From ea396a54cd771933875115e29510483935aa6c4c Mon Sep 17 00:00:00 2001 From: Matthew Farrellee Date: Thu, 18 Sep 2025 07:09:57 -0400 Subject: [PATCH 01/18] chore: update the ollama inference impl to use OpenAIMixin for openai-compat functions (#3395) # What does this PR do? update Ollama inference provider to use OpenAIMixin for openai-compat endpoints ## Test Plan ci --- .../remote/inference/ollama/ollama.py | 157 +-- .../recordings/responses/3a81146f2afa.json | 990 ++++++++++++++++++ .../recordings/responses/6412295819a1.json | 43 + .../recordings/responses/ecae140151d1.json | 43 + 4 files changed, 1100 insertions(+), 133 deletions(-) create mode 100644 tests/integration/recordings/responses/3a81146f2afa.json create mode 100644 tests/integration/recordings/responses/6412295819a1.json create mode 100644 tests/integration/recordings/responses/ecae140151d1.json diff --git a/llama_stack/providers/remote/inference/ollama/ollama.py b/llama_stack/providers/remote/inference/ollama/ollama.py index d3d107e1d..67a22cbe3 100644 --- a/llama_stack/providers/remote/inference/ollama/ollama.py +++ b/llama_stack/providers/remote/inference/ollama/ollama.py @@ -7,12 +7,10 @@ import asyncio import base64 -import uuid from collections.abc import AsyncGenerator, AsyncIterator from typing import Any -from ollama import AsyncClient # type: ignore[attr-defined] -from openai import AsyncOpenAI +from ollama import AsyncClient as AsyncOllamaClient from llama_stack.apis.common.content_types import ( ImageContentItem, @@ -37,9 +35,6 @@ from llama_stack.apis.inference import ( Message, OpenAIChatCompletion, OpenAIChatCompletionChunk, - OpenAICompletion, - OpenAIEmbeddingsResponse, - OpenAIEmbeddingUsage, OpenAIMessageParam, OpenAIResponseFormatParam, ResponseFormat, @@ -64,15 +59,14 @@ from llama_stack.providers.utils.inference.model_registry import ( from llama_stack.providers.utils.inference.openai_compat import ( OpenAICompatCompletionChoice, OpenAICompatCompletionResponse, - b64_encode_openai_embeddings_response, get_sampling_options, prepare_openai_completion_params, - prepare_openai_embeddings_params, process_chat_completion_response, process_chat_completion_stream_response, process_completion_response, process_completion_stream_response, ) +from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin from llama_stack.providers.utils.inference.prompt_adapter import ( chat_completion_request_to_prompt, completion_request_to_prompt, @@ -89,6 +83,7 @@ logger = get_logger(name=__name__, category="inference::ollama") class OllamaInferenceAdapter( + OpenAIMixin, InferenceProvider, ModelsProtocolPrivate, ): @@ -98,23 +93,21 @@ class OllamaInferenceAdapter( def __init__(self, config: OllamaImplConfig) -> None: self.register_helper = ModelRegistryHelper(MODEL_ENTRIES) self.config = config - self._clients: dict[asyncio.AbstractEventLoop, AsyncClient] = {} - self._openai_client = None + self._clients: dict[asyncio.AbstractEventLoop, AsyncOllamaClient] = {} @property - def client(self) -> AsyncClient: + def ollama_client(self) -> AsyncOllamaClient: # ollama client attaches itself to the current event loop (sadly?) loop = asyncio.get_running_loop() if loop not in self._clients: - self._clients[loop] = AsyncClient(host=self.config.url) + self._clients[loop] = AsyncOllamaClient(host=self.config.url) return self._clients[loop] - @property - def openai_client(self) -> AsyncOpenAI: - if self._openai_client is None: - url = self.config.url.rstrip("/") - self._openai_client = AsyncOpenAI(base_url=f"{url}/v1", api_key="ollama") - return self._openai_client + def get_api_key(self): + return "NO_KEY" + + def get_base_url(self): + return self.config.url.rstrip("/") + "/v1" async def initialize(self) -> None: logger.info(f"checking connectivity to Ollama at `{self.config.url}`...") @@ -129,7 +122,7 @@ class OllamaInferenceAdapter( async def list_models(self) -> list[Model] | None: provider_id = self.__provider_id__ - response = await self.client.list() + response = await self.ollama_client.list() # always add the two embedding models which can be pulled on demand models = [ @@ -189,7 +182,7 @@ class OllamaInferenceAdapter( HealthResponse: A dictionary containing the health status. """ try: - await self.client.ps() + await self.ollama_client.ps() return HealthResponse(status=HealthStatus.OK) except Exception as e: return HealthResponse(status=HealthStatus.ERROR, message=f"Health check failed: {str(e)}") @@ -238,7 +231,7 @@ class OllamaInferenceAdapter( params = await self._get_params(request) async def _generate_and_convert_to_openai_compat(): - s = await self.client.generate(**params) + s = await self.ollama_client.generate(**params) async for chunk in s: choice = OpenAICompatCompletionChoice( finish_reason=chunk["done_reason"] if chunk["done"] else None, @@ -254,7 +247,7 @@ class OllamaInferenceAdapter( async def _nonstream_completion(self, request: CompletionRequest) -> CompletionResponse: params = await self._get_params(request) - r = await self.client.generate(**params) + r = await self.ollama_client.generate(**params) choice = OpenAICompatCompletionChoice( finish_reason=r["done_reason"] if r["done"] else None, @@ -346,9 +339,9 @@ class OllamaInferenceAdapter( async def _nonstream_chat_completion(self, request: ChatCompletionRequest) -> ChatCompletionResponse: params = await self._get_params(request) if "messages" in params: - r = await self.client.chat(**params) + r = await self.ollama_client.chat(**params) else: - r = await self.client.generate(**params) + r = await self.ollama_client.generate(**params) if "message" in r: choice = OpenAICompatCompletionChoice( @@ -372,9 +365,9 @@ class OllamaInferenceAdapter( async def _generate_and_convert_to_openai_compat(): if "messages" in params: - s = await self.client.chat(**params) + s = await self.ollama_client.chat(**params) else: - s = await self.client.generate(**params) + s = await self.ollama_client.generate(**params) async for chunk in s: if "message" in chunk: choice = OpenAICompatCompletionChoice( @@ -407,7 +400,7 @@ class OllamaInferenceAdapter( assert all(not content_has_media(content) for content in contents), ( "Ollama does not support media for embeddings" ) - response = await self.client.embed( + response = await self.ollama_client.embed( model=model.provider_resource_id, input=[interleaved_content_as_str(content) for content in contents], ) @@ -422,14 +415,14 @@ class OllamaInferenceAdapter( pass # Ignore statically unknown model, will check live listing if model.model_type == ModelType.embedding: - response = await self.client.list() + response = await self.ollama_client.list() if model.provider_resource_id not in [m.model for m in response.models]: - await self.client.pull(model.provider_resource_id) + await self.ollama_client.pull(model.provider_resource_id) # we use list() here instead of ps() - # - ps() only lists running models, not available models # - models not currently running are run by the ollama server as needed - response = await self.client.list() + response = await self.ollama_client.list() available_models = [m.model for m in response.models] provider_resource_id = model.provider_resource_id @@ -448,90 +441,6 @@ class OllamaInferenceAdapter( return model - async def openai_embeddings( - self, - model: str, - input: str | list[str], - encoding_format: str | None = "float", - dimensions: int | None = None, - user: str | None = None, - ) -> OpenAIEmbeddingsResponse: - model_obj = await self._get_model(model) - if model_obj.provider_resource_id is None: - raise ValueError(f"Model {model} has no provider_resource_id set") - - # Note, at the moment Ollama does not support encoding_format, dimensions, and user parameters - params = prepare_openai_embeddings_params( - model=model_obj.provider_resource_id, - input=input, - encoding_format=encoding_format, - dimensions=dimensions, - user=user, - ) - - response = await self.openai_client.embeddings.create(**params) - data = b64_encode_openai_embeddings_response(response.data, encoding_format) - - usage = OpenAIEmbeddingUsage( - prompt_tokens=response.usage.prompt_tokens, - total_tokens=response.usage.total_tokens, - ) - # TODO: Investigate why model_obj.identifier is used instead of response.model - return OpenAIEmbeddingsResponse( - data=data, - model=model_obj.identifier, - usage=usage, - ) - - async def openai_completion( - self, - model: str, - prompt: str | list[str] | list[int] | list[list[int]], - best_of: int | None = None, - echo: bool | None = None, - frequency_penalty: float | None = None, - logit_bias: dict[str, float] | None = None, - logprobs: bool | None = None, - max_tokens: int | None = None, - n: int | None = None, - presence_penalty: float | None = None, - seed: int | None = None, - stop: str | list[str] | None = None, - stream: bool | None = None, - stream_options: dict[str, Any] | None = None, - temperature: float | None = None, - top_p: float | None = None, - user: str | None = None, - guided_choice: list[str] | None = None, - prompt_logprobs: int | None = None, - suffix: str | None = None, - ) -> OpenAICompletion: - if not isinstance(prompt, str): - raise ValueError("Ollama does not support non-string prompts for completion") - - model_obj = await self._get_model(model) - params = await prepare_openai_completion_params( - model=model_obj.provider_resource_id, - prompt=prompt, - best_of=best_of, - echo=echo, - frequency_penalty=frequency_penalty, - logit_bias=logit_bias, - logprobs=logprobs, - max_tokens=max_tokens, - n=n, - presence_penalty=presence_penalty, - seed=seed, - stop=stop, - stream=stream, - stream_options=stream_options, - temperature=temperature, - top_p=top_p, - user=user, - suffix=suffix, - ) - return await self.openai_client.completions.create(**params) # type: ignore - async def openai_chat_completion( self, model: str, @@ -599,25 +508,7 @@ class OllamaInferenceAdapter( top_p=top_p, user=user, ) - response = await self.openai_client.chat.completions.create(**params) - return await self._adjust_ollama_chat_completion_response_ids(response) - - async def _adjust_ollama_chat_completion_response_ids( - self, - response: OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk], - ) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]: - id = f"chatcmpl-{uuid.uuid4()}" - if isinstance(response, AsyncIterator): - - async def stream_with_chunk_ids() -> AsyncIterator[OpenAIChatCompletionChunk]: - async for chunk in response: - chunk.id = id - yield chunk - - return stream_with_chunk_ids() - else: - response.id = id - return response + return await OpenAIMixin.openai_chat_completion(self, **params) async def convert_message_to_openai_dict_for_ollama(message: Message) -> list[dict]: diff --git a/tests/integration/recordings/responses/3a81146f2afa.json b/tests/integration/recordings/responses/3a81146f2afa.json new file mode 100644 index 000000000..e2d2d52d6 --- /dev/null +++ b/tests/integration/recordings/responses/3a81146f2afa.json @@ -0,0 +1,990 @@ +{ + "request": { + "method": "POST", + "url": "http://0.0.0.0:11434/v1/v1/completions", + "headers": {}, + "body": { + "model": "llama3.2:3b-instruct-fp16", + "prompt": "Respond to this question and explain your answer. Complete the sentence using one word: Roses are red, violets are ", + "max_tokens": 50, + "stream": true, + "extra_body": {} + }, + "endpoint": "/v1/completions", + "model": "llama3.2:3b-instruct-fp16" + }, + "response": { + "body": [ + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": "Blue" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": ".\n\n" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": "The" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " completed" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " sentence" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " is" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " a" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " well" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": "-known" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " phrase" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " from" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " a" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " traditional" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " English" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " poem" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": ":\n\n" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": "\"" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": "R" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": "oses" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " are" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " red" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": "," + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " v" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": "io" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": "lets" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " are" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " blue" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": ",\n" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": "Sugar" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " is" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " sweet" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": "," + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " and" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " so" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " are" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " you" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": ".\"" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " However" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": "," + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " in" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " many" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " variations" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " of" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " this" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " poem" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": "," + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " the" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " line" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": " \"" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": null, + "index": 0, + "logprobs": null, + "text": "vio" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + }, + { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-439", + "choices": [ + { + "finish_reason": "length", + "index": 0, + "logprobs": null, + "text": "" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": null + } + } + ], + "is_streaming": true + } +} diff --git a/tests/integration/recordings/responses/6412295819a1.json b/tests/integration/recordings/responses/6412295819a1.json new file mode 100644 index 000000000..728380b02 --- /dev/null +++ b/tests/integration/recordings/responses/6412295819a1.json @@ -0,0 +1,43 @@ +{ + "request": { + "method": "POST", + "url": "http://0.0.0.0:11434/v1/v1/completions", + "headers": {}, + "body": { + "model": "llama3.2:3b-instruct-fp16", + "prompt": "Respond to this question and explain your answer. Complete the sentence using one word: Roses are red, violets are ", + "stream": false, + "extra_body": {} + }, + "endpoint": "/v1/completions", + "model": "llama3.2:3b-instruct-fp16" + }, + "response": { + "body": { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-104", + "choices": [ + { + "finish_reason": "stop", + "index": 0, + "logprobs": null, + "text": "blue.\n\nI completed the sentence with \"blue\" because it is a common completion used to complete the traditional nursery rhyme, which ends with:\n\nRoses are red,\nViolets are blue.\n\nThe complete rhyme is often remembered and recited as follows:\n\nRoses are red,\nViolets are blue,\nSugar is sweet,\nAnd so are you!" + } + ], + "created": 1757857132, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": { + "completion_tokens": 72, + "prompt_tokens": 50, + "total_tokens": 122, + "completion_tokens_details": null, + "prompt_tokens_details": null + } + } + }, + "is_streaming": false + } +} diff --git a/tests/integration/recordings/responses/ecae140151d1.json b/tests/integration/recordings/responses/ecae140151d1.json new file mode 100644 index 000000000..433597080 --- /dev/null +++ b/tests/integration/recordings/responses/ecae140151d1.json @@ -0,0 +1,43 @@ +{ + "request": { + "method": "POST", + "url": "http://0.0.0.0:11434/v1/v1/completions", + "headers": {}, + "body": { + "model": "llama3.2:3b-instruct-fp16", + "prompt": "Say completions", + "max_tokens": 20, + "extra_body": {} + }, + "endpoint": "/v1/completions", + "model": "llama3.2:3b-instruct-fp16" + }, + "response": { + "body": { + "__type__": "openai.types.completion.Completion", + "__data__": { + "id": "cmpl-406", + "choices": [ + { + "finish_reason": "length", + "index": 0, + "logprobs": null, + "text": "Sure, I'd be happy to provide some definitions and examples of related words or phrases.\n\nTo better" + } + ], + "created": 1757857133, + "model": "llama3.2:3b-instruct-fp16", + "object": "text_completion", + "system_fingerprint": "fp_ollama", + "usage": { + "completion_tokens": 20, + "prompt_tokens": 28, + "total_tokens": 48, + "completion_tokens_details": null, + "prompt_tokens_details": null + } + } + }, + "is_streaming": false + } +} From e66103c09d12dde7c1a8878251c09c3c6bf71eb9 Mon Sep 17 00:00:00 2001 From: Jiayi Ni Date: Thu, 18 Sep 2025 04:49:46 -0700 Subject: [PATCH 02/18] fix: add missing files provider to NVIDIA distribution (#3479) # What does this PR do? The rag-runtime tool requires files API as a dependency, but the NVIDIA distribution was missing the files provider configuration. Thus, when running: ``` llama stack build --distro nvidia --image-type venv ``` And then: ``` llama stack run {path_to_distribution_config} --image-type venv ``` It would raise an error: ``` RuntimeError: Failed to resolve 'tool_runtime' provider 'rag-runtime' of type 'inline::rag-runtime': required dependency 'files' is not available. Please add a 'files' provider to your configuration or check if the provider is properly configured. ``` This PR fixes the issue by adding missing files provider to NVIDIA distribution. ## Test Plan N/A --- .../distributions/self_hosted_distro/nvidia.md | 1 + llama_stack/distributions/nvidia/build.yaml | 2 ++ llama_stack/distributions/nvidia/nvidia.py | 13 +++++++++++-- .../distributions/nvidia/run-with-safety.yaml | 9 +++++++++ llama_stack/distributions/nvidia/run.yaml | 9 +++++++++ 5 files changed, 32 insertions(+), 2 deletions(-) diff --git a/docs/source/distributions/self_hosted_distro/nvidia.md b/docs/source/distributions/self_hosted_distro/nvidia.md index 86d025ce7..d4f070075 100644 --- a/docs/source/distributions/self_hosted_distro/nvidia.md +++ b/docs/source/distributions/self_hosted_distro/nvidia.md @@ -11,6 +11,7 @@ The `llamastack/distribution-nvidia` distribution consists of the following prov | agents | `inline::meta-reference` | | datasetio | `inline::localfs`, `remote::nvidia` | | eval | `remote::nvidia` | +| files | `inline::localfs` | | inference | `remote::nvidia` | | post_training | `remote::nvidia` | | safety | `remote::nvidia` | diff --git a/llama_stack/distributions/nvidia/build.yaml b/llama_stack/distributions/nvidia/build.yaml index f3e73a2c1..bc78756d2 100644 --- a/llama_stack/distributions/nvidia/build.yaml +++ b/llama_stack/distributions/nvidia/build.yaml @@ -23,6 +23,8 @@ distribution_spec: - provider_type: inline::basic tool_runtime: - provider_type: inline::rag-runtime + files: + - provider_type: inline::localfs image_type: venv additional_pip_packages: - aiosqlite diff --git a/llama_stack/distributions/nvidia/nvidia.py b/llama_stack/distributions/nvidia/nvidia.py index aedda0ae9..779fabf2c 100644 --- a/llama_stack/distributions/nvidia/nvidia.py +++ b/llama_stack/distributions/nvidia/nvidia.py @@ -8,6 +8,7 @@ from pathlib import Path from llama_stack.core.datatypes import BuildProvider, ModelInput, Provider, ShieldInput, ToolGroupInput from llama_stack.distributions.template import DistributionTemplate, RunConfigSettings, get_model_registry +from llama_stack.providers.inline.files.localfs.config import LocalfsFilesImplConfig from llama_stack.providers.remote.datasetio.nvidia import NvidiaDatasetIOConfig from llama_stack.providers.remote.eval.nvidia import NVIDIAEvalConfig from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig @@ -15,7 +16,7 @@ from llama_stack.providers.remote.inference.nvidia.models import MODEL_ENTRIES from llama_stack.providers.remote.safety.nvidia import NVIDIASafetyConfig -def get_distribution_template() -> DistributionTemplate: +def get_distribution_template(name: str = "nvidia") -> DistributionTemplate: providers = { "inference": [BuildProvider(provider_type="remote::nvidia")], "vector_io": [BuildProvider(provider_type="inline::faiss")], @@ -30,6 +31,7 @@ def get_distribution_template() -> DistributionTemplate: ], "scoring": [BuildProvider(provider_type="inline::basic")], "tool_runtime": [BuildProvider(provider_type="inline::rag-runtime")], + "files": [BuildProvider(provider_type="inline::localfs")], } inference_provider = Provider( @@ -52,6 +54,11 @@ def get_distribution_template() -> DistributionTemplate: provider_type="remote::nvidia", config=NVIDIAEvalConfig.sample_run_config(), ) + files_provider = Provider( + provider_id="meta-reference-files", + provider_type="inline::localfs", + config=LocalfsFilesImplConfig.sample_run_config(f"~/.llama/distributions/{name}"), + ) inference_model = ModelInput( model_id="${env.INFERENCE_MODEL}", provider_id="nvidia", @@ -73,7 +80,7 @@ def get_distribution_template() -> DistributionTemplate: default_models, _ = get_model_registry(available_models) return DistributionTemplate( - name="nvidia", + name=name, distro_type="self_hosted", description="Use NVIDIA NIM for running LLM inference, evaluation and safety", container_image=None, @@ -86,6 +93,7 @@ def get_distribution_template() -> DistributionTemplate: "inference": [inference_provider], "datasetio": [datasetio_provider], "eval": [eval_provider], + "files": [files_provider], }, default_models=default_models, default_tool_groups=default_tool_groups, @@ -97,6 +105,7 @@ def get_distribution_template() -> DistributionTemplate: safety_provider, ], "eval": [eval_provider], + "files": [files_provider], }, default_models=[inference_model, safety_model], default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}", provider_id="nvidia")], diff --git a/llama_stack/distributions/nvidia/run-with-safety.yaml b/llama_stack/distributions/nvidia/run-with-safety.yaml index 015724050..5a958116e 100644 --- a/llama_stack/distributions/nvidia/run-with-safety.yaml +++ b/llama_stack/distributions/nvidia/run-with-safety.yaml @@ -4,6 +4,7 @@ apis: - agents - datasetio - eval +- files - inference - post_training - safety @@ -88,6 +89,14 @@ providers: tool_runtime: - provider_id: rag-runtime provider_type: inline::rag-runtime + files: + - provider_id: meta-reference-files + provider_type: inline::localfs + config: + storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/nvidia/files} + metadata_store: + type: sqlite + db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/files_metadata.db metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/registry.db diff --git a/llama_stack/distributions/nvidia/run.yaml b/llama_stack/distributions/nvidia/run.yaml index 9fd6b0404..362970d2e 100644 --- a/llama_stack/distributions/nvidia/run.yaml +++ b/llama_stack/distributions/nvidia/run.yaml @@ -4,6 +4,7 @@ apis: - agents - datasetio - eval +- files - inference - post_training - safety @@ -77,6 +78,14 @@ providers: tool_runtime: - provider_id: rag-runtime provider_type: inline::rag-runtime + files: + - provider_id: meta-reference-files + provider_type: inline::localfs + config: + storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/nvidia/files} + metadata_store: + type: sqlite + db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/files_metadata.db metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/registry.db From 8422bd102a672c90f3eb189297f8e36332c4d17e Mon Sep 17 00:00:00 2001 From: Charlie Doern Date: Thu, 18 Sep 2025 10:10:00 -0400 Subject: [PATCH 03/18] feat: combine ProviderSpec datatypes (#3378) # What does this PR do? currently `RemoteProviderSpec` has an `AdapterSpec` embedded in it. Remove `AdapterSpec`, and put its leftover fields into `RemoteProviderSpec`. Additionally, many of the fields were duplicated between `InlineProviderSpec` and `RemoteProviderSpec`. Move these to `ProviderSpec` so they are shared. Fixup the distro codegen to use `RemoteProviderSpec` directly rather than `remote_provider_spec` which took an AdapterSpec and returned a full provider spec ## Test Plan existing distro tests should pass. Signed-off-by: Charlie Doern --- llama_stack/core/datatypes.py | 4 - llama_stack/core/distribution.py | 22 +- llama_stack/distributions/starter/starter.py | 4 +- llama_stack/providers/datatypes.py | 88 +--- llama_stack/providers/registry/datasetio.py | 41 +- llama_stack/providers/registry/eval.py | 21 +- llama_stack/providers/registry/files.py | 23 +- llama_stack/providers/registry/inference.py | 380 +++++++++--------- .../providers/registry/post_training.py | 17 +- llama_stack/providers/registry/safety.py | 50 ++- .../providers/registry/tool_runtime.py | 88 ++-- llama_stack/providers/registry/vector_io.py | 108 +++-- tests/external/kaze.yaml | 9 +- .../src/llama_stack_api_weather/weather.py | 11 +- tests/unit/distribution/test_distribution.py | 18 +- 15 files changed, 381 insertions(+), 503 deletions(-) diff --git a/llama_stack/core/datatypes.py b/llama_stack/core/datatypes.py index faaeefd01..b5558c66f 100644 --- a/llama_stack/core/datatypes.py +++ b/llama_stack/core/datatypes.py @@ -121,10 +121,6 @@ class AutoRoutedProviderSpec(ProviderSpec): default=None, ) - @property - def pip_packages(self) -> list[str]: - raise AssertionError("Should not be called on AutoRoutedProviderSpec") - # Example: /models, /shields class RoutingTableProviderSpec(ProviderSpec): diff --git a/llama_stack/core/distribution.py b/llama_stack/core/distribution.py index c104b6764..302ecb960 100644 --- a/llama_stack/core/distribution.py +++ b/llama_stack/core/distribution.py @@ -16,11 +16,10 @@ from llama_stack.core.datatypes import BuildConfig, DistributionSpec from llama_stack.core.external import load_external_apis from llama_stack.log import get_logger from llama_stack.providers.datatypes import ( - AdapterSpec, Api, InlineProviderSpec, ProviderSpec, - remote_provider_spec, + RemoteProviderSpec, ) logger = get_logger(name=__name__, category="core") @@ -77,27 +76,12 @@ def providable_apis() -> list[Api]: def _load_remote_provider_spec(spec_data: dict[str, Any], api: Api) -> ProviderSpec: - adapter = AdapterSpec(**spec_data["adapter"]) - spec = remote_provider_spec( - api=api, - adapter=adapter, - api_dependencies=[Api(dep) for dep in spec_data.get("api_dependencies", [])], - ) + spec = RemoteProviderSpec(api=api, provider_type=f"remote::{spec_data['adapter_type']}", **spec_data) return spec def _load_inline_provider_spec(spec_data: dict[str, Any], api: Api, provider_name: str) -> ProviderSpec: - spec = InlineProviderSpec( - api=api, - provider_type=f"inline::{provider_name}", - pip_packages=spec_data.get("pip_packages", []), - module=spec_data["module"], - config_class=spec_data["config_class"], - api_dependencies=[Api(dep) for dep in spec_data.get("api_dependencies", [])], - optional_api_dependencies=[Api(dep) for dep in spec_data.get("optional_api_dependencies", [])], - provider_data_validator=spec_data.get("provider_data_validator"), - container_image=spec_data.get("container_image"), - ) + spec = InlineProviderSpec(api=api, provider_type=f"inline::{provider_name}", **spec_data) return spec diff --git a/llama_stack/distributions/starter/starter.py b/llama_stack/distributions/starter/starter.py index c2dfe95ad..6bee51ff0 100644 --- a/llama_stack/distributions/starter/starter.py +++ b/llama_stack/distributions/starter/starter.py @@ -78,12 +78,12 @@ def get_remote_inference_providers() -> list[Provider]: remote_providers = [ provider for provider in available_providers() - if isinstance(provider, RemoteProviderSpec) and provider.adapter.adapter_type in ENABLED_INFERENCE_PROVIDERS + if isinstance(provider, RemoteProviderSpec) and provider.adapter_type in ENABLED_INFERENCE_PROVIDERS ] inference_providers = [] for provider_spec in remote_providers: - provider_type = provider_spec.adapter.adapter_type + provider_type = provider_spec.adapter_type if provider_type in INFERENCE_PROVIDER_IDS: provider_id = INFERENCE_PROVIDER_IDS[provider_type] diff --git a/llama_stack/providers/datatypes.py b/llama_stack/providers/datatypes.py index 5e15dd8e1..c8ff9cecb 100644 --- a/llama_stack/providers/datatypes.py +++ b/llama_stack/providers/datatypes.py @@ -131,6 +131,15 @@ class ProviderSpec(BaseModel): """, ) + pip_packages: list[str] = Field( + default_factory=list, + description="The pip dependencies needed for this implementation", + ) + + provider_data_validator: str | None = Field( + default=None, + ) + is_external: bool = Field(default=False, description="Notes whether this provider is an external provider.") # used internally by the resolver; this is a hack for now @@ -145,45 +154,8 @@ class RoutingTable(Protocol): async def get_provider_impl(self, routing_key: str) -> Any: ... -# TODO: this can now be inlined into RemoteProviderSpec -@json_schema_type -class AdapterSpec(BaseModel): - adapter_type: str = Field( - ..., - description="Unique identifier for this adapter", - ) - module: str = Field( - default_factory=str, - description=""" -Fully-qualified name of the module to import. The module is expected to have: - - - `get_adapter_impl(config, deps)`: returns the adapter implementation -""", - ) - pip_packages: list[str] = Field( - default_factory=list, - description="The pip dependencies needed for this implementation", - ) - config_class: str = Field( - description="Fully-qualified classname of the config for this provider", - ) - provider_data_validator: str | None = Field( - default=None, - ) - description: str | None = Field( - default=None, - description=""" -A description of the provider. This is used to display in the documentation. -""", - ) - - @json_schema_type class InlineProviderSpec(ProviderSpec): - pip_packages: list[str] = Field( - default_factory=list, - description="The pip dependencies needed for this implementation", - ) container_image: str | None = Field( default=None, description=""" @@ -191,10 +163,6 @@ The container image to use for this implementation. If one is provided, pip_pack If a provider depends on other providers, the dependencies MUST NOT specify a container image. """, ) - # module field is inherited from ProviderSpec - provider_data_validator: str | None = Field( - default=None, - ) description: str | None = Field( default=None, description=""" @@ -223,10 +191,15 @@ class RemoteProviderConfig(BaseModel): @json_schema_type class RemoteProviderSpec(ProviderSpec): - adapter: AdapterSpec = Field( + adapter_type: str = Field( + ..., + description="Unique identifier for this adapter", + ) + + description: str | None = Field( + default=None, description=""" -If some code is needed to convert the remote responses into Llama Stack compatible -API responses, specify the adapter here. +A description of the provider. This is used to display in the documentation. """, ) @@ -234,33 +207,6 @@ API responses, specify the adapter here. def container_image(self) -> str | None: return None - # module field is inherited from ProviderSpec - - @property - def pip_packages(self) -> list[str]: - return self.adapter.pip_packages - - @property - def provider_data_validator(self) -> str | None: - return self.adapter.provider_data_validator - - -def remote_provider_spec( - api: Api, - adapter: AdapterSpec, - api_dependencies: list[Api] | None = None, - optional_api_dependencies: list[Api] | None = None, -) -> RemoteProviderSpec: - return RemoteProviderSpec( - api=api, - provider_type=f"remote::{adapter.adapter_type}", - config_class=adapter.config_class, - module=adapter.module, - adapter=adapter, - api_dependencies=api_dependencies or [], - optional_api_dependencies=optional_api_dependencies or [], - ) - class HealthStatus(StrEnum): OK = "OK" diff --git a/llama_stack/providers/registry/datasetio.py b/llama_stack/providers/registry/datasetio.py index f641b4ce3..a9feb0bac 100644 --- a/llama_stack/providers/registry/datasetio.py +++ b/llama_stack/providers/registry/datasetio.py @@ -6,11 +6,10 @@ from llama_stack.providers.datatypes import ( - AdapterSpec, Api, InlineProviderSpec, ProviderSpec, - remote_provider_spec, + RemoteProviderSpec, ) @@ -25,28 +24,26 @@ def available_providers() -> list[ProviderSpec]: api_dependencies=[], description="Local filesystem-based dataset I/O provider for reading and writing datasets to local storage.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.datasetio, - adapter=AdapterSpec( - adapter_type="huggingface", - pip_packages=[ - "datasets>=4.0.0", - ], - module="llama_stack.providers.remote.datasetio.huggingface", - config_class="llama_stack.providers.remote.datasetio.huggingface.HuggingfaceDatasetIOConfig", - description="HuggingFace datasets provider for accessing and managing datasets from the HuggingFace Hub.", - ), + adapter_type="huggingface", + provider_type="remote::huggingface", + pip_packages=[ + "datasets>=4.0.0", + ], + module="llama_stack.providers.remote.datasetio.huggingface", + config_class="llama_stack.providers.remote.datasetio.huggingface.HuggingfaceDatasetIOConfig", + description="HuggingFace datasets provider for accessing and managing datasets from the HuggingFace Hub.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.datasetio, - adapter=AdapterSpec( - adapter_type="nvidia", - pip_packages=[ - "datasets>=4.0.0", - ], - module="llama_stack.providers.remote.datasetio.nvidia", - config_class="llama_stack.providers.remote.datasetio.nvidia.NvidiaDatasetIOConfig", - description="NVIDIA's dataset I/O provider for accessing datasets from NVIDIA's data platform.", - ), + adapter_type="nvidia", + provider_type="remote::nvidia", + module="llama_stack.providers.remote.datasetio.nvidia", + config_class="llama_stack.providers.remote.datasetio.nvidia.NvidiaDatasetIOConfig", + pip_packages=[ + "datasets>=4.0.0", + ], + description="NVIDIA's dataset I/O provider for accessing datasets from NVIDIA's data platform.", ), ] diff --git a/llama_stack/providers/registry/eval.py b/llama_stack/providers/registry/eval.py index 9f0d17916..4ef0bb41f 100644 --- a/llama_stack/providers/registry/eval.py +++ b/llama_stack/providers/registry/eval.py @@ -5,7 +5,7 @@ # the root directory of this source tree. -from llama_stack.providers.datatypes import AdapterSpec, Api, InlineProviderSpec, ProviderSpec, remote_provider_spec +from llama_stack.providers.datatypes import Api, InlineProviderSpec, ProviderSpec, RemoteProviderSpec def available_providers() -> list[ProviderSpec]: @@ -25,17 +25,16 @@ def available_providers() -> list[ProviderSpec]: ], description="Meta's reference implementation of evaluation tasks with support for multiple languages and evaluation metrics.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.eval, - adapter=AdapterSpec( - adapter_type="nvidia", - pip_packages=[ - "requests", - ], - module="llama_stack.providers.remote.eval.nvidia", - config_class="llama_stack.providers.remote.eval.nvidia.NVIDIAEvalConfig", - description="NVIDIA's evaluation provider for running evaluation tasks on NVIDIA's platform.", - ), + adapter_type="nvidia", + pip_packages=[ + "requests", + ], + provider_type="remote::nvidia", + module="llama_stack.providers.remote.eval.nvidia", + config_class="llama_stack.providers.remote.eval.nvidia.NVIDIAEvalConfig", + description="NVIDIA's evaluation provider for running evaluation tasks on NVIDIA's platform.", api_dependencies=[ Api.datasetio, Api.datasets, diff --git a/llama_stack/providers/registry/files.py b/llama_stack/providers/registry/files.py index ebe90310c..9acabfacd 100644 --- a/llama_stack/providers/registry/files.py +++ b/llama_stack/providers/registry/files.py @@ -4,13 +4,7 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.providers.datatypes import ( - AdapterSpec, - Api, - InlineProviderSpec, - ProviderSpec, - remote_provider_spec, -) +from llama_stack.providers.datatypes import Api, InlineProviderSpec, ProviderSpec, RemoteProviderSpec from llama_stack.providers.utils.sqlstore.sqlstore import sql_store_pip_packages @@ -25,14 +19,13 @@ def available_providers() -> list[ProviderSpec]: config_class="llama_stack.providers.inline.files.localfs.config.LocalfsFilesImplConfig", description="Local filesystem-based file storage provider for managing files and documents locally.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.files, - adapter=AdapterSpec( - adapter_type="s3", - pip_packages=["boto3"] + sql_store_pip_packages, - module="llama_stack.providers.remote.files.s3", - config_class="llama_stack.providers.remote.files.s3.config.S3FilesImplConfig", - description="AWS S3-based file storage provider for scalable cloud file management with metadata persistence.", - ), + provider_type="remote::s3", + adapter_type="s3", + pip_packages=["boto3"] + sql_store_pip_packages, + module="llama_stack.providers.remote.files.s3", + config_class="llama_stack.providers.remote.files.s3.config.S3FilesImplConfig", + description="AWS S3-based file storage provider for scalable cloud file management with metadata persistence.", ), ] diff --git a/llama_stack/providers/registry/inference.py b/llama_stack/providers/registry/inference.py index 0eb4cf104..658611698 100644 --- a/llama_stack/providers/registry/inference.py +++ b/llama_stack/providers/registry/inference.py @@ -6,11 +6,10 @@ from llama_stack.providers.datatypes import ( - AdapterSpec, Api, InlineProviderSpec, ProviderSpec, - remote_provider_spec, + RemoteProviderSpec, ) META_REFERENCE_DEPS = [ @@ -49,177 +48,167 @@ def available_providers() -> list[ProviderSpec]: config_class="llama_stack.providers.inline.inference.sentence_transformers.config.SentenceTransformersInferenceConfig", description="Sentence Transformers inference provider for text embeddings and similarity search.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="cerebras", - pip_packages=[ - "cerebras_cloud_sdk", - ], - module="llama_stack.providers.remote.inference.cerebras", - config_class="llama_stack.providers.remote.inference.cerebras.CerebrasImplConfig", - description="Cerebras inference provider for running models on Cerebras Cloud platform.", - ), + adapter_type="cerebras", + provider_type="remote::cerebras", + pip_packages=[ + "cerebras_cloud_sdk", + ], + module="llama_stack.providers.remote.inference.cerebras", + config_class="llama_stack.providers.remote.inference.cerebras.CerebrasImplConfig", + description="Cerebras inference provider for running models on Cerebras Cloud platform.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="ollama", - pip_packages=["ollama", "aiohttp", "h11>=0.16.0"], - config_class="llama_stack.providers.remote.inference.ollama.OllamaImplConfig", - module="llama_stack.providers.remote.inference.ollama", - description="Ollama inference provider for running local models through the Ollama runtime.", - ), + adapter_type="ollama", + provider_type="remote::ollama", + pip_packages=["ollama", "aiohttp", "h11>=0.16.0"], + config_class="llama_stack.providers.remote.inference.ollama.OllamaImplConfig", + module="llama_stack.providers.remote.inference.ollama", + description="Ollama inference provider for running local models through the Ollama runtime.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="vllm", - pip_packages=[], - module="llama_stack.providers.remote.inference.vllm", - config_class="llama_stack.providers.remote.inference.vllm.VLLMInferenceAdapterConfig", - provider_data_validator="llama_stack.providers.remote.inference.vllm.VLLMProviderDataValidator", - description="Remote vLLM inference provider for connecting to vLLM servers.", - ), + adapter_type="vllm", + provider_type="remote::vllm", + pip_packages=[], + module="llama_stack.providers.remote.inference.vllm", + config_class="llama_stack.providers.remote.inference.vllm.VLLMInferenceAdapterConfig", + provider_data_validator="llama_stack.providers.remote.inference.vllm.VLLMProviderDataValidator", + description="Remote vLLM inference provider for connecting to vLLM servers.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="tgi", - pip_packages=["huggingface_hub", "aiohttp"], - module="llama_stack.providers.remote.inference.tgi", - config_class="llama_stack.providers.remote.inference.tgi.TGIImplConfig", - description="Text Generation Inference (TGI) provider for HuggingFace model serving.", - ), + adapter_type="tgi", + provider_type="remote::tgi", + pip_packages=["huggingface_hub", "aiohttp"], + module="llama_stack.providers.remote.inference.tgi", + config_class="llama_stack.providers.remote.inference.tgi.TGIImplConfig", + description="Text Generation Inference (TGI) provider for HuggingFace model serving.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="hf::serverless", - pip_packages=["huggingface_hub", "aiohttp"], - module="llama_stack.providers.remote.inference.tgi", - config_class="llama_stack.providers.remote.inference.tgi.InferenceAPIImplConfig", - description="HuggingFace Inference API serverless provider for on-demand model inference.", - ), + adapter_type="hf::serverless", + provider_type="remote::hf::serverless", + pip_packages=["huggingface_hub", "aiohttp"], + module="llama_stack.providers.remote.inference.tgi", + config_class="llama_stack.providers.remote.inference.tgi.InferenceAPIImplConfig", + description="HuggingFace Inference API serverless provider for on-demand model inference.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="hf::endpoint", - pip_packages=["huggingface_hub", "aiohttp"], - module="llama_stack.providers.remote.inference.tgi", - config_class="llama_stack.providers.remote.inference.tgi.InferenceEndpointImplConfig", - description="HuggingFace Inference Endpoints provider for dedicated model serving.", - ), + provider_type="remote::hf::endpoint", + adapter_type="hf::endpoint", + pip_packages=["huggingface_hub", "aiohttp"], + module="llama_stack.providers.remote.inference.tgi", + config_class="llama_stack.providers.remote.inference.tgi.InferenceEndpointImplConfig", + description="HuggingFace Inference Endpoints provider for dedicated model serving.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="fireworks", - pip_packages=[ - "fireworks-ai<=0.17.16", - ], - module="llama_stack.providers.remote.inference.fireworks", - config_class="llama_stack.providers.remote.inference.fireworks.FireworksImplConfig", - provider_data_validator="llama_stack.providers.remote.inference.fireworks.FireworksProviderDataValidator", - description="Fireworks AI inference provider for Llama models and other AI models on the Fireworks platform.", - ), + adapter_type="fireworks", + provider_type="remote::fireworks", + pip_packages=[ + "fireworks-ai<=0.17.16", + ], + module="llama_stack.providers.remote.inference.fireworks", + config_class="llama_stack.providers.remote.inference.fireworks.FireworksImplConfig", + provider_data_validator="llama_stack.providers.remote.inference.fireworks.FireworksProviderDataValidator", + description="Fireworks AI inference provider for Llama models and other AI models on the Fireworks platform.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="together", - pip_packages=[ - "together", - ], - module="llama_stack.providers.remote.inference.together", - config_class="llama_stack.providers.remote.inference.together.TogetherImplConfig", - provider_data_validator="llama_stack.providers.remote.inference.together.TogetherProviderDataValidator", - description="Together AI inference provider for open-source models and collaborative AI development.", - ), + adapter_type="together", + provider_type="remote::together", + pip_packages=[ + "together", + ], + module="llama_stack.providers.remote.inference.together", + config_class="llama_stack.providers.remote.inference.together.TogetherImplConfig", + provider_data_validator="llama_stack.providers.remote.inference.together.TogetherProviderDataValidator", + description="Together AI inference provider for open-source models and collaborative AI development.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="bedrock", - pip_packages=["boto3"], - module="llama_stack.providers.remote.inference.bedrock", - config_class="llama_stack.providers.remote.inference.bedrock.BedrockConfig", - description="AWS Bedrock inference provider for accessing various AI models through AWS's managed service.", - ), + adapter_type="bedrock", + provider_type="remote::bedrock", + pip_packages=["boto3"], + module="llama_stack.providers.remote.inference.bedrock", + config_class="llama_stack.providers.remote.inference.bedrock.BedrockConfig", + description="AWS Bedrock inference provider for accessing various AI models through AWS's managed service.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="databricks", - pip_packages=[], - module="llama_stack.providers.remote.inference.databricks", - config_class="llama_stack.providers.remote.inference.databricks.DatabricksImplConfig", - description="Databricks inference provider for running models on Databricks' unified analytics platform.", - ), + adapter_type="databricks", + provider_type="remote::databricks", + pip_packages=[], + module="llama_stack.providers.remote.inference.databricks", + config_class="llama_stack.providers.remote.inference.databricks.DatabricksImplConfig", + description="Databricks inference provider for running models on Databricks' unified analytics platform.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="nvidia", - pip_packages=[], - module="llama_stack.providers.remote.inference.nvidia", - config_class="llama_stack.providers.remote.inference.nvidia.NVIDIAConfig", - description="NVIDIA inference provider for accessing NVIDIA NIM models and AI services.", - ), + adapter_type="nvidia", + provider_type="remote::nvidia", + pip_packages=[], + module="llama_stack.providers.remote.inference.nvidia", + config_class="llama_stack.providers.remote.inference.nvidia.NVIDIAConfig", + description="NVIDIA inference provider for accessing NVIDIA NIM models and AI services.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="runpod", - pip_packages=[], - module="llama_stack.providers.remote.inference.runpod", - config_class="llama_stack.providers.remote.inference.runpod.RunpodImplConfig", - description="RunPod inference provider for running models on RunPod's cloud GPU platform.", - ), + adapter_type="runpod", + provider_type="remote::runpod", + pip_packages=[], + module="llama_stack.providers.remote.inference.runpod", + config_class="llama_stack.providers.remote.inference.runpod.RunpodImplConfig", + description="RunPod inference provider for running models on RunPod's cloud GPU platform.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="openai", - pip_packages=["litellm"], - module="llama_stack.providers.remote.inference.openai", - config_class="llama_stack.providers.remote.inference.openai.OpenAIConfig", - provider_data_validator="llama_stack.providers.remote.inference.openai.config.OpenAIProviderDataValidator", - description="OpenAI inference provider for accessing GPT models and other OpenAI services.", - ), + adapter_type="openai", + provider_type="remote::openai", + pip_packages=["litellm"], + module="llama_stack.providers.remote.inference.openai", + config_class="llama_stack.providers.remote.inference.openai.OpenAIConfig", + provider_data_validator="llama_stack.providers.remote.inference.openai.config.OpenAIProviderDataValidator", + description="OpenAI inference provider for accessing GPT models and other OpenAI services.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="anthropic", - pip_packages=["litellm"], - module="llama_stack.providers.remote.inference.anthropic", - config_class="llama_stack.providers.remote.inference.anthropic.AnthropicConfig", - provider_data_validator="llama_stack.providers.remote.inference.anthropic.config.AnthropicProviderDataValidator", - description="Anthropic inference provider for accessing Claude models and Anthropic's AI services.", - ), + adapter_type="anthropic", + provider_type="remote::anthropic", + pip_packages=["litellm"], + module="llama_stack.providers.remote.inference.anthropic", + config_class="llama_stack.providers.remote.inference.anthropic.AnthropicConfig", + provider_data_validator="llama_stack.providers.remote.inference.anthropic.config.AnthropicProviderDataValidator", + description="Anthropic inference provider for accessing Claude models and Anthropic's AI services.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="gemini", - pip_packages=["litellm"], - module="llama_stack.providers.remote.inference.gemini", - config_class="llama_stack.providers.remote.inference.gemini.GeminiConfig", - provider_data_validator="llama_stack.providers.remote.inference.gemini.config.GeminiProviderDataValidator", - description="Google Gemini inference provider for accessing Gemini models and Google's AI services.", - ), + adapter_type="gemini", + provider_type="remote::gemini", + pip_packages=[ + "litellm", + ], + module="llama_stack.providers.remote.inference.gemini", + config_class="llama_stack.providers.remote.inference.gemini.GeminiConfig", + provider_data_validator="llama_stack.providers.remote.inference.gemini.config.GeminiProviderDataValidator", + description="Google Gemini inference provider for accessing Gemini models and Google's AI services.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="vertexai", - pip_packages=["litellm", "google-cloud-aiplatform"], - module="llama_stack.providers.remote.inference.vertexai", - config_class="llama_stack.providers.remote.inference.vertexai.VertexAIConfig", - provider_data_validator="llama_stack.providers.remote.inference.vertexai.config.VertexAIProviderDataValidator", - description="""Google Vertex AI inference provider enables you to use Google's Gemini models through Google Cloud's Vertex AI platform, providing several advantages: + adapter_type="vertexai", + provider_type="remote::vertexai", + pip_packages=[ + "litellm", + "google-cloud-aiplatform", + ], + module="llama_stack.providers.remote.inference.vertexai", + config_class="llama_stack.providers.remote.inference.vertexai.VertexAIConfig", + provider_data_validator="llama_stack.providers.remote.inference.vertexai.config.VertexAIProviderDataValidator", + description="""Google Vertex AI inference provider enables you to use Google's Gemini models through Google Cloud's Vertex AI platform, providing several advantages: • Enterprise-grade security: Uses Google Cloud's security controls and IAM • Better integration: Seamless integration with other Google Cloud services @@ -239,76 +228,73 @@ Available Models: - vertex_ai/gemini-2.0-flash - vertex_ai/gemini-2.5-flash - vertex_ai/gemini-2.5-pro""", - ), ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="groq", - pip_packages=["litellm"], - module="llama_stack.providers.remote.inference.groq", - config_class="llama_stack.providers.remote.inference.groq.GroqConfig", - provider_data_validator="llama_stack.providers.remote.inference.groq.config.GroqProviderDataValidator", - description="Groq inference provider for ultra-fast inference using Groq's LPU technology.", - ), + adapter_type="groq", + provider_type="remote::groq", + pip_packages=[ + "litellm", + ], + module="llama_stack.providers.remote.inference.groq", + config_class="llama_stack.providers.remote.inference.groq.GroqConfig", + provider_data_validator="llama_stack.providers.remote.inference.groq.config.GroqProviderDataValidator", + description="Groq inference provider for ultra-fast inference using Groq's LPU technology.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="llama-openai-compat", - pip_packages=["litellm"], - module="llama_stack.providers.remote.inference.llama_openai_compat", - config_class="llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaCompatConfig", - provider_data_validator="llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaProviderDataValidator", - description="Llama OpenAI-compatible provider for using Llama models with OpenAI API format.", - ), + adapter_type="llama-openai-compat", + provider_type="remote::llama-openai-compat", + pip_packages=["litellm"], + module="llama_stack.providers.remote.inference.llama_openai_compat", + config_class="llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaCompatConfig", + provider_data_validator="llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaProviderDataValidator", + description="Llama OpenAI-compatible provider for using Llama models with OpenAI API format.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="sambanova", - pip_packages=["litellm"], - module="llama_stack.providers.remote.inference.sambanova", - config_class="llama_stack.providers.remote.inference.sambanova.SambaNovaImplConfig", - provider_data_validator="llama_stack.providers.remote.inference.sambanova.config.SambaNovaProviderDataValidator", - description="SambaNova inference provider for running models on SambaNova's dataflow architecture.", - ), + adapter_type="sambanova", + provider_type="remote::sambanova", + pip_packages=[ + "litellm", + ], + module="llama_stack.providers.remote.inference.sambanova", + config_class="llama_stack.providers.remote.inference.sambanova.SambaNovaImplConfig", + provider_data_validator="llama_stack.providers.remote.inference.sambanova.config.SambaNovaProviderDataValidator", + description="SambaNova inference provider for running models on SambaNova's dataflow architecture.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="passthrough", - pip_packages=[], - module="llama_stack.providers.remote.inference.passthrough", - config_class="llama_stack.providers.remote.inference.passthrough.PassthroughImplConfig", - provider_data_validator="llama_stack.providers.remote.inference.passthrough.PassthroughProviderDataValidator", - description="Passthrough inference provider for connecting to any external inference service not directly supported.", - ), + adapter_type="passthrough", + provider_type="remote::passthrough", + pip_packages=[], + module="llama_stack.providers.remote.inference.passthrough", + config_class="llama_stack.providers.remote.inference.passthrough.PassthroughImplConfig", + provider_data_validator="llama_stack.providers.remote.inference.passthrough.PassthroughProviderDataValidator", + description="Passthrough inference provider for connecting to any external inference service not directly supported.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="watsonx", - pip_packages=["ibm_watsonx_ai"], - module="llama_stack.providers.remote.inference.watsonx", - config_class="llama_stack.providers.remote.inference.watsonx.WatsonXConfig", - provider_data_validator="llama_stack.providers.remote.inference.watsonx.WatsonXProviderDataValidator", - description="IBM WatsonX inference provider for accessing AI models on IBM's WatsonX platform.", - ), + adapter_type="watsonx", + provider_type="remote::watsonx", + pip_packages=["ibm_watsonx_ai"], + module="llama_stack.providers.remote.inference.watsonx", + config_class="llama_stack.providers.remote.inference.watsonx.WatsonXConfig", + provider_data_validator="llama_stack.providers.remote.inference.watsonx.WatsonXProviderDataValidator", + description="IBM WatsonX inference provider for accessing AI models on IBM's WatsonX platform.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.inference, - adapter=AdapterSpec( - adapter_type="azure", - pip_packages=["litellm"], - module="llama_stack.providers.remote.inference.azure", - config_class="llama_stack.providers.remote.inference.azure.AzureConfig", - provider_data_validator="llama_stack.providers.remote.inference.azure.config.AzureProviderDataValidator", - description=""" + provider_type="remote::azure", + adapter_type="azure", + pip_packages=["litellm"], + module="llama_stack.providers.remote.inference.azure", + config_class="llama_stack.providers.remote.inference.azure.AzureConfig", + provider_data_validator="llama_stack.providers.remote.inference.azure.config.AzureProviderDataValidator", + description=""" Azure OpenAI inference provider for accessing GPT models and other Azure services. Provider documentation https://learn.microsoft.com/en-us/azure/ai-foundry/openai/overview """, - ), ), ] diff --git a/llama_stack/providers/registry/post_training.py b/llama_stack/providers/registry/post_training.py index 47aeb401e..2092e3b2d 100644 --- a/llama_stack/providers/registry/post_training.py +++ b/llama_stack/providers/registry/post_training.py @@ -7,7 +7,7 @@ from typing import cast -from llama_stack.providers.datatypes import AdapterSpec, Api, InlineProviderSpec, ProviderSpec, remote_provider_spec +from llama_stack.providers.datatypes import Api, InlineProviderSpec, ProviderSpec, RemoteProviderSpec # We provide two versions of these providers so that distributions can package the appropriate version of torch. # The CPU version is used for distributions that don't have GPU support -- they result in smaller container images. @@ -57,14 +57,13 @@ def available_providers() -> list[ProviderSpec]: ], description="HuggingFace-based post-training provider for fine-tuning models using the HuggingFace ecosystem.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.post_training, - adapter=AdapterSpec( - adapter_type="nvidia", - pip_packages=["requests", "aiohttp"], - module="llama_stack.providers.remote.post_training.nvidia", - config_class="llama_stack.providers.remote.post_training.nvidia.NvidiaPostTrainingConfig", - description="NVIDIA's post-training provider for fine-tuning models on NVIDIA's platform.", - ), + adapter_type="nvidia", + provider_type="remote::nvidia", + pip_packages=["requests", "aiohttp"], + module="llama_stack.providers.remote.post_training.nvidia", + config_class="llama_stack.providers.remote.post_training.nvidia.NvidiaPostTrainingConfig", + description="NVIDIA's post-training provider for fine-tuning models on NVIDIA's platform.", ), ] diff --git a/llama_stack/providers/registry/safety.py b/llama_stack/providers/registry/safety.py index 9dd791bd8..b30074398 100644 --- a/llama_stack/providers/registry/safety.py +++ b/llama_stack/providers/registry/safety.py @@ -6,11 +6,10 @@ from llama_stack.providers.datatypes import ( - AdapterSpec, Api, InlineProviderSpec, ProviderSpec, - remote_provider_spec, + RemoteProviderSpec, ) @@ -48,35 +47,32 @@ def available_providers() -> list[ProviderSpec]: config_class="llama_stack.providers.inline.safety.code_scanner.CodeScannerConfig", description="Code Scanner safety provider for detecting security vulnerabilities and unsafe code patterns.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.safety, - adapter=AdapterSpec( - adapter_type="bedrock", - pip_packages=["boto3"], - module="llama_stack.providers.remote.safety.bedrock", - config_class="llama_stack.providers.remote.safety.bedrock.BedrockSafetyConfig", - description="AWS Bedrock safety provider for content moderation using AWS's safety services.", - ), + adapter_type="bedrock", + provider_type="remote::bedrock", + pip_packages=["boto3"], + module="llama_stack.providers.remote.safety.bedrock", + config_class="llama_stack.providers.remote.safety.bedrock.BedrockSafetyConfig", + description="AWS Bedrock safety provider for content moderation using AWS's safety services.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.safety, - adapter=AdapterSpec( - adapter_type="nvidia", - pip_packages=["requests"], - module="llama_stack.providers.remote.safety.nvidia", - config_class="llama_stack.providers.remote.safety.nvidia.NVIDIASafetyConfig", - description="NVIDIA's safety provider for content moderation and safety filtering.", - ), + adapter_type="nvidia", + provider_type="remote::nvidia", + pip_packages=["requests"], + module="llama_stack.providers.remote.safety.nvidia", + config_class="llama_stack.providers.remote.safety.nvidia.NVIDIASafetyConfig", + description="NVIDIA's safety provider for content moderation and safety filtering.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.safety, - adapter=AdapterSpec( - adapter_type="sambanova", - pip_packages=["litellm", "requests"], - module="llama_stack.providers.remote.safety.sambanova", - config_class="llama_stack.providers.remote.safety.sambanova.SambaNovaSafetyConfig", - provider_data_validator="llama_stack.providers.remote.safety.sambanova.config.SambaNovaProviderDataValidator", - description="SambaNova's safety provider for content moderation and safety filtering.", - ), + adapter_type="sambanova", + provider_type="remote::sambanova", + pip_packages=["litellm", "requests"], + module="llama_stack.providers.remote.safety.sambanova", + config_class="llama_stack.providers.remote.safety.sambanova.SambaNovaSafetyConfig", + provider_data_validator="llama_stack.providers.remote.safety.sambanova.config.SambaNovaProviderDataValidator", + description="SambaNova's safety provider for content moderation and safety filtering.", ), ] diff --git a/llama_stack/providers/registry/tool_runtime.py b/llama_stack/providers/registry/tool_runtime.py index 5a58fa7af..ad8c31dfd 100644 --- a/llama_stack/providers/registry/tool_runtime.py +++ b/llama_stack/providers/registry/tool_runtime.py @@ -6,11 +6,10 @@ from llama_stack.providers.datatypes import ( - AdapterSpec, Api, InlineProviderSpec, ProviderSpec, - remote_provider_spec, + RemoteProviderSpec, ) @@ -35,59 +34,54 @@ def available_providers() -> list[ProviderSpec]: api_dependencies=[Api.vector_io, Api.inference, Api.files], description="RAG (Retrieval-Augmented Generation) tool runtime for document ingestion, chunking, and semantic search.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.tool_runtime, - adapter=AdapterSpec( - adapter_type="brave-search", - module="llama_stack.providers.remote.tool_runtime.brave_search", - config_class="llama_stack.providers.remote.tool_runtime.brave_search.config.BraveSearchToolConfig", - pip_packages=["requests"], - provider_data_validator="llama_stack.providers.remote.tool_runtime.brave_search.BraveSearchToolProviderDataValidator", - description="Brave Search tool for web search capabilities with privacy-focused results.", - ), + adapter_type="brave-search", + provider_type="remote::brave-search", + module="llama_stack.providers.remote.tool_runtime.brave_search", + config_class="llama_stack.providers.remote.tool_runtime.brave_search.config.BraveSearchToolConfig", + pip_packages=["requests"], + provider_data_validator="llama_stack.providers.remote.tool_runtime.brave_search.BraveSearchToolProviderDataValidator", + description="Brave Search tool for web search capabilities with privacy-focused results.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.tool_runtime, - adapter=AdapterSpec( - adapter_type="bing-search", - module="llama_stack.providers.remote.tool_runtime.bing_search", - config_class="llama_stack.providers.remote.tool_runtime.bing_search.config.BingSearchToolConfig", - pip_packages=["requests"], - provider_data_validator="llama_stack.providers.remote.tool_runtime.bing_search.BingSearchToolProviderDataValidator", - description="Bing Search tool for web search capabilities using Microsoft's search engine.", - ), + adapter_type="bing-search", + provider_type="remote::bing-search", + module="llama_stack.providers.remote.tool_runtime.bing_search", + config_class="llama_stack.providers.remote.tool_runtime.bing_search.config.BingSearchToolConfig", + pip_packages=["requests"], + provider_data_validator="llama_stack.providers.remote.tool_runtime.bing_search.BingSearchToolProviderDataValidator", + description="Bing Search tool for web search capabilities using Microsoft's search engine.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.tool_runtime, - adapter=AdapterSpec( - adapter_type="tavily-search", - module="llama_stack.providers.remote.tool_runtime.tavily_search", - config_class="llama_stack.providers.remote.tool_runtime.tavily_search.config.TavilySearchToolConfig", - pip_packages=["requests"], - provider_data_validator="llama_stack.providers.remote.tool_runtime.tavily_search.TavilySearchToolProviderDataValidator", - description="Tavily Search tool for AI-optimized web search with structured results.", - ), + adapter_type="tavily-search", + provider_type="remote::tavily-search", + module="llama_stack.providers.remote.tool_runtime.tavily_search", + config_class="llama_stack.providers.remote.tool_runtime.tavily_search.config.TavilySearchToolConfig", + pip_packages=["requests"], + provider_data_validator="llama_stack.providers.remote.tool_runtime.tavily_search.TavilySearchToolProviderDataValidator", + description="Tavily Search tool for AI-optimized web search with structured results.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.tool_runtime, - adapter=AdapterSpec( - adapter_type="wolfram-alpha", - module="llama_stack.providers.remote.tool_runtime.wolfram_alpha", - config_class="llama_stack.providers.remote.tool_runtime.wolfram_alpha.config.WolframAlphaToolConfig", - pip_packages=["requests"], - provider_data_validator="llama_stack.providers.remote.tool_runtime.wolfram_alpha.WolframAlphaToolProviderDataValidator", - description="Wolfram Alpha tool for computational knowledge and mathematical calculations.", - ), + adapter_type="wolfram-alpha", + provider_type="remote::wolfram-alpha", + module="llama_stack.providers.remote.tool_runtime.wolfram_alpha", + config_class="llama_stack.providers.remote.tool_runtime.wolfram_alpha.config.WolframAlphaToolConfig", + pip_packages=["requests"], + provider_data_validator="llama_stack.providers.remote.tool_runtime.wolfram_alpha.WolframAlphaToolProviderDataValidator", + description="Wolfram Alpha tool for computational knowledge and mathematical calculations.", ), - remote_provider_spec( + RemoteProviderSpec( api=Api.tool_runtime, - adapter=AdapterSpec( - adapter_type="model-context-protocol", - module="llama_stack.providers.remote.tool_runtime.model_context_protocol", - config_class="llama_stack.providers.remote.tool_runtime.model_context_protocol.config.MCPProviderConfig", - pip_packages=["mcp>=1.8.1"], - provider_data_validator="llama_stack.providers.remote.tool_runtime.model_context_protocol.config.MCPProviderDataValidator", - description="Model Context Protocol (MCP) tool for standardized tool calling and context management.", - ), + adapter_type="model-context-protocol", + provider_type="remote::model-context-protocol", + module="llama_stack.providers.remote.tool_runtime.model_context_protocol", + config_class="llama_stack.providers.remote.tool_runtime.model_context_protocol.config.MCPProviderConfig", + pip_packages=["mcp>=1.8.1"], + provider_data_validator="llama_stack.providers.remote.tool_runtime.model_context_protocol.config.MCPProviderDataValidator", + description="Model Context Protocol (MCP) tool for standardized tool calling and context management.", ), ] diff --git a/llama_stack/providers/registry/vector_io.py b/llama_stack/providers/registry/vector_io.py index 511734d57..3b82f6eb6 100644 --- a/llama_stack/providers/registry/vector_io.py +++ b/llama_stack/providers/registry/vector_io.py @@ -6,11 +6,10 @@ from llama_stack.providers.datatypes import ( - AdapterSpec, Api, InlineProviderSpec, ProviderSpec, - remote_provider_spec, + RemoteProviderSpec, ) @@ -300,14 +299,16 @@ See [sqlite-vec's GitHub repo](https://github.com/asg017/sqlite-vec/tree/main) f Please refer to the sqlite-vec provider documentation. """, ), - remote_provider_spec( - Api.vector_io, - AdapterSpec( - adapter_type="chromadb", - pip_packages=["chromadb-client"], - module="llama_stack.providers.remote.vector_io.chroma", - config_class="llama_stack.providers.remote.vector_io.chroma.ChromaVectorIOConfig", - description=""" + RemoteProviderSpec( + api=Api.vector_io, + adapter_type="chromadb", + provider_type="remote::chromadb", + pip_packages=["chromadb-client"], + module="llama_stack.providers.remote.vector_io.chroma", + config_class="llama_stack.providers.remote.vector_io.chroma.ChromaVectorIOConfig", + api_dependencies=[Api.inference], + optional_api_dependencies=[Api.files], + description=""" [Chroma](https://www.trychroma.com/) is an inline and remote vector database provider for Llama Stack. It allows you to store and query vectors directly within a Chroma database. That means you're not limited to storing vectors in memory or in a separate service. @@ -340,9 +341,6 @@ pip install chromadb ## Documentation See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introduction) for more details about Chroma in general. """, - ), - api_dependencies=[Api.inference], - optional_api_dependencies=[Api.files], ), InlineProviderSpec( api=Api.vector_io, @@ -387,14 +385,16 @@ See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introducti """, ), - remote_provider_spec( - Api.vector_io, - AdapterSpec( - adapter_type="pgvector", - pip_packages=["psycopg2-binary"], - module="llama_stack.providers.remote.vector_io.pgvector", - config_class="llama_stack.providers.remote.vector_io.pgvector.PGVectorVectorIOConfig", - description=""" + RemoteProviderSpec( + api=Api.vector_io, + adapter_type="pgvector", + provider_type="remote::pgvector", + pip_packages=["psycopg2-binary"], + module="llama_stack.providers.remote.vector_io.pgvector", + config_class="llama_stack.providers.remote.vector_io.pgvector.PGVectorVectorIOConfig", + api_dependencies=[Api.inference], + optional_api_dependencies=[Api.files], + description=""" [PGVector](https://github.com/pgvector/pgvector) is a remote vector database provider for Llama Stack. It allows you to store and query vectors directly in memory. That means you'll get fast and efficient vector retrieval. @@ -495,19 +495,18 @@ docker pull pgvector/pgvector:pg17 ## Documentation See [PGVector's documentation](https://github.com/pgvector/pgvector) for more details about PGVector in general. """, - ), + ), + RemoteProviderSpec( + api=Api.vector_io, + adapter_type="weaviate", + provider_type="remote::weaviate", + pip_packages=["weaviate-client"], + module="llama_stack.providers.remote.vector_io.weaviate", + config_class="llama_stack.providers.remote.vector_io.weaviate.WeaviateVectorIOConfig", + provider_data_validator="llama_stack.providers.remote.vector_io.weaviate.WeaviateRequestProviderData", api_dependencies=[Api.inference], optional_api_dependencies=[Api.files], - ), - remote_provider_spec( - Api.vector_io, - AdapterSpec( - adapter_type="weaviate", - pip_packages=["weaviate-client"], - module="llama_stack.providers.remote.vector_io.weaviate", - config_class="llama_stack.providers.remote.vector_io.weaviate.WeaviateVectorIOConfig", - provider_data_validator="llama_stack.providers.remote.vector_io.weaviate.WeaviateRequestProviderData", - description=""" + description=""" [Weaviate](https://weaviate.io/) is a vector database provider for Llama Stack. It allows you to store and query vectors directly within a Weaviate database. That means you're not limited to storing vectors in memory or in a separate service. @@ -538,9 +537,6 @@ To install Weaviate see the [Weaviate quickstart documentation](https://weaviate ## Documentation See [Weaviate's documentation](https://weaviate.io/developers/weaviate) for more details about Weaviate in general. """, - ), - api_dependencies=[Api.inference], - optional_api_dependencies=[Api.files], ), InlineProviderSpec( api=Api.vector_io, @@ -594,28 +590,29 @@ docker pull qdrant/qdrant See the [Qdrant documentation](https://qdrant.tech/documentation/) for more details about Qdrant in general. """, ), - remote_provider_spec( - Api.vector_io, - AdapterSpec( - adapter_type="qdrant", - pip_packages=["qdrant-client"], - module="llama_stack.providers.remote.vector_io.qdrant", - config_class="llama_stack.providers.remote.vector_io.qdrant.QdrantVectorIOConfig", - description=""" -Please refer to the inline provider documentation. -""", - ), + RemoteProviderSpec( + api=Api.vector_io, + adapter_type="qdrant", + provider_type="remote::qdrant", + pip_packages=["qdrant-client"], + module="llama_stack.providers.remote.vector_io.qdrant", + config_class="llama_stack.providers.remote.vector_io.qdrant.QdrantVectorIOConfig", api_dependencies=[Api.inference], optional_api_dependencies=[Api.files], + description=""" +Please refer to the inline provider documentation. +""", ), - remote_provider_spec( - Api.vector_io, - AdapterSpec( - adapter_type="milvus", - pip_packages=["pymilvus>=2.4.10"], - module="llama_stack.providers.remote.vector_io.milvus", - config_class="llama_stack.providers.remote.vector_io.milvus.MilvusVectorIOConfig", - description=""" + RemoteProviderSpec( + api=Api.vector_io, + adapter_type="milvus", + provider_type="remote::milvus", + pip_packages=["pymilvus>=2.4.10"], + module="llama_stack.providers.remote.vector_io.milvus", + config_class="llama_stack.providers.remote.vector_io.milvus.MilvusVectorIOConfig", + api_dependencies=[Api.inference], + optional_api_dependencies=[Api.files], + description=""" [Milvus](https://milvus.io/) is an inline and remote vector database provider for Llama Stack. It allows you to store and query vectors directly within a Milvus database. That means you're not limited to storing vectors in memory or in a separate service. @@ -806,9 +803,6 @@ See the [Milvus documentation](https://milvus.io/docs/install-overview.md) for m For more details on TLS configuration, refer to the [TLS setup guide](https://milvus.io/docs/tls.md). """, - ), - api_dependencies=[Api.inference], - optional_api_dependencies=[Api.files], ), InlineProviderSpec( api=Api.vector_io, diff --git a/tests/external/kaze.yaml b/tests/external/kaze.yaml index c61ac0e31..1b42f2e14 100644 --- a/tests/external/kaze.yaml +++ b/tests/external/kaze.yaml @@ -1,6 +1,5 @@ -adapter: - adapter_type: kaze - pip_packages: ["tests/external/llama-stack-provider-kaze"] - config_class: llama_stack_provider_kaze.config.KazeProviderConfig - module: llama_stack_provider_kaze +adapter_type: kaze +pip_packages: ["tests/external/llama-stack-provider-kaze"] +config_class: llama_stack_provider_kaze.config.KazeProviderConfig +module: llama_stack_provider_kaze optional_api_dependencies: [] diff --git a/tests/external/llama-stack-api-weather/src/llama_stack_api_weather/weather.py b/tests/external/llama-stack-api-weather/src/llama_stack_api_weather/weather.py index 4b3bfb641..de1427bfd 100644 --- a/tests/external/llama-stack-api-weather/src/llama_stack_api_weather/weather.py +++ b/tests/external/llama-stack-api-weather/src/llama_stack_api_weather/weather.py @@ -6,7 +6,7 @@ from typing import Protocol -from llama_stack.providers.datatypes import AdapterSpec, Api, ProviderSpec, RemoteProviderSpec +from llama_stack.providers.datatypes import Api, ProviderSpec, RemoteProviderSpec from llama_stack.schema_utils import webmethod @@ -16,12 +16,9 @@ def available_providers() -> list[ProviderSpec]: api=Api.weather, provider_type="remote::kaze", config_class="llama_stack_provider_kaze.KazeProviderConfig", - adapter=AdapterSpec( - adapter_type="kaze", - module="llama_stack_provider_kaze", - pip_packages=["llama_stack_provider_kaze"], - config_class="llama_stack_provider_kaze.KazeProviderConfig", - ), + adapter_type="kaze", + module="llama_stack_provider_kaze", + pip_packages=["llama_stack_provider_kaze"], ), ] diff --git a/tests/unit/distribution/test_distribution.py b/tests/unit/distribution/test_distribution.py index c6c2eb2c7..f24de0644 100644 --- a/tests/unit/distribution/test_distribution.py +++ b/tests/unit/distribution/test_distribution.py @@ -66,10 +66,9 @@ def base_config(tmp_path): def provider_spec_yaml(): """Common provider spec YAML for testing.""" return """ -adapter: - adapter_type: test_provider - config_class: test_provider.config.TestProviderConfig - module: test_provider +adapter_type: test_provider +config_class: test_provider.config.TestProviderConfig +module: test_provider api_dependencies: - safety """ @@ -182,9 +181,9 @@ class TestProviderRegistry: assert Api.inference in registry assert "remote::test_provider" in registry[Api.inference] provider = registry[Api.inference]["remote::test_provider"] - assert provider.adapter.adapter_type == "test_provider" - assert provider.adapter.module == "test_provider" - assert provider.adapter.config_class == "test_provider.config.TestProviderConfig" + assert provider.adapter_type == "test_provider" + assert provider.module == "test_provider" + assert provider.config_class == "test_provider.config.TestProviderConfig" assert Api.safety in provider.api_dependencies def test_external_inline_providers(self, api_directories, mock_providers, base_config, inline_provider_spec_yaml): @@ -246,8 +245,7 @@ class TestProviderRegistry: """Test handling of malformed remote provider spec (missing required fields).""" remote_dir, _ = api_directories malformed_spec = """ -adapter: - adapter_type: test_provider +adapter_type: test_provider # Missing required fields api_dependencies: - safety @@ -270,7 +268,7 @@ pip_packages: with open(inline_dir / "malformed.yaml", "w") as f: f.write(malformed_spec) - with pytest.raises(KeyError) as exc_info: + with pytest.raises(ValidationError) as exc_info: get_provider_registry(base_config) assert "config_class" in str(exc_info.value) From 4c2fcb6b515d9f3cbb068d979eba694bc10e1ff0 Mon Sep 17 00:00:00 2001 From: ehhuang Date: Thu, 18 Sep 2025 21:11:13 -0700 Subject: [PATCH 04/18] chore: refactor server.main (#3462) # What does this PR do? As shown in #3421, we can scale stack to handle more RPS with k8s replicas. This PR enables multi process stack with uvicorn --workers so that we can achieve the same scaling without being in k8s. To achieve that we refactor main to split out the app construction logic. This method needs to be non-async. We created a new `Stack` class to house impls and have a `start()` method to be called in lifespan to start background tasks instead of starting them in the old `construct_stack`. This way we avoid having to manage an event loop manually. ## Test Plan CI > uv run --with llama-stack python -m llama_stack.core.server.server benchmarking/k8s-benchmark/stack_run_config.yaml works. > LLAMA_STACK_CONFIG=benchmarking/k8s-benchmark/stack_run_config.yaml uv run uvicorn llama_stack.core.server.server:create_app --port 8321 --workers 4 works. --- benchmarking/k8s-benchmark/apply.sh | 5 +- .../k8s-benchmark/stack-configmap.yaml | 9 ++ .../k8s-benchmark/stack-k8s.yaml.template | 13 +- llama_stack/core/library_client.py | 8 +- llama_stack/core/server/server.py | 152 +++++++++++------- llama_stack/core/stack.py | 142 ++++++++-------- .../test_library_client_initialization.py | 50 ++++-- 7 files changed, 233 insertions(+), 146 deletions(-) diff --git a/benchmarking/k8s-benchmark/apply.sh b/benchmarking/k8s-benchmark/apply.sh index 4f2270da8..6e6607663 100755 --- a/benchmarking/k8s-benchmark/apply.sh +++ b/benchmarking/k8s-benchmark/apply.sh @@ -17,11 +17,8 @@ export POSTGRES_PASSWORD=llamastack export INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B -export MOCK_INFERENCE_MODEL=mock-inference - -export MOCK_INFERENCE_URL=openai-mock-service:8080 - export BENCHMARK_INFERENCE_MODEL=$INFERENCE_MODEL +export LLAMA_STACK_WORKERS=4 set -euo pipefail set -x diff --git a/benchmarking/k8s-benchmark/stack-configmap.yaml b/benchmarking/k8s-benchmark/stack-configmap.yaml index bf6109b68..286ba5f77 100644 --- a/benchmarking/k8s-benchmark/stack-configmap.yaml +++ b/benchmarking/k8s-benchmark/stack-configmap.yaml @@ -5,6 +5,7 @@ data: image_name: kubernetes-benchmark-demo apis: - agents + - files - inference - files - safety @@ -23,6 +24,14 @@ data: - provider_id: sentence-transformers provider_type: inline::sentence-transformers config: {} + files: + - provider_id: meta-reference-files + provider_type: inline::localfs + config: + storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files} + metadata_store: + type: sqlite + db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/files_metadata.db vector_io: - provider_id: ${env.ENABLE_CHROMADB:+chromadb} provider_type: remote::chromadb diff --git a/benchmarking/k8s-benchmark/stack-k8s.yaml.template b/benchmarking/k8s-benchmark/stack-k8s.yaml.template index 9cb1e5be3..8842c0bea 100644 --- a/benchmarking/k8s-benchmark/stack-k8s.yaml.template +++ b/benchmarking/k8s-benchmark/stack-k8s.yaml.template @@ -52,9 +52,20 @@ spec: value: http://vllm-server-safety.default.svc.cluster.local:8001/v1 - name: VLLM_TLS_VERIFY value: "false" - command: ["python", "-m", "llama_stack.core.server.server", "/etc/config/stack_run_config.yaml", "--port", "8323"] + - name: LLAMA_STACK_LOGGING + value: "all=WARNING" + - name: LLAMA_STACK_CONFIG + value: "/etc/config/stack_run_config.yaml" + - name: LLAMA_STACK_WORKERS + value: "${LLAMA_STACK_WORKERS}" + command: ["uvicorn", "llama_stack.core.server.server:create_app", "--host", "0.0.0.0", "--port", "8323", "--workers", "$LLAMA_STACK_WORKERS", "--factory"] ports: - containerPort: 8323 + resources: + requests: + cpu: "${LLAMA_STACK_WORKERS}" + limits: + cpu: "${LLAMA_STACK_WORKERS}" volumeMounts: - name: llama-storage mountPath: /root/.llama diff --git a/llama_stack/core/library_client.py b/llama_stack/core/library_client.py index ea5a2ac8e..e722e4de6 100644 --- a/llama_stack/core/library_client.py +++ b/llama_stack/core/library_client.py @@ -40,7 +40,7 @@ from llama_stack.core.request_headers import ( from llama_stack.core.resolver import ProviderRegistry from llama_stack.core.server.routes import RouteImpls, find_matching_route, initialize_route_impls from llama_stack.core.stack import ( - construct_stack, + Stack, get_stack_run_config_from_distro, replace_env_vars, ) @@ -252,7 +252,10 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient): try: self.route_impls = None - self.impls = await construct_stack(self.config, self.custom_provider_registry) + + stack = Stack(self.config, self.custom_provider_registry) + await stack.initialize() + self.impls = stack.impls except ModuleNotFoundError as _e: cprint(_e.msg, color="red", file=sys.stderr) cprint( @@ -289,6 +292,7 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient): ) raise _e + assert self.impls is not None if Api.telemetry in self.impls: setup_logger(self.impls[Api.telemetry]) diff --git a/llama_stack/core/server/server.py b/llama_stack/core/server/server.py index d3e875fec..9cca42268 100644 --- a/llama_stack/core/server/server.py +++ b/llama_stack/core/server/server.py @@ -6,6 +6,7 @@ import argparse import asyncio +import concurrent.futures import functools import inspect import json @@ -50,17 +51,15 @@ from llama_stack.core.request_headers import ( request_provider_data_context, user_from_scope, ) -from llama_stack.core.resolver import InvalidProviderError from llama_stack.core.server.routes import ( find_matching_route, get_all_api_routes, initialize_route_impls, ) from llama_stack.core.stack import ( + Stack, cast_image_name_to_string, - construct_stack, replace_env_vars, - shutdown_stack, validate_env_pair, ) from llama_stack.core.utils.config import redact_sensitive_fields @@ -156,21 +155,34 @@ def translate_exception(exc: Exception) -> HTTPException | RequestValidationErro ) -async def shutdown(app): - """Initiate a graceful shutdown of the application. - - Handled by the lifespan context manager. The shutdown process involves - shutting down all implementations registered in the application. +class StackApp(FastAPI): """ - await shutdown_stack(app.__llama_stack_impls__) + A wrapper around the FastAPI application to hold a reference to the Stack instance so that we can + start background tasks (e.g. refresh model registry periodically) from the lifespan context manager. + """ + + def __init__(self, config: StackRunConfig, *args, **kwargs): + super().__init__(*args, **kwargs) + self.stack: Stack = Stack(config) + + # This code is called from a running event loop managed by uvicorn so we cannot simply call + # asyncio.run() to initialize the stack. We cannot await either since this is not an async + # function. + # As a workaround, we use a thread pool executor to run the initialize() method + # in a separate thread. + with concurrent.futures.ThreadPoolExecutor() as executor: + future = executor.submit(asyncio.run, self.stack.initialize()) + future.result() @asynccontextmanager -async def lifespan(app: FastAPI): +async def lifespan(app: StackApp): logger.info("Starting up") + assert app.stack is not None + app.stack.create_registry_refresh_task() yield logger.info("Shutting down") - await shutdown(app) + await app.stack.shutdown() def is_streaming_request(func_name: str, request: Request, **kwargs): @@ -386,73 +398,61 @@ class ClientVersionMiddleware: return await self.app(scope, receive, send) -def main(args: argparse.Namespace | None = None): - """Start the LlamaStack server.""" - parser = argparse.ArgumentParser(description="Start the LlamaStack server.") +def create_app( + config_file: str | None = None, + env_vars: list[str] | None = None, +) -> StackApp: + """Create and configure the FastAPI application. - add_config_distro_args(parser) - parser.add_argument( - "--port", - type=int, - default=int(os.getenv("LLAMA_STACK_PORT", 8321)), - help="Port to listen on", - ) - parser.add_argument( - "--env", - action="append", - help="Environment variables in KEY=value format. Can be specified multiple times.", - ) + Args: + config_file: Path to config file. If None, uses LLAMA_STACK_CONFIG env var or default resolution. + env_vars: List of environment variables in KEY=value format. + disable_version_check: Whether to disable version checking. If None, uses LLAMA_STACK_DISABLE_VERSION_CHECK env var. - # Determine whether the server args are being passed by the "run" command, if this is the case - # the args will be passed as a Namespace object to the main function, otherwise they will be - # parsed from the command line - if args is None: - args = parser.parse_args() + Returns: + Configured StackApp instance. + """ + config_file = config_file or os.getenv("LLAMA_STACK_CONFIG") + if config_file is None: + raise ValueError("No config file provided and LLAMA_STACK_CONFIG env var is not set") - config_or_distro = get_config_from_args(args) - config_file = resolve_config_or_distro(config_or_distro, Mode.RUN) + config_file = resolve_config_or_distro(config_file, Mode.RUN) + # Load and process configuration logger_config = None with open(config_file) as fp: config_contents = yaml.safe_load(fp) if isinstance(config_contents, dict) and (cfg := config_contents.get("logging_config")): logger_config = LoggingConfig(**cfg) logger = get_logger(name=__name__, category="core::server", config=logger_config) - if args.env: - for env_pair in args.env: + + if env_vars: + for env_pair in env_vars: try: key, value = validate_env_pair(env_pair) - logger.info(f"Setting CLI environment variable {key} => {value}") + logger.info(f"Setting environment variable {key} => {value}") os.environ[key] = value except ValueError as e: logger.error(f"Error: {str(e)}") - sys.exit(1) + raise ValueError(f"Invalid environment variable format: {env_pair}") from e + config = replace_env_vars(config_contents) config = StackRunConfig(**cast_image_name_to_string(config)) _log_run_config(run_config=config) - app = FastAPI( + app = StackApp( lifespan=lifespan, docs_url="/docs", redoc_url="/redoc", openapi_url="/openapi.json", + config=config, ) if not os.environ.get("LLAMA_STACK_DISABLE_VERSION_CHECK"): app.add_middleware(ClientVersionMiddleware) - try: - # Create and set the event loop that will be used for both construction and server runtime - loop = asyncio.new_event_loop() - asyncio.set_event_loop(loop) - - # Construct the stack in the persistent event loop - impls = loop.run_until_complete(construct_stack(config)) - - except InvalidProviderError as e: - logger.error(f"Error: {str(e)}") - sys.exit(1) + impls = app.stack.impls if config.server.auth: logger.info(f"Enabling authentication with provider: {config.server.auth.provider_config.type.value}") @@ -553,9 +553,54 @@ def main(args: argparse.Namespace | None = None): app.exception_handler(RequestValidationError)(global_exception_handler) app.exception_handler(Exception)(global_exception_handler) - app.__llama_stack_impls__ = impls app.add_middleware(TracingMiddleware, impls=impls, external_apis=external_apis) + return app + + +def main(args: argparse.Namespace | None = None): + """Start the LlamaStack server.""" + parser = argparse.ArgumentParser(description="Start the LlamaStack server.") + + add_config_distro_args(parser) + parser.add_argument( + "--port", + type=int, + default=int(os.getenv("LLAMA_STACK_PORT", 8321)), + help="Port to listen on", + ) + parser.add_argument( + "--env", + action="append", + help="Environment variables in KEY=value format. Can be specified multiple times.", + ) + + # Determine whether the server args are being passed by the "run" command, if this is the case + # the args will be passed as a Namespace object to the main function, otherwise they will be + # parsed from the command line + if args is None: + args = parser.parse_args() + + config_or_distro = get_config_from_args(args) + + try: + app = create_app( + config_file=config_or_distro, + env_vars=args.env, + ) + except Exception as e: + logger.error(f"Error creating app: {str(e)}") + sys.exit(1) + + config_file = resolve_config_or_distro(config_or_distro, Mode.RUN) + with open(config_file) as fp: + config_contents = yaml.safe_load(fp) + if isinstance(config_contents, dict) and (cfg := config_contents.get("logging_config")): + logger_config = LoggingConfig(**cfg) + else: + logger_config = None + config = StackRunConfig(**cast_image_name_to_string(replace_env_vars(config_contents))) + import uvicorn # Configure SSL if certificates are provided @@ -593,7 +638,6 @@ def main(args: argparse.Namespace | None = None): if ssl_config: uvicorn_config.update(ssl_config) - # Run uvicorn in the existing event loop to preserve background tasks # We need to catch KeyboardInterrupt because uvicorn's signal handling # re-raises SIGINT signals using signal.raise_signal(), which Python # converts to KeyboardInterrupt. Without this catch, we'd get a confusing @@ -604,13 +648,9 @@ def main(args: argparse.Namespace | None = None): # Another approach would be to ignore SIGINT entirely - let uvicorn handle it through its own # signal handling but this is quite intrusive and not worth the effort. try: - loop.run_until_complete(uvicorn.Server(uvicorn.Config(**uvicorn_config)).serve()) + asyncio.run(uvicorn.Server(uvicorn.Config(**uvicorn_config)).serve()) except (KeyboardInterrupt, SystemExit): logger.info("Received interrupt signal, shutting down gracefully...") - finally: - if not loop.is_closed(): - logger.debug("Closing event loop") - loop.close() def _log_run_config(run_config: StackRunConfig): diff --git a/llama_stack/core/stack.py b/llama_stack/core/stack.py index 7ab8d2c64..a6c5093eb 100644 --- a/llama_stack/core/stack.py +++ b/llama_stack/core/stack.py @@ -315,78 +315,84 @@ def add_internal_implementations(impls: dict[Api, Any], run_config: StackRunConf impls[Api.prompts] = prompts_impl -# Produces a stack of providers for the given run config. Not all APIs may be -# asked for in the run config. -async def construct_stack( - run_config: StackRunConfig, provider_registry: ProviderRegistry | None = None -) -> dict[Api, Any]: - if "LLAMA_STACK_TEST_INFERENCE_MODE" in os.environ: - from llama_stack.testing.inference_recorder import setup_inference_recording +class Stack: + def __init__(self, run_config: StackRunConfig, provider_registry: ProviderRegistry | None = None): + self.run_config = run_config + self.provider_registry = provider_registry + self.impls = None + + # Produces a stack of providers for the given run config. Not all APIs may be + # asked for in the run config. + async def initialize(self): + if "LLAMA_STACK_TEST_INFERENCE_MODE" in os.environ: + from llama_stack.testing.inference_recorder import setup_inference_recording + + global TEST_RECORDING_CONTEXT + TEST_RECORDING_CONTEXT = setup_inference_recording() + if TEST_RECORDING_CONTEXT: + TEST_RECORDING_CONTEXT.__enter__() + logger.info(f"Inference recording enabled: mode={os.environ.get('LLAMA_STACK_TEST_INFERENCE_MODE')}") + + dist_registry, _ = await create_dist_registry(self.run_config.metadata_store, self.run_config.image_name) + policy = self.run_config.server.auth.access_policy if self.run_config.server.auth else [] + impls = await resolve_impls( + self.run_config, self.provider_registry or get_provider_registry(self.run_config), dist_registry, policy + ) + + # Add internal implementations after all other providers are resolved + add_internal_implementations(impls, self.run_config) + + if Api.prompts in impls: + await impls[Api.prompts].initialize() + + await register_resources(self.run_config, impls) + + await refresh_registry_once(impls) + self.impls = impls + + def create_registry_refresh_task(self): + assert self.impls is not None, "Must call initialize() before starting" + + global REGISTRY_REFRESH_TASK + REGISTRY_REFRESH_TASK = asyncio.create_task(refresh_registry_task(self.impls)) + + def cb(task): + import traceback + + if task.cancelled(): + logger.error("Model refresh task cancelled") + elif task.exception(): + logger.error(f"Model refresh task failed: {task.exception()}") + traceback.print_exception(task.exception()) + else: + logger.debug("Model refresh task completed") + + REGISTRY_REFRESH_TASK.add_done_callback(cb) + + async def shutdown(self): + for impl in self.impls.values(): + impl_name = impl.__class__.__name__ + logger.info(f"Shutting down {impl_name}") + try: + if hasattr(impl, "shutdown"): + await asyncio.wait_for(impl.shutdown(), timeout=5) + else: + logger.warning(f"No shutdown method for {impl_name}") + except TimeoutError: + logger.exception(f"Shutdown timeout for {impl_name}") + except (Exception, asyncio.CancelledError) as e: + logger.exception(f"Failed to shutdown {impl_name}: {e}") global TEST_RECORDING_CONTEXT - TEST_RECORDING_CONTEXT = setup_inference_recording() if TEST_RECORDING_CONTEXT: - TEST_RECORDING_CONTEXT.__enter__() - logger.info(f"Inference recording enabled: mode={os.environ.get('LLAMA_STACK_TEST_INFERENCE_MODE')}") + try: + TEST_RECORDING_CONTEXT.__exit__(None, None, None) + except Exception as e: + logger.error(f"Error during inference recording cleanup: {e}") - dist_registry, _ = await create_dist_registry(run_config.metadata_store, run_config.image_name) - policy = run_config.server.auth.access_policy if run_config.server.auth else [] - impls = await resolve_impls( - run_config, provider_registry or get_provider_registry(run_config), dist_registry, policy - ) - - # Add internal implementations after all other providers are resolved - add_internal_implementations(impls, run_config) - - if Api.prompts in impls: - await impls[Api.prompts].initialize() - - await register_resources(run_config, impls) - - await refresh_registry_once(impls) - - global REGISTRY_REFRESH_TASK - REGISTRY_REFRESH_TASK = asyncio.create_task(refresh_registry_task(impls)) - - def cb(task): - import traceback - - if task.cancelled(): - logger.error("Model refresh task cancelled") - elif task.exception(): - logger.error(f"Model refresh task failed: {task.exception()}") - traceback.print_exception(task.exception()) - else: - logger.debug("Model refresh task completed") - - REGISTRY_REFRESH_TASK.add_done_callback(cb) - return impls - - -async def shutdown_stack(impls: dict[Api, Any]): - for impl in impls.values(): - impl_name = impl.__class__.__name__ - logger.info(f"Shutting down {impl_name}") - try: - if hasattr(impl, "shutdown"): - await asyncio.wait_for(impl.shutdown(), timeout=5) - else: - logger.warning(f"No shutdown method for {impl_name}") - except TimeoutError: - logger.exception(f"Shutdown timeout for {impl_name}") - except (Exception, asyncio.CancelledError) as e: - logger.exception(f"Failed to shutdown {impl_name}: {e}") - - global TEST_RECORDING_CONTEXT - if TEST_RECORDING_CONTEXT: - try: - TEST_RECORDING_CONTEXT.__exit__(None, None, None) - except Exception as e: - logger.error(f"Error during inference recording cleanup: {e}") - - global REGISTRY_REFRESH_TASK - if REGISTRY_REFRESH_TASK: - REGISTRY_REFRESH_TASK.cancel() + global REGISTRY_REFRESH_TASK + if REGISTRY_REFRESH_TASK: + REGISTRY_REFRESH_TASK.cancel() async def refresh_registry_once(impls: dict[Api, Any]): diff --git a/tests/unit/distribution/test_library_client_initialization.py b/tests/unit/distribution/test_library_client_initialization.py index b7e7a1857..b01a5c3e2 100644 --- a/tests/unit/distribution/test_library_client_initialization.py +++ b/tests/unit/distribution/test_library_client_initialization.py @@ -27,13 +27,17 @@ class TestLlamaStackAsLibraryClientAutoInitialization: mock_impls = {} mock_route_impls = RouteImpls({}) - async def mock_construct_stack(config, custom_provider_registry): - return mock_impls + class MockStack: + def __init__(self, config, custom_provider_registry=None): + self.impls = mock_impls + + async def initialize(self): + pass def mock_initialize_route_impls(impls): return mock_route_impls - monkeypatch.setattr("llama_stack.core.library_client.construct_stack", mock_construct_stack) + monkeypatch.setattr("llama_stack.core.library_client.Stack", MockStack) monkeypatch.setattr("llama_stack.core.library_client.initialize_route_impls", mock_initialize_route_impls) client = LlamaStackAsLibraryClient("ci-tests") @@ -46,13 +50,17 @@ class TestLlamaStackAsLibraryClientAutoInitialization: mock_impls = {} mock_route_impls = RouteImpls({}) - async def mock_construct_stack(config, custom_provider_registry): - return mock_impls + class MockStack: + def __init__(self, config, custom_provider_registry=None): + self.impls = mock_impls + + async def initialize(self): + pass def mock_initialize_route_impls(impls): return mock_route_impls - monkeypatch.setattr("llama_stack.core.library_client.construct_stack", mock_construct_stack) + monkeypatch.setattr("llama_stack.core.library_client.Stack", MockStack) monkeypatch.setattr("llama_stack.core.library_client.initialize_route_impls", mock_initialize_route_impls) client = AsyncLlamaStackAsLibraryClient("ci-tests") @@ -68,13 +76,17 @@ class TestLlamaStackAsLibraryClientAutoInitialization: mock_impls = {} mock_route_impls = RouteImpls({}) - async def mock_construct_stack(config, custom_provider_registry): - return mock_impls + class MockStack: + def __init__(self, config, custom_provider_registry=None): + self.impls = mock_impls + + async def initialize(self): + pass def mock_initialize_route_impls(impls): return mock_route_impls - monkeypatch.setattr("llama_stack.core.library_client.construct_stack", mock_construct_stack) + monkeypatch.setattr("llama_stack.core.library_client.Stack", MockStack) monkeypatch.setattr("llama_stack.core.library_client.initialize_route_impls", mock_initialize_route_impls) client = LlamaStackAsLibraryClient("ci-tests") @@ -90,13 +102,17 @@ class TestLlamaStackAsLibraryClientAutoInitialization: mock_impls = {} mock_route_impls = RouteImpls({}) - async def mock_construct_stack(config, custom_provider_registry): - return mock_impls + class MockStack: + def __init__(self, config, custom_provider_registry=None): + self.impls = mock_impls + + async def initialize(self): + pass def mock_initialize_route_impls(impls): return mock_route_impls - monkeypatch.setattr("llama_stack.core.library_client.construct_stack", mock_construct_stack) + monkeypatch.setattr("llama_stack.core.library_client.Stack", MockStack) monkeypatch.setattr("llama_stack.core.library_client.initialize_route_impls", mock_initialize_route_impls) client = AsyncLlamaStackAsLibraryClient("ci-tests") @@ -112,13 +128,17 @@ class TestLlamaStackAsLibraryClientAutoInitialization: mock_impls = {} mock_route_impls = RouteImpls({}) - async def mock_construct_stack(config, custom_provider_registry): - return mock_impls + class MockStack: + def __init__(self, config, custom_provider_registry=None): + self.impls = mock_impls + + async def initialize(self): + pass def mock_initialize_route_impls(impls): return mock_route_impls - monkeypatch.setattr("llama_stack.core.library_client.construct_stack", mock_construct_stack) + monkeypatch.setattr("llama_stack.core.library_client.Stack", MockStack) monkeypatch.setattr("llama_stack.core.library_client.initialize_route_impls", mock_initialize_route_impls) sync_client = LlamaStackAsLibraryClient("ci-tests") From 9378bdca43e886c7ba3b79f017693726bed9b740 Mon Sep 17 00:00:00 2001 From: adam-d-young Date: Fri, 19 Sep 2025 10:41:26 -0500 Subject: [PATCH 05/18] docs: Fix incorrect vector_db_id usage in RAG tutorial (#3444) # What does this PR do? This PR fixes a blocking issue in the detailed RAG tutorial where the code fails with a 400 Bad Request error. The root cause is that recent versions of Llama-Stack ignore the client-generated vector_db_id and assign a new server-side ID. The tutorial was not updated to reflect this, causing the rag_tool.insert call to fail. This change updates the code to capture the authoritative ID from the .identifier attribute of the register() method's response. This ensures the tutorial code runs successfully and reflects the current API behavior. ## Test Plan The fix can be verified by running the Python code snippet from the detailed tutorial page. Run the original code (Before this change): Result: The script fails with a 400 Bad Request error on the rag_tool.insert step. Run the updated code (After this change): Result: The script runs successfully to completion. Co-authored-by: Adam Young --- docs/source/getting_started/detailed_tutorial.md | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/docs/source/getting_started/detailed_tutorial.md b/docs/source/getting_started/detailed_tutorial.md index 14f888628..77a899c48 100644 --- a/docs/source/getting_started/detailed_tutorial.md +++ b/docs/source/getting_started/detailed_tutorial.md @@ -460,10 +460,12 @@ client = LlamaStackClient(base_url="http://localhost:8321") embed_lm = next(m for m in client.models.list() if m.model_type == "embedding") embedding_model = embed_lm.identifier vector_db_id = f"v{uuid.uuid4().hex}" -client.vector_dbs.register( +# The VectorDB API is deprecated; the server now returns its own authoritative ID. +# We capture the correct ID from the response's .identifier attribute. +vector_db_id = client.vector_dbs.register( vector_db_id=vector_db_id, embedding_model=embedding_model, -) +).identifier # Create Documents urls = [ From d3600b92d10a3e11126c6120eadf0ba5ef4e1c3c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?S=C3=A9bastien=20Han?= Date: Fri, 19 Sep 2025 22:12:08 +0200 Subject: [PATCH 06/18] fix: force milvus-lite installation for inline::milvus (#3488) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit # What does this PR do? pymilvus recently made `milvus-lite` an optional dependency to their package. If someone wants to use the inline provider we must include the extra dependency. For more details see: https://github.com/milvus-io/pymilvus/pull/2976 Signed-off-by: Sébastien Han --- docs/source/providers/vector_io/remote_milvus.md | 8 +++++++- llama_stack/providers/registry/vector_io.py | 10 ++++++++-- 2 files changed, 15 insertions(+), 3 deletions(-) diff --git a/docs/source/providers/vector_io/remote_milvus.md b/docs/source/providers/vector_io/remote_milvus.md index 075423d04..8974ada10 100644 --- a/docs/source/providers/vector_io/remote_milvus.md +++ b/docs/source/providers/vector_io/remote_milvus.md @@ -23,7 +23,13 @@ To use Milvus in your Llama Stack project, follow these steps: ## Installation -You can install Milvus using pymilvus: +If you want to use inline Milvus, you can install: + +```bash +pip install pymilvus[milvus-lite] +``` + +If you want to use remote Milvus, you can install: ```bash pip install pymilvus diff --git a/llama_stack/providers/registry/vector_io.py b/llama_stack/providers/registry/vector_io.py index 3b82f6eb6..e8237bc62 100644 --- a/llama_stack/providers/registry/vector_io.py +++ b/llama_stack/providers/registry/vector_io.py @@ -633,7 +633,13 @@ To use Milvus in your Llama Stack project, follow these steps: ## Installation -You can install Milvus using pymilvus: +If you want to use inline Milvus, you can install: + +```bash +pip install pymilvus[milvus-lite] +``` + +If you want to use remote Milvus, you can install: ```bash pip install pymilvus @@ -807,7 +813,7 @@ For more details on TLS configuration, refer to the [TLS setup guide](https://mi InlineProviderSpec( api=Api.vector_io, provider_type="inline::milvus", - pip_packages=["pymilvus>=2.4.10"], + pip_packages=["pymilvus[milvus-lite]>=2.4.10"], module="llama_stack.providers.inline.vector_io.milvus", config_class="llama_stack.providers.inline.vector_io.milvus.MilvusVectorIOConfig", api_dependencies=[Api.inference], From f44eb935c4ff110278758ff2972bd5a5fd544915 Mon Sep 17 00:00:00 2001 From: ehhuang Date: Fri, 19 Sep 2025 16:13:56 -0700 Subject: [PATCH 07/18] chore: simplify authorized sqlstore (#3496) # What does this PR do? This PR is generated with AI and reviewed by me. Refactors the AuthorizedSqlStore class to store the access policy as an instance variable rather than passing it as a parameter to each method call. This simplifies the API. # Test Plan existing tests --- .../providers/inline/files/localfs/files.py | 5 ++--- .../providers/remote/files/s3/files.py | 5 ++--- .../utils/inference/inference_store.py | 4 +--- .../utils/responses/responses_store.py | 7 ++----- .../utils/sqlstore/authorized_sqlstore.py | 11 +++++------ .../sqlstore/test_authorized_sqlstore.py | 19 +++++++++++-------- tests/unit/utils/test_authorized_sqlstore.py | 18 +++++++++--------- 7 files changed, 32 insertions(+), 37 deletions(-) diff --git a/llama_stack/providers/inline/files/localfs/files.py b/llama_stack/providers/inline/files/localfs/files.py index 9c610c1ba..65cf8d815 100644 --- a/llama_stack/providers/inline/files/localfs/files.py +++ b/llama_stack/providers/inline/files/localfs/files.py @@ -44,7 +44,7 @@ class LocalfsFilesImpl(Files): storage_path.mkdir(parents=True, exist_ok=True) # Initialize SQL store for metadata - self.sql_store = AuthorizedSqlStore(sqlstore_impl(self.config.metadata_store)) + self.sql_store = AuthorizedSqlStore(sqlstore_impl(self.config.metadata_store), self.policy) await self.sql_store.create_table( "openai_files", { @@ -74,7 +74,7 @@ class LocalfsFilesImpl(Files): if not self.sql_store: raise RuntimeError("Files provider not initialized") - row = await self.sql_store.fetch_one("openai_files", policy=self.policy, where={"id": file_id}) + row = await self.sql_store.fetch_one("openai_files", where={"id": file_id}) if not row: raise ResourceNotFoundError(file_id, "File", "client.files.list()") @@ -150,7 +150,6 @@ class LocalfsFilesImpl(Files): paginated_result = await self.sql_store.fetch_all( table="openai_files", - policy=self.policy, where=where_conditions if where_conditions else None, order_by=[("created_at", order.value)], cursor=("id", after) if after else None, diff --git a/llama_stack/providers/remote/files/s3/files.py b/llama_stack/providers/remote/files/s3/files.py index 54742d900..8ea96af9e 100644 --- a/llama_stack/providers/remote/files/s3/files.py +++ b/llama_stack/providers/remote/files/s3/files.py @@ -137,7 +137,7 @@ class S3FilesImpl(Files): where: dict[str, str | dict] = {"id": file_id} if not return_expired: where["expires_at"] = {">": self._now()} - if not (row := await self.sql_store.fetch_one("openai_files", policy=self.policy, where=where)): + if not (row := await self.sql_store.fetch_one("openai_files", where=where)): raise ResourceNotFoundError(file_id, "File", "files.list()") return row @@ -164,7 +164,7 @@ class S3FilesImpl(Files): self._client = _create_s3_client(self._config) await _create_bucket_if_not_exists(self._client, self._config) - self._sql_store = AuthorizedSqlStore(sqlstore_impl(self._config.metadata_store)) + self._sql_store = AuthorizedSqlStore(sqlstore_impl(self._config.metadata_store), self.policy) await self._sql_store.create_table( "openai_files", { @@ -268,7 +268,6 @@ class S3FilesImpl(Files): paginated_result = await self.sql_store.fetch_all( table="openai_files", - policy=self.policy, where=where_conditions, order_by=[("created_at", order.value)], cursor=("id", after) if after else None, diff --git a/llama_stack/providers/utils/inference/inference_store.py b/llama_stack/providers/utils/inference/inference_store.py index 17f4c6268..ffc9f3e11 100644 --- a/llama_stack/providers/utils/inference/inference_store.py +++ b/llama_stack/providers/utils/inference/inference_store.py @@ -54,7 +54,7 @@ class InferenceStore: async def initialize(self): """Create the necessary tables if they don't exist.""" - self.sql_store = AuthorizedSqlStore(sqlstore_impl(self.sql_store_config)) + self.sql_store = AuthorizedSqlStore(sqlstore_impl(self.sql_store_config), self.policy) await self.sql_store.create_table( "chat_completions", { @@ -202,7 +202,6 @@ class InferenceStore: order_by=[("created", order.value)], cursor=("id", after) if after else None, limit=limit, - policy=self.policy, ) data = [ @@ -229,7 +228,6 @@ class InferenceStore: row = await self.sql_store.fetch_one( table="chat_completions", where={"id": completion_id}, - policy=self.policy, ) if not row: diff --git a/llama_stack/providers/utils/responses/responses_store.py b/llama_stack/providers/utils/responses/responses_store.py index 04778ed1c..829cd8a62 100644 --- a/llama_stack/providers/utils/responses/responses_store.py +++ b/llama_stack/providers/utils/responses/responses_store.py @@ -28,8 +28,7 @@ class ResponsesStore: sql_store_config = SqliteSqlStoreConfig( db_path=(RUNTIME_BASE_DIR / "sqlstore.db").as_posix(), ) - self.sql_store = AuthorizedSqlStore(sqlstore_impl(sql_store_config)) - self.policy = policy + self.sql_store = AuthorizedSqlStore(sqlstore_impl(sql_store_config), policy) async def initialize(self): """Create the necessary tables if they don't exist.""" @@ -87,7 +86,6 @@ class ResponsesStore: order_by=[("created_at", order.value)], cursor=("id", after) if after else None, limit=limit, - policy=self.policy, ) data = [OpenAIResponseObjectWithInput(**row["response_object"]) for row in paginated_result.data] @@ -105,7 +103,6 @@ class ResponsesStore: row = await self.sql_store.fetch_one( "openai_responses", where={"id": response_id}, - policy=self.policy, ) if not row: @@ -116,7 +113,7 @@ class ResponsesStore: return OpenAIResponseObjectWithInput(**row["response_object"]) async def delete_response_object(self, response_id: str) -> OpenAIDeleteResponseObject: - row = await self.sql_store.fetch_one("openai_responses", where={"id": response_id}, policy=self.policy) + row = await self.sql_store.fetch_one("openai_responses", where={"id": response_id}) if not row: raise ValueError(f"Response with id {response_id} not found") await self.sql_store.delete("openai_responses", where={"id": response_id}) diff --git a/llama_stack/providers/utils/sqlstore/authorized_sqlstore.py b/llama_stack/providers/utils/sqlstore/authorized_sqlstore.py index acb688f96..ab67f7052 100644 --- a/llama_stack/providers/utils/sqlstore/authorized_sqlstore.py +++ b/llama_stack/providers/utils/sqlstore/authorized_sqlstore.py @@ -53,13 +53,15 @@ class AuthorizedSqlStore: access control policies, user attribute capture, and SQL filtering optimization. """ - def __init__(self, sql_store: SqlStore): + def __init__(self, sql_store: SqlStore, policy: list[AccessRule]): """ Initialize the authorization layer. :param sql_store: Base SqlStore implementation to wrap + :param policy: Access control policy to use for authorization """ self.sql_store = sql_store + self.policy = policy self._detect_database_type() self._validate_sql_optimized_policy() @@ -117,14 +119,13 @@ class AuthorizedSqlStore: async def fetch_all( self, table: str, - policy: list[AccessRule], where: Mapping[str, Any] | None = None, limit: int | None = None, order_by: list[tuple[str, Literal["asc", "desc"]]] | None = None, cursor: tuple[str, str] | None = None, ) -> PaginatedResponse: """Fetch all rows with automatic access control filtering.""" - access_where = self._build_access_control_where_clause(policy) + access_where = self._build_access_control_where_clause(self.policy) rows = await self.sql_store.fetch_all( table=table, where=where, @@ -146,7 +147,7 @@ class AuthorizedSqlStore: str(record_id), table, User(principal=stored_owner_principal, attributes=stored_access_attrs) ) - if is_action_allowed(policy, Action.READ, sql_record, current_user): + if is_action_allowed(self.policy, Action.READ, sql_record, current_user): filtered_rows.append(row) return PaginatedResponse( @@ -157,14 +158,12 @@ class AuthorizedSqlStore: async def fetch_one( self, table: str, - policy: list[AccessRule], where: Mapping[str, Any] | None = None, order_by: list[tuple[str, Literal["asc", "desc"]]] | None = None, ) -> dict[str, Any] | None: """Fetch one row with automatic access control checking.""" results = await self.fetch_all( table=table, - policy=policy, where=where, limit=1, order_by=order_by, diff --git a/tests/integration/providers/utils/sqlstore/test_authorized_sqlstore.py b/tests/integration/providers/utils/sqlstore/test_authorized_sqlstore.py index 4002f2e1f..98bef0f2c 100644 --- a/tests/integration/providers/utils/sqlstore/test_authorized_sqlstore.py +++ b/tests/integration/providers/utils/sqlstore/test_authorized_sqlstore.py @@ -57,7 +57,7 @@ def authorized_store(backend_config): config = config_func() base_sqlstore = sqlstore_impl(config) - authorized_store = AuthorizedSqlStore(base_sqlstore) + authorized_store = AuthorizedSqlStore(base_sqlstore, default_policy()) yield authorized_store @@ -106,7 +106,7 @@ async def test_authorized_store_attributes(mock_get_authenticated_user, authoriz await authorized_store.insert(table_name, {"id": "1", "data": "public_data"}) # Test fetching with no user - should not error on JSON comparison - result = await authorized_store.fetch_all(table_name, policy=default_policy()) + result = await authorized_store.fetch_all(table_name) assert len(result.data) == 1 assert result.data[0]["id"] == "1" assert result.data[0]["access_attributes"] is None @@ -119,7 +119,7 @@ async def test_authorized_store_attributes(mock_get_authenticated_user, authoriz await authorized_store.insert(table_name, {"id": "2", "data": "admin_data"}) # Fetch all - admin should see both - result = await authorized_store.fetch_all(table_name, policy=default_policy()) + result = await authorized_store.fetch_all(table_name) assert len(result.data) == 2 # Test with non-admin user @@ -127,7 +127,7 @@ async def test_authorized_store_attributes(mock_get_authenticated_user, authoriz mock_get_authenticated_user.return_value = regular_user # Should only see public record - result = await authorized_store.fetch_all(table_name, policy=default_policy()) + result = await authorized_store.fetch_all(table_name) assert len(result.data) == 1 assert result.data[0]["id"] == "1" @@ -156,7 +156,7 @@ async def test_authorized_store_attributes(mock_get_authenticated_user, authoriz # Now test with the multi-user who has both roles=admin and teams=dev mock_get_authenticated_user.return_value = multi_user - result = await authorized_store.fetch_all(table_name, policy=default_policy()) + result = await authorized_store.fetch_all(table_name) # Should see: # - public record (1) - no access_attributes @@ -217,21 +217,24 @@ async def test_user_ownership_policy(mock_get_authenticated_user, authorized_sto ), ] + # Create a new authorized store with the owner-only policy + owner_only_store = AuthorizedSqlStore(authorized_store.sql_store, owner_only_policy) + # Test user1 access - should only see their own record mock_get_authenticated_user.return_value = user1 - result = await authorized_store.fetch_all(table_name, policy=owner_only_policy) + result = await owner_only_store.fetch_all(table_name) assert len(result.data) == 1, f"Expected user1 to see 1 record, got {len(result.data)}" assert result.data[0]["id"] == "1", f"Expected user1's record, got {result.data[0]['id']}" # Test user2 access - should only see their own record mock_get_authenticated_user.return_value = user2 - result = await authorized_store.fetch_all(table_name, policy=owner_only_policy) + result = await owner_only_store.fetch_all(table_name) assert len(result.data) == 1, f"Expected user2 to see 1 record, got {len(result.data)}" assert result.data[0]["id"] == "2", f"Expected user2's record, got {result.data[0]['id']}" # Test with anonymous user - should see no records mock_get_authenticated_user.return_value = None - result = await authorized_store.fetch_all(table_name, policy=owner_only_policy) + result = await owner_only_store.fetch_all(table_name) assert len(result.data) == 0, f"Expected anonymous user to see 0 records, got {len(result.data)}" finally: diff --git a/tests/unit/utils/test_authorized_sqlstore.py b/tests/unit/utils/test_authorized_sqlstore.py index 90eb706e4..d85e784a9 100644 --- a/tests/unit/utils/test_authorized_sqlstore.py +++ b/tests/unit/utils/test_authorized_sqlstore.py @@ -26,7 +26,7 @@ async def test_authorized_fetch_with_where_sql_access_control(mock_get_authentic db_path=tmp_dir + "/" + db_name, ) ) - sqlstore = AuthorizedSqlStore(base_sqlstore) + sqlstore = AuthorizedSqlStore(base_sqlstore, default_policy()) # Create table with access control await sqlstore.create_table( @@ -56,24 +56,24 @@ async def test_authorized_fetch_with_where_sql_access_control(mock_get_authentic mock_get_authenticated_user.return_value = admin_user # Admin should see both documents - result = await sqlstore.fetch_all("documents", policy=default_policy(), where={"id": 1}) + result = await sqlstore.fetch_all("documents", where={"id": 1}) assert len(result.data) == 1 assert result.data[0]["title"] == "Admin Document" # User should only see their document mock_get_authenticated_user.return_value = regular_user - result = await sqlstore.fetch_all("documents", policy=default_policy(), where={"id": 1}) + result = await sqlstore.fetch_all("documents", where={"id": 1}) assert len(result.data) == 0 - result = await sqlstore.fetch_all("documents", policy=default_policy(), where={"id": 2}) + result = await sqlstore.fetch_all("documents", where={"id": 2}) assert len(result.data) == 1 assert result.data[0]["title"] == "User Document" - row = await sqlstore.fetch_one("documents", policy=default_policy(), where={"id": 1}) + row = await sqlstore.fetch_one("documents", where={"id": 1}) assert row is None - row = await sqlstore.fetch_one("documents", policy=default_policy(), where={"id": 2}) + row = await sqlstore.fetch_one("documents", where={"id": 2}) assert row is not None assert row["title"] == "User Document" @@ -88,7 +88,7 @@ async def test_sql_policy_consistency(mock_get_authenticated_user): db_path=tmp_dir + "/" + db_name, ) ) - sqlstore = AuthorizedSqlStore(base_sqlstore) + sqlstore = AuthorizedSqlStore(base_sqlstore, default_policy()) await sqlstore.create_table( table="resources", @@ -144,7 +144,7 @@ async def test_sql_policy_consistency(mock_get_authenticated_user): user = User(principal=user_data["principal"], attributes=user_data["attributes"]) mock_get_authenticated_user.return_value = user - sql_results = await sqlstore.fetch_all("resources", policy=policy) + sql_results = await sqlstore.fetch_all("resources") sql_ids = {row["id"] for row in sql_results.data} policy_ids = set() for scenario in test_scenarios: @@ -174,7 +174,7 @@ async def test_authorized_store_user_attribute_capture(mock_get_authenticated_us db_path=tmp_dir + "/" + db_name, ) ) - authorized_store = AuthorizedSqlStore(base_sqlstore) + authorized_store = AuthorizedSqlStore(base_sqlstore, default_policy()) await authorized_store.create_table( table="user_data", From 142a38db8b45e76876eb4f143edff11432d165d6 Mon Sep 17 00:00:00 2001 From: Matthew Farrellee Date: Sat, 20 Sep 2025 19:09:27 -0400 Subject: [PATCH 08/18] chore: remove duplicate AnthropicProviderDataValidator (#3512) # What does this PR do? removes the duplicate AnthropicProviderDataValidator the active one is in config.py ## Test Plan ci --- .../providers/remote/inference/anthropic/__init__.py | 6 ------ 1 file changed, 6 deletions(-) diff --git a/llama_stack/providers/remote/inference/anthropic/__init__.py b/llama_stack/providers/remote/inference/anthropic/__init__.py index 8b420a5a0..30d986808 100644 --- a/llama_stack/providers/remote/inference/anthropic/__init__.py +++ b/llama_stack/providers/remote/inference/anthropic/__init__.py @@ -4,15 +4,9 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from pydantic import BaseModel - from .config import AnthropicConfig -class AnthropicProviderDataValidator(BaseModel): - anthropic_api_key: str | None = None - - async def get_adapter_impl(config: AnthropicConfig, _deps): from .anthropic import AnthropicInferenceAdapter From e3f77c10049a46ab44d7a506904bc00b6e4b12be Mon Sep 17 00:00:00 2001 From: Derek Higgins Date: Sun, 21 Sep 2025 14:32:39 +0100 Subject: [PATCH 09/18] fix: Update inference recorder to handle both Ollama and OpenAI model (#3470) - Handle Ollama format where models are nested under response['body']['models'] - Fall back to OpenAI format where models are directly in response['body'] Closes: #3457 Signed-off-by: Derek Higgins --- llama_stack/testing/inference_recorder.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/llama_stack/testing/inference_recorder.py b/llama_stack/testing/inference_recorder.py index 674016fb1..1071da13f 100644 --- a/llama_stack/testing/inference_recorder.py +++ b/llama_stack/testing/inference_recorder.py @@ -203,7 +203,12 @@ def _model_identifiers_digest(endpoint: str, response: dict[str, Any]) -> str: - '/v1/models' (OpenAI): response body is: [ { id: ... }, ... ] Returns a list of unique identifiers or None if structure doesn't match. """ - items = response["body"] + if "models" in response["body"]: + # ollama + items = response["body"]["models"] + else: + # openai + items = response["body"] idents = [m.model if endpoint == "/api/tags" else m.id for m in items] return sorted(set(idents)) From 0e43be36e1a0eef00bec19ad3c0c56b46330110f Mon Sep 17 00:00:00 2001 From: Derek Higgins Date: Mon, 22 Sep 2025 12:31:30 +0100 Subject: [PATCH 10/18] fix: handle missing API keys gracefully in model refresh (#3493) - Catch Errors from providers without API keys during model refresh - Log as warning instead of exception to avoid a scary startup Closes: #3492 Error message are now warnings instead of several tracebacks ``` INFO 2025-09-19 16:06:55,228 llama_stack.providers.utils.inference.inference_store:74 inference_store: Write queue disabled for SQLite to avoid concurrency issues WARNING 2025-09-19 16:06:59,362 llama_stack.providers.utils.inference.openai_mixin:327 providers::utils: Failed to list models for anthropic: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"anthropic_api_key": ""}, or in the provider config. WARNING 2025-09-19 16:06:59,364 llama_stack.providers.utils.inference.openai_mixin:327 providers::utils: Failed to list models for gemini: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"gemini_api_key": ""}, or in the provider config. WARNING 2025-09-19 16:06:59,367 llama_stack.providers.utils.inference.openai_mixin:327 providers::utils: Failed to list models for groq: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"groq_api_key": ""}, or in the provider config. WARNING 2025-09-19 16:06:59,372 llama_stack.providers.utils.inference.openai_mixin:327 providers::utils: Failed to list models for sambanova: API key is not set. Please provide a valid API key in the provider data header, e.g. x-llamastack-provider-data: {"sambanova_api_key": ""}, or in the provider config. INFO 2025-09-19 16:06:59,533 llama_stack.core.utils.config_resolution:45 core: Using file path: ``` Signed-off-by: Derek Higgins --- llama_stack/core/routing_tables/models.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/llama_stack/core/routing_tables/models.py b/llama_stack/core/routing_tables/models.py index b6141efa9..641c73c16 100644 --- a/llama_stack/core/routing_tables/models.py +++ b/llama_stack/core/routing_tables/models.py @@ -33,7 +33,7 @@ class ModelsRoutingTable(CommonRoutingTableImpl, Models): try: models = await provider.list_models() except Exception as e: - logger.exception(f"Model refresh failed for provider {provider_id}: {e}") + logger.warning(f"Model refresh failed for provider {provider_id}: {e}") continue self.listed_providers.add(provider_id) From e2e42c8a370e79bf97e11a54280d20f80f2e8108 Mon Sep 17 00:00:00 2001 From: Matthew Farrellee Date: Mon, 22 Sep 2025 07:53:17 -0400 Subject: [PATCH 11/18] chore: remove duplicate OpenAI and Gemini data validators (#3513) # What does this PR do? removes the duplicate OpenAI/GeminiProviderDataValidator the active ones are in config.pys ## Test Plan ci --- llama_stack/providers/remote/inference/gemini/__init__.py | 6 ------ llama_stack/providers/remote/inference/openai/__init__.py | 6 ------ 2 files changed, 12 deletions(-) diff --git a/llama_stack/providers/remote/inference/gemini/__init__.py b/llama_stack/providers/remote/inference/gemini/__init__.py index 9d35da893..bda2f52d4 100644 --- a/llama_stack/providers/remote/inference/gemini/__init__.py +++ b/llama_stack/providers/remote/inference/gemini/__init__.py @@ -4,15 +4,9 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from pydantic import BaseModel - from .config import GeminiConfig -class GeminiProviderDataValidator(BaseModel): - gemini_api_key: str | None = None - - async def get_adapter_impl(config: GeminiConfig, _deps): from .gemini import GeminiInferenceAdapter diff --git a/llama_stack/providers/remote/inference/openai/__init__.py b/llama_stack/providers/remote/inference/openai/__init__.py index c245dbe10..bd3daeb9a 100644 --- a/llama_stack/providers/remote/inference/openai/__init__.py +++ b/llama_stack/providers/remote/inference/openai/__init__.py @@ -4,15 +4,9 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from pydantic import BaseModel - from .config import OpenAIConfig -class OpenAIProviderDataValidator(BaseModel): - openai_api_key: str | None = None - - async def get_adapter_impl(config: OpenAIConfig, _deps): from .openai import OpenAIInferenceAdapter From 6ce2cf3e128ac20a0c2c40fa86b54d1475e77c33 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon, 22 Sep 2025 13:54:35 +0200 Subject: [PATCH 12/18] chore(github-deps): bump astral-sh/setup-uv from 6.6.1 to 6.7.0 (#3502) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Bumps [astral-sh/setup-uv](https://github.com/astral-sh/setup-uv) from 6.6.1 to 6.7.0.
Release notes

Sourced from astral-sh/setup-uv's releases.

v6.7.0 🌈 New inputs restore-cache and save-cache

Changes

This release adds fine-grained control over the caching steps.

  • The input restore-cache (true by default) can be set to false to skip restoring the cache while still allowing to save the cache.
  • The input save-cache (true by default) can be set to false to skip saving the cache.

Skipping cache saving can be useful if you know, that you will never use this version of the cache again and don't want to waste storage space:

- name: Save cache only on main branch
  uses: astral-sh/setup-uv@v6
  with:
    enable-cache: true
    save-cache: ${{ github.ref == 'refs/heads/main' }}

🚀 Enhancements

🧰 Maintenance

⬆️ Dependency updates

Commits

[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=astral-sh/setup-uv&package-manager=github_actions&previous-version=6.6.1&new-version=6.7.0)](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) ---
Dependabot commands and options
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 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)
Signed-off-by: dependabot[bot] Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> --- .github/workflows/python-build-test.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/python-build-test.yml b/.github/workflows/python-build-test.yml index 00f0950c7..ea8e6a66a 100644 --- a/.github/workflows/python-build-test.yml +++ b/.github/workflows/python-build-test.yml @@ -24,7 +24,7 @@ jobs: uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0 - name: Install uv - uses: astral-sh/setup-uv@557e51de59eb14aaaba2ed9621916900a91d50c6 # v6.6.1 + uses: astral-sh/setup-uv@b75a909f75acd358c2196fb9a5f1299a9a8868a4 # v6.7.0 with: python-version: ${{ matrix.python-version }} activate-environment: true From 21f7667bb7661e292f7f2d68f4a0d01c5223a2be Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon, 22 Sep 2025 13:56:43 +0200 Subject: [PATCH 13/18] chore(ui-deps): bump remeda from 2.30.0 to 2.32.0 in /llama_stack/ui (#3511) Bumps [remeda](https://github.com/remeda/remeda) from 2.30.0 to 2.32.0.
Release notes

Sourced from remeda's releases.

v2.32.0

2.32.0 (2025-09-18)

Features

v2.31.1

2.31.1 (2025-09-09)

This version is identical to 2.31.0. We were experimenting with some modernizations of our release pipelines and needed to generate a release as part of testing those changes.

v2.31.0

2.31.0 (2025-09-08)

Features

Commits
Maintainer changes

This version was pushed to npm by eranhirsch, a new releaser for remeda since your current version.


[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=remeda&package-manager=npm_and_yarn&previous-version=2.30.0&new-version=2.32.0)](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) ---
Dependabot commands and options
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 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)
Signed-off-by: dependabot[bot] Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> --- llama_stack/ui/package-lock.json | 8 ++++---- llama_stack/ui/package.json | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/llama_stack/ui/package-lock.json b/llama_stack/ui/package-lock.json index 3f22716c6..fc79f5845 100644 --- a/llama_stack/ui/package-lock.json +++ b/llama_stack/ui/package-lock.json @@ -27,7 +27,7 @@ "react-dom": "^19.1.1", "react-markdown": "^10.1.0", "remark-gfm": "^4.0.1", - "remeda": "^2.30.0", + "remeda": "^2.32.0", "shiki": "^1.29.2", "sonner": "^2.0.7", "tailwind-merge": "^3.3.1" @@ -12887,9 +12887,9 @@ } }, "node_modules/remeda": { - "version": "2.30.0", - "resolved": "https://registry.npmjs.org/remeda/-/remeda-2.30.0.tgz", - "integrity": "sha512-TcRpI1ecqnMer3jHhFtMerGvHFCDlCHljUp0/9A4HxHOh5bSY3kP1l8nQDFMnWYJKl3MSarDNY1tb0Bs/bCmvw==", + "version": "2.32.0", + "resolved": "https://registry.npmjs.org/remeda/-/remeda-2.32.0.tgz", + "integrity": "sha512-BZx9DsT4FAgXDTOdgJIc5eY6ECIXMwtlSPQoPglF20ycSWigttDDe88AozEsPPT4OWk5NujroGSBC1phw5uU+w==", "license": "MIT", "dependencies": { "type-fest": "^4.41.0" diff --git a/llama_stack/ui/package.json b/llama_stack/ui/package.json index 2b0322b28..49c1b85e1 100644 --- a/llama_stack/ui/package.json +++ b/llama_stack/ui/package.json @@ -32,7 +32,7 @@ "react-dom": "^19.1.1", "react-markdown": "^10.1.0", "remark-gfm": "^4.0.1", - "remeda": "^2.30.0", + "remeda": "^2.32.0", "shiki": "^1.29.2", "sonner": "^2.0.7", "tailwind-merge": "^3.3.1" From 7c4a740a085b789cd0ee65bed9656d136c814a41 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon, 22 Sep 2025 13:56:58 +0200 Subject: [PATCH 14/18] chore(ui-deps): bump @radix-ui/react-dialog from 1.1.13 to 1.1.15 in /llama_stack/ui (#3510) Bumps [@radix-ui/react-dialog](https://github.com/radix-ui/primitives) from 1.1.13 to 1.1.15.
Commits

[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=@radix-ui/react-dialog&package-manager=npm_and_yarn&previous-version=1.1.13&new-version=1.1.15)](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) ---
Dependabot commands and options
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 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)
Signed-off-by: dependabot[bot] Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> --- llama_stack/ui/package-lock.json | 706 ++----------------------------- llama_stack/ui/package.json | 2 +- 2 files changed, 39 insertions(+), 669 deletions(-) diff --git a/llama_stack/ui/package-lock.json b/llama_stack/ui/package-lock.json index fc79f5845..2734eedb9 100644 --- a/llama_stack/ui/package-lock.json +++ b/llama_stack/ui/package-lock.json @@ -9,7 +9,7 @@ "version": "0.1.0", "dependencies": { "@radix-ui/react-collapsible": "^1.1.12", - "@radix-ui/react-dialog": "^1.1.13", + "@radix-ui/react-dialog": "^1.1.15", "@radix-ui/react-dropdown-menu": "^2.1.16", "@radix-ui/react-select": "^2.2.6", "@radix-ui/react-separator": "^1.1.7", @@ -2110,9 +2110,9 @@ "license": "MIT" }, "node_modules/@radix-ui/primitive": { - "version": "1.1.2", - "resolved": "https://registry.npmjs.org/@radix-ui/primitive/-/primitive-1.1.2.tgz", - "integrity": "sha512-XnbHrrprsNqZKQhStrSwgRUQzoCI1glLzdw79xiZPoofhGICeZRSQ3dIxAKH1gb3OHfNf4d6f+vAv3kil2eggA==", + "version": "1.1.3", + "resolved": "https://registry.npmjs.org/@radix-ui/primitive/-/primitive-1.1.3.tgz", + "integrity": "sha512-JTF99U/6XIjCBo0wqkU5sK10glYe27MRRsfwoiq5zzOEZLHU3A3KCMa5X/azekYRCJ0HlwI0crAXS/5dEHTzDg==", "license": "MIT" }, "node_modules/@radix-ui/react-arrow": { @@ -2138,29 +2138,6 @@ } } }, - "node_modules/@radix-ui/react-arrow/node_modules/@radix-ui/react-primitive": { - "version": "2.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-2.1.3.tgz", - "integrity": "sha512-m9gTwRkhy2lvCPe6QJp4d3G1TYEUHn/FzJUtq9MjH46an1wJU+GdoGC5VLof8RX8Ft/DlpshApkhswDLZzHIcQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-slot": "1.2.3" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, "node_modules/@radix-ui/react-collapsible": { "version": "1.1.12", "resolved": "https://registry.npmjs.org/@radix-ui/react-collapsible/-/react-collapsible-1.1.12.tgz", @@ -2191,59 +2168,6 @@ } } }, - "node_modules/@radix-ui/react-collapsible/node_modules/@radix-ui/primitive": { - "version": "1.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/primitive/-/primitive-1.1.3.tgz", - "integrity": "sha512-JTF99U/6XIjCBo0wqkU5sK10glYe27MRRsfwoiq5zzOEZLHU3A3KCMa5X/azekYRCJ0HlwI0crAXS/5dEHTzDg==", - "license": "MIT" - }, - "node_modules/@radix-ui/react-collapsible/node_modules/@radix-ui/react-presence": { - "version": "1.1.5", - "resolved": "https://registry.npmjs.org/@radix-ui/react-presence/-/react-presence-1.1.5.tgz", - "integrity": "sha512-/jfEwNDdQVBCNvjkGit4h6pMOzq8bHkopq458dPt2lMjx+eBQUohZNG9A7DtO/O5ukSbxuaNGXMjHicgwy6rQQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-compose-refs": "1.1.2", - "@radix-ui/react-use-layout-effect": "1.1.1" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, - "node_modules/@radix-ui/react-collapsible/node_modules/@radix-ui/react-primitive": { - "version": "2.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-2.1.3.tgz", - "integrity": "sha512-m9gTwRkhy2lvCPe6QJp4d3G1TYEUHn/FzJUtq9MjH46an1wJU+GdoGC5VLof8RX8Ft/DlpshApkhswDLZzHIcQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-slot": "1.2.3" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, "node_modules/@radix-ui/react-collection": { "version": "1.1.7", "resolved": "https://registry.npmjs.org/@radix-ui/react-collection/-/react-collection-1.1.7.tgz", @@ -2270,29 +2194,6 @@ } } }, - "node_modules/@radix-ui/react-collection/node_modules/@radix-ui/react-primitive": { - "version": "2.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-2.1.3.tgz", - "integrity": "sha512-m9gTwRkhy2lvCPe6QJp4d3G1TYEUHn/FzJUtq9MjH46an1wJU+GdoGC5VLof8RX8Ft/DlpshApkhswDLZzHIcQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-slot": "1.2.3" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, "node_modules/@radix-ui/react-compose-refs": { "version": "1.1.2", "resolved": "https://registry.npmjs.org/@radix-ui/react-compose-refs/-/react-compose-refs-1.1.2.tgz", @@ -2324,22 +2225,22 @@ } }, "node_modules/@radix-ui/react-dialog": { - "version": "1.1.13", - "resolved": "https://registry.npmjs.org/@radix-ui/react-dialog/-/react-dialog-1.1.13.tgz", - "integrity": "sha512-ARFmqUyhIVS3+riWzwGTe7JLjqwqgnODBUZdqpWar/z1WFs9z76fuOs/2BOWCR+YboRn4/WN9aoaGVwqNRr8VA==", + "version": "1.1.15", + "resolved": "https://registry.npmjs.org/@radix-ui/react-dialog/-/react-dialog-1.1.15.tgz", + "integrity": "sha512-TCglVRtzlffRNxRMEyR36DGBLJpeusFcgMVD9PZEzAKnUs1lKCgX5u9BmC2Yg+LL9MgZDugFFs1Vl+Jp4t/PGw==", "license": "MIT", "dependencies": { - "@radix-ui/primitive": "1.1.2", + "@radix-ui/primitive": "1.1.3", "@radix-ui/react-compose-refs": "1.1.2", "@radix-ui/react-context": "1.1.2", - "@radix-ui/react-dismissable-layer": "1.1.9", - "@radix-ui/react-focus-guards": "1.1.2", - "@radix-ui/react-focus-scope": "1.1.6", + "@radix-ui/react-dismissable-layer": "1.1.11", + "@radix-ui/react-focus-guards": "1.1.3", + "@radix-ui/react-focus-scope": "1.1.7", "@radix-ui/react-id": "1.1.1", - "@radix-ui/react-portal": "1.1.8", - "@radix-ui/react-presence": "1.1.4", - "@radix-ui/react-primitive": "2.1.2", - "@radix-ui/react-slot": "1.2.2", + "@radix-ui/react-portal": "1.1.9", + "@radix-ui/react-presence": "1.1.5", + "@radix-ui/react-primitive": "2.1.3", + "@radix-ui/react-slot": "1.2.3", "@radix-ui/react-use-controllable-state": "1.2.2", "aria-hidden": "^1.2.4", "react-remove-scroll": "^2.6.3" @@ -2359,24 +2260,6 @@ } } }, - "node_modules/@radix-ui/react-dialog/node_modules/@radix-ui/react-slot": { - "version": "1.2.2", - "resolved": "https://registry.npmjs.org/@radix-ui/react-slot/-/react-slot-1.2.2.tgz", - "integrity": "sha512-y7TBO4xN4Y94FvcWIOIh18fM4R1A8S4q1jhoz4PNzOoHsFcN8pogcFmZrTYAm4F9VRUrWP/Mw7xSKybIeRI+CQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-compose-refs": "1.1.2" - }, - "peerDependencies": { - "@types/react": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - } - } - }, "node_modules/@radix-ui/react-direction": { "version": "1.1.1", "resolved": "https://registry.npmjs.org/@radix-ui/react-direction/-/react-direction-1.1.1.tgz", @@ -2393,14 +2276,14 @@ } }, "node_modules/@radix-ui/react-dismissable-layer": { - "version": "1.1.9", - "resolved": "https://registry.npmjs.org/@radix-ui/react-dismissable-layer/-/react-dismissable-layer-1.1.9.tgz", - "integrity": "sha512-way197PiTvNp+WBP7svMJasHl+vibhWGQDb6Mgf5mhEWJkgb85z7Lfl9TUdkqpWsf8GRNmoopx9ZxCyDzmgRMQ==", + "version": "1.1.11", + "resolved": "https://registry.npmjs.org/@radix-ui/react-dismissable-layer/-/react-dismissable-layer-1.1.11.tgz", + "integrity": "sha512-Nqcp+t5cTB8BinFkZgXiMJniQH0PsUt2k51FUhbdfeKvc4ACcG2uQniY/8+h1Yv6Kza4Q7lD7PQV0z0oicE0Mg==", "license": "MIT", "dependencies": { - "@radix-ui/primitive": "1.1.2", + "@radix-ui/primitive": "1.1.3", "@radix-ui/react-compose-refs": "1.1.2", - "@radix-ui/react-primitive": "2.1.2", + "@radix-ui/react-primitive": "2.1.3", "@radix-ui/react-use-callback-ref": "1.1.1", "@radix-ui/react-use-escape-keydown": "1.1.1" }, @@ -2448,39 +2331,10 @@ } } }, - "node_modules/@radix-ui/react-dropdown-menu/node_modules/@radix-ui/primitive": { - "version": "1.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/primitive/-/primitive-1.1.3.tgz", - "integrity": "sha512-JTF99U/6XIjCBo0wqkU5sK10glYe27MRRsfwoiq5zzOEZLHU3A3KCMa5X/azekYRCJ0HlwI0crAXS/5dEHTzDg==", - "license": "MIT" - }, - "node_modules/@radix-ui/react-dropdown-menu/node_modules/@radix-ui/react-primitive": { - "version": "2.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-2.1.3.tgz", - "integrity": "sha512-m9gTwRkhy2lvCPe6QJp4d3G1TYEUHn/FzJUtq9MjH46an1wJU+GdoGC5VLof8RX8Ft/DlpshApkhswDLZzHIcQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-slot": "1.2.3" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, "node_modules/@radix-ui/react-focus-guards": { - "version": "1.1.2", - "resolved": "https://registry.npmjs.org/@radix-ui/react-focus-guards/-/react-focus-guards-1.1.2.tgz", - "integrity": "sha512-fyjAACV62oPV925xFCrH8DR5xWhg9KYtJT4s3u54jxp+L/hbpTY2kIeEFFbFe+a/HCE94zGQMZLIpVTPVZDhaA==", + "version": "1.1.3", + "resolved": "https://registry.npmjs.org/@radix-ui/react-focus-guards/-/react-focus-guards-1.1.3.tgz", + "integrity": "sha512-0rFg/Rj2Q62NCm62jZw0QX7a3sz6QCQU0LpZdNrJX8byRGaGVTqbrW9jAoIAHyMQqsNpeZ81YgSizOt5WXq0Pw==", "license": "MIT", "peerDependencies": { "@types/react": "*", @@ -2493,13 +2347,13 @@ } }, "node_modules/@radix-ui/react-focus-scope": { - "version": "1.1.6", - "resolved": "https://registry.npmjs.org/@radix-ui/react-focus-scope/-/react-focus-scope-1.1.6.tgz", - "integrity": "sha512-r9zpYNUQY+2jWHWZGyddQLL9YHkM/XvSFHVcWs7bdVuxMAnCwTAuy6Pf47Z4nw7dYcUou1vg/VgjjrrH03VeBw==", + "version": "1.1.7", + "resolved": "https://registry.npmjs.org/@radix-ui/react-focus-scope/-/react-focus-scope-1.1.7.tgz", + "integrity": "sha512-t2ODlkXBQyn7jkl6TNaw/MtVEVvIGelJDCG41Okq/KwUsJBwQ4XVZsHAVUkK4mBv3ewiAS3PGuUWuY2BoK4ZUw==", "license": "MIT", "dependencies": { "@radix-ui/react-compose-refs": "1.1.2", - "@radix-ui/react-primitive": "2.1.2", + "@radix-ui/react-primitive": "2.1.3", "@radix-ui/react-use-callback-ref": "1.1.1" }, "peerDependencies": { @@ -2575,150 +2429,6 @@ } } }, - "node_modules/@radix-ui/react-menu/node_modules/@radix-ui/primitive": { - "version": "1.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/primitive/-/primitive-1.1.3.tgz", - "integrity": "sha512-JTF99U/6XIjCBo0wqkU5sK10glYe27MRRsfwoiq5zzOEZLHU3A3KCMa5X/azekYRCJ0HlwI0crAXS/5dEHTzDg==", - "license": "MIT" - }, - "node_modules/@radix-ui/react-menu/node_modules/@radix-ui/react-dismissable-layer": { - "version": "1.1.11", - "resolved": "https://registry.npmjs.org/@radix-ui/react-dismissable-layer/-/react-dismissable-layer-1.1.11.tgz", - "integrity": "sha512-Nqcp+t5cTB8BinFkZgXiMJniQH0PsUt2k51FUhbdfeKvc4ACcG2uQniY/8+h1Yv6Kza4Q7lD7PQV0z0oicE0Mg==", - "license": "MIT", - "dependencies": { - "@radix-ui/primitive": "1.1.3", - "@radix-ui/react-compose-refs": "1.1.2", - "@radix-ui/react-primitive": "2.1.3", - "@radix-ui/react-use-callback-ref": "1.1.1", - "@radix-ui/react-use-escape-keydown": "1.1.1" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, - "node_modules/@radix-ui/react-menu/node_modules/@radix-ui/react-focus-guards": { - "version": "1.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/react-focus-guards/-/react-focus-guards-1.1.3.tgz", - "integrity": "sha512-0rFg/Rj2Q62NCm62jZw0QX7a3sz6QCQU0LpZdNrJX8byRGaGVTqbrW9jAoIAHyMQqsNpeZ81YgSizOt5WXq0Pw==", - "license": "MIT", - "peerDependencies": { - "@types/react": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - } - } - }, - "node_modules/@radix-ui/react-menu/node_modules/@radix-ui/react-focus-scope": { - "version": "1.1.7", - "resolved": "https://registry.npmjs.org/@radix-ui/react-focus-scope/-/react-focus-scope-1.1.7.tgz", - "integrity": "sha512-t2ODlkXBQyn7jkl6TNaw/MtVEVvIGelJDCG41Okq/KwUsJBwQ4XVZsHAVUkK4mBv3ewiAS3PGuUWuY2BoK4ZUw==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-compose-refs": "1.1.2", - "@radix-ui/react-primitive": "2.1.3", - "@radix-ui/react-use-callback-ref": "1.1.1" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, - "node_modules/@radix-ui/react-menu/node_modules/@radix-ui/react-portal": { - "version": "1.1.9", - "resolved": "https://registry.npmjs.org/@radix-ui/react-portal/-/react-portal-1.1.9.tgz", - "integrity": "sha512-bpIxvq03if6UNwXZ+HTK71JLh4APvnXntDc6XOX8UVq4XQOVl7lwok0AvIl+b8zgCw3fSaVTZMpAPPagXbKmHQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-primitive": "2.1.3", - "@radix-ui/react-use-layout-effect": "1.1.1" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, - "node_modules/@radix-ui/react-menu/node_modules/@radix-ui/react-presence": { - "version": "1.1.5", - "resolved": "https://registry.npmjs.org/@radix-ui/react-presence/-/react-presence-1.1.5.tgz", - "integrity": "sha512-/jfEwNDdQVBCNvjkGit4h6pMOzq8bHkopq458dPt2lMjx+eBQUohZNG9A7DtO/O5ukSbxuaNGXMjHicgwy6rQQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-compose-refs": "1.1.2", - "@radix-ui/react-use-layout-effect": "1.1.1" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, - "node_modules/@radix-ui/react-menu/node_modules/@radix-ui/react-primitive": { - "version": "2.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-2.1.3.tgz", - "integrity": "sha512-m9gTwRkhy2lvCPe6QJp4d3G1TYEUHn/FzJUtq9MjH46an1wJU+GdoGC5VLof8RX8Ft/DlpshApkhswDLZzHIcQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-slot": "1.2.3" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, "node_modules/@radix-ui/react-popper": { "version": "1.2.8", "resolved": "https://registry.npmjs.org/@radix-ui/react-popper/-/react-popper-1.2.8.tgz", @@ -2751,36 +2461,13 @@ } } }, - "node_modules/@radix-ui/react-popper/node_modules/@radix-ui/react-primitive": { - "version": "2.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-2.1.3.tgz", - "integrity": "sha512-m9gTwRkhy2lvCPe6QJp4d3G1TYEUHn/FzJUtq9MjH46an1wJU+GdoGC5VLof8RX8Ft/DlpshApkhswDLZzHIcQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-slot": "1.2.3" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, "node_modules/@radix-ui/react-portal": { - "version": "1.1.8", - "resolved": "https://registry.npmjs.org/@radix-ui/react-portal/-/react-portal-1.1.8.tgz", - "integrity": "sha512-hQsTUIn7p7fxCPvao/q6wpbxmCwgLrlz+nOrJgC+RwfZqWY/WN+UMqkXzrtKbPrF82P43eCTl3ekeKuyAQbFeg==", + "version": "1.1.9", + "resolved": "https://registry.npmjs.org/@radix-ui/react-portal/-/react-portal-1.1.9.tgz", + "integrity": "sha512-bpIxvq03if6UNwXZ+HTK71JLh4APvnXntDc6XOX8UVq4XQOVl7lwok0AvIl+b8zgCw3fSaVTZMpAPPagXbKmHQ==", "license": "MIT", "dependencies": { - "@radix-ui/react-primitive": "2.1.2", + "@radix-ui/react-primitive": "2.1.3", "@radix-ui/react-use-layout-effect": "1.1.1" }, "peerDependencies": { @@ -2799,9 +2486,9 @@ } }, "node_modules/@radix-ui/react-presence": { - "version": "1.1.4", - "resolved": "https://registry.npmjs.org/@radix-ui/react-presence/-/react-presence-1.1.4.tgz", - "integrity": "sha512-ueDqRbdc4/bkaQT3GIpLQssRlFgWaL/U2z/S31qRwwLWoxHLgry3SIfCwhxeQNbirEUXFa+lq3RL3oBYXtcmIA==", + "version": "1.1.5", + "resolved": "https://registry.npmjs.org/@radix-ui/react-presence/-/react-presence-1.1.5.tgz", + "integrity": "sha512-/jfEwNDdQVBCNvjkGit4h6pMOzq8bHkopq458dPt2lMjx+eBQUohZNG9A7DtO/O5ukSbxuaNGXMjHicgwy6rQQ==", "license": "MIT", "dependencies": { "@radix-ui/react-compose-refs": "1.1.2", @@ -2823,12 +2510,12 @@ } }, "node_modules/@radix-ui/react-primitive": { - "version": "2.1.2", - "resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-2.1.2.tgz", - "integrity": "sha512-uHa+l/lKfxuDD2zjN/0peM/RhhSmRjr5YWdk/37EnSv1nJ88uvG85DPexSm8HdFQROd2VdERJ6ynXbkCFi+APw==", + "version": "2.1.3", + "resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-2.1.3.tgz", + "integrity": "sha512-m9gTwRkhy2lvCPe6QJp4d3G1TYEUHn/FzJUtq9MjH46an1wJU+GdoGC5VLof8RX8Ft/DlpshApkhswDLZzHIcQ==", "license": "MIT", "dependencies": { - "@radix-ui/react-slot": "1.2.2" + "@radix-ui/react-slot": "1.2.3" }, "peerDependencies": { "@types/react": "*", @@ -2845,24 +2532,6 @@ } } }, - "node_modules/@radix-ui/react-primitive/node_modules/@radix-ui/react-slot": { - "version": "1.2.2", - "resolved": "https://registry.npmjs.org/@radix-ui/react-slot/-/react-slot-1.2.2.tgz", - "integrity": "sha512-y7TBO4xN4Y94FvcWIOIh18fM4R1A8S4q1jhoz4PNzOoHsFcN8pogcFmZrTYAm4F9VRUrWP/Mw7xSKybIeRI+CQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-compose-refs": "1.1.2" - }, - "peerDependencies": { - "@types/react": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - } - } - }, "node_modules/@radix-ui/react-roving-focus": { "version": "1.1.11", "resolved": "https://registry.npmjs.org/@radix-ui/react-roving-focus/-/react-roving-focus-1.1.11.tgz", @@ -2894,35 +2563,6 @@ } } }, - "node_modules/@radix-ui/react-roving-focus/node_modules/@radix-ui/primitive": { - "version": "1.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/primitive/-/primitive-1.1.3.tgz", - "integrity": "sha512-JTF99U/6XIjCBo0wqkU5sK10glYe27MRRsfwoiq5zzOEZLHU3A3KCMa5X/azekYRCJ0HlwI0crAXS/5dEHTzDg==", - "license": "MIT" - }, - "node_modules/@radix-ui/react-roving-focus/node_modules/@radix-ui/react-primitive": { - "version": "2.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-2.1.3.tgz", - "integrity": "sha512-m9gTwRkhy2lvCPe6QJp4d3G1TYEUHn/FzJUtq9MjH46an1wJU+GdoGC5VLof8RX8Ft/DlpshApkhswDLZzHIcQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-slot": "1.2.3" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, "node_modules/@radix-ui/react-select": { "version": "2.2.6", "resolved": "https://registry.npmjs.org/@radix-ui/react-select/-/react-select-2.2.6.tgz", @@ -2966,126 +2606,6 @@ } } }, - "node_modules/@radix-ui/react-select/node_modules/@radix-ui/primitive": { - "version": "1.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/primitive/-/primitive-1.1.3.tgz", - "integrity": "sha512-JTF99U/6XIjCBo0wqkU5sK10glYe27MRRsfwoiq5zzOEZLHU3A3KCMa5X/azekYRCJ0HlwI0crAXS/5dEHTzDg==", - "license": "MIT" - }, - "node_modules/@radix-ui/react-select/node_modules/@radix-ui/react-dismissable-layer": { - "version": "1.1.11", - "resolved": "https://registry.npmjs.org/@radix-ui/react-dismissable-layer/-/react-dismissable-layer-1.1.11.tgz", - "integrity": "sha512-Nqcp+t5cTB8BinFkZgXiMJniQH0PsUt2k51FUhbdfeKvc4ACcG2uQniY/8+h1Yv6Kza4Q7lD7PQV0z0oicE0Mg==", - "license": "MIT", - "dependencies": { - "@radix-ui/primitive": "1.1.3", - "@radix-ui/react-compose-refs": "1.1.2", - "@radix-ui/react-primitive": "2.1.3", - "@radix-ui/react-use-callback-ref": "1.1.1", - "@radix-ui/react-use-escape-keydown": "1.1.1" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, - "node_modules/@radix-ui/react-select/node_modules/@radix-ui/react-focus-guards": { - "version": "1.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/react-focus-guards/-/react-focus-guards-1.1.3.tgz", - "integrity": "sha512-0rFg/Rj2Q62NCm62jZw0QX7a3sz6QCQU0LpZdNrJX8byRGaGVTqbrW9jAoIAHyMQqsNpeZ81YgSizOt5WXq0Pw==", - "license": "MIT", - "peerDependencies": { - "@types/react": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - } - } - }, - "node_modules/@radix-ui/react-select/node_modules/@radix-ui/react-focus-scope": { - "version": "1.1.7", - "resolved": "https://registry.npmjs.org/@radix-ui/react-focus-scope/-/react-focus-scope-1.1.7.tgz", - "integrity": "sha512-t2ODlkXBQyn7jkl6TNaw/MtVEVvIGelJDCG41Okq/KwUsJBwQ4XVZsHAVUkK4mBv3ewiAS3PGuUWuY2BoK4ZUw==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-compose-refs": "1.1.2", - "@radix-ui/react-primitive": "2.1.3", - "@radix-ui/react-use-callback-ref": "1.1.1" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, - "node_modules/@radix-ui/react-select/node_modules/@radix-ui/react-portal": { - "version": "1.1.9", - "resolved": "https://registry.npmjs.org/@radix-ui/react-portal/-/react-portal-1.1.9.tgz", - "integrity": "sha512-bpIxvq03if6UNwXZ+HTK71JLh4APvnXntDc6XOX8UVq4XQOVl7lwok0AvIl+b8zgCw3fSaVTZMpAPPagXbKmHQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-primitive": "2.1.3", - "@radix-ui/react-use-layout-effect": "1.1.1" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, - "node_modules/@radix-ui/react-select/node_modules/@radix-ui/react-primitive": { - "version": "2.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-2.1.3.tgz", - "integrity": "sha512-m9gTwRkhy2lvCPe6QJp4d3G1TYEUHn/FzJUtq9MjH46an1wJU+GdoGC5VLof8RX8Ft/DlpshApkhswDLZzHIcQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-slot": "1.2.3" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, "node_modules/@radix-ui/react-separator": { "version": "1.1.7", "resolved": "https://registry.npmjs.org/@radix-ui/react-separator/-/react-separator-1.1.7.tgz", @@ -3109,29 +2629,6 @@ } } }, - "node_modules/@radix-ui/react-separator/node_modules/@radix-ui/react-primitive": { - "version": "2.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-2.1.3.tgz", - "integrity": "sha512-m9gTwRkhy2lvCPe6QJp4d3G1TYEUHn/FzJUtq9MjH46an1wJU+GdoGC5VLof8RX8Ft/DlpshApkhswDLZzHIcQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-slot": "1.2.3" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, "node_modules/@radix-ui/react-slot": { "version": "1.2.3", "resolved": "https://registry.npmjs.org/@radix-ui/react-slot/-/react-slot-1.2.3.tgz", @@ -3184,110 +2681,6 @@ } } }, - "node_modules/@radix-ui/react-tooltip/node_modules/@radix-ui/primitive": { - "version": "1.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/primitive/-/primitive-1.1.3.tgz", - "integrity": "sha512-JTF99U/6XIjCBo0wqkU5sK10glYe27MRRsfwoiq5zzOEZLHU3A3KCMa5X/azekYRCJ0HlwI0crAXS/5dEHTzDg==", - "license": "MIT" - }, - "node_modules/@radix-ui/react-tooltip/node_modules/@radix-ui/react-dismissable-layer": { - "version": "1.1.11", - "resolved": "https://registry.npmjs.org/@radix-ui/react-dismissable-layer/-/react-dismissable-layer-1.1.11.tgz", - "integrity": "sha512-Nqcp+t5cTB8BinFkZgXiMJniQH0PsUt2k51FUhbdfeKvc4ACcG2uQniY/8+h1Yv6Kza4Q7lD7PQV0z0oicE0Mg==", - "license": "MIT", - "dependencies": { - "@radix-ui/primitive": "1.1.3", - "@radix-ui/react-compose-refs": "1.1.2", - "@radix-ui/react-primitive": "2.1.3", - "@radix-ui/react-use-callback-ref": "1.1.1", - "@radix-ui/react-use-escape-keydown": "1.1.1" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, - "node_modules/@radix-ui/react-tooltip/node_modules/@radix-ui/react-portal": { - "version": "1.1.9", - "resolved": "https://registry.npmjs.org/@radix-ui/react-portal/-/react-portal-1.1.9.tgz", - "integrity": "sha512-bpIxvq03if6UNwXZ+HTK71JLh4APvnXntDc6XOX8UVq4XQOVl7lwok0AvIl+b8zgCw3fSaVTZMpAPPagXbKmHQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-primitive": "2.1.3", - "@radix-ui/react-use-layout-effect": "1.1.1" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, - "node_modules/@radix-ui/react-tooltip/node_modules/@radix-ui/react-presence": { - "version": "1.1.5", - "resolved": "https://registry.npmjs.org/@radix-ui/react-presence/-/react-presence-1.1.5.tgz", - "integrity": "sha512-/jfEwNDdQVBCNvjkGit4h6pMOzq8bHkopq458dPt2lMjx+eBQUohZNG9A7DtO/O5ukSbxuaNGXMjHicgwy6rQQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-compose-refs": "1.1.2", - "@radix-ui/react-use-layout-effect": "1.1.1" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, - "node_modules/@radix-ui/react-tooltip/node_modules/@radix-ui/react-primitive": { - "version": "2.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-2.1.3.tgz", - "integrity": "sha512-m9gTwRkhy2lvCPe6QJp4d3G1TYEUHn/FzJUtq9MjH46an1wJU+GdoGC5VLof8RX8Ft/DlpshApkhswDLZzHIcQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-slot": "1.2.3" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, "node_modules/@radix-ui/react-use-callback-ref": { "version": "1.1.1", "resolved": "https://registry.npmjs.org/@radix-ui/react-use-callback-ref/-/react-use-callback-ref-1.1.1.tgz", @@ -3447,29 +2840,6 @@ } } }, - "node_modules/@radix-ui/react-visually-hidden/node_modules/@radix-ui/react-primitive": { - "version": "2.1.3", - "resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-2.1.3.tgz", - "integrity": "sha512-m9gTwRkhy2lvCPe6QJp4d3G1TYEUHn/FzJUtq9MjH46an1wJU+GdoGC5VLof8RX8Ft/DlpshApkhswDLZzHIcQ==", - "license": "MIT", - "dependencies": { - "@radix-ui/react-slot": "1.2.3" - }, - "peerDependencies": { - "@types/react": "*", - "@types/react-dom": "*", - "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc", - "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc" - }, - "peerDependenciesMeta": { - "@types/react": { - "optional": true - }, - "@types/react-dom": { - "optional": true - } - } - }, "node_modules/@radix-ui/rect": { "version": "1.1.1", "resolved": "https://registry.npmjs.org/@radix-ui/rect/-/rect-1.1.1.tgz", diff --git a/llama_stack/ui/package.json b/llama_stack/ui/package.json index 49c1b85e1..ac68dbc07 100644 --- a/llama_stack/ui/package.json +++ b/llama_stack/ui/package.json @@ -14,7 +14,7 @@ }, "dependencies": { "@radix-ui/react-collapsible": "^1.1.12", - "@radix-ui/react-dialog": "^1.1.13", + "@radix-ui/react-dialog": "^1.1.15", "@radix-ui/react-dropdown-menu": "^2.1.16", "@radix-ui/react-select": "^2.2.6", "@radix-ui/react-separator": "^1.1.7", From a1301911e419f5f43cfd9f17fadc67c5002de327 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon, 22 Sep 2025 13:57:10 +0200 Subject: [PATCH 15/18] chore(ui-deps): bump jest-environment-jsdom from 29.7.0 to 30.1.2 in /llama_stack/ui (#3509) Bumps [jest-environment-jsdom](https://github.com/jestjs/jest/tree/HEAD/packages/jest-environment-jsdom) from 29.7.0 to 30.1.2.
Release notes

