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): Strip Codex responses-lite marker from response.create frame body (#1820)
iotron5cece7bf587c
diff --git a/headroom/proxy/handlers/openai.py b/headroom/proxy/handlers/openai.pyindex 2eb4d0d65..effb7b982 100644--- a/headroom/proxy/handlers/openai.py+++ b/headroom/proxy/handlers/openai.py@@ -95,6 +95,33 @@ def _codex_ws_compression_timeout_seconds() -> float:_WS_ALLOWED_ORIGINS_ENV = "HEADROOM_WS_ORIGINS"_CORS_ALLOWED_ORIGINS_ENV = "HEADROOM_CORS_ORIGINS"_CODEX_RESPONSES_LITE_HEADER = "x-openai-internal-codex-responses-lite"+# Codex mirrors the responses-lite request header into the response.create+# frame body under client_metadata; upstream rejects gpt-5.x when it is+# truthy. Stripping the WS handshake header alone is insufficient+# (headroomlabs-ai/headroom#1523) — the frame-body mirror must be removed too.+_CODEX_LITE_METADATA_KEY = "ws_request_header_x_openai_internal_codex_responses_lite"+++def _strip_codex_lite_metadata(raw_msg: str) -> str:+ """Remove the Codex responses-lite marker mirrored into a response.create+ frame's client_metadata. Fail-safe: returns raw_msg unchanged on any+ parse issue or when the marker is absent."""+ try:+ frame = json.loads(raw_msg)+ except (json.JSONDecodeError, TypeError, ValueError):+ return raw_msg+ if not isinstance(frame, dict):+ return raw_msg+ changed = False+ for container in (frame, frame.get("response")):+ if isinstance(container, dict):+ cm = container.get("client_metadata")+ if isinstance(cm, dict) and _CODEX_LITE_METADATA_KEY in cm:+ del cm[_CODEX_LITE_METADATA_KEY]+ changed = True+ return json.dumps(frame) if changed else raw_msg++_OPENAI_CHAT_COMPLETIONS_PATH = "/chat/completions"_OPENAI_RESPONSES_PATH = "/responses"_OPENAI_ORIGINAL_PATH_HEADER = "x-headroom-original-path"@@ -5838,7 +5865,7 @@ class OpenAIHandlerMixin:if ws_connected:async with upstream:- await upstream.send(first_msg_raw)+ await upstream.send(_strip_codex_lite_metadata(first_msg_raw))# Unit 3: flag the upstream side flips on seeing# ``response.completed`` so the outer cause@@ -6211,7 +6238,7 @@ class OpenAIHandlerMixin:"transforms_applied": transforms_applied,},)- await upstream.send(msg)+ await upstream.send(_strip_codex_lite_metadata(msg))except asyncio.CancelledError:# Explicit cancel from the outer# orchestrator — re-raise sodiff --git a/tests/test_openai_codex_ws_lifecycle.py b/tests/test_openai_codex_ws_lifecycle.pyindex a7ac5d915..5b1a5bc0a 100644--- a/tests/test_openai_codex_ws_lifecycle.py+++ b/tests/test_openai_codex_ws_lifecycle.py@@ -1080,6 +1080,49 @@ async def test_ws_without_codex_lite_preserves_adjacent_headers_and_api_key_routassert "ChatGPT-Account-ID" not in forwarded_headers+async def test_ws_first_frame_strips_codex_lite_metadata_mirror():+ """Codex mirrors the lite header into response.create's client_metadata+ (regression for #1523): stripping the handshake header alone is not+ enough, upstream rejects gpt-5.x when the frame-body mirror survives.+ """+ upstream_events = [+ json.dumps({"type": "response.created", "response": {"id": "r_1"}}),+ json.dumps({"type": "response.completed", "response": {"id": "r_1"}}),+ ]+ upstream = _FakeUpstream(upstream_events)+ fake_ws_mod = _make_fake_websockets_module(upstream)++ first_frame = json.dumps(+ {+ "type": "response.create",+ "response": {+ "model": "gpt-5.5",+ "input": "hi",+ "client_metadata": {+ "thread_id": "t_1",+ "ws_request_header_x_openai_internal_codex_responses_lite": True,+ },+ },+ }+ )+ client_ws = _FakeWebSocket(+ frames=[first_frame],+ headers=_codex_lite_headers(chatgpt=True),+ )+ handler = _DummyOpenAIHandler()++ with patch.dict(sys.modules, {"websockets": fake_ws_mod}):+ await handler.handle_openai_responses_ws(client_ws)++ assert len(upstream.sent) == 1+ sent_body = json.loads(upstream.sent[0])+ client_metadata = sent_body["response"]["client_metadata"]+ assert "ws_request_header_x_openai_internal_codex_responses_lite" not in client_metadata+ # Sibling metadata must survive the strip.+ assert client_metadata["thread_id"] == "t_1"++@pytest.mark.asyncioasync def test_ws_connect_happens_before_accept():"""The upstream connect must complete before the client 101 is sent,