### Description
Adds `function_choice_behavior` parameter to Azure AI and OpenAI
Assistant agents, aligning them with the existing Responses agent and
Chat Completion agent APIs.
### Changes
- Add `function_choice_behavior` parameter to
`invoke`/`invoke_stream`/`get_response` on both `AzureAIAgent` and
`OpenAIAssistantAgent` public APIs
- Add `function_choice_behavior` parameter to internal
`AzureAIAgentThreadActions` and `AssistantThreadActions`
`invoke`/`invoke_stream` methods
- Support `tools` parameter override for SDK-level tools
(CodeInterpreter, FileSearch, etc.)
- Filter kernel functions based on `FunctionChoiceBehavior`
configuration
- Validate that only `Auto` type with auto-invoke enabled is supported
- Fix `_get_tools` in OpenAI path to use passed `kernel` parameter
instead of `agent.kernel`
- Add comprehensive unit tests for both thread actions and public agent
APIs
---------
Co-authored-by: Copilot <[email protected]>
Update OpenAPI document parsing to gate file and HTTP ref resolution
separately.
### Breaking change
- `RESOLVE_FILES` is no longer enabled by default. Only internal JSON
pointer references are resolved by default.
- Users with multi-file OpenAPI specs must now pass
`enable_file_ref_resolution=True` via
`OpenAPIFunctionExecutionParameters`.
- `enable_external_ref_resolution` has been renamed to
`enable_http_ref_resolution`.
---------
Co-authored-by: Copilot <[email protected]>
### Motivation and Context
Improvements for MCP tool calls by adding an optional sampling callback.
<!-- 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
Improvements for MCP tool calls by adding an optional sampling callback.
<!-- 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 😄
---------
Co-authored-by: Copilot <[email protected]>
### Motivation and Context
CI fails with `AttributeError: 'SearchIndexClient' object has no
attribute '_endpoint'` when `azure-search-documents` resolves to 12.0.0
(released 2026-04-01). The 12.0.0 release migrated from AutoRest to
TypeSpec code generation, removing private attributes `_endpoint` and
`_credential` from `SearchIndexClient`.
CI uses `uv sync -U` which upgrades past the lockfile, pulling in 12.0.0
since `pyproject.toml` specifies `>= 11.6.0b4` with no upper bound.
### Description
Stop reading `SearchIndexClient._endpoint` and `._credential`. Instead,
store endpoint and credential as explicit fields on `AzureAISearchStore`
and `AzureAISearchCollection`, and pass them directly when constructing
`SearchClient`.
**Changes:**
- `_get_search_client()` accepts explicit `endpoint` + `credential`
params instead of extracting from `SearchIndexClient` private attrs
- `_resolve_credential()` new helper extracted from
`_get_search_index_client()` for reuse
- `AzureAISearchStore` / `AzureAISearchCollection` store
`search_endpoint` and `search_credential` as fields, thread them through
construction
- Tests updated to assert on public fields instead of private SDK
attributes
### Contribution Checklist
- [x] The code builds clean without any errors or warnings
- [x] All unit tests pass with both `azure-search-documents==11.7.0b2`
and `==12.0.0`
- [x] No breaking changes to public API
---------
Co-authored-by: Copilot <[email protected]>
Apply `urllib.parse.quote(safe='')` to path parameter values before
substitution in `build_path()`, consistent with the .NET implementation
which uses `HttpUtility.UrlEncode`.
### Changes
- `rest_api_operation.py`: encode path parameter values per RFC 3986
- `test_sk_openapi.py`: add tests for encoded path parameters
- `pyproject.toml` / `uv.lock`: pin `azure-search-documents >= 11.6.0b4,
< 12.0.0`
### Pin azure-search-documents < 12.0.0
Version 12.0.0 removed the internal `_endpoint` attribute from
`SearchIndexClient`, which breaks `AzureAISearchCollection`
initialization at `azure_ai_search.py:158`. Pinning to `< 12.0.0` until
the code is updated to use the new public API.
