feat(miner): consume ORB live gate thresholds in self-review-context

[RealDiligent]

Summary

• Probe GET /v1/repos/:owner/:repo/live-gate-thresholds from fetchSelfReviewContext using the same loopover-mcp session posture as resolveGitHubToken.
• On success, overlay confidence_floor (raise-only readinessMinScore) and scope_cap_* onto the static .loopover.yml reconstruction; leave every other gate field untouched.
• On 403 / 404 / timeout / no session: zero behavior change (fully-standalone path unchanged). Probe timeout defaults to 400ms.
• Coverage fix vs closed feat(miner): consume ORB live gate thresholds in self-review-context #6562: unit-test resolveLoopoverBackendSession null-session path (the single codecov/patch miss).

Closes #6487

Test plan

• Unit: live 200 → thresholds applied
• Unit: 403 / 404 / timeout → static fallback
• Unit: loopoverAuth: null skips probe
• Unit: raise-only confidence + prefer live scope caps
• Unit: resolveLoopoverBackendSession returns null without a session token
• CI + codecov/patch ≥ 99%

[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 93.60%. Comparing base (93f3467) to head (e5c0d3e).

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #6565   +/-   ##
=======================================
  Coverage   93.60%   93.60%           
=======================================
  Files         675      675           
  Lines       67764    67797   +33     
  Branches    18627    18627           
=======================================
+ Hits        63431    63464   +33     
  Misses       3360     3360           
  Partials      973      973           

Flag	Coverage Δ
shard-1	43.88% <0.00%> (-0.17%)	⬇️
shard-2	36.92% <2.85%> (+0.12%)	⬆️
shard-3	32.32% <8.57%> (-0.11%)	⬇️
shard-4	34.62% <0.00%> (-0.28%)	⬇️
shard-5	31.51% <0.00%> (+0.39%)	⬆️
shard-6	45.86% <97.14%> (+0.24%)	⬆️

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

Files with missing lines	Coverage Δ
...ages/loopover-miner/lib/github-token-resolution.js	100.00% <100.00%> (ø)
packages/loopover-miner/lib/self-review-context.js	97.31% <100.00%> (+0.67%)	⬆️

[loopover-orb]

Tip

✅ LoopOver review result - approve/merge recommended

_{Review updated: 2026-07-16 14:34:04 UTC}

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

✅ Suggested Action - Approve/Merge

• safe to merge

Review summary
This diff adds an optional ORB live-gate-thresholds probe to the miner's self-review context builder, overlaying confidence_floor (raise-only readinessMinScore) and scope_cap_files/lines onto the static .loopover.yml reconstruction, with explicit fail-closed handling on 403/404/timeout/no-session. The implementation is correct: the probe is added as a fifth parallel Promise.all entry with its own short timeout, applyLiveGateThresholdsToManifest only mutates the gate object copy, and the raise-only floor logic is tested for both directions. Tests cover the 200/403/404/timeout/null-auth/timeout-budget paths thoroughly and the standalone path is verified byte-identical via an explicit assertion that live-gate-thresholds is never called.

Nits — 5 non-blocking

• packages/loopover-miner/lib/self-review-context.js:71 hardcodes the https:​//api.loopover.ai fallback inline inside normalizeOptions rather than reusing a shared DEFAULT constant already declared in github-token-resolution.js (DEFAULT_API_URL) — worth exporting/reusing that constant to avoid the two files drifting if the default ever changes.
• packages/loopover-miner/lib/self-review-context.js:97 parseLiveGateThresholdFields has three independent numeric-range validations inline; a small per-field helper would reduce the branch count and make future field additions (per feat(review): read-only endpoint exposing ORB's live self-tuned gate thresholds #6486) less repetitive.
• The external brief flags packages/loopover-miner/lib/self-review-context.js as now ~438 lines (over the 400-line convention) — consider whether the live-gate-threshold probe/parse/apply functions belong in a sibling module now that this file does two distinct jobs (GitHub context reconstruction + ORB overlay).
• Consider extracting parseLiveGateThresholdFields, applyLiveGateThresholdsToManifest, and probeLiveGateThresholds into a new lib/live-gate-thresholds.js to keep self-review-context.js focused and under the file-size convention.
• packages/loopover-miner/lib/self-review-context.js:71 — export DEFAULT_API_URL from github-token-resolution.js and reuse it here instead of restating the literal.

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	#6562, #6487
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 (2 linked issues).
Validation posture	✅ 25/25	PR body includes validation/test evidence.
Contributor workload	✅ 10/10	Author activity: 342 registered-repo PR(s), 166 merged, 31 issue(s).
Contributor context	✅ Confirmed Gittensor contributor	RealDiligent; Gittensor profile; 342 PR(s), 31 issue(s).
Improvement	✅ Minor	risk: clean · value: minor

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: 342 PR(s), 31 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.

🧪 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