Best possible solution:

Merge the focused scenario wrapper after normal maintainer review and required checks, leaving the broader temporary-plugin fixture migration as a separate QA Lab follow-up.

Do we have a high-confidence way to reproduce the issue?

Not applicable; this is a QA coverage wrapper rather than a bug report. Source review confirms the existing script and docs define the behavior being linked into QA Lab.

Is this the best way to solve the issue?

Yes; a script-backed scenario YAML is the supported QA Lab path for existing script producers, and it avoids duplicating Tool Search E2E logic before a first-class temporary-plugin fixture exists.

AGENTS.md: found and applied where relevant.

Codex review notes: model internal, reasoning high; reviewed against 119dc4bd821e.

Label justifications:

• P3: This is low-risk QA coverage metadata/linking work with no runtime product behavior change.
• rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🐚 platinum hermit and patch quality is 🐚 platinum hermit.
• status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Not applicable: This maintainer-labeled PR is not subject to the external-contributor real behavior proof gate; the PR body still includes targeted terminal and QA-suite evidence.

PR surface:

Other +28. Total +28 across 1 file.

What I checked:

• Live PR metadata: Live GitHub metadata shows the author is a repository member and the PR has the protected maintainer label, so this cleanup workflow should not close it automatically. (1061882269db)
• PR diff: The PR adds one scenario id, tool-search-gateway-e2e, with execution.kind script pointing at scripts/tool-search-gateway-e2e.ts. (qa/scenarios/runtime/tool-search-gateway-e2e.yaml:4, 1061882269db)
• Catalog discovery: Current main recursively discovers qa/scenarios/**/*.yaml and excludes only index.yaml, so a new nested runtime scenario is picked up without an index edit. (extensions/qa-lab/src/scenario-catalog.ts:421, 119dc4bd821e)
• Script execution support: The QA test-file runner executes script scenarios with node --import tsx and the declared execution.path, matching the new wrapper shape. (extensions/qa-lab/src/test-file-scenario-runner.ts:153, 119dc4bd821e)
• Existing E2E behavior: The existing Tool Search gateway E2E asserts direct mode calls the fake plugin tool, Tool Search code mode uses the compact bridge, the target tool is not directly exposed in code mode, and the provider payload/tool surface shrinks. (scripts/tool-search-gateway-e2e.ts:619, 119dc4bd821e)
• Documentation contract: Tool Search docs describe the same E2E validation path: fake plugin catalog, mock OpenAI provider, direct mode versus Tool Search, compact bridge exposure, smaller payload, and session log telemetry. Public docs: docs/tools/tool-search.md. (docs/tools/tool-search.md:268, 119dc4bd821e)

Likely related people:

• RomneyDa: Authored the current PR and recent merged QA scenario coverage work that uses the same wrapper pattern. (role: recent QA coverage contributor; confidence: high; commits: 1061882269db, ff6289049084, 119dc4bd821e; files: qa/scenarios/runtime/tool-search-gateway-e2e.yaml, qa/scenarios/runtime/openai-compatible-chat-tools.yaml, qa/scenarios/runtime/openwebui-openai-compatible.yaml)
• steipete: Authored the merged Tool Search PR that introduced the core runtime, docs, and the gateway E2E script this wrapper links. (role: Tool Search feature owner by history; confidence: high; commits: b85cb4e8d13e, b78604a0774f, 15b26be8daf0; files: src/agents/tool-search.ts, scripts/tool-search-gateway-e2e.ts, docs/tools/tool-search.md)
• pfrederiksen: Opened adjacent maintenance work for the Tool Search gateway E2E script and paired timeout issue, which may be useful context even though that PR was not merged. (role: adjacent script contributor; confidence: medium; commits: 58011ff347fb; files: scripts/tool-search-gateway-e2e.ts)

• 🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
• 🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
• 🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
• 🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
• 🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
• 🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
• 🌊 off-meta tidepool: rating does not apply to this item.

Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics.

• ClawSweeper keeps one durable marker-backed review comment per issue or PR.
• Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
• A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
• PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
• Maintainers can also comment @clawsweeper review to request a fresh review only.
• Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
• Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
• Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.