romtuck/openclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
7,457 Commits 258 Branches 39 Tags 276 MiB
ec2c69c230
Commit Graph

885 Commits

Author SHA1 Message Date
Peter Steinberger
cdb915d527 chore: normalize Clawdbot naming 2026-01-10 05:14:09 +01:00
Peter Steinberger
34664601e0 fix(auto-reply): default audioAsVoice to false 2026-01-10 02:25:19 +00:00
Peter Steinberger
003cda73e8 style: fix biome formatting 2026-01-10 02:11:43 +00:00
Peter Steinberger
afe6f182ca feat: show effective config in /debug 2026-01-10 03:10:14 +01:00
Peter Steinberger
5a6ae2624e docs: add /config get alias 2026-01-10 03:10:14 +01:00
Peter Steinberger
8b579c91a5 feat: add /config chat config updates 2026-01-10 03:01:27 +01:00
Peter Steinberger
f28a4a34ad refactor: unify inline directives and media fetch 2026-01-10 03:01:04 +01:00
Peter Steinberger
4075895c4c refactor: consolidate reply/media helpers 2026-01-10 02:41:16 +01:00
Peter Steinberger
a29f5dda2e test(live): gateway smoke across profile-key models 2026-01-10 01:09:41 +00:00
Peter Steinberger
623d1e11f1 refactor: centralize session agent resolution 2026-01-10 01:57:54 +01:00
Peter Steinberger
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
Peter Steinberger
c56b2f4bc1 fix: honor audio_as_voice streaming + parse tests (#490) (thanks @jarvis-medmatic) 2026-01-10 01:50:33 +01:00
Peter Steinberger
cb10682d3e fix(openai): avoid invalid reasoning replay 2026-01-10 00:45:10 +00:00
Jarvis
5fedfd8d15 chore: format audioAsVoice updates 
Co-authored-by: Manuel Hettich <17690367+ManuelHettich@users.noreply.github.com>
 2026-01-10 01:44:57 +01:00
Jarvis
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
Peter Steinberger
5898304fa0 fix: abort runs between tool calls 2026-01-10 01:26:25 +01:00
Peter Steinberger
1fd7a6e310 fix: keep telegram streamMode draft-only (#619) (thanks @rubyrunsstuff) 2026-01-10 01:14:40 +01:00
Ruby
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
Peter Steinberger
097550c299 fix: centralize verbose overrides and tool stream gating 2026-01-10 00:52:24 +01:00
Peter Steinberger
9a8d3aed26 test: update status expectations for verbose/elevated labels 2026-01-09 23:43:24 +00:00
Peter Steinberger
e18080163f fix: simplify verbose/elevated status labels 2026-01-09 23:41:57 +00:00
Peter Steinberger
96e17d407a fix: filter NO_REPLY prefixes 2026-01-09 23:29:05 +00:00
Peter Steinberger
a9a70ea278 fix: persist verbose off and gate tool stream 2026-01-10 00:22:28 +01:00
Peter Steinberger
98d0318d4e
refactor: cron payload migration cleanup (#621) 
* refactor: centralize cron payload migration

* test: stabilize block streaming mocks

* test: adjust chunker fence-close case
 2026-01-09 22:56:55 +00:00
Peter Steinberger
3b91148a0a fix: handle fence-close paragraph breaks 2026-01-09 22:20:22 +00:00
Peter Steinberger
3adec35632 fix: make forced block chunking fence-safe 2026-01-09 21:52:47 +00:00
Peter Steinberger
79af03ba5e fix(auto-reply): tighten block streaming defaults 2026-01-09 22:41:10 +01:00
Peter Steinberger
53f51786f2 fix: default block streaming coalesce idle to 1s 2026-01-09 22:31:19 +01:00
Peter Steinberger
6c7a27c010 refactor: normalize main session key handling 2026-01-09 22:30:15 +01:00
Peter Steinberger
c37b77855b
Merge pull request #464 from austinm911/fix/slack-thread-replies 
feat(slack): implement configurable reply threading
 2026-01-09 21:10:39 +00:00
Peter Steinberger
84046cbad8 fix(slack): mrkdwn + thread edge cases (#464) (thanks @austinm911) 2026-01-09 22:09:02 +01:00
Austin Mudd
b4663ed11c Slack: implement replyToMode threading for tool path 
- Add shared hasRepliedRef state between auto-reply and tool paths
- Extract buildSlackThreadingContext helper in agent-runner.ts
- Extract resolveThreadTsFromContext helper in slack-actions.ts
- Update docs with clear replyToMode table (off/first/all)
- Add tests for first mode behavior across multiple messages
 2026-01-09 21:59:51 +01:00
Peter Steinberger
42a0089b3b fix: require explicit system event session keys 2026-01-09 21:59:01 +01:00
Peter Steinberger
5fa26bfec7 feat: add per-agent elevated controls 2026-01-09 20:42:19 +00:00
Peter Steinberger
d3a0114b6b fix: dedupe followup queue by message id (#600) (thanks @samratjha96) 2026-01-09 20:44:11 +01:00
Samrat Jha
9185fdc896 fix(queue): deduplicate followup queue entries to prevent duplicate responses 
## Problem

When messages arrived while the agent was busy processing a previous message,
the same message could be enqueued multiple times into the followup queue.
This happened because Discord's event system can emit the same message multiple
times (e.g., during reconnects or due to slow listener processing), and the
followup queue had no deduplication logic.

This caused the bot to respond to the same user message 2-4+ times.

## Solution

Add simple exact-match deduplication in `enqueueFollowupRun()`: if a prompt
is already in the queue, skip adding it again. Extracted into a small
`isPromptAlreadyQueued()` helper for clarity.

## Testing

- Added test cases for deduplication (same prompt rejected, different accepted)
- Manually verified on Discord: single response per message even when multiple
  events fire during slow agent processing
 2026-01-09 20:40:18 +01:00
Peter Steinberger
2977b296e6 feat(messages): add whatsapp messagePrefix and responsePrefix auto 2026-01-09 19:29:04 +00:00
Peter Steinberger
72b0777341 fix(messages): restore explicit responsePrefix default 2026-01-09 19:18:34 +00:00
Peter Steinberger
fd15704c77 fix(auto-reply): coalesce block replies and document streaming toggles (#536) (thanks @mcinteerj) 2026-01-09 18:19:55 +00:00
Jake
a05916bee8 Config: add support for per-provider blockStreaming override 2026-01-09 18:11:27 +00:00
Peter Steinberger
cf1e0d743c fix: harden slash command registry 2026-01-09 17:53:24 +01:00
Luke
401f2a77e3
Merge branch 'main' into commands-list-clean 2026-01-09 11:46:08 -05:00
Peter Steinberger
1478473537 refactor(commands): canonicalize text command aliases 2026-01-09 17:22:46 +01:00
Peter Steinberger
1838582546 refactor(auto-reply): centralize chat command aliases 2026-01-09 17:16:52 +01:00
Peter Steinberger
d372fac9c6 refactor: streamline reply tag parsing 2026-01-09 17:14:40 +01:00
Peter Steinberger
cef13aa705
Merge pull request #586 from clawdbot/temp/landpr-492 
fix(commands): wire /usage alias to /status
 2026-01-09 16:14:11 +00:00
Peter Steinberger
68ad27e31c fix(commands): wire /usage to status (#492) (thanks @lc0rp) 2026-01-09 17:10:53 +01:00
Luke
4658f937cc
Merge branch 'main' into commands-list-clean 2026-01-09 11:06:06 -05:00
Peter Steinberger
67af3c3291
Merge pull request #560 from mcinteerj/fix/reply-tags-whitespace 
Auto-Reply: relax regex for reply tags to allow whitespace
 2026-01-09 16:05:17 +00:00
Luke
98b875cd0f
Merge branch 'main' into commands-list-clean 2026-01-09 11:04:23 -05:00
Peter Steinberger
7d9300e0f5 fix: allow whitespace in reply tags (#560) (thanks @mcinteerj) 2026-01-09 17:03:44 +01:00
LK
08caf7b9fc feat(commands): add /usage alias for /status 2026-01-09 17:02:29 +01:00
Jake
4381b03412 Auto-Reply: relax regex for reply tags to allow whitespace 2026-01-09 17:01:58 +01:00
Peter Steinberger
d099dabf37 refactor: centralize slack threading helpers 2026-01-09 16:01:53 +00:00
Peter Steinberger
be48233bc4 chore: format 2026-01-09 16:55:51 +01:00
Peter Steinberger
c643ce2a7a feat: add /debug runtime overrides 2026-01-09 16:55:16 +01:00
Peter Steinberger
36bdec0f2c refactor(messages): centralize per-agent prefixes 2026-01-09 16:54:54 +01:00
Peter Steinberger
8341b662af refactor(test): temp home env + normalize status 2026-01-09 16:50:09 +01:00
Peter Steinberger
c8b15af979 refactor(test): centralize temp home + polling 2026-01-09 16:49:02 +01:00
Peter Steinberger
09b602b4ec style: format trigger test 2026-01-09 16:41:05 +01:00
Peter Steinberger
4ffbd9802a refactor(test): consolidate temp home + vitest setup 2026-01-09 16:41:05 +01:00
Peter Steinberger
1eecce9a15
Merge pull request #578 from p6l-richard/feature/identity-based-message-prefix 
fix(messages): derive messagePrefix from identity.name
 2026-01-09 15:40:52 +00:00
Peter Steinberger
66bbb723c5 fix: derive prefixes from routed identity (#578) (thanks @p6l-richard) 2026-01-09 16:39:32 +01:00
Peter Steinberger
8de1c449ee
Merge pull request #558 from carlulsoe/mobile-ui-improvements 
feat(ui): improve mobile responsiveness [AI-assisted]
 2026-01-09 15:39:19 +00:00
Peter Steinberger
facf5c09a0 fix: honor slack reply threading (#574, thanks @bolismauro) 2026-01-09 15:38:43 +00:00
Peter Steinberger
b3e0fafe50 fix: stabilize windows CI (#558) (thanks @carlulsoe) 2026-01-09 16:37:58 +01:00
Mauro Bolis
96149d1f71 fix: honor slack reply threading 2026-01-09 15:35:54 +00:00
Peter Steinberger
922ca2ee1c fix(status): surface provider usage errors 2026-01-09 15:34:58 +00:00
Josh Palmer
25babbfdc4 🤖 codex: fix duplicate agentDir (no-issue) 2026-01-09 16:23:34 +01:00
Peter Steinberger
07430eb33d
Merge pull request #569 from bjesuiter/ui-build-default-to-relative-path 
fix(ui): default to relative paths for control UI assets
 2026-01-09 14:47:46 +00:00
Peter Steinberger
9af5b13803 test: make withTempHome cross-platform 2026-01-09 15:47:26 +01:00
Peter Steinberger
d77dee50c9
Merge pull request #570 from azade-c/feat/sessions-label 
feat(sessions): expose label in sessions.list and support label lookup in sessions_send
 2026-01-09 14:44:23 +00:00
Peter Steinberger
c4c0f1349a fix: keep build green after main rebase (#570) (thanks @azade-c) 2026-01-09 15:40:36 +01:00
Peter Steinberger
d17141b859 fix(status): show usage for token auth profiles 2026-01-09 14:36:46 +00:00
Peter Steinberger
1afa48fcdf style(models): biome format auth order 2026-01-09 14:36:46 +00:00
Peter Steinberger
59d942c9ec fix: unblock CI on main (#569) (thanks @bjesuiter) 2026-01-09 15:32:55 +01:00
Peter Steinberger
56e77f6843 fix: sessions label lookup and persistence (#570) (thanks @azade-c) 2026-01-09 15:32:49 +01:00
Azade
3133c7c84e feat(sessions): expose label in sessions.list and support label lookup in sessions_send 
- Add `label` field to session entries and expose it in `sessions.list`
- Display label column in the web UI sessions table
- Support `label` parameter in `sessions_send` for lookup by label instead of sessionKey

- `sessions.patch`: Accept and store `label` field
- `sessions.list`: Return `label` in session entries
- `sessions_spawn`: Pass label through to registry and announce flow
- `sessions_send`: Accept optional `label` param, lookup session by label if sessionKey not provided
- `agent` method: Accept `label` and `spawnedBy` params (stored in session entry)

- Add `label` column to sessions table in web UI

- Changed session store writes to merge with existing entry (`{ ...existing, ...new }`)
  to preserve fields like `label` that might be set separately

We attempted to implement label persistence "properly" by passing the label
through the `agent` call and storing it during session initialization. However,
the auto-reply flow has multiple write points that overwrite the session entry,
and making all of them merge-aware proved unreliable.

The working solution patches the label in the `finally` block of
`runSubagentAnnounceFlow`, after all other session writes complete.
This is a workaround but robust - the patch happens at the very end,
just before potential cleanup.