### Tests
All existing and new `build_path` tests pass.
---------
Co-authored-by: Copilot <[email protected]>
## Summary
- Minor defense-in-depth hardening for `InMemoryCollection` filter
parsing.
- Extends the internal dunder attribute blocklist and adds a regression
test covering the blocked set.
## Test plan
- [x] `uv run pytest tests/unit/connectors/memory/test_in_memory.py`
### Motivation and Context
This PR updates the Jinja2 and Handlebars prompt-template helpers to
serialize chat messages through the existing XML/message serializer
instead of assembling message XML manually. It also aligns the
prompt-template samples with the serializer-backed helper and adds
regression coverage for common message content.
<!-- 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
Prompt template message serialize improvements.
<!-- 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 😄
---------
Co-authored-by: MAF Dashboard Bot <[email protected]>
Co-authored-by: Copilot <[email protected]>
### Motivation and Context
Closes#12442
When `ChatCompletionAgent` instances are used as plugins with
`GoogleAIChatCompletion`, the application crashes with:
```
ValueError: Unknown field for Schema: anyOf
```
**Root cause**: The Semantic Kernel JSON schema builder generates
`anyOf` for Union types (e.g. `str | list[str]` on the agent's
`messages` parameter) and type-as-array for Optional types (e.g.
`["string", "null"]`). Google AI's protobuf `Schema` does not support
these constructs.
### Description
Add `sanitize_schema_for_google_ai()` to `shared_utils.py` that
recursively rewrites unsupported schema constructs:
- `anyOf` / `oneOf` with a null variant → single type + `nullable: true`
- `anyOf` / `oneOf` without null → picks the first variant
- `type` as array (e.g. `["string", "null"]`) → single type + `nullable:
true`
Applied in both
`kernel_function_metadata_to_google_ai_function_call_format()` and
`kernel_function_metadata_to_vertex_ai_function_call_format()`.
### Contribution Checklist
- [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)
- [x] The existing tests pass, and I have added 12 new regression tests
- [x] I didn't break any existing functionality
> [!NOTE]
> AI-assisted contribution: Claude helped with code review, test
generation, and formatting.
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
Co-authored-by: Evan Mattson <[email protected]>
## Summary
Fixes#13483
### Motivation and Context
When `use_vertexai=True`, users authenticate via Application Default
Credentials (ADC) and don't need an API key. However, the initialization
check for `api_key` runs unconditionally, blocking Vertex AI users with:
```
ServiceInitializationError: The API key is required when use_vertexai is False.
```
### Description
Guard the `api_key` validation with `not
google_ai_settings.use_vertexai` in all three Google AI service classes:
- `GoogleAIChatCompletion`
- `GoogleAITextCompletion`
- `GoogleAITextEmbedding`
The error message already reads *"when use_vertexai is False"*, so the
condition now matches the intent.
### Before / After
```python
# Before — fails even with use_vertexai=True
GoogleAIChatCompletion(
use_vertexai=True,
cloud_project_id="my-project",
cloud_region="us-central1"
)
# → ServiceInitializationError: The API key is required when use_vertexai is False.
# After — works correctly
GoogleAIChatCompletion(
use_vertexai=True,
cloud_project_id="my-project",
cloud_region="us-central1"
)
# → Initializes successfully, uses ADC for authentication
```
### Contribution Checklist
- [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)
- [x] The code follows the [SK coding
standards](https://github.com/microsoft/semantic-kernel/blob/main/python/README.md)
---------
Co-authored-by: giulio-leone <[email protected]>
Co-authored-by: giulio-leone <[email protected]>
Co-authored-by: Copilot <[email protected]>
### Motivation and Context
Follow-up to #13499. The previous PR added the `allowed_module_prefixes`
parameter but defaulted it to `None`, which meant the module restriction
was only active if developers discovered and configured it.
Secure-by-default is the right posture here — restrict first, let
developers widen as needed.
- Change `allowed_module_prefixes` default from `None` to
`("semantic_kernel.",)` across Dapr runtime step loading
- Non-SK step classes now require developers to explicitly add their
module prefix (e.g. `("semantic_kernel.", "myapp.steps.")`)
- Developers can pass `None` to opt out entirely, but the secure default
is now enforced
- The Dapr runtime code is experimental, so this is a non-breaking
change per our stability guarantees
<!-- 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.
-->
<!-- 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 😄
---------
Co-authored-by: MAF Dashboard Bot <[email protected]>
Co-authored-by: Copilot <[email protected]>
## Summary
Fixes#12708
`ChatHistoryTruncationReducer.reduce()` can orphan `TOOL` role messages
by truncating the preceding `assistant` message that contains the
`tool_calls`, causing OpenAI to reject the history with:
```
messages with role 'tool' must be a response to a preceding message with 'tool_calls'
```
## Root Cause
`locate_safe_reduction_index()` uses
`contains_function_call_or_result()` to detect tool-related messages
during its backward scan. This function only checks `msg.items` for
`FunctionCallContent`/`FunctionResultContent` instances.
However, `TOOL` role messages can contain only text content (no
`FunctionResultContent` in `items`), which causes the backward scan to
treat them as regular messages. The truncation point then lands between
the `tool_calls` assistant message and its `TOOL` responses, orphaning
the tool results.
## Fix
Added `AuthorRole.TOOL` check to `contains_function_call_or_result()`:
```python
if msg.role == AuthorRole.TOOL:
return True
```
This ensures **any** `TOOL` role message is recognized as part of a tool
call/result pair, regardless of whether it has `FunctionResultContent`
in its `items`.
## Test
Added
`test_locate_safe_reduction_index_tool_role_without_function_result_content`
that verifies TOOL role messages with only text content are not
separated from their tool call.
---------
Co-authored-by: giulio-leone <[email protected]>
Co-authored-by: Evan Mattson <[email protected]>
Co-authored-by: Copilot <[email protected]>
## Summary
`ChatHistoryTruncationReducer.reduce()` silently deletes
system/developer messages when truncating chat history. This is because
it calls `extract_range()`, which unconditionally filters out
system/developer messages — a function designed for the summarization
use case, not truncation.
Fixes#12612.
## Approach
Port the .NET SDK fix (PR #10344) to Python:
1. Detect the first system/developer message before truncation
2. Pass `has_system_message=True` to `locate_safe_reduction_index` so
`target_count` accounts for the preserved message (matches .NET's
`targetCount -= hasSystemMessage ? 1 : 0`)
3. Use a simple `history[truncation_index:]` slice instead of
`extract_range` (which strips system messages)
4. Prepend the system message if it was truncated away
Also adds a guard for `target_count <= 0` after the system message
adjustment to prevent `IndexError` when `target_count=1`.
## Changes
| File | Change |
|------|--------|
| `chat_history_reducer_utils.py` | Add `has_system_message` parameter,
adjust `target_count`, guard against `<= 0` |
| `chat_history_truncation_reducer.py` | Detect system message, bypass
`extract_range`, prepend if truncated |
| `test_chat_history_truncation_reducer.py` | Update 2 existing tests +
4 new tests (system, developer, no-system, target_count=1) |
## Note
The summarization reducer (`ChatHistorySummarizationReducer`) has the
same bug — it also uses `extract_range` and loses system messages during
summarization. The .NET summarization reducer preserves system messages
via `AssemblySummarizedHistory`. This should be addressed in a follow-up
PR to keep this change focused.
## Test plan
- [x] 11/11 truncation reducer tests pass (was 7, now 11)
- [x] 9/9 utils tests pass (no regressions from new parameter)
- [x] 11/11 summarization reducer tests pass (unaffected)
- [x] Reproduces and fixes the exact scenario from #12612
- [x] Edge case: `target_count=1` with system message does not crash
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
Co-authored-by: Evan Mattson <[email protected]>
### Motivation and Context
Fixes#13632
When a prompt contains HTML tags such as `<p>`, `<div>`, `<b>`, etc.,
the
`ChatHistory.from_rendered_prompt()` method wraps the rendered prompt in
a
`<root>` element and parses it as XML. Any child elements whose tag
names do
not match the known SK template tags (`message`, `chat_history`) were
silently
skipped, causing their text content to be lost. This meant a prompt
like:
```
Translate: "<p>What is your name?</p>"
```
would arrive at the LLM as an empty message, because `<p>What is your
name?</p>`
was discarded during XML traversal.
### Description
In `ChatHistory.from_rendered_prompt`, when an XML child element has an
unrecognized tag (i.e. it is not `message` or `chat_history`), the
element
is now serialized back to its original text representation and appended
to
the preceding message content. The element's tail text is likewise kept
in
the same message, preserving the full original prompt text.
**Changed files:**
- `python/semantic_kernel/contents/chat_history.py` -- handle unknown
XML
tags as literal text in `from_rendered_prompt()`
- `python/tests/unit/contents/test_chat_history.py` -- added four
regression
tests covering HTML `<p>`, multiple HTML tags, HTML surrounded by text,
and SK tags mixed with HTML
### Contribution Checklist
- [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)
- [x] The existing tests pass and new tests have been added
- [x] I didn't break any existing functionality
---------
Co-authored-by: Evan Mattson <[email protected]>
### Motivation and Context
Fixes#13480
When using Gemini models (2.5 Pro / 3 Pro) with thinking enabled, the
API returns a `thought_signature` on function call `Part` objects. Per
[Google's Thought Signatures
documentation](https://ai.google.dev/gemini-api/docs/thought-signatures),
this signature **must** be included in subsequent requests. Without it,
follow-up turns with tool results fail with:
```
HTTP 400: Function call is missing a thought_signature in functionCall parts
```
The .NET connector was already fixed in #13418. This PR applies the
equivalent fix to the Python connector.
### Description
**Response parsing** (capture `thought_signature`):
- `google_ai_chat_completion.py`: When creating `FunctionCallContent`
from response parts, capture `part.thought_signature` into
`FunctionCallContent.metadata` (both non-streaming and streaming paths)
- `vertex_ai_chat_completion.py`: Same capture via
`part_dict.get("thought_signature")` for Vertex AI
**Request building** (restore `thought_signature`):
- `google_ai/services/utils.py`: In `format_assistant_message()`, when a
`FunctionCallContent` has `thought_signature` in its metadata, construct
the `Part` directly with the `thought_signature` parameter instead of
using `Part.from_function_call()`
- `vertex_ai/services/utils.py`: In `format_assistant_message()`,
include `thought_signature` in the `Part.from_dict()` dictionary when
present
**Backward compatible**: When `thought_signature` is not present
(thinking disabled or older models), behavior is identical to before.
### Test Coverage
Added 4 new tests:
- `test_format_assistant_message_with_thought_signature` (Google AI) —
verifies round-trip preservation
- `test_format_assistant_message_without_thought_signature` (Google AI)
— verifies backward compatibility
- `test_format_assistant_message_with_thought_signature` (Vertex AI) —
verifies round-trip preservation
- `test_format_assistant_message_without_thought_signature` (Vertex AI)
— verifies backward compatibility
All 110 existing Google connector tests continue to pass.
### Contribution Checklist
- [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)
- [x] All unit tests pass, and I have added new tests
- [x] I didn't break anyone 😄
---------
Co-authored-by: giulio-leone <[email protected]>
Co-authored-by: Copilot <[email protected]>
### 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.
-->
Dall-e-3 and Dall-e-2 have been deprecated. The newer gpt-1-image model
returns base64 strings.
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
Return url if set, otherwise return the base64 string.
