fix(web): show all WhatsApp shared contacts

Claude API on Vertex AI (Cloud Code Assist / Antigravity) enforces strict
JSON Schema 2020-12 validation and rejects root-level anyOf without a
top-level type field.

TypeBox Type.Union compiles to { anyOf: [...] } which Anthropic's direct
API accepts but Vertex rejects with:
  tools.11.custom.input_schema: JSON schema is invalid

This follows the same pattern used in browser-tool.ts which has the same
fix with an explanatory comment.

Flatten the schema to Type.Object with an action enum, matching how
browser tool handles this constraint.

.github/workflows/ci.yml

@@ -169,6 +169,67 @@ jobs:
       - name: Run ${{ matrix.task }} (${{ matrix.runtime }})
         run: ${{ matrix.command }}
 
+  checks-macos:
+    if: github.event_name == 'pull_request'
+    runs-on: macos-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - task: test
+            command: pnpm test
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          submodules: false
+
+      - name: Checkout submodules (retry)
+        run: |
+          set -euo pipefail
+          git submodule sync --recursive
+          for attempt in 1 2 3 4 5; do
+            if git -c protocol.version=2 submodule update --init --force --depth=1 --recursive; then
+              exit 0
+            fi
+            echo "Submodule update failed (attempt $attempt/5). Retrying…"
+            sleep $((attempt * 10))
+          done
+          exit 1
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 24
+          check-latest: true
+
+      - name: Runtime versions
+        run: |
+          node -v
+          npm -v
+
+      - name: Capture node path
+        run: echo "NODE_BIN=$(dirname \"$(node -p \"process.execPath\")\")" >> "$GITHUB_ENV"
+
+      - name: Enable corepack and pin pnpm
+        run: |
+          corepack enable
+          corepack prepare pnpm@10.23.0 --activate
+          pnpm -v
+
+      - name: Install dependencies
+        env:
+          CI: true
+        run: |
+          export PATH="$NODE_BIN:$PATH"
+          which node
+          node -v
+          pnpm -v
+          pnpm install --ignore-scripts=false --config.engine-strict=false --config.enable-pre-post-scripts=true || pnpm install --ignore-scripts=false --config.engine-strict=false --config.enable-pre-post-scripts=true
+
+      - name: Run ${{ matrix.task }}
+        run: ${{ matrix.command }}
+
   macos-app:
     if: github.event_name == 'pull_request'
     runs-on: macos-latest

.swiftformat

@@ -48,4 +48,4 @@
 --allman false
 
 # Exclusions
---exclude .build,.swiftpm,DerivedData,node_modules,dist,coverage,xcuserdata,apps/macos/Sources/ClawdisProtocol,apps/macos/Sources/ClawdbotProtocol
+--exclude .build,.swiftpm,DerivedData,node_modules,dist,coverage,xcuserdata,Peekaboo,Swabble,apps/android,apps/ios,apps/shared,apps/macos/Sources/ClawdisProtocol,apps/macos/Sources/ClawdbotProtocol

.swiftlint.yml

@@ -17,6 +17,8 @@ excluded:
   - dist
   - coverage
   - "*.playground"
+  # Generated (protocol-gen-swift.ts)
+  - apps/macos/Sources/ClawdbotProtocol/GatewayModels.swift
 
 analyzer_rules:
   - unused_declaration

AGENTS.md

@@ -65,6 +65,7 @@
 ## Agent-Specific Notes
 - Vocabulary: "makeup" = "mac app".
 - When answering questions, respond with high-confidence answers only: verify in code; do not guess.
+- Never update the Carbon dependency.
 - Gateway currently runs only as the menubar app; there is no separate LaunchAgent/helper label installed. Restart via the Clawdbot Mac app or `scripts/restart-mac.sh`; to verify/kill use `launchctl print gui/$UID | grep clawdbot` rather than assuming a fixed label. **When debugging on macOS, start/stop the gateway via the app, not ad-hoc tmux sessions; kill any temporary tunnels before handoff.**
 - macOS logs: use `./scripts/clawlog.sh` (aka `vtlog`) to query unified logs for the Clawdbot subsystem; it supports follow/tail/category filters and expects passwordless sudo for `/usr/bin/log`.
 - If shared guardrails are available locally, review them; otherwise follow this repo's guidance.
@@ -87,7 +88,7 @@
 - **Multi-agent safety:** focus reports on your edits; avoid guard-rail disclaimers unless truly blocked; when multiple agents touch the same file, continue if safe; end with a brief “other files present” note only if relevant.
 - Bug investigations: read source code of relevant npm dependencies and all related local code before concluding; aim for high-confidence root cause.
 - Code style: add brief comments for tricky logic; keep files under ~500 LOC when feasible (split/refactor as needed).
-- When asked to open a “session” file, open the Pi session logs under `~/.clawdbot/sessions/*.jsonl` (newest unless a specific ID is given), not the default `sessions.json`. If logs are needed from another machine, SSH via Tailscale and read the same path there.
+- When asked to open a “session” file, open the Pi session logs under `~/.clawdbot/agents/main/sessions/*.jsonl` (newest unless a specific ID is given), not the default `sessions.json`. If logs are needed from another machine, SSH via Tailscale and read the same path there.
 - Menubar dimming + restart flow mirrors Trimmy: use `scripts/restart-mac.sh` (kills all Clawdbot variants, runs `swift build`, packages, relaunches). Icon dimming depends on MenuBarExtraAccess wiring in AppMain; keep `appearsDisabled` updates intact when touching the status item.
 - Do not rebuild the macOS app over SSH; rebuilds must be run directly on the Mac.
 - Never send streaming/partial replies to external messaging surfaces (WhatsApp, Telegram); only final replies should be delivered there. Streaming/tool events may still go to internal UIs/control channel.

CHANGELOG.md

@@ -2,21 +2,44 @@
 
 ## Unreleased
 
+- Models/Auth: add OpenCode Zen (multi-model proxy) onboarding. (#623) — thanks @magimetal
+- WhatsApp: refactor vCard parsing helper and improve empty contact card summaries. (#624) — thanks @steipete
+- WhatsApp: include phone numbers when multiple contacts are shared. (#625) — thanks @mahmoudashraf93
+- Agents: warn on small context windows (<32k) and block unusable ones (<16k). — thanks @steipete
+- Pairing: cap pending DM pairing requests at 3 per provider and avoid pairing replies for outbound DMs. — thanks @steipete
+- macOS: replace relay smoke test with version check in packaging script. (#615) — thanks @YuriNachos
+- macOS: avoid clearing Launch at Login during app initialization. (#607) — thanks @wes-davis
+- Onboarding: skip systemd checks/daemon installs when systemd user services are unavailable; add onboarding flags to skip flow steps and stabilize Docker E2E. (#573) — thanks @steipete
+- Onboarding: QuickStart provider picker uses single-select to avoid accidental Telegram token prompts when choosing WhatsApp. (#485) — thanks @frankstallone
 - macOS: add node bridge heartbeat pings to detect half-open sockets and reconnect cleanly. (#572) — thanks @ngutman
 - Node bridge: harden keepalive + heartbeat handling (TCP keepalive, better disconnects, and keepalive config tests). (#577) — thanks @steipete
 - Control UI: improve mobile responsiveness. (#558) — thanks @carlulsoe
+- Control UI: persist per-session verbose off and hide tool cards unless verbose is on. (#262) — thanks @steipete
+- Gateway: centralize verbose overrides and gate tool stream events at the server. (#262) — thanks @steipete
 - CLI: add `sandbox list` and `sandbox recreate` commands for managing Docker sandbox containers after image/config updates. (#563) — thanks @pasogott
+- Sandbox: allow `session_status` tool in sandboxed sessions by default. — thanks @steipete
+- CLI: add `clawdbot config --section <name>` to jump straight into a wizard section (repeatable).
 - Docs: add Hetzner Docker VPS guide. (#556) — thanks @Iamadig
 - Docs: link Hetzner guide from install + platforms docs. (#592) — thanks @steipete
 - Providers: add Microsoft Teams provider with polling, attachments, and CLI send support. (#404) — thanks @onutc
 - Slack: honor reply tags + replyToMode while keeping threaded replies in-thread. (#574) — thanks @bolismauro
+- Slack: configurable reply threading (`slack.replyToMode`) + proper mrkdwn formatting for outbound messages. (#464) — thanks @austinm911
 - Discord: avoid category parent overrides for channel allowlists and refactor thread context helpers. (#588) — thanks @steipete
 - Discord: fix forum thread starters and cache channel lookups for thread context. (#585) — thanks @thewilloftheshadow
+- Discord: log gateway disconnect/reconnect events at info and add verbose gateway metrics. (#595) — thanks @steipete
 - Commands: accept /models as an alias for /model.
 - Commands: add `/usage` as an alias for `/status`. (#492) — thanks @lc0rp
 - Models/Auth: add MiniMax Anthropic-compatible API onboarding (minimax-api). (#590) — thanks @mneves75
+- Models: centralize model override validation + hooks Gmail warnings in doctor. (#602) — thanks @steipete
+- Agents: avoid base-to-string error stringification in model fallback. (#604) — thanks @steipete
+- Agents: `sessions_spawn` inherits the requester's provider for child runs (avoid WhatsApp fallback). (#528) — thanks @rlmestre
+- Agents: sub-agent context now injects only AGENTS.md + TOOLS.md (omits identity/user/soul/heartbeat/bootstrap). — thanks @steipete
+- Gateway/CLI: harden agent provider routing + validation (Slack/MS Teams + aliases). (follow-up #528) — thanks @steipete
+- Agents: treat billing/insufficient-credits errors as failover-worthy so model fallbacks kick in. (#486) — thanks @steipete
+- Auth: default billing disable backoff to 5h (doubling, 24h cap) and surface disabled/cooldown profiles in `models list` + doctor. (#486) — thanks @steipete
 - Commands: harden slash command registry and list text-only commands in `/commands`.
 - Models/Auth: show per-agent auth candidates in `/model status`, and add `clawdbot models auth order {get,set,clear}` (per-agent auth rotation overrides). — thanks @steipete
+- Telegram: keep streamMode draft-only; avoid forcing block streaming. (#619) — thanks @rubyrunsstuff
 - Debugging: add raw model stream logging flags and document gateway watch mode.
 - Gateway: decode dns-sd escaped UTF-8 in discovery output and show scan progress immediately. — thanks @steipete
 - Agent: add claude-cli/opus-4.5 runner via Claude CLI with resume support (tools disabled).
@@ -25,31 +48,53 @@
 - Hooks: default hook agent delivery to true. (#533) — thanks @mcinteerj
 - Hooks: normalize hook agent providers (aliases + msteams support).
 - WhatsApp: route queued replies to the original sender instead of the bot's own number. (#534) — thanks @mcinteerj
+- WhatsApp: improve "no active web listener" errors (include account + relink hint). (#612) — thanks @YuriNachos
+- WhatsApp: add broadcast groups for multi-agent replies. (#547) — thanks @pasogott
+- WhatsApp: resolve @lid inbound senders via auth-dir mapping fallback + shared resolver. (#365)
+- WhatsApp: treat shared contact cards as inbound messages (prefer vCard FN). (#622) — thanks @mahmoudashraf93
+- iMessage: isolate group-ish threads by chat_id. (#535) — thanks @mdahmann
 - Models: add OAuth expiry checks in doctor, expanded `models status` auth output (missing auth + `--check` exit codes). (#538) — thanks @latitudeki5223
 - Deps: bump Pi to 0.40.0 and drop pi-ai patch (upstream 429 fix). (#543) — thanks @mcinteerj
 - Agent: skip empty error assistant messages when rebuilding session context to avoid tool-chain corruption. (#561) — thanks @mukhtharcm
 - Security: per-agent mention patterns and group elevated directives now require explicit mention to avoid cross-agent toggles.
 - Config: support inline env vars in config (`env.*` / `env.vars`) and document env precedence.
+- Config: write `clawdbot.json` atomically (temp file + replace) and keep a best-effort `.bak` backup.
 - Agent: enable adaptive context pruning by default for tool-result trimming.
+- Agent: drop empty error assistant messages when sanitizing session history. (#591) — thanks @steipete
+- Agent: inject eligible skills list into the system prompt so bundled skills load from their actual locations. (#551) — thanks @gabriel-trigo
 - Doctor: check config/state permissions and offer to tighten them. — thanks @steipete
 - Doctor/Daemon: audit supervisor configs, add --repair/--force flows, surface service config audits in daemon status, and document user vs system services. — thanks @steipete
 - Doctor: repair gateway service entrypoint when switching between npm and git installs; add Docker e2e coverage. — thanks @steipete
 - Daemon: align generated systemd unit with docs for network-online + restart delay. (#479) — thanks @azade-c
 - Daemon: add KillMode=process to systemd units to avoid podman restart hangs. (#541) — thanks @ogulcancelik
+- WhatsApp: make inbound media size cap configurable (default 50 MB). (#505) — thanks @koala73
 - Doctor: run legacy state migrations in non-interactive mode without prompts.
 - Cron: parse Telegram topic targets for isolated delivery. (#478) — thanks @nachoiacovino
+- Cron: enqueue main-session system events under the resolved main session key. (#510)
+- Mobile: centralize main session key normalization for iOS/Android runtime helpers. — thanks @steipete
+- Chat UI: stop pinning hardcoded `main` session in the recent list; prefer active session if missing. — thanks @steipete
 - Outbound: default Telegram account selection for config-only tokens; remove heartbeat-specific accountId handling. (follow-up #516) — thanks @YuriNachos
 - Cron: allow Telegram delivery targets with topic/thread IDs (e.g. `-100…:topic:123`). (#474) — thanks @mitschabaude-bot
 - Heartbeat: resolve Telegram account IDs from config-only tokens; cron tool accepts canonical `jobId` and legacy `id` for job actions. (#516) — thanks @YuriNachos
 - Discord: stop provider when gateway reconnects are exhausted and surface errors. (#514) — thanks @joshp123
 - Agents: strip empty assistant text blocks from session history to avoid Claude API 400s. (#210)
 - Agents: scrub unsupported JSON Schema keywords from tool schemas for Cloud Code Assist API compatibility. (#567) — thanks @erikpr1994
+- Agents: sanitize Cloud Code Assist tool call IDs and detect format/quota errors for failover. (#544) — thanks @jeffersonwarrior
+- Agents: simplify session tool schemas for Gemini compatibility. (#599) — thanks @mcinteerj
+- Agents: require `raw` for gateway `config.apply` tool calls while keeping schema 2020-12 compatible. (#566) — thanks @sircrumpet
+- Agents: add `session_status` agent tool for `/status`-equivalent status (incl. usage/cost) + per-session model overrides. — thanks @steipete
 - Auto-reply: preserve block reply ordering with timeout fallback for streaming. (#503) — thanks @joshp123
 - Auto-reply: block reply ordering fix (duplicate PR superseded by #503). (#483) — thanks @AbhisekBasu1
 - Auto-reply: avoid splitting outbound chunks inside parentheses. (#499) — thanks @philipp-spiess
 - Auto-reply: preserve spacing when stripping inline directives. (#539) — thanks @joshp123
 - Auto-reply: relax reply tag parsing to allow whitespace. (#560) — thanks @mcinteerj
+- Auto-reply: add per-provider block streaming toggles and coalesce streamed blocks to reduce line spam. (#536) — thanks @mcinteerj
+- Auto-reply: suppress `<think>` leakage in block streaming and emit `/reasoning` as a separate `Reasoning:` message. (#614) — thanks @zknicker
+- Auto-reply: default block streaming off for non-Telegram providers unless explicitly enabled, and avoid splitting on forced flushes below max.
+- Auto-reply: raise default coalesce minChars for Signal/Slack/Discord and clarify streaming vs draft streaming in docs.
+- Auto-reply: default block streaming coalesce idle to 1s to reduce tiny chunks. — thanks @steipete
 - Auto-reply: fix /status usage summary filtering for the active provider.
+- Auto-reply: deduplicate followup queue entries using message id/routing to avoid duplicate replies. (#600) — thanks @samratjha96
 - Status: show provider prefix in /status model display. (#506) — thanks @mcinteerj
 - Status: compact /status with session token usage + estimated cost, add `/cost` per-response usage lines (tokens-only for OAuth).
 - Status: show active auth profile and key snippet in /status.
@@ -63,15 +108,20 @@
 - Control UI: add Docs link, remove chat composer divider, and add New session button.
 - Control UI: link sessions list to chat view. (#471) — thanks @HazAT
 - Sessions: support session `label` in store/list/UI and allow `sessions_send` lookup by label. (#570) — thanks @azade-c
+- Sessions: clarify `sessions_send` delivery semantics, log announce failures, and enforce Discord request timeouts. (#507) — thanks @steipete
 - Control UI: show/patch per-session reasoning level and render extracted reasoning in chat.
 - Control UI: queue outgoing chat messages, add Enter-to-send, and show queued items. (#527) — thanks @YuriNachos
+- Control UI: refactor chat layout with tool sidebar, grouped messages, and nav improvements. (#475) — thanks @rahthakor
 - Control UI: drop explicit `ui:install` step; `ui:build` now auto-installs UI deps (docs + update flow).
 - Telegram: retry long-polling conflicts with backoff to avoid fatal exits.
 - Telegram: fix grammY fetch type mismatch when injecting `fetch`. (#512) — thanks @YuriNachos
+- Telegram: add inline keyboard buttons (capability-gated) and route callback query payloads as messages. (#491) — thanks @azade-c
 - WhatsApp: resolve @lid JIDs via Baileys mapping to unblock inbound messages. (#415)
 - Pairing: replies now include sender ids for Discord/Slack/Signal/iMessage/WhatsApp; pairing list labels them explicitly.
 - Messages: default inbound/outbound prefixes from the routed agent’s `identity.name` when set. (#578) — thanks @p6l-richard
 - Signal: accept UUID-only senders for pairing/allowlists/routing when sourceNumber is missing. (#523) — thanks @neist
+- Signal: ignore reaction-only messages so they don't surface as unknown media. (#616) — thanks @neist
+- Signal: add reaction notifications with allowlist support. — thanks @steipete
 - Agent system prompt: avoid automatic self-updates unless explicitly requested.
 - Onboarding: tighten QuickStart hint copy for configuring later.
 - Onboarding: set Gemini 3 Pro as the default model for Gemini API key auth. (#489) — thanks @jonasjancarik
@@ -97,6 +147,7 @@
 - Docs: expand parameter descriptions for agent/wake hooks. (#532) — thanks @mcinteerj
 - Docs: add community showcase entries from Discord. (#476) — thanks @gupsammy
 - TUI: refresh status bar after think/verbose/reasoning changes. (#519) — thanks @jdrhyne
+- TUI: stop overriding agent timeout so config defaults apply; warn on invalid `--timeout-ms`. (#549)
 - Status: show Verbose/Elevated only when enabled.
 - Status: filter usage summary to the active model provider.
 - Status: map model providers to usage sources so unrelated usage doesn’t appear.
@@ -125,6 +176,10 @@
 - Dev templates: ship C-3PO dev workspace defaults as docs templates and use them for dev bootstrap. — thanks @steipete
 - Config: fix Minimax hosted onboarding to write `agents.defaults` and allow `msteams` as a heartbeat target. — thanks @steipete
 - Discord: add channel/category management actions (create/edit/move/delete + category removal). (#487) - thanks @NicholasSpisak
+- Docs: split CLI install commands into separate code blocks. (#601) — thanks @martinpucik
+- WhatsApp: record outbound provider activity using the active account id. (#537) — thanks @Nachx639
+- Discord: add gateway HELLO timeout to detect zombie connections. (#608) — thanks @NicholasSpisak
+- Docker: cache dependency layer for faster rebuilds. (#605) — thanks @zknicker
 
 ## 2026.1.8
 

Dockerfile

@@ -8,9 +8,14 @@ RUN corepack enable
 
 WORKDIR /app
 
-COPY . .
+COPY package.json pnpm-lock.yaml pnpm-workspace.yaml .npmrc ./
+COPY ui/package.json ./ui/package.json
+COPY patches ./patches
+COPY scripts ./scripts
 
 RUN pnpm install --frozen-lockfile
+
+COPY . .
 RUN pnpm build
 RUN pnpm ui:install
 RUN pnpm ui:build

README.md

@@ -457,16 +457,17 @@ Special thanks to @andrewting19 for the Anthropic OAuth tool-name fix.
 Thanks to all clawtributors:
 
