vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-04-15 03:01:02 +00:00
Code Issues Packages Projects Releases Wiki Activity
28,007 Commits 1,293 Branches 108 Tags
7d54f2a3c2dddf0c87f6de0aec4ee2980ec5fbca
Commit Graph

98 Commits

Author SHA1 Message Date
Peter Steinberger
8b79cbcd06 build(plugins): align package versions to 2026.4.6 2026-04-06 17:05:30 +01:00
Peter Steinberger
ef923805f5 Revert "refactor(cli): remove custom cli backends" 
This reverts commit 6243806f7b.
 2026-04-06 13:40:42 +01:00
Peter Steinberger
c39f061003 Revert "refactor(cli): remove bundled cli text providers" 
This reverts commit 05d351c430.
 2026-04-06 13:40:41 +01:00
Vincent Koc
9ba97ceaed perf(agents): add continuation-skip context injection (#61268) 
* test(agents): cover continuation bootstrap reuse

* perf(agents): add continuation-skip context injection

* docs(changelog): note context injection reuse

* perf(agents): bound continuation bootstrap scan

* fix(agents): require full bootstrap proof for continuation skip

* fix(agents): decide continuation skip under lock

* fix(commands): re-export subagent chat message type

* fix(agents): clean continuation rebase leftovers
 2026-04-06 05:27:28 +01:00
Peter Steinberger
3e72c0352d chore: release 2026.4.5 2026-04-06 04:04:21 +01:00
Peter Steinberger
072e0795f8 chore: prepare 2026.4.6-beta.1 release 2026-04-06 03:33:55 +01:00
Peter Steinberger
d8270ef181 fix: gate async media direct delivery behind config 2026-04-06 03:28:58 +01:00
wirjo
699b2320a8 feat(memory): add Bedrock embedding provider for memory search (#61547) 
* feat(memory): add Bedrock embedding provider for memory search

Add Amazon Bedrock as a native embedding provider for memory search.
Supports Titan Embed Text v1/v2 and Cohere Embed models via AWS SDK.

- New embeddings-bedrock.ts: BedrockRuntimeClient + InvokeModel
- Auth via AWS default credential chain (same as Bedrock inference)
- Auto-selected in 'auto' mode when AWS credentials are detected
- Titan V2: configurable dimensions (256/512/1024), normalization
- Cohere: native batch support with search_query/search_document types
- 16 new tests covering all model types, auth detection, edge cases

Closes #26289

* fix(memory): harden bedrock embedding selection

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
 2026-04-06 01:19:56 +01:00
Peter Steinberger
ce8492f9a0 chore: bump version to 2026.4.5 2026-04-05 21:33:04 +01:00
Peter Steinberger
05d351c430 refactor(cli): remove bundled cli text providers 2026-04-05 18:46:36 +01:00
Peter Steinberger
7fe5dc36f0 test: remove extension-shaped talk and cli test fixtures 2026-04-05 18:41:57 +01:00
Peter Steinberger
6243806f7b refactor(cli): remove custom cli backends 2026-04-05 18:04:48 +01:00
Peter Steinberger
9a0d88a868 refactor: move talk config contract under plugin 2026-04-05 14:26:35 +01:00
Peter Steinberger
19de5d1b56 refactor: move provider discovery config into plugins 2026-04-05 09:55:55 +01:00
Peter Steinberger
455c642acb feat: add implicit discovery toggles 2026-04-05 09:27:48 +01:00
Peter Steinberger
68851f2e97 fix(config): cap generated schema export types 2026-04-05 07:58:02 +01:00
Peter Steinberger
fb580b551e fix: restore provider and config compatibility checks 2026-04-05 03:47:57 +01:00
Hiroshi Tanaka
3f1b369f4a feat(config): add rich description fields to JSON Schema output [AI-assisted] (#60067) 
Merged via squash.

Prepared head SHA: a98b971924
Co-authored-by: solavrc <145330217+solavrc@users.noreply.github.com>
Co-authored-by: altaywtf <9790196+altaywtf@users.noreply.github.com>
Reviewed-by: @altaywtf
 2026-04-04 22:10:08 +03:00
Peter Steinberger
e3ac0f43df feat(qwen): add qwen provider and video generation 2026-04-04 19:34:56 +01:00
Peter Steinberger
32d2654340 build: bump version to 2026.4.4 2026-04-04 16:09:42 +09:00
Peter Steinberger
14cfcdba1a docs(test): refresh stale model refs 2026-04-04 08:05:49 +01:00
Peter Steinberger
a82bc7d887 fix(ci): align contract expectations 2026-04-04 12:29:11 +09:00
Peter Steinberger
58d2b9dd46 fix: add runtime model contextTokens caps 2026-04-04 09:36:53 +09:00
Vincent Koc
4265a59892 fix(config): hide legacy internal hook handlers 2026-04-04 04:26:51 +09:00
Gustavo Madeira Santana
ddd250d130 feat(skills): add inherited agent skill allowlists (#59992) 
Merged via squash.

