Repository navigation
Fix XaiStreamedResponse finish_reason mapping for streaming responses - #6814
Conversation
xAI SDK `Response.finish_reason` returns proto enum *names* (e.g. `REASON_STOP`), but the streaming path keyed `_FINISH_REASON_MAP` on lowercase strings (`stop`, `length`, ...\), so it always fell through to the `stop` default. The non-streaming path already used `_FINISH_REASON_PROTO_MAP` keyed on proto ints, so the two paths disagreed on the same response, and streaming users always saw `finish_reason='stop'`, defeating `_agent_graph.py` length diagnostics (IncompleteToolCall and token-limit error). Delete `_FINISH_REASON_MAP` and add a shared `_map_finish_reason` helper that reads the proto int from the final output, returning `None` for empty outputs or `REASON_INVALID` (the proto default meaning not-finished-yet). Extend `_FINISH_REASON_PROTO_MAP` with `REASON_MAX_CONTEXT`->`length` and `REASON_TIME_LIMIT`->`error` so every enum member except `REASON_INVALID` is covered. Non-streaming uses the helper with an `or 'stop'` fallback; streaming only assigns `finish_reason` when the helper returns non-None, so intermediate chunks no longer clobber it with a false `stop`. Closes #6812
ApprovabilityVerdict: Approved 2dc7408 Straightforward bug fix that consolidates finish_reason mapping for streaming and non-streaming xAI responses to use the same proto-based lookup. Limited scope to xai.py model code with comprehensive test coverage added. You can customize Macroscope's approvability policy. Learn more. |
|
Original reporter here (#6812) — thanks for turning this around so fast. The fix matches what I proposed, and I have the same change on a branch locally, so I can point at exactly what the two red checks want. All four
|
Add type: ignore[arg-type] to the three create_response calls in mock_xai.py whose finish_reason arg is a plain str (matching the existing sibling annotations), add pyright: ignore[reportPrivateUsage] to the private _FINISH_REASON_PROTO_MAP access, and add test_xai_map_finish_reason_empty_outputs_returns_none to cover the empty-outputs return None branch in _map_finish_reason (xai.py:166).
Dismissing prior approval to re-evaluate b203d44
Match other providers: unknown finish reasons map to None, not 'stop'. Stream test now actually compares against the non-streamed path.
Dismissing prior approval to re-evaluate 2dc7408
This MR contains the following updates: | Package | Type | Update | Change | OpenSSF | |---|---|---|---|---| | [numpy](https://github.com/numpy/numpy) ([changelog](https://numpy.org/doc/stable/release)) | dependencies | patch | `2.5.2` → `2.5.3` | [](https://securityscorecards.dev/viewer/?uri=github.com/numpy/numpy) | | [openai](https://github.com/openai/openai-python) | dependencies | patch | `2.52.0` → `2.52.1` | [](https://securityscorecards.dev/viewer/?uri=github.com/openai/openai-python) | | [pydantic](https://github.com/pydantic/pydantic) ([changelog](https://docs.pydantic.dev/latest/changelog/)) | dependencies | patch | `2.13.4` → `2.13.5` | [](https://securityscorecards.dev/viewer/?uri=github.com/pydantic/pydantic) | | [pydantic-ai](https://github.com/pydantic/pydantic-ai) ([changelog](https://github.com/pydantic/pydantic-ai/releases)) | dependencies | patch | `2.27.0` → `2.27.1` | [](https://securityscorecards.dev/viewer/?uri=github.com/pydantic/pydantic-ai) | | [types-requests](https://github.com/python/typeshed) ([changelog](https://github.com/typeshed-internal/stub_uploader/blob/main/data/changelogs/requests.md)) | dependencies | patch | `2.33.0.20260712` → `2.33.0.20260906` | [](https://securityscorecards.dev/viewer/?uri=github.com/python/typeshed) | | [uvicorn](https://github.com/Kludex/uvicorn) ([changelog](https://uvicorn.dev/release-notes)) | dependencies | patch | `0.52.3` → `0.52.4` | [](https://securityscorecards.dev/viewer/?uri=github.com/Kludex/uvicorn) | --- ### Release Notes <details> <summary>numpy/numpy (numpy)</summary> ### [`v2.5.3`](https://github.com/numpy/numpy/releases/tag/v2.5.3): (Sep 6, 2026) [Compare Source](numpy/numpy@v2.5.2...v2.5.3) ### NumPy 2.5.3 Release Notes The NumPy 2.5.3 is a patch release that fixes bugs discovered after the 2.5.2 release. Apart from the usual bug and maintenance work, there are a number of StringDType related fixes for problems discovered during the ongoing string work in the main branch. This release supports Python versions 3.12-3.15 #### Changes - Casting a fixed-width byte string array (`np.bytes_`) to `StringDType` now raises `TypeError` when the bytes are not valid UTF-8. Previously the invalid bytes were stored as-is and later caused undefined behavior in string operations. ([gh-32296](numpy/numpy#32296)) - `MaskedArray._fill_value` would become stale when ufuncs that change dtype left the result holding a fill\_value typed for the old dtype. The mismatch was silent until something later called `_check_fill_value`, such as `.view()`, and then a `TypeError` would be raised. Now, when the copied fill\_value is no longer valid for the new dtype, fall back to the default fill\_value for that dtype instead of propagating the stale value. This may raise a `ComplexWarning` if the fill\_value is complex and the new dtype is real. ([gh-32423](numpy/numpy#32423)) #### Contributors A total of 9 people contributed to this release. People with a "+" by their names contributed a patch for the first time. - Charles Harris - Iason Krommydas - James Davies + - Joren Hammudoglu - Maanas Arora - Matti Picus - Nathan Goldbaum - Shikhar Goel + - Yeonho Kim + #### Pull requests merged A total of 27 pull requests were merged for this release. - [#​32235](numpy/numpy#32235): MAINT: Prepare 2.5.x for further development - [#​32289](numpy/numpy#32289): BUG: raise ValueError when reading into record array with references... - [#​32290](numpy/numpy#32290): BUG: avoid uninitialized memory access / NULL-pointer deref in... - [#​32291](numpy/numpy#32291): TYP: fix `np.random.{get,set}_bit_generator` implicit re-exports... - [#​32292](numpy/numpy#32292): BUG: don't assume strides are a multiple of itemsize in stringdtype... - [#​32293](numpy/numpy#32293): CI: fix ccache CC override, add CXX in mac Conda CI ([#​32285](numpy/numpy#32285)) - [#​32303](numpy/numpy#32303): BUG: Fix ref leak in \[convert\_from\_type]{#convert\_from\_type} for custom scalar types... - [#​32304](numpy/numpy#32304): BUG: fix a number of issues around iterators and StringDType... - [#​32326](numpy/numpy#32326): TST: avoid allocating huge tuple of arrays in concatenate test... - [#​32338](numpy/numpy#32338): BUG: avoid possible UB in 'safe' multiplication helpers ([#​32294](numpy/numpy#32294)) - [#​32339](numpy/numpy#32339): MAINT: use `PyObject_` functions instead of raw `PyArray_ ones` ([#​32331](numpy/numpy#32331)) - [#​32378](numpy/numpy#32378): BUG: validate UTF-8 and harden StringDType bounds handling ([#​32296](numpy/numpy#32296)) - [#​32380](numpy/numpy#32380): BUG: fix two error handling mistakes in stringdtype replace loop... - [#​32381](numpy/numpy#32381): BUG: fix visibility annotations for functions in StringDType... - [#​32384](numpy/numpy#32384): MAINT: Update ml\_dtypes pin to 8/21/2026. - [#​32385](numpy/numpy#32385): MAINT: Update numpy/\_core/src/umath/svml - [#​32410](numpy/numpy#32410): MAINT: skip failing cython limited API tests on Cython 3.3.0... - [#​32427](numpy/numpy#32427): BUG: close duplicated file descriptor if fdopen fails ([#​32386](numpy/numpy#32386)) - [#​32428](numpy/numpy#32428): MAINT: add missing space in warning and error messages ([#​32405](numpy/numpy#32405)) - [#​32430](numpy/numpy#32430): BUG: fix error handling in StringDType to fixed-width bytes case... - [#​32441](numpy/numpy#32441): MAINT: Only run nightly BLAS tests on main. - [#​32471](numpy/numpy#32471): BUG: fix memory leak in StringDType creation error path ([#​32470](numpy/numpy#32470)) - [#​32477](numpy/numpy#32477): BUG: fix stale fill\_value after ufuncs change MaskedArray dtype... - [#​32478](numpy/numpy#32478): MAINT: exit deadlock tests quickly on slow hardware ([#​32466](numpy/numpy#32466)) - [#​32481](numpy/numpy#32481): BUG: Backport StringDType byteorder fixes - [#​32506](numpy/numpy#32506): DOC: use static scipy doc site for intershpinx ([#​32503](numpy/numpy#32503)) - [#​32509](numpy/numpy#32509): BUG: fix crash in ufunc.resolve\_dtypes with a Python scalar type... </details> <details> <summary>openai/openai-python (openai)</summary> ### [`v2.52.1`](https://github.com/openai/openai-python/blob/HEAD/CHANGELOG.md#2521-2026-07-31) [Compare Source](openai/openai-python@v2.52.0...v2.52.1) Full Changelog: [v2.52.0...v2.52.1](openai/openai-python@v2.52.0...v2.52.1) ##### Chores - **ci:** pin setup-uv v5 to its underlying commit ([#​3560](openai/openai-python#3560)) ([cbdc98b](openai/openai-python@cbdc98b)) </details> <details> <summary>pydantic/pydantic (pydantic)</summary> ### [`v2.13.5`](https://github.com/pydantic/pydantic/releases/tag/v2.13.5) [Compare Source](pydantic/pydantic@v2.13.4...v2.13.5) #### v2.13.5 (2026-08-28) ##### What's Changed ##### Fixes - Allow reuse of validators when plugins are set by [@​Viicos](https://github.com/Viicos) in [#​13535](pydantic/pydantic#13535) - Fix missing GC traversal on some `pydantic-core` struct fields by [@​Viicos](https://github.com/Viicos) in [#​13624](pydantic/pydantic#13624) - Fix missing GC traversal in `pydantic-core` for `GeneralFieldsSerializer` by [@​Viicos](https://github.com/Viicos) in [#​13629](pydantic/pydantic#13629) - Count validated model fields once in smart unions by [@​tamird](https://github.com/tamird) in [#​13731](pydantic/pydantic#13731) </details> <details> <summary>pydantic/pydantic-ai (pydantic-ai)</summary> ### [`v2.27.1`](https://github.com/pydantic/pydantic-ai/releases/tag/v2.27.1): (2026-08-10) [Compare Source](pydantic/pydantic-ai@v2.27.0...v2.27.1) ##### 🛡️ Security This release fixed an information-disclosure issue: retry-prompt content (validation feedback sent back to the model, which can quote invalid values from its output) was not redacted by `InstrumentationSettings(include_content=False)` when the retry was not tied to a tool call. Now disclosed as [GHSA-3gh4-cghq-f8v4](GHSA-3gh4-cghq-f8v4) (low). Fixed here in `2.27.1` ([#​7357](pydantic/pydantic-ai#7357)); v1 users should upgrade to `1.107.4` or later. <!-- Release notes generated using configuration in .github/release.yml at main --> #### What's Changed ##### 🐛 Bug Fixes - Restore tool spans for failed argument validation by [@​adtyavrdhn](https://github.com/adtyavrdhn) in [#​6601](pydantic/pydantic-ai#6601) - Fix `XaiStreamedResponse` finish\_reason mapping for streaming responses by [@​pydanty](https://github.com/pydanty)\[bot] in [#​6814](pydantic/pydantic-ai#6814) - Point offline web UI hosting at the self-contained chat UI build by [@​dsfaccini](https://github.com/dsfaccini) in [#​7349](pydantic/pydantic-ai#7349) - Allow adaptive thinking with Tool Output and forced tool choice on Anthropic by [@​pydanty](https://github.com/pydanty)\[bot] in [#​7200](pydantic/pydantic-ai#7200) - Gate `RetryPromptPart` OpenTelemetry content on `include_content` by [@​sean-kim05](https://github.com/sean-kim05) in [#​7357](pydantic/pydantic-ai#7357) **Full Changelog**: <pydantic/pydantic-ai@v2.27.0...v2.27.1> </details> <details> <summary>Kludex/uvicorn (uvicorn)</summary> ### [`v0.52.4`](https://github.com/Kludex/uvicorn/releases/tag/0.52.4): Version 0.52.4 [Compare Source](Kludex/uvicorn@0.52.3...0.52.4) ##### Fixed - Remove duplicate `Date` headers from accepted WebSocket handshakes with `websockets-sansio` ([#​3078](Kludex/uvicorn#3078)) **Full Changelog**: <Kludex/uvicorn@0.52.3...0.52.4> </details> --- - [ ] <!-- rebase-check -->If you want to rebase/retry this MR, check this box --- This MR has been generated by [Mend Renovate CLI](https://github.com/renovatebot/renovate). <!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiI0NC4zOS4yIiwidXBkYXRlZEluVmVyIjoiNDQuOTAuMiIsInRhcmdldEJyYW5jaCI6Im1haW4iLCJsYWJlbHMiOlsiZGVwZW5kZW5jaWVzIiwicmVub3ZhdGUiXX0=--> See merge request swiss-armed-forces/cyber-command/cea/loom!769 Co-authored-by: Loom MR Pipeline Trigger <group_103951964_bot_9504bb8dead6d4e406ad817a607f24be@noreply.gitlab.com> Co-authored-by: shrewd-laidback palace <shrewd-laidback-palace-736-c41-2c1-e464fc974@swiss-armed-forces-open-source.ch>
Closes #6812
xAI SDK
Response.finish_reasonreturns proto enum names (e.g.REASON_STOP), but the streaming path inXaiStreamedResponse._update_response_statekeyed_FINISH_REASON_MAPon lowercase strings (stop,length, …), so it always fell through to thestopdefault. The non-streaming path (XaiModel._process_response) already used_FINISH_REASON_PROTO_MAPkeyed on proto ints, so the two paths disagreed on the same response. Streaming users therefore always sawfinish_reason='stop', defeating the_agent_graph.pyfinish_reason == 'length'diagnostics (IncompleteToolCalldetection and the token-limit-exceeded error).Fix
_FINISH_REASON_MAP._FINISH_REASON_PROTO_MAPwithREASON_MAX_CONTEXT→'length'andREASON_TIME_LIMIT→'error'so every proto enum member exceptREASON_INVALIDis covered._map_finish_reason(response)helper that reads the proto int from the final output, returningNonefor empty outputs orREASON_INVALID(the proto default meaning not-finished-yet)._map_finish_reason(response) or 'stop'; streaming only assignsfinish_reasonwhen the helper returns non-None, so intermediate chunks (REASON_INVALID) no longer clobber it with a false'stop'.REASON_MAX_CONTEXT→'length'follows the same class as the existingREASON_MAX_LEN→'length': a context-full truncation surfaces the sameIncompleteToolCall/token-limit diagnostics as a max-len truncation.Tests
test_xai_stream_finish_reason_matches_non_stream— parametrized acrossstop/length/tool_call/error, asserts the streamedModelResponse.finish_reasonagrees with the non-streamed value.test_xai_stream_intermediate_chunks_keep_finish_reason_unset— intermediate chunks (REASON_INVALID) keepfinish_reason=None; only the final chunk sets it.test_xai_finish_reason_proto_map_covers_all_enum_members— guards that everyFinishReasonproto enum member exceptREASON_INVALIDis mapped.mock_xai.pyupdated so chunk helpers passNone(→REASON_INVALID) instead of coercing to'stop', andcreate_responseacceptsFinishReason | None.Checklist
💰 Run usage: 702,091 tokens, 32 model requests (est. cost $0.2560)
pydanty-pr-openerpydanty-test-runner💰 Run usage: 1,696,310 tokens, 75 model requests (est. cost $0.7186)
pydanty-pr-openerpydanty-test-runner