 <p align="left">
-  <a href="https://github.com/steipete"><img src="https://avatars.githubusercontent.com/u/58493?v=4&s=48" width="48" height="48" alt="steipete" title="steipete"/></a> <a href="https://github.com/joaohlisboa"><img src="https://avatars.githubusercontent.com/u/8200873?v=4&s=48" width="48" height="48" alt="joaohlisboa" title="joaohlisboa"/></a> <a href="https://github.com/mneves75"><img src="https://avatars.githubusercontent.com/u/2423436?v=4&s=48" width="48" height="48" alt="mneves75" title="mneves75"/></a> <a href="https://github.com/joshp123"><img src="https://avatars.githubusercontent.com/u/1497361?v=4&s=48" width="48" height="48" alt="joshp123" title="joshp123"/></a> <a href="https://github.com/mukhtharcm"><img src="https://avatars.githubusercontent.com/u/56378562?v=4&s=48" width="48" height="48" alt="mukhtharcm" title="mukhtharcm"/></a> <a href="https://github.com/maxsumrall"><img src="https://avatars.githubusercontent.com/u/628843?v=4&s=48" width="48" height="48" alt="maxsumrall" title="maxsumrall"/></a> <a href="https://github.com/xadenryan"><img src="https://avatars.githubusercontent.com/u/165437834?v=4&s=48" width="48" height="48" alt="xadenryan" title="xadenryan"/></a> <a href="https://github.com/hsrvc"><img src="https://avatars.githubusercontent.com/u/129702169?v=4&s=48" width="48" height="48" alt="hsrvc" title="hsrvc"/></a> <a href="https://github.com/jamesgroat"><img src="https://avatars.githubusercontent.com/u/2634024?v=4&s=48" width="48" height="48" alt="jamesgroat" title="jamesgroat"/></a> <a href="https://github.com/dantelex"><img src="https://avatars.githubusercontent.com/u/631543?v=4&s=48" width="48" height="48" alt="dantelex" title="dantelex"/></a>
-  <a href="https://github.com/daveonkels"><img src="https://avatars.githubusercontent.com/u/533642?v=4&s=48" width="48" height="48" alt="daveonkels" title="daveonkels"/></a> <a href="https://github.com/omniwired"><img src="https://avatars.githubusercontent.com/u/322761?v=4&s=48" width="48" height="48" alt="Eng. Juan Combetto" title="Eng. Juan Combetto"/></a> <a href="https://github.com/mbelinky"><img src="https://avatars.githubusercontent.com/u/132747814?v=4&s=48" width="48" height="48" alt="Mariano Belinky" title="Mariano Belinky"/></a> <a href="https://github.com/julianengel"><img src="https://avatars.githubusercontent.com/u/10634231?v=4&s=48" width="48" height="48" alt="julianengel" title="julianengel"/></a> <a href="https://github.com/claude"><img src="https://avatars.githubusercontent.com/u/81847?v=4&s=48" width="48" height="48" alt="claude" title="claude"/></a> <a href="https://github.com/sreekaransrinath"><img src="https://avatars.githubusercontent.com/u/50989977?v=4&s=48" width="48" height="48" alt="sreekaransrinath" title="sreekaransrinath"/></a> <a href="https://github.com/dbhurley"><img src="https://avatars.githubusercontent.com/u/5251425?v=4&s=48" width="48" height="48" alt="dbhurley" title="dbhurley"/></a> <a href="https://github.com/gupsammy"><img src="https://avatars.githubusercontent.com/u/20296019?v=4&s=48" width="48" height="48" alt="gupsammy" title="gupsammy"/></a> <a href="https://github.com/nachoiacovino"><img src="https://avatars.githubusercontent.com/u/50103937?v=4&s=48" width="48" height="48" alt="nachoiacovino" title="nachoiacovino"/></a> <a href="https://github.com/vsabavat"><img src="https://avatars.githubusercontent.com/u/50385532?v=4&s=48" width="48" height="48" alt="Vasanth Rao Naik Sabavat" title="Vasanth Rao Naik Sabavat"/></a>
-  <a href="https://github.com/jeffersonwarrior"><img src="https://avatars.githubusercontent.com/u/89030989?v=4&s=48" width="48" height="48" alt="jeffersonwarrior" title="jeffersonwarrior"/></a> <a href="https://github.com/scald"><img src="https://avatars.githubusercontent.com/u/1215913?v=4&s=48" width="48" height="48" alt="scald" title="scald"/></a> <a href="https://github.com/andranik-sahakyan"><img src="https://avatars.githubusercontent.com/u/8908029?v=4&s=48" width="48" height="48" alt="andranik-sahakyan" title="andranik-sahakyan"/></a> <a href="https://github.com/Nachx639"><img src="https://avatars.githubusercontent.com/u/71144023?v=4&s=48" width="48" height="48" alt="nachx639" title="nachx639"/></a> <a href="https://github.com/sircrumpet"><img src="https://avatars.githubusercontent.com/u/4436535?v=4&s=48" width="48" height="48" alt="sircrumpet" title="sircrumpet"/></a> <a href="https://github.com/rafaelreis-r"><img src="https://avatars.githubusercontent.com/u/57492577?v=4&s=48" width="48" height="48" alt="rafaelreis-r" title="rafaelreis-r"/></a> <a href="https://github.com/meaningfool"><img src="https://avatars.githubusercontent.com/u/2862331?v=4&s=48" width="48" height="48" alt="meaningfool" title="meaningfool"/></a> <a href="https://github.com/ratulsarna"><img src="https://avatars.githubusercontent.com/u/105903728?v=4&s=48" width="48" height="48" alt="ratulsarna" title="ratulsarna"/></a> <a href="https://github.com/lutr0"><img src="https://avatars.githubusercontent.com/u/76906369?v=4&s=48" width="48" height="48" alt="lutr0" title="lutr0"/></a> <a href="https://github.com/AbhisekBasu1"><img src="https://avatars.githubusercontent.com/u/40645221?v=4&s=48" width="48" height="48" alt="abhisekbasu1" title="abhisekbasu1"/></a>
-  <a href="https://github.com/emanuelst"><img src="https://avatars.githubusercontent.com/u/9994339?v=4&s=48" width="48" height="48" alt="emanuelst" title="emanuelst"/></a> <a href="https://github.com/osolmaz"><img src="https://avatars.githubusercontent.com/u/2453968?v=4&s=48" width="48" height="48" alt="osolmaz" title="osolmaz"/></a> <a href="https://github.com/kiranjd"><img src="https://avatars.githubusercontent.com/u/25822851?v=4&s=48" width="48" height="48" alt="kiranjd" title="kiranjd"/></a> <a href="https://github.com/thewilloftheshadow"><img src="https://avatars.githubusercontent.com/u/35580099?v=4&s=48" width="48" height="48" alt="thewilloftheshadow" title="thewilloftheshadow"/></a> <a href="https://github.com/CashWilliams"><img src="https://avatars.githubusercontent.com/u/613573?v=4&s=48" width="48" height="48" alt="CashWilliams" title="CashWilliams"/></a> <a href="https://github.com/ManuelHettich"><img src="https://avatars.githubusercontent.com/u/17690367?v=4&s=48" width="48" height="48" alt="manuelhettich" title="manuelhettich"/></a> <a href="https://github.com/minghinmatthewlam"><img src="https://avatars.githubusercontent.com/u/14224566?v=4&s=48" width="48" height="48" alt="minghinmatthewlam" title="minghinmatthewlam"/></a> <a href="https://github.com/buddyh"><img src="https://avatars.githubusercontent.com/u/31752869?v=4&s=48" width="48" height="48" alt="buddyh" title="buddyh"/></a> <a href="https://github.com/search?q=sheeek"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="sheeek" title="sheeek"/></a> <a href="https://github.com/timkrase"><img src="https://avatars.githubusercontent.com/u/38947626?v=4&s=48" width="48" height="48" alt="timkrase" title="timkrase"/></a>
-  <a href="https://github.com/mcinteerj"><img src="https://avatars.githubusercontent.com/u/3613653?v=4&s=48" width="48" height="48" alt="mcinteerj" title="mcinteerj"/></a> <a href="https://github.com/azade-c"><img src="https://avatars.githubusercontent.com/u/252790079?v=4&s=48" width="48" height="48" alt="azade-c" title="azade-c"/></a> <a href="https://github.com/imfing"><img src="https://avatars.githubusercontent.com/u/5097752?v=4&s=48" width="48" height="48" alt="imfing" title="imfing"/></a> <a href="https://github.com/petter-b"><img src="https://avatars.githubusercontent.com/u/62076402?v=4&s=48" width="48" height="48" alt="petter-b" title="petter-b"/></a> <a href="https://github.com/RandyVentures"><img src="https://avatars.githubusercontent.com/u/149904821?v=4&s=48" width="48" height="48" alt="RandyVentures" title="RandyVentures"/></a> <a href="https://github.com/search?q=Yurii%20Chukhlib"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Yurii Chukhlib" title="Yurii Chukhlib"/></a> <a href="https://github.com/jalehman"><img src="https://avatars.githubusercontent.com/u/550978?v=4&s=48" width="48" height="48" alt="jalehman" title="jalehman"/></a> <a href="https://github.com/obviyus"><img src="https://avatars.githubusercontent.com/u/22031114?v=4&s=48" width="48" height="48" alt="obviyus" title="obviyus"/></a> <a href="https://github.com/dan-dr"><img src="https://avatars.githubusercontent.com/u/6669808?v=4&s=48" width="48" height="48" alt="dan-dr" title="dan-dr"/></a> <a href="https://github.com/Iamadig"><img src="https://avatars.githubusercontent.com/u/102129234?v=4&s=48" width="48" height="48" alt="iamadig" title="iamadig"/></a>
-  <a href="https://github.com/manmal"><img src="https://avatars.githubusercontent.com/u/142797?v=4&s=48" width="48" height="48" alt="manmal" title="manmal"/></a> <a href="https://github.com/ogulcancelik"><img src="https://avatars.githubusercontent.com/u/7064011?v=4&s=48" width="48" height="48" alt="ogulcancelik" title="ogulcancelik"/></a> <a href="https://github.com/VACInc"><img src="https://avatars.githubusercontent.com/u/3279061?v=4&s=48" width="48" height="48" alt="VACInc" title="VACInc"/></a> <a href="https://github.com/zats"><img src="https://avatars.githubusercontent.com/u/2688806?v=4&s=48" width="48" height="48" alt="zats" title="zats"/></a> <a href="https://github.com/djangonavarro220"><img src="https://avatars.githubusercontent.com/u/251162586?v=4&s=48" width="48" height="48" alt="Django Navarro" title="Django Navarro"/></a> <a href="https://github.com/search?q=L36%20Server"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="L36 Server" title="L36 Server"/></a> <a href="https://github.com/neist"><img src="https://avatars.githubusercontent.com/u/1029724?v=4&s=48" width="48" height="48" alt="neist" title="neist"/></a> <a href="https://github.com/pcty-nextgen-service-account"><img src="https://avatars.githubusercontent.com/u/112553441?v=4&s=48" width="48" height="48" alt="pcty-nextgen-service-account" title="pcty-nextgen-service-account"/></a> <a href="https://github.com/Syhids"><img src="https://avatars.githubusercontent.com/u/671202?v=4&s=48" width="48" height="48" alt="Syhids" title="Syhids"/></a> <a href="https://github.com/erik-agens"><img src="https://avatars.githubusercontent.com/u/80908960?v=4&s=48" width="48" height="48" alt="erik-agens" title="erik-agens"/></a>
-  <a href="https://github.com/fcatuhe"><img src="https://avatars.githubusercontent.com/u/17382215?v=4&s=48" width="48" height="48" alt="fcatuhe" title="fcatuhe"/></a> <a href="https://github.com/jayhickey"><img src="https://avatars.githubusercontent.com/u/1676460?v=4&s=48" width="48" height="48" alt="jayhickey" title="jayhickey"/></a> <a href="https://github.com/jonasjancarik"><img src="https://avatars.githubusercontent.com/u/2459191?v=4&s=48" width="48" height="48" alt="jonasjancarik" title="jonasjancarik"/></a> <a href="https://github.com/jdrhyne"><img src="https://avatars.githubusercontent.com/u/7828464?v=4&s=48" width="48" height="48" alt="Jonathan D. Rhyne (DJ-D)" title="Jonathan D. Rhyne (DJ-D)"/></a> <a href="https://github.com/jverdi"><img src="https://avatars.githubusercontent.com/u/345050?v=4&s=48" width="48" height="48" alt="jverdi" title="jverdi"/></a> <a href="https://github.com/mitschabaude-bot"><img src="https://avatars.githubusercontent.com/u/247582884?v=4&s=48" width="48" height="48" alt="mitschabaude-bot" title="mitschabaude-bot"/></a> <a href="https://github.com/oswalpalash"><img src="https://avatars.githubusercontent.com/u/6431196?v=4&s=48" width="48" height="48" alt="oswalpalash" title="oswalpalash"/></a> <a href="https://github.com/philipp-spiess"><img src="https://avatars.githubusercontent.com/u/458591?v=4&s=48" width="48" height="48" alt="philipp-spiess" title="philipp-spiess"/></a> <a href="https://github.com/pkrmf"><img src="https://avatars.githubusercontent.com/u/1714267?v=4&s=48" width="48" height="48" alt="pkrmf" title="pkrmf"/></a> <a href="https://github.com/search?q=Sash%20Catanzarite"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Sash Catanzarite" title="Sash Catanzarite"/></a>
-  <a href="https://github.com/search?q=VAC"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="VAC" title="VAC"/></a> <a href="https://github.com/search?q=alejandro%20maza"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="alejandro maza" title="alejandro maza"/></a> <a href="https://github.com/antons"><img src="https://avatars.githubusercontent.com/u/129705?v=4&s=48" width="48" height="48" alt="antons" title="antons"/></a> <a href="https://github.com/Asleep123"><img src="https://avatars.githubusercontent.com/u/122379135?v=4&s=48" width="48" height="48" alt="Asleep123" title="Asleep123"/></a> <a href="https://github.com/cash-echo-bot"><img src="https://avatars.githubusercontent.com/u/252747386?v=4&s=48" width="48" height="48" alt="cash-echo-bot" title="cash-echo-bot"/></a> <a href="https://github.com/search?q=Clawd"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Clawd" title="Clawd"/></a> <a href="https://github.com/conhecendocontato"><img src="https://avatars.githubusercontent.com/u/82890727?v=4&s=48" width="48" height="48" alt="conhecendocontato" title="conhecendocontato"/></a> <a href="https://github.com/erikpr1994"><img src="https://avatars.githubusercontent.com/u/6299331?v=4&s=48" width="48" height="48" alt="erikpr1994" title="erikpr1994"/></a> <a href="https://github.com/gtsifrikas"><img src="https://avatars.githubusercontent.com/u/8904378?v=4&s=48" width="48" height="48" alt="gtsifrikas" title="gtsifrikas"/></a> <a href="https://github.com/HazAT"><img src="https://avatars.githubusercontent.com/u/363802?v=4&s=48" width="48" height="48" alt="HazAT" title="HazAT"/></a>
-  <a href="https://github.com/hrdwdmrbl"><img src="https://avatars.githubusercontent.com/u/554881?v=4&s=48" width="48" height="48" alt="hrdwdmrbl" title="hrdwdmrbl"/></a> <a href="https://github.com/hugobarauna"><img src="https://avatars.githubusercontent.com/u/2719?v=4&s=48" width="48" height="48" alt="hugobarauna" title="hugobarauna"/></a> <a href="https://github.com/search?q=Jarvis"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Jarvis" title="Jarvis"/></a> <a href="https://github.com/search?q=Keith%20the%20Silly%20Goose"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Keith the Silly Goose" title="Keith the Silly Goose"/></a> <a href="https://github.com/search?q=Kit"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Kit" title="Kit"/></a> <a href="https://github.com/kitze"><img src="https://avatars.githubusercontent.com/u/1160594?v=4&s=48" width="48" height="48" alt="kitze" title="kitze"/></a> <a href="https://github.com/kkarimi"><img src="https://avatars.githubusercontent.com/u/875218?v=4&s=48" width="48" height="48" alt="kkarimi" title="kkarimi"/></a> <a href="https://github.com/loukotal"><img src="https://avatars.githubusercontent.com/u/18210858?v=4&s=48" width="48" height="48" alt="loukotal" title="loukotal"/></a> <a href="https://github.com/mrdbstn"><img src="https://avatars.githubusercontent.com/u/58957632?v=4&s=48" width="48" height="48" alt="mrdbstn" title="mrdbstn"/></a> <a href="https://github.com/MSch"><img src="https://avatars.githubusercontent.com/u/7475?v=4&s=48" width="48" height="48" alt="MSch" title="MSch"/></a>
-  <a href="https://github.com/nexty5870"><img src="https://avatars.githubusercontent.com/u/3869659?v=4&s=48" width="48" height="48" alt="nexty5870" title="nexty5870"/></a> <a href="https://github.com/ngutman"><img src="https://avatars.githubusercontent.com/u/1540134?v=4&s=48" width="48" height="48" alt="ngutman" title="ngutman"/></a> <a href="https://github.com/onutc"><img src="https://avatars.githubusercontent.com/u/152018508?v=4&s=48" width="48" height="48" alt="onutc" title="onutc"/></a> <a href="https://github.com/prathamdby"><img src="https://avatars.githubusercontent.com/u/134331217?v=4&s=48" width="48" height="48" alt="prathamdby" title="prathamdby"/></a> <a href="https://github.com/reeltimeapps"><img src="https://avatars.githubusercontent.com/u/637338?v=4&s=48" width="48" height="48" alt="reeltimeapps" title="reeltimeapps"/></a> <a href="https://github.com/RLTCmpe"><img src="https://avatars.githubusercontent.com/u/10762242?v=4&s=48" width="48" height="48" alt="RLTCmpe" title="RLTCmpe"/></a> <a href="https://github.com/search?q=Rolf%20Fredheim"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Rolf Fredheim" title="Rolf Fredheim"/></a> <a href="https://github.com/snopoke"><img src="https://avatars.githubusercontent.com/u/249606?v=4&s=48" width="48" height="48" alt="snopoke" title="snopoke"/></a> <a href="https://github.com/wstock"><img src="https://avatars.githubusercontent.com/u/1394687?v=4&s=48" width="48" height="48" alt="wstock" title="wstock"/></a> <a href="https://github.com/YuriNachos"><img src="https://avatars.githubusercontent.com/u/19365375?v=4&s=48" width="48" height="48" alt="YuriNachos" title="YuriNachos"/></a>
-  <a href="https://github.com/search?q=Azade"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Azade" title="Azade"/></a> <a href="https://github.com/search?q=ddyo"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="ddyo" title="ddyo"/></a> <a href="https://github.com/search?q=Erik"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Erik" title="Erik"/></a> <a href="https://github.com/latitudeki5223"><img src="https://avatars.githubusercontent.com/u/119656367?v=4&s=48" width="48" height="48" alt="latitudeki5223" title="latitudeki5223"/></a> <a href="https://github.com/search?q=Manuel%20Maly"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Manuel Maly" title="Manuel Maly"/></a> <a href="https://github.com/search?q=Mourad%20Boustani"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Mourad Boustani" title="Mourad Boustani"/></a> <a href="https://github.com/pcty-nextgen-ios-builder"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="pcty-nextgen-ios-builder" title="pcty-nextgen-ios-builder"/></a> <a href="https://github.com/search?q=Quentin"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Quentin" title="Quentin"/></a> <a href="https://github.com/search?q=Randy%20Torres"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Randy Torres" title="Randy Torres"/></a> <a href="https://github.com/search?q=Tobias%20Bischoff"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Tobias Bischoff" title="Tobias Bischoff"/></a>
-  <a href="https://github.com/search?q=William%20Stock"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="William Stock" title="William Stock"/></a> <a href="https://github.com/andrewting19"><img src="https://avatars.githubusercontent.com/u/10536704?v=4&s=48" width="48" height="48" alt="andrewting19" title="andrewting19"/></a>
+  <a href="https://github.com/steipete"><img src="https://avatars.githubusercontent.com/u/58493?v=4&s=48" width="48" height="48" alt="steipete" title="steipete"/></a> <a href="https://github.com/joaohlisboa"><img src="https://avatars.githubusercontent.com/u/8200873?v=4&s=48" width="48" height="48" alt="joaohlisboa" title="joaohlisboa"/></a> <a href="https://github.com/mneves75"><img src="https://avatars.githubusercontent.com/u/2423436?v=4&s=48" width="48" height="48" alt="mneves75" title="mneves75"/></a> <a href="https://github.com/rahthakor"><img src="https://avatars.githubusercontent.com/u/8470553?v=4&s=48" width="48" height="48" alt="rahthakor" title="rahthakor"/></a> <a href="https://github.com/joshp123"><img src="https://avatars.githubusercontent.com/u/1497361?v=4&s=48" width="48" height="48" alt="joshp123" title="joshp123"/></a> <a href="https://github.com/mukhtharcm"><img src="https://avatars.githubusercontent.com/u/56378562?v=4&s=48" width="48" height="48" alt="mukhtharcm" title="mukhtharcm"/></a> <a href="https://github.com/maxsumrall"><img src="https://avatars.githubusercontent.com/u/628843?v=4&s=48" width="48" height="48" alt="maxsumrall" title="maxsumrall"/></a> <a href="https://github.com/xadenryan"><img src="https://avatars.githubusercontent.com/u/165437834?v=4&s=48" width="48" height="48" alt="xadenryan" title="xadenryan"/></a> <a href="https://github.com/tobiasbischoff"><img src="https://avatars.githubusercontent.com/u/711564?v=4&s=48" width="48" height="48" alt="Tobias Bischoff" title="Tobias Bischoff"/></a> <a href="https://github.com/hsrvc"><img src="https://avatars.githubusercontent.com/u/129702169?v=4&s=48" width="48" height="48" alt="hsrvc" title="hsrvc"/></a>
+  <a href="https://github.com/jamesgroat"><img src="https://avatars.githubusercontent.com/u/2634024?v=4&s=48" width="48" height="48" alt="jamesgroat" title="jamesgroat"/></a> <a href="https://github.com/NicholasSpisak"><img src="https://avatars.githubusercontent.com/u/129075147?v=4&s=48" width="48" height="48" alt="NicholasSpisak" title="NicholasSpisak"/></a> <a href="https://github.com/dantelex"><img src="https://avatars.githubusercontent.com/u/631543?v=4&s=48" width="48" height="48" alt="dantelex" title="dantelex"/></a> <a href="https://github.com/daveonkels"><img src="https://avatars.githubusercontent.com/u/533642?v=4&s=48" width="48" height="48" alt="daveonkels" title="daveonkels"/></a> <a href="https://github.com/omniwired"><img src="https://avatars.githubusercontent.com/u/322761?v=4&s=48" width="48" height="48" alt="Eng. Juan Combetto" title="Eng. Juan Combetto"/></a> <a href="https://github.com/mbelinky"><img src="https://avatars.githubusercontent.com/u/132747814?v=4&s=48" width="48" height="48" alt="Mariano Belinky" title="Mariano Belinky"/></a> <a href="https://github.com/julianengel"><img src="https://avatars.githubusercontent.com/u/10634231?v=4&s=48" width="48" height="48" alt="julianengel" title="julianengel"/></a> <a href="https://github.com/claude"><img src="https://avatars.githubusercontent.com/u/81847?v=4&s=48" width="48" height="48" alt="claude" title="claude"/></a> <a href="https://github.com/sreekaransrinath"><img src="https://avatars.githubusercontent.com/u/50989977?v=4&s=48" width="48" height="48" alt="sreekaransrinath" title="sreekaransrinath"/></a> <a href="https://github.com/dbhurley"><img src="https://avatars.githubusercontent.com/u/5251425?v=4&s=48" width="48" height="48" alt="dbhurley" title="dbhurley"/></a>
+  <a href="https://github.com/gupsammy"><img src="https://avatars.githubusercontent.com/u/20296019?v=4&s=48" width="48" height="48" alt="gupsammy" title="gupsammy"/></a> <a href="https://github.com/nachoiacovino"><img src="https://avatars.githubusercontent.com/u/50103937?v=4&s=48" width="48" height="48" alt="nachoiacovino" title="nachoiacovino"/></a> <a href="https://github.com/vsabavat"><img src="https://avatars.githubusercontent.com/u/50385532?v=4&s=48" width="48" height="48" alt="Vasanth Rao Naik Sabavat" title="Vasanth Rao Naik Sabavat"/></a> <a href="https://github.com/jeffersonwarrior"><img src="https://avatars.githubusercontent.com/u/89030989?v=4&s=48" width="48" height="48" alt="jeffersonwarrior" title="jeffersonwarrior"/></a> <a href="https://github.com/lc0rp"><img src="https://avatars.githubusercontent.com/u/2609441?v=4&s=48" width="48" height="48" alt="lc0rp" title="lc0rp"/></a> <a href="https://github.com/scald"><img src="https://avatars.githubusercontent.com/u/1215913?v=4&s=48" width="48" height="48" alt="scald" title="scald"/></a> <a href="https://github.com/andranik-sahakyan"><img src="https://avatars.githubusercontent.com/u/8908029?v=4&s=48" width="48" height="48" alt="andranik-sahakyan" title="andranik-sahakyan"/></a> <a href="https://github.com/Nachx639"><img src="https://avatars.githubusercontent.com/u/71144023?v=4&s=48" width="48" height="48" alt="nachx639" title="nachx639"/></a> <a href="https://github.com/sircrumpet"><img src="https://avatars.githubusercontent.com/u/4436535?v=4&s=48" width="48" height="48" alt="sircrumpet" title="sircrumpet"/></a> <a href="https://github.com/rafaelreis-r"><img src="https://avatars.githubusercontent.com/u/57492577?v=4&s=48" width="48" height="48" alt="rafaelreis-r" title="rafaelreis-r"/></a>
+  <a href="https://github.com/meaningfool"><img src="https://avatars.githubusercontent.com/u/2862331?v=4&s=48" width="48" height="48" alt="meaningfool" title="meaningfool"/></a> <a href="https://github.com/ratulsarna"><img src="https://avatars.githubusercontent.com/u/105903728?v=4&s=48" width="48" height="48" alt="ratulsarna" title="ratulsarna"/></a> <a href="https://github.com/lutr0"><img src="https://avatars.githubusercontent.com/u/76906369?v=4&s=48" width="48" height="48" alt="lutr0" title="lutr0"/></a> <a href="https://github.com/AbhisekBasu1"><img src="https://avatars.githubusercontent.com/u/40645221?v=4&s=48" width="48" height="48" alt="abhisekbasu1" title="abhisekbasu1"/></a> <a href="https://github.com/emanuelst"><img src="https://avatars.githubusercontent.com/u/9994339?v=4&s=48" width="48" height="48" alt="emanuelst" title="emanuelst"/></a> <a href="https://github.com/thewilloftheshadow"><img src="https://avatars.githubusercontent.com/u/35580099?v=4&s=48" width="48" height="48" alt="thewilloftheshadow" title="thewilloftheshadow"/></a> <a href="https://github.com/osolmaz"><img src="https://avatars.githubusercontent.com/u/2453968?v=4&s=48" width="48" height="48" alt="osolmaz" title="osolmaz"/></a> <a href="https://github.com/kiranjd"><img src="https://avatars.githubusercontent.com/u/25822851?v=4&s=48" width="48" height="48" alt="kiranjd" title="kiranjd"/></a> <a href="https://github.com/onutc"><img src="https://avatars.githubusercontent.com/u/152018508?v=4&s=48" width="48" height="48" alt="onutc" title="onutc"/></a> <a href="https://github.com/CashWilliams"><img src="https://avatars.githubusercontent.com/u/613573?v=4&s=48" width="48" height="48" alt="CashWilliams" title="CashWilliams"/></a>
+  <a href="https://github.com/search?q=sheeek"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="sheeek" title="sheeek"/></a> <a href="https://github.com/ManuelHettich"><img src="https://avatars.githubusercontent.com/u/17690367?v=4&s=48" width="48" height="48" alt="manuelhettich" title="manuelhettich"/></a> <a href="https://github.com/minghinmatthewlam"><img src="https://avatars.githubusercontent.com/u/14224566?v=4&s=48" width="48" height="48" alt="minghinmatthewlam" title="minghinmatthewlam"/></a> <a href="https://github.com/magimetal"><img src="https://avatars.githubusercontent.com/u/36491250?v=4&s=48" width="48" height="48" alt="magimetal" title="magimetal"/></a> <a href="https://github.com/buddyh"><img src="https://avatars.githubusercontent.com/u/31752869?v=4&s=48" width="48" height="48" alt="buddyh" title="buddyh"/></a> <a href="https://github.com/mcinteerj"><img src="https://avatars.githubusercontent.com/u/3613653?v=4&s=48" width="48" height="48" alt="mcinteerj" title="mcinteerj"/></a> <a href="https://github.com/timkrase"><img src="https://avatars.githubusercontent.com/u/38947626?v=4&s=48" width="48" height="48" alt="timkrase" title="timkrase"/></a> <a href="https://github.com/azade-c"><img src="https://avatars.githubusercontent.com/u/252790079?v=4&s=48" width="48" height="48" alt="azade-c" title="azade-c"/></a> <a href="https://github.com/apps/blacksmith-sh"><img src="https://avatars.githubusercontent.com/in/807020?v=4&s=48" width="48" height="48" alt="blacksmith-sh[bot]" title="blacksmith-sh[bot]"/></a> <a href="https://github.com/imfing"><img src="https://avatars.githubusercontent.com/u/5097752?v=4&s=48" width="48" height="48" alt="imfing" title="imfing"/></a>
+  <a href="https://github.com/petter-b"><img src="https://avatars.githubusercontent.com/u/62076402?v=4&s=48" width="48" height="48" alt="petter-b" title="petter-b"/></a> <a href="https://github.com/RandyVentures"><img src="https://avatars.githubusercontent.com/u/149904821?v=4&s=48" width="48" height="48" alt="RandyVentures" title="RandyVentures"/></a> <a href="https://github.com/search?q=Yurii%20Chukhlib"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Yurii Chukhlib" title="Yurii Chukhlib"/></a> <a href="https://github.com/jalehman"><img src="https://avatars.githubusercontent.com/u/550978?v=4&s=48" width="48" height="48" alt="jalehman" title="jalehman"/></a> <a href="https://github.com/obviyus"><img src="https://avatars.githubusercontent.com/u/22031114?v=4&s=48" width="48" height="48" alt="obviyus" title="obviyus"/></a> <a href="https://github.com/dan-dr"><img src="https://avatars.githubusercontent.com/u/6669808?v=4&s=48" width="48" height="48" alt="dan-dr" title="dan-dr"/></a> <a href="https://github.com/Iamadig"><img src="https://avatars.githubusercontent.com/u/102129234?v=4&s=48" width="48" height="48" alt="iamadig" title="iamadig"/></a> <a href="https://github.com/koala73"><img src="https://avatars.githubusercontent.com/u/996596?v=4&s=48" width="48" height="48" alt="koala73" title="koala73"/></a> <a href="https://github.com/manmal"><img src="https://avatars.githubusercontent.com/u/142797?v=4&s=48" width="48" height="48" alt="manmal" title="manmal"/></a> <a href="https://github.com/ogulcancelik"><img src="https://avatars.githubusercontent.com/u/7064011?v=4&s=48" width="48" height="48" alt="ogulcancelik" title="ogulcancelik"/></a>
+  <a href="https://github.com/VACInc"><img src="https://avatars.githubusercontent.com/u/3279061?v=4&s=48" width="48" height="48" alt="VACInc" title="VACInc"/></a> <a href="https://github.com/zats"><img src="https://avatars.githubusercontent.com/u/2688806?v=4&s=48" width="48" height="48" alt="zats" title="zats"/></a> <a href="https://github.com/djangonavarro220"><img src="https://avatars.githubusercontent.com/u/251162586?v=4&s=48" width="48" height="48" alt="Django Navarro" title="Django Navarro"/></a> <a href="https://github.com/search?q=L36%20Server"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="L36 Server" title="L36 Server"/></a> <a href="https://github.com/neist"><img src="https://avatars.githubusercontent.com/u/1029724?v=4&s=48" width="48" height="48" alt="neist" title="neist"/></a> <a href="https://github.com/pcty-nextgen-service-account"><img src="https://avatars.githubusercontent.com/u/112553441?v=4&s=48" width="48" height="48" alt="pcty-nextgen-service-account" title="pcty-nextgen-service-account"/></a> <a href="https://github.com/Syhids"><img src="https://avatars.githubusercontent.com/u/671202?v=4&s=48" width="48" height="48" alt="Syhids" title="Syhids"/></a> <a href="https://github.com/erik-agens"><img src="https://avatars.githubusercontent.com/u/80908960?v=4&s=48" width="48" height="48" alt="erik-agens" title="erik-agens"/></a> <a href="https://github.com/erikpr1994"><img src="https://avatars.githubusercontent.com/u/6299331?v=4&s=48" width="48" height="48" alt="erikpr1994" title="erikpr1994"/></a> <a href="https://github.com/fcatuhe"><img src="https://avatars.githubusercontent.com/u/17382215?v=4&s=48" width="48" height="48" alt="fcatuhe" title="fcatuhe"/></a>
+  <a href="https://github.com/jayhickey"><img src="https://avatars.githubusercontent.com/u/1676460?v=4&s=48" width="48" height="48" alt="jayhickey" title="jayhickey"/></a> <a href="https://github.com/jonasjancarik"><img src="https://avatars.githubusercontent.com/u/2459191?v=4&s=48" width="48" height="48" alt="jonasjancarik" title="jonasjancarik"/></a> <a href="https://github.com/jdrhyne"><img src="https://avatars.githubusercontent.com/u/7828464?v=4&s=48" width="48" height="48" alt="Jonathan D. Rhyne (DJ-D)" title="Jonathan D. Rhyne (DJ-D)"/></a> <a href="https://github.com/jverdi"><img src="https://avatars.githubusercontent.com/u/345050?v=4&s=48" width="48" height="48" alt="jverdi" title="jverdi"/></a> <a href="https://github.com/search?q=Keith%20the%20Silly%20Goose"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Keith the Silly Goose" title="Keith the Silly Goose"/></a> <a href="https://github.com/search?q=Kit"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Kit" title="Kit"/></a> <a href="https://github.com/mitschabaude-bot"><img src="https://avatars.githubusercontent.com/u/247582884?v=4&s=48" width="48" height="48" alt="mitschabaude-bot" title="mitschabaude-bot"/></a> <a href="https://github.com/ngutman"><img src="https://avatars.githubusercontent.com/u/1540134?v=4&s=48" width="48" height="48" alt="ngutman" title="ngutman"/></a> <a href="https://github.com/oswalpalash"><img src="https://avatars.githubusercontent.com/u/6431196?v=4&s=48" width="48" height="48" alt="oswalpalash" title="oswalpalash"/></a> <a href="https://github.com/p6l-richard"><img src="https://avatars.githubusercontent.com/u/18185649?v=4&s=48" width="48" height="48" alt="p6l-richard" title="p6l-richard"/></a>
+  <a href="https://github.com/philipp-spiess"><img src="https://avatars.githubusercontent.com/u/458591?v=4&s=48" width="48" height="48" alt="philipp-spiess" title="philipp-spiess"/></a> <a href="https://github.com/pkrmf"><img src="https://avatars.githubusercontent.com/u/1714267?v=4&s=48" width="48" height="48" alt="pkrmf" title="pkrmf"/></a> <a href="https://github.com/search?q=Sash%20Catanzarite"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Sash Catanzarite" title="Sash Catanzarite"/></a> <a href="https://github.com/search?q=VAC"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="VAC" title="VAC"/></a> <a href="https://github.com/search?q=alejandro%20maza"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="alejandro maza" title="alejandro maza"/></a> <a href="https://github.com/andrewting19"><img src="https://avatars.githubusercontent.com/u/10536704?v=4&s=48" width="48" height="48" alt="andrewting19" title="andrewting19"/></a> <a href="https://github.com/antons"><img src="https://avatars.githubusercontent.com/u/129705?v=4&s=48" width="48" height="48" alt="antons" title="antons"/></a> <a href="https://github.com/Asleep123"><img src="https://avatars.githubusercontent.com/u/122379135?v=4&s=48" width="48" height="48" alt="Asleep123" title="Asleep123"/></a> <a href="https://github.com/bjesuiter"><img src="https://avatars.githubusercontent.com/u/2365676?v=4&s=48" width="48" height="48" alt="bjesuiter" title="bjesuiter"/></a> <a href="https://github.com/bolismauro"><img src="https://avatars.githubusercontent.com/u/771999?v=4&s=48" width="48" height="48" alt="bolismauro" title="bolismauro"/></a>
+  <a href="https://github.com/cash-echo-bot"><img src="https://avatars.githubusercontent.com/u/252747386?v=4&s=48" width="48" height="48" alt="cash-echo-bot" title="cash-echo-bot"/></a> <a href="https://github.com/search?q=Clawd"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Clawd" title="Clawd"/></a> <a href="https://github.com/conhecendocontato"><img src="https://avatars.githubusercontent.com/u/82890727?v=4&s=48" width="48" height="48" alt="conhecendocontato" title="conhecendocontato"/></a> <a href="https://github.com/gtsifrikas"><img src="https://avatars.githubusercontent.com/u/8904378?v=4&s=48" width="48" height="48" alt="gtsifrikas" title="gtsifrikas"/></a> <a href="https://github.com/HazAT"><img src="https://avatars.githubusercontent.com/u/363802?v=4&s=48" width="48" height="48" alt="HazAT" title="HazAT"/></a> <a href="https://github.com/hrdwdmrbl"><img src="https://avatars.githubusercontent.com/u/554881?v=4&s=48" width="48" height="48" alt="hrdwdmrbl" title="hrdwdmrbl"/></a> <a href="https://github.com/hugobarauna"><img src="https://avatars.githubusercontent.com/u/2719?v=4&s=48" width="48" height="48" alt="hugobarauna" title="hugobarauna"/></a> <a href="https://github.com/search?q=Jarvis"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Jarvis" title="Jarvis"/></a> <a href="https://github.com/kitze"><img src="https://avatars.githubusercontent.com/u/1160594?v=4&s=48" width="48" height="48" alt="kitze" title="kitze"/></a> <a href="https://github.com/kkarimi"><img src="https://avatars.githubusercontent.com/u/875218?v=4&s=48" width="48" height="48" alt="kkarimi" title="kkarimi"/></a>
+  <a href="https://github.com/loukotal"><img src="https://avatars.githubusercontent.com/u/18210858?v=4&s=48" width="48" height="48" alt="loukotal" title="loukotal"/></a> <a href="https://github.com/martinpucik"><img src="https://avatars.githubusercontent.com/u/5503097?v=4&s=48" width="48" height="48" alt="martinpucik" title="martinpucik"/></a> <a href="https://github.com/search?q=Miles"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Miles" title="Miles"/></a> <a href="https://github.com/mrdbstn"><img src="https://avatars.githubusercontent.com/u/58957632?v=4&s=48" width="48" height="48" alt="mrdbstn" title="mrdbstn"/></a> <a href="https://github.com/MSch"><img src="https://avatars.githubusercontent.com/u/7475?v=4&s=48" width="48" height="48" alt="MSch" title="MSch"/></a> <a href="https://github.com/nexty5870"><img src="https://avatars.githubusercontent.com/u/3869659?v=4&s=48" width="48" height="48" alt="nexty5870" title="nexty5870"/></a> <a href="https://github.com/prathamdby"><img src="https://avatars.githubusercontent.com/u/134331217?v=4&s=48" width="48" height="48" alt="prathamdby" title="prathamdby"/></a> <a href="https://github.com/reeltimeapps"><img src="https://avatars.githubusercontent.com/u/637338?v=4&s=48" width="48" height="48" alt="reeltimeapps" title="reeltimeapps"/></a> <a href="https://github.com/RLTCmpe"><img src="https://avatars.githubusercontent.com/u/10762242?v=4&s=48" width="48" height="48" alt="RLTCmpe" title="RLTCmpe"/></a> <a href="https://github.com/search?q=Rolf%20Fredheim"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Rolf Fredheim" title="Rolf Fredheim"/></a>
+  <a href="https://github.com/snopoke"><img src="https://avatars.githubusercontent.com/u/249606?v=4&s=48" width="48" height="48" alt="snopoke" title="snopoke"/></a> <a href="https://github.com/wstock"><img src="https://avatars.githubusercontent.com/u/1394687?v=4&s=48" width="48" height="48" alt="wstock" title="wstock"/></a> <a href="https://github.com/YuriNachos"><img src="https://avatars.githubusercontent.com/u/19365375?v=4&s=48" width="48" height="48" alt="YuriNachos" title="YuriNachos"/></a> <a href="https://github.com/search?q=Azade"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Azade" title="Azade"/></a> <a href="https://github.com/search?q=ddyo"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="ddyo" title="ddyo"/></a> <a href="https://github.com/search?q=Erik"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Erik" title="Erik"/></a> <a href="https://github.com/latitudeki5223"><img src="https://avatars.githubusercontent.com/u/119656367?v=4&s=48" width="48" height="48" alt="latitudeki5223" title="latitudeki5223"/></a> <a href="https://github.com/search?q=Manuel%20Maly"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Manuel Maly" title="Manuel Maly"/></a> <a href="https://github.com/search?q=Mourad%20Boustani"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Mourad Boustani" title="Mourad Boustani"/></a> <a href="https://github.com/pcty-nextgen-ios-builder"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="pcty-nextgen-ios-builder" title="pcty-nextgen-ios-builder"/></a>
+  <a href="https://github.com/search?q=Quentin"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Quentin" title="Quentin"/></a> <a href="https://github.com/search?q=Randy%20Torres"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="Randy Torres" title="Randy Torres"/></a> <a href="https://github.com/search?q=William%20Stock"><img src="assets/avatar-placeholder.svg" width="48" height="48" alt="William Stock" title="William Stock"/></a> <a href="https://github.com/zknicker"><img src="https://avatars.githubusercontent.com/u/1164085?v=4&s=48" width="48" height="48" alt="zknicker" title="zknicker"/></a>
 </p>

apps/android/app/src/main/java/com/clawdbot/android/NodeRuntime.kt

@@ -700,8 +700,8 @@ class NodeRuntime(context: Context) {
       val ui = config?.get("ui").asObjectOrNull()
       val raw = ui?.get("seamColor").asStringOrNull()?.trim()
       val sessionCfg = config?.get("session").asObjectOrNull()
-      val rawMainKey = sessionCfg?.get("mainKey").asStringOrNull()?.trim()
-      _mainSessionKey.value = rawMainKey?.takeIf { it.isNotEmpty() } ?: "main"
+      val mainKey = normalizeMainKey(sessionCfg?.get("mainKey").asStringOrNull())
+      _mainSessionKey.value = mainKey
 
       val parsed = parseHexColorArgb(raw)
       _seamColorArgb.value = parsed ?: DEFAULT_SEAM_COLOR_ARGB

apps/android/app/src/main/java/com/clawdbot/android/SessionKey.kt

@@ -0,0 +1,6 @@
+package com.clawdbot.android
+
+internal fun normalizeMainKey(raw: String?): String {
+  val trimmed = raw?.trim()
+  return if (!trimmed.isNullOrEmpty()) trimmed else "main"
+}

apps/android/app/src/main/java/com/clawdbot/android/voice/TalkModeManager.kt

@@ -21,6 +21,7 @@ import android.speech.tts.UtteranceProgressListener
 import android.util.Log
 import androidx.core.content.ContextCompat
 import com.clawdbot.android.bridge.BridgeSession
+import com.clawdbot.android.normalizeMainKey
 import java.net.HttpURLConnection
 import java.net.URL
 import java.util.UUID
@@ -814,7 +815,7 @@ class TalkModeManager(
       val config = root?.get("config").asObjectOrNull()
       val talk = config?.get("talk").asObjectOrNull()
       val sessionCfg = config?.get("session").asObjectOrNull()
-      val mainKey = sessionCfg?.get("mainKey").asStringOrNull()?.trim()?.takeIf { it.isNotEmpty() } ?: "main"
+      val mainKey = normalizeMainKey(sessionCfg?.get("mainKey").asStringOrNull())
       val voice = talk?.get("voiceId")?.asStringOrNull()?.trim()?.takeIf { it.isNotEmpty() }
       val aliases =
         talk?.get("voiceAliases").asObjectOrNull()?.entries?.mapNotNull { (key, value) ->

apps/ios/Sources/Model/NodeAppModel.swift

@@ -330,8 +330,7 @@ final class NodeAppModel {
             let ui = config["ui"] as? [String: Any]
             let raw = (ui?["seamColor"] as? String)?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
             let session = config["session"] as? [String: Any]
-            let rawMainKey = (session?["mainKey"] as? String)?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
-            let mainKey = rawMainKey.isEmpty ? "main" : rawMainKey
+            let mainKey = SessionKey.normalizeMainKey(session?["mainKey"] as? String)
             await MainActor.run {
                 self.seamColorHex = raw.isEmpty ? nil : raw
                 self.mainSessionKey = mainKey

apps/ios/Sources/SessionKey.swift

@@ -0,0 +1,8 @@
+import Foundation
+
+enum SessionKey {
+    static func normalizeMainKey(_ raw: String?) -> String {
+        let trimmed = (raw ?? "").trimmingCharacters(in: .whitespacesAndNewlines)
+        return trimmed.isEmpty ? "main" : trimmed
+    }
+}

apps/ios/Sources/Voice/TalkModeManager.swift

@@ -651,8 +651,7 @@ final class TalkModeManager: NSObject {
             guard let config = json["config"] as? [String: Any] else { return }
             let talk = config["talk"] as? [String: Any]
             let session = config["session"] as? [String: Any]
-            let rawMainKey = (session?["mainKey"] as? String)?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
-            self.mainSessionKey = rawMainKey.isEmpty ? "main" : rawMainKey
+            self.mainSessionKey = SessionKey.normalizeMainKey(session?["mainKey"] as? String)
             self.defaultVoiceId = (talk?["voiceId"] as? String)?.trimmingCharacters(in: .whitespacesAndNewlines)
             if let aliases = talk?["voiceAliases"] as? [String: Any] {
                 var resolved: [String: String] = [:]

apps/macos/Sources/Clawdbot/AppState.swift

@@ -29,7 +29,10 @@ final class AppState {
     }
 
     var launchAtLogin: Bool {
-        didSet { self.ifNotPreview { Task { AppStateStore.updateLaunchAtLogin(enabled: self.launchAtLogin) } } }
+        didSet {
+            guard !self.isInitializing else { return }
+            self.ifNotPreview { Task { AppStateStore.updateLaunchAtLogin(enabled: self.launchAtLogin) } }
+        }
     }
 
     var onboardingSeen: Bool {

apps/macos/Sources/Clawdbot/NodeMode/MacNodeBridgeSession.swift

@@ -331,8 +331,11 @@ actor MacNodeBridgeSession {
                 let now = self.clock.now
                 if now > last.advanced(by: timeout) {
                     let age = last.duration(to: now)
-                    self.logger.warning(
-                        "Node bridge heartbeat timed out; disconnecting (age: \(String(describing: age), privacy: .public)).")
+                    let ageDescription = String(describing: age)
+                    let message =
+                        "Node bridge heartbeat timed out; disconnecting " +
+                        "(age: \(ageDescription, privacy: .public))."
+                    self.logger.warning(message)
                     await self.disconnect()
                     return
                 }
@@ -342,8 +345,11 @@ actor MacNodeBridgeSession {
             do {
                 try await self.send(BridgePing(type: "ping", id: id))
             } catch {
-                self.logger.warning(
-                    "Node bridge ping send failed; disconnecting (error: \(String(describing: error), privacy: .public)).")
+                let errorDescription = String(describing: error)
+                let message =
+                    "Node bridge ping send failed; disconnecting " +
+                    "(error: \(errorDescription, privacy: .public))."
+                self.logger.warning(message)
                 await self.disconnect()
                 return
             }
@@ -358,8 +364,11 @@ actor MacNodeBridgeSession {
     private func handleConnectionState(_ state: NWConnection.State) async {
         switch state {
         case let .failed(error):
-            self.logger.warning(
-                "Node bridge connection failed; disconnecting (error: \(String(describing: error), privacy: .public)).")
+            let errorDescription = String(describing: error)
+            let message =
+                "Node bridge connection failed; disconnecting " +
+                "(error: \(errorDescription, privacy: .public))."
+            self.logger.warning(message)
             await self.disconnect()
         case .cancelled:
             self.logger.warning("Node bridge connection cancelled; disconnecting.")

apps/macos/Tests/ClawdbotIPCTests/MacNodeBridgeSessionTests.swift

@@ -16,4 +16,3 @@ struct MacNodeBridgeSessionTests {
         }
     }
 }
-

apps/shared/ClawdbotKit/Sources/ClawdbotChatUI/ChatViewModel.swift

@@ -112,24 +112,19 @@ public final class ClawdbotChatViewModel {
             recent.append(entry)
         }
 
-        let mainKey = "main"
         var result: [ClawdbotChatSessionEntry] = []
         var included = Set<String>()
-        if let main = sorted.first(where: { $0.key == mainKey }) {
-            result.append(main)
-            included.insert(mainKey)
-        } else if self.sessionKey == mainKey {
-            result.append(self.placeholderSession(key: mainKey))
-            included.insert(mainKey)
-        }
-
         for entry in recent where !included.contains(entry.key) {
             result.append(entry)
             included.insert(entry.key)
         }
 
         if !included.contains(self.sessionKey) {
-            result.append(self.placeholderSession(key: self.sessionKey))
+            if let current = sorted.first(where: { $0.key == self.sessionKey }) {
+                result.append(current)
+            } else {
+                result.append(self.placeholderSession(key: self.sessionKey))
+            }
         }
 
         return result

docker-setup.sh

@@ -98,7 +98,7 @@ echo "  - Gateway token: $CLAWDBOT_GATEWAY_TOKEN"
 echo "  - Tailscale exposure: Off"
 echo "  - Install Gateway daemon: No"
 echo ""
-docker compose -f "$COMPOSE_FILE" run --rm clawdbot-cli onboard
+docker compose -f "$COMPOSE_FILE" run --rm clawdbot-cli onboard --no-install-daemon
 
 echo ""
 echo "==> Provider setup (optional)"

docs/automation/gmail-pubsub.md

@@ -65,6 +65,25 @@ uses the last delivery route (falls back to WhatsApp).
 To force a cheaper model for Gmail runs, set `model` in the mapping
 (`provider/model` or alias). If you enforce `agents.defaults.models`, include it there.
 
