# What does this PR do?
* Cleans up API docstrings for better documentation rendering
<img width="2346" height="1126" alt="image"
src="https://github.com/user-attachments/assets/516b09a1-2d5b-4614-a3a9-13431fc21fc1"
/>
## Test Plan
* Manual testing
---------
Signed-off-by: Doug Edgar <dedgar@redhat.com>
Signed-off-by: Charlie Doern <cdoern@redhat.com>
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: ehhuang <ehhuang@users.noreply.github.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
Co-authored-by: Matthew Farrellee <matt@cs.wisc.edu>
Co-authored-by: Doug Edgar <dedgar@redhat.com>
Co-authored-by: Christian Zaccaria <73656840+ChristianZaccaria@users.noreply.github.com>
Co-authored-by: Anastas Stoyanovsky <contact@anastas.eu>
Co-authored-by: Charlie Doern <cdoern@redhat.com>
Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Young Han <110819238+seyeong-han@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
# What does this PR do?
- implement get_api_key instead of relying on
LiteLLMOpenAIMixin.get_api_key
- remove use of LiteLLMOpenAIMixin
- add default initialize/shutdown methods to OpenAIMixin
- remove __init__s to allow proper pydantic construction
- remove dead code from vllm adapter and associated / duplicate unit
tests
- update vllm adapter to use openaimixin for model registration
- remove ModelRegistryHelper from fireworks & together adapters
- remove Inference from nvidia adapter
- complete type hints on embedding_model_metadata
- allow extra fields on OpenAIMixin, for model_store, __provider_id__,
etc
- new recordings for ollama
- enhance the list models error handling
- update cerebras (remove cerebras-cloud-sdk) and anthropic (custom
model listing) inference adapters
- parametrized test_inference_client_caching
- remove cerebras, databricks, fireworks, together from blanket mypy
exclude
- removed unnecessary litellm deps
## Test Plan
ci
# What does this PR do?
when using the providers.d method of installation users could hand craft
their AdapterSpec's to use overlapping code meaning one repo could
contain an inline and remote impl. Currently installing a provider via
module does not allow for that as each repo is only allowed to have one
`get_provider_spec` method with one Spec returned
add an optional way for `get_provider_spec` to return a list of
`ProviderSpec` where each can be either an inline or remote impl.
Note: the `adapter_type` in `get_provider_spec` MUST match the
`provider_type` in the build/run yaml for this to work.
resolves#3226
## Test Plan
once this merges we need to re-enable the external provider test and
account for this functionality. Work needs to be done in the external
provider repos to support this functionality.
Signed-off-by: Charlie Doern <cdoern@redhat.com>
# What does this PR do?
https://github.com/llamastack/llama-stack/pull/3462 allows using uvicorn
to start llama stack server which supports spawning multiple workers.
This PR enables us to launch >1 workers from `llama stack run` (will add
the parameter in a follow-up PR, keeping this PR on simplifying) by
removing the old way of launching stack server and consolidates
launching via uvicorn.run only.
## Test Plan
ran `llama stack run starter`
CI
Uses test_id in request hashes and test-scoped subdirectories to prevent
cross-test contamination. Model list endpoints exclude test_id to enable
merging recordings from different servers.
Additionally, this PR adds a `record-if-missing` mode (which we will use
instead of `record` which records everything) which is very useful.
🤖 Co-authored with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude <noreply@anthropic.com>
IDs are now deterministic hashes based on request content, and
timestamps are normalized to constants, eliminating spurious changes
when re-recording tests.
## Changes
- Updated `inference_recorder.py` to normalize IDs and timestamps during
recording
- Added `scripts/normalize_recordings.py` utility to re-normalize
existing recordings
- Created documentation in `tests/integration/recordings/README.md`
- Normalized 350 existing recording files
## Summary
Introduce `ExtraBodyField` annotation to enable parameters that arrive
via extra_body in client SDKs but are accessible server-side with full
typing.
These parameters are documented in OpenAPI specs under
**`x-llama-stack-extra-body-params`** but excluded from generated SDK
signatures.
Add `shields` parameter to `create_openai_response` as the first
implementation using this pattern.