Sourced from jest-environment-jsdom's releases.

30.1.2

Fixes

  • [jest-snapshot-utils] Correct snapshot header regexp to work with newline across OSes (#15803)

30.1.1

Fixes

  • [jest-snapshot-utils] Fix deprecated goo.gl snapshot warning not handling Windows end-of-line sequences (#15800)

30.1.0

Features

  • [jest-leak-detector] Configurable GC aggressiveness regarding to V8 heap snapshot generation (#15793)
  • [jest-runtime] Reduce redundant ReferenceError messages
  • [jest-core] Include test modules that failed to load when --onlyFailures is active

Fixes

  • `[jest-snapshot-utils] Fix deprecated goo.gl snapshot guide link not getting replaced with fully canonical URL (#15787)
  • [jest-circus] Fix it.concurrent not working with describe.skip (#15765)
  • [jest-snapshot] Fix mangled inline snapshot updates when used with Prettier 3 and CRLF line endings
  • [jest-runtime] Importing from @jest/globals in more than one file no longer breaks relative paths (#15772)

Chore

  • [expect] Update docblock for toContain() to display info on substring check (#15789)

30.0.2

What's Changed

Fixes

  • [jest-matcher-utils] Make 'deepCyclicCopyObject' safer by setting descriptors to a null-prototype object (#15689)
  • [jest-util] Make garbage collection protection property writable (#15689)

Full Changelog: https://github.com/jestjs/jest/blob/main/CHANGELOG.md

Jest 30.0.1

What's Changed

Features

  • [jest-resolver] Implement the defaultAsyncResolver (#15679)

Fixes

  • [jest-resolver] Resolve builtin modules correctly (#15683)
  • [jest-environment-node, jest-util] Avoid setting globals cleanup protection symbol when feature is off (#15684)

... (truncated)

Changelog

Sourced from jest-environment-jsdom's changelog.

30.1.2

Fixes

  • [jest-snapshot-utils] Correct snapshot header regexp to work with newline across OSes (#15803)

30.1.1

Fixes

  • [jest-snapshot-utils] Fix deprecated goo.gl snapshot warning not handling Windows end-of-line sequences (#15800)

30.1.0

Features

  • [jest-leak-detector] Configurable GC aggressiveness regarding to V8 heap snapshot generation (#15793)
  • [jest-runtime] Reduce redundant ReferenceError messages
  • [jest-core] Include test modules that failed to load when --onlyFailures is active

Fixes

  • [jest-snapshot-utils] Fix deprecated goo.gl snapshot guide link not getting replaced with fully canonical URL (#15787)
  • [jest-circus] Fix it.concurrent not working with describe.skip (#15765)
  • [jest-snapshot] Fix mangled inline snapshot updates when used with Prettier 3 and CRLF line endings
  • [jest-runtime] Importing from @jest/globals in more than one file no longer breaks relative paths (#15772)

Chore

  • [expect] Update docblock for toContain() to display info on substring check (#15789)

30.0.5

Features

  • [jest-config] Allow testMatch to take a string value
  • [jest-worker] Let workerIdleMemoryLimit accept 0 to always restart worker child processes

Fixes

  • [expect] Fix bigint error (#15702)

30.0.4

Features

  • [expect] The Inverse type is now exported (#15714)
  • [expect] feat: support async functions in toBe (#15704)

Fixes

... (truncated)

