synth-ai 0.2.13.dev1__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.

Files changed (226) hide show
  1. examples/multi_step/configs/crafter_rl_stepwise_hosted_judge.toml +12 -1
  2. examples/swe/task_app/grpo_swe_mini.py +55 -26
  3. examples/swe/task_app/hosted/rollout.py +40 -0
  4. examples/swe/task_app/hosted/test_service.py +5 -6
  5. examples/task_apps/TESTING.md +275 -0
  6. examples/task_apps/__init__.py +0 -0
  7. examples/task_apps/crafter/__init__.py +0 -0
  8. examples/task_apps/crafter/task_app/__init__.py +2 -0
  9. examples/{warming_up_to_rl → task_apps/crafter}/task_app/grpo_crafter.py +18 -13
  10. examples/{warming_up_to_rl → task_apps/crafter}/task_app/grpo_crafter_task_app.py +1 -1
  11. examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/policy.py +60 -4
  12. examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/policy_routes.py +25 -3
  13. examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/rollout.py +10 -0
  14. examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/test_service.py +5 -6
  15. examples/task_apps/dev/pokemon_emerald/__init__.py +2 -0
  16. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/README.md +811 -0
  17. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/__init__.py +120 -0
  18. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/action.py +160 -0
  19. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/memory.py +155 -0
  20. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/perception.py +69 -0
  21. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/planning.py +96 -0
  22. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/simple.py +1502 -0
  23. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/system_prompt.py +4 -0
  24. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/grab_map.py +68 -0
  25. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/manual.py +216 -0
  26. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/__init__.py +35 -0
  27. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/emerald_utils.py +631 -0
  28. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/emulator.py +1544 -0
  29. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/enums.py +1428 -0
  30. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/memory_reader.py +4848 -0
  31. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/types.py +41 -0
  32. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/utils.py +298 -0
  33. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pyproject.toml +95 -0
  34. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/run.py +204 -0
  35. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/server/__init__.py +0 -0
  36. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/server/app.py +2152 -0
  37. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/server/client.py +429 -0
  38. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/server/frame_server.py +155 -0
  39. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/README.md +78 -0
  40. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/__init__.py +0 -0
  41. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/run_tests.py +122 -0
  42. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_agent_direct.py +76 -0
  43. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_agent_prompts.py +413 -0
  44. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_battle_state_formatting.py +204 -0
  45. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_dialogue_detection.py +133 -0
  46. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_dialogue_detection_comprehensive.py +229 -0
  47. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_direct_agent_emulator.py +300 -0
  48. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_fps_adjustment_pytest.py +205 -0
  49. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_house_to_outside_direct.py +200 -0
  50. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_house_to_outside_transition.py +284 -0
  51. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_map_ground_truth_comparison.py +468 -0
  52. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_memory_map.py +575 -0
  53. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_server_map_validation.py +311 -0
  54. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_torchic_state.py +259 -0
  55. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/__init__.py +0 -0
  56. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/anticheat.py +372 -0
  57. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/checkpoint.py +296 -0
  58. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/error_handler.py +275 -0
  59. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/get_local_ip.py +22 -0
  60. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/helpers.py +44 -0
  61. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/llm_logger.py +514 -0
  62. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_formatter.py +415 -0
  63. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_stitcher.py +1763 -0
  64. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_stitcher_singleton.py +33 -0
  65. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_trimmer.py +106 -0
  66. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_visualizer.py +334 -0
  67. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/ocr_dialogue.py +1020 -0
  68. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/recording.py +188 -0
  69. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/state_formatter.py +1481 -0
  70. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/vlm.py +862 -0
  71. examples/task_apps/dev/pokemon_emerald/modal_app.py +114 -0
  72. examples/task_apps/dev/pokemon_emerald/task_app/README.md +81 -0
  73. examples/task_apps/dev/pokemon_emerald/task_app/__init__.py +6 -0
  74. examples/task_apps/dev/pokemon_emerald/task_app/pokemon_emerald.py +685 -0
  75. examples/task_apps/enron/__init__.py +1 -0
  76. examples/task_apps/enron/eval_groq_qwen32.toml +16 -0
  77. examples/task_apps/enron/task_app/README.md +14 -0
  78. examples/task_apps/enron/task_app/__init__.py +1 -0
  79. examples/task_apps/enron/task_app/grpo_enron.py +906 -0
  80. examples/task_apps/enron/task_app/grpo_enron_task_app.py +146 -0
  81. examples/task_apps/enron/tests/__init__.py +2 -0
  82. examples/task_apps/enron/tests/conftest.py +115 -0
  83. examples/task_apps/enron/tests/integration/__init__.py +2 -0
  84. examples/task_apps/enron/tests/integration/test_enron_eval.py +177 -0
  85. examples/task_apps/enron/tests/integration/test_enron_rollout.py +135 -0
  86. examples/task_apps/enron/tests/unit/__init__.py +2 -0
  87. examples/task_apps/enron/tests/unit/test_enron_environment.py +126 -0
  88. examples/task_apps/math/__init__.py +0 -0
  89. examples/{rl/task_app → task_apps/math}/math_single_step.py +19 -10
  90. examples/task_apps/pokemon_battle/__init__.py +2 -0
  91. examples/task_apps/pokemon_battle/modal_app.py +104 -0
  92. examples/task_apps/pokemon_battle/task_app/README.md +68 -0
  93. examples/task_apps/pokemon_battle/task_app/__init__.py +6 -0
  94. examples/task_apps/pokemon_battle/task_app/pokemon_showdown.py +932 -0
  95. examples/task_apps/pokemon_red/README.md +357 -0
  96. examples/task_apps/pokemon_red/__init__.py +3 -0
  97. examples/task_apps/pokemon_red/eval_pokemon_red_policy.py +225 -0
  98. examples/task_apps/pokemon_red/pallet_town_rl_config.toml +73 -0
  99. examples/task_apps/pokemon_red/task_app.py +606 -0
  100. examples/task_apps/pokemon_red/test_pallet_town_rewards.py +191 -0
  101. examples/task_apps/sokoban/README.md +307 -0
  102. examples/task_apps/sokoban/__init__.py +3 -0
  103. examples/task_apps/sokoban/eval_groq_qwen32.toml +16 -0
  104. examples/task_apps/sokoban/eval_openai_gpt5.toml +16 -0
  105. examples/task_apps/sokoban/task_app.py +1058 -0
  106. examples/task_apps/sokoban/tests/__init__.py +2 -0
  107. examples/task_apps/sokoban/tests/conftest.py +113 -0
  108. examples/task_apps/sokoban/tests/integration/__init__.py +2 -0
