synth-ai 0.2.9.dev2__py3-none-any.whl → 0.2.9.dev4__py3-none-any.whl

synth_ai/demos/demo_task_apps/crafter/configs/crafter_fft_4b.toml

@@ -0,0 +1,54 @@
+# FFT job config for Qwen/Qwen3-4B on Crafter SFT dataset
+
+[algorithm]
+type = "offline"
+method = "supervised_finetune"
+variety = "fft"
+
+
+[job]
+model = "Qwen/Qwen3-4B"
+# Limit training to the first 100 conversations (export a 100-row JSONL and point to it here)
+# data = "../ft_data/qwen3_32b_ach_ge3_raw_filtered.head100.jsonl"
+
+[compute]
+# Adjust as needed for your quota
+gpu_type = "H100"
+gpu_count = 1
+nodes = 1
+
+[data]
+# Optional topology metadata (left empty for now)
+topology = {}
+
+# Optional local validation dataset path (JSONL). If set, the client will upload
+# this file and wire up validation so the frontend can display val.loss.
+validation_path = "../ft_data/qwen3_32b_ach_ge3_raw_filtered.tokens_1000000_seed_123.val_2000.jsonl"
+
+[training]
+mode = "sft_offline"
+use_qlora = false
+
+# Validation settings to emit val.loss on the frontend
+[training.validation]
+enabled = true
+evaluation_strategy = "steps"
+eval_steps = 20
+save_best_model_at_end = true
+metric_for_best_model = "val.loss"
+greater_is_better = false
+
+[hyperparameters]
+# Minimal safe defaults; backend can override
+n_epochs = 1
+batch_size = 1
+gradient_accumulation_steps = 64
+sequence_length = 4096
+learning_rate = 5e-6
+warmup_ratio = 0.03
+train_kind = "fft"
+
+# Optional parallelism block example
+#[hyperparameters.parallelism]
+# tensor_parallel_size = 1
+# pipeline_parallel_size = 1

synth_ai/demos/demo_task_apps/crafter/configs/rl_from_base_qwen4b.toml

@@ -0,0 +1,73 @@
+# RL training starting from base Qwen/Qwen3-4B (TOML-only model selection)
+
+[algorithm]
+type = "online"
+method = "policy_gradient"
+variety = "gspo"
+
+
+[services]
+task_url = "https://synth-laboratories--grpo-crafter-task-app-final-warming--ceb5b2.modal.run"
+
+[compute]
+# Cluster shape for RL pipeline
+gpu_type = "H100"
+gpu_count = 8
+
+[topology]
+# Split GPUs across vLLM, training, and reference
+# Must sum to compute.gpu_count
+type = "single_node_split"
+gpus_for_vllm = 4
+gpus_for_training = 3
+gpus_for_ref = 1
+tensor_parallel = 4
+
+[vllm]
+# Serving tensor parallel size
+tensor_parallel_size = 4
+max_model_len = 8192
+
+[reference]
+# Required by trainer/runtime; ensures dedicated/scoped scoring server config exists
+placement = "dedicated"
+port = 8002
+tp = 1
+health_max_wait_s = 180
+health_interval_ms = 300
+
+[model]
+# Base model start
+base = "Qwen/Qwen3-4B"
+label = "crafter-rl-from-base"
+
+[rollout]
+max_turns = 10
+episodes_per_batch = 64
+policy_name = "crafter"
+
+[evaluation]
+# Run baseline evaluation over the first 100 seeds every 20 training iterations
+instances = 10
+every_n_iters = 10
+seeds = [
+  0, 1, 2, 3, 4, 5, 6, 7, 8, 9,
+]
+
+[training]
+log_interval = 1
+weight_sync_interval = 1
+# Additional RL hyperparameters can go here
+
+# Stepwise rewards (Crafter decision-level)
+step_rewards_enabled = true
+step_rewards_mode = "decision_stepwise"  # "off" | "decision_stepwise" | "env_sparse"
+step_rewards_beta = 0.0
+step_rewards_indicator_lambda = 1.0
+# Optional selector for decision scalar: "unique" | "absolute" (default unique)
+event_rewards_kind = "unique"
+
+[training.weight_sync]
+enable  = true
+targets = ["policy"]
+weight_sync_interval = 1