+To set a default model and thinking level specifically for Gmail hooks, add
+`hooks.gmail.model` / `hooks.gmail.thinking` in your config:
+
+```json5
+{
+  hooks: {
+    gmail: {
+      model: "openrouter/meta-llama/llama-3.3-70b-instruct:free",
+      thinking: "off"
+    }
+  }
+}
+```
+
+Notes:
+- Per-hook `model`/`thinking` in the mapping still overrides these defaults.
+- Fallback order: `hooks.gmail.model` → `agents.defaults.model.fallbacks` → primary (auth/rate-limit/timeouts).
+- If `agents.defaults.models` is set, the Gmail model must be in the allowlist.
+
 To customize payload handling further, add `hooks.mappings` or a JS/TS transform module
 under `hooks.transformsDir` (see [`docs/webhook.md`](https://docs.clawd.bot/automation/webhook)).
 

docs/broadcast-groups.md

@@ -0,0 +1,395 @@
+# Broadcast Groups
+
+**Status:** Experimental  
+**Version:** Added in 2026.1.9
+
+## Overview
+
+Broadcast Groups enable multiple agents to process and respond to the same message simultaneously. This allows you to create specialized agent teams that work together in a single WhatsApp group, DM, or channel - all using one phone number.
+
+Broadcast groups are evaluated after provider allowlists and group activation rules. In WhatsApp groups, this means broadcasts happen when Clawdbot would normally reply (for example: on mention, depending on your group settings).
+
+## Use Cases
+
+### 1. Specialized Agent Teams
+Deploy multiple agents with atomic, focused responsibilities:
+```
+Group: "Development Team"
+Agents:
+  - CodeReviewer (reviews code snippets)
+  - DocumentationBot (generates docs)
+  - SecurityAuditor (checks for vulnerabilities)
+  - TestGenerator (suggests test cases)
+```
+
+Each agent processes the same message and provides its specialized perspective.
+
+### 2. Multi-Language Support
+```
+Group: "International Support"
+Agents:
+  - Agent_EN (responds in English)
+  - Agent_DE (responds in German)
+  - Agent_ES (responds in Spanish)
+```
+
+### 3. Quality Assurance Workflows
+```
+Group: "Customer Support"
+Agents:
+  - SupportAgent (provides answer)
+  - QAAgent (reviews quality, only responds if issues found)
+```
+
+### 4. Task Automation
+```
+Group: "Project Management"
+Agents:
+  - TaskTracker (updates task database)
+  - TimeLogger (logs time spent)
+  - ReportGenerator (creates summaries)
+```
+
+## Configuration
+
+### Basic Setup
+
+Add a top-level `broadcast` section (next to `bindings`):
+
+```json
+{
+  "broadcast": {
+    "120363403215116621@g.us": ["alfred", "baerbel", "assistant3"]
+  }
+}
+```
+
+**Result:** When Clawdbot would reply in this chat, it will run all three agents.
+
+### Processing Strategy
+
+Control how agents process messages:
+
+#### Parallel (Default)
+All agents process simultaneously:
+```json
+{
+  "broadcast": {
+    "strategy": "parallel",
+    "120363403215116621@g.us": ["alfred", "baerbel"]
+  }
+}
+```
+
+#### Sequential
+Agents process in order (one waits for previous to finish):
+```json
+{
+  "broadcast": {
+    "strategy": "sequential",
+    "120363403215116621@g.us": ["alfred", "baerbel"]
+  }
+}
+```
+
+### Complete Example
+
+```json
+{
+  "agents": {
+    "list": [
+      {
+        "id": "code-reviewer",
+        "name": "Code Reviewer",
+        "workspace": "/path/to/code-reviewer",
+        "sandbox": { "mode": "all" }
+      },
+      {
+        "id": "security-auditor",
+        "name": "Security Auditor",
+        "workspace": "/path/to/security-auditor",
+        "sandbox": { "mode": "all" }
+      },
+      {
+        "id": "docs-generator",
+        "name": "Documentation Generator",
+        "workspace": "/path/to/docs-generator",
+        "sandbox": { "mode": "all" }
+      }
+    ]
+  },
+  "broadcast": {
+    "strategy": "parallel",
+    "120363403215116621@g.us": ["code-reviewer", "security-auditor", "docs-generator"],
+    "120363424282127706@g.us": ["support-en", "support-de"],
+    "+15555550123": ["assistant", "logger"]
+  }
+}
+```
+
+## How It Works
+
+### Message Flow
+
+1. **Incoming message** arrives in a WhatsApp group
+2. **Broadcast check**: System checks if peer ID is in `broadcast`
+3. **If in broadcast list**:
+   - All listed agents process the message
+   - Each agent has its own session key and isolated context
+   - Agents process in parallel (default) or sequentially
+4. **If not in broadcast list**:
+   - Normal routing applies (first matching binding)
+
+Note: broadcast groups do not bypass provider allowlists or group activation rules (mentions/commands/etc). They only change *which agents run* when a message is eligible for processing.
+
+### Session Isolation
+
+Each agent in a broadcast group maintains completely separate:
+
+- **Session keys** (`agent:alfred:whatsapp:group:120363...` vs `agent:baerbel:whatsapp:group:120363...`)
+- **Conversation history** (agent doesn't see other agents' messages)
+- **Workspace** (separate sandboxes if configured)
+- **Tool access** (different allow/deny lists)
+- **Memory/context** (separate IDENTITY.md, SOUL.md, etc.)
+- **Group context buffer** (recent group messages used for context) is shared per peer, so all broadcast agents see the same context when triggered
+
+This allows each agent to have:
+- Different personalities
+- Different tool access (e.g., read-only vs. read-write)
+- Different models (e.g., opus vs. sonnet)
+- Different skills installed
+
+### Example: Isolated Sessions
+
+In group `120363403215116621@g.us` with agents `["alfred", "baerbel"]`:
+
+**Alfred's context:**
+```
+Session: agent:alfred:whatsapp:group:120363403215116621@g.us
+History: [user message, alfred's previous responses]
+Workspace: /Users/pascal/clawd-alfred/
+Tools: read, write, bash
+```
+
+**Bärbel's context:**
+```
+Session: agent:baerbel:whatsapp:group:120363403215116621@g.us  
+History: [user message, baerbel's previous responses]
+Workspace: /Users/pascal/clawd-baerbel/
+Tools: read only
+```
+
+## Best Practices
+
+### 1. Keep Agents Focused
+
+Design each agent with a single, clear responsibility:
+
+```json
+{
+  "broadcast": {
+    "DEV_GROUP": ["formatter", "linter", "tester"]
+  }
+}
+```
+
+✅ **Good:** Each agent has one job  
+❌ **Bad:** One generic "dev-helper" agent
+
+### 2. Use Descriptive Names
+
+Make it clear what each agent does:
+
+```json
+{
+  "agents": {
+    "security-scanner": { "name": "Security Scanner" },
+    "code-formatter": { "name": "Code Formatter" },
+    "test-generator": { "name": "Test Generator" }
+  }
+}
+```
+
+### 3. Configure Different Tool Access
+
+Give agents only the tools they need:
+
+```json
+{
+  "agents": {
+    "reviewer": {
+      "tools": { "allow": ["read", "bash"] }  // Read-only
+    },
+    "fixer": {
+      "tools": { "allow": ["read", "write", "edit", "bash"] }  // Read-write
+    }
+  }
+}
+```
+
+### 4. Monitor Performance
+
+With many agents, consider:
+- Using `"strategy": "parallel"` (default) for speed
+- Limiting broadcast groups to 5-10 agents
+- Using faster models for simpler agents
+
+### 5. Handle Failures Gracefully
+
+Agents fail independently. One agent's error doesn't block others:
+
+```
+Message → [Agent A ✓, Agent B ✗ error, Agent C ✓]
+Result: Agent A and C respond, Agent B logs error
+```
+
+## Compatibility
+
+### Providers
+
+Broadcast groups currently work with:
+- ✅ WhatsApp (implemented)
+- 🚧 Telegram (planned)
+- 🚧 Discord (planned)
+- 🚧 Slack (planned)
+
+### Routing
+
+Broadcast groups work alongside existing routing:
+
+```json
+{
+  "bindings": [
+    { "match": { "provider": "whatsapp", "peer": { "kind": "group", "id": "GROUP_A" } }, "agentId": "alfred" }
+  ],
+  "broadcast": {
+    "GROUP_B": ["agent1", "agent2"]
+  }
+}
+```
+
+- `GROUP_A`: Only alfred responds (normal routing)
+- `GROUP_B`: agent1 AND agent2 respond (broadcast)
+
+**Precedence:** `broadcast` takes priority over `bindings`.
+
+## Troubleshooting
+
+### Agents Not Responding
+
+**Check:**
+1. Agent IDs exist in `agents.list`
+2. Peer ID format is correct (e.g., `120363403215116621@g.us`)
+3. Agents are not in deny lists
+
+**Debug:**
+```bash
+tail -f ~/.clawdbot/logs/gateway.log | grep broadcast
+```
+
+### Only One Agent Responding
+
+**Cause:** Peer ID might be in `bindings` but not `broadcast`.
+
+**Fix:** Add to broadcast config or remove from bindings.
+
+### Performance Issues
+
+**If slow with many agents:**
+- Reduce number of agents per group
+- Use lighter models (sonnet instead of opus)
+- Check sandbox startup time
+
+## Examples
+
+### Example 1: Code Review Team
+
+```json
+{
+  "broadcast": {
+    "strategy": "parallel",
+    "120363403215116621@g.us": [
+      "code-formatter",
+      "security-scanner",
+      "test-coverage",
+      "docs-checker"
+    ]
+  },
+  "agents": {
+    "list": [
+      { "id": "code-formatter", "workspace": "~/agents/formatter", "tools": { "allow": ["read", "write"] } },
+      { "id": "security-scanner", "workspace": "~/agents/security", "tools": { "allow": ["read", "bash"] } },
+      { "id": "test-coverage", "workspace": "~/agents/testing", "tools": { "allow": ["read", "bash"] } },
+      { "id": "docs-checker", "workspace": "~/agents/docs", "tools": { "allow": ["read"] } }
+    ]
+  }
+}
+```
+
+**User sends:** Code snippet  
+**Responses:**
+- code-formatter: "Fixed indentation and added type hints"
+- security-scanner: "⚠️ SQL injection vulnerability in line 12"
+- test-coverage: "Coverage is 45%, missing tests for error cases"
+- docs-checker: "Missing docstring for function `process_data`"
+
+### Example 2: Multi-Language Support
+
+```json
+{
+  "broadcast": {
+    "strategy": "sequential",
+    "+15555550123": ["detect-language", "translator-en", "translator-de"]
+  },
+  "agents": {
+    "list": [
+      { "id": "detect-language", "workspace": "~/agents/lang-detect" },
+      { "id": "translator-en", "workspace": "~/agents/translate-en" },
+      { "id": "translator-de", "workspace": "~/agents/translate-de" }
+    ]
+  }
+}
+```
+
+## API Reference
+
+### Config Schema
+
+```typescript
+interface ClawdbotConfig {
+  broadcast?: {
+    strategy?: "parallel" | "sequential";
+    [peerId: string]: string[];
+  };
+}
+```
+
+### Fields
+
+- `strategy` (optional): How to process agents
+  - `"parallel"` (default): All agents process simultaneously
+  - `"sequential"`: Agents process in array order
+  
+- `[peerId]`: WhatsApp group JID, E.164 number, or other peer ID
+  - Value: Array of agent IDs that should process messages
+
+## Limitations
+
+1. **Max agents:** No hard limit, but 10+ agents may be slow
+2. **Shared context:** Agents don't see each other's responses (by design)
+3. **Message ordering:** Parallel responses may arrive in any order
+4. **Rate limits:** All agents count toward WhatsApp rate limits
+
+## Future Enhancements
+
+Planned features:
+- [ ] Shared context mode (agents see each other's responses)
+- [ ] Agent coordination (agents can signal each other)
+- [ ] Dynamic agent selection (choose agents based on message content)
+- [ ] Agent priorities (some agents respond before others)
+
+## See Also
+
+- [Multi-Agent Configuration](/multi-agent-sandbox-tools)
+- [Routing Configuration](/concepts/provider-routing)
+- [Session Management](/concepts/sessions)

docs/cli/index.md

@@ -177,7 +177,7 @@ Options:
 - `--workspace <dir>`
 - `--non-interactive`
 - `--mode <local|remote>`
-- `--auth-choice <setup-token|claude-cli|token|openai-codex|openai-api-key|codex-cli|antigravity|gemini-api-key|apiKey|minimax-cloud|minimax|skip>`
+- `--auth-choice <setup-token|claude-cli|token|openai-codex|openai-api-key|codex-cli|antigravity|gemini-api-key|apiKey|minimax-cloud|minimax-api|minimax|opencode-zen|skip>`
 - `--token-provider <id>` (non-interactive; used with `--auth-choice token`)
 - `--token <token>` (non-interactive; used with `--auth-choice token`)
 - `--token-profile-id <id>` (non-interactive; default: `<provider>:manual`)
@@ -186,6 +186,7 @@ Options:
 - `--openai-api-key <key>`
 - `--gemini-api-key <key>`
 - `--minimax-api-key <key>`
+- `--opencode-zen-api-key <key>`
 - `--gateway-port <port>`
 - `--gateway-bind <loopback|lan|tailnet|auto>`
 - `--gateway-auth <off|token|password>`
@@ -673,5 +674,5 @@ Options:
 - `--deliver`
 - `--thinking <level>`
 - `--message <text>`
-- `--timeout-ms <ms>`
+- `--timeout-ms <ms>` (defaults to `agents.defaults.timeoutSeconds`)
 - `--history-limit <n>`

docs/cli/message.md

@@ -24,7 +24,7 @@ Provider selection:
 Target formats (`--to`):
 - WhatsApp: E.164 or group JID
 - Telegram: chat id or `@username`
-- Discord/Slack: `channel:<id>` or `user:<id>` (raw id ok)
+- Discord/Slack: `channel:<id>` or `user:<id>` (raw id is ambiguous for Discord)
 - Signal: E.164, `group:<id>`, or `signal:+E.164`
 - iMessage: handle or `chat_id:<id>`
 - MS Teams: conversation id (`19:...@thread.tacv2`) or `conversation:<id>` or `user:<aad-object-id>`
@@ -44,6 +44,7 @@ Target formats (`--to`):
 - `send`
   - Required: `--to`, `--message`
   - Optional: `--media`, `--reply-to`, `--thread-id`, `--gif-playback`
+  - Telegram only: `--buttons-json` (requires `"inlineButtons"` in `telegram.capabilities` or `telegram.accounts.<id>.capabilities`)
 
 - `poll`
   - Required: `--to`, `--poll-question`, `--poll-option` (repeat)
@@ -174,3 +175,9 @@ React in Slack:
 clawdbot message react --provider slack \
   --to C123 --message-id 456 --emoji "✅"
 ```
+
+Send Telegram inline buttons:
+```
+clawdbot message send --provider telegram --to @mychat --message "Choose:" \
+  --buttons-json '[ [{"text":"Yes","callback_data":"cmd:yes"}], [{"text":"No","callback_data":"cmd:no"}] ]'
+```

docs/concepts/agent.md

@@ -83,11 +83,14 @@ When queue mode is `followup` or `collect`, inbound messages are held until the
 current turn ends, then a new agent turn starts with the queued payloads. See
 [`docs/queue.md`](/concepts/queue) for mode + debounce/cap behavior.
 
-Block streaming sends completed assistant blocks as soon as they finish; disable
-via `agents.defaults.blockStreamingDefault: "off"` if you only want the final response.
+Block streaming sends completed assistant blocks as soon as they finish; it is
+**off by default** (`agents.defaults.blockStreamingDefault: "off"`).
 Tune the boundary via `agents.defaults.blockStreamingBreak` (`text_end` vs `message_end`; defaults to text_end).
 Control soft block chunking with `agents.defaults.blockStreamingChunk` (defaults to
 800–1200 chars; prefers paragraph breaks, then newlines; sentences last).
+Coalesce streamed chunks with `agents.defaults.blockStreamingCoalesce` to reduce
+single-line spam (idle-based merging before send). Non-Telegram providers require
+explicit `*.blockStreaming: true` to enable block replies.
 Verbose tool summaries are emitted at tool start (no debounce); Control UI
 streams tool output via agent events when available.
 More details: [Streaming + chunking](/concepts/streaming).

docs/concepts/messages.md

@@ -0,0 +1,83 @@
+---
+summary: "Message flow, sessions, queueing, and reasoning visibility"
+read_when:
+  - Explaining how inbound messages become replies
+  - Clarifying sessions, queueing modes, or streaming behavior
+  - Documenting reasoning visibility and usage implications
+---
+# Messages
+
+This page ties together how Clawdbot handles inbound messages, sessions, queueing,
+streaming, and reasoning visibility.
+
+## Message flow (high level)
+
+```
+Inbound message
+  -> routing/bindings -> session key
+  -> queue (if a run is active)
+  -> agent run (streaming + tools)
+  -> outbound replies (provider limits + chunking)
+```
+
+Key knobs live in configuration:
+- `messages.*` for prefixes, queueing, and group behavior.
+- `agents.defaults.*` for block streaming and chunking defaults.
+- Provider overrides (`whatsapp.*`, `telegram.*`, etc.) for caps and streaming toggles.
+
+See [Configuration](/gateway/configuration) for full schema.
+
+## Sessions and devices
+
+Sessions are owned by the gateway, not by clients.
+- Direct chats collapse into the agent main session key.
+- Groups/channels get their own session keys.
+- The session store and transcripts live on the gateway host.
+
+Multiple devices/providers can map to the same session, but history is not fully
+synced back to every client. Recommendation: use one primary device for long
+conversations to avoid divergent context. The Control UI and TUI always show the
+gateway-backed session transcript, so they are the source of truth.
+
+Details: [Session management](/concepts/session).
+
+## Queueing and followups
+
+If a run is already active, inbound messages can be queued, steered into the
+current run, or collected for a followup turn.
+
+- Configure via `messages.queue` (and `messages.queue.byProvider`).
+- Modes: `interrupt`, `steer`, `followup`, `collect`, plus backlog variants.
+
+Details: [Queueing](/concepts/queue).
+
+## Streaming, chunking, and batching
+
+Block streaming sends partial replies as the model produces text blocks.
+Chunking respects provider text limits and avoids splitting fenced code.
+
+Key settings:
+- `agents.defaults.blockStreamingDefault` (`on|off`, default off)
+- `agents.defaults.blockStreamingBreak` (`text_end|message_end`)
+- `agents.defaults.blockStreamingChunk` (`minChars|maxChars|breakPreference`)
+- `agents.defaults.blockStreamingCoalesce` (idle-based batching)
+- Provider overrides: `*.blockStreaming` and `*.blockStreamingCoalesce` (non-Telegram providers require explicit `*.blockStreaming: true`)
+
+Details: [Streaming + chunking](/concepts/streaming).
+
+## Reasoning visibility and tokens
+
+Clawdbot can expose or hide model reasoning:
+- `/reasoning on|off|stream` controls visibility.
+- Reasoning content still counts toward token usage when produced by the model.
+- Telegram supports reasoning stream into the draft bubble.
+
+Details: [Thinking + reasoning directives](/tools/thinking) and [Token use](/token-use).
+
+## Prefixes, threading, and replies
+
+Outbound message formatting is centralized in `messages`:
+- `messages.responsePrefix` (outbound prefix) and `whatsapp.messagePrefix` (WhatsApp inbound prefix)
+- Reply threading via `replyToMode` and per-provider defaults
+
+Details: [Configuration](/gateway/configuration#messages) and provider docs.

docs/concepts/model-failover.md

@@ -46,7 +46,7 @@ When a provider has multiple profiles, Clawdbot chooses an order like this:
 If no explicit order is configured, Clawdbot uses a round‑robin order:
 - **Primary key:** profile type (**OAuth before API keys**).
 - **Secondary key:** `usageStats.lastUsed` (oldest first, within each type).
-- **Cooldown profiles** are moved to the end, ordered by soonest cooldown expiry.
+- **Cooldown/disabled profiles** are moved to the end, ordered by soonest expiry.
 
 ### Why OAuth can “look lost”
 
@@ -79,16 +79,42 @@ State is stored in `auth-profiles.json` under `usageStats`:
 }
 ```
 
+## Billing disables
+
+Billing/credit failures (for example “insufficient credits” / “credit balance too low”) are treated as failover‑worthy, but they’re usually not transient. Instead of a short cooldown, Clawdbot marks the profile as **disabled** (with a longer backoff) and rotates to the next profile/provider.
+
+State is stored in `auth-profiles.json`:
+
+```json
+{
+  "usageStats": {
+    "provider:profile": {
+      "disabledUntil": 1736178000000,
+      "disabledReason": "billing"
+    }
+  }
+}
+```
+
+Defaults:
+- Billing backoff starts at **5 hours**, doubles per billing failure, and caps at **24 hours**.
+- Backoff counters reset if the profile hasn’t failed for **24 hours** (configurable).
+
 ## Model fallback
 
 If all profiles for a provider fail, Clawdbot moves to the next model in
 `agents.defaults.model.fallbacks`. This applies to auth failures, rate limits, and
-timeouts that exhausted profile rotation.
+timeouts that exhausted profile rotation (other errors do not advance fallback).
+
+When a run starts with a model override (hooks or CLI), fallbacks still end at
+`agents.defaults.model.primary` after trying any configured fallbacks.
 
 ## Related config
 
 See [`docs/configuration.md`](/gateway/configuration) for:
 - `auth.profiles` / `auth.order`
+- `auth.cooldowns.billingBackoffHours` / `auth.cooldowns.billingBackoffHoursByProvider`
+- `auth.cooldowns.billingMaxHours` / `auth.cooldowns.failureWindowHours`
 - `agents.defaults.model.primary` / `agents.defaults.model.fallbacks`
 - `agents.defaults.imageModel` routing
 

docs/concepts/provider-routing.md

@@ -51,6 +51,24 @@ Routing picks **one agent** for each inbound message:
 
 The matched agent determines which workspace and session store are used.
 
+## Broadcast groups (run multiple agents)
+
+Broadcast groups let you run **multiple agents** for the same peer **when Clawdbot would normally reply** (for example: in WhatsApp groups, after mention/activation gating).
+
+Config:
+
+```json5
+{
+  broadcast: {
+    strategy: "parallel",
+    "120363403215116621@g.us": ["alfred", "baerbel"],
+    "+15555550123": ["support", "logger"]
+  }
+}
+```
+
+See: [Broadcast Groups](/broadcast-groups).
+
 ## Config overview
 
 - `agents.list`: named agent definitions (workspace, model, etc.).

docs/concepts/session-tool.md

@@ -76,6 +76,7 @@ Behavior:
 - `timeoutSeconds > 0`: wait up to N seconds for completion, then return `{ runId, status: "ok", reply }`.
 - If wait times out: `{ runId, status: "timeout", error }`. Run continues; call `sessions_history` later.
 - If the run fails: `{ runId, status: "error", error }`.
+- Announce delivery runs after the primary run completes and is best-effort; `status: "ok"` does not guarantee the announce was delivered.
 - Waits via gateway `agent.wait` (server-side) so reconnects don't drop the wait.
 - Agent-to-agent message context is injected for the primary run.
 - After the primary run completes, Clawdbot runs a **reply-back loop**:

docs/concepts/streaming.md

@@ -32,9 +32,11 @@ Legend:
 - `provider send`: actual outbound messages (block replies).
 
 **Controls:**
-- `agents.defaults.blockStreamingDefault`: `"on"`/`"off"` (default on).
+- `agents.defaults.blockStreamingDefault`: `"on"`/`"off"` (default off).
+- Provider overrides: `*.blockStreaming` (and per-account variants) to force `"on"`/`"off"` per provider.
 - `agents.defaults.blockStreamingBreak`: `"text_end"` or `"message_end"`.
 - `agents.defaults.blockStreamingChunk`: `{ minChars, maxChars, breakPreference? }`.
+- `agents.defaults.blockStreamingCoalesce`: `{ minChars?, maxChars?, idleMs? }` (merge streamed blocks before send).
 - Provider hard cap: `*.textChunkLimit` (e.g., `whatsapp.textChunkLimit`).
 - Discord soft cap: `discord.maxLinesPerMessage` (default 17) splits tall replies to avoid UI clipping.
 
@@ -54,13 +56,32 @@ Block chunking is implemented by `EmbeddedBlockChunker`:
 
 `maxChars` is clamped to the provider `textChunkLimit`, so you can’t exceed per-provider caps.
 
+## Coalescing (merge streamed blocks)
+
+When block streaming is enabled, Clawdbot can **merge consecutive block chunks**
+before sending them out. This reduces “single-line spam” while still providing
+progressive output.
+
+- Coalescing waits for **idle gaps** (`idleMs`) before flushing.
+- Buffers are capped by `maxChars` and will flush if they exceed it.
+- `minChars` prevents tiny fragments from sending until enough text accumulates
+  (final flush always sends remaining text).
+- Joiner is derived from `blockStreamingChunk.breakPreference`
+  (`paragraph` → `\n\n`, `newline` → `\n`, `sentence` → space).
+- Provider overrides are available via `*.blockStreamingCoalesce` (including per-account configs).
+- Default coalesce `minChars` is bumped to 1500 for Signal/Slack/Discord unless overridden.
+
 ## “Stream chunks or everything”
 
 This maps to:
-- **Stream chunks:** `blockStreamingDefault: "on"` + `blockStreamingBreak: "text_end"` (emit as you go).
+- **Stream chunks:** `blockStreamingDefault: "on"` + `blockStreamingBreak: "text_end"` (emit as you go). Non-Telegram providers also need `*.blockStreaming: true`.
 - **Stream everything at end:** `blockStreamingBreak: "message_end"` (flush once, possibly multiple chunks if very long).
 - **No block streaming:** `blockStreamingDefault: "off"` (only final reply).
 
+**Provider note:** For non-Telegram providers, block streaming is **off unless**
+`*.blockStreaming` is explicitly set to `true`. Telegram can stream drafts
+(`telegram.streamMode`) without block replies.
+
 ## Telegram draft streaming (token-ish)
 
 Telegram is the only provider with draft streaming:
@@ -69,6 +90,7 @@ Telegram is the only provider with draft streaming:
   - `partial`: draft updates with the latest stream text.
   - `block`: draft updates in chunked blocks (same chunker rules).
   - `off`: no draft streaming.
+- Draft streaming is separate from block streaming; block replies are off by default and only enabled by `*.blockStreaming: true` on non-Telegram providers.
 - Final reply is still a normal message.
 - `/reasoning stream` writes reasoning into the draft bubble (Telegram only).
 

docs/concepts/system-prompt.md

@@ -15,7 +15,7 @@ The prompt is assembled by Clawdbot and injected into each agent run.
 The prompt is intentionally compact and uses fixed sections:
 
 - **Tooling**: current tool list + short descriptions.
-- **Skills**: tells the model how to load skill instructions on demand.
+- **Skills** (when available): tells the model how to load skill instructions on demand.
 - **Clawdbot Self-Update**: how to run `config.apply` and `update.run`.
 - **Workspace**: working directory (`agents.defaults.workspace`).
 - **Workspace Files (injected)**: indicates bootstrap files are included below.
@@ -49,10 +49,20 @@ Use `agents.defaults.userTimezone` in `~/.clawdbot/clawdbot.json` to change the
 
 ## Skills
 
-Skills are **not** auto-injected. Instead, the prompt instructs the model to use `read` to load skill instructions on demand:
+When eligible skills exist, Clawdbot injects a compact **available skills list**
+(`formatSkillsForPrompt`) that includes the **file path** for each skill. The
+prompt instructs the model to use `read` to load the SKILL.md at the listed
+location (workspace, managed, or bundled). If no skills are eligible, the
+Skills section is omitted.
 
 ```
-<workspace>/skills/<name>/SKILL.md
+<available_skills>
+  <skill>
+    <name>...</name>
+    <description>...</description>
+    <location>...</location>
+  </skill>
+</available_skills>
 ```
 
 This keeps the base prompt small while still enabling targeted skill usage.

docs/docs.json

@@ -37,6 +37,14 @@
       "source": "/model/",
       "destination": "/models"
     },
+    {
+      "source": "/messages",
+      "destination": "/concepts/messages"
+    },
+    {
+      "source": "/messages/",
+      "destination": "/concepts/messages"
+    },
     {
       "source": "/AGENTS.default",
       "destination": "/reference/AGENTS.default"
@@ -575,6 +583,7 @@
           "concepts/session-tool",
           "concepts/presence",
           "concepts/provider-routing",
+          "concepts/messages",
           "concepts/groups",
           "concepts/group-messages",
           "concepts/typing-indicators",

docs/experiments/proposals/hooks-gmail-model.md

@@ -0,0 +1,306 @@
+---
+summary: "Spec for hooks.gmail.model - cheaper model for Gmail PubSub processing"
+read_when:
+  - Implementing hooks.gmail.model feature
+  - Modifying Gmail hook processing
+  - Working on hook model selection
+---
+# hooks.gmail.model: Cheaper Model for Gmail PubSub Processing
+
+## Problem
+
+Gmail PubSub hook processing (`/gmail-pubsub`) currently uses the session's primary model (`agents.defaults.model.primary`), which may be an expensive model like `claude-opus-4-5`. For automated email processing that doesn't require the most capable model, this wastes tokens/cost.
+
+## Solution
+
+Add `hooks.gmail.model` config option to specify an optional cheaper model for Gmail PubSub processing, with intelligent fallback to the primary model on auth/rate-limit/timeout failures.
+
+## Config Structure
+
+```json5
+{
+  hooks: {
+    gmail: {
+      account: "user@gmail.com",
+      // ... existing gmail config ...
+
+      // NEW: Optional model override for Gmail hook processing
+      model: "openrouter/meta-llama/llama-3.3-70b-instruct:free",
+
+      // NEW: Optional thinking level override
+      thinking: "off"
+    }
+  }
+}
+```
+
+### Fields
+
+| Field | Type | Default | Description |
+|-------|------|---------|-------------|
+| `hooks.gmail.model` | `string` | (none) | Model to use for Gmail hook processing. Accepts `provider/model` refs or aliases from `agents.defaults.models`. |
+| `hooks.gmail.thinking` | `string` | (inherited) | Thinking level override (`off`, `minimal`, `low`, `medium`, `high`). If unset, inherits from `agents.defaults.thinkingDefault` or model's default. |
+
+### Alias Support
+
+`hooks.gmail.model` accepts:
+- Full refs: `"openrouter/meta-llama/llama-3.3-70b-instruct:free"`
+- Aliases from `agents.defaults.models`: `"Opus"`, `"Sonnet"`, `"GLM"`
+
+Resolution uses `buildModelAliasIndex()` from `model-selection.ts`.
+
+## Fallback Behavior
+
+### Fallback Triggers
+
+Auth, rate-limit, and timeout errors trigger fallback:
+- `401 Unauthorized`
+- `403 Forbidden`
+- `429 Too Many Requests`
+- Timeouts (provider hangs / network timeouts)
+
+Other errors (500s, content errors) fail in place.
+
+### Fallback Chain
+
+```
+hooks.gmail.model (if set)
+    ↓ (on auth/rate-limit/timeout)
+agents.defaults.model.fallbacks[0..n]
+    ↓ (exhausted)
+agents.defaults.model.primary
+```
+
+### Uncatalogued Model
+
+If `hooks.gmail.model` is set but not found in the model catalog or allowlist:
+- **Config load**: Log warning (surfaced in `clawdbot doctor`)
+- **Allowlist**: If `agents.defaults.models` is set and the model isn't listed, the hook falls back to primary.
+
+### Cooldown Integration
+
+Uses existing model-failover cooldown from `model-failover.ts`:
+- After auth/rate-limit failure, model enters cooldown
+- Next hook invocation respects cooldown before retrying
+- Integrates with auth profile rotation
+
+## Implementation
+
+### Type Changes
+
+```typescript
+// src/config/types.ts
+export type HooksGmailConfig = {
+  account?: string;
+  label?: string;
+  // ... existing fields ...
+
+  /** Optional model override for Gmail hook processing (provider/model or alias). */
+  model?: string;
+  /** Optional thinking level override for Gmail hook processing. */
+  thinking?: "off" | "minimal" | "low" | "medium" | "high";
+};
+```
+
+### Model Resolution
+
+New function in `src/cron/isolated-agent.ts` or `src/agents/model-selection.ts`:
+
+```typescript
+export function resolveHooksGmailModel(params: {
+  cfg: ClawdbotConfig;
+  defaultProvider: string;
+  defaultModel: string;
+}): { provider: string; model: string; isHooksOverride: boolean } | null {
+  const hooksModel = params.cfg.hooks?.gmail?.model;
+  if (!hooksModel) return null;
+
+  const aliasIndex = buildModelAliasIndex({
+    cfg: params.cfg,
+    defaultProvider: params.defaultProvider,
+  });
+
+  const resolved = resolveModelRefFromString({
+    raw: hooksModel,
+    defaultProvider: params.defaultProvider,
+    aliasIndex,
+  });
+
+  if (!resolved) return null;
+  return {
+    provider: resolved.ref.provider,
+    model: resolved.ref.model,
+    isHooksOverride: true,
+  };
+}
+```
+
+### Processing Flow
+
+In `runCronIsolatedAgentTurn()` (or new wrapper for hooks):
+
+```typescript
+// Resolve model - prefer hooks.gmail.model for Gmail hooks
+const isGmailHook = params.sessionKey.startsWith("hook:gmail:");
+const hooksModelRef = isGmailHook
+  ? resolveHooksGmailModel({ cfg, defaultProvider, defaultModel })
+  : null;
+
+const { provider, model } = hooksModelRef ?? resolveConfiguredModelRef({
+  cfg: params.cfg,
+  defaultProvider: DEFAULT_PROVIDER,
+  defaultModel: DEFAULT_MODEL,
+});
+
+// Run with fallback - on auth/rate-limit/timeout, fall through to agents.defaults.model.fallbacks
+const fallbackResult = await runWithModelFallback({
+  cfg: params.cfg,
+  provider,
+  model,
+  hooksOverride: hooksModelRef?.isHooksOverride,
+  run: (providerOverride, modelOverride) => runEmbeddedPiAgent({
+    // ... existing params ...
+  }),
+});
+```
+
+### Fallback Detection
+
+Extend `runWithModelFallback()` to detect auth/rate-limit:
+
+```typescript
+function isAuthRateLimitError(err: unknown): boolean {
+  if (err instanceof ApiError) {
+    return [401, 403, 429].includes(err.status);
+  }
+  // Check for common patterns in error messages
+  const msg = String(err).toLowerCase();
+  return msg.includes("unauthorized")
+    || msg.includes("rate limit")
+    || msg.includes("quota exceeded");
+}
+```
+
+## Validation
+
+### Config Load Time
+
+In config validation (for `clawdbot doctor`):
+
+```typescript
+if (cfg.hooks?.gmail?.model) {
+  const resolved = resolveHooksGmailModel({ cfg, defaultProvider, defaultModel });
+  if (!resolved) {
+    issues.push({
+      path: "hooks.gmail.model",
+      message: `Model "${cfg.hooks.gmail.model}" could not be resolved`,
+    });
+  } else {
+    const catalog = await loadModelCatalog({ config: cfg });
+    const key = modelKey(resolved.provider, resolved.model);
+    const inCatalog = catalog.some(e => modelKey(e.provider, e.id) === key);
+    if (!inCatalog) {
+      issues.push({
+        path: "hooks.gmail.model",
+        message: `Model "${key}" not found in agents.defaults.models catalog (will fall back to primary)`,
+      });
+    }
+  }
+}
+```
+
+### Runtime
+
+At hook invocation time, validate and fall back:
+- If model not in catalog → log warning, use primary
+- If model auth fails → log warning, enter cooldown, fall back
+
+## Observability
+
+### Log Messages
+
+```
+[hooks] Gmail hook: using model openrouter/meta-llama/llama-3.3-70b-instruct:free
+[hooks] Gmail hook: model llama auth failed (429), falling back to claude-opus-4-5
+```
+
+### Hook Event Summary
+
+Include fallback info in the hook summary sent to session:
+
+```
+Hook Gmail (fallback:llama→opus): <summary>
+```
+
+## Hot Reload
+
+`hooks.gmail.model` and `hooks.gmail.thinking` are hot-reloadable:
+- Changes apply to the next hook invocation
+- No gateway restart required
+- Hooks config is already in the hot-reload matrix
+
+## Test Plan
+
+### Unit Tests
+
+1. **Model resolution** (`model-selection.test.ts`):
+   - `resolveHooksGmailModel()` with valid ref
+   - `resolveHooksGmailModel()` with alias
+   - `resolveHooksGmailModel()` with invalid input → null
+
+2. **Config validation** (`config.test.ts`):
+   - Warning on uncatalogued model
+   - No warning on valid model
+   - Graceful handling of missing hooks.gmail section
+
+3. **Fallback triggers** (`model-fallback.test.ts`):
+   - 401/403/429 → triggers fallback
+   - timeouts → triggers fallback
+   - 500/content error → no fallback
+   - Content error → no fallback
+
+### Integration Tests
+
+1. **Hook processing** (`server.hooks.test.ts`):
+   - Gmail hook uses `hooks.gmail.model` when set
+   - Fallback to primary on auth failure
+   - Thinking level override applied
+
+2. **Hot reload** (`config-reload.test.ts`):
+   - Change `hooks.gmail.model` → next hook uses new model
+
+## Documentation
+
+Update `docs/gateway/configuration.md`:
+
+```json5
+{
+  hooks: {
+    gmail: {
+      account: "user@gmail.com",
+      topic: "projects/my-project/topics/gmail-watch",
+      // ... existing config ...
+
+      // Optional: Use a cheaper model for Gmail processing
+      // Falls back to agents.defaults.model.primary on auth/rate-limit errors
+      model: "openrouter/meta-llama/llama-3.3-70b-instruct:free",
+
+      // Optional: Override thinking level for Gmail processing
+      thinking: "off"
+    }
+  }
+}
+```
+
+## Scope Limitation
+
+This PR is Gmail-specific. Future hooks (`hooks.github.model`, etc.) would follow the same pattern but are out of scope.
+
+## Changelog Entry
+
+```
+- feat: add hooks.gmail.model for cheaper Gmail PubSub processing (#XXX)
+  - Falls back to agents.defaults.model.primary on auth/rate-limit/timeouts (401/403/429)
+  - Supports aliases from agents.defaults.models
+  - Add hooks.gmail.thinking override
+```

docs/gateway/configuration-examples.md

@@ -208,13 +208,16 @@ Save to `~/.clawdbot/clawdbot.json` and you can DM the bot from that number.
       thinkingDefault: "low",
       verboseDefault: "off",
       elevatedDefault: "on",
-      blockStreamingDefault: "on",
+      blockStreamingDefault: "off",
       blockStreamingBreak: "text_end",
       blockStreamingChunk: {
         minChars: 800,
         maxChars: 1200,
         breakPreference: "paragraph"
       },
+      blockStreamingCoalesce: {
+        idleMs: 1000
+      },
       timeoutSeconds: 600,
       mediaMaxMb: 5,
       typingIntervalSeconds: 5,

docs/gateway/configuration.md

@@ -248,7 +248,7 @@ Controls how WhatsApp direct chats (DMs) are handled:
 - `"open"`: allow all inbound DMs (**requires** `whatsapp.allowFrom` to include `"*"`)
 - `"disabled"`: ignore all inbound DMs
 
-Pairing codes expire after 1 hour; the bot only sends a pairing code when a new request is created.
+Pairing codes expire after 1 hour; the bot only sends a pairing code when a new request is created. Pending DM pairing requests are capped at **3 per provider** by default.
 
 Pairing approvals:
 - `clawdbot pairing list --provider whatsapp`
@@ -265,7 +265,8 @@ For groups, use `whatsapp.groupPolicy` + `whatsapp.groupAllowFrom`.
   whatsapp: {
     dmPolicy: "pairing", // pairing | allowlist | open | disabled
     allowFrom: ["+15555550123", "+447700900123"],
-    textChunkLimit: 4000 // optional outbound chunk size (chars)
+    textChunkLimit: 4000, // optional outbound chunk size (chars)
+    mediaMaxMb: 50 // optional inbound media cap (MB)
   }
 }
 ```
@@ -508,7 +509,7 @@ Read-only tools + read-only workspace:
           workspaceAccess: "ro"
         },
         tools: {
-          allow: ["read", "sessions_list", "sessions_history", "sessions_send", "sessions_spawn"],
+          allow: ["read", "sessions_list", "sessions_history", "sessions_send", "sessions_spawn", "session_status"],
           deny: ["write", "edit", "bash", "process", "browser"]
         }
       }
@@ -531,7 +532,7 @@ No filesystem access (messaging/session tools enabled):
           workspaceAccess: "none"
         },
         tools: {
-          allow: ["sessions_list", "sessions_history", "sessions_send", "sessions_spawn", "whatsapp", "telegram", "slack", "discord", "gateway"],
+          allow: ["sessions_list", "sessions_history", "sessions_send", "sessions_spawn", "session_status", "whatsapp", "telegram", "slack", "discord", "gateway"],
           deny: ["read", "write", "edit", "bash", "process", "browser", "canvas", "nodes", "cron", "gateway", "image"]
         }
       }
@@ -674,7 +675,7 @@ Multi-account support lives under `telegram.accounts` (see the multi-account sec
       }
     },
     replyToMode: "first",                 // off | first | all
-    streamMode: "partial",               // off | partial | block (draft streaming)
+    streamMode: "partial",               // off | partial | block (draft streaming; separate from block streaming)
     actions: { reactions: true, sendMessage: true }, // tool action gates (false disables)
     mediaMaxMb: 5,
     retry: {                             // outbound retry policy
@@ -764,7 +765,7 @@ Multi-account support lives under `discord.accounts` (see the multi-account sect
 }
 ```
 
-Clawdbot starts Discord only when a `discord` config section exists. The token is resolved from `DISCORD_BOT_TOKEN` or `discord.token` (unless `discord.enabled` is `false`). Use `user:<id>` (DM) or `channel:<id>` (guild channel) when specifying delivery targets for cron/CLI commands.
+Clawdbot starts Discord only when a `discord` config section exists. The token is resolved from `DISCORD_BOT_TOKEN` or `discord.token` (unless `discord.enabled` is `false`). Use `user:<id>` (DM) or `channel:<id>` (guild channel) when specifying delivery targets for cron/CLI commands; bare numeric IDs are ambiguous and rejected.
 Guild slugs are lowercase with spaces replaced by `-`; channel keys use the slugged channel name (no leading `#`). Prefer guild ids as keys to avoid rename ambiguity.
 Reaction notification modes:
 - `off`: no reaction events.
@@ -845,6 +846,26 @@ Slack action groups (gate `slack` tool actions):
 | pins | enabled | Pin/unpin/list |
 | memberInfo | enabled | Member info |
 | emojiList | enabled | Custom emoji list |
+
+### `signal` (signal-cli)
+
+Signal reactions can emit system events (shared reaction tooling):
+
+```json5
+{
+  signal: {
+    reactionNotifications: "own", // off | own | all | allowlist
+    reactionAllowlist: ["+15551234567", "uuid:123e4567-e89b-12d3-a456-426614174000"]
+  }
+}
+```
+
+Reaction notification modes:
+- `off`: no reaction events.
+- `own`: reactions on the bot's own messages (default).
+- `all`: all reactions on all messages.
+- `allowlist`: reactions from `signal.reactionAllowlist` on all messages (empty list disables).
+
 ### `imessage` (imsg CLI)
 
 Clawdbot spawns `imsg rpc` (JSON-RPC over stdio). No daemon or port required.
@@ -920,12 +941,12 @@ message envelopes). If unset, Clawdbot uses the host timezone at runtime.
 ### `messages`
 
 Controls inbound/outbound prefixes and optional ack reactions.
+See [Messages](/concepts/messages) for queueing, sessions, and streaming context.
 
 ```json5
 {
   messages: {
-    messagePrefix: "[clawdbot]",
-    responsePrefix: "🦞",
+    responsePrefix: "🦞", // or "auto"
     ackReaction: "👀",
     ackReactionScope: "group-mentions"
   }
@@ -935,13 +956,14 @@ Controls inbound/outbound prefixes and optional ack reactions.
 `responsePrefix` is applied to **all outbound replies** (tool summaries, block
 streaming, final replies) across providers unless already present.
 
-If `messages.responsePrefix` is unset and the routed agent has `identity.name`
-set, Clawdbot defaults the prefix to `[{identity.name}]`.
+If `messages.responsePrefix` is unset, no prefix is applied by default.
+Set it to `"auto"` to derive `[{identity.name}]` for the routed agent (when set).
 
-If `messages.messagePrefix` is unset, the default stays **unchanged**:
-`"[clawdbot]"` when `whatsapp.allowFrom` is empty, otherwise `""` (no prefix).
-When using `"[clawdbot]"`, Clawdbot will instead use `[{identity.name}]` when
-the routed agent has `identity.name` set.
+WhatsApp inbound prefix is configured via `whatsapp.messagePrefix` (deprecated:
+`messages.messagePrefix`). Default stays **unchanged**: `"[clawdbot]"` when
+`whatsapp.allowFrom` is empty, otherwise `""` (no prefix). When using
+`"[clawdbot]"`, Clawdbot will instead use `[{identity.name}]` when the routed
+agent has `identity.name` set.
 
 `ackReaction` sends a best-effort emoji reaction to acknowledge inbound messages
 on providers that support reactions (Slack/Discord/Telegram). Defaults to the
@@ -1141,7 +1163,9 @@ Example (adaptive tuned):
 See [/concepts/session-pruning](/concepts/session-pruning) for behavior details.
 
 Block streaming:
-- `agents.defaults.blockStreamingDefault`: `"on"`/`"off"` (default on).
+- `agents.defaults.blockStreamingDefault`: `"on"`/`"off"` (default off).
+- Provider overrides: `*.blockStreaming` (and per-account variants) to force block streaming on/off.
+  Non-Telegram providers require an explicit `*.blockStreaming: true` to enable block replies.
 - `agents.defaults.blockStreamingBreak`: `"text_end"` or `"message_end"` (default: text_end).
 - `agents.defaults.blockStreamingChunk`: soft chunking for streamed blocks. Defaults to
   800–1200 chars, prefers paragraph breaks (`\n\n`), then newlines, then sentences.
@@ -1151,6 +1175,13 @@ Block streaming:
     agents: { defaults: { blockStreamingChunk: { minChars: 800, maxChars: 1200 } } }
   }
   ```
+- `agents.defaults.blockStreamingCoalesce`: merge streamed blocks before sending.
+  Defaults to `{ idleMs: 1000 }` and inherits `minChars` from `blockStreamingChunk`
+  with `maxChars` capped to the provider text limit. Signal/Slack/Discord default
+  to `minChars: 1500` unless overridden.
+  Provider overrides: `whatsapp.blockStreamingCoalesce`, `telegram.blockStreamingCoalesce`,
+  `discord.blockStreamingCoalesce`, `slack.blockStreamingCoalesce`, `signal.blockStreamingCoalesce`,
+  `imessage.blockStreamingCoalesce`, `msteams.blockStreamingCoalesce` (and per-account variants).
 See [/concepts/streaming](/concepts/streaming) for behavior + chunking details.
 
 Typing indicators:
@@ -1225,8 +1256,24 @@ Example:
 }
 ```
 
+Per-agent override (further restrict):
+```json5
+{
+  agents: {
+    list: [
+      {
+        id: "family",
+        tools: {
+          elevated: { enabled: false }
+        }
+      }
+    ]
+  }
+}
+```
+
 Notes:
-- `tools.elevated` is **global** (not per-agent). Availability is based on sender allowlists.
+- `tools.elevated` is the global baseline. `agents.list[].tools.elevated` can only further restrict (both must allow).
 - `/elevated on|off` stores state per session key; inline directives apply to a single message.
 - Elevated `bash` runs on the host and bypasses sandboxing.
 - Tool policy still applies; if `bash` is denied, elevated cannot be used.
@@ -1250,7 +1297,7 @@ Defaults (if enabled):
   - `"ro"`: keep the sandbox workspace at `/workspace`, and mount the agent workspace read-only at `/agent` (disables `write`/`edit`)
   - `"rw"`: mount the agent workspace read/write at `/workspace`
 - auto-prune: idle > 24h OR age > 7d
-- tool policy: allow only `bash`, `process`, `read`, `write`, `edit`, `sessions_list`, `sessions_history`, `sessions_send`, `sessions_spawn` (deny wins)
+- tool policy: allow only `bash`, `process`, `read`, `write`, `edit`, `sessions_list`, `sessions_history`, `sessions_send`, `sessions_spawn`, `session_status` (deny wins)
   - configure via `tools.sandbox.tools`, override per-agent via `agents.list[].tools.sandbox.tools`
 - optional sandboxed browser (Chromium + CDP, noVNC observer)
 - hardening knobs: `network`, `user`, `pidsLimit`, `memory`, `cpus`, `ulimits`, `seccompProfile`, `apparmorProfile`
@@ -1315,7 +1362,7 @@ Legacy: `perSession` is still supported (`true` → `scope: "session"`,
   tools: {
     sandbox: {
       tools: {
-        allow: ["bash", "process", "read", "write", "edit", "sessions_list", "sessions_history", "sessions_send", "sessions_spawn"],
+        allow: ["bash", "process", "read", "write", "edit", "sessions_list", "sessions_history", "sessions_send", "sessions_spawn", "session_status"],
         deny: ["browser", "canvas", "nodes", "cron", "discord", "gateway"]
       }
     }
@@ -1877,11 +1924,25 @@ Gmail helper config (used by `clawdbot hooks gmail setup` / `run`):
       renewEveryMinutes: 720,
       serve: { bind: "127.0.0.1", port: 8788, path: "/" },
       tailscale: { mode: "funnel", path: "/gmail-pubsub" },
+
+      // Optional: use a cheaper model for Gmail hook processing
+      // Falls back to agents.defaults.model.fallbacks, then primary, on auth/rate-limit/timeout
+      model: "openrouter/meta-llama/llama-3.3-70b-instruct:free",
+      // Optional: default thinking level for Gmail hooks
+      thinking: "off",
     }
   }
 }
 ```
 
+Model override for Gmail hooks:
+- `hooks.gmail.model` specifies a model to use for Gmail hook processing (defaults to session primary).
+- Accepts `provider/model` refs or aliases from `agents.defaults.models`.
+- Falls back to `agents.defaults.model.fallbacks`, then `agents.defaults.model.primary`, on auth/rate-limit/timeouts.
+- If `agents.defaults.models` is set, include the hooks model in the allowlist.
+- At startup, warns if the configured model is not in the model catalog or allowlist.
+- `hooks.gmail.thinking` sets the default thinking level for Gmail hooks and is overridden by per-hook `thinking`.
+
 Gateway auto-start:
 - If `hooks.enabled=true` and `hooks.gmail.account` is set, the Gateway starts
   `gog gmail watch serve` on boot and auto-renews the watch.

docs/gateway/doctor.md

@@ -61,7 +61,7 @@ cat ~/.clawdbot/clawdbot.json
 - Legacy on-disk state migration (sessions/agent dir/WhatsApp auth).
 - State integrity and permissions checks (sessions, transcripts, state dir).
 - Config file permission checks (chmod 600) when running locally.
-- Model auth health: checks OAuth expiry and can refresh expiring tokens.
+- Model auth health: checks OAuth expiry, can refresh expiring tokens, and reports auth-profile cooldown/disabled states.
 - Legacy workspace dir detection (`~/clawdis`, `~/clawdbot`).
 - Sandbox image repair when sandboxing is enabled.
 - Legacy service migration and extra gateway detection.
@@ -153,6 +153,10 @@ profile is stale, it suggests `claude setup-token` on the gateway host.
 Refresh prompts only appear when running interactively (TTY); `--non-interactive`
 skips refresh attempts.
 
+Doctor also reports auth profiles that are temporarily unusable due to:
+- short cooldowns (rate limits/timeouts/auth failures)
+- longer disables (billing/credit failures)
+
 ### 6) Sandbox image repair
 When sandboxing is enabled, doctor checks Docker images and offers to build or
 switch to legacy names if the current image is missing.

docs/gateway/security.md

@@ -38,7 +38,7 @@ Clawdbot’s stance:
 
 All current DM-capable providers support a DM policy (`dmPolicy` or `*.dm.policy`) that gates inbound DMs **before** the message is processed:
 
-- `pairing` (default): unknown senders receive a short pairing code and the bot ignores their message until approved. Codes expire after 1 hour; repeated DMs won’t resend a code until a new request is created.
+- `pairing` (default): unknown senders receive a short pairing code and the bot ignores their message until approved. Codes expire after 1 hour; repeated DMs won’t resend a code until a new request is created. Pending requests are capped at **3 per provider** by default.
 - `allowlist`: unknown senders are blocked (no pairing handshake).
 - `open`: allow anyone to DM (public). **Requires** the provider allowlist to include `"*"` (explicit opt-in).
 - `disabled`: ignore inbound DMs entirely.
@@ -172,7 +172,7 @@ Also consider agent workspace access inside the sandbox:
 - `agents.defaults.sandbox.workspaceAccess: "ro"` mounts the agent workspace read-only at `/agent` (disables `write`/`edit`)
 - `agents.defaults.sandbox.workspaceAccess: "rw"` mounts the agent workspace read/write at `/workspace`
 
-Important: `tools.elevated` is a **global**, sender-based escape hatch that runs bash on the host. Keep `tools.elevated.allowFrom` tight and don’t enable it for strangers. See [Elevated Mode](/tools/elevated).
+Important: `tools.elevated` is the global baseline escape hatch that runs bash on the host. Keep `tools.elevated.allowFrom` tight and don’t enable it for strangers. You can further restrict elevated per agent via `agents.list[].tools.elevated`. See [Elevated Mode](/tools/elevated).
 
 ## Per-agent access profiles (multi-agent)
 
@@ -241,7 +241,7 @@ Common use cases:
           workspaceAccess: "none"
         },
         tools: {
-          allow: ["sessions_list", "sessions_history", "sessions_send", "sessions_spawn", "whatsapp", "telegram", "slack", "discord", "gateway"],
+          allow: ["sessions_list", "sessions_history", "sessions_send", "sessions_spawn", "session_status", "whatsapp", "telegram", "slack", "discord", "gateway"],
           deny: ["read", "write", "edit", "bash", "process", "browser", "canvas", "nodes", "cron", "gateway", "image"]
         }
       }

docs/gateway/troubleshooting.md

@@ -169,6 +169,24 @@ clawdbot logs --follow
 tail -f "$(ls -t /tmp/clawdbot/clawdbot-*.log | head -1)" | grep "blocked\\|skip\\|unauthorized"
 ```
 
+### Pairing Code Not Arriving
+
+If `dmPolicy` is `pairing`, unknown senders should receive a code and their message is ignored until approved.
+
+**Check 1:** Is a pending request already waiting?
+```bash
+clawdbot pairing list --provider <provider>
+```
+
+Pending DM pairing requests are capped at **3 per provider** by default. If the list is full, new requests won’t generate a code until one is approved or expires.
+
+**Check 2:** Did the request get created but no reply was sent?
+```bash
+clawdbot logs --follow | grep "pairing request"
+```
+
+**Check 3:** Confirm `dmPolicy` isn’t `open`/`allowlist` for that provider.
+
 ### Image + Mention Not Working
 
 Known issue: When you send an image with ONLY a mention (no other text), WhatsApp sometimes doesn't include the mention metadata.

docs/index.md

@@ -112,6 +112,8 @@ clawdbot providers login
 clawdbot gateway --port 18789
 ```
 
+Switching between npm and git installs later is easy: install the other flavor and run `clawdbot doctor` to update the gateway service entrypoint.
+
 From source (development):
 
 ```bash

docs/install/docker.md

@@ -61,6 +61,40 @@ docker compose run --rm clawdbot-cli onboard
 docker compose up -d clawdbot-gateway
 ```
 
+### Faster rebuilds (recommended)
+
+To speed up rebuilds, order your Dockerfile so dependency layers are cached.
+This avoids re-running `pnpm install` unless lockfiles change:
+
+```dockerfile
+FROM node:22-bookworm
+
+# Install Bun (required for build scripts)
+RUN curl -fsSL https://bun.sh/install | bash
+ENV PATH="/root/.bun/bin:${PATH}"
+
+RUN corepack enable
+
+WORKDIR /app
+
+# Cache dependencies unless package metadata changes
+COPY package.json pnpm-lock.yaml pnpm-workspace.yaml .npmrc ./
+COPY ui/package.json ./ui/package.json
+COPY patches ./patches
+COPY scripts ./scripts
+
+RUN pnpm install --frozen-lockfile
+
+COPY . .
+RUN pnpm build
+RUN pnpm ui:install
+RUN pnpm ui:build
+
+ENV NODE_ENV=production
+
+CMD ["node","dist/index.js"]
+```
+
 ### Provider setup (optional)
 
 Use the CLI container to configure providers, then restart the gateway if needed.
@@ -144,7 +178,7 @@ precedence, and troubleshooting.
   - `"rw"` mounts the agent workspace read/write at `/workspace`
 - Auto-prune: idle > 24h OR age > 7d
 - Network: `none` by default (explicitly opt-in if you need egress)
-- Default allow: `bash`, `process`, `read`, `write`, `edit`, `sessions_list`, `sessions_history`, `sessions_send`, `sessions_spawn`
+- Default allow: `bash`, `process`, `read`, `write`, `edit`, `sessions_list`, `sessions_history`, `sessions_send`, `sessions_spawn`, `session_status`
 - Default deny: `browser`, `canvas`, `nodes`, `cron`, `discord`, `gateway`
 
 ### Enable sandboxing
@@ -191,7 +225,7 @@ precedence, and troubleshooting.
   tools: {
     sandbox: {
       tools: {
-        allow: ["bash", "process", "read", "write", "edit", "sessions_list", "sessions_history", "sessions_send", "sessions_spawn"],
+        allow: ["bash", "process", "read", "write", "edit", "sessions_list", "sessions_history", "sessions_send", "sessions_spawn", "session_status"],
         deny: ["browser", "canvas", "nodes", "cron", "discord", "gateway"]
       }
     }

docs/install/updating.md

@@ -67,6 +67,7 @@ pnpm clawdbot health
 Notes:
 - `pnpm build` matters when you run the packaged `clawdbot` binary ([`dist/entry.js`](https://github.com/clawdbot/clawdbot/blob/main/dist/entry.js)) or use Node to run `dist/`.
 - If you run directly from TypeScript (`pnpm clawdbot ...` / `bun run clawdbot ...`), a rebuild is usually unnecessary, but **config migrations still apply** → run doctor.
+- Switching between npm and git installs is easy: install the other flavor, then run `clawdbot doctor` so the gateway service entrypoint is rewritten to the current install.
 
 ## Always run: `clawdbot doctor`
 

docs/multi-agent-sandbox-tools.md

@@ -172,13 +172,14 @@ The filtering order is:
 Each level can further restrict tools, but cannot grant back denied tools from earlier levels.
 If `agents.list[].tools.sandbox.tools` is set, it replaces `tools.sandbox.tools` for that agent.
 
-### Elevated Mode (global)
-`tools.elevated` is **global** and **sender-based** (per-provider allowlist). It is **not** configurable per agent.
+### Elevated Mode
+`tools.elevated` is the global baseline (sender-based allowlist). `agents.list[].tools.elevated` can further restrict elevated for specific agents (both must allow).
 
 Mitigation patterns:
 - Deny `bash` for untrusted agents (`agents.list[].tools.deny: ["bash"]`)
 - Avoid allowlisting senders that route to restricted agents
 - Disable elevated globally (`tools.elevated.enabled: false`) if you only want sandboxed execution
+- Disable elevated per agent (`agents.list[].tools.elevated.enabled: false`) for sensitive profiles
 
 ---
 
@@ -252,7 +253,7 @@ Legacy `agent.*` configs are migrated by `clawdbot doctor`; prefer `agents.defau
 ```json
 {
   "tools": {
-    "allow": ["sessions_list", "sessions_send", "sessions_history"],
+    "allow": ["sessions_list", "sessions_send", "sessions_history", "session_status"],
     "deny": ["bash", "write", "edit", "read", "browser"]
   }
 }

docs/platforms/hetzner.md

@@ -214,9 +214,15 @@ RUN curl -L https://github.com/steipete/wacli/releases/latest/download/wacli_Lin
 # Add more binaries below using the same pattern
 
 WORKDIR /app
-COPY . .
+COPY package.json pnpm-lock.yaml pnpm-workspace.yaml .npmrc ./
+COPY ui/package.json ./ui/package.json
+COPY patches ./patches
+COPY scripts ./scripts
+
 RUN corepack enable
 RUN pnpm install --frozen-lockfile
+
+COPY . .
 RUN pnpm build
 RUN pnpm ui:install
 RUN pnpm ui:build

docs/providers/discord.md

@@ -20,7 +20,7 @@ Status: ready for DM and guild text channels via the official Discord bot gatewa
 3. Configure Clawdbot with `DISCORD_BOT_TOKEN` (or `discord.token` in `~/.clawdbot/clawdbot.json`).
 4. Run the gateway; it auto-starts the Discord provider only when a `discord` config section exists **and** the token is set (unless `discord.enabled = false`).
    - If you prefer env vars, still add `discord: { enabled: true }` to `~/.clawdbot/clawdbot.json` and set `DISCORD_BOT_TOKEN`.
-5. Direct chats: use `user:<id>` (or a `<@id>` mention) when delivering; all turns land in the shared `main` session.
+5. Direct chats: use `user:<id>` (or a `<@id>` mention) when delivering; all turns land in the shared `main` session. Bare numeric IDs are ambiguous and rejected.
 6. Guild channels: use `channel:<channelId>` for delivery. Mentions are required by default and can be set per guild or per channel.
 7. Direct chats: secure by default via `discord.dm.policy` (default: `"pairing"`). Unknown senders get a pairing code (expires after 1 hour); approve via `clawdbot pairing approve --provider discord <code>`.
    - To keep old “open to anyone” behavior: set `discord.dm.policy="open"` and `discord.dm.allowFrom=["*"]`.

docs/providers/grammy.md

@@ -18,7 +18,7 @@ read_when:
 - **Webhook support:** `webhook-set.ts` wraps `setWebhook/deleteWebhook`; `webhook.ts` hosts the callback with health + graceful shutdown. Gateway enables webhook mode when `telegram.webhookUrl` is set (otherwise it long-polls).
 - **Sessions:** direct chats collapse into the agent main session (`agent:<agentId>:<mainKey>`); groups use `agent:<agentId>:telegram:group:<chatId>`; replies route back to the same provider.
 - **Config knobs:** `telegram.botToken`, `telegram.dmPolicy`, `telegram.groups` (allowlist + mention defaults), `telegram.allowFrom`, `telegram.groupAllowFrom`, `telegram.groupPolicy`, `telegram.mediaMaxMb`, `telegram.proxy`, `telegram.webhookSecret`, `telegram.webhookUrl`.
-- **Draft streaming:** optional `telegram.streamMode` uses `sendMessageDraft` in private topic chats (Bot API 9.3+).
+- **Draft streaming:** optional `telegram.streamMode` uses `sendMessageDraft` in private topic chats (Bot API 9.3+). This is separate from provider block streaming.
 - **Tests:** grammy mocks cover DM + group mention gating and outbound send; more media/webhook fixtures still welcome.
 
 Open questions

docs/providers/imessage.md

@@ -13,6 +13,7 @@ Status: external CLI integration. Gateway spawns `imsg rpc` (JSON-RPC over stdio
 - iMessage provider backed by `imsg` on macOS.
 - Deterministic routing: replies always go back to iMessage.
 - DMs share the agent's main session; groups are isolated (`imessage:group:<chat_id>`).
+- If a multi-participant thread arrives with `is_group=false`, you can still isolate it by `chat_id` using `imessage.groups` (see “Group-ish threads” below).
 
 ## Requirements
 - macOS with Messages signed in.
@@ -24,35 +25,61 @@ Status: external CLI integration. Gateway spawns `imsg rpc` (JSON-RPC over stdio
 1) Ensure Messages is signed in on this Mac.
 2) Configure iMessage and start the gateway.
 
-### Remote/SSH variant (optional)
-If you want iMessage on another Mac, set `imessage.cliPath` to a wrapper that
-execs `ssh` and runs `imsg rpc` on the remote host. Clawdbot only needs a
-stdio stream; `imsg` still runs on the remote macOS host.
+### Dedicated bot macOS user (for isolated identity)
+If you want the bot to send from a **separate iMessage identity** (and keep your personal Messages clean), use a dedicated Apple ID + a dedicated macOS user.
 
-Example wrapper (save somewhere in your PATH and `chmod +x`):
+1) Create a dedicated Apple ID (example: `my-cool-bot@icloud.com`).
+   - Apple may require a phone number for verification / 2FA.
+2) Create a macOS user (example: `clawdshome`) and sign into it.
+3) Open Messages in that macOS user and sign into iMessage using the bot Apple ID.
+4) Enable Remote Login (System Settings → General → Sharing → Remote Login).
+5) Install `imsg`:
+   - `brew install steipete/tap/imsg`
+6) Set up SSH so `ssh <bot-macos-user>@localhost true` works without a password.
+7) Point `imessage.accounts.bot.cliPath` at an SSH wrapper that runs `imsg` as the bot user.
+
+First-run note: sending/receiving may require GUI approvals (Automation + Full Disk Access) in the *bot macOS user*. If `imsg rpc` looks stuck or exits, log into that user (Screen Sharing helps), run a one-time `imsg chats --limit 1` / `imsg send ...`, approve prompts, then retry.
+
+Example wrapper (`chmod +x`). Replace `<bot-macos-user>` with your actual macOS username:
+```bash
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Run an interactive SSH once first to accept host keys:
+#   ssh <bot-macos-user>@localhost true
+exec /usr/bin/ssh -o BatchMode=yes -o ConnectTimeout=5 -T <bot-macos-user>@localhost \
+  "/usr/local/bin/imsg" "$@"
+```
+
+Example config:
+```json5
+{
+  imessage: {
+    enabled: true,
+    accounts: {
+      bot: {
+        name: "Bot",
+        enabled: true,
+        cliPath: "/path/to/imsg-bot",
+        dbPath: "/Users/<bot-macos-user>/Library/Messages/chat.db"
+      }
+    }
+  }
+}
+```
+
+For single-account setups, use flat options (`imessage.cliPath`, `imessage.dbPath`) instead of the `accounts` map.
+
+### Remote/SSH variant (optional)
+If you want iMessage on another Mac, set `imessage.cliPath` to a wrapper that runs `imsg` on the remote macOS host over SSH. Clawdbot only needs stdio.
+
+Example wrapper:
 ```bash
 #!/usr/bin/env bash
 exec ssh -T mac-mini imsg "$@"
 ```
 
-Notes:
-- Remote Mac must have Messages signed in and `imsg` installed.
-- Full Disk Access + Automation prompts happen on the remote Mac.
-- Use SSH keys (no password prompt) so the gateway can launch `imsg rpc` unattended.
-
-Example:
-```json5
-{
-  imessage: {
-    enabled: true,
-    cliPath: "/usr/local/bin/imessage-remote",
-    dmPolicy: "pairing",
-    allowFrom: ["+15555550123"]
-  }
-}
-```
-
-Multi-account support: use `imessage.accounts` with per-account config and optional `name`. See [`gateway/configuration`](/gateway/configuration#telegramaccounts--discordaccounts--slackaccounts--signalaccounts--imessageaccounts) for the shared pattern.
+Multi-account support: use `imessage.accounts` with per-account config and optional `name`. See [`gateway/configuration`](/gateway/configuration#telegramaccounts--discordaccounts--slackaccounts--signalaccounts--imessageaccounts) for the shared pattern. Don’t commit `~/.clawdbot/clawdbot.json` (it often contains tokens).
 
 ## Access control (DMs + groups)
 DMs:
@@ -73,6 +100,27 @@ Groups:
 - `imsg` streams message events; the gateway normalizes them into the shared provider envelope.
 - Replies always route back to the same chat id or handle.
 
+## Group-ish threads (`is_group=false`)
+Some iMessage threads can have multiple participants but still arrive with `is_group=false` depending on how Messages stores the chat identifier.
+
+If you explicitly configure a `chat_id` under `imessage.groups`, Clawdbot treats that thread as a “group” for:
+- session isolation (separate `imessage:group:<chat_id>` session key)
+- group allowlisting / mention gating behavior
+
+Example:
+```json5
+{
+  imessage: {
+    groupPolicy: "allowlist",
+    groupAllowFrom: ["+15555550123"],
+    groups: {
+      "42": { "requireMention": false }
+    }
+  }
+}
+```
+This is useful when you want an isolated personality/model for a specific thread (see [Multi-agent routing](/concepts/multi-agent)). For filesystem isolation, see [Sandboxing](/gateway/sandboxing).
+
 ## Media + limits
 - Optional attachment ingestion via `imessage.includeAttachments`.
 - Media cap via `imessage.mediaMaxMb`.

docs/providers/slack.md

@@ -199,12 +199,20 @@ Ack reactions are controlled globally via `messages.ackReaction` +
 - Media uploads are capped by `slack.mediaMaxMb` (default 20).
 
 ## Reply threading
-Slack supports optional threaded replies via tags:
-- `[[reply_to_current]]` — reply to the triggering message.
-- `[[reply_to:<id>]]` — reply to a specific message id.
+By default, Clawdbot replies in the main channel. Use `slack.replyToMode` to control automatic threading:
 
-Controlled by `slack.replyToMode`:
-- `off` (default), `first`, `all`.
+| Mode | Behavior |
+| --- | --- |
+| `off` | **Default.** Reply in main channel. Only thread if the triggering message was already in a thread. |
+| `first` | First reply goes to thread (under the triggering message), subsequent replies go to main channel. Useful for keeping context visible while avoiding thread clutter. |
+| `all` | All replies go to thread. Keeps conversations contained but may reduce visibility. |
+
+The mode applies to both auto-replies and agent tool calls (`slack sendMessage`).
+
+### Manual threading tags
+For fine-grained control, use these tags in agent responses:
+- `[[reply_to_current]]` — reply to the triggering message (start/continue thread).
+- `[[reply_to:<id>]]` — reply to a specific message id.
 
 ## Sessions + routing
 - DMs share the `main` session (like WhatsApp/Telegram).

docs/providers/telegram.md

@@ -206,6 +206,10 @@ Config:
   - `block`: update the draft bubble in larger blocks (chunked).
   - `off`: disable draft streaming.
 
+Note: draft streaming is separate from **block streaming** (provider messages).
+Block streaming is off by default and requires `telegram.blockStreaming: true`
+if you want early Telegram messages instead of draft updates.
+
 Reasoning stream (Telegram only):
 - `/reasoning stream` streams reasoning into the draft bubble while the reply is
   generating, then sends the final answer without reasoning.

docs/providers/whatsapp.md

@@ -59,8 +59,8 @@ When the wizard asks for your personal WhatsApp number, enter the phone you will
 }
 ```
 
-Tip: if you set the routed agent’s `identity.name`, you can omit
-`messages.responsePrefix` and it will default to `[{identity.name}]`.
+Tip: set `messages.responsePrefix` explicitly if you want a consistent bot prefix
+on outbound replies.
 
