feat(h5-h6-hardening): Plan-07 Track A — A4 telemetry integrity, A5 cost controls

A4 (V9): telemetry-integrity.sh binds provider-usage.jsonl + cost/metrics.jsonl
  to a signed manifest head. Tampering a token flips the head (MISMATCH); an
  attacker who rewrites the head cannot re-sign it (SIGNATURE_INVALID) without
  the off-repo key. sign-audit-head.sh now also signs telemetry (best-effort).
  Supports CASAN_AUDIT_PRIV/PUB overrides for self-contained verification.
A5 (V12/V13/V14): cost-spike-detect.sh adds an absolute per-call cap
  (CASAN_COST_ABSOLUTE_MAX_TOKENS, enforced from record #1 → catches slow-boil
  and cold-start) and a cumulative budget (CASAN_COST_CUMULATIVE_BUDGET_TOKENS →
  catches under-threshold spray), keeping the existing median×mult spike test.
  Backward compatible: <3 records with no caps still exits 3.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

AINative_OKR_CASAN5/.specify/scripts/bash/cost-spike-detect.sh

@@ -1,15 +1,22 @@
 #!/usr/bin/env bash
 set -uo pipefail
 
-# CASAN H6 cost-spike detector (WP-C).
+# 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, computes
-# the median total_tokens across steps, and flags any step exceeding
-# MULTIPLIER x median. Exits non-zero if a spike is found (so a pipeline/CI gate
-# goes red).
+# 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]
-# Exit: 0 no spike, 2 spike detected, 64 usage, 3 not enough data.
+# 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 "${BASH_SOURCE[0]}")" && pwd)"
 PROJECT_ROOT="$(cd "$SCRIPT_DIR/../../.." && pwd)"
@@ -18,9 +25,14 @@ MULT="${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, sys, statistics
+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()
@@ -32,18 +44,45 @@ for line in open(path, encoding="utf-8"):
         continue
     if "total_tokens" in r:
         rows.append((r.get("step", "?"), int(r["total_tokens"])))
-if len(rows) < 3:
-    sys.stderr.write(f"COST_SPIKE_NO_DATA records={len(rows)} (need >=3)\n")
-    raise SystemExit(3)
+
 tokens = [t for _, t in rows]
-median = statistics.median(tokens)
-threshold = median * mult
-spikes = [(s, t) for s, t in rows if t > threshold]
-print(f"records={len(rows)} median_tokens={median} threshold={threshold:.0f} (x{mult})")
-for s, t in spikes:
-    print(f"SPIKE step={s} tokens={t} (> {threshold:.0f})")
-if spikes:
-    sys.stderr.write(f"COST_SPIKE_DETECTED count={len(spikes)}\n")
+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