Python: Adjust tool limit per request (microsoft#9894)

### 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 have set incorrect limits on the number of tools that can be provided
to the AI services per request.

### Description

1. This PR removes the limits and will have requests fail on the service
side if there is any limit.
2. Add unit tests for prompt execution settings of some services that
are previously lacking such tests.
3. Fix the test coverage workflow.

<!-- 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 😄

---------

Co-authored-by: Evan Mattson <[email protected]>

.github/workflows/python-test-coverage.yml

@@ -1,55 +1,53 @@
 name: Python Test Coverage
 
 on:
-  pull_request_target:
+  pull_request:
     branches: ["main", "feature*"]
     paths:
-      - "python/**"
-  workflow_run:
-    workflows: ["Python Unit Tests"]
-    types: 
-      - in_progress
+      - "python/semantic_kernel/**"
+      - "python/tests/unit/**"
+env:
+  # Configure a constant location for the uv cache
+  UV_CACHE_DIR: /tmp/.uv-cache
+
+permissions:
+  contents: write
+  checks: write
+  pull-requests: write
 
 jobs:
   python-tests-coverage:
     runs-on: ubuntu-latest
-    continue-on-error: true
-    permissions:
-      pull-requests: write
-      contents: read
-      actions: read
+    continue-on-error: false
+    defaults:
+      run:
+        working-directory: python
+    env:
+      UV_PYTHON: "3.10"
     steps:
-      - name: Wait for unit tests to succeed
-        uses: lewagon/[email protected]
-        with:
-          ref: ${{ github.event.pull_request.head.sha }}
-          check-name: 'Python Test Coverage'
-          repo-token: ${{ secrets.GH_ACTIONS_PR_WRITE }}
-          wait-interval: 90
-          allowed-conclusions: success
       - uses: actions/checkout@v4
       - name: Setup filename variables
         run: echo "FILE_ID=${{ github.event.number }}" >> $GITHUB_ENV
-      - name: Download Files
-        uses: actions/download-artifact@v4
+      - name: Set up uv
+        uses: astral-sh/setup-uv@v4
         with:
-          github-token: ${{ secrets.GH_ACTIONS_PR_WRITE }}
-          run-id: ${{ github.event.workflow_run.id }}
-          path: python/
-          merge-multiple: true
-      - name: Display structure of downloaded files
-        run: ls python/
+          version: "0.5.x"
+          enable-cache: true
+          cache-suffix: ${{ runner.os }}-${{ env.UV_PYTHON }}
+      - name: Install the project
+        run: uv sync --all-extras --dev
+      - name: Test with pytest
+        run: uv run --frozen pytest -q --junitxml=pytest.xml --cov=semantic_kernel --cov-report=term-missing:skip-covered ./tests/unit | tee python-coverage.txt
       - name: Pytest coverage comment
         id: coverageComment
         uses: MishaKav/pytest-coverage-comment@main
-        continue-on-error: true
+        continue-on-error: false
         with:
-          github-token: ${{ secrets.GH_ACTIONS_PR_WRITE }}
-          pytest-coverage-path: python-coverage.txt
+          pytest-coverage-path: python/python-coverage.txt
           coverage-path-prefix: "python/"
           title: "Python Test Coverage Report"
           badge-title: "Python Test Coverage"
           junitxml-title: "Python Unit Test Overview"
-          junitxml-path: pytest.xml
+          junitxml-path: python/pytest.xml
           default-branch: "main"
-          unique-id-for-comment: python-test-coverage
+          report-only-changed-files: true

