romtuck/openclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
7,682 Commits 258 Branches 39 Tags 276 MiB
feat/plugin-command-api
Commit Graph

1265 Commits

Author SHA1 Message Date
Peter Steinberger
88b37e80fc refactor: expand bootstrap helpers and tests 2026-01-18 05:51:55 +00:00
Peter Steinberger
9c0ff87c86 fix: align plugin runtime and exec wiring 2026-01-18 05:44:22 +00:00
Peter Steinberger
cf8b3ed988 fix: harden memory indexing and embedded session locks 2026-01-18 05:41:45 +00:00
Peter Steinberger
2dabce59ce feat(slash-commands): usage footer modes 2026-01-18 05:35:35 +00:00
Peter Steinberger
e7a4931932 refactor: centralize bootstrap file resolution 2026-01-18 05:31:04 +00:00
Peter Steinberger
ad3c12a43a feat: add bootstrap hook and soul-evil hook 2026-01-18 05:24:47 +00:00
Peter Steinberger
016693a1f5 fix: abort embedded prompts on cancel 2026-01-18 05:18:10 +00:00
Peter Steinberger
b105745299 feat: expand subagent status visibility 2026-01-18 04:46:04 +00:00
Peter Steinberger
1ae415e395 fix: align agent exec config 2026-01-18 04:37:15 +00:00
Peter Steinberger
e4e1396a98 perf: improve batch status logging 2026-01-18 04:28:14 +00:00
Peter Steinberger
efdb33c975 feat: add exec host approvals flow 2026-01-18 04:27:41 +00:00
Peter Steinberger
82e49af5a7 fix: resolve plugin tool meta typing 2026-01-18 04:24:16 +00:00
Peter Steinberger
fabc2882aa fix: avoid keychain prompts in embedded runner 2026-01-18 04:19:28 +00:00
Peter Steinberger
6b3d3f5e21 refactor: centralize plugin tool policy helpers 2026-01-18 04:18:32 +00:00
Peter Steinberger
6da6582ced feat: add optional plugin tools 2026-01-18 04:08:00 +00:00
Peter Steinberger
afb877a96b perf: speed up memory batch polling 2026-01-18 03:55:14 +00:00
Peter Steinberger
787bed4996 test: stabilize doctor + pi-embedded suites 2026-01-18 03:40:47 +00:00
Peter Steinberger
5fa1a63978
Merge pull request #1136 from cheeeee/fix/prompt-failover 
fix(agent): Enable model fallback for prompt-phase quota/rate limit errors
 2026-01-18 03:32:03 +00:00
Peter Steinberger
0f6f7059d9 test: stabilize embedded runner tests 2026-01-18 02:55:41 +00:00
Peter Steinberger
67f63ecd7e chore: remove tracked artifacts 2026-01-18 02:55:07 +00:00
Peter Steinberger
1420d113d8 refactor: migrate extensions to plugin sdk 2026-01-18 02:55:07 +00:00
Peter Steinberger
34590d2144 feat: persist session origin metadata across connectors 2026-01-18 02:42:10 +00:00
Peter Steinberger
0c93b9b7bb style: apply oxfmt 2026-01-18 02:19:35 +00:00
Peter Steinberger
9fd9f4c896 feat(plugins): add memory slot plugin 2026-01-18 02:12:10 +00:00
Peter Steinberger
005b831023 test: stabilize env-dependent tool defaults 2026-01-18 01:57:54 +00:00
Peter Steinberger
14e6b21b50 test: cover perplexity baseUrl precedence 2026-01-18 01:56:34 +00:00
Peter Steinberger
ccb30665f7 feat: add hybrid memory search 2026-01-18 01:47:58 +00:00
Peter Steinberger
0fb2777c6d feat: add memory embedding cache 2026-01-18 01:47:58 +00:00
Peter Steinberger
568b8ee96c refactor: split web tools and docs 2026-01-18 01:42:54 +00:00
Peter Steinberger
0674f1fa3c feat: add exec approvals allowlists 2026-01-18 01:34:31 +00:00
Mykyta Bozhenko
448394a0de fix(agent): Enable model fallback for prompt-phase quota/rate limit errors 
When a prompt submission fails with quota or rate limit errors, throw
FailoverError instead of the raw promptError. This enables the model
fallback system to try alternative models.

Previously, rate limit errors during the prompt phase (before streaming)
were thrown directly, bypassing fallback. Only response-phase errors
triggered model fallback.

Now checks if fallback models are configured and the error is failover-
eligible. If so, wraps in FailoverError to trigger the fallback chain.
 2026-01-18 01:29:48 +00:00
Peter Steinberger
8b1bec11d0 feat: speed up memory batch indexing 2026-01-18 01:24:51 +00:00
Peter Steinberger
1d83389776
Merge pull request #1131 from CMLKevin/feat/perplexity-search-provider 
feat(web): add Perplexity Sonar as alternative search provider
 2026-01-18 01:16:00 +00:00
Peter Steinberger
36d88f6079 fix: normalize gateway dev mode detection 2026-01-18 01:08:47 +00:00
Muhammed Mukhthar CM
b56b67cdbd UI: label Qwen provider 2026-01-18 01:03:08 +00:00
Muhammed Mukhthar CM
8eb80ee40a Models: add Qwen Portal OAuth support 2026-01-18 01:03:08 +00:00
Peter Steinberger
d593a809f0 fix: apply openai batch defaults 2026-01-18 00:29:18 +00:00
Peter Steinberger
4d590f9254 refactor(slack): centralize target parsing 2026-01-18 00:15:05 +00:00
Peter Steinberger
1bf3861ca4 feat: add thinking override to sessions_spawn 2026-01-18 00:14:18 +00:00
Kevin Lin
ff9d069a33 feat(web): add Perplexity Sonar as alternative search provider 2026-01-18 08:08:36 +08:00
Peter Steinberger
a08438ae97 refactor(discord): centralize target parsing 
Co-authored-by: Jonathan Rhyne <jonathan@pspdfkit.com>
 2026-01-18 00:04:38 +00:00
Peter Steinberger
b60a53e10d feat: enable batch indexing by default 2026-01-17 23:29:40 +00:00
Peter Steinberger
a31a79396b feat: add OpenAI batch memory indexing 2026-01-17 22:32:04 +00:00
Peter Steinberger
1e2ab8bf1e fix: improve frontmatter parsing 2026-01-17 19:56:10 +00:00
Peter Steinberger
0e49dca53c feat: add experimental session memory source 2026-01-17 18:53:52 +00:00
Peter Steinberger
3df2dc0b15 fix: normalize exec tool alias naming 2026-01-17 18:15:45 +00:00
Peter Steinberger
5304a8c2d1 fix: add timestamped tool context to logs 2026-01-17 18:14:21 +00:00
Peter Steinberger
5a08471dcd feat: add sqlite-vec memory search acceleration 2026-01-17 18:02:34 +00:00
Peter Steinberger
252dfbcd40 fix: include context in elevated exec denial 2026-01-17 17:55:11 +00:00
Peter Steinberger
7876679c5d style: apply oxfmt 2026-01-17 17:44:54 +00:00
Peter Steinberger
6cb5704291
Merge pull request #1085 from dan-dr/chore/kimi-code-provider 
Add Kimi Code provider onboarding
 2026-01-17 17:36:30 +00:00
Peter Steinberger
4a987c836d fix: add Kimi Code docs + defaults (#1085) (thanks @dan-dr) 2026-01-17 17:35:40 +00:00
Muhammed Mukhthar CM
f2a0e8e5bb feat(telegram): support sending audio as native voice notes via asVoice param in message tool 2026-01-17 17:32:50 +00:00
ddyo
e93a1d8138 feat: add kimi code provider onboarding 2026-01-17 17:25:07 +00:00
Peter Steinberger
6b784a9771 style: oxfmt 2026-01-17 10:26:08 +00:00
Peter Steinberger
31e8ecca10 fix: format verbose tool output by channel 2026-01-17 10:17:57 +00:00
Peter Steinberger
1a4313c2aa fix: avoid crash on memory embeddings errors (#1004) 2026-01-17 09:45:53 +00:00
Peter Steinberger
b6ea5895b6 fix: gate image tool and deepgram audio payload 2026-01-17 09:34:40 +00:00
Peter Steinberger
e637bbdfb5 feat: add Deepgram audio transcription 
Co-authored-by: Safzan Pirani <safzanpirani@users.noreply.github.com>
 2026-01-17 08:53:42 +00:00
Peter Steinberger
13b931c006 refactor: prune legacy group prefixes 2026-01-17 08:47:25 +00:00
Peter Steinberger
d8b463d0b3 fix: cap pending process output 2026-01-17 08:26:12 +00:00
Peter Steinberger
f172ccfcf6 fix: remove stray skills watcher bracket 2026-01-17 08:15:21 +00:00
Peter Steinberger
a2a6893566 fix: allow skills watcher ignore list 2026-01-17 08:12:57 +00:00
Peter Steinberger
616ee3075c fix: repair skills watcher ignored typing 2026-01-17 08:12:00 +00:00
Peter Steinberger
c5239f6a8e fix: stabilize pty tests and media kind 2026-01-17 08:10:44 +00:00
Peter Steinberger
cccd7c7b8e test: stabilize windows pty expectations 2026-01-17 08:07:31 +00:00
Peter Steinberger
8f1132e8ec fix: share skills watcher ignores 2026-01-17 08:07:06 +00:00
Peter Steinberger
e6477363e9 refactor: normalize channel capabilities typing 2026-01-17 08:06:35 +00:00
Peter Steinberger
f3f80509e3 test: cover tg/group/topic inline button targets (#1072) — thanks @danielz1z 
Co-authored-by: danielz1z <danielz1z@users.noreply.github.com>
 2026-01-17 08:00:16 +00:00
Peter Steinberger
7cebe7a506 style: run oxfmt 2026-01-17 08:00:05 +00:00
Peter Steinberger
7630c6dccb
Merge pull request #1074 from roshanasingh4/fix/1056-ignore-heavy-watch-paths 
Fix #1056: prevent macOS FD exhaustion by ignoring node_modules in skills watcher
 2026-01-17 07:56:54 +00:00
Peter Steinberger
78a4441ac2 test: stabilize bash send-keys submit 2026-01-17 07:41:24 +00:00
Peter Steinberger
8c9e32c4a3 refactor: share sessions list row type 
Co-authored-by: Adam Holt <mail@adamholt.co.nz>
 2026-01-17 07:34:21 +00:00
Peter Steinberger
5dc87a2ed4 fix: respond to PTY cursor queries 2026-01-17 07:05:24 +00:00
Peter Steinberger
a85ddf258c fix: expose deliveryContext in sessions_list 
Co-authored-by: Adam Holt <mail@adamholt.co.nz>
 2026-01-17 06:54:31 +00:00
Peter Steinberger
