1c7ac2a6ab
test: fix windows-only expectations
2026-01-15 05:25:08 +00:00
77cf40da87
feat: profile-aware gateway service names ( #671 )
...
Thanks @bjesuiter.
Co-authored-by: Benjamin Jesuiter <bjesuiter@gmail.com>
2026-01-15 05:23:41 +00:00
139f80a291
chore: format sources and update protocol outputs
2026-01-15 05:17:19 +00:00
757243993c
fix: stabilize gateway config tests + tool schema
2026-01-15 05:16:28 +00:00
57c66fe813
fix: clean up onboarding + channel selection types
2026-01-15 05:12:33 +00:00
042b65dfcc
feat: add web tools config to configure
2026-01-15 05:08:56 +00:00
f6a72ef3c2
feat: improve browser extension install output
2026-01-15 05:05:27 +00:00
568cc368ae
feat: add onboarding plugin install flow
2026-01-15 05:04:09 +00:00
5abe3c2145
feat: add plugin HTTP hooks + Zalo plugin
2026-01-15 05:04:09 +00:00
ef78b198cb
feat: add Chrome extension browser relay
2026-01-15 04:52:28 +00:00
5fdaef3646
fix: downgrade unsigned gemini thinking
2026-01-15 04:51:21 +00:00
fa4670c5fe
feat: improve agent auth guidance
2026-01-15 04:51:21 +00:00
edd8c613d6
feat(security): add audit --fix
2026-01-15 04:50:06 +00:00
0a7f5bf6a5
test(gateway): fix config.patch baseHash fixtures
2026-01-15 04:50:06 +00:00
eb3e865f15
fix(build): restore tool policy typing
2026-01-15 04:50:06 +00:00
1baa55c145
Structured subagent announce output + include run outcome ( #835 )
...
* docs: clarify subagent announce status
* Make subagent announce structured and include run outcome
* fix: stabilize sub-agent announce status (#835 ) (thanks @roshanasingh4)
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-01-15 04:48:07 +00:00
6ef3837e73
Remove debug logging for responsePrefix template resolution
2026-01-14 23:36:47 -05:00
e7167e35ed
debug: use console.log instead of logVerbose for always-visible logging
2026-01-14 23:29:17 -05:00
2e0325e3bf
feat: add web search hint to onboarding
2026-01-15 04:25:19 +00:00
56b3b44342
debug: add responsePrefix template logging
2026-01-14 23:23:21 -05:00
113eea5047
fix: mutate prefixContext object instead of reassigning for closure correctness
2026-01-14 23:20:19 -05:00
7b04e6ac42
debug: add prefix template resolution logging
2026-01-14 23:15:46 -05:00
f275cc180b
feat: add web tools
2026-01-15 04:07:40 +00:00
31d3aef8d6
fix: prevent config clobbering
2026-01-15 04:06:11 +00:00
d0a4cce41e
feat: add dynamic template variables to messages.responsePrefix ( #923 )
...
Adds support for template variables in `messages.responsePrefix` that
resolve dynamically at runtime with the actual model used (including
after fallback).
Supported variables (case-insensitive):
- {model} - short model name (e.g., "claude-opus-4-5", "gpt-4o")
- {modelFull} - full model identifier (e.g., "anthropic/claude-opus-4-5")
- {provider} - provider name (e.g., "anthropic", "openai")
- {thinkingLevel} or {think} - thinking level ("high", "low", "off")
- {identity.name} or {identityName} - agent identity name
Example: "[{model} | think:{thinkingLevel}]" → "[claude-opus-4-5 | think:high]"
Variables show the actual model used after fallback, not the intended
model. Unresolved variables remain as literal text.
Implementation:
- New module: src/auto-reply/reply/response-prefix-template.ts
- Template interpolation in normalize-reply.ts via context provider
- onModelSelected callback in agent-runner-execution.ts
- Updated all 6 provider message handlers (web, signal, discord,
telegram, slack, imessage)
- 27 unit tests covering all variables and edge cases
- Documentation in docs/gateway/configuration.md and JSDoc
Fixes #923
2026-01-14 23:05:08 -05:00
429f973280
test: cover browser snapshot labels and efficient mode
2026-01-15 04:04:30 +00:00
6320f739d4
refactor: centralize whatsapp auth detection
2026-01-15 04:01:06 +00:00
1732932c57
fix: unblock launchctl stub on windows
2026-01-15 03:58:32 +00:00
1c737f88fe
test: cover provider tool policies
2026-01-15 03:55:20 +00:00
fa8d9b9189
feat: add provider-specific tool policies
2026-01-15 03:55:20 +00:00
1078d178d7
fix: doctor ack reaction migration ( #927 )
...
Thanks @grp06.
Co-authored-by: George Pickett <gpickett00@gmail.com>
2026-01-15 03:51:55 +00:00
a6e780b2f6
feat: add browser snapshot modes
2026-01-15 03:50:57 +00:00
dfea2991c9
fix(daemon): clear launchd disabled state before bootstrap ( #849 ) (thanks @ndraiman)
2026-01-15 03:35:24 +00:00
d51a9ebb0e
fix(daemon): enable launchd service before bootstrap
...
When a launchd service is uninstalled via bootout, macOS marks it as
disabled in /var/db/com.apple.xpc.launchd/disabled.*.plist. This persists
across reboots and plist recreation. Future bootstrap calls fail with
error 5 (I/O error) because the service is still marked disabled.
Fix: Call 'launchctl enable' before 'launchctl bootstrap' to clear the
disabled state, matching the fix already applied to the macOS Swift app
in GatewayLaunchAgentManager.swift.
Related: #306
2026-01-15 03:31:52 +00:00
5c52dbf661
style: oxfmt fixes ( #925 ) (thanks @grp06)
2026-01-15 03:22:54 +00:00
8f797f213e
Logging: tolerate EIO console writes
2026-01-15 03:20:48 +00:00
aa74e28112
fix(telegram): aggregate split inbound messages
2026-01-15 03:04:59 +00:00
e569f15631
fix: scrub tuple items schemas for Gemini tools ( #926 ) — thanks @grp06
...
Co-authored-by: George Pickett <gpickett00@gmail.com>
2026-01-15 02:59:35 +00:00
eaace34233
fix: restore docker binds and PATH in sandbox exec ( #873 )
...
Thanks @akonyer.
Co-authored-by: Aaron Konyer <aaronk@gomodular.ca>
2026-01-15 02:58:20 +00:00
1b24b6a02b
fix: add plugin runtime registry
2026-01-15 02:44:45 +00:00
2b4a68e276
feat: load channel plugins
2026-01-15 02:42:44 +00:00
2fb2035dbf
fix: normalize Claude CLI auth mode to oauth ( #855 )
...
Thanks @sebslight.
Co-authored-by: Sebastian <sebslight@gmail.com>
2026-01-15 02:29:43 +00:00
765196d5c3
style(slack): satisfy oxfmt ( #850 )
2026-01-15 02:23:22 +00:00
09ce6ff99e
fix(slack): respect top-level requireMention config
...
The `channels.slack.requireMention` setting was defined in the schema
but never passed to `resolveSlackChannelConfig()`, which always
defaulted to `true`. This meant setting `requireMention: false` at the
top level had no effect—channels still required mentions.
Pass `slackCfg.requireMention` as `defaultRequireMention` to the
resolver and use it as the fallback instead of hardcoded `true`.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-15 02:17:27 +00:00
6ffd7111a6
fix: add TUI status spinner
2026-01-15 02:11:12 +00:00
7904a14af1
fix: render TUI pickers as overlays
2026-01-15 01:59:05 +00:00
1b79730db8
style: apply oxfmt fixes
2026-01-15 01:53:14 +00:00
ad8799522c
feat(config): gate channel config writes
2026-01-15 01:41:15 +00:00
f65668cb5f
fix: suppress raw API error payloads ( #924 ) (thanks @grp06)
...
Co-authored-by: George Pickett <gpickett00@gmail.com>
2026-01-15 01:34:19 +00:00
393d21d86c
Format: fix report + telegram formatting
2026-01-15 01:27:16 +00:00
232c512502
Format: apply oxfmt fixes
2026-01-15 01:27:16 +00:00
8c1e6a82b2
Tests: add Gemini thoughtSignature for tool-call ids
2026-01-15 01:27:16 +00:00
2d54efe851
Embedded runner: suppress raw API error payloads ( #919 )
2026-01-15 01:27:16 +00:00
c2a4f256c8
feat: add security audit + onboarding checkpoint
2026-01-15 01:25:11 +00:00
326d4049da
fix(telegram): migrate group config on supergroup IDs ( #906 )
...
Thanks @sleontenko.
Co-authored-by: Stan <sleontenko@users.noreply.github.com>
2026-01-15 01:10:30 +00:00
9b7c4b3884
feat(telegram): auto-migrate group config on supergroup migration
...
When a Telegram group is upgraded to a supergroup, the chat ID changes
(e.g., -123456 → -100123456). This causes the bot to lose its group
configuration since it's keyed by chat ID.
This change:
- Adds handler for `message:migrate_to_chat_id` event
- Logs the migration (old_id → new_id) for visibility
- If the old chat ID has config in channels.telegram.groups, automatically:
- Copies the config to the new chat ID
- Removes the old chat ID entry
- Saves the updated config file
This eliminates the need to manually update clawdbot.json when groups
migrate to supergroups.
2026-01-15 01:10:30 +00:00
bcde09ae91
feat: add /context prompt breakdown
2026-01-15 01:06:35 +00:00
e5c8abab9e
fix: preserve markdown code fences
2026-01-15 00:31:07 +00:00
9f1a8be2bf
refactor: unify markdown formatting pipeline
2026-01-15 00:31:07 +00:00
bd7d362d3b
refactor: unify markdown formatting pipeline
2026-01-15 00:31:07 +00:00
0d0b77ded6
fix(telegram): wire delete action for message tool ( #903 ) - thanks @sleontenko
...
Co-authored-by: Stan <sleontenko@users.noreply.github.com>
2026-01-15 00:29:53 +00:00
83a25d26fc
feat(telegram): add deleteMessage action
...
Add ability to delete messages in Telegram chats via the message tool.
Changes:
- Add deleteMessageTelegram function in send.ts
- Add deleteMessage action handler in telegram-actions.ts
- Add delete action support in telegram message plugin adapter
- Add deleteMessage to TelegramActionConfig type
- Update message tool description to mention delete action
Usage:
- Via message tool: action="delete", chatId, messageId
- Can be disabled via channels.telegram.actions.deleteMessage=false
Limitations (Telegram API):
- Bot can delete its own messages in any chat
- Bot can delete others' messages only if admin with "Delete Messages"
- Messages older than 48h in groups may fail to delete
2026-01-15 00:29:53 +00:00
9b7df414e6
test: add gemini 3 antigravity switch live repro
2026-01-15 00:29:53 +00:00
5894ffe82e
refactor(auth): streamline allowFrom normalization
2026-01-14 23:42:50 +00:00
57b4865ab3
fix(whatsapp): normalize user JIDs for group allowlists ( #838 )
...
Thanks @peschee.
Co-authored-by: Peter Siska <63866+peschee@users.noreply.github.com>
2026-01-14 23:25:42 +00:00
fd41000bc3
test(whatsapp): add context isolation coverage
...
Includes outbound gating, threading fallback, and web auto-reply context assertions.
2026-01-14 23:23:36 +00:00
a70937c926
refactor(discord): centralize autoThread reply plan ( #856 )
2026-01-14 23:07:05 +00:00
fe974f420d
chore: standardize Claude Code CLI naming ( #915 )
...
Follow-up to #915 .
2026-01-14 20:07:35 +00:00
e65e5f40c9
fix(whatsapp): use conversation id for context isolation ( #911 )
...
Thanks @tristanmanchester.
Co-authored-by: Tristan Manchester <tmanchester96@gmail.com>
2026-01-14 20:06:20 +00:00
0235eb6c72
refactor(discord): clean autoThread context wiring ( #856 )
...
Build reply/session context once (no post-hoc ctx mutation) and type into the actual delivery target.
Thanks @davidguttman.
Co-authored-by: David Guttman <david@davidguttman.com>
2026-01-14 20:04:25 +00:00
e943e63174
chore(auth): rename Claude CLI to Claude Code CLI ( #915 )
...
Thanks @SeanZoR.
Co-authored-by: Sean Katz <connect@sean8.com>
2026-01-14 19:57:42 +00:00
b4ba6e4eaf
Discord: isolate autoThread thread context ( #856 )
2026-01-14 12:25:35 -06:00
dadef27d7a
fix(slack): drop mismatched Socket Mode events ( #889 )
...
Filter Slack Socket Mode events by api_app_id/team_id.
Refs: #828
Contributor: @roshanasingh4
Co-authored-by: Roshan Singh <roshanasingh4@users.noreply.github.com>
2026-01-14 15:54:37 +00:00
53465a4d2d
fix: split long Telegram captions ( #907 ) - thanks @jalehman
...
Co-authored-by: Josh Lehman <josh@martian.engineering>
2026-01-14 15:52:54 +00:00
c379191f80
chore: migrate to oxlint and oxfmt
...
Co-authored-by: Christoph Nakazawa <christoph.pojer@gmail.com>
2026-01-14 15:02:19 +00:00
b7a11b7bd4
test(telegram): cover per-account timeoutSeconds ( #863 )
...
