Merge branch 'main' into lcore-1285

Author: jrobertboos

.tekton/lightspeed-stack-pull-request.yaml

@@ -54,7 +54,7 @@ spec:
            ],
            "requirements_build_files": ["requirements-build.txt"],
            "binary": {
-             "packages": "aiohappyeyeballs,aiohttp,aiosignal,aiosqlite,annotated-doc,annotated-types,anyio,asyncpg,attrs,cffi,charset-normalizer,chevron,click,cryptography,datasets,dill,distro,dnspython,docstring-parser,durationpy,einops,email-validator,faiss-cpu,fire,frozenlist,fsspec,google-cloud-core,google-cloud-resource-manager,google-crc32c,google-genai,google-resumable-media,googleapis-common-protos,grpc-google-iam-v1,grpcio,grpcio-status,h11,hf-xet,httpcore,httpx,httpx-sse,idna,importlib-metadata,jinja2,jiter,joblib,jsonschema,jsonschema-specifications,kubernetes,lxml,markdown-it-py,mcp,mdurl,mpmath,multidict,networkx,numpy,oauthlib,packaging,pandas,peft,pillow,prometheus-client,prompt-toolkit,propcache,psycopg2-binary,pyarrow,pyasn1,pyasn1-modules,pycparser,pydantic,pydantic-core,pygments,python-dateutil,python-multipart,pyyaml,referencing,requests,requests-oauthlib,rpds-py,rsa,safetensors,scikit-learn,scipy,setuptools,six,sniffio,sqlalchemy,starlette,sympy,termcolor,threadpoolctl,tiktoken,tokenizers,torch,tornado,tqdm,transformers,tree-sitter,triton,typing-extensions,typing-inspection,tzdata,urllib3,websocket-client,websockets,wrapt,xxhash,yarl,zipp,uv,pip,maturin",
+             "packages": "aiohappyeyeballs,aiohttp,aiosignal,aiosqlite,annotated-doc,annotated-types,anyio,asyncpg,attrs,cffi,chevron,click,cryptography,datasets,dill,distro,dnspython,docstring-parser,durationpy,einops,email-validator,faiss-cpu,fire,frozenlist,fsspec,google-cloud-core,google-cloud-resource-manager,google-crc32c,google-genai,google-resumable-media,grpc-google-iam-v1,grpcio,grpcio-status,h11,hf-xet,httpcore,httpx,httpx-sse,idna,importlib-metadata,jinja2,jiter,joblib,jsonschema,jsonschema-specifications,kubernetes,lxml,markdown-it-py,mcp,mdurl,mpmath,multidict,networkx,numpy,oauthlib,packaging,pandas,peft,pillow,prometheus-client,prompt-toolkit,propcache,psycopg2-binary,pyarrow,pyasn1,pyasn1-modules,pycparser,pydantic,pydantic-core,pygments,python-dateutil,python-multipart,pyyaml,referencing,requests,requests-oauthlib,rpds-py,rsa,safetensors,scikit-learn,scipy,setuptools,six,sniffio,sqlalchemy,starlette,sympy,termcolor,threadpoolctl,tiktoken,tokenizers,torch,tornado,tqdm,transformers,tree-sitter,triton,typing-extensions,typing-inspection,tzdata,urllib3,websocket-client,websockets,wrapt,xxhash,yarl,zipp,uv,pip,maturin",
              "os": "linux",
              "arch": "x86_64,aarch64",
              "py_version": 312

.tekton/lightspeed-stack-push.yaml

@@ -46,7 +46,7 @@ spec:
           ],
           "requirements_build_files": ["requirements-build.txt"],
           "binary": {
-            "packages": "aiohappyeyeballs,aiohttp,aiosignal,aiosqlite,annotated-doc,annotated-types,anyio,asyncpg,attrs,cffi,charset-normalizer,chevron,click,cryptography,datasets,dill,distro,dnspython,docstring-parser,durationpy,einops,email-validator,faiss-cpu,fire,frozenlist,fsspec,google-cloud-core,google-cloud-resource-manager,google-crc32c,google-genai,google-resumable-media,googleapis-common-protos,grpc-google-iam-v1,grpcio,grpcio-status,h11,hf-xet,httpcore,httpx,httpx-sse,idna,importlib-metadata,jinja2,jiter,joblib,jsonschema,jsonschema-specifications,kubernetes,lxml,markdown-it-py,mcp,mdurl,mpmath,multidict,networkx,numpy,oauthlib,packaging,pandas,peft,pillow,prometheus-client,prompt-toolkit,propcache,psycopg2-binary,pyarrow,pyasn1,pyasn1-modules,pycparser,pydantic,pydantic-core,pygments,python-dateutil,python-multipart,pyyaml,referencing,requests,requests-oauthlib,rpds-py,rsa,safetensors,scikit-learn,scipy,setuptools,six,sniffio,sqlalchemy,starlette,sympy,termcolor,threadpoolctl,tiktoken,tokenizers,torch,tornado,tqdm,transformers,tree-sitter,triton,typing-extensions,typing-inspection,tzdata,urllib3,websocket-client,websockets,wrapt,xxhash,yarl,zipp,uv,pip,maturin",
+            "packages": "aiohappyeyeballs,aiohttp,aiosignal,aiosqlite,annotated-doc,annotated-types,anyio,asyncpg,attrs,cffi,chevron,click,cryptography,datasets,dill,distro,dnspython,docstring-parser,durationpy,einops,email-validator,faiss-cpu,fire,frozenlist,fsspec,google-cloud-core,google-cloud-resource-manager,google-crc32c,google-genai,google-resumable-media,grpc-google-iam-v1,grpcio,grpcio-status,h11,hf-xet,httpcore,httpx,httpx-sse,idna,importlib-metadata,jinja2,jiter,joblib,jsonschema,jsonschema-specifications,kubernetes,lxml,markdown-it-py,mcp,mdurl,mpmath,multidict,networkx,numpy,oauthlib,packaging,pandas,peft,pillow,prometheus-client,prompt-toolkit,propcache,psycopg2-binary,pyarrow,pyasn1,pyasn1-modules,pycparser,pydantic,pydantic-core,pygments,python-dateutil,python-multipart,pyyaml,referencing,requests,requests-oauthlib,rpds-py,rsa,safetensors,scikit-learn,scipy,setuptools,six,sniffio,sqlalchemy,starlette,sympy,termcolor,threadpoolctl,tiktoken,tokenizers,torch,tornado,tqdm,transformers,tree-sitter,triton,typing-extensions,typing-inspection,tzdata,urllib3,websocket-client,websockets,wrapt,xxhash,yarl,zipp,uv,pip,maturin",
             "os": "linux",
             "arch": "x86_64,aarch64",
             "py_version": 312

