fix(error_classifier): classify generic-typed timeout messages as transient (carve-out of #22664)

RuntimeError('claude CLI turn timed out') from a local OpenAI-compatible
shim was falling through to FailoverReason.unknown, surfacing as 'Empty
response from model' and burning 3 retry slots on the same failing
endpoint. _classify_by_message had no timeout-message branch — only
billing/rate_limit/auth/context_overflow/model_not_found patterns. The
type-based check at line 565 also requires isinstance(error, (TimeoutError,
ConnectionError, OSError)) — a plain RuntimeError doesn't match.

Add _TIMEOUT_MESSAGE_PATTERNS for 'timed out', 'deadline exceeded',
'request timed out', 'operation timed out', 'upstream timed out', 'turn
timed out'. _classify_by_message returns FailoverReason.timeout (retryable=True)
when any pattern matches.

Salvage of #22664's classifier portion. The original PR also bundled a
fallback self-selection guard which is now redundant (already on main
via #22780) plus DeepSeek thinking and session_search fixes that are
their own separate concerns.

Follow-up to #22780 — fixes the still-broken classification of
generic-typed provider-shim timeouts that #22780's dedup didn't cover.

agent/error_classifier.py

@@ -254,6 +254,20 @@ _THINKING_SIG_PATTERNS = [
     "signature",  # Combined with "thinking" check
 ]
 
+# Message-string patterns that indicate a provider-side timeout even when
+# the exception type is generic (e.g. RuntimeError from a local shim that
+# wraps a subprocess timeout).  Checked before the type-based transport
+# heuristics so custom-provider "timed out" errors don't fall through to
+# the unknown bucket and get misreported as empty responses.
+_TIMEOUT_MESSAGE_PATTERNS = [
+    "timed out",
+    "turn timed out",
+    "request timed out",
+    "deadline exceeded",
+    "operation timed out",
+    "upstream timed out",
+]
+
 # Transport error type names
 _TRANSPORT_ERROR_TYPES = frozenset({
     "ReadTimeout", "ConnectTimeout", "PoolTimeout",
@@ -963,6 +977,14 @@ def _classify_by_message(
             should_fallback=True,
         )
 
+    # Timeout message patterns — generic exception types (e.g. RuntimeError)
+    # raised by local shims or custom providers that internally wrap a
+    # subprocess/HTTP timeout.  Classified as transport timeout so the retry
+    # loop rebuilds the client instead of treating the turn as an empty
+    # model response.
+    if any(p in error_msg for p in _TIMEOUT_MESSAGE_PATTERNS):
+        return result_fn(FailoverReason.timeout, retryable=True)
+
     return None
 
 

tests/agent/test_error_classifier.py

@@ -587,6 +587,28 @@ class TestClassifyApiError:
         result = classify_api_error(e)
         assert result.reason == FailoverReason.timeout
 
+    def test_runtime_error_cli_turn_timed_out_classifies_as_timeout(self):
+        # RuntimeError from a local claude-cli shim that wraps a subprocess
+        # timeout must classify as FailoverReason.timeout, not unknown, so
+        # the retry loop rebuilds the client instead of treating the turn as
+        # an empty model response (#22548).
+        e = RuntimeError("claude CLI turn timed out")
+        result = classify_api_error(e)
+        assert result.reason == FailoverReason.timeout
+        assert result.retryable is True
+
+    def test_runtime_error_request_timed_out_classifies_as_timeout(self):
+        e = RuntimeError("request timed out after 120s")
+        result = classify_api_error(e)
+        assert result.reason == FailoverReason.timeout
+        assert result.retryable is True
+
+    def test_runtime_error_deadline_exceeded_classifies_as_timeout(self):
+        e = RuntimeError("deadline exceeded")
+        result = classify_api_error(e)
+        assert result.reason == FailoverReason.timeout
+        assert result.retryable is True
+
     # ── Error code classification ──
 
     def test_error_code_resource_exhausted(self):