.github/workflows/python-unit-tests.yml

@@ -62,44 +62,3 @@ jobs:
           display-options: fEX
           fail-on-empty: true
           title: Test results
-  python-test-coverage:
-    name: Python Test Coverage
-    runs-on: [ubuntu-latest]
-    continue-on-error: true
-    permissions:
-      contents: write
-    defaults:
-      run:
-        working-directory: python
-    env:
-      UV_PYTHON: "3.10"
-    steps:
-      - uses: actions/checkout@v4
-      - name: Setup filename variables
-        run: echo "FILE_ID=${{ github.event.number }}" >> $GITHUB_ENV
-      - name: Set up uv
-        uses: astral-sh/setup-uv@v4
-        with:
-          version: "0.5.x"
-          enable-cache: true
-          cache-suffix: ${{ runner.os }}-${{ env.UV_PYTHON }}
-      - name: Install the project
-        run: uv sync --all-extras --dev
-      - name: Test with pytest
-        run: uv run --frozen pytest -q --junitxml=pytest.xml  --cov=semantic_kernel --cov-report=term-missing:skip-covered ./tests/unit | tee python-coverage.txt
-      - name: Upload coverage
-        if: always()
-        uses: actions/upload-artifact@v4
-        with:
-          name: python-coverage-${{ env.FILE_ID }}.txt
-          path: python/python-coverage.txt
-          overwrite: true
-          retention-days: 1
-      - name: Upload pytest.xml
-        if: always()
-        uses: actions/upload-artifact@v4
-        with:
-          name: pytest-${{ env.FILE_ID }}.xml
-          path: python/pytest.xml
-          overwrite: true
-          retention-days: 1

python/semantic_kernel/connectors/ai/anthropic/prompt_execution_settings/anthropic_prompt_execution_settings.py

@@ -32,7 +32,6 @@ class AnthropicChatPromptExecutionSettings(AnthropicPromptExecutionSettings):
     tools: Annotated[
         list[dict[str, Any]] | None,
         Field(
-            max_length=64,
             description=(
                 "Do not set this manually. It is set by the service based on the function choice configuration."
             ),

python/semantic_kernel/connectors/ai/azure_ai_inference/__init__.py

@@ -3,6 +3,7 @@
 from semantic_kernel.connectors.ai.azure_ai_inference.azure_ai_inference_prompt_execution_settings import (
     AzureAIInferenceChatPromptExecutionSettings,
     AzureAIInferenceEmbeddingPromptExecutionSettings,
+    AzureAIInferencePromptExecutionSettings,
 )
 from semantic_kernel.connectors.ai.azure_ai_inference.azure_ai_inference_settings import AzureAIInferenceSettings
 from semantic_kernel.connectors.ai.azure_ai_inference.services.azure_ai_inference_chat_completion import (
@@ -16,6 +17,7 @@
     "AzureAIInferenceChatCompletion",
     "AzureAIInferenceChatPromptExecutionSettings",
     "AzureAIInferenceEmbeddingPromptExecutionSettings",
+    "AzureAIInferencePromptExecutionSettings",
     "AzureAIInferenceSettings",
     "AzureAIInferenceTextEmbedding",
 ]

python/semantic_kernel/connectors/ai/azure_ai_inference/azure_ai_inference_prompt_execution_settings.py

@@ -33,7 +33,6 @@ class AzureAIInferenceChatPromptExecutionSettings(AzureAIInferencePromptExecutio
     tools: Annotated[
         list[dict[str, Any]] | None,
         Field(
-            max_length=64,
             description="Do not set this manually. It is set by the service based "
             "on the function choice configuration.",
         ),

python/semantic_kernel/connectors/ai/bedrock/bedrock_prompt_execution_settings.py

@@ -24,7 +24,6 @@ class BedrockChatPromptExecutionSettings(BedrockPromptExecutionSettings):
     tools: Annotated[
         list[dict[str, Any]] | None,
         Field(
-            max_length=64,
             description="Do not set this manually. It is set by the service based "
             "on the function choice configuration.",
         ),

python/semantic_kernel/connectors/ai/google/google_ai/google_ai_prompt_execution_settings.py

@@ -38,7 +38,6 @@ class GoogleAIChatPromptExecutionSettings(GoogleAIPromptExecutionSettings):
     tools: Annotated[
         list[dict[str, Any]] | None,
         Field(
-            max_length=64,
             description="Do not set this manually. It is set by the service based "
             "on the function choice configuration.",
         ),

python/semantic_kernel/connectors/ai/google/vertex_ai/vertex_ai_prompt_execution_settings.py

