Merge branch 'main' into build/uv-poc

Author: theagenticguy

CONTRIBUTING.md

@@ -25,6 +25,17 @@ Please try to include as much information as you can. Details like these are inc
 * Anything unusual about your environment or deployment
 
 
+## Finding contributions to work on
+Looking at the existing issues is a great way to find something to contribute to. We label issues that are well-defined and ready for community contributions with the "ready for contribution" label.
+
+Check our [Ready for Contribution](../../issues?q=is%3Aissue%20state%3Aopen%20label%3A%22ready%20for%20contribution%22) issues for items you can work on.
+
+Before starting work on any issue:
+1. Check if someone is already assigned or working on it
+2. Comment on the issue to express your interest and ask any clarifying questions
+3. Wait for maintainer confirmation before beginning significant work
+
+
 ## Development Environment
 
 This project uses [hatchling](https://hatch.pypa.io/latest/build/#hatchling) as the build backend and [hatch](https://hatch.pypa.io/latest/) for development workflow management.
@@ -70,7 +81,7 @@ This project uses [hatchling](https://hatch.pypa.io/latest/build/#hatchling) as
 
 ### Pre-commit Hooks
 
-We use [pre-commit](https://pre-commit.com/) to automatically run quality checks before each commit. The hook will run `hatch run format`, `hatch run lint`, `hatch run test`, and `hatch run cz check` on when you make a commit, ensuring code consistency.
+We use [pre-commit](https://pre-commit.com/) to automatically run quality checks before each commit. The hook will run `hatch run format`, `hatch run lint`, `hatch run test`, and `hatch run cz check` when you make a commit, ensuring code consistency.
 
 The pre-commit hook is installed with:
 
@@ -122,75 +133,6 @@ To send us a pull request, please:
 8. Pay attention to any automated CI failures reported in the pull request, and stay involved in the conversation.
 
 
-## Finding contributions to work on
-Looking at the existing issues is a great way to find something to contribute to.
-
-You can check:
-- Our known bugs list in [Bug Reports](../../issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) for issues that need fixing
-- Feature requests in [Feature Requests](../../issues?q=is%3Aissue%20state%3Aopen%20label%3Aenhancement) for new functionality to implement
-
-
-## Dependency Management with uv lock
-
-This project uses `uv lock` to ensure reproducible dependency resolution across all environments. The `uv.lock` file contains exact versions of all dependencies and **must be committed to git**.
-
-### For Developers
-
-**Initial Setup:**
-```bash
-# Install exact dependencies from lock file
-uv sync --dev
-```
-
-**Daily Development:**
-```bash
-# Use locked dependencies for all commands
-uv run poe test
-uv run poe lint
-uv run poe format
-```
-
-**Adding New Dependencies:**
-```bash
-# Add new dependency and update lock file
-uv add "new-package>=1.0.0"
-# The lock file is automatically updated
-git add pyproject.toml uv.lock
-git commit -m "feat: add new-package dependency"
-```
-
-**Updating Dependencies:**
-```bash
-# Update to latest compatible versions
-uv lock
-
-# Or upgrade to latest versions (major updates)
-uv lock --upgrade
-
-# Always commit lock file changes
-git add uv.lock
-git commit -m "chore: update dependencies"
-```
-
-### Why Lock Files Matter
-
-- **Reproducible Builds**: Same exact dependencies across dev, CI, and production
-- **Faster CI**: Pre-resolved dependencies eliminate resolution time
-- **Security**: Pinned versions prevent supply chain attacks
-- **Team Consistency**: Everyone gets identical dependency trees
-
-### Lock File Commands
-
-| Command | Purpose |
-|---------|---------|
-| `uv sync --dev` | Install exact dependencies from lock file |
-| `uv sync` | Install production dependencies only |
-| `uv lock` | Update lock file with latest compatible versions |
-| `uv lock --upgrade` | Upgrade all dependencies to latest versions |
-
-**Important**: Always commit `uv.lock` changes alongside `pyproject.toml` changes!
-
-
 ## Code of Conduct
 This project has adopted the [Amazon Open Source Code of Conduct](https://aws.github.io/code-of-conduct).
 For more information see the [Code of Conduct FAQ](https://aws.github.io/code-of-conduct-faq) or contact

src/strands/models/anthropic.py

@@ -55,7 +55,7 @@ class AnthropicConfig(TypedDict, total=False):
                 For a complete list of supported parameters, see https://docs.anthropic.com/en/api/messages.
         """
 
-        max_tokens: Required[str]
+        max_tokens: Required[int]
         model_id: Required[str]
         params: Optional[dict[str, Any]]
 

src/strands/multiagent/a2a/server.py

@@ -10,8 +10,9 @@
 
 import uvicorn
 from a2a.server.apps import A2AFastAPIApplication, A2AStarletteApplication
+from a2a.server.events import QueueManager
 from a2a.server.request_handlers import DefaultRequestHandler
-from a2a.server.tasks import InMemoryTaskStore
+from a2a.server.tasks import InMemoryTaskStore, PushNotificationConfigStore, PushNotificationSender, TaskStore
 from a2a.types import AgentCapabilities, AgentCard, AgentSkill
 from fastapi import FastAPI
 from starlette.applications import Starlette
@@ -36,6 +37,12 @@ def __init__(
         serve_at_root: bool = False,
         version: str = "0.0.1",
         skills: list[AgentSkill] | None = None,
+        # RequestHandler
+        task_store: TaskStore | None = None,
+        queue_manager: QueueManager | None = None,
+        push_config_store: PushNotificationConfigStore | None = None,
+        push_sender: PushNotificationSender | None = None,
+
     ):
         """Initialize an A2A-compatible server from a Strands agent.
 
@@ -52,6 +59,14 @@ def __init__(
                 Defaults to False.
             version: The version of the agent. Defaults to "0.0.1".
             skills: The list of capabilities or functions the agent can perform.
+            task_store: Custom task store implementation for managing agent tasks. If None,
+                uses InMemoryTaskStore.
+            queue_manager: Custom queue manager for handling message queues. If None,
+                no queue management is used.
+            push_config_store: Custom store for push notification configurations. If None,
+                no push notification configuration is used.
+            push_sender: Custom push notification sender implementation. If None,
+                no push notifications are sent.
         """
         self.host = host
         self.port = port
@@ -77,7 +92,10 @@ def __init__(
         self.capabilities = AgentCapabilities(streaming=True)
         self.request_handler = DefaultRequestHandler(
             agent_executor=StrandsA2AExecutor(self.strands_agent),
-            task_store=InMemoryTaskStore(),
+            task_store=task_store or InMemoryTaskStore(),
+            queue_manager=queue_manager,
+            push_config_store=push_config_store,
+            push_sender=push_sender,
         )
         self._agent_skills = skills
         logger.info("Strands' integration with A2A is experimental. Be aware of frequent breaking changes.")

src/strands/tools/mcp/mcp_client.py

@@ -29,6 +29,7 @@
 from ...types.media import ImageFormat
 from ...types.tools import ToolResultContent, ToolResultStatus
 from .mcp_agent_tool import MCPAgentTool
+from .mcp_instrumentation import mcp_instrumentation
 from .mcp_types import MCPToolResult, MCPTransport
 
 logger = logging.getLogger(__name__)
@@ -68,6 +69,7 @@ def __init__(self, transport_callable: Callable[[], MCPTransport]):
         Args:
             transport_callable: A callable that returns an MCPTransport (read_stream, write_stream) tuple
         """
+        mcp_instrumentation()
         self._session_id = uuid.uuid4()
         self._log_debug_with_thread("initializing MCPClient connection")
         self._init_future: futures.Future[None] = futures.Future()  # Main thread blocks until future completes