agent-framework 1.2.1__tar.gz → 1.2.2__tar.gz

{agent_framework-1.2.1 → agent_framework-1.2.2}/AGENTS.md

@@ -69,6 +69,7 @@ python/
 
 ### Azure Integrations
 - [foundry](packages/foundry/README.md) - Microsoft Foundry chat, agent, memory, and embedding integrations
+- [azure-contentunderstanding](packages/azure-contentunderstanding/AGENTS.md) - Azure Content Understanding context provider
 - [azure-ai-search](packages/azure-ai-search/AGENTS.md) - Azure AI Search RAG
 - [azure-cosmos](packages/azure-cosmos/AGENTS.md) - Azure Cosmos DB-backed history provider
 - [azurefunctions](packages/azurefunctions/AGENTS.md) - Azure Functions hosting

{agent_framework-1.2.1 → agent_framework-1.2.2}/CHANGELOG.md

@@ -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

{agent_framework-1.2.1 → agent_framework-1.2.2}/PACKAGE_STATUS.md

@@ -18,6 +18,7 @@ Status is grouped into these buckets:
 | `agent-framework-a2a` | `python/packages/a2a` | `beta` |
 | `agent-framework-ag-ui` | `python/packages/ag-ui` | `beta` |
 | `agent-framework-anthropic` | `python/packages/anthropic` | `beta` |
+| `agent-framework-azure-contentunderstanding` | `python/packages/azure-contentunderstanding` | `alpha` |
 | `agent-framework-azure-ai-search` | `python/packages/azure-ai-search` | `beta` |
 | `agent-framework-azure-cosmos` | `python/packages/azure-cosmos` | `beta` |
 | `agent-framework-azurefunctions` | `python/packages/azurefunctions` | `beta` |

{agent_framework-1.2.1 → agent_framework-1.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agent-framework
-Version: 1.2.1
+Version: 1.2.2
 Summary: Microsoft Agent Framework for building AI Agents with Python. This package contains all the core and optional packages.
 Author-email: Microsoft <af-support@microsoft.com>
 Requires-Python: >=3.10
@@ -16,7 +16,7 @@ Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: 3.14
 Classifier: Typing :: Typed
 License-File: LICENSE
-Requires-Dist: agent-framework-core[all]==1.2.1
+Requires-Dist: agent-framework-core[all]==1.2.2
 Project-URL: homepage, https://aka.ms/agent-framework
 Project-URL: issues, https://github.com/microsoft/agent-framework/issues
 Project-URL: release_notes, https://github.com/microsoft/agent-framework/releases?q=tag%3Apython-1&expanded=true

{agent_framework-1.2.1 → agent_framework-1.2.2}/packages/a2a/pyproject.toml

@@ -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",
 ]
 

{agent_framework-1.2.1 → agent_framework-1.2.2}/packages/ag-ui/pyproject.toml

@@ -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"

{agent_framework-1.2.1 → agent_framework-1.2.2}/packages/anthropic/pyproject.toml

@@ -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",
 ]
 

{agent_framework-1.2.1 → agent_framework-1.2.2}/packages/azure-ai-search/pyproject.toml

@@ -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",
 ]
 

agent_framework-1.2.2/packages/azure-contentunderstanding/.gitignore

@@ -0,0 +1,3 @@
+# Local-only files (not committed)
+_local_only/
+*_local_only*

agent_framework-1.2.2/packages/azure-contentunderstanding/AGENTS.md

@@ -0,0 +1,71 @@
+# AGENTS.md — azure-contentunderstanding
+
+## Package Overview
+
+`agent-framework-azure-contentunderstanding` integrates Azure Content Understanding (CU)
+into the Agent Framework as a context provider. It automatically analyzes file attachments
+(documents, images, audio, video) and injects structured results into the LLM context.
+
+## Public API
+
+| Symbol | Type | Description |
+|--------|------|-------------|
+| `ContentUnderstandingContextProvider` | class | Main context provider — extends `ContextProvider` |
+| `AnalysisSection` | enum | Output section selector (MARKDOWN, FIELDS, etc.) |
+| `DocumentStatus` | enum | Document lifecycle state (ANALYZING, UPLOADING, READY, FAILED) |
+| `FileSearchBackend` | ABC | Abstract vector store file operations interface |
+| `FileSearchConfig` | dataclass | Configuration for CU + vector store RAG mode |
+
+## Architecture
+
+- **`_context_provider.py`** — Main provider implementation. Overrides `before_run()` to detect
+  file attachments, call the CU API, manage session state with multi-document tracking,
+  and auto-register retrieval tools for follow-up turns.
+  - **Analyzer auto-detection** — When `analyzer_id=None` (default), `_resolve_analyzer_id()`
+    selects the CU analyzer based on media type prefix: `audio/` → `prebuilt-audioSearch`,
+    `video/` → `prebuilt-videoSearch`, everything else → `prebuilt-documentSearch`.
+  - **Multi-segment output** — CU splits long video/audio into multiple scene segments
+    (each a separate `contents[]` entry with its own `startTimeMs`, `endTimeMs`, `markdown`,
+    and `fields`). `_extract_sections()` produces:
+    - `segments`: list of per-segment dicts, each with `markdown`, `fields`, `start_time_s`, `end_time_s`
+    - `markdown`: concatenated at top level with `---` separators (for file_search uploads)
+    - `duration_seconds`: computed from global `min(startTimeMs)` → `max(endTimeMs)`
+    - Metadata (`kind`, `resolution`): taken from the first segment
+  - **Speaker diarization (not identification)** — CU transcripts label speakers as
+    `<Speaker 1>`, `<Speaker 2>`, etc. CU does **not** identify speakers by name.
+  - **file_search RAG** — When `FileSearchConfig` is provided, CU-extracted markdown is
+    uploaded to an OpenAI vector store and a `file_search` tool is registered on the context
+    instead of injecting the full document content. This enables token-efficient retrieval
+    for large documents.
+- **`_models.py`** — `AnalysisSection` enum, `DocumentStatus` enum, `DocumentEntry` TypedDict,
+  `FileSearchConfig` dataclass.
+- **`_file_search.py`** — `FileSearchBackend` ABC, `OpenAIFileSearchBackend`,
+  `FoundryFileSearchBackend`.
+
+## Key Patterns
+
+- Follows the Azure AI Search context provider pattern (same lifecycle, config style).
+- Uses provider-scoped `state` dict for multi-document tracking across turns.
+- Auto-registers `list_documents()` tool via `context.extend_tools()`.
+- Configurable timeout (`max_wait`) with `asyncio.create_task()` background fallback.
+- Strips supported binary attachments from `input_messages` to prevent LLM API errors.
+- Explicit `analyzer_id` always overrides auto-detection (user preference wins).
+- Vector store resources are cleaned up in `close()` / `__aexit__`.
+
+## Samples
+
+| Sample | Description |
+|--------|-------------|
+| `01_document_qa.py` | Upload a PDF via URL, ask questions about it |
+| `02_multi_turn_session.py` | AgentSession persistence across turns |
+| `03_multimodal_chat.py` | PDF + audio + video parallel analysis |
+| `04_invoice_processing.py` | Structured field extraction with `prebuilt-invoice` analyzer |
+| `05_large_doc_file_search.py` | CU extraction + OpenAI vector store RAG |
+| `02-devui/01-multimodal_agent/` | DevUI web UI for CU-powered chat |
+| `02-devui/02-file_search_agent/` | DevUI web UI combining CU + file_search RAG |
+
+## Running Tests
+
+```bash
+uv run poe test -P azure-contentunderstanding
+```

