feat(nix): container-aware CLI — auto-route hermes chat into managed container

When container.enable = true in the NixOS module, running 'hermes chat'
on the host now automatically execs into the managed container via
docker/podman exec. This means the interactive CLI runs in the same
environment as the gateway service, with access to all container-installed
packages and tools.

Implementation:
- NixOS activation script writes .container-mode metadata file to
  HERMES_HOME with backend, container_name, and hermes_bin path
- File is removed when container mode is disabled (nixos-rebuild switch)
- hermes_cli/config.py: _is_inside_container() detects Docker/Podman
  indicators (/.dockerenv, /run/.containerenv, cgroup)
- hermes_cli/config.py: get_container_exec_info() reads .container-mode
  metadata, returns None when already inside a container
- hermes_cli/main.py: _exec_in_container() validates the container is
  running, then os.execvp() replaces the process with the container exec
- cmd_chat intercepts before normal flow, checks container info, execs

Safety:
- --host flag bypasses container routing (run on host regardless)
- Falls back to host CLI if: container runtime not found, container not
  running, inspect fails, or any detection error
- Strips --host from forwarded args (not meaningful inside container)
- Already-inside-container detection prevents infinite exec loops

Closes #7380

.dockerignore

@@ -5,7 +5,6 @@
 
 # Dependencies
 node_modules
-.venv
 
 # CI/CD
 .github

.env.example

@@ -43,15 +43,6 @@
 # KIMI_BASE_URL=https://api.kimi.com/coding/v1  # Default for sk-kimi- keys
 # KIMI_BASE_URL=https://api.moonshot.ai/v1      # For legacy Moonshot keys
 # KIMI_BASE_URL=https://api.moonshot.cn/v1       # For Moonshot China keys
-# KIMI_CN_API_KEY=                               # Dedicated Moonshot China key
-
-# =============================================================================
-# LLM PROVIDER (Arcee AI)
-# =============================================================================
-# Arcee AI provides access to Trinity models (trinity-mini, trinity-large-*)
-# Get an Arcee key at: https://chat.arcee.ai/
-# ARCEEAI_API_KEY=
-# ARCEE_BASE_URL=                                 # Override default base URL
 
 # =============================================================================
 # LLM PROVIDER (MiniMax)
@@ -98,15 +89,6 @@
 # Optional base URL override:
 # HERMES_QWEN_BASE_URL=https://portal.qwen.ai/v1
 
-# =============================================================================
-# LLM PROVIDER (Xiaomi MiMo)
-# =============================================================================
-# Xiaomi MiMo models (mimo-v2-pro, mimo-v2-omni, mimo-v2-flash).
-# Get your key at: https://platform.xiaomimimo.com
-# XIAOMI_API_KEY=your_key_here
-# Optional base URL override:
-# XIAOMI_BASE_URL=https://api.xiaomimimo.com/v1
-
 # =============================================================================
 # TOOL API KEYS
 # =============================================================================

.gitattributes

@@ -1,2 +0,0 @@
-# Auto-generated files — collapse diffs and exclude from language stats
-web/package-lock.json linguist-generated=true

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -11,7 +11,6 @@ body:
         **Before submitting**, please:
         - [ ] Search [existing issues](https://github.com/NousResearch/hermes-agent/issues) to avoid duplicates
         - [ ] Update to the latest version (`hermes update`) and confirm the bug still exists
-        - [ ] Run `hermes debug share` and paste the links below (see Debug Report section)
 
   - type: textarea
     id: description
@@ -83,25 +82,6 @@ body:
         - Slack
         - WhatsApp
 
-  - type: textarea
-    id: debug-report
-    attributes:
-      label: Debug Report
-      description: |
-        Run `hermes debug share` from your terminal and paste the links it prints here.
-        This uploads your system info, config, and recent logs to a paste service automatically.
-
-        If you're in an interactive chat session, you can also use the `/debug` slash command — it does the same thing.
-
-        If the upload fails, run `hermes debug share --local` and paste the output directly.
-      placeholder: |
-        Report   https://paste.rs/abc123
-        agent.log   https://paste.rs/def456
-        gateway.log   https://paste.rs/ghi789
-      render: shell
-    validations:
-      required: true
-
   - type: input
     id: os
     attributes:
@@ -117,6 +97,8 @@ body:
       label: Python Version
       description: Output of `python --version`
       placeholder: "3.11.9"
+    validations:
+      required: true
 
   - type: input
     id: hermes-version
@@ -124,14 +106,14 @@ body:
       label: Hermes Version
       description: Output of `hermes version`
       placeholder: "2.1.0"
+    validations:
+      required: true
 
   - type: textarea
     id: logs
     attributes:
-      label: Additional Logs / Traceback (optional)
-      description: |
-        The debug report above covers most logs. Use this field for any extra error output, 
-        tracebacks, or screenshots not captured by `hermes debug share`.
+      label: Relevant Logs / Traceback
+      description: Paste any error output, traceback, or log messages. This will be auto-formatted as code.
       render: shell
 
   - type: textarea

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -71,15 +71,3 @@ body:
       label: Contribution
       options:
         - label: I'd like to implement this myself and submit a PR
-
-  - type: textarea
-    id: debug-report
-    attributes:
-      label: Debug Report (optional)
-      description: |
-        If this feature request is related to a problem you're experiencing, run `hermes debug share` and paste the links here.
-        In an interactive chat session, you can use `/debug` instead.
-        This helps us understand your environment and any related logs.
-      placeholder: |
-        Report   https://paste.rs/abc123
-      render: shell

.github/ISSUE_TEMPLATE/setup_help.yml

@@ -9,8 +9,7 @@ body:
         Sorry you're having trouble! Please fill out the details below so we can help.
 
         **Quick checks first:**
-        - Run `hermes debug share` and paste the links in the Debug Report section below
-        - If you're in a chat session, you can use `/debug` instead — it does the same thing
+        - Run `hermes doctor` and include the output below
         - Try `hermes update` to get the latest version
         - Check the [README troubleshooting section](https://github.com/NousResearch/hermes-agent#troubleshooting)
         - For general questions, consider the [Nous Research Discord](https://discord.gg/NousResearch) for faster help
@@ -75,21 +74,10 @@ body:
       placeholder: "2.1.0"
 
   - type: textarea
-    id: debug-report
+    id: doctor-output
     attributes:
-      label: Debug Report
-      description: |
-        Run `hermes debug share` from your terminal and paste the links it prints here.
-        This uploads your system info, config, and recent logs to a paste service automatically.
-
-        If you're in an interactive chat session, you can also use the `/debug` slash command — it does the same thing.
-
-        If the upload fails or install didn't get that far, run `hermes debug share --local` and paste the output directly.
-        If even that doesn't work, run `hermes doctor` and paste that output instead.
-      placeholder: |
-        Report   https://paste.rs/abc123
-        agent.log   https://paste.rs/def456
-        gateway.log   https://paste.rs/ghi789
+      label: Output of `hermes doctor`
+      description: Run `hermes doctor` and paste the full output. This will be auto-formatted.
       render: shell
 
   - type: textarea

.github/workflows/deploy-site.yml

@@ -41,19 +41,11 @@ jobs:
           python-version: '3.11'
 
       - name: Install PyYAML for skill extraction
-        run: pip install pyyaml httpx
+        run: pip install pyyaml
 
       - name: Extract skill metadata for dashboard
         run: python3 website/scripts/extract-skills.py
 
-      - name: Build skills index (if not already present)
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          if [ ! -f website/static/api/skills-index.json ]; then
-            python3 scripts/build_skills_index.py || echo "Skills index build failed (non-fatal)"
-          fi
-
       - name: Install dependencies
         run: npm ci
         working-directory: website

.github/workflows/docker-publish.yml

@@ -69,7 +69,9 @@ jobs:
           file: Dockerfile
           push: true
           platforms: linux/amd64,linux/arm64
-          tags: nousresearch/hermes-agent:latest
+          tags: |
+            nousresearch/hermes-agent:latest
+            nousresearch/hermes-agent:${{ github.sha }}
           cache-from: type=gha
           cache-to: type=gha,mode=max
 
@@ -81,6 +83,9 @@ jobs:
           file: Dockerfile
           push: true
           platforms: linux/amd64,linux/arm64
-          tags: nousresearch/hermes-agent:${{ github.event.release.tag_name }}
+          tags: |
+            nousresearch/hermes-agent:latest
+            nousresearch/hermes-agent:${{ github.event.release.tag_name }}
+            nousresearch/hermes-agent:${{ github.sha }}
           cache-from: type=gha
           cache-to: type=gha,mode=max

.github/workflows/skills-index.yml

@@ -1,101 +0,0 @@
-name: Build Skills Index
-
-on:
-  schedule:
-    # Run twice daily: 6 AM and 6 PM UTC
-    - cron: '0 6,18 * * *'
-  workflow_dispatch:  # Manual trigger
-  push:
-    branches: [main]
-    paths:
-      - 'scripts/build_skills_index.py'
-      - '.github/workflows/skills-index.yml'
-
-permissions:
-  contents: read
-
-jobs:
-  build-index:
-    # Only run on the upstream repository, not on forks
-    if: github.repository == 'NousResearch/hermes-agent'
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      - uses: actions/setup-python@v5
-        with:
-          python-version: '3.11'
-
-      - name: Install dependencies
-        run: pip install httpx pyyaml
-
-      - name: Build skills index
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: python scripts/build_skills_index.py
-
-      - name: Upload index artifact
-        uses: actions/upload-artifact@v4
-        with:
-          name: skills-index
-          path: website/static/api/skills-index.json
-          retention-days: 7
-
-  deploy-with-index:
-    needs: build-index
-    runs-on: ubuntu-latest
-    permissions:
-      pages: write
-      id-token: write
-    environment:
-      name: github-pages
-      url: ${{ steps.deploy.outputs.page_url }}
-    # Only deploy on schedule or manual trigger (not on every push to the script)
-    if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
-    steps:
-      - uses: actions/checkout@v4
-
-      - uses: actions/download-artifact@v4
-        with:
-          name: skills-index
-          path: website/static/api/
-
-      - uses: actions/setup-node@v4
-        with:
-          node-version: 20
-          cache: npm
-          cache-dependency-path: website/package-lock.json
-
-      - uses: actions/setup-python@v5
-        with:
-          python-version: '3.11'
-
-      - name: Install PyYAML for skill extraction
-        run: pip install pyyaml
-
-      - name: Extract skill metadata for dashboard
-        run: python3 website/scripts/extract-skills.py
-
-      - name: Install dependencies
-        run: npm ci
-        working-directory: website
-
-      - name: Build Docusaurus
-        run: npm run build
-        working-directory: website
-
-      - name: Stage deployment
-        run: |
-          mkdir -p _site/docs
-          cp -r landingpage/* _site/
-          cp -r website/build/* _site/docs/
-          echo "hermes-agent.nousresearch.com" > _site/CNAME
-
-      - name: Upload artifact
-        uses: actions/upload-pages-artifact@v3
-        with:
-          path: _site
-
-      - name: Deploy to GitHub Pages
-        id: deploy
-        uses: actions/deploy-pages@v4

.github/workflows/supply-chain-audit.yml

@@ -183,7 +183,7 @@ jobs:
           ---
           *Automated scan triggered by [supply-chain-audit](/.github/workflows/supply-chain-audit.yml). If this is a false positive, a maintainer can approve after manual review.*"
 
-          gh pr comment "${{ github.event.pull_request.number }}" --body "$BODY" || echo "::warning::Could not post PR comment (expected for fork PRs — GITHUB_TOKEN is read-only)"
+          gh pr comment "${{ github.event.pull_request.number }}" --body "$BODY"
 
       - name: Fail on critical findings
         if: steps.scan.outputs.critical == 'true'

.gitignore

@@ -51,9 +51,6 @@ ignored/
 .worktrees/
 environments/benchmarks/evals/
 
-# Web UI build output
-hermes_cli/web_dist/
-
 # Release script temp files
 .release_notes.md
 mini-swe-agent/
@@ -61,4 +58,3 @@ mini-swe-agent/
 # Nix
 .direnv/
 result
-website/static/api/skills-index.json

AGENTS.md

@@ -351,9 +351,8 @@ Cache-breaking forces dramatically higher costs. The ONLY time we alter context
 
 ### Background Process Notifications (Gateway)
 
-When `terminal(background=true, notify_on_complete=true)` is used, the gateway runs a watcher that
-detects process completion and triggers a new agent turn. Control verbosity of background process
-messages with `display.background_process_notifications`
+When `terminal(background=true, check_interval=...)` is used, the gateway runs a watcher that
+pushes status updates to the user's chat. Control verbosity with `display.background_process_notifications`
 in config.yaml (or `HERMES_BACKGROUND_NOTIFICATIONS` env var):
 
 - `all` — running-output updates + final message (default)

Dockerfile

@@ -1,44 +1,27 @@
-FROM ghcr.io/astral-sh/uv:0.11.6-python3.13-trixie@sha256:b3c543b6c4f23a5f2df22866bd7857e5d304b67a564f4feab6ac22044dde719b AS uv_source
-FROM tianon/gosu:1.19-trixie@sha256:3b176695959c71e123eb390d427efc665eeb561b1540e82679c15e992006b8b9 AS gosu_source
 FROM debian:13.4
 
 # Disable Python stdout buffering to ensure logs are printed immediately
 ENV PYTHONUNBUFFERED=1
 
-# Store Playwright browsers outside the volume mount so the build-time
-# install survives the /opt/data volume overlay at runtime.
-ENV PLAYWRIGHT_BROWSERS_PATH=/opt/hermes/.playwright
-
 # Install system dependencies in one layer, clear APT cache
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
-        build-essential nodejs npm python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git && \
+        build-essential nodejs npm python3 python3-pip ripgrep ffmpeg gcc python3-dev libffi-dev && \
     rm -rf /var/lib/apt/lists/*
 
-# Non-root user for runtime; UID can be overridden via HERMES_UID at runtime
-RUN useradd -u 10000 -m -d /opt/data hermes
-
-COPY --chmod=0755 --from=gosu_source /gosu /usr/local/bin/
-COPY --chmod=0755 --from=uv_source /usr/local/bin/uv /usr/local/bin/uvx /usr/local/bin/
-
 COPY . /opt/hermes
 WORKDIR /opt/hermes
 
-# Install Node dependencies and Playwright as root (--with-deps needs apt)
-RUN npm install --prefer-offline --no-audit && \
+# Install Python and Node dependencies in one layer, no cache
+RUN pip install --no-cache-dir uv --break-system-packages && \
+    uv pip install --system --break-system-packages --no-cache -e ".[all]" && \
+    npm install --prefer-offline --no-audit && \
     npx playwright install --with-deps chromium --only-shell && \
     cd /opt/hermes/scripts/whatsapp-bridge && \
     npm install --prefer-offline --no-audit && \
     npm cache clean --force
 
-# Hand ownership to hermes user, then install Python deps in a virtualenv
-RUN chown -R hermes:hermes /opt/hermes
-USER hermes
-
-RUN uv venv && \
-    uv pip install --no-cache-dir -e ".[all]"
-
-USER root
+WORKDIR /opt/hermes
 RUN chmod +x /opt/hermes/docker/entrypoint.sh
 
 ENV HERMES_HOME=/opt/data

README.md

@@ -167,7 +167,6 @@ python -m pytest tests/ -q
 - 📚 [Skills Hub](https://agentskills.io)
 - 🐛 [Issues](https://github.com/NousResearch/hermes-agent/issues)
 - 💡 [Discussions](https://github.com/NousResearch/hermes-agent/discussions)
-- 🔌 [HermesClaw](https://github.com/AaronWong1999/hermesclaw) — Community WeChat bridge: Run Hermes Agent and OpenClaw on the same WeChat account.
 
 ---
 

RELEASE_v0.9.0.md

@@ -1,329 +0,0 @@
-# Hermes Agent v0.9.0 (v2026.4.13)
-
-**Release Date:** April 13, 2026
-**Since v0.8.0:** 487 commits · 269 merged PRs · 167 resolved issues · 493 files changed · 63,281 insertions · 24 contributors
-
-> The everywhere release — Hermes goes mobile with Termux/Android, adds iMessage and WeChat, ships Fast Mode for OpenAI and Anthropic, introduces background process monitoring, launches a local web dashboard for managing your agent, and delivers the deepest security hardening pass yet across 16 supported platforms.
-
----
-
-## ✨ Highlights
-
-- **Local Web Dashboard** — A new browser-based dashboard for managing your Hermes Agent locally. Configure settings, monitor sessions, browse skills, and manage your gateway — all from a clean web interface without touching config files or the terminal. The easiest way to get started with Hermes.
-
-- **Fast Mode (`/fast`)** — Priority processing for OpenAI and Anthropic models. Toggle `/fast` to route through priority queues for significantly lower latency on supported models (GPT-5.4, Codex, Claude). Expands across all OpenAI Priority Processing models and Anthropic's fast tier. ([#6875](https://github.com/NousResearch/hermes-agent/pull/6875), [#6960](https://github.com/NousResearch/hermes-agent/pull/6960), [#7037](https://github.com/NousResearch/hermes-agent/pull/7037))
-
-- **iMessage via BlueBubbles** — Full iMessage integration through BlueBubbles, bringing Hermes to Apple's messaging ecosystem. Auto-webhook registration, setup wizard integration, and crash resilience. ([#6437](https://github.com/NousResearch/hermes-agent/pull/6437), [#6460](https://github.com/NousResearch/hermes-agent/pull/6460), [#6494](https://github.com/NousResearch/hermes-agent/pull/6494))
-
-- **WeChat (Weixin) & WeCom Callback Mode** — Native WeChat support via iLink Bot API and a new WeCom callback-mode adapter for self-built enterprise apps. Streaming cursor, media uploads, markdown link handling, and atomic state persistence. Hermes now covers the Chinese messaging ecosystem end-to-end. ([#7166](https://github.com/NousResearch/hermes-agent/pull/7166), [#7943](https://github.com/NousResearch/hermes-agent/pull/7943))
-
-- **Termux / Android Support** — Run Hermes natively on Android via Termux. Adapted install paths, TUI optimizations for mobile screens, voice backend support, and the `/image` command work on-device. ([#6834](https://github.com/NousResearch/hermes-agent/pull/6834))
-
-- **Background Process Monitoring (`watch_patterns`)** — Set patterns to watch for in background process output and get notified in real-time when they match. Monitor for errors, wait for specific events ("listening on port"), or watch build logs — all without polling. ([#7635](https://github.com/NousResearch/hermes-agent/pull/7635))
-
-- **Native xAI & Xiaomi MiMo Providers** — First-class provider support for xAI (Grok) and Xiaomi MiMo, with direct API access, model catalogs, and setup wizard integration. Plus Qwen OAuth with portal request support. ([#7372](https://github.com/NousResearch/hermes-agent/pull/7372), [#7855](https://github.com/NousResearch/hermes-agent/pull/7855))
-
-- **Pluggable Context Engine** — Context management is now a pluggable slot via `hermes plugins`. Swap in custom context engines that control what the agent sees each turn — filtering, summarization, or domain-specific context injection. ([#7464](https://github.com/NousResearch/hermes-agent/pull/7464))
-
-- **Unified Proxy Support** — SOCKS proxy, `DISCORD_PROXY`, and system proxy auto-detection across all gateway platforms. Hermes behind corporate firewalls just works. ([#6814](https://github.com/NousResearch/hermes-agent/pull/6814))
-
-- **Comprehensive Security Hardening** — Path traversal protection in checkpoint manager, shell injection neutralization in sandbox writes, SSRF redirect guards in Slack image uploads, Twilio webhook signature validation (SMS RCE fix), API server auth enforcement, git argument injection prevention, and approval button authorization. ([#7933](https://github.com/NousResearch/hermes-agent/pull/7933), [#7944](https://github.com/NousResearch/hermes-agent/pull/7944), [#7940](https://github.com/NousResearch/hermes-agent/pull/7940), [#7151](https://github.com/NousResearch/hermes-agent/pull/7151), [#7156](https://github.com/NousResearch/hermes-agent/pull/7156))
-
-- **`hermes backup` & `hermes import`** — Full backup and restore of your Hermes configuration, sessions, skills, and memory. Migrate between machines or create snapshots before major changes. ([#7997](https://github.com/NousResearch/hermes-agent/pull/7997))
-
-- **16 Supported Platforms** — With BlueBubbles (iMessage) and WeChat joining Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Email, SMS, DingTalk, Feishu, WeCom, Mattermost, Home Assistant, and Webhooks, Hermes now runs on 16 messaging platforms out of the box.
-
-- **`/debug` & `hermes debug share`** — New debugging toolkit: `/debug` slash command across all platforms for quick diagnostics, plus `hermes debug share` to upload a full debug report to a pastebin for easy sharing when troubleshooting. ([#8681](https://github.com/NousResearch/hermes-agent/pull/8681))
-
----
-
-## 🏗️ Core Agent & Architecture
-
-### Provider & Model Support
-- **Native xAI (Grok) provider** with direct API access and model catalog ([#7372](https://github.com/NousResearch/hermes-agent/pull/7372))
-- **Xiaomi MiMo as first-class provider** — setup wizard, model catalog, empty response recovery ([#7855](https://github.com/NousResearch/hermes-agent/pull/7855))
-- **Qwen OAuth provider** with portal request support ([#6282](https://github.com/NousResearch/hermes-agent/pull/6282))
-- **Fast Mode** — `/fast` toggle for OpenAI Priority Processing + Anthropic fast tier ([#6875](https://github.com/NousResearch/hermes-agent/pull/6875), [#6960](https://github.com/NousResearch/hermes-agent/pull/6960), [#7037](https://github.com/NousResearch/hermes-agent/pull/7037))
-- **Structured API error classification** for smart failover decisions ([#6514](https://github.com/NousResearch/hermes-agent/pull/6514))
-- **Rate limit header capture** shown in `/usage` ([#6541](https://github.com/NousResearch/hermes-agent/pull/6541))
-- **API server model name** derived from profile name ([#6857](https://github.com/NousResearch/hermes-agent/pull/6857))
-- **Custom providers** now included in `/model` listings and resolution ([#7088](https://github.com/NousResearch/hermes-agent/pull/7088))
-- **Fallback provider activation** on repeated empty responses with user-visible status ([#7505](https://github.com/NousResearch/hermes-agent/pull/7505))
-- **OpenRouter variant tags** (`:free`, `:extended`, `:fast`) preserved during model switch ([#6383](https://github.com/NousResearch/hermes-agent/pull/6383))
-- **Credential exhaustion TTL** reduced from 24 hours to 1 hour ([#6504](https://github.com/NousResearch/hermes-agent/pull/6504))
-- **OAuth credential lifecycle** hardening — stale pool keys, auth.json sync, Codex CLI race fixes ([#6874](https://github.com/NousResearch/hermes-agent/pull/6874))
-- Empty response recovery for reasoning models (MiMo, Qwen, GLM) ([#8609](https://github.com/NousResearch/hermes-agent/pull/8609))
-- MiniMax context lengths, thinking guard, endpoint corrections ([#6082](https://github.com/NousResearch/hermes-agent/pull/6082), [#7126](https://github.com/NousResearch/hermes-agent/pull/7126))
-- Z.AI endpoint auto-detect via probe and cache ([#5763](https://github.com/NousResearch/hermes-agent/pull/5763))
-
-### Agent Loop & Conversation
-- **Pluggable context engine slot** via `hermes plugins` ([#7464](https://github.com/NousResearch/hermes-agent/pull/7464))
-- **Background process monitoring** — `watch_patterns` for real-time output alerts ([#7635](https://github.com/NousResearch/hermes-agent/pull/7635))
-- **Improved context compression** — higher limits, tool tracking, degradation warnings, token-budget tail protection ([#6395](https://github.com/NousResearch/hermes-agent/pull/6395), [#6453](https://github.com/NousResearch/hermes-agent/pull/6453))
-- **`/compress <focus>`** — guided compression with a focus topic ([#8017](https://github.com/NousResearch/hermes-agent/pull/8017))
-- **Tiered context pressure warnings** with gateway dedup ([#6411](https://github.com/NousResearch/hermes-agent/pull/6411))
-- **Staged inactivity warning** before timeout escalation ([#6387](https://github.com/NousResearch/hermes-agent/pull/6387))
-- **Prevent agent from stopping mid-task** — compression floor, budget overhaul, activity tracking ([#7983](https://github.com/NousResearch/hermes-agent/pull/7983))
-- **Propagate child activity to parent** during `delegate_task` ([#7295](https://github.com/NousResearch/hermes-agent/pull/7295))
-- **Truncated streaming tool call detection** before execution ([#6847](https://github.com/NousResearch/hermes-agent/pull/6847))
-- Empty response retry (3 attempts with nudge) ([#6488](https://github.com/NousResearch/hermes-agent/pull/6488))
-- Adaptive streaming backoff + cursor strip to prevent message truncation ([#7683](https://github.com/NousResearch/hermes-agent/pull/7683))
-- Compression uses live session model instead of stale persisted config ([#8258](https://github.com/NousResearch/hermes-agent/pull/8258))
-- Strip `<thought>` tags from Gemma 4 responses ([#8562](https://github.com/NousResearch/hermes-agent/pull/8562))
-- Prevent `<think>` in prose from suppressing response output ([#6968](https://github.com/NousResearch/hermes-agent/pull/6968))
-- Turn-exit diagnostic logging to agent loop ([#6549](https://github.com/NousResearch/hermes-agent/pull/6549))
-- Scope tool interrupt signal per-thread to prevent cross-session leaks ([#7930](https://github.com/NousResearch/hermes-agent/pull/7930))
-
-### Memory & Sessions
-- **Hindsight memory plugin** — feature parity, setup wizard, config improvements — @nicoloboschi ([#6428](https://github.com/NousResearch/hermes-agent/pull/6428))
-- **Honcho** — opt-in `initOnSessionStart` for tools mode — @Kathie-yu ([#6995](https://github.com/NousResearch/hermes-agent/pull/6995))
-- Orphan children instead of cascade-deleting in prune/delete ([#6513](https://github.com/NousResearch/hermes-agent/pull/6513))
-- Doctor command only checks the active memory provider ([#6285](https://github.com/NousResearch/hermes-agent/pull/6285))
-
----
-
-## 📱 Messaging Platforms (Gateway)
-
-### New Platforms
-- **BlueBubbles (iMessage)** — full adapter with auto-webhook registration, setup wizard, and crash resilience ([#6437](https://github.com/NousResearch/hermes-agent/pull/6437), [#6460](https://github.com/NousResearch/hermes-agent/pull/6460), [#6494](https://github.com/NousResearch/hermes-agent/pull/6494), [#7107](https://github.com/NousResearch/hermes-agent/pull/7107))
-- **Weixin (WeChat)** — native support via iLink Bot API with streaming, media uploads, markdown links ([#7166](https://github.com/NousResearch/hermes-agent/pull/7166), [#8665](https://github.com/NousResearch/hermes-agent/pull/8665))
-- **WeCom Callback Mode** — self-built enterprise app adapter with atomic state persistence ([#7943](https://github.com/NousResearch/hermes-agent/pull/7943), [#7928](https://github.com/NousResearch/hermes-agent/pull/7928))
-
-### Discord
-- **Allowed channels whitelist** config — @jarvis-phw ([#7044](https://github.com/NousResearch/hermes-agent/pull/7044))
-- **Forum channel topic inheritance** in thread sessions — @hermes-agent-dhabibi ([#6377](https://github.com/NousResearch/hermes-agent/pull/6377))
-- **DISCORD_REPLY_TO_MODE** setting ([#6333](https://github.com/NousResearch/hermes-agent/pull/6333))
-- Accept `.log` attachments, raise document size limit — @kira-ariaki ([#6467](https://github.com/NousResearch/hermes-agent/pull/6467))
-- Decouple readiness from slash sync ([#8016](https://github.com/NousResearch/hermes-agent/pull/8016))
-
-### Slack
-- **Consolidated Slack improvements** — 7 community PRs salvaged into one ([#6809](https://github.com/NousResearch/hermes-agent/pull/6809))
-- Handle assistant thread lifecycle events ([#6433](https://github.com/NousResearch/hermes-agent/pull/6433))
-
-### Matrix
-- **Migrated from matrix-nio to mautrix-python** ([#7518](https://github.com/NousResearch/hermes-agent/pull/7518))
-- SQLite crypto store replacing pickle (fixes E2EE decryption) — @alt-glitch ([#7981](https://github.com/NousResearch/hermes-agent/pull/7981))
-- Cross-signing recovery key verification for E2EE migration ([#8282](https://github.com/NousResearch/hermes-agent/pull/8282))
-- DM mention threads + group chat events for Feishu ([#7423](https://github.com/NousResearch/hermes-agent/pull/7423))
-
-### Gateway Core
-- **Unified proxy support** — SOCKS, DISCORD_PROXY, multi-platform with macOS auto-detection ([#6814](https://github.com/NousResearch/hermes-agent/pull/6814))
-- **Inbound text batching** for Discord, Matrix, WeCom + adaptive delay ([#6979](https://github.com/NousResearch/hermes-agent/pull/6979))
-- **Surface natural mid-turn assistant messages** in chat platforms ([#7978](https://github.com/NousResearch/hermes-agent/pull/7978))
-- **WSL-aware gateway** with smart systemd detection ([#7510](https://github.com/NousResearch/hermes-agent/pull/7510))
-- **All missing platforms added to setup wizard** ([#7949](https://github.com/NousResearch/hermes-agent/pull/7949))
-- **Per-platform `tool_progress` overrides** ([#6348](https://github.com/NousResearch/hermes-agent/pull/6348))
-- **Configurable 'still working' notification interval** ([#8572](https://github.com/NousResearch/hermes-agent/pull/8572))
-- `/model` switch persists across messages ([#7081](https://github.com/NousResearch/hermes-agent/pull/7081))
-- `/usage` shows rate limits, cost, and token details between turns ([#7038](https://github.com/NousResearch/hermes-agent/pull/7038))
-- Drain in-flight work before restart ([#7503](https://github.com/NousResearch/hermes-agent/pull/7503))
-- Don't evict cached agent on failed runs — prevents MCP restart loop ([#7539](https://github.com/NousResearch/hermes-agent/pull/7539))
-- Replace `os.environ` session state with `contextvars` ([#7454](https://github.com/NousResearch/hermes-agent/pull/7454))
-- Derive channel directory platforms from enum instead of hardcoded list ([#7450](https://github.com/NousResearch/hermes-agent/pull/7450))
-- Validate image downloads before caching (cross-platform) ([#7125](https://github.com/NousResearch/hermes-agent/pull/7125))
-- Cross-platform webhook delivery for all platforms ([#7095](https://github.com/NousResearch/hermes-agent/pull/7095))
-- Cron Discord thread_id delivery support ([#7106](https://github.com/NousResearch/hermes-agent/pull/7106))
-- Feishu QR-based bot onboarding ([#8570](https://github.com/NousResearch/hermes-agent/pull/8570))
-- Gateway status scoped to active profile ([#7951](https://github.com/NousResearch/hermes-agent/pull/7951))
-- Prevent background process notifications from triggering false pairing requests ([#6434](https://github.com/NousResearch/hermes-agent/pull/6434))
-
----
-
-## 🖥️ CLI & User Experience
-
-### Interactive CLI
-- **Termux / Android support** — adapted install paths, TUI, voice, `/image` ([#6834](https://github.com/NousResearch/hermes-agent/pull/6834))
-- **Native `/model` picker modal** for provider → model selection ([#8003](https://github.com/NousResearch/hermes-agent/pull/8003))
-- **Live per-tool elapsed timer** restored in TUI spinner ([#7359](https://github.com/NousResearch/hermes-agent/pull/7359))
-- **Stacked tool progress scrollback** in TUI ([#8201](https://github.com/NousResearch/hermes-agent/pull/8201))
-- **Random tips on new session start** (CLI + gateway, 279 tips) ([#8225](https://github.com/NousResearch/hermes-agent/pull/8225), [#8237](https://github.com/NousResearch/hermes-agent/pull/8237))
-- **`hermes dump`** — copy-pasteable setup summary for debugging ([#6550](https://github.com/NousResearch/hermes-agent/pull/6550))
-- **`hermes backup` / `hermes import`** — full config backup and restore ([#7997](https://github.com/NousResearch/hermes-agent/pull/7997))
-- **WSL environment hint** in system prompt ([#8285](https://github.com/NousResearch/hermes-agent/pull/8285))
-- **Profile creation UX** — seed SOUL.md + credential warning ([#8553](https://github.com/NousResearch/hermes-agent/pull/8553))
-- Shell-aware sudo detection, empty password support ([#6517](https://github.com/NousResearch/hermes-agent/pull/6517))
-- Flush stdin after curses/terminal menus to prevent escape sequence leakage ([#7167](https://github.com/NousResearch/hermes-agent/pull/7167))
-- Handle broken stdin in prompt_toolkit startup ([#8560](https://github.com/NousResearch/hermes-agent/pull/8560))
-
-### Setup & Configuration
-- **Per-platform display verbosity** configuration ([#8006](https://github.com/NousResearch/hermes-agent/pull/8006))
-- **Component-separated logging** with session context and filtering ([#7991](https://github.com/NousResearch/hermes-agent/pull/7991))
-- **`network.force_ipv4`** config to fix IPv6 timeout issues ([#8196](https://github.com/NousResearch/hermes-agent/pull/8196))
-- **Standardize message whitespace and JSON formatting** ([#7988](https://github.com/NousResearch/hermes-agent/pull/7988))
-- **Rebrand OpenClaw → Hermes** during migration ([#8210](https://github.com/NousResearch/hermes-agent/pull/8210))
-- Config.yaml takes priority over env vars for auxiliary settings ([#7889](https://github.com/NousResearch/hermes-agent/pull/7889))
-- Harden setup provider flows + live OpenRouter catalog refresh ([#7078](https://github.com/NousResearch/hermes-agent/pull/7078))
-- Normalize reasoning effort ordering across all surfaces ([#6804](https://github.com/NousResearch/hermes-agent/pull/6804))
-- Remove dead `LLM_MODEL` env var + migration to clear stale entries ([#6543](https://github.com/NousResearch/hermes-agent/pull/6543))
-- Remove `/prompt` slash command — prefix expansion footgun ([#6752](https://github.com/NousResearch/hermes-agent/pull/6752))
-- `HERMES_HOME_MODE` env var to override permissions — @ygd58 ([#6993](https://github.com/NousResearch/hermes-agent/pull/6993))
-- Fall back to default model when model config is empty ([#8303](https://github.com/NousResearch/hermes-agent/pull/8303))
-- Warn when compression model context is too small ([#7894](https://github.com/NousResearch/hermes-agent/pull/7894))
-
----
-
-## 🔧 Tool System
-
-### Environments & Execution
-- **Unified spawn-per-call execution layer** for environments ([#6343](https://github.com/NousResearch/hermes-agent/pull/6343))
-- **Unified file sync** with mtime tracking, deletion, and transactional state ([#7087](https://github.com/NousResearch/hermes-agent/pull/7087))
-- **Persistent sandbox envs** survive between turns ([#6412](https://github.com/NousResearch/hermes-agent/pull/6412))
-- **Bulk file sync** via tar pipe for SSH/Modal backends — @alt-glitch ([#8014](https://github.com/NousResearch/hermes-agent/pull/8014))
-- **Daytona** — bulk upload, config bridge, silent disk cap ([#7538](https://github.com/NousResearch/hermes-agent/pull/7538))
-- Foreground timeout cap to prevent session deadlocks ([#7082](https://github.com/NousResearch/hermes-agent/pull/7082))
-- Guard invalid command values ([#6417](https://github.com/NousResearch/hermes-agent/pull/6417))
-
-### MCP
-- **`hermes mcp add --env` and `--preset`** support ([#7970](https://github.com/NousResearch/hermes-agent/pull/7970))
-- Combine `content` and `structuredContent` when both present ([#7118](https://github.com/NousResearch/hermes-agent/pull/7118))
-- MCP tool name deconfliction fixes ([#7654](https://github.com/NousResearch/hermes-agent/pull/7654))
-
-### Browser
-- Browser hardening — dead code removal, caching, scroll perf, security, thread safety ([#7354](https://github.com/NousResearch/hermes-agent/pull/7354))
-- `/browser connect` auto-launch uses dedicated Chrome profile dir ([#6821](https://github.com/NousResearch/hermes-agent/pull/6821))
-- Reap orphaned browser sessions on startup ([#7931](https://github.com/NousResearch/hermes-agent/pull/7931))
-
-### Voice & Vision
-- **Voxtral TTS provider** (Mistral AI) ([#7653](https://github.com/NousResearch/hermes-agent/pull/7653))
-- **TTS speed support** for Edge TTS, OpenAI TTS, MiniMax ([#8666](https://github.com/NousResearch/hermes-agent/pull/8666))
-- **Vision auto-resize** for oversized images, raise limit to 20 MB, retry-on-failure ([#7883](https://github.com/NousResearch/hermes-agent/pull/7883), [#7902](https://github.com/NousResearch/hermes-agent/pull/7902))
-- STT provider-model mismatch fix (whisper-1 vs faster-whisper) ([#7113](https://github.com/NousResearch/hermes-agent/pull/7113))
-
-### Other Tools
-- **`hermes dump`** command for setup summary ([#6550](https://github.com/NousResearch/hermes-agent/pull/6550))
-- TODO store enforces ID uniqueness during replace operations ([#7986](https://github.com/NousResearch/hermes-agent/pull/7986))
-- List all available toolsets in `delegate_task` schema description ([#8231](https://github.com/NousResearch/hermes-agent/pull/8231))
-- API server: tool progress as custom SSE event to prevent model corruption ([#7500](https://github.com/NousResearch/hermes-agent/pull/7500))
-- API server: share one Docker container across all conversations ([#7127](https://github.com/NousResearch/hermes-agent/pull/7127))
-
----
-
-## 🧩 Skills Ecosystem
-
-- **Centralized skills index + tree cache** — eliminates rate-limit failures on install ([#8575](https://github.com/NousResearch/hermes-agent/pull/8575))
-- **More aggressive skill loading instructions** in system prompt (v3) ([#8209](https://github.com/NousResearch/hermes-agent/pull/8209), [#8286](https://github.com/NousResearch/hermes-agent/pull/8286))
-- **Google Workspace skill** migrated to GWS CLI backend ([#6788](https://github.com/NousResearch/hermes-agent/pull/6788))
-- **Creative divergence strategies** skill — @SHL0MS ([#6882](https://github.com/NousResearch/hermes-agent/pull/6882))
-- **Creative ideation** — constraint-driven project generation — @SHL0MS ([#7555](https://github.com/NousResearch/hermes-agent/pull/7555))
-- Parallelize skills browse/search to prevent hanging ([#7301](https://github.com/NousResearch/hermes-agent/pull/7301))
-- Read name from SKILL.md frontmatter in skills_sync ([#7623](https://github.com/NousResearch/hermes-agent/pull/7623))
-
----
-
-## 🔒 Security & Reliability
-
-### Security Hardening
-- **Twilio webhook signature validation** — SMS RCE fix ([#7933](https://github.com/NousResearch/hermes-agent/pull/7933))
-- **Shell injection neutralization** in `_write_to_sandbox` via path quoting ([#7940](https://github.com/NousResearch/hermes-agent/pull/7940))
-- **Git argument injection** and path traversal prevention in checkpoint manager ([#7944](https://github.com/NousResearch/hermes-agent/pull/7944))
-- **SSRF redirect bypass** in Slack image uploads + base.py cache helpers ([#7151](https://github.com/NousResearch/hermes-agent/pull/7151))
-- **Path traversal, credential gate, DANGEROUS_PATTERNS gaps** ([#7156](https://github.com/NousResearch/hermes-agent/pull/7156))
-- **API bind guard** — enforce `API_SERVER_KEY` for non-loopback binding ([#7455](https://github.com/NousResearch/hermes-agent/pull/7455))
-- **Approval button authorization** — require auth for session continuation — @Cafexss ([#6930](https://github.com/NousResearch/hermes-agent/pull/6930))
-- Path boundary enforcement in skill manager operations ([#7156](https://github.com/NousResearch/hermes-agent/pull/7156))
-- DingTalk/API webhook URL origin validation, header injection rejection ([#7455](https://github.com/NousResearch/hermes-agent/pull/7455))
-
-### Reliability
-- **Contextual error diagnostics** for invalid API responses ([#8565](https://github.com/NousResearch/hermes-agent/pull/8565))
-- **Prevent 400 format errors** from triggering compression loop on Codex ([#6751](https://github.com/NousResearch/hermes-agent/pull/6751))
-- **Don't halve context_length** on output-cap-too-large errors — @KUSH42 ([#6664](https://github.com/NousResearch/hermes-agent/pull/6664))
-- **Recover primary client** on OpenAI transport errors ([#7108](https://github.com/NousResearch/hermes-agent/pull/7108))
-- **Credential pool rotation** on billing-classified 400s ([#7112](https://github.com/NousResearch/hermes-agent/pull/7112))
-- **Auto-increase stream read timeout** for local LLM providers ([#6967](https://github.com/NousResearch/hermes-agent/pull/6967))
-- **Fall back to default certs** when CA bundle path doesn't exist ([#7352](https://github.com/NousResearch/hermes-agent/pull/7352))
-- **Disambiguate usage-limit patterns** in error classifier — @sprmn24 ([#6836](https://github.com/NousResearch/hermes-agent/pull/6836))
-- Harden cron script timeout and provider recovery ([#7079](https://github.com/NousResearch/hermes-agent/pull/7079))
-- Gateway interrupt detection resilient to monitor task failures ([#8208](https://github.com/NousResearch/hermes-agent/pull/8208))
-- Prevent unwanted session auto-reset after graceful gateway restarts ([#8299](https://github.com/NousResearch/hermes-agent/pull/8299))
-- Prevent duplicate update prompt spam in gateway watcher ([#8343](https://github.com/NousResearch/hermes-agent/pull/8343))
-- Deduplicate reasoning items in Responses API input ([#7946](https://github.com/NousResearch/hermes-agent/pull/7946))
-
-### Infrastructure
-- **Multi-arch Docker image** — amd64 + arm64 ([#6124](https://github.com/NousResearch/hermes-agent/pull/6124))
-- **Docker runs as non-root user** with virtualenv — @benbarclay contributing ([#8226](https://github.com/NousResearch/hermes-agent/pull/8226))
-- **Use `uv`** for Docker dependency resolution to fix resolution-too-deep ([#6965](https://github.com/NousResearch/hermes-agent/pull/6965))
-- **Container-aware Nix CLI** — auto-route into managed container — @alt-glitch ([#7543](https://github.com/NousResearch/hermes-agent/pull/7543))
-- **Nix shared-state permission model** for interactive CLI users — @alt-glitch ([#6796](https://github.com/NousResearch/hermes-agent/pull/6796))
-- **Per-profile subprocess HOME isolation** ([#7357](https://github.com/NousResearch/hermes-agent/pull/7357))
-- Profile paths fixed in Docker — profiles go to mounted volume ([#7170](https://github.com/NousResearch/hermes-agent/pull/7170))
-- Docker container gateway pathway hardened ([#8614](https://github.com/NousResearch/hermes-agent/pull/8614))
-- Enable unbuffered stdout for live Docker logs ([#6749](https://github.com/NousResearch/hermes-agent/pull/6749))
-- Install procps in Docker image — @HiddenPuppy ([#7032](https://github.com/NousResearch/hermes-agent/pull/7032))
-- Shallow git clone for faster installation — @sosyz ([#8396](https://github.com/NousResearch/hermes-agent/pull/8396))
-- `hermes update` always reset on stash conflict ([#7010](https://github.com/NousResearch/hermes-agent/pull/7010))
-- Write update exit code before gateway restart (cgroup kill race) ([#8288](https://github.com/NousResearch/hermes-agent/pull/8288))
-- Nix: `setupSecrets` optional, tirith runtime dep — @devorun, @ethernet8023 ([#6261](https://github.com/NousResearch/hermes-agent/pull/6261), [#6721](https://github.com/NousResearch/hermes-agent/pull/6721))
-- launchd stop uses `bootout` so `KeepAlive` doesn't respawn ([#7119](https://github.com/NousResearch/hermes-agent/pull/7119))
-
----
-
-## 🐛 Notable Bug Fixes
-
-- Fix: `/model` switch not persisting across gateway messages ([#7081](https://github.com/NousResearch/hermes-agent/pull/7081))
-- Fix: session-scoped gateway model overrides ignored — @Hygaard ([#7662](https://github.com/NousResearch/hermes-agent/pull/7662))
-- Fix: compaction model context length ignoring config — 3 related issues ([#8258](https://github.com/NousResearch/hermes-agent/pull/8258), [#8107](https://github.com/NousResearch/hermes-agent/pull/8107))
-- Fix: OpenCode.ai context window resolved to 128K instead of 1M ([#6472](https://github.com/NousResearch/hermes-agent/pull/6472))
-- Fix: Codex fallback auth-store lookup — @cherifya ([#6462](https://github.com/NousResearch/hermes-agent/pull/6462))
-- Fix: duplicate completion notifications when process killed ([#7124](https://github.com/NousResearch/hermes-agent/pull/7124))
-- Fix: agent daemon thread prevents orphan CLI processes on tab close ([#8557](https://github.com/NousResearch/hermes-agent/pull/8557))
-- Fix: stale image attachment on text paste and voice input ([#7077](https://github.com/NousResearch/hermes-agent/pull/7077))
-- Fix: DM thread session seeding causing cross-thread contamination ([#7084](https://github.com/NousResearch/hermes-agent/pull/7084))
-- Fix: OpenClaw migration shows dry-run preview before executing ([#6769](https://github.com/NousResearch/hermes-agent/pull/6769))
-- Fix: auth errors misclassified as retryable — @kuishou68 ([#7027](https://github.com/NousResearch/hermes-agent/pull/7027))
-- Fix: Copilot-Integration-Id header missing ([#7083](https://github.com/NousResearch/hermes-agent/pull/7083))
-- Fix: ACP session capabilities — @luyao618 ([#6985](https://github.com/NousResearch/hermes-agent/pull/6985))
-- Fix: ACP PromptResponse usage from top-level fields ([#7086](https://github.com/NousResearch/hermes-agent/pull/7086))
-- Fix: several failing/flaky tests on main — @dsocolobsky ([#6777](https://github.com/NousResearch/hermes-agent/pull/6777))
-- Fix: backup marker filenames — @sprmn24 ([#8600](https://github.com/NousResearch/hermes-agent/pull/8600))
-- Fix: `NoneType` in fast_mode check — @0xbyt4 ([#7350](https://github.com/NousResearch/hermes-agent/pull/7350))
-- Fix: missing imports in uninstall.py — @JiayuuWang ([#7034](https://github.com/NousResearch/hermes-agent/pull/7034))
-
----
-
-## 📚 Documentation
-
-- Platform adapter developer guide + WeCom Callback docs ([#7969](https://github.com/NousResearch/hermes-agent/pull/7969))
-- Cron troubleshooting guide ([#7122](https://github.com/NousResearch/hermes-agent/pull/7122))
-- Streaming timeout auto-detection for local LLMs ([#6990](https://github.com/NousResearch/hermes-agent/pull/6990))
-- Tool-use enforcement documentation expanded ([#7984](https://github.com/NousResearch/hermes-agent/pull/7984))
-- BlueBubbles pairing instructions ([#6548](https://github.com/NousResearch/hermes-agent/pull/6548))
-- Telegram proxy support section ([#6348](https://github.com/NousResearch/hermes-agent/pull/6348))
-- `hermes dump` and `hermes logs` CLI reference ([#6552](https://github.com/NousResearch/hermes-agent/pull/6552))
-- `tool_progress_overrides` configuration reference ([#6364](https://github.com/NousResearch/hermes-agent/pull/6364))
-- Compression model context length warning docs ([#7879](https://github.com/NousResearch/hermes-agent/pull/7879))
-
----
-
-## 👥 Contributors
-
-**269 merged PRs** from **24 contributors** across **487 commits**.
-
-### Community Contributors
-- **@alt-glitch** (6 PRs) — Nix container-aware CLI, shared-state permissions, Matrix SQLite crypto store, bulk SSH/Modal file sync, Matrix mautrix compat
-- **@SHL0MS** (2 PRs) — Creative divergence strategies skill, creative ideation skill
-- **@sprmn24** (2 PRs) — Error classifier disambiguation, backup marker fix
-- **@nicoloboschi** — Hindsight memory plugin feature parity
-- **@Hygaard** — Session-scoped gateway model override fix
-- **@jarvis-phw** — Discord allowed_channels whitelist
-- **@Kathie-yu** — Honcho initOnSessionStart for tools mode
-- **@hermes-agent-dhabibi** — Discord forum channel topic inheritance
-- **@kira-ariaki** — Discord .log attachments and size limit
-- **@cherifya** — Codex fallback auth-store lookup
-- **@Cafexss** — Security: auth for session continuation
-- **@KUSH42** — Compaction context_length fix
-- **@kuishou68** — Auth error retryable classification fix
-- **@luyao618** — ACP session capabilities
-- **@ygd58** — HERMES_HOME_MODE env var override
-- **@0xbyt4** — Fast mode NoneType fix
-- **@JiayuuWang** — CLI uninstall import fix
-- **@HiddenPuppy** — Docker procps installation
-- **@dsocolobsky** — Test suite fixes
-- **@bobashopcashier** (1 PR) — Graceful gateway drain before restart (salvaged into #7503 from #7290)
-- **@benbarclay** — Docker image tag simplification
-- **@sosyz** — Shallow git clone for faster install
-- **@devorun** — Nix setupSecrets optional
-- **@ethernet8023** — Nix tirith runtime dep
-
----
-
-**Full Changelog**: [v2026.4.8...v2026.4.13](https://github.com/NousResearch/hermes-agent/compare/v2026.4.8...v2026.4.13)

agent/anthropic_adapter.py

@@ -60,8 +60,6 @@ _ANTHROPIC_OUTPUT_LIMITS = {
     "claude-3-opus":       4_096,
     "claude-3-sonnet":     4_096,
     "claude-3-haiku":      4_096,
-    # Third-party Anthropic-compatible providers
-    "minimax":            131_072,
 }
 
 # For any model not in the table, assume the highest current limit.
@@ -163,27 +161,18 @@ def _get_claude_code_version() -> str:
 
 
 def _is_oauth_token(key: str) -> bool:
-    """Check if the key is an Anthropic OAuth/setup token.
+    """Check if the key is an OAuth/setup token (not a regular Console API key).
 
-    Positively identifies Anthropic OAuth tokens by their key format:
-    - ``sk-ant-`` prefix (but NOT ``sk-ant-api``) → setup tokens, managed keys
-    - ``eyJ`` prefix → JWTs from the Anthropic OAuth flow
-
-    Non-Anthropic keys (MiniMax, Alibaba, etc.) don't match either pattern
-    and correctly return False.
+    Regular API keys start with 'sk-ant-api'. Everything else (setup-tokens
+    starting with 'sk-ant-oat', managed keys, JWTs, etc.) needs Bearer auth.
     """
     if not key:
         return False
-    # Regular Anthropic Console API keys — x-api-key auth, never OAuth
+    # Regular Console API keys use x-api-key header
     if key.startswith("sk-ant-api"):
         return False
-    # Anthropic-issued tokens (setup-tokens sk-ant-oat-*, managed keys)
-    if key.startswith("sk-ant-"):
-        return True
-    # JWTs from Anthropic OAuth flow
-    if key.startswith("eyJ"):
-        return True
-    return False
+    # Everything else (setup-tokens, managed keys, JWTs) uses Bearer auth
+    return True
 
 
 def _normalize_base_url_text(base_url) -> str:
@@ -1315,10 +1304,9 @@ def build_anthropic_kwargs(
     # Map reasoning_config to Anthropic's thinking parameter.
     # Claude 4.6 models use adaptive thinking + output_config.effort.
     # Older models use manual thinking with budget_tokens.
-    # MiniMax Anthropic-compat endpoints support thinking (manual mode only,
-    # not adaptive).  Haiku does NOT support extended thinking — skip entirely.
+    # Haiku and MiniMax models do NOT support extended thinking — skip entirely.
     if reasoning_config and isinstance(reasoning_config, dict):
-        if reasoning_config.get("enabled") is not False and "haiku" not in model.lower():
+        if reasoning_config.get("enabled") is not False and "haiku" not in model.lower() and "minimax" not in model.lower():
             effort = str(reasoning_config.get("effort", "medium")).lower()
             budget = THINKING_BUDGET.get(effort, 8000)
             if _supports_adaptive_thinking(model):

agent/auxiliary_client.py

@@ -23,10 +23,18 @@ Resolution order for vision/multimodal tasks (auto mode):
   6. Custom endpoint (for local vision models: Qwen-VL, LLaVA, Pixtral, etc.)
   7. None
 
-Per-task overrides are configured in config.yaml under the ``auxiliary:`` section
-(e.g. ``auxiliary.vision.provider``, ``auxiliary.compression.model``).
+Per-task provider overrides (e.g. AUXILIARY_VISION_PROVIDER,
+CONTEXT_COMPRESSION_PROVIDER) can force a specific provider for each task.
 Default "auto" follows the chains above.
 
+Per-task model overrides (e.g. AUXILIARY_VISION_MODEL,
+AUXILIARY_WEB_EXTRACT_MODEL) let callers use a different model slug
+than the provider's default.
+
+Per-task direct endpoint overrides (e.g. AUXILIARY_VISION_BASE_URL,
+AUXILIARY_VISION_API_KEY) let callers route a specific auxiliary task to a
+custom OpenAI-compatible endpoint without touching the main model settings.
+
 Payment / credit exhaustion fallback:
   When a resolved provider returns HTTP 402 or a credit-related error,
   call_llm() automatically retries with the next available provider in the
@@ -51,9 +59,6 @@ from hermes_constants import OPENROUTER_BASE_URL
 
 logger = logging.getLogger(__name__)
 
-# Module-level flag: only warn once per process about stale OPENAI_BASE_URL.
-_stale_base_url_warned = False
-
 _PROVIDER_ALIASES = {
     "google": "gemini",
     "google-gemini": "gemini",
@@ -64,8 +69,6 @@ _PROVIDER_ALIASES = {
     "zhipu": "zai",
     "kimi": "kimi-coding",
     "moonshot": "kimi-coding",
-    "kimi-cn": "kimi-coding-cn",
-    "moonshot-cn": "kimi-coding-cn",
     "minimax-china": "minimax-cn",
     "minimax_cn": "minimax-cn",
     "claude": "anthropic",
@@ -73,13 +76,13 @@ _PROVIDER_ALIASES = {
 }
 
 
-def _normalize_aux_provider(provider: Optional[str]) -> str:
+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
+        normalized = suffix if not for_vision else "custom"
     if normalized == "codex":
         return "openai-codex"
     if normalized == "main":
@@ -96,7 +99,6 @@ _API_KEY_PROVIDER_AUX_MODELS: Dict[str, str] = {
     "gemini": "gemini-3-flash-preview",
     "zai": "glm-4.5-flash",
     "kimi-coding": "kimi-k2-turbo-preview",
-    "kimi-coding-cn": "kimi-k2-turbo-preview",
     "minimax": "MiniMax-M2.7",
     "minimax-cn": "MiniMax-M2.7",
     "anthropic": "claude-haiku-4-5-20251001",
@@ -106,14 +108,6 @@ _API_KEY_PROVIDER_AUX_MODELS: Dict[str, str] = {
     "kilocode": "google/gemini-3-flash-preview",
 }
 
-# Vision-specific model overrides for direct providers.
-# When the user's main provider has a dedicated vision/multimodal model that
-# differs from their main chat model, map it here.  The vision auto-detect
-# "exotic provider" branch checks this before falling back to the main model.
-_PROVIDER_VISION_MODELS: Dict[str, str] = {
-    "xiaomi": "mimo-v2-omni",
-}
-
 # OpenRouter app attribution headers
 _OR_HEADERS = {
     "HTTP-Referer": "https://hermes-agent.nousresearch.com",
@@ -713,9 +707,7 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
             base_url = _to_openai_base_url(
                 _pool_runtime_base_url(entry, pconfig.inference_base_url) or pconfig.inference_base_url
             )
-            model = _API_KEY_PROVIDER_AUX_MODELS.get(provider_id)
-            if model is None:
-                continue  # skip provider if we don't know a valid aux model
+            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():
@@ -734,9 +726,7 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
         base_url = _to_openai_base_url(
             str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
         )
-        model = _API_KEY_PROVIDER_AUX_MODELS.get(provider_id)
-        if model is None:
-            continue  # skip provider if we don't know a valid aux model
+        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():
@@ -752,6 +742,30 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
 
 # ── Provider resolution helpers ─────────────────────────────────────────────
 
+def _get_auxiliary_provider(task: str = "") -> str:
+    """Read the provider override for a specific auxiliary task.
+
+    Checks AUXILIARY_{TASK}_PROVIDER first (e.g. AUXILIARY_VISION_PROVIDER),
+    then CONTEXT_{TASK}_PROVIDER (for the compression section's summary_provider),
+    then falls back to "auto".  Returns one of: "auto", "openrouter", "nous", "main".
+    """
+    if task:
+        for prefix in ("AUXILIARY_", "CONTEXT_"):
+            val = os.getenv(f"{prefix}{task.upper()}_PROVIDER", "").strip().lower()
+            if val and val != "auto":
+                return val
+    return "auto"
+
+
+def _get_auxiliary_env_override(task: str, suffix: str) -> Optional[str]:
+    """Read an auxiliary env override from AUXILIARY_* or CONTEXT_* prefixes."""
+    if not task:
+        return None
+    for prefix in ("AUXILIARY_", "CONTEXT_"):
+        val = os.getenv(f"{prefix}{task.upper()}_{suffix}", "").strip()
+        if val:
+            return val
+    return None
 
 
 def _try_openrouter() -> Tuple[Optional[OpenAI], Optional[str]]:
@@ -996,23 +1010,6 @@ _AUTO_PROVIDER_LABELS = {
 
 _AGGREGATOR_PROVIDERS = frozenset({"openrouter", "nous"})
 
-_MAIN_RUNTIME_FIELDS = ("provider", "model", "base_url", "api_key", "api_mode")
-
-
-def _normalize_main_runtime(main_runtime: Optional[Dict[str, Any]]) -> Dict[str, str]:
-    """Return a sanitized copy of a live main-runtime override."""
-    if not isinstance(main_runtime, dict):
-        return {}
-    normalized: Dict[str, str] = {}
-    for field in _MAIN_RUNTIME_FIELDS:
-        value = main_runtime.get(field)
-        if isinstance(value, str) and value.strip():
-            normalized[field] = value.strip()
-    provider = normalized.get("provider")
-    if provider:
-        normalized["provider"] = provider.lower()
-    return normalized
-
 
 def _get_provider_chain() -> List[tuple]:
     """Return the ordered provider detection chain.
@@ -1078,12 +1075,11 @@ def _is_connection_error(exc: Exception) -> bool:
 def _try_payment_fallback(
     failed_provider: str,
     task: str = None,
-    reason: str = "payment error",
 ) -> Tuple[Optional[Any], Optional[str], str]:
-    """Try alternative providers after a payment/credit or connection error.
+    """Try alternative providers after a payment/credit error.
 
     Iterates the standard auto-detection chain, skipping the provider that
-    failed.
+    returned a payment error.
 
     Returns:
         (client, model, provider_label) or (None, None, "") if no fallback.
@@ -1109,20 +1105,20 @@ def _try_payment_fallback(
         client, model = try_fn()
         if client is not None:
             logger.info(
-                "Auxiliary %s: %s on %s — falling back to %s (%s)",
-                task or "call", reason, failed_provider, label, model or "default",
+                "Auxiliary %s: payment error on %s — falling back to %s (%s)",
+                task or "call", failed_provider, label, model or "default",
             )
             return client, model, label
         tried.append(label)
 
     logger.warning(
-        "Auxiliary %s: %s on %s and no fallback available (tried: %s)",
-        task or "call", reason, failed_provider, ", ".join(tried),
+        "Auxiliary %s: payment error on %s and no fallback available (tried: %s)",
+        task or "call", failed_provider, ", ".join(tried),
     )
     return None, None, ""
 
 
-def _resolve_auto(main_runtime: Optional[Dict[str, Any]] = None) -> Tuple[Optional[OpenAI], Optional[str]]:
+def _resolve_auto() -> Tuple[Optional[OpenAI], Optional[str]]:
     """Full auto-detection chain.
 
     Priority:
@@ -1132,54 +1128,16 @@ def _resolve_auto(main_runtime: Optional[Dict[str, Any]] = None) -> Tuple[Option
          provider they already have credentials for — no OpenRouter key needed.
       2. OpenRouter → Nous → custom → Codex → API-key providers (original chain).
     """
-    global auxiliary_is_nous, _stale_base_url_warned
+    global auxiliary_is_nous
     auxiliary_is_nous = False  # Reset — _try_nous() will set True if it wins
-    runtime = _normalize_main_runtime(main_runtime)
-    runtime_provider = runtime.get("provider", "")
-    runtime_model = runtime.get("model", "")
-    runtime_base_url = runtime.get("base_url", "")
-    runtime_api_key = runtime.get("api_key", "")
-    runtime_api_mode = runtime.get("api_mode", "")
-
-    # ── Warn once if OPENAI_BASE_URL is set but config.yaml uses a named
-    #    provider (not 'custom').  This catches the common "env poisoning"
-    #    scenario where a user switches providers via `hermes model` but the
-    #    old OPENAI_BASE_URL lingers in ~/.hermes/.env. ──
-    if not _stale_base_url_warned:
-        _env_base = os.getenv("OPENAI_BASE_URL", "").strip()
-        _cfg_provider = runtime_provider or _read_main_provider()
-        if (_env_base and _cfg_provider
-                and _cfg_provider != "custom"
-                and not _cfg_provider.startswith("custom:")):
-            logger.warning(
-                "OPENAI_BASE_URL is set (%s) but model.provider is '%s'. "
-                "Auxiliary clients may route to the wrong endpoint. "
-                "Run: hermes model to reconfigure, or remove "
-                "OPENAI_BASE_URL from ~/.hermes/.env",
-                _env_base, _cfg_provider,
-            )
-            _stale_base_url_warned = True
 
     # ── Step 1: non-aggregator main provider → use main model directly ──
-    main_provider = runtime_provider or _read_main_provider()
-    main_model = runtime_model or _read_main_model()
+    main_provider = _read_main_provider()
+    main_model = _read_main_model()
     if (main_provider and main_model
             and main_provider not in _AGGREGATOR_PROVIDERS
             and main_provider not in ("auto", "")):
-        resolved_provider = main_provider
-        explicit_base_url = None
-        explicit_api_key = None
-        if runtime_base_url and (main_provider == "custom" or main_provider.startswith("custom:")):
-            resolved_provider = "custom"
-            explicit_base_url = runtime_base_url
-            explicit_api_key = runtime_api_key or None
-        client, resolved = resolve_provider_client(
-            resolved_provider,
-            main_model,
-            explicit_base_url=explicit_base_url,
-            explicit_api_key=explicit_api_key,
-            api_mode=runtime_api_mode or None,
-        )
+        client, resolved = resolve_provider_client(main_provider, main_model)
         if client is not None:
             logger.info("Auxiliary auto-detect: using main provider %s (%s)",
                         main_provider, resolved or main_model)
@@ -1223,12 +1181,6 @@ def _to_async_client(sync_client, model: str):
         return AsyncCodexAuxiliaryClient(sync_client), model
     if isinstance(sync_client, AnthropicAuxiliaryClient):
         return AsyncAnthropicAuxiliaryClient(sync_client), model
-    try:
-        from agent.copilot_acp_client import CopilotACPClient
-        if isinstance(sync_client, CopilotACPClient):
-            return sync_client, model
-    except ImportError:
-        pass
 
     async_kwargs = {
         "api_key": sync_client.api_key,
@@ -1265,8 +1217,6 @@ def resolve_provider_client(
     raw_codex: bool = False,
     explicit_base_url: str = None,
     explicit_api_key: str = None,
-    api_mode: str = None,
-    main_runtime: Optional[Dict[str, Any]] = None,
 ) -> Tuple[Optional[Any], Optional[str]]:
     """Central router: given a provider name and optional model, return a
     configured client with the correct auth, base URL, and API format.
@@ -1290,10 +1240,6 @@ def resolve_provider_client(
             the main agent loop).
         explicit_base_url: Optional direct OpenAI-compatible endpoint.
         explicit_api_key: Optional API key paired with explicit_base_url.
-        api_mode: API mode override.  One of "chat_completions",
-            "codex_responses", or None (auto-detect).  When set to
-            "codex_responses", the client is wrapped in
-            CodexAuxiliaryClient to route through the Responses API.
 
     Returns:
         (client, resolved_model) or (None, None) if auth is unavailable.
@@ -1301,43 +1247,9 @@ def resolve_provider_client(
     # Normalise aliases
     provider = _normalize_aux_provider(provider)
 
-    def _needs_codex_wrap(client_obj, base_url_str: str, model_str: str) -> bool:
-        """Decide if a plain OpenAI client should be wrapped for Responses API.
-
-        Returns True when api_mode is explicitly "codex_responses", or when
-        auto-detection (api.openai.com + codex-family model) suggests it.
-        Already-wrapped clients (CodexAuxiliaryClient) are skipped.
-        """
-        if isinstance(client_obj, CodexAuxiliaryClient):
-            return False
-        if raw_codex:
-            return False
-        if api_mode == "codex_responses":
-            return True
-        # Auto-detect: api.openai.com + codex model name pattern
-        if api_mode and api_mode != "codex_responses":
-            return False  # explicit non-codex mode
-        normalized_base = (base_url_str or "").strip().lower()
-        if "api.openai.com" in normalized_base and "openrouter" not in normalized_base:
-            model_lower = (model_str or "").lower()
-            if "codex" in model_lower:
-                return True
-        return False
-
-    def _wrap_if_needed(client_obj, final_model_str: str, base_url_str: str = ""):
-        """Wrap a plain OpenAI client in CodexAuxiliaryClient if Responses API is needed."""
-        if _needs_codex_wrap(client_obj, base_url_str, final_model_str):
-            logger.debug(
-                "resolve_provider_client: wrapping client in CodexAuxiliaryClient "
-                "(api_mode=%s, model=%s, base_url=%s)",
-                api_mode or "auto-detected", final_model_str,
-                base_url_str[:60] if base_url_str else "")
-            return CodexAuxiliaryClient(client_obj, final_model_str)
-        return client_obj
-
     # ── Auto: try all providers in priority order ────────────────────
     if provider == "auto":
-        client, resolved = _resolve_auto(main_runtime=main_runtime)
+        client, resolved = _resolve_auto()
         if client is None:
             return None, None
         # When auto-detection lands on a non-OpenRouter provider (e.g. a
@@ -1424,7 +1336,6 @@ def resolve_provider_client(
                 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 = _wrap_if_needed(client, final_model, 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
@@ -1433,8 +1344,6 @@ def resolve_provider_client(
             client, default = try_fn()
             if client is not None:
                 final_model = _normalize_resolved_model(model or default, provider)
-                _cbase = str(getattr(client, "base_url", "") or "")
-                client = _wrap_if_needed(client, final_model, _cbase)
                 return (_to_async_client(client, final_model) if async_mode
                         else (client, final_model))
         logger.warning("resolve_provider_client: custom/main requested "
@@ -1447,18 +1356,13 @@ def resolve_provider_client(
         custom_entry = _get_named_custom_provider(provider)
         if custom_entry:
             custom_base = custom_entry.get("base_url", "").strip()
-            custom_key = custom_entry.get("api_key", "").strip()
-            custom_key_env = custom_entry.get("key_env", "").strip()
-            if not custom_key and custom_key_env:
-                custom_key = os.getenv(custom_key_env, "").strip()
-            custom_key = custom_key or "no-key-required"
+            custom_key = custom_entry.get("api_key", "").strip() or "no-key-required"
             if custom_base:
                 final_model = _normalize_resolved_model(
-                    model or custom_entry.get("model") or _read_main_model() or "gpt-4o-mini",
+                    model or _read_main_model() or "gpt-4o-mini",
                     provider,
                 )
                 client = OpenAI(api_key=custom_key, base_url=custom_base)
-                client = _wrap_if_needed(client, final_model, custom_base)
                 logger.debug(
                     "resolve_provider_client: named custom provider %r (%s)",
                     provider, final_model)
@@ -1473,11 +1377,7 @@ def resolve_provider_client(
 
     # ── API-key providers from PROVIDER_REGISTRY ─────────────────────
     try:
-        from hermes_cli.auth import (
-            PROVIDER_REGISTRY,
-            resolve_api_key_provider_credentials,
-            resolve_external_process_provider_credentials,
-        )
+        from hermes_cli.auth import PROVIDER_REGISTRY, resolve_api_key_provider_credentials
     except ImportError:
         logger.debug("hermes_cli.auth not available for provider %s", provider)
         return None, None
@@ -1525,67 +1425,10 @@ def resolve_provider_client(
 
         client = OpenAI(api_key=api_key, base_url=base_url,
                         **({"default_headers": headers} if headers else {}))
-
-        # Copilot GPT-5+ models (except gpt-5-mini) require the Responses
-        # API — they are not accessible via /chat/completions.  Wrap the
-        # plain client in CodexAuxiliaryClient so call_llm() transparently
-        # routes through responses.stream().
-        if provider == "copilot" and final_model and not raw_codex:
-            try:
-                from hermes_cli.models import _should_use_copilot_responses_api
-                if _should_use_copilot_responses_api(final_model):
-                    logger.debug(
-                        "resolve_provider_client: copilot model %s needs "
-                        "Responses API — wrapping with CodexAuxiliaryClient",
-                        final_model)
-                    client = CodexAuxiliaryClient(client, final_model)
-            except ImportError:
-                pass
-
-        # Honor api_mode for any API-key provider (e.g. direct OpenAI with
-        # codex-family models).  The copilot-specific wrapping above handles
-        # copilot; this covers the general case (#6800).
-        client = _wrap_if_needed(client, final_model, base_url)
-
         logger.debug("resolve_provider_client: %s (%s)", provider, final_model)
         return (_to_async_client(client, final_model) if async_mode
                 else (client, final_model))
 
-    if pconfig.auth_type == "external_process":
-        creds = resolve_external_process_provider_credentials(provider)
-        final_model = _normalize_resolved_model(model or _read_main_model(), provider)
-        if provider == "copilot-acp":
-            api_key = str(creds.get("api_key", "")).strip()
-            base_url = str(creds.get("base_url", "")).strip()
-            command = str(creds.get("command", "")).strip() or None
-            args = list(creds.get("args") or [])
-            if not final_model:
-                logger.warning(
-                    "resolve_provider_client: copilot-acp requested but no model "
-                    "was provided or configured"
-                )
-                return None, None
-            if not api_key or not base_url:
-                logger.warning(
-                    "resolve_provider_client: copilot-acp requested but external "
-                    "process credentials are incomplete"
-                )
-                return None, None
-            from agent.copilot_acp_client import CopilotACPClient
-
-            client = CopilotACPClient(
-                api_key=api_key,
-                base_url=base_url,
-                command=command,
-                args=args,
-            )
-            logger.debug("resolve_provider_client: %s (%s)", provider, final_model)
-            return (_to_async_client(client, final_model) if async_mode
-                    else (client, final_model))
-        logger.warning("resolve_provider_client: external-process provider %s not "
-                       "directly supported", provider)
-        return None, None
-
     elif pconfig.auth_type in ("oauth_device_code", "oauth_external"):
         # OAuth providers — route through their specific try functions
         if provider == "nous":
@@ -1604,47 +1447,39 @@ def resolve_provider_client(
 
 # ── Public API ──────────────────────────────────────────────────────────────
 
-def get_text_auxiliary_client(
-    task: str = "",
-    *,
-    main_runtime: Optional[Dict[str, Any]] = None,
-) -> Tuple[Optional[OpenAI], Optional[str]]:
+def get_text_auxiliary_client(task: str = "") -> Tuple[Optional[OpenAI], Optional[str]]:
     """Return (client, default_model_slug) for text-only auxiliary tasks.
 
     Args:
         task: Optional task name ("compression", "web_extract") to check
               for a task-specific provider override.
 
-    Callers may override the returned model via config.yaml
-    (e.g. auxiliary.compression.model, auxiliary.web_extract.model).
+    Callers may override the returned model with a per-task env var
+    (e.g. CONTEXT_COMPRESSION_MODEL, AUXILIARY_WEB_EXTRACT_MODEL).
     """
-    provider, model, base_url, api_key, api_mode = _resolve_task_provider_model(task or None)
+    provider, model, base_url, api_key = _resolve_task_provider_model(task or None)
     return resolve_provider_client(
         provider,
         model=model,
         explicit_base_url=base_url,
         explicit_api_key=api_key,
-        api_mode=api_mode,
-        main_runtime=main_runtime,
     )
 
 
-def get_async_text_auxiliary_client(task: str = "", *, main_runtime: Optional[Dict[str, Any]] = None):
+def get_async_text_auxiliary_client(task: str = ""):
     """Return (async_client, model_slug) for async consumers.
 
     For standard providers returns (AsyncOpenAI, model). For Codex returns
     (AsyncCodexAuxiliaryClient, model) which wraps the Responses API.
     Returns (None, None) when no provider is available.
     """
-    provider, model, base_url, api_key, api_mode = _resolve_task_provider_model(task or None)
+    provider, model, base_url, api_key = _resolve_task_provider_model(task or None)
     return resolve_provider_client(
         provider,
         model=model,
         async_mode=True,
         explicit_base_url=base_url,
         explicit_api_key=api_key,
-        api_mode=api_mode,
-        main_runtime=main_runtime,
     )
 
 
@@ -1655,7 +1490,7 @@ _VISION_AUTO_PROVIDER_ORDER = (
 
 
 def _normalize_vision_provider(provider: Optional[str]) -> str:
-    return _normalize_aux_provider(provider)
+    return _normalize_aux_provider(provider, for_vision=True)
 
 
 def _resolve_strict_vision_backend(provider: str) -> Tuple[Optional[Any], Optional[str]]:
@@ -1717,7 +1552,7 @@ def resolve_vision_provider_client(
     backends, so users can intentionally force experimental providers. Auto mode
     stays conservative and only tries vision backends known to work today.
     """
-    requested, resolved_model, resolved_base_url, resolved_api_key, resolved_api_mode = _resolve_task_provider_model(
+    requested, resolved_model, resolved_base_url, resolved_api_key = _resolve_task_provider_model(
         "vision", provider, model, base_url, api_key
     )
     requested = _normalize_vision_provider(requested)
@@ -1738,7 +1573,6 @@ def resolve_vision_provider_client(
             async_mode=async_mode,
             explicit_base_url=resolved_base_url,
             explicit_api_key=resolved_api_key,
-            api_mode=resolved_api_mode,
         )
         if client is None:
             return "custom", None, None
@@ -1759,19 +1593,16 @@ def resolve_vision_provider_client(
                 if sync_client is not None:
                     return _finalize(main_provider, sync_client, default_model)
             else:
-                # Exotic provider (DeepSeek, Alibaba, Xiaomi, named custom, etc.)
-                # Use provider-specific vision model if available, otherwise main model.
-                vision_model = _PROVIDER_VISION_MODELS.get(main_provider, main_model)
+                # Exotic provider (DeepSeek, Alibaba, named custom, etc.)
                 rpc_client, rpc_model = resolve_provider_client(
-                    main_provider, vision_model,
-                    api_mode=resolved_api_mode)
+                    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 vision_model,
+                        main_provider, rpc_model or main_model,
                     )
                     return _finalize(
-                        main_provider, rpc_client, rpc_model or vision_model)
+                        main_provider, rpc_client, rpc_model or main_model)
 
         # Fall back through aggregators.
         for candidate in _VISION_AUTO_PROVIDER_ORDER:
@@ -1788,8 +1619,7 @@ def resolve_vision_provider_client(
         sync_client, default_model = _resolve_strict_vision_backend(requested)
         return _finalize(requested, sync_client, default_model)
 
-    client, final_model = _get_cached_client(requested, resolved_model, async_mode,
-                                             api_mode=resolved_api_mode)
+    client, final_model = _get_cached_client(requested, resolved_model, async_mode)
     if client is None:
         return requested, None, None
     return requested, client, final_model
@@ -1938,31 +1768,12 @@ def cleanup_stale_async_clients() -> None:
             del _client_cache[key]
 
 
-def _is_openrouter_client(client: Any) -> bool:
-    for obj in (client, getattr(client, "_client", None), getattr(client, "client", None)):
-        if obj and "openrouter" in str(getattr(obj, "base_url", "") or "").lower():
-            return True
-    return False
-
-
-def _compat_model(client: Any, model: Optional[str], cached_default: Optional[str]) -> Optional[str]:
-    """Drop OpenRouter-format model slugs (with '/') for non-OpenRouter clients.
-
-    Mirrors the guard in resolve_provider_client() which is skipped on cache hits.
-    """
-    if model and "/" in model and not _is_openrouter_client(client):
-        return cached_default
-    return model or cached_default
-
-
 def _get_cached_client(
     provider: str,
     model: str = None,
     async_mode: bool = False,
     base_url: str = None,
     api_key: str = None,
-    api_mode: str = None,
-    main_runtime: Optional[Dict[str, Any]] = None,
 ) -> Tuple[Optional[Any], Optional[str]]:
     """Get or create a cached client for the given provider.
 
@@ -1986,9 +1797,7 @@ def _get_cached_client(
             loop_id = id(current_loop)
         except RuntimeError:
             pass
-    runtime = _normalize_main_runtime(main_runtime)
-    runtime_key = tuple(runtime.get(field, "") for field in _MAIN_RUNTIME_FIELDS) if provider == "auto" else ()
-    cache_key = (provider, async_mode, base_url or "", api_key or "", api_mode or "", loop_id, runtime_key)
+    cache_key = (provider, async_mode, base_url or "", api_key or "", loop_id)
     with _client_cache_lock:
         if cache_key in _client_cache:
             cached_client, cached_default, cached_loop = _client_cache[cache_key]
@@ -2000,11 +1809,9 @@ def _get_cached_client(
                     _force_close_async_httpx(cached_client)
                     del _client_cache[cache_key]
                 else:
-                    effective = _compat_model(cached_client, model, cached_default)
-                    return cached_client, effective
+                    return cached_client, model or cached_default
             else:
-                effective = _compat_model(cached_client, model, cached_default)
-                return cached_client, effective
+                return cached_client, model or cached_default
     # Build outside the lock
     client, default_model = resolve_provider_client(
         provider,
@@ -2012,8 +1819,6 @@ def _get_cached_client(
         async_mode,
         explicit_base_url=base_url,
         explicit_api_key=api_key,
-        api_mode=api_mode,
-        main_runtime=runtime,
     )
     if client is not None:
         # For async clients, remember which loop they were created on so we
@@ -2033,25 +1838,24 @@ def _resolve_task_provider_model(
     model: str = None,
     base_url: str = None,
     api_key: str = None,
-) -> Tuple[str, Optional[str], Optional[str], Optional[str], Optional[str]]:
+) -> Tuple[str, Optional[str], Optional[str], Optional[str]]:
     """Determine provider + model for a call.
 
     Priority:
       1. Explicit provider/model/base_url/api_key args (always win)
-      2. Config file (auxiliary.{task}.provider/model/base_url)
-      3. "auto" (full auto-detection chain)
+      2. Env var overrides (AUXILIARY_{TASK}_*, CONTEXT_{TASK}_*)
+      3. Config file (auxiliary.{task}.* or compression.*)
+      4. "auto" (full auto-detection chain)
 
-    Returns (provider, model, base_url, api_key, api_mode) where model may
-    be None (use provider default). When base_url is set, provider is forced
-    to "custom" and the task uses that direct endpoint. api_mode is one of
-    "chat_completions", "codex_responses", or None (auto-detect).
+    Returns (provider, model, base_url, api_key) where model may be None
+    (use provider default). When base_url is set, provider is forced to
+    "custom" and the task uses that direct endpoint.
     """
     config = {}
     cfg_provider = None
     cfg_model = None
     cfg_base_url = None
     cfg_api_key = None
-    cfg_api_mode = None
 
     if task:
         try:
@@ -2068,26 +1872,43 @@ def _resolve_task_provider_model(
         cfg_model = str(task_config.get("model", "")).strip() or None
         cfg_base_url = str(task_config.get("base_url", "")).strip() or None
         cfg_api_key = str(task_config.get("api_key", "")).strip() or None
-        cfg_api_mode = str(task_config.get("api_mode", "")).strip() or None
 
-    resolved_model = model or cfg_model
-    resolved_api_mode = cfg_api_mode
+        # Backwards compat: compression section has its own keys.
+        # The auxiliary.compression defaults to provider="auto", so treat
+        # both None and "auto" as "not explicitly configured".
+        if task == "compression" and (not cfg_provider or cfg_provider == "auto"):
+            comp = config.get("compression", {}) if isinstance(config, dict) else {}
+            if isinstance(comp, dict):
+                cfg_provider = comp.get("summary_provider", "").strip() or None
+                cfg_model = cfg_model or comp.get("summary_model", "").strip() or None
+                _sbu = comp.get("summary_base_url") or ""
+                cfg_base_url = cfg_base_url or _sbu.strip() or None
+
+    env_model = _get_auxiliary_env_override(task, "MODEL") if task else None
+    resolved_model = model or env_model or cfg_model
 
     if base_url:
-        return "custom", resolved_model, base_url, api_key, resolved_api_mode
+        return "custom", resolved_model, base_url, api_key
     if provider:
-        return provider, resolved_model, base_url, api_key, resolved_api_mode
+        return provider, resolved_model, base_url, api_key
 
     if task:
-        # Config.yaml is the primary source for per-task overrides.
+        env_base_url = _get_auxiliary_env_override(task, "BASE_URL")
+        env_api_key = _get_auxiliary_env_override(task, "API_KEY")
+        if env_base_url:
+            return "custom", resolved_model, env_base_url, env_api_key or cfg_api_key
+
+        env_provider = _get_auxiliary_provider(task)
+        if env_provider != "auto":
+            return env_provider, resolved_model, None, None
+
         if cfg_base_url:
-            return "custom", resolved_model, cfg_base_url, cfg_api_key, resolved_api_mode
+            return "custom", resolved_model, cfg_base_url, cfg_api_key
         if cfg_provider and cfg_provider != "auto":
-            return cfg_provider, resolved_model, None, None, resolved_api_mode
+            return cfg_provider, resolved_model, None, None
+        return "auto", resolved_model, None, None
 
-        return "auto", resolved_model, None, None, resolved_api_mode
-
-    return "auto", resolved_model, None, None, resolved_api_mode
+    return "auto", resolved_model, None, None
 
 
 _DEFAULT_AUX_TIMEOUT = 30.0
@@ -2113,75 +1934,6 @@ def _get_task_timeout(task: str, default: float = _DEFAULT_AUX_TIMEOUT) -> float
     return default
 
 
-# ---------------------------------------------------------------------------
-# Anthropic-compatible endpoint detection + image block conversion
-# ---------------------------------------------------------------------------
-
-# Providers that use Anthropic-compatible endpoints (via OpenAI SDK wrapper).
-# Their image content blocks must use Anthropic format, not OpenAI format.
-_ANTHROPIC_COMPAT_PROVIDERS = frozenset({"minimax", "minimax-cn"})
-
-
-def _is_anthropic_compat_endpoint(provider: str, base_url: str) -> bool:
-    """Detect if an endpoint expects Anthropic-format content blocks.
-
-    Returns True for known Anthropic-compatible providers (MiniMax) and
-    any endpoint whose URL contains ``/anthropic`` in the path.
-    """
-    if provider in _ANTHROPIC_COMPAT_PROVIDERS:
-        return True
-    url_lower = (base_url or "").lower()
-    return "/anthropic" in url_lower
-
-
-def _convert_openai_images_to_anthropic(messages: list) -> list:
-    """Convert OpenAI ``image_url`` content blocks to Anthropic ``image`` blocks.
-
-    Only touches messages that have list-type content with ``image_url`` blocks;
-    plain text messages pass through unchanged.
-    """
-    converted = []
-    for msg in messages:
-        content = msg.get("content")
-        if not isinstance(content, list):
-            converted.append(msg)
-            continue
-        new_content = []
-        changed = False
-        for block in content:
-            if block.get("type") == "image_url":
-                image_url_val = (block.get("image_url") or {}).get("url", "")
-                if image_url_val.startswith("data:"):
-                    # Parse data URI: data:<media_type>;base64,<data>
-                    header, _, b64data = image_url_val.partition(",")
-                    media_type = "image/png"
-                    if ":" in header and ";" in header:
-                        media_type = header.split(":", 1)[1].split(";", 1)[0]
-                    new_content.append({
-                        "type": "image",
-                        "source": {
-                            "type": "base64",
-                            "media_type": media_type,
-                            "data": b64data,
-                        },
-                    })
-                else:
-                    # URL-based image
-                    new_content.append({
-                        "type": "image",
-                        "source": {
-                            "type": "url",
-                            "url": image_url_val,
-                        },
-                    })
-                changed = True
-            else:
-                new_content.append(block)
-        converted.append({**msg, "content": new_content} if changed else msg)
-    return converted
-
-
-
 def _build_call_kwargs(
     provider: str,
     model: str,
@@ -2228,37 +1980,6 @@ def _build_call_kwargs(
     return kwargs
 
 
-def _validate_llm_response(response: Any, task: str = None) -> Any:
-    """Validate that an LLM response has the expected .choices[0].message shape.
-
-    Fails fast with a clear error instead of letting malformed payloads
-    propagate to downstream consumers where they crash with misleading
-    AttributeError (e.g. "'str' object has no attribute 'choices'").
-
-    See #7264.
-    """
-    if response is None:
-        raise RuntimeError(
-            f"Auxiliary {task or 'call'}: LLM returned None response"
-        )
-    # Allow SimpleNamespace responses from adapters (CodexAuxiliaryClient,
-    # AnthropicAuxiliaryClient) — they have .choices[0].message.
-    try:
-        choices = response.choices
-        if not choices or not hasattr(choices[0], "message"):
-            raise AttributeError("missing choices[0].message")
-    except (AttributeError, TypeError, IndexError) as exc:
-        response_type = type(response).__name__
-        response_preview = str(response)[:120]
-        raise RuntimeError(
-            f"Auxiliary {task or 'call'}: LLM returned invalid response "
-            f"(type={response_type}): {response_preview!r}. "
-            f"Expected object with .choices[0].message — check provider "
-            f"adapter or custom endpoint compatibility."
-        ) from exc
-    return response
-
-
 def call_llm(
     task: str = None,
     *,
@@ -2266,7 +1987,6 @@ def call_llm(
     model: str = None,
     base_url: str = None,
     api_key: str = None,
-    main_runtime: Optional[Dict[str, Any]] = None,
     messages: list,
     temperature: float = None,
     max_tokens: int = None,
@@ -2298,7 +2018,7 @@ def call_llm(
     Raises:
         RuntimeError: If no provider is configured.
     """
-    resolved_provider, resolved_model, resolved_base_url, resolved_api_key, resolved_api_mode = _resolve_task_provider_model(
+    resolved_provider, resolved_model, resolved_base_url, resolved_api_key = _resolve_task_provider_model(
         task, provider, model, base_url, api_key)
 
     if task == "vision":
@@ -2331,8 +2051,6 @@ def call_llm(
             resolved_model,
             base_url=resolved_base_url,
             api_key=resolved_api_key,
-            api_mode=resolved_api_mode,
-            main_runtime=main_runtime,
         )
         if client is None:
             # When the user explicitly chose a non-OpenRouter provider but no
@@ -2353,7 +2071,7 @@ def call_llm(
             if not resolved_base_url:
                 logger.info("Auxiliary %s: provider %s unavailable, trying auto-detection chain",
                             task or "call", resolved_provider)
-                client, final_model = _get_cached_client("auto", main_runtime=main_runtime)
+                client, final_model = _get_cached_client("auto")
         if client is None:
             raise RuntimeError(
                 f"No LLM provider configured for task={task} provider={resolved_provider}. "
@@ -2374,27 +2092,20 @@ def call_llm(
         tools=tools, timeout=effective_timeout, extra_body=extra_body,
         base_url=resolved_base_url)
 
-    # Convert image blocks for Anthropic-compatible endpoints (e.g. MiniMax)
-    _client_base = str(getattr(client, "base_url", "") or "")
-    if _is_anthropic_compat_endpoint(resolved_provider, _client_base):
-        kwargs["messages"] = _convert_openai_images_to_anthropic(kwargs["messages"])
-
     # Handle max_tokens vs max_completion_tokens retry, then payment fallback.
     try:
-        return _validate_llm_response(
-            client.chat.completions.create(**kwargs), task)
+        return client.chat.completions.create(**kwargs)
     except Exception as first_err:
         err_str = str(first_err)
         if "max_tokens" in err_str or "unsupported_parameter" in err_str:
             kwargs.pop("max_tokens", None)
             kwargs["max_completion_tokens"] = max_tokens
             try:
-                return _validate_llm_response(
-                    client.chat.completions.create(**kwargs), task)
+                return client.chat.completions.create(**kwargs)
             except Exception as retry_err:
-                # If the max_tokens retry also hits a payment or connection
-                # error, fall through to the fallback chain below.
-                if not (_is_payment_error(retry_err) or _is_connection_error(retry_err)):
+                # If the max_tokens retry also hits a payment error,
+                # fall through to the payment fallback below.
+                if not _is_payment_error(retry_err):
                     raise
                 first_err = retry_err
 
@@ -2411,24 +2122,19 @@ def call_llm(
         # 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)
-        # Only try alternative providers when the user didn't explicitly
-        # configure this task's provider.  Explicit provider = hard constraint;
-        # auto (the default) = best-effort fallback chain.  (#7559)
-        is_auto = resolved_provider in ("auto", "", None)
-        if should_fallback and is_auto:
+        if should_fallback:
             reason = "payment error" if _is_payment_error(first_err) else "connection error"
             logger.info("Auxiliary %s: %s on %s (%s), trying fallback",
                         task or "call", reason, resolved_provider, first_err)
             fb_client, fb_model, fb_label = _try_payment_fallback(
-                resolved_provider, task, reason=reason)
+                resolved_provider, task)
             if fb_client is not None:
                 fb_kwargs = _build_call_kwargs(
                     fb_label, fb_model, messages,
                     temperature=temperature, max_tokens=max_tokens,
                     tools=tools, timeout=effective_timeout,
                     extra_body=extra_body)
-                return _validate_llm_response(
-                    fb_client.chat.completions.create(**fb_kwargs), task)
+                return fb_client.chat.completions.create(**fb_kwargs)
         raise
 
 
@@ -2455,9 +2161,9 @@ def extract_content_or_reasoning(response) -> str:
     if content:
         # Strip inline think/reasoning blocks (mirrors _strip_think_blocks)
         cleaned = re.sub(
-            r"<(?:think|thinking|reasoning|thought|REASONING_SCRATCHPAD)>"
+            r"<(?:think|thinking|reasoning|REASONING_SCRATCHPAD)>"
             r".*?"
-            r"</(?:think|thinking|reasoning|thought|REASONING_SCRATCHPAD)>",
+            r"</(?:think|thinking|reasoning|REASONING_SCRATCHPAD)>",
             "", content, flags=re.DOTALL | re.IGNORECASE,
         ).strip()
         if cleaned:
@@ -2506,7 +2212,7 @@ async def async_call_llm(
 
     Same as call_llm() but async. See call_llm() for full documentation.
     """
-    resolved_provider, resolved_model, resolved_base_url, resolved_api_key, resolved_api_mode = _resolve_task_provider_model(
+    resolved_provider, resolved_model, resolved_base_url, resolved_api_key = _resolve_task_provider_model(
         task, provider, model, base_url, api_key)
 
     if task == "vision":
@@ -2540,7 +2246,6 @@ async def async_call_llm(
             async_mode=True,
             base_url=resolved_base_url,
             api_key=resolved_api_key,
-            api_mode=resolved_api_mode,
         )
         if client is None:
             _explicit = (resolved_provider or "").strip().lower()
@@ -2551,9 +2256,11 @@ async def async_call_llm(
                     f"variable, or switch to a different provider with `hermes model`."
                 )
             if not resolved_base_url:
-                logger.info("Auxiliary %s: provider %s unavailable, trying auto-detection chain",
-                            task or "call", resolved_provider)
-                client, final_model = _get_cached_client("auto", async_mode=True)
+                logger.warning("Provider %s unavailable, falling back to openrouter",
+                               resolved_provider)
+                client, final_model = _get_cached_client(
+                    "openrouter", resolved_model or _OPENROUTER_MODEL,
+                    async_mode=True)
         if client is None:
             raise RuntimeError(
                 f"No LLM provider configured for task={task} provider={resolved_provider}. "
@@ -2567,48 +2274,12 @@ async def async_call_llm(
         tools=tools, timeout=effective_timeout, extra_body=extra_body,
         base_url=resolved_base_url)
 
-    # Convert image blocks for Anthropic-compatible endpoints (e.g. MiniMax)
-    _client_base = str(getattr(client, "base_url", "") or "")
-    if _is_anthropic_compat_endpoint(resolved_provider, _client_base):
-        kwargs["messages"] = _convert_openai_images_to_anthropic(kwargs["messages"])
-
     try:
-        return _validate_llm_response(
-            await client.chat.completions.create(**kwargs), task)
+        return await client.chat.completions.create(**kwargs)
     except Exception as first_err:
         err_str = str(first_err)
         if "max_tokens" in err_str or "unsupported_parameter" in err_str:
             kwargs.pop("max_tokens", None)
             kwargs["max_completion_tokens"] = max_tokens
-            try:
-                return _validate_llm_response(
-                    await client.chat.completions.create(**kwargs), task)
-            except Exception as retry_err:
-                # If the max_tokens retry also hits a payment or connection
-                # error, fall through to the fallback chain below.
-                if not (_is_payment_error(retry_err) or _is_connection_error(retry_err)):
-                    raise
-                first_err = retry_err
-
-        # ── Payment / connection fallback (mirrors sync call_llm) ─────
-        should_fallback = _is_payment_error(first_err) or _is_connection_error(first_err)
-        is_auto = resolved_provider in ("auto", "", None)
-        if should_fallback and is_auto:
-            reason = "payment error" if _is_payment_error(first_err) else "connection error"
-            logger.info("Auxiliary %s (async): %s on %s (%s), trying fallback",
-                        task or "call", reason, resolved_provider, first_err)
-            fb_client, fb_model, fb_label = _try_payment_fallback(
-                resolved_provider, task, reason=reason)
-            if fb_client is not None:
-                fb_kwargs = _build_call_kwargs(
-                    fb_label, fb_model, messages,
-                    temperature=temperature, max_tokens=max_tokens,
-                    tools=tools, timeout=effective_timeout,
-                    extra_body=extra_body)
-                # Convert sync fallback client to async
-                async_fb, async_fb_model = _to_async_client(fb_client, fb_model or "")
-                if async_fb_model and async_fb_model != fb_kwargs.get("model"):
-                    fb_kwargs["model"] = async_fb_model
-                return _validate_llm_response(
-                    await async_fb.chat.completions.create(**fb_kwargs), task)
+            return await client.chat.completions.create(**kwargs)
         raise

agent/context_compressor.py

@@ -4,12 +4,8 @@ Self-contained class with its own OpenAI client for summarization.
 Uses auxiliary model (cheap/fast) to summarize middle turns while
 protecting head and tail context.
 
-Improvements over v2:
-  - Structured summary template with Resolved/Pending question tracking
-  - Summarizer preamble: "Do not respond to any questions" (from OpenCode)
-  - Handoff framing: "different assistant" (from Codex) to create separation
-  - "Remaining Work" replaces "Next Steps" to avoid reading as active instructions
-  - Clear separator when summary merges into tail message
+Improvements over v1:
+  - Structured summary template (Goal, Progress, Decisions, Files, Next Steps)
   - Iterative summary updates (preserves info across multiple compactions)
   - Token-budget tail protection instead of fixed message count
   - Tool output pruning before LLM summarization (cheap pre-pass)
@@ -22,9 +18,7 @@ import time
 from typing import Any, Dict, List, Optional
 
 from agent.auxiliary_client import call_llm
-from agent.context_engine import ContextEngine
 from agent.model_metadata import (
-    MINIMUM_CONTEXT_LENGTH,
     get_model_context_length,
     estimate_messages_tokens_rough,
 )
@@ -32,13 +26,12 @@ from agent.model_metadata import (
 logger = logging.getLogger(__name__)
 
 SUMMARY_PREFIX = (
-    "[CONTEXT COMPACTION — REFERENCE ONLY] Earlier turns were compacted "
-    "into the summary below. This is a handoff from a previous context "
-    "window — treat it as background reference, NOT as active instructions. "
-    "Do NOT answer questions or fulfill requests mentioned in this summary; "
-    "they were already addressed. Respond ONLY to the latest user message "
-    "that appears AFTER this summary. The current session state (files, "
-    "config, etc.) may reflect work described here — avoid repeating it:"
+    "[CONTEXT COMPACTION] Earlier turns in this conversation were compacted "
+    "to save context space. The summary below describes work that was "
+    "already completed, and the current session state may still reflect "
+    "that work (for example, files may already be changed). Use the summary "
+    "and the current state to continue from where things left off, and "
+    "avoid repeating work:"
 )
 LEGACY_SUMMARY_PREFIX = "[CONTEXT SUMMARY]:"
 
@@ -57,8 +50,8 @@ _CHARS_PER_TOKEN = 4
 _SUMMARY_FAILURE_COOLDOWN_SECONDS = 600
 
 
-class ContextCompressor(ContextEngine):
-    """Default context engine — compresses conversation context via lossy summarization.
+class ContextCompressor:
+    """Compresses conversation context when approaching the model's context limit.
 
     Algorithm:
       1. Prune old tool results (cheap, no LLM call)
@@ -68,38 +61,6 @@ class ContextCompressor(ContextEngine):
       5. On subsequent compactions, iteratively update the previous summary
     """
 
-    @property
-    def name(self) -> str:
-        return "compressor"
-
-    def on_session_reset(self) -> None:
-        """Reset all per-session state for /new or /reset."""
-        super().on_session_reset()
-        self._context_probed = False
-        self._context_probe_persistable = False
-        self._previous_summary = None
-
-    def update_model(
-        self,
-        model: str,
-        context_length: int,
-        base_url: str = "",
-        api_key: str = "",
-        provider: str = "",
-        api_mode: str = "",
-    ) -> None:
-        """Update model info after a model switch or fallback activation."""
-        self.model = model
-        self.base_url = base_url
-        self.api_key = api_key
-        self.provider = provider
-        self.api_mode = api_mode
-        self.context_length = context_length
-        self.threshold_tokens = max(
-            int(context_length * self.threshold_percent),
-            MINIMUM_CONTEXT_LENGTH,
-        )
-
     def __init__(
         self,
         model: str,
@@ -113,13 +74,11 @@ class ContextCompressor(ContextEngine):
         api_key: str = "",
         config_context_length: int | None = None,
         provider: str = "",
-        api_mode: str = "",
     ):
         self.model = model
         self.base_url = base_url
         self.api_key = api_key
         self.provider = provider
-        self.api_mode = api_mode
         self.threshold_percent = threshold_percent
         self.protect_first_n = protect_first_n
         self.protect_last_n = protect_last_n
@@ -131,14 +90,7 @@ class ContextCompressor(ContextEngine):
             config_context_length=config_context_length,
             provider=provider,
         )
-        # Floor: never compress below MINIMUM_CONTEXT_LENGTH tokens even if
-        # the percentage would suggest a lower value.  This prevents premature
-        # compression on large-context models at 50% while keeping the % sane
-        # for models right at the minimum.
-        self.threshold_tokens = max(
-            int(self.context_length * threshold_percent),
-            MINIMUM_CONTEXT_LENGTH,
-        )
+        self.threshold_tokens = int(self.context_length * threshold_percent)
         self.compression_count = 0
 
         # Derive token budgets: ratio is relative to the threshold, not total context
@@ -315,20 +267,13 @@ class ContextCompressor(ContextEngine):
 
         return "\n\n".join(parts)
 
-    def _generate_summary(self, turns_to_summarize: List[Dict[str, Any]], focus_topic: str = None) -> Optional[str]:
+    def _generate_summary(self, turns_to_summarize: List[Dict[str, Any]]) -> Optional[str]:
         """Generate a structured summary of conversation turns.
 
-        Uses a structured template (Goal, Progress, Decisions, Resolved/Pending
-        Questions, Files, Remaining Work) with explicit preamble telling the
-        summarizer not to answer questions.  When a previous summary exists,
+        Uses a structured template (Goal, Progress, Decisions, Files, Next Steps)
+        inspired by Pi-mono and OpenCode. When a previous summary exists,
         generates an iterative update instead of summarizing from scratch.
 
-        Args:
-            focus_topic: Optional focus string for guided compression.  When
-                provided, the summariser prioritises preserving information
-                related to this topic and is more aggressive about compressing
-                everything else.  Inspired by Claude Code's ``/compact``.
-
         Returns None if all attempts fail — the caller should drop
         the middle turns without a summary rather than inject a useless
         placeholder.
@@ -344,27 +289,60 @@ class ContextCompressor(ContextEngine):
         summary_budget = self._compute_summary_budget(turns_to_summarize)
         content_to_summarize = self._serialize_for_summary(turns_to_summarize)
 
-        # Preamble shared by both first-compaction and iterative-update prompts.
-        # Inspired by OpenCode's "do not respond to any questions" instruction
-        # and Codex's "another language model" framing.
-        _summarizer_preamble = (
-            "You are a summarization agent creating a context checkpoint. "
-            "Your output will be injected as reference material for a DIFFERENT "
-            "assistant that continues the conversation. "
-            "Do NOT respond to any questions or requests in the conversation — "
-            "only output the structured summary. "
-            "Do NOT include any preamble, greeting, or prefix."
-        )
+        if self._previous_summary:
+            # Iterative update: preserve existing info, add new progress
+            prompt = f"""You are updating a context compaction summary. A previous compaction produced the summary below. New conversation turns have occurred since then and need to be incorporated.
 
-        # Shared structured template (used by both paths).
-        # Key changes vs v1:
-        #   - "Pending User Asks" section (from Claude Code) explicitly tracks
-        #     unanswered questions so the model knows what's resolved vs open
-        #   - "Remaining Work" replaces "Next Steps" to avoid reading as active
-        #     instructions
-        #   - "Resolved Questions" makes it clear which questions were already
-        #     answered (prevents model from re-answering them)
-        _template_sections = f"""## Goal
+PREVIOUS SUMMARY:
+{self._previous_summary}
+
+NEW TURNS TO INCORPORATE:
+{content_to_summarize}
+
+Update the summary using this exact structure. PRESERVE all existing information that is still relevant. ADD new progress. Move items from "In Progress" to "Done" when completed. Remove information only if it is clearly obsolete.
+
+## Goal
+[What the user is trying to accomplish — preserve from previous summary, update if goal evolved]
+
+## Constraints & Preferences
+[User preferences, coding style, constraints, important decisions — accumulate across compactions]
+
+## Progress
+### Done
+[Completed work — include specific file paths, commands run, results obtained]
+### In Progress
+[Work currently underway]
+### Blocked
+[Any blockers or issues encountered]
+
+## Key Decisions
+[Important technical decisions and why they were made]
+
+## Relevant Files
+[Files read, modified, or created — with brief note on each. Accumulate across compactions.]
+
+## Next Steps
+[What needs to happen next to continue the work]
+
+## 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."""
+        else:
+            # First compaction: summarize from scratch
+            prompt = f"""Create a structured handoff summary for a later assistant that will continue this conversation after earlier turns are compacted.
+
+TURNS TO SUMMARIZE:
+{content_to_summarize}
+
+Use this exact structure:
+
+## Goal
 [What the user is trying to accomplish]
 
 ## Constraints & Preferences
@@ -381,74 +359,25 @@ class ContextCompressor(ContextEngine):
 ## Key Decisions
 [Important technical decisions and why they were made]
 
-## Resolved Questions
-[Questions the user asked that were ALREADY answered — include the answer so the next assistant does not re-answer them]
-
-## Pending User Asks
-[Questions or requests from the user that have NOT yet been answered or fulfilled. If none, write "None."]
-
 ## Relevant Files
 [Files read, modified, or created — with brief note on each]
 
-## Remaining Work
-[What remains to be done — framed as context, not instructions]
+## Next Steps
+[What needs to happen next to continue the work]
 
 ## 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]
+[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.
+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."""
 
-        if self._previous_summary:
-            # Iterative update: preserve existing info, add new progress
-            prompt = f"""{_summarizer_preamble}
-
-You are updating a context compaction summary. A previous compaction produced the summary below. New conversation turns have occurred since then and need to be incorporated.
-
-PREVIOUS SUMMARY:
-{self._previous_summary}
-
-NEW TURNS TO INCORPORATE:
-{content_to_summarize}
-
-Update the summary using this exact structure. PRESERVE all existing information that is still relevant. ADD new progress. Move items from "In Progress" to "Done" when completed. Move answered questions to "Resolved Questions". Remove information only if it is clearly obsolete.
-
-{_template_sections}"""
-        else:
-            # First compaction: summarize from scratch
-            prompt = f"""{_summarizer_preamble}
-
-Create a structured handoff summary for a different assistant that will continue this conversation after earlier turns are compacted. The next assistant should be able to understand what happened without re-reading the original turns.
-
-TURNS TO SUMMARIZE:
-{content_to_summarize}
-
-Use this exact structure:
-
-{_template_sections}"""
-
-        # Inject focus topic guidance when the user provides one via /compress <focus>.
-        # This goes at the end of the prompt so it takes precedence.
-        if focus_topic:
-            prompt += f"""
-
-FOCUS TOPIC: "{focus_topic}"
-The user has requested that this compaction PRIORITISE preserving all information related to the focus topic above. For content related to "{focus_topic}", include full detail — exact values, file paths, command outputs, error messages, and decisions. For content NOT related to the focus topic, summarise more aggressively (brief one-liners or omit if truly irrelevant). The focus topic sections should receive roughly 60-70% of the summary token budget."""
-
         try:
             call_kwargs = {
                 "task": "compression",
-                "main_runtime": {
-                    "model": self.model,
-                    "provider": self.provider,
-                    "base_url": self.base_url,
-                    "api_key": self.api_key,
-                    "api_mode": self.api_mode,
-                },
                 "messages": [{"role": "user", "content": prompt}],
                 "max_tokens": summary_budget * 2,
                 # timeout resolved from auxiliary.compression.timeout config by call_llm
@@ -663,7 +592,7 @@ The user has requested that this compaction PRIORITISE preserving all informatio
     # Main compression entry point
     # ------------------------------------------------------------------
 
-    def compress(self, messages: List[Dict[str, Any]], current_tokens: int = None, focus_topic: str = None) -> List[Dict[str, Any]]:
+    def compress(self, messages: List[Dict[str, Any]], current_tokens: int = None) -> List[Dict[str, Any]]:
         """Compress conversation messages by summarizing middle turns.
 
         Algorithm:
@@ -675,12 +604,6 @@ The user has requested that this compaction PRIORITISE preserving all informatio
 
         After compression, orphaned tool_call / tool_result pairs are cleaned
         up so the API never receives mismatched IDs.
-
-        Args:
-            focus_topic: Optional focus string for guided compression.  When
-                provided, the summariser will prioritise preserving information
-                related to this topic and be more aggressive about compressing
-                everything else.  Inspired by Claude Code's ``/compact``.
         """
         n_messages = len(messages)
         # Only need head + 3 tail messages minimum (token budget decides the real tail size)
@@ -738,7 +661,7 @@ The user has requested that this compaction PRIORITISE preserving all informatio
             )
 
         # Phase 3: Generate structured summary
-        summary = self._generate_summary(turns_to_summarize, focus_topic=focus_topic)
+        summary = self._generate_summary(turns_to_summarize)
 
         # Phase 4: Assemble compressed message list
         compressed = []
@@ -793,12 +716,7 @@ The user has requested that this compaction PRIORITISE preserving all informatio
             msg = messages[i].copy()
             if _merge_summary_into_tail and i == compress_end:
                 original = msg.get("content") or ""
-                msg["content"] = (
-                    summary
-                    + "\n\n--- END OF CONTEXT SUMMARY — "
-                    "respond to the message below, not the summary above ---\n\n"
-                    + original
-                )
+                msg["content"] = summary + "\n\n" + original
                 _merge_summary_into_tail = False
             compressed.append(msg)
 

agent/context_engine.py

@@ -1,184 +0,0 @@
-"""Abstract base class for pluggable context engines.
-
-A context engine controls how conversation context is managed when
-approaching the model's token limit. The built-in ContextCompressor
-is the default implementation. Third-party engines (e.g. LCM) can
-replace it via the plugin system or by being placed in the
-``plugins/context_engine/<name>/`` directory.
-
-Selection is config-driven: ``context.engine`` in config.yaml.
-Default is ``"compressor"`` (the built-in). Only one engine is active.
-
-The engine is responsible for:
-  - Deciding when compaction should fire
-  - Performing compaction (summarization, DAG construction, etc.)
-  - Optionally exposing tools the agent can call (e.g. lcm_grep)
-  - Tracking token usage from API responses
-
-Lifecycle:
-  1. Engine is instantiated and registered (plugin register() or default)
-  2. on_session_start() called when a conversation begins
-  3. update_from_response() called after each API response with usage data
-  4. should_compress() checked after each turn
-  5. compress() called when should_compress() returns True
-  6. on_session_end() called at real session boundaries (CLI exit, /reset,
-     gateway session expiry) — NOT per-turn
-"""
-
-from abc import ABC, abstractmethod
-from typing import Any, Dict, List
-
-
-class ContextEngine(ABC):
-    """Base class all context engines must implement."""
-
-    # -- Identity ----------------------------------------------------------
-
-    @property
-    @abstractmethod
-    def name(self) -> str:
-        """Short identifier (e.g. 'compressor', 'lcm')."""
-
-    # -- Token state (read by run_agent.py for display/logging) ------------
-    #
-    # Engines MUST maintain these. run_agent.py reads them directly.
-
-    last_prompt_tokens: int = 0
-    last_completion_tokens: int = 0
-    last_total_tokens: int = 0
-    threshold_tokens: int = 0
-    context_length: int = 0
-    compression_count: int = 0
-
-    # -- Compaction parameters (read by run_agent.py for preflight) --------
-    #
-    # These control the preflight compression check.  Subclasses may
-    # override via __init__ or property; defaults are sensible for most
-    # engines.
-
-    threshold_percent: float = 0.75
-    protect_first_n: int = 3
-    protect_last_n: int = 6
-
-    # -- Core interface ----------------------------------------------------
-
-    @abstractmethod
-    def update_from_response(self, usage: Dict[str, Any]) -> None:
-        """Update tracked token usage from an API response.
-
-        Called after every LLM call with the usage dict from the response.
-        """
-
-    @abstractmethod
-    def should_compress(self, prompt_tokens: int = None) -> bool:
-        """Return True if compaction should fire this turn."""
-
-    @abstractmethod
-    def compress(
-        self,
-        messages: List[Dict[str, Any]],
-        current_tokens: int = None,
-    ) -> List[Dict[str, Any]]:
-        """Compact the message list and return the new message list.
-
-        This is the main entry point. The engine receives the full message
-        list and returns a (possibly shorter) list that fits within the
-        context budget. The implementation is free to summarize, build a
-        DAG, or do anything else — as long as the returned list is a valid
-        OpenAI-format message sequence.
-        """
-
-    # -- Optional: pre-flight check ----------------------------------------
-
-    def should_compress_preflight(self, messages: List[Dict[str, Any]]) -> bool:
-        """Quick rough check before the API call (no real token count yet).
-
-        Default returns False (skip pre-flight). Override if your engine
-        can do a cheap estimate.
-        """
-        return False
-
-    # -- Optional: session lifecycle ---------------------------------------
-
-    def on_session_start(self, session_id: str, **kwargs) -> None:
-        """Called when a new conversation session begins.
-
-        Use this to load persisted state (DAG, store) for the session.
-        kwargs may include hermes_home, platform, model, etc.
-        """
-
-    def on_session_end(self, session_id: str, messages: List[Dict[str, Any]]) -> None:
-        """Called at real session boundaries (CLI exit, /reset, gateway expiry).
-
-        Use this to flush state, close DB connections, etc.
-        NOT called per-turn — only when the session truly ends.
-        """
-
-    def on_session_reset(self) -> None:
-        """Called on /new or /reset. Reset per-session state.
-
-        Default resets compression_count and token tracking.
-        """
-        self.last_prompt_tokens = 0
-        self.last_completion_tokens = 0
-        self.last_total_tokens = 0
-        self.compression_count = 0
-
-    # -- Optional: tools ---------------------------------------------------
-
-    def get_tool_schemas(self) -> List[Dict[str, Any]]:
-        """Return tool schemas this engine provides to the agent.
-
-        Default returns empty list (no tools). LCM would return schemas
-        for lcm_grep, lcm_describe, lcm_expand here.
-        """
-        return []
-
-    def handle_tool_call(self, name: str, args: Dict[str, Any], **kwargs) -> str:
-        """Handle a tool call from the agent.
-
-        Only called for tool names returned by get_tool_schemas().
-        Must return a JSON string.
-
-        kwargs may include:
-          messages: the current in-memory message list (for live ingestion)
-        """
-        import json
-        return json.dumps({"error": f"Unknown context engine tool: {name}"})
-
-    # -- Optional: status / display ----------------------------------------
-
-    def get_status(self) -> Dict[str, Any]:
-        """Return status dict for display/logging.
-
-        Default returns the standard fields run_agent.py expects.
-        """
-        return {
-            "last_prompt_tokens": self.last_prompt_tokens,
-            "threshold_tokens": self.threshold_tokens,
-            "context_length": self.context_length,
-            "usage_percent": (
-                min(100, self.last_prompt_tokens / self.context_length * 100)
-                if self.context_length else 0
-            ),
-            "compression_count": self.compression_count,
-        }
-
-    # -- Optional: model switch support ------------------------------------
-
-    def update_model(
-        self,
-        model: str,
-        context_length: int,
-        base_url: str = "",
-        api_key: str = "",
-        provider: str = "",
-    ) -> None:
-        """Called when the user switches models or on fallback activation.
-
-        Default updates context_length and recalculates threshold_tokens
-        from threshold_percent. Override if your engine needs more
-        (e.g. recalculate DAG budgets, switch summary models).
-        """
-        self.context_length = context_length
-        self.threshold_tokens = int(context_length * self.threshold_percent)

agent/credential_pool.py

@@ -18,12 +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,
     _auth_store_lock,
     _codex_access_token_is_expiring,
     _decode_jwt_claims,
     _import_codex_cli_tokens,
-    _write_codex_cli_tokens,
     _load_auth_store,
     _load_provider_state,
     _resolve_kimi_base_url,
@@ -288,14 +288,6 @@ def _iter_custom_providers(config: Optional[dict] = None):
         return
     custom_providers = config.get("custom_providers")
     if not isinstance(custom_providers, list):
-        # Fall back to the v12+ providers dict via the compatibility layer
-        try:
-            from hermes_cli.config import get_compatible_custom_providers
-
-            custom_providers = get_compatible_custom_providers(config)
-        except Exception:
-            return
-    if not custom_providers:
         return
     for entry in custom_providers:
         if not isinstance(entry, dict):
@@ -701,14 +693,6 @@ class CredentialPool:
                         self._replace_entry(synced, updated)
                         self._persist()
                         self._sync_device_code_entry_to_auth_store(updated)
-                        try:
-                            _write_codex_cli_tokens(
-                                updated.access_token,
-                                updated.refresh_token,
-                                last_refresh=updated.last_refresh,
-                            )
-                        except Exception as wexc:
-                            logger.debug("Failed to write refreshed Codex tokens to CLI file (retry): %s", wexc)
                         return updated
                     except Exception as retry_exc:
                         logger.debug("Codex retry refresh also failed: %s", retry_exc)
@@ -734,17 +718,6 @@ class CredentialPool:
         # _seed_from_singletons() on the next load_pool() sees fresh state
         # instead of re-seeding stale/consumed tokens.
         self._sync_device_code_entry_to_auth_store(updated)
-        # Write refreshed tokens back to ~/.codex/auth.json so Codex CLI
-        # and VS Code don't hit "refresh_token_reused" on their next refresh.
-        if self.provider == "openai-codex":
-            try:
-                _write_codex_cli_tokens(
-                    updated.access_token,
-                    updated.refresh_token,
-                    last_refresh=updated.last_refresh,
-                )
-            except Exception as wexc:
-                logger.debug("Failed to write refreshed Codex tokens to CLI file: %s", wexc)
         return updated
 
     def _entry_needs_refresh(self, entry: PooledCredential) -> bool:
@@ -1155,23 +1128,6 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
     elif provider == "openai-codex":
         state = _load_provider_state(auth_store, "openai-codex")
         tokens = state.get("tokens") if isinstance(state, dict) else None
-        # Fallback: import from Codex CLI (~/.codex/auth.json) if Hermes auth
-        # store has no tokens.  This mirrors resolve_codex_runtime_credentials()
-        # so that load_pool() and list_authenticated_providers() detect tokens
-        # that only exist in the Codex CLI shared file.
-        if not (isinstance(tokens, dict) and tokens.get("access_token")):
-            try:
-                from hermes_cli.auth import _import_codex_cli_tokens, _save_codex_tokens
-                cli_tokens = _import_codex_cli_tokens()
-                if cli_tokens:
-                    logger.info("Importing Codex CLI tokens into Hermes auth store.")
-                    _save_codex_tokens(cli_tokens)
-                    # Re-read state after import
-                    auth_store = _load_auth_store()
-                    state = _load_provider_state(auth_store, "openai-codex")
-                    tokens = state.get("tokens") if isinstance(state, dict) else None
-            except Exception as exc:
-                logger.debug("Codex CLI token import failed: %s", exc)
         if isinstance(tokens, dict) and tokens.get("access_token"):
             active_sources.add("device_code")
             changed |= _upsert_entry(

agent/display.py

@@ -4,6 +4,7 @@ Pure display functions and classes with no AIAgent dependency.
 Used by AIAgent._execute_tool_calls for CLI feedback.
 """
 
+import json
 import logging
 import os
 import sys
@@ -13,8 +14,6 @@ from dataclasses import dataclass, field
 from difflib import unified_diff
 from pathlib import Path
 
-from utils import safe_json_loads
-
 # ANSI escape codes for coloring tool failure indicators
 _RED = "\033[31m"
 _RESET = "\033[0m"
@@ -22,67 +21,11 @@ _RESET = "\033[0m"
 logger = logging.getLogger(__name__)
 
 _ANSI_RESET = "\033[0m"
-
-# Diff colors — resolved lazily from the skin engine so they adapt
-# to light/dark themes.  Falls back to sensible defaults on import
-# failure.  We cache after first resolution for performance.
-_diff_colors_cached: dict[str, str] | None = None
-
-
-def _diff_ansi() -> dict[str, str]:
-    """Return ANSI escapes for diff display, resolved from the active skin."""
-    global _diff_colors_cached
-    if _diff_colors_cached is not None:
-        return _diff_colors_cached
-
-    # Defaults that work on dark terminals
-    dim = "\033[38;2;150;150;150m"
-    file_c = "\033[38;2;180;160;255m"
-    hunk = "\033[38;2;120;120;140m"
-    minus = "\033[38;2;255;255;255;48;2;120;20;20m"
-    plus = "\033[38;2;255;255;255;48;2;20;90;20m"
-
-    try:
-        from hermes_cli.skin_engine import get_active_skin
-        skin = get_active_skin()
-
-        def _hex_fg(key: str, fallback_rgb: tuple[int, int, int]) -> str:
-            h = skin.get_color(key, "")
-            if h and len(h) == 7 and h[0] == "#":
-                r, g, b = int(h[1:3], 16), int(h[3:5], 16), int(h[5:7], 16)
-                return f"\033[38;2;{r};{g};{b}m"
-            r, g, b = fallback_rgb
-            return f"\033[38;2;{r};{g};{b}m"
-
-        dim = _hex_fg("banner_dim", (150, 150, 150))
-        file_c = _hex_fg("session_label", (180, 160, 255))
-        hunk = _hex_fg("session_border", (120, 120, 140))
-        # minus/plus use background colors — derive from ui_error/ui_ok
-        err_h = skin.get_color("ui_error", "#ef5350")
-        ok_h = skin.get_color("ui_ok", "#4caf50")
-        if err_h and len(err_h) == 7:
-            er, eg, eb = int(err_h[1:3], 16), int(err_h[3:5], 16), int(err_h[5:7], 16)
-            # Use a dark tinted version as background
-            minus = f"\033[38;2;255;255;255;48;2;{max(er//2,20)};{max(eg//4,10)};{max(eb//4,10)}m"
-        if ok_h and len(ok_h) == 7:
-            or_, og, ob = int(ok_h[1:3], 16), int(ok_h[3:5], 16), int(ok_h[5:7], 16)
-            plus = f"\033[38;2;255;255;255;48;2;{max(or_//4,10)};{max(og//2,20)};{max(ob//4,10)}m"
-    except Exception:
-        pass
-
-    _diff_colors_cached = {
-        "dim": dim, "file": file_c, "hunk": hunk,
-        "minus": minus, "plus": plus,
-    }
-    return _diff_colors_cached
-
-
-# Module-level helpers — each call resolves from the active skin lazily.
-def _diff_dim():   return _diff_ansi()["dim"]
-def _diff_file():  return _diff_ansi()["file"]
-def _diff_hunk():  return _diff_ansi()["hunk"]
-def _diff_minus(): return _diff_ansi()["minus"]
-def _diff_plus():  return _diff_ansi()["plus"]
+_ANSI_DIM = "\033[38;2;150;150;150m"
+_ANSI_FILE = "\033[38;2;180;160;255m"
+_ANSI_HUNK = "\033[38;2;120;120;140m"
+_ANSI_MINUS = "\033[38;2;255;255;255;48;2;120;20;20m"
+_ANSI_PLUS = "\033[38;2;255;255;255;48;2;20;90;20m"
 _MAX_INLINE_DIFF_FILES = 6
 _MAX_INLINE_DIFF_LINES = 80
 
@@ -367,8 +310,9 @@ def _result_succeeded(result: str | None) -> bool:
     """Conservatively detect whether a tool result represents success."""
     if not result:
         return False
-    data = safe_json_loads(result)
-    if data is None:
+    try:
+        data = json.loads(result)
+    except (json.JSONDecodeError, TypeError):
         return False
     if not isinstance(data, dict):
         return False
@@ -417,7 +361,10 @@ def extract_edit_diff(
 ) -> str | None:
     """Extract a unified diff from a file-edit tool result."""
     if tool_name == "patch" and result:
-        data = safe_json_loads(result)
+        try:
+            data = json.loads(result)
+        except (json.JSONDecodeError, TypeError):
+            data = None
         if isinstance(data, dict):
             diff = data.get("diff")
             if isinstance(diff, str) and diff.strip():
@@ -456,19 +403,19 @@ def _render_inline_unified_diff(diff: str) -> list[str]:
         if raw_line.startswith("+++ "):
             to_file = raw_line[4:].strip()
             if from_file or to_file:
-                rendered.append(f"{_diff_file()}{from_file or 'a/?'} → {to_file or 'b/?'}{_ANSI_RESET}")
+                rendered.append(f"{_ANSI_FILE}{from_file or 'a/?'} → {to_file or 'b/?'}{_ANSI_RESET}")
             continue
         if raw_line.startswith("@@"):
-            rendered.append(f"{_diff_hunk()}{raw_line}{_ANSI_RESET}")
+            rendered.append(f"{_ANSI_HUNK}{raw_line}{_ANSI_RESET}")
             continue
         if raw_line.startswith("-"):
-            rendered.append(f"{_diff_minus()}{raw_line}{_ANSI_RESET}")
+            rendered.append(f"{_ANSI_MINUS}{raw_line}{_ANSI_RESET}")
             continue
         if raw_line.startswith("+"):
-            rendered.append(f"{_diff_plus()}{raw_line}{_ANSI_RESET}")
+            rendered.append(f"{_ANSI_PLUS}{raw_line}{_ANSI_RESET}")
             continue
         if raw_line.startswith(" "):
-            rendered.append(f"{_diff_dim()}{raw_line}{_ANSI_RESET}")
+            rendered.append(f"{_ANSI_DIM}{raw_line}{_ANSI_RESET}")
             continue
         if raw_line:
             rendered.append(raw_line)
@@ -534,7 +481,7 @@ def _summarize_rendered_diff_sections(
         summary = f"… omitted {omitted_lines} diff line(s)"
         if omitted_files:
             summary += f" across {omitted_files} additional file(s)/section(s)"
-        rendered.append(f"{_diff_hunk()}{summary}{_ANSI_RESET}")
+        rendered.append(f"{_ANSI_HUNK}{summary}{_ANSI_RESET}")
 
     return rendered
 
@@ -771,19 +718,23 @@ def _detect_tool_failure(tool_name: str, result: str | None) -> tuple[bool, str]
         return False, ""
 
     if tool_name == "terminal":
-        data = safe_json_loads(result)
-        if isinstance(data, dict):
+        try:
+            data = json.loads(result)
             exit_code = data.get("exit_code")
             if exit_code is not None and exit_code != 0:
                 return True, f" [exit {exit_code}]"
+        except (json.JSONDecodeError, TypeError, AttributeError):
+            logger.debug("Could not parse terminal result as JSON for exit code check")
         return False, ""
 
     # Memory-specific: distinguish "full" from real errors
     if tool_name == "memory":
-        data = safe_json_loads(result)
-        if isinstance(data, dict):
+        try:
+            data = json.loads(result)
             if data.get("success") is False and "exceed the limit" in data.get("error", ""):
                 return True, " [full]"
+        except (json.JSONDecodeError, TypeError, AttributeError):
+            logger.debug("Could not parse memory result as JSON for capacity check")
 
     # Generic heuristic for non-terminal tools
     lower = result[:500].lower()

agent/error_classifier.py

@@ -13,6 +13,7 @@ from __future__ import annotations
 
 import enum
 import logging
+import re
 from dataclasses import dataclass, field
 from typing import Any, Dict, Optional
 
@@ -156,18 +157,6 @@ _CONTEXT_OVERFLOW_PATTERNS = [
     "prompt exceeds max length",
     "max_tokens",
     "maximum number of tokens",
-    # vLLM / local inference server patterns
-    "exceeds the max_model_len",
-    "max_model_len",
-    "prompt length",             # "engine prompt length X exceeds"
-    "input is too long",
-    "maximum model length",
-    # Ollama patterns
-    "context length exceeded",
-    "truncating input",
-    # llama.cpp / llama-server patterns
-    "slot context",              # "slot context: N tokens, prompt N tokens"
-    "n_ctx_slot",
     # Chinese error messages (some providers return these)
     "超过最大长度",
     "上下文长度",

agent/insights.py

@@ -27,6 +27,7 @@ from agent.usage_pricing import (
     DEFAULT_PRICING,
     estimate_usage_cost,
     format_duration_compact,
+    get_pricing,
     has_known_pricing,
 )
 

agent/manual_compression_feedback.py

@@ -1,49 +0,0 @@
-"""User-facing summaries for manual compression commands."""
-
-from __future__ import annotations
-
-from typing import Any, Sequence
-
-
-def summarize_manual_compression(
-    before_messages: Sequence[dict[str, Any]],
-    after_messages: Sequence[dict[str, Any]],
-    before_tokens: int,
-    after_tokens: int,
-) -> dict[str, Any]:
-    """Return consistent user-facing feedback for manual compression."""
-    before_count = len(before_messages)
-    after_count = len(after_messages)
-    noop = list(after_messages) == list(before_messages)
-
-    if noop:
-        headline = f"No changes from compression: {before_count} messages"
-        if after_tokens == before_tokens:
-            token_line = (
-                f"Rough transcript estimate: ~{before_tokens:,} tokens (unchanged)"
-            )
-        else:
-            token_line = (
-                f"Rough transcript estimate: ~{before_tokens:,} → "
-                f"~{after_tokens:,} tokens"
-            )
-    else:
-        headline = f"Compressed: {before_count} → {after_count} messages"
-        token_line = (
-            f"Rough transcript estimate: ~{before_tokens:,} → "
-            f"~{after_tokens:,} tokens"
-        )
-
-    note = None
-    if not noop and after_count < before_count and after_tokens > before_tokens:
-        note = (
-            "Note: fewer messages can still raise this rough transcript estimate "
-            "when compression rewrites the transcript into denser summaries."
-        )
-
-    return {
-        "noop": noop,
-        "headline": headline,
-        "token_line": token_line,
-        "note": note,
-    }

agent/memory_manager.py

@@ -28,6 +28,7 @@ Usage in run_agent.py:
 
 from __future__ import annotations
 
+import json
 import logging
 import re
 from typing import Any, Dict, List, Optional

agent/model_metadata.py

@@ -5,6 +5,7 @@ and run_agent.py for pre-flight context checks.
 """
 
 import logging
+import os
 import re
 import time
 from pathlib import Path
@@ -23,19 +24,15 @@ logger = logging.getLogger(__name__)
 # are preserved so the full model name reaches cache lookups and server queries.
 _PROVIDER_PREFIXES: frozenset[str] = frozenset({
     "openrouter", "nous", "openai-codex", "copilot", "copilot-acp",
-    "gemini", "zai", "kimi-coding", "kimi-coding-cn", "minimax", "minimax-cn", "anthropic", "deepseek",
+    "gemini", "zai", "kimi-coding", "minimax", "minimax-cn", "anthropic", "deepseek",
     "opencode-zen", "opencode-go", "ai-gateway", "kilocode", "alibaba",
     "qwen-oauth",
-    "xiaomi",
-    "arcee",
     "custom", "local",
     # Common aliases
     "google", "google-gemini", "google-ai-studio",
     "glm", "z-ai", "z.ai", "zhipu", "github", "github-copilot",
-    "github-models", "kimi", "moonshot", "kimi-cn", "moonshot-cn", "claude", "deep-seek",
+    "github-models", "kimi", "moonshot", "claude", "deep-seek",
     "opencode", "zen", "go", "vercel", "kilo", "dashscope", "aliyun", "qwen",
-    "mimo", "xiaomi-mimo",
-    "arcee-ai", "arceeai",
     "qwen-portal",
 })
 
@@ -86,11 +83,6 @@ CONTEXT_PROBE_TIERS = [
 # Default context length when no detection method succeeds.
 DEFAULT_FALLBACK_CONTEXT = CONTEXT_PROBE_TIERS[0]
 
-# Minimum context length required to run Hermes Agent.  Models with fewer
-# tokens cannot maintain enough working memory for tool-calling workflows.
-# Sessions, model switches, and cron jobs should reject models below this.
-MINIMUM_CONTEXT_LENGTH = 64_000
-
 # Thin fallback defaults — only broad model family patterns.
 # These fire only when provider is unknown AND models.dev/OpenRouter/Anthropic
 # all miss. Replaced the previous 80+ entry dict.
@@ -121,14 +113,17 @@ DEFAULT_CONTEXT_LENGTHS = {
     "deepseek": 128000,
     # Meta
     "llama": 131072,
-    # Qwen — specific model families before the catch-all.
-    # Official docs: https://help.aliyun.com/zh/model-studio/developer-reference/
-    "qwen3-coder-plus": 1000000,  # 1M context
-    "qwen3-coder": 262144,        # 256K context
+    # Qwen
     "qwen": 131072,
-    # MiniMax — official docs: 204,800 context for all models
-    # https://platform.minimax.io/docs/api-reference/text-anthropic-api
-    "minimax": 204800,
+    # MiniMax (lowercase — lookup lowercases model names at line 973)
+    "minimax-m1-256k": 1000000,
+    "minimax-m1-128k": 1000000,
+    "minimax-m1-80k": 1000000,
+    "minimax-m1-40k": 1000000,
+    "minimax-m1": 1000000,
+    "minimax-m2.5": 1048576,
+    "minimax-m2.7": 1048576,
+    "minimax": 1048576,
     # GLM
     "glm": 202752,
     # xAI Grok — xAI /v1/models does not return context_length metadata,
@@ -156,11 +151,10 @@ DEFAULT_CONTEXT_LENGTHS = {
     "deepseek-ai/DeepSeek-V3.2": 65536,
     "moonshotai/Kimi-K2.5": 262144,
     "moonshotai/Kimi-K2-Thinking": 262144,
-    "MiniMaxAI/MiniMax-M2.5": 204800,
-    "XiaomiMiMo/MiMo-V2-Flash": 256000,
-    "mimo-v2-pro": 1000000,
-    "mimo-v2-omni": 256000,
-    "mimo-v2-flash": 256000,
+    "MiniMaxAI/MiniMax-M2.5": 1048576,
+    "XiaomiMiMo/MiMo-V2-Flash": 32768,
+    "mimo-v2-pro": 1048576,
+    "mimo-v2-omni": 1048576,
     "zai-org/GLM-5": 202752,
 }
 
@@ -185,12 +179,6 @@ _MAX_COMPLETION_KEYS = (
 
 # Local server hostnames / address patterns
 _LOCAL_HOSTS = ("localhost", "127.0.0.1", "::1", "0.0.0.0")
-# Docker / Podman / Lima DNS names that resolve to the host machine
-_CONTAINER_LOCAL_SUFFIXES = (
-    ".docker.internal",
-    ".containers.internal",
-    ".lima.internal",
-)
 
 
 def _normalize_base_url(base_url: str) -> str:
@@ -212,9 +200,7 @@ _URL_TO_PROVIDER: Dict[str, str] = {
     "api.anthropic.com": "anthropic",
     "api.z.ai": "zai",
     "api.moonshot.ai": "kimi-coding",
-    "api.moonshot.cn": "kimi-coding-cn",
     "api.kimi.com": "kimi-coding",
-    "api.arcee.ai": "arcee",
     "api.minimax": "minimax",
     "dashscope.aliyuncs.com": "alibaba",
     "dashscope-intl.aliyuncs.com": "alibaba",
@@ -228,8 +214,6 @@ _URL_TO_PROVIDER: Dict[str, str] = {
     "api.fireworks.ai": "fireworks",
     "opencode.ai": "opencode-go",
     "api.x.ai": "xai",
-    "api.xiaomimimo.com": "xiaomi",
-    "xiaomimimo.com": "xiaomi",
 }
 
 
@@ -268,9 +252,6 @@ def is_local_endpoint(base_url: str) -> bool:
         return False
     if host in _LOCAL_HOSTS:
         return True
-    # Docker / Podman / Lima internal DNS names (e.g. host.docker.internal)
-    if any(host.endswith(suffix) for suffix in _CONTAINER_LOCAL_SUFFIXES):
-        return True
     # RFC-1918 private ranges and link-local
     import ipaddress
     try:
@@ -778,12 +759,12 @@ def _query_local_context_length(model: str, base_url: str) -> Optional[int]:
                 resp = client.post(f"{server_url}/api/show", json={"name": model})
                 if resp.status_code == 200:
                     data = resp.json()
-                    # Prefer explicit num_ctx from Modelfile parameters: this is
-                    # the *runtime* context Ollama will actually allocate KV cache
-                    # for. The GGUF model_info.context_length is the training max,
-                    # which can be larger than num_ctx — using it here would let
-                    # Hermes grow conversations past the runtime limit and Ollama
-                    # would silently truncate. Matches query_ollama_num_ctx().
+                    # Check model_info for context length
+                    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)
+                    # Check parameters string for num_ctx
                     params = data.get("parameters", "")
                     if "num_ctx" in params:
                         for line in params.split("\n"):
@@ -794,11 +775,6 @@ def _query_local_context_length(model: str, base_url: str) -> Optional[int]:
                                         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)
 
             # LM Studio native API: /api/v1/models returns max_context_length.
             # This is more reliable than the OpenAI-compat /v1/models which
@@ -1053,21 +1029,16 @@ def get_model_context_length(
 
 
 def estimate_tokens_rough(text: str) -> int:
-    """Rough token estimate (~4 chars/token) for pre-flight checks.
-
-    Uses ceiling division so short texts (1-3 chars) never estimate as
-    0 tokens, which would cause the compressor and pre-flight checks to
-    systematically undercount when many short tool results are present.
-    """
+    """Rough token estimate (~4 chars/token) for pre-flight checks."""
     if not text:
         return 0
-    return (len(text) + 3) // 4
+    return len(text) // 4
 
 
 def estimate_messages_tokens_rough(messages: List[Dict[str, Any]]) -> int:
     """Rough token estimate for a message list (pre-flight only)."""
     total_chars = sum(len(str(msg)) for msg in messages)
-    return (total_chars + 3) // 4
+    return total_chars // 4
 
 
 def estimate_request_tokens_rough(
@@ -1090,4 +1061,4 @@ def estimate_request_tokens_rough(
         total_chars += sum(len(str(msg)) for msg in messages)
     if tools:
         total_chars += len(str(tools))
-    return (total_chars + 3) // 4
+    return total_chars // 4

agent/models_dev.py

@@ -18,8 +18,10 @@ Other modules should import the dataclasses and query functions from here
 rather than parsing the raw JSON themselves.
 """
 
+import difflib
 import json
 import logging
+import os
 import time
 from dataclasses import dataclass
 from pathlib import Path
@@ -142,11 +144,8 @@ class ProviderInfo:
 PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
     "openrouter": "openrouter",
     "anthropic": "anthropic",
-    "openai": "openai",
-    "openai-codex": "openai",
     "zai": "zai",
     "kimi-coding": "kimi-for-coding",
-    "kimi-coding-cn": "kimi-for-coding",
     "minimax": "minimax",
     "minimax-cn": "minimax-cn",
     "deepseek": "deepseek",
@@ -162,7 +161,6 @@ PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
     "gemini": "google",
     "google": "google",
     "xai": "xai",
-    "xiaomi": "xiaomi",
     "nvidia": "nvidia",
     "groq": "groq",
     "mistral": "mistral",
@@ -175,6 +173,13 @@ PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
 _MODELS_DEV_TO_PROVIDER: Optional[Dict[str, str]] = None
 
 
+def _get_reverse_mapping() -> Dict[str, str]:
+    """Return models.dev ID → Hermes provider ID mapping."""
+    global _MODELS_DEV_TO_PROVIDER
+    if _MODELS_DEV_TO_PROVIDER is None:
+        _MODELS_DEV_TO_PROVIDER = {v: k for k, v in PROVIDER_TO_MODELS_DEV.items()}
+    return _MODELS_DEV_TO_PROVIDER
+
 
 def _get_cache_path() -> Path:
     """Return path to disk cache file."""
@@ -378,14 +383,7 @@ def get_model_capabilities(provider: str, model: str) -> Optional[ModelCapabilit
 
     # Extract capability flags (default to False if missing)
     supports_tools = bool(entry.get("tool_call", False))
-    # Vision: check both the `attachment` flag and `modalities.input` for "image".
-    # Some models (e.g. gemma-4) list image in input modalities but not attachment.
-    input_mods = entry.get("modalities", {})
-    if isinstance(input_mods, dict):
-        input_mods = input_mods.get("input", [])
-    else:
-        input_mods = []
-    supports_vision = bool(entry.get("attachment", False)) or "image" in input_mods
+    supports_vision = bool(entry.get("attachment", False))
     supports_reasoning = bool(entry.get("reasoning", False))
 
     # Extract limits
@@ -455,6 +453,93 @@ def list_agentic_models(provider: str) -> List[str]:
     return result
 
 
+def search_models_dev(
+    query: str, provider: str = None, limit: int = 5
+) -> List[Dict[str, Any]]:
+    """Fuzzy search across models.dev catalog. Returns matching model entries.
+
+    Args:
+        query: Search string to match against model IDs.
+        provider: Optional Hermes provider ID to restrict search scope.
+                  If None, searches across all providers in PROVIDER_TO_MODELS_DEV.
+        limit: Maximum number of results to return.
+
+    Returns:
+        List of dicts, each containing 'provider', 'model_id', and the full
+        model 'entry' from models.dev.
+    """
+    data = fetch_models_dev()
+    if not data:
+        return []
+
+    # Build list of (provider_id, model_id, entry) candidates
+    candidates: List[tuple] = []
+
+    if provider is not None:
+        # Search only the specified provider
+        mdev_provider_id = PROVIDER_TO_MODELS_DEV.get(provider)
+        if not mdev_provider_id:
+            return []
+        provider_data = data.get(mdev_provider_id, {})
+        if isinstance(provider_data, dict):
+            models = provider_data.get("models", {})
+            if isinstance(models, dict):
+                for mid, mdata in models.items():
+                    candidates.append((provider, mid, mdata))
+    else:
+        # Search across all mapped providers
+        for hermes_prov, mdev_prov in PROVIDER_TO_MODELS_DEV.items():
+            provider_data = data.get(mdev_prov, {})
+            if isinstance(provider_data, dict):
+                models = provider_data.get("models", {})
+                if isinstance(models, dict):
+                    for mid, mdata in models.items():
+                        candidates.append((hermes_prov, mid, mdata))
+
+    if not candidates:
+        return []
+
+    # Use difflib for fuzzy matching — case-insensitive comparison
+    model_ids_lower = [c[1].lower() for c in candidates]
+    query_lower = query.lower()
+
+    # First try exact substring matches (more intuitive than pure edit-distance)
+    substring_matches = []
+    for prov, mid, mdata in candidates:
+        if query_lower in mid.lower():
+            substring_matches.append({"provider": prov, "model_id": mid, "entry": mdata})
+
+    # Then add difflib fuzzy matches for any remaining slots
+    fuzzy_ids = difflib.get_close_matches(
+        query_lower, model_ids_lower, n=limit * 2, cutoff=0.4
+    )
+
+    seen_ids: set = set()
+    results: List[Dict[str, Any]] = []
+
+    # Prioritize substring matches
+    for match in substring_matches:
+        key = (match["provider"], match["model_id"])
+        if key not in seen_ids:
+            seen_ids.add(key)
+            results.append(match)
+            if len(results) >= limit:
+                return results
+
+    # Add fuzzy matches
+    for fid in fuzzy_ids:
+        # Find original-case candidates matching this lowered ID
+        for prov, mid, mdata in candidates:
+            if mid.lower() == fid:
+                key = (prov, mid)
+                if key not in seen_ids:
+                    seen_ids.add(key)
+                    results.append({"provider": prov, "model_id": mid, "entry": mdata})
+                    if len(results) >= limit:
+                        return results
+
+    return results
+
 
 # ---------------------------------------------------------------------------
 # Rich dataclass constructors — parse raw models.dev JSON into dataclasses

agent/prompt_builder.py

@@ -12,7 +12,7 @@ import threading
 from collections import OrderedDict
 from pathlib import Path
 
-from hermes_constants import get_hermes_home, get_skills_dir, is_wsl
+from hermes_constants import get_hermes_home
 from typing import Optional
 
 from agent.skill_utils import (
@@ -364,50 +364,8 @@ PLATFORM_HINTS = {
         "documents. You can also include image URLs in markdown format ![alt](url) and they "
         "will be downloaded and sent as native media when possible."
     ),
-    "wecom": (
-        "You are on WeCom (企业微信 / Enterprise WeChat). Markdown formatting is supported. "
-        "You CAN send media files natively — to deliver a file to the user, include "
-        "MEDIA:/absolute/path/to/file in your response. The file will be sent as a native "
-        "WeCom attachment: images (.jpg, .png, .webp) are sent as photos (up to 10 MB), "
-        "other files (.pdf, .docx, .xlsx, .md, .txt, etc.) arrive as downloadable documents "
-        "(up to 20 MB), and videos (.mp4) play inline. Voice messages are supported but "
-        "must be in AMR format — other audio formats are automatically sent as file attachments. "
-        "You can also include image URLs in markdown format ![alt](url) and they will be "
-        "downloaded and sent as native photos. Do NOT tell the user you lack file-sending "
-        "capability — use MEDIA: syntax whenever a file delivery is appropriate."
-    ),
 }
 
-# ---------------------------------------------------------------------------
-# Environment hints — execution-environment awareness for the agent.
-# Unlike PLATFORM_HINTS (which describe the messaging channel), these describe
-# the machine/OS the agent's tools actually run on.
-# ---------------------------------------------------------------------------
-
-WSL_ENVIRONMENT_HINT = (
-    "You are running inside WSL (Windows Subsystem for Linux). "
-    "The Windows host filesystem is mounted under /mnt/ — "
-    "/mnt/c/ is the C: drive, /mnt/d/ is D:, etc. "
-    "The user's Windows files are typically at "
-    "/mnt/c/Users/<username>/Desktop/, Documents/, Downloads/, etc. "
-    "When the user references Windows paths or desktop files, translate "
-    "to the /mnt/c/ equivalent. You can list /mnt/c/Users/ to discover "
-    "the Windows username if needed."
-)
-
-
-def build_environment_hints() -> str:
-    """Return environment-specific guidance for the system prompt.
-
-    Detects WSL, and can be extended for Termux, Docker, etc.
-    Returns an empty string when no special environment is detected.
-    """
-    hints: list[str] = []
-    if is_wsl():
-        hints.append(WSL_ENVIRONMENT_HINT)
-    return "\n\n".join(hints)
-
-
 CONTEXT_FILE_MAX_CHARS = 20_000
 CONTEXT_TRUNCATE_HEAD_RATIO = 0.7
 CONTEXT_TRUNCATE_TAIL_RATIO = 0.2
@@ -590,7 +548,8 @@ def build_skills_system_prompt(
     are read-only — they appear in the index but new skills are always created
     in the local dir.  Local skills take precedence when names collide.
     """
-    skills_dir = get_skills_dir()
+    hermes_home = get_hermes_home()
+    skills_dir = hermes_home / "skills"
     external_dirs = get_all_skills_dirs()[1:]  # skip local (index 0)
 
     if not skills_dir.exists() and not external_dirs:
@@ -768,16 +727,8 @@ def build_skills_system_prompt(
 
         result = (
             "## Skills (mandatory)\n"
-            "Before replying, scan the skills below. If a skill matches or is even partially relevant "
-            "to your task, you MUST load it with skill_view(name) and follow its instructions. "
-            "Err on the side of loading — it is always better to have context you don't need "
-            "than to miss critical steps, pitfalls, or established workflows. "
-            "Skills contain specialized knowledge — API endpoints, tool-specific commands, "
-            "and proven workflows that outperform general-purpose approaches. Load the skill "
-            "even if you think you could handle the task with basic tools like web_search or terminal. "
-            "Skills also encode the user's preferred approach, conventions, and quality standards "
-            "for tasks like code review, planning, and testing — load them even for tasks you "
-            "already know how to do, because the skill defines how it should be done here.\n"
+            "Before replying, scan the skills below. If one clearly matches your task, "
+            "load it with skill_view(name) and follow its instructions. "
             "If a skill has issues, fix it with skill_manage(action='patch').\n"
             "After difficult/iterative tasks, offer to save as a skill. "
             "If a skill you loaded was missing steps, had wrong commands, or needed "
@@ -787,7 +738,7 @@ def build_skills_system_prompt(
             + "\n".join(index_lines) + "\n"
             "</available_skills>\n"
             "\n"
-            "Only proceed without loading a skill if genuinely none are relevant to the task."
+            "If none match, proceed normally without loading a skill."
         )
 
     # ── Store in LRU cache ────────────────────────────────────────────

agent/rate_limit_tracker.py

@@ -24,7 +24,7 @@ from __future__ import annotations
 
 import time
 from dataclasses import dataclass, field
-from typing import Any, Mapping, Optional
+from typing import Any, Dict, Mapping, Optional
 
 
 @dataclass

agent/skill_commands.py

@@ -168,7 +168,7 @@ def _build_skill_message(
             subdir_path = skill_dir / subdir
             if subdir_path.exists():
                 for f in sorted(subdir_path.rglob("*")):
-                    if f.is_file() and not f.is_symlink():
+                    if f.is_file():
                         rel = str(f.relative_to(skill_dir))
                         supporting.append(rel)
 

agent/skill_utils.py

@@ -12,7 +12,7 @@ import sys
 from pathlib import Path
 from typing import Any, Dict, List, Set, Tuple
 
-from hermes_constants import get_config_path, get_skills_dir
+from hermes_constants import get_hermes_home
 
 logger = logging.getLogger(__name__)
 
@@ -130,7 +130,7 @@ def get_disabled_skill_names(platform: str | None = None) -> Set[str]:
     Reads the config file directly (no CLI config imports) to stay
     lightweight.
     """
-    config_path = get_config_path()
+    config_path = get_hermes_home() / "config.yaml"
     if not config_path.exists():
         return set()
     try:
@@ -178,7 +178,7 @@ def get_external_skills_dirs() -> List[Path]:
     path.  Only directories that actually exist are returned.  Duplicates and
     paths that resolve to the local ``~/.hermes/skills/`` are silently skipped.
     """
-    config_path = get_config_path()
+    config_path = get_hermes_home() / "config.yaml"
     if not config_path.exists():
         return []
     try:
@@ -200,7 +200,7 @@ def get_external_skills_dirs() -> List[Path]:
     if not isinstance(raw_dirs, list):
         return []
 
