Merge branch 'main' into elasticsearch-integration

.github/workflows/conformance.yml

@@ -64,6 +64,7 @@ jobs:
           ref: ${{ github.event.pull_request.base.ref }}
           path: 'base'
 
+
       # Cache oasdiff to avoid checksum failures and speed up builds
       - name: Cache oasdiff
         if: steps.skip-check.outputs.skip != 'true'
@@ -136,6 +137,23 @@ jobs:
         run: |
           oasdiff breaking --fail-on ERR $BASE_SPEC $CURRENT_SPEC --match-path '^/v1/'
 
+      # Run oasdiff to detect breaking changes in the API specification when compared to the OpenAI openAPI spec
+      - name: Run OpenAPI Breaking Change Diff Against OpenAI API
+        if: steps.skip-check.outputs.skip != 'true'
+        continue-on-error: true
+        shell: bash
+        run: |
+          OPENAI_SPEC=docs/static/openai-spec-2.3.0.yml
+          LLAMA_STACK_SPEC=docs/static/llama-stack-spec.yaml
+
+          # Compare Llama Stack spec against OpenAI spec.
+          # This finds breaking changes in our implementation of common endpoints.
+          # By using our spec as the base, we avoid errors for endpoints we don't implement.
+          oasdiff breaking --fail-on ERR \
+            "$LLAMA_STACK_SPEC" \
+            "$OPENAI_SPEC" \
+            --strip-prefix-base "/v1"
+
       # Report when test is skipped
       - name: Report skip reason
         if: steps.skip-check.outputs.skip == 'true'

.pre-commit-config.yaml

@@ -19,6 +19,7 @@ repos:
     -   id: no-commit-to-branch
     -   id: check-yaml
         args: ["--unsafe"]
+        exclude: 'docs/static/openai-spec-2.3.0.yml'
     -   id: detect-private-key
     -   id: mixed-line-ending
         args: [--fix=lf] # Forces to replace line ending by LF (line feed)

docs/docs/distributions/list_of_distributions.mdx

@@ -28,7 +28,7 @@ Llama Stack provides several pre-configured distributions to help you get starte
 - Run locally with Ollama for development
 
 ```bash
-docker pull llama-stack/distribution-starter
+docker pull llamastack/distribution-starter
 ```
 
 **Guides:** [Starter Distribution Guide](self_hosted_distro/starter)
@@ -41,7 +41,7 @@ docker pull llama-stack/distribution-starter
 - Need to run inference locally
 
 ```bash
-docker pull llama-stack/distribution-meta-reference-gpu
+docker pull llamastack/distribution-meta-reference-gpu
 ```
 
 **Guides:** [Meta Reference GPU Guide](self_hosted_distro/meta-reference-gpu)

src/llama_stack/providers/remote/files/s3/files.py

@@ -4,8 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from __future__ import annotations
-
 import uuid
 from datetime import UTC, datetime
 from typing import TYPE_CHECKING, Annotated, Any, cast
@@ -39,7 +37,7 @@ from .config import S3FilesImplConfig
 # TODO: provider data for S3 credentials
 
 
-def _create_s3_client(config: S3FilesImplConfig) -> S3Client:
+def _create_s3_client(config: S3FilesImplConfig) -> "S3Client":
     try:
         s3_config = {
             "region_name": config.region,
@@ -66,7 +64,7 @@ def _create_s3_client(config: S3FilesImplConfig) -> S3Client:
         raise RuntimeError(f"Failed to initialize S3 client: {e}") from e
 
 
-async def _create_bucket_if_not_exists(client: S3Client, config: S3FilesImplConfig) -> None:
+async def _create_bucket_if_not_exists(client: "S3Client", config: S3FilesImplConfig) -> None:
     try:
         client.head_bucket(Bucket=config.bucket_name)
     except ClientError as e:
@@ -192,7 +190,7 @@ class S3FilesImpl(Files):
         pass
 
     @property
-    def client(self) -> S3Client:
+    def client(self) -> "S3Client":
         assert self._client is not None, "Provider not initialized"
         return self._client