synth-ai 0.2.9.dev0__py3-none-any.whl → 0.2.23.dev3__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- examples/README.md +1 -0
- examples/__init__.py +16 -0
- examples/analyze_semantic_words.sh +17 -0
- examples/baseline/banking77_baseline.py +243 -0
- examples/baseline/banking77_pipeline_baseline.py +294 -0
- examples/baseline/crafter_baseline.py +407 -0
- examples/baseline/pokemon_red_baseline.py +326 -0
- examples/baseline/simple_baseline.py +56 -0
- examples/baseline/warming_up_to_rl_baseline.py +239 -0
- examples/blog_posts/gepa/README.md +355 -0
- examples/blog_posts/gepa/configs/banking77_gepa_local.toml +95 -0
- examples/blog_posts/gepa/configs/banking77_gepa_test.toml +80 -0
- examples/blog_posts/gepa/configs/banking77_mipro_local.toml +50 -0
- examples/blog_posts/gepa/configs/banking77_pipeline_gepa_local.toml +101 -0
- examples/blog_posts/gepa/configs/banking77_pipeline_gepa_test.toml +96 -0
- examples/blog_posts/gepa/configs/hotpotqa_gepa_local.toml +57 -0
- examples/blog_posts/gepa/configs/hotpotqa_gepa_qwen.toml +35 -0
- examples/blog_posts/gepa/configs/hotpotqa_mipro_local.toml +51 -0
- examples/blog_posts/gepa/configs/hover_gepa_local.toml +57 -0
- examples/blog_posts/gepa/configs/hover_gepa_qwen.toml +35 -0
- examples/blog_posts/gepa/configs/hover_mipro_local.toml +51 -0
- examples/blog_posts/gepa/configs/ifbench_gepa_local.toml +57 -0
- examples/blog_posts/gepa/configs/ifbench_gepa_qwen.toml +35 -0
- examples/blog_posts/gepa/configs/ifbench_mipro_local.toml +51 -0
- examples/blog_posts/gepa/configs/pupa_gepa_local.toml +58 -0
- examples/blog_posts/gepa/configs/pupa_mipro_local.toml +52 -0
- examples/blog_posts/gepa/deploy_banking77_task_app.sh +54 -0
- examples/blog_posts/gepa/gepa_baseline.py +204 -0
- examples/blog_posts/gepa/query_prompts_example.py +97 -0
- examples/blog_posts/gepa/run_gepa_banking77.sh +112 -0
- examples/blog_posts/gepa/run_gepa_banking77_pipeline.sh +163 -0
- examples/blog_posts/gepa/task_apps.py +105 -0
- examples/blog_posts/gepa/test_gepa_local.sh +67 -0
- examples/blog_posts/gepa/verify_banking77_setup.sh +123 -0
- examples/blog_posts/mipro/README.md +415 -0
- examples/blog_posts/mipro/configs/banking77_mipro_local.toml +91 -0
- examples/blog_posts/mipro/configs/banking77_mipro_test.toml +87 -0
- examples/blog_posts/mipro/configs/banking77_pipeline_mipro_gemini_flash_lite_local.toml +98 -0
- examples/blog_posts/mipro/configs/banking77_pipeline_mipro_gpt41mini_local.toml +96 -0
- examples/blog_posts/mipro/configs/banking77_pipeline_mipro_local.toml +94 -0
- examples/blog_posts/mipro/configs/banking77_pipeline_mipro_test.toml +170 -0
- examples/blog_posts/mipro/deploy_banking77_pipeline_task_app.sh +59 -0
- examples/blog_posts/mipro/deploy_banking77_task_app.sh +41 -0
- examples/blog_posts/mipro/multi_step.md +79 -0
- examples/blog_posts/mipro/run_mipro_banking77.sh +191 -0
- examples/blog_posts/mipro/run_mipro_banking77_pipeline.sh +171 -0
- examples/blog_posts/mipro/run_mipro_banking77_pipeline_gemini_flash_lite.sh +177 -0
- examples/blog_posts/mipro/run_mipro_banking77_pipeline_gpt41mini.sh +173 -0
- examples/blog_posts/mipro/verify_banking77_setup.sh +117 -0
- examples/blog_posts/pokemon_vl/README.md +98 -0
- examples/blog_posts/pokemon_vl/configs/eval_gpt5nano.toml +26 -0
- examples/blog_posts/pokemon_vl/configs/eval_qwen3_vl.toml +27 -0
- examples/blog_posts/pokemon_vl/configs/eval_rl_final.toml +24 -0
- examples/blog_posts/pokemon_vl/configs/filter_high_reward.toml +10 -0
- examples/blog_posts/pokemon_vl/configs/train_rl_from_sft.toml +43 -0
- examples/blog_posts/pokemon_vl/configs/train_sft_qwen4b_vl.toml +40 -0
- examples/blog_posts/pokemon_vl/extract_images.py +239 -0
- examples/blog_posts/pokemon_vl/pokemon_vl_baseline.py +326 -0
- examples/blog_posts/pokemon_vl/run_eval_extract_images.py +209 -0
- examples/blog_posts/pokemon_vl/run_qwen_eval_extract_images.py +212 -0
- examples/blog_posts/pokemon_vl/text_box_analysis.md +106 -0
- examples/blog_posts/warming_up_to_rl/ARCHITECTURE.md +195 -0
- examples/blog_posts/warming_up_to_rl/FINAL_TEST_RESULTS.md +127 -0
- examples/blog_posts/warming_up_to_rl/INFERENCE_SUCCESS.md +132 -0
- examples/blog_posts/warming_up_to_rl/README.md +158 -0
- examples/blog_posts/warming_up_to_rl/SMOKE_TESTING.md +164 -0
- examples/blog_posts/warming_up_to_rl/SMOKE_TEST_COMPLETE.md +253 -0
- examples/blog_posts/warming_up_to_rl/configs/eval_baseline_qwen32b_10x20.toml +25 -0
- examples/blog_posts/warming_up_to_rl/configs/eval_ft_qwen4b.toml +25 -0
- examples/blog_posts/warming_up_to_rl/configs/eval_ft_qwen4b_10x20.toml +26 -0
- examples/blog_posts/warming_up_to_rl/configs/eval_groq_qwen32b.toml +25 -0
- examples/blog_posts/warming_up_to_rl/configs/eval_openai_gpt_oss_120b.toml +29 -0
- examples/blog_posts/warming_up_to_rl/configs/filter_high_reward_dataset.toml +10 -0
- examples/blog_posts/warming_up_to_rl/configs/smoke_test.toml +75 -0
- examples/blog_posts/warming_up_to_rl/configs/train_rl_from_sft.toml +91 -0
- examples/blog_posts/warming_up_to_rl/configs/train_sft_qwen4b.toml +40 -0
- examples/blog_posts/warming_up_to_rl/warming_up_to_rl_baseline.py +187 -0
- examples/crafter_debug_render.py +186 -0
- examples/dev/qwen3_32b_qlora_4xh100.toml +45 -0
- examples/gepa/banking77_pipeline_gepa.toml +96 -0
- examples/gepa/multi_stage_gepa_example.toml +84 -0
- examples/gepa/run_gepa_banking77_pipeline.sh +157 -0
- examples/multi_step/SFT_README.md +147 -0
- examples/multi_step/configs/README_verilog_rl.md +77 -0
- examples/multi_step/configs/VERILOG_REWARDS.md +103 -0
- examples/multi_step/configs/VERILOG_RL_CHECKLIST.md +196 -0
- examples/multi_step/configs/crafter_eval_synth_qwen4b.toml +35 -0
- examples/multi_step/configs/crafter_eval_text_only_groq_qwen32b.toml +36 -0
- examples/multi_step/configs/crafter_rl_outcome.toml +75 -0
- examples/multi_step/configs/crafter_rl_stepwise_hosted_judge.toml +145 -0
- examples/multi_step/configs/crafter_rl_stepwise_shaped.toml +84 -0
- examples/multi_step/configs/crafter_rl_stepwise_simple.toml +79 -0
- examples/multi_step/configs/crafter_rl_stepwise_simple_NEW_FORMAT.toml +105 -0
- examples/multi_step/configs/crafter_sft_qwen30b_lora.toml +62 -0
- examples/multi_step/configs/crafter_synth_backend.md +40 -0
- examples/multi_step/configs/verilog_eval_groq_qwen32b.toml +31 -0
- examples/multi_step/configs/verilog_eval_synth_qwen8b.toml +33 -0
- examples/multi_step/configs/verilog_rl_lora.toml +147 -0
- examples/multi_step/convert_traces_to_sft.py +84 -0
- examples/multi_step/crafter_rl_lora.md +70 -0
- examples/multi_step/judges/crafter_backend_judge.py +220 -0
- examples/multi_step/judges/verilog_backend_judge.py +234 -0
- examples/multi_step/readme.md +48 -0
- examples/multi_step/run_sft_qwen30b.sh +45 -0
- examples/multi_step/sse_metrics_streaming_notes.md +357 -0
- examples/multi_step/task_app_config_notes.md +494 -0
- examples/multi_step/verilog_rl_lora.md +218 -0
- examples/qwen_coder/README.md +102 -0
- examples/qwen_coder/_shared.py +113 -0
- examples/qwen_coder/configs/coder_lora_30b.toml +60 -0
- examples/qwen_coder/configs/coder_lora_4b.toml +61 -0
- examples/qwen_coder/configs/coder_lora_small.toml +57 -0
- examples/qwen_coder/generate_dataset.py +98 -0
- examples/qwen_coder/infer_ft_smoke.py +65 -0
- examples/qwen_coder/infer_prod_proxy.py +73 -0
- examples/qwen_coder/infer_via_synth.py +87 -0
- examples/qwen_coder/scripts/infer_coder.sh +19 -0
- examples/qwen_coder/scripts/train_coder_30b.sh +22 -0
- examples/qwen_coder/sft_full_17b.py +103 -0
- examples/qwen_coder/sft_lora_30b.py +110 -0
- examples/qwen_coder/subset_jsonl.py +39 -0
- examples/qwen_coder/todos.md +38 -0
- examples/qwen_coder/validate_jsonl.py +60 -0
- examples/qwen_vl/BUGS_AND_FIXES.md +232 -0
- examples/qwen_vl/IMAGE_VALIDATION_COMPLETE.md +271 -0
- examples/qwen_vl/IMAGE_VALIDATION_SUMMARY.md +260 -0
- examples/qwen_vl/INFERENCE_SFT_TESTS.md +412 -0
- examples/qwen_vl/NEXT_STEPS_2B.md +325 -0
- examples/qwen_vl/QUICKSTART.md +327 -0
- examples/qwen_vl/QUICKSTART_RL_VISION.md +110 -0
- examples/qwen_vl/README.md +152 -0
- examples/qwen_vl/RL_VISION_COMPLETE.md +475 -0
- examples/qwen_vl/RL_VISION_TESTING.md +333 -0
- examples/qwen_vl/SDK_VISION_INTEGRATION.md +328 -0
- examples/qwen_vl/SETUP_COMPLETE.md +274 -0
- examples/qwen_vl/VISION_TESTS_COMPLETE.md +489 -0
- examples/qwen_vl/VLM_PIPELINE_COMPLETE.md +242 -0
- examples/qwen_vl/__init__.py +2 -0
- examples/qwen_vl/collect_data_via_cli.md +415 -0
- examples/qwen_vl/collect_vision_traces.py +368 -0
- examples/qwen_vl/configs/crafter_rl_vision_qwen3vl4b.toml +110 -0
- examples/qwen_vl/configs/crafter_vlm_sft_example.toml +59 -0
- examples/qwen_vl/configs/eval_gpt4o_mini_vision.toml +26 -0
- examples/qwen_vl/configs/eval_gpt4o_vision_proper.toml +29 -0