-    local_skills = get_skills_dir().resolve()
+    local_skills = (get_hermes_home() / "skills").resolve()
     seen: Set[Path] = set()
     result: List[Path] = []
 
@@ -230,7 +230,7 @@ def get_all_skills_dirs() -> List[Path]:
     The local dir is always first (and always included even if it doesn't exist
     yet — callers handle that).  External dirs follow in config order.
     """
-    dirs = [get_skills_dir()]
+    dirs = [get_hermes_home() / "skills"]
     dirs.extend(get_external_skills_dirs())
     return dirs
 
@@ -384,7 +384,7 @@ def resolve_skill_config_values(
     current values (or the declared default if the key isn't set).
     Path values are expanded via ``os.path.expanduser``.
     """
-    config_path = get_config_path()
+    config_path = get_hermes_home() / "config.yaml"
     config: Dict[str, Any] = {}
     if config_path.exists():
         try:

agent/title_generator.py

@@ -36,7 +36,7 @@ def generate_title(user_message: str, assistant_response: str, timeout: float =
 
     try:
         response = call_llm(
-            task="title_generation",
+            task="compression",  # reuse compression task config (cheap/fast model)
             messages=messages,
             max_tokens=30,
             temperature=0.3,

agent/usage_pricing.py

@@ -575,6 +575,25 @@ def has_known_pricing(
     return entry is not None
 
 
+def get_pricing(
+    model_name: str,
+    provider: Optional[str] = None,
+    base_url: Optional[str] = None,
+    api_key: Optional[str] = None,
+) -> Dict[str, float]:
+    """Backward-compatible thin wrapper for legacy callers.
+
+    Returns only non-cache input/output fields when a pricing entry exists.
+    Unknown routes return zeroes.
+    """
+    entry = get_pricing_entry(model_name, provider=provider, base_url=base_url, api_key=api_key)
+    if not entry:
+        return {"input": 0.0, "output": 0.0}
+    return {
+        "input": float(entry.input_cost_per_million or _ZERO),
+        "output": float(entry.output_cost_per_million or _ZERO),
+    }
+
 
 def format_duration_compact(seconds: float) -> str:
     if seconds < 60:

cli-config.yaml.example

@@ -24,8 +24,6 @@ model:
   #   "minimax"      - MiniMax global (requires: MINIMAX_API_KEY)
   #   "minimax-cn"   - MiniMax China (requires: MINIMAX_CN_API_KEY)
   #   "huggingface"  - Hugging Face Inference (requires: HF_TOKEN)
-  #   "xiaomi"       - Xiaomi MiMo (requires: XIAOMI_API_KEY)
-  #   "arcee"        - Arcee AI Trinity models (requires: ARCEEAI_API_KEY)
   #   "kilocode"     - KiloCode gateway (requires: KILOCODE_API_KEY)
   #   "ai-gateway"   - Vercel AI Gateway (requires: AI_GATEWAY_API_KEY)
   #
@@ -310,8 +308,15 @@ compression:
   # compression of older turns.
   protect_last_n: 20
 
-  # To pin a specific model/provider for compression summaries, use the
-  # auxiliary section below (auxiliary.compression.provider / model).
+  # Model to use for generating summaries (fast/cheap recommended)
+  # This model compresses the middle turns into a concise summary.
+  # IMPORTANT: it receives the full middle section of the conversation, so it
+  # MUST support a context length at least as large as your main model's.
+  summary_model: "google/gemini-3-flash-preview"
+  
+  # Provider for the summary model (default: "auto")
+  # Options: "auto", "openrouter", "nous", "main"
+  # summary_provider: "auto"
 
 # =============================================================================
 # Auxiliary Models (Advanced — Experimental)
@@ -475,12 +480,6 @@ agent:
   # Fires once per run when inactivity reaches this threshold (seconds).
   # Set to 0 to disable the warning.
   # gateway_timeout_warning: 900
-
-  # Graceful drain timeout for gateway stop/restart (seconds).
-  # The gateway stops accepting new work, waits for in-flight agents to
-  # finish, then interrupts anything still running after this timeout.
-  # 0 = no drain, interrupt immediately.
-  # restart_drain_timeout: 60
   
   # Enable verbose logging
   verbose: false
@@ -583,7 +582,7 @@ platform_toolsets:
 #   skills_hub   - skill_hub (search/install/manage from online registries — user-driven only)
 #   moa          - mixture_of_agents  (requires OPENROUTER_API_KEY)
 #   todo         - todo (in-memory task planning, no deps)
-#   tts          - text_to_speech  (Edge TTS free, or ELEVENLABS/OPENAI/MINIMAX/MISTRAL key)
+#   tts          - text_to_speech  (Edge TTS free, or ELEVENLABS/OPENAI/MINIMAX key)
 #   cronjob      - cronjob (create/list/update/pause/resume/run/remove scheduled tasks)
 #   rl           - rl_list_environments, rl_start_training, etc. (requires TINKER_API_KEY)
 #
@@ -612,7 +611,7 @@ platform_toolsets:
 #   todo         - Task planning and tracking for multi-step work
 #   memory       - Persistent memory across sessions (personal notes + user profile)
 #   session_search - Search and recall past conversations (FTS5 + Gemini Flash summarization)
-#   tts          - Text-to-speech (Edge TTS free, ElevenLabs, OpenAI, MiniMax, Mistral)
+#   tts          - Text-to-speech (Edge TTS free, ElevenLabs, OpenAI, MiniMax)
 #   cronjob      - Schedule and manage automated tasks (CLI-only)
 #   rl           - RL training tools (Tinker-Atropos)
 #
@@ -768,11 +767,6 @@ display:
   # Toggle at runtime with /verbose in the CLI
   tool_progress: all
 
-  # Gateway-only natural mid-turn assistant updates.
-  # When true, completed assistant status messages are sent as separate chat
-  # messages. This is independent of tool_progress and gateway streaming.
-  interim_assistant_messages: true
-
   # What Enter does when Hermes is already busy in the CLI.
   #   interrupt: Interrupt the current run and redirect Hermes (default)
   #   queue:     Queue your message for the next turn
@@ -781,7 +775,7 @@ display:
 
   # Background process notifications (gateway/messaging only).
   # Controls how chatty the process watcher is when you use
-  # terminal(background=true, notify_on_complete=true) from Telegram/Discord/etc.
+  # terminal(background=true, check_interval=...) from Telegram/Discord/etc.
   #   off:     No watcher messages at all
   #   result:  Only the final completion message
   #   error:   Only the final message when exit code != 0

cron/scheduler.py

@@ -44,7 +44,7 @@ logger = logging.getLogger(__name__)
 _KNOWN_DELIVERY_PLATFORMS = frozenset({
     "telegram", "discord", "slack", "whatsapp", "signal",
     "matrix", "mattermost", "homeassistant", "dingtalk", "feishu",
-    "wecom", "wecom_callback", "weixin", "sms", "email", "webhook", "bluebubbles",
+    "wecom", "weixin", "sms", "email", "webhook", "bluebubbles",
 })
 
 from cron.jobs import get_due_jobs, mark_job_run, save_job_output, advance_next_run
@@ -219,21 +219,6 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
     chat_id = target["chat_id"]
     thread_id = target.get("thread_id")
 
-    # Diagnostic: log thread_id for topic-aware delivery debugging
-    origin = job.get("origin") or {}
-    origin_thread = origin.get("thread_id")
-    if origin_thread and not thread_id:
-        logger.warning(
-            "Job '%s': origin has thread_id=%s but delivery target lost it "
-            "(deliver=%s, target=%s)",
-            job["id"], origin_thread, job.get("deliver", "local"), target,
-        )
-    elif thread_id:
-        logger.debug(
-            "Job '%s': delivering to %s:%s thread_id=%s",
-            job["id"], platform_name, chat_id, thread_id,
-        )
-
     from tools.send_message_tool import _send_to_platform
     from gateway.config import load_gateway_config, Platform
 
@@ -249,7 +234,6 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
         "dingtalk": Platform.DINGTALK,
         "feishu": Platform.FEISHU,
         "wecom": Platform.WECOM,
-        "wecom_callback": Platform.WECOM_CALLBACK,
         "weixin": Platform.WEIXIN,
         "email": Platform.EMAIL,
         "sms": Platform.SMS,
@@ -458,14 +442,6 @@ def _run_job_script(script_path: str) -> tuple[bool, str]:
         stdout = (result.stdout or "").strip()
         stderr = (result.stderr or "").strip()
 
-        # Redact secrets from both stdout and stderr before any return path.
-        try:
-            from agent.redact import redact_sensitive_text
-            stdout = redact_sensitive_text(stdout)
-            stderr = redact_sensitive_text(stderr)
-        except Exception:
-            pass
-
         if result.returncode != 0:
             parts = [f"Script exited with code {result.returncode}"]
             if stderr:
@@ -474,6 +450,13 @@ def _run_job_script(script_path: str) -> tuple[bool, str]:
                 parts.append(f"stdout:\n{stdout}")
             return False, "\n".join(parts)
 
+        # Redact any secrets that may appear in script output before
+        # they are injected into the LLM prompt context.
+        try:
+            from agent.redact import redact_sensitive_text
+            stdout = redact_sensitive_text(stdout)
+        except Exception:
+            pass
         return True, stdout
 
     except subprocess.TimeoutExpired:
@@ -641,15 +624,6 @@ 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)
 
-        # Apply IPv4 preference if configured.
-        try:
-            from hermes_constants import apply_ipv4_preference
-            _net_cfg = _cfg.get("network", {})
-            if isinstance(_net_cfg, dict) and _net_cfg.get("force_ipv4"):
-                apply_ipv4_preference(force=True)
-        except Exception:
-            pass
-
         # Reasoning config from config.yaml
         from hermes_constants import parse_reasoning_effort
         effort = str(_cfg.get("agent", {}).get("reasoning_effort", "")).strip()
@@ -747,7 +721,6 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
             provider_sort=pr.get("sort"),
             disabled_toolsets=["cronjob", "messaging", "clarify"],
             quiet_mode=True,
-            skip_context_files=True,  # Don't inject SOUL.md/AGENTS.md from scheduler cwd
             skip_memory=True,  # Cron system prompts would corrupt user representations
             platform="cron",
             session_id=_cron_session_id,

docker/entrypoint.sh

@@ -5,33 +5,6 @@ set -e
 HERMES_HOME="/opt/data"
 INSTALL_DIR="/opt/hermes"
 
-# --- Privilege dropping via gosu ---
-# When started as root (the default), optionally remap the hermes user/group
-# to match host-side ownership, fix volume permissions, then re-exec as hermes.
-if [ "$(id -u)" = "0" ]; then
-    if [ -n "$HERMES_UID" ] && [ "$HERMES_UID" != "$(id -u hermes)" ]; then
-        echo "Changing hermes UID to $HERMES_UID"
-        usermod -u "$HERMES_UID" hermes
-    fi
-
-    if [ -n "$HERMES_GID" ] && [ "$HERMES_GID" != "$(id -g hermes)" ]; then
-        echo "Changing hermes GID to $HERMES_GID"
-        groupmod -g "$HERMES_GID" hermes
-    fi
-
-    actual_hermes_uid=$(id -u hermes)
-    if [ "$(stat -c %u "$HERMES_HOME" 2>/dev/null)" != "$actual_hermes_uid" ]; then
-        echo "$HERMES_HOME is not owned by $actual_hermes_uid, fixing"
-        chown -R hermes:hermes "$HERMES_HOME"
-    fi
-
-    echo "Dropping root privileges"
-    exec gosu hermes "$0" "$@"
-fi
-
-# --- Running as hermes from here ---
-source "${INSTALL_DIR}/.venv/bin/activate"
-
 # Create essential directory structure.  Cache and platform directories
 # (cache/images, cache/audio, platforms/whatsapp, etc.) are created on
 # demand by the application — don't pre-create them here so new installs

docs/migration/openclaw.md

@@ -11,14 +11,12 @@ When you run `hermes setup` for the first time and Hermes detects `~/.openclaw`,
 ### 2. CLI Command (quick, scriptable)
 
 ```bash
-hermes claw migrate                      # Preview then migrate (always shows preview first)
-hermes claw migrate --dry-run            # Preview only, no changes
+hermes claw migrate                      # Full migration with confirmation prompt
+hermes claw migrate --dry-run            # Preview what would happen
 hermes claw migrate --preset user-data   # Migrate without API keys/secrets
 hermes claw migrate --yes                # Skip confirmation prompt
 ```
 
-The migration always shows a full preview of what will be imported before making any changes. You review the preview and confirm before anything is written.
-
 **All options:**
 
