negodiy/openclaw
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
17,865 Commits 1 Branch 0 Tags
8e3f3bc3cf4744e38442d177573f706b78fbc0c5
Commit Graph

4611 Commits

Author SHA1 Message Date
Peter Steinberger
0f53177971 fix(tests): stabilize diffs localReq headers (supersedes #39063) 
Co-authored-by: Shennng <Shennng@users.noreply.github.com>
 2026-03-07 18:57:35 +00:00
Peter Steinberger
253e159700 fix: harden workspace skill path containment 2026-03-07 18:56:15 +00:00
Peter Steinberger
5effa6043e fix(agents): land #38935 from @MumuTW 
Co-authored-by: MumuTW <MumuTW@users.noreply.github.com>
 2026-03-07 18:55:49 +00:00
Peter Steinberger
231c1fa37a fix(models): land #38947 from @davidemanuelDEV 
Co-authored-by: davidemanuelDEV <davidemanuelDEV@users.noreply.github.com>
 2026-03-07 18:54:12 +00:00
Peter Steinberger
2f59a3cff3 fix(gateway): land #39064 from @Narcooo 
Co-authored-by: Narcooo <Narcooo@users.noreply.github.com>
 2026-03-07 18:52:42 +00:00
Peter Steinberger
2ada1b71b6 fix(models-auth): land #38951 from @MumuTW 
Co-authored-by: MumuTW <MumuTW@users.noreply.github.com>
 2026-03-07 18:51:17 +00:00
Peter Steinberger
8bd0eb5424 fix(outbound): land #38944 from @Narcooo 
Co-authored-by: Narcooo <Narcooo@users.noreply.github.com>
 2026-03-07 18:46:48 +00:00
Peter Steinberger
10d0e3f3ca fix(dashboard): keep gateway tokens out of URL storage 2026-03-07 18:33:30 +00:00
Peter Steinberger
46e324e269 docs(changelog): credit hook auth throttling report 2026-03-07 18:05:11 +00:00
Peter Steinberger
44820dcead fix(hooks): gate methods before auth lockout accounting 2026-03-07 18:05:09 +00:00
jsk
262fef6ac8 fix(discord): honor commands.allowFrom in guild slash auth (#38794) 
* fix(discord): honor commands.allowFrom in guild slash auth

* Update native-command.ts

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update native-command.commands-allowfrom.test.ts

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* fix(discord): address slash auth review feedback

* test(discord): add slash auth coverage for allowFrom variants

* fix: add changelog entry for discord slash auth fix (#38794) (thanks @jskoiz)

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Shadow <hi@shadowing.dev>
 2026-03-07 12:03:52 -06:00
Peter Steinberger
c6472c189f chore: land #39056 Node version hint sync (thanks @onstash) 
Land contributor change from #39056 and append changelog credit for @onstash.

Co-authored-by: Santosh Venkatraman <santosh.venk@gmail.com>
 2026-03-07 17:51:54 +00:00
Peter Steinberger
46715371b0 fix(security): strip custom auth headers on cross-origin redirects 2026-03-07 17:34:42 +00:00
Josh Avant
8e20dd22d8 Secrets: harden SecretRef-safe models.json persistence (#38955) 2026-03-07 11:28:39 -06:00
Peter Steinberger
b08337b902 docs(changelog): credit allowlist scoping report 2026-03-07 17:09:28 +00:00
Vincent Koc
70da80bcb5 Auto-reply: scope allowlist store writes by account (#39015) 
* Auto-reply: scope allowlist store writes

* Tests: cover allowlist store account scoping

* Changelog: note allowlist store scoping hardening
 2026-03-07 08:51:20 -08:00
Peter Steinberger
3a50e46cbf fix(nostr): harden profile mutation proxy guards 2026-03-07 16:44:21 +00:00
Peter Steinberger
1dd4f92ea2 fix: default local onboarding tools profile to coding 2026-03-07 16:41:27 +00:00
Muhammed Mukhthar CM
4f08dcccfd Mattermost: add interactive model picker (#38767) 
Merged via squash.

