6e95517659
* Python: Split type checkers by target (pyright source, 5 checkers on tests/samples) Rework the typing setup along the lines of the 'too many type checkers' approach: - Pyright (strict) is now the sole source-code type checker; mypy is removed from source and its [tool.mypy] block becomes a relaxed profile used only for tests/samples. - Tests are checked by all five checkers (pyright relaxed, mypy, pyrefly, ty, zuban); samples by pyright, pyrefly, and ty. All run in a relaxed/ basic profile so authors aren't forced into over-annotation. - Add pyrightconfig.tests.json and bump sample pyright configs to basic. - Unify test/sample typing onto the same parallel fan-out used by source pyright via run_command_items in task_runner.py. - Make version-conditional imports symmetric: keep or drop the '# type: ignore' on both branches so results match across interpreter versions (local vs CI). - Update SKILL.md, DEV_SETUP.md, and CODING_STANDARD.md for the five gating checkers and pyright on source+tests+samples. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Python: Fix merge regressions from main (typing + runtime) Merging main into the type-checker split branch surfaced regressions that the new five-checker test suite and unit tests caught: Runtime fixes: - anthropic: restore the dropped `cache_read_input_token_count` mapping in _parse_usage_from_anthropic (lost during merge conflict resolution). - gemini: _get_function_calling_mode test helper returned str(enum) ('FunctionCallingConfigMode.AUTO') instead of the enum value ('AUTO'). - openai: _response_id_from_token test helper was an infinite self-recursion; return token['response_id']. - orchestrations: reset output_events per approval iteration so the terminal output assertion counts only the final run. - core: drop a stale duplicate harness test whose message ('non-negative') contradicted the source ('positive'). - purview: import PolicyLocation/PolicyScope/ProtectionScopeActivities/ ExecutionMode used by the processor tests. Type-checker fixes (tests, relaxed profile): - core: pyright/mypy/pyrefly/ty/zuban green-ups across the harness, MCP, observability and types tests. - anthropic/openai: route provider-namespaced UsageDetails keys through a dict cast (extra_items TypedDict unsupported by mypy/ty). - purview: typed model constructors and cache-mock casts. - ag-ui: annotate WorkflowContext[Any, Any] so yield_output accepts test payloads, guard Optional forwarded_props, and ty-ignore intentional bad args. Source pyright (sole source checker) flagged unnecessary ignores newly introduced by merged code in core _tools.py and declarative _declarative_base.py. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Python: Isolate per-package mypy cache in test-typing fan-out The parallel test-typing fan-out runs many mypy processes concurrently, all defaulting to a single shared ./.mypy_cache. Concurrent writes corrupt the cache and mypy aborts with INTERNAL ERROR (intermittently, depending on worker timing) -- which is why CI's Test Typing job failed on a shifting set of packages while a single-package run was fine. Give each mypy invocation an isolated cache dir keyed by its target paths so incremental caching still works per package without races. Other checkers (zuban/pyrefly/ty/pyright) maintain their own caches and are unaffected. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Python: Make lab pyright-only on source (drop source mypy) Lab was the last package still running mypy on its source code, requiring mypy-only `# type: ignore` comments that pyright (the sole source checker everywhere else) flags as unnecessary. Align lab with the rest of the monorepo: - Remove the lab source mypy poe tasks (mypy-gaia/lightning/tau2) and the now-dead strict [tool.mypy] config block. - Drop the 'Run lab mypy' CI step; lab source is type-checked by pyright only. Lab tests remain covered by the workspace test-typing fan-out (mypy, pyrefly, ty, zuban, pyright over tests using the relaxed root config). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Python: Fix test-typing regressions from latest main merge A fresh merge from main brought in new test code never run under the five-checker test-typing suite. Green up across the affected packages: - core: narrow Optional span.attributes with 'and' guards in span filters and assert+cast the json.loads(...attributes[...]) reads (test_observability); match the existing as_agent ignore on the protocol-typed fixture (test_clients). - openai: align new streaming tests with the established chat_options dict pattern (ChatOptions TypedDict isn't assignable to dict), route Optional .annotations[0] access through a small _first_annotation helper (mirrors the file's assert-not-None convention), and annotate a mapped ResponseStream. - foundry_hosting: annotate error: dict[str, Any] = body.get(...) or {} (zuban needs the annotation). - foundry: narrow ignores for the live AIProjectClient credential arg (pyrefly) and connections.get_default (zuban) SDK type gaps. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * updated pyright version * pyright fix * Python: Fix source typing for pyright 1.1.410 Pyright 1.1.410 tightened several checks. Apply the same source fixes as upstream PR #6275: - anthropic: import AsyncAnthropicBedrock from anthropic.lib.bedrock and AsyncAnthropicVertex from anthropic.lib.vertex (no longer re-exported from the anthropic top-level package -> reportPrivateImportUsage). - core _types.py: cast the transform-hook result to UpdateT (reportAssignmentType). - core _workflows/_events.py: annotate the @contextmanager helper as Generator[None] instead of Iterator[None] (reportDeprecated). - redis: build the combined filter expression with an explicit loop instead of reduce(and_, ...), which pyright could no longer fully type (drops the now unused functools.reduce / operator.and_ imports). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Python: Accept plain-text body in Azure Functions workflow/run endpoint The workflow_orchestrator already accepts plain strings as well as JSON objects via context.get_input(), but the start_workflow_orchestration HTTP handler only accepted JSON and returned 400 for any non-JSON body. This made the functions integration tests that POST text/plain to /api/workflow/run (e.g. test_09_workflow_shared_state) fail consistently with 400 != 202. Fall back to the raw request body (decoded as UTF-8) when the body is not JSON, rejecting only a truly empty body. The JSON path is unchanged. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