 ### Number sourcing tips
 - **Local eSIM** from your country's mobile carrier (most reliable)
@@ -103,9 +103,9 @@ Tip: if you set the routed agent’s `identity.name`, you can omit
 If you run Clawdbot on your **personal WhatsApp number**, enable `whatsapp.selfChatMode` (see sample above).
 
 Behavior:
-- Suppresses pairing replies for **outbound DMs** (prevents spamming contacts).
+- Outbound DMs never trigger pairing replies (prevents spamming contacts).
 - Inbound unknown senders still follow `whatsapp.dmPolicy`.
-- Self-chat mode avoids auto read receipts and ignores mention JIDs.
+- Self-chat mode (allowFrom includes your number) avoids auto read receipts and ignores mention JIDs.
 - Read receipts sent for non-self-chat DMs.
 
 ## Message normalization (what the model sees)
@@ -151,7 +151,8 @@ Behavior:
 
 ## Limits
 - Outbound text is chunked to `whatsapp.textChunkLimit` (default 4000).
-- Media items are capped by `agents.defaults.mediaMaxMb` (default 5 MB).
+- Inbound media saves are capped by `whatsapp.mediaMaxMb` (default 50 MB).
+- Outbound media items are capped by `agents.defaults.mediaMaxMb` (default 5 MB).
 
 ## Outbound send (text + media)
 - Uses active web listener; error if gateway not running.
@@ -166,7 +167,7 @@ Behavior:
     - Gateway: `send` params include `gifPlayback: true`
 
 ## Media limits + optimization
-- Default cap: 5 MB (per media item).
+- Default outbound cap: 5 MB (per media item).
 - Override: `agents.defaults.mediaMaxMb`.
 - Images are auto-optimized to JPEG under cap (resize + quality sweep).
 - Oversize media => error; media reply falls back to text warning.
@@ -185,16 +186,18 @@ Behavior:
 
 ## Config quick map
 - `whatsapp.dmPolicy` (DM policy: pairing/allowlist/open/disabled).
-- `whatsapp.selfChatMode` (same-phone setup; suppress pairing replies for outbound DMs).
+- `whatsapp.selfChatMode` (same-phone setup; bot uses your personal WhatsApp number).
 - `whatsapp.allowFrom` (DM allowlist).
+- `whatsapp.mediaMaxMb` (inbound media save cap).
 - `whatsapp.accounts.<accountId>.*` (per-account settings + optional `authDir`).
+- `whatsapp.accounts.<accountId>.mediaMaxMb` (per-account inbound media cap).
 - `whatsapp.groupAllowFrom` (group sender allowlist).
 - `whatsapp.groupPolicy` (group policy).
 - `whatsapp.groups` (group allowlist + mention gating defaults; use `"*"` to allow all)
 - `whatsapp.actions.reactions` (gate WhatsApp tool reactions).
 - `agents.list[].groupChat.mentionPatterns` (or `messages.groupChat.mentionPatterns`)
 - `messages.groupChat.historyLimit`
-- `messages.messagePrefix` (inbound prefix)
+- `whatsapp.messagePrefix` (inbound prefix; per-account: `whatsapp.accounts.<accountId>.messagePrefix`; deprecated: `messages.messagePrefix`)
 - `messages.responsePrefix` (outbound prefix)
 - `agents.defaults.mediaMaxMb`
 - `agents.defaults.heartbeat.every`

docs/reference/AGENTS.default.md

@@ -92,7 +92,7 @@ git commit -m "Add Clawd workspace"
 - **eightctl** — Control your sleep, from the terminal.
 - **imsg** — Send, read, stream iMessage & SMS.
 - **wacli** — WhatsApp CLI: sync, search, send.
-- **discord** — Discord actions: react, stickers, polls.
+- **discord** — Discord actions: react, stickers, polls. Use `user:<id>` or `channel:<id>` targets (bare numeric ids are ambiguous).
 - **gog** — Google Suite CLI: Gmail, Calendar, Drive, Contacts.
 - **spotify-player** — Terminal Spotify client to search/queue/control playback.
 - **sag** — ElevenLabs speech with mac-style say UX; streams to speakers by default.

docs/start/faq.md

@@ -92,6 +92,31 @@ It also warns if your configured model is unknown or missing auth.
 
 Bun is supported for faster TypeScript execution, but **WhatsApp requires Node** in this ecosystem. The wizard lets you pick the runtime; choose **Node** if you use WhatsApp.
 
+### Can I switch between npm and git installs later?
+
+Yes. Install the other flavor, then run Doctor so the gateway service points at the new entrypoint.
+
+From npm → git:
+
+```bash
+git clone https://github.com/clawdbot/clawdbot.git
+cd clawdbot
+pnpm install
+pnpm build
+pnpm clawdbot doctor
+clawdbot daemon restart
+```
+
+From git → npm:
+
+```bash
+npm install -g clawdbot@latest
+clawdbot doctor
+clawdbot daemon restart
+```
+
+Doctor detects a gateway service entrypoint mismatch and offers to rewrite the service config to match the current install (use `--repair` in automation).
+
 ### Is there a dedicated sandboxing doc?
 
 Yes. See [Sandboxing](/gateway/sandboxing). For Docker-specific setup (full gateway in Docker or sandbox images), see [Docker](/install/docker).
@@ -422,6 +447,8 @@ Clawdbot uses provider‑prefixed IDs like:
 
 Yes. Config supports optional metadata for profiles and an ordering per provider (`auth.order.<provider>`). This does **not** store secrets; it maps IDs to provider/mode and sets rotation order.
 
+Clawdbot may temporarily skip a profile if it’s in a short **cooldown** (rate limits/timeouts/auth failures) or a longer **disabled** state (billing/insufficient credits). To inspect this, run `clawdbot models status --json` and check `auth.unusableProfiles`. Tuning: `auth.cooldowns.billingBackoffHours*`.
+
 You can also set a **per-agent** order override (stored in that agent’s `auth-profiles.json`) via the CLI:
 
 ```bash
@@ -605,6 +632,7 @@ Treat inbound DMs as untrusted input. Defaults are designed to reduce risk:
 - Default behavior on DM‑capable providers is **pairing**:
   - Unknown senders receive a pairing code; the bot does not process their message.
   - Approve with: `clawdbot pairing approve --provider <provider> <code>`
+  - Pending requests are capped at **3 per provider**; check `clawdbot pairing list --provider <provider>` if a code didn’t arrive.
 - Opening DMs publicly requires explicit opt‑in (`dmPolicy: "open"` and allowlist `"*"`).
 
 Run `clawdbot doctor` to surface risky DM policies.

docs/start/getting-started.md

@@ -48,7 +48,12 @@ Windows: use **WSL2** (Ubuntu recommended). WSL2 is strongly recommended; native
 
 ```bash
 npm install -g clawdbot@latest
-# or: pnpm add -g clawdbot@latest
+```
+
+Or:
+
+```bash
+pnpm add -g clawdbot@latest
 ```
 
 ## 2) Run the onboarding wizard (and install the daemon)

docs/start/pairing.md

@@ -25,6 +25,7 @@ Default DM policies are documented in: [Security](/gateway/security)
 Pairing codes:
 - 8 characters, uppercase, no ambiguous chars (`0O1I`).
 - **Expire after 1 hour**. The bot only sends the pairing message when a new request is created (roughly once per hour per sender).
+- Pending DM pairing requests are capped at **3 per provider** by default; additional requests are ignored until one expires or is approved.
 
 ### Approve a sender
 

docs/start/showcase.md

@@ -12,6 +12,94 @@ Real projects from the community. See what people are building with Clawdbot.
 **Want to be featured?** Share your project in [#showcase on Discord](https://discord.gg/clawdbot) or [tag @clawdbot on X](https://x.com/clawdbot).
 </Info>
 
+## 🎥 Clawdbot in Action
+
+Full setup walkthrough (28m) by VelvetShark.
+
+<div
+  style={{
+    position: "relative",
+    paddingBottom: "56.25%",
+    height: 0,
+    overflow: "hidden",
+    borderRadius: 16,
+  }}
+>
+  <iframe
+    src="https://www.youtube-nocookie.com/embed/SaWSPZoPX34"
+    title="ClawdBot: The self-hosted AI that Siri should have been (Full setup)"
+    style={{ position: "absolute", top: 0, left: 0, width: "100%", height: "100%" }}
+    frameBorder="0"
+    loading="lazy"
+    allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
+    allowFullScreen
+  />
+</div>
+
+[Watch on YouTube](https://www.youtube.com/watch?v=SaWSPZoPX34)
+
+## 🆕 Fresh from Discord
+
+<CardGroup cols={2}>
+
+<Card title="Tesco Shop Autopilot" icon="cart-shopping" href="https://x.com/i/status/2009724862470689131">
+  **@marchattonhere** • `automation` `browser` `shopping`
+
+  Weekly meal plan → regulars → book delivery slot → confirm order. No APIs, just browser control.
+
+  <img src="/assets/showcase/tesco-shop.jpg" alt="Tesco shop automation via chat" />
+</Card>
+
+<Card title="SNAG Screenshot-to-Markdown" icon="scissors" href="https://github.com/am-will/snag">
+  **@am-will** • `devtools` `screenshots` `markdown`
+
+  Hotkey a screen region → Gemini vision → instant Markdown in your clipboard.
+
+  <img src="/assets/showcase/snag.png" alt="SNAG screenshot-to-markdown tool" />
+</Card>
+
+<Card title="Agents UI" icon="window-maximize" href="https://releaseflow.net/kitze/agents-ui">
+  **@kitze** • `ui` `skills` `sync`
+
+  Desktop app to manage skills/commands across Agents, Claude, Codex, and Clawdbot.
+
+  <img src="/assets/showcase/agents-ui.jpg" alt="Agents UI app" />
+</Card>
+
+<Card title="Telegram Voice Notes (papla.media)" icon="microphone" href="https://papla.media/docs">
+  **Community** • `voice` `tts` `telegram`
+
+  Wraps papla.media TTS and sends results as Telegram voice notes (no annoying autoplay).
+
+  <img src="/assets/showcase/papla-tts.jpg" alt="Telegram voice note output from TTS" />
+</Card>
+
+<Card title="CodexMonitor" icon="eye" href="https://clawdhub.com/odrobnik/codexmonitor">
+  **@odrobnik** • `devtools` `codex` `brew`
+
+  Homebrew-installed helper to list/inspect/watch local OpenAI Codex sessions (CLI + VS Code).
+
+  <img src="/assets/showcase/codexmonitor.png" alt="CodexMonitor on ClawdHub" />
+</Card>
+
+<Card title="Bambu 3D Printer Control" icon="print" href="https://clawdhub.com/tobiasbischoff/bambu-cli">
+  **@tobiasbischoff** • `hardware` `3d-printing` `skill`
+
+  Control and troubleshoot BambuLab printers: status, jobs, camera, AMS, calibration, and more.
+
+  <img src="/assets/showcase/bambu-cli.png" alt="Bambu CLI skill on ClawdHub" />
+</Card>
+
+<Card title="Vienna Transport (Wiener Linien)" icon="train" href="https://clawdhub.com/hjanuschka/wienerlinien">
+  **@hjanuschka** • `travel` `transport` `skill`
+
+  Real-time departures, disruptions, elevator status, and routing for Vienna's public transport.
+
+  <img src="/assets/showcase/wienerlinien.png" alt="Wiener Linien skill on ClawdHub" />
+</Card>
+
+</CardGroup>
+
 ## 🤖 Automation & Workflows
 
 <CardGroup cols={2}>

docs/start/wizard.md

@@ -77,8 +77,11 @@ Tip: `--json` does **not** imply non-interactive mode. Use `--non-interactive` (
    - **OpenAI Codex OAuth**: browser flow; paste the `code#state`.
      - Sets `agents.defaults.model` to `openai-codex/gpt-5.2` when model is unset or `openai/*`.
    - **OpenAI API key**: uses `OPENAI_API_KEY` if present or prompts for a key, then saves it to `~/.clawdbot/.env` so launchd can read it.
+   - **OpenCode Zen (multi-model proxy)**: prompts for `OPENCODE_ZEN_API_KEY` (get it at https://opencode.ai/auth).
    - **API key**: stores the key for you.
-   - **Minimax M2.1 (LM Studio)**: config is auto‑written for the LM Studio endpoint.
+   - **MiniMax M2.1 (minimax.io)**: config is auto‑written for the OpenAI-compatible `/v1` endpoint.
+   - **MiniMax API (platform.minimax.io)**: config is auto‑written for the Anthropic-compatible `/anthropic` endpoint.
+   - **MiniMax M2.1 (LM Studio)**: config is auto‑written for the LM Studio endpoint.
    - **Skip**: no auth configured yet.
    - Wizard runs a model check and warns if the configured model is unknown or missing auth.
   - OAuth credentials live in `~/.clawdbot/credentials/oauth.json`; auth profiles live in `~/.clawdbot/agents/<agentId>/agent/auth-profiles.json` (API keys + OAuth).
@@ -183,6 +186,17 @@ clawdbot onboard --non-interactive \
   --gateway-bind loopback
 ```
 
