chore: enable session history for openai agent.

[k82cn]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @k82cn, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request enhances the OpenAI agent example by introducing robust session history management. It refactors the context object to store conversational messages and modifies the custom session implementation to load and persist this history. This change allows the agent to maintain conversational state across multiple interactions, leading to more coherent and context-aware responses without requiring manual history passing.

Highlights

• Context Refactoring: The SysPrompt dataclass has been renamed to MyContext and now includes a messages field, a list of strings, to store conversation history for the agent.
• Session History Persistence: The MyCustomSession class has been updated to initialize its message history from the MyContext object and to save the updated history back to MyContext after the agent processes a request, ensuring conversational state is maintained.
• Agent Logic Update: The my_agent function now correctly utilizes the MyContext for session initialization and updates, enabling the agent to leverage and persist conversational history across interactions.
• Client Compatibility: The client-side code has been adjusted to use the new MyContext object when creating new agent sessions, ensuring seamless integration with the updated context and session management.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request enables session history for the OpenAI agent example. The changes involve introducing a MyContext data class to hold session messages, updating MyCustomSession to initialize from and persist to this context, and modifying the agent logic to use this sessioning mechanism. The changes are well-structured and align with the goal. I've pointed out a potential crash due to unhandled JSON decoding errors when loading session history, which should be addressed.

[gemini-code-assist]

The json.loads(message) call could raise a json.JSONDecodeError if a message from the context is not a valid JSON string. This would cause the agent to fail during the initialization of the session. It's safer to handle this potential error, for example by logging a warning and skipping the malformed message.

Suggested change

	for message in ctx.messages:
	self._messages.append(json.loads(message))
	for message in ctx.messages:
	try:
	self._messages.append(json.loads(message))
	except json.JSONDecodeError:
	logger.warning("Failed to decode message from session history: %s", message)