A future refactor could make session writes consistently merge-based,
which would allow the cleaner approach of setting label at spawn time.

```typescript
// Spawn with label
sessions_spawn({ task: "...", label: "my-worker" })

// Later, find by label
sessions_send({ label: "my-worker", message: "continue..." })

// Or use sessions_list to see labels
sessions_list() // includes label field in response
```
 2026-01-09 15:32:49 +01:00
Peter Steinberger
3e400ff9f2 feat(models): add per-agent auth order overrides 2026-01-09 14:07:45 +00:00
Peter Steinberger
b21e62f072 style: format gateway discovery 2026-01-09 13:55:28 +01:00
Peter Steinberger
c2d185aab7 fix: normalize routed replies 2026-01-09 13:55:27 +01:00
Peter Steinberger
7b81d97ec2 feat: wire multi-agent config and routing 
Co-authored-by: Mark Pors <1078320+pors@users.noreply.github.com>
 2026-01-09 12:48:42 +00:00
Onur
0bc50abd73 style: format quickstart note and media-note test 2026-01-09 11:07:00 +01:00
Onur
c469fac8ef Tests: speed up media note prompt setup 2026-01-09 11:07:00 +01:00
Onur
1df7bfefe7 MSTeams: stop on shutdown and honor chunk limit 2026-01-09 11:07:00 +01:00
Onur
2ab5890eab wip 2026-01-09 11:06:49 +01:00
Onur
d6256a388e feat(msteams): wire up proactive messaging in routeReply for queued replies 2026-01-09 11:06:49 +01:00
Onur
1c73d45106 feat(msteams): wire agent integration for Teams messages 
- Integrate dispatchReplyFromConfig() for full agent routing
- Add msteams to TextChunkProvider and OriginatingChannelType
- Add msteams case to route-reply (proactive not yet supported)
- Strip @mention HTML tags from Teams messages
- Fix session key to exclude messageid suffix
- Add typing indicator support
- Add proper logging for debugging
 2026-01-09 11:05:34 +01:00
Luke K (pr-0f3t)
5f4df5e336 Auto-reply: drop native command flag 2026-01-09 04:14:36 -05:00
Luke
aa64abe84c
Merge branch 'main' into commands-list-clean 2026-01-09 03:12:08 -05:00
Peter Steinberger
37cbcc97d3 feat: support token auth profiles 2026-01-09 08:13:04 +01:00
Peter Steinberger
0a026fea1c fix: disable restart by default 2026-01-09 05:49:30 +00:00
Peter Steinberger
8e35ad5484 style: format after gate 2026-01-09 05:27:54 +00:00
Peter Steinberger
31a2830f7d fix: support /models alias for /model 2026-01-09 06:24:40 +01:00
Peter Steinberger
7842109609 fix: report auth label from configured order 2026-01-09 05:17:27 +00:00
Peter Steinberger
9114331218 fix: serialize claude cli runs 2026-01-09 04:58:21 +00:00
Luke
a4806e9417
Merge branch 'main' into commands-list-clean 2026-01-08 23:21:31 -05:00
Luke K (pr-0f3t)
5d34e27078 Revert: non-PR file edits 2026-01-08 23:19:44 -05:00
Peter Steinberger
64fc5fa9fc fix: allow default model outside allowlist 2026-01-09 04:18:30 +00:00
Luke K (pr-0f3t)
16f893c46b Tests: align google shared expectations 2026-01-08 23:12:37 -05:00
Peter Steinberger
7e4d5c9f84 test: align status and google-shared expectations 2026-01-09 05:03:12 +01:00
Luke
1be8a39442
Merge branch 'main' into commands-list-clean 2026-01-08 22:58:54 -05:00
Luke K (pr-0f3t)
1309cee124 Auto-reply: fix status command lint 2026-01-08 22:51:35 -05:00
Luke K (pr-0f3t)
8aa80fa464 Auto-reply: tidy help message 2026-01-08 22:48:46 -05:00
Peter Steinberger
8e27ea7371 feat: add raw stream logging flags 2026-01-09 03:45:21 +00:00
Peter Steinberger
69546d563d fix: combine status usage and cost line 2026-01-09 03:45:01 +00:00
Luke
b97a9235e0
Merge branch 'main' into commands-list-clean 2026-01-08 22:19:52 -05:00
Peter Steinberger
3e19f82af2 fix: repair status reply call 2026-01-09 03:18:20 +00:00
Peter Steinberger
d8a23cf5ab fix: restore emoji-rich status output 2026-01-09 03:15:33 +00:00
Luke K (pr-0f3t)
6c8b2a8dc9 Auto-reply: organize status imports 2026-01-08 22:14:24 -05:00
Peter Steinberger
b3b84ffefa fix: fallback /model list when catalog is unavailable 2026-01-09 03:56:19 +01:00
Luke
e52a2888cc
Merge branch 'main' into commands-list-clean 2026-01-08 21:47:09 -05:00
Peter Steinberger
0cbc5fea93 fix: keep status for directive-only messages 2026-01-09 03:46:00 +01:00
Peter Steinberger
dc81d0a649 fix: improve /status auth label 2026-01-09 03:39:02 +01:00
Peter Steinberger
3c79d5c711 fix: keep /status usage filtering 2026-01-09 03:31:02 +01:00
Peter Steinberger
151523f47b feat: add usage cost reporting 2026-01-09 02:29:54 +00:00
Peter Steinberger
1a295d9460 fix: improve status usage filtering and directives 2026-01-09 03:18:47 +01:00
Peter Steinberger
468889abef fix: refine status usage and elevated directives 2026-01-09 03:09:56 +01:00
Luke
c678216ac2
Merge branch 'main' into commands-list-clean 2026-01-08 20:58:26 -05:00
Peter Steinberger
455723375e fix: show directive options on query 2026-01-09 01:40:44 +01:00
Luke
daafa9e3bc
Merge branch 'main' into commands-list-clean 2026-01-08 19:33:56 -05:00
Peter Steinberger
27adabbeea test: cover reasoning directive spacing (thanks @joshp123) (#539) 2026-01-09 00:51:05 +01:00
Peter Steinberger
f666f60731 fix: preserve inline directive spacing tests (thanks @joshp123) (#539) 2026-01-09 00:37:40 +01:00
Josh Palmer
43545a4864 🤖 codex: preserve spacing after inline directives (issue-telegram-inline-spacing) 2026-01-09 00:37:40 +01:00
Peter Steinberger
a33271d374 refactor: share paren-aware chunk break scan 2026-01-08 23:09:34 +01:00
Peter Steinberger
b48ed56635 test: add DM elevated regression coverage 2026-01-08 22:58:15 +01:00
Peter Steinberger
014667e00b fix: tighten group elevated targeting 2026-01-08 22:57:18 +01:00
Luke
a574ae5415
Merge branch 'main' into commands-list-clean 2026-01-08 15:35:17 -05:00
Peter Steinberger
4a918ccf47 fix: avoid splitting outbound chunks inside parentheses (#499) — thanks @philipp-spiess 2026-01-08 20:39:28 +01:00
Philipp Spiess
4082b90aa4 Chunking: avoid splits inside parentheses 2026-01-08 20:38:00 +01:00
Peter Steinberger
ba19173b96 test: cover status model provider prefix 2026-01-08 20:23:38 +01:00
Keith the Silly Goose
7866203c5c fix(status): include provider prefix in model display 
The /status command was showing 'anthropic/claude-sonnet-4-5' even when
using 'google-antigravity/claude-sonnet-4-5' because buildStatusMessage
received only the model name without the provider prefix.

When resolveConfiguredModelRef parsed a model string without a slash,
it fell back to DEFAULT_PROVIDER ('anthropic'), causing the misleading
display.

Fix: Pass the full 'provider/model' string to buildStatusMessage so
the provider is correctly extracted and displayed.

🪿 Investigated and submitted by Keith the Silly Goose
 2026-01-08 20:11:37 +01:00
Josh Palmer
cc94db458c
🤖 codex: fix block reply ordering (#503) 
What: serialize block reply sends, make typing non-blocking, add timeout fallback + abort-aware routing, and add regression tests.
Why: prevent out-of-order streamed blocks while keeping final fallback on timeouts.
Tests: ./node_modules/.bin/vitest run src/auto-reply/reply.block-streaming.test.ts src/auto-reply/reply/route-reply.test.ts
Tests: corepack pnpm lint && corepack pnpm build (pass). corepack pnpm test (ran locally; failure observed during run).

Co-authored-by: Josh Palmer <joshp123@users.noreply.github.com>
 2026-01-08 19:30:24 +01:00
Luke K (pr-0f3t)
713eb898f6 Removed compact command changes from elsewhere 2026-01-08 10:41:09 -05:00
Luke
8445c9a5e8
Removing stray commits 2026-01-08 10:33:11 -05:00
LK
559e175b38 feat(commands): add /commands slash list 2026-01-08 16:23:36 +01:00
Peter Steinberger
bce3cc992f fix: group /model list output 2026-01-08 09:44:59 +01:00
Peter Steinberger
8930ec32cb feat: add slack multi-account routing 2026-01-08 08:49:16 +01:00
Peter Steinberger
00c1403f5c fix: unblock ci 2026-01-08 07:41:39 +00:00
Peter Steinberger
d1ceb3aa60 feat: add logs cli and restart hints 2026-01-08 06:56:34 +00:00
Peter Steinberger
6a81652ebf fix(typing): keep tool-start ttl mode-safe (#452, thanks @thesash) 2026-01-08 06:18:35 +00:00
Sash Catanzarite
29c5ed54b2 feat(typing): trigger indicator on tool start events 
Add signalToolStart to TypingSignaler and call it from onAgentEvent
when tools begin executing. This keeps the typing indicator visible
during long-running tool operations.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-01-08 06:18:35 +00:00
Sash Catanzarite
a6a550032a fix(typing): refresh TTL on every startTypingLoop call 
Previously, startTypingLoop would return early if the typing timer was
already running, which meant the TTL would never get refreshed during
long tool executions. This caused the typing indicator to stop after
2 minutes even if tools were still running.

Now we refresh the TTL at the start of startTypingLoop, before the
early-return checks. This keeps typing alive during long operations.
 2026-01-08 05:45:46 +01:00
Peter Steinberger
dc3e3f27d4 style: apply lint fixes 2026-01-08 04:44:15 +00:00
Peter Steinberger
5b45a143a1 fix: stabilize media paths and logs 2026-01-08 04:41:01 +00:00
Peter Steinberger
9c9d191d6f feat: improve cli setup flow 2026-01-08 05:33:54 +01:00
Peter Steinberger
4ef2fd328d test: cover multi-media prompt note 2026-01-08 05:30:04 +01:00
Peter Steinberger
ab8db941d0 feat: expand inbound media notes 2026-01-08 05:20:39 +01:00
Peter Steinberger
15379dedf0 fix(telegram): voice-note tag defaults (#188, thanks @manmal) 2026-01-08 03:15:08 +00:00
Manuel Maly
2972fce02c fix: flip audio default to file (backward compat) 
- Default: sendAudio (file with metadata) - preserves old behavior
- Opt-in: [[audio_as_voice]] tag for voice bubble

This is non-breaking - existing integrations keep working.
 2026-01-08 03:15:08 +00:00
Manuel Maly
262f8a8d45 feat(telegram): add [[audio_as_file]] tag support 
Allow agents to specify audio mode via inline tag:
- Default: voice bubble (sendVoice)
- [[audio_as_file]]: audio file with metadata (sendAudio)

The tag is stripped from the final message text.

Example agent response:
  Here's a podcast episode! [[audio_as_file]]
  MEDIA:https://example.com/episode.mp3
 2026-01-08 03:15:08 +00:00
Manuel Maly
5e1b91b32c feat(telegram): wire audioAsVoice through bot.ts 
- Add audioAsVoice option to ReplyPayload type
- Update bot.ts to use sendVoice by default for audio (voice bubble)
- When audioAsVoice is false, use sendAudio (file with metadata)

This allows agents to control voice vs file mode via ReplyPayload.
 2026-01-08 03:15:08 +00:00
Peter Steinberger
6e4174b5dc fix(ci): stabilize windows paths 2026-01-08 03:03:03 +00:00
Peter Steinberger
8aa3efb9e8 refactor: tidy directive parsing + queue status 2026-01-08 03:47:52 +01:00
Peter Steinberger
fbeb9e6775 fix(ci): stabilize windows tests 2026-01-08 02:44:19 +00:00
Peter Steinberger
780385e31f fix(auto-reply): handle /think no-arg 2026-01-08 03:39:05 +01:00
Peter Steinberger
ad5c87c193 fix: relax slash command parsing 2026-01-08 03:24:18 +01:00
Lutro
36b443f4f3 Telegram: fix /think command to show current level when no arg 2026-01-08 03:24:18 +01:00
Peter Steinberger
a450390f7c refactor: share reply payload threading/dedupe 2026-01-08 01:09:23 +00:00
Peter Steinberger
05b8679c8b feat: add providers CLI and multi-account onboarding 2026-01-08 01:55:59 +01:00
Peter Steinberger
17d052bcda fix: polish reply threading + tool dedupe (thanks @mneves75) (#326) 2026-01-08 00:50:47 +00:00
mneves75
33e2d53be3 feat(telegram): wire replyToMode config, add forum topic support, fix messaging tool duplicates 
Changes:
- Default replyToMode from "off" to "first" for better threading UX
- Add messageThreadId and replyToMessageId params for forum topic support
- Add messaging tool duplicate detection to suppress redundant block replies
- Add sendMessage action to telegram tool schema
- Add @grammyjs/types devDependency for proper TypeScript typing
- Remove @ts-nocheck and fix all type errors in send.ts
- Add comprehensive docs/telegram.md documentation
- Add PR-326-REVIEW.md with John Carmack-level code review

Test coverage:
- normalizeTextForComparison: 5 cases
- isMessagingToolDuplicate: 7 cases
- sendMessageTelegram thread params: 5 cases
- handleTelegramAction sendMessage: 4 cases
- Forum topic isolation: 4 cases

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-08 00:50:47 +00:00
Peter Steinberger
b2de667b11 fix: persist topic session files 2026-01-07 22:56:50 +00:00
hsrvc
8da4f259dd Implement Phase 2: Topic-level message history isolation for multi-topic Telegram support 
Add topic-specific session file isolation to fix root cause of Gemini turn validation errors.
Each Telegram topic now maintains its own conversation history file, eliminating race
conditions and message corruption during concurrent topic processing.

Changes:
1. Enhanced resolveSessionTranscriptPath() to support optional topicId parameter
   - Topic ID (Telegram messageThreadId) now incorporated into session filename
   - Format: sessionId.jsonl (direct chats) vs sessionId-topic-{topicId}.jsonl (topics)
   - Backward compatible: topicId is optional

2. Updated reply.ts to pass MessageThreadId to session file resolution
   - ctx.MessageThreadId now flows through to resolveSessionTranscriptPath()
   - Automatically provides topic context for each incoming message

3. Automatic propagation through entire system
   - sessionFile parameter automatically carries topic-specific path through:
     - FollowupRun object (queued runs)
     - runEmbeddedPiAgent() calls
     - compactEmbeddedPiSession() calls
     - SessionManager lifecycle (load, read, write operations)

Benefits:
✓ Complete elimination of shared .jsonl race conditions
✓ Each topic's conversation history independently cached
✓ SessionManager instances operate on isolated files
✓ No concurrent mutations of the same message history
✓ Maintains full Phase 1 turn validation as safety layer

Testing:
✓ Build succeeds with no TypeScript errors
✓ Backward compatible with non-topic sessions (direct messages)
✓ Topic ID properly extracted from Telegram messageThreadId

Expected impact:
- Gemini "function call turn" errors eliminated (root cause fixed)
- Message history corruption prevented across all topics
- Improved stability in multi-topic scenarios
- Each topic maintains independent conversation state

This completes the two-phase fix:
- Phase 1 (previous): Turn validation to suppress errors
- Phase 2 (current): Topic isolation to fix root cause