agent_framework-1.2.2/packages/azure-contentunderstanding/README.md

@@ -0,0 +1,127 @@
+# Get Started with Azure Content Understanding in Microsoft Agent Framework
+
+Please install this package via pip:
+
+```bash
+pip install agent-framework-azure-contentunderstanding --pre
+```
+
+## Azure Content Understanding Integration
+
+### Prerequisites
+
+Before using this package, you need an Azure Content Understanding resource:
+
+1. An active **Azure subscription** ([create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account))
+2. A **Microsoft Foundry resource** created in a [supported region](https://learn.microsoft.com/azure/ai-services/content-understanding/language-region-support)
+3. **Default model deployments** configured for your resource (GPT-4.1, GPT-4.1-mini, text-embedding-3-large)
+
+Follow the [prerequisites section](https://learn.microsoft.com/azure/ai-services/content-understanding/quickstart/use-rest-api?tabs=portal%2Cdocument&pivots=programming-language-rest#prerequisites) in the Azure Content Understanding quickstart for setup instructions.
+
+### Introduction
+
+The Azure Content Understanding integration provides a context provider that automatically analyzes file attachments (documents, images, audio, video) using [Azure Content Understanding](https://learn.microsoft.com/azure/ai-services/content-understanding/) and injects structured results into the LLM context.
+
+- **Document & image analysis**: State-of-the-art OCR with markdown extraction, table preservation, and structured field extraction — handles scanned PDFs, handwritten content, and complex layouts
+- **Audio & video analysis**: Transcription, speaker diarization, and per-segment summaries
+- **Background processing**: Configurable timeout with async background fallback for large files
+- **file_search integration**: Optional vector store upload for token-efficient RAG on large documents
+
+> Learn more about Azure Content Understanding capabilities at [https://learn.microsoft.com/azure/ai-services/content-understanding/](https://learn.microsoft.com/azure/ai-services/content-understanding/)
+
+### Basic Usage Example
+
+See the [samples directory](samples/) which demonstrates:
+
+- Single PDF upload and Q&A ([01_document_qa](samples/01-get-started/01_document_qa.py))
+- Multi-turn sessions with cached results ([02_multi_turn_session](samples/01-get-started/02_multi_turn_session.py))
+- PDF + audio + video parallel analysis ([03_multimodal_chat](samples/01-get-started/03_multimodal_chat.py))
+- Structured field extraction with prebuilt-invoice ([04_invoice_processing](samples/01-get-started/04_invoice_processing.py))
+- CU extraction + OpenAI vector store RAG ([05_large_doc_file_search](samples/01-get-started/05_large_doc_file_search.py))
+- Interactive web UI with DevUI ([02-devui](samples/02-devui/))
+
+```python
+import asyncio
+from agent_framework import Agent, AgentSession, Message, Content
+from agent_framework.foundry import FoundryChatClient
+from agent_framework.foundry import ContentUnderstandingContextProvider
+from azure.identity import AzureCliCredential
+
+credential = AzureCliCredential()
+
+cu = ContentUnderstandingContextProvider(
+    endpoint="https://my-resource.cognitiveservices.azure.com/",
+    credential=credential,
+    max_wait=None,  # block until CU extraction completes before sending to LLM
+)
+
+client = FoundryChatClient(
+    project_endpoint="https://your-project.services.ai.azure.com",
+    model="gpt-4.1",
+    credential=credential,
+)
+
+async def main():
+    async with cu:
+        agent = Agent(
+            client=client,
+            name="DocumentQA",
+            instructions="You are a helpful document analyst.",
+            context_providers=[cu],
+        )
+        session = AgentSession()
+
+        response = await agent.run(
+            Message(role="user", contents=[
+                Content.from_text("What's on this invoice?"),
+                Content.from_uri(
+                    "https://raw.githubusercontent.com/Azure-Samples/"
+                    "azure-ai-content-understanding-assets/main/document/invoice.pdf",
+                    media_type="application/pdf",
+                    additional_properties={"filename": "invoice.pdf"},
+                ),
+            ]),
+            session=session,
+        )
+        print(response.text)
+
+asyncio.run(main())
+```
+
+### Supported File Types
+
+| Category | Types |
+|----------|-------|
+| Documents | PDF, DOCX, XLSX, PPTX, HTML, TXT, Markdown |
+| Images | JPEG, PNG, TIFF, BMP |
+| Audio | WAV, MP3, M4A, FLAC, OGG |
+| Video | MP4, MOV, AVI, WebM |
+
+For the complete list of supported file types and size limits, see [Azure Content Understanding service limits](https://learn.microsoft.com/azure/ai-services/content-understanding/service-limits#input-file-limits).
+
+### Environment Variables
+
+The provider supports automatic endpoint resolution from environment variables.
+When ``endpoint`` is not passed to the constructor, it is loaded from
+``AZURE_CONTENTUNDERSTANDING_ENDPOINT``:
+
+```python
+# Endpoint auto-loaded from AZURE_CONTENTUNDERSTANDING_ENDPOINT env var
+cu = ContentUnderstandingContextProvider(credential=credential)
+```
+
+Set these in your shell or in a `.env` file:
+
+```bash
+AZURE_CONTENTUNDERSTANDING_ENDPOINT=https://your-cu-resource.cognitiveservices.azure.com/
+AZURE_AI_PROJECT_ENDPOINT=https://your-project.services.ai.azure.com
+AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4.1
+```
+
+You also need to be logged in with `az login` (for `AzureCliCredential`).
+
+### Next steps
+
+- Explore the [samples directory](samples/) for complete code examples
+- Read the [Azure Content Understanding documentation](https://learn.microsoft.com/azure/ai-services/content-understanding/) for detailed service information
+- Learn more about the [Microsoft Agent Framework](https://aka.ms/agent-framework)

agent_framework-1.2.2/packages/azure-contentunderstanding/agent_framework_azure_contentunderstanding/__init__.py

@@ -0,0 +1,28 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+"""Azure Content Understanding integration for Microsoft Agent Framework.
+
+Provides a context provider that analyzes file attachments (documents, images,
+audio, video) using Azure Content Understanding and injects structured results
+into the LLM context.
+"""
+
+import importlib.metadata
+
+from ._context_provider import ContentUnderstandingContextProvider
+from ._file_search import FileSearchBackend
+from ._models import AnalysisSection, DocumentStatus, FileSearchConfig
+
+try:
+    __version__ = importlib.metadata.version(__name__)
+except importlib.metadata.PackageNotFoundError:
+    __version__ = "0.0.0"
+
+__all__ = [
+    "AnalysisSection",
+    "ContentUnderstandingContextProvider",
+    "DocumentStatus",
+    "FileSearchBackend",
+    "FileSearchConfig",
+    "__version__",
+]