synth-ai 0.2.13.dev1__py3-none-any.whl → 0.2.13.dev2__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of synth-ai might be problematic. Click here for more details.
- examples/multi_step/configs/crafter_rl_stepwise_hosted_judge.toml +12 -1
- examples/swe/task_app/grpo_swe_mini.py +55 -26
- examples/swe/task_app/hosted/rollout.py +40 -0
- examples/swe/task_app/hosted/test_service.py +5 -6
- examples/task_apps/TESTING.md +275 -0
- examples/task_apps/__init__.py +0 -0
- examples/task_apps/crafter/__init__.py +0 -0
- examples/task_apps/crafter/task_app/__init__.py +2 -0
- examples/{warming_up_to_rl → task_apps/crafter}/task_app/grpo_crafter.py +18 -13
- examples/{warming_up_to_rl → task_apps/crafter}/task_app/grpo_crafter_task_app.py +1 -1
- examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/policy.py +60 -4
- examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/policy_routes.py +25 -3
- examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/rollout.py +10 -0
- examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/test_service.py +5 -6
- examples/task_apps/dev/pokemon_emerald/__init__.py +2 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/README.md +811 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/__init__.py +120 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/action.py +160 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/memory.py +155 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/perception.py +69 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/planning.py +96 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/simple.py +1502 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/agent/system_prompt.py +4 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/grab_map.py +68 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/manual.py +216 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/__init__.py +35 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/emerald_utils.py +631 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/emulator.py +1544 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/enums.py +1428 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/memory_reader.py +4848 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/types.py +41 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pokemon_env/utils.py +298 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/pyproject.toml +95 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/run.py +204 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/server/__init__.py +0 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/server/app.py +2152 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/server/client.py +429 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/server/frame_server.py +155 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/README.md +78 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/__init__.py +0 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/run_tests.py +122 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_agent_direct.py +76 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_agent_prompts.py +413 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_battle_state_formatting.py +204 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_dialogue_detection.py +133 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_dialogue_detection_comprehensive.py +229 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_direct_agent_emulator.py +300 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_fps_adjustment_pytest.py +205 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_house_to_outside_direct.py +200 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_house_to_outside_transition.py +284 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_map_ground_truth_comparison.py +468 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_memory_map.py +575 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_server_map_validation.py +311 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/tests/test_torchic_state.py +259 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/__init__.py +0 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/anticheat.py +372 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/checkpoint.py +296 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/error_handler.py +275 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/get_local_ip.py +22 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/helpers.py +44 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/llm_logger.py +514 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_formatter.py +415 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_stitcher.py +1763 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_stitcher_singleton.py +33 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_trimmer.py +106 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/map_visualizer.py +334 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/ocr_dialogue.py +1020 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/recording.py +188 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/state_formatter.py +1481 -0
- examples/task_apps/dev/pokemon_emerald/external/pokeagent-speedrun/utils/vlm.py +862 -0
- examples/task_apps/dev/pokemon_emerald/modal_app.py +114 -0
- examples/task_apps/dev/pokemon_emerald/task_app/README.md +81 -0
- examples/task_apps/dev/pokemon_emerald/task_app/__init__.py +6 -0
- examples/task_apps/dev/pokemon_emerald/task_app/pokemon_emerald.py +685 -0
- examples/task_apps/enron/__init__.py +1 -0
- examples/task_apps/enron/eval_groq_qwen32.toml +16 -0
- examples/task_apps/enron/task_app/README.md +14 -0
- examples/task_apps/enron/task_app/__init__.py +1 -0
- examples/task_apps/enron/task_app/grpo_enron.py +906 -0
- examples/task_apps/enron/task_app/grpo_enron_task_app.py +146 -0
- examples/task_apps/enron/tests/__init__.py +2 -0
- examples/task_apps/enron/tests/conftest.py +115 -0
- examples/task_apps/enron/tests/integration/__init__.py +2 -0
- examples/task_apps/enron/tests/integration/test_enron_eval.py +177 -0
- examples/task_apps/enron/tests/integration/test_enron_rollout.py +135 -0
- examples/task_apps/enron/tests/unit/__init__.py +2 -0
- examples/task_apps/enron/tests/unit/test_enron_environment.py +126 -0
- examples/task_apps/math/__init__.py +0 -0
- examples/{rl/task_app → task_apps/math}/math_single_step.py +19 -10
- examples/task_apps/pokemon_battle/__init__.py +2 -0
- examples/task_apps/pokemon_battle/modal_app.py +104 -0
- examples/task_apps/pokemon_battle/task_app/README.md +68 -0
- examples/task_apps/pokemon_battle/task_app/__init__.py +6 -0
- examples/task_apps/pokemon_battle/task_app/pokemon_showdown.py +932 -0
- examples/task_apps/pokemon_red/README.md +357 -0
- examples/task_apps/pokemon_red/__init__.py +3 -0
- examples/task_apps/pokemon_red/eval_pokemon_red_policy.py +225 -0
- examples/task_apps/pokemon_red/pallet_town_rl_config.toml +73 -0
- examples/task_apps/pokemon_red/task_app.py +606 -0
- examples/task_apps/pokemon_red/test_pallet_town_rewards.py +191 -0
- examples/task_apps/sokoban/README.md +307 -0
- examples/task_apps/sokoban/__init__.py +3 -0
- examples/task_apps/sokoban/eval_groq_qwen32.toml +16 -0
- examples/task_apps/sokoban/eval_openai_gpt5.toml +16 -0
- examples/task_apps/sokoban/task_app.py +1058 -0
- examples/task_apps/sokoban/tests/__init__.py +2 -0
- examples/task_apps/sokoban/tests/conftest.py +113 -0
- examples/task_apps/sokoban/tests/integration/__init__.py +2 -0
- examples/task_apps/sokoban/tests/integration/test_sokoban_eval.py +57 -0
- examples/task_apps/sokoban/tests/integration/test_sokoban_rollout.py +198 -0
- examples/task_apps/sokoban/tests/unit/__init__.py +2 -0
- examples/task_apps/sokoban/tests/unit/test_sokoban_environment.py +114 -0
- examples/task_apps/verilog/__init__.py +1 -0
- examples/task_apps/verilog/eval_groq_qwen32b.toml +20 -0
- examples/task_apps/verilog/task_app/README.md +12 -0
- examples/task_apps/verilog/task_app/__init__.py +1 -0
- examples/task_apps/verilog/task_app/grpo_verilog.py +931 -0
- examples/task_apps/verilog/task_app/grpo_verilog_task_app.py +145 -0
- examples/task_apps/verilog/tests/__init__.py +2 -0
- examples/task_apps/verilog/tests/conftest.py +115 -0
- examples/task_apps/verilog/tests/integration/__init__.py +2 -0
- examples/task_apps/verilog/tests/integration/test_verilog_eval.py +179 -0
- examples/task_apps/verilog/tests/integration/test_verilog_rollout.py +55 -0
- examples/task_apps/verilog/tests/unit/__init__.py +2 -0
- examples/task_apps/verilog/tests/unit/test_verilog_scoring.py +118 -0
- examples/vlm/crafter_openai_vlm_agent.py +4 -4
- examples/vlm/run_crafter_vlm_benchmark.py +4 -4
- examples/workflows/__init__.py +0 -0
- examples/workflows/math_rl/__init__.py +0 -0
- examples/workflows/math_rl/download_dataset.py +80 -0
- synth_ai/__init__.py +2 -2
- synth_ai/api/train/builders.py +25 -11
- synth_ai/api/train/cli.py +12 -6
- synth_ai/api/train/configs/__init__.py +10 -10
- synth_ai/api/train/configs/rl.py +5 -4
- synth_ai/api/train/configs/sft.py +4 -3
- synth_ai/api/train/env_resolver.py +5 -2
- synth_ai/api/train/supported_algos.py +10 -5
- synth_ai/api/train/utils.py +7 -4
- synth_ai/cli/__init__.py +7 -51
- synth_ai/cli/_storage.py +4 -3
- synth_ai/cli/_validate_task_app.py +11 -0
- synth_ai/cli/balance.py +4 -3
- synth_ai/cli/calc.py +2 -2
- synth_ai/cli/demo.py +14 -7
- synth_ai/cli/legacy_root_backup.py +1 -1
- synth_ai/cli/rl_demo.py +8 -7
- synth_ai/cli/root.py +0 -97
- synth_ai/cli/task_apps.py +1707 -186
- synth_ai/demos/demo_task_apps/crafter/grpo_crafter_task_app.py +28 -16
- synth_ai/environments/examples/enron/engine.py +7 -2
- synth_ai/environments/examples/enron/environment.py +68 -0
- synth_ai/environments/examples/red/engine.py +27 -0
- synth_ai/environments/examples/red/engine_helpers/memory_map.py +7 -0
- synth_ai/environments/examples/red/engine_helpers/reward_library/pallet_town_progression.py +477 -0
- synth_ai/environments/examples/red/engine_helpers/state_extraction.py +32 -0
- synth_ai/environments/examples/red/environment.py +60 -0
- synth_ai/environments/examples/sokoban/taskset.py +116 -0
- synth_ai/environments/examples/verilog/engine.py +30 -4
- synth_ai/evals/client.py +58 -61
- synth_ai/jobs/client.py +16 -4
- synth_ai/judge_schemas.py +16 -16
- synth_ai/py.typed +0 -0
- synth_ai/task/__init__.py +14 -5
- synth_ai/task/contracts.py +124 -38
- synth_ai/task/proxy.py +48 -56
- synth_ai/task/rubrics/__init__.py +53 -0
- synth_ai/task/rubrics/loaders.py +133 -0
- synth_ai/task/rubrics/models.py +57 -0
- synth_ai/task/rubrics/scoring.py +113 -0
- synth_ai/{rubrics/validators.py → task/rubrics/strict.py} +53 -30
- synth_ai/task/server.py +8 -7
- synth_ai/task/validators.py +269 -6
- synth_ai/tracing_v3/decorators.py +7 -3
- synth_ai/tracing_v3/replica_sync.py +4 -4
- synth_ai/tracing_v3/serialization.py +5 -5
- synth_ai/tracing_v3/trace_utils.py +317 -0
- synth_ai/tracing_v3/turso/native_manager.py +3 -3
- {synth_ai-0.2.13.dev1.dist-info → synth_ai-0.2.13.dev2.dist-info}/METADATA +4 -1
- {synth_ai-0.2.13.dev1.dist-info → synth_ai-0.2.13.dev2.dist-info}/RECORD +214 -101
- examples/agora_ex/README_MoE.md +0 -224
- examples/agora_ex/__init__.py +0 -7
- examples/agora_ex/agora_ex.py +0 -65
- examples/agora_ex/agora_ex_task_app.py +0 -590
- examples/agora_ex/configs/rl_lora_qwen3_moe_2xh200.toml +0 -121
- examples/agora_ex/reward_fn_grpo-human.py +0 -129
- examples/agora_ex/system_prompt_CURRENT.md +0 -63
- examples/agora_ex/task_app/agora_ex_task_app.py +0 -590
- examples/agora_ex/task_app/reward_fn_grpo-human.py +0 -129
- examples/agora_ex/task_app/system_prompt_CURRENT.md +0 -63
- synth_ai/rubrics/__init__.py +0 -22
- synth_ai/task/rubrics.py +0 -219
