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 74 tools (main pins 73 after REST + CLI mirror for loopover_plan_idea_claims #6756; 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 (30 passed locally)

Safety

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

Made with Cursor

[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 (8fa47d1) to head (e77db49).
⚠️ Report is 3 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #6958   +/-   ##
=======================================
  Coverage   93.71%   93.71%           
=======================================
  Files         685      685           
  Lines       68373    68373           
  Branches    18729    18729           
=======================================
  Hits        64074    64074           
  Misses       3302     3302           
  Partials      997      997           

Flag	Coverage Δ
shard-1	43.75% <0.00%> (ø)
shard-2	36.79% <0.00%> (-0.02%)	⬇️
shard-3	32.75% <66.66%> (+0.01%)	⬆️
shard-4	34.61% <0.00%> (-0.01%)	⬇️
shard-5	32.13% <0.00%> (ø)
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%> (ø)
src/mcp/server.ts	96.29% <ø> (-0.02%)	⬇️

[loopover-orb]

Warning

⏸️ LoopOver review result - manual review recommended

_{Review updated: 2026-07-17 16:05:43 UTC}

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

⏸️ Suggested Action - Manual Review

Review summary
This PR moves buildGateDispositions from src/mcp/server.ts into @​loopover/engine's predicted-gate.ts, exports it, and wires a new CLI/stdio mirror tool loopover_explain_gate_disposition that proxies /v1/local/branch-analysis and reshapes predictedGate the same way the remote tool does. The refactor is clean — server.ts re-exports the moved symbols for backward compatibility, the discovery-count pin is correctly bumped from 73 to 74, and new tests cover registration, HTTP proxying, parity with loopover_predict_gate, API-failure surfacing, and input validation. The main gap is that #6740 is only partially addressed per the external brief, though the visible diff is internally consistent and correct.

Nits — 4 non-blocking

• packages/loopover-mcp/bin/loopover-mcp.js: the new tool duplicates the same body-construction and apiPost pattern already used by loopover_predict_gate a few dozen lines above — consider extracting a shared helper to avoid drift between the two.
• src/mcp/server.ts:167-168: re-exporting buildGateDispositions/GateDisposition from server.ts right after importing them is a bit unusual placement (mid-import-block) — consider moving the re-export near the other public exports for clarity.
• packages/loopover-engine/src/predicted-gate.ts: buildGateDispositions takes Pick<PredictedGateVerdict, 'blockers'|'warnings'> but the CLI call site passes predictedGate straight from an untyped HTTP response — consider a runtime shape check or note that it trusts the API response.
• Consider extracting a shared 'buildBranchAnalysisRequestBody' helper reused by loopover_predict_gate and loopover_explain_gate_disposition in loopover-mcp.js to reduce duplication.

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

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: not available
• Official Gittensor activity: 85 PR(s), 6 issue(s).
• Related work: Titles/paths share 7 meaningful terms. (issue #6740, issue #6747)
• Related work: Titles/paths share 7 meaningful terms. (issue #6740, issue #6741)
• Related work: Titles/paths share 8 meaningful terms. (issue #6744, issue #6743)
• 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.

[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.