Prepared head SHA: 0883654e887b1176fc9299370b4ef5a351f5ac9d
Co-authored-by: mukhtharcm <56378562+mukhtharcm@users.noreply.github.com>
Co-authored-by: mukhtharcm <56378562+mukhtharcm@users.noreply.github.com>
Reviewed-by: @mukhtharcm
 2026-03-07 21:45:29 +05:30
Florian Hines
33e7394861 fix(providers): make all models available in kilocode provider (#32352) 
* kilocode: dynamic model discovery, kilo/auto default, cooldown exemption

- Replace 9-model hardcoded catalog with dynamic discovery from
  GET /api/gateway/models (Venice-like pattern with static fallback)
- Default model changed from anthropic/claude-opus-4.6 to kilo/auto
  (smart routing model)
- Add createKilocodeWrapper for X-KILOCODE-FEATURE header injection
  and reasoning.effort handling (skip for kilo/auto)
- Add kilocode to cooldown-exempt providers (proxy like OpenRouter)
- Keep sync buildKilocodeProvider for onboarding, add async
  buildKilocodeProviderWithDiscovery for implicit provider resolution
- Per-token gateway pricing converted to per-1M-token for cost fields

* kilocode: skip reasoning injection for x-ai models, harden discovery loop

* fix(kilocode): keep valid discovered duplicates (openclaw#32352, thanks @pandemicsyn)

* refactor(proxy): normalize reasoning payload guards (openclaw#32352, thanks @pandemicsyn)

* chore(changelog): note kilocode hardening (openclaw#32352, thanks @pandemicsyn and @vincentkoc)

* chore(changelog): fix kilocode note format (openclaw#32352, thanks @pandemicsyn and @vincentkoc)

* test(kilocode): support auto-model override cases (openclaw#32352, thanks @pandemicsyn)

* Update CHANGELOG.md

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
 2026-03-07 08:14:06 -08:00
Jason
786ec21b5a docs(cli): improve memory command examples (#31803) 
Merged via squash.

Prepared head SHA: 15dcda3027f836e3f780533f7dc6d05c81c6b65a
Co-authored-by: JasonOA888 <101583541+JasonOA888@users.noreply.github.com>
Co-authored-by: altaywtf <9790196+altaywtf@users.noreply.github.com>
Reviewed-by: @altaywtf
 2026-03-07 19:03:23 +03:00
Nimrod Gutman
1eb7198bad fix(ios): skip quick setup when a gateway is configured (#38964) 
* fix(ios): hide quick setup when gateway is configured

* fix: note ios quick setup gating for configured gateways (#38964) (thanks @ngutman)
 2026-03-07 17:46:16 +02:00
Nimrod Gutman
0bac6e4d67 fix: add changelog note for ios app store connect release prep (#38936) (thanks @ngutman) 2026-03-07 17:21:07 +02:00
Rodrigo Uroz
4c0b873a4d Config/Compaction: expose safeguard preserve and quality settings (#25557) 
Merged via squash.

Prepared head SHA: ea9904039a35d8d9ced55cd6d1c459a46666954d
Co-authored-by: rodrigouroz <384037+rodrigouroz@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
 2026-03-07 07:13:13 -08:00
Ayaan Zaidi
bdd0f74188 docs: add changelog for markdown image hardening (#38895) 2026-03-07 19:46:41 +05:30
Ayaan Zaidi
9e1de97a69 fix(telegram): route native topic commands to the active session (#38871) 
* fix(telegram): resolve session entry for /stop in forum topics

Fixes #38675

- Export normalizeStoreSessionKey from store.ts for reuse
- Use it in resolveSessionEntryForKey so topic session keys (lowercase
  in store) are found when handling /stop
- Add test for forum topic session key lookup

* fix(telegram): share native topic routing with inbound messages

* fix: land telegram topic routing follow-up (#38871)

---------

Co-authored-by: xialonglee <li.xialong@xydigit.com>
 2026-03-07 19:01:16 +05:30
Ayaan Zaidi
05c240fad6 fix: restart Windows gateway via Scheduled Task (#38825) (#38825) 2026-03-07 18:00:38 +05:30
Ayaan Zaidi
26c9796736 fix: check managed systemd unit before is-enabled (#38819) 2026-03-07 17:11:07 +05:30
Peter Steinberger
f358c6f2fb docs: reorder 2026.3.7 changelog highlights 2026-03-07 10:10:42 +00:00
Peter Steinberger
997a9f5b9e chore: bump version to 2026.3.7 2026-03-07 10:09:02 +00:00
Ayaan Zaidi
2018d8aa99 docs: add changelog entry for Android package rename (#38712) 2026-03-07 14:51:03 +05:30
Tak Hoffman
8873e13f1e fix(gateway): stop stale-socket restarts before first event (#38643) 
* fix(gateway): guard stale-socket restarts by event liveness

