m_context(self):
-        from agent.model_metadata import DEFAULT_CONTEXT_LENGTHS
-        # Keys are lowercase because the lookup lowercases model names
-        for model in ("minimax-m1", "minimax-m1-40k", "minimax-m1-80k",
-                       "minimax-m1-128k", "minimax-m1-256k"):
-            assert model in DEFAULT_CONTEXT_LENGTHS, f"{model} missing from context lengths"
-            assert DEFAULT_CONTEXT_LENGTHS[model] == 1_000_000, f"{model} expected 1M"
-
-    def test_m2_variants_have_1m_context(self):
-        from agent.model_metadata import DEFAULT_CONTEXT_LENGTHS
-        # Keys are lowercase because the lookup lowercases model names
-        for model in ("minimax-m2.5", "minimax-m2.7"):
-            assert model in DEFAULT_CONTEXT_LENGTHS, f"{model} missing from context lengths"
-            assert DEFAULT_CONTEXT_LENGTHS[model] == 1_048_576, f"{model} expected 1048576"
-
-    def test_minimax_prefix_fallback(self):
-        from agent.model_metadata import DEFAULT_CONTEXT_LENGTHS
-        # The generic "minimax" prefix entry should be 1M for unknown models
-        assert DEFAULT_CONTEXT_LENGTHS["minimax"] == 1_048_576
-
-
-
-class TestMinimaxThinkingGuard:
-    """Verify that build_anthropic_kwargs does NOT add thinking params for MiniMax models."""
-
-    def test_no_thinking_for_minimax_m27(self):
-        from agent.anthropic_adapter import build_anthropic_kwargs
-        kwargs = build_anthropic_kwargs(
-            model="MiniMax-M2.7",
-            messages=[{"role": "user", "content": "hello"}],
-            tools=None,
-            max_tokens=4096,
-            reasoning_config={"enabled": True, "effort": "medium"},
-        )
-        assert "thinking" not in kwargs
-        assert "output_config" not in kwargs
-
-    def test_no_thinking_for_minimax_m1(self):
-        from agent.anthropic_adapter import build_anthropic_kwargs
-        kwargs = build_anthropic_kwargs(
-            model="MiniMax-M1-128k",
-            messages=[{"role": "user", "content": "hello"}],
-            tools=None,
-            max_tokens=4096,
-            reasoning_config={"enabled": True, "effort": "high"},
-        )
-        assert "thinking" not in kwargs
-
-    def test_thinking_still_works_for_claude(self):
-        from agent.anthropic_adapter import build_anthropic_kwargs
-        kwargs = build_anthropic_kwargs(
-            model="claude-sonnet-4-20250514",
-            messages=[{"role": "user", "content": "hello"}],
-            tools=None,
-            max_tokens=4096,
-            reasoning_config={"enabled": True, "effort": "medium"},
-        )
-        assert "thinking" in kwargs
-
-
-class TestMinimaxAuxModel:
-    """Verify auxiliary model is standard (not highspeed)."""
-
-    def test_minimax_aux_is_standard(self):
-        from agent.auxiliary_client import _API_KEY_PROVIDER_AUX_MODELS
-        assert _API_KEY_PROVIDER_AUX_MODELS["minimax"] == "MiniMax-M2.7"
-        assert _API_KEY_PROVIDER_AUX_MODELS["minimax-cn"] == "MiniMax-M2.7"
-
-    def test_minimax_aux_not_highspeed(self):
-        from agent.auxiliary_client import _API_KEY_PROVIDER_AUX_MODELS
-        assert "highspeed" not in _API_KEY_PROVIDER_AUX_MODELS["minimax"]
-        assert "highspeed" not in _API_KEY_PROVIDER_AUX_MODELS["minimax-cn"]
-
-
-class TestMinimaxModelCatalog:
-    """Verify the model catalog includes M1 family and excludes deprecated models."""
-
-    def test_catalog_includes_m1_family(self):
-        from hermes_cli.models import _PROVIDER_MODELS
-        for provider in ("minimax", "minimax-cn"):
-            models = _PROVIDER_MODELS[provider]
-            assert "MiniMax-M1" in models
-            assert "MiniMax-M1-40k" in models
-            assert "MiniMax-M1-80k" in models
-            assert "MiniMax-M1-128k" in models
-            assert "MiniMax-M1-256k" in models
-
-    def test_catalog_excludes_deprecated(self):
-        from hermes_cli.models import _PROVIDER_MODELS
-        for provider in ("minimax", "minimax-cn"):
-            models = _PROVIDER_MODELS[provider]
-            assert "MiniMax-M2.1" not in models
-
-    def test_catalog_excludes_highspeed(self):
-        from hermes_cli.models import _PROVIDER_MODELS
-        for provider in ("minimax", "minimax-cn"):
-            models = _PROVIDER_MODELS[provider]
-            assert "MiniMax-M2.7-highspeed" not in models
-            assert "MiniMax-M2.5-highspeed" not in models
@@ -1,212 +0,0 @@
-"""Tests for agent.rate_limit_tracker — header parsing and formatting."""
-
-import time
-import pytest
-from agent.rate_limit_tracker import (
-    RateLimitBucket,
-    RateLimitState,
-    parse_rate_limit_headers,
-    format_rate_limit_display,
-    format_rate_limit_compact,
-    _fmt_count,
-    _fmt_seconds,
-    _bar,
-)
-
-
-# ── Sample headers from Nous inference API ──────────────────────────────
-
-NOUS_HEADERS = {
-    "x-ratelimit-limit-requests": "800",
-    "x-ratelimit-limit-requests-1h": "33600",
-    "x-ratelimit-limit-tokens": "8000000",
-    "x-ratelimit-limit-tokens-1h": "336000000",
-    "x-ratelimit-remaining-requests": "795",
-    "x-ratelimit-remaining-requests-1h": "33590",
-    "x-ratelimit-remaining-tokens": "7999500",
-    "x-ratelimit-remaining-tokens-1h": "335999000",
-    "x-ratelimit-reset-requests": "45.5",
-    "x-ratelimit-reset-requests-1h": "3500.0",
-    "x-ratelimit-reset-tokens": "42.3",
-    "x-ratelimit-reset-tokens-1h": "3490.0",
-}
-
-
-class TestParseHeaders:
-    def test_basic_parsing(self):
-        state = parse_rate_limit_headers(NOUS_HEADERS, provider="nous")
-        assert state is not None
-        assert state.provider == "nous"
-        assert state.has_data
-
-        assert state.requests_min.limit == 800
-        assert state.requests_min.remaining == 795
-        assert state.requests_min.reset_seconds == 45.5
-
-        assert state.requests_hour.limit == 33600
-        assert state.requests_hour.remaining == 33590
-
-        assert state.tokens_min.limit == 8000000
-        assert state.tokens_min.remaining == 7999500
-
-        assert state.tokens_hour.limit == 336000000
-        assert state.tokens_hour.remaining == 335999000
-        assert state.tokens_hour.reset_seconds == 3490.0
-
-    def test_no_headers(self):
-        state = parse_rate_limit_headers({})
-        assert state is None
-
-    def test_partial_headers(self):
-        headers = {
-            "x-ratelimit-limit-requests": "100",
-            "x-ratelimit-remaining-requests": "50",
-        }
-        state = parse_rate_limit_headers(headers)
-        assert state is not None
-        assert state.requests_min.limit == 100
-        assert state.requests_min.remaining == 50
-        # Missing fields default to 0
-        assert state.tokens_min.limit == 0
-
-    def test_non_rate_limit_headers_ignored(self):
-        headers = {
-            "content-type": "application/json",
-            "server": "nginx",
-        }
-        state = parse_rate_limit_headers(headers)
-        assert state is None
-
-    def test_malformed_values(self):
-        headers = {
-            "x-ratelimit-limit-requests": "not-a-number",
-            "x-ratelimit-remaining-requests": "",
-            "x-ratelimit-reset-requests": "abc",
-        }
-        state = parse_rate_limit_headers(headers)
-        assert state is not None
-        assert state.requests_min.limit == 0
-        assert state.requests_min.remaining == 0
-        assert state.requests_min.reset_seconds == 0.0
-
-
-class TestBucket:
-    def test_used(self):
-        b = RateLimitBucket(limit=800, remaining=795, reset_seconds=45.0, captured_at=time.time())
-        assert b.used == 5
-
-    def test_usage_pct(self):
-        b = RateLimitBucket(limit=100, remaining=20, reset_seconds=30.0, captured_at=time.time())
-        assert b.usage_pct == pytest.approx(80.0)
-
-    def test_usage_pct_zero_limit(self):
-        b = RateLimitBucket(limit=0, remaining=0)
-        assert b.usage_pct == 0.0
-
-    def test_remaining_seconds_now(self):
-        now = time.time()
-        b = RateLimitBucket(limit=800, remaining=795, reset_seconds=60.0, captured_at=now - 10)
-        # ~50 seconds should remain
-        assert 49 <= b.remaining_seconds_now <= 51
-
-    def test_remaining_seconds_expired(self):
-        b = RateLimitBucket(limit=800, remaining=795, reset_seconds=30.0, captured_at=time.time() - 60)
-        assert b.remaining_seconds_now == 0.0
-
-
-class TestFormatting:
-    def test_fmt_count_millions(self):
-        assert _fmt_count(8000000) == "8.0M"
-        assert _fmt_count(336000000) == "336.0M"
-
-    def test_fmt_count_thousands(self):
-        assert _fmt_count(33600) == "33.6K"
-        assert _fmt_count(1500) == "1.5K"
-
-    def test_fmt_count_small(self):
-        assert _fmt_count(800) == "800"
-        assert _fmt_count(0) == "0"
-
-    def test_fmt_seconds_short(self):
-        assert _fmt_seconds(45) == "45s"
-        assert _fmt_seconds(0) == "0s"
-
-    def test_fmt_seconds_minutes(self):
-        assert _fmt_seconds(125) == "2m 5s"
-        assert _fmt_seconds(120) == "2m"
-
-    def test_fmt_seconds_hours(self):
-        assert _fmt_seconds(3660) == "1h 1m"
-        assert _fmt_seconds(3600) == "1h"
-
-    def test_bar(self):
-        bar = _bar(50.0, width=10)
-        assert bar == "[█████░░░░░]"
-        assert _bar(0.0, width=10) == "[░░░░░░░░░░]"
-        assert _bar(100.0, width=10) == "[██████████]"
-
-    def test_format_display_no_data(self):
-        state = RateLimitState()
-        result = format_rate_limit_display(state)
-        assert "No rate limit data" in result
-
-    def test_format_display_with_data(self):
-        state = parse_rate_limit_headers(NOUS_HEADERS, provider="nous")
-        result = format_rate_limit_display(state)
-        assert "Nous" in result
-        assert "Requests/min" in result
-        assert "Requests/hr" in result
-        assert "Tokens/min" in result
-        assert "Tokens/hr" in result
-        assert "resets in" in result
-
-    def test_format_display_warning_on_high_usage(self):
-        headers = {
-            **NOUS_HEADERS,
-            "x-ratelimit-remaining-requests": "50",  # 750/800 used = 93.75%
-        }
-        state = parse_rate_limit_headers(headers)
-        result = format_rate_limit_display(state)
-        assert "⚠" in result
-
-    def test_format_compact(self):
-        state = parse_rate_limit_headers(NOUS_HEADERS, provider="nous")
-        result = format_rate_limit_compact(state)
-        assert "RPM:" in result
-        assert "RPH:" in result
-        assert "TPM:" in result
-        assert "TPH:" in result
-        assert "resets" in result
-
-    def test_format_compact_no_data(self):
-        state = RateLimitState()
-        result = format_rate_limit_compact(state)
-        assert "No rate limit data" in result
-
-
-class TestAgentIntegration:
-    """Test that AIAgent captures rate limit state correctly."""
-
-    def test_capture_rate_limits_from_headers(self):
-        """Simulate the header capture path without a real API call."""
-        import sys
-        import os
-        # Use a mock httpx-like response
-        class MockResponse:
-            headers = NOUS_HEADERS
-
-        # Import AIAgent minimally
-        from unittest.mock import MagicMock, patch
-
-        # Test the parsing directly
-        state = parse_rate_limit_headers(MockResponse.headers, provider="nous")
-        assert state is not None
-        assert state.requests_min.limit == 800
-        assert state.tokens_hour.limit == 336000000
-
-    def test_capture_rate_limits_none_response(self):
-        """_capture_rate_limits should handle None gracefully."""
-        from agent.rate_limit_tracker import parse_rate_limit_headers
-        # None should not crash
-        result = parse_rate_limit_headers({})
-        assert result is None
@@ -3,7 +3,6 @@
 import os
 import pytest
 from pathlib import Path
-from unittest.mock import patch

 from agent.subdirectory_hints import SubdirectoryHintTracker

@@ -190,45 +189,3 @@ class TestSubdirectoryHintTracker:
            "terminal", {"command": "curl https://example.com/frontend/api"}
        )
        assert result is None
-
-
-class TestPermissionErrorHandling:
-    """Regression tests for PermissionError in filesystem checks (ref #6214)."""
-
-    def test_is_valid_subdir_permission_error(self, tmp_path):
-        """_is_valid_subdir should return False when is_dir() raises PermissionError."""
-        tracker = SubdirectoryHintTracker(working_dir=str(tmp_path))
-        restricted = tmp_path / "restricted"
-        restricted.mkdir()
-        with patch.object(Path, "is_dir", side_effect=PermissionError("Permission denied")):
-            assert tracker._is_valid_subdir(restricted) is False
-
-    def test_load_hints_permission_error_on_is_file(self, tmp_path):
-        """_load_hints_for_directory should skip files when is_file() raises PermissionError."""
-        tracker = SubdirectoryHintTracker(working_dir=str(tmp_path))
-        restricted = tmp_path / "restricted"
-        restricted.mkdir()
-        original_is_file = Path.is_file
-        def patched_is_file(self):
-            if "restricted" in str(self):
-                raise PermissionError("Permission denied")
-            return original_is_file(self)
-        with patch.object(Path, "is_file", patched_is_file):
-            result = tracker._load_hints_for_directory(restricted)
-        assert result is None
-
-    def test_check_tool_call_survives_inaccessible_path(self, project):
-        """Full check_tool_call should not crash when a path is inaccessible."""
-        tracker = SubdirectoryHintTracker(working_dir=str(project))
-        original_is_dir = Path.is_dir
-        def patched_is_dir(self):
-            if "backend" in str(self) and "src" not in str(self):
-                raise PermissionError("Permission denied")
-            return original_is_dir(self)
-        with patch.object(Path, "is_dir", patched_is_dir):
-            # Should not raise — gracefully skip the inaccessible directory
-            result = tracker.check_tool_call(
-                "read_file", {"path": str(project / "backend" / "src" / "main.py")}
-            )
-            # Result may be None (backend skipped) — the key point is no crash
-            assert result is None or isinstance(result, str)
@@ -2,65 +2,22 @@ import queue
 import threading
 import time
 from types import SimpleNamespace
-from unittest.mock import MagicMock, patch
+from unittest.mock import MagicMock

-import cli as cli_module
 from cli import HermesCLI


-class _FakeBuffer:
-    def __init__(self, text="", cursor_position=None):
-        self.text = text
-        self.cursor_position = len(text) if cursor_position is None else cursor_position
-
-    def reset(self, append_to_history=False):
-        self.text = ""
-        self.cursor_position = 0
-
-
 def _make_cli_stub():
    cli = HermesCLI.__new__(HermesCLI)
    cli._approval_state = None
    cli._approval_deadline = 0
    cli._approval_lock = threading.Lock()
-    cli._sudo_state = None
-    cli._sudo_deadline = 0
-    cli._modal_input_snapshot = None
    cli._invalidate = MagicMock()
-    cli._app = SimpleNamespace(invalidate=MagicMock(), current_buffer=_FakeBuffer())
+    cli._app = SimpleNamespace(invalidate=MagicMock())
    return cli


 class TestCliApprovalUi:
-    def test_sudo_prompt_restores_existing_draft_after_response(self):
-        cli = _make_cli_stub()
-        cli._app.current_buffer = _FakeBuffer("draft command", cursor_position=5)
-        result = {}
-
-        def _run_callback():
-            result["value"] = cli._sudo_password_callback()
-
-        with patch.object(cli_module, "_cprint"):
-            thread = threading.Thread(target=_run_callback, daemon=True)
-            thread.start()
-
-            deadline = time.time() + 2
-            while cli._sudo_state is None and time.time() < deadline:
-                time.sleep(0.01)
-
-            assert cli._sudo_state is not None
-            assert cli._app.current_buffer.text == ""
-
-            cli._app.current_buffer.text = "secret"
-            cli._app.current_buffer.cursor_position = len("secret")
-            cli._sudo_state["response_queue"].put("secret")
-
-            thread.join(timeout=2)
-
-        assert result["value"] == "secret"
-        assert cli._app.current_buffer.text == "draft command"
-        assert cli._app.current_buffer.cursor_position == 5
-
    def test_approval_callback_includes_view_for_long_commands(self):
        cli = _make_cli_stub()
        command = "sudo dd if=/tmp/githubcli-keyring.gpg of=/usr/share/keyrings/githubcli-archive-keyring.gpg bs=4M status=progress"
@@ -41,7 +41,6 @@ def _attach_agent(
        session_completion_tokens=completion_tokens,
        session_total_tokens=total_tokens,
        session_api_calls=api_calls,
-        get_rate_limit_state=lambda: None,
        context_compressor=SimpleNamespace(
            last_prompt_tokens=context_tokens,
            context_length=context_length,
@@ -1,66 +0,0 @@
-import pytest
-from unittest.mock import MagicMock, patch
-from hermes_cli.plugins import VALID_HOOKS, PluginManager
-import os
-import shutil
-import tempfile
-from cli import HermesCLI
-
-
-def test_session_hooks_in_valid_hooks():
-    """Verify on_session_finalize and on_session_reset are registered as valid hooks."""
-    assert "on_session_finalize" in VALID_HOOKS
-    assert "on_session_reset" in VALID_HOOKS
-
-
-@patch("hermes_cli.plugins.invoke_hook")
-def test_session_finalize_on_reset(mock_invoke_hook):
-    """Verify on_session_finalize fires when /new or /reset is used."""
-    cli = HermesCLI()
-    cli.agent = MagicMock()
-    cli.agent.session_id = "test-session-id"
-
-    # Simulate /new command which triggers on_session_finalize for the old session
-    cli.new_session(silent=True)
-
-    # Check if on_session_finalize was called for the old session
-    mock_invoke_hook.assert_any_call(
-        "on_session_finalize", session_id="test-session-id", platform="cli"
-    )
-    # Check if on_session_reset was called for the new session
-    mock_invoke_hook.assert_any_call(
-        "on_session_reset", session_id=cli.session_id, platform="cli"
-    )
-
-
-@patch("hermes_cli.plugins.invoke_hook")
-def test_session_finalize_on_cleanup(mock_invoke_hook):
-    """Verify on_session_finalize fires during CLI exit cleanup."""
-    import cli as cli_mod
-
-    mock_agent = MagicMock()
-    mock_agent.session_id = "cleanup-session-id"
-    cli_mod._active_agent_ref = mock_agent
-    cli_mod._cleanup_done = False
-
-    cli_mod._run_cleanup()
-
-    mock_invoke_hook.assert_any_call(
-        "on_session_finalize", session_id="cleanup-session-id", platform="cli"
-    )
-
-
-@patch("hermes_cli.plugins.invoke_hook")
-def test_hook_errors_are_caught(mock_invoke_hook):
-    """Verify hook exceptions are caught and don't crash the agent."""
-    mgr = PluginManager()
-
-    # Register a hook that raises
-    def bad_callback(**kwargs):
-        raise Exception("Hook failed")
-
-    mgr._hooks["on_session_finalize"] = [bad_callback]
-
-    # This should not raise
-    results = mgr.invoke_hook("on_session_finalize", session_id="test", platform="cli")
-    assert results == []
@@ -33,13 +33,6 @@ def git_repo(tmp_path):
        ["git", "commit", "-m", "Initial commit"],
        cwd=repo, capture_output=True,
    )
-    # Add a fake remote ref so cleanup logic sees the initial commit as
-    # "pushed".  Without this, `git log HEAD --not --remotes` treats every
-    # commit as unpushed and cleanup refuses to delete worktrees.
-    subprocess.run(
-        ["git", "update-ref", "refs/remotes/origin/main", "HEAD"],
-        cwd=repo, capture_output=True,
-    )
    return repo