Co-authored-by: Snaver <194855+Snaver@users.noreply.github.com>
2026-01-14 10:35:42 +00:00
95bdb28a05
test(doctor): bump timeouts for slow cases
2026-01-14 10:35:39 +00:00
9930ba91c5
fix(telegram): honor timeoutSeconds (thanks @Snaver) ( #863 )
2026-01-14 10:10:05 +00:00
802c02eb74
style(lint): fix minimax usage lint
2026-01-14 10:10:04 +00:00
2d4e3253ca
fix(lint): tidy minimax usage fetch
2026-01-14 10:04:26 +00:00
18b4575e4d
feat(usage): add minimax usage snapshot
2026-01-14 09:57:32 +00:00
40fb59e5f7
refactor(live-tests): stabilize docker live suites
2026-01-14 09:52:39 +00:00
ce59e2dd76
refactor(telegram): split bot handlers
2026-01-14 09:11:32 +00:00
32cfc49002
refactor(tui): split handlers
2026-01-14 09:11:28 +00:00
d19bc1562b
refactor(gateway): split server runtime
2026-01-14 09:11:21 +00:00
ea018a68cc
refactor(auto-reply): split reply pipeline
2026-01-14 09:11:16 +00:00
1089444807
fix(gateway): reduce flaky ws rpc timeouts
2026-01-14 05:41:02 +00:00
4af8228c34
test(web): rename split suites
2026-01-14 05:40:58 +00:00
ebea98b8ec
test(slack): rename split suites
2026-01-14 05:40:55 +00:00
51683071e8
test(signal): rename split suites
2026-01-14 05:40:52 +00:00
bfa46b2471
test(providers): rename split suites
2026-01-14 05:40:49 +00:00
de62797128
test(imessage): rename split suites
2026-01-14 05:40:45 +00:00
05673fb6cf
test(cron): rename split suites
2026-01-14 05:40:42 +00:00
350f4709b7
test(auto-reply): rename split suites
2026-01-14 05:40:39 +00:00
b11eea07b0
refactor(wizard): split onboarding
2026-01-14 05:40:10 +00:00
35cea9be25
refactor(telegram): split bot helpers
2026-01-14 05:40:07 +00:00
3e0e608110
refactor(infra): split provider usage
2026-01-14 05:40:03 +00:00
e2f8909982
refactor(agents): split tools + PI subscribe
2026-01-14 05:39:59 +00:00
ac613b6632
refactor(discord): split send pipeline
2026-01-14 05:39:55 +00:00
5323652cfd
refactor(config): split legacy handling
2026-01-14 05:39:51 +00:00
a58ff1ac63
refactor(commands): split CLI commands
2026-01-14 05:39:47 +00:00
2b60ee96f2
refactor(browser): split pw tools + agent routes
2026-01-14 05:39:44 +00:00
da6f07b7c1
refactor(auto-reply): split directive handling
2026-01-14 05:39:41 +00:00
a44f1912b3
chore(repo): drop .DS_Store
2026-01-14 01:17:56 +00:00
bcbfb357be
refactor(src): split oversized modules
2026-01-14 01:17:56 +00:00
b1102cedd7
fix: support non-interactive token auth
2026-01-14 00:56:34 +00:00
4c932edabc
fix: make postinstall patcher idempotent
2026-01-13 23:12:27 +00:00
b071f73fef
fix: resume subagent registry safely ( #831 ) (thanks @roshanasingh4)
2026-01-13 10:10:15 +00:00
714de9d996
Persist subagent registry across restarts
2026-01-13 10:00:30 +00:00
aac3615d7a
test: fix cron delivery channel expectations
2026-01-13 09:07:13 +00:00
7de6e925aa
chore(lint): format entry shim
2026-01-13 08:43:54 +00:00
6fdfe8ea73
fix: finalize channels rename cleanup
2026-01-13 08:40:40 +00:00
84bfaad6e6
fix: finish channels rename sweep
2026-01-13 08:40:40 +00:00
fcac2464e6
refactor: remove redundant spread fallbacks
2026-01-13 08:40:39 +00:00
993c1de361
fix: stabilize channel migration
2026-01-13 08:40:39 +00:00
90342a4f3a
refactor!: rename chat providers to channels
2026-01-13 08:40:39 +00:00
0cd632ba84
Merge pull request #832 from danielz1z/fix/overloaded-error-handling
...
fix: handle Anthropic overloaded_error gracefully
2026-01-13 08:33:16 +00:00
e8779ac329
fix: handle Anthropic overloaded_error gracefully ( #832 ) (thanks @danielz1z)
2026-01-13 08:32:06 +00:00
32d844d3b6
fix: preserve execArgv on reexec
2026-01-13 08:31:50 +00:00
36725ce153
fix: handle Anthropic overloaded_error gracefully
...
When Anthropic's API returns an overloaded_error (temporary capacity issue),
the raw JSON error was being sent to users instead of a friendly message.
Changes:
- Add overloaded error pattern detection
- Return user-friendly message for overloaded errors
- Classify overloaded as failover-worthy (triggers retry logic)
2026-01-13 08:18:59 +00:00
f825dd2897
chore(lint): format live profiles test
2026-01-13 08:03:58 +00:00
9faa95d558
fix: recover from compaction overflow
2026-01-13 08:03:11 +00:00
3a90335b5a
chore(lint): satisfy biome checks
2026-01-13 07:53:38 +00:00
9007920695
fix(auth): drop invalid auth profiles from order
2026-01-13 07:53:38 +00:00
2887376646
test: stabilize gpt-5.2 tool-only live check
2026-01-13 07:51:24 +00:00
165841ae79
fix: suppress experimental sqlite warning at startup
2026-01-13 07:27:32 +00:00
dfbe4041f5
fix: skip Control UI asset check when UI is skipped
2026-01-13 07:27:32 +00:00
4fd1a6dec3
fix: harden doctor install checks
2026-01-13 07:25:25 +00:00
d5b17d344b
Merge pull request #722 from vrknetha/feat/slash-bash-command
...
feat(bash): add host-only /bash slash command
2026-01-13 07:18:35 +00:00
ba7d12f205
refactor: centralize onboarding auth paths
2026-01-13 07:12:20 +00:00
cb0f6cefa4
Deps: update Pi + Vitest and add Bedrock docs
2026-01-13 06:57:11 +00:00
6db0201fcd
Merge pull request #583 from mitschabaude-bot/feat/agent-model-fallbacks
...
Config: per-agent model fallbacks
2026-01-13 06:54:00 +00:00
3368284b2a
fix: per-agent model fallbacks ( #583 ) (thanks @mitschabaude-bot)
2026-01-13 06:50:41 +00:00
9c0c4f50ec
Agents: test per-agent model fallbacks override
2026-01-13 06:50:20 +00:00
6729637f61
Config: support per-agent model fallbacks
2026-01-13 06:50:20 +00:00
18d22aa426
fix: gate xhigh by model ( #444 ) (thanks @grp06)
2026-01-13 06:48:41 +00:00
a3641526ab
Thinking: gate xhigh by model
2026-01-13 06:48:26 +00:00
f50e06a1b6
test(tools): cover tool policy helpers
2026-01-13 06:32:59 +00:00
780a43711f
feat(tools): add tool profiles and group shorthands
2026-01-13 06:30:20 +00:00
d682b604de
fix(tools): harden tool schemas for strict providers
2026-01-13 06:30:20 +00:00
25a5f1cb96
Auto-reply: add host-only /bash + ! bash command
2026-01-13 11:54:34 +05:30
bb2df13be0
Merge pull request #700 from clawdbot/shadow/compaction
...
Agents: safeguard compaction summarization
2026-01-13 05:59:15 +00:00
5918def440
fix: honor gateway service override labels
2026-01-13 05:58:49 +00:00
1fdd3592d3
fix: tune compaction safeguard schema ( #700 ) (thanks @thewilloftheshadow)
2026-01-13 05:58:35 +00:00
a96d299971
Agents: safeguard compaction summarization
2026-01-13 05:55:30 +00:00
61b7398cb7
refactor: centralize auth-choice model defaults
2026-01-13 05:25:16 +00:00
0321d5ed74
Merge pull request #740 from jeffersonwarrior/main
...
feat: add Tailscale binary detection, custom gateway IP binding, and health probe auth fix
2026-01-13 05:22:48 +00:00
78627ce7c2
fix: tighten custom bind probing ( #740 ) (thanks @jeffersonwarrior)
2026-01-13 05:21:59 +00:00
c851bdd47a
feat: add Tailscale binary detection, IP binding modes, and health probe password fix
...
This PR includes three main improvements:
1. Tailscale Binary Detection with Fallback Strategies
- Added findTailscaleBinary() with multi-strategy detection:
* PATH lookup via 'which' command
* Known macOS app path (/Applications/Tailscale.app/Contents/MacOS/Tailscale)
* find /Applications for Tailscale.app
* locate database lookup
- Added getTailscaleBinary() with caching
- Updated all Tailscale operations to use detected binary
- Added TUI warning when Tailscale binary not found for serve/funnel modes
2. Custom Gateway IP Binding with Fallback
- New bind mode "custom" allowing user-specified IP with fallback to 0.0.0.0
- Removed "tailnet" mode (folded into "auto")
- All modes now support graceful fallback: custom (if fail → 0.0.0.0), loopback (127.0.0.1 → 0.0.0.0), auto (tailnet → 0.0.0.0), lan (0.0.0.0)
- Added customBindHost config option for custom bind mode
- Added canBindTo() helper to test IP availability before binding
- Updated configure and onboarding wizards with new bind mode options
3. Health Probe Password Auth Fix
- Gateway probe now tries both new and old passwords
- Fixes issue where password change fails health check if gateway hasn't restarted yet
- Uses nextConfig password first, falls back to baseConfig password if needed
Files changed:
- src/infra/tailscale.ts: Binary detection + caching
- src/gateway/net.ts: IP binding with fallback logic
- src/config/types.ts: BridgeBindMode type + customBindHost field
- src/commands/configure.ts: Health probe dual-password try + Tailscale detection warning + bind mode UI
- src/wizard/onboarding.ts: Tailscale detection warning + bind mode UI
- src/gateway/server.ts: Use new resolveGatewayBindHost
- src/gateway/call.ts: Updated preferTailnet logic (removed "tailnet" mode)
- src/commands/onboard-types.ts: Updated GatewayBind type
- src/commands/onboard-helpers.ts: resolveControlUiLinks updated
- src/cli/*.ts: Updated bind mode casts
- src/gateway/call.test.ts: Removed "tailnet" mode test
2026-01-13 05:20:02 +00:00
01776e0569
refactor: dedupe OAuth flow handlers
2026-01-13 05:14:05 +00:00
8eb1c76337
fix: clean up api key validation
2026-01-13 05:12:42 +00:00
f94ad21f1e
style: format cron cli flags
2026-01-13 05:05:39 +00:00
8d640ccc68
Merge pull request #726 from FrieSei/feature/chutes-oauth
...
Auth: add Chutes OAuth
2026-01-13 05:02:25 +00:00
f566e6451f
fix: harden Chutes OAuth flow ( #726 ) (thanks @FrieSei)
2026-01-13 05:01:08 +00:00
75a7855223
feat: cron ISO at + delete-after-run
2026-01-13 04:55:48 +00:00
3271ff1d6e
Tests: clean chutes fetch spies
2026-01-13 04:50:27 +00:00
0efcfc0864
Chores: fix chutes oauth build
2026-01-13 04:50:27 +00:00
0aba911912
Chores: format chutes oauth
2026-01-13 04:50:26 +00:00
4efb5cc18e
Auth: add Chutes OAuth
2026-01-13 04:50:26 +00:00
57db3f22a1
fix: clean lint in auth-choice + tests
2026-01-13 04:49:04 +00:00
7c7f4d0eb7
chore(discord): restore gateway log context
2026-01-13 04:40:22 +00:00
ccc24e2c26
chore(logging): strip redundant provider tags
2026-01-13 04:40:22 +00:00
62bdbe1821
chore(logging): strip redundant console prefixes
2026-01-13 04:40:22 +00:00
58d1d11762
chore(discord): trim gateway log prefixes
2026-01-13 04:40:22 +00:00
7616b02bb1
Fix tailscale allowTailscale bypass in token mode
2026-01-13 04:34:28 +00:00
d4c205f8e1
fix: start typing on message start
2026-01-13 04:33:24 +00:00
0ba60ff69c
Merge pull request #794 from roshanasingh4/fix/777-windows-openurl-quotes
...
Fix Antigravity OAuth login on Windows (quote URL for cmd start)
2026-01-13 04:28:11 +00:00
755a7e1b20
feat: add configurable bootstrap truncation
2026-01-13 04:27:03 +00:00
3061d8e057
fix: preserve Windows cmd start URL quoting ( #794 ) (thanks @roshanasingh4)
2026-01-13 04:26:43 +00:00
ea5597b483
fix: restore implicit providers + copilot auth choice
2026-01-13 04:26:08 +00:00
b41e75a15d
feat: cron agent binding + doctor UI refresh
2026-01-13 04:25:41 +00:00
bfdbaa5ab6
feat(doctor): add UI protocol freshness check
2026-01-13 04:25:41 +00:00
93ae3b8405
fix: sync protocol artifacts and resolve linting errors
2026-01-13 04:25:41 +00:00
f249a82383
fix: resolve CI failures (test timeout & formatting)
2026-01-13 04:25:41 +00:00
ea9486ae2d
Fix: quote URLs when opening browser on Windows
2026-01-13 04:23:20 +00:00
da95b58a2a
Typing: keep indicators active during tool runs
...
Closes #450
Closes #447
2026-01-12 22:20:29 -06:00
e15d5d0533
Cron: persist enabled=false patches
...
Closes #205
2026-01-12 22:16:17 -06:00
1cf45f8439
Merge pull request #805 from marcmarg/fix/strip-thought-signatures
...
fix: strip thought_signature fields for cross-provider compatibility
2026-01-13 04:14:45 +00:00
2a9ef806a0
fix: strip only msg_* thought_signature ( #805 ) (thanks @marcmarg)
2026-01-13 04:13:24 +00:00
32115a8b98
test: expand auth fallback coverage
2026-01-13 04:12:16 +00:00
c4e8b60d2c
fix: strip thought_signature fields for cross-provider compatibility
...
Claude's extended thinking feature generates thought_signature fields
(message IDs like "msg_abc123...") in content blocks. When these are
sent to Google's Gemini API, it expects Base64-encoded bytes and
rejects Claude's format with a 400 error.
This commit adds stripThoughtSignatures() to remove these fields from
assistant message content blocks during sanitization, enabling session
histories to be shared across different providers (e.g., Claude → Gemini).
Fixes cross-provider session bug where switching from Claude-thinking
to Gemini (or vice versa) would fail with:
"Invalid value at 'thought_signature' (TYPE_BYTES), Base64 decoding failed"
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-13 04:11:02 +00:00
c9fdd68232
Telegram: keep forum topic thread ids in replies
...
Closes #727
2026-01-12 22:07:28 -06:00
2c2ca7f03b
fix: treat credential validation errors as auth errors ( #822 ) (thanks @sebslight)
2026-01-13 04:02:47 +00:00
c4014c0092
fix: treat credential validation failures as auth errors for fallback ( #761 )
2026-01-12 22:53:21 -05:00
c08441c42c
Telegram: persist polling update offsets
...
Closes #739
2026-01-12 21:52:20 -06:00
980f274fc9
fix: stabilize docs and tests after system event timestamps
2026-01-13 03:51:34 +00:00
9f1f65f0e3
Discord: dedupe listener registration on reload
...
Closes #744
2026-01-12 21:41:59 -06:00
cddd836909
Merge pull request #821 from gumadeiras/fix-bindings-telegram-webhook
...
Telegram: fix webhook multi-account routing (respect bindings.accountId)
2026-01-13 03:41:17 +00:00
d45915d39f
fix: refine group intro prompt guidance
2026-01-13 03:40:27 +00:00
fcc814accd
System events: add local timestamps in prompt injection
...
Closes #245
2026-01-12 21:38:56 -06:00
66ad8a9289
fix: apply lint fixes
2026-01-13 03:36:53 +00:00
df6634727e
fix: refine synthetic provider + minimax probes
2026-01-13 03:36:53 +00:00
8b5cd97ceb
Add Synthetic provider support
2026-01-13 03:36:53 +00:00
25297ce3f5
Cron: accept jobId in gateway cron params
...
Closes #252
2026-01-12 21:35:43 -06:00
3800fea962
Improve webhook test config verification
...
Refactors tests to use a shared config object and adds stricter assertions to verify that the config is passed correctly to createTelegramBot. Ensures the bindings property is checked in the test expectations.
2026-01-13 03:34:32 +00:00
ecb91bbb1a
Add accountId and config support to Telegram webhook
...
The Telegram webhook and monitor now accept and pass through accountId and config parameters, enabling routing and configuration per Telegram account. Tests have been updated to verify correct bot instantiation and DM routing based on accountId bindings.
2026-01-13 03:34:32 +00:00
ab993904d7
Models: normalize Gemini 3 ids in runtime selection
...
Closes #795
2026-01-12 21:32:53 -06:00
2467a103b2
TUI: keep streamed text when final output is empty
...
Closes #747
2026-01-12 21:29:15 -06:00
68569afb4b
Slack: accept slash command names with or without leading slash
...