- examples/qwen_vl/configs/eval_gpt5nano_vision.toml +26 -0
- examples/qwen_vl/configs/eval_qwen3vl_vision.toml +26 -0
- examples/qwen_vl/configs/filter_qwen3vl_sft.toml +49 -0
- examples/qwen_vl/configs/filter_vision_sft.toml +52 -0
- examples/qwen_vl/configs/filter_vision_test.toml +8 -0
- examples/qwen_vl/configs/sft_qwen3_vl_2b_test.toml +54 -0
- examples/qwen_vl/crafter_gpt5nano_agent.py +308 -0
- examples/qwen_vl/crafter_qwen_vl_agent.py +300 -0
- examples/qwen_vl/run_vision_comparison.sh +61 -0
- examples/qwen_vl/run_vision_sft_pipeline.sh +175 -0
- examples/qwen_vl/test_image_validation.py +201 -0
- examples/qwen_vl/test_sft_vision_data.py +110 -0
- examples/rl/README.md +169 -0
- examples/rl/configs/eval_base_qwen.toml +17 -0
- examples/rl/configs/eval_rl_qwen.toml +13 -0
- examples/rl/configs/rl_from_base_qwen.toml +62 -0
- examples/rl/configs/rl_from_base_qwen17.toml +80 -0
- examples/rl/configs/rl_from_ft_qwen.toml +37 -0
- examples/rl/download_dataset.py +80 -0
- examples/rl/run_eval.py +436 -0
- examples/rl/run_rl_and_save.py +111 -0
- examples/rl/task_app/README.md +21 -0
- {synth_ai/task/apps → examples/rl/task_app}/math_single_step.py +188 -50
- examples/rl/task_app/math_task_app.py +111 -0
- examples/run_crafter_demo.sh +10 -0
- examples/sdk_prompt_learning_example.py +55 -0
- examples/sft/README.md +139 -0
- examples/sft/configs/crafter_fft_qwen0p6b.toml +49 -0
- examples/sft/configs/crafter_lora_qwen0p6b.toml +49 -0
- examples/sft/evaluate.py +117 -0
- examples/sft/export_dataset.py +120 -0
- examples/sft/generate_traces.py +164 -0
- examples/swe/__init__.py +12 -0
- examples/swe/task_app/README.md +135 -0
- examples/swe/task_app/__init__.py +2 -0
- examples/swe/task_app/grpo_swe_mini.py +604 -0
- examples/swe/task_app/grpo_swe_mini_task_app.py +124 -0
- examples/swe/task_app/hosted/README.md +173 -0
- examples/swe/task_app/hosted/__init__.py +5 -0
- examples/swe/task_app/hosted/branching.py +143 -0
- examples/swe/task_app/hosted/environment_routes.py +1289 -0
- examples/swe/task_app/hosted/envs/__init__.py +1 -0
- examples/swe/task_app/hosted/envs/crafter/__init__.py +6 -0
- examples/swe/task_app/hosted/envs/crafter/app.py +1 -0
- examples/swe/task_app/hosted/envs/crafter/environment.py +522 -0
- examples/swe/task_app/hosted/envs/crafter/policy.py +478 -0
- examples/swe/task_app/hosted/envs/crafter/react_agent.py +108 -0
- examples/swe/task_app/hosted/envs/crafter/shared.py +305 -0
- examples/swe/task_app/hosted/envs/crafter/tools.py +47 -0
- examples/swe/task_app/hosted/envs/mini_swe/__init__.py +8 -0
- examples/swe/task_app/hosted/envs/mini_swe/environment.py +1191 -0
- examples/swe/task_app/hosted/envs/mini_swe/policy.py +355 -0
- examples/swe/task_app/hosted/envs/mini_swe/shared.py +83 -0
- examples/swe/task_app/hosted/envs/mini_swe/tools.py +96 -0
- examples/swe/task_app/hosted/hosted_app.py +204 -0
- examples/swe/task_app/hosted/inference/__init__.py +5 -0
- examples/swe/task_app/hosted/inference/openai_client.py +584 -0
- examples/swe/task_app/hosted/main.py +100 -0
- examples/swe/task_app/hosted/policy_routes.py +1094 -0
- examples/swe/task_app/hosted/registry.py +195 -0
- examples/swe/task_app/hosted/rollout.py +1905 -0
- examples/swe/task_app/hosted/storage/__init__.py +5 -0
- examples/swe/task_app/hosted/storage/volume.py +211 -0
- examples/swe/task_app/hosted/test_agents.py +161 -0
- examples/swe/task_app/hosted/test_service.py +136 -0
- examples/swe/task_app/hosted/utils.py +62 -0
- examples/swe/task_app/morph_backend.py +178 -0
- examples/task_apps/IMAGE_ONLY_EVAL_QUICKSTART.md +258 -0
- examples/task_apps/TESTING.md +275 -0
- examples/task_apps/banking77/__init__.py +6 -0
- examples/task_apps/banking77/banking77_task_app.py +912 -0
- examples/task_apps/banking77/deploy_wrapper.py +46 -0
- examples/task_apps/banking77_pipeline/__init__.py +6 -0
- examples/task_apps/banking77_pipeline/banking77_pipeline_task_app.py +489 -0
- examples/task_apps/banking77_pipeline/deploy_wrapper.py +50 -0
- examples/task_apps/crafter/CREATE_SFT_DATASET.md +286 -0
- examples/task_apps/crafter/EVAL_IMAGE_ONLY_RESULTS.md +152 -0
- examples/task_apps/crafter/FILTER_COMMAND_STATUS.md +187 -0
- examples/task_apps/crafter/FILTER_COMMAND_SUCCESS.md +281 -0
- examples/task_apps/crafter/QUERY_EXAMPLES.md +203 -0
- examples/task_apps/crafter/README_IMAGE_ONLY_EVAL.md +316 -0
- examples/task_apps/crafter/eval_image_only_gpt4o.toml +28 -0
- examples/task_apps/crafter/eval_text_only_groq_llama.toml +36 -0
- examples/task_apps/crafter/filter_sft_dataset.toml +16 -0
- examples/task_apps/crafter/task_app/README.md +42 -0
- examples/task_apps/crafter/task_app/__init__.py +5 -0
- examples/task_apps/crafter/task_app/grpo_crafter.py +1055 -0
- examples/task_apps/crafter/task_app/grpo_crafter_task_app.py +146 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/README.md +173 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/__init__.py +5 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/branching.py +143 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/environment_routes.py +1226 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/envs/__init__.py +1 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/envs/crafter/__init__.py +6 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/envs/crafter/app.py +1 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/envs/crafter/environment.py +532 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/envs/crafter/policy.py +583 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/envs/crafter/react_agent.py +122 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/envs/crafter/shared.py +305 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/envs/crafter/tools.py +47 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/hosted_app.py +253 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/inference/__init__.py +5 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/inference/openai_client.py +999 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/main.py +100 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/policy_routes.py +1252 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/registry.py +195 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/rollout.py +2233 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/storage/__init__.py +5 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/storage/volume.py +211 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/test_agents.py +161 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/test_service.py +136 -0
- examples/task_apps/crafter/task_app/synth_envs_hosted/utils.py +411 -0
- examples/task_apps/dev/pokemon_emerald/__init__.py +2 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/README.md +811 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/__init__.py +120 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/action.py +160 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/memory.py +155 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/perception.py +69 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/planning.py +96 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/simple.py +1502 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/system_prompt.py +4 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/grab_map.py +68 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/manual.py +216 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/__init__.py +35 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/emerald_utils.py +631 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/emulator.py +1544 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/enums.py +1428 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/memory_reader.py +4848 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/types.py +41 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/utils.py +298 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pyproject.toml +95 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/run.py +204 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/server/app.py +2152 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/server/client.py +429 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/server/frame_server.py +155 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/README.md +78 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/run_tests.py +122 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_agent_direct.py +76 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_agent_prompts.py +413 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_battle_state_formatting.py +204 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_dialogue_detection.py +133 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_dialogue_detection_comprehensive.py +229 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_direct_agent_emulator.py +300 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_fps_adjustment_pytest.py +205 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_house_to_outside_direct.py +200 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_house_to_outside_transition.py +284 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_map_ground_truth_comparison.py +468 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_memory_map.py +575 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_server_map_validation.py +311 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_torchic_state.py +259 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/anticheat.py +372 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/checkpoint.py +296 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/error_handler.py +275 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/get_local_ip.py +22 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/helpers.py +44 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/llm_logger.py +514 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_formatter.py +415 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_stitcher.py +1763 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_stitcher_singleton.py +33 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_trimmer.py +106 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_visualizer.py +334 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/ocr_dialogue.py +1020 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/recording.py +188 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/state_formatter.py +1481 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/vlm.py +862 -0
- examples/task_apps/dev/pokemon_emerald/modal_app.py +114 -0
- examples/task_apps/dev/pokemon_emerald/task_app/README.md +81 -0
- examples/task_apps/dev/pokemon_emerald/task_app/__init__.py +6 -0
- examples/task_apps/dev/pokemon_emerald/task_app/pokemon_emerald.py +685 -0
- examples/task_apps/enron/__init__.py +2 -0
- examples/task_apps/enron/eval_groq_qwen32.toml +16 -0
- examples/task_apps/enron/filter_sft.toml +5 -0
- examples/task_apps/enron/task_app/README.md +14 -0
- examples/task_apps/enron/task_app/__init__.py +1 -0
- examples/task_apps/enron/task_app/grpo_enron.py +906 -0
- examples/task_apps/enron/task_app/grpo_enron_task_app.py +146 -0
- examples/task_apps/enron/tests/__init__.py +4 -0
- examples/task_apps/enron/tests/conftest.py +115 -0
- examples/task_apps/enron/tests/integration/__init__.py +4 -0
- examples/task_apps/enron/tests/integration/test_enron_eval.py +179 -0
- examples/task_apps/enron/tests/integration/test_enron_rollout.py +135 -0
- examples/task_apps/enron/tests/unit/__init__.py +4 -0
- examples/task_apps/enron/tests/unit/test_enron_environment.py +126 -0
- examples/task_apps/gepa_benchmarks/__init__.py +7 -0
- examples/task_apps/gepa_benchmarks/common.py +260 -0
- examples/task_apps/gepa_benchmarks/hotpotqa_task_app.py +507 -0
- examples/task_apps/gepa_benchmarks/hover_task_app.py +436 -0
- examples/task_apps/gepa_benchmarks/ifbench_task_app.py +563 -0
- examples/task_apps/gepa_benchmarks/pupa_task_app.py +460 -0
- examples/task_apps/math/README.md +21 -0
- examples/task_apps/math/math_single_step.py +1000 -0
- examples/task_apps/math/math_task_app.py +115 -0
- examples/task_apps/pokemon_battle/__init__.py +2 -0
- examples/task_apps/pokemon_battle/modal_app.py +104 -0
- examples/task_apps/pokemon_battle/task_app/README.md +68 -0
- examples/task_apps/pokemon_battle/task_app/__init__.py +6 -0
- examples/task_apps/pokemon_battle/task_app/pokemon_showdown.py +932 -0
- examples/task_apps/pokemon_red/EVAL_IMAGE_ONLY_COMPLETE.md +283 -0
- examples/task_apps/pokemon_red/EVAL_IMAGE_ONLY_STATUS.md +155 -0
- examples/task_apps/pokemon_red/README.md +356 -0
- examples/task_apps/pokemon_red/README_IMAGE_ONLY_EVAL.md +428 -0
- examples/task_apps/pokemon_red/__init__.py +3 -0
- examples/task_apps/pokemon_red/eval_image_only_gpt4o.toml +30 -0
- examples/task_apps/pokemon_red/eval_pokemon_red_policy.py +224 -0
- examples/task_apps/pokemon_red/pallet_town_rl_config.toml +75 -0
- examples/task_apps/pokemon_red/task_app.py +1048 -0
- examples/task_apps/pokemon_red/test_pallet_town_rewards.py +193 -0
- examples/task_apps/sokoban/README.md +306 -0
- examples/task_apps/sokoban/__init__.py +3 -0
- examples/task_apps/sokoban/eval_groq_qwen32.toml +16 -0
- examples/task_apps/sokoban/eval_openai_gpt5.toml +16 -0
- examples/task_apps/sokoban/filter_sft.toml +5 -0
- examples/task_apps/sokoban/task_app.py +1058 -0
- examples/task_apps/sokoban/tests/__init__.py +4 -0
- examples/task_apps/sokoban/tests/conftest.py +113 -0
- examples/task_apps/sokoban/tests/integration/__init__.py +4 -0
- examples/task_apps/sokoban/tests/integration/test_sokoban_eval.py +57 -0
- examples/task_apps/sokoban/tests/integration/test_sokoban_rollout.py +198 -0
- examples/task_apps/sokoban/tests/unit/__init__.py +4 -0
- examples/task_apps/sokoban/tests/unit/test_sokoban_environment.py +114 -0
- examples/task_apps/verilog/__init__.py +1 -0
- examples/task_apps/verilog/eval_groq_qwen32b.toml +22 -0
- examples/task_apps/verilog/filter_sft.toml +5 -0
- examples/task_apps/verilog/task_app/README.md +12 -0
- examples/task_apps/verilog/task_app/__init__.py +1 -0
- examples/task_apps/verilog/task_app/grpo_verilog.py +1166 -0
- examples/task_apps/verilog/task_app/grpo_verilog_task_app.py +145 -0
- examples/task_apps/verilog/tests/__init__.py +4 -0
- examples/task_apps/verilog/tests/conftest.py +115 -0
- examples/task_apps/verilog/tests/integration/__init__.py +4 -0
- examples/task_apps/verilog/tests/integration/test_verilog_eval.py +181 -0
- examples/task_apps/verilog/tests/integration/test_verilog_rollout.py +55 -0
- examples/task_apps/verilog/tests/unit/__init__.py +4 -0
- examples/task_apps/verilog/tests/unit/test_verilog_scoring.py +118 -0
- examples/tunnel_gepa_banking77/README.md +106 -0
- examples/tunnel_gepa_banking77/banking77_gepa_tunnel.toml +95 -0
- examples/tunnel_gepa_banking77/keep_tunnel_running.py +60 -0
- examples/tunnel_gepa_banking77/run_gepa_with_tunnel.sh +226 -0
- examples/vlm/PROPOSAL.md +53 -0
- examples/vlm/README.md +68 -0
- examples/vlm/configs/crafter_vlm_gpt4o.toml +49 -0
- examples/vlm/crafter_image_only_agent.py +207 -0
- examples/vlm/crafter_openai_vlm_agent.py +275 -0
- examples/vlm/filter_image_rows.py +63 -0
- examples/vlm/run_crafter_vlm_benchmark.py +316 -0
- examples/warming_up_to_rl/_utils.py +92 -0
- examples/warming_up_to_rl/analyze_trace_db.py +422 -0
- examples/warming_up_to_rl/configs/crafter_fft.toml +53 -0
- examples/warming_up_to_rl/configs/crafter_fft_4b.toml +54 -0
- examples/warming_up_to_rl/configs/eval_fft_qwen4b.toml +22 -0
- examples/warming_up_to_rl/configs/eval_groq_qwen32b.toml +15 -0
- examples/warming_up_to_rl/configs/eval_modal_qwen4b.toml +24 -0
- examples/warming_up_to_rl/configs/eval_stepwise_complex.toml +35 -0
- examples/warming_up_to_rl/configs/eval_stepwise_consistent.toml +26 -0
- examples/warming_up_to_rl/configs/eval_stepwise_per_achievement.toml +36 -0
- examples/warming_up_to_rl/configs/eval_stepwise_simple.toml +32 -0
- examples/warming_up_to_rl/configs/rl_from_base_qwen4b.toml +85 -0
- examples/warming_up_to_rl/configs/rl_from_ft.toml +58 -0
- examples/warming_up_to_rl/export_trace_sft.py +837 -0
- examples/warming_up_to_rl/groq_test.py +97 -0
- examples/warming_up_to_rl/manage_secrets.py +131 -0
- examples/warming_up_to_rl/old/event_rewards.md +234 -0
- examples/warming_up_to_rl/old/notes.md +73 -0
- examples/warming_up_to_rl/readme.md +110 -0
- examples/warming_up_to_rl/run_eval.py +736 -0
- examples/warming_up_to_rl/run_fft_and_save.py +380 -0
- examples/warming_up_to_rl/run_local_rollout.py +239 -0
- examples/warming_up_to_rl/run_local_rollout_modal.py +248 -0
- examples/warming_up_to_rl/run_local_rollout_parallel.py +405 -0
- examples/warming_up_to_rl/run_local_rollout_traced.py +477 -0
- examples/warming_up_to_rl/run_rl_and_save.py +124 -0
- examples/warming_up_to_rl/run_rollout_remote.py +156 -0
- examples/warming_up_to_rl/task_app/README.md +42 -0
- examples/warming_up_to_rl/task_app/grpo_crafter.py +876 -0
- examples/warming_up_to_rl/task_app/grpo_crafter_task_app.py +135 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/README.md +173 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/__init__.py +5 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/branching.py +143 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/environment_routes.py +1226 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/__init__.py +1 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/__init__.py +6 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/app.py +1 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/environment.py +522 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/policy.py +454 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/react_agent.py +108 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/shared.py +305 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/tools.py +47 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/hosted_app.py +253 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/inference/__init__.py +5 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/inference/openai_client.py +729 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/main.py +100 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/policy_routes.py +1114 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/registry.py +195 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/rollout.py +1891 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/storage/__init__.py +5 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/storage/volume.py +211 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/test_agents.py +161 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/test_service.py +137 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/utils.py +129 -0
- examples/workflows/math_rl/configs/eval_base_qwen.toml +15 -0
- examples/workflows/math_rl/configs/eval_rl_qwen.toml +11 -0
- examples/workflows/math_rl/configs/rl_from_base_qwen.toml +62 -0
- examples/workflows/math_rl/configs/rl_from_base_qwen17.toml +80 -0
- examples/workflows/math_rl/configs/rl_from_ft_qwen.toml +35 -0
- examples/workflows/math_rl/download_dataset.py +80 -0
- examples/workflows/math_rl/run_eval.py +436 -0
- examples/workflows/math_rl/run_rl_and_save.py +111 -0
- synth_ai/__init__.py +47 -23
- synth_ai/_utils/__init__.py +47 -0
- synth_ai/_utils/base_url.py +10 -0
- synth_ai/_utils/http.py +10 -0
- synth_ai/_utils/prompts.py +10 -0
- synth_ai/_utils/task_app_state.py +12 -0
- synth_ai/_utils/user_config.py +10 -0
- synth_ai/api/models/supported.py +514 -0
- synth_ai/api/train/__init__.py +60 -2
- synth_ai/api/train/builders.py +347 -39
- synth_ai/api/train/cli.py +895 -160
- synth_ai/api/train/config_finder.py +103 -25
- synth_ai/api/train/configs/__init__.py +65 -0
- synth_ai/api/train/configs/prompt_learning.py +496 -0
- synth_ai/api/train/configs/rl.py +188 -0
- synth_ai/api/train/configs/sft.py +99 -0
- synth_ai/api/train/configs/shared.py +81 -0
- synth_ai/api/train/env_resolver.py +70 -20
- synth_ai/api/train/pollers.py +29 -4
- synth_ai/api/train/prompt_learning.py +425 -0
- synth_ai/api/train/sft.py +390 -0
- synth_ai/api/train/supported_algos.py +147 -0
- synth_ai/api/train/task_app.py +6 -4
- synth_ai/api/train/utils.py +64 -52
- synth_ai/api/train/validators.py +1117 -0
- synth_ai/api/tunnel.py +49 -0
- synth_ai/auth/credentials.py +94 -0
- synth_ai/baseline/__init__.py +25 -0
- synth_ai/baseline/config.py +209 -0
- synth_ai/baseline/discovery.py +214 -0
- synth_ai/baseline/execution.py +146 -0
- synth_ai/cfgs.py +227 -0
- synth_ai/cli/__init__.py +85 -63
- synth_ai/cli/_modal_wrapper.py +31 -0
- synth_ai/cli/_storage.py +20 -0
- synth_ai/cli/_typer_patch.py +47 -0
- synth_ai/cli/_validate_task_app.py +29 -0
- synth_ai/cli/balance.py +16 -4
- synth_ai/cli/calc.py +36 -21
- synth_ai/cli/claude.py +70 -0
- synth_ai/cli/codex.py +267 -0
- synth_ai/cli/commands/__init__.py +18 -0
- synth_ai/cli/commands/baseline/__init__.py +12 -0
- synth_ai/cli/commands/baseline/core.py +637 -0
- synth_ai/cli/commands/baseline/list.py +93 -0
- synth_ai/cli/commands/demo/__init__.py +6 -0
- synth_ai/cli/commands/demo/core.py +163 -0
- synth_ai/cli/commands/eval/__init__.py +19 -0
- synth_ai/cli/commands/eval/core.py +1112 -0
- synth_ai/cli/commands/eval/errors.py +81 -0
- synth_ai/cli/commands/eval/validation.py +133 -0
- synth_ai/cli/commands/filter/__init__.py +12 -0
- synth_ai/cli/commands/filter/core.py +424 -0
- synth_ai/cli/commands/filter/errors.py +55 -0
- synth_ai/cli/commands/filter/validation.py +77 -0
- synth_ai/cli/commands/help/__init__.py +185 -0
- synth_ai/cli/commands/help/core.py +72 -0
- synth_ai/cli/commands/smoke/__init__.py +7 -0
- synth_ai/cli/commands/smoke/core.py +1437 -0
- synth_ai/cli/commands/status/__init__.py +66 -0
- synth_ai/cli/commands/status/client.py +192 -0
- synth_ai/cli/commands/status/config.py +92 -0
- synth_ai/cli/commands/status/errors.py +20 -0
- synth_ai/cli/commands/status/formatters.py +164 -0
- synth_ai/cli/commands/status/subcommands/__init__.py +9 -0
- synth_ai/cli/commands/status/subcommands/files.py +79 -0
- synth_ai/cli/commands/status/subcommands/jobs.py +334 -0
- synth_ai/cli/commands/status/subcommands/models.py +79 -0
- synth_ai/cli/commands/status/subcommands/pricing.py +22 -0
- synth_ai/cli/commands/status/subcommands/runs.py +81 -0
- synth_ai/cli/commands/status/subcommands/session.py +183 -0
- synth_ai/cli/commands/status/subcommands/summary.py +47 -0
- synth_ai/cli/commands/status/subcommands/usage.py +203 -0
- synth_ai/cli/commands/status/utils.py +114 -0
- synth_ai/cli/commands/train/__init__.py +53 -0
- synth_ai/cli/commands/train/core.py +21 -0
- synth_ai/cli/commands/train/errors.py +117 -0
- synth_ai/cli/commands/train/judge_schemas.py +200 -0
- synth_ai/cli/commands/train/judge_validation.py +305 -0
- synth_ai/cli/commands/train/validation.py +386 -0
- synth_ai/cli/demo.py +32 -140
- synth_ai/cli/deploy.py +233 -0
- synth_ai/cli/eval/__init__.py +36 -0
- synth_ai/cli/eval/core.py +5 -0
- synth_ai/cli/eval/errors.py +31 -0
- synth_ai/cli/eval/validation.py +5 -0
- synth_ai/cli/filter/__init__.py +28 -0
- synth_ai/cli/filter/core.py +5 -0
- synth_ai/cli/filter/errors.py +23 -0
- synth_ai/cli/filter/validation.py +5 -0
- synth_ai/cli/legacy_root_backup.py +28 -22
- synth_ai/cli/lib/__init__.py +10 -0
- synth_ai/cli/lib/task_app_discovery.py +7 -0
- synth_ai/cli/lib/task_app_env.py +518 -0
- synth_ai/cli/mcp.py +34 -0
- synth_ai/cli/modal_serve/__init__.py +12 -0
- synth_ai/cli/modal_serve/core.py +14 -0
- synth_ai/cli/modal_serve/errors.py +8 -0
- synth_ai/cli/modal_serve/validation.py +11 -0
- synth_ai/cli/opencode.py +256 -0
- synth_ai/cli/recent.py +13 -7
- synth_ai/cli/rl_demo.py +156 -116
- synth_ai/cli/root.py +131 -132
- synth_ai/cli/serve/__init__.py +12 -0
- synth_ai/cli/serve/core.py +14 -0
- synth_ai/cli/serve/errors.py +8 -0
- synth_ai/cli/serve/validation.py +11 -0
- synth_ai/cli/setup.py +49 -0
- synth_ai/cli/status.py +7 -125
- synth_ai/cli/task_app_deploy.py +7 -0
- synth_ai/cli/task_app_list.py +25 -0
- synth_ai/cli/task_app_modal_serve.py +11 -0
- synth_ai/cli/task_app_serve.py +11 -0
- synth_ai/cli/task_apps.py +2284 -257
- synth_ai/cli/traces.py +9 -5
- synth_ai/cli/train/__init__.py +12 -0
- synth_ai/cli/train/core.py +21 -0
- synth_ai/cli/train/errors.py +8 -0
- synth_ai/cli/train/validation.py +24 -0
- synth_ai/cli/train.py +5 -0
- synth_ai/cli/turso.py +73 -0
- synth_ai/cli/watch.py +13 -18
- synth_ai/demos/__init__.py +10 -0
- synth_ai/demos/core/__init__.py +28 -1
- synth_ai/demos/core/cli.py +579 -291
- synth_ai/demos/crafter/__init__.py +1 -0
- synth_ai/demos/crafter/crafter_fft_4b.toml +55 -0
- synth_ai/demos/crafter/grpo_crafter_task_app.py +185 -0
- synth_ai/demos/crafter/rl_from_base_qwen4b.toml +74 -0
- synth_ai/demos/demo_registry.py +176 -0
- synth_ai/demos/demo_task_apps/__init__.py +3 -3
- synth_ai/demos/demo_task_apps/core.py +64 -28
- synth_ai/demos/demo_task_apps/crafter/__init__.py +1 -0
- synth_ai/demos/demo_task_apps/crafter/configs/crafter_fft_4b.toml +53 -0
- synth_ai/demos/demo_task_apps/crafter/configs/rl_from_base_qwen4b.toml +73 -0
- synth_ai/demos/demo_task_apps/crafter/grpo_crafter_task_app.py +184 -0
- synth_ai/demos/demo_task_apps/math/_common.py +1 -2
- synth_ai/demos/demo_task_apps/math/app.py +2 -1
- synth_ai/demos/demo_task_apps/math/deploy_modal.py +3 -6
- synth_ai/demos/demo_task_apps/math/modal_task_app.py +185 -83
- synth_ai/demos/demo_task_apps/math/task_app_entry.py +0 -2
- synth_ai/demos/math/__init__.py +1 -0
- synth_ai/demos/math/_common.py +16 -0
- synth_ai/demos/math/app.py +38 -0
- synth_ai/demos/math/config.toml +76 -0
- synth_ai/demos/math/deploy_modal.py +54 -0
- synth_ai/demos/math/modal_task_app.py +703 -0
- synth_ai/demos/math/task_app_entry.py +51 -0
- synth_ai/environments/environment/core.py +7 -1
- synth_ai/environments/examples/bandit/engine.py +12 -5
- synth_ai/environments/examples/bandit/environment.py +0 -1
- synth_ai/environments/examples/bandit/taskset.py +4 -4
- synth_ai/environments/examples/crafter_classic/engine_deterministic_patch.py +7 -4
