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
d8f1124d59
feat: add CLI backend fallback
2026-01-11 00:55:22 +00:00
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
7c76561569
fix: dedupe inbound messages across providers
2026-01-11 00:12:25 +01:00
1eb50ffac4
feat(status): improve status output
2026-01-10 23:32:07 +01:00
708f04b02f
fix: keep mock openai responses requests
2026-01-10 22:56:08 +01:00
fa61699f9a
fix: polish restart feedback + stabilize tests ( #685 ) (thanks @carlulsoe)
2026-01-10 22:52:09 +01:00
a6a9930a34
fix: enable block streaming for all providers ( #684 )
2026-01-10 15:25:55 -06:00
686b3f884c
fix: expose WhatsApp sender ids in group context
2026-01-10 21:09:08 +01:00
cf192f8551
style: biome format
2026-01-10 19:47:17 +00:00
9f9098406c
feat(sandbox): add sandbox explain inspector
2026-01-10 20:28:43 +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
6480ef369f
fix: telegram draft chunking defaults ( #667 ) (thanks @rubyrunsstuff)
2026-01-10 18:30:06 +01:00
a54706a063
fix: throttle cli credential sync
2026-01-10 17:44:03 +01:00
e3cd431551
fix(auto-reply): RawBody commands + locked session updates ( #643 )
2026-01-10 17:32:31 +01:00
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
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
70c1732dd1
refactor: centralize messaging dedupe helpers
2026-01-10 16:02:56 +01:00
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
cdb915d527
chore: normalize Clawdbot naming
2026-01-10 05:14:09 +01:00
34664601e0
fix(auto-reply): default audioAsVoice to false
2026-01-10 02:25:19 +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
8b579c91a5
feat: add /config chat config updates
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
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
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
5898304fa0
fix: abort runs between tool calls
2026-01-10 01:26:25 +01:00
1fd7a6e310
fix: keep telegram streamMode draft-only ( #619 ) (thanks @rubyrunsstuff)
2026-01-10 01:14:40 +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
097550c299
fix: centralize verbose overrides and tool stream gating
2026-01-10 00:52:24 +01:00
9a8d3aed26
test: update status expectations for verbose/elevated labels
2026-01-09 23:43:24 +00:00
e18080163f
fix: simplify verbose/elevated status labels
2026-01-09 23:41:57 +00:00
96e17d407a
fix: filter NO_REPLY prefixes
2026-01-09 23:29:05 +00:00
a9a70ea278
fix: persist verbose off and gate tool stream
2026-01-10 00:22:28 +01:00
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
3b91148a0a
fix: handle fence-close paragraph breaks
2026-01-09 22:20:22 +00:00
3adec35632
fix: make forced block chunking fence-safe
2026-01-09 21:52:47 +00:00
79af03ba5e
fix(auto-reply): tighten block streaming defaults
2026-01-09 22:41:10 +01:00
53f51786f2
fix: default block streaming coalesce idle to 1s
2026-01-09 22:31:19 +01:00
6c7a27c010
refactor: normalize main session key handling
2026-01-09 22:30:15 +01:00
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
84046cbad8
fix(slack): mrkdwn + thread edge cases ( #464 ) (thanks @austinm911)
2026-01-09 22:09:02 +01:00
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
42a0089b3b
fix: require explicit system event session keys
2026-01-09 21:59:01 +01:00
5fa26bfec7
feat: add per-agent elevated controls
2026-01-09 20:42:19 +00:00
d3a0114b6b
fix: dedupe followup queue by message id ( #600 ) (thanks @samratjha96)
2026-01-09 20:44:11 +01:00
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
2977b296e6
feat(messages): add whatsapp messagePrefix and responsePrefix auto