 | Flag | Description |
@@ -41,7 +39,7 @@ Ask the agent to run the migration for you:
 ```
 
 The agent will use the `openclaw-migration` skill to:
-1. Run a preview first to show what would change
+1. Run a dry-run first to preview changes
 2. Ask about conflict resolution (SOUL.md, skills, etc.)
 3. Let you choose between `user-data` and `full` presets
 4. Execute the migration with your choices
@@ -60,31 +58,16 @@ The agent will use the `openclaw-migration` skill to:
 | Messaging settings | `~/.openclaw/config.yaml` (TELEGRAM_ALLOWED_USERS, MESSAGING_CWD) | `~/.hermes/.env` |
 | TTS assets | `~/.openclaw/workspace/tts/` | `~/.hermes/tts/` |
 
-Workspace files are also checked at `workspace.default/` and `workspace-main/` as fallback paths (OpenClaw renamed `workspace/` to `workspace-main/` in recent versions).
-
 ### `full` preset (adds to `user-data`)
 | Item | Source | Destination |
 |------|--------|-------------|
-| Telegram bot token | `openclaw.json` channels config | `~/.hermes/.env` |
-| OpenRouter API key | `.env`, `openclaw.json`, or `openclaw.json["env"]` | `~/.hermes/.env` |
-| OpenAI API key | `.env`, `openclaw.json`, or `openclaw.json["env"]` | `~/.hermes/.env` |
-| Anthropic API key | `.env`, `openclaw.json`, or `openclaw.json["env"]` | `~/.hermes/.env` |
-| ElevenLabs API key | `.env`, `openclaw.json`, or `openclaw.json["env"]` | `~/.hermes/.env` |
+| Telegram bot token | `~/.openclaw/config.yaml` | `~/.hermes/.env` |
+| OpenRouter API key | `~/.openclaw/.env` or config | `~/.hermes/.env` |
+| OpenAI API key | `~/.openclaw/.env` or config | `~/.hermes/.env` |
+| Anthropic API key | `~/.openclaw/.env` or config | `~/.hermes/.env` |
+| ElevenLabs API key | `~/.openclaw/.env` or config | `~/.hermes/.env` |
 
-API keys are searched across four sources: inline config values, `~/.openclaw/.env`, the `openclaw.json` `"env"` sub-object, and per-agent auth profiles.
-
-Only allowlisted secrets are ever imported. Other credentials are skipped and reported.
-
-## OpenClaw Schema Compatibility
-
-The migration handles both old and current OpenClaw config layouts:
-
-- **Channel tokens**: Reads from flat paths (`channels.telegram.botToken`) and the newer `accounts.default` layout (`channels.telegram.accounts.default.botToken`)
-- **TTS provider**: OpenClaw renamed "edge" to "microsoft" — both are recognized and mapped to Hermes' "edge"
-- **Provider API types**: Both short (`openai`, `anthropic`) and hyphenated (`openai-completions`, `anthropic-messages`, `google-generative-ai`) values are mapped correctly
-- **thinkingDefault**: All enum values are handled including newer ones (`minimal`, `xhigh`, `adaptive`)
-- **Matrix**: Uses `accessToken` field (not `botToken`)
-- **SecretRef formats**: Plain strings, env templates (`${VAR}`), and `source: "env"` SecretRefs are resolved. `source: "file"` and `source: "exec"` SecretRefs produce a warning — add those keys manually after migration.
+Only these 6 allowlisted secrets are ever imported. Other credentials are skipped and reported.
 
 ## Conflict Handling
 
@@ -101,24 +84,18 @@ For skills, you can also use `--skill-conflict rename` to import conflicting ski
 
 ## Migration Report
 
-Every migration produces a report showing:
+Every migration (including dry runs) produces a report showing:
 - **Migrated items** — what was successfully imported
 - **Conflicts** — items skipped because they already exist
 - **Skipped items** — items not found in the source
 - **Errors** — items that failed to import
 
-For executed migrations, the full report is saved to `~/.hermes/migration/openclaw/<timestamp>/`.
-
-## Post-Migration Notes
-
-- **Skills require a new session** — imported skills take effect after restarting your agent or starting a new chat.
-- **WhatsApp requires re-pairing** — WhatsApp uses QR-code pairing, not token-based auth. Run `hermes whatsapp` to pair.
-- **Archive cleanup** — after migration, you'll be offered to rename `~/.openclaw/` to `.openclaw.pre-migration/` to prevent state confusion. You can also run `hermes claw cleanup` later.
+For execute runs, the full report is saved to `~/.hermes/migration/openclaw/<timestamp>/`.
 
 ## Troubleshooting
 
 ### "OpenClaw directory not found"
-The migration looks for `~/.openclaw` by default, then tries `~/.clawdbot` and `~/.moltbot`. If your OpenClaw is installed elsewhere, use `--source`:
+The migration looks for `~/.openclaw` by default. If your OpenClaw is installed elsewhere, use `--source`:
 ```bash
 hermes claw migrate --source /path/to/.openclaw
 ```
@@ -131,12 +108,3 @@ hermes skills install openclaw-migration
 
 ### Memory overflow
 If your OpenClaw MEMORY.md or USER.md exceeds Hermes' character limits, excess entries are exported to an overflow file in the migration report directory. You can manually review and add the most important ones.
-
-### API keys not found
-Keys might be stored in different places depending on your OpenClaw setup:
-- `~/.openclaw/.env` file
-- Inline in `openclaw.json` under `models.providers.*.apiKey`
-- In `openclaw.json` under the `"env"` or `"env.vars"` sub-objects
-- In `~/.openclaw/agents/main/agent/auth-profiles.json`
-
-The migration checks all four. If keys use `source: "file"` or `source: "exec"` SecretRefs, they can't be resolved automatically — add them via `hermes config set`.

docs/specs/container-cli-review-fixes.md

@@ -1,329 +0,0 @@
-# Container-Aware CLI Review Fixes Spec
-
-**PR:** NousResearch/hermes-agent#7543
-**Review:** cursor[bot] bugbot review (4094049442) + two prior rounds
-**Date:** 2026-04-12
-**Branch:** `feat/container-aware-cli-clean`
-
-## Review Issues Summary
-
-Six issues were raised across three bugbot review rounds. Three were fixed in intermediate commits (38277a6a, 726cf90f). This spec addresses remaining design concerns surfaced by those reviews and simplifies the implementation based on interview decisions.
-
-| # | Issue | Severity | Status |
-|---|-------|----------|--------|
-| 1 | `os.execvp` retry loop unreachable | Medium | Fixed in 79e8cd12 (switched to subprocess.run) |
-| 2 | Redundant `shutil.which("sudo")` | Medium | Fixed in 38277a6a (reuses `sudo` var) |
-| 3 | Missing `chown -h` on symlink update | Low | Fixed in 38277a6a |
-| 4 | Container routing after `parse_args()` | High | Fixed in 726cf90f |
-| 5 | Hardcoded `/home/${user}` | Medium | Fixed in 726cf90f |
-| 6 | Group membership not gated on `container.enable` | Low | Fixed in 726cf90f |
-
-The mechanical fixes are in place but the overall design needs revision. The retry loop, error swallowing, and process model have deeper issues than what the bugbot flagged.
-
----
-
-## Spec: Revised `_exec_in_container`
-
-### Design Principles
-
-1. **Let it crash.** No silent fallbacks. If `.container-mode` exists but something goes wrong, the error propagates naturally (Python traceback). The only case where container routing is skipped is when `.container-mode` doesn't exist or `HERMES_DEV=1`.
-2. **No retries.** Probe once for sudo, exec once. If it fails, docker/podman's stderr reaches the user verbatim.
-3. **Completely transparent.** No error wrapping, no prefixes, no spinners. Docker's output goes straight through.
-4. **`os.execvp` on the happy path.** Replace the Python process entirely so there's no idle parent during interactive sessions. Note: `execvp` never returns on success (process is replaced) and raises `OSError` on failure (it does not return a value). The container process's exit code becomes the process exit code by definition — no explicit propagation needed.
-5. **One human-readable exception to "let it crash".** `subprocess.TimeoutExpired` from the sudo probe gets a specific catch with a readable message, since a raw traceback for "your Docker daemon is slow" is confusing. All other exceptions propagate naturally.
-
-### Execution Flow
-
-```
-1. get_container_exec_info()
-   - HERMES_DEV=1 → return None (skip routing)
-   - Inside container → return None (skip routing)
-   - .container-mode doesn't exist → return None (skip routing)
-   - .container-mode exists → parse and return dict
-   - .container-mode exists but malformed/unreadable → LET IT CRASH (no try/except)
-
-2. _exec_in_container(container_info, sys.argv[1:])
-   a. shutil.which(backend) → if None, print "{backend} not found on PATH" and sys.exit(1)
-   b. Sudo probe: subprocess.run([runtime, "inspect", "--format", "ok", container_name], timeout=15)
-      - If succeeds → needs_sudo = False
-      - If fails → try subprocess.run([sudo, "-n", runtime, "inspect", ...], timeout=15)
-        - If succeeds → needs_sudo = True
-        - If fails → print error with sudoers hint (including why -n is required) and sys.exit(1)
-      - If TimeoutExpired → catch specifically, print human-readable message about slow daemon
-   c. Build exec_cmd: [sudo? + runtime, "exec", tty_flags, "-u", exec_user, env_flags, container, hermes_bin, *cli_args]
-   d. os.execvp(exec_cmd[0], exec_cmd)
-      - On success: process is replaced — Python is gone, container exit code IS the process exit code
-      - On OSError: let it crash (natural traceback)
-```
-
-### Changes to `hermes_cli/main.py`
-
-#### `_exec_in_container` — rewrite
-
-Remove:
-- The entire retry loop (`max_retries`, `for attempt in range(...)`)
-- Spinner logic (`"Waiting for container..."`, dots)
-- Exit code classification (125/126/127 handling)
-- `subprocess.run` for the exec call (keep it only for the sudo probe)
-- Special TTY vs non-TTY retry counts
-- The `time` import (no longer needed)
-
-Change:
-- Use `os.execvp(exec_cmd[0], exec_cmd)` as the final call
-- Keep the `subprocess` import only for the sudo probe
-- Keep TTY detection for the `-it` vs `-i` flag
-- Keep env var forwarding (TERM, COLORTERM, LANG, LC_ALL)
-- Keep the sudo probe as-is (it's the one "smart" part)
-- Bump probe `timeout` from 5s to 15s — cold podman on a loaded machine needs headroom
-- Catch `subprocess.TimeoutExpired` specifically on both probe calls — print a readable message about the daemon being unresponsive instead of a raw traceback
-- Expand the sudoers hint error message to explain *why* `-n` (non-interactive) is required: a password prompt would hang the CLI or break piped commands
-
-The function becomes roughly:
-
-```python
-def _exec_in_container(container_info: dict, cli_args: list):
-    """Replace the current process with a command inside the managed container.
-
-    Probes whether sudo is needed (rootful containers), then os.execvp
-    into the container. If exec fails, the OS error propagates naturally.
-    """
-    import shutil
-    import subprocess
-
-    backend = container_info["backend"]
-    container_name = container_info["container_name"]
-    exec_user = container_info["exec_user"]
-    hermes_bin = container_info["hermes_bin"]
-
-    runtime = shutil.which(backend)
-    if not runtime:
-        print(f"Error: {backend} not found on PATH. Cannot route to container.",
-              file=sys.stderr)
-        sys.exit(1)
-
-    # Probe whether we need sudo to see the rootful container.
-    # Timeout is 15s — cold podman on a loaded machine can take a while.
-    # TimeoutExpired is caught specifically for a human-readable message;
-    # all other exceptions propagate naturally.
-    needs_sudo = False
-    sudo = None
-    try:
-        probe = subprocess.run(
-            [runtime, "inspect", "--format", "ok", container_name],
-            capture_output=True, text=True, timeout=15,
-        )
-    except subprocess.TimeoutExpired:
-        print(
-            f"Error: timed out waiting for {backend} to respond.\n"
-            f"The {backend} daemon may be unresponsive or starting up.",
-            file=sys.stderr,
-        )
-        sys.exit(1)
-
-    if probe.returncode != 0:
-        sudo = shutil.which("sudo")
-        if sudo:
-            try:
-                probe2 = subprocess.run(
-                    [sudo, "-n", runtime, "inspect", "--format", "ok", container_name],
-                    capture_output=True, text=True, timeout=15,
-                )
-            except subprocess.TimeoutExpired:
-                print(
-                    f"Error: timed out waiting for sudo {backend} to respond.",
-                    file=sys.stderr,
-                )
-                sys.exit(1)
-
-            if probe2.returncode == 0:
-                needs_sudo = True
-            else:
-                print(
-                    f"Error: container '{container_name}' not found via {backend}.\n"
-                    f"\n"
-                    f"The NixOS service runs the container as root. Your user cannot\n"
-                    f"see it because {backend} uses per-user namespaces.\n"
-                    f"\n"
-                    f"Fix: grant passwordless sudo for {backend}. The -n (non-interactive)\n"
-                    f"flag is required because the CLI calls sudo non-interactively —\n"
-                    f"a password prompt would hang or break piped commands:\n"
-                    f"\n"
-                    f'  security.sudo.extraRules = [{{\n'
-                    f'    users = [ "{os.getenv("USER", "your-user")}" ];\n'
-                    f'    commands = [{{ command = "{runtime}"; options = [ "NOPASSWD" ]; }}];\n'
-                    f'  }}];\n'
-                    f"\n"
-                    f"Or run: sudo hermes {' '.join(cli_args)}",
-                    file=sys.stderr,
-                )
-                sys.exit(1)
-        else:
-            print(
-                f"Error: container '{container_name}' not found via {backend}.\n"
-                f"The container may be running under root. Try: sudo hermes {' '.join(cli_args)}",
-                file=sys.stderr,
-            )
-            sys.exit(1)
-
-    is_tty = sys.stdin.isatty()
-    tty_flags = ["-it"] if is_tty else ["-i"]
-
-    env_flags = []
-    for var in ("TERM", "COLORTERM", "LANG", "LC_ALL"):
-        val = os.environ.get(var)
-        if val:
-            env_flags.extend(["-e", f"{var}={val}"])
-
-    cmd_prefix = [sudo, "-n", runtime] if needs_sudo else [runtime]
-    exec_cmd = (
-        cmd_prefix + ["exec"]
-        + tty_flags
-        + ["-u", exec_user]
-        + env_flags
-        + [container_name, hermes_bin]
-        + cli_args
-    )
-
-    # execvp replaces this process entirely — it never returns on success.
-    # On failure it raises OSError, which propagates naturally.
-    os.execvp(exec_cmd[0], exec_cmd)
-```
-
-#### Container routing call site in `main()` — remove try/except
-
-Current:
-```python
-try:
-    from hermes_cli.config import get_container_exec_info
-    container_info = get_container_exec_info()
-    if container_info:
-        _exec_in_container(container_info, sys.argv[1:])
-        sys.exit(1)  # exec failed if we reach here
-except SystemExit:
-    raise
-except Exception:
-    pass  # Container routing unavailable, proceed locally
-```
-
-Revised:
-```python
-from hermes_cli.config import get_container_exec_info
-container_info = get_container_exec_info()
-if container_info:
-    _exec_in_container(container_info, sys.argv[1:])
-    # Unreachable: os.execvp never returns on success (process is replaced)
-    # and raises OSError on failure (which propagates as a traceback).
-    # This line exists only as a defensive assertion.
-    sys.exit(1)
-```
-
-No try/except. If `.container-mode` doesn't exist, `get_container_exec_info()` returns `None` and we skip routing. If it exists but is broken, the exception propagates with a natural traceback.
-
-Note: `sys.exit(1)` after `_exec_in_container` is dead code in all paths — `os.execvp` either replaces the process or raises. It's kept as a belt-and-suspenders assertion with a comment marking it unreachable, not as actual error handling.
-
-### Changes to `hermes_cli/config.py`
-
-#### `get_container_exec_info` — remove inner try/except
-
-Current code catches `(OSError, IOError)` and returns `None`. This silently hides permission errors, corrupt files, etc.
-
-Change: Remove the try/except around file reading. Keep the early returns for `HERMES_DEV=1` and `_is_inside_container()`. The `FileNotFoundError` from `open()` when `.container-mode` doesn't exist should still return `None` (this is the "container mode not enabled" case). All other exceptions propagate.
-
-```python
-def get_container_exec_info() -> Optional[dict]:
-    if os.environ.get("HERMES_DEV") == "1":
-        return None
-    if _is_inside_container():
-        return None
-
-    container_mode_file = get_hermes_home() / ".container-mode"
-
-    try:
-        with open(container_mode_file, "r") as f:
-            # ... parse key=value lines ...
-    except FileNotFoundError:
-        return None
-    # All other exceptions (PermissionError, malformed data, etc.) propagate
-
-    return { ... }
-```
-
----
-
-## Spec: NixOS Module Changes
-
-### Symlink creation — simplify to two branches
-
-Current: 4 branches (symlink exists, directory exists, other file, doesn't exist).
-
-Revised: 2 branches.
-
-```bash
-if [ -d "${symlinkPath}" ] && [ ! -L "${symlinkPath}" ]; then
-  # Real directory — back it up, then create symlink
-  _backup="${symlinkPath}.bak.$(date +%s)"
-  echo "hermes-agent: backing up existing ${symlinkPath} to $_backup"
-  mv "${symlinkPath}" "$_backup"
-fi
-# For everything else (symlink, doesn't exist, etc.) — just force-create
-ln -sfn "${target}" "${symlinkPath}"
-chown -h ${user}:${cfg.group} "${symlinkPath}"
-```
-
-`ln -sfn` handles: existing symlink (replaces), doesn't exist (creates), and after the `mv` above (creates). The only case that needs special handling is a real directory, because `ln -sfn` cannot atomically replace a directory.
-
-Note: there is a theoretical race between the `[ -d ... ]` check and the `mv` (something could create/remove the directory in between). In practice this is a NixOS activation script running as root during `nixos-rebuild switch` — no other process should be touching `~/.hermes` at that moment. Not worth adding locking for.
-
-### Sudoers — document, don't auto-configure
-
-Do NOT add `security.sudo.extraRules` to the module. Document the sudoers requirement in the module's description/comments and in the error message the CLI prints when sudo probe fails.
-
-### Group membership gating — keep as-is
-
-The fix in 726cf90f (`cfg.container.enable && cfg.container.hostUsers != []`) is correct. Leftover group membership when container mode is disabled is harmless. No cleanup needed.
-
----
-
-## Spec: Test Rewrite
-
-The existing test file (`tests/hermes_cli/test_container_aware_cli.py`) has 16 tests. With the simplified exec model, several are obsolete.
-
-### Tests to keep (update as needed)
-
-- `test_is_inside_container_dockerenv` — unchanged
-- `test_is_inside_container_containerenv` — unchanged
-- `test_is_inside_container_cgroup_docker` — unchanged
-- `test_is_inside_container_false_on_host` — unchanged
-- `test_get_container_exec_info_returns_metadata` — unchanged
-- `test_get_container_exec_info_none_inside_container` — unchanged
-- `test_get_container_exec_info_none_without_file` — unchanged
-- `test_get_container_exec_info_skipped_when_hermes_dev` — unchanged
-- `test_get_container_exec_info_not_skipped_when_hermes_dev_zero` — unchanged
-- `test_get_container_exec_info_defaults` — unchanged
-- `test_get_container_exec_info_docker_backend` — unchanged
-
-### Tests to add
-
-- `test_get_container_exec_info_crashes_on_permission_error` — verify that `PermissionError` propagates (no silent `None` return)
-- `test_exec_in_container_calls_execvp` — verify `os.execvp` is called with correct args (runtime, tty flags, user, env, container, binary, cli args)
-- `test_exec_in_container_sudo_probe_sets_prefix` — verify that when first probe fails and sudo probe succeeds, `os.execvp` is called with `sudo -n` prefix
-- `test_exec_in_container_no_runtime_hard_fails` — keep existing, verify `sys.exit(1)` when `shutil.which` returns None
-- `test_exec_in_container_non_tty_uses_i_only` — update to check `os.execvp` args instead of `subprocess.run` args
-- `test_exec_in_container_probe_timeout_prints_message` — verify that `subprocess.TimeoutExpired` from the probe produces a human-readable error and `sys.exit(1)`, not a raw traceback
-- `test_exec_in_container_container_not_running_no_sudo` — verify the path where runtime exists (`shutil.which` returns a path) but probe returns non-zero and no sudo is available. Should print the "container may be running under root" error. This is distinct from `no_runtime_hard_fails` which covers `shutil.which` returning None.
-
-### Tests to delete
-
-- `test_exec_in_container_tty_retries_on_container_failure` — retry loop removed
-- `test_exec_in_container_non_tty_retries_silently_exits_126` — retry loop removed
-- `test_exec_in_container_propagates_hermes_exit_code` — no subprocess.run to check exit codes; execvp replaces the process. Note: exit code propagation still works correctly — when `os.execvp` succeeds, the container's process *becomes* this process, so its exit code is the process exit code by OS semantics. No application code needed, no test needed. A comment in the function docstring documents this intent for future readers.
-
----
-
-## Out of Scope
-
-- Auto-configuring sudoers rules in the NixOS module
-- Any changes to `get_container_exec_info` parsing logic beyond the try/except narrowing
-- Changes to `.container-mode` file format
-- Changes to the `HERMES_DEV=1` bypass
-- Changes to container detection logic (`_is_inside_container`)

environments/tool_call_parsers/hermes_parser.py

@@ -49,8 +49,6 @@ class HermesToolCallParser(ToolCallParser):
                     continue
 
                 tc_data = json.loads(raw_json)
-                if "name" not in tc_data:
-                    continue
                 tool_calls.append(
                     ChatCompletionMessageToolCall(
                         id=f"call_{uuid.uuid4().hex[:8]}",

environments/tool_call_parsers/mistral_parser.py

@@ -89,8 +89,6 @@ class MistralToolCallParser(ToolCallParser):
                         parsed = [parsed]
 
                     for tc in parsed:
-                        if "name" not in tc:
-                            continue
                         args = tc.get("arguments", {})
                         if isinstance(args, dict):
                             args = json.dumps(args, ensure_ascii=False)

gateway/builtin_hooks/boot_md.py

@@ -18,7 +18,9 @@ suppress delivery.
 """
 
 import logging
+import os
 import threading
+from pathlib import Path
 
 logger = logging.getLogger("hooks.boot-md")
 

gateway/config.py

@@ -63,7 +63,6 @@ class Platform(Enum):
     WEBHOOK = "webhook"
     FEISHU = "feishu"
     WECOM = "wecom"
-    WECOM_CALLBACK = "wecom_callback"
     WEIXIN = "weixin"
     BLUEBUBBLES = "bluebubbles"
 
@@ -191,7 +190,7 @@ class StreamingConfig:
     """Configuration for real-time token streaming to messaging platforms."""
     enabled: bool = False
     transport: str = "edit"       # "edit" (progressive editMessageText) or "off"
-    edit_interval: float = 1.0    # Seconds between message edits (Telegram rate-limits at ~1/s)
+    edit_interval: float = 0.3    # Seconds between message edits
     buffer_threshold: int = 40    # Chars before forcing an edit
     cursor: str = " ▉"           # Cursor shown during streaming
 
@@ -211,7 +210,7 @@ class StreamingConfig:
         return cls(
             enabled=data.get("enabled", False),
             transport=data.get("transport", "edit"),
-            edit_interval=float(data.get("edit_interval", 1.0)),
+            edit_interval=float(data.get("edit_interval", 0.3)),
             buffer_threshold=int(data.get("buffer_threshold", 40)),
             cursor=data.get("cursor", " ▉"),
         )
@@ -292,14 +291,9 @@ class GatewayConfig:
             # Feishu uses extra dict for app credentials
             elif platform == Platform.FEISHU and config.extra.get("app_id"):
                 connected.append(platform)
-            # WeCom bot mode uses extra dict for bot credentials
+            # WeCom uses extra dict for bot credentials
             elif platform == Platform.WECOM and config.extra.get("bot_id"):
                 connected.append(platform)
-            # WeCom callback mode uses corp_id or apps list
-            elif platform == Platform.WECOM_CALLBACK and (
-                config.extra.get("corp_id") or config.extra.get("apps")
-            ):
-                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)
@@ -665,17 +659,6 @@ def load_gateway_config() -> GatewayConfig:
     _apply_env_overrides(config)
     
     # --- Validate loaded values ---
-    _validate_gateway_config(config)
-
-    return config
-
-
-def _validate_gateway_config(config: "GatewayConfig") -> None:
-    """Validate and sanitize a loaded GatewayConfig in place.
-
-    Called by ``load_gateway_config()`` after all config sources are merged.
-    Extracted as a separate function for testability.
-    """
     policy = config.default_reset_policy
 
     if not (0 <= policy.at_hour <= 23):
@@ -712,31 +695,7 @@ def _validate_gateway_config(config: "GatewayConfig") -> None:
                 platform.value, env_name,
             )
 
-    # Reject known-weak placeholder tokens.
-    # Ported from openclaw/openclaw#64586: users who copy .env.example
-    # without changing placeholder values get a clear startup error instead
-    # of a confusing "auth failed" from the platform API.
-    try:
-        from hermes_cli.auth import has_usable_secret
-    except ImportError:
-        has_usable_secret = None  # type: ignore[assignment]
-
-    if has_usable_secret is not None:
-        for platform, pconfig in config.platforms.items():
-            if not pconfig.enabled:
-                continue
-            env_name = _token_env_names.get(platform)
-            if not env_name:
-                continue
-            token = pconfig.token
-            if token and token.strip() and not has_usable_secret(token, min_length=4):
-                logger.error(
-                    "%s is enabled but %s is set to a placeholder value ('%s'). "
-                    "Set a real bot token before starting the gateway. "
-                    "The adapter will NOT be started.",
-                    platform.value, env_name, token.strip()[:6] + "...",
-                )
-                pconfig.enabled = False
+    return config
 
 
 def _apply_env_overrides(config: GatewayConfig) -> None:
@@ -1028,23 +987,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
                 name=os.getenv("WECOM_HOME_CHANNEL_NAME", "Home"),
             )
 
-    # WeCom callback mode (self-built apps)
-    wecom_callback_corp_id = os.getenv("WECOM_CALLBACK_CORP_ID")
-    wecom_callback_corp_secret = os.getenv("WECOM_CALLBACK_CORP_SECRET")
-    if wecom_callback_corp_id and wecom_callback_corp_secret:
-        if Platform.WECOM_CALLBACK not in config.platforms:
-            config.platforms[Platform.WECOM_CALLBACK] = PlatformConfig()
-        config.platforms[Platform.WECOM_CALLBACK].enabled = True
-        config.platforms[Platform.WECOM_CALLBACK].extra.update({
-            "corp_id": wecom_callback_corp_id,
-            "corp_secret": wecom_callback_corp_secret,
-            "agent_id": os.getenv("WECOM_CALLBACK_AGENT_ID", ""),
-            "token": os.getenv("WECOM_CALLBACK_TOKEN", ""),
-            "encoding_aes_key": os.getenv("WECOM_CALLBACK_ENCODING_AES_KEY", ""),
-            "host": os.getenv("WECOM_CALLBACK_HOST", "0.0.0.0"),
-            "port": int(os.getenv("WECOM_CALLBACK_PORT", "8645")),
-        })
-
     # Weixin (personal WeChat via iLink Bot API)
     weixin_token = os.getenv("WEIXIN_TOKEN")
     weixin_account_id = os.getenv("WEIXIN_ACCOUNT_ID")
@@ -1075,9 +1017,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
         weixin_group_allowed_users = os.getenv("WEIXIN_GROUP_ALLOWED_USERS", "").strip()
         if weixin_group_allowed_users:
             extra["group_allow_from"] = weixin_group_allowed_users
-        weixin_split_multiline = os.getenv("WEIXIN_SPLIT_MULTILINE_MESSAGES", "").strip()
-        if weixin_split_multiline:
-            extra["split_multiline_messages"] = weixin_split_multiline
         weixin_home = os.getenv("WEIXIN_HOME_CHANNEL", "").strip()
         if weixin_home:
             config.platforms[Platform.WEIXIN].home_channel = HomeChannel(

gateway/delivery.py

@@ -12,7 +12,7 @@ import logging
 from pathlib import Path
 from datetime import datetime
 from dataclasses import dataclass
-from typing import Dict, List, Optional, Any
+from typing import Dict, List, Optional, Any, Union
 
 from hermes_cli.config import get_hermes_home
 

gateway/display_config.py

@@ -1,187 +0,0 @@
-"""Per-platform display/verbosity configuration resolver.
-
-Provides ``resolve_display_setting()`` — the single entry-point for reading
-display settings with platform-specific overrides and sensible defaults.
-
-Resolution order (first non-None wins):
-    1. ``display.platforms.<platform>.<key>``  — explicit per-platform user override
-    2. ``display.<key>``                       — global user setting
-    3. ``_PLATFORM_DEFAULTS[<platform>][<key>]``  — built-in sensible default
-    4. ``_GLOBAL_DEFAULTS[<key>]``              — built-in global default
-
-Backward compatibility: ``display.tool_progress_overrides`` is still read as a
-fallback for ``tool_progress`` when no ``display.platforms`` entry exists.  A
-config migration (version bump) automatically moves the old format into the new
-``display.platforms`` structure.
-"""
-
-from __future__ import annotations
-
-from typing import Any
-
-# ---------------------------------------------------------------------------
-# Overrideable display settings and their global defaults
-# ---------------------------------------------------------------------------
-# These are the settings that can be configured per-platform.
-# Other display settings (compact, personality, skin, etc.) are CLI-only
-# and don't participate in per-platform resolution.
-
-_GLOBAL_DEFAULTS: dict[str, Any] = {
-    "tool_progress": "all",
-    "show_reasoning": False,
-    "tool_preview_length": 0,
-    "streaming": None,  # None = follow top-level streaming config
-}
-
-# ---------------------------------------------------------------------------
-# Sensible per-platform defaults — tiered by platform capability
-# ---------------------------------------------------------------------------
-# Tier 1 (high): Supports message editing, typically personal/team use
-# Tier 2 (medium): Supports editing but often workspace/customer-facing
-# Tier 3 (low): No edit support — each progress msg is permanent
-# Tier 4 (minimal): Batch/non-interactive delivery
-
-_TIER_HIGH = {
-    "tool_progress": "all",
-    "show_reasoning": False,
-    "tool_preview_length": 40,
-    "streaming": None,  # follow global
-}
-
-_TIER_MEDIUM = {
-    "tool_progress": "new",
-    "show_reasoning": False,
-    "tool_preview_length": 40,
-    "streaming": None,
-}
-
-_TIER_LOW = {
-    "tool_progress": "off",
-    "show_reasoning": False,
-    "tool_preview_length": 40,
-    "streaming": False,
-}
-
-_TIER_MINIMAL = {
-    "tool_progress": "off",
-    "show_reasoning": False,
-    "tool_preview_length": 0,
-    "streaming": False,
-}
-
-_PLATFORM_DEFAULTS: dict[str, dict[str, Any]] = {
-    # Tier 1 — full edit support, personal/team use
-    "telegram":    _TIER_HIGH,
-    "discord":     _TIER_HIGH,
-
-    # Tier 2 — edit support, often customer/workspace channels
-    "slack":           _TIER_MEDIUM,
-    "mattermost":      _TIER_MEDIUM,
-    "matrix":          _TIER_MEDIUM,
-    "feishu":          _TIER_MEDIUM,
-
-    # Tier 3 — no edit support, progress messages are permanent
-    "signal":          _TIER_LOW,
-    "whatsapp":        _TIER_MEDIUM,  # Baileys bridge supports /edit
-    "bluebubbles":     _TIER_LOW,
-    "weixin":          _TIER_LOW,
-    "wecom":           _TIER_LOW,
-    "wecom_callback":  _TIER_LOW,
-    "dingtalk":        _TIER_LOW,
-
-    # Tier 4 — batch or non-interactive delivery
-    "email":           _TIER_MINIMAL,
-    "sms":             _TIER_MINIMAL,
-    "webhook":         _TIER_MINIMAL,
-    "homeassistant":   _TIER_MINIMAL,
-    "api_server":      {**_TIER_HIGH, "tool_preview_length": 0},
-}
-
-# Canonical set of per-platform overrideable keys (for validation).
-OVERRIDEABLE_KEYS = frozenset(_GLOBAL_DEFAULTS.keys())
-
-
-def resolve_display_setting(
-    user_config: dict,
-    platform_key: str,
-    setting: str,
-    fallback: Any = None,
-) -> Any:
-    """Resolve a display setting with per-platform override support.
-
-    Parameters
-    ----------
-    user_config : dict
-        The full parsed config.yaml dict.
-    platform_key : str
-        Platform config key (e.g. ``"telegram"``, ``"slack"``).  Use
-        ``_platform_config_key(source.platform)`` from gateway/run.py.
-    setting : str
-        Display setting name (e.g. ``"tool_progress"``, ``"show_reasoning"``).
-    fallback : Any
-        Fallback value when the setting isn't found anywhere.
-
-    Returns
-    -------
-    The resolved value, or *fallback* if nothing is configured.
-    """
-    display_cfg = user_config.get("display") or {}
-
-    # 1. Explicit per-platform override (display.platforms.<platform>.<key>)
-    platforms = display_cfg.get("platforms") or {}
-    plat_overrides = platforms.get(platform_key)
-    if isinstance(plat_overrides, dict):
-        val = plat_overrides.get(setting)
-        if val is not None:
-            return _normalise(setting, val)
-
-    # 1b. Backward compat: display.tool_progress_overrides.<platform>
-    if setting == "tool_progress":
-        legacy = display_cfg.get("tool_progress_overrides")
-        if isinstance(legacy, dict):
-            val = legacy.get(platform_key)
-            if val is not None:
-                return _normalise(setting, val)
-
-    # 2. Global user setting (display.<key>)
-    val = display_cfg.get(setting)
-    if val is not None:
-        return _normalise(setting, val)
-
-    # 3. Built-in platform default
-    plat_defaults = _PLATFORM_DEFAULTS.get(platform_key)
-    if plat_defaults:
-        val = plat_defaults.get(setting)
-        if val is not None:
-            return val
-
-    # 4. Built-in global default
-    val = _GLOBAL_DEFAULTS.get(setting)
-    if val is not None:
-        return val
-
-    return fallback
-
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-def _normalise(setting: str, value: Any) -> Any:
-    """Normalise YAML quirks (bare ``off`` → False in YAML 1.1)."""
-    if setting == "tool_progress":
-        if value is False:
-            return "off"
-        if value is True:
-            return "all"
-        return str(value).lower()
-    if setting in ("show_reasoning", "streaming"):
-        if isinstance(value, str):
-            return value.lower() in ("true", "1", "yes", "on")
-        return bool(value)
-    if setting == "tool_preview_length":
-        try:
-            return int(value)
-        except (TypeError, ValueError):
-            return 0
-    return value

gateway/platforms/api_server.py

@@ -53,67 +53,6 @@ DEFAULT_HOST = "127.0.0.1"
 DEFAULT_PORT = 8642
 MAX_STORED_RESPONSES = 100
 MAX_REQUEST_BYTES = 1_000_000  # 1 MB default limit for POST bodies
-CHAT_COMPLETIONS_SSE_KEEPALIVE_SECONDS = 30.0
-MAX_NORMALIZED_TEXT_LENGTH = 65_536  # 64 KB cap for normalized content parts
-MAX_CONTENT_LIST_SIZE = 1_000  # Max items when content is an array
-
-
-def _normalize_chat_content(
-    content: Any, *, _max_depth: int = 10, _depth: int = 0,
-) -> str:
-    """Normalize OpenAI chat message content into a plain text string.
-
-    Some clients (Open WebUI, LobeChat, etc.) send content as an array of
-    typed parts instead of a plain string::
-
-        [{"type": "text", "text": "hello"}, {"type": "input_text", "text": "..."}]
-
-    This function flattens those into a single string so the agent pipeline
-    (which expects strings) doesn't choke.
-
-    Defensive limits prevent abuse: recursion depth, list size, and output
-    length are all bounded.
-    """
-    if _depth > _max_depth:
-        return ""
-    if content is None:
-        return ""
-    if isinstance(content, str):
-        return content[:MAX_NORMALIZED_TEXT_LENGTH] if len(content) > MAX_NORMALIZED_TEXT_LENGTH else content
-
-    if isinstance(content, list):
-        parts: List[str] = []
-        items = content[:MAX_CONTENT_LIST_SIZE] if len(content) > MAX_CONTENT_LIST_SIZE else content
-        for item in items:
-            if isinstance(item, str):
-                if item:
-                    parts.append(item[:MAX_NORMALIZED_TEXT_LENGTH])
-            elif isinstance(item, dict):
-                item_type = str(item.get("type") or "").strip().lower()
-                if item_type in {"text", "input_text", "output_text"}:
-                    text = item.get("text", "")
-                    if text:
-                        try:
-                            parts.append(str(text)[:MAX_NORMALIZED_TEXT_LENGTH])
-                        except Exception:
-                            pass
-                # Silently skip image_url / other non-text parts
-            elif isinstance(item, list):
-                nested = _normalize_chat_content(item, _max_depth=_max_depth, _depth=_depth + 1)
-                if nested:
-                    parts.append(nested)
-            # Check accumulated size
-            if sum(len(p) for p in parts) >= MAX_NORMALIZED_TEXT_LENGTH:
-                break
-        result = "\n".join(parts)
-        return result[:MAX_NORMALIZED_TEXT_LENGTH] if len(result) > MAX_NORMALIZED_TEXT_LENGTH else result
-
-    # Fallback for unexpected types (int, float, bool, etc.)
-    try:
-        result = str(content)
-        return result[:MAX_NORMALIZED_TEXT_LENGTH] if len(result) > MAX_NORMALIZED_TEXT_LENGTH else result
-    except Exception:
-        return ""
 
 
 def check_api_server_requirements() -> bool:
@@ -613,7 +552,7 @@ class APIServerAdapter(BasePlatformAdapter):
 
         for msg in messages:
             role = msg.get("role", "")
-            content = _normalize_chat_content(msg.get("content", ""))
+            content = msg.get("content", "")
             if role == "system":
                 # Accumulate system messages
                 if system_prompt is None:
@@ -705,35 +644,15 @@ class APIServerAdapter(BasePlatformAdapter):
                     _stream_q.put(delta)
 
             def _on_tool_progress(event_type, name, preview, args, **kwargs):
-                """Send tool progress as a separate SSE event.
-
-                Previously, progress markers like ``⏰ list`` were injected
-                directly into ``delta.content``.  OpenAI-compatible frontends
-                (Open WebUI, LobeChat, …) store ``delta.content`` verbatim as
-                the assistant message and send it back on subsequent requests.
-                After enough turns the model learns to *emit* the markers as
-                plain text instead of issuing real tool calls — silently
-                hallucinating tool results.  See #6972.
-
-                The fix: push a tagged tuple ``("__tool_progress__", payload)``
-                onto the stream queue.  The SSE writer emits it as a custom
-                ``event: hermes.tool.progress`` line that compliant frontends
-                can render for UX but will *not* persist into conversation
-                history.  Clients that don't understand the custom event type
-                silently ignore it per the SSE specification.
-                """
+                """Inject tool progress into the SSE stream for Open WebUI."""
                 if event_type != "tool.started":
-                    return
+                    return  # Only show tool start events in chat stream
                 if name.startswith("_"):
-                    return
+                    return  # Skip internal events (_thinking)
                 from agent.display import get_tool_emoji
                 emoji = get_tool_emoji(name)
                 label = preview or name
-                _stream_q.put(("__tool_progress__", {
-                    "tool": name,
-                    "emoji": emoji,
-                    "label": label,
-                }))
+                _stream_q.put(f"\n`{emoji} {label}`\n")
 
             # Start agent in background.  agent_ref is a mutable container
             # so the SSE writer can interrupt the agent on client disconnect.
@@ -823,11 +742,7 @@ class APIServerAdapter(BasePlatformAdapter):
         """
         import queue as _q
 
-        sse_headers = {
-            "Content-Type": "text/event-stream",
-            "Cache-Control": "no-cache",
-            "X-Accel-Buffering": "no",
-        }
+        sse_headers = {"Content-Type": "text/event-stream", "Cache-Control": "no-cache"}
         # CORS middleware can't inject headers into StreamResponse after
         # prepare() flushes them, so resolve CORS headers up front.
         origin = request.headers.get("Origin", "")
@@ -840,8 +755,6 @@ class APIServerAdapter(BasePlatformAdapter):
         await response.prepare(request)
 
         try:
-            last_activity = time.monotonic()
-
             # Role chunk
             role_chunk = {
                 "id": completion_id, "object": "chat.completion.chunk",
@@ -849,31 +762,6 @@ class APIServerAdapter(BasePlatformAdapter):
                 "choices": [{"index": 0, "delta": {"role": "assistant"}, "finish_reason": None}],
             }
             await response.write(f"data: {json.dumps(role_chunk)}\n\n".encode())
-            last_activity = time.monotonic()
-
-            # Helper — route a queue item to the correct SSE event.
-            async def _emit(item):
-                """Write a single queue item to the SSE stream.
-
-                Plain strings are sent as normal ``delta.content`` chunks.
-                Tagged tuples ``("__tool_progress__", payload)`` are sent
-                as a custom ``event: hermes.tool.progress`` SSE event so
-                frontends can display them without storing the markers in
-                conversation history.  See #6972.
-                """
-                if isinstance(item, tuple) and len(item) == 2 and item[0] == "__tool_progress__":
-                    event_data = json.dumps(item[1])
-                    await response.write(
-                        f"event: hermes.tool.progress\ndata: {event_data}\n\n".encode()
-                    )
-                else:
-                    content_chunk = {
-                        "id": completion_id, "object": "chat.completion.chunk",
-                        "created": created, "model": model,
-                        "choices": [{"index": 0, "delta": {"content": item}, "finish_reason": None}],
-                    }
-                    await response.write(f"data: {json.dumps(content_chunk)}\n\n".encode())
-                return time.monotonic()
 
             # Stream content chunks as they arrive from the agent
             loop = asyncio.get_event_loop()
@@ -888,19 +776,26 @@ class APIServerAdapter(BasePlatformAdapter):
                                 delta = stream_q.get_nowait()
                                 if delta is None:
                                     break
-                                last_activity = await _emit(delta)
+                                content_chunk = {
+                                    "id": completion_id, "object": "chat.completion.chunk",
+                                    "created": created, "model": model,
+                                    "choices": [{"index": 0, "delta": {"content": delta}, "finish_reason": None}],
+                                }
+                                await response.write(f"data: {json.dumps(content_chunk)}\n\n".encode())
                             except _q.Empty:
                                 break
                         break
-                    if time.monotonic() - last_activity >= CHAT_COMPLETIONS_SSE_KEEPALIVE_SECONDS:
-                        await response.write(b": keepalive\n\n")
-                        last_activity = time.monotonic()
                     continue
 
                 if delta is None:  # End of stream sentinel
                     break
 
-                last_activity = await _emit(delta)
+                content_chunk = {
+                    "id": completion_id, "object": "chat.completion.chunk",
+                    "created": created, "model": model,
+                    "choices": [{"index": 0, "delta": {"content": delta}, "finish_reason": None}],
+                }
+                await response.write(f"data: {json.dumps(content_chunk)}\n\n".encode())
 
             # Get usage from completed agent
             usage = {"input_tokens": 0, "output_tokens": 0, "total_tokens": 0}
@@ -986,7 +881,18 @@ class APIServerAdapter(BasePlatformAdapter):
                     input_messages.append({"role": "user", "content": item})
                 elif isinstance(item, dict):
                     role = item.get("role", "user")
-                    content = _normalize_chat_content(item.get("content", ""))
+                    content = item.get("content", "")
+                    # Handle content that may be a list of content parts
+                    if isinstance(content, list):
+                        text_parts = []
+                        for part in content:
+                            if isinstance(part, dict) and part.get("type") == "input_text":
+                                text_parts.append(part.get("text", ""))
+                            elif isinstance(part, dict) and part.get("type") == "output_text":
+                                text_parts.append(part.get("text", ""))
+                            elif isinstance(part, str):
+                                text_parts.append(part)
+                        content = "\n".join(text_parts)
                     input_messages.append({"role": role, "content": content})
         else:
             return web.json_response(_openai_error("'input' must be a string or array"), status=400)
@@ -1819,23 +1725,6 @@ class APIServerAdapter(BasePlatformAdapter):
                 )
                 return False
 
-            # Refuse to start network-accessible with a placeholder key.
-            # Ported from openclaw/openclaw#64586.
-            if is_network_accessible(self._host) and self._api_key:
-                try:
-                    from hermes_cli.auth import has_usable_secret
-                    if not has_usable_secret(self._api_key, min_length=8):
-                        logger.error(
-                            "[%s] Refusing to start: API_SERVER_KEY is set to a "
-                            "placeholder value. Generate a real secret "
-                            "(e.g. `openssl rand -hex 32`) and set API_SERVER_KEY "
-                            "before exposing the API server on %s.",
-                            self.name, self._host,
-                        )
-                        return False
-                except ImportError:
-                    pass
-
             # Port conflict detection — fail fast if port is already in use
             try:
                 with _socket.socket(_socket.AF_INET, _socket.SOCK_STREAM) as _s:

gateway/platforms/base.py

@@ -21,59 +21,6 @@ from urllib.parse import urlsplit
 logger = logging.getLogger(__name__)
 
 
-def utf16_len(s: str) -> int:
-    """Count UTF-16 code units in *s*.
-
-    Telegram's message-length limit (4 096) is measured in UTF-16 code units,
-    **not** Unicode code-points.  Characters outside the Basic Multilingual
-    Plane (emoji like 😀, CJK Extension B, musical symbols, …) are encoded as
-    surrogate pairs and therefore consume **two** UTF-16 code units each, even
-    though Python's ``len()`` counts them as one.
-
-    Ported from nearai/ironclaw#2304 which discovered the same discrepancy in
-    Rust's ``chars().count()``.
-    """
-    return len(s.encode("utf-16-le")) // 2
-
-
-def _prefix_within_utf16_limit(s: str, limit: int) -> str:
-    """Return the longest prefix of *s* whose UTF-16 length ≤ *limit*.
-
-    Unlike a plain ``s[:limit]``, this respects surrogate-pair boundaries so
-    we never slice a multi-code-unit character in half.
-    """
-    if utf16_len(s) <= limit:
-        return s
-    # Binary search for the longest safe prefix
-    lo, hi = 0, len(s)
-    while lo < hi:
-        mid = (lo + hi + 1) // 2
-        if utf16_len(s[:mid]) <= limit:
-            lo = mid
-        else:
-            hi = mid - 1
-    return s[:lo]
-
-
-def _custom_unit_to_cp(s: str, budget: int, len_fn) -> int:
-    """Return the largest codepoint offset *n* such that ``len_fn(s[:n]) <= budget``.
-
-    Used by :meth:`BasePlatformAdapter.truncate_message` when *len_fn* measures
-    length in units different from Python codepoints (e.g. UTF-16 code units).
-    Falls back to binary search which is O(log n) calls to *len_fn*.
-    """
-    if len_fn(s) <= budget:
-        return len(s)
-    lo, hi = 0, len(s)
-    while lo < hi:
-        mid = (lo + hi + 1) // 2
-        if len_fn(s[:mid]) <= budget:
-            lo = mid
-        else:
-            hi = mid - 1
-    return lo
-
-
 def is_network_accessible(host: str) -> bool:
     """Return True if *host* would expose the server beyond loopback.
 
@@ -726,32 +673,6 @@ class SendResult:
     retryable: bool = False  # True for transient connection errors — base will retry automatically
 
 
-def merge_pending_message_event(
-    pending_messages: Dict[str, MessageEvent],
-    session_key: str,
-    event: MessageEvent,
-) -> None:
-    """Store or merge a pending event for a session.
-
-    Photo bursts/albums often arrive as multiple near-simultaneous PHOTO
-    events. Merge those into the existing queued event so the next turn sees
-    the whole burst, while non-photo follow-ups still replace the pending
-    event normally.
-    """
-    existing = pending_messages.get(session_key)
-    if (
-        existing
-        and getattr(existing, "message_type", None) == MessageType.PHOTO
-        and event.message_type == MessageType.PHOTO
-    ):
-        existing.media_urls.extend(event.media_urls)
-        existing.media_types.extend(event.media_types)
-        if event.text:
-            existing.text = BasePlatformAdapter._merge_caption(existing.text, event.text)
-        return
-    pending_messages[session_key] = event
-
-
 # Error substrings that indicate a transient *connection* failure worth retrying.
 # "timeout" / "timed out" / "readtimeout" / "writetimeout" are intentionally
 # excluded: a read/write timeout on a non-idempotent call (e.g. send_message)
@@ -806,7 +727,6 @@ class BasePlatformAdapter(ABC):
         # working on a task after --replace or manual restarts.
         self._background_tasks: set[asyncio.Task] = set()
         self._expected_cancelled_tasks: set[asyncio.Task] = set()
-        self._busy_session_handler: Optional[Callable[[MessageEvent, str], Awaitable[bool]]] = None
         # Chats where auto-TTS on voice input is disabled (set by /voice off)
         self._auto_tts_disabled_chats: set = set()
         # Chats where typing indicator is paused (e.g. during approval waits).
@@ -876,36 +796,7 @@ class BasePlatformAdapter(ABC):
         result = handler(self)
         if asyncio.iscoroutine(result):
             await result
-
-    def _acquire_platform_lock(self, scope: str, identity: str, resource_desc: str) -> bool:
-        """Acquire a scoped lock for this adapter. Returns True on success."""
-        from gateway.status import acquire_scoped_lock
-        self._platform_lock_scope = scope
-        self._platform_lock_identity = identity
-        acquired, existing = acquire_scoped_lock(
-            scope, identity, metadata={'platform': self.platform.value}
-        )
-        if acquired:
-            return True
-        owner_pid = existing.get('pid') if isinstance(existing, dict) else None
-        message = (
-            f'{resource_desc} already in use'
-            + (f' (PID {owner_pid})' if owner_pid else '')
-            + '. Stop the other gateway first.'
-        )
-        logger.error('[%s] %s', self.name, message)
-        self._set_fatal_error(f'{scope}_lock', message, retryable=False)
-        return False
-
-    def _release_platform_lock(self) -> None:
-        """Release the scoped lock acquired by _acquire_platform_lock."""
-        identity = getattr(self, '_platform_lock_identity', None)
-        if not identity:
-            return
-        from gateway.status import release_scoped_lock
-        release_scoped_lock(self._platform_lock_scope, identity)
-        self._platform_lock_identity = None
-
+    
     @property
     def name(self) -> str:
         """Human-readable name for this adapter."""
@@ -924,10 +815,6 @@ class BasePlatformAdapter(ABC):
         an optional response string.
         """
         self._message_handler = handler
-
-    def set_busy_session_handler(self, handler: Optional[Callable[[MessageEvent, str], Awaitable[bool]]]) -> None:
-        """Set an optional handler for messages arriving during active sessions."""
-        self._busy_session_handler = handler
     
     def set_session_store(self, session_store: Any) -> None:
         """
@@ -1509,7 +1396,7 @@ class BasePlatformAdapter(ABC):
             # session lifecycle and its cleanup races with the running task
             # (see PR #4926).
             cmd = event.get_command()
-            if cmd in ("approve", "deny", "status", "stop", "new", "reset", "background", "restart"):
+            if cmd in ("approve", "deny", "status", "stop", "new", "reset", "background"):
                 logger.debug(
                     "[%s] Command '/%s' bypassing active-session guard for %s",
                     self.name, cmd, session_key,
@@ -1528,19 +1415,19 @@ class BasePlatformAdapter(ABC):
                     logger.error("[%s] Command '/%s' dispatch failed: %s", self.name, cmd, e, exc_info=True)
                 return
 
-            if self._busy_session_handler is not None:
-                try:
-                    if await self._busy_session_handler(event, session_key):
-                        return
-                except Exception as e:
-                    logger.error("[%s] Busy-session handler failed: %s", self.name, e, exc_info=True)
-
             # Special case: photo bursts/albums frequently arrive as multiple near-
             # simultaneous messages. Queue them without interrupting the active run,
             # then process them immediately after the current task finishes.
             if event.message_type == MessageType.PHOTO:
                 logger.debug("[%s] Queuing photo follow-up for session %s without interrupt", self.name, session_key)
-                merge_pending_message_event(self._pending_messages, session_key, event)
+                existing = self._pending_messages.get(session_key)
+                if existing and existing.message_type == MessageType.PHOTO:
+                    existing.media_urls.extend(event.media_urls)
+                    existing.media_types.extend(event.media_types)
+                    if event.text:
+                        existing.text = self._merge_caption(existing.text, event.text)
+                else:
+                    self._pending_messages[session_key] = event
                 return  # Don't interrupt now - will run after current task completes
 
             # Default behavior for non-photo follow-ups: interrupt the running agent
@@ -1939,11 +1826,7 @@ class BasePlatformAdapter(ABC):
         return content
     
     @staticmethod
-    def truncate_message(
-        content: str,
-        max_length: int = 4096,
-        len_fn: Optional["Callable[[str], int]"] = None,
-    ) -> List[str]:
+    def truncate_message(content: str, max_length: int = 4096) -> List[str]:
         """
         Split a long message into chunks, preserving code block boundaries.
 
@@ -1955,16 +1838,11 @@ class BasePlatformAdapter(ABC):
         Args:
             content: The full message content
             max_length: Maximum length per chunk (platform-specific)
-            len_fn: Optional length function for measuring string length.
-                     Defaults to ``len`` (Unicode code-points).  Pass
-                     ``utf16_len`` for platforms that measure message
-                     length in UTF-16 code units (e.g. Telegram).
 
         Returns:
             List of message chunks
         """
-        _len = len_fn or len
-        if _len(content) <= max_length:
+        if len(content) <= max_length:
             return [content]
 
         INDICATOR_RESERVE = 10   # room for " (XX/XX)"
@@ -1983,33 +1861,22 @@ class BasePlatformAdapter(ABC):
 
             # How much body text we can fit after accounting for the prefix,
             # a potential closing fence, and the chunk indicator.
-            headroom = max_length - INDICATOR_RESERVE - _len(prefix) - _len(FENCE_CLOSE)
+            headroom = max_length - INDICATOR_RESERVE - len(prefix) - len(FENCE_CLOSE)
             if headroom < 1:
                 headroom = max_length // 2
 
             # Everything remaining fits in one final chunk
-            if _len(prefix) + _len(remaining) <= max_length - INDICATOR_RESERVE:
+            if len(prefix) + len(remaining) <= max_length - INDICATOR_RESERVE:
                 chunks.append(prefix + remaining)
                 break
 
-            # Find a natural split point (prefer newlines, then spaces).
-            # When _len != len (e.g. utf16_len for Telegram), headroom is
-            # measured in the custom unit.  We need codepoint-based slice
-            # positions that stay within the custom-unit budget.
-            #
-            # _safe_slice_pos() maps a custom-unit budget to the largest
-            # codepoint offset whose custom length ≤ budget.
-            if _len is not len:
-                # Map headroom (custom units) → codepoint slice length
-                _cp_limit = _custom_unit_to_cp(remaining, headroom, _len)
-            else:
-                _cp_limit = headroom
-            region = remaining[:_cp_limit]
+            # Find a natural split point (prefer newlines, then spaces)
+            region = remaining[:headroom]
             split_at = region.rfind("\n")
-            if split_at < _cp_limit // 2:
+            if split_at < headroom // 2:
                 split_at = region.rfind(" ")
             if split_at < 1:
-                split_at = _cp_limit
+                split_at = headroom
 
             # Avoid splitting inside an inline code span (`...`).
             # If the text before split_at has an odd number of unescaped
@@ -2029,7 +1896,7 @@ class BasePlatformAdapter(ABC):
                     safe_split = candidate.rfind(" ", 0, last_bt)
                     nl_split = candidate.rfind("\n", 0, last_bt)
                     safe_split = max(safe_split, nl_split)
-                    if safe_split > _cp_limit // 4:
+                    if safe_split > headroom // 4:
                         split_at = safe_split
 
             chunk_body = remaining[:split_at]

gateway/platforms/bluebubbles.py

@@ -30,7 +30,6 @@ from gateway.platforms.base import (
     cache_audio_from_bytes,
     cache_document_from_bytes,
 )
-from gateway.platforms.helpers import strip_markdown
 
 logger = logging.getLogger(__name__)
 
@@ -90,7 +89,18 @@ def _normalize_server_url(raw: str) -> str:
     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()
 
 
 # ---------------------------------------------------------------------------
@@ -383,7 +393,7 @@ class BlueBubblesAdapter(BasePlatformAdapter):
         reply_to: Optional[str] = None,
         metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
-        text = strip_markdown(content or "")
+        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)
@@ -604,6 +614,35 @@ class BlueBubblesAdapter(BasePlatformAdapter):
     # 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
     # ------------------------------------------------------------------
@@ -640,7 +679,7 @@ class BlueBubblesAdapter(BasePlatformAdapter):
         return info
 
     def format_message(self, content: str) -> str:
-        return strip_markdown(content)
+        return _strip_markdown(content)
 
     # ------------------------------------------------------------------
     # Inbound attachment downloading (from #4588)

gateway/platforms/dingtalk.py

@@ -21,6 +21,7 @@ import asyncio
 import logging
 import os
 import re
+import time
 import uuid
 from datetime import datetime, timezone
 from typing import Any, Dict, Optional
@@ -41,7 +42,6 @@ except ImportError:
     httpx = None  # type: ignore[assignment]
 
 from gateway.config import Platform, PlatformConfig
-from gateway.platforms.helpers import MessageDeduplicator
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
@@ -52,6 +52,8 @@ from gateway.platforms.base import (
 logger = logging.getLogger(__name__)
 
 MAX_MESSAGE_LENGTH = 20000
+DEDUP_WINDOW_SECONDS = 300
+DEDUP_MAX_SIZE = 1000
 RECONNECT_BACKOFF = [2, 5, 10, 30, 60]
 _SESSION_WEBHOOKS_MAX = 500
 _DINGTALK_WEBHOOK_RE = re.compile(r'^https://api\.dingtalk\.com/')
@@ -87,8 +89,8 @@ class DingTalkAdapter(BasePlatformAdapter):
         self._stream_task: Optional[asyncio.Task] = None
         self._http_client: Optional["httpx.AsyncClient"] = None
 
-        # Message deduplication
-        self._dedup = MessageDeduplicator(max_size=1000)
+        # Message deduplication: msg_id -> timestamp
+        self._seen_messages: Dict[str, float] = {}
         # Map chat_id -> session_webhook for reply routing
         self._session_webhooks: Dict[str, str] = {}
 
@@ -168,7 +170,7 @@ class DingTalkAdapter(BasePlatformAdapter):
 
         self._stream_client = None
         self._session_webhooks.clear()
-        self._dedup.clear()
+        self._seen_messages.clear()
         logger.info("[%s] Disconnected", self.name)
 
     # -- Inbound message processing -----------------------------------------
@@ -176,7 +178,7 @@ class DingTalkAdapter(BasePlatformAdapter):
     async def _on_message(self, message: "ChatbotMessage") -> None:
         """Process an incoming DingTalk chatbot message."""
         msg_id = getattr(message, "message_id", None) or uuid.uuid4().hex
-        if self._dedup.is_duplicate(msg_id):
+        if self._is_duplicate(msg_id):
             logger.debug("[%s] Duplicate message %s, skipping", self.name, msg_id)
             return
 
@@ -254,6 +256,20 @@ class DingTalkAdapter(BasePlatformAdapter):
                 content = " ".join(parts).strip()
         return content
 
+    # -- Deduplication ------------------------------------------------------
+
+    def _is_duplicate(self, msg_id: str) -> bool:
+        """Check and record a message ID. Returns True if already seen."""
+        now = time.time()
+        if len(self._seen_messages) > DEDUP_MAX_SIZE:
+            cutoff = now - DEDUP_WINDOW_SECONDS
+            self._seen_messages = {k: v for k, v in self._seen_messages.items() if v > cutoff}
+
+        if msg_id in self._seen_messages:
+            return True
+        self._seen_messages[msg_id] = now
+        return False
+
     # -- Outbound messaging -------------------------------------------------
 
     async def send(

gateway/platforms/discord.py

@@ -10,6 +10,7 @@ Uses discord.py library for:
 """
 
 import asyncio
+import json
 import logging
 import os
 import struct
@@ -18,6 +19,7 @@ import tempfile
 import threading
 import time
 from collections import defaultdict
+from pathlib import Path
 from typing import Callable, Dict, Optional, Any
 
 logger = logging.getLogger(__name__)
@@ -43,7 +45,6 @@ sys.path.insert(0, str(_Path(__file__).resolve().parents[2]))
 from gateway.config import Platform, PlatformConfig
 import re
 
-from gateway.platforms.helpers import MessageDeduplicator, ThreadParticipationTracker
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
@@ -440,7 +441,6 @@ class DiscordAdapter(BasePlatformAdapter):
         self._pending_text_batches: Dict[str, MessageEvent] = {}
         self._pending_text_batch_tasks: Dict[str, asyncio.Task] = {}
         self._voice_text_channels: Dict[int, int] = {}  # guild_id -> text_channel_id
-        self._voice_sources: Dict[int, Dict[str, Any]] = {}  # guild_id -> linked text channel source metadata
         self._voice_timeout_tasks: Dict[int, asyncio.Task] = {}  # guild_id -> timeout task
         # Phase 2: voice listening
         self._voice_receivers: Dict[int, VoiceReceiver] = {}  # guild_id -> VoiceReceiver
@@ -450,15 +450,18 @@ class DiscordAdapter(BasePlatformAdapter):
         # Track threads where the bot has participated so follow-up messages
         # in those threads don't require @mention.  Persisted to disk so the
         # set survives gateway restarts.
-        self._threads = ThreadParticipationTracker("discord")
+        self._bot_participated_threads: set = self._load_participated_threads()
         # Persistent typing indicator loops per channel (DMs don't reliably
         # show the standard typing gateway event for bots)
         self._typing_tasks: Dict[str, asyncio.Task] = {}
         self._bot_task: Optional[asyncio.Task] = None
-        self._post_connect_task: Optional[asyncio.Task] = None
-        # Dedup cache: prevents duplicate bot responses when Discord
-        # RESUME replays events after reconnects.
-        self._dedup = MessageDeduplicator()
+        # Cap to prevent unbounded growth (Discord threads get archived).
+        self._MAX_TRACKED_THREADS = 500
+        # Dedup cache: message_id → timestamp.  Prevents duplicate bot
+        # responses when Discord RESUME replays events after reconnects.
+        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'
@@ -499,9 +502,18 @@ class DiscordAdapter(BasePlatformAdapter):
             return False
 
         try:
-            if not self._acquire_platform_lock('discord-bot-token', self.config.token, 'Discord bot token'):
+            # Acquire scoped lock to prevent duplicate bot token usage
+            from gateway.status import acquire_scoped_lock
+            self._token_lock_identity = self.config.token
+            acquired, existing = acquire_scoped_lock('discord-bot-token', self._token_lock_identity, metadata={'platform': 'discord'})
+            if not acquired:
+                owner_pid = existing.get('pid') if isinstance(existing, dict) else None
+                message = f'Discord bot token already in use' + (f' (PID {owner_pid})' if owner_pid else '') + '. Stop the other gateway first.'
+                logger.error('[%s] %s', self.name, message)
+                self._set_fatal_error('discord_token_lock', message, retryable=False)
                 return False
 
+
             # Parse allowed user entries (may contain usernames or IDs)
             allowed_env = os.getenv("DISCORD_ALLOWED_USERS", "")
             if allowed_env:
@@ -545,19 +557,29 @@ class DiscordAdapter(BasePlatformAdapter):
 
                 # Resolve any usernames in the allowed list to numeric IDs
                 await adapter_self._resolve_allowed_usernames()
-                adapter_self._ready_event.set()
 
-                if adapter_self._post_connect_task and not adapter_self._post_connect_task.done():
-                    adapter_self._post_connect_task.cancel()
-                adapter_self._post_connect_task = asyncio.create_task(
-                    adapter_self._run_post_connect_initialization()
-                )
+                # Sync slash commands with Discord
+                try:
+                    synced = await adapter_self._client.tree.sync()
+                    logger.info("[%s] Synced %d slash command(s)", adapter_self.name, len(synced))
+                except Exception as e:  # pragma: no cover - defensive logging
+                    logger.warning("[%s] Slash command sync failed: %s", adapter_self.name, e, exc_info=True)
+                adapter_self._ready_event.set()
 
             @self._client.event
             async def on_message(message: DiscordMessage):
                 # Dedup: Discord RESUME replays events after reconnects (#4777)
-                if adapter_self._dedup.is_duplicate(str(message.id)):
+                msg_id = str(message.id)
+                now = time.time()
+                if msg_id in adapter_self._seen_messages:
                     return
+                adapter_self._seen_messages[msg_id] = now
+                if len(adapter_self._seen_messages) > adapter_self._SEEN_MAX:
+                    cutoff = now - adapter_self._SEEN_TTL
+                    adapter_self._seen_messages = {
+                        k: v for k, v in adapter_self._seen_messages.items()
+                        if v > cutoff
+                    }
 
                 # Always ignore our own messages
                 if message.author == self._client.user:
@@ -663,11 +685,23 @@ class DiscordAdapter(BasePlatformAdapter):
 
         except asyncio.TimeoutError:
             logger.error("[%s] Timeout waiting for connection to Discord", self.name, exc_info=True)
-            self._release_platform_lock()
+            try:
+                from gateway.status import release_scoped_lock
+                if getattr(self, '_token_lock_identity', None):
+                    release_scoped_lock('discord-bot-token', self._token_lock_identity)
+                    self._token_lock_identity = None
+            except Exception:
+                pass
             return False
         except Exception as e:  # pragma: no cover - defensive logging
             logger.error("[%s] Failed to connect to Discord: %s", self.name, e, exc_info=True)
-            self._release_platform_lock()
+            try:
+                from gateway.status import release_scoped_lock
+                if getattr(self, '_token_lock_identity', None):
+                    release_scoped_lock('discord-bot-token', self._token_lock_identity)
+                    self._token_lock_identity = None
+            except Exception:
+                pass
             return False
 
     async def disconnect(self) -> None:
@@ -685,36 +719,21 @@ class DiscordAdapter(BasePlatformAdapter):
             except Exception as e:  # pragma: no cover - defensive logging
                 logger.warning("[%s] Error during disconnect: %s", self.name, e, exc_info=True)
 
-        if self._post_connect_task and not self._post_connect_task.done():
-            self._post_connect_task.cancel()
-            try:
-                await self._post_connect_task
-            except asyncio.CancelledError:
-                pass
-
         self._running = False
         self._client = None
         self._ready_event.clear()
-        self._post_connect_task = None
 
-        self._release_platform_lock()
+        # Release the token lock
+        try:
+            from gateway.status import release_scoped_lock
+            if getattr(self, '_token_lock_identity', None):
+                release_scoped_lock('discord-bot-token', self._token_lock_identity)
+                self._token_lock_identity = None
+        except Exception:
+            pass
 
         logger.info("[%s] Disconnected", self.name)
 
-    async def _run_post_connect_initialization(self) -> None:
-        """Finish non-critical startup work after Discord is connected."""
-        if not self._client:
-            return
-        try:
-            synced = await asyncio.wait_for(self._client.tree.sync(), timeout=30)
-            logger.info("[%s] Synced %d slash command(s)", self.name, len(synced))
-        except asyncio.TimeoutError:
-            logger.warning("[%s] Slash command sync timed out after 30s", self.name)
-        except asyncio.CancelledError:
-            raise
-        except Exception as e:  # pragma: no cover - defensive logging
-            logger.warning("[%s] Slash command sync failed: %s", self.name, e, exc_info=True)
-
     async def _add_reaction(self, message: Any, emoji: str) -> bool:
         """Add an emoji reaction to a Discord message."""
         if not message or not hasattr(message, "add_reaction"):
@@ -1044,7 +1063,6 @@ class DiscordAdapter(BasePlatformAdapter):
         if task:
             task.cancel()
         self._voice_text_channels.pop(guild_id, None)
-        self._voice_sources.pop(guild_id, None)
 
     # Maximum seconds to wait for voice playback before giving up
     PLAYBACK_TIMEOUT = 120
@@ -1852,7 +1870,7 @@ class DiscordAdapter(BasePlatformAdapter):
 
         # Track thread participation so follow-ups don't require @mention
         if thread_id:
-            self._threads.mark(thread_id)
+            self._track_thread(thread_id)
 
         # If a message was provided, kick off a new Hermes session in the thread
         starter = (message or "").strip()
@@ -2223,6 +2241,49 @@ class DiscordAdapter(BasePlatformAdapter):
             return f"{parent_name} / {thread_name}"
         return thread_name
 
+    # ------------------------------------------------------------------
+    # Thread participation persistence
+    # ------------------------------------------------------------------
+
+    @staticmethod
+    def _thread_state_path() -> Path:
+        """Path to the persisted thread participation set."""
+        from hermes_cli.config import get_hermes_home
+        return get_hermes_home() / "discord_threads.json"
+
+    @classmethod
+    def _load_participated_threads(cls) -> set:
+        """Load persisted thread IDs from disk."""
+        path = cls._thread_state_path()
+        try:
+            if path.exists():
+                data = json.loads(path.read_text(encoding="utf-8"))
+                if isinstance(data, list):
+                    return set(data)
+        except Exception as e:
+            logger.debug("Could not load discord thread state: %s", e)
+        return set()
+
+    def _save_participated_threads(self) -> None:
+        """Persist the current thread set to disk (best-effort)."""
+        path = self._thread_state_path()
+        try:
+            # Trim to most recent entries if over cap
+            thread_list = list(self._bot_participated_threads)
+            if len(thread_list) > self._MAX_TRACKED_THREADS:
+                thread_list = thread_list[-self._MAX_TRACKED_THREADS:]
+                self._bot_participated_threads = set(thread_list)
+            path.parent.mkdir(parents=True, exist_ok=True)
+            path.write_text(json.dumps(thread_list), encoding="utf-8")
+        except Exception as e:
+            logger.debug("Could not save discord thread state: %s", e)
+
+    def _track_thread(self, thread_id: str) -> None:
+        """Add a thread to the participation set and persist."""
+        if thread_id not in self._bot_participated_threads:
+            self._bot_participated_threads.add(thread_id)
+            self._save_participated_threads()
+
     async def _handle_message(self, message: DiscordMessage) -> None:
         """Handle incoming Discord messages."""
         # In server channels (not DMs), require the bot to be @mentioned
@@ -2244,7 +2305,6 @@ class DiscordAdapter(BasePlatformAdapter):
             thread_id = str(message.channel.id)
             parent_channel_id = self._get_parent_channel_id(message.channel)
 
-        is_voice_linked_channel = False
         if not isinstance(message.channel, discord.DMChannel):
             channel_ids = {str(message.channel.id)}
             if parent_channel_id:
@@ -2271,16 +2331,11 @@ class DiscordAdapter(BasePlatformAdapter):
                 channel_ids.add(parent_channel_id)
 
             require_mention = os.getenv("DISCORD_REQUIRE_MENTION", "true").lower() not in ("false", "0", "no")
-            # Voice-linked text channels act as free-response while voice is active.
-            # Only the exact bound channel gets the exemption, not sibling threads.
-            voice_linked_ids = {str(ch_id) for ch_id in self._voice_text_channels.values()}
-            current_channel_id = str(message.channel.id)
-            is_voice_linked_channel = current_channel_id in voice_linked_ids
-            is_free_channel = bool(channel_ids & free_channels) or is_voice_linked_channel
+            is_free_channel = bool(channel_ids & free_channels)
 
             # Skip the mention check if the message is in a thread where
             # the bot has previously participated (auto-created or replied in).
-            in_bot_thread = is_thread and thread_id in self._threads
+            in_bot_thread = is_thread and thread_id in self._bot_participated_threads
 
             if require_mention and not is_free_channel and not in_bot_thread:
                 if self._client.user not in message.mentions:
@@ -2300,13 +2355,13 @@ class DiscordAdapter(BasePlatformAdapter):
             no_thread_channels = {ch.strip() for ch in no_thread_channels_raw.split(",") if ch.strip()}
             skip_thread = bool(channel_ids & no_thread_channels)
             auto_thread = os.getenv("DISCORD_AUTO_THREAD", "true").lower() in ("true", "1", "yes")
-            if auto_thread and not skip_thread and not is_voice_linked_channel:
+            if auto_thread and not skip_thread:
                 thread = await self._auto_create_thread(message)
                 if thread:
                     is_thread = True
                     thread_id = str(thread.id)
                     auto_threaded_channel = thread
-                    self._threads.mark(thread_id)
+                    self._track_thread(thread_id)
 
         # Determine message type
         msg_type = MessageType.TEXT
@@ -2490,7 +2545,7 @@ class DiscordAdapter(BasePlatformAdapter):
         # Track thread participation so the bot won't require @mention for
         # follow-up messages in threads it has already engaged in.
         if thread_id:
-            self._threads.mark(thread_id)
+            self._track_thread(thread_id)
 
         # Only batch plain text messages — commands, media, etc. dispatch
         # immediately since they won't be split by the Discord client.

gateway/platforms/feishu.py

@@ -34,9 +34,6 @@ from datetime import datetime
 from pathlib import Path
 from types import SimpleNamespace
 from typing import Any, Dict, List, Optional
-from urllib.error import HTTPError, URLError
-from urllib.parse import urlencode
-from urllib.request import Request, urlopen
 
 # aiohttp/websockets are independent optional deps — import outside lark_oapi
 # so they remain available for tests and webhook mode even if lark_oapi is missing.
@@ -172,19 +169,6 @@ _FEISHU_CARD_ACTION_DEDUP_TTL_SECONDS = 15 * 60    # card action token dedup win
 _FEISHU_BOT_MSG_TRACK_SIZE = 512                   # LRU size for tracking sent message IDs
 _FEISHU_REPLY_FALLBACK_CODES = frozenset({230011, 231003})  # reply target withdrawn/missing → create fallback
 _FEISHU_ACK_EMOJI = "OK"
-
-# QR onboarding constants
-_ONBOARD_ACCOUNTS_URLS = {
-    "feishu": "https://accounts.feishu.cn",
-    "lark": "https://accounts.larksuite.com",
-}
-_ONBOARD_OPEN_URLS = {
-    "feishu": "https://open.feishu.cn",
-    "lark": "https://open.larksuite.com",
-}
-_REGISTRATION_PATH = "/oauth/v1/app/registration"
-_ONBOARD_REQUEST_TIMEOUT_S = 10
-
 # ---------------------------------------------------------------------------
 # Fallback display strings
 # ---------------------------------------------------------------------------
@@ -376,21 +360,19 @@ def _render_code_block_element(element: Dict[str, Any]) -> str:
 
 
 def _strip_markdown_to_plain_text(text: str) -> str:
-    """Strip markdown formatting to plain text for Feishu text fallbacks.
-
-    Delegates common markdown stripping to the shared helper and adds
-    Feishu-specific patterns (blockquotes, strikethrough, underline tags,
-    horizontal rules, \\r\\n normalisation).
-    """
-    from gateway.platforms.helpers import strip_markdown
     plain = text.replace("\r\n", "\n")
     plain = _MARKDOWN_LINK_RE.sub(lambda m: f"{m.group(1)} ({m.group(2).strip()})", plain)
+    plain = re.sub(r"^#{1,6}\s+", "", plain, flags=re.MULTILINE)
     plain = re.sub(r"^>\s?", "", plain, flags=re.MULTILINE)
     plain = re.sub(r"^\s*---+\s*$", "---", plain, flags=re.MULTILINE)
+    plain = re.sub(r"```(?:[^\n]*\n)?([\s\S]*?)```", lambda m: m.group(1).strip("\n"), plain)
+    plain = re.sub(r"`([^`\n]+)`", r"\1", plain)
+    plain = re.sub(r"\*\*([^*\n]+)\*\*", r"\1", plain)
+    plain = re.sub(r"\*([^*\n]+)\*", r"\1", plain)
     plain = re.sub(r"~~([^~\n]+)~~", r"\1", plain)
     plain = re.sub(r"<u>([\s\S]*?)</u>", r"\1", plain)
-    plain = strip_markdown(plain)
-    return plain
+    plain = re.sub(r"\n{3,}", "\n\n", plain)
+    return plain.strip()
 
 
 def _coerce_int(value: Any, default: Optional[int] = None, min_value: int = 0) -> Optional[int]:
@@ -430,6 +412,14 @@ def _build_markdown_post_payload(content: str) -> str:
     )
 
 
+def parse_feishu_post_content(raw_content: str) -> FeishuPostParseResult:
+    try:
+        parsed = json.loads(raw_content) if raw_content else {}
+    except json.JSONDecodeError:
+        return FeishuPostParseResult(text_content=FALLBACK_POST_TEXT)
+    return parse_feishu_post_payload(parsed)
+
+
 def parse_feishu_post_payload(payload: Any) -> FeishuPostParseResult:
     resolved = _resolve_post_payload(payload)
     if not resolved:
@@ -2680,6 +2670,12 @@ class FeishuAdapter(BasePlatformAdapter):
             return self._resolve_media_message_type(media_types[0] if media_types else "", default=MessageType.DOCUMENT)
         return MessageType.TEXT
 
+    def _normalize_inbound_text(self, text: str) -> str:
+        """Strip Feishu mention placeholders from inbound text."""
+        text = _MENTION_RE.sub(" ", text or "")
+        text = _MULTISPACE_RE.sub(" ", text)
+        return text.strip()
+
     async def _maybe_extract_text_document(self, cached_path: str, media_type: str) -> str:
         if not cached_path or not media_type.startswith("text/"):
             return ""
@@ -3623,328 +3619,3 @@ class FeishuAdapter(BasePlatformAdapter):
             return _FEISHU_FILE_UPLOAD_TYPE, "file"
 
         return _FEISHU_FILE_UPLOAD_TYPE, "file"
-
-
-# =============================================================================
-# QR scan-to-create onboarding
-#
-# Device-code flow: user scans a QR code with Feishu/Lark mobile app and the
-# platform creates a fully configured bot application automatically.
-# Called by `hermes gateway setup` via _setup_feishu() in hermes_cli/gateway.py.
-# =============================================================================
-
-
-def _accounts_base_url(domain: str) -> str:
-    return _ONBOARD_ACCOUNTS_URLS.get(domain, _ONBOARD_ACCOUNTS_URLS["feishu"])
-
-
-def _onboard_open_base_url(domain: str) -> str:
-    return _ONBOARD_OPEN_URLS.get(domain, _ONBOARD_OPEN_URLS["feishu"])
-
-
-def _post_registration(base_url: str, body: Dict[str, str]) -> dict:
-    """POST form-encoded data to the registration endpoint, return parsed JSON.
-
-    The registration endpoint returns JSON even on 4xx (e.g. poll returns
-    authorization_pending as a 400). We always parse the body regardless of
-    HTTP status.
-    """
-    url = f"{base_url}{_REGISTRATION_PATH}"
-    data = urlencode(body).encode("utf-8")
-    req = Request(url, data=data, headers={"Content-Type": "application/x-www-form-urlencoded"})
-    try:
-        with urlopen(req, timeout=_ONBOARD_REQUEST_TIMEOUT_S) as resp:
-            return json.loads(resp.read().decode("utf-8"))
-    except HTTPError as exc:
-        body_bytes = exc.read()
-        if body_bytes:
-            try:
-                return json.loads(body_bytes.decode("utf-8"))
-            except (ValueError, json.JSONDecodeError):
-                raise exc from None
-        raise
-
-
-def _init_registration(domain: str = "feishu") -> None:
-    """Verify the environment supports client_secret auth.
-
-    Raises RuntimeError if not supported.
-    """
-    base_url = _accounts_base_url(domain)
-    res = _post_registration(base_url, {"action": "init"})
-    methods = res.get("supported_auth_methods") or []
-    if "client_secret" not in methods:
-        raise RuntimeError(
-            f"Feishu / Lark registration environment does not support client_secret auth. "
-            f"Supported: {methods}"
-        )
-
-
-def _begin_registration(domain: str = "feishu") -> dict:
-    """Start the device-code flow. Returns device_code, qr_url, user_code, interval, expire_in."""
-    base_url = _accounts_base_url(domain)
-    res = _post_registration(base_url, {
-        "action": "begin",
-        "archetype": "PersonalAgent",
-        "auth_method": "client_secret",
-        "request_user_info": "open_id",
-    })
-    device_code = res.get("device_code")
-    if not device_code:
-        raise RuntimeError("Feishu / Lark registration did not return a device_code")
-    qr_url = res.get("verification_uri_complete", "")
-    if "?" in qr_url:
-        qr_url += "&from=hermes&tp=hermes"
-    else:
-        qr_url += "?from=hermes&tp=hermes"
-    return {
-        "device_code": device_code,
-        "qr_url": qr_url,
-        "user_code": res.get("user_code", ""),
-        "interval": res.get("interval") or 5,
-        "expire_in": res.get("expire_in") or 600,
-    }
-
-
-def _poll_registration(
-    *,
-    device_code: str,
-    interval: int,
-    expire_in: int,
-    domain: str = "feishu",
-) -> Optional[dict]:
-    """Poll until the user scans the QR code, or timeout/denial.
-
-    Returns dict with app_id, app_secret, domain, open_id on success.
-    Returns None on failure.
-    """
-    deadline = time.time() + expire_in
-    current_domain = domain
-    domain_switched = False
-    poll_count = 0
-
-    while time.time() < deadline:
-        base_url = _accounts_base_url(current_domain)
-        try:
-            res = _post_registration(base_url, {
-                "action": "poll",
-                "device_code": device_code,
-                "tp": "ob_app",
-            })
-        except (URLError, OSError, json.JSONDecodeError):
-            time.sleep(interval)
-            continue
-
-        poll_count += 1
-        if poll_count == 1:
-            print("  Fetching configuration results...", end="", flush=True)
-        elif poll_count % 6 == 0:
-            print(".", end="", flush=True)
-
-        # Domain auto-detection
-        user_info = res.get("user_info") or {}
-        tenant_brand = user_info.get("tenant_brand")
-        if tenant_brand == "lark" and not domain_switched:
-            current_domain = "lark"
-            domain_switched = True
-            # Fall through — server may return credentials in this same response.
-
-        # Success
-        if res.get("client_id") and res.get("client_secret"):
-            if poll_count > 0:
-                print()  # newline after "Fetching configuration results..." dots
-            return {
-                "app_id": res["client_id"],
-                "app_secret": res["client_secret"],
-                "domain": current_domain,
-                "open_id": user_info.get("open_id"),
-            }
-
-        # Terminal errors
-        error = res.get("error", "")
-        if error in ("access_denied", "expired_token"):
-            if poll_count > 0:
-                print()
-            logger.warning("[Feishu onboard] Registration %s", error)
-            return None
-
-        # authorization_pending or unknown — keep polling
-        time.sleep(interval)
-
-    if poll_count > 0:
-        print()
-    logger.warning("[Feishu onboard] Poll timed out after %ds", expire_in)
-    return None
-
-
-try:
-    import qrcode as _qrcode_mod
-except (ImportError, TypeError):
-    _qrcode_mod = None  # type: ignore[assignment]
-
-
-def _render_qr(url: str) -> bool:
-    """Try to render a QR code in the terminal. Returns True if successful."""
-    if _qrcode_mod is None:
-        return False
-    try:
-        qr = _qrcode_mod.QRCode()
-        qr.add_data(url)
-        qr.make(fit=True)
-        qr.print_ascii(invert=True)
-        return True
-    except Exception:
-        return False
-
-
-def probe_bot(app_id: str, app_secret: str, domain: str) -> Optional[dict]:
-    """Verify bot connectivity via /open-apis/bot/v3/info.
-
-    Uses lark_oapi SDK when available, falls back to raw HTTP otherwise.
-    Returns {"bot_name": ..., "bot_open_id": ...} on success, None on failure.
-    """
-    if FEISHU_AVAILABLE:
-        return _probe_bot_sdk(app_id, app_secret, domain)
-    return _probe_bot_http(app_id, app_secret, domain)
-
-
-def _build_onboard_client(app_id: str, app_secret: str, domain: str) -> Any:
-    """Build a lark Client for the given credentials and domain."""
-    sdk_domain = LARK_DOMAIN if domain == "lark" else FEISHU_DOMAIN
-    return (
-        lark.Client.builder()
-        .app_id(app_id)
-        .app_secret(app_secret)
-        .domain(sdk_domain)
-        .log_level(lark.LogLevel.WARNING)
-        .build()
-    )
-
-
-def _parse_bot_response(data: dict) -> Optional[dict]:
-    """Extract bot_name and bot_open_id from a /bot/v3/info response."""
-    if data.get("code") != 0:
-        return None
-    bot = data.get("bot") or data.get("data", {}).get("bot") or {}
-    return {
-        "bot_name": bot.get("bot_name"),
-        "bot_open_id": bot.get("open_id"),
-    }
-
-
-def _probe_bot_sdk(app_id: str, app_secret: str, domain: str) -> Optional[dict]:
-    """Probe bot info using lark_oapi SDK."""
-    try:
-        client = _build_onboard_client(app_id, app_secret, domain)
-        resp = client.request(
-            method="GET",
-            url="/open-apis/bot/v3/info",
-            body=None,
-            raw_response=True,
-        )
-        return _parse_bot_response(json.loads(resp.content))
-    except Exception as exc:
-        logger.debug("[Feishu onboard] SDK probe failed: %s", exc)
-        return None
-
-
-def _probe_bot_http(app_id: str, app_secret: str, domain: str) -> Optional[dict]:
-    """Fallback probe using raw HTTP (when lark_oapi is not installed)."""
-    base_url = _onboard_open_base_url(domain)
-    try:
-        token_data = json.dumps({"app_id": app_id, "app_secret": app_secret}).encode("utf-8")
-        token_req = Request(
-            f"{base_url}/open-apis/auth/v3/tenant_access_token/internal",
-            data=token_data,
-            headers={"Content-Type": "application/json"},
-        )
-        with urlopen(token_req, timeout=_ONBOARD_REQUEST_TIMEOUT_S) as resp:
-            token_res = json.loads(resp.read().decode("utf-8"))
-
-        access_token = token_res.get("tenant_access_token")
-        if not access_token:
-            return None
-
-        bot_req = Request(
-            f"{base_url}/open-apis/bot/v3/info",
-            headers={
-                "Authorization": f"Bearer {access_token}",
-                "Content-Type": "application/json",
-            },
-        )