### 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 😄
---------
Co-authored-by: Evan Mattson <[email protected]>
### 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 another way of escaping allowed commands.
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
### 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.
-->
Improves the robustness of filename handling in the Bedrock agent
integration. Ensures that filenames sourced from external responses are
properly sanitized before use in file operations, and adds safer
defaults for file write behavior.
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
1. Sanitize filenames received from Bedrock agent responses.
2. Add overwrite parameter to BinaryContent.write_to_file (defaults to
False).
3. Add tests.
4. Update 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
- [ ] I didn't break anyone 😄
### Motivation and Context
As of 2/27/2026, revived the PR, and the latest code is working for both
Azure OpenAI realtime models and OpenAI realtime models.
SK has support for realtime-preview models; however, since they've gone
to GA we have not added support for the latest library abstractions.
This PR brings in the changes to support running models like
`gpt-realtime-1.5`, `gpt-realtime`, `gpt-realtime-mini` or `gpt-audio`.
<!-- 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#13267
- Code now relies on `openai` >= 2.0
- Considered a breaking change due some new config added to the
execution settings.
<!-- 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 😄
### Motivation and Context
The Dapr Runtime uses string-based class names to load step classes
dynamically. This PR adds validation to ensure that only valid
KernelProcessStep subclasses can be loaded and instantiated, improving
type safety and providing better error messages when misconfigured.
The new allowed_module_prefixes parameter gives users control over which
modules are permitted for step class loading, which can be useful in
environments where stricter control is desired.
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
### Description
- Add issubclass(cls, KernelProcessStep) validation when loading step
classes from qualified names
- Add optional allowed_module_prefixes parameter for restricting which
modules can be loaded
- Centralize class loading logic in get_step_class_from_qualified_name()
utility function
- Remove duplicate _get_class_from_string methods from DaprStepInfo and
StepActor
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
Overriding merge checks as there are unrelated Python integration test failures
### Motivation and Context
- Uploads: Require both EnableDangerousFileUploads = true AND
AllowedUploadDirectories configured
- Downloads: Permissive by default, but if AllowedDownloadDirectories is
configured, path validation
applies
- Both use path canonicalization to prevent traversal attacks
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
### Motivation and Context
When `SessionsPythonTool` is used with an AI model, providing explicit
directory boundaries for file operations gives developers fine-grained
control over which parts of the filesystem the plugin can access. This
follows the pattern established by `HttpPlugin.allowed_domains`.
- Add `allowed_upload_directories` parameter to control which local
directories can be used for file uploads
- Add `allowed_download_directories` parameter for optional restrictions
on file download destinations
- Implement path canonicalization to resolve symlinks and normalize
paths
Usage:
```python
tool = SessionsPythonTool(
credential=credential,
allowed_upload_directories={"/app/data/uploads", "/app/user_files"},
allowed_download_directories={"/app/data/downloads"}, # optional
)
```
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
### Description
- `upload_file` now requires `allowed_upload_directories` to be
configured (deny-by-default)
- `download_file` optionally supports `allowed_download_directories`
(permissive-by-default, since it's not exposed as a kernel function)
- Both parameters accept `set[str]` or `list[str]` for convenience
- Paths are canonicalized using `os.path.realpath()` before validation
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
Adds allowed_domains setup for HttpPlugin.
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
Fixes some issues with the forbidden list approach for the in-memory
vector store filtering.
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
### Motivation and Context
Bump to v1.39.1 for a release
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
### Description
Bump to v1.39.1 for a release
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
Renamed dependency from Copilot Studio README.
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
…ync support
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
This change is required to enable Semantic Kernel users to store and
retrieve embeddings using Oracle databases. Currently, Semantic Kernel
supports vector storage for several backends, but Oracle was missing.
This connector solves that gap by providing full async support, native
VECTOR type handling, and vector index management.
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
This PR introduces a new Oracle connector for Semantic Kernel with the
following features:
- Asynchronous upsert, get, delete and search operations for memory
records.
