thanhnvandClaude Opus 4.8
2c765c9a45
Task 1.2: introduce a single path resolver so no harness script hardcodes `.specify/...` scattered across the tree. casan-paths.sh resolves four roots (HARNESS/STATE/GOVERNANCE/APP) by marker-based walk-up from its own location — never `git rev-parse` (git root is the repo PARENT here, not the app dir). - 101 bash scripts/tests: 238 hardcoded `$PROJECT_ROOT/.specify/...` refs rewritten to CASAN_HARNESS_ROOT (code) / CASAN_STATE_ROOT (logs,state) / CASAN_GOVERNANCE_ROOT. Sandbox test vars ($WORK/$TP/$FP/$T1_WORK) left untouched. - Roots are NOT exported: each script/subprocess self-resolves from its own tree, matching the original per-script semantics and preserving hermetic sandbox isolation (node casan-step.mjs, copied telemetry/rollback scripts must not inherit real roots). - Sandbox tests that copy a harness script now also copy casan-paths.sh (its new sibling dependency): adversarial (verify-audit-chain/verify-tool-audit/rollback) + track-a (security-check/telemetry-integrity). - control-plane-settings.json reclassified as STATE (untracked runtime store). Roots all still resolve to `.specify` in this monolithic layout, so behavior is unchanged. Full gate: PASS=64 FAIL=0 SKIP=3 (adversarial 44/0, track-a 25/0). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
64 lines
3.0 KiB
Bash
64 lines
3.0 KiB
Bash
#!/usr/bin/env bash
|
|
set -uo pipefail
|
|
|
|
# CASAN Plan-04 — self-improve core (harness-owned) tests.
|
|
# Deterministic. Proves proposals are generated from telemetry (dry-run, no writes),
|
|
# apply is refused without approval, and an approved apply goes through the governed
|
|
# settings store (audited).
|
|
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
source "$SCRIPT_DIR/../scripts/bash/casan-paths.sh"
|
|
PROJECT_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
|
|
SI="$CASAN_HARNESS_ROOT/scripts/bash/self-improve.py"
|
|
CPS="$CASAN_HARNESS_ROOT/scripts/bash/control-plane-settings.py"
|
|
WORK="$(mktemp -d)"
|
|
trap 'rm -rf "$WORK"' EXIT
|
|
export CASAN_CP_STORE_FILE="$WORK/store.json"
|
|
|
|
PASS=0; FAIL=0
|
|
pass() { echo "PASS: $1"; PASS=$((PASS + 1)); }
|
|
fail() { echo "FAIL: $1"; FAIL=$((FAIL + 1)); }
|
|
|
|
echo "===== Plan-04 self-improve core (harness) ====="
|
|
|
|
# metrics telemetry
|
|
cat > "$WORK/metrics.jsonl" <<'JSON'
|
|
{"step":"01-srs","cost_usd":0.02,"status":"ok"}
|
|
{"step":"10-impl","cost_usd":0.08,"status":"ok"}
|
|
JSON
|
|
cat > "$WORK/drift.json" <<'JSON'
|
|
{"drift": true, "entries": ["golden mismatch on 03-spec"]}
|
|
JSON
|
|
|
|
# 1) propose is dry-run (no store write) and yields a cost-cap proposal
|
|
python3 "$SI" propose --metrics "$WORK/metrics.jsonl" --drift "$WORK/drift.json" > "$WORK/props.json" 2>/dev/null
|
|
grep -q "P-COST-CAP" "$WORK/props.json" && pass "propose emits cost-cap proposal from telemetry" || fail "no cost-cap proposal"
|
|
[[ ! -f "$CASAN_CP_STORE_FILE" ]] && pass "propose is dry-run (no store written)" || fail "propose wrote store (not dry-run)"
|
|
|
|
# 2) drift → security-sensitive golden proposal present
|
|
grep -q "P-GOLDEN" "$WORK/props.json" && pass "drift yields review-required golden proposal" || fail "no golden proposal"
|
|
|
|
# 3) apply WITHOUT approval => deny (fail-able: proposal != application)
|
|
set +e
|
|
python3 "$SI" apply --proposals "$WORK/props.json" --id P-COST-CAP >/dev/null 2>"$WORK/3.err"; RC=$?
|
|
set -e 2>/dev/null || true
|
|
[[ "$RC" -eq 1 ]] && grep -q "APPROVAL_REQUIRED" "$WORK/3.err" \
|
|
&& pass "apply refused without approval" || fail "apply not refused without approval (rc=$RC)"
|
|
|
|
# 4) apply WITH approval => governed set recorded in store
|
|
python3 "$SI" apply --proposals "$WORK/props.json" --id P-COST-CAP --approval human-ok >/dev/null 2>&1 \
|
|
&& pass "approved apply succeeds" || fail "approved apply failed"
|
|
VAL="$(python3 "$CPS" get cost.absolute_cap_usd 2>/dev/null | python3 -c 'import json,sys;print(json.load(sys.stdin)["value"])' 2>/dev/null)"
|
|
[[ "$VAL" == "0.12" ]] && pass "applied change persisted via governed store (value=$VAL)" || fail "governed store value unexpected (value=$VAL)"
|
|
|
|
# 5) security-sensitive golden proposal without approval => deny
|
|
set +e
|
|
python3 "$SI" apply --proposals "$WORK/props.json" --id P-GOLDEN >/dev/null 2>"$WORK/5.err"; RC=$?
|
|
set -e 2>/dev/null || true
|
|
[[ "$RC" -eq 1 ]] && grep -q "APPROVAL_REQUIRED" "$WORK/5.err" \
|
|
&& pass "sensitive proposal refused without approval" || fail "sensitive proposal not refused (rc=$RC)"
|
|
|
|
echo ""
|
|
echo "===== SELF-IMPROVE SUMMARY: PASS=$PASS FAIL=$FAIL ====="
|
|
[[ "$FAIL" -eq 0 ]] || exit 1
|