The claude-sdk-python agent :8000 wedges under D6/LLM load: two synchronous
anthropic.Anthropic().messages.create() calls run directly on the uvicorn
asyncio event loop, freezing it for the full LLM round-trip so /health stops
responding. The watchdog counts 3 consecutive failures (~90s) and kill-restarts
the container, dropping active sessions.
Root cause (sync-in-async), all in integrations/claude-sdk-python/:
- src/agents/agent.py: _execute_tool's generate_a2ui branch builds a sync
anthropic.Anthropic() and calls messages.create() synchronously; invoked on
the loop from run_agent's agentic loop AND from the Claude-Agent-SDK MCP tool
handler in claude_agent_sdk_adapter.py.
- src/agents/a2ui_dynamic.py: _generate_a2ui, same sync pattern, invoked on the
loop from the run_a2ui_dynamic_agent generator.
Fix: wrap every async call site in `await asyncio.to_thread(...)` (lowest blast
radius — the sync functions and the shared ExecuteTool callback type are
unchanged, and the whole tool-dispatch path is fixed uniformly, not just
generate_a2ui):
- agent.py run_agent call site
- claude_agent_sdk_adapter.py MCP tool handler
- a2ui_dynamic.py secondary call site
Blast radius: claude-sdk-python only. a2ui_dynamic.py is per-integration (each
framework has its own copy); every other claude-sdk-python agent already uses
AsyncAnthropic. The `tools` symlink to shared/python was not touched.
entrypoint.sh: drop the Slack alert from the :8000 agent watchdog branch (keep
the kill-restart — it self-heals silently now that the root cause is fixed);
keep the LOUD #oss-alerts page on the public $PORT /api/health branch.
Adds showcase/tests/repro/async-wedge/ — a faithful RED/GREEN harness driving
the real anthropic sync client against a controllable slow endpoint, plus a
mutation guard on the real _generate_a2ui.
Self-activate CVDIAG_LOG_STDOUT=0 when CVDIAG_PB_URL is wired (safe: only silences stdout when PB is receiving; explicit override preserved). Extend the watchdog to poll the public $PORT /api/health and, on sustained failure, POST a loud #oss-alerts Slack alert BEFORE kill-restart; add the same alert to the agent-\:8000 branch (no silent recovery). Add uvicorn --no-access-log to cut the access-log flood. Together these keep the shared log stream under the 500/sec cap so the pipe never backs up.
Replace sys.path.insert hacks in Python agent files with direct
imports via symlinks to shared/{python,typescript}/tools.
Update Dockerfiles, entrypoints, and configs to support the new
symlink-based tool resolution. Add PARITY_NOTES for frameworks
that have known gaps.
The showcase framework directories better reflect their role as
integration examples rather than distributable packages.
Renames showcase/packages/ -> showcase/integrations/ and updates
the test docker-compose file reference accordingly.
Jordan Ritter