pyproject.toml

@@ -223,7 +223,7 @@ disable = ["R0801"]
 extend-exclude = ["tests/profiles/syntax_error.py"]
 
 [tool.ruff.lint]
-extend-select = ["TID251", "UP006", "UP007", "UP017", "UP035", "RUF100", "B010"]
+extend-select = ["TID251", "UP006", "UP007", "UP017", "UP035", "RUF100", "B009", "B010"]
 
 [tool.ruff.lint.flake8-tidy-imports.banned-api]
 unittest = { msg = "use pytest instead of unittest" }

scripts/konflux_requirements.sh

@@ -4,6 +4,8 @@
 # Packages from pypi.org go to requirements.source.txt
 # Packages from console.redhat.com go to requirements.wheel.txt
 
+set -x
+
 RAW_REQ_FILE="requirements.no_hashes.txt"
 SOURCE_FILE="requirements.source.txt"
 WHEEL_FILE="requirements.wheel.txt"
@@ -87,4 +89,4 @@ echo "Done!"
 echo "Packages from pypi.org written to: $SOURCE_HASH_FILE ($(wc -l < "$SOURCE_HASH_FILE") packages)"
 echo "Packages from console.redhat.com written to: $WHEEL_HASH_FILE ($(wc -l < "$WHEEL_HASH_FILE") packages)"
 echo "Build dependencies written to: $BUILD_FILE ($(wc -l < "$BUILD_FILE") packages)"
-echo "Remember to commit $SOURCE_HASH_FILE, $WHEEL_HASH_FILE, $BUILD_FILE, pipeline configurations and push the changes"
+echo "Remember to commit $SOURCE_HASH_FILE, $WHEEL_HASH_FILE, $BUILD_FILE, pipeline configurations and push the changes"

src/app/endpoints/streaming_query.py

@@ -698,7 +698,7 @@ async def response_generator(  # pylint: disable=too-many-branches,too-many-stat
         # Completed response - capture final text and response object
         elif event_type == "response.completed":
             latest_response_object = cast(
-                OpenAIResponseObject, getattr(chunk, "response")
+                OpenAIResponseObject, getattr(chunk, "response")  # noqa: B009
             )
             turn_summary.llm_response = turn_summary.llm_response or "".join(text_parts)
             yield stream_event(
@@ -714,7 +714,7 @@ async def response_generator(  # pylint: disable=too-many-branches,too-many-stat
         # Incomplete or failed response - emit error
         elif event_type in ("response.incomplete", "response.failed"):
             latest_response_object = cast(
-                OpenAIResponseObject, getattr(chunk, "response")
+                OpenAIResponseObject, getattr(chunk, "response")  # noqa: B009
             )
             error_message = (
                 latest_response_object.error.message

src/llama_stack_configuration.py

@@ -251,8 +251,7 @@ def construct_models_section(
 
         # Strip sentence-transformers/ prefix if present
         provider_model_id = embedding_model
-        if provider_model_id.startswith("sentence-transformers/"):
-            provider_model_id = provider_model_id[len("sentence-transformers/") :]
+        provider_model_id = provider_model_id.removeprefix("sentence-transformers/")
 
         # Skip if embedding model already registered
         existing_model_ids = [m.get("provider_model_id") for m in output]
@@ -489,8 +488,7 @@ def enrich_solr(ls_config: dict[str, Any], solr_config: dict[str, Any]) -> None:
 
     # Strip sentence-transformers/ prefix from constant for provider_model_id
     provider_model_id = constants.SOLR_DEFAULT_EMBEDDING_MODEL
-    if provider_model_id.startswith("sentence-transformers/"):
-        provider_model_id = provider_model_id[len("sentence-transformers/") :]
+    provider_model_id = provider_model_id.removeprefix("sentence-transformers/")
 
     # Check if already registered
     registered_models = ls_config["registered_resources"]["models"]

src/utils/suid.py

@@ -40,7 +40,7 @@ def check_suid(suid: str) -> bool:
         return False
 
     # Strip 'conv_' prefix if present
-    hex_part = suid[5:] if suid.startswith("conv_") else suid
+    hex_part = suid.removeprefix("conv_")
 
     # Check for 48-char hex string (llama-stack conversation ID format)
     if len(hex_part) == 48: