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: normalize /p/<project> prefix on WebSocket upgrades so the Responses WS route is not rejected with 403 (#2379)
Matt Van Horn789a4f3060aa
diff --git a/headroom/proxy/handlers/openai.py b/headroom/proxy/handlers/openai.pyindex 1024238c3..d2a2e39f1 100644--- a/headroom/proxy/handlers/openai.py+++ b/headroom/proxy/handlers/openai.py@@ -75,7 +75,11 @@ from headroom.proxy.outcome import RequestOutcomefrom headroom.proxy.passthrough import (custom_base_passthrough_telemetry as _custom_base_passthrough_telemetry,)-from headroom.proxy.project_context import classify_project, set_current_project+from headroom.proxy.project_context import (+ classify_project,+ get_current_project,+ set_current_project,+)from headroom.proxy.token_counting import gemini_output_tokenslogger = logging.getLogger("headroom.proxy")@@ -5726,8 +5730,11 @@ class OpenAIHandlerMixin:# Captured in closure so per-turn RequestOutcome can stamp it.client = classify_client(ws_headers)# WS sessions bypass the HTTP middleware, so bind the project here;- # per-turn outcome emission inside this task inherits the context.- set_current_project(classify_project(ws_headers))+ # per-turn outcome emission inside this task inherits the context. An+ # explicit X-Headroom-Project header wins; otherwise fall back to the+ # /p/<name> path prefix already bound by WebSocketProjectPrefixMiddleware+ # so prefix-only clients (aider, Copilot BYOK, Cursor) stay attributed.+ set_current_project(classify_project(ws_headers) or get_current_project())metrics_for_inbound_ws = getattr(self, "metrics", None)if metrics_for_inbound_ws is not None and hasattr(metrics_for_inbound_ws, "record_inbound_request"diff --git a/headroom/proxy/server.py b/headroom/proxy/server.pyindex a9ac18caa..c03c76ee8 100644--- a/headroom/proxy/server.py+++ b/headroom/proxy/server.py@@ -2364,6 +2364,22 @@ _is_known_websocket_callback_failure = is_known_websocket_callback_failure_tool_schema_saved_from_tags = tool_schema_saved_from_tags+class WebSocketProjectPrefixMiddleware:+ """Normalize project-prefixed WebSocket paths before route matching."""++ def __init__(self, app: Any) -> None:+ self.app = app++ async def __call__(self, scope: Any, receive: Any, send: Any) -> None:+ if scope["type"] == "websocket":+ prefix_project = strip_project_path_prefix(scope)+ headers = {+ name.decode("latin-1"): value.decode("latin-1") for name, value in scope["headers"]+ }+ set_current_project(classify_project(headers) or prefix_project)+ await self.app(scope, receive, send)++def create_app(config: ProxyConfig | None = None) -> FastAPI:"""Create FastAPI application."""if not FASTAPI_AVAILABLE:@@ -2573,6 +2589,7 @@ def create_app(config: ProxyConfig | None = None) -> FastAPI:version=__version__,lifespan=lifespan,)+ app.add_middleware(WebSocketProjectPrefixMiddleware)loop_health_state: LoopHealthState = {"status": "healthy","known_failures": 0,diff --git a/tests/test_provider_proxy_routes.py b/tests/test_provider_proxy_routes.pyindex 7a6ebb599..fe7f9ddd0 100644--- a/tests/test_provider_proxy_routes.py+++ b/tests/test_provider_proxy_routes.py@@ -10,6 +10,7 @@ from fastapi.responses import JSONResponsefrom fastapi.testclient import TestClientfrom headroom.providers.codex.runtime import CodexRoutingDecision+from headroom.proxy.project_context import get_current_projectfrom headroom.proxy.server import HeadroomProxy, ProxyConfig, create_app@@ -481,6 +482,31 @@ def test_openai_response_websocket_aliases_delegate_to_openai_ws_handler(monkeyp]+def test_project_prefixed_openai_response_websocket_delegates_to_openai_ws_handler(+ monkeypatch,+) -> None:+ seen_paths: list[str] = []+ seen_projects: list[str | None] = []++ async def fake_ws(self, websocket): # type: ignore[no-untyped-def]+ seen_paths.append(websocket.url.path)+ seen_projects.append(get_current_project())+ await websocket.accept()+ await websocket.send_json({"path": websocket.url.path})+ await websocket.close()++ monkeypatch.setattr(HeadroomProxy, "handle_openai_responses_ws", fake_ws)++ with TestClient(_app()) as client:+ with client.websocket_connect("/p/test-project/v1/responses") as websocket:+ assert websocket.receive_json() == {"path": "/v1/responses"}++ assert seen_paths == ["/v1/responses"]+ # The /p/<name> prefix is bound as the project even without a header, so a+ # prefix-only Codex WS client is still attributed (not just routed).+ assert seen_projects == ["test-project"]++def test_openai_response_subpath_passthrough_returns_502_on_http_failure() -> None:class FailingAsyncClient:async def request(self, method, url, **kwargs): # type: ignore[no-untyped-def]