Closes #798
2026-01-12 21:27:04 -06:00
da0a062fa7
fix: memory search remote overrides ( #819 ) (thanks @mukhtharcm)
2026-01-13 03:11:03 +00:00
ba316a10cc
feat: add remote config overrides to memorySearch
2026-01-13 03:02:43 +00:00
c1f82d9ec1
refactor: dedupe enforceFinalTag resolution
2026-01-13 02:38:07 +00:00
46a694bbc7
fix: preserve explicit maxChars=0 ( #796 ) (thanks @gabriel-trigo)
2026-01-13 02:33:38 +00:00
79a6506593
fix(browser): limit ai snapshot size
...
test(browser): cover ai snapshot limit
2026-01-13 02:33:38 +00:00
8edf2146ae
fix: cleanup stale resume cli processes
2026-01-13 02:21:20 +00:00
958a4fd414
Merge pull request #782 from AbhisekBasu1/fix/antigravity-opus-tools-not-working
...
Fix - Opus on Antigravity Errors
2026-01-13 01:59:52 +00:00
a27efd57bd
fix: drop null-only union variants ( #782 ) (thanks @AbhisekBasu1)
...
Co-authored-by: Abhi <AbhisekBasu1@users.noreply.github.com>
2026-01-13 01:58:30 +00:00
4f1c6e76fd
fix: gate inline /status stripping
2026-01-13 01:53:40 +00:00
2111d0c653
test: force real config module for lan onboarding test ( #766 )
2026-01-13 01:53:40 +00:00
642e6acf49
test: unmock config for lan onboarding auto-token ( #766 )
2026-01-13 01:53:40 +00:00
88716d8d2a
fix: harden inline /status stripping ( #766 )
2026-01-13 01:53:40 +00:00
c2e37c78ff
fix: trim sender ids before auth fallback
2026-01-13 01:53:40 +00:00
ba1d80bd00
formatting fix
2026-01-13 01:48:56 +00:00
4dfcd56893
Fix pi-tools test ordering and clean-for-gemini handling - which fixes the 400 error people are experiencing trying to use antigravity on opus
2026-01-13 01:48:34 +00:00
c012019a8a
fix: enforce reasoning tags on fallback providers ( #810 ) (thanks @mcinteerj)
2026-01-13 01:46:21 +00:00
7896b30489
fix(auto-reply): enforce reasoning tags on fallback providers
2026-01-13 01:40:55 +00:00
ffc465394e
fix: enforce message context isolation
2026-01-13 01:19:14 +00:00
0edbdb1948
fix: downgrade Gemini tool history
2026-01-13 01:19:13 +00:00
5dc187f00c
fix: accept Claude/Gemini tool param aliases
2026-01-13 01:19:13 +00:00
231d2d5fdf
fix(config): require doctor for invalid configs ( #764 — thanks @mukhtharcm)
2026-01-13 01:18:18 +00:00
20ba8d4891
fix(config): preserve config data when validation fails
...
When readConfigFileSnapshot encounters validation errors, it now:
1. Returns the resolved config data instead of empty object
2. Uses passthrough() on main schema to preserve unknown fields
This prevents config loss when:
- User has custom/unknown fields
- Legacy config issues are detected but config is otherwise valid
- Zod schema does not recognize newer fields
Fixes config being overwritten with empty object on validation failure.
2026-01-13 01:16:13 +00:00
dd8f7552ad
refactor: reuse dispatcher helper for native commands
2026-01-13 01:07:59 +00:00
07bdb8af7e
fix: pass --non-interactive to doctor during update
2026-01-13 00:57:18 +00:00
6a48688c09
fix: stream native slash tool replies
2026-01-13 00:53:30 +00:00
c03a745f61
test: expand Minimax XML strip coverage
2026-01-13 00:43:59 +00:00
48fdf3775d
test: cover user turn merging
2026-01-13 00:42:15 +00:00
e2ea20f862
fix: gate minimax XML stripping ( #809 ) (thanks @latitudeki5223)
2026-01-13 00:36:39 +00:00
1eb924739b
style: fix import order in pi-embedded-utils.test.ts
2026-01-13 00:34:01 +00:00
350f956f2c
fix(minimax): strip tool invocation XML from assistant text
2026-01-13 00:34:01 +00:00
4f3bedfdb7
fix: align discord autoThread config types
2026-01-13 00:22:42 +00:00
6f75feaeb8
refactor: reuse model selection assertions
2026-01-13 00:20:08 +00:00
a4bd960880
refactor: streamline thread reply planning
2026-01-13 00:15:29 +00:00
3636a2bf51
refactor: unify message tool + CLI
2026-01-13 00:12:57 +00:00
ce23c70855
fix: validate Anthropic turn order ( #804 ) (thanks @ThomsenDrake)
2026-01-12 23:43:25 +00:00
c5fa757ef6
fix(agents): prevent Anthropic 400 'Incorrect role information' error
...
Add validateAnthropicTurns() to merge consecutive user messages that can
occur when steering messages are injected during streaming. This prevents
the API from rejecting requests due to improper role alternation.
Changes:
- Add validateAnthropicTurns() function in pi-embedded-helpers.ts
- Integrate validation into sanitization pipeline in pi-embedded-runner.ts
- Add user-friendly error message for role ordering errors
- Add comprehensive tests for the new validation function
2026-01-12 23:42:13 +00:00
bb9a9633a8
fix: align reply threading refs
2026-01-12 23:41:40 +00:00
ca98f87b2f
chore: reinforce memory recall prompts
2026-01-12 23:29:56 +00:00
df64771ecf
test: cover fuzzy model selection
2026-01-12 23:16:54 +00:00
cbe11e3de0
fix: address lint warnings
2026-01-12 23:13:40 +00:00
daa753112c
fix: unblock auto-reply lint/typecheck
2026-01-12 23:13:39 +00:00
2e654e8d63
Fix Discord autoThread thread-only replies ( #807 )
...
Co-authored-by: Shadow <shadow@clawd.bot>
2026-01-12 17:11:48 -06:00
cf92099d40
test(auto-reply): fix heartbeat typing block reply assertions
2026-01-12 23:01:53 +00:00
a8680f9a09
fix(auto-reply): fix streaming block reply media handling
2026-01-12 22:59:36 +00:00
2e08a868a7
style: format native commands bits
2026-01-12 22:59:36 +00:00
2785009c6f
fix(config): resolve native commands schemas
2026-01-12 22:59:36 +00:00
73d9469bf8
fix(telegram): tolerate missing native command APIs
2026-01-12 22:59:36 +00:00
72100ba3ab
refactor(sandbox): drop legacy memory shorthand
2026-01-12 22:59:36 +00:00
ec5099db89
fix: pick best fuzzy model match
2026-01-12 22:59:35 +00:00
209380edf8
Merge pull request #801 from mcinteerj/fix/restore-reasoning-tag-check
...
fix(agent): restore reasoning tag enforcement for non-ollama providers
2026-01-12 22:59:13 +00:00
cf8251bb81
test: cover typing signals from block and tool streams
2026-01-12 22:55:17 +00:00
fd768334a9
refactor: fast-lane directives helpers
2026-01-12 22:34:13 +00:00
27d940f5b6
refactor: reuse streaming text normalizer across callbacks
2026-01-12 22:27:56 +00:00
7ba72aeb6c
fix: make pw download tests platform-safe
2026-01-12 22:27:19 +00:00
9d5bf38416
style(telegram): format bot.ts
2026-01-12 22:19:02 +00:00
e0c1f2fdc0
test(agents): avoid Copilot token fetch in image-tool tests
2026-01-12 22:19:02 +00:00
08fdac0561
fix(telegram): guard setMyCommands in native commands
2026-01-12 22:19:02 +00:00
d3eeddfc2f
chore: fix lint after rebase
2026-01-12 22:19:02 +00:00
9da97d1a41
test(browser): expand scrollintoview coverage
2026-01-12 22:19:02 +00:00
29b7b2068a
refactor: centralize streaming text normalization
2026-01-12 22:17:14 +00:00
f4ab057807
fix: start typing on partial deltas
2026-01-12 22:16:29 +00:00
f13db1c836
test: guard telegram native commands when mock lacks .command
2026-01-12 22:12:16 +00:00
59063a7c15
test: skip setMyCommands when API mock lacks it
2026-01-12 22:08:53 +00:00
5bc4971432
chore: fix lint warnings
2026-01-12 22:07:39 +00:00
59c8d2d17f
docs: clarify sandbox bind mounts ( #790 )
2026-01-12 22:06:35 +00:00
21405b0dfc
fix(discord): rebalance reasoning italics
2026-01-12 22:01:48 +00:00
256304037e
fix: keep Claude file_path aliases validated
2026-01-12 22:00:08 +00:00
bbc34215a2
fix: land sandbox binds ( #790 ) (thanks @akonyer)
2026-01-12 21:58:16 +00:00
583fc4fb11
test(sandbox): add coverage for binds -v flag emission
2026-01-12 21:57:51 +00:00
0b2b8c7c52
Add docker bind mounds for sandboxing
2026-01-12 21:57:51 +00:00
5d83be76c9
test: cover mixed directive fast-lane
2026-01-12 21:57:10 +00:00
fcaeee7073
test(browser): cover scrollintoview
2026-01-12 21:56:27 +00:00
6857f16609
feat(browser): add scrollintoview action
2026-01-12 21:56:27 +00:00
2faf7cea93
feat(sandbox): add tool-policy groups
2026-01-12 21:51:49 +00:00
26d5cca97c
feat: auto native commands defaults
2026-01-12 21:49:44 +00:00
99fea64823
fix: fast-lane directives bypass queue dedupe
2026-01-12 21:44:19 +00:00
42c17adb5e
feat: restore voice-call plugin parity
2026-01-12 21:44:19 +00:00
3467b0ba07
Discord: add allowBots config option ( #802 )
...
Co-authored-by: Shadow <shadow@clawd.bot>
2026-01-12 15:30:05 -06:00
490cb834e5
style: italicize reasoning output
2026-01-12 21:24:36 +00:00
cd12ad8aab
fix(image): accept @-prefixed file paths
2026-01-12 20:53:16 +00:00
eceb41f6f7
fix(agent): restore reasoning tag enforcement for non-ollama providers
...
This restores the fix from PR #754 which was accidentally reverted in bf11a42c3
2026-01-13 09:47:04 +13:00
e961e02f71
fix(gateway): quiet loopback ws closes
2026-01-12 20:38:34 +00:00
36a02b3e67
fix(image): route MiniMax vision to VLM
2026-01-12 20:38:34 +00:00
b73042500e
Discord: per-channel autoThread ( #800 )
...
Co-authored-by: Shadow <shadow@clawd.bot>
2026-01-12 14:33:07 -06:00
f839d949b2
test(browser): cover downloads + responsebody
2026-01-12 19:41:12 +00:00
d4f7dc067e
feat(browser): add downloads + response bodies
2026-01-12 19:41:12 +00:00
ddd4b55cf6
fix: prevent onboarding TUI auto-delivery ( #791 ) (thanks @roshanasingh4)
2026-01-12 19:38:52 +00:00
298c6eea1f
Fix: prevent onboarding TUI auto-delivery
2026-01-12 19:31:04 +00:00
55aeb8a0d3
fix(image): drop temperature for OpenAI
2026-01-12 19:09:15 +00:00
86ea00dc21
fix(tools): accept legacy bash tool calls
2026-01-12 19:09:15 +00:00
a0a7e74a62
fix(models): preserve implicit vision models
2026-01-12 19:09:15 +00:00
bb7397c636
feat: add dashboard command
2026-01-12 19:08:29 +00:00
7dc44b04c1
fix: close memory index and refresh protocol outputs
2026-01-12 18:49:24 +00:00
45232137a2
fix(logging): honor silent console level
2026-01-12 18:46:40 +00:00
b1c3e38df0
refactor(models): share implicit providers
2026-01-12 18:46:40 +00:00
0be62c3542
fix(image): fail over on empty output
2026-01-12 18:46:16 +00:00
523f91758d
test(browser): extend automation coverage
2026-01-12 18:42:46 +00:00
ffbcd83d1e
chore: log elevated and reasoning toggles
2026-01-12 18:37:44 +00:00
1baf9f6a83
fix(image): normalize mime type handling
2026-01-12 18:24:11 +00:00
77b20377cc
fix: stabilize session tools and tests
2026-01-12 18:21:20 +00:00
3ffb9a3b5e
fix: keep session sanitizer stable
2026-01-12 18:19:30 +00:00
29807119d5
chore: format tool guard files
2026-01-12 18:19:30 +00:00
b88ea39b83
fix: add subagent default model typing
2026-01-12 18:18:15 +00:00
0a2dcd844b
fix(image): support data URLs
2026-01-12 18:17:43 +00:00
2ed95634fe
fix: relax image tool agentDir guard
2026-01-12 18:12:51 +00:00
7b93356fb7
feat: subagent model defaults
2026-01-12 18:08:30 +00:00
17ff25bd20
fix(sandbox): always allow image tool
2026-01-12 18:07:34 +00:00
d24de1ec3b
feat(sandbox): allow image tool
2026-01-12 17:56:51 +00:00
44e1f271c8
fix: keep image sanitizer scoped
2026-01-12 17:55:45 +00:00
8ff09f8337
feat(image): auto-pair image model
2026-01-12 17:50:47 +00:00
e91aa0657e
fix: add copilot tests and lint fixes
2026-01-12 17:48:08 +00:00
14801b46fc
Merge pull request #792 from clawdbot/fix/gateway-auth-off
...
fix: clear gateway auth when set to off
2026-01-12 23:10:15 +05:30
35bbc2ba87
feat(cli): expand browser commands
2026-01-12 17:32:44 +00:00
cf78d28d74
test(browser): add regression coverage
2026-01-12 17:32:44 +00:00
eeca541dde
feat(browser): expand browser control surface
2026-01-12 17:32:44 +00:00
4bba49770d
fix: clear gateway auth on off selection
2026-01-12 22:59:37 +05:30
f5d5661adf
fix: guard session tool results
2026-01-12 17:28:46 +00:00
f83fb70360
fix: keep main agent in list output
2026-01-12 17:24:03 +00:00
355c13564c
fix: restore heartbeat defaults and model listing
2026-01-12 17:17:54 +00:00
f1dd59bf82
test: update heartbeat and agent list thresholds
2026-01-12 17:14:04 +00:00
fd1e959c2d
fix: clean up models-config provider normalization
2026-01-12 17:14:04 +00:00
05ac67c520
refactor: split models-config provider helpers
2026-01-12 17:05:53 +00:00
f5ee2b3a4f
Merge pull request #705 from TAGOOZ/feat/github-copilot-onboard
...
feat: add GitHub Copilot provider
2026-01-12 16:56:51 +00:00
8afdf75e2b
fix: honor copilot config and profiles ( #705 ) (thanks @TAGOOZ)
2026-01-12 16:55:47 +00:00
5a3eb5ad62
test: cover models.json apiKey fill
2026-01-12 16:52:43 +00:00
79beb20ba2
fix: make models.json generation fill apiKey
2026-01-12 16:52:43 +00:00
3da1afed68
feat: add GitHub Copilot provider
...
Copilot device login + onboarding option; model list auth detection.
2026-01-12 16:52:15 +00:00
adaa30c73a
test(telegram): cover General topic typing fallback
2026-01-12 22:03:42 +05:30
ff292e67ce
fix(telegram): show typing indicator in General forum topic
...
In forum supergroups, messages from the General topic arrive without
message_thread_id in updates, but sendChatAction requires one to display
the typing indicator in the correct topic.
