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
4,692 Commits 63 Branches 1,077 Tags
d4e02783307da0159a7278e37824909ebb58b260
Commit Graph
1146 Commits
Author SHA1 Message Date
Evan Mattson d4e0278330 Python: Bump Python version to 1.35.2 for a release (#12894) 
### Motivation and Context

Bump Python version to 1.35.2 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 Python version to 1.35.2 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
- [X] I didn't break anyone 😄
 2025-08-08 01:14:45 +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
Eduard van Valkenburg a6b5f34d9b Python: fix parsing of types in mcp server (#12871) 
### 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 parsing of tool call output was not working correctly, this fixes
that.
Solves #12850 

### 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 😄
 2025-08-07 21:49:37 +00:00
dependabot[bot]andEvan Mattson 433b2874b7 Python: Update boto3 requirement from <1.40.0,>=1.36.4 to >=1.36.4,<1.41.0 in /python (#12857) 
Updates the requirements on [boto3](https://github.com/boto/boto3) to
permit the latest version.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/boto/boto3/commit/ad48a219e467d13a50f6ffeeec5191d75c454ea7"><code>ad48a21</code></a>
Merge branch 'release-1.40.2'</li>
<li><a
href="https://github.com/boto/boto3/commit/0a92fe40bf86d48a5e8dd7ee6b06fcfbae52b597"><code>0a92fe4</code></a>
Bumping version to 1.40.2</li>
<li><a
href="https://github.com/boto/boto3/commit/b1d3cd4e4b46ade160224ad589e9918f5da84ca8"><code>b1d3cd4</code></a>
Add changelog entries from botocore</li>
<li><a
href="https://github.com/boto/boto3/commit/72d9a28a0c79ff7966226855593a366a40076d74"><code>72d9a28</code></a>
Merge branch 'release-1.40.1'</li>
<li><a
href="https://github.com/boto/boto3/commit/1c32a227314c9d8fa38baa9e0da5d373cf61683f"><code>1c32a22</code></a>
Merge branch 'release-1.40.1' into develop</li>
<li><a
href="https://github.com/boto/boto3/commit/a3ffa6102045e1ec958c7e9548105339b2c195b9"><code>a3ffa61</code></a>
Bumping version to 1.40.1</li>
<li><a
href="https://github.com/boto/boto3/commit/c643766d437bc994f2d94966fa9dd3bc39662402"><code>c643766</code></a>
Add changelog entries from botocore</li>
<li><a
href="https://github.com/boto/boto3/commit/e2fb47b057930792b8bfe192063207b8c4794395"><code>e2fb47b</code></a>
Merge branch 'release-1.40.0'</li>
<li><a
href="https://github.com/boto/boto3/commit/e19cb9fbb32d6187d731fecf374de5ac2b851ce0"><code>e19cb9f</code></a>
Merge branch 'release-1.40.0' into develop</li>
<li><a
href="https://github.com/boto/boto3/commit/9e895ba0a527098909b07b98412f0fb962a3466b"><code>9e895ba</code></a>
Bumping version to 1.40.0</li>
<li>Additional commits viewable in <a
href="https://github.com/boto/boto3/compare/1.36.4...1.40.2">compare
view</a></li>
</ul>
</details>
<br />


Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Evan Mattson <[email protected]>
 2025-08-06 02:42:11 +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
Evan Mattson 58c3c4d27f Python: Bump Python version to 1.35.1 for a release. (#12856) 
### Motivation and Context

Bump Python version to 1.35.1 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 Python version to 1.35.1 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
- [X] I didn't break anyone 😄
 2025-08-05 11:09:38 +09:00
dependabot[bot]andEvan Mattson 7300b843c1 Python: Update pyarrow requirement from <21.0,>=12.0 to >=12.0,<22.0 in /python (#12836) 
Updates the requirements on [pyarrow](https://github.com/apache/arrow)
to permit the latest version.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/apache/arrow/releases">pyarrow's
releases</a>.</em></p>
<blockquote>
<h2>Apache Arrow 21.0.0</h2>
<p>Release Notes URL: <a
href="https://arrow.apache.org/release/21.0.0.html">https://arrow.apache.org/release/21.0.0.html</a></p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/apache/arrow/commit/ee4d09ebef61c663c1efbfa4c18e518a03b798be"><code>ee4d09e</code></a>
MINOR: [Release] Update versions for 21.0.0</li>
<li><a
href="https://github.com/apache/arrow/commit/f13a5796008e3a5e546af1a7b2be0fbd3c148c26"><code>f13a579</code></a>
MINOR: [Release] Update .deb/.rpm changelogs for 21.0.0</li>
<li><a
href="https://github.com/apache/arrow/commit/6fd2a167e0ed74dbe4c059e579a561fcc2aae11f"><code>6fd2a16</code></a>
MINOR: [Release] Update CHANGELOG.md for 21.0.0</li>
<li><a
href="https://github.com/apache/arrow/commit/cf261bf58ae74a1f7fa99d81c201ca8e1d679c9b"><code>cf261bf</code></a>
<a
href="https://redirect.github.com/apache/arrow/issues/47078">GH-47078</a>:
[Release] Ensure using cloned apache/arrow for reproducible check
(...</li>
<li><a
href="https://github.com/apache/arrow/commit/ddbc3dc005dfdde5a79d42cb5953190479b12b73"><code>ddbc3dc</code></a>
<a
href="https://redirect.github.com/apache/arrow/issues/47074">GH-47074</a>:
[Release] Use reproducible mtime for csharp/ in source archive (<a
href="https://redirect.github.com/apache/arrow/issues/47">#47</a>...</li>
<li><a
href="https://github.com/apache/arrow/commit/0534eb2d279f445ac67b99a22eca344484749b6f"><code>0534eb2</code></a>
<a
href="https://redirect.github.com/apache/arrow/issues/47071">GH-47071</a>:
[Release] Dereference all hard links in source archive (<a
href="https://redirect.github.com/apache/arrow/issues/47072">#47072</a>)</li>
<li><a
href="https://github.com/apache/arrow/commit/f845b4184664aee522f7fd73864d3093e84b6580"><code>f845b41</code></a>
<a
href="https://redirect.github.com/apache/arrow/issues/47069">GH-47069</a>:
[Release] Add missing &quot;needs: target&quot; (<a
href="https://redirect.github.com/apache/arrow/issues/47070">#47070</a>)</li>
<li><a
href="https://github.com/apache/arrow/commit/1c08f8ee6947bd2a9bffb441af946c6a7373015b"><code>1c08f8e</code></a>
<a
href="https://redirect.github.com/apache/arrow/issues/47067">GH-47067</a>:
[Release] Fix wrong GitHub Actions context in verify_rc.yml (<a
href="https://redirect.github.com/apache/arrow/issues/47068">#47068</a>)</li>
<li><a
href="https://github.com/apache/arrow/commit/70e5c51e6d5de1ca6f669b47ff0b98e1075336d0"><code>70e5c51</code></a>
<a
href="https://redirect.github.com/apache/arrow/issues/47065">GH-47065</a>:
[Release] Fix timeout key in verify_rc.yml (<a
href="https://redirect.github.com/apache/arrow/issues/47066">#47066</a>)</li>
<li><a
href="https://github.com/apache/arrow/commit/254a85c8bddb52eef03d623882836717f027061d"><code>254a85c</code></a>
<a
href="https://redirect.github.com/apache/arrow/issues/47063">GH-47063</a>:
[Release] Define missing RELEASE_TARBALL (<a
href="https://redirect.github.com/apache/arrow/issues/47064">#47064</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/apache/arrow/compare/go/v12.0.0...apache-arrow-21.0.0">compare
view</a></li>
</ul>
</details>
<br />


Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Evan Mattson <[email protected]>
 2025-08-05 01:33:57 +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
Evan Mattson e5972e2430 Python: Add incomplete details reason to AzureAIAgent error message (#12796) 
### Motivation and Context

When errors occur processing a run of an AzureAIAgent, we surface the
error message but not the incomplete_details reason if it exists.