synth_ai/demos/demo_task_apps/crafter/grpo_crafter_task_app.py

@@ -0,0 +1,165 @@
+
+"""Compatibility wrapper for the GRPO Crafter task app.
+
+This module now delegates to the shared TaskAppConfig defined in
+`synth_ai.task.apps.grpo_crafter`. It is kept for legacy usage (running the
+file directly or targeting `fastapi_app` from external tooling). Prefer using
+`uvx synth-ai serve grpo-crafter` for local development and testing.
+"""
+
+from __future__ import annotations
+
+import argparse
+from pathlib import Path
+
+from fastapi.exceptions import RequestValidationError
+from fastapi.responses import JSONResponse
+from starlette.requests import Request
+
+from synth_ai.task.apps import ModalDeploymentConfig, registry
+from synth_ai.task.apps.grpo_crafter import build_config
+from synth_ai.task.auth import is_api_key_header_authorized, normalize_environment_api_key
+from synth_ai.task.server import TaskAppConfig, create_task_app, run_task_app
+
+
+APP_ID = "grpo-crafter"
+
+
+_BASE_CONFIG = build_config()
+TASK_APP_CONFIG = TaskAppConfig(
+    app_id="grpo-crafter",
+    name=_BASE_CONFIG.name,
+    description=_BASE_CONFIG.description,
+    base_task_info=_BASE_CONFIG.base_task_info,
+    describe_taskset=_BASE_CONFIG.describe_taskset,
+    provide_task_instances=_BASE_CONFIG.provide_task_instances,
+    rollout=_BASE_CONFIG.rollout,
+    dataset_registry=_BASE_CONFIG.dataset_registry,
+    rubrics=_BASE_CONFIG.rubrics,
+    proxy=_BASE_CONFIG.proxy,
+    routers=_BASE_CONFIG.routers,
+    middleware=_BASE_CONFIG.middleware,
+    app_state=_BASE_CONFIG.app_state,
+    require_api_key=_BASE_CONFIG.require_api_key,
+    expose_debug_env=_BASE_CONFIG.expose_debug_env,
+    cors_origins=_BASE_CONFIG.cors_origins,
+    startup_hooks=_BASE_CONFIG.startup_hooks,
+    shutdown_hooks=_BASE_CONFIG.shutdown_hooks,
+)
+
+try:
+    _REGISTERED_ENTRY = registry.get(APP_ID)
+except Exception:  # pragma: no cover - registry unavailable in some contexts
+    MODAL_DEPLOYMENT: ModalDeploymentConfig | None = None
+    ENV_FILES: tuple[str, ...] = ()
+else:
+    MODAL_DEPLOYMENT = _REGISTERED_ENTRY.modal
+    ENV_FILES = tuple(_REGISTERED_ENTRY.env_files)
+
+
+def build_task_app_config() -> TaskAppConfig:
+    """Return a fresh TaskAppConfig for this wrapper."""
+
+    return TASK_APP_CONFIG.clone()
+
+
+def fastapi_app():
+    """Return the FastAPI application for Modal or other ASGI hosts."""
+
+    app = create_task_app(build_task_app_config())
+
+    # Replace default health endpoints so we can permit soft auth failures and log 422s.
+    filtered_routes = []
+    for route in app.router.routes:
+        path = getattr(route, "path", None)
+        methods = getattr(route, "methods", set()) or set()
+        if path in {"/health", "/health/rollout"} and "GET" in methods:
+            continue
+        filtered_routes.append(route)
+    app.router.routes = filtered_routes
+
+    def _log_env_key_prefix(source: str, env_key: str | None) -> str | None:
+        if not env_key:
+            return None
+        prefix = env_key[: max(1, len(env_key) // 2)]
+        print(f"[{source}] expected ENVIRONMENT_API_KEY prefix: {prefix}")
+        return prefix
+
+    @app.get("/health")
+    async def health(request: Request):
+        env_key = normalize_environment_api_key()
+        if not env_key:
+            return JSONResponse(
+                status_code=503,
+                content={"status": "unhealthy", "detail": "Missing ENVIRONMENT_API_KEY"},
+            )
+        if not is_api_key_header_authorized(request):
+            prefix = _log_env_key_prefix("health", env_key)
+            content = {"status": "healthy", "authorized": False}
+            if prefix:
+                content["expected_api_key_prefix"] = prefix
+            return JSONResponse(status_code=200, content=content)
+        return {"status": "healthy", "authorized": True}
+
+    @app.get("/health/rollout")
+    async def health_rollout(request: Request):
+        env_key = normalize_environment_api_key()
+        if not env_key:
+            return JSONResponse(
+                status_code=503,
+                content={"status": "unhealthy", "detail": "Missing ENVIRONMENT_API_KEY"},
+            )
+        if not is_api_key_header_authorized(request):
+            prefix = _log_env_key_prefix("health/rollout", env_key)
+            content = {"status": "healthy", "authorized": False}
+            if prefix:
+                content["expected_api_key_prefix"] = prefix
+            return JSONResponse(status_code=200, content=content)
+        return {"ok": True, "authorized": True}
+
+    @app.exception_handler(RequestValidationError)
+    async def _on_validation_error(request: Request, exc: RequestValidationError):
+        try:
+            hdr = request.headers
+            snapshot = {
+                "path": str(getattr(request, "url").path),
+                "have_x_api_key": bool(hdr.get("x-api-key")),
+                "have_x_api_keys": bool(hdr.get("x-api-keys")),
+                "have_authorization": bool(hdr.get("authorization")),
+                "errors": exc.errors()[:5],
+            }
+            print("[422] validation", snapshot, flush=True)
+        except Exception:
+            pass
+        return JSONResponse(
+            status_code=422,
+            content={"status": "invalid", "detail": exc.errors()[:5]},
+        )
+
+    return app
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Run the Crafter task app locally")
+    parser.add_argument("--host", default="0.0.0.0")
+    parser.add_argument("--port", type=int, default=8001)
+    parser.add_argument("--reload", action="store_true", help="Enable uvicorn autoreload")
+    parser.add_argument(
+        "--env-file",
+        action="append",
+        default=[],
+        help="Additional .env files to load before startup",
+    )
+    args = parser.parse_args()
+
+    default_env = Path(__file__).resolve().parents[4] / "backend" / ".env.dev"
+    env_files = [str(default_env)] if default_env.exists() else []
+    env_files.extend(args.env_file or [])
+
+    run_task_app(
+        build_task_app_config,
+        host=args.host,
+        port=args.port,
+        reload=args.reload,
+        env_files=env_files,
+    )

synth_ai/task/apps/__init__.py

@@ -2,7 +2,11 @@ from __future__ import annotations
 
 """Registry for Task Apps exposed via the shared FastAPI harness."""
 
