fix(miner-governor): wire buildHouseRulesPreToolUseHook into a real driver-construction call site

[JSONbored]

Summary

Follow-up to #2343 (merged as #5031). That PR built buildHouseRulesPreToolUseHook (the live Agent SDK PreToolUse interception point) but nothing ever called it — confirmed via grep that createCodingAgentDriver/runCodingAgentAttempt (driver-factory.ts) had zero real callers anywhere in packages/gittensory-miner. The engine package cannot import the miner package's hook builder directly (dependency only flows miner → engine, never the reverse), so the wiring has to live miner-side.

• buildHouseRulesAgentSdkHooks wraps the hook callback into the Agent SDK's documented hooks.PreToolUse registration shape (an array of matcher groups, each holding an array of callbacks).
• runHouseRulesEnforcedCodingAgentAttempt is a drop-in replacement for the engine's runCodingAgentAttempt that defaults hooks to house-rule enforcement for the agent-sdk provider whenever the caller omits it — an explicit hooks override still wins.

This does not build a CLI entrypoint — nothing constructs a coding-agent driver in production yet, which is separate, larger follow-up work. What this guarantees: whenever such an entrypoint exists, it only has to call runHouseRulesEnforcedCodingAgentAttempt instead of the engine's own runCodingAgentAttempt to get real, unbypassable house-rule enforcement automatically, rather than depending on that future author to remember to wire hooks by hand.

Verification

Tested end-to-end, not just the shape: the defaulted hooks are captured at the exact point they'd reach the SDK's query() call (same query-capturing test seam agent-sdk-driver.test.ts already uses), and the resulting callback is invoked directly to confirm it genuinely denies a house-rule violation (.env read) and allows a clean one — proving the wiring reaches a real, enforcing hook, not a placeholder.

Test plan

• npm run typecheck clean
• packages/gittensory-miner's build script (node --check) passes on the new file
• Engine package rebuilt fresh; its full node:test suite passes (505 tests)
• New root vitest suite (8 tests): hook-shape wrapping, real enforcement through the wrapped callback, config/options threading, hooks defaulting when omitted, caller-supplied hooks NOT overridden, inert for non-agent-sdk providers, paused/dry-run never constructs a driver so hooks are never even consulted
• Measured coverage on the new file directly: 100% statements/branches/functions/lines

Advances #2343 (does not close it — the "wire a real CLI entrypoint that actually invokes a coding-agent attempt in production" work is still open, tracked separately)

[cloudflare-workers-and-pages]

Deploying with    Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status	Name	Latest Commit	Preview URL	Updated (UTC)
✅ Deployment successful! View logs	gittensory-ui	768913e	Commit Preview URL Branch Preview URL	Jul 11 2026, 02:06 PM

[superagent-security]

Superagent didn't find any vulnerabilities or security issues in this PR.

[loopover-orb]

Warning

🟨🟨🟨🟨🟨🟨🟨🟨🟨🟨🟨🟨

⏸️ Gittensory review result - manual review recommended

_{Review updated: 2026-07-11 14:33:35 UTC}

4 files · 1 AI reviewer · 2 blockers · readiness 93/100 · CI green · unstable

⏸️ Suggested Action - Manual Review

• No linked issue detected — If this PR is intended to solve an issue, link it explicitly in the PR body.
• Maintainer requires a linked issue — Link the relevant issue (for example Closes #123) before opening the PR.

Review summary
Adds a miner-side wrapper module that composes the already-merged buildHouseRulesPreToolUseHook into the SDK's PreToolUse registration shape and defaults it into runCodingAgentAttempt for the agent-sdk provider, plus a matching .d.ts and a test file that exercises the wrapping, defaulting, override, and inert-provider behavior against the real (non-mocked) deny-hook logic. The wiring is correct and narrowly scoped: hooks default only when the caller omits them, non-agent-sdk providers pass hooks through inertly, and the tests genuinely invoke the callback to prove a `.env` read is denied rather than just asserting shape. The PR is explicit that no production call site is created yet, so real-world enforcement still depends on a future entrypoint calling this function — the description itself flags this as intentional scope-limiting rather than a gap being hidden.

