lightspeed-stack 0.4.2__tar.gz → 0.5.0__tar.gz

{lightspeed_stack-0.4.2 → lightspeed_stack-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: lightspeed-stack
-Version: 0.4.2
+Version: 0.5.0
 Summary: LLM tooling stack
 Keywords: LLM,RAG
 Maintainer-Email: =?utf-8?b?UGF2ZWwgVGnFoW5vdnNrw70=?= <tisnik@centrum.cz>
@@ -218,14 +218,14 @@ Requires-Python: <3.14,>=3.12
 Requires-Dist: fastapi>=0.115.12
 Requires-Dist: uvicorn>=0.34.3
 Requires-Dist: kubernetes>=30.1.0
-Requires-Dist: llama-stack==0.4.3
-Requires-Dist: llama-stack-client==0.4.3
-Requires-Dist: llama-stack-api==0.4.4
+Requires-Dist: llama-stack==0.5.2
+Requires-Dist: llama-stack-client==0.5.2
+Requires-Dist: llama-stack-api==0.5.2
 Requires-Dist: rich>=14.0.0
 Requires-Dist: cachetools>=6.1.0
 Requires-Dist: prometheus-client>=0.22.1
 Requires-Dist: starlette>=0.47.1
-Requires-Dist: aiohttp>=3.12.14
+Requires-Dist: aiohttp>=3.13.3
 Requires-Dist: authlib>=1.6.0
 Requires-Dist: a2a-sdk<0.4.0,>=0.3.4
 Requires-Dist: email-validator>=2.2.0
@@ -236,14 +236,15 @@ Requires-Dist: asyncpg>=0.31.0
 Requires-Dist: semver<4.0.0
 Requires-Dist: jsonpath-ng>=1.6.1
 Requires-Dist: psycopg2-binary>=2.9.10
-Requires-Dist: litellm>=1.75.5.post1
-Requires-Dist: urllib3==2.6.3
+Requires-Dist: litellm<=1.82.6,>=1.75.5.post1
+Requires-Dist: urllib3>=2.6.3
 Requires-Dist: PyYAML>=6.0.0
 Requires-Dist: einops>=0.8.1
 Requires-Dist: azure-core>=1.38.0
 Requires-Dist: azure-identity>=1.21.0
-Requires-Dist: pyasn1>=0.6.2
+Requires-Dist: pyasn1>=0.6.3
 Requires-Dist: jinja2>=3.1.0
+Requires-Dist: requests>=2.33.0
 Description-Content-Type: text/markdown
 
 # lightspeed-stack
@@ -254,7 +255,7 @@ Description-Content-Type: text/markdown
 [![License](https://img.shields.io/badge/license-Apache-blue)](https://github.com/lightspeed-core/lightspeed-stack/blob/main/LICENSE)
 [![made-with-python](https://img.shields.io/badge/Made%20with-Python-1f425f.svg)](https://www.python.org/)
 [![Required Python version](https://img.shields.io/python/required-version-toml?tomlFilePath=https%3A%2F%2Fraw.githubusercontent.com%2Flightspeed-core%2Flightspeed-stack%2Frefs%2Fheads%2Fmain%2Fpyproject.toml)](https://www.python.org/)
-[![Tag](https://img.shields.io/github/v/tag/lightspeed-core/lightspeed-stack)](https://github.com/lightspeed-core/lightspeed-stack/releases/tag/0.4.2)
+[![Tag](https://img.shields.io/github/v/tag/lightspeed-core/lightspeed-stack)](https://github.com/lightspeed-core/lightspeed-stack/releases/tag/0.5.0)
 
 Lightspeed Core Stack (LCS) is an AI-powered assistant that provides answers to product questions using backend LLM services, agents, and RAG databases.
 
@@ -283,6 +284,7 @@ The service includes comprehensive user data collection capabilities for various
                 * [2. Kubernetes Service Account Tokens (For K8s Deployments)](#2-kubernetes-service-account-tokens-for-k8s-deployments)
                 * [3. Client-Provided Tokens (For Per-User Authentication)](#3-client-provided-tokens-for-per-user-authentication)
                 * [4. OAuth (For MCP Servers Requiring OAuth)](#4-oauth-for-mcp-servers-requiring-oauth)
+                * [5. Automatic Header Propagation (For Gateway-Injected Headers)](#5-automatic-header-propagation-for-gateway-injected-headers)
                 * [Client-Authenticated MCP Servers Discovery](#client-authenticated-mcp-servers-discovery)
                 * [Combining Authentication Methods](#combining-authentication-methods)
                 * [Authentication Method Comparison](#authentication-method-comparison)
@@ -1077,7 +1079,6 @@ Usage: make <OPTIONS> ... <TARGETS>
 Available targets are:
 
 run                               Run the service locally
-help                              Show this help screen
 run-llama-stack                   Start Llama Stack with enriched config (for local service mode)
 test-unit                         Run the unit tests
 test-integration                  Run integration tests tests
@@ -1090,7 +1091,6 @@ format                            Format the code into unified format
 schema                            Generate OpenAPI schema file
 openapi-doc                       Generate OpenAPI documentation
 generate-documentation            Generate documentation
-requirements.txt                  Generate requirements.txt file containing hashes for all non-devel packages
 doc                               Generate documentation for developers
 docs/config.puml                  Generate PlantUML class diagram for configuration
 docs/config.png                   Generate an image with configuration graph
@@ -1105,9 +1105,12 @@ verify                            Run all linters
 distribution-archives             Generate distribution archives to be uploaded into Python registry
 upload-distribution-archives      Upload distribution archives into Python registry
 konflux-requirements              Generate hermetic requirements.*.txt file for konflux build
-konflux-rpm-lock 	              Generate rpm.lock.yaml file for konflux build
+konflux-rpm-lock                  Generate rpm.lock.yaml file for konflux build
+help                              Show this help screen
 ```
 
+
+
 ## Running Linux container image
 
 Stable release images are tagged with versions like `0.1.0`. Tag `latest` always points to latest stable release.

{lightspeed_stack-0.4.2 → lightspeed_stack-0.5.0}/README.md

@@ -6,7 +6,7 @@
 [![License](https://img.shields.io/badge/license-Apache-blue)](https://github.com/lightspeed-core/lightspeed-stack/blob/main/LICENSE)
 [![made-with-python](https://img.shields.io/badge/Made%20with-Python-1f425f.svg)](https://www.python.org/)
 [![Required Python version](https://img.shields.io/python/required-version-toml?tomlFilePath=https%3A%2F%2Fraw.githubusercontent.com%2Flightspeed-core%2Flightspeed-stack%2Frefs%2Fheads%2Fmain%2Fpyproject.toml)](https://www.python.org/)
-[![Tag](https://img.shields.io/github/v/tag/lightspeed-core/lightspeed-stack)](https://github.com/lightspeed-core/lightspeed-stack/releases/tag/0.4.2)
+[![Tag](https://img.shields.io/github/v/tag/lightspeed-core/lightspeed-stack)](https://github.com/lightspeed-core/lightspeed-stack/releases/tag/0.5.0)
 
 Lightspeed Core Stack (LCS) is an AI-powered assistant that provides answers to product questions using backend LLM services, agents, and RAG databases.
 
@@ -35,6 +35,7 @@ The service includes comprehensive user data collection capabilities for various
                 * [2. Kubernetes Service Account Tokens (For K8s Deployments)](#2-kubernetes-service-account-tokens-for-k8s-deployments)
                 * [3. Client-Provided Tokens (For Per-User Authentication)](#3-client-provided-tokens-for-per-user-authentication)
                 * [4. OAuth (For MCP Servers Requiring OAuth)](#4-oauth-for-mcp-servers-requiring-oauth)
+                * [5. Automatic Header Propagation (For Gateway-Injected Headers)](#5-automatic-header-propagation-for-gateway-injected-headers)
                 * [Client-Authenticated MCP Servers Discovery](#client-authenticated-mcp-servers-discovery)
                 * [Combining Authentication Methods](#combining-authentication-methods)
                 * [Authentication Method Comparison](#authentication-method-comparison)
@@ -829,7 +830,6 @@ Usage: make <OPTIONS> ... <TARGETS>
 Available targets are:
 
 run                               Run the service locally
-help                              Show this help screen
 run-llama-stack                   Start Llama Stack with enriched config (for local service mode)
 test-unit                         Run the unit tests
 test-integration                  Run integration tests tests
@@ -842,7 +842,6 @@ format                            Format the code into unified format
 schema                            Generate OpenAPI schema file
 openapi-doc                       Generate OpenAPI documentation
 generate-documentation            Generate documentation
-requirements.txt                  Generate requirements.txt file containing hashes for all non-devel packages
 doc                               Generate documentation for developers
 docs/config.puml                  Generate PlantUML class diagram for configuration
 docs/config.png                   Generate an image with configuration graph
@@ -857,9 +856,12 @@ verify                            Run all linters
 distribution-archives             Generate distribution archives to be uploaded into Python registry
 upload-distribution-archives      Upload distribution archives into Python registry
 konflux-requirements              Generate hermetic requirements.*.txt file for konflux build
-konflux-rpm-lock 	              Generate rpm.lock.yaml file for konflux build
+konflux-rpm-lock                  Generate rpm.lock.yaml file for konflux build
+help                              Show this help screen
 ```
 
+
+
 ## Running Linux container image
 
 Stable release images are tagged with versions like `0.1.0`. Tag `latest` always points to latest stable release.

{lightspeed_stack-0.4.2 → lightspeed_stack-0.5.0}/pyproject.toml

@@ -24,14 +24,14 @@ dependencies = [
     "fastapi>=0.115.12",
     "uvicorn>=0.34.3",
     "kubernetes>=30.1.0",
-    "llama-stack==0.4.3",
-    "llama-stack-client==0.4.3",
-    "llama-stack-api==0.4.4",
+    "llama-stack==0.5.2",
+    "llama-stack-client==0.5.2",
+    "llama-stack-api==0.5.2",
     "rich>=14.0.0",
     "cachetools>=6.1.0",
     "prometheus-client>=0.22.1",
     "starlette>=0.47.1",
-    "aiohttp>=3.12.14",
+    "aiohttp>=3.13.3",
     "authlib>=1.6.0",
     "a2a-sdk>=0.3.4,<0.4.0",
     "email-validator>=2.2.0",
@@ -42,16 +42,17 @@ dependencies = [
     "semver<4.0.0",
     "jsonpath-ng>=1.6.1",
     "psycopg2-binary>=2.9.10",
-    "litellm>=1.75.5.post1",
-    "urllib3==2.6.3",
+    "litellm>=1.75.5.post1,<=1.82.6",
+    "urllib3>=2.6.3",
     "PyYAML>=6.0.0",
     "einops>=0.8.1",
     "azure-core>=1.38.0",
     "azure-identity>=1.21.0",
-    "pyasn1>=0.6.2",
+    "pyasn1>=0.6.3",
     "jinja2>=3.1.0",
+    "requests>=2.33.0",
 ]
-version = "0.4.2"
+version = "0.5.0"
 
 [project.license]
 file = "LICENSE"
@@ -64,10 +65,7 @@ Homepage = "https://github.com/lightspeed-core/lightspeed-stack"
 Issues = "https://github.com/lightspeed-core/lightspeed-stack/issues"
 
 [tool.pyright]
-exclude = [
-    "src/authentication/k8s.py",
-    "src/app/endpoints/conversations.py",
-]
+exclude = []
 extraPaths = [
     "./src",
 ]
@@ -124,10 +122,15 @@ extend-select = [
     "TID251",
     "UP006",
     "UP007",
+    "UP010",
     "UP017",
     "UP035",
     "RUF100",
+    "B009",
     "B010",
+    "DTZ005",
+    "D202",
+    "I001",
 ]
 
