Merge branch 'main' into rename-aws-bedrock-api-key

Author: ashwinb

.github/CODEOWNERS

@@ -2,4 +2,4 @@
 
 # These owners will be the default owners for everything in
 # the repo. Unless a later match takes precedence,
-* @ashwinb @yanxi0830 @hardikjshah @raghotham @ehhuang @terrytangyuan @leseb @bbrowning @reluctantfuturist @mattf @slekkala1 @franciscojavierarceo
+* @ashwinb @yanxi0830 @hardikjshah @raghotham @ehhuang @leseb @bbrowning @reluctantfuturist @mattf @slekkala1 @franciscojavierarceo

.github/workflows/python-build-test.yml

@@ -31,15 +31,15 @@ jobs:
         version: 0.7.6
 
     - name: Build Llama Stack API package
-      working-directory: src/llama-stack-api
+      working-directory: src/llama_stack_api
       run: uv build
 
     - name: Build Llama Stack package
       run: uv build
 
     - name: Install Llama Stack package (with api stubs from local build)
       run: |
-        uv pip install --find-links src/llama-stack-api/dist dist/*.whl
+        uv pip install --find-links src/llama_stack_api/dist dist/*.whl
 
     - name: Verify Llama Stack package
       run: |
@@ -48,3 +48,4 @@ jobs:
         command -v llama
         llama stack list-apis
         llama stack list-providers inference
+        llama stack list-deps starter

.pre-commit-config.yaml

@@ -42,7 +42,6 @@ repos:
     hooks:
     -   id: ruff
         args: [ --fix ]
-        exclude: ^(src/llama_stack/strong_typing/.*|src/llama-stack-api/llama_stack_api/strong_typing/.*)$
     -   id: ruff-format
 
 -   repo: https://github.com/adamchainz/blacken-docs
@@ -106,16 +105,16 @@ repos:
         language: python
         pass_filenames: false
         require_serial: true
-        files: ^src/llama_stack/providers/.*$
+        files: ^src/llama_stack/providers/.*$|^scripts/run_openapi_generator.sh$
       - id: openapi-codegen
         name: API Spec Codegen
         additional_dependencies:
           - uv==0.7.8
-        entry: sh -c './scripts/uv-run-with-index.sh run ./docs/openapi_generator/run_openapi_generator.sh > /dev/null'
+        entry: sh -c './scripts/uv-run-with-index.sh run scripts/run_openapi_generator.sh'
         language: python
         pass_filenames: false
         require_serial: true
-        files: ^src/llama_stack/apis/|^docs/openapi_generator/
+        files: ^src/llama_stack_api/.*$
       - id: check-workflows-use-hashes
         name: Check GitHub Actions use SHA-pinned actions
         entry: ./scripts/check-workflows-use-hashes.sh

CONTRIBUTING.md

@@ -231,7 +231,7 @@ npm run serve
 If you modify or add new API endpoints, update the API documentation accordingly. You can do this by running the following command:
 
 ```bash
-uv run ./docs/openapi_generator/run_openapi_generator.sh
+uv run ./scripts/run_openapi_generator.sh
 ```
 
 The generated API schema will be available in `docs/static/`. Make sure to review the changes before committing.

client-sdks/stainless/README.md

@@ -5,4 +5,4 @@ These are the source-of-truth configuration files used to generate the Stainless
 
 A small side note: notice the `.yml` suffixes since Stainless uses that suffix typically for its configuration files.
 
-These files go hand-in-hand. As of now, only the `openapi.yml` file is automatically generated using the `run_openapi_generator.sh` script.
+These files go hand-in-hand. As of now, only the `openapi.yml` file is automatically generated using the `scripts/run_openapi_generator.sh` script.

client-sdks/stainless/config.yml

@@ -115,9 +115,6 @@ resources:
       sampling_params: SamplingParams
       scoring_result: ScoringResult
       system_message: SystemMessage
-      query_result: RAGQueryResult
-      document: RAGDocument
-      query_config: RAGQueryConfig
   toolgroups:
     models:
       tool_group: ToolGroup
@@ -143,11 +140,6 @@ resources:
         endpoint: get /v1/tool-runtime/list-tools
         paginated: false
       invoke_tool: post /v1/tool-runtime/invoke
-    subresources:
-      rag_tool:
-        methods:
-          insert: post /v1/tool-runtime/rag-tool/insert
-          query: post /v1/tool-runtime/rag-tool/query
 
   responses:
     models:
@@ -173,6 +165,7 @@ resources:
           list:
             type: http
             endpoint: get /v1/responses/{response_id}/input_items
+            paginated: false
 
   prompts:
     models:
@@ -220,6 +213,9 @@ resources:
           create:
             type: http
             endpoint: post /v1/conversations/{conversation_id}/items
+          delete:
+            type: http
+            endpoint: delete /v1/conversations/{conversation_id}/items/{item_id}
 
   inspect:
     models:
@@ -252,6 +248,7 @@ resources:
           list:
             type: http
             endpoint: get /v1/chat/completions
+            paginated: false
           retrieve:
             type: http
             endpoint: get /v1/chat/completions/{completion_id}
@@ -375,6 +372,7 @@ resources:
         endpoint: get /v1/scoring-functions
         paginated: false
       register: post /v1/scoring-functions
+      unregister: delete /v1/scoring-functions/{scoring_fn_id}
     models:
       scoring_fn: ScoringFn
       scoring_fn_params: ScoringFnParams
@@ -392,6 +390,13 @@ resources:
       list_files_response: ListOpenAIFileResponse
       delete_file_response: OpenAIFileDeleteResponse
 
+  batches:
+    methods:
+      create: post /v1/batches
+      list: get /v1/batches
+      retrieve: get /v1/batches/{batch_id}
+      cancel: post /v1/batches/{batch_id}/cancel
+
   alpha:
     subresources:
       inference:
@@ -423,6 +428,7 @@ resources:
             endpoint: get /v1alpha/eval/benchmarks
             paginated: false
           register: post /v1alpha/eval/benchmarks
+          unregister: delete /v1alpha/eval/benchmarks/{benchmark_id}
         models:
           benchmark: Benchmark
           list_benchmarks_response: ListBenchmarksResponse
@@ -519,7 +525,7 @@ readme:
       params: &ref_0 {}
     headline:
       type: request
-      endpoint: post /v1/models
+      endpoint: get /v1/models
       params: *ref_0
     pagination:
       type: request