feat(persistence): add ORM models, repositories, DB/JSONL event stores, RunJournal, and API endpoints

Phase 2-B: run persistence + event storage + token tracking.

- ORM models: RunRow (with token fields), ThreadMetaRow, RunEventRow
- RunRepository implements RunStore ABC via SQLAlchemy ORM
- ThreadMetaRepository with owner access control
- DbRunEventStore with trace content truncation and cursor pagination
- JsonlRunEventStore with per-run files and seq recovery from disk
- RunJournal (BaseCallbackHandler) captures LLM/tool/lifecycle events,
  accumulates token usage by caller type, buffers and flushes to store
- RunManager now accepts optional RunStore for persistent backing
- Worker creates RunJournal, writes human_message, injects callbacks
- Gateway deps use factory functions (RunRepository when DB available)
- New endpoints: messages, run messages, run events, token-usage
- ThreadCreateRequest gains assistant_id field
- 92 tests pass (33 new), zero regressions

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

backend/packages/harness/deerflow/persistence/models/__init__.py

@@ -0,0 +1,5 @@
+from deerflow.persistence.models.run import RunRow
+from deerflow.persistence.models.run_event import RunEventRow
+from deerflow.persistence.models.thread_meta import ThreadMetaRow
+
+__all__ = ["RunEventRow", "RunRow", "ThreadMetaRow"]

backend/packages/harness/deerflow/persistence/models/run.py

@@ -0,0 +1,49 @@
+"""ORM model for run metadata."""
+
+from __future__ import annotations
+
+from datetime import UTC, datetime
+
+from sqlalchemy import JSON, Index, String, Text
+from sqlalchemy.orm import Mapped, mapped_column
+
+from deerflow.persistence.base import Base
+
+
+class RunRow(Base):
+    __tablename__ = "runs"
+
+    run_id: Mapped[str] = mapped_column(String(64), primary_key=True)
+    thread_id: Mapped[str] = mapped_column(String(64), nullable=False, index=True)
+    assistant_id: Mapped[str | None] = mapped_column(String(128))
+    owner_id: Mapped[str | None] = mapped_column(String(64), index=True)
+    status: Mapped[str] = mapped_column(String(20), default="pending")
+    # "pending" | "running" | "success" | "error" | "timeout" | "interrupted"
+
+    model_name: Mapped[str | None] = mapped_column(String(128))
+    multitask_strategy: Mapped[str] = mapped_column(String(20), default="reject")
+    metadata_json: Mapped[dict] = mapped_column(JSON, default=dict)
+    kwargs_json: Mapped[dict] = mapped_column(JSON, default=dict)
+    error: Mapped[str | None] = mapped_column(Text)
+
+    # Convenience fields (for listing pages without querying RunEventStore)
+    message_count: Mapped[int] = mapped_column(default=0)
+    first_human_message: Mapped[str | None] = mapped_column(Text)
+    last_ai_message: Mapped[str | None] = mapped_column(Text)
+
+    # Token usage (accumulated in-memory by RunJournal, written on run completion)
+    total_input_tokens: Mapped[int] = mapped_column(default=0)
+    total_output_tokens: Mapped[int] = mapped_column(default=0)
+    total_tokens: Mapped[int] = mapped_column(default=0)
+    llm_call_count: Mapped[int] = mapped_column(default=0)
+    lead_agent_tokens: Mapped[int] = mapped_column(default=0)
+    subagent_tokens: Mapped[int] = mapped_column(default=0)
+    middleware_tokens: Mapped[int] = mapped_column(default=0)
+
+    # Follow-up association
+    follow_up_to_run_id: Mapped[str | None] = mapped_column(String(64))
+
+    created_at: Mapped[datetime] = mapped_column(default=lambda: datetime.now(UTC))
+    updated_at: Mapped[datetime] = mapped_column(default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))
+
+    __table_args__ = (Index("ix_runs_thread_status", "thread_id", "status"),)

backend/packages/harness/deerflow/persistence/models/run_event.py

@@ -0,0 +1,30 @@
+"""ORM model for run events."""
+
+from __future__ import annotations
+
+from datetime import UTC, datetime
+
+from sqlalchemy import JSON, Index, String, Text
+from sqlalchemy.orm import Mapped, mapped_column
+
+from deerflow.persistence.base import Base
+
+
+class RunEventRow(Base):
+    __tablename__ = "run_events"
+
+    id: Mapped[int] = mapped_column(primary_key=True, autoincrement=True)
+    thread_id: Mapped[str] = mapped_column(String(64), nullable=False)
+    run_id: Mapped[str] = mapped_column(String(64), nullable=False)
+    event_type: Mapped[str] = mapped_column(String(32), nullable=False)
+    category: Mapped[str] = mapped_column(String(16), nullable=False)
+    # "message" | "trace" | "lifecycle"
+    content: Mapped[str] = mapped_column(Text, default="")
+    event_metadata: Mapped[dict] = mapped_column(JSON, default=dict)
+    seq: Mapped[int] = mapped_column(nullable=False)
+    created_at: Mapped[datetime] = mapped_column(default=lambda: datetime.now(UTC))
+
+    __table_args__ = (
+        Index("ix_events_thread_cat_seq", "thread_id", "category", "seq"),
+        Index("ix_events_run", "thread_id", "run_id", "seq"),
+    )

backend/packages/harness/deerflow/persistence/models/thread_meta.py

@@ -0,0 +1,23 @@
+"""ORM model for thread metadata."""
+
+from __future__ import annotations
+
+from datetime import UTC, datetime
+
+from sqlalchemy import JSON, String
+from sqlalchemy.orm import Mapped, mapped_column
+
+from deerflow.persistence.base import Base
+
+
+class ThreadMetaRow(Base):
+    __tablename__ = "threads_meta"
+
+    thread_id: Mapped[str] = mapped_column(String(64), primary_key=True)
+    assistant_id: Mapped[str | None] = mapped_column(String(128), index=True)
+    owner_id: Mapped[str | None] = mapped_column(String(64), index=True)
+    display_name: Mapped[str | None] = mapped_column(String(256))
+    status: Mapped[str] = mapped_column(String(20), default="idle")
+    metadata_json: Mapped[dict] = mapped_column(JSON, default=dict)
+    created_at: Mapped[datetime] = mapped_column(default=lambda: datetime.now(UTC))
+    updated_at: Mapped[datetime] = mapped_column(default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))