Skip to content

Tags: microsoft/agent-framework

Tags

dotnet-1.4.0

Toggle dotnet-1.4.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
.NET: Add Microsoft.Agents.AI.Hyperlight package for CodeAct integrat…

…ion (.NET) (#5329)

* Add Microsoft.Agents.AI.Hyperlight package for CodeAct integration

Introduces a new Microsoft.Agents.AI.Hyperlight package that enables CodeAct-style sandboxed code execution via Hyperlight (hyperlight-sandbox .NET SDK, PR #46) for .NET agents, following the docs/features/code_act/dotnet-implementation.md design and the Python agent_framework_hyperlight reference.

Highlights:
- HyperlightCodeActProvider (AIContextProvider): injects an execute_code tool and CodeAct guidance per invocation; single-instance-per-agent via a fixed StateKeys value; supports multiple provider-owned tools (exposed inside the sandbox via call_tool), file mounts, and an outbound domain allow-list; snapshot/restore per run.
- HyperlightExecuteCodeFunction: standalone AIFunction for manual/static wiring when the sandbox configuration is fixed.
- Approval model via CodeActApprovalMode (AlwaysRequire / NeverRequire) with propagation from ApprovalRequiredAIFunction-wrapped tools.
- Unit tests (instruction builder, tool bridge, approval computation, provider CRUD, ProvideAIContextAsync snapshot isolation and approval wrapping).
- Env-gated integration test (HYPERLIGHT_PYTHON_GUEST_PATH).
- Three samples under samples/02-agents/AgentWithCodeAct (interpreter, tool-enabled, manual wiring).

Build is not yet runnable: requires .NET SDK 10.0.200 and the not-yet-published HyperlightSandbox.Api 0.1.0-preview NuGet package. Package is marked IsPackable=false until the dependency is available.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address PR #5329 review feedback for Hyperlight CodeAct provider

- A. Build-breakers: drop unused usings, override test TargetFrameworks
  off net472, drop redundant Microsoft.Extensions.AI.Abstractions PackageRef.
- B. API: keep CRUD but rebuild sandbox when config fingerprint changes;
  add HyperlightCodeActProviderOptions.CreateForWasm/CreateForJavaScript
  factory methods (Backend/ModulePath now read-only); rename WorkspaceRoot
  to HostInputDirectory; convert AllowedDomain & FileMount from record to
  sealed class; drop ToolBridge.Unwrap (ApprovalRequiredAIFunction is
  invocable as-is).
- C. ToolBridge: collapse SerializeResult switch; add comment explaining
  AOT-driven choice to keep JsonNode.Parse over typed Deserialize.
- D. InstructionBuilder: drop language-specific 'Python code' phrasing;
  strip host filesystem paths from execute_code description.
- E. Style polish: ternary expression-body for ComputeApprovalRequired,
  .Where(x is not null), .ToList() over .ToArray() in IReadOnlyList
  returns.
- F. Samples: add guest-module / KVM-WHP build instructions to Step01;
  note future Excel-upload sample in Step02.

Also adds SandboxExecutorTests covering the new RunSnapshot.ComputeFingerprint
used for sandbox-rebuild detection.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Align Hyperlight package id and JS warm-up with merged upstream SDK

The .NET SDK in hyperlight-dev/hyperlight-sandbox PR #46 has merged. The
published package id is Hyperlight.HyperlightSandbox.Api (the bare
HyperlightSandbox.Api remains the assembly/namespace) and the reference
CodeExecutionTool uses 'void 0;' as the JavaScript warm-up no-op. Update
the package reference, project comment, README, and SandboxExecutor warm-up
accordingly.

No functional change beyond that — all other public APIs we depend on
(SandboxBuilder.With*, Sandbox.Run/RegisterToolAsync/AllowDomain/Snapshot/
Restore, ExecutionResult, SandboxBackend) match the merged shape.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Bump Hyperlight package to 0.4.0 and fix build/test issues

Hyperlight.HyperlightSandbox.Api 0.4.0 is now published on nuget.org. Bump
the version reference and address the analyzer/runtime issues that surfaced
once restore could complete:

- Add HyperlightJsonContext source-generated JsonSerializerContext for the
  execute_code result + tool error envelopes; route arbitrary AIFunction
  results through AIJsonUtilities.DefaultOptions to keep IsAotCompatible=true.
- Replace explicit ObjectDisposedException throws with
  ObjectDisposedException.ThrowIf (CA1513).
- Use HyperlightSandbox.Api.SandboxBackend in cref docs to disambiguate.
- Update tests to match AIContext.Tools being IEnumerable<AITool>, drop
  ConfigureAwait(false) in xUnit test methods (xUnit1030), use collection
  expressions for AllowedDomain methods.
- Add 'using OpenAI.Chat;' to all three samples so AsAIAgent resolves.
- Verified: dotnet build of all four hyperlight projects + samples succeeds
  on net8/9/10; dotnet test for the unit tests passes 32/32 on net10.0.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix CI check failures: file encoding (UTF-8 BOM + LF) and broken markdown link