<!-- 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 adds handling for the incomplete details reason, if it exists,
so it can be passed back via the error message.
- Closes #12752

<!-- 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 21:59:19 +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
Tao ChenandChris 358b0f343b Python: .Net: Magentic orchestration to return the last agent message when limits reached (#12839) 
### 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.
-->
Related to #12687
Related to #12656 

Currently, the Magentic orchestration returns a static message if the
max reset limit or the max invocation limit is reached.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
Return the last agent response if either of the limit is reached.

### 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: Chris <[email protected]>
 2025-08-04 18:17:44 +00:00
Nava-7andEvan Mattson c16db27622 Python: Update README.md (#12737) 
Update links due to renamed files

### 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.
-->

### 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
- [ ] 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
- [ ] 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 07:22:25 +00:00
Evan Mattson 30391ade09 Python: AzureAI Agent int test update to pass (#12849) 
### Motivation and Context

The AzureAI Agent code interpreter is failing when asking it to use the
code interpreter to create bar charts. Updating the unit test so that it
uses the code interpreter and doesn't fail/block.

<!-- 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

Update integration test while trying to understand the root cause of the
failure.

<!-- 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 15:51:41 +09:00
Evan Mattson 1efc7ad04e Python: Pass through arguments when creating agents from specs (#12771) 
### Motivation and Context

Currently, attempting to pass through KernelArguments through agent
creation via declarative spec isn't working properly. The arguments are
used to normalize fields, but are then not passed through fully to where
the agent is created.

<!-- 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

Pass arguments through, and merge them properly with the normalized
fields. This allows for underlying args to be used by the agent, like in
the case of structured outputs.
- Closes #12770

<!-- 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 😄
 2025-07-24 05:47:43 +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
Eduard van Valkenburg c79f5a5c63 Python: improved MCP connect and additional samples (#12696) 
### 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.
-->
Adding a sample using StreamableHTTPServer towards Github.
Added a demo showing how to connect to a OAuth protected MCP server.
Also some improvements in the connect logic for MCP.


### 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 😄
 2025-07-22 15:14:32 +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
dependabot[bot]andEvan Mattson d96cadcebe Python: Update sentence-transformers requirement from <5.0,>=2.2 to >=2.2,<6.0 in /python (#12679) 
Updates the requirements on
[sentence-transformers](https://github.com/UKPLab/sentence-transformers)
to permit the latest version.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/UKPLab/sentence-transformers/releases">sentence-transformers's
releases</a>.</em></p>
<blockquote>
<h2>v5.0.0 - SparseEncoder support; encode_query &amp; encode_document;
multi-processing in encode; Router; and more</h2>
<p>This release consists of significant updates including the
introduction of Sparse Encoder models, new methods
<code>encode_query</code> and <code>encode_document</code>,
multi-processing support in <code>encode</code>, the <code>Router</code>
module for asymmetric models, custom learning rates for parameter
groups, composite loss logging, and various small improvements and bug
fixes.</p>
<p>Install this version with</p>
<pre lang="bash"><code># Training + Inference
pip install sentence-transformers[train]==5.0.0
<h1>Inference only, use one of:</h1>
<p>pip install sentence-transformers==5.0.0
pip install sentence-transformers[onnx-gpu]==5.0.0
pip install sentence-transformers[onnx]==5.0.0
pip install sentence-transformers[openvino]==5.0.0
</code></pre></p>
<blockquote>
<p>[!TIP]
Our <a href="https://huggingface.co/blog/train-sparse-encoder">Training
and Finetuning Sparse Embedding Models with Sentence Transformers v5
blogpost</a> is an excellent place to learn about finetuning sparse
embedding models!</p>
</blockquote>
<blockquote>
<p>[!NOTE]
This release is designed to be fully backwards compatible, meaning that
you should be able to upgrade from older versions to v5.x without any
issues. If you are running into issues when upgrading, feel free to open
<a href="https://github.com/uKPLab/sentence-transformers/issues/new">an
issue</a>. Also see the <a
href="https://sbert.net/docs/migration_guide.html">Migration Guide</a>
for changes that we would recommend.</p>
</blockquote>
<h2>Sparse Encoder models</h2>
<p>The Sentence Transformers v5.0 release introduces Sparse Embedding
models, also known as Sparse Encoders. These models generate
high-dimensional embeddings, often with 30,000+ dimensions, where often
only &lt;1% of dimensions are non-zero. This is in contrast to the
standard dense embedding models, which produce low-dimensional
embeddings (e.g., 384, 768, or 1024 dimensions) where all values are
non-zero.</p>
<p>Usually, each active dimension (i.e. the dimension with a non-zero
value) in a sparse embedding corresponds to a specific token in the
model's vocabulary, allowing for interpretability. This means that you
can e.g. see exactly which words/tokens are important in an embedding,
and that you can inspect exactly because of which words/tokens two texts
are deemed similar.</p>
<p>Let's have a look at <a
href="https://huggingface.co/naver/splade-v3">naver/splade-v3</a>, a
strong sparse embedding model, as an example:</p>
<pre lang="python"><code>from sentence_transformers import SparseEncoder
<h1>Download from the 🤗 Hub</h1>
<p>model = SparseEncoder(&quot;naver/splade-v3&quot;)</p>
<h1>Run inference</h1>
<p>sentences = [
&quot;The weather is lovely today.&quot;,
&quot;It's so sunny outside!&quot;,
&quot;He drove to the stadium.&quot;,
]
embeddings = model.encode(sentences)
print(embeddings.shape)</p>
<h1>(3, 30522)</h1>
<h1>Get the similarity scores for the embeddings</h1>
<p>similarities = model.similarity(embeddings, embeddings)
print(similarities)</p>
<h1>tensor([[   32.4323,     5.8528,     0.0258],</h1>
<p>&lt;/tr&gt;&lt;/table&gt;
</code></pre></p>
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/UKPLab/sentence-transformers/commit/8dc0fca767afd74208764fd28f89dd83e8743241"><code>8dc0fca</code></a>
Release v5.0.0</li>
<li><a
href="https://github.com/UKPLab/sentence-transformers/commit/e91af6ac3e160aa0d610ea32aeb295f3ff648e67"><code>e91af6a</code></a>
Update links for SPLADE and Inference-Free SPLADE models collections in
docum...</li>
<li><a
href="https://github.com/UKPLab/sentence-transformers/commit/4c00aea59d4b25061ba03761804a4266c3e8fd33"><code>4c00aea</code></a>
[<code>fix</code>] Remove hub_kwargs in SparseStaticEmbedding.from_json
in favor of more...</li>
<li><a
href="https://github.com/UKPLab/sentence-transformers/commit/28685bb1d771b8609c5e4d4115a8b862267358ce"><code>28685bb</code></a>
Clean up gitignore (<a
href="https://redirect.github.com/UKPLab/sentence-transformers/issues/3409">#3409</a>)</li>
<li><a
href="https://github.com/UKPLab/sentence-transformers/commit/85dd17518f15a8466ec131a4f82e1e93e4ada631"><code>85dd175</code></a>
Fix formatting of docstring arguments in
SpladeRegularizerWeightSchedulerCall...</li>
<li><a
href="https://github.com/UKPLab/sentence-transformers/commit/14afc4b6681f0b83bded05fe91a8fd3320d453f9"><code>14afc4b</code></a>
Merge PR <a
href="https://redirect.github.com/UKPLab/sentence-transformers/issues/3401">#3401</a>:
[<code>v5</code>] Add support for Sparse Embedding models</li>
<li><a
href="https://github.com/UKPLab/sentence-transformers/commit/2d248419eb47c3710d50fa560d41e7fd17459846"><code>2d24841</code></a>
Update tip phrasing and fix links</li>
<li><a
href="https://github.com/UKPLab/sentence-transformers/commit/ed043c56b21d4a6c8f600e9d2a74523e522d6823"><code>ed043c5</code></a>
typo</li>
<li><a
href="https://github.com/UKPLab/sentence-transformers/commit/b2679d12294f9e0e5a2250cbcb400e9b4111f856"><code>b2679d1</code></a>
fix broken link</li>
<li><a
href="https://github.com/UKPLab/sentence-transformers/commit/d30341ec2f3a8fa50eb41f924273e414bb7c0db7"><code>d30341e</code></a>
Update tips to prepared for v5.0</li>
<li>Additional commits viewable in <a
href="https://github.com/UKPLab/sentence-transformers/compare/v2.2.0...v5.0.0">compare
view</a></li>
</ul>
</details>
<br />


Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Evan Mattson <[email protected]>
 2025-07-17 06:01:11 +00:00
Evan Mattson 190954a2c9 Python: Bump Python version to 1.35.0 for a release (#12725) 
### Motivation and Context

Bump Python version to 1.35.0 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 Python version to 1.35.0 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
- [X] I didn't break anyone 😄
 2025-07-16 08:19:31 +09:00
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
dependabot[bot]andEvan Mattson 9fe95bf30e Python: Update boto3 requirement from <1.39.0,>=1.36.4 to >=1.36.4,<1.40.0 in /python (#12638) 
Updates the requirements on [boto3](https://github.com/boto/boto3) to
permit the latest version.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/boto/boto3/commit/74b661c51dce9ff7bea2d60bc0394883650f1bd6"><code>74b661c</code></a>
Merge branch 'release-1.39.0'</li>
<li><a
href="https://github.com/boto/boto3/commit/eba3ce194234574b446ab9ef78eae7ad50266e54"><code>eba3ce1</code></a>
Bumping version to 1.39.0</li>
<li><a
href="https://github.com/boto/boto3/commit/171fcea4db5a1d9cbc9ba8760a9a7c5cffe4c476"><code>171fcea</code></a>
Add changelog entries from botocore</li>
<li><a
href="https://github.com/boto/boto3/commit/f02c8ee2d7d3f7cfcc91df05ebe8be434433875a"><code>f02c8ee</code></a>
Merge branch 'release-1.38.46'</li>
<li><a
href="https://github.com/boto/boto3/commit/058a5507e8866a58bb4b3c27b6e9885584b81473"><code>058a550</code></a>
Merge branch 'release-1.38.46' into develop</li>
<li><a
href="https://github.com/boto/boto3/commit/804ef0f99d92575611f623f700e693c2f3e1ada2"><code>804ef0f</code></a>
Bumping version to 1.38.46</li>
<li><a
href="https://github.com/boto/boto3/commit/533e5c24002b7f8df6f8c93d216ba9bfbd6d6203"><code>533e5c2</code></a>
Add changelog entries from botocore</li>
<li><a
href="https://github.com/boto/boto3/commit/3595b04d47f723ae62d9f2b1e560cc88dbabb96c"><code>3595b04</code></a>
Merge branch 'release-1.38.45'</li>
<li><a
href="https://github.com/boto/boto3/commit/874b24a403d49d4528a3e56bf979bd900d6b86c4"><code>874b24a</code></a>
Merge branch 'release-1.38.45' into develop</li>
<li><a
href="https://github.com/boto/boto3/commit/df0b3fc9f783271a4fb3c137bb88509ae8377326"><code>df0b3fc</code></a>
Bumping version to 1.38.45</li>
<li>Additional commits viewable in <a
href="https://github.com/boto/boto3/compare/1.36.4...1.39.0">compare
view</a></li>
</ul>
</details>
<br />


Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Evan Mattson <[email protected]>
 2025-07-15 08:29:13 +00:00
dependabot[bot]andEvan Mattson 1e77014180 Python: Update pymongo requirement from <4.13,>=4.8.0 to >=4.8.0,<4.14 in /python (#12494) 
Updates the requirements on
[pymongo](https://github.com/mongodb/mongo-python-driver) to permit the
latest version.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/mongodb/mongo-python-driver/releases">pymongo's
releases</a>.</em></p>
<blockquote>
<h2>PyMongo 4.13.2</h2>
<p>Community notes: <a
href="https://www.mongodb.com/community/forums/t/pymongo-4-13-2-released/323705">https://www.mongodb.com/community/forums/t/pymongo-4-13-2-released/323705</a></p>
</blockquote>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/mongodb/mongo-python-driver/blob/master/doc/changelog.rst">pymongo's
changelog</a>.</em></p>
<blockquote>
<h2>Changes in Version 4.13.2 (2025/06/17)</h2>
<p>Version 4.13.2 is a bug fix release.</p>
<ul>
<li>Fixed a bug where <code>AsyncMongoClient</code> would block the
event loop while creating new connections,
potentially significantly increasing latency for ongoing
operations.</li>
</ul>
<p>Issues Resolved
...............</p>
<p>See the <code>PyMongo 4.13.2 release notes in JIRA</code>_ for the
list of resolved issues
in this release.</p>
<p>.. _PyMongo 4.13.2 release notes in JIRA: <a
href="https://jira.mongodb.org/secure/ReleaseNote.jspa?projectId=10004&amp;version=43937">https://jira.mongodb.org/secure/ReleaseNote.jspa?projectId=10004&amp;version=43937</a></p>
<h2>Changes in Version 4.13.1 (2025/06/10)</h2>
<p>Version 4.13.1 is a bug fix release.</p>
<ul>
<li>Fixed a bug that could raise
<code>ServerSelectionTimeoutError</code> when using timeouts with
<code>AsyncMongoClient</code>.</li>
<li>Fixed a bug that could raise <code>NetworkTimeout</code> errors on
Windows.</li>
</ul>
<p>Issues Resolved
...............</p>
<p>See the <code>PyMongo 4.13.1 release notes in JIRA</code>_ for the
list of resolved issues
in this release.</p>
<p>.. _PyMongo 4.13.1 release notes in JIRA: <a
href="https://jira.mongodb.org/secure/ReleaseNote.jspa?projectId=10004&amp;version=43924">https://jira.mongodb.org/secure/ReleaseNote.jspa?projectId=10004&amp;version=43924</a></p>
<h2>Changes in Version 4.13.0 (2025/05/14)</h2>
<p>PyMongo 4.13 brings a number of changes including:</p>
<ul>
<li>The asynchronous API is now stable and no longer in beta.
See the :mod:<code>pymongo.asynchronous</code> docs
or the <code>migration guide
&lt;https://www.mongodb.com/docs/languages/python/pymongo-driver/current/reference/migration/&gt;</code>_
for more information.</li>
<li>Fixed a bug where
:class:<code>pymongo.write_concern.WriteConcern</code> repr was not
eval-able
when using <code>w=&quot;majority&quot;</code>.</li>
</ul>
<p>Issues Resolved
...............</p>
<p>See the <code>PyMongo 4.13 release notes in JIRA</code>_ for the list
of resolved issues
in this release.</p>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/mongodb/mongo-python-driver/commit/0a150feeeff5e19944b85a55875dd7e91dca6ce9"><code>0a150fe</code></a>
PYTHON-5416 Prep for 4.13.2 release (<a
href="https://redirect.github.com/mongodb/mongo-python-driver/issues/2389">#2389</a>)</li>
<li><a
href="https://github.com/mongodb/mongo-python-driver/commit/ad3417411ae1ea1564402a1caa66f2269b426ca1"><code>ad34174</code></a>
[v4.13] PYTHON-5414 Fix &quot;module service_identity has no attribute
SICertifica...</li>
<li><a
href="https://github.com/mongodb/mongo-python-driver/commit/b127460c908fcb8a36f3ed6c591c6d7a25333b66"><code>b127460</code></a>
[v4.13] PYTHON 5212 - Use asyncio.loop.sock_connect in
_async_create_connecti...</li>
<li><a
href="https://github.com/mongodb/mongo-python-driver/commit/a2077f60ea8da8aeaa17d19a9e744134e90778bb"><code>a2077f6</code></a>
BUMP 4.13.2.dev0</li>
<li><a
href="https://github.com/mongodb/mongo-python-driver/commit/5f800da807bb7772d544a6e6775c74dacdb1ffd5"><code>5f800da</code></a>
[v4.13] PYTHON-5406 - Use correct client for test (<a
href="https://redirect.github.com/mongodb/mongo-python-driver/issues/2378">#2378</a>)</li>
<li><a
href="https://github.com/mongodb/mongo-python-driver/commit/386d1afcb5919177ac48880321e1392e6f4b5576"><code>386d1af</code></a>
[v4.13] PYTHON-5400 Migrate away from Windows Server 2019 runner image
on Git...</li>
<li><a
href="https://github.com/mongodb/mongo-python-driver/commit/1eee90f0e55291738b026d2cc26805efcb9d25ed"><code>1eee90f</code></a>
[v4.13] PYTHON-5405 Use legacy wait_for_read cancellation approach on
Windows...</li>
<li><a
href="https://github.com/mongodb/mongo-python-driver/commit/09a32f6d409ba8eeb7d800abd7cf249fc6022827"><code>09a32f6</code></a>
[v4.13] PYTHON-5406 - AsyncPeriodicExecutor must reset CSOT contextvars
befor...</li>
<li><a
href="https://github.com/mongodb/mongo-python-driver/commit/14417adc3fa2269402190b05089d4bc24c284223"><code>14417ad</code></a>
PYTHON-5411 Prep for 4.13.1 release (<a
href="https://redirect.github.com/mongodb/mongo-python-driver/issues/2370">#2370</a>)</li>
<li><a
href="https://github.com/mongodb/mongo-python-driver/commit/56e6f1c3585d3db6779cd90cc5d79ffc4e81b736"><code>56e6f1c</code></a>
[v4.13] Update release metadata (<a
href="https://redirect.github.com/mongodb/mongo-python-driver/issues/2365">#2365</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/mongodb/mongo-python-driver/compare/4.8.0...4.13.2">compare
view</a></li>
</ul>
</details>
<br />


Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Evan Mattson <[email protected]>
 2025-07-10 02:49:53 +00:00
Evan Mattson ba031e689d Python: Properly handle AzureAI Search results for AzureAIAgent (#12654) 
### Motivation and Context

After the Azure AI Agent service went to GA, there were some updates in
the underlying SDK. When there are azure_ai_search results while running
the agent, they no longer show up as attributes related to the tool
call. They are present in the dictionary, so our current code is failing
when trying to access the attribute. This PR updates how we form the
FunctionCallContent or FunctionResultContent for both azure_ai_search
streaming and non-streaming.

<!-- 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

Update how we form the FunctionCallContent or FunctionResultContent for
both azure_ai_search streaming and non-streaming for the AzureAIAgent.
- Closes #12422

<!-- 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 😄
 2025-07-08 01:53:17 +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
Tao Chen ba000c3368 Python: Use message cache in agent orchestrations (#12618) 
### 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.
-->
Some agent threads don't support adding messages. An example of this is
the copilot studio agent.

In an agent orchestration, an agent may receive multiple messages before
it is asked to generate a response. The currently approach in the
orchestrations would add new messages to an agent thread whenever an
agent receives a message, making the copilot studio agent not compatible
with some orchestrations.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
Instead of adding messages to the agent thread, this PR introduces a
message cache to store messages temporarily before the agent is invoked.


### 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 😄
 2025-07-01 19:00:05 +00:00
Evan Mattson ef392d22ee Python: Bump version to 1.34.0 for a release (#12580) 
### Motivation and Context

Bump version to 1.34.0 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 version to 1.34.0 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
- [X] I didn't break anyone 😄
 2025-06-25 09:16:33 +09:00
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
Evan Mattson 2bfa31b754 Python: pseudo-stream copilot invoke_stream (#12548) 
### Motivation and Context

The current copilot studio client doesn't support streaming invocation.
The underlying orchestration patterns rely on agents to have an
invoke_stream. Since it doesn't exist in the copilot agent, that agent
type cannot be used. This PR implements a pseudo-invoke_stream so that
the agent can be used with patterns - although it doesn't stream the
response back in chunks, it unblocks the use if one desired to use our
new orchestration patterns.

<!-- 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 #12449

<!-- 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 😄
 2025-06-20 15:21:43 +00:00
Evan Mattson 9e3cdffc6b Python: Improve AzureAIAgent get thread msg handling. (#12535) 
### Motivation and Context

Currently, when fetching thread messages for an AzureAIAgent, it assumes
that the agent exists, so we can pull it down and get its id. This may
not always be the case - an agent could have been deleted, but the
thread still exists. We need to account for this.

When creating user messages that we add to the thread, there's no `name`
or `id` parameter allowed. We can, however, add metadata to the message.
Going forward we are adding the `agent_id` as metadata to the message,
so upon retrieval later, we can attempt to get it and return the id with
the user's message. This allows one to see which agent_id has responded
to the user's message:

```
# Messages in the thread (asc order):

# AuthorRole.USER for name=asst_mXwZOwyJLxXGtaYKHizRH6Ip: Hello
# AuthorRole.ASSISTANT for name=asst_mXwZOwyJLxXGtaYKHizRH6Ip: Hello! How can I assist you with the menu today?
# AuthorRole.USER for name=asst_mXwZOwyJLxXGtaYKHizRH6Ip: What is the special soup?
# AuthorRole.ASSISTANT for name=asst_mXwZOwyJLxXGtaYKHizRH6Ip: The special soup today is Clam Chowder. Would you like to know more about it or anything else on the menu?
# AuthorRole.USER for name=asst_mXwZOwyJLxXGtaYKHizRH6Ip: How much does that cost?
# AuthorRole.ASSISTANT for name=asst_mXwZOwyJLxXGtaYKHizRH6Ip: The Clam Chowder costs $9.99. Would you like to order it or need information on other items?
# AuthorRole.USER for name=asst_mXwZOwyJLxXGtaYKHizRH6Ip: Thank you
# AuthorRole.ASSISTANT for name=asst_mXwZOwyJLxXGtaYKHizRH6Ip: You're welcome! If you have any more questions or need assistance with the menu, feel free to ask. Enjoy your meal!
```

<!-- 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 #12435

<!-- 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 😄
 2025-06-19 23:52:07 +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
Evan Mattson 466a610727 Python: Allow for structured outputs with Ollama (#12533) 
### Motivation and Context

Ollama's execution settings currently only allow for `json` literal. We
also want to support structured outputs for models that support it.

<!-- 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 #12355
- Supersedes #12386

