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): kill the image worker a timed-out call abandons (#3940)
gglucass793bb85659d9
diff --git a/headroom/proxy/image_isolation.py b/headroom/proxy/image_isolation.pyindex 2e2addf54..fb291057e 100644--- a/headroom/proxy/image_isolation.py+++ b/headroom/proxy/image_isolation.py@@ -84,6 +84,14 @@ def _sleep_worker(return messages, None+def _hang_worker(+ messages: list[dict[str, Any]],+ provider: str,+) -> tuple[list[dict[str, Any]], dict[str, Any] | None]:+ time.sleep(60)+ return messages, None++def _abort_worker(messages: list[dict[str, Any]],provider: str,@@ -108,13 +116,28 @@ def _image_pool() -> ProcessPoolExecutor:return _IMAGE_POOL-def _reset_image_pool() -> None:+def _reset_image_pool(pool: ProcessPoolExecutor | None = None) -> None:+ """Drop ``pool`` (default: the current one) and kill its worker.++ ``shutdown(wait=False)`` alone never stops a worker that is still running+ an abandoned call: after a timeout it ran the image to the end, its result+ discarded, while the next request cold-loaded the models in a fresh worker+ beside it. Only the current pool is unpublished, so a call that fails+ after another request already rebuilt the pool leaves the rebuilt one alone.+ """global _IMAGE_POOLwith _IMAGE_POOL_LOCK:- pool = _IMAGE_POOL- _IMAGE_POOL = None- if pool is not None:- pool.shutdown(wait=False, cancel_futures=True)+ if pool is None:+ pool = _IMAGE_POOL+ if _IMAGE_POOL is pool:+ _IMAGE_POOL = None+ if pool is None:+ return+ # shutdown() sets _processes to None, so take the workers first.+ workers = list((pool._processes or {}).values())+ pool.shutdown(wait=False, cancel_futures=True)+ for worker in workers:+ worker.kill()async def run_image_compression_isolated(@@ -124,21 +147,23 @@ async def run_image_compression_isolated(timeout: float,) -> tuple[list[dict[str, Any]], dict[str, Any] | None]:loop = asyncio.get_running_loop()+ pool: ProcessPoolExecutor | None = Nonetry:- future = loop.run_in_executor(_image_pool(), _IMAGE_WORKER, messages, provider)+ pool = _image_pool()+ future = loop.run_in_executor(pool, _IMAGE_WORKER, messages, provider)return await asyncio.wait_for(future, timeout=timeout)except BrokenProcessPool:logger.warning("Image compression worker crashed; forwarding original image payload")- _reset_image_pool()+ _reset_image_pool(pool)return messages, Noneexcept TimeoutError:logger.warning("Image compression worker timed out; forwarding original image payload")- _reset_image_pool()+ _reset_image_pool(pool)return messages, Noneexcept Exception as exc:logger.warning("Image compression worker failed (%s); forwarding original image payload",type(exc).__name__,)- _reset_image_pool()+ _reset_image_pool(pool)return messages, Nonediff --git a/tests/test_image_compression_isolation.py b/tests/test_image_compression_isolation.pyindex 8509f13bc..a7fde07e4 100644--- a/tests/test_image_compression_isolation.py+++ b/tests/test_image_compression_isolation.py@@ -85,6 +85,39 @@ async def test_worker_timeout_fails_open(monkeypatch) -> None:assert recovered_result is not None+async def test_worker_timeout_kills_the_abandoned_worker(monkeypatch) -> None:+ # shutdown(wait=False) alone left the worker running the abandoned call to+ # the end while the next request cold-started a fresh worker beside it.+ messages = _messages()+ monkeypatch.setattr(image_isolation, "_IMAGE_WORKER", image_isolation._success_worker)+ await image_isolation.run_image_compression_isolated(messages, provider="openai", timeout=30.0)+ (worker,) = image_isolation._IMAGE_POOL._processes.values()++ monkeypatch.setattr(image_isolation, "_IMAGE_WORKER", image_isolation._hang_worker)+ returned, result = await image_isolation.run_image_compression_isolated(+ messages,+ provider="openai",+ timeout=0.5,+ )++ assert returned is messages+ assert result is None+ worker.join(timeout=5.0)+ assert not worker.is_alive()+++def test_late_failure_leaves_a_rebuilt_pool_alone() -> None:+ # A call that fails after another request already replaced its pool must+ # not drop (and kill the worker of) the replacement.+ old = image_isolation._image_pool()+ image_isolation._reset_image_pool(old)+ rebuilt = image_isolation._image_pool()++ image_isolation._reset_image_pool(old)++ assert image_isolation._IMAGE_POOL is rebuilt++async def test_worker_success_returns_compressed(monkeypatch) -> None:messages = _messages()monkeypatch.setattr(image_isolation, "_IMAGE_WORKER", image_isolation._success_worker)