Follow up on #375 review: dedupe live-data route and harden serializers.

Align full /api/live-data with slow-tier orjson options, remove dead main.py duplicate, cap slow batches to pool size, cancel queued work on timeout, and stop retrying HTTP 4xx/5xx.

Co-authored-by: Cursor <cursoragent@cursor.com>

backend/services/fetchers/_store.py

@@ -230,12 +230,14 @@ _active_layers_version: int = 0
 def bump_active_layers_version() -> None:
     """Increment the active-layer version when frontend toggles change response shape."""
     global _active_layers_version
-    _active_layers_version += 1
+    with _data_lock:
+        _active_layers_version += 1
 
 
 def get_active_layers_version() -> int:
     """Return the current active-layer version (for ETag generation)."""
-    return _active_layers_version
+    with _data_lock:
+        return _active_layers_version
 
 
 def get_latest_data_subset(*keys: str) -> DashboardData:

backend/services/fetchers/retry.py

@@ -11,15 +11,20 @@ import random
 import logging
 import functools
 import requests
+from requests.exceptions import ChunkedEncodingError, ConnectionError as RequestsConnectionError
+from requests.exceptions import Timeout as RequestsTimeout
 
 logger = logging.getLogger(__name__)
 
-# Only retry on transient network/OS errors — not on parse errors, key errors, etc.
+# Only retry on transient network/OS errors — not parse/key errors or HTTP 4xx/5xx.
+# requests.HTTPError (from raise_for_status) is intentionally excluded.
 TRANSIENT_ERRORS = (
     TimeoutError,
     ConnectionError,
     OSError,
-    requests.RequestException,
+    RequestsConnectionError,
+    RequestsTimeout,
+    ChunkedEncodingError,
 )
 
 
@@ -43,6 +48,8 @@ def with_retry(max_retries: int = 3, base_delay: float = 2.0, max_delay: float =
             for attempt in range(1 + max_retries):
                 try:
                     return func(*args, **kwargs)
+                except requests.HTTPError:
+                    raise
                 except TRANSIENT_ERRORS as exc:
                     last_exc = exc
                     if attempt < max_retries: