synth-ai 0.2.8.dev4__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.
Files changed (889) hide show
  1. examples/README.md +1 -0
  2. examples/__init__.py +16 -0
  3. examples/analyze_semantic_words.sh +17 -0
  4. examples/baseline/banking77_baseline.py +243 -0
  5. examples/baseline/banking77_pipeline_baseline.py +294 -0
  6. examples/baseline/crafter_baseline.py +407 -0
  7. examples/baseline/pokemon_red_baseline.py +326 -0
  8. examples/baseline/simple_baseline.py +56 -0
  9. examples/baseline/warming_up_to_rl_baseline.py +239 -0
  10. examples/blog_posts/gepa/README.md +355 -0
  11. examples/blog_posts/gepa/configs/banking77_gepa_local.toml +95 -0
  12. examples/blog_posts/gepa/configs/banking77_gepa_test.toml +80 -0
  13. examples/blog_posts/gepa/configs/banking77_mipro_local.toml +50 -0
  14. examples/blog_posts/gepa/configs/banking77_pipeline_gepa_local.toml +101 -0
  15. examples/blog_posts/gepa/configs/banking77_pipeline_gepa_test.toml +96 -0
  16. examples/blog_posts/gepa/configs/hotpotqa_gepa_local.toml +57 -0
  17. examples/blog_posts/gepa/configs/hotpotqa_gepa_qwen.toml +35 -0
  18. examples/blog_posts/gepa/configs/hotpotqa_mipro_local.toml +51 -0
  19. examples/blog_posts/gepa/configs/hover_gepa_local.toml +57 -0
  20. examples/blog_posts/gepa/configs/hover_gepa_qwen.toml +35 -0
  21. examples/blog_posts/gepa/configs/hover_mipro_local.toml +51 -0
  22. examples/blog_posts/gepa/configs/ifbench_gepa_local.toml +57 -0
  23. examples/blog_posts/gepa/configs/ifbench_gepa_qwen.toml +35 -0
  24. examples/blog_posts/gepa/configs/ifbench_mipro_local.toml +51 -0
  25. examples/blog_posts/gepa/configs/pupa_gepa_local.toml +58 -0
  26. examples/blog_posts/gepa/configs/pupa_mipro_local.toml +52 -0
  27. examples/blog_posts/gepa/deploy_banking77_task_app.sh +54 -0
  28. examples/blog_posts/gepa/gepa_baseline.py +204 -0
  29. examples/blog_posts/gepa/query_prompts_example.py +97 -0
  30. examples/blog_posts/gepa/run_gepa_banking77.sh +112 -0
  31. examples/blog_posts/gepa/run_gepa_banking77_pipeline.sh +163 -0
  32. examples/blog_posts/gepa/task_apps.py +105 -0
  33. examples/blog_posts/gepa/test_gepa_local.sh +67 -0
  34. examples/blog_posts/gepa/verify_banking77_setup.sh +123 -0
  35. examples/blog_posts/mipro/README.md +415 -0
  36. examples/blog_posts/mipro/configs/banking77_mipro_local.toml +91 -0
  37. examples/blog_posts/mipro/configs/banking77_mipro_test.toml +87 -0
  38. examples/blog_posts/mipro/configs/banking77_pipeline_mipro_gemini_flash_lite_local.toml +98 -0
  39. examples/blog_posts/mipro/configs/banking77_pipeline_mipro_gpt41mini_local.toml +96 -0
  40. examples/blog_posts/mipro/configs/banking77_pipeline_mipro_local.toml +94 -0
  41. examples/blog_posts/mipro/configs/banking77_pipeline_mipro_test.toml +170 -0
  42. examples/blog_posts/mipro/deploy_banking77_pipeline_task_app.sh +59 -0
  43. examples/blog_posts/mipro/deploy_banking77_task_app.sh +41 -0
  44. examples/blog_posts/mipro/multi_step.md +79 -0
  45. examples/blog_posts/mipro/run_mipro_banking77.sh +191 -0
  46. examples/blog_posts/mipro/run_mipro_banking77_pipeline.sh +171 -0
  47. examples/blog_posts/mipro/run_mipro_banking77_pipeline_gemini_flash_lite.sh +177 -0
  48. examples/blog_posts/mipro/run_mipro_banking77_pipeline_gpt41mini.sh +173 -0
  49. examples/blog_posts/mipro/verify_banking77_setup.sh +117 -0
  50. examples/blog_posts/pokemon_vl/README.md +98 -0
  51. examples/blog_posts/pokemon_vl/configs/eval_gpt5nano.toml +26 -0
  52. examples/blog_posts/pokemon_vl/configs/eval_qwen3_vl.toml +27 -0
  53. examples/blog_posts/pokemon_vl/configs/eval_rl_final.toml +24 -0
  54. examples/blog_posts/pokemon_vl/configs/filter_high_reward.toml +10 -0
  55. examples/blog_posts/pokemon_vl/configs/train_rl_from_sft.toml +43 -0
  56. examples/blog_posts/pokemon_vl/configs/train_sft_qwen4b_vl.toml +40 -0
  57. examples/blog_posts/pokemon_vl/extract_images.py +239 -0
  58. examples/blog_posts/pokemon_vl/pokemon_vl_baseline.py +326 -0
  59. examples/blog_posts/pokemon_vl/run_eval_extract_images.py +209 -0
  60. examples/blog_posts/pokemon_vl/run_qwen_eval_extract_images.py +212 -0
  61. examples/blog_posts/pokemon_vl/text_box_analysis.md +106 -0
  62. examples/blog_posts/warming_up_to_rl/ARCHITECTURE.md +195 -0
  63. examples/blog_posts/warming_up_to_rl/FINAL_TEST_RESULTS.md +127 -0
  64. examples/blog_posts/warming_up_to_rl/INFERENCE_SUCCESS.md +132 -0
  65. examples/blog_posts/warming_up_to_rl/README.md +158 -0
  66. examples/blog_posts/warming_up_to_rl/SMOKE_TESTING.md +164 -0
  67. examples/blog_posts/warming_up_to_rl/SMOKE_TEST_COMPLETE.md +253 -0
  68. examples/blog_posts/warming_up_to_rl/configs/eval_baseline_qwen32b_10x20.toml +25 -0
  69. examples/blog_posts/warming_up_to_rl/configs/eval_ft_qwen4b.toml +25 -0
  70. examples/blog_posts/warming_up_to_rl/configs/eval_ft_qwen4b_10x20.toml +26 -0
  71. examples/blog_posts/warming_up_to_rl/configs/eval_groq_qwen32b.toml +25 -0
  72. examples/blog_posts/warming_up_to_rl/configs/eval_openai_gpt_oss_120b.toml +29 -0
  73. examples/blog_posts/warming_up_to_rl/configs/filter_high_reward_dataset.toml +10 -0
  74. examples/blog_posts/warming_up_to_rl/configs/smoke_test.toml +75 -0
  75. examples/blog_posts/warming_up_to_rl/configs/train_rl_from_sft.toml +91 -0
  76. examples/blog_posts/warming_up_to_rl/configs/train_sft_qwen4b.toml +40 -0
  77. examples/blog_posts/warming_up_to_rl/warming_up_to_rl_baseline.py +187 -0
  78. examples/crafter_debug_render.py +186 -0
  79. examples/dev/qwen3_32b_qlora_4xh100.toml +45 -0
  80. examples/gepa/banking77_pipeline_gepa.toml +96 -0
  81. examples/gepa/multi_stage_gepa_example.toml +84 -0
  82. examples/gepa/run_gepa_banking77_pipeline.sh +157 -0
  83. examples/multi_step/SFT_README.md +147 -0
  84. examples/multi_step/configs/README_verilog_rl.md +77 -0
  85. examples/multi_step/configs/VERILOG_REWARDS.md +103 -0
  86. examples/multi_step/configs/VERILOG_RL_CHECKLIST.md +196 -0
  87. examples/multi_step/configs/crafter_eval_synth_qwen4b.toml +35 -0
  88. examples/multi_step/configs/crafter_eval_text_only_groq_qwen32b.toml +36 -0
  89. examples/multi_step/configs/crafter_rl_outcome.toml +75 -0
  90. examples/multi_step/configs/crafter_rl_stepwise_hosted_judge.toml +145 -0
  91. examples/multi_step/configs/crafter_rl_stepwise_shaped.toml +84 -0
  92. examples/multi_step/configs/crafter_rl_stepwise_simple.toml +79 -0
  93. examples/multi_step/configs/crafter_rl_stepwise_simple_NEW_FORMAT.toml +105 -0
  94. examples/multi_step/configs/crafter_sft_qwen30b_lora.toml +62 -0
  95. examples/multi_step/configs/crafter_synth_backend.md +40 -0
  96. examples/multi_step/configs/verilog_eval_groq_qwen32b.toml +31 -0
  97. examples/multi_step/configs/verilog_eval_synth_qwen8b.toml +33 -0
  98. examples/multi_step/configs/verilog_rl_lora.toml +147 -0
  99. examples/multi_step/convert_traces_to_sft.py +84 -0
  100. examples/multi_step/crafter_rl_lora.md +70 -0
  101. examples/multi_step/judges/crafter_backend_judge.py +220 -0
  102. examples/multi_step/judges/verilog_backend_judge.py +234 -0
  103. examples/multi_step/readme.md +48 -0
  104. examples/multi_step/run_sft_qwen30b.sh +45 -0
  105. examples/multi_step/sse_metrics_streaming_notes.md +357 -0
  106. examples/multi_step/task_app_config_notes.md +494 -0
  107. examples/multi_step/verilog_rl_lora.md +218 -0
  108. examples/qwen_coder/README.md +102 -0
  109. examples/qwen_coder/_shared.py +113 -0
  110. examples/qwen_coder/configs/coder_lora_30b.toml +60 -0
  111. examples/qwen_coder/configs/coder_lora_4b.toml +61 -0
  112. examples/qwen_coder/configs/coder_lora_small.toml +57 -0
  113. examples/qwen_coder/generate_dataset.py +98 -0
  114. examples/qwen_coder/infer_ft_smoke.py +65 -0
  115. examples/qwen_coder/infer_prod_proxy.py +73 -0
  116. examples/qwen_coder/infer_via_synth.py +87 -0
  117. examples/qwen_coder/scripts/infer_coder.sh +19 -0
  118. examples/qwen_coder/scripts/train_coder_30b.sh +22 -0
  119. examples/qwen_coder/sft_full_17b.py +103 -0
  120. examples/qwen_coder/sft_lora_30b.py +110 -0
  121. examples/qwen_coder/subset_jsonl.py +39 -0
  122. examples/qwen_coder/todos.md +38 -0
  123. examples/qwen_coder/validate_jsonl.py +60 -0
  124. examples/qwen_vl/BUGS_AND_FIXES.md +232 -0
  125. examples/qwen_vl/IMAGE_VALIDATION_COMPLETE.md +271 -0
  126. examples/qwen_vl/IMAGE_VALIDATION_SUMMARY.md +260 -0
  127. examples/qwen_vl/INFERENCE_SFT_TESTS.md +412 -0
  128. examples/qwen_vl/NEXT_STEPS_2B.md +325 -0
  129. examples/qwen_vl/QUICKSTART.md +327 -0
  130. examples/qwen_vl/QUICKSTART_RL_VISION.md +110 -0
  131. examples/qwen_vl/README.md +152 -0
  132. examples/qwen_vl/RL_VISION_COMPLETE.md +475 -0
  133. examples/qwen_vl/RL_VISION_TESTING.md +333 -0
  134. examples/qwen_vl/SDK_VISION_INTEGRATION.md +328 -0
  135. examples/qwen_vl/SETUP_COMPLETE.md +274 -0
  136. examples/qwen_vl/VISION_TESTS_COMPLETE.md +489 -0
  137. examples/qwen_vl/VLM_PIPELINE_COMPLETE.md +242 -0
  138. examples/qwen_vl/__init__.py +2 -0
  139. examples/qwen_vl/collect_data_via_cli.md +415 -0
  140. examples/qwen_vl/collect_vision_traces.py +368 -0
  141. examples/qwen_vl/configs/crafter_rl_vision_qwen3vl4b.toml +110 -0
  142. examples/qwen_vl/configs/crafter_vlm_sft_example.toml +59 -0
  143. examples/qwen_vl/configs/eval_gpt4o_mini_vision.toml +26 -0
  144. examples/qwen_vl/configs/eval_gpt4o_vision_proper.toml +29 -0
  145. examples/qwen_vl/configs/eval_gpt5nano_vision.toml +26 -0
  146. examples/qwen_vl/configs/eval_qwen3vl_vision.toml +26 -0
  147. examples/qwen_vl/configs/filter_qwen3vl_sft.toml +49 -0
  148. examples/qwen_vl/configs/filter_vision_sft.toml +52 -0
  149. examples/qwen_vl/configs/filter_vision_test.toml +8 -0
  150. examples/qwen_vl/configs/sft_qwen3_vl_2b_test.toml +54 -0
  151. examples/qwen_vl/crafter_gpt5nano_agent.py +308 -0
  152. examples/qwen_vl/crafter_qwen_vl_agent.py +300 -0
  153. examples/qwen_vl/run_vision_comparison.sh +61 -0
  154. examples/qwen_vl/run_vision_sft_pipeline.sh +175 -0
  155. examples/qwen_vl/test_image_validation.py +201 -0
  156. examples/qwen_vl/test_sft_vision_data.py +110 -0
  157. examples/rl/README.md +169 -0
  158. examples/rl/configs/eval_base_qwen.toml +17 -0
