Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Python agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript
fix(proxy): reset memory backend to None on init timeout
Adryan Eka Vandra3f1f82d7e27d
diff --git a/headroom/proxy/memory_handler.py b/headroom/proxy/memory_handler.pyindex f42e038d5..75770d3f9 100644--- a/headroom/proxy/memory_handler.py+++ b/headroom/proxy/memory_handler.py@@ -185,6 +185,12 @@ class MemoryHandler:await asyncio.wait_for(_do_init(), timeout=STARTUP_INIT_TIMEOUT_SECONDS)except asyncio.TimeoutError:# Fail-open: leave _initialized=False so subsequent calls retry.+ # CRITICAL: also null the backend — _init_backend_locked may have+ # already assigned ``self._backend`` before its own await raised /+ # was cancelled by wait_for. Callers that do+ # ``if self.memory_handler._backend:`` must not see a+ # truthy-but-broken backend.+ self._backend = Nonelogger.error("Memory: backend initialization timed out after "f"{STARTUP_INIT_TIMEOUT_SECONDS}s "diff --git a/tests/test_memory_handler_concurrent_init.py b/tests/test_memory_handler_concurrent_init.pyindex 3c22124de..6a7424b4d 100644--- a/tests/test_memory_handler_concurrent_init.py+++ b/tests/test_memory_handler_concurrent_init.py@@ -149,6 +149,47 @@ async def test_ensure_initialized_timeout_leaves_handler_unready(assert STARTUP_INIT_TIMEOUT_SECONDS == 30.0+async def test_ensure_initialized_timeout_nulls_partially_initialized_backend(+ tmp_path, monkeypatch+):+ """If wait_for fires while _init_backend_locked has already set+ ``self._backend`` but before ``self._initialized = True``, the timeout+ handler must null ``_backend``. Otherwise callers doing+ ``if self.memory_handler._backend:`` see a truthy-but-broken backend.+ """++ class SlowBackend:+ def __init__(self, config):+ self.config = config++ async def _ensure_initialized(self) -> None:+ # Hang long enough to blow the 0.01s timeout below.+ await asyncio.sleep(5.0)++ async def close(self) -> None:+ pass++ import headroom.memory.backends.local as local_mod++ monkeypatch.setattr(local_mod, "LocalBackend", SlowBackend)++ handler = MemoryHandler(+ MemoryConfig(+ enabled=True, backend="local", db_path=str(tmp_path / "mem.db")+ )+ )++ with patch(+ "headroom.proxy.memory_handler.STARTUP_INIT_TIMEOUT_SECONDS", 0.01+ ):+ await handler._ensure_initialized()++ # Both must be consistent after timeout.+ assert handler._initialized is False+ assert handler._backend is None++# -------------------------------------------------------------------# Real backend init (no monkeypatching) — integration smoke test# -------------------------------------------------------------------