Files
headroom/tests/test_openai_streaming_backend.py
alan blountandJD Davis 0ddaa56c21 fix(vertex): explain Vertex failures in-band, correct the model/region matrix (#2640)
## Description

Vertex rejects onboarding requests for a handful of recurring reasons —
expired ADC, a partner model never enabled in Model Garden, a model not
served in the requested location, a missing optional SDK — and its own
error text names none of the fixes. Users see a bare `404` or an opaque
`500` through their SDK and cannot tell a proxy bug from a
project-config gap.

This makes the proxy explain those failures where it happens, adds a
`[vertex]` extra so the LiteLLM Vertex backend can actually start, and
corrects an example, a test matrix, and three documentation claims that
could not have worked as written.

Closes #2632

## Type of Change

- [x] Bug fix (non-breaking change that fixes an issue)
- [x] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [x] Documentation update
- [ ] Performance improvement
- [ ] Code refactoring (no functional changes)

## Changes Made

**Explain Vertex failures in-band**
(`headroom/providers/vertex/diagnostics.py`, new)

- On `401/403/404/429`, attach an actionable hint three ways: a WARNING
in the proxy log, an `x-headroom-hint` response header, and a note
appended to `error.message`. The last is load-bearing — SDKs raise with
the message string and discard headers.
- Successful responses are never modified; annotation is idempotent;
statuses we cannot explain get no hint rather than a plausible-sounding
wrong one.
- Routes opt in via a one-line `@with_vertex_diagnostics` decorator
reading path params FastAPI already injects (**+8 lines** in
`proxy_routes.py`, no re-indentation).
- Same treatment for backend setup failures, where `--backend vertex`
surfaced LiteLLM's raw `No module named 'vertexai'` as an opaque 500.

**Make `--backend vertex` able to start** (`pyproject.toml`,
`registry.py`, `cli/proxy.py`)

- New `[vertex]` extra carrying `google-cloud-aiplatform>=1.38`.
Deliberately **not** folded into `[proxy]`: measured at ~175 MB
installed, and the native passthrough routes never needed it. Follows
the existing `proxy-prod` split.
- Startup preflight keyed on the **resolved provider**, so every alias
normalized at `registry.py:229` (`vertex`, `vertex_ai`,
`litellm-vertex`, `google-vertex`, `googlevertex`) is covered. Skipped
when a backend class is injected, so existing fake-based tests are
unaffected.
- New `BackendUnavailableError` so the CLI prints the remedy and exits
`2` instead of dumping a traceback through startup internals.

**Correct things that could not have worked**

| | was | is |
|---|---|---|
| SDK client | `http_options={"api_endpoint": ...}` | `{"base_url":
"http://..."}` — `api_endpoint` is not a field on `HttpOptions`;
pydantic rejects it before any request is sent |
| Thinking config | `ThinkingConfig(thinking_budget_tokens=)` |
`thinking_budget=` |
| Request payload | `contents: [{parts: [...]}]` | adds `role: "user"` —
the `global` endpoint enforces it, regional was silently lenient |
| Auth guidance | `gcloud auth print-access-token` |
`application-default` — the plain user token gets `401
ACCESS_TOKEN_TYPE_UNSUPPORTED` |
| Test matrix | model × location cross-product | explicit servable pairs
|

- Test matrix is now four pairs that can actually serve:
`global`/`gemini-flash-latest`, `global`/`claude-sonnet-4-6`,
`europe-west2`/`gemini-3.5-flash`, `us-east5`/`claude-sonnet-4-6`.
Gemini 3.x has no US regional endpoint and `-latest` aliases are
global-only, so a pinned `us-central1` Gemini case can never pass. No
Gemini 2.5 — it retires 2026-10-16.
- `test_thinking_levels` asserted only `status_code < 500` while sending
an ignored `thinkingBudgetTokens` key: it passed on 400s and proved
nothing. Now asserts 200 plus scored usage metadata with the correct
`thinkingBudget` spelling.
- Cases the caller's project genuinely cannot serve now **skip** with an
actionable reason instead of reporting a red proxy.

**Docs** (`proxy.mdx`, `installation.mdx`, `wiki/vertex.md`)

- `proxy.mdx` claimed `publisher=anthropic` passthrough "routes through
the same LiteLLM-Vertex path as `--backend vertex_ai`". It does not —
without the flag it is a direct forward, which is why it works on a bare
`[proxy]` install where the LiteLLM path cannot even import.
- Documented the trap of combining `--backend vertex` with native Vertex
URLs: LiteLLM takes project/region/model from its own config and ignores
the URL.
- `installation.mdx` and `wiki/vertex.md` said the SDK is "not included
in any extra".
- Cleared 15 pre-existing `ruff` findings in the two files this PR
rewrites (4 remain in `plugins/headroom-oauth2`, untouched by this
work).

## Testing

- [x] Unit tests pass (`pytest`)
- [x] Linting passes (`ruff check .`)
- [x] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed

### Test Output

```text
$ mypy headroom
Success: no issues found in 511 source files

$ ruff check .
Found 4 errors.        # all in plugins/headroom-oauth2, pre-existing, untouched by this PR

$ pytest tests/test_proxy_vertex_native_integration.py tests/test_vertex_diagnostics.py -q
44 passed, 1 warning in 69.86s          # 8 live integration + 36 offline diagnostics, 0 skipped

$ pytest tests/ -k "anthropic_messages or handler_anthropic or backend or registry or cli_proxy or vertex or proxy_routes"
853 passed, 49 skipped, 9345 deselected, 2 warnings in 28.41s
```

New tests in `tests/test_vertex_diagnostics.py` (36, no credentials
required): status coverage, per-publisher remedy divergence,
idempotency, `content-length` consistency after body rewrite, non-JSON
and body-less/streaming responses, every backend alias preflighted,
other providers unaffected, injected backend bypasses the preflight.

## Real Behavior Proof

- Environment: macOS 14, Python 3.11.15, live GCP project
(`alanblount-sandbox`) with `aiplatform.googleapis.com` enabled and
Claude enabled in Model Garden; ADC via `gcloud auth application-default
login`
- Exact command / steps: `export GCP_PROJECT_ID=alanblount-sandbox &&
export GCP_ACCESS_TOKEN=$(gcloud auth application-default
print-access-token) && uv run --extra proxy --with google-genai python3
examples/vertex_genai_sdk_demo.py && uv run --extra proxy --with
pytest-asyncio pytest tests/test_proxy_vertex_native_integration.py
tests/test_vertex_diagnostics.py -q && headroom proxy --backend vertex`
(exits 2, then retried with `[proxy,vertex]` extra installed)
- Observed result: demo printed `✓ Standard response received
successfully! > 1, 2, 3, 4, 5` and `✓ Thinking response received
successfully!`; 44 tests passed (8 live integration, 36 diagnostics), 0
skipped; `--backend vertex` exited 2 with the remedy message; same
request with the extra installed returned 200; invalid region produced
`[headroom] hint:` in the response body and `x-headroom-hint` header;
success responses were byte-clean
- Not tested: Windows; `us`/`eu` multi-region endpoints and Claude 4.7+
(project cannot serve them); Provisioned Throughput; Rust proxy path;
`--backend vertex` dropping URL project/model on native Vertex routes
(documented as known gap in Additional Notes)


## Review Readiness

- [x] I have performed a self-review
- [x] This PR is ready for human review

## Checklist

- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] I did **not** edit `CHANGELOG.md` — it is generated by
release-please from my Conventional Commit PR title (a CI guard enforces
this)

## Screenshots (if applicable)

N/A — proxy and CLI behavior; terminal output is quoted above.

