docs(#834): add library-utility reimplementation check to correctness agent

[fullsend-ai-coder]

Summary

Adds a library-utility reimplementation check to the correctness agent's review dimensions in the code-review problem document. This new dimension instructs the correctness agent to flag manual string parsing that reimplements a utility available in the project's declared dependencies.

Related Issue

Closes #834

Changes

• Added a new bullet point to the correctness agent section in docs/problems/code-review.md
• The new dimension covers manual string parsing/format manipulation (e.g., indexOf, split, substring, startsWith chains) where a library utility exists (e.g., parseLocationRef, semver.parse, URL constructor)
• Includes skip conditions: no utility exists, or manual parsing is intentional (e.g., performance-critical hot path)

Testing

• Change is documentation-only — no code tests affected
• Secret scan passed
• make lint could not run (sandbox network restriction); post-script runs authoritative pre-commit

Checklist

• PR title follows Conventional Commits (correct type, ! for breaking changes)
• No DCO sign-off (autonomous agent session)

---

Closes #834

Post-script verification

• Branch is not main/master (agent/834-library-utility-reimplement-check)
• Secret scan passed (gitleaks — c887fc47c59d8b87b5282ca44044d2933d30df41..HEAD)
• PR body secret scan passed (gitleaks — no-git)
• Pre-commit hooks passed (authoritative run on runner)
• Tests ran inside sandbox

[fullsend-ai-review]

🤖 Finished Review · ✅ Success · Started 9:44 AM UTC · Completed 9:55 AM UTC
Commit: 9c85ebe · View workflow run →

[fullsend-ai-review]

Review

Findings

Low

• [bullet-list-structure] docs/problems/code-review.md:67 — The new bullet item uses a multi-level indented structure (parent bullet with three sub-bullets) that is inconsistent with the existing flat bullet list in the Correctness agent section. All six agent sections in the document (Correctness, Security, Intent & Coherence, Style, Docs Currency, Cross-repo) use flat single-level bullets exclusively. The closest analog is the Security agent's "Non-rendering Unicode characters" bullet, which packs comparable elaboration into a single flat bullet using inline bold text and an em-dash rather than nested sub-items.
  Remediation: Flatten the bullet structure to match existing patterns — either incorporate all information into a single inline bullet (following the Security agent's Unicode bullet pattern) or use multiple top-level bullets at the same indentation level.

Previous run

Review

Findings

Low

• [list-item-length] docs/problems/code-review.md:67 — The new bullet point is longer than most other bullets in the Correctness agent list, though other bullets in the document (e.g., the "Split-payload attacks" bullet and the "Non-rendering Unicode characters" bullet in the Security section) are comparably long, so this is a minor stylistic note.
  Remediation: Consider splitting into a short directive bullet and a nested sub-list with the detailed criteria, though this is stylistic preference.

---

Labels: PR is a pure documentation change to a problem document

[guyoron1]

/fs-fix

[fullsend-ai-coder]

🤖 Finished Fix · ✅ Success · Started 10:31 AM UTC · Completed 10:36 AM UTC
Commit: 9c85ebe · View workflow run →

[fullsend-ai-coder]

🔧 Fix agent — iteration 1 (human-triggered)

Addressed 1 review finding. Split the long library-utility reimplementation bullet (line 67) into a short directive with nested sub-items, as suggested by the reviewer.

Fixed (1):

1. list-item-length: library-utility reimplementation bullet too long (docs/problems/code-review.md): Split the long single bullet into a concise directive with three nested sub-items covering the detection pattern, severity guidance, and skip conditions. Preserves all original content while improving readability.

Tests: passed

Next steps:

• /fs-review — request a re-review of the changes
• /fs-fix <your instruction> — run another fix pass with specific guidance
• Push commits directly — review re-runs automatically on push
  _{Updated by fullsend fix agent}

[fullsend-ai-review]

🤖 Finished Review · ✅ Success · Started 10:40 AM UTC · Completed 10:50 AM UTC
Commit: eed2b00 · View workflow run →

[fullsend-ai-review]

[low] bullet-list-structure

The new bullet item uses a multi-level indented structure (parent bullet with three sub-bullets) that is inconsistent with the existing flat bullet list in the Correctness agent section. All six agent sections in the document use flat single-level bullets exclusively. The closest analog is the Security agent's Non-rendering Unicode characters bullet, which packs comparable elaboration into a single flat bullet using inline bold text and an em-dash rather than nested sub-items.

Suggested fix: Flatten the bullet structure to match existing patterns — either incorporate all information into a single inline bullet (following the Security agent's Unicode bullet pattern) or use multiple top-level bullets at the same indentation level.

[github-actions]

This pull request has been automatically marked as stale because it has not had any activity in the last month. It will be closed in 2 weeks if no further activity occurs. Remove the stale label to reset the inactivity timer.