  159. examples/rl/configs/eval_rl_qwen.toml +13 -0
  160. examples/rl/configs/rl_from_base_qwen.toml +62 -0
  161. examples/rl/configs/rl_from_base_qwen17.toml +80 -0
  162. examples/rl/configs/rl_from_ft_qwen.toml +37 -0
  163. examples/rl/download_dataset.py +80 -0
  164. examples/rl/run_eval.py +436 -0
  165. examples/rl/run_rl_and_save.py +111 -0
  166. examples/rl/task_app/README.md +21 -0
  167. examples/rl/task_app/math_single_step.py +990 -0
  168. examples/rl/task_app/math_task_app.py +111 -0
  169. examples/run_crafter_demo.sh +10 -0
  170. examples/sdk_prompt_learning_example.py +55 -0
  171. examples/sft/README.md +139 -0
  172. examples/sft/configs/crafter_fft_qwen0p6b.toml +49 -0
  173. examples/sft/configs/crafter_lora_qwen0p6b.toml +49 -0
  174. examples/sft/evaluate.py +117 -0
  175. examples/sft/export_dataset.py +120 -0
  176. examples/sft/generate_traces.py +164 -0
  177. examples/swe/__init__.py +12 -0
  178. examples/swe/task_app/README.md +135 -0
  179. examples/swe/task_app/__init__.py +2 -0
  180. examples/swe/task_app/grpo_swe_mini.py +604 -0
  181. examples/swe/task_app/grpo_swe_mini_task_app.py +124 -0
  182. examples/swe/task_app/hosted/README.md +173 -0
  183. examples/swe/task_app/hosted/__init__.py +5 -0
  184. examples/swe/task_app/hosted/branching.py +143 -0
  185. examples/swe/task_app/hosted/environment_routes.py +1289 -0
  186. examples/swe/task_app/hosted/envs/__init__.py +1 -0
  187. examples/swe/task_app/hosted/envs/crafter/__init__.py +6 -0
  188. examples/swe/task_app/hosted/envs/crafter/app.py +1 -0
  189. examples/swe/task_app/hosted/envs/crafter/environment.py +522 -0
  190. examples/swe/task_app/hosted/envs/crafter/policy.py +478 -0
  191. examples/swe/task_app/hosted/envs/crafter/react_agent.py +108 -0
  192. examples/swe/task_app/hosted/envs/crafter/shared.py +305 -0
  193. examples/swe/task_app/hosted/envs/crafter/tools.py +47 -0
  194. examples/swe/task_app/hosted/envs/mini_swe/__init__.py +8 -0
  195. examples/swe/task_app/hosted/envs/mini_swe/environment.py +1191 -0
  196. examples/swe/task_app/hosted/envs/mini_swe/policy.py +355 -0
  197. examples/swe/task_app/hosted/envs/mini_swe/shared.py +83 -0
  198. examples/swe/task_app/hosted/envs/mini_swe/tools.py +96 -0
  199. examples/swe/task_app/hosted/hosted_app.py +204 -0
  200. examples/swe/task_app/hosted/inference/__init__.py +5 -0
  201. examples/swe/task_app/hosted/inference/openai_client.py +584 -0
  202. examples/swe/task_app/hosted/main.py +100 -0
  203. examples/swe/task_app/hosted/policy_routes.py +1094 -0
  204. examples/swe/task_app/hosted/registry.py +195 -0
  205. examples/swe/task_app/hosted/rollout.py +1905 -0
  206. examples/swe/task_app/hosted/storage/__init__.py +5 -0
  207. examples/swe/task_app/hosted/storage/volume.py +211 -0
  208. examples/swe/task_app/hosted/test_agents.py +161 -0
  209. examples/swe/task_app/hosted/test_service.py +136 -0
  210. examples/swe/task_app/hosted/utils.py +62 -0
  211. examples/swe/task_app/morph_backend.py +178 -0
  212. examples/task_apps/IMAGE_ONLY_EVAL_QUICKSTART.md +258 -0
  213. examples/task_apps/TESTING.md +275 -0
  214. examples/task_apps/banking77/__init__.py +6 -0
  215. examples/task_apps/banking77/banking77_task_app.py +912 -0
  216. examples/task_apps/banking77/deploy_wrapper.py +46 -0
  217. examples/task_apps/banking77_pipeline/__init__.py +6 -0
  218. examples/task_apps/banking77_pipeline/banking77_pipeline_task_app.py +489 -0
  219. examples/task_apps/banking77_pipeline/deploy_wrapper.py +50 -0
  220. examples/task_apps/crafter/CREATE_SFT_DATASET.md +286 -0
  221. examples/task_apps/crafter/EVAL_IMAGE_ONLY_RESULTS.md +152 -0
  222. examples/task_apps/crafter/FILTER_COMMAND_STATUS.md +187 -0
  223. examples/task_apps/crafter/FILTER_COMMAND_SUCCESS.md +281 -0
  224. examples/task_apps/crafter/QUERY_EXAMPLES.md +203 -0
  225. examples/task_apps/crafter/README_IMAGE_ONLY_EVAL.md +316 -0
  226. examples/task_apps/crafter/eval_image_only_gpt4o.toml +28 -0
  227. examples/task_apps/crafter/eval_text_only_groq_llama.toml +36 -0
  228. examples/task_apps/crafter/filter_sft_dataset.toml +16 -0
  229. examples/task_apps/crafter/task_app/README.md +42 -0
  230. examples/task_apps/crafter/task_app/__init__.py +5 -0
  231. examples/task_apps/crafter/task_app/grpo_crafter.py +1055 -0
  232. examples/task_apps/crafter/task_app/grpo_crafter_task_app.py +146 -0
  233. examples/task_apps/crafter/task_app/synth_envs_hosted/README.md +173 -0
  234. examples/task_apps/crafter/task_app/synth_envs_hosted/__init__.py +5 -0
  235. examples/task_apps/crafter/task_app/synth_envs_hosted/branching.py +143 -0
  236. examples/task_apps/crafter/task_app/synth_envs_hosted/environment_routes.py +1226 -0
  237. examples/task_apps/crafter/task_app/synth_envs_hosted/envs/__init__.py +1 -0
  238. examples/task_apps/crafter/task_app/synth_envs_hosted/envs/crafter/__init__.py +6 -0
  239. examples/task_apps/crafter/task_app/synth_envs_hosted/envs/crafter/app.py +1 -0
  240. examples/task_apps/crafter/task_app/synth_envs_hosted/envs/crafter/environment.py +532 -0
  241. examples/task_apps/crafter/task_app/synth_envs_hosted/envs/crafter/policy.py +583 -0
  242. examples/task_apps/crafter/task_app/synth_envs_hosted/envs/crafter/react_agent.py +122 -0
  243. examples/task_apps/crafter/task_app/synth_envs_hosted/envs/crafter/shared.py +305 -0
  244. examples/task_apps/crafter/task_app/synth_envs_hosted/envs/crafter/tools.py +47 -0
  245. examples/task_apps/crafter/task_app/synth_envs_hosted/hosted_app.py +253 -0
  246. examples/task_apps/crafter/task_app/synth_envs_hosted/inference/__init__.py +5 -0
  247. examples/task_apps/crafter/task_app/synth_envs_hosted/inference/openai_client.py +999 -0
  248. examples/task_apps/crafter/task_app/synth_envs_hosted/main.py +100 -0
  249. examples/task_apps/crafter/task_app/synth_envs_hosted/policy_routes.py +1252 -0
  250. examples/task_apps/crafter/task_app/synth_envs_hosted/registry.py +195 -0
  251. examples/task_apps/crafter/task_app/synth_envs_hosted/rollout.py +2233 -0
  252. examples/task_apps/crafter/task_app/synth_envs_hosted/storage/__init__.py +5 -0
  253. examples/task_apps/crafter/task_app/synth_envs_hosted/storage/volume.py +211 -0
  254. examples/task_apps/crafter/task_app/synth_envs_hosted/test_agents.py +161 -0
  255. examples/task_apps/crafter/task_app/synth_envs_hosted/test_service.py +136 -0
  256. examples/task_apps/crafter/task_app/synth_envs_hosted/utils.py +411 -0
  257. examples/task_apps/dev/pokemon_emerald/__init__.py +2 -0
  258. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/README.md +811 -0
  259. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/__init__.py +120 -0
  260. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/action.py +160 -0
  261. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/memory.py +155 -0
  262. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/perception.py +69 -0
  263. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/planning.py +96 -0
  264. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/simple.py +1502 -0
  265. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/system_prompt.py +4 -0
  266. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/grab_map.py +68 -0
  267. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/manual.py +216 -0
  268. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/__init__.py +35 -0
  269. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/emerald_utils.py +631 -0
  270. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/emulator.py +1544 -0
  271. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/enums.py +1428 -0
  272. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/memory_reader.py +4848 -0
  273. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/types.py +41 -0
  274. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/utils.py +298 -0
  275. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pyproject.toml +95 -0
  276. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/run.py +204 -0
  277. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/server/app.py +2152 -0
  278. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/server/client.py +429 -0
  279. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/server/frame_server.py +155 -0
  280. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/README.md +78 -0
  281. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/run_tests.py +122 -0
  282. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_agent_direct.py +76 -0
  283. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_agent_prompts.py +413 -0
  284. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_battle_state_formatting.py +204 -0
  285. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_dialogue_detection.py +133 -0
  286. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_dialogue_detection_comprehensive.py +229 -0
  287. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_direct_agent_emulator.py +300 -0
  288. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_fps_adjustment_pytest.py +205 -0
  289. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_house_to_outside_direct.py +200 -0
  290. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_house_to_outside_transition.py +284 -0
  291. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_map_ground_truth_comparison.py +468 -0
  292. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_memory_map.py +575 -0
  293. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_server_map_validation.py +311 -0
  294. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_torchic_state.py +259 -0
  295. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/anticheat.py +372 -0
  296. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/checkpoint.py +296 -0
  297. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/error_handler.py +275 -0
  298. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/get_local_ip.py +22 -0
  299. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/helpers.py +44 -0
  300. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/llm_logger.py +514 -0
  301. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_formatter.py +415 -0
  302. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_stitcher.py +1763 -0
  303. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_stitcher_singleton.py +33 -0
  304. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_trimmer.py +106 -0
  305. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_visualizer.py +334 -0
  306. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/ocr_dialogue.py +1020 -0
  307. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/recording.py +188 -0
  308. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/state_formatter.py +1481 -0
  309. examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/vlm.py +862 -0
  310. examples/task_apps/dev/pokemon_emerald/modal_app.py +114 -0
  311. examples/task_apps/dev/pokemon_emerald/task_app/README.md +81 -0
  312. examples/task_apps/dev/pokemon_emerald/task_app/__init__.py +6 -0
  313. examples/task_apps/dev/pokemon_emerald/task_app/pokemon_emerald.py +685 -0
  314. examples/task_apps/enron/__init__.py +2 -0
  315. examples/task_apps/enron/eval_groq_qwen32.toml +16 -0
  316. examples/task_apps/enron/filter_sft.toml +5 -0
  317. examples/task_apps/enron/task_app/README.md +14 -0
  318. examples/task_apps/enron/task_app/__init__.py +1 -0
  319. examples/task_apps/enron/task_app/grpo_enron.py +906 -0
  320. examples/task_apps/enron/task_app/grpo_enron_task_app.py +146 -0
  321. examples/task_apps/enron/tests/__init__.py +4 -0
  322. examples/task_apps/enron/tests/conftest.py +115 -0
  323. examples/task_apps/enron/tests/integration/__init__.py +4 -0
  324. examples/task_apps/enron/tests/integration/test_enron_eval.py +179 -0
  325. examples/task_apps/enron/tests/integration/test_enron_rollout.py +135 -0
  326. examples/task_apps/enron/tests/unit/__init__.py +4 -0
  327. examples/task_apps/enron/tests/unit/test_enron_environment.py +126 -0
  328. examples/task_apps/gepa_benchmarks/__init__.py +7 -0
  329. examples/task_apps/gepa_benchmarks/common.py +260 -0
  330. examples/task_apps/gepa_benchmarks/hotpotqa_task_app.py +507 -0
  331. examples/task_apps/gepa_benchmarks/hover_task_app.py +436 -0
  332. examples/task_apps/gepa_benchmarks/ifbench_task_app.py +563 -0
  333. examples/task_apps/gepa_benchmarks/pupa_task_app.py +460 -0
  334. examples/task_apps/math/README.md +21 -0
  335. examples/task_apps/math/math_single_step.py +1000 -0
  336. examples/task_apps/math/math_task_app.py +115 -0
  337. examples/task_apps/pokemon_battle/__init__.py +2 -0
  338. examples/task_apps/pokemon_battle/modal_app.py +104 -0
  339. examples/task_apps/pokemon_battle/task_app/README.md +68 -0
  340. examples/task_apps/pokemon_battle/task_app/__init__.py +6 -0
  341. examples/task_apps/pokemon_battle/task_app/pokemon_showdown.py +932 -0
  342. examples/task_apps/pokemon_red/EVAL_IMAGE_ONLY_COMPLETE.md +283 -0
  343. examples/task_apps/pokemon_red/EVAL_IMAGE_ONLY_STATUS.md +155 -0
  344. examples/task_apps/pokemon_red/README.md +356 -0
  345. examples/task_apps/pokemon_red/README_IMAGE_ONLY_EVAL.md +428 -0
  346. examples/task_apps/pokemon_red/__init__.py +3 -0
  347. examples/task_apps/pokemon_red/eval_image_only_gpt4o.toml +30 -0
  348. examples/task_apps/pokemon_red/eval_pokemon_red_policy.py +224 -0
  349. examples/task_apps/pokemon_red/pallet_town_rl_config.toml +75 -0
  350. examples/task_apps/pokemon_red/task_app.py +1048 -0
  351. examples/task_apps/pokemon_red/test_pallet_town_rewards.py +193 -0
  352. examples/task_apps/sokoban/README.md +306 -0
  353. examples/task_apps/sokoban/__init__.py +3 -0
  354. examples/task_apps/sokoban/eval_groq_qwen32.toml +16 -0
  355. examples/task_apps/sokoban/eval_openai_gpt5.toml +16 -0
  356. examples/task_apps/sokoban/filter_sft.toml +5 -0
  357. examples/task_apps/sokoban/task_app.py +1058 -0
  358. examples/task_apps/sokoban/tests/__init__.py +4 -0
  359. examples/task_apps/sokoban/tests/conftest.py +113 -0
  360. examples/task_apps/sokoban/tests/integration/__init__.py +4 -0
  361. examples/task_apps/sokoban/tests/integration/test_sokoban_eval.py +57 -0
  362. examples/task_apps/sokoban/tests/integration/test_sokoban_rollout.py +198 -0
  363. examples/task_apps/sokoban/tests/unit/__init__.py +4 -0
  364. examples/task_apps/sokoban/tests/unit/test_sokoban_environment.py +114 -0
  365. examples/task_apps/verilog/__init__.py +1 -0
  366. examples/task_apps/verilog/eval_groq_qwen32b.toml +22 -0
  367. examples/task_apps/verilog/filter_sft.toml +5 -0
  368. examples/task_apps/verilog/task_app/README.md +12 -0
  369. examples/task_apps/verilog/task_app/__init__.py +1 -0
  370. examples/task_apps/verilog/task_app/grpo_verilog.py +1166 -0
  371. examples/task_apps/verilog/task_app/grpo_verilog_task_app.py +145 -0
  372. examples/task_apps/verilog/tests/__init__.py +4 -0
  373. examples/task_apps/verilog/tests/conftest.py +115 -0
  374. examples/task_apps/verilog/tests/integration/__init__.py +4 -0
  375. examples/task_apps/verilog/tests/integration/test_verilog_eval.py +181 -0
  376. examples/task_apps/verilog/tests/integration/test_verilog_rollout.py +55 -0
  377. examples/task_apps/verilog/tests/unit/__init__.py +4 -0
  378. examples/task_apps/verilog/tests/unit/test_verilog_scoring.py +118 -0
  379. examples/tunnel_gepa_banking77/README.md +106 -0
  380. examples/tunnel_gepa_banking77/banking77_gepa_tunnel.toml +95 -0
  381. examples/tunnel_gepa_banking77/keep_tunnel_running.py +60 -0
  382. examples/tunnel_gepa_banking77/run_gepa_with_tunnel.sh +226 -0
  383. examples/vlm/PROPOSAL.md +53 -0
  384. examples/vlm/README.md +68 -0
  385. examples/vlm/configs/crafter_vlm_gpt4o.toml +49 -0
  386. examples/vlm/crafter_image_only_agent.py +207 -0
  387. examples/vlm/crafter_openai_vlm_agent.py +275 -0
  388. examples/vlm/filter_image_rows.py +63 -0
  389. examples/vlm/run_crafter_vlm_benchmark.py +316 -0
  390. examples/warming_up_to_rl/_utils.py +92 -0
  391. examples/warming_up_to_rl/analyze_trace_db.py +422 -0
  392. examples/warming_up_to_rl/configs/crafter_fft.toml +53 -0
  393. examples/warming_up_to_rl/configs/crafter_fft_4b.toml +54 -0
  394. examples/warming_up_to_rl/configs/eval_fft_qwen4b.toml +22 -0
  395. examples/warming_up_to_rl/configs/eval_groq_qwen32b.toml +15 -0
  396. examples/warming_up_to_rl/configs/eval_modal_qwen4b.toml +24 -0
  397. examples/warming_up_to_rl/configs/eval_stepwise_complex.toml +35 -0
  398. examples/warming_up_to_rl/configs/eval_stepwise_consistent.toml +26 -0
  399. examples/warming_up_to_rl/configs/eval_stepwise_per_achievement.toml +36 -0
  400. examples/warming_up_to_rl/configs/eval_stepwise_simple.toml +32 -0
  401. examples/warming_up_to_rl/configs/rl_from_base_qwen4b.toml +85 -0
  402. examples/warming_up_to_rl/configs/rl_from_ft.toml +58 -0
  403. examples/warming_up_to_rl/export_trace_sft.py +837 -0
  404. examples/warming_up_to_rl/groq_test.py +97 -0
  405. examples/warming_up_to_rl/manage_secrets.py +131 -0
  406. examples/warming_up_to_rl/old/event_rewards.md +234 -0
  407. examples/warming_up_to_rl/old/notes.md +73 -0
  408. examples/warming_up_to_rl/readme.md +110 -0
  409. examples/warming_up_to_rl/run_eval.py +736 -0
  410. examples/warming_up_to_rl/run_fft_and_save.py +380 -0
  411. examples/warming_up_to_rl/run_local_rollout.py +239 -0
  412. examples/warming_up_to_rl/run_local_rollout_modal.py +248 -0
  413. examples/warming_up_to_rl/run_local_rollout_parallel.py +405 -0
  414. examples/warming_up_to_rl/run_local_rollout_traced.py +477 -0
  415. examples/warming_up_to_rl/run_rl_and_save.py +124 -0
  416. examples/warming_up_to_rl/run_rollout_remote.py +156 -0
  417. examples/warming_up_to_rl/task_app/README.md +42 -0
  418. examples/warming_up_to_rl/task_app/grpo_crafter.py +876 -0
  419. examples/warming_up_to_rl/task_app/grpo_crafter_task_app.py +135 -0
  420. examples/warming_up_to_rl/task_app/synth_envs_hosted/README.md +173 -0
  421. examples/warming_up_to_rl/task_app/synth_envs_hosted/__init__.py +5 -0
  422. examples/warming_up_to_rl/task_app/synth_envs_hosted/branching.py +143 -0
  423. examples/warming_up_to_rl/task_app/synth_envs_hosted/environment_routes.py +1226 -0
  424. examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/__init__.py +1 -0
  425. examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/__init__.py +6 -0
  426. examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/app.py +1 -0
  427. examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/environment.py +522 -0
  428. examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/policy.py +454 -0
  429. examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/react_agent.py +108 -0
  430. examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/shared.py +305 -0
  431. examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/tools.py +47 -0
  432. examples/warming_up_to_rl/task_app/synth_envs_hosted/hosted_app.py +253 -0
  433. examples/warming_up_to_rl/task_app/synth_envs_hosted/inference/__init__.py +5 -0
  434. examples/warming_up_to_rl/task_app/synth_envs_hosted/inference/openai_client.py +729 -0
  435. examples/warming_up_to_rl/task_app/synth_envs_hosted/main.py +100 -0
  436. examples/warming_up_to_rl/task_app/synth_envs_hosted/policy_routes.py +1114 -0
  437. examples/warming_up_to_rl/task_app/synth_envs_hosted/registry.py +195 -0
  438. examples/warming_up_to_rl/task_app/synth_envs_hosted/rollout.py +1891 -0
  439. examples/warming_up_to_rl/task_app/synth_envs_hosted/storage/__init__.py +5 -0
  440. examples/warming_up_to_rl/task_app/synth_envs_hosted/storage/volume.py +211 -0
  441. examples/warming_up_to_rl/task_app/synth_envs_hosted/test_agents.py +161 -0
  442. examples/warming_up_to_rl/task_app/synth_envs_hosted/test_service.py +137 -0
  443. examples/warming_up_to_rl/task_app/synth_envs_hosted/utils.py +129 -0
  444. examples/workflows/math_rl/configs/eval_base_qwen.toml +15 -0
  445. examples/workflows/math_rl/configs/eval_rl_qwen.toml +11 -0
  446. examples/workflows/math_rl/configs/rl_from_base_qwen.toml +62 -0
  447. examples/workflows/math_rl/configs/rl_from_base_qwen17.toml +80 -0
  448. examples/workflows/math_rl/configs/rl_from_ft_qwen.toml +35 -0
  449. examples/workflows/math_rl/download_dataset.py +80 -0
  450. examples/workflows/math_rl/run_eval.py +436 -0
  451. examples/workflows/math_rl/run_rl_and_save.py +111 -0
  452. synth_ai/__init__.py +47 -23
  453. synth_ai/_utils/__init__.py +47 -0
  454. synth_ai/_utils/base_url.py +10 -0
  455. synth_ai/_utils/http.py +10 -0
  456. synth_ai/_utils/prompts.py +10 -0
  457. synth_ai/_utils/task_app_state.py +12 -0
  458. synth_ai/_utils/user_config.py +10 -0
  459. synth_ai/api/models/supported.py +514 -0
  460. synth_ai/api/train/__init__.py +63 -0
  461. synth_ai/api/train/builders.py +473 -0
  462. synth_ai/api/train/cli.py +1185 -0
  463. synth_ai/api/train/config_finder.py +246 -0
  464. synth_ai/api/train/configs/__init__.py +65 -0
  465. synth_ai/api/train/configs/prompt_learning.py +496 -0
  466. synth_ai/api/train/configs/rl.py +188 -0
  467. synth_ai/api/train/configs/sft.py +99 -0
  468. synth_ai/api/train/configs/shared.py +81 -0
  469. synth_ai/api/train/env_resolver.py +352 -0
  470. synth_ai/api/train/pollers.py +91 -0
  471. synth_ai/api/train/prompt_learning.py +425 -0
  472. synth_ai/api/train/sft.py +390 -0
  473. synth_ai/api/train/supported_algos.py +147 -0
  474. synth_ai/api/train/task_app.py +195 -0
  475. synth_ai/api/train/utils.py +244 -0
  476. synth_ai/api/train/validators.py +1117 -0
  477. synth_ai/api/tunnel.py +49 -0
  478. synth_ai/auth/credentials.py +94 -0
  479. synth_ai/baseline/__init__.py +25 -0
  480. synth_ai/baseline/config.py +209 -0
  481. synth_ai/baseline/discovery.py +214 -0
  482. synth_ai/baseline/execution.py +146 -0
  483. synth_ai/cfgs.py +227 -0
  484. synth_ai/cli/__init__.py +90 -45
  485. synth_ai/cli/_modal_wrapper.py +31 -0
  486. synth_ai/cli/_storage.py +20 -0
  487. synth_ai/cli/_typer_patch.py +47 -0
  488. synth_ai/cli/_validate_task_app.py +29 -0
  489. synth_ai/cli/balance.py +16 -4
  490. synth_ai/cli/calc.py +36 -21
  491. synth_ai/cli/claude.py +70 -0
  492. synth_ai/cli/codex.py +267 -0
  493. synth_ai/cli/commands/__init__.py +18 -0
  494. synth_ai/cli/commands/baseline/__init__.py +12 -0
  495. synth_ai/cli/commands/baseline/core.py +637 -0
  496. synth_ai/cli/commands/baseline/list.py +93 -0
  497. synth_ai/cli/commands/demo/__init__.py +6 -0
  498. synth_ai/cli/commands/demo/core.py +163 -0
  499. synth_ai/cli/commands/eval/__init__.py +19 -0
  500. synth_ai/cli/commands/eval/core.py +1112 -0
  501. synth_ai/cli/commands/eval/errors.py +81 -0
  502. synth_ai/cli/commands/eval/validation.py +133 -0
  503. synth_ai/cli/commands/filter/__init__.py +12 -0
  504. synth_ai/cli/commands/filter/core.py +424 -0
  505. synth_ai/cli/commands/filter/errors.py +55 -0
  506. synth_ai/cli/commands/filter/validation.py +77 -0
  507. synth_ai/cli/commands/help/__init__.py +185 -0
  508. synth_ai/cli/commands/help/core.py +72 -0
  509. synth_ai/cli/commands/smoke/__init__.py +7 -0
  510. synth_ai/cli/commands/smoke/core.py +1437 -0
  511. synth_ai/cli/commands/status/__init__.py +66 -0
  512. synth_ai/cli/commands/status/client.py +192 -0
  513. synth_ai/cli/commands/status/config.py +92 -0
  514. synth_ai/cli/commands/status/errors.py +20 -0
  515. synth_ai/cli/commands/status/formatters.py +164 -0
  516. synth_ai/cli/commands/status/subcommands/__init__.py +9 -0
  517. synth_ai/cli/commands/status/subcommands/files.py +79 -0
  518. synth_ai/cli/commands/status/subcommands/jobs.py +334 -0
  519. synth_ai/cli/commands/status/subcommands/models.py +79 -0
  520. synth_ai/cli/commands/status/subcommands/pricing.py +22 -0
  521. synth_ai/cli/commands/status/subcommands/runs.py +81 -0
  522. synth_ai/cli/commands/status/subcommands/session.py +183 -0
  523. synth_ai/cli/commands/status/subcommands/summary.py +47 -0
  524. synth_ai/cli/commands/status/subcommands/usage.py +203 -0
  525. synth_ai/cli/commands/status/utils.py +114 -0
  526. synth_ai/cli/commands/train/__init__.py +53 -0
  527. synth_ai/cli/commands/train/core.py +21 -0
  528. synth_ai/cli/commands/train/errors.py +117 -0
  529. synth_ai/cli/commands/train/judge_schemas.py +200 -0
  530. synth_ai/cli/commands/train/judge_validation.py +305 -0
  531. synth_ai/cli/commands/train/validation.py +386 -0
  532. synth_ai/cli/demo.py +32 -140
  533. synth_ai/cli/deploy.py +233 -0
  534. synth_ai/cli/eval/__init__.py +36 -0
  535. synth_ai/cli/eval/core.py +5 -0
  536. synth_ai/cli/eval/errors.py +31 -0
  537. synth_ai/cli/eval/validation.py +5 -0
  538. synth_ai/cli/filter/__init__.py +28 -0
  539. synth_ai/cli/filter/core.py +5 -0
  540. synth_ai/cli/filter/errors.py +23 -0
  541. synth_ai/cli/filter/validation.py +5 -0
  542. synth_ai/cli/legacy_root_backup.py +28 -22
  543. synth_ai/cli/lib/__init__.py +10 -0
  544. synth_ai/cli/lib/task_app_discovery.py +7 -0
  545. synth_ai/cli/lib/task_app_env.py +518 -0
  546. synth_ai/cli/mcp.py +34 -0
  547. synth_ai/cli/modal_serve/__init__.py +12 -0
  548. synth_ai/cli/modal_serve/core.py +14 -0
  549. synth_ai/cli/modal_serve/errors.py +8 -0
  550. synth_ai/cli/modal_serve/validation.py +11 -0
  551. synth_ai/cli/opencode.py +256 -0
  552. synth_ai/cli/recent.py +13 -7
  553. synth_ai/cli/rl_demo.py +166 -114
  554. synth_ai/cli/root.py +143 -112
  555. synth_ai/cli/serve/__init__.py +12 -0
  556. synth_ai/cli/serve/core.py +14 -0
  557. synth_ai/cli/serve/errors.py +8 -0
  558. synth_ai/cli/serve/validation.py +11 -0
  559. synth_ai/cli/setup.py +49 -0
  560. synth_ai/cli/status.py +7 -125
  561. synth_ai/cli/task_app_deploy.py +7 -0
  562. synth_ai/cli/task_app_list.py +25 -0
  563. synth_ai/cli/task_app_modal_serve.py +11 -0
  564. synth_ai/cli/task_app_serve.py +11 -0
  565. synth_ai/cli/task_apps.py +3134 -0
  566. synth_ai/cli/traces.py +9 -5
  567. synth_ai/cli/train/__init__.py +12 -0
  568. synth_ai/cli/train/core.py +21 -0
  569. synth_ai/cli/train/errors.py +8 -0
  570. synth_ai/cli/train/validation.py +24 -0
  571. synth_ai/cli/train.py +5 -0
  572. synth_ai/cli/turso.py +73 -0
  573. synth_ai/cli/watch.py +13 -18
  574. synth_ai/demos/__init__.py +10 -0
  575. synth_ai/demos/core/__init__.py +28 -1
  576. synth_ai/demos/core/cli.py +745 -416
  577. synth_ai/demos/crafter/__init__.py +1 -0
  578. synth_ai/demos/crafter/crafter_fft_4b.toml +55 -0
  579. synth_ai/demos/crafter/grpo_crafter_task_app.py +185 -0
  580. synth_ai/demos/crafter/rl_from_base_qwen4b.toml +74 -0
  581. synth_ai/demos/demo_registry.py +176 -0
  582. synth_ai/demos/demo_task_apps/__init__.py +7 -1
  583. synth_ai/demos/demo_task_apps/core.py +75 -37
  584. synth_ai/demos/demo_task_apps/crafter/__init__.py +1 -0
  585. synth_ai/demos/demo_task_apps/crafter/configs/crafter_fft_4b.toml +53 -0
  586. synth_ai/demos/demo_task_apps/crafter/configs/rl_from_base_qwen4b.toml +73 -0
  587. synth_ai/demos/demo_task_apps/crafter/grpo_crafter_task_app.py +184 -0
  588. synth_ai/demos/demo_task_apps/math/_common.py +1 -2
  589. synth_ai/demos/demo_task_apps/math/app.py +2 -1
  590. synth_ai/demos/demo_task_apps/math/config.toml +55 -110
  591. synth_ai/demos/demo_task_apps/math/deploy_modal.py +3 -6
  592. synth_ai/demos/demo_task_apps/math/modal_task_app.py +491 -166
  593. synth_ai/demos/demo_task_apps/math/task_app_entry.py +37 -0
  594. synth_ai/demos/math/__init__.py +1 -0
  595. synth_ai/demos/math/_common.py +16 -0
  596. synth_ai/demos/math/app.py +38 -0
  597. synth_ai/demos/math/config.toml +76 -0
  598. synth_ai/demos/math/deploy_modal.py +54 -0
  599. synth_ai/demos/math/modal_task_app.py +703 -0
  600. synth_ai/demos/math/task_app_entry.py +51 -0
  601. synth_ai/environments/environment/core.py +7 -1
  602. synth_ai/environments/examples/bandit/engine.py +12 -5
  603. synth_ai/environments/examples/bandit/environment.py +0 -1
  604. synth_ai/environments/examples/bandit/taskset.py +4 -4
  605. synth_ai/environments/examples/crafter_classic/engine_deterministic_patch.py +7 -4
  606. synth_ai/environments/examples/crafter_classic/engine_serialization_patch_v3.py +9 -5
  607. synth_ai/environments/examples/crafter_classic/environment.py +93 -2
  608. synth_ai/environments/examples/crafter_classic/world_config_patch_simple.py +4 -3
  609. synth_ai/environments/examples/enron/engine.py +7 -2
  610. synth_ai/environments/examples/enron/environment.py +68 -0
  611. synth_ai/environments/examples/red/engine.py +60 -12
  612. synth_ai/environments/examples/red/engine_helpers/memory_map.py +7 -0
  613. synth_ai/environments/examples/red/engine_helpers/reward_components.py +151 -179
  614. synth_ai/environments/examples/red/engine_helpers/reward_library/pallet_town_progression.py +477 -0
  615. synth_ai/environments/examples/red/engine_helpers/state_extraction.py +32 -0
  616. synth_ai/environments/examples/red/environment.py +86 -0
  617. synth_ai/environments/examples/red/trace_hooks_v3.py +168 -0
  618. synth_ai/environments/examples/sokoban/taskset.py +116 -0
  619. synth_ai/environments/examples/verilog/engine.py +104 -12
  620. synth_ai/environments/examples/wordle/environment.py +0 -1
  621. synth_ai/environments/reproducibility/tree.py +5 -6
  622. synth_ai/environments/service/app.py +11 -12
  623. synth_ai/environments/service/core_routes.py +10 -9
  624. synth_ai/environments/stateful/engine.py +1 -1
  625. synth_ai/environments/tasks/core.py +1 -0
  626. synth_ai/environments/tasks/filters.py +5 -6
  627. synth_ai/environments/tasks/utils.py +4 -5
  628. synth_ai/evals/__init__.py +15 -0
  629. synth_ai/evals/base.py +14 -5
  630. synth_ai/evals/client.py +82 -0
  631. synth_ai/evals/types.py +42 -0
  632. synth_ai/http.py +8 -22
  633. synth_ai/http_client.py +45 -12
  634. synth_ai/inference/__init__.py +0 -2
  635. synth_ai/inference/client.py +21 -7
  636. synth_ai/jobs/client.py +129 -80
  637. synth_ai/judge_schemas.py +127 -0
  638. synth_ai/learning/__init__.py +51 -6
  639. synth_ai/learning/algorithms.py +14 -0
  640. synth_ai/learning/client.py +122 -30
  641. synth_ai/learning/config.py +2 -40
  642. synth_ai/learning/constants.py +0 -2
  643. synth_ai/learning/ft_client.py +4 -56
  644. synth_ai/learning/health.py +14 -8
  645. synth_ai/learning/jobs.py +43 -47
  646. synth_ai/learning/prompt_learning_client.py +276 -0
  647. synth_ai/learning/prompt_learning_types.py +185 -0