236 lines
7.8 KiB
Python
236 lines
7.8 KiB
Python
# Copyright (c) Microsoft. All rights reserved.
|
|
|
|
import asyncio
|
|
from collections.abc import AsyncIterable, Awaitable
|
|
from typing import Any, Literal, overload
|
|
|
|
from agent_framework import (
|
|
AgentResponse,
|
|
AgentResponseUpdate,
|
|
AgentSession,
|
|
BaseAgent,
|
|
Content,
|
|
InMemoryHistoryProvider,
|
|
Message,
|
|
normalize_messages,
|
|
)
|
|
|
|
"""
|
|
Custom Agent Implementation Example
|
|
|
|
This sample demonstrates implementing a custom agent by extending BaseAgent class,
|
|
showing the minimal requirements for both streaming and non-streaming responses.
|
|
"""
|
|
|
|
|
|
class EchoAgent(BaseAgent):
|
|
"""A simple custom agent that echoes user messages with a prefix.
|
|
|
|
This demonstrates how to create a fully custom agent by extending BaseAgent
|
|
and implementing the required run() method with stream support.
|
|
"""
|
|
|
|
echo_prefix: str = "Echo: "
|
|
|
|
def __init__(
|
|
self,
|
|
*,
|
|
name: str | None = None,
|
|
description: str | None = None,
|
|
echo_prefix: str = "Echo: ",
|
|
**kwargs: Any,
|
|
) -> None:
|
|
"""Initialize the EchoAgent.
|
|
|
|
Args:
|
|
name: The name of the agent.
|
|
description: The description of the agent.
|
|
echo_prefix: The prefix to add to echoed messages.
|
|
**kwargs: Additional keyword arguments passed to BaseAgent.
|
|
"""
|
|
super().__init__(
|
|
name=name,
|
|
description=description,
|
|
**kwargs,
|
|
)
|
|
self.echo_prefix = echo_prefix
|
|
|
|
@overload
|
|
def run(
|
|
self,
|
|
messages: str | Message | list[str] | list[Message] | None = None,
|
|
*,
|
|
stream: Literal[False] = False,
|
|
session: AgentSession | None = None,
|
|
**kwargs: Any,
|
|
) -> asyncio.Future[AgentResponse]: ...
|
|
|
|
@overload
|
|
def run(
|
|
self,
|
|
messages: str | Message | list[str] | list[Message] | None = None,
|
|
*,
|
|
stream: Literal[True],
|
|
session: AgentSession | None = None,
|
|
**kwargs: Any,
|
|
) -> AsyncIterable[AgentResponseUpdate]: ...
|
|
|
|
def run(
|
|
self,
|
|
messages: str | Message | list[str] | list[Message] | None = None,
|
|
*,
|
|
stream: bool = False,
|
|
session: AgentSession | None = None,
|
|
**kwargs: Any,
|
|
) -> "AsyncIterable[AgentResponseUpdate] | Awaitable[AgentResponse]":
|
|
"""Execute the agent and return a response.
|
|
|
|
Args:
|
|
messages: The message(s) to process.
|
|
stream: If True, return an async iterable of updates. If False, return an awaitable response.
|
|
session: The conversation session (optional).
|
|
**kwargs: Additional keyword arguments.
|
|
|
|
Returns:
|
|
When stream=False: An awaitable AgentResponse containing the agent's reply.
|
|
When stream=True: An async iterable of AgentResponseUpdate objects.
|
|
"""
|
|
if stream:
|
|
return self._run_stream(messages=messages, session=session, **kwargs)
|
|
return self._run(messages=messages, session=session, **kwargs)
|
|
|
|
async def _run(
|
|
self,
|
|
messages: str | Message | list[str] | list[Message] | None = None,
|
|
*,
|
|
session: AgentSession | None = None,
|
|
**kwargs: Any,
|
|
) -> AgentResponse:
|
|
"""Non-streaming implementation."""
|
|
# Normalize input messages to a list
|
|
normalized_messages = normalize_messages(messages)
|
|
|
|
if not normalized_messages:
|
|
response_message = Message(
|
|
role="assistant",
|
|
contents=[
|
|
Content.from_text(text="Hello! I'm a custom echo agent. Send me a message and I'll echo it back.")
|
|
],
|
|
)
|
|
else:
|
|
# For simplicity, echo the last user message
|
|
last_message = normalized_messages[-1]
|
|
if last_message.text:
|
|
echo_text = f"{self.echo_prefix}{last_message.text}"
|
|
else:
|
|
echo_text = f"{self.echo_prefix}[Non-text message received]"
|
|
|
|
response_message = Message(role="assistant", contents=[Content.from_text(text=echo_text)])
|
|
|
|
# Store messages in session state if provided
|
|
if session is not None:
|
|
stored = session.state.setdefault(InMemoryHistoryProvider.DEFAULT_SOURCE_ID, {}).setdefault("messages", [])
|
|
stored.extend(normalized_messages)
|
|
stored.append(response_message)
|
|
|
|
return AgentResponse(messages=[response_message])
|
|
|
|
async def _run_stream(
|
|
self,
|
|
messages: str | Message | list[str] | list[Message] | None = None,
|
|
*,
|
|
session: AgentSession | None = None,
|
|
**kwargs: Any,
|
|
) -> AsyncIterable[AgentResponseUpdate]:
|
|
"""Streaming implementation."""
|
|
# Normalize input messages to a list
|
|
normalized_messages = normalize_messages(messages)
|
|
|
|
if not normalized_messages:
|
|
response_text = "Hello! I'm a custom echo agent. Send me a message and I'll echo it back."
|
|
else:
|
|
# For simplicity, echo the last user message
|
|
last_message = normalized_messages[-1]
|
|
if last_message.text:
|
|
response_text = f"{self.echo_prefix}{last_message.text}"
|
|
else:
|
|
response_text = f"{self.echo_prefix}[Non-text message received]"
|
|
|
|
# Simulate streaming by yielding the response word by word
|
|
words = response_text.split()
|
|
for i, word in enumerate(words):
|
|
# Add space before word except for the first one
|
|
chunk_text = f" {word}" if i > 0 else word
|
|
|
|
yield AgentResponseUpdate(
|
|
contents=[Content.from_text(text=chunk_text)],
|
|
role="assistant",
|
|
)
|
|
|
|
# Small delay to simulate streaming
|
|
await asyncio.sleep(0.1)
|
|
|
|
# Store messages in session state if provided
|
|
if session is not None:
|
|
complete_response = Message(role="assistant", contents=[Content.from_text(text=response_text)])
|
|
stored = session.state.setdefault(InMemoryHistoryProvider.DEFAULT_SOURCE_ID, {}).setdefault("messages", [])
|
|
stored.extend(normalized_messages)
|
|
stored.append(complete_response)
|
|
|
|
|
|
async def main() -> None:
|
|
"""Demonstrates how to use the custom EchoAgent."""
|
|
print("=== Custom Agent Example ===\n")
|
|
|
|
# Create EchoAgent
|
|
print("--- EchoAgent Example ---")
|
|
echo_agent = EchoAgent(
|
|
name="EchoBot", description="A simple agent that echoes messages with a prefix", echo_prefix="🔊 Echo: "
|
|
)
|
|
|
|
# Test non-streaming
|
|
print(f"Agent Name: {echo_agent.name}")
|
|
print(f"Agent ID: {echo_agent.id}")
|
|
|
|
query = "Hello, custom agent!"
|
|
print(f"\nUser: {query}")
|
|
result = await echo_agent.run(query)
|
|
print(f"Agent: {result.messages[0].text}")
|
|
|
|
# Test streaming
|
|
query2 = "This is a streaming test"
|
|
print(f"\nUser: {query2}")
|
|
print("Agent: ", end="", flush=True)
|
|
stream = echo_agent.run(query2, stream=True)
|
|
assert isinstance(stream, AsyncIterable)
|
|
async for chunk in stream:
|
|
if chunk.text:
|
|
print(chunk.text, end="", flush=True)
|
|
print()
|
|
|
|
# Example with sessions
|
|
print("\n--- Using Custom Agent with Session ---")
|
|
session = echo_agent.create_session()
|
|
|
|
# First message
|
|
result1 = await echo_agent.run("First message", session=session)
|
|
print("User: First message")
|
|
print(f"Agent: {result1.messages[0].text}")
|
|
|
|
# Second message in same thread
|
|
result2 = await echo_agent.run("Second message", session=session)
|
|
print("User: Second message")
|
|
print(f"Agent: {result2.messages[0].text}")
|
|
|
|
# Check conversation history
|
|
memory_state = session.state.get(InMemoryHistoryProvider.DEFAULT_SOURCE_ID, {})
|
|
messages = memory_state.get("messages", [])
|
|
if messages:
|
|
print(f"\nSession contains {len(messages)} messages in history")
|
|
else:
|
|
print("\nSession has no messages stored")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(main())
|