# What does this PR do?
Introduces two main fixes to enhance the stability of Responses API when
dealing with tool calling responses and structured outputs.
### Changes Made
1. It added OpenAIResponseOutputMessageMCPCall and ListTools to
OpenAIResponseInput but
https://github.com/llamastack/llama-stack/pull/3810 got merge that did
the same in a different way. Still this PR does it in a way that keep
the sync between OpenAIResponsesOutput and the allowed objects in
OpenAIResponseInput.
2. Add protection in case self.ctx.response_format does not have type
attribute
BREAKING CHANGE: OpenAIResponseInput now uses OpenAIResponseOutput union
type.
This is semantically equivalent - all previously accepted types are
still supported
via the OpenAIResponseOutput union. This improves type consistency and
maintainability.
# What does this PR do?
Clean up telemetry code since the telemetry API has been remove.
- moved telemetry files out of providers to core
- removed from Api
## Test Plan
❯ OTEL_SERVICE_NAME=llama_stack
OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318 uv run llama stack run
starter
❯ curl http://localhost:8321/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-4o-mini",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'
-> verify traces in Grafana
CI
# What does this PR do?
https://platform.openai.com/docs/api-reference/moderations supports
optional model parameter.
This PR adds support for using moderations API with model=None if a
default shield id is provided via safety config.
## Test Plan
added tests
manual test:
```
> SAFETY_MODEL='together/meta-llama/Llama-Guard-4-12B' uv run llama stack run starter
> curl http://localhost:8321/v1/moderations \
-H "Content-Type: application/json" \
-d '{
"input": [
"hello"
]
}'
```
Our unit test outputs are filled with all kinds of obscene logs. This
makes it really hard to spot real issues quickly. The problem is that
these logs are necessary to output at the given logging level when the
server is operating normally. It's just that we don't want to see some
of them (especially the noisy ones) during tests.
This PR begins the cleanup. We pytest's caplog fixture to for
suppression.
Bumps [openai](https://github.com/openai/openai-python) from 1.107.0 to
2.5.0.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/openai/openai-python/releases">openai's
releases</a>.</em></p>
<blockquote>
<h2>v2.5.0</h2>
<h2>2.5.0 (2025-10-17)</h2>
<p>Full Changelog: <a
href="https://github.com/openai/openai-python/compare/v2.4.0...v2.5.0">v2.4.0...v2.5.0</a></p>
<h3>Features</h3>
<ul>
<li><strong>api:</strong> api update (<a
href="8b280d57d6">8b280d5</a>)</li>
</ul>
<h3>Chores</h3>
<ul>
<li>bump <code>httpx-aiohttp</code> version to 0.1.9 (<a
href="67f2f0afe5">67f2f0a</a>)</li>
</ul>
<h2>v2.4.0</h2>
<h2>2.4.0 (2025-10-16)</h2>
<p>Full Changelog: <a
href="https://github.com/openai/openai-python/compare/v2.3.0...v2.4.0">v2.3.0...v2.4.0</a></p>
<h3>Features</h3>
<ul>
<li><strong>api:</strong> Add support for gpt-4o-transcribe-diarize on
audio/transcriptions endpoint (<a
href="bdbe9b8f44">bdbe9b8</a>)</li>
</ul>
<h3>Chores</h3>
<ul>
<li>fix dangling comment (<a
href="da14e99606">da14e99</a>)</li>
<li><strong>internal:</strong> detect missing future annotations with
ruff (<a
href="2672b8f072">2672b8f</a>)</li>
</ul>
<h2>v2.3.0</h2>
<h2>2.3.0 (2025-10-10)</h2>
<p>Full Changelog: <a
href="https://github.com/openai/openai-python/compare/v2.2.0...v2.3.0">v2.2.0...v2.3.0</a></p>
<h3>Features</h3>
<ul>
<li><strong>api:</strong> comparison filter in/not in (<a
href="aa49f626a6">aa49f62</a>)</li>
</ul>
<h3>Chores</h3>
<ul>
<li><strong>package:</strong> bump jiter to >=0.10.0 to support
Python 3.14 (<a
href="https://redirect.github.com/openai/openai-python/issues/2618">#2618</a>)
(<a
href="aa445cab5c">aa445ca</a>)</li>
</ul>
<h2>v2.2.0</h2>
<h2>2.2.0 (2025-10-06)</h2>
<p>Full Changelog: <a
href="https://github.com/openai/openai-python/compare/v2.1.0...v2.2.0">v2.1.0...v2.2.0</a></p>
<h3>Features</h3>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/openai/openai-python/blob/main/CHANGELOG.md">openai's
changelog</a>.</em></p>
<blockquote>
<h2>2.5.0 (2025-10-17)</h2>
<p>Full Changelog: <a
href="https://github.com/openai/openai-python/compare/v2.4.0...v2.5.0">v2.4.0...v2.5.0</a></p>
<h3>Features</h3>
<ul>
<li><strong>api:</strong> api update (<a
href="8b280d57d6">8b280d5</a>)</li>
</ul>
<h3>Chores</h3>
<ul>
<li>bump <code>httpx-aiohttp</code> version to 0.1.9 (<a
href="67f2f0afe5">67f2f0a</a>)</li>
</ul>
<h2>2.4.0 (2025-10-16)</h2>
<p>Full Changelog: <a
href="https://github.com/openai/openai-python/compare/v2.3.0...v2.4.0">v2.3.0...v2.4.0</a></p>
<h3>Features</h3>
<ul>
<li><strong>api:</strong> Add support for gpt-4o-transcribe-diarize on
audio/transcriptions endpoint (<a
href="bdbe9b8f44">bdbe9b8</a>)</li>
</ul>
<h3>Chores</h3>
<ul>
<li>fix dangling comment (<a
href="da14e99606">da14e99</a>)</li>
<li><strong>internal:</strong> detect missing future annotations with
ruff (<a
href="2672b8f072">2672b8f</a>)</li>
</ul>
<h2>2.3.0 (2025-10-10)</h2>
<p>Full Changelog: <a
href="https://github.com/openai/openai-python/compare/v2.2.0...v2.3.0">v2.2.0...v2.3.0</a></p>
<h3>Features</h3>
<ul>
<li><strong>api:</strong> comparison filter in/not in (<a
href="aa49f626a6">aa49f62</a>)</li>
</ul>
<h3>Chores</h3>
<ul>
<li><strong>package:</strong> bump jiter to >=0.10.0 to support
Python 3.14 (<a
href="https://redirect.github.com/openai/openai-python/issues/2618">#2618</a>)
(<a
href="aa445cab5c">aa445ca</a>)</li>
</ul>
<h2>2.2.0 (2025-10-06)</h2>
<p>Full Changelog: <a
href="https://github.com/openai/openai-python/compare/v2.1.0...v2.2.0">v2.1.0...v2.2.0</a></p>
<h3>Features</h3>
<ul>
<li><strong>api:</strong> dev day 2025 launches (<a
href="38ac0093eb">38ac009</a>)</li>
</ul>
<h3>Bug Fixes</h3>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="513ae76253"><code>513ae76</code></a>
release: 2.5.0 (<a
href="https://redirect.github.com/openai/openai-python/issues/2694">#2694</a>)</li>
<li><a
href="ebf32212f7"><code>ebf3221</code></a>
release: 2.4.0</li>
<li><a
href="e043d7b164"><code>e043d7b</code></a>
chore: fix dangling comment</li>
<li><a
href="25cbb74f83"><code>25cbb74</code></a>
feat(api): Add support for gpt-4o-transcribe-diarize on
audio/transcriptions ...</li>
<li><a
href="8cdfd0650e"><code>8cdfd06</code></a>
codegen metadata</li>
<li><a
href="d5c64434b7"><code>d5c6443</code></a>
codegen metadata</li>
<li><a
href="b20a9e7b81"><code>b20a9e7</code></a>
chore(internal): detect missing future annotations with ruff</li>
<li><a
href="e5f93f5dae"><code>e5f93f5</code></a>
release: 2.3.0</li>
<li><a
href="044878859c"><code>0448788</code></a>
feat(api): comparison filter in/not in</li>
<li><a
href="85a91ade61"><code>85a91ad</code></a>
chore(package): bump jiter to >=0.10.0 to support Python 3.14 (<a
href="https://redirect.github.com/openai/openai-python/issues/2618">#2618</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/openai/openai-python/compare/v1.107.0...v2.5.0">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
---------
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
- Extend the model type to include rerank models.