<!-- 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 😄
 2025-06-19 15:22:40 +00:00
dependabot[bot] 2e8f17dadd Python: Bump google-cloud-aiplatform from 1.95.1 to 1.97.0 in /python (#12496) 
Bumps
[google-cloud-aiplatform](https://github.com/googleapis/python-aiplatform)
from 1.95.1 to 1.97.0.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/googleapis/python-aiplatform/releases">google-cloud-aiplatform's
releases</a>.</em></p>
<blockquote>
<h2>v1.97.0</h2>
<h2><a
href="https://github.com/googleapis/python-aiplatform/compare/v1.96.0...v1.97.0">1.97.0</a>
(2025-06-11)</h2>
<h3>Features</h3>
<ul>
<li>Add GenAI client (experimental) (<a
href="https://github.com/googleapis/python-aiplatform/commit/166b747b2f1676651cd020c9b66df169ca5920fa">166b747</a>)</li>
<li>Expose UrlContextMetadata API to v1 (<a
href="https://github.com/googleapis/python-aiplatform/commit/b57cbd34ca1de69ded45ea584ff5808fe30bd89c">b57cbd3</a>)</li>
<li>Expose UrlContextMetadata API to v1beta1 (<a
href="https://github.com/googleapis/python-aiplatform/commit/b57cbd34ca1de69ded45ea584ff5808fe30bd89c">b57cbd3</a>)</li>
<li>Integration with Vertex AI Multimodal Datasets: Update
<code>train_dataset</code> and <code>validation_dataset</code> in
<code>sft.train()</code> docstring to include the Vertex Multimodal
Dataset as a dataset source option. (<a
href="https://github.com/googleapis/python-aiplatform/commit/eac1de0e363624edd5abede7eb42de66c5ae4d17">eac1de0</a>)</li>
<li>RAG - Introduce configuration to corpus types, with DocumentCorpus
and MemoryCorpus options. (<a
href="https://github.com/googleapis/python-aiplatform/commit/ede4b5b718197ba077e897e49f8079f3da21422e">ede4b5b</a>)</li>
</ul>
<h3>Bug Fixes</h3>
<ul>
<li>Add default auth scope (<a
href="https://github.com/googleapis/python-aiplatform/commit/3d747e7ea3c7b681c374c6036e008332e7e04888">3d747e7</a>)</li>
<li>Add support for ADK Agents as a supported type for agent engine (<a
href="https://github.com/googleapis/python-aiplatform/commit/6b177ca9261afb07b291d36e4b8e214d359c4296">6b177ca</a>)</li>
<li>Set memory corpus configuration into RagCorpus object. (<a
href="https://github.com/googleapis/python-aiplatform/commit/39d3c702443af4c4ef2c804d1c43f890c8915878">39d3c70</a>)</li>
</ul>
<h2>v1.96.0</h2>
<h2><a
href="https://github.com/googleapis/python-aiplatform/compare/v1.95.1...v1.96.0">1.96.0</a>
(2025-06-03)</h2>
<h3>Features</h3>
<ul>
<li>A new field <code>include_thoughts</code> is added to message
<code>.google.cloud.aiplatform.v1.GenerationConfig.ThinkingConfig</code>
(<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>A new field <code>include_thoughts</code> is added to message
<code>.google.cloud.aiplatform.v1.Part</code> (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>A new field <code>thought_signature</code> is added to message
<code>.google.cloud.aiplatform.v1.Part</code> (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>A new field <code>thought</code> is added to message
<code>.google.cloud.aiplatform.v1.Part</code> (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>Add json schema support to structured output and function
declaration (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>Add json schema support to structured output and function
declaration (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>Add network_attachment to PscInterfaceConfig (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>Add psc_interface_config to CustomJobSpec (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>Add psc_interface_config to PersistentResource (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>Add psc_interface_config to PipelineJob (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>Expose URL Context API to v1 (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>Expose URL Context API to v1beta1 (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
</ul>
<h3>Bug Fixes</h3>
<ul>
<li>Small fix in <code>MultimodalDataset.toBigframes()</code>. (<a
href="https://github.com/googleapis/python-aiplatform/commit/ee12f055cb7cd42b99b0d72908243e94907f5470">ee12f05</a>)</li>
</ul>
<h3>Documentation</h3>
<ul>
<li>Allow field <code>thought</code> to be set as input (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
</ul>
<h3>Miscellaneous Chores</h3>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/googleapis/python-aiplatform/blob/main/CHANGELOG.md">google-cloud-aiplatform's
changelog</a>.</em></p>
<blockquote>
<h2><a
href="https://github.com/googleapis/python-aiplatform/compare/v1.96.0...v1.97.0">1.97.0</a>
(2025-06-11)</h2>
<h3>Features</h3>
<ul>
<li>Add GenAI client (experimental) (<a
href="https://github.com/googleapis/python-aiplatform/commit/166b747b2f1676651cd020c9b66df169ca5920fa">166b747</a>)</li>
<li>Expose UrlContextMetadata API to v1 (<a
href="https://github.com/googleapis/python-aiplatform/commit/b57cbd34ca1de69ded45ea584ff5808fe30bd89c">b57cbd3</a>)</li>
<li>Expose UrlContextMetadata API to v1beta1 (<a
href="https://github.com/googleapis/python-aiplatform/commit/b57cbd34ca1de69ded45ea584ff5808fe30bd89c">b57cbd3</a>)</li>
<li>Integration with Vertex AI Multimodal Datasets: Update
<code>train_dataset</code> and <code>validation_dataset</code> in
<code>sft.train()</code> docstring to include the Vertex Multimodal
Dataset as a dataset source option. (<a
href="https://github.com/googleapis/python-aiplatform/commit/eac1de0e363624edd5abede7eb42de66c5ae4d17">eac1de0</a>)</li>
<li>RAG - Introduce configuration to corpus types, with DocumentCorpus
and MemoryCorpus options. (<a
href="https://github.com/googleapis/python-aiplatform/commit/ede4b5b718197ba077e897e49f8079f3da21422e">ede4b5b</a>)</li>
</ul>
<h3>Bug Fixes</h3>
<ul>
<li>Add default auth scope (<a
href="https://github.com/googleapis/python-aiplatform/commit/3d747e7ea3c7b681c374c6036e008332e7e04888">3d747e7</a>)</li>
<li>Add support for ADK Agents as a supported type for agent engine (<a
href="https://github.com/googleapis/python-aiplatform/commit/6b177ca9261afb07b291d36e4b8e214d359c4296">6b177ca</a>)</li>
<li>Set memory corpus configuration into RagCorpus object. (<a
href="https://github.com/googleapis/python-aiplatform/commit/39d3c702443af4c4ef2c804d1c43f890c8915878">39d3c70</a>)</li>
</ul>
<h2><a
href="https://github.com/googleapis/python-aiplatform/compare/v1.95.1...v1.96.0">1.96.0</a>
(2025-06-03)</h2>
<h3>Features</h3>
<ul>
<li>A new field <code>include_thoughts</code> is added to message
<code>.google.cloud.aiplatform.v1.GenerationConfig.ThinkingConfig</code>
(<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>A new field <code>include_thoughts</code> is added to message
<code>.google.cloud.aiplatform.v1.Part</code> (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>A new field <code>thought_signature</code> is added to message
<code>.google.cloud.aiplatform.v1.Part</code> (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>A new field <code>thought</code> is added to message
<code>.google.cloud.aiplatform.v1.Part</code> (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>Add json schema support to structured output and function
declaration (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>Add json schema support to structured output and function
declaration (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>Add network_attachment to PscInterfaceConfig (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>Add psc_interface_config to CustomJobSpec (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>Add psc_interface_config to PersistentResource (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>Add psc_interface_config to PipelineJob (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>Expose URL Context API to v1 (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
<li>Expose URL Context API to v1beta1 (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
</ul>
<h3>Bug Fixes</h3>
<ul>
<li>Small fix in <code>MultimodalDataset.toBigframes()</code>. (<a
href="https://github.com/googleapis/python-aiplatform/commit/ee12f055cb7cd42b99b0d72908243e94907f5470">ee12f05</a>)</li>
</ul>
<h3>Documentation</h3>
<ul>
<li>Allow field <code>thought</code> to be set as input (<a
href="https://github.com/googleapis/python-aiplatform/commit/f2244aac08867e292a07ec7aa958f4f0c6eea09d">f2244aa</a>)</li>
</ul>
<h3>Miscellaneous Chores</h3>
<ul>
<li>Release 1.96.0 (<a
href="https://github.com/googleapis/python-aiplatform/commit/97be629f2790b356340ed6b6ebfe78bff73afca5">97be629</a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/da09275f08109a9cb39d7838cf67e7e75b10af84"><code>da09275</code></a>
chore(main): release 1.97.0 (<a
href="https://redirect.github.com/googleapis/python-aiplatform/issues/5385">#5385</a>)</li>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/1fe610e13e2fb76372378f5103b5d3faec0a2ab1"><code>1fe610e</code></a>
chore: add evaluate method to GenAI evals module</li>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/fde5c658aeea27e30a6a9d75a8813f161c725dad"><code>fde5c65</code></a>
chore: add metric handlers for GenAI evals module</li>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/5b1b83cf08b37ed9c01378b897434f760d01583e"><code>5b1b83c</code></a>
chore: Add evals metric validation, load/dump, and versioning utils</li>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/3d747e7ea3c7b681c374c6036e008332e7e04888"><code>3d747e7</code></a>
fix: Add default auth scope</li>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/eac1de0e363624edd5abede7eb42de66c5ae4d17"><code>eac1de0</code></a>
feat: Integration with Vertex AI Multimodal Datasets: Update
<code>train_dataset</code> ...</li>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/6b177ca9261afb07b291d36e4b8e214d359c4296"><code>6b177ca</code></a>
fix: Add support for ADK Agents as a supported type for agent
engine</li>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/b57cbd34ca1de69ded45ea584ff5808fe30bd89c"><code>b57cbd3</code></a>
Copybara import of the project:</li>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/9e37d2ea0ff682dadb5b81ec8c0904680e82c7b8"><code>9e37d2e</code></a>
chore: Fix sample lint</li>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/467e9ed78e13a9aef1b09211aa0210b84009dd3d"><code>467e9ed</code></a>
chore: add eval dataset merging utilities</li>
<li>Additional commits viewable in <a
href="https://github.com/googleapis/python-aiplatform/compare/v1.95.1...v1.97.0">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=google-cloud-aiplatform&package-manager=pip&previous-version=1.95.1&new-version=1.97.0)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-06-19 15:21:24 +00:00
Eduard van Valkenburg bd4168316d Python: add Foundry local sample (#12214) 
### 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.
-->
Sample on how to use Foundry Local with SK.

