synth-ai 0.2.9.dev5__py3-none-any.whl → 0.2.10__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of synth-ai might be problematic. Click here for more details.
- examples/__init__.py +16 -0
- examples/crafter_debug_render.py +23 -17
- examples/dev/qwen3_32b_qlora_4xh100.toml +40 -0
- examples/multi_step/crafter_rl_lora.md +29 -0
- examples/qwen_coder/README.md +102 -0
- examples/qwen_coder/_shared.py +113 -0
- examples/qwen_coder/configs/coder_lora_30b.toml +61 -0
- examples/qwen_coder/configs/coder_lora_4b.toml +57 -0
- examples/qwen_coder/configs/coder_lora_small.toml +58 -0
- examples/qwen_coder/generate_dataset.py +98 -0
- examples/qwen_coder/infer_ft_smoke.py +65 -0
- examples/qwen_coder/infer_prod_proxy.py +73 -0
- examples/qwen_coder/infer_via_synth.py +87 -0
- examples/qwen_coder/scripts/infer_coder.sh +19 -0
- examples/qwen_coder/scripts/train_coder_30b.sh +22 -0
- examples/qwen_coder/sft_full_17b.py +103 -0
- examples/qwen_coder/sft_lora_30b.py +110 -0
- examples/qwen_coder/subset_jsonl.py +39 -0
- examples/qwen_coder/todos.md +38 -0
- examples/qwen_coder/validate_jsonl.py +60 -0
- examples/rl/configs/eval_base_qwen.toml +1 -1
- examples/rl/configs/rl_from_base_qwen17.toml +1 -1
- examples/rl/download_dataset.py +26 -10
- examples/rl/run_eval.py +53 -52
- examples/rl/run_rl_and_save.py +29 -12
- examples/rl/task_app/math_single_step.py +180 -41
- examples/rl/task_app/math_task_app.py +14 -6
- examples/sft/README.md +139 -0
- examples/sft/configs/crafter_fft_qwen0p6b.toml +44 -0
- examples/sft/configs/crafter_lora_qwen0p6b.toml +45 -0
- examples/sft/evaluate.py +117 -0
- examples/sft/export_dataset.py +117 -0
- examples/sft/generate_traces.py +162 -0
- examples/swe/__init__.py +12 -0
- examples/swe/task_app/README.md +105 -0
- examples/swe/task_app/__init__.py +2 -0
- examples/swe/task_app/grpo_swe_mini.py +571 -0
- examples/swe/task_app/grpo_swe_mini_task_app.py +136 -0
- examples/swe/task_app/hosted/README.md +173 -0
- examples/swe/task_app/hosted/__init__.py +5 -0
- examples/swe/task_app/hosted/branching.py +143 -0
- examples/swe/task_app/hosted/environment_routes.py +1289 -0
- examples/swe/task_app/hosted/envs/__init__.py +1 -0
- examples/swe/task_app/hosted/envs/crafter/__init__.py +6 -0
- examples/swe/task_app/hosted/envs/crafter/app.py +1 -0
- examples/swe/task_app/hosted/envs/crafter/environment.py +522 -0
- examples/swe/task_app/hosted/envs/crafter/policy.py +478 -0
- examples/swe/task_app/hosted/envs/crafter/react_agent.py +108 -0
- examples/swe/task_app/hosted/envs/crafter/shared.py +305 -0
- examples/swe/task_app/hosted/envs/crafter/tools.py +47 -0
- examples/swe/task_app/hosted/envs/mini_swe/__init__.py +8 -0
- examples/swe/task_app/hosted/envs/mini_swe/environment.py +1164 -0
- examples/swe/task_app/hosted/envs/mini_swe/policy.py +355 -0
- examples/swe/task_app/hosted/envs/mini_swe/shared.py +83 -0
- examples/swe/task_app/hosted/envs/mini_swe/tools.py +96 -0
- examples/swe/task_app/hosted/hosted_app.py +204 -0
- examples/swe/task_app/hosted/inference/__init__.py +5 -0
- examples/swe/task_app/hosted/inference/openai_client.py +618 -0
- examples/swe/task_app/hosted/main.py +100 -0
