Merge pull request 'fix(a2a): add cache-first check to enrich_peer_metadata_nonblocking' (#518) from sre/fix-enrich-nonblocking-cache-check into main

workspace/a2a_client.py

@@ -187,11 +187,27 @@ def enrich_peer_metadata_nonblocking(
     canon = _validate_peer_id(peer_id)
     if canon is None:
         return None
-    # Schedule background fetch unless one is already in flight for this
-    # peer. The synchronous version atomically reads-then-writes; the
-    # async version splits that into "schedule fetch" + "fetch fills
-    # cache later." The in-flight set keeps a flurry of pushes from
-    # one peer (e.g., a chatty agent) from spawning N parallel GETs.
+
+    # Cache-first: return immediately on warm hit (same TTL logic as the
+    # sync path). This is the hot-path optimisation — every push from a
+    # warm peer must return the record without touching the in-flight set
+    # or the executor. A background fetch that races to fill the cache
+    # will find the entry already present when it calls
+    # enrich_peer_metadata (which does its own fresh-TTL check), so it
+    # exits as a no-op with no extra network traffic.
+    current = time.monotonic()
+    cached = _peer_metadata_get(canon)
+    if cached is not None:
+        fetched_at, record = cached
+        if current - fetched_at < _PEER_METADATA_TTL_SECONDS:
+            return record
+
+    # Cache miss or TTL expired: schedule background fetch unless one is
+    # already in flight for this peer. The synchronous version atomically
+    # reads-then-writes; the async version splits that into "schedule
+    # fetch" + "fetch fills cache later." The in-flight set keeps a
+    # flurry of pushes from one peer (e.g., a chatty agent) from
+    # spawning N parallel GETs.
     with _enrich_in_flight_lock:
         if canon in _enrich_in_flight:
             return None