 [tool.ruff.lint.flake8-tidy-imports.banned-api.unittest]
@@ -160,6 +163,7 @@ dev = [
     "ruff>=0.11.13",
     "aiosqlite",
     "behave>=1.3.0",
+    "trustme>=1.2.1",
     "types-cachetools>=6.1.0.20250717",
     "build>=1.2.2.post1",
     "twine>=6.1.0",
@@ -180,7 +184,7 @@ llslibdev = [
     "faiss-cpu>=1.11.0",
     "chardet>=5.2.0",
     "psycopg2-binary>=2.9.10",
-    "requests>=2.32.4",
+    "requests>=2.33.0",
     "aiosqlite>=0.21.0",
     "datasets>=3.6.0",
     "opentelemetry-sdk>=1.34.1",
@@ -192,13 +196,17 @@ llslibdev = [
     "trl>=0.18.2",
     "peft>=0.15.2",
     "google-cloud-aiplatform>=1.130.0",
-    "litellm>=1.81.0",
+    "litellm>=1.81.0,<=1.82.6",
     "autoevals>=0.0.129",
     "fire>=0.7.0",
     "opentelemetry-instrumentation>=0.55b0",
     "blobfile>=3.0.0",
     "psutil>=7.0.0",
     "azure-identity>=1.21.0",
+    "httpx>=0.27.0",
+    "pydantic>=2.10.6",
+    "protobuf>=6.33.5",
+    "filelock>=3.20.3",
 ]
 build = [
     "build>=1.2.2.post1",

{lightspeed_stack-0.4.2 → lightspeed_stack-0.5.0}/src/a2a_storage/postgres_context_store.py

@@ -2,7 +2,7 @@
 
 from typing import Optional
 
-from sqlalchemy import Column, String, Table, MetaData, select, delete
+from sqlalchemy import Column, MetaData, String, Table, delete, select
 from sqlalchemy.dialects.postgresql import insert as pg_insert
 from sqlalchemy.ext.asyncio import AsyncEngine, async_sessionmaker
 

{lightspeed_stack-0.4.2 → lightspeed_stack-0.5.0}/src/a2a_storage/sqlite_context_store.py

@@ -2,7 +2,7 @@
 
 from typing import Optional
 
-from sqlalchemy import Column, String, Table, MetaData, select, delete
+from sqlalchemy import Column, MetaData, String, Table, delete, select
 from sqlalchemy.ext.asyncio import AsyncEngine, async_sessionmaker
 
 from a2a_storage.context_store import A2AContextStore

{lightspeed_stack-0.4.2 → lightspeed_stack-0.5.0}/src/a2a_storage/storage_factory.py

@@ -1,18 +1,17 @@
 """Factory for creating A2A storage backends."""
 
-from urllib.parse import quote_plus
 from typing import Optional
+from urllib.parse import quote_plus
 
-from sqlalchemy.ext.asyncio import create_async_engine, AsyncEngine
-
-from a2a.server.tasks import TaskStore, InMemoryTaskStore, DatabaseTaskStore
+from a2a.server.tasks import DatabaseTaskStore, InMemoryTaskStore, TaskStore
+from sqlalchemy.ext.asyncio import AsyncEngine, create_async_engine
 
 from a2a_storage.context_store import A2AContextStore
 from a2a_storage.in_memory_context_store import InMemoryA2AContextStore
-from a2a_storage.sqlite_context_store import SQLiteA2AContextStore
 from a2a_storage.postgres_context_store import PostgresA2AContextStore
-from models.config import A2AStateConfiguration
+from a2a_storage.sqlite_context_store import SQLiteA2AContextStore
 from log import get_logger
+from models.config import A2AStateConfiguration
 
 logger = get_logger(__name__)
 

{lightspeed_stack-0.4.2 → lightspeed_stack-0.5.0}/src/app/database.py

@@ -6,12 +6,12 @@ from typing import Any, Optional
 
 from sqlalchemy import create_engine, text
 from sqlalchemy.engine.base import Engine
-from sqlalchemy.orm import sessionmaker, Session
+from sqlalchemy.orm import Session, sessionmaker
 