@@ -88,11 +81,7 @@ def _setup_worktree(repo_root):


 def _cleanup_worktree(info):
-    """Test version of _cleanup_worktree.
-
-    Preserves the worktree only if it has unpushed commits.
-    Dirty working tree alone is not enough to keep it.
-    """
+    """Test version of _cleanup_worktree."""
    wt_path = info["path"]
    branch = info["branch"]
    repo_root = info["repo_root"]
@@ -100,15 +89,15 @@ def _cleanup_worktree(info):
    if not Path(wt_path).exists():
        return

-    # Check for unpushed commits
-    result = subprocess.run(
-        ["git", "log", "--oneline", "HEAD", "--not", "--remotes"],
+    # Check for uncommitted changes
+    status = subprocess.run(
+        ["git", "status", "--porcelain"],
        capture_output=True, text=True, timeout=10, cwd=wt_path,
    )
-    has_unpushed = bool(result.stdout.strip())
+    has_changes = bool(status.stdout.strip())

-    if has_unpushed:
-        return False  # Did not clean up — has unpushed commits
+    if has_changes:
+        return False  # Did not clean up

    subprocess.run(
        ["git", "worktree", "remove", wt_path, "--force"],
@@ -215,45 +204,20 @@ class TestWorktreeCleanup:
        assert result is True
        assert not Path(info["path"]).exists()

-    def test_dirty_worktree_cleaned_when_no_unpushed(self, git_repo):
-        """Dirty working tree without unpushed commits is cleaned up.
-
-        Agent sessions typically leave untracked files / artifacts behind.
-        Since all real work is in pushed commits, these don't warrant
-        keeping the worktree.
-        """
+    def test_dirty_worktree_kept(self, git_repo):
        info = _setup_worktree(str(git_repo))
        assert info is not None

-        # Make uncommitted changes (untracked file)
+        # Make uncommitted changes
        (Path(info["path"]) / "new-file.txt").write_text("uncommitted")
        subprocess.run(
            ["git", "add", "new-file.txt"],
            cwd=info["path"], capture_output=True,
        )

-        # The git_repo fixture already has a fake remote ref so the initial
-        # commit is seen as "pushed".  No unpushed commits → cleanup proceeds.
        result = _cleanup_worktree(info)
-        assert result is True  # Cleaned up despite dirty working tree
-        assert not Path(info["path"]).exists()
-
-    def test_worktree_with_unpushed_commits_kept(self, git_repo):
-        """Worktree with unpushed commits is preserved."""
-        info = _setup_worktree(str(git_repo))
-        assert info is not None
-
-        # Make a commit that is NOT on any remote
-        (Path(info["path"]) / "work.txt").write_text("real work")
-        subprocess.run(["git", "add", "work.txt"], cwd=info["path"], capture_output=True)
-        subprocess.run(
-            ["git", "commit", "-m", "agent work"],
-            cwd=info["path"], capture_output=True,
-        )
-
-        result = _cleanup_worktree(info)
-        assert result is False  # Kept — has unpushed commits
-        assert Path(info["path"]).exists()
+        assert result is False
+        assert Path(info["path"]).exists()  # Still there

    def test_branch_deleted_on_cleanup(self, git_repo):
        info = _setup_worktree(str(git_repo))
@@ -403,7 +367,7 @@ class TestMultipleWorktrees:
        lines = [l for l in result.stdout.strip().splitlines() if l.strip()]
        assert len(lines) == 11

-        # Cleanup all (git_repo fixture has a fake remote ref so cleanup works)
+        # Cleanup all
        for info in worktrees:
            # Discard changes first so cleanup works
            subprocess.run(
@@ -528,77 +492,33 @@ class TestStaleWorktreePruning:
        assert not pruned
        assert Path(info["path"]).exists()

-    def test_keeps_old_worktree_with_unpushed_commits(self, git_repo):
-        """Old worktrees (24-72h) with unpushed commits should NOT be pruned."""
+    def test_keeps_dirty_old_worktree(self, git_repo):
+        """Old worktrees with uncommitted changes should NOT be pruned."""
        import time

        info = _setup_worktree(str(git_repo))
        assert info is not None

-        # Make an unpushed commit
-        (Path(info["path"]) / "work.txt").write_text("real work")
-        subprocess.run(["git", "add", "work.txt"], cwd=info["path"], capture_output=True)
+        # Make it dirty
+        (Path(info["path"]) / "dirty.txt").write_text("uncommitted")
        subprocess.run(
-            ["git", "commit", "-m", "agent work"],
+            ["git", "add", "dirty.txt"],
            cwd=info["path"], capture_output=True,
        )

-        # Make it old (25h — in the 24-72h soft tier)
+        # Make it old
        old_time = time.time() - (25 * 3600)
        os.utime(info["path"], (old_time, old_time))

-        # Check for unpushed commits (simulates prune logic)
-        result = subprocess.run(
-            ["git", "log", "--oneline", "HEAD", "--not", "--remotes"],
+        # Check if it would be pruned
+        status = subprocess.run(
+            ["git", "status", "--porcelain"],
            capture_output=True, text=True, cwd=info["path"],
        )
-        has_unpushed = bool(result.stdout.strip())
-        assert has_unpushed  # Has unpushed commits → not pruned in soft tier
+        has_changes = bool(status.stdout.strip())
+        assert has_changes  # Should be dirty → not pruned
        assert Path(info["path"]).exists()

-    def test_force_prunes_very_old_worktree(self, git_repo):
-        """Worktrees older than 72h should be force-pruned regardless."""
-        import time
-
-        info = _setup_worktree(str(git_repo))
-        assert info is not None
-
-        # Make an unpushed commit (would normally protect it)
-        (Path(info["path"]) / "work.txt").write_text("stale work")
-        subprocess.run(["git", "add", "work.txt"], cwd=info["path"], capture_output=True)
-        subprocess.run(
-            ["git", "commit", "-m", "old agent work"],
-            cwd=info["path"], capture_output=True,
-        )
-
-        # Make it very old (73h — beyond the 72h hard threshold)
-        old_time = time.time() - (73 * 3600)
-        os.utime(info["path"], (old_time, old_time))
-
-        # Simulate the force-prune tier check
-        hard_cutoff = time.time() - (72 * 3600)
-        mtime = Path(info["path"]).stat().st_mtime
-        assert mtime <= hard_cutoff  # Should qualify for force removal
-
-        # Actually remove it (simulates _prune_stale_worktrees force path)
-        branch_result = subprocess.run(
-            ["git", "branch", "--show-current"],
-            capture_output=True, text=True, timeout=5, cwd=info["path"],
-        )
-        branch = branch_result.stdout.strip()
-
-        subprocess.run(
-            ["git", "worktree", "remove", info["path"], "--force"],
-            capture_output=True, text=True, timeout=15, cwd=str(git_repo),
-        )
-        if branch:
-            subprocess.run(
-                ["git", "branch", "-D", branch],
-                capture_output=True, text=True, timeout=10, cwd=str(git_repo),
-            )
-
-        assert not Path(info["path"]).exists()
-

 class TestEdgeCases:
    """Test edge cases for robustness."""
@@ -691,133 +611,6 @@ class TestTerminalCWDIntegration:
        assert result.stdout.strip() == "true"


-class TestOrphanedBranchPruning:
-    """Test cleanup of orphaned hermes/* and pr-* branches."""
-
-    def test_prunes_orphaned_hermes_branch(self, git_repo):
-        """hermes/hermes-* branches with no worktree should be deleted."""
-        # Create a branch that looks like a worktree branch but has no worktree
-        subprocess.run(
-            ["git", "branch", "hermes/hermes-deadbeef", "HEAD"],
-            cwd=str(git_repo), capture_output=True,
-        )
-
-        # Verify it exists
-        result = subprocess.run(
-            ["git", "branch", "--list", "hermes/hermes-deadbeef"],
-            capture_output=True, text=True, cwd=str(git_repo),
-        )
-        assert "hermes/hermes-deadbeef" in result.stdout
-
-        # Simulate _prune_orphaned_branches logic
-        result = subprocess.run(
-            ["git", "branch", "--format=%(refname:short)"],
-            capture_output=True, text=True, cwd=str(git_repo),
-        )
-        all_branches = [b.strip() for b in result.stdout.strip().split("\n") if b.strip()]
-
-        wt_result = subprocess.run(
-            ["git", "worktree", "list", "--porcelain"],
-            capture_output=True, text=True, cwd=str(git_repo),
-        )
-        active_branches = {"main"}
-        for line in wt_result.stdout.split("\n"):
-            if line.startswith("branch refs/heads/"):
-                active_branches.add(line.split("branch refs/heads/", 1)[-1].strip())
-
-        orphaned = [
-            b for b in all_branches
-            if b not in active_branches
-            and (b.startswith("hermes/hermes-") or b.startswith("pr-"))
-        ]
-        assert "hermes/hermes-deadbeef" in orphaned
-
-        # Delete them
-        if orphaned:
-            subprocess.run(
-                ["git", "branch", "-D"] + orphaned,
-                capture_output=True, text=True, cwd=str(git_repo),
-            )
-
-        # Verify gone
-        result = subprocess.run(
-            ["git", "branch", "--list", "hermes/hermes-deadbeef"],
-            capture_output=True, text=True, cwd=str(git_repo),
-        )
-        assert "hermes/hermes-deadbeef" not in result.stdout
-
-    def test_prunes_orphaned_pr_branch(self, git_repo):
-        """pr-* branches should be deleted during pruning."""
-        subprocess.run(
-            ["git", "branch", "pr-1234", "HEAD"],
-            cwd=str(git_repo), capture_output=True,
-        )
-        subprocess.run(
-            ["git", "branch", "pr-5678", "HEAD"],
-            cwd=str(git_repo), capture_output=True,
-        )
-
-        result = subprocess.run(
-            ["git", "branch", "--format=%(refname:short)"],
-            capture_output=True, text=True, cwd=str(git_repo),
-        )
-        all_branches = [b.strip() for b in result.stdout.strip().split("\n") if b.strip()]
-
-        active_branches = {"main"}
-        orphaned = [
-            b for b in all_branches
-            if b not in active_branches and b.startswith("pr-")
-        ]
-        assert "pr-1234" in orphaned
-        assert "pr-5678" in orphaned
-
-        subprocess.run(
-            ["git", "branch", "-D"] + orphaned,
-            capture_output=True, text=True, cwd=str(git_repo),
-        )
-
-        # Verify gone
-        result = subprocess.run(
-            ["git", "branch", "--format=%(refname:short)"],
-            capture_output=True, text=True, cwd=str(git_repo),
-        )
-        remaining = result.stdout.strip()
-        assert "pr-1234" not in remaining
-        assert "pr-5678" not in remaining
-
-    def test_preserves_active_worktree_branch(self, git_repo):
-        """Branches with active worktrees should NOT be pruned."""
-        info = _setup_worktree(str(git_repo))
-        assert info is not None
-
-        result = subprocess.run(
-            ["git", "worktree", "list", "--porcelain"],
-            capture_output=True, text=True, cwd=str(git_repo),
-        )
-        active_branches = set()
-        for line in result.stdout.split("\n"):
-            if line.startswith("branch refs/heads/"):
-                active_branches.add(line.split("branch refs/heads/", 1)[-1].strip())
-
-        assert info["branch"] in active_branches  # Protected
-
-    def test_preserves_main_branch(self, git_repo):
-        """main branch should never be pruned."""
-        result = subprocess.run(
-            ["git", "branch", "--format=%(refname:short)"],
-            capture_output=True, text=True, cwd=str(git_repo),
-        )
-        all_branches = [b.strip() for b in result.stdout.strip().split("\n") if b.strip()]
-        active_branches = {"main"}
-
-        orphaned = [
-            b for b in all_branches
-            if b not in active_branches
-            and (b.startswith("hermes/hermes-") or b.startswith("pr-"))
-        ]
-        assert "main" not in orphaned
-
-
 class TestSystemPromptInjection:
    """Test that the agent gets worktree context in its system prompt."""

@@ -832,7 +625,7 @@ class TestSystemPromptInjection:
            f"{info['path']}. Your branch is `{info['branch']}`. "
            f"Changes here do not affect the main working tree or other agents. "
            f"Remember to commit and push your changes, and create a PR if appropriate. "
-            f"The original repo is at {info['repo_root']}.]\n"
+            f"The original repo is at {info['repo_root']}.]"
        )

        assert info["path"] in wt_note
@@ -38,8 +38,6 @@ def _isolate_hermes_home(tmp_path, monkeypatch):
    monkeypatch.delenv("HERMES_SESSION_CHAT_ID", raising=False)
    monkeypatch.delenv("HERMES_SESSION_CHAT_NAME", raising=False)
    monkeypatch.delenv("HERMES_GATEWAY_SESSION", raising=False)
-    # Avoid making real calls during tests if this key is set in the env files
-    monkeypatch.delenv("OPENROUTER_API_KEY", raising=False)


@pytest.fixture()
@@ -339,36 +339,6 @@ class TestMarkJobRun:
        assert updated["last_status"] == "error"
        assert updated["last_error"] == "timeout"

-    def test_delivery_error_tracked_separately(self, tmp_cron_dir):
-        """Agent succeeds but delivery fails — both tracked independently."""
-        job = create_job(prompt="Report", schedule="every 1h")
-        mark_job_run(job["id"], success=True, delivery_error="platform 'telegram' not configured")
-        updated = get_job(job["id"])
-        assert updated["last_status"] == "ok"
-        assert updated["last_error"] is None
-        assert updated["last_delivery_error"] == "platform 'telegram' not configured"
-
-    def test_delivery_error_cleared_on_success(self, tmp_cron_dir):
-        """Successful delivery clears the previous delivery error."""
-        job = create_job(prompt="Report", schedule="every 1h")
-        mark_job_run(job["id"], success=True, delivery_error="network timeout")
-        updated = get_job(job["id"])
-        assert updated["last_delivery_error"] == "network timeout"
-        # Next run delivers successfully
-        mark_job_run(job["id"], success=True, delivery_error=None)
-        updated = get_job(job["id"])
-        assert updated["last_delivery_error"] is None
-
-    def test_both_agent_and_delivery_error(self, tmp_cron_dir):
-        """Agent fails AND delivery fails — both errors recorded."""
-        job = create_job(prompt="Report", schedule="every 1h")
-        mark_job_run(job["id"], success=False, error="model timeout",
-                     delivery_error="platform 'discord' not enabled")
-        updated = get_job(job["id"])
-        assert updated["last_status"] == "error"
-        assert updated["last_error"] == "model timeout"
-        assert updated["last_delivery_error"] == "platform 'discord' not enabled"
-

 class TestAdvanceNextRun:
    """Tests for advance_next_run() — crash-safety for recurring jobs."""
@@ -508,90 +508,6 @@ class TestDeliverResultWrapping:
        assert send_mock.call_args.kwargs["thread_id"] == "17585"