🤖 Generated with Claude Code

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
 2026-01-07 22:51:26 +00:00
Peter Steinberger
434c25331e refactor: centralize typing mode signals 2026-01-07 22:18:11 +00:00
Peter Steinberger
bac1608933 feat: add typing mode controls 2026-01-07 21:58:54 +00:00
Peter Steinberger
7ce1f635cd fix(commands): harden model alias parsing 2026-01-07 20:41:41 +00:00
Azade
bb29a3ee3f fix: filter reserved commands from model aliases + add tests 2026-01-07 20:41:41 +00:00
Azade
e41540e4ff feat(commands): add dynamic /<alias> model switching 2026-01-07 20:41:41 +00:00
Peter Steinberger
cb9f8146c4 refactor: centralize thread helpers 2026-01-07 20:01:19 +01:00
Peter Steinberger
8584bcd2f6 Merge remote-tracking branch 'origin/main' 2026-01-07 19:44:26 +01:00
Peter Steinberger
0d021391a9 fix: scope thread sessions and discord starter fetch 2026-01-07 19:42:50 +01:00
Peter Steinberger
aba4695cd1 test(status): cover model override display 2026-01-07 18:38:55 +00:00
Azade
2b09cb3d9f fix(status): show configured model instead of last-run model 2026-01-07 18:37:42 +00:00
Shadow
7e5cef29a0 Threads: add Slack/Discord thread sessions 2026-01-07 19:30:30 +01:00
Peter Steinberger
1011640a13 refactor: drop autoReply, add topic requireMention 
Co-authored-by: kitze <kristijan.mkd@gmail.com>
 2026-01-07 12:07:15 +01:00
Peter Steinberger
eef90b47a3 chore: satisfy lint 2026-01-07 11:49:01 +01:00
Peter Steinberger
43c6bb7595 feat: add channel/topic overrides for skills + auto-reply 2026-01-07 11:44:37 +01:00
Peter Steinberger
61f720b945 feat: add skill filter + group system prompt plumbing 2026-01-07 11:44:37 +01:00
Peter Steinberger
9bf6684366 feat: add provider usage tracking 2026-01-07 11:42:46 +01:00
Peter Steinberger
a700f9896d feat: telegram draft streaming 2026-01-07 11:08:32 +01:00
Peter Steinberger
e8420bd047 fix: refine bootstrap injections 2026-01-07 10:04:23 +00:00
Tobias Bischoff
412990a139 Reduce prompt token overhead with leaner context injections 2026-01-07 10:04:23 +00:00
Peter Steinberger
7973fd4caf feat: add agents command 2026-01-07 10:03:53 +01:00
Peter Steinberger
8b1263ce11 fix: split status activation line 2026-01-07 07:26:52 +01:00
Peter Steinberger
dc941b7e57 fix: refresh status output 2026-01-07 07:22:06 +01:00
Peter Steinberger
1673a221f8 feat: add /reasoning reasoning visibility 2026-01-07 06:17:31 +01:00
Peter Steinberger
cb2a72f8a9 test(routing): add route-reply coverage 2026-01-07 05:07:53 +00:00
Peter Steinberger
3668388912 fix(routing): harden originating reply routing 2026-01-07 05:02:34 +00:00
Josh Lehman
5414da9fd4 fix(routing): handle cross-provider messages in collect mode 
When queued messages come from different providers (Slack + Telegram),
process them individually instead of collecting into a single prompt.
This ensures each reply routes back to its originating provider.

- Add hasCrossProviderItems() to detect multi-provider queues
- Skip collect mode when cross-provider detected
- Preserve originatingChannel/originatingTo when collecting same-provider
 2026-01-07 04:51:33 +00:00
Josh Lehman
2d67ec5bfa fix(routing): only route to originating channel when cross-provider 
When OriginatingChannel matches Surface (same provider), use normal
dispatcher. Only route via routeReply() when they differ, ensuring
cross-provider messages (e.g., Telegram queued while Slack active)
get routed back to their origin.
 2026-01-07 04:51:33 +00:00
Josh Lehman
9d50ebad7d feat(routing): route replies to originating channel 
Implement reply routing based on OriginatingChannel/OriginatingTo fields.
This ensures replies go back to the provider where the message originated
instead of using the session's lastChannel.

Changes:
- Add OriginatingChannel/OriginatingTo fields to MsgContext (templating.ts)
- Add originatingChannel/originatingTo fields to FollowupRun (queue.ts)
- Create route-reply.ts with provider-agnostic router
- Update all providers (Telegram, Slack, Discord, Signal, iMessage)
  to pass originating channel info
- Update reply.ts to pass originating channel to followupRun
- Update followup-runner.ts to use route-reply for originating channels

This addresses the issue where messages from one provider (e.g., Slack)
would receive replies on a different provider (e.g., Telegram) because
the queue used the last active dispatcher instead of the originating one.
 2026-01-07 04:51:33 +00:00
Peter Steinberger
80112433a5 fix(telegram): support forum topics 
Co-authored-by: Daniel Griesser <HazAT@users.noreply.github.com>
Co-authored-by: Nacho Iacovino <nachoiacovino@users.noreply.github.com>
Co-authored-by: Randy Ventures <RandyVentures@users.noreply.github.com>
 2026-01-07 02:19:42 +00:00
Peter Steinberger
dd0d23cd96 test(commands): add /stop native regression 2026-01-06 23:11:57 +00:00
Peter Steinberger
e0efcda77f fix(commands): wire /stop across chat commands 2026-01-06 23:11:57 +00:00
Peter Steinberger
fec7f37271 merge upstream/main 2026-01-06 23:09:01 +01:00
Peter Steinberger
86b56b2308 fix: harden gemini session reset 2026-01-06 23:06:01 +01:00
Peter Steinberger
7aa7fa79d0 feat: update heartbeat defaults 2026-01-06 21:54:42 +00:00
Peter Steinberger
96164b5955 fix: improve socket error handling 2026-01-06 22:43:29 +01:00
Emanuel Stadler
fb17a32283 feat: enhance error handling for socket connection errors 
- Added `isError` property to `EmbeddedPiRunResult` and reply items to indicate error states.
- Updated error handling in `runReplyAgent` to provide more informative messages for specific socket connection errors.
 2026-01-06 22:19:37 +01:00
Peter Steinberger
84c8209158 fix(slack): clear assistant thread status after replies 2026-01-06 21:41:30 +01:00
Shadow
9b22e1f6e9
feat(commands): unify chat commands (#275) 
* Chat commands: registry, access groups, Carbon

* Chat commands: clear native commands on disable

* fix(commands): align command surface typing

* docs(changelog): note commands registry (PR #275)

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
 2026-01-06 20:17:56 +00:00
Peter Steinberger
67bda21811 fix: preserve markdown fences when chunking 2026-01-06 20:23:41 +01:00
Peter Steinberger
31dbc62bdd fix(telegram): prevent stuck typing after tool runs 2026-01-06 18:56:43 +00:00
Abhi
bdf597eb95
fix(telegram): stop typing after tool results (#322) 
Thanks @AbhisekBasu1.
 2026-01-06 18:54:08 +00:00
Peter Steinberger
2f24ea492b fix: restore Anthropic token accounting 2026-01-06 18:52:01 +00:00
Peter Steinberger
dbfa316d19 feat: multi-agent routing + multi-account providers 2026-01-06 18:33:37 +00:00
Onur
6cf3570c5b
feat(agent): add skipBootstrap config to skip bootstrap file creation (#292) 2026-01-06 11:02:51 -06:00
VAC
eadb923000 fix: auto-recover from Gemini session corruption 
Detect the Gemini API error 'function call turn comes immediately after
a user turn or after a function response turn' which indicates corrupted
session history.

When detected:
- Delete the corrupted transcript file
- Remove the session entry from the store
- Return a user-friendly message asking them to retry

This prevents the error loop where every subsequent message fails with
the same error until manual intervention.

Fixes #296
 2026-01-06 07:25:15 -05:00
Peter Steinberger
b5c604b7b7 fix: require slash for control commands 2026-01-06 07:05:17 +01:00
Shadow
88cb13dc82
Auto-reply: fix typing stop race (#270) 2026-01-05 22:57:04 -06:00
Peter Steinberger
ea6ee16461 chore: fix lint warnings 2026-01-06 05:41:24 +01:00
Ayaan Zaidi
bd735182b6
feat(telegram): support media groups (multi-image messages) (#220) 2026-01-05 22:04:33 -06:00
Peter Steinberger
13eb9c9ee9 refactor: centralize reply dispatch 2026-01-06 04:55:00 +01:00
Peter Steinberger
5946f4c341 test: extend typing idle coverage 2026-01-06 03:42:33 +00:00
Peter Steinberger
58186aa56e test: cover typing idle gate 2026-01-06 03:28:47 +00:00
Peter Steinberger
ca8f66f844 refactor: unify group allowlist policy 2026-01-06 04:27:51 +01:00
Peter Steinberger
9d656f4269 style: satisfy lint 2026-01-06 03:11:42 +00:00
Peter Steinberger
d5f088978a fix: stop typing after dispatcher idle 2026-01-06 03:09:49 +00:00
Peter Steinberger
20a361a3cf refactor: centralize agent timeout defaults 2026-01-06 02:48:44 +00:00
Peter Steinberger
b30bae89ed feat: track compaction count + verbose notice 2026-01-06 02:49:03 +01:00
Peter Steinberger
b6ae376076 fix: gate reset auth and infer whatsapp sender 2026-01-06 02:23:55 +01:00
Peter Steinberger
b56338171b feat: gate slash commands and add compact 2026-01-06 02:23:55 +01:00
Peter Steinberger
e73573eaea fix: clean model config typing 2026-01-06 01:08:36 +00:00
Peter Steinberger
b04c838c15 feat!: redesign model config + auth profiles 2026-01-06 00:56:58 +00:00
Peter Steinberger
d813e14950 chore: update mention gating docs and tests 2026-01-06 01:38:36 +01:00
Peter Steinberger
811ec8b78b fix: unify mention gating across providers 2026-01-06 01:32:17 +01:00
Peter Steinberger
ac3dedaa1b feat: standardize timestamps to UTC 2026-01-05 23:03:59 +00:00
Peter Steinberger
f790f3f3ba
fix/heartbeat ok delivery filter (#246) 
* cron: skip delivery for HEARTBEAT_OK responses