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/README.md +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/README.md +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/__init__.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/branching.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/environment_routes.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/__init__.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/__init__.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/app.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/environment.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/react_agent.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/shared.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/envs/crafter/tools.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/hosted_app.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/inference/__init__.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/inference/openai_client.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/main.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/registry.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/storage/__init__.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/storage/volume.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/test_agents.py +0 -0
- /examples/{warming_up_to_rl → task_apps/crafter}/task_app/synth_envs_hosted/utils.py +0 -0
- /examples/{rl/task_app → task_apps/math}/README.md +0 -0
- /examples/{rl/task_app → task_apps/math}/math_task_app.py +0 -0
- /examples/{rl → workflows/math_rl}/configs/eval_base_qwen.toml +0 -0
- /examples/{rl → workflows/math_rl}/configs/eval_rl_qwen.toml +0 -0
- /examples/{rl → workflows/math_rl}/configs/rl_from_base_qwen.toml +0 -0
- /examples/{rl → workflows/math_rl}/configs/rl_from_base_qwen17.toml +0 -0
- /examples/{rl → workflows/math_rl}/configs/rl_from_ft_qwen.toml +0 -0
- /examples/{rl → workflows/math_rl}/run_eval.py +0 -0
- /examples/{rl → workflows/math_rl}/run_rl_and_save.py +0 -0
- {synth_ai-0.2.13.dev1.dist-info → synth_ai-0.2.13.dev2.dist-info}/WHEEL +0 -0
- {synth_ai-0.2.13.dev1.dist-info → synth_ai-0.2.13.dev2.dist-info}/entry_points.txt +0 -0
- {synth_ai-0.2.13.dev1.dist-info → synth_ai-0.2.13.dev2.dist-info}/licenses/LICENSE +0 -0
- {synth_ai-0.2.13.dev1.dist-info → synth_ai-0.2.13.dev2.dist-info}/top_level.txt +0 -0
synth_ai/cli/root.py
CHANGED
|
@@ -156,103 +156,6 @@ def cli():
|
|
|
156
156
|
"""Top-level command group for Synth AI."""
|
|
157
157
|
|
|
158
158
|
|
|
159
|
-
# === Legacy demo command group (aliases new rl_demo implementation) ===
|
|
160
|
-
@cli.group()
|
|
161
|
-
def demo():
|
|
162
|
-
"""Demo helpers (deploy, configure, run)."""
|
|
163
|
-
|
|
164
|
-
|
|
165
|
-
def _forward_to_demo(args: list[str]) -> None:
|
|
166
|
-
# Lazy import to avoid loading demo deps unless needed
|
|
167
|
-
try:
|
|
168
|
-
from synth_ai.demos.core import cli as demo_cli # type: ignore
|
|
169
|
-
except Exception as e: # pragma: no cover
|
|
170
|
-
click.echo(f"Failed to import demo CLI: {e}")
|
|
171
|
-
sys.exit(1)
|
|
172
|
-
rc = int(demo_cli.main(args) or 0) # type: ignore[attr-defined]
|
|
173
|
-
if rc != 0:
|
|
174
|
-
sys.exit(rc)
|
|
175
|
-
|
|
176
|
-
|
|
177
|
-
# (prepare command removed; handled by configure)
|
|
178
|
-
|
|
179
|
-
|
|
180
|
-
@demo.command()
|
|
181
|
-
@click.option("--local", is_flag=True, help="Run local FastAPI instead of Modal deploy")
|
|
182
|
-
@click.option(
|
|
183
|
-
"--app", type=click.Path(), default=None, help="Path to Modal app.py for uv run modal deploy"
|
|
184
|
-
)
|
|
185
|
-
@click.option("--name", type=str, default="synth-math-demo", help="Modal app name")
|
|
186
|
-
@click.option(
|
|
187
|
-
"--script", type=click.Path(), default=None, help="Path to deploy_task_app.sh (optional legacy)"
|
|
188
|
-
)
|
|
189
|
-
def deploy(local: bool, app: str | None, name: str, script: str | None):
|
|
190
|
-
"""Deploy the Math Task App (Modal by default)."""