- Convert all new .cs/.csproj files to UTF-8 with BOM and LF line endings
  to satisfy the dotnet/.editorconfig charset/end_of_line settings
  enforced by check-format.
- Drop unused System.Collections.Generic using in HyperlightCodeActProviderTests.
- Add missing using Microsoft.Extensions.AI in CodeActApprovalMode.cs and
  shorten ApprovalRequiredAIFunction cref (IDE0001).
- Fix broken README link to docs/decisions/0024-codeact-integration.md.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address PR review: AIFunction inheritance, packaging, GetService approval check

- HyperlightExecuteCodeFunction now inherits AIFunction directly. The
  AsAIFunction() indirection is gone; instances are accepted anywhere an
  AIFunction is. Approval requirement is surfaced via GetService<ApprovalRequiredAIFunction>()
  which lazily exposes a wrapping ApprovalRequiredAIFunction proxy when the
  effective ApprovalMode/tool stack requires it.
- ComputeApprovalRequired now uses GetService<ApprovalRequiredAIFunction>() so
  approval-required tools nested anywhere in the AITool decorator stack are
  detected (not just the top-most class).
- csproj: drop IsPackable=false (ready to release with the published
  Hyperlight.HyperlightSandbox.Api 0.4.0 dependency); add PackageReadmeFile
  and pack README.md at the package root, matching the pattern used by
  Aspire.Hosting.AgentFramework.DevUI / Microsoft.Agents.AI.DurableTask.
- Update Step03 sample and README wording to reflect direct AIFunction usage.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

python-1.2.2

Toggle python-1.2.2's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Python: bump package versions for 1.2.2 release (#5561)

* Python: bump package versions for 1.2.2 release

PATCH bump (1.2.1 -> 1.2.2) for the released cohort. Five PRs land in this
window:

- agent-framework-openai: fix file_search citations breaking the assistant-
  message history roundtrip (#5557) — drives the released-tier PATCH
- agent-framework-orchestrations: [BREAKING] standardize orchestration
  terminal outputs as AgentResponse (#5301)
- agent-framework-core, agent-framework-declarative: preserve Workflow.run()
  shared state across calls, accept list[Message] in declarative start
  executor, and coerce Enum values when serializing PowerFx symbols (#5531)
- agent-framework-foundry-hosting: add hosted Durable Workflow support
  (#5531)
- agent-framework-azure-contentunderstanding: new alpha package — Azure AI
  Content Understanding context provider (#4829)
- dependencies: workspace package dependency refresh (#5555)

Per lockstep convention, all 21 beta packages stamp 1.0.0b260429 and all 4
alpha packages (now including the new contentunderstanding) stamp
1.0.0a260429. Date stamp reflects 2026-04-29 Pacific. Every non-core package
floor on agent-framework-core is raised to >=1.2.2; the new
contentunderstanding package's stale >=1.0.0 floor is brought into line.

Two follow-on fixes bundled to keep validate-dependency-bounds-test green
at lowest-direct resolution:
- Bump agent-framework-azure-contentunderstanding's azure-ai-content
  understanding lower bound from >=1.0.0 to >=1.0.1 (1.0.0 ships without
  proper typing — pyright reports 65 unknown-type errors)
- Add pyright ignore comments to core/foundry/__init__.pyi for the new
  alpha package's type-stub imports, since alpha packages are not in
  core's [all] extra and therefore aren't installed at lowest-direct

* Python: add #5552 to 1.2.2 CHANGELOG

Add the streaming-span observability fix to the Fixed section. PR is on
upstream/main but not yet pulled into origin/main; the code itself will
land via the PR merge.

* Python: address PR #5561 review feedback on dependency bounds

Two packaging fixes flagged in review:

1. agent-framework-azure-contentunderstanding: add agent-framework-foundry
   as a runtime dependency. The package's README directs users to
   `pip install agent-framework-azure-contentunderstanding --pre` and the
   basic example imports `FoundryChatClient` from `agent_framework.foundry`,
   so the documented install path was failing with ImportError. Pulling
   agent-framework-foundry into deps makes the advertised entry path
   self-contained.

2. agent-framework-foundry: bump agent-framework-openai lower bound from
   >=1.1.0 to >=1.2.2,<2. Foundry imports private modules from
   agent_framework_openai (`_chat_client.py:22`, `_agent.py:34`), so
   resolvers were free to pair foundry==1.2.2 with older OpenAI versions
   that lack this release's coordinated Responses/history fix. Lockstep the
   floor with the released cohort to prevent mismatched installs.

Both changes pass `validate-dependency-bounds-test` lower + upper at
their respective packages.

python-1.2.1

Toggle python-1.2.1's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Python: bump package versions for 1.2.1 release (#5536)

* Python: bump package versions for 1.2.1 release

PATCH bump (1.2.0 -> 1.2.1) for the released cohort. The release window
covers two PRs, no new public APIs:

- agent-framework-core: prevent inner_exception from being lost in
  AgentFrameworkException (#5167)
- samples: add requirements.txt and .env.example to the a2a/ hosting
  sample for pip-based setup (#5510)

Per lockstep convention, all 21 beta packages stamp 1.0.0b260428 and all
3 alpha packages stamp 1.0.0a260428, regardless of per-package code
churn. Every non-core package floor on agent-framework-core is raised to
>=1.2.1 to keep cohort signaling consistent. Date stamp reflects the
local (Asia) cut date 2026-04-28.

* Python: silence pyright unknown-type warnings in hosted-env detection

`azure.ai.agentserver.core` is probed at runtime via `importlib.util.find_spec`
and is not a declared dependency. The existing `# pyright: ignore[reportMissingImports]`
suppresses the missing-import warning, but at `lowest-direct` resolution pyright
still reports the imported symbol (`AgentConfig`) and its members (`from_env`,
`is_hosted`) as unknown, breaking `validate-dependency-bounds-test` for
`packages/core`.

Extend the existing ignore to cover `reportUnknownVariableType` on the import
and `reportUnknownMemberType` on the call site so the bounds check returns to
green. Behavior is unchanged.

Latent since #5455 (shipped in 1.2.0).

* Python: raise agent-framework-gemini lower bound to google-genai>=1.65.0

The Gemini chat client references several `google.genai.types` symbols
(`FileSearch`, `ThinkingLevel`, `SearchTypes`, `McpServer`,
`StreamableHttpTransport`, plus call-site keyword args `mcp_servers` and
`search_types`) that are not present at the lower bound of `google-genai>=1.0.0`.
At `lowest-direct` resolution this caused `validate-dependency-bounds-test` to
fail for `packages/gemini` with eleven `reportAttributeAccessIssue` /
`reportUnknownVariableType` errors.

Walking the upstream `google.genai.types` API:
- `GoogleMaps`, `AuthConfig`: present from 1.40.0
- `FileSearch`: introduced in 1.49.0
- `ThinkingLevel`: introduced in 1.55.0
- `SearchTypes`, `McpServer`, `StreamableHttpTransport`: introduced in 1.65.0

Bump the lower bound to 1.65.0 — the minimum version that exposes every symbol
the package actually uses. Keep the `<2.0.0` upper cap unchanged. With this
bump `validate-dependency-bounds-test` passes for both lower and upper
resolution scenarios across all 27 workspace packages.

Latent since #4847 (Gemini package introduction in 1.1.0); aggravated by
subsequent feature additions that pulled in newer `types.*` symbols.

* Python: add dependabot bumps to 1.2.1 CHANGELOG

Catalog the 15 dependabot dependency updates that merged on `upstream/main`
between python-1.2.0 and the 1.2.1 cut window under a new Changed section:

- Workspace dev/runtime deps: `rich`, `prek`, `python-multipart`, `pyasn1`,
  `pytest` (ag-ui, devui, lab), `uv` (lab)
- Frontend deps: `vite` (devui, chatkit), `postcss` (devui, chatkit, handoff),
  `picomatch` (devui, handoff)

CHANGELOG-only — no source or pyproject.toml changes. PRs themselves merged
upstream independently of this release branch and will be brought in via the
PR merge.

python-1.2.0

Toggle python-1.2.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Python: Bump Python package versions for 1.2.0 release (#5468)

* Bump Python package versions for 1.2.0 release

Released tier bumps 1.1.1 -> 1.2.0 (core, openai, foundry, root) to
reflect additive public APIs landed since 1.1.0: functional workflow API
(#4238) and FunctionTool SKIP_PARSING sentinel (#5424). All beta packages
stamped 1.0.0b260424, alpha packages 1.0.0a260424. All 26 non-core
agent-framework-core floors raised to >=1.2.0,<2. CHANGELOG consolidates
the never-tagged 1.1.1 entries with the post-merge additions into [1.2.0].

* Update CHANGELOG footer links for 1.2.0

Advance [Unreleased] comparison base from python-1.1.0 to python-1.2.0
and add a [1.2.0] reference link comparing python-1.1.0...python-1.2.0
so the heading links resolve correctly.

* Fix CHANGELOG: restore [1.1.1] section and add proper [1.2.0]

Previous commit incorrectly renamed the [1.1.1] header to [1.2.0], which
wiped the historical 1.1.1 entries and wrongly attributed them to 1.2.0.
This restores [1.1.1] to its origin/main content and adds a new [1.2.0]
section above containing only the commits in python-1.1.1..HEAD:

- #4238 functional workflow API
- #5142 GitHub Copilot OpenTelemetry
- #2403 A2A bridge support
- #5070 oauth_consent_request events in Foundry clients
- #5447 FoundryAgent hosted agent sessions
- #5459 hosting server dependency upgrade + types
- #5389 AG-UI reasoning/multimodal parsing fix
- #5440 stop [TOOLBOXES] warning spam
- #5455 user agent prefix fix

Also corrects the [1.2.0] compare base to python-1.1.1 (not 1.1.0) and
adds the missing [1.1.1] reference link.

dotnet-1.3.0

Toggle dotnet-1.3.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Python: Add OpenTelemetry integration for GitHubCopilotAgent (#5142)

* Python: Add OpenTelemetry integration for GitHubCopilotAgent

- Split GitHubCopilotAgent into RawGitHubCopilotAgent (core, no OTel) and
  GitHubCopilotAgent(AgentTelemetryLayer, RawGitHubCopilotAgent) with tracing
- Add default_options property to expose model for span attributes
- Export RawGitHubCopilotAgent from all public namespaces
- Add github_copilot_with_observability.py sample and update README

* Python: Fix OTEL_SERVICE_NAME default in GitHub Copilot README

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Python: Add unit tests for RawGitHubCopilotAgent.default_options property

* Python: Address review feedback on GitHubCopilotAgent OTel integration

- Add middleware param to GitHubCopilotAgent.run() overloads so per-call
  middleware is explicitly forwarded through AgentTelemetryLayer
- Remove github_copilot_with_observability.py sample per feedback; replace
  with inline snippet + link to observability samples in README

* Python: Address review feedback on log_level and session kwargs typing

- Add middleware param to RawGitHubCopilotAgent.run() overloads for interface
  compatibility with AgentTelemetryLayer
- Fix import in README observability snippet to use agent_framework.github

* Python: Add AgentMiddlewareLayer to GitHubCopilotAgent MRO

Follow FoundryAgent pattern: AgentMiddlewareLayer runs outside the telemetry
span so middleware execution time is not captured in traces. Overloads removed
as AgentMiddlewareLayer.run() handles dispatch via MRO.

* Python: Add explicit __init__ to GitHubCopilotAgent for auto-complete and docstrings

* Python: Address review feedback on middleware warning and test assertions

- Add assert "timeout" not in opts to test_default_options_includes_model_for_telemetry
  to document the intentional asymmetry where timeout is extracted into _settings
  and not returned in default_options.
- Replace silent del middleware with a logged warning when per-run middleware is
  passed to RawGitHubCopilotAgent, making it clear that the GitHub Copilot SDK
  handles tool execution internally and chat/function middleware cannot be injected.

* Python: Use Self for __aenter__ return type in RawGitHubCopilotAgent

Address review feedback: use typing.Self (3.11+) / typing_extensions.Self
(3.10) for __aenter__ so subclasses like GitHubCopilotAgent get the correct
return type from async context manager usage.

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>

python-1.1.1

Toggle python-1.1.1's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Python: Hyperlight: thread-confine sandbox, skip parsing on host call…

…backs, schema/tool cleanup (#5424)

* improved parsing of tool call results and tweaks

* Address PR review: skip_parsing flag, broader registry close, comment fix

- FunctionTool.invoke now takes a boolean skip_parsing flag instead of the
  SKIP_PARSING sentinel; the sentinel is still accepted as result_parser at
  construction time to opt out of parsing for every call. The two paths are
  equivalent.
- _SandboxRegistry.close now invokes any sandbox close/shutdown hook on the
  entry's own worker thread (PyO3 unsendable), then shuts the worker down,
  then cleans up the per-entry temporary directories.
- Clarified the _SandboxWorker.shutdown comment to describe the actual
  ThreadPoolExecutor.shutdown(wait=False, cancel_futures=False) semantics.
- Hyperlight host callback uses skip_parsing=True (the new flag).

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Drop redundant 'is not SKIP_PARSING' guard that mypy 1.x flags

After callable(configured_parser) the sentinel is already excluded; the extra
identity check tripped mypy's non-overlapping identity warning.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fixed sandbox working on copy of tool

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

python-1.1.0

Toggle python-1.1.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Python: Bump versions for a release. Update CHANGELOG (#5385)

* Bump versions for a release. Update CHANGELOG

* Bump devui

python-devui-1.0.0b260414

Toggle python-devui-1.0.0b260414's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Python: Bump agent-framework-devui to 1.0.0b260414 for release (#5259)

Update devui version and changelog for the streaming memory fix release.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>