When an isolated cron job has deliver:true, skip message delivery if the
response is just HEARTBEAT_OK (or contains HEARTBEAT_OK at edges with
short remaining content <= 30 chars). This allows cron jobs to silently
ack when nothing to report but still deliver actual content when there
is something meaningful to say.

Media is still delivered even if text is HEARTBEAT_OK, since the
presence of media indicates there's something to share.

* fix(heartbeat): make ack padding configurable

* chore(deps): update to latest

---------

Co-authored-by: Josh Lehman <josh@martian.engineering>
 2026-01-05 22:52:13 +00:00
Peter Steinberger
53bf8b7b80 fix: avoid duplicate missing auth label 2026-01-05 23:00:37 +01:00
Peter Steinberger
c75b2a7067 refactor: unify reply dispatch across providers 2026-01-05 19:43:54 +01:00
Peter Steinberger
b7e708c764 fix(chat): stabilize web UI tool runs 2026-01-05 17:22:29 +00:00
Peter Steinberger
86c404c48b chore: fix reply commands lint 2026-01-05 18:16:39 +01:00
Peter Steinberger
7f3f73af1c fix: show model auth in status 2026-01-05 15:50:18 +01:00
Peter Steinberger
bf6aad1965 fix(ci): format directive-handling 2026-01-05 14:34:55 +00:00
Peter Steinberger
0c37f27a4a fix: show /model auth source 2026-01-05 14:14:26 +00:00
Peter Steinberger
cffbe79077 fix: add /model list alias 2026-01-05 14:11:33 +00:00
Peter Steinberger
8e8d07cbf4 fix(ci): satisfy formatter checks 2026-01-05 13:55:53 +00:00
Peter Steinberger
7619534bc0 feat(groups): resolve requireMention for discord/slack 2026-01-05 13:55:32 +00:00
Peter Steinberger
ce68d82dfa fix: widen /model key masking 2026-01-05 13:50:45 +00:00
Peter Steinberger
5163886694 fix: show auth in /model list 2026-01-05 13:49:25 +00:00
Peter Steinberger
5431a9c692 fix: clean status + help + mid alias 2026-01-05 07:24:51 +01:00
Peter Steinberger
9be1a14a08 fix: resolve agent dir in onboarding 2026-01-05 07:12:13 +01:00
Peter Steinberger
17ef7b3b0e fix: status runtime + help 2026-01-05 07:07:17 +01:00
Peter Steinberger
995f5959af fix: stage sandbox media for inbound attachments 2026-01-05 06:18:11 +01:00
Peter Steinberger
67420e9a81 fix: allow group activation for allowFrom senders 2026-01-05 02:33:51 +01:00
Peter Steinberger
359cb66e68 fix: allow wildcard control commands 2026-01-05 02:06:18 +01:00
Peter Steinberger
17422608b2 fix: gate /activation to owners in groups 2026-01-05 02:03:29 +01:00
Peter Steinberger
85549ac3b6 fix: gate group activation by owner 2026-01-05 00:48:16 +00:00
Peter Steinberger
1bad96aa2b style: tidy auto-reply imports and formatting 2026-01-05 01:46:16 +01:00
Peter Steinberger
852f947b44 fix: unify control command handling 2026-01-05 01:31:36 +01:00
Jake
946b32c842
fix(whatsapp): suppress typing during heartbeats 
- Prevent typing indicator during heartbeat runs
- Add regression tests

Co-authored-by: Jake <mcinteerj@gmail.com>
 2026-01-04 23:03:36 +00:00
Peter Steinberger
1657c5e3d2 fix: route system events per session 2026-01-04 22:11:04 +01:00
Peter Steinberger
ff46f8ce58 chore: format models CLI 2026-01-04 18:11:41 +01:00
Peter Steinberger
734bb6b4fd feat: add models scan and fallbacks 2026-01-04 17:57:52 +01:00
Cash Williams
64e656af82 fix: default elevated level to 'off' when not allowed 
When elevatedAllowed is false (e.g., for heartbeat surface which isn't
in any allowFrom list), the elevated level was incorrectly defaulting
to 'on', causing bash commands to fail with 'elevated is not available'.

Now defaults to 'off' when elevated isn't allowed, so bash works
normally without trying to use elevated mode.

