microsoft/semantic-kernel
1
0
Fork 0
mirror of https://github.com/microsoft/semantic-kernel.git synced 2026-10-12 02:19:06 +00:00
Code Issues Packages Projects Releases Wiki Activity
4,897 Commits 63 Branches 1,077 Tags
889807dfda389a7c98c897d820f45c898a80da99
Commit Graph
428 Commits
Author SHA1 Message Date
Evan Mattson b6f95e2c45 Python: Add class validation for Dapr Runtime step loading (#13499) 
### Motivation and Context

The Dapr Runtime uses string-based class names to load step classes
dynamically. This PR adds validation to ensure that only valid
KernelProcessStep subclasses can be loaded and instantiated, improving
type safety and providing better error messages when misconfigured.

The new allowed_module_prefixes parameter gives users control over which
modules are permitted for step class loading, which can be useful in
environments where stricter control is desired.

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

- Add issubclass(cls, KernelProcessStep) validation when loading step
classes from qualified names
- Add optional allowed_module_prefixes parameter for restricting which
modules can be loaded
- Centralize class loading logic in get_step_class_from_qualified_name()
utility function
- Remove duplicate _get_class_from_string methods from DaprStepInfo and
StepActor

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
 2026-02-02 10:18:19 +09:00
Roger Barreto 5b27a727a2 Python: Add file upload security controls to SessionsPythonPlugin (#13478) 
Overriding merge checks as there are unrelated Python integration test failures

### Motivation and Context

- Uploads: Require both EnableDangerousFileUploads = true AND
AllowedUploadDirectories configured
- Downloads: Permissive by default, but if AllowedDownloadDirectories is
configured, path validation
  applies
- Both use path canonicalization to prevent traversal attacks

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
 2026-01-29 10:53:44 +00:00
Evan Mattson e696dc7d52 Python: Add directory allowlist configuration for SessionsPythonTool file (#13467) 
### Motivation and Context

When `SessionsPythonTool` is used with an AI model, providing explicit
directory boundaries for file operations gives developers fine-grained
control over which parts of the filesystem the plugin can access. This
follows the pattern established by `HttpPlugin.allowed_domains`.

- Add `allowed_upload_directories` parameter to control which local
directories can be used for file uploads
- Add `allowed_download_directories` parameter for optional restrictions
on file download destinations
- Implement path canonicalization to resolve symlinks and normalize
paths

Usage:

```python
tool = SessionsPythonTool(
    credential=credential,
    allowed_upload_directories={"/app/data/uploads", "/app/user_files"},
    allowed_download_directories={"/app/data/downloads"},  # optional
)
```


<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

- `upload_file` now requires `allowed_upload_directories` to be
configured (deny-by-default)
- `download_file` optionally supports `allowed_download_directories`
(permissive-by-default, since it's not exposed as a kernel function)
- Both parameters accept `set[str]` or `list[str]` for convenience
- Paths are canonicalized using `os.path.realpath()` before validation

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
 2026-01-23 09:02:05 +00:00
Eduard van Valkenburg 72bc02551f Python: added allowed_domains to HttpPlugin (#13462) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
Adds allowed_domains setup for HttpPlugin.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
 2026-01-22 12:52:56 +09:00
Eduard van Valkenburg f511c965c1 Python: inversed the filter logic for InMemory vector stores (#13457) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
Fixes some issues with the forbidden list approach for the in-memory
vector store filtering.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
 2026-01-19 12:22:19 +09:00
Evan Mattson adb71bc63b Python: Bump to v1.39.1 for a release (#13455) 
### Motivation and Context

Bump to v1.39.1 for a release

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

Bump to v1.39.1 for a release

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
 2026-01-16 07:56:08 +09:00
Dmytro Struk dc7c1c0484 Python: Updated Copilot Studio README (#13432) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

Renamed dependency from Copilot Studio README.

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
 2025-12-23 00:28:28 +00:00
Monita e1fbafe552 Python: feat(oracle): add new Oracle connector for Semantic Kernel (#13229) 
…ync support

### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
This change is required to enable Semantic Kernel users to store and
retrieve embeddings using Oracle databases. Currently, Semantic Kernel
supports vector storage for several backends, but Oracle was missing.
This connector solves that gap by providing full async support, native
VECTOR type handling, and vector index management.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
This PR introduces a new Oracle connector for Semantic Kernel with the
following features:

- Asynchronous upsert, get, delete and search operations for memory
records.

- Native Oracle VECTOR type support for storing embeddings efficiently.

- Support for HNSW and IVFFLAT vector indexes for similarity search.

- Integration with Semantic Kernel collections, enabling semantic search
and memory operations.

- Comprehensive unit tests to ensure correctness and stability.

The connector is designed to work seamlessly with existing Semantic
Kernel memory abstractions and follows the same async patterns as other
vector stores.

Integration tests have also been implemented and verified locally;
however, they are not included in this PR because the current CI
environment setup for Oracle Database support is unknown.
Once guidance is provided on Oracle DB availability in the CI pipeline,
integration tests can be enabled and added in a follow-up PR.

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
 2025-11-26 20:08:16 +00:00
Tao Chen d84363f477 Python: Migrate to new Google GenAI SDK (#13371) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
Closes #12970, #13352

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
1. Migrate Google AI connector to use the new Google AI SDK.
2. This PR also marks the VertexAI connector as deprecated in favor of
the Google AI connector. With this update, if users wants to connect to
a VertexAI project instead of a Google AI endpoint, they can do so with
the Google AI connector.
3. This PR also adds the ability for users to provide a custom client to
the Google AI connector (#13352).
4. This PR also marks `AzureTextCompletion` deprecated.

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
 2025-11-24 21:53:57 +00:00
Nico MöllerandEvan Mattson 145ad9bfd2 Python: Upgrade Onnx Connector to use 0.9.0 (#13162) 
### Motivation and Context

Fixes : #13001 

### Description

Package version 0.9.0 introduced very helpful methods like applying chat
templates automatically from the tokenizer and also support for multi
audio & image files.

This PR adds the following functionalities:

- [x] Add Inference with multiple Images
- [x] Add Inference with multiple Audios
- [x] Chat Templates for non Multimodal Models are read via onnx 

### Samples

Text Sample with ONNX:
<img width="1728" height="90" alt="image"
src="https://github.com/user-attachments/assets/b93d9fc1-4e38-4fa9-b535-cc316e0900ed"
/>

Image Sample with ONNX :
<img width="1721" height="91" alt="image"
src="https://github.com/user-attachments/assets/47761beb-b728-4936-a6b6-fd253e041689"
/>


### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄

---------

Co-authored-by: Evan Mattson <[email protected]>
 2025-11-11 08:44:52 +00:00
Tao Chen b2cceb5985 .Net: Update OTel GenAI operation names (#13334) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
OTel GenAI operation names have the following updates:
1. `chat.completion` to `chat`
2. `text.completion` to `text_completion`

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
This PR updates those operation names

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
 2025-11-05 05:07:34 +00:00
Evan Mattson 05d659d6e9 Python: Fix non-string KernelArguments being converted to strings in prompt template function calls (#13292) 
### Motivation and Context

Fixes #13199 - Non-string kernel arguments are now preserved when passed
to functions in prompt templates. Adds unit tests.

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
 2025-10-30 06:11:35 +00:00
Tao ChenCopilotmoonbox3
 		1f8fea2b49 Python: Fix ai connector integration tests (#13311) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
Vertex AI and Bedrock integration tests have been failing.


### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
1. This PR fixes the vertex ai integration tests by upgrading the Google
AI SDK version.
2. This PR fixes the Bedrock integration tests by upgrading the models.


### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄

---------

Co-authored-by: Copilot <[email protected]>
Co-authored-by: moonbox3 <[email protected]>
 2025-10-30 04:22:14 +00:00
Taylor Rockey e73446e86e Python: [Python] Updated Agents SDK version to latest for CopilotStudio connector (#13144) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
- The Agents SDK has been released, and the recent release changed the
namespace from `microsoft.agents` to `microsoft_agents`, which breaks
imports.
  2. What problem does it solve?
- This updates the `pyproject.toml` and copilot studio related files to
fix the imports
  3. What scenario does it contribute to?
      - Using a Copilot Studio agent as an Agent in Semantic Kernel
  4. If it fixes an open issue, please link to the issue here.
      - N/A
-->

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

- Updated pyproject.toml to use the released packages for the Agents
SDK.
- Updated imports in the `copilot_studio_agent` related files to use the
new `microsoft_agents` namespace

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [] I didn't break anyone 😄
 2025-09-23 01:01:51 +00:00
Soumili Nandi 61d3e6ee8d Python: Introduce NvidiaChatCompletion AI Connector (#12952) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
Enables developers to use NVIDIA's chat models through Semantic Kernel
with structured output support.
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
This change adds chat completion support with structured output to the
existing NVIDIA connector, enabling developers to use NVIDIA's chat
models through Semantic Kernel while building conversational AI
applications that require structured, validated responses. The connector
will support more model types iteratively, with future PRs introducing
VLM models and additional capabilities.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

- New Chat Completion Service:
`NvidiaChatCompletion`: Chat completion service following same structure
as other connectors
- Extends existing NVIDIA embedding connector patterns and architecture
- Custom logic for handling structured output specific to NVIDIA models
  
- Enhanced Configuration:
`NvidiaChatPromptExecutionSettings`: Chat-specific settings following
existing connector patterns
### Contribution Checklist



<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
 2025-09-15 23:26:38 +00:00
Evan Mattson d8af1ed633 Python: Safely clone plugins (#13109) 
### Motivation and Context

Currently, we attempt to deep copy plugins, no matter what the plugin
instance holds. This will cause issues when plugins contain unpickleable
items like an async generator.

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

- Closes #12819

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
 2025-09-12 00:25:07 +00:00
Evan Mattson 22ff5f844f Python: Fix responses agent kernel args bug (#13056) 
### Motivation and Context

The `arguments: KernelArguments` are not getting handled properly for
the Responses Agent invoke. Use the provided `arguments` instead of
trying to get them from the kwargs.

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

- Closes #13053
- Adds unit test coverage. 

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
 2025-09-04 01:27:27 +00:00
Tao Chen d7db35dc47 Python: Fix Azure AI Inference connector model_extras duplication (#13066) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
Addresses #13005 

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
1. Remove the `extra_parameters` key from
`AzureAIInferenceChatPromptExecutionSettings` before calling the chat
completion API to avoid unknown parameter error.
2. Allow setting the API version on the `AzureAIInferenceXXX`
connectors.

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
 2025-09-04 01:27:19 +00:00
Evan Mattson 86b10b95d2 Python: provide AzureAIAgent thread msg id during streaming (#13032) 
### Motivation and Context

As part of invoking an AzureAIAgent via streaming, we weren't providing
the `thread_id` via the `AgentStreamEvent.THREAD_MESSAGE_CREATED` event.

