feat: 添加 Google ADK、CrewAI、LangChain 和 PydanticAI 模型适配器的流选项支持，更新数据 AP…

[OhYee]

增加 include_usage 参数，确保探针可以正确采集 token

Thank you for creating a pull request to contribute to Serverless Devs agentrun-sdk-python code! Before you open the request please answer the following questions to help it be more easily integrated. Please check the boxes "[ ]" with "[x]" when done too.
Please select one of the PR types below to complete

---

Fix bugs

Bug detail

The specific manifestation of the bug or the associated issue.

Pull request tasks

• Add test cases for the changes
• Passed the CI test

---

Update docs

Reason for update

Why do you need to update your documentation?

Pull request tasks

• Update Chinese documentation
• Update English documentation

---

Add contributor

Contributed content

• Code
• Document

Content detail

if content_type == 'code' || content_type == 'document':
    please tell us `PR url`，like: https://github.com/Serverless-Devs/agentrun-sdk-python/pull/1
else:
    please describe your contribution in detail

---

Others

Reason for update

Why do you need to update your documentation?

[Copilot]

Pull request overview

This PR adds include_usage parameter support to streaming options across multiple AI framework model adapters (Google ADK, CrewAI, LangChain, PydanticAI, and AgentScope) and the data API to ensure probes can properly collect token usage information. Additionally, a new GitHub workflow for test package releases has been added.

Key Changes:

• Added stream_options: {"include_usage": True} to all model adapters for proper token usage collection
• Updated data API methods (completions and responses) to set include_usage: True in stream options
• Added test assertions to verify stream_options are correctly configured

Reviewed changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
agentrun/model/api/data.py	Modified completions() and responses() methods to set stream_options.include_usage = True, but contains a critical bug with KeyError handling
agentrun/integration/google_adk/model_adapter.py	Added stream_options={"include_usage": True} to LiteLlm initialization
agentrun/integration/crewai/model_adapter.py	Added stream_options={"include_usage": True} to LLM initialization
agentrun/integration/langchain/model_adapter.py	Added stream_usage=True parameter to ChatOpenAI initialization
agentrun/integration/pydantic_ai/model_adapter.py	Added ModelSettings with extra_body containing stream_options, removed unused imports
agentrun/integration/agentscope/model_adapter.py	Added generate_kwargs={"stream_options": {"include_usage": True}} to OpenAIChatModel
tests/unittests/integration/test_integration.py	Added assertions to verify stream_options.include_usage is True in mocked completion calls
.github/workflows/release-test.yml	New workflow for building and publishing test packages to PyPI with tag-based triggers

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

This code will raise a KeyError when stream_options is not present in kwargs. The condition checks if kwargs["stream_options"] is None, but this will fail if the key doesn't exist at all. Use kwargs.get("stream_options") instead or check with if "stream_options" not in kwargs or kwargs["stream_options"] is None:.

[Copilot]

@OhYee I've opened a new pull request, #12, to work on those changes. Once the pull request is ready, I'll request review from you.