f16ecd1dac
fix(ollama): unify context window handling across discovery, merge, and OpenAI-compat transport ( #29205 )
...
* fix(ollama): inject num_ctx for OpenAI-compatible transport
* fix(ollama): discover per-model context and preserve higher limits
* fix(agents): prefer matching provider model for fallback limits
* fix(types): require numeric token limits in provider model merge
* fix(types): accept unknown payload in ollama num_ctx wrapper
* fix(types): simplify ollama settled-result extraction
* config(models): add provider flag for Ollama OpenAI num_ctx injection
* config(schema): allow provider num_ctx injection flag
* config(labels): label provider num_ctx injection flag
* config(help): document provider num_ctx injection flag
* agents(ollama): gate OpenAI num_ctx injection with provider config
* tests(ollama): cover provider num_ctx injection flag behavior
* docs(config): list provider num_ctx injection option
* docs(ollama): document OpenAI num_ctx injection toggle
* docs(config): clarify merge token-limit precedence
* config(help): note merge uses higher model token limits
* fix(ollama): cap /api/show discovery concurrency
* fix(ollama): restrict num_ctx injection to OpenAI compat
* tests(ollama): cover ipv6 and compat num_ctx gating
* fix(ollama): detect remote compat endpoints for ollama-labeled providers
* fix(ollama): cap per-model /api/show lookups to bound discovery load
2026-02-27 17:20:47 -08:00
70a4f25ab1
fix(security): remove post-compaction audit injection message ( #28507 )
...
* fix: remove post-compaction audit injection (Layer 3)
Remove the post-compaction read audit that injects fake system messages
into conversations after context compaction. This audit:
- Hardcodes WORKFLOW_AUTO.md (a file that doesn't exist in standard
workspaces) as a required read after every compaction
- Leaks raw regex syntax (memory\/\d{4}-\d{2}-\d{2}\.md) in
user-facing warning messages
- Injects messages via enqueueSystemEvent that appear as user-role
messages, tricking agents into reading attacker-controlled files
- Creates a persistent prompt injection vector (see #27697 )
Layer 1 (compaction summary) and Layer 2 (workspace context refresh
from AGENTS.md via post-compaction-context.ts) remain intact and are
sufficient for post-compaction context recovery.
Deleted files:
- src/auto-reply/reply/post-compaction-audit.ts
- src/auto-reply/reply/post-compaction-audit.test.ts
Modified files:
- src/auto-reply/reply/agent-runner.ts (removed imports, audit map,
flag setting, and Layer 3 audit block)
Fixes #27697 , fixes #26851 , fixes #20484 , fixes #22339 , fixes #25600
Relates to #26461
* fix: resolve lint failures from post-compaction audit removal
* Tests: add regression for removed post-compaction audit warnings
---------
Co-authored-by: Wilfred (OpenClaw Agent) <jay@openclaw.dev>
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-02-27 17:15:59 -08:00
a509154be5
Feishu: send media payloads as attachments (openclaw#28959) thanks @icesword0760
...
Verified:
- pnpm build
- pnpm check
- pnpm test:macmini
Co-authored-by: icesword0760 <23316247+icesword0760@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-02-27 19:06:27 -06:00
5cb2a3aa1b
Tests: validate discord slash command options
2026-02-27 18:41:16 -06:00
32ee2f0109
fix(feishu): break infinite typing-indicator retry loop on rate-limit / quota errors (openclaw#28494) thanks @guoqunabc
...
Verified:
- pnpm build
- pnpm check
- pnpm test:macmini
Co-authored-by: guoqunabc <9532020+guoqunabc@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-02-27 18:41:08 -06:00
0e755ad99a
fix(feishu): use msg_type "audio" for opus files instead of "media" (openclaw#28269) thanks @Glucksberg
...
Verified:
- pnpm build
- pnpm check
- pnpm test:macmini
Co-authored-by: Glucksberg <80581902+Glucksberg@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-02-27 18:23:19 -06:00
60ef923051
fix(feishu): cache probeFeishu() results with 10-min TTL to reduce API calls (openclaw#28907) thanks @Glucksberg
...