- synth_ai/environments/examples/crafter_classic/engine_serialization_patch_v3.py +9 -5
- synth_ai/environments/examples/crafter_classic/environment.py +93 -2
- synth_ai/environments/examples/crafter_classic/world_config_patch_simple.py +4 -3
- synth_ai/environments/examples/enron/engine.py +7 -2
- synth_ai/environments/examples/enron/environment.py +68 -0
- synth_ai/environments/examples/red/engine.py +60 -12
- synth_ai/environments/examples/red/engine_helpers/memory_map.py +7 -0
- synth_ai/environments/examples/red/engine_helpers/reward_components.py +151 -179
- synth_ai/environments/examples/red/engine_helpers/reward_library/pallet_town_progression.py +477 -0
- synth_ai/environments/examples/red/engine_helpers/state_extraction.py +32 -0
- synth_ai/environments/examples/red/environment.py +86 -0
- synth_ai/environments/examples/red/trace_hooks_v3.py +168 -0
- synth_ai/environments/examples/sokoban/taskset.py +116 -0
- synth_ai/environments/examples/verilog/engine.py +104 -12
- synth_ai/environments/examples/wordle/environment.py +0 -1
- synth_ai/environments/reproducibility/tree.py +5 -6
- synth_ai/environments/service/app.py +11 -12
- synth_ai/environments/service/core_routes.py +10 -9
- synth_ai/environments/stateful/engine.py +1 -1
- synth_ai/environments/tasks/core.py +1 -0
- synth_ai/environments/tasks/filters.py +5 -6
- synth_ai/environments/tasks/utils.py +4 -5
- synth_ai/evals/__init__.py +15 -0
- synth_ai/evals/base.py +14 -5
- synth_ai/evals/client.py +82 -0
- synth_ai/evals/types.py +42 -0
- synth_ai/http.py +8 -22
- synth_ai/http_client.py +45 -12
- synth_ai/inference/__init__.py +0 -2
- synth_ai/inference/client.py +21 -7
- synth_ai/jobs/client.py +129 -80
- synth_ai/judge_schemas.py +127 -0
- synth_ai/learning/__init__.py +51 -6
- synth_ai/learning/algorithms.py +14 -0
- synth_ai/learning/client.py +122 -30
- synth_ai/learning/config.py +2 -40
- synth_ai/learning/constants.py +0 -2
- synth_ai/learning/ft_client.py +4 -56
- synth_ai/learning/health.py +14 -8
- synth_ai/learning/jobs.py +43 -47
- synth_ai/learning/prompt_learning_client.py +276 -0
- synth_ai/learning/prompt_learning_types.py +185 -0
- synth_ai/{rl → learning/rl}/__init__.py +14 -5
- synth_ai/learning/rl/client.py +269 -0
- synth_ai/learning/rl/config.py +31 -0
- synth_ai/{rl → learning/rl}/contracts.py +5 -10
- synth_ai/{rl → learning/rl}/env_keys.py +45 -16
- synth_ai/learning/rl/secrets.py +13 -0
- synth_ai/learning/rl_client.py +2 -253
- synth_ai/learning/sft/__init__.py +29 -0
- synth_ai/learning/sft/client.py +68 -0
- synth_ai/learning/sft/config.py +270 -0
- synth_ai/learning/sft/data.py +698 -0
- synth_ai/learning/sse.py +25 -26
- synth_ai/learning/validators.py +29 -25
- synth_ai/mcp/__init__.py +5 -0
- synth_ai/mcp/__main__.py +8 -0
- synth_ai/mcp/main.py +254 -0
- synth_ai/mcp/setup.py +100 -0
- synth_ai/modal.py +257 -0
- synth_ai/pricing/__init__.py +3 -0
- synth_ai/pricing/model_pricing.py +64 -0
- synth_ai/session/__init__.py +75 -0
- synth_ai/session/client.py +383 -0
- synth_ai/session/constants.py +63 -0
- synth_ai/session/exceptions.py +105 -0
- synth_ai/session/manager.py +139 -0
- synth_ai/session/models.py +89 -0
- synth_ai/session/query.py +110 -0
- synth_ai/spec/__init__.py +46 -0
- synth_ai/spec/dataclasses.py +149 -0
- synth_ai/spec/loader.py +144 -0
- synth_ai/spec/serializer.py +199 -0
- synth_ai/spec/validation.py +250 -0
- synth_ai/streaming/__init__.py +29 -0
- synth_ai/streaming/config.py +94 -0
- synth_ai/streaming/handlers.py +589 -0
- synth_ai/streaming/streamer.py +320 -0
- synth_ai/streaming/types.py +95 -0
- synth_ai/task/__init__.py +50 -30
- synth_ai/task/apps/__init__.py +63 -19
- synth_ai/task/auth.py +35 -23
- synth_ai/task/client.py +15 -13
- synth_ai/task/config.py +261 -0
- synth_ai/task/contracts.py +165 -64
- synth_ai/task/datasets.py +9 -6
- synth_ai/task/errors.py +11 -10
- synth_ai/task/health.py +17 -11
- synth_ai/task/inference_api.py +101 -0
- synth_ai/task/json.py +58 -24
- synth_ai/task/proxy.py +59 -66
- synth_ai/task/rubrics/__init__.py +55 -0
- synth_ai/task/rubrics/loaders.py +156 -0
- synth_ai/task/rubrics/models.py +57 -0
- synth_ai/task/rubrics/scoring.py +116 -0
- synth_ai/task/rubrics/strict.py +149 -0
- synth_ai/task/rubrics.py +22 -15
- synth_ai/task/server.py +65 -31
- synth_ai/task/trace_correlation_helpers.py +328 -0
- synth_ai/task/tracing_utils.py +44 -28
- synth_ai/task/validators.py +449 -6
- synth_ai/task/vendors.py +5 -7
- synth_ai/tracing_v3/__init__.py +4 -0
- synth_ai/tracing_v3/abstractions.py +21 -4
- synth_ai/tracing_v3/config.py +167 -22
- synth_ai/tracing_v3/constants.py +21 -0
- synth_ai/tracing_v3/db_config.py +42 -29
- synth_ai/tracing_v3/decorators.py +80 -45
- synth_ai/tracing_v3/examples/basic_usage.py +15 -9
- synth_ai/tracing_v3/hooks.py +6 -4
- synth_ai/tracing_v3/llm_call_record_helpers.py +161 -61
- synth_ai/tracing_v3/migration_helper.py +1 -2
- synth_ai/tracing_v3/replica_sync.py +12 -7
- synth_ai/tracing_v3/serialization.py +130 -0
- synth_ai/tracing_v3/session_tracer.py +73 -16
- synth_ai/tracing_v3/storage/base.py +89 -1
- synth_ai/tracing_v3/storage/config.py +63 -16
- synth_ai/tracing_v3/storage/factory.py +11 -9
- synth_ai/tracing_v3/storage/utils.py +15 -11
- synth_ai/tracing_v3/trace_utils.py +317 -0
- synth_ai/tracing_v3/turso/__init__.py +8 -21
- synth_ai/tracing_v3/turso/daemon.py +123 -15
- synth_ai/tracing_v3/turso/models.py +5 -2
- synth_ai/tracing_v3/turso/native_manager.py +1293 -0
- synth_ai/tracing_v3/utils.py +5 -4
- synth_ai/tunnel.py +143 -0
- synth_ai/tunnel_deploy.py +278 -0
- synth_ai/types.py +8 -0
- synth_ai/urls.py +11 -0
- synth_ai/utils/__init__.py +166 -0
- synth_ai/utils/agents.py +74 -0
- synth_ai/utils/apps.py +152 -0
- synth_ai/utils/base_url.py +94 -0
- synth_ai/utils/bin.py +39 -0
- synth_ai/utils/claude.py +36 -0
- synth_ai/utils/cli.py +284 -0
- synth_ai/utils/config.py +81 -0
- synth_ai/utils/env.py +346 -0
- synth_ai/utils/errors.py +85 -0
- synth_ai/utils/http.py +172 -0
- synth_ai/utils/json.py +72 -0
- synth_ai/utils/log_filter.py +99 -0
- synth_ai/utils/logging.py +198 -0
- synth_ai/utils/modal.py +299 -0
- synth_ai/utils/paths.py +95 -0
- synth_ai/utils/process.py +233 -0
- synth_ai/utils/prompts.py +39 -0
- synth_ai/utils/sqld.py +122 -0
- synth_ai/utils/ssl.py +25 -0
- synth_ai/utils/task_app_discovery.py +882 -0
- synth_ai/utils/task_app_env.py +186 -0
- synth_ai/utils/task_app_state.py +318 -0
- synth_ai/utils/tunnel/__init__.py +12 -0
- synth_ai/utils/tunnel/config.py +55 -0
- synth_ai/utils/user_config.py +137 -0
- synth_ai/uvicorn.py +77 -0
- synth_ai-0.2.23.dev3.dist-info/METADATA +357 -0
- synth_ai-0.2.23.dev3.dist-info/RECORD +983 -0
- {synth_ai-0.2.9.dev0.dist-info → synth_ai-0.2.23.dev3.dist-info}/entry_points.txt +0 -1
- {synth_ai-0.2.9.dev0.dist-info → synth_ai-0.2.23.dev3.dist-info}/top_level.txt +1 -0
- synth_ai/cli/man.py +0 -106
- synth_ai/core/experiment.py +0 -15
- synth_ai/core/system.py +0 -15
- synth_ai/demo_registry.py +0 -258
- synth_ai/environments/examples/sokoban/units/astar_common.py +0 -95
- synth_ai/experimental/synth_oss.py +0 -446
- synth_ai/handshake.py +0 -107
- synth_ai/install_sqld.sh +0 -40
- synth_ai/learning/offline/dpo.py +0 -0
- synth_ai/learning/offline/providers.py +0 -7
- synth_ai/learning/offline/sft.py +0 -0
- synth_ai/learning/offline/shared.py +0 -0
- synth_ai/learning/online/grpo.py +0 -0
- synth_ai/learning/online/irft.py +0 -0
- synth_ai/learning/prompts/banking77_injection_eval.py +0 -168
- synth_ai/learning/prompts/gepa.py +0 -0
- synth_ai/learning/prompts/hello_world_in_context_injection_ex.py +0 -213
- synth_ai/learning/prompts/mipro.py +0 -289
- synth_ai/learning/prompts/random_search.py +0 -246
- synth_ai/learning/prompts/run_mipro_banking77.py +0 -172
- synth_ai/learning/prompts/run_random_search_banking77.py +0 -324
- synth_ai/lm/__init__.py +0 -51
- synth_ai/lm/caching/constants.py +0 -6
- synth_ai/lm/caching/dbs.py +0 -0
- synth_ai/lm/caching/ephemeral.py +0 -102
- synth_ai/lm/caching/handler.py +0 -137
- synth_ai/lm/caching/initialize.py +0 -11
- synth_ai/lm/caching/persistent.py +0 -114
- synth_ai/lm/config.py +0 -110
- synth_ai/lm/constants.py +0 -32
- synth_ai/lm/core/__init__.py +0 -8
- synth_ai/lm/core/all.py +0 -73
- synth_ai/lm/core/exceptions.py +0 -7
- synth_ai/lm/core/main.py +0 -319
- synth_ai/lm/core/main_v3.py +0 -594
- synth_ai/lm/core/synth_models.py +0 -48
- synth_ai/lm/core/vendor_clients.py +0 -188
- synth_ai/lm/cost/monitor.py +0 -1
- synth_ai/lm/cost/statefulness.py +0 -1
- synth_ai/lm/injection.py +0 -80
- synth_ai/lm/overrides.py +0 -206
- synth_ai/lm/provider_support/__init__.py +0 -8
- synth_ai/lm/provider_support/anthropic.py +0 -972
