mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
## Description Fixes #2410. When a streaming `/v1/responses` request has `headroom_retrieve` available, Headroom forces a non-streaming (`stream:false`) upstream call so CCR retrieval can be resolved server-side, then reconstructs the complete response as SSE for the client. GitHub Copilot returns 200 with real output tokens, but OpenCode shows no assistant response. Root cause: `_openai_responses_to_sse` emitted only two events — `response.created` and `response.completed`: ```python created_response = {**response, "status": "in_progress", "output": []} events = [("response.created", created_response), ("response.completed", response)] ``` Clients that read the whole answer off the terminal `response.completed` event work, but OpenCode and the Vercel AI SDK render output from the **incremental** item/text events (`response.output_item.added`, `response.output_text.delta`, ...). With those absent, the SDK displays nothing. ## Fix Reconstruct the real Responses event sequence: ``` response.created (status in_progress, empty output) response.in_progress for each output item: response.output_item.added (message items start with empty content) for each message content part: response.content_part.added (text blanked) response.output_text.delta (the text) response.output_text.done response.content_part.done response.output_item.done (full item) response.completed (full response) data: [DONE] ``` Non-message items (reasoning, function_call, ...) get `output_item.added` + `output_item.done` with the full item. Every event carries a contiguous `sequence_number`. The terminal `response.completed` still carries the full response, so clients that key off it are unaffected; clients that stream now receive the deltas they need. ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) - [ ] New feature (non-breaking change that adds functionality) - [ ] Breaking change (fix or feature that would cause existing functionality to change) - [ ] Documentation update - [ ] Performance improvement - [ ] Code refactoring (no functional changes) ## Changes Made - `headroom/proxy/handlers/openai.py`: rewrite `_openai_responses_to_sse` to replay the incremental output-item/content-part/output-text events between `response.created`/`response.in_progress` and `response.completed`. - `tests/test_openai_responses_buffered_sse.py`: new test asserting the incremental `output_text.delta` (visible text), the per-item sequence for message vs non-message items, the empty-output case, and contiguous sequence numbers. ## Testing - [x] Unit tests pass (`pytest`) - [x] Linting passes (`ruff check .`) - [x] Type checking passes (`mypy headroom`) - [x] New tests added for new functionality - [ ] Manual testing performed ### Test Output ```text $ uvx ruff@0.15.17 check headroom/proxy/handlers/openai.py tests/test_openai_responses_buffered_sse.py All checks passed! $ uvx mypy@1.20.2 --ignore-missing-imports headroom/proxy/handlers/openai.py # no errors in the changed file # _openai_responses_to_sse is a pure module-level function, so I ran the new # tests against the real code in the project venv (uv sync): 3 passed. ``` ## Real Behavior Proof - Environment: Windows 11, Python 3.12, project venv (`uv sync --extra proxy`), `uvx ruff@0.15.17` / `uvx mypy@1.20.2`. - Exact command / steps: fed the real `_openai_responses_to_sse` a completed response with a reasoning item and a message item whose content is `output_text: "Hello world"`, plus an empty-output response and a function_call-only response. - Observed result: the stream now contains `response.output_text.delta` with `"Hello world"` at `output_index=1, content_index=0`, wrapped by `content_part.added/done` and `output_item.added/done`, with the reasoning and function_call items emitted as `output_item.added/done` and preserved whole; `response.created`/`in_progress` carry empty output while `response.completed` carries the full output; sequence numbers are `0..n`. Ran against the actual module. - Not tested: a live OpenCode -> Copilot Responses round trip; the added tests assert the event stream directly. ## 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 - [ ] 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 - [ ] I have updated the CHANGELOG.md if applicable ## Additional Notes `_openai_responses_to_sse` is a pure function, so I verified the fix against the real code in the venv (output above) in addition to the unit tests. This mirrors the incremental replay the Anthropic buffered path already does in `StreamingMixin._response_to_sse` (content_block_start/delta/stop), bringing the Responses buffered-CCR path to the same fidelity.
109 lines
3.8 KiB
Python
109 lines
3.8 KiB
Python
"""Regression for #2410: the buffered-CCR Responses -> SSE reconstruction must
|
|
replay the incremental output-item/text events, not just response.created +
|
|
response.completed, so AI-SDK / OpenCode clients render the output."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
|
|
from headroom.proxy.handlers.openai import _openai_responses_to_sse
|
|
|
|
|
|
def _parse(events: list[bytes]) -> list[dict]:
|
|
out: list[dict] = []
|
|
for e in events:
|
|
s = e.decode()
|
|
if s.startswith("data: [DONE]"):
|
|
out.append({"type": "[DONE]"})
|
|
continue
|
|
out.append(json.loads(s.split("data: ", 1)[1]))
|
|
return out
|
|
|
|
|
|
def test_responses_sse_replays_incremental_output_text() -> None:
|
|
resp = {
|
|
"id": "resp_1",
|
|
"object": "response",
|
|
"status": "completed",
|
|
"model": "gpt-5.3-codex",
|
|
"output": [
|
|
{"type": "reasoning", "id": "rs_1", "summary": []},
|
|
{
|
|
"type": "message",
|
|
"id": "msg_1",
|
|
"status": "completed",
|
|
"role": "assistant",
|
|
"content": [{"type": "output_text", "text": "Hello world", "annotations": []}],
|
|
},
|
|
],
|
|
"usage": {"input_tokens": 10, "output_tokens": 3},
|
|
}
|
|
|
|
parsed = _parse(_openai_responses_to_sse(resp))
|
|
types = [p["type"] for p in parsed]
|
|
|
|
assert types[0] == "response.created"
|
|
assert types[1] == "response.in_progress"
|
|
assert types[-2] == "response.completed"
|
|
assert types[-1] == "[DONE]"
|
|
|
|
# The visible assistant text is streamed as an output_text.delta.
|
|
deltas = [p for p in parsed if p["type"] == "response.output_text.delta"]
|
|
assert len(deltas) == 1
|
|
assert deltas[0]["delta"] == "Hello world"
|
|
assert deltas[0]["output_index"] == 1
|
|
assert deltas[0]["content_index"] == 0
|
|
|
|
# The message item gets the full content-part sequence; the reasoning item
|
|
# gets add/done with no content parts.
|
|
assert types.count("response.output_item.added") == 2
|
|
assert types.count("response.output_item.done") == 2
|
|
assert "response.content_part.added" in types
|
|
assert "response.output_text.done" in types
|
|
assert "response.content_part.done" in types
|
|
|
|
# created / in_progress carry an empty output; completed carries the full one.
|
|
created = next(p for p in parsed if p["type"] == "response.created")
|
|
assert created["response"]["output"] == []
|
|
completed = next(p for p in parsed if p["type"] == "response.completed")
|
|
assert completed["response"]["output"] == resp["output"]
|
|
|
|
# Sequence numbers are contiguous from 0.
|
|
seqs = [p["sequence_number"] for p in parsed if p["type"] != "[DONE]"]
|
|
assert seqs == list(range(len(seqs)))
|
|
|
|
|
|
def test_responses_sse_empty_output_still_valid() -> None:
|
|
resp = {"id": "resp_2", "status": "completed", "output": [], "usage": {}}
|
|
types = [p["type"] for p in _parse(_openai_responses_to_sse(resp))]
|
|
assert types == ["response.created", "response.in_progress", "response.completed", "[DONE]"]
|
|
|
|
|
|
def test_responses_sse_non_message_item_added_and_done() -> None:
|
|
resp = {
|
|
"id": "resp_3",
|
|
"status": "completed",
|
|
"output": [
|
|
{
|
|
"type": "function_call",
|
|
"id": "fc_1",
|
|
"call_id": "c1",
|
|
"name": "grep",
|
|
"arguments": "{}",
|
|
}
|
|
],
|
|
"usage": {},
|
|
}
|
|
parsed = _parse(_openai_responses_to_sse(resp))
|
|
types = [p["type"] for p in parsed]
|
|
assert types == [
|
|
"response.created",
|
|
"response.in_progress",
|
|
"response.output_item.added",
|
|
"response.output_item.done",
|
|
"response.completed",
|
|
"[DONE]",
|
|
]
|
|
# The function_call item is preserved whole on added and done.
|
|
done = next(p for p in parsed if p["type"] == "response.output_item.done")
|
|
assert done["item"]["name"] == "grep"
|