Verified:
- pnpm build
- pnpm check
- pnpm test:macmini
Co-authored-by: Glucksberg <80581902+Glucksberg@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-02-27 18:15:28 -06:00
56fa05838a
feat(feishu): support Docx table create/write + image/file upload actions in feishu_doc ( #20304 )
...
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-02-27 18:00:56 -06:00
1725839720
fix(tools): honor tools.fs.workspaceOnly=false for host write/edit ( #28822 )
...
Merged via squash.
Prepared head SHA: 83d432961d
2026-02-28 00:53:20 +01:00
ad804b0356
fix(feishu): propagate mediaLocalRoots for local file sends ( #27884 ) (openclaw#27928) thanks @joelnishanth
...
Verified:
- pnpm build
- pnpm check
- pnpm test:macmini
Co-authored-by: joelnishanth <140015627+joelnishanth@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-02-27 17:43:57 -06:00
bf9585d056
PR: Feishu Plugin - Auto-grant document permissions to requesting user (openclaw#28295) thanks @zhoulongchao77
...
Verified:
- pnpm build
- pnpm check
- pnpm test:macmini
Co-authored-by: zhoulongchao77 <65058500+zhoulongchao77@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-02-27 17:34:18 -06:00
fa5e71d1ae
fix: harden Ollama autodiscovery and warning behavior ( #29201 )
...
* agents: auto-discover Ollama models without API key
* tests: cover Ollama autodiscovery warning behavior
2026-02-27 15:22:34 -08:00
d17c083803
docs(ollama): clarify /v1 tool-calling guidance ( #29204 )
2026-02-27 15:21:13 -08:00
de77497ea8
chore: add convex to sponsors table
2026-02-27 23:27:27 +01:00
4aa2dc6857
fix(infra): land #29078 from @cathrynlavery with restart fallback
...
Co-authored-by: Cathryn Lavery <cathryn@littlemight.com>
2026-02-27 22:04:46 +00:00
db67492a00
fix(infra): actively kickstart launchd on supervised gateway restart
...
When an agent triggers a gateway restart in supervised mode, the process
exits expecting launchd KeepAlive to respawn it. But ThrottleInterval
(default 10s, or 60s on older installs) can delay or prevent restart.
Now calls triggerOpenClawRestart() to issue an explicit launchctl
kickstart before exiting, ensuring immediate respawn. Falls back to
in-process restart if kickstart fails.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-27 22:02:05 +00:00
ee2eaddeb3
fix(onboard): increase verification timeout and reduce max_tokens for custom provider probes ( #27380 )
...
* fix(onboard): increase verification timeout and reduce max_tokens for custom provider probes
The onboard wizard sends a chat-completion request to verify custom
providers. With max_tokens: 1024 and a 10 s timeout, large local
models (e.g. Qwen3.5-27B on llama.cpp) routinely time out because
the server needs to load the model and generate up to 1024 tokens
before responding.
Changes:
- Raise VERIFY_TIMEOUT_MS from 10 s to 30 s
- Lower max_tokens from 1024 to 1 (verification only needs a single
token to confirm the API is reachable and the model ID is valid)
- Add explicit stream: false to both OpenAI and Anthropic probes
Closes #27346
Made-with: Cursor
* Changelog: note custom-provider onboarding verification fix
---------
Co-authored-by: Philipp Spiess <hello@philippspiess.com>
2026-02-27 22:51:58 +01:00
46d9605ef8
merge-pr: use short squash merge banner
2026-02-27 21:41:24 +00:00
12618c333c
tests: complete openai-responses model fixture typing
2026-02-27 22:30:30 +01:00
f943c76cde
security(feishu): bound unauthenticated webhook rate-limit state (openclaw#26050) thanks @bmendonca3
...