+OpenCode Zen example:
+
+```bash
+clawdbot onboard --non-interactive \
+  --mode local \
+  --auth-choice opencode-zen \
+  --opencode-zen-api-key "$OPENCODE_ZEN_API_KEY" \
+  --gateway-port 18789 \
+  --gateway-bind loopback
+```
+
 Add agent (non‑interactive) example:
 
 ```bash

docs/tools/elevated.md

@@ -12,7 +12,7 @@ read_when:
 - Only `on|off` are accepted; anything else returns a hint and does not change state.
 
 ## What it controls (and what it doesn’t)
-- **Global availability gate**: `tools.elevated` is global (not per-agent). If disabled or sender not allowlisted, elevated is unavailable everywhere.
+- **Availability gates**: `tools.elevated` is the global baseline. `agents.list[].tools.elevated` can further restrict elevated per agent (both must allow).
 - **Per-session state**: `/elevated on|off` sets the elevated level for the current session key.
 - **Inline directive**: `/elevated on` inside a message applies to that message only.
 - **Groups**: In group chats, elevated directives are only honored when the agent is mentioned. Command-only messages that bypass mention requirements are treated as mentioned.
@@ -42,8 +42,10 @@ Note:
 ## Availability + allowlists
 - Feature gate: `tools.elevated.enabled` (default can be off via config even if the code supports it).
 - Sender allowlist: `tools.elevated.allowFrom` with per-provider allowlists (e.g. `discord`, `whatsapp`).
-- Both must pass; otherwise elevated is treated as unavailable.
-- Discord fallback: if `tools.elevated.allowFrom.discord` is omitted, the `discord.dm.allowFrom` list is used as a fallback. Set `tools.elevated.allowFrom.discord` (even `[]`) to override.
+- Per-agent gate: `agents.list[].tools.elevated.enabled` (optional; can only further restrict).
+- Per-agent allowlist: `agents.list[].tools.elevated.allowFrom` (optional; when set, the sender must match **both** global + per-agent allowlists).
+- Discord fallback: if `tools.elevated.allowFrom.discord` is omitted, the `discord.dm.allowFrom` list is used as a fallback. Set `tools.elevated.allowFrom.discord` (even `[]`) to override. Per-agent allowlists do **not** use the fallback.
+- All gates must pass; otherwise elevated is treated as unavailable.
 
 ## Logging + status
 - Elevated bash calls are logged at info level.

docs/tools/index.md

@@ -39,7 +39,7 @@ Notes:
 - Returns `status: "running"` with a `sessionId` when backgrounded.
 - Use `process` to poll/log/write/kill/clear background sessions.
 - If `process` is disallowed, `bash` runs synchronously and ignores `yieldMs`/`background`.
-- `elevated` is gated by `tools.elevated` (global sender allowlist) and runs on the host.
+- `elevated` is gated by `tools.elevated` plus any `agents.list[].tools.elevated` override (both must allow) and runs on the host.
 - `elevated` only changes behavior when the agent is sandboxed (otherwise it’s a no-op).
 
 ### `process`
@@ -193,7 +193,7 @@ Notes:
 - Use `delayMs` (defaults to 2000) to avoid interrupting an in-flight reply.
 - `restart` is disabled by default; enable with `commands.restart: true`.
 
-### `sessions_list` / `sessions_history` / `sessions_send` / `sessions_spawn`
+### `sessions_list` / `sessions_history` / `sessions_send` / `sessions_spawn` / `session_status`
 List sessions, inspect transcript history, or send to another session.
 
 Core parameters:
@@ -201,11 +201,13 @@ Core parameters:
 - `sessions_history`: `sessionKey`, `limit?`, `includeTools?`
 - `sessions_send`: `sessionKey`, `message`, `timeoutSeconds?` (0 = fire-and-forget)
 - `sessions_spawn`: `task`, `label?`, `agentId?`, `model?`, `runTimeoutSeconds?`, `cleanup?`
+- `session_status`: `sessionKey?` (default current), `model?` (`default` clears override)
 
 Notes:
 - `main` is the canonical direct-chat key; global/unknown are hidden.
 - `messageLimit > 0` fetches last N messages per session (tool messages filtered).
 - `sessions_send` waits for final completion when `timeoutSeconds > 0`.
+- Delivery/announce happens after completion and is best-effort; `status: "ok"` confirms the agent run finished, not that the announce was delivered.
 - `sessions_spawn` starts a sub-agent run and posts an announce reply back to the requester chat.
 - `sessions_spawn` is non-blocking and returns `status: "accepted"` immediately.
 - `sessions_send` runs a reply‑back ping‑pong (reply `REPLY_SKIP` to stop; max turns via `session.agentToAgent.maxPingPongTurns`, 0–5).

docs/tools/reactions.md

@@ -16,3 +16,4 @@ Provider notes:
 - **Discord/Slack**: empty `emoji` removes all of the bot's reactions on the message; `remove: true` removes just that emoji.
 - **Telegram**: `remove: true` removes your own reaction (Bot API limitation).
 - **WhatsApp**: `remove: true` maps to empty emoji (remove bot reaction).
+- **Signal**: inbound reaction notifications emit system events when `signal.reactionNotifications` is enabled.

docs/tools/slash-commands.md

@@ -48,7 +48,7 @@ Text + native (when enabled):
 - `/reset` or `/new`
 - `/think <level>` (aliases: `/thinking`, `/t`)
 - `/verbose on|off` (alias: `/v`)
-- `/reasoning on|off|stream` (alias: `/reason`; `stream` = Telegram draft only)
+- `/reasoning on|off|stream` (alias: `/reason`; when on, sends a separate message prefixed `Reasoning:`; `stream` = Telegram draft only)
 - `/elevated on|off` (alias: `/elev`)
 - `/model <name>` (alias: `/models`; or `/<alias>` from `agents.defaults.models.*.alias`)
 - `/queue <mode>` (plus options like `debounce:2s cap:25 drop:summarize`; send `/queue` to see current settings)

docs/tools/subagents.md

@@ -98,3 +98,4 @@ Sub-agents use a dedicated in-process queue lane:
 - Sub-agent announce is **best-effort**. If the gateway restarts, pending “announce back” work is lost.
 - Sub-agents still share the same gateway process resources; treat `maxConcurrent` as a safety valve.
 - `sessions_spawn` is always non-blocking: it returns `{ status: "accepted", runId, childSessionKey }` immediately.
+- Sub-agent context only injects `AGENTS.md` + `TOOLS.md` (no `SOUL.md`, `IDENTITY.md`, `USER.md`, `HEARTBEAT.md`, or `BOOTSTRAP.md`).

docs/tools/thinking.md

@@ -32,14 +32,15 @@ read_when:
 ## Verbose directives (/verbose or /v)
 - Levels: `on|full` or `off` (default).
 - Directive-only message toggles session verbose and replies `Verbose logging enabled.` / `Verbose logging disabled.`; invalid levels return a hint without changing state.
+- `/verbose off` stores an explicit session override; clear it via the Sessions UI by choosing `inherit`.
 - Inline directive affects only that message; session/global defaults apply otherwise.
 - Send `/verbose` (or `/verbose:`) with no argument to see the current verbose level.
 - When verbose is on, agents that emit structured tool results (Pi, other JSON agents) send each tool result back as its own metadata-only message, prefixed with `<emoji> <tool-name>: <arg>` when available (path/command); the tool output itself is not forwarded. These tool summaries are sent as soon as each tool finishes (separate bubbles), not as streaming deltas. If you toggle `/verbose on|off` while a run is in-flight, subsequent tool bubbles honor the new setting.
 
 ## Reasoning visibility (/reasoning)
 - Levels: `on|off|stream`.
-- Directive-only message toggles whether thinking blocks are shown as italic text in replies.
-- When enabled, any model-provided reasoning content is appended as a separate italic block.
+- Directive-only message toggles whether thinking blocks are shown in replies.
+- When enabled, reasoning is sent as a **separate message** prefixed with `Reasoning:`.
 - `stream` (Telegram only): streams reasoning into the Telegram draft bubble while the reply is generating, then sends the final answer without reasoning.
 - Alias: `/reason`.
 - Send `/reasoning` (or `/reasoning:`) with no argument to see the current reasoning level.

docs/tui.md

@@ -109,7 +109,7 @@ Session lifecycle:
 - `--session <key>`: Session key (default: `main`, or `global` when scope is global)
 - `--deliver`: Deliver assistant replies to the provider (default off)
 - `--thinking <level>`: Override thinking level for sends
-- `--timeout-ms <ms>`: Agent timeout (default 30000)
+- `--timeout-ms <ms>`: Agent timeout in ms (defaults to `agents.defaults.timeoutSeconds`)
 - `--history-limit <n>`: History entries to load (default 200)
 
 ## Troubleshooting

docs/web/tui.md

@@ -30,7 +30,7 @@ Use SSH tunneling or Tailscale to reach the Gateway WS.
 - `--session <key>`: Session key (default: `main`, or `global` when scope is global).
 - `--deliver`: Deliver assistant replies to the provider (default off).
 - `--thinking <level>`: Override thinking level for sends.
-- `--timeout-ms <ms>`: Agent timeout in ms (default 30000).
+- `--timeout-ms <ms>`: Agent timeout in ms (defaults to `agents.defaults.timeoutSeconds`).
 - `--history-limit <n>`: History entries to load (default 200).
 
 ## Controls

package.json

@@ -1,6 +1,6 @@
 {
   "name": "clawdbot",
-  "version": "2026.1.8-2",
+  "version": "2026.1.9",
   "description": "WhatsApp gateway CLI (Baileys web) with Pi RPC agent",
   "type": "module",
   "main": "dist/index.js",
@@ -66,11 +66,24 @@
     "clawdbot": "tsx src/entry.ts",
     "gateway:watch": "tsx watch src/entry.ts gateway --force",
     "clawdbot:rpc": "tsx src/entry.ts agent --mode rpc --json",
+    "ios:gen": "cd apps/ios && xcodegen generate",
+    "ios:open": "cd apps/ios && xcodegen generate && open Clawdbot.xcodeproj",
+    "ios:build": "bash -lc 'cd apps/ios && xcodegen generate && xcodebuild -project Clawdbot.xcodeproj -scheme Clawdbot -destination \"${IOS_DEST:-platform=iOS Simulator,name=iPhone 17}\" -configuration Debug build'",
+    "ios:run": "bash -lc 'cd apps/ios && xcodegen generate && xcodebuild -project Clawdbot.xcodeproj -scheme Clawdbot -destination \"${IOS_DEST:-platform=iOS Simulator,name=iPhone 17}\" -configuration Debug build && xcrun simctl boot \"${IOS_SIM:-iPhone 17}\" || true && xcrun simctl launch booted com.clawdbot.ios'",
+    "android:assemble": "cd apps/android && ./gradlew :app:assembleDebug",
+    "android:install": "cd apps/android && ./gradlew :app:installDebug",
+    "android:run": "cd apps/android && ./gradlew :app:installDebug && adb shell am start -n com.clawdbot.android/.MainActivity",
+    "android:test": "cd apps/android && ./gradlew :app:testDebugUnitTest",
+    "mac:restart": "bash scripts/restart-mac.sh",
+    "mac:package": "bash scripts/package-mac-app.sh",
+    "mac:open": "open dist/Clawdbot.app",
     "lint": "biome check src test && oxlint --type-aware src test --ignore-pattern src/canvas-host/a2ui/a2ui.bundle.js",
     "lint:swift": "swiftlint lint --config .swiftlint.yml && (cd apps/ios && swiftlint lint --config .swiftlint.yml)",
+    "lint:all": "pnpm lint && pnpm lint:swift",
     "lint:fix": "biome check --write --unsafe src && biome format --write src",
     "format": "biome format src",
     "format:swift": "swiftformat --lint --config .swiftformat apps/macos/Sources apps/ios/Sources apps/shared/ClawdbotKit/Sources",
+    "format:all": "pnpm format && pnpm format:swift",
     "format:fix": "biome format src --write",
     "test": "vitest run",
     "test:watch": "vitest",
@@ -94,15 +107,15 @@
   },
   "packageManager": "pnpm@10.23.0",
   "dependencies": {
-    "@buape/carbon": "0.0.0-beta-20260109165250",
+    "@buape/carbon": "0.0.0-beta-20260109194934",
     "@clack/prompts": "^0.11.0",
     "@grammyjs/runner": "^2.0.3",
     "@grammyjs/transformer-throttler": "^1.2.1",
     "@homebridge/ciao": "^1.3.4",
-    "@mariozechner/pi-agent-core": "^0.41.0",
-    "@mariozechner/pi-ai": "^0.41.0",
-    "@mariozechner/pi-coding-agent": "^0.41.0",
-    "@mariozechner/pi-tui": "^0.41.0",
+    "@mariozechner/pi-agent-core": "^0.42.1",
+    "@mariozechner/pi-ai": "^0.42.1",
+    "@mariozechner/pi-coding-agent": "^0.42.1",
+    "@mariozechner/pi-tui": "^0.42.1",
     "@microsoft/agents-hosting": "^1.1.1",
     "@microsoft/agents-hosting-express": "^1.1.1",
     "@microsoft/agents-hosting-extensions-teams": "^1.1.1",
@@ -156,7 +169,7 @@
     "lucide": "^0.562.0",
     "ollama": "^0.6.3",
     "oxlint": "^1.38.0",
-    "oxlint-tsgolint": "^0.10.1",
+    "oxlint-tsgolint": "^0.11.0",
     "quicktype-core": "^23.2.6",
     "rolldown": "1.0.0-beta.59",
     "signal-utils": "^0.21.1",
@@ -170,6 +183,7 @@
       "@sinclair/typebox": "0.34.47"
     },
     "patchedDependencies": {
+      "@buape/carbon": "patches/@buape__carbon.patch",
       "@mariozechner/pi-agent-core": "patches/@mariozechner__pi-agent-core.patch",
       "@mariozechner/pi-coding-agent": "patches/@mariozechner__pi-coding-agent.patch",
       "@mariozechner/pi-ai": "patches/@mariozechner__pi-ai.patch"
@@ -208,6 +222,7 @@
     ]
   },
   "patchedDependencies": {
+    "@buape/carbon": "patches/@buape__carbon.patch",
     "@mariozechner/pi-agent-core": "patches/@mariozechner__pi-agent-core.patch",
     "@mariozechner/pi-coding-agent": "patches/@mariozechner__pi-coding-agent.patch",
     "@mariozechner/pi-ai": "patches/@mariozechner__pi-ai.patch",

patches/@buape__carbon.patch

@@ -0,0 +1,53 @@
+--- a/dist/src/classes/RequestClient.js
++++ b/dist/src/classes/RequestClient.js
+@@ -118,6 +118,9 @@
+             }
+         }
+         this.abortController = new AbortController();
++        const timeoutMs = typeof this.options.timeout === "number" && this.options.timeout > 0
++            ? this.options.timeout
++            : undefined;
+         let body;
+         if (data?.body &&
+             typeof data.body === "object" &&
+@@ -178,12 +181,26 @@
+                 body = JSON.stringify(data.body);
+             }
+         }
+-        const response = await fetch(url, {
+-            method,
+-            headers,
+-            body,
+-            signal: this.abortController.signal
+-        });
++        let timeoutId;
++        if (timeoutMs !== undefined) {
++            timeoutId = setTimeout(() => {
++                this.abortController?.abort();
++            }, timeoutMs);
++        }
++        let response;
++        try {
++            response = await fetch(url, {
++                method,
++                headers,
++                body,
++                signal: this.abortController.signal
++            });
++        }
++        finally {
++            if (timeoutId) {
++                clearTimeout(timeoutId);
++            }
++        }
+         let rawBody = "";
+         let parsedBody;
+         try {
+@@ -405,4 +422,4 @@
+     }
+ }
+ const sleep = (ms) => new Promise((resolve) => setTimeout(resolve, Math.max(ms, 0)));
+-//# sourceMappingURL=RequestClient.js.map
+\ No newline at end of file
++//# sourceMappingURL=RequestClient.js.map
+

pnpm-lock.yaml

@@ -23,8 +23,8 @@ importers:
   .:
     dependencies:
       '@buape/carbon':
-        specifier: 0.0.0-beta-20260109165250
-        version: 0.0.0-beta-20260109165250(hono@4.11.3)
+        specifier: 0.0.0-beta-20260109194934
+        version: 0.0.0-beta-20260109194934(hono@4.11.3)
       '@clack/prompts':
         specifier: ^0.11.0
         version: 0.11.0
@@ -38,17 +38,17 @@ importers:
         specifier: ^1.3.4
         version: 1.3.4
       '@mariozechner/pi-agent-core':
-        specifier: ^0.41.0
-        version: 0.41.0(patch_hash=01312ceb1f6be7e42822c24c9a7a4f7db56b24ae114a364855bd3819779d1cf4)(ws@8.19.0)(zod@4.3.5)
+        specifier: ^0.42.1
+        version: 0.42.1(patch_hash=01312ceb1f6be7e42822c24c9a7a4f7db56b24ae114a364855bd3819779d1cf4)(ws@8.19.0)(zod@4.3.5)
       '@mariozechner/pi-ai':
-        specifier: ^0.41.0
-        version: 0.41.0(patch_hash=3f4c1f943c57dbe2980bf21b1768dc780355f9124eeffbc30b5d5e42d2ea4b7c)(ws@8.19.0)(zod@4.3.5)
+        specifier: ^0.42.1
+        version: 0.42.1(patch_hash=3f4c1f943c57dbe2980bf21b1768dc780355f9124eeffbc30b5d5e42d2ea4b7c)(ws@8.19.0)(zod@4.3.5)
       '@mariozechner/pi-coding-agent':
-        specifier: ^0.41.0
-        version: 0.41.0(patch_hash=58af7c712ebe270527c2ad9d3351fac39d6cd4b81cc475a258d87840b446b90e)(ws@8.19.0)(zod@4.3.5)
+        specifier: ^0.42.1
+        version: 0.42.1(patch_hash=58af7c712ebe270527c2ad9d3351fac39d6cd4b81cc475a258d87840b446b90e)(ws@8.19.0)(zod@4.3.5)
       '@mariozechner/pi-tui':
-        specifier: ^0.41.0
-        version: 0.41.0
+        specifier: ^0.42.1
+        version: 0.42.1
       '@microsoft/agents-hosting':
         specifier: ^1.1.1
         version: 1.1.1
@@ -202,10 +202,10 @@ importers:
         version: 0.6.3
       oxlint:
         specifier: ^1.38.0
-        version: 1.38.0(oxlint-tsgolint@0.10.1)
+        version: 1.38.0(oxlint-tsgolint@0.11.0)
       oxlint-tsgolint:
-        specifier: ^0.10.1
-        version: 0.10.1
+        specifier: ^0.11.0
+        version: 0.11.0
       quicktype-core:
         specifier: ^23.2.6
         version: 23.2.6
@@ -372,8 +372,8 @@ packages:
   '@borewit/text-codec@0.2.1':
     resolution: {integrity: sha512-k7vvKPbf7J2fZ5klGRD9AeKfUvojuZIQ3BT5u7Jfv+puwXkUBUT5PVyMDfJZpy30CBDXGMgw7fguK/lpOMBvgw==}
 
-  '@buape/carbon@0.0.0-beta-20260109165250':
-    resolution: {integrity: sha512-Xt8W0RYZxaprp2YxMU1rZRfGkHQWEJ2KZUurMwK/G4WVTfJSWAUeaeOGhpO40fCm/g0iPMuSLgQ4eudGOQHigw==}
+  '@buape/carbon@0.0.0-beta-20260109194934':
+    resolution: {integrity: sha512-rtyoOhtihd25k8ABHf+BTCOQSF3XjUMX+TPtS7UATC3dWVE8BXvmrLeX+s7q1LBh0LLRiz6w1YtGL145laoSJA==}
 
   '@cacheable/memory@2.0.7':
     resolution: {integrity: sha512-RbxnxAMf89Tp1dLhXMS7ceft/PGsDl1Ip7T20z5nZ+pwIAsQ1p2izPjVG69oCLv/jfQ7HDPHTWK0c9rcAWXN3A==}
@@ -851,22 +851,22 @@ packages:
     peerDependencies:
       lit: ^3.3.1
 
-  '@mariozechner/pi-agent-core@0.41.0':
-    resolution: {integrity: sha512-eXmnMWCeRnSjvF5nbC8LbiOhdcSuUG/p+ZzfZqhfzkc5JMKGccGPnEHzXwfrVkJpyqL0rIWi9cG0yelVAat30A==}
+  '@mariozechner/pi-agent-core@0.42.1':
+    resolution: {integrity: sha512-sIRB1jHheQSGONoVorrQ3X9vc1JFLoAe+48k7UJmpLAhJXnQmRtq1+CtzvKOVe5qVRyNBNuNdXipH+seicbwvQ==}
     engines: {node: '>=20.0.0'}
 
-  '@mariozechner/pi-ai@0.41.0':
-    resolution: {integrity: sha512-ZcI+lFMbf35kQvppHa4hy5tu34GiH5WYwWxPD7BHm7AiYxPcytdP+0NiaJdLIRGSLZqKklXDDejbb6/QvOwI3w==}
+  '@mariozechner/pi-ai@0.42.1':
+    resolution: {integrity: sha512-uRiH+s7EPDz9Q7hjQJ4Mm8lU4e4/C8pB4rnqGds73B5/0rqZb8DeSBukKU6uOwMNkXol/tYgnkEqXy7qEoHLJQ==}
     engines: {node: '>=20.0.0'}
     hasBin: true
 
-  '@mariozechner/pi-coding-agent@0.41.0':
-    resolution: {integrity: sha512-+x5tPGxjsT5d9u48xvTwayHW/v+w7L/zK1Oyyfhpu8qqSqkM5G5jeqK3tqQREG2YE+PwPSozmDtVzHYPrcNamA==}
+  '@mariozechner/pi-coding-agent@0.42.1':
+    resolution: {integrity: sha512-BsLgFBC//98EdQCCoNYPfxKi2TEJ64a9w/CQC8/DyeAVhjrdJELUd+3EoRV6iiodbpUspUASW9w3ELoqQGAtoA==}
     engines: {node: '>=20.0.0'}
     hasBin: true
 
-  '@mariozechner/pi-tui@0.41.0':
-    resolution: {integrity: sha512-FxhNyQfsQvZJBbUIPbtvBzF8yJo2JjEXVksn5cUU8Qphw8z1Uf+bRXeleH7Q7VVvGnaH9zJR3r2cfkaWxC1Jig==}
+  '@mariozechner/pi-tui@0.42.1':
+    resolution: {integrity: sha512-dsmzcOjD+9MNgqnJ6/BJ255Sc9KQWN4Asyh1ron7bMA4Q9lqSWl6q8dk78DBp2QcVeWHtvqbwdZwNnDwWyxw3g==}
     engines: {node: '>=20.0.0'}
 
   '@microsoft/agents-activity@1.1.1':
@@ -906,33 +906,33 @@ packages:
   '@oxc-project/types@0.107.0':
     resolution: {integrity: sha512-QFDRbYfV2LVx8tyqtyiah3jQPUj1mK2+RYwxyFWyGoys6XJnwTdlzO6rdNNHOPorHAu5Uo34oWRKcvNpbJarmQ==}
 
-  '@oxlint-tsgolint/darwin-arm64@0.10.1':
-    resolution: {integrity: sha512-KGC4++BeEqrIcmDHiJt/e6/860PWJmUJjjp0mE+smpBmRXMjmOFFjrPmN+ZyCyVgf1WdmhPkQXsRSPeTR+2omw==}
+  '@oxlint-tsgolint/darwin-arm64@0.11.0':
+    resolution: {integrity: sha512-F67T8dXgYIrgv6wpd52fKQFdmieSOHaxBkscgso64YdtEHrV3s52ASiZGNzw62TKihn9Ox9ek3PYx9XsxIJDUw==}
     cpu: [arm64]
     os: [darwin]
 
-  '@oxlint-tsgolint/darwin-x64@0.10.1':
-    resolution: {integrity: sha512-tvmrDgj3Q0tdc+zMWfCVLVq8EQDEUqasm1zaWgSMYIszpID6qdgqbT+OpWWXV9fLZgtvrkoXGwxkHAUJzdVZXQ==}
+  '@oxlint-tsgolint/darwin-x64@0.11.0':
+    resolution: {integrity: sha512-z44LO7+3z2mtcBxA9T66yEy/otp/2r5ypbkx7EYlPwbEqBAIDRt/8hqQ9/BUC//1qE549P1cBU6NjhgeyuXjYQ==}
     cpu: [x64]
     os: [darwin]
 
-  '@oxlint-tsgolint/linux-arm64@0.10.1':
-    resolution: {integrity: sha512-7kD28z6/ykGx8WetKTPRZt30pd+ziassxg/8cM24lhjUI+hNXyRHVtHes73dh9D6glJKno+1ut+3amUdZBZcpQ==}
+  '@oxlint-tsgolint/linux-arm64@0.11.0':
+    resolution: {integrity: sha512-IeIjmpPi2j2Dn1CRizGikysyLp9B0q3jqiAalv9ewRyb8hqQW5YeMlsswo8pHd0Hz3KyFfone0NkvBt77Ex2pg==}
     cpu: [arm64]
     os: [linux]
 
-  '@oxlint-tsgolint/linux-x64@0.10.1':
-    resolution: {integrity: sha512-NmJmiqdzYUTHIxteSTyX6IFFgnIsOAjRWXfrS6Jbo5xlB3g39WHniSF3asB/khLJNtwSg4InUS34NprYM7zrEw==}
+  '@oxlint-tsgolint/linux-x64@0.11.0':
+    resolution: {integrity: sha512-fpYGYU2pXjaXYnKgWrihFXE8zJiTRjYKSHAaBaVI056oqKjKGEoU2BfFbddpBrKgz9TmSOX/NGftrJnyMn1wXQ==}
     cpu: [x64]
     os: [linux]
 
-  '@oxlint-tsgolint/win32-arm64@0.10.1':
-    resolution: {integrity: sha512-3KrT80vl3nXUkjuJI/z8dF6xWsKx0t9Tz4ZQHgQw3fYw+CoihBRWGklrdlmCz+EGfMyVaQLqBV9PZckhSqLe2A==}
+  '@oxlint-tsgolint/win32-arm64@0.11.0':
+    resolution: {integrity: sha512-37nzks9eqBt7NYE6okquu51vaqMruF5voX475L16Y8asJVCGpO/2VSy3ulYAXhZ+5Kdc8ZgrljVViJOjfPEPaA==}
     cpu: [arm64]
     os: [win32]
 
-  '@oxlint-tsgolint/win32-x64@0.10.1':
-    resolution: {integrity: sha512-hW1fSJZVxG51sLdGq1sQjOzb1tsQ23z/BquJfUwL7CqBobxr7TJvGmoINL+9KryOJt0jCoaiMfWe4yoYw5XfIA==}
+  '@oxlint-tsgolint/win32-x64@0.11.0':
+    resolution: {integrity: sha512-TsK4C61+mjmbkUJ3Q3E9Ev3VFbeI6prPEAm9FAOq8VsfUGEiIUBBjrZ8ysGoQXNiU3dCKpmu012ptVUZTk5/eg==}
     cpu: [x64]
     os: [win32]
 
@@ -2542,8 +2542,8 @@ packages:
     resolution: {integrity: sha512-GJR9XnS8dQ+sAdbhX90RA4WbmEyrso7X9aHMws4MaQ2GRpfEjnOUSZIdOXJQfnIfBoy9oCc7US/MNFCyuJQzjg==}
     engines: {node: '>=20'}
 
-  oxlint-tsgolint@0.10.1:
-    resolution: {integrity: sha512-EEHNdo5cW2w1xwYdBQ7d3IXDqWAtMkfVFrh+9gQ4kYbYJwygY4QXSh1eH80/xVipZdVKujAwBgg/nNNHk56kxQ==}
+  oxlint-tsgolint@0.11.0:
+    resolution: {integrity: sha512-fGYb7z/cljC0Rjtbxh7mIe8vtF/M9TShLvniwc2rdcqNG3Z9g3nM01cr2kWRb1DZdbY4/kItvIsrV4uhaMifyQ==}
     hasBin: true
 
   oxlint@1.38.0:
@@ -3374,7 +3374,7 @@ snapshots:
 
   '@borewit/text-codec@0.2.1': {}
 
-  '@buape/carbon@0.0.0-beta-20260109165250(hono@4.11.3)':
+  '@buape/carbon@0.0.0-beta-20260109194934(hono@4.11.3)':
     dependencies:
       '@types/node': 24.10.4
       discord-api-types: 0.38.36
@@ -3781,10 +3781,10 @@ snapshots:
     transitivePeerDependencies:
       - tailwindcss
 
-  '@mariozechner/pi-agent-core@0.41.0(patch_hash=01312ceb1f6be7e42822c24c9a7a4f7db56b24ae114a364855bd3819779d1cf4)(ws@8.19.0)(zod@4.3.5)':
+  '@mariozechner/pi-agent-core@0.42.1(patch_hash=01312ceb1f6be7e42822c24c9a7a4f7db56b24ae114a364855bd3819779d1cf4)(ws@8.19.0)(zod@4.3.5)':
     dependencies:
-      '@mariozechner/pi-ai': 0.41.0(patch_hash=3f4c1f943c57dbe2980bf21b1768dc780355f9124eeffbc30b5d5e42d2ea4b7c)(ws@8.19.0)(zod@4.3.5)
-      '@mariozechner/pi-tui': 0.41.0
+      '@mariozechner/pi-ai': 0.42.1(patch_hash=3f4c1f943c57dbe2980bf21b1768dc780355f9124eeffbc30b5d5e42d2ea4b7c)(ws@8.19.0)(zod@4.3.5)
+      '@mariozechner/pi-tui': 0.42.1
     transitivePeerDependencies:
       - '@modelcontextprotocol/sdk'
       - bufferutil
@@ -3793,7 +3793,7 @@ snapshots:
       - ws
       - zod
 
-  '@mariozechner/pi-ai@0.41.0(patch_hash=3f4c1f943c57dbe2980bf21b1768dc780355f9124eeffbc30b5d5e42d2ea4b7c)(ws@8.19.0)(zod@4.3.5)':
+  '@mariozechner/pi-ai@0.42.1(patch_hash=3f4c1f943c57dbe2980bf21b1768dc780355f9124eeffbc30b5d5e42d2ea4b7c)(ws@8.19.0)(zod@4.3.5)':
     dependencies:
       '@anthropic-ai/sdk': 0.71.2(zod@4.3.5)
       '@google/genai': 1.34.0
@@ -3813,12 +3813,12 @@ snapshots:
       - ws
       - zod
 
-  '@mariozechner/pi-coding-agent@0.41.0(patch_hash=58af7c712ebe270527c2ad9d3351fac39d6cd4b81cc475a258d87840b446b90e)(ws@8.19.0)(zod@4.3.5)':
+  '@mariozechner/pi-coding-agent@0.42.1(patch_hash=58af7c712ebe270527c2ad9d3351fac39d6cd4b81cc475a258d87840b446b90e)(ws@8.19.0)(zod@4.3.5)':
     dependencies:
       '@mariozechner/clipboard': 0.3.0
-      '@mariozechner/pi-agent-core': 0.41.0(patch_hash=01312ceb1f6be7e42822c24c9a7a4f7db56b24ae114a364855bd3819779d1cf4)(ws@8.19.0)(zod@4.3.5)
-      '@mariozechner/pi-ai': 0.41.0(patch_hash=3f4c1f943c57dbe2980bf21b1768dc780355f9124eeffbc30b5d5e42d2ea4b7c)(ws@8.19.0)(zod@4.3.5)
-      '@mariozechner/pi-tui': 0.41.0
+      '@mariozechner/pi-agent-core': 0.42.1(patch_hash=01312ceb1f6be7e42822c24c9a7a4f7db56b24ae114a364855bd3819779d1cf4)(ws@8.19.0)(zod@4.3.5)
+      '@mariozechner/pi-ai': 0.42.1(patch_hash=3f4c1f943c57dbe2980bf21b1768dc780355f9124eeffbc30b5d5e42d2ea4b7c)(ws@8.19.0)(zod@4.3.5)
+      '@mariozechner/pi-tui': 0.42.1
       chalk: 5.6.2
       cli-highlight: 2.1.11
       diff: 8.0.2
@@ -3837,7 +3837,7 @@ snapshots:
       - ws
       - zod
 
-  '@mariozechner/pi-tui@0.41.0':
+  '@mariozechner/pi-tui@0.42.1':
     dependencies:
       '@types/mime-types': 2.1.4
       chalk: 5.6.2
@@ -3907,22 +3907,22 @@ snapshots:
 
   '@oxc-project/types@0.107.0': {}
 
-  '@oxlint-tsgolint/darwin-arm64@0.10.1':
+  '@oxlint-tsgolint/darwin-arm64@0.11.0':
     optional: true
 
-  '@oxlint-tsgolint/darwin-x64@0.10.1':
+  '@oxlint-tsgolint/darwin-x64@0.11.0':
     optional: true
 
-  '@oxlint-tsgolint/linux-arm64@0.10.1':
+  '@oxlint-tsgolint/linux-arm64@0.11.0':
     optional: true
 
-  '@oxlint-tsgolint/linux-x64@0.10.1':
+  '@oxlint-tsgolint/linux-x64@0.11.0':
     optional: true
 
-  '@oxlint-tsgolint/win32-arm64@0.10.1':
+  '@oxlint-tsgolint/win32-arm64@0.11.0':
     optional: true
 
-  '@oxlint-tsgolint/win32-x64@0.10.1':
+  '@oxlint-tsgolint/win32-x64@0.11.0':
     optional: true
 
   '@oxlint/darwin-arm64@1.38.0':
@@ -5572,16 +5572,16 @@ snapshots:
 
   osc-progress@0.2.0: {}
 
-  oxlint-tsgolint@0.10.1:
+  oxlint-tsgolint@0.11.0:
     optionalDependencies:
-      '@oxlint-tsgolint/darwin-arm64': 0.10.1
-      '@oxlint-tsgolint/darwin-x64': 0.10.1
-      '@oxlint-tsgolint/linux-arm64': 0.10.1
-      '@oxlint-tsgolint/linux-x64': 0.10.1
-      '@oxlint-tsgolint/win32-arm64': 0.10.1
-      '@oxlint-tsgolint/win32-x64': 0.10.1
+      '@oxlint-tsgolint/darwin-arm64': 0.11.0
+      '@oxlint-tsgolint/darwin-x64': 0.11.0
+      '@oxlint-tsgolint/linux-arm64': 0.11.0
+      '@oxlint-tsgolint/linux-x64': 0.11.0
+      '@oxlint-tsgolint/win32-arm64': 0.11.0
+      '@oxlint-tsgolint/win32-x64': 0.11.0
 
-  oxlint@1.38.0(oxlint-tsgolint@0.10.1):
+  oxlint@1.38.0(oxlint-tsgolint@0.11.0):
     optionalDependencies:
       '@oxlint/darwin-arm64': 1.38.0
       '@oxlint/darwin-x64': 1.38.0
@@ -5591,7 +5591,7 @@ snapshots:
       '@oxlint/linux-x64-musl': 1.38.0
       '@oxlint/win32-arm64': 1.38.0
       '@oxlint/win32-x64': 1.38.0
-      oxlint-tsgolint: 0.10.1
+      oxlint-tsgolint: 0.11.0
 
   p-finally@1.0.0: {}
 

scripts/e2e/onboard-docker.sh

@@ -12,6 +12,7 @@ docker run --rm -t "$IMAGE_NAME" bash -lc '
   set -euo pipefail
   trap "" PIPE
   export TERM=xterm-256color
+  ONBOARD_FLAGS="--flow quickstart --auth-choice skip --skip-providers --skip-skills --skip-daemon --skip-ui"
 
   # Provide a minimal trash shim to avoid noisy "missing trash" logs in containers.
   export PATH="/tmp/clawdbot-bin:$PATH"
@@ -42,7 +43,7 @@ TRASH
   }
 
   start_gateway() {
-    node dist/index.js gateway --port 18789 --bind loopback > /tmp/gateway-e2e.log 2>&1 &
+    node dist/index.js gateway --port 18789 --bind loopback --allow-unconfigured > /tmp/gateway-e2e.log 2>&1 &
     GATEWAY_PID="$!"
   }
 
@@ -71,6 +72,7 @@ TRASH
     local command="$3"
     local send_fn="$4"
     local with_gateway="${5:-false}"
+    local validate_fn="${6:-}"
 
     echo "== Wizard case: $case_name =="
     export HOME="$home_dir"
@@ -78,8 +80,9 @@ TRASH
 
     input_fifo="$(mktemp -u "/tmp/clawdbot-onboard-${case_name}.XXXXXX")"
     mkfifo "$input_fifo"
+    local log_path="/tmp/clawdbot-onboard-${case_name}.log"
     # Run under script to keep an interactive TTY for clack prompts.
-    script -q -c "$command" /dev/null < "$input_fifo" &
+    script -q -c "$command" "$log_path" < "$input_fifo" &
     wizard_pid=$!
     exec 3> "$input_fifo"
 
@@ -96,15 +99,19 @@ TRASH
     wait "$wizard_pid"
     rm -f "$input_fifo"
     stop_gateway "$gw_pid"
+    if [ -n "$validate_fn" ]; then
+      "$validate_fn" "$log_path"
+    fi
   }
 
   run_wizard() {
     local case_name="$1"
     local home_dir="$2"
     local send_fn="$3"
+    local validate_fn="${4:-}"
 
     # Default onboarding command wrapper.
-    run_wizard_cmd "$case_name" "$home_dir" "node dist/index.js onboard" "$send_fn" true
+    run_wizard_cmd "$case_name" "$home_dir" "node dist/index.js onboard $ONBOARD_FLAGS" "$send_fn" true "$validate_fn"
   }
 
   make_home() {
@@ -129,23 +136,7 @@ TRASH
 
   send_local_basic() {
     # Choose local gateway, accept defaults, skip provider/skills/daemon, skip UI.
-    send $'"'"'\r'"'"' 1.0
-    send $'"'"'\r'"'"' 1.0
-    send "" 1.2
-    send $'"'"'\e[B'"'"' 0.6
-    send $'"'"'\e[B'"'"' 0.6
-    send $'"'"'\e[B'"'"' 0.6
-    send $'"'"'\e[B'"'"' 0.6
-    send $'"'"'\e[B'"'"' 0.6
-    send $'"'"'\r'"'"' 0.6
     send $'"'"'\r'"'"' 0.5
-    send $'"'"'\r'"'"' 0.5
-    send $'"'"'\r'"'"' 0.5
-    send $'"'"'\r'"'"' 0.5
-    send $'"'"'n\r'"'"' 0.5
-    send $'"'"'n\r'"'"' 0.5
-    send $'"'"'n\r'"'"' 0.5
-    send $'"'"'n\r'"'"' 0.5
   }
 
   send_reset_config_only() {
@@ -160,62 +151,31 @@ TRASH
 
   send_providers_flow() {
     # Configure providers via configure wizard.
-    send "" 0.6
+    send $'"'"'\r'"'"' 1.0
+    send "" 1.5
+    # Provider mode (default Configure providers)
     send $'"'"'\r'"'"' 0.8
-    send "" 1.2
-    # Select Providers section only.
-    send $'"'"'\e[B'"'"' 0.5
-    send $'"'"'\e[B'"'"' 0.5
-    send $'"'"'\e[B'"'"' 0.5
-    send $'"'"'\e[B'"'"' 0.5
-    send $'"'"' '"'"' 0.4
-    send $'"'"'\r'"'"' 0.6
-    # Configure providers now? (default Yes)
-    send $'"'"'\r'"'"' 0.8
-    send "" 0.8
-    # Select Telegram, Discord, Slack.
-    send $'"'"'\e[B'"'"' 0.4
-    send $'"'"' '"'"' 0.4
-    send $'"'"'\e[B'"'"' 0.4
-    send $'"'"' '"'"' 0.4
-    send $'"'"'\e[B'"'"' 0.4
-    send $'"'"' '"'"' 0.4
-    send $'"'"'\r'"'"' 0.6
-    send $'"'"'tg_token\r'"'"' 0.8
-    send $'"'"'discord_token\r'"'"' 0.8
-    send "" 0.6
-    send $'"'"'\r'"'"' 0.6
-    send "" 0.6
-    send $'"'"'slack_bot\r'"'"' 0.8
-    send "" 0.6
-    send $'"'"'slack_app\r'"'"' 0.8
+    send "" 1.0
+    # Configure chat providers now? -> No
+    send $'"'"'n\r'"'"' 0.6
   }
 
   send_skills_flow() {
     # Select skills section and skip optional installs.
-    send "" 0.6
-    send $'"'"'\r'"'"' 0.6
-    send "" 1.0
-    send $'"'"'\e[B'"'"' 0.4
-    send $'"'"'\e[B'"'"' 0.4
-    send $'"'"'\e[B'"'"' 0.4
-    send $'"'"'\e[B'"'"' 0.4
-    send $'"'"'\e[B'"'"' 0.4
-    send $'"'"' '"'"' 0.3
-    send $'"'"'\r'"'"' 0.4
-    send $'"'"'n\r'"'"' 0.4
-    send $'"'"'n\r'"'"' 0.4
+    send $'"'"'\r'"'"' 1.0
+    send "" 1.2
+    send $'"'"'n\r'"'"' 0.6
   }
 
   run_case_local_basic() {
     local home_dir
     home_dir="$(make_home local-basic)"
-    run_wizard local-basic "$home_dir" send_local_basic
+    run_wizard local-basic "$home_dir" send_local_basic validate_local_basic_log
 
     # Assert config + workspace scaffolding.
     workspace_dir="$HOME/clawd"
     config_path="$HOME/.clawdbot/clawdbot.json"
-    sessions_dir="$HOME/.clawdbot/sessions"
+    sessions_dir="$HOME/.clawdbot/agents/main/sessions"
 
     assert_file "$config_path"
     assert_dir "$sessions_dir"
@@ -383,7 +343,7 @@ NODE
     local home_dir
     home_dir="$(make_home providers)"
     # Providers-only configure flow.
-    run_wizard_cmd providers "$home_dir" "node dist/index.js configure" send_providers_flow
+    run_wizard_cmd providers "$home_dir" "node dist/index.js configure --section providers" send_providers_flow
 
     config_path="$HOME/.clawdbot/clawdbot.json"
     assert_file "$config_path"
@@ -395,21 +355,22 @@ import JSON5 from "json5";
 const cfg = JSON5.parse(fs.readFileSync(process.env.CONFIG_PATH, "utf-8"));
 const errors = [];
 
-if (cfg?.telegram?.botToken !== "tg_token") {
-  errors.push(`telegram.botToken mismatch (got ${cfg?.telegram?.botToken ?? "unset"})`);
-}
-if (cfg?.discord?.token !== "discord_token") {
-  errors.push(`discord.token mismatch (got ${cfg?.discord?.token ?? "unset"})`);
-}
-if (cfg?.slack?.botToken !== "slack_bot") {
-  errors.push(`slack.botToken mismatch (got ${cfg?.slack?.botToken ?? "unset"})`);
-}
-if (cfg?.slack?.appToken !== "slack_app") {
-  errors.push(`slack.appToken mismatch (got ${cfg?.slack?.appToken ?? "unset"})`);
-}
-if (cfg?.wizard?.lastRunMode !== "local") {
-  errors.push(`wizard.lastRunMode mismatch (got ${cfg?.wizard?.lastRunMode ?? "unset"})`);
-}
+    if (cfg?.telegram?.botToken) {
+      errors.push(`telegram.botToken should be unset (got ${cfg?.telegram?.botToken})`);
+    }
+    if (cfg?.discord?.token) {
+      errors.push(`discord.token should be unset (got ${cfg?.discord?.token})`);
+    }
+    if (cfg?.slack?.botToken || cfg?.slack?.appToken) {
+      errors.push(
+        `slack tokens should be unset (got bot=${cfg?.slack?.botToken ?? "unset"}, app=${cfg?.slack?.appToken ?? "unset"})`,
+      );
+    }
+    if (cfg?.wizard?.lastRunCommand !== "configure") {
+      errors.push(
+        `wizard.lastRunCommand mismatch (got ${cfg?.wizard?.lastRunCommand ?? "unset"})`,
+      );
+    }
 
 if (errors.length > 0) {
   console.error(errors.join("\n"));
@@ -433,7 +394,7 @@ NODE
 }
 JSON
 
-    run_wizard_cmd skills "$home_dir" "node dist/index.js configure" send_skills_flow
+    run_wizard_cmd skills "$home_dir" "node dist/index.js configure --section skills" send_skills_flow
 
     config_path="$HOME/.clawdbot/clawdbot.json"
     assert_file "$config_path"
@@ -462,6 +423,20 @@ if (errors.length > 0) {
 NODE
   }
 
+  assert_log_not_contains() {
+    local file_path="$1"
+    local needle="$2"
+    if grep -q "$needle" "$file_path"; then
+      echo "Unexpected log output: $needle"
+      exit 1
+    fi
+  }
+
+  validate_local_basic_log() {
+    local log_path="$1"
+    assert_log_not_contains "$log_path" "systemctl --user unavailable"
+  }
+
   run_case_local_basic
   run_case_remote_non_interactive
   run_case_reset

scripts/package-mac-app.sh

@@ -272,8 +272,8 @@ if [[ "${SKIP_GATEWAY_PACKAGE:-0}" != "1" ]]; then
   fi
   rm -rf "$RELAY_BUILD_DIR"
 
-  echo "🧪 Smoke testing bundled relay QR modules"
-  "$RELAY_OUT" --smoke qr >/dev/null
+  echo "🧪 Verifying bundled relay (version)"
+  "$RELAY_OUT" --version >/dev/null
 
   echo "🎨 Copying gateway A2UI host assets"
   rm -rf "$RELAY_DIR/a2ui"

showcase.md

@@ -1,39 +0,0 @@
-# Showcase: what your personal assistant can do
-
-Highlights from #showcase (Jan 2–5, 2026). Curated for “wow” factor + concrete links.
-
-## Clawdhub projects (formerly Clawdis)
