# What does this PR do?
- when create vector store is called without chunk strategy, we actually
the strategy used so that the value is persisted instead of
strategy='None'
## Test Plan
updated tests
## What does this PR do?
The starter distribution now comes with all the required packages to
support persistent stores—like the agent store, metadata, and
inference—using PostgreSQL. Users can enable PostgreSQL support by
setting the `ENABLE_POSTGRES_STORE=1` environment variable.
This PR consolidates the functionality from the removed `postgres-demo`
distribution into the starter distribution, reducing maintenance
overhead.
**Closes: #2619**
**Supersedes: #2851** (rebased and updated)
## Changes Made
1. **Added PostgreSQL support to starter distribution**
- New `run-with-postgres-store.yaml` configuration
- Automatic config switching via `ENABLE_POSTGRES_STORE` environment
variable
- Removed separate `postgres-demo` distribution
2. **Updated to new build system**
- Integrated postgres switching logic into Containerfile entrypoint
- Uses new `storage_backends` and `storage_stores` API
- Properly configured both PostgreSQL KV store and SQL store
3. **Updated dependencies**
- Added `psycopg2-binary` and `asyncpg` to starter distribution
- All postgres-related dependencies automatically included
## How to Use
### With Docker (PostgreSQL):
```bash
docker run \
-e ENABLE_POSTGRES_STORE=1 \
-e POSTGRES_HOST=your_postgres_host \
-e POSTGRES_PORT=5432 \
-e POSTGRES_DB=llamastack \
-e POSTGRES_USER=llamastack \
-e POSTGRES_PASSWORD=llamastack \
-e OPENAI_API_KEY=your_key \
llamastack/distribution-starter
```
### PostgreSQL environment variables:
- `POSTGRES_HOST`: Postgres host (default: `localhost`)
- `POSTGRES_PORT`: Postgres port (default: `5432`)
- `POSTGRES_DB`: Postgres database name (default: `llamastack`)
- `POSTGRES_USER`: Postgres username (default: `llamastack`)
- `POSTGRES_PASSWORD`: Postgres password (default: `llamastack`)
## Test Plan
All pre-commit hooks pass (mypy, ruff, distro-codegen)
`llama stack list-deps starter` confirms psycopg2-binary is included
Storage configuration correctly uses PostgreSQL backends
Container builds successfully with postgres support
## Credits
Original work by @leseb in #2851. Rebased and updated by @r-bit-rry to
work with latest main.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Sébastien Han @leseb
---------
Signed-off-by: Sébastien Han <seb@redhat.com>
Co-authored-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
list-deps takes positional args OR things like --providers
the issue with this, is that these args need to be optional since by
nature, one or the other can be specified.
add a check to list-deps that checks `if not args.providers and not
args.config`. If this is true, help is printed and we exit.
resolves#4075
## Test Plan
before:
```
╰─ llama stack list-deps
Traceback (most recent call last):
File "/Users/charliedoern/projects/Documents/llama-stack/venv/bin/llama", line 10, in <module>
sys.exit(main())
^^^^^^
File "/Users/charliedoern/projects/Documents/llama-stack/src/llama_stack/cli/llama.py", line 52, in main
parser.run(args)
File "/Users/charliedoern/projects/Documents/llama-stack/src/llama_stack/cli/llama.py", line 43, in run
args.func(args)
File "/Users/charliedoern/projects/Documents/llama-stack/src/llama_stack/cli/stack/list_deps.py", line 51, in _run_stack_list_deps_command
return run_stack_list_deps_command(args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/charliedoern/projects/Documents/llama-stack/src/llama_stack/cli/stack/_list_deps.py", line 135, in run_stack_list_deps_command
normal_deps, special_deps, external_provider_dependencies = get_provider_dependencies(build_config)
^^^^^^^^^^^^
UnboundLocalError: cannot access local variable 'build_config' where it is not associated with a value
```
after:
```
╰─ llama stack list-deps
usage: llama stack list-deps [-h] [--providers PROVIDERS] [--format {uv,deps-only}] [config | distro]
list the dependencies for a llama stack distribution
positional arguments:
config | distro Path to config file to use or name of known distro (llama stack list for a list). (default: None)
options:
-h, --help show this help message and exit
--providers PROVIDERS
sync dependencies for a list of providers and only those providers. This list is formatted like: api1=provider1,api2=provider2. Where there can be multiple
providers per API. (default: None)
--format {uv,deps-only}
Output format: 'uv' shows shell commands, 'deps-only' shows just the list of dependencies without `uv` (default) (default: deps-only)
```
Signed-off-by: Charlie Doern <cdoern@redhat.com>
# What does this PR do?
It avoids model_limit KeyError while trying to get embedding models for
Watsonx
<!-- If resolving an issue, uncomment and update the line below -->
Closes https://github.com/llamastack/llama-stack/issues/4059
## Test Plan
<!-- Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.* -->
Start server with watsonx distro:
```bash
llama stack list-deps watsonx | xargs -L1 uv pip install
uv run llama stack run watsonx
```
Run
```python
client = LlamaStackClient(base_url=base_url)
client.models.list()
```
Check if there is any embedding model available (currently there is not
a single one)
# What does this PR do?
1. Make telemetry tests as easy as possible for users by expanding the
`SpanStub` data class and creating the `MetricStub` dataclass as a way
to consistently marshal telemetry data in test fixtures and unmarshal
and handle it in tests.
2. Structure server and client tests to always follow the same standards
for consistent testing experience by using the `SpanStub` and
`MetricStub` data class objects.
3. Enable Metrics Testing for completions endpoint
4. Correct token metrics to use histograms instead of counts to capture
tokens per request rather than a cumulative count of tokens over the
lifecycle of the server.
## Test Plan
These are tests
# What does this PR do?
Fixes issue #3922 where `llama stack list` only showed distributions
after they were run. This PR makes the command show all available
distributions immediately on a fresh install.
Closes#3922
## Changes
- **Updated `_get_distribution_dirs()`** to discover both built-in and
built distributions:
- Built-in distributions from `src/llama_stack/distributions/` (e.g.,
starter, nvidia, dell)
- Built distributions from `~/.llama/distributions`
- **Added a "Source" column** to distinguish between "built-in" and
"built" distributions
- **Built distributions override built-in ones** with the same name
(expected behavior)
- **Updated config file detection logic** to handle both naming
conventions:
- Built-in: `build.yaml` and `run.yaml`
- Built: `{name}-build.yaml` and `{name}-run.yaml`
## Test Plan
### Unit Tests
Added comprehensive unit tests in
`tests/unit/distribution/test_stack_list.py`:
```bash
uv run pytest tests/unit/distribution/test_stack_list.py -v
```
**Result**: ✅ All 8 tests pass
- `test_builtin_distros_shown_without_running` - Verifies the core fix
for issue #3922
- `test_builtin_and_built_distros_shown_together` - Ensures both types
are shown
- `test_built_distribution_overrides_builtin` - Tests override behavior
- `test_empty_distributions` - Edge case handling
- `test_config_files_detection_builtin` - Config file detection for
built-in distros
- `test_config_files_detection_built` - Config file detection for built
distros
- `test_llamastack_prefix_stripped` - Name normalization
- `test_hidden_directories_ignored` - Filters hidden directories
### Manual Testing
**Before the fix** (simulated with empty `~/.llama/distributions`):
```bash
$ llama stack list
No stacks found in ~/.llama/distributions
```
**After the fix**:
```bash
$ llama stack list
┏━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Stack Name ┃ Source ┃ Path ┃ Build Config ┃ Run Config ┃
┡━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ ci-tests │ built-in │ /path/to/src/... │ Yes │ Yes │
│ dell │ built-in │ /path/to/src/... │ Yes │ Yes │
│ meta-reference-g… │ built-in │ /path/to/src/... │ Yes │ Yes │
│ nvidia │ built-in │ /path/to/src/... │ Yes │ Yes │
│ open-benchmark │ built-in │ /path/to/src/... │ Yes │ Yes │
│ postgres-demo │ built-in │ /path/to/src/... │ Yes │ Yes │
│ starter │ built-in │ /path/to/src/... │ Yes │ Yes │
│ starter-gpu │ built-in │ /path/to/src/... │ Yes │ Yes │
│ watsonx │ built-in │ /path/to/src/... │ Yes │ Yes │
└───────────────────┴──────────┴───────────────────┴──────────────┴────────────┘
```
**After running a distribution**:
```bash
$ llama stack run starter # Creates ~/.llama/distributions/starter
$ llama stack list
┏━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Stack Name ┃ Source ┃ Path ┃ Build Config ┃ Run Config ┃
┡━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ ... │ built-in │ ... │ Yes │ Yes │
│ starter │ built │ ~/.llama/distri… │ No │ No │
│ ... │ built-in │ ... │ Yes │ Yes │
└───────────────────┴──────────┴───────────────────┴──────────────┴────────────┘
```
Note how `starter` now shows as "built" and points to
`~/.llama/distributions`, overriding the built-in version.
## Breaking Changes
**No breaking changes** - This is a bug fix that improves user
experience with minimal risk:
- No programmatic parsing of output found in the codebase
- Table format is clearly for human consumption
- The new "Source" column helps users understand where distributions
come from
- The behavior change is exactly what users expect (seeing all available
distributions)
---------
Co-authored-by: Claude <noreply@anthropic.com>
# What does this PR do?
These were maybe be included in the webmethod?
The unit test was pointless too since the request was never used
anywhere?
This shouldn't be in the API definition, if we never consume it.
## Test Plan
CI with pre-commit on OpenAPI spec generation.
Signed-off-by: Sébastien Han <seb@redhat.com>
RAG aka file search is implemented via the Responses API by specifying
the file-search tool. The backend implementation remains unchanged. This
PR merely removes the directly exposed API surface which allowed users
to directly perform searches from the client.
This facility is now available via the `client.vector_store.search()`
OpenAI compatible API.
- Removes the deprecated agents (sessions and turns) API that was marked
alpha in 0.3.0
- Cleans up unused imports and orphaned types after the API removal
- Removes `SessionNotFoundError` and `AgentTurnInputType` which are no
longer needed
The agents API is completely superseded by the Responses + Conversations
APIs, and the client SDK Agent class already uses those implementations.
Corresponding client-side PR:
https://github.com/llamastack/llama-stack-client-python/pull/295
This PR removes all routes which we had marked deprecated for the 0.3.0
release.
This includes:
- all the `/v1/openai/v1/` routes (the corresponding /v1 routes still
exist of course)
- the /agents API (which is superseded completely by Responses +
Conversations)
- several alpha routes which had a "v1" route to aide transitioning to
"v1alpha"
This is the corresponding client-python change:
https://github.com/llamastack/llama-stack-client-python/pull/294
The llama-stack-client now uses /`v1/openai/v1/models` which returns
OpenAI-compatible model objects with 'id' and 'custom_metadata' fields
instead of the Resource-style 'identifier' field. Updated api_recorder
to handle the new endpoint and modified tests to access model metadata
appropriately. Deleted stale model recordings for re-recording.
**NOTE: CI will be red on this one since it is dependent on
https://github.com/llamastack/llama-stack-client-python/pull/291/files
landing. I verified locally that it is green.**
# What does this PR do?
This API hasn't received any traction and close to zero interest from
the community. Let's revisit in the future if things change.
Signed-off-by: Sébastien Han <seb@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
We need to remove `/v1/openai/v1` paths shortly. There is one trouble --
our current `/v1/openai/v1/models` endpoint provides different data than
`/v1/models`. Unfortunately our tests target the latter (llama-stack
customized) behavior. We need to get to true OpenAI compatibility.
This is step 1: adding `custom_metadata` field to `OpenAIModel` that
includes all the extra stuff we add in the native `/v1/models` response.
This can be extracted on the consumer end by look at
`__pydantic_extra__` or other similar fields.
This PR:
- Adds `custom_metadata` field to `OpenAIModel` class in
`src/llama_stack/apis/models/models.py`
- Modified `openai_list_models()` in
`src/llama_stack/core/routing_tables/models.py` to populate
custom_metadata
Next Steps
1. Update stainless client to use `/v1/openai/v1/models` instead of
`/v1/models`
2. Migrate tests to read from `custom_metadata`
3. Remove `/v1/openai/v1/` prefix entirely and consolidate to single
`/v1/models` endpoint
Fixes race condition causing "database is locked" errors during
concurrent writes to SQLite, particularly in streaming responses with
guardrails where multiple inference calls write simultaneously.
Enable Write-Ahead Logging (WAL) mode for SQLite which allows multiple
concurrent readers and one writer without blocking. Set busy_timeout to
5s so SQLite retries instead of failing immediately. Remove the logic
that disabled write queues for SQLite since WAL mode eliminates the
locking issues that prompted disabling them.
Fixes: test_output_safety_guardrails_safe_content[stream=True] flake
# What does this PR do?
llama stack run --providers takes a list of providers in the format of
api1=provider1,api2=provider2
this allows users to run with a simple list of providers.
given the architecture of `create_app`, this run config needs to be
written to disk. use ~/.llama/distribution/providers-run/run.yaml each
time for consistency
resolves#3956
## Test Plan
new unit tests to ensure --providers.
Signed-off-by: Charlie Doern <cdoern@redhat.com>
# What does this PR do?
Allow filtering for v1alpha, v1beta, deprecated and v1. Backward
incompatible change since by default it only returns v1 apis now.
## Test Plan
added unit test
# What does this PR do?
Add rerank API for NVIDIA Inference Provider.
<!-- If resolving an issue, uncomment and update the line below -->
Closes#3278
## Test Plan
Unit test:
```
pytest tests/unit/providers/nvidia/test_rerank_inference.py
```
Integration test:
```
pytest -s -v tests/integration/inference/test_rerank.py --stack-config="inference=nvidia" --rerank-model=nvidia/nvidia/nv-rerankqa-mistral-4b-v3 --env NVIDIA_API_KEY="" --env NVIDIA_BASE_URL="https://integrate.api.nvidia.com"
```
# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
This PR fixes the handling of the external_providers_dir configuration
field to align with its ongoing deprecation, in favor of the provider
`module` specification approach.
It addresses the issue in #3950, where using the default provided
run.yaml config resulted in the `external_providers_dir` parameter being
set to the literal string `None`, and crashing the llama-stack server
when starting.
<!-- If resolving an issue, uncomment and update the line below -->
Closes#3950
## Test Plan
<!-- Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.* -->
- Built a new container image from `podman build . -f
containers/Containerfile --build-arg DISTRO_NAME=starter --tag
llama-stack:starter`
- Tested it locally with `podman run -it localhost/llama-stack:starter`
- Tested it on an OpenShift 4.19 cluster, deployed via the
llama-stack-k8s-operator.
Signed-off-by: Doug Edgar <dedgar@redhat.com>
`mypy` became very slow for the common path. This can make local
pre-commit runs very slow. Let's restore that.
- restore fast mirrors-mypy hook for local runs
- add optional mypy-full hook and docs so devs can match CI
- run full mypy in CI with a hint when failures occur
### Test Plan
- uv run pre-commit run mypy --all-files
- uv run pre-commit run mypy-full --hook-stage manual --all-files
- uv run --group dev --group type_checking mypy
# What does this PR do?
chunk_id in the Chunk class executes actual logic to compute a chunk ID.
This sort of logic should not live in the API spec.
Instead, the providers should be in charge of calling generate_chunk_id,
and pass it to `Chunk`.
this removes the incorrect dependency between Provider impl and API impl
Signed-off-by: Charlie Doern <cdoern@redhat.com>
## Summary
When users provide API keys via `X-LlamaStack-Provider-Data` header,
`models.list()` now returns models they can access from those providers,
not just pre-registered models from the registry.
This complements the routing fix from f88416ef8 which enabled inference
calls with `provider_id/model_id` format for unregistered models. Users
can now discover which models are available to them before making
inference requests.
The implementation reuses
`NeedsRequestProviderData.get_request_provider_data()` to validate
credentials, then dynamically fetches models from providers without
caching them since they're user-specific. Registry models take
precedence to respect any pre-configured aliases.
## Test Script
```python
#!/usr/bin/env python3
import json
import os
from openai import OpenAI
# Test 1: Without provider_data header
client = OpenAI(base_url="http://localhost:8321/v1/openai/v1", api_key="dummy")
models = client.models.list()
anthropic_without = [m.id for m in models.data if m.id and "anthropic" in m.id]
print(f"Without header: {len(models.data)} models, {len(anthropic_without)} anthropic")
# Test 2: With provider_data header containing Anthropic API key
anthropic_api_key = os.environ["ANTHROPIC_API_KEY"]
client_with_key = OpenAI(
base_url="http://localhost:8321/v1/openai/v1",
api_key="dummy",
default_headers={
"X-LlamaStack-Provider-Data": json.dumps({"anthropic_api_key": anthropic_api_key})
}
)
models_with_key = client_with_key.models.list()
anthropic_with = [m.id for m in models_with_key.data if m.id and "anthropic" in m.id]
print(f"With header: {len(models_with_key.data)} models, {len(anthropic_with)} anthropic")
print(f"Anthropic models: {anthropic_with}")
assert len(anthropic_with) > len(anthropic_without), "Should have more anthropic models with API key"
print("\n✓ Test passed!")