2026-01-09 19:29:04 +00:00
72b0777341
fix(messages): restore explicit responsePrefix default
2026-01-09 19:18:34 +00:00
fd15704c77
fix(auto-reply): coalesce block replies and document streaming toggles ( #536 ) (thanks @mcinteerj)
2026-01-09 18:19:55 +00:00
a05916bee8
Config: add support for per-provider blockStreaming override
2026-01-09 18:11:27 +00:00
cf1e0d743c
fix: harden slash command registry
2026-01-09 17:53:24 +01:00
401f2a77e3
Merge branch 'main' into commands-list-clean
2026-01-09 11:46:08 -05:00
1478473537
refactor(commands): canonicalize text command aliases
2026-01-09 17:22:46 +01:00
1838582546
refactor(auto-reply): centralize chat command aliases
2026-01-09 17:16:52 +01:00
d372fac9c6
refactor: streamline reply tag parsing
2026-01-09 17:14:40 +01:00
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
68ad27e31c
fix(commands): wire /usage to status ( #492 ) (thanks @lc0rp)
2026-01-09 17:10:53 +01:00
4658f937cc
Merge branch 'main' into commands-list-clean
2026-01-09 11:06:06 -05:00
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
98b875cd0f
Merge branch 'main' into commands-list-clean
2026-01-09 11:04:23 -05:00
7d9300e0f5
fix: allow whitespace in reply tags ( #560 ) (thanks @mcinteerj)
2026-01-09 17:03:44 +01:00
08caf7b9fc
feat(commands): add /usage alias for /status
2026-01-09 17:02:29 +01:00
4381b03412
Auto-Reply: relax regex for reply tags to allow whitespace
2026-01-09 17:01:58 +01:00
d099dabf37
refactor: centralize slack threading helpers
2026-01-09 16:01:53 +00:00
be48233bc4
chore: format
2026-01-09 16:55:51 +01:00
c643ce2a7a
feat: add /debug runtime overrides
2026-01-09 16:55:16 +01:00
36bdec0f2c
refactor(messages): centralize per-agent prefixes
2026-01-09 16:54:54 +01:00
8341b662af
refactor(test): temp home env + normalize status
2026-01-09 16:50:09 +01:00
c8b15af979
refactor(test): centralize temp home + polling
2026-01-09 16:49:02 +01:00
09b602b4ec
style: format trigger test
2026-01-09 16:41:05 +01:00
4ffbd9802a
refactor(test): consolidate temp home + vitest setup
2026-01-09 16:41:05 +01:00
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
66bbb723c5
fix: derive prefixes from routed identity ( #578 ) (thanks @p6l-richard)
2026-01-09 16:39:32 +01:00
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
facf5c09a0
fix: honor slack reply threading ( #574 , thanks @bolismauro)
2026-01-09 15:38:43 +00:00
b3e0fafe50
fix: stabilize windows CI ( #558 ) (thanks @carlulsoe)
2026-01-09 16:37:58 +01:00
96149d1f71
fix: honor slack reply threading
2026-01-09 15:35:54 +00:00
922ca2ee1c
fix(status): surface provider usage errors
2026-01-09 15:34:58 +00:00
25babbfdc4
🤖 codex: fix duplicate agentDir (no-issue)
2026-01-09 16:23:34 +01:00
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
9af5b13803
test: make withTempHome cross-platform
2026-01-09 15:47:26 +01:00
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
c4c0f1349a
fix: keep build green after main rebase ( #570 ) (thanks @azade-c)
2026-01-09 15:40:36 +01:00
d17141b859
fix(status): show usage for token auth profiles
2026-01-09 14:36:46 +00:00
1afa48fcdf
style(models): biome format auth order
2026-01-09 14:36:46 +00:00
59d942c9ec
fix: unblock CI on main ( #569 ) (thanks @bjesuiter)
2026-01-09 15:32:55 +01:00
56e77f6843
fix: sessions label lookup and persistence ( #570 ) (thanks @azade-c)
2026-01-09 15:32:49 +01:00
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
3e400ff9f2
feat(models): add per-agent auth order overrides
2026-01-09 14:07:45 +00:00
b21e62f072
style: format gateway discovery
2026-01-09 13:55:28 +01:00
