synth-ai 0.2.12__py3-none-any.whl → 0.2.13.dev2__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.
Potentially problematic release.
This version of synth-ai might be problematic. Click here for more details.
- examples/multi_step/configs/crafter_rl_outcome.toml +74 -0
- examples/multi_step/configs/crafter_rl_stepwise_hosted_judge.toml +186 -0
- examples/multi_step/configs/crafter_rl_stepwise_shaped.toml +83 -0
- examples/multi_step/configs/crafter_rl_stepwise_simple.toml +78 -0
- examples/multi_step/crafter_rl_lora.md +51 -10
- examples/multi_step/sse_metrics_streaming_notes.md +357 -0
- examples/multi_step/task_app_config_notes.md +7 -1
- examples/swe/task_app/grpo_swe_mini.py +55 -26
- examples/swe/task_app/hosted/rollout.py +40 -0
- examples/swe/task_app/hosted/test_service.py +5 -6
- examples/task_apps/TESTING.md +275 -0
- examples/task_apps/__init__.py +0 -0
- examples/task_apps/crafter/__init__.py +0 -0
- examples/task_apps/crafter/task_app/__init__.py +2 -0
- examples/{warming_up_to_rl → task_apps/crafter}/task_app/grpo_crafter.py +21 -46
- examples/{warming_up_to_rl → task_apps/crafter}/task_app/grpo_crafter_task_app.py +1 -1
- examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/policy.py +60 -4
- examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/inference/openai_client.py +109 -45
- examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/policy_routes.py +67 -49
- examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/rollout.py +242 -193
- examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/test_service.py +5 -6
- 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/__init__.py +0 -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/__init__.py +0 -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/__init__.py +0 -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 +1 -0
- examples/task_apps/enron/eval_groq_qwen32.toml +16 -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 +2 -0
- examples/task_apps/enron/tests/conftest.py +115 -0
- examples/task_apps/enron/tests/integration/__init__.py +2 -0
- examples/task_apps/enron/tests/integration/test_enron_eval.py +177 -0
- examples/task_apps/enron/tests/integration/test_enron_rollout.py +135 -0
- examples/task_apps/enron/tests/unit/__init__.py +2 -0
- examples/task_apps/enron/tests/unit/test_enron_environment.py +126 -0
- examples/task_apps/math/__init__.py +0 -0
- examples/{rl/task_app → task_apps/math}/math_single_step.py +19 -10
- 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/README.md +357 -0
- examples/task_apps/pokemon_red/__init__.py +3 -0
- examples/task_apps/pokemon_red/eval_pokemon_red_policy.py +225 -0
- examples/task_apps/pokemon_red/pallet_town_rl_config.toml +73 -0
- examples/task_apps/pokemon_red/task_app.py +606 -0
- examples/task_apps/pokemon_red/test_pallet_town_rewards.py +191 -0
- examples/task_apps/sokoban/README.md +307 -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/task_app.py +1058 -0
- examples/task_apps/sokoban/tests/__init__.py +2 -0
- examples/task_apps/sokoban/tests/conftest.py +113 -0
- examples/task_apps/sokoban/tests/integration/__init__.py +2 -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 +2 -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 +20 -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 +931 -0
- examples/task_apps/verilog/task_app/grpo_verilog_task_app.py +145 -0
- examples/task_apps/verilog/tests/__init__.py +2 -0
- examples/task_apps/verilog/tests/conftest.py +115 -0
- examples/task_apps/verilog/tests/integration/__init__.py +2 -0
- examples/task_apps/verilog/tests/integration/test_verilog_eval.py +179 -0
- examples/task_apps/verilog/tests/integration/test_verilog_rollout.py +55 -0
- examples/task_apps/verilog/tests/unit/__init__.py +2 -0
- examples/task_apps/verilog/tests/unit/test_verilog_scoring.py +118 -0
- examples/vlm/crafter_openai_vlm_agent.py +4 -4
- examples/vlm/run_crafter_vlm_benchmark.py +4 -4
- examples/warming_up_to_rl/configs/eval_stepwise_complex.toml +4 -2
- examples/warming_up_to_rl/configs/eval_stepwise_simple.toml +4 -2
- examples/warming_up_to_rl/run_eval.py +127 -18
- examples/workflows/__init__.py +0 -0
- examples/workflows/math_rl/__init__.py +0 -0
- examples/workflows/math_rl/download_dataset.py +80 -0
- synth_ai/__init__.py +41 -1
- synth_ai/api/train/builders.py +73 -29
- synth_ai/api/train/cli.py +12 -6
- synth_ai/api/train/configs/__init__.py +44 -0
- synth_ai/api/train/configs/rl.py +134 -0
- synth_ai/api/train/configs/sft.py +95 -0
- synth_ai/api/train/configs/shared.py +24 -0
- synth_ai/api/train/env_resolver.py +5 -2
- synth_ai/api/train/supported_algos.py +10 -5
- synth_ai/api/train/utils.py +7 -4
- synth_ai/cli/__init__.py +7 -51
- synth_ai/cli/_storage.py +4 -3
- synth_ai/cli/_validate_task_app.py +11 -0
- synth_ai/cli/balance.py +4 -3
- synth_ai/cli/calc.py +2 -2