-from log import get_logger
 from configuration import configuration
+from log import get_logger
+from models.config import PostgreSQLDatabaseConfiguration, SQLiteDatabaseConfiguration
 from models.database.base import Base
-from models.config import SQLiteDatabaseConfiguration, PostgreSQLDatabaseConfiguration
 
 logger = get_logger(__name__)
 

{lightspeed_stack-0.4.2 → lightspeed_stack-0.5.0}/src/app/endpoints/README.md

@@ -30,6 +30,9 @@ Handler for REST API call to provide info.
 ## [mcp_auth.py](mcp_auth.py)
 Handler for REST API calls related to MCP server authentication.
 
+## [mcp_servers.py](mcp_servers.py)
+Handler for REST API calls to dynamically manage MCP servers.
+
 ## [metrics.py](metrics.py)
 Handler for REST API call to provide metrics.
 
@@ -45,6 +48,9 @@ Handler for REST API call to provide answer to query using Response API.
 ## [rags.py](rags.py)
 Handler for REST API calls to list and retrieve available RAGs.
 
+## [responses.py](responses.py)
+Handler for REST API call to provide answer using Responses API (LCORE specification).
+
 ## [rlsapi_v1.py](rlsapi_v1.py)
 Handler for RHEL Lightspeed rlsapi v1 REST API endpoints.
 
@@ -54,6 +60,9 @@ Handler for the / endpoint.
 ## [shields.py](shields.py)
 Handler for REST API call to list available shields.
 
+## [stream_interrupt.py](stream_interrupt.py)
+Endpoint for interrupting in-progress streaming query requests.
+
 ## [streaming_query.py](streaming_query.py)
 Streaming query handler using Responses API.
 

{lightspeed_stack-0.4.2 → lightspeed_stack-0.5.0}/src/app/endpoints/a2a.py

@@ -3,8 +3,8 @@
 import asyncio
 import json
 import uuid
-from collections.abc import Mapping, AsyncIterator, MutableMapping
-from datetime import datetime, UTC
+from collections.abc import AsyncIterator, Mapping, MutableMapping
+from datetime import UTC, datetime
 from typing import Annotated, Any, Optional
 
 from a2a.server.agent_execution import AgentExecutor, RequestContext
@@ -36,23 +36,22 @@ from llama_stack_client import APIConnectionError
 from starlette.responses import Response, StreamingResponse
 
 from a2a_storage import A2AContextStore, A2AStorageFactory
-
 from authentication import get_auth_dependency
 from authentication.interface import AuthTuple
 from authorization.middleware import authorize
 from client import AsyncLlamaStackClientHolder
 from configuration import configuration
 from constants import MEDIA_TYPE_EVENT_STREAM
+from log import get_logger
 from models.config import Action
 from models.requests import QueryRequest
-from utils.mcp_headers import mcp_headers_dependency, McpHeaders
+from utils.mcp_headers import McpHeaders, mcp_headers_dependency
 from utils.responses import (
     extract_text_from_response_item,
     prepare_responses_params,
 )
 from utils.suid import normalize_conversation_id
 from version import __version__
-from log import get_logger
 
 logger = get_logger(__name__)
 router = APIRouter(tags=["a2a"])
@@ -340,7 +339,7 @@ class A2AAgentExecutor(AgentExecutor):
             stream = await client.responses.create(**responses_params.model_dump())
         except APIConnectionError as e:
             error_message = (
-                f"Unable to connect to Llama Stack backend service: {str(e)}. "
+                f"Unable to connect to Llama Stack backend service: {e!s}. "
                 "The service may be temporarily unavailable. Please try again later."
             )
             logger.error(

{lightspeed_stack-0.4.2 → lightspeed_stack-0.5.0}/src/app/endpoints/conversations_v1.py