-        with urlopen(bot_req, timeout=_ONBOARD_REQUEST_TIMEOUT_S) as resp:
-            bot_res = json.loads(resp.read().decode("utf-8"))
-
-        return _parse_bot_response(bot_res)
-    except (URLError, OSError, KeyError, json.JSONDecodeError) as exc:
-        logger.debug("[Feishu onboard] HTTP probe failed: %s", exc)
-        return None
-
-
-def qr_register(
-    *,
-    initial_domain: str = "feishu",
-    timeout_seconds: int = 600,
-) -> Optional[dict]:
-    """Run the Feishu / Lark scan-to-create QR registration flow.
-
-    Returns on success::
-
-        {
-            "app_id": str,
-            "app_secret": str,
-            "domain": "feishu" | "lark",
-            "open_id": str | None,
-            "bot_name": str | None,
-            "bot_open_id": str | None,
-        }
-
-    Returns None on expected failures (network, auth denied, timeout).
-    Unexpected errors (bugs, protocol regressions) propagate to the caller.
-    """
-    try:
-        return _qr_register_inner(initial_domain=initial_domain, timeout_seconds=timeout_seconds)
-    except (RuntimeError, URLError, OSError, json.JSONDecodeError) as exc:
-        logger.warning("[Feishu onboard] Registration failed: %s", exc)
-        return None
-
-
-def _qr_register_inner(
-    *,
-    initial_domain: str,
-    timeout_seconds: int,
-) -> Optional[dict]:
-    """Run init → begin → poll → probe. Raises on network/protocol errors."""
-    print("  Connecting to Feishu / Lark...", end="", flush=True)
-    _init_registration(initial_domain)
-    begin = _begin_registration(initial_domain)
-    print(" done.")
-
-    print()
-    qr_url = begin["qr_url"]
-    if _render_qr(qr_url):
-        print(f"\n  Scan the QR code above, or open this URL directly:\n  {qr_url}")
-    else:
-        print(f"  Open this URL in Feishu / Lark on your phone:\n\n  {qr_url}\n")
-        print("  Tip: pip install qrcode  to display a scannable QR code here next time")
-    print()
-
-    result = _poll_registration(
-        device_code=begin["device_code"],
-        interval=begin["interval"],
-        expire_in=min(begin["expire_in"], timeout_seconds),
-        domain=initial_domain,
-    )
-    if not result:
-        return None
-
-    # Probe bot — best-effort, don't fail the registration
-    bot_info = probe_bot(result["app_id"], result["app_secret"], result["domain"])
-    if bot_info:
-        result["bot_name"] = bot_info.get("bot_name")
-        result["bot_open_id"] = bot_info.get("bot_open_id")
-    else:
-        result["bot_name"] = None
-        result["bot_open_id"] = None
-
-    return result

gateway/platforms/helpers.py

@@ -1,261 +0,0 @@
-"""Shared helper classes for gateway platform adapters.
-
-Extracts common patterns that were duplicated across 5-7 adapters:
-message deduplication, text batch aggregation, markdown stripping,
-and thread participation tracking.
-"""
-
-import asyncio
-import json
-import logging
-import re
-import time
-from pathlib import Path
-from typing import TYPE_CHECKING, Dict, Optional
-
-if TYPE_CHECKING:
-    from gateway.platforms.base import BasePlatformAdapter, MessageEvent
-
-logger = logging.getLogger(__name__)
-
-
-# ─── Message Deduplication ────────────────────────────────────────────────────
-
-
-class MessageDeduplicator:
-    """TTL-based message deduplication cache.
-
-    Replaces the identical ``_seen_messages`` / ``_is_duplicate()`` pattern
-    previously duplicated in discord, slack, dingtalk, wecom, weixin,
-    mattermost, and feishu adapters.
-
-    Usage::
-
-        self._dedup = MessageDeduplicator()
-
-        # In message handler:
-        if self._dedup.is_duplicate(msg_id):
-            return
-    """
-
-    def __init__(self, max_size: int = 2000, ttl_seconds: float = 300):
-        self._seen: Dict[str, float] = {}
-        self._max_size = max_size
-        self._ttl = ttl_seconds
-
-    def is_duplicate(self, msg_id: str) -> bool:
-        """Return True if *msg_id* was already seen within the TTL window."""
-        if not msg_id:
-            return False
-        now = time.time()
-        if msg_id in self._seen:
-            return True
-        self._seen[msg_id] = now
-        if len(self._seen) > self._max_size:
-            cutoff = now - self._ttl
-            self._seen = {k: v for k, v in self._seen.items() if v > cutoff}
-        return False
-
-    def clear(self):
-        """Clear all tracked messages."""
-        self._seen.clear()
-
-
-# ─── Text Batch Aggregation ──────────────────────────────────────────────────
-
-
-class TextBatchAggregator:
-    """Aggregates rapid-fire text events into single messages.
-
-    Replaces the ``_enqueue_text_event`` / ``_flush_text_batch`` pattern
-    previously duplicated in telegram, discord, matrix, wecom, and feishu.
-
-    Usage::
-
-        self._text_batcher = TextBatchAggregator(
-            handler=self._message_handler,
-            batch_delay=0.6,
-            split_threshold=1900,
-        )
-
-        # In message dispatch:
-        if msg_type == MessageType.TEXT and self._text_batcher.is_enabled():
-            self._text_batcher.enqueue(event, session_key)
-            return
-    """
-
-    def __init__(
-        self,
-        handler,
-        *,
-        batch_delay: float = 0.6,
-        split_delay: float = 2.0,
-        split_threshold: int = 4000,
-    ):
-        self._handler = handler
-        self._batch_delay = batch_delay
-        self._split_delay = split_delay
-        self._split_threshold = split_threshold
-        self._pending: Dict[str, "MessageEvent"] = {}
-        self._pending_tasks: Dict[str, asyncio.Task] = {}
-
-    def is_enabled(self) -> bool:
-        """Return True if batching is active (delay > 0)."""
-        return self._batch_delay > 0
-
-    def enqueue(self, event: "MessageEvent", key: str) -> None:
-        """Add *event* to the pending batch for *key*."""
-        chunk_len = len(event.text or "")
-        existing = self._pending.get(key)
-        if not existing:
-            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
-            self._pending[key] = event
-        else:
-            existing.text = f"{existing.text}\n{event.text}"
-            existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
-
-        # Cancel prior flush timer, start a new one
-        prior = self._pending_tasks.get(key)
-        if prior and not prior.done():
-            prior.cancel()
-        self._pending_tasks[key] = asyncio.create_task(self._flush(key))
-
-    async def _flush(self, key: str) -> None:
-        """Wait then dispatch the batched event for *key*."""
-        current_task = self._pending_tasks.get(key)
-        pending = self._pending.get(key)
-        last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
-
-        # Use longer delay when the last chunk looks like a split message
-        delay = self._split_delay if last_len >= self._split_threshold else self._batch_delay
-        await asyncio.sleep(delay)
-
-        event = self._pending.pop(key, None)
-        if event:
-            try:
-                await self._handler(event)
-            except Exception:
-                logger.exception("[TextBatchAggregator] Error dispatching batched event for %s", key)
-
-        if self._pending_tasks.get(key) is current_task:
-            self._pending_tasks.pop(key, None)
-
-    def cancel_all(self) -> None:
-        """Cancel all pending flush tasks."""
-        for task in self._pending_tasks.values():
-            if not task.done():
-                task.cancel()
-        self._pending_tasks.clear()
-        self._pending.clear()
-
-
-# ─── Markdown Stripping ──────────────────────────────────────────────────────
-
-# Pre-compiled regexes for performance
-_RE_BOLD = re.compile(r"\*\*(.+?)\*\*", re.DOTALL)
-_RE_ITALIC_STAR = re.compile(r"\*(.+?)\*", re.DOTALL)
-_RE_BOLD_UNDER = re.compile(r"__(.+?)__", re.DOTALL)
-_RE_ITALIC_UNDER = re.compile(r"_(.+?)_", re.DOTALL)
-_RE_CODE_BLOCK = re.compile(r"```[a-zA-Z0-9_+-]*\n?")
-_RE_INLINE_CODE = re.compile(r"`(.+?)`")
-_RE_HEADING = re.compile(r"^#{1,6}\s+", re.MULTILINE)
-_RE_LINK = re.compile(r"\[([^\]]+)\]\([^\)]+\)")
-_RE_MULTI_NEWLINE = re.compile(r"\n{3,}")
-
-
-def strip_markdown(text: str) -> str:
-    """Strip markdown formatting for plain-text platforms (SMS, iMessage, etc.).
-
-    Replaces the identical ``_strip_markdown()`` functions previously
-    duplicated in sms.py, bluebubbles.py, and feishu.py.
-    """
-    text = _RE_BOLD.sub(r"\1", text)
-    text = _RE_ITALIC_STAR.sub(r"\1", text)
-    text = _RE_BOLD_UNDER.sub(r"\1", text)
-    text = _RE_ITALIC_UNDER.sub(r"\1", text)
-    text = _RE_CODE_BLOCK.sub("", text)
-    text = _RE_INLINE_CODE.sub(r"\1", text)
-    text = _RE_HEADING.sub("", text)
-    text = _RE_LINK.sub(r"\1", text)
-    text = _RE_MULTI_NEWLINE.sub("\n\n", text)
-    return text.strip()
-
-
-# ─── Thread Participation Tracking ───────────────────────────────────────────
-
-
-class ThreadParticipationTracker:
-    """Persistent tracking of threads the bot has participated in.
-
-    Replaces the identical ``_load/_save_participated_threads`` +
-    ``_mark_thread_participated`` pattern previously duplicated in
-    discord.py and matrix.py.
-
-    Usage::
-
-        self._threads = ThreadParticipationTracker("discord")
-
-        # Check membership:
-        if thread_id in self._threads:
-            ...
-
-        # Mark participation:
-        self._threads.mark(thread_id)
-    """
-
-    _MAX_TRACKED = 500
-
-    def __init__(self, platform_name: str, max_tracked: int = 500):
-        self._platform = platform_name
-        self._max_tracked = max_tracked
-        self._threads: set = self._load()
-
-    def _state_path(self) -> Path:
-        from hermes_constants import get_hermes_home
-        return get_hermes_home() / f"{self._platform}_threads.json"
-
-    def _load(self) -> set:
-        path = self._state_path()
-        if path.exists():
-            try:
-                return set(json.loads(path.read_text(encoding="utf-8")))
-            except Exception:
-                pass
-        return set()
-
-    def _save(self) -> None:
-        path = self._state_path()
-        path.parent.mkdir(parents=True, exist_ok=True)
-        thread_list = list(self._threads)
-        if len(thread_list) > self._max_tracked:
-            thread_list = thread_list[-self._max_tracked:]
-            self._threads = set(thread_list)
-        path.write_text(json.dumps(thread_list), encoding="utf-8")
-
-    def mark(self, thread_id: str) -> None:
-        """Mark *thread_id* as participated and persist."""
-        if thread_id not in self._threads:
-            self._threads.add(thread_id)
-            self._save()
-
-    def __contains__(self, thread_id: str) -> bool:
-        return thread_id in self._threads
-
-    def clear(self) -> None:
-        self._threads.clear()
-
-
-# ─── Phone Number Redaction ──────────────────────────────────────────────────
-
-
-def redact_phone(phone: str) -> str:
-    """Redact a phone number for logging, preserving country code and last 4.
-
-    Replaces the identical ``_redact_phone()`` functions in signal.py,
-    sms.py, and bluebubbles.py.
-    """
-    if not phone:
-        return "<none>"
-    if len(phone) <= 8:
-        return phone[:2] + "****" + phone[-2:] if len(phone) > 4 else "****"
-    return phone[:4] + "****" + phone[-4:]

gateway/platforms/mattermost.py

@@ -18,11 +18,11 @@ import json
 import logging
 import os
 import re
+import time
 from pathlib import Path
 from typing import Any, Dict, List, Optional
 
 from gateway.config import Platform, PlatformConfig
-from gateway.platforms.helpers import MessageDeduplicator
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
@@ -96,8 +96,10 @@ class MattermostAdapter(BasePlatformAdapter):
             or os.getenv("MATTERMOST_REPLY_MODE", "off")
         ).lower()
 
-        # Dedup cache (prevent reprocessing)
-        self._dedup = MessageDeduplicator()
+        # Dedup cache: post_id → timestamp (prevent reprocessing)
+        self._seen_posts: Dict[str, float] = {}
+        self._SEEN_MAX = 2000
+        self._SEEN_TTL = 300  # 5 minutes
 
     # ------------------------------------------------------------------
     # HTTP helpers
@@ -602,8 +604,10 @@ class MattermostAdapter(BasePlatformAdapter):
         post_id = post.get("id", "")
 
         # Dedup.
-        if self._dedup.is_duplicate(post_id):
+        self._prune_seen()
+        if post_id in self._seen_posts:
             return
+        self._seen_posts[post_id] = time.time()
 
         # Build message event.
         channel_id = post.get("channel_id", "")
@@ -730,4 +734,13 @@ class MattermostAdapter(BasePlatformAdapter):
 
         await self.handle_message(msg_event)
 
-
+    def _prune_seen(self) -> None:
+        """Remove expired entries from the dedup cache."""
+        if len(self._seen_posts) < self._SEEN_MAX:
+            return
+        now = time.time()
+        self._seen_posts = {
+            pid: ts
+            for pid, ts in self._seen_posts.items()
+            if now - ts < self._SEEN_TTL
+        }

gateway/platforms/signal.py

@@ -17,6 +17,7 @@ import json
 import logging
 import os
 import random
+import re
 import time
 from datetime import datetime, timezone
 from pathlib import Path
@@ -36,7 +37,6 @@ from gateway.platforms.base import (
     cache_document_from_bytes,
     cache_image_from_url,
 )
-from gateway.platforms.helpers import redact_phone
 
 logger = logging.getLogger(__name__)
 
@@ -51,10 +51,22 @@ SSE_RETRY_DELAY_MAX = 60.0
 HEALTH_CHECK_INTERVAL = 30.0  # seconds between health checks
 HEALTH_CHECK_STALE_THRESHOLD = 120.0  # seconds without SSE activity before concern
 
+# E.164 phone number pattern for redaction
+_PHONE_RE = re.compile(r"\+[1-9]\d{6,14}")
+
+
 # ---------------------------------------------------------------------------
 # Helpers
 # ---------------------------------------------------------------------------
 
+def _redact_phone(phone: str) -> str:
+    """Redact a phone number for logging: +15551234567 -> +155****4567."""
+    if not phone:
+        return "<none>"
+    if len(phone) <= 8:
+        return phone[:2] + "****" + phone[-2:] if len(phone) > 4 else "****"
+    return phone[:4] + "****" + phone[-4:]
+
 
 def _parse_comma_list(value: str) -> List[str]:
     """Split a comma-separated string into a list, stripping whitespace."""
@@ -172,8 +184,10 @@ class SignalAdapter(BasePlatformAdapter):
         self._recent_sent_timestamps: set = set()
         self._max_recent_timestamps = 50
 
+        self._phone_lock_identity: Optional[str] = None
+
         logger.info("Signal adapter initialized: url=%s account=%s groups=%s",
-                     self.http_url, redact_phone(self.account),
+                     self.http_url, _redact_phone(self.account),
                      "enabled" if self.group_allow_from else "disabled")
 
     # ------------------------------------------------------------------
@@ -188,7 +202,23 @@ class SignalAdapter(BasePlatformAdapter):
 
         # Acquire scoped lock to prevent duplicate Signal listeners for the same phone
         try:
-            if not self._acquire_platform_lock('signal-phone', self.account, 'Signal account'):
+            from gateway.status import acquire_scoped_lock
+
+            self._phone_lock_identity = self.account
+            acquired, existing = acquire_scoped_lock(
+                "signal-phone",
+                self._phone_lock_identity,
+                metadata={"platform": self.platform.value},
+            )
+            if not acquired:
+                owner_pid = existing.get("pid") if isinstance(existing, dict) else None
+                message = (
+                    "Another local Hermes gateway is already using this Signal account"
+                    + (f" (PID {owner_pid})." if owner_pid else ".")
+                    + " Stop the other gateway before starting a second Signal listener."
+                )
+                logger.error("Signal: %s", message)
+                self._set_fatal_error("signal_phone_lock", message, retryable=False)
                 return False
         except Exception as e:
             logger.warning("Signal: Could not acquire phone lock (non-fatal): %s", e)
@@ -240,7 +270,13 @@ class SignalAdapter(BasePlatformAdapter):
             await self.client.aclose()
             self.client = None
 
-        self._release_platform_lock()
+        if self._phone_lock_identity:
+            try:
+                from gateway.status import release_scoped_lock
+                release_scoped_lock("signal-phone", self._phone_lock_identity)
+            except Exception as e:
+                logger.warning("Signal: Error releasing phone lock: %s", e, exc_info=True)
+            self._phone_lock_identity = None
 
         logger.info("Signal: disconnected")
 
@@ -506,7 +542,7 @@ class SignalAdapter(BasePlatformAdapter):
         )
 
         logger.debug("Signal: message from %s in %s: %s",
-                      redact_phone(sender), chat_id[:20], (text or "")[:50])
+                      _redact_phone(sender), chat_id[:20], (text or "")[:50])
 
         await self.handle_message(event)
 
@@ -780,6 +816,21 @@ class SignalAdapter(BasePlatformAdapter):
     # Typing Indicators
     # ------------------------------------------------------------------
 
+    async def _start_typing_indicator(self, chat_id: str) -> None:
+        """Start a typing indicator loop for a chat."""
+        if chat_id in self._typing_tasks:
+            return  # Already running
+
+        async def _typing_loop():
+            try:
+                while True:
+                    await self.send_typing(chat_id)
+                    await asyncio.sleep(TYPING_INTERVAL)
+            except asyncio.CancelledError:
+                pass
+
+        self._typing_tasks[chat_id] = asyncio.create_task(_typing_loop())
+
     async def _stop_typing_indicator(self, chat_id: str) -> None:
         """Stop a typing indicator loop for a chat."""
         task = self._typing_tasks.pop(chat_id, None)

gateway/platforms/slack.py

@@ -33,7 +33,6 @@ from pathlib import Path as _Path
 sys.path.insert(0, str(_Path(__file__).resolve().parents[2]))
 
 from gateway.config import Platform, PlatformConfig
-from gateway.platforms.helpers import MessageDeduplicator
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
@@ -90,9 +89,11 @@ class SlackAdapter(BasePlatformAdapter):
         self._team_clients: Dict[str, AsyncWebClient] = {}   # team_id → WebClient
         self._team_bot_user_ids: Dict[str, str] = {}          # team_id → bot_user_id
         self._channel_team: Dict[str, str] = {}                # channel_id → team_id
-        # Dedup cache: prevents duplicate bot responses when Socket Mode
-        # reconnects redeliver events.
-        self._dedup = MessageDeduplicator()
+        # Dedup cache: event_ts → timestamp.  Prevents duplicate bot
+        # responses when Socket Mode reconnects redeliver events.
+        self._seen_messages: Dict[str, float] = {}
+        self._SEEN_TTL = 300   # 5 minutes
+        self._SEEN_MAX = 2000  # prune threshold
         # Track pending approval message_ts → resolved flag to prevent
         # double-clicks on approval buttons.
         self._approval_resolved: Dict[str, bool] = {}
@@ -151,7 +152,15 @@ class SlackAdapter(BasePlatformAdapter):
                 logger.warning("[Slack] Failed to read %s: %s", tokens_file, e)
 
         try:
-            if not self._acquire_platform_lock('slack-app-token', app_token, 'Slack app token'):
+            # Acquire scoped lock to prevent duplicate app token usage
+            from gateway.status import acquire_scoped_lock
+            self._token_lock_identity = app_token
+            acquired, existing = acquire_scoped_lock('slack-app-token', app_token, metadata={'platform': 'slack'})
+            if not acquired:
+                owner_pid = existing.get('pid') if isinstance(existing, dict) else None
+                message = f'Slack app token already in use' + (f' (PID {owner_pid})' if owner_pid else '') + '. Stop the other gateway first.'
+                logger.error('[%s] %s', self.name, message)
+                self._set_fatal_error('slack_token_lock', message, retryable=False)
                 return False
 
             # First token is the primary — used for AsyncApp / Socket Mode
@@ -238,7 +247,14 @@ class SlackAdapter(BasePlatformAdapter):
                 logger.warning("[Slack] Error while closing Socket Mode handler: %s", e, exc_info=True)
         self._running = False
 
-        self._release_platform_lock()
+        # Release the token lock (use stored identity, not re-read env)
+        try:
+            from gateway.status import release_scoped_lock
+            if getattr(self, '_token_lock_identity', None):
+                release_scoped_lock('slack-app-token', self._token_lock_identity)
+                self._token_lock_identity = None
+        except Exception:
+            pass
 
         logger.info("[Slack] Disconnected")
 
@@ -937,8 +953,17 @@ class SlackAdapter(BasePlatformAdapter):
         """Handle an incoming Slack message event."""
         # Dedup: Slack Socket Mode can redeliver events after reconnects (#4777)
         event_ts = event.get("ts", "")
-        if event_ts and self._dedup.is_duplicate(event_ts):
-            return
+        if event_ts:
+            now = time.time()
+            if event_ts in self._seen_messages:
+                return
+            self._seen_messages[event_ts] = now
+            if len(self._seen_messages) > self._SEEN_MAX:
+                cutoff = now - self._SEEN_TTL
+                self._seen_messages = {
+                    k: v for k, v in self._seen_messages.items()
+                    if v > cutoff
+                }
 
         # Bot message filtering (SLACK_ALLOW_BOTS / config allow_bots):
         #   "none"     — ignore all bot messages (default, backward-compatible)

gateway/platforms/sms.py

@@ -10,9 +10,6 @@ Shares credentials with the optional telephony skill — same env vars:
 
 Gateway-specific env vars:
   - SMS_WEBHOOK_PORT     (default 8080)
-  - SMS_WEBHOOK_HOST     (default 0.0.0.0)
-  - SMS_WEBHOOK_URL      (public URL for Twilio signature validation — required)
-  - SMS_INSECURE_NO_SIGNATURE  (true to disable signature validation — dev only)
   - SMS_ALLOWED_USERS    (comma-separated E.164 phone numbers)
   - SMS_ALLOW_ALL_USERS  (true/false)
   - SMS_HOME_CHANNEL     (phone number for cron delivery)
@@ -20,10 +17,9 @@ Gateway-specific env vars:
 
 import asyncio
 import base64
-import hashlib
-import hmac
 import logging
 import os
+import re
 import urllib.parse
 from typing import Any, Dict, Optional
 
@@ -34,14 +30,24 @@ from gateway.platforms.base import (
     MessageType,
     SendResult,
 )
-from gateway.platforms.helpers import redact_phone, strip_markdown
 
 logger = logging.getLogger(__name__)
 
 TWILIO_API_BASE = "https://api.twilio.com/2010-04-01/Accounts"
 MAX_SMS_LENGTH = 1600  # ~10 SMS segments
 DEFAULT_WEBHOOK_PORT = 8080
-DEFAULT_WEBHOOK_HOST = "0.0.0.0"
+
+# E.164 phone number pattern for redaction
+_PHONE_RE = re.compile(r"\+[1-9]\d{6,14}")
+
+
+def _redact_phone(phone: str) -> str:
+    """Redact a phone number for logging: +15551234567 -> +1555***4567."""
+    if not phone:
+        return "<none>"
+    if len(phone) <= 8:
+        return phone[:2] + "***" + phone[-2:] if len(phone) > 4 else "****"
+    return phone[:5] + "***" + phone[-4:]
 
 
 def check_sms_requirements() -> bool:
@@ -71,8 +77,6 @@ class SmsAdapter(BasePlatformAdapter):
         self._webhook_port: int = int(
             os.getenv("SMS_WEBHOOK_PORT", str(DEFAULT_WEBHOOK_PORT))
         )
-        self._webhook_host: str = os.getenv("SMS_WEBHOOK_HOST", DEFAULT_WEBHOOK_HOST)
-        self._webhook_url: str = os.getenv("SMS_WEBHOOK_URL", "").strip()
         self._runner = None
         self._http_session: Optional["aiohttp.ClientSession"] = None
 
@@ -94,33 +98,13 @@ class SmsAdapter(BasePlatformAdapter):
             logger.error("[sms] TWILIO_PHONE_NUMBER not set — cannot send replies")
             return False
 
-        insecure_no_sig = os.getenv("SMS_INSECURE_NO_SIGNATURE", "").lower() == "true"
-
-        if not self._webhook_url and not insecure_no_sig:
-            logger.error(
-                "[sms] Refusing to start: SMS_WEBHOOK_URL is required for Twilio "
-                "signature validation. Set it to the public URL configured in your "
-                "Twilio console (e.g. https://example.com/webhooks/twilio). "
-                "For local development without validation, set "
-                "SMS_INSECURE_NO_SIGNATURE=true (NOT recommended for production).",
-            )
-            return False
-
-        if insecure_no_sig and not self._webhook_url:
-            logger.warning(
-                "[sms] SMS_INSECURE_NO_SIGNATURE=true — Twilio signature validation "
-                "is DISABLED. Any client that can reach port %d can inject messages. "
-                "Do NOT use this in production.",
-                self._webhook_port,
-            )
-
         app = web.Application()
         app.router.add_post("/webhooks/twilio", self._handle_webhook)
         app.router.add_get("/health", lambda _: web.Response(text="ok"))
 
         self._runner = web.AppRunner(app)
         await self._runner.setup()
-        site = web.TCPSite(self._runner, self._webhook_host, self._webhook_port)
+        site = web.TCPSite(self._runner, "0.0.0.0", self._webhook_port)
         await site.start()
         self._http_session = aiohttp.ClientSession(
             timeout=aiohttp.ClientTimeout(total=30),
@@ -128,10 +112,9 @@ class SmsAdapter(BasePlatformAdapter):
         self._running = True
 
         logger.info(
-            "[sms] Twilio webhook server listening on %s:%d, from: %s",
-            self._webhook_host,
+            "[sms] Twilio webhook server listening on port %d, from: %s",
             self._webhook_port,
-            redact_phone(self._from_number),
+            _redact_phone(self._from_number),
         )
         return True
 
@@ -180,7 +163,7 @@ class SmsAdapter(BasePlatformAdapter):
                             error_msg = body.get("message", str(body))
                             logger.error(
                                 "[sms] send failed to %s: %s %s",
-                                redact_phone(chat_id),
+                                _redact_phone(chat_id),
                                 resp.status,
                                 error_msg,
                             )
@@ -191,7 +174,7 @@ class SmsAdapter(BasePlatformAdapter):
                         msg_sid = body.get("sid", "")
                         last_result = SendResult(success=True, message_id=msg_sid)
                 except Exception as e:
-                    logger.error("[sms] send error to %s: %s", redact_phone(chat_id), e)
+                    logger.error("[sms] send error to %s: %s", _redact_phone(chat_id), e)
                     return SendResult(success=False, error=str(e))
         finally:
             # Close session only if we created a fallback (no persistent session)
@@ -209,75 +192,16 @@ class SmsAdapter(BasePlatformAdapter):
 
     def format_message(self, content: str) -> str:
         """Strip markdown — SMS renders it as literal characters."""
-        return strip_markdown(content)
-
-    # ------------------------------------------------------------------
-    # Twilio signature validation
-    # ------------------------------------------------------------------
-
-    def _validate_twilio_signature(
-        self, url: str, post_params: dict, signature: str,
-    ) -> bool:
-        """Validate ``X-Twilio-Signature`` header (HMAC-SHA1, base64).
-
-        Tries both with and without the default port for the URL scheme,
-        since Twilio may sign with either variant.
-
-        Algorithm: https://www.twilio.com/docs/usage/security#validating-requests
-        """
-        if self._check_signature(url, post_params, signature):
-            return True
-
-        variant = self._port_variant_url(url)
-        if variant and self._check_signature(variant, post_params, signature):
-            return True
-
-        return False
-
-    def _check_signature(
-        self, url: str, post_params: dict, signature: str,
-    ) -> bool:
-        """Compute and compare a single Twilio signature."""
-        data_to_sign = url
-        for key in sorted(post_params.keys()):
-            data_to_sign += key + post_params[key]
-        mac = hmac.new(
-            self._auth_token.encode("utf-8"),
-            data_to_sign.encode("utf-8"),
-            hashlib.sha1,
-        )
-        computed = base64.b64encode(mac.digest()).decode("utf-8")
-        return hmac.compare_digest(computed, signature)
-
-    @staticmethod
-    def _port_variant_url(url: str) -> str | None:
-        """Return the URL with the default port toggled, or None.
-
-        Only toggles default ports (443 for https, 80 for http).
-        Non-standard ports are never modified.
-        """
-        parsed = urllib.parse.urlparse(url)
-        default_ports = {"https": 443, "http": 80}
-        default_port = default_ports.get(parsed.scheme)
-        if default_port is None:
-            return None
-
-        if parsed.port == default_port:
-            # Has explicit default port → strip it
-            return urllib.parse.urlunparse(
-                (parsed.scheme, parsed.hostname, parsed.path,
-                 parsed.params, parsed.query, parsed.fragment)
-            )
-        elif parsed.port is None:
-            # No port → add default
-            netloc = f"{parsed.hostname}:{default_port}"
-            return urllib.parse.urlunparse(
-                (parsed.scheme, netloc, parsed.path,
-                 parsed.params, parsed.query, parsed.fragment)
-            )
-
-        # Non-standard port — no variant
-        return None
+        content = re.sub(r"\*\*(.+?)\*\*", r"\1", content, flags=re.DOTALL)
+        content = re.sub(r"\*(.+?)\*", r"\1", content, flags=re.DOTALL)
+        content = re.sub(r"__(.+?)__", r"\1", content, flags=re.DOTALL)
+        content = re.sub(r"_(.+?)_", r"\1", content, flags=re.DOTALL)
+        content = re.sub(r"```[a-z]*\n?", "", content)
+        content = re.sub(r"`(.+?)`", r"\1", content)
+        content = re.sub(r"^#{1,6}\s+", "", content, flags=re.MULTILINE)
+        content = re.sub(r"\[([^\]]+)\]\([^\)]+\)", r"\1", content)
+        content = re.sub(r"\n{3,}", "\n\n", content)
+        return content.strip()
 
     # ------------------------------------------------------------------
     # Twilio webhook handler
@@ -289,7 +213,7 @@ class SmsAdapter(BasePlatformAdapter):
         try:
             raw = await request.read()
             # Twilio sends form-encoded data, not JSON
-            form = urllib.parse.parse_qs(raw.decode("utf-8"), keep_blank_values=True)
+            form = urllib.parse.parse_qs(raw.decode("utf-8"))
         except Exception as e:
             logger.error("[sms] webhook parse error: %s", e)
             return web.Response(
@@ -298,27 +222,6 @@ class SmsAdapter(BasePlatformAdapter):
                 status=400,
             )
 
-        # Validate Twilio request signature when SMS_WEBHOOK_URL is configured
-        if self._webhook_url:
-            twilio_sig = request.headers.get("X-Twilio-Signature", "")
-            if not twilio_sig:
-                logger.warning("[sms] Rejected: missing X-Twilio-Signature header")
-                return web.Response(
-                    text='<?xml version="1.0" encoding="UTF-8"?><Response></Response>',
-                    content_type="application/xml",
-                    status=403,
-                )
-            flat_params = {k: v[0] for k, v in form.items() if v}
-            if not self._validate_twilio_signature(
-                self._webhook_url, flat_params, twilio_sig
-            ):
-                logger.warning("[sms] Rejected: invalid Twilio signature")
-                return web.Response(
-                    text='<?xml version="1.0" encoding="UTF-8"?><Response></Response>',
-                    content_type="application/xml",
-                    status=403,
-                )
-
         # Extract fields (parse_qs returns lists)
         from_number = (form.get("From", [""]))[0].strip()
         to_number = (form.get("To", [""]))[0].strip()
@@ -333,7 +236,7 @@ class SmsAdapter(BasePlatformAdapter):
 
         # Ignore messages from our own number (echo prevention)
         if from_number == self._from_number:
-            logger.debug("[sms] ignoring echo from own number %s", redact_phone(from_number))
+            logger.debug("[sms] ignoring echo from own number %s", _redact_phone(from_number))
             return web.Response(
                 text='<?xml version="1.0" encoding="UTF-8"?><Response></Response>',
                 content_type="application/xml",
@@ -341,8 +244,8 @@ class SmsAdapter(BasePlatformAdapter):
 
         logger.info(
             "[sms] inbound from %s -> %s: %s",
-            redact_phone(from_number),
-            redact_phone(to_number),
+            _redact_phone(from_number),
+            _redact_phone(to_number),
             text[:80],
         )
 

gateway/platforms/telegram.py

@@ -65,10 +65,7 @@ from gateway.platforms.base import (
     cache_image_from_bytes,
     cache_audio_from_bytes,
     cache_document_from_bytes,
-    resolve_proxy_url,
     SUPPORTED_DOCUMENT_TYPES,
-    utf16_len,
-    _prefix_within_utf16_limit,
 )
 from gateway.platforms.telegram_network import (
     TelegramFallbackTransport,
@@ -150,6 +147,7 @@ class TelegramAdapter(BasePlatformAdapter):
         self._text_batch_split_delay_seconds = float(os.getenv("HERMES_TELEGRAM_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0"))
         self._pending_text_batches: Dict[str, MessageEvent] = {}
         self._pending_text_batch_tasks: Dict[str, asyncio.Task] = {}
+        self._token_lock_identity: Optional[str] = None
         self._polling_error_task: Optional[asyncio.Task] = None
         self._polling_conflict_count: int = 0
         self._polling_network_error_count: int = 0
@@ -302,11 +300,9 @@ class TelegramAdapter(BasePlatformAdapter):
 
         # Exhausted retries — fatal
         message = (
-            "Another process is already polling this Telegram bot token "
-            "(possibly OpenClaw or another Hermes instance). "
+            "Another Telegram bot poller is already using this token. "
             "Hermes stopped Telegram polling after %d retries. "
-            "Only one poller can run per token — stop the other process "
-            "and restart with 'hermes start'."
+            "Make sure only one gateway instance is running for this bot token."
             % MAX_CONFLICT_RETRIES
         )
         logger.error("[%s] %s Original error: %s", self.name, message, error)
@@ -501,7 +497,23 @@ class TelegramAdapter(BasePlatformAdapter):
             return False
         
         try:
-            if not self._acquire_platform_lock('telegram-bot-token', self.config.token, 'Telegram bot token'):
+            from gateway.status import acquire_scoped_lock
+
+            self._token_lock_identity = self.config.token
+            acquired, existing = acquire_scoped_lock(
+                "telegram-bot-token",
+                self._token_lock_identity,
+                metadata={"platform": self.platform.value},
+            )
+            if not acquired:
+                owner_pid = existing.get("pid") if isinstance(existing, dict) else None
+                message = (
+                    "Another local Hermes gateway is already using this Telegram bot token"
+                    + (f" (PID {owner_pid})." if owner_pid else ".")
+                    + " Stop the other gateway before starting a second Telegram poller."
+                )
+                logger.error("[%s] %s", self.name, message)
+                self._set_fatal_error("telegram_token_lock", message, retryable=False)
                 return False
 
             # Build the application
@@ -540,7 +552,10 @@ class TelegramAdapter(BasePlatformAdapter):
                 "write_timeout": _env_float("HERMES_TELEGRAM_HTTP_WRITE_TIMEOUT", 20.0),
             }
 
-            proxy_url = resolve_proxy_url()
+            proxy_configured = any(
+                (os.getenv(k) or "").strip()
+                for k in ("HTTPS_PROXY", "HTTP_PROXY", "ALL_PROXY", "https_proxy", "http_proxy", "all_proxy")
+            )
             disable_fallback = (os.getenv("HERMES_TELEGRAM_DISABLE_FALLBACK_IPS", "").strip().lower() in ("1", "true", "yes", "on"))
             fallback_ips = self._fallback_ips()
             if not fallback_ips:
@@ -551,7 +566,7 @@ class TelegramAdapter(BasePlatformAdapter):
                     ", ".join(fallback_ips),
                 )
 
-            if fallback_ips and not proxy_url and not disable_fallback:
+            if fallback_ips and not proxy_configured and not disable_fallback:
                 logger.info(
                     "[%s] Telegram fallback IPs active: %s",
                     self.name,
@@ -567,12 +582,10 @@ class TelegramAdapter(BasePlatformAdapter):
                     **request_kwargs,
                     httpx_kwargs={"transport": TelegramFallbackTransport(fallback_ips)},
                 )
-            elif proxy_url:
-                logger.info("[%s] Proxy detected; passing explicitly to HTTPXRequest: %s", self.name, proxy_url)
-                request = HTTPXRequest(**request_kwargs, proxy=proxy_url)
-                get_updates_request = HTTPXRequest(**request_kwargs, proxy=proxy_url)
             else:
-                if disable_fallback:
+                if proxy_configured:
+                    logger.info("[%s] Proxy configured; skipping Telegram fallback-IP transport", self.name)
+                elif disable_fallback:
                     logger.info("[%s] Telegram fallback-IP transport disabled via env", self.name)
                 request = HTTPXRequest(**request_kwargs)
                 get_updates_request = HTTPXRequest(**request_kwargs)
@@ -724,7 +737,12 @@ class TelegramAdapter(BasePlatformAdapter):
             return True
             
         except Exception as e:
-            self._release_platform_lock()
+            if self._token_lock_identity:
+                try:
+                    from gateway.status import release_scoped_lock
+                    release_scoped_lock("telegram-bot-token", self._token_lock_identity)
+                except Exception:
+                    pass
             message = f"Telegram startup failed: {e}"
             self._set_fatal_error("telegram_connect_error", message, retryable=True)
             logger.error("[%s] Failed to connect to Telegram: %s", self.name, e, exc_info=True)
@@ -750,7 +768,12 @@ class TelegramAdapter(BasePlatformAdapter):
                 await self._app.shutdown()
             except Exception as e:
                 logger.warning("[%s] Error during Telegram disconnect: %s", self.name, e, exc_info=True)
-        self._release_platform_lock()
+        if self._token_lock_identity:
+            try:
+                from gateway.status import release_scoped_lock
+                release_scoped_lock("telegram-bot-token", self._token_lock_identity)
+            except Exception as e:
+                logger.warning("[%s] Error releasing Telegram token lock: %s", self.name, e, exc_info=True)
 
         for task in self._pending_photo_batch_tasks.values():
             if task and not task.done():
@@ -761,6 +784,7 @@ class TelegramAdapter(BasePlatformAdapter):
         self._mark_disconnected()
         self._app = None
         self._bot = None
+        self._token_lock_identity = None
         logger.info("[%s] Disconnected from Telegram", self.name)
 
     def _should_thread_reply(self, reply_to: Optional[str], chunk_index: int) -> bool:
@@ -801,9 +825,7 @@ class TelegramAdapter(BasePlatformAdapter):
         try:
             # Format and split message if needed
             formatted = self.format_message(content)
-            chunks = self.truncate_message(
-                formatted, self.MAX_MESSAGE_LENGTH, len_fn=utf16_len,
-            )
+            chunks = self.truncate_message(formatted, self.MAX_MESSAGE_LENGTH)
             if len(chunks) > 1:
                 # truncate_message appends a raw " (1/2)" suffix. Escape the
                 # MarkdownV2-special parentheses so Telegram doesn't reject the
@@ -974,9 +996,7 @@ class TelegramAdapter(BasePlatformAdapter):
             # streaming).  Truncate and succeed so the stream consumer can
             # split the overflow into a new message instead of dying.
             if "message_too_long" in err_str or "too long" in err_str:
-                truncated = _prefix_within_utf16_limit(
-                    content, self.MAX_MESSAGE_LENGTH - 20
-                ) + "…"
+                truncated = content[: self.MAX_MESSAGE_LENGTH - 20] + "…"
                 try:
                     await self._bot.edit_message_text(
                         chat_id=int(chat_id),

gateway/platforms/telegram_network.py

@@ -12,6 +12,7 @@ from __future__ import annotations
 import asyncio
 import ipaddress
 import logging
+import os
 import socket
 from typing import Iterable, Optional
 

gateway/platforms/webhook.py

@@ -27,6 +27,7 @@ import hashlib
 import hmac
 import json
 import logging
+import os
 import re
 import subprocess
 import time
@@ -200,7 +201,6 @@ class WebhookAdapter(BasePlatformAdapter):
             "dingtalk",
             "feishu",
             "wecom",
-            "wecom_callback",
             "weixin",
             "bluebubbles",
         ):

gateway/platforms/wecom.py

@@ -37,6 +37,7 @@ import logging
 import mimetypes
 import os
 import re
+import time
 import uuid
 from datetime import datetime, timezone
 from pathlib import Path
@@ -58,7 +59,6 @@ except ImportError:
     httpx = None  # type: ignore[assignment]
 
 from gateway.config import Platform, PlatformConfig
-from gateway.platforms.helpers import MessageDeduplicator
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
@@ -92,6 +92,7 @@ REQUEST_TIMEOUT_SECONDS = 15.0
 HEARTBEAT_INTERVAL_SECONDS = 30.0
 RECONNECT_BACKOFF = [2, 5, 10, 30, 60]
 
+DEDUP_WINDOW_SECONDS = 300
 DEDUP_MAX_SIZE = 1000
 
 IMAGE_MAX_BYTES = 10 * 1024 * 1024
@@ -171,7 +172,7 @@ class WeComAdapter(BasePlatformAdapter):
         self._listen_task: Optional[asyncio.Task] = None
         self._heartbeat_task: Optional[asyncio.Task] = None
         self._pending_responses: Dict[str, asyncio.Future] = {}
-        self._dedup = MessageDeduplicator(max_size=DEDUP_MAX_SIZE)
+        self._seen_messages: Dict[str, float] = {}
         self._reply_req_ids: Dict[str, str] = {}
 
         # Text batching: merge rapid successive messages (Telegram-style).
@@ -249,7 +250,7 @@ class WeComAdapter(BasePlatformAdapter):
             await self._http_client.aclose()
             self._http_client = None
 
-        self._dedup.clear()
+        self._seen_messages.clear()
         logger.info("[%s] Disconnected", self.name)
 
     async def _cleanup_ws(self) -> None:
@@ -265,7 +266,7 @@ class WeComAdapter(BasePlatformAdapter):
     async def _open_connection(self) -> None:
         """Open and authenticate a websocket connection."""
         await self._cleanup_ws()
-        self._session = aiohttp.ClientSession(trust_env=True)
+        self._session = aiohttp.ClientSession()
         self._ws = await self._session.ws_connect(
             self._ws_url,
             heartbeat=HEARTBEAT_INTERVAL_SECONDS * 2,
@@ -475,7 +476,7 @@ class WeComAdapter(BasePlatformAdapter):
             return
 
         msg_id = str(body.get("msgid") or self._payload_req_id(payload) or uuid.uuid4().hex)
-        if self._dedup.is_duplicate(msg_id):
+        if self._is_duplicate(msg_id):
             logger.debug("[%s] Duplicate message %s ignored", self.name, msg_id)
             return
         self._remember_reply_req_id(msg_id, self._payload_req_id(payload))
@@ -635,13 +636,6 @@ class WeComAdapter(BasePlatformAdapter):
                 if voice_text:
                     text_parts.append(voice_text)
 
-            # Extract appmsg title (filename) for WeCom AI Bot attachments
-            if msgtype == "appmsg":
-                appmsg = body.get("appmsg") if isinstance(body.get("appmsg"), dict) else {}
-                title = str(appmsg.get("title") or "").strip()
-                if title:
-                    text_parts.append(title)
-
         quote = body.get("quote") if isinstance(body.get("quote"), dict) else {}
         quote_type = str(quote.get("msgtype") or "").lower()
         if quote_type == "text":
@@ -674,13 +668,6 @@ class WeComAdapter(BasePlatformAdapter):
                 refs.append(("image", body["image"]))
             if msgtype == "file" and isinstance(body.get("file"), dict):
                 refs.append(("file", body["file"]))
-            # Handle appmsg (WeCom AI Bot attachments with PDF/Word/Excel)
-            if msgtype == "appmsg" and isinstance(body.get("appmsg"), dict):
-                appmsg = body["appmsg"]
-                if isinstance(appmsg.get("file"), dict):
-                    refs.append(("file", appmsg["file"]))
-                elif isinstance(appmsg.get("image"), dict):
-                    refs.append(("image", appmsg["image"]))
 
         quote = body.get("quote") if isinstance(body.get("quote"), dict) else {}
         quote_type = str(quote.get("msgtype") or "").lower()
@@ -838,6 +825,24 @@ class WeComAdapter(BasePlatformAdapter):
         wildcard = self._groups.get("*")
         return wildcard if isinstance(wildcard, dict) else {}
 
+    def _is_duplicate(self, msg_id: str) -> bool:
+        now = time.time()
+        if len(self._seen_messages) > DEDUP_MAX_SIZE:
+            cutoff = now - DEDUP_WINDOW_SECONDS
+            self._seen_messages = {
+                key: ts for key, ts in self._seen_messages.items() if ts > cutoff
+            }
+            if self._reply_req_ids:
+                self._reply_req_ids = {
+                    key: value for key, value in self._reply_req_ids.items() if key in self._seen_messages
+                }
+
+        if msg_id in self._seen_messages:
+            return True
+
+        self._seen_messages[msg_id] = now
+        return False
+
     def _remember_reply_req_id(self, message_id: str, req_id: str) -> None:
         normalized_message_id = str(message_id or "").strip()
         normalized_req_id = str(req_id or "").strip()

gateway/platforms/wecom_callback.py

@@ -1,387 +0,0 @@
-"""WeCom callback-mode adapter for self-built enterprise applications.
-
-Unlike the bot/websocket adapter in ``wecom.py``, this handles the standard
-WeCom callback flow: WeCom POSTs encrypted XML to an HTTP endpoint, the
-adapter decrypts it, queues the message for the agent, and immediately
-acknowledges.  The agent's reply is delivered later via the proactive
-``message/send`` API using an access-token.
-
-Supports multiple self-built apps under one gateway instance, scoped by
-``corp_id:user_id`` to avoid cross-corp collisions.
-"""
-
-from __future__ import annotations
-
-import asyncio
-import logging
-import socket as _socket
-import time
-from typing import Any, Dict, List, Optional
-from xml.etree import ElementTree as ET
-
-try:
-    from aiohttp import web
-
-    AIOHTTP_AVAILABLE = True
-except ImportError:
-    web = None  # type: ignore[assignment]
-    AIOHTTP_AVAILABLE = False
-
-try:
-    import httpx
-
-    HTTPX_AVAILABLE = True
-except ImportError:
-    httpx = None  # type: ignore[assignment]
-    HTTPX_AVAILABLE = False
-
-from gateway.config import Platform, PlatformConfig
-from gateway.platforms.base import BasePlatformAdapter, MessageEvent, MessageType, SendResult
-from gateway.platforms.wecom_crypto import WXBizMsgCrypt, WeComCryptoError
-
-logger = logging.getLogger(__name__)
-
-DEFAULT_HOST = "0.0.0.0"
-DEFAULT_PORT = 8645
-DEFAULT_PATH = "/wecom/callback"
-ACCESS_TOKEN_TTL_SECONDS = 7200
-MESSAGE_DEDUP_TTL_SECONDS = 300
-
-
-def check_wecom_callback_requirements() -> bool:
-    return AIOHTTP_AVAILABLE and HTTPX_AVAILABLE
-
-
-class WecomCallbackAdapter(BasePlatformAdapter):
-    def __init__(self, config: PlatformConfig):
-        super().__init__(config, Platform.WECOM_CALLBACK)
-        extra = config.extra or {}
-        self._host = str(extra.get("host") or DEFAULT_HOST)
-        self._port = int(extra.get("port") or DEFAULT_PORT)
-        self._path = str(extra.get("path") or DEFAULT_PATH)
-        self._apps: List[Dict[str, Any]] = self._normalize_apps(extra)
-        self._runner: Optional[web.AppRunner] = None
-        self._site: Optional[web.TCPSite] = None
-        self._app: Optional[web.Application] = None
-        self._http_client: Optional[httpx.AsyncClient] = None
-        self._message_queue: asyncio.Queue[MessageEvent] = asyncio.Queue()
-        self._poll_task: Optional[asyncio.Task] = None
-        self._seen_messages: Dict[str, float] = {}
-        self._user_app_map: Dict[str, str] = {}
-        self._access_tokens: Dict[str, Dict[str, Any]] = {}
-
-    # ------------------------------------------------------------------
-    # App normalisation
-    # ------------------------------------------------------------------
-
-    @staticmethod
-    def _user_app_key(corp_id: str, user_id: str) -> str:
-        return f"{corp_id}:{user_id}" if corp_id else user_id
-
-    @staticmethod
-    def _normalize_apps(extra: Dict[str, Any]) -> List[Dict[str, Any]]:
-        apps = extra.get("apps")
-        if isinstance(apps, list) and apps:
-            return [dict(app) for app in apps if isinstance(app, dict)]
-        if extra.get("corp_id"):
-            return [
-                {
-                    "name": extra.get("name") or "default",
-                    "corp_id": extra.get("corp_id", ""),
-                    "corp_secret": extra.get("corp_secret", ""),
-                    "agent_id": str(extra.get("agent_id", "")),
-                    "token": extra.get("token", ""),
-                    "encoding_aes_key": extra.get("encoding_aes_key", ""),
-                }
-            ]
-        return []
-
-    # ------------------------------------------------------------------
-    # Lifecycle
-    # ------------------------------------------------------------------
-
-    async def connect(self) -> bool:
-        if not self._apps:
-            logger.warning("[WecomCallback] No callback apps configured")
-            return False
-        if not check_wecom_callback_requirements():
-            logger.warning("[WecomCallback] aiohttp/httpx not installed")
-            return False
-
-        # Quick port-in-use check.
-        try:
-            with _socket.socket(_socket.AF_INET, _socket.SOCK_STREAM) as sock:
-                sock.settimeout(1)
-                sock.connect(("127.0.0.1", self._port))
-            logger.error("[WecomCallback] Port %d already in use", self._port)
-            return False
-        except (ConnectionRefusedError, OSError):
-            pass
-
-        try:
-            self._http_client = httpx.AsyncClient(timeout=20.0)
-            self._app = web.Application()
-            self._app.router.add_get("/health", self._handle_health)
-            self._app.router.add_get(self._path, self._handle_verify)
-            self._app.router.add_post(self._path, self._handle_callback)
-            self._runner = web.AppRunner(self._app)
-            await self._runner.setup()
-            self._site = web.TCPSite(self._runner, self._host, self._port)
-            await self._site.start()
-            self._poll_task = asyncio.create_task(self._poll_loop())
-            self._mark_connected()
-            logger.info(
-                "[WecomCallback] HTTP server listening on %s:%s%s",
-                self._host, self._port, self._path,
-            )
-            for app in self._apps:
-                try:
-                    await self._refresh_access_token(app)
-                except Exception as exc:
-                    logger.warning(
-                        "[WecomCallback] Initial token refresh failed for app '%s': %s",
-                        app.get("name", "default"), exc,
-                    )
-            return True
-        except Exception:
-            await self._cleanup()
-            logger.exception("[WecomCallback] Failed to start")
-            return False
-
-    async def disconnect(self) -> None:
-        self._running = False
-        if self._poll_task:
-            self._poll_task.cancel()
-            try:
-                await self._poll_task
-            except asyncio.CancelledError:
-                pass
-            self._poll_task = None
-        await self._cleanup()
-        self._mark_disconnected()
-        logger.info("[WecomCallback] Disconnected")
-
-    async def _cleanup(self) -> None:
-        self._site = None
-        if self._runner:
-            await self._runner.cleanup()
-            self._runner = None
-        self._app = None
-        if self._http_client:
-            await self._http_client.aclose()
-            self._http_client = None
-
-    # ------------------------------------------------------------------
-    # Outbound: proactive send via access-token API
-    # ------------------------------------------------------------------
-
-    async def send(
-        self,
-        chat_id: str,
-        content: str,
-        reply_to: Optional[str] = None,
-        metadata: Optional[Dict[str, Any]] = None,
-    ) -> SendResult:
-        app = self._resolve_app_for_chat(chat_id)
-        touser = chat_id.split(":", 1)[1] if ":" in chat_id else chat_id
-        try:
-            token = await self._get_access_token(app)
-            payload = {
-                "touser": touser,
-                "msgtype": "text",
-                "agentid": int(str(app.get("agent_id") or 0)),
-                "text": {"content": content[:2048]},
-                "safe": 0,
-            }
-            resp = await self._http_client.post(
-                f"https://qyapi.weixin.qq.com/cgi-bin/message/send?access_token={token}",
-                json=payload,
-            )
-            data = resp.json()
-            if data.get("errcode") != 0:
-                return SendResult(success=False, error=str(data))
-            return SendResult(
-                success=True,
-                message_id=str(data.get("msgid", "")),
-                raw_response=data,
-            )
-        except Exception as exc:
-            return SendResult(success=False, error=str(exc))
-
-    def _resolve_app_for_chat(self, chat_id: str) -> Dict[str, Any]:
-        """Pick the app associated with *chat_id*, falling back sensibly."""
-        app_name = self._user_app_map.get(chat_id)
-        if not app_name and ":" not in chat_id:
-            # Legacy bare user_id — try to find a unique match.
-            matching = [k for k in self._user_app_map if k.endswith(f":{chat_id}")]
-            if len(matching) == 1:
-                app_name = self._user_app_map.get(matching[0])
-        app = self._get_app_by_name(app_name) if app_name else None
-        return app or self._apps[0]
-
-    async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
-        return {"name": chat_id, "type": "dm"}
-
-    # ------------------------------------------------------------------
-    # Inbound: HTTP callback handlers
-    # ------------------------------------------------------------------
-
-    async def _handle_health(self, request: web.Request) -> web.Response:
-        return web.json_response({"status": "ok", "platform": "wecom_callback"})
-
-    async def _handle_verify(self, request: web.Request) -> web.Response:
-        """GET endpoint — WeCom URL verification handshake."""
-        msg_signature = request.query.get("msg_signature", "")
-        timestamp = request.query.get("timestamp", "")
-        nonce = request.query.get("nonce", "")
-        echostr = request.query.get("echostr", "")
-        for app in self._apps:
-            try:
-                crypt = self._crypt_for_app(app)
-                plain = crypt.verify_url(msg_signature, timestamp, nonce, echostr)
-                return web.Response(text=plain, content_type="text/plain")
-            except Exception:
-                continue
-        return web.Response(status=403, text="signature verification failed")
-
-    async def _handle_callback(self, request: web.Request) -> web.Response:
-        """POST endpoint — receive an encrypted message callback."""
-        msg_signature = request.query.get("msg_signature", "")
-        timestamp = request.query.get("timestamp", "")
-        nonce = request.query.get("nonce", "")
-        body = await request.text()
-
-        for app in self._apps:
-            try:
-                decrypted = self._decrypt_request(
-                    app, body, msg_signature, timestamp, nonce,
-                )
-                event = self._build_event(app, decrypted)
-                if event is not None:
-                    # Record which app this user belongs to.
-                    if event.source and event.source.user_id:
-                        map_key = self._user_app_key(
-                            str(app.get("corp_id") or ""), event.source.user_id,
-                        )
-                        self._user_app_map[map_key] = app["name"]
-                    await self._message_queue.put(event)
-                # Immediately acknowledge — the agent's reply will arrive
-                # later via the proactive message/send API.
-                return web.Response(text="success", content_type="text/plain")
-            except WeComCryptoError:
-                continue
-            except Exception:
-                logger.exception("[WecomCallback] Error handling message")
-                break
-        return web.Response(status=400, text="invalid callback payload")
-
-    async def _poll_loop(self) -> None:
-        """Drain the message queue and dispatch to the gateway runner."""
-        while True:
-            event = await self._message_queue.get()
-            try:
-                task = asyncio.create_task(self.handle_message(event))
-                self._background_tasks.add(task)
-                task.add_done_callback(self._background_tasks.discard)
-            except Exception:
-                logger.exception("[WecomCallback] Failed to enqueue event")
-
-    # ------------------------------------------------------------------
-    # XML / crypto helpers
-    # ------------------------------------------------------------------
-
-    def _decrypt_request(
-        self, app: Dict[str, Any], body: str,
-        msg_signature: str, timestamp: str, nonce: str,
-    ) -> str:
-        root = ET.fromstring(body)
-        encrypt = root.findtext("Encrypt", default="")
-        crypt = self._crypt_for_app(app)
-        return crypt.decrypt(msg_signature, timestamp, nonce, encrypt).decode("utf-8")
-
-    def _build_event(self, app: Dict[str, Any], xml_text: str) -> Optional[MessageEvent]:
-        root = ET.fromstring(xml_text)
-        msg_type = (root.findtext("MsgType") or "").lower()
-        # Silently acknowledge lifecycle events.
-        if msg_type == "event":
-            event_name = (root.findtext("Event") or "").lower()
-            if event_name in {"enter_agent", "subscribe"}:
-                return None
-        if msg_type not in {"text", "event"}:
-            return None
-
-        user_id = root.findtext("FromUserName", default="")
-        corp_id = root.findtext("ToUserName", default=app.get("corp_id", ""))
-        scoped_chat_id = self._user_app_key(corp_id, user_id)
-        content = root.findtext("Content", default="").strip()
-        if not content and msg_type == "event":
-            content = "/start"
-        msg_id = (
-            root.findtext("MsgId")
-            or f"{user_id}:{root.findtext('CreateTime', default='0')}"
-        )
-        source = self.build_source(
-            chat_id=scoped_chat_id,
-            chat_name=user_id,
-            chat_type="dm",
-            user_id=user_id,
-            user_name=user_id,
-        )
-        return MessageEvent(
-            text=content,
-            message_type=MessageType.TEXT,
-            source=source,
-            raw_message=xml_text,
-            message_id=msg_id,
-        )
-
-    def _crypt_for_app(self, app: Dict[str, Any]) -> WXBizMsgCrypt:
-        return WXBizMsgCrypt(
-            token=str(app.get("token") or ""),
-            encoding_aes_key=str(app.get("encoding_aes_key") or ""),
-            receive_id=str(app.get("corp_id") or ""),
-        )
-
-    def _get_app_by_name(self, name: Optional[str]) -> Optional[Dict[str, Any]]:
-        if not name:
-            return None
-        for app in self._apps:
-            if app.get("name") == name:
-                return app
-        return None
-
-    # ------------------------------------------------------------------
-    # Access-token management
-    # ------------------------------------------------------------------
-
-    async def _get_access_token(self, app: Dict[str, Any]) -> str:
-        cached = self._access_tokens.get(app["name"])
-        now = time.time()
-        if cached and cached.get("expires_at", 0) > now + 60:
-            return cached["token"]
-        return await self._refresh_access_token(app)
-
-    async def _refresh_access_token(self, app: Dict[str, Any]) -> str:
-        resp = await self._http_client.get(
-            "https://qyapi.weixin.qq.com/cgi-bin/gettoken",
-            params={
-                "corpid": app.get("corp_id"),
-                "corpsecret": app.get("corp_secret"),
-            },
-        )
-        data = resp.json()
-        if data.get("errcode") != 0:
-            raise RuntimeError(f"WeCom token refresh failed: {data}")
-        token = data["access_token"]
-        expires_in = int(data.get("expires_in", ACCESS_TOKEN_TTL_SECONDS))
-        self._access_tokens[app["name"]] = {
-            "token": token,
-            "expires_at": time.time() + expires_in,
-        }
-        logger.info(
-            "[WecomCallback] Token refreshed for app '%s' (corp=%s), expires in %ss",
-            app.get("name", "default"),
-            app.get("corp_id", ""),
-            expires_in,
-        )
-        return token

gateway/platforms/wecom_crypto.py

@@ -1,142 +0,0 @@
-"""WeCom BizMsgCrypt-compatible AES-CBC encryption for callback mode.
-
-Implements the same wire format as Tencent's official ``WXBizMsgCrypt``
-SDK so that WeCom can verify, encrypt, and decrypt callback payloads.
-"""
-
-from __future__ import annotations
-
-import base64
-import hashlib
-import os
-import secrets
-import socket
-import struct
-from typing import Optional
-from xml.etree import ElementTree as ET
-
-from cryptography.hazmat.backends import default_backend
-from cryptography.hazmat.primitives.ciphers import Cipher, algorithms, modes
-
-
-class WeComCryptoError(Exception):
-    pass
-
-
-class SignatureError(WeComCryptoError):
-    pass
-
-
-class DecryptError(WeComCryptoError):
-    pass
-
-
-class EncryptError(WeComCryptoError):
-    pass
-
-
-class PKCS7Encoder:
-    block_size = 32
-
-    @classmethod
-    def encode(cls, text: bytes) -> bytes:
-        amount_to_pad = cls.block_size - (len(text) % cls.block_size)
-        if amount_to_pad == 0:
-            amount_to_pad = cls.block_size
-        pad = bytes([amount_to_pad]) * amount_to_pad
-        return text + pad
-
-    @classmethod
-    def decode(cls, decrypted: bytes) -> bytes:
-        if not decrypted:
-            raise DecryptError("empty decrypted payload")
-        pad = decrypted[-1]
-        if pad < 1 or pad > cls.block_size:
-            raise DecryptError("invalid PKCS7 padding")
-        if decrypted[-pad:] != bytes([pad]) * pad:
-            raise DecryptError("malformed PKCS7 padding")
-        return decrypted[:-pad]
-
-
-def _sha1_signature(token: str, timestamp: str, nonce: str, encrypt: str) -> str:
-    parts = sorted([token, timestamp, nonce, encrypt])
-    return hashlib.sha1("".join(parts).encode("utf-8")).hexdigest()
-
-
-class WXBizMsgCrypt:
-    """Minimal WeCom callback crypto helper compatible with BizMsgCrypt semantics."""
-
-    def __init__(self, token: str, encoding_aes_key: str, receive_id: str):
-        if not token:
-            raise ValueError("token is required")
-        if not encoding_aes_key:
-            raise ValueError("encoding_aes_key is required")
-        if len(encoding_aes_key) != 43:
-            raise ValueError("encoding_aes_key must be 43 chars")
-        if not receive_id:
-            raise ValueError("receive_id is required")
-
-        self.token = token
-        self.receive_id = receive_id
-        self.key = base64.b64decode(encoding_aes_key + "=")
-        self.iv = self.key[:16]
-
-    def verify_url(self, msg_signature: str, timestamp: str, nonce: str, echostr: str) -> str:
-        plain = self.decrypt(msg_signature, timestamp, nonce, echostr)
-        return plain.decode("utf-8")
-
-    def decrypt(self, msg_signature: str, timestamp: str, nonce: str, encrypt: str) -> bytes:
-        expected = _sha1_signature(self.token, timestamp, nonce, encrypt)
-        if expected != msg_signature:
-            raise SignatureError("signature mismatch")
-        try:
-            cipher_text = base64.b64decode(encrypt)
-        except Exception as exc:
-            raise DecryptError(f"invalid base64 payload: {exc}") from exc
-        try:
-            cipher = Cipher(algorithms.AES(self.key), modes.CBC(self.iv), backend=default_backend())
-            decryptor = cipher.decryptor()
-            padded = decryptor.update(cipher_text) + decryptor.finalize()
-            plain = PKCS7Encoder.decode(padded)
-            content = plain[16:]  # skip 16-byte random prefix
-            xml_length = socket.ntohl(struct.unpack("I", content[:4])[0])
-            xml_content = content[4:4 + xml_length]
-            receive_id = content[4 + xml_length:].decode("utf-8")
-        except WeComCryptoError:
-            raise
-        except Exception as exc:
-            raise DecryptError(f"decrypt failed: {exc}") from exc
-
-        if receive_id != self.receive_id:
-            raise DecryptError("receive_id mismatch")
-        return xml_content
-
-    def encrypt(self, plaintext: str, nonce: Optional[str] = None, timestamp: Optional[str] = None) -> str:
-        nonce = nonce or self._random_nonce()
-        timestamp = timestamp or str(int(__import__("time").time()))
-        encrypt = self._encrypt_bytes(plaintext.encode("utf-8"))
-        signature = _sha1_signature(self.token, timestamp, nonce, encrypt)
-        root = ET.Element("xml")
-        ET.SubElement(root, "Encrypt").text = encrypt
-        ET.SubElement(root, "MsgSignature").text = signature
-        ET.SubElement(root, "TimeStamp").text = timestamp
-        ET.SubElement(root, "Nonce").text = nonce
-        return ET.tostring(root, encoding="unicode")
-
-    def _encrypt_bytes(self, raw: bytes) -> str:
-        try:
-            random_prefix = os.urandom(16)
-            msg_len = struct.pack("I", socket.htonl(len(raw)))
-            payload = random_prefix + msg_len + raw + self.receive_id.encode("utf-8")
-            padded = PKCS7Encoder.encode(payload)
-            cipher = Cipher(algorithms.AES(self.key), modes.CBC(self.iv), backend=default_backend())
-            encryptor = cipher.encryptor()
-            encrypted = encryptor.update(padded) + encryptor.finalize()
-            return base64.b64encode(encrypted).decode("utf-8")
-        except Exception as exc:
-            raise EncryptError(f"encrypt failed: {exc}") from exc
-
-    @staticmethod
-    def _random_nonce(length: int = 10) -> str:
-        alphabet = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
-        return "".join(secrets.choice(alphabet) for _ in range(length))

gateway/platforms/weixin.py

@@ -53,7 +53,6 @@ except ImportError:  # pragma: no cover - dependency gate
     CRYPTO_AVAILABLE = False
 
 from gateway.config import Platform, PlatformConfig
-from gateway.platforms.helpers import MessageDeduplicator
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
@@ -64,7 +63,6 @@ from gateway.platforms.base import (
     cache_image_from_bytes,
 )
 from hermes_constants import get_hermes_home
-from utils import atomic_json_write
 
 ILINK_BASE_URL = "https://ilinkai.weixin.qq.com"
 WEIXIN_CDN_BASE_URL = "https://novac2c.cdn.weixin.qq.com/c2c"
@@ -112,7 +110,6 @@ TYPING_STOP = 2
 _HEADER_RE = re.compile(r"^(#{1,6})\s+(.+?)\s*$")
 _TABLE_RULE_RE = re.compile(r"^\s*\|?(?:\s*:?-{3,}:?\s*\|)+\s*:?-{3,}:?\s*\|?\s*$")
 _FENCE_RE = re.compile(r"^```([^\n`]*)\s*$")
-_MARKDOWN_LINK_RE = re.compile(r"\[([^\]]+)\]\(([^)]+)\)")
 
 
 def check_weixin_requirements() -> bool:
@@ -209,7 +206,7 @@ def save_weixin_account(
         "saved_at": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
     }
     path = _account_file(hermes_home, account_id)
-    atomic_json_write(path, payload)
+    path.write_text(json.dumps(payload, indent=2), encoding="utf-8")
     try:
         path.chmod(0o600)
     except OSError:
@@ -272,7 +269,7 @@ class ContextTokenStore:
             if key.startswith(prefix)
         }
         try:
-            atomic_json_write(self._path(account_id), payload)
+            self._path(account_id).write_text(json.dumps(payload), encoding="utf-8")
         except Exception as exc:
             logger.warning("weixin: failed to persist context tokens for %s: %s", _safe_id(account_id), exc)
 
@@ -399,16 +396,15 @@ async def _send_message(
     context_token: Optional[str],
     client_id: str,
 ) -> None:
-    if not text or not text.strip():
-        raise ValueError("_send_message: text must not be empty")
     message: Dict[str, Any] = {
         "from_user_id": "",
         "to_user_id": to,
         "client_id": client_id,
         "message_type": MSG_TYPE_BOT,
         "message_state": MSG_STATE_FINISH,
-        "item_list": [{"type": ITEM_TEXT, "text_item": {"text": text}}],
     }
+    if text:
+        message["item_list"] = [{"type": ITEM_TEXT, "text_item": {"text": text}}]
     if context_token:
         message["context_token"] = context_token
     await _api_post(
@@ -501,15 +497,13 @@ async def _upload_ciphertext(
     session: "aiohttp.ClientSession",
     *,
     ciphertext: bytes,
-    upload_url: str,
+    cdn_base_url: str,
+    upload_param: str,
+    filekey: str,
 ) -> str:
-    """Upload encrypted media to the CDN.
-
-    Accepts either a constructed CDN URL (from upload_param) or a direct
-    upload_full_url — both use POST with the raw ciphertext as the body.
-    """
+    url = _cdn_upload_url(cdn_base_url, upload_param, filekey)
     timeout = aiohttp.ClientTimeout(total=120)
-    async with session.post(upload_url, data=ciphertext, headers={"Content-Type": "application/octet-stream"}, timeout=timeout) as response:
+    async with session.post(url, data=ciphertext, headers={"Content-Type": "application/octet-stream"}, timeout=timeout) as response:
         if response.status == 200:
             encrypted_param = response.headers.get("x-encrypted-param")
             if encrypted_param:
@@ -653,7 +647,7 @@ def _normalize_markdown_blocks(content: str) -> str:
             result.append(_rewrite_table_block_for_weixin(table_lines))
             continue
 
-        result.append(_MARKDOWN_LINK_RE.sub(r"\1 (\2)", _rewrite_headers_for_weixin(line)))
+        result.append(_rewrite_headers_for_weixin(line))
         i += 1
 
     normalized = "\n".join(item.rstrip() for item in result)
@@ -738,42 +732,6 @@ def _split_delivery_units_for_weixin(content: str) -> List[str]:
     return [unit for unit in units if unit]
 
 
-def _looks_like_chatty_line_for_weixin(line: str) -> bool:
-    """Return True when a line looks like a standalone chat utterance."""
-    stripped = line.strip()
-    if not stripped:
-        return False
-    if len(stripped) > 48:
-        return False
-    if line.startswith((" ", "\t")):
-        return False
-    if stripped.startswith((">", "-", "*", "【")):
-        return False
-    if re.match(r"^\*\*[^*]+\*\*$", stripped):
-        return False
-    if re.match(r"^\d+\.\s", stripped):
-        return False
-    return True
-
-
-def _looks_like_heading_line_for_weixin(line: str) -> bool:
-    """Return True when a short line behaves like a plain-text heading."""
-    stripped = line.strip()
-    if not stripped:
-        return False
-    return len(stripped) <= 24 and stripped.endswith((":", "："))
-
-
-def _should_split_short_chat_block_for_weixin(block: str) -> bool:
-    """Split only chat-like multiline blocks into separate bubbles."""
-    lines = [line for line in block.splitlines() if line.strip()]
-    if not 2 <= len(lines) <= 6:
-        return False
-    if _looks_like_heading_line_for_weixin(lines[0]):
-        return False
-    return all(_looks_like_chatty_line_for_weixin(line) for line in lines)
-
-
 def _pack_markdown_blocks_for_weixin(content: str, max_length: int) -> List[str]:
     if len(content) <= max_length:
         return [content]
@@ -797,66 +755,23 @@ def _pack_markdown_blocks_for_weixin(content: str, max_length: int) -> List[str]
     return packed
 
 
-def _split_text_for_weixin_delivery(
-    content: str, max_length: int, split_per_line: bool = False,
-) -> List[str]:
+def _split_text_for_weixin_delivery(content: str, max_length: int) -> List[str]:
     """Split content into sequential Weixin messages.
 
-    *compact* (default): Keep everything in a single message whenever it fits
-    within the platform limit, even when the author used explicit line breaks.
-    Only fall back to block-aware packing when the payload exceeds
-    ``max_length``.
-
-    *per_line* (``split_per_line=True``): Legacy behavior — top-level line
-    breaks become separate chat messages; oversized units still use
-    block-aware packing.
-
-    The active mode is controlled via ``config.yaml`` ->
-    ``platforms.weixin.extra.split_multiline_messages`` (``true`` / ``false``)
-    or the env var ``WEIXIN_SPLIT_MULTILINE_MESSAGES``.
+    Prefer one message per top-level line/markdown unit when the author used
+    explicit line breaks. Oversized units fall back to block-aware packing so
+    long code fences still split safely.
     """
-    if not content:
-        return []
-    if split_per_line:
-        # Legacy: one message per top-level delivery unit.
-        if len(content) <= max_length and "\n" not in content:
-            return [content]
-        chunks: List[str] = []
-        for unit in _split_delivery_units_for_weixin(content):
-            if len(unit) <= max_length:
-                chunks.append(unit)
-                continue
-            chunks.extend(_pack_markdown_blocks_for_weixin(unit, max_length))
-        return [c for c in chunks if c] or [content]
+    if len(content) <= max_length and "\n" not in content:
+        return [content]
 
-    # Compact (default): single message when under the limit — unless the
-    # content looks like a short chatty exchange, in which case split into
-    # separate bubbles for a more natural chat feel.
-    if len(content) <= max_length:
-        return (
-            [u for u in _split_delivery_units_for_weixin(content) if u]
-            if _should_split_short_chat_block_for_weixin(content)
-            else [content]
-        )
-    return _pack_markdown_blocks_for_weixin(content, max_length) or [content]
-
-
-def _coerce_bool(value: Any, default: bool = True) -> bool:
-    """Coerce a config value to bool, tolerating strings like ``"true"``."""
-    if value is None:
-        return default
-    if isinstance(value, bool):
-        return value
-    if isinstance(value, (int, float)):
-        return bool(value)
-    text = str(value).strip().lower()
-    if not text:
-        return default
-    if text in {"1", "true", "yes", "on"}:
-        return True
-    if text in {"0", "false", "no", "off"}:
-        return False
-    return default
+    chunks: List[str] = []
+    for unit in _split_delivery_units_for_weixin(content):
+        if len(unit) <= max_length:
+            chunks.append(unit)
+            continue
+        chunks.extend(_pack_markdown_blocks_for_weixin(unit, max_length))
+    return chunks or [content]
 
 
 def _extract_text(item_list: List[Dict[str, Any]]) -> str:
@@ -918,7 +833,7 @@ def _load_sync_buf(hermes_home: str, account_id: str) -> str:
 
 def _save_sync_buf(hermes_home: str, account_id: str, sync_buf: str) -> None:
     path = _sync_buf_path(hermes_home, account_id)
-    atomic_json_write(path, {"get_updates_buf": sync_buf})
+    path.write_text(json.dumps({"get_updates_buf": sync_buf}), encoding="utf-8")
 
 
 async def qr_login(
@@ -935,7 +850,7 @@ async def qr_login(
     if not AIOHTTP_AVAILABLE:
         raise RuntimeError("aiohttp is required for Weixin QR login")
 
-    async with aiohttp.ClientSession(trust_env=True) as session:
+    async with aiohttp.ClientSession() as session:
         try:
             qr_resp = await _api_get(
                 session,
@@ -1048,10 +963,6 @@ class WeixinAdapter(BasePlatformAdapter):
 
     MAX_MESSAGE_LENGTH = 4000
 
-    # WeChat does not support editing sent messages — streaming must use the
-    # fallback "send-final-only" path so the cursor (▉) is never left visible.
-    SUPPORTS_MESSAGE_EDITING = False
-
     def __init__(self, config: PlatformConfig):
         super().__init__(config, Platform.WEIXIN)
         extra = config.extra or {}
@@ -1061,7 +972,8 @@ class WeixinAdapter(BasePlatformAdapter):
         self._typing_cache = TypingTicketCache()
         self._session: Optional[aiohttp.ClientSession] = None
         self._poll_task: Optional[asyncio.Task] = None
-        self._dedup = MessageDeduplicator(ttl_seconds=MESSAGE_DEDUP_TTL_SECONDS)
+        self._seen_messages: Dict[str, float] = {}
+        self._token_lock_identity: Optional[str] = None
 
         self._account_id = str(extra.get("account_id") or os.getenv("WEIXIN_ACCOUNT_ID", "")).strip()
         self._token = str(config.token or extra.get("token") or os.getenv("WEIXIN_TOKEN", "")).strip()
@@ -1069,16 +981,6 @@ class WeixinAdapter(BasePlatformAdapter):
         self._cdn_base_url = str(
             extra.get("cdn_base_url") or os.getenv("WEIXIN_CDN_BASE_URL", WEIXIN_CDN_BASE_URL)
         ).strip().rstrip("/")
-        self._send_chunk_delay_seconds = float(
-            extra.get("send_chunk_delay_seconds") or os.getenv("WEIXIN_SEND_CHUNK_DELAY_SECONDS", "0.35")
-        )
-        self._send_chunk_retries = int(
-            extra.get("send_chunk_retries") or os.getenv("WEIXIN_SEND_CHUNK_RETRIES", "2")
-        )
-        self._send_chunk_retry_delay_seconds = float(
-            extra.get("send_chunk_retry_delay_seconds")
-            or os.getenv("WEIXIN_SEND_CHUNK_RETRY_DELAY_SECONDS", "1.0")
-        )
         self._dm_policy = str(extra.get("dm_policy") or os.getenv("WEIXIN_DM_POLICY", "open")).strip().lower()
         self._group_policy = str(extra.get("group_policy") or os.getenv("WEIXIN_GROUP_POLICY", "disabled")).strip().lower()
         allow_from = extra.get("allow_from")
@@ -1089,11 +991,6 @@ class WeixinAdapter(BasePlatformAdapter):
             group_allow_from = os.getenv("WEIXIN_GROUP_ALLOWED_USERS", "")
         self._allow_from = self._coerce_list(allow_from)
         self._group_allow_from = self._coerce_list(group_allow_from)
-        self._split_multiline_messages = _coerce_bool(
-            extra.get("split_multiline_messages")
-            or os.getenv("WEIXIN_SPLIT_MULTILINE_MESSAGES"),
-            default=False,
-        )
 
         if self._account_id and not self._token:
             persisted = load_weixin_account(hermes_home, self._account_id)
@@ -1129,12 +1026,28 @@ class WeixinAdapter(BasePlatformAdapter):
             return False
 
         try:
-            if not self._acquire_platform_lock('weixin-bot-token', self._token, 'Weixin bot token'):
+            from gateway.status import acquire_scoped_lock
+
+            self._token_lock_identity = self._token
+            acquired, existing = acquire_scoped_lock(
+                "weixin-bot-token",
+                self._token_lock_identity,
+                metadata={"platform": self.platform.value},
+            )
+            if not acquired:
+                owner_pid = existing.get("pid") if isinstance(existing, dict) else None
+                message = (
+                    "Another local Hermes gateway is already using this Weixin token"
+                    + (f" (PID {owner_pid})." if owner_pid else ".")
+                    + " Stop the other gateway before starting a second Weixin poller."
+                )
+                logger.error("[%s] %s", self.name, message)
+                self._set_fatal_error("weixin_token_lock", message, retryable=False)
                 return False
         except Exception as exc:
             logger.debug("[%s] Token lock unavailable (non-fatal): %s", self.name, exc)
 
-        self._session = aiohttp.ClientSession(trust_env=True)
+        self._session = aiohttp.ClientSession()
         self._token_store.restore(self._account_id)
         self._poll_task = asyncio.create_task(self._poll_loop(), name="weixin-poll")
         self._mark_connected()
@@ -1153,7 +1066,12 @@ class WeixinAdapter(BasePlatformAdapter):
         if self._session and not self._session.closed:
             await self._session.close()
         self._session = None
-        self._release_platform_lock()
+        if self._token_lock_identity:
+            try:
+                from gateway.status import release_scoped_lock
+                release_scoped_lock("weixin-bot-token", self._token_lock_identity)
+            except Exception as exc:
+                logger.warning("[%s] Error releasing Weixin token lock: %s", self.name, exc, exc_info=True)
         self._mark_disconnected()
         logger.info("[%s] Disconnected", self.name)
 
@@ -1231,8 +1149,16 @@ class WeixinAdapter(BasePlatformAdapter):
             return
 
         message_id = str(message.get("message_id") or "").strip()
-        if message_id and self._dedup.is_duplicate(message_id):
-            return
+        if message_id:
+            now = time.time()
+            self._seen_messages = {
+                key: value
+                for key, value in self._seen_messages.items()
+                if now - value < MESSAGE_DEDUP_TTL_SECONDS
+            }
+            if message_id in self._seen_messages:
+                return
+            self._seen_messages[message_id] = now
 
         chat_type, effective_chat_id = _guess_chat_type(message, self._account_id)
         if chat_type == "group":
@@ -1404,50 +1330,7 @@ class WeixinAdapter(BasePlatformAdapter):
             logger.debug("[%s] getConfig failed for %s: %s", self.name, _safe_id(user_id), exc)
 
     def _split_text(self, content: str) -> List[str]:
-        return _split_text_for_weixin_delivery(
-            content, self.MAX_MESSAGE_LENGTH, self._split_multiline_messages,
-        )
-
-    async def _send_text_chunk(
-        self,
-        *,
-        chat_id: str,
-        chunk: str,
-        context_token: Optional[str],
-        client_id: str,
-    ) -> None:
-        """Send a single text chunk with per-chunk retry and backoff."""
-        last_error: Optional[Exception] = None
-        for attempt in range(self._send_chunk_retries + 1):
-            try:
-                await _send_message(
-                    self._session,
-                    base_url=self._base_url,
-                    token=self._token,
-                    to=chat_id,
-                    text=chunk,
-                    context_token=context_token,
-                    client_id=client_id,
-                )
-                return
-            except Exception as exc:
-                last_error = exc
-                if attempt >= self._send_chunk_retries:
-                    break
-                wait = self._send_chunk_retry_delay_seconds * (attempt + 1)
-                logger.warning(
-                    "[%s] send chunk failed to=%s attempt=%d/%d, retrying in %.2fs: %s",
-                    self.name,
-                    _safe_id(chat_id),
-                    attempt + 1,
-                    self._send_chunk_retries + 1,
-                    wait,
-                    exc,
-                )
-                if wait > 0:
-                    await asyncio.sleep(wait)
-        assert last_error is not None
-        raise last_error
+        return _split_text_for_weixin_delivery(content, self.MAX_MESSAGE_LENGTH)
 
     async def send(
         self,
@@ -1461,18 +1344,18 @@ class WeixinAdapter(BasePlatformAdapter):
         context_token = self._token_store.get(self._account_id, chat_id)
         last_message_id: Optional[str] = None
         try:
-            chunks = [c for c in self._split_text(self.format_message(content)) if c and c.strip()]
-            for idx, chunk in enumerate(chunks):
+            for chunk in self._split_text(self.format_message(content)):
                 client_id = f"hermes-weixin-{uuid.uuid4().hex}"
-                await self._send_text_chunk(
-                    chat_id=chat_id,
-                    chunk=chunk,
+                await _send_message(
+                    self._session,
+                    base_url=self._base_url,
+                    token=self._token,
+                    to=chat_id,
+                    text=chunk,
                     context_token=context_token,
                     client_id=client_id,
                 )
                 last_message_id = client_id
-                if idx < len(chunks) - 1 and self._send_chunk_delay_seconds > 0:
-                    await asyncio.sleep(self._send_chunk_delay_seconds)
             return SendResult(success=True, message_id=last_message_id)
         except Exception as exc:
             logger.error("[%s] send failed to=%s: %s", self.name, _safe_id(chat_id), exc)
@@ -1547,51 +1430,24 @@ class WeixinAdapter(BasePlatformAdapter):
         reply_to: Optional[str] = None,
         metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
-        return await self.send_document(chat_id, file_path=path, caption=caption, metadata=metadata)
+        return await self.send_document(chat_id, path, caption=caption, metadata=metadata)
 
     async def send_document(
         self,
         chat_id: str,
-        file_path: str,
+        path: str,
         caption: str = "",
         metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
         if not self._session or not self._token:
             return SendResult(success=False, error="Not connected")
         try:
-            message_id = await self._send_file(chat_id, file_path, caption)
+            message_id = await self._send_file(chat_id, path, caption)
             return SendResult(success=True, message_id=message_id)
         except Exception as exc:
             logger.error("[%s] send_document failed to=%s: %s", self.name, _safe_id(chat_id), exc)
             return SendResult(success=False, error=str(exc))
 
-    async def send_video(
-        self,
-        chat_id: str,
-        video_path: str,
-        caption: Optional[str] = None,
-        reply_to: Optional[str] = None,
-        metadata: Optional[Dict[str, Any]] = None,
-    ) -> SendResult:
-        if not self._session or not self._token:
-            return SendResult(success=False, error="Not connected")
-        try:
-            message_id = await self._send_file(chat_id, video_path, caption or "")
-            return SendResult(success=True, message_id=message_id)
-        except Exception as exc:
-            logger.error("[%s] send_video failed to=%s: %s", self.name, _safe_id(chat_id), exc)
-            return SendResult(success=False, error=str(exc))
-
-    async def send_voice(
-        self,
-        chat_id: str,
-        audio_path: str,
-        caption: Optional[str] = None,
-        reply_to: Optional[str] = None,
-        metadata: Optional[Dict[str, Any]] = None,
-    ) -> SendResult:
-        return await self.send_document(chat_id, audio_path, caption=caption or "", metadata=metadata)
-
     async def _download_remote_media(self, url: str) -> str:
         from tools.url_safety import is_safe_url
 
@@ -1614,7 +1470,6 @@ class WeixinAdapter(BasePlatformAdapter):
         filekey = secrets.token_hex(16)
         aes_key = secrets.token_bytes(16)
         rawsize = len(plaintext)
-        rawfilemd5 = hashlib.md5(plaintext).hexdigest()
         upload_response = await _get_upload_url(
             self._session,
             base_url=self._base_url,
@@ -1623,42 +1478,41 @@ class WeixinAdapter(BasePlatformAdapter):
             media_type=media_type,
             filekey=filekey,
             rawsize=rawsize,
-            rawfilemd5=rawfilemd5,
+            rawfilemd5=hashlib.md5(plaintext).hexdigest(),
             filesize=_aes_padded_size(rawsize),
             aeskey_hex=aes_key.hex(),
         )
         upload_param = str(upload_response.get("upload_param") or "")
         upload_full_url = str(upload_response.get("upload_full_url") or "")
         ciphertext = _aes128_ecb_encrypt(plaintext, aes_key)
-
-        # Prefer upload_full_url (direct CDN), fall back to constructed CDN URL
-        # from upload_param.  Both paths use POST — the old PUT for
-        # upload_full_url caused 404s on the WeChat CDN.
-        if upload_full_url:
-            upload_url = upload_full_url
-        elif upload_param:
-            upload_url = _cdn_upload_url(self._cdn_base_url, upload_param, filekey)
+        if upload_param:
+            encrypted_query_param = await _upload_ciphertext(
+                self._session,
+                ciphertext=ciphertext,
+                cdn_base_url=self._cdn_base_url,
+                upload_param=upload_param,
+                filekey=filekey,
+            )
+        elif upload_full_url:
+            timeout = aiohttp.ClientTimeout(total=120)
+            async with self._session.put(
+                upload_full_url,
+                data=ciphertext,
+                headers={"Content-Type": "application/octet-stream"},
+                timeout=timeout,
+            ) as response:
+                response.raise_for_status()
+                encrypted_query_param = response.headers.get("x-encrypted-param") or filekey
         else:
             raise RuntimeError(f"getUploadUrl returned neither upload_param nor upload_full_url: {upload_response}")
 
-        encrypted_query_param = await _upload_ciphertext(
-            self._session,
-            ciphertext=ciphertext,
-            upload_url=upload_url,
-        )
-
         context_token = self._token_store.get(self._account_id, chat_id)
-        # The iLink API expects aes_key as base64(hex_string), not base64(raw_bytes).
-        # Sending base64(raw_bytes) causes images to show as grey boxes on the
-        # receiver side because the decryption key doesn't match.
-        aes_key_for_api = base64.b64encode(aes_key.hex().encode("ascii")).decode("ascii")
         media_item = item_builder(
             encrypt_query_param=encrypted_query_param,
-            aes_key_for_api=aes_key_for_api,
+            aes_key_b64=base64.b64encode(aes_key).decode("ascii"),
             ciphertext_size=len(ciphertext),
             plaintext_size=rawsize,
             filename=Path(path).name,
-            rawfilemd5=rawfilemd5,
         )
 
         last_message_id = None
@@ -1698,53 +1552,39 @@ class WeixinAdapter(BasePlatformAdapter):
     def _outbound_media_builder(self, path: str):
         mime = mimetypes.guess_type(path)[0] or "application/octet-stream"
         if mime.startswith("image/"):
-            return MEDIA_IMAGE, lambda **kw: {
+            return MEDIA_IMAGE, lambda **kwargs: {
                 "type": ITEM_IMAGE,
                 "image_item": {
                     "media": {
-                        "encrypt_query_param": kw["encrypt_query_param"],
-                        "aes_key": kw["aes_key_for_api"],
+                        "encrypt_query_param": kwargs["encrypt_query_param"],
+                        "aes_key": kwargs["aes_key_b64"],
                         "encrypt_type": 1,
                     },
-                    "mid_size": kw["ciphertext_size"],
+                    "mid_size": kwargs["ciphertext_size"],
                 },
             }
         if mime.startswith("video/"):
-            return MEDIA_VIDEO, lambda **kw: {
+            return MEDIA_VIDEO, lambda **kwargs: {
                 "type": ITEM_VIDEO,
                 "video_item": {
                     "media": {
-                        "encrypt_query_param": kw["encrypt_query_param"],
-                        "aes_key": kw["aes_key_for_api"],
+                        "encrypt_query_param": kwargs["encrypt_query_param"],
+                        "aes_key": kwargs["aes_key_b64"],
                         "encrypt_type": 1,
                     },
-                    "video_size": kw["ciphertext_size"],
-                    "play_length": kw.get("play_length", 0),
-                    "video_md5": kw.get("rawfilemd5", ""),
+                    "video_size": kwargs["ciphertext_size"],
                 },
             }
-        if mime.startswith("audio/") or path.endswith(".silk"):
-            return MEDIA_VOICE, lambda **kw: {
-                "type": ITEM_VOICE,
-                "voice_item": {
-                    "media": {
-                        "encrypt_query_param": kw["encrypt_query_param"],
-                        "aes_key": kw["aes_key_for_api"],
-                        "encrypt_type": 1,
-                    },
-                    "playtime": kw.get("playtime", 0),
-                },
-            }
-        return MEDIA_FILE, lambda **kw: {
+        return MEDIA_FILE, lambda **kwargs: {
             "type": ITEM_FILE,
             "file_item": {
                 "media": {
-                    "encrypt_query_param": kw["encrypt_query_param"],
-                    "aes_key": kw["aes_key_for_api"],
+                    "encrypt_query_param": kwargs["encrypt_query_param"],
+                    "aes_key": kwargs["aes_key_b64"],
                     "encrypt_type": 1,
                 },
-                "file_name": kw["filename"],
-                "len": str(kw["plaintext_size"]),
+                "file_name": kwargs["filename"],
+                "len": str(kwargs["plaintext_size"]),
             },
         }
 
@@ -1784,7 +1624,7 @@ async def send_weixin_direct(
     token_store.restore(account_id)
     context_token = token_store.get(account_id, chat_id)
 
-    async with aiohttp.ClientSession(trust_env=True) as session:
+    async with aiohttp.ClientSession() as session:
         adapter = WeixinAdapter(
             PlatformConfig(
                 enabled=True,

gateway/platforms/whatsapp.py

@@ -120,9 +120,8 @@ class WhatsAppAdapter(BasePlatformAdapter):
     - session_path: Path to store WhatsApp session data
     """
     
-    # WhatsApp message limits — practical UX limit, not protocol max.
-    # WhatsApp allows ~65K but long messages are unreadable on mobile.
-    MAX_MESSAGE_LENGTH = 4096
+    # WhatsApp message limits
+    MAX_MESSAGE_LENGTH = 65536  # WhatsApp allows longer messages
     
     # Default bridge location relative to the hermes-agent install
     _DEFAULT_BRIDGE_DIR = Path(__file__).resolve().parents[2] / "scripts" / "whatsapp-bridge"
@@ -146,6 +145,7 @@ class WhatsAppAdapter(BasePlatformAdapter):
         self._bridge_log: Optional[Path] = None
         self._poll_task: Optional[asyncio.Task] = None
         self._http_session: Optional["aiohttp.ClientSession"] = None
+        self._session_lock_identity: Optional[str] = None
 
     def _whatsapp_require_mention(self) -> bool:
         configured = self.config.extra.get("require_mention")
@@ -290,7 +290,23 @@ class WhatsAppAdapter(BasePlatformAdapter):
         
         # Acquire scoped lock to prevent duplicate sessions
         try:
-            if not self._acquire_platform_lock('whatsapp-session', str(self._session_path), 'WhatsApp session'):
+            from gateway.status import acquire_scoped_lock
+
+            self._session_lock_identity = str(self._session_path)
+            acquired, existing = acquire_scoped_lock(
+                "whatsapp-session",
+                self._session_lock_identity,
+                metadata={"platform": self.platform.value},
+            )
+            if not acquired:
+                owner_pid = existing.get("pid") if isinstance(existing, dict) else None
+                message = (
+                    "Another local Hermes gateway is already using this WhatsApp session"
+                    + (f" (PID {owner_pid})." if owner_pid else ".")
+                    + " Stop the other gateway before starting a second WhatsApp bridge."
+                )
+                logger.error("[%s] %s", self.name, message)
+                self._set_fatal_error("whatsapp_session_lock", message, retryable=False)
                 return False
         except Exception as e:
             logger.warning("[%s] Could not acquire session lock (non-fatal): %s", self.name, e)
@@ -452,7 +468,12 @@ class WhatsAppAdapter(BasePlatformAdapter):
             return True
             
         except Exception as e:
-            self._release_platform_lock()
+            if self._session_lock_identity:
+                try:
+                    from gateway.status import release_scoped_lock
+                    release_scoped_lock("whatsapp-session", self._session_lock_identity)
+                except Exception:
+                    pass
             logger.error("[%s] Failed to start bridge: %s", self.name, e, exc_info=True)
             self._close_bridge_log()
             return False
@@ -525,70 +546,19 @@ class WhatsAppAdapter(BasePlatformAdapter):
             await self._http_session.close()
         self._http_session = None
 
-        self._release_platform_lock()
+        if self._session_lock_identity:
+            try:
+                from gateway.status import release_scoped_lock
+                release_scoped_lock("whatsapp-session", self._session_lock_identity)
+            except Exception as e:
+                logger.warning("[%s] Error releasing WhatsApp session lock: %s", self.name, e, exc_info=True)
 
         self._mark_disconnected()
         self._bridge_process = None
         self._close_bridge_log()
+        self._session_lock_identity = None
         print(f"[{self.name}] Disconnected")
     
-    def format_message(self, content: str) -> str:
-        """Convert standard markdown to WhatsApp-compatible formatting.
-
-        WhatsApp supports: *bold*, _italic_, ~strikethrough~, ```code```,
-        and monospaced `inline`. Standard markdown uses different syntax
-        for bold/italic/strikethrough, so we convert here.
-
-        Code blocks (``` fenced) and inline code (`) are protected from
-        conversion via placeholder substitution.
-        """
-        if not content:
-            return content
-
-        # --- 1. Protect fenced code blocks from formatting changes ---
-        _FENCE_PH = "\x00FENCE"
-        fences: list[str] = []
-
-        def _save_fence(m: re.Match) -> str:
-            fences.append(m.group(0))
-            return f"{_FENCE_PH}{len(fences) - 1}\x00"
-
-        result = re.sub(r"```[\s\S]*?```", _save_fence, content)
-
-        # --- 2. Protect inline code ---
-        _CODE_PH = "\x00CODE"
-        codes: list[str] = []
-
-        def _save_code(m: re.Match) -> str:
-            codes.append(m.group(0))
-            return f"{_CODE_PH}{len(codes) - 1}\x00"
-
-        result = re.sub(r"`[^`\n]+`", _save_code, result)
-
-        # --- 3. Convert markdown formatting to WhatsApp syntax ---
-        # Bold: **text** or __text__ → *text*
-        result = re.sub(r"\*\*(.+?)\*\*", r"*\1*", result)
-        result = re.sub(r"__(.+?)__", r"*\1*", result)
-        # Strikethrough: ~~text~~ → ~text~
-        result = re.sub(r"~~(.+?)~~", r"~\1~", result)
-        # Italic: *text* is already WhatsApp italic — leave as-is
-        # _text_ is already WhatsApp italic — leave as-is
-
-        # --- 4. Convert markdown headers to bold text ---
-        # # Header → *Header*
-        result = re.sub(r"^#{1,6}\s+(.+)$", r"*\1*", result, flags=re.MULTILINE)
-
-        # --- 5. Convert markdown links: [text](url) → text (url) ---
-        result = re.sub(r"\[([^\]]+)\]\(([^)]+)\)", r"\1 (\2)", result)
-
-        # --- 6. Restore protected sections ---
-        for i, fence in enumerate(fences):
-            result = result.replace(f"{_FENCE_PH}{i}\x00", fence)
-        for i, code in enumerate(codes):
-            result = result.replace(f"{_CODE_PH}{i}\x00", code)
-
-        return result
-
     async def send(
         self,
         chat_id: str,
@@ -596,57 +566,38 @@ class WhatsAppAdapter(BasePlatformAdapter):
         reply_to: Optional[str] = None,
         metadata: Optional[Dict[str, Any]] = None
     ) -> SendResult:
-        """Send a message via the WhatsApp bridge.
-
-        Formats markdown for WhatsApp, splits long messages into chunks
-        that preserve code block boundaries, and sends each chunk sequentially.
-        """
+        """Send a message via the WhatsApp bridge."""
         if not self._running or not self._http_session:
             return SendResult(success=False, error="Not connected")
         bridge_exit = await self._check_managed_bridge_exit()
         if bridge_exit:
             return SendResult(success=False, error=bridge_exit)
-
-        if not content or not content.strip():
-            return SendResult(success=True, message_id=None)
-
+        
         try:
             import aiohttp
 
-            # Format and chunk the message
-            formatted = self.format_message(content)
-            chunks = self.truncate_message(formatted, self.MAX_MESSAGE_LENGTH)
-
-            last_message_id = None
-            for chunk in chunks:
-                payload: Dict[str, Any] = {
-                    "chatId": chat_id,
-                    "message": chunk,
-                }
-                if reply_to and last_message_id is None:
-                    # Only reply-to on the first chunk
-                    payload["replyTo"] = reply_to
-
-                async with self._http_session.post(
-                    f"http://127.0.0.1:{self._bridge_port}/send",
-                    json=payload,
-                    timeout=aiohttp.ClientTimeout(total=30)
-                ) as resp:
-                    if resp.status == 200:
-                        data = await resp.json()
-                        last_message_id = data.get("messageId")
-                    else:
-                        error = await resp.text()
-                        return SendResult(success=False, error=error)
-
-                # Small delay between chunks to avoid rate limiting
-                if len(chunks) > 1:
-                    await asyncio.sleep(0.3)
-
-            return SendResult(
-                success=True,
-                message_id=last_message_id,
-            )
+            payload = {
+                "chatId": chat_id,
+                "message": content,
+            }
+            if reply_to:
+                payload["replyTo"] = reply_to
+            
+            async with self._http_session.post(
+                f"http://127.0.0.1:{self._bridge_port}/send",
+                json=payload,
+                timeout=aiohttp.ClientTimeout(total=30)
+            ) as resp:
+                if resp.status == 200:
+                    data = await resp.json()
+                    return SendResult(
+                        success=True,
+                        message_id=data.get("messageId"),
+                        raw_response=data
+                    )
+                else:
+                    error = await resp.text()
+                    return SendResult(success=False, error=error)
         except Exception as e:
             return SendResult(success=False, error=str(e))
 

gateway/restart.py

@@ -1,20 +0,0 @@
-"""Shared gateway restart constants and parsing helpers."""
-
-from hermes_cli.config import DEFAULT_CONFIG
-
-# EX_TEMPFAIL from sysexits.h — used to ask the service manager to restart
-# the gateway after a graceful drain/reload path completes.
-GATEWAY_SERVICE_RESTART_EXIT_CODE = 75
-
-DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT = float(
-    DEFAULT_CONFIG["agent"]["restart_drain_timeout"]
-)
-
-
-def parse_restart_drain_timeout(raw: object) -> float:
-    """Parse a configured drain timeout, falling back to the shared default."""
-    try:
-        value = float(raw) if str(raw or "").strip() else DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
-    except (TypeError, ValueError):
-        return DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
-    return max(0.0, value)

gateway/session.py

@@ -12,6 +12,7 @@ import hashlib
 import logging
 import os
 import json
+import re
 import threading
 import uuid
 from pathlib import Path
@@ -367,11 +368,6 @@ class SessionEntry:
     # survives gateway restarts (the old in-memory _pre_flushed_sessions
     # set was lost on restart, causing redundant re-flushes).
     memory_flushed: bool = False
-
-    # When True the next call to get_or_create_session() will auto-reset
-    # this session (create a new session_id) so the user starts fresh.
-    # Set by /stop to break stuck-resume loops (#7536).
-    suspended: bool = False
     
     def to_dict(self) -> Dict[str, Any]:
         result = {
@@ -391,7 +387,6 @@ class SessionEntry:
             "estimated_cost_usd": self.estimated_cost_usd,
             "cost_status": self.cost_status,
             "memory_flushed": self.memory_flushed,
-            "suspended": self.suspended,
         }
         if self.origin:
             result["origin"] = self.origin.to_dict()
@@ -428,7 +423,6 @@ class SessionEntry:
             estimated_cost_usd=data.get("estimated_cost_usd", 0.0),
             cost_status=data.get("cost_status", "unknown"),
             memory_flushed=data.get("memory_flushed", False),
-            suspended=data.get("suspended", False),
         )
 
 
@@ -704,12 +698,7 @@ class SessionStore:
             if session_key in self._entries and not force_new:
                 entry = self._entries[session_key]
 
-                # Auto-reset sessions marked as suspended (e.g. after /stop
-                # broke a stuck loop — #7536).
-                if entry.suspended:
-                    reset_reason = "suspended"
-                else:
-                    reset_reason = self._should_reset(entry, source)
+                reset_reason = self._should_reset(entry, source)
                 if not reset_reason:
                     entry.updated_at = now
                     self._save()
@@ -782,44 +771,6 @@ class SessionStore:
                     entry.last_prompt_tokens = last_prompt_tokens
                 self._save()
 
-    def suspend_session(self, session_key: str) -> bool:
-        """Mark a session as suspended so it auto-resets on next access.
-
-        Used by ``/stop`` to prevent stuck sessions from being resumed
-        after a gateway restart (#7536).  Returns True if the session
-        existed and was marked.
-        """
-        with self._lock:
-            self._ensure_loaded_locked()
-            if session_key in self._entries:
-                self._entries[session_key].suspended = True
-                self._save()
-                return True
-        return False
-
-    def suspend_recently_active(self, max_age_seconds: int = 120) -> int:
-        """Mark recently-active sessions as suspended.
-
-        Called on gateway startup to prevent sessions that were likely
-        in-flight when the gateway last exited from being blindly resumed
-        (#7536).  Only suspends sessions updated within *max_age_seconds*
-        to avoid resetting long-idle sessions that are harmless to resume.
-        Returns the number of sessions that were suspended.
-        """
-        from datetime import timedelta
-
-        cutoff = _now() - timedelta(seconds=max_age_seconds)
-        count = 0
-        with self._lock:
-            self._ensure_loaded_locked()
-            for entry in self._entries.values():
-                if not entry.suspended and entry.updated_at >= cutoff:
-                    entry.suspended = True
-                    count += 1
-            if count:
-                self._save()
-        return count
-
     def reset_session(self, session_key: str) -> Optional[SessionEntry]:
         """Force reset a session, creating a new session ID."""
         db_end_session_id = None
@@ -877,8 +828,7 @@ class SessionStore:
         Used by ``/resume`` to restore a previously-named session.
         Ends the current session in SQLite (like reset), but instead of
         generating a fresh session ID, re-uses ``target_session_id`` so the
-        old transcript is loaded on the next message. If the target session was
-        previously ended, re-open it so gateway resume semantics match the CLI.
+        old transcript is loaded on the next message.
         """
         db_end_session_id = None
         new_entry = None
@@ -918,12 +868,6 @@ class SessionStore:
             except Exception as e:
                 logger.debug("Session DB end_session failed: %s", e)
 
-        if self._db:
-            try:
-                self._db.reopen_session(target_session_id)
-            except Exception as e:
-                logger.debug("Session DB reopen_session failed: %s", e)
-
         return new_entry
 
     def list_sessions(self, active_minutes: Optional[int] = None) -> List[SessionEntry]:

gateway/session_context.py

@@ -46,18 +46,12 @@ _SESSION_PLATFORM: ContextVar[str] = ContextVar("HERMES_SESSION_PLATFORM", defau
 _SESSION_CHAT_ID: ContextVar[str] = ContextVar("HERMES_SESSION_CHAT_ID", default="")
 _SESSION_CHAT_NAME: ContextVar[str] = ContextVar("HERMES_SESSION_CHAT_NAME", default="")
 _SESSION_THREAD_ID: ContextVar[str] = ContextVar("HERMES_SESSION_THREAD_ID", default="")
-_SESSION_USER_ID: ContextVar[str] = ContextVar("HERMES_SESSION_USER_ID", default="")
-_SESSION_USER_NAME: ContextVar[str] = ContextVar("HERMES_SESSION_USER_NAME", default="")
-_SESSION_KEY: ContextVar[str] = ContextVar("HERMES_SESSION_KEY", default="")
 
 _VAR_MAP = {
     "HERMES_SESSION_PLATFORM": _SESSION_PLATFORM,
     "HERMES_SESSION_CHAT_ID": _SESSION_CHAT_ID,
     "HERMES_SESSION_CHAT_NAME": _SESSION_CHAT_NAME,
     "HERMES_SESSION_THREAD_ID": _SESSION_THREAD_ID,
-    "HERMES_SESSION_USER_ID": _SESSION_USER_ID,
-    "HERMES_SESSION_USER_NAME": _SESSION_USER_NAME,
-    "HERMES_SESSION_KEY": _SESSION_KEY,
 }
 
 
@@ -66,9 +60,6 @@ def set_session_vars(
     chat_id: str = "",
     chat_name: str = "",
     thread_id: str = "",
-    user_id: str = "",
-    user_name: str = "",
-    session_key: str = "",
 ) -> list:
     """Set all session context variables and return reset tokens.
 
@@ -83,9 +74,6 @@ def set_session_vars(
         _SESSION_CHAT_ID.set(chat_id),
         _SESSION_CHAT_NAME.set(chat_name),
         _SESSION_THREAD_ID.set(thread_id),
-        _SESSION_USER_ID.set(user_id),
-        _SESSION_USER_NAME.set(user_name),
-        _SESSION_KEY.set(session_key),
     ]
     return tokens
 
@@ -99,9 +87,6 @@ def clear_session_vars(tokens: list) -> None:
         _SESSION_CHAT_ID,
         _SESSION_CHAT_NAME,
         _SESSION_THREAD_ID,
-        _SESSION_USER_ID,
-        _SESSION_USER_NAME,
-        _SESSION_KEY,
     ]
     for var, token in zip(vars_in_order, tokens):
         var.reset(token)

gateway/status.py

@@ -26,7 +26,6 @@ _GATEWAY_KIND = "hermes-gateway"
 _RUNTIME_STATUS_FILE = "gateway_state.json"
 _LOCKS_DIRNAME = "gateway-locks"
 _IS_WINDOWS = sys.platform == "win32"
-_UNSET = object()
 
 
 def _get_pid_path() -> Path:
@@ -159,8 +158,6 @@ def _build_runtime_status_record() -> dict[str, Any]:
     payload.update({
         "gateway_state": "starting",
         "exit_reason": None,
-        "restart_requested": False,
-        "active_agents": 0,
         "platforms": {},
         "updated_at": _utc_now_iso(),
     })
@@ -219,14 +216,12 @@ def write_pid_file() -> None:
 
 def write_runtime_status(
     *,
-    gateway_state: Any = _UNSET,
-    exit_reason: Any = _UNSET,
-    restart_requested: Any = _UNSET,
-    active_agents: Any = _UNSET,
-    platform: Any = _UNSET,
-    platform_state: Any = _UNSET,
-    error_code: Any = _UNSET,
-    error_message: Any = _UNSET,
+    gateway_state: Optional[str] = None,
+    exit_reason: Optional[str] = None,
+    platform: Optional[str] = None,
+    platform_state: Optional[str] = None,
+    error_code: Optional[str] = None,
+    error_message: Optional[str] = None,
 ) -> None:
     """Persist gateway runtime health information for diagnostics/status."""
     path = _get_runtime_status_path()
@@ -237,22 +232,18 @@ def write_runtime_status(
     payload["start_time"] = _get_process_start_time(os.getpid())
     payload["updated_at"] = _utc_now_iso()
 
-    if gateway_state is not _UNSET:
+    if gateway_state is not None:
         payload["gateway_state"] = gateway_state
-    if exit_reason is not _UNSET:
+    if exit_reason is not None:
         payload["exit_reason"] = exit_reason
-    if restart_requested is not _UNSET:
-        payload["restart_requested"] = bool(restart_requested)
-    if active_agents is not _UNSET:
-        payload["active_agents"] = max(0, int(active_agents))
 
-    if platform is not _UNSET:
+    if platform is not None:
         platform_payload = payload["platforms"].get(platform, {})
-        if platform_state is not _UNSET:
+        if platform_state is not None:
             platform_payload["state"] = platform_state
-        if error_code is not _UNSET:
+        if error_code is not None:
             platform_payload["error_code"] = error_code
-        if error_message is not _UNSET:
+        if error_message is not None:
             platform_payload["error_message"] = error_message
         platform_payload["updated_at"] = _utc_now_iso()
         payload["platforms"][platform] = platform_payload
@@ -290,15 +281,6 @@ def acquire_scoped_lock(scope: str, identity: str, metadata: Optional[dict[str,
     }
 
     existing = _read_json_file(lock_path)
-    if existing is None and lock_path.exists():
-        # Lock file exists but is empty or contains invalid JSON — treat as
-        # stale.  This happens when a previous process was killed between
-        # O_CREAT|O_EXCL and the subsequent json.dump() (e.g. DNS failure
-        # during rapid Slack reconnect retries).
-        try:
-            lock_path.unlink(missing_ok=True)
-        except OSError:
-            pass
     if existing:
         try:
             existing_pid = int(existing["pid"])

gateway/stream_consumer.py

@@ -32,15 +32,11 @@ _DONE = object()
 # new one so that subsequent text appears below tool progress messages.
 _NEW_SEGMENT = object()
 
-# Queue marker for a completed assistant commentary message emitted between
-# API/tool iterations (for example: "I'll inspect the repo first.").
-_COMMENTARY = object()
-
 
 @dataclass
 class StreamConsumerConfig:
     """Runtime config for a single stream consumer instance."""
-    edit_interval: float = 1.0
+    edit_interval: float = 0.3
     buffer_threshold: int = 40
     cursor: str = " ▉"
 
@@ -60,10 +56,6 @@ class GatewayStreamConsumer:
         await task         # wait for final edit
     """
 
-    # After this many consecutive flood-control failures, permanently disable
-    # progressive edits for the remainder of the stream.
-    _MAX_FLOOD_STRIKES = 3
-
     def __init__(
         self,
         adapter: Any,
@@ -79,43 +71,18 @@ class GatewayStreamConsumer:
         self._accumulated = ""
         self._message_id: Optional[str] = None
         self._already_sent = False
-        self._edit_supported = True  # Disabled when progressive edits are no longer usable
+        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 = ""
-        self._flood_strikes = 0         # Consecutive flood-control edit failures
-        self._current_edit_interval = self.cfg.edit_interval  # Adaptive backoff
-        self._final_response_sent = False
 
     @property
     def already_sent(self) -> bool:
-        """True if at least one message was sent or edited during the run."""
+        """True if at least one message was sent/edited — signals the base
+        adapter to skip re-sending the final response."""
         return self._already_sent
 
-    @property
-    def final_response_sent(self) -> bool:
-        """True when the stream consumer delivered the final assistant reply."""
-        return self._final_response_sent
-
-    def on_segment_break(self) -> None:
-        """Finalize the current stream segment and start a fresh message."""
-        self._queue.put(_NEW_SEGMENT)
-
-    def on_commentary(self, text: str) -> None:
-        """Queue a completed interim assistant commentary message."""
-        if text:
-            self._queue.put((_COMMENTARY, text))
-
-    def _reset_segment_state(self, *, preserve_no_edit: bool = False) -> None:
-        if preserve_no_edit and self._message_id == "__no_edit__":
-            return
-        self._message_id = None
-        self._accumulated = ""
-        self._last_sent_text = ""
-        self._fallback_final_send = False
-        self._fallback_prefix = ""
-
     def on_delta(self, text: str) -> None:
         """Thread-safe callback — called from the agent's worker thread.
 
@@ -126,7 +93,7 @@ class GatewayStreamConsumer:
         if text:
             self._queue.put(text)
         elif text is None:
-            self.on_segment_break()
+            self._queue.put(_NEW_SEGMENT)
 
     def finish(self) -> None:
         """Signal that the stream is complete."""
@@ -143,7 +110,6 @@ class GatewayStreamConsumer:
                 # Drain all available items from the queue
                 got_done = False
                 got_segment_break = False
-                commentary_text = None
                 while True:
                     try:
                         item = self._queue.get_nowait()
@@ -153,9 +119,6 @@ class GatewayStreamConsumer:
                         if item is _NEW_SEGMENT:
                             got_segment_break = True
                             break
-                        if isinstance(item, tuple) and len(item) == 2 and item[0] is _COMMENTARY:
-                            commentary_text = item[1]
-                            break
                         self._accumulated += item
                     except queue.Empty:
                         break
@@ -166,13 +129,11 @@ class GatewayStreamConsumer:
                 should_edit = (
                     got_done
                     or got_segment_break
-                    or commentary_text is not None
-                    or (elapsed >= self._current_edit_interval
+                    or (elapsed >= self.cfg.edit_interval
                         and self._accumulated)
                     or len(self._accumulated) >= self.cfg.buffer_threshold
                 )
 
-                current_update_visible = False
                 if should_edit and self._accumulated:
                     # Split overflow: if accumulated text exceeds the platform
                     # limit, split into properly sized chunks.
@@ -194,7 +155,6 @@ class GatewayStreamConsumer:
                         self._last_sent_text = ""
                         self._last_edit_time = time.monotonic()
                         if got_done:
-                            self._final_response_sent = self._already_sent
                             return
                         if got_segment_break:
                             self._message_id = None
@@ -213,23 +173,22 @@ class GatewayStreamConsumer:
                         if split_at < _safe_limit // 2:
                             split_at = _safe_limit
                         chunk = self._accumulated[:split_at]
-                        ok = await self._send_or_edit(chunk)
-                        if self._fallback_final_send or not ok:
-                            # Edit failed (or backed off due to flood control)
-                            # 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.
+                        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 = ""
 
                     display_text = self._accumulated
-                    if not got_done and not got_segment_break and commentary_text is None:
+                    if not got_done and not got_segment_break:
                         display_text += self.cfg.cursor
 
-                    current_update_visible = await self._send_or_edit(display_text)
+                    await self._send_or_edit(display_text)
                     self._last_edit_time = time.monotonic()
 
                 if got_done:
@@ -240,20 +199,12 @@ class GatewayStreamConsumer:
                     if self._accumulated:
                         if self._fallback_final_send:
                             await self._send_fallback_final(self._accumulated)
-                        elif current_update_visible:
-                            self._final_response_sent = True
                         elif self._message_id:
-                            self._final_response_sent = await self._send_or_edit(self._accumulated)
+                            await self._send_or_edit(self._accumulated)
                         elif not self._already_sent:
-                            self._final_response_sent = await self._send_or_edit(self._accumulated)
+                            await self._send_or_edit(self._accumulated)
                     return
 
-                if commentary_text is not None:
-                    self._reset_segment_state()
-                    await self._send_commentary(commentary_text)
-                    self._last_edit_time = time.monotonic()
-                    self._reset_segment_state()
-
                 # Tool boundary: reset message state so the next text chunk
                 # creates a fresh message below any tool-progress messages.
                 #
@@ -262,14 +213,17 @@ class GatewayStreamConsumer:
                 # github_comment delivery).  Resetting to None would re-enter
                 # the "first send" path on every tool boundary and post one
                 # platform message per tool call — that is what caused 155
-                # comments under a single PR.  Instead, preserve the sentinel
-                # so the full continuation is delivered once via
-                # _send_fallback_final.
+                # comments under a single PR.  Instead, keep all state so the
+                # full continuation is delivered once via _send_fallback_final.
                 # (When editing fails mid-stream due to flood control the id is
                 # a real string like "msg_1", not "__no_edit__", so that case
                 # still resets and creates a fresh segment as intended.)
-                if got_segment_break:
-                    self._reset_segment_state(preserve_no_edit=True)
+                if got_segment_break and self._message_id != "__no_edit__":
+                    self._message_id = None
+                    self._accumulated = ""
+                    self._last_sent_text = ""
+                    self._fallback_final_send = False
+                    self._fallback_prefix = ""
 
                 await asyncio.sleep(0.05)  # Small yield to not busy-loop
 
@@ -368,17 +322,13 @@ class GatewayStreamConsumer:
         return chunks
 
     async def _send_fallback_final(self, text: str) -> None:
-        """Send the final continuation after streaming edits stop working.
-
-        Retries each chunk once on flood-control failures with a short delay.
-        """
+        """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
-            self._final_response_sent = True
             return
 
         raw_limit = getattr(self.adapter, "MAX_MESSAGE_LENGTH", 4096)
@@ -389,31 +339,17 @@ class GatewayStreamConsumer:
         last_successful_chunk = ""
         sent_any_chunk = False
         for chunk in chunks:
-            # Try sending with one retry on flood-control errors.
-            result = None
-            for attempt in range(2):
-                result = await self.adapter.send(
-                    chat_id=self.chat_id,
-                    content=chunk,
-                    metadata=self.metadata,
-                )
-                if result.success:
-                    break
-                if attempt == 0 and self._is_flood_error(result):
-                    logger.debug(
-                        "Flood control on fallback send, retrying in 3s"
-                    )
-                    await asyncio.sleep(3.0)
-                else:
-                    break  # non-flood error or second attempt failed
-
-            if not result or not result.success:
+            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._final_response_sent = True
                     self._message_id = last_message_id
                     self._last_sent_text = last_successful_chunk
                     self._fallback_prefix = ""
@@ -431,81 +367,23 @@ class GatewayStreamConsumer:
 
         self._message_id = last_message_id
         self._already_sent = True
-        self._final_response_sent = True
         self._last_sent_text = chunks[-1]
         self._fallback_prefix = ""
 
-    def _is_flood_error(self, result) -> bool:
-        """Check if a SendResult failure is due to flood control / rate limiting."""
-        err = getattr(result, "error", "") or ""
-        err_lower = err.lower()
-        return "flood" in err_lower or "retry after" in err_lower or "rate" in err_lower
-
-    async def _try_strip_cursor(self) -> None:
-        """Best-effort edit to remove the cursor from the last visible message.
-
-        Called when entering fallback mode so the user doesn't see a stuck
-        cursor (▉) in the partial message.
-        """
-        if not self._message_id or self._message_id == "__no_edit__":
-            return
-        prefix = self._visible_prefix()
-        if not prefix or not prefix.strip():
-            return
-        try:
-            await self.adapter.edit_message(
-                chat_id=self.chat_id,
-                message_id=self._message_id,
-                content=prefix,
-            )
-            self._last_sent_text = prefix
-        except Exception:
-            pass  # best-effort — don't let this block the fallback path
-
-    async def _send_commentary(self, text: str) -> bool:
-        """Send a completed interim assistant commentary message."""
-        text = self._clean_for_display(text)
-        if not text.strip():
-            return False
-        try:
-            result = await self.adapter.send(
-                chat_id=self.chat_id,
-                content=text,
-                metadata=self.metadata,
-            )
-            if result.success:
-                self._already_sent = True
-                return True
-        except Exception as e:
-            logger.error("Commentary send error: %s", e)
-        return False
-
-    async def _send_or_edit(self, text: str) -> bool:
-        """Send or edit the streaming message.
-
-        Returns True if the text was successfully delivered (sent or edited),
-        False otherwise.  Callers like the overflow split loop use this to
-        decide whether to advance past the delivered chunk.
-        """
+    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.
         # Media files are delivered as native attachments after the stream
         # finishes (via _deliver_media_from_response in gateway/run.py).
         text = self._clean_for_display(text)
-        # A bare streaming cursor is not meaningful user-visible content and
-        # can render as a stray tofu/white-box message on some clients.
-        visible_without_cursor = text
-        if self.cfg.cursor:
-            visible_without_cursor = visible_without_cursor.replace(self.cfg.cursor, "")
-        if not visible_without_cursor.strip():
-            return True  # cursor-only / whitespace-only update
         if not text.strip():
-            return True  # nothing to send is "success"
+            return
         try:
             if self._message_id is not None:
                 if self._edit_supported:
                     # Skip if text is identical to what we last sent
                     if text == self._last_sent_text:
-                        return True
+                        return
                     # Edit existing message
                     result = await self.adapter.edit_message(
                         chat_id=self.chat_id,
@@ -515,52 +393,19 @@ class GatewayStreamConsumer:
                     if result.success:
                         self._already_sent = True
                         self._last_sent_text = text
-                        # Successful edit — reset flood strike counter
-                        self._flood_strikes = 0
-                        return True
                     else:
-                        # Edit failed.  If this looks like flood control / rate
-                        # limiting, use adaptive backoff: double the edit interval
-                        # and retry on the next cycle.  Only permanently disable
-                        # edits after _MAX_FLOOD_STRIKES consecutive failures.
-                        if self._is_flood_error(result):
-                            self._flood_strikes += 1
-                            self._current_edit_interval = min(
-                                self._current_edit_interval * 2, 10.0,
-                            )
-                            logger.debug(
-                                "Flood control on edit (strike %d/%d), "
-                                "backoff interval → %.1fs",
-                                self._flood_strikes,
-                                self._MAX_FLOOD_STRIKES,
-                                self._current_edit_interval,
-                            )
-                            if self._flood_strikes < self._MAX_FLOOD_STRIKES:
-                                # Don't disable edits yet — just slow down.
-                                # Update _last_edit_time so the next edit
-                                # respects the new interval.
-                                self._last_edit_time = time.monotonic()
-                                return False
-
-                        # Non-flood error OR flood strikes exhausted: enter
-                        # fallback mode — send only the missing tail once the
+                        # 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.
-                        logger.debug(
-                            "Edit failed (strikes=%d), entering fallback mode",
-                            self._flood_strikes,
-                        )
+                        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
-                        # Best-effort: strip the cursor from the last visible
-                        # message so the user doesn't see a stuck ▉.
-                        await self._try_strip_cursor()
-                        return False
                 else:
                     # Editing not supported — skip intermediate updates.
                     # The final response will be sent by the fallback path.
-                    return False
+                    pass
             else:
                 # First message — send new
                 result = await self.adapter.send(
@@ -568,25 +413,23 @@ class GatewayStreamConsumer:
                     content=text,
                     metadata=self.metadata,
                 )
-                if result.success:
-                    if result.message_id:
-                        self._message_id = result.message_id
-                    else:
-                        self._edit_supported = False
+                if result.success and result.message_id:
+                    self._message_id = result.message_id
                     self._already_sent = True
                     self._last_sent_text = text
-                    if not result.message_id:
-                        self._fallback_prefix = self._visible_prefix()
-                        self._fallback_final_send = True
-                        # Sentinel prevents re-entering the first-send path on
-                        # every delta/tool boundary when platforms accept a
-                        # message but do not return an editable message id.
-                        self._message_id = "__no_edit__"
-                    return True
+                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
-                    return False
         except Exception as e:
             logger.error("Stream send/edit error: %s", e)
-            return False

hermes_cli/__init__.py

@@ -11,5 +11,5 @@ Provides subcommands for:
 - hermes cron          - Manage cron jobs
 """
 
-__version__ = "0.9.0"
-__release_date__ = "2026.4.13"
+__version__ = "0.8.0"
+__release_date__ = "2026.4.8"

hermes_cli/auth.py

@@ -127,7 +127,6 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
         auth_type="api_key",
         inference_base_url=DEFAULT_GITHUB_MODELS_BASE_URL,
         api_key_env_vars=("COPILOT_GITHUB_TOKEN", "GH_TOKEN", "GITHUB_TOKEN"),
-        base_url_env_var="COPILOT_API_BASE_URL",
     ),
     "copilot-acp": ProviderConfig(
         id="copilot-acp",
@@ -160,21 +159,6 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
         api_key_env_vars=("KIMI_API_KEY",),
         base_url_env_var="KIMI_BASE_URL",
     ),
-    "kimi-coding-cn": ProviderConfig(
-        id="kimi-coding-cn",
-        name="Kimi / Moonshot (China)",
-        auth_type="api_key",
-        inference_base_url="https://api.moonshot.cn/v1",
-        api_key_env_vars=("KIMI_CN_API_KEY",),
-    ),
-    "arcee": ProviderConfig(
-        id="arcee",
-        name="Arcee AI",
-        auth_type="api_key",
-        inference_base_url="https://api.arcee.ai/api/v1",
-        api_key_env_vars=("ARCEEAI_API_KEY",),
-        base_url_env_var="ARCEE_BASE_URL",
-    ),
     "minimax": ProviderConfig(
         id="minimax",
         name="MiniMax",
@@ -266,39 +250,9 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
         api_key_env_vars=("HF_TOKEN",),
         base_url_env_var="HF_BASE_URL",
     ),
-    "xiaomi": ProviderConfig(
-        id="xiaomi",
-        name="Xiaomi MiMo",
-        auth_type="api_key",
-        inference_base_url="https://api.xiaomimimo.com/v1",
-        api_key_env_vars=("XIAOMI_API_KEY",),
-        base_url_env_var="XIAOMI_BASE_URL",
-    ),
 }
 
 
-# =============================================================================
-# Anthropic Key Helper
-# =============================================================================
-
-def get_anthropic_key() -> str:
-    """Return the first usable Anthropic credential, or ``""``.
-
-    Checks both the ``.env`` file (via ``get_env_value``) and the process
-    environment (``os.getenv``).  The fallback order mirrors the
-    ``PROVIDER_REGISTRY["anthropic"].api_key_env_vars`` tuple:
-
-        ANTHROPIC_API_KEY -> ANTHROPIC_TOKEN -> CLAUDE_CODE_OAUTH_TOKEN
-    """
-    from hermes_cli.config import get_env_value
-
-    for var in PROVIDER_REGISTRY["anthropic"].api_key_env_vars:
-        value = get_env_value(var) or os.getenv(var, "")
-        if value:
-            return value
-    return ""
-
-
 # =============================================================================
 # Kimi Code Endpoint Detection
 # =============================================================================
@@ -323,6 +277,44 @@ def _resolve_kimi_base_url(api_key: str, default_url: str, env_override: str) ->
     return default_url
 
 
+def _gh_cli_candidates() -> list[str]:
+    """Return candidate ``gh`` binary paths, including common Homebrew installs."""
+    candidates: list[str] = []
+
+    resolved = shutil.which("gh")
+    if resolved:
+        candidates.append(resolved)
+
+    for candidate in (
+        "/opt/homebrew/bin/gh",
+        "/usr/local/bin/gh",
+        str(Path.home() / ".local" / "bin" / "gh"),
+    ):
+        if candidate in candidates:
+            continue
+        if os.path.isfile(candidate) and os.access(candidate, os.X_OK):
+            candidates.append(candidate)
+
+    return candidates
+
+
+def _try_gh_cli_token() -> Optional[str]:
+    """Return a token from ``gh auth token`` when the GitHub CLI is available."""
+    for gh_path in _gh_cli_candidates():
+        try:
+            result = subprocess.run(
+                [gh_path, "auth", "token"],
+                capture_output=True,
+                text=True,
+                timeout=5,
+            )
+        except (FileNotFoundError, subprocess.TimeoutExpired) as exc:
+            logger.debug("gh CLI token lookup failed (%s): %s", gh_path, exc)
+            continue
+        if result.returncode == 0 and result.stdout.strip():
+            return result.stdout.strip()
+    return None
+
 
 _PLACEHOLDER_SECRET_VALUES = {
     "*",
@@ -907,8 +899,6 @@ def resolve_provider(
         "glm": "zai", "z-ai": "zai", "z.ai": "zai", "zhipu": "zai",
         "google": "gemini", "google-gemini": "gemini", "google-ai-studio": "gemini",
         "kimi": "kimi-coding", "kimi-for-coding": "kimi-coding", "moonshot": "kimi-coding",
-        "kimi-cn": "kimi-coding-cn", "moonshot-cn": "kimi-coding-cn",
-        "arcee-ai": "arcee", "arceeai": "arcee",
         "minimax-china": "minimax-cn", "minimax_cn": "minimax-cn",
         "claude": "anthropic", "claude-code": "anthropic",
         "github": "copilot", "github-copilot": "copilot",
@@ -918,7 +908,6 @@ def resolve_provider(
         "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",
-        "mimo": "xiaomi", "xiaomi-mimo": "xiaomi",
         "go": "opencode-go", "opencode-go-sub": "opencode-go",
         "kilo": "kilocode", "kilo-code": "kilocode", "kilo-gateway": "kilocode",
         # Local server aliases — route through the generic custom provider
@@ -1283,49 +1272,6 @@ def _read_codex_tokens(*, _lock: bool = True) -> Dict[str, Any]:
     }
 
 
-def _write_codex_cli_tokens(
-    access_token: str,
-    refresh_token: str,
-    *,
-    last_refresh: Optional[str] = None,
-) -> None:
-    """Write refreshed tokens back to ~/.codex/auth.json.
-
-    OpenAI OAuth refresh tokens are single-use and rotate on every refresh.
-    When Hermes refreshes a token it consumes the old refresh_token; if we
-    don't write the new pair back, the Codex CLI (or VS Code extension) will
-    fail with ``refresh_token_reused`` on its next refresh attempt.
-
-    This mirrors the Anthropic write-back to ~/.claude/.credentials.json
-    via ``_write_claude_code_credentials()``.
-    """
-    codex_home = os.getenv("CODEX_HOME", "").strip()
-    if not codex_home:
-        codex_home = str(Path.home() / ".codex")
-    auth_path = Path(codex_home).expanduser() / "auth.json"
-    try:
-        existing: Dict[str, Any] = {}
-        if auth_path.is_file():
-            existing = json.loads(auth_path.read_text(encoding="utf-8"))
-        if not isinstance(existing, dict):
-            existing = {}
-
-        tokens_dict = existing.get("tokens")
-        if not isinstance(tokens_dict, dict):
-            tokens_dict = {}
-        tokens_dict["access_token"] = access_token
-        tokens_dict["refresh_token"] = refresh_token
-        existing["tokens"] = tokens_dict
-        if last_refresh is not None:
-            existing["last_refresh"] = last_refresh
-
-        auth_path.parent.mkdir(parents=True, exist_ok=True)
-        auth_path.write_text(json.dumps(existing, indent=2), encoding="utf-8")
-        auth_path.chmod(0o600)
-    except (OSError, IOError) as exc:
-        logger.debug("Failed to write refreshed tokens to %s: %s", auth_path, exc)
-
-
 def _save_codex_tokens(tokens: Dict[str, str], last_refresh: str = None) -> None:
     """Save Codex OAuth tokens to Hermes auth store (~/.hermes/auth.json)."""
     if last_refresh is None:
@@ -1448,12 +1394,6 @@ def _refresh_codex_auth_tokens(
     updated_tokens["refresh_token"] = refreshed["refresh_token"]
 
     _save_codex_tokens(updated_tokens)
-    # Write back to ~/.codex/auth.json so Codex CLI / VS Code stay in sync.
-    _write_codex_cli_tokens(
-        refreshed["access_token"],
-        refreshed["refresh_token"],
-        last_refresh=refreshed.get("last_refresh"),
-    )
     return updated_tokens
 
 
@@ -2262,40 +2202,7 @@ def resolve_nous_runtime_credentials(
 # =============================================================================
 
 def get_nous_auth_status() -> Dict[str, Any]:
-    """Status snapshot for `hermes status` output.
-
-    Checks the credential pool first (where the dashboard device-code flow
-    and ``hermes auth`` store credentials), then falls back to the legacy
-    auth-store provider state.
-    """
-    # Check credential pool first — the dashboard device-code flow saves
-    # here but may not have written to the auth store yet.
-    try:
-        from agent.credential_pool import load_pool
-        pool = load_pool("nous")
-        if pool and pool.has_credentials():
-            entry = pool.select()
-            if entry is not None:
-                access_token = (
-                    getattr(entry, "access_token", None)
-                    or getattr(entry, "runtime_api_key", "")
-                )
-                if access_token:
-                    return {
-                        "logged_in": True,
-                        "portal_base_url": getattr(entry, "portal_base_url", None)
-                            or getattr(entry, "base_url", None),
-                        "inference_base_url": getattr(entry, "inference_base_url", None)
-                            or getattr(entry, "base_url", None),
-                        "access_token": access_token,
-                        "access_expires_at": getattr(entry, "expires_at", None),
-                        "agent_key_expires_at": getattr(entry, "agent_key_expires_at", None),
-                        "has_refresh_token": bool(getattr(entry, "refresh_token", None)),
-                    }
-    except Exception:
-        pass
-
-    # Fall back to auth-store provider state
+    """Status snapshot for `hermes status` output."""
     state = get_provider_auth_state("nous")
     if not state:
         return {

hermes_cli/auth_commands.py

@@ -36,23 +36,25 @@ _OAUTH_CAPABLE_PROVIDERS = {"anthropic", "nous", "openai-codex", "qwen-oauth"}
 
 
 def _get_custom_provider_names() -> list:
-    """Return list of (display_name, pool_key, provider_key) tuples."""
+    """Return list of (display_name, pool_key) tuples for custom_providers in config."""
     try:
-        from hermes_cli.config import get_compatible_custom_providers, load_config
+        from hermes_cli.config import load_config
 
         config = load_config()
     except Exception:
         return []
+    custom_providers = config.get("custom_providers")
+    if not isinstance(custom_providers, list):
+        return []
     result = []
-    for entry in get_compatible_custom_providers(config):
+    for entry in custom_providers:
         if not isinstance(entry, dict):
             continue
         name = entry.get("name")
         if not isinstance(name, str) or not name.strip():
             continue
         pool_key = f"{CUSTOM_POOL_PREFIX}{_normalize_custom_pool_name(name)}"
-        provider_key = str(entry.get("provider_key", "") or "").strip()
-        result.append((name.strip(), pool_key, provider_key))
+        result.append((name.strip(), pool_key))
     return result
 
 
@@ -64,11 +66,9 @@ def _resolve_custom_provider_input(raw: str) -> str | None:
     # Direct match on 'custom:name' format
     if normalized.startswith(CUSTOM_POOL_PREFIX):
         return normalized
-    for display_name, pool_key, provider_key in _get_custom_provider_names():
+    for display_name, pool_key in _get_custom_provider_names():
         if _normalize_custom_pool_name(display_name) == normalized:
             return pool_key
-        if provider_key and provider_key.strip().lower() == normalized:
-            return pool_key
     return None
 
 
@@ -405,7 +405,7 @@ def _pick_provider(prompt: str = "Provider") -> str:
     known = sorted(set(list(PROVIDER_REGISTRY.keys()) + ["openrouter"]))
     custom_names = _get_custom_provider_names()
     if custom_names:
-        custom_display = [name for name, _key, _provider_key in custom_names]
+        custom_display = [name for name, _key in custom_names]
         print(f"\nKnown providers: {', '.join(known)}")
         print(f"Custom endpoints: {', '.join(custom_display)}")
     else:

hermes_cli/backup.py

@@ -1,655 +0,0 @@
-"""
-Backup and import commands for hermes CLI.
-
-`hermes backup` creates a zip archive of the entire ~/.hermes/ directory
-(excluding the hermes-agent repo and transient files).
-
-`hermes import` restores from a backup zip, overlaying onto the current
-HERMES_HOME root.
-"""
-
-import json
-import logging
-import os
-import shutil
-import sqlite3
-import sys
-import tempfile
-import time
-import zipfile
-from datetime import datetime, timezone
-from pathlib import Path
-from typing import Any, Dict, List, Optional
-
-from hermes_constants import get_default_hermes_root, get_hermes_home, display_hermes_home
-
-logger = logging.getLogger(__name__)
-
-
-# ---------------------------------------------------------------------------
-# Exclusion rules
-# ---------------------------------------------------------------------------
-
-# Directory names to skip entirely (matched against each path component)
-_EXCLUDED_DIRS = {
-    "hermes-agent",     # the codebase repo — re-clone instead
-    "__pycache__",      # bytecode caches — regenerated on import
-    ".git",             # nested git dirs (profiles shouldn't have these, but safety)
-    "node_modules",     # js deps if website/ somehow leaks in
-}
-
-# File-name suffixes to skip
-_EXCLUDED_SUFFIXES = (
-    ".pyc",
-    ".pyo",
-)
-
-# File names to skip (runtime state that's meaningless on another machine)
-_EXCLUDED_NAMES = {
-    "gateway.pid",
-    "cron.pid",
-}
-
-
-def _should_exclude(rel_path: Path) -> bool:
-    """Return True if *rel_path* (relative to hermes root) should be skipped."""
-    parts = rel_path.parts
-
-    # Any path component matches an excluded dir name
-    for part in parts:
-        if part in _EXCLUDED_DIRS:
-            return True
-
-    name = rel_path.name
-
-    if name in _EXCLUDED_NAMES:
-        return True
-
-    if name.endswith(_EXCLUDED_SUFFIXES):
-        return True
-
-    return False
-
-
-# ---------------------------------------------------------------------------
-# SQLite safe copy
-# ---------------------------------------------------------------------------
-
-def _safe_copy_db(src: Path, dst: Path) -> bool:
-    """Copy a SQLite database safely using the backup() API.
-
-    Handles WAL mode — produces a consistent snapshot even while
-    the DB is being written to.  Falls back to raw copy on failure.
-    """
-    try:
-        conn = sqlite3.connect(f"file:{src}?mode=ro", uri=True)
-        backup_conn = sqlite3.connect(str(dst))
-        conn.backup(backup_conn)
-        backup_conn.close()
-        conn.close()
-        return True
-    except Exception as exc:
-        logger.warning("SQLite safe copy failed for %s: %s", src, exc)
-        try:
-            shutil.copy2(src, dst)
-            return True
-        except Exception as exc2:
-            logger.error("Raw copy also failed for %s: %s", src, exc2)
-            return False
-
-
-# ---------------------------------------------------------------------------
-# Backup
-# ---------------------------------------------------------------------------
-
-def _format_size(nbytes: int) -> str:
-    """Human-readable file size."""
-    for unit in ("B", "KB", "MB", "GB"):
-        if nbytes < 1024:
-            return f"{nbytes:.1f} {unit}" if unit != "B" else f"{nbytes} {unit}"
-        nbytes /= 1024
-    return f"{nbytes:.1f} TB"
-
-
-def run_backup(args) -> None:
-    """Create a zip backup of the Hermes home directory."""
-    hermes_root = get_default_hermes_root()
-
-    if not hermes_root.is_dir():
-        print(f"Error: Hermes home directory not found at {hermes_root}")
-        sys.exit(1)
-
-    # Determine output path
-    if args.output:
-        out_path = Path(args.output).expanduser().resolve()
-        # If user gave a directory, put the zip inside it
-        if out_path.is_dir():
-            stamp = datetime.now().strftime("%Y-%m-%d-%H%M%S")
-            out_path = out_path / f"hermes-backup-{stamp}.zip"
-    else:
-        stamp = datetime.now().strftime("%Y-%m-%d-%H%M%S")
-        out_path = Path.home() / f"hermes-backup-{stamp}.zip"
-
-    # Ensure the suffix is .zip
-    if out_path.suffix.lower() != ".zip":
-        out_path = out_path.with_suffix(out_path.suffix + ".zip")
-
-    # Ensure parent directory exists
-    out_path.parent.mkdir(parents=True, exist_ok=True)
-
-    # Collect files
-    print(f"Scanning {display_hermes_home()} ...")
-    files_to_add: list[tuple[Path, Path]] = []  # (absolute, relative)
-    skipped_dirs = set()
-
-    for dirpath, dirnames, filenames in os.walk(hermes_root, followlinks=False):
-        dp = Path(dirpath)
-        rel_dir = dp.relative_to(hermes_root)
-
-        # Prune excluded directories in-place so os.walk doesn't descend
-        orig_dirnames = dirnames[:]
-        dirnames[:] = [
-            d for d in dirnames
-            if d not in _EXCLUDED_DIRS
-        ]
-        for removed in set(orig_dirnames) - set(dirnames):
-            skipped_dirs.add(str(rel_dir / removed))
-
-        for fname in filenames:
-            fpath = dp / fname
-            rel = fpath.relative_to(hermes_root)
-
-            if _should_exclude(rel):
-                continue
-
-            # Skip the output zip itself if it happens to be inside hermes root
-            try:
-                if fpath.resolve() == out_path.resolve():
-                    continue
-            except (OSError, ValueError):
-                pass
-
-            files_to_add.append((fpath, rel))
-
-    if not files_to_add:
-        print("No files to back up.")
-        return
-
-    # Create the zip
-    file_count = len(files_to_add)
-    print(f"Backing up {file_count} files ...")
-
-    total_bytes = 0
-    errors = []
-    t0 = time.monotonic()
-
-    with zipfile.ZipFile(out_path, "w", zipfile.ZIP_DEFLATED, compresslevel=6) as zf:
-        for i, (abs_path, rel_path) in enumerate(files_to_add, 1):
-            try:
-                # Safe copy for SQLite databases (handles WAL mode)
-                if abs_path.suffix == ".db":
-                    with tempfile.NamedTemporaryFile(suffix=".db", delete=False) as tmp:
-                        tmp_db = Path(tmp.name)
-                    if _safe_copy_db(abs_path, tmp_db):
-                        zf.write(tmp_db, arcname=str(rel_path))
-                        total_bytes += tmp_db.stat().st_size
-                        tmp_db.unlink(missing_ok=True)
-                    else:
-                        tmp_db.unlink(missing_ok=True)
-                        errors.append(f"  {rel_path}: SQLite safe copy failed")
-                        continue
-                else:
-                    zf.write(abs_path, arcname=str(rel_path))
-                    total_bytes += abs_path.stat().st_size
-            except (PermissionError, OSError) as exc:
-                errors.append(f"  {rel_path}: {exc}")
-                continue
-
-            # Progress every 500 files
-            if i % 500 == 0:
-                print(f"  {i}/{file_count} files ...")
-
-    elapsed = time.monotonic() - t0
-    zip_size = out_path.stat().st_size
-
-    # Summary
-    print()
-    print(f"Backup complete: {out_path}")
-    print(f"  Files:       {file_count}")
-    print(f"  Original:    {_format_size(total_bytes)}")
-    print(f"  Compressed:  {_format_size(zip_size)}")
-    print(f"  Time:        {elapsed:.1f}s")
-
-    if skipped_dirs:
-        print(f"\n  Excluded directories:")
-        for d in sorted(skipped_dirs):
-            print(f"    {d}/")
-
-    if errors:
-        print(f"\n  Warnings ({len(errors)} files skipped):")
-        for e in errors[:10]:
-            print(e)
-        if len(errors) > 10:
-            print(f"  ... and {len(errors) - 10} more")
-
-    print(f"\nRestore with: hermes import {out_path.name}")
-
-
-# ---------------------------------------------------------------------------
-# Import
-# ---------------------------------------------------------------------------
-
-def _validate_backup_zip(zf: zipfile.ZipFile) -> tuple[bool, str]:
-    """Check that a zip looks like a Hermes backup.
-
-    Returns (ok, reason).
-    """
-    names = zf.namelist()
-    if not names:
-        return False, "zip archive is empty"
-
-    # Look for telltale files that a hermes home would have
-    markers = {"config.yaml", ".env", "state.db"}
-    found = set()
-    for n in names:
-        # Could be at the root or one level deep (if someone zipped the directory)
-        basename = Path(n).name
-        if basename in markers:
-            found.add(basename)
-
-    if not found:
-        return False, (
-            "zip does not appear to be a Hermes backup "
-            "(no config.yaml, .env, or state databases found)"
-        )
-
-    return True, ""
-
-
-def _detect_prefix(zf: zipfile.ZipFile) -> str:
-    """Detect if the zip has a common directory prefix wrapping all entries.
-
-    Some tools zip as `.hermes/config.yaml` instead of `config.yaml`.
-    Returns the prefix to strip (empty string if none).
-    """
-    names = [n for n in zf.namelist() if not n.endswith("/")]
-    if not names:
-        return ""
-
-    # Find common prefix
-    parts_list = [Path(n).parts for n in names]
-
-    # Check if all entries share a common first directory
-    first_parts = {p[0] for p in parts_list if len(p) > 1}
-    if len(first_parts) == 1:
-        prefix = first_parts.pop()
-        # Only strip if it looks like a hermes dir name
-        if prefix in (".hermes", "hermes"):
-            return prefix + "/"
-
-    return ""
-
-
-def run_import(args) -> None:
-    """Restore a Hermes backup from a zip file."""
-    zip_path = Path(args.zipfile).expanduser().resolve()
-
-    if not zip_path.is_file():
-        print(f"Error: File not found: {zip_path}")
-        sys.exit(1)
-
-    if not zipfile.is_zipfile(zip_path):
-        print(f"Error: Not a valid zip file: {zip_path}")
-        sys.exit(1)
-
-    hermes_root = get_default_hermes_root()
-
-    with zipfile.ZipFile(zip_path, "r") as zf:
-        # Validate
-        ok, reason = _validate_backup_zip(zf)
-        if not ok:
-            print(f"Error: {reason}")
-            sys.exit(1)
-
-        prefix = _detect_prefix(zf)
-        members = [n for n in zf.namelist() if not n.endswith("/")]
-        file_count = len(members)
-
-        print(f"Backup contains {file_count} files")
-        print(f"Target: {display_hermes_home()}")
-
-        if prefix:
-            print(f"Detected archive prefix: {prefix!r} (will be stripped)")
-
-        # Check for existing installation
-        has_config = (hermes_root / "config.yaml").exists()
-        has_env = (hermes_root / ".env").exists()
-
-        if (has_config or has_env) and not args.force:
-            print()
-            print("Warning: Target directory already has Hermes configuration.")
-            print("Importing will overwrite existing files with backup contents.")
-            print()
-            try:
-                answer = input("Continue? [y/N] ").strip().lower()
-            except (EOFError, KeyboardInterrupt):
-                print("\nAborted.")
-                sys.exit(1)
-            if answer not in ("y", "yes"):
-                print("Aborted.")
-                return
-
-        # Extract
-        print(f"\nImporting {file_count} files ...")
-        hermes_root.mkdir(parents=True, exist_ok=True)
-
-        errors = []
-        restored = 0
-        t0 = time.monotonic()
-
-        for member in members:
-            # Strip prefix if detected
-            if prefix and member.startswith(prefix):
-                rel = member[len(prefix):]
-            else:
-                rel = member
-
-            if not rel:
-                continue
-
-            target = hermes_root / rel
-
-            # Security: reject absolute paths and traversals
-            try:
-                target.resolve().relative_to(hermes_root.resolve())
-            except ValueError:
-                errors.append(f"  {rel}: path traversal blocked")
-                continue
-
-            try:
-                target.parent.mkdir(parents=True, exist_ok=True)
-                with zf.open(member) as src, open(target, "wb") as dst:
-                    dst.write(src.read())
-                restored += 1
-            except (PermissionError, OSError) as exc:
-                errors.append(f"  {rel}: {exc}")
-
-            if restored % 500 == 0:
-                print(f"  {restored}/{file_count} files ...")
-
-        elapsed = time.monotonic() - t0
-
-        # Summary
-        print()
-        print(f"Import complete: {restored} files restored in {elapsed:.1f}s")
-        print(f"  Target: {display_hermes_home()}")
-
-        if errors:
-            print(f"\n  Warnings ({len(errors)} files skipped):")
-            for e in errors[:10]:
-                print(e)
-            if len(errors) > 10:
-                print(f"  ... and {len(errors) - 10} more")
-
-        # Post-import: restore profile wrapper scripts
-        profiles_dir = hermes_root / "profiles"
-        restored_profiles = []
-        if profiles_dir.is_dir():
-            try:
-                from hermes_cli.profiles import (
-                    create_wrapper_script, check_alias_collision,
-                    _is_wrapper_dir_in_path, _get_wrapper_dir,
-                )
-                for entry in sorted(profiles_dir.iterdir()):
-                    if not entry.is_dir():
-                        continue
-                    profile_name = entry.name
-                    # Only create wrappers for directories with config
-                    if not (entry / "config.yaml").exists() and not (entry / ".env").exists():
-                        continue
-                    collision = check_alias_collision(profile_name)
-                    if collision:
-                        print(f"  Skipped alias '{profile_name}': {collision}")
-                        restored_profiles.append((profile_name, False))
-                    else:
-                        wrapper = create_wrapper_script(profile_name)
-                        restored_profiles.append((profile_name, wrapper is not None))
-
-                if restored_profiles:
-                    created = [n for n, ok in restored_profiles if ok]
-                    skipped = [n for n, ok in restored_profiles if not ok]
-                    if created:
-                        print(f"\n  Profile aliases restored: {', '.join(created)}")
-                    if skipped:
-                        print(f"  Profile aliases skipped:  {', '.join(skipped)}")
-                    if not _is_wrapper_dir_in_path():
-                        print(f"\n  Note: {_get_wrapper_dir()} is not in your PATH.")
-                        print('  Add to your shell config (~/.bashrc or ~/.zshrc):')
-                        print('    export PATH="$HOME/.local/bin:$PATH"')
-            except ImportError:
-                # hermes_cli.profiles might not be available (fresh install)
-                if any(profiles_dir.iterdir()):
-                    print(f"\n  Profiles detected but aliases could not be created.")
-                    print(f"  Run: hermes profile list  (after installing hermes)")
-
-        # Guidance
-        print()
-        if not (hermes_root / "hermes-agent").is_dir():
-            print("Note: The hermes-agent codebase was not included in the backup.")
-            print("  If this is a fresh install, run: hermes update")
-
-        if restored_profiles:
-            gw_profiles = [n for n, _ in restored_profiles]
-            print("\nTo re-enable gateway services for profiles:")
-            for pname in gw_profiles:
-                print(f"  hermes -p {pname} gateway install")
-
-        print("Done. Your Hermes configuration has been restored.")
-
-
-# ---------------------------------------------------------------------------
-# Quick state snapshots (used by /snapshot slash command and hermes backup --quick)
-# ---------------------------------------------------------------------------
-
-# Critical state files to include in quick snapshots (relative to HERMES_HOME).
-# Everything else is either regeneratable (logs, cache) or managed separately
-# (skills, repo, sessions/).
-_QUICK_STATE_FILES = (
-    "state.db",
-    "config.yaml",
-    ".env",
-    "auth.json",
-    "cron/jobs.json",
-    "gateway_state.json",
-    "channel_directory.json",
-    "processes.json",
-)
-
-_QUICK_SNAPSHOTS_DIR = "state-snapshots"
-_QUICK_DEFAULT_KEEP = 20
-
-
-def _quick_snapshot_root(hermes_home: Optional[Path] = None) -> Path:
-    home = hermes_home or get_hermes_home()
-    return home / _QUICK_SNAPSHOTS_DIR
-
-
-def create_quick_snapshot(
-    label: Optional[str] = None,
-    hermes_home: Optional[Path] = None,
-) -> Optional[str]:
-    """Create a quick state snapshot of critical files.
-
-    Copies STATE_FILES to a timestamped directory under state-snapshots/.
-    Auto-prunes old snapshots beyond the keep limit.
-
-    Returns:
-        Snapshot ID (timestamp-based), or None if no files found.
-    """
-    home = hermes_home or get_hermes_home()
-    root = _quick_snapshot_root(home)
-
-    ts = datetime.now(timezone.utc).strftime("%Y%m%d-%H%M%S")
-    snap_id = f"{ts}-{label}" if label else ts
-    snap_dir = root / snap_id
-    snap_dir.mkdir(parents=True, exist_ok=True)
-
-    manifest: Dict[str, int] = {}  # rel_path -> file size
-
-    for rel in _QUICK_STATE_FILES:
-        src = home / rel
-        if not src.exists() or not src.is_file():
-            continue
-
-        dst = snap_dir / rel
-        dst.parent.mkdir(parents=True, exist_ok=True)
-
-        try:
-            if src.suffix == ".db":
-                if not _safe_copy_db(src, dst):
-                    continue
-            else:
-                shutil.copy2(src, dst)
-            manifest[rel] = dst.stat().st_size
-        except (OSError, PermissionError) as exc:
-            logger.warning("Could not snapshot %s: %s", rel, exc)
-
-    if not manifest:
-        shutil.rmtree(snap_dir, ignore_errors=True)
-        return None
-
-    # Write manifest
-    meta = {
-        "id": snap_id,
-        "timestamp": ts,
-        "label": label,
-        "file_count": len(manifest),
-        "total_size": sum(manifest.values()),
-        "files": manifest,
-    }
-    with open(snap_dir / "manifest.json", "w") as f:
-        json.dump(meta, f, indent=2)
-
-    # Auto-prune
-    _prune_quick_snapshots(root, keep=_QUICK_DEFAULT_KEEP)
-
-    logger.info("State snapshot created: %s (%d files)", snap_id, len(manifest))
-    return snap_id
-
-
-def list_quick_snapshots(
-    limit: int = 20,
-    hermes_home: Optional[Path] = None,
-) -> List[Dict[str, Any]]:
-    """List existing quick state snapshots, most recent first."""
-    root = _quick_snapshot_root(hermes_home)
-    if not root.exists():
-        return []
-
-    results = []
-    for d in sorted(root.iterdir(), reverse=True):
-        if not d.is_dir():
-            continue
-        manifest_path = d / "manifest.json"
-        if manifest_path.exists():
-            try:
-                with open(manifest_path) as f:
-                    results.append(json.load(f))
-            except (json.JSONDecodeError, OSError):
-                results.append({"id": d.name, "file_count": 0, "total_size": 0})
-        if len(results) >= limit:
-            break
-
-    return results
-
-
-def restore_quick_snapshot(
-    snapshot_id: str,
-    hermes_home: Optional[Path] = None,
-) -> bool:
-    """Restore state from a quick snapshot.
-
-    Overwrites current state files with the snapshot's copies.
-    Returns True if at least one file was restored.
-    """
-    home = hermes_home or get_hermes_home()
-    root = _quick_snapshot_root(home)
-    snap_dir = root / snapshot_id
-
-    if not snap_dir.is_dir():
-        return False
-
-    manifest_path = snap_dir / "manifest.json"
-    if not manifest_path.exists():
-        return False
-
-    with open(manifest_path) as f:
-        meta = json.load(f)
-
-    restored = 0
-    for rel in meta.get("files", {}):
-        src = snap_dir / rel
-        if not src.exists():
-            continue
-
-        dst = home / rel
-        dst.parent.mkdir(parents=True, exist_ok=True)
-
-        try:
-            if dst.suffix == ".db":
-                # Atomic-ish replace for databases
-                tmp = dst.parent / f".{dst.name}.snap_restore"
-                shutil.copy2(src, tmp)
-                dst.unlink(missing_ok=True)
-                shutil.move(str(tmp), str(dst))
-            else:
-                shutil.copy2(src, dst)
-            restored += 1
-        except (OSError, PermissionError) as exc:
-            logger.error("Failed to restore %s: %s", rel, exc)
-
-    logger.info("Restored %d files from snapshot %s", restored, snapshot_id)
-    return restored > 0
-
-
-def _prune_quick_snapshots(root: Path, keep: int = _QUICK_DEFAULT_KEEP) -> int:
-    """Remove oldest quick snapshots beyond the keep limit. Returns count deleted."""
-    if not root.exists():
-        return 0
-
-    dirs = sorted(
-        (d for d in root.iterdir() if d.is_dir()),
-        key=lambda d: d.name,
-        reverse=True,
-    )
-
-    deleted = 0
-    for d in dirs[keep:]:
-        try:
-            shutil.rmtree(d)
-            deleted += 1
-        except OSError as exc:
-            logger.warning("Failed to prune snapshot %s: %s", d.name, exc)
-
-    return deleted
-
-
-def prune_quick_snapshots(
-    keep: int = _QUICK_DEFAULT_KEEP,
-    hermes_home: Optional[Path] = None,
-) -> int:
-    """Manually prune quick snapshots. Returns count deleted."""
-    return _prune_quick_snapshots(_quick_snapshot_root(hermes_home), keep=keep)
-
-
-def run_quick_backup(args) -> None:
-    """CLI entry point for hermes backup --quick."""
-    label = getattr(args, "label", None)
-    snap_id = create_quick_snapshot(label=label)
-    if snap_id:
-        print(f"State snapshot created: {snap_id}")
-        snaps = list_quick_snapshots()
-        print(f"  {len(snaps)} snapshot(s) stored in {display_hermes_home()}/state-snapshots/")
-        print(f"  Restore with: /snapshot restore {snap_id}")
-    else:
-        print("No state files found to snapshot.")

hermes_cli/banner.py

@@ -5,6 +5,7 @@ Pure display functions with no HermesCLI state dependency.
 
 import json
 import logging
+import os
 import shutil
 import subprocess
 import threading

hermes_cli/claw.py

@@ -1,9 +1,8 @@
 """hermes claw — OpenClaw migration commands.
 
 Usage:
-    hermes claw migrate              # Preview then migrate (always shows preview first)
-    hermes claw migrate --dry-run    # Preview only, no changes
-    hermes claw migrate --yes        # Skip confirmation prompt
+    hermes claw migrate              # Interactive migration from ~/.openclaw
+    hermes claw migrate --dry-run    # Preview what would be migrated
     hermes claw migrate --preset full --overwrite  # Full migration, overwrite conflicts
     hermes claw cleanup              # Archive leftover OpenClaw directories
     hermes claw cleanup --dry-run    # Preview what would be archived
@@ -11,7 +10,6 @@ Usage:
 
 import importlib.util
 import logging
-import subprocess
 import sys
 from datetime import datetime
 from pathlib import Path
@@ -51,138 +49,10 @@ _OPENCLAW_SCRIPT_INSTALLED = (
 )
 
 # Known OpenClaw directory names (current + legacy)
-_OPENCLAW_DIR_NAMES = (".openclaw", ".clawdbot", ".moltbot")
+_OPENCLAW_DIR_NAMES = (".openclaw", ".clawdbot", ".moldbot")
 
-def _detect_openclaw_processes() -> list[str]:
-    """Detect running OpenClaw processes and services.
-
-    Returns a list of human-readable descriptions of what was found.
-    An empty list means nothing was detected.
-    """
-    found: list[str] = []
-
-    # -- systemd service (Linux) ------------------------------------------
-    if sys.platform != "win32":
-        try:
-            result = subprocess.run(
-                ["systemctl", "--user", "is-active", "openclaw-gateway.service"],
-                capture_output=True, text=True, timeout=5,
-            )
-            if result.stdout.strip() == "active":
-                found.append("systemd service: openclaw-gateway.service")
-        except (FileNotFoundError, subprocess.TimeoutExpired):
-            pass
-
-    # -- process scan ------------------------------------------------------
-    if sys.platform == "win32":
-        try:
-            for exe in ("openclaw.exe", "clawd.exe"):
-                result = subprocess.run(
-                    ["tasklist", "/FI", f"IMAGENAME eq {exe}"],
-                    capture_output=True, text=True, timeout=5,
-                )
-                if exe in result.stdout.lower():
-                    found.append(f"process: {exe}")
-
-            # Node.js-hosted OpenClaw — tasklist doesn't show command lines,
-            # so fall back to PowerShell.
-            ps_cmd = (
-                'Get-CimInstance Win32_Process -Filter "Name = \'node.exe\'" | '
-                'Where-Object { $_.CommandLine -match "openclaw|clawd" } | '
-                'Select-Object -First 1 ProcessId'
-            )
-            result = subprocess.run(
-                ["powershell", "-NoProfile", "-Command", ps_cmd],
-                capture_output=True, text=True, timeout=5,
-            )
-            if result.stdout.strip():
-                found.append(f"node.exe process with openclaw in command line (PID {result.stdout.strip()})")
-        except Exception:
-            pass
-    else:
-        try:
-            result = subprocess.run(
-                ["pgrep", "-f", "openclaw"],
-                capture_output=True, text=True, timeout=3,
-            )
-            if result.returncode == 0:
-                pids = result.stdout.strip().split()
-                found.append(f"openclaw process(es) (PIDs: {', '.join(pids)})")
-        except (FileNotFoundError, subprocess.TimeoutExpired):
-            pass
-
-    return found
-
-
-def _warn_if_openclaw_running(auto_yes: bool) -> None:
-    """Warn if OpenClaw is still running before migration.
-
-    Telegram, Discord, and Slack only allow one active connection per bot
-    token. Migrating while OpenClaw is running causes both to fight for the
-    same token.
-    """
-    running = _detect_openclaw_processes()
-    if not running:
-        return
-
-    print()
-    print_error("OpenClaw appears to be running:")
-    for detail in running:
-        print_info(f"  * {detail}")
-    print_info(
-        "Messaging platforms (Telegram, Discord, Slack) only allow one "
-        "active session per bot token. If you continue, both OpenClaw and "
-        "Hermes may try to use the same token, causing disconnects."
-    )
-    print_info("Recommendation: stop OpenClaw before migrating.")
-    print()
-    if auto_yes:
-        return
-    if not sys.stdin.isatty():
-        print_info("Non-interactive session — continuing to preview only.")
-        return
-    if not prompt_yes_no("Continue anyway?", default=False):
-        print_info("Migration cancelled. Stop OpenClaw and try again.")
-        sys.exit(0)
-
-
-def _warn_if_gateway_running(auto_yes: bool) -> None:
-    """Check if a Hermes gateway is running with connected platforms.
-
-    Migrating bot tokens while the gateway is polling will cause conflicts
-    (e.g. Telegram 409 "terminated by other getUpdates request"). Warn the
-    user and let them decide whether to continue.
-    """
-    from gateway.status import get_running_pid, read_runtime_status
-
-    if not get_running_pid():
-        return
-
-    data = read_runtime_status() or {}
-    platforms = data.get("platforms") or {}
-    connected = [name for name, info in platforms.items()
-                 if isinstance(info, dict) and info.get("state") == "connected"]
-    if not connected:
-        return
-
-    print()
-    print_error(
-        "Hermes gateway is running with active connections: "
-        + ", ".join(connected)
-    )
-    print_info(
-        "Migrating bot tokens while the gateway is active will cause "
-        "conflicts (Telegram, Discord, and Slack only allow one active "
-        "session per token)."
-    )
-    print_info("Recommendation: stop the gateway first with 'hermes stop'.")
-    print()
-    if not auto_yes and not prompt_yes_no("Continue anyway?", default=False):
-        print_info("Migration cancelled. Stop the gateway and try again.")
-        sys.exit(0)
-
-# State files commonly found in OpenClaw workspace directories — listed
-# during cleanup to help the user decide whether to archive
+# State files commonly found in OpenClaw workspace directories that cause
+# confusion after migration (the agent discovers them and writes to them)
 _WORKSPACE_STATE_GLOBS = (
     "*/todo.json",
     "*/sessions/*",
@@ -227,7 +97,7 @@ def _find_openclaw_dirs() -> list[Path]:
 
 
 def _scan_workspace_state(source_dir: Path) -> list[tuple[Path, str]]:
-    """Scan an OpenClaw directory for workspace state files.
+    """Scan an OpenClaw directory for workspace state files that cause confusion.
 
     Returns a list of (path, description) tuples.
     """
@@ -310,7 +180,7 @@ def _cmd_migrate(args):
         source_dir = Path.home() / ".openclaw"
         if not source_dir.is_dir():
             # Try legacy directory names
-            for legacy in (".clawdbot", ".moltbot"):
+            for legacy in (".clawdbot", ".moldbot"):
                 candidate = Path.home() / legacy
                 if candidate.is_dir():
                     source_dir = candidate
@@ -367,12 +237,12 @@ def _cmd_migrate(args):
 
     # Show what we're doing
     hermes_home = get_hermes_home()
-    auto_yes = getattr(args, "yes", False)
     print()
     print_header("Migration Settings")
     print_info(f"Source:      {source_dir}")
     print_info(f"Target:      {hermes_home}")
     print_info(f"Preset:      {preset}")
+    print_info(f"Mode:        {'dry run (preview only)' if dry_run else 'execute'}")
     print_info(f"Overwrite:   {'yes' if overwrite else 'no (skip conflicts)'}")
     print_info(f"Secrets:     {'yes (allowlisted only)' if migrate_secrets else 'no'}")
     if skill_conflict != "skip":
@@ -381,88 +251,31 @@ def _cmd_migrate(args):
         print_info(f"Workspace:   {workspace_target}")
     print()
 
-    # Check if OpenClaw is still running — migrating tokens while both are
-    # active will cause conflicts (e.g. Telegram 409).
-    _warn_if_openclaw_running(auto_yes)
-
-    # Check if a Hermes gateway is running with connected platforms.
-    _warn_if_gateway_running(auto_yes)
+    # For execute mode (non-dry-run), confirm unless --yes was passed
+    if not dry_run and not getattr(args, "yes", False):
+        if not prompt_yes_no("Proceed with migration?", default=True):
+            print_info("Migration cancelled.")
+            return
 
     # Ensure config.yaml exists before migration tries to read it
     config_path = get_config_path()
     if not config_path.exists():
         save_config(load_config())
 
-    # Load the migration module
+    # Load and run the migration
     try:
         mod = _load_migration_module(script_path)
         if mod is None:
             print_error("Could not load migration script.")
             return
-    except Exception as e:
-        print()
-        print_error(f"Could not load migration script: {e}")
-        logger.debug("OpenClaw migration error", exc_info=True)
-        return
 
-    selected = mod.resolve_selected_options(None, None, preset=preset)
-    ws_target = Path(workspace_target).resolve() if workspace_target else None
+        selected = mod.resolve_selected_options(None, None, preset=preset)
+        ws_target = Path(workspace_target).resolve() if workspace_target else None
 
-    # ── Phase 1: Always preview first ──────────────────────────
-    try:
-        preview = mod.Migrator(
-            source_root=source_dir.resolve(),
-            target_root=hermes_home.resolve(),
-            execute=False,
-            workspace_target=ws_target,
-            overwrite=overwrite,
-            migrate_secrets=migrate_secrets,
-            output_dir=None,
-            selected_options=selected,
-            preset_name=preset,
-            skill_conflict_mode=skill_conflict,
-        )
-        preview_report = preview.migrate()
-    except Exception as e:
-        print()
-        print_error(f"Migration preview failed: {e}")
-        logger.debug("OpenClaw migration preview error", exc_info=True)
-        return
-
-    preview_summary = preview_report.get("summary", {})
-    preview_count = preview_summary.get("migrated", 0)
-
-    if preview_count == 0:
-        print()
-        print_info("Nothing to migrate from OpenClaw.")
-        _print_migration_report(preview_report, dry_run=True)
-        return
-
-    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_migration_report(preview_report, dry_run=True)
-
-    # If --dry-run, stop here
-    if dry_run:
-        return
-
-    # ── Phase 2: Confirm and execute ───────────────────────────
-    print()
-    if not auto_yes:
-        if not sys.stdin.isatty():
-            print_info("Non-interactive session — preview only.")
-            print_info("To execute, re-run with: hermes claw migrate --yes")
-            return
-        if not prompt_yes_no("Proceed with migration?", default=True):
-            print_info("Migration cancelled.")
-            return
-
-    try:
         migrator = mod.Migrator(
             source_root=source_dir.resolve(),
             target_root=hermes_home.resolve(),
-            execute=True,
+            execute=not dry_run,
             workspace_target=ws_target,
             overwrite=overwrite,
             migrate_secrets=migrate_secrets,
@@ -479,18 +292,62 @@ def _cmd_migrate(args):
         return
 
     # Print results
-    _print_migration_report(report, dry_run=False)
+    _print_migration_report(report, dry_run)
 
-    # Source directory is left untouched — archiving is not the migration
-    # tool's responsibility.  Users who want to clean up can run
-    # 'hermes claw cleanup' separately.
+    # After successful non-dry-run migration, offer to archive the source directory
+    if not dry_run and report.get("summary", {}).get("migrated", 0) > 0:
+        _offer_source_archival(source_dir, getattr(args, "yes", False))
+
+
+def _offer_source_archival(source_dir: Path, auto_yes: bool = False):
+    """After migration, offer to rename the source directory to prevent state fragmentation.
+
+    OpenClaw workspace directories contain state files (todo.json, sessions, etc.)
+    that the agent may discover and write to, causing confusion. Renaming the
+    directory prevents this.
+    """
+    if not source_dir.is_dir():
+        return
+
+    # Scan for state files that could cause problems
+    state_files = _scan_workspace_state(source_dir)
+
+    print()
+    print_header("Post-Migration Cleanup")
+    print_info("The OpenClaw directory still exists and contains workspace state files")
+    print_info("that can confuse the agent (todo lists, sessions, logs).")
+    if state_files:
+        print()
+        print(color("  Found state files:", Colors.YELLOW))
+        # Show up to 10 most relevant findings
+        for path, desc in state_files[:10]:
+            print(f"      {desc}")
+        if len(state_files) > 10:
+            print(f"      ... and {len(state_files) - 10} more")
+    print()
+    print_info(f"Recommend: rename {source_dir.name}/ to {source_dir.name}.pre-migration/")
+    print_info("This prevents the agent from discovering old workspace directories.")
+    print_info("You can always rename it back if needed.")
+    print()
+
+    if auto_yes or prompt_yes_no(f"Archive {source_dir} now?", default=True):
+        try:
+            archive_path = _archive_directory(source_dir)
+            print_success(f"Archived: {source_dir} → {archive_path}")
+            print_info("The original directory has been renamed, not deleted.")
+            print_info(f"To undo: mv {archive_path} {source_dir}")
+        except OSError as e:
+            print_error(f"Could not archive: {e}")
+            print_info(f"You can do it manually: mv {source_dir} {source_dir}.pre-migration")
+    else:
+        print_info("Skipped. You can archive later with: hermes claw cleanup")
 
 
 def _cmd_cleanup(args):
     """Archive leftover OpenClaw directories after migration.
 
     Scans for OpenClaw directories that still exist after migration and offers
-    to rename them to .pre-migration to free disk space.
+    to rename them to .pre-migration to prevent state fragmentation.
     """
     dry_run = getattr(args, "dry_run", False)
     auto_yes = getattr(args, "yes", False)
@@ -527,28 +384,6 @@ def _cmd_cleanup(args):
         print_success("No OpenClaw directories found. Nothing to clean up.")
         return
 
-    # Warn if OpenClaw is still running — archiving while the service is