-class TestDeliverResultErrorReturns:
-    """Verify _deliver_result returns error strings on failure, None on success."""
-
-    def test_returns_none_on_successful_delivery(self):
-        from gateway.config import Platform
-
-        pconfig = MagicMock()
-        pconfig.enabled = True
-        mock_cfg = MagicMock()
-        mock_cfg.platforms = {Platform.TELEGRAM: pconfig}
-
-        with patch("gateway.config.load_gateway_config", return_value=mock_cfg), \
-             patch("tools.send_message_tool._send_to_platform", new=AsyncMock(return_value={"success": True})):
-            job = {
-                "id": "ok-job",
-                "deliver": "origin",
-                "origin": {"platform": "telegram", "chat_id": "123"},
-            }
-            result = _deliver_result(job, "Output.")
-        assert result is None
-
-    def test_returns_none_for_local_delivery(self):
-        """local-only jobs don't deliver — not a failure."""
-        job = {"id": "local-job", "deliver": "local"}
-        result = _deliver_result(job, "Output.")
-        assert result is None
-
-    def test_returns_error_for_unknown_platform(self):
-        job = {
-            "id": "bad-platform",
-            "deliver": "origin",
-            "origin": {"platform": "fax", "chat_id": "123"},
-        }
-        with patch("gateway.config.load_gateway_config"):
-            result = _deliver_result(job, "Output.")
-        assert result is not None
-        assert "unknown platform" in result
-
-    def test_returns_error_when_platform_disabled(self):
-        from gateway.config import Platform
-
-        pconfig = MagicMock()
-        pconfig.enabled = False
-        mock_cfg = MagicMock()
-        mock_cfg.platforms = {Platform.TELEGRAM: pconfig}
-
-        with patch("gateway.config.load_gateway_config", return_value=mock_cfg):
-            job = {
-                "id": "disabled",
-                "deliver": "origin",
-                "origin": {"platform": "telegram", "chat_id": "123"},
-            }
-            result = _deliver_result(job, "Output.")
-        assert result is not None
-        assert "not configured" in result
-
-    def test_returns_error_on_send_failure(self):
-        from gateway.config import Platform
-
-        pconfig = MagicMock()
-        pconfig.enabled = True
-        mock_cfg = MagicMock()
-        mock_cfg.platforms = {Platform.TELEGRAM: pconfig}
-
-        with patch("gateway.config.load_gateway_config", return_value=mock_cfg), \
-             patch("tools.send_message_tool._send_to_platform", new=AsyncMock(return_value={"error": "rate limited"})):
-            job = {
-                "id": "rate-limited",
-                "deliver": "origin",
-                "origin": {"platform": "telegram", "chat_id": "123"},
-            }
-            result = _deliver_result(job, "Output.")
-        assert result is not None
-        assert "rate limited" in result
-
-    def test_returns_error_for_unresolved_target(self, monkeypatch):
-        """Non-local delivery with no resolvable target should return an error."""
-        monkeypatch.delenv("TELEGRAM_HOME_CHANNEL", raising=False)
-        job = {"id": "no-target", "deliver": "telegram"}
-        result = _deliver_result(job, "Output.")
-        assert result is not None
-        assert "no delivery target" in result
-
-
 class TestRunJobSessionPersistence:
    def test_run_job_passes_session_db_and_cron_platform(self, tmp_path):
        job = {
@@ -1,361 +0,0 @@
-"""Tests for the BlueBubbles iMessage gateway adapter."""
-import pytest
-
-from gateway.config import Platform, PlatformConfig
-
-
-def _make_adapter(monkeypatch, **extra):
-    monkeypatch.setenv("BLUEBUBBLES_SERVER_URL", "http://localhost:1234")
-    monkeypatch.setenv("BLUEBUBBLES_PASSWORD", "secret")
-    from gateway.platforms.bluebubbles import BlueBubblesAdapter
-
-    cfg = PlatformConfig(
-        enabled=True,
-        extra={
-            "server_url": "http://localhost:1234",
-            "password": "secret",
-            **extra,
-        },
-    )
-    return BlueBubblesAdapter(cfg)
-
-
-class TestBlueBubblesPlatformEnum:
-    def test_bluebubbles_enum_exists(self):
-        assert Platform.BLUEBUBBLES.value == "bluebubbles"
-
-
-class TestBlueBubblesConfigLoading:
-    def test_apply_env_overrides_bluebubbles(self, monkeypatch):
-        monkeypatch.setenv("BLUEBUBBLES_SERVER_URL", "http://localhost:1234")
-        monkeypatch.setenv("BLUEBUBBLES_PASSWORD", "secret")
-        monkeypatch.setenv("BLUEBUBBLES_WEBHOOK_PORT", "9999")
-        from gateway.config import GatewayConfig, _apply_env_overrides
-
-        config = GatewayConfig()
-        _apply_env_overrides(config)
-        assert Platform.BLUEBUBBLES in config.platforms
-        bc = config.platforms[Platform.BLUEBUBBLES]
-        assert bc.enabled is True
-        assert bc.extra["server_url"] == "http://localhost:1234"
-        assert bc.extra["password"] == "secret"
-        assert bc.extra["webhook_port"] == 9999
-
-    def test_connected_platforms_includes_bluebubbles(self, monkeypatch):
-        monkeypatch.setenv("BLUEBUBBLES_SERVER_URL", "http://localhost:1234")
-        monkeypatch.setenv("BLUEBUBBLES_PASSWORD", "secret")
-        from gateway.config import GatewayConfig, _apply_env_overrides
-
-        config = GatewayConfig()
-        _apply_env_overrides(config)
-        assert Platform.BLUEBUBBLES in config.get_connected_platforms()
-
-    def test_home_channel_set_from_env(self, monkeypatch):
-        monkeypatch.setenv("BLUEBUBBLES_SERVER_URL", "http://localhost:1234")
-        monkeypatch.setenv("BLUEBUBBLES_PASSWORD", "secret")
-        monkeypatch.setenv("BLUEBUBBLES_HOME_CHANNEL", "user@example.com")
-        from gateway.config import GatewayConfig, _apply_env_overrides
-
-        config = GatewayConfig()
-        _apply_env_overrides(config)
-        hc = config.platforms[Platform.BLUEBUBBLES].home_channel
-        assert hc is not None
-        assert hc.chat_id == "user@example.com"
-
-    def test_not_connected_without_password(self, monkeypatch):
-        monkeypatch.setenv("BLUEBUBBLES_SERVER_URL", "http://localhost:1234")
-        monkeypatch.delenv("BLUEBUBBLES_PASSWORD", raising=False)
-        from gateway.config import GatewayConfig, _apply_env_overrides
-
-        config = GatewayConfig()
-        _apply_env_overrides(config)
-        assert Platform.BLUEBUBBLES not in config.get_connected_platforms()
-
-
-class TestBlueBubblesHelpers:
-    def test_check_requirements(self, monkeypatch):
-        monkeypatch.setenv("BLUEBUBBLES_SERVER_URL", "http://localhost:1234")
-        monkeypatch.setenv("BLUEBUBBLES_PASSWORD", "secret")
-        from gateway.platforms.bluebubbles import check_bluebubbles_requirements
-
-        assert check_bluebubbles_requirements() is True
-
-    def test_format_message_strips_markdown(self, monkeypatch):
-        adapter = _make_adapter(monkeypatch)
-        assert adapter.format_message("**Hello** `world`") == "Hello world"
-
-    def test_strip_markdown_headers(self, monkeypatch):
-        adapter = _make_adapter(monkeypatch)
-        assert adapter.format_message("## Heading\ntext") == "Heading\ntext"
-
-    def test_strip_markdown_links(self, monkeypatch):
-        adapter = _make_adapter(monkeypatch)
-        assert adapter.format_message("[click here](http://example.com)") == "click here"
-
-    def test_init_normalizes_webhook_path(self, monkeypatch):
-        adapter = _make_adapter(monkeypatch, webhook_path="bluebubbles-webhook")
-        assert adapter.webhook_path == "/bluebubbles-webhook"
-
-    def test_init_preserves_leading_slash(self, monkeypatch):
-        adapter = _make_adapter(monkeypatch, webhook_path="/my-hook")
-        assert adapter.webhook_path == "/my-hook"
-
-    def test_server_url_normalized(self, monkeypatch):
-        adapter = _make_adapter(monkeypatch, server_url="http://localhost:1234/")
-        assert adapter.server_url == "http://localhost:1234"
-
-    def test_server_url_adds_scheme(self, monkeypatch):
-        adapter = _make_adapter(monkeypatch, server_url="localhost:1234")
-        assert adapter.server_url == "http://localhost:1234"
-
-
-class TestBlueBubblesWebhookParsing:
-    def test_webhook_prefers_chat_guid_over_message_guid(self, monkeypatch):
-        adapter = _make_adapter(monkeypatch)
-        payload = {
-            "guid": "MESSAGE-GUID",
-            "chatGuid": "iMessage;-;user@example.com",
-            "chatIdentifier": "user@example.com",
-        }
-        record = adapter._extract_payload_record(payload) or {}
-        chat_guid = adapter._value(
-            record.get("chatGuid"),
-            payload.get("chatGuid"),
-            record.get("chat_guid"),
-            payload.get("chat_guid"),
-            payload.get("guid"),
-        )
-        assert chat_guid == "iMessage;-;user@example.com"
-
-    def test_webhook_can_fall_back_to_sender_when_chat_fields_missing(self, monkeypatch):
-        adapter = _make_adapter(monkeypatch)
-        payload = {
-            "data": {
-                "guid": "MESSAGE-GUID",
-                "text": "hello",
-                "handle": {"address": "user@example.com"},
-                "isFromMe": False,
-            }
-        }
-        record = adapter._extract_payload_record(payload) or {}
-        chat_guid = adapter._value(
-            record.get("chatGuid"),
-            payload.get("chatGuid"),
-            record.get("chat_guid"),
-            payload.get("chat_guid"),
-            payload.get("guid"),
-        )
-        chat_identifier = adapter._value(
-            record.get("chatIdentifier"),
-            record.get("identifier"),
-            payload.get("chatIdentifier"),
-            payload.get("identifier"),
-        )
-        sender = (
-            adapter._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
-        assert chat_identifier == "user@example.com"
-
-    def test_extract_payload_record_accepts_list_data(self, monkeypatch):
-        adapter = _make_adapter(monkeypatch)
-        payload = {
-            "type": "new-message",
-            "data": [
-                {
-                    "text": "hello",
-                    "chatGuid": "iMessage;-;user@example.com",
-                    "chatIdentifier": "user@example.com",
-                }
-            ],
-        }
-        record = adapter._extract_payload_record(payload)
-        assert record == payload["data"][0]
-
-    def test_extract_payload_record_dict_data(self, monkeypatch):
-        adapter = _make_adapter(monkeypatch)
-        payload = {"data": {"text": "hello", "chatGuid": "iMessage;-;+1234"}}
-        record = adapter._extract_payload_record(payload)
-        assert record["text"] == "hello"
-
-    def test_extract_payload_record_fallback_to_message(self, monkeypatch):
-        adapter = _make_adapter(monkeypatch)
-        payload = {"message": {"text": "hello"}}
-        record = adapter._extract_payload_record(payload)
-        assert record["text"] == "hello"
-
-
-class TestBlueBubblesGuidResolution:
-    def test_raw_guid_returned_as_is(self, monkeypatch):
-        """If target already contains ';' it's a raw GUID — return unchanged."""
-        adapter = _make_adapter(monkeypatch)
-        import asyncio
-
-        result = asyncio.get_event_loop().run_until_complete(
-            adapter._resolve_chat_guid("iMessage;-;user@example.com")
-        )
-        assert result == "iMessage;-;user@example.com"
-
-    def test_empty_target_returns_none(self, monkeypatch):
-        adapter = _make_adapter(monkeypatch)
-        import asyncio
-
-        result = asyncio.get_event_loop().run_until_complete(
-            adapter._resolve_chat_guid("")
-        )
-        assert result is None
-
-
-class TestBlueBubblesToolsetIntegration:
-    def test_toolset_exists(self):
-        from toolsets import TOOLSETS
-
-        assert "hermes-bluebubbles" in TOOLSETS
-
-    def test_toolset_in_gateway_composite(self):
-        from toolsets import TOOLSETS
-
-        gateway = TOOLSETS["hermes-gateway"]
-        assert "hermes-bluebubbles" in gateway["includes"]
-
-
-class TestBlueBubblesPromptHint:
-    def test_platform_hint_exists(self):
-        from agent.prompt_builder import PLATFORM_HINTS
-
-        assert "bluebubbles" in PLATFORM_HINTS
-        hint = PLATFORM_HINTS["bluebubbles"]
-        assert "iMessage" in hint
-        assert "plain text" in hint
-
-
-class TestBlueBubblesAttachmentDownload:
-    """Verify _download_attachment routes to the correct cache helper."""
-
-    def test_download_image_uses_image_cache(self, monkeypatch):
-        """Image MIME routes to cache_image_from_bytes."""
-        adapter = _make_adapter(monkeypatch)
-        import asyncio
-        import httpx
-
-        # Mock the HTTP client response
-        class MockResponse:
-            status_code = 200
-            content = b"\x89PNG\r\n\x1a\n"
-
-            def raise_for_status(self):
-                pass
-
-        async def mock_get(*args, **kwargs):
-            return MockResponse()
-
-        adapter.client = type("MockClient", (), {"get": mock_get})()
-
-        cached_path = None
-
-        def mock_cache_image(data, ext):
-            nonlocal cached_path
-            cached_path = f"/tmp/test_image{ext}"
-            return cached_path
-
-        monkeypatch.setattr(
-            "gateway.platforms.bluebubbles.cache_image_from_bytes",
-            mock_cache_image,
-        )
-
-        att_meta = {"mimeType": "image/png", "transferName": "photo.png"}
-        result = asyncio.get_event_loop().run_until_complete(
-            adapter._download_attachment("att-guid-123", att_meta)
-        )
-        assert result == "/tmp/test_image.png"
-
-    def test_download_audio_uses_audio_cache(self, monkeypatch):
-        """Audio MIME routes to cache_audio_from_bytes."""
-        adapter = _make_adapter(monkeypatch)
-        import asyncio
-
-        class MockResponse:
-            status_code = 200
-            content = b"fake-audio-data"
-
-            def raise_for_status(self):
-                pass
-
-        async def mock_get(*args, **kwargs):
-            return MockResponse()
-
-        adapter.client = type("MockClient", (), {"get": mock_get})()
-
-        cached_path = None
-
-        def mock_cache_audio(data, ext):
-            nonlocal cached_path
-            cached_path = f"/tmp/test_audio{ext}"
-            return cached_path
-
-        monkeypatch.setattr(
-            "gateway.platforms.bluebubbles.cache_audio_from_bytes",
-            mock_cache_audio,
-        )
-
-        att_meta = {"mimeType": "audio/mpeg", "transferName": "voice.mp3"}
-        result = asyncio.get_event_loop().run_until_complete(
-            adapter._download_attachment("att-guid-456", att_meta)
-        )
-        assert result == "/tmp/test_audio.mp3"
-
-    def test_download_document_uses_document_cache(self, monkeypatch):
-        """Non-image/audio MIME routes to cache_document_from_bytes."""
-        adapter = _make_adapter(monkeypatch)
-        import asyncio
-
-        class MockResponse:
-            status_code = 200
-            content = b"fake-doc-data"
-
-            def raise_for_status(self):
-                pass
-
-        async def mock_get(*args, **kwargs):
-            return MockResponse()
-
-        adapter.client = type("MockClient", (), {"get": mock_get})()
-
-        cached_path = None
-
-        def mock_cache_doc(data, filename):
-            nonlocal cached_path
-            cached_path = f"/tmp/{filename}"
-            return cached_path
-
-        monkeypatch.setattr(
-            "gateway.platforms.bluebubbles.cache_document_from_bytes",
-            mock_cache_doc,
-        )
-
-        att_meta = {"mimeType": "application/pdf", "transferName": "report.pdf"}
-        result = asyncio.get_event_loop().run_until_complete(
-            adapter._download_attachment("att-guid-789", att_meta)
-        )
-        assert result == "/tmp/report.pdf"
-
-    def test_download_returns_none_without_client(self, monkeypatch):
-        """No client → returns None gracefully."""
-        adapter = _make_adapter(monkeypatch)
-        adapter.client = None
-        import asyncio
-
-        result = asyncio.get_event_loop().run_until_complete(
-            adapter._download_attachment("att-guid", {"mimeType": "image/png"})
-        )
-        assert result is None
@@ -209,31 +209,14 @@ class TestIncomingDocumentHandling:
        assert "[Content of readme.md]:" in event.text
        assert "# Title" in event.text

-    @pytest.mark.asyncio
-    async def test_log_content_injected(self, adapter):
-        """.log file under 100KB should be treated as text/plain and injected."""
-        file_content = b"BLE trace line 1\nBLE trace line 2"
-
-        with _mock_aiohttp_download(file_content):
-            msg = make_message(
-                attachments=[make_attachment(filename="btsnoop_hci.log", content_type="text/plain")],
-                content="please inspect this",
-            )
-            await adapter._handle_message(msg)
-
-        event = adapter.handle_message.call_args[0][0]
-        assert "[Content of btsnoop_hci.log]:" in event.text
-        assert "BLE trace line 1" in event.text
-        assert "please inspect this" in event.text
-
    @pytest.mark.asyncio
    async def test_oversized_document_skipped(self, adapter):
-        """A document over 32MB should be skipped — media_urls stays empty."""
+        """A document over 20MB should be skipped — media_urls stays empty."""
        msg = make_message([
            make_attachment(
                filename="huge.pdf",
                content_type="application/pdf",
-                size=33 * 1024 * 1024,
+                size=25 * 1024 * 1024,
            )
        ])
        await adapter._handle_message(msg)
@@ -243,24 +226,6 @@ class TestIncomingDocumentHandling:
        # handler must still be called
        adapter.handle_message.assert_called_once()

