Skip to content

Optimize Explorer#531

Merged
pan-x-c merged 20 commits intoagentscope-ai:mainfrom
pan-x-c:feature/optmize_explorer
Apr 28, 2026
Merged

Optimize Explorer#531
pan-x-c merged 20 commits intoagentscope-ai:mainfrom
pan-x-c:feature/optmize_explorer

Conversation

@pan-x-c
Copy link
Copy Markdown
Collaborator

@pan-x-c pan-x-c commented Apr 25, 2026

Description

  1. Introduce RolloutCoordinator as a Ray Actor that directly holds the Scheduler and ExperiencePipeline objects, thereby eliminating the overhead previously incurred when the Scheduler transmitted Experience data to the ExperiencePipeline over the network.
  2. The WorkflowRunner passes pre-serialized Experience data to avoid the overhead associated with Ray's built-in serialization and deserialization mechanisms.
  3. Add a warm-up period for the Dynamic Timeout feature to enhance the representativeness of the computed results.

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

@pan-x-c
Copy link
Copy Markdown
Collaborator Author

pan-x-c commented Apr 25, 2026

/unittest-diff

@pan-x-c
Copy link
Copy Markdown
Collaborator Author

pan-x-c commented Apr 27, 2026

/unittest-diff

@github-actions
Copy link
Copy Markdown

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
189 187 0 2 0 0 35m 56s

Skipped

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

Tests

Test Name Status Flaky Duration
tests/buffer/experience_pipeline_test.py::TestExperiencePipeline::test_experience_pipeline 11.6s
tests/buffer/experience_pipeline_test.py::TestExperiencePipeline::test_pass_rate_calculation 6.2s
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_experience_buffer 2.7s
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 6.2s
tests/buffer/file_test.py::TestFileBuffer::test_file_reader 412ms
tests/buffer/file_test.py::TestFileBuffer::test_file_writer 1.8s
tests/buffer/formatter_test.py::TestFormatter::test_dpo_messages_formatter 907ms
tests/buffer/formatter_test.py::TestFormatter::test_dpo_plaintext_formatter 850ms
tests/buffer/formatter_test.py::TestFormatter::test_multi_modal_sft_formatter 1.7s
tests/buffer/formatter_test.py::TestFormatter::test_sft_messages_formatter 1.7s
tests/buffer/formatter_test.py::TestFormatter::test_sft_plaintext_formatter 1.4s
tests/buffer/formatter_test.py::TestFormatter::test_task_formatter 265ms
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_buffer_reuse 6.6s
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_capacity 2.3s
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 3.3s
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_capacity 3.8s
tests/buffer/reader_test.py::TestBufferReader::test_buffer_reader_registration 1.1s
tests/buffer/reward_shaping_mapper_test.py::TestRewardShapingMapper::test_basic_usage 9ms
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_default_queue_default_sample_strategy 2.1s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_default_queue_staleness_control_sample_strategy 1.8s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_priority_queue_default_sample_strategy 1.8s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_priority_queue_staleness_control_sample_strategy 1.6s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_sql_staleness_control_sample_strategy 4.6s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_default_queue_default_sample_strategy 1.9s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_default_queue_staleness_control_sample_strategy 1.6s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_priority_queue_default_sample_strategy 1.6s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_priority_queue_staleness_control_sample_strategy 1.8s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_sql_staleness_control_sample_strategy 3.7s
tests/buffer/sql_test.py::TestSQLBuffer::test_sql_exp_buffer_read_write_0 5.7s
tests/buffer/sql_test.py::TestSQLBuffer::test_sql_exp_buffer_read_write_1 2.4s
tests/buffer/sql_test.py::TestSQLBuffer::test_sql_task_buffer_read_write 3.0s
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_0 81ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_1 65ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_2 98ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_3 98ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_4 98ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_5 102ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_6 116ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_simple 53ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_0_file 351ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_1_sql 4.1s
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_2_file 47ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_3_sql 3.0s
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_4_file 47ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_5_sql 3.7s
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 22.1s
tests/common/config_test.py::TestConfig::test_chat_template_path 98ms
tests/common/config_test.py::TestConfig::test_config_flatten 36ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 212ms
tests/common/config_test.py::TestConfig::test_default_workflow 97ms
tests/common/config_test.py::TestConfig::test_load_default_config 1.3s
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly 100ms
tests/common/config_test.py::TestConfig::test_optimizer_config_propagation 97ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster 388ms
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_build_experience_token_view_aligns_prompt_action_mask_and_logprobs 1ms
tests/common/experience_test.py::TestExperience::test_deserialize_legacy_pickle_payload 1ms
tests/common/experience_test.py::TestExperience::test_deserialize_single_rejects_batch_payload 1ms
tests/common/experience_test.py::TestExperience::test_dpo_experience 1ms
tests/common/experience_test.py::TestExperience::test_format_colored_tokens_uses_action_mask 1ms
tests/common/experience_test.py::TestExperience::test_format_colored_tokens_uses_decoded_token_text 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_print_colored_tokens_writes_to_file 1ms
tests/common/experience_test.py::TestExperience::test_serialize_deserialize 1ms
tests/common/experience_test.py::TestExperience::test_serialize_many_deserialize_many 1ms
tests/common/experience_test.py::TestExperience::test_serialize_many_with_shared_multimodal_tensor 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_experience_model_experience_conversion 1ms
tests/common/external_model_test.py::TestExternalModel::test_external_model 55.0s
tests/common/external_model_test.py::TestExternalModelLoad::test_external_model_load 2.1s
tests/common/models/utils_test.py::TestTokenizeAndMaskMessagesDefault::test_first_message_is_assistant 295ms
tests/common/models/utils_test.py::TestTokenizeAndMaskMessagesDefault::test_messages_empty 606ms
tests/common/models/utils_test.py::TestTokenizeAndMaskMessagesDefault::test_no_assistant_messages 266ms
tests/common/models/utils_test.py::TestTokenizeAndMaskMessagesDefault::test_normal_conversation_data 647ms
tests/common/sudoku_test.py::test_9x9_generator_produces_valid_solution 2ms
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 1m 7s
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 41.9s
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 55.4s
tests/common/vllm_test.py::TestModelLen_0::test_model_len 27.0s
tests/common/vllm_test.py::TestModelLen_1::test_model_len 24.1s
tests/common/vllm_test.py::TestModelLen_2::test_model_len 43.3s
tests/common/vllm_test.py::TestModelLenWithoutPromptTruncation::test_model_len 27.6s
tests/common/vllm_test.py::TestMessageProcess::test_no_prompt_truncation 26.8s
tests/common/vllm_test.py::TestMessageProcess::test_truncation_status 27.4s
tests/common/vllm_test.py::TestAPIServer::test_api 25.6s
tests/common/vllm_test.py::TestAPIServer::test_reasoning_content ⏭️ 525ms
tests/common/vllm_test.py::TestLogprobs::test_logprobs_api 27.2s
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async 25.8s
tests/common/vllm_test.py::TestTinkerAsyncAPIServer::test_api_async ⏭️ 1ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask 312ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools 581ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 2m 27s
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 2m
tests/common/vllm_test.py::TestSuperLongGeneration::test_generate 4m 40s
tests/common/vllm_test.py::TestTinkerAPI::test_tinker_api 45.9s
tests/explorer/explorer_test.py::TestExplorerCountdownEval::test_explorer 1m 53s
tests/explorer/explorer_test.py::TestExplorerEvalDetailedStats::test_explorer 1m 20s
tests/explorer/explorer_test.py::TestExplorerGSM8KRULERNoEval::test_explorer 1m 27s
tests/explorer/explorer_test.py::TestExplorerGSM8k::test_explorer 3m 12s
tests/explorer/explorer_test.py::TestExplorerCoordinatorPath::test_explore_step_submits_train_batch_to_rollout_coordinator 2ms
tests/explorer/explorer_test.py::TestExplorerCoordinatorPath::test_finish_current_steps_uses_rollout_coordinator_finalize 2ms
tests/explorer/explorer_test.py::TestExplorerCoordinatorPath::test_finish_eval_step_uses_rollout_coordinator_finalize 2ms
tests/explorer/explorer_test.py::TestExplorerCoordinatorPolicies::test_over_rollout_submits_partial_finalize_policy_to_rollout_coordinator 1ms
tests/explorer/explorer_test.py::ServeTest::test_serve 1m 9s
tests/explorer/proxy_test.py::RecorderTest::test_recorder 60ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_abort_batch_marks_batch_aborted_and_evicts_it 2ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_eval_batch_aggregates_eval_metrics 3ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_train_batch_processes_scheduler_payloads_and_is_idempotent 3ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_train_batch_rejects_eval_batches_before_waiting 1ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_train_batch_supports_partial_finalize 3ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_train_batch_times_out_without_any_results 1ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_shutdown_closes_internal_dependencies 1ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_terminal_batches_are_not_reusable_after_finalize 3ms
tests/explorer/scheduler_test.py::SchedulerTest::test_async_workflow 5.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_collect_results_reads_payloads_returned_by_workflow_runner 5.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_concurrent_operations 5.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_dynamic_timeout 13.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_dynamic_timeout_warmup_min_steps_uses_completed_steps 7.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_eval_tasks_do_not_return_training_experiences 5.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_get_payload_results 30.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_get_payload_results_keeps_payloads_serialized 5.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_get_statuses_skips_payload_deserialization 5.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_0 5.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_1 5.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_0 5.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_1 5.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_multi_step_execution 5.7s
tests/explorer/scheduler_test.py::SchedulerTest::test_non_repeatable_workflow 5.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_async_cancelled_runner_accepts_next_batch 5.7s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_min_wait 9.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_return_partial_tasks 5.9s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_sync_cancel_does_not_imply_immediate_runner_reuse 7.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_all_methods 15.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_restart_after_stop 10.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_split_tasks 8.7s
tests/explorer/scheduler_test.py::SchedulerTest::test_stepwise_experience_eid 25.8s
tests/explorer/scheduler_test.py::SchedulerTest::test_timeout_cleanup_keeps_completed_payloads_local 10.8s
tests/explorer/scheduler_test.py::SchedulerTest::test_timeout_cleanup_still_restarts_runner 6.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_unexpected_task_exception_restarts_runner 4.9s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all 8.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all_timeout_with_multi_batch 14.0s
tests/explorer/scheduler_test.py::TestRunnerStateCollection::test_runner_state_collection 10.3s
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_reward_propagation_workflow_0 2ms
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 34ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_boxed_workflow 17ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_complex_workflow 141ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_eval_workflow 4ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_fraction_workflow 13ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_workflow 8ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_0 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_1 102ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_0 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_1 202ms
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_0::test_multi_turn_workflow 22.9s
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_1::test_multi_turn_workflow 22.9s
tests/explorer/workflow_test.py::TestWorkflowStateRecording::test_workflow_state_recording 4.0s
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter_v1 3.4s
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner 144ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_fail_fast_without_partial_collection_0_sequential 69ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_fail_fast_without_partial_collection_1_asynchronous 60ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_fail_fast_without_partial_collection_2_multi_threading 540ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_get_state 8.1s
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_partial_success_non_repeatable_0_sequential 39ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_partial_success_non_repeatable_1_asynchronous 40ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_partial_success_non_repeatable_2_multi_threading 41ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_with_openai 25.1s
tests/explorer/workflow_test.py::TestConcurrentWorkflowRunner::test_concurrent_workflow_runner 46.3s

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Copy Markdown
Collaborator Author

pan-x-c commented Apr 27, 2026

/unittest-module-trainer

@pan-x-c pan-x-c requested a review from Copilot April 27, 2026 08:21
Copy link
Copy Markdown

Copilot AI left a comment

Choose a reason for hiding this comment

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

Pull request overview

This PR optimizes the Explorer rollout path by keeping the Scheduler and ExperiencePipeline co-located in a new Ray actor (RolloutCoordinator), and by passing pre-serialized experience payloads to reduce Ray object serialization overhead. It also refines dynamic timeout behavior with a step-based warmup.

Changes:

  • Introduces RolloutCoordinator to own and coordinate Scheduler + ExperiencePipeline, providing batch-level finalize APIs.
  • Switches rollouts to return serialized experience payloads (bytes) instead of materialized Experience lists, and adds pipeline support for processing multiple serialized chunks.
  • Updates Scheduler APIs to return statuses separately from serialized payloads, and adds dynamic-timeout warmup by completed steps.

Reviewed changes

Copilot reviewed 14 out of 14 changed files in this pull request and generated 5 comments.

Show a summary per file
File Description
trinity/explorer/workflow_runner.py Returns serialized experience payloads from run_task and updates debug path accordingly.
trinity/explorer/scheduler.py Reworks result handling to keep payloads serialized; adds get_payload_results/get_statuses; updates dynamic timeout warmup logic.
trinity/explorer/rollout_coordinator.py New actor that owns Scheduler + ExperiencePipeline and exposes batch submission/finalization APIs.
trinity/explorer/proxy/service.py Routes experience submission through RolloutCoordinator.process_experiences.
trinity/explorer/explorer.py Switches exploration/eval finalization flow to use RolloutCoordinator.
trinity/explorer/init.py Exports RolloutCoordinator.
trinity/common/config.py Adds dynamic_timeout.warmup_min_steps.
trinity/buffer/pipelines/experience_pipeline.py Adds process_serialized_chunks to process multiple serialized payload chunks.
tests/explorer/workflow_test.py Adapts tests to deserialize payload bytes into experiences.
tests/explorer/scheduler_test.py Updates tests to use get_payload_results and validates no-deserialization paths.
tests/explorer/rollout_coordinator_test.py New unit tests for coordinator behavior.
tests/explorer/explorer_test.py Adds tests for coordinator-based Explorer path and adjusts serve wait loop.
docs/sphinx_doc/source_zh/tutorial/trinity_configs.md Documents warmup_min_steps and updated dynamic-timeout wording (ZH).
docs/sphinx_doc/source/tutorial/trinity_configs.md Documents warmup_min_steps and updated dynamic-timeout wording (EN).

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

Comment thread trinity/explorer/scheduler.py
Comment thread trinity/explorer/scheduler.py
Comment thread trinity/explorer/scheduler.py
Comment thread trinity/explorer/rollout_coordinator.py
Comment thread tests/explorer/rollout_coordinator_test.py Outdated
@github-actions
Copy link
Copy Markdown

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
27 18 6 3 0 0 53m 48s

Failed Tests

Failed Tests ❌ Fail Message
❌ tests/trainer/trainer_test.py::TestTrainerCountdown_0_fsdp::test_trainer The test failed in the call phase due to an assertion error
❌ tests/trainer/trainer_test.py::TestTrainerCountdown_1_megatron::test_trainer The test failed in the call phase due to an assertion error
❌ tests/trainer/trainer_test.py::TestFullyAsyncMode_0_fsdp::test_fully_async_mode The test failed in the call phase due to an assertion error
❌ tests/trainer/trainer_test.py::TestFullyAsyncMode_1_fsdp::test_fully_async_mode The test failed in the call phase due to an assertion error
❌ tests/trainer/trainer_test.py::TestFullyAsyncMode_2_megatron::test_fully_async_mode The test failed in the call phase due to an assertion error
❌ tests/trainer/trainer_test.py::TestTrainerLoRA::test_trainer The test failed in the call phase due to an assertion error

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 4m 37s
tests/trainer/trainer_test.py::TestTrainerCountdown_1_megatron::test_trainer 5m 34s
tests/trainer/trainer_test.py::TestStepAheadAsyncRL::test_trainer 1m 53s
tests/trainer/trainer_test.py::TestTrainerGSM8K_0_fsdp::test_trainer 1m 10s
tests/trainer/trainer_test.py::TestTrainerGSM8K_1_fsdp2::test_trainer 1m 17s
tests/trainer/trainer_test.py::TestTrainerGSM8K_2_fsdp::test_trainer 1m 10s
tests/trainer/trainer_test.py::TestTrainerGSM8K_3_fsdp2::test_trainer 1m 16s
tests/trainer/trainer_test.py::TestTrainerSFTWarmupGSM8K::test_trainer ⏭️ 1ms
tests/trainer/trainer_test.py::TestTrainerDPO::test_trainer 34.8s
tests/trainer/trainer_test.py::TestTrainerSFT::test_trainer 33.8s
tests/trainer/trainer_test.py::TestTrainerToolsSFT::test_trainer_tools 34.0s
tests/trainer/trainer_test.py::TestFullyAsyncMode_0_fsdp::test_fully_async_mode 1m 51s
tests/trainer/trainer_test.py::TestFullyAsyncMode_1_fsdp::test_fully_async_mode 1m 50s
tests/trainer/trainer_test.py::TestFullyAsyncMode_2_megatron::test_fully_async_mode 2m 37s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_0_fsdp::test_trainer 3m 3s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_1_megatron::test_trainer 5m 53s
tests/trainer/trainer_test.py::TestTrainerMIX::test_trainer 2m 10s
tests/trainer/trainer_test.py::TestServeWithTrainer::test_serve_with_trainer 1m 55s
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer 4m 25s
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer 1m 45s
tests/trainer/trainer_test.py::TestTrainerLoRA::test_trainer 3m 34s
tests/trainer/trainer_test.py::TestOverRollout::test_trainer 1m 9s
tests/trainer/trainer_test.py::TestTrainerPromptTruncation::test_trainer 53.6s
tests/trainer/trainer_test.py::TestTinkerTrainer::test_trainer ⏭️ 2ms
tests/trainer/trainer_test.py::TestTinkerTrainer::test_trainer_class ⏭️ 1ms
tests/trainer/trainer_test.py::AgentScopeTunerTest::test_agentscope_tuner 1m 38s
tests/trainer/trainer_test.py::ColocateModeTest::test_trainer 2m 11s

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Copy Markdown
Collaborator Author

pan-x-c commented Apr 27, 2026

/unittest-module-trainer

@github-actions
Copy link
Copy Markdown

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
27 24 0 3 0 0 53m 19s

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 4m 33s
tests/trainer/trainer_test.py::TestTrainerCountdown_1_megatron::test_trainer 5m 35s
tests/trainer/trainer_test.py::TestStepAheadAsyncRL::test_trainer 1m 45s
tests/trainer/trainer_test.py::TestTrainerGSM8K_0_fsdp::test_trainer 1m 16s
tests/trainer/trainer_test.py::TestTrainerGSM8K_1_fsdp2::test_trainer 1m 7s
tests/trainer/trainer_test.py::TestTrainerGSM8K_2_fsdp::test_trainer 1m 11s
tests/trainer/trainer_test.py::TestTrainerGSM8K_3_fsdp2::test_trainer 1m 15s
tests/trainer/trainer_test.py::TestTrainerSFTWarmupGSM8K::test_trainer ⏭️ 1ms
tests/trainer/trainer_test.py::TestTrainerDPO::test_trainer 36.6s
tests/trainer/trainer_test.py::TestTrainerSFT::test_trainer 32.3s
tests/trainer/trainer_test.py::TestTrainerToolsSFT::test_trainer_tools 31.7s
tests/trainer/trainer_test.py::TestFullyAsyncMode_0_fsdp::test_fully_async_mode 1m 51s
tests/trainer/trainer_test.py::TestFullyAsyncMode_1_fsdp::test_fully_async_mode 1m 51s
tests/trainer/trainer_test.py::TestFullyAsyncMode_2_megatron::test_fully_async_mode 2m 37s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_0_fsdp::test_trainer 3m 3s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_1_megatron::test_trainer 5m 53s
tests/trainer/trainer_test.py::TestTrainerMIX::test_trainer 2m 12s
tests/trainer/trainer_test.py::TestServeWithTrainer::test_serve_with_trainer 1m 58s
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer 4m 21s
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer 1m 46s
tests/trainer/trainer_test.py::TestTrainerLoRA::test_trainer 3m 30s
tests/trainer/trainer_test.py::TestOverRollout::test_trainer 1m 9s
tests/trainer/trainer_test.py::TestTrainerPromptTruncation::test_trainer 52.3s
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 39s
tests/trainer/trainer_test.py::ColocateModeTest::test_trainer 2m 4s

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Copy Markdown
Collaborator Author

pan-x-c commented Apr 27, 2026

/unittest-diff

@pan-x-c
Copy link
Copy Markdown
Collaborator Author

pan-x-c commented Apr 27, 2026

/unittest-diff

@github-actions
Copy link
Copy Markdown

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
189 179 8 2 0 0 37m 32s

Failed Tests

Failed Tests ❌ Fail Message
❌ tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_abort_batch_marks_batch_aborted_and_evicts_it The test failed in the call phase
❌ tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_eval_batch_aggregates_eval_metrics The test failed in the call phase
❌ tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_train_batch_processes_scheduler_payloads The test failed in the call phase
❌ tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_train_batch_rejects_eval_batches_before_waiting The test failed in the call phase
❌ tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_train_batch_supports_partial_finalize The test failed in the call phase
❌ tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_train_batch_times_out_without_any_results The test failed in the call phase
❌ tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_shutdown_closes_internal_dependencies The test failed in the call phase
❌ tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_terminal_batches_are_not_reusable_after_finalize The test failed in the call phase

Skipped

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

Tests

Test Name Status Flaky Duration
tests/buffer/experience_pipeline_test.py::TestExperiencePipeline::test_experience_pipeline 11.8s
tests/buffer/experience_pipeline_test.py::TestExperiencePipeline::test_pass_rate_calculation 10.7s
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_experience_buffer 2.7s
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_storage_0_sft 4.4s
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_storage_1_dpo 5.1s
tests/buffer/file_test.py::TestFileBuffer::test_file_reader 408ms
tests/buffer/file_test.py::TestFileBuffer::test_file_writer 1.5s
tests/buffer/formatter_test.py::TestFormatter::test_dpo_messages_formatter 906ms
tests/buffer/formatter_test.py::TestFormatter::test_dpo_plaintext_formatter 883ms
tests/buffer/formatter_test.py::TestFormatter::test_multi_modal_sft_formatter 1.7s
tests/buffer/formatter_test.py::TestFormatter::test_sft_messages_formatter 1.7s
tests/buffer/formatter_test.py::TestFormatter::test_sft_plaintext_formatter 1.4s
tests/buffer/formatter_test.py::TestFormatter::test_task_formatter 264ms
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_buffer_reuse 6.4s
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_capacity 2.3s
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 3.1s
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_1_priority_queue 3.3s
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_capacity 3.8s
tests/buffer/reader_test.py::TestBufferReader::test_buffer_reader_registration 1.1s
tests/buffer/reward_shaping_mapper_test.py::TestRewardShapingMapper::test_basic_usage 8ms
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_default_queue_default_sample_strategy 2.1s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_default_queue_staleness_control_sample_strategy 1.8s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_priority_queue_default_sample_strategy 1.8s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_priority_queue_staleness_control_sample_strategy 1.8s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_sql_staleness_control_sample_strategy 4.6s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_default_queue_default_sample_strategy 1.9s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_default_queue_staleness_control_sample_strategy 1.8s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_priority_queue_default_sample_strategy 1.6s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_priority_queue_staleness_control_sample_strategy 1.8s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_sql_staleness_control_sample_strategy 3.7s
tests/buffer/sql_test.py::TestSQLBuffer::test_sql_exp_buffer_read_write_0 5.7s
tests/buffer/sql_test.py::TestSQLBuffer::test_sql_exp_buffer_read_write_1 2.4s
tests/buffer/sql_test.py::TestSQLBuffer::test_sql_task_buffer_read_write 3.1s
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_0 79ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_1 63ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_2 98ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_3 99ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_4 98ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_5 103ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_6 117ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_simple 52ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_0_file 335ms
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 46ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_3_sql 2.7s
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_4_file 46ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_5_sql 3.5s
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 22.0s
tests/common/config_test.py::TestConfig::test_chat_template_path 98ms
tests/common/config_test.py::TestConfig::test_config_flatten 36ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 213ms
tests/common/config_test.py::TestConfig::test_default_workflow 97ms
tests/common/config_test.py::TestConfig::test_load_default_config 1.3s
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly 98ms
tests/common/config_test.py::TestConfig::test_optimizer_config_propagation 96ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster 384ms
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_build_experience_token_view_aligns_prompt_action_mask_and_logprobs 1ms
tests/common/experience_test.py::TestExperience::test_deserialize_legacy_pickle_payload 1ms
tests/common/experience_test.py::TestExperience::test_deserialize_single_rejects_batch_payload 1ms
tests/common/experience_test.py::TestExperience::test_dpo_experience 1ms
tests/common/experience_test.py::TestExperience::test_format_colored_tokens_uses_action_mask 1ms
tests/common/experience_test.py::TestExperience::test_format_colored_tokens_uses_decoded_token_text 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_print_colored_tokens_writes_to_file 1ms
tests/common/experience_test.py::TestExperience::test_serialize_deserialize 1ms
tests/common/experience_test.py::TestExperience::test_serialize_many_deserialize_many 1ms
tests/common/experience_test.py::TestExperience::test_serialize_many_with_shared_multimodal_tensor 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_experience_model_experience_conversion 1ms
tests/common/external_model_test.py::TestExternalModel::test_external_model 50.6s
tests/common/external_model_test.py::TestExternalModelLoad::test_external_model_load 2.1s
tests/common/models/utils_test.py::TestTokenizeAndMaskMessagesDefault::test_first_message_is_assistant 290ms
tests/common/models/utils_test.py::TestTokenizeAndMaskMessagesDefault::test_messages_empty 570ms
tests/common/models/utils_test.py::TestTokenizeAndMaskMessagesDefault::test_no_assistant_messages 263ms
tests/common/models/utils_test.py::TestTokenizeAndMaskMessagesDefault::test_normal_conversation_data 563ms
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 1m 8s
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 42.3s
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 49.3s
tests/common/vllm_test.py::TestModelLen_0::test_model_len 27.6s
tests/common/vllm_test.py::TestModelLen_1::test_model_len 42.0s
tests/common/vllm_test.py::TestModelLen_2::test_model_len 27.0s
tests/common/vllm_test.py::TestModelLenWithoutPromptTruncation::test_model_len 27.0s
tests/common/vllm_test.py::TestMessageProcess::test_no_prompt_truncation 31.9s
tests/common/vllm_test.py::TestMessageProcess::test_truncation_status 26.8s
tests/common/vllm_test.py::TestAPIServer::test_api 28.5s
tests/common/vllm_test.py::TestAPIServer::test_reasoning_content ⏭️ 523ms
tests/common/vllm_test.py::TestLogprobs::test_logprobs_api 23.2s
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async 26.3s
tests/common/vllm_test.py::TestTinkerAsyncAPIServer::test_api_async ⏭️ 1ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask 313ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools 641ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 2m 28s
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 2m 25s
tests/common/vllm_test.py::TestSuperLongGeneration::test_generate 4m 40s
tests/common/vllm_test.py::TestTinkerAPI::test_tinker_api 45.5s
tests/explorer/explorer_test.py::TestExplorerCountdownEval::test_explorer 1m 55s
tests/explorer/explorer_test.py::TestExplorerEvalDetailedStats::test_explorer 1m 23s
tests/explorer/explorer_test.py::TestExplorerGSM8KRULERNoEval::test_explorer 2m 37s
tests/explorer/explorer_test.py::TestExplorerGSM8k::test_explorer 3m 13s
tests/explorer/explorer_test.py::TestExplorerCoordinatorPath::test_explore_step_submits_train_batch_to_rollout_coordinator 3ms
tests/explorer/explorer_test.py::TestExplorerCoordinatorPath::test_finish_current_steps_uses_rollout_coordinator_finalize 2ms
tests/explorer/explorer_test.py::TestExplorerCoordinatorPath::test_finish_eval_step_uses_rollout_coordinator_finalize 3ms
tests/explorer/explorer_test.py::TestExplorerCoordinatorPolicies::test_over_rollout_submits_partial_finalize_policy_to_rollout_coordinator 2ms
tests/explorer/explorer_test.py::ServeTest::test_serve 1m 10s
tests/explorer/proxy_test.py::RecorderTest::test_recorder 60ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_abort_batch_marks_batch_aborted_and_evicts_it 9ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_eval_batch_aggregates_eval_metrics 7ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_train_batch_processes_scheduler_payloads 8ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_train_batch_rejects_eval_batches_before_waiting 9ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_train_batch_supports_partial_finalize 7ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_train_batch_times_out_without_any_results 7ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_shutdown_closes_internal_dependencies 8ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_terminal_batches_are_not_reusable_after_finalize 7ms
tests/explorer/scheduler_test.py::SchedulerTest::test_async_workflow 5.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_collect_results_reads_payloads_returned_by_workflow_runner 5.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_concurrent_operations 5.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_dynamic_timeout 13.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_dynamic_timeout_warmup_min_steps_uses_completed_steps 7.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_eval_tasks_do_not_return_training_experiences 5.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_get_payload_results 29.9s
tests/explorer/scheduler_test.py::SchedulerTest::test_get_payload_results_keeps_payloads_serialized 5.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_get_statuses_skips_payload_deserialization 5.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_0 5.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_1 5.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_0 5.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_1 5.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_multi_step_execution 5.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_non_repeatable_workflow 5.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_async_cancelled_runner_accepts_next_batch 5.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_min_wait 9.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_return_partial_tasks 5.7s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_sync_cancel_does_not_imply_immediate_runner_reuse 7.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_all_methods 15.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_restart_after_stop 10.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_split_tasks 9.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_stepwise_experience_eid 25.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_timeout_cleanup_keeps_completed_payloads_local 11.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_timeout_cleanup_still_restarts_runner 6.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_unexpected_task_exception_restarts_runner 5.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all 8.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all_timeout_with_multi_batch 13.9s
tests/explorer/scheduler_test.py::TestRunnerStateCollection::test_runner_state_collection 10.6s
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 27ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_boxed_workflow 17ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_complex_workflow 135ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_eval_workflow 4ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_fraction_workflow 11ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_workflow 9ms
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 202ms
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_0::test_multi_turn_workflow 22.1s
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_1::test_multi_turn_workflow 22.5s
tests/explorer/workflow_test.py::TestWorkflowStateRecording::test_workflow_state_recording 4.0s
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter_v1 3.5s
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner 142ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_fail_fast_without_partial_collection_0_sequential 69ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_fail_fast_without_partial_collection_1_asynchronous 59ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_fail_fast_without_partial_collection_2_multi_threading 540ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_get_state 8.1s
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_partial_success_non_repeatable_0_sequential 40ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_partial_success_non_repeatable_1_asynchronous 39ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_partial_success_non_repeatable_2_multi_threading 40ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_with_openai 24.2s
tests/explorer/workflow_test.py::TestConcurrentWorkflowRunner::test_concurrent_workflow_runner 45.0s

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Copy Markdown
Collaborator Author

pan-x-c commented Apr 27, 2026

/unittest-module-explorer

@github-actions
Copy link
Copy Markdown

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
77 77 0 0 0 0 18m 15s

Tests

Test Name Status Flaky Duration
tests/explorer/explorer_test.py::TestExplorerCountdownEval::test_explorer 2m 28s
tests/explorer/explorer_test.py::TestExplorerEvalDetailedStats::test_explorer 1m 51s
tests/explorer/explorer_test.py::TestExplorerGSM8KRULERNoEval::test_explorer 2m 57s
tests/explorer/explorer_test.py::TestExplorerGSM8k::test_explorer 3m 12s
tests/explorer/explorer_test.py::TestExplorerCoordinatorPath::test_explore_step_submits_train_batch_to_rollout_coordinator 3ms
tests/explorer/explorer_test.py::TestExplorerCoordinatorPath::test_finish_current_steps_uses_rollout_coordinator_finalize 2ms
tests/explorer/explorer_test.py::TestExplorerCoordinatorPath::test_finish_eval_step_uses_rollout_coordinator_finalize 1ms
tests/explorer/explorer_test.py::TestExplorerCoordinatorPolicies::test_over_rollout_submits_partial_finalize_policy_to_rollout_coordinator 2ms
tests/explorer/explorer_test.py::ServeTest::test_serve 1m 12s
tests/explorer/proxy_test.py::RecorderTest::test_recorder 59ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_abort_batch_marks_batch_aborted_and_evicts_it 2ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_eval_batch_aggregates_eval_metrics 3ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_train_batch_processes_scheduler_payloads 3ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_train_batch_rejects_eval_batches_before_waiting 2ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_train_batch_supports_partial_finalize 2ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_finalize_train_batch_times_out_without_any_results 2ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_shutdown_closes_internal_dependencies 1ms
tests/explorer/rollout_coordinator_test.py::TestRolloutCoordinator::test_terminal_batches_are_not_reusable_after_finalize 3ms
tests/explorer/scheduler_test.py::SchedulerTest::test_async_workflow 6.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_collect_results_reads_payloads_returned_by_workflow_runner 5.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_concurrent_operations 5.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_dynamic_timeout 13.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_dynamic_timeout_warmup_min_steps_uses_completed_steps 7.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_eval_tasks_do_not_return_training_experiences 5.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_get_payload_results 30.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_get_payload_results_keeps_payloads_serialized 5.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_get_statuses_skips_payload_deserialization 5.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_0 5.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_1 5.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_0 5.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_1 5.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_multi_step_execution 5.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_non_repeatable_workflow 5.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_async_cancelled_runner_accepts_next_batch 5.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_min_wait 8.9s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_return_partial_tasks 5.9s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_sync_cancel_does_not_imply_immediate_runner_reuse 7.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_all_methods 14.8s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_restart_after_stop 9.7s
tests/explorer/scheduler_test.py::SchedulerTest::test_split_tasks 8.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_stepwise_experience_eid 25.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_timeout_cleanup_keeps_completed_payloads_local 10.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_timeout_cleanup_still_restarts_runner 5.9s
tests/explorer/scheduler_test.py::SchedulerTest::test_unexpected_task_exception_restarts_runner 4.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all 8.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all_timeout_with_multi_batch 13.8s
tests/explorer/scheduler_test.py::TestRunnerStateCollection::test_runner_state_collection 10.2s
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_reward_propagation_workflow_0 2ms
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 30ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_boxed_workflow 18ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_complex_workflow 140ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_eval_workflow 4ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_fraction_workflow 13ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_workflow 8ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_0 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_1 102ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_0 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_1 202ms
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_0::test_multi_turn_workflow 22.8s
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_1::test_multi_turn_workflow 22.1s
tests/explorer/workflow_test.py::TestWorkflowStateRecording::test_workflow_state_recording 4.0s
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter_v1 3.3s
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner 540ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_fail_fast_without_partial_collection_0_sequential 69ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_fail_fast_without_partial_collection_1_asynchronous 60ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_fail_fast_without_partial_collection_2_multi_threading 542ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_get_state 8.1s
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_partial_success_non_repeatable_0_sequential 40ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_partial_success_non_repeatable_1_asynchronous 39ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_partial_success_non_repeatable_2_multi_threading 41ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_with_openai 24.0s
tests/explorer/workflow_test.py::TestConcurrentWorkflowRunner::test_concurrent_workflow_runner 46.2s

Github Test Reporter by CTRF 💚

@pan-x-c pan-x-c merged commit 4165dc1 into agentscope-ai:main Apr 28, 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.

3 participants