mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
Compare commits
5
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
  Evan MattsonandGitHub
|
f5419b9f38 | ||
 Tao ChenandGitHub
|
03e47b5232 | ||
|
Evan MattsonandGitHub
|
46ab47b9e1 | ||
|
Evan MattsonandGitHub
|
094f9903b3 | ||
  
|
8b71f9459a |
+17
-1
@@ -7,6 +7,21 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
## [1.2.2] - 2026-04-29
|
||||
|
||||
### Added
|
||||
- **agent-framework-azure-contentunderstanding**: New alpha package — Azure AI Content Understanding context provider that auto-analyzes file attachments (documents, images, audio, video) and injects structured results into the LLM context, with multi-document session state, configurable timeout, output filtering via `AnalysisSection`, and auto-registered `list_documents` / `get_analyzed_document` tools ([#4829](https://github.com/microsoft/agent-framework/pull/4829))
|
||||
- **agent-framework-foundry-hosting**: Add hosted Durable Workflow support — propagate full conversation history to workflow agents and wire `Workflow.as_agent()` end-to-end via the foundry hosting layer ([#5531](https://github.com/microsoft/agent-framework/pull/5531))
|
||||
|
||||
### Changed
|
||||
- **agent-framework-orchestrations**: [BREAKING] Standardize orchestration terminal outputs as `AgentResponse` so `Workflow.as_agent()` returns the final answer only; aligns sequential-approval (`with_request_info`) and concurrent (`intermediate_outputs=True`) flows on the same output contract ([#5301](https://github.com/microsoft/agent-framework/pull/5301))
|
||||
- **agent-framework-core**, **agent-framework-declarative**: Preserve `Workflow.run()` shared state across calls so multi-turn `WorkflowAgent` invocations retain context, accept `list[Message]` input in the declarative start executor, and coerce `Enum` values when serializing PowerFx symbols ([#5531](https://github.com/microsoft/agent-framework/pull/5531))
|
||||
- **dependencies**: Update workspace package dependencies and preserve `mcp[ws]` / `uvicorn[standard]` extras through override-dependencies in `/python` ([#5555](https://github.com/microsoft/agent-framework/pull/5555))
|
||||
|
||||
### Fixed
|
||||
- **agent-framework-core**: Fix observability spans not being correctly nested when using streaming ([#5552](https://github.com/microsoft/agent-framework/pull/5552))
|
||||
- **agent-framework-openai**: Fix `file_search` citations breaking the assistant-message history roundtrip — skip `hosted_file` content in the assistant role so the Responses API no longer rejects `input_file` ([#5557](https://github.com/microsoft/agent-framework/pull/5557))
|
||||
|
||||
## [1.2.1] - 2026-04-28
|
||||
|
||||
### Added
|
||||
@@ -1003,7 +1018,8 @@ Release candidate for **agent-framework-core** and **agent-framework-azure-ai**
|
||||
|
||||
For more information, see the [announcement blog post](https://devblogs.microsoft.com/foundry/introducing-microsoft-agent-framework-the-open-source-engine-for-agentic-ai-apps/).
|
||||
|
||||
[Unreleased]: https://github.com/microsoft/agent-framework/compare/python-1.2.1...HEAD
|
||||
[Unreleased]: https://github.com/microsoft/agent-framework/compare/python-1.2.2...HEAD
|
||||
[1.2.2]: https://github.com/microsoft/agent-framework/compare/python-1.2.1...python-1.2.2
|
||||
[1.2.1]: https://github.com/microsoft/agent-framework/compare/python-1.2.0...python-1.2.1
|
||||
[1.2.0]: https://github.com/microsoft/agent-framework/compare/python-1.1.1...python-1.2.0
|
||||
[1.1.1]: https://github.com/microsoft/agent-framework/compare/python-1.1.0...python-1.1.1
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "A2A integration for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,7 +23,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"a2a-sdk>=0.3.5,<0.3.24",
|
||||
]
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[project]
|
||||
name = "agent-framework-ag-ui"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
description = "AG-UI protocol integration for Agent Framework"
|
||||
readme = "README.md"
|
||||
license-files = ["LICENSE"]
|
||||
@@ -22,7 +22,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"ag-ui-protocol>=0.1.16,<0.2",
|
||||
"fastapi>=0.115.0,<0.133.1",
|
||||
"uvicorn[standard]>=0.30.0,<0.42.0"
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Anthropic integration for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,7 +23,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"anthropic>=0.80.0,<0.80.1",
|
||||
]
|
||||
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Azure AI Search integration for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,7 +23,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"azure-search-documents>=11.7.0b2,<11.7.0b3",
|
||||
]
|
||||
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Azure Content Understanding integration for Microsoft Agent Frame
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com" }]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0a260401"
|
||||
version = "1.0.0a260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,8 +23,9 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.0.0,<2",
|
||||
"azure-ai-contentunderstanding>=1.0.0,<1.1",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"agent-framework-foundry>=1.2.2,<2",
|
||||
"azure-ai-contentunderstanding>=1.0.1,<1.1",
|
||||
"aiohttp>=3.9,<4",
|
||||
"filetype>=1.2,<2",
|
||||
]
|
||||
|
||||
@@ -15,12 +15,10 @@ import os
|
||||
from pathlib import Path
|
||||
|
||||
from agent_framework import Agent, Content, Message
|
||||
from agent_framework.foundry import FoundryChatClient
|
||||
from agent_framework.foundry import ContentUnderstandingContextProvider, FoundryChatClient
|
||||
from azure.identity import AzureCliCredential
|
||||
from dotenv import load_dotenv
|
||||
|
||||
from agent_framework.foundry import ContentUnderstandingContextProvider
|
||||
|
||||
load_dotenv()
|
||||
|
||||
"""
|
||||
|
||||
+1
-3
@@ -15,12 +15,10 @@ import os
|
||||
from pathlib import Path
|
||||
|
||||
from agent_framework import Agent, AgentSession, Content, Message
|
||||
from agent_framework.foundry import FoundryChatClient
|
||||
from agent_framework.foundry import ContentUnderstandingContextProvider, FoundryChatClient
|
||||
from azure.identity import AzureCliCredential
|
||||
from dotenv import load_dotenv
|
||||
|
||||
from agent_framework.foundry import ContentUnderstandingContextProvider
|
||||
|
||||
load_dotenv()
|
||||
|
||||
"""
|
||||
|
||||
+1
-3
@@ -16,12 +16,10 @@ import time
|
||||
from pathlib import Path
|
||||
|
||||
from agent_framework import Agent, AgentSession, Content, Message
|
||||
from agent_framework.foundry import FoundryChatClient
|
||||
from agent_framework.foundry import ContentUnderstandingContextProvider, FoundryChatClient
|
||||
from azure.identity import AzureCliCredential
|
||||
from dotenv import load_dotenv
|
||||
|
||||
from agent_framework.foundry import ContentUnderstandingContextProvider
|
||||
|
||||
load_dotenv()
|
||||
|
||||
"""
|
||||
|
||||
+1
-3
@@ -16,13 +16,11 @@ import os
|
||||
from pathlib import Path
|
||||
|
||||
from agent_framework import Agent, AgentSession, Content, Message
|
||||
from agent_framework.foundry import FoundryChatClient
|
||||
from agent_framework.foundry import ContentUnderstandingContextProvider, FoundryChatClient
|
||||
from azure.identity import AzureCliCredential
|
||||
from dotenv import load_dotenv
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from agent_framework.foundry import ContentUnderstandingContextProvider
|
||||
|
||||
load_dotenv()
|
||||
|
||||
"""
|
||||
|
||||
+1
-3
@@ -21,13 +21,11 @@ Run with DevUI:
|
||||
import os
|
||||
|
||||
from agent_framework import Agent
|
||||
from agent_framework.foundry import FoundryChatClient
|
||||
from agent_framework.foundry import ContentUnderstandingContextProvider, FoundryChatClient
|
||||
from azure.core.credentials import AzureKeyCredential
|
||||
from azure.identity import AzureCliCredential
|
||||
from dotenv import load_dotenv
|
||||
|
||||
from agent_framework.foundry import ContentUnderstandingContextProvider
|
||||
|
||||
load_dotenv()
|
||||
|
||||
# --- Auth ---
|
||||
|
||||
+5
-6
@@ -32,17 +32,16 @@ Run with DevUI:
|
||||
import os
|
||||
|
||||
from agent_framework import Agent
|
||||
from agent_framework.foundry import FoundryChatClient
|
||||
from agent_framework.foundry import (
|
||||
ContentUnderstandingContextProvider,
|
||||
FileSearchConfig,
|
||||
FoundryChatClient,
|
||||
)
|
||||
from azure.core.credentials import AzureKeyCredential
|
||||
from azure.identity import AzureCliCredential
|
||||
from dotenv import load_dotenv
|
||||
from openai import AzureOpenAI
|
||||
|
||||
from agent_framework.foundry import (
|
||||
ContentUnderstandingContextProvider,
|
||||
FileSearchConfig,
|
||||
)
|
||||
|
||||
load_dotenv()
|
||||
|
||||
# --- Auth ---
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Azure Cosmos DB history provider integration for Microsoft Agent
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,7 +23,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"azure-cosmos>=4.3.0,<5",
|
||||
]
|
||||
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Azure Functions integration for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -22,7 +22,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"agent-framework-durabletask",
|
||||
"azure-functions>=1.24.0,<2",
|
||||
"azure-functions-durable>=1.3.1,<2",
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Amazon Bedrock integration for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,7 +23,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"boto3>=1.35.0,<2.0.0",
|
||||
"botocore>=1.35.0,<2.0.0",
|
||||
]
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "OpenAI ChatKit integration for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -22,7 +22,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"openai-chatkit>=1.4.1,<2.0.0",
|
||||
]
|
||||
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Claude Agent SDK integration for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,7 +23,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"claude-agent-sdk>=0.1.36,<0.1.49",
|
||||
]
|
||||
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Copilot Studio integration for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,7 +23,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"microsoft-agents-copilotstudio-client>=0.3.1,<0.3.2",
|
||||
]
|
||||
|
||||
|
||||
@@ -3,6 +3,7 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import base64
|
||||
import contextlib
|
||||
import json
|
||||
import logging
|
||||
import re
|
||||
@@ -2890,6 +2891,7 @@ class ResponseStream(AsyncIterable[UpdateT], Generic[UpdateT, FinalT]):
|
||||
self._inner_stream_source: ResponseStream[Any, Any] | Awaitable[ResponseStream[Any, Any]] | None = None
|
||||
self._wrap_inner: bool = False
|
||||
self._map_update: Callable[[Any], UpdateT | Awaitable[UpdateT]] | None = None
|
||||
self._pull_context_manager_factories: list[Callable[[], contextlib.AbstractContextManager[Any]]] = []
|
||||
|
||||
def map(
|
||||
self,
|
||||
@@ -3008,11 +3010,18 @@ class ResponseStream(AsyncIterable[UpdateT], Generic[UpdateT, FinalT]):
|
||||
return self
|
||||
|
||||
async def __anext__(self) -> UpdateT:
|
||||
if self._iterator is None:
|
||||
stream = await self._get_stream()
|
||||
self._iterator = stream.__aiter__()
|
||||
try:
|
||||
update: UpdateT = await self._iterator.__anext__()
|
||||
with contextlib.ExitStack() as stack:
|
||||
for factory in self._pull_context_manager_factories:
|
||||
stack.enter_context(factory())
|
||||
# Resolve the underlying stream inside the pull contexts so that any
|
||||
# spans/contexts created during stream resolution (e.g. inner chat
|
||||
# completion spans created on the first pull of a wrapped agent stream)
|
||||
# inherit the active context (e.g. an outer agent invoke span).
|
||||
if self._iterator is None:
|
||||
stream = await self._get_stream()
|
||||
self._iterator = stream.__aiter__()
|
||||
update: UpdateT = await self._iterator.__anext__()
|
||||
except StopAsyncIteration:
|
||||
self._consumed = True
|
||||
await self._run_cleanup_hooks()
|
||||
@@ -3038,9 +3047,25 @@ class ResponseStream(AsyncIterable[UpdateT], Generic[UpdateT, FinalT]):
|
||||
update = hooked
|
||||
return update
|
||||
|
||||
async def _resolve_stream_with_pull_contexts(self) -> AsyncIterable[UpdateT]:
|
||||
"""Resolve the underlying stream while activating any registered pull context managers.
|
||||
|
||||
Used by ``__await__`` and ``get_final_response`` so that any spans/contexts created
|
||||
during stream resolution (e.g. when the source is an Awaitable that internally
|
||||
creates child telemetry spans) inherit the same active context as iterator pulls.
|
||||
``__anext__`` resolves the stream inside its own ExitStack and so calls ``_get_stream``
|
||||
directly.
|
||||
"""
|
||||
if self._stream is not None:
|
||||
return await self._get_stream()
|
||||
with contextlib.ExitStack() as stack:
|
||||
for factory in self._pull_context_manager_factories:
|
||||
stack.enter_context(factory())
|
||||
return await self._get_stream()
|
||||
|
||||
def __await__(self) -> Any:
|
||||
async def _wrap() -> ResponseStream[UpdateT, FinalT]:
|
||||
await self._get_stream()
|
||||
await self._resolve_stream_with_pull_contexts()
|
||||
return self
|
||||
|
||||
return _wrap().__await__()
|
||||
@@ -3064,10 +3089,12 @@ class ResponseStream(AsyncIterable[UpdateT], Generic[UpdateT, FinalT]):
|
||||
"""
|
||||
if self._wrap_inner:
|
||||
if self._inner_stream is None:
|
||||
# Use _get_stream() to resolve the awaitable - this properly handles
|
||||
# Use _resolve_stream_with_pull_contexts() so that any spans/contexts
|
||||
# created while resolving the awaitable (e.g. inner telemetry spans)
|
||||
# inherit the same active context as iterator pulls. This also handles
|
||||
# the case where _stream_source and _inner_stream_source are the same
|
||||
# coroutine (e.g., from from_awaitable), avoiding double-await errors.
|
||||
await self._get_stream()
|
||||
await self._resolve_stream_with_pull_contexts()
|
||||
if self._inner_stream is None:
|
||||
raise RuntimeError("Inner stream not available")
|
||||
if not self._finalized and not self._consumed:
|
||||
@@ -3177,6 +3204,25 @@ class ResponseStream(AsyncIterable[UpdateT], Generic[UpdateT, FinalT]):
|
||||
self._cleanup_hooks.append(hook)
|
||||
return self
|
||||
|
||||
def with_pull_context_manager(
|
||||
self,
|
||||
cm_factory: Callable[[], contextlib.AbstractContextManager[Any]],
|
||||
) -> ResponseStream[UpdateT, FinalT]:
|
||||
"""Register a context manager factory invoked around each underlying iterator pull.
|
||||
|
||||
The factory is called once per ``__anext__`` and the returned context manager wraps
|
||||
the await of the underlying iterator. This is useful for state that needs to be
|
||||
active while the inner async work runs - for example, attaching an OpenTelemetry
|
||||
span to the current context so child spans created by inner code (HTTP clients,
|
||||
tool execution) are correctly parented.
|
||||
|
||||
Because the context manager is entered and exited within the same ``__anext__``
|
||||
invocation, attach/detach style operations remain symmetric in the same async
|
||||
context regardless of where the stream is iterated.
|
||||
"""
|
||||
self._pull_context_manager_factories.append(cm_factory)
|
||||
return self
|
||||
|
||||
async def _run_cleanup_hooks(self) -> None:
|
||||
if self._cleanup_run:
|
||||
return
|
||||
|
||||
@@ -622,9 +622,7 @@ class Workflow(DictConvertible):
|
||||
"checkpointing; there is no in-process recovery path."
|
||||
)
|
||||
|
||||
initial_executor_fn = self._resolve_execution_mode(
|
||||
message, responses, checkpoint_id, checkpoint_storage
|
||||
)
|
||||
initial_executor_fn = self._resolve_execution_mode(message, responses, checkpoint_id, checkpoint_storage)
|
||||
|
||||
async for event in self._run_workflow_with_tracing(
|
||||
initial_executor_fn=initial_executor_fn,
|
||||
@@ -724,9 +722,7 @@ class Workflow(DictConvertible):
|
||||
initial_executor_fn = functools.partial(self._send_responses_internal, responses)
|
||||
return initial_executor_fn
|
||||
# Regular run or checkpoint restoration
|
||||
return functools.partial(
|
||||
self._execute_with_message_or_checkpoint, message, checkpoint_id, checkpoint_storage
|
||||
)
|
||||
return functools.partial(self._execute_with_message_or_checkpoint, message, checkpoint_id, checkpoint_storage)
|
||||
|
||||
async def _restore_and_send_responses(
|
||||
self,
|
||||
|
||||
@@ -15,7 +15,10 @@ from typing import Any
|
||||
_IMPORTS: dict[str, tuple[str, str]] = {
|
||||
"AnalysisSection": ("agent_framework_azure_contentunderstanding", "agent-framework-azure-contentunderstanding"),
|
||||
"AnthropicFoundryClient": ("agent_framework_anthropic", "agent-framework-anthropic"),
|
||||
"ContentUnderstandingContextProvider": ("agent_framework_azure_contentunderstanding", "agent-framework-azure-contentunderstanding"),
|
||||
"ContentUnderstandingContextProvider": (
|
||||
"agent_framework_azure_contentunderstanding",
|
||||
"agent-framework-azure-contentunderstanding",
|
||||
),
|
||||
"DocumentStatus": ("agent_framework_azure_contentunderstanding", "agent-framework-azure-contentunderstanding"),
|
||||
"FileSearchBackend": ("agent_framework_azure_contentunderstanding", "agent-framework-azure-contentunderstanding"),
|
||||
"FileSearchConfig": ("agent_framework_azure_contentunderstanding", "agent-framework-azure-contentunderstanding"),
|
||||
|
||||
@@ -4,12 +4,12 @@
|
||||
# Install the relevant packages for full type support.
|
||||
|
||||
from agent_framework_anthropic import AnthropicFoundryClient, RawAnthropicFoundryClient
|
||||
from agent_framework_azure_contentunderstanding import (
|
||||
AnalysisSection,
|
||||
ContentUnderstandingContextProvider,
|
||||
DocumentStatus,
|
||||
FileSearchBackend,
|
||||
FileSearchConfig,
|
||||
from agent_framework_azure_contentunderstanding import ( # pyright: ignore[reportMissingImports]
|
||||
AnalysisSection, # pyright: ignore[reportUnknownVariableType]
|
||||
ContentUnderstandingContextProvider, # pyright: ignore[reportUnknownVariableType]
|
||||
DocumentStatus, # pyright: ignore[reportUnknownVariableType]
|
||||
FileSearchBackend, # pyright: ignore[reportUnknownVariableType]
|
||||
FileSearchConfig, # pyright: ignore[reportUnknownVariableType]
|
||||
)
|
||||
from agent_framework_foundry import (
|
||||
FoundryAgent,
|
||||
|
||||
@@ -26,6 +26,7 @@ from time import perf_counter, time_ns
|
||||
from typing import TYPE_CHECKING, Any, ClassVar, Final, Generic, Literal, TypedDict, cast, overload
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from opentelemetry import context as otel_context
|
||||
from opentelemetry import metrics, trace
|
||||
|
||||
from . import __version__ as version_info
|
||||
@@ -1277,27 +1278,8 @@ class ChatTelemetryLayer(Generic[OptionsCoT]):
|
||||
)
|
||||
|
||||
if stream:
|
||||
result_stream = cast(
|
||||
ResponseStream[ChatResponseUpdate, ChatResponse[Any]],
|
||||
super_get_response(
|
||||
messages=messages,
|
||||
stream=True,
|
||||
options=opts,
|
||||
compaction_strategy=compaction_strategy,
|
||||
tokenizer=tokenizer,
|
||||
function_invocation_kwargs=function_invocation_kwargs,
|
||||
client_kwargs=merged_client_kwargs,
|
||||
),
|
||||
)
|
||||
span = _start_streaming_span(attributes, OtelAttr.REQUEST_MODEL)
|
||||
|
||||
# Create span directly without trace.use_span() context attachment.
|
||||
# Streaming spans are closed asynchronously in cleanup hooks, which run
|
||||
# in a different async context than creation — using use_span() would
|
||||
# cause "Failed to detach context" errors from OpenTelemetry.
|
||||
operation = attributes.get(OtelAttr.OPERATION, "operation")
|
||||
span_name = attributes.get(OtelAttr.REQUEST_MODEL, "unknown")
|
||||
span = get_tracer().start_span(f"{operation} {span_name}")
|
||||
span.set_attributes(attributes)
|
||||
if OBSERVABILITY_SETTINGS.SENSITIVE_DATA_ENABLED and messages:
|
||||
_capture_messages(
|
||||
span=span,
|
||||
@@ -1319,6 +1301,24 @@ class ChatTelemetryLayer(Generic[OptionsCoT]):
|
||||
def _record_duration() -> None:
|
||||
duration_state["duration"] = perf_counter() - start_time
|
||||
|
||||
try:
|
||||
result_stream = cast(
|
||||
ResponseStream[ChatResponseUpdate, ChatResponse[Any]],
|
||||
super_get_response(
|
||||
messages=messages,
|
||||
stream=True,
|
||||
options=opts,
|
||||
compaction_strategy=compaction_strategy,
|
||||
tokenizer=tokenizer,
|
||||
function_invocation_kwargs=function_invocation_kwargs,
|
||||
client_kwargs=merged_client_kwargs,
|
||||
),
|
||||
)
|
||||
except Exception as exception:
|
||||
capture_exception(span=span, exception=exception, timestamp=time_ns())
|
||||
_close_span()
|
||||
raise
|
||||
|
||||
async def _finalize_stream() -> None:
|
||||
from ._types import ChatResponse
|
||||
|
||||
@@ -1357,11 +1357,18 @@ class ChatTelemetryLayer(Generic[OptionsCoT]):
|
||||
finally:
|
||||
_close_span()