-    # active causes it to recreate an empty skeleton directory (#8502).
-    running = _detect_openclaw_processes()
-    if running:
-        print()
-        print_error("OpenClaw appears to be still running:")
-        for detail in running:
-            print_info(f"  * {detail}")
-        print_info(
-            "Archiving .openclaw/ while the service is active may cause it to "
-            "immediately recreate an empty skeleton directory, destroying your config."
-        )
-        print_info("Stop OpenClaw first: systemctl --user stop openclaw-gateway.service")
-        print()
-        if not auto_yes:
-            if not sys.stdin.isatty():
-                print_info("Non-interactive session — aborting. Stop OpenClaw and re-run.")
-                return
-            if not prompt_yes_no("Proceed anyway?", default=False):
-                print_info("Aborted. Stop OpenClaw first, then re-run: hermes claw cleanup")
-                return
-
     total_archived = 0
 
     for source_dir in dirs_to_check:
@@ -587,7 +422,7 @@ def _cmd_cleanup(args):
 
         if state_files:
             print()
-            print(color(f"  {len(state_files)} state file(s) found:", Colors.YELLOW))
+            print(color(f"  {len(state_files)} state file(s) that could cause confusion:", Colors.YELLOW))
             for path, desc in state_files[:8]:
                 print(f"      {desc}")
             if len(state_files) > 8:
@@ -598,9 +433,6 @@ def _cmd_cleanup(args):
         if dry_run:
             archive_path = _archive_directory(source_dir, dry_run=True)
             print_info(f"Would archive: {source_dir} → {archive_path}")
-        elif not auto_yes and not sys.stdin.isatty():
-            print_info(f"Non-interactive session — would archive: {source_dir}")
-            print_info("To execute, re-run with: hermes claw cleanup --yes")
         else:
             if auto_yes or prompt_yes_no(f"Archive {source_dir}?", default=True):
                 try:

hermes_cli/cli_output.py

@@ -1,78 +0,0 @@
-"""Shared CLI output helpers for Hermes CLI modules.
-
-Extracts the identical ``print_info/success/warning/error`` and ``prompt()``
-functions previously duplicated across setup.py, tools_config.py,
-mcp_config.py, and memory_setup.py.
-"""
-
-import getpass
-
-from hermes_cli.colors import Colors, color
-
-
-# ─── Print Helpers ────────────────────────────────────────────────────────────
-
-
-def print_info(text: str) -> None:
-    """Print a dim informational message."""
-    print(color(f"  {text}", Colors.DIM))
-
-
-def print_success(text: str) -> None:
-    """Print a green success message with ✓ prefix."""
-    print(color(f"✓ {text}", Colors.GREEN))
-
-
-def print_warning(text: str) -> None:
-    """Print a yellow warning message with ⚠ prefix."""
-    print(color(f"⚠ {text}", Colors.YELLOW))
-
-
-def print_error(text: str) -> None:
-    """Print a red error message with ✗ prefix."""
-    print(color(f"✗ {text}", Colors.RED))
-
-
-def print_header(text: str) -> None:
-    """Print a bold yellow header."""
-    print(color(f"\n  {text}", Colors.YELLOW))
-
-
-# ─── Input Prompts ────────────────────────────────────────────────────────────
-
-
-def prompt(
-    question: str,
-    default: str | None = None,
-    password: bool = False,
-) -> str:
-    """Prompt the user for input with optional default and password masking.
-
-    Replaces the four independent ``_prompt()`` / ``prompt()`` implementations
-    in setup.py, tools_config.py, mcp_config.py, and memory_setup.py.
-
-    Returns the user's input (stripped), or *default* if the user presses Enter.
-    Returns empty string on Ctrl-C or EOF.
-    """
-    suffix = f" [{default}]" if default else ""
-    display = color(f"  {question}{suffix}: ", Colors.YELLOW)
-
-    try:
-        if password:
-            value = getpass.getpass(display)
-        else:
-            value = input(display)
-        value = value.strip()
-        return value if value else (default or "")
-    except (KeyboardInterrupt, EOFError):
-        print()
-        return ""
-
-
-def prompt_yes_no(question: str, default: bool = True) -> bool:
-    """Prompt for a yes/no answer. Returns bool."""
-    hint = "Y/n" if default else "y/N"
-    answer = prompt(f"{question} ({hint})")
-    if not answer:
-        return default
-    return answer.lower().startswith("y")

hermes_cli/clipboard.py

@@ -19,10 +19,11 @@ import subprocess
 import sys
 from pathlib import Path
 
-from hermes_constants import is_wsl as _is_wsl
-
 logger = logging.getLogger(__name__)
 
+# Cache WSL detection (checked once per process)
+_wsl_detected: bool | None = None
+
 
 def save_clipboard_image(dest: Path) -> bool:
     """Extract an image from the system clipboard and save it as PNG.
@@ -216,6 +217,19 @@ def _windows_save(dest: Path) -> bool:
 
 # ── Linux ────────────────────────────────────────────────────────────────
 
+def _is_wsl() -> bool:
+    """Detect if running inside WSL (1 or 2)."""
+    global _wsl_detected
+    if _wsl_detected is not None:
+        return _wsl_detected
+    try:
+        with open("/proc/version", "r") as f:
+            _wsl_detected = "microsoft" in f.read().lower()
+    except Exception:
+        _wsl_detected = False
+    return _wsl_detected
+
+
 def _linux_save(dest: Path) -> bool:
     """Try clipboard backends in priority order: WSL → Wayland → X11."""
     if _is_wsl():

hermes_cli/commands.py

@@ -69,12 +69,9 @@ COMMAND_REGISTRY: list[CommandDef] = [
                args_hint="[name]"),
     CommandDef("branch", "Branch the current session (explore a different path)", "Session",
                aliases=("fork",), args_hint="[name]"),
-    CommandDef("compress", "Manually compress conversation context", "Session",
-               args_hint="[focus topic]"),
+    CommandDef("compress", "Manually compress conversation context", "Session"),
     CommandDef("rollback", "List or restore filesystem checkpoints", "Session",
                args_hint="[number]"),
-    CommandDef("snapshot", "Create or restore state snapshots of Hermes config/state", "Session",
-               aliases=("snap",), args_hint="[create|restore <id>|prune]"),
     CommandDef("stop", "Kill all running background processes", "Session"),
     CommandDef("approve", "Approve a pending dangerous command", "Session",
                gateway_only=True, args_hint="[session|always]"),
@@ -131,7 +128,6 @@ COMMAND_REGISTRY: list[CommandDef] = [
     CommandDef("cron", "Manage scheduled tasks", "Tools & Skills",
                cli_only=True, args_hint="[subcommand]",
                subcommands=("list", "add", "create", "edit", "pause", "resume", "run", "remove")),
-    CommandDef("reload", "Reload .env variables into the running session", "Tools & Skills"),
     CommandDef("reload-mcp", "Reload MCP servers from config", "Tools & Skills",
                aliases=("reload_mcp",)),
     CommandDef("browser", "Connect browser tools to your live Chrome via CDP", "Tools & Skills",
@@ -144,8 +140,6 @@ 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("restart", "Gracefully restart the gateway after draining active runs", "Session",
-               gateway_only=True),
     CommandDef("usage", "Show token usage and rate limits for the current session", "Info"),
     CommandDef("insights", "Show usage insights and analytics", "Info",
                args_hint="[days]"),
@@ -157,7 +151,6 @@ COMMAND_REGISTRY: list[CommandDef] = [
                cli_only=True, args_hint="<path>"),
     CommandDef("update", "Update Hermes Agent to the latest version", "Info",
                gateway_only=True),
-    CommandDef("debug", "Upload debug report (system info + logs) and get shareable links", "Info"),
 
     # Exit
     CommandDef("quit", "Exit the CLI", "Exit",
@@ -190,6 +183,52 @@ def resolve_command(name: str) -> CommandDef | None:
     return _COMMAND_LOOKUP.get(name.lower().lstrip("/"))
 
 
+def rebuild_lookups() -> None:
+    """Rebuild all derived lookup dicts from the current COMMAND_REGISTRY.
+
+    Called after plugin commands are registered so they appear in help,
+    autocomplete, gateway dispatch, Telegram menu, and Slack mapping.
+    """
+    global GATEWAY_KNOWN_COMMANDS
+
+    _COMMAND_LOOKUP.clear()
+    _COMMAND_LOOKUP.update(_build_command_lookup())
+
+    COMMANDS.clear()
+    for cmd in COMMAND_REGISTRY:
+        if not cmd.gateway_only:
+            COMMANDS[f"/{cmd.name}"] = _build_description(cmd)
+            for alias in cmd.aliases:
+                COMMANDS[f"/{alias}"] = f"{cmd.description} (alias for /{cmd.name})"
+
+    COMMANDS_BY_CATEGORY.clear()
+    for cmd in COMMAND_REGISTRY:
+        if not cmd.gateway_only:
+            cat = COMMANDS_BY_CATEGORY.setdefault(cmd.category, {})
+            cat[f"/{cmd.name}"] = COMMANDS[f"/{cmd.name}"]
+            for alias in cmd.aliases:
+                cat[f"/{alias}"] = COMMANDS[f"/{alias}"]
+
+    SUBCOMMANDS.clear()
+    for cmd in COMMAND_REGISTRY:
+        if cmd.subcommands:
+            SUBCOMMANDS[f"/{cmd.name}"] = list(cmd.subcommands)
+    for cmd in COMMAND_REGISTRY:
+        key = f"/{cmd.name}"
+        if key in SUBCOMMANDS or not cmd.args_hint:
+            continue
+        m = _PIPE_SUBS_RE.search(cmd.args_hint)
+        if m:
+            SUBCOMMANDS[key] = m.group(0).split("|")
+
+    GATEWAY_KNOWN_COMMANDS = frozenset(
+        name
+        for cmd in COMMAND_REGISTRY
+        if not cmd.cli_only or cmd.gateway_config_gate
+        for name in (cmd.name, *cmd.aliases)
+    )
+
+
 def _build_description(cmd: CommandDef) -> str:
     """Build a CLI-facing description string including usage hint."""
     if cmd.args_hint:

hermes_cli/config.py

@@ -32,15 +32,13 @@ _ENV_VAR_NAME_RE = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*$")
 _EXTRA_ENV_KEYS = frozenset({
     "OPENAI_API_KEY", "OPENAI_BASE_URL",
     "ANTHROPIC_API_KEY", "ANTHROPIC_TOKEN",
+    "AUXILIARY_VISION_MODEL",
     "DISCORD_HOME_CHANNEL", "TELEGRAM_HOME_CHANNEL",
     "SIGNAL_ACCOUNT", "SIGNAL_HTTP_URL",
     "SIGNAL_ALLOWED_USERS", "SIGNAL_GROUP_ALLOWED_USERS",
     "DINGTALK_CLIENT_ID", "DINGTALK_CLIENT_SECRET",
     "FEISHU_APP_ID", "FEISHU_APP_SECRET", "FEISHU_ENCRYPT_KEY", "FEISHU_VERIFICATION_TOKEN",
     "WECOM_BOT_ID", "WECOM_SECRET",
-    "WECOM_CALLBACK_CORP_ID", "WECOM_CALLBACK_CORP_SECRET", "WECOM_CALLBACK_AGENT_ID",
-    "WECOM_CALLBACK_TOKEN", "WECOM_CALLBACK_ENCODING_AES_KEY",
-    "WECOM_CALLBACK_HOST", "WECOM_CALLBACK_PORT",
     "WEIXIN_ACCOUNT_ID", "WEIXIN_TOKEN", "WEIXIN_BASE_URL", "WEIXIN_CDN_BASE_URL",
     "WEIXIN_HOME_CHANNEL", "WEIXIN_HOME_CHANNEL_NAME", "WEIXIN_DM_POLICY", "WEIXIN_GROUP_POLICY",
     "WEIXIN_ALLOWED_USERS", "WEIXIN_GROUP_ALLOWED_USERS", "WEIXIN_ALLOW_ALL_USERS",
@@ -50,7 +48,6 @@ _EXTRA_ENV_KEYS = frozenset({
     "MATTERMOST_HOME_CHANNEL", "MATTERMOST_REPLY_MODE",
     "MATRIX_PASSWORD", "MATRIX_ENCRYPTION", "MATRIX_DEVICE_ID", "MATRIX_HOME_ROOM",
     "MATRIX_REQUIRE_MENTION", "MATRIX_FREE_RESPONSE_ROOMS", "MATRIX_AUTO_THREAD",
-    "MATRIX_RECOVERY_KEY",
 })
 import yaml
 
@@ -148,25 +145,41 @@ def managed_error(action: str = "modify configuration"):
 # Container-aware CLI (NixOS container mode)
 # =============================================================================
 
+def _is_inside_container() -> bool:
+    """Detect if we're already running inside a Docker/Podman container."""
+    # Standard Docker/Podman indicators
+    if os.path.exists("/.dockerenv"):
+        return True
+    # Podman uses /run/.containerenv
+    if os.path.exists("/run/.containerenv"):
+        return True
+    # Check cgroup for container runtime evidence (works for both Docker & Podman)
+    try:
+        with open("/proc/1/cgroup", "r") as f:
+            cgroup = f.read()
+            if "docker" in cgroup or "podman" in cgroup or "/lxc/" in cgroup:
+                return True
+    except (OSError, IOError):
+        pass
+    return False
+
+
 def get_container_exec_info() -> Optional[dict]:
     """Read container mode metadata from HERMES_HOME/.container-mode.
 
-    Returns a dict with keys: backend, container_name, exec_user, hermes_bin
-    or None if container mode is not active, we're already inside the
-    container, or HERMES_DEV=1 is set.
+    Returns a dict with keys: backend, container_name, hermes_bin
+    or None if container mode is not active or we're already inside the container.
 
     The .container-mode file is written by the NixOS activation script when
     container.enable = true. It tells the host CLI to exec into the container
     instead of running locally.
     """
-    if os.environ.get("HERMES_DEV") == "1":
-        return None
-
-    from hermes_constants import is_container
-    if is_container():
+    if _is_inside_container():
         return None
 
     container_mode_file = get_hermes_home() / ".container-mode"
+    if not container_mode_file.exists():
+        return None
 
     try:
         info = {}
@@ -176,21 +189,18 @@ def get_container_exec_info() -> Optional[dict]:
                 if "=" in line and not line.startswith("#"):
                     key, _, value = line.partition("=")
                     info[key.strip()] = value.strip()
-    except FileNotFoundError:
+
+        backend = info.get("backend", "docker")
+        container_name = info.get("container_name", "hermes-agent")
+        hermes_bin = info.get("hermes_bin", "/data/current-package/bin/hermes")
+
+        return {
+            "backend": backend,
+            "container_name": container_name,
+            "hermes_bin": hermes_bin,
+        }
+    except (OSError, IOError):
         return None
-    # All other exceptions (PermissionError, malformed data, etc.) propagate
-
-    backend = info.get("backend", "docker")
-    container_name = info.get("container_name", "hermes-agent")
-    exec_user = info.get("exec_user", "hermes")
-    hermes_bin = info.get("hermes_bin", "/data/current-package/bin/hermes")
-
-    return {
-        "backend": backend,
-        "container_name": container_name,
-        "exec_user": exec_user,
-        "hermes_bin": hermes_bin,
-    }
 
 
 # =============================================================================
@@ -321,11 +331,6 @@ DEFAULT_CONFIG = {
         # tools or receiving API responses.  Only fires when the agent has
         # been completely idle for this duration.  0 = unlimited.
         "gateway_timeout": 1800,
-        # Graceful drain timeout for gateway stop/restart (seconds).
-        # The gateway stops accepting new work, waits for running agents
-        # to finish, then interrupts any remaining runs after the timeout.
-        # 0 = no drain, interrupt immediately.
-        "restart_drain_timeout": 60,
         "service_tier": "",
         # Tool-use enforcement: injects system prompt guidance that tells the
         # model to actually call tools instead of describing intended actions.
@@ -337,10 +342,6 @@ DEFAULT_CONFIG = {
         # 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,
-        # Periodic "still working" notification interval (seconds).
-        # Sends a status message every N seconds so the user knows the
-        # agent hasn't died during long tasks.  0 = disable notifications.
-        "gateway_notify_interval": 600,
     },
     
     "terminal": {
@@ -414,7 +415,9 @@ DEFAULT_CONFIG = {
         "threshold": 0.50,            # compress when context usage exceeds this ratio
         "target_ratio": 0.20,         # fraction of threshold to preserve as recent tail
         "protect_last_n": 20,         # minimum recent messages to keep uncompressed
-
+        "summary_model": "",          # empty = use main configured model
+        "summary_provider": "auto",
+        "summary_base_url": None,
     },
     "smart_model_routing": {
         "enabled": False,
@@ -435,7 +438,7 @@ DEFAULT_CONFIG = {
             "model": "",           # e.g. "google/gemini-2.5-flash", "gpt-4o"
             "base_url": "",        # direct OpenAI-compatible endpoint (takes precedence over provider)
             "api_key": "",         # API key for base_url (falls back to OPENAI_API_KEY)
-            "timeout": 120,        # seconds — LLM API call timeout; vision payloads need generous timeout
+            "timeout": 30,         # seconds — LLM API call timeout; increase for slow local vision models
             "download_timeout": 30,  # seconds — image HTTP download timeout; increase for slow connections
         },
         "web_extract": {
@@ -500,11 +503,9 @@ DEFAULT_CONFIG = {
         "inline_diffs": True,     # Show inline diff previews for write actions (write_file, patch, skill_manage)
         "show_cost": False,       # Show $ cost in the status bar (off by default)
         "skin": "default",
-        "interim_assistant_messages": True,  # Gateway: show natural mid-turn assistant status messages
         "tool_progress_command": False,  # Enable /verbose command in messaging gateway
-        "tool_progress_overrides": {},  # DEPRECATED — use display.platforms instead
+        "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)
-        "platforms": {},  # Per-platform display overrides: {"telegram": {"tool_progress": "all"}, "slack": {"tool_progress": "off"}}
     },
 
     # Privacy settings
@@ -514,7 +515,7 @@ DEFAULT_CONFIG = {
     
     # Text-to-speech configuration
     "tts": {
-        "provider": "edge",  # "edge" (free) | "elevenlabs" (premium) | "openai" | "minimax" | "mistral" | "neutts" (local)
+        "provider": "edge",  # "edge" (free) | "elevenlabs" (premium) | "openai" | "neutts" (local)
         "edge": {
             "voice": "en-US-AriaNeural",
             # Popular: AriaNeural, JennyNeural, AndrewNeural, BrianNeural, SoniaNeural
@@ -528,10 +529,6 @@ DEFAULT_CONFIG = {
             "voice": "alloy",
             # Voices: alloy, echo, fable, onyx, nova, shimmer
         },
-        "mistral": {
-            "model": "voxtral-mini-tts-2603",
-            "voice_id": "c69964a6-ab8b-4f8a-9465-ec0925096ec8",  # Paul - Neutral
-        },
         "neutts": {
             "ref_audio": "",  # Path to reference voice audio (empty = bundled default)
             "ref_text": "",   # Path to reference voice transcript (empty = bundled default)
@@ -569,16 +566,6 @@ DEFAULT_CONFIG = {
         "max_ms": 2500,
     },
     
-    # Context engine -- controls how the context window is managed when
-    # approaching the model's token limit.
-    # "compressor" = built-in lossy summarization (default).
-    # Set to a plugin name to activate an alternative engine (e.g. "lcm"
-    # for Lossless Context Management).  The engine must be installed as
-    # a plugin in plugins/context_engine/<name>/ or ~/.hermes/plugins/.
-    "context": {
-        "engine": "compressor",
-    },
-
     # Persistent memory -- bounded curated memory injected into system prompt
     "memory": {
         "memory_enabled": True,
@@ -603,8 +590,6 @@ DEFAULT_CONFIG = {
         "api_key": "",     # API key for delegation.base_url (falls back to OPENAI_API_KEY)
         "max_iterations": 50,  # per-subagent iteration cap (each subagent gets its own budget,
                                # independent of the parent's max_iterations)
-        "reasoning_effort": "",  # reasoning effort for subagents: "xhigh", "high", "medium",
-                                 # "low", "minimal", "none" (empty = inherit parent's level)
     },
 
     # Ephemeral prefill messages file — JSON list of {role, content} dicts
@@ -691,16 +676,8 @@ DEFAULT_CONFIG = {
         "backup_count": 3,     # Number of rotated backup files to keep
     },
 
-    # Network settings — workarounds for connectivity issues.
-    "network": {
-        # Force IPv4 connections.  On servers with broken or unreachable IPv6,
-        # Python tries AAAA records first and hangs for the full TCP timeout
-        # before falling back to IPv4.  Set to true to skip IPv6 entirely.
-        "force_ipv4": False,
-    },
-
     # Config schema version - bump this when adding new required fields
-    "_config_version": 17,
+    "_config_version": 14,
 }
 
 # =============================================================================
@@ -816,30 +793,6 @@ OPTIONAL_ENV_VARS = {
         "category": "provider",
         "advanced": True,
     },
-    "KIMI_CN_API_KEY": {
-        "description": "Kimi / Moonshot China API key",
-        "prompt": "Kimi (China) API key",
-        "url": "https://platform.moonshot.cn/",
-        "password": True,
-        "category": "provider",
-        "advanced": True,
-    },
-    "ARCEEAI_API_KEY": {
-        "description": "Arcee AI API key",
-        "prompt": "Arcee AI API key",
-        "url": "https://chat.arcee.ai/",
-        "password": True,
-        "category": "provider",
-        "advanced": True,
-    },
-    "ARCEE_BASE_URL": {
-        "description": "Arcee AI base URL override",
-        "prompt": "Arcee base URL (leave empty for default)",
-        "url": None,
-        "password": False,
-        "category": "provider",
-        "advanced": True,
-    },
     "MINIMAX_API_KEY": {
         "description": "MiniMax API key (international)",
         "prompt": "MiniMax API key",
@@ -956,21 +909,6 @@ OPTIONAL_ENV_VARS = {
         "category": "provider",
         "advanced": True,
     },
-    "XIAOMI_API_KEY": {
-        "description": "Xiaomi MiMo API key for MiMo models (mimo-v2-pro, mimo-v2-omni, mimo-v2-flash)",
-        "prompt": "Xiaomi MiMo API Key",
-        "url": "https://platform.xiaomimimo.com",
-        "password": True,
-        "category": "provider",
-    },
-    "XIAOMI_BASE_URL": {
-        "description": "Xiaomi MiMo base URL override (default: https://api.xiaomimimo.com/v1)",
-        "prompt": "Xiaomi base URL (leave empty for default)",
-        "url": None,
-        "password": False,
-        "category": "provider",
-        "advanced": True,
-    },
 
     # ── Tool API keys ──
     "EXA_API_KEY": {
@@ -1123,13 +1061,6 @@ OPTIONAL_ENV_VARS = {
         "password": True,
         "category": "tool",
     },
-    "MISTRAL_API_KEY": {
-        "description": "Mistral API key for Voxtral TTS and transcription (STT)",
-        "prompt": "Mistral API key",
-        "url": "https://console.mistral.ai/",
-        "password": True,
-        "category": "tool",
-    },
     "GITHUB_TOKEN": {
         "description": "GitHub token for Skills Hub (higher API rate limits, skill publish)",
         "prompt": "GitHub Token",
@@ -1192,7 +1123,7 @@ OPTIONAL_ENV_VARS = {
     "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, "
-                       "im:history, im:read, im:write, users:read, files:read, files:write",
+                       "im:history, im:read, im:write, users:read, files:write",
         "prompt": "Slack Bot Token (xoxb-...)",
         "url": "https://api.slack.com/apps",
         "password": True,
@@ -1302,14 +1233,6 @@ OPTIONAL_ENV_VARS = {
         "category": "messaging",
         "advanced": True,
     },
-    "MATRIX_RECOVERY_KEY": {
-        "description": "Matrix recovery key for cross-signing verification after device key rotation (from Element: Settings → Security → Recovery Key)",
-        "prompt": "Matrix recovery key",
-        "url": None,
-        "password": True,
-        "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",
@@ -1568,137 +1491,6 @@ def get_missing_skill_config_vars() -> List[Dict[str, Any]]:
     return missing
 
 
-def _normalize_custom_provider_entry(
-    entry: Any,
-    *,
-    provider_key: str = "",
-) -> Optional[Dict[str, Any]]:
-    """Return a runtime-compatible custom provider entry or ``None``."""
-    if not isinstance(entry, dict):
-        return None
-
-    base_url = ""
-    for url_key in ("api", "url", "base_url"):
-        raw_url = entry.get(url_key)
-        if isinstance(raw_url, str) and raw_url.strip():
-            base_url = raw_url.strip()
-            break
-    if not base_url:
-        return None
-
-    name = ""
-    raw_name = entry.get("name")
-    if isinstance(raw_name, str) and raw_name.strip():
-        name = raw_name.strip()
-    elif provider_key.strip():
-        name = provider_key.strip()
-    if not name:
-        return None
-
-    normalized: Dict[str, Any] = {
-        "name": name,
-        "base_url": base_url,
-    }
-
-    provider_key = provider_key.strip()
-    if provider_key:
-        normalized["provider_key"] = provider_key
-
-    api_key = entry.get("api_key")
-    if isinstance(api_key, str) and api_key.strip():
-        normalized["api_key"] = api_key.strip()
-
-    key_env = entry.get("key_env")
-    if isinstance(key_env, str) and key_env.strip():
-        normalized["key_env"] = key_env.strip()
-
-    api_mode = entry.get("api_mode") or entry.get("transport")
-    if isinstance(api_mode, str) and api_mode.strip():
-        normalized["api_mode"] = api_mode.strip()
-
-    model_name = entry.get("model") or entry.get("default_model")
-    if isinstance(model_name, str) and model_name.strip():
-        normalized["model"] = model_name.strip()
-
-    models = entry.get("models")
-    if isinstance(models, dict) and models:
-        normalized["models"] = models
-
-    context_length = entry.get("context_length")
-    if isinstance(context_length, int) and context_length > 0:
-        normalized["context_length"] = context_length
-
-    rate_limit_delay = entry.get("rate_limit_delay")
-    if isinstance(rate_limit_delay, (int, float)) and rate_limit_delay >= 0:
-        normalized["rate_limit_delay"] = rate_limit_delay
-
-    return normalized
-
-
-def providers_dict_to_custom_providers(providers_dict: Any) -> List[Dict[str, Any]]:
-    """Normalize ``providers`` config entries into the legacy custom-provider shape."""
-    if not isinstance(providers_dict, dict):
-        return []
-
-    custom_providers: List[Dict[str, Any]] = []
-    for key, entry in providers_dict.items():
-        normalized = _normalize_custom_provider_entry(entry, provider_key=str(key))
-        if normalized is not None:
-            custom_providers.append(normalized)
-
-    return custom_providers
-
-
-def get_compatible_custom_providers(
-    config: Optional[Dict[str, Any]] = None,
-) -> List[Dict[str, Any]]:
-    """Return a deduplicated custom-provider view across legacy and v12+ config.
-
-    ``custom_providers`` remains the on-disk legacy format, while ``providers``
-    is the newer keyed schema.  Runtime and picker flows still need a single
-    list-shaped view, but we should not materialise that compatibility layer
-    back into config.yaml because it duplicates entries in UIs.
-    """
-    if config is None:
-        config = load_config()
-
-    compatible: List[Dict[str, Any]] = []
-    seen_provider_keys: set = set()
-    seen_name_url_pairs: set = set()
-
-    def _append_if_new(entry: Optional[Dict[str, Any]]) -> None:
-        if entry is None:
-            return
-        provider_key = str(entry.get("provider_key", "") or "").strip().lower()
-        name = str(entry.get("name", "") or "").strip().lower()
-        base_url = str(entry.get("base_url", "") or "").strip().rstrip("/").lower()
-        model = str(entry.get("model", "") or "").strip().lower()
-        pair = (name, base_url, model)
-
-        if provider_key and provider_key in seen_provider_keys:
-            return
-        if name and base_url and pair in seen_name_url_pairs:
-            return
-
-        compatible.append(entry)
-        if provider_key:
-            seen_provider_keys.add(provider_key)
-        if name and base_url:
-            seen_name_url_pairs.add(pair)
-
-    custom_providers = config.get("custom_providers")
-    if custom_providers is not None:
-        if not isinstance(custom_providers, list):
-            return []
-        for entry in custom_providers:
-            _append_if_new(_normalize_custom_provider_entry(entry))
-
-    for entry in providers_dict_to_custom_providers(config.get("providers")):
-        _append_if_new(entry)
-
-    return compatible
-
-
 def check_config_version() -> Tuple[int, int]:
     """
     Check config version.
@@ -1720,12 +1512,12 @@ _KNOWN_ROOT_KEYS = {
     "_config_version", "model", "providers", "fallback_model",
     "fallback_providers", "credential_pool_strategies", "toolsets",
     "agent", "terminal", "display", "compression", "delegation",
-    "auxiliary", "custom_providers", "context", "memory", "gateway",
+    "auxiliary", "custom_providers", "memory", "gateway",
 }
 
 # Valid fields inside a custom_providers list entry
 _VALID_CUSTOM_PROVIDER_FIELDS = {
-    "name", "base_url", "api_key", "api_mode", "model", "models",
+    "name", "base_url", "api_key", "api_mode", "models",
     "context_length", "rate_limit_delay",
 }
 
@@ -2016,8 +1808,8 @@ def migrate_config(interactive: bool = True, quiet: bool = False) -> Dict[str, A
 
             if migrated_count > 0:
                 config["providers"] = providers_dict
-                # Remove the old list — runtime reads via get_compatible_custom_providers()
-                config.pop("custom_providers", None)
+                # Remove the old list
+                del config["custom_providers"]
                 save_config(config)
                 if not quiet:
                     print(f"  ✓ Migrated {migrated_count} custom provider(s) to providers: section")
@@ -2090,81 +1882,6 @@ def migrate_config(interactive: bool = True, quiet: bool = False) -> Dict[str, A
             if not quiet:
                 print(f"  ✓ Migrated legacy stt.model to provider-specific config")
 
-    # ── Version 14 → 15: add explicit gateway interim-message gate ──
-    if current_ver < 15:
-        config = read_raw_config()
-        display = config.get("display", {})
-        if not isinstance(display, dict):
-            display = {}
-        if "interim_assistant_messages" not in display:
-            display["interim_assistant_messages"] = True
-            config["display"] = display
-            results["config_added"].append("display.interim_assistant_messages=true (default)")
-            save_config(config)
-            if not quiet:
-                print("  ✓ Added display.interim_assistant_messages=true")
-
-    # ── Version 15 → 16: migrate tool_progress_overrides into display.platforms ──
-    if current_ver < 16:
-        config = read_raw_config()
-        display = config.get("display", {})
-        if not isinstance(display, dict):
-            display = {}
-        old_overrides = display.get("tool_progress_overrides")
-        if isinstance(old_overrides, dict) and old_overrides:
-            platforms = display.get("platforms", {})
-            if not isinstance(platforms, dict):
-                platforms = {}
-            for plat, mode in old_overrides.items():
-                if plat not in platforms:
-                    platforms[plat] = {}
-                if "tool_progress" not in platforms[plat]:
-                    platforms[plat]["tool_progress"] = mode
-            display["platforms"] = platforms
-            config["display"] = display
-            save_config(config)
-            if not quiet:
-                migrated = ", ".join(f"{p}={m}" for p, m in old_overrides.items())
-                print(f"  ✓ Migrated tool_progress_overrides → display.platforms: {migrated}")
-            results["config_added"].append("display.platforms (migrated from tool_progress_overrides)")
-
-    # ── Version 16 → 17: remove legacy compression.summary_* keys ──
-    if current_ver < 17:
-        config = read_raw_config()
-        comp = config.get("compression", {})
-        if isinstance(comp, dict):
-            s_model = comp.pop("summary_model", None)
-            s_provider = comp.pop("summary_provider", None)
-            s_base_url = comp.pop("summary_base_url", None)
-            migrated_keys = []
-            # Migrate non-empty, non-default values to auxiliary.compression
-            if s_model and str(s_model).strip():
-                aux = config.setdefault("auxiliary", {})
-                aux_comp = aux.setdefault("compression", {})
-                if not aux_comp.get("model"):
-                    aux_comp["model"] = str(s_model).strip()
-                    migrated_keys.append(f"model={s_model}")
-            if s_provider and str(s_provider).strip() not in ("", "auto"):
-                aux = config.setdefault("auxiliary", {})
-                aux_comp = aux.setdefault("compression", {})
-                if not aux_comp.get("provider") or aux_comp.get("provider") == "auto":
-                    aux_comp["provider"] = str(s_provider).strip()
-                    migrated_keys.append(f"provider={s_provider}")
-            if s_base_url and str(s_base_url).strip():
-                aux = config.setdefault("auxiliary", {})
-                aux_comp = aux.setdefault("compression", {})
-                if not aux_comp.get("base_url"):
-                    aux_comp["base_url"] = str(s_base_url).strip()
-                    migrated_keys.append(f"base_url={s_base_url}")
-            if migrated_keys or s_model is not None or s_provider is not None or s_base_url is not None:
-                config["compression"] = comp
-                save_config(config)
-                if not quiet:
-                    if migrated_keys:
-                        print(f"  ✓ Migrated compression.summary_* → auxiliary.compression: {', '.join(migrated_keys)}")
-                    else:
-                        print("  ✓ Removed unused compression.summary_* keys")
-
     if current_ver < latest_ver and not quiet:
         print(f"Config version: {current_ver} → {latest_ver}")
     
@@ -2477,7 +2194,6 @@ _FALLBACK_COMMENT = """
 #   nous         (OAuth — hermes auth) — Nous Portal
 #   zai          (ZAI_API_KEY)         — Z.AI / GLM
 #   kimi-coding  (KIMI_API_KEY)        — Kimi / Moonshot
-#   kimi-coding-cn (KIMI_CN_API_KEY)   — Kimi / Moonshot (China)
 #   minimax      (MINIMAX_API_KEY)     — MiniMax
 #   minimax-cn   (MINIMAX_CN_API_KEY)  — MiniMax (China)
 #
@@ -2521,7 +2237,6 @@ _COMMENTED_SECTIONS = """
 #   nous         (OAuth — hermes auth) — Nous Portal
 #   zai          (ZAI_API_KEY)         — Z.AI / GLM
 #   kimi-coding  (KIMI_API_KEY)        — Kimi / Moonshot
-#   kimi-coding-cn (KIMI_CN_API_KEY)   — Kimi / Moonshot (China)
 #   minimax      (MINIMAX_API_KEY)     — MiniMax
 #   minimax-cn   (MINIMAX_CN_API_KEY)  — MiniMax (China)
 #
@@ -2576,13 +2291,7 @@ def save_config(config: Dict[str, Any]):
 
 
 def load_env() -> Dict[str, str]:
-    """Load environment variables from ~/.hermes/.env.
-
-    Sanitizes lines before parsing so that corrupted files (e.g.
-    concatenated KEY=VALUE pairs on a single line) are handled
-    gracefully instead of producing mangled values such as duplicated
-    bot tokens.  See #8908.
-    """
+    """Load environment variables from ~/.hermes/.env."""
     env_path = get_env_path()
     env_vars = {}
     
@@ -2591,21 +2300,17 @@ def load_env() -> Dict[str, str]:
         # fail on UTF-8 .env files. Use explicit UTF-8 only on Windows.
         open_kw = {"encoding": "utf-8", "errors": "replace"} if _IS_WINDOWS else {}
         with open(env_path, **open_kw) as f:
-            raw_lines = f.readlines()
-        # Sanitize before parsing: split concatenated lines & drop stale
-        # placeholders so corrupted .env files don't produce invalid tokens.
-        lines = _sanitize_env_lines(raw_lines)
-        for line in lines:
-            line = line.strip()
-            if line and not line.startswith('#') and '=' in line:
-                key, _, value = line.partition('=')
-                env_vars[key.strip()] = value.strip().strip('"\'')
+            for line in f:
+                line = line.strip()
+                if line and not line.startswith('#') and '=' in line:
+                    key, _, value = line.partition('=')
+                    env_vars[key.strip()] = value.strip().strip('"\'')
     
     return env_vars
 
 
 def _sanitize_env_lines(lines: list) -> list:
-    """Fix corrupted .env lines before reading or writing.
+    """Fix corrupted .env lines before writing.
 
     Handles two known corruption patterns:
     1. Concatenated KEY=VALUE pairs on a single line (missing newline between
@@ -2838,28 +2543,6 @@ def save_env_value_secure(key: str, value: str) -> Dict[str, Any]:
 
 
 
-def reload_env() -> int:
-    """Re-read ~/.hermes/.env into os.environ. Returns count of vars updated.
-
-    Adds/updates vars that changed and removes vars that were deleted from
-    the .env file (but only vars known to Hermes — OPTIONAL_ENV_VARS and
-    _EXTRA_ENV_KEYS — to avoid clobbering unrelated environment).
-    """
-    env_vars = load_env()
-    known_keys = set(OPTIONAL_ENV_VARS.keys()) | _EXTRA_ENV_KEYS
-    count = 0
-    for key, value in env_vars.items():
-        if os.environ.get(key) != value:
-            os.environ[key] = value
-            count += 1
-    # Remove known Hermes vars that are no longer in .env
-    for key in known_keys:
-        if key not in env_vars and key in os.environ:
-            del os.environ[key]
-            count += 1
-    return count
-
-
 def get_env_value(key: str) -> Optional[str]:
     """Get a value from ~/.hermes/.env or environment."""
     # Check environment first
@@ -2919,8 +2602,7 @@ def show_config():
     for env_key, name in keys:
         value = get_env_value(env_key)
         print(f"  {name:<14} {redact_key(value)}")
-    from hermes_cli.auth import get_anthropic_key
-    anthropic_value = get_anthropic_key()
+    anthropic_value = get_env_value("ANTHROPIC_TOKEN") or get_env_value("ANTHROPIC_API_KEY")
     print(f"  {'Anthropic':<14} {redact_key(anthropic_value)}")
     
     # Model settings
@@ -2982,11 +2664,10 @@ def show_config():
         print(f"  Threshold:    {compression.get('threshold', 0.50) * 100:.0f}%")
         print(f"  Target ratio: {compression.get('target_ratio', 0.20) * 100:.0f}% of threshold preserved")
         print(f"  Protect last: {compression.get('protect_last_n', 20)} messages")
-        _aux_comp = config.get('auxiliary', {}).get('compression', {})
-        _sm = _aux_comp.get('model', '') or '(auto)'
+        _sm = compression.get('summary_model', '') or '(main model)'
         print(f"  Model:        {_sm}")
-        comp_provider = _aux_comp.get('provider', 'auto')
-        if comp_provider and comp_provider != 'auto':
+        comp_provider = compression.get('summary_provider', 'auto')
+        if comp_provider != 'auto':
             print(f"  Provider:     {comp_provider}")
     
     # Auxiliary models
@@ -3137,8 +2818,8 @@ def set_config_value(key: str, value: str):
     
     # Write only user config back (not the full merged defaults)
     ensure_hermes_home()
-    from utils import atomic_yaml_write
-    atomic_yaml_write(config_path, user_config, sort_keys=False)
+    with open(config_path, 'w', encoding="utf-8") as f:
+        yaml.dump(user_config, f, default_flow_style=False, sort_keys=False)
     
     # Keep .env in sync for keys that terminal_tool reads directly from env vars.
     # config.yaml is authoritative, but terminal_tool only reads TERMINAL_ENV etc.
@@ -3154,10 +2835,6 @@ def set_config_value(key: str, value: str):
         "terminal.timeout": "TERMINAL_TIMEOUT",
         "terminal.sandbox_dir": "TERMINAL_SANDBOX_DIR",
         "terminal.persistent_shell": "TERMINAL_PERSISTENT_SHELL",
-        "terminal.container_cpu": "TERMINAL_CONTAINER_CPU",
-        "terminal.container_memory": "TERMINAL_CONTAINER_MEMORY",
-        "terminal.container_disk": "TERMINAL_CONTAINER_DISK",
-        "terminal.container_persistent": "TERMINAL_CONTAINER_PERSISTENT",
     }
     if key in _config_to_env_sync:
         save_env_value(_config_to_env_sync[key], str(value))

hermes_cli/copilot_auth.py

@@ -117,30 +117,14 @@ def _gh_cli_candidates() -> list[str]:
 
 
 def _try_gh_cli_token() -> Optional[str]:
-    """Return a token from ``gh auth token`` when the GitHub CLI is available.
-
-    When COPILOT_GH_HOST is set, passes ``--hostname`` so gh returns the
-    correct host's token.  Also strips GITHUB_TOKEN / GH_TOKEN from the
-    subprocess environment so ``gh`` reads from its own credential store
-    (hosts.yml) instead of just echoing the env var back.
-    """
-    hostname = os.getenv("COPILOT_GH_HOST", "").strip()
-
-    # Build a clean env so gh doesn't short-circuit on GITHUB_TOKEN / GH_TOKEN
-    clean_env = {k: v for k, v in os.environ.items()
-                 if k not in ("GITHUB_TOKEN", "GH_TOKEN")}
-
+    """Return a token from ``gh auth token`` when the GitHub CLI is available."""
     for gh_path in _gh_cli_candidates():
-        cmd = [gh_path, "auth", "token"]
-        if hostname:
-            cmd += ["--hostname", hostname]
         try:
             result = subprocess.run(
-                cmd,
+                [gh_path, "auth", "token"],
                 capture_output=True,
                 text=True,
                 timeout=5,
-                env=clean_env,
             )
         except (FileNotFoundError, subprocess.TimeoutExpired) as exc:
             logger.debug("gh CLI token lookup failed (%s): %s", gh_path, exc)

hermes_cli/curses_ui.py

@@ -160,256 +160,6 @@ def curses_checklist(
         return _numbered_fallback(title, items, selected, cancel_returns, status_fn)
 
 
-def curses_radiolist(
-    title: str,
-    items: List[str],
-    selected: int = 0,
-    *,
-    cancel_returns: int | None = None,
-) -> int:
-    """Curses single-select radio list. Returns the selected index.
-
-    Args:
-        title: Header line displayed above the list.
-        items: Display labels for each row.
-        selected: Index that starts selected (pre-selected).
-        cancel_returns: Returned on ESC/q. Defaults to the original *selected*.
-    """
-    if cancel_returns is None:
-        cancel_returns = selected
-
-    if not sys.stdin.isatty():
-        return cancel_returns
-
-    try:
-        import curses
-        result_holder: list = [None]
-
-        def _draw(stdscr):
-            curses.curs_set(0)
-            if curses.has_colors():
-                curses.start_color()
-                curses.use_default_colors()
-                curses.init_pair(1, curses.COLOR_GREEN, -1)
-                curses.init_pair(2, curses.COLOR_YELLOW, -1)
-            cursor = selected
-            scroll_offset = 0
-
-            while True:
-                stdscr.clear()
-                max_y, max_x = stdscr.getmaxyx()
-
-                # Header
-                try:
-                    hattr = curses.A_BOLD
-                    if curses.has_colors():
-                        hattr |= curses.color_pair(2)
-                    stdscr.addnstr(0, 0, title, max_x - 1, hattr)
-                    stdscr.addnstr(
-                        1, 0,
-                        "  \u2191\u2193 navigate  ENTER/SPACE select  ESC cancel",
-                        max_x - 1, curses.A_DIM,
-                    )
-                except curses.error:
-                    pass
-
-                # Scrollable item list
-                visible_rows = max_y - 4
-                if cursor < scroll_offset:
-                    scroll_offset = cursor
-                elif cursor >= scroll_offset + visible_rows:
-                    scroll_offset = cursor - visible_rows + 1
-
-                for draw_i, i in enumerate(
-                    range(scroll_offset, min(len(items), scroll_offset + visible_rows))
-                ):
-                    y = draw_i + 3
-                    if y >= max_y - 1:
-                        break
-                    radio = "\u25cf" if i == selected else "\u25cb"
-                    arrow = "\u2192" if i == cursor else " "
-                    line = f" {arrow} ({radio}) {items[i]}"
-                    attr = curses.A_NORMAL
-                    if i == cursor:
-                        attr = curses.A_BOLD
-                        if curses.has_colors():
-                            attr |= curses.color_pair(1)
-                    try:
-                        stdscr.addnstr(y, 0, line, max_x - 1, attr)
-                    except curses.error:
-                        pass
-
-                stdscr.refresh()
-                key = stdscr.getch()
-
-                if key in (curses.KEY_UP, ord("k")):
-                    cursor = (cursor - 1) % len(items)
-                elif key in (curses.KEY_DOWN, ord("j")):
-                    cursor = (cursor + 1) % len(items)
-                elif key in (ord(" "), curses.KEY_ENTER, 10, 13):
-                    result_holder[0] = cursor
-                    return
-                elif key in (27, ord("q")):
-                    result_holder[0] = cancel_returns
-                    return
-
-        curses.wrapper(_draw)
-        flush_stdin()
-        return result_holder[0] if result_holder[0] is not None else cancel_returns
-
-    except Exception:
-        return _radio_numbered_fallback(title, items, selected, cancel_returns)
-
-
-def _radio_numbered_fallback(
-    title: str,
-    items: List[str],
-    selected: int,
-    cancel_returns: int,
-) -> int:
-    """Text-based numbered fallback for radio selection."""
-    print(color(f"\n  {title}", Colors.YELLOW))
-    print(color("  Select by number, Enter to confirm.\n", Colors.DIM))
-
-    for i, label in enumerate(items):
-        marker = color("(\u25cf)", Colors.GREEN) if i == selected else "(\u25cb)"
-        print(f"  {marker} {i + 1:>2}. {label}")
-    print()
-    try:
-        val = input(color(f"  Choice [default {selected + 1}]: ", Colors.DIM)).strip()
-        if not val:
-            return selected
-        idx = int(val) - 1
-        if 0 <= idx < len(items):
-            return idx
-        return selected
-    except (ValueError, KeyboardInterrupt, EOFError):
-        return cancel_returns
-
-
-def curses_single_select(
-    title: str,
-    items: List[str],
-    default_index: int = 0,
-    *,
-    cancel_label: str = "Cancel",
-) -> int | None:
-    """Curses single-select menu. Returns selected index or None on cancel.
-
-    Works inside prompt_toolkit because curses.wrapper() restores the terminal
-    safely, unlike simple_term_menu which conflicts with /dev/tty.
-    """
-    if not sys.stdin.isatty():
-        return None
-
-    try:
-        import curses
-        result_holder: list = [None]
-
-        all_items = list(items) + [cancel_label]
-        cancel_idx = len(items)
-
-        def _draw(stdscr):
-            curses.curs_set(0)
-            if curses.has_colors():
-                curses.start_color()
-                curses.use_default_colors()
-                curses.init_pair(1, curses.COLOR_GREEN, -1)
-                curses.init_pair(2, curses.COLOR_YELLOW, -1)
-            cursor = min(default_index, len(all_items) - 1)
-            scroll_offset = 0
-
-            while True:
-                stdscr.clear()
-                max_y, max_x = stdscr.getmaxyx()
-
-                try:
-                    hattr = curses.A_BOLD
-                    if curses.has_colors():
-                        hattr |= curses.color_pair(2)
-                    stdscr.addnstr(0, 0, title, max_x - 1, hattr)
-                    stdscr.addnstr(
-                        1, 0,
-                        "  ↑↓ navigate  ENTER confirm  ESC/q cancel",
-                        max_x - 1, curses.A_DIM,
-                    )
-                except curses.error:
-                    pass
-
-                visible_rows = max_y - 3
-                if cursor < scroll_offset:
-                    scroll_offset = cursor
-                elif cursor >= scroll_offset + visible_rows:
-                    scroll_offset = cursor - visible_rows + 1
-
-                for draw_i, i in enumerate(
-                    range(scroll_offset, min(len(all_items), scroll_offset + visible_rows))
-                ):
-                    y = draw_i + 3
-                    if y >= max_y - 1:
-                        break
-                    arrow = "→" if i == cursor else " "
-                    line = f" {arrow} {all_items[i]}"
-                    attr = curses.A_NORMAL
-                    if i == cursor:
-                        attr = curses.A_BOLD
-                        if curses.has_colors():
-                            attr |= curses.color_pair(1)
-                    try:
-                        stdscr.addnstr(y, 0, line, max_x - 1, attr)
-                    except curses.error:
-                        pass
-
-                stdscr.refresh()
-                key = stdscr.getch()
-
-                if key in (curses.KEY_UP, ord("k")):
-                    cursor = (cursor - 1) % len(all_items)
-                elif key in (curses.KEY_DOWN, ord("j")):
-                    cursor = (cursor + 1) % len(all_items)
-                elif key in (curses.KEY_ENTER, 10, 13):
-                    result_holder[0] = cursor
-                    return
-                elif key in (27, ord("q")):
-                    result_holder[0] = None
-                    return
-
-        curses.wrapper(_draw)
-        flush_stdin()
-        if result_holder[0] is not None and result_holder[0] >= cancel_idx:
-            return None
-        return result_holder[0]
-
-    except Exception:
-        all_items = list(items) + [cancel_label]
-        cancel_idx = len(items)
-        return _numbered_single_fallback(title, all_items, cancel_idx)
-
-
-def _numbered_single_fallback(
-    title: str,
-    items: List[str],
-    cancel_idx: int,
-) -> int | None:
-    """Text-based numbered fallback for single-select."""
-    print(f"\n  {title}\n")
-    for i, label in enumerate(items, 1):
-        print(f"  {i}. {label}")
-    print()
-    try:
-        val = input(f"  Choice [1-{len(items)}]: ").strip()
-        if not val:
-            return None
-        idx = int(val) - 1
-        if 0 <= idx < len(items) and idx < cancel_idx:
-            return idx
-        if idx == cancel_idx:
-            return None
-    except (ValueError, KeyboardInterrupt, EOFError):
-        pass
-    return None
-
-
 def _numbered_fallback(
     title: str,
     items: List[str],

hermes_cli/debug.py

@@ -1,336 +0,0 @@
-"""``hermes debug`` — debug tools for Hermes Agent.
-
-Currently supports:
-    hermes debug share    Upload debug report (system info + logs) to a
-                          paste service and print a shareable URL.
-"""
-
-import io
-import sys
-import urllib.error
-import urllib.parse
-import urllib.request
-from pathlib import Path
-from typing import Optional
-
-from hermes_constants import get_hermes_home
-
-
-# ---------------------------------------------------------------------------
-# Paste services — try paste.rs first, dpaste.com as fallback.
-# ---------------------------------------------------------------------------
-
-_PASTE_RS_URL = "https://paste.rs/"
-_DPASTE_COM_URL = "https://dpaste.com/api/"
-
-# Maximum bytes to read from a single log file for upload.
-# paste.rs caps at ~1 MB; we stay under that with headroom.
-_MAX_LOG_BYTES = 512_000
-
-
-def _upload_paste_rs(content: str) -> str:
-    """Upload to paste.rs.  Returns the paste URL.
-
-    paste.rs accepts a plain POST body and returns the URL directly.
-    """
-    data = content.encode("utf-8")
-    req = urllib.request.Request(
-        _PASTE_RS_URL, data=data, method="POST",
-        headers={
-            "Content-Type": "text/plain; charset=utf-8",
-            "User-Agent": "hermes-agent/debug-share",
-        },
-    )
-    with urllib.request.urlopen(req, timeout=30) as resp:
-        url = resp.read().decode("utf-8").strip()
-    if not url.startswith("http"):
-        raise ValueError(f"Unexpected response from paste.rs: {url[:200]}")
-    return url
-
-
-def _upload_dpaste_com(content: str, expiry_days: int = 7) -> str:
-    """Upload to dpaste.com.  Returns the paste URL.
-
-    dpaste.com uses multipart form data.
-    """
-    boundary = "----HermesDebugBoundary9f3c"
-
-    def _field(name: str, value: str) -> str:
-        return (
-            f"--{boundary}\r\n"
-            f'Content-Disposition: form-data; name="{name}"\r\n'
-            f"\r\n"
-            f"{value}\r\n"
-        )
-
-    body = (
-        _field("content", content)
-        + _field("syntax", "text")
-        + _field("expiry_days", str(expiry_days))
-        + f"--{boundary}--\r\n"
-    ).encode("utf-8")
-
-    req = urllib.request.Request(
-        _DPASTE_COM_URL, data=body, method="POST",
-        headers={
-            "Content-Type": f"multipart/form-data; boundary={boundary}",
-            "User-Agent": "hermes-agent/debug-share",
-        },
-    )
-    with urllib.request.urlopen(req, timeout=30) as resp:
-        url = resp.read().decode("utf-8").strip()
-    if not url.startswith("http"):
-        raise ValueError(f"Unexpected response from dpaste.com: {url[:200]}")
-    return url
-
-
-def upload_to_pastebin(content: str, expiry_days: int = 7) -> str:
-    """Upload *content* to a paste service, trying paste.rs then dpaste.com.
-
-    Returns the paste URL on success, raises on total failure.
-    """
-    errors: list[str] = []
-
-    # Try paste.rs first (simple, fast)
-    try:
-        return _upload_paste_rs(content)
-    except Exception as exc:
-        errors.append(f"paste.rs: {exc}")
-
-    # Fallback: dpaste.com (supports expiry)
-    try:
-        return _upload_dpaste_com(content, expiry_days=expiry_days)
-    except Exception as exc:
-        errors.append(f"dpaste.com: {exc}")
-
-    raise RuntimeError(
-        "Failed to upload to any paste service:\n  " + "\n  ".join(errors)
-    )
-
-
-# ---------------------------------------------------------------------------
-# Log file reading
-# ---------------------------------------------------------------------------
-
-def _resolve_log_path(log_name: str) -> Optional[Path]:
-    """Find the log file for *log_name*, falling back to the .1 rotation.
-
-    Returns the path if found, or None.
-    """
-    from hermes_cli.logs import LOG_FILES
-
-    filename = LOG_FILES.get(log_name)
-    if not filename:
-        return None
-
-    log_dir = get_hermes_home() / "logs"
-    primary = log_dir / filename
-    if primary.exists() and primary.stat().st_size > 0:
-        return primary
-
-    # Fall back to the most recent rotated file (.1).
-    rotated = log_dir / f"{filename}.1"
-    if rotated.exists() and rotated.stat().st_size > 0:
-        return rotated
-
-    return None
-
-
-def _read_log_tail(log_name: str, num_lines: int) -> str:
-    """Read the last *num_lines* from a log file, or return a placeholder."""
-    from hermes_cli.logs import _read_last_n_lines
-
-    log_path = _resolve_log_path(log_name)
-    if log_path is None:
-        return "(file not found)"
-
-    try:
-        lines = _read_last_n_lines(log_path, num_lines)
-        return "".join(lines).rstrip("\n")
-    except Exception as exc:
-        return f"(error reading: {exc})"
-
-
-def _read_full_log(log_name: str, max_bytes: int = _MAX_LOG_BYTES) -> Optional[str]:
-    """Read a log file for standalone upload.
-
-    Returns the file content (last *max_bytes* if truncated), or None if the
-    file doesn't exist or is empty.
-    """
-    log_path = _resolve_log_path(log_name)
-    if log_path is None:
-        return None
-
-    try:
-        size = log_path.stat().st_size
-        if size == 0:
-            return None
-
-        if size <= max_bytes:
-            return log_path.read_text(encoding="utf-8", errors="replace")
-
-        # File is larger than max_bytes — read the tail.
-        with open(log_path, "rb") as f:
-            f.seek(size - max_bytes)
-            # Skip partial line at the seek point.
-            f.readline()
-            content = f.read().decode("utf-8", errors="replace")
-        return f"[... truncated — showing last ~{max_bytes // 1024}KB ...]\n{content}"
-    except Exception:
-        return None
-
-
-# ---------------------------------------------------------------------------
-# Debug report collection
-# ---------------------------------------------------------------------------
-
-def _capture_dump() -> str:
-    """Run ``hermes dump`` and return its stdout as a string."""
-    from hermes_cli.dump import run_dump
-
-    class _FakeArgs:
-        show_keys = False
-
-    old_stdout = sys.stdout
-    sys.stdout = capture = io.StringIO()
-    try:
-        run_dump(_FakeArgs())
-    except SystemExit:
-        pass
-    finally:
-        sys.stdout = old_stdout
-
-    return capture.getvalue()
-
-
-def collect_debug_report(*, log_lines: int = 200, dump_text: str = "") -> str:
-    """Build the summary debug report: system dump + log tails.
-
-    Parameters
-    ----------
-    log_lines
-        Number of recent lines to include per log file.
-    dump_text
-        Pre-captured dump output.  If empty, ``hermes dump`` is run
-        internally.
-
-    Returns the report as a plain-text string ready for upload.
-    """
-    buf = io.StringIO()
-
-    if not dump_text:
-        dump_text = _capture_dump()
-    buf.write(dump_text)
-
-    # ── Recent log tails (summary only) ──────────────────────────────────
-    buf.write("\n\n")
-    buf.write(f"--- agent.log (last {log_lines} lines) ---\n")
-    buf.write(_read_log_tail("agent", log_lines))
-    buf.write("\n\n")
-
-    errors_lines = min(log_lines, 100)
-    buf.write(f"--- errors.log (last {errors_lines} lines) ---\n")
-    buf.write(_read_log_tail("errors", errors_lines))
-    buf.write("\n\n")
-
-    buf.write(f"--- gateway.log (last {errors_lines} lines) ---\n")
-    buf.write(_read_log_tail("gateway", errors_lines))
-    buf.write("\n")
-
-    return buf.getvalue()
-
-
-# ---------------------------------------------------------------------------
-# CLI entry points
-# ---------------------------------------------------------------------------
-
-def run_debug_share(args):
-    """Collect debug report + full logs, upload each, print URLs."""
-    log_lines = getattr(args, "lines", 200)
-    expiry = getattr(args, "expire", 7)
-    local_only = getattr(args, "local", False)
-
-    print("Collecting debug report...")
-
-    # Capture dump once — prepended to every paste for context.
-    dump_text = _capture_dump()
-
-    report = collect_debug_report(log_lines=log_lines, dump_text=dump_text)
-    agent_log = _read_full_log("agent")
-    gateway_log = _read_full_log("gateway")
-
-    # Prepend dump header to each full log so every paste is self-contained.
-    if agent_log:
-        agent_log = dump_text + "\n\n--- full agent.log ---\n" + agent_log
-    if gateway_log:
-        gateway_log = dump_text + "\n\n--- full gateway.log ---\n" + gateway_log
-
-    if local_only:
-        print(report)
-        if agent_log:
-            print(f"\n\n{'=' * 60}")
-            print("FULL agent.log")
-            print(f"{'=' * 60}\n")
-            print(agent_log)
-        if gateway_log:
-            print(f"\n\n{'=' * 60}")
-            print("FULL gateway.log")
-            print(f"{'=' * 60}\n")
-            print(gateway_log)
-        return
-
-    print("Uploading...")
-    urls: dict[str, str] = {}
-    failures: list[str] = []
-
-    # 1. Summary report (required)
-    try:
-        urls["Report"] = upload_to_pastebin(report, expiry_days=expiry)
-    except RuntimeError as exc:
-        print(f"\nUpload failed: {exc}", file=sys.stderr)
-        print("\nFull report printed below — copy-paste it manually:\n")
-        print(report)
-        sys.exit(1)
-
-    # 2. Full agent.log (optional)
-    if agent_log:
-        try:
-            urls["agent.log"] = upload_to_pastebin(agent_log, expiry_days=expiry)
-        except Exception as exc:
-            failures.append(f"agent.log: {exc}")
-
-    # 3. Full gateway.log (optional)
-    if gateway_log:
-        try:
-            urls["gateway.log"] = upload_to_pastebin(gateway_log, expiry_days=expiry)
-        except Exception as exc:
-            failures.append(f"gateway.log: {exc}")
-
-    # Print results
-    label_width = max(len(k) for k in urls)
-    print(f"\nDebug report uploaded:")
-    for label, url in urls.items():
-        print(f"  {label:<{label_width}}  {url}")
-
-    if failures:
-        print(f"\n  (failed to upload: {', '.join(failures)})")
-
-    print(f"\nShare these links with the Hermes team for support.")
-
-
-def run_debug(args):
-    """Route debug subcommands."""
-    subcmd = getattr(args, "debug_command", None)
-    if subcmd == "share":
-        run_debug_share(args)
-    else:
-        # Default: show help
-        print("Usage: hermes debug share [--lines N] [--expire N] [--local]")
-        print()
-        print("Commands:")
-        print("  share    Upload debug report to a paste service and print URL")
-        print()
-        print("Options:")
-        print("  --lines N    Number of log lines to include (default: 200)")
-        print("  --expire N   Paste expiry in days (default: 7)")
-        print("  --local      Print report locally instead of uploading")

hermes_cli/doctor.py

@@ -51,7 +51,6 @@ _PROVIDER_ENV_HINTS = (
     "AI_GATEWAY_API_KEY",
     "OPENCODE_ZEN_API_KEY",
     "OPENCODE_GO_API_KEY",
-    "XIAOMI_API_KEY",
 )
 
 
@@ -336,8 +335,8 @@ def run_doctor(args):
                             model_section[k] = raw_config.pop(k)
                         else:
                             raw_config.pop(k)
-                    from utils import atomic_yaml_write
-                    atomic_yaml_write(config_path, raw_config)
+                    with open(config_path, "w") as f:
+                        yaml.dump(raw_config, f, default_flow_style=False)
                     check_ok("Migrated stale root-level keys into model section")
                     fixed_count += 1
                 else:
@@ -686,8 +685,7 @@ def run_doctor(args):
     else:
         check_warn("OpenRouter API", "(not configured)")
     
-    from hermes_cli.auth import get_anthropic_key
-    anthropic_key = get_anthropic_key()
+    anthropic_key = os.getenv("ANTHROPIC_TOKEN") or os.getenv("ANTHROPIC_API_KEY")
     if anthropic_key:
         print("  Checking Anthropic API...", end="", flush=True)
         try:
@@ -721,14 +719,12 @@ def run_doctor(args):
     _apikey_providers = [
         ("Z.AI / GLM",      ("GLM_API_KEY", "ZAI_API_KEY", "Z_AI_API_KEY"), "https://api.z.ai/api/paas/v4/models", "GLM_BASE_URL", True),
         ("Kimi / Moonshot",  ("KIMI_API_KEY",),                              "https://api.moonshot.ai/v1/models",   "KIMI_BASE_URL", True),
-        ("Kimi / Moonshot (China)", ("KIMI_CN_API_KEY",),                    "https://api.moonshot.cn/v1/models",   None, True),
-        ("Arcee AI",         ("ARCEEAI_API_KEY",),                            "https://api.arcee.ai/api/v1/models",  "ARCEE_BASE_URL", True),
         ("DeepSeek",         ("DEEPSEEK_API_KEY",),                           "https://api.deepseek.com/v1/models",  "DEEPSEEK_BASE_URL", True),
         ("Hugging Face",     ("HF_TOKEN",),                                   "https://router.huggingface.co/v1/models", "HF_BASE_URL", True),
         ("Alibaba/DashScope", ("DASHSCOPE_API_KEY",),                         "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/models", "DASHSCOPE_BASE_URL", True),
-        # MiniMax: the /anthropic endpoint doesn't support /models, but the /v1 endpoint does.
-        ("MiniMax",          ("MINIMAX_API_KEY",),                            "https://api.minimax.io/v1/models",    "MINIMAX_BASE_URL", True),
-        ("MiniMax (China)",  ("MINIMAX_CN_API_KEY",),                         "https://api.minimaxi.com/v1/models",  "MINIMAX_CN_BASE_URL", True),
+        # MiniMax APIs don't support /models endpoint — https://github.com/NousResearch/hermes-agent/issues/811
+        ("MiniMax",          ("MINIMAX_API_KEY",),                            None,                                  "MINIMAX_BASE_URL", False),
+        ("MiniMax (China)",  ("MINIMAX_CN_API_KEY",),                         None,                                  "MINIMAX_CN_BASE_URL", False),
         ("AI Gateway",       ("AI_GATEWAY_API_KEY",),                          "https://ai-gateway.vercel.sh/v1/models", "AI_GATEWAY_BASE_URL", True),
         ("Kilo Code",        ("KILOCODE_API_KEY",),                            "https://api.kilo.ai/api/gateway/models",  "KILOCODE_BASE_URL", True),
         ("OpenCode Zen",     ("OPENCODE_ZEN_API_KEY",),                        "https://opencode.ai/zen/v1/models",  "OPENCODE_ZEN_BASE_URL", True),
@@ -753,11 +749,6 @@ def run_doctor(args):
                 # Auto-detect Kimi Code keys (sk-kimi-) → api.kimi.com
                 if not _base and _key.startswith("sk-kimi-"):
                     _base = "https://api.kimi.com/coding/v1"
-                # Anthropic-compat endpoints (/anthropic) don't support /models.
-                # Rewrite to the OpenAI-compat /v1 surface for health checks.
-                if _base and _base.rstrip("/").endswith("/anthropic"):
-                    from agent.auxiliary_client import _to_openai_base_url
-                    _base = _to_openai_base_url(_base)
                 _url = (_base.rstrip("/") + "/models") if _base else _default_url
                 _headers = {"Authorization": f"Bearer {_key}"}
                 if "api.kimi.com" in _url.lower():

hermes_cli/dump.py

@@ -44,16 +44,6 @@ def _redact(value: str) -> str:
 def _gateway_status() -> str:
     """Return a short gateway status string."""
     if sys.platform.startswith("linux"):
-        from hermes_constants import is_container
-        if is_container():
-            try:
-                from hermes_cli.gateway import find_gateway_pids
-                pids = find_gateway_pids()
-                if pids:
-                    return f"running (docker, pid {pids[0]})"
-                return "stopped (docker)"
-            except Exception:
-                return "stopped (docker)"
         try:
             from hermes_cli.gateway import get_service_name
             svc = get_service_name()
@@ -129,7 +119,6 @@ def _configured_platforms() -> list[str]:
         "dingtalk": "DINGTALK_CLIENT_ID",
         "feishu": "FEISHU_APP_ID",
         "wecom": "WECOM_BOT_ID",
-        "wecom_callback": "WECOM_CALLBACK_CORP_ID",
         "weixin": "WEIXIN_ACCOUNT_ID",
     }
     return [name for name, env in checks.items() if os.getenv(env)]

hermes_cli/env_loader.py

@@ -15,51 +15,6 @@ def _load_dotenv_with_fallback(path: Path, *, override: bool) -> None:
         load_dotenv(dotenv_path=path, override=override, encoding="latin-1")
 
 
-def _sanitize_env_file_if_needed(path: Path) -> None:
-    """Pre-sanitize a .env file before python-dotenv reads it.
-
-    python-dotenv does not handle corrupted lines where multiple
-    KEY=VALUE pairs are concatenated on a single line (missing newline).
-    This produces mangled values — e.g. a bot token duplicated 8×
-    (see #8908).
-
-    We delegate to ``hermes_cli.config._sanitize_env_lines`` which
-    already knows all valid Hermes env-var names and can split
-    concatenated lines correctly.
-    """
-    if not path.exists():
-        return
-    try:
-        from hermes_cli.config import _sanitize_env_lines
-    except ImportError:
-        return  # early bootstrap — config module not available yet
-
-    read_kw = {"encoding": "utf-8", "errors": "replace"}
-    try:
-        with open(path, **read_kw) as f:
-            original = f.readlines()
-        sanitized = _sanitize_env_lines(original)
-        if sanitized != original:
-            import tempfile
-            fd, tmp = tempfile.mkstemp(
-                dir=str(path.parent), suffix=".tmp", prefix=".env_"
-            )
-            try:
-                with os.fdopen(fd, "w", encoding="utf-8") as f:
-                    f.writelines(sanitized)
-                    f.flush()
-                    os.fsync(f.fileno())
-                os.replace(tmp, path)
-            except BaseException:
-                try:
-                    os.unlink(tmp)
-                except OSError:
-                    pass
-                raise
-    except Exception:
-        pass  # best-effort — don't block gateway startup
-
-
 def load_hermes_dotenv(
     *,
     hermes_home: str | os.PathLike | None = None,
@@ -79,10 +34,6 @@ def load_hermes_dotenv(
     user_env = home_path / ".env"
     project_env_path = Path(project_env) if project_env else None
 
-    # Fix corrupted .env files before python-dotenv parses them (#8908).
-    if user_env.exists():
-        _sanitize_env_file_if_needed(user_env)
-
     if user_env.exists():
         _load_dotenv_with_fallback(user_env, override=True)
         loaded.append(user_env)

hermes_cli/logs.py

@@ -1,18 +1,16 @@
 """``hermes logs`` — view and filter Hermes log files.
 
-Supports tailing, following, session filtering, level filtering,
-component filtering, and relative time ranges.  All log files live
-under ``~/.hermes/logs/``.
+Supports tailing, following, session filtering, level filtering, and
+relative time ranges.  All log files live under ``~/.hermes/logs/``.
 
 Usage examples::
 
     hermes logs                    # last 50 lines of agent.log
     hermes logs -f                 # follow agent.log in real time
     hermes logs errors             # last 50 lines of errors.log
-    hermes logs gateway -n 100    # last 100 lines of gateway.log
+    hermes logs gateway -n 100     # last 100 lines of gateway.log
     hermes logs --level WARNING    # only WARNING+ lines
     hermes logs --session abc123   # filter by session ID substring
-    hermes logs --component tools  # only tool-related lines
     hermes logs --since 1h         # lines from the last hour
     hermes logs --since 30m -f     # follow, starting 30 min ago
 """
@@ -22,7 +20,7 @@ import sys
 import time
 from datetime import datetime, timedelta
 from pathlib import Path
-from typing import Optional, Sequence
+from typing import Optional
 
 from hermes_constants import get_hermes_home, display_hermes_home
 
@@ -40,15 +38,6 @@ _TS_RE = re.compile(r"^(\d{4}-\d{2}-\d{2}\s+\d{2}:\d{2}:\d{2})")
 # Level extraction — matches " INFO ", " WARNING ", " ERROR ", " DEBUG ", " CRITICAL "
 _LEVEL_RE = re.compile(r"\s(DEBUG|INFO|WARNING|ERROR|CRITICAL)\s")
 
-# Logger name extraction — after level and optional session tag, the next
-# non-space token before ":" is the logger name.
-# Matches: "INFO gateway.run:" or "INFO [sess_abc] tools.terminal_tool:"
-_LOGGER_NAME_RE = re.compile(
-    r"\s(?:DEBUG|INFO|WARNING|ERROR|CRITICAL)"  # level
-    r"(?:\s+\[.*?\])?"                           # optional session tag
-    r"\s+(\S+):"                                 # logger name
-)
-
 # Level ordering for >= filtering
 _LEVEL_ORDER = {"DEBUG": 0, "INFO": 1, "WARNING": 2, "ERROR": 3, "CRITICAL": 4}
 
@@ -90,27 +79,12 @@ def _extract_level(line: str) -> Optional[str]:
     return m.group(1) if m else None
 
 
-def _extract_logger_name(line: str) -> Optional[str]:
-    """Extract the logger name from a log line."""
-    m = _LOGGER_NAME_RE.search(line)
-    return m.group(1) if m else None
-
-
-def _line_matches_component(line: str, prefixes: Sequence[str]) -> bool:
-    """Check if a log line's logger name starts with any of *prefixes*."""
-    name = _extract_logger_name(line)
-    if name is None:
-        return False
-    return name.startswith(tuple(prefixes))
-
-
 def _matches_filters(
     line: str,
     *,
     min_level: Optional[str] = None,
     session_filter: Optional[str] = None,
     since: Optional[datetime] = None,
-    component_prefixes: Optional[Sequence[str]] = None,
 ) -> bool:
     """Check if a log line passes all active filters."""
     if since is not None:
@@ -128,10 +102,6 @@ def _matches_filters(
         if session_filter not in line:
             return False
 
-    if component_prefixes is not None:
-        if not _line_matches_component(line, component_prefixes):
-            return False
-
     return True
 
 
@@ -143,7 +113,6 @@ def tail_log(
     level: Optional[str] = None,
     session: Optional[str] = None,
     since: Optional[str] = None,
-    component: Optional[str] = None,
 ) -> None:
     """Read and display log lines, optionally following in real time.
 
@@ -161,8 +130,6 @@ def tail_log(
         Session ID substring to filter on.
     since
         Relative time string (e.g. ``"1h"``, ``"30m"``).
-    component
-        Component name to filter by (e.g. ``"gateway"``, ``"tools"``).
     """
     filename = LOG_FILES.get(log_name)
     if filename is None:
@@ -188,29 +155,13 @@ def tail_log(
         print(f"Invalid --level: {level!r}. Use DEBUG, INFO, WARNING, ERROR, or CRITICAL.")
         sys.exit(1)
 
-    # Resolve component to logger name prefixes
-    component_prefixes = None
-    if component:
-        from hermes_logging import COMPONENT_PREFIXES
-        component_lower = component.lower()
-        if component_lower not in COMPONENT_PREFIXES:
-            available = ", ".join(sorted(COMPONENT_PREFIXES))
-            print(f"Unknown component: {component!r}. Available: {available}")
-            sys.exit(1)
-        component_prefixes = COMPONENT_PREFIXES[component_lower]
-
-    has_filters = (
-        min_level is not None
-        or session is not None
-        or since_dt is not None
-        or component_prefixes is not None
-    )
+    has_filters = min_level is not None or session is not None or since_dt is not None
 
     # Read and display the tail
     try:
         lines = _read_tail(log_path, num_lines, has_filters=has_filters,
                            min_level=min_level, session_filter=session,
-                           since=since_dt, component_prefixes=component_prefixes)
+                           since=since_dt)
     except PermissionError:
         print(f"Permission denied: {log_path}")
         sys.exit(1)
@@ -221,8 +172,6 @@ def tail_log(
         filter_parts.append(f"level>={min_level}")
     if session:
         filter_parts.append(f"session={session}")
-    if component:
-        filter_parts.append(f"component={component}")
     if since:
         filter_parts.append(f"since={since}")
     filter_desc = f" [{', '.join(filter_parts)}]" if filter_parts else ""
@@ -241,7 +190,7 @@ def tail_log(
     # Follow mode — poll for new content
     try:
         _follow_log(log_path, min_level=min_level, session_filter=session,
-                     since=since_dt, component_prefixes=component_prefixes)
+                     since=since_dt)
     except KeyboardInterrupt:
         print("\n--- stopped ---")
 
@@ -254,7 +203,6 @@ def _read_tail(
     min_level: Optional[str] = None,
     session_filter: Optional[str] = None,
     since: Optional[datetime] = None,
-    component_prefixes: Optional[Sequence[str]] = None,
 ) -> list:
     """Read the last *num_lines* matching lines from a log file.
 
@@ -267,8 +215,7 @@ def _read_tail(
         filtered = [
             l for l in raw_lines
             if _matches_filters(l, min_level=min_level,
-                                session_filter=session_filter, since=since,
-                                component_prefixes=component_prefixes)
+                                session_filter=session_filter, since=since)
         ]
         return filtered[-num_lines:]
     else:
@@ -337,7 +284,6 @@ def _follow_log(
     min_level: Optional[str] = None,
     session_filter: Optional[str] = None,
     since: Optional[datetime] = None,
-    component_prefixes: Optional[Sequence[str]] = None,
 ) -> None:
     """Poll a log file for new content and print matching lines."""
     with open(path, "r", encoding="utf-8", errors="replace") as f:
@@ -347,8 +293,7 @@ def _follow_log(
             line = f.readline()
             if line:
                 if _matches_filters(line, min_level=min_level,
-                                    session_filter=session_filter, since=since,
-                                    component_prefixes=component_prefixes):
+                                    session_filter=session_filter, since=since):
                     print(line, end="")
                     sys.stdout.flush()
             else:

hermes_cli/main.py

@@ -151,18 +151,6 @@ try:
 except Exception:
     pass  # best-effort — don't crash the CLI if logging setup fails
 
-# Apply IPv4 preference early, before any HTTP clients are created.
-try:
-    from hermes_cli.config import load_config as _load_config_early
-    from hermes_constants import apply_ipv4_preference as _apply_ipv4
-    _early_cfg = _load_config_early()
-    _net = _early_cfg.get("network", {})
-    if isinstance(_net, dict) and _net.get("force_ipv4"):
-        _apply_ipv4(force=True)
-    del _early_cfg, _net
-except Exception:
-    pass  # best-effort — don't crash if config isn't available yet
-
 import logging
 import time as _time
 from datetime import datetime
@@ -540,111 +528,54 @@ def _resolve_last_cli_session() -> Optional[str]:
     return None
 
 
-def _probe_container(cmd: list, backend: str, via_sudo: bool = False):
-    """Run a container inspect probe, returning the CompletedProcess.
-
-    Catches TimeoutExpired specifically for a human-readable message;
-    all other exceptions propagate naturally.
-    """
-    try:
-        return subprocess.run(cmd, capture_output=True, text=True, timeout=15)
-    except subprocess.TimeoutExpired:
-        label = f"sudo {backend}" if via_sudo else backend
-        print(
-            f"Error: timed out waiting for {label} to respond.\n"
-            f"The {backend} daemon may be unresponsive or starting up.",
-            file=sys.stderr,
-        )
-        sys.exit(1)
-
-
 def _exec_in_container(container_info: dict, cli_args: list):
     """Replace the current process with a command inside the managed container.
 
-    Probes whether sudo is needed (rootful containers), then os.execvp
-    into the container. On success the Python process is replaced entirely
-    and the container's exit code becomes the process exit code (OS semantics).
-    On failure, OSError propagates naturally.
+    Uses os.execvp to hand off to docker/podman exec, preserving the TTY
+    so the interactive CLI works seamlessly inside the container.
 
     Args:
-        container_info: dict with backend, container_name, exec_user, hermes_bin
+        container_info: dict with backend, container_name, hermes_bin
         cli_args: the original CLI arguments (everything after 'hermes')
     """
     import shutil
+    import subprocess
 
     backend = container_info["backend"]
     container_name = container_info["container_name"]
-    exec_user = container_info["exec_user"]
     hermes_bin = container_info["hermes_bin"]
 
+    # Find the container runtime on PATH
     runtime = shutil.which(backend)
     if not runtime:
-        print(f"Error: {backend} not found on PATH. Cannot route to container.",
+        print(f"Warning: {backend} not found on PATH, falling back to host CLI.",
               file=sys.stderr)
-        sys.exit(1)
+        return  # Fall through to normal CLI
 
-    # Rootful containers (NixOS systemd service) are invisible to unprivileged
-    # users — Podman uses per-user namespaces, Docker needs group access.
-    # Probe whether the runtime can see the container; if not, try via sudo.
-    sudo_path = None
-    probe = _probe_container(
-        [runtime, "inspect", "--format", "ok", container_name], backend,
-    )
-    if probe.returncode != 0:
-        sudo_path = shutil.which("sudo")
-        if sudo_path:
-            probe2 = _probe_container(
-                [sudo_path, "-n", runtime, "inspect", "--format", "ok", container_name],
-                backend, via_sudo=True,
-            )
-            if probe2.returncode != 0:
-                print(
-                    f"Error: container '{container_name}' not found via {backend}.\n"
-                    f"\n"
-                    f"The container is likely running as root. Your user cannot see it\n"
-                    f"because {backend} uses per-user namespaces. Grant passwordless\n"
-                    f"sudo for {backend} — the -n (non-interactive) flag is required\n"
-                    f"because a password prompt would hang or break piped commands.\n"
-                    f"\n"
-                    f"On NixOS:\n"
-                    f"\n"
-                    f'  security.sudo.extraRules = [{{\n'
-                    f'    users = [ "{os.getenv("USER", "your-user")}" ];\n'
-                    f'    commands = [{{ command = "{runtime}"; options = [ "NOPASSWD" ]; }}];\n'
-                    f'  }}];\n'
-                    f"\n"
-                    f"Or run: sudo hermes {' '.join(cli_args)}",
-                    file=sys.stderr,
-                )
-                sys.exit(1)
-        else:
-            print(
-                f"Error: container '{container_name}' not found via {backend}.\n"
-                f"The container may be running under root. Try: sudo hermes {' '.join(cli_args)}",
-                file=sys.stderr,
-            )
-            sys.exit(1)
+    # Check if the container is actually running
+    try:
+        result = subprocess.run(
+            [runtime, "inspect", "--format", "{{.State.Running}}", container_name],
+            capture_output=True, text=True, timeout=5
+        )
+        if result.returncode != 0 or result.stdout.strip().lower() != "true":
+            print(f"Warning: container '{container_name}' is not running, falling back to host CLI.",
+                  file=sys.stderr)
+            return
+    except (subprocess.TimeoutExpired, OSError):
+        return  # Fall through on any error
 
-    is_tty = sys.stdin.isatty()
-    tty_flags = ["-it"] if is_tty else ["-i"]
+    # Filter out --host flag from forwarded args (it's not meaningful inside)
+    forwarded_args = [a for a in cli_args if a != "--host"]
 
-    env_flags = []
-    for var in ("TERM", "COLORTERM", "LANG", "LC_ALL"):
-        val = os.environ.get(var)
-        if val:
-            env_flags.extend(["-e", f"{var}={val}"])
+    # Build the exec command
+    exec_cmd = [runtime, "exec", "-it", container_name, hermes_bin] + forwarded_args
 
-    cmd_prefix = [sudo_path, "-n", runtime] if sudo_path else [runtime]
-    exec_cmd = (
-        cmd_prefix + ["exec"]
-        + tty_flags
-        + ["-u", exec_user]
-        + env_flags
-        + [container_name, hermes_bin]
-        + cli_args
-    )
+    print(f"Routing to container '{container_name}' via {backend}...",
+          file=sys.stderr)
 
-    os.execvp(exec_cmd[0], exec_cmd)
+    # Replace the current process — this never returns on success
+    os.execvp(runtime, exec_cmd)
 
 
 def _resolve_session_by_name_or_id(name_or_id: str) -> Optional[str]:
@@ -675,6 +606,21 @@ def _resolve_session_by_name_or_id(name_or_id: str) -> Optional[str]:
 
 def cmd_chat(args):
     """Run interactive chat CLI."""
+    # ── Container-aware routing ──────────────────────────────────────────
+    # When NixOS container mode is active and we're on the host, exec into
+    # the managed container instead of running locally. --host bypasses this.
+    if not getattr(args, "host", False):
+        try:
+            from hermes_cli.config import get_container_exec_info
+            container_info = get_container_exec_info()
+            if container_info:
+                _exec_in_container(container_info, sys.argv[1:])
+                # _exec_in_container calls os.execvp which replaces the process.
+                # If we get here, the exec failed.
+                sys.exit(1)
+        except Exception:
+            pass  # Fall through to normal CLI on any detection error
+
     # Resolve --continue into --resume with the latest CLI session or by name
     continue_val = getattr(args, "continue_last", None)
     if continue_val and not getattr(args, "resume", None):
@@ -999,7 +945,7 @@ def select_provider_and_model(args=None):
     from hermes_cli.auth import (
         resolve_provider, AuthError, format_auth_error,
     )
-    from hermes_cli.config import get_compatible_custom_providers, load_config, get_env_value
+    from hermes_cli.config import load_config, get_env_value
 
     config = load_config()
     current_model = config.get("model")
@@ -1034,9 +980,27 @@ def select_provider_and_model(args=None):
     if active == "openrouter" and get_env_value("OPENAI_BASE_URL"):
         active = "custom"
 
-    from hermes_cli.models import CANONICAL_PROVIDERS, _PROVIDER_LABELS
-
-    provider_labels = dict(_PROVIDER_LABELS)  # derive from canonical list
+    provider_labels = {
+        "openrouter": "OpenRouter",
+        "nous": "Nous Portal",
+        "openai-codex": "OpenAI Codex",
+        "qwen-oauth": "Qwen OAuth",
+        "copilot-acp": "GitHub Copilot ACP",
+        "copilot": "GitHub Copilot",
+        "anthropic": "Anthropic",
+        "gemini": "Google AI Studio",
+        "zai": "Z.AI / GLM",
+        "kimi-coding": "Kimi / Moonshot",
+        "minimax": "MiniMax",
+        "minimax-cn": "MiniMax (China)",
+        "opencode-zen": "OpenCode Zen",
+        "opencode-go": "OpenCode Go",
+        "ai-gateway": "AI Gateway",
+        "kilocode": "Kilo Code",
+        "alibaba": "Alibaba Cloud (DashScope)",
+        "huggingface": "Hugging Face",
+        "custom": "Custom endpoint",
+    }
     active_label = provider_labels.get(active, active) if active else "none"
 
     print()
@@ -1044,12 +1008,37 @@ def select_provider_and_model(args=None):
     print(f"  Active provider:  {active_label}")
     print()
 
-    # Step 1: Provider selection — flat list from CANONICAL_PROVIDERS
-    all_providers = [(p.slug, p.tui_desc) for p in CANONICAL_PROVIDERS]
+    # Step 1: Provider selection — top providers shown first, rest behind "More..."
+    top_providers = [
+        ("nous", "Nous Portal (Nous Research subscription)"),
+        ("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)"),
+    ]
+
+    extended_providers = [
+        ("copilot-acp", "GitHub Copilot ACP (spawns `copilot --acp --stdio`)"),
+        ("gemini", "Google AI Studio (Gemini models — OpenAI-compatible endpoint)"),
+        ("zai", "Z.AI / GLM (Zhipu AI direct API)"),
+        ("kimi-coding", "Kimi / Moonshot (Moonshot AI direct API)"),
+        ("minimax", "MiniMax (global direct API)"),
+        ("minimax-cn", "MiniMax China (domestic direct API)"),
+        ("kilocode", "Kilo Code (Kilo Gateway API)"),
+        ("opencode-zen", "OpenCode Zen (35+ curated models, pay-as-you-go)"),
+        ("opencode-go", "OpenCode Go (open models, $10/month subscription)"),
+        ("ai-gateway", "AI Gateway (Vercel — 200+ models, pay-per-use)"),
+        ("alibaba", "Alibaba Cloud / DashScope Coding (Qwen + multi-provider)"),
+    ]
 
     def _named_custom_provider_map(cfg) -> dict[str, dict[str, str]]:
+        custom_providers_cfg = cfg.get("custom_providers") or []
         custom_provider_map = {}
-        for entry in get_compatible_custom_providers(cfg):
+        if not isinstance(custom_providers_cfg, list):
+            return custom_provider_map
+        for entry in custom_providers_cfg:
             if not isinstance(entry, dict):
                 continue
             name = (entry.get("name") or "").strip()
@@ -1057,20 +1046,11 @@ def select_provider_and_model(args=None):
             if not name or not base_url:
                 continue
             key = "custom:" + name.lower().replace(" ", "-")
-            provider_key = (entry.get("provider_key") or "").strip()
-            if provider_key:
-                try:
-                    resolve_provider(provider_key)
-                except AuthError:
-                    key = provider_key
             custom_provider_map[key] = {
                 "name": name,
                 "base_url": base_url,
                 "api_key": entry.get("api_key", ""),
-                "key_env": entry.get("key_env", ""),
                 "model": entry.get("model", ""),
-                "api_mode": entry.get("api_mode", ""),
-                "provider_key": provider_key,
             }
         return custom_provider_map
 
@@ -1082,22 +1062,29 @@ def select_provider_and_model(args=None):
         short_url = base_url.replace("https://", "").replace("http://", "").rstrip("/")
         saved_model = provider_info.get("model", "")
         model_hint = f" — {saved_model}" if saved_model else ""
-        all_providers.append((key, f"{name} ({short_url}){model_hint}"))
+        top_providers.append((key, f"{name} ({short_url}){model_hint}"))
 
-    # Build the menu
+    top_keys = {k for k, _ in top_providers}
+    extended_keys = {k for k, _ in extended_providers}
+
+    # If the active provider is in the extended list, promote it into top
+    if active and active in extended_keys:
+        promoted = [(k, l) for k, l in extended_providers if k == active]
+        extended_providers = [(k, l) for k, l in extended_providers if k != active]
+        top_providers = promoted + top_providers
+        top_keys.add(active)
+
+    # Build the primary menu
     ordered = []
     default_idx = 0
-    for key, label in all_providers:
+    for key, label in top_providers:
         if active and key == active:
             ordered.append((key, f"{label}  ← currently active"))
             default_idx = len(ordered) - 1
         else:
             ordered.append((key, label))
 
-    ordered.append(("custom", "Custom endpoint (enter URL manually)"))
-    _has_saved_custom_list = isinstance(config.get("custom_providers"), list) and bool(config.get("custom_providers"))
-    if _has_saved_custom_list:
-        ordered.append(("remove-custom", "Remove a saved custom provider"))
+    ordered.append(("more", "More providers..."))
     ordered.append(("cancel", "Cancel"))
 
     provider_idx = _prompt_provider_choice(
@@ -1109,6 +1096,22 @@ def select_provider_and_model(args=None):
 
     selected_provider = ordered[provider_idx][0]
 
+    # "More providers..." — show the extended list
+    if selected_provider == "more":
+        ext_ordered = list(extended_providers)
+        ext_ordered.append(("custom", "Custom endpoint (enter URL manually)"))
+        if _custom_provider_map:
+            ext_ordered.append(("remove-custom", "Remove a saved custom provider"))
+        ext_ordered.append(("cancel", "Cancel"))
+
+        ext_idx = _prompt_provider_choice(
+            [label for _, label in ext_ordered], default=0,
+        )
+        if ext_idx is None or ext_ordered[ext_idx][0] == "cancel":
+            print("No change.")
+            return
+        selected_provider = ext_ordered[ext_idx][0]
+
     # Step 2: Provider-specific setup + model selection
     if selected_provider == "openrouter":
         _model_flow_openrouter(config, current_model)
@@ -1124,7 +1127,7 @@ def select_provider_and_model(args=None):
         _model_flow_copilot(config, current_model)
     elif selected_provider == "custom":
         _model_flow_custom(config)
-    elif selected_provider.startswith("custom:") or selected_provider in _custom_provider_map:
+    elif selected_provider.startswith("custom:"):
         provider_info = _named_custom_provider_map(load_config()).get(selected_provider)
