Compare commits

..
Author SHA1 Message Date
Peter Steinberger 3ad11051c3 docs: expand Slack scope notes 2026-01-06 01:52:08 +01:00
Peter Steinberger 3b6b8e7696 Merge branch 'main' into docs/fix-slack-scopes 2026-01-06 00:39:12 +00:00
Manuel Hettich f1b023dc6c docs(slack): add missing scopes for DM replies
The manifest was missing scopes required for conversations.open API,
which is used to get DM channel IDs for replies.

Added scopes:
- im:write (required for DM replies)
- im:read (list DM conversations)
- mpim:write (reply to multi-person DMs)
- mpim:read (list MPDMs)
- groups:write (private channel interactions)
- groups:read (list private channels)

Without im:write, the example config (dm.enabled: true) cannot
actually reply to DMs - fails with missing_scope error.
2026-01-05 19:14:31 +00:00
1094 changed files with 21519 additions and 116216 deletions

No files matched your search

-1
View File
@@ -1 +0,0 @@
* text=auto eol=lf
-28
View File
@@ -1,28 +0,0 @@
---
name: Bug report
about: Report a problem or unexpected behavior in Clawdbot.
title: "[Bug]: "
labels: bug
---
## Summary
What went wrong?
## Steps to reproduce
1.
2.
3.
## Expected behavior
What did you expect to happen?
## Actual behavior
What actually happened?
## Environment
- Clawdbot version:
- OS:
- Install method (pnpm/npx/docker/etc):
## Logs or screenshots
Paste relevant logs or add screenshots (redact secrets).
-8
View File
@@ -1,8 +0,0 @@
blank_issues_enabled: true
contact_links:
- name: Onboarding
url: https://discord.gg/clawd
about: New to Clawdbot? Join Discord for setup guidance from Krill in #help.
- name: Support
url: https://discord.gg/clawd
about: Get help from Krill and the community on Discord in #help.
-18
View File
@@ -1,18 +0,0 @@
---
name: Feature request
about: Suggest an idea or improvement for Clawdbot.
title: "[Feature]: "
labels: enhancement
---
## Summary
Describe the problem you are trying to solve or the opportunity you see.
## Proposed solution
What would you like Clawdbot to do?
## Alternatives considered
Any other approaches you have considered?
## Additional context
Links, screenshots, or related issues.
+10 -80
View File
@@ -6,7 +6,7 @@ on:
jobs:
checks:
runs-on: blacksmith-4vcpu-ubuntu-2404
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
@@ -52,100 +52,32 @@ jobs:
exit 1
- name: Setup Node.js
if: matrix.runtime == 'node'
uses: actions/setup-node@v4
with:
node-version: 24
check-latest: true
- name: Setup Bun
if: matrix.runtime == 'bun'
uses: oven-sh/setup-bun@v2
with:
bun-version: latest
# bun.sh downloads currently fail with:
# "Failed to list releases from GitHub: 401" -> "Unexpected HTTP response: 400"
bun-download-url: "https://github.com/oven-sh/bun/releases/latest/download/bun-linux-x64.zip"
- name: Runtime versions
run: |
node -v
npm -v
bun -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 ${{ matrix.task }} (${{ matrix.runtime }})
run: ${{ matrix.command }}
checks-windows:
runs-on: blacksmith-4vcpu-windows-2025
defaults:
run:
shell: bash
strategy:
fail-fast: false
matrix:
include:
- runtime: node
task: lint
command: pnpm lint
- runtime: node
task: test
command: pnpm test
- runtime: node
task: build
command: pnpm build
- runtime: node
task: protocol
command: pnpm protocol:check
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 $((attempt * 10))
done
exit 1
- name: Setup Node.js
- name: Setup Node.js (tooling for bun)
if: matrix.runtime == 'bun'
uses: actions/setup-node@v4
with:
node-version: 24
check-latest: true
- name: Setup Bun
uses: oven-sh/setup-bun@v2
with:
bun-version: latest
- name: Runtime versions
run: |
node -v
npm -v
bun -v
if [ "${{ matrix.runtime }}" = "bun" ]; then bun -v; fi
- name: Capture node path
run: echo "NODE_BIN=$(dirname \"$(node -p \"process.execPath\")\")" >> "$GITHUB_ENV"
@@ -412,7 +344,7 @@ jobs:
PY
android:
runs-on: blacksmith-4vcpu-ubuntu-2404
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
@@ -448,8 +380,6 @@ jobs:
- name: Setup Android SDK
uses: android-actions/setup-android@v3
with:
accept-android-sdk-licenses: false
- name: Setup Gradle
uses: gradle/actions/setup-gradle@v4
-37
View File
@@ -1,37 +0,0 @@
name: Workflow Sanity
on:
pull_request:
push:
jobs:
no-tabs:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Fail on tabs in workflow files
run: |
python - <<'PY'
from __future__ import annotations
import pathlib
import sys
root = pathlib.Path(".github/workflows")
bad: list[str] = []
for path in sorted(root.rglob("*.yml")):
if b"\t" in path.read_bytes():
bad.append(str(path))
for path in sorted(root.rglob("*.yaml")):
if b"\t" in path.read_bytes():
bad.append(str(path))
if bad:
print("Tabs found in workflow file(s):")
for path in bad:
print(f"- {path}")
sys.exit(1)
PY
-6
View File
@@ -3,8 +3,6 @@ node_modules
dist
*.bun-build
pnpm-lock.yaml
bun.lock
bun.lockb
coverage
.pnpm-store
.worktrees/
@@ -50,7 +48,3 @@ apps/ios/*.dSYM.zip
# provisioning profiles (local)
apps/ios/*.mobileprovision
.env
# Local untracked files
.local/
.vscode/
+16 -49
View File
@@ -5,19 +5,9 @@
- Tests: colocated `*.test.ts`.
- Docs: `docs/` (images, queue, Pi config). Built output lives in `dist/`.
## Docs Linking (Mintlify)
- Docs are hosted on Mintlify (docs.clawd.bot).
- Internal doc links in `docs/**/*.md`: root-relative, no `.md`/`.mdx` (example: `[Config](/configuration)`).
- Section cross-references: use anchors on root-relative paths (example: `[Hooks](/configuration#hooks)`).
- README (GitHub): keep absolute docs URLs (`https://docs.clawd.bot/...`) so links work on GitHub.
## Build, Test, and Development Commands
- Runtime baseline: Node **22+** (keep Node + Bun paths working).
- Install deps: `pnpm install`
- Also supported: `bun install` (keep `pnpm-lock.yaml` + Bun patching in sync when touching deps/patches).
- Prefer Bun for TypeScript execution (scripts, dev, tests): `bun <file.ts>` / `bunx <tool>`.
- Run CLI in dev: `pnpm clawdbot ...` (bun) or `pnpm dev`.
- Node remains supported for running built output (`dist/*`) and production installs.
- Run CLI in dev: `pnpm clawdbot ...` (tsx entry) or `pnpm dev` for `src/index.ts`.
- Type-check/build: `pnpm build` (tsc)
- Lint/format: `pnpm lint` (biome check), `pnpm format` (biome format)
- Tests: `pnpm test` (vitest); coverage: `pnpm test:coverage`
@@ -25,10 +15,8 @@
## Coding Style & Naming Conventions
- Language: TypeScript (ESM). Prefer strict typing; avoid `any`.
- Formatting/linting via Biome; run `pnpm lint` before commits.
- Add brief code comments for tricky or non-obvious logic.
- Keep files concise; extract helpers instead of “V2” copies. Use existing patterns for CLI options and dependency injection via `createDefaultDeps`.
- Aim to keep files under ~700 LOC; guideline only (not a hard guardrail). Split/refactor when it improves clarity or testability.
- Naming: use **Clawdbot** for product/app/docs headings; use `clawdbot` for CLI command, package/binary, paths, and config keys.
## Testing Guidelines
- Framework: Vitest with V8 coverage thresholds (70% lines/branches/functions/statements).
@@ -42,69 +30,48 @@
- Follow concise, action-oriented commit messages (e.g., `CLI: add verbose flag to send`).
- Group related changes; avoid bundling unrelated refactors.
- PRs should summarize scope, note testing performed, and mention any user-facing changes or new flags.
- PR review flow: when given a PR link, review via `gh pr view`/`gh pr diff` and do **not** change branches.
- PR merge flow: create a temp branch from `main`, merge the PR branch into it (prefer squash unless commit history is important; use rebase/merge when it is). Always try to merge the PR unless it’s truly difficult, then use another approach. If we squash, add the PR author as a co-contributor. Apply fixes, add changelog entry (include PR # + thanks), run full gate before the final commit, commit, merge back to `main`, delete the temp branch, and end on `main`.
- When working on a PR: add a changelog entry with the PR number and thank the contributor.
- When working on an issue: reference the issue in the changelog entry.
- When merging a PR: leave a PR comment that explains exactly what we did and include the SHA hashes.
- When merging a PR from a new contributor: add their avatar to the README “Thanks to all clawtributors” thumbnail list.
- After merging a PR: run `bun scripts/update-clawtributors.ts` if the contributor is missing, then commit the regenerated README.
### PR Workflow (Review vs Land)
- **Review mode (PR link only):** read `gh pr view/diff`; **do not** switch branches; **do not** change code.
- **Landing mode:** create an integration branch from `main`, bring in PR commits (**prefer rebase** for linear history; **merge allowed** when complexity/conflicts make it safer), apply fixes, add changelog (+ thanks + PR #), run full gate **locally before committing** (`pnpm lint && pnpm build && pnpm test`), commit, merge back to `main`, then `git switch main` (never stay on a topic branch after landing). Important: contributor needs to be in git graph after this!
## Security & Configuration Tips
- Web provider stores creds at `~/.clawdbot/credentials/`; rerun `clawdbot login` if logged out.
- Pi sessions live under `~/.clawdbot/sessions/` by default; the base directory is not configurable.
- Never commit or publish real phone numbers, videos, or live configuration values. Use obviously fake placeholders in docs, tests, and examples.
## Troubleshooting
- Rebrand/migration issues (Clawdis → Clawdbot) or legacy config/service warnings: run `clawdbot doctor` (see `docs/gateway/doctor.md`).
## Agent-Specific Notes
- Vocabulary: "makeup" = "mac app".
- When answering questions, respond with high-confidence answers only: verify in code; do not guess.
- 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.
- Gateway currently runs only as the menubar app (launchctl shows `application.com.steipete.clawdbot.debug.*`), 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 expecting `com.steipete.clawdbot`. **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 subsystem `com.steipete.clawdbot`; it supports follow/tail/category filters and expects passwordless sudo for `/usr/bin/log`.
- Also read the shared guardrails at `~/Projects/oracle/AGENTS.md` and `~/Projects/agent-scripts/AGENTS.MD` before making changes; align with any cross-repo rules noted there.
- SwiftUI state management (iOS/macOS): prefer the `Observation` framework (`@Observable`, `@Bindable`) over `ObservableObject`/`@StateObject`; don’t introduce new `ObservableObject` unless required for compatibility, and migrate existing usages when touching related code.
- Connection providers: when adding a new connection, update every UI surface and docs (macOS app, web UI, mobile if applicable, onboarding/overview docs) and add matching status + configuration forms so provider lists and settings stay in sync.
- Version locations: `package.json` (CLI), `apps/android/app/build.gradle.kts` (versionName/versionCode), `apps/ios/Sources/Info.plist` + `apps/ios/Tests/Info.plist` (CFBundleShortVersionString/CFBundleVersion), `apps/macos/Sources/Clawdbot/Resources/Info.plist` (CFBundleShortVersionString/CFBundleVersion), `docs/install/updating.md` (pinned npm version), `docs/platforms/mac/release.md` (APP_VERSION/APP_BUILD examples), Peekaboo Xcode projects/Info.plists (MARKETING_VERSION/CURRENT_PROJECT_VERSION).
- **Restart apps:** “restart iOS/Android apps” means rebuild (recompile/install) and relaunch, not just kill/launch.
- **Device checks:** before testing, verify connected real devices (iOS/Android) before reaching for simulators/emulators.
- iOS Team ID lookup: `security find-identity -p codesigning -v` → use Apple Development (…) TEAMID. Fallback: `defaults read com.apple.dt.Xcode IDEProvisioningTeamIdentifiers`.
- A2UI bundle hash: `src/canvas-host/a2ui/.bundle.hash` is auto-generated; ignore unexpected changes, and only regenerate via `pnpm canvas:a2ui:bundle` (or `scripts/bundle-a2ui.sh`) when needed. Commit the hash as a separate commit.
- Release signing/notary keys are managed outside the repo; follow internal release docs.
- Notary auth env vars (`APP_STORE_CONNECT_ISSUER_ID`, `APP_STORE_CONNECT_KEY_ID`, `APP_STORE_CONNECT_API_KEY_P8`) are expected in your environment (per internal release docs).
- **Multi-agent safety:** do **not** create/apply/drop `git stash` entries unless explicitly requested (this includes `git pull --rebase --autostash`). Assume other agents may be working; keep unrelated WIP untouched and avoid cross-cutting state changes.
- **Multi-agent safety:** when the user says "push", you may `git pull --rebase` to integrate latest changes (never discard other agents' work). When the user says "commit", scope to your changes only. When the user says "commit all", commit everything in grouped chunks.
- **Multi-agent safety:** do **not** create/remove/modify `git worktree` checkouts (or edit `.worktrees/*`) unless explicitly requested.
- **Multi-agent safety:** do **not** switch branches / check out a different branch unless explicitly requested.
- Notary key file lives at `~/Library/CloudStorage/Dropbox/Backup/AppStore/AuthKey_NJF3NFGTS3.p8` (Sparkle keys live under `~/Library/CloudStorage/Dropbox/Backup/Sparkle`).
- Notary auth env vars (`APP_STORE_CONNECT_ISSUER_ID`, `APP_STORE_CONNECT_KEY_ID`, `APP_STORE_CONNECT_API_KEY_P8`) are in `~/.profile`.
- **Multi-agent safety:** do **not** create/apply/drop `git stash` entries unless Peter explicitly asks (this includes `git pull --rebase --autostash`). Assume other agents may be working; keep unrelated WIP untouched and avoid cross-cutting state changes.
- **Multi-agent safety:** when Peter says "push", you may `git pull --rebase` to integrate latest changes (never discard other agents' work). When Peter says "commit", scope to your changes only. When Peter says "commit all", commit everything in grouped chunks.
- **Multi-agent safety:** do **not** create/remove/modify `git worktree` checkouts (or edit `.worktrees/*`) unless Peter explicitly asks.
- **Multi-agent safety:** do **not** switch branches / check out a different branch unless Peter explicitly asks.
- **Multi-agent safety:** running multiple agents is OK as long as each agent has its own session.
- **Multi-agent safety:** when you see unrecognized files, keep going; focus on your changes and commit only those.
- Lobster seam: use the shared CLI palette in `src/terminal/palette.ts` (no hardcoded colors); apply palette to onboarding/config prompts and other TTY UI output as needed.
- **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/sessions/*.jsonl` (newest unless a specific ID is given), not the default `sessions.json`. If logs are needed from Mac Studio, 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.
- Voice wake forwarding tips:
- Command template should stay `clawdbot-mac agent --message "${text}" --thinking low`; `VoiceWakeForwarder` already shell-escapes `${text}`. Don’t add extra quotes.
- launchd PATH is minimal; ensure the app’s launch agent PATH includes standard system paths plus your pnpm bin (typically `$HOME/Library/pnpm`) so `pnpm`/`clawdbot` binaries resolve when invoked via `clawdbot-mac`.
- For manual `clawdbot message send` messages that include `!`, use the heredoc pattern noted below to avoid the Bash tool’s escaping.
- launchd PATH is minimal; ensure the app’s launch agent sets PATH to include `/opt/homebrew/bin:/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin:/Users/steipete/Library/pnpm` so `pnpm`/`clawdbot` binaries resolve when invoked via `clawdbot-mac`.
- For manual `clawdbot send` messages that include `!`, use the heredoc pattern noted below to avoid the Bash tool’s escaping.
## Exclamation Mark Escaping Workaround
The Claude Code Bash tool escapes `!` to `\\!` in command arguments. When using `clawdbot message send` with messages containing exclamation marks, use heredoc syntax:
The Claude Code Bash tool escapes `!` to `\\!` in command arguments. When using `clawdbot send` with messages containing exclamation marks, use heredoc syntax:
```bash
# WRONG - will send "Hello\\!" with backslash
clawdbot message send --to "+1234" --message 'Hello!'
clawdbot send --to "+1234" --message 'Hello!'
# CORRECT - use heredoc to avoid escaping
clawdbot message send --to "+1234" --message "$(cat <<'EOF'
clawdbot send --to "+1234" --message "$(cat <<'EOF'
Hello!
EOF
)"
+156 -160
View File
@@ -1,170 +1,66 @@
# Changelog
**Why this looks different:** the project was renamed from **Clawdis → Clawdbot**. To make the transition clear, releases now use **date-based versions** (`YYYY.M.D`) and the changelog is **compressed** into milestone summaries. Full detail still lives in git history and the docs.
## Unreleased
- 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
- CLI: add `sandbox list` and `sandbox recreate` commands for managing Docker sandbox containers after image/config updates. (#563) — thanks @pasogott
- 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
- 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
- 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
- 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
- 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).
- CLI: move `clawdbot message` to subcommands (`message send|poll|…`), fold Discord/Slack/Telegram/WhatsApp tools into `message`, and require `--provider` unless only one provider is configured.
- CLI: improve `logs` output (pretty/plain/JSONL), add gateway unreachable hint, and document logging.
- 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
- 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.
- Agent: enable adaptive context pruning by default for tool-result trimming.
- 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
- Doctor: run legacy state migrations in non-interactive mode without prompts.
- Cron: parse Telegram topic targets for isolated delivery. (#478) — thanks @nachoiacovino
- 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
- 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: fix /status usage summary filtering for the active provider.
- 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.
- Status: show provider usage windows when auth uses token-based OAuth (e.g. Claude setup-token).
- Agent: promote `<think>`/`<thinking>` tag reasoning into structured thinking blocks so `/reasoning` works consistently for OpenAI-compat providers.
- macOS: package ClawdbotKit resources and Swift 6.2 compatibility dylib to avoid launch/tool crashes. (#473) — thanks @gupsammy
- WhatsApp: group `/model list` output by provider for scannability. (#456) - thanks @mcinteerj
- Hooks: allow per-hook model overrides for webhook/Gmail runs (e.g. GPT 5 Mini).
- Control UI: logs tab opens at the newest entries (bottom).
- Control UI: default to relative paths for control UI assets. (#569) — thanks @bjesuiter
- 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
- 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: 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
- 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
- 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
- Onboarding: avoid “token expired” for Codex CLI when expiry is heuristic.
- Onboarding: QuickStart jumps straight into provider selection with Telegram preselected when unset.
- Onboarding: QuickStart auto-installs the Gateway daemon with Node (no runtime picker).
- Onboarding: clarify WhatsApp owner number prompt and label pairing phone number.
- Auto-reply: normalize routed replies to drop NO_REPLY and apply response prefixes.
- Commands: add /debug for runtime config overrides (memory-only).
- Daemon runtime: remove Bun from selection options.
- CLI: restore hidden `gateway-daemon` alias for legacy launchd configs.
- Onboarding/Configure: add OpenAI API key flow that stores in shared `~/.clawdbot/.env` for launchd; simplify Anthropic token prompt order.
- Configure/Onboarding: show Control UI docs with gateway reachability status and only offer to open when a gateway is detected; default model prompt now prefers Opus 4.5 for Anthropic auth.
- Control UI: show skill install progress + per-skill results, hide install once binaries present. (#445) — thanks @pkrmf
- Providers/Doctor: surface Discord privileged intent (Message Content) misconfiguration with actionable warnings.
- Providers/Doctor: warn when Telegram config expects unmentioned group messages but Bot API privacy mode is likely enabled; surface WhatsApp login/disconnect hints.
- Providers/Doctor: add last inbound/outbound activity timestamps in `providers status` and extend `--probe` with Discord channel permission + Telegram group membership audits.
- Docs: add provider troubleshooting index (`/providers/troubleshooting`) and link it from the main troubleshooting guide.
- Docs: clarify model allowlist errors and add safety notes for verbose/reasoning in groups.
- Docs: add Ansible installation guide. (#545) — thanks @pasogott
- Telegram: include the user id in DM pairing messages and label it clearly in `clawdbot pairing list --provider telegram`.
- Apps: refresh iOS/Android/macOS app icons for Clawdbot branding. (#521) — thanks @fishfisher
- 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
- 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.
- Status: fix Claude usage snapshots when `anthropic:default` is a setup-token lacking `user:profile` by preferring `anthropic:claude-cli`; optional claude.ai fallback via `CLAUDE_AI_SESSION_KEY` / `CLAUDE_WEB_COOKIE`.
- Commands: allow /elevated off in groups without a mention; keep /elevated on mention-gated.
- Commands: keep multi-directive messages from clearing directive handling.
- Commands: warn when /elevated runs in direct (unsandboxed) runtime.
- Commands: treat mention-bypassed group command messages as mentioned so elevated directives respond.
- Commands: return /status in directive-only multi-line messages.
- Models: fall back to configured models when the provider catalog is unavailable.
- Agent system prompt: add messaging guidance for reply routing and cross-session sends. (#526) — thanks @neist
- Agent: bypass Anthropic OAuth tool-name blocks by capitalizing built-ins and keeping pruning tool matching case-insensitive. (#553) — thanks @andrewting19
- Commands/Tools: disable /restart and gateway restart tool by default (enable with commands.restart=true).
- Gateway/CLI: add `clawdbot gateway discover` (Bonjour scan on `local.` + `clawdbot.internal.`) with `--timeout` and `--json`. — thanks @steipete
- Gateway/CLI: make `clawdbot gateway status` human-readable by default, add `--json`, and probe localhost + configured remote (warn on multiple gateways). — thanks @steipete
- Gateway/CLI: support remote loopback gateways via SSH tunnel in `clawdbot gateway status` (`--ssh` / `--ssh-auto`). — thanks @steipete
- Gateway/Discovery: include `gatewayPort`/`sshPort`/`cliPath` in wide-area Bonjour records, and add a tailnet DNS fallback for `gateway discover` when split DNS isn’t configured. — thanks @steipete
- CLI: add global `--no-color` (and respect `NO_COLOR=1`) to disable ANSI output. — thanks @steipete
- CLI: centralize lobster palette + apply it to onboarding/config prompts. — thanks @steipete
- Gateway/CLI: add `clawdbot gateway --dev/--reset` to auto-create a dev config/workspace with a robot identity (no BOOTSTRAP.md), and reset wipes config/creds/sessions/workspace (subcommand --dev no longer collides with global --dev profile). — thanks @steipete
- Configure: stop prompting to open the Control UI (still shown in onboarding). — thanks @steipete
- Configure: add wizard mode to remove a provider config block. — thanks @steipete
- Onboarding/TUI: prompt to start TUI (best option) when BOOTSTRAP.md exists and add `tui --message` to auto-send the first prompt. — thanks @steipete
- Telegram: suppress grammY getUpdates stack traces; log concise retry message instead. — thanks @steipete
- Gateway/CLI: allow dev profile (`clawdbot --dev`) to auto-create the dev config + workspace. — thanks @steipete
- 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
## 2026.1.8
### Highlights
- Security: DMs locked down by default across providers; pairing-first + allowlist guidance.
- Sandbox: per-agent scope defaults + workspace access controls; tool/session isolation tuned.
- Agent loop: compaction, pruning, streaming, and error handling hardened.
- Providers: Telegram/WhatsApp/Discord/Slack reliability, threading, reactions, media, and retries improved.
- Control UI: logs tab, streaming stability, focus mode, and large-output rendering fixes.
- CLI/Gateway/Doctor: daemon/logs/status, auth migration, and diagnostics significantly expanded.
### Breaking
- **SECURITY (update ASAP):** inbound DMs are now **locked down by default** on Telegram/WhatsApp/Signal/iMessage/Discord/Slack.
- Previously, if you didn’t configure an allowlist, your bot could be **open to anyone** (especially discoverable Telegram bots).
- New default: DM pairing (`dmPolicy="pairing"` / `discord.dm.policy="pairing"` / `slack.dm.policy="pairing"`).
- To keep old “open to everyone” behavior: set `dmPolicy="open"` and include `"*"` in the relevant `allowFrom` (Discord/Slack: `discord.dm.allowFrom` / `slack.dm.allowFrom`).
- Approve requests via `clawdbot pairing list --provider <provider>` + `clawdbot pairing approve --provider <provider> <code>`.
- Sandbox: default `agent.sandbox.scope` to `"agent"` (one container/workspace per agent). Use `"session"` for per-session isolation; `"shared"` disables cross-session isolation.
- Timestamps in agent envelopes are now UTC (compact `YYYY-MM-DDTHH:mmZ`); removed `messages.timestampPrefix`. Add `agent.userTimezone` to tell the model the user’s local time (system prompt only).
- Model config schema changes (auth profiles + model lists); doctor auto-migrates and the gateway rewrites legacy configs on startup.
- Commands: gate all slash commands to authorized senders; add `/compact` to manually compact session context.
- Groups: `whatsapp.groups`, `telegram.groups`, and `imessage.groups` now act as allowlists when set. Add `"*"` to keep allow-all behavior.
- Auto-reply: removed `autoReply` from Discord/Slack/Telegram channel configs; use `requireMention` instead (Telegram topics now support `requireMention` overrides).
- CLI: remove `update`, `gateway-daemon`, `gateway {install|uninstall|start|stop|restart|daemon status|wake|send|agent}`, and `telegram` commands; move `login/logout` to `providers login/logout` (top-level aliases hidden); use `daemon` for service control, `send`/`agent`/`wake` for RPC, and `nodes canvas` for canvas ops.
### Fixes
- **CLI/Gateway/Doctor:** daemon runtime selection + improved logs/status/health/errors; auth/password handling for local CLI; richer close/timeout details; auto-migrate legacy config/sessions/state; integrity checks + repair prompts; `--yes`/`--non-interactive`; `--deep` gateway scans; better restart/service hints.
- **Agent loop + compaction:** compaction/pruning tuning, overflow handling, safer bootstrap context, and per-provider threading/confirmations; opt-in tool-result pruning + compact tracking.
- **Sandbox + tools:** per-agent sandbox overrides, workspaceAccess controls, session tool visibility, tool policy overrides, process isolation, and tool schema/timeout/reaction unification.
- **Providers (Telegram/WhatsApp/Discord/Slack/Signal/iMessage):** retry/backoff, threading, reactions, media groups/attachments, mention gating, typing behavior, and error/log stability; long polling + forum topic isolation for Telegram.
- **Gateway/CLI UX:** `clawdbot logs`, cron list colors/aliases, docs search, agents list/add/delete flows, status usage snapshots, runtime/auth source display, and `/status`/commands auth unification.
- **Control UI/Web:** logs tab, focus mode polish, config form resilience, streaming stability, tool output caps, windowed chat history, and reconnect/password URL auth.
- **macOS/Android/TUI/Build:** macOS gateway races, QR bundling, JSON5 config safety, Voice Wake hardening; Android EXIF rotation + APK naming/versioning; TUI key handling; tooling/bundling fixes.
- **Packaging/compat:** npm dist folder coverage, Node 25 qrcode-terminal import fixes, Bun/Playwright/WebSocket patches, and Docker Bun install.
- **Docs:** new FAQ/ClawdHub/config examples/showcase entries and clarified auth, sandbox, and systemd docs.
- Onboarding: resolve CLI entrypoint when running via `npx` so gateway daemon install works without a build step.
- Linux: auto-attempt lingering during onboarding (try without sudo, fallback to sudo) and prompt on install/restart to keep the gateway alive after logout/idle. Thanks @tobiasbischoff for PR #237.
- TUI: migrate key handling to the updated pi-tui Key matcher API.
- Logging: redact sensitive tokens in verbose tool summaries by default (configurable patterns).
- macOS: prefer gateway config reads/writes in local mode (fall back to disk if the gateway is unavailable).
- macOS: local gateway now connects via tailnet IP when bind mode is `tailnet`/`auto`.
- macOS: Connections settings now use a custom sidebar to avoid toolbar toggle issues, with rounded styling and full-width row hit targets.
- macOS: drop deprecated `afterMs` from agent wait params to match gateway schema.
- Auth: add OpenAI Codex OAuth support and migrate legacy oauth.json into auth.json.
- Model: `/model` list shows auth source (masked key or OAuth email) per provider.
- Model: `/model list` is an alias for `/model`.
- Model: `/model` output now includes auth source location (env/auth.json/models.json).
- Model: avoid duplicate `missing (missing)` auth labels in `/model` list output.
- Docs: clarify auth storage, migration, and OpenAI Codex OAuth onboarding.
- Sandbox: copy inbound media into sandbox workspaces so agent tools can read attachments.
- Control UI: show a reading indicator bubble while the assistant is responding.
- Control UI: animate reading indicator dots (honors reduced-motion).
- Control UI: stabilize chat streaming during tool runs (no flicker/vanishing text; correct run scoping).
- Status: show runtime (docker/direct) and move shortcuts to `/help`.
- Status: show model auth source (api-key/oauth).
- Block streaming: avoid splitting Markdown fenced blocks and reopen fences when forced to split.
- Block streaming: preserve leading indentation in block replies (lists, indented fences).
- Docs: document systemd lingering and logged-in session requirements on macOS/Windows.
- Auto-reply: unify tool/block/final delivery across providers and apply consistent heartbeat/prefix handling. Thanks @MSch for PR #225 (superseded commit 92c953d0749143eb2a3f31f3cd6ad0e8eabf48c3).
- Heartbeat: make HEARTBEAT_OK ack padding configurable across heartbeat and cron delivery. (#238) — thanks @jalehman
- WhatsApp: set sender E.164 for direct chats so owner commands work in DMs.
- Slack: keep auto-replies in the original thread when responding to thread messages. Thanks @scald for PR #251.
- Docs: clarify Slack manifest scopes (current vs optional) with references. Thanks @jarvis-medmatic for PR #235.
- Control UI: avoid Slack config ReferenceError by reading slack config snapshots. Thanks @sreekaransrinath for PR #249.
### Maintenance
- Skills additions (Himalaya email, CodexBar, 1Password).
- Dependency refreshes (pi-* stack, Slack SDK, discord-api-types, file-type, zod, Biome, Vite).
- Refactors: centralized group allowlist/mention policy; lint/import cleanup; switch tsx → bun for TS execution.
- Deps: bump pi-* stack, Slack SDK, discord-api-types, file-type, zod, and Biome.
- Skills: add CodexBar model usage helper with macOS requirement metadata.
- Skills: add 1Password CLI skill with op examples.
- Lint: organize imports and wrap long lines in reply commands.
- Deps: update to latest across the repo.
## 2026.1.5-3
### Fixes
- NPM package: include missing runtime dist folders (slack/signal/imessage/tui/wizard/control-ui/daemon) to avoid `ERR_MODULE_NOT_FOUND` in Node 25 npx installs.
## 2026.1.5-2
### Fixes
- NPM package: include `dist/sessions` so `clawdbot agent` resolves session helpers in npx installs.
- Node 25: avoid unsupported directory import by targeting `qrcode-terminal/vendor/QRCode/*.js` modules.
## 2026.1.5-1
### Fixes
- NPM package: include `dist/sessions` so `clawdbot agent` resolves session helpers in npx installs.
- Node 25: avoid unsupported directory import by targeting `qrcode-terminal/vendor/QRCode/index.js`.
## 2026.1.5
@@ -173,7 +69,6 @@
- Agent tools: new `image` tool routed to the image model (when configured).
- Config: default model shorthands (`opus`, `sonnet`, `gpt`, `gpt-mini`, `gemini`, `gemini-flash`).
- Docs: document built-in model shorthands + precedence (user config wins).
- Bun: optional local install/build workflow without maintaining a Bun lockfile (see `docs/bun.md`).
### Fixes
- Control UI: render Markdown in tool result cards.
@@ -192,9 +87,110 @@
- Env: load global `$CLAWDBOT_STATE_DIR/.env` (`~/.clawdbot/.env`) as a fallback after CWD `.env`.
- Env: optional login-shell env fallback (opt-in; imports expected keys without overriding existing env).
- Agent tools: OpenAI-compatible tool JSON Schemas (fix `browser`, normalize union schemas).
- Onboarding: when running from source, auto-build missing Control UI assets (`bun run ui:build`).
- Onboarding: when running from source, auto-build missing Control UI assets (`pnpm ui:build`).
- Discord/Slack: route reaction + system notifications to the correct session (no main-session bleed).
- Agent tools: honor `agent.tools` allow/deny policy even when sandbox is off.
- Discord: avoid duplicate replies when OpenAI emits repeated `message_end` events.
- Commands: unify /status (inline) and command auth across providers; group bypass for authorized control commands; remove Discord /clawd slash handler.
- CLI: run `clawdbot agent` via the Gateway by default; use `--local` to force embedded mode.
- Control UI: render Markdown in chat messages (sanitized).
## 2026.1.4
### Highlights
- Rename completion: all CLIs, paths, bundle IDs, env vars, and docs standardized on **Clawdbot**.
- Agent-to-agent relay: `sessions_send` ping‑pong with `REPLY_SKIP` plus announce step with `ANNOUNCE_SKIP`.
- Gateway quality-of-life: config hot reload, port config support, and Control UI base paths.
- Sandbox additions: per-session Docker sandbox with hardened limits + optional sandboxed Chromium.
- New node capability: `location.get` across macOS/iOS/Android (CLI + tools).
- Models CLI: scan OpenRouter free models (tools/images), manage aliases/fallbacks, and show last-used model in status.
### Breaking
- Tool names drop the `clawdbot_` prefix (`browser`, `canvas`, `nodes`, `cron`, `gateway`).
- Bash tool removes node-pty `stdinMode: "pty"` support (use tmux for real TTYs).
- Primary session key is fixed to `main` (or `global` for global scope).
### Fixes
- Doctor migrates legacy Clawdis config/service installs and normalizes sandbox Docker names.
- Doctor checks sandbox image availability and offers to build or fall back to legacy images.
- Presence beacons keep node lists fresh; Instances view stays accurate.
- Block streaming/chunking reliability (Telegram/Discord ordering, fewer duplicates).
- WhatsApp GIF playback for MP4-based GIFs.
- Onboarding + Control UI basePath handling fixes and UI polish.
- Clearer tool summaries, reduced log noise, and safer watchdog/queue behavior.
- Canvas host watcher resilience; build and packaging edge cases cleaned up.
### Docs
- Sandbox setup, hot reload, port config, and session announce step coverage.
- Skills and onboarding clarifications + additional examples.
## 2026.1.3 (beta 5)
### Breaking
- Skills config moved under `skills.*` (new `skills.entries`, `skills.allowBundled`).
- Group session keys now `surface:group:<id>` / `surface:channel:<id>`; legacy `group:*` removed.
- Discord config refactor; `discord.allowFrom` + `discord.requireMention` removed.
- Discord/Telegram require `enabled: true` in config when using env tokens.
- Routing `allowFrom`/mention settings moved to per-surface group settings.
### Highlights
- Talk Mode (continuous voice) with ElevenLabs TTS on macOS/iOS/Android.
- Discord: expanded tool actions, richer routing, and threaded reply tags.
- Auto-reply queue modes + session model overrides; TUI upgrades.
- Nix mode (declarative config) and Docker setup flow.
- Onboarding wizard + configure/doctor/update flows.
- Signal + iMessage providers; new skills (Trello, Things, Notes/Reminders, tmux coding).
- Browser tooling upgrades (remote CDP, no-sandbox, profiles).
### Fixes
- macOS codesign/TCC hardening and menu/UI stability improvements.
- Streaming/typing fixes; per-provider chunk limit tuning.
- Remote gateway auth + token handling tightened.
- Camera capture reliability and media sizing fixes.
## 2025.12.27 (betas 3–4)
### Highlights
- First-class tools replace `clawdbot-*` skills (browser, canvas, nodes, cron).
- Per-session model selection and custom model providers.
- Group activation commands; Discord provider for DMs/guilds.
- Gateway webhooks + Gmail Pub/Sub hooks.
- Command queue modes + `agent.maxConcurrent` cap.
- Background bash tasks with `process` tool; gateway in-process restart.
### Fixes
- Packaging fixes, heartbeat cleanup, WhatsApp reconnect reliability.
- macOS menu/Chat UI polish and presence reporting fixes.
## 2025.12.21 (beta 2)
### Highlights
- Bundled gateway packaging + DMG distribution pipeline.
- Skills platform (bundled/managed/workspace) with install gating + UI.
- Onboarding polish and agent UX improvements.
- Canvas host served from Gateway; browser control simplification.
## 2025.12.19 (beta 1)
### Highlights
- First Clawdbot release: Gateway WS control plane + optional Bridge.
- macOS menu bar companion app with Voice Wake + WebChat.
- iOS node pairing with Canvas surface.
- WhatsApp groups, thinking/verbose directives, health/status tooling.
### Breaking
- Switched to Pi-only agent runtime; legacy providers removed.
- Gateway became the single source of truth (no ad-hoc direct sends).
## 2025.12.05–2025.12.03 (pre-Clawdbot)
### Highlights
- Pi-only agent path and web-only gateway workflow.
- Thinking/verbose directives, group chat support, and heartbeat controls.
- `clawdbot agent` CLI added; session tables and health reporting.
## 2025.11.28–2025.11.25 (early web-only)
- Heartbeat CLI + interval handling.
- Media MIME sniffing, size caps, and timeout fallbacks.
- Web provider reconnects and early stability fixes.
-4
View File
@@ -1,9 +1,5 @@
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
+152 -191
View File
@@ -16,141 +16,109 @@
</p>
**Clawdbot** is a *personal AI assistant* you run on your own devices.
It answers you on the providers you already use (WhatsApp, Telegram, Slack, Discord, Signal, iMessage, WebChat), can speak and listen on macOS/iOS/Android, and can render a live Canvas you control. The Gateway is just the control plane — the product is the assistant.
It answers you on the surfaces you already use (WhatsApp, Telegram, Slack, Discord, Signal, iMessage, WebChat), can speak and listen on macOS/iOS/Android, and can render a live Canvas you control. The Gateway is just the control plane — the product is the assistant.
If you want a personal, single-user assistant that feels local, fast, and always-on, this is it.
[Website](https://clawdbot.com) · [Docs](https://docs.clawd.bot) · [Getting Started](https://docs.clawd.bot/getting-started) · [Updating](https://docs.clawd.bot/updating) · [Showcase](https://docs.clawd.bot/showcase) · [FAQ](https://docs.clawd.bot/faq) · [Wizard](https://docs.clawd.bot/wizard) · [Nix](https://github.com/clawdbot/nix-clawdbot) · [Docker](https://docs.clawd.bot/docker) · [Discord](https://discord.gg/clawd)
Website: [https://clawdbot.com](https://clawdbot.com) · Docs: [https://docs.clawdbot.com](https://docs.clawdbot.com/) · Showcase: [https://docs.clawdbot.com/showcase](https://docs.clawdbot.com/showcase) · FAQ: [https://docs.clawdbot.com/faq](https://docs.clawdbot.com/faq) · Wizard: [https://docs.clawdbot.com/wizard](https://docs.clawdbot.com/wizard) · Nix: [https://github.com/clawdbot/nix-clawdbot](https://github.com/clawdbot/nix-clawdbot) · Docker: [https://docs.clawdbot.com/docker](https://docs.clawdbot.com/docker) · Discord: [https://discord.gg/clawd](https://discord.gg/clawd)
Preferred setup: run the onboarding wizard (`clawdbot onboard`). It walks through gateway, workspace, providers, and skills. The CLI wizard is the recommended path and works on **macOS, Linux, and Windows (via WSL2; strongly recommended)**.
Preferred setup: run the onboarding wizard (`clawdbot onboard`). It walks through gateway, workspace, providers, and skills. The CLI wizard is the recommended path and works on **macOS, Windows, and Linux**.
Works with npm, pnpm, or bun.
New install? Start here: [Getting started](https://docs.clawd.bot/getting-started)
**Subscriptions (OAuth):**
- **[Anthropic](https://www.anthropic.com/)** (Claude Pro/Max)
- **[OpenAI](https://openai.com/)** (ChatGPT/Codex)
- **Anthropic** (Claude Pro/Max)
- **OpenAI** (ChatGPT/Codex)
Model note: while any model is supported, I strongly recommend **Anthropic Pro/Max (100/200) + Opus 4.5** for long‑context strength and better prompt‑injection resistance. See [Onboarding](https://docs.clawd.bot/onboarding).
Model note: while any model is supported, I strongly recommend **Anthropic Pro/Max (100/200) + Opus 4.5** for long‑context strength and better prompt‑injection resistance. See [Onboarding](https://docs.clawdbot.com/onboarding).
## Models (selection + auth)
## Recommended setup (from source)
- Models config + CLI: [Models](https://docs.clawd.bot/models)
- Auth profile rotation (OAuth vs API keys) + fallbacks: [Model failover](https://docs.clawd.bot/model-failover)
## Install (recommended)
Runtime: **Node ≥22**.
```bash
npm install -g clawdbot@latest
# or: pnpm add -g clawdbot@latest
clawdbot onboard --install-daemon
```
The wizard installs the Gateway daemon (launchd/systemd user service) so it stays running.
## Quick start (TL;DR)
Runtime: **Node ≥22**.
Full beginner guide (auth, pairing, providers): [Getting started](https://docs.clawd.bot/getting-started)
```bash
clawdbot onboard --install-daemon
clawdbot gateway --port 18789 --verbose
# Send a message
clawdbot message send --to +1234567890 --message "Hello from Clawdbot"
# Talk to the assistant (optionally deliver back to WhatsApp/Telegram/Slack/Discord)
clawdbot agent --message "Ship checklist" --thinking high
```
Upgrading? [Updating guide](https://docs.clawd.bot/updating) (and run `clawdbot doctor`).
## From source (development)
Prefer `pnpm` for builds from source. Bun is optional for running TypeScript directly.
Do **not** download prebuilt binaries. Build from source.
```bash
# Clone this repo
git clone https://github.com/clawdbot/clawdbot.git
cd clawdbot
pnpm install
pnpm ui:build # auto-installs UI deps on first run
pnpm build
pnpm ui:build
pnpm clawdbot onboard
```
pnpm clawdbot onboard --install-daemon
## Quick start (from source)
Runtime: **Node ≥22** + **pnpm**.
```bash
pnpm install
pnpm build
pnpm ui:build
# Recommended: run the onboarding wizard
pnpm clawdbot onboard
# Link WhatsApp (stores creds in ~/.clawdbot/credentials)
pnpm clawdbot login
# Start the gateway
pnpm clawdbot gateway --port 18789 --verbose
# Dev loop (auto-reload on TS changes)
pnpm gateway:watch
# Send a message
pnpm clawdbot send --to +1234567890 --message "Hello from Clawdbot"
# Talk to the assistant (optionally deliver back to WhatsApp/Telegram/Slack/Discord)
pnpm clawdbot agent --message "Ship checklist" --thinking high
```
Note: `pnpm clawdbot ...` runs TypeScript directly (via `tsx`). `pnpm build` produces `dist/` for running via Node / the packaged `clawdbot` binary.
Upgrading? `clawdbot doctor`.
## Security defaults (DM access)
Clawdbot connects to real messaging surfaces. Treat inbound DMs as **untrusted input**.
Full security guide: [Security](https://docs.clawd.bot/security)
Default behavior on Telegram/WhatsApp/Signal/iMessage/Discord/Slack:
- **DM pairing** (`dmPolicy="pairing"` / `discord.dm.policy="pairing"` / `slack.dm.policy="pairing"`): unknown senders receive a short pairing code and the bot does not process their message.
- Approve with: `clawdbot pairing approve --provider <provider> <code>` (then the sender is added to a local allowlist store).
- Public inbound DMs require an explicit opt-in: set `dmPolicy="open"` and include `"*"` in the provider allowlist (`allowFrom` / `discord.dm.allowFrom` / `slack.dm.allowFrom`).
Run `clawdbot doctor` to surface risky/misconfigured DM policies.
If you run from source, prefer `pnpm clawdbot …` (not global `clawdbot`).
## Highlights
- **[Local-first Gateway](https://docs.clawd.bot/gateway)** — single control plane for sessions, providers, tools, and events.
- **[Multi-provider inbox](https://docs.clawd.bot/surface)** — WhatsApp, Telegram, Slack, Discord, Signal, iMessage, WebChat, macOS, iOS/Android.
- **[Multi-agent routing](https://docs.clawd.bot/configuration)** — route inbound providers/accounts/peers to isolated agents (workspaces + per-agent sessions).
- **[Voice Wake](https://docs.clawd.bot/voicewake) + [Talk Mode](https://docs.clawd.bot/talk)** — always-on speech for macOS/iOS/Android with ElevenLabs.
- **[Live Canvas](https://docs.clawd.bot/mac/canvas)** — agent-driven visual workspace with [A2UI](https://docs.clawd.bot/mac/canvas#canvas-a2ui).
- **[First-class tools](https://docs.clawd.bot/tools)** — browser, canvas, nodes, cron, sessions, and Discord/Slack actions.
- **[Companion apps](https://docs.clawd.bot/macos)** — macOS menu bar app + iOS/Android [nodes](https://docs.clawd.bot/nodes).
- **[Onboarding](https://docs.clawd.bot/wizard) + [skills](https://docs.clawd.bot/skills)** — wizard-driven setup with bundled/managed/workspace skills.
- **[Local-first Gateway](https://docs.clawdbot.com/gateway)** — single control plane for sessions, providers, tools, and events.
- **[Multi-surface inbox](https://docs.clawdbot.com/surface)** — WhatsApp, Telegram, Slack, Discord, Signal, iMessage, WebChat, macOS, iOS/Android.
- **[Voice Wake](https://docs.clawdbot.com/voicewake) + [Talk Mode](https://docs.clawdbot.com/talk)** — always-on speech for macOS/iOS/Android with ElevenLabs.
- **[Live Canvas](https://docs.clawdbot.com/mac/canvas)** — agent-driven visual workspace with [A2UI](https://docs.clawdbot.com/refactor/canvas-a2ui).
- **[First-class tools](https://docs.clawdbot.com/tools)** — browser, canvas, nodes, cron, sessions, and Discord/Slack actions.
- **[Companion apps](https://docs.clawdbot.com/macos)** — macOS menu bar app + iOS/Android [nodes](https://docs.clawdbot.com/nodes).
- **[Onboarding](https://docs.clawdbot.com/wizard) + [skills](https://docs.clawdbot.com/skills)** — wizard-driven setup with bundled/managed/workspace skills.
## Everything we built so far
### Core platform
- [Gateway WS control plane](https://docs.clawd.bot/gateway) with sessions, presence, config, cron, webhooks, [Control UI](https://docs.clawd.bot/web), and [Canvas host](https://docs.clawd.bot/mac/canvas#canvas-a2ui).
- [CLI surface](https://docs.clawd.bot/agent-send): gateway, agent, send, [wizard](https://docs.clawd.bot/wizard), and [doctor](https://docs.clawd.bot/doctor).
- [Pi agent runtime](https://docs.clawd.bot/agent) in RPC mode with tool streaming and block streaming.
- [Session model](https://docs.clawd.bot/session): `main` for direct chats, group isolation, activation modes, queue modes, reply-back. Group rules: [Groups](https://docs.clawd.bot/groups).
- [Media pipeline](https://docs.clawd.bot/images): images/audio/video, transcription hooks, size caps, temp file lifecycle. Audio details: [Audio](https://docs.clawd.bot/audio).
- [Gateway WS control plane](https://docs.clawdbot.com/gateway) with sessions, presence, config, cron, webhooks, [Control UI](https://docs.clawdbot.com/web), and [Canvas host](https://docs.clawdbot.com/refactor/canvas-a2ui).
- [CLI surface](https://docs.clawdbot.com/agent-send): gateway, agent, send, [wizard](https://docs.clawdbot.com/wizard), and [doctor](https://docs.clawdbot.com/doctor).
- [Pi agent runtime](https://docs.clawdbot.com/agent) in RPC mode with tool streaming and block streaming.
- [Session model](https://docs.clawdbot.com/session): `main` for direct chats, group isolation, activation modes, queue modes, reply-back. Group rules: [Groups](https://docs.clawdbot.com/groups).
- [Media pipeline](https://docs.clawdbot.com/images): images/audio/video, transcription hooks, size caps, temp file lifecycle. Audio details: [Audio](https://docs.clawdbot.com/audio).
### Providers
- [Providers](https://docs.clawd.bot/surface): [WhatsApp](https://docs.clawd.bot/whatsapp) (Baileys), [Telegram](https://docs.clawd.bot/telegram) (grammY), [Slack](https://docs.clawd.bot/slack) (Bolt), [Discord](https://docs.clawd.bot/discord) (discord.js), [Signal](https://docs.clawd.bot/signal) (signal-cli), [iMessage](https://docs.clawd.bot/imessage) (imsg), [WebChat](https://docs.clawd.bot/webchat).
- [Group routing](https://docs.clawd.bot/group-messages): mention gating, reply tags, per-provider chunking and routing. Provider rules: [Providers](https://docs.clawd.bot/surface).
### Surfaces + providers
- [Providers](https://docs.clawdbot.com/surface): [WhatsApp](https://docs.clawdbot.com/whatsapp) (Baileys), [Telegram](https://docs.clawdbot.com/telegram) (grammY), [Slack](https://docs.clawdbot.com/slack) (Bolt), [Discord](https://docs.clawdbot.com/discord) (discord.js), [Signal](https://docs.clawdbot.com/signal) (signal-cli), [iMessage](https://docs.clawdbot.com/imessage) (imsg), [WebChat](https://docs.clawdbot.com/webchat).
- [Group routing](https://docs.clawdbot.com/group-messages): mention gating, reply tags, per-surface chunking and routing. Surface rules: [Surface routing](https://docs.clawdbot.com/surface).
### Apps + nodes
- [macOS app](https://docs.clawd.bot/macos): menu bar control plane, [Voice Wake](https://docs.clawd.bot/voicewake)/PTT, [Talk Mode](https://docs.clawd.bot/talk) overlay, [WebChat](https://docs.clawd.bot/webchat), debug tools, [remote gateway](https://docs.clawd.bot/remote) control.
- [iOS node](https://docs.clawd.bot/ios): [Canvas](https://docs.clawd.bot/mac/canvas), [Voice Wake](https://docs.clawd.bot/voicewake), [Talk Mode](https://docs.clawd.bot/talk), camera, screen recording, Bonjour pairing.
- [Android node](https://docs.clawd.bot/android): [Canvas](https://docs.clawd.bot/mac/canvas), [Talk Mode](https://docs.clawd.bot/talk), camera, screen recording, optional SMS.
- [macOS node mode](https://docs.clawd.bot/nodes): system.run/notify + canvas/camera exposure.
- [macOS app](https://docs.clawdbot.com/macos): menu bar control plane, [Voice Wake](https://docs.clawdbot.com/voicewake)/PTT, [Talk Mode](https://docs.clawdbot.com/talk) overlay, [WebChat](https://docs.clawdbot.com/webchat), debug tools, [remote gateway](https://docs.clawdbot.com/remote) control.
- [iOS node](https://docs.clawdbot.com/ios): [Canvas](https://docs.clawdbot.com/mac/canvas), [Voice Wake](https://docs.clawdbot.com/voicewake), [Talk Mode](https://docs.clawdbot.com/talk), camera, screen recording, Bonjour pairing.
- [Android node](https://docs.clawdbot.com/android): [Canvas](https://docs.clawdbot.com/mac/canvas), [Talk Mode](https://docs.clawdbot.com/talk), camera, screen recording, optional SMS.
- [macOS node mode](https://docs.clawdbot.com/nodes): system.run/notify + canvas/camera exposure.
### Tools + automation
- [Browser control](https://docs.clawd.bot/browser): dedicated clawd Chrome/Chromium, snapshots, actions, uploads, profiles.
- [Canvas](https://docs.clawd.bot/mac/canvas): [A2UI](https://docs.clawd.bot/mac/canvas#canvas-a2ui) push/reset, eval, snapshot.
- [Nodes](https://docs.clawd.bot/nodes): camera snap/clip, screen record, [location.get](https://docs.clawd.bot/location-command), notifications.
- [Cron + wakeups](https://docs.clawd.bot/cron); [webhooks](https://docs.clawd.bot/webhook); [Gmail Pub/Sub](https://docs.clawd.bot/gmail-pubsub).
- [Skills platform](https://docs.clawd.bot/skills): bundled, managed, and workspace skills with install gating + UI.
### Runtime + safety
- [Provider routing](https://docs.clawd.bot/provider-routing), [retry policy](https://docs.clawd.bot/retry), and [streaming/chunking](https://docs.clawd.bot/streaming).
- [Presence](https://docs.clawd.bot/presence), [typing indicators](https://docs.clawd.bot/typing-indicators), and [usage tracking](https://docs.clawd.bot/usage-tracking).
- [Models](https://docs.clawd.bot/models), [model failover](https://docs.clawd.bot/model-failover), and [session pruning](https://docs.clawd.bot/session-pruning).
- [Security](https://docs.clawd.bot/security) and [troubleshooting](https://docs.clawd.bot/troubleshooting).
- [Browser control](https://docs.clawdbot.com/browser): dedicated clawd Chrome/Chromium, snapshots, actions, uploads, profiles.
- [Canvas](https://docs.clawdbot.com/mac/canvas): [A2UI](https://docs.clawdbot.com/refactor/canvas-a2ui) push/reset, eval, snapshot.
- [Nodes](https://docs.clawdbot.com/nodes): camera snap/clip, screen record, [location.get](https://docs.clawdbot.com/location-command), notifications.
- [Cron + wakeups](https://docs.clawdbot.com/cron); [webhooks](https://docs.clawdbot.com/webhook); [Gmail Pub/Sub](https://docs.clawdbot.com/gmail-pubsub).
- [Skills platform](https://docs.clawdbot.com/skills): bundled, managed, and workspace skills with install gating + UI.
### Ops + packaging
- [Control UI](https://docs.clawd.bot/web) + [WebChat](https://docs.clawd.bot/webchat) served directly from the Gateway.
- [Tailscale Serve/Funnel](https://docs.clawd.bot/tailscale) or [SSH tunnels](https://docs.clawd.bot/remote) with token/password auth.
- [Nix mode](https://docs.clawd.bot/nix) for declarative config; [Docker](https://docs.clawd.bot/docker)-based installs.
- [Doctor](https://docs.clawd.bot/doctor) migrations, [logging](https://docs.clawd.bot/logging).
- [Control UI](https://docs.clawdbot.com/web) + [WebChat](https://docs.clawdbot.com/webchat) served directly from the Gateway.
- [Tailscale Serve/Funnel](https://docs.clawdbot.com/tailscale) or [SSH tunnels](https://docs.clawdbot.com/remote) with token/password auth.
- [Nix mode](https://docs.clawdbot.com/nix) for declarative config; [Docker](https://docs.clawdbot.com/docker)-based installs.
- [Doctor](https://docs.clawdbot.com/doctor) migrations, [logging](https://docs.clawdbot.com/logging).
## How it works (short)
@@ -172,12 +140,12 @@ WhatsApp / Telegram / Slack / Discord / Signal / iMessage / WebChat
## Key subsystems
- **[Gateway WebSocket network](https://docs.clawd.bot/architecture)** — single WS control plane for clients, tools, and events (plus ops: [Gateway runbook](https://docs.clawd.bot/gateway)).
- **[Tailscale exposure](https://docs.clawd.bot/tailscale)** — Serve/Funnel for the Gateway dashboard + WS (remote access: [Remote](https://docs.clawd.bot/remote)).
- **[Browser control](https://docs.clawd.bot/browser)** — clawd‑managed Chrome/Chromium with CDP control.
- **[Canvas + A2UI](https://docs.clawd.bot/mac/canvas)** — agent‑driven visual workspace (A2UI host: [Canvas/A2UI](https://docs.clawd.bot/mac/canvas#canvas-a2ui)).
- **[Voice Wake](https://docs.clawd.bot/voicewake) + [Talk Mode](https://docs.clawd.bot/talk)** — always‑on speech and continuous conversation.
- **[Nodes](https://docs.clawd.bot/nodes)** — Canvas, camera snap/clip, screen record, `location.get`, notifications, plus macOS‑only `system.run`/`system.notify`.
- **[Gateway WebSocket network](https://docs.clawdbot.com/architecture)** — single WS control plane for clients, tools, and events (plus ops: [Gateway runbook](https://docs.clawdbot.com/gateway)).
- **[Tailscale exposure](https://docs.clawdbot.com/tailscale)** — Serve/Funnel for the Gateway dashboard + WS (remote access: [Remote](https://docs.clawdbot.com/remote)).
- **[Browser control](https://docs.clawdbot.com/browser)** — clawd‑managed Chrome/Chromium with CDP control.
- **[Canvas + A2UI](https://docs.clawdbot.com/mac/canvas)** — agent‑driven visual workspace (A2UI host: [Canvas/A2UI](https://docs.clawdbot.com/refactor/canvas-a2ui)).
- **[Voice Wake](https://docs.clawdbot.com/voicewake) + [Talk Mode](https://docs.clawdbot.com/talk)** — always‑on speech and continuous conversation.
- **[Nodes](https://docs.clawdbot.com/nodes)** — Canvas, camera snap/clip, screen record, `location.get`, notifications, plus macOS‑only `system.run`/`system.notify`.
## Tailscale access (Gateway dashboard)
@@ -193,7 +161,7 @@ Notes:
- Funnel refuses to start unless `gateway.auth.mode: "password"` is set.
- Optional: `gateway.tailscale.resetOnExit` to undo Serve/Funnel on shutdown.
Details: [Tailscale guide](https://docs.clawd.bot/tailscale) · [Web surfaces](https://docs.clawd.bot/web)
Details: [Tailscale guide](https://docs.clawdbot.com/tailscale) · [Web surfaces](https://docs.clawdbot.com/web)
## Remote Gateway (Linux is great)
@@ -203,7 +171,7 @@ It’s perfectly fine to run the Gateway on a small Linux instance. Clients (mac
- **Device nodes** run device‑local actions (`system.run`, camera, screen recording, notifications) via `node.invoke`.
In short: bash runs where the Gateway lives; device actions run where the device lives.
Details: [Remote access](https://docs.clawd.bot/remote) · [Nodes](https://docs.clawd.bot/nodes) · [Security](https://docs.clawd.bot/security)
