Skip to content

Add log manager to track experiement logs#507

Merged
yanxi-chen merged 16 commits intoagentscope-ai:mainfrom
pan-x-c:feature/log_manager
Feb 12, 2026
Merged

Add log manager to track experiement logs#507
yanxi-chen merged 16 commits intoagentscope-ai:mainfrom
pan-x-c:feature/log_manager

Conversation

@pan-x-c
Copy link
Collaborator

@pan-x-c pan-x-c commented Feb 11, 2026

Description

Using trinity log to track the logs during training.

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
Copy link
Contributor

Summary of Changes

Hello @pan-x-c, 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 significantly enhances the trinity CLI by adding a powerful new log command for real-time monitoring of experiment logs. This new utility allows users to easily track training progress and debug issues by providing flexible options for filtering, searching, and displaying log data. The changes also include a minor refactoring in the configuration handling to streamline directory path generation.

Highlights

  • New CLI Command: Introduced a new trinity log command for real-time monitoring of experiment logs, offering options for directory specification, configuration loading, keyword filtering, log level control, displaying last N lines, search patterns, and color output.
  • Log Management System: Added a comprehensive LogManager and LogFileTracker system to efficiently handle multiple log files, including features like file rotation detection, log level parsing, and continuous monitoring.
  • Configuration Refactoring: Refactored the Config class to include a dedicated method get_checkpoint_job_dir, centralizing the logic for determining checkpoint job directory paths and improving code reusability.
Changelog
  • trinity/cli/launcher.py
    • Added a new log command to the typer application, enabling real-time log monitoring with various configurable options.
  • trinity/common/config.py
    • Introduced a new method get_checkpoint_job_dir to the Config class for consistent retrieval of checkpoint job directory paths.
  • trinity/common/config_validator.py
    • Updated the validate method to utilize the newly added get_checkpoint_job_dir method for setting the checkpoint job directory.
  • trinity/manager/log_manager.py
    • Added a new module containing LogManager and LogFileTracker classes, providing core functionality for real-time log file tracking, parsing, and display.
Activity
  • No human activity has been recorded on this pull request yet.
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.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request introduces a new trinity log command to monitor experiment logs in real-time. The core logic is encapsulated in a new LogManager. The changes also include a small refactoring in the Config class to centralize the construction of the checkpoint job directory path.

My review focuses on improving robustness and performance. I've identified a potential high-memory usage issue in the log searching feature, a case of silent exception handling that could hide bugs, and an opportunity to simplify some redundant code in the new CLI command. Overall, this is a great addition for improving observability during training.

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Feb 12, 2026

/unittest-diff

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
80 79 0 1 0 0 34m 17s

Skipped

Tests Status
tests/common/vllm_test.py::TestTinkerAsyncAPIServer::test_api_async skipped ⏭️

