feat(mcp): CLI mirror for loopover_explain_gate_disposition

[RealDiligent]

Summary

• Export buildGateDispositions / GateDisposition from @loopover/engine (MCP re-exports the same pure reshaper).
• Register loopover_explain_gate_disposition stdio tool: fetch predictedGate via POST /v1/local/branch-analysis (same as loopover_predict_gate), then reshape locally.
• Bump stdio tool-count pin 75 → 76; add engine + CLI parity tests.

Closes #6740.

Test plan

• CI validate-code / unit tests green
• codecov/patch ≥ 99%
• loopover-mcp tools --json reports count 76 and lists the new tool
• Stdio call returns dispositions matching buildGateDispositions on the fixture verdict

[superagent-security]

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

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 93.71%. Comparing base (244988b) to head (35e03c6).
⚠️ Report is 2 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #6966   +/-   ##
=======================================
  Coverage   93.71%   93.71%           
=======================================
  Files         685      685           
  Lines       68379    68379           
  Branches    18730    18730           
=======================================
  Hits        64080    64080           
  Misses       3302     3302           
  Partials      997      997           

Flag	Coverage Δ
shard-1	43.75% <0.00%> (ø)
shard-2	36.80% <0.00%> (ø)
shard-3	32.93% <66.66%> (+0.13%)	⬆️
shard-4	33.85% <0.00%> (-0.59%)	⬇️
shard-5	32.13% <0.00%> (-0.04%)	⬇️
shard-6	45.74% <100.00%> (ø)

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

Files with missing lines	Coverage Δ
packages/loopover-engine/src/predicted-gate.ts	100.00% <100.00%> (ø)
src/mcp/server.ts	96.29% <ø> (-0.02%)	⬇️

[loopover-orb]

Tip

✅ LoopOver review result - approve/merge recommended

_{Review updated: 2026-07-17 16:15:28 UTC}

8 files · 1 AI reviewer · no blockers · readiness 80/100 · CI green · clean

✅ Suggested Action - Approve/Merge

• safe to merge

Review summary
This PR moves buildGateDispositions from src/mcp/server.ts into @​loopover/engine (predicted-gate.ts), re-exports it from src/mcp/server.ts for backward compatibility, and registers a new loopover_explain_gate_disposition stdio tool that fetches predictedGate via the existing branch-analysis endpoint and reshapes it locally with the shared engine function. The tool-count pin is correctly bumped 75→76 and both engine-level and CLI-parity tests are added, including a fixture update that now exercises a real advisory warning instead of an empty array. The move is a clean, low-risk relocation of pure logic with no behavior change and good MCP/CLI parity coverage.

Nits — 5 non-blocking

• packages/loopover-mcp/bin/loopover-mcp.js: the tool description says 'per-rule dispositions' but doesn't document that verdict?.pack falls back to 'unknown' pack; worth a one-line note for callers relying on `pack`.
• src/mcp/server.ts:167-168 re-exports buildGateDispositions/GateDisposition solely for backward compatibility with any existing importers of that path — confirm nothing still imports the type from src/rules/predicted-gate directly and that this re-export isn't dead weight.
• packages/loopover-engine/test/gate-dispositions.test.ts imports from `../dist/predicted-gate.js` (built output) rather than `../src/predicted-gate.ts`, which is consistent with existing engine test conventions but means the test won't catch source-level type errors without a build step first — verify this matches how other engine tests are wired.
• Consider adding a short doc comment on the re-export in src/mcp/server.ts:167 clarifying it's kept for compatibility now that the canonical definition lives in @​loopover/engine.
• The fixture change in test/unit/support/mcp-cli-harness.ts (warnings: [] → one warning) is shared infrastructure — worth double-checking no other existing test asserted on the old empty-warnings shape and is now silently passing a different fixture.

Decision drivers

• ✅ Code review — No blockers (1 reviewer)
• ✅ Gate result — Passing (No configured blocker found.)

Context & advisory signals — never blocks the verdict

Signal	Result	Evidence
Linked issue	✅ Linked	#6740
Related work	⚠️ 3 scoped overlaps	Top overlaps are listed below; lower-confidence bulk is hidden.
Change scope	❌ 8/20	High review scope from cached public metadata (1 linked issue).
Validation posture	✅ 25/25	PR body includes validation/test evidence.
Contributor workload	✅ 10/10	Author activity: 389 registered-repo PR(s), 194 merged, 33 issue(s).
Contributor context	✅ Confirmed Gittensor contributor	RealDiligent; Gittensor profile; 389 PR(s), 33 issue(s).
Improvement	✅ Minor	risk: clean · value: minor · LLM: moderate

Linked issue satisfaction

Addressed
The PR exports buildGateDispositions/GateDisposition from @​loopover/engine (moving the pure reshaper into predicted-gate.ts and re-exporting via index.ts), and registers a loopover_explain_gate_disposition stdio tool in loopover-mcp.js that calls the same /v1/local/branch-analysis route as loopover_predict_gate before running buildGateDispositions locally, exactly matching the issue's requirements

Review context

• Author: RealDiligent
• Role context: outside_contributor
• Public audience mode: oss maintainer
• Lane context: Repository is configured for direct PR review.
• Public profile languages: not available
• Official Gittensor activity: 389 PR(s), 33 issue(s).
• Related work: Titles/paths share 7 meaningful terms. (issue #6747, issue #6740)
• Related work: Items reference the same linked issue REST + CLI mirror for loopover_pr_outcome #6747. (issue #6747, PR #6963)
• Related work: Titles/paths share 7 meaningful terms. (issue #6741, issue #6740)
• Additional title-only matches omitted; title-only overlap does not block.

Contributor next steps

• Start here: Review top overlaps.
• Then work through the remaining 2 steps in the Signals table above.

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.

🧪 Chat with LoopOver

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

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

Full command reference: https://loopover.ai/docs/loopover-commands

🧪 Experimental — new and may change.

_{🟩 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 LoopOver, a quiet PR intelligence layer for OSS maintainers.

• Re-run LoopOver review

[loopover-orb]

LoopOver approves — the gate is satisfied and CI is green.