c2d185aab7
fix: normalize routed replies
2026-01-09 13:55:27 +01:00
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
0bc50abd73
style: format quickstart note and media-note test
2026-01-09 11:07:00 +01:00
c469fac8ef
Tests: speed up media note prompt setup
2026-01-09 11:07:00 +01:00
1df7bfefe7
MSTeams: stop on shutdown and honor chunk limit
2026-01-09 11:07:00 +01:00
2ab5890eab
wip
2026-01-09 11:06:49 +01:00
d6256a388e
feat(msteams): wire up proactive messaging in routeReply for queued replies
2026-01-09 11:06:49 +01:00
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
5f4df5e336
Auto-reply: drop native command flag
2026-01-09 04:14:36 -05:00
aa64abe84c
Merge branch 'main' into commands-list-clean
2026-01-09 03:12:08 -05:00
37cbcc97d3
feat: support token auth profiles
2026-01-09 08:13:04 +01:00
0a026fea1c
fix: disable restart by default
2026-01-09 05:49:30 +00:00
8e35ad5484
style: format after gate
2026-01-09 05:27:54 +00:00
31a2830f7d
fix: support /models alias for /model
2026-01-09 06:24:40 +01:00
7842109609
fix: report auth label from configured order
2026-01-09 05:17:27 +00:00
9114331218
fix: serialize claude cli runs
2026-01-09 04:58:21 +00:00
a4806e9417
Merge branch 'main' into commands-list-clean
2026-01-08 23:21:31 -05:00
5d34e27078
Revert: non-PR file edits
2026-01-08 23:19:44 -05:00
64fc5fa9fc
fix: allow default model outside allowlist
2026-01-09 04:18:30 +00:00
16f893c46b
Tests: align google shared expectations
2026-01-08 23:12:37 -05:00
7e4d5c9f84
test: align status and google-shared expectations
2026-01-09 05:03:12 +01:00
1be8a39442
Merge branch 'main' into commands-list-clean
2026-01-08 22:58:54 -05:00
1309cee124
Auto-reply: fix status command lint
2026-01-08 22:51:35 -05:00
8aa80fa464
Auto-reply: tidy help message
2026-01-08 22:48:46 -05:00
8e27ea7371
feat: add raw stream logging flags
2026-01-09 03:45:21 +00:00
69546d563d
fix: combine status usage and cost line
2026-01-09 03:45:01 +00:00
b97a9235e0
Merge branch 'main' into commands-list-clean
2026-01-08 22:19:52 -05:00
3e19f82af2
fix: repair status reply call
2026-01-09 03:18:20 +00:00
d8a23cf5ab
fix: restore emoji-rich status output
2026-01-09 03:15:33 +00:00
6c8b2a8dc9
Auto-reply: organize status imports
2026-01-08 22:14:24 -05:00
b3b84ffefa
fix: fallback /model list when catalog is unavailable
2026-01-09 03:56:19 +01:00
e52a2888cc
Merge branch 'main' into commands-list-clean
2026-01-08 21:47:09 -05:00
0cbc5fea93
fix: keep status for directive-only messages
2026-01-09 03:46:00 +01:00
dc81d0a649
fix: improve /status auth label
2026-01-09 03:39:02 +01:00
3c79d5c711
fix: keep /status usage filtering
2026-01-09 03:31:02 +01:00
151523f47b
feat: add usage cost reporting
2026-01-09 02:29:54 +00:00
1a295d9460
fix: improve status usage filtering and directives
2026-01-09 03:18:47 +01:00
468889abef
fix: refine status usage and elevated directives
2026-01-09 03:09:56 +01:00
c678216ac2
Merge branch 'main' into commands-list-clean
2026-01-08 20:58:26 -05:00
455723375e
fix: show directive options on query
2026-01-09 01:40:44 +01:00
daafa9e3bc
Merge branch 'main' into commands-list-clean
2026-01-08 19:33:56 -05:00
27adabbeea
test: cover reasoning directive spacing (thanks @joshp123) ( #539 )
2026-01-09 00:51:05 +01:00
f666f60731
fix: preserve inline directive spacing tests (thanks @joshp123) ( #539 )
2026-01-09 00:37:40 +01:00
43545a4864
🤖 codex: preserve spacing after inline directives (issue-telegram-inline-spacing)
2026-01-09 00:37:40 +01:00
Peter Steinberger
Ruby
Lloyd
Jarvis
Austin Mudd
Samrat Jha
Jake
Luke
LK
Mauro Bolis
Josh Palmer
Azade
Onur