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(proxy): add versionless Vertex AI routes for Claude Code compatibility (#1321)

Aykut Bulgubb3e040a463b
diff --git a/headroom/providers/proxy_routes.py b/headroom/providers/proxy_routes.py
index 0b1e1ae97..40a4faea5 100644
--- a/headroom/providers/proxy_routes.py
+++ b/headroom/providers/proxy_routes.py
@@ -732,6 +732,24 @@ def register_provider_routes(app: FastAPI, proxy: Any) -> None:
)
return await vertex_publisher_passthrough(request, publisher, "rawPredict")
+ @app.post(
+ "/projects/{project}/locations/{location}/publishers/anthropic/models/{model}:rawPredict"
+ )
+ async def vertex_raw_predict_no_version(
+ request: Request,
+ project: str,
+ location: str,
+ model: str,
+ ):
+ del project
+ target = _vertex_target_for_location(proxy, location).rstrip("/") + "/v1"
+ return await proxy.handle_anthropic_messages(
+ request,
+ target,
+ "vertex:anthropic",
+ model,
+ )
+
@app.post(
"/{api_version}/projects/{project}/locations/{location}/publishers/{publisher}/models/{model}:streamRawPredict"
)
@@ -754,6 +772,25 @@ def register_provider_routes(app: FastAPI, proxy: Any) -> None:
)
return await vertex_publisher_passthrough(request, publisher, "streamRawPredict")
+ @app.post(
+ "/projects/{project}/locations/{location}/publishers/anthropic/models/{model}:streamRawPredict"
+ )
+ async def vertex_stream_raw_predict_no_version(
+ request: Request,
+ project: str,
+ location: str,
+ model: str,
+ ):
+ del project
+ target = _vertex_target_for_location(proxy, location).rstrip("/") + "/v1"
+ return await proxy.handle_anthropic_messages(
+ request,
+ target,
+ "vertex:anthropic",
+ model,
+ True,
+ )
+
@app.get("/v1/models")
async def list_models(request: Request):
chatgpt_response = await _handle_chatgpt_model_metadata(
diff --git a/tests/test_provider_proxy_routes.py b/tests/test_provider_proxy_routes.py
index 32312ba37..3b8a79a17 100644
--- a/tests/test_provider_proxy_routes.py
+++ b/tests/test_provider_proxy_routes.py
@@ -163,6 +163,24 @@ def test_provider_passthrough_routes_forward_expected_targets(monkeypatch) -> No
"model": "claude-3-5-sonnet@20240620",
"force_stream": False,
}
+ assert client.post(
+ "/projects/p/locations/us-central1/publishers/anthropic/models/claude-3-5-sonnet@20240620:rawPredict"
+ ).json() == {
+ "handler": "handle_anthropic_messages",
+ "path": "/projects/p/locations/us-central1/publishers/anthropic/models/claude-3-5-sonnet@20240620:rawPredict",
+ "upstream_base_url": "https://vertex.test/v1",
+ "provider": "vertex:anthropic",
+ "model": "claude-3-5-sonnet@20240620",
+ "force_stream": False,
+ }
+ non_anthropic_raw = client.post(
+ "/projects/p/locations/us-central1/publishers/google/models/gemini-2.0-flash:rawPredict"
+ ).json()
+ assert non_anthropic_raw.get("handler") != "handle_anthropic_messages"
+ non_anthropic_stream = client.post(
+ "/projects/p/locations/us-central1/publishers/google/models/gemini-2.0-flash:streamRawPredict"
+ ).json()
+ assert non_anthropic_stream.get("handler") != "handle_anthropic_messages"
assert client.post("/v1beta/cachedContents").json()["sub_path"] == "cachedContents"
assert client.get("/v1beta/cachedContents").json()["sub_path"] == "cachedContents"
assert client.get("/v1beta/cachedContents/cache-1").json()["sub_path"] == "cachedContents"
@@ -201,7 +219,7 @@ def test_provider_passthrough_routes_forward_expected_targets(monkeypatch) -> No
assert len(calls) >= 16
assert len(gemini_calls) >= 1
assert len(gemini_count_calls) >= 1
- assert len(anthropic_calls) >= 1
+ assert len(anthropic_calls) >= 2
def test_proxy_route_helpers_prefer_legacy_targets_and_gemini_passthrough() -> None:
@@ -339,6 +357,21 @@ def test_provider_specific_routes_delegate_to_expected_proxy_handlers(monkeypatc
"claude-3-5-sonnet@20240620",
True,
]
+ assert client.post(
+ "/projects/p/locations/us-central1/publishers/anthropic/models/claude-3-5-sonnet@20240620:rawPredict"
+ ).json()["args"] == [
+ "https://vertex.test/v1",
+ "vertex:anthropic",
+ "claude-3-5-sonnet@20240620",
+ ]
+ assert client.post(
+ "/projects/p/locations/us-central1/publishers/anthropic/models/claude-3-5-sonnet@20240620:streamRawPredict"
+ ).json()["args"] == [
+ "https://vertex.test/v1",
+ "vertex:anthropic",
+ "claude-3-5-sonnet@20240620",
+ True,
+ ]
assert client.post("/v1internal:streamGenerateContent").json()["handler"] == (
"handle_google_cloudcode_stream"
)
@@ -356,7 +389,7 @@ def test_provider_specific_routes_delegate_to_expected_proxy_handlers(monkeypatc
"handle_google_batch_passthrough"
)
- assert len(delegated) >= 24
+ assert len(delegated) >= 26
def test_openai_response_websocket_aliases_delegate_to_openai_ws_handler(monkeypatch) -> None: