claudemd-cli 0.14.0 → 0.16.0

package/CHANGELOG.md

@@ -8,6 +8,85 @@ 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).
 
+## [0.16.0] - 2026-05-11
+
+**Minor — fix: `sandbox-disposal-check` no longer false-positive-flags `version-sync.sh` sentinel files; cuts 95% of 30d warn volume.**
+
+### Background
+
+30-day rule-hits telemetry: `sandbox-disposal` accounted for **47% of all hook log lines** (853/1819), with **70% concentration in the last 3 days** (596/853 since 2026-05-08). Diagnostic sampling across 3 sessions (claudemd ship session 7930b8b6, code-graph-mcp Rust session 892392d9) showed 100% FP rate on the surveyed fires — the hook warned during pure read-only investigation, AskUserQuestion-only turns, and `git tag` / `gh release create` ship sequences with no `mkdtemp` activity.
+
+### Root cause
+
+Two of this plugin's own hooks stepping on each other:
+
+- `hooks/version-sync.sh:27` creates per-session sentinel **files** via `touch "$TMPDIR/claudemd-sync-<sid>"` (intentionally persisted 24h for session-scoped early-exit).
+- `hooks/sandbox-disposal-check.sh:54` scanned the same `~/.claude/tmp/` directory via `platform_find_newer`, filtering by name prefix (`^claudemd-` / `^tmp\.`) but **not by inode type**. Result: `version-sync`'s session-scoping touch-files were detected as "fresh mkdtemp directories from this session."
+
+Live FS state at fix time: `~/.claude/tmp` held **704 matching entries — 668 files (95%), 36 directories (5%)**. Spec §8.V4 explicitly scopes the rule to "`mkdtempSync` / scratch fixtures / HACK `tmp/`+`scripts/` output" — i.e. directories. Hook header (`sandbox-disposal-check.sh:3`) already documented intent: "Warns if `tmp.XXXXXX`-style mkdtemp **directories** were created this session." Implementation drift, not spec misalignment.
+
+### What changed
+
+- **`hooks/sandbox-disposal-check.sh`**: 1 LOC fix — caller-side `[[ -d "$path" ]] || continue` filter (kept the `-type d` semantic local to this hook rather than baking it into `platform_find_newer`, which `tests/hooks/platform.test.sh` exercises with file fixtures).
+- **`tests/hooks/sandbox-disposal.test.sh`**: new Case 9 — `touch claudemd-sync-fake-session-id` + `touch tmp.fake-mktemp-file` must NOT trigger a warn. Regression guard for cross-hook collision.
+
+### Why not also touch `~/.claude/tmp` residue
+
+The 668 stale sentinels are <24h old (high-volume CC session user — 668 sessions / 24h). `version-sync.sh:34`'s `-mmin +1440 -delete` GC will sweep them on next first-prompt-per-session. `/claudemd-clean-residue` already handles manual cleanup if wanted. Fix is the durable solution; cleanup is mechanical recovery from past noise.
+
+### Why not `(b) + (c)` (per-session first-fire sentinel / cwd-`/tmp` skip)
+
+Original 30d telemetry triage proposed 5 cuts (demote / sentinel / cwd-skip / per-session-create tracking / test-trap). Root-cause investigation collapsed them to 1: 95% of the noise pool was version-sync sentinels misclassified. The remaining 5% is real `mkdtemp` residue the hook *should* catch. Adding per-session sentinel or cwd-skip filters on top would now bias toward FN (silencing legitimate residue) without proportional FP reduction.
+
+### Tests
+
+- New `tests/hooks/sandbox-disposal.test.sh` Case 9 (file-shaped match not flagged). 9/9 passed.
+- Full hook suite: 23 files, all green. JS suite: 405 unchanged. Integration: full-lifecycle + upgrade-lifecycle PASS.
+- `platform.test.sh` unchanged — keeping the type-filter at caller rather than helper preserves the generic file-or-dir contract that platform-lib tests depend on.
+
+### Operator notes
+
+Existing `~/.claude/tmp/claudemd-sync-*` residue (any amount) will be silently ignored by sandbox-disposal from this version forward; `version-sync.sh`'s own 24h GC continues to age them out. Warn-noise reduction is immediate on next CC session reload.
+
+## [0.15.0] - 2026-05-11
+
+**Minor — feat: `mid-spine-yield-scan` Stop hook closes the §11-mid-spine-yield observation gap.**
+
+P2 #1 (a-mini) from the P2/P3 phase plan. Highest-confidence detector in the 5-rule transcript-scan extension queue, shipped first so its FP profile can be measured before layering medium-confidence siblings (iron-law-1 / parallel-path / session-exit / author-not-reviewer).
+
+### Background
+