-- **xuezh** — Chinese learning engine + Clawdbot skill for pronunciation feedback and study flows. <span class="showcase-link"><a href="https://github.com/joshp123/xuezh">github.com/joshp123/xuezh</a><span class="showcase-preview"><img src="/assets/showcase/xuezh-pronunciation.jpeg" alt="xuezh pronunciation feedback in Clawdbot" loading="lazy" decoding="async" /></span></span>
-- **gohome** — Nix-native home automation with Clawdbot as the interface, plus Grafana dashboards. <span class="showcase-link"><a href="https://github.com/joshp123/gohome">github.com/joshp123/gohome</a><span class="showcase-preview"><img src="/assets/showcase/gohome-grafana.png" alt="GoHome Grafana dashboard" loading="lazy" decoding="async" /></span></span>
-- **Roborock skill for GoHome** — Vacuum control plugin with gRPC actions + metrics. <span class="showcase-link"><a href="https://github.com/joshp123/gohome/tree/main/plugins/roborock">github.com/joshp123/gohome/tree/main/plugins/roborock</a><span class="showcase-preview"><img src="/assets/showcase/roborock-screenshot.jpg" alt="GoHome Roborock status screenshot" loading="lazy" decoding="async" /></span></span>
-- **padel-cli** — Playtomic availability + booking CLI with a Clawdbot plugin output. <span class="showcase-link"><a href="https://github.com/joshp123/padel-cli">github.com/joshp123/padel-cli</a><span class="showcase-preview"><img src="/assets/showcase/padel-screenshot.jpg" alt="padel-cli availability screenshot" loading="lazy" decoding="async" /></span></span>
-
-## Automation & real-world outcomes
-- **Grocery autopilot (Picnic)** — Skill built around an unofficial Picnic API client. Pulls order history, infers preferred brands, maps recipes to cart, completes order in minutes. https://github.com/timkrase/clawdis-picnic-skill
-- **Grocery autopilot (Picnic, alt)** — Another Picnic-based skill built via the `picnic-api` package. https://github.com/MRVDH/picnic-api
-- **German rail planning** — Go CLI for Deutsche Bahn; skill picks best connections given time windows and preferences. https://github.com/timkrase/dbrest-cli + https://github.com/timkrase/clawdis-skills/tree/main/db-bahn (link check pending)
-- **Accounting intake** — Collect PDFs from email, prep for tax consultant (monthly accounting batch). (No link shared.)
-
-## Knowledge & memory systems
-- **WhatsApp memory vault** — Ingests full exports, transcribes 1k+ voice notes, cross‑checks with git logs, outputs linked MD reports + ongoing indexing. (No link shared.)
-- **Karakeep semantic search** — Sidecar adds vector search to Karakeep bookmarks (Qdrant + OpenAI/Ollama), includes Clawdis skill. https://github.com/jamesbrooksco/karakeep-semantic-search
-- **Inside‑Out‑2 style memory** — Separate memory manager app turns session files into memories → beliefs → self model. (No link shared.)
-
-## Voice, docs, and assistants on the phone
-- **Clawdia phone bridge** — Vapi voice assistant ↔ Clawdis HTTP bridge; near‑real‑time phone calls. https://github.com/alejandroOPI/clawdia-bridge
-- **Google Docs edit skill** — Rich‑text editing skill built fast with Claude Code. (No link shared.)
-- **OpenRouter transcription skill** — Multi‑lingual audio transcription via OpenRouter (Gemini etc). ClawdHub: https://clawdhub.com/obviyus/openrouter-transcribe (user/slug link)
-
-## Infrastructure & deployment
-- **Home Assistant OS gateway add‑on** — Clawdbot gateway running on HA OS (Raspberry Pi), with SSH tunnel support + persistent state in /config. https://github.com/ngutman/clawdbot-ha-addon
-- **Home Assistant skill** — Control/automate HA via ClawdHub. https://clawdhub.com/skills/homeassistant
-- **Nix packaging** — Batteries‑included nixified clawdis config. https://github.com/joshp123/nix-clawdis
-- **CalDAV skill** — khal/vdirsyncer based calendar skill. ClawdHub: caldav-calendar → https://clawdhub.com/skills/caldav-calendar
-
-## Home + hardware
-- **Roborock integration** — Plugin for robot vacuum control. https://github.com/joshp123/gohome/tree/main/plugins/roborock
-
-## Community builds (non‑Clawdis but made with/around it)
-- **StarSwap marketplace** — Full astronomy gear marketplace. https://star-swap.com/
-
----

src/agents/agent-scope.test.ts

@@ -85,6 +85,10 @@ describe("resolveAgentConfig", () => {
             tools: {
               allow: ["read"],
               deny: ["bash", "write", "edit"],
+              elevated: {
+                enabled: false,
+                allowFrom: { whatsapp: ["+15555550123"] },
+              },
             },
           },
         ],
@@ -94,6 +98,10 @@ describe("resolveAgentConfig", () => {
     expect(result?.tools).toEqual({
       allow: ["read"],
       deny: ["bash", "write", "edit"],
+      elevated: {
+        enabled: false,
+        allowFrom: { whatsapp: ["+15555550123"] },
+      },
     });
   });
 

src/agents/auth-profiles.test.ts

@@ -11,6 +11,7 @@ import {
   CODEX_CLI_PROFILE_ID,
   calculateAuthProfileCooldownMs,
   ensureAuthProfileStore,
+  markAuthProfileFailure,
   resolveAuthProfileOrder,
 } from "./auth-profiles.js";
 
@@ -151,6 +152,49 @@ describe("resolveAuthProfileOrder", () => {
     expect(order).toEqual(["anthropic:work", "anthropic:default"]);
   });
 
+  it("pushes disabled profiles to the end even with store order", () => {
+    const now = Date.now();
+    const order = resolveAuthProfileOrder({
+      store: {
+        ...store,
+        order: { anthropic: ["anthropic:default", "anthropic:work"] },
+        usageStats: {
+          "anthropic:default": {
+            disabledUntil: now + 60_000,
+            disabledReason: "billing",
+          },
+          "anthropic:work": { lastUsed: 1 },
+        },
+      },
+      provider: "anthropic",
+    });
+    expect(order).toEqual(["anthropic:work", "anthropic:default"]);
+  });
+
+  it("pushes disabled profiles to the end even with configured order", () => {
+    const now = Date.now();
+    const order = resolveAuthProfileOrder({
+      cfg: {
+        auth: {
+          order: { anthropic: ["anthropic:default", "anthropic:work"] },
+          profiles: cfg.auth.profiles,
+        },
+      },
+      store: {
+        ...store,
+        usageStats: {
+          "anthropic:default": {
+            disabledUntil: now + 60_000,
+            disabledReason: "billing",
+          },
+          "anthropic:work": { lastUsed: 1 },
+        },
+      },
+      provider: "anthropic",
+    });
+    expect(order).toEqual(["anthropic:work", "anthropic:default"]);
+  });
+
   it("normalizes z.ai aliases in auth.order", () => {
     const order = resolveAuthProfileOrder({
       cfg: {
@@ -397,6 +441,138 @@ describe("auth profile cooldowns", () => {
   });
 });
 
+describe("markAuthProfileFailure", () => {
+  it("disables billing failures for ~5 hours by default", async () => {
+    const agentDir = fs.mkdtempSync(path.join(os.tmpdir(), "clawdbot-auth-"));
+    try {
+      const authPath = path.join(agentDir, "auth-profiles.json");
+      fs.writeFileSync(
+        authPath,
+        JSON.stringify({
+          version: 1,
+          profiles: {
+            "anthropic:default": {
+              type: "api_key",
+              provider: "anthropic",
+              key: "sk-default",
+            },
+          },
+        }),
+      );
+
+      const store = ensureAuthProfileStore(agentDir);
+      const startedAt = Date.now();
+      await markAuthProfileFailure({
+        store,
+        profileId: "anthropic:default",
+        reason: "billing",
+        agentDir,
+      });
+
+      const disabledUntil =
+        store.usageStats?.["anthropic:default"]?.disabledUntil;
+      expect(typeof disabledUntil).toBe("number");
+      const remainingMs = (disabledUntil as number) - startedAt;
+      expect(remainingMs).toBeGreaterThan(4.5 * 60 * 60 * 1000);
+      expect(remainingMs).toBeLessThan(5.5 * 60 * 60 * 1000);
+    } finally {
+      fs.rmSync(agentDir, { recursive: true, force: true });
+    }
+  });
+
+  it("honors per-provider billing backoff overrides", async () => {
+    const agentDir = fs.mkdtempSync(path.join(os.tmpdir(), "clawdbot-auth-"));
+    try {
+      const authPath = path.join(agentDir, "auth-profiles.json");
+      fs.writeFileSync(
+        authPath,
+        JSON.stringify({
+          version: 1,
+          profiles: {
+            "anthropic:default": {
+              type: "api_key",
+              provider: "anthropic",
+              key: "sk-default",
+            },
+          },
+        }),
+      );
+
+      const store = ensureAuthProfileStore(agentDir);
+      const startedAt = Date.now();
+      await markAuthProfileFailure({
+        store,
+        profileId: "anthropic:default",
+        reason: "billing",
+        agentDir,
+        cfg: {
+          auth: {
+            cooldowns: {
+              billingBackoffHoursByProvider: { Anthropic: 1 },
+              billingMaxHours: 2,
+            },
+          },
+        } as never,
+      });
+
+      const disabledUntil =
+        store.usageStats?.["anthropic:default"]?.disabledUntil;
+      expect(typeof disabledUntil).toBe("number");
+      const remainingMs = (disabledUntil as number) - startedAt;
+      expect(remainingMs).toBeGreaterThan(0.8 * 60 * 60 * 1000);
+      expect(remainingMs).toBeLessThan(1.2 * 60 * 60 * 1000);
+    } finally {
+      fs.rmSync(agentDir, { recursive: true, force: true });
+    }
+  });
+
+  it("resets backoff counters outside the failure window", async () => {
+    const agentDir = fs.mkdtempSync(path.join(os.tmpdir(), "clawdbot-auth-"));
+    try {
+      const authPath = path.join(agentDir, "auth-profiles.json");
+      const now = Date.now();
+      fs.writeFileSync(
+        authPath,
+        JSON.stringify({
+          version: 1,
+          profiles: {
+            "anthropic:default": {
+              type: "api_key",
+              provider: "anthropic",
+              key: "sk-default",
+            },
+          },
+          usageStats: {
+            "anthropic:default": {
+              errorCount: 9,
+              failureCounts: { billing: 3 },
+              lastFailureAt: now - 48 * 60 * 60 * 1000,
+            },
+          },
+        }),
+      );
+
+      const store = ensureAuthProfileStore(agentDir);
+      await markAuthProfileFailure({
+        store,
+        profileId: "anthropic:default",
+        reason: "billing",
+        agentDir,
+        cfg: {
+          auth: { cooldowns: { failureWindowHours: 24 } },
+        } as never,
+      });
+
+      expect(store.usageStats?.["anthropic:default"]?.errorCount).toBe(1);
+      expect(
+        store.usageStats?.["anthropic:default"]?.failureCounts?.billing,
+      ).toBe(1);
+    } finally {
+      fs.rmSync(agentDir, { recursive: true, force: true });
+    }
+  });
+});
+
 describe("external CLI credential sync", () => {
   it("syncs Claude CLI credentials into anthropic:claude-cli", async () => {
     const agentDir = fs.mkdtempSync(

src/agents/auth-profiles.ts

@@ -72,11 +72,22 @@ export type AuthProfileCredential =
   | TokenCredential
   | OAuthCredential;
 
+export type AuthProfileFailureReason =
+  | "auth"
+  | "rate_limit"
+  | "billing"
+  | "timeout"
+  | "unknown";
+
 /** Per-profile usage statistics for round-robin and cooldown tracking */
 export type ProfileUsageStats = {
   lastUsed?: number;
   cooldownUntil?: number;
+  disabledUntil?: number;
+  disabledReason?: AuthProfileFailureReason;
   errorCount?: number;
+  failureCounts?: Partial<Record<AuthProfileFailureReason, number>>;
+  lastFailureAt?: number;
 };
 
 export type AuthProfileStore = {
@@ -772,8 +783,9 @@ export function isProfileInCooldown(
   profileId: string,
 ): boolean {
   const stats = store.usageStats?.[profileId];
-  if (!stats?.cooldownUntil) return false;
-  return Date.now() < stats.cooldownUntil;
+  if (!stats) return false;
+  const unusableUntil = resolveProfileUnusableUntil(stats);
+  return unusableUntil ? Date.now() < unusableUntil : false;
 }
 
 /**
@@ -796,6 +808,9 @@ export async function markAuthProfileUsed(params: {
         lastUsed: Date.now(),
         errorCount: 0,
         cooldownUntil: undefined,
+        disabledUntil: undefined,
+        disabledReason: undefined,
+        failureCounts: undefined,
       };
       return true;
     },
@@ -812,6 +827,9 @@ export async function markAuthProfileUsed(params: {
     lastUsed: Date.now(),
     errorCount: 0,
     cooldownUntil: undefined,
+    disabledUntil: undefined,
+    disabledReason: undefined,
+    failureCounts: undefined,
   };
   saveAuthProfileStore(store, agentDir);
 }
@@ -824,34 +842,163 @@ export function calculateAuthProfileCooldownMs(errorCount: number): number {
   );
 }
 
+type ResolvedAuthCooldownConfig = {
+  billingBackoffMs: number;
+  billingMaxMs: number;
+  failureWindowMs: number;
+};
+
+function resolveAuthCooldownConfig(params: {
+  cfg?: ClawdbotConfig;
+  providerId: string;
+}): ResolvedAuthCooldownConfig {
+  const defaults = {
+    billingBackoffHours: 5,
+    billingMaxHours: 24,
+    failureWindowHours: 24,
+  } as const;
+
+  const resolveHours = (value: unknown, fallback: number) =>
+    typeof value === "number" && Number.isFinite(value) && value > 0
+      ? value
+      : fallback;
+
+  const cooldowns = params.cfg?.auth?.cooldowns;
+  const billingOverride = (() => {
+    const map = cooldowns?.billingBackoffHoursByProvider;
+    if (!map) return undefined;
+    for (const [key, value] of Object.entries(map)) {
+      if (normalizeProviderId(key) === params.providerId) return value;
+    }
+    return undefined;
+  })();
+
+  const billingBackoffHours = resolveHours(
+    billingOverride ?? cooldowns?.billingBackoffHours,
+    defaults.billingBackoffHours,
+  );
+  const billingMaxHours = resolveHours(
+    cooldowns?.billingMaxHours,
+    defaults.billingMaxHours,
+  );
+  const failureWindowHours = resolveHours(
+    cooldowns?.failureWindowHours,
+    defaults.failureWindowHours,
+  );
+
+  return {
+    billingBackoffMs: billingBackoffHours * 60 * 60 * 1000,
+    billingMaxMs: billingMaxHours * 60 * 60 * 1000,
+    failureWindowMs: failureWindowHours * 60 * 60 * 1000,
+  };
+}
+
+function calculateAuthProfileBillingDisableMsWithConfig(params: {
+  errorCount: number;
+  baseMs: number;
+  maxMs: number;
+}): number {
+  const normalized = Math.max(1, params.errorCount);
+  const baseMs = Math.max(60_000, params.baseMs);
+  const maxMs = Math.max(baseMs, params.maxMs);
+  const exponent = Math.min(normalized - 1, 10);
+  const raw = baseMs * 2 ** exponent;
+  return Math.min(maxMs, raw);
+}
+
+function resolveProfileUnusableUntil(stats: ProfileUsageStats): number | null {
+  const values = [stats.cooldownUntil, stats.disabledUntil]
+    .filter((value): value is number => typeof value === "number")
+    .filter((value) => Number.isFinite(value) && value > 0);
+  if (values.length === 0) return null;
+  return Math.max(...values);
+}
+
+export function resolveProfileUnusableUntilForDisplay(
+  store: AuthProfileStore,
+  profileId: string,
+): number | null {
+  const stats = store.usageStats?.[profileId];
+  if (!stats) return null;
+  return resolveProfileUnusableUntil(stats);
+}
+
+function computeNextProfileUsageStats(params: {
+  existing: ProfileUsageStats;
+  now: number;
+  reason: AuthProfileFailureReason;
+  cfgResolved: ResolvedAuthCooldownConfig;
+}): ProfileUsageStats {
+  const windowMs = params.cfgResolved.failureWindowMs;
+  const windowExpired =
+    typeof params.existing.lastFailureAt === "number" &&
+    params.existing.lastFailureAt > 0 &&
+    params.now - params.existing.lastFailureAt > windowMs;
+
+  const baseErrorCount = windowExpired ? 0 : (params.existing.errorCount ?? 0);
+  const nextErrorCount = baseErrorCount + 1;
+  const failureCounts = windowExpired
+    ? {}
+    : { ...params.existing.failureCounts };
+  failureCounts[params.reason] = (failureCounts[params.reason] ?? 0) + 1;
+
+  const updatedStats: ProfileUsageStats = {
+    ...params.existing,
+    errorCount: nextErrorCount,
+    failureCounts,
+    lastFailureAt: params.now,
+  };
+
+  if (params.reason === "billing") {
+    const billingCount = failureCounts.billing ?? 1;
+    const backoffMs = calculateAuthProfileBillingDisableMsWithConfig({
+      errorCount: billingCount,
+      baseMs: params.cfgResolved.billingBackoffMs,
+      maxMs: params.cfgResolved.billingMaxMs,
+    });
+    updatedStats.disabledUntil = params.now + backoffMs;
+    updatedStats.disabledReason = "billing";
+  } else {
+    const backoffMs = calculateAuthProfileCooldownMs(nextErrorCount);
+    updatedStats.cooldownUntil = params.now + backoffMs;
+  }
+
+  return updatedStats;
+}
+
 /**
- * Mark a profile as failed/rate-limited. Applies exponential backoff cooldown.
- * Cooldown times: 1min, 5min, 25min, max 1 hour.
- * Uses store lock to avoid overwriting concurrent usage updates.
+ * Mark a profile as failed for a specific reason. Billing failures are treated
+ * as "disabled" (longer backoff) vs the regular cooldown window.
  */
-export async function markAuthProfileCooldown(params: {
+export async function markAuthProfileFailure(params: {
   store: AuthProfileStore;
   profileId: string;
+  reason: AuthProfileFailureReason;
+  cfg?: ClawdbotConfig;
   agentDir?: string;
 }): Promise<void> {
-  const { store, profileId, agentDir } = params;
+  const { store, profileId, reason, agentDir, cfg } = params;
   const updated = await updateAuthProfileStoreWithLock({
     agentDir,
     updater: (freshStore) => {
-      if (!freshStore.profiles[profileId]) return false;
-
+      const profile = freshStore.profiles[profileId];
+      if (!profile) return false;
       freshStore.usageStats = freshStore.usageStats ?? {};
       const existing = freshStore.usageStats[profileId] ?? {};
-      const errorCount = (existing.errorCount ?? 0) + 1;
 
-      // Exponential backoff: 1min, 5min, 25min, capped at 1h
-      const backoffMs = calculateAuthProfileCooldownMs(errorCount);
+      const now = Date.now();
+      const providerKey = normalizeProviderId(profile.provider);
+      const cfgResolved = resolveAuthCooldownConfig({
+        cfg,
+        providerId: providerKey,
+      });
 
-      freshStore.usageStats[profileId] = {
-        ...existing,
-        errorCount,
-        cooldownUntil: Date.now() + backoffMs,
-      };
+      freshStore.usageStats[profileId] = computeNextProfileUsageStats({
+        existing,
+        now,
+        reason,
+        cfgResolved,
+      });
       return true;
     },
   });
@@ -863,19 +1010,42 @@ export async function markAuthProfileCooldown(params: {
 
   store.usageStats = store.usageStats ?? {};
   const existing = store.usageStats[profileId] ?? {};
-  const errorCount = (existing.errorCount ?? 0) + 1;
+  const now = Date.now();
+  const providerKey = normalizeProviderId(
+    store.profiles[profileId]?.provider ?? "",
+  );
+  const cfgResolved = resolveAuthCooldownConfig({
+    cfg,
+    providerId: providerKey,
+  });
 
-  // Exponential backoff: 1min, 5min, 25min, capped at 1h
-  const backoffMs = calculateAuthProfileCooldownMs(errorCount);
-
-  store.usageStats[profileId] = {
-    ...existing,
-    errorCount,
-    cooldownUntil: Date.now() + backoffMs,
-  };
+  store.usageStats[profileId] = computeNextProfileUsageStats({
+    existing,
+    now,
+    reason,
+    cfgResolved,
+  });
   saveAuthProfileStore(store, agentDir);
 }
 
+/**
+ * Mark a profile as failed/rate-limited. Applies exponential backoff cooldown.
+ * Cooldown times: 1min, 5min, 25min, max 1 hour.
+ * Uses store lock to avoid overwriting concurrent usage updates.
+ */
+export async function markAuthProfileCooldown(params: {
+  store: AuthProfileStore;
+  profileId: string;
+  agentDir?: string;
+}): Promise<void> {
+  await markAuthProfileFailure({
+    store: params.store,
+    profileId: params.profileId,
+    reason: "unknown",
+    agentDir: params.agentDir,
+  });
+}
+
 /**
  * Clear cooldown for a profile (e.g., manual reset).
  * Uses store lock to avoid overwriting concurrent usage updates.
@@ -973,7 +1143,8 @@ export function resolveAuthProfileOrder(params: {
     const inCooldown: Array<{ profileId: string; cooldownUntil: number }> = [];
 
     for (const profileId of deduped) {
-      const cooldownUntil = store.usageStats?.[profileId]?.cooldownUntil;
+      const cooldownUntil =
+        resolveProfileUnusableUntil(store.usageStats?.[profileId] ?? {}) ?? 0;
       if (
         typeof cooldownUntil === "number" &&
         Number.isFinite(cooldownUntil) &&
@@ -1057,7 +1228,8 @@ function orderProfilesByMode(
   const cooldownSorted = inCooldown
     .map((profileId) => ({
       profileId,
-      cooldownUntil: store.usageStats?.[profileId]?.cooldownUntil ?? now,
+      cooldownUntil:
+        resolveProfileUnusableUntil(store.usageStats?.[profileId] ?? {}) ?? now,
     }))
     .sort((a, b) => a.cooldownUntil - b.cooldownUntil)
     .map((entry) => entry.profileId);

src/agents/bash-tools.test.ts

@@ -1,4 +1,4 @@
-import { beforeEach, describe, expect, it } from "vitest";
+import { afterEach, beforeEach, describe, expect, it } from "vitest";
 import { resetProcessRegistryForTests } from "./bash-process-registry.js";
 import {
   bashTool,
@@ -50,6 +50,16 @@ beforeEach(() => {
 });
 
 describe("bash tool backgrounding", () => {
+  const originalShell = process.env.SHELL;
+
+  beforeEach(() => {
+    if (!isWin) process.env.SHELL = "/bin/bash";
+  });
+
+  afterEach(() => {
+    if (!isWin) process.env.SHELL = originalShell;
+  });
+
   it(
     "backgrounds after yield and can be polled",
     async () => {

src/agents/claude-cli-runner.ts

@@ -9,13 +9,19 @@ import { shouldLogVerbose } from "../globals.js";
 import { createSubsystemLogger } from "../logging.js";
 import { runCommandWithTimeout } from "../process/exec.js";
 import { resolveUserPath } from "../utils.js";
+import { FailoverError, resolveFailoverStatus } from "./failover-error.js";
 import {
   buildBootstrapContextFiles,
+  classifyFailoverReason,
   type EmbeddedContextFile,
+  isFailoverErrorMessage,
 } from "./pi-embedded-helpers.js";
 import type { EmbeddedPiRunResult } from "./pi-embedded-runner.js";
 import { buildAgentSystemPrompt } from "./system-prompt.js";
-import { loadWorkspaceBootstrapFiles } from "./workspace.js";
+import {
+  filterBootstrapFilesForSession,
+  loadWorkspaceBootstrapFiles,
+} from "./workspace.js";
 
 const log = createSubsystemLogger("agent/claude-cli");
 const CLAUDE_CLI_QUEUE_KEY = "global";
@@ -310,6 +316,16 @@ async function runClaudeCliOnce(params: {
   }
   if (result.code !== 0) {
     const err = result.stderr.trim() || stdout || "Claude CLI failed.";
+    if (isFailoverErrorMessage(err)) {
+      const reason = classifyFailoverReason(err) ?? "unknown";
+      const status = resolveFailoverStatus(reason);
+      throw new FailoverError(err, {
+        reason,
+        provider: "claude-cli",
+        model: params.modelId,
+        status,
+      });
+    }
     throw new Error(err);
   }
   const parsed = parseClaudeCliJson(stdout);
@@ -353,7 +369,10 @@ export async function runClaudeCliAgent(params: {
     .filter(Boolean)
     .join("\n");
 
-  const bootstrapFiles = await loadWorkspaceBootstrapFiles(workspaceDir);
+  const bootstrapFiles = filterBootstrapFilesForSession(
+    await loadWorkspaceBootstrapFiles(workspaceDir),
+    params.sessionKey ?? params.sessionId,
+  );
   const contextFiles = buildBootstrapContextFiles(bootstrapFiles);
   const systemPrompt = buildSystemPrompt({
     workspaceDir,

src/agents/clawdbot-tools.session-status.test.ts

@@ -0,0 +1,146 @@
+import { describe, expect, it, vi } from "vitest";
+
+const loadSessionStoreMock = vi.fn();
+const saveSessionStoreMock = vi.fn();
+
+vi.mock("../config/sessions.js", async (importOriginal) => {
+  const actual = await importOriginal<typeof import("../config/sessions.js")>();
+  return {
+    ...actual,
+    loadSessionStore: (storePath: string) => loadSessionStoreMock(storePath),
+    saveSessionStore: (storePath: string, store: Record<string, unknown>) =>
+      saveSessionStoreMock(storePath, store),
+    resolveStorePath: () => "/tmp/sessions.json",
+  };
+});
+
+vi.mock("../config/config.js", async (importOriginal) => {
+  const actual = await importOriginal<typeof import("../config/config.js")>();
+  return {
+    ...actual,
+    loadConfig: () => ({
+      session: { mainKey: "main", scope: "per-sender" },
+      agents: {
+        defaults: {
+          model: { primary: "anthropic/claude-opus-4-5" },
+          models: {},
+        },
+      },
+    }),
+  };
+});
+
+vi.mock("../agents/model-catalog.js", () => ({
+  loadModelCatalog: async () => [
+    {
+      provider: "anthropic",
+      id: "claude-opus-4-5",
+      name: "Opus",
+      contextWindow: 200000,
+    },
+    {
+      provider: "anthropic",
+      id: "claude-sonnet-4-5",
+      name: "Sonnet",
+      contextWindow: 200000,
+    },
+  ],
+}));
+
+vi.mock("../agents/auth-profiles.js", () => ({
+  ensureAuthProfileStore: () => ({ profiles: {} }),
+  resolveAuthProfileDisplayLabel: () => undefined,
+  resolveAuthProfileOrder: () => [],
+}));
+
+vi.mock("../agents/model-auth.js", () => ({
+  resolveEnvApiKey: () => null,
+  getCustomProviderApiKey: () => null,
+  resolveModelAuthMode: () => "api-key",
+}));
+
+vi.mock("../infra/provider-usage.js", () => ({
+  resolveUsageProviderId: () => undefined,
+  loadProviderUsageSummary: async () => ({
+    updatedAt: Date.now(),
+    providers: [],
+  }),
+  formatUsageSummaryLine: () => null,
+}));
+
+import { createClawdbotTools } from "./clawdbot-tools.js";
+
+describe("session_status tool", () => {
+  it("returns a status card for the current session", async () => {
+    loadSessionStoreMock.mockReset();
+    saveSessionStoreMock.mockReset();
+    loadSessionStoreMock.mockReturnValue({
+      main: {
+        sessionId: "s1",
+        updatedAt: 10,
+      },
+    });
+
+    const tool = createClawdbotTools({ agentSessionKey: "main" }).find(
+      (candidate) => candidate.name === "session_status",
+    );
+    expect(tool).toBeDefined();
+    if (!tool) throw new Error("missing session_status tool");
+
+    const result = await tool.execute("call1", {});
+    const details = result.details as { ok?: boolean; statusText?: string };
+    expect(details.ok).toBe(true);
+    expect(details.statusText).toContain("ClawdBot");
+    expect(details.statusText).toContain("🧠 Model:");
+  });
+
+  it("errors for unknown session keys", async () => {
+    loadSessionStoreMock.mockReset();
+    saveSessionStoreMock.mockReset();
+    loadSessionStoreMock.mockReturnValue({
+      main: { sessionId: "s1", updatedAt: 10 },
+    });
+
+    const tool = createClawdbotTools({ agentSessionKey: "main" }).find(
+      (candidate) => candidate.name === "session_status",
+    );
+    expect(tool).toBeDefined();
+    if (!tool) throw new Error("missing session_status tool");
+
+    await expect(tool.execute("call2", { sessionKey: "nope" })).rejects.toThrow(
+      "Unknown sessionKey",
+    );
+    expect(saveSessionStoreMock).not.toHaveBeenCalled();
+  });
+
+  it("resets per-session model override via model=default", async () => {
+    loadSessionStoreMock.mockReset();
+    saveSessionStoreMock.mockReset();
+    loadSessionStoreMock.mockReturnValue({
+      main: {
+        sessionId: "s1",
+        updatedAt: 10,
+        providerOverride: "anthropic",
+        modelOverride: "claude-sonnet-4-5",
+        authProfileOverride: "p1",
+      },
+    });
+
+    const tool = createClawdbotTools({ agentSessionKey: "main" }).find(
+      (candidate) => candidate.name === "session_status",
+    );
+    expect(tool).toBeDefined();
+    if (!tool) throw new Error("missing session_status tool");
+
+    await tool.execute("call3", { model: "default" });
+    expect(saveSessionStoreMock).toHaveBeenCalled();
+    const [, savedStore] = saveSessionStoreMock.mock.calls.at(-1) as [
+      string,
+      Record<string, unknown>,
+    ];
+    const saved = savedStore.main as Record<string, unknown>;
+    expect(saved.providerOverride).toBeUndefined();
+    expect(saved.modelOverride).toBeUndefined();
+    expect(saved.authProfileOverride).toBeUndefined();
+  });
+});

src/agents/clawdbot-tools.sessions.test.ts

@@ -23,6 +23,43 @@ vi.mock("../config/config.js", async (importOriginal) => {
 import { createClawdbotTools } from "./clawdbot-tools.js";
 
 describe("sessions tools", () => {
+  it("uses number (not integer) in tool schemas for Gemini compatibility", () => {
+    const tools = createClawdbotTools();
+    const byName = (name: string) => {
+      const tool = tools.find((candidate) => candidate.name === name);
+      expect(tool).toBeDefined();
+      if (!tool) throw new Error(`missing ${name} tool`);
+      return tool;
+    };
+
+    const schemaProp = (toolName: string, prop: string) => {
+      const tool = byName(toolName);
+      const schema = tool.parameters as {
+        anyOf?: unknown;
+        oneOf?: unknown;
+        properties?: Record<string, unknown>;
+      };
+      expect(schema.anyOf).toBeUndefined();
+      expect(schema.oneOf).toBeUndefined();
+
+      const properties = schema.properties ?? {};
+      const value = properties[prop] as { type?: unknown } | undefined;
+      expect(value).toBeDefined();
+      if (!value) throw new Error(`missing ${toolName} schema prop: ${prop}`);
+      return value;
+    };
+
+    expect(schemaProp("sessions_history", "limit").type).toBe("number");
+    expect(schemaProp("sessions_list", "limit").type).toBe("number");
+    expect(schemaProp("sessions_list", "activeMinutes").type).toBe("number");
+    expect(schemaProp("sessions_list", "messageLimit").type).toBe("number");
+    expect(schemaProp("sessions_send", "timeoutSeconds").type).toBe("number");
+    expect(schemaProp("sessions_spawn", "runTimeoutSeconds").type).toBe(
+      "number",
+    );
+    expect(schemaProp("sessions_spawn", "timeoutSeconds").type).toBe("number");
+  });
+
   it("sessions_list filters kinds and includes messages", async () => {
     callGatewayMock.mockReset();
     callGatewayMock.mockImplementation(async (opts: unknown) => {
@@ -206,7 +243,11 @@ describe("sessions tools", () => {
       message: "ping",
       timeoutSeconds: 0,
     });
-    expect(fire.details).toMatchObject({ status: "accepted", runId: "run-1" });
+    expect(fire.details).toMatchObject({
+      status: "accepted",
+      runId: "run-1",
+      delivery: { status: "pending", mode: "announce" },
+    });
     await new Promise((resolve) => setTimeout(resolve, 0));
     await new Promise((resolve) => setTimeout(resolve, 0));
 
@@ -219,6 +260,7 @@ describe("sessions tools", () => {
     expect(waited.details).toMatchObject({
       status: "ok",
       reply: "done",
+      delivery: { status: "pending", mode: "announce" },
     });
     expect(typeof (waited.details as { runId?: string }).runId).toBe("string");
     await new Promise((resolve) => setTimeout(resolve, 0));
@@ -231,7 +273,10 @@ describe("sessions tools", () => {
     );
     expect(agentCalls).toHaveLength(8);
     for (const call of agentCalls) {
-      expect(call.params).toMatchObject({ lane: "nested" });
+      expect(call.params).toMatchObject({
+        lane: "nested",
+        provider: "webchat",
+      });
     }
     expect(
       agentCalls.some(
@@ -357,6 +402,15 @@ describe("sessions tools", () => {
     await new Promise((resolve) => setTimeout(resolve, 0));
     await new Promise((resolve) => setTimeout(resolve, 0));
 
+    const agentCalls = calls.filter((call) => call.method === "agent");
+    expect(agentCalls).toHaveLength(4);
+    for (const call of agentCalls) {
+      expect(call.params).toMatchObject({
+        lane: "nested",
+        provider: "webchat",
+      });
+    }
+
     const replySteps = calls.filter(
       (call) =>
         call.method === "agent" &&

src/agents/clawdbot-tools.subagents.test.ts

@@ -57,6 +57,7 @@ describe("subagents", () => {
         const params = request.params as {
           message?: string;
           sessionKey?: string;
+          provider?: string;
           timeout?: number;
         };
         const message = params?.message ?? "";
@@ -67,6 +68,7 @@ describe("subagents", () => {
           childRunId = runId;
           childSessionKey = sessionKey;
           sessionLastAssistantText.set(sessionKey, "result");
+          expect(params?.provider).toBe("discord");
           expect(params?.timeout).toBe(1);
         }
         return {
@@ -155,12 +157,24 @@ describe("subagents", () => {
     const agentCalls = calls.filter((call) => call.method === "agent");
     expect(agentCalls).toHaveLength(2);
     const first = agentCalls[0]?.params as
-      | { lane?: string; deliver?: boolean; sessionKey?: string }
+      | {
+          lane?: string;
+          deliver?: boolean;
+          sessionKey?: string;
+          provider?: string;
+        }
       | undefined;
     expect(first?.lane).toBe("subagent");
     expect(first?.deliver).toBe(false);
+    expect(first?.provider).toBe("discord");
     expect(first?.sessionKey?.startsWith("agent:main:subagent:")).toBe(true);
     expect(childSessionKey?.startsWith("agent:main:subagent:")).toBe(true);
+    const second = agentCalls[1]?.params as
+      | { provider?: string; deliver?: boolean; lane?: string }
+      | undefined;
+    expect(second?.lane).toBe("nested");
+    expect(second?.deliver).toBe(false);
+    expect(second?.provider).toBe("webchat");
 
     expect(sendParams.provider).toBe("discord");
     expect(sendParams.to).toBe("channel:req");

src/agents/clawdbot-tools.ts

@@ -1,4 +1,5 @@
 import type { ClawdbotConfig } from "../config/config.js";
+import type { GatewayMessageProvider } from "../utils/message-provider.js";
 import { createAgentsListTool } from "./tools/agents-list-tool.js";
 import { createBrowserTool } from "./tools/browser-tool.js";
 import { createCanvasTool } from "./tools/canvas-tool.js";
@@ -8,6 +9,7 @@ import { createGatewayTool } from "./tools/gateway-tool.js";
 import { createImageTool } from "./tools/image-tool.js";
 import { createMessageTool } from "./tools/message-tool.js";
 import { createNodesTool } from "./tools/nodes-tool.js";
+import { createSessionStatusTool } from "./tools/session-status-tool.js";
 import { createSessionsHistoryTool } from "./tools/sessions-history-tool.js";
 import { createSessionsListTool } from "./tools/sessions-list-tool.js";
 import { createSessionsSendTool } from "./tools/sessions-send-tool.js";
@@ -16,11 +18,19 @@ import { createSessionsSpawnTool } from "./tools/sessions-spawn-tool.js";
 export function createClawdbotTools(options?: {
   browserControlUrl?: string;
   agentSessionKey?: string;
-  agentProvider?: string;
+  agentProvider?: GatewayMessageProvider;
   agentAccountId?: string;