- synth_ai/lm/provider_support/openai.py +0 -1139
- synth_ai/lm/provider_support/suppress_logging.py +0 -31
- synth_ai/lm/structured_outputs/handler.py +0 -440
- synth_ai/lm/structured_outputs/inject.py +0 -297
- synth_ai/lm/structured_outputs/rehabilitate.py +0 -185
- synth_ai/lm/tools/__init__.py +0 -3
- synth_ai/lm/tools/base.py +0 -172
- synth_ai/lm/unified_interface.py +0 -202
- synth_ai/lm/vendors/base.py +0 -81
- synth_ai/lm/vendors/core/anthropic_api.py +0 -387
- synth_ai/lm/vendors/core/gemini_api.py +0 -292
- synth_ai/lm/vendors/core/mistral_api.py +0 -322
- synth_ai/lm/vendors/core/openai_api.py +0 -225
- synth_ai/lm/vendors/core/synth_dev_api.py +0 -0
- synth_ai/lm/vendors/local/ollama.py +0 -0
- synth_ai/lm/vendors/openai_standard.py +0 -780
- synth_ai/lm/vendors/openai_standard_responses.py +0 -256
- synth_ai/lm/vendors/retries.py +0 -22
- synth_ai/lm/vendors/supported/custom_endpoint.py +0 -417
- synth_ai/lm/vendors/supported/deepseek.py +0 -69
- synth_ai/lm/vendors/supported/grok.py +0 -75
- synth_ai/lm/vendors/supported/groq.py +0 -16
- synth_ai/lm/vendors/supported/ollama.py +0 -15
- synth_ai/lm/vendors/supported/openrouter.py +0 -74
- synth_ai/lm/vendors/supported/together.py +0 -11
- synth_ai/lm/vendors/synth_client.py +0 -808
- synth_ai/lm/warmup.py +0 -186
- synth_ai/rl/secrets.py +0 -19
- synth_ai/scripts/verify_rewards.py +0 -100
- synth_ai/task/apps/grpo_crafter.py +0 -438
- synth_ai/tracing/__init__.py +0 -30
- synth_ai/tracing_v1/__init__.py +0 -33
- synth_ai/tracing_v3/turso/manager.py +0 -774
- synth_ai/v0/tracing/abstractions.py +0 -224
- synth_ai/v0/tracing/base_client.py +0 -91
- synth_ai/v0/tracing/client_manager.py +0 -131
- synth_ai/v0/tracing/config.py +0 -142
- synth_ai/v0/tracing/context.py +0 -146
- synth_ai/v0/tracing/decorators.py +0 -682
- synth_ai/v0/tracing/events/__init__.py +0 -0
- synth_ai/v0/tracing/events/manage.py +0 -147
- synth_ai/v0/tracing/events/scope.py +0 -86
- synth_ai/v0/tracing/events/store.py +0 -228
- synth_ai/v0/tracing/immediate_client.py +0 -151
- synth_ai/v0/tracing/local.py +0 -18
- synth_ai/v0/tracing/log_client_base.py +0 -73
- synth_ai/v0/tracing/retry_queue.py +0 -186
- synth_ai/v0/tracing/trackers.py +0 -515
- synth_ai/v0/tracing/upload.py +0 -512
- synth_ai/v0/tracing/utils.py +0 -9
- synth_ai/v0/tracing_v1/__init__.py +0 -16
- synth_ai/v0/tracing_v1/abstractions.py +0 -224
- synth_ai/v0/tracing_v1/base_client.py +0 -91
- synth_ai/v0/tracing_v1/client_manager.py +0 -131
- synth_ai/v0/tracing_v1/config.py +0 -142
- synth_ai/v0/tracing_v1/context.py +0 -146
- synth_ai/v0/tracing_v1/decorators.py +0 -703
- synth_ai/v0/tracing_v1/events/__init__.py +0 -0
- synth_ai/v0/tracing_v1/events/manage.py +0 -147
- synth_ai/v0/tracing_v1/events/scope.py +0 -86
- synth_ai/v0/tracing_v1/events/store.py +0 -228
- synth_ai/v0/tracing_v1/immediate_client.py +0 -151
- synth_ai/v0/tracing_v1/local.py +0 -18
- synth_ai/v0/tracing_v1/log_client_base.py +0 -73
- synth_ai/v0/tracing_v1/retry_queue.py +0 -186
- synth_ai/v0/tracing_v1/trackers.py +0 -515
- synth_ai/v0/tracing_v1/upload.py +0 -527
- synth_ai/v0/tracing_v1/utils.py +0 -9
- synth_ai/zyk/__init__.py +0 -30
- synth_ai-0.2.9.dev0.dist-info/METADATA +0 -131
- synth_ai-0.2.9.dev0.dist-info/RECORD +0 -444
- {synth_ai/lm/caching → examples/task_apps}/__init__.py +0 -0
- {synth_ai/lm/cost → examples/task_apps/crafter}/__init__.py +0 -0
- {synth_ai/lm/structured_outputs → examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/server}/__init__.py +0 -0
- {synth_ai/lm/vendors → examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests}/__init__.py +0 -0
- {synth_ai/lm/vendors/core → examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils}/__init__.py +0 -0
- {synth_ai/lm/vendors/local → examples/task_apps/math}/__init__.py +0 -0
- {synth_ai/lm/vendors/supported → examples/workflows}/__init__.py +0 -0
- {synth_ai/v0/tracing → examples/workflows/math_rl}/__init__.py +0 -0
- /synth_ai/{compound/cais.py → cli/__main__.py} +0 -0
- /synth_ai/{learning/filtering.py → py.typed} +0 -0
- {synth_ai-0.2.9.dev0.dist-info → synth_ai-0.2.23.dev3.dist-info}/WHEEL +0 -0
- {synth_ai-0.2.9.dev0.dist-info → synth_ai-0.2.23.dev3.dist-info}/licenses/LICENSE +0 -0
|
@@ -1,438 +0,0 @@
|
|
|
1
|
-
from __future__ import annotations
|
|
2
|
-
|
|
3
|
-
"""Task App configuration for the GRPO Crafter example."""
|
|
4
|
-
|
|
5
|
-
import os
|
|
6
|
-
import sys
|
|
7
|
-
from dataclasses import dataclass
|
|
8
|
-
from pathlib import Path
|
|
9
|
-
from typing import Any, Dict, Iterable, List, Sequence
|
|
10
|
-
|
|
11
|
-
from ..contracts import RolloutRequest, RolloutResponse, TaskInfo
|
|
12
|
-
from ..datasets import TaskDatasetRegistry, TaskDatasetSpec
|
|
13
|
-
from ..rubrics import load_rubric
|
|
14
|
-
from ..server import ProxyConfig, RubricBundle, TaskAppConfig
|
|
15
|
-
from ..json import to_jsonable # noqa: F401 (imported for side-effect compatibility)
|
|
16
|
-
from . import ModalDeploymentConfig, TaskAppEntry, register_task_app
|
|
17
|
-
from ..tracing_utils import (
|
|
18
|
-
build_tracer_factory,
|
|
19
|
-
resolve_sft_output_dir,
|
|
20
|
-
resolve_tracing_db_url,
|
|
21
|
-
tracing_env_enabled,
|
|
22
|
-
)
|
|
23
|
-
|
|
24
|
-
from synth_ai.tracing_v3.session_tracer import SessionTracer
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
REPO_ROOT = Path(__file__).resolve().parents[3]
|
|
28
|
-
TASK_APP_ROOT = REPO_ROOT / "examples" / "warming_up_to_rl" / "task_app"
|
|
29
|
-
SYNTH_ENVS_HOSTED_ROOT = TASK_APP_ROOT / "synth_envs_hosted"
|
|
30
|
-
|
|
31
|
-
for path in [REPO_ROOT, TASK_APP_ROOT, SYNTH_ENVS_HOSTED_ROOT]:
|
|
32
|
-
path_str = str(path)
|
|
33
|
-
if path_str not in sys.path:
|
|
34
|
-
sys.path.insert(0, path_str)
|
|
35
|
-
|
|
36
|
-
try:
|
|
37
|
-
import crafter # type: ignore
|
|
38
|
-
import crafter.constants as C # type: ignore
|
|
39
|
-
from synth_ai.environments.examples.crafter_classic.taskset import TRAIT_BOUNDS, world_traits
|
|
40
|
-
from synth_envs_hosted.branching import router as branching_router
|
|
41
|
-
from synth_envs_hosted.environment_routes import router as environment_router
|
|
42
|
-
from synth_envs_hosted.hosted_app import TaskApp as HostedTaskApp
|
|
43
|
-
from synth_envs_hosted.policy_routes import router as policy_router
|
|
44
|
-
from synth_envs_hosted.rollout import (
|
|
45
|
-
RolloutEnvSpec as LegacyRolloutEnvSpec,
|
|
46
|
-
RolloutPolicySpec as LegacyRolloutPolicySpec,
|
|
47
|
-
RolloutRecordConfig as LegacyRolloutRecordConfig,
|
|
48
|
-
RolloutRequest as LegacyRolloutRequest,
|
|
49
|
-
RolloutResponse as LegacyRolloutResponse,
|
|
50
|
-
RolloutSafetyConfig as LegacyRolloutSafetyConfig,
|
|
51
|
-
execute_rollout as legacy_execute_rollout,
|
|
52
|
-
)
|
|
53
|
-
except Exception as exc: # pragma: no cover - import-time validation
|
|
54
|
-
# Provide a more actionable error with the missing module and fix hints
|
|
55
|
-
missing_mod = None
|
|
56
|
-
if isinstance(exc, ModuleNotFoundError):
|
|
57
|
-
missing_mod = getattr(exc, "name", None) or str(exc).split("'")[1] if "'" in str(exc) else None
|
|
58
|
-
fix_hint = None
|
|
59
|
-
if missing_mod:
|
|
60
|
-
mapping = {
|
|
61
|
-
"dotenv": "python-dotenv",
|
|
62
|
-
"crafter": "crafter",
|
|
63
|
-
"httpx": "httpx",
|
|
64
|
-
"aiohttp": "aiohttp",
|
|
65
|
-
"fastapi": "fastapi",
|
|
66
|
-
"uvicorn": "uvicorn",
|
|
67
|
-
"sqlalchemy": "sqlalchemy",
|
|
68
|
-
"aiosqlite": "aiosqlite",
|
|
69
|
-
"greenlet": "greenlet",
|
|
70
|
-
}
|
|
71
|
-
pkg = mapping.get(missing_mod, missing_mod)
|
|
72
|
-
fix_hint = (
|
|
73
|
-
f"Missing Python module '{missing_mod}'. Install the package '{pkg}'.\n"
|
|
74
|
-
f"For Modal: add '{pkg}' to ModalDeploymentConfig.pip_packages in synth_ai/task/apps/grpo_crafter.py.\n"
|
|
75
|
-
f"Locally: pip install {pkg}"
|
|
76
|
-
)
|
|
77
|
-
detailed = (
|
|
78
|
-
"grpo_crafter task app requires example dependencies and runtime libs.\n"
|
|
79
|
-
+ (fix_hint + "\n" if fix_hint else "")
|
|
80
|
-
+ f"Original error: {exc}"
|
|
81
|
-
)
|
|
82
|
-
raise RuntimeError(detailed) from exc
|
|
83
|
-
|
|
84
|
-
|
|
85
|
-
CRAFTING_RULES_SYSTEM_HINT = (
|
|
86
|
-
"Crafter crafting rules (from the paper):\n"
|
|
87
|
-
"- Make Wood Pickaxe: Nearby a table; have wood in inventory.\n"
|
|
88
|
-
"- Make Stone Pickaxe: Nearby a table; have wood and stone in inventory.\n"
|
|
89
|
-
"- Make Iron Pickaxe: Nearby a table; furnace exists; have wood, coal, and iron in inventory.\n"
|
|
90
|
-
"- Make Wood Sword: Nearby a table; have wood in inventory.\n"
|
|
91
|
-
"- Make Stone Sword: Nearby a table; have wood and stone in inventory.\n"
|
|
92
|
-
"- Make Iron Sword: Nearby a table; furnace exists; have wood, coal, and iron in inventory."
|
|
93
|
-
)
|
|
94
|
-
|
|
95
|
-
|
|
96
|
-
DATASET_SPEC = TaskDatasetSpec(
|
|
97
|
-
id="crafter_classic_procedural",
|
|
98
|
-
name="Crafter Classic Procedural Seeds",
|
|
99
|
-
version="1.0.0",
|
|
100
|
-
splits=["train"],
|
|
101
|
-
default_split="train",
|
|
102
|
-
description="Procedural Crafter Classic seeds with reproducible world traits.",
|
|
103
|
-
)
|
|
104
|
-
|
|
105
|
-
|
|
106
|
-
@dataclass
|
|
107
|
-
class CrafterDataset:
|
|
108
|
-
spec: TaskDatasetSpec
|
|
109
|
-
|
|
110
|
-
def __post_init__(self) -> None:
|
|
111
|
-
self.default_seed = int(env_value("CRAFTER_DEFAULT_SEED", 42))
|
|
112
|
-
self.seed_min = 0
|
|
113
|
-
self.seed_max = int(env_value("CRAFTER_MAX_SEED", 2**31 - 1))
|
|
114
|
-
area_env = env_value("CRAFTER_AREA", "64,64")
|
|
115
|
-
self.area = tuple(int(x) for x in str(area_env).split(","))
|
|
116
|
-
self.length = int(env_value("CRAFTER_EPISODE_LENGTH", 10000))
|
|
117
|
-
self._cache: Dict[int, Dict[str, Any]] = {}
|
|
118
|
-
|
|
119
|
-
def config_for_seed(self, seed: int) -> Dict[str, Any]:
|
|
120
|
-
return {
|
|
121
|
-
"seed": int(seed),
|
|
122
|
-
"area": list(self.area),
|
|
123
|
-
"length": self.length,
|
|
124
|
-
}
|
|
125
|
-
|
|
126
|
-
def describe_seed(self, seed: int) -> Dict[str, Any]:
|
|
127
|
-
seed = int(seed)
|
|
128
|
-
if seed in self._cache:
|
|
129
|
-
return self._cache[seed]
|
|
130
|
-
env = crafter.Env(area=self.area, length=self.length, seed=seed)
|
|
131
|
-
try:
|
|
132
|
-
env.reset()
|
|
133
|
-
traits = world_traits(env)
|
|
134
|
-
player = getattr(env, "_player", None)
|
|
135
|
-
inventory = dict(getattr(player, "inventory", {})) if player else {}
|
|
136
|
-
position = getattr(player, "pos", None)
|
|
137
|
-
finally:
|
|
138
|
-
close_fn = getattr(env, "close", None)
|
|
139
|
-
if callable(close_fn):
|
|
140
|
-
close_fn()
|
|
141
|
-
summary = {
|
|
142
|
-
"seed": seed,
|
|
143
|
-
"difficulty": self._difficulty(traits),
|
|
144
|
-
"traits": traits,
|
|
145
|
-
"inventory": inventory,
|
|
146
|
-
"player_position": list(position) if position is not None else None,
|
|
147
|
-
"config": self.config_for_seed(seed),
|
|
148
|
-
}
|
|
149
|
-
self._cache[seed] = summary
|
|
150
|
-
return summary
|
|
151
|
-
|
|
152
|
-
def _difficulty(self, traits: Dict[str, int]) -> str:
|
|
153
|
-
for difficulty, bounds in TRAIT_BOUNDS.items():
|
|
154
|
-
if (
|
|
155
|
-
traits.get("trees", 0) >= bounds.get("min_trees", 0)
|
|
156
|
-
and traits.get("hostiles", 0) <= bounds.get("max_hostiles", 0)
|
|
157
|
-
):
|
|
158
|
-
return difficulty
|
|
159
|
-
return "custom"
|
|
160
|
-
|
|
161
|
-
@property
|
|
162
|
-
def seed_range(self) -> List[int]:
|
|
163
|
-
return [self.seed_min, self.seed_max]
|
|
164
|
-
|
|
165
|
-
|
|
166
|
-
def env_value(key: str, default: Any) -> Any:
|
|
167
|
-
import os
|
|
168
|
-
|
|
169
|
-
return os.getenv(key, default)
|
|
170
|
-
|
|
171
|
-
|
|
172
|
-
def build_dataset() -> tuple[TaskDatasetRegistry, CrafterDataset]:
|
|
173
|
-
registry = TaskDatasetRegistry()
|
|
174
|
-
dataset = CrafterDataset(DATASET_SPEC)
|
|
175
|
-
registry.register(DATASET_SPEC, lambda _spec: dataset, cache=True)
|
|
176
|
-
return registry, dataset
|
|
177
|
-
|
|
178
|
-
|
|
179
|
-
def _base_task_info(dataset: CrafterDataset) -> TaskInfo:
|
|
180
|
-
return TaskInfo(
|
|
181
|
-
task={"id": "crafter_classic", "name": "Crafter Classic", "version": "1.0.0"},
|
|
182
|
-
environments=["crafter"],
|
|
183
|
-
action_space={
|
|
184
|
-
"type": "discrete",
|
|
185
|
-
"size": len(C.actions),
|
|
186
|
-
"actions": list(C.actions),
|
|
187
|
-
},
|
|
188
|
-
observation={
|
|
189
|
-
"summary": "RGB frame plus inventory, achievements, and semantic map patches.",
|
|
190
|
-
"keys": ["image", "inventory", "achievements", "semantic_map_patch7"],
|
|
191
|
-
"image_shape": [64, 64, 3],
|
|
192
|
-
},
|
|
193
|
-
dataset={
|
|
194
|
-
**DATASET_SPEC.model_dump(),
|
|
195
|
-
"seed_range": dataset.seed_range,
|
|
196
|
-
"default_seed": dataset.default_seed,
|
|
197
|
-
},
|
|
198
|
-
rubric={
|
|
199
|
-
"version": "1",
|
|
200
|
-
"criteria_count": 2,
|
|
201
|
-
"source": "inline",
|
|
202
|
-
"aggregation": "weighted_sum",
|
|
203
|
-
},
|
|
204
|
-
inference={
|
|
205
|
-
"supports_proxy": True,
|
|
206
|
-
"endpoints": {
|
|
207
|
-
"openai": "/proxy/v1/chat/completions",
|
|
208
|
-
"groq": "/proxy/groq/v1/chat/completions",
|
|
209
|
-
},
|
|
210
|
-
"tool": {"name": "interact", "parallel_tool_calls": False},
|
|
211
|
-
},
|
|
212
|
-
capabilities={
|
|
213
|
-
"supports_rollout": True,
|
|
214
|
-
"supports_env_lifecycle": True,
|
|
215
|
-
"requires_api_key_header": True,
|
|
216
|
-
},
|
|
217
|
-
limits={"max_ops": 100000, "max_time_s": 3600},
|
|
218
|
-
)
|
|
219
|
-
|
|
220
|
-
|
|
221
|
-
OUTCOME_RUBRIC = load_rubric(
|
|
222
|
-
{
|
|
223
|
-
"version": "1",
|
|
224
|
-
"goal_text": "Reward unlocking Crafter achievements and survival.",
|
|
225
|
-
"aggregation": "weighted_sum",
|
|
226
|
-
"criteria": [
|
|
227
|
-
{
|
|
228
|
-
"id": "achievements",
|
|
229
|
-
"description": "Unlock achievements or crafting milestones.",
|
|
230
|
-
"weight": 1.0,
|
|
231
|
-
},
|
|
232
|
-
{
|
|
233
|
-
"id": "survival",
|
|
234
|
-
"description": "Maintain health, food, and drink levels.",
|
|
235
|
-
"weight": 1.0,
|
|
236
|
-
},
|
|
237
|
-
],
|
|
238
|
-
}
|
|
239
|
-
)
|
|
240
|
-
|
|
241
|
-
EVENTS_RUBRIC = load_rubric(
|
|
242
|
-
{
|
|
243
|
-
"version": "1",
|
|
244
|
-
"goal_text": "Encourage purposeful step-wise exploration and crafting.",
|
|
245
|
-
"aggregation": "weighted_sum",
|
|
246
|
-
"criteria": [
|
|
247
|
-
{
|
|
248
|
-
"id": "progress_steps",
|
|
249
|
-
"description": "Actions progress quests, crafting, or exploration.",
|
|
250
|
-
"weight": 1.0,
|
|
251
|
-
}
|
|
252
|
-
],
|
|
253
|
-
}
|
|
254
|
-
)
|
|
255
|
-
|
|
256
|
-
|
|
257
|
-
def describe_taskset(dataset: CrafterDataset) -> Dict[str, Any]:
|
|
258
|
-
return {
|
|
259
|
-
**DATASET_SPEC.model_dump(),
|
|
260
|
-
"seed_range": dataset.seed_range,
|
|
261
|
-
"default_seed": dataset.default_seed,
|
|
262
|
-
"config": {
|
|
263
|
-
"area": list(dataset.area),
|
|
264
|
-
"length": dataset.length,
|
|
265
|
-
},
|
|
266
|
-
}
|
|
267
|
-
|
|
268
|
-
|
|
269
|
-
def provide_task_instances(dataset: CrafterDataset, base_info: TaskInfo, seeds: Sequence[int]) -> Iterable[TaskInfo]:
|
|
270
|
-
infos: list[TaskInfo] = []
|
|
271
|
-
for seed_value in seeds:
|
|
272
|
-
summary = dataset.describe_seed(seed_value)
|
|
273
|
-
infos.append(
|
|
274
|
-
TaskInfo(
|
|
275
|
-
task=base_info.task,
|
|
276
|
-
environments=base_info.environments,
|
|
277
|
-
action_space=base_info.action_space,
|
|
278
|
-
observation={
|
|
279
|
-
**base_info.observation,
|
|
280
|
-
"seed": seed_value,
|
|
281
|
-
"traits": summary["traits"],
|
|
282
|
-
"inventory": summary["inventory"],
|
|
283
|
-
"player_position": summary["player_position"],
|
|
284
|
-
},
|
|
285
|
-
dataset={
|
|
286
|
-
**base_info.dataset,
|
|
287
|
-
"seed": seed_value,
|
|
288
|
-
"difficulty": summary["difficulty"],
|
|
289
|
-
"config": summary["config"],
|
|
290
|
-
},
|
|
291
|
-
rubric=base_info.rubric,
|
|
292
|
-
inference=base_info.inference,
|
|
293
|
-
capabilities=base_info.capabilities,
|
|
294
|
-
limits=base_info.limits,
|
|
295
|
-
)
|
|
296
|
-
)
|
|
297
|
-
return infos
|
|
298
|
-
|
|
299
|
-
|
|
300
|
-
def _normalise_op(op_value: Any, index: int) -> str:
|
|
301
|
-
if isinstance(op_value, str):
|
|
302
|
-
candidate = op_value
|
|
303
|
-
elif isinstance(op_value, dict):
|
|
304
|
-
candidate = op_value.get("type") or op_value.get("op")
|
|
305
|
-
else:
|
|
306
|
-
candidate = None
|
|
307
|
-
if not candidate:
|
|
308
|
-
raise ValueError(f"Missing op type at index {index}")
|
|
309
|
-
lowered = str(candidate).strip().lower()
|
|
