synth-ai 0.2.4.dev7__py3-none-any.whl → 0.2.4.dev9__py3-none-any.whl

synth_ai/tracing_v3/turso/manager.py

@@ -30,6 +30,7 @@ import pandas as pd
 from sqlalchemy import select, text, update
 from sqlalchemy.exc import IntegrityError
 from sqlalchemy.ext.asyncio import AsyncEngine, AsyncSession, create_async_engine
+from sqlalchemy import event
 from sqlalchemy.orm import selectinload, sessionmaker
 from sqlalchemy.pool import NullPool
 
@@ -59,6 +60,12 @@ from .models import (
 from .models import (
     SessionTrace as DBSessionTrace,
 )
+from .models import (
+    OutcomeReward as DBOutcomeReward,
+)
+from .models import (
+    EventReward as DBEventReward,
+)
 
 logger = logging.getLogger(__name__)
 
@@ -125,6 +132,18 @@ class AsyncSQLTraceManager:
                     connect_args=connect_args,
                     echo=CONFIG.echo_sql,
                 )
+                # Ensure PRAGMA foreign_keys=ON for every connection
+                try:
+                    @event.listens_for(self.engine.sync_engine, "connect")
+                    def _set_sqlite_pragma(dbapi_connection, connection_record):  # type: ignore[no-redef]
+                        try:
+                            cursor = dbapi_connection.cursor()
+                            cursor.execute("PRAGMA foreign_keys=ON")
+                            cursor.close()
+                        except Exception:
+                            pass
+                except Exception:
+                    pass
             else:
                 connect_args = CONFIG.get_connect_args()
                 engine_kwargs = CONFIG.get_engine_kwargs()
@@ -538,3 +557,202 @@ class AsyncSQLTraceManager:
             self.engine = None
             self.SessionLocal = None
             self._schema_ready = False
+
+    # -------------------------------
+    # Incremental insert helpers
+    # -------------------------------
+
+    async def ensure_session(self, session_id: str, *, created_at: datetime | None = None, metadata: dict[str, Any] | None = None):
+        """Ensure a DB session row exists for session_id."""
+        async with self.session() as sess:
+            result = await sess.execute(select(DBSessionTrace).where(DBSessionTrace.session_id == session_id))
+            existing = result.scalar_one_or_none()
+            if existing:
+                return
+            row = DBSessionTrace(
+                session_id=session_id,
+                created_at=created_at or datetime.utcnow(),
+                num_timesteps=0,
+                num_events=0,
+                num_messages=0,
+                session_metadata=metadata or {},
+            )
+            sess.add(row)
+            await sess.commit()
+
+    async def ensure_timestep(self, session_id: str, *, step_id: str, step_index: int, turn_number: int | None = None, started_at: datetime | None = None, completed_at: datetime | None = None, metadata: dict[str, Any] | None = None) -> int:
+        """Ensure a timestep row exists; return its DB id."""
+        async with self.session() as sess:
+            result = await sess.execute(
+                select(DBSessionTimestep).where(DBSessionTimestep.session_id == session_id, DBSessionTimestep.step_id == step_id)
+            )
+            row = result.scalar_one_or_none()
+            if row:
+                return row.id
+            row = DBSessionTimestep(
+                session_id=session_id,
+                step_id=step_id,
+                step_index=step_index,
+                turn_number=turn_number,
+                started_at=started_at or datetime.utcnow(),
+                completed_at=completed_at,
+                num_events=0,
+                num_messages=0,
+                step_metadata=metadata or {},
+            )
+            sess.add(row)
+            await sess.flush()
+            # increment session num_timesteps
+            await sess.execute(
+                update(DBSessionTrace)
+                .where(DBSessionTrace.session_id == session_id)
+                .values(num_timesteps=DBSessionTrace.num_timesteps + 1)
+            )
+            await sess.commit()
+            return row.id
+
+    async def insert_message_row(self, session_id: str, *, timestep_db_id: int | None, message_type: str, content: str, event_time: float | None = None, message_time: int | None = None, metadata: dict[str, Any] | None = None) -> int:
+        """Insert a message and return its id."""
+        async with self.session() as sess:
+            db_msg = DBMessage(
+                session_id=session_id,
+                timestep_id=timestep_db_id,
+                message_type=message_type,
+                content=content,
+                event_time=event_time,
+                message_time=message_time,
+                message_metadata=metadata or {},
+            )
+            sess.add(db_msg)
+            await sess.flush()
+            # increment session num_messages
+            await sess.execute(
+                update(DBSessionTrace)
+                .where(DBSessionTrace.session_id == session_id)
+                .values(num_messages=DBSessionTrace.num_messages + 1)
+            )
+            await sess.commit()
+            return db_msg.id
+
+    async def insert_event_row(self, session_id: str, *, timestep_db_id: int | None, event: EnvironmentEvent | LMCAISEvent | RuntimeEvent, metadata_override: dict[str, Any] | None = None) -> int:
+        """Insert an event and return its id."""
+        def to_cents(cost: float | None) -> int | None:
+            return int(cost * 100) if cost is not None else None
+
+        event_data: dict[str, Any] = {
+            "session_id": session_id,
+            "timestep_id": timestep_db_id,
+            "system_instance_id": event.system_instance_id,
+            "event_time": event.time_record.event_time,
+            "message_time": event.time_record.message_time,
+            "event_metadata_json": metadata_override or event.metadata or {},
+            "event_extra_metadata": getattr(event, "event_metadata", None),
+        }
+        if isinstance(event, LMCAISEvent):
+            call_records_data = None
+            if getattr(event, "call_records", None):
+                from dataclasses import asdict
+
+                call_records_data = [asdict(record) for record in event.call_records]
+            event_data.update({
+                "event_type": "cais",
+                "model_name": event.model_name,
+                "provider": event.provider,
+                "input_tokens": event.input_tokens,
+                "output_tokens": event.output_tokens,
+                "total_tokens": event.total_tokens,
+                "cost_usd": to_cents(event.cost_usd),
+                "latency_ms": event.latency_ms,
+                "span_id": event.span_id,
+                "trace_id": event.trace_id,
+                "system_state_before": event.system_state_before,
+                "system_state_after": event.system_state_after,
+                "call_records": call_records_data,
+            })
+        elif isinstance(event, EnvironmentEvent):
+            event_data.update({
+                "event_type": "environment",
+                "reward": event.reward,
+                "terminated": event.terminated,
+                "truncated": event.truncated,
+                "system_state_before": event.system_state_before,
+                "system_state_after": event.system_state_after,
+            })
+        elif isinstance(event, RuntimeEvent):
+            event_data.update({
+                "event_type": "runtime",
+                "event_metadata_json": {**(event.metadata or {}), "actions": event.actions},
+            })
+        else:
+            event_data["event_type"] = event.__class__.__name__.lower()
+
+        async with self.session() as sess:
+            db_event = DBEvent(**event_data)
+            sess.add(db_event)
+            await sess.flush()
+            # increment session num_events
+            await sess.execute(
+                update(DBSessionTrace)
+                .where(DBSessionTrace.session_id == session_id)
+                .values(num_events=DBSessionTrace.num_events + 1)
+            )
+            await sess.commit()
+            return db_event.id
+
+    # -------------------------------
+    # Reward helpers
+    # -------------------------------
+
+    async def insert_outcome_reward(self, session_id: str, *, total_reward: int, achievements_count: int, total_steps: int) -> int:
+        async with self.session() as sess:
+            row = DBOutcomeReward(
+                session_id=session_id,
+                total_reward=total_reward,
+                achievements_count=achievements_count,
+                total_steps=total_steps,
+            )
+            sess.add(row)
+            await sess.flush()
+            await sess.commit()
+            return row.id
+
+    async def insert_event_reward(self, session_id: str, *, event_id: int, message_id: int | None = None, turn_number: int | None = None, reward_value: float = 0.0, reward_type: str | None = None, key: str | None = None, annotation: dict[str, Any] | None = None, source: str | None = None) -> int:
+        async with self.session() as sess:
+            row = DBEventReward(
+                event_id=event_id,
+                session_id=session_id,
+                message_id=message_id,
+                turn_number=turn_number,
+                reward_value=reward_value,
+                reward_type=reward_type,
+                key=key,
+                annotation=annotation or {},
+                source=source,
+            )
+            sess.add(row)
+            await sess.flush()
+            await sess.commit()
+            return row.id
+
+    async def get_outcome_rewards(self) -> list[dict[str, Any]]:
+        async with self.session() as sess:
+            result = await sess.execute(select(DBOutcomeReward))
+            rows = result.scalars().all()
+            return [
+                {
+                    "id": r.id,
+                    "session_id": r.session_id,
+                    "total_reward": r.total_reward,
+                    "achievements_count": r.achievements_count,
+                    "total_steps": r.total_steps,
+                    "created_at": r.created_at,
+                }
+                for r in rows
+            ]
+
+    async def get_outcome_rewards_by_min_reward(self, min_reward: int) -> list[str]:
+        async with self.session() as sess:
+            result = await sess.execute(
+                select(DBOutcomeReward.session_id).where(DBOutcomeReward.total_reward >= min_reward)
+            )
+            return [row[0] for row in result.all()]

synth_ai/tracing_v3/turso/models.py

@@ -408,3 +408,56 @@ analytics_views = {
         GROUP BY e.experiment_id
     """,
 }
+
+
+# Reward persistence tables
+
+
+class OutcomeReward(Base):
+    """Episode-level rewards/outcomes per session.
+
+    Stores per-episode summary including total_reward (e.g., unique achievements),
+    achievements_count, and total_steps. Used for filtering episodes by outcome.
+    """
+
+    __tablename__ = "outcome_rewards"
+
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    session_id = Column(String, ForeignKey("session_traces.session_id"), nullable=False)
+    total_reward = Column(Integer, nullable=False)
+    achievements_count = Column(Integer, nullable=False, default=0)
+    total_steps = Column(Integer, nullable=False, default=0)
+    created_at = Column(DateTime, default=func.current_timestamp(), nullable=False)
+
+    __table_args__ = (
+        Index("idx_outcome_rewards_session", "session_id"),
+        Index("idx_outcome_rewards_total", "total_reward"),
+    )
+
+
+class EventReward(Base):
+    """First-class event-level rewards with annotations.
+
+    Links to an event and session. `message_id` is optional.
+    """
+
+    __tablename__ = "event_rewards"
+
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    event_id = Column(Integer, ForeignKey("events.id"), nullable=False)
+    session_id = Column(String, ForeignKey("session_traces.session_id"), nullable=False)
+    message_id = Column(Integer, ForeignKey("messages.id"), nullable=True)
+    turn_number = Column(Integer, nullable=True)
+    reward_value = Column(Float, nullable=False, default=0.0)
+    reward_type = Column(String, nullable=True)  # shaped | sparse | achievement | penalty | evaluator | human
+    key = Column(String, nullable=True)  # e.g., achievement name
+    annotation = Column(JSONText)  # free-form JSON
+    source = Column(String, nullable=True)  # environment | runner | evaluator | human
+    created_at = Column(DateTime, default=func.current_timestamp(), nullable=False)
+
+    __table_args__ = (
+        Index("idx_event_rewards_session", "session_id"),
+        Index("idx_event_rewards_event", "event_id"),
+        Index("idx_event_rewards_type", "reward_type"),
+        Index("idx_event_rewards_key", "key"),
+    )

synth_ai-0.2.4.dev9.dist-info/METADATA

@@ -0,0 +1,91 @@
+Metadata-Version: 2.4
+Name: synth-ai
+Version: 0.2.4.dev9
+Summary: Software for aiding the best and multiplying the will - Core AI functionality and tracing
+Author-email: Synth AI <josh@usesynth.ai>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/synth-laboratories/synth-ai
+Project-URL: Repository, https://github.com/synth-laboratories/synth-ai
+Project-URL: Issues, https://github.com/synth-laboratories/synth-ai/issues
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: python-dotenv>=1.0.1
+Requires-Dist: requests>=2.32.3
+Requires-Dist: urllib3>=2.3.0
+Requires-Dist: tqdm>=4.66.4
+Requires-Dist: jsonschema>=4.23.0
+Requires-Dist: backoff>=2.0.0
+Requires-Dist: typing_extensions>=4.0.0
+Requires-Dist: openai>=1.99.0
+Requires-Dist: anthropic>=0.42.0
+Requires-Dist: langfuse<3.0.0,>=2.53.9
+Requires-Dist: opentelemetry-api<1.27.0,>=1.26.0
+Requires-Dist: opentelemetry-sdk<1.27.0,>=1.26.0
+Requires-Dist: diskcache>=5.6.3
+Requires-Dist: groq>=0.30.0
+Requires-Dist: google-genai>=1.26.0
+Requires-Dist: together>=1.5.21
+Requires-Dist: mistralai>=1.9.2
+Requires-Dist: fastapi>=0.115.12
+Requires-Dist: uvicorn>=0.34.2
+Requires-Dist: numpy>=2.2.3
+Requires-Dist: networkx>=3.4.2
+Requires-Dist: redis>=6.2.0
+Requires-Dist: duckdb>=1.0.0
+Requires-Dist: pandas>=2.2.3
+Requires-Dist: ty>=0.0.1a5
+Requires-Dist: toml>=0.10.2
+Requires-Dist: sqlalchemy>=2.0.42
+Requires-Dist: aiosqlite>=0.21.0
+Requires-Dist: greenlet>=3.2.3
+Requires-Dist: libsql>=0.1.8
+Requires-Dist: pynacl>=1.5.0
+Requires-Dist: google-api-core>=2.25.1
+Requires-Dist: google-generativeai>=0.8.5
+Requires-Dist: crafter>=1.8.3
+Requires-Dist: click>=8.1.0
+Requires-Dist: textual>=1.1.0
+Requires-Dist: openai-harmony>=0.0.1
+Requires-Dist: asyncpg>=0.30.0
+Requires-Dist: aiohttp>=3.8.0
+Requires-Dist: datasets>=4.0.0
+Requires-Dist: transformers>=4.56.1
+Requires-Dist: modal>=1.1.4
+Provides-Extra: dev
+Requires-Dist: build>=1.2.2.post1; extra == "dev"
+Requires-Dist: twine>=4.0.0; extra == "dev"
+Requires-Dist: keyring>=24.0.0; extra == "dev"
+Requires-Dist: pytest>=8.3.3; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.24.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
+Requires-Dist: pyright>=1.1.350; extra == "dev"
+Requires-Dist: coverage[toml]>=7.3.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Provides-Extra: research
+Requires-Dist: crafter>=1.8.3; extra == "research"
+Requires-Dist: datasets>=4.0.0; extra == "research"
+Provides-Extra: all
+Requires-Dist: crafter>=1.8.3; extra == "all"
+Requires-Dist: datasets>=4.0.0; extra == "all"
+Dynamic: license-file
+
+# Synth-AI
+
+[![Python](https://img.shields.io/badge/python-3.11+-blue)](https://www.python.org/)
+[![License](https://img.shields.io/badge/license-MIT-green)](LICENSE)
+[![PyPI](https://img.shields.io/badge/PyPI-0.2.4.dev8-orange)](https://pypi.org/project/synth-ai/)
+![Coverage](https://img.shields.io/badge/coverage-0.0%25-red)
+![Tests](https://img.shields.io/badge/tests-17%2F17%20passing-brightgreen)
+
+Docs: [Synth‑AI Documentation](https://docs.usesynth.ai/synth-ai/introduction)
+
+Fast and effective reinforcement learning for agents, via an API
+
+# Highlights
+
+- Easily scale gpu topologies - train on 3 a10gs or 8 H100s (multi-node available upon request)
+- Requires only a thin fastapi wrapper to integrate with existing agent software.
+- Supports the best OSS models like Qwen3. (gpt-oss available upon request, GA soon)
+- Own your trained models