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): send VS Code next-edit requests to the completions host (#4188)

Tejas Chopra22a1296cfabc
diff --git a/headroom/copilot_auth.py b/headroom/copilot_auth.py
index c81e1036c..f28593158 100644
--- a/headroom/copilot_auth.py
+++ b/headroom/copilot_auth.py
@@ -346,6 +346,28 @@ def is_copilot_completions_host(url: str | None) -> bool:
return host.startswith("proxy.") and host.endswith(".githubcopilot.com")
+def copilot_nes_base_url(model: Any, upstream_base_url: str) -> str | None:
+ """Return the completions host for a next-edit request aimed at public CAPI.
+
+ Copilot Chat serves ghost text and next edits by posting ``copilot-nes-*``
+ models to ``{overrideProxyUrl}/chat/completions``. ``headroom wrap vscode``
+ points that override at the same proxy as CAPI, but only the completions
+ host serves these models; CAPI answers ``400 model_not_supported``.
+
+ Returns ``None`` (keep the upstream) for any other model, for an upstream
+ that already is a completions host, and for a GHE or custom deployment,
+ whose traffic must not leave it (see :func:`copilot_completions_base_url`).
+ """
+
+ if not (isinstance(model, str) and model.startswith("copilot-nes-")):
+ return None
+ if not _is_public_copilot_api_host(_url_host(upstream_base_url)):
+ return None
+ if is_copilot_completions_host(upstream_base_url):
+ return None
+ return copilot_completions_base_url()
+
+
def copilot_completions_base_url() -> str:
"""Return the base URL serving Copilot's inline-completions endpoint.
diff --git a/headroom/proxy/handlers/openai.py b/headroom/proxy/handlers/openai.py
index 9604102ee..80f0657a4 100644
--- a/headroom/proxy/handlers/openai.py
+++ b/headroom/proxy/handlers/openai.py
@@ -69,6 +69,7 @@ from headroom.config import is_tool_excluded, unwrap_tool_call_name
from headroom.copilot_auth import (
apply_copilot_api_auth,
build_copilot_upstream_url,
+ copilot_nes_base_url,
is_copilot_api_url,
)
from headroom.pipeline import PipelineStage, summarize_routing_markers
@@ -3145,6 +3146,16 @@ class OpenAIHandlerMixin:
)
custom_upstream_base_url = _resolve_openai_upstream_base(request.headers)
upstream_base_url = self._resolve_openai_upstream(request)
+ # Ghost text and next edits: CAPI does not serve these models. A
+ # caller-chosen x-headroom-base-url is left alone, as in
+ # select_passthrough_base_url.
+ nes_base_url = (
+ copilot_nes_base_url(model, upstream_base_url)
+ if custom_upstream_base_url is None
+ else None
+ )
+ if nes_base_url:
+ upstream_base_url = nes_base_url
handler_path_suffix = _resolve_openai_chat_handler_path(
upstream_base_url,
model,
diff --git a/tests/test_proxy/test_copilot_nes_routing.py b/tests/test_proxy/test_copilot_nes_routing.py
new file mode 100644
index 000000000..7f66d0931
--- /dev/null
+++ b/tests/test_proxy/test_copilot_nes_routing.py
@@ -0,0 +1,183 @@
+"""VS Code's ghost text and next edits must reach Copilot's completions host.
+
+Copilot Chat posts ``copilot-nes-*`` models to ``{overrideProxyUrl}/chat/completions``.
+``headroom wrap vscode`` points that override and the CAPI override at the same
+proxy, so these requests arrive on the chat handler next to ordinary chat turns.
+CAPI answers them with ``400 model_not_supported`` on both the generic and the
+per-plan host, so VS Code showed no ghost text at all behind Headroom. Pinned at
+the send seams: the URL that was built and the credentials sent.
+"""
+
+from __future__ import annotations
+
+import pytest
+
+fastapi = pytest.importorskip("fastapi")
+httpx = pytest.importorskip("httpx")
+
+from fastapi.testclient import TestClient # noqa: E402
+
+from headroom import copilot_auth # noqa: E402
+from headroom.proxy.server import ProxyConfig, create_app # noqa: E402
+
+BUSINESS_CAPI = "https://api.business.githubcopilot.com"
+DEFAULT_COMPLETIONS = "https://copilot-proxy.githubusercontent.com"
+NES_MODEL = "copilot-nes-pandia-25"
+MINTED = "tid_minted_for_test"
+
+
+class _Send:
+ """Capture what the buffered or streaming arm was about to send."""
+
+ def __init__(self) -> None:
+ self.url: str | None = None
+ self.headers: dict[str, str] = {}
+
+ async def __call__(self, method, url, headers, body, **kwargs):
+ self.url = url
+ self.headers = {k.lower(): v for k, v in dict(headers).items()}
+ return httpx.Response(
+ 200,
+ json={
+ "id": "c1",
+ "object": "chat.completion",
+ "model": "m",
+ "choices": [
+ {
+ "index": 0,
+ "message": {"role": "assistant", "content": "ok"},
+ "finish_reason": "stop",
+ }
+ ],
+ "usage": {"prompt_tokens": 5, "completion_tokens": 1, "total_tokens": 6},
+ },
+ request=httpx.Request(method, url),
+ )
+
+ async def send_stream(self, request, **kwargs):
+ """Stand in for ``http_client.send``: the streaming arm's wire, after auth."""
+ self.url = str(request.url)
+ self.headers = {k.lower(): v for k, v in request.headers.items()}
+ return httpx.Response(
+ 200,
+ headers={"content-type": "text/event-stream"},
+ content=b'data: {"choices":[{"index":0,"delta":{"content":"ok"}}]}\n\ndata: [DONE]\n\n',
+ request=request,
+ )
+
+
[email protected](autouse=True)
+def _isolated_copilot_state(monkeypatch: pytest.MonkeyPatch):
+ class _Token:
+ token = MINTED
+
+ class _Provider:
+ async def get_api_token(self, integration_id: str | None = None):
+ return _Token()
+
+ monkeypatch.setattr(copilot_auth, "get_copilot_token_provider", lambda: _Provider())
+ for name in (
+ "GITHUB_COPILOT_PROXY_URL",
+ "GITHUB_COPILOT_API_URL",
+ "GITHUB_COPILOT_ENTERPRISE_URL",
+ ):
+ monkeypatch.delenv(name, raising=False)
+ copilot_auth.reset_observed_completions_endpoint()
+ yield
+ copilot_auth.reset_observed_completions_endpoint()
+
+
+def _post(
+ model: str,
+ *,
+ openai_api_url: str = BUSINESS_CAPI,
+ stream: bool = False,
+ headers: dict[str, str] | None = None,
+) -> _Send:
+ send = _Send()
+ config = ProxyConfig(
+ optimize=False,
+ cache_enabled=False,
+ rate_limit_enabled=False,
+ mode="token",
+ openai_api_url=openai_api_url,
+ )
+ with TestClient(create_app(config)) as client:
+ proxy = client.app.state.proxy
+ proxy._retry_request = send
+ proxy.http_client.send = send.send_stream
+ resp = client.post(
+ "/chat/completions",
+ json={
+ "model": model,
+ "stream": stream,
+ "max_tokens": 16,
+ "messages": [{"role": "user", "content": "def add(a, b):\n "}],
+ },
+ headers={"Authorization": "Bearer vscode-session-token", **(headers or {})},
+ )
+ assert resp.status_code == 200
+ return send
+
+
+def test_next_edit_models_go_to_the_completions_host_with_copilot_credentials() -> None:
+ send = _post(NES_MODEL)
+
+ assert send.url == f"{DEFAULT_COMPLETIONS}/chat/completions"
+ assert send.headers["authorization"] == f"Bearer {MINTED}"
+
+
+def test_streamed_next_edits_go_to_the_completions_host_with_copilot_credentials() -> None:
+ send = _post(NES_MODEL, stream=True)
+
+ assert send.url == f"{DEFAULT_COMPLETIONS}/chat/completions"
+ assert send.headers["authorization"] == f"Bearer {MINTED}"
+
+
+def test_next_edit_models_follow_the_completions_host_github_advertised() -> None:
+ copilot_auth._remember_completions_endpoint(
+ {"endpoints": {"proxy": "https://proxy.business.githubcopilot.com"}}
+ )
+
+ send = _post(NES_MODEL)
+
+ assert send.url == "https://proxy.business.githubcopilot.com/chat/completions"
+
+
+def test_chat_models_stay_on_the_plan_host() -> None:
+ send = _post("gpt-4o-mini")
+
+ assert send.url == f"{BUSINESS_CAPI}/chat/completions"
+
+
+def test_a_ghe_tenant_keeps_its_next_edits_inside_its_deployment() -> None:
+ send = _post(NES_MODEL, openai_api_url="https://copilot-api.acme.ghe.com")
+
+ assert send.url is not None
+ assert send.url.startswith("https://copilot-api.acme.ghe.com/")
+
+
+def test_a_configured_enterprise_deployment_keeps_next_edits_with_a_public_upstream(
+ monkeypatch: pytest.MonkeyPatch,
+) -> None:
+ monkeypatch.setenv("GITHUB_COPILOT_ENTERPRISE_URL", "https://acme.ghe.com")
+
+ send = _post(NES_MODEL, openai_api_url="https://api.githubcopilot.com")
+
+ assert send.url == "https://copilot-api.acme.ghe.com/chat/completions"
+
+
+def test_a_completions_host_target_is_not_moved() -> None:
+ send = _post(NES_MODEL, openai_api_url="https://proxy.enterprise.githubcopilot.com")
+
+ assert send.url == "https://proxy.enterprise.githubcopilot.com/chat/completions"
+
+
+def test_a_caller_chosen_base_url_is_left_alone() -> None:
+ send = _post(
+ NES_MODEL,
+ headers={"x-headroom-base-url": "https://api.githubcopilot.com"},
+ )
+
+ assert send.url is not None
+ assert send.url.startswith("https://api.githubcopilot.com/")