43545a4864
🤖 codex: preserve spacing after inline directives (issue-telegram-inline-spacing)
2026-01-09 00:37:40 +01:00
014667e00b
fix: tighten group elevated targeting
2026-01-08 22:57:18 +01:00
a574ae5415
Merge branch 'main' into commands-list-clean
2026-01-08 15:35:17 -05:00
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
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
559e175b38
feat(commands): add /commands slash list
2026-01-08 16:23:36 +01:00
bce3cc992f
fix: group /model list output
2026-01-08 09:44:59 +01:00
8930ec32cb
feat: add slack multi-account routing
2026-01-08 08:49:16 +01:00
d1ceb3aa60
feat: add logs cli and restart hints
2026-01-08 06:56:34 +00:00
6a81652ebf
fix(typing): keep tool-start ttl mode-safe ( #452 , thanks @thesash)
2026-01-08 06:18:35 +00:00
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
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
15379dedf0
fix(telegram): voice-note tag defaults ( #188 , thanks @manmal)
2026-01-08 03:15:08 +00:00
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
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
8aa3efb9e8
refactor: tidy directive parsing + queue status
2026-01-08 03:47:52 +01:00
fbeb9e6775
fix(ci): stabilize windows tests
2026-01-08 02:44:19 +00:00
780385e31f
fix(auto-reply): handle /think no-arg
2026-01-08 03:39:05 +01:00
ad5c87c193
fix: relax slash command parsing
2026-01-08 03:24:18 +01:00
36b443f4f3
Telegram: fix /think command to show current level when no arg
2026-01-08 03:24:18 +01:00
a450390f7c
refactor: share reply payload threading/dedupe
2026-01-08 01:09:23 +00:00
05b8679c8b
feat: add providers CLI and multi-account onboarding
2026-01-08 01:55:59 +01:00
17d052bcda
fix: polish reply threading + tool dedupe (thanks @mneves75) ( #326 )
2026-01-08 00:50:47 +00:00
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
b2de667b11
fix: persist topic session files
2026-01-07 22:56:50 +00:00
434c25331e
refactor: centralize typing mode signals
2026-01-07 22:18:11 +00:00
bac1608933
feat: add typing mode controls
2026-01-07 21:58:54 +00:00
e41540e4ff
feat(commands): add dynamic /<alias> model switching
2026-01-07 20:41:41 +00:00
0d021391a9
fix: scope thread sessions and discord starter fetch
2026-01-07 19:42:50 +01:00
7e5cef29a0
Threads: add Slack/Discord thread sessions
2026-01-07 19:30:30 +01:00
1011640a13
refactor: drop autoReply, add topic requireMention
...
Co-authored-by: kitze <kristijan.mkd@gmail.com>
2026-01-07 12:07:15 +01:00
eef90b47a3
chore: satisfy lint
2026-01-07 11:49:01 +01:00
43c6bb7595
feat: add channel/topic overrides for skills + auto-reply
2026-01-07 11:44:37 +01:00
61f720b945
feat: add skill filter + group system prompt plumbing
2026-01-07 11:44:37 +01:00
9bf6684366
feat: add provider usage tracking
2026-01-07 11:42:46 +01:00
a700f9896d
feat: telegram draft streaming
2026-01-07 11:08:32 +01:00
e8420bd047
fix: refine bootstrap injections
2026-01-07 10:04:23 +00:00
412990a139
Reduce prompt token overhead with leaner context injections
2026-01-07 10:04:23 +00:00
7973fd4caf
feat: add agents command
2026-01-07 10:03:53 +01:00
dc941b7e57
fix: refresh status output
2026-01-07 07:22:06 +01:00
1673a221f8
feat: add /reasoning reasoning visibility
2026-01-07 06:17:31 +01:00
cb2a72f8a9
test(routing): add route-reply coverage
2026-01-07 05:07:53 +00:00
3668388912
fix(routing): harden originating reply routing
2026-01-07 05:02:34 +00:00
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
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
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
e0efcda77f
fix(commands): wire /stop across chat commands
2026-01-06 23:11:57 +00:00
fec7f37271
merge upstream/main
2026-01-06 23:09:01 +01:00
86b56b2308
fix: harden gemini session reset
2026-01-06 23:06:01 +01:00
96164b5955
fix: improve socket error handling
2026-01-06 22:43:29 +01:00
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
84c8209158
fix(slack): clear assistant thread status after replies
2026-01-06 21:41:30 +01:00
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
31dbc62bdd
fix(telegram): prevent stuck typing after tool runs
2026-01-06 18:56:43 +00:00
bdf597eb95
fix(telegram): stop typing after tool results ( #322 )
...
Thanks @AbhisekBasu1.
