Skip to content

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.

fix(copilot): route mixed-model requests per model (#1785)

Rod Boev5af5e22862a0
diff --git a/headroom/proxy/handlers/openai.py b/headroom/proxy/handlers/openai.py
index 962847423..24e72f684 100644
--- a/headroom/proxy/handlers/openai.py
+++ b/headroom/proxy/handlers/openai.py
@@ -44,8 +44,13 @@ if TYPE_CHECKING:
import httpx
from headroom.agent_savings import proxy_pipeline_kwargs
-from headroom.copilot_auth import apply_copilot_api_auth, build_copilot_upstream_url
+from headroom.copilot_auth import (
+ apply_copilot_api_auth,
+ build_copilot_upstream_url,
+ is_copilot_api_url,
+)
from headroom.pipeline import PipelineStage, summarize_routing_markers
+from headroom.providers.copilot import model_prefers_responses_api
from headroom.proxy.auth_mode import (
classify_auth_mode,
classify_client,
@@ -168,6 +173,14 @@ def _resolve_openai_upstream_base(request_headers: dict[str, str]) -> str | None
return normalized
+def _resolve_openai_chat_handler_path(base_url: str, model: str | None) -> str:
+ """Return the upstream path suffix for an OpenAI chat-completions request."""
+
+ if is_copilot_api_url(base_url) and model_prefers_responses_api(model):
+ return _OPENAI_RESPONSES_PATH
+ return _OPENAI_CHAT_COMPLETIONS_PATH
+
+
def _append_request_query(url: str, query: str) -> str:
if not query:
return url
@@ -965,8 +978,7 @@ class OpenAIHandlerMixin:
not just the generic passthrough route that already honors it. Falls
back to the configured ``OPENAI_API_URL`` (``OPENAI_TARGET_API_URL``).
"""
- custom = request.headers.get("x-headroom-base-url", "").strip()
- return custom or self.OPENAI_API_URL
+ return _resolve_openai_upstream_base(request.headers) or self.OPENAI_API_URL
@staticmethod
def _strict_previous_turn_frozen_count(
@@ -1896,6 +1908,17 @@ class OpenAIHandlerMixin:
model = body.get("model", "unknown")
messages = body.get("messages", [])
original_client_messages = copy.deepcopy(messages)
+ custom_upstream_base_url = _resolve_openai_upstream_base(request.headers)
+ upstream_base_url = self._resolve_openai_upstream(request)
+ handler_path_suffix = _resolve_openai_chat_handler_path(
+ upstream_base_url,
+ model,
+ )
+ handler_path = (
+ _resolve_openai_handler_path(request.headers, handler_path=handler_path_suffix)
+ if custom_upstream_base_url is not None
+ else f"/v1{handler_path_suffix}"
+ )
input_event = self.pipeline_extensions.emit(
PipelineStage.INPUT_RECEIVED,
operation="proxy.request",
@@ -1904,7 +1927,7 @@ class OpenAIHandlerMixin:
model=model,
messages=messages,
tools=body.get("tools"),
- metadata={"path": "/v1/chat/completions", "stream": body.get("stream", False)},
+ metadata={"path": handler_path, "stream": body.get("stream", False)},
)
if input_event.messages is not None:
messages = input_event.messages
@@ -2112,7 +2135,7 @@ class OpenAIHandlerMixin:
provider="openai",
model=model,
messages=messages,
- metadata={"cache_hit": True, "path": "/v1/chat/completions"},
+ metadata={"cache_hit": True, "path": handler_path},
)
# Response-cache hit: same pattern as the anthropic
# cache-hit site. ``from_response_cache=True`` is the
@@ -2598,7 +2621,7 @@ class OpenAIHandlerMixin:
messages=optimized_messages,
tools=tools,
headers=headers,
- metadata={"path": "/v1/chat/completions", "stream": stream},
+ metadata={"path": handler_path, "stream": stream},
)
if presend_event.messages is not None:
optimized_messages = presend_event.messages
@@ -2632,7 +2655,7 @@ class OpenAIHandlerMixin:
model=model,
messages=body["messages"],
tools=tools,
- metadata={"path": "/v1/chat/completions", "stream": True},
+ metadata={"path": handler_path, "stream": True},
)
# Streaming: use stream_openai_message() → SSE events
return await self._stream_openai_via_backend(
@@ -2667,7 +2690,7 @@ class OpenAIHandlerMixin:
tools=tools,
response=backend_response.body,
metadata={
- "path": "/v1/chat/completions",
+ "path": handler_path,
"stream": False,
"status_code": backend_response.status_code,
},
@@ -2680,7 +2703,7 @@ class OpenAIHandlerMixin:
model=model,
response=backend_response.body,
metadata={
- "path": "/v1/chat/completions",
+ "path": handler_path,
"stream": False,
"status_code": backend_response.status_code,
},
@@ -2883,7 +2906,7 @@ class OpenAIHandlerMixin:
model=model,
messages=body["messages"],
tools=tools,
- metadata={"path": "/v1/chat/completions", "stream": True},
+ metadata={"path": handler_path, "stream": True},
)
return await self._stream_response(
url,
@@ -2915,7 +2938,7 @@ class OpenAIHandlerMixin:
tools=tools,
response=response,
metadata={
- "path": "/v1/chat/completions",
+ "path": handler_path,
"stream": False,
"status_code": response.status_code,
},
@@ -2928,7 +2951,7 @@ class OpenAIHandlerMixin:
model=model,
response=response,
metadata={
- "path": "/v1/chat/completions",
+ "path": handler_path,
"stream": False,
"status_code": response.status_code,
},
diff --git a/tests/test_proxy_copilot_auth_hooks.py b/tests/test_proxy_copilot_auth_hooks.py
index 99761c08b..eb0eecd4a 100644
--- a/tests/test_proxy_copilot_auth_hooks.py
+++ b/tests/test_proxy_copilot_auth_hooks.py
@@ -46,6 +46,7 @@ def _load_handler_module(monkeypatch: pytest.MonkeyPatch, module_name: str, rela
httpx_mod.ConnectError = type("ConnectError", (Exception,), {})
httpx_mod.ConnectTimeout = type("ConnectTimeout", (Exception,), {})
httpx_mod.PoolTimeout = type("PoolTimeout", (Exception,), {})
+ httpx_mod.ReadTimeout = type("ReadTimeout", (Exception,), {})
monkeypatch.setitem(sys.modules, "httpx", httpx_mod)
responses_mod = types.ModuleType("fastapi.responses")
@@ -227,3 +228,42 @@ def test_streaming_response_applies_copilot_auth(monkeypatch: pytest.MonkeyPatch
assert sent_headers["Authorization"] == "Bearer upstream-token"
assert sent_headers["content-type"] == "application/json"
assert response.status_code == 200
+
+
+def test_openai_chat_routes_copilot_requests_per_model(monkeypatch: pytest.MonkeyPatch) -> None:
+ openai_mod = _load_handler_module(
+ monkeypatch,
+ "tests.headroom_proxy_handlers_openai",
+ "headroom/proxy/handlers/openai.py",
+ )
+
+ copilot_base = "https://api.githubcopilot.com"
+ gpt54_mini_url = openai_mod.build_copilot_upstream_url(
+ copilot_base,
+ openai_mod._resolve_openai_handler_path(
+ {},
+ handler_path=openai_mod._resolve_openai_chat_handler_path(copilot_base, "gpt-5.4-mini"),
+ ),
+ )
+ claude_url = openai_mod.build_copilot_upstream_url(
+ copilot_base,
+ openai_mod._resolve_openai_handler_path(
+ {},
+ handler_path=openai_mod._resolve_openai_chat_handler_path(
+ copilot_base, "claude-sonnet-5"
+ ),
+ ),
+ )
+ openai_url = openai_mod.build_copilot_upstream_url(
+ "https://api.openai.com",
+ openai_mod._resolve_openai_handler_path(
+ {},
+ handler_path=openai_mod._resolve_openai_chat_handler_path(
+ "https://api.openai.com", "gpt-5.4-mini"
+ ),
+ ),
+ )
+
+ assert gpt54_mini_url == "https://api.githubcopilot.com/responses"
+ assert claude_url == "https://api.githubcopilot.com/chat/completions"
+ assert openai_url == "https://api.openai.com/v1/chat/completions"