  109. examples/task_apps/sokoban/tests/integration/test_sokoban_eval.py +57 -0
  110. examples/task_apps/sokoban/tests/integration/test_sokoban_rollout.py +198 -0
  111. examples/task_apps/sokoban/tests/unit/__init__.py +2 -0
  112. examples/task_apps/sokoban/tests/unit/test_sokoban_environment.py +114 -0
  113. examples/task_apps/verilog/__init__.py +1 -0
  114. examples/task_apps/verilog/eval_groq_qwen32b.toml +20 -0
  115. examples/task_apps/verilog/task_app/README.md +12 -0
  116. examples/task_apps/verilog/task_app/__init__.py +1 -0
  117. examples/task_apps/verilog/task_app/grpo_verilog.py +931 -0
  118. examples/task_apps/verilog/task_app/grpo_verilog_task_app.py +145 -0
  119. examples/task_apps/verilog/tests/__init__.py +2 -0
  120. examples/task_apps/verilog/tests/conftest.py +115 -0
  121. examples/task_apps/verilog/tests/integration/__init__.py +2 -0
  122. examples/task_apps/verilog/tests/integration/test_verilog_eval.py +179 -0
  123. examples/task_apps/verilog/tests/integration/test_verilog_rollout.py +55 -0
  124. examples/task_apps/verilog/tests/unit/__init__.py +2 -0
  125. examples/task_apps/verilog/tests/unit/test_verilog_scoring.py +118 -0
  126. examples/vlm/crafter_openai_vlm_agent.py +4 -4
  127. examples/vlm/run_crafter_vlm_benchmark.py +4 -4
  128. examples/workflows/__init__.py +0 -0
  129. examples/workflows/math_rl/__init__.py +0 -0
  130. examples/workflows/math_rl/download_dataset.py +80 -0
  131. synth_ai/__init__.py +2 -2
  132. synth_ai/api/train/builders.py +25 -11
  133. synth_ai/api/train/cli.py +12 -6
  134. synth_ai/api/train/configs/__init__.py +10 -10
  135. synth_ai/api/train/configs/rl.py +5 -4
  136. synth_ai/api/train/configs/sft.py +4 -3
  137. synth_ai/api/train/env_resolver.py +5 -2
  138. synth_ai/api/train/supported_algos.py +10 -5
  139. synth_ai/api/train/utils.py +7 -4
  140. synth_ai/cli/__init__.py +7 -51
  141. synth_ai/cli/_storage.py +4 -3
  142. synth_ai/cli/_validate_task_app.py +11 -0
  143. synth_ai/cli/balance.py +4 -3
  144. synth_ai/cli/calc.py +2 -2
  145. synth_ai/cli/demo.py +14 -7
  146. synth_ai/cli/legacy_root_backup.py +1 -1
  147. synth_ai/cli/rl_demo.py +8 -7
  148. synth_ai/cli/root.py +0 -97
  149. synth_ai/cli/task_apps.py +1707 -186
  150. synth_ai/demos/demo_task_apps/crafter/grpo_crafter_task_app.py +28 -16
  151. synth_ai/environments/examples/enron/engine.py +7 -2
  152. synth_ai/environments/examples/enron/environment.py +68 -0
  153. synth_ai/environments/examples/red/engine.py +27 -0
  154. synth_ai/environments/examples/red/engine_helpers/memory_map.py +7 -0
  155. synth_ai/environments/examples/red/engine_helpers/reward_library/pallet_town_progression.py +477 -0
  156. synth_ai/environments/examples/red/engine_helpers/state_extraction.py +32 -0
  157. synth_ai/environments/examples/red/environment.py +60 -0
  158. synth_ai/environments/examples/sokoban/taskset.py +116 -0
  159. synth_ai/environments/examples/verilog/engine.py +30 -4
  160. synth_ai/evals/client.py +58 -61
  161. synth_ai/jobs/client.py +16 -4
  162. synth_ai/judge_schemas.py +16 -16
  163. synth_ai/py.typed +0 -0
  164. synth_ai/task/__init__.py +14 -5
  165. synth_ai/task/contracts.py +124 -38
  166. synth_ai/task/proxy.py +48 -56
  167. synth_ai/task/rubrics/__init__.py +53 -0
  168. synth_ai/task/rubrics/loaders.py +133 -0
  169. synth_ai/task/rubrics/models.py +57 -0
  170. synth_ai/task/rubrics/scoring.py +113 -0
  171. synth_ai/{rubrics/validators.py → task/rubrics/strict.py} +53 -30
  172. synth_ai/task/server.py +8 -7
  173. synth_ai/task/validators.py +269 -6
  174. synth_ai/tracing_v3/decorators.py +7 -3
  175. synth_ai/tracing_v3/replica_sync.py +4 -4
  176. synth_ai/tracing_v3/serialization.py +5 -5
  177. synth_ai/tracing_v3/trace_utils.py +317 -0
  178. synth_ai/tracing_v3/turso/native_manager.py +3 -3
  179. {synth_ai-0.2.13.dev1.dist-info → synth_ai-0.2.13.dev2.dist-info}/METADATA +4 -1
  180. {synth_ai-0.2.13.dev1.dist-info → synth_ai-0.2.13.dev2.dist-info}/RECORD +214 -101
  181. examples/agora_ex/README_MoE.md +0 -224
  182. examples/agora_ex/__init__.py +0 -7
  183. examples/agora_ex/agora_ex.py +0 -65
  184. examples/agora_ex/agora_ex_task_app.py +0 -590
  185. examples/agora_ex/configs/rl_lora_qwen3_moe_2xh200.toml +0 -121
  186. examples/agora_ex/reward_fn_grpo-human.py +0 -129
  187. examples/agora_ex/system_prompt_CURRENT.md +0 -63
  188. examples/agora_ex/task_app/agora_ex_task_app.py +0 -590
  189. examples/agora_ex/task_app/reward_fn_grpo-human.py +0 -129
  190. examples/agora_ex/task_app/system_prompt_CURRENT.md +0 -63
  191. synth_ai/rubrics/__init__.py +0 -22
  192. synth_ai/task/rubrics.py +0 -219
  193. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/README.md +0 -0
  194. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/README.md +0 -0
  195. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/__init__.py +0 -0
  196. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/branching.py +0 -0
  197. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/environment_routes.py +0 -0
  198. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/__init__.py +0 -0
  199. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/__init__.py +0 -0
  200. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/app.py +0 -0
  201. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/environment.py +0 -0
  202. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/react_agent.py +0 -0
  203. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/shared.py +0 -0
  204. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/tools.py +0 -0
  205. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/hosted_app.py +0 -0
  206. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/inference/__init__.py +0 -0
  207. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/inference/openai_client.py +0 -0
  208. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/main.py +0 -0
  209. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/registry.py +0 -0
  210. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/storage/__init__.py +0 -0
  211. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/storage/volume.py +0 -0
  212. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/test_agents.py +0 -0
  213. /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/utils.py +0 -0
  214. /examples/{rl/task_app → task_apps/math}/README.md +0 -0
  215. /examples/{rl/task_app → task_apps/math}/math_task_app.py +0 -0
  216. /examples/{rl → workflows/math_rl}/configs/eval_base_qwen.toml +0 -0
  217. /examples/{rl → workflows/math_rl}/configs/eval_rl_qwen.toml +0 -0
  218. /examples/{rl → workflows/math_rl}/configs/rl_from_base_qwen.toml +0 -0
  219. /examples/{rl → workflows/math_rl}/configs/rl_from_base_qwen17.toml +0 -0
  220. /examples/{rl → workflows/math_rl}/configs/rl_from_ft_qwen.toml +0 -0
  221. /examples/{rl → workflows/math_rl}/run_eval.py +0 -0
  222. /examples/{rl → workflows/math_rl}/run_rl_and_save.py +0 -0
  223. {synth_ai-0.2.13.dev1.dist-info → synth_ai-0.2.13.dev2.dist-info}/WHEEL +0 -0
  224. {synth_ai-0.2.13.dev1.dist-info → synth_ai-0.2.13.dev2.dist-info}/entry_points.txt +0 -0
  225. {synth_ai-0.2.13.dev1.dist-info → synth_ai-0.2.13.dev2.dist-info}/licenses/LICENSE +0 -0
  226. {synth_ai-0.2.13.dev1.dist-info → synth_ai-0.2.13.dev2.dist-info}/top_level.txt +0 -0
@@ -0,0 +1,114 @@
1
+ """Modal deployment helper for the Pokémon Emerald speedrun task app example.
2
+
3
+ This reproduces the manual setup described in the README:
4
+
5
+ - Clone `pokeagent-speedrun` and install its Python (and mGBA) dependencies.
6
+ - Mount the Synth AI repository so the task app can be imported directly.
7
+ - Mount a Modal volume that stores the ROM and savestates used by the environment.
8
+
9
+ Deploy with:
10
+
11
+ ```
12
+ modal deploy examples/task_apps/pokemon_emerald/modal_app.py
13
+ ```
14
+
15
+ Before deploying, upload `emerald.gba` and any required savestate files to the
16
+ `pokemon-emerald-assets` volume (see the README for `modal volume put` examples).
17
+ """
18
+
19
+ from __future__ import annotations
20
+
21
+ import subprocess
22
+ import sys
23
+ from pathlib import Path
24
+
25
+ import modal
26
+
27
+ REPO_ROOT = Path(__file__).resolve().parents[3]
28
+ POKEAGENT_SPEEDRUN_REPO = "https://github.com/sethkarten/pokeagent-speedrun.git"
29
+
30
+ app = modal.App("pokemon-emerald-task-app-example")
31
+
32
+ BASE_IMAGE = (
33
+ modal.Image.debian_slim(python_version="3.11")
34
+ .apt_install(
35
+ "git",
36
+ "cmake",
37
+ "ninja-build",
38
+ "build-essential",
39
+ "pkg-config",
40
+ "libpng-dev",
41
+ "libzip-dev",
42
+ "libepoxy-dev",
43
+ "libavcodec-dev",
44
+ "libavformat-dev",
45
+ "libavutil-dev",
46
+ "libswscale-dev",
47
+ "zlib1g-dev",
48
+ "libgles2-mesa-dev",
49
+ "libegl1-mesa-dev",
50
+ )
51
+ .pip_install(["uvicorn[standard]", "fastapi", "httpx", "horizons-ai"])
52
+ .run_commands(
53
+ [
54
+ "mkdir -p /external",
55
+ f"if [ ! -d /external/pokeagent-speedrun ]; then git clone --depth 1 {POKEAGENT_SPEEDRUN_REPO} /external/pokeagent-speedrun; fi",
56
+ "pip install --no-cache-dir -r /external/pokeagent-speedrun/requirements.txt",
57
+ ]
58
+ )
59
+ )
60
+
61
+ REPO_MOUNT = modal.Mount.from_local_dir(REPO_ROOT, remote_path="/workspace/synth-ai")
62
+ ASSET_VOLUME = modal.Volume.from_name("pokemon-emerald-assets", create_if_missing=True)
63
+
64
+
65
+ @app.function(
66
+ image=BASE_IMAGE,
67
+ mounts=[REPO_MOUNT],
68
+ volumes={"/assets": ASSET_VOLUME},
69
+ timeout=900,
70
+ memory=9216,
71
+ cpu=4.0,
72
+ secrets=[modal.Secret.from_name("environment-api-key")],
73
+ keep_warm=1,
74
+ )
75
+ @modal.asgi_app()
76
+ def fastapi_app():
77
+ """Serve the Synth task app via Modal."""
78
+
79
+ import os
80
+
81
+ repo_path = Path("/workspace/synth-ai").resolve()
82
+ if str(repo_path) not in sys.path:
83
+ sys.path.insert(0, str(repo_path))
84
+
85
+ marker = Path("/tmp/.synth_ai_editable")
86
+ if not marker.exists():
87
+ subprocess.check_call([sys.executable, "-m", "pip", "install", "-e", str(repo_path)])
88
+ marker.touch()
89
+
90
+ os.environ.setdefault("POKEAGENT_SPEEDRUN_ROOT", "/external/pokeagent-speedrun")
91
+ os.environ.setdefault("POKEMON_EMERALD_ASSETS", "/assets")
92
+
93
+ rom_path = Path(os.getenv("POKEMON_EMERALD_ROM", "/assets/emerald.gba"))
94
+ if not rom_path.exists():
95
+ raise RuntimeError(
96
+ f"Missing ROM at {rom_path}. Upload it with "
97
+ "\"modal volume put pokemon-emerald-assets emerald.gba\" before deployment."
98
+ )
99
+
100
+ from examples.task_apps.pokemon_emerald.task_app.pokemon_emerald import build_config
101
+ from synth_ai.task.server import create_task_app
102
+
103
+ return create_task_app(build_config())
104
+
105
+
106
+ @app.local_entrypoint()
107
+ def main():
108
+ """Print usage hints for local operators."""
109
+
110
+ print("Pokémon Emerald task app Modal helper")
111
+ print("Upload assets: modal volume put pokemon-emerald-assets /path/to/emerald.gba")
112
+ print("Optional savestates can also be uploaded to the same volume.")
113
+ print("Deploy with: modal deploy examples/task_apps/pokemon_emerald/modal_app.py")
114
+ print("Test locally: modal serve examples/task_apps/pokemon_emerald/modal_app.py")
@@ -0,0 +1,81 @@
1
+ # Pokemon Emerald Task App
2
+
3
+ This directory contains a task app for the PokéAgent Track 2 speedrunning
4
+ environment. It wraps the `pokeagent-speedrun` mGBA integration in the Horizons
5
+ environment API so agents trained with Synth AI can reset, step, snapshot, and
6
+ restore deterministically.
7
+
8
+ ## Local setup (Track 2)
9
+
10
+ 1. Clone and install the **pokeagent-speedrun** project (brings in the mGBA
11
+ Python bindings and emulator helpers). A snapshot of the repository is
12
+ vendored under `examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun`,
13
+ but you can also clone a separate working copy if you prefer to track upstream:
14
+
15
+ ```bash
16
+ git clone https://github.com/sethkarten/pokeagent-speedrun.git
17
+ cd pokeagent-speedrun
18
+ pip install -r requirements.txt
19
+ ```
20
+
21
+ Installing `mgba==0.10.2` may require system packages such as `cmake`,
22
+ `ninja-build`, `pkg-config`, `libpng-dev`, `libzip-dev`, and the FFmpeg
23
+ libraries listed in the repo README.
24
+
25
+ 2. Provide a legal copy of the Pokémon Emerald ROM and any savestate
26
+ checkpoints you wish to use. Place them in a known directory.
27
+
28
+ 3. Export environment variables so the task app can locate both the repository
29
+ and the assets:
30
+
31
+ ```bash
32
+ export POKEAGENT_SPEEDRUN_ROOT=/path/to/pokeagent-speedrun # or the vendored path under examples/task_apps/dev/pokemon_emerald/external
33
+ export POKEMON_EMERALD_ROM=/path/to/emerald.gba
34
+ ```
35
+
36
+ 4. Run a rollout to validate the wiring:
37
+
38
+ ```bash
39
+ uv run python -m synth_ai.task.describe pokemon_emerald
40
+ uv run python -m synth_ai.task.rollout pokemon_emerald --seed 4001
41
+ ```
42
+
43
+ ## Modal deployment
44
+
45
+ `examples/task_apps/pokemon_emerald/modal_app.py` packages the same workflow for
46
+ Modal. It clones `pokeagent-speedrun`, installs dependencies (including mGBA),
47
+ and mounts a persistent volume (`pokemon-emerald-assets`) where you can upload
48
+ the ROM and savestates:
49
+
50
+ ```bash
51
+ modal volume put pokemon-emerald-assets /path/to/emerald.gba
52
+ modal deploy examples/task_apps/pokemon_emerald/modal_app.py
53
+ ```
54
+
55
+ After deployment, point Synth AI workflows at the issued `modal.run` URL.
56
+
57
+ ## Notes (Not Yet Ready)
58
+
59
+ - The adapter currently requires manual mgba installation (`mgba==0.10.2`),
60
+ which is not automated for Apple Silicon—treat this example as
61
+ **experimental** until we land a turnkey build recipe.
62
+ - Dataset entries report savestate availability, but some scenarios may still
63
+ lack assets locally; `/info` will surface this.
64
+ - Snapshot/restore wiring is complete, yet we have not validated
65
+ deterministic parity across platforms pending a reliable mgba install flow.
66
+ - Actions are exposed as macro buttons; further tuning is needed once the
67
+ runtime environment is stable.
68
+
69
+ ## Status & Next Steps
70
+
71
+ - **Environment readiness (blocker)**: provide a reproducible mgba installation
72
+ path (possibly via prebaked wheels or containerized build) before relying on
73
+ this adapter.
74
+ - **Visual observations**: once runtime is reliable, keep the base64 PNG output
75
+ and validate frame fidelity across platforms.
76
+ - **Macro tuning**: calibrate macro durations and add higher-level navigation
77
+ macros.
78
+ - **Reward shaping**: extend badge/location bonuses with richer event hooks.
79
+ - **Stability checks**: add regression tests for snapshot/restore determinism.
80
+ - **Agent integration**: publish rollout scripts after environment setup is
81
+ automated.
@@ -0,0 +1,6 @@
1
+ """Pokemon Emerald task app configuration."""
2
+
3
+ from .pokemon_emerald import build_config
4
+
5
+ __all__ = ["build_config"]
6
+