refactor(persistence): organize entities into per-entity directories

Restructure the persistence layer from horizontal "models/ + repositories/"
split into vertical entity-aligned directories. Each entity (thread_meta,
run, feedback) now owns its ORM model, abstract interface (where applicable),
and concrete implementations under a single directory with an aggregating
__init__.py for one-line imports.

Layout:
  persistence/thread_meta/{base,model,sql,memory}.py
  persistence/run/{model,sql}.py
  persistence/feedback/{model,sql}.py

models/__init__.py is kept as a facade so Alembic autogenerate continues to
discover all ORM tables via Base.metadata. RunEventRow remains under
models/run_event.py because its storage implementation lives in
runtime/events/store/db.py and has no matching repository directory.

The repositories/ directory is removed entirely. All call sites in
gateway/deps.py and tests are updated to import from the new entity
packages, e.g.:

    from deerflow.persistence.thread_meta import ThreadMetaRepository
    from deerflow.persistence.run import RunRepository
    from deerflow.persistence.feedback import FeedbackRepository

Full test suite passes (1690 passed, 14 skipped).

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

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

@@ -1,6 +1,21 @@
-from deerflow.persistence.models.feedback import FeedbackRow
-from deerflow.persistence.models.run import RunRow
+"""ORM model registration entry point.
+
+Importing this module ensures all ORM models are registered with
+``Base.metadata`` so Alembic autogenerate detects every table.
+
+The actual ORM classes have moved to entity-specific subpackages:
+- ``deerflow.persistence.thread_meta``
+- ``deerflow.persistence.run``
+- ``deerflow.persistence.feedback``
+
+``RunEventRow`` remains in ``deerflow.persistence.models.run_event`` because
+its storage implementation lives in ``deerflow.runtime.events.store.db`` and
+there is no matching entity directory.
+"""
+
+from deerflow.persistence.feedback.model import FeedbackRow
 from deerflow.persistence.models.run_event import RunEventRow
-from deerflow.persistence.models.thread_meta import ThreadMetaRow
+from deerflow.persistence.run.model import RunRow
+from deerflow.persistence.thread_meta.model import ThreadMetaRow
 
 __all__ = ["FeedbackRow", "RunEventRow", "RunRow", "ThreadMetaRow"]

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

@@ -1,30 +0,0 @@
-"""ORM model for user feedback on runs."""
-
-from __future__ import annotations
-
-from datetime import UTC, datetime
-
-from sqlalchemy import DateTime, String, Text
-from sqlalchemy.orm import Mapped, mapped_column
-
-from deerflow.persistence.base import Base
-
-
-class FeedbackRow(Base):
-    __tablename__ = "feedback"
-
-    feedback_id: Mapped[str] = mapped_column(String(64), primary_key=True)
-    run_id: Mapped[str] = mapped_column(String(64), nullable=False, index=True)
-    thread_id: Mapped[str] = mapped_column(String(64), nullable=False, index=True)
-    owner_id: Mapped[str | None] = mapped_column(String(64), index=True)
-    message_id: Mapped[str | None] = mapped_column(String(64))
-    # message_id is an optional RunEventStore event identifier —
-    # allows feedback to target a specific message or the entire run
-
-    rating: Mapped[int] = mapped_column(nullable=False)
-    # +1 (thumbs-up) or -1 (thumbs-down)
-
-    comment: Mapped[str | None] = mapped_column(Text)
-    # Optional text feedback from the user
-
-    created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC))

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

@@ -1,49 +0,0 @@
-"""ORM model for run metadata."""
-
-from __future__ import annotations
-
-from datetime import UTC, datetime
-
-from sqlalchemy import JSON, DateTime, 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(DateTime(timezone=True), default=lambda: datetime.now(UTC))
-    updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), 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/thread_meta.py

@@ -1,23 +0,0 @@
-"""ORM model for thread metadata."""
-
-from __future__ import annotations
-
-from datetime import UTC, datetime
-
-from sqlalchemy import JSON, DateTime, 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(DateTime(timezone=True), default=lambda: datetime.now(UTC))
-    updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC), onupdate=lambda: datetime.now(UTC))