Commits

[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=jest-environment-jsdom&package-manager=npm_and_yarn&previous-version=29.7.0&new-version=30.1.2)](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) ---
Dependabot commands and options
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 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)
Signed-off-by: dependabot[bot] Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> --- llama_stack/ui/package-lock.json | 1010 ++++++++++++++++++++++-------- llama_stack/ui/package.json | 2 +- 2 files changed, 738 insertions(+), 274 deletions(-) diff --git a/llama_stack/ui/package-lock.json b/llama_stack/ui/package-lock.json index 2734eedb9..638655639 100644 --- a/llama_stack/ui/package-lock.json +++ b/llama_stack/ui/package-lock.json @@ -47,7 +47,7 @@ "eslint-config-prettier": "^10.1.8", "eslint-plugin-prettier": "^5.5.4", "jest": "^29.7.0", - "jest-environment-jsdom": "^29.7.0", + "jest-environment-jsdom": "^30.1.2", "prettier": "3.6.2", "tailwindcss": "^4", "ts-node": "^10.9.2", @@ -89,6 +89,27 @@ "node": ">=6.0.0" } }, + "node_modules/@asamuzakjp/css-color": { + "version": "3.2.0", + "resolved": "https://registry.npmjs.org/@asamuzakjp/css-color/-/css-color-3.2.0.tgz", + "integrity": "sha512-K1A6z8tS3XsmCMM86xoWdn7Fkdn9m6RSVtocUrJYIwZnFVkng/PvkEoWtOWmP+Scc6saYWHWZYbndEEXxl24jw==", + "dev": true, + "license": "MIT", + "dependencies": { + "@csstools/css-calc": "^2.1.3", + "@csstools/css-color-parser": "^3.0.9", + "@csstools/css-parser-algorithms": "^3.0.4", + "@csstools/css-tokenizer": "^3.0.3", + "lru-cache": "^10.4.3" + } + }, + "node_modules/@asamuzakjp/css-color/node_modules/lru-cache": { + "version": "10.4.3", + "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-10.4.3.tgz", + "integrity": "sha512-JNAzZcXrCt42VGLuYz0zfAzDfAvJWW6AfYlDBQyDV5DClI2m5sAmK+OIO7s59XfsRsWHp02jAJrRadPRGTt6SQ==", + "dev": true, + "license": "ISC" + }, "node_modules/@babel/code-frame": { "version": "7.27.1", "resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.27.1.tgz", @@ -651,6 +672,121 @@ "@jridgewell/sourcemap-codec": "^1.4.10" } }, + "node_modules/@csstools/color-helpers": { + "version": "5.1.0", + "resolved": "https://registry.npmjs.org/@csstools/color-helpers/-/color-helpers-5.1.0.tgz", + "integrity": "sha512-S11EXWJyy0Mz5SYvRmY8nJYTFFd1LCNV+7cXyAgQtOOuzb4EsgfqDufL+9esx72/eLhsRdGZwaldu/h+E4t4BA==", + "dev": true, + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/csstools" + }, + { + "type": "opencollective", + "url": "https://opencollective.com/csstools" + } + ], + "license": "MIT-0", + "engines": { + "node": ">=18" + } + }, + "node_modules/@csstools/css-calc": { + "version": "2.1.4", + "resolved": "https://registry.npmjs.org/@csstools/css-calc/-/css-calc-2.1.4.tgz", + "integrity": "sha512-3N8oaj+0juUw/1H3YwmDDJXCgTB1gKU6Hc/bB502u9zR0q2vd786XJH9QfrKIEgFlZmhZiq6epXl4rHqhzsIgQ==", + "dev": true, + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/csstools" + }, + { + "type": "opencollective", + "url": "https://opencollective.com/csstools" + } + ], + "license": "MIT", + "engines": { + "node": ">=18" + }, + "peerDependencies": { + "@csstools/css-parser-algorithms": "^3.0.5", + "@csstools/css-tokenizer": "^3.0.4" + } + }, + "node_modules/@csstools/css-color-parser": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/@csstools/css-color-parser/-/css-color-parser-3.1.0.tgz", + "integrity": "sha512-nbtKwh3a6xNVIp/VRuXV64yTKnb1IjTAEEh3irzS+HkKjAOYLTGNb9pmVNntZ8iVBHcWDA2Dof0QtPgFI1BaTA==", + "dev": true, + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/csstools" + }, + { + "type": "opencollective", + "url": "https://opencollective.com/csstools" + } + ], + "license": "MIT", + "dependencies": { + "@csstools/color-helpers": "^5.1.0", + "@csstools/css-calc": "^2.1.4" + }, + "engines": { + "node": ">=18" + }, + "peerDependencies": { + "@csstools/css-parser-algorithms": "^3.0.5", + "@csstools/css-tokenizer": "^3.0.4" + } + }, + "node_modules/@csstools/css-parser-algorithms": { + "version": "3.0.5", + "resolved": "https://registry.npmjs.org/@csstools/css-parser-algorithms/-/css-parser-algorithms-3.0.5.tgz", + "integrity": "sha512-DaDeUkXZKjdGhgYaHNJTV9pV7Y9B3b644jCLs9Upc3VeNGg6LWARAT6O+Q+/COo+2gg/bM5rhpMAtf70WqfBdQ==", + "dev": true, + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/csstools" + }, + { + "type": "opencollective", + "url": "https://opencollective.com/csstools" + } + ], + "license": "MIT", + "engines": { + "node": ">=18" + }, + "peerDependencies": { + "@csstools/css-tokenizer": "^3.0.4" + } + }, + "node_modules/@csstools/css-tokenizer": { + "version": "3.0.4", + "resolved": "https://registry.npmjs.org/@csstools/css-tokenizer/-/css-tokenizer-3.0.4.tgz", + "integrity": "sha512-Vd/9EVDiu6PPJt9yAh6roZP6El1xHrdvIVGjyBsHR0RYwNHgL7FJPyIIW4fANJNG6FtyZfvlRPpFI4ZM/lubvw==", + "dev": true, + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/csstools" + }, + { + "type": "opencollective", + "url": "https://opencollective.com/csstools" + } + ], + "license": "MIT", + "engines": { + "node": ">=18" + } + }, "node_modules/@emnapi/core": { "version": "1.4.3", "resolved": "https://registry.npmjs.org/@emnapi/core/-/core-1.4.3.tgz", @@ -1591,6 +1727,235 @@ "node": "^14.15.0 || ^16.10.0 || >=18.0.0" } }, + "node_modules/@jest/environment-jsdom-abstract": { + "version": "30.1.2", + "resolved": "https://registry.npmjs.org/@jest/environment-jsdom-abstract/-/environment-jsdom-abstract-30.1.2.tgz", + "integrity": "sha512-u8kTh/ZBl97GOmnGJLYK/1GuwAruMC4hoP6xuk/kwltmVWsA9u/6fH1/CsPVGt2O+Wn2yEjs8n1B1zZJ62Cx0w==", + "dev": true, + "license": "MIT", + "dependencies": { + "@jest/environment": "30.1.2", + "@jest/fake-timers": "30.1.2", + "@jest/types": "30.0.5", + "@types/jsdom": "^21.1.7", + "@types/node": "*", + "jest-mock": "30.0.5", + "jest-util": "30.0.5" + }, + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + }, + "peerDependencies": { + "canvas": "^3.0.0", + "jsdom": "*" + }, + "peerDependenciesMeta": { + "canvas": { + "optional": true + } + } + }, + "node_modules/@jest/environment-jsdom-abstract/node_modules/@jest/environment": { + "version": "30.1.2", + "resolved": "https://registry.npmjs.org/@jest/environment/-/environment-30.1.2.tgz", + "integrity": "sha512-N8t1Ytw4/mr9uN28OnVf0SYE2dGhaIxOVYcwsf9IInBKjvofAjbFRvedvBBlyTYk2knbJTiEjEJ2PyyDIBnd9w==", + "dev": true, + "license": "MIT", + "dependencies": { + "@jest/fake-timers": "30.1.2", + "@jest/types": "30.0.5", + "@types/node": "*", + "jest-mock": "30.0.5" + }, + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + } + }, + "node_modules/@jest/environment-jsdom-abstract/node_modules/@jest/fake-timers": { + "version": "30.1.2", + "resolved": "https://registry.npmjs.org/@jest/fake-timers/-/fake-timers-30.1.2.tgz", + "integrity": "sha512-Beljfv9AYkr9K+ETX9tvV61rJTY706BhBUtiaepQHeEGfe0DbpvUA5Z3fomwc5Xkhns6NWrcFDZn+72fLieUnA==", + "dev": true, + "license": "MIT", + "dependencies": { + "@jest/types": "30.0.5", + "@sinonjs/fake-timers": "^13.0.0", + "@types/node": "*", + "jest-message-util": "30.1.0", + "jest-mock": "30.0.5", + "jest-util": "30.0.5" + }, + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + } + }, + "node_modules/@jest/environment-jsdom-abstract/node_modules/@jest/schemas": { + "version": "30.0.5", + "resolved": "https://registry.npmjs.org/@jest/schemas/-/schemas-30.0.5.tgz", + "integrity": "sha512-DmdYgtezMkh3cpU8/1uyXakv3tJRcmcXxBOcO0tbaozPwpmh4YMsnWrQm9ZmZMfa5ocbxzbFk6O4bDPEc/iAnA==", + "dev": true, + "license": "MIT", + "dependencies": { + "@sinclair/typebox": "^0.34.0" + }, + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + } + }, + "node_modules/@jest/environment-jsdom-abstract/node_modules/@jest/types": { + "version": "30.0.5", + "resolved": "https://registry.npmjs.org/@jest/types/-/types-30.0.5.tgz", + "integrity": "sha512-aREYa3aku9SSnea4aX6bhKn4bgv3AXkgijoQgbYV3yvbiGt6z+MQ85+6mIhx9DsKW2BuB/cLR/A+tcMThx+KLQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "@jest/pattern": "30.0.1", + "@jest/schemas": "30.0.5", + "@types/istanbul-lib-coverage": "^2.0.6", + "@types/istanbul-reports": "^3.0.4", + "@types/node": "*", + "@types/yargs": "^17.0.33", + "chalk": "^4.1.2" + }, + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + } + }, + "node_modules/@jest/environment-jsdom-abstract/node_modules/@sinclair/typebox": { + "version": "0.34.41", + "resolved": "https://registry.npmjs.org/@sinclair/typebox/-/typebox-0.34.41.tgz", + "integrity": "sha512-6gS8pZzSXdyRHTIqoqSVknxolr1kzfy4/CeDnrzsVz8TTIWUbOBr6gnzOmTYJ3eXQNh4IYHIGi5aIL7sOZ2G/g==", + "dev": true, + "license": "MIT" + }, + "node_modules/@jest/environment-jsdom-abstract/node_modules/@sinonjs/fake-timers": { + "version": "13.0.5", + "resolved": "https://registry.npmjs.org/@sinonjs/fake-timers/-/fake-timers-13.0.5.tgz", + "integrity": "sha512-36/hTbH2uaWuGVERyC6da9YwGWnzUZXuPro/F2LfsdOsLnCojz/iSH8MxUt/FD2S5XBSVPhmArFUXcpCQ2Hkiw==", + "dev": true, + "license": "BSD-3-Clause", + "dependencies": { + "@sinonjs/commons": "^3.0.1" + } + }, + "node_modules/@jest/environment-jsdom-abstract/node_modules/ansi-styles": { + "version": "5.2.0", + "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-5.2.0.tgz", + "integrity": "sha512-Cxwpt2SfTzTtXcfOlzGEee8O+c+MmUgGrNiBcXnuWxuFJHe6a5Hz7qwhwe5OgaSYI0IJvkLqWX1ASG+cJOkEiA==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/chalk/ansi-styles?sponsor=1" + } + }, + "node_modules/@jest/environment-jsdom-abstract/node_modules/ci-info": { + "version": "4.3.0", + "resolved": "https://registry.npmjs.org/ci-info/-/ci-info-4.3.0.tgz", + "integrity": "sha512-l+2bNRMiQgcfILUi33labAZYIWlH1kWDp+ecNo5iisRKrbm0xcRyCww71/YU0Fkw0mAFpz9bJayXPjey6vkmaQ==", + "dev": true, + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/sibiraj-s" + } + ], + "license": "MIT", + "engines": { + "node": ">=8" + } + }, + "node_modules/@jest/environment-jsdom-abstract/node_modules/jest-message-util": { + "version": "30.1.0", + "resolved": "https://registry.npmjs.org/jest-message-util/-/jest-message-util-30.1.0.tgz", + "integrity": "sha512-HizKDGG98cYkWmaLUHChq4iN+oCENohQLb7Z5guBPumYs+/etonmNFlg1Ps6yN9LTPyZn+M+b/9BbnHx3WTMDg==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/code-frame": "^7.27.1", + "@jest/types": "30.0.5", + "@types/stack-utils": "^2.0.3", + "chalk": "^4.1.2", + "graceful-fs": "^4.2.11", + "micromatch": "^4.0.8", + "pretty-format": "30.0.5", + "slash": "^3.0.0", + "stack-utils": "^2.0.6" + }, + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + } + }, + "node_modules/@jest/environment-jsdom-abstract/node_modules/jest-mock": { + "version": "30.0.5", + "resolved": "https://registry.npmjs.org/jest-mock/-/jest-mock-30.0.5.tgz", + "integrity": "sha512-Od7TyasAAQX/6S+QCbN6vZoWOMwlTtzzGuxJku1GhGanAjz9y+QsQkpScDmETvdc9aSXyJ/Op4rhpMYBWW91wQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "@jest/types": "30.0.5", + "@types/node": "*", + "jest-util": "30.0.5" + }, + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + } + }, + "node_modules/@jest/environment-jsdom-abstract/node_modules/jest-util": { + "version": "30.0.5", + "resolved": "https://registry.npmjs.org/jest-util/-/jest-util-30.0.5.tgz", + "integrity": "sha512-pvyPWssDZR0FlfMxCBoc0tvM8iUEskaRFALUtGQYzVEAqisAztmy+R8LnU14KT4XA0H/a5HMVTXat1jLne010g==", + "dev": true, + "license": "MIT", + "dependencies": { + "@jest/types": "30.0.5", + "@types/node": "*", + "chalk": "^4.1.2", + "ci-info": "^4.2.0", + "graceful-fs": "^4.2.11", + "picomatch": "^4.0.2" + }, + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + } + }, + "node_modules/@jest/environment-jsdom-abstract/node_modules/picomatch": { + "version": "4.0.3", + "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.3.tgz", + "integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=12" + }, + "funding": { + "url": "https://github.com/sponsors/jonschlinkert" + } + }, + "node_modules/@jest/environment-jsdom-abstract/node_modules/pretty-format": { + "version": "30.0.5", + "resolved": "https://registry.npmjs.org/pretty-format/-/pretty-format-30.0.5.tgz", + "integrity": "sha512-D1tKtYvByrBkFLe2wHJl2bwMJIiT8rW+XA+TiataH79/FszLQMrpGEvzUVkzPau7OCO0Qnrhpe87PqtOAIB8Yw==", + "dev": true, + "license": "MIT", + "dependencies": { + "@jest/schemas": "30.0.5", + "ansi-styles": "^5.2.0", + "react-is": "^18.3.1" + }, + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + } + }, + "node_modules/@jest/environment-jsdom-abstract/node_modules/react-is": { + "version": "18.3.1", + "resolved": "https://registry.npmjs.org/react-is/-/react-is-18.3.1.tgz", + "integrity": "sha512-/LLMVyas0ljjAtoYiPqYiL8VWXzUUdThrmU5+n20DZv+a+ClRoevUzw5JxU+Ieh5/c87ytoTBV9G1FiKfNJdmg==", + "dev": true, + "license": "MIT" + }, "node_modules/@jest/expect": { "version": "29.7.0", "resolved": "https://registry.npmjs.org/@jest/expect/-/expect-29.7.0.tgz", @@ -1652,6 +2017,30 @@ "node": "^14.15.0 || ^16.10.0 || >=18.0.0" } }, + "node_modules/@jest/pattern": { + "version": "30.0.1", + "resolved": "https://registry.npmjs.org/@jest/pattern/-/pattern-30.0.1.tgz", + "integrity": "sha512-gWp7NfQW27LaBQz3TITS8L7ZCQ0TLvtmI//4OwlQRx4rnWxcPNIYjxZpDcN4+UlGxgm3jS5QPz8IPTCkb59wZA==", + "dev": true, + "license": "MIT", + "dependencies": { + "@types/node": "*", + "jest-regex-util": "30.0.1" + }, + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + } + }, + "node_modules/@jest/pattern/node_modules/jest-regex-util": { + "version": "30.0.1", + "resolved": "https://registry.npmjs.org/jest-regex-util/-/jest-regex-util-30.0.1.tgz", + "integrity": "sha512-jHEQgBXAgc+Gh4g0p3bCevgRCVRkB4VB70zhoAE48gxeSr1hfUOsM/C2WoJgVL7Eyg//hudYENbm3Ne+/dRVVA==", + "dev": true, + "license": "MIT", + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + } + }, "node_modules/@jest/reporters": { "version": "29.7.0", "resolved": "https://registry.npmjs.org/@jest/reporters/-/reporters-29.7.0.tgz", @@ -3340,16 +3729,6 @@ } } }, - "node_modules/@tootallnate/once": { - "version": "2.0.0", - "resolved": "https://registry.npmjs.org/@tootallnate/once/-/once-2.0.0.tgz", - "integrity": "sha512-XCuKFP5PS55gnMVu3dty8KPatLqUoy/ZYzDzAGCQ8JNFCkLXzmI7vNHCR+XpbZaMWQK/vQubr7PkYq8g470J/A==", - "dev": true, - "license": "MIT", - "engines": { - "node": ">= 10" - } - }, "node_modules/@tsconfig/node10": { "version": "1.0.11", "resolved": "https://registry.npmjs.org/@tsconfig/node10/-/node10-1.0.11.tgz", @@ -3558,9 +3937,9 @@ "license": "MIT" }, "node_modules/@types/jsdom": { - "version": "20.0.1", - "resolved": "https://registry.npmjs.org/@types/jsdom/-/jsdom-20.0.1.tgz", - "integrity": "sha512-d0r18sZPmMQr1eG35u12FZfhIXNrnsPU/g5wvRKCUf/tOGilKKwYMYGqh33BNR6ba+2gkHw1EUiHoN3mn7E5IQ==", + "version": "21.1.7", + "resolved": "https://registry.npmjs.org/@types/jsdom/-/jsdom-21.1.7.tgz", + "integrity": "sha512-yOriVnggzrnQ3a9OKOCxaVuSug3w3/SbOj5i7VwXWZEyUNl3bLF9V3MfxGbZKuwqJOQyRfqXyROBB1CoZLFWzA==", "dev": true, "license": "MIT", "dependencies": { @@ -4208,14 +4587,6 @@ "win32" ] }, - "node_modules/abab": { - "version": "2.0.6", - "resolved": "https://registry.npmjs.org/abab/-/abab-2.0.6.tgz", - "integrity": "sha512-j2afSsaIENvHZN2B8GOpF566vZ5WVk5opAiMTvWgaQT8DkbOqsTfvNAvHoRGU2zzP8cPoqys+xHTRDWW8L+/BA==", - "deprecated": "Use your platform's native atob() and btoa() methods instead", - "dev": true, - "license": "BSD-3-Clause" - }, "node_modules/abort-controller": { "version": "3.0.0", "resolved": "https://registry.npmjs.org/abort-controller/-/abort-controller-3.0.0.tgz", @@ -4255,17 +4626,6 @@ "node": ">=0.4.0" } }, - "node_modules/acorn-globals": { - "version": "7.0.1", - "resolved": "https://registry.npmjs.org/acorn-globals/-/acorn-globals-7.0.1.tgz", - "integrity": "sha512-umOSDSDrfHbTNPuNpC2NSnnA3LUrqpevPb4T9jRx4MagXNS0rs+gwiTcAvqCRmsD6utzsrzNt+ebm00SNWiC3Q==", - "dev": true, - "license": "MIT", - "dependencies": { - "acorn": "^8.1.0", - "acorn-walk": "^8.0.2" - } - }, "node_modules/acorn-jsx": { "version": "5.3.2", "resolved": "https://registry.npmjs.org/acorn-jsx/-/acorn-jsx-5.3.2.tgz", @@ -4290,16 +4650,13 @@ } }, "node_modules/agent-base": { - "version": "6.0.2", - "resolved": "https://registry.npmjs.org/agent-base/-/agent-base-6.0.2.tgz", - "integrity": "sha512-RZNwNclF7+MS/8bDg70amg32dyeZGZxiDuQmZxKLAlQjr3jGyLx+4Kkk58UO7D2QdgFIQCovuSuZESne6RG6XQ==", + "version": "7.1.4", + "resolved": "https://registry.npmjs.org/agent-base/-/agent-base-7.1.4.tgz", + "integrity": "sha512-MnA+YT8fwfJPgBx3m60MNqakm30XOkyIoH1y6huTQvC0PwZG7ki8NacLBcrPbNoo8vEZy7Jpuk7+jMO+CUovTQ==", "dev": true, "license": "MIT", - "dependencies": { - "debug": "4" - }, "engines": { - "node": ">= 6.0.0" + "node": ">= 14" } }, "node_modules/agentkeepalive": { @@ -5335,33 +5692,20 @@ "dev": true, "license": "MIT" }, - "node_modules/cssom": { - "version": "0.5.0", - "resolved": "https://registry.npmjs.org/cssom/-/cssom-0.5.0.tgz", - "integrity": "sha512-iKuQcq+NdHqlAcwUY0o/HL69XQrUaQdMjmStJ8JFmUaiiQErlhrmuigkg/CU4E2J0IyUKUrMAgl36TvN67MqTw==", - "dev": true, - "license": "MIT" - }, "node_modules/cssstyle": { - "version": "2.3.0", - "resolved": "https://registry.npmjs.org/cssstyle/-/cssstyle-2.3.0.tgz", - "integrity": "sha512-AZL67abkUzIuvcHqk7c09cezpGNcxUxU4Ioi/05xHk4DQeTkWmGYftIE6ctU6AEt+Gn4n1lDStOtj7FKycP71A==", + "version": "4.6.0", + "resolved": "https://registry.npmjs.org/cssstyle/-/cssstyle-4.6.0.tgz", + "integrity": "sha512-2z+rWdzbbSZv6/rhtvzvqeZQHrBaqgogqt85sqFNbabZOuFbCVFb8kPeEtZjiKkbrm395irpNKiYeFeLiQnFPg==", "dev": true, "license": "MIT", "dependencies": { - "cssom": "~0.3.6" + "@asamuzakjp/css-color": "^3.2.0", + "rrweb-cssom": "^0.8.0" }, "engines": { - "node": ">=8" + "node": ">=18" } }, - "node_modules/cssstyle/node_modules/cssom": { - "version": "0.3.8", - "resolved": "https://registry.npmjs.org/cssom/-/cssom-0.3.8.tgz", - "integrity": "sha512-b0tGHbfegbhPJpxpiBPU2sCkigAqtM9O121le6bbOlgyV+NyGyCmVfJ6QW9eRjz8CpNfWEOYBIMIGRYkLwsIYg==", - "dev": true, - "license": "MIT" - }, "node_modules/csstype": { "version": "3.1.3", "resolved": "https://registry.npmjs.org/csstype/-/csstype-3.1.3.tgz", @@ -5376,31 +5720,30 @@ "license": "BSD-2-Clause" }, "node_modules/data-urls": { - "version": "3.0.2", - "resolved": "https://registry.npmjs.org/data-urls/-/data-urls-3.0.2.tgz", - "integrity": "sha512-Jy/tj3ldjZJo63sVAvg6LHt2mHvl4V6AgRAmNDtLdm7faqtsx+aJG42rsyCo9JCoRVKwPFzKlIPx3DIibwSIaQ==", + "version": "5.0.0", + "resolved": "https://registry.npmjs.org/data-urls/-/data-urls-5.0.0.tgz", + "integrity": "sha512-ZYP5VBHshaDAiVZxjbRVcFJpc+4xGgT0bK3vzy1HLN8jTO975HEbuYzZJcHoQEY5K1a0z8YayJkyVETa08eNTg==", "dev": true, "license": "MIT", "dependencies": { - "abab": "^2.0.6", - "whatwg-mimetype": "^3.0.0", - "whatwg-url": "^11.0.0" + "whatwg-mimetype": "^4.0.0", + "whatwg-url": "^14.0.0" }, "engines": { - "node": ">=12" + "node": ">=18" } }, "node_modules/data-urls/node_modules/tr46": { - "version": "3.0.0", - "resolved": "https://registry.npmjs.org/tr46/-/tr46-3.0.0.tgz", - "integrity": "sha512-l7FvfAHlcmulp8kr+flpQZmVwtu7nfRV7NZujtN0OqES8EL4O4e0qqzL0DC5gAvx/ZC/9lk6rhcUwYvkBnBnYA==", + "version": "5.1.1", + "resolved": "https://registry.npmjs.org/tr46/-/tr46-5.1.1.tgz", + "integrity": "sha512-hdF5ZgjTqgAntKkklYw0R03MG2x/bSzTtkxmIRw/sTNV8YXsCJ1tfLAX23lhxhHJlEf3CRCOCGGWw3vI3GaSPw==", "dev": true, "license": "MIT", "dependencies": { - "punycode": "^2.1.1" + "punycode": "^2.3.1" }, "engines": { - "node": ">=12" + "node": ">=18" } }, "node_modules/data-urls/node_modules/webidl-conversions": { @@ -5414,17 +5757,17 @@ } }, "node_modules/data-urls/node_modules/whatwg-url": { - "version": "11.0.0", - "resolved": "https://registry.npmjs.org/whatwg-url/-/whatwg-url-11.0.0.tgz", - "integrity": "sha512-RKT8HExMpoYx4igMiVMY83lN6UeITKJlBQ+vR/8ZJ8OCdSiN3RwCq+9gH0+Xzj0+5IrM6i4j/6LuvzbZIQgEcQ==", + "version": "14.2.0", + "resolved": "https://registry.npmjs.org/whatwg-url/-/whatwg-url-14.2.0.tgz", + "integrity": "sha512-De72GdQZzNTUBBChsXueQUnPKDkg/5A5zp7pFDuQAj5UFoENpiACU0wlCvzpAGnTkj++ihpKwKyYewn/XNUbKw==", "dev": true, "license": "MIT", "dependencies": { - "tr46": "^3.0.0", + "tr46": "^5.1.0", "webidl-conversions": "^7.0.0" }, "engines": { - "node": ">=12" + "node": ">=18" } }, "node_modules/data-view-buffer": { @@ -5499,9 +5842,9 @@ } }, "node_modules/decimal.js": { - "version": "10.5.0", - "resolved": "https://registry.npmjs.org/decimal.js/-/decimal.js-10.5.0.tgz", - "integrity": "sha512-8vDa8Qxvr/+d94hSh5P3IJwI5t8/c0KsMp+g8bNw9cY2icONa5aPfvKeieW1WlG0WQYwwhJ7mjui2xtiePQSXw==", + "version": "10.6.0", + "resolved": "https://registry.npmjs.org/decimal.js/-/decimal.js-10.6.0.tgz", + "integrity": "sha512-YpgQiITW3JXGntzdUmyUR1V812Hn8T1YVXhCu+wO3OpS4eU9l4YdD3qjyiKdV6mvV29zapkMeD390UVEf2lkUg==", "dev": true, "license": "MIT" }, @@ -5693,30 +6036,6 @@ "dev": true, "license": "MIT" }, - "node_modules/domexception": { - "version": "4.0.0", - "resolved": "https://registry.npmjs.org/domexception/-/domexception-4.0.0.tgz", - "integrity": "sha512-A2is4PLG+eeSfoTMA95/s4pvAoSo2mKtiM5jlHkAVewmiO8ISFTFKZjH7UAM1Atli/OT/7JHOrJRJiMKUZKYBw==", - "deprecated": "Use your platform's native DOMException instead", - "dev": true, - "license": "MIT", - "dependencies": { - "webidl-conversions": "^7.0.0" - }, - "engines": { - "node": ">=12" - } - }, - "node_modules/domexception/node_modules/webidl-conversions": { - "version": "7.0.0", - "resolved": "https://registry.npmjs.org/webidl-conversions/-/webidl-conversions-7.0.0.tgz", - "integrity": "sha512-VwddBukDzu71offAQR975unBIGqfKZpM+8ZX6ySk8nYhVoo5CYaZyzt3YBvYtRtO+aoGlqxPg/B87NGVZ/fu6g==", - "dev": true, - "license": "BSD-2-Clause", - "engines": { - "node": ">=12" - } - }, "node_modules/dunder-proto": { "version": "1.0.1", "resolved": "https://registry.npmjs.org/dunder-proto/-/dunder-proto-1.0.1.tgz", @@ -5796,9 +6115,9 @@ } }, "node_modules/entities": { - "version": "6.0.0", - "resolved": "https://registry.npmjs.org/entities/-/entities-6.0.0.tgz", - "integrity": "sha512-aKstq2TDOndCn4diEyp9Uq/Flu2i1GlLkc6XIDQSDMuaFE3OPW5OphLCyQ5SpSJZTb4reN+kTcYru5yIfXoRPw==", + "version": "6.0.1", + "resolved": "https://registry.npmjs.org/entities/-/entities-6.0.1.tgz", + "integrity": "sha512-aN97NXWF6AWBTahfVOIrB/NShkzi5H7F9r1s9mD3cDj4Ko5f2qhhVoYMibXF7GlLveb/D2ioWay8lxI97Ven3g==", "dev": true, "license": "BSD-2-Clause", "engines": { @@ -6025,28 +6344,6 @@ "url": "https://github.com/sponsors/sindresorhus" } }, - "node_modules/escodegen": { - "version": "2.1.0", - "resolved": "https://registry.npmjs.org/escodegen/-/escodegen-2.1.0.tgz", - "integrity": "sha512-2NlIDTwUWJN0mRPQOdtQBzbUHvdGY2P1VXSyU83Q3xKxM7WHX2Ql8dKq782Q9TgQUNOLEzEYu9bzLNj1q88I5w==", - "dev": true, - "license": "BSD-2-Clause", - "dependencies": { - "esprima": "^4.0.1", - "estraverse": "^5.2.0", - "esutils": "^2.0.2" - }, - "bin": { - "escodegen": "bin/escodegen.js", - "esgenerate": "bin/esgenerate.js" - }, - "engines": { - "node": ">=6.0" - }, - "optionalDependencies": { - "source-map": "~0.6.1" - } - }, "node_modules/eslint": { "version": "9.26.0", "resolved": "https://registry.npmjs.org/eslint/-/eslint-9.26.0.tgz", @@ -7410,16 +7707,16 @@ } }, "node_modules/html-encoding-sniffer": { - "version": "3.0.0", - "resolved": "https://registry.npmjs.org/html-encoding-sniffer/-/html-encoding-sniffer-3.0.0.tgz", - "integrity": "sha512-oWv4T4yJ52iKrufjnyZPkrN0CH3QnrUqdB6In1g5Fe1mia8GmF36gnfNySxoZtxD5+NmYw1EElVXiBk93UeskA==", + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/html-encoding-sniffer/-/html-encoding-sniffer-4.0.0.tgz", + "integrity": "sha512-Y22oTqIU4uuPgEemfz7NDJz6OeKf12Lsu+QC+s3BVpda64lTiMYCyGwg5ki4vFxkMwQdeZDl2adZoqUgdFuTgQ==", "dev": true, "license": "MIT", "dependencies": { - "whatwg-encoding": "^2.0.0" + "whatwg-encoding": "^3.1.1" }, "engines": { - "node": ">=12" + "node": ">=18" } }, "node_modules/html-escaper": { @@ -7467,32 +7764,31 @@ } }, "node_modules/http-proxy-agent": { - "version": "5.0.0", - "resolved": "https://registry.npmjs.org/http-proxy-agent/-/http-proxy-agent-5.0.0.tgz", - "integrity": "sha512-n2hY8YdoRE1i7r6M0w9DIw5GgZN0G25P8zLCRQ8rjXtTU3vsNFBI/vWK/UIeE6g5MUUz6avwAPXmL6Fy9D/90w==", + "version": "7.0.2", + "resolved": "https://registry.npmjs.org/http-proxy-agent/-/http-proxy-agent-7.0.2.tgz", + "integrity": "sha512-T1gkAiYYDWYx3V5Bmyu7HcfcvL7mUrTWiM6yOfa3PIphViJ/gFPbvidQ+veqSOHci/PxBcDabeUNCzpOODJZig==", "dev": true, "license": "MIT", "dependencies": { - "@tootallnate/once": "2", - "agent-base": "6", - "debug": "4" + "agent-base": "^7.1.0", + "debug": "^4.3.4" }, "engines": { - "node": ">= 6" + "node": ">= 14" } }, "node_modules/https-proxy-agent": { - "version": "5.0.1", - "resolved": "https://registry.npmjs.org/https-proxy-agent/-/https-proxy-agent-5.0.1.tgz", - "integrity": "sha512-dFcAjpTQFgoLMzC2VwU+C/CbS7uRL0lWmxDITmqm7C+7F0Odmj6s9l6alZc6AELXhrnggM2CeWSXHGOdX2YtwA==", + "version": "7.0.6", + "resolved": "https://registry.npmjs.org/https-proxy-agent/-/https-proxy-agent-7.0.6.tgz", + "integrity": "sha512-vK9P5/iUfdl95AI+JVyUuIcVtd4ofvtrOr3HNtM2yxC9bnMbEdp3x01OhQNnjb8IJYi38VlTE3mBXwcfvywuSw==", "dev": true, "license": "MIT", "dependencies": { - "agent-base": "6", + "agent-base": "^7.1.2", "debug": "4" }, "engines": { - "node": ">= 6" + "node": ">= 14" } }, "node_modules/human-signals": { @@ -8586,26 +8882,23 @@ "license": "MIT" }, "node_modules/jest-environment-jsdom": { - "version": "29.7.0", - "resolved": "https://registry.npmjs.org/jest-environment-jsdom/-/jest-environment-jsdom-29.7.0.tgz", - "integrity": "sha512-k9iQbsf9OyOfdzWH8HDmrRT0gSIcX+FLNW7IQq94tFX0gynPwqDTW0Ho6iMVNjGz/nb+l/vW3dWM2bbLLpkbXA==", + "version": "30.1.2", + "resolved": "https://registry.npmjs.org/jest-environment-jsdom/-/jest-environment-jsdom-30.1.2.tgz", + "integrity": "sha512-LXsfAh5+mDTuXDONGl1ZLYxtJEaS06GOoxJb2arcJTjIfh1adYg8zLD8f6P0df8VmjvCaMrLmc1PgHUI/YUTbg==", "dev": true, "license": "MIT", "dependencies": { - "@jest/environment": "^29.7.0", - "@jest/fake-timers": "^29.7.0", - "@jest/types": "^29.6.3", - "@types/jsdom": "^20.0.0", + "@jest/environment": "30.1.2", + "@jest/environment-jsdom-abstract": "30.1.2", + "@types/jsdom": "^21.1.7", "@types/node": "*", - "jest-mock": "^29.7.0", - "jest-util": "^29.7.0", - "jsdom": "^20.0.0" + "jsdom": "^26.1.0" }, "engines": { - "node": "^14.15.0 || ^16.10.0 || >=18.0.0" + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" }, "peerDependencies": { - "canvas": "^2.5.0" + "canvas": "^3.0.0" }, "peerDependenciesMeta": { "canvas": { @@ -8613,6 +8906,207 @@ } } }, + "node_modules/jest-environment-jsdom/node_modules/@jest/environment": { + "version": "30.1.2", + "resolved": "https://registry.npmjs.org/@jest/environment/-/environment-30.1.2.tgz", + "integrity": "sha512-N8t1Ytw4/mr9uN28OnVf0SYE2dGhaIxOVYcwsf9IInBKjvofAjbFRvedvBBlyTYk2knbJTiEjEJ2PyyDIBnd9w==", + "dev": true, + "license": "MIT", + "dependencies": { + "@jest/fake-timers": "30.1.2", + "@jest/types": "30.0.5", + "@types/node": "*", + "jest-mock": "30.0.5" + }, + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + } + }, + "node_modules/jest-environment-jsdom/node_modules/@jest/fake-timers": { + "version": "30.1.2", + "resolved": "https://registry.npmjs.org/@jest/fake-timers/-/fake-timers-30.1.2.tgz", + "integrity": "sha512-Beljfv9AYkr9K+ETX9tvV61rJTY706BhBUtiaepQHeEGfe0DbpvUA5Z3fomwc5Xkhns6NWrcFDZn+72fLieUnA==", + "dev": true, + "license": "MIT", + "dependencies": { + "@jest/types": "30.0.5", + "@sinonjs/fake-timers": "^13.0.0", + "@types/node": "*", + "jest-message-util": "30.1.0", + "jest-mock": "30.0.5", + "jest-util": "30.0.5" + }, + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + } + }, + "node_modules/jest-environment-jsdom/node_modules/@jest/schemas": { + "version": "30.0.5", + "resolved": "https://registry.npmjs.org/@jest/schemas/-/schemas-30.0.5.tgz", + "integrity": "sha512-DmdYgtezMkh3cpU8/1uyXakv3tJRcmcXxBOcO0tbaozPwpmh4YMsnWrQm9ZmZMfa5ocbxzbFk6O4bDPEc/iAnA==", + "dev": true, + "license": "MIT", + "dependencies": { + "@sinclair/typebox": "^0.34.0" + }, + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + } + }, + "node_modules/jest-environment-jsdom/node_modules/@jest/types": { + "version": "30.0.5", + "resolved": "https://registry.npmjs.org/@jest/types/-/types-30.0.5.tgz", + "integrity": "sha512-aREYa3aku9SSnea4aX6bhKn4bgv3AXkgijoQgbYV3yvbiGt6z+MQ85+6mIhx9DsKW2BuB/cLR/A+tcMThx+KLQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "@jest/pattern": "30.0.1", + "@jest/schemas": "30.0.5", + "@types/istanbul-lib-coverage": "^2.0.6", + "@types/istanbul-reports": "^3.0.4", + "@types/node": "*", + "@types/yargs": "^17.0.33", + "chalk": "^4.1.2" + }, + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + } + }, + "node_modules/jest-environment-jsdom/node_modules/@sinclair/typebox": { + "version": "0.34.41", + "resolved": "https://registry.npmjs.org/@sinclair/typebox/-/typebox-0.34.41.tgz", + "integrity": "sha512-6gS8pZzSXdyRHTIqoqSVknxolr1kzfy4/CeDnrzsVz8TTIWUbOBr6gnzOmTYJ3eXQNh4IYHIGi5aIL7sOZ2G/g==", + "dev": true, + "license": "MIT" + }, + "node_modules/jest-environment-jsdom/node_modules/@sinonjs/fake-timers": { + "version": "13.0.5", + "resolved": "https://registry.npmjs.org/@sinonjs/fake-timers/-/fake-timers-13.0.5.tgz", + "integrity": "sha512-36/hTbH2uaWuGVERyC6da9YwGWnzUZXuPro/F2LfsdOsLnCojz/iSH8MxUt/FD2S5XBSVPhmArFUXcpCQ2Hkiw==", + "dev": true, + "license": "BSD-3-Clause", + "dependencies": { + "@sinonjs/commons": "^3.0.1" + } + }, + "node_modules/jest-environment-jsdom/node_modules/ansi-styles": { + "version": "5.2.0", + "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-5.2.0.tgz", + "integrity": "sha512-Cxwpt2SfTzTtXcfOlzGEee8O+c+MmUgGrNiBcXnuWxuFJHe6a5Hz7qwhwe5OgaSYI0IJvkLqWX1ASG+cJOkEiA==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=10" + }, + "funding": { + "url": "https://github.com/chalk/ansi-styles?sponsor=1" + } + }, + "node_modules/jest-environment-jsdom/node_modules/ci-info": { + "version": "4.3.0", + "resolved": "https://registry.npmjs.org/ci-info/-/ci-info-4.3.0.tgz", + "integrity": "sha512-l+2bNRMiQgcfILUi33labAZYIWlH1kWDp+ecNo5iisRKrbm0xcRyCww71/YU0Fkw0mAFpz9bJayXPjey6vkmaQ==", + "dev": true, + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/sibiraj-s" + } + ], + "license": "MIT", + "engines": { + "node": ">=8" + } + }, + "node_modules/jest-environment-jsdom/node_modules/jest-message-util": { + "version": "30.1.0", + "resolved": "https://registry.npmjs.org/jest-message-util/-/jest-message-util-30.1.0.tgz", + "integrity": "sha512-HizKDGG98cYkWmaLUHChq4iN+oCENohQLb7Z5guBPumYs+/etonmNFlg1Ps6yN9LTPyZn+M+b/9BbnHx3WTMDg==", + "dev": true, + "license": "MIT", + "dependencies": { + "@babel/code-frame": "^7.27.1", + "@jest/types": "30.0.5", + "@types/stack-utils": "^2.0.3", + "chalk": "^4.1.2", + "graceful-fs": "^4.2.11", + "micromatch": "^4.0.8", + "pretty-format": "30.0.5", + "slash": "^3.0.0", + "stack-utils": "^2.0.6" + }, + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + } + }, + "node_modules/jest-environment-jsdom/node_modules/jest-mock": { + "version": "30.0.5", + "resolved": "https://registry.npmjs.org/jest-mock/-/jest-mock-30.0.5.tgz", + "integrity": "sha512-Od7TyasAAQX/6S+QCbN6vZoWOMwlTtzzGuxJku1GhGanAjz9y+QsQkpScDmETvdc9aSXyJ/Op4rhpMYBWW91wQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "@jest/types": "30.0.5", + "@types/node": "*", + "jest-util": "30.0.5" + }, + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + } + }, + "node_modules/jest-environment-jsdom/node_modules/jest-util": { + "version": "30.0.5", + "resolved": "https://registry.npmjs.org/jest-util/-/jest-util-30.0.5.tgz", + "integrity": "sha512-pvyPWssDZR0FlfMxCBoc0tvM8iUEskaRFALUtGQYzVEAqisAztmy+R8LnU14KT4XA0H/a5HMVTXat1jLne010g==", + "dev": true, + "license": "MIT", + "dependencies": { + "@jest/types": "30.0.5", + "@types/node": "*", + "chalk": "^4.1.2", + "ci-info": "^4.2.0", + "graceful-fs": "^4.2.11", + "picomatch": "^4.0.2" + }, + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + } + }, + "node_modules/jest-environment-jsdom/node_modules/picomatch": { + "version": "4.0.3", + "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.3.tgz", + "integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=12" + }, + "funding": { + "url": "https://github.com/sponsors/jonschlinkert" + } + }, + "node_modules/jest-environment-jsdom/node_modules/pretty-format": { + "version": "30.0.5", + "resolved": "https://registry.npmjs.org/pretty-format/-/pretty-format-30.0.5.tgz", + "integrity": "sha512-D1tKtYvByrBkFLe2wHJl2bwMJIiT8rW+XA+TiataH79/FszLQMrpGEvzUVkzPau7OCO0Qnrhpe87PqtOAIB8Yw==", + "dev": true, + "license": "MIT", + "dependencies": { + "@jest/schemas": "30.0.5", + "ansi-styles": "^5.2.0", + "react-is": "^18.3.1" + }, + "engines": { + "node": "^18.14.0 || ^20.0.0 || ^22.0.0 || >=24.0.0" + } + }, + "node_modules/jest-environment-jsdom/node_modules/react-is": { + "version": "18.3.1", + "resolved": "https://registry.npmjs.org/react-is/-/react-is-18.3.1.tgz", + "integrity": "sha512-/LLMVyas0ljjAtoYiPqYiL8VWXzUUdThrmU5+n20DZv+a+ClRoevUzw5JxU+Ieh5/c87ytoTBV9G1FiKfNJdmg==", + "dev": true, + "license": "MIT" + }, "node_modules/jest-environment-node": { "version": "29.7.0", "resolved": "https://registry.npmjs.org/jest-environment-node/-/jest-environment-node-29.7.0.tgz", @@ -9221,44 +9715,38 @@ } }, "node_modules/jsdom": { - "version": "20.0.3", - "resolved": "https://registry.npmjs.org/jsdom/-/jsdom-20.0.3.tgz", - "integrity": "sha512-SYhBvTh89tTfCD/CRdSOm13mOBa42iTaTyfyEWBdKcGdPxPtLFBXuHR8XHb33YNYaP+lLbmSvBTsnoesCNJEsQ==", + "version": "26.1.0", + "resolved": "https://registry.npmjs.org/jsdom/-/jsdom-26.1.0.tgz", + "integrity": "sha512-Cvc9WUhxSMEo4McES3P7oK3QaXldCfNWp7pl2NNeiIFlCoLr3kfq9kb1fxftiwk1FLV7CvpvDfonxtzUDeSOPg==", "dev": true, "license": "MIT", "dependencies": { - "abab": "^2.0.6", - "acorn": "^8.8.1", - "acorn-globals": "^7.0.0", - "cssom": "^0.5.0", - "cssstyle": "^2.3.0", - "data-urls": "^3.0.2", - "decimal.js": "^10.4.2", - "domexception": "^4.0.0", - "escodegen": "^2.0.0", - "form-data": "^4.0.0", - "html-encoding-sniffer": "^3.0.0", - "http-proxy-agent": "^5.0.0", - "https-proxy-agent": "^5.0.1", + "cssstyle": "^4.2.1", + "data-urls": "^5.0.0", + "decimal.js": "^10.5.0", + "html-encoding-sniffer": "^4.0.0", + "http-proxy-agent": "^7.0.2", + "https-proxy-agent": "^7.0.6", "is-potential-custom-element-name": "^1.0.1", - "nwsapi": "^2.2.2", - "parse5": "^7.1.1", + "nwsapi": "^2.2.16", + "parse5": "^7.2.1", + "rrweb-cssom": "^0.8.0", "saxes": "^6.0.0", "symbol-tree": "^3.2.4", - "tough-cookie": "^4.1.2", - "w3c-xmlserializer": "^4.0.0", + "tough-cookie": "^5.1.1", + "w3c-xmlserializer": "^5.0.0", "webidl-conversions": "^7.0.0", - "whatwg-encoding": "^2.0.0", - "whatwg-mimetype": "^3.0.0", - "whatwg-url": "^11.0.0", - "ws": "^8.11.0", - "xml-name-validator": "^4.0.0" + "whatwg-encoding": "^3.1.1", + "whatwg-mimetype": "^4.0.0", + "whatwg-url": "^14.1.1", + "ws": "^8.18.0", + "xml-name-validator": "^5.0.0" }, "engines": { - "node": ">=14" + "node": ">=18" }, "peerDependencies": { - "canvas": "^2.5.0" + "canvas": "^3.0.0" }, "peerDependenciesMeta": { "canvas": { @@ -9267,16 +9755,16 @@ } }, "node_modules/jsdom/node_modules/tr46": { - "version": "3.0.0", - "resolved": "https://registry.npmjs.org/tr46/-/tr46-3.0.0.tgz", - "integrity": "sha512-l7FvfAHlcmulp8kr+flpQZmVwtu7nfRV7NZujtN0OqES8EL4O4e0qqzL0DC5gAvx/ZC/9lk6rhcUwYvkBnBnYA==", + "version": "5.1.1", + "resolved": "https://registry.npmjs.org/tr46/-/tr46-5.1.1.tgz", + "integrity": "sha512-hdF5ZgjTqgAntKkklYw0R03MG2x/bSzTtkxmIRw/sTNV8YXsCJ1tfLAX23lhxhHJlEf3CRCOCGGWw3vI3GaSPw==", "dev": true, "license": "MIT", "dependencies": { - "punycode": "^2.1.1" + "punycode": "^2.3.1" }, "engines": { - "node": ">=12" + "node": ">=18" } }, "node_modules/jsdom/node_modules/webidl-conversions": { @@ -9290,17 +9778,17 @@ } }, "node_modules/jsdom/node_modules/whatwg-url": { - "version": "11.0.0", - "resolved": "https://registry.npmjs.org/whatwg-url/-/whatwg-url-11.0.0.tgz", - "integrity": "sha512-RKT8HExMpoYx4igMiVMY83lN6UeITKJlBQ+vR/8ZJ8OCdSiN3RwCq+9gH0+Xzj0+5IrM6i4j/6LuvzbZIQgEcQ==", + "version": "14.2.0", + "resolved": "https://registry.npmjs.org/whatwg-url/-/whatwg-url-14.2.0.tgz", + "integrity": "sha512-De72GdQZzNTUBBChsXueQUnPKDkg/5A5zp7pFDuQAj5UFoENpiACU0wlCvzpAGnTkj++ihpKwKyYewn/XNUbKw==", "dev": true, "license": "MIT", "dependencies": { - "tr46": "^3.0.0", + "tr46": "^5.1.0", "webidl-conversions": "^7.0.0" }, "engines": { - "node": ">=12" + "node": ">=18" } }, "node_modules/jsesc": { @@ -11133,9 +11621,9 @@ } }, "node_modules/nwsapi": { - "version": "2.2.20", - "resolved": "https://registry.npmjs.org/nwsapi/-/nwsapi-2.2.20.tgz", - "integrity": "sha512-/ieB+mDe4MrrKMT8z+mQL8klXydZWGR5Dowt4RAGKbJ3kIGEx3X4ljUo+6V73IXtUPWgfOlU5B9MlGxFO5T+cA==", + "version": "2.2.22", + "resolved": "https://registry.npmjs.org/nwsapi/-/nwsapi-2.2.22.tgz", + "integrity": "sha512-ujSMe1OWVn55euT1ihwCI1ZcAaAU3nxUiDwfDQldc51ZXaB9m2AyOn6/jh1BLe2t/G8xd6uKG1UBF2aZJeg2SQ==", "dev": true, "license": "MIT" }, @@ -11873,19 +12361,6 @@ "node": ">= 0.10" } }, - "node_modules/psl": { - "version": "1.15.0", - "resolved": "https://registry.npmjs.org/psl/-/psl-1.15.0.tgz", - "integrity": "sha512-JZd3gMVBAVQkSs6HdNZo9Sdo0LNcQeMNP3CozBJb3JYC/QUYZTnKxP+f8oWRX4rHP5EurWxqAHTSwUCjlNKa1w==", - "dev": true, - "license": "MIT", - "dependencies": { - "punycode": "^2.3.1" - }, - "funding": { - "url": "https://github.com/sponsors/lupomontero" - } - }, "node_modules/punycode": { "version": "2.3.1", "resolved": "https://registry.npmjs.org/punycode/-/punycode-2.3.1.tgz", @@ -11929,13 +12404,6 @@ "url": "https://github.com/sponsors/ljharb" } }, - "node_modules/querystringify": { - "version": "2.2.0", - "resolved": "https://registry.npmjs.org/querystringify/-/querystringify-2.2.0.tgz", - "integrity": "sha512-FIqgj2EUvTa7R50u0rGsyTftzjYmv/a3hO345bZNrqabNqjtgiDMgmo4mkUjd+nzU5oF3dClKqFIPUKybUyqoQ==", - "dev": true, - "license": "MIT" - }, "node_modules/queue-microtask": { "version": "1.2.3", "resolved": "https://registry.npmjs.org/queue-microtask/-/queue-microtask-1.2.3.tgz", @@ -12287,13 +12755,6 @@ "node": ">=0.10.0" } }, - "node_modules/requires-port": { - "version": "1.0.0", - "resolved": "https://registry.npmjs.org/requires-port/-/requires-port-1.0.0.tgz", - "integrity": "sha512-KigOCHcocU3XODJxsu8i/j8T9tzT4adHiecwORRQ0ZZFcp7ahwXuRU1m+yuO90C5ZUyGeGfocHDI14M3L3yDAQ==", - "dev": true, - "license": "MIT" - }, "node_modules/resolve": { "version": "1.22.10", "resolved": "https://registry.npmjs.org/resolve/-/resolve-1.22.10.tgz", @@ -12396,6 +12857,13 @@ "node": ">= 18" } }, + "node_modules/rrweb-cssom": { + "version": "0.8.0", + "resolved": "https://registry.npmjs.org/rrweb-cssom/-/rrweb-cssom-0.8.0.tgz", + "integrity": "sha512-guoltQEx+9aMf2gDZ0s62EcV8lsXR+0w8915TC3ITdn2YueuNjdAYh/levpU9nFaoChh9RUS5ZdQMrKfVEN9tw==", + "dev": true, + "license": "MIT" + }, "node_modules/run-parallel": { "version": "1.2.0", "resolved": "https://registry.npmjs.org/run-parallel/-/run-parallel-1.2.0.tgz", @@ -13336,6 +13804,26 @@ "url": "https://github.com/sponsors/jonschlinkert" } }, + "node_modules/tldts": { + "version": "6.1.86", + "resolved": "https://registry.npmjs.org/tldts/-/tldts-6.1.86.tgz", + "integrity": "sha512-WMi/OQ2axVTf/ykqCQgXiIct+mSQDFdH2fkwhPwgEwvJ1kSzZRiinb0zF2Xb8u4+OqPChmyI6MEu4EezNJz+FQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "tldts-core": "^6.1.86" + }, + "bin": { + "tldts": "bin/cli.js" + } + }, + "node_modules/tldts-core": { + "version": "6.1.86", + "resolved": "https://registry.npmjs.org/tldts-core/-/tldts-core-6.1.86.tgz", + "integrity": "sha512-Je6p7pkk+KMzMv2XXKmAE3McmolOQFdxkKw0R8EYNr7sELW46JqnNeTX8ybPiQgvg1ymCoF8LXs5fzFaZvJPTA==", + "dev": true, + "license": "MIT" + }, "node_modules/tmpl": { "version": "1.0.5", "resolved": "https://registry.npmjs.org/tmpl/-/tmpl-1.0.5.tgz", @@ -13367,19 +13855,16 @@ } }, "node_modules/tough-cookie": { - "version": "4.1.4", - "resolved": "https://registry.npmjs.org/tough-cookie/-/tough-cookie-4.1.4.tgz", - "integrity": "sha512-Loo5UUvLD9ScZ6jh8beX1T6sO1w2/MpCRpEP7V280GKMVUQ0Jzar2U3UJPsrdbziLEMMhu3Ujnq//rhiFuIeag==", + "version": "5.1.2", + "resolved": "https://registry.npmjs.org/tough-cookie/-/tough-cookie-5.1.2.tgz", + "integrity": "sha512-FVDYdxtnj0G6Qm/DhNPSb8Ju59ULcup3tuJxkFb5K8Bv2pUXILbf0xZWU8PX8Ov19OXljbUyveOFwRMwkXzO+A==", "dev": true, "license": "BSD-3-Clause", "dependencies": { - "psl": "^1.1.33", - "punycode": "^2.1.1", - "universalify": "^0.2.0", - "url-parse": "^1.5.3" + "tldts": "^6.1.32" }, "engines": { - "node": ">=6" + "node": ">=16" } }, "node_modules/tr46": { @@ -13749,16 +14234,6 @@ "url": "https://opencollective.com/unified" } }, - "node_modules/universalify": { - "version": "0.2.0", - "resolved": "https://registry.npmjs.org/universalify/-/universalify-0.2.0.tgz", - "integrity": "sha512-CJ1QgKmNg3CwvAv/kOFmtnEN05f0D/cn9QntgNOQlQF9dgvVTHj3t+8JPdjqawCHk7V/KA+fbUqzZ9XWhcqPUg==", - "dev": true, - "license": "MIT", - "engines": { - "node": ">= 4.0.0" - } - }, "node_modules/unpipe": { "version": "1.0.0", "resolved": "https://registry.npmjs.org/unpipe/-/unpipe-1.0.0.tgz", @@ -13843,17 +14318,6 @@ "punycode": "^2.1.0" } }, - "node_modules/url-parse": { - "version": "1.5.10", - "resolved": "https://registry.npmjs.org/url-parse/-/url-parse-1.5.10.tgz", - "integrity": "sha512-WypcfiRhfeUP9vvF0j6rw0J3hrWrw6iZv3+22h6iRMJ/8z1Tj6XfLP4DsUix5MhMPnXpiHDoKyoZ/bdCkwBCiQ==", - "dev": true, - "license": "MIT", - "dependencies": { - "querystringify": "^2.1.1", - "requires-port": "^1.0.0" - } - }, "node_modules/use-callback-ref": { "version": "1.3.3", "resolved": "https://registry.npmjs.org/use-callback-ref/-/use-callback-ref-1.3.3.tgz", @@ -13967,16 +14431,16 @@ } }, "node_modules/w3c-xmlserializer": { - "version": "4.0.0", - "resolved": "https://registry.npmjs.org/w3c-xmlserializer/-/w3c-xmlserializer-4.0.0.tgz", - "integrity": "sha512-d+BFHzbiCx6zGfz0HyQ6Rg69w9k19nviJspaj4yNscGjrHu94sVP+aRm75yEbCh+r2/yR+7q6hux9LVtbuTGBw==", + "version": "5.0.0", + "resolved": "https://registry.npmjs.org/w3c-xmlserializer/-/w3c-xmlserializer-5.0.0.tgz", + "integrity": "sha512-o8qghlI8NZHU1lLPrpi2+Uq7abh4GGPpYANlalzWxyWteJOCsr/P+oPBA49TOLu5FTZO4d3F9MnWJfiMo4BkmA==", "dev": true, "license": "MIT", "dependencies": { - "xml-name-validator": "^4.0.0" + "xml-name-validator": "^5.0.0" }, "engines": { - "node": ">=14" + "node": ">=18" } }, "node_modules/walker": { @@ -14005,26 +14469,26 @@ "license": "BSD-2-Clause" }, "node_modules/whatwg-encoding": { - "version": "2.0.0", - "resolved": "https://registry.npmjs.org/whatwg-encoding/-/whatwg-encoding-2.0.0.tgz", - "integrity": "sha512-p41ogyeMUrw3jWclHWTQg1k05DSVXPLcVxRTYsXUk+ZooOCZLcoYgPZ/HL/D/N+uQPOtcp1me1WhBEaX02mhWg==", + "version": "3.1.1", + "resolved": "https://registry.npmjs.org/whatwg-encoding/-/whatwg-encoding-3.1.1.tgz", + "integrity": "sha512-6qN4hJdMwfYBtE3YBTTHhoeuUrDBPZmbQaxWAqSALV/MeEnR5z1xd8UKud2RAkFoPkmB+hli1TZSnyi84xz1vQ==", "dev": true, "license": "MIT", "dependencies": { "iconv-lite": "0.6.3" }, "engines": { - "node": ">=12" + "node": ">=18" } }, "node_modules/whatwg-mimetype": { - "version": "3.0.0", - "resolved": "https://registry.npmjs.org/whatwg-mimetype/-/whatwg-mimetype-3.0.0.tgz", - "integrity": "sha512-nt+N2dzIutVRxARx1nghPKGv1xHikU7HKdfafKkLNLindmPU/ch3U31NOCGGA/dmPcmb1VlofO0vnKAcsm0o/Q==", + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/whatwg-mimetype/-/whatwg-mimetype-4.0.0.tgz", + "integrity": "sha512-QaKxh0eNIi2mE9p2vEdzfagOKHCcj1pJ56EEHGQOVxp8r9/iszLUUV7v89x9O1p/T+NlTM5W7jW6+cz4Fq1YVg==", "dev": true, "license": "MIT", "engines": { - "node": ">=12" + "node": ">=18" } }, "node_modules/whatwg-url": { @@ -14192,9 +14656,9 @@ } }, "node_modules/ws": { - "version": "8.18.2", - "resolved": "https://registry.npmjs.org/ws/-/ws-8.18.2.tgz", - "integrity": "sha512-DMricUmwGZUVr++AEAe2uiVM7UoO9MAVZMDu05UQOaUII0lp+zOzLLU4Xqh/JvTqklB1T4uELaaPBKyjE1r4fQ==", + "version": "8.18.3", + "resolved": "https://registry.npmjs.org/ws/-/ws-8.18.3.tgz", + "integrity": "sha512-PEIGCY5tSlUt50cqyMXfCzX+oOPqN0vuGqWzbcJ2xvnkzkq46oOpz7dQaTDBdfICb4N14+GARUDw2XV2N4tvzg==", "dev": true, "license": "MIT", "engines": { @@ -14214,13 +14678,13 @@ } }, "node_modules/xml-name-validator": { - "version": "4.0.0", - "resolved": "https://registry.npmjs.org/xml-name-validator/-/xml-name-validator-4.0.0.tgz", - "integrity": "sha512-ICP2e+jsHvAj2E2lIHxa5tjXRlKDJo4IdvPvCXbXQGdzSfmSpNVyIKMvoZHjDY9DP0zV17iI85o90vRFXNccRw==", + "version": "5.0.0", + "resolved": "https://registry.npmjs.org/xml-name-validator/-/xml-name-validator-5.0.0.tgz", + "integrity": "sha512-EvGK8EJ3DhaHfbRlETOWAS5pO9MZITeauHKJyb8wyajUfQUenkIg2MvLDTZ4T/TgIcm3HU0TFBgWWboAZ30UHg==", "dev": true, "license": "Apache-2.0", "engines": { - "node": ">=12" + "node": ">=18" } }, "node_modules/xmlchars": { diff --git a/llama_stack/ui/package.json b/llama_stack/ui/package.json index ac68dbc07..2ba81ea84 100644 --- a/llama_stack/ui/package.json +++ b/llama_stack/ui/package.json @@ -52,7 +52,7 @@ "eslint-config-prettier": "^10.1.8", "eslint-plugin-prettier": "^5.5.4", "jest": "^29.7.0", - "jest-environment-jsdom": "^29.7.0", + "jest-environment-jsdom": "^30.1.2", "prettier": "3.6.2", "tailwindcss": "^4", "ts-node": "^10.9.2", From e3fd70c321270d1a191eb79f3550a5df201538f2 Mon Sep 17 00:00:00 2001 From: Kai Wu Date: Mon, 22 Sep 2025 09:55:32 -0700 Subject: [PATCH 16/18] fix: change ModelRegistryHelper to use ProviderModelEntry instead of hardcoded ModelType.llm (#3451) # What does this PR do? change ModelRegistryHelper to use ProviderModelEntry instead of hardcoded ModelType.llm which fixed issue #3330. ## Test Plan 1. open llama-stack server ``` uv sync --python 3.12 source .venv/bin/activate uv run llama stack build --distro starter --image-type venv --run ``` 2.Used following script to test ``` from llama_stack_client import LlamaStackClient import os def test_openai_embedding_type(): client = LlamaStackClient( base_url=os.environ.get("LLAMA_STACK_ENDPOINT", "http://localhost:8321"), provider_data={ "openai_api_key": os.environ.get("OPENAI_API_KEY", ""), }, ) model = client.models.retrieve("openai/text-embedding-3-small") print(model) assert model.identifier == "openai/text-embedding-3-small" assert model.model_type == "embedding" test_openai_embedding_type() ``` logs: ``` python test_openai.py INFO:httpx:HTTP Request: GET http://localhost:8321/v1/models/openai/text-embedding-3-small "HTTP/1.1 200 OK" Model(identifier='openai/text-embedding-3-small', metadata={'embedding_dimension': 1536.0, 'context_length': 8192.0}, api_model_type='embedding', provider_id='openai', type='model', provider_resource_id='text-embedding-3-small', owner=None, source='listed_from_provider', model_type='embedding') ``` --- llama_stack/providers/utils/inference/model_registry.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/llama_stack/providers/utils/inference/model_registry.py b/llama_stack/providers/utils/inference/model_registry.py index 44add8f9e..b6b06c0b6 100644 --- a/llama_stack/providers/utils/inference/model_registry.py +++ b/llama_stack/providers/utils/inference/model_registry.py @@ -103,7 +103,7 @@ class ModelRegistryHelper(ModelsProtocolPrivate): Model( identifier=id, provider_resource_id=entry.provider_model_id, - model_type=ModelType.llm, + model_type=entry.model_type, metadata=entry.metadata, provider_id=self.__provider_id__, ) From 8d8261961e7e0615a207010bf52a7980b7abb3e3 Mon Sep 17 00:00:00 2001 From: slekkala1 Date: Mon, 22 Sep 2025 10:19:36 -0700 Subject: [PATCH 17/18] chore: Refactor fireworks to use OpenAIMixin (#3480) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit # What does this PR do? Refactor Fireworks to use OpenAIMixin Closes https://github.com/llamastack/llama-stack/issues/3391 Related to https://github.com/llamastack/llama-stack/issues/3387 ## Test Plan ``` (llama-stack) (base) swapna942@swapna942-mac llama-stack % FIREWORKS_API_KEY=**** ./scripts/integration-tests.sh --stack-config server:ci-tests --setup fireworks --subdirs inference --pattern openai tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_single_string[openai_client-emb=nomic-ai/nomic-embed-text-v1.5] instantiating llama_stack_client Port 8321 is already in use, assuming server is already running... llama_stack_client instantiated in 0.031s PASSED [ 2%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_multiple_strings[openai_client-emb=nomic-ai/nomic-embed-text-v1.5] PASSED [ 4%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_float[openai_client-emb=nomic-ai/nomic-embed-text-v1.5] PASSED [ 6%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_dimensions[openai_client-emb=nomic-ai/nomic-embed-text-v1.5] PASSED [ 8%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_user_parameter[openai_client-emb=nomic-ai/nomic-embed-text-v1.5] SKIPPED [ 10%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_empty_list_error[openai_client-emb=nomic-ai/nomic-embed-text-v1.5] PASSED [ 12%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_invalid_model_error[openai_client-emb=nomic-ai/nomic-embed-text-v1.5] PASSED [ 14%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_different_inputs_different_outputs[openai_client-emb=nomic-ai/nomic-embed-text-v1.5] PASSED [ 17%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_base64[openai_client-emb=nomic-ai/nomic-embed-text-v1.5] SKIPPED [ 19%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_base64_batch_processing[openai_client-emb=nomic-ai/nomic-embed-text-v1.5] SKIPPED [ 21%] tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming[txt=accounts/fireworks/models/llama-v3p1-8b-instruct-inference:completion:sanity] PASSED [ 23%] tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming_suffix[txt=accounts/fireworks/models/llama-v3p1-8b-instruct-inference:completion:suffix] SKIPPED [ 25%] tests/integration/inference/test_openai_completion.py::test_openai_completion_streaming[txt=accounts/fireworks/models/llama-v3p1-8b-instruct-inference:completion:sanity] PASSED [ 27%] tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=accounts/fireworks/models/llama-v3p1-8b-instruct-1] SKIPPED [ 29%] tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=accounts/fireworks/models/llama-v3p1-8b-instruct] SKIPPED [ 31%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-inference:chat_completion:non_streaming_01] PASSED [ 34%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-inference:chat_completion:streaming_01] PASSED [ 36%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-inference:chat_completion:streaming_01] PASSED [ 38%] tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-True] PASSED [ 40%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-True] PASSED [ 42%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming_with_file[txt=accounts/fireworks/models/llama-v3p1-8b-instruct] SKIPPED [ 44%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_single_string[llama_stack_client-emb=nomic-ai/nomic-embed-text-v1.5] PASSED [ 46%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_multiple_strings[llama_stack_client-emb=nomic-ai/nomic-embed-text-v1.5] PASSED [ 48%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_float[llama_stack_client-emb=nomic-ai/nomic-embed-text-v1.5] PASSED [ 51%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_dimensions[llama_stack_client-emb=nomic-ai/nomic-embed-text-v1.5] PASSED [ 53%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_user_parameter[llama_stack_client-emb=nomic-ai/nomic-embed-text-v1.5] SKIPPED [ 55%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_empty_list_error[llama_stack_client-emb=nomic-ai/nomic-embed-text-v1.5] PASSED [ 57%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_invalid_model_error[llama_stack_client-emb=nomic-ai/nomic-embed-text-v1.5] PASSED [ 59%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_different_inputs_different_outputs[llama_stack_client-emb=nomic-ai/nomic-embed-text-v1.5] PASSED [ 61%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_base64[llama_stack_client-emb=nomic-ai/nomic-embed-text-v1.5] SKIPPED [ 63%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_base64_batch_processing[llama_stack_client-emb=nomic-ai/nomic-embed-text-v1.5] SKIPPED [ 65%] tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=accounts/fireworks/models/llama-v3p1-8b-instruct-0] SKIPPED [ 68%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-inference:chat_completion:non_streaming_02] PASSED [ 70%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-inference:chat_completion:streaming_02] PASSED [ 72%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-inference:chat_completion:streaming_02] PASSED [ 74%] tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-False] PASSED [ 76%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-False] PASSED [ 78%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-inference:chat_completion:non_streaming_01] PASSED [ 80%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-inference:chat_completion:streaming_01] PASSED [ 82%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-inference:chat_completion:streaming_01] PASSED [ 85%] tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-True] PASSED [ 87%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-True] PASSED [ 89%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-inference:chat_completion:non_streaming_02] PASSED [ 91%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-inference:chat_completion:streaming_02] PASSED [ 93%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-inference:chat_completion:streaming_02] PASSED [ 95%] tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-False] PASSED [ 97%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-False] PASSED [100%] ========================================== slowest 10 durations ========================================== 30.01s teardown tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_multiple_strings[llama_stack_client-emb=nomic-ai/nomic-embed-text-v1.5] 30.01s teardown tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-False] 30.01s teardown tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_different_inputs_different_outputs[openai_client-emb=nomic-ai/nomic-embed-text-v1.5] 30.01s teardown tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_user_parameter[openai_client-emb=nomic-ai/nomic-embed-text-v1.5] 30.01s teardown tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-True] 30.01s teardown tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_different_inputs_different_outputs[llama_stack_client-emb=nomic-ai/nomic-embed-text-v1.5] 30.01s teardown tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=accounts/fireworks/models/llama-v3p1-8b-instruct-inference:chat_completion:non_streaming_02] 30.01s teardown tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_single_string[llama_stack_client-emb=nomic-ai/nomic-embed-text-v1.5] 30.01s teardown tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_base64_batch_processing[openai_client-emb=nomic-ai/nomic-embed-text-v1.5] 30.01s teardown tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_invalid_model_error[openai_client-emb=nomic-ai/nomic-embed-text-v1.5] ================= 36 passed, 11 skipped, 50 deselected, 4 warnings in 1429.05s (0:23:49) ================= + exit_code=0 + set +x ✅ All tests completed successfully ``` --- .../remote/inference/fireworks/fireworks.py | 178 ++---------------- .../inference/test_openai_embeddings.py | 3 +- tests/integration/suites.py | 9 + 3 files changed, 22 insertions(+), 168 deletions(-) diff --git a/llama_stack/providers/remote/inference/fireworks/fireworks.py b/llama_stack/providers/remote/inference/fireworks/fireworks.py index e907e8ec6..2fcf1be2e 100644 --- a/llama_stack/providers/remote/inference/fireworks/fireworks.py +++ b/llama_stack/providers/remote/inference/fireworks/fireworks.py @@ -4,11 +4,9 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from collections.abc import AsyncGenerator, AsyncIterator -from typing import Any +from collections.abc import AsyncGenerator from fireworks.client import Fireworks -from openai import AsyncOpenAI from llama_stack.apis.common.content_types import ( InterleavedContent, @@ -24,12 +22,6 @@ from llama_stack.apis.inference import ( Inference, LogProbConfig, Message, - OpenAIChatCompletion, - OpenAIChatCompletionChunk, - OpenAICompletion, - OpenAIEmbeddingsResponse, - OpenAIMessageParam, - OpenAIResponseFormatParam, ResponseFormat, ResponseFormatType, SamplingParams, @@ -45,15 +37,14 @@ from llama_stack.providers.utils.inference.model_registry import ( ModelRegistryHelper, ) from llama_stack.providers.utils.inference.openai_compat import ( - OpenAIChatCompletionToLlamaStackMixin, convert_message_to_openai_dict, get_sampling_options, - prepare_openai_completion_params, process_chat_completion_response, process_chat_completion_stream_response, process_completion_response, process_completion_stream_response, ) +from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin from llama_stack.providers.utils.inference.prompt_adapter import ( chat_completion_request_to_prompt, completion_request_to_prompt, @@ -68,7 +59,7 @@ from .models import MODEL_ENTRIES logger = get_logger(name=__name__, category="inference::fireworks") -class FireworksInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProviderData): +class FireworksInferenceAdapter(OpenAIMixin, ModelRegistryHelper, Inference, NeedsRequestProviderData): def __init__(self, config: FireworksImplConfig) -> None: ModelRegistryHelper.__init__(self, MODEL_ENTRIES, config.allowed_models) self.config = config @@ -79,7 +70,7 @@ class FireworksInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProv async def shutdown(self) -> None: pass - def _get_api_key(self) -> str: + def get_api_key(self) -> str: config_api_key = self.config.api_key.get_secret_value() if self.config.api_key else None if config_api_key: return config_api_key @@ -91,15 +82,18 @@ class FireworksInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProv ) return provider_data.fireworks_api_key - def _get_base_url(self) -> str: + def get_base_url(self) -> str: return "https://api.fireworks.ai/inference/v1" def _get_client(self) -> Fireworks: - fireworks_api_key = self._get_api_key() + fireworks_api_key = self.get_api_key() return Fireworks(api_key=fireworks_api_key) - def _get_openai_client(self) -> AsyncOpenAI: - return AsyncOpenAI(base_url=self._get_base_url(), api_key=self._get_api_key()) + def _preprocess_prompt_for_fireworks(self, prompt: str) -> str: + """Remove BOS token as Fireworks automatically prepends it""" + if prompt.startswith("<|begin_of_text|>"): + return prompt[len("<|begin_of_text|>") :] + return prompt async def completion( self, @@ -285,153 +279,3 @@ class FireworksInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProv embeddings = [data.embedding for data in response.data] return EmbeddingsResponse(embeddings=embeddings) - - async def openai_embeddings( - self, - model: str, - input: str | list[str], - encoding_format: str | None = "float", - dimensions: int | None = None, - user: str | None = None, - ) -> OpenAIEmbeddingsResponse: - raise NotImplementedError() - - async def openai_completion( - self, - model: str, - prompt: str | list[str] | list[int] | list[list[int]], - best_of: int | None = None, - echo: bool | None = None, - frequency_penalty: float | None = None, - logit_bias: dict[str, float] | None = None, - logprobs: bool | None = None, - max_tokens: int | None = None, - n: int | None = None, - presence_penalty: float | None = None, - seed: int | None = None, - stop: str | list[str] | None = None, - stream: bool | None = None, - stream_options: dict[str, Any] | None = None, - temperature: float | None = None, - top_p: float | None = None, - user: str | None = None, - guided_choice: list[str] | None = None, - prompt_logprobs: int | None = None, - suffix: str | None = None, - ) -> OpenAICompletion: - model_obj = await self.model_store.get_model(model) - - # Fireworks always prepends with BOS - if isinstance(prompt, str) and prompt.startswith("<|begin_of_text|>"): - prompt = prompt[len("<|begin_of_text|>") :] - - params = await prepare_openai_completion_params( - model=model_obj.provider_resource_id, - prompt=prompt, - best_of=best_of, - echo=echo, - frequency_penalty=frequency_penalty, - logit_bias=logit_bias, - logprobs=logprobs, - max_tokens=max_tokens, - n=n, - presence_penalty=presence_penalty, - seed=seed, - stop=stop, - stream=stream, - stream_options=stream_options, - temperature=temperature, - top_p=top_p, - user=user, - ) - - return await self._get_openai_client().completions.create(**params) - - async def openai_chat_completion( - self, - model: str, - messages: list[OpenAIMessageParam], - frequency_penalty: float | None = None, - function_call: str | dict[str, Any] | None = None, - functions: list[dict[str, Any]] | None = None, - logit_bias: dict[str, float] | None = None, - logprobs: bool | None = None, - max_completion_tokens: int | None = None, - max_tokens: int | None = None, - n: int | None = None, - parallel_tool_calls: bool | None = None, - presence_penalty: float | None = None, - response_format: OpenAIResponseFormatParam | None = None, - seed: int | None = None, - stop: str | list[str] | None = None, - stream: bool | None = None, - stream_options: dict[str, Any] | None = None, - temperature: float | None = None, - tool_choice: str | dict[str, Any] | None = None, - tools: list[dict[str, Any]] | None = None, - top_logprobs: int | None = None, - top_p: float | None = None, - user: str | None = None, - ) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]: - model_obj = await self.model_store.get_model(model) - - # Divert Llama Models through Llama Stack inference APIs because - # Fireworks chat completions OpenAI-compatible API does not support - # tool calls properly. - llama_model = self.get_llama_model(model_obj.provider_resource_id) - - if llama_model: - return await OpenAIChatCompletionToLlamaStackMixin.openai_chat_completion( - self, - model=model, - messages=messages, - frequency_penalty=frequency_penalty, - function_call=function_call, - functions=functions, - logit_bias=logit_bias, - logprobs=logprobs, - max_completion_tokens=max_completion_tokens, - max_tokens=max_tokens, - n=n, - parallel_tool_calls=parallel_tool_calls, - presence_penalty=presence_penalty, - response_format=response_format, - seed=seed, - stop=stop, - stream=stream, - stream_options=stream_options, - temperature=temperature, - tool_choice=tool_choice, - tools=tools, - top_logprobs=top_logprobs, - top_p=top_p, - user=user, - ) - - params = await prepare_openai_completion_params( - messages=messages, - frequency_penalty=frequency_penalty, - function_call=function_call, - functions=functions, - logit_bias=logit_bias, - logprobs=logprobs, - max_completion_tokens=max_completion_tokens, - max_tokens=max_tokens, - n=n, - parallel_tool_calls=parallel_tool_calls, - presence_penalty=presence_penalty, - response_format=response_format, - seed=seed, - stop=stop, - stream=stream, - stream_options=stream_options, - temperature=temperature, - tool_choice=tool_choice, - tools=tools, - top_logprobs=top_logprobs, - top_p=top_p, - user=user, - ) - - logger.debug(f"fireworks params: {params}") - return await self._get_openai_client().chat.completions.create(model=model_obj.provider_resource_id, **params) diff --git a/tests/integration/inference/test_openai_embeddings.py b/tests/integration/inference/test_openai_embeddings.py index 622b97287..ce3d2a8ea 100644 --- a/tests/integration/inference/test_openai_embeddings.py +++ b/tests/integration/inference/test_openai_embeddings.py @@ -33,6 +33,7 @@ def skip_if_model_doesnt_support_user_param(client, model_id): provider = provider_from_model(client, model_id) if provider.provider_type in ( "remote::together", # service returns 400 + "remote::fireworks", # service returns 400 malformed input ): pytest.skip(f"Model {model_id} hosted by {provider.provider_type} does not support user param.") @@ -41,6 +42,7 @@ def skip_if_model_doesnt_support_encoding_format_base64(client, model_id): provider = provider_from_model(client, model_id) if provider.provider_type in ( "remote::together", # param silently ignored, always returns floats + "remote::fireworks", # param silently ignored, always returns list of floats ): pytest.skip(f"Model {model_id} hosted by {provider.provider_type} does not support encoding_format='base64'.") @@ -287,7 +289,6 @@ def test_openai_embeddings_base64_batch_processing(compat_client, client_with_mo input=input_texts, encoding_format="base64", ) - # Validate response structure assert response.object == "list" assert response.model == embedding_model_id diff --git a/tests/integration/suites.py b/tests/integration/suites.py index 231480447..fb2c44308 100644 --- a/tests/integration/suites.py +++ b/tests/integration/suites.py @@ -108,6 +108,15 @@ SETUP_DEFINITIONS: dict[str, Setup] = { "embedding_model": "together/togethercomputer/m2-bert-80M-32k-retrieval", }, ), + "fireworks": Setup( + name="fireworks", + description="Fireworks provider with a text model", + defaults={ + "text_model": "accounts/fireworks/models/llama-v3p1-8b-instruct", + "vision_model": "accounts/fireworks/models/llama-v3p2-90b-vision-instruct", + "embedding_model": "nomic-ai/nomic-embed-text-v1.5", + }, + ), } From a7f9ce9a3a9e6d80c428ebf995462cb6e57d36bc Mon Sep 17 00:00:00 2001 From: ehhuang Date: Mon, 22 Sep 2025 22:53:48 -0700 Subject: [PATCH 18/18] chore: fix build (#3522) # What does this PR do? error: https://github.com/llamastack/llama-stack-ops/actions/runs/17932015232/job/50990948479 ## Test Plan GITHUB_ACTIONS=true BUILD_PLATFORM=linux/amd64 USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run --with llama-stack llama stack build --distro starter --image-type container --image-name ehhuang/distribution-starter succeeds --- llama_stack/core/build_container.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/llama_stack/core/build_container.sh b/llama_stack/core/build_container.sh index 424b40a9d..8e47fc592 100755 --- a/llama_stack/core/build_container.sh +++ b/llama_stack/core/build_container.sh @@ -147,7 +147,7 @@ WORKDIR /app RUN dnf -y update && dnf install -y iputils git net-tools wget \ vim-minimal python3.12 python3.12-pip python3.12-wheel \ - python3.12-setuptools python3.12-devel gcc make && \ + python3.12-setuptools python3.12-devel gcc gcc-c++ make && \ ln -s /bin/pip3.12 /bin/pip && ln -s /bin/python3.12 /bin/python && dnf clean all ENV UV_SYSTEM_PYTHON=1 @@ -164,7 +164,7 @@ RUN apt-get update && apt-get install -y \ procps psmisc lsof \ traceroute \ bubblewrap \ - gcc \ + gcc g++ \ && rm -rf /var/lib/apt/lists/* ENV UV_SYSTEM_PYTHON=1