  648. synth_ai/{rl → learning/rl}/__init__.py +14 -5
  649. synth_ai/learning/rl/client.py +269 -0
  650. synth_ai/learning/rl/config.py +31 -0
  651. synth_ai/{rl → learning/rl}/contracts.py +5 -10
  652. synth_ai/{rl → learning/rl}/env_keys.py +45 -16
  653. synth_ai/learning/rl/secrets.py +13 -0
  654. synth_ai/learning/rl_client.py +2 -253
  655. synth_ai/learning/sft/__init__.py +29 -0
  656. synth_ai/learning/sft/client.py +68 -0
  657. synth_ai/learning/sft/config.py +270 -0
  658. synth_ai/learning/sft/data.py +698 -0
  659. synth_ai/learning/sse.py +25 -26
  660. synth_ai/learning/validators.py +29 -25
  661. synth_ai/mcp/__init__.py +5 -0
  662. synth_ai/mcp/__main__.py +8 -0
  663. synth_ai/mcp/main.py +254 -0
  664. synth_ai/mcp/setup.py +100 -0
  665. synth_ai/modal.py +257 -0
  666. synth_ai/pricing/__init__.py +3 -0
  667. synth_ai/pricing/model_pricing.py +64 -0
  668. synth_ai/session/__init__.py +75 -0
  669. synth_ai/session/client.py +383 -0
  670. synth_ai/session/constants.py +63 -0
  671. synth_ai/session/exceptions.py +105 -0
  672. synth_ai/session/manager.py +139 -0
  673. synth_ai/session/models.py +89 -0
  674. synth_ai/session/query.py +110 -0
  675. synth_ai/spec/__init__.py +46 -0
  676. synth_ai/spec/dataclasses.py +149 -0
  677. synth_ai/spec/loader.py +144 -0
  678. synth_ai/spec/serializer.py +199 -0
  679. synth_ai/spec/validation.py +250 -0
  680. synth_ai/streaming/__init__.py +29 -0
  681. synth_ai/streaming/config.py +94 -0
  682. synth_ai/streaming/handlers.py +589 -0
  683. synth_ai/streaming/streamer.py +320 -0
  684. synth_ai/streaming/types.py +95 -0
  685. synth_ai/task/__init__.py +116 -3
  686. synth_ai/task/apps/__init__.py +132 -0
  687. synth_ai/task/auth.py +165 -0
  688. synth_ai/task/client.py +167 -0
  689. synth_ai/task/config.py +261 -0
  690. synth_ai/task/contracts.py +173 -57
  691. synth_ai/task/datasets.py +108 -0
  692. synth_ai/task/errors.py +50 -0
  693. synth_ai/task/health.py +17 -11
  694. synth_ai/task/inference_api.py +101 -0
  695. synth_ai/task/json.py +111 -0
  696. synth_ai/task/proxy.py +251 -0
  697. synth_ai/task/rubrics/__init__.py +55 -0
  698. synth_ai/task/rubrics/loaders.py +156 -0
  699. synth_ai/task/rubrics/models.py +57 -0
  700. synth_ai/task/rubrics/scoring.py +116 -0
  701. synth_ai/task/rubrics/strict.py +149 -0
  702. synth_ai/task/rubrics.py +219 -0
  703. synth_ai/task/server.py +432 -0
  704. synth_ai/task/trace_correlation_helpers.py +328 -0
  705. synth_ai/task/tracing_utils.py +95 -0
  706. synth_ai/task/validators.py +449 -6
  707. synth_ai/task/vendors.py +59 -0
  708. synth_ai/tracing_v3/__init__.py +4 -0
  709. synth_ai/tracing_v3/abstractions.py +21 -4
  710. synth_ai/tracing_v3/config.py +167 -22
  711. synth_ai/tracing_v3/constants.py +21 -0
  712. synth_ai/tracing_v3/db_config.py +42 -29
  713. synth_ai/tracing_v3/decorators.py +80 -45
  714. synth_ai/tracing_v3/examples/basic_usage.py +15 -9
  715. synth_ai/tracing_v3/hooks.py +6 -4
  716. synth_ai/tracing_v3/llm_call_record_helpers.py +161 -61
  717. synth_ai/tracing_v3/migration_helper.py +1 -2
  718. synth_ai/tracing_v3/replica_sync.py +12 -7
  719. synth_ai/tracing_v3/serialization.py +130 -0
  720. synth_ai/tracing_v3/session_tracer.py +86 -21
  721. synth_ai/tracing_v3/storage/base.py +98 -12
  722. synth_ai/tracing_v3/storage/config.py +63 -16
  723. synth_ai/tracing_v3/storage/factory.py +11 -9
  724. synth_ai/tracing_v3/storage/utils.py +15 -11
  725. synth_ai/tracing_v3/trace_utils.py +317 -0
  726. synth_ai/tracing_v3/turso/__init__.py +8 -21
  727. synth_ai/tracing_v3/turso/daemon.py +123 -15
  728. synth_ai/tracing_v3/turso/models.py +5 -2
  729. synth_ai/tracing_v3/turso/native_manager.py +1293 -0
  730. synth_ai/tracing_v3/utils.py +5 -4
  731. synth_ai/tunnel.py +143 -0
  732. synth_ai/tunnel_deploy.py +278 -0
  733. synth_ai/types.py +8 -0
  734. synth_ai/urls.py +11 -0
  735. synth_ai/utils/__init__.py +166 -0
  736. synth_ai/utils/agents.py +74 -0
  737. synth_ai/utils/apps.py +152 -0
  738. synth_ai/utils/base_url.py +94 -0
  739. synth_ai/utils/bin.py +39 -0
  740. synth_ai/utils/claude.py +36 -0
  741. synth_ai/utils/cli.py +284 -0
  742. synth_ai/utils/config.py +81 -0
  743. synth_ai/utils/env.py +346 -0
  744. synth_ai/utils/errors.py +85 -0
  745. synth_ai/utils/http.py +172 -0
  746. synth_ai/utils/json.py +72 -0
  747. synth_ai/utils/log_filter.py +99 -0
  748. synth_ai/utils/logging.py +198 -0
  749. synth_ai/utils/modal.py +299 -0
  750. synth_ai/utils/paths.py +95 -0
  751. synth_ai/utils/process.py +233 -0
  752. synth_ai/utils/prompts.py +39 -0
  753. synth_ai/utils/sqld.py +122 -0
  754. synth_ai/utils/ssl.py +25 -0
  755. synth_ai/utils/task_app_discovery.py +882 -0
  756. synth_ai/utils/task_app_env.py +186 -0
  757. synth_ai/utils/task_app_state.py +318 -0
  758. synth_ai/utils/tunnel/__init__.py +12 -0
  759. synth_ai/utils/tunnel/config.py +55 -0
  760. synth_ai/utils/user_config.py +137 -0
  761. synth_ai/uvicorn.py +77 -0
  762. synth_ai-0.2.23.dev3.dist-info/METADATA +357 -0
  763. synth_ai-0.2.23.dev3.dist-info/RECORD +983 -0
  764. {synth_ai-0.2.8.dev4.dist-info → synth_ai-0.2.23.dev3.dist-info}/entry_points.txt +0 -1
  765. {synth_ai-0.2.8.dev4.dist-info → synth_ai-0.2.23.dev3.dist-info}/top_level.txt +1 -0
  766. synth_ai/cli/man.py +0 -106
  767. synth_ai/core/experiment.py +0 -15
  768. synth_ai/core/system.py +0 -15
  769. synth_ai/environments/examples/sokoban/units/astar_common.py +0 -95
  770. synth_ai/experimental/synth_oss.py +0 -446
  771. synth_ai/handshake.py +0 -63
  772. synth_ai/install_sqld.sh +0 -40
  773. synth_ai/learning/offline/dpo.py +0 -0
  774. synth_ai/learning/offline/providers.py +0 -7
  775. synth_ai/learning/offline/sft.py +0 -0
  776. synth_ai/learning/offline/shared.py +0 -0
  777. synth_ai/learning/online/grpo.py +0 -0
  778. synth_ai/learning/online/irft.py +0 -0
  779. synth_ai/learning/prompts/banking77_injection_eval.py +0 -168
  780. synth_ai/learning/prompts/gepa.py +0 -0
  781. synth_ai/learning/prompts/hello_world_in_context_injection_ex.py +0 -213
  782. synth_ai/learning/prompts/mipro.py +0 -289
  783. synth_ai/learning/prompts/random_search.py +0 -246
  784. synth_ai/learning/prompts/run_mipro_banking77.py +0 -172
  785. synth_ai/learning/prompts/run_random_search_banking77.py +0 -324
  786. synth_ai/lm/__init__.py +0 -51
  787. synth_ai/lm/caching/constants.py +0 -6
  788. synth_ai/lm/caching/dbs.py +0 -0
  789. synth_ai/lm/caching/ephemeral.py +0 -102
  790. synth_ai/lm/caching/handler.py +0 -137
  791. synth_ai/lm/caching/initialize.py +0 -11
  792. synth_ai/lm/caching/persistent.py +0 -114
  793. synth_ai/lm/config.py +0 -110
  794. synth_ai/lm/constants.py +0 -32
  795. synth_ai/lm/core/__init__.py +0 -8
  796. synth_ai/lm/core/all.py +0 -73
  797. synth_ai/lm/core/exceptions.py +0 -7
  798. synth_ai/lm/core/main.py +0 -319
  799. synth_ai/lm/core/main_v3.py +0 -594
  800. synth_ai/lm/core/synth_models.py +0 -48
  801. synth_ai/lm/core/vendor_clients.py +0 -188
  802. synth_ai/lm/cost/monitor.py +0 -1
  803. synth_ai/lm/cost/statefulness.py +0 -1
  804. synth_ai/lm/injection.py +0 -80
  805. synth_ai/lm/overrides.py +0 -206
  806. synth_ai/lm/provider_support/__init__.py +0 -8
  807. synth_ai/lm/provider_support/anthropic.py +0 -972
  808. synth_ai/lm/provider_support/openai.py +0 -1139
  809. synth_ai/lm/provider_support/suppress_logging.py +0 -31
  810. synth_ai/lm/structured_outputs/handler.py +0 -440
  811. synth_ai/lm/structured_outputs/inject.py +0 -297
  812. synth_ai/lm/structured_outputs/rehabilitate.py +0 -185
  813. synth_ai/lm/tools/__init__.py +0 -3
  814. synth_ai/lm/tools/base.py +0 -172
  815. synth_ai/lm/unified_interface.py +0 -202
  816. synth_ai/lm/vendors/base.py +0 -81
  817. synth_ai/lm/vendors/core/anthropic_api.py +0 -387
  818. synth_ai/lm/vendors/core/gemini_api.py +0 -292
  819. synth_ai/lm/vendors/core/mistral_api.py +0 -322
  820. synth_ai/lm/vendors/core/openai_api.py +0 -225
  821. synth_ai/lm/vendors/core/synth_dev_api.py +0 -0
  822. synth_ai/lm/vendors/local/ollama.py +0 -0
  823. synth_ai/lm/vendors/openai_standard.py +0 -780
  824. synth_ai/lm/vendors/openai_standard_responses.py +0 -256
  825. synth_ai/lm/vendors/retries.py +0 -22
  826. synth_ai/lm/vendors/supported/custom_endpoint.py +0 -417
  827. synth_ai/lm/vendors/supported/deepseek.py +0 -69
  828. synth_ai/lm/vendors/supported/grok.py +0 -75
  829. synth_ai/lm/vendors/supported/groq.py +0 -16
  830. synth_ai/lm/vendors/supported/ollama.py +0 -15
  831. synth_ai/lm/vendors/supported/openrouter.py +0 -74
  832. synth_ai/lm/vendors/supported/together.py +0 -11
  833. synth_ai/lm/vendors/synth_client.py +0 -808
  834. synth_ai/lm/warmup.py +0 -186
  835. synth_ai/rl/secrets.py +0 -19
  836. synth_ai/scripts/verify_rewards.py +0 -100
  837. synth_ai/tracing/__init__.py +0 -30
  838. synth_ai/tracing_v1/__init__.py +0 -33
  839. synth_ai/tracing_v3/turso/manager.py +0 -760
  840. synth_ai/v0/tracing/abstractions.py +0 -224
  841. synth_ai/v0/tracing/base_client.py +0 -91
  842. synth_ai/v0/tracing/client_manager.py +0 -131
  843. synth_ai/v0/tracing/config.py +0 -142
  844. synth_ai/v0/tracing/context.py +0 -146
  845. synth_ai/v0/tracing/decorators.py +0 -682
  846. synth_ai/v0/tracing/events/__init__.py +0 -0
  847. synth_ai/v0/tracing/events/manage.py +0 -147
  848. synth_ai/v0/tracing/events/scope.py +0 -86
  849. synth_ai/v0/tracing/events/store.py +0 -228
  850. synth_ai/v0/tracing/immediate_client.py +0 -151
  851. synth_ai/v0/tracing/local.py +0 -18
  852. synth_ai/v0/tracing/log_client_base.py +0 -73
  853. synth_ai/v0/tracing/retry_queue.py +0 -186
  854. synth_ai/v0/tracing/trackers.py +0 -515
  855. synth_ai/v0/tracing/upload.py +0 -512
  856. synth_ai/v0/tracing/utils.py +0 -9
  857. synth_ai/v0/tracing_v1/__init__.py +0 -16
  858. synth_ai/v0/tracing_v1/abstractions.py +0 -224
  859. synth_ai/v0/tracing_v1/base_client.py +0 -91
  860. synth_ai/v0/tracing_v1/client_manager.py +0 -131
  861. synth_ai/v0/tracing_v1/config.py +0 -142
  862. synth_ai/v0/tracing_v1/context.py +0 -146
  863. synth_ai/v0/tracing_v1/decorators.py +0 -703
  864. synth_ai/v0/tracing_v1/events/__init__.py +0 -0