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

Supply the caller with the `thread_msg_id` by sticking it into the
returned SCMC's `metadata` dictionary.
- Closes #12959

Sample output looks like:

```
Sample Output:

# User: 'Hello'
# AuthorRole.ASSISTANT: (thread message id: msg_HZ2h4Wzbj7GEcnVCjnyEuYWT) Hello! How can I assist you with 
    the menu today?
# User: 'What is the special soup?'
# AuthorRole.ASSISTANT: (thread message id: msg_TSjkJK6hHJojIkPvF6uUofHD) The special soup today is 
    Clam Chowder. Would you like to know more about it or anything else from the menu?
# User: 'How much does that cost?'
# AuthorRole.ASSISTANT: (thread message id: msg_liwTpBFrB9JpCM1oM9EXKiwq) The Clam Chowder costs $9.99. 
    Is there anything else you'd like to know?
# User: 'Thank you'
# AuthorRole.ASSISTANT: (thread message id: msg_K6lpR3gYIHethXq17T6gJcxi) You're welcome! 
    If you have any more questions or need assistance, feel free to ask. Enjoy your meal!
```

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
 2025-08-30 10:05:55 +00:00
Christian GlessnerEvan MattsonEvan Mattson
 		5e50e190c4 Python: Add reasoning support for OpenAI Responses Agents (GPT-5, o4-mini, o3) (#12881) 
## Summary

Adds reasoning capabilities to Python OpenAI ResponsesAgent, bringing
parity with the C# implementation. This enables fine-grained control
over reasoning effort for O-series models (o1, o3-mini, o4-mini) and
gpt-5 that support the reasoning parameter.

Fixes #12843

## Changes

### Core Implementation
- **`openai_responses_agent.py`**: Added reasoning configuration support
  - Constructor-level reasoning effort setting
  - Per-invocation reasoning effort override capability
  - Proper parameter validation and model compatibility checks
- **`responses_agent_thread_actions.py`**: Extended thread actions to
support reasoning parameters
  - Reasoning effort propagation through thread operations
  - Metadata preservation for reasoning tokens and summaries

### Sample and Tests
- **`responses_agent_reasoning.py`**: Comprehensive demonstration sample
  - Constructor vs per-invocation reasoning configuration
  - Function calling integration with reasoning
  - Reasoning comparison scenarios (low/medium/high effort)
  - Error handling and troubleshooting guidance
- **`test_openai_responses_agent_reasoning.py`**: Full unit test
coverage
  - Parameter validation tests
  - Integration scenarios with function calling
  - Edge cases and error conditions

## Features

✅ **Constructor-Level Reasoning**: Set default reasoning effort when
creating agents
✅ **Per-Invocation Override**: Override reasoning effort per request  
✅ **Priority Hierarchy**: per-invocation > constructor > model default  
✅ **Function Calling Compatible**: Works seamlessly with existing plugin
system
✅ **Azure OpenAI & OpenAI Support**: Compatible with both service
providers
✅ **Model Validation**: Automatic compatibility checks for O-series
models nad GÜT-5
✅ **Metadata Access**: Reasoning tokens and summaries available in
response metadata

## Usage Example

```python
# Constructor-level reasoning
# Constructor-level reasoning configuration
agent = AzureResponsesAgent(
    ai_model_id="gpt-5",
    client=client,
    reasoning={"effort": "low"}  # Default reasoning for all requests
)

# Per-invocation override
response = await agent.invoke(
    "Solve this complex problem step by step",
    reasoning={"effort": "high"}  
)


# Invoke with reasoning callback to capture intermediate thoughts
response = await agent.invoke(
    "Analyze this data step by step",
    reasoning={"effort": "high", "summary": "detailed"},
    on_intermediate_message=handle_reasoning_message
)

# Streaming with reasoning
async for response in agent.invoke_stream(
    "Explain quantum computing in detail",
    reasoning={"effort": "high", "summary": "detailed"},
    on_intermediate_message=handle_reasoning_message
):
    print(response.content, end="", flush=True)

---------

Co-authored-by: Evan Mattson <[email protected]>
Co-authored-by: Evan Mattson <[email protected]>
 2025-08-28 23:25:26 +00:00
Dmytro Struk 18d9a8e8b2 Python: .Net: Updated encoding logic in prompt templates (#12983) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

Resolves: https://github.com/microsoft/semantic-kernel/issues/11821

Today, the encoding of template arguments is performed only if argument
type is `string`. In case of custom type, anonymous type or collection -
the encoding is not performed.

This PR contains changes to throw an exception in case if encoding is
enabled but complex type is used. In case of complex type, the encoding
should be performed manually according to business logic and automatic
encoding should be explicitly disabled.

This enforces stricter, but more secure template rendering rules.

**Note**: this is a breaking change for customers who use Handlebars or
Liquid template with complex type arguments. Code changes are required
when initializing template arguments:
```diff
var arguments = new KernelArguments()
{
    { "customer", new
        {
-             firstName = userInput.FirstName,
-             lastName = userInput.LastName,
+             firstName = HttpUtility.HtmlEncode(userInput.FirstName),
+             lastName = HttpUtility.HtmlEncode(userInput.LastName),
        }
    }
};

var templateFactory = new LiquidPromptTemplateFactory();
var promptTemplateConfig = new PromptTemplateConfig()
{
    TemplateFormat = "liquid"
+   InputVariables = new()
+   {
+       // We set AllowDangerouslySetContent to 'true' because each property of this argument is encoded manually. 
+       new() { Name = "customer", AllowDangerouslySetContent = true },
+   }
};

var promptTemplate = templateFactory.Create(promptTemplateConfig);
var renderedPrompt = await promptTemplate.RenderAsync(kernel, arguments); 
```

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
 2025-08-26 22:09:00 -07:00
Dmytro Struk 2a47ba9b7d Python: Removed usage of DefaultAzureCredential (#12964) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

The usage of `DefaultAzureCredential` by default is unsafe and raises
security issues. Instead, users should provide their own credential
types such as `AzureCliCredential`, `ManagedIdentityCredential` and so
on. More information here:

https://learn.microsoft.com/en-us/python/api/azure-identity/azure.identity.aio?view=azure-python

In this PR:
1. Removed the usage of `DefaultAzureCredential` from authentication
logic.
2. Replaced `DefaultAzureCredential` with `AzureCliCredential` in all
examples.

**Note**: this is breaking change for Azure users, who relies on
`DefaultAzureCredential`. Users will need to update the code and pass
the credential type of their choice by using `credential` parameter when
initializing one of the Azure clients.

Before:
```python
chat_completion = AzureChatCompletion()
```

After:
```python
chat_completion = AzureChatCompletion(credential=AzureCliCredential())
```

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
 2025-08-25 18:29:13 +00:00
AllaouaAllaoua BenchikhEvan MattsonEvan Mattson
 		45fe60545c Python: Fix issue with orphaned tool/tool_calls (#12923) 
### Motivation and Context

Tool/tool_calls are getting orphaned.

Issue : https://github.com/microsoft/semantic-kernel/issues/12708

How to reproduce :

```python
from semantic_kernel.contents import (
    AuthorRole,
    ChatMessageContent,
    FunctionCallContent,
    FunctionResultContent,
    ChatHistoryTruncationReducer,
)

messages = [
    ChatMessageContent(role=AuthorRole.SYSTEM, content="sys"),
    ChatMessageContent(role=AuthorRole.USER, content="user A"),
    ChatMessageContent(
        role=AuthorRole.ASSISTANT,
        items=[
            FunctionCallContent(
                id="123", function_name="search", plugin_name="plugin", arguments={"q": "x"}
            )
        ],
    ),
    ChatMessageContent(
        role=AuthorRole.TOOL,
        items=[
            FunctionResultContent(
                id="123", function_name="search", plugin_name="plugin", result="RESULT"
            )
        ],
    ),
    ChatMessageContent(role=AuthorRole.USER, content="user B"),
    ChatMessageContent(role=AuthorRole.ASSISTANT, content="done"),
]

reducer = ChatHistoryTruncationReducer(target_count=3, threshold_count=0)
reducer.messages = messages

print("Before reduce:", [m.role for m in reducer.messages])
await reducer.reduce()
print("After reduce:", [m.role for m in reducer.messages])

# After reduce: [<AuthorRole.TOOL: 'tool'>, <AuthorRole.USER: 'user'>, <AuthorRole.ASSISTANT: 'assistant'>]
```

### Description

Move backward as long as we are in a tool/tool_call island when reducing
the messages.

---------

Co-authored-by: Allaoua Benchikh <[email protected]>
Co-authored-by: Evan Mattson <[email protected]>
Co-authored-by: Evan Mattson <[email protected]>
 2025-08-14 00:23:04 +00:00
Evan Mattson 40734345dc Python: Fix the Responses agent msg chaining with reasoning models (#12907) 
### Motivation and Context

When running a reasoning model with the OpenAI responses agent, it was
producing 400s due to the way we were either including or not including
FCC related to tool calls. This PR fixes it for both the default
(store_enabled=True) and the case where uses don't want to use OpenAI's
previous response id as a pseudo-thread (store_enabled=False).

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

- Closes #12843

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
 2025-08-13 10:35:38 +00:00
Mehdi MoshtaghiandEvan Mattson 73ad6e8923 Python: Fix: Implement __deepcopy__ on KernelFunction to handle non-serializable OTEL metrics (#12803) 
### Description

This PR fixes TypeError: cannot pickle '_thread.RLock' object which
occurs when kernel.clone() is called while OpenTelemetry metrics are
enabled.

-   Fixes: #12802

### Motivation and Context

When using features like `HandoffOrchestration`, the agent's `Kernel` is
cloned. This process uses `copy.deepcopy`, which fails on the
`KernelFunction`'s OpenTelemetry `Histogram` fields
(`invocation_duration_histogram` and `streaming_duration_histogram`).
These histogram objects contain thread locks, making them
non-serializable.

Previous solutions, like the one in **PR #9292**, used
`Field(exclude=True, default_factory=...)`. While that was a necessary
step, it was insufficient because `deepcopy` does not respect the
`exclude` flag in the same way that Pydantic's serialization does. This
bug blocks the use of certain agentic features in any application that
has metrics-based observability enabled.

### Description of the change

This solution introduces a custom __deepcopy__ method to the
KernelFunction Pydantic model. This method correctly handles the
deep-copying process for KernelFunction instances:

1.  It intercepts the deepcopy call for KernelFunction objects.
2. It uses self.model_copy(deep=False) to create a new instance of the
Pydantic model. Using deep=False allows the default_factory for the
histogram fields to create new, clean instances on the copied object,
while other fields are shallow-copied.
3. It then manually deep-copies all other attributes from the original
object to the new one, ensuring that any other mutable objects (like
metadata`) are correctly duplicated. The histogram fields are explicitly
skipped in this step, as they have already been recreated by
`model_copy.
4. Standard deepcopy memoization is used to prevent infinite recursion
in the case of cyclic object graphs.

This approach ensures that the non-serializable fields are
re-initialized instead of copied, resolving the TypeError while
maintaining the integrity of the cloned object.

### How has this been tested?

The fix was validated using the reproduction steps outlined in the
associated issue. Running an agent orchestration that triggers
kernel.clone() with OpenTelemetry metrics enabled now completes
successfully without any errors.

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄

---------

Co-authored-by: Evan Mattson <[email protected]>
 2025-08-07 22:48:43 +00:00
Evan Mattson 91392a77e0 Python: Fix ResponsesAgent image duplication in chat history preparation (#12859) 
### Motivation and Context

The ResponsesAgent is duplicating messages in chat history preparation
when messages contained multiple content items (text + images). The
`response_inputs.append()` call is inside the content processing loop,
causing each message to be added once per content item.

The fix:
- Moved `response_inputs.append()` outside the content processing loop
- Added unit test to verify multiple images don't get duplicated

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

- Fixed loop placement in `_prepare_chat_history_for_request`
- Added test `test_prepare_chat_history_multiple_images_no_duplication`
- Fixes #12848

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
 2025-08-05 14:58:35 +00:00
Tao ChenandDmytro Struk 8336c320d9 Python: Add bedrock model provider parameter (#12853) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
Fixes #12833 

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
Add an optional setting to the Bedrock AI connectors to allow users to
specify the Bedrock model providers (i.e. amazon, anthropic, etc) so
that they can use application inference profiles.


### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄

---------

Co-authored-by: Dmytro Struk <[email protected]>
 2025-08-05 00:43:00 +00:00
Evan Mattson 1198b573d1 Python: Add ability to specify encoding when adding a plugin. Add tests. (#12797) 
### Motivation and Context

Right now when adding a plugin, we don't allow one to specify the type
of encoding used.

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

Allow configuration for the type of encoding used.
- Adds unit tests
- Closes #12440

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
 2025-08-04 22:00:30 +00:00
Tao ChenandEvan Mattson b7bb2832aa Python: Input & output attributes in invoke_agent span (#12834) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
The OTel workgroup has been thinking about enhancing tracing for agents.
This is a proposal from our tracing team:
https://github.com/open-telemetry/semantic-conventions/pull/2528. This
PR implements part of the proposal so that when the proposal gets
merged, we can quickly follow.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
Two new attributes are added to the `invoke_agent` span, namely the
`gen_ai.agent.invocation_input` and `gen_ai.agent.invocation_output`.

<img width="747" height="583" alt="image"
src="https://github.com/user-attachments/assets/d8b81f68-915b-48ee-8f86-66a0d4f686cc"
/>


### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄

---------

Co-authored-by: Evan Mattson <[email protected]>
 2025-08-04 21:54:45 +00:00
Evan Mattson 5332c2e330 Python: Require tool_call_id parameter for string-based tool messages in ChatHistory (#12753) 
### Motivation and Context

The `add_tool_message` method of `ChatHistory` accepts string content
without requiring a `tool_call_id` parameter. This design is flawed from
an API design perspective. It created tool messages that:

1. Violated chat completion protocols: most LLM APIs (OpenAI, etc.)
require tool messages to have a `tool_call_id` that references a
previous function call
2. Broke conversation flow: tool messages should always be responses to
specific tool calls, maintaining the call-response relationship
3. Created malformed message sequences: messages without proper tool
call IDs would fail when sent to language models

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

This PR modifies the `add_tool_message` string overload to require a
`tool_call_id` parameter, which makes sure we have proper tool call
protocol compliance.

1. The string overload now validates that `tool_call_id` is provided and
raises a clear error if missing
2. Tool messages now create `FunctionResultContent` objects with both
`id` and `call_id` set to the provided `tool_call_id`
3. Added support for an optional `function_name` parameter for better
bookkeeping
4. Provides informative error messages explaining why `tool_call_id` is
required
- Closes #12744 

Before:

```python
# This would create an invalid tool message without tool_call_id
# when the `.to_dict()` method is called on `ChatMessageContent`
chat_history.add_tool_message("Function result")  # Creates broken message and losing pairing to the corresponding `FunctionCallContent`.
```

After: 

```python
# Now requires tool_call_id for proper protocol compliance
chat_history.add_tool_message("Function result")  # raises clear error due to missing `tool_call_id`
chat_history.add_tool_message("Function result", tool_call_id="call_123")  # works correctly

# Optional function name for better bookkeeping
chat_history.add_tool_message("Function result", tool_call_id="call_123", function_name="get_weather") # works as well
```

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
 2025-07-23 04:07:20 +00:00
Evan Mattson d4f6703cf3 Python: fix Bing grounding & custom search content generation (#12760) 
### Motivation and Context

The same `agent_content_generation` method is used to handle both
`bing_grounding` and `bing_custom_search` tool calls; however, the
method expected that the dicts on the underlying types were named the
same - which they aren't. They have their respective names, as shown
above.

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

Fix Bing content generation based on the instance we're dealing with.
- Add unit tests.
- Closes #12746

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
 2025-07-23 03:17:29 +00:00
Tao Chen b723fbd5e1 Python: Add mix agent orchestration sample (#12749) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
We don't have a sample showing how to use a mix of agents of various
types in an orchestration. This PR adds one.
A bug is also discovered in the OpenAIResponsesAgent while creating the
sample.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
1. Add a new sample showing how to use a mix of agents in the Handoff
orchestration.
2. Fix a bug in the OpenAIResponsesAgent where the tools were not
considering the tools in the kernel instance. A new test is added too.
3. Fix a bug in the AgentActorBase where the intermediate message
callback was rejecting ChatMeesageContent type.

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
 2025-07-22 16:57:05 +00:00
Evan Mattson 48f71b1f2e Python: Support AzureAI agent MCP tools for streaming and non-streaming invocations (#12736) 
### Motivation and Context

MCP tool support was released for the AzureAI Agent and it has yet to be
added to the SK Python AzureAIAgent. This PR adds functionality to
handle the MCP tools for both streaming and non-streaming invocations.

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

Adds MCP support for the Python AzureAI Agent.
- Upgrades dependent packages to be able to use the mcp tool from the
Azure SDK.

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
 2025-07-18 07:08:00 +00:00
Tao Chen b74ea05540 Python: Improve orchestration exception handling (#12716) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
Currently, exceptions that occur inside the orchestration actors are not
properly surfaced to the caller as it happens.

Fixes: https://github.com/microsoft/semantic-kernel/issues/12719

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
This PR addresses the issue by introducing a new exception_callback that
is hidden from the user but will raise exceptions that occurs inside the
orchestration actors to the caller.

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
 2025-07-15 23:03:22 +00:00
ふぁー 93a14d5115 Python: feature: support gpt-image-1 (#12621) 
This pull request was created in response to the issue
https://github.com/microsoft/semantic-kernel/issues/12500#issuecomment-2998387488.
The current AzureTextToImage implementation only works with DALL-E 3.
For gpt-image-1, the response format has changed from a URL to base64
only, which the current code does not support.

Additionally, gpt-image-1 introduces a new image editing feature that
also needs to be supported. Since breaking changes are required, new
methods have been added.

Minimal code that reproduces the problem
```python
service = AzureTextToImage(
        service_id=service_id,
        deployment_name="image-1",
        endpoint=AZURE_OPENAI_IMAGE_ENDPOINT,
        api_key=AZURE_OPENAI_IMAGE_API_KEY,
    )
)

settings = service.get_prompt_execution_settings_class()(service_id="image1")
settings.prompt = "sky"
settings.size = ImageSize(width=1024, height=1024)
settings.quality = "low"
r = await service.generate_image(settings=settings)
```

Example of use with newly added methods
```python
from semantic_kernel.connectors.ai.open_ai import AzureTextToImage
service = AzureTextToImage(
    service_id="image1",
    deployment_name="gpt-image-1",
    endpoint=AZURE_OPENAI_IMAGE_ENDPOINT,
    api_key=AZURE_OPENAI_IMAGE_API_KEY,
    api_version="2025-04-01-preview",
)
settings = service.get_prompt_execution_settings_class()(service_id="image1")
settings.n = 3
images_b64 = await service.generate_images("A cute cat wearing a whimsical striped hat", settings=settings)
```

```python
  from semantic_kernel.connectors.ai.open_ai import AzureTextToImage
  service = AzureTextToImage(
      service_id="image1",
      deployment_name="gpt-image-1",
      endpoint=AZURE_OPENAI_IMAGE_ENDPOINT,
      api_key=AZURE_OPENAI_IMAGE_API_KEY,
      api_version="2025-04-01-preview",
  )
  file_paths = ["./new_images/img_1.png", "./new_images/img_2.png"]
  settings = service.get_prompt_execution_settings_class()(service_id="image1")
  settings.n = 2
  results = await service.edit_image(
      prompt="Make the cat wear a wizard hat",
      image_paths=file_paths,
      settings=settings,
  )
```

## Problems Identified
1. Assumption of URL-based responses. The current implementation assumes
a response format that includes an image url, which is not the case for
gpt-image-1. See:
https://github.com/microsoft/semantic-kernel/blob/8d1b3fd55155bb65e9671383366d2672c4582fb0/python/semantic_kernel/connectors/ai/open_ai/services/open_ai_text_to_image_base.py#L69
 2025-07-04 14:11:56 +00:00
Evan Mattson c15c885f84 Python: Emit partial result for magentic pattern when retrieving final result, if available (#12656) 
### Motivation and Context

When using the magentic orchestration pattern, if the `max_round_count`
is hit, the final result shows as:

```
Final result:
Max round count reached.
```

The interim messages do show as part of the `agent_response_callback`;
however, not everyone may have that configured. We should return more
meaningful results, even if partial. This PR updates to try and get a
partial result if it exists. When one calls:

```python
value = await orchestration_result.get()
```

for the `step5_magentic.py` sample, with `max_round_count=1` they should
receive the partial result:

```
Final result:
Based on the available data, here is a comparison of the estimated training and inference energy consumption for ResNet-50, BERT-base, and GPT-2, along with the associated CO₂ emissions when training on an Azure Standard_NC6s_v3 VM for 24 hours.

**Model Architectures and Datasets:**

- **ResNet-50**: Image classification model trained on ImageNet.
- **BERT-base**: Text classification model fine-tuned on the GLUE benchmark.
- **GPT-2**: Text generation model trained on WebText.

... <rest omitted for brevity> ...
```

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

Return partial results for magentic orchestration if they exist.
- Closes #12625

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
 2025-07-02 15:18:27 +00:00
sshandilya1991 16d708e161 Python: added operationid validation in openapi spec (#12551) 
Description
This PR enforces the presence of an explicit `operationId` for every
operation in the OpenAPI specification. Previously, if `operationId` was
missing, a default value was generated using the path and HTTP method.
Now, the parser will raise a PluginInitializationError if operationId is
not provided, ensuring that all operations are uniquely and explicitly
identified as required by the OpenAPI standard.

Key changes:

- Added validation to check for the existence of operationId in each
operation.
- If operationId is missing, a clear error is raised, preventing
fallback to a default value.
-
[python/tests/unit/connectors/openapi_plugin/no-operationid-openapi.yaml](https://github.com/microsoft/semantic-kernel/compare/main...sshandilya1991:semantic-kernel:sshandilya/12443_add_operation_id_validation?expand=1#diff-3d272039b3afa97f89805f0ee0258a98b613f0f373c603467b336a8912d5651a)
serves as a test case.
- Closes #12443

Edit:
- Added more validation for operationId to be unique & throw in case
duplicate operationId found while parsing.
 2025-06-24 06:36:02 +00:00
Eduard van Valkenburg 003cc4c010 Python: Feature python vector stores preb (#12271) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
Overhaul of the VectorStores to get it matching with dotnet and the
latest development there.

Closes: 
- #11938 
- #11598 
- #11597
- #11517 
- #10561 
- #10391 
- #9911 
- #9892 
- #10867 

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

Many changes, some highlights:
- Moved from different vector fields types, to a single with a enum
first VectorStoreField()
- Renamed several items
- Made embeddinggenerrator a part of the vector field spec and do
automatic vectorization from there or from the same param on a
collection
- Adds hybrid search using the same setup
- Removed the intermediate TextSeachVectorSearch object need, by
allowing `create_search_function` directly on a collection

Will write out full changes in a migration guide in the docs.

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
 2025-06-19 18:34:59 +00:00
kanchi cef5ae7402 Python: Support | and |= operators for KernelArgument (#12499) 
### Motivation and Context

`KernelArguments` extends the built-in `dict` by adding an
`execution_settings` attribute.
However, when using the `|` and `|=` operators, only the `dict` part
(excluding `execution_settings`) is merged, and the result becomes a
plain `dict`.
This causes the `execution_settings` attribute to be lost and not
updated.

### Description

- Implemented support for the `|` and `|=` operators to make it easier
for users to merge `KernelArgument` objects.
- The right-hand or left-hand side of the operator can be either a
`KernelArgument` or a `dict` (or any subclass of dict).
- When merging, both the `execution_settings` attribute and the rest of
the `dict` data are merged individually, and the result is returned as a
`KernelArgument`.
- As long as either side of the operator is a `KernelArgument`, the
result will also be a `KernelArgument`.

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
 2025-06-19 07:24:16 +00:00
Tao Chen 44f1253460 Python: Agent response callbacks to provide full context (#12501) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
Currently, the agent response callbacks in the `Orchestrations` are
triggered only when the final responses from the agents become
available. This limits developers to create solutions that can expose
the internal processing of the agents in multi agent orchestrations.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
The callbacks will now be triggered by the intermediate messages of the
agents:
1. A new sample
2. Tests

P.s. Fix a bug where the name of the intermediate messages is not
assigned.

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
 2025-06-17 16:17:11 +00:00
Tao Chen dfbc993d8f Python: Remove orchestration persona adaptation messages (#12446) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
We previously found that agents might get carried away from in long
contexts. The persona adaptation messages were designed to steer the
agents in an orchestration to respond more closely to the instructions
provided (as system message).

As we perform more testing with newer models, we believe that the
persona adaptation messages are no longer necessary. The additional
instability (because they are hardcoded messages that devs can't
override) and cost (the additional token cost which is not significant,
but they do pollute the context which makes debugging difficult) they
introduce is not worth the benefit they provide.


Closing #12294 


> Ideally, we'd want to approach this more analytically. The lack of a
multi-agent evaluation process makes it difficult. All samples were
verified to make sure they behave the same before and after the removal
of the persona adaptation messages.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
1. Remove the persona adaptation messages.
2. Unit tests.
3. Replace `OpenAIChatCompletion` with `AzureChatCompletion` in some of
the samples.

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
 2025-06-11 15:58:21 +00:00
Tao Chen a7eab4ac6d Python: Remove model info check in Bedrock connectors (#12395) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
Closing #10941 

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
To support more ways (via `model_id`, `inference_profile`, or `model
arn`) to send requests to Bedrock models, we have removed the checks on
whether a model supports certain features, i.e. streaming and embedding
generation. This is because to check for if a model support certain
features, we need the model id, but given the flexibility in specifying
the target model, it's no longer possible to retrieve the model
information realiably.


### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
 2025-06-09 21:16:39 +00:00
Christian GlessnerandEvan Mattson 0e7556e112 Python: Add file handling support to BinaryContent for OpenAI Responses API (#12258) 
## Summary

Enhances `BinaryContent` to support file handling for OpenAI Responses
API, enabling file uploads through the responses agent while maintaining
a provider-agnostic design.

  ## Changes

  ### BinaryContent Enhancements
- **Add `can_read` property**: Indicates whether content has readable
data available
- **Add `from_file()` class method**: Creates BinaryContent instances
from file paths with automatic base64 encoding
- **Fix Unicode handling**: Prevents decode errors when processing
binary files (PDFs, images, etc.)

  ### OpenAI Responses Agent Integration
- **Add BinaryContent support**: Pattern matching case for file handling
in `responses_agent_thread_actions.py`
- **Correct OpenAI API format**: Uses proper `filename` and `file_data`
structure with data URI format
- **UUID-based filenames**: Generates appropriate filenames with
mime-type extensions
- **Provider-specific mapping**: File format conversion happens only in
OpenAI agent code

  ### Testing
- **Test coverage**: New tests for `can_read`, `from_file()`, and binary
data handling
- **Unicode error prevention**: Specific test for binary PDF-like
content
- **Base64 encoding verification**: Ensures proper data format for API
compatibility

  ## Design Principles

- **Provider-agnostic**: BinaryContent remains completely generic with
no OpenAI-specific dependencies
- **Clean separation**: OpenAI format mapping isolated to OpenAI agent
files
- **No FileContent class**: Enhances existing BinaryContent instead of
introducing new types
- **Follows existing patterns**: Similar approach to ImageContent and
TextContent handling

  ## Usage Example

  ```python
 response = await self.agent.get_response(
        messages=ChatMessageContent(
            content="Analyse PDF",
            role=AuthorRole("user"),
            items=[BinaryContent.from_file(file_path=c":/test.pdf")],
        )
    )

Co-authored-by: Evan Mattson <[email protected]>
 2025-06-09 21:15:39 +00:00
Evan Mattson 32d7fa1a53 Python: Normalize MCP function names to allowed tool calling values. Add tests. (#12420) 
### Motivation and Context

When using some MCP plugins, the tool names or prompt names may contain
invalid chars that cause function calling to throw a 400. The following
is such a case:

```python
async with MCPStdioPlugin(
        name="nasa",
        description="nasa Plugin",
        command="docker",
        args=["run","-i","--rm","ghcr.io/metorial/mcp-container--programcomputer--nasa-mcp-server--nasa-mcp-server","npm run start"]
    ) as nasa_plugin:
        agent = ChatCompletionAgent(
            service=AzureChatCompletion(),
            name="NasaAgent",
            instructions="Answer questions about Nasa.",
            plugins=[nasa_plugin],
        )
```

Some prompt tools with that MCP server contain `/` (forward slashes),
which cause the OpenAI model to throw a 400 due to a failed regex.

```
prompt_list.prompts
Prompt(name='nasa/get-astronomy-picture', description="Fetch NASA's Astronomy Picture...nail for video content', required=False)]), 
Prompt(name='nasa/browse-near-earth-objects', description='Find near-Earth asteroids ...rch (YYYY-MM-DD format)', required=True)]),
...
```

We will introduce name normalization when we're loading the kernel
functions, and replace any non-allowed values with a hyphen (`-`). This
then allows to be called successfully.

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

- Name normalize any tool or prompt tools from an MCP server.
- Closes #12406
- Adds unit test coverage

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
 2025-06-09 20:30:25 +00:00
Tao Chen 2f84e5d1bf Python: Add chat completion agent code interpreter sample (#12393) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
Closing #10962 

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
1. Add a sample to demonstrate how to create a chat completion agent
with code interpreter capabilities using the Azure Container Apps
session pool service.
2. Fix a bug that cause the session tool to throw because the upload API
doesn't return the file uploaded.
3. Modify unit tests accordingly.

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
 2025-06-06 18:13:44 +00:00
Evan Mattson 6b964c0328 Python: Allow custom httpx client timeout when not using custom client (#12379) 
### Motivation and Context

Currently, if one is using the OpenAPI plugin within SK, and not
providing a custom httpx client, they are hit with a hard-coded 5 second
timeout. Devs need a way to be able to customize the timeout.

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

Provide a way to customize the timeout used during API calls.
- Closes #12373 
- Adds unit tests

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
 2025-06-04 23:31:05 +00:00
Tao Chen 3baaee2ff3 Python: streaming agent response callback in agent orchestrations (#12360) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
Issue: #12306 
Discussion: #12302 

Currently, we only have a **non-streaming** agent response callback for
users to interact with the agents inside an orchestration. Support for a
stream one has been requested by developers.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
Add support for a streaming agent response callback to all
orchestrations.

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
 2025-06-04 23:06:58 +00:00
Evan Mattson ff1997047d Python: Support Declarative Spec for OpenAIAssistantAgent & OpenAIResponsesAgent (#12247) 
### Motivation and Context

This PR builds on the initial work/abstractions from #11982. The
`AzureAssistantAgent` / `OpenAIAssistantAgent` as well as the
`AzureResponsesAgent` / `OpenAIResponsesAgent` now support declarative
specs. Several examples on how to declare the spec are shown in the
respective dirs in `samples/concepts/agents`, as well as a simple
getting started example for each agent type.

To further simplify working with these two agents, the
`setup_resources()` methods for each agent type have been marked with a
deprecation tag. The new method to use is
`OpenAIAssistantAgent.create_client()` or
`OpenAIResponsesAgent.create_client()`. Further, when one needs to
access the underlying setting's, it's simple to do so with a settings
object and accessing the attribute.

In the previous PR for the AzureAIAgent, it lacked support for
templating - this is included in this current PR.

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

Bring in support for the declarative single agent spec for these agent
types.
- Add samples
- Add unit tests
- Add support for prompt templates for all current agent types
- Closes #11979

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
 2025-05-26 05:02:59 +00:00
Eduard van Valkenburg f5017a1d64 Python: updated onnx deps (#12251) 
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
Updated onnx dependencies, since it now supports both python 3.13 and
all platforms.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
 2025-05-23 16:29:00 +00:00
Evan Mattson afb1e15724 Python: Relax Agent Invocation Methods to Allow Positional or Keyword Arguments for messages (#12248) 
### Motivation and Context

This PR relaxes the API signatures of all agent invocation methods
(`get_response`, `invoke`, `invoke_stream`) by changing the `messages`
parameter from keyword-only to positional-or-keyword. This enhances
ergonomics and Pythonic usability by allowing callers to pass messages
either positionally or as a keyword argument:

```python
agent.get_response("Why is the sky blue?")
agent.get_response(messages="Why is the sky blue?")
```

With our current use of **kwargs, it is possible to explicitly pass None
for messages (like `agent.get_response(messages=None)`). However, this
does not feel idiomatic in Python. If a caller wishes to invoke the
agent on an existing thread (which already contains all relevant
context), it is more natural and Pythonic to simply write:

```python
response = await agent.get_response()
```

This change makes the API more user-friendly, and removes unnecessary
verbosity when no new messages need to be provided.

Impact
- Backward compatible for all previous usage.
- Enables concise and intuitive API calls for primary message arguments.
- Subclasses overriding the prior keyword-only signature will continue
to work at runtime, but static type-checkers may require updating their
signatures to match the new base definition.
- No runtime breaking changes are expected.

| Scenario | Breaks at runtime? | Breaks at type-check? | Notes |

|----------------------------------|----------------------|-------------------------|--------------------------------------------------|
| Subclass w/keyword-only | No | Yes | Type checker error, but runtime
OK |
| Subclass matching base | No | No | Fine |
| Calls expecting keyword-only | No | No | Fine |
| Calls expecting positional | No (now allowed) | No | Improved
ergonomics |
| Decorators relying on kw-only | No | No (unless strict sig) | Only if
decorator is brittle, rare |
| Code generation/docs | No | No | Needs updating docs, not an actual
code break |
| Reflection-based invocation | No | No | Slight difference in behavior,
but not breaking |


Documentation and usage examples will be updated to reflect the improved
invocation style.

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

Relaxes the API signatures of all agent invocation methods.

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
 2025-05-23 13:24:04 +00:00