* fix(gateway): centralize connect-time liveness tracking

* fix(web): apply connected status patch atomically

* fix(gateway): require active socket for stale checks

* fix(gateway): ignore inherited stale event timestamps
 2026-03-07 00:58:08 -06:00
ql-wade
a5c07fa115 fix(gateway): skip stale-socket restarts for Telegram polling (openclaw#38405) 
Verified:
- pnpm build
- pnpm check
- pnpm test:macmini

Co-authored-by: ql-wade <262266039+ql-wade@users.noreply.github.com>
 2026-03-07 00:20:34 -06:00
拐爷&&老拐瘦
2e31aead39 fix(gateway): invalidate bootstrap cache on session rollover (openclaw#38535) 
Verified:
- pnpm install --frozen-lockfile
- pnpm build
- pnpm check
- pnpm test:macmini

Co-authored-by: yfge <1186273+yfge@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
 2026-03-06 23:46:02 -06:00
Ayaan Zaidi
e802840b62 docs: update changelog for reply media delivery (#38572) 2026-03-07 10:52:16 +05:30
Xinhua Gu
024af2b738 fix(feishu): disable block streaming to prevent silent reply drops (openclaw#38422) 
Verified:
- pnpm build
- pnpm check
- pnpm test:macmini

Co-authored-by: xinhuagu <562450+xinhuagu@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
 2026-03-06 22:33:30 -06:00
ql-wade
e309a15d73 fix: suppress ACP NO_REPLY fragments in console output (#38436) 2026-03-07 09:34:45 +05:30
Xinhua Gu
1a022a31de fix(gateway): classify wrapped "fetch failed" messages as transient network errors (openclaw#38530) 
Verified:
- pnpm build
- pnpm check
- pnpm test:macmini

Co-authored-by: xinhuagu <562450+xinhuagu@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
 2026-03-06 21:47:32 -06:00
Jakob
fa69f836c4 fix: increase maxTokens for tool probe to support reasoning models 
Closes #7521
 2026-03-06 22:27:28 -05:00
Tak Hoffman
a01978ba96 fix(googlechat): inherit shared defaults for multi-account webhook auth (#38492) 
* fix(googlechat): inherit shared defaults from accounts.default

* fix(googlechat): do not inherit default enabled state

* fix(googlechat): avoid inheriting default credentials

* fix(googlechat): keep dangerous auth flags account-local
 2026-03-06 21:11:55 -06:00
Vincent Koc
563a125c66 fix(gateway): stop shared-main chat.send from inheriting stale external routes (#38418) 
* fix(gateway): prevent webchat messages from cross-routing to external channels

chat.send always originates from the webchat/control-UI surface.  Previously,
channel-scoped session keys (e.g. agent:main:slack:direct:U…) caused
OriginatingChannel to inherit the session's stored external route, so the
reply dispatcher would route responses to Slack/Telegram instead of back to
the gateway connection.  Remove the route-inheritance logic from chat.send and
always set OriginatingChannel to INTERNAL_MESSAGE_CHANNEL ("webchat").

Closes #34647

Made-with: Cursor

* Gateway: preserve configured-main connect gating

* Gateway: cover connect-without-client routing

* Gateway: add chat.send session key length limit

* Gateway: cap chat.send session key schema

* Gateway: bound chat.send session key parsing

* Gateway: cover oversized chat.send session keys

* Update CHANGELOG.md

---------

Co-authored-by: SidQin-cyber <sidqin0410@gmail.com>
 2026-03-06 21:59:08 -05:00
Vincent Koc
bf623a580b Agents: add skill API rate-limit guardrail (#38452) 
* Agents: add rate-limit guardrail for skill API writes

* Changelog: note skill API rate-limit awareness
 2026-03-06 20:20:00 -05:00
Vincent Koc
3070fafec1 fix(venice): switch default model to kimi-k2-5 (#38423) 
* Docs: refresh Venice default model guidance

* Venice: switch default model to Kimi K2.5

* Changelog: credit Venice default refresh
 2026-03-06 19:31:07 -05:00
OfflynAI
adb9234d03 fix(imessage): prevent echo loop from leaking internal metadata and amplifying NO_REPLY into queue overflow (#33295) 
* fix(imessage): prevent echo loop from leaking internal metadata and amplifying NO_REPLY into queue overflow

- Add outbound sanitization at channel boundary (sanitize-outbound.ts):
  strips thinking/reasoning tags, relevant-memories tags, model-specific
  separators (+#+#), and assistant role markers before iMessage delivery

