fix(review): isolate review.profile from consensus prompts

[JSONbored]

Motivation

• A recent change threaded .gittensory.yml review.profile into the single system prompt used for both advisory write-ups and block-mode consensus reviewers, allowing a maintainer presentation knob to influence gate-producing consensus outputs.
• review.profile is intended to be PRESENTATION ONLY and must never affect the consensus-defect path that the gate consumes.

Description

• Split system-prompt construction by adding an options.includeProfile flag to buildSystemPrompt so callers can opt out of appending the review.profile suffix.
• Compute two prompts in runGittensoryAiReview: advisorySystem (includes review.profile) and consensusSystem (explicitly excludes the profile), and route advisory/BYOK calls to advisorySystem and block-mode Workers-AI consensus calls to consensusSystem.
• Adjust neuron estimation to account for the separate advisory/consensus prompts so grounding/path context is still billed without letting review.profile change consensus accounting.
• Add a regression unit test that proves an assertive profile affects the advisory prompt but not the two block-mode consensus prompts.

Testing

• Ran npx vitest run test/unit/ai-review.test.ts --reporter=verbose, which passed (1 file, 41 tests, all green) including the new regression test.
• Ran npm run typecheck, which completed successfully with no type errors.
• Ran git diff --check to ensure no whitespace/conflict markers; it passed.

---

Codex Task

[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 95.38%. Comparing base (9e1c351) to head (c80f326).
⚠️ Report is 4 commits behind head on main.
✅ All tests successful. No failed tests found.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #1391   +/-   ##
=======================================
  Coverage   95.38%   95.38%           
=======================================
  Files         201      201           
  Lines       21598    21603    +5     
  Branches     7807     7810    +3     
=======================================
+ Hits        20601    20606    +5     
  Misses        416      416           
  Partials      581      581           

Files with missing lines	Coverage Δ
src/services/ai-review.ts	98.58% <100.00%> (+0.02%)	⬆️

🚀 New features to boost your workflow:

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

[gittensory-orb]

Warning

🟨🟨🟨🟨🟨🟨🟨🟨🟨🟨🟨🟨

⏸️ Gittensory review — held for maintainer review

2 files · 1 AI reviewers · no blockers · readiness 48/100 · CI green · blocked

⏸️ Held for maintainer review

Signal	Result	Evidence
Code review	✅ No blockers	1 reviewers, synthesized
Linked issue	⚠️ Missing	No linked issue or no-issue rationale found.
Related work	⚠️ 3 scoped overlaps	Top overlaps are listed below; lower-confidence bulk is hidden.
Review load	❌ 8/20	Readiness component derived from cached public PR metadata and labels; size label size:M.
Validation evidence	❌ 5/25	Cached preflight status is hold.
Open PR queue	❌ 3/10	48 open PR(s), 9 likely reviewable, 39 unlinked.
Contributor context	✅ Confirmed Gittensor contributor	JSONbored; Gittensor profile; 81 PR(s), 261 issue(s).
Gate result	✅ Passing	No configured blocker found.

Nits — 2 non-blocking

• Repository config was not parsed
• No linked issue detected — If this PR is intended to solve an issue, link it explicitly in the PR body.

Review context

• Author: JSONbored
• Role context: owner (maintainer lane)
• Public audience mode: oss maintainer
• Lane context: Repository registration is not available in the local Gittensory cache.
• Public profile languages: not available
• Official Gittensor activity: 81 PR(s), 261 issue(s).
• Related work: Titles/paths share 6 meaningful terms. (PR #1392)
• Related work: Titles/paths share 6 meaningful terms. (PR #1396)
• Related work: Titles/paths share 6 meaningful terms. (PR #1398)
• Additional title-only matches omitted; title-only overlap does not block.

Contributor next steps

• Treat this as maintainer-lane context rather than normal contributor-lane activity.
• Explain no-issue PR.
• Review top overlaps.
• Add scope summary.
• Fix blocker.
• Expect slower review.
• Refresh registry data or choose a registered active repo.
• Link the issue being solved, or explicitly explain why this is a no-issue PR.
• Check active issues and PRs before submitting.

Signal definitions

• Related work = same linked issue, overlapping active PRs, or title/path similarity.
• Review load = cached public PR metadata such as size labels, changed paths, and preflight status.
• Open PR queue = repo-wide review pressure; it is not a PR quality failure.
• Contributor context = public GitHub/Gittensor identity context; non-Gittensor status is not a blocker.

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

• Re-run Gittensory review

[JSONbored]

Closing — this guards a path the prompt already prevents. The assertive profile raises extra items as nits (ai-review.ts:51,55: "defensive or speculative hardening … is a NIT, not a blocker"), and the consensus gate only fires when both reviewers populate blockers[] (ai-review.ts:672, consensusDefectOf returns null otherwise). So review.profile can't leak into the consensus verdict. The fix also abandons the #1347 advisory-leg reuse (it pays for an extra free Workers-AI consensus call whenever a profile is set), and the regression test fabricates a model that promotes a nit into blockers[], which the prompt explicitly forbids. Net cost, no real protection.