Standard production layout: the OKR app (was nested under AINative_OKR_CASAN5/) is now
the repository root. No more wrapper directory.
- Promote AINative_OKR_CASAN5/* -> repo root (backend/ frontend/ packages/ apps/
.specify/ docs/ infra/ nginx/ scripts/ + configs). Merge tool dirs: .gitea (kept the
active deploy ci.yml, added harness-ci.yml + runbooks), .claude (agents/commands +
launch.json), .github moved up.
- Remove redundant: 00_SUBMISSION_PACKAGE, scattered root notes (FPT_CASAN_Full.md,
tu-tuong-casan.md, casan-tu-sinh..., casan_harness_assessment.md, source-review...,
README_CASAN5_REFINED.md), casan-next-plans/ and optimize-docs/ (competition/planning
artifacts — roadmap + design history preserved in git log / commit messages).
- Update all references to the old layout:
- .gitea/workflows/{ci,harness-ci}.yml, .github/workflows/{ci,deploy}.yml:
working-directory .; drop AINative_OKR_CASAN5/ prefix; .specify/{tests,scripts}
-> packages/casan-harness/... (.specify/logs state kept)
- .claude/launch.json, .gitea/*-runbook.md: path prefixes
- CLAUDE.md, README.md: docs/input -> apps/okr/domain/input
- policy-bundle.yaml: 8 policy paths -> packages/casan-harness/...; manifest re-signed
- secrets-scan.sh: fixture excludes -> new package/domain paths.
Full gate from the new root: PASS=64 FAIL=0 SKIP=3.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
100 lines
4.1 KiB
Bash
Executable File
100 lines
4.1 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
set -uo pipefail
|
|
|
|
# CASAN H6 cost detector (WP-C + Track A cost controls A5 / V12,V13,V14).
|
|
# Answers the H6 key question: "if a step suddenly costs 3x the tokens, does
|
|
# anyone know?". Reads real per-step usage from provider-usage.jsonl and applies
|
|
# three complementary controls:
|
|
# 1. Relative spike — any step > MULTIPLIER x median (needs >=3 records).
|
|
# 2. Absolute cap — any single step > CASAN_COST_ABSOLUTE_MAX_TOKENS. Works
|
|
# from the very first record, so a slow-boil that drags the median up
|
|
# (V12) and a cold-start with no history (V14) are BOTH still caught.
|
|
# 3. Cumulative budget — sum of tokens > CASAN_COST_CUMULATIVE_BUDGET_TOKENS,
|
|
# catching a spray of many under-threshold calls (V13).
|
|
#
|
|
# Usage: cost-spike-detect.sh [provider-usage.jsonl] [multiplier]
|
|
# Env: CASAN_COST_ABSOLUTE_MAX_TOKENS per-call hard cap (0/unset = off)
|
|
# CASAN_COST_CUMULATIVE_BUDGET_TOKENS run/session budget (0/unset = off)
|
|
# Exit: 0 no violation, 2 violation (spike/absolute/cumulative), 64 usage,
|
|
# 3 not enough data for the RELATIVE test and no absolute/cumulative cap set.
|
|
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
source "$SCRIPT_DIR/casan-paths.sh"
|
|
PROJECT_ROOT="$CASAN_APP_ROOT"
|
|
# SEC-23 (MT-03): per-tenant cost/quota. With no explicit log arg, a tenant run
|
|
# evaluates its OWN usage log so one tenant's spend never counts against another's
|
|
# budget (noisy-neighbor isolation). No tenant set -> the shared default log.
|
|
if [[ -n "${1:-}" ]]; then
|
|
LOG="$1"
|
|
elif [[ -n "${CASAN_TENANT_ID:-}" ]]; then
|
|
LOG="$(bash "$SCRIPT_DIR/tenant-store.sh" resolve telemetry/provider-usage.jsonl 2>/dev/null)" \
|
|
|| { echo "COST_SPIKE_TENANT_DENIED" >&2; exit 3; }
|
|
else
|
|
LOG="$CASAN_STATE_ROOT/logs/level5/provider-usage.jsonl"
|
|
fi
|
|
MULT="${2:-3.0}"
|
|
|
|
[[ -f "$LOG" ]] || { echo "COST_SPIKE_NO_DATA file=$LOG" >&2; exit 3; }
|
|
|
|
CASAN_COST_ABSOLUTE_MAX_TOKENS="${CASAN_COST_ABSOLUTE_MAX_TOKENS:-0}" \
|
|
CASAN_COST_CUMULATIVE_BUDGET_TOKENS="${CASAN_COST_CUMULATIVE_BUDGET_TOKENS:-0}" \
|
|
python - "$LOG" "$MULT" <<'PY'
|
|
import json, os, sys, statistics
|
|
path, mult = sys.argv[1], float(sys.argv[2])
|
|
abs_max = int(os.environ.get("CASAN_COST_ABSOLUTE_MAX_TOKENS", "0") or "0")
|
|
cum_budget = int(os.environ.get("CASAN_COST_CUMULATIVE_BUDGET_TOKENS", "0") or "0")
|
|
|
|
rows = []
|
|
for line in open(path, encoding="utf-8"):
|
|
line = line.strip()
|
|
if not line:
|
|
continue
|
|
try:
|
|
r = json.loads(line)
|
|
except ValueError:
|
|
continue
|
|
if "total_tokens" in r:
|
|
rows.append((r.get("step", "?"), int(r["total_tokens"])))
|
|
|
|
tokens = [t for _, t in rows]
|
|
total = sum(tokens)
|
|
violations = []
|
|
|
|
# 2. Absolute per-call cap — enforced from the first record (cold-start safe).
|
|
if abs_max > 0:
|
|
over = [(s, t) for s, t in rows if t > abs_max]
|
|
for s, t in over:
|
|
violations.append(f"ABSOLUTE step={s} tokens={t} (> cap {abs_max})")
|
|
|
|
# 3. Cumulative budget over the whole run/session.
|
|
if cum_budget > 0 and total > cum_budget:
|
|
violations.append(f"CUMULATIVE total={total} (> budget {cum_budget})")
|
|
|
|
# 1. Relative median spike — needs enough history.
|
|
median = threshold = None
|
|
if len(rows) >= 3:
|
|
median = statistics.median(tokens)
|
|
threshold = median * mult
|
|
for s, t in rows:
|
|
if t > threshold:
|
|
violations.append(f"SPIKE step={s} tokens={t} (> {threshold:.0f} = median x{mult})")
|
|
|
|
med_str = f"{median}" if median is not None else "n/a(<3 records)"
|
|
print(f"records={len(rows)} total_tokens={total} median_tokens={med_str} "
|
|
f"abs_cap={abs_max or 'off'} cum_budget={cum_budget or 'off'}")
|
|
for v in violations:
|
|
print(v)
|
|
|
|
if violations:
|
|
sys.stderr.write(f"COST_VIOLATION_DETECTED count={len(violations)}\n")
|
|
raise SystemExit(2)
|
|
|
|
# No violations. If we could not run the relative test AND no absolute/cumulative
|
|
# cap was configured, we truly had nothing to check -> preserve the old rc=3.
|
|
if len(rows) < 3 and abs_max == 0 and cum_budget == 0:
|
|
sys.stderr.write(f"COST_SPIKE_NO_DATA records={len(rows)} (need >=3, no absolute/cumulative cap set)\n")
|
|
raise SystemExit(3)
|
|
|
|
print("COST_SPIKE_NONE")
|
|
PY
|