feat(mcp): route ideas through intake into a loop claim plan

[luciferlive112116]

Summary

Implements #4799 — the deterministic hand-off from idea intake (#4798) to the claim/code/submit loop. A submitted idea becomes a scored task-graph and is then dispositioned into what the loop can claim now vs defer vs skip, so intake output flows toward real execution without a manual step.

• new buildClaimPlan(taskGraph, targetRepo) in packages/loopover-engine/src/idea-intake.ts (pure): routes each constituent issue by its already-computed feasibility verdict — go → claimable, raise → deferred (held on a prerequisite or its own quality), avoid → skipped — preserving the graph's dependency-respecting order so a prerequisite is always claimed before its dependents, and carrying the target repo the loop will act on. It decides what to claim; the loop does the claiming/running (no IO). Per-issue scoring is factored into a shared scoreIssue helper reused by scoreTaskGraph (no behavior change — the existing suite is unchanged and green).
• new loopover_plan_idea_claims MCP tool (src/mcp/server.ts): idea → task-graph → claim plan, reusing the intake input schema; a malformed/empty submission returns an actionable error list.

Closes #4799

Scope

• Conventional Commit title (feat(mcp): …).
• Focused: the claim-plan hand-off + its tool, building directly on the merged Idea-intake API/MCP tool #4798 bridge.
• Follows CONTRIBUTING.md; no site//CNAME/VitePress.
• Linked open issue: Closes #4799.

Validation

• git diff --check
• npm run typecheck clean
• npm --workspace @loopover/engine run build + npm run build:mcp (compile clean)
• npm run test:coverage on the changed code: packages/loopover-engine/src/idea-intake.ts 100% lines & branches (86/86); the new src/mcp/server.ts handler + schema + registration are fully covered (statements and both branch sides).
• MCP tool-invariant suites pass with the new tool (mcp-output-schemas "outputSchema on EVERY tool" + "schema-valid structured content", mcp-cli-tools).
• Tests cover the claimable/deferred/skipped split, dependency-hold ordering, carried target repo, and the malformed-input path — end-to-end through the MCP tool.

If any required check was skipped, explain why:

• Full test:ci not run end-to-end locally (Linux-only shell/self-host steps on this Windows box); the change-relevant gates above were validated directly.

Safety

• No secrets, wallet/hotkey/coldkey, trust scores, rewards, private rankings, or private maintainer evidence — metadata-only, source-free; the plan never mints gittensor:priority.
• No auth/cookie/CORS/GitHub App/session change (pure function over caller-supplied data).
• MCP behavior added + tested (output schema + schema-valid content).
• No UI changes; no changelog edit.

[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 95.10%. Comparing base (b83d060) to head (e36b571).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #5795   +/-   ##
=======================================
  Coverage   95.10%   95.10%           
=======================================
  Files         583      583           
  Lines       46399    46419   +20     
  Branches    14838    14841    +3     
=======================================
+ Hits        44128    44148   +20     
  Misses       1515     1515           
  Partials      756      756           

Flag	Coverage Δ
shard-1	43.74% <8.00%> (-0.02%)	⬇️
shard-2	36.23% <68.00%> (+<0.01%)	⬆️
shard-3	32.11% <8.00%> (-0.01%)	⬇️
shard-4	32.85% <8.00%> (-0.01%)	⬇️
shard-5	31.63% <8.00%> (-0.01%)	⬇️
shard-6	44.53% <92.00%> (+0.01%)	⬆️

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/idea-intake.ts	100.00% <100.00%> (ø)
src/mcp/server.ts	95.84% <100.00%> (+0.04%)	⬆️

🚀 New features to boost your workflow:

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

[loopover-orb]

Tip

🟩🟩🟩🟩🟩🟩🟩🟩🟩🟩🟩🟩

✅ LoopOver review result - approve/merge recommended

_{Review updated: 2026-07-14 17:06:40 UTC}

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

✅ Suggested Action - Approve/Merge

• safe to merge

Review summary
This PR extracts `scoreIssue` from `scoreTaskGraph` (pure refactor, no behavior change) and adds `buildClaimPlan`, which routes a scored task-graph's issues into claimable/deferred/skipped by re-deriving each issue's verdict via the same `scoreIssue` helper — correctly avoiding a second decision surface. A new `loopover_plan_idea_claims` MCP tool wires idea validation → task-graph → claim plan, mirroring the existing `intakeIdea` handler's error-path shape. Tests cover the dependency-hold and least-favorable-verdict cases end-to-end, and the diff cleanly maps to its stated intent (closing #4799) building directly on the merged #4798 bridge.

Nits — 5 non-blocking

• The magic-number flag on `idea-intake.ts:140` is a false positive — the `5` there is inside a doc comment referencing 'Rule 5 (spec §2)', not a numeric literal in code.
• `buildClaimPlan` calls `scoreIssue` independently of `graph.rubric.perIssue`, which was already computed by `scoreTaskGraph` in `buildTaskGraph` — recomputing is harmless since `scoreIssue` is pure and cheap, but consider reusing `graph.rubric.perIssue` directly to avoid the redundant pass, per idea-intake.ts:255.
• codecov/patch failed at 92% vs 99% target — worth checking which changed line/branch is uncovered before merge, likely in src/mcp/server.ts's new handler or schema.
• packages/loopover-engine/src/idea-intake.ts:255 — index `graph.rubric.perIssue` by `issue.key` instead of re-calling `scoreIssue`, to keep buildClaimPlan as a pure router over an already-scored graph rather than a second scoring pass.
• Confirm the codecov/patch gap (92% vs 99%) isn't hiding an untested branch in the new `planIdeaClaims` handler in src/mcp/server.ts.

Signal	Result	Evidence
Code review	✅ No blockers	1 reviewer
Linked issue	✅ Linked	#4799
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 (1 linked issue).
Validation posture	✅ 25/25	PR body includes validation/test evidence.
Contributor workload	✅ 10/10	Author activity: 91 registered-repo PR(s), 37 merged, 39 issue(s).
Contributor context	✅ Confirmed Gittensor contributor	luciferlive112116; Gittensor profile; 91 PR(s), 39 issue(s).
Gate result	✅ Passing	No configured blocker found.
Improvement	✅ Minor	risk: clean · value: minor — Code changes are accompanied by test evidence. LLM value judgment: moderate — The change delivers a small, well-scoped, dependency-order-respecting hand-off from scored intake output to a loop-claimable plan, directly closing the linked issue #4799 with full test coverage on the pure logic.

Linked issue satisfaction

Partially addressed
The PR builds a claim/code/submit disposition (claimable/deferred/skipped) from the task-graph and exposes it via a new MCP tool, which is real progress toward the wiring #4799 asks for, but it only produces a plan — it does not actually run a claim/code/submit loop against the target repo, so the acceptance criterion of "a submitted idea results in a running loop" is not yet met.

Review context

• Author: luciferlive112116
• 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: 91 PR(s), 39 issue(s).
• PR-specific overlap: none found.

Contributor next steps

• Keep the PR focused and include validation evidence before maintainer review.

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 LoopOver, a quiet PR intelligence layer for OSS maintainers.

• Re-run LoopOver review

[loopover-orb]

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