- examples/swe/task_app/hosted/policy_routes.py +1079 -0
- examples/swe/task_app/hosted/registry.py +195 -0
- examples/swe/task_app/hosted/rollout.py +1869 -0
- examples/swe/task_app/hosted/storage/__init__.py +5 -0
- examples/swe/task_app/hosted/storage/volume.py +211 -0
- examples/swe/task_app/hosted/test_agents.py +161 -0
- examples/swe/task_app/hosted/test_service.py +137 -0
- examples/swe/task_app/hosted/utils.py +62 -0
- examples/vlm/PROPOSAL.md +53 -0
- examples/vlm/README.md +68 -0
- examples/vlm/configs/crafter_vlm_gpt4o.toml +44 -0
- examples/vlm/crafter_image_only_agent.py +207 -0
- examples/vlm/crafter_openai_vlm_agent.py +277 -0
- examples/vlm/filter_image_rows.py +63 -0
- examples/vlm/run_crafter_vlm_benchmark.py +316 -0
- examples/warming_up_to_rl/analyze_trace_db.py +12 -10
- examples/warming_up_to_rl/configs/rl_from_base_qwen4b.toml +11 -1
- examples/warming_up_to_rl/export_trace_sft.py +218 -36
- examples/warming_up_to_rl/groq_test.py +15 -8
- examples/warming_up_to_rl/manage_secrets.py +29 -25
- examples/warming_up_to_rl/readme.md +9 -2
- examples/warming_up_to_rl/run_eval.py +137 -61
- examples/warming_up_to_rl/run_fft_and_save.py +131 -60
- examples/warming_up_to_rl/run_local_rollout.py +88 -39
- examples/warming_up_to_rl/run_local_rollout_modal.py +114 -28
- examples/warming_up_to_rl/run_local_rollout_parallel.py +81 -20
- examples/warming_up_to_rl/run_local_rollout_traced.py +126 -23
- examples/warming_up_to_rl/run_rl_and_save.py +35 -12
- examples/warming_up_to_rl/run_rollout_remote.py +44 -19
- examples/warming_up_to_rl/task_app/README.md +6 -2
- examples/warming_up_to_rl/task_app/grpo_crafter.py +319 -57
- examples/warming_up_to_rl/task_app/grpo_crafter_task_app.py +11 -30
- examples/warming_up_to_rl/task_app/synth_envs_hosted/__init__.py +1 -1
- examples/warming_up_to_rl/task_app/synth_envs_hosted/branching.py +9 -11
- examples/warming_up_to_rl/task_app/synth_envs_hosted/environment_routes.py +137 -182
- examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/__init__.py +1 -1
- examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/__init__.py +1 -1
- examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/app.py +1 -1
- examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/environment.py +150 -57
- examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/policy.py +105 -69
- examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/react_agent.py +19 -7
- examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/shared.py +45 -42
- examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/tools.py +1 -1
- examples/warming_up_to_rl/task_app/synth_envs_hosted/hosted_app.py +47 -45
- examples/warming_up_to_rl/task_app/synth_envs_hosted/inference/__init__.py +1 -1
- examples/warming_up_to_rl/task_app/synth_envs_hosted/inference/openai_client.py +198 -92
- examples/warming_up_to_rl/task_app/synth_envs_hosted/main.py +0 -2
- examples/warming_up_to_rl/task_app/synth_envs_hosted/policy_routes.py +361 -263
- examples/warming_up_to_rl/task_app/synth_envs_hosted/registry.py +21 -23
- examples/warming_up_to_rl/task_app/synth_envs_hosted/rollout.py +394 -274
