Commit Graph

13 Commits

Author SHA1 Message Date
Peter Steinberger eec2c0cc26 refactor(providers): unify lifecycle-safe manifest registration (#114381)
* refactor(providers): canonicalize manifest-driven registration

* fix(zai): eliminate type-only SDK import side effects
2026-07-27 03:20:02 -04:00
Jason (Json) 55cf9523e0 feat: discover models from live provider catalogs (#112412)
* feat: discover models from live provider catalogs

* fix(provider-catalog): satisfy current catalog contracts

* fix(deps): update fast-uri past new advisory

* fix(deps): refresh fast-uri shrinkwraps

* fix(openrouter): satisfy provider catalog lint

* fix(agents): preserve refreshable catalog metadata

* test(agents): keep catalog fallback proof within lint budget

* fix(provider-catalog): honor live model contracts

* fix(minimax): type discovery headers explicitly

* docs(plugin-sdk): define live model discovery contract
2026-07-21 19:29:57 -06:00
Peter Steinberger 0393189243 chore(plugins): gate deprecation hygiene in CI and purge internal deprecated usage (#108261)
* chore(plugins): gate deprecation hygiene in CI and purge internal deprecated usage

* fix(agents): migrate auth-profiles oauth import to OAuthProviderId

* fix(whatsapp): use durability param in delivery-recovery test

* chore(scripts): declare shouldRunDeprecationHygieneChecks in check-changed types

* test(plugins): update runtime-api guard for ssrf policy rename
2026-07-15 04:15:23 -07:00
Peter Steinberger 2ad6314d72 docs: document small provider plugins 2026-06-04 07:20:32 -04:00
Peter Steinberger 304e2c83c0 chore(lint): enable stricter oxlint rules 2026-05-31 18:59:02 +01:00
Val Alexander 05c9492bff fix: reduce WebUI session latency churn (#76277) thanks @BunsDev
Reduce WebUI/Gateway latency churn by avoiding redundant session reloads, carrying session keys through transcript update events, and deferring explicit media provider discovery. Includes changelog attribution and closes the referenced runtime latency issues.
2026-05-02 18:39:06 -05:00
Vincent Koc dd43caa27a Fix Trinity main-session compatibility mismatch (#73388)
Summary:
- The PR marks Arcee Trinity Large Thinking tool-incompatible in catalog/config/runtime paths, updates Arcee docs and changelog, and adds provider regression tests.
- Reproducibility: yes. The linked reports provide concrete main-session failure logs, and current main still exposes Trinity without `compat.supportsTools:false` while the runtime sends tools unless that flag is false.

ClawSweeper fixups:
- Included follow-up commit: fix(arcee): disable Trinity tools in main sessions
- Included follow-up commit: fix(clawsweeper): address review for automerge-openclaw-openclaw-7338…
- Included follow-up commit: fix(arcee): repair Trinity main-session compatibility

Validation:
- ClawSweeper review passed for head 4c669d66cb.
- Required merge gates passed before the squash merge.

Prepared head SHA: 4c669d66cb
Review: https://github.com/openclaw/openclaw/pull/73388#issuecomment-4338585215

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
2026-05-02 23:10:13 +00:00
Vincent Koc 791dbf4f9d fix(openrouter): heal stale provider base urls (#68574)
* fix(openrouter): heal stale provider base urls

* chore(changelog): fix openrouter baseurl entry placement

* fix(arcee): keep catalog config optional
2026-04-18 08:42:51 -07:00
Vincent Koc 4c15f1310b fix(plugin-sdk): share canonical replay hook families 2026-04-14 16:34:09 +01:00
Peter Steinberger b7d3a26356 refactor: extract arcee provider cleanup seams 2026-04-06 19:53:27 +01:00
Peter Steinberger 177be0f237 fix: remove provider hardcoding and fix arcee openrouter 2026-04-06 19:53:27 +01:00
arthurbr11 95106be59b feat: enhance Arcee AI provider with OpenRouter support and update onboarding instructions 2026-04-06 19:53:27 +01:00
arthurbr11 5ac2f58c57 feat: add Arcee AI provider plugin
Add a bundled Arcee AI provider plugin with ARCEEAI_API_KEY onboarding,
Trinity model catalog (mini, large-preview, large-thinking), and
OpenAI-compatible API support.

- Trinity Large Thinking: 256K context, reasoning enabled
- Trinity Large Preview: 128K context, general-purpose
- Trinity Mini 26B: 128K context, fast and cost-efficient
2026-04-06 19:53:27 +01:00