Skip to content

[AgentServer] beta release#43930

Open
lusu-msft wants to merge 104 commits intomainfrom
lusu/agentserver-1110
Open

[AgentServer] beta release#43930
lusu-msft wants to merge 104 commits intomainfrom
lusu/agentserver-1110

Conversation

@lusu-msft
Copy link
Member

@lusu-msft lusu-msft commented Nov 11, 2025

Description

Please add an informative description that covers that changes made by the pull request and link all relevant issues.

If an SDK is being regenerated based on a new API spec, a link to the pull request containing these API spec changes should be included above.

All SDK Contribution checklist:

  • The pull request does not introduce [breaking changes]
  • CHANGELOG is updated for new features, bug fixes or other significant changes.
  • I have read the contribution guidelines.

General Guidelines and Best Practices

  • Title of the pull request is clear and informative.
  • There are a small number of commits, each of which have an informative message. This means that previously merged commits do not appear in the history of the PR. For more information on cleaning up the commits in your PR, see this page.

Testing Guidelines

  • Pull request includes test coverage for the included changes.

@github-actions
Copy link

github-actions bot commented Nov 11, 2025

API Change Check

APIView identified API level changes in this PR and created the following API reviews

azure-ai-agentserver-core

@lusu-msft lusu-msft marked this pull request as ready for review November 11, 2025 01:31
Copilot AI review requested due to automatic review settings November 11, 2025 01:31
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

This PR syncs code from the container_agent repository, bumping three agentserver packages from version 1.0.0b1 to 1.0.0b2. The changes include bug fixes, code formatting improvements, environment variable standardization, and the addition of a conversation field to response objects.

  • Version bumps for azure-ai-agentserver-langgraph, azure-ai-agentserver-core, and azure-ai-agentserver-agentframework from 1.0.0b1 to 1.0.0b2
  • Code formatting fixes (removing extra spaces before type/mypy ignore comments)
  • Refactoring of error message formatting with new _format_error helper function
  • Environment variable name standardization for Application Insights
  • ID generation format fix in FoundryIdGenerator
  • Addition of conversation field to agent framework response output

Reviewed Changes

Copilot reviewed 14 out of 17 changed files in this pull request and generated 5 comments.

Show a summary per file
File Description
sdk/agentserver/azure-ai-agentserver-langgraph/azure/ai/agentserver/langgraph/models/response_event_generators/response_output_text_event_generator.py Fixed code formatting by removing extra spaces before mypy ignore comments
sdk/agentserver/azure-ai-agentserver-langgraph/azure/ai/agentserver/langgraph/models/response_event_generators/response_event_generator.py Fixed code formatting and added trailing comma for better style consistency
sdk/agentserver/azure-ai-agentserver-langgraph/azure/ai/agentserver/langgraph/models/response_event_generators/response_content_part_event_generator.py Fixed code formatting by removing extra spaces before mypy ignore comments
sdk/agentserver/azure-ai-agentserver-langgraph/_version.py Version bump from 1.0.0b1 to 1.0.0b2
sdk/agentserver/azure-ai-agentserver-langgraph/CHANGELOG.md Added changelog entry for 1.0.0b2 release
sdk/agentserver/azure-ai-agentserver-core/azure/ai/agentserver/core/server/common/id_generator/foundry_id_generator.py Changed ID generation format from {prefix}{entropy}{infix}{pkey} to {prefix}{infix}{pkey}{entropy}
sdk/agentserver/azure-ai-agentserver-core/azure/ai/agentserver/core/server/common/agent_run_context.py Fixed code formatting by removing extra spaces before type ignore comments
sdk/agentserver/azure-ai-agentserver-core/azure/ai/agentserver/core/server/base.py Added import for APPINSIGHT_CONNSTR_ENV_NAME, improved log messages, refactored error formatting with new _format_error helper function
sdk/agentserver/azure-ai-agentserver-core/azure/ai/agentserver/core/logger.py Introduced APPINSIGHT_CONNSTR_ENV_NAME constant and updated references to use it
sdk/agentserver/azure-ai-agentserver-core/azure/ai/agentserver/core/constants.py Removed APPLICATION_INSIGHTS_CONNECTION_STRING constant and changed ENABLE_APPLICATION_INSIGHTS_LOGGER value
sdk/agentserver/azure-ai-agentserver-core/_version.py Version bump from 1.0.0b1 to 1.0.0b2
sdk/agentserver/azure-ai-agentserver-core/CHANGELOG.md Added changelog entry for 1.0.0b2 release
sdk/agentserver/azure-ai-agentserver-agentframework/azure/ai/agentserver/agentframework/models/agent_framework_output_streaming_converter.py Added conversation field to response output
sdk/agentserver/azure-ai-agentserver-agentframework/azure/ai/agentserver/agentframework/models/agent_framework_output_non_streaming_converter.py Fixed code formatting by removing extra spaces before type ignore comment
sdk/agentserver/azure-ai-agentserver-agentframework/azure/ai/agentserver/agentframework/agent_framework.py Updated import and reference to use APPINSIGHT_CONNSTR_ENV_NAME
sdk/agentserver/azure-ai-agentserver-agentframework/_version.py Version bump from 1.0.0b1 to 1.0.0b2
sdk/agentserver/azure-ai-agentserver-agentframework/CHANGELOG.md Added changelog entry for 1.0.0b2 release