+import importlib
+import os
+import sys
 from dataclasses import dataclass, field
+from pathlib import Path
 from typing import Callable, Dict, Iterable, List, Sequence
 
 from ..server import TaskAppConfig
@@ -64,6 +68,11 @@ class TaskAppRegistry:
 
     def __iter__(self) -> Iterable[TaskAppEntry]:
         return iter(self.list())
+    
+    def clear(self) -> None:
+        """Clear all registered task apps."""
+        self._entries.clear()
+        self._alias_to_id.clear()
 
 
 registry = TaskAppRegistry()
@@ -73,16 +82,48 @@ def register_task_app(*, entry: TaskAppEntry) -> None:
     registry.register(entry)
 
 
-
-# Register built-in task apps
-try:
-    from . import grpo_crafter  # noqa: F401
-except Exception:
-    # Defer import errors so CLI can report missing deps gracefully
-    pass
-
-try:
-    from . import math_single_step  # noqa: F401
-except Exception:
-    # Defer import errors so CLI can report missing deps gracefully
-    pass
+def discover_task_apps_from_cwd() -> None:
+    """Discover and register task apps from the current working directory and subdirectories."""
+    cwd = Path.cwd()
+    
+    # Look for task app files in common patterns
+    patterns = [
+        "**/task_app/*.py",
+        "**/task_apps/*.py", 
+        "**/*_task_app.py",
+        "**/grpo_crafter.py",
+        "**/math_single_step.py",
+    ]
+    
+    discovered_files = []
+    for pattern in patterns:
+        discovered_files.extend(cwd.glob(pattern))
+    
+    # Add current directory to Python path temporarily
+    original_path = sys.path.copy()
+    try:
+        sys.path.insert(0, str(cwd))
+        
+        for file_path in discovered_files:
+            if file_path.name.startswith('__'):
+                continue
+                
+            # Convert file path to module name
+            relative_path = file_path.relative_to(cwd)
+            module_parts = list(relative_path.parts[:-1]) + [relative_path.stem]
+            module_name = '.'.join(module_parts)
+            
+            try:
+                # Import the module to trigger registration
+                importlib.import_module(module_name)
+            except Exception as exc:
+                # Silently skip modules that can't be imported
+                # This allows for graceful handling of missing dependencies
+                continue
+                
+    finally:
+        sys.path[:] = original_path
+
+
+# Note: Task apps are now discovered dynamically by the CLI, not auto-registered
+# This allows for better separation between SDK and example-specific implementations

{synth_ai-0.2.9.dev2.dist-info → synth_ai-0.2.9.dev4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: synth-ai
-Version: 0.2.9.dev2
+Version: 0.2.9.dev4
 Summary: RL as a service SDK - Core AI functionality and tracing
 Author-email: Synth AI <josh@usesynth.ai>
 License-Expression: MIT

{synth_ai-0.2.9.dev2.dist-info → synth_ai-0.2.9.dev4.dist-info}/RECORD

@@ -1,6 +1,103 @@
+examples/analyze_semantic_words.sh,sha256=z-3qJBAlQuMrfRzoszofle_2b3Fy79rymvEAcoBQGXU,652
+examples/crafter_debug_render.py,sha256=6Zak0RQZPXYy88v5dcon-XEdt01_NI027o1v2Fx4nhk,6178
+examples/run_crafter_demo.sh,sha256=7FNvooSgq-ezccGy5j_h_uRXObiQtcnybPcTwaVGDpo,392
+examples/common_old/backend.py,sha256=ygPtZREi9W2JQI7xI0J1jz3VaWBgILTfgpgFLVGMEPY,538
+examples/evals_old/README.md,sha256=Te1TsgcOyDBf-ICdHkA12XBd4ClQXGFj8uytbggto1s,3503
+examples/evals_old/__init__.py,sha256=6E7OuWJsBiG7USgsR5uFGeU1JYZ6TFreUFMwgBxrJ6A,189
+examples/evals_old/compare_models.py,sha256=bCqtIKkR06u5pJHY65496ImokYlIEOMrtWFT_T_b3dM,43883
+examples/evals_old/example_log.md,sha256=DgdmUkU0N_g2WhobwCqkpw1Itjq8E7wS2CCcLsLSLJw,9470
+examples/evals_old/run_demo.sh,sha256=UwygYAn-LDdq-XSjygrDSs30UykQX5EO9Q5atqspc0Q,4625
+examples/evals_old/trace_analysis.py,sha256=uIImBarDqo81zJOcFxjCusZg9YHsARs09q0Y5l6-iXs,10686
+examples/finetuning_old/_backup_synth_qwen/config.toml,sha256=7bs3-AS23Cu9nbTYYurlk1fMJPF5LuYPD1Vumyt3XK4,734
+examples/finetuning_old/_backup_synth_qwen/example_log.md,sha256=1CG-1dZsIzdWDVLrTYBO3vld_b8o9sqG_-rDEpTcA_I,12246
+examples/finetuning_old/_backup_synth_qwen/filter_traces.py,sha256=aFGy0-KoPQyIbk4cJBh4wnqzuqgCEVsrFbEor454ktY,2045
+examples/finetuning_old/_backup_synth_qwen/filter_traces_achievements.py,sha256=bploSuwCeLelHytJcVoDKkRyldvrFfZMpTVfWrwEzcg,9359
+examples/finetuning_old/_backup_synth_qwen/purge_v3_traces.py,sha256=qGHwWA0DKBCNs8rB39NHwpTFe8izNNYQjtyHVrzWYTk,3406
+examples/finetuning_old/_backup_synth_qwen/react_agent_lm.py,sha256=sYTauRlPdsZeA17YNffjdWyHUZeojRUFHgQ4bu27TvQ,80387
+examples/finetuning_old/_backup_synth_qwen/readme.md,sha256=2M7m1VqHNCEDOPmEWC0NsyXMFn0rB3bjMX4uNA5GOp0,1763
+examples/finetuning_old/_backup_synth_qwen/run_crafter_qwen4b.py,sha256=gUrjpMtLRJCuM4UMY9k-8gKqDoY4nyK4aY5G4rC9exw,4353
+examples/finetuning_old/_backup_synth_qwen/run_demo.sh,sha256=bN3TdD2Bowdu2yFrcKkN1rDqeSjivSNS63fO5tAjB6o,7239
+examples/finetuning_old/_backup_synth_qwen/sft_kickoff.py,sha256=oFyK6LQDQ5SbsTJXJUzyUTPklWOZwdw_VyO3SR7IXSw,4223
+examples/finetuning_old/synth_qwen_v1/README.md,sha256=ZWYfjax9iyrljAwUqiZwNHqtJAajz1G75rSiBNTveHo,4322
+examples/finetuning_old/synth_qwen_v1/filter_traces.py,sha256=aFGy0-KoPQyIbk4cJBh4wnqzuqgCEVsrFbEor454ktY,2045
+examples/finetuning_old/synth_qwen_v1/filter_traces_achievements.py,sha256=bploSuwCeLelHytJcVoDKkRyldvrFfZMpTVfWrwEzcg,9359
+examples/finetuning_old/synth_qwen_v1/finetune.py,sha256=6dLJjR3T-QOCgyOwz9jiucKuCz-So_eN88Z8ZwChJiU,1204
+examples/finetuning_old/synth_qwen_v1/hello_ft_model.py,sha256=G4JLMmqGYBsV2rEfguOU-ZZlryE2bVO7vGxoxFBi3Jg,2286
+examples/finetuning_old/synth_qwen_v1/infer.py,sha256=q9ykYhlP7Rrtb8RSK0qn6y8Tm63hax6rBpsFwtTMocY,918
+examples/finetuning_old/synth_qwen_v1/poll.py,sha256=AJx2StdxkZBLnZPNupBSoIc4BHCifEmybPt5pb57QqA,1228
+examples/finetuning_old/synth_qwen_v1/prepare_data.py,sha256=1UMP23z-TkJOGYCEEJqC9980_k2l7x5cpPSpEUWykx0,832
+examples/finetuning_old/synth_qwen_v1/purge_v3_traces.py,sha256=qGHwWA0DKBCNs8rB39NHwpTFe8izNNYQjtyHVrzWYTk,3406
+examples/finetuning_old/synth_qwen_v1/react_agent_lm.py,sha256=NYjf5Vqyi2Ri_oC6etDYmCE4Am9kK4aF3d1wqDut6j8,80577
+examples/finetuning_old/synth_qwen_v1/run_crafter_sft_job.py,sha256=-bpXjFPp00JCEE5T7TCeRARZjQzCTmcpd0nH4y-sDho,7878