Use message_thread_id=1 (Telegram's internal ID for General topic) as
fallback when messageThreadId is undefined in a forum chat.
2026-01-12 22:01:21 +05:30
bf11a42c37
feat: add memory vector search
2026-01-12 11:23:44 +00:00
8049f33435
chore: sanitize onboarding api keys
2026-01-12 11:18:31 +00:00
115591c5b6
feat: add cron agent binding
2026-01-12 11:07:38 +00:00
a3938d62f6
chore: raise heartbeat ack window
2026-01-12 11:06:46 +00:00
3c7a8579ad
test: cover minimax env provider injection
2026-01-12 11:05:08 +00:00
f5a9421b10
fix: auto-add minimax provider from auth
2026-01-12 11:05:08 +00:00
562d0e3b5f
fix: avoid duplicate status replies
2026-01-12 11:04:03 +00:00
bf7e813573
chore: release 2026.1.11-4
2026-01-12 10:52:34 +00:00
5a29ec78ca
chore: release 2026.1.11-3
2026-01-12 10:35:50 +00:00
8fb655198f
test: skip lan auto-token on windows
2026-01-12 09:20:37 +00:00
a4308a2428
chore: tidy changelog and format
2026-01-12 09:14:44 +00:00
f102d1bb9d
fix: add ws handshake user agent
2026-01-12 09:08:07 +00:00
d8feadb57a
fix: strip gemini cli tool ids ( #756 )
2026-01-12 09:01:19 +00:00
1050126132
fix: default groupPolicy to open for discord/telegram
2026-01-12 08:55:02 +00:00
9554292083
fix: default groupPolicy to open
2026-01-12 08:55:02 +00:00
a8f67f0be6
fix: only strip inline /status for allowlisted senders
2026-01-12 08:55:02 +00:00
fadad6e061
feat: role snapshot refs for browser
2026-01-12 08:55:02 +00:00
6711eaf8a5
fix: finalize tool param aliasing ( #768 ) (thanks @hsrvc)
2026-01-12 08:49:11 +00:00
71fdc829e6
Agents: add Claude Code parameter aliasing for read/write/edit tools
2026-01-12 08:49:11 +00:00
19c96e8c0b
Merge pull request #754 from mcinteerj/fix/reasoning-tag-strip
...
fix(agent): prevent reasoning and tag leaks for Gemini 3/Antigravity models
2026-01-12 08:47:15 +00:00
98e75fce17
test: align group policy defaults
2026-01-12 08:45:57 +00:00
252841ab13
fix: enforce final tag gating ( #754 ) (thanks @mcinteerj)
2026-01-12 08:45:23 +00:00
a7cb270999
fix(agent): buffer streaming output until <final> tag appears
...
- Enforces strict buffering when enforceFinalTag is enabled.
- Prevents 'thinking out loud' planning steps (e.g. '*Locating Manulife*') from leaking to WhatsApp.
- Hardens <final> tag stripping to remove nested/hallucinated tags.
2026-01-12 08:34:06 +00:00
efdf874407
fix(agent): correctly strip <final> tags from reasoning providers
...
- Added src/utils/provider-utils.ts to track reasoning provider logic
- Updated isReasoningTagProvider to loosely match 'google-antigravity' (fixes sub-models)
- Enabled enforceFinalTag in reply.ts when provider matches
- Verified <final> tag stripping logic in pi-embedded-subscribe.ts
- Updated pi-embedded-runner to use consistent provider check for prompt hints
2026-01-12 08:34:06 +00:00
7db1cbe178
fix: improve daemon node selection
2026-01-12 08:33:32 +00:00
006e1352d8
fix: harden msteams group access
2026-01-12 08:32:08 +00:00
4d075a703e
fix: add ws handshake context
2026-01-12 08:30:08 +00:00
842e91d019
fix: default groupPolicy to allowlist
2026-01-12 08:22:01 +00:00
d0ba56c5ac
fix: set default model after auth choice
2026-01-12 08:04:32 +00:00
b8f8e7f4dd
fix: correct MiniMax Lightning hint
2026-01-12 08:04:32 +00:00
3fba8ceb97
test(model): cover provider-less id fuzzy match
2026-01-12 08:02:55 +00:00
60823fd9bd
feat(model): fuzzy /model matching
2026-01-12 07:57:53 +00:00
e79cf5a8b1
feat: improve onboarding auth prompts
2026-01-12 07:47:15 +00:00
018f7aa4df
fix: streamline configure section flow
2026-01-12 07:47:15 +00:00
e1150f1b93
test: expand memory flush coverage
2026-01-12 07:42:03 +00:00
d17fc7e448
fix(auto-reply): preserve inline /status text for unauthorized senders
2026-01-12 07:42:03 +00:00
484a33f348
fix: cap ai snapshots for tool calls ( #763 ) (thanks @thesash)
2026-01-12 07:40:34 +00:00
d5d8c01dc7
Browser: cap AI snapshots to avoid context overflow
2026-01-12 07:40:34 +00:00
097e66391f
fix(auto-reply): show config models in /model
2026-01-12 07:31:20 +00:00
7466575120
fix: ignore inline status directives
2026-01-12 07:13:08 +00:00
e19a5dc2b1
feat(control-ui): add model presets
2026-01-12 07:09:58 +00:00
f00667ea25
fix: clean up lint + guardCancel typing
2026-01-12 07:07:27 +00:00
1850013cae
fix: modernize live tests and gemini ids
2026-01-12 07:05:33 +00:00
496bad8b98
feat: add Moonshot auth choice
2026-01-12 06:48:06 +00:00
1a89a5dd14
test(model): expand /model picker coverage
2026-01-12 06:34:33 +00:00
5b44825cb3
fix: skip memory flush on read-only workspace
2026-01-12 06:33:27 +00:00
1ffb0fe787
fix: handle inline status for allowlisted senders
2026-01-12 06:33:27 +00:00
46a6d79784
fix: sender fallback for command auth ( #755 ) (thanks @juanpablodlc)
2026-01-12 06:28:53 +00:00
20d606c4c4
fix: use logical OR for sender ID fallback in command auth
...
The nullish coalescing operator (??) only skips null/undefined, not
empty strings. For direct WhatsApp messages, ctx.SenderId was an empty
string, causing senderRaw to be "" instead of falling through to the
valid ctx.SenderE164 value.
This caused commands like /status to be rejected with "unauthorized
sender" for self-chat WhatsApp messages.
Tested: Verified /status command now works correctly for self-chat
WhatsApp messages after the fix.
2026-01-12 06:20:51 +00:00
e388334127
test: cover pi session jsonl ordering
2026-01-12 06:19:58 +00:00
c9f2358769
test: clean unused var
2026-01-12 06:14:45 +00:00
4044957819
test: fix lint warning
2026-01-12 06:14:45 +00:00
b185d130ba
test: cover inline slash command fast-path
2026-01-12 06:14:45 +00:00
2bed0d78af
test: stabilize lan auto-token onboarding
2026-01-12 06:13:31 +00:00
0baf08fda1
fix: dedupe minimax non-interactive auth
2026-01-12 06:13:31 +00:00
d0861670bd
feat: simplify minimax auth choice
2026-01-12 06:13:00 +00:00
744fadbded
feat: loop configure section picker
2026-01-12 06:13:00 +00:00
0f257f792a
fix: fast-path slash commands
2026-01-12 06:10:17 +00:00
2da2057a37
feat(model): add /model picker
2026-01-12 06:02:39 +00:00
7dbb21be8e
feat: add pre-compaction memory flush
2026-01-12 05:29:18 +00:00
cc8a2457c0
fix: persist first Pi user message in JSONL
2026-01-12 05:18:05 +00:00
f5c851e11e
fix(models): default MiniMax to /anthropic
2026-01-12 05:12:07 +00:00
873cee6947
feat: streamline wizard selection prompts
2026-01-12 05:08:07 +00:00
51d5f16770
refactor: remove mac attach-only setting
2026-01-12 04:58:38 +00:00
8e1cdf3a1f
fix: require gateway client id
...
# Conflicts:
# apps/macos/Sources/Clawdbot/GatewayChannel.swift
# docs/concepts/typebox.md
# docs/gateway/index.md
# src/commands/onboard-non-interactive.gateway-auth.test.ts
# src/commands/onboard-non-interactive.lan-auto-token.test.ts
# src/gateway/call.ts
# src/gateway/client.ts
# src/gateway/gateway.wizard.e2e.test.ts
# src/gateway/probe.ts
# src/gateway/protocol/schema.ts
# src/gateway/server.auth.test.ts
# src/gateway/server.health.test.ts
# src/gateway/server.ts
# src/gateway/test-helpers.ts
# src/tui/gateway-chat.ts
2026-01-12 04:58:38 +00:00
87f270df23
test: respect openai max tokens floor
2026-01-12 04:04:04 +00:00
8b4bdaa8a4
feat: add apply_patch tool (exec-gated)
2026-01-12 03:42:56 +00:00
6a012fd625
refactor: reuse resolved think default
2026-01-12 03:00:30 +00:00
1fa7a587d6
fix: flush block reply buffers on tool boundaries ( #750 ) (thanks @sebslight)
2026-01-12 02:54:57 +00:00
c64bcd047b
fix: flush block reply coalescer on tool boundaries
...
When block streaming is enabled with verbose=off, tool blocks are hidden
but their boundary information was lost. Text segments before and after
tool execution would get coalesced into a single message because the
coalescer had no signal that a tool had executed between them.
This adds an onBlockReplyFlush callback that fires on tool_execution_start,
allowing the block reply pipeline to flush pending text before the tool
runs. This preserves natural message boundaries even when tools are hidden.
Fixes the issue where:
text → [hidden tool] → text → rendered as one merged message
Now correctly renders as:
text → [hidden tool] → text → two separate messages
Co-diagnosed-by: Krill (Discord assistant)
2026-01-12 02:52:48 +00:00
d4d15c8a71
Merge pull request #751 from gabriel-trigo/fix/think-default-743
...
fix: align /think default with model reasoning
2026-01-12 02:52:25 +00:00
17e6354383
Merge pull request #748 from myfunc/main
...
fix(bash): use PowerShell on Windows to capture system utility output
2026-01-12 02:50:30 +00:00
99877e8e63
fix: align /think default with model reasoning
2026-01-12 02:50:13 +00:00
98337a14b3
fix: rename bash tool to exec ( #748 ) (thanks @myfunc)
2026-01-12 02:49:55 +00:00
76c8fc8697
fix(sandbox): canonicalize agent main alias
2026-01-12 02:23:02 +00:00
b33bd6aaeb
fix(bash): use PowerShell on Windows to capture system utility output
...
Windows system utilities like ipconfig, systeminfo, etc. write directly to
the console via WriteConsole API instead of stdout. When Node.js spawns
cmd.exe with piped stdio, these utilities produce empty output.
Changes:
- Switch from cmd.exe to PowerShell on Windows (properly redirects output)
- Disable detached mode on Windows (PowerShell doesn't pipe stdout when detached)
- Add windowsHide option to prevent console window flashing
- Update tests to use PowerShell-compatible syntax (Start-Sleep, semicolons)
2026-01-12 02:13:02 +00:00
4ced7b886e
docs: fix browser CLI docs link
2026-01-12 02:09:10 +00:00
2941a7002d
fix(subagents): align wait timeout with run timeout
2026-01-12 02:06:43 +00:00
b518fb29c6
test(gateway): cover main alias resolve
2026-01-12 02:06:43 +00:00
f504bfdde8
refactor(gateway): use canonical session store keys
2026-01-12 02:06:43 +00:00
c1236e86fa
test: fix windows nix config path assertion
2026-01-12 02:05:38 +00:00
e3960cde3f
test: add normalizeConfigPaths unit test
2026-01-12 01:55:55 +00:00
ecc6243edc
test: cover tilde path expansion
2026-01-12 01:53:42 +00:00
328d47f1df
fix: normalize ~ in path config
2026-01-12 01:53:42 +00:00
28f97e6152
refactor(sandbox): normalize main session aliases
2026-01-12 01:37:56 +00:00
23a0bf2abe
fix(plugins): extract archives without system tar
2026-01-12 01:36:18 +00:00
07b93e1d26
test: run npm pack via npm-cli.js
2026-01-12 01:31:26 +00:00
5bdb9c0e99
style: format plugin install test
2026-01-12 01:27:01 +00:00
6947ab18dc
fix: load plugin packages from config dirs
2026-01-12 01:25:56 +00:00
177ad3f06d
test: pack plugin archives via npm
2026-01-12 01:25:40 +00:00
58a12a757e
fix(sandbox): avoid sandboxing main DM sessions
2026-01-12 01:24:44 +00:00
f13ae50ff8
test: plugin install + docker e2e
2026-01-12 01:16:42 +00:00
2f4a248314
feat: plugin system + voice-call
2026-01-12 01:16:39 +00:00
9877733748
fix(gateway): canonicalize main session aliases
2026-01-12 01:05:43 +00:00
d4e9f23ee9
fix(gateway): normalize session key to canonical form before store writes
...
Ensure 'main' alias is always stored as 'agent:main:main' to prevent
duplicate entries. Also update loadSessionEntry to check both forms
when looking up entries.
Fixes duplicate main sessions in session store.
2026-01-12 00:53:20 +00:00
7d6f17d77f
fix(subagent): make announce prompt more emphatic
...
The previous prompt was too permissive about skipping announcements.
Updated to strongly encourage announcing results since the requester
is waiting for a response.
- Add 'You MUST announce your result' instruction
- Clarify ANNOUNCE_SKIP is only for complete failures
- Improve guidance on providing useful summaries
2026-01-12 00:52:36 +00:00
0ed7ea698a
fix(subagent): wait for completion before announce
...
The previous immediate probe (timeoutMs: 0) only caught already-completed
runs. Cross-process spawns need to actually wait via agent.wait RPC for
the gateway to signal completion, then trigger the announce flow.
- Rename probeImmediateCompletion to waitForSubagentCompletion
- Use 10 minute wait timeout for agent.wait RPC
- Remove leftover debug console.log statements
2026-01-12 00:52:36 +00:00
74526645eb
test: cover unset docker env vars
2026-01-12 00:46:55 +00:00
cb095c8606
test: fix includes tests on windows
2026-01-12 00:39:14 +00:00
9c8967ef5d
style: biome fixes
2026-01-12 00:32:47 +00:00
720b9dd116
fix: make codex keychain platform-aware
2026-01-12 00:32:47 +00:00
9f9f6b75e7
test: expand include coverage
2026-01-12 00:30:26 +00:00
26cbbafc86
fix: skip pnpm patch fallback
2026-01-12 00:28:34 +00:00
67743325ee
fix: reset session after compaction overflow
2026-01-12 00:28:16 +00:00
32df2ef7bd
fix: stabilize invalid-connect handshake response
2026-01-12 00:19:47 +00:00
e3e3498a4b
fix: guard config includes ( #731 ) (thanks @pasogott)
2026-01-12 00:12:03 +00:00
53d3134fe8
refactor(config): simplify includes with class-based processor
...
- Replace free functions with IncludeProcessor class
- Simplify IncludeResolver interface: { readFile, parseJson }
- Break down loadFile into focused private methods
- Use reduce() for array include merging
- Cleaner separation of concerns
2026-01-12 00:08:27 +00:00
e6400b0b0f
refactor(config): extract includes logic to separate module
...