Fixes: https://github.com/clawdbot/clawdbot/issues/181
 2026-01-04 17:36:14 +01:00
Peter Steinberger
c6b8235862 style: format tests and helpers 2026-01-04 14:57:57 +00:00
Peter Steinberger
246adaa119 chore: rename project to clawdbot 2026-01-04 14:38:51 +00:00
Shadow
8c38a7fee8
Slack: add some fixes and connect it all up 2026-01-04 01:53:26 -06:00
Peter Steinberger
607de4a403 fix: add slack chunk limits 2026-01-04 07:23:39 +01:00
Shadow
bf3d120f8c Slack: add new slack connection 2026-01-04 07:18:20 +01:00
Peter Steinberger
c9504a6f20 refactor: split config module 2026-01-04 07:05:17 +01:00
Peter Steinberger
5e36e2c3f3 fix: allow elevated via discord username 2026-01-04 05:47:28 +00:00
Peter Steinberger
d2da305190 feat: fallback elevated allowlist to discord dms 2026-01-04 05:31:00 +00:00
Peter Steinberger
ff88f3c075 style: fix lint ordering 2026-01-04 06:27:54 +01:00
Peter Steinberger
a03895dfa9 fix: default elevated mode to on 2026-01-04 05:19:28 +00:00
Peter Steinberger
fe0b3500cc feat: add elevated bash mode 2026-01-04 05:15:59 +00:00
Peter Steinberger
72a9e58777 refactor(auto-reply): split reply flow 2026-01-04 05:47:37 +01:00
Peter Steinberger
a1780efb9f fix: adjust typing TTL 2026-01-04 00:26:31 +00:00
Peter Steinberger
86038ec165 chore: apply lint fixes 2026-01-04 00:06:02 +01:00
Peter Steinberger
e7c9b9a749 feat: add sessions tools and send policy 2026-01-03 23:44:42 +01:00
Peter Steinberger
934f891932 fix: include embedded agent error cause in reply 2026-01-03 21:30:43 +00:00
Peter Steinberger
a15cffb7de fix: stream tool summaries early and tool output 2026-01-03 21:04:40 +01:00
Shadow
ce92fac983
chore: formatting 2026-01-03 12:35:16 -06:00
Peter Steinberger
217b84f2ac fix: drop final payloads after block streaming 2026-01-03 17:55:31 +01:00
Peter Steinberger
f313af75e9 fix: avoid duplicate block-stream payloads 2026-01-03 16:53:56 +00:00
Peter Steinberger
200dd634fb fix: preserve block streaming order 2026-01-03 17:14:01 +01:00
Peter Steinberger
3bbdcaf87f fix: avoid duplicate block streaming 2026-01-03 17:10:47 +01:00
Peter Steinberger
9f8eeceae7 feat: soften block streaming chunking 2026-01-03 16:48:26 +01:00
Peter Steinberger
53baba71fa feat: unify onboarding + config schema 2026-01-03 16:48:08 +01:00
Peter Steinberger
733e86516e fix: address runtime warnings in build 2026-01-03 15:01:38 +00:00
Peter Steinberger
1a00175eb7 chore: fix lint formatting 2026-01-03 14:57:49 +00:00
Peter Steinberger
77c76ca52f test: fix transcription and tool schema assertions 2026-01-03 14:55:05 +00:00
Peter Steinberger
48731f494b fix: add embedded run logs and typing ttl 2026-01-03 14:09:19 +00:00
Peter Steinberger
bb54e60179 fix(logging): decouple file logs from console verbose 2026-01-03 12:32:14 +00:00
Peter Steinberger
e52bdaa2a2 fix: repair tool meta regex 2026-01-03 12:30:46 +00:00
Peter Steinberger
b6301c719b fix: default low thinking for reasoning models 2026-01-03 12:19:06 +00:00
Peter Steinberger
6e16c0699a feat: centralize tool display metadata 2026-01-03 13:18:27 +01:00
Peter Steinberger
7a80e8fe77 refactor: centralize home path shortening 2026-01-03 12:42:27 +01:00
Peter Steinberger
1ec3512925 refactor!: drop clawdis_ tool prefix 2026-01-03 12:39:52 +01:00
Peter Steinberger
772ada4308 fix: refine tool summaries and scope discord tool 2026-01-03 12:33:42 +01:00
Peter Steinberger
b914eaa6fa chore: apply biome lint fixes 2026-01-03 05:10:09 +01:00
Peter Steinberger
988b67aa30 test: refresh auto-reply expectations 2026-01-03 05:09:59 +01:00
Peter Steinberger
971b98c96d test: cover new queue modes 2026-01-03 04:47:34 +01:00
Peter Steinberger
ac36eba822 feat: expand queue modes and followup backlog 2026-01-03 04:26:49 +01:00
Peter Steinberger
1781105438 group chat: hint that reactions are welcome while lurking 
Even when staying silent, emoji reactions show engagement without cluttering chat.
 2026-01-03 02:29:32 +00:00
Peter Steinberger
632ca01fbf style: format linted files 2026-01-03 03:10:17 +01:00
Peter Steinberger
a3865f1417 group chat: add lurking guidance to system prompt 
Be a good group participant: lurk and follow the conversation,
but only chime in when genuinely helpful. Quality over quantity.
 2026-01-03 02:02:55 +00:00
Peter Steinberger
0c013a237f fix: default block streaming break to message_end 2026-01-03 01:33:10 +00:00
Peter Steinberger
3368fcf31e fix: avoid duplicate replies with block streaming 2026-01-03 02:16:01 +01:00
Peter Steinberger
f5189cc897 refactor: move text chunk limits to providers 2026-01-03 01:49:27 +01:00
Peter Steinberger
5684e2d658 feat: configurable outbound text chunk limits 2026-01-03 01:49:27 +01:00
Peter Steinberger
2d28fa34f5 feat: make block streaming break configurable 2026-01-03 01:49:27 +01:00
Peter Steinberger
59601eb99c fix: preserve newlines in reply tags 2026-01-02 23:36:43 +00:00
Peter Steinberger
9616f4b2b1 feat: stream reply blocks immediately 2026-01-03 00:28:33 +01:00
Peter Steinberger
2c92ccd66e feat: add reply tags and replyToMode 2026-01-02 23:18:41 +01:00
Peter Steinberger
a9ff03acaf feat: unify group mention defaults 2026-01-02 22:50:58 +01:00
Peter Steinberger
5cf1a9535e feat: move group mention gating to provider groups 2026-01-02 22:24:26 +01:00
Peter Steinberger
8989bd9fd7 fix(auto-reply): default whatsapp self-only on empty config 2026-01-02 17:15:26 +01:00
Peter Steinberger
314164fb8a chore: fix lint and add gateway auth tests 2026-01-02 17:15:26 +01:00
Shadow
b135b3efb9 Discord: add slash command handling 2026-01-02 13:38:35 +01:00
Peter Steinberger
0766c5e3cb refactor: move whatsapp allowFrom config 2026-01-02 13:00:29 +01:00
Peter Steinberger
b50df6eb1d style: format linted files 2026-01-02 12:20:38 +01:00
Peter Steinberger
eb44ae76f1 feat: add discord guild map + group dm controls 2026-01-02 11:15:52 +01:00
Peter Steinberger
9adbf47773 refactor: normalize group session keys 2026-01-02 10:14:58 +01:00
Peter Steinberger
4c2812b429 fix: refine HEARTBEAT_OK handling 2026-01-02 01:42:27 +01:00
Peter Steinberger
c0976ec099 fix(gateway): stream chat events for agent runs 2026-01-02 01:04:59 +01:00
Peter Steinberger
06e379a239 fix: suppress stray HEARTBEAT_OK replies 2026-01-01 23:53:29 +01:00
Peter Steinberger
dc8f2bda2a fix: restart via systemd on linux 2026-01-01 17:48:28 +01:00
Peter Steinberger
91c9859000 fix: harden heartbeat acks + gateway reconnect 2025-12-27 20:02:27 +00:00
Peter Steinberger
cae78b3f91 fix: treat /model status as model list 2025-12-27 12:10:44 +00:00
Peter Steinberger
c0fb814658 fix: normalize imports for lint 2025-12-27 04:02:13 +01:00
Peter Steinberger
96911d7790 fix: enqueue system event on model switch 2025-12-27 01:17:12 +00:00
Peter Steinberger
7e380bb6f8 fix: enable lmstudio responses and drop think tags 2025-12-27 00:28:52 +00:00
Peter Steinberger
2477ffd860 chore: fix lint/test gating 2025-12-26 23:54:30 +00:00
Peter Steinberger
5c8e1b6eef feat: add model aliases + minimax shortlist 2025-12-26 23:26:14 +00:00
Peter Steinberger
ce91aba4de fix: apply biome formatting 2025-12-26 14:38:37 +01:00
Peter Steinberger
e33c09f8d4 fix(tests): align discord + queue changes 2025-12-26 14:32:57 +01:00
Peter Steinberger
a678c3f53e refactor(queue): remove drop mode 2025-12-26 14:29:28 +01:00
Peter Steinberger
3e4fc7ff7f feat(queue): add reset/default directive 2025-12-26 14:24:53 +01:00
Peter Steinberger
8dda07a1e9 feat(queue): add queue modes and discord gating 2025-12-26 13:35:44 +01:00
Shadow
ac659ff5a7 feat(discord): Discord transport 2025-12-26 13:20:30 +01:00
Peter Steinberger
d28265cfbe fix: handle embedded agent overflow 2025-12-26 10:20:21 +01:00
Peter Steinberger
0d8e0ddc4f feat: unify gateway heartbeat 2025-12-26 02:35:40 +01:00
Peter Steinberger
8f9d7405ed style: fix biome formatting 2025-12-26 00:50:46 +00:00
Peter Steinberger
9f7b1f0942 feat: move heartbeat config to agent.heartbeat 2025-12-26 01:13:42 +01:00
Peter Steinberger
1ef888ca23 refactor(config): drop agent.provider 2025-12-26 01:13:42 +01:00
Peter Steinberger
8b815bce94 feat(config): allow provider/model shorthand 2025-12-26 01:13:42 +01:00
Peter Steinberger
198f8ea700 fix(agent): serialize runs per session 2025-12-25 23:50:52 +01:00
Peter Steinberger
0139a77e94 fix: resolve ts build errors 2025-12-24 00:57:11 +00:00
Peter Steinberger
267cdf20e1 style: fix biome lint 2025-12-24 00:33:35 +00:00
Peter Steinberger
93af424ce5 refactor: move inbound config 2025-12-24 00:22:52 +00:00
Peter Steinberger
364a6a9444 feat: add per-session model selection 2025-12-23 23:45:20 +00:00
Peter Steinberger
b6bfd8e34f fix: anchor typing loop to run 2025-12-23 15:03:05 +00:00
Peter Steinberger
f667d56701 fix: tag owner numbers in system prompt 2025-12-23 14:19:41 +00:00
Peter Steinberger
df5284beaf fix: suppress thinking stream + typing 2025-12-23 14:17:18 +00:00
Peter Steinberger
863d26558a fix: delay typing until reply payload 2025-12-23 13:55:01 +00:00
Peter Steinberger
cba12a1abd fix: inject group activation in system prompt 2025-12-23 13:32:07 +00:00
Peter Steinberger
e54ed10bc1 fix: honor /new resets with mentions in groups 2025-12-23 13:20:11 +00:00
Peter Steinberger
cd6ed79433 fix: honor group requireMention default 2025-12-23 12:53:30 +00:00
Peter Steinberger
ffe75f3e20 🤖 codex: add telegram reply context 
# Conflicts:
#	src/telegram/bot.ts
 2025-12-23 02:30:21 +01:00
Peter Steinberger
918cbdcf03 refactor: lint cleanups and helpers 2025-12-23 00:28:55 +00:00
Peter Steinberger
9717f2d374 fix: bump pi deps and fix lint 2025-12-22 20:45:38 +00:00
Peter Steinberger
f10c8f2b4c feat: add group activation command 2025-12-22 20:36:29 +01:00
Peter Steinberger
15e468f5dd feat: add group chat activation mode 2025-12-22 19:32:12 +01:00
Peter Steinberger
50e817f193 fix: use local timestamps in agent envelope 2025-12-20 19:40:48 +01:00
Peter Steinberger
759ab8acbc test: mock embedded queue in auto-reply tests 2025-12-20 18:01:09 +01:00
Peter Steinberger
e618a21f4e style: biome formatting 2025-12-20 17:50:45 +01:00
Peter Steinberger
44339a6447 feat(agent): queue steering messages 2025-12-20 16:10:53 +01:00
Peter Steinberger
e1b8c30163 feat(web): toggle tool summaries mid-run 2025-12-20 13:52:04 +00:00
Peter Steinberger
70faa4ff36 feat(web): stream tool summaries 2025-12-20 13:47:07 +00:00
Peter Steinberger
63b63cd66d style(auto-reply): format bare /new 2025-12-20 13:31:46 +00:00
Peter Steinberger
c2c5b28c70 feat(auto-reply): greet on bare /new 2025-12-20 13:04:55 +00:00
Peter Steinberger
f0ebad3f21 fix: address skills lint 2025-12-20 12:29:45 +01:00
Peter Steinberger
d1850aaada feat: add managed skills gating 2025-12-20 12:22:38 +01:00
Peter Steinberger
fece42ce0a feat: embed pi agent runtime 2025-12-17 11:29:04 +01:00
Peter Steinberger
060a209ecb fix(system): inject transitions only 2025-12-17 08:31:23 +01:00
Peter Steinberger
e1e3da946f fix(chat): reduce system spam and cap history 2025-12-16 20:35:03 +01:00
Peter Steinberger
2b0f846f1b chore(auto-reply): satisfy biome 2025-12-16 10:30:57 +01:00
Peter Steinberger
e7713a28ae fix(auto-reply): parse agent_end and avoid rpc JSON leaks 2025-12-16 10:28:57 +01:00
Peter Steinberger
b817225fb8 feat(agent): enforce provider/model and identity defaults 2025-12-14 04:22:38 +00:00
Peter Steinberger
073285409b feat: bootstrap agent workspace and AGENTS.md 2025-12-14 03:14:58 +00:00
Peter Steinberger
507f5623f4 fix: expand reply cwd (~) and document AGENTS 2025-12-14 03:00:18 +00:00
Peter Steinberger
cf28ea0d1c test: raise vitest coverage 2025-12-13 20:37:56 +00:00
Peter Steinberger
c3aed2543e fix(status): account cached prompt tokens 2025-12-12 23:22:24 +00:00
Peter Steinberger
bc618ec290 refactor(auto-reply): remove pi json fallback 2025-12-12 17:43:11 +00:00
Peter Steinberger
0780859a4d fix(auto-reply): prefer Pi RPC by default 2025-12-12 17:30:34 +00:00
Peter Steinberger
f1ff24d634 web: default to self-only without config 2025-12-12 01:22:03 +00:00
Peter Steinberger
47a1f757a9 lint: format and stabilize gateway health 2025-12-10 18:00:33 +00:00
Peter Steinberger
6c005b3d35 fix(session): ignore agent meta session id 2025-12-10 16:38:22 +00:00
Peter Steinberger
c2adda1cfe chore: drop rpc->json fallback 2025-12-10 15:58:45 +00:00
Peter Steinberger
51d77aea2e fix(auto-reply): acknowledge reset triggers 2025-12-10 15:55:20 +00:00
Peter Steinberger
4db69c8eac fix(auto-reply): fall back to json when rpc prompt empty 2025-12-10 14:58:03 +00:00
Peter Steinberger
b61147aed0 fix(auto-reply): guard empty rpc prompt 2025-12-10 14:26:03 +00:00
Peter Steinberger
5e4a91f996 Auto-reply: reject empty inbound messages 2025-12-10 13:51:06 +00:00
Peter Steinberger
81385cf820 pi: parse turn_end streams 2025-12-10 11:31:28 +00:00
Peter Steinberger
c4b02645f5 fix: persist usage from rpc 2025-12-10 11:31:28 +00:00
Peter Steinberger
5ed1d4e178 test: drop obsolete reply session placeholder 2025-12-10 01:00:44 +00:00
Peter Steinberger
1dd5c97ae0 feat: add ws chat attachments 2025-12-09 23:16:57 +01:00
Peter Steinberger
ffc930b871 surface: envelope inbound messages for agent 2025-12-09 18:43:21 +00:00
Peter Steinberger
a3bf2bdd8c chore: rename relay to gateway 2025-12-09 18:00:01 +00:00
Peter Steinberger
1f19ca1665 chore: drop runner shim and add committer helper 2025-12-09 17:24:25 +00:00
Peter Steinberger
8d888b426f chore: format swift/ts and fix gateway lint 2025-12-09 17:11:25 +00:00
Peter Steinberger
b2e7fb01a9 Gateway: finalize WS control plane 2025-12-09 14:41:41 +01:00
Peter Steinberger
998a5b080d Update auto-reply and voice wake runtime 2025-12-09 04:15:01 +00:00
Peter Steinberger
99a3102134 Docs: voice overlay plan and fix web mocks 2025-12-09 03:25:55 +01:00
Peter Steinberger
e15475449c fix merge; add control logging 2025-12-09 01:46:09 +00:00
Peter Steinberger
1969e78d54 feat: surface system presence for the agent 2025-12-09 02:25:37 +01:00
Peter Steinberger
5bfecc6152 fix: stop partial replies for whatsapp/telegram surfaces 2025-12-09 01:41:05 +01:00
Peter Steinberger
e44ed2681f refactor: type tau rpc stream events 2025-12-09 01:41:05 +01:00