+examples/finetuning_old/synth_qwen_v1/run_ft_job.py,sha256=-OOt2dJNw5dwYq5lF7XXZkuY5Qsj1Qnl5dKulZvDoSA,8561
+examples/finetuning_old/synth_qwen_v1/upload_data.py,sha256=bYEFbsaKGt6nZ6kQKNnx7AklFmE3Hxp9d6r6xsh8PeE,882
+examples/finetuning_old/synth_qwen_v1/util.py,sha256=v_4c2JQNRG7oIHIKOkXLZXg42CMqs4-yav2MuId7MpY,5801
+examples/rl/README.md,sha256=qzv-URBhEr3r4ipEyh-mP9CiCIz_KbckZWlfXdWbafA,6560
+examples/rl/download_dataset.py,sha256=XZwRbASLN4rjvfwqvet-sdhOojcEjCAvXWFNOSUZhWc,2515
+examples/rl/run_eval.py,sha256=TlUlTHJ9dNOxZuyTF4A6F6JpSghvQ6rqC3yk4271BKw,14973
+examples/rl/run_rl_and_save.py,sha256=Pe-zQzLrdO6CbRTt3vMslRlACMmLXQSUTr5Ow_DVh6k,3160
+examples/rl/configs/eval_base_qwen.toml,sha256=EntLk6oScfan4-CiK0MeqO9vu-ZFBTo97tjlNSQOhd8,323
+examples/rl/configs/eval_rl_qwen.toml,sha256=o07ZvAxjj_ejj3zbjESmtpIOh6QqkwpTD2ZUL9Lzx5A,247
+examples/rl/configs/rl_from_base_qwen.toml,sha256=KDDtpvVikHZCcyUKYtgWq9XAfAEY5vRADPpcxpkdVsg,605
+examples/rl/configs/rl_from_base_qwen17.toml,sha256=CLfuzZaTvpqezPrpOy03ZKvR6D3tZ0vExOsyvdn4ETo,1346
+examples/rl/configs/rl_from_ft_qwen.toml,sha256=7s5HK_YM7zVnvjJavvfai8Nc_eUx_70cgHeWN19vXXM,638
+examples/rl/task_app/README.md,sha256=oHfcMF9V_CPLnGbrarTRRIQpQ1wqV1zL74KWUZtcKwI,802
+examples/rl/task_app/math_single_step.py,sha256=DIucCB5MC_1doIxfJxH6qXVsSijqh78cz-vQaKjFDEk,30379
+examples/rl/task_app/math_task_app.py,sha256=e8inAZsLJxcAMtjwDVzvgb9-x9DYds4OKugthtm_riw,4180
+examples/rl_old/task_app.py,sha256=ctVxuMKPaEKuf46fmSi2tb2bXe55bvhpxA5xTAYxwh4,47078
+examples/warming_up_to_rl/analyze_trace_db.py,sha256=ywtQj-p2vsGQ8ikr4zXQY18YDKsbEnCRcz1MkJZot68,14424
+examples/warming_up_to_rl/export_trace_sft.py,sha256=dreS63IyvpEjm2wVOGfPKIsE67bX0sui4WVS8aq46yA,20278
+examples/warming_up_to_rl/groq_test.py,sha256=McqwDlKc2YZXmJQ9sI27dpdUl5wqn8xEDNi7V58ltl4,3089
+examples/warming_up_to_rl/manage_secrets.py,sha256=ySZ6V_AXOWpFzjVSpxA-TaBWkhpWeIiC5jM6K3FOrmQ,4372
+examples/warming_up_to_rl/readme.md,sha256=viacw40ZG-u-duqBd2RN5mG63__h2x1w37DPnKqpYV8,6169
+examples/warming_up_to_rl/run_eval.py,sha256=llgsyx7E8pi7egn0qcDONzldDXShP6_Ntp-qTjQuNQQ,19078
+examples/warming_up_to_rl/run_fft_and_save.py,sha256=DPeFnGJ2U2lB0azJ9CcN1c5pn0lSOfb6qYgtSGi0cEw,13426
+examples/warming_up_to_rl/run_local_rollout.py,sha256=V6uMFZkfnh6ndndNq-rPnTkzWr3gNVWLVNmQlWb6Oik,8164
+examples/warming_up_to_rl/run_local_rollout_modal.py,sha256=XxKZv_zE9zWFrt99N1tP6X8TfB883pKWsvDUUsHW1oc,6798
+examples/warming_up_to_rl/run_local_rollout_parallel.py,sha256=_p11RDzH6DVVzanML9VKQahDxuKRH5PwwGsBgzo7DSE,12951
+examples/warming_up_to_rl/run_local_rollout_traced.py,sha256=_UL46Rdj_oo8gEnyBfPfVkvCj7VoU99eahn3_i_-pMI,13656
+examples/warming_up_to_rl/run_rl_and_save.py,sha256=dpFr42Vk03jTlDPyOUcDbu8zGJwGsMW4PKKPuBciAJs,3649
+examples/warming_up_to_rl/run_rollout_remote.py,sha256=iIW5FI5cFDcnt80Tjh-uqL_O4uVoIqdnqfIjjLjFGZg,4769
+examples/warming_up_to_rl/configs/crafter_fft.toml,sha256=Hbp2tVhaGxRAip1vwhID73rCIO6bi_yI-gUen-oylcA,1137
+examples/warming_up_to_rl/configs/crafter_fft_4b.toml,sha256=q_cnU3P-eGG_VFOepw9IA1U-m7L-uJH37EUFR3mNWBI,1358
+examples/warming_up_to_rl/configs/eval_fft_qwen4b.toml,sha256=YP4HLWDh6iIvw6McPXw5kK1RUFQF4dvKP4yH5bHT5nI,678
+examples/warming_up_to_rl/configs/eval_groq_qwen32b.toml,sha256=zQi31JYa83kW-ceEqDZi-7oajsCmEPrlJR57zN5ygO8,340