lusu-msft and others added 22 commits January 23, 2026 17:05
* try skip apistub for langgraph

* added beta classifier

* fix pylint

* fix pylint
* add unittests for tools

* add more tests

* remove unnecessary test case

* move to upper level
* make project endpoint optional

* add UT
* Bump version to 1.0.0b10

* Revert "remove "from __future__ import annotations" as we support py>=3.10"

This reverts commit 39a4b21.

* fix pylint
* make conversation id optional

* Moved the LangGraph checkpointer guard back to agent_run and switched it to a dedicated exception so the core base server handles it (now surfaces as server_error), with tests updated to assert the new behavior.
* init AGENTS.md

* init AGENTS.md, PLANNING.md and TASK.md

* Task.md template

* Task.md template

* Apply suggestions from code review

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* move task.md tempalte instructions to agents.md

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
…ader (#44929)

* use git worktree

* [agentserver] Attach package metadata to OpenAIResponse.metadata + header

* [agentserver] Attach package metadata to OpenAIResponse.metadata + header
@iuiaoin iuiaoin requested a review from JC-386 as a code owner February 3, 2026 22:16
iuiaoin and others added 7 commits February 4, 2026 20:27
…ork (#45004)

* [Hosted Agents] Implement managed checkpoints feature for AgentFramework

* misc: use project_endpoint instead of project_id and foundry_endpoint

* misc: use get_project_endpoint

* misc: refine checkpoint init logic

* misc: Add a mutual-exclusion check

* misc: move the check into workflow_agent_adapter
Some MCP tool servers (e.g. HuggingFace) return tool manifests where
certain parameters have an empty string for their JSON Schema 'type'
field. This causes a Pydantic ValidationError when the SDK tries to
deserialise the ListFoundryConnectedToolsResponse, because SchemaType
only accepts the six standard JSON Schema types.

Changes:
- SchemaProperty.type is now Optional[SchemaType] with a model_validator
  that coerces empty type strings to None.
- FoundryToolClient._create_ai_function skips parameters whose type is
  None with a warning log, instead of crashing with an AttributeError.
…45041)

* [Hosted Agents] Implement managed checkpoints feature for Langgraph

* misc: preserves all other compile parameters

* chore: refactor AgentFramework to remove managed_checkpoints flag

* chore: refactor langgraph to remove managed_checkpoints flag
…d langgraph (#45064)

* [Hosted Agents] Add foundry checkpoints samples for agentframework and langgraph

* docs: Add README files for Foundry checkpoint samples
Co-authored-by: Declan <lixiaoli@microsoft.com>
Applies the same guard as the agentframework fix (PR #45051) to the
LangGraph tool resolver. When an MCP tool manifest contains a property
with an empty or unrecognised schema type, the resolver now skips that
field with a warning instead of crashing with AttributeError.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

6 participants