- Move $include resolution to src/config/includes.ts
- Simplify io.ts by importing from includes module
- Cleaner API: resolveConfigIncludes(obj, configPath, resolver?)
- Re-export errors from io.ts for backwards compatibility
- Rename test file to match module name
2026-01-12 00:08:27 +00:00
15d286b617
feat(config): add $include directive for modular configs
...
Adds support for splitting clawdbot.json into multiple files using the
$include directive. This enables:
- Single file includes: { "$include": "./agents.json5" }
- Multiple file merging: { "$include": ["./a.json5", "./b.json5"] }
- Nested includes (up to 10 levels deep)
- Sibling key merging with includes
Features:
- Relative paths resolved from including file
- Absolute paths supported
- Circular include detection
- Clear error messages with resolved paths
Use case: Per-client agent configs for isolated sandboxed environments
(e.g., legal case management with strict data separation).
2026-01-12 00:08:27 +00:00
4b51c96e4e
fix: apply model extra params without overwriting stream ( #732 ) (thanks @peschee)
2026-01-12 00:03:48 +00:00
d9960d83c1
style: fix formatting (biome)
2026-01-12 00:03:25 +00:00
32affaee02
feat: wire up model extraParams (temperature, maxTokens) to pi agent
...
- Use resolveExtraParams() which was defined but unused
- Create streamFn wrapper that injects config-driven params
- Apply to both compaction and run sessions
Config path: agents.defaults.models["provider/model"].params.temperature
Example:
agents.defaults.models["anthropic/claude-sonnet-4"].params.temperature = 0.7
agents.defaults.models["openai/gpt-4"].params.maxTokens = 8192
2026-01-12 00:03:24 +00:00
60430fcd2e
chore: harden installer and add smoke ci
2026-01-12 00:00:54 +00:00
55e55c8825
fix: preserve handshake close code and test truncation
2026-01-11 23:57:37 +00:00
146f7ab433
fix: surface handshake reasons
2026-01-11 23:46:20 +00:00
1f95d7fc8b
fix: read codex keychain credentials
2026-01-11 23:39:10 +00:00
3a8bfc0a5d
Merge pull request #733 from AbhisekBasu1/patch-1
...
Readme Fix: Update section title from 'macOS app' to 'Apps'
2026-01-11 23:38:38 +00:00
26cc2bd384
fix: land PR #733 (thanks @AbhisekBasu1)
2026-01-11 23:37:44 +00:00
248c731e78
test: expand voice-call coverage
2026-01-11 23:35:47 +00:00
4181e72977
fix: strip markup heartbeat acks
2026-01-11 23:26:51 +00:00
367baaca20
feat: implement voice-call plugin
2026-01-11 23:23:14 +00:00
f082f1e06e
fix: add discord channel actions
2026-01-11 22:32:17 +05:30
0d9a1009ff
fix: format discord parentId
2026-01-11 22:28:05 +05:30
33aaccd1c3
Merge pull request #728 from pkrmf/feature/dm-history-limit
...
feat: add configurable DM history limits with per-chat overrides
2026-01-11 22:25:12 +05:30
a4385dc920
fix: skip dm history limit for non-dm sessions
2026-01-11 22:18:15 +05:30
d63eae528c
feat(discord): expose channel management actions via message tool
...
Add channel-create, channel-edit, channel-delete, channel-move,
category-create, category-edit, and category-delete actions to the
unified message tool. These actions were already implemented in the
Discord-specific handler but weren't accessible via the pi_message tool.
Changes:
- Add 7 new channel/category management actions to MessageActionSchema
- Add parameters: name, type, parentId, topic, position, nsfw,
rateLimitPerUser, categoryId
- Gate actions behind discord.actions.channels (disabled by default)
- Add execute handlers routing to existing Discord action handlers
- Update Discord skill SKILL.md with documentation
Channel types: 0=text, 2=voice, 4=category
2026-01-11 10:01:32 -06:00
68f6f3f0bd
fix: normalize telegram command mentions
2026-01-11 21:06:04 +05:30
23717c5036
test: add comprehensive per-DM override tests for all providers
2026-01-11 08:55:32 -06:00
54abf4b0d7
feat: add per-DM history limit overrides
2026-01-11 08:53:50 -06:00
ab9ea827a4
refactor: move dmHistoryLimit to provider-level config
2026-01-11 08:38:19 -06:00
a005a97fef
feat: add configurable DM history limit
2026-01-11 08:21:14 -06:00
933c157092
test: add plugin docker e2e
2026-01-11 12:21:45 +00:00
cf0c72a557
feat: add plugin architecture
2026-01-11 12:11:12 +00:00
7acd26a2fc
Move provider to a plugin-architecture ( #661 )
...
* refactor: introduce provider plugin registry
* refactor: move provider CLI to plugins
* docs: add provider plugin implementation notes
* refactor: shift provider runtime logic into plugins
* refactor: add plugin defaults and summaries
* docs: update provider plugin notes
* feat(commands): add /commands slash list
* Auto-reply: tidy help message
* Auto-reply: fix status command lint
* Tests: align google shared expectations
* Auto-reply: tidy help message
* Auto-reply: fix status command lint
* refactor: move provider routing into plugins
* test: align agent routing expectations
* docs: update provider plugin notes
* refactor: route replies via provider plugins
* docs: note route-reply plugin hooks
* refactor: extend provider plugin contract
* refactor: derive provider status from plugins
* refactor: unify gateway provider control
* refactor: use plugin metadata in auto-reply
* fix: parenthesize cron target selection
* refactor: derive gateway methods from plugins
* refactor: generalize provider logout
* refactor: route provider logout through plugins
* refactor: move WhatsApp web login methods into plugin
* refactor: generalize provider log prefixes
* refactor: centralize default chat provider
* refactor: derive provider lists from registry
* refactor: move provider reload noops into plugins
* refactor: resolve web login provider via alias
* refactor: derive CLI provider options from plugins
* refactor: derive prompt provider list from plugins
* style: apply biome lint fixes
* fix: resolve provider routing edge cases
* docs: update provider plugin refactor notes
* fix(gateway): harden agent provider routing
* refactor: move provider routing into plugins
* refactor: move provider CLI to plugins
* refactor: derive provider lists from registry
* fix: restore slash command parsing
* refactor: align provider ids for schema
* refactor: unify outbound target resolution
* fix: keep outbound labels stable
* feat: add msteams to cron surfaces
* fix: clean up lint build issues
* refactor: localize chat provider alias normalization
* refactor: drive gateway provider lists from plugins
* docs: update provider plugin notes
* style: format message-provider
* fix: avoid provider registry init cycles
* style: sort message-provider imports
* fix: relax provider alias map typing
* refactor: move provider routing into plugins
* refactor: add plugin pairing/config adapters
* refactor: route pairing and provider removal via plugins
* refactor: align auto-reply provider typing
* test: stabilize telegram media mocks
* docs: update provider plugin refactor notes
* refactor: pluginize outbound targets
* refactor: pluginize provider selection
* refactor: generalize text chunk limits
* docs: update provider plugin notes
* refactor: generalize group session/config
* fix: normalize provider id for room detection
* fix: avoid provider init in system prompt
* style: formatting cleanup
* refactor: normalize agent delivery targets
* test: update outbound delivery labels
* chore: fix lint regressions
* refactor: extend provider plugin adapters
* refactor: move elevated/block streaming defaults to plugins
* refactor: defer outbound send deps to plugins
* docs: note plugin-driven streaming/elevated defaults
* refactor: centralize webchat provider constant
* refactor: add provider setup adapters
* refactor: delegate provider add config to plugins
* docs: document plugin-driven provider add
* refactor: add plugin state/binding metadata
* refactor: build agent provider status from plugins
* docs: note plugin-driven agent bindings
* refactor: centralize internal provider constant usage
* fix: normalize WhatsApp targets for groups and E.164 (#631 ) (thanks @imfing)
* refactor: centralize default chat provider
* refactor: centralize WhatsApp target normalization
* refactor: move provider routing into plugins
* refactor: normalize agent delivery targets
* chore: fix lint regressions
* fix: normalize WhatsApp targets for groups and E.164 (#631 ) (thanks @imfing)
* feat: expand provider plugin adapters
* refactor: route auto-reply via provider plugins
* fix: align WhatsApp target normalization
* fix: normalize WhatsApp targets for groups and E.164 (#631 ) (thanks @imfing)
* refactor: centralize WhatsApp target normalization
* feat: add /config chat config updates
* docs: add /config get alias
* feat(commands): add /commands slash list
* refactor: centralize default chat provider
* style: apply biome lint fixes
* chore: fix lint regressions
* fix: clean up whatsapp allowlist typing
* style: format config command helpers
* refactor: pluginize tool threading context
* refactor: normalize session announce targets
* docs: note new plugin threading and announce hooks
* refactor: pluginize message actions
* docs: update provider plugin actions notes
* fix: align provider action adapters
* refactor: centralize webchat checks
* style: format message provider helpers
* refactor: move provider onboarding into adapters
* docs: note onboarding provider adapters
* feat: add msteams onboarding adapter
* style: organize onboarding imports
* fix: normalize msteams allowFrom types
* feat: add plugin text chunk limits
* refactor: use plugin chunk limit fallbacks
* feat: add provider mention stripping hooks
* style: organize provider plugin type imports
* refactor: generalize health snapshots
* refactor: update macOS health snapshot handling
* docs: refresh health snapshot notes
* style: format health snapshot updates
* refactor: drive security warnings via plugins
* docs: note provider security adapter
* style: format provider security adapters
* refactor: centralize provider account defaults
* refactor: type gateway client identity constants
* chore: regen gateway protocol swift
* fix: degrade health on failed provider probe
* refactor: centralize pairing approve hint
* docs: add plugin CLI command references
* refactor: route auth and tool sends through plugins
* docs: expand provider plugin hooks
* refactor: document provider docking touchpoints
* refactor: normalize internal provider defaults
* refactor: streamline outbound delivery wiring
* refactor: make provider onboarding plugin-owned
* refactor: support provider-owned agent tools
* refactor: move telegram draft chunking into telegram module
* refactor: infer provider tool sends via extractToolSend
* fix: repair plugin onboarding imports
* refactor: de-dup outbound target normalization
* style: tidy plugin and agent imports
* refactor: data-drive provider selection line
* fix: satisfy lint after provider plugin rebase
* test: deflake gateway-cli coverage
* style: format gateway-cli coverage test
* refactor(provider-plugins): simplify provider ids
* test(pairing-cli): avoid provider-specific ternary
* style(macos): swiftformat HealthStore
* refactor(sandbox): derive provider tool denylist
* fix(sandbox): avoid plugin init in defaults
* refactor(provider-plugins): centralize provider aliases
* style(test): satisfy biome
* refactor(protocol): v3 providers.status maps
* refactor(ui): adapt to protocol v3
* refactor(macos): adapt to protocol v3
* test: update providers.status v3 fixtures
* refactor(gateway): map provider runtime snapshot
* test(gateway): update reload runtime snapshot
* refactor(whatsapp): normalize heartbeat provider id
* docs(refactor): update provider plugin notes
* style: satisfy biome after rebase
* fix: describe sandboxed elevated in prompt
* feat(gateway): add agent image attachments + live probe
* refactor: derive CLI provider options from plugins
* fix(gateway): harden agent provider routing
* fix(gateway): harden agent provider routing
* refactor: align provider ids for schema
* fix(protocol): keep agent provider string
* fix(gateway): harden agent provider routing
* fix(protocol): keep agent provider string
* refactor: normalize agent delivery targets
* refactor: support provider-owned agent tools
* refactor(config): provider-keyed elevated allowFrom
* style: satisfy biome
* fix(gateway): appease provider narrowing
* style: satisfy biome
* refactor(reply): move group intro hints into plugin
* fix(reply): avoid plugin registry init cycle
* refactor(providers): add lightweight provider dock
* refactor(gateway): use typed client id in connect
* refactor(providers): document docks and avoid init cycles
* refactor(providers): make media limit helper generic
* fix(providers): break plugin registry import cycles
* style: satisfy biome
* refactor(status-all): build providers table from plugins
* refactor(gateway): delegate web login to provider plugin
* refactor(provider): drop web alias
* refactor(provider): lazy-load monitors
* style: satisfy lint/format
* style: format status-all providers table
* style: swiftformat gateway discovery model
* test: make reload plan plugin-driven
* fix: avoid token stringification in status-all
* refactor: make provider IDs explicit in status
* feat: warn on signal/imessage provider runtime errors
* test: cover gateway provider runtime warnings in status
* fix: add runtime kind to provider status issues
* test: cover health degradation on probe failure
* fix: keep routeReply lightweight
* style: organize routeReply imports
* refactor(web): extract auth-store helpers
* refactor(whatsapp): lazy login imports
* refactor(outbound): route replies via plugin outbound
* docs: update provider plugin notes
* style: format provider status issues
* fix: make sandbox scope warning wrap-safe
* refactor: load outbound adapters from provider plugins
* docs: update provider plugin outbound notes
* style(macos): fix swiftformat lint
* docs: changelog for provider plugins
* fix(macos): satisfy swiftformat
* fix(macos): open settings via menu action
* style: format after rebase
* fix(macos): open Settings via menu action
---------
Co-authored-by: LK <luke@kyohere.com>
Co-authored-by: Luke K (pr-0f3t) <2609441+lc0rp@users.noreply.github.com>
Co-authored-by: Xin <xin@imfing.com>
2026-01-11 11:45:25 +00:00
23eec7d841
fix: update heartbeat prompt
2026-01-11 11:35:52 +00:00
a3747b1ee3
fix: add compaction headroom for memory writes
2026-01-11 11:25:15 +00:00
96e4fdb443
test: skip codex refresh token reuse
2026-01-11 11:24:25 +00:00
6b46217d19
fix: route subagent transcripts and keep tool action enums ( #708 ) (thanks @xMikeMickelson)
2026-01-11 11:19:38 +00:00
dc3c733612
fix(agent): use session key agentId for transcript path
...
Cross-agent subagent spawns wrote transcripts to the spawner's agent
directory instead of the target agent's directory. For example, when
main spawned a codex subagent with session key agent:codex:subagent:...,
the transcript went to agents/main/sessions/ instead of agents/codex/sessions/.
Pass sessionAgentId to resolveSessionFilePath so transcripts are written
to the correct agent's session directory.
2026-01-11 11:11:43 +00:00
580791088c
test: cover messaging tool error fallback ( #717 )
2026-01-11 11:10:03 +00:00
fb1fc5feee
fix(message-tool): strip reply/media tags from content in send/thread-reply actions
2026-01-11 11:04:07 +00:00
3da3e201de
Agents: harden message tool sends
2026-01-11 11:04:07 +00:00
2ebad5af1c
test: cover cron cli model overrides
2026-01-11 10:56:46 +00:00
0590365683
style: format cleanup commands
2026-01-11 10:54:33 +00:00
8e3f7c45d2
Merge pull request #711 from mjrussell/feat/cron-model-override
...
feat(cron): add --model flag to cron add/edit commands
2026-01-11 10:53:42 +00:00
a8a4993ffd
fix: trim cron model overrides and doc guidance ( #711 ) (thanks @mjrussell)
2026-01-11 10:52:40 +00:00
314e075df2
feat(cron): add --model flag to cron add/edit commands
...
Expose the existing model override capability via CLI flags:
- Add --model to cron add and cron edit commands
- Document model and thinking overrides in cron-jobs.md
- Add CLI example showing model/thinking usage
The backend already supported model in agentTurn payloads;
this change exposes it through the CLI interface.
2026-01-11 10:49:34 +00:00
0ef07bc142
test: extend discord tool-result timeout
2026-01-11 10:48:49 +00:00
4a166cf227
fix: add update env regression test ( #713 ) (thanks @danielz1z)
2026-01-11 10:48:46 +00:00
4570e1db7d
fix(update): merge custom env with process.env in spawn
...
When the update runner passes custom env vars (like CLAWDBOT_UPDATE_IN_PROGRESS),
the current code uses `env ?? process.env` which replaces the entire environment
instead of merging — losing PATH, HOME, etc.
This causes the doctor step to fail with 'node: No such file or directory'.
Fix: merge custom env with process.env instead of replacing it.
2026-01-11 10:39:07 +00:00
11a3b5aac9
style: biome fixes
2026-01-11 10:35:16 +00:00
11c8db14a1
feat: add reset/uninstall commands
2026-01-11 10:23:52 +00:00
323200b551
test(live): harden gateway probes
2026-01-11 04:46:30 +00:00
dbe156e881
fix(agents): sanitize transcripts for strict tool APIs
2026-01-11 04:46:18 +00:00
f00038b383
fix(testing): stabilize live model runs
2026-01-11 04:22:35 +00:00
343b6ac31b
feat: add onboard reset option
2026-01-11 05:04:36 +01:00
9046296ed3
fix: clarify sub-agent sandbox limits
2026-01-11 05:04:14 +01:00
b4e9a0c975
style: add blank line after note imports
2026-01-11 05:01:50 +01:00
71791d5a6a
fix: restore ZAI provider preference
2026-01-11 04:58:37 +01:00
7acdaad04e
style: fix note import spacing
2026-01-11 04:54:19 +01:00
b7ac9095e6
fix: skip tool-only reasoning replay
2026-01-11 04:52:16 +01:00
30348e41c6
test: stabilize doctor + sandbox tests
2026-01-11 04:45:04 +01:00
7343597075
chore: keep gate green
2026-01-11 04:42:44 +01:00
50e62122bb
chore: format sandbox skills test
2026-01-11 04:39:42 +01:00
eeae5ce7fd
fix: stabilize notes and reasoning replay
2026-01-11 04:37:06 +01:00
57e6a9a762
fix: clamp z.ai developer role
2026-01-11 04:28:30 +01:00
7660a78330
fix: mirror skills for read-only sandbox
2026-01-11 04:24:19 +01:00
29884f8d6f
fix: wrap clack notes for cleaner boxes
2026-01-11 04:23:43 +01:00
76c5bff7d6
test: cover whoami command
2026-01-11 04:20:34 +01:00
38604acd94
fix: tighten WhatsApp ack reactions and migrate config ( #629 ) (thanks @pasogott)
2026-01-11 04:11:04 +01:00
c928df7237
fix: remove any casts in backward compat code
2026-01-11 04:10:43 +01:00
30b4c14296
style: fix biome linting in ack-reaction tests
2026-01-11 04:10:43 +01:00
2daead27cf
feat(whatsapp): redesign ack-reaction as whatsapp-specific feature
...
- Move config from messages.ackReaction to whatsapp.ackReaction
- New structure: {emoji, direct, group} with granular control
- Support per-account overrides in whatsapp.accounts.*.ackReaction
- Add Zod schema validation for new config
- Maintain backward compatibility with old messages.ackReaction format
- Update tests to new config structure (14 tests, all passing)
- Add comprehensive documentation in docs/providers/whatsapp.md
- Timing: reactions sent immediately upon message receipt (before bot reply)
Breaking changes:
- Config moved from messages.ackReaction to whatsapp.ackReaction
- Scope values changed: 'all'/'direct'/'group-all'/'group-mentions'
→ direct: boolean + group: 'always'/'mentions'/'never'
- Old config still supported via fallback for smooth migration
2026-01-11 04:10:43 +01:00
d38b232724
chore: fix linting issues in ack-reaction feature
...
- Remove unused mock variables in tests
- Remove unused ackReactionScope variables in simple test cases
- Fix line length for ackReactionScope declaration
- All lint checks passing (0 warnings, 0 errors)
- All tests passing (8/8)
2026-01-11 04:10:43 +01:00
c3587d6cae
fix(whatsapp): ack reaction logic for group activation 'always' mode
...
- Fix bug where ack reaction was not sent when group activation is 'always'
- When requireMention=false (activation: always), always send reaction
- Add test case for activation='always' scenario
- Update inline comments for clarity
2026-01-11 04:10:43 +01:00
b3b507c6ea
feat(whatsapp): add ack reaction support after successful replies
...
- Add automatic emoji reactions on inbound WhatsApp messages
- Support all ackReactionScope modes: all, direct, group-all, group-mentions
- Reaction is sent AFTER successful reply (unlike Telegram/Discord)
- Errors are logged with proper context
- Add comprehensive test suite for ack reaction logic
Config usage:
messages:
ackReaction: "👀 "
ackReactionScope: "group-mentions" # default
Closes: WhatsApp ack-reaction feature request
2026-01-11 04:10:42 +01:00
579b00503f
style: format onboard providers
2026-01-11 04:08:26 +01:00
36a21ae9b0
fix: improve telegram configuration safety
2026-01-11 03:57:52 +01:00
11f897b7df
fix(gateway): show connect vs RPC status
2026-01-11 03:57:52 +01:00
1f9b4e3af6
fix: send heartbeat reasoning ( #694 ) (thanks @antons)
2026-01-11 03:51:51 +01:00
4ce2e73521
fix: improve provider issue formatting
2026-01-11 03:51:51 +01:00
c7caa9a87d
fix: deliver reasoning alongside HEARTBEAT_OK
2026-01-11 03:51:51 +01:00
7a518166bb
fix: persist reasoning across session resets
2026-01-11 03:51:51 +01:00
9d802abd9a
test: cover docker setup env plumbing
2026-01-11 03:45:45 +01:00
480bf916e2
fix(status): simplify footer guidance
2026-01-11 03:44:28 +01:00
9a4021a277
Merge pull request #703 from mteam88/openrouter-auth-config
...
Openrouter auth config (AI)
2026-01-11 02:44:24 +00:00
2b07a2a8ab
fix: stabilize onboarding auth tests ( #703 ) (thanks @mteam88)
2026-01-11 03:42:27 +01:00
77bc11f91c
chore: format OpenRouter auth edits
2026-01-11 03:35:45 +01:00
7890bd7369
CLI: reuse OpenRouter credentials
2026-01-11 03:35:45 +01:00
b6982236a6
CLI: add OpenRouter auth choice
2026-01-11 03:35:45 +01:00
494f41d575
docs(status): make status first-step
2026-01-11 03:34:33 +01:00
20b4e2b859
fix: stabilize live probes and docs
2026-01-11 02:26:39 +00:00
6668805aca
fix(agents): enforce single-writer session files
2026-01-11 02:25:45 +00:00
3a113b7752
fix: stabilize cli runner output
2026-01-11 02:25:45 +00:00
9b6bc0e66b
fix: reset unsigned launchd overrides ( #695 ) (thanks @jeffersonwarrior)
2026-01-11 03:19:24 +01:00
5ec3663748
fix: guard update spinner output ( #701 ) (thanks @bjesuiter)
2026-01-11 03:03:09 +01:00
f3bd6e4957
fix(update): use git status --porcelain for dirty check cross-platform
2026-01-11 03:00:43 +01:00
6cb55eaaa7
feat(update): show stderr for failed steps
2026-01-11 03:00:43 +01:00
3f27b23d5a
fix(update): remove command hint from step labels
2026-01-11 03:00:43 +01:00
4102e2f1b8
refactor(update): simplify progress with proper exit codes
2026-01-11 03:00:43 +01:00
35d42be828
fix(update): show skipped status with warning indicator for dirty repo
2026-01-11 03:00:43 +01:00
6a2b8328df
fix(update): restore reason in summary
2026-01-11 03:00:43 +01:00
cc8e6e00a0
fix(update): hide steps in summary when shown live, fix command hint
2026-01-11 03:00:43 +01:00
6e0c1cb051
fix(update): show each step with spinner as it runs
2026-01-11 03:00:43 +01:00
8f9aa3e8c5
fix(progress): start spinner immediately when delayMs is 0
2026-01-11 03:00:43 +01:00
88c404bcfc
feat(update): add progress spinner during update steps
2026-01-11 03:00:43 +01:00
4759633df1
fix(cli): keep build/lint green
2026-01-11 02:44:24 +01:00
e824b3514b
fix(status): improve diagnostics and output
2026-01-11 02:42:24 +01:00
02270abc87
feat: add codex cli backend
2026-01-11 01:39:30 +00:00
2d74119a08
test: cover auto-reply command gating
2026-01-11 02:27:16 +01:00
e0bf86f06c
feat: improve gateway services and auto-reply commands
2026-01-11 02:27:16 +01:00
a32021dc3e
fix: inject image paths for cli backends
2026-01-11 00:55:22 +00:00
4cf3e84b39
test: add CLI backend image probe
2026-01-11 00:55:22 +00:00
24c3ab6fe0
fix: unblock claude-cli live runs
2026-01-11 00:55:22 +00:00
d8f1124d59
feat: add CLI backend fallback
2026-01-11 00:55:22 +00:00
07be761779
feat: add sandbox browser control allowlists
2026-01-11 01:52:32 +01:00
b0b4b33b6b
fix: update gateway auth docs and clients
2026-01-11 01:51:24 +01:00
d33285a9cd
fix: harden gateway auth defaults
2026-01-11 01:51:24 +01:00
3e6d27ac4e
fix(status): show gateway auth when reachable
2026-01-11 01:46:37 +01:00
506cc9e7a1
chore(release): 2026.1.11-3
2026-01-11 01:38:15 +01:00
b339097179
style: format browser tool wiring
2026-01-11 01:34:45 +01:00
07eed3de56
docs(status): add diagnostics commands
2026-01-11 01:31:56 +01:00
326fb04d12
feat: add browser target selection for sandboxed agents
2026-01-11 01:31:56 +01:00
362fc3e235
Merge pull request #692 from peschee/fix/whatsapp-lid-mention-detection
...
fix(whatsapp): pass authDir to jidToE164 for LID mention detection
2026-01-11 00:16:03 +00:00
6444258ad3
fix: handle WhatsApp LID mentions ( #692 ) (thanks @peschee)
2026-01-11 01:14:57 +01:00
318f59ec3e
fix(status): show token previews
2026-01-11 01:11:46 +01:00
57dafec0ec
docs(status): add troubleshooting footer
2026-01-11 01:06:58 +01:00
518dfd4e42
fix(status): provider setup vs warn
2026-01-11 01:05:06 +01:00
9cb1bfa1c1
fix(whatsapp): pass authDir to jidToE164 for LID mention detection
...
WhatsApp group mentions using the new Linked ID format (@lid) were not
being detected because jidToE164() was called without the authDir needed
to find the LID reverse mapping files.
Now isBotMentioned() and debugMention() accept an optional authDir
parameter, which is passed through from account.authDir.
2026-01-11 01:04:10 +01:00
5fa3ac1e01
fix(status): full-width tables + better diagnosis
2026-01-11 00:54:27 +01:00
7c76561569
fix: dedupe inbound messages across providers
2026-01-11 00:12:25 +01:00
1d9199b529
style(test): format update-cli test
2026-01-10 23:46:11 +01:00
eff092268a
fix(test): avoid update-cli import timeout
2026-01-10 23:40:27 +01:00
621f710d60
fix(mac): add tailnet discovery fallback and debug CLI
2026-01-10 23:39:27 +01:00
c731a87d07
Discord: add fetch message action
2026-01-10 16:38:20 -06:00
786eac1d6f
test(cli): avoid update-cli import timeout
2026-01-10 23:35:04 +01:00
1eb50ffac4
feat(status): improve status output
2026-01-10 23:32:07 +01:00
3166cc911b
Heartbeat: optional reasoning delivery ( #690 )
...
* feat: expose heartbeat reasoning output
* docs(changelog): mention heartbeat reasoning toggle
2026-01-10 22:26:20 +00:00
4d0e74ab6c
fix: cover extra thinking tags ( #688 ) (thanks @theglove44)
2026-01-10 23:23:23 +01:00
a580639abf
fix(agents): strip <thought> and <antthinking> tags from output
2026-01-10 23:19:58 +01:00
494743a4e5
feat: run doctor after restart
2026-01-10 23:14:55 +01:00
0afa370869
fix: add 'usage limit' to rate limit detection patterns
...
OpenAI/ChatGPT returns "You have hit your ChatGPT usage limit (plus plan)"
when users exceed their plan quota. This error wasn't being recognized as a
rate limit, so fallback to alternative models wasn't triggering.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-10 23:11:06 +01:00
08cc8f2281
refactor(agents): extract transcript repair module
2026-01-10 22:07:25 +00:00
708f04b02f
fix: keep mock openai responses requests
2026-01-10 22:56:08 +01:00
1c257f170a
Gateway: disable OpenAI HTTP chat completions by default ( #686 )
...
* feat(gateway): disable OpenAI chat completions HTTP by default
* test(gateway): deflake mock OpenAI tool-calling
* docs(changelog): note OpenAI HTTP endpoint default-off
2026-01-10 21:55:54 +00:00
06052640e8
Merge pull request #685 from carlulsoe/fix/daemon-restart-feedback
...
fix(cli): improve daemon restart feedback [AI-assisted]
2026-01-10 21:53:00 +00:00
fa61699f9a
fix: polish restart feedback + stabilize tests ( #685 ) (thanks @carlulsoe)
2026-01-10 22:52:09 +01:00
98377c7c6b
fix(agents): harden tool transcript repair
2026-01-10 21:45:15 +00:00
805a29252e
test: add setup-token live smoke
2026-01-10 21:45:15 +00:00
f699dc3777
fix(cli): improve daemon restart feedback
...