Verified:
- pnpm install --frozen-lockfile
- pnpm build
- pnpm check
- pnpm test:macmini
Co-authored-by: bmendonca3 <208517100+bmendonca3@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-02-27 13:22:24 -06:00
3882b8a5be
ci: fix CONTRIBUTING.md oxfmt formatting
...
- Remove trailing blank line after Jonathan Taylor entry
- Escape underscore in @jlehman_ X handle
Fixes #29039
2026-02-27 11:12:04 -08:00
8bc80fad47
fix(slack): land #29032 /agentstatus alias from @maloqab
...
Land contributor PR #29032 by @maloqab with Slack native alias docs, integration tests, and changelog entry.
Co-authored-by: maloqab <mitebaloqab@gmail.com>
2026-02-27 19:09:38 +00:00
1867611733
fix(memory): readonly sync recovery (openclaw#25799) thanks @rodrigouroz
...
Verified:
- pnpm build
- pnpm check
- pnpm test:macmini (fails in this environment at src/daemon/launchd.integration.test.ts beforeAll hook timeout; merged with Tak override)
Co-authored-by: rodrigouroz <384037+rodrigouroz@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-02-27 12:26:43 -06:00
2916152f83
Add contributor Josh Lehman to CONTRIBUTING.md
2026-02-27 12:03:49 -06:00
15cf288d73
Update CHANGELOG.md
2026-02-27 09:11:58 -08:00
dede4089a6
docs(openai): add clear server compaction toggle examples
2026-02-27 16:21:08 +00:00
645791c35e
ci: add timeout for windows checks job
2026-02-27 16:20:02 +00:00
8da3a9a92d
fix(agents): auto-enable OpenAI Responses server-side compaction ( #16930 , #22441 , #25088 )
...
Landed from contributor PRs #16930 , #22441 , and #25088 .
Co-authored-by: liweiguang <codingpunk@gmail.com>
Co-authored-by: EdwardWu7 <wuzhiyuan7@gmail.com>
Co-authored-by: MoerAI <friendnt@g.skku.edu>
2026-02-27 16:15:50 +00:00
6675aacb5e
feat(memory-lancedb): Custom OpenAI BaseURL & Dimensions Support ( #17874 )
...
* feat(memory-lancedb): add custom baseUrl and dimensions support
* fix(memory-lancedb): strict model typing and safe dimension resolution
* style: fix formatting in memory-lancedb config
* fix(memory-lancedb): sync manifest schema with new embedding options
---------
Co-authored-by: OpenClaw Bot <bot@openclaw.ai>
2026-02-27 07:56:09 -08:00
62fa65ec85
Fix npm global install deprecation warnings ( #28318 )
...
* Dependencies: make @discordjs/opus an optional peer
* Dependencies: bump node-llama-cpp peer to 3.16.2
* Dependencies: pin Google auth deps to warning-free versions
* CI: reduce Dependabot cooldown to 2 days
* CI: fix invalid Dependabot npm registry config
* CI: restore Dependabot npm registry with token auth
* Dependencies: remove global Google auth pnpm overrides
* CI: make Dependabot updates daily
* Dependencies: restore optional install semantics for @discordjs/opus
* CI: keep Docker Dependabot interval weekly
2026-02-27 07:38:02 -08:00
fe807e4bed
chore(release): bump 2026.2.27 and split changelog
2026-02-27 16:09:28 +01:00
0fe6cf06b2
Compaction: preserve opaque identifiers in summaries (openclaw#25553) thanks @rodrigouroz
...
Verified:
- pnpm install --frozen-lockfile
- pnpm build
- pnpm check
- pnpm test:macmini
Co-authored-by: rodrigouroz <384037+rodrigouroz@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-02-27 08:14:05 -06:00
84a88b2ace
feat(i18n): add German (de) locale ( #28495 )
...
Merged via /review-pr -> /prepare-pr -> /merge-pr.
Prepared head SHA: e418326aaf
2026-02-27 11:44:09 +01:00
6b317b1f17
fix(agents): normalize whitespace-padded tool call names before dispatch ( #27094 )
...
Fix tool-call lookup failures when models emit whitespace-padded names by normalizing
both transcript history and live streamed embedded-runner tool calls before dispatch.
Co-authored-by: wangchunyue <80630709+openperf@users.noreply.github.com>
Co-authored-by: Sid <sidqin0410@gmail.com>
Co-authored-by: Philipp Spiess <hello@philippspiess.com>
2026-02-27 11:26:37 +01:00
aae90cb036
fix(telegram): include replied media files in reply context ( #28488 )
...
* fix(telegram): include replied media files in reply context
* fix(telegram): keep reply media fields nullable
* perf(telegram): defer reply-media fetch to debounce flush
* fix(telegram): gate and preserve reply media attachments
* fix(telegram): preserve cached-sticker reply media context
* fix: update changelog for telegram reply-media context fixes (#28488 ) (thanks @obviyus)
2026-02-27 15:16:21 +05:30
a7929abad8
Discord: thread bindings idle + max-age lifecycle ( #27845 ) (thanks @osolmaz)
...
* refactor discord thread bindings to idle and max-age lifecycle
* fix: migrate legacy thread binding expiry and reduce hot-path disk writes
* refactor: remove remaining thread-binding ttl legacy paths
* fix: harden thread-binding lifecycle persistence
* Discord: fix thread binding types in message/reply paths
* Infra: handle win32 unknown inode in file identity checks
* Infra: relax win32 guarded-open identity checks
* Config: migrate threadBindings ttlHours to idleHours
* Revert "Infra: relax win32 guarded-open identity checks"
This reverts commit de9412677196fc5ddfb3#27845 ) (thanks @osolmaz)
---------
Co-authored-by: Onur Solmaz <onur@textcortex.com>
2026-02-27 10:02:39 +01:00
0fb7add7d6
fix: document canvas capability refresh params fix ( #28413 ) (thanks @obviyus)
2026-02-27 13:26:42 +05:30
3a35035512
fix(android): send object params for canvas capability refresh
2026-02-27 13:26:42 +05:30
256021b8da
fix: update changelog for android capability refresh land ( #28388 ) (thanks @obviyus)
2026-02-27 12:16:36 +05:30
6222d6650b
fix(android): avoid duplicate A2UI readiness probe on happy path
2026-02-27 12:16:36 +05:30
8187fbc571
fix(android): refresh scoped canvas URLs without trailing slash
2026-02-27 12:16:36 +05:30
4b37b7b6a9
fix(media): serve JavaScript assets with text/javascript
2026-02-27 12:16:36 +05:30
d53b24d185
fix(android): return valid debug.ed25519 diagnostics JSON
2026-02-27 12:16:36 +05:30
34486f8c10
fix(android): retry A2UI after canvas capability refresh
2026-02-27 12:16:36 +05:30
9b64ad30c4
docs(android): add integration test preconditions and pitfalls
2026-02-27 12:16:36 +05:30
72adf1e993
test(gateway): add live android capability integration suite
2026-02-27 12:16:36 +05:30
54eaf17327
feat(gateway): add node canvas capability refresh flow
2026-02-27 12:16:36 +05:30
0896bb09b0
feat(android): wire runtime canvas capability refresh
2026-02-27 12:16:36 +05:30
6ed00abc1e
docs: document android capability sweep in testing guide
2026-02-27 12:16:36 +05:30
7f6e822526
test: add android integration test script
2026-02-27 12:16:36 +05:30
Vincent Koc
fuller-stack-dev
icesword0760
Shadow
Madoka
Glucksberg
XuHao
大猫子
OfflynAI
zhoulc777
Agent
Peter Steinberger
Cathryn Lavery
Sid
Shakker
Philipp Spiess
bmendonca3
Bartok Moltbot
Rodrigo Uroz
Josh Lehman
Rishabh Jain
Rodrigo Uroz
Daniel Reis
wangchunyue
Ayaan Zaidi
Onur Solmaz
Ayaan Zaidi