feat(queue): resilience schema + backoff helper + config (ORCH-1)

jobs.transient_attempts + available_at columns (idempotent _ensure_column
migration); claim_next_job honours available_at; mark_job_transient (backoff
requeue with separate transient budget). Config: preflight_cache_ttl,
backoff_base/max_seconds, transient_max_attempts, breaker_threshold,
breaker_pause_seconds.

src/config.py

@@ -36,6 +36,23 @@ class Settings(BaseSettings):
     max_concurrency: int = 1
     queue_poll_interval: float = 2.0
 
+    # ORCH-1b (resilience): preflight + 429/rate-limit + backoff + circuit breaker.
+    # preflight_cache_ttl  -> cache the cheap CLI/network preflight result (seconds);
+    #                         the worker does NOT re-run `claude --version` more often
+    #                         than this (env ORCH_PREFLIGHT_CACHE_TTL).
+    # backoff_base_seconds -> base for exponential transient backoff.
+    # backoff_max_seconds  -> ceiling for the transient backoff.
+    # transient_max_attempts -> retry budget for transient (429/overload/network)
+    #                         failures, separate from code-fault `attempts`.
+    # breaker_threshold    -> consecutive transient failures that OPEN the breaker.
+    # breaker_pause_seconds -> how long the breaker stays open before half-open.
+    preflight_cache_ttl: int = 45
+    backoff_base_seconds: int = 10
+    backoff_max_seconds: int = 600
+    transient_max_attempts: int = 5
+    breaker_threshold: int = 3
+    breaker_pause_seconds: int = 300
+
 
     # Telegram notifications
     telegram_bot_token: str = ""