Details: [Remote access](https://docs.clawdbot.com/remote) · [Nodes](https://docs.clawdbot.com/nodes) · [Security](https://docs.clawdbot.com/security)
## macOS permissions via the Gateway protocol
@@ -218,7 +186,7 @@ Elevated bash (host permissions) is separate from macOS TCC:
- Use `/elevated on|off` to toggle per‑session elevated access when enabled + allowlisted.
- Gateway persists the per‑session toggle via `sessions.patch` (WS method) alongside `thinkingLevel`, `verboseLevel`, `model`, `sendPolicy`, and `groupActivation`.
Details: [Nodes](https://docs.clawd.bot/nodes) · [macOS app](https://docs.clawd.bot/macos) · [Gateway protocol](https://docs.clawd.bot/architecture)
Details: [Nodes](https://docs.clawdbot.com/nodes) · [macOS app](https://docs.clawdbot.com/macos) · [Gateway protocol](https://docs.clawdbot.com/architecture)
## Agent to Agent (sessions_* tools)
@@ -227,24 +195,22 @@ Details: [Nodes](https://docs.clawd.bot/nodes) · [macOS app](https://docs.clawd
- `sessions_history` — fetch transcript logs for a session.
- `sessions_send` — message another session; optional reply‑back ping‑pong + announce step (`REPLY_SKIP`, `ANNOUNCE_SKIP`).
Details: [Session tools](https://docs.clawd.bot/session-tool)
Details: [Session tools](https://docs.clawdbot.com/session-tool)
## Skills registry (ClawdHub)
ClawdHub is a minimal skill registry. With ClawdHub enabled, the agent can search for skills automatically and pull in new ones as needed.
[ClawdHub](https://ClawdHub.com)
https://ClawdHub.com
## Chat commands
Send these in WhatsApp/Telegram/Slack/WebChat (group commands are owner-only):
- `/status` — compact session status (model + tokens, cost when available)
- `/status` — health + session info (group shows activation mode)
- `/new` or `/reset` — reset the session
- `/compact` — compact session context (summary)
- `/think <level>` — off|minimal|low|medium|high
- `/verbose on|off`
- `/cost on|off` — append per-response token/cost usage lines
- `/restart` — restart the gateway (owner-only in groups)
- `/activation mention|always` — group activation toggle (groups only)
@@ -274,17 +240,17 @@ Note: signed builds required for macOS permissions to stick across rebuilds (see
- Voice trigger forwarding + Canvas surface.
- Controlled via `clawdbot nodes …`.
Runbook: [iOS connect](https://docs.clawd.bot/ios).
Runbook: [iOS connect](https://docs.clawdbot.com/ios).
### Android node (optional)
- Pairs via the same Bridge + pairing flow as iOS.
- Exposes Canvas, Camera, and Screen capture commands.
- Runbook: [Android connect](https://docs.clawd.bot/android).
- Runbook: [Android connect](https://docs.clawdbot.com/android).
## Agent workspace + skills
- Workspace root: `~/clawd` (configurable via `agents.defaults.workspace`).
- Workspace root: `~/clawd` (configurable via `agent.workspace`).
- Injected prompt files: `AGENTS.md`, `SOUL.md`, `TOOLS.md`.
- Skills: `~/clawd/skills/<skill>/SKILL.md`.
@@ -300,26 +266,25 @@ Minimal `~/.clawdbot/clawdbot.json` (model + defaults):
}
```
[Full configuration reference (all keys + examples).](https://docs.clawd.bot/configuration)
[Full configuration reference (all keys + examples).](https://docs.clawdbot.com/configuration)
## Security model (important)
- **Default:** tools run on the host for the **main** session, so the agent has full access when it’s just you.
- **Group/channel safety:** set `agents.defaults.sandbox.mode: "non-main"` to run **non‑main sessions** (groups/channels) inside per‑session Docker sandboxes; bash then runs in Docker for those sessions.
- **Sandbox defaults:** allowlist `bash`, `process`, `read`, `write`, `edit`, `sessions_list`, `sessions_history`, `sessions_send`, `sessions_spawn`; denylist `browser`, `canvas`, `nodes`, `cron`, `discord`, `gateway`.
- **Group/channel safety:** set `agent.sandbox.mode: "non-main"` to run **non‑main sessions** (groups/channels) inside per‑session Docker sandboxes; bash then runs in Docker for those sessions.
- **Sandbox defaults:** allowlist `bash`, `process`, `read`, `write`, `edit`; denylist `browser`, `canvas`, `nodes`, `cron`, `discord`, `gateway`.
Details: [Security guide](https://docs.clawd.bot/security) · [Docker + sandboxing](https://docs.clawd.bot/docker) · [Sandbox config](https://docs.clawd.bot/configuration)
Details: [Security guide](https://docs.clawdbot.com/security) · [Docker + sandboxing](https://docs.clawdbot.com/docker) · [Sandbox config](https://docs.clawdbot.com/configuration)
### [WhatsApp](https://docs.clawd.bot/whatsapp)
### [WhatsApp](https://docs.clawdbot.com/whatsapp)
- Link the device: `pnpm clawdbot login` (stores creds in `~/.clawdbot/credentials`).
- Allowlist who can talk to the assistant via `whatsapp.allowFrom`.
- If `whatsapp.groups` is set, it becomes a group allowlist; include `"*"` to allow all.
### [Telegram](https://docs.clawd.bot/telegram)
### [Telegram](https://docs.clawdbot.com/telegram)
- Set `TELEGRAM_BOT_TOKEN` or `telegram.botToken` (env wins).
- Optional: set `telegram.groups` (with `telegram.groups."*".requireMention`); when set, it is a group allowlist (include `"*"` to allow all). Also `telegram.allowFrom` or `telegram.webhookUrl` as needed.
- Optional: set `telegram.groups` (with `telegram.groups."*".requireMention`), `telegram.allowFrom`, or `telegram.webhookUrl` as needed.
```json5
{
@@ -329,14 +294,14 @@ Details: [Security guide](https://docs.clawd.bot/security) · [Docker + sandboxi
}
```
### [Slack](https://docs.clawd.bot/slack)
### [Slack](https://docs.clawdbot.com/slack)
- Set `SLACK_BOT_TOKEN` + `SLACK_APP_TOKEN` (or `slack.botToken` + `slack.appToken`).
### [Discord](https://docs.clawd.bot/discord)
### [Discord](https://docs.clawdbot.com/discord)
- Set `DISCORD_BOT_TOKEN` or `discord.token` (env wins).
- Optional: set `commands.native`, `commands.text`, or `commands.useAccessGroups`, plus `discord.dm.allowFrom`, `discord.guilds`, or `discord.mediaMaxMb` as needed.
- Optional: set `discord.slashCommand`, `discord.dm.allowFrom`, `discord.guilds`, or `discord.mediaMaxMb` as needed.
```json5
{
@@ -346,16 +311,15 @@ Details: [Security guide](https://docs.clawd.bot/security) · [Docker + sandboxi
}
```
### [Signal](https://docs.clawd.bot/signal)
### [Signal](https://docs.clawdbot.com/signal)
- Requires `signal-cli` and a `signal` config section.
### [iMessage](https://docs.clawd.bot/imessage)
### [iMessage](https://docs.clawdbot.com/imessage)
- macOS only; Messages must be signed in.
- If `imessage.groups` is set, it becomes a group allowlist; include `"*"` to allow all.
### [WebChat](https://docs.clawd.bot/webchat)
### [WebChat](https://docs.clawdbot.com/webchat)
- Uses the Gateway WebSocket; no separate WebChat port/config.
@@ -374,99 +338,96 @@ Browser control (optional):
## Docs
Use these when you’re past the onboarding flow and want the deeper reference.
- [Start with the docs index for navigation and “what’s where.”](https://docs.clawd.bot)
- [Read the architecture overview for the gateway + protocol model.](https://docs.clawd.bot/architecture)
- [Use the full configuration reference when you need every key and example.](https://docs.clawd.bot/configuration)
- [Run the Gateway by the book with the operational runbook.](https://docs.clawd.bot/gateway)
- [Learn how the Control UI/Web surfaces work and how to expose them safely.](https://docs.clawd.bot/web)
- [Understand remote access over SSH tunnels or tailnets.](https://docs.clawd.bot/remote)
- [Follow the onboarding wizard flow for a guided setup.](https://docs.clawd.bot/wizard)
- [Wire external triggers via the webhook surface.](https://docs.clawd.bot/webhook)
- [Set up Gmail Pub/Sub triggers.](https://docs.clawd.bot/gmail-pubsub)
- [Learn the macOS menu bar companion details.](https://docs.clawd.bot/mac/menu-bar)
- [Platform guides: Windows (WSL2)](https://docs.clawd.bot/windows), [Linux](https://docs.clawd.bot/linux), [macOS](https://docs.clawd.bot/macos), [iOS](https://docs.clawd.bot/ios), [Android](https://docs.clawd.bot/android)
- [Debug common failures with the troubleshooting guide.](https://docs.clawd.bot/troubleshooting)
- [Review security guidance before exposing anything.](https://docs.clawd.bot/security)
- [Start with the docs index for navigation and “what’s where.”](https://docs.clawdbot.com/)
- [Read the architecture overview for the gateway + protocol model.](https://docs.clawdbot.com/architecture)
- [Use the full configuration reference when you need every key and example.](https://docs.clawdbot.com/configuration)
- [Run the Gateway by the book with the operational runbook.](https://docs.clawdbot.com/gateway)
- [Learn how the Control UI/Web surfaces work and how to expose them safely.](https://docs.clawdbot.com/web)
- [Understand remote access over SSH tunnels or tailnets.](https://docs.clawdbot.com/remote)
- [Follow the onboarding wizard flow for a guided setup.](https://docs.clawdbot.com/wizard)
- [Wire external triggers via the webhook surface.](https://docs.clawdbot.com/webhook)
- [Set up Gmail Pub/Sub triggers.](https://docs.clawdbot.com/gmail-pubsub)
- [Learn the macOS menu bar companion details.](https://docs.clawdbot.com/mac/menu-bar)
- [Platform guides: Windows](https://docs.clawdbot.com/windows), [Linux](https://docs.clawdbot.com/linux), [macOS](https://docs.clawdbot.com/macos), [iOS](https://docs.clawdbot.com/ios), [Android](https://docs.clawdbot.com/android)
- [Debug common failures with the troubleshooting guide.](https://docs.clawdbot.com/troubleshooting)
- [Review security guidance before exposing anything.](https://docs.clawdbot.com/security)
## Advanced docs (discovery + control)
- [Discovery + transports](https://docs.clawd.bot/discovery)
- [Bonjour/mDNS](https://docs.clawd.bot/bonjour)
- [Gateway pairing](https://docs.clawd.bot/gateway/pairing)
- [Remote gateway README](https://docs.clawd.bot/remote-gateway-readme)
- [Control UI](https://docs.clawd.bot/control-ui)
- [Dashboard](https://docs.clawd.bot/dashboard)
- [Discovery + transports](https://docs.clawdbot.com/discovery)
- [Bonjour/mDNS](https://docs.clawdbot.com/bonjour)
- [Gateway pairing](https://docs.clawdbot.com/gateway/pairing)
- [Remote gateway README](https://docs.clawdbot.com/remote-gateway-readme)
- [Control UI](https://docs.clawdbot.com/control-ui)
- [Dashboard](https://docs.clawdbot.com/dashboard)
## Operations & troubleshooting
- [Health checks](https://docs.clawd.bot/health)
- [Gateway lock](https://docs.clawd.bot/gateway-lock)
- [Background process](https://docs.clawd.bot/background-process)
- [Browser troubleshooting (Linux)](https://docs.clawd.bot/browser-linux-troubleshooting)
- [Logging](https://docs.clawd.bot/logging)
- [Health checks](https://docs.clawdbot.com/health)
- [Gateway lock](https://docs.clawdbot.com/gateway-lock)
- [Background process](https://docs.clawdbot.com/background-process)
- [Browser troubleshooting (Linux)](https://docs.clawdbot.com/browser-linux-troubleshooting)
- [Logging](https://docs.clawdbot.com/logging)
## Deep dives
- [Agent loop](https://docs.clawd.bot/agent-loop)
- [Presence](https://docs.clawd.bot/presence)
- [TypeBox schemas](https://docs.clawd.bot/typebox)
- [RPC adapters](https://docs.clawd.bot/rpc)
- [Queue](https://docs.clawd.bot/queue)
- [Agent loop](https://docs.clawdbot.com/agent-loop)
- [Presence](https://docs.clawdbot.com/presence)
- [TypeBox schemas](https://docs.clawdbot.com/typebox)
- [RPC adapters](https://docs.clawdbot.com/rpc)
- [Queue](https://docs.clawdbot.com/queue)
## Workspace & skills
- [Skills config](https://docs.clawd.bot/skills-config)
- [Default AGENTS](https://docs.clawd.bot/AGENTS.default)
- [Templates: AGENTS](https://docs.clawd.bot/templates/AGENTS)
- [Templates: BOOTSTRAP](https://docs.clawd.bot/templates/BOOTSTRAP)
- [Templates: IDENTITY](https://docs.clawd.bot/templates/IDENTITY)
- [Templates: SOUL](https://docs.clawd.bot/templates/SOUL)
- [Templates: TOOLS](https://docs.clawd.bot/templates/TOOLS)
- [Templates: USER](https://docs.clawd.bot/templates/USER)
- [Skills config](https://docs.clawdbot.com/skills-config)
- [Default AGENTS](https://docs.clawdbot.com/AGENTS.default)
- [Templates: AGENTS](https://docs.clawdbot.com/templates/AGENTS)
- [Templates: BOOTSTRAP](https://docs.clawdbot.com/templates/BOOTSTRAP)
- [Templates: IDENTITY](https://docs.clawdbot.com/templates/IDENTITY)
- [Templates: SOUL](https://docs.clawdbot.com/templates/SOUL)
- [Templates: TOOLS](https://docs.clawdbot.com/templates/TOOLS)
- [Templates: USER](https://docs.clawdbot.com/templates/USER)
## Platform internals
- [macOS dev setup](https://docs.clawd.bot/mac/dev-setup)
- [macOS menu bar](https://docs.clawd.bot/mac/menu-bar)
- [macOS voice wake](https://docs.clawd.bot/mac/voicewake)
- [iOS node](https://docs.clawd.bot/ios)
- [Android node](https://docs.clawd.bot/android)
- [Windows (WSL2)](https://docs.clawd.bot/windows)
- [Linux app](https://docs.clawd.bot/linux)
- [macOS dev setup](https://docs.clawdbot.com/mac/dev-setup)
- [macOS menu bar](https://docs.clawdbot.com/mac/menu-bar)
- [macOS voice wake](https://docs.clawdbot.com/mac/voicewake)
- [iOS node](https://docs.clawdbot.com/ios)
- [Android node](https://docs.clawdbot.com/android)
- [Windows app](https://docs.clawdbot.com/windows)
- [Linux app](https://docs.clawdbot.com/linux)
## Email hooks (Gmail)
- [docs.clawd.bot/gmail-pubsub](https://docs.clawd.bot/gmail-pubsub)
[Gmail Pub/Sub wiring (gcloud + gogcli), hook tokens, and auto-watch behavior are documented here.](https://docs.clawdbot.com/gmail-pubsub)
Gateway auto-starts the watcher when `hooks.enabled=true` and `hooks.gmail.account` is set; `clawdbot hooks gmail run` is the manual daemon wrapper if you don’t want auto-start.
```bash
clawdbot hooks gmail setup --account you@gmail.com
clawdbot hooks gmail run
```
## Clawd
Clawdbot was built for **Clawd**, a space lobster AI assistant. 🦞
by Peter Steinberger and the community.
- [clawd.me](https://clawd.me)
- [soul.md](https://soul.md)
- [steipete.me](https://steipete.me)
- https://clawd.me
- https://soul.md
- https://steipete.me
## Community
See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines, maintainers, and how to submit PRs.
AI/vibe-coded PRs welcome! 🤖
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/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/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/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/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/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/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/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/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/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/mbelinky"><img src="https://avatars.githubusercontent.com/u/132747814?v=4&s=48" width="48" height="48" alt="mbelinky" title="mbelinky"/></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/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/omniwired"><img src="https://avatars.githubusercontent.com/u/322761?v=4&s=48" width="48" height="48" alt="omniwired" title="omniwired"/></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/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/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/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/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/vsabavat"><img src="https://avatars.githubusercontent.com/u/50385532?v=4&s=48" width="48" height="48" alt="vsabavat" title="vsabavat"/></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/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/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/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/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/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/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/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/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/djangonavarro220"><img src="https://avatars.githubusercontent.com/u/251162586?v=4&s=48" width="48" height="48" alt="djangonavarro220" title="djangonavarro220"/></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/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>
</p>
+11 -11
View File
@@ -13,7 +13,7 @@ public struct WakeWordSegment: Sendable, Equatable {
self.range = range
}
public var end: TimeInterval { start + duration }
public var end: TimeInterval { self.start + self.duration }
}
public struct WakeWordGateConfig: Sendable, Equatable {
@@ -62,10 +62,10 @@ public enum WakeWordGate {
segments: [WakeWordSegment],
config: WakeWordGateConfig)
-> WakeWordGateMatch? {
let triggerTokens = normalizeTriggers(config.triggers)
let triggerTokens = self.normalizeTriggers(config.triggers)
guard !triggerTokens.isEmpty else { return nil }
let tokens = normalizeSegments(segments)
let tokens = self.normalizeSegments(segments)
guard !tokens.isEmpty else { return nil }
var best: (index: Int, triggerEnd: TimeInterval, gap: TimeInterval)?
@@ -89,7 +89,7 @@ public enum WakeWordGate {
}
guard let best else { return nil }
let command = commandText(transcript: transcript, segments: segments, triggerEndTime: best.triggerEnd)
let command = self.commandText(transcript: transcript, segments: segments, triggerEndTime: best.triggerEnd)
.trimmingCharacters(in: Self.whitespaceAndPunctuation)
guard command.count >= config.minCommandLength else { return nil }
return WakeWordGateMatch(triggerEndTime: best.triggerEnd, postGap: best.gap, command: command)
@@ -111,7 +111,7 @@ public enum WakeWordGate {
}
let text = segments
.filter { $0.start >= threshold && !normalizeToken($0.text).isEmpty }
.filter { $0.start >= threshold && !self.normalizeToken($0.text).isEmpty }
.map(\.text)
.joined(separator: " ")
return text.trimmingCharacters(in: Self.whitespaceAndPunctuation)
@@ -121,7 +121,7 @@ public enum WakeWordGate {
guard !text.isEmpty else { return false }
let normalized = text.lowercased()
for trigger in triggers {
let token = trigger.trimmingCharacters(in: whitespaceAndPunctuation).lowercased()
let token = trigger.trimmingCharacters(in: self.whitespaceAndPunctuation).lowercased()
if token.isEmpty { continue }
if normalized.contains(token) { return true }
}
@@ -131,11 +131,11 @@ public enum WakeWordGate {
public static func stripWake(text: String, triggers: [String]) -> String {
var out = text
for trigger in triggers {
let token = trigger.trimmingCharacters(in: whitespaceAndPunctuation)
let token = trigger.trimmingCharacters(in: self.whitespaceAndPunctuation)
guard !token.isEmpty else { continue }
out = out.replacingOccurrences(of: token, with: "", options: [.caseInsensitive])
}
return out.trimmingCharacters(in: whitespaceAndPunctuation)
return out.trimmingCharacters(in: self.whitespaceAndPunctuation)
}
private static func normalizeTriggers(_ triggers: [String]) -> [TriggerTokens] {
@@ -143,7 +143,7 @@ public enum WakeWordGate {
for trigger in triggers {
let tokens = trigger
.split(whereSeparator: { $0.isWhitespace })
.map { normalizeToken(String($0)) }
.map { self.normalizeToken(String($0)) }
.filter { !$0.isEmpty }
if tokens.isEmpty { continue }
output.append(TriggerTokens(tokens: tokens))
@@ -153,7 +153,7 @@ public enum WakeWordGate {
private static func normalizeSegments(_ segments: [WakeWordSegment]) -> [Token] {
segments.compactMap { segment in
let normalized = normalizeToken(segment.text)
let normalized = self.normalizeToken(segment.text)
guard !normalized.isEmpty else { return nil }
return Token(
normalized: normalized,
@@ -166,7 +166,7 @@ public enum WakeWordGate {
private static func normalizeToken(_ token: String) -> String {
token
.trimmingCharacters(in: whitespaceAndPunctuation)
.trimmingCharacters(in: self.whitespaceAndPunctuation)
.lowercased()
}
@@ -1,6 +1,6 @@
import Foundation
import SwabbleKit
import Testing
import SwabbleKit
@Suite struct WakeWordGateTests {
@Test func matchRequiresGapAfterTrigger() {
+2 -17
View File
@@ -1,5 +1,3 @@
import com.android.build.api.variant.impl.VariantOutputImpl
plugins {
id("com.android.application")
id("org.jetbrains.kotlin.android")
@@ -21,8 +19,8 @@ android {
applicationId = "com.clawdbot.android"
minSdk = 31
targetSdk = 36
versionCode = 20260109
versionName = "2026.1.9"
versionCode = 1
versionName = "2.0.0-beta3"
}
buildTypes {
@@ -56,19 +54,6 @@ android {
}
}
androidComponents {
onVariants { variant ->
variant.outputs
.filterIsInstance<VariantOutputImpl>()
.forEach { output ->
val versionName = output.versionName.orNull ?: "0"
val buildType = variant.buildType
val outputFileName = "clawdbot-${versionName}-${buildType}.apk"
output.outputFileName = outputFileName
}
}
}
kotlin {
compilerOptions {
jvmTarget.set(org.jetbrains.kotlin.gradle.dsl.JvmTarget.JVM_17)
@@ -12,7 +12,7 @@
"element",
"node",
"nodeId",
"id",
"jobId",
"requestId",
"to",
"channelId",
@@ -136,10 +136,10 @@
"label": "add",
"detailKeys": ["job.name", "job.id", "job.schedule", "job.cron"]
},
"update": { "label": "update", "detailKeys": ["id"] },
"remove": { "label": "remove", "detailKeys": ["id"] },
"run": { "label": "run", "detailKeys": ["id"] },
"runs": { "label": "runs", "detailKeys": ["id"] },
"update": { "label": "update", "detailKeys": ["jobId"] },
"remove": { "label": "remove", "detailKeys": ["jobId"] },
"run": { "label": "run", "detailKeys": ["jobId"] },
"runs": { "label": "runs", "detailKeys": ["jobId"] },
"wake": { "label": "wake", "detailKeys": ["text", "mode"] }
}
},
@@ -5,10 +5,8 @@ import android.content.Context
import android.annotation.SuppressLint
import android.graphics.Bitmap
import android.graphics.BitmapFactory
import android.graphics.Matrix
import android.util.Base64
import android.content.pm.PackageManager
import android.media.ExifInterface
import androidx.lifecycle.LifecycleOwner
import androidx.camera.core.CameraSelector
import androidx.camera.core.ImageCapture
@@ -88,19 +86,18 @@ class CameraCaptureManager(private val context: Context) {
provider.unbindAll()
provider.bindToLifecycle(owner, selector, capture)
val (bytes, orientation) = capture.takeJpegWithExif(context.mainExecutor())
val bytes = capture.takeJpegBytes(context.mainExecutor())
val decoded = BitmapFactory.decodeByteArray(bytes, 0, bytes.size)
?: throw IllegalStateException("UNAVAILABLE: failed to decode captured image")
val rotated = rotateBitmapByExif(decoded, orientation)
val scaled =
if (maxWidth != null && maxWidth > 0 && rotated.width > maxWidth) {
if (maxWidth != null && maxWidth > 0 && decoded.width > maxWidth) {
val h =
(rotated.height.toDouble() * (maxWidth.toDouble() / rotated.width.toDouble()))
(decoded.height.toDouble() * (maxWidth.toDouble() / decoded.width.toDouble()))
.toInt()
.coerceAtLeast(1)
rotated.scale(maxWidth, h)
decoded.scale(maxWidth, h)
} else {
rotated
decoded
}
val maxPayloadBytes = 5 * 1024 * 1024
@@ -197,31 +194,6 @@ class CameraCaptureManager(private val context: Context) {
)
}
private fun rotateBitmapByExif(bitmap: Bitmap, orientation: Int): Bitmap {
val matrix = Matrix()
when (orientation) {
ExifInterface.ORIENTATION_ROTATE_90 -> matrix.postRotate(90f)
ExifInterface.ORIENTATION_ROTATE_180 -> matrix.postRotate(180f)
ExifInterface.ORIENTATION_ROTATE_270 -> matrix.postRotate(270f)
ExifInterface.ORIENTATION_FLIP_HORIZONTAL -> matrix.postScale(-1f, 1f)
ExifInterface.ORIENTATION_FLIP_VERTICAL -> matrix.postScale(1f, -1f)
ExifInterface.ORIENTATION_TRANSPOSE -> {
matrix.postRotate(90f)
matrix.postScale(-1f, 1f)
}
ExifInterface.ORIENTATION_TRANSVERSE -> {
matrix.postRotate(-90f)
matrix.postScale(-1f, 1f)
}
else -> return bitmap
}
val rotated = Bitmap.createBitmap(bitmap, 0, 0, bitmap.width, bitmap.height, matrix, true)
if (rotated !== bitmap) {
bitmap.recycle()
}
return rotated
}
private fun parseFacing(paramsJson: String?): String? =
when {
paramsJson?.contains("\"front\"") == true -> "front"
@@ -282,8 +254,7 @@ private suspend fun Context.cameraProvider(): ProcessCameraProvider =
)
}
/** Returns (jpegBytes, exifOrientation) so caller can rotate the decoded bitmap. */
private suspend fun ImageCapture.takeJpegWithExif(executor: Executor): Pair<ByteArray, Int> =
private suspend fun ImageCapture.takeJpegBytes(executor: Executor): ByteArray =
suspendCancellableCoroutine { cont ->
val file = File.createTempFile("clawdbot-snap-", ".jpg")
val options = ImageCapture.OutputFileOptions.Builder(file).build()
@@ -292,19 +263,13 @@ private suspend fun ImageCapture.takeJpegWithExif(executor: Executor): Pair<Byte
executor,
object : ImageCapture.OnImageSavedCallback {
override fun onError(exception: ImageCaptureException) {
file.delete()
cont.resumeWithException(exception)
}
override fun onImageSaved(outputFileResults: ImageCapture.OutputFileResults) {
try {
val exif = ExifInterface(file.absolutePath)
val orientation = exif.getAttributeInt(
ExifInterface.TAG_ORIENTATION,
ExifInterface.ORIENTATION_NORMAL,
)
val bytes = file.readBytes()
cont.resume(Pair(bytes, orientation))
cont.resume(bytes)
} catch (e: Exception) {
cont.resumeWithException(e)
} finally {
@@ -4,7 +4,6 @@ import android.content.Context
import android.hardware.display.DisplayManager
import android.media.MediaRecorder
import android.media.projection.MediaProjectionManager
import android.os.Build
import android.util.Base64
import com.clawdbot.android.ScreenCaptureRequester
import kotlinx.coroutines.Dispatchers
@@ -66,7 +65,7 @@ class ScreenRecordManager(private val context: Context) {
val file = File.createTempFile("clawdbot-screen-", ".mp4")
if (includeAudio) ensureMicPermission()
val recorder = createMediaRecorder()
val recorder = MediaRecorder()
var virtualDisplay: android.hardware.display.VirtualDisplay? = null
try {
if (includeAudio) {
@@ -122,14 +121,6 @@ class ScreenRecordManager(private val context: Context) {
)
}
private fun createMediaRecorder(): MediaRecorder =
if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.S) {
MediaRecorder(context)
} else {
@Suppress("DEPRECATION")
MediaRecorder()
}
private suspend fun ensureMicPermission() {
val granted =
androidx.core.content.ContextCompat.checkSelfPermission(
@@ -39,7 +39,6 @@ import androidx.compose.material3.MaterialTheme
import androidx.compose.material3.ModalBottomSheet
import androidx.compose.material3.rememberModalBottomSheetState
import androidx.compose.material.icons.Icons
import androidx.compose.material.icons.automirrored.filled.ScreenShare
import androidx.compose.material.icons.filled.ChatBubble
import androidx.compose.material.icons.filled.CheckCircle
import androidx.compose.material.icons.filled.Error
@@ -48,6 +47,7 @@ import androidx.compose.material.icons.filled.PhotoCamera
import androidx.compose.material.icons.filled.RecordVoiceOver
import androidx.compose.material.icons.filled.Refresh
import androidx.compose.material.icons.filled.Report
import androidx.compose.material.icons.filled.ScreenShare
import androidx.compose.material.icons.filled.Settings
import androidx.compose.runtime.Composable
import androidx.compose.runtime.collectAsState
@@ -123,7 +123,7 @@ fun RootScreen(viewModel: MainViewModel) {
if (screenRecordActive) {
return@remember StatusActivity(
title = "Recording screen…",
icon = Icons.AutoMirrored.Filled.ScreenShare,
icon = Icons.Default.ScreenShare,
contentDescription = "Recording screen",
tint = androidx.compose.ui.graphics.Color.Red,
)
@@ -327,10 +327,11 @@ private fun CanvasView(viewModel: MainViewModel, modifier: Modifier = Modifier)
// Some embedded web UIs (incl. the "background website") use localStorage/sessionStorage.
settings.domStorageEnabled = true
settings.mixedContentMode = WebSettings.MIXED_CONTENT_COMPATIBILITY_MODE
if (WebViewFeature.isFeatureSupported(WebViewFeature.FORCE_DARK)) {
WebSettingsCompat.setForceDark(settings, WebSettingsCompat.FORCE_DARK_OFF)
}
if (WebViewFeature.isFeatureSupported(WebViewFeature.ALGORITHMIC_DARKENING)) {
WebSettingsCompat.setAlgorithmicDarkeningAllowed(settings, false)
} else {
disableForceDarkIfSupported(settings)
}
if (isDebuggable) {
Log.d("ClawdbotWebView", "userAgent: ${settings.userAgentString}")
@@ -413,12 +414,6 @@ private fun CanvasView(viewModel: MainViewModel, modifier: Modifier = Modifier)
)
}
private fun disableForceDarkIfSupported(settings: WebSettings) {
if (!WebViewFeature.isFeatureSupported(WebViewFeature.FORCE_DARK)) return
@Suppress("DEPRECATION")
WebSettingsCompat.setForceDark(settings, WebSettingsCompat.FORCE_DARK_OFF)
}
private class CanvasA2UIActionBridge(private val onMessage: (String) -> Unit) {
@JavascriptInterface
fun postMessage(payload: String?) {
@@ -714,7 +714,6 @@ class TalkModeManager(
systemTtsPendingId = null
}
@Suppress("OVERRIDE_DEPRECATION")
@Deprecated("Deprecated in Java")
override fun onError(utteranceId: String?) {
if (utteranceId == null) return
Binary file not shown.