- Add inbound reflection guard (reflection-guard.ts): detects and drops
  messages containing assistant-internal markers that indicate a reflected
  outbound message, preventing recursive echo amplification

- Harden echo cache: increase text TTL from 5s to 30s to catch delayed
  reflections that previously expired before the echo could be detected

- Add loop rate limiter (loop-rate-limiter.ts): per-conversation rapid-fire
  detection that suppresses conversations exceeding threshold within a
  time window, acting as a safety net against amplification

Closes #33281

* fix(imessage): address review — stricter reflection regex, loop-aware rate limiter

- Reflection guard: require closing > bracket on thinking/final/memory
  tag patterns to prevent false-positives on user phrases like
  '<final answer>' or '<thought experiment>' (#33295 review)

- Rate limiter: only record echo/reflection/from-me drops instead of
  all dispatches, so the limiter acts as a loop-specific escalation
  mechanism rather than a general throttle on normal conversation
  velocity (#33295 review)

* Changelog: add iMessage echo-loop hardening entry

* iMessage: restore short echo-text TTL

* iMessage: ignore reflection markers in code

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
 2026-03-06 19:19:57 -05:00
Vincent Koc
5320ee7731 fix(venice): harden discovery limits and tool support (#38306) 
* Config: add supportsTools compat flag

* Agents: add model tool support helper

* Venice: sync discovery and fallback metadata

* Agents: skip tools for unsupported models

* Changelog: note Venice provider hardening

* Update CHANGELOG.md

* Venice: cap degraded discovery metadata

* Apply suggestion from @greptile-apps[bot]

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* Venice: tolerate partial discovery capabilities

* Venice: tolerate missing discovery specs

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
 2026-03-06 19:07:11 -05:00
SP
942c53e7f0 fix(agents): prevent totalTokens crash when assistant usage is missing (#34977) 
Merged via squash.

Prepared head SHA: 1c14094f3f85f2c87596df2d67fd0ca6af4e9084
Co-authored-by: sp-hk2ldn <8068616+sp-hk2ldn@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
 2026-03-06 15:59:16 -08:00
Marcus Widing
48b3c4a043 fix(auth): treat unconfigured-owner sessions as owner for ownerOnly tools (#26331) 
Merged via squash.

Prepared head SHA: 1fbe1c765102c223b4e8d6f8e831db54c975430d
Co-authored-by: widingmarcus-cyber <245375637+widingmarcus-cyber@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
 2026-03-06 15:37:07 -08:00
Drew Wagner
ae96a81916 fix: strip skill-injected env vars from ACP harness spawn env (#36280) (#36316) 
* fix: strip skill-injected env vars from ACP harness spawn env

Skill apiKey entries (e.g., openai-image-gen with primaryEnv=OPENAI_API_KEY)
are set on process.env during agent runs and only reverted after the run
completes. ACP harnesses like Codex CLI inherit these vars, causing them
to silently use API billing instead of their own auth (e.g., OAuth).

The fix tracks which env vars are actively injected by skill overrides in
a module-level Set (activeSkillEnvKeys) and strips them in
resolveAcpClientSpawnEnv() before spawning ACP child processes.

Fixes #36280

* ACP: type spawn env for stripped keys

* Skills: cover active env key lifecycle

* Changelog: note ACP skill env isolation

* ACP: preserve shell marker after env stripping

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
 2026-03-06 18:18:13 -05:00
Efe Büken
03b9abab84 feat(compaction): make post-compaction context sections configurable (#34556) 
Merged via squash.

Prepared head SHA: 491bb28544b2e0d3563dd1c78593ed2d829d65f6
Co-authored-by: efe-arv <259833796+efe-arv@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
 2026-03-06 14:57:15 -08:00
Altay
6e962d8b9e fix(agents): handle overloaded failover separately (#38301) 
* fix(agents): skip auth-profile failure on overload

* fix(agents): note overload auth-profile fallback fix

* fix(agents): classify overloaded failures separately

* fix(agents): back off before overload failover

* fix(agents): tighten overload probe and backoff state

* fix(agents): persist overloaded cooldown across runs

* fix(agents): tighten overloaded status handling

* test(agents): add overload regression coverage

* fix(agents): restore runner imports after rebase

* test(agents): add overload fallback integration coverage

* fix(agents): harden overloaded failover abort handling

* test(agents): tighten overload classifier coverage

* test(agents): cover all-overloaded fallback exhaustion

* fix(cron): retry overloaded fallback summaries

* fix(cron): treat HTTP 529 as overloaded retry
 2026-03-07 01:42:11 +03:00