Tests

Test Name Status Flaky Duration
tests/cli/launcher_test.py::TestLauncherMain::test_debug_mode 47.7s
tests/cli/launcher_test.py::TestLauncherMain::test_log_mode 424ms
tests/cli/launcher_test.py::TestLauncherMain::test_main_run_command 6.5s
tests/cli/launcher_test.py::TestLauncherMain::test_main_run_in_dlc 1.6s
tests/cli/launcher_test.py::TestLauncherMain::test_main_studio_command 911ms
tests/cli/launcher_test.py::TestLauncherMain::test_multi_stage_run 15.0s
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 32.4s
tests/common/config_test.py::TestConfig::test_chat_template_path 342ms
tests/common/config_test.py::TestConfig::test_config_flatten 32ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 385ms
tests/common/config_test.py::TestConfig::test_default_workflow 298ms
tests/common/config_test.py::TestConfig::test_load_default_config 5.4s
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly 317ms
tests/common/config_test.py::TestConfig::test_optimizer_config_propagation 310ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster 376ms
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_gather_with_token_level_reward 1ms
tests/common/experience_test.py::TestExperience::test_hf_datasets_conversion 16ms
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/sudoku_test.py::test_9x9_generator_produces_valid_solution 1ms
tests/common/sudoku_test.py::test_9x9_generator_creates_holes 1ms
tests/common/sudoku_test.py::test_9x9_solution_is_fully_filled 1ms
tests/common/sudoku_test.py::test_judge_allows_incomplete_board 1ms
tests/common/sudoku_test.py::test_judge_detects_row_violation 1ms
tests/common/sudoku_test.py::test_judge_detects_column_violation 1ms
tests/common/sudoku_test.py::test_judge_detects_block_violation 1ms
tests/common/sudoku_test.py::test_4x4_generator_produces_valid_solution 1ms
tests/common/sudoku_test.py::test_4x4_solution_is_fully_filled 1ms
tests/common/sudoku_test.py::test_4x4_judge_detects_row_violation 1ms
tests/common/sudoku_test.py::test_4x4_judge_detects_block_violation 1ms
tests/common/vllm_test.py::ModelWrapperTest_0::test_generate 56.8s
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 39.6s
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 38.4s
tests/common/vllm_test.py::TestModelLen_0::test_model_len 27.7s
tests/common/vllm_test.py::TestModelLen_1::test_model_len 32.1s
tests/common/vllm_test.py::TestModelLen_2::test_model_len 27.6s
tests/common/vllm_test.py::TestModelLenWithoutPromptTruncation::test_model_len 25.5s
tests/common/vllm_test.py::TestMessageProcess::test_no_prompt_truncation 26.7s
tests/common/vllm_test.py::TestMessageProcess::test_truncation_status 27.1s
tests/common/vllm_test.py::TestAPIServer::test_api 28.7s
tests/common/vllm_test.py::TestLogprobs::test_logprobs_api 27.2s
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async 28.4s
tests/common/vllm_test.py::TestTinkerAsyncAPIServer::test_api_async ⏭️ 1ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask 244ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools 229ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 31.8s
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 28.5s
tests/common/vllm_test.py::TestSuperLongGeneration::test_generate 2m 39s
tests/common/vllm_test.py::TestTinkerAPI::test_tinker_api 41.0s
tests/manager/log_manager_test.py::TestLogManager::test_file_rotation 2ms
tests/manager/log_manager_test.py::TestLogManager::test_init_and_tracking 1ms
tests/manager/log_manager_test.py::TestLogManager::test_keyword_filter_and_search_pattern 1ms
tests/manager/synchronizer_test.py::TestSynchronizerExit_0::test_synchronizer 2m 27s
tests/manager/synchronizer_test.py::TestSynchronizerExit_1::test_synchronizer 2m 28s
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_0::test_synchronizer 2m 3s
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_1::test_synchronizer 1m 40s
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_2::test_synchronizer 2m 1s
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_3::test_synchronizer 2m 37s
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_4::test_synchronizer 2m 19s
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_5::test_synchronizer 2m 39s
tests/manager/synchronizer_test.py::TestNCCLBasedSynchronizer_0::test_synchronizer 1m 8s
tests/manager/synchronizer_test.py::TestNCCLBasedSynchronizer_1::test_synchronizer 1m 2s
tests/manager/synchronizer_test.py::TestNCCLBasedSynchronizer_2::test_synchronizer 1m 3s
tests/manager/synchronizer_test.py::TestPullLatestWeights::test_no_new_version_logs_warning 4ms
tests/manager/synchronizer_test.py::TestPullLatestWeights::test_pull_latest_weights_0 2ms
tests/manager/synchronizer_test.py::TestPullLatestWeights::test_pull_latest_weights_1 3ms
tests/manager/synchronizer_test.py::TestPullLatestWeights::test_pull_latest_weights_2 2ms
tests/manager/synchronizer_test.py::TestPullLatestWeights::test_pull_latest_weights_3 2ms

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Feb 12, 2026

/unittest-all

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Feb 12, 2026

/unittest-trainer

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Feb 12, 2026

/unittest-module-trainer

@pan-x-c pan-x-c changed the title Add log manager to tracker experiement logs Add log manager to track experiement logs Feb 12, 2026
@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Feb 12, 2026

