As a LangChain user streaming a tool-calling model, I expect each
streamed chunk to expose structured `tool_call_chunk` content blocks so
I can render or process tool calls live, instead of waiting for the
final aggregated message.
This adds `tool_call_streaming` to `ModelProfile` and uses it in the
standard chat-model tool-calling tests. When a model profile opts in,
`test_tool_calling` and `test_tool_calling_async` now validate that at
least one streamed chunk includes a `tool_call_chunk` block via
`content_blocks`, while preserving the existing final-message
validation.
This keeps the contract profile-gated so providers can opt in once their
streaming chunk shape is verified. This PR opts in the providers
verified by smoke testing with straightforward profile coverage: OpenAI,
Anthropic, Fireworks, HuggingFace, OpenRouter, DeepSeek, and xAI. The
generated profile artifacts are refreshed so runtime profiles expose the
new capability flag.
Perplexity Responses also passed the smoke test, but its current profile
data is for the `sonar` family while the Responses smoke path used a
routed model string. That profile strategy is left as follow-up.
MistralAI currently streams `.tool_call_chunks`, but its content-block
translator exposes a complete `tool_call` block instead of
`tool_call_chunk`, so it also stays out of this flag until that
integration is fixed.
The custom VCR serializer pipes the cassette dict through
`yaml.safe_dump`, which raises on stream objects — so any request with
an `io.BytesIO` body (multipart/file-upload endpoints) couldn't be
recorded. A new `_coerce_bytesio` helper walks the cassette and replaces
each `BytesIO` with its raw bytes before dumping.
Scheduled integration runs set `LANGSMITH_TAGS` and `LANGSMITH_METADATA`
in `$GITHUB_ENV` (per #37615), but the LangSmith SDK does not read those
env vars natively, so the tags/metadata were silently dropped. A new
pytest plugin in `langchain-tests` bridges that gap by entering
`langsmith.run_helpers.tracing_context` for the duration of each
session.
`test_no_overrides_DO_NOT_OVERRIDE` only treated an override as valid
when the method itself carried an `@pytest.mark.xfail(reason=...)`.
Overrides that re-parametrize a standard test and xfail only a subset of
cases via `pytest.param(..., marks=pytest.mark.xfail(...))` were
rejected.
Reasoning-emitting chat models return `[reasoning, text]` content blocks
where vanilla models return `[text]`. The shared streaming integration
tests asserted exactly one block, which fails when reasoning blocks are
returned when streaming is otherwise correct.
Relaxed to assert text presence without touching the lifecycle,
`chunk_position`, or `output_version` checks.
Adds a standard unit test so every chat-model integration verifies that
`_get_ls_params` picks up a runtime `model` kwarg instead of always
reporting the constructor default.
During an automated code review of .github/scripts/get_min_versions.py,
the following issue was identified. Set a timeout on get min versions
HTTP calls. Network calls without a timeout can hang a worker
indefinitely. I kept the patch small and re-ran syntax checks after
applying it.
Regression introduced in 8e3c6b109f
The commit changed the return annotation of `with_structured_output`
from `typing.Dict | BaseModel` to `builtins.dict[str, Any] | BaseModel`.
Since `BaseModel` refers to `pydantic.BaseModel (v2)`, but the test
`test_structured_output_pydantic_2_v1` uses `pydantic.v1.BaseModel`,
mypy's `warn_unreachable` setting flags the `isinstance` checks as
unreachable (since a class can't be both a `dict` and a different
`BaseModel` type).
Switching to `builtins.dict[str, Any]` made the type more precise, which
exposed this type incompatibility that was always latent but hidden by
the looser `typing.Dict` annotation.
Use of the fixture `_base_vcr_config` is deprecated with alternative
function `base_vcr_config()`
This way:
* we don't need to import `_base_vcr_config` seen as unused (which leads
to ruff violations PLC0414 and F811)
* we don't need to make a copy since a new dict is created at each
function invocation
Co-authored-by: Mason Daugherty <mason@langchain.dev>
