feat(mcp): add CLI mirror for loopover_explain_gate_disposition

[bohdansolovie]

Summary

• Export buildGateDispositions from @loopover/engine and register a stdio loopover_explain_gate_disposition tool that proxies /v1/local/branch-analysis (metadata-only) and reshapes predictedGate into per-rule dispositions — matching the remote MCP tool.
• Bump the stdio discovery invariant to 73 tools (main already registers 72; this adds one).

Closes #6740

Scope

• packages/loopover-engine — export buildGateDispositions / GateDisposition
• packages/loopover-mcp — CLI/stdio mirror
• src/mcp/server.ts — import shared helper (remove duplicate)
• Unit tests for CLI HTTP paths + discovery count

Validation

• vitest run test/unit/mcp-tool-rename-aliases.test.ts test/unit/mcp-cli-plan-scorer-tools.test.ts

Safety

• Read-only metadata analysis; no git writes, no PR mutations.

Made with Cursor

[loopover-orb]

Warning

⏸️ LoopOver review result - manual review recommended

_{Review updated: 2026-07-17 15:23:53 UTC}

6 files · 1 AI reviewer · no blockers · CI green · dirty

⏸️ Suggested Action - Manual Review

Review summary
This PR extracts the existing `buildGateDispositions` helper (previously local to `src/mcp/server.ts`) into `@​loopover/engine`'s `predicted-gate.ts`, re-exports it from both `src/mcp/server.ts` and the engine index, and registers a new stdio CLI tool `loopover_explain_gate_disposition` that mirrors the remote tool by proxying `/v1/local/branch-analysis` and calling the shared helper. The discovery-count bump from 71/72 to 73 is consistent across the two tool-count assertions and the CLI registration, and the added tests cover registration, the HTTP proxy shape, parity with `loopover_predict_gate`, an API-failure path, and zod validation of missing input. The 'parity' test only asserts an empty-dispositions case (`expect(explained.dispositions).toEqual([])`), which is weak coverage for the actual per-rule mapping logic, though the first test does exercise a non-trivial blockers/warnings payload.

Nits — 4 non-blocking

• The re-export line `export { buildGateDispositions, type GateDisposition };` in src/mcp/server.ts:167 is placed between two import statements rather than after the import block, which is unusual ordering and worth a lint/style pass.
• The JSDoc comments duplicated across predicted-gate.ts and the removed server.ts block both reference 'feat(mcp): add gittensory_explain_gate_disposition tool (deterministic dry-run gate reasons) #2234 / CLI mirror for loopover_explain_gate_disposition #6740' vs just 'feat(mcp): add gittensory_explain_gate_disposition tool (deterministic dry-run gate reasons) #2234' — minor inconsistency but harmless.
• Strengthen the parity test to use a fixture with non-empty blockers/warnings so it actually confirms both tools produce the same disposition list end-to-end.
• Consider moving the `export { buildGateDispositions, type GateDisposition }` line in src/mcp/server.ts below the full import block for readability.

Flagged checks (non-blocking)

• Contributor trust — Contributor flagged for review

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: 85 registered-repo PR(s), 30 merged, 6 issue(s).
Contributor context	✅ Confirmed Gittensor contributor	bohdansolovie; Gittensor profile; 85 PR(s), 6 issue(s).
Improvement	✅ Minor	risk: clean · value: minor · LLM: moderate

Review context

• Author: bohdansolovie
• Role context: outside_contributor
• Public audience mode: oss maintainer
• Lane context: Repository is configured for direct PR review.
• Public profile languages: Python, C++, JavaScript
• Official Gittensor activity: 85 PR(s), 6 issue(s).
• Related work: Titles/paths share 6 meaningful terms. (issue #6737)
• Related work: Titles/paths share 8 meaningful terms. (issue #6735, issue #6737)
• Related work: Titles/paths share 8 meaningful terms. (issue #6735, issue #6736)
• 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

[superagent-security]

🚨 Contributor flagged. Click here for more info: Superagent Dashboard

[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 (d6cf892) to head (c3a2fce).
⚠️ Report is 2 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #6950      +/-   ##
==========================================
+ Coverage   89.35%   93.71%   +4.35%     
==========================================
  Files         685      685              
  Lines       68364    68364              
  Branches    18727    18727              
==========================================
+ Hits        61088    64065    +2977     
+ Misses       5517     3302    -2215     
+ Partials     1759      997     -762     

Flag	Coverage Δ
shard-1	43.63% <0.00%> (ø)
shard-2	36.93% <0.00%> (+0.12%)	⬆️
shard-3	32.80% <66.66%> (?)
shard-4	34.85% <0.00%> (+0.23%)	⬆️
shard-5	31.32% <0.00%> (-0.82%)	⬇️
shard-6	45.75% <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%> (+1.44%)	⬆️
src/mcp/server.ts	96.29% <ø> (+2.04%)	⬆️

... and 100 files with indirect coverage changes

[loopover-orb]

LoopOver is closing this pull request on the maintainer's behalf (conflicts with the base branch — resolve and open a fresh PR). This is an automated maintenance action — to pursue this change, please open a new pull request with the issues resolved. Closed PRs may be analyzed later to improve review accuracy, but they are not automatically reopened or re-reviewed.