Summary:
- Hide retired and non-public Google Gemini model IDs from Control UI/chat model catalogs.
- Route the bare gemini-3-pro alias to gemini-3.1-pro-preview.
- Keep models.list fallback rows filtered by manifest suppressions and update stale pricing-cache expectations.
Verification:
- pnpm test src/commands/models/list.list-command.forward-compat.test.ts src/commands/models/list.rows.test.ts extensions/google/manifest.test.ts extensions/google/model-id.test.ts extensions/google/provider-models.test.ts extensions/google/provider-policy-api.test.ts extensions/google/media-understanding-provider.video.test.ts src/plugin-sdk/provider-model-id-normalize.test.ts src/plugins/manifest-model-suppression.test.ts src/gateway/server-methods/models.test.ts ui/src/ui/chat-model-select-state.test.ts ui/src/ui/chat-model-ref.test.ts
- pnpm test src/gateway/model-pricing-cache.test.ts
- pnpm --silent openclaw models list --all --json --provider google / google-vertex hidden-row probe
- Testbox pnpm check:changed: https://github.com/openclaw/openclaw/actions/runs/25534551033
Adds bounded Talk lifecycle/audio diagnostics and session recovery metrics for OTEL, Prometheus, and stability snapshots after the Talk SDK/session refactor. Includes changelog/docs updates and Testbox/live proof.
Summary:
- The PR removes `max` from OpenRouter DeepSeek V4 thinking profiles, maps stale OpenRouter `max` overrides to `xhigh`, preserves direct DeepSeek behavior, and updates docs, tests, and changelog.
- Reproducibility: yes. Source inspection on current main shows OpenRouter DeepSeek V4 advertises `max` and se ... ffort: "max"`, matching the linked 400 logs; I did not need a live OpenRouter request for this assist pass.
Automerge notes:
- Ran the ClawSweeper repair loop before final review.
- Addressed earlier ClawSweeper review findings before merge.
- Included post-review commit in the final squash: docs(changelog): credit OpenRouter duplicate fix
- Included post-review commit in the final squash: fix(openrouter): keep DeepSeek V4 reasoning effort valid
Validation:
- ClawSweeper review passed for head becdea4223.
- Required merge gates passed before the squash merge.
Prepared head SHA: becdea4223
Review: https://github.com/openclaw/openclaw/pull/77423#issuecomment-4372880583
Co-authored-by: sallyom <somalley@redhat.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Summary:
- Adds a plugin-owned CLI backend argument rewrite hook and wires Anthropic `claude-cli` to translate non-off `/think` levels into Claude Code `--effort`, with docs, changelog, API baseline, and tests.
- Reproducibility: yes. Current main has a high-confidence source reproduction: choose `claude-cli`, set a non ... builds argv from backend args that contain no `--effort` even though `thinkLevel` exists on the run params.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head be17754009.
- Required merge gates passed before the squash merge.
Prepared head SHA: be17754009
Review: https://github.com/openclaw/openclaw/pull/77410#issuecomment-4372812685
Co-authored-by: stainlu <stainlu@newtype-ai.org>
