[genesiscz]

A Claude session is titled by the name Claude Code gave it (its ai-title line, the one /resume shows) when the transcript has one, instead of the first prompt.

• b2b7905 fix(ai, history): a Claude session is titled by the name Claude Code gave it (its ai-title line, shown in /resume and the terminal tab) instead of its first prompt, so the widget lists "Kalendora hotfix research" under that name; a /rename still wins

Gates on this branch (clean worktree, 2026-10-25): bun scripts/git/check-commits.ts, root tsc --noEmit, biome on the changed files, the related tests, and scripts/ci/placeholder-check.sh. Tests: src/utils/agent-sessions/readers/claude.test.ts 15 pass.

Split out of the unified branch (#507); each commit is a cherry-pick of its unified original.

[eve-bot-lovinka]

🐉 eve review — ⏭️ superseded

→ run

• Queued 01:06:52Z
• Reading diff — 2 files
• Building repo map
• Analyzing (find → verify)
• Posting review
• Done 01:16:06Z (9m 14s)

superseded — head moved to 0cb0967 during prep; the queued review covers it

_{run wrun_01M5TVY3069NW6C8PZDAMGWCSP}

Previous runs (1)

run	head	outcome	findings	took
1	b2b7905	✅ APPROVE	1	8m 32s

[coderabbitai]

Warning

Review limit reached

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

Next included review available in 10 minutes.

Check out review usage here.

View limit details

Limit details: You’ve used all 3 included reviews currently available. Your 43 included PR review attempts over the past 7 days set your current allowance at 3 reviews per hour.

Learn how review limits work.

Review configuration:

Run configuration

• Source mode: Auto
• Repository: genesiscz/GenesisTools
• Branch: fix/2026-10-25-claude-session-title
• File: .coderabbit.yaml
• Commit: 0cb0967
• Layers: Repository YAML (base), Organization UI (inherited)
• Review profile: ASSERTIVE
• Plan: Essentials
• Run ID: 23889485-45d8-496d-95f4-1a54c05ba520

Commits

Reviewing files that changed from the base of the PR and between b70571c and 0cb0967.

Files selected for processing: 2

• src/utils/agent-sessions/readers/claude.test.ts
• src/utils/agent-sessions/readers/claude.ts

• Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

_{Comment @coderabbitai help to get the list of available commands.}

[eve-bot-lovinka]

🐉 eve review — 🟡 Review comments

b2b7905 · 1 actionable finding · reviewed by find codex/gpt-6.1-sol, verify codex/gpt-6-luna · view run ↗

Severity	Count
🟡 Medium	1

Blast radius

• createClaudeHistoryOperations (~) → 5 dependent(s) outside this PR: src/utils/agent-sessions/compact-readers.ts, src/utils/agent-sessions/service.test.ts, src/utils/agent-sessions/provider-extensibility.test.ts

ℹ️ Claims vs diff — 4 claims could not be checked from the diff (c1, c2, c3, c4).

[genesiscz]

Review fixes 2026-10-26 02:06 from GPT-6.1 Sol judged by Claude Opus 5.5 (fable-judge)

Round 1. 1 open thread (eve 1, CodeRabbit 0). 1 fixed, 0 rejected, 0 already done. Full PR diff self-review found no additional defects. Fixed in e811a36.

Include ai-title text in searchable record entries (eve-bot-lovinka)

• Context: The ai-title row updated summary metadata but emitted no searchable entries and had no system role. Claude searches scan source entries without metadata matching, so a generated title absent from the prompt could not be found. The expanded reviewer finding labels this Medium.
• Commit(s): e811a3682
• Verdict: accepted
• Code before:

  if (row.type === "queue-operation" || row.type === "summary" || row.type === "custom-title") {
      const text =
          row.type === "summary"
              ? asText(row.summary)

• Code after:

          const text =
              row.type === "summary" || row.type === "ai-title"
                  ? autoTitleOf(row)
                  : row.type === "custom-title"
                    ? asText(row.customTitle)
                    : asText(row.content);

• How was this fixed: The Claude source reader now classifies ai-title rows as system records and emits their aiTitle text as a system entry through the shared autoTitleOf helper. Parser version advances from 6 to 7 to invalidate cached search data. The existing claude.test.ts gains a source-search regression whose generated title is absent from the user prompt, plus assertions for the matched locator, first prompt, selected-record hydration, metadata and system roles. No files outside the original PR diff were required. Post-fix verification: not run (the lead verifies at integration). Before the lead prohibited tests, the regression ran against the unfixed parser and failed with undefined matchedLocators instead of jsonl:2; the other 15 tests passed.
• Confidence: 95%

_{Threads: t1 accepted}