   agentDir?: string;
   sandboxed?: boolean;
   config?: ClawdbotConfig;
+  /** Current channel ID for auto-threading (Slack). */
+  currentChannelId?: string;
+  /** Current thread timestamp for auto-threading (Slack). */
+  currentThreadTs?: string;
+  /** Reply-to mode for Slack auto-threading. */
+  replyToMode?: "off" | "first" | "all";
+  /** Mutable ref to track if a reply was sent (for "first" mode). */
+  hasRepliedRef?: { value: boolean };
 }): AnyAgentTool[] {
   const imageTool = createImageTool({
     config: options?.config,
@@ -34,6 +44,10 @@ export function createClawdbotTools(options?: {
     createMessageTool({
       agentAccountId: options?.agentAccountId,
       config: options?.config,
+      currentChannelId: options?.currentChannelId,
+      currentThreadTs: options?.currentThreadTs,
+      replyToMode: options?.replyToMode,
+      hasRepliedRef: options?.hasRepliedRef,
     }),
     createGatewayTool({
       agentSessionKey: options?.agentSessionKey,
@@ -58,6 +72,10 @@ export function createClawdbotTools(options?: {
       agentProvider: options?.agentProvider,
       sandboxed: options?.sandboxed,
     }),
+    createSessionStatusTool({
+      agentSessionKey: options?.agentSessionKey,
+      config: options?.config,
+    }),
     ...(imageTool ? [imageTool] : []),
   ];
 }

src/agents/context-window-guard.test.ts

@@ -0,0 +1,135 @@
+import { describe, expect, it } from "vitest";
+
+import type { ClawdbotConfig } from "../config/config.js";
+import {
+  CONTEXT_WINDOW_HARD_MIN_TOKENS,
+  CONTEXT_WINDOW_WARN_BELOW_TOKENS,
+  evaluateContextWindowGuard,
+  resolveContextWindowInfo,
+} from "./context-window-guard.js";
+
+describe("context-window-guard", () => {
+  it("blocks below 16k (model metadata)", () => {
+    const info = resolveContextWindowInfo({
+      cfg: undefined,
+      provider: "openrouter",
+      modelId: "tiny",
+      modelContextWindow: 8000,
+      defaultTokens: 200_000,
+    });
+    const guard = evaluateContextWindowGuard({ info });
+    expect(guard.source).toBe("model");
+    expect(guard.tokens).toBe(8000);
+    expect(guard.shouldWarn).toBe(true);
+    expect(guard.shouldBlock).toBe(true);
+  });
+
+  it("warns below 32k but does not block at 16k+", () => {
+    const info = resolveContextWindowInfo({
+      cfg: undefined,
+      provider: "openai",
+      modelId: "small",
+      modelContextWindow: 24_000,
+      defaultTokens: 200_000,
+    });
+    const guard = evaluateContextWindowGuard({ info });
+    expect(guard.tokens).toBe(24_000);
+    expect(guard.shouldWarn).toBe(true);
+    expect(guard.shouldBlock).toBe(false);
+  });
+
+  it("does not warn at 32k+ (model metadata)", () => {
+    const info = resolveContextWindowInfo({
+      cfg: undefined,
+      provider: "openai",
+      modelId: "ok",
+      modelContextWindow: 64_000,
+      defaultTokens: 200_000,
+    });
+    const guard = evaluateContextWindowGuard({ info });
+    expect(guard.shouldWarn).toBe(false);
+    expect(guard.shouldBlock).toBe(false);
+  });
+
+  it("uses models.providers.*.models[].contextWindow when present", () => {
+    const cfg = {
+      models: {
+        providers: {
+          openrouter: {
+            baseUrl: "http://localhost",
+            apiKey: "x",
+            models: [
+              {
+                id: "tiny",
+                name: "tiny",
+                reasoning: false,
+                input: ["text"],
+                cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+                contextWindow: 12_000,
+                maxTokens: 256,
+              },
+            ],
+          },
+        },
+      },
+    } satisfies ClawdbotConfig;
+
+    const info = resolveContextWindowInfo({
+      cfg,
+      provider: "openrouter",
+      modelId: "tiny",
+      modelContextWindow: undefined,
+      defaultTokens: 200_000,
+    });
+    const guard = evaluateContextWindowGuard({ info });
+    expect(info.source).toBe("modelsConfig");
+    expect(guard.shouldBlock).toBe(true);
+  });
+
+  it("falls back to agents.defaults.contextTokens", () => {
+    const cfg = {
+      agents: { defaults: { contextTokens: 20_000 } },
+    } satisfies ClawdbotConfig;
+    const info = resolveContextWindowInfo({
+      cfg,
+      provider: "anthropic",
+      modelId: "whatever",
+      modelContextWindow: undefined,
+      defaultTokens: 200_000,
+    });
+    const guard = evaluateContextWindowGuard({ info });
+    expect(info.source).toBe("agentContextTokens");
+    expect(guard.shouldWarn).toBe(true);
+    expect(guard.shouldBlock).toBe(false);
+  });
+
+  it("uses default when nothing else is available", () => {
+    const info = resolveContextWindowInfo({
+      cfg: undefined,
+      provider: "anthropic",
+      modelId: "unknown",
+      modelContextWindow: undefined,
+      defaultTokens: 200_000,
+    });
+    const guard = evaluateContextWindowGuard({ info });
+    expect(info.source).toBe("default");
+    expect(guard.shouldWarn).toBe(false);
+    expect(guard.shouldBlock).toBe(false);
+  });
+
+  it("allows overriding thresholds", () => {
+    const info = { tokens: 10_000, source: "model" as const };
+    const guard = evaluateContextWindowGuard({
+      info,
+      warnBelowTokens: 12_000,
+      hardMinTokens: 9_000,
+    });
+    expect(guard.shouldWarn).toBe(true);
+    expect(guard.shouldBlock).toBe(false);
+  });
+
+  it("exports thresholds as expected", () => {
+    expect(CONTEXT_WINDOW_HARD_MIN_TOKENS).toBe(16_000);
+    expect(CONTEXT_WINDOW_WARN_BELOW_TOKENS).toBe(32_000);
+  });
+});

src/agents/context-window-guard.ts

@@ -0,0 +1,84 @@
+import type { ClawdbotConfig } from "../config/config.js";
+
+export const CONTEXT_WINDOW_HARD_MIN_TOKENS = 16_000;
+export const CONTEXT_WINDOW_WARN_BELOW_TOKENS = 32_000;
+
+export type ContextWindowSource =
+  | "model"
+  | "modelsConfig"
+  | "agentContextTokens"
+  | "default";
+
+export type ContextWindowInfo = {
+  tokens: number;
+  source: ContextWindowSource;
+};
+
+function normalizePositiveInt(value: unknown): number | null {
+  if (typeof value !== "number" || !Number.isFinite(value)) return null;
+  const int = Math.floor(value);
+  return int > 0 ? int : null;
+}
+
+export function resolveContextWindowInfo(params: {
+  cfg: ClawdbotConfig | undefined;
+  provider: string;
+  modelId: string;
+  modelContextWindow?: number;
+  defaultTokens: number;
+}): ContextWindowInfo {
+  const fromModel = normalizePositiveInt(params.modelContextWindow);
+  if (fromModel) return { tokens: fromModel, source: "model" };
+
+  const fromModelsConfig = (() => {
+    const providers = params.cfg?.models?.providers as
+      | Record<
+          string,
+          { models?: Array<{ id?: string; contextWindow?: number }> }
+        >
+      | undefined;
+    const providerEntry = providers?.[params.provider];
+    const models = Array.isArray(providerEntry?.models)
+      ? providerEntry.models
+      : [];
+    const match = models.find((m) => m?.id === params.modelId);
+    return normalizePositiveInt(match?.contextWindow);
+  })();
+  if (fromModelsConfig)
+    return { tokens: fromModelsConfig, source: "modelsConfig" };
+
+  const fromAgentConfig = normalizePositiveInt(
+    params.cfg?.agents?.defaults?.contextTokens,
+  );
+  if (fromAgentConfig)
+    return { tokens: fromAgentConfig, source: "agentContextTokens" };
+
+  return { tokens: Math.floor(params.defaultTokens), source: "default" };
+}
+
+export type ContextWindowGuardResult = ContextWindowInfo & {
+  shouldWarn: boolean;
+  shouldBlock: boolean;
+};
+
+export function evaluateContextWindowGuard(params: {
+  info: ContextWindowInfo;
+  warnBelowTokens?: number;
+  hardMinTokens?: number;
+}): ContextWindowGuardResult {
+  const warnBelow = Math.max(
+    1,
+    Math.floor(params.warnBelowTokens ?? CONTEXT_WINDOW_WARN_BELOW_TOKENS),
+  );
+  const hardMin = Math.max(
+    1,
+    Math.floor(params.hardMinTokens ?? CONTEXT_WINDOW_HARD_MIN_TOKENS),
+  );
+  const tokens = Math.max(0, Math.floor(params.info.tokens));
+  return {
+    ...params.info,
+    tokens,
+    shouldWarn: tokens > 0 && tokens < warnBelow,
+    shouldBlock: tokens > 0 && tokens < hardMin,
+  };
+}

src/agents/failover-error.test.ts

@@ -0,0 +1,44 @@
+import { describe, expect, it } from "vitest";
+import {
+  coerceToFailoverError,
+  describeFailoverError,
+  resolveFailoverReasonFromError,
+} from "./failover-error.js";
+
+describe("failover-error", () => {
+  it("infers failover reason from HTTP status", () => {
+    expect(resolveFailoverReasonFromError({ status: 402 })).toBe("billing");
+    expect(resolveFailoverReasonFromError({ statusCode: "429" })).toBe(
+      "rate_limit",
+    );
+    expect(resolveFailoverReasonFromError({ status: 403 })).toBe("auth");
+    expect(resolveFailoverReasonFromError({ status: 408 })).toBe("timeout");
+  });
+
+  it("infers timeout from common node error codes", () => {
+    expect(resolveFailoverReasonFromError({ code: "ETIMEDOUT" })).toBe(
+      "timeout",
+    );
+    expect(resolveFailoverReasonFromError({ code: "ECONNRESET" })).toBe(
+      "timeout",
+    );
+  });
+
+  it("coerces failover-worthy errors into FailoverError with metadata", () => {
+    const err = coerceToFailoverError("credit balance too low", {
+      provider: "anthropic",
+      model: "claude-opus-4-5",
+    });
+    expect(err?.name).toBe("FailoverError");
+    expect(err?.reason).toBe("billing");
+    expect(err?.status).toBe(402);
+    expect(err?.provider).toBe("anthropic");
+    expect(err?.model).toBe("claude-opus-4-5");
+  });
+
+  it("describes non-Error values consistently", () => {
+    const described = describeFailoverError(123);
+    expect(described.message).toBe("123");
+    expect(described.reason).toBeUndefined();
+  });
+});

src/agents/failover-error.ts

@@ -0,0 +1,169 @@
+import {
+  classifyFailoverReason,
+  type FailoverReason,
+} from "./pi-embedded-helpers.js";
+
+export class FailoverError extends Error {
+  readonly reason: FailoverReason;
+  readonly provider?: string;
+  readonly model?: string;
+  readonly profileId?: string;
+  readonly status?: number;
+  readonly code?: string;
+
+  constructor(
+    message: string,
+    params: {
+      reason: FailoverReason;
+      provider?: string;
+      model?: string;
+      profileId?: string;
+      status?: number;
+      code?: string;
+      cause?: unknown;
+    },
+  ) {
+    super(message, { cause: params.cause });
+    this.name = "FailoverError";
+    this.reason = params.reason;
+    this.provider = params.provider;
+    this.model = params.model;
+    this.profileId = params.profileId;
+    this.status = params.status;
+    this.code = params.code;
+  }
+}
+
+export function isFailoverError(err: unknown): err is FailoverError {
+  return err instanceof FailoverError;
+}
+
+export function resolveFailoverStatus(
+  reason: FailoverReason,
+): number | undefined {
+  switch (reason) {
+    case "billing":
+      return 402;
+    case "rate_limit":
+      return 429;
+    case "auth":
+      return 401;
+    case "timeout":
+      return 408;
+    default:
+      return undefined;
+  }
+}
+
+function getStatusCode(err: unknown): number | undefined {
+  if (!err || typeof err !== "object") return undefined;
+  const candidate =
+    (err as { status?: unknown; statusCode?: unknown }).status ??
+    (err as { statusCode?: unknown }).statusCode;
+  if (typeof candidate === "number") return candidate;
+  if (typeof candidate === "string" && /^\d+$/.test(candidate)) {
+    return Number(candidate);
+  }
+  return undefined;
+}
+
+function getErrorCode(err: unknown): string | undefined {
+  if (!err || typeof err !== "object") return undefined;
+  const candidate = (err as { code?: unknown }).code;
+  if (typeof candidate !== "string") return undefined;
+  const trimmed = candidate.trim();
+  return trimmed ? trimmed : undefined;
+}
+
+function getErrorMessage(err: unknown): string {
+  if (err instanceof Error) return err.message;
+  if (typeof err === "string") return err;
+  if (
+    typeof err === "number" ||
+    typeof err === "boolean" ||
+    typeof err === "bigint"
+  ) {
+    return String(err);
+  }
+  if (typeof err === "symbol") return err.description ?? "";
+  if (err && typeof err === "object") {
+    const message = (err as { message?: unknown }).message;
+    if (typeof message === "string") return message;
+  }
+  return "";
+}
+
+export function resolveFailoverReasonFromError(
+  err: unknown,
+): FailoverReason | null {
+  if (isFailoverError(err)) return err.reason;
+
+  const status = getStatusCode(err);
+  if (status === 402) return "billing";
+  if (status === 429) return "rate_limit";
+  if (status === 401 || status === 403) return "auth";
+  if (status === 408) return "timeout";
+
+  const code = (getErrorCode(err) ?? "").toUpperCase();
+  if (
+    ["ETIMEDOUT", "ESOCKETTIMEDOUT", "ECONNRESET", "ECONNABORTED"].includes(
+      code,
+    )
+  ) {
+    return "timeout";
+  }
+
+  const message = getErrorMessage(err);
+  if (!message) return null;
+  return classifyFailoverReason(message);
+}
+
+export function describeFailoverError(err: unknown): {
+  message: string;
+  reason?: FailoverReason;
+  status?: number;
+  code?: string;
+} {
+  if (isFailoverError(err)) {
+    return {
+      message: err.message,
+      reason: err.reason,
+      status: err.status,
+      code: err.code,
+    };
+  }
+  const message = getErrorMessage(err) || String(err);
+  return {
+    message,
+    reason: resolveFailoverReasonFromError(err) ?? undefined,
+    status: getStatusCode(err),
+    code: getErrorCode(err),
+  };
+}
+
+export function coerceToFailoverError(
+  err: unknown,
+  context?: {
+    provider?: string;
+    model?: string;
+    profileId?: string;
+  },
+): FailoverError | null {
+  if (isFailoverError(err)) return err;
+  const reason = resolveFailoverReasonFromError(err);
+  if (!reason) return null;
+
+  const message = getErrorMessage(err) || String(err);
+  const status = getStatusCode(err) ?? resolveFailoverStatus(reason);
+  const code = getErrorCode(err);
+
+  return new FailoverError(message, {
+    reason,
+    provider: context?.provider,
+    model: context?.model,
+    profileId: context?.profileId,
+    status,
+    code,
+    cause: err instanceof Error ? err : undefined,
+  });
+}

src/agents/identity.test.ts

@@ -0,0 +1,65 @@
+import { describe, expect, it } from "vitest";
+import type { ClawdbotConfig } from "../config/config.js";
+import { resolveMessagePrefix, resolveResponsePrefix } from "./identity.js";
+
+describe("message prefix resolution", () => {
+  it("returns configured messagePrefix override", () => {
+    const cfg: ClawdbotConfig = {};
+    expect(
+      resolveMessagePrefix(cfg, "main", {
+        configured: "[x]",
+        hasAllowFrom: true,
+      }),
+    ).toBe("[x]");
+    expect(
+      resolveMessagePrefix(cfg, "main", {
+        configured: "",
+        hasAllowFrom: false,
+      }),
+    ).toBe("");
+  });
+
+  it("defaults messagePrefix based on allowFrom + identity", () => {
+    const cfg: ClawdbotConfig = {
+      agents: { list: [{ id: "main", identity: { name: "Richbot" } }] },
+    };
+    expect(resolveMessagePrefix(cfg, "main", { hasAllowFrom: true })).toBe("");
+    expect(resolveMessagePrefix(cfg, "main", { hasAllowFrom: false })).toBe(
+      "[Richbot]",
+    );
+  });
+
+  it("falls back to [clawdbot] when identity is missing", () => {
+    const cfg: ClawdbotConfig = {};
+    expect(resolveMessagePrefix(cfg, "main", { hasAllowFrom: false })).toBe(
+      "[clawdbot]",
+    );
+  });
+});
+
+describe("response prefix resolution", () => {
+  it("does not apply any default when unset", () => {
+    const cfg: ClawdbotConfig = {
+      agents: { list: [{ id: "main", identity: { name: "Richbot" } }] },
+    };
+    expect(resolveResponsePrefix(cfg, "main")).toBeUndefined();
+  });
+
+  it("returns explicit responsePrefix when set", () => {
+    const cfg: ClawdbotConfig = { messages: { responsePrefix: "PFX" } };
+    expect(resolveResponsePrefix(cfg, "main")).toBe("PFX");
+  });
+
+  it("supports responsePrefix: auto (identity-derived opt-in)", () => {
+    const withIdentity: ClawdbotConfig = {
+      agents: { list: [{ id: "main", identity: { name: "Richbot" } }] },
+      messages: { responsePrefix: "auto" },
+    };
+    expect(resolveResponsePrefix(withIdentity, "main")).toBe("[Richbot]");
+
+    const withoutIdentity: ClawdbotConfig = {
+      messages: { responsePrefix: "auto" },
+    };
+    expect(resolveResponsePrefix(withoutIdentity, "main")).toBeUndefined();
+  });
+});

src/agents/identity.ts

@@ -32,9 +32,9 @@ export function resolveIdentityNamePrefix(
 export function resolveMessagePrefix(
   cfg: ClawdbotConfig,
   agentId: string,
-  opts?: { hasAllowFrom?: boolean; fallback?: string },
+  opts?: { configured?: string; hasAllowFrom?: boolean; fallback?: string },
 ): string {
-  const configured = cfg.messages?.messagePrefix;
+  const configured = opts?.configured ?? cfg.messages?.messagePrefix;
   if (configured !== undefined) return configured;
 
   const hasAllowFrom = opts?.hasAllowFrom === true;
@@ -50,8 +50,13 @@ export function resolveResponsePrefix(
   agentId: string,
 ): string | undefined {
   const configured = cfg.messages?.responsePrefix;
-  if (configured !== undefined) return configured;
-  return resolveIdentityNamePrefix(cfg, agentId);
+  if (configured !== undefined) {
+    if (configured === "auto") {
+      return resolveIdentityNamePrefix(cfg, agentId);
+    }
+    return configured;
+  }
+  return undefined;
 }
 
 export function resolveEffectiveMessagesConfig(

src/agents/lanes.ts

@@ -0,0 +1,2 @@
+export const AGENT_LANE_NESTED = "nested" as const;
+export const AGENT_LANE_SUBAGENT = "subagent" as const;

src/agents/model-auth.ts

@@ -139,6 +139,7 @@ export function resolveEnvApiKey(provider: string): EnvApiKeyResult | null {
     minimax: "MINIMAX_API_KEY",
     zai: "ZAI_API_KEY",
     mistral: "MISTRAL_API_KEY",
+    "opencode-zen": "OPENCODE_ZEN_API_KEY",
   };
   const envVar = envMap[provider];
   if (!envVar) return null;

src/agents/model-fallback.test.ts

@@ -0,0 +1,135 @@
+import { describe, expect, it, vi } from "vitest";
+
+import type { ClawdbotConfig } from "../config/config.js";
+import { runWithModelFallback } from "./model-fallback.js";
+
+function makeCfg(overrides: Partial<ClawdbotConfig> = {}): ClawdbotConfig {
+  return {
+    agents: {
+      defaults: {
+        model: {
+          primary: "openai/gpt-4.1-mini",
+          fallbacks: ["anthropic/claude-haiku-3-5"],
+        },
+      },
+    },
+    ...overrides,
+  } as ClawdbotConfig;
+}
+
+describe("runWithModelFallback", () => {
+  it("does not fall back on non-auth errors", async () => {
+    const cfg = makeCfg();
+    const run = vi
+      .fn()
+      .mockRejectedValueOnce(new Error("bad request"))
+      .mockResolvedValueOnce("ok");
+
+    await expect(
+      runWithModelFallback({
+        cfg,
+        provider: "openai",
+        model: "gpt-4.1-mini",
+        run,
+      }),
+    ).rejects.toThrow("bad request");
+    expect(run).toHaveBeenCalledTimes(1);
+  });
+
+  it("falls back on auth errors", async () => {
+    const cfg = makeCfg();
+    const run = vi
+      .fn()
+      .mockRejectedValueOnce(Object.assign(new Error("nope"), { status: 401 }))
+      .mockResolvedValueOnce("ok");
+
+    const result = await runWithModelFallback({
+      cfg,
+      provider: "openai",
+      model: "gpt-4.1-mini",
+      run,
+    });
+
+    expect(result.result).toBe("ok");
+    expect(run).toHaveBeenCalledTimes(2);
+    expect(run.mock.calls[1]?.[0]).toBe("anthropic");
+    expect(run.mock.calls[1]?.[1]).toBe("claude-haiku-3-5");
+  });
+
+  it("falls back on 402 payment required", async () => {
+    const cfg = makeCfg();
+    const run = vi
+      .fn()
+      .mockRejectedValueOnce(
+        Object.assign(new Error("payment required"), { status: 402 }),
+      )
+      .mockResolvedValueOnce("ok");
+
+    const result = await runWithModelFallback({
+      cfg,
+      provider: "openai",
+      model: "gpt-4.1-mini",
+      run,
+    });
+
+    expect(result.result).toBe("ok");
+    expect(run).toHaveBeenCalledTimes(2);
+    expect(run.mock.calls[1]?.[0]).toBe("anthropic");
+    expect(run.mock.calls[1]?.[1]).toBe("claude-haiku-3-5");
+  });
+
+  it("falls back on billing errors", async () => {
+    const cfg = makeCfg();
+    const run = vi
+      .fn()
+      .mockRejectedValueOnce(
+        new Error(
+          "LLM request rejected: Your credit balance is too low to access the Anthropic API. Please go to Plans & Billing to upgrade or purchase credits.",
+        ),
+      )
+      .mockResolvedValueOnce("ok");
+
+    const result = await runWithModelFallback({
+      cfg,
+      provider: "openai",
+      model: "gpt-4.1-mini",
+      run,
+    });
+
+    expect(result.result).toBe("ok");
+    expect(run).toHaveBeenCalledTimes(2);
+    expect(run.mock.calls[1]?.[0]).toBe("anthropic");
+    expect(run.mock.calls[1]?.[1]).toBe("claude-haiku-3-5");
+  });
+
+  it("appends the configured primary as a last fallback", async () => {
+    const cfg = makeCfg({
+      agents: {
+        defaults: {
+          model: {
+            primary: "openai/gpt-4.1-mini",
+            fallbacks: [],
+          },
+        },
+      },
+    });
+    const run = vi
+      .fn()
+      .mockRejectedValueOnce(
+        Object.assign(new Error("timeout"), { code: "ETIMEDOUT" }),
+      )
+      .mockResolvedValueOnce("ok");
+
+    const result = await runWithModelFallback({
+      cfg,
+      provider: "openrouter",
+      model: "meta-llama/llama-3.3-70b:free",
+      run,
+    });
+
+    expect(result.result).toBe("ok");
+    expect(run).toHaveBeenCalledTimes(2);
+    expect(result.provider).toBe("openai");
+    expect(result.model).toBe("gpt-4.1-mini");
+  });
+});

src/agents/model-fallback.ts

@@ -1,11 +1,18 @@
 import type { ClawdbotConfig } from "../config/config.js";
 import { DEFAULT_MODEL, DEFAULT_PROVIDER } from "./defaults.js";
+import {
+  coerceToFailoverError,
+  describeFailoverError,
+  isFailoverError,
+} from "./failover-error.js";
 import {
   buildModelAliasIndex,
   modelKey,
   parseModelRef,
+  resolveConfiguredModelRef,
   resolveModelRefFromString,
 } from "./model-selection.js";
+import type { FailoverReason } from "./pi-embedded-helpers.js";
 
 type ModelCandidate = {
   provider: string;
@@ -16,6 +23,9 @@ type FallbackAttempt = {
   provider: string;
   model: string;
   error: string;
+  reason?: FailoverReason;
+  status?: number;
+  code?: string;
 };
 
 function isAbortError(err: unknown): boolean {
@@ -119,6 +129,13 @@ function resolveFallbackCandidates(params: {
 }): ModelCandidate[] {
   const provider = params.provider.trim() || DEFAULT_PROVIDER;
   const model = params.model.trim() || DEFAULT_MODEL;
+  const primary = params.cfg
+    ? resolveConfiguredModelRef({
+        cfg: params.cfg,
+        defaultProvider: DEFAULT_PROVIDER,
+        defaultModel: DEFAULT_MODEL,
+      })
+    : null;
   const aliasIndex = buildModelAliasIndex({
     cfg: params.cfg ?? {},
     defaultProvider: DEFAULT_PROVIDER,
@@ -160,6 +177,10 @@ function resolveFallbackCandidates(params: {
     addCandidate(resolved.ref, true);
   }
 
+  if (primary?.provider && primary.model) {
+    addCandidate({ provider: primary.provider, model: primary.model }, false);
+  }
+
   return candidates;
 }
 
@@ -197,16 +218,27 @@ export async function runWithModelFallback<T>(params: {
       };
     } catch (err) {
       if (isAbortError(err)) throw err;
-      lastError = err;
+      const normalized =
+        coerceToFailoverError(err, {
+          provider: candidate.provider,
+          model: candidate.model,
+        }) ?? err;
+      if (!isFailoverError(normalized)) throw err;
+
+      lastError = normalized;
+      const described = describeFailoverError(normalized);
       attempts.push({
         provider: candidate.provider,
         model: candidate.model,
-        error: err instanceof Error ? err.message : String(err),
+        error: described.message,
+        reason: described.reason,
+        status: described.status,
+        code: described.code,
       });
       await params.onError?.({
         provider: candidate.provider,
         model: candidate.model,
-        error: err,
+        error: normalized,
         attempt: i + 1,
         total: candidates.length,
       });
@@ -219,7 +251,9 @@ export async function runWithModelFallback<T>(params: {
       ? attempts
           .map(
             (attempt) =>
-              `${attempt.provider}/${attempt.model}: ${attempt.error}`,
+              `${attempt.provider}/${attempt.model}: ${attempt.error}${
+                attempt.reason ? ` (${attempt.reason})` : ""
+              }`,
           )
           .join(" | ")
       : "unknown";

src/agents/model-selection.test.ts

@@ -1,10 +1,13 @@
 import { describe, expect, it } from "vitest";
 
 import type { ClawdbotConfig } from "../config/config.js";
+import { DEFAULT_PROVIDER } from "./defaults.js";
 import {
   buildAllowedModelSet,
   modelKey,
   parseModelRef,
+  resolveAllowedModelRef,
+  resolveHooksGmailModel,
 } from "./model-selection.js";
 
 const catalog = [
@@ -70,3 +73,133 @@ describe("parseModelRef", () => {
     });
   });
 });
+
+describe("resolveHooksGmailModel", () => {
+  it("returns null when hooks.gmail.model is not set", () => {
+    const cfg = {} satisfies ClawdbotConfig;
+    const result = resolveHooksGmailModel({
+      cfg,
+      defaultProvider: DEFAULT_PROVIDER,
+    });
+    expect(result).toBeNull();
+  });
+
+  it("returns null when hooks.gmail.model is empty", () => {
+    const cfg = {
+      hooks: { gmail: { model: "" } },
+    } satisfies ClawdbotConfig;
+    const result = resolveHooksGmailModel({
+      cfg,
+      defaultProvider: DEFAULT_PROVIDER,
+    });
+    expect(result).toBeNull();
+  });
+
+  it("parses provider/model from hooks.gmail.model", () => {
+    const cfg = {
+      hooks: { gmail: { model: "openrouter/meta-llama/llama-3.3-70b:free" } },
+    } satisfies ClawdbotConfig;
+    const result = resolveHooksGmailModel({
+      cfg,
+      defaultProvider: DEFAULT_PROVIDER,
+    });
+    expect(result).toEqual({
+      provider: "openrouter",
+      model: "meta-llama/llama-3.3-70b:free",
+    });
+  });
+
+  it("resolves alias from agent.models", () => {
+    const cfg = {
+      agents: {
+        defaults: {
+          models: {
+            "anthropic/claude-sonnet-4-1": { alias: "Sonnet" },
+          },
+        },
+      },
+      hooks: { gmail: { model: "Sonnet" } },
+    } satisfies ClawdbotConfig;
+    const result = resolveHooksGmailModel({
+      cfg,
+      defaultProvider: DEFAULT_PROVIDER,
+    });
+    expect(result).toEqual({
+      provider: "anthropic",
+      model: "claude-sonnet-4-1",
+    });
+  });
+
+  it("uses default provider when model omits provider", () => {
+    const cfg = {
+      hooks: { gmail: { model: "claude-haiku-3-5" } },
+    } satisfies ClawdbotConfig;
+    const result = resolveHooksGmailModel({
+      cfg,
+      defaultProvider: "anthropic",
+    });
+    expect(result).toEqual({
+      provider: "anthropic",
+      model: "claude-haiku-3-5",
+    });
+  });
+});
+
+describe("resolveAllowedModelRef", () => {
+  it("resolves aliases when allowed", () => {
+    const cfg = {
+      agents: {
+        defaults: {
+          models: {
+            "anthropic/claude-sonnet-4-1": { alias: "Sonnet" },
+          },
+        },
+      },
+    } satisfies ClawdbotConfig;
+    const resolved = resolveAllowedModelRef({
+      cfg,
+      catalog: [
+        {
+          provider: "anthropic",
+          id: "claude-sonnet-4-1",
+          name: "Sonnet",
+        },
+      ],
+      raw: "Sonnet",
+      defaultProvider: "anthropic",
+      defaultModel: "claude-opus-4-5",
+    });
+    expect("error" in resolved).toBe(false);
+    if ("ref" in resolved) {
+      expect(resolved.ref).toEqual({
+        provider: "anthropic",
+        model: "claude-sonnet-4-1",
+      });
+    }
+  });
+
+  it("rejects disallowed models", () => {
+    const cfg = {
+      agents: {
+        defaults: {
+          models: {
+            "openai/gpt-4": { alias: "GPT4" },
+          },
+        },
+      },
+    } satisfies ClawdbotConfig;
+    const resolved = resolveAllowedModelRef({
+      cfg,
+      catalog: [
+        { provider: "openai", id: "gpt-4", name: "GPT-4" },
+        { provider: "anthropic", id: "claude-sonnet-4-1", name: "Sonnet" },
+      ],
+      raw: "anthropic/claude-sonnet-4-1",
+      defaultProvider: "openai",
+      defaultModel: "gpt-4",
+    });
+    expect(resolved).toEqual({
+      error: "model not allowed: anthropic/claude-sonnet-4-1",
+    });
+  });
+});

src/agents/model-selection.ts

@@ -197,6 +197,76 @@ export function buildAllowedModelSet(params: {
   return { allowAny: false, allowedCatalog, allowedKeys };
 }
 
+export type ModelRefStatus = {
+  key: string;
+  inCatalog: boolean;
+  allowAny: boolean;
+  allowed: boolean;
+};
+
+export function getModelRefStatus(params: {
+  cfg: ClawdbotConfig;
+  catalog: ModelCatalogEntry[];
+  ref: ModelRef;
+  defaultProvider: string;
+  defaultModel?: string;
+}): ModelRefStatus {
+  const allowed = buildAllowedModelSet({
+    cfg: params.cfg,
+    catalog: params.catalog,
+    defaultProvider: params.defaultProvider,
+    defaultModel: params.defaultModel,
+  });
+  const key = modelKey(params.ref.provider, params.ref.model);
+  return {
+    key,
+    inCatalog: params.catalog.some(
+      (entry) => modelKey(entry.provider, entry.id) === key,
+    ),
+    allowAny: allowed.allowAny,
+    allowed: allowed.allowAny || allowed.allowedKeys.has(key),
+  };
+}
+
+export function resolveAllowedModelRef(params: {
+  cfg: ClawdbotConfig;
+  catalog: ModelCatalogEntry[];
+  raw: string;
+  defaultProvider: string;
+  defaultModel?: string;
+}):
+  | { ref: ModelRef; key: string }
+  | {
+      error: string;
+    } {
+  const trimmed = params.raw.trim();
+  if (!trimmed) return { error: "invalid model: empty" };
+
+  const aliasIndex = buildModelAliasIndex({
+    cfg: params.cfg,
+    defaultProvider: params.defaultProvider,
+  });
+  const resolved = resolveModelRefFromString({
+    raw: trimmed,
+    defaultProvider: params.defaultProvider,
+    aliasIndex,
+  });
+  if (!resolved) return { error: `invalid model: ${trimmed}` };
+
+  const status = getModelRefStatus({
+    cfg: params.cfg,
+    catalog: params.catalog,
+    ref: resolved.ref,
+    defaultProvider: params.defaultProvider,
+    defaultModel: params.defaultModel,
+  });
+  if (!status.allowed) {
+    return { error: `model not allowed: ${status.key}` };
+  }
+
+  return { ref: resolved.ref, key: status.key };
+}
+
 export function resolveThinkingDefault(params: {
   cfg: ClawdbotConfig;
   provider: string;
@@ -211,3 +281,28 @@ export function resolveThinkingDefault(params: {
   if (candidate?.reasoning) return "low";
   return "off";
 }
+
+/**
+ * Resolve the model configured for Gmail hook processing.
+ * Returns null if hooks.gmail.model is not set.
+ */
+export function resolveHooksGmailModel(params: {
+  cfg: ClawdbotConfig;
+  defaultProvider: string;
+}): ModelRef | null {
+  const hooksModel = params.cfg.hooks?.gmail?.model;
+  if (!hooksModel?.trim()) return null;
+
+  const aliasIndex = buildModelAliasIndex({
+    cfg: params.cfg,
+    defaultProvider: params.defaultProvider,
+  });
+
+  const resolved = resolveModelRefFromString({
+    raw: hooksModel,
+    defaultProvider: params.defaultProvider,
+    aliasIndex,
+  });
+
+  return resolved?.ref ?? null;
+}

src/agents/opencode-zen-models.test.ts

@@ -0,0 +1,88 @@
+import { describe, expect, it } from "vitest";
+
+import {
+  getOpencodeZenStaticFallbackModels,
+  OPENCODE_ZEN_MODEL_ALIASES,
+  resolveOpencodeZenAlias,
+  resolveOpencodeZenModelApi,
+} from "./opencode-zen-models.js";
+
+describe("resolveOpencodeZenAlias", () => {
+  it("resolves opus alias", () => {
+    expect(resolveOpencodeZenAlias("opus")).toBe("claude-opus-4-5");
+  });
+
+  it("resolves gpt5 alias", () => {
+    expect(resolveOpencodeZenAlias("gpt5")).toBe("gpt-5.2");
+  });
+
+  it("resolves gemini alias", () => {
+    expect(resolveOpencodeZenAlias("gemini")).toBe("gemini-3-pro");
+  });
+
+  it("returns input if no alias exists", () => {
+    expect(resolveOpencodeZenAlias("some-unknown-model")).toBe(
+      "some-unknown-model",
+    );
+  });
+
+  it("is case-insensitive", () => {
+    expect(resolveOpencodeZenAlias("OPUS")).toBe("claude-opus-4-5");
+    expect(resolveOpencodeZenAlias("Gpt5")).toBe("gpt-5.2");
+  });
+});
+
+describe("resolveOpencodeZenModelApi", () => {
+  it("returns openai-completions for all models (OpenCode Zen is OpenAI-compatible)", () => {
+    expect(resolveOpencodeZenModelApi("claude-opus-4-5")).toBe(
+      "openai-completions",
+    );
+    expect(resolveOpencodeZenModelApi("gpt-5.2")).toBe("openai-completions");
+    expect(resolveOpencodeZenModelApi("gemini-3-pro")).toBe(
+      "openai-completions",
+    );
+    expect(resolveOpencodeZenModelApi("some-unknown-model")).toBe(
+      "openai-completions",
+    );
+  });
+});
+
+describe("getOpencodeZenStaticFallbackModels", () => {
+  it("returns an array of models", () => {
+    const models = getOpencodeZenStaticFallbackModels();
+    expect(Array.isArray(models)).toBe(true);
+    expect(models.length).toBeGreaterThan(0);
+  });
+
+  it("includes Claude, GPT, and Gemini models", () => {
+    const models = getOpencodeZenStaticFallbackModels();
+    const ids = models.map((m) => m.id);
+
+    expect(ids).toContain("claude-opus-4-5");
+    expect(ids).toContain("gpt-5.2");
+    expect(ids).toContain("gemini-3-pro");
+  });
+
+  it("returns valid ModelDefinitionConfig objects", () => {
+    const models = getOpencodeZenStaticFallbackModels();
+    for (const model of models) {
+      expect(model.id).toBeDefined();
+      expect(model.name).toBeDefined();
+      expect(typeof model.reasoning).toBe("boolean");
+      expect(Array.isArray(model.input)).toBe(true);
+      expect(model.cost).toBeDefined();
+      expect(typeof model.contextWindow).toBe("number");
+      expect(typeof model.maxTokens).toBe("number");
+    }
+  });
+});
+
+describe("OPENCODE_ZEN_MODEL_ALIASES", () => {
+  it("has expected aliases", () => {
+    expect(OPENCODE_ZEN_MODEL_ALIASES.opus).toBe("claude-opus-4-5");
+    expect(OPENCODE_ZEN_MODEL_ALIASES.sonnet).toBe("claude-sonnet-4-20250514");
+    expect(OPENCODE_ZEN_MODEL_ALIASES.gpt5).toBe("gpt-5.2");
+    expect(OPENCODE_ZEN_MODEL_ALIASES.o1).toBe("o1-2025-04-16");
+    expect(OPENCODE_ZEN_MODEL_ALIASES.gemini).toBe("gemini-3-pro");
+  });
+});