Prepared head SHA: 6f60779a57
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
 2026-04-03 13:41:28 -04:00
Peter Steinberger
865fa2ba72 fix: narrow auth permanent lockouts 2026-04-04 02:35:27 +09:00
Vincent Koc
c7a947dc0a fix(config): remove legacy config aliases from public schema 2026-04-04 01:24:14 +09:00
Vincent Koc
8f5f78bbe8 feat(providers): reopen model request transport config (#60327) 
* feat(providers): reopen model request transport config

* chore(config): refresh request override baselines
 2026-04-03 23:25:11 +09:00
Doruk Ardahan
f7d24c1ed5 fix(plugins): allow configured bundled channels past allowlists 2026-04-03 22:55:30 +09:00
Peter Steinberger
d921784718 fix: support default subagent allowlists (#59944) (thanks @hclsys) 2026-04-03 19:43:17 +09:00
Peter Steinberger
71f8c0344a fix(ci): refresh schema and boundary expectations 2026-04-03 11:26:06 +01:00
Vincent Koc
61f13173c2 feat(providers): add model request transport overrides (#60200) 
* feat(providers): add model request transport overrides

* chore(providers): finalize request override follow-ups

* fix(providers): narrow model request overrides
 2026-04-03 19:00:06 +09:00
Vincent Koc
23719dd513 feat(media): add request transport overrides (#59848) 
* style(providers): normalize request policy formatting

* style(providers): normalize request policy formatting

* feat(media): add request transport overrides

* fix(secrets): resolve media request secret refs

* fix(secrets): cover shared media request refs

* fix(secrets): scope media request ref activity

* fix(media): align request ref gating
 2026-04-03 17:35:26 +09:00
Peter Steinberger
bff6025bde test: refresh generated baselines 2026-04-03 04:54:59 +09:00
Peter Steinberger
0ebb69b882 build: set release version to 2026.4.2 2026-04-02 19:09:58 +01:00
Peter Steinberger
423f7c3487 build: prep 2026.4.2-beta.1 release 2026-04-02 16:33:21 +01:00
Vincent Koc
3872a866a1 fix(xai): make x_search auth plugin-owned (#59691) 
* fix(xai): make x_search auth plugin-owned

* fix(xai): restore x_search runtime migration fallback

* fix(xai): narrow legacy x_search auth migration

* fix(secrets): drop legacy x_search target registry entry

* fix(xai): no-op knob-only x_search migration fallback
 2026-04-02 23:54:07 +09:00
Vincent Koc
3e4de956c0 !refactor(xai): move x_search config behind plugin boundary (#59674) 
* refactor(xai): move x_search config behind plugin boundary

* chore(changelog): note x_search config migration

* fix(xai): include x_search migration helpers
 2026-04-02 22:08:59 +09:00
Vincent Koc
15e6a88c67 fix(config): sync generated base schema 2026-04-02 21:04:06 +09:00
Vincent Koc
38d2faee20 !feat(plugins): add web fetch provider boundary (#59465) 
* feat(plugins): add web fetch provider boundary

* feat(plugins): add web fetch provider modules

* refactor(web-fetch): remove remaining core firecrawl fetch config

* fix(web-fetch): address review follow-ups

* fix(web-fetch): harden provider runtime boundaries

* fix(web-fetch): restore firecrawl compare helper

* fix(web-fetch): restore env-based provider autodetect

* fix(web-fetch): tighten provider hardening

* fix(web-fetch): restore fetch autodetect and compat args

* chore(changelog): note firecrawl fetch config break
 2026-04-02 20:25:19 +09:00
Oguri Cap
1f99c87a44 feat: add agents.defaults.compaction.notifyUser config option (default: false) [Fix #54249] (#54251) 
Merged via squash.

Prepared head SHA: 6fd4cdb7c3
Co-authored-by: oguricap0327 <266246182+oguricap0327@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
 2026-04-01 12:29:17 -07:00
Peter Steinberger
8abba663c5 chore: bump version to 2026.4.2 2026-04-01 19:39:27 +01:00
Peter Steinberger
da64a978e5 chore: prepare 2026.4.1 release 2026-04-01 17:57:10 +01:00
Peter Steinberger
8988894ff7 build: prepare 2026.4.1-beta.1 release 2026-04-01 15:09:19 +01:00
Luke
1654c3a851 feat(gateway): make chat history max chars configurable (#58900) 
* feat(gateway): make chat history max chars configurable

* fix(gateway): address review feedback

* docs(changelog): note configurable chat history limits
 2026-04-01 21:08:37 +11:00
Forgely3D
4fa11632b4 fix: escalate to model fallback after rate-limit profile rotation cap (#58707) 
* fix: escalate to model fallback after rate-limit profile rotation cap

Per-model rate limits (e.g. Anthropic Sonnet-only quotas) are not
relieved by rotating auth profiles — if all profiles share the same
model quota, cycling between them loops forever without falling back
to the next model in the configured fallbacks chain.

Apply the same rotation-cap pattern introduced for overloaded_error
(#58348) to rate_limit errors:

- Add `rateLimitedProfileRotations` to auth.cooldowns config (default: 1)
- After N profile rotations on a rate_limit error, throw FailoverError
  to trigger cross-provider model fallback
- Add `resolveRateLimitProfileRotationLimit` helper following the same
  pattern as `resolveOverloadProfileRotationLimit`

Fixes #58572

* fix: cap prompt-side rate-limit failover (#58707) (thanks @Forgely3D)

* fix: restore latest-main gates for #58707

---------

Co-authored-by: Ember (Forgely3D) <ember@forgely.co>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
 2026-04-01 17:54:10 +09:00
joshavant
ccb67bd4bf config: regenerate base config schema baseline 2026-03-31 22:54:36 -05:00
Peter Steinberger
9ea7e06460 build: bump version to 2026.4.1 2026-03-31 22:53:17 +01:00
Peter Steinberger
418fa12dfa fix: make overload failover configurable 2026-03-31 21:34:35 +01:00
Peter Steinberger
2a60e34f2a build: prepare 2026.3.31 stable release 2026-03-31 21:32:38 +01:00