@@ -7,6 +7,7 @@
     from typing import override  # pragma: no cover
 else:
     from typing_extensions import override  # pragma: no cover
+
 from pydantic import Field
 from vertexai.generative_models import Tool, ToolConfig
 
@@ -38,7 +39,6 @@ class VertexAIChatPromptExecutionSettings(VertexAIPromptExecutionSettings):
     tools: Annotated[
         list[Tool] | None,
         Field(
-            max_length=64,
             description="Do not set this manually. It is set by the service based "
             "on the function choice configuration.",
         ),

python/semantic_kernel/connectors/ai/mistral_ai/prompt_execution_settings/mistral_ai_prompt_execution_settings.py

@@ -45,7 +45,6 @@ class MistralAIChatPromptExecutionSettings(MistralAIPromptExecutionSettings):
     tools: Annotated[
         list[dict[str, Any]] | None,
         Field(
-            max_length=64,
             description="Do not set this manually. It is set by the service based "
             "on the function choice configuration.",
         ),

python/semantic_kernel/connectors/ai/ollama/ollama_prompt_execution_settings.py

@@ -13,9 +13,6 @@ class OllamaPromptExecutionSettings(PromptExecutionSettings):
     format: Literal["json"] | None = None
     options: dict[str, Any] | None = None
 
-    # TODO(@taochen): Add individual properties for execution settings and
-    # convert them to the appropriate types in the options dictionary.
-
 
 class OllamaTextPromptExecutionSettings(OllamaPromptExecutionSettings):
     """Settings for Ollama text prompt execution."""
@@ -32,7 +29,6 @@ class OllamaChatPromptExecutionSettings(OllamaPromptExecutionSettings):
     tools: Annotated[
         list[dict[str, Any]] | None,
         Field(
-            max_length=64,
             description="Do not set this manually. It is set by the service based "
             "on the function choice configuration.",
         ),

python/semantic_kernel/connectors/ai/open_ai/prompt_execution_settings/open_ai_prompt_execution_settings.py

@@ -76,7 +76,6 @@ class OpenAIChatPromptExecutionSettings(OpenAIPromptExecutionSettings):
     tools: Annotated[
         list[dict[str, Any]] | None,
         Field(
-            max_length=64,
             description="Do not set this manually. It is set by the service based "
             "on the function choice configuration.",
         ),

python/tests/unit/connectors/ai/azure_ai_inference/test_azure_ai_inference_request_settings.py