|
|
191
|
-
args: list[str] = ["rl_demo.deploy"]
|
|
192
|
-
if local:
|
|
193
|
-
args.append("--local")
|
|
194
|
-
if app:
|
|
195
|
-
args.extend(["--app", app])
|
|
196
|
-
if name:
|
|
197
|
-
args.extend(["--name", name])
|
|
198
|
-
if script:
|
|
199
|
-
args.extend(["--script", script])
|
|
200
|
-
_forward_to_demo(args)
|
|
201
|
-
|
|
202
|
-
|
|
203
|
-
@demo.command()
|
|
204
|
-
def configure():
|
|
205
|
-
"""Print resolved environment and config path."""
|
|
206
|
-
_forward_to_demo(["rl_demo.configure"])
|
|
207
|
-
|
|
208
|
-
|
|
209
|
-
@demo.command()
|
|
210
|
-
def setup():
|
|
211
|
-
"""Perform SDK handshake and write keys to .env."""
|
|
212
|
-
_forward_to_demo(["rl_demo.setup"])
|
|
213
|
-
|
|
214
|
-
|
|
215
|
-
@demo.command()
|
|
216
|
-
@click.option("--template", type=str, default=None, help="Template id to instantiate")
|
|
217
|
-
@click.option("--dest", type=str, default=None, help="Destination directory for files")
|
|
218
|
-
@click.option("--force", is_flag=True, help="Overwrite existing files in destination")
|
|
219
|
-
def init(template: str | None, dest: str | None, force: bool):
|
|
220
|
-
"""Copy demo task app template into the current directory."""
|
|
221
|
-
args: list[str] = ["demo.init"]
|
|
222
|
-
if template:
|
|
223
|
-
args.extend(["--template", template])
|
|
224
|
-
if dest:
|
|
225
|
-
args.extend(["--dest", dest])
|
|
226
|
-
if force:
|
|
227
|
-
args.append("--force")
|
|
228
|
-
_forward_to_demo(args)
|
|
229
|
-
|
|
230
|
-
|
|
231
|
-
@demo.command()
|
|
232
|
-
@click.option("--batch-size", type=int, default=None)
|
|
233
|
-
@click.option("--group-size", type=int, default=None)
|
|
234
|
-
@click.option("--model", type=str, default=None)
|
|
235
|
-
@click.option("--timeout", type=int, default=600)
|
|
236
|
-
def run(batch_size: int | None, group_size: int | None, model: str | None, timeout: int):
|
|
237
|
-
"""Kick off a short RL job using the prepared TOML."""
|
|
238
|
-
args = ["rl_demo.run"]
|
|
239
|
-
if batch_size is not None:
|
|
240
|
-
args.extend(["--batch-size", str(batch_size)])
|
|
241
|
-
if group_size is not None:
|
|
242
|
-
args.extend(["--group-size", str(group_size)])
|
|
243
|
-
if model:
|
|
244
|
-
args.extend(["--model", model])
|
|
245
|
-
if timeout:
|
|
246
|
-
args.extend(["--timeout", str(timeout)])
|
|
247
|
-
_forward_to_demo(args)
|
|
248
|
-
|
|
249
|
-
|
|
250
|
-
@cli.command(name="setup")
|
|
251
|
-
def setup_command():
|
|
252
|
-
"""Perform SDK handshake and write keys to .env."""
|
|
253
|
-
_forward_to_demo(["rl_demo.setup"])
|
|
254
|
-
|
|
255
|
-
|
|
256
159
|
@cli.command()
|
|
257
160
|
@click.option("--db-file", default="traces/v3/synth_ai.db", help="Database file path")
|
|
258
161
|
@click.option("--sqld-port", default=8080, type=int, help="Port for sqld HTTP interface")
|