@@ -14,9 +14,9 @@ from authentication import get_auth_dependency
 from authorization.middleware import authorize
 from client import AsyncLlamaStackClientHolder
 from configuration import configuration
+from log import get_logger
 from models.config import Action
 from models.database.conversations import (
-    UserTurn,
     UserConversation,
 )
 from models.requests import ConversationUpdateRequest
@@ -33,11 +33,16 @@ from models.responses import (
     ServiceUnavailableResponse,
     UnauthorizedResponse,
 )
+from utils.conversations import (
+    build_conversation_turns_from_items,
+    get_all_conversation_items,
+)
 from utils.endpoints import (
     can_access_conversation,
     check_configuration_loaded,
     delete_conversation,
     retrieve_conversation,
+    retrieve_conversation_turns,
     validate_and_retrieve_conversation,
 )
 from utils.suid import (
@@ -45,8 +50,6 @@ from utils.suid import (
     normalize_conversation_id,
     to_llama_stack_conversation_id,
 )
-from utils.conversations import build_conversation_turns_from_items
-from log import get_logger
 
 logger = get_logger(__name__)
 router = APIRouter(tags=["conversations_v1"])
@@ -236,46 +239,23 @@ async def get_conversation_endpoint_handler(  # pylint: disable=too-many-locals,
             llama_stack_conv_id,
         )
 
-        # Use Conversations API to retrieve conversation items
-        conversation_items_response = await client.conversations.items.list(
-            conversation_id=llama_stack_conv_id,
-            after=None,
-            include=None,
-            limit=None,
-            order="asc",  # oldest first
-        )
+        # Retrieve turns metadata from database (can be empty for legacy conversations)
+        db_turns = retrieve_conversation_turns(normalized_conv_id)
 
-        if not conversation_items_response.data:
+        # Use Conversations API to retrieve conversation items
+        items = await get_all_conversation_items(client, llama_stack_conv_id)
+        if not items:
             logger.error("No items found for conversation %s", conversation_id)
             response = NotFoundResponse(
                 resource="conversation", resource_id=normalized_conv_id
             ).model_dump()
             raise HTTPException(**response)
 
-        items = conversation_items_response.data
-
         logger.info(
             "Successfully retrieved %d items for conversation %s",
             len(items),
             conversation_id,
         )
-        # Retrieve turns metadata from database
-        db_turns: list[UserTurn] = []
-        try:
-            with get_session() as session:
-                db_turns = (
-                    session.query(UserTurn)
-                    .filter_by(conversation_id=normalized_conv_id)
-                    .order_by(UserTurn.turn_number)
-                    .all()
-                )
-        except SQLAlchemyError as e:
-            logger.error(
-                "Database error occurred while retrieving conversation turns for %s.",
-                normalized_conv_id,
-            )
-            response = InternalServerErrorResponse.database_error()
-            raise HTTPException(**response.model_dump()) from e
 
         # Build conversation turns from items and populate turns metadata
         # Use conversation.created_at for legacy conversations without turn metadata

{lightspeed_stack-0.4.2 → lightspeed_stack-0.5.0}/src/app/endpoints/health.py

@@ -75,7 +75,7 @@ async def get_providers_health_statuses() -> list[ProviderHealthStatus]:
         providers = await client.providers.list()
         logger.debug("Found %d providers", len(providers))
 
-        health_results = [
+        return [
             ProviderHealthStatus(
                 provider_id=provider.provider_id,
                 status=str(provider.health.get("status", "unknown")),
@@ -83,7 +83,6 @@ async def get_providers_health_statuses() -> list[ProviderHealthStatus]:
             )
             for provider in providers
         ]
-        return health_results
 
     except APIConnectionError as e:
         logger.error("Failed to check providers health: %s", e)
@@ -91,7 +90,7 @@ async def get_providers_health_statuses() -> list[ProviderHealthStatus]:
             ProviderHealthStatus(
                 provider_id="unknown",
                 status=HealthStatus.ERROR.value,
-                message=f"Failed to initialize health check: {str(e)}",
+                message=f"Failed to initialize health check: {e!s}",
             )
         ]