## Additional Notes

- `uv.lock` intentionally not included: the new extra is opt-in and does
not change default resolution.
- Error-body rewriting is confined to already-failing responses and
wrapped so a diagnostic can never turn a clean upstream error into a
proxy 500.
- The preflight raises where the provider is resolved (`registry.py`)
rather than at the CLI, so programmatic embedders get the same
guarantee; the CLI only formats it.
- Three test files fail to collect on this branch
(`test_hermes_passthrough_compression`, `test_observability_metrics`,
`test_observability_tracing`). They predate this work and are unrelated,
so they were excluded rather than fixed — happy to open a separate
issue.
- `[vertex]` was chosen over adding the dependency to `[proxy]` after
measuring the footprint at ~175 MB. If maintainers prefer it in
`[proxy]`, that is a one-line change.
## Runtime Rollout Safety

- Rollout-managed feature(s): none; diagnostics annotate already-failing
Vertex responses and the backend dependency is opt-in through the vertex
extra.
- Minimum rollout channel: normal stable release after Vertex
diagnostics, route, and backend-path tests pass.
- Stable/default behavior changed: successful responses and native
passthrough remain unchanged; supported Vertex failures gain an
actionable header/message, and selecting the LiteLLM Vertex backend
without its SDK now fails once at startup.
- Kill switch / disable path: use native Vertex passthrough without the
LiteLLM backend, or human-revert the diagnostic/preflight change.
- Unsafe override required: none.
- Qualification impact: offline diagnostics, native integration, and
mocked LiteLLM Vertex request-shaping tests must remain green.
- Rollback path: human-revert the PR; no persisted state or migration is
involved.
<!-- devin-review-badge-begin -->

---

<a href="https://app.devin.ai/review/headroomlabs-ai/headroom/pull/2640"
target="_blank"><picture><source media="(prefers-color-scheme: dark)"
srcset="https://static.devin.ai/assets/gh-devin-review-dark.svg?v=4"><img
src="https://static.devin.ai/assets/gh-devin-review-light.svg?v=4"
alt="Devin Review"></picture></a>
<!-- devin-review-badge-end -->

### Maintainer current-main requalification

Exact head `5d7071f348d2462f666fd7ac1ceb8ac18050169a`, upstream main
`2d3ee51846435ef5b320eea4806af14e602b0d8c`.

Re-reviewed latest integration head c70c1a497 and current author
responses, including fixed public error hints, log escaping, body/header
consistency, all four backend error sites, and native-route versus
LiteLLM SDK dependency behavior. Clean integration with upstream/main
2d3ee51846. No new PR-specific source
blocker found in reviewed scope; no contributor diagnostic/routing logic
rewritten.

232 Vertex diagnostics/native-route/backend/CLI/release/version/MCP
tests pass with11 skips. Offline lock validation passes (268 packages);
all12 changed Python files pass Ruff check/format, and whitespace
passes. These checks cover synthetic error/transport paths and do not
establish live cloud regional availability or billing behavior. Earlier
author live evidence remains scoped to its stated environment; no fresh
cloud request or native build claimed here. Historical shared
cached-read fixture failure was main-reproduced and is not a
contributor-code blocker. Maintainers handle current exact-head hosted
qualification before approval; nothing merged.


Exact-head hosted checks are being handled by maintainers. No new
finding in the reviewed scope; formal approval awaits exact-head hosted
qualification; nothing merged.


### Maintainer current-main requalification

Exact head `486a716adbf642ae5e43276df4c2dc1e63b901d7`, upstream main
`c01cf07d943d816cfd9d97e6838ed4e38f1ff9a4`.

Clean mechanical sync with upstream main
c01cf07d94. Re-reviewed current
author/Devin discussion and public diagnostic/error boundaries,
native-versus-SDK route separation and startup preflight. This sync does
not alter the PR Vertex diagnostics, backend or route-registry
modules.158 focused diagnostics/native-route/backend/streaming/CLI tests
pass,11live-environment skips,1deprecation warning. Offline uv lock
--check passes;all12 changed Python files pass Ruff lint/format and
main-relative whitespace passes. Fixed hints remain separate from raw
provider error text; multi-worker preflight and non-Google partner
guidance retain resolved regressions. No contributor diagnostic/routing
correctness logic rewritten. Tests use existing current-main DLL and
synthetic errors/transports; no fresh native build, live regional
availability/provider inference or billing qualification claimed. Formal
approval awaits exact-head hosted qualification; maintainers handle CI.
Nothing merged.


Exact-head hosted checks are being handled by maintainers. No new
finding in the reviewed scope; formal approval awaits exact-head hosted
qualification; nothing merged.


### Maintainer current-main requalification

Exact head `0b75c609f24562c8b6ed2aaeaf58239984b4810c`, upstream main
`ce4275491299231bc9d2907833f72f72ea22b8a9`.

Requalified after human merges #4667,#4669,#4670 against upstream main
ce42754912. Earlier approval and
publication guards stopped stale candidates before either was posted.
Current clean merge retains Vertex diagnostics/native-versus-SDK routing
and main enable_kompress checks, lossless cold-prefix disable, and
Python token-window boundary behavior.190 combined
Vertex/backend/CLI/Kompress-disable/must-keep tests
pass,11live-environment skips,1warning. Offline lock validation,12-file
Ruff lint/format and main-relative whitespace pass. No contributor
diagnostic/routing logic rewritten. Native Rust/Cargo sources are
identical to c01 across these merges; existing matching-core DLL
supports tests, not a fresh native build. No new live Vertex
regional/provider/billing qualification claimed. All prior-main hosted
results are superseded for readiness; approval awaits exact checks on
this published merge head. Maintainers handle CI; no agent merge.


Exact-head hosted checks are being handled by maintainers. No new
finding in the reviewed scope; formal approval awaits exact-head hosted
qualification; nothing merged.


### Maintainer current-main requalification

Exact head `1fe62702ce614315679d68d9d126e31c57208c67`, upstream main
`00d4f441d3f1d48c463fea57e6c574c2f3671302`.

Requalified after human merges #4667,#4669,#4670 against upstream main
ce42754912. Earlier approval and
publication guards stopped stale candidates before either was posted.
Current clean merge retains Vertex diagnostics/native-versus-SDK routing
and main enable_kompress checks, lossless cold-prefix disable, and
Python token-window boundary behavior.190 combined
Vertex/backend/CLI/Kompress-disable/must-keep tests
pass,11live-environment skips,1warning. Offline lock validation,12-file
Ruff lint/format and main-relative whitespace pass. No contributor
diagnostic/routing logic rewritten. Native Rust/Cargo sources are
identical to c01 across these merges; existing matching-core DLL
supports tests, not a fresh native build. No new live Vertex
regional/provider/billing qualification claimed. All prior-main hosted
results are superseded for readiness; approval awaits exact checks on
this published merge head. Maintainers handle CI; no agent merge.

Final current-main requalification:
07d5add5ba, including human merges #4671
action pinning and #4648 multimodal memory preservation. Clean
mechanical merge; Vertex/backend/CLI inputs retain the preceding
190-test qualification. Fresh workflow/release suite: 62 passed. Fresh
memory wrapper suite: 9 passed. New wrapper retains list payload parts
and extracts textual search inputs; no contributor Vertex logic
rewritten. Existing native input provenance remains unchanged. Hosted
qualification must run on this final head before approval.

Newer human merge #4646 advanced authoritative main to
8cdce172ea before publication. Cleanly
integrated quote-aware read detection; reviewed new masking/segmentation
overlap. Fresh read-command/content-router suite: 188 passed, 1 optional
SOCKS warning. Vertex code remains unchanged by this merge.

Final additional human merge #4067 packaging changes advanced main to
a8905214d: cleanly integrated explicit torch-extras split, retaining
Vertex optional dependencies. Fresh ONNX/optional-dependency contracts:
12 passed. Offline lock check and whitespace pass. No live clean-install
or Torch backend claim. Earlier publication candidates were stopped
before push by fresh-main guard.

Latest human merge #4042 advances authoritative main to
cde584d7fe. Clean merge preserves optional
LangChain availability handling and CI dependency setup. Fresh
binding/compatibility/startup-log/xAI regression suite: 29 passed. New
main integration re-reviewed; no contributor Vertex behavior rewritten.

Subsequent #4049 main merge 00d4f441d adds graceful context lookup/init
failure handling. Cleanly integrated with Vertex handler diagnostics
intact. Fresh Anthropic pre-upstream/memory native ops/OpenAI Codex
routing/WebSocket lifecycle suite: 192 passed, 1 deprecation warning.
Reviewed exception handling and transport overlap; no live provider
qualification claim.


Exact-head hosted checks are being handled by maintainers. No new
finding in the reviewed scope; formal approval awaits exact-head hosted
qualification; nothing merged.


### Maintainer current-main requalification

Exact head `6c63811d6de7491ebce9a16f89e197f5f5dd86dd`, upstream main
`2b0315b2d4b0d54947050bbdad2de9e89df06378`.

Requalified against authoritative
main2b0315b2d4b0d54947050bbdad2de9e89df06378 after further human merges.
All10 integration patches exactly match00d4f441-to-current-main changes
after diff-location normalization; contributor Vertex
diagnostics/routing policy unchanged.539combined
Vertex/backend/CLI/Kompress-disable/must-keep/binary/doctor/Windows-supervisor/provider/search/text
tests pass;13platform/live-environment skips,2warnings. Nine changed
Python files pass Ruff lint/format; offline lock and whitespace pass.
Existing pr3982 native DLL verified against every tracked native
build-input hash and artifact checksum; no fresh native build claimed.
Current author/Devin discussion checked; prior fixes remain intact. No
live Vertex regional/provider/billing,IPv6 listener or unsupported cloud
qualification claimed. No new finding in reviewed scope. Exact-head
hosted checks must qualify this published head before formal approval;
maintainers handle them. Nothing merged.


Exact-head hosted checks are being handled by maintainers. No new
finding in the reviewed scope; formal approval awaits exact-head hosted
qualification; nothing merged.

---------

Co-authored-by: JD Davis <mxjerrett@gmail.com>
2026-11-06 12:27:47 -06:00

313 lines
12 KiB
Python

"""Test OpenAI /v1/chat/completions streaming through headroom proxy backends.
Proves that streaming works end-to-end: client → headroom proxy → backend → OpenAI API.
Two test modes:
1. Real API test (requires OPENAI_API_KEY): hits actual OpenAI with gpt-4o-mini
2. Mock test: proves the proxy returns SSE when stream:true with a backend configured
Run with:
OPENAI_API_KEY=sk-... pytest tests/test_openai_streaming_backend.py -v
"""
import os
from types import SimpleNamespace
from unittest.mock import AsyncMock, MagicMock, patch
import pytest
fastapi = pytest.importorskip("fastapi")
httpx = pytest.importorskip("httpx")
from fastapi.testclient import TestClient # noqa: E402
from headroom.backends.base import BackendResponse # noqa: E402
from headroom.proxy.server import ProxyConfig, create_app # noqa: E402
# =============================================================================
# Real API test (requires OPENAI_API_KEY)
# =============================================================================
@pytest.mark.skipif(not os.environ.get("OPENAI_API_KEY"), reason="OPENAI_API_KEY not set")
class TestOpenAIStreamingRealAPI:
"""Test streaming with real OpenAI API calls through the proxy."""
@pytest.fixture
def openai_api_key(self):
return os.environ["OPENAI_API_KEY"]
@pytest.fixture
def direct_proxy_client(self):
"""Proxy with NO backend — direct to OpenAI. This is the baseline."""
config = ProxyConfig(
optimize=False,
cache_enabled=False,
rate_limit_enabled=False,
)
app = create_app(config)
with TestClient(app) as client:
yield client
@pytest.fixture
def litellm_backend_client(self):
"""Proxy with litellm-openai backend — routes through LiteLLM."""
config = ProxyConfig(
optimize=False,
cache_enabled=False,
rate_limit_enabled=False,
backend="litellm-openai",
)
app = create_app(config)
with TestClient(app) as client:
yield client
def test_baseline_streaming_works_direct(self, direct_proxy_client, openai_api_key):
"""Baseline: streaming through proxy WITHOUT backend works (direct to OpenAI)."""
response = direct_proxy_client.post(
"/v1/chat/completions",
json={
"model": "gpt-4o-mini",
"messages": [{"role": "user", "content": "Say 'hello' and nothing else."}],
"stream": True,
"max_tokens": 10,
},
headers={"Authorization": f"Bearer {openai_api_key}"},
)
assert response.status_code == 200, f"Got {response.status_code}: {response.text[:200]}"
content_type = response.headers.get("content-type", "")
assert "text/event-stream" in content_type, (
f"Direct proxy streaming broken: got content-type '{content_type}'"
)
# Verify we got actual SSE chunks
body = response.text
assert "data: " in body, "No SSE data chunks in response"
assert "data: [DONE]" in body, "Missing [DONE] terminator"
def test_streaming_with_litellm_backend(self, litellm_backend_client, openai_api_key):
"""CRITICAL: streaming through proxy WITH litellm backend must also stream.
This test fails before the fix — the proxy returns a JSON blob
instead of SSE events, causing clients to hang.
"""
response = litellm_backend_client.post(
"/v1/chat/completions",
json={
"model": "gpt-4o-mini",
"messages": [{"role": "user", "content": "Say 'hello' and nothing else."}],
"stream": True,
"max_tokens": 10,
},
headers={"Authorization": f"Bearer {openai_api_key}"},
)
assert response.status_code == 200, f"Got {response.status_code}: {response.text[:200]}"
content_type = response.headers.get("content-type", "")
assert "text/event-stream" in content_type, (
f"STREAMING BUG: litellm backend returned '{content_type}' instead of "
f"'text/event-stream'. Client sees a JSON blob, not SSE events.\n"
f"Response body (first 300 chars): {response.text[:300]}"
)
# Verify SSE format
body = response.text
assert "data: " in body, "No SSE data chunks in streaming response"
def test_non_streaming_with_litellm_backend(self, litellm_backend_client, openai_api_key):
"""Non-streaming with backend should return normal JSON (sanity check)."""
response = litellm_backend_client.post(
"/v1/chat/completions",
json={
"model": "gpt-4o-mini",
"messages": [{"role": "user", "content": "Say 'hello' and nothing else."}],
"stream": False,
"max_tokens": 10,
},
headers={"Authorization": f"Bearer {openai_api_key}"},
)
assert response.status_code == 200, f"Got {response.status_code}: {response.text[:200]}"
content_type = response.headers.get("content-type", "")
assert "application/json" in content_type
data = response.json()
assert "choices" in data
assert data["choices"][0]["message"]["content"]
# =============================================================================
# Mock test (no API key needed — proves the routing bug)
# =============================================================================
class TestOpenAIStreamingMock:
"""Prove the streaming bug with mocks — no API key needed."""
def test_streaming_request_returns_sse_not_json(self):
"""When stream:true with a backend, content-type MUST be text/event-stream.
This test FAILS before the fix: the proxy calls send_openai_message()
(non-streaming) and returns application/json even though stream:true.
"""
config = ProxyConfig(
optimize=False,
cache_enabled=False,
rate_limit_enabled=False,
backend="anyllm",
anyllm_provider="openai",
)
mock_backend = MagicMock()
mock_backend.name = "anyllm-openai"
mock_backend.send_openai_message = AsyncMock(
return_value=BackendResponse(
body={
"id": "chatcmpl-123",
"object": "chat.completion",
"model": "test-model",
"choices": [
{
"index": 0,
"message": {"role": "assistant", "content": "Hello!"},
"finish_reason": "stop",
}
],
"usage": {"prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15},
},
status_code=200,
headers={"content-type": "application/json"},
)
)
with patch("headroom.proxy.server.AnyLLMBackend", return_value=mock_backend):
app = create_app(config)
with TestClient(app) as client:
response = client.post(
"/v1/chat/completions",
json={
"model": "test-model",
"messages": [{"role": "user", "content": "hello"}],
"stream": True,
},
headers={"Authorization": "Bearer test-key"},
)
assert response.status_code == 200, (
f"Got {response.status_code}: {response.text[:200]}"
)
content_type = response.headers.get("content-type", "")
assert "text/event-stream" in content_type, (
f"STREAMING BUG: stream:true with backend returned '{content_type}' "
f"instead of 'text/event-stream'. The proxy ignored the stream flag "
f"and returned a JSON blob. Clients expecting SSE will hang.\n"
f"Response: {response.text[:300]}"
)
def test_non_streaming_still_returns_json(self):
"""Sanity: stream:false with backend should return JSON as before."""
config = ProxyConfig(
optimize=False,
cache_enabled=False,
rate_limit_enabled=False,
backend="anyllm",
anyllm_provider="openai",
)
mock_backend = MagicMock()
mock_backend.name = "anyllm-openai"
mock_backend.send_openai_message = AsyncMock(
return_value=BackendResponse(
body={
"id": "chatcmpl-123",
"object": "chat.completion",
"model": "test-model",
"choices": [
{
"index": 0,
"message": {"role": "assistant", "content": "Hello!"},
"finish_reason": "stop",
}
],
"usage": {"prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15},
},
status_code=200,
headers={"content-type": "application/json"},
)
)
with patch("headroom.proxy.server.AnyLLMBackend", return_value=mock_backend):
app = create_app(config)
with TestClient(app) as client:
response = client.post(
"/v1/chat/completions",
json={
"model": "test-model",
"messages": [{"role": "user", "content": "hello"}],
"stream": False,
},
headers={"Authorization": "Bearer test-key"},
)
assert response.status_code == 200
content_type = response.headers.get("content-type", "")
assert "application/json" in content_type
data = response.json()
assert data["choices"][0]["message"]["content"] == "Hello!"
def test_litellm_vertex_streaming_preserves_max_tokens_and_vendor_fields(self):
config = ProxyConfig(
optimize=False,
cache_enabled=False,
rate_limit_enabled=False,
backend="litellm-vertex",
)
async def fake_stream():
yield SimpleNamespace(
model_dump=lambda **kwargs: {
"id": "chunk1",
"choices": [{"delta": {"content": "a"}}],
}
)
with (
patch("headroom.backends.litellm._fetch_bedrock_inference_profiles", return_value={}),
patch("headroom.backends.litellm.acompletion", new_callable=AsyncMock) as mock_acomp,
# Suppress the SDK preflight: this test proves LiteLLM request-shaping,
# not whether google-cloud-aiplatform is installed in the CI environment.
patch("headroom.providers.vertex.diagnostics.vertex_sdk_available", return_value=True),
):
mock_acomp.return_value = fake_stream()
app = create_app(config)
with TestClient(app) as client:
response = client.post(
"/v1/chat/completions",
json={
"model": "claude-sonnet-4-6",
"messages": [{"role": "user", "content": "hi"}],
"max_tokens": 32,
"chat_template_kwargs": {"enable_thinking": False},
"stream": True,
},
headers={"Authorization": "Bearer test-key"},
)
assert response.status_code == 200, response.text
assert "text/event-stream" in response.headers.get("content-type", "")
assert "data: [DONE]" in response.text
kwargs = mock_acomp.await_args.kwargs
assert kwargs["stream"] is True
assert kwargs["max_tokens"] == 32
assert kwargs["extra_body"] == {"chat_template_kwargs": {"enable_thinking": False}}
assert "max_completion_tokens" not in kwargs["extra_body"]