### 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 😄
 2025-06-19 08:18:18 +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
Nico MöllerChrisEvan Mattson
 		206655adbb Python: Add check for not approved and approved for Agent Sample (#12316) 
### Motivation and Context

I was having a Demo with the Agents, and found that
`step06_chat_completion_agent_group_chat.py` sample always terminated
after one iteration.

The Reviewer Agent answered "not approved", which also triggered the
`Termination Strategy`, due to the fact that the word `approved` is also
in `not approved`.
To only trigger when there is a real approval I added a check if the
answer is `approved` **and** the answer also don't include `not approve`


### 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: Chris <[email protected]>
Co-authored-by: Evan Mattson <[email protected]>
 2025-06-19 05:34:53 +00:00
dependabot[bot] 6ab348991f Python: Bump torch from 2.7.0 to 2.7.1 in /python (#12424) 
Bumps [torch](https://github.com/pytorch/pytorch) from 2.7.0 to 2.7.1.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/pytorch/pytorch/releases">torch's
releases</a>.</em></p>
<blockquote>
<h2>PyTorch 2.7.1 Release, bug fix release</h2>
<p>This release is meant to fix the following issues (regressions /
silent correctness):</p>
<h3>Torch.compile</h3>
<p>Fix Excessive cudagraph re-recording for HF LLM models (<a
href="https://redirect.github.com/pytorch/pytorch/pull/152287">#152287</a>)
Fix torch.compile on some HuggingFace models (<a
href="https://redirect.github.com/pytorch/pytorch/pull/151154">#151154</a>)
Fix crash due to Exception raised inside torch.autocast (<a
href="https://redirect.github.com/pytorch/pytorch/pull/152503">#152503</a>)
Improve Error logging in torch.compile (<a
href="https://redirect.github.com/pytorch/pytorch/pull/149831">#149831</a>)
Mark mutable custom operators as cacheable in torch.compile (<a
href="https://redirect.github.com/pytorch/pytorch/pull/151194">#151194</a>)
Implement workaround for a graph break with older version einops (<a
href="https://redirect.github.com/pytorch/pytorch/pull/153925">#153925</a>)
Fix an issue with tensor.view(dtype).copy_(...) (<a
href="https://redirect.github.com/pytorch/pytorch/pull/151598">#151598</a>)</p>
<h3>Flex Attention</h3>
<p>Fix assertion error due to inductor permuting inputs to flex
attention (<a
href="https://redirect.github.com/pytorch/pytorch/pull/151959">#151959</a>)
Fix performance regression on nanogpt speedrun (<a
href="https://redirect.github.com/pytorch/pytorch/pull/152641">#152641</a>)</p>
<h3>Distributed</h3>
<p>Fix extra CUDA context created by barrier (<a
href="https://redirect.github.com/pytorch/pytorch/pull/149144">#149144</a>)
Fix an issue related to Distributed Fused Adam in Rocm/APEX when using
nccl_ub feature (<a
href="https://redirect.github.com/pytorch/pytorch/pull/150010">#150010</a>)
Add a workaround random hang in non-blocking API mode in NCCL 2.26 (<a
href="https://redirect.github.com/pytorch/pytorch/pull/154055">#154055</a>)</p>
<h3>MacOS</h3>
<p>Fix MacOS compilation error with Clang 17 (<a
href="https://redirect.github.com/pytorch/pytorch/pull/151344">#151316</a>)
Fix binary kernels produce incorrect results when one of the tensor
arguments is from a wrapped scalar on MPS devices (<a
href="https://redirect.github.com/pytorch/pytorch/pull/152997">#152997</a>)</p>
<h3>Other</h3>
<p>Improve PyTorch Wheel size due to introduction of addition of 128 bit
vectorization (<a
href="https://redirect.github.com/pytorch/pytorch/pull/148320">#148320</a>)
(<a
href="https://redirect.github.com/pytorch/pytorch/pull/152396">#152396</a>)
Fix fmsub function definition (<a
href="https://redirect.github.com/pytorch/pytorch/pull/152075">#152075</a>)
Fix Floating point exception in torch.mkldnn_max_pool2d (<a
href="https://redirect.github.com/pytorch/pytorch/pull/151848">#151848</a>)
Fix abnormal inference output with XPU:1 device (<a
href="https://redirect.github.com/pytorch/pytorch/pull/153067">#153067</a>)
Fix Illegal Instruction Caused by grid_sample on Windows (<a
href="https://redirect.github.com/pytorch/pytorch/pull/152613">#152613</a>)
Fix ONNX decomposition does not preserve custom
CompositeImplicitAutograd ops (<a
href="https://redirect.github.com/pytorch/pytorch/pull/151826">#151826</a>)
Fix error with dynamic linking of libgomp library (<a
href="https://redirect.github.com/pytorch/pytorch/pull/150084">#150084</a>)
Fix segfault in profiler with Python 3.13 (<a
href="https://redirect.github.com/pytorch/pytorch/pull/153848">#153848</a>)</p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/pytorch/pytorch/commit/e2d141dbde55c2a4370fac5165b0561b6af4798b"><code>e2d141d</code></a>
set thread_work_size to 4 for unrolled kernel (<a
href="https://redirect.github.com/pytorch/pytorch/issues/154541">#154541</a>)</li>
<li><a
href="https://github.com/pytorch/pytorch/commit/121419899b9955bbd41b14a207205a9b298ed3f0"><code>1214198</code></a>
[c10d] Fix extra CUDA context created by barrier (<a
href="https://redirect.github.com/pytorch/pytorch/issues/152834">#152834</a>)</li>
<li><a
href="https://github.com/pytorch/pytorch/commit/790cc2f02c193b955a1225cea2f79b624a3013bc"><code>790cc2f</code></a>
[c10d] Add more tests to prevent extra context (<a
href="https://redirect.github.com/pytorch/pytorch/issues/154179">#154179</a>)</li>
<li><a
href="https://github.com/pytorch/pytorch/commit/62ea99a94771dc547320583576b0bc10ded6a3ce"><code>62ea99a</code></a>
[CI] Remove the xpu env source for linux binary validate (<a
href="https://redirect.github.com/pytorch/pytorch/issues/154409">#154409</a>)</li>
<li><a
href="https://github.com/pytorch/pytorch/commit/941732c8298c3a5f5e72b4f744c9d723b751967e"><code>941732c</code></a>
[ROCm] Added unit test to test the cuda_pluggable allocator (<a
href="https://redirect.github.com/pytorch/pytorch/issues/154135">#154135</a>)</li>
<li><a
href="https://github.com/pytorch/pytorch/commit/769d5da70224ee032fce196b9400927f8b515540"><code>769d5da</code></a>
[binary builds] Linux aarch64 CUDA builds. Make sure tag is set
correctly (<a
href="https://redirect.github.com/pytorch/pytorch/issues/1">#1</a>...</li>
<li><a
href="https://github.com/pytorch/pytorch/commit/306ba122bd4653875d450a94918227a180ebe5d4"><code>306ba12</code></a>
Fix uint view copy (<a
href="https://redirect.github.com/pytorch/pytorch/issues/151598">#151598</a>)
(<a
href="https://redirect.github.com/pytorch/pytorch/issues/154121">#154121</a>)</li>
<li><a
href="https://github.com/pytorch/pytorch/commit/1ae99532808dac1b833df6bfa37fb21f6e17aa0f"><code>1ae9953</code></a>
[ROCm] Update CUDAPluggableAllocator.h (<a
href="https://redirect.github.com/pytorch/pytorch/issues/1984">#1984</a>)
(<a
href="https://redirect.github.com/pytorch/pytorch/issues/153974">#153974</a>)</li>
<li><a
href="https://github.com/pytorch/pytorch/commit/4a815ed15aa99dee3527011cfdd11068dcb946ad"><code>4a815ed</code></a>
ci: Set minimum cmake version for halide build (<a
href="https://redirect.github.com/pytorch/pytorch/issues/154122">#154122</a>)</li>
<li><a
href="https://github.com/pytorch/pytorch/commit/4c7314e78c3aef08ef9ac674ef708200fb10c35c"><code>4c7314e</code></a>
[Dynamo] Fix einops regression (<a
href="https://redirect.github.com/pytorch/pytorch/issues/154053">#154053</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/pytorch/pytorch/compare/v2.7.0...v2.7.1">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=torch&package-manager=pip&previous-version=2.7.0&new-version=2.7.1)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-06-19 05:18:34 +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
Eduard van Valkenburg 8d1b3fd551 Python: fixes for new MCP types and small openapi fix (#12486) 
### 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 to include AudioContent for MCP
Small typing improvement in OpenAPI.

### 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 😄
 2025-06-16 21:32:42 +00:00
Tao Chen 9b8f8e22c3 Python: Correct chat completion agent history truncation samples (#12474) 
### 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.
-->
While addressing the developer in this
[discussion](https://github.com/microsoft/semantic-kernel/discussions/12450),
I notice that there are a few changes needed to the improve the
truncation history reducer samples of the chat completion agent.

### Description

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


### Contribution Checklist

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

- [ ] The code builds clean without any errors or warnings
- [ ] 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
- [ ] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
 2025-06-13 20:11:00 +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
Evan Mattson 029732dc36 Python: Bump Python version to 1.33.0 for release (#12427) 
### Motivation and Context

Bump Python version to 1.33.0 for 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 Python version to 1.33.0 for 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
- [X] I didn't break anyone 😄
 2025-06-10 09:00:08 +09:00
Evan Mattson 4b23389f71 Python: Emit token usage with streaming chat completion agent. (#12416) 
### Motivation and Context

The chat completion agent was not emitting token using during streaming
invocation because we were only allowing through `response.items`. In
the case of token usage, `response.items` is [] and the usage is
contained as part of the message's `metadata` dict. This PR fixes that
bug and allows for `response.items or response.metadata.get("usage")`.
Two new samples are added to the concepts/agents/chat_completion dir to
show how one can track token use for streaming and non-streaming agent
invocation. Token usage handling is also added to the chat completion
agent integration 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.
-->

### Description

- Fixes a bug where we weren't emitting the streaming token usage for
the chat completion agent. Also now includes the `prompt_tokens_details`
and `completion_tokens_details` models that are returned, but not
previously handled.
- Adds new samples
- Updates integration tests to track token usage and make sure they're
non-zero.
- Closes #12411

<!-- 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 23:12:05 +00:00
Evan Mattson c3c8dfabc6 Python: Bing custom search tool content support (#12415) 
### Motivation and Context

In the `azure-ai-agent` package version 1.1.0b1, they provided the
`AgentsNamedToolChoiceType.BING_CUSTOM_SEARCH` enum. Adding this to then
provide support for generating bing grounding content for
streaming/non-streaming path.

<!-- 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 BING_CUSTOM_SEARCH enum to allow for content support.
- Bumps `pyproject.toml` `azure-ai-agents` min allowed version to
`1.1.0b1` which includes this new enum.

<!-- 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 23:10:44 +00:00
Evan Mattson 3e31c3bdc6 Python: Remove planner-related code and samples. (#12417) 
### Motivation and Context

Per deprecation method, removing planner-related code after June 1,
2025.

<!-- 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

- Removing planner-related code.
- Closes #12400

<!-- 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 😄
 2025-06-09 21:35:23 +00:00
Evan Mattson e0221e58ce Python: Fix OpenAPI concept sample (#12418) 
### Motivation and Context

An OpenAPI concept sample that we have is broken. This PR fixes it to
run properly based on the current OpenAPI plugin handling.

<!-- 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

Fixes the broken OpenAPI sample.

