From edcbc5f7ea9bffc95e8e131b6cf3a27a04fb6aed Mon Sep 17 00:00:00 2001 From: Mike Swanson Date: Mon, 8 Jun 2026 08:24:28 -0700 Subject: [PATCH] feat(self-check): harness smoke tests lock in the 1.4.0 invariants (VERSION 1.4.1) Adds a 'harness' category to /self-check (Task 12, self-check half) so the harness- optimization gains can't silently regress. All read-only / non-invasive: - VERSION marker present + not older than manifest.harness.min_version - skill-registry description budget (sum of all SKILL.md description: fields under registry_desc_budget_chars) -- the metric that catches Task 5 bloating back - global deploy targets ~/.claude/skills + ~/.claude/commands populated (Mac-wipe failure) - harness-guard.sh present + wired into sync.sh - core scripts parse (bash -n on sync/guard/now-phoenix); now-phoenix.sh emits a valid date Tunables in baseline/manifest.json 'harness' block. Verified 9/9 PASS; budget WARN negative-tested at a synthetic over-budget value. Co-Authored-By: Claude Opus 4.8 (1M context) --- .claude/harness/CHANGELOG.md | 12 ++ .claude/harness/VERSION | 2 +- .claude/skills/self-check/SKILL.md | 1 + .../skills/self-check/baseline/manifest.json | 13 ++ .../skills/self-check/scripts/self-check.sh | 116 ++++++++++++++++++ .../claudetools-harness-optimization/plan.md | 4 + 6 files changed, 147 insertions(+), 1 deletion(-) diff --git a/.claude/harness/CHANGELOG.md b/.claude/harness/CHANGELOG.md index e174b05..c2bc440 100644 --- a/.claude/harness/CHANGELOG.md +++ b/.claude/harness/CHANGELOG.md @@ -46,3 +46,15 @@ or old harness during a heterogeneous rollout. See --fmt` formats. `post-bot-alert.sh` already uses `jq -nc --arg` (verified, no change needed). - Deferred (unchanged): full Python port = separate spec; Task 8 shard command bodies; promote guard to FATAL after a clean warn window; schedule memory-dream --apply-safe per-machine. + +## 1.4.1 — 2026-06-08 (Task 12: self-check smoke tests) +- /self-check gained a `harness` category that locks in the 1.4.0 invariants (all read-only): + VERSION present + not older than manifest min_version; **skill-registry description budget** + (sum of all SKILL.md description: fields under manifest.harness.registry_desc_budget_chars — + WARN on regrowth, the metric that would catch Task 5 bloating back); global deploy targets + ~/.claude/skills + ~/.claude/commands populated (the Mac-wipe failure); harness-guard.sh wired + into sync.sh; core scripts parse (bash -n on sync/guard/now-phoenix); now-phoenix.sh emits a + valid date. Tunables live in baseline/manifest.json `harness` block. Verified: 9/9 PASS on this + machine; budget WARN trips correctly on a synthetic over-budget value. +- Also reconciled the remaining "GrepAI first" docs (standard + CODING_GUIDELINES) with the + wiki-first recall hierarchy (started in CLAUDE_EXTENDED). diff --git a/.claude/harness/VERSION b/.claude/harness/VERSION index 88c5fb8..347f583 100644 --- a/.claude/harness/VERSION +++ b/.claude/harness/VERSION @@ -1 +1 @@ -1.4.0 +1.4.1 diff --git a/.claude/skills/self-check/SKILL.md b/.claude/skills/self-check/SKILL.md index 1fae29b..26455ba 100644 --- a/.claude/skills/self-check/SKILL.md +++ b/.claude/skills/self-check/SKILL.md @@ -81,6 +81,7 @@ SELFCHECK_TS="$(date -u +%Y-%m-%dT%H:%M:%SZ)" \ | **skills/commands** | every skill dir and command file in the baseline is present; extras are reported as census candidates. | | **duplicates** | command/skill names present in BOTH the repo and `~/.claude`. Divergent content = WARN (the "same `/cmd`, different behaviour on the Mac" bug); identical = INFO (redundant, will drift). CRLF-only differences are ignored. | | **memory** | `MEMORY.md` index exists; no orphaned memory files; manifest-declared contradiction patterns (see semantic pass below). Never FAILs the grade. | +| **harness** | the 1.4.0 invariants (read-only): VERSION marker present + not older than `manifest.harness.min_version`; **skill-registry description budget** (sum of all SKILL.md `description:` fields under `registry_desc_budget_chars` — WARN on regrowth); global deploy targets `~/.claude/skills` + `~/.claude/commands` populated (the "Mac wiped global skills" failure); `harness-guard.sh` present + wired into `sync.sh`; core scripts parse (`bash -n` on sync/guard/now-phoenix); `now-phoenix.sh --date` emits a valid date. Budget/min-version/script-list are tunable in `manifest.harness`. | | **vault** | vault repo exists; sops+age present; `vault.sh list` succeeds (decrypt wired). | | **connectivity** | coord API (required), main API + internal Gitea (advisory; off-network is OK). | diff --git a/.claude/skills/self-check/baseline/manifest.json b/.claude/skills/self-check/baseline/manifest.json index a6c8043..419565b 100644 --- a/.claude/skills/self-check/baseline/manifest.json +++ b/.claude/skills/self-check/baseline/manifest.json @@ -5,6 +5,19 @@ "derived_at": "2026-06-02", "note": "PROVISIONAL baseline, generated from a single known-good machine. V1 of self-check is a CENSUS tool: every machine probes itself, publishes to the coord API, and we refine this manifest from real fleet data (see baseline/README.md). Do NOT treat 'extra' or 'missing' items as authoritative until the fleet census has confirmed them across machines.", + "harness": { + "min_version": "1.4.0", + "version_file": ".claude/harness/VERSION", + "registry_desc_budget_chars": 10500, + "registry_desc_why": "Sum of all skill SKILL.md description: fields. These inject into EVERY session's skill registry, so a bloated description is a fleet-wide context tax. Budget set at the 1.4.0 post-trim size (~8.7k) + headroom; a WARN here means a skill description grew back and should be re-trimmed (move triggers/examples into the SKILL.md body).", + "syntax_check_scripts": [ + ".claude/scripts/sync.sh", + ".claude/scripts/harness-guard.sh", + ".claude/scripts/now-phoenix.sh" + ], + "guard_wired_in": ".claude/scripts/sync.sh" + }, + "required_tools": [ { "name": "bash", "why": "hooks, scripts, sync, vault wrapper" }, { "name": "git", "why": "repo + submodules + Gitea sync" }, diff --git a/.claude/skills/self-check/scripts/self-check.sh b/.claude/skills/self-check/scripts/self-check.sh index 6286508..0a01c00 100644 --- a/.claude/skills/self-check/scripts/self-check.sh +++ b/.claude/skills/self-check/scripts/self-check.sh @@ -546,6 +546,121 @@ check_memory() { fi } +# --------------------------------------------------------------------------- +# CHECK: harness smoke tests (the 1.4.0 invariants). +# Locks in the harness-optimization gains so they can't silently regress: +# - VERSION marker present and not older than the manifest's min_version +# - skill-registry description budget (a bloated description taxes EVERY session) +# - global deploy targets populated (the "Mac wiped ~/.claude/skills" failure) +# - guard wired into sync.sh + executable +# - core scripts parse (bash -n) and now-phoenix.sh emits a valid date +# All read-only / non-invasive: no commits, no pushes, only a parse + a clock read. +# --------------------------------------------------------------------------- +ver_ge() { # $1 >= $2 -> echoes 1/0 (portable dotted-numeric compare) + awk -v a="$1" -v b="$2" 'BEGIN{ + na=split(a,A,"."); nb=split(b,B,"."); n=(na>nb?na:nb); + for(i=1;i<=n;i++){x=(i<=na?A[i]+0:0); y=(i<=nb?B[i]+0:0); + if(x>y){print 1; exit} if(x= min ${minver:-n/a})" + fi + fi + + # 2. Skill-registry description budget (sum of all SKILL.md description: fields) + local total=0 f n=0 sub + for f in "$REPO_ROOT"/.claude/skills/*/SKILL.md; do + [ -f "$f" ] || continue + sub="$(awk ' + /^---[ \t]*$/ { d++; next } + d==1 { + if ($0 ~ /^[A-Za-z0-9_-]+:/ && $0 !