|
||||
|
||||
# Register a weak reference callback to close the span if stream is garbage collected
|
||||
# without being consumed. This ensures spans don't leak if users don't consume streams.
|
||||
wrapped_stream: ResponseStream[ChatResponseUpdate, ChatResponse[Any]] = result_stream.with_cleanup_hook(
|
||||
_record_duration
|
||||
).with_cleanup_hook(_finalize_stream)
|
||||
# The pull context manager attaches the span around each underlying iterator pull so
|
||||
# that child spans created during the pull (e.g. HTTP requests, inner tool execution)
|
||||
# are parented under this chat span. Attach and detach happen in the same async
|
||||
# context as the pull, avoiding cross-context cleanup issues. The weakref finalizer
|
||||
# ensures the span is closed even if the stream is garbage collected without being
|
||||
# consumed.
|
||||
wrapped_stream: ResponseStream[ChatResponseUpdate, ChatResponse[Any]] = (
|
||||
result_stream
|
||||
.with_cleanup_hook(_record_duration)
|
||||
.with_cleanup_hook(_finalize_stream)
|
||||
.with_pull_context_manager(lambda: _activate_span(span))
|
||||
)
|
||||
weakref.finalize(wrapped_stream, _close_span)
|
||||
return wrapped_stream
|
||||
|
||||
@@ -1543,23 +1550,8 @@ class AgentTelemetryLayer:
|
||||
inner_accumulated_usage_token = INNER_ACCUMULATED_USAGE.set({})
|
||||
|
||||
if stream:
|
||||
try:
|
||||
run_result: object = execute()
|
||||
if isinstance(run_result, ResponseStream):
|
||||
result_stream: ResponseStream[AgentResponseUpdate, AgentResponse[Any]] = run_result # pyright: ignore[reportUnknownVariableType]
|
||||
elif isinstance(run_result, Awaitable):
|
||||
result_stream = ResponseStream.from_awaitable(run_result) # type: ignore[arg-type] # pyright: ignore[reportArgumentType]
|
||||
else:
|
||||
raise RuntimeError("Streaming telemetry requires a ResponseStream result.")
|
||||
except Exception:
|
||||
INNER_RESPONSE_TELEMETRY_CAPTURED_FIELDS.reset(inner_response_telemetry_captured_fields_token)
|
||||
INNER_ACCUMULATED_USAGE.reset(inner_accumulated_usage_token)
|
||||
raise
|
||||
span = _start_streaming_span(attributes, OtelAttr.AGENT_NAME)
|
||||
|
||||
operation = attributes.get(OtelAttr.OPERATION, "operation")
|
||||
span_name = attributes.get(OtelAttr.AGENT_NAME, "unknown")
|
||||
span = get_tracer().start_span(f"{operation} {span_name}")
|
||||
span.set_attributes(attributes)
|
||||
if OBSERVABILITY_SETTINGS.SENSITIVE_DATA_ENABLED and messages:
|
||||
_capture_messages(
|
||||
span=span,
|
||||
@@ -1581,6 +1573,21 @@ class AgentTelemetryLayer:
|
||||
def _record_duration() -> None:
|
||||
duration_state["duration"] = perf_counter() - start_time
|
||||
|
||||
try:
|
||||
run_result: object = execute()
|
||||
if isinstance(run_result, ResponseStream):
|
||||
result_stream: ResponseStream[AgentResponseUpdate, AgentResponse[Any]] = run_result # pyright: ignore[reportUnknownVariableType]
|
||||
elif isinstance(run_result, Awaitable):
|
||||
result_stream = ResponseStream.from_awaitable(run_result) # type: ignore[arg-type] # pyright: ignore[reportArgumentType]
|
||||
else:
|
||||
raise RuntimeError("Streaming telemetry requires a ResponseStream result.")
|
||||
except Exception as exception:
|
||||
capture_exception(span=span, exception=exception, timestamp=time_ns())
|
||||
INNER_RESPONSE_TELEMETRY_CAPTURED_FIELDS.reset(inner_response_telemetry_captured_fields_token)
|
||||
INNER_ACCUMULATED_USAGE.reset(inner_accumulated_usage_token)
|
||||
_close_span()
|
||||
raise
|
||||
|
||||
async def _finalize_stream() -> None:
|
||||
from ._types import AgentResponse
|
||||
|
||||
@@ -1620,9 +1627,18 @@ class AgentTelemetryLayer:
|
||||
INNER_ACCUMULATED_USAGE.reset(inner_accumulated_usage_token)
|
||||
_close_span()
|
||||
|
||||
wrapped_stream: ResponseStream[AgentResponseUpdate, AgentResponse[Any]] = result_stream.with_cleanup_hook(
|
||||
_record_duration
|
||||
).with_cleanup_hook(_finalize_stream)
|
||||
# The pull context manager attaches the span around each underlying iterator pull so
|
||||
# that child spans created during the pull (e.g. inner chat completion spans from the
|
||||
# underlying ChatTelemetryLayer) are parented under this agent invoke span. Attach and
|
||||
# detach happen in the same async context as the pull, avoiding cross-context cleanup
|
||||
# issues. The weakref finalizer ensures the span is closed even if the stream is
|
||||
# garbage collected without being consumed.
|
||||
wrapped_stream: ResponseStream[AgentResponseUpdate, AgentResponse[Any]] = (
|
||||
result_stream
|
||||
.with_cleanup_hook(_record_duration)
|
||||
.with_cleanup_hook(_finalize_stream)
|
||||
.with_pull_context_manager(lambda: _activate_span(span))
|
||||
)
|
||||
weakref.finalize(wrapped_stream, _close_span)
|
||||
return wrapped_stream
|
||||
|
||||
@@ -1809,6 +1825,27 @@ def get_function_span(
|
||||
)
|
||||
|
||||
|
||||
@contextlib.contextmanager
|
||||
def _activate_span(span: trace.Span) -> Generator[None]:
|
||||
"""Attach ``span`` as the current span in the OpenTelemetry context.
|
||||
|
||||
Designed to be used as a per-pull context manager registered on a
|
||||
``ResponseStream`` via ``with_pull_context_manager``: it attaches the span
|
||||
before each underlying iterator pull and detaches immediately after, so
|
||||
child spans created during the pull (HTTP clients, inner chat completions,
|
||||
tool execution) are correctly parented under ``span``.
|
||||
|
||||
Because attach and detach happen within the same ``__anext__`` invocation
|
||||
(and therefore the same async task / contextvars context), there is no risk
|
||||
of "Failed to detach context" warnings from cross-context cleanup.
|
||||
"""
|
||||
token = otel_context.attach(trace.set_span_in_context(span))
|
||||
try:
|
||||
yield
|
||||
finally:
|
||||
otel_context.detach(token)
|
||||
|
||||
|
||||
@contextlib.contextmanager
|
||||
def _get_span(
|
||||
attributes: dict[str, Any],
|
||||
@@ -1831,6 +1868,29 @@ def _get_span(
|
||||
yield current_span
|
||||
|
||||
|
||||
def _start_streaming_span(attributes: dict[str, Any], span_name_attribute: str) -> trace.Span:
|
||||
"""Start a non-current span for a streaming operation.
|
||||
|
||||
Unlike :func:`_get_span`, the returned span is not attached to the current
|
||||
OpenTelemetry context. The caller is responsible for:
|
||||
|
||||
- Ending the span via cleanup hooks on the wrapped
|
||||
:class:`~agent_framework._types.ResponseStream`.
|
||||
- Activating the span around each iterator pull via
|
||||
:func:`_activate_span` registered with ``with_pull_context_manager`` so
|
||||
that child spans created during stream production inherit it as parent.
|
||||
|
||||
Streaming spans are closed asynchronously in cleanup hooks that run in a
|
||||
different async context than creation, so attaching the span at creation
|
||||
time would cause "Failed to detach context" errors from OpenTelemetry.
|
||||
"""
|
||||
operation = attributes.get(OtelAttr.OPERATION, "operation")
|
||||
span_name = attributes.get(span_name_attribute, "unknown")
|
||||
span = get_tracer().start_span(f"{operation} {span_name}")
|
||||
span.set_attributes(attributes)
|
||||
return span
|
||||
|
||||
|
||||
def _get_instructions_from_options(options: Any) -> str | list[str] | None:
|
||||
"""Extract instructions from options dict."""
|
||||
if options is None:
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Microsoft Agent Framework for building AI Agents with Python. Thi
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.2.1"
|
||||
version = "1.2.2"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
|
||||
@@ -3313,3 +3313,487 @@ async def test_agent_invoke_span_aggregates_usage_on_max_iterations_exhaustion(s
|
||||
# The invoke_agent span must aggregate usage from the in-loop call and the final exhaustion call
|
||||
assert agent_span.attributes.get(OtelAttr.INPUT_TOKENS) == 500
|
||||
assert agent_span.attributes.get(OtelAttr.OUTPUT_TOKENS) == 100
|
||||
|
||||
|
||||
# region Test span nesting (parent-child relationships)
|
||||
|
||||
|
||||
@pytest.mark.parametrize("stream", [False, True])
|
||||
async def test_chat_span_nested_under_agent_span(span_exporter: InMemorySpanExporter, stream: bool):
|
||||
"""The inner chat span must be a child of the outer agent invoke span."""
|
||||
|
||||
class NestedChatClient(ChatTelemetryLayer, BaseChatClient[Any]):
|
||||
def service_url(self):
|
||||
return "https://test.example.com"
|
||||
|
||||
def _inner_get_response(
|
||||
self, *, messages: MutableSequence[Message], stream: bool, options: dict[str, Any], **kwargs: Any
|
||||
) -> Awaitable[ChatResponse] | ResponseStream[ChatResponseUpdate, ChatResponse]:
|
||||
if stream:
|
||||
|
||||
async def _stream() -> AsyncIterable[ChatResponseUpdate]:
|
||||
yield ChatResponseUpdate(contents=[Content.from_text("Hello")], role="assistant")
|
||||
yield ChatResponseUpdate(
|
||||
contents=[Content.from_text(" world")], role="assistant", finish_reason="stop"
|
||||
)
|
||||
|
||||
def _finalize(updates: Sequence[ChatResponseUpdate]) -> ChatResponse:
|
||||
return ChatResponse(
|
||||
messages=[Message(role="assistant", contents=["Hello world"])],
|
||||
response_id="resp_1",
|
||||
usage_details=UsageDetails(input_token_count=3, output_token_count=4),
|
||||
finish_reason="stop",
|
||||
)
|
||||
|
||||
return ResponseStream(_stream(), finalizer=_finalize)
|
||||
|
||||
async def _get() -> ChatResponse:
|
||||
return ChatResponse(
|
||||
messages=[Message(role="assistant", contents=["Hello world"])],
|
||||
response_id="resp_1",
|
||||
usage_details=UsageDetails(input_token_count=3, output_token_count=4),
|
||||
finish_reason="stop",
|
||||
)
|
||||
|
||||
return _get()
|
||||
|
||||
agent = Agent(
|
||||
client=NestedChatClient(),
|
||||
id="nested_agent_id",
|
||||
name="nested_agent",
|
||||
default_options={"model": "NestedModel"},
|
||||
)
|
||||
|
||||
span_exporter.clear()
|
||||
if stream:
|
||||
result_stream = agent.run("Test message", stream=True)
|
||||
async for _ in result_stream:
|
||||
pass
|
||||
await result_stream.get_final_response()
|
||||
else:
|
||||
await agent.run("Test message")
|
||||
|
||||
spans = span_exporter.get_finished_spans()
|
||||
assert len(spans) == 2
|
||||
|
||||
span_by_op = {s.attributes[OtelAttr.OPERATION.value]: s for s in spans}
|
||||
agent_span = span_by_op[OtelAttr.AGENT_INVOKE_OPERATION]
|
||||
chat_span = span_by_op[OtelAttr.CHAT_COMPLETION_OPERATION]
|
||||
|
||||
# Agent span has no parent (it is the root)
|
||||
assert agent_span.parent is None
|
||||
|
||||
# Chat span's parent must be the agent span
|
||||
assert chat_span.parent is not None
|
||||
assert chat_span.parent.span_id == agent_span.context.span_id
|
||||
assert chat_span.parent.trace_id == agent_span.context.trace_id
|
||||
|
||||
# Both spans must share the same trace
|
||||
assert chat_span.context.trace_id == agent_span.context.trace_id
|
||||
|
||||
|
||||
@pytest.mark.parametrize("stream", [False, True])
|
||||
async def test_function_call_spans_nested_under_agent_span(span_exporter: InMemorySpanExporter, stream: bool):
|
||||
"""All inner spans (chat completions and execute_tool) must be children of the agent span."""
|
||||
from agent_framework import Content
|
||||
from agent_framework._tools import FunctionInvocationLayer
|
||||
|
||||
@tool(name="get_weather", description="Get the weather for a location")
|
||||
def get_weather(location: str) -> str:
|
||||
return f"The weather in {location} is sunny."
|
||||
|
||||
class NestedToolChatClient(FunctionInvocationLayer, ChatTelemetryLayer, BaseChatClient[Any]):
|
||||
def __init__(self) -> None:
|
||||
super().__init__()
|
||||
self.call_count = 0
|
||||
|
||||
def service_url(self):
|
||||
return "https://test.example.com"
|
||||
|
||||
def _inner_get_response(
|
||||
self, *, messages: MutableSequence[Message], stream: bool, options: dict[str, Any], **kwargs: Any
|
||||
) -> Awaitable[ChatResponse] | ResponseStream[ChatResponseUpdate, ChatResponse]:
|
||||
self.call_count += 1
|
||||
is_first = self.call_count == 1
|
||||
|
||||
if stream:
|
||||
|
||||
async def _stream() -> AsyncIterable[ChatResponseUpdate]:
|
||||
if is_first:
|
||||
yield ChatResponseUpdate(
|
||||
contents=[
|
||||
Content.from_function_call(
|
||||
call_id="call_123",
|
||||
name="get_weather",
|
||||
arguments='{"location": "Seattle"}',
|
||||
)
|
||||
],
|
||||
role="assistant",
|
||||
)
|
||||
else:
|
||||
yield ChatResponseUpdate(
|
||||
contents=[Content.from_text("The weather in Seattle is sunny!")],
|
||||
role="assistant",
|
||||
finish_reason="stop",
|
||||
)
|
||||
|
||||
def _finalize(updates: Sequence[ChatResponseUpdate]) -> ChatResponse:
|
||||
return ChatResponse.from_updates(updates)
|
||||
|
||||
return ResponseStream(_stream(), finalizer=_finalize)
|
||||
|
||||
async def _get() -> ChatResponse:
|
||||
if is_first:
|
||||
return ChatResponse(
|
||||
messages=[
|
||||
Message(
|
||||
role="assistant",
|
||||
contents=[
|
||||
Content.from_function_call(
|
||||
call_id="call_123",
|
||||
name="get_weather",
|
||||
arguments='{"location": "Seattle"}',
|
||||
)
|
||||
],
|
||||
)
|
||||
],
|
||||
)
|
||||
return ChatResponse(
|
||||
messages=[Message(role="assistant", contents=["The weather in Seattle is sunny!"])],
|
||||
finish_reason="stop",
|
||||
)
|
||||
|
||||
return _get()
|
||||
|
||||
agent = Agent(
|
||||
client=NestedToolChatClient(),
|
||||
id="tool_agent_id",
|
||||
name="tool_agent",
|
||||
default_options={"model": "ToolModel", "tools": [get_weather], "tool_choice": "auto"},
|
||||
)
|
||||
|
||||
span_exporter.clear()
|
||||
if stream:
|
||||
result_stream = agent.run("What's the weather in Seattle?", stream=True)
|
||||
async for _ in result_stream:
|
||||
pass
|
||||
await result_stream.get_final_response()
|
||||
else:
|
||||
await agent.run("What's the weather in Seattle?")
|
||||
|
||||
spans = span_exporter.get_finished_spans()
|
||||
|
||||
invoke_spans = [s for s in spans if s.attributes.get(OtelAttr.OPERATION.value) == OtelAttr.AGENT_INVOKE_OPERATION]
|
||||
chat_spans = [s for s in spans if s.attributes.get(OtelAttr.OPERATION.value) == OtelAttr.CHAT_COMPLETION_OPERATION]
|
||||
tool_spans = [s for s in spans if s.attributes.get(OtelAttr.OPERATION.value) == OtelAttr.TOOL_EXECUTION_OPERATION]
|
||||
|
||||
assert len(invoke_spans) == 1, f"Expected 1 invoke_agent span, got {len(invoke_spans)}"
|
||||
assert len(chat_spans) == 2, f"Expected 2 chat spans, got {len(chat_spans)}"
|
||||
assert len(tool_spans) == 1, f"Expected 1 execute_tool span, got {len(tool_spans)}"
|
||||
|
||||
agent_span = invoke_spans[0]
|
||||
assert agent_span.parent is None
|
||||
|
||||
# All inner spans must be parented under the agent invoke span
|
||||
for inner in (*chat_spans, *tool_spans):
|
||||
assert inner.parent is not None, f"Span {inner.name} has no parent"
|
||||
assert inner.parent.span_id == agent_span.context.span_id, (
|
||||
f"Span {inner.name} parent={inner.parent.span_id} != agent={agent_span.context.span_id}"
|
||||
)
|
||||
assert inner.context.trace_id == agent_span.context.trace_id
|
||||
|
||||
|
||||
@pytest.mark.parametrize("stream", [False, True])
|
||||
async def test_chat_span_nested_under_explicit_outer_span(
|
||||
span_exporter: InMemorySpanExporter, mock_chat_client, stream: bool
|
||||
):
|
||||
"""Chat telemetry spans (including streaming) must inherit a user-provided outer span as parent."""
|
||||
from agent_framework.observability import get_tracer
|
||||
|
||||
client = mock_chat_client()
|
||||
span_exporter.clear()
|
||||
|
||||
tracer = get_tracer()
|
||||
with tracer.start_as_current_span("outer") as outer_span:
|
||||
outer_ctx = outer_span.get_span_context()
|
||||
if stream:
|
||||
stream_obj = client.get_response(
|
||||
stream=True, messages=[Message(role="user", contents=["Test"])], options={"model": "Test"}
|
||||
)
|
||||
async for _ in stream_obj:
|
||||
pass
|
||||
await stream_obj.get_final_response()
|
||||
else:
|
||||
await client.get_response(messages=[Message(role="user", contents=["Test"])], options={"model": "Test"})
|
||||
|
||||
spans = span_exporter.get_finished_spans()
|
||||
chat_spans = [s for s in spans if s.attributes.get(OtelAttr.OPERATION.value) == OtelAttr.CHAT_COMPLETION_OPERATION]
|
||||
assert len(chat_spans) == 1
|
||||
chat_span = chat_spans[0]
|
||||
|
||||
assert chat_span.parent is not None
|
||||
assert chat_span.parent.span_id == outer_ctx.span_id
|
||||
assert chat_span.context.trace_id == outer_ctx.trace_id
|
||||
|
||||
|
||||
@pytest.mark.parametrize("stream", [False, True])
|
||||
async def test_http_span_nested_under_chat_span(span_exporter: InMemorySpanExporter, stream: bool):
|
||||
"""A span created inside ``_inner_get_response`` (e.g. an HTTP client call to the LLM provider)
|
||||
must be parented under the chat completion span.
|
||||
|
||||
This validates that the chat span context is active while the inner client implementation
|
||||
runs, both for non-streaming responses and while streaming updates are being pulled.
|
||||
"""
|
||||
from agent_framework.observability import get_tracer
|
||||
|
||||
tracer = get_tracer()
|
||||
|
||||
class HttpEmittingClient(ChatTelemetryLayer, BaseChatClient[Any]):
|
||||
def service_url(self):
|
||||
return "https://test.example.com"
|
||||
|
||||
def _inner_get_response(
|
||||
self, *, messages: MutableSequence[Message], stream: bool, options: dict[str, Any], **kwargs: Any
|
||||
) -> Awaitable[ChatResponse] | ResponseStream[ChatResponseUpdate, ChatResponse]:
|
||||
if stream:
|
||||
|
||||
async def _stream() -> AsyncIterable[ChatResponseUpdate]:
|
||||
# Simulate an HTTP request to the model provider while producing the stream.
|
||||
with tracer.start_as_current_span("HTTP POST"):
|
||||
pass
|
||||
yield ChatResponseUpdate(contents=[Content.from_text("hi")], role="assistant", finish_reason="stop")
|
||||
|
||||
def _finalize(updates: Sequence[ChatResponseUpdate]) -> ChatResponse:
|
||||
return ChatResponse.from_updates(updates)
|
||||
|
||||
return ResponseStream(_stream(), finalizer=_finalize)
|
||||
|
||||
async def _get() -> ChatResponse:
|
||||
# Simulate an HTTP request to the model provider during the call.
|
||||
with tracer.start_as_current_span("HTTP POST"):
|
||||
pass
|
||||
return ChatResponse(
|
||||
messages=[Message(role="assistant", contents=["done"])],
|
||||
usage_details=UsageDetails(input_token_count=1, output_token_count=1),
|
||||
)
|
||||
|
||||
return _get()
|
||||
|
||||
span_exporter.clear()
|
||||
client = HttpEmittingClient()
|
||||
if stream:
|
||||
result_stream = client.get_response(
|
||||
stream=True, messages=[Message(role="user", contents=["Test"])], options={"model": "Test"}
|
||||
)
|
||||
async for _ in result_stream:
|
||||
pass
|
||||
await result_stream.get_final_response()
|
||||
else:
|
||||
await client.get_response(messages=[Message(role="user", contents=["Test"])], options={"model": "Test"})
|
||||
|
||||
spans = span_exporter.get_finished_spans()
|
||||
chat_spans = [s for s in spans if s.attributes.get(OtelAttr.OPERATION.value) == OtelAttr.CHAT_COMPLETION_OPERATION]
|
||||
http_spans = [s for s in spans if s.name == "HTTP POST"]
|
||||
assert len(chat_spans) == 1
|
||||
assert len(http_spans) == 1
|
||||
|
||||
chat_span = chat_spans[0]
|
||||
http_span = http_spans[0]
|
||||
|
||||
assert http_span.parent is not None
|
||||
assert http_span.parent.span_id == chat_span.context.span_id
|
||||
assert http_span.context.trace_id == chat_span.context.trace_id
|
||||
|
||||
|
||||
# region Test ResponseStream.with_pull_context_manager
|
||||
|
||||
|
||||
async def test_with_pull_context_manager_enters_and_exits_per_pull():
|
||||
"""The registered factory is entered and exited symmetrically around each iterator pull."""
|
||||
import contextlib
|
||||
|
||||
events: list[str] = []
|
||||
|
||||
@contextlib.contextmanager
|
||||
def cm():
|
||||
events.append("enter")
|
||||
try:
|
||||
yield
|
||||
finally:
|
||||
events.append("exit")
|
||||
|
||||
async def src() -> AsyncIterable[int]:
|
||||
yield 1
|
||||
yield 2
|
||||
|
||||
stream: ResponseStream[int, list[int]] = ResponseStream(src(), finalizer=lambda updates: list(updates))
|
||||
stream.with_pull_context_manager(cm)
|
||||
|
||||
pulled = [u async for u in stream]
|
||||
|
||||
assert pulled == [1, 2]
|
||||
# Enter/exit must be balanced and there must be at least one pair per yielded update.
|
||||
assert events.count("enter") == events.count("exit")
|
||||
assert events.count("enter") >= 2
|
||||
# Verify symmetric ordering (no overlapping pairs).
|
||||
for i in range(0, len(events), 2):
|
||||
assert events[i] == "enter"
|
||||
assert events[i + 1] == "exit"
|
||||
|
||||
|
||||
async def test_with_pull_context_manager_exits_on_iteration_error():
|
||||
"""The pull context is exited even when the underlying stream raises mid-iteration."""
|
||||
import contextlib
|
||||
|
||||
events: list[str] = []
|
||||
|
||||
@contextlib.contextmanager
|
||||
def cm():
|
||||
events.append("enter")
|
||||
try:
|
||||
yield
|
||||
finally:
|
||||
events.append("exit")
|
||||
|
||||
async def src() -> AsyncIterable[int]:
|
||||
yield 1
|
||||
raise RuntimeError("boom")
|
||||
|
||||
stream: ResponseStream[int, list[int]] = ResponseStream(src(), finalizer=lambda updates: list(updates))
|
||||
stream.with_pull_context_manager(cm)
|
||||
|
||||
with pytest.raises(RuntimeError, match="boom"):
|
||||
async for _ in stream:
|
||||
pass
|
||||
|
||||
# Enter/exit balanced even on the failing pull.
|
||||
assert events.count("enter") == events.count("exit")
|
||||
assert events.count("enter") >= 2
|
||||
|
||||
|
||||
async def test_with_pull_context_manager_wraps_stream_resolution_via_await():
|
||||
"""Awaiting a ``from_awaitable`` stream resolves the inner stream under the pull contexts."""
|
||||
import contextlib
|
||||
|
||||
events: list[str] = []
|
||||
|
||||
@contextlib.contextmanager
|
||||
def cm():
|
||||
events.append("enter")
|
||||
try:
|
||||
yield
|
||||
finally:
|
||||
events.append("exit")
|
||||
|
||||
async def inner() -> AsyncIterable[int]:
|
||||
yield 1
|
||||
|
||||
async def make_stream() -> ResponseStream[int, list[int]]:
|
||||
# Record that we resolve while a pull context is active.
|
||||
events.append("resolving")
|
||||
return ResponseStream(inner(), finalizer=lambda updates: list(updates))
|
||||
|
||||
stream: ResponseStream[int, list[int]] = ResponseStream.from_awaitable(make_stream())
|
||||
stream.with_pull_context_manager(cm)
|
||||
|
||||
await stream # Triggers _resolve_stream_with_pull_contexts via __await__
|
||||
|
||||
assert "resolving" in events
|
||||
resolve_index = events.index("resolving")
|
||||
assert events[resolve_index - 1] == "enter" # Pull context active during resolution
|
||||
|
||||
|
||||
# region Test streaming telemetry error paths
|
||||
|
||||
|
||||
@pytest.mark.parametrize("enable_sensitive_data", [True], indirect=True)
|
||||
async def test_chat_streaming_super_failure_closes_span(span_exporter: InMemorySpanExporter, enable_sensitive_data):
|
||||
"""If the underlying client raises synchronously when constructing the stream, the chat
|
||||
span is ended and the exception is recorded (no span leak)."""
|
||||
|
||||
class FailingClient(ChatTelemetryLayer, BaseChatClient[Any]):
|
||||
def service_url(self):
|
||||
return "https://test.example.com"
|
||||
|
||||
def _inner_get_response(
|
||||
self, *, messages: MutableSequence[Message], stream: bool, options: dict[str, Any], **kwargs: Any
|
||||
) -> Awaitable[ChatResponse] | ResponseStream[ChatResponseUpdate, ChatResponse]:
|
||||
raise RuntimeError("inner failed")
|
||||
|
||||
span_exporter.clear()
|
||||
client = FailingClient()
|
||||
with pytest.raises(RuntimeError, match="inner failed"):
|
||||
client.get_response(stream=True, messages=[Message(role="user", contents=["Test"])], options={"model": "Test"})
|
||||
|
||||
spans = span_exporter.get_finished_spans()
|
||||
chat_spans = [s for s in spans if s.attributes.get(OtelAttr.OPERATION.value) == OtelAttr.CHAT_COMPLETION_OPERATION]
|
||||
assert len(chat_spans) == 1
|
||||
assert chat_spans[0].status.status_code == StatusCode.ERROR
|
||||
|
||||
|
||||
@pytest.mark.parametrize("enable_sensitive_data", [True], indirect=True)
|
||||
async def test_agent_streaming_execute_failure_closes_span_and_resets_contextvars(
|
||||
span_exporter: InMemorySpanExporter, enable_sensitive_data
|
||||
):
|
||||
"""If ``execute()`` raises synchronously during streaming agent invocation, the agent span is
|
||||
ended, the exception is recorded, and the telemetry contextvars are reset."""
|
||||
from agent_framework.observability import (
|
||||
INNER_ACCUMULATED_USAGE,
|
||||
INNER_RESPONSE_TELEMETRY_CAPTURED_FIELDS,
|
||||
)
|
||||
|
||||
class _FailingExecuteAgent:
|
||||
AGENT_PROVIDER_NAME = "test_provider"
|
||||
|
||||
def __init__(self):
|
||||
self._id = "failing_execute"
|
||||
self._name = "Failing Execute"
|
||||
self._description = "Agent whose stream call raises synchronously"
|
||||
self._default_options: dict[str, Any] = {}
|
||||
|
||||
@property
|
||||
def id(self):
|
||||
return self._id
|
||||
|
||||
@property
|
||||
def name(self):
|
||||
return self._name
|
||||
|
||||
@property
|
||||
def description(self):
|
||||
return self._description
|
||||
|
||||
@property
|
||||
def default_options(self):
|
||||
return self._default_options
|
||||
|
||||
def run(self, messages=None, *, stream: bool = False, session=None, **kwargs):
|
||||
if stream:
|
||||
raise RuntimeError("execute failed")
|
||||
raise NotImplementedError
|
||||
|
||||
class FailingExecuteAgent(AgentTelemetryLayer, _FailingExecuteAgent):
|
||||
pass
|
||||
|
||||
# Sentinel values to detect that contextvars were reset to their pre-call state.
|
||||
sentinel_fields: set[str] = set()
|
||||
sentinel_usage: dict[str, Any] = {}
|
||||
fields_token = INNER_RESPONSE_TELEMETRY_CAPTURED_FIELDS.set(sentinel_fields)
|
||||
usage_token = INNER_ACCUMULATED_USAGE.set(sentinel_usage)
|
||||
try:
|
||||
agent = FailingExecuteAgent()
|
||||
span_exporter.clear()
|
||||
with pytest.raises(RuntimeError, match="execute failed"):
|
||||
agent.run(messages="Hello", stream=True)
|
||||
|
||||
# Contextvars must be back to the sentinel values registered before the call.
|
||||
assert INNER_RESPONSE_TELEMETRY_CAPTURED_FIELDS.get() is sentinel_fields
|
||||
assert INNER_ACCUMULATED_USAGE.get() is sentinel_usage
|
||||
finally:
|
||||
INNER_ACCUMULATED_USAGE.reset(usage_token)
|
||||
INNER_RESPONSE_TELEMETRY_CAPTURED_FIELDS.reset(fields_token)
|
||||
|
||||
spans = span_exporter.get_finished_spans()
|
||||
agent_spans = [s for s in spans if s.attributes.get(OtelAttr.OPERATION.value) == OtelAttr.AGENT_INVOKE_OPERATION]
|
||||
assert len(agent_spans) == 1
|
||||
assert agent_spans[0].status.status_code == StatusCode.ERROR
|
||||
|
||||
+2
-6
@@ -959,16 +959,12 @@ class DeclarativeActionExecutor(Executor):
|
||||
last_user_msg = messages_list[last_user_index]
|
||||
last_user_text = last_user_msg.text or ""
|
||||
last_user_id = getattr(last_user_msg, "message_id", "") or ""
|
||||
history_messages = (
|
||||
messages_list[:last_user_index] + messages_list[last_user_index + 1:]
|
||||
)
|
||||
history_messages = messages_list[:last_user_index] + messages_list[last_user_index + 1 :]
|
||||
else:
|
||||
history_messages = list(messages_list)
|
||||
tail = messages_list[-1] if messages_list else None
|
||||
last_user_text = (tail.text or "") if tail is not None else ""
|
||||
last_user_id = (
|
||||
getattr(tail, "message_id", "") or "" if tail is not None else ""
|
||||
)
|
||||
last_user_id = getattr(tail, "message_id", "") or "" if tail is not None else ""
|
||||
|
||||
if is_continuation:
|
||||
# Continuation turn: keep prior Conversation.messages intact.
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Declarative specification support for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -22,7 +22,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"powerfx>=0.0.32,<0.0.35; python_version < '3.14'",
|
||||
"pyyaml>=6.0,<7.0",
|
||||
]
|
||||
|
||||
@@ -284,17 +284,13 @@ actions:
|
||||
agent = workflow.as_agent(name="continuation-agent")
|
||||
|
||||
first = await agent.run("turn-1-msg")
|
||||
assert first.text == "turn-1-msg", (
|
||||
f"Expected turn-1 echo 'turn-1-msg', got: {first.text!r}"
|
||||
)
|
||||
assert first.text == "turn-1-msg", f"Expected turn-1 echo 'turn-1-msg', got: {first.text!r}"
|
||||
|
||||
# Stamp a marker into the declarative state between turns. The
|
||||
# continuation branch must preserve it; a state-clearing run would
|
||||
# wipe ``DECLARATIVE_STATE_KEY`` and force re-initialization.
|
||||
state_data = workflow._state.get(DECLARATIVE_STATE_KEY)
|
||||
assert isinstance(state_data, dict), (
|
||||
"Expected declarative state to be initialized after turn 1"
|
||||
)
|
||||
assert isinstance(state_data, dict), "Expected declarative state to be initialized after turn 1"
|
||||
state_data["Local"] = {"persisted_marker": "kept-from-turn-1"}
|
||||
workflow._state.set(DECLARATIVE_STATE_KEY, state_data)
|
||||
workflow._state.commit()
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Debug UI for Microsoft Agent Framework with OpenAI-compatible API
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://github.com/microsoft/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,7 +23,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"openai>=1.99.0,<3",
|
||||
"opentelemetry-sdk>=1.39.0,<2",
|
||||
"fastapi>=0.115.0,<0.133.1",
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Durable Task integration for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -22,7 +22,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"durabletask>=1.3.0,<2",
|
||||
"durabletask-azuremanaged>=1.3.0,<2",
|
||||
"python-dateutil>=2.8.0,<3",
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Microsoft Foundry integrations for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.2.1"
|
||||
version = "1.2.2"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,8 +23,8 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-openai>=1.1.0,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"agent-framework-openai>=1.2.2,<2",
|
||||
"azure-ai-inference>=1.0.0b9,<1.0.0b10",
|
||||
"azure-ai-projects>=2.1.0,<3.0",
|
||||
]
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Foundry Hosting integration for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0a260428"
|
||||
version = "1.0.0a260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,7 +23,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"azure-ai-agentserver-core>=2.0.0b3,<3",
|
||||
"azure-ai-agentserver-responses>=1.0.0b5,<2",
|
||||
"azure-ai-agentserver-invocations>=1.0.0b3,<2",
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Foundry Local integration for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,7 +23,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"agent-framework-openai>=1.1.0,<2",
|
||||
"foundry-local-sdk>=0.5.1,<0.5.2",
|
||||
]
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Google Gemini integration for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0a260428"
|
||||
version = "1.0.0a260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -24,7 +24,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2.0",
|
||||
"agent-framework-core>=1.2.2,<2.0",
|
||||
"google-genai>=1.65.0,<2.0.0",
|
||||
]
|
||||
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "GitHub Copilot integration for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,7 +23,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"github-copilot-sdk>=0.2.1,<=0.2.1; python_version >= '3.11'",
|
||||
]
|
||||
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Hyperlight CodeAct integrations for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0a260428"
|
||||
version = "1.0.0a260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -22,7 +22,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"hyperlight-sandbox>=0.3.0,<0.4",
|
||||
"hyperlight-sandbox-backend-wasm>=0.3.0,<0.4 ; ((sys_platform == 'linux' and platform_machine == 'x86_64') or (sys_platform == 'win32' and platform_machine == 'AMD64')) and python_version < '3.14'",
|
||||
"hyperlight-sandbox-python-guest>=0.3.0,<0.4",
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Experimental modules for Microsoft Agent Framework"
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -22,7 +22,7 @@ classifiers = [
|
||||
"Programming Language :: Python :: 3.14",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
]
|
||||
|
||||
[project.optional-dependencies]
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Mem0 integration for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,7 +23,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"mem0ai>=1.0.0,<2",
|
||||
]
|
||||
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Ollama integration for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://learn.microsoft.com/en-us/agent-framework/"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,7 +23,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"ollama>=0.5.3,<0.5.4",
|
||||
]
|
||||
|
||||
|
||||
@@ -241,6 +241,85 @@ OpenAIChatOptionsT = TypeVar(
|
||||
# endregion
|
||||
|
||||
|
||||
# region Helpers
|
||||
|
||||
|
||||
def _annotations_to_output_text(annotations: Sequence[Annotation] | None) -> list[dict[str, Any]]:
|
||||
"""Convert framework `Annotation` objects to Responses API `output_text` annotation dicts.
|
||||
|
||||
Citations from `file_search`, `code_interpreter` file paths, and url citations all collapse
|
||||
to `Annotation(type="citation", ...)` in the framework. The original API form is recovered
|
||||
here so assistant messages roundtrip cleanly through history forwarding.
|
||||
|
||||
Each Responses API annotation dict carries at most one `start_index`/`end_index` pair, so an
|
||||
`Annotation` with multiple `annotated_regions` is fanned out into one entry per region.
|
||||
Regions missing valid integer span bounds are skipped.
|
||||
"""
|
||||
if not annotations:
|
||||
return []
|
||||
out: list[dict[str, Any]] = []
|
||||
for annotation in annotations:
|
||||
if annotation.get("type") != "citation":
|
||||
continue
|
||||
props = annotation.get("additional_properties") or {}
|
||||
regions = annotation.get("annotated_regions") or []
|
||||
file_id = annotation.get("file_id")
|
||||
url = annotation.get("url")
|
||||
title = annotation.get("title")
|
||||
container_id = props.get("container_id")
|
||||
|
||||
if container_id and file_id:
|
||||
for region in regions:
|
||||
start = region.get("start_index")
|
||||
end = region.get("end_index")
|
||||
if not (isinstance(start, int) and isinstance(end, int)):
|
||||
continue
|
||||
entry: dict[str, Any] = {
|
||||
"type": "container_file_citation",
|
||||
"container_id": container_id,
|
||||
"file_id": file_id,
|
||||
"start_index": start,
|
||||
"end_index": end,
|
||||
}
|
||||
if url:
|
||||
entry["filename"] = url
|
||||
out.append(entry)
|
||||
elif url and not file_id and regions:
|
||||
for region in regions:
|
||||
start = region.get("start_index")
|
||||
end = region.get("end_index")
|
||||
if not (isinstance(start, int) and isinstance(end, int)):
|
||||
continue
|
||||
out.append({
|
||||
"type": "url_citation",
|
||||
"url": url,
|
||||
"title": title or "",
|
||||
"start_index": start,
|
||||
"end_index": end,
|
||||
})
|
||||
elif file_id and url:
|
||||
entry = {
|
||||
"type": "file_citation",
|
||||
"file_id": file_id,
|
||||
"filename": url,
|
||||
}
|
||||
if (idx := props.get("index")) is not None:
|
||||
entry["index"] = idx
|
||||
out.append(entry)
|
||||
elif file_id:
|
||||
entry = {
|
||||
"type": "file_path",
|
||||
"file_id": file_id,
|
||||
}
|
||||
if (idx := props.get("index")) is not None:
|
||||
entry["index"] = idx
|
||||
out.append(entry)
|
||||
return out
|
||||
|
||||
|
||||
# endregion
|
||||
|
||||
|
||||
# region ResponsesClient
|
||||
|
||||
|
||||
@@ -1374,7 +1453,7 @@ class RawOpenAIChatClient( # type: ignore[misc]
|
||||
return {
|
||||
"type": "output_text",
|
||||
"text": content.text,
|
||||
"annotations": [],
|
||||
"annotations": _annotations_to_output_text(getattr(content, "annotations", None)),
|
||||
}
|
||||
return {
|
||||
"type": "input_text",
|
||||
@@ -1522,6 +1601,13 @@ class RawOpenAIChatClient( # type: ignore[misc]
|
||||
"approve": content.approved,
|
||||
}
|
||||
case "hosted_file":
|
||||
# `input_file` is an input-only content type in the Responses API and is rejected
|
||||
# inside an assistant message. Hosted-file content on an assistant message
|
||||
# represents a citation produced by a hosted tool (e.g., file_search) and cannot be
|
||||
# meaningfully replayed as input — drop it. The accompanying text annotations carry
|
||||
# the citation context for round-tripping.
|
||||
if role == "assistant":
|
||||
return {}
|
||||
return {
|
||||
"type": "input_file",
|
||||
"file_id": content.file_id,
|
||||
@@ -2502,45 +2588,63 @@ class RawOpenAIChatClient( # type: ignore[misc]
|
||||
|
||||
ann_type = _get_ann_value("type")
|
||||
ann_file_id = _get_ann_value("file_id")
|
||||
# Hosted-file citations attach as text annotations (matching the non-streaming path)
|
||||
# so they don't roundtrip as standalone `input_file` items in assistant history.
|
||||
if ann_type == "file_path":
|
||||
if ann_file_id:
|
||||
annotation_obj = Annotation(
|
||||
type="citation",
|
||||
file_id=str(ann_file_id),
|
||||
additional_properties={
|
||||
"annotation_index": event.annotation_index,
|
||||
"index": _get_ann_value("index"),
|
||||
},
|
||||
raw_representation=annotation,
|
||||
)
|
||||
contents.append(
|
||||
Content.from_hosted_file(
|
||||
file_id=str(ann_file_id),
|
||||
additional_properties={
|
||||
"annotation_index": event.annotation_index,
|
||||
"index": _get_ann_value("index"),
|
||||
},
|
||||
raw_representation=event,
|
||||
)
|
||||
Content.from_text(text="", annotations=[annotation_obj], raw_representation=event)
|
||||
)
|
||||
elif ann_type == "file_citation":
|
||||
if ann_file_id:
|
||||
ann_filename = _get_ann_value("filename")
|
||||
annotation_obj = Annotation(
|
||||
type="citation",
|
||||
file_id=str(ann_file_id),
|
||||
url=ann_filename,
|
||||
additional_properties={
|
||||
"annotation_index": event.annotation_index,
|
||||
"index": _get_ann_value("index"),
|
||||
},
|
||||
raw_representation=annotation,
|
||||
)
|
||||
contents.append(
|
||||
Content.from_hosted_file(
|
||||
file_id=str(ann_file_id),
|
||||
additional_properties={
|
||||
"annotation_index": event.annotation_index,
|
||||
"filename": _get_ann_value("filename"),
|
||||
"index": _get_ann_value("index"),
|
||||
},
|
||||
raw_representation=event,
|
||||
)
|
||||
Content.from_text(text="", annotations=[annotation_obj], raw_representation=event)
|
||||
)
|
||||
elif ann_type == "container_file_citation":
|
||||
if ann_file_id:
|
||||
ann_filename = _get_ann_value("filename")
|
||||
ann_start = _get_ann_value("start_index")
|
||||
ann_end = _get_ann_value("end_index")
|
||||
annotation_obj = Annotation(
|
||||
type="citation",
|
||||
file_id=str(ann_file_id),
|
||||
url=ann_filename,
|
||||
additional_properties={
|
||||
"annotation_index": event.annotation_index,
|
||||
"container_id": _get_ann_value("container_id"),
|
||||
},
|
||||
raw_representation=annotation,
|
||||
)
|
||||
if ann_start is not None and ann_end is not None:
|
||||
annotation_obj["annotated_regions"] = [
|
||||
TextSpanRegion(
|
||||
type="text_span",
|
||||
start_index=ann_start,
|
||||
end_index=ann_end,
|
||||
)
|
||||
]
|
||||
contents.append(
|
||||
Content.from_hosted_file(
|
||||
file_id=str(ann_file_id),
|
||||
additional_properties={
|
||||
"annotation_index": event.annotation_index,
|
||||
"container_id": _get_ann_value("container_id"),
|
||||
"filename": _get_ann_value("filename"),
|
||||
"start_index": _get_ann_value("start_index"),
|
||||
"end_index": _get_ann_value("end_index"),
|
||||
},
|
||||
raw_representation=event,
|
||||
)
|
||||
Content.from_text(text="", annotations=[annotation_obj], raw_representation=event)
|
||||
)
|
||||
elif ann_type == "url_citation":
|
||||
ann_url = _get_ann_value("url")
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "OpenAI integrations for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.2.1"
|
||||
version = "1.2.2"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,7 +23,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"openai>=1.99.0,<3",
|
||||
]
|
||||
|
||||
|
||||
@@ -1914,6 +1914,285 @@ def test_hosted_file_content_preparation() -> None:
|
||||
assert result["file_id"] == "file_abc123"
|
||||
|
||||
|
||||
def test_assistant_text_preserves_citation_annotations_on_roundtrip() -> None:
|
||||
"""Citation annotations on assistant text should survive serialization back to the Responses API.