- examples/warming_up_to_rl/task_app/synth_envs_hosted/storage/__init__.py +1 -1
- examples/warming_up_to_rl/task_app/synth_envs_hosted/storage/volume.py +56 -62
- examples/warming_up_to_rl/task_app/synth_envs_hosted/test_agents.py +1 -0
- examples/warming_up_to_rl/task_app/synth_envs_hosted/test_service.py +6 -15
- examples/warming_up_to_rl/task_app/synth_envs_hosted/utils.py +4 -3
- synth_ai/__init__.py +1 -0
- synth_ai/api/models/supported.py +376 -0
- synth_ai/api/train/builders.py +157 -26
- synth_ai/api/train/cli.py +213 -57
- synth_ai/api/train/config_finder.py +65 -5
- synth_ai/api/train/env_resolver.py +33 -15
- synth_ai/api/train/pollers.py +13 -4
- synth_ai/api/train/supported_algos.py +139 -0
- synth_ai/api/train/task_app.py +5 -3
- synth_ai/api/train/utils.py +33 -48
- synth_ai/cli/__init__.py +19 -4
- synth_ai/cli/_modal_wrapper.py +28 -0
- synth_ai/cli/_typer_patch.py +49 -0
- synth_ai/cli/balance.py +2 -3
- synth_ai/cli/calc.py +1 -1
- synth_ai/cli/demo.py +21 -6
- synth_ai/cli/recent.py +2 -2
- synth_ai/cli/rl_demo.py +77 -17
- synth_ai/cli/root.py +116 -39
- synth_ai/cli/status.py +2 -2
- synth_ai/cli/task_apps.py +1699 -259
- synth_ai/cli/traces.py +7 -4
- synth_ai/cli/turso.py +73 -0
- synth_ai/cli/watch.py +12 -18
- synth_ai/core/experiment.py +0 -2
- synth_ai/demo_registry.py +68 -31
- synth_ai/demos/core/cli.py +516 -194
- synth_ai/demos/demo_task_apps/__init__.py +3 -3
- synth_ai/demos/demo_task_apps/core.py +64 -28
- synth_ai/demos/demo_task_apps/crafter/configs/crafter_fft_4b.toml +2 -3
- synth_ai/demos/demo_task_apps/crafter/grpo_crafter_task_app.py +37 -30
- synth_ai/demos/demo_task_apps/math/_common.py +1 -2
- synth_ai/demos/demo_task_apps/math/app.py +2 -1
- synth_ai/demos/demo_task_apps/math/deploy_modal.py +3 -6
- synth_ai/demos/demo_task_apps/math/modal_task_app.py +183 -82
- synth_ai/demos/demo_task_apps/math/task_app_entry.py +0 -2
- synth_ai/environments/examples/bandit/engine.py +12 -4
- synth_ai/environments/examples/bandit/taskset.py +4 -4
- synth_ai/environments/examples/crafter_classic/environment.py +76 -1
- synth_ai/environments/reproducibility/tree.py +5 -6
- synth_ai/environments/service/app.py +11 -12
- synth_ai/environments/service/core_routes.py +10 -9
- synth_ai/environments/stateful/engine.py +1 -1
- synth_ai/environments/tasks/core.py +1 -0
- synth_ai/environments/tasks/filters.py +5 -6
- synth_ai/environments/tasks/utils.py +4 -5
- synth_ai/evals/base.py +0 -2
- synth_ai/handshake.py +11 -9
- synth_ai/http.py +1 -1
- synth_ai/http_client.py +43 -11
- synth_ai/inference/__init__.py +0 -2
- synth_ai/inference/client.py +20 -6
- synth_ai/jobs/client.py +103 -78
- synth_ai/learning/__init__.py +41 -6
- synth_ai/learning/algorithms.py +14 -0
- synth_ai/learning/client.py +121 -29
- synth_ai/learning/config.py +2 -40
- synth_ai/learning/constants.py +0 -2
- synth_ai/learning/ft_client.py +4 -56
- synth_ai/learning/health.py +13 -7
- synth_ai/learning/jobs.py +43 -47
- synth_ai/{rl → learning/rl}/__init__.py +14 -5
- synth_ai/learning/rl/client.py +267 -0
- synth_ai/learning/rl/config.py +31 -0
- synth_ai/{rl → learning/rl}/contracts.py +5 -10
- synth_ai/{rl → learning/rl}/env_keys.py +45 -16
- synth_ai/learning/rl/secrets.py +13 -0
- synth_ai/learning/rl_client.py +2 -253
- synth_ai/learning/sft/__init__.py +29 -0
- synth_ai/learning/sft/client.py +68 -0
- synth_ai/learning/sft/config.py +270 -0
- synth_ai/learning/sft/data.py +295 -0
- synth_ai/learning/sse.py +25 -26
- synth_ai/learning/validators.py +25 -24
- synth_ai/lm/__init__.py +21 -47
- synth_ai/task/__init__.py +26 -27
- synth_ai/task/apps/__init__.py +18 -19
- synth_ai/task/auth.py +35 -23
- synth_ai/task/client.py +15 -13
- synth_ai/task/contracts.py +37 -35
- synth_ai/task/datasets.py +9 -6
- synth_ai/task/errors.py +11 -10
- synth_ai/task/health.py +17 -11
- synth_ai/task/json.py +58 -24
- synth_ai/task/proxy.py +15 -14
- synth_ai/task/rubrics.py +22 -15
- synth_ai/task/server.py +43 -17
- synth_ai/task/tracing_utils.py +12 -7
- synth_ai/task/validators.py +0 -1
- synth_ai/task/vendors.py +5 -7
- synth_ai/tracing_v3/__init__.py +2 -0
- synth_ai/tracing_v3/abstractions.py +21 -4
- synth_ai/tracing_v3/db_config.py +26 -1
- synth_ai/tracing_v3/decorators.py +18 -15
- synth_ai/tracing_v3/examples/basic_usage.py +3 -2
- synth_ai/tracing_v3/hooks.py +6 -4
- synth_ai/tracing_v3/llm_call_record_helpers.py +6 -6
- synth_ai/tracing_v3/replica_sync.py +1 -0
- synth_ai/tracing_v3/session_tracer.py +63 -16
- synth_ai/tracing_v3/storage/base.py +89 -1
- synth_ai/tracing_v3/storage/config.py +21 -8
- synth_ai/tracing_v3/storage/factory.py +10 -8
- synth_ai/tracing_v3/storage/utils.py +4 -2
- synth_ai/tracing_v3/turso/daemon.py +7 -2
- synth_ai/tracing_v3/turso/models.py +5 -2
- synth_ai/tracing_v3/turso/native_manager.py +1173 -0
- synth_ai/tracing_v3/utils.py +4 -3
- synth_ai/v0/api/__init__.py +8 -0
- synth_ai/v0/api/models/__init__.py +8 -0
- synth_ai/v0/api/models/supported.py +8 -0
- synth_ai/v0/config/__init__.py +15 -0
- synth_ai/v0/config/base_url.py +12 -0
- synth_ai/v0/lm/__init__.py +51 -0
- synth_ai/{lm → v0/lm}/caching/ephemeral.py +3 -5
- synth_ai/{lm → v0/lm}/caching/handler.py +4 -4
- synth_ai/{lm → v0/lm}/caching/initialize.py +1 -1
- synth_ai/{lm → v0/lm}/caching/persistent.py +1 -1
- synth_ai/{lm → v0/lm}/config.py +6 -1
- synth_ai/{lm → v0/lm}/core/all.py +9 -9
- synth_ai/{lm → v0/lm}/core/exceptions.py +0 -2
- synth_ai/{lm → v0/lm}/core/main.py +19 -7
- synth_ai/{lm → v0/lm}/core/main_v3.py +10 -10
- synth_ai/{lm → v0/lm}/core/synth_models.py +2 -15
- synth_ai/{lm → v0/lm}/core/vendor_clients.py +6 -4
- synth_ai/{lm → v0/lm}/overrides.py +4 -4
- synth_ai/{lm → v0/lm}/provider_support/anthropic.py +4 -4
- synth_ai/{lm → v0/lm}/provider_support/openai.py +5 -5
- synth_ai/{lm → v0/lm}/structured_outputs/handler.py +5 -5
- synth_ai/{lm → v0/lm}/structured_outputs/rehabilitate.py +1 -1
- synth_ai/{lm → v0/lm}/vendors/core/anthropic_api.py +16 -16
- synth_ai/{lm → v0/lm}/vendors/core/gemini_api.py +5 -5
- synth_ai/{lm → v0/lm}/vendors/core/mistral_api.py +5 -5
- synth_ai/{lm → v0/lm}/vendors/core/openai_api.py +12 -10
- synth_ai/{lm → v0/lm}/vendors/openai_standard.py +11 -9
- synth_ai/{lm → v0/lm}/vendors/openai_standard_responses.py +8 -5
- synth_ai/{lm → v0/lm}/vendors/supported/custom_endpoint.py +4 -6
- synth_ai/{lm → v0/lm}/vendors/supported/deepseek.py +2 -2
- synth_ai/{lm → v0/lm}/vendors/supported/grok.py +2 -2
- synth_ai/{lm → v0/lm}/vendors/supported/groq.py +1 -1
- synth_ai/{lm → v0/lm}/vendors/supported/ollama.py +1 -1
- synth_ai/{lm → v0/lm}/vendors/supported/openrouter.py +3 -3
- synth_ai/{lm → v0/lm}/vendors/supported/together.py +1 -1
- synth_ai/{lm → v0/lm}/vendors/synth_client.py +38 -11
- synth_ai/v0/tracing/upload.py +32 -135
- synth_ai/v0/tracing_v3/__init__.py +10 -0
- synth_ai/v0/tracing_v3/abstractions.py +3 -0
- synth_ai/v0/tracing_v3/decorators.py +3 -0
- synth_ai/v0/tracing_v3/llm_call_record_helpers.py +3 -0
- synth_ai/v0/tracing_v3/session_tracer.py +3 -0
- {synth_ai-0.2.9.dev5.dist-info → synth_ai-0.2.10.dist-info}/METADATA +10 -7
- {synth_ai-0.2.9.dev5.dist-info → synth_ai-0.2.10.dist-info}/RECORD +294 -258
- examples/common_old/backend.py +0 -21
- examples/evals_old/README.md +0 -98
- examples/evals_old/__init__.py +0 -6
- examples/evals_old/compare_models.py +0 -1037
- examples/evals_old/example_log.md +0 -145
- examples/evals_old/run_demo.sh +0 -126
- examples/evals_old/trace_analysis.py +0 -270
- examples/finetuning_old/_backup_synth_qwen/config.toml +0 -29
- examples/finetuning_old/_backup_synth_qwen/example_log.md +0 -324
- examples/finetuning_old/_backup_synth_qwen/filter_traces.py +0 -60
- examples/finetuning_old/_backup_synth_qwen/filter_traces_achievements.py +0 -239
- examples/finetuning_old/_backup_synth_qwen/purge_v3_traces.py +0 -109
- examples/finetuning_old/_backup_synth_qwen/react_agent_lm.py +0 -1924
- examples/finetuning_old/_backup_synth_qwen/readme.md +0 -49
- examples/finetuning_old/_backup_synth_qwen/run_crafter_qwen4b.py +0 -114
- examples/finetuning_old/_backup_synth_qwen/run_demo.sh +0 -195
- examples/finetuning_old/_backup_synth_qwen/sft_kickoff.py +0 -118
- examples/finetuning_old/synth_qwen_v1/README.md +0 -68
- examples/finetuning_old/synth_qwen_v1/filter_traces.py +0 -60
- examples/finetuning_old/synth_qwen_v1/filter_traces_achievements.py +0 -239
- examples/finetuning_old/synth_qwen_v1/finetune.py +0 -46
- examples/finetuning_old/synth_qwen_v1/hello_ft_model.py +0 -71
- examples/finetuning_old/synth_qwen_v1/infer.py +0 -37
- examples/finetuning_old/synth_qwen_v1/poll.py +0 -44
- examples/finetuning_old/synth_qwen_v1/prepare_data.py +0 -35
- examples/finetuning_old/synth_qwen_v1/purge_v3_traces.py +0 -109
- examples/finetuning_old/synth_qwen_v1/react_agent_lm.py +0 -1932
- examples/finetuning_old/synth_qwen_v1/run_crafter_sft_job.py +0 -207
- examples/finetuning_old/synth_qwen_v1/run_ft_job.py +0 -232
- examples/finetuning_old/synth_qwen_v1/upload_data.py +0 -34
- examples/finetuning_old/synth_qwen_v1/util.py +0 -147
- examples/rl_old/task_app.py +0 -962
- synth_ai/experimental/synth_oss.py +0 -446
- synth_ai/install_sqld.sh +0 -40
- synth_ai/learning/filtering.py +0 -0
- synth_ai/learning/offline/dpo.py +0 -0
- synth_ai/learning/offline/providers.py +0 -7
- synth_ai/learning/offline/sft.py +0 -0
- synth_ai/learning/offline/shared.py +0 -0
- synth_ai/learning/online/grpo.py +0 -0
- synth_ai/learning/online/irft.py +0 -0
