fix(vedastro): pin SDK at install and cap free-tier wait

Image build patches vedastro.check_for_update to a no-op after pip install so import cannot hit pypi or upgrade the pin. Free-tier queue waits are capped to VEDASTRO_TIMEOUT_SECONDS and fail fast as free_tier_rate_limited. Gateway status exposes runtime mode as booleans without secrets. BUG-719 resolved; BUG-720 stays investigating until production env is filled in.

scripts/vedastro_gateway.py

@@ -29,6 +29,14 @@ def _official_network_enabled() -> bool:
     return os.environ.get("VEDASTRO_ENABLE_NETWORK", "1").strip().lower() in {"1", "true", "yes", "on"}
 
 
+def _sdk_version() -> str | None:
+    try:
+        import importlib.metadata
+        return importlib.metadata.version("vedastro")
+    except Exception:
+        return None
+
+
 def _int_env(name: str, default: int = 0) -> int:
     raw = os.environ.get(name, "").strip()
     if not raw:
@@ -271,7 +279,16 @@ def gateway_status() -> dict[str, Any]:
         "self_host_configured": config["self_host_endpoint_configured"],
         "official_configured": config["official_endpoint_configured"],
         "credential_configured": bool(os.environ.get("VEDASTRO_API_KEY", "").strip()),
+        "endpoint_configured": bool(config["official_endpoint_configured"] or config["self_host_endpoint_configured"]),
+        "fanout_enabled": os.environ.get("VEDASTRO_FULL_SNAPSHOT_FANOUT_ENABLED", "1").strip().lower() in {"1", "true", "yes", "on"},
+        "range_scan_network_enabled": os.environ.get("VEDASTRO_RANGE_SCAN_NETWORK_ENABLED", "").strip().lower() in {"1", "true", "yes", "on"},
+        "free_tier_queue_active": bool(
+            config["official_endpoint_configured"]
+            and not os.environ.get("VEDASTRO_API_KEY", "").strip()
+        ),
+        "sdk_version": _sdk_version(),
         "cache_ttl_seconds": config["cache_ttl_seconds"],
+        "official_full_snapshot_cache_ttl_seconds": _int_env("VEDASTRO_OFFICIAL_FULL_SNAPSHOT_CACHE_TTL_SECONDS", 0),
         "queue_enabled": config["queue_enabled"],
         "fail_open_local": config["fail_open_local"],
         "official_readiness": {

scripts/vedastro_service_adapter.py

@@ -350,6 +350,7 @@ ALLOW_NETWORK_ENV = "VEDASTRO_ENABLE_NETWORK"
 CACHE_TTL_ENV = "VEDASTRO_CACHE_TTL_SECONDS"
 FREE_TIER_MAX_REQUESTS_ENV = "VEDASTRO_FREE_TIER_MAX_REQUESTS"
 FREE_TIER_WINDOW_SECONDS_ENV = "VEDASTRO_FREE_TIER_WINDOW_SECONDS"
+FREE_TIER_WAIT_BUDGET_ENV = "VEDASTRO_FREE_TIER_WAIT_BUDGET_SECONDS"
 DEFAULT_CACHE_TTL_SECONDS = 86400.0
 DEFAULT_FREE_TIER_MAX_REQUESTS = 5
 DEFAULT_FREE_TIER_WINDOW_SECONDS = 60.0
@@ -505,6 +506,17 @@ def _free_tier_window_seconds() -> float:
         return DEFAULT_FREE_TIER_WINDOW_SECONDS
 
 
+def _free_tier_wait_budget_seconds() -> float:
+    timeout = _timeout_seconds()
+    raw = os.environ.get(FREE_TIER_WAIT_BUDGET_ENV, "").strip()
+    if not raw:
+        return timeout
+    try:
+        return max(0.0, min(float(raw), timeout))
+    except ValueError:
+        return timeout
+
+
 def schema() -> dict[str, Any]:
     request_example = {
         **PARITY_CASES["beijing_first_use_demo"],
@@ -1903,6 +1915,7 @@ def _acquire_free_tier_slot(request_url: str) -> dict[str, Any]:
         }
 
     waited_seconds = 0.0
+    budget = _free_tier_wait_budget_seconds()
     with _FREE_TIER_REQUEST_LOCK:
         while True:
             now = time.monotonic()
@@ -1913,6 +1926,16 @@ def _acquire_free_tier_slot(request_url: str) -> dict[str, Any]:
                 _FREE_TIER_REQUEST_TIMESTAMPS.append(now)
                 break
             sleep_seconds = max(window_seconds - (now - _FREE_TIER_REQUEST_TIMESTAMPS[0]), 0.0)
+            if waited_seconds + sleep_seconds > budget:
+                return {
+                    "mode": "free_tier_budget_exceeded",
+                    "queue_active": False,
+                    "waited_seconds": round(waited_seconds, 6),
+                    "window_seconds": window_seconds,
+                    "max_requests": max_requests,
+                    "wait_budget_seconds": budget,
+                    "degraded_reason": "free_tier_rate_limited",
+                }
             waited_seconds += sleep_seconds
             if sleep_seconds > 0:
                 time.sleep(sleep_seconds)
@@ -1963,6 +1986,15 @@ def _post_json_with_retry(endpoint: str, request_preview: dict[str, Any]) -> tup
     for attempt in range(1, max_attempts + 1):
         try:
             rate_limit_metadata = _acquire_free_tier_slot(request_url)
+            if rate_limit_metadata.get("mode") == "free_tier_budget_exceeded":
+                return {
+                    "Status": "Fail",
+                    "Payload": {"reason": "free_tier_rate_limited"},
+                    "source_metadata": {
+                        "free_tier_rate_limit": rate_limit_metadata,
+                        "degraded_reason": "free_tier_rate_limited",
+                    },
+                }, attempt, retry_error_codes
             payload = _post_json(endpoint, request_preview)
             if not isinstance(payload, dict):
                 return {}, attempt, retry_error_codes
@@ -2176,9 +2208,12 @@ def _official_snapshot_budget_exhausted_bundle(reason: str) -> dict[str, Any]:
 def _payload_status(payload: dict[str, Any]) -> str:
     if not isinstance(payload, dict):
         return "invalid"
+    metadata = payload.get("source_metadata") if isinstance(payload.get("source_metadata"), dict) else {}
+    if metadata.get("degraded_reason") == "free_tier_rate_limited":
+        return "rate_limited"
     if str(payload.get("Status") or "").lower() == "fail":
         failure_text = json.dumps(payload.get("Payload"), ensure_ascii=False).lower()
-        if "rate limit" in failure_text or "calls/minute" in failure_text or "too many requests" in failure_text:
+        if "rate limit" in failure_text or "calls/minute" in failure_text or "too many requests" in failure_text or "free_tier_rate_limited" in failure_text:
             return "rate_limited"
     return "ok" if payload.get("Status") == "Pass" else "fail"