Commit Graph

263 Commits

Author SHA1 Message Date
Peter Steinberger af94a3a89b
test: use native vitest root projects 2026-04-04 04:01:32 +01:00
Peter Steinberger 45675c1698
docs: update Anthropic subscription billing guidance 2026-04-04 09:32:13 +09:00
Bruce MacDonald 5ec53fff0c
feat(ollama): add bundled web search provider (#59318)
Merged via squash.

Prepared head SHA: 1ec105f356
Co-authored-by: BruceMacD <5853428+BruceMacD@users.noreply.github.com>
Co-authored-by: BruceMacD <5853428+BruceMacD@users.noreply.github.com>
Reviewed-by: @BruceMacD
2026-04-03 13:41:24 -07:00
Gustavo Madeira Santana 1420b3bad7 docs: tighten skills and Matrix wording 2026-04-03 14:51:37 -04:00
Gustavo Madeira Santana 1f660bf930 Docs: document agent skill allowlists 2026-04-03 14:23:05 -04:00
Peter Steinberger 1bee69f79b
refactor: route direct extension test targets 2026-04-04 02:36:48 +09:00
Peter Steinberger 2b900b576c
refactor: modernize vitest projects config 2026-04-03 17:20:30 +01:00
Peter Steinberger 5184522f2f
refactor: trim extension test runner surface 2026-04-03 13:15:43 +01:00
Peter Steinberger a2077b28ef
refactor: trim vitest wrapper layers 2026-04-03 12:52:14 +01:00
Peter Steinberger 6845b8061c
docs: simplify vitest workflow guidance 2026-04-03 12:45:13 +01:00
Peter Steinberger f4393791eb
test: split vitest setup for projects 2026-04-03 12:29:29 +01:00
Peter Steinberger e2e1197fa9
refactor(gateway): clarify local mode guardrails 2026-04-03 20:02:32 +09:00
Vincent Koc d9c662dc69 docs: restructure automation section as Automation & Tasks 2026-04-03 03:16:51 +09:00
Peter Steinberger 209535b7c7
build: make npm release tag configurable 2026-04-02 19:06:37 +01:00
Peter Steinberger 45c8207ef2 fix(exec): clarify auto routing semantics (#58897) (thanks @vincentkoc) 2026-04-03 02:37:12 +09:00
Peter Steinberger bf1fcf2e5f
docs(approvals): clarify auto native approval routing 2026-04-02 17:31:02 +01:00
Peter Steinberger a5f99f4a30
test: stabilize docker test lanes 2026-04-02 15:59:23 +01:00
Peter Steinberger c678ae7e7a
feat(exec): default host exec to yolo 2026-04-02 14:52:51 +01:00
Scott Glover 9bbbee32e1
Docs: replace personal device names with generic placeholders (#50825) 2026-04-02 00:50:25 -04:00
Peter Steinberger a842e34f15
test: require Claude 4.6 for Anthropic live selection 2026-03-31 16:41:50 +01:00
Peter Steinberger 3bb02d3338
fix(media): align outbound sends with fs read capability 2026-04-01 00:07:50 +09:00
Vincent Koc 8ef9e7f159 docs: add Related sections to install and help pages
- install/docker.md: link to podman, clawdock, updating, config
- install/node.md: link to overview, updating, getting-started
- install/updating.md: link to overview, doctor, migrating
- help/troubleshooting.md: link to FAQ, gateway/channel/automation troubleshooting, doctor
2026-03-31 14:38:46 +09:00
Gustavo Madeira Santana 47136536c8
tests: use multi-sample CLI startup baselines 2026-03-30 22:35:50 -04:00
Gustavo Madeira Santana 68e49fa791
tests: standardize CLI startup benchmarks 2026-03-30 22:15:56 -04:00
Peter Steinberger 7633b6fe0b
docs: add exec approval troubleshooting 2026-03-30 09:45:20 +01:00
Vincent Koc ae0e1ecf5c docs: add background tasks cross-references across 6 doc pages
Link to /automation/tasks from all pages that mention subagent runs,
ACP runs, or detached background work:

- tools/subagents.md: note that each sub-agent run is tracked as a background task
- tools/acp-agents.md: note that ACP session spawns are tracked as background tasks
- cli/index.md: link tasks section to doc page, add tasks audit subcommand
- concepts/queue.md: note that detached lane runs are tracked as background tasks
- gateway/configuration-reference.md: cron section cross-ref to tasks
- help/faq.md: add tasks link to sub-agent offloading FAQ answer
2026-03-30 16:42:47 +09:00
Vincent Koc 7ed5a4a33d docs: fix P2s in faq -- remote mode accordion title, gpt-5.4 model refs, stable/beta cross-reference 2026-03-30 10:19:51 +09:00
Vincent Koc d3429e0c70 docs: fix FAQ P1s -- model aliases and heartbeat OAuth default
- Remove /model haiku (not a built-in alias); add gemini-flash-lite
- Note custom aliases can be added via config
- Heartbeat: note 1h default for OAuth auth
2026-03-30 09:46:15 +09:00
Vincent Koc 32ba94b7b3 docs: fix wrong defaults and config path in FAQ
- session.idleMinutes default: 60 -> 0 (disabled by default, per DEFAULT_IDLE_MINUTES)
- crossContext config path: agents.defaults.tools.message.crossContext -> tools.message.crossContext (matches schema)
- Remove incorrect per-agent tools.message override claim
2026-03-30 09:41:30 +09:00
Radek Sienkiewicz 4680335b2a
docs: fix English link audits (#57039)
Merged via squash.

Prepared head SHA: d20a3b620f
Co-authored-by: velvet-shark <126378+velvet-shark@users.noreply.github.com>
Reviewed-by: @velvet-shark
2026-03-30 01:21:00 +02:00
Peter Steinberger e0f0a1aa1f
docs: clarify browser allowlist troubleshooting 2026-03-29 22:19:22 +09:00
Vincent Koc 3aac43e30b docs: remove stale MiniMax M2.5 refs and add image generation docs
After the M2.7-only catalog trim (#54487), update 10 docs files:
- Replace removed M2.5/VL-01 model references across FAQ, wizard,
  config reference, local-models, and provider pages
- Make local-models guide model-agnostic (generic LM Studio placeholder)
- Add image-01 generation section to minimax.md
- Leave third-party catalogs (Synthetic, Venice) unchanged
2026-03-29 17:26:02 +09:00
Peter Steinberger 341e617c84
docs(plugins): refresh bundled plugin runtime docs 2026-03-29 09:10:39 +01:00
Peter Steinberger 914becee52 fix: isolate live test home from real config 2026-03-28 19:06:59 +00:00
Robin Waslander 840b806c2f
fix(docs): remove broken Xfinity SSL troubleshooting links from FAQ (#56500)
Remove circular self-link in English FAQ and dead anchor reference in
zh-CN FAQ. Both FAQ sections already contain the full workaround inline,
so the cross-references added no value and were never backed by a valid
target in troubleshooting.md.

Fixes #36970
2026-03-28 17:18:26 +01:00
Peter Steinberger 6a556c6851
test(gateway): add live docker ACP bind coverage 2026-03-28 05:23:55 +00:00
Peter Steinberger 048a4e4f9e
docs: clarify mcp server and client modes 2026-03-28 04:10:20 +00:00
Peter Steinberger 5e93419c31
fix: move Mistral compat into provider plugin 2026-03-28 04:08:37 +00:00
Jacob Tomlinson 3e4222e9d4
docs: fix duplicate testing heading 2026-03-27 19:50:09 +00:00
Radek Sienkiewicz 47ae562cc9
Docs: unify link audit entrypoint (#55912)
Merged via squash.