Nits — 5 non-blocking

• packages/gittensory-miner/lib/coding-agent-house-rules.js:36 embeds the issue number `2343` as a bare literal in the JSDoc rather than a named constant, per the external brief — purely cosmetic, not worth blocking on.
• The module doc comments are unusually long and repeat the PR description almost verbatim (coding-agent-house-rules.js:1-14); consider trimming to what a future reader needs at the call site rather than re-narrating the PR history.
• CI shows `validate` and `validate-code` as FAILED on this commit — worth confirming those failures are unrelated lint/format issues rather than something in this new file before merge, though that's a CI-status note, not a code defect I can independently verify from the diff.
• Consider adding a one-line CHANGELOG or README pointer in coding-agent-driver.md noting `runHouseRulesEnforcedCodingAgentAttempt` exists as the house-rules-enforcing entrypoint, so a future author building the real CLI call site discovers it instead of reaching for the engine's raw `runCodingAgentAttempt`.
• Since this PR explicitly defers building any real call site, consider linking the follow-up issue that will wire an actual entrypoint to this function, so the dangling guarantee doesn't go unnoticed.

Concerns raised — review before merging

• No linked issue detected — If this PR is intended to solve an issue, link it explicitly in the PR body.
• Maintainer requires a linked issue — Link the relevant issue (for example Closes #123) before opening the PR.

Signal	Result	Evidence
Code review	❌ 2 blockers	1 reviewer
Linked issue	⚠️ Missing	No linked issue or no-issue rationale found.
Related work	✅ No active overlap found	No same-issue or scoped active PR overlap found.
Change scope	✅ 20/20	Low review scope from cached public metadata (no linked issue context).
Validation posture	✅ 25/25	PR body includes validation/test evidence.
Contributor workload	✅ 10/10	Author activity: 46 registered-repo PR(s), 38 merged, 416 issue(s).
Contributor context	✅ Confirmed Gittensor contributor	JSONbored; Gittensor profile; 46 PR(s), 416 issue(s).
Gate result	❌ Blocking	Repo-configured hard blocker found.
Improvement	✅ Minor	risk: clean · value: minor — Code changes are accompanied by test evidence.

Review context

• Author: JSONbored
• Role context: owner (maintainer lane)
• Public audience mode: oss maintainer
• Lane context: Repository is configured for direct PR review.
• Public profile languages: not available
• Official Gittensor activity: 46 PR(s), 416 issue(s).
• PR-specific overlap: none found.

Contributor next steps

• Treat this as maintainer-lane context rather than normal contributor-lane activity.
• Explain no-issue PR.
• Link the issue being solved, or explicitly explain why this is a no-issue PR.

Signal definitions

• Related work = same linked issue, overlapping active PRs, or title/path similarity.
• Change scope = cached public metadata such as size labels, draft state, and review-burden hints.
• Validation posture = whether the PR provides enough public validation/test evidence for maintainer review.
• Contributor workload = public contributor activity and cleanup pressure, not a repo-wide quality failure.
• Contributor context = public GitHub/Gittensor identity context; non-Gittensor status is not a blocker.

[BETA] Chat with Gittensory

Ask Gittensory a question about this PR directly in a comment — grounded only in the same cached, public-safe facts shown above, never a new claim.

• @gittensory ask <question> answers contribution-quality Q&A with source citations and freshness.
• @gittensory chat <question> answers in natural prose from cached decision-pack facts via local inference (maintainer/collaborator; read-only).
• A plain-language @gittensory mention with a real question is routed to the closest matching read-only command automatically -- no exact syntax required.

Full command reference: https://gittensory.aethereal.dev/docs/gittensory-commands

_{🟩 Safe / merged · 🟦 Advisory · 🟨 Held for review · 🟥 Blocked / closed}

---

💰 Earn for open-source contributions like this. Gittensor lets GitHub contributors earn for the work they already do — register to start earning →.

Checked by Gittensory, a quiet PR intelligence layer for OSS maintainers.

• Re-run Gittensory review

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 94.20%. Comparing base (0800f23) to head (2561b4d).
⚠️ Report is 4 commits behind head on main.
✅ All tests successful. No failed tests found.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #5082   +/-   ##
=======================================
  Coverage   94.20%   94.20%           
=======================================
  Files         470      470           
  Lines       39722    39722           
  Branches    14493    14493           
=======================================
  Hits        37421    37421           
  Misses       1645     1645           
  Partials      656      656           

Flag	Coverage Δ
shard-1	46.40% <ø> (-0.02%)	⬇️
shard-2	33.47% <ø> (-0.12%)	⬇️
shard-3	31.16% <ø> (-0.18%)	⬇️
shard-4	33.12% <ø> (+0.31%)	⬆️
shard-5	33.36% <ø> (-0.18%)	⬇️
shard-6	45.21% <ø> (+0.30%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

🚀 New features to boost your workflow:

• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.