Files
FabledScribe/src/scribe/models/note.py
T
bvandeusen cca40affe4
CI & Build / Python lint (push) Successful in 2s
CI & Build / TypeScript typecheck (push) Successful in 12s
CI & Build / integration (push) Successful in 25s
CI & Build / Python tests (push) Failing after 29s
CI & Build / Build & push image (push) Has been skipped
feat(snippets): add notes.data JSONB — the indexed mirror of snippet fields
Milestone #232 step 1 (task #2081). Takes the enabler first rather than the
write-path trigger: reverse lookup, drift checks and the duplicate finder all
need to QUERY structured fields, and building them on body-regex first means
writing them twice.

#227 deferred this bag "unless body-convention ergonomics prove insufficient" —
answering "which snippets live in this file?" by scanning every snippet and
regexing its body is that condition being met.

Migration 0070 adds `notes.data` (nullable JSONB) + a GIN index. The body is
UNCHANGED and still what gets embedded and read by humans; `data` mirrors the
same facts in a shape Postgres can index. Code is deliberately not copied into
it — the body holds it, and duplicating a blob into the column we index around
would be waste.

- compose_data() builds the mirror, omitting empties so the column stays sparse
- snippet_fields() prefers `data`, falling back to parsing the body. Rows written
  before 0070 have no `data` and are never backfilled, so a hand-edited body
  stays authoritative for them with no conversion deadline
- create / update / merge all write body and mirror from the same merged field
  set, so the two can't drift; merge in particular has to grow the mirror with
  the survivor's location set or a merged snippet would be unfindable at the very
  call sites the merge just recorded

Named `data`, not `metadata`, because that collides with SQLAlchemy's declarative
Base.metadata — which is why the pre-0069 model had to map an awkward
`entity_metadata` attribute. Not a revival of the column 0069 dropped: different
name, different purpose, nothing reads the old shape.

Two test fakes needed an explicit `data = None`: snippet_fields prefers `data`
when truthy and an auto-MagicMock attribute is truthy, so every parsed field
would have come back a MagicMock. Checked every fake reaching snippet code this
time rather than waiting for CI (note 2109).

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RLwAaV4DQEmVyn496HnEvt
2026-07-26 18:25:55 -04:00

129 lines
5.7 KiB
Python

import enum
from datetime import date, datetime
from sqlalchemy import Date, DateTime, ForeignKey, Index, Integer, Text
from sqlalchemy.dialects.postgresql import ARRAY, JSONB
from sqlalchemy.orm import Mapped, mapped_column
from scribe.models import Base
from scribe.models.base import TimestampMixin, SoftDeleteMixin
class TaskStatus(str, enum.Enum):
todo = "todo"
in_progress = "in_progress"
done = "done"
cancelled = "cancelled"
class TaskPriority(str, enum.Enum):
none = "none"
low = "low"
medium = "medium"
high = "high"
class Note(Base, TimestampMixin, SoftDeleteMixin):
__tablename__ = "notes"
id: Mapped[int] = mapped_column(primary_key=True)
user_id: Mapped[int | None] = mapped_column(
Integer, ForeignKey("users.id", ondelete="CASCADE"), nullable=True
)
title: Mapped[str] = mapped_column(Text, default="")
body: Mapped[str] = mapped_column(Text, default="")
description: Mapped[str | None] = mapped_column(Text, nullable=True)
consolidated_at: Mapped[datetime | None] = mapped_column(
DateTime(timezone=True), nullable=True
)
tags: Mapped[list[str]] = mapped_column(ARRAY(Text), default=list)
parent_id: Mapped[int | None] = mapped_column(
Integer, ForeignKey("notes.id", ondelete="SET NULL"), nullable=True
)
# Provenance: the task/feature an issue arose from. Distinct from parent_id
# (sub-task hierarchy) — this is "what spawned this". Only meaningful for
# issues; nullable for every record.
arose_from_id: Mapped[int | None] = mapped_column(
Integer, ForeignKey("notes.id", ondelete="SET NULL"), nullable=True
)
project_id: Mapped[int | None] = mapped_column(
Integer, ForeignKey("projects.id", ondelete="SET NULL"), nullable=True
)
milestone_id: Mapped[int | None] = mapped_column(
Integer, ForeignKey("milestones.id", ondelete="SET NULL"), nullable=True
)
status: Mapped[str | None] = mapped_column(Text, nullable=True)
priority: Mapped[str | None] = mapped_column(Text, nullable=True)
due_date: Mapped[date | None] = mapped_column(Date, nullable=True)
started_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
completed_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
recurrence_rule: Mapped[dict | None] = mapped_column(JSONB, nullable=True)
recurrence_next_spawn_at: Mapped[datetime | None] = mapped_column(
DateTime(timezone=True), nullable=True
)
# Note type — 'note' (default) or 'process' (a stored process). Task-ness is
# tracked by `status`, not here. (person/place/list entity types removed 2026-07.)
note_type: Mapped[str] = mapped_column(Text, default="note", server_default="note")
# Task sub-kind — 'work' (default), 'plan', or 'issue' (corrective work).
# Only meaningful when the note is a task (status is not None); ordinary
# notes keep the 'work' default and ignore it. Orthogonal to note_type
# (which is the note/entity axis).
task_kind: Mapped[str] = mapped_column(Text, default="work", server_default="work")
# Queryable structured fields for typed records — currently snippets, whose
# name/language/signature/locations live here so they can be INDEXED. The
# body keeps the same facts in readable markdown and remains what gets
# embedded; this is a mirror for querying, not the source of truth for
# display. NULL on every row written before migration 0070, so readers fall
# back to parsing the body (see services/snippets.snippet_fields).
data: Mapped[dict | None] = mapped_column(JSONB, nullable=True)
__table_args__ = (
Index("ix_notes_tags", "tags", postgresql_using="gin"),
Index("ix_notes_status", "status"),
Index("ix_notes_title", "title"),
Index("ix_notes_user_id", "user_id"),
Index("ix_notes_project_id", "project_id"),
Index("ix_notes_milestone_id", "milestone_id"),
Index("ix_notes_note_type", "note_type"),
Index("ix_notes_arose_from_id", "arose_from_id"),
# Containment queries into `data` — e.g. which snippets name a given
# repo/path in their locations. See migration 0070.
Index("ix_notes_data_gin", "data", postgresql_using="gin"),
)
@property
def is_task(self) -> bool:
return self.status is not None
def to_dict(self) -> dict:
return {
"id": self.id,
"title": self.title,
"body": self.body,
"description": self.description,
"consolidated_at": (
self.consolidated_at.isoformat() if self.consolidated_at else None
),
"tags": self.tags or [],
"parent_id": self.parent_id,
"arose_from_id": self.arose_from_id,
"project_id": self.project_id,
"milestone_id": self.milestone_id,
"status": self.status,
"priority": self.priority,
"due_date": self.due_date.isoformat() if self.due_date else None,
"started_at": self.started_at.isoformat() if self.started_at else None,
"completed_at": self.completed_at.isoformat() if self.completed_at else None,
"recurrence_rule": self.recurrence_rule,
"recurrence_next_spawn_at": (
self.recurrence_next_spawn_at.isoformat()
if self.recurrence_next_spawn_at
else None
),
"is_task": self.is_task,
"note_type": self.note_type or "note",
"task_kind": self.task_kind,
"created_at": self.created_at.isoformat(),
"updated_at": self.updated_at.isoformat(),
}