37a2eee837 refactor: drop legacy session store keys 2026-01-17 06:48:44 +00:00
Peter Steinberger
353d778988 refactor: centralize target normalization 2026-01-17 06:45:11 +00:00
Peter Steinberger
3dc4a96330 feat: add process submit helper 2026-01-17 06:38:56 +00:00
Peter Steinberger
65a8a93854 fix: normalize delivery routing context 
Co-authored-by: adam91holt <adam91holt@users.noreply.github.com>
 2026-01-17 06:38:33 +00:00
Peter Steinberger
eb8a0510e0 refactor: unify queue drop handling 2026-01-17 06:38:33 +00:00
Peter Steinberger
a4178e4062 fix: stabilize pty send-keys tests 2026-01-17 06:32:24 +00:00
Roshan Singh
e7953d8164 Fix #1056: ignore heavy paths in skills watcher 
On macOS, watching deep dependency trees can exhaust file descriptors and lead to spawn EBADF failures. The skills watcher only needs to observe skill changes, so ignore dotfiles, node_modules, and dist by default. Adds regression coverage.
 2026-01-17 06:26:27 +00:00
Peter Steinberger
5ebfc0738f feat: add session slug generator 2026-01-17 06:23:26 +00:00
Peter Steinberger
bd32cc40e6 feat: add keypad key mappings 2026-01-17 06:22:05 +00:00
Peter Steinberger
b31d8d3b10 feat: add tmux-style process key helpers 2026-01-17 06:12:56 +00:00
Peter Steinberger
c7ae5100fa refactor: share queue helpers 
Co-authored-by: adam91holt <adam91holt@users.noreply.github.com>
 2026-01-17 06:02:27 +00:00
Peter Steinberger
e59d8c5436 style: oxfmt format 2026-01-17 05:48:56 +00:00
Peter Steinberger
8b42902cee refactor: drop legacy room chatType 2026-01-17 05:46:40 +00:00
Peter Steinberger
07a3db153d feat: notify on exec exit 2026-01-17 05:43:34 +00:00
Peter Steinberger
68d35be383 feat: emit tool outputs for full verbose 2026-01-17 05:40:21 +00:00
Peter Steinberger
99dd428862 feat: extend verbose tool feedback 2026-01-17 05:33:39 +00:00
Peter Steinberger
4d314db750 refactor: extract subagent announce queue 
Co-authored-by: adam91holt <adam91holt@users.noreply.github.com>
 2026-01-17 05:29:07 +00:00
Peter Steinberger
c4ea25a509 feat: add exec pty support 2026-01-17 04:57:11 +00:00
Peter Steinberger
49ecbd8fea test: expand accountId routing coverage 
Co-authored-by: adam91holt <adam91holt@users.noreply.github.com>
 2026-01-17 04:33:24 +00:00
Peter Steinberger
19ee6699d2 refactor: clarify subagent announce origin 
Co-authored-by: adam91holt <adam91holt@users.noreply.github.com>
 2026-01-17 04:33:24 +00:00
Peter Steinberger
780c811146 refactor: migrate subagent registry store v2 
Co-authored-by: adam91holt <adam91holt@users.noreply.github.com>
 2026-01-17 04:24:59 +00:00
Peter Steinberger
4f37f66264 refactor: normalize delivery context 
Co-authored-by: adam91holt <adam91holt@users.noreply.github.com>
 2026-01-17 04:24:59 +00:00
Peter Steinberger
6e4d86f426 refactor: require target for message actions 2026-01-17 04:15:46 +00:00
Peter Steinberger
a2b5b1f0cb refactor: normalize inbound context 2026-01-17 04:05:33 +00:00
Peter Steinberger
9f4b7a1683 fix: normalize subagent announce delivery origin 
Co-authored-by: Adam Holt <mail@adamholt.co.nz>
 2026-01-17 04:03:28 +00:00
Peter Steinberger
dd68faef23 refactor: split message tool schema + action handling 2026-01-17 03:58:55 +00:00
Peter Steinberger
1b973f7506 feat: add inbound media understanding 
Co-authored-by: Tristan Manchester <tmanchester96@gmail.com>
 2026-01-17 03:54:46 +00:00
Peter Steinberger
7f1f9473a0 refactor: dedupe message action helpers 2026-01-17 03:46:03 +00:00
Peter Steinberger
a82217a5f3 chore: format + regenerate protocol 2026-01-17 03:40:49 +00:00
Peter Steinberger
09bed2ccde refactor: centralize outbound policy + target schema 2026-01-17 03:33:56 +00:00
Peter Steinberger
3fcd6fadf3 fix: land oxlint config follow-ups (#1064) (thanks @connorshea) 2026-01-17 03:25:05 +00:00
Peter Steinberger
bc7d603867 test: expand accountId delivery coverage 
Co-authored-by: Adam Holt <adam91holt@users.noreply.github.com>
 2026-01-17 03:17:33 +00:00
Peter Steinberger
46015a3dd8 feat: add cross-context messaging resolver 
Co-authored-by: Thinh Dinh <tobalsan@users.noreply.github.com>
 2026-01-17 03:17:13 +00:00
Peter Steinberger
0291105913 fix: thread accountId through subagent announce delivery 
Co-authored-by: Adam Holt <adam91holt@users.noreply.github.com>
 2026-01-17 02:45:18 +00:00
Peter Steinberger
d5332ae29a fix: thread accountId through subagent announce 
Co-authored-by: Adam Holt <adam91holt@users.noreply.github.com>
 2026-01-17 02:09:35 +00:00
Peter Steinberger
fdaeada3ec feat: mirror delivered outbound messages (#1031) 
Co-authored-by: T Savo <TSavo@users.noreply.github.com>
 2026-01-17 02:03:18 +00:00
Peter Steinberger
3fb699a84b style: apply oxfmt 2026-01-17 01:55:42 +00:00
Peter Steinberger
19016f16e0 fix: queue subagent announce delivery 2026-01-17 01:44:13 +00:00
Peter Steinberger
0179717d61 feat: enhance web_fetch fallbacks 2026-01-17 00:43:37 +00:00
Sash Catanzarite
89bbbe75a6
fix: honor message tool channel for tool dedupe (#1053) 
- Treat message tool `channel` as provider hint for dedupe/suppression.
- Prefer NO_REPLY after message tool sends to avoid duplicate replies.