|
||||
|
||||
Previously `output_text.annotations` was hardcoded to `[]`, silently dropping `file_search`
|
||||
citation context on every roundtrip. Preserving them keeps citations intact across
|
||||
multi-agent forwarding.
|
||||
"""
|
||||
from agent_framework._types import Annotation, TextSpanRegion
|
||||
|
||||
client = OpenAIChatClient(model="test-model", api_key="test-key")
|
||||
|
||||
text_content = Content.from_text(
|
||||
"Per the docs, the answer is X. See also the report.",
|
||||
annotations=[
|
||||
Annotation(
|
||||
type="citation",
|
||||
file_id="file-abc123",
|
||||
url="guidelines.md",
|
||||
additional_properties={"index": 12},
|
||||
),
|
||||
Annotation(
|
||||
type="citation",
|
||||
title="Quarterly Report",
|
||||
url="https://example.com/report",
|
||||
annotated_regions=[TextSpanRegion(type="text_span", start_index=40, end_index=46)],
|
||||
),
|
||||
Annotation(
|
||||
type="citation",
|
||||
file_id="file-container456",
|
||||
url="data.csv",
|
||||
additional_properties={"container_id": "container-789"},
|
||||
annotated_regions=[TextSpanRegion(type="text_span", start_index=0, end_index=3)],
|
||||
),
|
||||
],
|
||||
)
|
||||
|
||||
result = client._prepare_content_for_openai("assistant", text_content)
|
||||
|
||||
assert result["type"] == "output_text"
|
||||
annotations = result["annotations"]
|
||||
assert len(annotations) == 3
|
||||
|
||||
file_citation = next(a for a in annotations if a["type"] == "file_citation")
|
||||
assert file_citation["file_id"] == "file-abc123"
|
||||
assert file_citation["filename"] == "guidelines.md"
|
||||
assert file_citation["index"] == 12
|
||||
|
||||
url_citation = next(a for a in annotations if a["type"] == "url_citation")
|
||||
assert url_citation["url"] == "https://example.com/report"
|
||||
assert url_citation["title"] == "Quarterly Report"
|
||||
assert url_citation["start_index"] == 40
|
||||
assert url_citation["end_index"] == 46
|
||||
|
||||
container = next(a for a in annotations if a["type"] == "container_file_citation")
|
||||
assert container["file_id"] == "file-container456"
|
||||
assert container["container_id"] == "container-789"
|
||||
assert container["filename"] == "data.csv"
|
||||
assert container["start_index"] == 0
|
||||
assert container["end_index"] == 3
|
||||
|
||||
|
||||
def test_assistant_text_preserves_file_path_annotation() -> None:
|
||||
"""A `file_path`-style citation (file_id only, no url) should serialize as `file_path`."""
|
||||
from agent_framework._types import Annotation
|
||||
|
||||
client = OpenAIChatClient(model="test-model", api_key="test-key")
|
||||
|
||||
text_content = Content.from_text(
|
||||
"See attached.",
|
||||
annotations=[
|
||||
Annotation(
|
||||
type="citation",
|
||||
file_id="file-only",
|
||||
additional_properties={"index": 42},
|
||||
),
|
||||
],
|
||||
)
|
||||
|
||||
result = client._prepare_content_for_openai("assistant", text_content)
|
||||
|
||||
assert result["type"] == "output_text"
|
||||
annotations = result["annotations"]
|
||||
assert annotations == [{"type": "file_path", "file_id": "file-only", "index": 42}]
|
||||
|
||||
|
||||
def test_assistant_text_fans_out_multiple_annotated_regions() -> None:
|
||||
"""A url_citation with multiple `annotated_regions` should emit one entry per region.
|
||||
|
||||
The Responses API annotation dict carries one start/end pair, so a framework Annotation
|
||||
with N regions must produce N output annotation entries.
|
||||
"""
|
||||
from agent_framework._types import Annotation, TextSpanRegion
|
||||
|
||||
client = OpenAIChatClient(model="test-model", api_key="test-key")
|
||||
|
||||
text_content = Content.from_text(
|
||||
"See report. The report says X. Also report.",
|
||||
annotations=[
|
||||
Annotation(
|
||||
type="citation",
|
||||
title="Report",
|
||||
url="https://example.com/report",
|
||||
annotated_regions=[
|
||||
TextSpanRegion(type="text_span", start_index=4, end_index=10),
|
||||
TextSpanRegion(type="text_span", start_index=16, end_index=22),
|
||||
TextSpanRegion(type="text_span", start_index=36, end_index=42),
|
||||
],
|
||||
),
|
||||
],
|
||||
)
|
||||
|
||||
result = client._prepare_content_for_openai("assistant", text_content)
|
||||
annotations = result["annotations"]
|
||||
assert len(annotations) == 3
|
||||
assert all(a["type"] == "url_citation" for a in annotations)
|
||||
spans = [(a["start_index"], a["end_index"]) for a in annotations]
|
||||
assert spans == [(4, 10), (16, 22), (36, 42)]
|
||||
|
||||
|
||||
def test_assistant_text_skips_regions_with_invalid_span() -> None:
|
||||
"""Regions missing integer start/end bounds are skipped rather than emitted with `None`."""
|
||||
from agent_framework._types import Annotation, TextSpanRegion
|
||||
|
||||
client = OpenAIChatClient(model="test-model", api_key="test-key")
|
||||
|
||||
text_content = Content.from_text(
|
||||
"See report.",
|
||||
annotations=[
|
||||
Annotation(
|
||||
type="citation",
|
||||
title="Report",
|
||||
url="https://example.com/report",
|
||||
annotated_regions=[
|
||||
TextSpanRegion(type="text_span"), # type: ignore[typeddict-item]
|
||||
TextSpanRegion(type="text_span", start_index=4, end_index=10),
|
||||
],
|
||||
),
|
||||
],
|
||||
)
|
||||
|
||||
result = client._prepare_content_for_openai("assistant", text_content)
|
||||
annotations = result["annotations"]
|
||||
assert len(annotations) == 1
|
||||
assert annotations[0]["start_index"] == 4
|
||||
assert annotations[0]["end_index"] == 10
|
||||
|
||||
|
||||
def test_assistant_text_without_annotations_emits_empty_list() -> None:
|
||||
"""Plain assistant text should still emit `annotations: []` (Azure validation requires the field)."""
|
||||
client = OpenAIChatClient(model="test-model", api_key="test-key")
|
||||
|
||||
result = client._prepare_content_for_openai("assistant", Content.from_text("hello"))
|
||||
|
||||
assert result["type"] == "output_text"
|
||||
assert result["text"] == "hello"
|
||||
assert result["annotations"] == []
|
||||
|
||||
|
||||
def test_streamed_file_citation_coalesces_onto_surrounding_text() -> None:
|
||||
"""Streamed citation events emit empty-text Content with annotations; `_finalize_response`
|
||||
coalesces consecutive text contents and unions their annotations, so the citation lands on
|
||||
the merged assistant text content (not a stray empty-text entry).
|
||||
|
||||
Without this, span indices in the annotation would reference `text == ""` after roundtrip.
|
||||
"""
|
||||
text_event = MagicMock()
|
||||
text_event.type = "response.output_text.delta"
|
||||
text_event.delta = "Hello world."
|
||||
text_event.item_id = "item_1"
|
||||
text_event.output_index = 0
|
||||
text_event.content_index = 0
|
||||
|
||||
citation_event = MagicMock()
|
||||
citation_event.type = "response.output_text.annotation.added"
|
||||
citation_event.annotation_index = 0
|
||||
citation_event.annotation = {
|
||||
"type": "file_citation",
|
||||
"file_id": "file-abc",
|
||||
"filename": "guidelines.md",
|
||||
"index": 5,
|
||||
}
|
||||
|
||||
client = OpenAIChatClient(model="test-model", api_key="test-key")
|
||||
chat_options = ChatOptions()
|
||||
function_call_ids: dict[int, tuple[str, str]] = {}
|
||||
|
||||
update1 = client._parse_chunk_from_openai(text_event, chat_options, function_call_ids)
|
||||
update2 = client._parse_chunk_from_openai(citation_event, chat_options, function_call_ids)
|
||||
|
||||
response = ChatResponse.from_updates([update1, update2])
|
||||
|
||||
assert len(response.messages) == 1
|
||||
contents = response.messages[0].contents
|
||||
assert len(contents) == 1
|
||||
merged = contents[0]
|
||||
assert merged.type == "text"
|
||||
assert merged.text == "Hello world."
|
||||
assert merged.annotations is not None
|
||||
assert len(merged.annotations) == 1
|
||||
assert merged.annotations[0]["file_id"] == "file-abc"
|
||||
|
||||
|
||||
def test_streamed_file_citation_roundtrips_as_assistant_history() -> None:
|
||||
"""End-to-end: file_citation arrives via streaming, then gets forwarded as assistant history.
|
||||
|
||||
Reproduces the user-reported sequential/group-chat workflow bug where one agent's
|
||||
`file_search` citations became `input_file` items in the next agent's request and were
|
||||
rejected by the Responses API.
|
||||
"""
|
||||
client = OpenAIChatClient(model="test-model", api_key="test-key")
|
||||
chat_options = ChatOptions()
|
||||
function_call_ids: dict[int, tuple[str, str]] = {}
|
||||
|
||||
text_event = MagicMock()
|
||||
text_event.type = "response.output_text.delta"
|
||||
text_event.delta = "According to the docs, the answer is X."
|
||||
text_event.item_id = "item_1"
|
||||
text_event.output_index = 0
|
||||
text_event.content_index = 0
|
||||
|
||||
citation_event = MagicMock()
|
||||
citation_event.type = "response.output_text.annotation.added"
|
||||
citation_event.annotation_index = 0
|
||||
citation_event.annotation = {
|
||||
"type": "file_citation",
|
||||
"file_id": "file-xyz789",
|
||||
"filename": "guidelines.md",
|
||||
"index": 12,
|
||||
}
|
||||
|
||||
update1 = client._parse_chunk_from_openai(text_event, chat_options, function_call_ids)
|
||||
update2 = client._parse_chunk_from_openai(citation_event, chat_options, function_call_ids)
|
||||
|
||||
assistant_history = Message(
|
||||
role="assistant",
|
||||
contents=[*update1.contents, *update2.contents],
|
||||
)
|
||||
prepared = client._prepare_message_for_openai(assistant_history)
|
||||
|
||||
assert len(prepared) == 1
|
||||
content_items = prepared[0].get("content", [])
|
||||
types = [c.get("type") for c in content_items]
|
||||
assert "input_file" not in types, f"input_file leaked into assistant history: {types}"
|
||||
output_text_items = [c for c in content_items if c.get("type") == "output_text"]
|
||||
assert any(
|
||||
any(a.get("type") == "file_citation" and a.get("file_id") == "file-xyz789" for a in c.get("annotations", []))
|
||||
for c in output_text_items
|
||||
), "file_citation annotation should survive the streaming → history roundtrip"
|
||||
|
||||
|
||||
def test_hosted_file_in_assistant_message_does_not_emit_input_file() -> None:
|
||||
"""Hosted file citations attached to an assistant message must not roundtrip as `input_file`.