## Test Plan
- added an integration test which checks that shields parameter passed
via extra_body reaches server implementation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
# What does this PR do?
on the path to maintainable impls of inference providers. make all
configs instances of RemoteInferenceProviderConfig.
## Test Plan
ci
# What does this PR do?
Initial implementation for `Conversations` and `ConversationItems` using
`AuthorizedSqlStore` with endpoints to:
- CREATE
- UPDATE
- GET/RETRIEVE/LIST
- DELETE
Set `level=LLAMA_STACK_API_V1`.
NOTE: This does not currently incorporate changes for Responses, that'll
be done in a subsequent PR.
Closes https://github.com/llamastack/llama-stack/issues/3235
## Test Plan
- Unit tests
- Integration tests
Also comparison of [OpenAPI spec for OpenAI
API](https://github.com/openai/openai-openapi/tree/manual_spec)
```bash
oasdiff breaking --fail-on ERR docs/static/llama-stack-spec.yaml https://raw.githubusercontent.com/openai/openai-openapi/refs/heads/manual_spec/openapi.yaml --strip-prefix-base "/v1/openai/v1" \
--match-path '(^/v1/openai/v1/conversations.*|^/conversations.*)'
```
Note I still have some uncertainty about this, I borrowed this info from
@cdoern on https://github.com/llamastack/llama-stack/pull/3514 but need
to spend more time to confirm it's working, at the moment it suggests it
does.
UPDATE on `oasdiff`, I investigated the OpenAI spec further and it looks
like currently the spec does not list Conversations, so that analysis is
useless. Noting for future reference.
---------
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
# What does this PR do?
remove unused chat_completion implementations
vllm features ported -
- requires max_tokens be set, use config value
- set tool_choice to none if no tools provided
## Test Plan
ci
# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
- This PR implements keyword and hybrid search for Weaviate DB based on
its inbuilt functions.
- Added fixtures to conftest.py for Weaviate.
- Enabled integration tests for remote Weaviate on all 3 search modes.
<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->
Closes#3010
## 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.* -->
Unit tests and integration tests should pass on this PR.
# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
Addresses Issue #3271 - "Starting LLS server locally on a terminal with
120 chars width results in an output with empty lines".
This removes the specific 150-character width limit specified for the
Console, and will now auto-detect the terminal width instead. Now the
formatting of Console output is consistent across different sizes of
terminal windows.
<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->
Closes#3271
## 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.* -->
Launching the server with several different sizes of terminal windows
results in Console output without unexpected spacing. e.g. `python -m
llama_stack.core.server.server /tmp/run.yaml --port 8321`
---------
Signed-off-by: Doug Edgar <dedgar@redhat.com>
Co-authored-by: Matthew Farrellee <matt@cs.wisc.edu>
# What does this PR do?
add ModelsProtocolPrivate methods to OpenAIMixin
this will allow providers using OpenAIMixin to use a common interface
## Test Plan
ci w/ new tests
# What does this PR do?
closes#3268closes#3498
When resuming from previous response ID, currently we attempt to convert
from the stored responses input to chat completion messages, which is
not always possible, e.g. for tool calls where some data is lost once
converted from chat completion message to repsonses input format.
This PR stores the chat completion messages that correspond to the
_last_ call to chat completion, which is sufficient to be resumed from
in the next responses API call, where we load these saved messages and
skip conversion entirely.
Separate issue to optimize storage:
https://github.com/llamastack/llama-stack/issues/3646
## Test Plan
existing CI tests
This is a sweeping change to clean up some gunk around our "Tool"
definitions.
First, we had two types `Tool` and `ToolDef`. The first of these was a
"Resource" type for the registry but we had stopped registering tools
inside the Registry long back (and only registered ToolGroups.) The
latter was for specifying tools for the Agents API. This PR removes the
former and adds an optional `toolgroup_id` field to the latter.
Secondly, as pointed out by @bbrowning in
https://github.com/llamastack/llama-stack/pull/3003#issuecomment-3245270132,
we were doing a lossy conversion from a full JSON schema from the MCP
tool specification into our ToolDefinition to send it to the model.
