claudemd-cli 0.9.10 → 0.9.12

package/CHANGELOG.md

@@ -8,6 +8,75 @@ All notable changes to the `claudemd` plugin. This changelog tracks plugin artif
 - **Canonical spec version source**: `spec/CLAUDE.md` top-line title (`# AI-CODING-SPEC vX.Y.Z — Core`) + `spec/CLAUDE-changelog.md` top `##` entry.
 - **Plugin semver vs spec semver** are independent: plugin patch (0.2.0 → 0.2.1) may ship when spec is unchanged (this release); plugin minor (0.1.9 → 0.2.0) ships when spec minor updates (v0.2.0 shipped spec v6.10.0).
 
+## [0.9.12] - 2026-05-10
+
+**Patch — `session-summary.sh` `top_section` bucket pollution fix.** Spec v6.11.7 unchanged. Empirical session run produced banner `[claudemd] last session: 61 denies, 3 bypasses, 134 warns, top: (unset)` despite the log holding 95 `§8.V4` warns and 54 `§10-V` denies in window — i.e. `(unset)` should not have won.
+
+### Fixed
+
+- `[fix]` **`top_section` calculation in `hooks/session-summary.sh`**: previously `group_by(.spec_section // "(unset)")` over **all** events in window, including operational telemetry that lacks `spec_section` by design (`session-start.bootstrap`, `user-prompt-submit.version-sync`, `session-start.upstream-banner`, `ship-baseline.pass`, `ship-baseline.pass-known-red`). On a healthy session those ops events outnumber rule-violation events ≥1:1, so the synthetic `"(unset)"` bucket dominates and the banner reads `top: (unset)` regardless of actual rule activity. Reproducer (24h window): 18 events total, 2 deny `§10-V` + 1 warn `§8.V4` + 15 housekeeping (no `spec_section`) → `top_section = "(unset)"` (wrong; correct: `§10-V`).
+- `[fix]` Now restricts `top_section` aggregation to the same three event types whose counts the banner reports — `deny` + `bypass-escape-hatch` + `warn` — and drops null-`spec_section` rows. `top_section` becomes "the most-cited spec_section among events that contributed to the displayed counts," internally consistent with denies/bypasses/warns numerals.
+
+### Added
+
+- `[test]` **Case 7 in `tests/hooks/session-summary.test.sh` (6/6 → 7/7)**: regression for the pollution scenario. 2 deny `§10-V` + 1 warn `§8.V4` + 15 housekeeping events (5× bootstrap + 5× version-sync + 5× pass) → asserts `top_section == "§10-V"` and `denies == 2 && warns == 1`. Pre-fix this test fails with `top_section == "(unset)"`.
+
+### Why no L3 / pre-ship-review chain
+
+`fix:` (bugfix restoring intended behavior, not feat/change) per spec §2 hard-upgrade exclusion list — `top_section` is meant to surface "what rule hit you most this session," docstring at hook L8 reads "the agent sees its own recent tendency"; the polluted `(unset)` form fails that intent. L2 ceiling applies. Diff: 1 hook (12 lines net), 1 test (33 lines added), 0 spec/contract change. CHANGELOG `fix:` voice.
+
+### Versioning
+
+- `package.json`, `plugin.json`, `marketplace.json` (×2 fields) → `0.9.12`. Spec trio unchanged at v6.11.7.
+
+---
+
+## [0.9.11] - 2026-05-10
+
+**Patch — `transcript-structure-scan.sh` regex coverage gap fix.** Spec v6.11.7 unchanged. v0.9.10 shipped the hook with `^Done:` / `^Not done:` etc. line-anchored regex (canonical spec form). Empirical run against 5 real session transcripts (`~/.claude/projects/-mnt-data-ssd-dev-projects-claudemd/*.jsonl`) showed the prevalent style in this project is the **markdown-header form** (`## Done` / `## Done — <title>` / `## Not done`) per memory `feedback_done_section_chinese_prose` example — not canonical inline. v0.9.10 hook missed those entirely.
+
+### Fixed
+
+- `[fix]` **Label regex**: now matches both canonical `^Done:` and markdown-header `^## Done\b` (with `:`, em-dash + space, or EOL terminators). Single awk pass strips `^##\s+` prefix then tests `^<label>(<sp>—|:|<sp>$)`. Same for `Not done`, `Failed`, `Uncertain`. Narrative text like `## Done with the analysis` (no canonical terminator after `Done`) does NOT match.
+- `[fix]` **Evidence window 3 → up to 15 lines, capped at next-label-line - 1**: previously `Done` evidence had to land in the next 2 lines. Markdown reports commonly use `## Done — title` / blank / intro / table — evidence lives in the table 3-15 lines later. Window expansion captures those. Cap-at-next-label prevents bleed-through (e.g. "untested" in `Uncertain` matching `\btest\b` and falsely satisfying `Done`'s evidence requirement).
+- `[fix]` **Evidence regex 中文 addition**: `证据[:：]` (literal "evidence:" / "evidence：" header marker, both ASCII and full-width colon). Tight — requires colon, so prose mentions of the word "证据" don't trigger.
+- `[fix]` **Empty-Done skip applies only to canonical form**: `Done: (none)` / `Done: ` skip; `## Done` (header alone, body on subsequent lines) does NOT auto-skip — the evidence-window check above is authoritative for markdown form.
+- `[fix]` **`uncertain-hedge` matches `## Uncertain` markdown form too**, but bare `## Uncertain` (header alone, rationale on following lines) is correctly excluded — the test fires only when content lives ON the same line as the label. `^## Uncertain[[:space:]]*$` short-circuits to silent.
+
+### Added
+
+- `[test]` **3 new cases (12/12 → 15/15)** in `tests/hooks/transcript-structure-scan.test.sh`:
+  - case 13: markdown four-section with evidence in window → silent
+  - case 14: markdown four-section without evidence → `§iron-law-2` fires
+  - case 15: bare `## Uncertain` header alone → silent
+
+### Empirical validation against real transcripts
+
+After the broadening fix, the hook was run against 5 most-recent session transcripts under `~/.claude/projects/-mnt-data-ssd-dev-projects-claudemd/*.jsonl` (each transcript represents one session's full event stream, last 200 lines = last ~20-50 turns).
+
+| Transcript | `## Done` | `## Not done` | `## Failed` | `## Uncertain` | hook hits |
+|---|---|---|---|---|---|
+| 78696600 (current session) | 2 | 2 | 2 | 2 | 0 |
+| 3e4c19fb | 2 | 2 | 2 | 2 | 0 |
+| 8f6585f6 | 0 | 0 | 0 | 0 | 0 |
+| 84078778 | 0 | 0 | 0 | 0 | 0 |
+| 71210740 | 0 (4 plain `Done:`) | 0 | 0 | 0 | 0 |
+
+**0 hits across 5 transcripts.** Verified manually: the v0.9.10 ship report's Done window (last assistant turn of session 78696600) contains 4 evidence fingerprints (`证据：`, `passed`, `tests`, `baseline`) — hook correctly stays silent. Uncertain section uses `## Uncertain` standalone with rationale on following lines — bare-header skip applies. Reports are honestly clean; the hook isn't suppressing.
+
+### Versioning
+
+- `package.json` 0.9.10 → **0.9.11** (npm).
+- `.claude-plugin/plugin.json` 0.9.10 → **0.9.11**.
+- `.claude-plugin/marketplace.json` two version fields 0.9.10 → **0.9.11**.
+- Spec headers unchanged (v6.11.7 still current); no `spec/CLAUDE-changelog.md` entry — plugin-only patch.
+
+### Validation
+
+- `bash tests/hooks/transcript-structure-scan.test.sh` → 15/15 passed.
+- `node --test tests/scripts/*.test.js` → 217 passed.
+- `bash tests/run-all.sh` → all suites passed.
+
 ## [0.9.10] - 2026-05-10
 
 **Patch — P1.2 restart: agent self-rule observation mirror via new `transcript-structure-scan` Stop hook.** Spec v6.11.7 unchanged. Closes the audit gap that ~7 self-enforced HARD rules in `spec/hard-rules.json` (§iron-law-2, §10-four-section-order, §10-honesty, §10-specificity, §0-hard-auth-override, §11-mid-spine-yield, §11-session-exit) had **no hook-side feedback signal** — only banned-vocab (§10-V) was observed via `transcript-vocab-scan`. P1.2 was deferred in v0.9.7 with two reasons (pattern lockstep on `tests/scripts/spec-pattern-drift.test.js`; FP storm risk on every `PostToolUse`); both addressed by design pivot.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claudemd-cli",
-  "version": "0.9.10",
+  "version": "0.9.12",
   "description": "Standalone CLI for §10-V banned-vocab + transcript scanning. Companion to the claudemd Claude Code plugin (github.com/sdsrss/claudemd) for use in git pre-commit hooks, GitHub Actions, and other agents.",
   "type": "module",
   "bin": {