Best possible solution:

Land the narrow test-harness update after maintainer review and CI, preserving provider-hook module exports in these tests without changing runtime behavior.

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

No executed pre-patch repro was run in this read-only review. Source inspection shows the current mock replaces provider-hook-runtime with a narrow object while the real module has additional exports, and the PR body reports the focused shard passing after the patch.

Is this the best way to solve the issue?

Yes. For this test harness, importing the real module and overriding only the isolation points is narrower than duplicating the provider-hook export list, and both affected call sites are updated for the async factory.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 277d8fece2e3.

Label changes:

• add rating: 🦞 diamond lobster: Overall readiness is 🦞 diamond lobster; proof is 🦞 diamond lobster and patch quality is 🦞 diamond lobster.
• remove rating: 🐚 platinum hermit: Current PR rating is rating: 🦞 diamond lobster, so this older rating label is no longer current.

Label justifications:

• P3: This is a low-risk, test-only harness cleanup for agent tests with no runtime or user-facing behavior change.
• rating: 🦞 diamond lobster: Overall readiness is 🦞 diamond lobster; proof is 🦞 diamond lobster and patch quality is 🦞 diamond lobster.
• status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (terminal): The PR body includes structured after-fix proof with the exact focused Vitest command, observed pass count, oxlint, and git diff --check result from a real WSL checkout.
• proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes structured after-fix proof with the exact focused Vitest command, observed pass count, oxlint, and git diff --check result from a real WSL checkout.

PR surface:

Source +4, Tests +3. Total +7 across 3 files.

What I checked:

• Repository policy read: Root and scoped agent review policy were read fully; the scoped guide specifically warns that hot agent tests should avoid broad partial mocks, so the patch was checked as a test-harness tradeoff rather than a runtime change. (AGENTS.md:1, 277d8fece2e3)
• Current main mock shape: Current main's shared sanitize-session-history hook mock hand-builds only a small export object, so unrelated provider-hook exports are absent from tests that use this mock. (src/agents/pi-embedded-runner.sanitize-session-history.test-harness.ts:87, 277d8fece2e3)
• Real module contract: The real provider hook runtime exports additional helpers such as loaded-runtime lookup, runtime handle helpers, auth profile, extra params, and fallback route helpers that the current test mock does not preserve. (src/plugins/provider-hook-runtime.ts:265, 277d8fece2e3)
• PR head change: The provided PR diff for head bb8fdb6 changes the hook mock factory to vi.importActual the real module, spread actual exports, and keep overriding the hook functions used by the tests. (src/agents/pi-embedded-runner.sanitize-session-history.test-harness.ts:87, bb8fdb65b7bd)
• Contributor proof: The PR body reports the focused scripts/run-vitest.mjs shard passing with 4 files and 12 tests, plus oxlint and git diff --check, in a WSL Ubuntu 24.04 checkout after the patch. (bb8fdb65b7bd)
• History provenance: Available blame for the touched helper and adjacent tests points to commit 2fcd481 as the current-source provenance for this test harness surface. (src/agents/pi-embedded-runner.sanitize-session-history.test-harness.ts:87, 2fcd48127606)

Likely related people:

• Neerav Makwana: Available local blame and shortlog for the touched sanitize-session-history test harness and provider-hook-runtime surface point to the current-source commit 2fcd481. (role: current source contributor; confidence: medium; commits: 2fcd48127606; files: src/agents/pi-embedded-runner.sanitize-session-history.test-harness.ts, src/agents/pi-embedded-runner.openai-tool-id-preservation.test.ts, src/plugins/provider-hook-runtime.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.

• Eggs appear after the PR passes real-behavior proof. It is here for vibes, not verdicts: it does not change labels, ratings, merge decisions, or automation.
• The shell reacts to review momentum: open follow-up work warms it up, re-review makes it wobble, and a clean final review lets it hatch.
• Hatchability usually comes from sufficient real-behavior proof, no blocking P0/P1/P2 findings, no security attention needed, and clean correctness. A merged PR is already final, so merge makes the egg hatchable independently.
• The hatch is seeded from this repository and PR number, so the same PR keeps the same creature; the reviewed head SHA can only change safe visual details.
• Rarity is just collectible sparkle: 🥚 common, 🌱 uncommon, 💎 rare, ✨ glimmer, and 🌈 legendary.