/unittest-module-trainer

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
27 24 0 3 0 0 46m 57s

Skipped

Tests Status
tests/trainer/trainer_test.py::TestTrainerSFTWarmupGSM8K::test_trainer skipped ⏭️
tests/trainer/trainer_test.py::TestTinkerTrainer::test_trainer skipped ⏭️
tests/trainer/trainer_test.py::TestTinkerTrainer::test_trainer_class skipped ⏭️

Tests

Test Name Status Flaky Duration
tests/trainer/trainer_test.py::TestTrainerCountdown_0_fsdp::test_trainer 3m 57s
tests/trainer/trainer_test.py::TestTrainerCountdown_1_megatron::test_trainer 5m 1s
tests/trainer/trainer_test.py::TestStepAheadAsyncRL::test_trainer 1m 44s
tests/trainer/trainer_test.py::TestTrainerGSM8K_0_fsdp::test_trainer 1m 15s
tests/trainer/trainer_test.py::TestTrainerGSM8K_1_fsdp2::test_trainer 1m 1s
tests/trainer/trainer_test.py::TestTrainerGSM8K_2_fsdp::test_trainer 1m 6s
tests/trainer/trainer_test.py::TestTrainerGSM8K_3_fsdp2::test_trainer 1m 12s
tests/trainer/trainer_test.py::TestTrainerSFTWarmupGSM8K::test_trainer ⏭️ 1ms
tests/trainer/trainer_test.py::TestTrainerDPO::test_trainer 33.9s
tests/trainer/trainer_test.py::TestTrainerSFT::test_trainer 32.1s
tests/trainer/trainer_test.py::TestTrainerToolsSFT::test_trainer_tools 29.4s
tests/trainer/trainer_test.py::TestFullyAsyncMode_0_fsdp::test_fully_async_mode 1m 37s
tests/trainer/trainer_test.py::TestFullyAsyncMode_1_fsdp::test_fully_async_mode 1m 36s
tests/trainer/trainer_test.py::TestFullyAsyncMode_2_megatron::test_fully_async_mode 2m 24s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_0_fsdp::test_trainer 2m 53s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_1_megatron::test_trainer 5m 45s
tests/trainer/trainer_test.py::TestTrainerMIX::test_trainer 1m 53s
tests/trainer/trainer_test.py::TestServeWithTrainer::test_serve_with_trainer 1m 48s
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer 2m 39s
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer 1m 8s
tests/trainer/trainer_test.py::TestTrainerLoRA::test_trainer 3m 7s
tests/trainer/trainer_test.py::TestOverRollout::test_trainer 1m 11s
tests/trainer/trainer_test.py::TestTrainerPromptTruncation::test_trainer 45.2s
tests/trainer/trainer_test.py::TestTinkerTrainer::test_trainer ⏭️ 1ms
tests/trainer/trainer_test.py::TestTinkerTrainer::test_trainer_class ⏭️ 1ms
tests/trainer/trainer_test.py::AgentScopeTunerTest::test_agentscope_tuner 1m 12s
tests/trainer/trainer_test.py::ColocateModeTest::test_trainer 1m 55s

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Feb 12, 2026

/unittest-module-explorer

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
49 49 0 0 0 0 13m 20s

Tests

Test Name Status Flaky Duration
tests/explorer/explorer_test.py::TestExplorerCountdownEval::test_explorer 1m 48s
tests/explorer/explorer_test.py::TestExplorerEvalDetailedStats::test_explorer 1m 12s
tests/explorer/explorer_test.py::TestExplorerGSM8KRULERNoEval::test_explorer 1m 6s
tests/explorer/explorer_test.py::TestExplorerGSM8k::test_explorer 3m
tests/explorer/explorer_test.py::ServeTest::test_serve 54.6s
tests/explorer/proxy_test.py::RecorderTest::test_recorder 62ms
tests/explorer/scheduler_test.py::SchedulerTest::test_async_workflow 5.8s
tests/explorer/scheduler_test.py::SchedulerTest::test_concurrent_operations 4.8s
tests/explorer/scheduler_test.py::SchedulerTest::test_dynamic_timeout 13.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_get_results 29.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_0 4.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_1 4.7s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_0 4.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_1 4.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_multi_step_execution 5.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_non_repeatable_workflow 4.9s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_min_wait 12.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_all_methods 14.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_restart_after_stop 8.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_split_tasks 8.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_stepwise_experience_eid 25.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all 7.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all_timeout_with_multi_batch 13.6s
tests/explorer/scheduler_test.py::TestRunnerStateCollection::test_runner_state_collection 9.7s
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_reward_propagation_workflow_0 1ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_reward_propagation_workflow_1 602ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_step_wise_reward_workflow_0 1ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_step_wise_reward_workflow_1 1.0s
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_workflows_raise_error 1ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_workflows_stop_at_max_env_steps 1.0s
tests/explorer/workflow_test.py::WorkflowTest::test_gsm8k_workflow 28ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_boxed_workflow 17ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_complex_workflow 131ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_eval_workflow 3ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_fraction_workflow 11ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_workflow 7ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_0 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_1 101ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_0 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_1 201ms
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_0::test_multi_turn_workflow 23.4s
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_1::test_multi_turn_workflow 23.6s
tests/explorer/workflow_test.py::TestWorkflowStateRecording::test_workflow_state_recording 4.0s
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter_v0 785ms
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter_v1 15ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner 137ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_get_state 8.0s
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_with_openai 26.6s
tests/explorer/workflow_test.py::TestConcurrentWorkflowRunner::test_concurrent_workflow_runner 44.6s

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Feb 12, 2026

/unittest-module-buffer

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Feb 12, 2026

/unittest-module-algorithm

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
48 48 0 0 0 0 1m 42s

Tests

Test Name Status Flaky Duration
tests/buffer/experience_pipeline_test.py::TestExperiencePipeline::test_experience_pipeline 10.6s
tests/buffer/experience_pipeline_test.py::TestExperiencePipeline::test_pass_rate_calculation 6.0s
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_experience_buffer 2.4s
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_storage_0_sft 4.3s
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_storage_1_dpo 4.8s
tests/buffer/file_test.py::TestFileBuffer::test_file_reader 434ms
tests/buffer/file_test.py::TestFileBuffer::test_file_writer 1.5s
tests/buffer/formatter_test.py::TestFormatter::test_dpo_messages_formatter 557ms
tests/buffer/formatter_test.py::TestFormatter::test_dpo_plaintext_formatter 481ms
tests/buffer/formatter_test.py::TestFormatter::test_multi_modal_sft_formatter 841ms
tests/buffer/formatter_test.py::TestFormatter::test_sft_messages_formatter 997ms
tests/buffer/formatter_test.py::TestFormatter::test_sft_plaintext_formatter 766ms
tests/buffer/formatter_test.py::TestFormatter::test_task_formatter 229ms
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_buffer_reuse 6.3s
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_capacity 2.1s
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_reuse_count_control 4.1s
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_0_queue 3.3s
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_1_priority_queue 3.1s
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_capacity 3.8s
tests/buffer/reader_test.py::TestBufferReader::test_buffer_reader_registration 752ms
tests/buffer/reward_shaping_mapper_test.py::TestRewardShapingMapper::test_basic_usage 6ms
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_default_queue_default_sample_strategy 1.8s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_default_queue_staleness_control_sample_strategy 1.5s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_priority_queue_default_sample_strategy 1.6s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_priority_queue_staleness_control_sample_strategy 1.7s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_sql_staleness_control_sample_strategy 4.3s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_default_queue_default_sample_strategy 2.0s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_default_queue_staleness_control_sample_strategy 1.7s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_priority_queue_default_sample_strategy 1.7s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_priority_queue_staleness_control_sample_strategy 1.6s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_sql_staleness_control_sample_strategy 3.4s
tests/buffer/sql_test.py::TestSQLBuffer::test_sql_exp_buffer_read_write_0 5.5s
tests/buffer/sql_test.py::TestSQLBuffer::test_sql_exp_buffer_read_write_1 2.0s
tests/buffer/sql_test.py::TestSQLBuffer::test_sql_task_buffer_read_write 2.7s
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_0 72ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_1 58ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_2 90ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_3 90ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_4 92ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_5 93ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_6 107ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_simple 46ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_0_file 288ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_1_sql 2.8s
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_2_file 41ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_3_sql 2.6s
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_4_file 41ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_5_sql 3.2s

Github Test Reporter by CTRF 💚

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
27 27 0 0 0 0 3.1s

Tests

Test Name Status Flaky Duration
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_batch_level_std_grpo 6ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_batch_level_step_wise_grpo_advantage 3ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_duplicate_grpo 4ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_advantage 3ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_correct_bias 2ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_reward_std 1ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_step_wise_grpo_advantage 1ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_step_wise_grpo_with_std_threshold 2ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_abs_kl_fn 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_corrected_k3_fallback 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_corrected_k3_loss 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_corrected_k3_same_policy 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_corrected_k3_with_old_logprob 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_dummy_kl_fn 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_k1_kl_fn 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_k2_kl_fn 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_k3_kl_fn 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_kl_loss_aggregation_modes 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_low_var_kl_fn 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_dpo_policy_loss 2ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_gspo_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_mix_policy_loss 3ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_opmd_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_ppo_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_ppo_policy_loss_with_sequence_masking 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_sapo_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_sft_policy_loss 1ms

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Feb 12, 2026

/unittest-module-common

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
55 54 0 1 0 0 11m 36s

Skipped

Tests Status
tests/common/vllm_test.py::TestTinkerAsyncAPIServer::test_api_async skipped ⏭️

Tests

Test Name Status Flaky Duration
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 22.7s
tests/common/config_test.py::TestConfig::test_chat_template_path 77ms
tests/common/config_test.py::TestConfig::test_config_flatten 32ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 161ms
tests/common/config_test.py::TestConfig::test_default_workflow 76ms
tests/common/config_test.py::TestConfig::test_load_default_config 1.2s
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly 76ms
tests/common/config_test.py::TestConfig::test_optimizer_config_propagation 76ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster 1.7s
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_gather_with_token_level_reward 1ms
tests/common/experience_test.py::TestExperience::test_hf_datasets_conversion 14ms
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/sudoku_test.py::test_9x9_generator_produces_valid_solution 1ms
tests/common/sudoku_test.py::test_9x9_generator_creates_holes 1ms
tests/common/sudoku_test.py::test_9x9_solution_is_fully_filled 1ms
tests/common/sudoku_test.py::test_judge_allows_incomplete_board 1ms
tests/common/sudoku_test.py::test_judge_detects_row_violation 1ms
tests/common/sudoku_test.py::test_judge_detects_column_violation 1ms
tests/common/sudoku_test.py::test_judge_detects_block_violation 1ms
tests/common/sudoku_test.py::test_4x4_generator_produces_valid_solution 1ms
tests/common/sudoku_test.py::test_4x4_solution_is_fully_filled 1ms
tests/common/sudoku_test.py::test_4x4_judge_detects_row_violation 1ms
tests/common/sudoku_test.py::test_4x4_judge_detects_block_violation 1ms
tests/common/vllm_test.py::ModelWrapperTest_0::test_generate 57.6s
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 39.8s
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 46.6s
tests/common/vllm_test.py::TestModelLen_0::test_model_len 32.5s
tests/common/vllm_test.py::TestModelLen_1::test_model_len 26.2s
tests/common/vllm_test.py::TestModelLen_2::test_model_len 26.7s
tests/common/vllm_test.py::TestModelLenWithoutPromptTruncation::test_model_len 26.9s
tests/common/vllm_test.py::TestMessageProcess::test_no_prompt_truncation 25.1s
tests/common/vllm_test.py::TestMessageProcess::test_truncation_status 27.2s
tests/common/vllm_test.py::TestAPIServer::test_api 29.9s
tests/common/vllm_test.py::TestLogprobs::test_logprobs_api 26.2s
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async 28.1s
tests/common/vllm_test.py::TestTinkerAsyncAPIServer::test_api_async ⏭️ 1ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask 239ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools 254ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 32.1s
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 31.1s
tests/common/vllm_test.py::TestSuperLongGeneration::test_generate 2m 49s
tests/common/vllm_test.py::TestTinkerAPI::test_tinker_api 40.0s

Github Test Reporter by CTRF 💚

@yanxi-chen yanxi-chen merged commit c3d356c into agentscope-ai:main Feb 12, 2026
2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants