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): alias nested codex responses routes
JerrettDavis2ceceb402459
diff --git a/headroom/proxy/server.py b/headroom/proxy/server.pyindex 5574334a1..40d70eb20 100644--- a/headroom/proxy/server.py+++ b/headroom/proxy/server.py@@ -1822,7 +1822,6 @@ def create_app(config: ProxyConfig | None = None) -> FastAPI:async def openai_codex_nested_responses_sub(request: Request, sub_path: str):"""Passthrough for /backend-api/codex/responses/* sub-endpoints."""return await openai_responses_sub(request, sub_path)-# OpenAI Batch API endpoints (with compression!)@app.post("/v1/batches")async def create_batch(request: Request):diff --git a/tests/test_proxy_codex_route_aliases.py b/tests/test_proxy_codex_route_aliases.pyindex cda428fc6..67aacee3a 100644--- a/tests/test_proxy_codex_route_aliases.py+++ b/tests/test_proxy_codex_route_aliases.py@@ -1,17 +1,37 @@+from fastapi import WebSocketfrom fastapi.responses import JSONResponsefrom fastapi.testclient import TestClientfrom headroom.proxy.server import HeadroomProxy, ProxyConfig, create_app-def test_backend_api_responses_alias_delegates_to_openai_handler(monkeypatch):+def test_codex_responses_aliases_delegate_to_openai_handler(monkeypatch):async def fake_handle(self, request): # type: ignore[no-untyped-def]return JSONResponse({"ok": True, "path": request.url.path})monkeypatch.setattr(HeadroomProxy, "handle_openai_responses", fake_handle)with TestClient(create_app(ProxyConfig())) as client:- response = client.post("/backend-api/responses", json={"model": "gpt-5.3-codex"})+ for path in ("/backend-api/responses", "/backend-api/codex/responses"):+ response = client.post(path, json={"model": "gpt-5.3-codex"})+ assert response.status_code == 200+ assert response.json() == {"ok": True, "path": path}- assert response.status_code == 200- assert response.json() == {"ok": True, "path": "/backend-api/responses"}++def test_codex_responses_websocket_aliases_delegate_to_openai_handler(monkeypatch):+ seen_paths: list[str] = []++ async def fake_handle_ws(self, websocket: WebSocket): # type: ignore[no-untyped-def]+ seen_paths.append(websocket.url.path)+ await websocket.accept()+ await websocket.send_json({"ok": True, "path": websocket.url.path})+ await websocket.close()++ monkeypatch.setattr(HeadroomProxy, "handle_openai_responses_ws", fake_handle_ws)++ with TestClient(create_app(ProxyConfig())) as client:+ for path in ("/backend-api/responses", "/backend-api/codex/responses"):+ with client.websocket_connect(path) as websocket:+ assert websocket.receive_json() == {"ok": True, "path": path}++ assert seen_paths == ["/backend-api/responses", "/backend-api/codex/responses"]