fix(agent): always prefer streaming for API calls to prevent hung subagents (#3120)

The non-streaming API call path (_interruptible_api_call) had no
wall-clock timeout. When providers keep connections alive with SSE
keep-alive pings but never deliver a response, httpx's inactivity
timeout never fires and the call hangs indefinitely.

Subagents always used the non-streaming path because they have no
stream consumers (quiet_mode=True). This caused delegate_task to
hang for 40+ minutes in production.

The streaming path has two layers of protection:
- httpx read timeout (60s, HERMES_STREAM_READ_TIMEOUT)
- Stale stream detection (90s, HERMES_STREAM_STALE_TIMEOUT)

Both work because streaming sends chunks continuously — a 90-second
gap between chunks genuinely means the connection is broken, even for
reasoning models that take minutes to complete.

Now run_conversation() always prefers the streaming path. The streaming
method falls back to non-streaming automatically if the provider
doesn't support it. Stream delta callbacks are no-ops when no
consumers are registered, so there's no overhead for subagents.

tests/test_anthropic_error_handling.py

@@ -273,6 +273,9 @@ def test_401_credential_refresh_recovers(monkeypatch):
                 return _anthropic_response("Auth refreshed")
 
             self._interruptible_api_call = _fake_api_call
+            # Also patch streaming path — run_conversation now prefers
+            # streaming for health checking even without stream consumers.
+            self._interruptible_streaming_api_call = lambda api_kwargs, **kw: _fake_api_call(api_kwargs)
             return super().run_conversation(
                 user_message, conversation_history=conversation_history, task_id=task_id
             )