- Native Oracle VECTOR type support for storing embeddings efficiently.
- Support for HNSW and IVFFLAT vector indexes for similarity search.
- Integration with Semantic Kernel collections, enabling semantic search
and memory operations.
- Comprehensive unit tests to ensure correctness and stability.
The connector is designed to work seamlessly with existing Semantic
Kernel memory abstractions and follows the same async patterns as other
vector stores.
Integration tests have also been implemented and verified locally;
however, they are not included in this PR because the current CI
environment setup for Oracle Database support is unknown.
Once guidance is provided on Oracle DB availability in the CI pipeline,
integration tests can be enabled and added in a follow-up PR.
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
Closes#12970, #13352
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
1. Migrate Google AI connector to use the new Google AI SDK.
2. This PR also marks the VertexAI connector as deprecated in favor of
the Google AI connector. With this update, if users wants to connect to
a VertexAI project instead of a Google AI endpoint, they can do so with
the Google AI connector.
3. This PR also adds the ability for users to provide a custom client to
the Google AI connector (#13352).
4. This PR also marks `AzureTextCompletion` deprecated.
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
OTel GenAI operation names have the following updates:
1. `chat.completion` to `chat`
2. `text.completion` to `text_completion`
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
This PR updates those operation names
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
### Motivation and Context
Fixes#13199 - Non-string kernel arguments are now preserved when passed
to functions in prompt templates. Adds unit tests.
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
Vertex AI and Bedrock integration tests have been failing.
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
1. This PR fixes the vertex ai integration tests by upgrading the Google
AI SDK version.
2. This PR fixes the Bedrock integration tests by upgrading the models.
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
---------
Co-authored-by: Copilot <[email protected]>
Co-authored-by: moonbox3 <[email protected]>
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
- The Agents SDK has been released, and the recent release changed the
namespace from `microsoft.agents` to `microsoft_agents`, which breaks
imports.
2. What problem does it solve?
- This updates the `pyproject.toml` and copilot studio related files to
fix the imports
3. What scenario does it contribute to?
- Using a Copilot Studio agent as an Agent in Semantic Kernel
4. If it fixes an open issue, please link to the issue here.
- N/A
-->
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
- Updated pyproject.toml to use the released packages for the Agents
SDK.
- Updated imports in the `copilot_studio_agent` related files to use the
new `microsoft_agents` namespace
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [] I didn't break anyone 😄
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
Enables developers to use NVIDIA's chat models through Semantic Kernel
with structured output support.
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
This change adds chat completion support with structured output to the
existing NVIDIA connector, enabling developers to use NVIDIA's chat
models through Semantic Kernel while building conversational AI
applications that require structured, validated responses. The connector
will support more model types iteratively, with future PRs introducing
VLM models and additional capabilities.
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
- New Chat Completion Service:
`NvidiaChatCompletion`: Chat completion service following same structure
as other connectors
- Extends existing NVIDIA embedding connector patterns and architecture
- Custom logic for handling structured output specific to NVIDIA models
- Enhanced Configuration:
`NvidiaChatPromptExecutionSettings`: Chat-specific settings following
existing connector patterns
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
### Motivation and Context
Currently, we attempt to deep copy plugins, no matter what the plugin
instance holds. This will cause issues when plugins contain unpickleable
items like an async generator.
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
### Description
- Closes#12819
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
### Motivation and Context
The `arguments: KernelArguments` are not getting handled properly for
the Responses Agent invoke. Use the provided `arguments` instead of
trying to get them from the kwargs.
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
### Description
- Closes#13053
- Adds unit test coverage.
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
Addresses #13005
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
1. Remove the `extra_parameters` key from
`AzureAIInferenceChatPromptExecutionSettings` before calling the chat
completion API to avoid unknown parameter error.
2. Allow setting the API version on the `AzureAIInferenceXXX`
connectors.
