The TUI comparison picker silently ignored --model-a/--model-b (only the
--format json path used them), and both paths required the canonical model
id verbatim with no way to pass the display name the picker itself shows
(e.g. "Opus 4.8" for claude-opus-4-8).
Adds findModelStat, a shared lookup that matches the canonical id first and
falls back to getShortModelName's existing canonical -> display mapping
(case-insensitive) rather than a new alias table. Both the JSON path and
renderCompare/CompareView now use it; renderCompare resolves --model-a/
--model-b up front and seeds CompareView's picked-models state so results
load immediately instead of showing the picker. Also validates "both or
neither" for the TUI (default) format, matching the JSON path.
Fixesgetagentseal/codeburn#767 (item 1).
Compare defined cache-hit as read/(input+read+write) while menubar-json
and every other surface use read/(input+read), so the same model showed
two different numbers depending on screen. Standardize on the latter;
TUI compare output changes intentionally.
Turns whose only assistant tool is `Skill` collapse to category `general`
because `classifyByToolPattern` returns `'general'` and `refineByKeywords`
only operates on `coding`/`exploration`. In environments that lean on Claude
Code skills, the per-activity dashboard column flattens — every `/init`,
`/review`, `/security-review`, `/claude-api`, plus user-defined skills, all
land in `general` with no signal about which workflow ran.
Implements Option A from the issue:
- `ParsedApiCall.skills: string[]` populated in the Anthropic-path parser
via a new `extractSkillNames` helper that reads `input.skill || input.name`
from each `Skill` ToolUseBlock (mirrors `detectGhostSkills` extraction at
optimize.ts:765 so the two stay in sync).
- `ClassifiedTurn.subCategory?: string` set to the first skill name when the
resolved category is `general` AND any skill identifier was extracted.
Top-level category stays `general` — existing aggregations, exports, and
category-keyed code paths unchanged.
- `SessionSummary.skillBreakdown: Record<string, {turns,costUSD,editTurns,
oneShotTurns}>` populated in the same per-turn loop that builds
`categoryBreakdown`. Provider sessions (Codex/Cursor/etc.) keep `skills:
[]` — they don't expose the Skill tool surface today.
- Dashboard `ActivityBreakdown` renders top-N skill sub-rows beneath the
`general` row when present (indented `/skill-name`, dimmed). Other
categories render exactly as before; if no skills were invoked, the panel
is byte-identical to current output.
Existing 419 tests still pass. New `tests/classifier.test.ts` adds 8 cases:
single skill via `input.skill`, single via `input.name`, first-wins for
multi-skill turns, aggregation across multiple assistant calls in one turn,
no-name fallback (`subCategory` stays undefined), `Skill+Edit` promoting to
`coding` and dropping subCategory, non-Skill general turns, and a legacy
ParsedApiCall shape with `skills` field absent (forward-compat). Pre-fix
verification by stashing the source change reproduces 4/8 failures with the
exact "expected 'init', received undefined" diff; restoring → 8/8 pass.
Closes#203.
🤖 AI assistance disclosure: assistant-scaffolded by Claude (Opus 4.7);
author of record reviewed every line, ran the full vitest suite locally
(`npm test` → 32 files / 427 tests pass), `npx tsc --noEmit` clean, and
`npm run build` produces a clean ESM bundle.
5-section compare view: Performance (one-shot, retry, self-correction),
Efficiency (cost/call, cost/edit, output/call, cache hit), Category
Head-to-Head bar charts, Working Style, and Context.
Planning rate now detects TaskCreate/TaskUpdate/TodoWrite instead of
only EnterPlanMode (which was never used, showing 0% for all models).
Validated against raw JSONL with zero false positives.
Responsive side-by-side layout at 90+ cols. Self-correction scanner
with compact file skipping and model+timestamp dedup. 274 tests.
Remove high-false-positive patterns (I'm sorry, I should have, sorry for).
Add precise patterns (you're right I, that was incorrect, let me correct).
Skip compact JSONL files that replay compressed context.
Deduplicate by model+timestamp to prevent double-counting.
Fix test timestamps to work with deduplication.
Adds scanSelfCorrections() which reads raw .jsonl session files (including subagent dirs) and counts per-model self-correction patterns for use in the model comparison metrics.