Before

Width:  |  Height:  |  Size: 11 KiB

After

Width:  |  Height:  |  Size: 9.4 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 44 KiB

After

Width:  |  Height:  |  Size: 39 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 5.5 KiB

After

Width:  |  Height:  |  Size: 4.6 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 21 KiB

After

Width:  |  Height:  |  Size: 19 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 17 KiB

After

Width:  |  Height:  |  Size: 16 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 73 KiB

After

Width:  |  Height:  |  Size: 67 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 36 KiB

After

Width:  |  Height:  |  Size: 32 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 155 KiB

After

Width:  |  Height:  |  Size: 148 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 60 KiB

After

Width:  |  Height:  |  Size: 54 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 270 KiB

After

Width:  |  Height:  |  Size: 267 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 1.3 MiB

After

Width:  |  Height:  |  Size: 1.4 MiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 1.9 KiB

After

Width:  |  Height:  |  Size: 1.0 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.2 KiB

After

Width:  |  Height:  |  Size: 3.3 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 7.9 KiB

After

Width:  |  Height:  |  Size: 6.5 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 2.8 KiB

After

Width:  |  Height:  |  Size: 1.9 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 7.4 KiB

After

Width:  |  Height:  |  Size: 6.2 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 15 KiB

After

Width:  |  Height:  |  Size: 12 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.2 KiB

After

Width:  |  Height:  |  Size: 3.3 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 13 KiB

After

Width:  |  Height:  |  Size: 11 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 26 KiB

After

Width:  |  Height:  |  Size: 21 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 26 KiB

After

Width:  |  Height:  |  Size: 21 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 53 KiB

After

Width:  |  Height:  |  Size: 43 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 39 KiB

After

Width:  |  Height:  |  Size: 32 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 46 KiB

After

Width:  |  Height:  |  Size: 38 KiB

+2 -2
View File
@@ -19,9 +19,9 @@
<key>CFBundlePackageType</key>
<string>APPL</string>
<key>CFBundleShortVersionString</key>
<string>2026.1.9</string>
<string>1.0</string>
<key>CFBundleVersion</key>
<string>20260109</string>
<string>1</string>
<key>NSAppTransportSecurity</key>
<dict>
<key>NSAllowsArbitraryLoadsInWebContent</key>
@@ -5,8 +5,7 @@ import Testing
@Test func errorDescriptionsAreStable() {
#expect(CameraController.CameraError.cameraUnavailable.errorDescription == "Camera unavailable")
#expect(CameraController.CameraError.microphoneUnavailable.errorDescription == "Microphone unavailable")
#expect(CameraController.CameraError.permissionDenied(kind: "Camera")
.errorDescription == "Camera permission denied")
#expect(CameraController.CameraError.permissionDenied(kind: "Camera").errorDescription == "Camera permission denied")
#expect(CameraController.CameraError.invalidParams("bad").errorDescription == "bad")
#expect(CameraController.CameraError.captureFailed("nope").errorDescription == "nope")
#expect(CameraController.CameraError.exportFailed("export").errorDescription == "export")
+2 -2
View File
@@ -17,8 +17,8 @@
<key>CFBundlePackageType</key>
<string>BNDL</string>
<key>CFBundleShortVersionString</key>
<string>2026.1.9</string>
<string>1.0</string>
<key>CFBundleVersion</key>
<string>20260109</string>
<string>1</string>
</dict>
</plist>
@@ -20,3 +20,4 @@ import Testing
#expect(triggers == nil)
}
}
@@ -1,6 +1,6 @@
import Foundation
import SwabbleKit
import Testing
import SwabbleKit
@testable import Clawdbot
@Suite struct VoiceWakeManagerExtractCommandTests {
@@ -1,6 +1,6 @@
import Foundation
import SwabbleKit
import Testing
import SwabbleKit
@testable import Clawdbot
@Suite(.serialized) struct VoiceWakeManagerStateTests {
Binary file not shown.

Before

Width:  |  Height:  |  Size: 1.3 MiB

After

Width:  |  Height:  |  Size: 1.3 MiB

@@ -1,4 +1,3 @@
import ClawdbotProtocol
import SwiftUI
@MainActor
@@ -0,0 +1,54 @@
import Foundation
/// Lightweight `Codable` wrapper that round-trips heterogeneous JSON payloads.
/// Marked `@unchecked Sendable` because it can hold reference types.
struct AnyCodable: Codable, @unchecked Sendable {
let value: Any
init(_ value: Any) { self.value = value }
init(from decoder: Decoder) throws {
let container = try decoder.singleValueContainer()
if let intVal = try? container.decode(Int.self) { self.value = intVal; return }
if let doubleVal = try? container.decode(Double.self) { self.value = doubleVal; return }
if let boolVal = try? container.decode(Bool.self) { self.value = boolVal; return }
if let stringVal = try? container.decode(String.self) { self.value = stringVal; return }
if container.decodeNil() { self.value = NSNull(); return }
if let dict = try? container.decode([String: AnyCodable].self) { self.value = dict; return }
if let array = try? container.decode([AnyCodable].self) { self.value = array; return }
throw DecodingError.dataCorruptedError(
in: container,
debugDescription: "Unsupported type")
}
func encode(to encoder: Encoder) throws {
var container = encoder.singleValueContainer()
switch self.value {
case let intVal as Int: try container.encode(intVal)
case let doubleVal as Double: try container.encode(doubleVal)
case let boolVal as Bool: try container.encode(boolVal)
case let stringVal as String: try container.encode(stringVal)
case is NSNull: try container.encodeNil()
case let dict as [String: AnyCodable]: try container.encode(dict)
case let array as [AnyCodable]: try container.encode(array)
case let dict as [String: Any]:
try container.encode(dict.mapValues { AnyCodable($0) })
case let array as [Any]:
try container.encode(array.map { AnyCodable($0) })
case let dict as NSDictionary:
var converted: [String: AnyCodable] = [:]
for (k, v) in dict {
guard let key = k as? String else { continue }
converted[key] = AnyCodable(v)
}
try container.encode(converted)
case let array as NSArray:
try container.encode(array.map { AnyCodable($0) })
default:
let context = EncodingError.Context(
codingPath: encoder.codingPath,
debugDescription: "Unsupported type")
throw EncodingError.invalidValue(self.value, context)
}
}
}
+3 -14
View File
@@ -100,10 +100,6 @@ final class AppState {
}
}
var voiceWakeMicName: String {
didSet { self.ifNotPreview { UserDefaults.standard.set(self.voiceWakeMicName, forKey: voiceWakeMicNameKey) } }
}
var voiceWakeLocaleID: String {
didSet {
self.ifNotPreview {
@@ -233,7 +229,6 @@ final class AppState {
}
self.showDockIcon = UserDefaults.standard.bool(forKey: showDockIconKey)
self.voiceWakeMicID = UserDefaults.standard.string(forKey: voiceWakeMicKey) ?? ""
self.voiceWakeMicName = UserDefaults.standard.string(forKey: voiceWakeMicNameKey) ?? ""
self.voiceWakeLocaleID = UserDefaults.standard.string(forKey: voiceWakeLocaleKey) ?? Locale.current.identifier
self.voiceWakeAdditionalLocaleIDs = UserDefaults.standard
.stringArray(forKey: voiceWakeAdditionalLocalesKey) ?? []
@@ -421,8 +416,7 @@ final class AppState {
: nil
Task { @MainActor in
// Keep app-only connection settings local to avoid overwriting remote gateway config.
var root = ClawdbotConfigFile.loadDict()
var root = await ConfigStore.load()
var gateway = root["gateway"] as? [String: Any] ?? [:]
var changed = false
@@ -452,12 +446,8 @@ final class AppState {
}
guard changed else { return }
if gateway.isEmpty {
root.removeValue(forKey: "gateway")
} else {
root["gateway"] = gateway
}
ClawdbotConfigFile.saveDict(root)
root["gateway"] = gateway
try? await ConfigStore.save(root)
}
}
@@ -588,7 +578,6 @@ extension AppState {
state.iconAnimationsEnabled = true
state.showDockIcon = true
state.voiceWakeMicID = "BuiltInMic"
state.voiceWakeMicName = "Built-in Microphone"
state.voiceWakeLocaleID = Locale.current.identifier
state.voiceWakeAdditionalLocaleIDs = ["en-US", "de-DE"]
state.voicePushToTalkEnabled = false
@@ -1,216 +0,0 @@
import CoreAudio
import Foundation
import OSLog
final class AudioInputDeviceObserver {
private let logger = Logger(subsystem: "com.clawdbot", category: "audio.devices")
private var isActive = false
private var devicesListener: AudioObjectPropertyListenerBlock?
private var defaultInputListener: AudioObjectPropertyListenerBlock?
static func defaultInputDeviceUID() -> String? {
let systemObject = AudioObjectID(kAudioObjectSystemObject)
var address = AudioObjectPropertyAddress(
mSelector: kAudioHardwarePropertyDefaultInputDevice,
mScope: kAudioObjectPropertyScopeGlobal,
mElement: kAudioObjectPropertyElementMain)
var deviceID = AudioObjectID(0)
var size = UInt32(MemoryLayout<AudioObjectID>.size)
let status = AudioObjectGetPropertyData(
systemObject,
&address,
0,
nil,
&size,
&deviceID)
guard status == noErr, deviceID != 0 else { return nil }
return self.deviceUID(for: deviceID)
}
static func aliveInputDeviceUIDs() -> Set<String> {
let systemObject = AudioObjectID(kAudioObjectSystemObject)
var address = AudioObjectPropertyAddress(
mSelector: kAudioHardwarePropertyDevices,
mScope: kAudioObjectPropertyScopeGlobal,
mElement: kAudioObjectPropertyElementMain)
var size: UInt32 = 0
var status = AudioObjectGetPropertyDataSize(systemObject, &address, 0, nil, &size)
guard status == noErr, size > 0 else { return [] }
let count = Int(size) / MemoryLayout<AudioObjectID>.size
var deviceIDs = [AudioObjectID](repeating: 0, count: count)
status = AudioObjectGetPropertyData(systemObject, &address, 0, nil, &size, &deviceIDs)
guard status == noErr else { return [] }
var output = Set<String>()
for deviceID in deviceIDs {
guard self.deviceIsAlive(deviceID) else { continue }
guard self.deviceHasInput(deviceID) else { continue }
if let uid = self.deviceUID(for: deviceID) {
output.insert(uid)
}
}
return output
}
static func defaultInputDeviceSummary() -> String {
let systemObject = AudioObjectID(kAudioObjectSystemObject)
var address = AudioObjectPropertyAddress(
mSelector: kAudioHardwarePropertyDefaultInputDevice,
mScope: kAudioObjectPropertyScopeGlobal,
mElement: kAudioObjectPropertyElementMain)
var deviceID = AudioObjectID(0)
var size = UInt32(MemoryLayout<AudioObjectID>.size)
let status = AudioObjectGetPropertyData(
systemObject,
&address,
0,
nil,
&size,
&deviceID)
guard status == noErr, deviceID != 0 else {
return "defaultInput=unknown"
}
let uid = self.deviceUID(for: deviceID) ?? "unknown"
let name = self.deviceName(for: deviceID) ?? "unknown"
return "defaultInput=\(name) (\(uid))"
}
func start(onChange: @escaping @Sendable () -> Void) {
guard !self.isActive else { return }
self.isActive = true
let systemObject = AudioObjectID(kAudioObjectSystemObject)
let queue = DispatchQueue.main
var devicesAddress = AudioObjectPropertyAddress(
mSelector: kAudioHardwarePropertyDevices,
mScope: kAudioObjectPropertyScopeGlobal,
mElement: kAudioObjectPropertyElementMain)
let devicesListener: AudioObjectPropertyListenerBlock = { _, _ in
self.logDefaultInputChange(reason: "devices")
onChange()
}
let devicesStatus = AudioObjectAddPropertyListenerBlock(
systemObject,
&devicesAddress,
queue,
devicesListener)
var defaultInputAddress = AudioObjectPropertyAddress(
mSelector: kAudioHardwarePropertyDefaultInputDevice,
mScope: kAudioObjectPropertyScopeGlobal,
mElement: kAudioObjectPropertyElementMain)
let defaultInputListener: AudioObjectPropertyListenerBlock = { _, _ in
self.logDefaultInputChange(reason: "default")
onChange()
}
let defaultStatus = AudioObjectAddPropertyListenerBlock(
systemObject,
&defaultInputAddress,
queue,
defaultInputListener)
if devicesStatus != noErr || defaultStatus != noErr {
self.logger.error("audio device observer install failed devices=\(devicesStatus) default=\(defaultStatus)")
}
self.logger.info("audio device observer started (\(Self.defaultInputDeviceSummary(), privacy: .public))")
self.devicesListener = devicesListener
self.defaultInputListener = defaultInputListener
}
func stop() {
guard self.isActive else { return }
self.isActive = false
let systemObject = AudioObjectID(kAudioObjectSystemObject)
if let devicesListener {
var devicesAddress = AudioObjectPropertyAddress(
mSelector: kAudioHardwarePropertyDevices,
mScope: kAudioObjectPropertyScopeGlobal,
mElement: kAudioObjectPropertyElementMain)
_ = AudioObjectRemovePropertyListenerBlock(
systemObject,
&devicesAddress,
DispatchQueue.main,
devicesListener)
}
if let defaultInputListener {
var defaultInputAddress = AudioObjectPropertyAddress(
mSelector: kAudioHardwarePropertyDefaultInputDevice,
mScope: kAudioObjectPropertyScopeGlobal,
mElement: kAudioObjectPropertyElementMain)
_ = AudioObjectRemovePropertyListenerBlock(
systemObject,
&defaultInputAddress,
DispatchQueue.main,
defaultInputListener)
}
self.devicesListener = nil
self.defaultInputListener = nil
}
private static func deviceUID(for deviceID: AudioObjectID) -> String? {
var address = AudioObjectPropertyAddress(
mSelector: kAudioDevicePropertyDeviceUID,
mScope: kAudioObjectPropertyScopeGlobal,
mElement: kAudioObjectPropertyElementMain)
var uid: Unmanaged<CFString>?
var size = UInt32(MemoryLayout<Unmanaged<CFString>?>.size)
let status = AudioObjectGetPropertyData(deviceID, &address, 0, nil, &size, &uid)
guard status == noErr, let uid else { return nil }
return uid.takeUnretainedValue() as String
}
private static func deviceName(for deviceID: AudioObjectID) -> String? {
var address = AudioObjectPropertyAddress(
mSelector: kAudioObjectPropertyName,
mScope: kAudioObjectPropertyScopeGlobal,
mElement: kAudioObjectPropertyElementMain)
var name: Unmanaged<CFString>?
var size = UInt32(MemoryLayout<Unmanaged<CFString>?>.size)
let status = AudioObjectGetPropertyData(deviceID, &address, 0, nil, &size, &name)
guard status == noErr, let name else { return nil }
return name.takeUnretainedValue() as String
}
private static func deviceIsAlive(_ deviceID: AudioObjectID) -> Bool {
var address = AudioObjectPropertyAddress(
mSelector: kAudioDevicePropertyDeviceIsAlive,
mScope: kAudioObjectPropertyScopeGlobal,
mElement: kAudioObjectPropertyElementMain)
var alive: UInt32 = 0
var size = UInt32(MemoryLayout<UInt32>.size)
let status = AudioObjectGetPropertyData(deviceID, &address, 0, nil, &size, &alive)
return status == noErr && alive != 0
}
private static func deviceHasInput(_ deviceID: AudioObjectID) -> Bool {
var address = AudioObjectPropertyAddress(
mSelector: kAudioDevicePropertyStreamConfiguration,
mScope: kAudioDevicePropertyScopeInput,
mElement: kAudioObjectPropertyElementMain)
var size: UInt32 = 0
var status = AudioObjectGetPropertyDataSize(deviceID, &address, 0, nil, &size)
guard status == noErr, size > 0 else { return false }
let raw = UnsafeMutableRawPointer.allocate(
byteCount: Int(size),
alignment: MemoryLayout<AudioBufferList>.alignment)
defer { raw.deallocate() }
let bufferList = raw.bindMemory(to: AudioBufferList.self, capacity: 1)
status = AudioObjectGetPropertyData(deviceID, &address, 0, nil, &size, bufferList)
guard status == noErr else { return false }
let buffers = UnsafeMutableAudioBufferListPointer(bufferList)
return buffers.contains(where: { $0.mNumberChannels > 0 })
}
private func logDefaultInputChange(reason: StaticString) {
self.logger.info("audio input changed (\(reason)) (\(Self.defaultInputDeviceSummary(), privacy: .public))")
}
}
@@ -187,7 +187,7 @@ actor BridgeServer {
thinking: "low",
deliver: false,
to: nil,
provider: .last))
channel: .last))
case "agent.request":
guard let json = evt.payloadJSON, let data = json.data(using: .utf8) else {
@@ -205,7 +205,7 @@ actor BridgeServer {
?? "node-\(nodeId)"
let thinking = link.thinking?.trimmingCharacters(in: .whitespacesAndNewlines).nonEmpty
let to = link.to?.trimmingCharacters(in: .whitespacesAndNewlines).nonEmpty
let provider = GatewayAgentProvider(raw: link.channel)
let channel = GatewayAgentChannel(raw: link.channel)
_ = await GatewayConnection.shared.sendAgent(GatewayAgentInvocation(
message: message,
@@ -213,7 +213,7 @@ actor BridgeServer {
thinking: thinking,
deliver: link.deliver,
to: to,
provider: provider))
channel: channel))
default:
break
@@ -229,7 +229,7 @@ actor BridgeServer {
error: BridgeRPCError(code: "FORBIDDEN", message: "Method not allowed"))
}
let params: [String: ClawdbotProtocol.AnyCodable]?
let params: [String: AnyCodable]?
if let json = req.paramsJSON?.trimmingCharacters(in: .whitespacesAndNewlines), !json.isEmpty {
guard let data = json.data(using: .utf8) else {
return BridgeRPCResponse(
@@ -238,7 +238,7 @@ actor BridgeServer {
error: BridgeRPCError(code: "INVALID_REQUEST", message: "paramsJSON not UTF-8"))
}
do {
params = try JSONDecoder().decode([String: ClawdbotProtocol.AnyCodable].self, from: data)
params = try JSONDecoder().decode([String: AnyCodable].self, from: data)
} catch {
return BridgeRPCResponse(
id: req.id,
@@ -360,16 +360,16 @@ actor BridgeServer {
"reason \(reason)",
].compactMap(\.self).joined(separator: " · ")
var params: [String: ClawdbotProtocol.AnyCodable] = [
"text": ClawdbotProtocol.AnyCodable(summary),
"instanceId": ClawdbotProtocol.AnyCodable(nodeId),
"host": ClawdbotProtocol.AnyCodable(host),
"mode": ClawdbotProtocol.AnyCodable("node"),
"reason": ClawdbotProtocol.AnyCodable(reason),
"tags": ClawdbotProtocol.AnyCodable(tags),
var params: [String: AnyCodable] = [
"text": AnyCodable(summary),
"instanceId": AnyCodable(nodeId),
"host": AnyCodable(host),
"mode": AnyCodable("node"),
"reason": AnyCodable(reason),
"tags": AnyCodable(tags),
]
if let ip { params["ip"] = ClawdbotProtocol.AnyCodable(ip) }
if let version { params["version"] = ClawdbotProtocol.AnyCodable(version) }
if let ip { params["ip"] = AnyCodable(ip) }
if let version { params["version"] = AnyCodable(version) }
await GatewayConnection.shared.sendSystemEvent(params)
}
@@ -79,15 +79,14 @@ final class CanvasA2UIActionMessageHandler: NSObject, WKScriptMessageHandler {
GatewayProcessManager.shared.setActive(true)
}
let result = await GatewayConnection.shared.sendAgent(
GatewayAgentInvocation(
message: text,
sessionKey: self.sessionKey,
thinking: "low",
deliver: false,
to: nil,
provider: .last,
idempotencyKey: actionId))
let result = await GatewayConnection.shared.sendAgent(GatewayAgentInvocation(
message: text,
sessionKey: self.sessionKey,
thinking: "low",
deliver: false,
to: nil,
channel: .last,
idempotencyKey: actionId))
await MainActor.run {
guard let webView else { return }
@@ -1,4 +1,3 @@
import ClawdbotProtocol
import Foundation
enum ClawdbotConfigFile {
@@ -33,8 +32,7 @@ enum ClawdbotConfigFile {
}
static func saveDict(_ dict: [String: Any]) {
// Nix mode disables config writes in production, but tests rely on saving temp configs.
if ProcessInfo.processInfo.isNixMode, !ProcessInfo.processInfo.isRunningTests { return }
if ProcessInfo.processInfo.isNixMode { return }
do {
let data = try JSONSerialization.data(withJSONObject: dict, options: [.prettyPrinted, .sortedKeys])
let url = self.url()
@@ -81,33 +79,22 @@ enum ClawdbotConfigFile {
static func agentWorkspace() -> String? {
let root = self.loadDict()
let agents = root["agents"] as? [String: Any]
let defaults = agents?["defaults"] as? [String: Any]
return defaults?["workspace"] as? String
let agent = root["agent"] as? [String: Any]
return agent?["workspace"] as? String
}
static func setAgentWorkspace(_ workspace: String?) {
var root = self.loadDict()
var agents = root["agents"] as? [String: Any] ?? [:]
var defaults = agents["defaults"] as? [String: Any] ?? [:]
var agent = root["agent"] as? [String: Any] ?? [:]
let trimmed = workspace?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
if trimmed.isEmpty {
defaults.removeValue(forKey: "workspace")
agent.removeValue(forKey: "workspace")
} else {
defaults["workspace"] = trimmed
}
if defaults.isEmpty {
agents.removeValue(forKey: "defaults")
} else {
agents["defaults"] = defaults
}
if agents.isEmpty {
root.removeValue(forKey: "agents")
} else {
root["agents"] = agents
agent["workspace"] = trimmed
}
root["agent"] = agent
self.saveDict(root)
self.logger.debug("agents.defaults.workspace updated set=\(!trimmed.isEmpty)")
self.logger.debug("agent workspace updated set=\(!trimmed.isEmpty)")
}
static func gatewayPassword() -> String? {
@@ -136,70 +123,6 @@ enum ClawdbotConfigFile {
return nil
}
static func remoteGatewayPort() -> Int? {
guard let url = self.remoteGatewayUrl(),
let port = url.port,
port > 0
else { return nil }
return port
}
static func remoteGatewayPort(matchingHost sshHost: String) -> Int? {
let trimmedSshHost = sshHost.trimmingCharacters(in: .whitespacesAndNewlines)
guard !trimmedSshHost.isEmpty,
let url = self.remoteGatewayUrl(),
let port = url.port,
port > 0,
let urlHost = url.host?.trimmingCharacters(in: .whitespacesAndNewlines),
!urlHost.isEmpty
else {
return nil
}
let sshKey = Self.hostKey(trimmedSshHost)
let urlKey = Self.hostKey(urlHost)
guard !sshKey.isEmpty, !urlKey.isEmpty, sshKey == urlKey else { return nil }
return port
}
static func setRemoteGatewayUrl(host: String, port: Int?) {
guard let port, port > 0 else { return }
let trimmedHost = host.trimmingCharacters(in: .whitespacesAndNewlines)
guard !trimmedHost.isEmpty else { return }
self.updateGatewayDict { gateway in
var remote = gateway["remote"] as? [String: Any] ?? [:]
let existingUrl = (remote["url"] as? String)?
.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
let scheme = URL(string: existingUrl)?.scheme ?? "ws"
remote["url"] = "\(scheme)://\(trimmedHost):\(port)"
gateway["remote"] = remote
}
}
private static func remoteGatewayUrl() -> URL? {
let root = self.loadDict()
guard let gateway = root["gateway"] as? [String: Any],
let remote = gateway["remote"] as? [String: Any],
let raw = remote["url"] as? String
else {
return nil
}
let trimmed = raw.trimmingCharacters(in: .whitespacesAndNewlines)
guard !trimmed.isEmpty, let url = URL(string: trimmed) else { return nil }
return url
}
private static func hostKey(_ host: String) -> String {
let trimmed = host.trimmingCharacters(in: .whitespacesAndNewlines).lowercased()
guard !trimmed.isEmpty else { return "" }
if trimmed.contains(":") { return trimmed }
let digits = CharacterSet(charactersIn: "0123456789.")
if trimmed.rangeOfCharacter(from: digits.inverted) == nil {
return trimmed
}
return trimmed.split(separator: ".").first.map(String.init) ?? trimmed
}
private static func parseConfigData(_ data: Data) -> [String: Any]? {
if let root = try? JSONSerialization.jsonObject(with: data) as? [String: Any] {
return root
@@ -3,9 +3,9 @@ import Foundation
enum ClawdbotEnv {
static func path(_ key: String) -> String? {
// Normalize env overrides once so UI + file IO stay consistent.
guard let raw = getenv(key) else { return nil }
let value = String(cString: raw).trimmingCharacters(in: .whitespacesAndNewlines)
guard !value.isEmpty
guard let value = ProcessInfo.processInfo.environment[key]?
.trimmingCharacters(in: .whitespacesAndNewlines),
!value.isEmpty
else {
return nil
}
@@ -387,20 +387,13 @@ struct ConfigSettings: View {
private func loadConfig() async {
let parsed = await ConfigStore.load()
let agents = parsed["agents"] as? [String: Any]
let defaults = agents?["defaults"] as? [String: Any]
let heartbeat = defaults?["heartbeat"] as? [String: Any]
let heartbeatEvery = heartbeat?["every"] as? String
let heartbeatBody = heartbeat?["prompt"] as? String
let agent = parsed["agent"] as? [String: Any]
let heartbeatMinutes = agent?["heartbeatMinutes"] as? Int
let heartbeatBody = agent?["heartbeatBody"] as? String
let browser = parsed["browser"] as? [String: Any]
let talk = parsed["talk"] as? [String: Any]
let loadedModel: String = {
if let raw = defaults?["model"] as? String { return raw }
if let modelDict = defaults?["model"] as? [String: Any],
let primary = modelDict["primary"] as? String { return primary }
return ""
}()
let loadedModel = (agent?["model"] as? String) ?? ""
if !loadedModel.isEmpty {
self.configModel = loadedModel
self.customModel = loadedModel
@@ -409,13 +402,7 @@ struct ConfigSettings: View {
self.customModel = SessionLoader.fallbackModel
}
if let heartbeatEvery {
let digits = heartbeatEvery.trimmingCharacters(in: .whitespacesAndNewlines)
.prefix { $0.isNumber }
if let minutes = Int(digits) {
self.heartbeatMinutes = minutes
}
}
if let heartbeatMinutes { self.heartbeatMinutes = heartbeatMinutes }
if let heartbeatBody, !heartbeatBody.isEmpty { self.heartbeatBody = heartbeatBody }
if let browser {
@@ -493,49 +480,25 @@ struct ConfigSettings: View {
@MainActor
private static func buildAndSaveConfig(_ draft: ConfigDraft) async -> String? {
var root = await ConfigStore.load()
var agents = root["agents"] as? [String: Any] ?? [:]
var defaults = agents["defaults"] as? [String: Any] ?? [:]
var agent = root["agent"] as? [String: Any] ?? [:]
var browser = root["browser"] as? [String: Any] ?? [:]
var talk = root["talk"] as? [String: Any] ?? [:]
let chosenModel = (draft.configModel == "__custom__" ? draft.customModel : draft.configModel)
.trimmingCharacters(in: .whitespacesAndNewlines)
let trimmedModel = chosenModel
if !trimmedModel.isEmpty {
var model = defaults["model"] as? [String: Any] ?? [:]
model["primary"] = trimmedModel
defaults["model"] = model
var models = defaults["models"] as? [String: Any] ?? [:]
if models[trimmedModel] == nil {
models[trimmedModel] = [:]
}
defaults["models"] = models
}
if !trimmedModel.isEmpty { agent["model"] = trimmedModel }
if let heartbeatMinutes = draft.heartbeatMinutes {
var heartbeat = defaults["heartbeat"] as? [String: Any] ?? [:]
heartbeat["every"] = "\(heartbeatMinutes)m"
defaults["heartbeat"] = heartbeat
agent["heartbeatMinutes"] = heartbeatMinutes
}
let trimmedBody = draft.heartbeatBody.trimmingCharacters(in: .whitespacesAndNewlines)
if !trimmedBody.isEmpty {
var heartbeat = defaults["heartbeat"] as? [String: Any] ?? [:]
heartbeat["prompt"] = trimmedBody
defaults["heartbeat"] = heartbeat
agent["heartbeatBody"] = trimmedBody
}
if defaults.isEmpty {
agents.removeValue(forKey: "defaults")
} else {
agents["defaults"] = defaults
}
if agents.isEmpty {
root.removeValue(forKey: "agents")
} else {
root["agents"] = agents
}
root["agent"] = agent
browser["enabled"] = draft.browserEnabled
let trimmedUrl = draft.browserControlUrl.trimmingCharacters(in: .whitespacesAndNewlines)
@@ -1,4 +1,3 @@
import ClawdbotProtocol
import Foundation
enum ConfigStore {
@@ -13,7 +13,6 @@ let voiceWakeSendChimeKey = "clawdbot.voiceWakeSendChime"
let showDockIconKey = "clawdbot.showDockIcon"
let defaultVoiceWakeTriggers = ["clawd", "claude"]
let voiceWakeMicKey = "clawdbot.voiceWakeMicID"
let voiceWakeMicNameKey = "clawdbot.voiceWakeMicName"
let voiceWakeLocaleKey = "clawdbot.voiceWakeLocaleID"
let voiceWakeAdditionalLocalesKey = "clawdbot.voiceWakeAdditionalLocaleIDs"
let voicePushToTalkEnabledKey = "clawdbot.voicePushToTalkEnabled"
@@ -1,4 +1,3 @@
import ClawdbotProtocol
import Foundation
import SwiftUI
@@ -34,13 +33,13 @@ extension CronJobEditor {
case let .systemEvent(text):
self.payloadKind = .systemEvent
self.systemEventText = text
case let .agentTurn(message, thinking, timeoutSeconds, deliver, provider, to, bestEffortDeliver):
case let .agentTurn(message, thinking, timeoutSeconds, deliver, channel, to, bestEffortDeliver):
self.payloadKind = .agentTurn
self.agentMessage = message
self.thinking = thinking ?? ""
self.timeoutSeconds = timeoutSeconds.map(String.init) ?? ""
self.deliver = deliver ?? false
self.provider = GatewayAgentProvider(raw: provider)
self.channel = GatewayAgentChannel(raw: channel)
self.to = to ?? ""
self.bestEffortDeliver = bestEffortDeliver ?? false
}
@@ -167,7 +166,7 @@ extension CronJobEditor {
if let n = Int(self.timeoutSeconds), n > 0 { payload["timeoutSeconds"] = n }
payload["deliver"] = self.deliver
if self.deliver {
payload["provider"] = self.provider.rawValue
payload["channel"] = self.channel.rawValue
let to = self.to.trimmingCharacters(in: .whitespacesAndNewlines)
if !to.isEmpty { payload["to"] = to }
payload["bestEffortDeliver"] = self.bestEffortDeliver
@@ -13,7 +13,7 @@ extension CronJobEditor {
self.payloadKind = .agentTurn
self.agentMessage = "Run diagnostic"
self.deliver = true
self.provider = .last
self.channel = .last
self.to = "+15551230000"
self.thinking = "low"
self.timeoutSeconds = "90"
@@ -1,4 +1,3 @@
import ClawdbotProtocol
import SwiftUI
struct CronJobEditor: View {
@@ -18,7 +17,7 @@ struct CronJobEditor: View {
static let scheduleKindNote =
"“At” runs once, “Every” repeats with a duration, “Cron” uses a 5-field Unix expression."
static let isolatedPayloadNote =
"Isolated jobs always run an agent turn. The result can be delivered to a provider, "
"Isolated jobs always run an agent turn. The result can be delivered to a surface, "
+ "and a short summary is posted back to your main chat."
static let mainPayloadNote =
"System events are injected into the current main session. Agent turns require an isolated session target."
@@ -43,7 +42,7 @@ struct CronJobEditor: View {
@State var systemEventText: String = ""
@State var agentMessage: String = ""
@State var deliver: Bool = false
@State var provider: GatewayAgentProvider = .last
@State var channel: GatewayAgentChannel = .last
@State var to: String = ""
@State var thinking: String = ""
@State var timeoutSeconds: String = ""
@@ -310,7 +309,7 @@ struct CronJobEditor: View {
}
GridRow {
self.gridLabel("Deliver")
Toggle("Deliver result to a provider", isOn: self.$deliver)
Toggle("Deliver result to a surface", isOn: self.$deliver)
.toggleStyle(.switch)
}
}
@@ -318,15 +317,12 @@ struct CronJobEditor: View {
if self.deliver {
Grid(alignment: .leadingFirstTextBaseline, horizontalSpacing: 14, verticalSpacing: 10) {
GridRow {
self.gridLabel("Provider")
Picker("", selection: self.$provider) {
Text("last").tag(GatewayAgentProvider.last)
Text("whatsapp").tag(GatewayAgentProvider.whatsapp)
Text("telegram").tag(GatewayAgentProvider.telegram)
Text("discord").tag(GatewayAgentProvider.discord)
Text("slack").tag(GatewayAgentProvider.slack)
Text("signal").tag(GatewayAgentProvider.signal)
Text("imessage").tag(GatewayAgentProvider.imessage)
self.gridLabel("Channel")
Picker("", selection: self.$channel) {
Text("last").tag(GatewayAgentChannel.last)
Text("whatsapp").tag(GatewayAgentChannel.whatsapp)
Text("telegram").tag(GatewayAgentChannel.telegram)
Text("discord").tag(GatewayAgentChannel.discord)
}
.labelsHidden()
.pickerStyle(.segmented)
+5 -5
View File
@@ -74,12 +74,12 @@ enum CronPayload: Codable, Equatable {
thinking: String?,
timeoutSeconds: Int?,
deliver: Bool?,
provider: String?,
channel: String?,
to: String?,
bestEffortDeliver: Bool?)
enum CodingKeys: String, CodingKey {
case kind, text, message, thinking, timeoutSeconds, deliver, provider, to, bestEffortDeliver
case kind, text, message, thinking, timeoutSeconds, deliver, channel, to, bestEffortDeliver
}
var kind: String {
@@ -101,7 +101,7 @@ enum CronPayload: Codable, Equatable {
thinking: container.decodeIfPresent(String.self, forKey: .thinking),
timeoutSeconds: container.decodeIfPresent(Int.self, forKey: .timeoutSeconds),
deliver: container.decodeIfPresent(Bool.self, forKey: .deliver),
provider: container.decodeIfPresent(String.self, forKey: .provider),
channel: container.decodeIfPresent(String.self, forKey: .channel),
to: container.decodeIfPresent(String.self, forKey: .to),
bestEffortDeliver: container.decodeIfPresent(Bool.self, forKey: .bestEffortDeliver))
default:
@@ -118,12 +118,12 @@ enum CronPayload: Codable, Equatable {
switch self {
case let .systemEvent(text):
try container.encode(text, forKey: .text)
case let .agentTurn(message, thinking, timeoutSeconds, deliver, provider, to, bestEffortDeliver):
case let .agentTurn(message, thinking, timeoutSeconds, deliver, channel, to, bestEffortDeliver):
try container.encode(message, forKey: .message)
try container.encodeIfPresent(thinking, forKey: .thinking)
try container.encodeIfPresent(timeoutSeconds, forKey: .timeoutSeconds)
try container.encodeIfPresent(deliver, forKey: .deliver)
try container.encodeIfPresent(provider, forKey: .provider)
try container.encodeIfPresent(channel, forKey: .channel)
try container.encodeIfPresent(to, forKey: .to)
try container.encodeIfPresent(bestEffortDeliver, forKey: .bestEffortDeliver)
}
@@ -1,4 +1,3 @@
import ClawdbotProtocol
import Foundation
extension CronSettings {
@@ -206,7 +206,7 @@ extension CronSettings {
Text(text)
.font(.callout)
.textSelection(.enabled)
case let .agentTurn(message, thinking, timeoutSeconds, deliver, provider, to, _):
case let .agentTurn(message, thinking, timeoutSeconds, deliver, channel, to, _):
VStack(alignment: .leading, spacing: 4) {
Text(message)
.font(.callout)
@@ -216,7 +216,7 @@ extension CronSettings {
if let timeoutSeconds { StatusPill(text: "\(timeoutSeconds)s", tint: .secondary) }
if deliver ?? false {
StatusPill(text: "deliver", tint: .secondary)
if let provider, !provider.isEmpty { StatusPill(text: provider, tint: .secondary) }
if let channel, !channel.isEmpty { StatusPill(text: channel, tint: .secondary) }
if let to, !to.isEmpty { StatusPill(text: to, tint: .secondary) }
}
}
@@ -20,7 +20,7 @@ struct CronSettings_Previews: PreviewProvider {
thinking: "low",
timeoutSeconds: 600,
deliver: true,
provider: "last",
channel: "last",
to: nil,
bestEffortDeliver: true),
isolation: CronIsolation(postToMainPrefix: "Cron"),
@@ -72,7 +72,7 @@ extension CronSettings {
thinking: "low",
timeoutSeconds: 120,
deliver: true,
provider: "whatsapp",
channel: "whatsapp",
to: "+15551234567",
bestEffortDeliver: true),
isolation: CronIsolation(postToMainPrefix: "[cron] "),
+3 -3
View File
@@ -59,7 +59,7 @@ final class DeepLinkHandler {
}
do {
let provider = GatewayAgentProvider(raw: link.channel)
let channel = GatewayAgentChannel(raw: link.channel)
let explicitSessionKey = link.sessionKey?
.trimmingCharacters(in: .whitespacesAndNewlines)
.nonEmpty
@@ -72,9 +72,9 @@ final class DeepLinkHandler {
message: messagePreview,
sessionKey: resolvedSessionKey,
thinking: link.thinking?.trimmingCharacters(in: .whitespacesAndNewlines).nonEmpty,
deliver: provider.shouldDeliver(link.deliver),
deliver: channel.shouldDeliver(link.deliver),
to: link.to?.trimmingCharacters(in: .whitespacesAndNewlines).nonEmpty,
provider: provider,
channel: channel,
timeoutSeconds: link.timeoutSeconds,
idempotencyKey: UUID().uuidString)
@@ -1,26 +0,0 @@
import Foundation
enum GatewayAgentChannel: String, CaseIterable, Sendable {
case last
case webchat
case whatsapp
case telegram
init(raw: String?) {
let trimmed = raw?
.trimmingCharacters(in: .whitespacesAndNewlines)
.lowercased() ?? ""
self = GatewayAgentChannel(rawValue: trimmed) ?? .last
}
func shouldDeliver(_ isLast: Bool) -> Bool {
switch self {
case .webchat:
false
case .last:
isLast
case .whatsapp, .telegram:
true
}
}
}
@@ -5,19 +5,16 @@ import OSLog
private let gatewayConnectionLogger = Logger(subsystem: "com.clawdbot", category: "gateway.connection")
enum GatewayAgentProvider: String, Codable, CaseIterable, Sendable {
enum GatewayAgentChannel: String, Codable, CaseIterable, Sendable {
case last
case whatsapp
case telegram
case discord
case slack
case signal
case imessage
case webchat
init(raw: String?) {
let normalized = (raw ?? "").trimmingCharacters(in: .whitespacesAndNewlines).lowercased()
self = GatewayAgentProvider(rawValue: normalized) ?? .last
self = GatewayAgentChannel(rawValue: normalized) ?? .last
}
var isDeliverable: Bool { self != .webchat }
@@ -31,7 +28,7 @@ struct GatewayAgentInvocation: Sendable {
var thinking: String?
var deliver: Bool = false
var to: String?
var provider: GatewayAgentProvider = .last
var channel: GatewayAgentChannel = .last
var timeoutSeconds: Int?
var idempotencyKey: String = UUID().uuidString
}
@@ -368,7 +365,7 @@ extension GatewayConnection {
"thinking": AnyCodable(invocation.thinking ?? "default"),
"deliver": AnyCodable(invocation.deliver),
"to": AnyCodable(invocation.to ?? ""),
"provider": AnyCodable(invocation.provider.rawValue),
"channel": AnyCodable(invocation.channel.rawValue),
"idempotencyKey": AnyCodable(invocation.idempotencyKey),
]
if let timeout = invocation.timeoutSeconds {
@@ -389,7 +386,7 @@ extension GatewayConnection {
sessionKey: String,
deliver: Bool,
to: String?,
provider: GatewayAgentProvider = .last,
channel: GatewayAgentChannel = .last,
timeoutSeconds: Int? = nil,
idempotencyKey: String = UUID().uuidString) async -> (ok: Bool, error: String?)
{
@@ -399,7 +396,7 @@ extension GatewayConnection {
thinking: thinking,
deliver: deliver,
to: to,
provider: provider,
channel: channel,
timeoutSeconds: timeoutSeconds,
idempotencyKey: idempotencyKey))
}
@@ -18,7 +18,6 @@ final class GatewayDiscoveryModel {
var lanHost: String?
var tailnetDns: String?
var sshPort: Int
var gatewayPort: Int?
var cliPath: String?
var stableID: String
var debugID: String
@@ -139,7 +138,6 @@ final class GatewayDiscoveryModel {
lanHost: parsedTXT.lanHost,
tailnetDns: parsedTXT.tailnetDns,
sshPort: parsedTXT.sshPort,
gatewayPort: parsedTXT.gatewayPort,
cliPath: parsedTXT.cliPath,
stableID: stableID,
debugID: BridgeEndpointID.prettyDescription(result.endpoint),
@@ -208,19 +206,12 @@ final class GatewayDiscoveryModel {
return merged
}
struct GatewayTXT: Equatable {
var lanHost: String?
var tailnetDns: String?
var sshPort: Int
var gatewayPort: Int?
var cliPath: String?
}
static func parseGatewayTXT(_ txt: [String: String]) -> GatewayTXT {
static func parseGatewayTXT(_ txt: [String: String])
-> (lanHost: String?, tailnetDns: String?, sshPort: Int, cliPath: String?)
{
var lanHost: String?
var tailnetDns: String?
var sshPort = 22
var gatewayPort: Int?
var cliPath: String?
if let value = txt["lanHost"] {
@@ -237,23 +228,12 @@ final class GatewayDiscoveryModel {
{
sshPort = parsed
}
if let value = txt["gatewayPort"],
let parsed = Int(value.trimmingCharacters(in: .whitespacesAndNewlines)),
parsed > 0
{
gatewayPort = parsed
}
if let value = txt["cliPath"] {
let trimmed = value.trimmingCharacters(in: .whitespacesAndNewlines)
cliPath = trimmed.isEmpty ? nil : trimmed
}
return GatewayTXT(
lanHost: lanHost,
tailnetDns: tailnetDns,
sshPort: sshPort,
gatewayPort: gatewayPort,
cliPath: cliPath)
return (lanHost, tailnetDns, sshPort, cliPath)
}
static func buildSSHTarget(user: String, host: String, port: Int) -> String {
@@ -43,52 +43,25 @@ enum GatewayLaunchAgentManager {
return [gatewayBin, "gateway-daemon", "--port", "\(port)", "--bind", bind]
}
static func isLoaded() async -> Bool {
static func status() async -> Bool {
guard FileManager.default.fileExists(atPath: self.plistURL.path) else { return false }
let result = await Launchctl.run(["print", "gui/\(getuid())/\(gatewayLaunchdLabel)"])
let result = await self.runLaunchctl(["print", "gui/\(getuid())/\(gatewayLaunchdLabel)"])
return result.status == 0
}
static func set(enabled: Bool, bundlePath: String, port: Int) async -> String? {
if enabled {
_ = await Launchctl.run(["bootout", "gui/\(getuid())/\(self.legacyGatewayLaunchdLabel)"])
_ = await self.runLaunchctl(["bootout", "gui/\(getuid())/\(self.legacyGatewayLaunchdLabel)"])
try? FileManager.default.removeItem(at: self.legacyPlistURL)
let gatewayBin = self.gatewayExecutablePath(bundlePath: bundlePath)
guard FileManager.default.isExecutableFile(atPath: gatewayBin) else {
self.logger.error("launchd enable failed: gateway missing at \(gatewayBin)")
return "Embedded gateway missing in bundle; rebuild via scripts/package-mac-app.sh"
}
let desiredBind = self.preferredGatewayBind() ?? "loopback"
let desiredToken = self.preferredGatewayToken()
let desiredPassword = self.preferredGatewayPassword()
let desiredConfig = DesiredConfig(
port: port,
bind: desiredBind,
token: desiredToken,
password: desiredPassword)
// If launchd already loaded the job (common on login), avoid `bootout` unless we must
// change the config. `bootout` can kill a just-started gateway and cause attach loops.
let loaded = await self.isLoaded()
if loaded,
let existing = self.readPlistConfig(),
existing.matches(desiredConfig)
{
self.logger.info("launchd job already loaded with desired config; skipping bootout")
await self.ensureEnabled()
_ = await Launchctl.run(["kickstart", "gui/\(getuid())/\(gatewayLaunchdLabel)"])
return nil
}
self.logger.info("launchd enable requested port=\(port) bind=\(desiredBind)")
self.logger.info("launchd enable requested port=\(port)")
self.writePlist(bundlePath: bundlePath, port: port)
await self.ensureEnabled()
if loaded {
_ = await Launchctl.run(["bootout", "gui/\(getuid())/\(gatewayLaunchdLabel)"])
}
let bootstrap = await Launchctl.run(["bootstrap", "gui/\(getuid())", self.plistURL.path])
_ = await self.runLaunchctl(["bootout", "gui/\(getuid())/\(gatewayLaunchdLabel)"])
let bootstrap = await self.runLaunchctl(["bootstrap", "gui/\(getuid())", self.plistURL.path])
if bootstrap.status != 0 {
let msg = bootstrap.output.trimmingCharacters(in: .whitespacesAndNewlines)
self.logger.error("launchd bootstrap failed: \(msg)")
@@ -96,19 +69,20 @@ enum GatewayLaunchAgentManager {
? "Failed to bootstrap gateway launchd job"
: bootstrap.output.trimmingCharacters(in: .whitespacesAndNewlines)
}
await self.ensureEnabled()
// Note: removed redundant `kickstart -k` that caused race condition.
// bootstrap already starts the job; kickstart -k would kill it immediately
// and with KeepAlive=true, cause a restart loop with port conflicts.
return nil
}
self.logger.info("launchd disable requested")
_ = await Launchctl.run(["bootout", "gui/\(getuid())/\(gatewayLaunchdLabel)"])
await self.ensureDisabled()
_ = await self.runLaunchctl(["bootout", "gui/\(getuid())/\(gatewayLaunchdLabel)"])
try? FileManager.default.removeItem(at: self.plistURL)
return nil
}
static func kickstart() async {
_ = await Launchctl.run(["kickstart", "-k", "gui/\(getuid())/\(gatewayLaunchdLabel)"])
_ = await self.runLaunchctl(["kickstart", "-k", "gui/\(getuid())/\(gatewayLaunchdLabel)"])
}
private static func writePlist(bundlePath: String, port: Int) {
@@ -234,57 +208,30 @@ enum GatewayLaunchAgentManager {
.replacingOccurrences(of: "'", with: "&apos;")
}
private struct DesiredConfig: Equatable {
let port: Int
let bind: String
let token: String?
let password: String?
private struct LaunchctlResult {
let status: Int32
let output: String
}
private struct InstalledConfig: Equatable {
let port: Int?
let bind: String?
let token: String?
let password: String?
func matches(_ desired: DesiredConfig) -> Bool {
guard self.port == desired.port else { return false }
guard (self.bind ?? "loopback") == desired.bind else { return false }
guard self.token == desired.token else { return false }
guard self.password == desired.password else { return false }
return true
}
}
private static func readPlistConfig() -> InstalledConfig? {
guard let snapshot = LaunchAgentPlist.snapshot(url: self.plistURL) else { return nil }
return InstalledConfig(
port: snapshot.port,
bind: snapshot.bind,
token: snapshot.token,
password: snapshot.password)
}
private static func ensureEnabled() async {
let result = await Launchctl.run(["enable", "gui/\(getuid())/\(gatewayLaunchdLabel)"])
guard result.status != 0 else { return }
let msg = result.output.trimmingCharacters(in: .whitespacesAndNewlines)
if msg.isEmpty {
self.logger.warning("launchd enable failed")
} else {
self.logger.warning("launchd enable failed: \(msg)")
}
}
private static func ensureDisabled() async {
let result = await Launchctl.run(["disable", "gui/\(getuid())/\(gatewayLaunchdLabel)"])
guard result.status != 0 else { return }
let msg = result.output.trimmingCharacters(in: .whitespacesAndNewlines)
if msg.isEmpty {
self.logger.warning("launchd disable failed")
} else {
self.logger.warning("launchd disable failed: \(msg)")
}
@discardableResult
private static func runLaunchctl(_ args: [String]) async -> LaunchctlResult {
await Task.detached(priority: .utility) { () -> LaunchctlResult in
let process = Process()
process.launchPath = "/bin/launchctl"
process.arguments = args
let pipe = Pipe()
process.standardOutput = pipe
process.standardError = pipe
do {
try process.run()
process.waitUntilExit()
let data = pipe.fileHandleForReading.readToEndSafely()
let output = String(data: data, encoding: .utf8) ?? ""
return LaunchctlResult(status: process.terminationStatus, output: output)
} catch {
return LaunchctlResult(status: -1, output: error.localizedDescription)
}
}.value
}
}
@@ -70,7 +70,7 @@ final class GatewayProcessManager {
func ensureLaunchAgentEnabledIfNeeded() async {
guard !CommandResolver.connectionModeIsRemote() else { return }
guard !AppStateStore.attachExistingGatewayOnly else { return }
let enabled = await GatewayLaunchAgentManager.isLoaded()
let enabled = await GatewayLaunchAgentManager.status()
guard !enabled else { return }
let bundlePath = Bundle.main.bundleURL.path
let port = GatewayEnvironment.gatewayPort()
@@ -694,7 +694,6 @@ extension GeneralSettings {
host: host,
port: gateway.sshPort)
self.state.remoteCliPath = gateway.cliPath ?? ""
ClawdbotConfigFile.setRemoteGatewayUrl(host: host, port: gateway.gatewayPort)
}
}
@@ -1,81 +0,0 @@
import Foundation
enum Launchctl {
struct Result: Sendable {
let status: Int32
let output: String
}
@discardableResult
static func run(_ args: [String]) async -> Result {
await Task.detached(priority: .utility) { () -> Result in
let process = Process()
process.launchPath = "/bin/launchctl"
process.arguments = args
let pipe = Pipe()
process.standardOutput = pipe
process.standardError = pipe
do {
try process.run()
process.waitUntilExit()
let data = pipe.fileHandleForReading.readToEndSafely()
let output = String(data: data, encoding: .utf8) ?? ""
return Result(status: process.terminationStatus, output: output)
} catch {
return Result(status: -1, output: error.localizedDescription)
}
}.value
}
}
struct LaunchAgentPlistSnapshot: Equatable, Sendable {
let programArguments: [String]
let environment: [String: String]
let port: Int?
let bind: String?
let token: String?
let password: String?
}
enum LaunchAgentPlist {
static func snapshot(url: URL) -> LaunchAgentPlistSnapshot? {
guard let data = try? Data(contentsOf: url) else { return nil }
let rootAny: Any
do {
rootAny = try PropertyListSerialization.propertyList(
from: data,
options: [],
format: nil)
} catch {
return nil
}
guard let root = rootAny as? [String: Any] else { return nil }
let programArguments = root["ProgramArguments"] as? [String] ?? []
let env = root["EnvironmentVariables"] as? [String: String] ?? [:]
let port = Self.extractFlagInt(programArguments, flag: "--port")
let bind = Self.extractFlagString(programArguments, flag: "--bind")?.lowercased()
let token = env["CLAWDBOT_GATEWAY_TOKEN"]?.trimmingCharacters(in: .whitespacesAndNewlines).nonEmpty
let password = env["CLAWDBOT_GATEWAY_PASSWORD"]?.trimmingCharacters(in: .whitespacesAndNewlines).nonEmpty
return LaunchAgentPlistSnapshot(
programArguments: programArguments,
environment: env,
port: port,
bind: bind,
token: token,
password: password)
}
private static func extractFlagInt(_ args: [String], flag: String) -> Int? {
guard let raw = self.extractFlagString(args, flag: flag) else { return nil }
return Int(raw)
}
private static func extractFlagString(_ args: [String], flag: String) -> String? {
guard let idx = args.firstIndex(of: flag) else { return nil }
let valueIdx = args.index(after: idx)
guard valueIdx < args.endIndex else { return nil }
let token = args[valueIdx].trimmingCharacters(in: .whitespacesAndNewlines)
return token.isEmpty ? nil : token
}
}
@@ -18,8 +18,6 @@ struct MenuContent: View {
@Environment(\.openSettings) private var openSettings
@State private var availableMics: [AudioInputDevice] = []
@State private var loadingMics = false
@State private var micObserver = AudioInputDeviceObserver()
@State private var micRefreshTask: Task<Void, Never>?
@State private var browserControlEnabled = true
@AppStorage(cameraEnabledKey) private var cameraEnabled: Bool = false
@AppStorage(appLogLevelKey) private var appLogLevelRaw: String = AppLogLevel.default.rawValue
@@ -145,14 +143,6 @@ struct MenuContent: View {
.task(id: self.state.connectionMode) {
await self.loadBrowserControlEnabled()
}
.onAppear {
self.startMicObserver()
}
.onDisappear {
self.micRefreshTask?.cancel()
self.micRefreshTask = nil
self.micObserver.stop()
}
}
private var connectionLabel: String {
@@ -450,22 +440,13 @@ struct MenuContent: View {
if let match = self.availableMics.first(where: { $0.uid == self.state.voiceWakeMicID }) {
return match.name
}
if !self.state.voiceWakeMicName.isEmpty { return self.state.voiceWakeMicName }
return "Unavailable"
}
private var microphoneMenuItems: some View {
Group {
if self.isSelectedMicUnavailable {
Label("Disconnected (using System default)", systemImage: "exclamationmark.triangle")
.labelStyle(.titleAndIcon)
.foregroundStyle(.secondary)
.disabled(true)
Divider()
}
Button {
self.state.voiceWakeMicID = ""
self.state.voiceWakeMicName = ""
} label: {
Label(self.defaultMicLabel, systemImage: self.state.voiceWakeMicID.isEmpty ? "checkmark" : "")
.labelStyle(.titleAndIcon)
@@ -475,7 +456,6 @@ struct MenuContent: View {
ForEach(self.availableMics) { mic in
Button {
self.state.voiceWakeMicID = mic.uid
self.state.voiceWakeMicName = mic.name
} label: {
Label(mic.name, systemImage: self.state.voiceWakeMicID == mic.uid ? "checkmark" : "")
.labelStyle(.titleAndIcon)
@@ -485,12 +465,6 @@ struct MenuContent: View {
}
}
private var isSelectedMicUnavailable: Bool {
let selected = self.state.voiceWakeMicID
guard !selected.isEmpty else { return false }
return !self.availableMics.contains(where: { $0.uid == selected })
}
private var defaultMicLabel: String {
if let host = Host.current().localizedName, !host.isEmpty {
return "Auto-detect (\(host))"
@@ -526,53 +500,14 @@ struct MenuContent: View {
deviceTypes: [.external, .microphone],
mediaType: .audio,
position: .unspecified)
let connectedDevices = discovery.devices.filter(\.isConnected)
self.availableMics = connectedDevices
self.availableMics = discovery.devices
.sorted { lhs, rhs in
lhs.localizedName.localizedCaseInsensitiveCompare(rhs.localizedName) == .orderedAscending
}
.map { AudioInputDevice(uid: $0.uniqueID, name: $0.localizedName) }
self.availableMics = self.filterAliveInputs(self.availableMics)
self.updateSelectedMicName()
self.loadingMics = false
}
private func startMicObserver() {
self.micObserver.start {
Task { @MainActor in
self.scheduleMicRefresh()
}
}
}
@MainActor
private func scheduleMicRefresh() {
self.micRefreshTask?.cancel()
self.micRefreshTask = Task { @MainActor in
try? await Task.sleep(nanoseconds: 300_000_000)
guard !Task.isCancelled else { return }
await self.loadMicrophones(force: true)
}
}
private func filterAliveInputs(_ inputs: [AudioInputDevice]) -> [AudioInputDevice] {
let aliveUIDs = AudioInputDeviceObserver.aliveInputDeviceUIDs()
guard !aliveUIDs.isEmpty else { return inputs }
return inputs.filter { aliveUIDs.contains($0.uid) }
}
@MainActor
private func updateSelectedMicName() {
let selected = self.state.voiceWakeMicID
if selected.isEmpty {
self.state.voiceWakeMicName = ""
return
}
if let match = self.availableMics.first(where: { $0.uid == selected }) {
self.state.voiceWakeMicName = match.name
}
}
private struct AudioInputDevice: Identifiable, Equatable {
let uid: String
let name: String
@@ -22,10 +22,6 @@ final class MenuSessionsInjector: NSObject, NSMenuDelegate {
private var cachedErrorText: String?
private var cacheUpdatedAt: Date?
private let refreshIntervalSeconds: TimeInterval = 12
private var cachedUsageSummary: GatewayUsageSummary?
private var cachedUsageErrorText: String?
private var usageCacheUpdatedAt: Date?
private let usageRefreshIntervalSeconds: TimeInterval = 30
private let nodesStore = NodesStore.shared
#if DEBUG
private var testControlChannelConnected: Bool?
@@ -62,7 +58,6 @@ final class MenuSessionsInjector: NSObject, NSMenuDelegate {
self.loadTask = Task { [weak self] in
guard let self else { return }
await self.refreshCache(force: forceRefresh)
await self.refreshUsageCache(force: forceRefresh)
await MainActor.run {
guard self.isMenuOpen else { return }
self.inject(into: menu)
@@ -110,86 +105,68 @@ final class MenuSessionsInjector: NSObject, NSMenuDelegate {
guard let insertIndex = self.findInsertIndex(in: menu) else { return }
let width = self.initialWidth(for: menu)
let isConnected = self.isControlChannelConnected
var cursor = insertIndex
var headerView: NSView?
if let snapshot = self.cachedSnapshot {
let now = Date()
let rows = snapshot.rows.filter { row in
if row.key == "main" { return true }
guard let updatedAt = row.updatedAt else { return false }
return now.timeIntervalSince(updatedAt) <= self.activeWindowSeconds
}.sorted { lhs, rhs in
if lhs.key == "main" { return true }
if rhs.key == "main" { return false }
return (lhs.updatedAt ?? .distantPast) > (rhs.updatedAt ?? .distantPast)
}
guard self.isControlChannelConnected else { return }
guard let snapshot = self.cachedSnapshot else {
let headerItem = NSMenuItem()
headerItem.tag = self.tag
headerItem.isEnabled = false
let hosted = self.makeHostedView(
rootView: AnyView(MenuSessionsHeaderView(
count: rows.count,
statusText: isConnected ? nil : "Gateway disconnected")),
width: width,
highlighted: false)
headerItem.view = hosted
headerView = hosted
menu.insertItem(headerItem, at: cursor)
cursor += 1
if rows.isEmpty {
menu.insertItem(
self.makeMessageItem(text: "No active sessions", symbolName: "minus", width: width),
at: cursor)
cursor += 1
} else {
for row in rows {
let item = NSMenuItem()
item.tag = self.tag
item.isEnabled = true
item.submenu = self.buildSubmenu(for: row, storePath: snapshot.storePath)
item.view = self.makeHostedView(
rootView: AnyView(SessionMenuLabelView(row: row, width: width)),
width: width,
highlighted: true)
menu.insertItem(item, at: cursor)
cursor += 1
}
}
} else {
let headerItem = NSMenuItem()
headerItem.tag = self.tag
headerItem.isEnabled = false
let statusText = isConnected
? (self.cachedErrorText ?? "Loading sessions…")
: "Gateway disconnected"
let hosted = self.makeHostedView(
headerItem.view = self.makeHostedView(
rootView: AnyView(MenuSessionsHeaderView(
count: 0,
statusText: statusText)),
statusText: self.cachedErrorText ?? "Loading sessions…")),
width: width,
highlighted: false)
headerItem.view = hosted
headerView = hosted
menu.insertItem(headerItem, at: cursor)
cursor += 1
if !isConnected {
menu.insertItem(
self.makeMessageItem(
text: "Connect the gateway to see sessions",
symbolName: "bolt.slash",
width: width),
at: cursor)
cursor += 1
menu.insertItem(headerItem, at: insertIndex)
DispatchQueue.main.async { [weak self, weak view = headerItem.view] in
guard let self, let view else { return }
self.captureMenuWidthIfAvailable(from: view)
}
return
}
cursor = self.insertUsageSection(into: menu, at: cursor, width: width)
let now = Date()
let rows = snapshot.rows.filter { row in
if row.key == "main" { return true }
guard let updatedAt = row.updatedAt else { return false }
return now.timeIntervalSince(updatedAt) <= self.activeWindowSeconds
}.sorted { lhs, rhs in
if lhs.key == "main" { return true }
if rhs.key == "main" { return false }
return (lhs.updatedAt ?? .distantPast) > (rhs.updatedAt ?? .distantPast)
}
let headerItem = NSMenuItem()
headerItem.tag = self.tag
headerItem.isEnabled = false
let headerView = self.makeHostedView(
rootView: AnyView(MenuSessionsHeaderView(count: rows.count, statusText: nil)),
width: width,
highlighted: false)
headerItem.view = headerView
menu.insertItem(headerItem, at: insertIndex)
var cursor = insertIndex + 1
if rows.isEmpty {
menu.insertItem(
self.makeMessageItem(text: "No active sessions", symbolName: "minus", width: width),
at: cursor)
return
}
for row in rows {
let item = NSMenuItem()
item.tag = self.tag
item.isEnabled = true
item.submenu = self.buildSubmenu(for: row, storePath: snapshot.storePath)
item.view = self.makeHostedView(
rootView: AnyView(SessionMenuLabelView(row: row, width: width)),
width: width,
highlighted: true)
menu.insertItem(item, at: cursor)
cursor += 1
}
DispatchQueue.main.async { [weak self, weak headerView] in
guard let self, let headerView else { return }
@@ -263,55 +240,6 @@ final class MenuSessionsInjector: NSObject, NSMenuDelegate {
_ = cursor
}
private func insertUsageSection(into menu: NSMenu, at cursor: Int, width: CGFloat) -> Int {
let rows = self.usageRows
let errorText = self.cachedUsageErrorText
if rows.isEmpty, errorText == nil {
return cursor
}
var cursor = cursor
let headerItem = NSMenuItem()
headerItem.tag = self.tag
headerItem.isEnabled = false
headerItem.view = self.makeHostedView(
rootView: AnyView(MenuUsageHeaderView(
count: rows.count,
statusText: errorText)),
width: width,
highlighted: false)
menu.insertItem(headerItem, at: cursor)
cursor += 1
if rows.isEmpty {
menu.insertItem(
self.makeMessageItem(text: errorText ?? "No usage available", symbolName: "minus", width: width),
at: cursor)
cursor += 1
return cursor
}
for row in rows {
let item = NSMenuItem()
item.tag = self.tag
item.isEnabled = false
item.view = self.makeHostedView(
rootView: AnyView(UsageMenuLabelView(row: row, width: width)),
width: width,
highlighted: false)
menu.insertItem(item, at: cursor)
cursor += 1
}
return cursor
}
private var usageRows: [UsageRow] {
guard let summary = self.cachedUsageSummary else { return [] }
return summary.primaryRows()
}
private var isControlChannelConnected: Bool {
#if DEBUG
if let override = self.testControlChannelConnected { return override }
@@ -436,40 +364,6 @@ final class MenuSessionsInjector: NSObject, NSMenuDelegate {
}
}
private func refreshUsageCache(force: Bool) async {
if !force,
let updated = self.usageCacheUpdatedAt,
Date().timeIntervalSince(updated) < self.usageRefreshIntervalSeconds
{
return
}
guard self.isControlChannelConnected else {
self.cachedUsageSummary = nil
self.cachedUsageErrorText = nil
self.usageCacheUpdatedAt = Date()
return
}
do {
self.cachedUsageSummary = try await UsageLoader.loadSummary()
self.cachedUsageErrorText = nil
self.usageCacheUpdatedAt = Date()
} catch {
if self.cachedUsageSummary == nil {
self.cachedUsageErrorText = self.compactUsageError(error)
}
self.usageCacheUpdatedAt = Date()
}
}
private func compactUsageError(_ error: Error) -> String {
let message = error.localizedDescription.trimmingCharacters(in: .whitespacesAndNewlines)
if message.isEmpty { return "Usage unavailable" }
if message.count > 90 { return "\(message.prefix(87))…" }
return message
}
private func compactError(_ error: Error) -> String {
if let loadError = error as? SessionLoadError {
switch loadError {
@@ -1,44 +0,0 @@
import SwiftUI
struct MenuUsageHeaderView: View {
let count: Int
let statusText: String?
private let paddingTop: CGFloat = 8
private let paddingBottom: CGFloat = 6
private let paddingTrailing: CGFloat = 10
private let paddingLeading: CGFloat = 20
var body: some View {
VStack(alignment: .leading, spacing: 6) {
HStack(alignment: .firstTextBaseline) {
Text("Usage")
.font(.caption.weight(.semibold))
.foregroundStyle(.secondary)
Spacer(minLength: 10)
Text(self.subtitle)
.font(.caption)
.foregroundStyle(.secondary)
}
if let statusText, !statusText.isEmpty {
Text(statusText)
.font(.caption)
.foregroundStyle(.secondary)
.lineLimit(1)
.truncationMode(.tail)
}
}
.padding(.top, self.paddingTop)
.padding(.bottom, self.paddingBottom)
.padding(.leading, self.paddingLeading)
.padding(.trailing, self.paddingTrailing)
.frame(minWidth: 300, maxWidth: .infinity, alignment: .leading)
.transaction { txn in txn.animation = nil }
}
private var subtitle: String {
if self.count == 1 { return "1 provider" }
return "\(self.count) providers"
}
}
@@ -1,10 +1,8 @@
import AVFoundation
import OSLog
import SwiftUI
actor MicLevelMonitor {
private let logger = Logger(subsystem: "com.clawdbot", category: "voicewake.meter")
private var engine: AVAudioEngine?
private let engine = AVAudioEngine()
private var update: (@Sendable (Double) -> Void)?
private var running = false
private var smoothedLevel: Double = 0
@@ -12,37 +10,23 @@ actor MicLevelMonitor {
func start(onLevel: @Sendable @escaping (Double) -> Void) async throws {
self.update = onLevel
if self.running { return }
self.logger.info(
"mic level monitor start (\(AudioInputDeviceObserver.defaultInputDeviceSummary(), privacy: .public))")
let engine = AVAudioEngine()
self.engine = engine
let input = engine.inputNode
let input = self.engine.inputNode
let format = input.outputFormat(forBus: 0)
guard format.channelCount > 0, format.sampleRate > 0 else {
self.engine = nil
throw NSError(
domain: "MicLevelMonitor",
code: 1,
userInfo: [NSLocalizedDescriptionKey: "No audio input available"])
}
input.removeTap(onBus: 0)
input.installTap(onBus: 0, bufferSize: 512, format: format) { [weak self] buffer, _ in
guard let self else { return }
let level = Self.normalizedLevel(from: buffer)
Task { await self.push(level: level) }
}
engine.prepare()
try engine.start()
self.engine.prepare()
try self.engine.start()
self.running = true
}
func stop() {
guard self.running else { return }
if let engine {
engine.inputNode.removeTap(onBus: 0)
engine.stop()
}
self.engine = nil
self.engine.inputNode.removeTap(onBus: 0)
self.engine.stop()
self.running = false
}
@@ -1,7 +1,6 @@
import ClawdbotKit
import Foundation
import Network
import OSLog
actor MacNodeBridgeSession {
private struct TimeoutError: LocalizedError {
@@ -16,18 +15,14 @@ actor MacNodeBridgeSession {
case failed(message: String)
}
private let logger = Logger(subsystem: "com.clawdbot", category: "node.bridge-session")
private let encoder = JSONEncoder()
private let decoder = JSONDecoder()
private let clock = ContinuousClock()
private var connection: NWConnection?
private var queue: DispatchQueue?
private var buffer = Data()
private var pendingRPC: [String: CheckedContinuation<BridgeRPCResponse, Error>] = [:]
private var serverEventSubscribers: [UUID: AsyncStream<BridgeEventFrame>.Continuation] = [:]
private var pingTask: Task<Void, Never>?
private var lastPongAt: ContinuousClock.Instant?
private(set) var state: State = .idle
@@ -43,12 +38,6 @@ actor MacNodeBridgeSession {
let params = NWParameters.tcp
params.includePeerToPeer = true
let tcpOptions = NWProtocolTCP.Options()
tcpOptions.enableKeepalive = true
tcpOptions.keepaliveIdle = 30
tcpOptions.keepaliveInterval = 15
tcpOptions.keepaliveCount = 3
params.defaultProtocolStack.transportProtocol = tcpOptions
let connection = NWConnection(to: endpoint, using: params)
let queue = DispatchQueue(label: "com.clawdbot.macos.bridge-session")
self.connection = connection
@@ -58,10 +47,6 @@ actor MacNodeBridgeSession {
connection.start(queue: queue)
try await Self.waitForReady(stateStream, timeoutSeconds: 6)
connection.stateUpdateHandler = { [weak self] state in
guard let self else { return }
Task { await self.handleConnectionState(state) }
}
try await AsyncTimeout.withTimeout(
seconds: 6,
@@ -92,7 +77,6 @@ actor MacNodeBridgeSession {
if base.type == "hello-ok" {
let ok = try self.decoder.decode(BridgeHelloOk.self, from: data)
self.state = .connected(serverName: ok.serverName)
self.startPingLoop()
await onConnected?(ok.serverName)
} else if base.type == "error" {
let err = try self.decoder.decode(BridgeErrorFrame.self, from: data)
@@ -129,10 +113,6 @@ actor MacNodeBridgeSession {
let ping = try self.decoder.decode(BridgePing.self, from: nextData)
try await self.send(BridgePong(type: "pong", id: ping.id))
case "pong":
let pong = try self.decoder.decode(BridgePong.self, from: nextData)
self.notePong(pong)
case "invoke":
let req = try self.decoder.decode(BridgeInvokeRequest.self, from: nextData)
let res = await onInvoke(req)
@@ -202,10 +182,6 @@ actor MacNodeBridgeSession {
}
func disconnect() async {
self.pingTask?.cancel()
self.pingTask = nil
self.lastPongAt = nil
self.connection?.cancel()
self.connection = nil
self.queue = nil
@@ -263,17 +239,12 @@ actor MacNodeBridgeSession {
}
private func send(_ obj: some Encodable) async throws {
guard let connection = self.connection else {
throw NSError(domain: "Bridge", code: 15, userInfo: [
NSLocalizedDescriptionKey: "not connected",
])
}
let data = try self.encoder.encode(obj)
var line = Data()
line.append(data)
line.append(0x0A)
try await withCheckedThrowingContinuation(isolation: self) { (cont: CheckedContinuation<Void, Error>) in
connection.send(content: line, completion: .contentProcessed { err in
self.connection?.send(content: line, completion: .contentProcessed { err in
if let err { cont.resume(throwing: err) } else { cont.resume(returning: ()) }
})
}
@@ -309,66 +280,6 @@ actor MacNodeBridgeSession {
}
}
private func startPingLoop() {
self.pingTask?.cancel()
self.lastPongAt = self.clock.now
self.pingTask = Task { [weak self] in
guard let self else { return }
await self.runPingLoop()
}
}
private func runPingLoop() async {
let interval: Duration = .seconds(15)
let timeout: Duration = .seconds(45)
while !Task.isCancelled {
try? await Task.sleep(for: interval)
guard self.connection != nil else { return }
if let last = self.lastPongAt {
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)).")
await self.disconnect()
return
}
}
let id = UUID().uuidString
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)).")
await self.disconnect()
return
}
}
}
private func notePong(_ pong: BridgePong) {
_ = pong
self.lastPongAt = self.clock.now
}
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)).")
await self.disconnect()
case .cancelled:
self.logger.warning("Node bridge connection cancelled; disconnecting.")
await self.disconnect()
default:
break
}
}
private static func makeStateStream(
for connection: NWConnection) -> AsyncStream<NWConnection.State>
{
@@ -202,23 +202,6 @@ final class MacNodeModeCoordinator {
return 18790
}
static func remoteBridgePort() -> Int {
let fallback = Int(Self.loopbackBridgePort() ?? 18790)
let settings = CommandResolver.connectionSettings()
let sshHost = CommandResolver.parseSSHTarget(settings.target)?.host ?? ""
let base =
ClawdbotConfigFile.remoteGatewayPort(matchingHost: sshHost) ??
GatewayEnvironment.gatewayPort()
guard base > 0 else { return fallback }
return Self.derivePort(base: base, offset: 1, fallback: fallback)
}
private static func derivePort(base: Int, offset: Int, fallback: Int) -> Int {
let derived = base + offset
guard derived > 0, derived <= Int(UInt16.max) else { return fallback }
return derived
}
static func probeEndpoint(_ endpoint: NWEndpoint, timeoutSeconds: Double) async -> Bool {
let connection = NWConnection(to: endpoint, using: .tcp)
let stream = Self.makeStateStream(for: connection)
@@ -286,10 +269,7 @@ final class MacNodeModeCoordinator {
if mode == .remote {
do {
if self.tunnel == nil || self.tunnel?.process.isRunning == false {
let remotePort = Self.remoteBridgePort()
self.tunnel = try await RemotePortTunnel.create(
remotePort: remotePort,
allowRemoteUrlOverride: false)
self.tunnel = try await RemotePortTunnel.create(remotePort: 18790)
}
if let localPort = self.tunnel?.localPort,
let port = NWEndpoint.Port(rawValue: localPort)
@@ -5,16 +5,8 @@ import Foundation
actor MacNodeRuntime {
private let cameraCapture = CameraCaptureService()
private let makeMainActorServices: () async -> any MacNodeRuntimeMainActorServices
private var cachedMainActorServices: (any MacNodeRuntimeMainActorServices)?
init(
makeMainActorServices: @escaping () async -> any MacNodeRuntimeMainActorServices = {
await MainActor.run { LiveMacNodeRuntimeMainActorServices() }
})
{
self.makeMainActorServices = makeMainActorServices
}
@MainActor private let screenRecorder = ScreenRecordService()
@MainActor private let locationService = MacNodeLocationService()
func handleInvoke(_ req: BridgeInvokeRequest) async -> BridgeInvokeResponse {
let command = req.command
@@ -220,8 +212,7 @@ actor MacNodeRuntime {
ClawdbotLocationGetParams()
let desired = params.desiredAccuracy ??
(Self.locationPreciseEnabled() ? .precise : .balanced)
let services = await self.mainActorServices()
let status = await services.locationAuthorizationStatus()
let status = await self.locationService.authorizationStatus()
if status != .authorizedAlways {
return BridgeInvokeResponse(
id: req.id,
@@ -231,11 +222,11 @@ actor MacNodeRuntime {
message: "LOCATION_PERMISSION_REQUIRED: grant Location permission"))
}
do {
let location = try await services.currentLocation(
let location = try await self.locationService.currentLocation(
desiredAccuracy: desired,
maxAgeMs: params.maxAgeMs,
timeoutMs: params.timeoutMs)
let isPrecise = await services.locationAccuracyAuthorization() == .fullAccuracy
let isPrecise = await self.locationService.accuracyAuthorization() == .fullAccuracy
let payload = ClawdbotLocationPayload(
lat: location.coordinate.latitude,
lon: location.coordinate.longitude,
@@ -274,8 +265,7 @@ actor MacNodeRuntime {
code: .invalidRequest,
message: "INVALID_REQUEST: screen format must be mp4")
}
let services = await self.mainActorServices()
let res = try await services.recordScreen(
let res = try await self.screenRecorder.record(
screenIndex: params.screenIndex,
durationMs: params.durationMs,
fps: params.fps,
@@ -301,13 +291,6 @@ actor MacNodeRuntime {
return BridgeInvokeResponse(id: req.id, ok: true, payloadJSON: payload)
}
private func mainActorServices() async -> any MacNodeRuntimeMainActorServices {
if let cachedMainActorServices { return cachedMainActorServices }
let services = await self.makeMainActorServices()
self.cachedMainActorServices = services
return services
}
private func handleA2UIReset(_ req: BridgeInvokeRequest) async throws -> BridgeInvokeResponse {
try await self.ensureA2UIHost()
@@ -1,60 +0,0 @@
import ClawdbotKit
import CoreLocation
import Foundation
@MainActor
protocol MacNodeRuntimeMainActorServices: Sendable {
func recordScreen(
screenIndex: Int?,
durationMs: Int?,
fps: Double?,
includeAudio: Bool?,
outPath: String?) async throws -> (path: String, hasAudio: Bool)
func locationAuthorizationStatus() -> CLAuthorizationStatus
func locationAccuracyAuthorization() -> CLAccuracyAuthorization
func currentLocation(
desiredAccuracy: ClawdbotLocationAccuracy,
maxAgeMs: Int?,
timeoutMs: Int?) async throws -> CLLocation
}
@MainActor
final class LiveMacNodeRuntimeMainActorServices: MacNodeRuntimeMainActorServices, @unchecked Sendable {
private let screenRecorder = ScreenRecordService()
private let locationService = MacNodeLocationService()
func recordScreen(
screenIndex: Int?,
durationMs: Int?,
fps: Double?,
includeAudio: Bool?,
outPath: String?) async throws -> (path: String, hasAudio: Bool)
{
try await self.screenRecorder.record(
screenIndex: screenIndex,
durationMs: durationMs,
fps: fps,
includeAudio: includeAudio,
outPath: outPath)
}
func locationAuthorizationStatus() -> CLAuthorizationStatus {
self.locationService.authorizationStatus()
}
func locationAccuracyAuthorization() -> CLAccuracyAuthorization {
self.locationService.accuracyAuthorization()
}
func currentLocation(
desiredAccuracy: ClawdbotLocationAccuracy,
maxAgeMs: Int?,
timeoutMs: Int?) async throws -> CLLocation
{
try await self.locationService.currentLocation(
desiredAccuracy: desiredAccuracy,
maxAgeMs: maxAgeMs,
timeoutMs: timeoutMs)
}
}
@@ -29,7 +29,6 @@ extension OnboardingView {
user: user,
host: host,
port: gateway.sshPort)
ClawdbotConfigFile.setRemoteGatewayUrl(host: host, port: gateway.gatewayPort)
}
self.state.remoteCliPath = gateway.cliPath ?? ""
@@ -607,7 +607,7 @@ extension OnboardingView {
let saved = await self.saveAgentWorkspace(AgentWorkspace.displayPath(for: url))
if saved {
self.workspaceStatus =
"Saved to ~/.clawdbot/clawdbot.json (agents.defaults.workspace)"
"Saved to ~/.clawdbot/clawdbot.json (agent.workspace)"
}
}
}
@@ -12,7 +12,6 @@ extension OnboardingView {
lanHost: "bridge.local",
tailnetDns: "bridge.ts.net",
sshPort: 2222,
gatewayPort: 18789,
cliPath: "/usr/local/bin/clawdbot",
stableID: "bridge-1",
debugID: "bridge-1",
@@ -69,9 +69,8 @@ extension OnboardingView {
private func loadAgentWorkspace() async -> String? {
let root = await ConfigStore.load()
let agents = root["agents"] as? [String: Any]
let defaults = agents?["defaults"] as? [String: Any]
return defaults?["workspace"] as? String
let agent = root["agent"] as? [String: Any]
return agent?["workspace"] as? String
}
@discardableResult
@@ -87,23 +86,17 @@ extension OnboardingView {
@MainActor
private static func buildAndSaveWorkspace(_ workspace: String?) async -> (Bool, String?) {
var root = await ConfigStore.load()
var agents = root["agents"] as? [String: Any] ?? [:]
var defaults = agents["defaults"] as? [String: Any] ?? [:]
var agent = root["agent"] as? [String: Any] ?? [:]
let trimmed = workspace?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
if trimmed.isEmpty {
defaults.removeValue(forKey: "workspace")
agent.removeValue(forKey: "workspace")
} else {
defaults["workspace"] = trimmed
agent["workspace"] = trimmed
}
if defaults.isEmpty {
agents.removeValue(forKey: "defaults")
if agent.isEmpty {
root.removeValue(forKey: "agent")
} else {
agents["defaults"] = defaults
}
if agents.isEmpty {
root.removeValue(forKey: "agents")
} else {
root["agents"] = agents
root["agent"] = agent
}
do {
try await ConfigStore.save(root)
@@ -2,12 +2,11 @@ import Foundation
extension ProcessInfo {
var isPreview: Bool {
guard let raw = getenv("XCODE_RUNNING_FOR_PREVIEWS") else { return false }
return String(cString: raw) == "1"
self.environment["XCODE_RUNNING_FOR_PREVIEWS"] == "1"
}
var isNixMode: Bool {
if let raw = getenv("CLAWDBOT_NIX_MODE"), String(cString: raw) == "1" { return true }
if self.environment["CLAWDBOT_NIX_MODE"] == "1" { return true }
return UserDefaults.standard.bool(forKey: "clawdbot.nixMode")
}
@@ -38,11 +38,7 @@ final class RemotePortTunnel {
Task { await PortGuardian.shared.removeRecord(pid: pid) }
}
static func create(
remotePort: Int,
preferredLocalPort: UInt16? = nil,
allowRemoteUrlOverride: Bool = true) async throws -> RemotePortTunnel
{
static func create(remotePort: Int, preferredLocalPort: UInt16? = nil) async throws -> RemotePortTunnel {
let settings = CommandResolver.connectionSettings()
guard settings.mode == .remote, let parsed = CommandResolver.parseSSHTarget(settings.target) else {
throw NSError(
@@ -53,10 +49,7 @@ final class RemotePortTunnel {
let localPort = try await Self.findPort(preferred: preferredLocalPort)
let sshHost = parsed.host.trimmingCharacters(in: .whitespacesAndNewlines)
let remotePortOverride =
allowRemoteUrlOverride && remotePort == GatewayEnvironment.gatewayPort()
? Self.resolveRemotePortOverride(for: sshHost)
: nil
let remotePortOverride = Self.resolveRemotePortOverride(for: sshHost)
let resolvedRemotePort = remotePortOverride ?? remotePort
if let override = remotePortOverride {
Self.logger.info(
Binary file not shown.
@@ -15,9 +15,9 @@
<key>CFBundlePackageType</key>
<string>APPL</string>
<key>CFBundleShortVersionString</key>
<string>2026.1.9</string>
<string>0.0.0</string>
<key>CFBundleVersion</key>
<string>20260109</string>
<string>0.0.0</string>
<key>CFBundleIconFile</key>
<string>Clawdbot</string>
<key>CFBundleURLTypes</key>
@@ -9,7 +9,7 @@ struct GatewaySessionDefaultsRecord: Codable {
struct GatewaySessionEntryRecord: Codable {
let key: String
let displayName: String?
let provider: String?
let surface: String?
let subject: String?
let room: String?
let space: String?
@@ -71,7 +71,7 @@ struct SessionRow: Identifiable {
let key: String
let kind: SessionKind
let displayName: String?
let provider: String?
let surface: String?
let subject: String?
let room: String?
let space: String?
@@ -141,7 +141,7 @@ extension SessionRow {
key: "user@example.com",
kind: .direct,
displayName: nil,
provider: nil,
surface: nil,
subject: nil,
room: nil,
space: nil,
@@ -158,7 +158,7 @@ extension SessionRow {
key: "discord:channel:release-squad",
kind: .group,
displayName: "discord:#release-squad",
provider: "discord",
surface: "discord",
subject: nil,
room: "#release-squad",
space: nil,
@@ -175,7 +175,7 @@ extension SessionRow {
key: "global",
kind: .global,
displayName: nil,
provider: nil,
surface: nil,
subject: nil,
room: nil,
space: nil,
@@ -298,7 +298,7 @@ enum SessionLoader {
key: entry.key,
kind: SessionKind.from(key: entry.key),
displayName: entry.displayName,
provider: entry.provider,
surface: entry.surface,
subject: entry.subject,
room: entry.room,
space: entry.space,
@@ -31,7 +31,7 @@ struct SettingsRootView: View {
.tabItem { Label("Connections", systemImage: "link") }
.tag(SettingsTab.connections)
VoiceWakeSettings(state: self.state, isActive: self.selectedTab == .voiceWake)
VoiceWakeSettings(state: self.state)
.tabItem { Label("Voice Wake", systemImage: "waveform.circle") }
.tag(SettingsTab.voiceWake)
-109
View File
@@ -1,109 +0,0 @@
import Foundation
struct GatewayUsageWindow: Codable {
let label: String
let usedPercent: Double
let resetAt: Double?
}
struct GatewayUsageProvider: Codable {
let provider: String
let displayName: String
let windows: [GatewayUsageWindow]
let plan: String?
let error: String?
}
struct GatewayUsageSummary: Codable {
let updatedAt: Double
let providers: [GatewayUsageProvider]
}
struct UsageRow: Identifiable {
let id: String
let displayName: String
let plan: String?
let windowLabel: String?
let usedPercent: Double?
let resetAt: Date?
let error: String?
var titleText: String {
if let plan, !plan.isEmpty { return "\(self.displayName) (\(plan))" }
return self.displayName
}
var remainingPercent: Int? {
guard let usedPercent, usedPercent.isFinite else { return nil }
let remaining = max(0, min(100, Int(round(100 - usedPercent))))
return remaining
}
func detailText(now: Date = .init()) -> String {
if let error, !error.isEmpty { return error }
guard let remaining = self.remainingPercent else { return "No data" }
var parts = ["\(remaining)% left"]
if let windowLabel, !windowLabel.isEmpty { parts.append(windowLabel) }
if let resetAt {
let reset = UsageRow.formatResetRemaining(target: resetAt, now: now)
if let reset { parts.append("⏱\(reset)") }
}
return parts.joined(separator: " · ")
}
private static func formatResetRemaining(target: Date, now: Date) -> String? {
let diff = target.timeIntervalSince(now)
if diff <= 0 { return "now" }
let minutes = Int(floor(diff / 60))
if minutes < 60 { return "\(minutes)m" }
let hours = minutes / 60
let mins = minutes % 60
if hours < 24 { return mins > 0 ? "\(hours)h \(mins)m" : "\(hours)h" }
let days = hours / 24
if days < 7 { return "\(days)d \(hours % 24)h" }
let formatter = DateFormatter()
formatter.dateFormat = "MMM d"
return formatter.string(from: target)
}
}
extension GatewayUsageSummary {
func primaryRows() -> [UsageRow] {
self.providers.compactMap { provider in
if let error = provider.error, provider.windows.isEmpty {
return UsageRow(
id: provider.provider,
displayName: provider.displayName,
plan: provider.plan,
windowLabel: nil,
usedPercent: nil,
resetAt: nil,
error: error)
}
guard let window = provider.windows.max(by: { $0.usedPercent < $1.usedPercent }) else {
return nil
}
return UsageRow(
id: "\(provider.provider)-\(window.label)",
displayName: provider.displayName,
plan: provider.plan,
windowLabel: window.label,
usedPercent: window.usedPercent,
resetAt: window.resetAt.map { Date(timeIntervalSince1970: $0 / 1000) },
error: provider.error)
}
}
}
@MainActor
enum UsageLoader {
static func loadSummary() async throws -> GatewayUsageSummary {
let data = try await ControlChannel.shared.request(
method: "usage.status",
params: nil,
timeoutMs: 5000)
return try JSONDecoder().decode(GatewayUsageSummary.self, from: data)
}
}
@@ -1,45 +0,0 @@
import SwiftUI
struct UsageMenuLabelView: View {
let row: UsageRow
let width: CGFloat
private let paddingLeading: CGFloat = 22
private let paddingTrailing: CGFloat = 14
private let barHeight: CGFloat = 6
private var primaryTextColor: Color { .primary }
private var secondaryTextColor: Color { .secondary }
var body: some View {
VStack(alignment: .leading, spacing: 8) {
if let used = row.usedPercent {
ContextUsageBar(
usedTokens: Int(round(used)),
contextTokens: 100,
width: max(1, self.width - (self.paddingLeading + self.paddingTrailing)),
height: self.barHeight)
}
HStack(alignment: .firstTextBaseline, spacing: 6) {
Text(self.row.titleText)
.font(.caption.weight(.semibold))
.foregroundStyle(self.primaryTextColor)
.lineLimit(1)
.truncationMode(.middle)
.layoutPriority(1)
Spacer(minLength: 4)
Text(self.row.detailText())
.font(.caption.monospacedDigit())
.foregroundStyle(self.secondaryTextColor)
.lineLimit(1)
.fixedSize(horizontal: true, vertical: false)
.layoutPriority(2)
}
}
.padding(.vertical, 10)
.padding(.leading, self.paddingLeading)
.padding(.trailing, self.paddingTrailing)
}
}
@@ -37,7 +37,7 @@ enum VoiceWakeForwarder {
var thinking: String = "low"
var deliver: Bool = true
var to: String?
var provider: GatewayAgentProvider = .last
var channel: GatewayAgentChannel = .last
}
@discardableResult
@@ -46,14 +46,14 @@ enum VoiceWakeForwarder {
options: ForwardOptions = ForwardOptions()) async -> Result<Void, VoiceWakeForwardError>
{
let payload = Self.prefixedTranscript(transcript)
let deliver = options.provider.shouldDeliver(options.deliver)
let deliver = options.channel.shouldDeliver(options.deliver)
let result = await GatewayConnection.shared.sendAgent(GatewayAgentInvocation(
message: payload,
sessionKey: options.sessionKey,
thinking: options.thinking,
deliver: deliver,
to: options.to,
provider: options.provider))
channel: options.channel))
if result.ok {
self.logger.info("voice wake forward ok")
@@ -38,15 +38,6 @@ actor VoiceWakeRuntime {
private var overlayToken: UUID?
private var activeTriggerEndTime: TimeInterval?
private var scheduledRestartTask: Task<Void, Never>?
private var lastLoggedText: String?
private var lastLoggedAt: Date?
private var lastTapLogAt: Date?
private var lastCallbackLogAt: Date?
private var lastTranscript: String?
private var lastTranscriptAt: Date?
private var preDetectTask: Task<Void, Never>?
private var isStarting: Bool = false
private var triggerOnlyTask: Task<Void, Never>?
// Tunables
// Silence threshold once we've captured user speech (post-trigger).
@@ -59,8 +50,6 @@ actor VoiceWakeRuntime {
// Voice activity detection parameters (RMS-based).
private let minSpeechRMS: Double = 1e-3
private let speechBoostFactor: Double = 6.0 // how far above noise floor we require to mark speech
private let preDetectSilenceWindow: TimeInterval = 1.0
private let triggerPauseWindow: TimeInterval = 0.55
/// Stops the active Speech pipeline without clearing the stored config, so we can restart cleanly.
private func haltRecognitionPipeline() {
@@ -117,19 +106,6 @@ actor VoiceWakeRuntime {
let config = snapshot.1
if self.isStarting {
return
}
if self.scheduledRestartTask != nil, config == self.currentConfig, self.recognitionTask == nil {
return
}
if self.scheduledRestartTask != nil {
self.scheduledRestartTask?.cancel()
self.scheduledRestartTask = nil
}
if config == self.currentConfig, self.recognitionTask != nil {
return
}
@@ -139,11 +115,6 @@ actor VoiceWakeRuntime {
}
private func start(with config: RuntimeConfig) async {
if self.isStarting {
return
}
self.isStarting = true
defer { self.isStarting = false }
do {
self.recognitionGeneration &+= 1
let generation = self.recognitionGeneration
@@ -157,7 +128,6 @@ actor VoiceWakeRuntime {
self.recognitionRequest = SFSpeechAudioBufferRecognitionRequest()
self.recognitionRequest?.shouldReportPartialResults = true
self.recognitionRequest?.taskHint = .dictation
guard let request = self.recognitionRequest else { return }
// Lazily create the engine here so app launch doesn't grab audio resources / trigger Bluetooth HFP.
@@ -168,19 +138,13 @@ actor VoiceWakeRuntime {
let input = audioEngine.inputNode
let format = input.outputFormat(forBus: 0)
guard format.channelCount > 0, format.sampleRate > 0 else {
throw NSError(
domain: "VoiceWakeRuntime",
code: 1,
userInfo: [NSLocalizedDescriptionKey: "No audio input available"])
}
input.removeTap(onBus: 0)
input.installTap(onBus: 0, bufferSize: 2048, format: format) { [weak self, weak request] buffer, _ in
request?.append(buffer)
guard let rms = Self.rmsLevel(buffer: buffer) else { return }
Task.detached { [weak self] in
await self?.noteAudioLevel(rms: rms)
await self?.noteAudioTap(rms: rms)
if let rms = Self.rmsLevel(buffer: buffer) {
Task.detached { [weak self] in
await self?.noteAudioLevel(rms: rms)
}
}
}
@@ -199,7 +163,6 @@ actor VoiceWakeRuntime {
.map { WakeWordSpeechSegments.from(transcription: result.bestTranscription, transcript: $0) }
} ?? []
let isFinal = result?.isFinal ?? false
Task { await self.noteRecognitionCallback(transcript: transcript, isFinal: isFinal, error: error) }
let update = RecognitionUpdate(
transcript: transcript,
segments: segments,
@@ -209,10 +172,6 @@ actor VoiceWakeRuntime {
Task { await self.handleRecognition(update, config: config) }
}
let preferred = config.micID?.isEmpty == false ? config.micID! : "system-default"
self.logger.info(
"voicewake runtime input preferred=\(preferred, privacy: .public) " +
"\(AudioInputDeviceObserver.defaultInputDeviceSummary(), privacy: .public)")
self.logger.info("voicewake runtime started")
DiagnosticsFileLog.shared.log(category: "voicewake.runtime", event: "started", fields: [
"locale": config.localeID ?? "",
@@ -235,12 +194,6 @@ actor VoiceWakeRuntime {
self.capturedTranscript = ""
self.captureStartedAt = nil
self.triggerChimePlayed = false
self.lastTranscript = nil
self.lastTranscriptAt = nil
self.preDetectTask?.cancel()
self.preDetectTask = nil
self.triggerOnlyTask?.cancel()
self.triggerOnlyTask = nil
self.haltRecognitionPipeline()
self.recognizer = nil
self.currentConfig = nil
@@ -264,7 +217,6 @@ actor VoiceWakeRuntime {
private func configureSession(localeID: String?) {
let locale = localeID.flatMap { Locale(identifier: $0) } ?? Locale(identifier: Locale.current.identifier)
self.recognizer = SFSpeechRecognizer(locale: locale)
self.recognizer?.defaultTaskHint = .dictation
}
private func handleRecognition(_ update: RecognitionUpdate, config: RuntimeConfig) async {
@@ -280,19 +232,7 @@ actor VoiceWakeRuntime {
let now = Date()
if !transcript.isEmpty {
self.lastHeard = now
if !self.isCapturing {
self.lastTranscript = transcript
self.lastTranscriptAt = now
}
if self.isCapturing {
self.maybeLogRecognition(
transcript: transcript,
segments: update.segments,
triggers: config.triggers,
isFinal: update.isFinal,
match: nil,
usedFallback: false,
capturing: true)
let trimmed = Self.commandAfterTrigger(
transcript: transcript,
segments: update.segments,
@@ -326,214 +266,15 @@ actor VoiceWakeRuntime {
if self.isCapturing { return }
let gateConfig = WakeWordGateConfig(triggers: config.triggers)
var usedFallback = false
var match = WakeWordGate.match(transcript: transcript, segments: update.segments, config: gateConfig)
if match == nil, update.isFinal {
match = self.textOnlyFallbackMatch(
transcript: transcript,
triggers: config.triggers,
config: gateConfig)
usedFallback = match != nil
}
self.maybeLogRecognition(
transcript: transcript,
segments: update.segments,
triggers: config.triggers,
isFinal: update.isFinal,
match: match,
usedFallback: usedFallback,
capturing: false)
if let match {
if let match = WakeWordGate.match(transcript: transcript, segments: update.segments, config: gateConfig) {
if let cooldown = cooldownUntil, now < cooldown {
return
}
if usedFallback {
self.logger.info("voicewake runtime detected (text-only fallback) len=\(match.command.count)")
} else {
self.logger.info("voicewake runtime detected len=\(match.command.count)")
}
await self.beginCapture(command: match.command, triggerEndTime: match.triggerEndTime, config: config)
} else if !transcript.isEmpty, update.error == nil {
if self.isTriggerOnly(transcript: transcript, triggers: config.triggers) {
self.preDetectTask?.cancel()
self.preDetectTask = nil
self.scheduleTriggerOnlyPauseCheck(triggers: config.triggers, config: config)
} else {
self.triggerOnlyTask?.cancel()
self.triggerOnlyTask = nil
self.schedulePreDetectSilenceCheck(
triggers: config.triggers,
gateConfig: gateConfig,
config: config)
}
}
}
private func maybeLogRecognition(
transcript: String,
segments: [WakeWordSegment],
triggers: [String],
isFinal: Bool,
match: WakeWordGateMatch?,
usedFallback: Bool,
capturing: Bool)
{
guard !transcript.isEmpty else { return }
let level = self.logger.logLevel
guard level == .debug || level == .trace else { return }
if transcript == self.lastLoggedText, !isFinal {
if let last = self.lastLoggedAt, Date().timeIntervalSince(last) < 0.25 {
return
}
}
self.lastLoggedText = transcript
self.lastLoggedAt = Date()
let textOnly = WakeWordGate.matchesTextOnly(text: transcript, triggers: triggers)
let timingCount = segments.count(where: { $0.start > 0 || $0.duration > 0 })
let matchSummary = match.map {
"match=true gap=\(String(format: "%.2f", $0.postGap))s cmdLen=\($0.command.count)"
} ?? "match=false"
let segmentSummary = segments.map { seg in
let start = String(format: "%.2f", seg.start)
let end = String(format: "%.2f", seg.end)
return "\(seg.text)@\(start)-\(end)"
}.joined(separator: ", ")
self.logger.debug(
"voicewake runtime transcript='\(transcript, privacy: .private)' textOnly=\(textOnly) " +
"isFinal=\(isFinal) timing=\(timingCount)/\(segments.count) " +
"capturing=\(capturing) fallback=\(usedFallback) " +
"\(matchSummary) segments=[\(segmentSummary, privacy: .private)]")
}
private func noteAudioTap(rms: Double) {
let now = Date()
if let last = self.lastTapLogAt, now.timeIntervalSince(last) < 1.0 {
return
}
self.lastTapLogAt = now
let db = 20 * log10(max(rms, 1e-7))
self.logger.debug(
"voicewake runtime audio tap rms=\(String(format: "%.6f", rms)) " +
"db=\(String(format: "%.1f", db)) capturing=\(self.isCapturing)")
}
private func noteRecognitionCallback(transcript: String?, isFinal: Bool, error: Error?) {
guard transcript?.isEmpty ?? true else { return }
let now = Date()
if let last = self.lastCallbackLogAt, now.timeIntervalSince(last) < 1.0 {
return
}
self.lastCallbackLogAt = now
let errorSummary = error?.localizedDescription ?? "none"
self.logger.debug(
"voicewake runtime callback empty transcript isFinal=\(isFinal) error=\(errorSummary, privacy: .public)")
}
private func scheduleTriggerOnlyPauseCheck(triggers: [String], config: RuntimeConfig) {
self.triggerOnlyTask?.cancel()
let lastSeenAt = self.lastTranscriptAt
let lastText = self.lastTranscript
let windowNanos = UInt64(self.triggerPauseWindow * 1_000_000_000)
self.triggerOnlyTask = Task { [weak self, lastSeenAt, lastText] in
try? await Task.sleep(nanoseconds: windowNanos)
guard let self else { return }
await self.triggerOnlyPauseCheck(
lastSeenAt: lastSeenAt,
lastText: lastText,
triggers: triggers,
config: config)
}
}
private func schedulePreDetectSilenceCheck(
triggers: [String],
gateConfig: WakeWordGateConfig,
config: RuntimeConfig)
{
self.preDetectTask?.cancel()
let lastSeenAt = self.lastTranscriptAt
let lastText = self.lastTranscript
let windowNanos = UInt64(self.preDetectSilenceWindow * 1_000_000_000)
self.preDetectTask = Task { [weak self, lastSeenAt, lastText] in
try? await Task.sleep(nanoseconds: windowNanos)
guard let self else { return }
await self.preDetectSilenceCheck(
lastSeenAt: lastSeenAt,
lastText: lastText,
triggers: triggers,
gateConfig: gateConfig,
config: config)
}
}
private func triggerOnlyPauseCheck(
lastSeenAt: Date?,
lastText: String?,
triggers: [String],
config: RuntimeConfig) async
{
guard !Task.isCancelled else { return }
guard !self.isCapturing else { return }
guard let lastSeenAt, let lastText else { return }
guard self.lastTranscriptAt == lastSeenAt, self.lastTranscript == lastText else { return }
guard self.isTriggerOnly(transcript: lastText, triggers: triggers) else { return }
if let cooldown = self.cooldownUntil, Date() < cooldown {
return
}
self.logger.info("voicewake runtime detected (trigger-only pause)")
await self.beginCapture(command: "", triggerEndTime: nil, config: config)
}
private func textOnlyFallbackMatch(
transcript: String,
triggers: [String],
config: WakeWordGateConfig) -> WakeWordGateMatch?
{
guard let command = VoiceWakeTextUtils.textOnlyCommand(
transcript: transcript,
triggers: triggers,
minCommandLength: config.minCommandLength,
trimWake: Self.trimmedAfterTrigger)
else { return nil }
return WakeWordGateMatch(triggerEndTime: 0, postGap: 0, command: command)
}
private func isTriggerOnly(transcript: String, triggers: [String]) -> Bool {
guard WakeWordGate.matchesTextOnly(text: transcript, triggers: triggers) else { return false }
guard VoiceWakeTextUtils.startsWithTrigger(transcript: transcript, triggers: triggers) else { return false }
return Self.trimmedAfterTrigger(transcript, triggers: triggers).isEmpty
}
private func preDetectSilenceCheck(
lastSeenAt: Date?,
lastText: String?,
triggers: [String],
gateConfig: WakeWordGateConfig,
config: RuntimeConfig) async
{
guard !Task.isCancelled else { return }
guard !self.isCapturing else { return }
guard let lastSeenAt, let lastText else { return }
guard self.lastTranscriptAt == lastSeenAt, self.lastTranscript == lastText else { return }
guard let match = self.textOnlyFallbackMatch(
transcript: lastText,
triggers: triggers,
config: gateConfig)
else { return }
if let cooldown = self.cooldownUntil, Date() < cooldown {
return
}
self.logger.info("voicewake runtime detected (silence fallback) len=\(match.command.count)")
await self.beginCapture(
command: match.command,
triggerEndTime: match.triggerEndTime,
config: config)
}
private func beginCapture(command: String, triggerEndTime: TimeInterval?, config: RuntimeConfig) async {
private func beginCapture(command: String, triggerEndTime: TimeInterval, config: RuntimeConfig) async {
self.listeningState = .voiceWake
self.isCapturing = true
DiagnosticsFileLog.shared.log(category: "voicewake.runtime", event: "beginCapture")
@@ -545,10 +286,6 @@ actor VoiceWakeRuntime {
self.heardBeyondTrigger = !command.isEmpty
self.triggerChimePlayed = false
self.activeTriggerEndTime = triggerEndTime
self.preDetectTask?.cancel()
self.preDetectTask = nil
self.triggerOnlyTask?.cancel()
self.triggerOnlyTask = nil
if config.triggerChime != .none, !self.triggerChimePlayed {
self.triggerChimePlayed = true
@@ -621,12 +358,6 @@ actor VoiceWakeRuntime {
self.heardBeyondTrigger = false
self.triggerChimePlayed = false
self.activeTriggerEndTime = nil
self.lastTranscript = nil
self.lastTranscriptAt = nil
self.preDetectTask?.cancel()
self.preDetectTask = nil
self.triggerOnlyTask?.cancel()
self.triggerOnlyTask = nil
await MainActor.run { AppStateStore.shared.stopVoiceEars() }
if let token = self.overlayToken {
@@ -710,15 +441,10 @@ actor VoiceWakeRuntime {
let nanos = UInt64(max(0, delay) * 1_000_000_000)
try? await Task.sleep(nanoseconds: nanos)
guard let self else { return }
await self.consumeScheduledRestart()
await self.restartRecognizerIfIdleAndOverlayHidden()
}
}
private func consumeScheduledRestart() {
self.scheduledRestartTask = nil
}
func applyPushToTalkCooldown() {
self.cooldownUntil = Date().addingTimeInterval(self.debounceAfterSend)
}
@@ -2,24 +2,19 @@ import AppKit
import AVFoundation
import Observation
import Speech
import SwabbleKit
import SwiftUI
import UniformTypeIdentifiers
struct VoiceWakeSettings: View {
@Bindable var state: AppState
let isActive: Bool
@State private var testState: VoiceWakeTestState = .idle
@State private var tester = VoiceWakeTester()
@State private var isTesting = false
@State private var testTimeoutTask: Task<Void, Never>?
@State private var availableMics: [AudioInputDevice] = []
@State private var loadingMics = false
@State private var meterLevel: Double = 0
@State private var meterError: String?
private let meter = MicLevelMonitor()
@State private var micObserver = AudioInputDeviceObserver()
@State private var micRefreshTask: Task<Void, Never>?
@State private var availableLocales: [Locale] = []
private let fieldLabelWidth: CGFloat = 140
private let controlWidth: CGFloat = 240
@@ -102,39 +97,12 @@ struct VoiceWakeSettings: View {
guard !self.isPreview else { return }
await self.restartMeter()
}
.onAppear {
guard !self.isPreview else { return }
self.startMicObserver()
}
.onChange(of: self.state.voiceWakeMicID) { _, _ in
guard !self.isPreview else { return }
self.updateSelectedMicName()
Task { await self.restartMeter() }
}
.onChange(of: self.isActive) { _, active in
guard !self.isPreview else { return }
if !active {
self.tester.stop()
self.isTesting = false
self.testState = .idle
self.testTimeoutTask?.cancel()
self.micRefreshTask?.cancel()
self.micRefreshTask = nil
Task { await self.meter.stop() }
self.micObserver.stop()
} else {
self.startMicObserver()
}
}
.onDisappear {
guard !self.isPreview else { return }
self.tester.stop()
self.isTesting = false
self.testState = .idle
self.testTimeoutTask?.cancel()
self.micRefreshTask?.cancel()
self.micRefreshTask = nil
self.micObserver.stop()
Task { await self.meter.stop() }
}
}
@@ -237,23 +205,13 @@ struct VoiceWakeSettings: View {
return
}
if self.isTesting {
self.tester.finalize()
self.tester.stop()
self.isTesting = false
self.testState = .finalizing
Task { @MainActor in
try? await Task.sleep(nanoseconds: 2_000_000_000)
if self.testState == .finalizing {
self.tester.stop()
self.testState = .failed("Stopped")
}
}
self.testTimeoutTask?.cancel()
self.testState = .idle
return
}
let triggers = self.sanitizedTriggers()
self.tester.stop()
self.testTimeoutTask?.cancel()
self.isTesting = true
self.testState = .requesting
Task { @MainActor in
@@ -267,31 +225,18 @@ struct VoiceWakeSettings: View {
self.testState = newState
if case .detected = newState { self.isTesting = false }
if case .failed = newState { self.isTesting = false }
if case .detected = newState { self.testTimeoutTask?.cancel() }
if case .failed = newState { self.testTimeoutTask?.cancel() }
}
})
self.testTimeoutTask?.cancel()
self.testTimeoutTask = Task { @MainActor in
try? await Task.sleep(nanoseconds: 10 * 1_000_000_000)
guard !Task.isCancelled else { return }
if self.isTesting {
self.tester.stop()
if case let .hearing(text) = self.testState,
let command = Self.textOnlyCommand(from: text, triggers: triggers)
{
self.testState = .detected(command)
} else {
self.testState = .failed("Timeout: no trigger heard")
}
self.isTesting = false
}
try await Task.sleep(nanoseconds: 10 * 1_000_000_000)
if self.isTesting {
self.tester.stop()
self.testState = .failed("Timeout: no trigger heard")
self.isTesting = false
}
} catch {
self.tester.stop()
self.testState = .failed(error.localizedDescription)
self.isTesting = false
self.testTimeoutTask?.cancel()
}
}
}
@@ -369,14 +314,6 @@ struct VoiceWakeSettings: View {
sanitizeVoiceWakeTriggers(self.state.swabbleTriggerWords)
}
private static func textOnlyCommand(from transcript: String, triggers: [String]) -> String? {
VoiceWakeTextUtils.textOnlyCommand(
transcript: transcript,
triggers: triggers,
minCommandLength: 1,
trimWake: { WakeWordGate.stripWake(text: $0, triggers: $1) })
}
private var micPicker: some View {
VStack(alignment: .leading, spacing: 6) {
HStack(alignment: .firstTextBaseline, spacing: 10) {
@@ -385,10 +322,6 @@ struct VoiceWakeSettings: View {
.frame(width: self.fieldLabelWidth, alignment: .leading)
Picker("Microphone", selection: self.$state.voiceWakeMicID) {
Text("System default").tag("")
if self.isSelectedMicUnavailable {
Text(self.state.voiceWakeMicName.isEmpty ? "Unavailable" : self.state.voiceWakeMicName)
.tag(self.state.voiceWakeMicID)
}
ForEach(self.availableMics) { mic in
Text(mic.name).tag(mic.uid)
}
@@ -396,15 +329,6 @@ struct VoiceWakeSettings: View {
.labelsHidden()
.frame(width: self.controlWidth)
}
if self.isSelectedMicUnavailable {
HStack(spacing: 10) {
Color.clear.frame(width: self.fieldLabelWidth, height: 1)
Text("Disconnected (using System default)")
.font(.caption)
.foregroundStyle(.secondary)
.lineLimit(1)
}
}
if self.loadingMics {
ProgressView().controlSize(.small)
}
@@ -497,60 +421,17 @@ struct VoiceWakeSettings: View {
}
@MainActor
private func loadMicsIfNeeded(force: Bool = false) async {
guard force || self.availableMics.isEmpty, !self.loadingMics else { return }
private func loadMicsIfNeeded() async {
guard self.availableMics.isEmpty, !self.loadingMics else { return }
self.loadingMics = true
let discovery = AVCaptureDevice.DiscoverySession(
deviceTypes: [.external, .microphone],
mediaType: .audio,
position: .unspecified)
let aliveUIDs = AudioInputDeviceObserver.aliveInputDeviceUIDs()
let connectedDevices = discovery.devices.filter(\.isConnected)
let devices = aliveUIDs.isEmpty
? connectedDevices
: connectedDevices.filter { aliveUIDs.contains($0.uniqueID) }
self.availableMics = devices.map { AudioInputDevice(uid: $0.uniqueID, name: $0.localizedName) }
self.updateSelectedMicName()
self.availableMics = discovery.devices.map { AudioInputDevice(uid: $0.uniqueID, name: $0.localizedName) }
self.loadingMics = false
}
private var isSelectedMicUnavailable: Bool {
let selected = self.state.voiceWakeMicID
guard !selected.isEmpty else { return false }
return !self.availableMics.contains(where: { $0.uid == selected })
}
@MainActor
private func updateSelectedMicName() {
let selected = self.state.voiceWakeMicID
if selected.isEmpty {
self.state.voiceWakeMicName = ""
return
}
if let match = self.availableMics.first(where: { $0.uid == selected }) {
self.state.voiceWakeMicName = match.name
}
}
private func startMicObserver() {
self.micObserver.start {
Task { @MainActor in
self.scheduleMicRefresh()
}
}
}
@MainActor
private func scheduleMicRefresh() {
self.micRefreshTask?.cancel()
self.micRefreshTask = Task { @MainActor in
try? await Task.sleep(nanoseconds: 300_000_000)
guard !Task.isCancelled else { return }
await self.loadMicsIfNeeded(force: true)
await self.restartMeter()
}
}
@MainActor
private func loadLocalesIfNeeded() async {
guard self.availableLocales.isEmpty else { return }
@@ -625,7 +506,7 @@ struct VoiceWakeSettings: View {
#if DEBUG
struct VoiceWakeSettings_Previews: PreviewProvider {
static var previews: some View {
VoiceWakeSettings(state: .preview, isActive: true)
VoiceWakeSettings(state: .preview)
.frame(width: SettingsTab.windowWidth, height: SettingsTab.windowHeight)
}
}
@@ -638,7 +519,7 @@ extension VoiceWakeSettings {
state.voicePushToTalkEnabled = true
state.swabbleTriggerWords = ["Claude", "Hey"]
let view = VoiceWakeSettings(state: state, isActive: true)
let view = VoiceWakeSettings(state: state)
view.availableMics = [AudioInputDevice(uid: "mic-1", name: "Built-in")]
view.availableLocales = [Locale(identifier: "en_US")]
view.meterLevel = 0.42
@@ -57,9 +57,6 @@ struct VoiceWakeTestCard: View {
.symbolEffect(.pulse)
.foregroundStyle(Color.accentColor))
case .finalizing:
AnyView(ProgressView().controlSize(.small))
case .detected:
AnyView(Image(systemName: "checkmark.circle.fill").foregroundStyle(.green))
@@ -82,9 +79,6 @@ struct VoiceWakeTestCard: View {
case let .hearing(text):
"Heard: \(text)"
case .finalizing:
"Finalizing…"
case .detected:
"Voice wake detected!"
Loaded 100 of 1094 files, more files were not shown because too many files have changed in this diff. Show more