- synth_ai/learning/prompts/banking77_injection_eval.py +0 -168
- synth_ai/learning/prompts/gepa.py +0 -0
- synth_ai/learning/prompts/hello_world_in_context_injection_ex.py +0 -213
- synth_ai/learning/prompts/mipro.py +0 -289
- synth_ai/learning/prompts/random_search.py +0 -246
- synth_ai/learning/prompts/run_mipro_banking77.py +0 -172
- synth_ai/learning/prompts/run_random_search_banking77.py +0 -324
- synth_ai/rl/secrets.py +0 -19
- synth_ai/scripts/verify_rewards.py +0 -100
- synth_ai/tracing/__init__.py +0 -30
- synth_ai/tracing_v1/__init__.py +0 -33
- synth_ai/tracing_v3/turso/__init__.py +0 -25
- synth_ai/tracing_v3/turso/manager.py +0 -774
- synth_ai/zyk/__init__.py +0 -30
- /synth_ai/{lm → v0/lm}/caching/__init__.py +0 -0
- /synth_ai/{lm → v0/lm}/caching/constants.py +0 -0
- /synth_ai/{lm → v0/lm}/caching/dbs.py +0 -0
- /synth_ai/{lm → v0/lm}/constants.py +0 -0
- /synth_ai/{lm → v0/lm}/core/__init__.py +0 -0
- /synth_ai/{lm → v0/lm}/cost/__init__.py +0 -0
- /synth_ai/{lm → v0/lm}/cost/monitor.py +0 -0
- /synth_ai/{lm → v0/lm}/cost/statefulness.py +0 -0
- /synth_ai/{lm → v0/lm}/injection.py +0 -0
- /synth_ai/{lm → v0/lm}/provider_support/__init__.py +0 -0
- /synth_ai/{lm → v0/lm}/provider_support/suppress_logging.py +0 -0
- /synth_ai/{lm → v0/lm}/structured_outputs/__init__.py +0 -0
- /synth_ai/{lm → v0/lm}/structured_outputs/inject.py +0 -0
- /synth_ai/{lm → v0/lm}/tools/__init__.py +0 -0
- /synth_ai/{lm → v0/lm}/tools/base.py +0 -0
- /synth_ai/{lm → v0/lm}/unified_interface.py +0 -0
- /synth_ai/{lm → v0/lm}/vendors/__init__.py +0 -0
- /synth_ai/{lm → v0/lm}/vendors/base.py +0 -0
- /synth_ai/{lm → v0/lm}/vendors/core/__init__.py +0 -0
- /synth_ai/{lm → v0/lm}/vendors/core/synth_dev_api.py +0 -0
- /synth_ai/{lm → v0/lm}/vendors/local/__init__.py +0 -0
- /synth_ai/{lm → v0/lm}/vendors/local/ollama.py +0 -0
- /synth_ai/{lm → v0/lm}/vendors/retries.py +0 -0
- /synth_ai/{lm → v0/lm}/vendors/supported/__init__.py +0 -0
- /synth_ai/{lm → v0/lm}/warmup.py +0 -0
- {synth_ai-0.2.9.dev5.dist-info → synth_ai-0.2.10.dist-info}/WHEEL +0 -0
- {synth_ai-0.2.9.dev5.dist-info → synth_ai-0.2.10.dist-info}/entry_points.txt +0 -0
- {synth_ai-0.2.9.dev5.dist-info → synth_ai-0.2.10.dist-info}/licenses/LICENSE +0 -0
- {synth_ai-0.2.9.dev5.dist-info → synth_ai-0.2.10.dist-info}/top_level.txt +0 -0
|
@@ -0,0 +1,195 @@
|
|
|
1
|
+
from __future__ import annotations
|
|
2
|
+
|
|
3
|
+
import uuid
|
|
4
|
+
from dataclasses import dataclass, field
|
|
5
|
+
from datetime import datetime
|
|
6
|
+
from typing import Any
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
@dataclass
|
|
10
|
+
class EnvHandle:
|
|
11
|
+
"""In-memory handle for an active environment instance."""
|
|
12
|
+
|
|
13
|
+
env_id: str
|
|
14
|
+
env: Any # StatefulEnvironment or wrapper
|
|
15
|
+
last_observation: dict[str, Any] | None
|
|
16
|
+
last_info: dict[str, Any] | None
|
|
17
|
+
step_idx: int
|
|
18
|
+
seed: int | None
|
|
19
|
+
rl_run_id: str
|
|
20
|
+
created_at: datetime = field(default_factory=datetime.utcnow)
|
|
21
|
+
|
|
22
|
+
|
|
23
|
+
@dataclass
|
|
24
|
+
class PolicyHandle:
|
|
25
|
+
"""In-memory handle for an active policy instance."""
|
|
26
|
+
|
|
27
|
+
policy_id: str
|
|
28
|
+
policy: Any # Policy instance
|
|
29
|
+
bound_env_id: str | None
|
|
30
|
+
rl_run_id: str
|
|
31
|
+
created_at: datetime = field(default_factory=datetime.utcnow)
|
|
32
|
+
|
|
33
|
+
|
|
34
|
+
@dataclass
|
|
35
|
+
class RunHandle:
|
|
36
|
+
"""Track run status for abort support."""
|
|
37
|
+
|
|
38
|
+
run_id: str
|
|
39
|
+
status: str # "running" | "aborted" | "completed"
|
|
40
|
+
started_at: datetime
|
|
41
|
+
finished_at: datetime | None = None
|
|
42
|
+
|
|
43
|
+
|
|
44
|
+
@dataclass
|
|
45
|
+
class SnapshotMeta:
|
|
46
|
+
"""Metadata for a stored snapshot."""
|
|
47
|
+
|
|
48
|
+
snapshot_id: str
|
|
49
|
+
kind: str # "env" | "policy"
|
|
50
|
+
rl_run_id: str
|
|
51
|
+
parent_snapshot_id: str | None
|
|
52
|
+
size: int
|
|
53
|
+
created_at: datetime
|
|
54
|
+
path: str
|
|
55
|
+
|
|
56
|
+
|
|
57
|
+
class Registry:
|
|
58
|
+
"""In-memory registries for the service."""
|
|
59
|
+
|
|
60
|
+
def __init__(self) -> None:
|
|
61
|
+
self.envs: dict[str, EnvHandle] = {}
|
|
62
|
+
self.policies: dict[str, PolicyHandle] = {}
|
|
63
|
+
self.runs: dict[str, RunHandle] = {}
|
|
64
|
+
self.snapshots: dict[str, SnapshotMeta] = {}
|
|
65
|
+
|
|
66
|
+
def generate_id(self) -> str:
|
|
67
|
+
"""Generate a UUID for unique identification."""
|
|
68
|
+
return str(uuid.uuid4())
|
|
69
|
+
|
|
70
|
+
def register_env(
|
|
71
|
+
self,
|
|
72
|
+
env: Any,
|
|
73
|
+
seed: int | None,
|
|
74
|
+
rl_run_id: str,
|
|
75
|
+
last_observation: dict[str, Any] | None = None,
|
|
76
|
+
last_info: dict[str, Any] | None = None,
|
|
77
|
+
) -> str:
|
|
78
|
+
"""Register a new environment instance."""
|
|
79
|
+
env_id = self.generate_id()
|
|
80
|
+
handle = EnvHandle(
|
|
81
|
+
env_id=env_id,
|
|
82
|
+
env=env,
|
|
83
|
+
last_observation=last_observation,
|
|
84
|
+
last_info=last_info,
|
|
85
|
+
step_idx=0,
|
|
86
|
+
seed=seed,
|
|
87
|
+
rl_run_id=rl_run_id,
|
|
88
|
+
)
|
|
89
|
+
self.envs[env_id] = handle
|
|
90
|
+
return env_id
|
|
91
|
+
|
|
92
|
+
def register_policy(
|
|
93
|
+
self,
|
|
94
|
+
policy: Any,
|
|
95
|
+
rl_run_id: str,
|
|
96
|
+
bound_env_id: str | None = None,
|
|
97
|
+
) -> str:
|
|
98
|
+
"""Register a new policy instance."""
|
|
99
|
+
policy_id = self.generate_id()
|
|
100
|
+
handle = PolicyHandle(
|
|
101
|
+
policy_id=policy_id,
|
|
102
|
+
policy=policy,
|
|
103
|
+
bound_env_id=bound_env_id,
|
|
104
|
+
rl_run_id=rl_run_id,
|
|
105
|
+
)
|
|
106
|
+
self.policies[policy_id] = handle
|
|
107
|
+
return policy_id
|
|
108
|
+
|
|
109
|
+
def register_run(self, run_id: str | None = None) -> str:
|
|
110
|
+
"""Register a new run."""
