Move vLLM Qwen thinking control onto configured model compat metadata and carry it through catalog/model-selection/runtime thinking contexts.
Also migrate legacy provider/default request params in doctor and keep Pi/runtime model rows buildable with explicit reasoning defaults.
Thanks @rendrag-git.
Co-authored-by: rendrag-git <253747599+rendrag-git@users.noreply.github.com>
Summary:
- The PR moves the runtime `HEARTBEAT.md` bootstrap template into `src/agents/templates`, keeps docs templates ... or other workspace files, adds a legacy heartbeat-template doctor repair, and updates package guards/tests.
- PR surface: Source +281, Tests +283, Docs +11, Config +1, Other 0. Total +576 across 15 files.
- Reproducibility: yes. from source inspection: current main loads `HEARTBEAT.md` from the docs template, and ... pty heartbeat file non-empty to the runtime. I did not run a live heartbeat repro in this read-only review.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(doctor): recognize heartbeat docs boilerplate
- PR branch already contained follow-up commit before automerge: fix(agents): update heartbeat workspace test
- PR branch already contained follow-up commit before automerge: fix(doctor): tighten heartbeat template repair
Validation:
- ClawSweeper review passed for head e34e85864c.
- Required merge gates passed before the squash merge.
Prepared head SHA: e34e85864c
Review: https://github.com/openclaw/openclaw/pull/85416#issuecomment-4519851630
Co-authored-by: Mason Huang <masonxhuang@tencent.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: hxy91819
Co-authored-by: hxy91819 <8814856+hxy91819@users.noreply.github.com>
Carry over #82973 and fix#81281 by preserving explicit cacheRetention for OpenAI-compatible completions providers that opt into prompt-cache-key support.
The change keeps explicit cacheRetention suppressed for OpenAI-compatible providers without compat.supportsPromptCacheKey, adds regression coverage for both paths, and updates prompt-caching docs for prompt_cache_key / prompt_cache_retention behavior.
Fixes#81281.
Supersedes #82973.
Co-authored-by: lonexreb <reach2shubhankar@gmail.com>
Fix runtime context placement so hidden runtime context is model-visible before the active user turn without persisting as a visible/session message.
Verification:
- git diff --check origin/main...origin/pr/86995-merge
- gh pr checks 86995 --repo openclaw/openclaw --watch=false
- gh run rerun 26493979156 --repo openclaw/openclaw --failed
- gh run watch 26493979156 --repo openclaw/openclaw --exit-status
- CodeQL run 26493979156 attempt 2, Security High (mcp-process-tool-boundary) job 78066719467 passed
Preserve replayability for direct Anthropic sessions whose stored assistant thinking blocks have empty or blank signatures after a newer user turn. Older invalid thinking-only assistant turns are replaced with the existing omitted-reasoning placeholder so the turn shape survives provider replay.
Also keep active tool-use continuations safe: when an assistant tool call is followed by tool results, preserve the latest assistant thinking block so signed-thinking providers can replay the current tool turn unchanged.
Proof:
- node scripts/run-vitest.mjs src/agents/pi-embedded-runner.sanitize-session-history.test.ts src/agents/pi-embedded-runner/thinking.test.ts test/scripts/openclaw-e2e-instance.test.ts
- pnpm check:changed via Blacksmith Testbox through Crabbox, tbx_01ksmfypqet50et92vdm5mmv5v, run https://github.com/openclaw/openclaw/actions/runs/26505947008
- Live Anthropic Messages replay accepted the OpenClaw-sanitized active tool-turn history with a real thinking signature.
- PR CI on 37c2e72d82 completed successfully for relevant checks.
Fixes#86886.
Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com>
Forward cache-read token counts through the OpenAI-compatible chat-completions usage shape as prompt_tokens_details.cached_tokens so clients can price cached turns correctly.
Align internal gateway usage typing with the expanded wire shape.
Thanks @caz0075.
Preserve existing `agents.list` and top-level `bindings` during ordinary onboarding reruns so rerunning `openclaw onboard` cannot silently wipe configured agents or routing bindings.
Keep config size-drop allowances scoped to explicit reset/import/plugin-install migration flows, validate binding agent ids with normalized agent ids, and add doctor repair coverage for dangling bindings that is still best-effort around malformed agent lists.
Closes#84692.
Co-authored-by: yetval <yetvald@gmail.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Closes#87181.
Direct Anthropic Messages requests now send bare Claude model ids even when OpenClaw stores them with the `anthropic/` provider prefix. Anthropic-compatible proxy and custom endpoint routes keep slash-bearing model ids unchanged so configured proxy models do not regress.
Also preserves the original parse error as `cause` in the JSONL request tail helper to keep the current CI lint gate green.
Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com>
* fix(deepinfra): load all DeepInfra models when user wants to browse them during onboarding
* docs(deepinfra): align TTS default
* fix(deepinfra): refresh video fallbacks
* fix(deepinfra): share credential-aware catalog discovery
* test(deepinfra): narrow catalog regression types
* test(deepinfra): keep catalog narrowing across callback
* fix(deepinfra): preserve default model in live catalog
* fix(deepinfra): align default model pricing
* fix(deepinfra): keep pixverse as video default
* docs(deepinfra): match video fallback default
* fix(deepinfra): honor config api keys for live catalog
* test(e2e): wait for watchdog stdio close
* test(media): align live harness provider expectation
* fix(deepinfra): always augment custom catalogs
* test(e2e): resolve watchdog commands before spawning
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Validates forced plugin harness support for the requested provider/model before pinning Codex or any other plugin harness. This prevents an explicitly forced Codex runtime from accepting unsupported OpenAI-like providers through a hardcoded bypass while preserving implicit PI fallback and CLI runtime alias passthrough.
Regression coverage covers forced Codex rejection for unsupported openai/openai-codex support, Codex provider support declarations, CLI attempt routing, pi-embedded auth/profile forwarding fakes, Testbox scenario probes, and live Docker Codex plugin E2E.
Thanks @cathrynlavery.
Keep macOS Homebrew setup lazy so users with supported Node and Git can install without admin/Homebrew, while still installing Homebrew before macOS Node or Git package installs.
Updates installer docs and adds focused install.sh coverage for the lazy Git path. Also aligns the live-media provider expectation with current main so built-artifact checks stay green.
Fixes#83232
Co-authored-by: Sebastien Tardif <sebtardif@ncf.ca>