Co-authored-by: Sash Catanzarite <1166151+thesash@users.noreply.github.com>
 2026-01-17 00:23:51 +00:00
Peter Steinberger
1569db1754 style: format with oxfmt 2026-01-17 00:03:00 +00:00
Peter Steinberger
c54c665f97 feat: enhance web_fetch fallbacks 2026-01-17 00:00:49 +00:00
Peter Steinberger
37fa4f7eef feat: improve web_fetch readability extraction 2026-01-16 23:18:01 +00:00
Yurii Chukhlib
171060541a docs(web-search): document country and language parameters 
Co-Authored-By: Claude <noreply@anthropic.com>
 2026-01-16 23:14:33 +00:00
Yurii Chukhlib
003547c818 test(web-search): add tests for country and language parameters 
Added three new test cases to verify the new country, search_lang, and ui_lang
parameters are correctly passed to the Brave Search API.

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-01-16 23:14:33 +00:00
Yurii Chukhlib
c4e1064066 feat(web-search): pass country and language params to Brave API 
- Add country, search_lang, and ui_lang optional parameters to runWebSearch
- Pass new parameters to Brave Search API as URL query parameters
- Update cache key to include localization parameters
- Wire parameters through createWebSearchTool execute function
 2026-01-16 23:14:33 +00:00
Yurii Chukhlib
d163dbcfcd feat(web-search): add country and language optional parameters to schema 2026-01-16 23:14:33 +00:00
Peter Steinberger
28a5d124c3 fix: stabilize transport-ready test timing 2026-01-16 23:03:12 +00:00
Peter Steinberger
a7bec3340f fix: drop unsigned gemini tool calls from history 2026-01-16 22:43:16 +00:00
Peter Steinberger
500c75b4f0 fix: align ZAI thinking toggles 2026-01-16 22:26:43 +00:00
Peter Steinberger
a0be85c34c fix: /stop aborts subagents 2026-01-16 21:37:22 +00:00
Peter Steinberger
d887027e95 style: run oxfmt 2026-01-16 21:11:55 +00:00
Timo Lins
beb9eac5f7 Models: add Vercel AI Gateway auth 2026-01-16 21:00:15 +00:00
Peter Steinberger
0dcffcd5b0 fix: repair orphaned user turns before embedded prompts 2026-01-16 20:52:18 +00:00
Peter Steinberger
08c0405f0f fix: quiet skill command normalization logs 2026-01-16 20:37:23 +00:00
Peter Steinberger
470add877c feat: default telegram reaction level minimal 2026-01-16 20:35:47 +00:00
Marc
5ee4456c6e fix: merge subagent auth profiles 2026-01-16 20:20:26 +00:00
Marc
de31583021 fix: avoid format keyword in tool schemas 
Co-authored-by: marcmarg <marcmarg@users.noreply.github.com>
 2026-01-16 20:20:26 +00:00
Peter Steinberger
38b49aa0f6 feat: expand skill command registration 2026-01-16 20:17:32 +00:00
Peter Steinberger
69761e8a51 feat: scope telegram inline buttons 2026-01-16 20:16:41 +00:00
Peter Steinberger
3431d3d115 chore: tweak tool call narration guidance (#1008) 
Co-authored-by: Christoph Nakazawa <christoph.pojer@gmail.com>
 2026-01-16 19:56:04 +00:00
Peter Steinberger
fe9e027d58 test: deflake background exec timeout 2026-01-16 19:48:52 +00:00
Wilkins
bb14b19922
fix: truncate skill command descriptions to 100 chars for Discord (#1018) 
* fix: truncate skill command descriptions to 100 chars for Discord

Discord slash commands have a 100 character limit for descriptions.
Skill descriptions were not being truncated, causing command registration
to fail with an empty error from the Discord API.

* style: format

* style: format
 2026-01-16 10:01:59 -06:00
Peter Steinberger
0d6af15d1c feat: add user-invocable skill commands 2026-01-16 12:10:29 +00:00
Peter Steinberger
eda9410bce fix: stabilize docker test suite 2026-01-16 11:47:14 +00:00
Peter Steinberger
f49d0e5476 fix: expand exec abort/timeout coverage 2026-01-16 10:43:22 +00:00
gerardward2007
0f34255359
chore: ignore local identity files (#1001) (thanks @gerardward2007) 
* chore: ignore local identity files (IDENTITY.md, USER.md)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* chore: ignore local identity files (#1001) (thanks @gerardward2007)

* chore: format session status tool

* chore: format bash exec background abort test

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
 2026-01-16 10:30:04 +00:00
Roshan Singh
e773f84e39
fix: keep background exec aborts from killing sessions (#1000) (thanks @roshanasingh4) 
When exec returns early in background mode, the tool-call AbortSignal can fire and previously caused killProcessTree(SIGKILL). Ignore abort after yielding/backgrounding so background sessions keep running.
 2026-01-16 10:01:39 +00:00
Peter Steinberger
30b3a9de30 fix: drop oauth status from session status 2026-01-16 09:39:12 +00:00
Peter Steinberger
0391f6553b fix: correct minimax usage + show reset 2026-01-16 09:36:45 +00:00
Peter Steinberger
4965727f39 chore: run format and fix sandbox browser timeouts 2026-01-16 09:18:58 +00:00
Peter Steinberger
9838a2850f fix: reset sessions after role ordering conflicts 2026-01-16 09:04:04 +00:00
Muhammed Mukhthar CM
cd409e5667
fix: exclude google-antigravity from history downgrade hack (#894) 
* Agent: exclude google-antigravity from history downgrade hack

* Lint: fix formatting in test

* Lint: formatting and unused vars in test

* fix: preserve google-antigravity tool calls (#894) (thanks @mukhtharcm)

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
 2026-01-16 08:14:56 +00:00
Peter Steinberger
f5a881c99d fix: port OpenRouter Gemini sanitization to split files (#845) (thanks @MatthieuBizien) 2026-01-16 08:02:56 +00:00
Matthieu Bizien
ef36e24522 Agents: sanitize OpenRouter Gemini thoughtSignature 2026-01-16 07:51:49 +00:00
Peter Steinberger
f2db894685
Merge pull request #992 from tyler6204/fix/tool-typing-race-condition 
fix: send text between tool calls to channel immediately
 2026-01-16 07:26:10 +00:00
Peter Steinberger
dfa6c5c2b3 fix(google): scrub tool schemas for gemini 2026-01-16 06:57:54 +00:00
Jamie Openshaw
72f28be648 fix(config): allow discord action flags in schema 
Ensure discord action flags survive config validation.

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-01-16 06:48:25 +00:00
Peter Steinberger
e48d68bbc7
Merge pull request #993 from cpojer/reminder-improvement 
Improve reminder text generation.
 2026-01-16 06:03:04 +00:00
Peter Steinberger
54ec14262b feat: add plugin update tracking 2026-01-16 05:55:05 +00:00
Tyler Yust
0d5dec4c66 fix: handle async tool start handler rejections 
Add .catch() to handleToolExecutionStart call to prevent unhandled
promise rejections when onAgentEvent or typing signaling fails.
 2026-01-15 21:10:52 -08:00
cpojer
b2d5889f6e
Improve reminder text generation. 2026-01-16 14:03:17 +09:00
Tyler Yust
2ee71e4154 fix: send text between tool calls to channel immediately 
Previously, when block streaming was disabled (the default), text generated
between tool calls would only appear after all tools completed. This was
because onBlockReply wasn't passed to the subscription when block streaming
was off, so flushBlockReplyBuffer() before tool execution did nothing.

Now onBlockReply is always passed, and when block streaming is disabled,
block replies are sent directly during tool flush. Directly sent payloads
are tracked to avoid duplicates in final payloads.

Also fixes a race condition where tool summaries could be emitted before
the typing indicator started by awaiting onAgentEvent in tool handlers.
 2026-01-15 20:55:52 -08:00
Peter Steinberger
01c8d099ad fix: repair CI formatting + launchd test 2026-01-16 03:52:47 +00:00
Peter Steinberger
b2b331230b feat: mac node exec policy + remote skills hot reload 2026-01-16 03:45:06 +00:00
Peter Steinberger
abcca86e4e chore: format and sync protocol outputs 2026-01-16 03:30:56 +00:00
Peter Steinberger
a5d8f89b53 feat(browser): prefer Chrome default + add Brave/Edge fallbacks 
Co-authored-by: Christoph Nakazawa <christoph.pojer@gmail.com>
 2026-01-16 03:28:56 +00:00
Peter Steinberger
a0d2a7232e fix: allow media-only sends 2026-01-16 03:15:26 +00:00
Peter Steinberger
23e4ba845c fix: sanitize user-facing errors and strip final tags 
Co-authored-by: Drake Thomsen <drake.thomsen@example.com>
 2026-01-16 03:01:23 +00:00
Peter Steinberger
29476b222d fix: restore status usage summary output 2026-01-16 02:49:18 +00:00
Peter Steinberger
3dddbe1053 fix: ignore properties in google tool schema warnings 2026-01-16 02:35:55 +00:00
Peter Steinberger
3e32050601 fix: correct final tag strip typing 2026-01-16 02:16:17 +00:00
Peter Steinberger
7fb45ed9b8 fix: strip final tags from session messages 2026-01-16 02:16:17 +00:00
Peter Steinberger
b7ba94f0c1 fix: harden antigravity claude support (#968) 
Co-authored-by: Max <rdev@users.noreply.github.com>
 2026-01-16 02:16:17 +00:00
Peter Steinberger
12afec953f test: stabilize sandbox config tests 2026-01-16 01:44:12 +00:00
Peter Steinberger
8e2707e232 fix: cleanup suspended CLI processes (#978) (thanks @Nachx639) 2026-01-16 01:39:33 +00:00
Tu Nombre Real
8befe7f8a7 fix: cleanup suspended Clawdbot CLI processes 
Add cleanupSuspendedCliProcesses() to kill accumulated suspended processes
from isolated sessions that don't share sessionIds (e.g., cron jobs).

- Only targets Clawdbot processes (--session-id pattern)
- Only kills suspended processes (state T)
- Only triggers when >10 processes accumulated
- Does not affect user's Claude Code sessions

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-16 01:38:03 +00:00
Peter Steinberger
61e385b331 feat: add per-agent heartbeat config 2026-01-16 01:17:34 +00:00
Peter Steinberger
bca5c0d569 refactor: system prompt sections + docs/tests 2026-01-16 00:28:43 +00:00
Peter Steinberger
8c3cdba21c feat: sticky auth profile rotation + usage headers 2026-01-16 00:25:49 +00:00
void
e274b5a040
fix: heartbeat prompt + dedupe (#980) (thanks @voidserf) 
- tighten default heartbeat prompt guidance
- suppress duplicate heartbeat alerts within 24h

Co-authored-by: void <voidserf@users.noreply.github.com>
 2026-01-16 00:24:52 +00:00
Josh Lehman
a139d35fa2
feat(slack): add userToken for read-only access to DMs and private channels (#981) 
- Add userToken and userTokenReadOnly (default: true) config fields
- Implement token routing: reads prefer user token, writes use bot token
- Add tests for token routing logic
- Update documentation with required OAuth scopes

User tokens enable reading DMs and private channels without requiring
bot membership. The userTokenReadOnly flag (true by default) ensures
the user token can only be used for reads, preventing accidental
sends as the user.