-    @pytest.mark.asyncio
-    async def test_mid_sized_zip_under_32mb_is_cached(self, adapter):
-        """A 25MB .zip should be accepted now that Discord documents allow up to 32MB."""
-        msg = make_message([
-            make_attachment(
-                filename="bugreport.zip",
-                content_type="application/zip",
-                size=25 * 1024 * 1024,
-            )
-        ])
-
-        with _mock_aiohttp_download(b"PK\x03\x04test"):
-            await adapter._handle_message(msg)
-
-        event = adapter.handle_message.call_args[0][0]
-        assert len(event.media_urls) == 1
-        assert event.media_types == ["application/zip"]
-
    @pytest.mark.asyncio
    async def test_zip_document_cached(self, adapter):
        """A .zip file should be cached as a supported document."""
@@ -1,277 +0,0 @@
-"""Tests for Discord reply_to_mode functionality.
-
-Covers the threading behavior control for multi-chunk replies:
- "off": Never reply-reference to original message
- "first": Only first chunk uses reply reference (default)
- "all": All chunks reply-reference the original message
-"""
-import os
-import sys
-from types import SimpleNamespace
-from unittest.mock import MagicMock, AsyncMock, patch
-
-import pytest
-
-from gateway.config import PlatformConfig, GatewayConfig, Platform, _apply_env_overrides
-
-
-def _ensure_discord_mock():
-    """Install a mock discord module when discord.py isn't available."""
-    if "discord" in sys.modules and hasattr(sys.modules["discord"], "__file__"):
-        return
-
-    discord_mod = MagicMock()
-    discord_mod.Intents.default.return_value = MagicMock()
-    discord_mod.Client = MagicMock
-    discord_mod.File = MagicMock
-    discord_mod.DMChannel = type("DMChannel", (), {})
-    discord_mod.Thread = type("Thread", (), {})
-    discord_mod.ForumChannel = type("ForumChannel", (), {})
-    discord_mod.ui = SimpleNamespace(View=object, button=lambda *a, **k: (lambda fn: fn), Button=object)
-    discord_mod.ButtonStyle = SimpleNamespace(success=1, primary=2, secondary=2, danger=3, green=1, grey=2, blurple=2, red=3)
-    discord_mod.Color = SimpleNamespace(orange=lambda: 1, green=lambda: 2, blue=lambda: 3, red=lambda: 4, purple=lambda: 5)
-    discord_mod.Interaction = object
-    discord_mod.Embed = MagicMock
-    discord_mod.app_commands = SimpleNamespace(
-        describe=lambda **kwargs: (lambda fn: fn),
-        choices=lambda **kwargs: (lambda fn: fn),
-        Choice=lambda **kwargs: SimpleNamespace(**kwargs),
-    )
-
-    ext_mod = MagicMock()
-    commands_mod = MagicMock()
-    commands_mod.Bot = MagicMock
-    ext_mod.commands = commands_mod
-
-    sys.modules.setdefault("discord", discord_mod)
-    sys.modules.setdefault("discord.ext", ext_mod)
-    sys.modules.setdefault("discord.ext.commands", commands_mod)
-
-
-_ensure_discord_mock()
-
-from gateway.platforms.discord import DiscordAdapter  # noqa: E402
-
-
-@pytest.fixture()
-def adapter_factory():
-    """Factory to create DiscordAdapter with custom reply_to_mode."""
-    def create(reply_to_mode: str = "first"):
-        config = PlatformConfig(enabled=True, token="test-token", reply_to_mode=reply_to_mode)
-        return DiscordAdapter(config)
-    return create
-
-
-class TestReplyToModeConfig:
-    """Tests for reply_to_mode configuration loading."""
-
-    def test_default_mode_is_first(self, adapter_factory):
-        adapter = adapter_factory()
-        assert adapter._reply_to_mode == "first"
-
-    def test_off_mode(self, adapter_factory):
-        adapter = adapter_factory(reply_to_mode="off")
-        assert adapter._reply_to_mode == "off"
-
-    def test_first_mode(self, adapter_factory):
-        adapter = adapter_factory(reply_to_mode="first")
-        assert adapter._reply_to_mode == "first"
-
-    def test_all_mode(self, adapter_factory):
-        adapter = adapter_factory(reply_to_mode="all")
-        assert adapter._reply_to_mode == "all"
-
-    def test_invalid_mode_stored_as_is(self, adapter_factory):
-        """Invalid modes are stored but send() handles them gracefully."""
-        adapter = adapter_factory(reply_to_mode="invalid")
-        assert adapter._reply_to_mode == "invalid"
-
-    def test_none_mode_defaults_to_first(self):
-        config = PlatformConfig(enabled=True, token="test-token")
-        adapter = DiscordAdapter(config)
-        assert adapter._reply_to_mode == "first"
-
-    def test_empty_string_mode_defaults_to_first(self):
-        config = PlatformConfig(enabled=True, token="test-token", reply_to_mode="")
-        adapter = DiscordAdapter(config)
-        assert adapter._reply_to_mode == "first"
-
-
-def _make_discord_adapter(reply_to_mode: str = "first"):
-    """Create a DiscordAdapter with mocked client and channel for send() tests."""
-    config = PlatformConfig(enabled=True, token="test-token", reply_to_mode=reply_to_mode)
-    adapter = DiscordAdapter(config)
-
-    # Mock the Discord client and channel
-    mock_channel = AsyncMock()
-    ref_message = MagicMock()
-    mock_channel.fetch_message = AsyncMock(return_value=ref_message)
-
-    sent_msg = MagicMock()
-    sent_msg.id = 42
-    mock_channel.send = AsyncMock(return_value=sent_msg)
-
-    mock_client = MagicMock()
-    mock_client.get_channel = MagicMock(return_value=mock_channel)
-
-    adapter._client = mock_client
-    return adapter, mock_channel, ref_message
-
-
-class TestSendWithReplyToMode:
-    """Tests for send() method respecting reply_to_mode."""
-
-    @pytest.mark.asyncio
-    async def test_off_mode_no_reply_reference(self):
-        adapter, channel, ref_msg = _make_discord_adapter("off")
-        adapter.truncate_message = lambda content, max_len: ["chunk1", "chunk2", "chunk3"]
-
-        await adapter.send("12345", "test content", reply_to="999")
-
-        # Should never try to fetch the reference message
-        channel.fetch_message.assert_not_called()
-        # All chunks sent without reference
-        for call in channel.send.call_args_list:
-            assert call.kwargs.get("reference") is None
-
-    @pytest.mark.asyncio
-    async def test_first_mode_only_first_chunk_references(self):
-        adapter, channel, ref_msg = _make_discord_adapter("first")
-        adapter.truncate_message = lambda content, max_len: ["chunk1", "chunk2", "chunk3"]
-
-        await adapter.send("12345", "test content", reply_to="999")
-
-        # Should fetch the reference message
-        channel.fetch_message.assert_called_once_with(999)
-        calls = channel.send.call_args_list
-        assert len(calls) == 3
-        assert calls[0].kwargs.get("reference") is ref_msg
-        assert calls[1].kwargs.get("reference") is None
-        assert calls[2].kwargs.get("reference") is None
-
-    @pytest.mark.asyncio
-    async def test_all_mode_all_chunks_reference(self):
-        adapter, channel, ref_msg = _make_discord_adapter("all")
-        adapter.truncate_message = lambda content, max_len: ["chunk1", "chunk2", "chunk3"]
-
-        await adapter.send("12345", "test content", reply_to="999")
-
-        channel.fetch_message.assert_called_once_with(999)
-        calls = channel.send.call_args_list
-        assert len(calls) == 3
-        for call in calls:
-            assert call.kwargs.get("reference") is ref_msg
-
-    @pytest.mark.asyncio
-    async def test_no_reply_to_param_no_reference(self):
-        adapter, channel, ref_msg = _make_discord_adapter("all")
-        adapter.truncate_message = lambda content, max_len: ["chunk1", "chunk2"]
-
-        await adapter.send("12345", "test content", reply_to=None)
-
-        channel.fetch_message.assert_not_called()
-        for call in channel.send.call_args_list:
-            assert call.kwargs.get("reference") is None
-
-    @pytest.mark.asyncio
-    async def test_single_chunk_respects_first_mode(self):
-        adapter, channel, ref_msg = _make_discord_adapter("first")
-        adapter.truncate_message = lambda content, max_len: ["single chunk"]
-
-        await adapter.send("12345", "test", reply_to="999")
-
-        calls = channel.send.call_args_list
-        assert len(calls) == 1
-        assert calls[0].kwargs.get("reference") is ref_msg
-
-    @pytest.mark.asyncio
-    async def test_single_chunk_off_mode(self):
-        adapter, channel, ref_msg = _make_discord_adapter("off")
-        adapter.truncate_message = lambda content, max_len: ["single chunk"]
-
-        await adapter.send("12345", "test", reply_to="999")
-
-        channel.fetch_message.assert_not_called()
-        calls = channel.send.call_args_list
-        assert len(calls) == 1
-        assert calls[0].kwargs.get("reference") is None
-
-    @pytest.mark.asyncio
-    async def test_invalid_mode_falls_back_to_first_behavior(self):
-        """Invalid mode behaves like 'first' — only first chunk gets reference."""
-        adapter, channel, ref_msg = _make_discord_adapter("banana")
-        adapter.truncate_message = lambda content, max_len: ["chunk1", "chunk2"]
-
-        await adapter.send("12345", "test", reply_to="999")
-
-        calls = channel.send.call_args_list
-        assert len(calls) == 2
-        assert calls[0].kwargs.get("reference") is ref_msg
-        assert calls[1].kwargs.get("reference") is None
-
-
-class TestConfigSerialization:
-    """Tests for reply_to_mode serialization (shared with Telegram)."""
-
-    def test_to_dict_includes_reply_to_mode(self):
-        config = PlatformConfig(enabled=True, token="test", reply_to_mode="all")
-        result = config.to_dict()
-        assert result["reply_to_mode"] == "all"
-
-    def test_from_dict_loads_reply_to_mode(self):
-        data = {"enabled": True, "token": "***", "reply_to_mode": "off"}
-        config = PlatformConfig.from_dict(data)
-        assert config.reply_to_mode == "off"
-
-    def test_from_dict_defaults_to_first(self):
-        data = {"enabled": True, "token": "***"}
-        config = PlatformConfig.from_dict(data)
-        assert config.reply_to_mode == "first"
-
-
-class TestEnvVarOverride:
-    """Tests for DISCORD_REPLY_TO_MODE environment variable override."""
-
-    def _make_config(self):
-        config = GatewayConfig()
-        config.platforms[Platform.DISCORD] = PlatformConfig(enabled=True, token="test")
-        return config
-
-    def test_env_var_sets_off_mode(self):
-        config = self._make_config()
-        with patch.dict(os.environ, {"DISCORD_REPLY_TO_MODE": "off"}, clear=False):
-            _apply_env_overrides(config)
-        assert config.platforms[Platform.DISCORD].reply_to_mode == "off"
-
-    def test_env_var_sets_all_mode(self):
-        config = self._make_config()
-        with patch.dict(os.environ, {"DISCORD_REPLY_TO_MODE": "all"}, clear=False):
-            _apply_env_overrides(config)
-        assert config.platforms[Platform.DISCORD].reply_to_mode == "all"
-
-    def test_env_var_case_insensitive(self):
-        config = self._make_config()
-        with patch.dict(os.environ, {"DISCORD_REPLY_TO_MODE": "ALL"}, clear=False):
-            _apply_env_overrides(config)
-        assert config.platforms[Platform.DISCORD].reply_to_mode == "all"
-
-    def test_env_var_invalid_value_ignored(self):
-        config = self._make_config()
-        with patch.dict(os.environ, {"DISCORD_REPLY_TO_MODE": "banana"}, clear=False):
-            _apply_env_overrides(config)
-        assert config.platforms[Platform.DISCORD].reply_to_mode == "first"
-
-    def test_env_var_empty_value_ignored(self):
-        config = self._make_config()
-        with patch.dict(os.environ, {"DISCORD_REPLY_TO_MODE": ""}, clear=False):
-            _apply_env_overrides(config)
-        assert config.platforms[Platform.DISCORD].reply_to_mode == "first"
-
-    def test_env_var_creates_platform_config_if_missing(self):
-        """DISCORD_REPLY_TO_MODE creates PlatformConfig even without DISCORD_BOT_TOKEN."""
-        config = GatewayConfig()
-        assert Platform.DISCORD not in config.platforms
-        with patch.dict(os.environ, {"DISCORD_REPLY_TO_MODE": "off"}, clear=False):
-            _apply_env_overrides(config)
-        assert Platform.DISCORD in config.platforms
-        assert config.platforms[Platform.DISCORD].reply_to_mode == "off"
@@ -1,432 +0,0 @@
-"""Tests for Feishu interactive card approval buttons."""
-
-import asyncio
-import json
-import os
-import sys
-from pathlib import Path
-from types import SimpleNamespace
-from unittest.mock import AsyncMock, MagicMock, Mock, patch
-
-import pytest
-
-# ---------------------------------------------------------------------------
-# Ensure the repo root is importable
-# ---------------------------------------------------------------------------
-_repo = str(Path(__file__).resolve().parents[2])
-if _repo not in sys.path:
-    sys.path.insert(0, _repo)
-
-
-# ---------------------------------------------------------------------------
-# Minimal Feishu mock so FeishuAdapter can be imported without lark-oapi
-# ---------------------------------------------------------------------------
-def _ensure_feishu_mocks():
-    """Provide stubs for lark-oapi / aiohttp.web so the import succeeds."""
-    if "lark_oapi" not in sys.modules:
-        mod = MagicMock()
-        for name in (
-            "lark_oapi", "lark_oapi.api.im.v1",
-            "lark_oapi.event", "lark_oapi.event.callback_type",
-        ):
-            sys.modules.setdefault(name, mod)
-    if "aiohttp" not in sys.modules:
-        aio = MagicMock()
-        sys.modules.setdefault("aiohttp", aio)
-        sys.modules.setdefault("aiohttp.web", aio.web)
-
-
-_ensure_feishu_mocks()
-
-from gateway.config import PlatformConfig
-from gateway.platforms.feishu import FeishuAdapter
-
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-def _make_adapter() -> FeishuAdapter:
-    """Create a FeishuAdapter with mocked internals."""
-    config = PlatformConfig(enabled=True)
-    adapter = FeishuAdapter(config)
-    adapter._client = MagicMock()
-    return adapter
-
-
-def _make_card_action_data(
-    action_value: dict,
-    chat_id: str = "oc_12345",
-    open_id: str = "ou_user1",
-    token: str = "tok_abc",
-) -> SimpleNamespace:
-    """Create a mock Feishu card action callback data object."""
-    return SimpleNamespace(
-        event=SimpleNamespace(
-            token=token,
-            context=SimpleNamespace(open_chat_id=chat_id),
-            operator=SimpleNamespace(open_id=open_id),
-            action=SimpleNamespace(
-                tag="button",
-                value=action_value,
-            ),
-        ),
-    )
-
-
-# ===========================================================================
-# send_exec_approval — interactive card with buttons
-# ===========================================================================
-
-class TestFeishuExecApproval:
-    """Test send_exec_approval sends an interactive card."""
-
-    @pytest.mark.asyncio
-    async def test_sends_interactive_card(self):
-        adapter = _make_adapter()
-
-        mock_response = SimpleNamespace(
-            success=lambda: True,
-            data=SimpleNamespace(message_id="msg_001"),
-        )
-        with patch.object(
-            adapter, "_feishu_send_with_retry", new_callable=AsyncMock,
-            return_value=mock_response,
-        ) as mock_send:
-            result = await adapter.send_exec_approval(
-                chat_id="oc_12345",
-                command="rm -rf /important",
-                session_key="agent:main:feishu:group:oc_12345",
-                description="dangerous deletion",
-            )
-
-        assert result.success is True
-        assert result.message_id == "msg_001"
-
-        mock_send.assert_called_once()
-        kwargs = mock_send.call_args[1]
-        assert kwargs["chat_id"] == "oc_12345"
-        assert kwargs["msg_type"] == "interactive"
-
-        # Verify card payload contains the command and buttons
-        card = json.loads(kwargs["payload"])
-        assert card["header"]["template"] == "orange"
-        assert "rm -rf /important" in card["elements"][0]["content"]
-        assert "dangerous deletion" in card["elements"][0]["content"]
-
-        # Check buttons
-        actions = card["elements"][1]["actions"]
-        assert len(actions) == 4
-        action_names = [a["value"]["hermes_action"] for a in actions]
-        assert action_names == [
-            "approve_once", "approve_session", "approve_always", "deny"
-        ]
-
-    @pytest.mark.asyncio
-    async def test_stores_approval_state(self):
-        adapter = _make_adapter()
-
-        mock_response = SimpleNamespace(
-            success=lambda: True,
-            data=SimpleNamespace(message_id="msg_002"),
-        )
-        with patch.object(
-            adapter, "_feishu_send_with_retry", new_callable=AsyncMock,
-            return_value=mock_response,
-        ):
-            await adapter.send_exec_approval(
-                chat_id="oc_12345",
-                command="echo test",
-                session_key="my-session-key",
-            )
-
-        assert len(adapter._approval_state) == 1
-        approval_id = list(adapter._approval_state.keys())[0]
-        state = adapter._approval_state[approval_id]
-        assert state["session_key"] == "my-session-key"
-        assert state["message_id"] == "msg_002"
-        assert state["chat_id"] == "oc_12345"
-
-    @pytest.mark.asyncio
-    async def test_not_connected(self):
-        adapter = _make_adapter()
-        adapter._client = None
-        result = await adapter.send_exec_approval(
-            chat_id="oc_12345", command="ls", session_key="s"
-        )
-        assert result.success is False
-
-    @pytest.mark.asyncio
-    async def test_truncates_long_command(self):
-        adapter = _make_adapter()
-
-        mock_response = SimpleNamespace(
-            success=lambda: True,
-            data=SimpleNamespace(message_id="msg_003"),
-        )
-        with patch.object(
-            adapter, "_feishu_send_with_retry", new_callable=AsyncMock,
-            return_value=mock_response,
-        ) as mock_send:
-            long_cmd = "x" * 5000
-            await adapter.send_exec_approval(
-                chat_id="oc_12345", command=long_cmd, session_key="s"
-            )
-
-        card = json.loads(mock_send.call_args[1]["payload"])
-        content = card["elements"][0]["content"]
-        assert "..." in content
-        assert len(content) < 5000
-
-    @pytest.mark.asyncio
-    async def test_multiple_approvals_get_unique_ids(self):
-        adapter = _make_adapter()
-
-        mock_response = SimpleNamespace(
-            success=lambda: True,
-            data=SimpleNamespace(message_id="msg_x"),
-        )
-        with patch.object(
-            adapter, "_feishu_send_with_retry", new_callable=AsyncMock,
-            return_value=mock_response,
-        ):
-            await adapter.send_exec_approval(
-                chat_id="oc_1", command="cmd1", session_key="s1"
-            )
-            await adapter.send_exec_approval(
-                chat_id="oc_2", command="cmd2", session_key="s2"
-            )
-
-        assert len(adapter._approval_state) == 2
-        ids = list(adapter._approval_state.keys())
-        assert ids[0] != ids[1]
-
-
-# ===========================================================================
-# _handle_card_action_event — approval button clicks
-# ===========================================================================
-
-class TestFeishuApprovalCallback:
-    """Test the approval intercept in _handle_card_action_event."""
-
-    @pytest.mark.asyncio
-    async def test_resolves_approval_on_click(self):
-        adapter = _make_adapter()
-        adapter._approval_state[1] = {
-            "session_key": "agent:main:feishu:group:oc_12345",
-            "message_id": "msg_001",
-            "chat_id": "oc_12345",
-        }
-
-        data = _make_card_action_data(
-            action_value={"hermes_action": "approve_once", "approval_id": 1},
-        )
-
-        with (
-            patch.object(
-                adapter, "_resolve_sender_profile", new_callable=AsyncMock,
-                return_value={"user_id": "ou_user1", "user_name": "Norbert", "user_id_alt": None},
-            ),
-            patch.object(adapter, "_update_approval_card", new_callable=AsyncMock) as mock_update,
-            patch("tools.approval.resolve_gateway_approval", return_value=1) as mock_resolve,
-        ):
-            await adapter._handle_card_action_event(data)
-
-        mock_resolve.assert_called_once_with("agent:main:feishu:group:oc_12345", "once")
-        mock_update.assert_called_once_with("msg_001", "Approved once", "Norbert", "once")
-
-        # State should be cleaned up
-        assert 1 not in adapter._approval_state
-
-    @pytest.mark.asyncio
-    async def test_deny_button(self):
-        adapter = _make_adapter()
-        adapter._approval_state[2] = {
-            "session_key": "some-session",
-            "message_id": "msg_002",
-            "chat_id": "oc_12345",
-        }
-
-        data = _make_card_action_data(
-            action_value={"hermes_action": "deny", "approval_id": 2},
-            token="tok_deny",
-        )
-
-        with (
-            patch.object(
-                adapter, "_resolve_sender_profile", new_callable=AsyncMock,
-                return_value={"user_id": "ou_alice", "user_name": "Alice", "user_id_alt": None},
-            ),
-            patch.object(adapter, "_update_approval_card", new_callable=AsyncMock) as mock_update,
-            patch("tools.approval.resolve_gateway_approval", return_value=1) as mock_resolve,
-        ):
-            await adapter._handle_card_action_event(data)
-
-        mock_resolve.assert_called_once_with("some-session", "deny")
-        mock_update.assert_called_once_with("msg_002", "Denied", "Alice", "deny")
-
-    @pytest.mark.asyncio
-    async def test_session_approval(self):
-        adapter = _make_adapter()
-        adapter._approval_state[3] = {
-            "session_key": "sess-3",
-            "message_id": "msg_003",
-            "chat_id": "oc_99",
-        }
-
-        data = _make_card_action_data(
-            action_value={"hermes_action": "approve_session", "approval_id": 3},
-            token="tok_ses",
-        )
-
-        with (
-            patch.object(
-                adapter, "_resolve_sender_profile", new_callable=AsyncMock,
-                return_value={"user_id": "ou_u", "user_name": "Bob", "user_id_alt": None},
-            ),
-            patch.object(adapter, "_update_approval_card", new_callable=AsyncMock) as mock_update,
-            patch("tools.approval.resolve_gateway_approval", return_value=1) as mock_resolve,
-        ):
-            await adapter._handle_card_action_event(data)
-
-        mock_resolve.assert_called_once_with("sess-3", "session")
-        mock_update.assert_called_once_with("msg_003", "Approved for session", "Bob", "session")
-
-    @pytest.mark.asyncio
-    async def test_always_approval(self):
-        adapter = _make_adapter()
-        adapter._approval_state[4] = {
-            "session_key": "sess-4",
-            "message_id": "msg_004",
-            "chat_id": "oc_55",
-        }
-
-        data = _make_card_action_data(
-            action_value={"hermes_action": "approve_always", "approval_id": 4},
-            token="tok_alw",
-        )
-
-        with (
-            patch.object(
-                adapter, "_resolve_sender_profile", new_callable=AsyncMock,
-                return_value={"user_id": "ou_u", "user_name": "Carol", "user_id_alt": None},
-            ),
-            patch.object(adapter, "_update_approval_card", new_callable=AsyncMock),
-            patch("tools.approval.resolve_gateway_approval", return_value=1) as mock_resolve,
-        ):
-            await adapter._handle_card_action_event(data)
-
-        mock_resolve.assert_called_once_with("sess-4", "always")
-
-    @pytest.mark.asyncio
-    async def test_already_resolved_drops_silently(self):
-        adapter = _make_adapter()
-        # No state for approval_id 99 — already resolved
-
-        data = _make_card_action_data(
-            action_value={"hermes_action": "approve_once", "approval_id": 99},
-            token="tok_gone",
-        )
-
-        with patch("tools.approval.resolve_gateway_approval") as mock_resolve:
-            await adapter._handle_card_action_event(data)
-
-        # Should NOT resolve — already handled
-        mock_resolve.assert_not_called()
-
-    @pytest.mark.asyncio
-    async def test_non_approval_actions_route_normally(self):
-        """Non-approval card actions should still become synthetic commands."""
-        adapter = _make_adapter()
-
-        data = _make_card_action_data(
-            action_value={"custom_action": "something_else"},
-            token="tok_normal",
-        )
-
-        with (
-            patch.object(
-                adapter, "_resolve_sender_profile", new_callable=AsyncMock,
-                return_value={"user_id": "ou_u", "user_name": "Dave", "user_id_alt": None},
-            ),
-            patch.object(adapter, "get_chat_info", new_callable=AsyncMock, return_value={"name": "Test Chat"}),
-            patch.object(adapter, "_handle_message_with_guards", new_callable=AsyncMock) as mock_handle,
-            patch("tools.approval.resolve_gateway_approval") as mock_resolve,
-        ):
-            await adapter._handle_card_action_event(data)
-
-        # Should NOT resolve any approval
-        mock_resolve.assert_not_called()
-        # Should have routed as synthetic command
-        mock_handle.assert_called_once()
-        event = mock_handle.call_args[0][0]
-        assert "/card button" in event.text
-
-
-# ===========================================================================
-# _update_approval_card — card replacement after resolution
-# ===========================================================================
-
-class TestFeishuUpdateApprovalCard:
-    """Test the card update after approval resolution."""
-
-    @pytest.mark.asyncio
-    async def test_updates_card_on_approve(self):
-        adapter = _make_adapter()
-
-        mock_update = AsyncMock()
-        adapter._client.im.v1.message.update = MagicMock()
-
-        with patch("asyncio.to_thread", new_callable=AsyncMock) as mock_thread:
-            await adapter._update_approval_card(
-                "msg_001", "Approved once", "Norbert", "once"
-            )
-
-        mock_thread.assert_called_once()
-        # Verify the update request was built
-        call_args = mock_thread.call_args
-        assert call_args[0][0] == adapter._client.im.v1.message.update
-
-    @pytest.mark.asyncio
-    async def test_updates_card_on_deny(self):
-        adapter = _make_adapter()
-
-        with patch("asyncio.to_thread", new_callable=AsyncMock) as mock_thread:
-            await adapter._update_approval_card(
-                "msg_002", "Denied", "Alice", "deny"
-            )
-
-        mock_thread.assert_called_once()
-
-    @pytest.mark.asyncio
-    async def test_skips_update_when_not_connected(self):
-        adapter = _make_adapter()
-        adapter._client = None
-
-        with patch("asyncio.to_thread", new_callable=AsyncMock) as mock_thread:
-            await adapter._update_approval_card(
-                "msg_001", "Approved", "Bob", "once"
-            )
-
-        mock_thread.assert_not_called()
-
-    @pytest.mark.asyncio
-    async def test_skips_update_when_no_message_id(self):
-        adapter = _make_adapter()
-
-        with patch("asyncio.to_thread", new_callable=AsyncMock) as mock_thread:
-            await adapter._update_approval_card(
-                "", "Approved", "Bob", "once"
-            )
-
-        mock_thread.assert_not_called()
-
-    @pytest.mark.asyncio
-    async def test_swallows_update_errors(self):
-        adapter = _make_adapter()
-
-        with patch("asyncio.to_thread", new_callable=AsyncMock, side_effect=Exception("API error")):
-            # Should not raise
-            await adapter._update_approval_card(
-                "msg_001", "Approved", "Bob", "once"
-            )
@@ -1,315 +0,0 @@
-"""Tests for staged inactivity timeout in gateway agent runs.
-
-Tests cover:
- Warning fires once when inactivity reaches gateway_timeout_warning threshold
- Warning does not fire when gateway_timeout is 0 (unlimited)
- Warning fires only once per run, not on every poll
- Full timeout still fires at gateway_timeout threshold
- Warning respects HERMES_AGENT_TIMEOUT_WARNING env var
- Warning disabled when gateway_timeout_warning is 0
-"""
-
-import concurrent.futures
-import os
-import sys
-import time
-from pathlib import Path
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-sys.path.insert(0, str(Path(__file__).parent.parent.parent))
-
-
-class FakeAgent:
-    """Mock agent with controllable activity summary for timeout tests."""
-
-    def __init__(self, idle_seconds=0.0, activity_desc="tool_call",
-                 current_tool=None, api_call_count=5, max_iterations=90):
-        self._idle_seconds = idle_seconds
-        self._activity_desc = activity_desc
-        self._current_tool = current_tool
-        self._api_call_count = api_call_count
-        self._max_iterations = max_iterations
-        self._interrupted = False
-        self._interrupt_msg = None
-
-    def get_activity_summary(self):
-        return {
-            "last_activity_ts": time.time() - self._idle_seconds,
-            "last_activity_desc": self._activity_desc,
-            "seconds_since_activity": self._idle_seconds,
-            "current_tool": self._current_tool,
-            "api_call_count": self._api_call_count,
-            "max_iterations": self._max_iterations,
-        }
-
-    def interrupt(self, msg):
-        self._interrupted = True
-        self._interrupt_msg = msg
-
-    def run_conversation(self, prompt):
-        return {"final_response": "Done", "messages": []}
-
-
-class SlowFakeAgent(FakeAgent):
-    """Agent that runs for a while, then goes idle."""
-
-    def __init__(self, run_duration=0.5, idle_after=None, **kwargs):
-        super().__init__(**kwargs)
-        self._run_duration = run_duration
-        self._idle_after = idle_after
-        self._start_time = None
-
-    def get_activity_summary(self):
-        summary = super().get_activity_summary()
-        if self._idle_after is not None and self._start_time:
-            elapsed = time.time() - self._start_time
-            if elapsed > self._idle_after:
-                idle_time = elapsed - self._idle_after
-                summary["seconds_since_activity"] = idle_time
-                summary["last_activity_desc"] = "api_call_streaming"
-            else:
-                summary["seconds_since_activity"] = 0.0
-        return summary
-
-    def run_conversation(self, prompt):
-        self._start_time = time.time()
-        time.sleep(self._run_duration)
-        return {"final_response": "Completed after work", "messages": []}
-
-
-class TestStagedInactivityWarning:
-    """Test the staged inactivity warning before full timeout."""
-
-    def test_warning_fires_once_before_timeout(self):
-        """Warning fires when inactivity reaches warning threshold."""
-        agent = SlowFakeAgent(
-            run_duration=10.0,
-            idle_after=0.1,
-            activity_desc="api_call_streaming",
-        )
-
-        _agent_timeout = 20.0
-        _agent_warning = 5.0
-        _POLL_INTERVAL = 0.1
-
-        pool = concurrent.futures.ThreadPoolExecutor(max_workers=1)
-        future = pool.submit(agent.run_conversation, "test prompt")
-        _inactivity_timeout = False
-        _warning_fired = False
-        _warning_send_count = 0
-
-        while True:
-            done, _ = concurrent.futures.wait({future}, timeout=_POLL_INTERVAL)
-            if done:
-                result = future.result()
-                break
-            _idle_secs = 0.0
-            if hasattr(agent, "get_activity_summary"):
-                try:
-                    _act = agent.get_activity_summary()
-                    _idle_secs = _act.get("seconds_since_activity", 0.0)
-                except Exception:
-                    pass
-            if (not _warning_fired and _agent_warning > 0
-                    and _idle_secs >= _agent_warning):
-                _warning_fired = True
-                _warning_send_count += 1
-            if _idle_secs >= _agent_timeout:
-                _inactivity_timeout = True
-                break
-
-        pool.shutdown(wait=False, cancel_futures=True)
-
-        assert _warning_fired
-        assert _warning_send_count == 1
-        assert not _inactivity_timeout
-
-    def test_warning_disabled_when_zero(self):
-        """No warning fires when gateway_timeout_warning is 0."""
-        agent = SlowFakeAgent(
-            run_duration=5.0,
-            idle_after=0.1,
-        )
-
-        _agent_timeout = 20.0
-        _agent_warning = 0.0
-        _POLL_INTERVAL = 0.1
-
-        pool = concurrent.futures.ThreadPoolExecutor(max_workers=1)
-        future = pool.submit(agent.run_conversation, "test")
-        _warning_fired = False
-
-        while True:
-            done, _ = concurrent.futures.wait({future}, timeout=_POLL_INTERVAL)
-            if done:
-                future.result()
-                break
-            _idle_secs = 0.0
-            if hasattr(agent, "get_activity_summary"):
-                try:
-                    _act = agent.get_activity_summary()
-                    _idle_secs = _act.get("seconds_since_activity", 0.0)
-                except Exception:
-                    pass
-            if (not _warning_fired and _agent_warning > 0
-                    and _idle_secs >= _agent_warning):
-                _warning_fired = True
-            if _idle_secs >= _agent_timeout:
-                break
-
-        pool.shutdown(wait=False, cancel_futures=True)
-        assert not _warning_fired
-
-    def test_warning_fires_only_once(self):
-        """Warning fires exactly once even if agent remains idle."""
-        agent = SlowFakeAgent(
-            run_duration=10.0,
-            idle_after=0.05,
-        )
-
-        _agent_timeout = 20.0
-        _agent_warning = 0.2
-        _POLL_INTERVAL = 0.05
-
-        pool = concurrent.futures.ThreadPoolExecutor(max_workers=1)
-        future = pool.submit(agent.run_conversation, "test")
-        _warning_count = 0
-
-        while True:
-            done, _ = concurrent.futures.wait({future}, timeout=_POLL_INTERVAL)
-            if done:
-                future.result()
-                break
-            _idle_secs = 0.0
-            if hasattr(agent, "get_activity_summary"):
-                try:
-                    _act = agent.get_activity_summary()
-                    _idle_secs = _act.get("seconds_since_activity", 0.0)
-                except Exception:
-                    pass
-            if (not _warning_count and _agent_warning > 0
-                    and _idle_secs >= _agent_warning):
-                _warning_count += 1
-            if _idle_secs >= _agent_timeout:
-                break
-
-        pool.shutdown(wait=False, cancel_futures=True)
-        assert _warning_count == 1
-
-    def test_full_timeout_still_fires_after_warning(self):
-        """Full timeout fires even after warning was sent."""
-        agent = SlowFakeAgent(
-            run_duration=15.0,
-            idle_after=0.1,
-            activity_desc="waiting for provider response (streaming)",
-        )
-
-        _agent_timeout = 1.0
-        _agent_warning = 0.3
-        _POLL_INTERVAL = 0.05
-
-        pool = concurrent.futures.ThreadPoolExecutor(max_workers=1)
-        future = pool.submit(agent.run_conversation, "test")
-        _inactivity_timeout = False
-        _warning_fired = False
-
-        while True:
-            done, _ = concurrent.futures.wait({future}, timeout=_POLL_INTERVAL)
-            if done:
-                future.result()
-                break
-            _idle_secs = 0.0
-            if hasattr(agent, "get_activity_summary"):
-                try:
-                    _act = agent.get_activity_summary()
-                    _idle_secs = _act.get("seconds_since_activity", 0.0)
-                except Exception:
-                    pass
-            if (not _warning_fired and _agent_warning > 0
-                    and _idle_secs >= _agent_warning):
-                _warning_fired = True
-            if _idle_secs >= _agent_timeout:
-                _inactivity_timeout = True
-                break
-
-        pool.shutdown(wait=False, cancel_futures=True)
-        assert _warning_fired
-        assert _inactivity_timeout
-
-    def test_warning_env_var_respected(self, monkeypatch):
-        """HERMES_AGENT_TIMEOUT_WARNING env var is parsed correctly."""
-        monkeypatch.setenv("HERMES_AGENT_TIMEOUT_WARNING", "600")
-        _warning = float(os.getenv("HERMES_AGENT_TIMEOUT_WARNING", 900))
-        assert _warning == 600.0
-
-    def test_warning_zero_means_disabled(self, monkeypatch):
-        """HERMES_AGENT_TIMEOUT_WARNING=0 disables the warning."""
-        monkeypatch.setenv("HERMES_AGENT_TIMEOUT_WARNING", "0")
-        _raw = float(os.getenv("HERMES_AGENT_TIMEOUT_WARNING", 900))
-        _warning = _raw if _raw > 0 else None
-        assert _warning is None
-
-    def test_unlimited_timeout_no_warning(self):
-        """When timeout is unlimited (0), no warning fires either."""
-        agent = SlowFakeAgent(
-            run_duration=0.5,
-            idle_after=0.0,
-        )
-
-        _agent_timeout = None
-        _agent_warning = 5.0
-        _POLL_INTERVAL = 0.05
-
-        pool = concurrent.futures.ThreadPoolExecutor(max_workers=1)
-        future = pool.submit(agent.run_conversation, "test")
-
-        result = future.result(timeout=2.0)
-        pool.shutdown(wait=False)
-
-        assert result["final_response"] == "Completed after work"
-
-
-class TestWarningThresholdBelowTimeout:
-    """Test that warning threshold must be less than timeout threshold."""
-
-    def test_warning_at_half_timeout(self):
-        """Warning fires at half the timeout duration."""
-        agent = SlowFakeAgent(
-            run_duration=10.0,
-            idle_after=0.1,
-            activity_desc="receiving stream response",
-        )
-
-        _agent_timeout = 2.0
-        _agent_warning = 1.0
-        _POLL_INTERVAL = 0.05
-
-        pool = concurrent.futures.ThreadPoolExecutor(max_workers=1)
-        future = pool.submit(agent.run_conversation, "test")
-        _warning_fired = False
-        _timeout_fired = False
-
-        while True:
-            done, _ = concurrent.futures.wait({future}, timeout=_POLL_INTERVAL)
-            if done:
-                future.result()
-                break
-            _idle_secs = 0.0
-            if hasattr(agent, "get_activity_summary"):
-                try:
-                    _act = agent.get_activity_summary()
-                    _idle_secs = _act.get("seconds_since_activity", 0.0)
-                except Exception:
-                    pass
-            if (not _warning_fired and _agent_warning > 0
-                    and _idle_secs >= _agent_warning):
-                _warning_fired = True
-            if _idle_secs >= _agent_timeout:
-                _timeout_fired = True
-                break
-
-        pool.shutdown(wait=False, cancel_futures=True)
-        assert _warning_fired
-        assert _timeout_fired
@@ -1,226 +0,0 @@
-"""Tests that internal synthetic events (e.g. background process completion)
-bypass user authorization and do not trigger DM pairing.
-
-Regression test for the bug where ``_run_process_watcher`` with
-``notify_on_complete=True`` injected a ``MessageEvent`` without ``user_id``,
-causing ``_is_user_authorized`` to reject it and the gateway to send a
-pairing code to the chat.
-"""
-
-import asyncio
-from types import SimpleNamespace
-from unittest.mock import AsyncMock, patch
-
-import pytest
-
-from gateway.config import GatewayConfig, Platform
-from gateway.platforms.base import MessageEvent
-from gateway.run import GatewayRunner
-from gateway.session import SessionSource
-
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-class _FakeRegistry:
-    """Return pre-canned sessions, then None once exhausted."""
-
-    def __init__(self, sessions):
-        self._sessions = list(sessions)
-
-    def get(self, session_id):
-        if self._sessions:
-            return self._sessions.pop(0)
-        return None
-
-
-def _build_runner(monkeypatch, tmp_path) -> GatewayRunner:
-    """Create a GatewayRunner with notifications set to 'all'."""
-    (tmp_path / "config.yaml").write_text(
-        "display:\n  background_process_notifications: all\n",
-        encoding="utf-8",
-    )
-
-    import gateway.run as gateway_run
-
-    monkeypatch.setattr(gateway_run, "_hermes_home", tmp_path)
-
-    runner = GatewayRunner(GatewayConfig())
-    adapter = SimpleNamespace(send=AsyncMock(), handle_message=AsyncMock())
-    runner.adapters[Platform.DISCORD] = adapter
-    return runner
-
-
-def _watcher_dict_with_notify():
-    return {
-        "session_id": "proc_test_internal",
-        "check_interval": 0,
-        "session_key": "agent:main:discord:dm:123",
-        "platform": "discord",
-        "chat_id": "123",
-        "thread_id": "",
-        "notify_on_complete": True,
-    }
-
-
-# ---------------------------------------------------------------------------
-# Tests
-# ---------------------------------------------------------------------------
-
-@pytest.mark.asyncio
-async def test_notify_on_complete_sets_internal_flag(monkeypatch, tmp_path):
-    """Synthetic completion event must have internal=True."""
-    import tools.process_registry as pr_module
-
-    sessions = [
-        SimpleNamespace(
-            output_buffer="done\n", exited=True, exit_code=0, command="echo test"
-        ),
-    ]
-    monkeypatch.setattr(pr_module, "process_registry", _FakeRegistry(sessions))
-
-    async def _instant_sleep(*_a, **_kw):
-        pass
-    monkeypatch.setattr(asyncio, "sleep", _instant_sleep)
-
-    runner = _build_runner(monkeypatch, tmp_path)
-    adapter = runner.adapters[Platform.DISCORD]
-
-    await runner._run_process_watcher(_watcher_dict_with_notify())
-
-    assert adapter.handle_message.await_count == 1
-    event = adapter.handle_message.await_args.args[0]
-    assert isinstance(event, MessageEvent)
-    assert event.internal is True, "Synthetic completion event must be marked internal"
-
-
-@pytest.mark.asyncio
-async def test_internal_event_bypasses_authorization(monkeypatch, tmp_path):
-    """An internal event should skip _is_user_authorized entirely."""
-    import gateway.run as gateway_run
-
-    monkeypatch.setattr(gateway_run, "_hermes_home", tmp_path)
-    (tmp_path / "config.yaml").write_text("", encoding="utf-8")
-
-    runner = GatewayRunner(GatewayConfig())
-
-    # Create an internal event with no user_id (simulates the bug scenario)
-    source = SessionSource(
-        platform=Platform.DISCORD,
-        chat_id="123",
-        chat_type="dm",
-    )
-    event = MessageEvent(
-        text="[SYSTEM: Background process completed]",
-        source=source,
-        internal=True,
-    )
-
-    # Track if _is_user_authorized is called
-    auth_called = False
-    original_auth = GatewayRunner._is_user_authorized
-
-    def tracking_auth(self, src):
-        nonlocal auth_called
-        auth_called = True
-        return original_auth(self, src)
-
-    monkeypatch.setattr(GatewayRunner, "_is_user_authorized", tracking_auth)
-
-    # _handle_message will proceed past auth check and eventually fail on
-    # downstream logic. We just need to verify auth is skipped.
-    try:
-        await runner._handle_message(event)
-    except Exception:
-        pass  # Expected — downstream code needs more setup
-
-    assert not auth_called, (
-        "_is_user_authorized should NOT be called for internal events"
-    )
-
-
-@pytest.mark.asyncio
-async def test_internal_event_does_not_trigger_pairing(monkeypatch, tmp_path):
-    """An internal event with no user_id must not generate a pairing code."""
-    import gateway.run as gateway_run
-
-    monkeypatch.setattr(gateway_run, "_hermes_home", tmp_path)
-    (tmp_path / "config.yaml").write_text("", encoding="utf-8")
-
-    runner = GatewayRunner(GatewayConfig())
-    # Add adapter so pairing would have somewhere to send
-    adapter = SimpleNamespace(send=AsyncMock())
-    runner.adapters[Platform.DISCORD] = adapter
-
-    source = SessionSource(
-        platform=Platform.DISCORD,
-        chat_id="123",
-        chat_type="dm",  # DM would normally trigger pairing
-    )
-    event = MessageEvent(
-        text="[SYSTEM: Background process completed]",
-        source=source,
-        internal=True,
-    )
-
-    # Track pairing code generation
-    generate_called = False
-    original_generate = runner.pairing_store.generate_code
-
-    def tracking_generate(*args, **kwargs):
-        nonlocal generate_called
-        generate_called = True
-        return original_generate(*args, **kwargs)
-
-    runner.pairing_store.generate_code = tracking_generate
-
-    try:
-        await runner._handle_message(event)
-    except Exception:
-        pass  # Expected — downstream code needs more setup
-
-    assert not generate_called, (
-        "Pairing code should NOT be generated for internal events"
-    )
-
-
-@pytest.mark.asyncio
-async def test_non_internal_event_without_user_triggers_pairing(monkeypatch, tmp_path):
-    """Verify the normal (non-internal) path still triggers pairing for unknown users."""
-    import gateway.run as gateway_run
-
-    monkeypatch.setattr(gateway_run, "_hermes_home", tmp_path)
-    (tmp_path / "config.yaml").write_text("", encoding="utf-8")
-
-    # Clear env vars that could let all users through (loaded by
-    # module-level dotenv in gateway/run.py from the real ~/.hermes/.env).
-    monkeypatch.delenv("DISCORD_ALLOW_ALL_USERS", raising=False)
-    monkeypatch.delenv("DISCORD_ALLOWED_USERS", raising=False)
-    monkeypatch.delenv("GATEWAY_ALLOW_ALL_USERS", raising=False)
-    monkeypatch.delenv("GATEWAY_ALLOWED_USERS", raising=False)
-
-    runner = GatewayRunner(GatewayConfig())
-    adapter = SimpleNamespace(send=AsyncMock())
-    runner.adapters[Platform.DISCORD] = adapter
-
-    source = SessionSource(
-        platform=Platform.DISCORD,
-        chat_id="123",
-        chat_type="dm",
-        user_id="unknown_user_999",
-    )
-    # Normal event (not internal)
-    event = MessageEvent(
-        text="hello",
-        source=source,
-        internal=False,
-    )
-
-    result = await runner._handle_message(event)
-
-    # Should return None (unauthorized) and send pairing message
-    assert result is None
-    assert adapter.send.await_count == 1
-    sent_text = adapter.send.await_args.args[1]
-    assert "don't recognize you" in sent_text
@@ -38,11 +38,10 @@ def _make_timeout_error() -> httpx.TimeoutException:
 # cache_image_from_url (base.py)
 # ---------------------------------------------------------------------------