~ /^description:/) indesc=0 + if ($0 ~ /^description:/) indesc=1 + if (indesc) total += length($0) + } + d>=2 { print total+0; exit } + END { if (d<2) print total+0 }' "$f")" + total=$((total + ${sub:-0})); n=$((n+1)) + done + if [ "$total" -gt "$budget" ] 2>/dev/null; then + emit harness.registry_budget harness WARN \ + "skill-registry descriptions = $total chars over budget $budget ($n skills) — registry bloat taxes every session" \ + "Trim the longest skill description(s) to one line; move triggers/examples into the SKILL.md body" + else + emit harness.registry_budget harness PASS "skill-registry descriptions $total/$budget chars ($n skills)" + fi + + # 3. Global deploy targets populated (Phase 5b/5c deploy; empty = the Mac-wipe failure) + local gs gc + gs="$(ls -1d "$HOME"/.claude/skills/*/ 2>/dev/null | wc -l | tr -d '[:space:]')" + gc="$(ls -1 "$HOME"/.claude/commands/*.md 2>/dev/null | wc -l | tr -d '[:space:]')" + if [ "${gs:-0}" -eq 0 ] 2>/dev/null; then + emit harness.deploy_skills harness WARN "~/.claude/skills is EMPTY (global skill deploy missing)" \ + "Run /sync — sync.sh Phase 5c redeploys skills to ~/.claude/skills" + else + emit harness.deploy_skills harness PASS "~/.claude/skills populated ($gs skills)" + fi + if [ "${gc:-0}" -eq 0 ] 2>/dev/null; then + emit harness.deploy_commands harness WARN "~/.claude/commands has no .md files (global command deploy missing)" \ + "Run /sync — sync.sh Phase 5b redeploys commands to ~/.claude/commands" + else + emit harness.deploy_commands harness PASS "~/.claude/commands populated ($gc commands)" + fi + + # 4. Guard wired into sync.sh + executable + local guard="$REPO_ROOT/.claude/scripts/harness-guard.sh" + if [ ! -f "$guard" ]; then + emit harness.guard harness WARN "harness-guard.sh missing" "Restore via /sync" + elif ! grep -q "harness-guard" "$REPO_ROOT/$guard_in" 2>/dev/null; then + emit harness.guard harness WARN "harness-guard.sh not wired into $guard_in (pre-commit guard inactive)" \ + "Re-check $guard_in: it should call harness-guard.sh before commit" + else + emit harness.guard harness PASS "harness-guard.sh present + wired into $guard_in" + fi + + # 5. Core scripts parse (bash -n) + now-phoenix emits a valid date + local s sp + for s in $(jq -r '.harness.syntax_check_scripts[]? // empty' "$MANIFEST"); do + sp="$REPO_ROOT/$s" + if [ ! -f "$sp" ]; then + emit "harness.syntax.$(basename "$s")" harness WARN "script missing: $s" "Restore via /sync" + elif bash -n "$sp" 2>/dev/null; then + emit "harness.syntax.$(basename "$s")" harness PASS "parses clean: $s" + else + emit "harness.syntax.$(basename "$s")" harness FAIL "SYNTAX ERROR in $s (bash -n failed)" \ + "Fix the parse error: bash -n \"$s\"" + fi + done + local nph="$REPO_ROOT/.claude/scripts/now-phoenix.sh" out + if [ -f "$nph" ]; then + out="$(bash "$nph" --date 2>/dev/null)" + if echo "$out" | grep -qE '^[0-9]{4}-[0-9]{2}-[0-9]{2}$'; then + emit harness.now_phoenix harness PASS "now-phoenix.sh --date OK ($out)" + else + emit harness.now_phoenix harness WARN "now-phoenix.sh --date returned unexpected output: '$out'" \ + "Check .claude/scripts/now-phoenix.sh" + fi + fi +} + # --------------------------------------------------------------------------- # Build the census JSON from accumulated results # --------------------------------------------------------------------------- @@ -730,6 +845,7 @@ check_git check_skills_commands check_duplicates check_memory +check_harness_smoke check_vault check_connectivity diff --git a/specs/claudetools-harness-optimization/plan.md b/specs/claudetools-harness-optimization/plan.md index a7eab7f..bbec471 100644 --- a/specs/claudetools-harness-optimization/plan.md +++ b/specs/claudetools-harness-optimization/plan.md @@ -40,6 +40,10 @@ left in place — recall grep covers both layouts; NO mass migration (would break wiki `source_logs` refs for low payoff). - **P1+P2+P3 COMPLETE (2026-06-08, VERSION 1.4.0).** +- [DONE] Task 12 (self-check half) — `/self-check` now has a `harness` category enforcing the + 1.4.0 invariants (VERSION/min-version, skill-registry description budget, global deploy targets + populated, guard wired, core scripts parse, now-phoenix valid). Read-only; 9/9 PASS; budget WARN + negative-tested. Tunables in `self-check/baseline/manifest.json` `harness` block. (VERSION 1.4.1.) - REMAINING (ops follow-ups, not blocking): - Promote the warn-only guard (Task 4) to FATAL after a clean warn window (check `.claude/harness/guard.log` across the fleet).