There is no necessity to do this -- we ourselves aren't doing any
execution at all but merely passing it to the chat completions API which
supports this. By doing this (and by doing it poorly), we encountered
limitations like not supporting array items, or not resolving $refs,
etc.
To fix this, we replaced the `parameters` field by `{ input_schema,
output_schema }` which can be full blown JSON schemas.
Finally, there were some types in our llama-related chat format
conversion which needed some cleanup. We are taking this opportunity to
clean those up.
This PR is a substantial breaking change to the API. However, given our
window for introducing breaking changes, this suits us just fine. I will
be landing a concurrent `llama-stack-client` change as well since API
shapes are changing.
# What does this PR do?
* Updates code snippets for Dell distribution, fixing specific user home
directory in code (replacing with $HOME) and updates docker instructions
to use `docker` instead of `podman`.
## Test Plan
N.A.
Co-authored-by: Connor Hack <connorhack@fb.com>
# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->
Spammy
## 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.* -->
n/a
# What does this PR do?
the LiteLLMOpenAIMixin provides support for reading key from provider
data (headers users send).
this adds the same functionality to the OpenAIMixin.
this is infrastructure for migrating providers.
## Test Plan
ci w/ new tests
# What does this PR do?
First step towards cleaning up the API reference section of the docs.
- Separates API reference into 3 sections: stable (`v1`), experimental (`v1alpha` and `v1beta`), and deprecated (`deprecated=True`)
- Each section is accessible via the dropdown menu and `docs/api-overview`
<img width="1237" height="321" alt="Screenshot 2025-09-30 at 5 47 30 PM" src="https://github.com/user-attachments/assets/fe0e498c-b066-46ed-a48e-4739d3b6724c" />
<img width="860" height="510" alt="Screenshot 2025-09-30 at 5 47 49 PM" src="https://github.com/user-attachments/assets/a92a8d8c-94bf-42d5-9f5b-b47bb2b14f9c" />
- Deprecated APIs: Added styling to the sidebar, and a notice on the endpoint pages
<img width="867" height="428" alt="Screenshot 2025-09-30 at 5 47 43 PM" src="https://github.com/user-attachments/assets/9e6e050d-c782-461b-8084-5ff6496d7bd9" />
Closes#3628
TODO in follow-up PRs:
- Add the ability to annotate API groups with supplementary content (so we can have longer descriptions of complex APIs like Responses)
- Clean up docstrings to show API endpoints (or short semantic titles) in the sidebar
## Test Plan
- Local testing
- Made sure API conformance test still passes
# What does this PR do?
- categories like "core::server" is not recognized so it's level is not
set by 'all=debug'
- removed spammy telemetry debug logging
## Test Plan
test server launched with LLAMA_STACK_LOGGING='all=debug'
# What does this PR do?
level the following APIs, keeping their old routes around as well until
0.4.0
1. datasetio to v1beta: used primarily by eval and training. Given that
training is v1alpha, and eval is v1alpha, datasetio is likely to change
in structure as real usages of the API spin up. Register,unregister, and
iter dataset is sparsely implemented meaning the shape of that route is
likely to change.
2. telemetry to v1alpha: telemetry has been going through many changes.
for example query_metrics was not even implemented until recently and
had to change its shape to work. putting this in v1beta will allow us to
fix functionality like OTEL, sqlite, etc. The routes themselves are set,
but the structure might change a bit
Signed-off-by: Charlie Doern <cdoern@redhat.com>
# What does this PR do?
When a model decides to use an MCP tool call that requires no arguments,
it sets the `arguments` field to `None`. This causes the user to see a
`400 bad requst error` due to validation errors down the stack because
this field gets removed when being parsed by an openai compatible
inference provider like vLLM
This PR ensures that, as soon as the tool call args are accumulated
while streaming, we check to ensure no tool call function arguments are
set to None - if they are we replace them with "{}"
<!-- If resolving an issue, uncomment and update the line below -->
Closes#3456
## Test Plan
Added new unit test to verify that any tool calls with function
arguments set to `None` get handled correctly
---------
Signed-off-by: Jaideep Rao <jrao@redhat.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?
Fireworks doesn't allow repsonse_format with tool use. The default
response format is 'text' anyway, so we can safely omit.
## Test Plan
Below script failed without the change, runs after.
```
#!/usr/bin/env python3
"""
Script to test Responses API with kubernetes-mcp-server.
This script:
1. Connects to the llama stack server
2. Uses the Responses API with MCP tools
3. Asks for the list of Kubernetes namespaces using the kubernetes-mcp-server
"""
import json
from openai import OpenAI
# Connect to the llama stack server
base_url = "http://localhost:8321/v1"
client = OpenAI(base_url=base_url, api_key="fake")
# Define the MCP tool pointing to the kubernetes-mcp-server
# The kubernetes-mcp-server is running on port 3000 with SSE endpoint at /sse
mcp_server_url = "http://localhost:3000/sse"
tools = [
{
"type": "mcp",
"server_label": "k8s",
"server_url": mcp_server_url,
}
]
# Create a response request asking for k8s namespaces
print("Sending request to list Kubernetes namespaces...")
print(f"Using MCP server at: {mcp_server_url}")
print("Available tools will be listed automatically by the MCP server.")
print()
response = client.responses.create(
# model="meta-llama/Llama-3.2-3B-Instruct", # Using the vllm model
model="fireworks/accounts/fireworks/models/llama4-scout-instruct-basic",
# model="openai/gpt-4o",
input="what are all the Kubernetes namespaces? Use tool call to `namespaces_list`. make sure to adhere to the tool calling format UNDER ALL CIRCUMSTANCES.",
tools=tools,
stream=False,
)
print("\n" + "=" * 80)
print("RESPONSE OUTPUT:")
print("=" * 80)
# Print the output
for i, output in enumerate(response.output):
print(f"\n[Output {i + 1}] Type: {output.type}")
if output.type == "mcp_list_tools":
print(f" Server: {output.server_label}")
print(f" Tools available: {[t.name for t in output.tools]}")
elif output.type == "mcp_call":
print(f" Tool called: {output.name}")
print(f" Arguments: {output.arguments}")
print(f" Result: {output.output}")
if output.error:
print(f" Error: {output.error}")
elif output.type == "message":
print(f" Role: {output.role}")
print(f" Content: {output.content}")
print("\n" + "=" * 80)
print("FINAL RESPONSE TEXT:")
print("=" * 80)
print(response.output_text)
```
# What does this PR do?
This PR adds support for the require_approval on an mcp tool definition
passed to create response in the Responses API. This allows the caller
to indicate whether they want to approve calls to that server, or let
them be called without approval.
Closes#3443
## Test Plan
Tested both approval and denial.
Added automated integration test for both cases.
---------
Signed-off-by: Gordon Sim <gsim@redhat.com>
Co-authored-by: Matthew Farrellee <matt@cs.wisc.edu>
https://github.com/llamastack/llama-stack/pull/3604 broke multipart form
data field parsing for the Files API since it changed its shape -- so as
to match the API exactly to the OpenAI spec even in the generated client
code.
The underlying reason is that multipart/form-data cannot transport
structured nested fields. Each field must be str-serialized. The client
(specifically the OpenAI client whose behavior we must match),
transports sub-fields as `expires_after[anchor]` and
`expires_after[seconds]`, etc. We must be able to handle these fields
somehow on the server without compromising the shape of the YAML spec.
This PR "fixes" this by adding a dependency to convert the data. The
main trade-off here is that we must add this `Depends()` annotation on
every provider implementation for Files. This is a headache, but a much
more reasonable one (in my opinion) given the alternatives.
## Test Plan
Tests as shown in
https://github.com/llamastack/llama-stack/pull/3604#issuecomment-3351090653
pass.
# What does this PR do?
agents is likely to be deprecated in favor of responses. Lets level it
as alpha to indicate the lack of longterm support
keep v1 route for backwards compat.
Closes#3611
Signed-off-by: Charlie Doern <cdoern@redhat.com>
# What does this PR do?
migrate safety api implementation from /inference/chat-completion to
/v1/chat/completions
## Test Plan
ci w/ recordings
---------
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