|
||||
|
||||
The Responses API rejects `input_file` items inside an assistant role's content array;
|
||||
`input_file` is an input-only content type. This guards the multi-agent / sequential workflow
|
||||
case where one agent's `file_search` citations get forwarded as history to the next call.
|
||||
"""
|
||||
client = OpenAIChatClient(model="test-model", api_key="test-key")
|
||||
|
||||
assistant_msg = Message(
|
||||
role="assistant",
|
||||
contents=[
|
||||
Content.from_text("According to the docs, the answer is X."),
|
||||
Content.from_hosted_file(file_id="file_abc123"),
|
||||
],
|
||||
)
|
||||
|
||||
prepared = client._prepare_message_for_openai(assistant_msg)
|
||||
|
||||
assert len(prepared) == 1
|
||||
assistant_item = prepared[0]
|
||||
assert assistant_item["role"] == "assistant"
|
||||
content_types = [c.get("type") for c in assistant_item.get("content", [])]
|
||||
assert "input_file" not in content_types, (
|
||||
f"`input_file` is not valid inside an assistant message; got {content_types}"
|
||||
)
|
||||
assert "output_text" in content_types
|
||||
|
||||
|
||||
def test_function_approval_response_with_mcp_tool_call() -> None:
|
||||
"""Test function approval response content with MCP server tool call content."""
|
||||
client = OpenAIChatClient(model="test-model", api_key="test-key")
|
||||
@@ -2682,7 +2961,7 @@ def test_streaming_response_in_progress_type() -> None:
|
||||
|
||||
|
||||
def test_streaming_annotation_added_with_file_path() -> None:
|
||||
"""Test streaming annotation added event with file_path type extracts HostedFileContent."""
|
||||
"""Streaming `file_path` should attach as a text annotation, matching non-streaming."""
|
||||
client = OpenAIChatClient(model="test-model", api_key="test-key")
|
||||
chat_options = ChatOptions()
|
||||
function_call_ids: dict[int, tuple[str, str]] = {}
|
||||
@@ -2700,15 +2979,23 @@ def test_streaming_annotation_added_with_file_path() -> None:
|
||||
|
||||
assert len(response.contents) == 1
|
||||
content = response.contents[0]
|
||||
assert content.type == "hosted_file"
|
||||
assert content.file_id == "file-abc123"
|
||||
assert content.additional_properties is not None
|
||||
assert content.additional_properties.get("annotation_index") == 0
|
||||
assert content.additional_properties.get("index") == 42
|
||||
assert content.type == "text"
|
||||
assert content.annotations is not None
|
||||
assert len(content.annotations) == 1
|
||||
annotation = content.annotations[0]
|
||||
assert annotation["type"] == "citation"
|
||||
assert annotation["file_id"] == "file-abc123"
|
||||
assert annotation["additional_properties"]["annotation_index"] == 0
|
||||
assert annotation["additional_properties"]["index"] == 42
|
||||
|
||||
|
||||
def test_streaming_annotation_added_with_file_citation() -> None:
|
||||
"""Test streaming annotation added event with file_citation type extracts HostedFileContent."""
|
||||
"""Streaming `file_citation` should attach as a text annotation, matching non-streaming.
|
||||
|
||||
Previously the streaming path produced a standalone `HostedFileContent`, which then
|
||||
serialized as `input_file` in assistant history and was rejected by the Responses API.
|
||||
Annotations on text content roundtrip cleanly.
|
||||
"""
|
||||
client = OpenAIChatClient(model="test-model", api_key="test-key")
|
||||
chat_options = ChatOptions()
|
||||
function_call_ids: dict[int, tuple[str, str]] = {}
|
||||
@@ -2727,15 +3014,19 @@ def test_streaming_annotation_added_with_file_citation() -> None:
|
||||
|
||||
assert len(response.contents) == 1
|
||||
content = response.contents[0]
|
||||
assert content.type == "hosted_file"
|
||||
assert content.file_id == "file-xyz789"
|
||||
assert content.additional_properties is not None
|
||||
assert content.additional_properties.get("filename") == "sample.txt"
|
||||
assert content.additional_properties.get("index") == 15
|
||||
assert content.type == "text"
|
||||
assert content.annotations is not None
|
||||
assert len(content.annotations) == 1
|
||||
annotation = content.annotations[0]
|
||||
assert annotation["type"] == "citation"
|
||||
assert annotation["file_id"] == "file-xyz789"
|
||||
assert annotation["url"] == "sample.txt"
|
||||
assert annotation["additional_properties"]["annotation_index"] == 1
|
||||
assert annotation["additional_properties"]["index"] == 15
|
||||
|
||||
|
||||
def test_streaming_annotation_added_with_container_file_citation() -> None:
|
||||
"""Test streaming annotation added event with container_file_citation type."""
|
||||
"""Streaming `container_file_citation` should attach as a text annotation."""
|
||||
client = OpenAIChatClient(model="test-model", api_key="test-key")
|
||||
chat_options = ChatOptions()
|
||||
function_call_ids: dict[int, tuple[str, str]] = {}
|
||||
@@ -2756,13 +3047,19 @@ def test_streaming_annotation_added_with_container_file_citation() -> None:
|
||||
|
||||
assert len(response.contents) == 1
|
||||
content = response.contents[0]
|
||||
assert content.type == "hosted_file"
|
||||
assert content.file_id == "file-container123"
|
||||
assert content.additional_properties is not None
|
||||
assert content.additional_properties.get("container_id") == "container-456"
|
||||
assert content.additional_properties.get("filename") == "data.csv"
|
||||
assert content.additional_properties.get("start_index") == 10
|
||||
assert content.additional_properties.get("end_index") == 50
|
||||
assert content.type == "text"
|
||||
assert content.annotations is not None
|
||||
assert len(content.annotations) == 1
|
||||
annotation = content.annotations[0]
|
||||
assert annotation["type"] == "citation"
|
||||
assert annotation["file_id"] == "file-container123"
|
||||
assert annotation["url"] == "data.csv"
|
||||
assert annotation["additional_properties"]["container_id"] == "container-456"
|
||||
assert annotation["annotated_regions"] is not None
|
||||
assert len(annotation["annotated_regions"]) == 1
|
||||
region = annotation["annotated_regions"][0]
|
||||
assert region["start_index"] == 10
|
||||
assert region["end_index"] == 50
|
||||
|
||||
|
||||
def test_streaming_annotation_added_with_url_citation() -> None:
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Orchestration patterns for Microsoft Agent Framework. Includes Se
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,7 +23,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
]
|
||||
|
||||
[tool.uv]
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Microsoft Purview (Graph dataSecurityAndGovernance) integration f
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://github.com/microsoft/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -24,7 +24,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"azure-core>=1.30.0,<2",
|
||||
"httpx>=0.27.0,<0.29",
|
||||
]
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Redis integration for Microsoft Agent Framework."
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.0.0b260428"
|
||||
version = "1.0.0b260429"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,7 +23,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core>=1.2.1,<2",
|
||||
"agent-framework-core>=1.2.2,<2",
|
||||
"redis>=6.4.0,<7.2.1",
|
||||
"redisvl>=0.11.0,<0.16",
|
||||
"numpy>=2.2.6,<3"
|
||||
|
||||
@@ -4,7 +4,7 @@ description = "Microsoft Agent Framework for building AI Agents with Python. Thi
|
||||
authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
version = "1.2.1"
|
||||
version = "1.2.2"
|
||||
license-files = ["LICENSE"]
|
||||
urls.homepage = "https://aka.ms/agent-framework"
|
||||
urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
|
||||
@@ -23,7 +23,7 @@ classifiers = [
|
||||
"Typing :: Typed",
|
||||
]
|
||||
dependencies = [
|
||||
"agent-framework-core[all]==1.2.1",
|
||||
"agent-framework-core[all]==1.2.2",
|
||||
]
|
||||
|
||||
[dependency-groups]
|
||||
@@ -52,8 +52,9 @@ dev = [
|
||||
[tool.uv]
|
||||
package = false
|
||||
prerelease = "if-necessary-or-explicit"
|
||||
# Keep transitive litellm below the compromised 1.82.7/1.82.8 releases.
|
||||
constraint-dependencies = ["litellm<1.82.7"]
|
||||
# Security floors for transitive deps; overrides bypass litellm[proxy]'s strict pins.
|
||||
constraint-dependencies = ["litellm>=1.83.7", "fastapi-sso>=0.19.0"]
|
||||
override-dependencies = ["mcp[ws]>=1.27.0", "uvicorn[standard]>=0.34.0"]
|
||||
environments = [
|
||||
"sys_platform == 'darwin'",
|
||||
"sys_platform == 'linux'",
|
||||
@@ -93,7 +94,6 @@ agent-framework-orchestrations = { workspace = true }
|
||||
agent-framework-purview = { workspace = true }
|
||||
agent-framework-redis = { workspace = true }
|
||||
agent-framework-azure-contentunderstanding = { workspace = true }
|
||||
litellm = { url = "https://files.pythonhosted.org/packages/57/77/0c6eca2cb049793ddf8ce9cdcd5123a35666c4962514788c4fc90edf1d3b/litellm-1.82.1-py3-none-any.whl" }
|
||||
|
||||
[tool.ruff]
|
||||
line-length = 120
|
||||
|
||||
+13
-26
@@ -1199,6 +1199,19 @@
|
||||
"dev": true,
|
||||
"license": "ISC"
|
||||
},
|
||||
"node_modules/picomatch": {
|
||||
"version": "4.0.4",
|
||||
"resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.4.tgz",
|
||||
"integrity": "sha512-QP88BAKvMam/3NxH6vj2o21R6MjxZUAd6nlwAS/pnGvN9IVLocLHxGYIzFhg6fUQ+5th6P4dv4eW9jX3DSIj7A==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">=12"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/jonschlinkert"
|
||||
}
|
||||
},
|
||||
"node_modules/postcss": {
|
||||
"version": "8.5.10",
|
||||
"resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.10.tgz",
|
||||
@@ -1345,19 +1358,6 @@
|
||||
}
|
||||
}
|
||||
},
|
||||
"node_modules/tinyglobby/node_modules/picomatch": {
|
||||
"version": "4.0.3",
|
||||
"resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.3.tgz",
|
||||
"integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">=12"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/jonschlinkert"
|
||||
}
|
||||
},
|
||||
"node_modules/typescript": {
|
||||
"version": "5.9.3",
|
||||
"resolved": "https://registry.npmjs.org/typescript/-/typescript-5.9.3.tgz",
|
||||
@@ -1464,19 +1464,6 @@
|
||||
"optional": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"node_modules/vite/node_modules/picomatch": {
|
||||
"version": "4.0.3",
|
||||
"resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.3.tgz",
|
||||
"integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">=12"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/sponsors/jonschlinkert"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Generated
+313
-343
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user