- runDaemonRestart() now returns Promise<boolean> indicating success
- update command only shows success when restart actually happened
- Fixes missing reasoningLevel type in compactEmbeddedPiSession
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Carl Ulsøe Christensen <carlulsoe@users.noreply.github.com>
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-10 22:44:31 +01:00
ad17966e2f
fix(doctor): warn on opencode overrides
2026-01-10 22:44:31 +01:00
1110d96769
feat(gateway): add config toggle for chat completions endpoint
2026-01-10 22:39:06 +01:00
050c1c5391
fix(agents): include reasoningLevel in compaction params
2026-01-10 22:39:06 +01:00
a6a9930a34
fix: enable block streaming for all providers ( #684 )
2026-01-10 15:25:55 -06:00
6d70524aa8
fix: add reasoning visibility hint
2026-01-10 22:24:22 +01:00
aa30995aa1
test(live): add provider filters + google skip rules
2026-01-10 21:16:59 +00:00
0d00d6dfd4
style(gateway): format openai-http
2026-01-10 22:11:15 +01:00
6546a1a23a
feat(gateway): allow agent via model
2026-01-10 22:11:12 +01:00
dafa8a2881
feat(gateway): add OpenAI-compatible HTTP endpoint
2026-01-10 22:11:04 +01:00
ab314a22e0
chore: refresh pi-ai patch repro note
2026-01-10 20:55:57 +00:00
9790b39d80
feat(gateway): add agent image attachments + live probe
2026-01-10 20:44:23 +00:00
b9b1bc2726
test: relax reasoning replay expectations
2026-01-10 21:43:52 +01:00
8a194b4abc
fix: align opencode-zen provider setup
2026-01-10 21:38:18 +01:00
46e00ad5e7
fix: describe sandboxed elevated in prompt
2026-01-10 21:37:15 +01:00
3389231ecb
feat(doctor): offer update first
2026-01-10 21:34:59 +01:00
d772ff06c8
test: update openai responses reasoning replay
2026-01-10 21:20:26 +01:00
686b3f884c
fix: expose WhatsApp sender ids in group context
2026-01-10 21:09:08 +01:00
0ef429f532
feat: color docs search output
2026-01-10 21:02:27 +01:00
1bd5500832
feat: add colored CLI docs links
2026-01-10 20:51:03 +01:00
cf192f8551
style: biome format
2026-01-10 19:47:17 +00:00
afede929b3
test: harden gateway tool probes
2026-01-10 19:46:13 +00:00
d44bb41d27
fix: replay OpenAI reasoning for tool calls
2026-01-10 19:46:13 +00:00
fa346d7b78
fix: accept Z_AI_API_KEY for zai
2026-01-10 19:46:13 +00:00
ec1047583a
Merge pull request #640 from mcinteerj/fix/whatsapp-group-reactions
...
fix(whatsapp): enable reactions in group chats
2026-01-10 19:44:05 +00:00
7e6fa94720
fix: update WhatsApp history assertions ( #640 ) (thanks @mcinteerj)
2026-01-10 20:41:30 +01:00
4933113252
fix(whatsapp): preserve group message IDs and normalize reaction participants
2026-01-10 20:36:32 +01:00
4c4c167416
fix(update): harden root selection
2026-01-10 20:33:02 +01:00
777fb6b7bb
CLI: add clawdbot update command and --update flag
2026-01-10 20:33:02 +01:00
9f9098406c
feat(sandbox): add sandbox explain inspector
2026-01-10 20:28:43 +01:00
4533dd6e5d
test: add image attachment regression coverage
2026-01-10 20:25:38 +01:00
212b13b099
fix: repair tool-use history for anthropic
2026-01-10 19:15:57 +00:00
193ebba657
fix: sniff chat attachment mime ( #670 ) (thanks @cristip73)
2026-01-10 20:06:33 +01:00
c4e76eb635
fix: enable image attachments in chat messages for Claude API
...
Images were previously converted to markdown data URLs which Claude API
treats as plain text, not as actual images.
Changes:
- Add parseMessageWithAttachments() that returns {message, images[]}
- Pass images through the stack to session.prompt() as content blocks
- Filter null/empty attachments before parsing
- Strip data URL prefix if client sends it
This enables iOS and other clients to send images that Claude can actually see.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-10 20:00:25 +01:00
0279f09459
fix: avoid duplicate cli banners
2026-01-10 19:57:24 +01:00
7947059884
test(gateway): deflake temp HOME cleanup
2026-01-10 19:53:04 +01:00
1fe9f648b1
feat(hooks): allow gmail tailscale target URLs
2026-01-10 19:19:43 +01:00
b1664ec9c7
test: rename signal reaction-only test ( #637 )
2026-01-10 19:19:05 +01:00
82f71d25e5
refactor: centralize history context wrapping
2026-01-10 19:16:26 +01:00
b977ae19af
chore: fix lint and typing
2026-01-10 19:16:25 +01:00
d41372b9d9
feat: unify provider history context
2026-01-10 19:16:25 +01:00
8c1d39064d
test: adjust tool id sanitization
2026-01-10 18:15:15 +00:00
7c925aa5a0
style: format helper
2026-01-10 18:15:15 +00:00
651a9e9be4
fix: restore minimax tool calling
2026-01-10 18:15:15 +00:00
8dbb22cc93
fix: signal handle dataMessage.reaction safely ( #637 ) (thanks @neist)
2026-01-10 19:13:23 +01:00
59e6064006
fix(signal): handle reactions in dataMessage.reaction format ( #1 )
...
* fix(signal): handle reactions inside dataMessage.reaction
Signal reactions can arrive in two formats:
1. envelope.reactionMessage (already handled)
2. envelope.dataMessage.reaction (now handled)
The signal-cli SSE events use the second format, which was being
misinterpreted as a message with attachments, leading to 'broken
media / attachments' errors.
Changes:
- Add reaction property to SignalDataMessage type
- Check both envelope.reactionMessage and dataMessage.reaction
- Improve body content detection to properly identify reaction-only messages
- Add test for dataMessage.reaction format
* fix(signal): reaction notifications work when account is phone number
When reactionNotifications mode is 'own', notifications would never fire
because resolveSignalReactionTarget() returned a UUID but
shouldEmitSignalReactionNotification() compared it against the account
phone number, which never matched.
The fix:
- Add optional 'phone' field to SignalReactionTarget type
- Extract phone number first in resolveSignalReactionTarget(), include
it even when UUID is present
- In shouldEmitSignalReactionNotification() 'own' mode, check phone
match first before falling back to UUID comparison
This ensures reactions to your own messages are properly detected when
the Signal account is configured as a phone number and the reaction
event contains both targetAuthor (phone) and targetAuthorUuid.
* fix(signal): include phone in reaction target for own-mode matching
When targetAuthorUuid is present, also store targetAuthor phone number
in the reaction target. This allows own-mode reaction notifications to
match when comparing account phone against UUID-based targets.
2026-01-10 19:10:39 +01:00
26ce65995f
fix(gmail): keep tailscale serve path at root
...
The default Gmail hook path configured by `clawdbot hooks gmail setup` is `/gmail-pubsub`. Tailscale strips the mount path before proxying, so the request lands on `/` and the hook 404s under the default configuration.
When Tailscale is enabled, always listen on `/` internally and keep the public URL on the configured path (defaulting to `/gmail-pubsub`). This makes default and custom paths work reliably.
Alternative (not implemented here): call tailscale with a full target URL so the backend keeps the path, e.g. `tailscale funnel --set-path /gmail-pubsub http://127.0.0.1:8788/gmail-pubsub `. We did not take this path because it requires changing the CLI invocation to pass URLs (not ports) plus extra validation, which is a larger behavior change.
2026-01-10 18:51:12 +01:00
7dd0899856
fix: voicewake respects state dir override ( #666 ) (thanks @roshanasingh4)
2026-01-10 18:32:09 +01:00
f1a1032cd6
fix: serialize telegram media-group processing
2026-01-10 18:31:36 +01:00
b383fbeed3
fix: cron wakeMode now waits for heartbeat ( #666 ) (thanks @roshanasingh4)
2026-01-10 18:31:35 +01:00
91c870a0c4
fix(cron): wait for heartbeat to complete when wakeMode is "now"
...
Fixes #652
When cron jobs with sessionTarget:"main" have wakeMode:"now",
they were being marked as completed immediately without waiting for the
agent to actually process the system event.
The issue was that requestHeartbeatNow() is fire-and-forget and
doesn't wait for the heartbeat to complete. The job would finish
with durationMs: 0 before the agent had a chance to run.
This fix:
- Adds runHeartbeatOnce to CronServiceDeps
- Wires it up in gateway/server.ts to load config and pass runtime
- Modifies executeJob() to call runHeartbeatOnce when wakeMode:"now"
- Waits for heartbeat to complete and maps status to cron result:
* "ran" → "ok"
* "skipped" → "skipped"
* "failed" → "error"
- Falls back to old behavior for wakeMode:"next-heartbeat" or if
runHeartbeatOnce is not available (backward compatibility)
Benefits:
- Jobs now have accurate durationMs reflecting actual processing time
- Jobs are correctly marked with "error" status if heartbeat fails
- Prevents race condition where job completes before agent runs
[AI-assisted] - Generated with z.ai GLM-4.7
[Tested: Lightly tested - Logic validated with test scenarios, code quality checks passed, integration testing requires live Clawdbot instance]
2026-01-10 18:31:35 +01:00
5a57cbe571
Merge pull request #667 from rubyrunsstuff/fix/discord-forwarded-snapshots
...
Discord: include forwarded message snapshots
2026-01-10 17:31:26 +00:00
6480ef369f
fix: telegram draft chunking defaults ( #667 ) (thanks @rubyrunsstuff)
2026-01-10 18:30:06 +01:00
2d105d16f8
fix(opencode-zen): keep legacy aliases + rationale ( #669 ) (thanks @magimetal)
2026-01-10 18:25:43 +01:00
7a836c9ff0
Discord: include forwarded message snapshots
2026-01-10 18:23:30 +01:00
738269eb74
feat(opencode-zen): update models with sensible defaults
...
- Replace model catalog with 11 current models: gpt-5.1-codex, claude-opus-4-5,
gemini-3-pro, alpha-glm-4.7, gpt-5.1-codex-mini, gpt-5.1, glm-4.7-free,
gemini-3-flash, gpt-5.1-codex-max, minimax-m2.1-free, gpt-5.2
- Add accurate per-token costs from OpenCode Zen pricing
- Add accurate context windows and output limits
- Update aliases for new model families (codex, glm, minimax)
- Remove deprecated models (sonnet, haiku, o-series, gemini-2.5)
2026-01-10 18:22:26 +01:00
9b5ce2530a
Merge pull request #665 from sebslight/fix/cloud-code-assist-schema-and-tool-ids
...
fix(agents): harden Cloud Code Assist compatibility
2026-01-10 17:07:58 +00:00
38d6930fbe
Merge pull request #664 from azade-c/fix/use-state-dir-for-nodes-voicewake
...
fix: use resolveStateDir() for node-pairing and voicewake storage
2026-01-10 17:07:28 +00:00
0d98e93253
fix: harden cloud code assist tool schema sanitizing ( #665 ) (thanks @sebslight)
2026-01-10 18:07:26 +01:00
64babcac7a
fix(agents): harden Cloud Code Assist compatibility
...
- Expand schema scrubber to strip additional constraint keywords rejected
by Cloud Code Assist (examples, minLength, maxLength, minimum, maximum,
multipleOf, pattern, format, minItems, maxItems, uniqueItems,
minProperties, maxProperties)
- Extend tool call ID sanitization to cover toolUse and toolCall block
types (previously only functionCall was sanitized)
- Update pi-tools test to include 'examples' in unsupported keywords
Fixes 400 errors when using google-antigravity/claude-opus-4-5-thinking:
- tools.N.custom.input_schema: JSON schema is invalid
- messages.N.content.N.tool_use.id: String should match pattern
2026-01-10 18:06:35 +01:00
464f0645a8
fix: stabilize telegram media tests ( #664 ) (thanks @azade-c)
2026-01-10 18:06:05 +01:00
ef08c3f038
fix(agents): stabilize cli creds cache + bash cwd
2026-01-10 18:02:21 +01:00
48ad3bbbe6
fix: use resolveStateDir() for node-pairing and voicewake storage
...
Both node-pairing.ts and voicewake.ts were using a local defaultBaseDir()
that hardcoded ~/.clawdbot, ignoring CLAWDBOT_STATE_DIR.
This caused nodes/paired.json and settings/voicewake.json to be stored
in ~/.clawdbot instead of the configured state directory.
Fixes the bug where paired nodes config was stored in a different
location than the rest of the gateway state.
2026-01-10 17:55:30 +01:00
843ff5f2d4
fix(sessions): tolerate ENOENT during lock
2026-01-10 17:50:53 +01:00
60bf349201
fix(sessions): lock store saves; wait for bash close
2026-01-10 17:47:12 +01:00
a54706a063
fix: throttle cli credential sync
2026-01-10 17:44:03 +01:00
12722acb55
feat: wizard model picker ( #611 , thanks @jonasjancarik)
2026-01-10 16:32:59 +00:00
687a10b8cc
fix: map opencode-zen preferred provider
2026-01-10 16:32:59 +00:00
9f80d8ec7c
fix: skip model picker when auth choice preset
2026-01-10 16:32:59 +00:00
dcc41e932d
feat: add shared model picker to configure/onboarding
2026-01-10 16:32:59 +00:00
e3cd431551
fix(auto-reply): RawBody commands + locked session updates ( #643 )
2026-01-10 17:32:31 +01:00
e2ea02160d
test: add workspace path regressions
2026-01-10 17:28:43 +01:00
a1533a17f7
fix(gateway): harden chat abort semantics
2026-01-10 17:23:27 +01:00
84d64f9395
Merge pull request #446 from tony-freedomology/feat/human-delay
...
feat(agent): add human-like delay between block replies
2026-01-10 16:16:52 +00:00
fb03149df4
fix: finalize human delay config typing ( #446 ) (thanks @tony-freedomology)
2026-01-10 17:15:27 +01:00
ab994d2c63
feat(agent): add human-like delay between block replies
...
Adds `agent.humanDelay` config option to create natural rhythm between
streamed message bubbles. When enabled, introduces a random delay
(default 800-2500ms) between block replies, making multi-message
responses feel more like natural human texting.
Config example:
```json
{
"agent": {
"blockStreamingDefault": "on",
"humanDelay": {
"enabled": true,
"minMs": 800,
"maxMs": 2500
}
}
}
```
- First message sends immediately
- Subsequent messages wait a random delay before sending
- Works with iMessage, Signal, and Discord providers
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-10 17:12:50 +01:00
de5b75eff6
fix(tools): resolve Read/Write/Edit paths against workspace directory
...
Previously, Read/Write/Edit tools used the global tool instances from
pi-coding-agent which had process.cwd() baked in at import time. Since
the gateway starts from /root/dev/ai/clawdbot, relative paths like
'SOUL.md' would incorrectly resolve there instead of the agent's
workspace (/root/clawd).
This fix:
- Adds workspaceDir option to createClawdbotCodingTools
- Creates fresh Read/Write/Edit tools bound to workspaceDir
- Adds cwd option to Bash tool defaults for consistency
- Passes effectiveWorkspace from pi-embedded-runner
Absolute paths and ~/... paths are unaffected. Sandboxed sessions
continue to use sandbox root as before.
Includes tests for Read/Write/Edit workspace path resolution.
2026-01-10 17:08:56 +01:00
d1943a9337
chore: format reply session
2026-01-10 17:03:17 +01:00
d781508952
fix: make chat.send non-blocking
2026-01-10 17:02:28 +01:00
b7fdc266ad
test(auto-reply): cover native /model session routing
2026-01-10 16:50:32 +01:00
b99eb4c9f3
fix(auto-reply): apply native commands to target session
2026-01-10 16:48:53 +01:00
8978ac425e
fix: harden cli credential sync
2026-01-10 16:37:54 +01:00
81f9093c3c
fix(pairing): accept positional provider args
2026-01-10 16:36:43 +01:00
41c8bdfada
feat: add ZAI auth choice
2026-01-10 16:32:21 +01:00
8b47368167
fix: harden cli credential sync
2026-01-10 16:25:40 +01:00
e60c3fc1b3
fix: doctor ignore install dir in legacy workspace check
2026-01-10 16:23:35 +01:00
78532d76bd
test: clean up lint warnings
2026-01-10 16:17:02 +01:00
53a0c966a5
refactor: unify configure auth choice
2026-01-10 16:14:49 +01:00
43b530ca1c
fix(agents): suppress partial replies with reasoning
2026-01-10 16:03:17 +01:00
44564df028
refactor(sessions): add mergeSessionEntry
2026-01-10 16:03:17 +01:00
70c1732dd1
refactor: centralize messaging dedupe helpers
2026-01-10 16:02:56 +01:00
5a93447294
fix: prevent claude-cli oauth downgrade ( #654 ) (thanks @radek-paclt)
2026-01-10 15:50:25 +01:00
a39951d463
fix(auth): enable OAuth refresh for Claude CLI credentials
...
When Claude CLI credentials (anthropic:claude-cli) expire, automatically
refresh using the stored refresh token instead of failing with
"No credentials found" error.
Changes:
- Read refreshToken from Claude CLI and store as OAuth credential type
- Implement bidirectional sync: after refresh, write new tokens back to
Claude Code storage (file on Linux/Windows, Keychain on macOS)
- Prefer OAuth over Token credentials (enables auto-refresh capability)
- Maintain backward compatibility for credentials without refreshToken
This enables long-running agents to operate autonomously without manual
re-authentication when OAuth tokens expire.
Co-Authored-By: Claude <noreply@anthropic.com>
2026-01-10 15:40:27 +01:00
1281c1d155
Merge pull request #655 from antons/fix/reasoning-imsg
...
Fix reasoning in iMessage
2026-01-10 14:39:14 +00:00
236f8560b3
fix: reasoning iMessage sessions + final reply ( #655 ) (thanks @antons)
2026-01-10 15:31:57 +01:00
ae3711bfbd
Merge pull request #659 from mickahouan/fix/dedupe-message-tool
...
Fix: avoid duplicate replies when message tool sends
2026-01-10 14:30:02 +00:00
449bee9645
fix: bundle node runtime for mac app
2026-01-10 15:28:37 +01:00
4d146ea2f5
fix: dedupe message tool replies ( #659 ) (thanks @mickahouan)
2026-01-10 15:28:13 +01:00
3b5149ca39
fix: send only final answer with reasoning
...
When reasoning is enabled on non‑block providers, we now ignore interim streaming chunks and send only the final assistant answer at completion, so replies aren’t partial or duplicated.
2026-01-10 15:28:04 +01:00
4c86da044e
fix(sessions): persist reasoning/elevated across DMs
2026-01-10 15:28:04 +01:00
d01e06f09a
Fix: dedupe message tool sends
2026-01-10 15:25:20 +01:00
65c2532cd5
fix: minimax apiKey optional for providers ( #656 ) (thanks @mneves75)
2026-01-10 15:08:12 +01:00
3e2e3eb023
Config: add MiniMax direct API authentication option
...
Makes apiKey optional in ModelProviderConfig so MiniMax can use auth
profiles or environment variables (MINIMAX_API_KEY) instead of requiring
explicit config.
Changes:
- src/config/types.ts: apiKey changed from required to optional
- src/config/zod-schema.ts: use z.string().min(1).optional() for validation
- src/commands/configure.ts: add minimax-api auth choice in wizard
- src/commands/onboard-auth.ts: MiniMax provider omits apiKey (uses env/auth)
- patches/@mariozechner__pi-ai@0.42.1.patch: map minimax → MINIMAX_API_KEY
Auth Resolution Order (unchanged):
1. Auth profiles (highest priority)
2. Environment variables (MINIMAX_API_KEY, etc.)
3. Custom provider apiKey from models.json (lowest priority)
2026-01-10 10:57:09 -03:00
920b3880c1
test: add elevated mode regressions
2026-01-10 05:31:48 +01:00
66db6c749d
fix: persist elevated off override
2026-01-10 05:23:46 +01:00
2045395ccb
test(live): add optional write/bash probes
2026-01-10 04:14:39 +00:00
d3674f4d6c
test(onboard): cover remote + lan token flows
2026-01-10 04:14:39 +00:00
cdb915d527
chore: normalize Clawdbot naming
2026-01-10 05:14:09 +01:00
a7c8341452
feat: show more session flags
2026-01-10 05:14:07 +01:00
7b392ca74b
test(onboard): gateway token auth flow
2026-01-10 03:54:29 +00:00
eee04fa2ce
fix(onboard): persist gateway token in config
2026-01-10 03:54:25 +00:00
4fac94f259
test(gateway): add wizard e2e + isolate live suite
2026-01-10 03:44:21 +00:00
0f409cb99d
test(telegram): force real timers for media groups
2026-01-10 03:44:21 +00:00
241bc737cf
test(telegram): deflake media groups on windows
2026-01-10 04:43:04 +01:00
2a0d8f6e38
test(gateway): avoid real OpenAI in mock test
2026-01-10 03:25:45 +00:00
056c4ae622
test(telegram): harden media tests
2026-01-10 04:18:05 +01:00
6274adce3a
fix(tools): keep canonical tool names for oauth
2026-01-10 04:18:00 +01:00
4f79122068
test: stabilize gateway mock + lint
2026-01-10 03:14:13 +00:00
7376d1e6c9
feat: improve tui status output
2026-01-10 04:07:15 +01:00
782863ea6c
test(gateway): add offline tool-calling regression
2026-01-10 03:06:02 +00:00
cc1c5f800f
fix(tools): harden schemas and oauth tool names
2026-01-10 03:05:56 +00:00
f241859c98
fix: relax fetch typing for Bun
2026-01-10 04:01:06 +01:00
8466e53b5d
fix: restore Anthropic OAuth tool dispatch
2026-01-10 04:01:00 +01:00
8e63cd9a76
feat: improve tui status line
2026-01-10 03:53:32 +01:00
2cfed7952e
test(telegram): relax media group timeouts on Windows
2026-01-10 02:32:03 +00:00
8a5fb796c0
test(live): probe Read tool via gateway
2026-01-10 02:25:24 +00:00
34664601e0
fix(auto-reply): default audioAsVoice to false
2026-01-10 02:25:19 +00:00
d693f02fa7
fix(msteams): download image attachments reliably
2026-01-10 02:25:14 +00:00
003cda73e8
style: fix biome formatting
2026-01-10 02:11:43 +00:00
afe6f182ca
feat: show effective config in /debug
2026-01-10 03:10:14 +01:00
5a6ae2624e
docs: add /config get alias
2026-01-10 03:10:14 +01:00
2dc7872ad1
feat: auto-start sandbox browser
2026-01-10 02:06:21 +00:00
8b579c91a5
feat: add /config chat config updates
2026-01-10 03:01:27 +01:00
63b0a16357
feat(cli): colorize gateway health + daemon output
2026-01-10 03:01:27 +01:00
f28a4a34ad
refactor: unify inline directives and media fetch
2026-01-10 03:01:04 +01:00
4075895c4c
refactor: consolidate reply/media helpers
2026-01-10 02:41:16 +01:00
9cd2662a86
refactor: centralize WhatsApp target normalization
2026-01-10 02:39:52 +01:00
8f8caa8d89
test(telegram): relax media group test timeouts
2026-01-10 02:37:59 +01:00
991f6dda38
Merge pull request #631 from imfing/fix-normalize
...
fix(whatsapp): normalize targets for groups and E.164
2026-01-10 01:27:33 +00:00
2485701835
fix: hide tui reasoning label when off
2026-01-10 01:25:15 +00:00
f634db5c17
fix: signal own reactions match uuid + phone ( #632 ) (thanks @neist)
...
Co-authored-by: neist <1029724+neist@users.noreply.github.com>
2026-01-10 02:24:57 +01:00
f0700e9778
fix: normalize WhatsApp targets for groups and E.164 ( #631 ) (thanks @imfing)
2026-01-10 02:22:13 +01:00
38e2362be6
fix: remove ack reactions after reply ( #633 ) (thanks @levifig)
2026-01-10 02:14:14 +01:00
b5858c0148
feat: add removeAckAfterReply option for Discord, Slack, and Telegram
...
Add `messages.removeAckAfterReply` config option to automatically remove
acknowledgment reactions after the bot sends a reply, reducing visual
clutter while still providing immediate feedback.
Platforms: Discord, Slack, Telegram
Implementation:
- Added removeAckAfterReply boolean field to MessagesConfig (default: false)
- Track ack reaction state in all three platform handlers
- Remove ack reaction after successful reply delivery
- Graceful error handling with verbose logging
Platform-specific:
- Discord: uses removeReactionDiscord()
- Slack: uses removeSlackReaction()
- Telegram: uses setMessageReaction() with empty array
Closes #627
2026-01-10 02:13:46 +01:00
a29f5dda2e
test(live): gateway smoke across profile-key models
2026-01-10 01:09:41 +00:00
623d1e11f1
refactor: centralize session agent resolution
2026-01-10 01:57:54 +01:00
f4b3869f45
Merge pull request #490 from jarvis-medmatic/feat/audio-as-voice-tag
...
feat(telegram): `[[audio_as_voice]]` tag support
2026-01-10 00:52:02 +00:00
c56b2f4bc1
fix: honor audio_as_voice streaming + parse tests ( #490 ) (thanks @jarvis-medmatic)
2026-01-10 01:50:33 +01:00
cb10682d3e
fix(openai): avoid invalid reasoning replay
2026-01-10 00:45:10 +00:00
5fedfd8d15
chore: format audioAsVoice updates
...
Co-authored-by: Manuel Hettich <17690367+ManuelHettich@users.noreply.github.com>
2026-01-10 01:44:57 +01:00
8c7d1781bc
fix(pi): preserve audio_as_voice tag
...
- Allow flag-only chunks so audio_as_voice propagates
- Keep reply item scan aware of empty audio tag blocks
Co-authored-by: Manuel Hettich <17690367+ManuelHettich@users.noreply.github.com>
2026-01-10 01:43:51 +01:00
9a7f050568
refactor(telegram): centralize voice decisions
...
- Share voice compatibility decision logic across send + bot flows
- Keep voice fallback logging consistent
- Simplify voice handling in the audio send path
2026-01-10 01:43:23 +01:00
ce786762db
fix(telegram): guard voice note sends
2026-01-10 01:43:01 +01:00
2f036f7173
fix(audio): preserve audioAsVoice propagation
...
- Keep audioAsVoice-only payloads from being filtered out
- Allow empty payloads through when they carry the flag
- Remove temporary debug logs around audioAsVoice buffering
Co-authored-by: Manuel Hettich <17690367+ManuelHettich@users.noreply.github.com>
2026-01-10 01:42:09 +01:00
05a99aa49b
feat(telegram): buffer audio blocks for [[audio_as_voice]] tag support
...
- Add [[audio_as_voice]] detection to splitMediaFromOutput()
- Pass audioAsVoice through onBlockReply callback chain
- Buffer audio blocks during streaming, flush at end with correct flag
- Non-audio media still streams immediately
- Fix: emit payloads with audioAsVoice flag even if text is empty
Co-authored-by: Manuel Hettich <17690367+ManuelHettich@users.noreply.github.com>
2026-01-10 01:41:18 +01:00
43975a39dc
fix: gate heartbeat prompt to default agent sessions ( #630 ) (thanks @adam91holt)
2026-01-10 01:32:58 +01:00
c91ec2aab7
fix: only inject heartbeat prompt for default agent
...
The heartbeat prompt from agents.defaults.heartbeat.prompt was being
injected into the system prompt for ALL agents, causing non-default
agents to read the default agent's identity files and adopt its persona.
Now the heartbeat prompt is only included when the session's agent ID
matches the configured default agent. Other agents receive no heartbeat
section in their system prompt.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-10 01:32:30 +01:00
5898304fa0
fix: abort runs between tool calls
2026-01-10 01:26:25 +01:00
53ec8e36cb
refactor: centralize failover error parsing
2026-01-10 01:26:06 +01:00
82ffcfb181
fix(web): show all WhatsApp shared contacts
2026-01-10 00:22:31 +00:00
20d4773f14
fix(agents): require raw for gateway config.apply ( #566 ) (thanks @sircrumpet)
2026-01-10 00:21:15 +00:00
52565864d1
Merge pull request #619 from rubyrunsstuff/fix/telegram-block-streaming
...
fix: enable block streaming for Telegram when streamMode is 'block'
2026-01-10 00:16:04 +00:00
1fd7a6e310
fix: keep telegram streamMode draft-only ( #619 ) (thanks @rubyrunsstuff)
2026-01-10 01:14:40 +01:00
08015fbce6
Merge pull request #544 from jeffersonwarrior/fix/cloud-code-assist-api-errors
...
Fix Cloud Code Assist API errors (429/400)
2026-01-10 00:13:46 +00:00
a9bd01b523
refactor: unify contact list summaries
2026-01-10 01:13:38 +01:00
251ed83680
fix: harden Cloud Code Assist failover ( #544 ) (thanks @jeffersonwarrior)
2026-01-10 01:12:46 +01:00
d75b302699
style: fix pi-embedded-runner formatting ( #623 ) (thanks @magimetal)
2026-01-10 01:12:22 +01:00
b4fbf2fe0d
fix: enable block streaming for Telegram when streamMode is 'block'
...
- Fix disableBlockStreaming logic in telegram/bot.ts to properly enable
block streaming when telegram.streamMode is 'block' regardless of
blockStreamingDefault setting
- Set minChars default to 1 for Telegram block mode so chunks send
immediately on newlines/sentences instead of waiting for 800 chars
- Skip coalescing for Telegram block mode when not explicitly configured
to reduce chunk batching delays
- Fix newline preference to wait for actual newlines instead of breaking
on any whitespace when buffer is under maxChars
Fixes issue where all Telegram messages were batched into one message
at the end instead of streaming as separate messages during generation.
2026-01-10 01:11:41 +01:00
5843733978
Fix Cloud Code Assist API errors (429/400)
...
- Enhanced rate limit detection for Cloud Code Assist quota exhaustion
- Added tool call ID sanitization to fix invalid request format errors
- Integrated Cloud Code Assist format error detection into failover system
- Added comprehensive error pattern matching for Cloud Code Assist APIs
Fixes #cloud-code-assist-api-errors
2026-01-10 01:10:23 +01:00
c69c4caa33
fix: polish opencode-zen onboarding ( #623 ) (thanks @magimetal)
2026-01-10 01:09:34 +01:00
05bd100f7a
style: fix formatting
2026-01-10 01:09:34 +01:00
a399fa36c8
feat(onboard): add OpenCode Zen as model provider
2026-01-10 01:09:34 +01:00
9b1f164447
fix: guard small context windows
2026-01-10 01:08:56 +01:00
Peter Steinberger
Roshan Singh
Sebastian
Netanel Draiman
George Pickett
Jonathan Wilkins
sleontenko
Shadow
danielz1z
Gregor's Bot
vrknetha
Shadow
Jefferson Warrior
Friederike Seiler
meaningfool
Marc
Travis Hinton
Gustavo Madeira Santana
Muhammed Mukhthar CM
Gabriel Trigo
Abhi
Keith the Silly Goose
hsrvc
Rony Kelner
L36 Server
Drake Thomsen
David Guttman
Aaron Konyer
Zach Knickerbocker
Jake
Ayaan Zaidi
Ayaan Zaidi
Mustafa Tag Eldeen
Azade
Sash Catanzarite
juanpablodlc
The Admiral
myfunc
user
sheeek
Peter Siska
Nicholas Spisak
Marc Terns
Chris Taylor
Matthew Russell
Anton Sotkov
Matthew
Benjamin Jesuiter
Kit
Ruby
Claude
cristip73
Kasper Neist Christjansen
Magi Metal
Sebastian Barrios
Jonáš Jančařík
Lloyd
Radek Paclt
Mickaël Ahouansou
mneves75
Xin
Levi Figueira
Jarvis
Adam Holt