- Implement `rerank()` method in inference router.
- Add `rerank_model_list` to `OpenAIMixin` to enable providers to
register and identify rerank models
- Update documentation.
<!-- 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.* -->
```
pytest tests/unit/providers/utils/inference/test_openai_mixin.py
```
# What does this PR do?
metadata is conflicting with the default embedding model set on server
side via extra body, removing the check and just letting metadata take
precedence over extra body
`ValueError: Embedding model inconsistent between metadata
('text-embedding-3-small') and extra_body
('sentence-transformers/nomic-ai/nomic-embed-text-v1.5')`
## Test Plan
CI
Kill the `builtin::rag` tool group completely since it is no longer
targeted. We use the Responses implementation for knowledge_search which
uses the `openai_vector_stores` pathway.
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
# What does this PR do?
Refactor setting default vector store provider and embedding model to
use an optional `vector_stores` config in the `StackRunConfig` and clean
up code to do so (had to add back in some pieces of VectorDB). Also
added remote Qdrant and Weaviate to starter distro (based on other PR
where inference providers were added for UX).
New config is simply (default for Starter distro):
```yaml
vector_stores:
default_provider_id: faiss
default_embedding_model:
provider_id: sentence-transformers
model_id: nomic-ai/nomic-embed-text-v1.5
```
## Test Plan
CI and Unit tests.
---------
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
**This PR changes configurations in a backward incompatible way.**
Run configs today repeat full SQLite/Postgres snippets everywhere a
store is needed, which means duplicated credentials, extra connection
pools, and lots of drift between files. This PR introduces named storage
backends so the stack and providers can share a single catalog and
reference those backends by name.
## Key Changes
- Add `storage.backends` to `StackRunConfig`, register each KV/SQL
backend once at startup, and validate that references point to the right
family.
- Move server stores under `storage.stores` with lightweight references
(backend + namespace/table) instead of full configs.
- Update every provider/config/doc to use the new reference style;
docs/codegen now surface the simplified YAML.
## Migration
Before:
```yaml
metadata_store:
type: sqlite
db_path: ~/.llama/distributions/foo/registry.db
inference_store:
type: postgres
host: ${env.POSTGRES_HOST}
port: ${env.POSTGRES_PORT}
db: ${env.POSTGRES_DB}
user: ${env.POSTGRES_USER}
password: ${env.POSTGRES_PASSWORD}
conversations_store:
type: postgres
host: ${env.POSTGRES_HOST}
port: ${env.POSTGRES_PORT}
db: ${env.POSTGRES_DB}
user: ${env.POSTGRES_USER}
password: ${env.POSTGRES_PASSWORD}
```
After:
```yaml
storage:
backends:
kv_default:
type: kv_sqlite
db_path: ~/.llama/distributions/foo/kvstore.db
sql_default:
type: sql_postgres
host: ${env.POSTGRES_HOST}
port: ${env.POSTGRES_PORT}
db: ${env.POSTGRES_DB}
user: ${env.POSTGRES_USER}
password: ${env.POSTGRES_PASSWORD}
stores:
metadata:
backend: kv_default
namespace: registry
inference:
backend: sql_default
table_name: inference_store
max_write_queue_size: 10000
num_writers: 4
conversations:
backend: sql_default
table_name: openai_conversations
```
Provider configs follow the same pattern—for example, a Chroma vector
adapter switches from:
```yaml
providers:
vector_io:
- provider_id: chromadb
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL}
kvstore:
type: sqlite
db_path: ~/.llama/distributions/foo/chroma.db
```
to:
```yaml
providers:
vector_io:
- provider_id: chromadb
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL}
persistence:
backend: kv_default
namespace: vector_io::chroma_remote
```
Once the backends are declared, everything else just points at them, so
rotating credentials or swapping to Postgres happens in one place and
the stack reuses a single connection pool.
# Problem
The current inline provider appends the user provided instructions to
messages as a system prompt, but the returned response object does not
contain the instructions field (as specified in the OpenAI responses
spec).
# What does this PR do?
This pull request adds the instruction field to the response object
definition and updates the inline provider. It also ensures that
instructions from previous response is not carried over to the next
response (as specified in the openAI spec).
Closes #[3566](https://github.com/llamastack/llama-stack/issues/3566)
## Test Plan
- Tested manually for change in model response w.r.t supplied
instructions field.
- Added unit test to check that the instructions from previous response
is not carried over to the next response.
- Added integration tests to check instructions parameter in the
returned response object.
- Added new recordings for the integration tests.
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
fix: nested claims mapping in OAuth2 token validation
The get_attributes_from_claims function was only checking for top-level
claim keys, causing token validation to fail when using nested claims
like "resource_access.llamastack.roles" (common in Keycloak JWT tokens).
Updated the function to support dot notation for traversing nested claim
structures. Give precedence to dot notation over literal keys with dots
in claims mapping.
Added test coverage.
Closes: #3812
Signed-off-by: Derek Higgins <derekh@redhat.com>
# What does this PR do?
remove telemetry as a providable API from the codebase. This includes
removing it from generated distributions but also the provider registry,
the router, etc
since `setup_logger` is tied pretty strictly to `Api.telemetry` being in
impls we still need an "instantiated provider" in our implementations.
However it should not be auto-routed or provided. So in
validate_and_prepare_providers (called from resolve_impls) I made it so
that if run_config.telemetry.enabled, we set up the meta-reference
"provider" internally to be used so that log_event will work when
called.
This is the neatest way I think we can remove telemetry from the
provider configs but also not need to rip apart the whole "telemetry is
a provider" logic just yet, but we can do it internally later without
disrupting users.
so telemetry is removed from the registry such that if a user puts
`telemetry:` as an API in their build/run config it will err out, but
can still be used by us internally as we go through this transition.
relates to #3806
Signed-off-by: Charlie Doern <cdoern@redhat.com>
As indicated in the title. Our `starter` distribution enables all remote
providers _very intentionally_ because we believe it creates an easier,
more welcoming experience to new folks using the software. If we do
that, and then slam the logs with errors making them question their life
choices, it is not so good :)
Note that this fix is limited in scope. If you ever try to actually
instantiate the OpenAI client from a code path without an API key being
present, you deserve to fail hard.
## Test Plan
Run `llama stack run starter` with `OPENAI_API_KEY` set. No more wall of
text, just one message saying "listed 96 models".
a bunch of logger.info()s are good for server code to help debug in
production, but we don't want them killing our unit test output :)
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
**!!BREAKING CHANGE!!**
The lookup is also straightforward -- we always look for this identifier
and don't try to find a match for something without the provider_id
prefix.
Note that, this ideally means we need to update the `register_model()`
API also (we should kill "identifier" from there) but I am not doing
that as part of this PR.
## Test Plan
Existing unit tests
# What does this PR do?
Have closed the previous PR due to merge conflicts with multiple PRs
Addressed all comments from
https://github.com/llamastack/llama-stack/pull/3768 (sorry for carrying
over to this one)
## Test Plan
Added UTs and integration tests
Fixed KeyError when chunks don't have document_id in metadata or
chunk_metadata. Updated logging to safely extract document_id using
getattr and RAG memory to handle different document_id locations. Added
test for missing document_id scenarios.
Fixes issue #3494 where /v1/vector-io/insert would crash with KeyError.
Fixed KeyError when chunks don't have document_id in metadata or
chunk_metadata. Updated logging to safely extract document_id using
getattr and RAG memory to handle different document_id locations. Added
test for missing document_id scenarios.
# What does this PR do?
Fixes a KeyError crash in `/v1/vector-io/insert` when chunks are missing
`document_id` fields. The API
was failing even though `document_id` is optional according to the
schema.
Closes#3494
## Test Plan
**Before fix:**
- POST to `/v1/vector-io/insert` with chunks → 500 KeyError
- Happened regardless of where `document_id` was placed
**After fix:**
- Same request works fine → 200 OK
- Tested with Postman using FAISS backend
- Added unit test covering missing `document_id` scenarios
This PR updates the Conversation item related types and improves a
couple critical parts of the implemenation:
- it creates a streaming output item for the final assistant message
output by
the model. until now we only added content parts and included that
message in the final response.
- rewrites the conversation update code completely to account for items
other than messages (tool calls, outputs, etc.)
## Test Plan
Used the test script from
https://github.com/llamastack/llama-stack-client-python/pull/281 for
this
```
TEST_API_BASE_URL=http://localhost:8321/v1 \
pytest tests/integration/test_agent_turn_step_events.py::test_client_side_function_tool -xvs
```
# What does this PR do?
Enables automatic embedding model detection for vector stores and by
using a `default_configured` boolean that can be defined in the
`run.yaml`.
<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->
## Test Plan
- Unit tests
- Integration tests
- Simple example below:
Spin up the stack:
```bash
uv run llama stack build --distro starter --image-type venv --run
```
Then test with OpenAI's client:
```python
from openai import OpenAI
client = OpenAI(base_url="http://localhost:8321/v1/", api_key="none")
vs = client.vector_stores.create()
```
Previously you needed:
```python
vs = client.vector_stores.create(
extra_body={
"embedding_model": "sentence-transformers/all-MiniLM-L6-v2",
"embedding_dimension": 384,
}
)
```
The `extra_body` is now unnecessary.
---------
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
The purpose of this PR is to replace the Llama Stack's default embedding
model by nomic-embed-text-v1.5.
These are the key reasons why Llama Stack community decided to switch
from all-MiniLM-L6-v2 to nomic-embed-text-v1.5:
1. The training data for
[all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2#training-data)
includes a lot of data sets with various licensing terms, so it is
tricky to know when/whether it is appropriate to use this model for
commercial applications.
2. The model is not particularly competitive on major benchmarks. For
example, if you look at the [MTEB
Leaderboard](https://huggingface.co/spaces/mteb/leaderboard) and click
on Miscellaneous/BEIR to see English information retrieval accuracy, you
see that the top of the leaderboard is dominated by enormous models but
also that there are many, many models of relatively modest size whith
much higher Retrieval scores. If you want to look closely at the data, I
recommend clicking "Download Table" because it is easier to browse that
way.
More discussion info can be founded
[here](https://github.com/llamastack/llama-stack/issues/2418)
<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->
Closes#2418
## 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.* -->
1. Run `./scripts/unit-tests.sh`
2. Integration tests via CI wokrflow
---------
Signed-off-by: Sébastien Han <seb@redhat.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com>
Co-authored-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
This commit migrates the authentication system from python-jose to PyJWT
to eliminate the dependency on the archived rsa package. The migration
includes:
- Refactored OAuth2TokenAuthProvider to use PyJWT's PyJWKClient for
clean JWKS handling
- Removed manual JWKS fetching, caching and key extraction logic in
favor of PyJWT's built-in functionality
The new implementation is cleaner, more maintainable, and follows PyJWT
best practices while maintaining full backward compatibility.
## Test Plan
Unit tests. Auth CI.
---------
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
2 main changes:
1. Remove `provider_id` requirement in call to vector stores and
2. Removes "register first embedding model" logic
- Now forces embedding model id as required on Vector Store creation
Simplifies the UX for OpenAI to:
```python
vs = client.vector_stores.create(
name="my_citations_db",
extra_body={
"embedding_model": "ollama/nomic-embed-text:latest",
}
)
```
<!-- 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.* -->
---------
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
Applies the same pattern from
https://github.com/llamastack/llama-stack/pull/3777 to embeddings and
vector_stores.create() endpoints.
This should _not_ be a breaking change since (a) our tests were already
using the `extra_body` parameter when passing in to the backend (b) but
the backend probably wasn't extracting the parameters correctly. This PR
will fix that.
Updated APIs: `openai_embeddings(), openai_create_vector_store(),
openai_create_vector_store_file_batch()`
# What does this PR do?
Removes VectorDBs from API surface and our tests.
Moves tests to Vector Stores.
<!-- 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.* -->
---------
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
# What does this PR do?
Allows passing through extra_body parameters to inference providers.
With this, we removed the 2 vllm-specific parameters from completions
API into `extra_body`.
Before/After
<img width="1883" height="324" alt="image"
src="https://github.com/user-attachments/assets/acb27c08-c748-46c9-b1da-0de64e9908a1"
/>
closes#2720
## Test Plan
CI and added new test
```
❯ uv run pytest -s -v tests/integration/ --stack-config=server:starter --inference-mode=record -k 'not( builtin_tool or safety_with_image or code_interpreter or test_rag ) and test_openai_completion_guided_choice' --setup=vllm --suite=base --color=yes
Uninstalled 3 packages in 125ms
Installed 3 packages in 19ms
INFO 2025-10-10 14:29:54,317 tests.integration.conftest:118 tests: Applying setup 'vllm' for suite base
INFO 2025-10-10 14:29:54,331 tests.integration.conftest:47 tests: Test stack config type: server
(stack_config=server:starter)
============================================================================================================== test session starts ==============================================================================================================
platform darwin -- Python 3.12.11, pytest-8.4.2, pluggy-1.6.0 -- /Users/erichuang/projects/llama-stack-1/.venv/bin/python
cachedir: .pytest_cache
metadata: {'Python': '3.12.11', 'Platform': 'macOS-15.6.1-arm64-arm-64bit', 'Packages': {'pytest': '8.4.2', 'pluggy': '1.6.0'}, 'Plugins': {'anyio': '4.9.0', 'html': '4.1.1', 'socket': '0.7.0', 'asyncio': '1.1.0', 'json-report': '1.5.0', 'timeout': '2.4.0', 'metadata': '3.1.1', 'cov': '6.2.1', 'nbval': '0.11.0'}}
rootdir: /Users/erichuang/projects/llama-stack-1
configfile: pyproject.toml
plugins: anyio-4.9.0, html-4.1.1, socket-0.7.0, asyncio-1.1.0, json-report-1.5.0, timeout-2.4.0, metadata-3.1.1, cov-6.2.1, nbval-0.11.0
asyncio: mode=Mode.AUTO, asyncio_default_fixture_loop_scope=None, asyncio_default_test_loop_scope=function
collected 285 items / 284 deselected / 1 selected
tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B]
instantiating llama_stack_client
Starting llama stack server with config 'starter' on port 8321...
Waiting for server at http://localhost:8321... (0.0s elapsed)
Waiting for server at http://localhost:8321... (0.5s elapsed)
Waiting for server at http://localhost:8321... (5.1s elapsed)
Waiting for server at http://localhost:8321... (5.6s elapsed)
Waiting for server at http://localhost:8321... (10.1s elapsed)
Waiting for server at http://localhost:8321... (10.6s elapsed)
Server is ready at http://localhost:8321
llama_stack_client instantiated in 11.773s
PASSEDTerminating llama stack server process...
Terminating process 98444 and its group...
Server process and children terminated gracefully
============================================================================================================= slowest 10 durations ==============================================================================================================
11.88s setup tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B]
3.02s call tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B]
0.01s teardown tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B]
================================================================================================ 1 passed, 284 deselected, 3 warnings in 16.21s =================================================================================================
```
# What does this PR do?
Converts openai(_chat)_completions params to pydantic BaseModel to
reduce code duplication across all providers.
## Test Plan
CI
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with
[ReviewStack](https://reviewstack.dev/llamastack/llama-stack/pull/3761).
* #3777
* __->__ #3761
The AuthenticationMiddleware was blocking all requests without an
Authorization header, including health and version endpoints that are
needed by monitoring tools, load balancers, and Kubernetes probes.
This commit allows endpoints ending in /health or /version to bypass
authentication, enabling operational tooling to function properly
without requiring credentials.
Closes: #3735
Signed-off-by: Derek Higgins <derekh@redhat.com>
Implementats usage accumulation to StreamingResponseOrchestrator.
The most important part was to pass `stream_options = { "include_usage":
true }` to the chat_completion call. This means I will have to record
all responses tests again because request hash will change :)
Test changes:
- Add usage assertions to streaming and non-streaming tests
- Update test recordings with actual usage data from OpenAI
# What does this PR do?
This PR checks whether, if a previous response is linked, there are
mcp_list_tools objects that can be reused instead of listing the tools
explicitly every time.
Closes#3106
## Test Plan
Tested manually.
Added unit tests to cover new behaviour.
---------
Signed-off-by: Gordon Sim <gsim@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
# What does this PR do?
use SecretStr for OpenAIMixin providers
- RemoteInferenceProviderConfig now has auth_credential: SecretStr
- the default alias is api_key (most common name)
- some providers override to use api_token (RunPod, vLLM, Databricks)
- some providers exclude it (Ollama, TGI, Vertex AI)
addresses #3517
## Test Plan
ci w/ new tests
# What does this PR do?
objects (vector dbs, models, scoring functions, etc) have an identifier
and associated object values.
we allow exact duplicate registrations.
we reject registrations when the identifier exists and the associated
object values differ.
note: model are namespaced, i.e. {provider_id}/{identifier}, while other
object types are not
## Test Plan
ci w/ new tests
Replaces opaque error messages when recordings are not found with
somewhat better guidance
Before:
```
No recorded response found for request hash: abc123...
To record this response, run with LLAMA_STACK_TEST_INFERENCE_MODE=record
```
After:
```
Recording not found for request hash: abc123
Model: gpt-4 | Request: POST https://api.openai.com/v1/chat/completions
Run './scripts/integration-tests.sh --inference-mode record-if-missing' with required API keys to generate.
```
These vector databases are already thoroughly tested in integration
tests.
Unit tests now focus on sqlite_vec, faiss, and pgvector with mocked
dependencies, removing the need for external service dependencies.
## Changes:
- Deleted test_qdrant.py unit test file
- Removed chroma/qdrant fixtures and parametrization from conftest.py
- Fixed SqliteKVStoreConfig import to use correct location
- Removed chromadb, qdrant-client, pymilvus, milvus-lite, and
weaviate-client from unit test dependencies in pyproject.toml
Renames `inference_recorder.py` to `api_recorder.py` and extends it to
support recording/replaying tool invocations in addition to inference
calls.
This allows us to record web-search, etc. tool calls and thereafter
apply recordings for `tests/integration/responses`
## Test Plan
```
export OPENAI_API_KEY=...
export TAVILY_SEARCH_API_KEY=...
./scripts/integration-tests.sh --stack-config ci-tests \
--suite responses --inference-mode record-if-missing
```