+examples/warming_up_to_rl/configs/eval_modal_qwen4b.toml,sha256=6eeU1GVvK1cYSEuGXk-AhOwJLgRcf74CTOI5XlqNYBc,817
+examples/warming_up_to_rl/configs/rl_from_base_qwen4b.toml,sha256=qVSypYOMUd8g6pmiovi7nsgk4jgMBjJIORpIsrmNV4U,1644
+examples/warming_up_to_rl/configs/rl_from_ft.toml,sha256=d1cIoLeC80NgOjn0Wohk0a5IXE_ImHVgMsxWPkyAFKQ,1381
+examples/warming_up_to_rl/old/event_rewards.md,sha256=gHJd3ZeYOnj4xPXt-7sSJamgOaJQ-BpfdaF-CKJK3-0,13450
+examples/warming_up_to_rl/old/notes.md,sha256=Y9Zs_tUb2Y6kv0MmGe-kAvGM9zCtEDY3Ccf5j7PoFGU,4468
+examples/warming_up_to_rl/task_app/README.md,sha256=kqDPpv7f0Oh0CoH4qSXqZoKXNIh8guNpxHrELW0z6RY,1346
+examples/warming_up_to_rl/task_app/grpo_crafter.py,sha256=Cx_uNlo1hXpN5VO72O5MdBSz0Z8CZNfhlhbm868lTmg,15898
+examples/warming_up_to_rl/task_app/grpo_crafter_task_app.py,sha256=lMfIcWpJdXMdQyozLAaCeK9dx2D1LPNSav2I2zG7Z9I,6046
+examples/warming_up_to_rl/task_app/synth_envs_hosted/README.md,sha256=kJaN1do8V4XM2_g51WMI3edCDpv5zEw_nrMFtEwO1SQ,4614
+examples/warming_up_to_rl/task_app/synth_envs_hosted/__init__.py,sha256=_zdnpK5Dl26o0-CTcljBBRfdwTy4o60aOLhex59VE6U,120
+examples/warming_up_to_rl/task_app/synth_envs_hosted/branching.py,sha256=SlCgKMg8_quH8bIJSMKlkommz36XvngVvgzrjRR1SBs,5393
+examples/warming_up_to_rl/task_app/synth_envs_hosted/environment_routes.py,sha256=W8MWFhRor65u0lp6FhOXJjc-j5W5ooEwWwF2UnCg1KE,50069
+examples/warming_up_to_rl/task_app/synth_envs_hosted/hosted_app.py,sha256=QMQHxi6glj9cnTJc6F8H7ivv2x8Mer5WQrR5Vs-xv94,7776
+examples/warming_up_to_rl/task_app/synth_envs_hosted/main.py,sha256=0g7OZl6CnrddETD1DOAQZxz_P1fZR0F7kuCeZb4BRHg,2510
+examples/warming_up_to_rl/task_app/synth_envs_hosted/policy_routes.py,sha256=qP3E9XAhHihKyz1l44FD4Zb5zoZt8v6m5HNhOLe4fxk,43685
+examples/warming_up_to_rl/task_app/synth_envs_hosted/registry.py,sha256=pMVwiutZe5DcPXdNmIhRJGwxIz3Xn3FtdkKKqrOEdOM,5613
+examples/warming_up_to_rl/task_app/synth_envs_hosted/rollout.py,sha256=506KV0x0oOajTuNVVWLUxeIXG2YaZjWwfgbVg2EorcA,71477
+examples/warming_up_to_rl/task_app/synth_envs_hosted/test_agents.py,sha256=PRkQlVKGfn2-w4EOTTHc8T-tqFW6m21mS7BII6TUUd4,5599
+examples/warming_up_to_rl/task_app/synth_envs_hosted/test_service.py,sha256=PAYPP0tWU0cQUUxJuAYbDwvWeGjAcPFRHsW2vG3vOpg,5228
+examples/warming_up_to_rl/task_app/synth_envs_hosted/test_stepwise_rewards.py,sha256=OfzZ18_bykLll6-4-2-OZI4a2wFx68hnTxufZeFE5t4,1836
+examples/warming_up_to_rl/task_app/synth_envs_hosted/utils.py,sha256=Qcxfa_WASxbUCbAKejiZB6QIl8eJeeIrFPt5GU-Zb6E,2013
+examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/__init__.py,sha256=5e-BmaXi_5EGcqF2hEGsnbtkHsNvPNMTX9wJ3yiz3XQ,34
+examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/__init__.py,sha256=nTmSVzOfRUnjxEN1-IHjxuvPHij-AdRu_NZoH6Ozv2M,197
+examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/app.py,sha256=MnaRrqkxxeOaHLD-ulH5P1BauDs3tWKdxM0n85jfp6g,19
+examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/environment.py,sha256=9OzSAPO5HMhMLQ2cfJMs6TO8-r4uGSw_JQgztu1MXGM,20112
+examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/policy.py,sha256=Bf7ypw2VqPUtiIycAP_irglYtf7sGvAWIvvIZsok-qI,19373
+examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/react_agent.py,sha256=dHASD8zbinK32mE4dEMQqmQpGjaomFbJQ_yIw8vYOrY,6157
+examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/shared.py,sha256=2ampoR9RVrh7T05nq-z4hg2KnSGVBo5A1ESYMae780s,10180
+examples/warming_up_to_rl/task_app/synth_envs_hosted/envs/crafter/tools.py,sha256=-jVxok4pkDm3t9VwuUivm0y4xmYBq16wqOrSpAHoT6Q,1787
+examples/warming_up_to_rl/task_app/synth_envs_hosted/inference/__init__.py,sha256=6O23CobxVe8fkuGmWDPhg4Kzf1Q6pmtQZIad8DHubjI,178
+examples/warming_up_to_rl/task_app/synth_envs_hosted/inference/openai_client.py,sha256=3lIubZOcCslZTu1dK8qt76yB68l9RAx9WFKy6_9BaVk,23807
+examples/warming_up_to_rl/task_app/synth_envs_hosted/storage/__init__.py,sha256=55vZdcz3qI1wt4qfNyC1LSFTPm6wKM7oF5iyNnR6Lvg,133
+examples/warming_up_to_rl/task_app/synth_envs_hosted/storage/volume.py,sha256=dxAHrHnOa-_pnbHrtLYdD1EwYX8la8LwR5B6kOmt_n8,6953
 synth_ai/__init__.py,sha256=NixuXddy4lS2Wmj0F8eMt0HS_oYCTnq3iVVq5VYwWIc,1341
 synth_ai/__main__.py,sha256=Kh1xBKkTE5Vs2qNMtDuuOXerHUptMcOiF3YziOpC6DA,146
-synth_ai/demo_registry.py,sha256=PhBV3oQpNDTPdPqnUcRchOyYB4BZlQkbhPZfIneLskk,8485
+synth_ai/demo_registry.py,sha256=pH-Pyrocp2vNBcw7J80Nu_525nBtI5G_dC4d4mQDYl8,8531
 synth_ai/handshake.py,sha256=uzoTOpkf9JQgsyKWrlx8gjfQmK3HpqFQAZY1gZDtiIo,3735
 synth_ai/http.py,sha256=lqjFXDmAP_xgfywK_rDSOVxuMy4rDH9S3Rtu9k1tLmk,1028
 synth_ai/http_client.py,sha256=_9J8rUGoItUMnJLGZw7r0uXiJeLWR939kByRkvtP1XM,4429
@@ -8,8 +105,8 @@ synth_ai/install_sqld.sh,sha256=AMBhlfq661PxeTTc6D4K_Nei_qwMvA84ei4NhQzmUUk,928
 synth_ai/api/train/__init__.py,sha256=aBwlmrj1HWVwDcvUrX4TqpS0BgvkE7Pv7npoIZmtTFU,118
 synth_ai/api/train/builders.py,sha256=Fe684cGh-CQGPXydESCOjTkQpxbTJb47rVYKT8uONTs,6045
 synth_ai/api/train/cli.py,sha256=OyS6-NU1BUVitjUYYCtQenLXmprU9dDqYOR6tfeW7B0,17897
-synth_ai/api/train/config_finder.py,sha256=iH4a-_6rtGvhxBNINag5WivEX2W-Jb1_YysjN-ooOYM,5311
-synth_ai/api/train/env_resolver.py,sha256=PLvuorBg3ugxZUsfDeZAMrqmqEt56aGRInmhuHD6z8g,10715
+synth_ai/api/train/config_finder.py,sha256=8HwyVRZ3WuXU2c7MdJgQVT29C-53zOWGcaucbkMso6c,5194
+synth_ai/api/train/env_resolver.py,sha256=PoXGD-Gpifs8FuSGF_xKNIA90QrUnLW8S5zMaUGm_yg,11451
 synth_ai/api/train/pollers.py,sha256=EbkoV601aXEpqgfjNuugivtDooiRgOxBXSYZZ0Muj24,2114
 synth_ai/api/train/task_app.py,sha256=Pk-bCqBEkjgbf9tzFeRik5uC0No_2Y536TSiLcJ47h0,6419
 synth_ai/api/train/utils.py,sha256=rkouZjOFvY9WKXIuG-rlJhH9eyLLxi_ID6dj0JMNSmI,7213
@@ -23,7 +120,7 @@ synth_ai/cli/recent.py,sha256=mHhM-QrR_MfjfKSzBvvPUEC-lkXTWUZrQwqYTmb2x0Y,4173
 synth_ai/cli/rl_demo.py,sha256=P09_atVrSTfGUhAs0Obe63erniJ3EDHtm51yL2xBouM,8796
 synth_ai/cli/root.py,sha256=0fuWNO5NeWTSCANzPBfoQsZKe3iUxnJ9hsSWS-SK2UM,11370
 synth_ai/cli/status.py,sha256=M_bt7U58Ubi-q-ZlrIpgCASKq9_k6uMjpx926f6kLLA,4591
-synth_ai/cli/task_apps.py,sha256=gJDoW4aH2HFZK1fLPkCQ4EpVaBq_3lL8DmHzwObtdDo,40070
+synth_ai/cli/task_apps.py,sha256=bpknAGET9vUP6iRHTJcQcA_r4TCkqsP-QMIXayc7VIo,50723
 synth_ai/cli/traces.py,sha256=_QBdCR92u0Gv51U4DH0Ws1d5yCrbJRpaYKe7pmcHrHs,6484
 synth_ai/cli/watch.py,sha256=HBKbAcpUkkPhGvsPRofckbu8oILiVqp35NXHkIEpTTc,17808
 synth_ai/compound/cais.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -34,6 +131,10 @@ synth_ai/demos/core/__init__.py,sha256=A2FjhY7KXGtyzdQXqeTPCkEhHfrH-eQg6bvP8HaYh
 synth_ai/demos/core/cli.py,sha256=5z89ykvJAP-MipT-RYx7BXwTwi8nIAyUb-RcPDpXL5w,57520
 synth_ai/demos/demo_task_apps/__init__.py,sha256=LmNLB5oHncmVmavbLb6_1fsFYoNxijMd3ksLScBMxiw,243