```
Run with a stack that has Anthropic provider configured (but without API
key in config):
```bash
ANTHROPIC_API_KEY=sk-ant-... python test_provider_data_models.py
```
## Summary
Fixes all mypy type errors in `providers/inline/agents/meta_reference/`
and removes exclusions from pyproject.toml.
## Changes
- Fix type annotations for Safety API message parameters
(OpenAIMessageParam)
- Add Action enum usage in access control checks
- Correct method signatures to match API supertype (parameter ordering)
- Handle optional return types with proper None checks
- Remove 3 meta_reference exclusions from mypy config
**Files fixed:** 25 errors across 3 files (safety.py, persistence.py,
agents.py)
## Summary
Resolves all mypy errors in meta reference agent OpenAI responses
implementation by adding proper type narrowing, None checks, and
Sequence type support.
## Changes
- Fixed streaming.py, openai_responses.py, utils.py, tool_executor.py,
agent_instance.py
- Added Sequence type support to schema generator (ensures correct JSON
schema generation)
- Applied union type narrowing and None checks throughout
## Test plan
- All modified files pass mypy type checking (0 errors)
- Schema generator produces correct `type: array` for Sequence types
---------
Co-authored-by: Claude <noreply@anthropic.com>
Error fixes in Agents implementation (`meta-reference` provider) --
adding proper type annotations and using type narrowing for optional
attributes. Essentially a bunch of `if x and x_foo := getattr(x, "foo")`
instead of `x.foo` directly
Part of ongoing mypy remediation effort.
---------
Co-authored-by: Claude <noreply@anthropic.com>
Remove unused methods that became obsolete after d266c59c: o
_compute_and_log_token_usage
o _count_tokens
o stream_tokens_and_compute_metrics
o count_tokens_and_compute_metrics
These methods are no longer referenced anywhere in the codebase
following the removal of deprecated inference.chat_completion
implementations.
---------
Signed-off-by: Derek Higgins <derekh@redhat.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
# What does this PR do?
- Adds OpenAI files provider
- Note that file content retrieval is pretty limited by `purpose`
https://community.openai.com/t/file-uploads-error-why-can-t-i-download-files-with-purpose-user-data/1357013?utm_source=chatgpt.com
## Test Plan
Modify run yaml to use openai files provider:
```
files:
- provider_id: openai
provider_type: remote::openai
config:
api_key: ${env.OPENAI_API_KEY:=}
metadata_store:
backend: sql_default
table_name: openai_files_metadata
# Then run files tests
❯ uv run --no-sync ./scripts/integration-tests.sh --stack-config server:ci-tests --inference-mode replay --setup ollama --suite base --pattern test_files
```
This PR enables routing of fully qualified model IDs of the form
`provider_id/model_id` even when the models are not registered with the
Stack.
Here's the situation: assume a remote inference provider which works
only when users provide their own API keys via
`X-LlamaStack-Provider-Data` header. By definition, we cannot list
models and hence update our routing registry. But because we _require_ a
provider ID in the models now, we can identify which provider to route
to and let that provider decide.
Note that we still try to look up our registry since it may have a
pre-registered alias. Just that we don't outright fail when we are not
able to look it up.
Also, updated inference router so that the responses have the _exact_
model that the request had.
## Test Plan
Added an integration test
Closes#3929
---------
Co-authored-by: ehhuang <ehhuang@users.noreply.github.com>
Adds type stubs and fixes mypy errors for better type coverage.
Changes:
- Added type_checking dependency group with type stubs (torchtune, trl,
etc.)
- Added lm-format-enforcer to pre-commit hook
- Created HFAutoModel Protocol for type-safe HuggingFace model handling
- Added mypy.overrides for untyped libraries (torchtune, fairscale,
etc.)
- Fixed type issues in post-training providers, databricks, and
api_recorder
Note: ~1,200 errors remain in excluded files (see pyproject.toml exclude
list).