@@ -0,0 +1,143 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+from semantic_kernel.connectors.ai.azure_ai_inference import (
+    AzureAIInferenceChatPromptExecutionSettings,
+    AzureAIInferenceEmbeddingPromptExecutionSettings,
+    AzureAIInferencePromptExecutionSettings,
+)
+from semantic_kernel.connectors.ai.prompt_execution_settings import PromptExecutionSettings
+
+
+def test_default_azure_ai_inference_prompt_execution_settings():
+    settings = AzureAIInferencePromptExecutionSettings()
+
+    assert settings.frequency_penalty is None
+    assert settings.max_tokens is None
+    assert settings.presence_penalty is None
+    assert settings.seed is None
+    assert settings.stop is None
+    assert settings.temperature is None
+    assert settings.top_p is None
+    assert settings.extra_parameters is None
+
+
+def test_custom_azure_ai_inference_prompt_execution_settings():
+    settings = AzureAIInferencePromptExecutionSettings(
+        frequency_penalty=0.5,
+        max_tokens=128,
+        presence_penalty=0.5,
+        seed=1,
+        stop="world",
+        temperature=0.5,
+        top_p=0.5,
+        extra_parameters={"key": "value"},
+    )
+
+    assert settings.frequency_penalty == 0.5
+    assert settings.max_tokens == 128
+    assert settings.presence_penalty == 0.5
+    assert settings.seed == 1
+    assert settings.stop == "world"
+    assert settings.temperature == 0.5
+    assert settings.top_p == 0.5
+    assert settings.extra_parameters == {"key": "value"}
+
+
+def test_azure_ai_inference_prompt_execution_settings_from_default_completion_config():
+    settings = PromptExecutionSettings(service_id="test_service")
+    chat_settings = AzureAIInferenceChatPromptExecutionSettings.from_prompt_execution_settings(settings)
+
+    assert chat_settings.service_id == "test_service"
+    assert chat_settings.frequency_penalty is None
+    assert chat_settings.max_tokens is None
+    assert chat_settings.presence_penalty is None
+    assert chat_settings.seed is None
+    assert chat_settings.stop is None
+    assert chat_settings.temperature is None
+    assert chat_settings.top_p is None
+    assert chat_settings.extra_parameters is None
+
+
+def test_azure_ai_inference_prompt_execution_settings_from_openai_prompt_execution_settings():
+    chat_settings = AzureAIInferenceChatPromptExecutionSettings(service_id="test_service", temperature=1.0)
+    new_settings = AzureAIInferencePromptExecutionSettings(service_id="test_2", temperature=0.0)
+    chat_settings.update_from_prompt_execution_settings(new_settings)
+
+    assert chat_settings.service_id == "test_2"
+    assert chat_settings.temperature == 0.0
+
+
+def test_azure_ai_inference_prompt_execution_settings_from_custom_completion_config():
+    settings = PromptExecutionSettings(
+        service_id="test_service",
+        extension_data={
+            "frequency_penalty": 0.5,
+            "max_tokens": 128,
+            "presence_penalty": 0.5,
+            "seed": 1,
+            "stop": "world",
+            "temperature": 0.5,
+            "top_p": 0.5,
+            "extra_parameters": {"key": "value"},
+        },
+    )
+    chat_settings = AzureAIInferenceChatPromptExecutionSettings.from_prompt_execution_settings(settings)
+
+    assert chat_settings.service_id == "test_service"
+    assert chat_settings.frequency_penalty == 0.5
+    assert chat_settings.max_tokens == 128
+    assert chat_settings.presence_penalty == 0.5
+    assert chat_settings.seed == 1
+    assert chat_settings.stop == "world"
+    assert chat_settings.temperature == 0.5
+    assert chat_settings.top_p == 0.5
+    assert chat_settings.extra_parameters == {"key": "value"}
+
+
+def test_azure_ai_inference_chat_prompt_execution_settings_from_custom_completion_config_with_functions():
+    settings = PromptExecutionSettings(
+        service_id="test_service",
+        extension_data={
+            "tools": [{"function": {}}],
+        },
+    )
+    chat_settings = AzureAIInferenceChatPromptExecutionSettings.from_prompt_execution_settings(settings)
+
+    assert chat_settings.tools == [{"function": {}}]
+
+
+def test_create_options():
+    settings = AzureAIInferenceChatPromptExecutionSettings(
+        service_id="test_service",
+        extension_data={
+            "frequency_penalty": 0.5,
+            "max_tokens": 128,
+            "presence_penalty": 0.5,
+            "seed": 1,
+            "stop": "world",
+            "temperature": 0.5,
+            "top_p": 0.5,
+            "extra_parameters": {"key": "value"},
+        },
+    )
+    options = settings.prepare_settings_dict()
+
+    assert options["frequency_penalty"] == 0.5
+    assert options["max_tokens"] == 128
+    assert options["presence_penalty"] == 0.5
+    assert options["seed"] == 1
+    assert options["stop"] == "world"
+    assert options["temperature"] == 0.5
+    assert options["top_p"] == 0.5
+    assert options["extra_parameters"] == {"key": "value"}
+    assert "tools" not in options
+    assert "tool_config" not in options
+
+
+def test_default_azure_ai_inference_embedding_prompt_execution_settings():
+    settings = AzureAIInferenceEmbeddingPromptExecutionSettings()
+
+    assert settings.dimensions is None
+    assert settings.encoding_format is None
+    assert settings.input_type is None
+    assert settings.extra_parameters is None