|
|
111
|
+
if run_id is None:
|
|
112
|
+
run_id = self.generate_id()
|
|
113
|
+
handle = RunHandle(
|
|
114
|
+
run_id=run_id,
|
|
115
|
+
status="running",
|
|
116
|
+
started_at=datetime.utcnow(),
|
|
117
|
+
)
|
|
118
|
+
self.runs[run_id] = handle
|
|
119
|
+
return run_id
|
|
120
|
+
|
|
121
|
+
def abort_run(self, run_id: str) -> bool:
|
|
122
|
+
"""Mark a run as aborted."""
|
|
123
|
+
if run_id in self.runs:
|
|
124
|
+
self.runs[run_id].status = "aborted"
|
|
125
|
+
self.runs[run_id].finished_at = datetime.utcnow()
|
|
126
|
+
return True
|
|
127
|
+
return False
|
|
128
|
+
|
|
129
|
+
def complete_run(self, run_id: str) -> bool:
|
|
130
|
+
"""Mark a run as completed."""
|
|
131
|
+
if run_id in self.runs:
|
|
132
|
+
self.runs[run_id].status = "completed"
|
|
133
|
+
self.runs[run_id].finished_at = datetime.utcnow()
|
|
134
|
+
return True
|
|
135
|
+
return False
|
|
136
|
+
|
|
137
|
+
def is_run_aborted(self, run_id: str) -> bool:
|
|
138
|
+
"""Check if a run has been aborted."""
|
|
139
|
+
return run_id in self.runs and self.runs[run_id].status == "aborted"
|
|
140
|
+
|
|
141
|
+
def register_snapshot(
|
|
142
|
+
self,
|
|
143
|
+
kind: str,
|
|
144
|
+
rl_run_id: str,
|
|
145
|
+
size: int,
|
|
146
|
+
path: str,
|
|
147
|
+
parent_snapshot_id: str | None = None,
|
|
148
|
+
) -> str:
|
|
149
|
+
"""Register a new snapshot."""
|
|
150
|
+
snapshot_id = self.generate_id()
|
|
151
|
+
meta = SnapshotMeta(
|
|
152
|
+
snapshot_id=snapshot_id,
|
|
153
|
+
kind=kind,
|
|
154
|
+
rl_run_id=rl_run_id,
|
|
155
|
+
parent_snapshot_id=parent_snapshot_id,
|
|
156
|
+
size=size,
|
|
157
|
+
created_at=datetime.utcnow(),
|
|
158
|
+
path=path,
|
|
159
|
+
)
|
|
160
|
+
self.snapshots[snapshot_id] = meta
|
|
161
|
+
return snapshot_id
|
|
162
|
+
|
|
163
|
+
def get_env(self, env_id: str) -> EnvHandle | None:
|
|
164
|
+
"""Get an environment handle by ID."""
|
|
165
|
+
return self.envs.get(env_id)
|
|
166
|
+
|
|
167
|
+
def get_policy(self, policy_id: str) -> PolicyHandle | None:
|
|
168
|
+
"""Get a policy handle by ID."""
|
|
169
|
+
return self.policies.get(policy_id)
|
|
170
|
+
|
|
171
|
+
def get_run(self, run_id: str) -> RunHandle | None:
|
|
172
|
+
"""Get a run handle by ID."""
|
|
173
|
+
return self.runs.get(run_id)
|
|
174
|
+
|
|
175
|
+
def get_snapshot(self, snapshot_id: str) -> SnapshotMeta | None:
|
|
176
|
+
"""Get snapshot metadata by ID."""
|
|
177
|
+
return self.snapshots.get(snapshot_id)
|
|
178
|
+
|
|
179
|
+
def remove_env(self, env_id: str) -> bool:
|
|
180
|
+
"""Remove an environment from the registry."""
|
|
181
|
+
if env_id in self.envs:
|
|
182
|
+
del self.envs[env_id]
|
|
183
|
+
return True
|
|
184
|
+
return False
|
|
185
|
+
|
|
186
|
+
def remove_policy(self, policy_id: str) -> bool:
|
|
187
|
+
"""Remove a policy from the registry."""
|
|
188
|
+
if policy_id in self.policies:
|
|
189
|
+
del self.policies[policy_id]
|
|
190
|
+
return True
|
|
191
|
+
return False
|
|
192
|
+
|
|
193
|
+
|
|
194
|
+
# Global registry instance
|
|
195
|
+
registry = Registry()
|