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
test(proxy): cover codex responses subpath aliases
JerrettDaviseb302fa35e52
diff --git a/headroom/proxy/server.py b/headroom/proxy/server.pyindex 40d70eb20..94a045870 100644--- a/headroom/proxy/server.py+++ b/headroom/proxy/server.py@@ -1818,10 +1818,13 @@ def create_app(config: ProxyConfig | None = None) -> FastAPI:"""Passthrough for /backend-api/responses/* sub-endpoints."""return await openai_responses_sub(request, sub_path)- @app.api_route("/backend-api/codex/responses/{sub_path:path}", methods=["GET", "POST", "DELETE"])+ @app.api_route(+ "/backend-api/codex/responses/{sub_path:path}", methods=["GET", "POST", "DELETE"]+ )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 67aacee3a..797361f61 100644--- a/tests/test_proxy_codex_route_aliases.py+++ b/tests/test_proxy_codex_route_aliases.py@@ -1,3 +1,4 @@+import httpxfrom fastapi import WebSocketfrom fastapi.responses import JSONResponsefrom fastapi.testclient import TestClient@@ -35,3 +36,38 @@ def test_codex_responses_websocket_aliases_delegate_to_openai_handler(monkeypatcassert websocket.receive_json() == {"ok": True, "path": path}assert seen_paths == ["/backend-api/responses", "/backend-api/codex/responses"]+++def test_codex_responses_subpath_aliases_delegate_to_passthrough():+ class FakeAsyncClient:+ def __init__(self) -> None:+ self.calls: list[tuple[str, str]] = []++ async def request(self, method, url, **_kwargs): # type: ignore[no-untyped-def]+ self.calls.append((method, url))+ return httpx.Response(200, json={"method": method, "url": url})++ async def aclose(self) -> None:+ return None++ with TestClient(create_app(ProxyConfig())) as client:+ fake_http_client = FakeAsyncClient()+ client.app.state.proxy.http_client = fake_http_client+ client.app.state.proxy.OPENAI_API_URL = "https://api.openai.test"++ api_key_response = client.post(+ "/backend-api/responses/compact?trace=1",+ json={"model": "gpt-5.3-codex"},+ )+ chatgpt_response = client.post(+ "/backend-api/codex/responses/compact?trace=2",+ headers={"chatgpt-account-id": "acct_123"},+ json={"model": "gpt-5.3-codex"},+ )++ assert api_key_response.status_code == 200+ assert chatgpt_response.status_code == 200+ assert fake_http_client.calls == [+ ("POST", "https://api.openai.test/v1/responses/compact?trace=1"),+ ("POST", "https://chatgpt.com/backend-api/codex/responses/compact?trace=2"),+ ]