▚ MODEL AUDIT // 6-bit MLX

// Qwen3 Coder 30B

CRIT — Critical Bugs 62/100 tests: CRASH

tok/sec72.70

tokens—

TTFT—

▮ PILLAR BREAKDOWN

Schema / I/O

15/20

Transport

11/20

Error Handling

12/20

State Safety

14/20

Test Integrity

10/20

✓ WENT RIGHT

No pillar reached 16+ — no standout strengths.

✗ WENT WRONG

Error Handling (12/20)
Transport (11/20)
Test Integrity (10/20)

▮ CRITICAL BUGS

Idempotency store never evicts stale entries: is_idempotent inserts on every first sighting and only checks expiry on re-lookup — there is no sweep/background task to delete keys older than 300s, so the dict grows without bound for the lifetime of the process.
429 handler has no retry cap: forward_to_discord's `while True` loop sleeps retry_after and loops with no attempt counter, so a Discord endpoint stuck returning 429 blocks the request thread indefinitely; since HTTPServer is single-threaded this deadlocks the whole server and the client never gets a response.
Server binds a fixed port with no SO_REUSEADDR and is never closed: HTTPServer(('localhost', 8080), ...) plus serve_forever() with no server_close()/allow_reuse_address — on restart the socket sits in TIME_WAIT and the next run hits EADDRINUSE (the exact failure observed).
Token-bucket: under sustained burst the `while not rate_limit(): await asyncio.sleep(0.1)` busy-spins; last_refill is only updated when elapsed > RATE_LIMIT_WINDOW so sub-window requests leak refill credit inconsistently.
HMAC and idempotency state are module globals mutated without a lock from the single request thread — works only because HTTPServer is serial.

▮ RECOMMENDED USE

A starting skeleton for a stdlib webhook bridge where someone will finish the eviction sweep, cap the retry loop, and add SO_REUSEADDR before it ships.

▮ REFACTORED PATCH

# 1) Evict stale idempotency entries (bounded store + monotonic clock)
import time
IDEMPOTENCY_TTL = 300
def is_idempotent(event_id):
    now = time.monotonic()
    stale = [k for k, ts in list(idempotency_store.items()) if now - ts > IDEMPOTENCY_TTL]
    for k in stale[:64]: del idempotency_store[k]
    if event_id in idempotency_store and now - idempotency_store[event_id] < IDEMPOTENCY_TTL:
        idempotency_store[event_id] = now; return True
    idempotency_store[event_id] = now; return False

# 2) Cap 429 retries so a stuck Discord never hangs the server
MAX_429_RETRIES = 1
async def forward_to_discord(self, data):
    while not rate_limit(): await asyncio.sleep(0.05)
    payload = {"content": f"Event {data.get('type')}: {data.get('data', {}).get('message', '')}"}
    attempts = 0
    while True:
        try: await discord_send(payload); return
        except Exception as e:
            if 'HTTP 429' in str(e) and attempts < MAX_429_RETRIES:
                m = re.search(r'Retry-After (\d+)', str(e))
                await asyncio.sleep(int(m.group(1)) if m else 1); attempts += 1; continue
            raise  # let caller return a clear 502, do not swallow

# 3) SO_REUSEADDR + clean shutdown (fixes EADDRINUSE)
class ReusableHTTPServer(HTTPServer): allow_reuse_address = True
if __name__ == '__main__':
    unittest.main(argv=[''], exit=False, verbosity=2)
    server = ReusableHTTPServer(('localhost', 8080), WebhookHandler)
    try: server.serve_forever()
    finally: server.server_close()