  865. synth_ai/v0/tracing_v1/events/manage.py +0 -147
  866. synth_ai/v0/tracing_v1/events/scope.py +0 -86
  867. synth_ai/v0/tracing_v1/events/store.py +0 -228
  868. synth_ai/v0/tracing_v1/immediate_client.py +0 -151
  869. synth_ai/v0/tracing_v1/local.py +0 -18
  870. synth_ai/v0/tracing_v1/log_client_base.py +0 -73
  871. synth_ai/v0/tracing_v1/retry_queue.py +0 -186
  872. synth_ai/v0/tracing_v1/trackers.py +0 -515
  873. synth_ai/v0/tracing_v1/upload.py +0 -527
  874. synth_ai/v0/tracing_v1/utils.py +0 -9
  875. synth_ai/zyk/__init__.py +0 -30
  876. synth_ai-0.2.8.dev4.dist-info/METADATA +0 -129
  877. synth_ai-0.2.8.dev4.dist-info/RECORD +0 -420
  878. {synth_ai/lm/caching → examples/task_apps}/__init__.py +0 -0
  879. {synth_ai/lm/cost → examples/task_apps/crafter}/__init__.py +0 -0
  880. {synth_ai/lm/structured_outputs → examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/server}/__init__.py +0 -0
  881. {synth_ai/lm/vendors → examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests}/__init__.py +0 -0
  882. {synth_ai/lm/vendors/core → examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils}/__init__.py +0 -0
  883. {synth_ai/lm/vendors/local → examples/task_apps/math}/__init__.py +0 -0
  884. {synth_ai/lm/vendors/supported → examples/workflows}/__init__.py +0 -0
  885. {synth_ai/v0/tracing → examples/workflows/math_rl}/__init__.py +0 -0
  886. /synth_ai/{compound/cais.py → cli/__main__.py} +0 -0
  887. /synth_ai/{learning/filtering.py → py.typed} +0 -0
  888. {synth_ai-0.2.8.dev4.dist-info → synth_ai-0.2.23.dev3.dist-info}/WHEEL +0 -0
  889. {synth_ai-0.2.8.dev4.dist-info → synth_ai-0.2.23.dev3.dist-info}/licenses/LICENSE +0 -0
@@ -0,0 +1,256 @@
1
+ import subprocess
2
+ from pathlib import Path
3
+ from typing import Any
4
+
5
+ import click
6
+ from synth_ai.types import MODEL_NAMES, ModelName
7
+ from synth_ai.urls import BACKEND_URL_SYNTH_RESEARCH_BASE
8
+ from synth_ai.utils import (
9
+ create_and_write_json,
10
+ get_bin_path,
11
+ install_bin,
12
+ load_json_to_dict,
13
+ resolve_env_var,
14
+ verify_bin,
15
+ write_agents_md,
16
+ get_backend_from_env,
17
+ )
18
+
19
+ CONFIG_PATH = Path.home() / ".config" / "opencode" / "opencode.json"
20
+ AUTH_PATH = Path.home() / ".local" / "share" / "opencode" / "auth.json"
21
+ SYNTH_PROVIDER_ID = "synth"
22
+
23
+ try:
24
+ import tomllib # Python 3.11+
25
+ except ImportError:
26
+ try:
27
+ import tomli as tomllib # type: ignore
28
+ except ImportError:
29
+ tomllib = None # type: ignore
30
+
31
+
32
+ def _load_session_config(config_path: Path | None = None) -> dict[str, Any]:
33
+ """Load session configuration from TOML file.
34
+
35
+ Looks for [session] section with:
36
+ - limit_cost_usd: float (default: 20.0)
37
+ - limit_tokens: int | None
38
+ - limit_gpu_hours: float | None
39
+
40
+ Returns dict with session limits.
41
+ """
42
+ if config_path is None:
43
+ # Look for opencode.toml or synth.toml in current directory
44
+ for name in ["opencode.toml", "synth.toml"]:
45
+ path = Path(name)
46
+ if path.exists():
47
+ config_path = path
48
+ break
49
+
50
+ if config_path is None or not config_path.exists():
51
+ # Default: $20 cost limit
52
+ return {"limit_cost_usd": 20.0}
53
+
54
+ if tomllib is None:
55
+ return {"limit_cost_usd": 20.0}
56
+
57
+ try:
58
+ with config_path.open("rb") as f:
59
+ config = tomllib.load(f)
60
+
61
+ session_config = config.get("session", {})
62
+ result: dict[str, Any] = {}
63
+
64
+ # Default cost limit is $20 if not specified
65
+ result["limit_cost_usd"] = session_config.get("limit_cost_usd", 20.0)
66
+
67
+ if "limit_tokens" in session_config:
68
+ result["limit_tokens"] = session_config["limit_tokens"]
69
+ if "limit_gpu_hours" in session_config:
70
+ result["limit_gpu_hours"] = session_config["limit_gpu_hours"]
71
+
72
+ return result
73
+ except Exception as e:
74
+ click.echo(f"Warning: Failed to load session config from {config_path}: {e}", err=True)
75
+ return {"limit_cost_usd": 20.0}
76
+
77
+
78
+ @click.command("opencode")
79
+ @click.option(
80
+ "--model",
81
+ "model_name",
82
+ type=str,
83
+ default=None
84
+ )
85
+ @click.option(
86
+ "--force",
87
+ is_flag=True,
88
+ help="Prompt for API keys even if cached values exist."
89
+ )
90
+ @click.option(
91
+ "--url",
92
+ "override_url",
93
+ type=str,
94
+ default=None,
95
+ )
96
+ @click.option(
97
+ "--config",
98
+ "config_path",
99
+ type=click.Path(exists=True, path_type=Path),
100
+ default=None,
101
+ help="Path to TOML config file (default: opencode.toml or synth.toml in current directory)"
102
+ )
103
+ def opencode_cmd(
104
+ model_name: ModelName | None = None,
105
+ force: bool = False,
106
+ override_url: str | None = None,
107
+ config_path: Path | None = None,
108
+ ) -> None:
109
+
110
+ while True:
111
+ bin_path = get_bin_path("opencode")
112
+ if bin_path:
113
+ break
114
+ if not install_bin(
115
+ "OpenCode",
116
+ [
117
+ "brew install opencode",
118
+ "bun add -g opencode-ai",
119
+ "curl -fsSL https://opencode.ai/install | bash",
120
+ "npm i -g opencode-ai",
121
+ "paru -S opencode"
122
+ ]
123
+ ):
124
+ print("Failed to find your installed OpenCode")
125
+ print("Please install from: https://opencode.ai")
126
+ return
127
+ print(f"Using OpenCode at {bin_path}")
128
+
129
+ if not verify_bin(bin_path):
130
+ print("Failed to verify OpenCode is runnable")
131
+ return
132
+
133
+ write_agents_md()
134
+
135
+ # Load session config from TOML
136
+ session_config = _load_session_config(config_path)
137
+ session_limit_cost = session_config.get("limit_cost_usd")
138
+ session_limit_tokens = session_config.get("limit_tokens")
139
+ session_limit_gpu_hours = session_config.get("limit_gpu_hours")
140
+
141
+ # Get API key and base URL for session creation
142
+ synth_api_key = resolve_env_var("SYNTH_API_KEY", override_process_env=force)
143
+ if override_url:
144
+ base_url = override_url.rstrip("/")
145
+ if base_url.endswith("/api"):
146
+ base_url = base_url[:-4]
147
+ else:
148
+ base_url, _ = get_backend_from_env()
149
+
150
+ # Create agent session with limits from config (default: $20 cost limit)
151
+ session_id: str | None = None
152
+ if session_limit_tokens or session_limit_cost or session_limit_gpu_hours:
153
+ try:
154
+ import asyncio
155
+
156
+ # Create session - org_id will be fetched from backend /me endpoint
157
+ async def create_session():
158
+ from synth_ai.session import AgentSessionClient
159
+
160
+ client = AgentSessionClient(f"{base_url}/api", synth_api_key)
161
+
162
+ limits = []
163
+ if session_limit_tokens:
164
+ limits.append({
165
+ "limit_type": "hard",
166
+ "metric_type": "tokens",
167
+ "limit_value": float(session_limit_tokens),
168
+ })
169
+ if session_limit_cost:
170
+ limits.append({
171
+ "limit_type": "hard",
172
+ "metric_type": "cost_usd",
173
+ "limit_value": float(session_limit_cost),
174
+ })
175
+ if session_limit_gpu_hours:
176
+ limits.append({
177
+ "limit_type": "hard",
178
+ "metric_type": "gpu_hours",
179
+ "limit_value": float(session_limit_gpu_hours),
180
+ })
181
+
182
+ # org_id will be automatically fetched from /api/v1/me endpoint
183
+ session = await client.create(
184
+ org_id=None, # Will be fetched from backend
185
+ limits=limits,
186
+ tracing_session_id=None,
187
+ session_type="opencode_agent",
188
+ )
189
+ return session.session_id
190
+
191
+ session_id = asyncio.run(create_session())
192
+ click.echo(f"✓ Created agent session: {session_id}")
193
+ if session_limit_tokens:
194
+ click.echo(f" Token limit: {session_limit_tokens:,}")
195
+ if session_limit_cost:
196
+ click.echo(f" Cost limit: ${session_limit_cost:.2f}")
197
+ if session_limit_gpu_hours:
198
+ click.echo(f" GPU hours limit: {session_limit_gpu_hours:.2f}")
199
+ except Exception as e:
200
+ click.echo(f"Warning: Failed to create agent session: {e}", err=True)
201
+ click.echo("Continuing without session limits...", err=True)
202
+
203
+ if model_name is not None:
204
+ if model_name not in MODEL_NAMES:
205
+ raise ValueError(
206
+ f"model_name={model_name} is invalid. Valid values for model_name: {MODEL_NAMES}"
207
+ )
208
+ synth_api_key = resolve_env_var("SYNTH_API_KEY", override_process_env=force)
209
+ data = load_json_to_dict(AUTH_PATH)
210
+ good_entry = {
211
+ "type": "api",
212
+ "key": synth_api_key,
213
+ }
214
+ if data.get(SYNTH_PROVIDER_ID) != good_entry:
215
+ data[SYNTH_PROVIDER_ID] = good_entry
216
+ create_and_write_json(AUTH_PATH, data)
217
+ config = load_json_to_dict(CONFIG_PATH)
218
+ config.setdefault("$schema", "https://opencode.ai/config.json")
219
+ if override_url:
220
+ url = override_url
221
+ print("Using override URL:", url)
222
+ else:
223
+ url = BACKEND_URL_SYNTH_RESEARCH_BASE
224
+ provider_section = config.setdefault("provider", {})
225
+ synth_provider = provider_section.setdefault(SYNTH_PROVIDER_ID, {})
226
+ synth_provider["npm"] = "@ai-sdk/openai-compatible"
227
+ synth_provider.setdefault("name", "Synth")
228
+ models = synth_provider.setdefault("models", {})
229
+ models.setdefault(model_name, {})
230
+ options = synth_provider.setdefault("options", {})
231
+ options["baseURL"] = url
232
+ full_model_name = f"{SYNTH_PROVIDER_ID}/{model_name}"
233
+ config["model"] = full_model_name
234
+ create_and_write_json(CONFIG_PATH, config)
235
+
236
+ try:
237
+ subprocess.run([str(bin_path)], check=True)
238
+ except subprocess.CalledProcessError:
239
+ print("Failed to launch OpenCode")
240
+ finally:
241
+ # End session if created
242
+ if session_id is not None:
243
+ try:
244
+ # Assign to local variable to help type checker
245
+ final_session_id: str = session_id
246
+ import asyncio
247
+
248
+ async def end_session():
249
+ from synth_ai.session import AgentSessionClient
250
+ client = AgentSessionClient(f"{base_url}/api", synth_api_key)
251
+ await client.end(final_session_id)
252
+ click.echo(f"✓ Ended agent session: {final_session_id}")
253
+
254
+ asyncio.run(end_session())
255
+ except Exception as e:
256
+ click.echo(f"Warning: Failed to end agent session: {e}", err=True)
synth_ai/cli/recent.py CHANGED
@@ -5,40 +5,46 @@ CLI: experiments active in the last K hours with summary stats.
5
5
 
6
6
  import asyncio
7
7
  from datetime import datetime, timedelta
8
+ from typing import TYPE_CHECKING, Any
8
9
 
9
10
  import click
10
11
  from rich import box
11
12
  from rich.console import Console
12
13
  from rich.table import Table
13
14
 
15
+ from ._storage import load_storage
14
16
 
15
- def _fmt_int(v) -> str:
17
+ if TYPE_CHECKING: # pragma: no cover - typing only
18
+ import pandas as pd
19
+ else:
20
+ pd = Any # type: ignore[assignment]
21
+
22
+ def _fmt_int(v: Any) -> str:
16
23
  try:
17
24
  return f"{int(v):,}"
18
25
  except Exception:
19
26
  return "0"
20
27
 
21
28
 
22
- def _fmt_money(v) -> str:
29
+ def _fmt_money(v: Any) -> str:
23
30
  try:
24
31
  return f"${float(v or 0.0):.4f}"
25
32
  except Exception:
26
33
  return "$0.0000"
27
34
 
28
35
 
29
- def _fmt_time(v) -> str:
36
+ def _fmt_time(v: Any) -> str:
30
37
  try:
31
38
  return str(v)
32
39
  except Exception:
33
40
  return "-"
34
41
 
35
42
 
36
- async def _fetch_recent(db_url: str, hours: float):
37
- from synth_ai.tracing_v3.turso.manager import AsyncSQLTraceManager
38
-
43
+ async def _fetch_recent(db_url: str, hours: float) -> "pd.DataFrame":
39
44
  start_time = datetime.now() - timedelta(hours=hours)
40
45
 
41
- db = AsyncSQLTraceManager(db_url)
46
+ create_storage, storage_config = load_storage()
47
+ db: Any = create_storage(storage_config(connection_string=db_url))
42
48
  await db.initialize()
43
49
  try:
44
50
  query = """
synth_ai/cli/rl_demo.py CHANGED
@@ -15,19 +15,31 @@ For convenience, dotted aliases are also exposed:
15
15
 
16
16
  from __future__ import annotations
17
17
 
18
+ import importlib
19
+ from typing import Any, cast
20
+
18
21
  import click
22
+ from click.exceptions import Exit
23
+
24
+ demo_commands = cast(Any, importlib.import_module("synth_ai.demos.core.cli"))
25
+
19
26
 
27
+ def _run_demo_command(func, *args, **kwargs) -> None:
28
+ """Invoke a demo command and exit via Click on non-zero status codes."""
29
+
30
+ try:
31
+ result = func(*args, **kwargs)
32
+ except SystemExit as exc: # pragma: no cover - defensive
33
+ raise Exit(exc.code or 1) from exc
20
34
 
21
- def _forward(args: list[str]) -> None:
22
- import sys
35
+ if result is None:
36
+ return
23
37
  try:
24
- from synth_ai.demos.core import cli as demo_cli # type: ignore
25
- except Exception as e: # pragma: no cover
26
- click.echo(f"Failed to import RL demo CLI: {e}")
27
- sys.exit(1)
28
- rc = int(demo_cli.main(args) or 0)
29
- if rc != 0:
30
- sys.exit(rc)
38
+ code = int(result)
39
+ except (TypeError, ValueError):
40
+ return
41
+ if code != 0:
42
+ raise Exit(code)
31
43
 
32
44
 
33
45
  def register(cli):
@@ -36,167 +48,207 @@ def register(cli):
36
48
  """RL Demo commands (separate from legacy demo)."""
37
49
 
38
50
  # Help pyright understand dynamic Click group attributes
39
- from typing import Any, cast as _cast
40
- _rlg = _cast(Any, rl_demo)
51
+ _rlg = cast(Any, rl_demo)
41
52
 
42
53
  @_rlg.command("setup")
43
54
  def rl_setup():
44
- _forward(["rl_demo.setup"]) # primary setup command
55
+ _run_demo_command(demo_commands.setup)
45
56
 
46
57
  # (prepare command removed; consolidated into configure)
47
58
 
48
59
  @_rlg.command("deploy")
49
60
  @click.option("--local", is_flag=True, help="Run local FastAPI instead of Modal deploy")
50
- @click.option("--app", type=click.Path(), default=None, help="Path to Modal app.py for uv run modal deploy")
61
+ @click.option(
62
+ "--app",
63
+ type=click.Path(),
64
+ default=None,
65
+ help="Path to Modal app.py for uv run modal deploy",
66
+ )
51
67
  @click.option("--name", type=str, default="synth-math-demo", help="Modal app name")
52
- @click.option("--script", type=click.Path(), default=None, help="Path to deploy_task_app.sh (optional legacy)")
68
+ @click.option(
69
+ "--script",
70
+ type=click.Path(),
71
+ default=None,
72
+ help="Path to deploy_task_app.sh (optional legacy)",
73
+ )
53
74
  def rl_deploy(local: bool, app: str | None, name: str, script: str | None):
54
- args: list[str] = ["rl_demo.deploy"]
55
- if local:
56
- args.append("--local")
57
- if app:
58
- args.extend(["--app", app])
59
- if name:
60
- args.extend(["--name", name])
61
- if script:
62
- args.extend(["--script", script])
63
- _forward(args)
75
+ _run_demo_command(
76
+ demo_commands.deploy,
77
+ local=local,
78
+ app=app,
79
+ name=name,
80
+ script=script,
81
+ )
64
82
 
65
83
  @_rlg.command("configure")
66
84
  def rl_configure():
67
- _forward(["rl_demo.configure"])
85
+ _run_demo_command(demo_commands.run)
68
86
 
69
87
  @_rlg.command("init")
70
- @click.option("--force", is_flag=True, help="Overwrite existing files in CWD")
71
- def rl_init(force: bool):
72
- args = ["rl_demo.init"]
73
- if force:
74
- args.append("--force")
75
- _forward(args)
88
+ @click.option("--template", type=str, default=None, help="Template id to instantiate")
89
+ @click.option("--dest", type=click.Path(), default=None, help="Destination directory for files")
90
+ @click.option("--force", is_flag=True, help="Overwrite existing files in destination")
91
+ def rl_init(template: str | None, dest: str | None, force: bool):
92
+ _run_demo_command(
93
+ demo_commands.init,
94
+ template=template,
95
+ dest=dest,
96
+ force=force,
97
+ )
76
98
 
77
99
  @_rlg.command("run")
78
- @click.option("--config", type=click.Path(), default=None, help="Path to TOML config (skip prompt)")
100
+ @click.option(
101
+ "--config", type=click.Path(), default=None, help="Path to TOML config (skip prompt)"
102
+ )
79
103
  @click.option("--batch-size", type=int, default=None)
80
104
  @click.option("--group-size", type=int, default=None)
81
105
  @click.option("--model", type=str, default=None)
82
106
  @click.option("--timeout", type=int, default=600)
83
107
  @click.option("--dry-run", is_flag=True, help="Print request body and exit")
84
- def rl_run(config: str | None, batch_size: int | None, group_size: int | None, model: str | None, timeout: int, dry_run: bool):
85
- args = ["rl_demo.run"]
86
- if config:
87
- args.extend(["--config", config])
88
- if batch_size is not None:
89
- args.extend(["--batch-size", str(batch_size)])
90
- if group_size is not None:
91
- args.extend(["--group-size", str(group_size)])
92
- if model:
93
- args.extend(["--model", model])
94
- if timeout is not None:
95
- args.extend(["--timeout", str(timeout)])
96
- if dry_run:
97
- args.append("--dry-run")
98
- _forward(args)
108
+ def rl_run(
109
+ config: str | None,
110
+ batch_size: int | None,
111
+ group_size: int | None,
112
+ model: str | None,
113
+ timeout: int,
114
+ dry_run: bool,
115
+ ):
116
+ _run_demo_command(
117
+ demo_commands.run,
118
+ config=config,
119
+ batch_size=batch_size,
120
+ group_size=group_size,
121
+ model=model,
122
+ timeout=timeout,
123
+ dry_run=dry_run,
124
+ )
99
125
 
100
126
  # Dotted aliases (top-level): legacy check → setup
101
127
  @cli.command("rl_demo.check")
102
128
  def rl_check_alias():
103
- _forward(["rl_demo.setup"])
129
+ _run_demo_command(demo_commands.setup)
104
130
 
105
131
  @cli.command("rl_demo.setup")
106
132
  def rl_setup_alias():
107
- _forward(["rl_demo.setup"])
133
+ _run_demo_command(demo_commands.setup)
108
134
 
109
135
  # (prepare alias removed)
110
136
 
111
137
  @cli.command("rl_demo.deploy")
112
138
  @click.option("--local", is_flag=True, help="Run local FastAPI instead of Modal deploy")
113
- @click.option("--app", type=click.Path(), default=None, help="Path to Modal app.py for uv run modal deploy")
139
+ @click.option(
140
+ "--app",
141
+ type=click.Path(),
142
+ default=None,
143
+ help="Path to Modal app.py for uv run modal deploy",
144
+ )
114
145
  @click.option("--name", type=str, default="synth-math-demo", help="Modal app name")
115
- @click.option("--script", type=click.Path(), default=None, help="Path to deploy_task_app.sh (optional legacy)")
146
+ @click.option(
147
+ "--script",
148
+ type=click.Path(),
149
+ default=None,
150
+ help="Path to deploy_task_app.sh (optional legacy)",
151
+ )
116
152
  def rl_deploy_alias(local: bool, app: str | None, name: str, script: str | None):
117
- args: list[str] = ["rl_demo.deploy"]
118
- if local:
119
- args.append("--local")
120
- if app:
121
- args.extend(["--app", app])
122
- if name:
123
- args.extend(["--name", name])
124
- if script:
125
- args.extend(["--script", script])
126
- _forward(args)
153
+ _run_demo_command(
154
+ demo_commands.deploy,
155
+ local=local,
156
+ app=app,
157
+ name=name,
158
+ script=script,
159
+ )
127
160
 
128
161
  @cli.command("rl_demo.configure")
129
162
  def rl_configure_alias():
130
- _forward(["rl_demo.configure"])
163
+ _run_demo_command(demo_commands.run)
131
164
 
132
165
  @cli.command("rl_demo.init")
133
- @click.option("--force", is_flag=True, help="Overwrite existing files in CWD")
134
- def rl_init_alias(force: bool):
135
- args = ["rl_demo.init"]
136
- if force:
137
- args.append("--force")
138
- _forward(args)
166
+ @click.option("--template", type=str, default=None, help="Template id to instantiate")
167
+ @click.option("--dest", type=click.Path(), default=None, help="Destination directory for files")
168
+ @click.option("--force", is_flag=True, help="Overwrite existing files in destination")
169
+ def rl_init_alias(template: str | None, dest: str | None, force: bool):
170
+ _run_demo_command(
171
+ demo_commands.init,
172
+ template=template,
173
+ dest=dest,
174
+ force=force,
175
+ )
139
176
 
140
177
  @cli.command("rl_demo.run")
141
- @click.option("--config", type=click.Path(), default=None, help="Path to TOML config (skip prompt)")
178
+ @click.option(
179
+ "--config", type=click.Path(), default=None, help="Path to TOML config (skip prompt)"
180
+ )
142
181
  @click.option("--batch-size", type=int, default=None)
143
182
  @click.option("--group-size", type=int, default=None)
144
183
  @click.option("--model", type=str, default=None)
145
184
  @click.option("--timeout", type=int, default=600)
146
185
  @click.option("--dry-run", is_flag=True, help="Print request body and exit")
147
- def rl_run_alias(config: str | None, batch_size: int | None, group_size: int | None, model: str | None, timeout: int, dry_run: bool):
148
- args = ["rl_demo.run"]
149
- if config:
150
- args.extend(["--config", config])
151
- if batch_size is not None:
152
- args.extend(["--batch-size", str(batch_size)])
153
- if group_size is not None:
154
- args.extend(["--group-size", str(group_size)])
155
- if model:
156
- args.extend(["--model", model])
157
- if timeout is not None:
158
- args.extend(["--timeout", str(timeout)])
159
- if dry_run:
160
- args.append("--dry-run")
161
- _forward(args)
186
+ def rl_run_alias(
187
+ config: str | None,
188
+ batch_size: int | None,
189
+ group_size: int | None,
190
+ model: str | None,
191
+ timeout: int,
192
+ dry_run: bool,
193
+ ):
194
+ _run_demo_command(
195
+ demo_commands.run,
196
+ config=config,
197
+ batch_size=batch_size,
198
+ group_size=group_size,
199
+ model=model,
200
+ timeout=timeout,
201
+ dry_run=dry_run,
202
+ )
162
203
 
163
204
  # Top-level convenience alias: `synth-ai deploy`
164
- @cli.command("deploy")
205
+ @cli.command("demo-deploy")
165
206
  @click.option("--local", is_flag=True, help="Run local FastAPI instead of Modal deploy")
166
- @click.option("--app", type=click.Path(), default=None, help="Path to Modal app.py for uv run modal deploy")
207
+ @click.option(
208
+ "--app",
209
+ type=click.Path(),
210
+ default=None,
211
+ help="Path to Modal app.py for uv run modal deploy",
212
+ )
167
213
  @click.option("--name", type=str, default="synth-math-demo", help="Modal app name")
168
- @click.option("--script", type=click.Path(), default=None, help="Path to deploy_task_app.sh (optional legacy)")
169
- def deploy_top(local: bool, app: str | None, name: str, script: str | None):
170
- args: list[str] = ["rl_demo.deploy"]
171
- if local:
172
- args.append("--local")
173
- if app:
174
- args.extend(["--app", app])
175
- if name:
176
- args.extend(["--name", name])
177
- if script:
178
- args.extend(["--script", script])
179
- _forward(args)
214
+ @click.option(
215
+ "--script",
216
+ type=click.Path(),
217
+ default=None,
218
+ help="Path to deploy_task_app.sh (optional legacy)",
219
+ )
220
+ def deploy_demo(local: bool, app: str | None, name: str, script: str | None):
221
+ _run_demo_command(
222
+ demo_commands.deploy,
223
+ local=local,
224
+ app=app,
225
+ name=name,
226
+ script=script,
227
+ )
180
228
 
181
229
  @cli.command("run")
182
- @click.option("--config", type=click.Path(), default=None, help="Path to TOML config (skip prompt)")
230
+ @click.option(
231
+ "--config", type=click.Path(), default=None, help="Path to TOML config (skip prompt)"
232
+ )
183
233
  @click.option("--batch-size", type=int, default=None)
184
234
  @click.option("--group-size", type=int, default=None)
185
235
  @click.option("--model", type=str, default=None)
186
236
  @click.option("--timeout", type=int, default=600)
187
237
  @click.option("--dry-run", is_flag=True, help="Print request body and exit")
188
- def run_top(config: str | None, batch_size: int | None, group_size: int | None, model: str | None, timeout: int, dry_run: bool):
189
- args = ["run"]
190
- if config:
191
- args.extend(["--config", config])
192
- if batch_size is not None:
193
- args.extend(["--batch-size", str(batch_size)])
194
- if group_size is not None:
195
- args.extend(["--group-size", str(group_size)])
196
- if model:
197
- args.extend(["--model", model])
198
- if timeout is not None:
199
- args.extend(["--timeout", str(timeout)])
200
- if dry_run:
201
- args.append("--dry-run")
202
- _forward(args)
238
+ def run_top(
239
+ config: str | None,
240
+ batch_size: int | None,
241
+ group_size: int | None,
242
+ model: str | None,
243
+ timeout: int,
244
+ dry_run: bool,
245
+ ):
246
+ _run_demo_command(
247
+ demo_commands.run,
248
+ config=config,
249
+ batch_size=batch_size,
250
+ group_size=group_size,
251
+ model=model,
252
+ timeout=timeout,
253
+ dry_run=dry_run,
254
+ )