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
### Motivation and Context
As part of invoking an AzureAIAgent via streaming, we weren't providing
the `thread_id` via the `AgentStreamEvent.THREAD_MESSAGE_CREATED` event.
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
### Description
Supply the caller with the `thread_msg_id` by sticking it into the
returned SCMC's `metadata` dictionary.
- Closes#12959
Sample output looks like:
```
Sample Output:
# User: 'Hello'
# AuthorRole.ASSISTANT: (thread message id: msg_HZ2h4Wzbj7GEcnVCjnyEuYWT) Hello! How can I assist you with
the menu today?
# User: 'What is the special soup?'
# AuthorRole.ASSISTANT: (thread message id: msg_TSjkJK6hHJojIkPvF6uUofHD) The special soup today is
Clam Chowder. Would you like to know more about it or anything else from the menu?
# User: 'How much does that cost?'
# AuthorRole.ASSISTANT: (thread message id: msg_liwTpBFrB9JpCM1oM9EXKiwq) The Clam Chowder costs $9.99.
Is there anything else you'd like to know?
# User: 'Thank you'
# AuthorRole.ASSISTANT: (thread message id: msg_K6lpR3gYIHethXq17T6gJcxi) You're welcome!
If you have any more questions or need assistance, feel free to ask. Enjoy your meal!
```
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
Resolves: https://github.com/microsoft/semantic-kernel/issues/11821
Today, the encoding of template arguments is performed only if argument
type is `string`. In case of custom type, anonymous type or collection -
the encoding is not performed.
This PR contains changes to throw an exception in case if encoding is
enabled but complex type is used. In case of complex type, the encoding
should be performed manually according to business logic and automatic
encoding should be explicitly disabled.
This enforces stricter, but more secure template rendering rules.
**Note**: this is a breaking change for customers who use Handlebars or
Liquid template with complex type arguments. Code changes are required
when initializing template arguments:
```diff
var arguments = new KernelArguments()
{
{ "customer", new
{
- firstName = userInput.FirstName,
- lastName = userInput.LastName,
+ firstName = HttpUtility.HtmlEncode(userInput.FirstName),
+ lastName = HttpUtility.HtmlEncode(userInput.LastName),
}
}
};
var templateFactory = new LiquidPromptTemplateFactory();
var promptTemplateConfig = new PromptTemplateConfig()
{
TemplateFormat = "liquid"
+ InputVariables = new()
+ {
+ // We set AllowDangerouslySetContent to 'true' because each property of this argument is encoded manually.
+ new() { Name = "customer", AllowDangerouslySetContent = true },
+ }
};
var promptTemplate = templateFactory.Create(promptTemplateConfig);
var renderedPrompt = await promptTemplate.RenderAsync(kernel, arguments);
```
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
The usage of `DefaultAzureCredential` by default is unsafe and raises
security issues. Instead, users should provide their own credential
types such as `AzureCliCredential`, `ManagedIdentityCredential` and so
on. More information here:
https://learn.microsoft.com/en-us/python/api/azure-identity/azure.identity.aio?view=azure-python
In this PR:
1. Removed the usage of `DefaultAzureCredential` from authentication
logic.
2. Replaced `DefaultAzureCredential` with `AzureCliCredential` in all
examples.
**Note**: this is breaking change for Azure users, who relies on
`DefaultAzureCredential`. Users will need to update the code and pass
the credential type of their choice by using `credential` parameter when
initializing one of the Azure clients.
Before:
```python
chat_completion = AzureChatCompletion()
```
After:
```python
chat_completion = AzureChatCompletion(credential=AzureCliCredential())
```
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
### Motivation and Context
When running a reasoning model with the OpenAI responses agent, it was
producing 400s due to the way we were either including or not including
FCC related to tool calls. This PR fixes it for both the default
(store_enabled=True) and the case where uses don't want to use OpenAI's
previous response id as a pseudo-thread (store_enabled=False).
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
### Description
- Closes#12843
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
### 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]>
### 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 😄
### 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]>
### 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 😄