310
|
-
if lowered in {"policy", "agent", "model"}:
|
|
311
|
-
return "agent"
|
|
312
|
-
if lowered in {"env", "environment", "step"}:
|
|
313
|
-
return "env"
|
|
314
|
-
raise ValueError(f"Unsupported op type '{candidate}' at index {index}")
|
|
315
|
-
|
|
316
|
-
|
|
317
|
-
async def rollout_executor(request: RolloutRequest, fastapi_request) -> RolloutResponse:
|
|
318
|
-
converted_ops: List[str] = [_normalise_op(op, idx) for idx, op in enumerate(request.ops)]
|
|
319
|
-
legacy_request = LegacyRolloutRequest(
|
|
320
|
-
run_id=request.run_id,
|
|
321
|
-
env=LegacyRolloutEnvSpec(
|
|
322
|
-
env_id=request.env.env_id,
|
|
323
|
-
env_name=request.env.env_name,
|
|
324
|
-
config=request.env.config or {},
|
|
325
|
-
seed=request.env.seed,
|
|
326
|
-
),
|
|
327
|
-
policy=LegacyRolloutPolicySpec(
|
|
328
|
-
policy_id=request.policy.policy_id,
|
|
329
|
-
policy_name=request.policy.policy_name,
|
|
330
|
-
config=request.policy.config or {},
|
|
331
|
-
),
|
|
332
|
-
ops=converted_ops,
|
|
333
|
-
record=LegacyRolloutRecordConfig(**request.record.model_dump()),
|
|
334
|
-
on_done=request.on_done,
|
|
335
|
-
branch=None,
|
|
336
|
-
safety=LegacyRolloutSafetyConfig(**request.safety.model_dump()),
|
|
337
|
-
training_session_id=request.training_session_id,
|
|
338
|
-
synth_base_url=request.synth_base_url,
|
|
339
|
-
)
|
|
340
|
-
|
|
341
|
-
legacy_response: LegacyRolloutResponse = await legacy_execute_rollout(legacy_request, fastapi_request)
|
|
342
|
-
data = legacy_response.model_dump()
|
|
343
|
-
metrics = data.get("metrics", {}) or {}
|
|
344
|
-
metrics.setdefault("outcome_score", None)
|
|
345
|
-
metrics.setdefault("events_score", None)
|
|
346
|
-
metrics.setdefault("details", {})
|
|
347
|
-
data["metrics"] = metrics
|
|
348
|
-
return RolloutResponse.model_validate(data)
|
|
349
|
-
|
|
350
|
-
|
|
351
|
-
def build_config() -> TaskAppConfig:
|
|
352
|
-
registry, dataset = build_dataset()
|
|
353
|
-
base_info = _base_task_info(dataset)
|
|
354
|
-
|
|
355
|
-
hosted_task_app = HostedTaskApp()
|
|
356
|
-
|
|
357
|
-
tracing_enabled = tracing_env_enabled()
|
|
358
|
-
tracing_db_url = resolve_tracing_db_url()
|
|
359
|
-
tracer_factory = build_tracer_factory(SessionTracer, enabled=tracing_enabled, db_url=tracing_db_url)
|
|
360
|
-
sft_output_dir = resolve_sft_output_dir()
|
|
361
|
-
|
|
362
|
-
app_state: Dict[str, Any] = {
|
|
363
|
-
"task_app": hosted_task_app,
|
|
364
|
-
"allowed_environments": ["crafter"],
|
|
365
|
-
"tracing_enabled": tracing_enabled,
|
|
366
|
-
}
|
|
367
|
-
if tracer_factory is not None:
|
|
368
|
-
app_state["session_tracer_factory"] = tracer_factory
|
|
369
|
-
if sft_output_dir:
|
|
370
|
-
app_state["sft_output_dir"] = sft_output_dir
|
|
371
|
-
|
|
372
|
-
if tracing_enabled:
|
|
373
|
-
status_msg = f"[task:tracing] enabled (db={tracing_db_url or 'default'})"
|
|
374
|
-
else:
|
|
375
|
-
status_msg = "[task:tracing] disabled"
|
|
376
|
-
print(status_msg, flush=True)
|
|
377
|
-
if sft_output_dir:
|
|
378
|
-
print(f"[task:sft] writing JSONL to {sft_output_dir}", flush=True)
|
|
379
|
-
|
|
380
|
-
def _describe_taskset() -> Dict[str, Any]:
|
|
381
|
-
return describe_taskset(dataset)
|
|
382
|
-
|
|
383
|
-
def _provide_instances(seeds: Sequence[int]):
|
|
384
|
-
return provide_task_instances(dataset, base_info, seeds)
|
|
385
|
-
|
|
386
|
-
config = TaskAppConfig(
|
|
387
|
-
app_id="grpo-crafter",
|
|
388
|
-
name="GRPO Crafter Task App",
|
|
389
|
-
description="Crafter Classic environment with GRPO task endpoints and LLM proxies.",
|
|
390
|
-
base_task_info=base_info,
|
|
391
|
-
describe_taskset=_describe_taskset,
|
|
392
|
-
provide_task_instances=_provide_instances,
|
|
393
|
-
rollout=rollout_executor,
|
|
394
|
-
dataset_registry=registry,
|
|
395
|
-
rubrics=RubricBundle(outcome=OUTCOME_RUBRIC, events=EVENTS_RUBRIC),
|
|
396
|
-
proxy=ProxyConfig(enable_openai=True, enable_groq=True, system_hint=CRAFTING_RULES_SYSTEM_HINT),
|
|
397
|
-
routers=(environment_router, policy_router, branching_router),
|
|
398
|
-
app_state=app_state,
|
|
399
|
-
cors_origins=["*"],
|
|
400
|
-
)
|
|
401
|
-
return config
|
|
402
|
-
|
|
403
|
-
|
|
404
|
-
register_task_app(
|
|
405
|
-
entry=TaskAppEntry(
|
|
406
|
-
app_id="grpo-crafter",
|
|
407
|
-
description="Crafter Classic task app with rollout + proxy endpoints",
|
|
408
|
-
config_factory=build_config,
|
|
409
|
-
aliases=("crafter", "crafter-task"),
|
|
410
|
-
env_files=(str(REPO_ROOT / "backend" / ".env.dev"),),
|
|
411
|
-
modal=ModalDeploymentConfig(
|
|
412
|
-
app_name="grpo-crafter-task-app",
|
|
413
|
-
python_version="3.11",
|
|
414
|
-
pip_packages=(
|
|
415
|
-
"fastapi>=0.100.0",
|
|
416
|
-
"uvicorn>=0.23.0",
|
|
417
|
-
"pydantic>=2.0.0",
|
|
418
|
-
"numpy>=1.24.0",
|
|
419
|
-
"aiohttp>=3.8.0",
|
|
420
|
-
"httpx>=0.24.0",
|
|
421
|
-
"python-dotenv>=1.0.1",
|
|
422
|
-
# Tracing/DB runtime deps
|
|
423
|
-
"sqlalchemy>=2.0.42",
|
|
424
|
-
"aiosqlite>=0.21.0",
|
|
425
|
-
"greenlet>=3.2.3",
|
|
426
|
-
"crafter",
|
|
427
|
-
),
|
|
428
|
-
extra_local_dirs=(
|
|
429
|
-
(str(REPO_ROOT / 'synth_ai'), '/opt/synth_ai_repo/synth_ai'),
|
|
430
|
-
(str(TASK_APP_ROOT), '/opt/synth_ai_repo/examples/warming_up_to_rl/task_app'),
|
|
431
|
-
),
|
|
432
|
-
secret_names=("crafter-environment-sdk", "groq-api-key", "openai-api-key"),
|
|
433
|
-
memory=16384,
|
|
434
|
-
cpu=4.0,
|
|
435
|
-
max_containers=10,
|
|
436
|
-
),
|
|
437
|
-
)
|
|
438
|
-
)
|
synth_ai/tracing/__init__.py
DELETED
|
@@ -1,30 +0,0 @@
|
|
|
1
|
-
import importlib as _importlib
|
|
2
|
-
import sys as _sys
|
|
3
|
-
|
|
4
|
-
_pkg = _importlib.import_module("synth_ai.v0.tracing")
|
|
5
|
-
_sys.modules[__name__] = _pkg
|
|
6
|
-
|
|
7
|
-
_SUBMODULES = [
|
|
8
|
-
"abstractions",
|
|
9
|
-
"base_client",
|
|
10
|
-
"client_manager",
|
|
11
|
-
"config",
|
|
12
|
-
"context",
|
|
13
|
-
"decorators",
|
|
14
|
-
"immediate_client",
|
|
15
|
-
"local",
|
|
16
|
-
"log_client_base",
|
|
17
|
-
"retry_queue",
|
|
18
|
-
"trackers",
|
|
19
|
-
"upload",
|
|
20
|
-
"utils",
|
|
21
|
-
]
|
|
22
|
-
for _m in _SUBMODULES:
|
|
23
|
-
_sys.modules[f"{__name__}.{_m}"] = _importlib.import_module(f"synth_ai.v0.tracing.{_m}")
|
|
24
|
-
|
|
25
|
-
_events_pkg = _importlib.import_module("synth_ai.v0.tracing.events")
|
|
26
|
-
_sys.modules[f"{__name__}.events"] = _events_pkg
|
|
27
|
-
for _m in ["manage", "scope", "store"]:
|
|
28
|
-
_sys.modules[f"{__name__}.events.{_m}"] = _importlib.import_module(
|
|
29
|
-
f"synth_ai.v0.tracing.events.{_m}"
|
|
30
|
-
)
|
synth_ai/tracing_v1/__init__.py
DELETED
|
@@ -1,33 +0,0 @@
|
|
|
1
|
-
import importlib as _importlib
|
|
2
|
-
import sys as _sys
|
|
3
|
-
|
|
4
|
-
# Forward top-level package
|
|
5
|
-
_pkg = _importlib.import_module("synth_ai.v0.tracing_v1")
|
|
6
|
-
_sys.modules[__name__] = _pkg
|
|
7
|
-
|
|
8
|
-
# Explicitly forward submodules so `synth_ai.tracing_v1.X` works
|
|
9
|
-
_SUBMODULES = [
|
|
10
|
-
"abstractions",
|
|
11
|
-
"base_client",
|
|
12
|
-
"client_manager",
|
|
13
|
-
"config",
|
|
14
|
-
"context",
|
|
15
|
-
"decorators",
|
|
16
|
-
"immediate_client",
|
|
17
|
-
"local",
|
|
18
|
-
"log_client_base",
|
|
19
|
-
"retry_queue",
|
|
20
|
-
"trackers",
|
|
21
|
-
"upload",
|
|
22
|
-
"utils",
|
|
23
|
-
]
|
|
24
|
-
for _m in _SUBMODULES:
|
|
25
|
-
_sys.modules[f"{__name__}.{_m}"] = _importlib.import_module(f"synth_ai.v0.tracing_v1.{_m}")
|
|
26
|
-
|
|
27
|
-
# Forward events package and its submodules
|
|
28
|
-
_events_pkg = _importlib.import_module("synth_ai.v0.tracing_v1.events")
|
|
29
|
-
_sys.modules[f"{__name__}.events"] = _events_pkg
|
|
30
|
-
for _m in ["manage", "scope", "store"]:
|
|
31
|
-
_sys.modules[f"{__name__}.events.{_m}"] = _importlib.import_module(
|
|
32
|
-
f"synth_ai.v0.tracing_v1.events.{_m}"
|
|
33
|
-
)
|