<!-- 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 21:33:06 +00:00
dependabot[bot] 576a49b7fb Python: Bump google-cloud-aiplatform from 1.93.0 to 1.95.1 in /python (#12346) 
Bumps
[google-cloud-aiplatform](https://github.com/googleapis/python-aiplatform)
from 1.93.0 to 1.95.1.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/googleapis/python-aiplatform/releases">google-cloud-aiplatform's
releases</a>.</em></p>
<blockquote>
<h2>v1.95.1</h2>
<h2><a
href="https://github.com/googleapis/python-aiplatform/compare/v1.95.0...v1.95.1">1.95.1</a>
(2025-05-30)</h2>
<h3>Features</h3>
<ul>
<li>Add support to process RAG response and generate inline citations in
RAG v1. (<a
href="https://github.com/googleapis/python-aiplatform/commit/2b2dc4fbc5d52b16159868b112affafa8ac716ae">2b2dc4f</a>)</li>
<li>Register async methods to AdkApp. (<a
href="https://github.com/googleapis/python-aiplatform/commit/cb2754de4707228bf7df7f7be078c61b77abd314">cb2754d</a>)</li>
</ul>
<h3>Bug Fixes</h3>
<ul>
<li>Fix CachedContent.create if the kms_key_name is not given (<a
href="https://github.com/googleapis/python-aiplatform/commit/05986c068b1719de22ee32536ec592ea04ee012b">05986c0</a>)</li>
</ul>
<h3>Miscellaneous Chores</h3>
<ul>
<li>Release 1.95.1 (<a
href="https://github.com/googleapis/python-aiplatform/commit/1d2387f1e418efa8db7c1e14f37d36647662b3d2">1d2387f</a>)</li>
</ul>
<h2>v1.95.0</h2>
<h2><a
href="https://github.com/googleapis/python-aiplatform/compare/v1.94.0...v1.95.0">1.95.0</a>
(2025-05-28)</h2>
<h3>Features</h3>
<ul>
<li>[vertexai] Fix the result of export function (<a
href="https://github.com/googleapis/python-aiplatform/commit/9427b158dd9d3d8a6ec56024484855947d4a0eac">9427b15</a>)</li>
<li>Add async support for reasoning engine. (<a
href="https://github.com/googleapis/python-aiplatform/commit/1b7d29cb8727a8ce49f849705451aba64c4f88dd">1b7d29c</a>)</li>
<li>Introduce RAG as context/memory store for Gemini Live API (<a
href="https://github.com/googleapis/python-aiplatform/commit/787c60fc1f79f80c693df1300f8a33cc17a08ee1">787c60f</a>)</li>
<li>Update AdkApp template to match ADK async interface. After this
change, AdkApp will only work with ADK &gt;= 1.0.0. (<a
href="https://github.com/googleapis/python-aiplatform/commit/e1745d7767780613de2211ef0fb302105eff9cef">e1745d7</a>)</li>
</ul>
<h2>v1.94.0</h2>
<h2><a
href="https://github.com/googleapis/python-aiplatform/compare/v1.93.1...v1.94.0">1.94.0</a>
(2025-05-22)</h2>
<h3>Features</h3>
<ul>
<li>Add checkpoint ID to endpoint proto (<a
href="https://github.com/googleapis/python-aiplatform/commit/f0812e3983df66ca4b53add8f8a8e9a4a9a7699a">f0812e3</a>)</li>
<li>Add checkpoint ID to endpoint proto (<a
href="https://github.com/googleapis/python-aiplatform/commit/f0812e3983df66ca4b53add8f8a8e9a4a9a7699a">f0812e3</a>)</li>
<li>Add encryption_spec to Model Monitoring public preview API (<a
href="https://github.com/googleapis/python-aiplatform/commit/f0812e3983df66ca4b53add8f8a8e9a4a9a7699a">f0812e3</a>)</li>
<li>Add VertexAISearch.max_results, filter, data_store_specs options (<a
href="https://github.com/googleapis/python-aiplatform/commit/f0812e3983df66ca4b53add8f8a8e9a4a9a7699a">f0812e3</a>)</li>
<li>Add VertexAISearch.max_results, filter, data_store_specs options (<a
href="https://github.com/googleapis/python-aiplatform/commit/f0812e3983df66ca4b53add8f8a8e9a4a9a7699a">f0812e3</a>)</li>
<li>Adding thoughts_token_count to prediction service (<a
href="https://github.com/googleapis/python-aiplatform/commit/f0812e3983df66ca4b53add8f8a8e9a4a9a7699a">f0812e3</a>)</li>
<li>Adding thoughts_token_count to v1beta1 client library (<a
href="https://github.com/googleapis/python-aiplatform/commit/f0812e3983df66ca4b53add8f8a8e9a4a9a7699a">f0812e3</a>)</li>
<li>Update preview <code>create_corpus</code> to accept
<code>encryption_spec</code> in <code>rag_data.py</code> (<a
href="https://github.com/googleapis/python-aiplatform/commit/ad821c58f834981adb9759013248e7156f3706b9">ad821c5</a>)</li>
</ul>
<h3>Bug Fixes</h3>
<ul>
<li>Throw error when user is using google-adk&gt;=1.0.0 as it is not
well supported for now. (<a
href="https://github.com/googleapis/python-aiplatform/commit/634bb78c32168fac7ac084a1fcbdede8e45bdae8">634bb78</a>)</li>
</ul>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/googleapis/python-aiplatform/blob/main/CHANGELOG.md">google-cloud-aiplatform's
changelog</a>.</em></p>
<blockquote>
<h2><a
href="https://github.com/googleapis/python-aiplatform/compare/v1.95.0...v1.95.1">1.95.1</a>
(2025-05-30)</h2>
<h3>Features</h3>
<ul>
<li>Add support to process RAG response and generate inline citations in
RAG v1. (<a
href="https://github.com/googleapis/python-aiplatform/commit/2b2dc4fbc5d52b16159868b112affafa8ac716ae">2b2dc4f</a>)</li>
<li>Register async methods to AdkApp. (<a
href="https://github.com/googleapis/python-aiplatform/commit/cb2754de4707228bf7df7f7be078c61b77abd314">cb2754d</a>)</li>
</ul>
<h3>Bug Fixes</h3>
<ul>
<li>Fix CachedContent.create if the kms_key_name is not given (<a
href="https://github.com/googleapis/python-aiplatform/commit/05986c068b1719de22ee32536ec592ea04ee012b">05986c0</a>)</li>
</ul>
<h3>Miscellaneous Chores</h3>
<ul>
<li>Release 1.95.1 (<a
href="https://github.com/googleapis/python-aiplatform/commit/1d2387f1e418efa8db7c1e14f37d36647662b3d2">1d2387f</a>)</li>
</ul>
<h2><a
href="https://github.com/googleapis/python-aiplatform/compare/v1.94.0...v1.95.0">1.95.0</a>
(2025-05-28)</h2>
<h3>Features</h3>
<ul>
<li>[vertexai] Fix the result of export function (<a
href="https://github.com/googleapis/python-aiplatform/commit/9427b158dd9d3d8a6ec56024484855947d4a0eac">9427b15</a>)</li>
<li>Add async support for reasoning engine. (<a
href="https://github.com/googleapis/python-aiplatform/commit/1b7d29cb8727a8ce49f849705451aba64c4f88dd">1b7d29c</a>)</li>
<li>Introduce RAG as context/memory store for Gemini Live API (<a
href="https://github.com/googleapis/python-aiplatform/commit/787c60fc1f79f80c693df1300f8a33cc17a08ee1">787c60f</a>)</li>
<li>Update AdkApp template to match ADK async interface. After this
change, AdkApp will only work with ADK &gt;= 1.0.0. (<a
href="https://github.com/googleapis/python-aiplatform/commit/e1745d7767780613de2211ef0fb302105eff9cef">e1745d7</a>)</li>
</ul>
<h2><a
href="https://github.com/googleapis/python-aiplatform/compare/v1.93.1...v1.94.0">1.94.0</a>
(2025-05-22)</h2>
<h3>Features</h3>
<ul>
<li>Add checkpoint ID to endpoint proto (<a
href="https://github.com/googleapis/python-aiplatform/commit/f0812e3983df66ca4b53add8f8a8e9a4a9a7699a">f0812e3</a>)</li>
<li>Add checkpoint ID to endpoint proto (<a
href="https://github.com/googleapis/python-aiplatform/commit/f0812e3983df66ca4b53add8f8a8e9a4a9a7699a">f0812e3</a>)</li>
<li>Add encryption_spec to Model Monitoring public preview API (<a
href="https://github.com/googleapis/python-aiplatform/commit/f0812e3983df66ca4b53add8f8a8e9a4a9a7699a">f0812e3</a>)</li>
<li>Add VertexAISearch.max_results, filter, data_store_specs options (<a
href="https://github.com/googleapis/python-aiplatform/commit/f0812e3983df66ca4b53add8f8a8e9a4a9a7699a">f0812e3</a>)</li>
<li>Add VertexAISearch.max_results, filter, data_store_specs options (<a
href="https://github.com/googleapis/python-aiplatform/commit/f0812e3983df66ca4b53add8f8a8e9a4a9a7699a">f0812e3</a>)</li>
<li>Adding thoughts_token_count to prediction service (<a
href="https://github.com/googleapis/python-aiplatform/commit/f0812e3983df66ca4b53add8f8a8e9a4a9a7699a">f0812e3</a>)</li>
<li>Adding thoughts_token_count to v1beta1 client library (<a
href="https://github.com/googleapis/python-aiplatform/commit/f0812e3983df66ca4b53add8f8a8e9a4a9a7699a">f0812e3</a>)</li>
<li>Update preview <code>create_corpus</code> to accept
<code>encryption_spec</code> in <code>rag_data.py</code> (<a
href="https://github.com/googleapis/python-aiplatform/commit/ad821c58f834981adb9759013248e7156f3706b9">ad821c5</a>)</li>
</ul>
<h3>Bug Fixes</h3>
<ul>
<li>Throw error when user is using google-adk&gt;=1.0.0 as it is not
well supported for now. (<a
href="https://github.com/googleapis/python-aiplatform/commit/634bb78c32168fac7ac084a1fcbdede8e45bdae8">634bb78</a>)</li>
</ul>
<h2><a
href="https://github.com/googleapis/python-aiplatform/compare/v1.93.0...v1.93.1">1.93.1</a>
(2025-05-20)</h2>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/060ff3bd214308e71d8cd5f8458e2bc72e943096"><code>060ff3b</code></a>
chore(main): release 1.95.1 (<a
href="https://redirect.github.com/googleapis/python-aiplatform/issues/5363">#5363</a>)</li>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/1d2387f1e418efa8db7c1e14f37d36647662b3d2"><code>1d2387f</code></a>
chore: release 1.95.1</li>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/05986c068b1719de22ee32536ec592ea04ee012b"><code>05986c0</code></a>
fix: Fix CachedContent.create if the kms_key_name is not given</li>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/b7968d8fb303e6c0ae2e5a1f5e51a824ed04e42e"><code>b7968d8</code></a>
chore: Update Gen AI types</li>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/17a6385c8402eafe0db09aad430dff7788ff49b5"><code>17a6385</code></a>
chore: Update Gen AI types</li>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/cb2754de4707228bf7df7f7be078c61b77abd314"><code>cb2754d</code></a>
feat: Register async methods to AdkApp.</li>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/4aa9eee4f89767bcec22ae56a2c1ad4393c4ff45"><code>4aa9eee</code></a>
Copybara import of the project:</li>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/2b2dc4fbc5d52b16159868b112affafa8ac716ae"><code>2b2dc4f</code></a>
feat: add support to process RAG response and generate inline citations
in RA...</li>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/d0a2bab3ee01f955a5da8b1175f258b974d0229b"><code>d0a2bab</code></a>
chore(main): release 1.95.0 (<a
href="https://redirect.github.com/googleapis/python-aiplatform/issues/5350">#5350</a>)</li>
<li><a
href="https://github.com/googleapis/python-aiplatform/commit/787c60fc1f79f80c693df1300f8a33cc17a08ee1"><code>787c60f</code></a>
Copybara import of the project:</li>
<li>Additional commits viewable in <a
href="https://github.com/googleapis/python-aiplatform/compare/v1.93.0...v1.95.1">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=google-cloud-aiplatform&package-manager=pip&previous-version=1.93.0&new-version=1.95.1)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-06-09 21:17:21 +00:00