2026-01-06 18:54:08 +00:00
2f24ea492b
fix: restore Anthropic token accounting
2026-01-06 18:52:01 +00:00
dbfa316d19
feat: multi-agent routing + multi-account providers
2026-01-06 18:33:37 +00:00
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
b5c604b7b7
fix: require slash for control commands
2026-01-06 07:05:17 +01:00
88cb13dc82
Auto-reply: fix typing stop race ( #270 )
2026-01-05 22:57:04 -06:00
ea6ee16461
chore: fix lint warnings
2026-01-06 05:41:24 +01:00
13eb9c9ee9
refactor: centralize reply dispatch
2026-01-06 04:55:00 +01:00
5946f4c341
test: extend typing idle coverage
2026-01-06 03:42:33 +00:00
58186aa56e
test: cover typing idle gate
2026-01-06 03:28:47 +00:00
ca8f66f844
refactor: unify group allowlist policy
2026-01-06 04:27:51 +01:00
9d656f4269
style: satisfy lint
2026-01-06 03:11:42 +00:00
d5f088978a
fix: stop typing after dispatcher idle
2026-01-06 03:09:49 +00:00
b30bae89ed
feat: track compaction count + verbose notice
2026-01-06 02:49:03 +01:00
b6ae376076
fix: gate reset auth and infer whatsapp sender
2026-01-06 02:23:55 +01:00
b56338171b
feat: gate slash commands and add compact
2026-01-06 02:23:55 +01:00
e73573eaea
fix: clean model config typing
2026-01-06 01:08:36 +00:00
b04c838c15
feat!: redesign model config + auth profiles
2026-01-06 00:56:58 +00:00
d813e14950
chore: update mention gating docs and tests
2026-01-06 01:38:36 +01:00
811ec8b78b
fix: unify mention gating across providers
2026-01-06 01:32:17 +01:00
53bf8b7b80
fix: avoid duplicate missing auth label
2026-01-05 23:00:37 +01:00
c75b2a7067
refactor: unify reply dispatch across providers
2026-01-05 19:43:54 +01:00
b7e708c764
fix(chat): stabilize web UI tool runs
2026-01-05 17:22:29 +00:00
86c404c48b
chore: fix reply commands lint
2026-01-05 18:16:39 +01:00
7f3f73af1c
fix: show model auth in status
2026-01-05 15:50:18 +01:00
bf6aad1965
fix(ci): format directive-handling
2026-01-05 14:34:55 +00:00
0c37f27a4a
fix: show /model auth source
2026-01-05 14:14:26 +00:00
cffbe79077
fix: add /model list alias
2026-01-05 14:11:33 +00:00
8e8d07cbf4
fix(ci): satisfy formatter checks
2026-01-05 13:55:53 +00:00
7619534bc0
feat(groups): resolve requireMention for discord/slack
2026-01-05 13:55:32 +00:00
ce68d82dfa
fix: widen /model key masking
2026-01-05 13:50:45 +00:00
5163886694
fix: show auth in /model list
2026-01-05 13:49:25 +00:00
17ef7b3b0e
fix: status runtime + help
2026-01-05 07:07:17 +01:00
67420e9a81
fix: allow group activation for allowFrom senders
2026-01-05 02:33:51 +01:00
359cb66e68
fix: allow wildcard control commands
2026-01-05 02:06:18 +01:00
17422608b2
fix: gate /activation to owners in groups
2026-01-05 02:03:29 +01:00
85549ac3b6
fix: gate group activation by owner
2026-01-05 00:48:16 +00:00
1bad96aa2b
style: tidy auto-reply imports and formatting
2026-01-05 01:46:16 +01:00
852f947b44
fix: unify control command handling
2026-01-05 01:31:36 +01:00
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
1657c5e3d2
fix: route system events per session
2026-01-04 22:11:04 +01:00
ff46f8ce58
chore: format models CLI
2026-01-04 18:11:41 +01:00
734bb6b4fd
feat: add models scan and fallbacks
2026-01-04 17:57:52 +01:00
246adaa119
chore: rename project to clawdbot
2026-01-04 14:38:51 +00:00
bf3d120f8c
Slack: add new slack connection
2026-01-04 07:18:20 +01:00
c9504a6f20
refactor: split config module
2026-01-04 07:05:17 +01:00
ff88f3c075
style: fix lint ordering
2026-01-04 06:27:54 +01:00
fe0b3500cc
feat: add elevated bash mode
2026-01-04 05:15:59 +00:00
72a9e58777
refactor(auto-reply): split reply flow
2026-01-04 05:47:37 +01:00
Josh Palmer
Peter Steinberger
Luke
Keith the Silly Goose
LK
Sash Catanzarite
Manuel Maly
Lutro
mneves75
Azade
Shadow
Tobias Bischoff
Josh Lehman
Emanuel Stadler
Abhi
VAC
Jake