         if provider_info is None:
             print(
@@ -1139,45 +1142,9 @@ def select_provider_and_model(args=None):
         _model_flow_anthropic(config, current_model)
     elif selected_provider == "kimi-coding":
         _model_flow_kimi(config, current_model)
-    elif selected_provider in ("gemini", "deepseek", "xai", "zai", "kimi-coding-cn", "minimax", "minimax-cn", "kilocode", "opencode-zen", "opencode-go", "ai-gateway", "alibaba", "huggingface", "xiaomi", "arcee"):
+    elif selected_provider in ("gemini", "zai", "minimax", "minimax-cn", "kilocode", "opencode-zen", "opencode-go", "ai-gateway", "alibaba", "huggingface"):
         _model_flow_api_key_provider(config, selected_provider, current_model)
 
-    # ── Post-switch cleanup: clear stale OPENAI_BASE_URL ──────────────
-    # When the user switches to a named provider (anything except "custom"),
-    # a leftover OPENAI_BASE_URL in ~/.hermes/.env can poison auxiliary
-    # clients that use provider:auto. Clear it proactively.  (#5161)
-    if selected_provider not in ("custom", "cancel", "remove-custom") \
-            and not selected_provider.startswith("custom:"):
-        _clear_stale_openai_base_url()
-
-
-def _clear_stale_openai_base_url():
-    """Remove OPENAI_BASE_URL from ~/.hermes/.env if the active provider is not 'custom'.
-
-    After a provider switch, a leftover OPENAI_BASE_URL causes auxiliary
-    clients (compression, vision, delegation) with provider:auto to route
-    requests to the old custom endpoint instead of the newly selected
-    provider.  See issue #5161.
-    """
-    from hermes_cli.config import get_env_value, save_env_value, load_config
-
-    cfg = load_config()
-    model_cfg = cfg.get("model", {})
-    if isinstance(model_cfg, dict):
-        provider = (model_cfg.get("provider") or "").strip().lower()
-    else:
-        provider = ""
-
-    if provider == "custom" or not provider:
-        return  # custom provider legitimately uses OPENAI_BASE_URL
-
-    stale_url = get_env_value("OPENAI_BASE_URL")
-    if stale_url:
-        save_env_value("OPENAI_BASE_URL", "")
-        print(f"Cleared stale OPENAI_BASE_URL from .env (was: {stale_url[:40]}...)"
-              if len(stale_url) > 40
-              else f"Cleared stale OPENAI_BASE_URL from .env (was: {stale_url})")
-
 
 def _prompt_provider_choice(choices, *, default=0):
     """Show provider selection menu with curses arrow-key navigation.
@@ -1809,9 +1776,7 @@ def _model_flow_named_custom(config, provider_info):
     name = provider_info["name"]
     base_url = provider_info["base_url"]
     api_key = provider_info.get("api_key", "")
-    key_env = provider_info.get("key_env", "")
     saved_model = provider_info.get("model", "")
-    provider_key = (provider_info.get("provider_key") or "").strip()
 
     print(f"  Provider: {name}")
     print(f"  URL:      {base_url}")
@@ -1894,41 +1859,15 @@ def _model_flow_named_custom(config, provider_info):
     if not isinstance(model, dict):
         model = {"default": model} if model else {}
         cfg["model"] = model
-    if provider_key:
-        model["provider"] = provider_key
-        model.pop("base_url", None)
-        model.pop("api_key", None)
-    else:
-        model["provider"] = "custom"
-        model["base_url"] = base_url
-        if api_key:
-            model["api_key"] = api_key
-    # Apply api_mode from custom_providers entry, or clear stale value
-    custom_api_mode = provider_info.get("api_mode", "")
-    if custom_api_mode:
-        model["api_mode"] = custom_api_mode
-    else:
-        model.pop("api_mode", None)  # let runtime auto-detect from URL
+    model["provider"] = "custom"
+    model["base_url"] = base_url
+    if api_key:
+        model["api_key"] = api_key
     save_config(cfg)
     deactivate_provider()
 
-    # Persist the selected model back to whichever schema owns this endpoint.
-    if provider_key:
-        cfg = load_config()
-        providers_cfg = cfg.get("providers")
-        if isinstance(providers_cfg, dict):
-            provider_entry = providers_cfg.get(provider_key)
-            if isinstance(provider_entry, dict):
-                provider_entry["default_model"] = model_name
-                if api_key and not str(provider_entry.get("api_key", "") or "").strip():
-                    provider_entry["api_key"] = api_key
-                if key_env and not str(provider_entry.get("key_env", "") or "").strip():
-                    provider_entry["key_env"] = key_env
-                cfg["providers"] = providers_cfg
-                save_config(cfg)
-    else:
-        # Save model name to the custom_providers entry for next time
-        _save_custom_provider(base_url, api_key, model_name)
+    # Save model name to the custom_providers entry for next time
+    _save_custom_provider(base_url, api_key, model_name)
 
     print(f"\n✅ Model set to: {model_name}")
     print(f"   Provider: {name} ({base_url})")
@@ -2461,11 +2400,8 @@ def _model_flow_api_key_provider(config, provider_id, current_model=""):
         print()
         override = ""
     if override and base_url_env:
-        if not override.startswith(("http://", "https://")):
-            print("  Invalid URL — must start with http:// or https://. Keeping current value.")
-        else:
-            save_env_value(base_url_env, override)
-            effective_base = override
+        save_env_value(base_url_env, override)
+        effective_base = override
 
     # Model selection — resolution order:
     #   1. models.dev registry (cached, filtered for agentic/tool-capable models)
@@ -2628,19 +2564,25 @@ def _run_anthropic_oauth_flow(save_env_value):
 
 def _model_flow_anthropic(config, current_model=""):
     """Flow for Anthropic provider — OAuth subscription, API key, or Claude Code creds."""
+    import os
     from hermes_cli.auth import (
-        _prompt_model_selection, _save_model_choice,
+        PROVIDER_REGISTRY, _prompt_model_selection, _save_model_choice,
         deactivate_provider,
     )
     from hermes_cli.config import (
-        save_env_value, load_config, save_config,
+        get_env_value, save_env_value, load_config, save_config,
         save_anthropic_api_key,
     )
     from hermes_cli.models import _PROVIDER_MODELS
 
     # Check ALL credential sources
-    from hermes_cli.auth import get_anthropic_key
-    existing_key = get_anthropic_key()
+    existing_key = (
+        get_env_value("ANTHROPIC_TOKEN")
+        or os.getenv("ANTHROPIC_TOKEN", "")
+        or get_env_value("ANTHROPIC_API_KEY")
+        or os.getenv("ANTHROPIC_API_KEY", "")
+        or os.getenv("CLAUDE_CODE_OAUTH_TOKEN", "")
+    )
     cc_available = False
     try:
         from agent.anthropic_adapter import read_claude_code_credentials, is_claude_code_token_valid
@@ -2795,34 +2737,12 @@ def cmd_dump(args):
     run_dump(args)
 
 
-def cmd_debug(args):
-    """Debug tools (share report, etc.)."""
-    from hermes_cli.debug import run_debug
-    run_debug(args)
-
-
 def cmd_config(args):
     """Configuration management."""
     from hermes_cli.config import config_command
     config_command(args)
 
 
-def cmd_backup(args):
-    """Back up Hermes home directory to a zip file."""
-    if getattr(args, "quick", False):
-        from hermes_cli.backup import run_quick_backup
-        run_quick_backup(args)
-    else:
-        from hermes_cli.backup import run_backup
-        run_backup(args)
-
-
-def cmd_import(args):
-    """Restore a Hermes backup from a zip file."""
-    from hermes_cli.backup import run_import
-    run_import(args)
-
-
 def cmd_version(args):
     """Show version."""
     print(f"Hermes Agent v{__version__} ({__release_date__})")
@@ -2941,44 +2861,6 @@ def _gateway_prompt(prompt_text: str, default: str = "", timeout: float = 300.0)
     return default
 
 
-def _build_web_ui(web_dir: Path, *, fatal: bool = False) -> bool:
-    """Build the web UI frontend if npm is available.
-
-    Args:
-        web_dir: Path to the ``web/`` source directory.
-        fatal: If True, print error guidance and return False on failure
-               instead of a soft warning (used by ``hermes web``).
-
-    Returns True if the build succeeded or was skipped (no package.json).
-    """
-    if not (web_dir / "package.json").exists():
-        return True
-    import shutil
-    npm = shutil.which("npm")
-    if not npm:
-        if fatal:
-            print("Web UI frontend not built and npm is not available.")
-            print("Install Node.js, then run:  cd web && npm install && npm run build")
-        return not fatal
-    print("→ Building web UI...")
-    r1 = subprocess.run([npm, "install", "--silent"], cwd=web_dir, capture_output=True)
-    if r1.returncode != 0:
-        print(f"  {'✗' if fatal else '⚠'} Web UI npm install failed"
-              + ("" if fatal else " (hermes web will not be available)"))
-        if fatal:
-            print("  Run manually:  cd web && npm install && npm run build")
-        return False
-    r2 = subprocess.run([npm, "run", "build"], cwd=web_dir, capture_output=True)
-    if r2.returncode != 0:
-        print(f"  {'✗' if fatal else '⚠'} Web UI build failed"
-              + ("" if fatal else " (hermes web will not be available)"))
-        if fatal:
-            print("  Run manually:  cd web && npm install && npm run build")
-        return False
-    print("  ✓ Web UI built")
-    return True
-
-
 def _update_via_zip(args):
     """Update Hermes Agent by downloading a ZIP archive.
     
@@ -3073,10 +2955,7 @@ def _update_via_zip(args):
                 check=True,
             )
         _install_python_dependencies_with_optional_fallback(pip_cmd)
-
-    # Build web UI frontend (optional — requires npm)
-    _build_web_ui(PROJECT_ROOT / "web")
-
+    
     # Sync skills
     try:
         from tools.skills_sync import sync_skills
@@ -3823,10 +3702,7 @@ def cmd_update(args):
             if shutil.which("npm"):
                 print("→ Updating Node.js dependencies...")
                 subprocess.run(["npm", "install", "--silent"], cwd=PROJECT_ROOT, check=False)
-
-        # Build web UI frontend (optional — requires npm)
-        _build_web_ui(PROJECT_ROOT / "web")
-
+        
         print()
         print("✓ Code updated!")
         
@@ -3954,26 +3830,6 @@ def cmd_update(args):
         print()
         print("✓ Update complete!")
         
-        # Write exit code *before* the gateway restart attempt.
-        # When running as ``hermes update --gateway`` (spawned by the gateway's
-        # /update command), this process lives inside the gateway's systemd
-        # cgroup.  ``systemctl restart hermes-gateway`` kills everything in the
-        # cgroup (KillMode=mixed → SIGKILL to remaining processes), including
-        # us and the wrapping bash shell.  The shell never reaches its
-        # ``printf $status > .update_exit_code`` epilogue, so the exit-code
-        # marker file is never created.  The new gateway's update watcher then
-        # polls for 30 minutes and sends a spurious timeout message.
-        #
-        # Writing the marker here — after git pull + pip install succeed but
-        # before we attempt the restart — ensures the new gateway sees it
-        # regardless of how we die.
-        if gateway_mode:
-            _exit_code_path = get_hermes_home() / ".update_exit_code"
-            try:
-                _exit_code_path.write_text("0")
-            except OSError:
-                pass
-        
         # Auto-restart ALL gateways after update.
         # The code update (git pull) is shared across all profiles, so every
         # running gateway needs restarting to pick up the new code.
@@ -4052,7 +3908,7 @@ def cmd_update(args):
             # Exclude PIDs that belong to just-restarted services so we don't
             # immediately kill the process that systemd/launchd just spawned.
             service_pids = _get_service_pids()
-            manual_pids = find_gateway_pids(exclude_pids=service_pids, all_profiles=True)
+            manual_pids = find_gateway_pids(exclude_pids=service_pids)
             for pid in manual_pids:
                 try:
                     os.kill(pid, _signal.SIGTERM)
@@ -4108,7 +3964,7 @@ def _coalesce_session_name_args(argv: list) -> list:
         "chat", "model", "gateway", "setup", "whatsapp", "login", "logout", "auth",
         "status", "cron", "doctor", "config", "pairing", "skills", "tools",
         "mcp", "sessions", "insights", "version", "update", "uninstall",
-        "profile", "dashboard",
+        "profile",
     }
     _SESSION_FLAGS = {"-c", "--continue", "-r", "--resume"}
 
@@ -4258,24 +4114,18 @@ def cmd_profile(args):
                             print(f'  Add to your shell config (~/.bashrc or ~/.zshrc):')
                             print(f'    export PATH="$HOME/.local/bin:$PATH"')
 
-            # Profile dir for display
-            try:
-                profile_dir_display = "~/" + str(profile_dir.relative_to(Path.home()))
-            except ValueError:
-                profile_dir_display = str(profile_dir)
-
             # Next steps
             print(f"\nNext steps:")
             print(f"  {name} setup              Configure API keys and model")
             print(f"  {name} chat               Start chatting")
             print(f"  {name} gateway start      Start the messaging gateway")
             if clone or clone_all:
+                try:
+                    profile_dir_display = "~/" + str(profile_dir.relative_to(Path.home()))
+                except ValueError:
+                    profile_dir_display = str(profile_dir)
                 print(f"\n  Edit {profile_dir_display}/.env for different API keys")
                 print(f"  Edit {profile_dir_display}/SOUL.md for different personality")
-            else:
-                print(f"\n  ⚠ This profile has no API keys yet. Run '{name} setup' first,")
-                print(f"    or it will inherit keys from your shell environment.")
-                print(f"  Edit {profile_dir_display}/SOUL.md to customize personality")
             print()
 
         except (ValueError, FileExistsError, FileNotFoundError) as e:
@@ -4386,27 +4236,6 @@ def cmd_profile(args):
             sys.exit(1)
 
 
-def cmd_dashboard(args):
-    """Start the web UI server."""
-    try:
-        import fastapi  # noqa: F401
-        import uvicorn  # noqa: F401
-    except ImportError:
-        print("Web UI dependencies not installed.")
-        print("Install them with:  pip install hermes-agent[web]")
-        sys.exit(1)
-
-    if not _build_web_ui(PROJECT_ROOT / "web", fatal=True):
-        sys.exit(1)
-
-    from hermes_cli.web_server import start_server
-    start_server(
-        host=args.host,
-        port=args.port,
-        open_browser=not args.no_open,
-    )
-
-
 def cmd_completion(args):
     """Print shell completion script."""
     from hermes_cli.profiles import generate_bash_completion, generate_zsh_completion
@@ -4434,7 +4263,6 @@ def cmd_logs(args):
         level=getattr(args, "level", None),
         session=getattr(args, "session", None),
         since=getattr(args, "since", None),
-        component=getattr(args, "component", None),
     )
 
 
@@ -4472,7 +4300,6 @@ Examples:
     hermes logs -f                Follow agent.log in real time
     hermes logs errors            View errors.log
     hermes logs --since 1h        Lines from the last hour
-    hermes debug share             Upload debug report for support
     hermes update                 Update to latest version
 
 For more help on a command:
@@ -4559,7 +4386,7 @@ For more help on a command:
     )
     chat_parser.add_argument(
         "--provider",
-        choices=["auto", "openrouter", "nous", "openai-codex", "copilot-acp", "copilot", "anthropic", "gemini", "huggingface", "zai", "kimi-coding", "kimi-coding-cn", "minimax", "minimax-cn", "kilocode", "xiaomi", "arcee"],
+        choices=["auto", "openrouter", "nous", "openai-codex", "copilot-acp", "copilot", "anthropic", "gemini", "huggingface", "zai", "kimi-coding", "minimax", "minimax-cn", "kilocode"],
         default=None,
         help="Inference provider (default: auto)"
     )
@@ -4624,6 +4451,12 @@ For more help on a command:
         default=None,
         help="Session source tag for filtering (default: cli). Use 'tool' for third-party integrations that should not appear in user session lists."
     )
+    chat_parser.add_argument(
+        "--host",
+        action="store_true",
+        default=False,
+        help="Run on the host even when NixOS container mode is active (bypass container exec)"
+    )
     chat_parser.set_defaults(func=cmd_chat)
 
     # =========================================================================
@@ -4685,7 +4518,7 @@ For more help on a command:
     gateway_subparsers = gateway_parser.add_subparsers(dest="gateway_command")
     
     # gateway run (default)
-    gateway_run = gateway_subparsers.add_parser("run", help="Run gateway in foreground (recommended for WSL, Docker, Termux)")
+    gateway_run = gateway_subparsers.add_parser("run", help="Run gateway in foreground")
     gateway_run.add_argument("-v", "--verbose", action="count", default=0,
                              help="Increase stderr log verbosity (-v=INFO, -vv=DEBUG)")
     gateway_run.add_argument("-q", "--quiet", action="store_true",
@@ -4694,7 +4527,7 @@ For more help on a command:
                              help="Replace any existing gateway instance (useful for systemd)")
     
     # gateway start
-    gateway_start = gateway_subparsers.add_parser("start", help="Start the installed systemd/launchd background service")
+    gateway_start = gateway_subparsers.add_parser("start", help="Start gateway service")
     gateway_start.add_argument("--system", action="store_true", help="Target the Linux system-level gateway service")
     
     # gateway stop
@@ -4712,7 +4545,7 @@ For more help on a command:
     gateway_status.add_argument("--system", action="store_true", help="Target the Linux system-level gateway service")
     
     # gateway install
-    gateway_install = gateway_subparsers.add_parser("install", help="Install gateway as a systemd/launchd background service")
+    gateway_install = gateway_subparsers.add_parser("install", help="Install gateway as service")
     gateway_install.add_argument("--force", action="store_true", help="Force reinstall")
     gateway_install.add_argument("--system", action="store_true", help="Install as a Linux system-level service (starts at boot)")
     gateway_install.add_argument("--run-as-user", dest="run_as_user", help="User account the Linux system service should run as")
@@ -5001,90 +4834,7 @@ For more help on a command:
         help="Show redacted API key prefixes (first/last 4 chars) instead of just set/not set"
     )
     dump_parser.set_defaults(func=cmd_dump)
-
-    # =========================================================================
-    # debug command
-    # =========================================================================
-    debug_parser = subparsers.add_parser(
-        "debug",
-        help="Debug tools — upload logs and system info for support",
-        description="Debug utilities for Hermes Agent. Use 'hermes debug share' to "
-                    "upload a debug report (system info + recent logs) to a paste "
-                    "service and get a shareable URL.",
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-        epilog="""\
-Examples:
-    hermes debug share              Upload debug report and print URL
-    hermes debug share --lines 500  Include more log lines
-    hermes debug share --expire 30  Keep paste for 30 days
-    hermes debug share --local      Print report locally (no upload)
-""",
-    )
-    debug_sub = debug_parser.add_subparsers(dest="debug_command")
-    share_parser = debug_sub.add_parser(
-        "share",
-        help="Upload debug report to a paste service and print a shareable URL",
-    )
-    share_parser.add_argument(
-        "--lines", type=int, default=200,
-        help="Number of log lines to include per log file (default: 200)",
-    )
-    share_parser.add_argument(
-        "--expire", type=int, default=7,
-        help="Paste expiry in days (default: 7)",
-    )
-    share_parser.add_argument(
-        "--local", action="store_true",
-        help="Print the report locally instead of uploading",
-    )
-    debug_parser.set_defaults(func=cmd_debug)
-
-    # =========================================================================
-    # backup command
-    # =========================================================================
-    backup_parser = subparsers.add_parser(
-        "backup",
-        help="Back up Hermes home directory to a zip file",
-        description="Create a zip archive of your entire Hermes configuration, "
-                    "skills, sessions, and data (excludes the hermes-agent codebase). "
-                    "Use --quick for a fast snapshot of just critical state files."
-    )
-    backup_parser.add_argument(
-        "-o", "--output",
-        help="Output path for the zip file (default: ~/hermes-backup-<timestamp>.zip)"
-    )
-    backup_parser.add_argument(
-        "-q", "--quick",
-        action="store_true",
-        help="Quick snapshot: only critical state files (config, state.db, .env, auth, cron)"
-    )
-    backup_parser.add_argument(
-        "-l", "--label",
-        help="Label for the snapshot (only used with --quick)"
-    )
-    backup_parser.set_defaults(func=cmd_backup)
-
-    # =========================================================================
-    # import command
-    # =========================================================================
-    import_parser = subparsers.add_parser(
-        "import",
-        help="Restore a Hermes backup from a zip file",
-        description="Extract a previously created Hermes backup into your "
-                    "Hermes home directory, restoring configuration, skills, "
-                    "sessions, and data"
-    )
-    import_parser.add_argument(
-        "zipfile",
-        help="Path to the backup zip file"
-    )
-    import_parser.add_argument(
-        "--force", "-f",
-        action="store_true",
-        help="Overwrite existing files without confirmation"
-    )
-    import_parser.set_defaults(func=cmd_import)
-
+    
     # =========================================================================
     # config command
     # =========================================================================
@@ -5434,8 +5184,6 @@ Examples:
     mcp_add_p.add_argument("--command", help="Stdio command (e.g. npx)")
     mcp_add_p.add_argument("--args", nargs="*", default=[], help="Arguments for stdio command")
     mcp_add_p.add_argument("--auth", choices=["oauth", "header"], help="Auth method")
-    mcp_add_p.add_argument("--preset", help="Known MCP preset name")
-    mcp_add_p.add_argument("--env", nargs="*", default=[], help="Environment variables for stdio servers (KEY=VALUE)")
 
     mcp_rm_p = mcp_sub.add_parser("remove", aliases=["rm"], help="Remove an MCP server")
     mcp_rm_p.add_argument("name", help="Server name to remove")
@@ -5698,8 +5446,7 @@ Examples:
     claw_migrate = claw_subparsers.add_parser(
         "migrate",
         help="Migrate from OpenClaw to Hermes",
-        description="Import settings, memories, skills, and API keys from an OpenClaw installation. "
-                    "Always shows a preview before making changes."
+        description="Import settings, memories, skills, and API keys from an OpenClaw installation"
     )
     claw_migrate.add_argument(
         "--source",
@@ -5708,7 +5455,7 @@ Examples:
     claw_migrate.add_argument(
         "--dry-run",
         action="store_true",
-        help="Preview only — stop after showing what would be migrated"
+        help="Preview what would be migrated without making changes"
     )
     claw_migrate.add_argument(
         "--preset",
@@ -5902,19 +5649,6 @@ Examples:
     )
     completion_parser.set_defaults(func=cmd_completion)
 
-    # =========================================================================
-    # dashboard command
-    # =========================================================================
-    dashboard_parser = subparsers.add_parser(
-        "dashboard",
-        help="Start the web UI dashboard",
-        description="Launch the Hermes Agent web dashboard for managing config, API keys, and sessions",
-    )
-    dashboard_parser.add_argument("--port", type=int, default=9119, help="Port (default 9119)")
-    dashboard_parser.add_argument("--host", default="127.0.0.1", help="Host (default 127.0.0.1)")
-    dashboard_parser.add_argument("--no-open", action="store_true", help="Don't open browser automatically")
-    dashboard_parser.set_defaults(func=cmd_dashboard)
-
     # =========================================================================
     # logs command
     # =========================================================================
@@ -5931,7 +5665,6 @@ Examples:
     hermes logs gateway -n 100     Show last 100 lines of gateway.log
     hermes logs --level WARNING    Only show WARNING and above
     hermes logs --session abc123   Filter by session ID
-    hermes logs --component tools  Only show tool-related lines
     hermes logs --since 1h         Lines from the last hour
     hermes logs --since 30m -f     Follow, starting from 30 min ago
     hermes logs list               List available log files with sizes
@@ -5961,10 +5694,6 @@ Examples:
         "--since", metavar="TIME",
         help="Show lines since TIME ago (e.g. 1h, 30m, 2d)",
     )
-    logs_parser.add_argument(
-        "--component", metavar="NAME",
-        help="Filter by component: gateway, agent, tools, cli, cron",
-    )
     logs_parser.set_defaults(func=cmd_logs)
 
     # =========================================================================
@@ -5973,22 +5702,9 @@ Examples:
     # Pre-process argv so unquoted multi-word session names after -c / -r
     # are merged into a single token before argparse sees them.
     # e.g. ``hermes -c Pokemon Agent Dev`` → ``hermes -c 'Pokemon Agent Dev'``
-    # ── Container-aware routing ────────────────────────────────────────
-    # When NixOS container mode is active, route ALL subcommands into
-    # the managed container.  This MUST run before parse_args() so that
-    # --help, unrecognised flags, and every subcommand are forwarded
-    # transparently instead of being intercepted by argparse on the host.
-    from hermes_cli.config import get_container_exec_info
-    container_info = get_container_exec_info()
-    if container_info:
-        _exec_in_container(container_info, sys.argv[1:])
-        # Unreachable: os.execvp never returns on success (process is replaced)
-        # and raises OSError on failure (which propagates as a traceback).
-        sys.exit(1)
-
     _processed_argv = _coalesce_session_name_args(sys.argv[1:])
     args = parser.parse_args(_processed_argv)
-
+    
     # Handle --version flag
     if args.version:
         cmd_version(args)

hermes_cli/mcp_config.py

@@ -9,6 +9,7 @@ configuration in ~/.hermes/config.yaml under the ``mcp_servers`` key.
 """
 
 import asyncio
+import getpass
 import logging
 import os
 import re
@@ -27,11 +28,6 @@ from hermes_constants import display_hermes_home
 
 logger = logging.getLogger(__name__)
 
-_ENV_VAR_NAME_RE = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*$")
-
-
-_MCP_PRESETS: Dict[str, Dict[str, Any]] = {}
-
 
 # ─── UI Helpers ───────────────────────────────────────────────────────────────
 
@@ -61,8 +57,19 @@ def _confirm(question: str, default: bool = True) -> bool:
 
 
 def _prompt(question: str, *, password: bool = False, default: str = "") -> str:
-    from hermes_cli.cli_output import prompt as _shared_prompt
-    return _shared_prompt(question, default=default, password=password)
+    display = f"  {question}"
+    if default:
+        display += f" [{default}]"
+    display += ": "
+    try:
+        if password:
+            value = getpass.getpass(color(display, Colors.YELLOW))
+        else:
+            value = input(color(display, Colors.YELLOW))
+        return value.strip() or default
+    except (KeyboardInterrupt, EOFError):
+        print()
+        return default
 
 
 # ─── Config Helpers ───────────────────────────────────────────────────────────
@@ -102,59 +109,6 @@ def _env_key_for_server(name: str) -> str:
     return f"MCP_{name.upper().replace('-', '_')}_API_KEY"
 
 
-def _parse_env_assignments(raw_env: Optional[List[str]]) -> Dict[str, str]:
-    """Parse ``KEY=VALUE`` strings from CLI args into an env dict."""
-    parsed: Dict[str, str] = {}
-    for item in raw_env or []:
-        text = str(item or "").strip()
-        if not text:
-            continue
-        if "=" not in text:
-            raise ValueError(f"Invalid --env value '{text}' (expected KEY=VALUE)")
-        key, value = text.split("=", 1)
-        key = key.strip()
-        if not key:
-            raise ValueError(f"Invalid --env value '{text}' (missing variable name)")
-        if not _ENV_VAR_NAME_RE.match(key):
-            raise ValueError(f"Invalid --env variable name '{key}'")
-        parsed[key] = value
-    return parsed
-
-
-def _apply_mcp_preset(
-    name: str,
-    *,
-    preset_name: Optional[str],
-    url: Optional[str],
-    command: Optional[str],
-    cmd_args: List[str],
-    server_config: Dict[str, Any],
-) -> tuple[Optional[str], Optional[str], List[str], bool]:
-    """Apply a known MCP preset when transport details were omitted."""
-    if not preset_name:
-        return url, command, cmd_args, False
-
-    preset = _MCP_PRESETS.get(preset_name)
-    if not preset:
-        raise ValueError(f"Unknown MCP preset: {preset_name}")
-
-    if url or command:
-        return url, command, cmd_args, False
-
-    url = preset.get("url")
-    command = preset.get("command")
-    cmd_args = list(preset.get("args") or [])
-
-    if url:
-        server_config["url"] = url
-    if command:
-        server_config["command"] = command
-    if cmd_args:
-        server_config["args"] = cmd_args
-
-    return url, command, cmd_args, True
-
-
 # ─── Discovery (temporary connect) ───────────────────────────────────────────
 
 def _probe_single_server(
@@ -223,35 +177,13 @@ def cmd_mcp_add(args):
     command = getattr(args, "command", None)
     cmd_args = getattr(args, "args", None) or []
     auth_type = getattr(args, "auth", None)
-    preset_name = getattr(args, "preset", None)
-    raw_env = getattr(args, "env", None)
-
-    server_config: Dict[str, Any] = {}
-    try:
-        explicit_env = _parse_env_assignments(raw_env)
-        url, command, cmd_args, _preset_applied = _apply_mcp_preset(
-            name,
-            preset_name=preset_name,
-            url=url,
-            command=command,
-            cmd_args=list(cmd_args),
-            server_config=server_config,
-        )
-    except ValueError as exc:
-        _error(str(exc))
-        return
-
-    if url and explicit_env:
-        _error("--env is only supported for stdio MCP servers (--command or stdio presets)")
-        return
 
     # Validate transport
     if not url and not command:
-        _error("Must specify --url <endpoint>, --command <cmd>, or --preset <name>")
+        _error("Must specify --url <endpoint> or --command <cmd>")
         _info("Examples:")
         _info('  hermes mcp add ink --url "https://mcp.ml.ink/mcp"')
         _info('  hermes mcp add github --command npx --args @modelcontextprotocol/server-github')
-        _info('  hermes mcp add myserver --preset mypreset')
         return
 
     # Check if server already exists
@@ -262,15 +194,13 @@ def cmd_mcp_add(args):
             return
 
     # Build initial config
+    server_config: Dict[str, Any] = {}
     if url:
         server_config["url"] = url
     else:
         server_config["command"] = command
         if cmd_args:
             server_config["args"] = cmd_args
-        if explicit_env:
-            server_config["env"] = explicit_env
-
 
     # ── Authentication ────────────────────────────────────────────────
 
@@ -708,7 +638,6 @@ def mcp_command(args):
         _info("hermes mcp serve                              Run as MCP server")
         _info("hermes mcp add <name> --url <endpoint>        Add an MCP server")
         _info("hermes mcp add <name> --command <cmd>         Add a stdio server")
-        _info("hermes mcp add <name> --preset <preset>       Add from a known preset")
         _info("hermes mcp remove <name>                      Remove a server")
         _info("hermes mcp list                               List servers")
         _info("hermes mcp test <name>                        Test connection")

hermes_cli/memory_setup.py

@@ -25,13 +25,85 @@ def _curses_select(title: str, items: list[tuple[str, str]], default: int = 0) -
     items: list of (label, description) tuples.
     Returns selected index, or default on escape/quit.
     """
-    from hermes_cli.curses_ui import curses_radiolist
-    # Format (label, desc) tuples into display strings
-    display_items = [
-        f"{label}  {desc}" if desc else label
-        for label, desc in items
-    ]
-    return curses_radiolist(title, display_items, selected=default, cancel_returns=default)
+    try:
+        import curses
+        result = [default]
+
+        def _menu(stdscr):
+            curses.curs_set(0)
+            if curses.has_colors():
+                curses.start_color()
+                curses.use_default_colors()
+                curses.init_pair(1, curses.COLOR_GREEN, -1)
+                curses.init_pair(2, curses.COLOR_YELLOW, -1)
+                curses.init_pair(3, curses.COLOR_CYAN, -1)
+            cursor = default
+
+            while True:
+                stdscr.clear()
+                max_y, max_x = stdscr.getmaxyx()
+
+                # Title
+                try:
+                    stdscr.addnstr(0, 0, title, max_x - 1,
+                                   curses.A_BOLD | (curses.color_pair(2) if curses.has_colors() else 0))
+                    stdscr.addnstr(1, 0, "  ↑↓ navigate  ⏎ select  q quit", max_x - 1,
+                                   curses.color_pair(3) if curses.has_colors() else curses.A_DIM)
+                except curses.error:
+                    pass
+
+                for i, (label, desc) in enumerate(items):
+                    y = i + 3
+                    if y >= max_y - 1:
+                        break
+                    arrow = "→" if i == cursor else " "
+                    line = f" {arrow}  {label}"
+                    if desc:
+                        line += f"  {desc}"
+
+                    attr = curses.A_NORMAL
+                    if i == cursor:
+                        attr = curses.A_BOLD
+                        if curses.has_colors():
+                            attr |= curses.color_pair(1)
+                    try:
+                        stdscr.addnstr(y, 0, line[:max_x - 1], max_x - 1, attr)
+                    except curses.error:
+                        pass
+
+                stdscr.refresh()
+                key = stdscr.getch()
+
+                if key in (curses.KEY_UP, ord('k')):
+                    cursor = (cursor - 1) % len(items)
+                elif key in (curses.KEY_DOWN, ord('j')):
+                    cursor = (cursor + 1) % len(items)
+                elif key in (curses.KEY_ENTER, 10, 13):
+                    result[0] = cursor
+                    return
+                elif key in (27, ord('q')):
+                    return
+
+        curses.wrapper(_menu)
+        return result[0]
+
+    except Exception:
+        # Fallback: numbered input
+        print(f"\n  {title}\n")
+        for i, (label, desc) in enumerate(items):
+            marker = "→" if i == default else " "
+            d = f"  {desc}" if desc else ""
+            print(f"  {marker} {i + 1}. {label}{d}")
+        while True:
+            try:
+                val = input(f"\n  Select [1-{len(items)}] ({default + 1}): ")
+                if not val:
+                    return default
+                idx = int(val) - 1
+                if 0 <= idx < len(items):
+                    return idx
+            except (ValueError, EOFError):
+                return default
 
 
 def _prompt(label: str, default: str | None = None, secret: bool = False) -> str:

hermes_cli/model_normalize.py

@@ -8,9 +8,8 @@ Different LLM providers expect model identifiers in different formats:
   hyphens: ``claude-sonnet-4-6``.
 - **Copilot** expects bare names *with* dots preserved:
   ``claude-sonnet-4.6``.
-- **OpenCode Zen** preserves dots for GPT/GLM/Gemini/Kimi/MiniMax-style
-  model IDs, but Claude still uses hyphenated native names like
-  ``claude-sonnet-4-6``.
+- **OpenCode Zen** follows the same dot-to-hyphen convention as
+  Anthropic: ``claude-sonnet-4-6``.
 - **OpenCode Go** preserves dots in model names: ``minimax-m2.7``.
 - **DeepSeek** only accepts two model identifiers:
   ``deepseek-chat`` and ``deepseek-reasoner``.
@@ -51,7 +50,6 @@ _VENDOR_PREFIXES: dict[str, str] = {
     "grok": "x-ai",
     "qwen": "qwen",
     "mimo": "xiaomi",
-    "trinity": "arcee-ai",
     "nemotron": "nvidia",
     "llama": "meta-llama",
     "step": "stepfun",
@@ -69,19 +67,20 @@ _AGGREGATOR_PROVIDERS: frozenset[str] = frozenset({
 # Providers that want bare names with dots replaced by hyphens.
 _DOT_TO_HYPHEN_PROVIDERS: frozenset[str] = frozenset({
     "anthropic",
+    "opencode-zen",
 })
 
 # Providers that want bare names with dots preserved.
 _STRIP_VENDOR_ONLY_PROVIDERS: frozenset[str] = frozenset({
     "copilot",
     "copilot-acp",
-    "openai-codex",
 })
 
 # Providers whose native naming is authoritative -- pass through unchanged.
 _AUTHORITATIVE_NATIVE_PROVIDERS: frozenset[str] = frozenset({
     "gemini",
     "huggingface",
+    "openai-codex",
 })
 
 # Direct providers that accept bare native names but should repair a matching
@@ -89,13 +88,10 @@ _AUTHORITATIVE_NATIVE_PROVIDERS: frozenset[str] = frozenset({
 _MATCHING_PREFIX_STRIP_PROVIDERS: frozenset[str] = frozenset({
     "zai",
     "kimi-coding",
-    "kimi-coding-cn",
     "minimax",
     "minimax-cn",
     "alibaba",
     "qwen-oauth",
-    "xiaomi",
-    "arcee",
     "custom",
 })
 
@@ -332,9 +328,6 @@ def normalize_model_for_provider(model_input: str, target_provider: str) -> str:
         >>> normalize_model_for_provider("claude-sonnet-4.6", "opencode-zen")
         'claude-sonnet-4-6'
 
-        >>> normalize_model_for_provider("minimax-m2.5-free", "opencode-zen")
-        'minimax-m2.5-free'
-
         >>> normalize_model_for_provider("deepseek-v3", "deepseek")
         'deepseek-chat'
 
@@ -357,16 +350,7 @@ def normalize_model_for_provider(model_input: str, target_provider: str) -> str:
     if provider in _AGGREGATOR_PROVIDERS:
         return _prepend_vendor(name)
 
-    # --- OpenCode Zen: Claude stays hyphenated; other models keep dots ---
-    if provider == "opencode-zen":
-        bare = _strip_matching_provider_prefix(name, provider)
-        if "/" in bare:
-            return bare
-        if bare.lower().startswith("claude-"):
-            return _dots_to_hyphens(bare)
-        return bare
-
-    # --- Anthropic: strip matching provider prefix, dots -> hyphens ---
+    # --- Anthropic / OpenCode: strip matching provider prefix, dots -> hyphens ---
     if provider in _DOT_TO_HYPHEN_PROVIDERS:
         bare = _strip_matching_provider_prefix(name, provider)
         if "/" in bare:
@@ -375,11 +359,7 @@ def normalize_model_for_provider(model_input: str, target_provider: str) -> str:
 
     # --- Copilot: strip matching provider prefix, keep dots ---
     if provider in _STRIP_VENDOR_ONLY_PROVIDERS:
-        stripped = _strip_matching_provider_prefix(name, provider)
-        if stripped == name and name.startswith("openai/"):
-            # openai-codex maps openai/gpt-5.4 -> gpt-5.4
-            return name.split("/", 1)[1]
-        return stripped
+        return _strip_matching_provider_prefix(name, provider)
 
     # --- DeepSeek: map to one of two canonical names ---
     if provider == "deepseek":

hermes_cli/model_switch.py

@@ -21,7 +21,6 @@ OpenRouter variant suffixes (``:free``, ``:extended``, ``:fast``).
 from __future__ import annotations
 
 import logging
-import re
 from dataclasses import dataclass
 from typing import List, NamedTuple, Optional
 
@@ -41,6 +40,7 @@ from agent.models_dev import (
     get_model_capabilities,
     get_model_info,
     list_provider_models,
+    search_models_dev,
 )
 
 logger = logging.getLogger(__name__)
@@ -57,36 +57,10 @@ _HERMES_MODEL_WARNING = (
     "(Claude, GPT, Gemini, DeepSeek, etc.)."
 )
 
-# Match only the real Nous Research Hermes 3 / Hermes 4 chat families.
-# The previous substring check (`"hermes" in name.lower()`) false-positived on
-# unrelated local Modelfiles like ``hermes-brain:qwen3-14b-ctx16k`` that just
-# happen to carry "hermes" in their tag but are fully tool-capable.
-#
-# Positive examples the regex must match:
-#   NousResearch/Hermes-3-Llama-3.1-70B, hermes-4-405b, openrouter/hermes3:70b
-# Negative examples it must NOT match:
-#   hermes-brain:qwen3-14b-ctx16k, qwen3:14b, claude-opus-4-6
-_NOUS_HERMES_NON_AGENTIC_RE = re.compile(
-    r"(?:^|[/:])hermes[-_ ]?[34](?:[-_.:]|$)",
-    re.IGNORECASE,
-)
-
-
-def is_nous_hermes_non_agentic(model_name: str) -> bool:
-    """Return True if *model_name* is a real Nous Hermes 3/4 chat model.
-
-    Used to decide whether to surface the non-agentic warning at startup.
-    Callers in :mod:`cli.py` and here should go through this single helper
-    so the two sites don't drift.
-    """
-    if not model_name:
-        return False
-    return bool(_NOUS_HERMES_NON_AGENTIC_RE.search(model_name))
-
 
 def _check_hermes_model_warning(model_name: str) -> str:
-    """Return a warning string if *model_name* is a Nous Hermes 3/4 chat model."""
-    if is_nous_hermes_non_agentic(model_name):
+    """Return a warning string if *model_name* looks like a Hermes LLM model."""
+    if "hermes" in model_name.lower():
         return _HERMES_MODEL_WARNING
     return ""
 
@@ -865,11 +839,8 @@ def list_authenticated_providers(
                     if any(os.environ.get(ev) for ev in pcfg.api_key_env_vars):
                         has_creds = True
                         break
-        # Check auth store and credential pool for non-env-var credentials.
-        # This applies to OAuth providers AND api_key providers that also
-        # support OAuth (e.g. anthropic supports both API key and Claude Code
-        # OAuth via external credential files).
-        if not has_creds:
+        if not has_creds and 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()
@@ -882,38 +853,6 @@ def list_authenticated_providers(
                     has_creds = True
             except Exception as exc:
                 logger.debug("Auth store check failed for %s: %s", pid, exc)
-        # Fallback: check the credential pool with full auto-seeding.
-        # This catches credentials that exist in external stores (e.g.
-        # Codex CLI ~/.codex/auth.json) which _seed_from_singletons()
-        # imports on demand but aren't in the raw auth.json yet.
-        if not has_creds:
-            try:
-                from agent.credential_pool import load_pool
-                pool = load_pool(hermes_slug)
-                if pool.has_credentials():
-                    has_creds = True
-            except Exception as exc:
-                logger.debug("Credential pool check failed for %s: %s", hermes_slug, exc)
-        # Fallback: check external credential files directly.
-        # The credential pool gates anthropic behind
-        # is_provider_explicitly_configured() to prevent auxiliary tasks
-        # from silently consuming Claude Code tokens (PR #4210).
-        # But the /model picker is discovery-oriented — we WANT to show
-        # providers the user can switch to, even if they aren't currently
-        # configured.
-        if not has_creds and hermes_slug == "anthropic":
-            try:
-                from agent.anthropic_adapter import (
-                    read_claude_code_credentials,
-                    read_hermes_oauth_credentials,
-                )
-                hermes_creds = read_hermes_oauth_credentials()
-                cc_creds = read_claude_code_credentials()
-                if (hermes_creds and hermes_creds.get("accessToken")) or \
-                   (cc_creds and cc_creds.get("accessToken")):
-                    has_creds = True
-            except Exception as exc:
-                logger.debug("Anthropic external creds check failed: %s", exc)
         if not has_creds:
             continue
 
@@ -934,65 +873,6 @@ def list_authenticated_providers(
         seen_slugs.add(pid)
         seen_slugs.add(hermes_slug)
 
-    # --- 2b. Cross-check canonical provider list ---
-    # Catches providers that are in CANONICAL_PROVIDERS but weren't found
-    # in PROVIDER_TO_MODELS_DEV or HERMES_OVERLAYS (keeps /model in sync
-    # with `hermes model`).
-    try:
-        from hermes_cli.models import CANONICAL_PROVIDERS as _canon_provs
-    except ImportError:
-        _canon_provs = []
-
-    for _cp in _canon_provs:
-        if _cp.slug in seen_slugs:
-            continue
-
-        # Check credentials via PROVIDER_REGISTRY (auth.py)
-        _cp_config = _auth_registry.get(_cp.slug)
-        _cp_has_creds = False
-        if _cp_config and _cp_config.api_key_env_vars:
-            _cp_has_creds = any(os.environ.get(ev) for ev in _cp_config.api_key_env_vars)
-        # Also check auth store and credential pool
-        if not _cp_has_creds:
-            try:
-                from hermes_cli.auth import _load_auth_store
-                _cp_store = _load_auth_store()
-                _cp_providers_store = _cp_store.get("providers", {})
-                _cp_pool_store = _cp_store.get("credential_pool", {})
-                if _cp_store and (
-                    _cp.slug in _cp_providers_store
-                    or _cp.slug in _cp_pool_store
-                ):
-                    _cp_has_creds = True
-            except Exception:
-                pass
-        if not _cp_has_creds:
-            try:
-                from agent.credential_pool import load_pool
-                _cp_pool = load_pool(_cp.slug)
-                if _cp_pool.has_credentials():
-                    _cp_has_creds = True
-            except Exception:
-                pass
-
-        if not _cp_has_creds:
-            continue
-
-        _cp_model_ids = curated.get(_cp.slug, [])
-        _cp_total = len(_cp_model_ids)
-        _cp_top = _cp_model_ids[:max_models]
-
-        results.append({
-            "slug": _cp.slug,
-            "name": _cp.label,
-            "is_current": _cp.slug == current_provider,
-            "is_user_defined": False,
-            "models": _cp_top,
-            "total_models": _cp_total,
-            "source": "canonical",
-        })
-        seen_slugs.add(_cp.slug)
-
     # --- 3. User-defined endpoints from config ---
     if user_providers and isinstance(user_providers, dict):
         for ep_name, ep_cfg in user_providers.items():
@@ -1002,16 +882,9 @@ def list_authenticated_providers(
             api_url = ep_cfg.get("api", "") or ep_cfg.get("url", "") or ""
             default_model = ep_cfg.get("default_model", "")
 
-            # Build models list from both default_model and full models array
             models_list = []
             if default_model:
                 models_list.append(default_model)
-            # Also include the full models list from config
-            cfg_models = ep_cfg.get("models", [])
-            if isinstance(cfg_models, list):
-                for m in cfg_models:
-                    if m and m not in models_list:
-                        models_list.append(m)
 
             # Try to probe /v1/models if URL is set (but don't block on it)
             # For now just show what we know from config
@@ -1027,17 +900,7 @@ def list_authenticated_providers(
             })
 
     # --- 4. Saved custom providers from config ---
-    # Each ``custom_providers`` entry represents one model under a named
-    # provider. Entries sharing the same provider name are grouped into a
-    # single picker row so that e.g. four Ollama Cloud entries
-    # (qwen3-coder, glm-5.1, kimi-k2, minimax-m2.7) appear as one
-    # "Ollama Cloud" row with four models inside instead of four
-    # duplicate "Ollama Cloud" rows. Entries with distinct provider names
-    # still produce separate rows (e.g. Ollama Cloud vs Moonshot).
     if custom_providers and isinstance(custom_providers, list):
-        from collections import OrderedDict
-
-        groups: "OrderedDict[str, dict]" = OrderedDict()
         for entry in custom_providers:
             if not isinstance(entry, dict):
                 continue
@@ -1053,28 +916,23 @@ def list_authenticated_providers(
                 continue
 
             slug = custom_provider_slug(display_name)
-            if slug not in groups:
-                groups[slug] = {
-                    "name": display_name,
-                    "api_url": api_url,
-                    "models": [],
-                }
-            default_model = (entry.get("model") or "").strip()
-            if default_model and default_model not in groups[slug]["models"]:
-                groups[slug]["models"].append(default_model)
-
-        for slug, grp in groups.items():
             if slug in seen_slugs:
                 continue
+
+            models_list = []
+            default_model = (entry.get("model") or "").strip()
+            if default_model:
+                models_list.append(default_model)
+
             results.append({
                 "slug": slug,
-                "name": grp["name"],
+                "name": display_name,
                 "is_current": slug == current_provider,
                 "is_user_defined": True,
-                "models": grp["models"],
-                "total_models": len(grp["models"]),
+                "models": models_list,
+                "total_models": len(models_list),
                 "source": "user-config",
-                "api_url": grp["api_url"],
+                "api_url": api_url,
             })
             seen_slugs.add(slug)
 

hermes_cli/models.py

@@ -12,7 +12,7 @@ import os
 import urllib.request
 import urllib.error
 from difflib import get_close_matches
-from typing import Any, NamedTuple, Optional
+from typing import Any, Optional
 
 COPILOT_BASE_URL = "https://api.githubcopilot.com"
 COPILOT_MODELS_URL = f"{COPILOT_BASE_URL}/models"
@@ -56,27 +56,15 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
 
 _openrouter_catalog_cache: list[tuple[str, str]] | None = None
 
-
-def _codex_curated_models() -> list[str]:
-    """Derive the openai-codex curated list from codex_models.py.
-
-    Single source of truth: DEFAULT_CODEX_MODELS + forward-compat synthesis.
-    This keeps the gateway /model picker in sync with the CLI `hermes model`
-    flow without maintaining a separate static list.
-    """
-    from hermes_cli.codex_models import DEFAULT_CODEX_MODELS, _add_forward_compat_models
-    return _add_forward_compat_models(list(DEFAULT_CODEX_MODELS))
-
-
 _PROVIDER_MODELS: dict[str, list[str]] = {
     "nous": [
-        "xiaomi/mimo-v2-pro",
         "anthropic/claude-opus-4.6",
         "anthropic/claude-sonnet-4.6",
         "anthropic/claude-sonnet-4.5",
         "anthropic/claude-haiku-4.5",
         "openai/gpt-5.4",
         "openai/gpt-5.4-mini",
+        "xiaomi/mimo-v2-pro",
         "openai/gpt-5.3-codex",
         "google/gemini-3-pro-preview",
         "google/gemini-3-flash-preview",
@@ -98,7 +86,12 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "openai/gpt-5.4-pro",
         "openai/gpt-5.4-nano",
     ],
-    "openai-codex": _codex_curated_models(),
+    "openai-codex": [
+        "gpt-5.3-codex",
+        "gpt-5.2-codex",
+        "gpt-5.1-codex-mini",
+        "gpt-5.1-codex-max",
+    ],
     "copilot-acp": [
         "copilot-acp",
     ],
@@ -130,7 +123,6 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "gemma-4-26b-it",
     ],
     "zai": [
-        "glm-5.1",
         "glm-5",
         "glm-5-turbo",
         "glm-4.7",
@@ -158,12 +150,6 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "kimi-k2-turbo-preview",
         "kimi-k2-0905-preview",
     ],
-    "kimi-coding-cn": [
-        "kimi-k2.5",
-        "kimi-k2-thinking",
-        "kimi-k2-turbo-preview",
-        "kimi-k2-0905-preview",
-    ],
     "moonshot": [
         "kimi-k2.5",
         "kimi-k2-thinking",
@@ -171,16 +157,22 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "kimi-k2-0905-preview",
     ],
     "minimax": [
-        "MiniMax-M2.7",
+        "MiniMax-M1",
+        "MiniMax-M1-40k",
+        "MiniMax-M1-80k",
+        "MiniMax-M1-128k",
+        "MiniMax-M1-256k",
         "MiniMax-M2.5",
-        "MiniMax-M2.1",
-        "MiniMax-M2",
+        "MiniMax-M2.7",
     ],
     "minimax-cn": [
-        "MiniMax-M2.7",
+        "MiniMax-M1",
+        "MiniMax-M1-40k",
+        "MiniMax-M1-80k",
+        "MiniMax-M1-128k",
+        "MiniMax-M1-256k",
         "MiniMax-M2.5",
-        "MiniMax-M2.1",
-        "MiniMax-M2",
+        "MiniMax-M2.7",
     ],
     "anthropic": [
         "claude-opus-4-6",
@@ -195,16 +187,6 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "deepseek-chat",
         "deepseek-reasoner",
     ],
-    "xiaomi": [
-        "mimo-v2-pro",
-        "mimo-v2-omni",
-        "mimo-v2-flash",
-    ],
-    "arcee": [
-        "trinity-large-thinking",
-        "trinity-large-preview",
-        "trinity-mini",
-    ],
     "opencode-zen": [
         "gpt-5.4-pro",
         "gpt-5.4",
@@ -490,52 +472,28 @@ def check_nous_free_tier() -> bool:
         return False  # default to paid on error — don't block users
 
 
-# ---------------------------------------------------------------------------
-# Canonical provider list — single source of truth for provider identity.
-# Every code path that lists, displays, or iterates providers derives from
-# this list:  hermes model, /model, /provider, list_authenticated_providers.
-#
-# Fields:
-#   slug        — internal provider ID (used in config.yaml, --provider flag)
-#   label       — short display name
-#   tui_desc    — longer description for the `hermes model` interactive picker
-# ---------------------------------------------------------------------------
-
-class ProviderEntry(NamedTuple):
-    slug: str
-    label: str
-    tui_desc: str   # detailed description for `hermes model` TUI
-
-
-CANONICAL_PROVIDERS: list[ProviderEntry] = [
-    ProviderEntry("nous",           "Nous Portal",              "Nous Portal (Nous Research subscription)"),
-    ProviderEntry("openrouter",     "OpenRouter",               "OpenRouter (100+ models, pay-per-use)"),
-    ProviderEntry("anthropic",      "Anthropic",                "Anthropic (Claude models — API key or Claude Code)"),
-    ProviderEntry("openai-codex",   "OpenAI Codex",             "OpenAI Codex"),
-    ProviderEntry("qwen-oauth",     "Qwen OAuth (Portal)",      "Qwen OAuth (reuses local Qwen CLI login)"),
-    ProviderEntry("copilot",        "GitHub Copilot",           "GitHub Copilot (uses GITHUB_TOKEN or gh auth token)"),
-    ProviderEntry("copilot-acp",    "GitHub Copilot ACP",       "GitHub Copilot ACP (spawns `copilot --acp --stdio`)"),
-    ProviderEntry("huggingface",    "Hugging Face",             "Hugging Face Inference Providers (20+ open models)"),
-    ProviderEntry("gemini",         "Google AI Studio",         "Google AI Studio (Gemini models — OpenAI-compatible endpoint)"),
-    ProviderEntry("deepseek",       "DeepSeek",                 "DeepSeek (DeepSeek-V3, R1, coder — direct API)"),
-    ProviderEntry("xai",            "xAI",                      "xAI (Grok models — direct API)"),
-    ProviderEntry("zai",            "Z.AI / GLM",               "Z.AI / GLM (Zhipu AI direct API)"),
-    ProviderEntry("kimi-coding",    "Kimi / Moonshot",          "Kimi / Moonshot (Moonshot AI direct API)"),
-    ProviderEntry("kimi-coding-cn", "Kimi / Moonshot (China)",  "Kimi / Moonshot China (Moonshot CN direct API)"),
-    ProviderEntry("minimax",        "MiniMax",                  "MiniMax (global direct API)"),
-    ProviderEntry("minimax-cn",     "MiniMax (China)",          "MiniMax China (domestic direct API)"),
-    ProviderEntry("alibaba",        "Alibaba Cloud (DashScope)","Alibaba Cloud / DashScope Coding (Qwen + multi-provider)"),
-    ProviderEntry("xiaomi",         "Xiaomi MiMo",              "Xiaomi MiMo (MiMo-V2 models — pro, omni, flash)"),
-    ProviderEntry("arcee",          "Arcee AI",                 "Arcee AI (Trinity models — direct API)"),
-    ProviderEntry("kilocode",       "Kilo Code",                "Kilo Code (Kilo Gateway API)"),
-    ProviderEntry("opencode-zen",   "OpenCode Zen",             "OpenCode Zen (35+ curated models, pay-as-you-go)"),
-    ProviderEntry("opencode-go",    "OpenCode Go",              "OpenCode Go (open models, $10/month subscription)"),
-    ProviderEntry("ai-gateway",     "AI Gateway",               "AI Gateway (Vercel — 200+ models, pay-per-use)"),
-]
-
-# Derived dicts — used throughout the codebase
-_PROVIDER_LABELS = {p.slug: p.label for p in CANONICAL_PROVIDERS}
-_PROVIDER_LABELS["custom"] = "Custom endpoint"  # special case: not a named provider
+_PROVIDER_LABELS = {
+    "openrouter": "OpenRouter",
+    "openai-codex": "OpenAI Codex",
+    "copilot-acp": "GitHub Copilot ACP",
+    "nous": "Nous Portal",
+    "copilot": "GitHub Copilot",
+    "gemini": "Google AI Studio",
+    "zai": "Z.AI / GLM",
+    "kimi-coding": "Kimi / Moonshot",
+    "minimax": "MiniMax",
+    "minimax-cn": "MiniMax (China)",
+    "anthropic": "Anthropic",
+    "deepseek": "DeepSeek",
+    "opencode-zen": "OpenCode Zen",
+    "opencode-go": "OpenCode Go",
+    "ai-gateway": "AI Gateway",
+    "kilocode": "Kilo Code",
+    "alibaba": "Alibaba Cloud (DashScope)",
+    "qwen-oauth": "Qwen OAuth (Portal)",
+    "huggingface": "Hugging Face",
+    "custom": "Custom endpoint",
+}
 
 _PROVIDER_ALIASES = {
     "glm": "zai",
@@ -553,10 +511,6 @@ _PROVIDER_ALIASES = {
     "google-ai-studio": "gemini",
     "kimi": "kimi-coding",
     "moonshot": "kimi-coding",
-    "kimi-cn": "kimi-coding-cn",
-    "moonshot-cn": "kimi-coding-cn",
-    "arcee-ai": "arcee",
-    "arceeai": "arcee",
     "minimax-china": "minimax-cn",
     "minimax_cn": "minimax-cn",
     "claude": "anthropic",
@@ -580,28 +534,9 @@ _PROVIDER_ALIASES = {
     "hf": "huggingface",
     "hugging-face": "huggingface",
     "huggingface-hub": "huggingface",
-    "mimo": "xiaomi",
-    "xiaomi-mimo": "xiaomi",
-    "grok": "xai",
-    "x-ai": "xai",
-    "x.ai": "xai",
 }
 
 
-def get_default_model_for_provider(provider: str) -> str:
-    """Return the default model for a provider, or empty string if unknown.
-
-    Uses the first entry in _PROVIDER_MODELS as the default.  This is the
-    model a user would be offered first in the ``hermes model`` picker.
-
-    Used as a fallback when the user has configured a provider but never
-    selected a model (e.g. ``hermes auth add openai-codex`` without
-    ``hermes model``).
-    """
-    models = _PROVIDER_MODELS.get(provider, [])
-    return models[0] if models else ""
-
-
 def _openrouter_model_is_free(pricing: Any) -> bool:
     """Return True when both prompt and completion pricing are zero."""
     if not isinstance(pricing, dict):
@@ -671,6 +606,13 @@ def model_ids(*, force_refresh: bool = False) -> list[str]:
     return [mid for mid, _ in fetch_openrouter_models(force_refresh=force_refresh)]
 
 
+def menu_labels(*, force_refresh: bool = False) -> list[str]:
+    """Return display labels like 'anthropic/claude-opus-4.6 (recommended)'."""
+    labels = []
+    for mid, desc in fetch_openrouter_models(force_refresh=force_refresh):
+        labels.append(f"{mid} ({desc})" if desc else mid)
+    return labels
+
 
 
 # ---------------------------------------------------------------------------
@@ -870,20 +812,23 @@ def list_available_providers() -> list[dict[str, str]]:
 
     Each dict has ``id``, ``label``, and ``aliases``.
     Checks which providers have valid credentials configured.
-
-    Derives the provider list from :data:`CANONICAL_PROVIDERS` (single
-    source of truth shared with ``hermes model``, ``/model``, etc.).
     """
-    # Derive display order from canonical list + custom
-    provider_order = [p.slug for p in CANONICAL_PROVIDERS] + ["custom"]
-
+    # Canonical providers in display order
+    _PROVIDER_ORDER = [
+        "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",
+    ]
     # Build reverse alias map
     aliases_for: dict[str, list[str]] = {}
     for alias, canonical in _PROVIDER_ALIASES.items():
         aliases_for.setdefault(canonical, []).append(alias)
 
     result = []
-    for pid in provider_order:
+    for pid in _PROVIDER_ORDER:
         label = _PROVIDER_LABELS.get(pid, pid)
         alias_list = aliases_for.get(pid, [])
         # Check if this provider has credentials available
@@ -1855,35 +1800,6 @@ def validate_requested_model(
             "message": message,
         }
 
-    # OpenAI Codex has its own catalog path; /v1/models probing is not the right validation path.
-    if normalized == "openai-codex":
-        try:
-            codex_models = provider_model_ids("openai-codex")
-        except Exception:
-            codex_models = []
-        if codex_models:
-            if requested_for_lookup in set(codex_models):
-                return {
-                    "accepted": True,
-                    "persist": True,
-                    "recognized": True,
-                    "message": None,
-                }
-            suggestions = get_close_matches(requested_for_lookup, codex_models, n=3, cutoff=0.5)
-            suggestion_text = ""
-            if suggestions:
-                suggestion_text = "\n  Similar models: " + ", ".join(f"`{s}`" for s in suggestions)
-            return {
-                "accepted": True,
-                "persist": True,
-                "recognized": False,
-                "message": (
-                    f"Note: `{requested}` was not found in the OpenAI Codex model listing. "
-                    f"It may still work if your account has access to it."
-                    f"{suggestion_text}"
-                ),
-            }
-
     # Probe the live API to check if the model actually exists
     api_models = fetch_api_models(api_key, base_url)
 

hermes_cli/nous_subscription.py

@@ -143,7 +143,6 @@ def _tts_label(current_provider: str) -> str:
         "openai": "OpenAI TTS",
         "elevenlabs": "ElevenLabs",
         "edge": "Edge TTS",
-        "mistral": "Mistral Voxtral TTS",
         "neutts": "NeuTTS",
     }
     return mapping.get(current_provider or "edge", current_provider or "Edge TTS")
@@ -310,7 +309,6 @@ def get_nous_subscription_features(
         tts_current_provider in {"edge", "neutts"}
         or (tts_current_provider == "openai" and (managed_tts_available or direct_openai_tts))
         or (tts_current_provider == "elevenlabs" and direct_elevenlabs)
-        or (tts_current_provider == "mistral" and bool(get_env_value("MISTRAL_API_KEY")))
     )
     tts_active = bool(tts_tool_enabled and tts_available)
 

hermes_cli/platforms.py

@@ -1,46 +0,0 @@
-"""
-Shared platform registry for Hermes Agent.
-
-Single source of truth for platform metadata consumed by both
-skills_config (label display) and tools_config (default toolset
-resolution).  Import ``PLATFORMS`` from here instead of maintaining
-duplicate dicts in each module.
-"""
-
-from collections import OrderedDict
-from typing import NamedTuple
-
-
-class PlatformInfo(NamedTuple):
-    """Metadata for a single platform entry."""
-    label: str
-    default_toolset: str
-
-
-# Ordered so that TUI menus are deterministic.
-PLATFORMS: OrderedDict[str, PlatformInfo] = OrderedDict([
-    ("cli",            PlatformInfo(label="🖥️  CLI",            default_toolset="hermes-cli")),
-    ("telegram",       PlatformInfo(label="📱 Telegram",        default_toolset="hermes-telegram")),
-    ("discord",        PlatformInfo(label="💬 Discord",         default_toolset="hermes-discord")),
-    ("slack",          PlatformInfo(label="💼 Slack",           default_toolset="hermes-slack")),
-    ("whatsapp",       PlatformInfo(label="📱 WhatsApp",        default_toolset="hermes-whatsapp")),
-    ("signal",         PlatformInfo(label="📡 Signal",          default_toolset="hermes-signal")),
-    ("bluebubbles",    PlatformInfo(label="💙 BlueBubbles",     default_toolset="hermes-bluebubbles")),
-    ("email",          PlatformInfo(label="📧 Email",           default_toolset="hermes-email")),
-    ("homeassistant",  PlatformInfo(label="🏠 Home Assistant",  default_toolset="hermes-homeassistant")),
-    ("mattermost",     PlatformInfo(label="💬 Mattermost",      default_toolset="hermes-mattermost")),
-    ("matrix",         PlatformInfo(label="💬 Matrix",          default_toolset="hermes-matrix")),
-    ("dingtalk",       PlatformInfo(label="💬 DingTalk",        default_toolset="hermes-dingtalk")),
-    ("feishu",         PlatformInfo(label="🪽 Feishu",          default_toolset="hermes-feishu")),
-    ("wecom",          PlatformInfo(label="💬 WeCom",           default_toolset="hermes-wecom")),
-    ("wecom_callback", PlatformInfo(label="💬 WeCom Callback",  default_toolset="hermes-wecom-callback")),
-    ("weixin",         PlatformInfo(label="💬 Weixin",          default_toolset="hermes-weixin")),
-    ("webhook",        PlatformInfo(label="🔗 Webhook",         default_toolset="hermes-webhook")),
-    ("api_server",     PlatformInfo(label="🌐 API Server",      default_toolset="hermes-api-server")),
-])
-
-
-def platform_label(key: str, default: str = "") -> str:
-    """Return the display label for a platform key, or *default*."""
-    info = PLATFORMS.get(key)
-    return info.label if info is not None else default

hermes_cli/plugins.py

@@ -31,6 +31,7 @@ import importlib
 import importlib.metadata
 import importlib.util
 import logging
+import os
 import sys
 import types
 from dataclasses import dataclass, field
@@ -200,7 +201,8 @@ class PluginContext:
 
         The *setup_fn* receives an argparse subparser and should add any
         arguments/sub-subparsers.  If *handler_fn* is provided it is set
-        as the default dispatch function via ``set_defaults(func=...)``."""
+        as the default dispatch function via ``set_defaults(func=...)``.
+        """
         self._manager._cli_commands[name] = {
             "name": name,
             "help": help,
@@ -211,38 +213,6 @@ class PluginContext:
         }
         logger.debug("Plugin %s registered CLI command: %s", self.manifest.name, name)
 
-    # -- context engine registration -----------------------------------------
-
-    def register_context_engine(self, engine) -> None:
-        """Register a context engine to replace the built-in ContextCompressor.
-
-        Only one context engine plugin is allowed. If a second plugin tries
-        to register one, it is rejected with a warning.
-
-        The engine must be an instance of ``agent.context_engine.ContextEngine``.
-        """
-        if self._manager._context_engine is not None:
-            logger.warning(
-                "Plugin '%s' tried to register a context engine, but one is "
-                "already registered. Only one context engine plugin is allowed.",
-                self.manifest.name,
-            )
-            return
-        # Defer the import to avoid circular deps at module level
-        from agent.context_engine import ContextEngine
-        if not isinstance(engine, ContextEngine):
-            logger.warning(
-                "Plugin '%s' tried to register a context engine that does not "
-                "inherit from ContextEngine. Ignoring.",
-                self.manifest.name,
-            )
-            return
-        self._manager._context_engine = engine
-        logger.info(
-            "Plugin '%s' registered context engine: %s",
-            self.manifest.name, engine.name,
-        )
-
     # -- hook registration --------------------------------------------------
 
     def register_hook(self, hook_name: str, callback: Callable) -> None:
@@ -275,7 +245,6 @@ class PluginManager:
         self._hooks: Dict[str, List[Callable]] = {}
         self._plugin_tool_names: Set[str] = set()
         self._cli_commands: Dict[str, dict] = {}
-        self._context_engine = None  # Set by a plugin via register_context_engine()
         self._discovered: bool = False
         self._cli_ref = None  # Set by CLI after plugin discovery
 
@@ -583,10 +552,18 @@ def invoke_hook(hook_name: str, **kwargs: Any) -> List[Any]:
     return get_plugin_manager().invoke_hook(hook_name, **kwargs)
 
 
+def get_plugin_tool_names() -> Set[str]:
+    """Return the set of tool names registered by plugins."""
+    return get_plugin_manager()._plugin_tool_names
 
-def get_plugin_context_engine():
-    """Return the plugin-registered context engine, or None."""
-    return get_plugin_manager()._context_engine
+
+def get_plugin_cli_commands() -> Dict[str, dict]:
+    """Return CLI commands registered by general plugins.
+
+    Returns a dict of ``{name: {help, setup_fn, handler_fn, ...}}``
+    suitable for wiring into argparse subparsers.
+    """
+    return dict(get_plugin_manager()._cli_commands)
 
 
 def get_plugin_toolsets() -> List[tuple]:

hermes_cli/plugins_cmd.py

@@ -531,7 +531,7 @@ def cmd_disable(name: str) -> None:
 
     disabled.add(name)
     _save_disabled_set(disabled)
-    console.print(f"[yellow]\u2298[/yellow] Plugin [bold]{name}[/bold] disabled. Takes effect on next session.")
+    console.print(f"[yellow]⊘[/yellow] Plugin [bold]{name}[/bold] disabled. Takes effect on next session.")
 
 
 def cmd_list() -> None:
@@ -594,152 +594,8 @@ def cmd_list() -> None:
     console.print("[dim]Enable/disable:[/dim] hermes plugins enable/disable <name>")
 
 
-# ---------------------------------------------------------------------------
-# Provider plugin discovery helpers
-# ---------------------------------------------------------------------------
-
-
-def _discover_memory_providers() -> list[tuple[str, str]]:
-    """Return [(name, description), ...] for available memory providers."""
-    try:
-        from plugins.memory import discover_memory_providers
-        return [(name, desc) for name, desc, _avail in discover_memory_providers()]
-    except Exception:
-        return []
-
-
-def _discover_context_engines() -> list[tuple[str, str]]:
-    """Return [(name, description), ...] for available context engines."""
-    try:
-        from plugins.context_engine import discover_context_engines
-        return [(name, desc) for name, desc, _avail in discover_context_engines()]
-    except Exception:
-        return []
-
-
-def _get_current_memory_provider() -> str:
-    """Return the current memory.provider from config (empty = built-in)."""
-    try:
-        from hermes_cli.config import load_config
-        config = load_config()
-        return config.get("memory", {}).get("provider", "") or ""
-    except Exception:
-        return ""
-
-
-def _get_current_context_engine() -> str:
-    """Return the current context.engine from config."""
-    try:
-        from hermes_cli.config import load_config
-        config = load_config()
-        return config.get("context", {}).get("engine", "compressor") or "compressor"
-    except Exception:
-        return "compressor"
-
-
-def _save_memory_provider(name: str) -> None:
-    """Persist memory.provider to config.yaml."""
-    from hermes_cli.config import load_config, save_config
-    config = load_config()
-    if "memory" not in config:
-        config["memory"] = {}
-    config["memory"]["provider"] = name
-    save_config(config)
-
-
-def _save_context_engine(name: str) -> None:
-    """Persist context.engine to config.yaml."""
-    from hermes_cli.config import load_config, save_config
-    config = load_config()
-    if "context" not in config:
-        config["context"] = {}
-    config["context"]["engine"] = name
-    save_config(config)
-
-
-def _configure_memory_provider() -> bool:
-    """Launch a radio picker for memory providers. Returns True if changed."""
-    from hermes_cli.curses_ui import curses_radiolist
-
-    current = _get_current_memory_provider()
-    providers = _discover_memory_providers()
-
-    # Build items: "built-in" first, then discovered providers
-    items = ["built-in (default)"]
-    names = [""]  # empty string = built-in
-    selected = 0
-
-    for name, desc in providers:
-        names.append(name)
-        label = f"{name} \u2014 {desc}" if desc else name
-        items.append(label)
-        if name == current:
-            selected = len(items) - 1
-
-    # If current provider isn't in discovered list, add it
-    if current and current not in names:
-        names.append(current)
-        items.append(f"{current} (not found)")
-        selected = len(items) - 1
-
-    choice = curses_radiolist(
-        title="Memory Provider (select one)",
-        items=items,
-        selected=selected,
-    )
-
-    new_provider = names[choice]
-    if new_provider != current:
-        _save_memory_provider(new_provider)
-        return True
-    return False
-
-
-def _configure_context_engine() -> bool:
-    """Launch a radio picker for context engines. Returns True if changed."""
-    from hermes_cli.curses_ui import curses_radiolist
-
-    current = _get_current_context_engine()
-    engines = _discover_context_engines()
-
-    # Build items: "compressor" first (built-in), then discovered engines
-    items = ["compressor (default)"]
-    names = ["compressor"]
-    selected = 0
-
-    for name, desc in engines:
-        names.append(name)
-        label = f"{name} \u2014 {desc}" if desc else name
-        items.append(label)
-        if name == current:
-            selected = len(items) - 1
-
-    # If current engine isn't in discovered list and isn't compressor, add it
-    if current != "compressor" and current not in names:
-        names.append(current)
-        items.append(f"{current} (not found)")
-        selected = len(items) - 1
-
-    choice = curses_radiolist(
-        title="Context Engine (select one)",
-        items=items,
-        selected=selected,
-    )
-
-    new_engine = names[choice]
-    if new_engine != current:
-        _save_context_engine(new_engine)
-        return True
-    return False
-
-
-# ---------------------------------------------------------------------------
-# Composite plugins UI
-# ---------------------------------------------------------------------------
-
-
 def cmd_toggle() -> None:
-    """Interactive composite UI — general plugins + provider plugin categories."""
+    """Interactive curses checklist to enable/disable installed plugins."""
     from rich.console import Console
 
     try:
@@ -750,13 +606,18 @@ def cmd_toggle() -> None:
     console = Console()
     plugins_dir = _plugins_dir()
 
-    # -- General plugins discovery --
     dirs = sorted(d for d in plugins_dir.iterdir() if d.is_dir())
+    if not dirs:
+        console.print("[dim]No plugins installed.[/dim]")
+        console.print("[dim]Install with:[/dim] hermes plugins install owner/repo")
+        return
+
     disabled = _get_disabled_set()
 
-    plugin_names = []
-    plugin_labels = []
-    plugin_selected = set()
+    # Build items list: "name — description" for display
+    names = []
+    labels = []
+    selected = set()
 
     for i, d in enumerate(dirs):
         manifest_file = d / "plugin.yaml"
@@ -772,335 +633,36 @@ def cmd_toggle() -> None:
             except Exception:
                 pass
 
-        plugin_names.append(name)
-        label = f"{name} \u2014 {description}" if description else name
-        plugin_labels.append(label)
+        names.append(name)
+        label = f"{name} — {description}" if description else name
+        labels.append(label)
 
         if name not in disabled and d.name not in disabled:
-            plugin_selected.add(i)
+            selected.add(i)
 
-    # -- Provider categories --
-    current_memory = _get_current_memory_provider() or "built-in"
-    current_context = _get_current_context_engine()
-    categories = [
-        ("Memory Provider", current_memory, _configure_memory_provider),
-        ("Context Engine", current_context, _configure_context_engine),
-    ]
+    from hermes_cli.curses_ui import curses_checklist
 
-    has_plugins = bool(plugin_names)
-    has_categories = bool(categories)
+    result = curses_checklist(
+        title="Plugins — toggle enabled/disabled",
+        items=labels,
+        selected=selected,
+    )
 
-    if not has_plugins and not has_categories:
-        console.print("[dim]No plugins installed and no provider categories available.[/dim]")
-        console.print("[dim]Install with:[/dim] hermes plugins install owner/repo")
-        return
-
-    # Non-TTY fallback
-    if not sys.stdin.isatty():
-        console.print("[dim]Interactive mode requires a terminal.[/dim]")
-        return
-
-    # Launch the composite curses UI
-    try:
-        import curses
-        _run_composite_ui(curses, plugin_names, plugin_labels, plugin_selected,
-                          disabled, categories, console)
-    except ImportError:
-        _run_composite_fallback(plugin_names, plugin_labels, plugin_selected,
-                                disabled, categories, console)
-
-
-def _run_composite_ui(curses, plugin_names, plugin_labels, plugin_selected,
-                      disabled, categories, console):
-    """Custom curses screen with checkboxes + category action rows."""
-    from hermes_cli.curses_ui import flush_stdin
-
-    chosen = set(plugin_selected)
-    n_plugins = len(plugin_names)
-    # Total rows: plugins + separator + categories
-    # separator is not navigable
-    n_categories = len(categories)
-    total_items = n_plugins + n_categories  # navigable items
-
-    result_holder = {"plugins_changed": False, "providers_changed": False}
-
-    def _draw(stdscr):
-        curses.curs_set(0)
-        if curses.has_colors():
-            curses.start_color()
-            curses.use_default_colors()
-            curses.init_pair(1, curses.COLOR_GREEN, -1)
-            curses.init_pair(2, curses.COLOR_YELLOW, -1)
-            curses.init_pair(3, curses.COLOR_CYAN, -1)
-            curses.init_pair(4, 8, -1)  # dim gray
-        cursor = 0
-        scroll_offset = 0
-
-        while True:
-            stdscr.clear()
-            max_y, max_x = stdscr.getmaxyx()
-
-            # Header
-            try:
-                hattr = curses.A_BOLD
-                if curses.has_colors():
-                    hattr |= curses.color_pair(2)
-                stdscr.addnstr(0, 0, "Plugins", max_x - 1, hattr)
-                stdscr.addnstr(
-                    1, 0,
-                    "  \u2191\u2193 navigate  SPACE toggle  ENTER configure/confirm  ESC done",
-                    max_x - 1, curses.A_DIM,
-                )
-            except curses.error:
-                pass
-
-            # Build display rows
-            # Row layout:
-            #   [plugins section header] (not navigable, skipped in scroll math)
-            #   plugin checkboxes (navigable, indices 0..n_plugins-1)
-            #   [separator] (not navigable)
-            #   [categories section header] (not navigable)
-            #   category action rows (navigable, indices n_plugins..total_items-1)
-
-            visible_rows = max_y - 4
-            if cursor < scroll_offset:
-                scroll_offset = cursor
-            elif cursor >= scroll_offset + visible_rows:
-                scroll_offset = cursor - visible_rows + 1
-
-            y = 3  # start drawing after header
-
-            # Determine which items are visible based on scroll
-            # We need to map logical cursor positions to screen rows
-            # accounting for non-navigable separator/headers
-
-            draw_row = 0  # tracks navigable item index
-
-            # --- General Plugins section ---
-            if n_plugins > 0:
-                # Section header
-                if y < max_y - 1:
-                    try:
-                        sattr = curses.A_BOLD
-                        if curses.has_colors():
-                            sattr |= curses.color_pair(2)
-                        stdscr.addnstr(y, 0, "  General Plugins", max_x - 1, sattr)
-                    except curses.error:
-                        pass
-                    y += 1
-
-                for i in range(n_plugins):
-                    if y >= max_y - 1:
-                        break
-                    check = "\u2713" if i in chosen else " "
-                    arrow = "\u2192" if i == cursor else " "
-                    line = f" {arrow} [{check}] {plugin_labels[i]}"
-                    attr = curses.A_NORMAL
-                    if i == cursor:
-                        attr = curses.A_BOLD
-                        if curses.has_colors():
-                            attr |= curses.color_pair(1)
-                    try:
-                        stdscr.addnstr(y, 0, line, max_x - 1, attr)
-                    except curses.error:
-                        pass
-                    y += 1
-
-            # --- Separator ---
-            if y < max_y - 1:
-                y += 1  # blank line
-
-            # --- Provider Plugins section ---
-            if n_categories > 0 and y < max_y - 1:
-                try:
-                    sattr = curses.A_BOLD
-                    if curses.has_colors():
-                        sattr |= curses.color_pair(2)
-                    stdscr.addnstr(y, 0, "  Provider Plugins", max_x - 1, sattr)
-                except curses.error:
-                    pass
-                y += 1
-
-                for ci, (cat_name, cat_current, _cat_fn) in enumerate(categories):
-                    if y >= max_y - 1:
-                        break
-                    cat_idx = n_plugins + ci
-                    arrow = "\u2192" if cat_idx == cursor else " "
-                    line = f" {arrow}   {cat_name:<24} \u25b8 {cat_current}"
-                    attr = curses.A_NORMAL
-                    if cat_idx == cursor:
-                        attr = curses.A_BOLD
-                        if curses.has_colors():
-                            attr |= curses.color_pair(3)
-                    try:
-                        stdscr.addnstr(y, 0, line, max_x - 1, attr)
-                    except curses.error:
-                        pass
-                    y += 1
-
-            stdscr.refresh()
-            key = stdscr.getch()
-
-            if key in (curses.KEY_UP, ord("k")):
-                if total_items > 0:
-                    cursor = (cursor - 1) % total_items
-            elif key in (curses.KEY_DOWN, ord("j")):
-                if total_items > 0:
-                    cursor = (cursor + 1) % total_items
-            elif key == ord(" "):
-                if cursor < n_plugins:
-                    # Toggle general plugin
-                    chosen.symmetric_difference_update({cursor})
-                else:
-                    # Provider category — launch sub-screen
-                    ci = cursor - n_plugins
-                    if 0 <= ci < n_categories:
-                        curses.endwin()
-                        _cat_name, _cat_cur, cat_fn = categories[ci]
-                        changed = cat_fn()
-                        if changed:
-                            result_holder["providers_changed"] = True
-                            # Refresh current values
-                            categories[ci] = (
-                                _cat_name,
-                                _get_current_memory_provider() or "built-in" if ci == 0
-                                else _get_current_context_engine(),
-                                cat_fn,
-                            )
-                        # Re-enter curses
-                        stdscr = curses.initscr()
-                        curses.noecho()
-                        curses.cbreak()
-                        stdscr.keypad(True)
-                        if curses.has_colors():
-                            curses.start_color()
-                            curses.use_default_colors()
-                            curses.init_pair(1, curses.COLOR_GREEN, -1)
-                            curses.init_pair(2, curses.COLOR_YELLOW, -1)
-                            curses.init_pair(3, curses.COLOR_CYAN, -1)
-                            curses.init_pair(4, 8, -1)
-                        curses.curs_set(0)
-            elif key in (curses.KEY_ENTER, 10, 13):
-                if cursor < n_plugins:
-                    # ENTER on a plugin checkbox — confirm and exit
-                    result_holder["plugins_changed"] = True
-                    return
-                else:
-                    # ENTER on a category — same as SPACE, launch sub-screen
-                    ci = cursor - n_plugins
-                    if 0 <= ci < n_categories:
-                        curses.endwin()
-                        _cat_name, _cat_cur, cat_fn = categories[ci]
-                        changed = cat_fn()
-                        if changed:
-                            result_holder["providers_changed"] = True
-                            categories[ci] = (
-                                _cat_name,
-                                _get_current_memory_provider() or "built-in" if ci == 0
-                                else _get_current_context_engine(),
-                                cat_fn,
-                            )
-                        stdscr = curses.initscr()
-                        curses.noecho()
-                        curses.cbreak()
-                        stdscr.keypad(True)
-                        if curses.has_colors():
-                            curses.start_color()
-                            curses.use_default_colors()
-                            curses.init_pair(1, curses.COLOR_GREEN, -1)
-                            curses.init_pair(2, curses.COLOR_YELLOW, -1)
-                            curses.init_pair(3, curses.COLOR_CYAN, -1)
-                            curses.init_pair(4, 8, -1)
-                        curses.curs_set(0)
-            elif key in (27, ord("q")):
-                # Save plugin changes on exit
-                result_holder["plugins_changed"] = True
-                return
-
-    curses.wrapper(_draw)
-    flush_stdin()
-
-    # Persist general plugin changes
+    # Compute new disabled set from deselected items
     new_disabled = set()
-    for i, name in enumerate(plugin_names):
-        if i not in chosen:
+    for i, name in enumerate(names):
+        if i not in result:
             new_disabled.add(name)
 
     if new_disabled != disabled:
         _save_disabled_set(new_disabled)
-        enabled_count = len(plugin_names) - len(new_disabled)
+        enabled_count = len(names) - len(new_disabled)
         console.print(
-            f"\n[green]\u2713[/green] General plugins: {enabled_count} enabled, "
-            f"{len(new_disabled)} disabled."
+            f"\n[green]✓[/green] {enabled_count} enabled, {len(new_disabled)} disabled. "
+            f"Takes effect on next session."
         )
-    elif n_plugins > 0:
-        console.print("\n[dim]General plugins unchanged.[/dim]")
-
-    if result_holder["providers_changed"]:
-        new_memory = _get_current_memory_provider() or "built-in"
-        new_context = _get_current_context_engine()
-        console.print(
-            f"[green]\u2713[/green] Memory provider: [bold]{new_memory}[/bold]  "
-            f"Context engine: [bold]{new_context}[/bold]"
-        )
-
-    if n_plugins > 0 or result_holder["providers_changed"]:
-        console.print("[dim]Changes take effect on next session.[/dim]")
-    console.print()
-
-
-def _run_composite_fallback(plugin_names, plugin_labels, plugin_selected,
-                            disabled, categories, console):
-    """Text-based fallback for the composite plugins UI."""
-    from hermes_cli.colors import Colors, color
-
-    print(color("\n  Plugins", Colors.YELLOW))
-
-    # General plugins
-    if plugin_names:
-        chosen = set(plugin_selected)
-        print(color("\n  General Plugins", Colors.YELLOW))
-        print(color("  Toggle by number, Enter to confirm.\n", Colors.DIM))
-
-        while True:
-            for i, label in enumerate(plugin_labels):
-                marker = color("[\u2713]", Colors.GREEN) if i in chosen else "[ ]"
-                print(f"  {marker} {i + 1:>2}. {label}")
-            print()
-            try:
-                val = input(color("  Toggle # (or Enter to confirm): ", Colors.DIM)).strip()
-                if not val:
-                    break
-                idx = int(val) - 1
-                if 0 <= idx < len(plugin_names):
-                    chosen.symmetric_difference_update({idx})
-            except (ValueError, KeyboardInterrupt, EOFError):
-                return
-            print()
-
-        new_disabled = set()
-        for i, name in enumerate(plugin_names):
-            if i not in chosen:
-                new_disabled.add(name)
-        if new_disabled != disabled:
-            _save_disabled_set(new_disabled)
-
-    # Provider categories
-    if categories:
-        print(color("\n  Provider Plugins", Colors.YELLOW))
-        for ci, (cat_name, cat_current, cat_fn) in enumerate(categories):
-            print(f"  {ci + 1}. {cat_name} [{cat_current}]")
-        print()
-        try:
-            val = input(color("  Configure # (or Enter to skip): ", Colors.DIM)).strip()
-            if val:
-                ci = int(val) - 1
-                if 0 <= ci < len(categories):
-                    categories[ci][2]()  # call the configure function
-        except (ValueError, KeyboardInterrupt, EOFError):
-            pass
-
-    print()
+    else:
+        console.print("\n[dim]No changes.[/dim]")
 
 
 def plugins_command(args) -> None:

hermes_cli/profiles.py

@@ -459,16 +459,6 @@ def create_profile(
                     dst.parent.mkdir(parents=True, exist_ok=True)
                     shutil.copy2(src, dst)
 
-    # Seed a default SOUL.md so the user has a file to customize immediately.
-    # Skipped when the profile already has one (from --clone / --clone-all).
-    soul_path = profile_dir / "SOUL.md"
-    if not soul_path.exists():
-        try:
-            from hermes_cli.default_soul import DEFAULT_SOUL_MD
-            soul_path.write_text(DEFAULT_SOUL_MD, encoding="utf-8")
-        except Exception:
-            pass  # best-effort — don't fail profile creation over this
-
     return profile_dir