---------
Co-authored-by: Claude <noreply@anthropic.com>
## Summary
- Fix OpenAI SDK NotGiven/Omit type mismatches in embeddings calls
- Fix incorrect OpenAIChatCompletionChunk import in vllm provider
- Refactor to avoid type:ignore comments by using conditional kwargs
## Changes
**openai_mixin.py (9 errors fixed):**
- Build kwargs conditionally for embeddings.create() to avoid
NotGiven/Omit mismatch
- Only include parameters when they have actual values (not None)
**gemini.py (9 errors fixed):**
- Apply same conditional kwargs pattern
- Add missing Any import
**vllm.py (2 errors fixed):**
- Use correct OpenAIChatCompletionChunk from llama_stack.apis.inference
- Remove incorrect alias from openai package
## Technical Notes
The OpenAI SDK has a type system quirk where `NOT_GIVEN` has type
`NotGiven` but parameter signatures expect `Omit`. By only passing
parameters with actual values, we avoid this mismatch entirely without
needing `# type: ignore` comments.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude <noreply@anthropic.com>
Fixes mypy type errors in provider utilities and testing infrastructure:
- `mcp.py`: Cast incompatible client types, wrap image data properly
- `batches.py`: Rename walrus variable to avoid shadowing
- `api_recorder.py`: Use cast for Pydantic field annotation
No functional changes.
---------
Co-authored-by: Claude <noreply@anthropic.com>
## Summary
Fixes mypy type errors across 4 model implementation files (Phase 2d of
mypy suppression removal plan):
- `src/llama_stack/models/llama/llama3/multimodal/image_transform.py`
(10 errors fixed)
- `src/llama_stack/models/llama/checkpoint.py` (2 errors fixed)
- `src/llama_stack/models/llama/hadamard_utils.py` (1 error fixed)
- `src/llama_stack/models/llama/llama3/multimodal/encoder_utils.py` (1
error fixed)
## Changes
### image_transform.py
- Fixed return type annotation for `find_supported_resolutions` from
`Tensor` to `list[tuple[int, int]]`
- Fixed parameter and return type annotations for
`resize_without_distortion` from `Tensor` to `Image.Image`
- Resolved variable shadowing by using separate names:
`possible_resolutions_list` for the list and
`possible_resolutions_tensor` for the tensor
### checkpoint.py
- Replaced deprecated `torch.BFloat16Tensor` and
`torch.cuda.BFloat16Tensor` with
`torch.set_default_dtype(torch.bfloat16)`
- Fixed variable shadowing by renaming numpy array to `ckpt_paths_array`
to distinguish from the parameter `ckpt_paths: list[Path]`
### hadamard_utils.py
- Added `isinstance` assertion to narrow type from `nn.Module` to
`nn.Linear` before accessing `in_features` attribute
### encoder_utils.py
- Fixed variable shadowing by using `masks_list` for list accumulation
and `masks` for the final Tensor result
## Test plan
- Verified all files pass mypy type checking (only optional dependency
import warnings remain)
- No functional changes - only type annotations and variable naming
improvements
Stacks on PR #3933
Co-authored-by: Claude <noreply@anthropic.com>
Fixes mypy type errors in OpenTelemetry integration:
- Add type aliases for AttributeValue and Attributes
- Add helper to filter None values from attributes (OpenTelemetry
doesn't accept None)
- Cast metric and tracer objects to proper types
- Update imports after refactoring
No functional changes.
# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
This PR is responsible for making changes to Responses API scheme to
introduce OpenAI compatible prompts there. Change to the API only,
therefore currently no implementation at all. However, the follow up PR
with actual implementation will be submitted after current PR lands.
The need of this functionality was initiated in #3514.
> Note, #3514 is divided on three separate PRs. Current PR is the second
of three.
<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->
## Test Plan
<!-- Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.* -->
CI
## Summary
- `preserve_contexts_async_generator` left `PROVIDER_DATA_VAR` (and
other context vars) populated after a streaming generator completed on
HEAD~1, so the asyncio context for request N+1 started with request N's
provider payload.
- FastAPI dependencies and middleware execute before
`request_provider_data_context` rebinds the header data, meaning
auth/logging hooks could observe a prior tenant's credentials or treat
them as authenticated. Traces and any background work that inspects the
context outside the `with` block leak as well—this is a real security
regression, not just a CLI artifact.
- The wrapper now restores each tracked `ContextVar` to the value it
held before the iteration (falling back to clearing when necessary)
after every yield and when the generator terminates, so provider data is
wiped while callers that set their own defaults keep them.
## Test Plan
- `uv run pytest tests/unit/core/test_provider_data_context.py -q`
- `uv run pytest tests/unit/distribution/test_context.py -q`
Both suites fail on HEAD~1 and pass with this change.