 synth_ai/demos/demo_task_apps/core.py,sha256=Eu7gp0VtZ9tE1HPLG14-pkjC1cD_7brsdl2IRbdSBts,14764
+synth_ai/demos/demo_task_apps/crafter/__init__.py,sha256=3SnNZTzBjGR9eudStcww259vPmzoFBHJL-M0GDUD7Qo,24
+synth_ai/demos/demo_task_apps/crafter/grpo_crafter_task_app.py,sha256=SfP7YbGyYDpoY4ZWyMiUSeQAjintKPAkJRZz3U2951U,6064
+synth_ai/demos/demo_task_apps/crafter/configs/crafter_fft_4b.toml,sha256=q_cnU3P-eGG_VFOepw9IA1U-m7L-uJH37EUFR3mNWBI,1358
+synth_ai/demos/demo_task_apps/crafter/configs/rl_from_base_qwen4b.toml,sha256=qVSypYOMUd8g6pmiovi7nsgk4jgMBjJIORpIsrmNV4U,1644
 synth_ai/demos/demo_task_apps/math/__init__.py,sha256=WBzpZwSn7pRarBmhopQi34i9bEm05-71eM3siboOavY,43
 synth_ai/demos/demo_task_apps/math/_common.py,sha256=SgtVW1pne4pgwGS2gYYQWkmG9BvU2sQTYzlncmUJ0NM,533
 synth_ai/demos/demo_task_apps/math/app.py,sha256=gNopoAhwM0vzdKuCa7AwQqSwiV2xagrjMxMH9YIniv4,1160
@@ -370,9 +471,7 @@ synth_ai/task/server.py,sha256=bYrqnwtbGEdI_lieBMslgh-sUwdyzEbbHnmjovrRef8,15187
 synth_ai/task/tracing_utils.py,sha256=kro--A6BTCVReLMNRX4_v2arLVXYIQNKtn3RDMMrOmE,2400
 synth_ai/task/validators.py,sha256=IGE9zTjHYXOehwakMkcOAaDLSaHw_0Tp8uzL2ydCZ9U,361
 synth_ai/task/vendors.py,sha256=zG-qeP2OC1s5kJECZdf02QBvn-v_qHcz-rG0C8Ws0wA,1664
-synth_ai/task/apps/__init__.py,sha256=M0DeEhvUhyXh1A_AnVSBXTeJY75c7BVsW0A_1vxL_08,2677
-synth_ai/task/apps/grpo_crafter.py,sha256=eCxD9eHYLIkvo4mFhlIY14u-Ipp_zmHj6wvg08Vu58Y,15809
-synth_ai/task/apps/math_single_step.py,sha256=jhoArV52jlWxN6HO2XYTnrLC3aWF23G1B9PRVx5LkVM,30278
+synth_ai/task/apps/__init__.py,sha256=yLY31OII4Hbt9ibTj1vmxVCd9JBluCGh6Xgy6biKEIs,4151
 synth_ai/tracing/__init__.py,sha256=0Yy1YDMe_Duw976yu0HL1cbqPWdZEvtgEdtjDguNvcc,781
 synth_ai/tracing_v1/__init__.py,sha256=uV6qf8_rJTxRx6tCsXvqnjHhA1mR0im2rANuh0McrHA,930
 synth_ai/tracing_v3/__init__.py,sha256=9lKM-blbXo6Sk1oBpyYayjMVU43f9Y_35M1OvRynWoU,3251
@@ -436,9 +535,9 @@ synth_ai/v0/tracing_v1/events/manage.py,sha256=ZDXXP-ZwLH9LCsmw7Ru9o55d7bl_diPtJ
 synth_ai/v0/tracing_v1/events/scope.py,sha256=BuBkhSpVHUJt8iGT9HJZF82rbb88mQcd2vM2shg-w2I,2550
 synth_ai/v0/tracing_v1/events/store.py,sha256=0342lvAcalyJbVEIzQFaPuMQGgwiFm7M5rE6gr-G0E8,9041
 synth_ai/zyk/__init__.py,sha256=htVLnzTYQ5rxzYpzSYBm7_o6uNKZ3pB_PrqkBrgTRS4,771
-synth_ai-0.2.9.dev2.dist-info/licenses/LICENSE,sha256=ynhjRQUfqA_RdGRATApfFA_fBAy9cno04sLtLUqxVFM,1069
-synth_ai-0.2.9.dev2.dist-info/METADATA,sha256=THCYAnIiKaYkPjSZDpNfSvkWdGO11WRUT2pT3fbOcS8,5200
-synth_ai-0.2.9.dev2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-synth_ai-0.2.9.dev2.dist-info/entry_points.txt,sha256=Neq-3bT7TAijjgOIR77pKL-WYg6TWBDeO8pp_nL4vGY,91
-synth_ai-0.2.9.dev2.dist-info/top_level.txt,sha256=fBmtZyVHuKaGa29oHBaaUkrUIWTqSpoVMPiVdCDP3k8,9
-synth_ai-0.2.9.dev2.dist-info/RECORD,,
+synth_ai-0.2.9.dev4.dist-info/licenses/LICENSE,sha256=ynhjRQUfqA_RdGRATApfFA_fBAy9cno04sLtLUqxVFM,1069
+synth_ai-0.2.9.dev4.dist-info/METADATA,sha256=BH5A-8mU_wP4Sid2eqWcFQu6cGs198X5_DcmFFKON8o,5200
+synth_ai-0.2.9.dev4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+synth_ai-0.2.9.dev4.dist-info/entry_points.txt,sha256=Neq-3bT7TAijjgOIR77pKL-WYg6TWBDeO8pp_nL4vGY,91
+synth_ai-0.2.9.dev4.dist-info/top_level.txt,sha256=1moNHgctEUJ3F3eH3V-7FSMb2iTTze1V13dj1R04oUY,18
+synth_ai-0.2.9.dev4.dist-info/RECORD,,

{synth_ai-0.2.9.dev2.dist-info → synth_ai-0.2.9.dev4.dist-info}/top_level.txt

@@ -1 +1,2 @@
+examples
 synth_ai