Prepared head SHA: 6b1ccb9f1f
Co-authored-by: velvet-shark <126378+velvet-shark@users.noreply.github.com>
Co-authored-by: velvet-shark <126378+velvet-shark@users.noreply.github.com>
Reviewed-by: @velvet-shark
2026-03-27 18:31:19 +01:00
Peter Steinberger 8d054e7892 test: move shared seams into contract suites 2026-03-27 16:33:53 +00:00
Peter Steinberger 09f2832670 test: split contract seams from unit lane 2026-03-27 16:28:23 +00:00
Peter Steinberger 10527ff8a3 build: refresh deps and vitest cache lanes 2026-03-27 02:26:07 +00:00
Peter Steinberger eef27001de
docs: explain anthropic claude cli migration 2026-03-26 23:04:47 +00:00
Peter Steinberger 8b42ad08e5 perf: speed up shared extension test batches 2026-03-26 21:51:25 +00:00
Peter Steinberger 663ba5a3cd perf: speed up test parallelism 2026-03-26 20:09:40 +00:00
Peter Steinberger f0991aab57
test: add docker cli-backend smoke 2026-03-26 16:49:52 +00:00
Peter Steinberger 339cc33cf8 perf: speed up channel test runs 2026-03-26 15:40:01 +00:00
pomelo dad68d319b
Remove Qwen OAuth integration (qwen-portal-auth) (#52709)
* Remove Qwen OAuth integration (qwen-portal-auth)

Qwen OAuth via portal.qwen.ai is being deprecated by the Qwen team due
to traffic impact on their primary Qwen Code user base. Users should
migrate to the officially supported Model Studio (Alibaba Cloud Coding
Plan) provider instead.

Ref: https://github.com/openclaw/openclaw/issues/49557

- Delete extensions/qwen-portal-auth/ plugin entirely
- Remove qwen-portal from onboarding auth choices, provider aliases,
  auto-enable list, bundled plugin defaults, and pricing cache
- Remove Qwen CLI credential sync (external-cli-sync, cli-credentials)
- Remove QWEN_OAUTH_MARKER from model auth markers
- Update docs/providers/qwen.md to redirect to Model Studio
- Update model-providers docs (EN + zh-CN) to remove Qwen OAuth section
- Regenerate config and plugin-sdk baselines
- Update all affected tests

Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>

* Clean up residual qwen-portal references after OAuth removal

* Add migration hint for deprecated qwen-portal OAuth provider

* fix: finish qwen oauth removal follow-up

---------

Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
Co-authored-by: Frank Yang <frank.ekn@gmail.com>
2026-03-26 16:32:34 +08:00
liyuan97 e2e9f979ca
feat(minimax): add image generation provider and trim model catalog to M2.7 (#54487)
* feat(minimax): add image generation and TTS providers, trim TUI model list

Register MiniMax image-01 and speech-2.8 models as plugin providers for
the image_generate and TTS tools. Both resolve CN/global base URLs from
the configured model endpoint origin.

- Image generation: base64 response, aspect-ratio support, image-to-image
  via subject_reference, registered for minimax and minimax-portal
- TTS: speech-2.8-turbo (default) and speech-2.8-hd, hex-encoded audio,
  voice listing via get_voice API, telephony PCM support
- Add MiniMax to TTS auto-detection cascade (after ElevenLabs, before
  Microsoft) and TTS config section
- Remove MiniMax-VL-01, M2, M2.1, M2.5 and variants from TUI picker;
  keep M2.7 and M2.7-highspeed only (backend routing unchanged)

* feat(minimax): trim legacy model catalog to M2.7 only

Cherry-picked from temp/feat/minimax-trim-legacy-models (949ed28).
Removes MiniMax-VL-01, M2, M2.1, M2.5 and variants from the model
catalog, model order, modern model matchers, OAuth config, docs, and
tests. Keeps only M2.7 and M2.7-highspeed.

Conflicts resolved:
- provider-catalog.ts: removed MINIMAX_TUI_MODELS filter (no longer
  needed since source array is now M2.7-only)
- index.ts: kept image generation + speech provider registrations
  (added by this branch), moved media understanding registrations
  earlier (as intended by the cherry-picked commit)

* fix(minimax): update discovery contract test to reflect M2.7-only catalog

Cherry-picked from temp/feat/minimax-trim-legacy-models (2c750cb).

* feat(minimax): add web search provider and register in plugin entry

* fix(minimax): resolve OAuth credentials for TTS speech provider

* MiniMax: remove web search and TTS providers

* fix(minimax): throw on empty images array after generation failure

* feat(minimax): add image generation provider and trim catalog to M2.7 (#54487) (thanks @liyuan97)

---------

Co-authored-by: tars90percent <tars@minimaxi.com>
Co-authored-by: George Zhang <georgezhangtj97@gmail.com>
2026-03-25 09:29:35 -07:00