Required user token scopes:
- channels:history, channels:read
- groups:history, groups:read
- im:history, im:read
- mpim:history, mpim:read
- users:read, reactions:read, pins:read, emoji:read, search:read
 2026-01-16 00:11:33 +00:00
Peter Steinberger
10eb1beccf fix: tighten session entry updates 
Co-authored-by: Tyler Yust <tyler6204@users.noreply.github.com>
 2026-01-15 23:44:32 +00:00
Peter Steinberger
a4b347b454 feat: refine subagents + add chat.inject 
Co-authored-by: Tyler Yust <tyler6204@users.noreply.github.com>
 2026-01-15 23:44:31 +00:00
Peter Steinberger
688a0ce439 refactor: harden session store updates 
Co-authored-by: Tyler Yust <tyler6204@users.noreply.github.com>
 2026-01-15 23:41:34 +00:00
juanpablodlc
4a99b9b651
feat(whatsapp): add debounceMs for batching rapid messages (#971) 
* feat(whatsapp): add debounceMs for batching rapid messages

Add a `debounceMs` configuration option to WhatsApp channel settings
that batches rapid consecutive messages from the same sender into a
single response. This prevents triggering separate agent runs for
each message when a user sends multiple short messages in quick
succession (e.g., "Hey!", "how are you?", "I was wondering...").

Changes:
- Add `debounceMs` config to WhatsAppConfig and WhatsAppAccountConfig
- Implement message buffering in `monitorWebInbox` with:
  - Map-based buffer keyed by sender (DM) or chat ID (groups)
  - Debounce timer that resets on each new message
  - Message combination with newline separator
  - Single message optimization (no modification if only one message)
- Wire `debounceMs` through account resolution and monitor tuning
- Add UI hints and schema documentation

Usage example:
{
  "channels": {
    "whatsapp": {
      "debounceMs": 5000  // 5 second window
    }
  }
}

Default behavior: `debounceMs: 0` (disabled by default)

Verified: All existing tests pass (3204 tests), TypeScript compilation
succeeds with no errors.

Implemented with assistance from AI coding tools.

Closes #967

* chore: wip inbound debounce

* fix: debounce inbound messages across channels (#971) (thanks @juanpablodlc)

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
 2026-01-15 23:07:19 +00:00
Peter Steinberger
8b89980a89 feat(date-time): standardize time context and tool timestamps 2026-01-15 22:27:06 +00:00
Peter Steinberger
cb78fa46a1 fix: make node-llama-cpp optional 2026-01-15 18:37:02 +00:00
Peter Steinberger
b6fb24f6d2
Merge pull request #964 from bohdanpodvirnyi/feat/telegram-reactions 
feat(telegram): add bidirectional emoji reactions support
 2026-01-15 17:21:51 +00:00
Peter Steinberger
2b1c26f900 fix: refine telegram reactions (#964) (thanks @bohdanpodvirnyi) 2026-01-15 17:20:17 +00:00
Bohdan Podvirnyi
0e1dcf9cb4 feat: added capability for clawdbot to react 2026-01-15 17:07:38 +00:00
Peter Steinberger
36292d3fbb fix: preserve Antigravity Claude signatures (#959) (thanks @rdev) 2026-01-15 17:06:39 +00:00
Max
1ae344d8a6 Fix antigravity claude 2026-01-15 17:06:39 +00:00
Peter Steinberger
fc4aa9a683
Merge pull request #954 from roshanasingh4/fix/946-openai-completions-trim 
Fix model fallback crash on undefined provider/model (#946)
 2026-01-15 16:59:19 +00:00
Peter Steinberger
c043e9767f fix: default model fallback when provider/model missing (#954) (thanks @roshanasingh4) 2026-01-15 16:58:41 +00:00
Peter Steinberger
8b48299d8f
Merge pull request #953 from roshanasingh4/fix/cli-quick-reference-system-prompt 
Fix system prompt: prevent invented CLI commands
 2026-01-15 16:55:52 +00:00
Roshan Singh
0f27cff247 Fix model fallback crash on undefined provider/model (#946) 2026-01-15 16:50:46 +00:00
Roshan Singh
d0455f2683 fix(system-prompt): add CLI quick reference to prevent invented commands 2026-01-15 11:43:22 +00:00
Peter Steinberger
3a446dd400 style: oxfmt 2026-01-15 10:48:04 +00:00
Peter Steinberger
6042485367 fix(browser): default chrome profile to host 2026-01-15 10:43:39 +00:00
Peter Steinberger
9097ef90b7 docs(browser): clarify chrome extension profile usage 2026-01-15 10:22:29 +00:00
Peter Steinberger
4f1a4ab072 feat(browser): add snapshot refs=aria mode 2026-01-15 10:22:29 +00:00
Peter Steinberger
0facc63019 fix(skills): improve summarize selection 2026-01-15 10:14:59 +00:00
Peter Steinberger
f9170c5d02 fix(browser): keep tab stable across snapshot and act 2026-01-15 09:36:48 +00:00
Peter Steinberger
7e1e7ba2d8 fix(agents): skip thinking tags in code spans 2026-01-15 09:23:56 +00:00
Peter Steinberger
c86b257d38 docs(tools): hint chrome extension in browser tool prompt 2026-01-15 09:13:36 +00:00
Peter Steinberger
4291d56e0b chore: format + fix telegram thread ids 2026-01-15 09:13:19 +00:00
Peter Steinberger
1797233989 fix(tui): surface model errors 2026-01-15 08:31:02 +00:00
Peter Steinberger
081e5ef572 fix(tools): enable web_fetch by default 2026-01-15 07:42:07 +00:00
Cash Williams
51e871f9e5 Make timezone and 24 hour clock explicit in system prompt 2026-01-15 06:08:43 +00:00
Peter Steinberger
47634c294d style: format pi embedded utils 2026-01-15 06:08:17 +00:00
Peter Steinberger
2bd9e84851 fix(agents): strip tool leak text (#905) 
Thanks @erikpr1994.

Co-authored-by: Erik Pastor Rios <erikpastorrios1994@gmail.com>
 2026-01-15 05:58:02 +00:00
Erik
5c2eedc340 test: add thought tag stripping test case 2026-01-15 05:58:02 +00:00
Erik
3b7d103758 fix(agent): strip thinking tags from text content 2026-01-15 05:58:02 +00:00
Erik
8146c43aa3 fix(agents): strip leaked tool call text from assistant messages 
When replaying conversation history to Gemini, tool calls without
thought_signature are downgraded to text blocks like [Tool Call: ...].
This leaked internal technical info into user-facing chat messages.

Added stripDowngradedToolCallText filter alongside existing Minimax
filter to remove these text representations before extraction.
 2026-01-15 05:58:02 +00:00
Peter Steinberger
2e70c3ceab fix: return setup hint when web_search lacks key 2026-01-15 05:35:22 +00:00
Peter Steinberger
7d4f2d9aed
Merge pull request #928 from sebslight/feature/response-prefix-template-variables 
feat: add dynamic template variables to messages.responsePrefix
 2026-01-15 05:27:20 +00:00
Peter Steinberger
738b3592cd fix: remove conflict marker in google helper (#875) 2026-01-15 05:25:45 +00:00
Peter Steinberger
cd2af64860 fix: cap tool call IDs for OpenAI/OpenRouter (#875) (thanks @j1philli) 2026-01-15 05:25:45 +00:00
Josh Phillips
04f1e767b2 Fix OpenAI tool_call id length for OpenRouter 2026-01-15 05:25:45 +00:00
Peter Steinberger
139f80a291 chore: format sources and update protocol outputs 2026-01-15 05:17:19 +00:00
Peter Steinberger
57c66fe813 fix: clean up onboarding + channel selection types 2026-01-15 05:12:33 +00:00
Peter Steinberger
ef78b198cb feat: add Chrome extension browser relay 2026-01-15 04:52:28 +00:00
Peter Steinberger
5fdaef3646 fix: downgrade unsigned gemini thinking 2026-01-15 04:51:21 +00:00
Peter Steinberger
fa4670c5fe feat: improve agent auth guidance 2026-01-15 04:51:21 +00:00
Roshan Singh
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
Peter Steinberger
f275cc180b feat: add web tools 2026-01-15 04:07:40 +00:00
Peter Steinberger
31d3aef8d6 fix: prevent config clobbering 2026-01-15 04:06:11 +00:00
Sebastian
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
Peter Steinberger
429f973280 test: cover browser snapshot labels and efficient mode 2026-01-15 04:04:30 +00:00
Peter Steinberger
1c737f88fe test: cover provider tool policies 2026-01-15 03:55:20 +00:00
Peter Steinberger
fa8d9b9189 feat: add provider-specific tool policies 2026-01-15 03:55:20 +00:00
Peter Steinberger
a6e780b2f6 feat: add browser snapshot modes 2026-01-15 03:50:57 +00:00
Peter Steinberger
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
Peter Steinberger
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
Peter Steinberger
2b4a68e276 feat: load channel plugins 2026-01-15 02:42:44 +00:00
Peter Steinberger
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
Peter Steinberger
1b79730db8 style: apply oxfmt fixes 2026-01-15 01:53:14 +00:00
Peter Steinberger
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
George Pickett
393d21d86c Format: fix report + telegram formatting 2026-01-15 01:27:16 +00:00
George Pickett
232c512502 Format: apply oxfmt fixes 2026-01-15 01:27:16 +00:00
George Pickett
2d54efe851 Embedded runner: suppress raw API error payloads (#919) 2026-01-15 01:27:16 +00:00
Peter Steinberger
bcde09ae91 feat: add /context prompt breakdown 2026-01-15 01:06:35 +00:00
Peter Steinberger
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
sleontenko
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
Peter Steinberger
9b7df414e6 test: add gemini 3 antigravity switch live repro 2026-01-15 00:29:53 +00:00
Peter Steinberger
fe974f420d chore: standardize Claude Code CLI naming (#915) 
Follow-up to #915.
 2026-01-14 20:07:35 +00:00
Peter Steinberger
c379191f80 chore: migrate to oxlint and oxfmt 
Co-authored-by: Christoph Nakazawa <christoph.pojer@gmail.com>
 2026-01-14 15:02:19 +00:00
Peter Steinberger
40fb59e5f7 refactor(live-tests): stabilize docker live suites 2026-01-14 09:52:39 +00:00
Peter Steinberger
e2f8909982 refactor(agents): split tools + PI subscribe 2026-01-14 05:39:59 +00:00
Peter Steinberger
a44f1912b3 chore(repo): drop .DS_Store 2026-01-14 01:17:56 +00:00
Peter Steinberger
bcbfb357be refactor(src): split oversized modules 2026-01-14 01:17:56 +00:00
Peter Steinberger
b071f73fef fix: resume subagent registry safely (#831) (thanks @roshanasingh4) 2026-01-13 10:10:15 +00:00
Roshan Singh
714de9d996 Persist subagent registry across restarts 2026-01-13 10:00:30 +00:00
Peter Steinberger
90342a4f3a refactor!: rename chat providers to channels 2026-01-13 08:40:39 +00:00
Peter Steinberger
e8779ac329 fix: handle Anthropic overloaded_error gracefully (#832) (thanks @danielz1z) 2026-01-13 08:32:06 +00:00
danielz1z
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
Peter Steinberger
f825dd2897 chore(lint): format live profiles test 2026-01-13 08:03:58 +00:00
Peter Steinberger
9faa95d558 fix: recover from compaction overflow 2026-01-13 08:03:11 +00:00
Peter Steinberger
9007920695 fix(auth): drop invalid auth profiles from order 2026-01-13 07:53:38 +00:00
Peter Steinberger
2887376646 test: stabilize gpt-5.2 tool-only live check 2026-01-13 07:51:24 +00:00
Peter Steinberger
ba7d12f205 refactor: centralize onboarding auth paths 2026-01-13 07:12:20 +00:00
Peter Steinberger
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
Peter Steinberger
3368284b2a fix: per-agent model fallbacks (#583) (thanks @mitschabaude-bot) 2026-01-13 06:50:41 +00:00
Gregor's Bot
9c0c4f50ec Agents: test per-agent model fallbacks override 2026-01-13 06:50:20 +00:00
Gregor's Bot
6729637f61 Config: support per-agent model fallbacks 2026-01-13 06:50:20 +00:00
Peter Steinberger
18d22aa426 fix: gate xhigh by model (#444) (thanks @grp06) 2026-01-13 06:48:41 +00:00
George Pickett
a3641526ab Thinking: gate xhigh by model 2026-01-13 06:48:26 +00:00
Peter Steinberger
f50e06a1b6 test(tools): cover tool policy helpers 2026-01-13 06:32:59 +00:00
Peter Steinberger
780a43711f feat(tools): add tool profiles and group shorthands 2026-01-13 06:30:20 +00:00
Peter Steinberger
d682b604de fix(tools): harden tool schemas for strict providers 2026-01-13 06:30:20 +00:00
Peter Steinberger
1fdd3592d3 fix: tune compaction safeguard schema (#700) (thanks @thewilloftheshadow) 2026-01-13 05:58:35 +00:00
Shadow
a96d299971 Agents: safeguard compaction summarization 2026-01-13 05:55:30 +00:00
Peter Steinberger
61b7398cb7 refactor: centralize auth-choice model defaults 2026-01-13 05:25:16 +00:00
Jefferson Warrior
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
Peter Steinberger
8d640ccc68
Merge pull request #726 from FrieSei/feature/chutes-oauth 
Auth: add Chutes OAuth
 2026-01-13 05:02:25 +00:00
Peter Steinberger
f566e6451f fix: harden Chutes OAuth flow (#726) (thanks @FrieSei) 2026-01-13 05:01:08 +00:00
Peter Steinberger
75a7855223 feat: cron ISO at + delete-after-run 2026-01-13 04:55:48 +00:00
Friederike Seiler
3271ff1d6e Tests: clean chutes fetch spies 2026-01-13 04:50:27 +00:00
Friederike Seiler
0efcfc0864 Chores: fix chutes oauth build 2026-01-13 04:50:27 +00:00
Friederike Seiler
4efb5cc18e Auth: add Chutes OAuth 2026-01-13 04:50:26 +00:00
Peter Steinberger
57db3f22a1 fix: clean lint in auth-choice + tests 2026-01-13 04:49:04 +00:00
Peter Steinberger
d4c205f8e1 fix: start typing on message start 2026-01-13 04:33:24 +00:00
Peter Steinberger
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
Peter Steinberger
755a7e1b20 feat: add configurable bootstrap truncation 2026-01-13 04:27:03 +00:00
Peter Steinberger
3061d8e057 fix: preserve Windows cmd start URL quoting (#794) (thanks @roshanasingh4) 2026-01-13 04:26:43 +00:00
Peter Steinberger
ea5597b483 fix: restore implicit providers + copilot auth choice 2026-01-13 04:26:08 +00:00
Peter Steinberger
b41e75a15d feat: cron agent binding + doctor UI refresh 2026-01-13 04:25:41 +00:00
meaningfool
f249a82383 fix: resolve CI failures (test timeout & formatting) 2026-01-13 04:25:41 +00:00
Peter Steinberger
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
Peter Steinberger
2a9ef806a0 fix: strip only msg_* thought_signature (#805) (thanks @marcmarg) 2026-01-13 04:13:24 +00:00
Peter Steinberger
32115a8b98 test: expand auth fallback coverage 2026-01-13 04:12:16 +00:00
Marc
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
Peter Steinberger
2c2ca7f03b fix: treat credential validation errors as auth errors (#822) (thanks @sebslight) 2026-01-13 04:02:47 +00:00
Sebastian
c4014c0092 fix: treat credential validation failures as auth errors for fallback (#761) 2026-01-12 22:53:21 -05:00
Peter Steinberger
66ad8a9289 fix: apply lint fixes 2026-01-13 03:36:53 +00:00
Peter Steinberger
df6634727e fix: refine synthetic provider + minimax probes 2026-01-13 03:36:53 +00:00
Travis Hinton
8b5cd97ceb Add Synthetic provider support 2026-01-13 03:36:53 +00:00
Shadow
ab993904d7
Models: normalize Gemini 3 ids in runtime selection 
Closes #795
 2026-01-12 21:32:53 -06:00
Peter Steinberger
da0a062fa7 fix: memory search remote overrides (#819) (thanks @mukhtharcm) 2026-01-13 03:11:03 +00:00
Muhammed Mukhthar CM
ba316a10cc feat: add remote config overrides to memorySearch 2026-01-13 03:02:43 +00:00
Peter Steinberger
46a694bbc7 fix: preserve explicit maxChars=0 (#796) (thanks @gabriel-trigo) 2026-01-13 02:33:38 +00:00
Gabriel Trigo
79a6506593 fix(browser): limit ai snapshot size 
test(browser): cover ai snapshot limit
 2026-01-13 02:33:38 +00:00
Peter Steinberger
8edf2146ae fix: cleanup stale resume cli processes 2026-01-13 02:21:20 +00:00
Peter Steinberger
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