Fix/email search

[chenyushuo]

Description

1. Bug fix in email search.
2. Update agentscope_gsm8k_reward.png.

Checklist

Please check the following items before code is ready to be reviewed.

• Code has passed all tests
• Docstrings have been added/updated in Google Style
• Documentation has been updated
• Code is ready for review

[gemini-code-assist]

Summary of Changes

Hello @chenyushuo, 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 addresses a bug in the email search functionality by introducing asynchronous programming patterns to key reward calculation and judging logic. This refactoring aims to improve the responsiveness and efficiency of the system, especially when interacting with external services like LLMs. Additionally, it enhances the robustness of the reward calculation process by providing a fallback mechanism for unhandled rubrics, preventing application crashes.

Highlights

• Asynchronous Operations: The judge_correctness and calculate_reward functions have been converted to asynchronous functions to support non-blocking operations.
• LLM Interaction: Calls to judger.chat.completions.create and judge_correctness are now properly awaited, indicating interaction with an external LLM service is handled asynchronously.
• Error Handling Improvement: The calculate_reward function now gracefully handles unaddressed rubrics by returning a default reward dictionary {"accuracy": 0.0, "format": 0.0} instead of raising a ValueError.

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. ↩

[chenyushuo]

/unittest-diff

[gemini-code-assist]

Code Review

The pull request correctly transitions parts of the email search workflow to be asynchronous, using async and await appropriately. This addresses a bug and improves the design of the async workflow. The change to handle unhandled rubric cases more gracefully by returning a default reward instead of raising an exception is also a good improvement for robustness. My review includes one suggestion to further improve the robustness of the code by explicitly handling cases where a judge model may not be available.

[github-actions]

Summary

Tests 📝	Passed ✅	Failed ❌	Skipped ⏭️	Other ❓	Flaky 🍂	Duration ⏱️
33	33	0	0	0	0	352ms

Tests

Test Name	Status	Flaky	Duration
tests/common/config_test.py::TestConfig::test_all_examples_are_valid	✅		32ms
tests/common/config_test.py::TestConfig::test_config_flatten	✅		1ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid	✅		1ms
tests/common/config_test.py::TestConfig::test_default_workflow	✅		1ms
tests/common/config_test.py::TestConfig::test_load_default_config	✅		35ms
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly	✅		1ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster	✅		1ms
tests/common/experience_test.py::TestEID::test_eid_properties	✅		1ms
tests/common/experience_test.py::TestExperience::test_action_mask_and_logprobs_type	✅		1ms
tests/common/experience_test.py::TestExperience::test_assertions	✅		1ms
tests/common/experience_test.py::TestExperience::test_dpo_experience	✅		1ms
tests/common/experience_test.py::TestExperience::test_gather	✅		1ms
tests/common/experience_test.py::TestExperience::test_hf_datasets_conversion	✅		1ms
tests/common/experience_test.py::TestExperience::test_multi_turn_experience	✅		1ms
tests/common/experience_test.py::TestExperience::test_serialize_deserialize	✅		1ms
tests/common/experience_test.py::TestExperience::test_single_turn_experience	✅		1ms
tests/common/experience_test.py::TestExperience::test_to_dict	✅		1ms
tests/common/experience_test.py::TestExperienceConversion::test_batch_conversion	✅		1ms
tests/common/experience_test.py::TestExperienceConversion::test_dpo_experience_batch_conversion	✅		1ms
tests/common/experience_test.py::TestExperienceConversion::test_experience_model_experience_conversion	✅		1ms
tests/common/experience_test.py::TestExperienceConversion::test_gather_experiences_with_custom_fields	✅		1ms
tests/common/experience_test.py::TestExperienceConversion::test_multiturn_experience_batch_converstion	✅		1ms
tests/common/vllm_test.py::ModelWrapperTest_0::test_generate	✅		55ms
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate	✅		37ms
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate	✅		46ms
tests/common/vllm_test.py::TestModelLen_0::test_model_len	✅		21ms
tests/common/vllm_test.py::TestModelLen_1::test_model_len	✅		20ms
tests/common/vllm_test.py::TestAPIServer::test_api	✅		25ms
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async	✅		26ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask	✅		1ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools	✅		1ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls	✅		22ms
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls	✅		21ms

Github Test Reporter by CTRF 💚