- synth_ai/cli/demo.py +49 -43
- synth_ai/cli/legacy_root_backup.py +1 -1
- synth_ai/cli/rl_demo.py +86 -106
- synth_ai/cli/root.py +0 -97
- synth_ai/cli/task_apps.py +1710 -186
- synth_ai/demos/core/cli.py +121 -159
- synth_ai/demos/demo_task_apps/crafter/grpo_crafter_task_app.py +28 -16
- synth_ai/environments/examples/crafter_classic/environment.py +16 -0
- 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 +27 -0
- synth_ai/environments/examples/red/engine_helpers/memory_map.py +7 -0
- 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 +60 -0
- synth_ai/environments/examples/sokoban/taskset.py +116 -0
- synth_ai/environments/examples/verilog/engine.py +30 -4
- synth_ai/evals/__init__.py +15 -0
- synth_ai/evals/client.py +82 -0
- synth_ai/evals/types.py +42 -0
- synth_ai/jobs/client.py +16 -4
- synth_ai/judge_schemas.py +127 -0
- synth_ai/py.typed +0 -0
- synth_ai/task/__init__.py +14 -5
- synth_ai/task/contracts.py +124 -38
- synth_ai/task/proxy.py +48 -56
- synth_ai/task/rubrics/__init__.py +53 -0
- synth_ai/task/rubrics/loaders.py +133 -0
- synth_ai/task/rubrics/models.py +57 -0
- synth_ai/task/rubrics/scoring.py +113 -0
- synth_ai/task/rubrics/strict.py +149 -0
- synth_ai/task/server.py +8 -7
- synth_ai/task/validators.py +269 -6
- synth_ai/tracing_v3/decorators.py +7 -3
- synth_ai/tracing_v3/replica_sync.py +4 -4
- synth_ai/tracing_v3/serialization.py +130 -0
- synth_ai/tracing_v3/trace_utils.py +317 -0
- synth_ai/tracing_v3/turso/native_manager.py +3 -3
- {synth_ai-0.2.12.dist-info → synth_ai-0.2.13.dev2.dist-info}/METADATA +4 -1
- {synth_ai-0.2.12.dist-info → synth_ai-0.2.13.dev2.dist-info}/RECORD +228 -89
- {synth_ai-0.2.12.dist-info → synth_ai-0.2.13.dev2.dist-info}/entry_points.txt +0 -1
- synth_ai/task/rubrics.py +0 -219
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/README.md +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/README.md +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/__init__.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/branching.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/environment_routes.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/__init__.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/__init__.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/app.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/environment.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/react_agent.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/shared.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/tools.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/hosted_app.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/inference/__init__.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/main.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/registry.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/storage/__init__.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/storage/volume.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/test_agents.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/utils.py +0 -0
- /examples/{rl/task_app → task_apps/math}/README.md +0 -0
- /examples/{rl/task_app → task_apps/math}/math_task_app.py +0 -0
- /examples/{rl → workflows/math_rl}/configs/eval_base_qwen.toml +0 -0
- /examples/{rl → workflows/math_rl}/configs/eval_rl_qwen.toml +0 -0
- /examples/{rl → workflows/math_rl}/configs/rl_from_base_qwen.toml +0 -0
- /examples/{rl → workflows/math_rl}/configs/rl_from_base_qwen17.toml +0 -0
- /examples/{rl → workflows/math_rl}/configs/rl_from_ft_qwen.toml +0 -0
- /examples/{rl → workflows/math_rl}/run_eval.py +0 -0
- /examples/{rl → workflows/math_rl}/run_rl_and_save.py +0 -0
- {synth_ai-0.2.12.dist-info → synth_ai-0.2.13.dev2.dist-info}/WHEEL +0 -0
- {synth_ai-0.2.12.dist-info → synth_ai-0.2.13.dev2.dist-info}/licenses/LICENSE +0 -0
- {synth_ai-0.2.12.dist-info → synth_ai-0.2.13.dev2.dist-info}/top_level.txt +0 -0
|
@@ -0,0 +1,14 @@
|
|
|
1
|
+
# GRPO Enron Task App
|
|
2
|
+
|
|
3
|
+
This example mirrors the layout of the Crafter task app while targeting the
|
|
4
|
+
Enron email question answering environment found under
|
|
5
|
+
`synth_ai.environments.examples.enron`. It exposes the usual task-app config
|
|
6
|
+
entry point (`grpo_enron.py`) together with a compatibility wrapper
|
|
7
|
+
(`grpo_enron_task_app.py`) for running the FastAPI service directly or via
|
|
8
|
+
Modal.
|
|
9
|
+
|
|
10
|
+
The configuration builds a lightweight dataset from the Enron sample QA
|
|
11
|
+
corpus, publishes minimal task metadata, and provides a no-op rollout bridge
|
|
12
|
+
that yields the initial observation for the selected instance. The intent is
|
|
13
|
+
to serve as a starting point for richer integrations (rubrics, hosted env
|
|
14
|
+
service, policy orchestration) matching the Crafter example.
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
|