-@patch("tools.url_safety.is_safe_url", return_value=True)
 class TestCacheImageFromUrl:
    """Tests for gateway.platforms.base.cache_image_from_url"""

-    def test_success_on_first_attempt(self, _mock_safe, tmp_path, monkeypatch):
+    def test_success_on_first_attempt(self, tmp_path, monkeypatch):
        """A clean 200 response caches the image and returns a path."""
        monkeypatch.setattr("gateway.platforms.base.IMAGE_CACHE_DIR", tmp_path / "img")

@@ -66,7 +65,7 @@ class TestCacheImageFromUrl:
        assert path.endswith(".jpg")
        mock_client.get.assert_called_once()

-    def test_retries_on_timeout_then_succeeds(self, _mock_safe, tmp_path, monkeypatch):
+    def test_retries_on_timeout_then_succeeds(self, tmp_path, monkeypatch):
        """A timeout on the first attempt is retried; second attempt succeeds."""
        monkeypatch.setattr("gateway.platforms.base.IMAGE_CACHE_DIR", tmp_path / "img")

@@ -96,7 +95,7 @@ class TestCacheImageFromUrl:
        assert mock_client.get.call_count == 2
        mock_sleep.assert_called_once()

-    def test_retries_on_429_then_succeeds(self, _mock_safe, tmp_path, monkeypatch):
+    def test_retries_on_429_then_succeeds(self, tmp_path, monkeypatch):
        """A 429 response on the first attempt is retried; second attempt succeeds."""
        monkeypatch.setattr("gateway.platforms.base.IMAGE_CACHE_DIR", tmp_path / "img")

@@ -123,7 +122,7 @@ class TestCacheImageFromUrl:
        assert path.endswith(".jpg")
        assert mock_client.get.call_count == 2

-    def test_raises_after_max_retries_exhausted(self, _mock_safe, tmp_path, monkeypatch):
+    def test_raises_after_max_retries_exhausted(self, tmp_path, monkeypatch):
        """Timeout on every attempt raises after all retries are consumed."""
        monkeypatch.setattr("gateway.platforms.base.IMAGE_CACHE_DIR", tmp_path / "img")

@@ -146,7 +145,7 @@ class TestCacheImageFromUrl:
        # 3 total calls: initial + 2 retries
        assert mock_client.get.call_count == 3

-    def test_non_retryable_4xx_raises_immediately(self, _mock_safe, tmp_path, monkeypatch):
+    def test_non_retryable_4xx_raises_immediately(self, tmp_path, monkeypatch):
        """A 404 (non-retryable) is raised immediately without any retry."""
        monkeypatch.setattr("gateway.platforms.base.IMAGE_CACHE_DIR", tmp_path / "img")

@@ -176,11 +175,10 @@ class TestCacheImageFromUrl:
 # cache_audio_from_url (base.py)
 # ---------------------------------------------------------------------------

-@patch("tools.url_safety.is_safe_url", return_value=True)
 class TestCacheAudioFromUrl:
    """Tests for gateway.platforms.base.cache_audio_from_url"""

-    def test_success_on_first_attempt(self, _mock_safe, tmp_path, monkeypatch):
+    def test_success_on_first_attempt(self, tmp_path, monkeypatch):
        """A clean 200 response caches the audio and returns a path."""
        monkeypatch.setattr("gateway.platforms.base.AUDIO_CACHE_DIR", tmp_path / "audio")

@@ -204,7 +202,7 @@ class TestCacheAudioFromUrl:
        assert path.endswith(".ogg")
        mock_client.get.assert_called_once()

-    def test_retries_on_timeout_then_succeeds(self, _mock_safe, tmp_path, monkeypatch):
+    def test_retries_on_timeout_then_succeeds(self, tmp_path, monkeypatch):
        """A timeout on the first attempt is retried; second attempt succeeds."""
        monkeypatch.setattr("gateway.platforms.base.AUDIO_CACHE_DIR", tmp_path / "audio")

@@ -234,7 +232,7 @@ class TestCacheAudioFromUrl:
        assert mock_client.get.call_count == 2
        mock_sleep.assert_called_once()

-    def test_retries_on_429_then_succeeds(self, _mock_safe, tmp_path, monkeypatch):
+    def test_retries_on_429_then_succeeds(self, tmp_path, monkeypatch):
        """A 429 response on the first attempt is retried; second attempt succeeds."""
        monkeypatch.setattr("gateway.platforms.base.AUDIO_CACHE_DIR", tmp_path / "audio")

@@ -261,7 +259,7 @@ class TestCacheAudioFromUrl:
        assert path.endswith(".ogg")
        assert mock_client.get.call_count == 2

-    def test_retries_on_500_then_succeeds(self, _mock_safe, tmp_path, monkeypatch):
+    def test_retries_on_500_then_succeeds(self, tmp_path, monkeypatch):
        """A 500 response on the first attempt is retried; second attempt succeeds."""
        monkeypatch.setattr("gateway.platforms.base.AUDIO_CACHE_DIR", tmp_path / "audio")

@@ -288,7 +286,7 @@ class TestCacheAudioFromUrl:
        assert path.endswith(".ogg")
        assert mock_client.get.call_count == 2

-    def test_raises_after_max_retries_exhausted(self, _mock_safe, tmp_path, monkeypatch):
+    def test_raises_after_max_retries_exhausted(self, tmp_path, monkeypatch):
        """Timeout on every attempt raises after all retries are consumed."""
        monkeypatch.setattr("gateway.platforms.base.AUDIO_CACHE_DIR", tmp_path / "audio")

@@ -311,7 +309,7 @@ class TestCacheAudioFromUrl:
        # 3 total calls: initial + 2 retries
        assert mock_client.get.call_count == 3

-    def test_non_retryable_4xx_raises_immediately(self, _mock_safe, tmp_path, monkeypatch):
+    def test_non_retryable_4xx_raises_immediately(self, tmp_path, monkeypatch):
        """A 404 (non-retryable) is raised immediately without any retry."""
        monkeypatch.setattr("gateway.platforms.base.AUDIO_CACHE_DIR", tmp_path / "audio")

@@ -87,6 +87,7 @@ class TestReasoningCommand:
        )

        monkeypatch.setattr(gateway_run, "_hermes_home", hermes_home)
+        monkeypatch.delenv("HERMES_REASONING_EFFORT", raising=False)

        runner = _make_runner()
        runner._reasoning_config = {"enabled": True, "effort": "xhigh"}
@@ -107,6 +108,7 @@ class TestReasoningCommand:
        config_path.write_text("agent:\n  reasoning_effort: medium\n", encoding="utf-8")

        monkeypatch.setattr(gateway_run, "_hermes_home", hermes_home)
+        monkeypatch.delenv("HERMES_REASONING_EFFORT", raising=False)

        runner = _make_runner()
        runner._reasoning_config = {"enabled": True, "effort": "medium"}
@@ -136,6 +138,7 @@ class TestReasoningCommand:
                "api_key": "test-key",
            },
        )
+        monkeypatch.delenv("HERMES_REASONING_EFFORT", raising=False)
        fake_run_agent = types.ModuleType("run_agent")
        fake_run_agent.AIAgent = _CapturingAgent
        monkeypatch.setitem(sys.modules, "run_agent", fake_run_agent)
@@ -167,6 +170,55 @@ class TestReasoningCommand:
        assert _CapturingAgent.last_init is not None
        assert _CapturingAgent.last_init["reasoning_config"] == {"enabled": True, "effort": "low"}

+    def test_run_agent_prefers_config_over_stale_reasoning_env(self, tmp_path, monkeypatch):
+        hermes_home = tmp_path / "hermes"
+        hermes_home.mkdir()
+        (hermes_home / "config.yaml").write_text("agent:\n  reasoning_effort: none\n", encoding="utf-8")
+
+        monkeypatch.setattr(gateway_run, "_hermes_home", hermes_home)
+        monkeypatch.setattr(gateway_run, "_env_path", hermes_home / ".env")
+        monkeypatch.setattr(gateway_run, "load_dotenv", lambda *args, **kwargs: None)
+        monkeypatch.setattr(
+            gateway_run,
+            "_resolve_runtime_agent_kwargs",
+            lambda: {
+                "provider": "openrouter",
+                "api_mode": "chat_completions",
+                "base_url": "https://openrouter.ai/api/v1",
+                "api_key": "test-key",
+            },
+        )
+        monkeypatch.setenv("HERMES_REASONING_EFFORT", "low")
+        fake_run_agent = types.ModuleType("run_agent")
+        fake_run_agent.AIAgent = _CapturingAgent
+        monkeypatch.setitem(sys.modules, "run_agent", fake_run_agent)
+
+        _CapturingAgent.last_init = None
+        runner = _make_runner()
+
+        source = SessionSource(
+            platform=Platform.LOCAL,
+            chat_id="cli",
+            chat_name="CLI",
+            chat_type="dm",
+            user_id="user-1",
+        )
+
+        result = asyncio.run(
+            runner._run_agent(
+                message="ping",
+                context_prompt="",
+                history=[],
+                source=source,
+                session_id="session-1",
+                session_key="agent:main:local:dm",
+            )
+        )
+
+        assert result["final_response"] == "ok"
+        assert _CapturingAgent.last_init is not None
+        assert _CapturingAgent.last_init["reasoning_config"] == {"enabled": False}
+
    def test_run_agent_includes_enabled_mcp_servers_in_gateway_toolsets(self, tmp_path, monkeypatch):
        hermes_home = tmp_path / "hermes"
        hermes_home.mkdir()
@@ -1,158 +0,0 @@
-"""Tests that on_session_finalize and on_session_reset plugin hooks fire in the gateway."""
-from datetime import datetime
-from types import SimpleNamespace
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import pytest
-
-from gateway.config import GatewayConfig, Platform, PlatformConfig
-from gateway.platforms.base import MessageEvent
-from gateway.session import SessionEntry, SessionSource, build_session_key
-
-
-def _make_source() -> SessionSource:
-    return SessionSource(
-        platform=Platform.TELEGRAM,
-        user_id="u1",
-        chat_id="c1",
-        user_name="tester",
-        chat_type="dm",
-    )
-
-
-def _make_event(text: str) -> MessageEvent:
-    return MessageEvent(text=text, source=_make_source(), message_id="m1")
-
-
-def _make_runner():
-    from gateway.run import GatewayRunner
-
-    runner = object.__new__(GatewayRunner)
-    runner.config = GatewayConfig(
-        platforms={Platform.TELEGRAM: PlatformConfig(enabled=True, token="***")}
-    )
-    adapter = MagicMock()
-    adapter.send = AsyncMock()
-    runner.adapters = {Platform.TELEGRAM: adapter}
-    runner._voice_mode = {}
-    runner.hooks = SimpleNamespace(emit=AsyncMock(), loaded_hooks=False)
-    runner._session_model_overrides = {}
-    runner._pending_model_notes = {}
-    runner._background_tasks = set()
-
-    session_key = build_session_key(_make_source())
-    session_entry = SessionEntry(
-        session_key=session_key,
-        session_id="sess-old",
-        created_at=datetime.now(),
-        updated_at=datetime.now(),
-        platform=Platform.TELEGRAM,
-        chat_type="dm",
-    )
-    new_session_entry = SessionEntry(
-        session_key=session_key,
-        session_id="sess-new",
-        created_at=datetime.now(),
-        updated_at=datetime.now(),
-        platform=Platform.TELEGRAM,
-        chat_type="dm",
-    )
-    runner.session_store = MagicMock()
-    runner.session_store.get_or_create_session.return_value = new_session_entry
-    runner.session_store.reset_session.return_value = new_session_entry
-    runner.session_store._entries = {session_key: session_entry}
-    runner.session_store._generate_session_key.return_value = session_key
-    runner._running_agents = {}
-    runner._pending_messages = {}
-    runner._pending_approvals = {}
-    runner._session_db = None
-    runner._agent_cache_lock = None
-    runner._is_user_authorized = lambda _source: True
-    runner._format_session_info = lambda: ""
-
-    return runner
-
-
-@pytest.mark.asyncio
-@patch("hermes_cli.plugins.invoke_hook")
-async def test_reset_fires_finalize_hook(mock_invoke_hook):
-    """/new must fire on_session_finalize with the OLD session id."""
-    runner = _make_runner()
-
-    await runner._handle_reset_command(_make_event("/new"))
-
-    mock_invoke_hook.assert_any_call(
-        "on_session_finalize", session_id="sess-old", platform="telegram"
-    )
-
-
-@pytest.mark.asyncio
-@patch("hermes_cli.plugins.invoke_hook")
-async def test_reset_fires_reset_hook(mock_invoke_hook):
-    """/new must fire on_session_reset with the NEW session id."""
-    runner = _make_runner()
-
-    await runner._handle_reset_command(_make_event("/new"))
-
-    mock_invoke_hook.assert_any_call(
-        "on_session_reset", session_id="sess-new", platform="telegram"
-    )
-
-
-@pytest.mark.asyncio
-@patch("hermes_cli.plugins.invoke_hook")
-async def test_finalize_before_reset(mock_invoke_hook):
-    """on_session_finalize must fire before on_session_reset."""
-    runner = _make_runner()
-
-    await runner._handle_reset_command(_make_event("/new"))
-
-    calls = [c for c in mock_invoke_hook.call_args_list
-             if c[0][0] in ("on_session_finalize", "on_session_reset")]
-    hook_names = [c[0][0] for c in calls]
-    assert hook_names == ["on_session_finalize", "on_session_reset"]
-
-
-@pytest.mark.asyncio
-@patch("hermes_cli.plugins.invoke_hook")
-async def test_shutdown_fires_finalize_for_active_agents(mock_invoke_hook):
-    """Gateway stop() must fire on_session_finalize for each active agent."""
-    from gateway.run import GatewayRunner
-
-    runner = object.__new__(GatewayRunner)
-    runner._running = True
-    runner._background_tasks = set()
-    runner._pending_messages = {}
-    runner._pending_approvals = {}
-    runner._shutdown_event = MagicMock()
-    runner.adapters = {}
-    runner._exit_reason = "test"
-
-    agent1 = MagicMock()
-    agent1.session_id = "sess-a"
-    agent2 = MagicMock()
-    agent2.session_id = "sess-b"
-    runner._running_agents = {"key-a": agent1, "key-b": agent2}
-
-    with patch("gateway.status.remove_pid_file"), \
-         patch("gateway.status.write_runtime_status"):
-        await runner.stop()
-
-    finalize_calls = [
-        c for c in mock_invoke_hook.call_args_list
-        if c[0][0] == "on_session_finalize"
-    ]
-    session_ids = {c[1]["session_id"] for c in finalize_calls}
-    assert session_ids == {"sess-a", "sess-b"}
-
-
-@pytest.mark.asyncio
-@patch("hermes_cli.plugins.invoke_hook", side_effect=Exception("boom"))
-async def test_hook_error_does_not_break_reset(mock_invoke_hook):
-    """Plugin hook errors must not prevent /new from completing."""
-    runner = _make_runner()
-
-    result = await runner._handle_reset_command(_make_event("/new"))
-
-    # Should still return a success message despite hook errors
-    assert "Session reset" in result or "New session" in result
@@ -707,66 +707,3 @@ class TestSignalSendDocumentViaHelper:

        assert result.success is False
        assert "/nonexistent.pdf" in result.error
-
-
-# ---------------------------------------------------------------------------
-# send() returns message_id from timestamp (#4647)
-# ---------------------------------------------------------------------------
-
-class TestSignalSendReturnsMessageId:
-    """Signal send() must return a timestamp-based message_id so the stream
-    consumer can follow its edit→fallback path correctly."""
-
-    @pytest.mark.asyncio
-    async def test_send_returns_timestamp_as_message_id(self, monkeypatch):
-        adapter = _make_signal_adapter(monkeypatch)
-        mock_rpc, _ = _stub_rpc({"timestamp": 1712345678000})
-        adapter._rpc = mock_rpc
-        adapter._stop_typing_indicator = AsyncMock()
-
-        result = await adapter.send(chat_id="+155****4567", content="hello")
-
-        assert result.success is True
-        assert result.message_id == "1712345678000"
-
-    @pytest.mark.asyncio
-    async def test_send_returns_none_message_id_when_no_timestamp(self, monkeypatch):
-        adapter = _make_signal_adapter(monkeypatch)
-        mock_rpc, _ = _stub_rpc({})  # No timestamp key
-        adapter._rpc = mock_rpc
-        adapter._stop_typing_indicator = AsyncMock()
-
-        result = await adapter.send(chat_id="+155****4567", content="hello")
-
-        assert result.success is True
-        assert result.message_id is None
-
-    @pytest.mark.asyncio
-    async def test_send_returns_none_message_id_for_non_dict(self, monkeypatch):
-        adapter = _make_signal_adapter(monkeypatch)
-        mock_rpc, _ = _stub_rpc("ok")  # Non-dict result
-        adapter._rpc = mock_rpc
-        adapter._stop_typing_indicator = AsyncMock()
-
-        result = await adapter.send(chat_id="+155****4567", content="hello")
-
-        assert result.success is True
-        assert result.message_id is None
-
-
-# ---------------------------------------------------------------------------
-# stop_typing() delegates to _stop_typing_indicator (#4647)
-# ---------------------------------------------------------------------------
-
-class TestSignalStopTyping:
-    """Signal must expose a public stop_typing() so base adapter's
-    _keep_typing finally block can clean up platform-level typing tasks."""
-
-    @pytest.mark.asyncio
-    async def test_stop_typing_calls_private_method(self, monkeypatch):
-        adapter = _make_signal_adapter(monkeypatch)
-        adapter._stop_typing_indicator = AsyncMock()
-
-        await adapter.stop_typing("+155****4567")
-
-        adapter._stop_typing_indicator.assert_awaited_once_with("+155****4567")
@@ -96,7 +96,7 @@ class TestAppMentionHandler:
    """Verify that the app_mention event handler is registered."""

    def test_app_mention_registered_on_connect(self):
-        """connect() should register message + assistant lifecycle handlers."""
+        """connect() should register both 'message' and 'app_mention' handlers."""
        config = PlatformConfig(enabled=True, token="xoxb-fake")
        adapter = SlackAdapter(config)

@@ -145,8 +145,6 @@ class TestAppMentionHandler:

        assert "message" in registered_events
        assert "app_mention" in registered_events
-        assert "assistant_thread_started" in registered_events
-        assert "assistant_thread_context_changed" in registered_events
        assert "/hermes" in registered_commands


@@ -842,114 +840,6 @@ class TestThreadReplyHandling:
        adapter.handle_message.assert_not_called()


-# ---------------------------------------------------------------------------
-# TestAssistantThreadLifecycle
-# ---------------------------------------------------------------------------
-
-
-class TestAssistantThreadLifecycle:
-    """Slack Assistant lifecycle events should seed session/user context."""
-
-    @pytest.fixture()
-    def mock_session_store(self):
-        store = MagicMock()
-        store._entries = {}
-        store._ensure_loaded = MagicMock()
-        store.config = MagicMock()
-        store.config.group_sessions_per_user = True
-        store.get_or_create_session = MagicMock()
-        return store
-
-    @pytest.fixture()
-    def assistant_adapter(self, mock_session_store):
-        config = PlatformConfig(enabled=True, token="***")
-        a = SlackAdapter(config)
-        a._app = MagicMock()
-        a._app.client = AsyncMock()
-        a._bot_user_id = "U_BOT"
-        a._team_bot_user_ids = {"T_TEAM": "U_BOT"}
-        a._running = True
-        a.handle_message = AsyncMock()
-        a.set_session_store(mock_session_store)
-        return a
-
-    @pytest.mark.asyncio
-    async def test_lifecycle_event_seeds_session_store(self, assistant_adapter, mock_session_store):
-        event = {
-            "type": "assistant_thread_started",
-            "team_id": "T_TEAM",
-            "assistant_thread": {
-                "channel_id": "D123",
-                "thread_ts": "171.000",
-                "user_id": "U_USER",
-                "context": {"channel_id": "C_ORIGIN"},
-            },
-        }
-
-        await assistant_adapter._handle_assistant_thread_lifecycle_event(event)
-
-        assert assistant_adapter._assistant_threads[("D123", "171.000")]["user_id"] == "U_USER"
-        mock_session_store.get_or_create_session.assert_called_once()
-        source = mock_session_store.get_or_create_session.call_args[0][0]
-        assert source.chat_id == "D123"
-        assert source.chat_type == "dm"
-        assert source.user_id == "U_USER"
-        assert source.thread_id == "171.000"
-        assert source.chat_topic == "C_ORIGIN"
-
-    @pytest.mark.asyncio
-    async def test_message_uses_cached_assistant_thread_identity(self, assistant_adapter):
-        assistant_adapter._assistant_threads[("D123", "171.000")] = {
-            "channel_id": "D123",
-            "thread_ts": "171.000",
-            "user_id": "U_USER",
-            "team_id": "T_TEAM",
-        }
-        assistant_adapter._app.client.users_info = AsyncMock(return_value={
-            "user": {"profile": {"display_name": "Tyler"}}
-        })
-        assistant_adapter._app.client.reactions_add = AsyncMock()
-        assistant_adapter._app.client.reactions_remove = AsyncMock()
-
-        event = {
-            "text": "hello from assistant dm",
-            "channel": "D123",
-            "channel_type": "im",
-            "thread_ts": "171.000",
-            "ts": "171.111",
-            "team": "T_TEAM",
-        }
-
-        await assistant_adapter._handle_slack_message(event)
-
-        msg_event = assistant_adapter.handle_message.call_args[0][0]
-        assert msg_event.source.user_id == "U_USER"
-        assert msg_event.source.thread_id == "171.000"
-        assert msg_event.source.user_name == "Tyler"
-
-    def test_assistant_threads_cache_eviction(self, assistant_adapter):
-        """Cache should evict oldest entries when exceeding the size limit."""
-        assistant_adapter._ASSISTANT_THREADS_MAX = 10
-        # Fill to the limit
-        for i in range(10):
-            assistant_adapter._cache_assistant_thread_metadata({
-                "channel_id": f"D{i}",
-                "thread_ts": f"{i}.000",
-                "user_id": f"U{i}",
-            })
-        assert len(assistant_adapter._assistant_threads) == 10
-
-        # Adding one more should trigger eviction (down to max // 2 = 5)
-        assistant_adapter._cache_assistant_thread_metadata({
-            "channel_id": "D999",
-            "thread_ts": "999.000",
-            "user_id": "U999",
-        })
-        assert len(assistant_adapter._assistant_threads) <= 10
-        # The newest entry must survive eviction
-        assert ("D999", "999.000") in assistant_adapter._assistant_threads
-
-
 # ---------------------------------------------------------------------------
 # TestUserNameResolution
 # ---------------------------------------------------------------------------
@@ -324,145 +324,3 @@ class TestSegmentBreakOnToolBoundary:
        await consumer.run()

        assert consumer.already_sent
-
-    @pytest.mark.asyncio
-    async def test_edit_failure_sends_only_unsent_tail_at_finish(self):
-        """If an edit fails mid-stream, send only the missing tail once at finish."""
-        adapter = MagicMock()
-        send_results = [
-            SimpleNamespace(success=True, message_id="msg_1"),
-            SimpleNamespace(success=True, message_id="msg_2"),
-        ]
-        adapter.send = AsyncMock(side_effect=send_results)
-        adapter.edit_message = AsyncMock(return_value=SimpleNamespace(success=False, error="flood_control:6"))
-        adapter.MAX_MESSAGE_LENGTH = 4096
-
-        config = StreamConsumerConfig(edit_interval=0.01, buffer_threshold=5, cursor=" ▉")
-        consumer = GatewayStreamConsumer(adapter, "chat_123", config)
-
-        consumer.on_delta("Hello")
-        task = asyncio.create_task(consumer.run())
-        await asyncio.sleep(0.08)
-        consumer.on_delta(" world")
-        await asyncio.sleep(0.08)
-        consumer.finish()
-        await task
-
-        assert adapter.send.call_count == 2
-        first_text = adapter.send.call_args_list[0][1]["content"]
-        second_text = adapter.send.call_args_list[1][1]["content"]
-        assert "Hello" in first_text
-        assert second_text.strip() == "world"
-        assert consumer.already_sent
-
-    @pytest.mark.asyncio
-    async def test_segment_break_clears_failed_edit_fallback_state(self):
-        """A tool boundary after edit failure must not duplicate the next segment."""
-        adapter = MagicMock()
-        send_results = [
-            SimpleNamespace(success=True, message_id="msg_1"),
-            SimpleNamespace(success=True, message_id="msg_2"),
-        ]
-        adapter.send = AsyncMock(side_effect=send_results)
-        adapter.edit_message = AsyncMock(return_value=SimpleNamespace(success=False, error="flood_control:6"))
-        adapter.MAX_MESSAGE_LENGTH = 4096
-
-        config = StreamConsumerConfig(edit_interval=0.01, buffer_threshold=5, cursor=" ▉")
-        consumer = GatewayStreamConsumer(adapter, "chat_123", config)
-
-        consumer.on_delta("Hello")
-        task = asyncio.create_task(consumer.run())
-        await asyncio.sleep(0.08)
-        consumer.on_delta(" world")
-        await asyncio.sleep(0.08)
-        consumer.on_delta(None)
-        consumer.on_delta("Next segment")
-        consumer.finish()
-        await task
-
-        sent_texts = [call[1]["content"] for call in adapter.send.call_args_list]
-        assert sent_texts == ["Hello ▉", "Next segment"]
-
-    @pytest.mark.asyncio
-    async def test_no_message_id_enters_fallback_mode(self):
-        """Platform returns success but no message_id (Signal) — must not
-        re-send on every delta.  Should enter fallback mode and send only
-        the continuation at finish."""
-        adapter = MagicMock()
-        # First send succeeds but returns no message_id (Signal behavior)
-        send_result_no_id = SimpleNamespace(success=True, message_id=None)
-        # Fallback final send succeeds
-        send_result_final = SimpleNamespace(success=True, message_id="msg_final")
-        adapter.send = AsyncMock(side_effect=[send_result_no_id, send_result_final])
-        adapter.edit_message = AsyncMock(return_value=SimpleNamespace(success=True))
-        adapter.MAX_MESSAGE_LENGTH = 4096
-
-        config = StreamConsumerConfig(edit_interval=0.01, buffer_threshold=5)
-        consumer = GatewayStreamConsumer(adapter, "chat_123", config)
-
-        consumer.on_delta("Hello")
-        task = asyncio.create_task(consumer.run())
-        await asyncio.sleep(0.08)
-        consumer.on_delta(" world, this is a longer response.")
-        await asyncio.sleep(0.08)
-        consumer.finish()
-        await task
-
-        # Should send exactly 2 messages: initial chunk + fallback continuation
-        # NOT one message per delta
-        assert adapter.send.call_count == 2
-        assert consumer.already_sent
-        # edit_message should NOT have been called (no valid message_id to edit)
-        adapter.edit_message.assert_not_called()
-
-    @pytest.mark.asyncio
-    async def test_no_message_id_single_delta_marks_already_sent(self):
-        """When the entire response fits in one delta and platform returns no
-        message_id, already_sent must still be True to prevent the gateway
-        from re-sending the full response."""
-        adapter = MagicMock()
-        send_result = SimpleNamespace(success=True, message_id=None)
-        adapter.send = AsyncMock(return_value=send_result)
-        adapter.MAX_MESSAGE_LENGTH = 4096
-
-        config = StreamConsumerConfig(edit_interval=0.01, buffer_threshold=5)
-        consumer = GatewayStreamConsumer(adapter, "chat_123", config)
-
-        consumer.on_delta("Short response.")
-        consumer.finish()
-
-        await consumer.run()
-
-        assert consumer.already_sent
-        # Only one send call (the initial message)
-        assert adapter.send.call_count == 1
-
-    @pytest.mark.asyncio
-    async def test_fallback_final_splits_long_continuation_without_dropping_text(self):
-        """Long continuation tails should be chunked when fallback final-send runs."""
-        adapter = MagicMock()
-        adapter.send = AsyncMock(side_effect=[
-            SimpleNamespace(success=True, message_id="msg_1"),
-            SimpleNamespace(success=True, message_id="msg_2"),
-            SimpleNamespace(success=True, message_id="msg_3"),
-        ])
-        adapter.edit_message = AsyncMock(return_value=SimpleNamespace(success=False, error="flood_control:6"))
-        adapter.MAX_MESSAGE_LENGTH = 610
-
-        config = StreamConsumerConfig(edit_interval=0.01, buffer_threshold=5, cursor=" ▉")
-        consumer = GatewayStreamConsumer(adapter, "chat_123", config)
-
-        prefix = "abc"
-        tail = "x" * 620
-        consumer.on_delta(prefix)
-        task = asyncio.create_task(consumer.run())
-        await asyncio.sleep(0.08)
-        consumer.on_delta(tail)
-        await asyncio.sleep(0.08)
-        consumer.finish()
-        await task
-
-        sent_texts = [call[1]["content"] for call in adapter.send.call_args_list]
-        assert len(sent_texts) == 3
-        assert sent_texts[0].startswith(prefix)
-        assert sum(len(t) for t in sent_texts[1:]) == len(tail)
@@ -4,7 +4,7 @@ import base64
 import os
 from pathlib import Path
 from types import SimpleNamespace
-from unittest.mock import AsyncMock, patch
+from unittest.mock import AsyncMock

 import pytest

@@ -355,8 +355,7 @@ class TestMediaUpload:
        assert calls[3][1]["chunk_index"] == 2

    @pytest.mark.asyncio
-    @patch("tools.url_safety.is_safe_url", return_value=True)
-    async def test_download_remote_bytes_rejects_large_content_length(self, _mock_safe):
+    async def test_download_remote_bytes_rejects_large_content_length(self):
        from gateway.platforms.wecom import WeComAdapter

        class FakeResponse:
@@ -628,21 +628,14 @@ class TestHasAnyProviderConfigured:
    def test_claude_code_creds_ignored_on_fresh_install(self, monkeypatch, tmp_path):
        """Claude Code credentials should NOT skip the wizard when Hermes is unconfigured."""
        from hermes_cli import config as config_module
-        from hermes_cli.auth import PROVIDER_REGISTRY
        hermes_home = tmp_path / ".hermes"
        hermes_home.mkdir()
        monkeypatch.setattr(config_module, "get_env_path", lambda: hermes_home / ".env")
        monkeypatch.setattr(config_module, "get_hermes_home", lambda: hermes_home)
        # Clear all provider env vars so earlier checks don't short-circuit
-        _all_vars = {"OPENROUTER_API_KEY", "OPENAI_API_KEY", "ANTHROPIC_API_KEY",
-                      "ANTHROPIC_TOKEN", "OPENAI_BASE_URL"}
-        for pconfig in PROVIDER_REGISTRY.values():
-            if pconfig.auth_type == "api_key":
-                _all_vars.update(pconfig.api_key_env_vars)
-        for var in _all_vars:
+        for var in ("OPENROUTER_API_KEY", "OPENAI_API_KEY", "ANTHROPIC_API_KEY",
+                     "ANTHROPIC_TOKEN", "OPENAI_BASE_URL"):
            monkeypatch.delenv(var, raising=False)
-        # Prevent gh-cli / copilot auth fallback from leaking in
-        monkeypatch.setattr("hermes_cli.auth.get_auth_status", lambda _pid: {})
        # Simulate valid Claude Code credentials
        monkeypatch.setattr(
            "agent.anthropic_adapter.read_claude_code_credentials",
@@ -717,7 +710,6 @@ class TestHasAnyProviderConfigured:
        """config.yaml model dict with empty default and no creds stays false."""
        import yaml
        from hermes_cli import config as config_module
-        from hermes_cli.auth import PROVIDER_REGISTRY
        hermes_home = tmp_path / ".hermes"
        hermes_home.mkdir()
        config_file = hermes_home / "config.yaml"
@@ -727,15 +719,9 @@ class TestHasAnyProviderConfigured:
        monkeypatch.setattr(config_module, "get_env_path", lambda: hermes_home / ".env")
        monkeypatch.setattr(config_module, "get_hermes_home", lambda: hermes_home)
        monkeypatch.setenv("HERMES_HOME", str(hermes_home))
-        _all_vars = {"OPENROUTER_API_KEY", "OPENAI_API_KEY", "ANTHROPIC_API_KEY",
-                      "ANTHROPIC_TOKEN", "OPENAI_BASE_URL"}
-        for pconfig in PROVIDER_REGISTRY.values():
-            if pconfig.auth_type == "api_key":
-                _all_vars.update(pconfig.api_key_env_vars)
-        for var in _all_vars:
+        for var in ("OPENROUTER_API_KEY", "OPENAI_API_KEY", "ANTHROPIC_API_KEY",
+                     "ANTHROPIC_TOKEN", "OPENAI_BASE_URL"):
            monkeypatch.delenv(var, raising=False)
-        # Prevent gh-cli / copilot auth fallback from leaking in
-        monkeypatch.setattr("hermes_cli.auth.get_auth_status", lambda _pid: {})
        from hermes_cli.main import _has_any_provider_configured
        assert _has_any_provider_configured() is False

@@ -955,10 +941,9 @@ class TestHuggingFaceModels:
        """Every HF model should have a context length entry."""
        from hermes_cli.models import _PROVIDER_MODELS
        from agent.model_metadata import DEFAULT_CONTEXT_LENGTHS
-        lower_keys = {k.lower() for k in DEFAULT_CONTEXT_LENGTHS}
        hf_models = _PROVIDER_MODELS["huggingface"]
        for model in hf_models:
-            assert model.lower() in lower_keys, (
+            assert model in DEFAULT_CONTEXT_LENGTHS, (
                f"HF model {model!r} missing from DEFAULT_CONTEXT_LENGTHS"
            )

@@ -1,399 +0,0 @@
-"""Tests for Qwen OAuth provider authentication (hermes_cli/auth.py).
-
-Covers: _qwen_cli_auth_path, _read_qwen_cli_tokens, _save_qwen_cli_tokens,
-_qwen_access_token_is_expiring, _refresh_qwen_cli_tokens,
-resolve_qwen_runtime_credentials, get_qwen_auth_status.
-"""
-
-import json
-import os
-import stat
-import time
-from pathlib import Path
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-from hermes_cli.auth import (
-    AuthError,
-    DEFAULT_QWEN_BASE_URL,
-    QWEN_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
-    _qwen_cli_auth_path,
-    _read_qwen_cli_tokens,
-    _save_qwen_cli_tokens,
-    _qwen_access_token_is_expiring,
-    _refresh_qwen_cli_tokens,
-    resolve_qwen_runtime_credentials,
-    get_qwen_auth_status,
-)
-
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-def _make_qwen_tokens(
-    access_token="test-access-token",
-    refresh_token="test-refresh-token",
-    expiry_date=None,
-    **extra,
-):
-    """Create a minimal Qwen CLI OAuth credential dict."""
-    if expiry_date is None:
-        # 1 hour from now in milliseconds
-        expiry_date = int((time.time() + 3600) * 1000)
-    data = {
-        "access_token": access_token,
-        "refresh_token": refresh_token,
-        "token_type": "Bearer",
-        "expiry_date": expiry_date,
-        "resource_url": "portal.qwen.ai",
-    }
-    data.update(extra)
-    return data
-
-
-def _write_qwen_creds(tmp_path, tokens=None):
-    """Write tokens to the Qwen CLI credentials file and return the path."""
-    qwen_dir = tmp_path / ".qwen"
-    qwen_dir.mkdir(parents=True, exist_ok=True)
-    creds_path = qwen_dir / "oauth_creds.json"
-    if tokens is None:
-        tokens = _make_qwen_tokens()
-    creds_path.write_text(json.dumps(tokens), encoding="utf-8")
-    return creds_path
-
-
-@pytest.fixture()
-def qwen_env(tmp_path, monkeypatch):
-    """Redirect _qwen_cli_auth_path to tmp_path/.qwen/oauth_creds.json."""
-    creds_path = tmp_path / ".qwen" / "oauth_creds.json"
-    monkeypatch.setattr(
-        "hermes_cli.auth._qwen_cli_auth_path", lambda: creds_path
-    )
-    return tmp_path
-
-
-# ---------------------------------------------------------------------------
-# _qwen_cli_auth_path
-# ---------------------------------------------------------------------------
-
-def test_qwen_cli_auth_path_returns_expected_location():
-    path = _qwen_cli_auth_path()
-    assert path == Path.home() / ".qwen" / "oauth_creds.json"
-
-
-# ---------------------------------------------------------------------------
-# _read_qwen_cli_tokens
-# ---------------------------------------------------------------------------
-
-def test_read_qwen_cli_tokens_success(qwen_env):
-    tokens = _make_qwen_tokens(access_token="my-access")
-    _write_qwen_creds(qwen_env, tokens)
-    result = _read_qwen_cli_tokens()
-    assert result["access_token"] == "my-access"
-    assert result["refresh_token"] == "test-refresh-token"
-
-
-def test_read_qwen_cli_tokens_missing_file(qwen_env):
-    with pytest.raises(AuthError) as exc:
-        _read_qwen_cli_tokens()
-    assert exc.value.code == "qwen_auth_missing"
-
-
-def test_read_qwen_cli_tokens_invalid_json(qwen_env):
-    creds_path = qwen_env / ".qwen" / "oauth_creds.json"
-    creds_path.parent.mkdir(parents=True, exist_ok=True)
-    creds_path.write_text("not json{{{", encoding="utf-8")
-    with pytest.raises(AuthError) as exc:
-        _read_qwen_cli_tokens()
-    assert exc.value.code == "qwen_auth_read_failed"
-
-
-def test_read_qwen_cli_tokens_non_dict(qwen_env):
-    creds_path = qwen_env / ".qwen" / "oauth_creds.json"
-    creds_path.parent.mkdir(parents=True, exist_ok=True)
-    creds_path.write_text(json.dumps(["a", "b"]), encoding="utf-8")
-    with pytest.raises(AuthError) as exc:
-        _read_qwen_cli_tokens()
-    assert exc.value.code == "qwen_auth_invalid"
-
-
-# ---------------------------------------------------------------------------
-# _save_qwen_cli_tokens
-# ---------------------------------------------------------------------------
-
-def test_save_qwen_cli_tokens_roundtrip(qwen_env):
-    tokens = _make_qwen_tokens(access_token="saved-token")
-    saved_path = _save_qwen_cli_tokens(tokens)
-    assert saved_path.exists()
-    loaded = json.loads(saved_path.read_text(encoding="utf-8"))
-    assert loaded["access_token"] == "saved-token"
-
-
-def test_save_qwen_cli_tokens_creates_parent(qwen_env):
-    tokens = _make_qwen_tokens()
-    saved_path = _save_qwen_cli_tokens(tokens)
-    assert saved_path.parent.exists()
-
-
-def test_save_qwen_cli_tokens_permissions(qwen_env):
-    tokens = _make_qwen_tokens()
-    saved_path = _save_qwen_cli_tokens(tokens)
-    mode = saved_path.stat().st_mode
-    assert mode & stat.S_IRUSR  # owner read
-    assert mode & stat.S_IWUSR  # owner write
-    assert not (mode & stat.S_IRGRP)  # no group read
-    assert not (mode & stat.S_IROTH)  # no other read
-
-
-# ---------------------------------------------------------------------------
-# _qwen_access_token_is_expiring
-# ---------------------------------------------------------------------------
-
-def test_expiring_token_not_expired():
-    # 1 hour from now in milliseconds
-    future_ms = int((time.time() + 3600) * 1000)
-    assert not _qwen_access_token_is_expiring(future_ms)
-
-
-def test_expiring_token_already_expired():
-    # 1 hour ago in milliseconds
-    past_ms = int((time.time() - 3600) * 1000)
-    assert _qwen_access_token_is_expiring(past_ms)
-
-
-def test_expiring_token_within_skew():
-    # Just inside the default skew window
-    near_ms = int((time.time() + QWEN_ACCESS_TOKEN_REFRESH_SKEW_SECONDS - 5) * 1000)
-    assert _qwen_access_token_is_expiring(near_ms)
-
-
-def test_expiring_token_none_returns_true():
-    assert _qwen_access_token_is_expiring(None)
-
-
-def test_expiring_token_non_numeric_returns_true():
-    assert _qwen_access_token_is_expiring("not-a-number")
-
-
-# ---------------------------------------------------------------------------
-# _refresh_qwen_cli_tokens
-# ---------------------------------------------------------------------------
-
-def test_refresh_qwen_cli_tokens_success(qwen_env):
-    tokens = _make_qwen_tokens(refresh_token="old-refresh")
-
-    resp = MagicMock()
-    resp.status_code = 200
-    resp.json.return_value = {
-        "access_token": "new-access",
-        "refresh_token": "new-refresh",
-        "expires_in": 7200,
-    }
-
-    with patch("hermes_cli.auth.httpx") as mock_httpx:
-        mock_httpx.post.return_value = resp
-        result = _refresh_qwen_cli_tokens(tokens)
-
-    assert result["access_token"] == "new-access"
-    assert result["refresh_token"] == "new-refresh"
-    assert "expiry_date" in result
-
-
-def test_refresh_qwen_cli_tokens_preserves_old_refresh_if_not_in_response(qwen_env):
-    tokens = _make_qwen_tokens(refresh_token="keep-me")
-
-    resp = MagicMock()
-    resp.status_code = 200
-    resp.json.return_value = {
-        "access_token": "new-access",
-        # No refresh_token in response — should keep old one
-        "expires_in": 3600,
-    }
-
-    with patch("hermes_cli.auth.httpx") as mock_httpx:
-        mock_httpx.post.return_value = resp
-        result = _refresh_qwen_cli_tokens(tokens)
-
-    assert result["refresh_token"] == "keep-me"
-
-
-def test_refresh_qwen_cli_tokens_missing_refresh_token():
-    tokens = {"access_token": "at", "refresh_token": ""}
-    with pytest.raises(AuthError) as exc:
-        _refresh_qwen_cli_tokens(tokens)
-    assert exc.value.code == "qwen_refresh_token_missing"
-
-
-def test_refresh_qwen_cli_tokens_http_error(qwen_env):
-    tokens = _make_qwen_tokens()
-
-    resp = MagicMock()
-    resp.status_code = 401
-    resp.text = "unauthorized"
-
-    with patch("hermes_cli.auth.httpx") as mock_httpx:
-        mock_httpx.post.return_value = resp
-        with pytest.raises(AuthError) as exc:
-            _refresh_qwen_cli_tokens(tokens)
-    assert exc.value.code == "qwen_refresh_failed"
-
-
-def test_refresh_qwen_cli_tokens_network_error(qwen_env):
-    tokens = _make_qwen_tokens()
-
-    with patch("hermes_cli.auth.httpx") as mock_httpx:
-        mock_httpx.post.side_effect = ConnectionError("timeout")
-        with pytest.raises(AuthError) as exc:
-            _refresh_qwen_cli_tokens(tokens)
-    assert exc.value.code == "qwen_refresh_failed"
-
-
-def test_refresh_qwen_cli_tokens_invalid_json_response(qwen_env):
-    tokens = _make_qwen_tokens()
-
-    resp = MagicMock()
-    resp.status_code = 200
-    resp.json.side_effect = ValueError("bad json")
-
-    with patch("hermes_cli.auth.httpx") as mock_httpx:
-        mock_httpx.post.return_value = resp
-        with pytest.raises(AuthError) as exc:
-            _refresh_qwen_cli_tokens(tokens)
-    assert exc.value.code == "qwen_refresh_invalid_json"
-
-
-def test_refresh_qwen_cli_tokens_missing_access_token_in_response(qwen_env):
-    tokens = _make_qwen_tokens()
-
-    resp = MagicMock()
-    resp.status_code = 200
-    resp.json.return_value = {"something": "but no access_token"}
-
-    with patch("hermes_cli.auth.httpx") as mock_httpx:
-        mock_httpx.post.return_value = resp
-        with pytest.raises(AuthError) as exc:
-            _refresh_qwen_cli_tokens(tokens)
-    assert exc.value.code == "qwen_refresh_invalid_response"
-
-
-def test_refresh_qwen_cli_tokens_default_expires_in(qwen_env):
-    """When expires_in is missing, default to 6 hours."""
-    tokens = _make_qwen_tokens()
-
-    resp = MagicMock()
-    resp.status_code = 200
-    resp.json.return_value = {"access_token": "new"}
-
-    with patch("hermes_cli.auth.httpx") as mock_httpx:
-        mock_httpx.post.return_value = resp
-        result = _refresh_qwen_cli_tokens(tokens)
-
-    # Verify expiry_date is roughly now + 6h (within 60s tolerance)
-    expected_ms = int(time.time() * 1000) + 6 * 60 * 60 * 1000
-    assert abs(result["expiry_date"] - expected_ms) < 60_000
-
-
-def test_refresh_qwen_cli_tokens_saves_to_disk(qwen_env):
-    tokens = _make_qwen_tokens()
-
-    resp = MagicMock()
-    resp.status_code = 200
-    resp.json.return_value = {
-        "access_token": "disk-check",
-        "expires_in": 3600,
-    }
-
-    with patch("hermes_cli.auth.httpx") as mock_httpx:
-        mock_httpx.post.return_value = resp
-        _refresh_qwen_cli_tokens(tokens)
-
-    # Verify it was persisted
-    creds_path = qwen_env / ".qwen" / "oauth_creds.json"
-    assert creds_path.exists()
-    saved = json.loads(creds_path.read_text(encoding="utf-8"))
-    assert saved["access_token"] == "disk-check"
-
-
-# ---------------------------------------------------------------------------
-# resolve_qwen_runtime_credentials
-# ---------------------------------------------------------------------------
-
-def test_resolve_qwen_runtime_credentials_fresh_token(qwen_env):
-    tokens = _make_qwen_tokens(access_token="fresh-at")
-    _write_qwen_creds(qwen_env, tokens)
-
-    creds = resolve_qwen_runtime_credentials(refresh_if_expiring=False)
-    assert creds["provider"] == "qwen-oauth"
-    assert creds["api_key"] == "fresh-at"
-    assert creds["base_url"] == DEFAULT_QWEN_BASE_URL
-    assert creds["source"] == "qwen-cli"
-
-
-def test_resolve_qwen_runtime_credentials_triggers_refresh(qwen_env):
-    # Write an expired token
-    expired_ms = int((time.time() - 3600) * 1000)
-    tokens = _make_qwen_tokens(access_token="old", expiry_date=expired_ms)
-    _write_qwen_creds(qwen_env, tokens)
-
-    refreshed = _make_qwen_tokens(access_token="refreshed-at")
-
-    with patch(
-        "hermes_cli.auth._refresh_qwen_cli_tokens", return_value=refreshed
-    ) as mock_refresh:
-        creds = resolve_qwen_runtime_credentials()
-    mock_refresh.assert_called_once()
-    assert creds["api_key"] == "refreshed-at"
-
-
-def test_resolve_qwen_runtime_credentials_force_refresh(qwen_env):
-    tokens = _make_qwen_tokens(access_token="old-at")
-    _write_qwen_creds(qwen_env, tokens)
-
-    refreshed = _make_qwen_tokens(access_token="force-refreshed")
-
-    with patch(
-        "hermes_cli.auth._refresh_qwen_cli_tokens", return_value=refreshed
-    ) as mock_refresh:
-        creds = resolve_qwen_runtime_credentials(force_refresh=True)
-    mock_refresh.assert_called_once()
-    assert creds["api_key"] == "force-refreshed"
-
-
-def test_resolve_qwen_runtime_credentials_missing_access_token(qwen_env):
-    tokens = _make_qwen_tokens(access_token="")
-    _write_qwen_creds(qwen_env, tokens)
-
-    with pytest.raises(AuthError) as exc:
-        resolve_qwen_runtime_credentials(refresh_if_expiring=False)
-    assert exc.value.code == "qwen_access_token_missing"
-
-
-def test_resolve_qwen_runtime_credentials_base_url_env_override(qwen_env, monkeypatch):
-    tokens = _make_qwen_tokens(access_token="at")
-    _write_qwen_creds(qwen_env, tokens)
-    monkeypatch.setenv("HERMES_QWEN_BASE_URL", "https://custom.qwen.ai/v1")
-
-    creds = resolve_qwen_runtime_credentials(refresh_if_expiring=False)
-    assert creds["base_url"] == "https://custom.qwen.ai/v1"
-
-
-# ---------------------------------------------------------------------------
-# get_qwen_auth_status
-# ---------------------------------------------------------------------------
-
-def test_get_qwen_auth_status_logged_in(qwen_env):
-    tokens = _make_qwen_tokens(access_token="status-at")
-    _write_qwen_creds(qwen_env, tokens)
-
-    status = get_qwen_auth_status()
-    assert status["logged_in"] is True
-    assert status["api_key"] == "status-at"
-
-
-def test_get_qwen_auth_status_not_logged_in(qwen_env):
-    # No credentials file
-    status = get_qwen_auth_status()
-    assert status["logged_in"] is False
-    assert "error" in status
@@ -425,8 +425,8 @@ class TestSlashCommandCompleter:
 class TestSubcommands:
    def test_explicit_subcommands_extracted(self):
        """Commands with explicit subcommands on CommandDef are extracted."""
-        assert "/skills" in SUBCOMMANDS
-        assert "install" in SUBCOMMANDS["/skills"]
+        assert "/prompt" in SUBCOMMANDS
+        assert "clear" in SUBCOMMANDS["/prompt"]

    def test_reasoning_has_subcommands(self):
        assert "/reasoning" in SUBCOMMANDS
@@ -136,73 +136,3 @@ def test_check_gateway_service_linger_skips_when_service_not_installed(monkeypat
    out = capsys.readouterr().out
    assert out == ""
    assert issues == []
-
-
-# ── Memory provider section (doctor should only check the *active* provider) ──
-
-
-class TestDoctorMemoryProviderSection:
-    """The ◆ Memory Provider section should respect memory.provider config."""
-
-    def _make_hermes_home(self, tmp_path, provider=""):
-        """Create a minimal HERMES_HOME with config.yaml."""
-        home = tmp_path / ".hermes"
-        home.mkdir(parents=True, exist_ok=True)
-        import yaml
-        config = {"memory": {"provider": provider}} if provider else {"memory": {}}
-        (home / "config.yaml").write_text(yaml.dump(config))
-        return home
-
-    def _run_doctor_and_capture(self, monkeypatch, tmp_path, provider=""):
-        """Run doctor and capture stdout."""
-        home = self._make_hermes_home(tmp_path, provider)
-        monkeypatch.setattr(doctor_mod, "HERMES_HOME", home)
-        monkeypatch.setattr(doctor_mod, "PROJECT_ROOT", tmp_path / "project")
-        monkeypatch.setattr(doctor_mod, "_DHH", str(home))
-        (tmp_path / "project").mkdir(exist_ok=True)
-
-        # Stub tool availability (returns empty) so doctor runs past it
-        fake_model_tools = types.SimpleNamespace(
-            check_tool_availability=lambda *a, **kw: ([], []),
-            TOOLSET_REQUIREMENTS={},
-        )
-        monkeypatch.setitem(sys.modules, "model_tools", fake_model_tools)
-
-        # Stub auth checks to avoid real API calls
-        try:
-            from hermes_cli import auth as _auth_mod
-            monkeypatch.setattr(_auth_mod, "get_nous_auth_status", lambda: {})
-            monkeypatch.setattr(_auth_mod, "get_codex_auth_status", lambda: {})
-        except Exception:
-            pass
-
-        import io, contextlib
-        buf = io.StringIO()
-        with contextlib.redirect_stdout(buf):
-            doctor_mod.run_doctor(Namespace(fix=False))
-        return buf.getvalue()
-
-    def test_no_provider_shows_builtin_ok(self, monkeypatch, tmp_path):
-        out = self._run_doctor_and_capture(monkeypatch, tmp_path, provider="")
-        assert "Memory Provider" in out
-        assert "Built-in memory active" in out
-        # Should NOT mention Honcho or Mem0 errors
-        assert "Honcho API key" not in out
-        assert "Mem0" not in out
-
-    def test_honcho_provider_not_installed_shows_fail(self, monkeypatch, tmp_path):
-        # Make honcho import fail
-        monkeypatch.setitem(
-            sys.modules, "plugins.memory.honcho.client", None
-        )
-        out = self._run_doctor_and_capture(monkeypatch, tmp_path, provider="honcho")
-        assert "Memory Provider" in out
-        # Should show failure since honcho is set but not importable
-        assert "Built-in memory active" not in out
-
-    def test_mem0_provider_not_installed_shows_fail(self, monkeypatch, tmp_path):
-        # Make mem0 import fail
-        monkeypatch.setitem(sys.modules, "plugins.memory.mem0", None)
-        out = self._run_doctor_and_capture(monkeypatch, tmp_path, provider="mem0")
-        assert "Memory Provider" in out
-        assert "Built-in memory active" not in out
--- a/Show More
+++ b/Show More