+§11 Mid-SPINE turn-yield (HARD): once a turn has executed ≥1 tool call inside an active SPINE cycle, the agent must continue planned steps through VALIDATE. Yield only on `[AUTH REQUIRED]`, real ambiguity, or context pressure. Spec gives the tell: "next user message is `继续 / next / 怎么停了 / why did you stop` → confirmed prior yield." Pre-fix, the rule was self-discipline only — no hook observed it, no `rule_hits.jsonl` row carried `§11-mid-spine-yield`, and `/claudemd-rules` staleReviews permanently listed it as un-reviewed. The 4 sibling self-rules (§iron-law-2 / §10-four-section-order / §10-honesty / §10-V) already had hook-side observers (`transcript-structure-scan` / `transcript-vocab-scan`); mid-spine-yield was the only §11 rule still observability-dark.
+
+### What changed
+
+- **New hook** `hooks/mid-spine-yield-scan.sh` (~125 LOC). Stop event; opt-in `MID_SPINE_YIELD_SCAN=1` (default OFF per behavior-layer hook convention — same as `transcript-vocab-scan` / `transcript-structure-scan` / `memory-coverage-scan`).
+- **Detection**: walks the session transcript in order; tracks each assistant turn's text + tool_use count. For each user message matching the continuation tell (`继续 / next / continue / proceed / 怎么停了 / 为什么停了 / 还有吗 / why (did) you stop / why stop / keep going / again`, body ≤ 30 chars after whitespace), evaluates the immediately-prior assistant turn. Suspect mid-SPINE yield when the prior turn (a) contained ≥1 tool_use AND (b) text body lacked four-section report anchor (`^Done:` / `^## Done` / `^Done —`) AND (c) text body lacked `[AUTH REQUIRED` (legitimate yield) AND (d) text body lacked `[PARTIAL:` (legitimate partial-completion signal).
+- **Aggregation**: per-session count emitted as one advisory row with `extra.count`. Per-session dedup via state sentinel `~/.claude/.claudemd-state/mid-spine-yield-<sid>.ts` — at most one row per `session_id`.
+- **Schema additive**: new event `mid-spine-advisory`; new section-mapping row `§11-mid-spine-yield`. `tests/hooks/contract.test.sh` DOCUMENTED array extended.
+- **Registry sync**: 16 → 17 hooks. `scripts/lib/hook-registry.js` adds entry; `tests/scripts/{install,hook-registry}.test.js` count pins moved (real-plugin count: 16 → 17; fixture array stays at 12 — fixture is intentionally minimal); `tests/integration/full-lifecycle.test.sh` MCOUNT + regex group moved; `README.md` shell-hook count + name list updated; `commands/claudemd-toggle.md` valid-name list extended; `README.md` kill-switch enumeration extended with `DISABLE_MID_SPINE_YIELD_HOOK`.
+- **Kill-switch**: `DISABLE_MID_SPINE_YIELD_HOOK=1` (and the global `DISABLE_CLAUDEMD_HOOKS=1`).
+
+### Why minor (not patch)
+
+New hook = new contract surface (rule-hits emits `mid-spine-advisory` rows, schema documents `§11-mid-spine-yield`). Per `feedback_claudemd_spec_single_source_of_truth.md`: plugin semver vs spec semver are independent — plugin minor for additive observability instrumentation; spec stays at v6.11.15 (rule itself unchanged, only the observation surface added). §13.2 budget cost: 0 (no rule add/remove/downgrade).
+
+### Tests
+
+- New `tests/hooks/mid-spine-yield-scan.test.sh`: 12 cases — default OFF / missing-transcript fail-open / four-section-prev silence / tool-call-prev TP / `[AUTH REQUIRED]` legit-yield / `[PARTIAL:]` legit-partial / long-form-message FP filter / kill-switch / per-session dedup / multi-yield count aggregation / tool+report combined silence / EN `next` continuation parity.
+- Updated `tests/hooks/contract.test.sh`: `mid-spine-advisory:mid-spine-yield-scan` in DOCUMENTED array; B/C invariants auto-verify via grep.
+- Updated `tests/scripts/install.test.js` + `tests/scripts/hook-registry.test.js`: count pin 16 → 17.
+- Updated `tests/integration/full-lifecycle.test.sh`: MCOUNT + settings-eviction regex group.
+- Full JS suite: 405 unchanged (count pins only). Hook suite 12/12 new + 8/8 existing transcript-vocab unchanged. Integration: PASS.
+
+### Operator notes
+
+Hook ships default-OFF for ≥30 days FP signal collection before flipping default-ON, mirroring the `transcript-*-scan` + `memory-coverage-scan` precedent. Enable per project via:
+```
+export MID_SPINE_YIELD_SCAN=1
+```
+Once FP rate is measurable, the next 4 sibling detectors (iron-law-1 / parallel-path / session-exit / author-not-reviewer) ship as v0.16.0 / v0.17.0 per the P2 #1 (a/b) split — calibrated against this hook's signal-to-noise baseline.
+
 ## [0.14.0] - 2026-05-11
 
 **Minor — feat: `/claudemd-sampling-audit` retrospective batch scanner for 4 self-enforced HARD rules.**

package/README.md

@@ -58,8 +58,8 @@ Verify in one command (Linux): `node --version && jq --version && gh --version &
 
 | Layer | Contents |
 |---|---|
-| 16 shell hooks | `banned-vocab-check` · `pre-bash-safety-check` · `ship-baseline-check` · `residue-audit` · `memory-read-check` · `memory-prompt-hint` · `memory-coverage-scan` · `sandbox-disposal-check` · `session-start-check` · `session-extended-read` · `session-summary` · `session-end-check` · `transcript-vocab-scan` · `transcript-structure-scan` · `version-sync` · `mem-audit` |
-| 10 slash commands | `/claudemd-status` · `/claudemd-update` · `/claudemd-audit` · `/claudemd-toggle` · `/claudemd-doctor` · `/claudemd-analyze` · `/claudemd-uninstall` · `/claudemd-rules` · `/claudemd-clean-residue` · `/claudemd-sparkline` |
+| 17 shell hooks | `banned-vocab-check` · `pre-bash-safety-check` · `ship-baseline-check` · `residue-audit` · `memory-read-check` · `memory-prompt-hint` · `memory-coverage-scan` · `mid-spine-yield-scan` · `sandbox-disposal-check` · `session-start-check` · `session-extended-read` · `session-summary` · `session-end-check` · `transcript-vocab-scan` · `transcript-structure-scan` · `version-sync` · `mem-audit` |
+| 11 slash commands | `/claudemd-status` · `/claudemd-update` · `/claudemd-audit` · `/claudemd-toggle` · `/claudemd-doctor` · `/claudemd-analyze` · `/claudemd-uninstall` · `/claudemd-rules` · `/claudemd-clean-residue` · `/claudemd-sparkline` · `/claudemd-sampling-audit` |
 | 1 standalone CLI | `claudemd-cli lint` · `claudemd-cli audit` ([npm: `claudemd-cli`](https://www.npmjs.com/package/claudemd-cli)) |
 | Spec v6.11.15 | `~/.claude/CLAUDE.md` · `CLAUDE-extended.md` · `CLAUDE-changelog.md` (backup-before-overwrite) |
 
@@ -180,6 +180,7 @@ export DISABLE_MEM_AUDIT_HOOK=1                  # v0.9.4+ — Stop Why:-less ci
 export DISABLE_SESSION_END_CHECK_HOOK=1          # v0.9.27+ — SessionEnd §11-session-exit mid-SPINE check
 export DISABLE_SESSION_EXTENDED_READ_HOOK=1      # v0.10.1+ — PreToolUse:Read §13.1-extended-read denominator signal
 export DISABLE_MEMORY_COVERAGE_HOOK=1            # v0.13.0+ — Stop §11-mem-coverage advisory (opt-in via MEMORY_COVERAGE_SCAN=1)
+export DISABLE_MID_SPINE_YIELD_HOOK=1            # v0.15.0+ — Stop §11-mid-spine-yield advisory (opt-in via MID_SPINE_YIELD_SCAN=1)
 ```
 
 **2a. Per-sub-feature** (v0.4.0+). Sub-flags inside an enabled hook, named without the `_HOOK` suffix:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claudemd-cli",
-  "version": "0.14.0",
+  "version": "0.16.0",
   "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": {