Files
gitlore/migrations/024_note_documents.sql
teernisse 0ca9391b9d feat: implement 18 NOTE beads — per-note search and document pipeline
Tier 0 (Ingestion):
- NOTE-0A: Upsert/sweep for issue discussion notes (stable IDs)
- NOTE-0B: Immediate deletion propagation for swept notes
- NOTE-0C: Sweep safety guard for partial fetch protection
- NOTE-0D: Capture immutable author_id in note upserts

Tier 1 (Query/CLI):
- NOTE-1A: Note query layer data types and filters (28+ filter combinations)
- NOTE-1B: CLI arguments and command wiring for lore notes
- NOTE-1C: Human and robot output formatting (table/json/jsonl/csv)
- NOTE-1D: robot-docs integration for notes command
- NOTE-1E: Migration 022 — composite query indexes + author_id column

Tier 2 (Document/Search):
- NOTE-2A: Migration 024 — schema rebuild for note documents
- NOTE-2B: SourceType::Note enum extension
- NOTE-2C: Note document extractor function
- NOTE-2D: Regenerator and dirty tracking for note documents
- NOTE-2E: Generate-docs full rebuild support for notes
- NOTE-2F: Search CLI --type note support
- NOTE-2G: Parent metadata change propagation to note documents
- NOTE-2H: Migration 025 — backfill existing notes after upgrade
- NOTE-2I: Batch parent metadata cache for note regeneration

21 files changed, 5364 insertions, 713 tests passing.
2026-02-12 13:13:41 -05:00

154 lines
5.6 KiB
SQL

-- Migration 024: Add 'note' source_type to documents and dirty_sources
-- SQLite does not support ALTER CONSTRAINT, so we use the table-rebuild pattern.
-- ============================================================
-- 1. Rebuild dirty_sources with updated CHECK constraint
-- ============================================================
CREATE TABLE dirty_sources_new (
source_type TEXT NOT NULL CHECK (source_type IN ('issue','merge_request','discussion','note')),
source_id INTEGER NOT NULL,
queued_at INTEGER NOT NULL,
attempt_count INTEGER NOT NULL DEFAULT 0,
last_attempt_at INTEGER,
last_error TEXT,
next_attempt_at INTEGER,
PRIMARY KEY(source_type, source_id)
);
INSERT INTO dirty_sources_new SELECT * FROM dirty_sources;
DROP TABLE dirty_sources;
ALTER TABLE dirty_sources_new RENAME TO dirty_sources;
CREATE INDEX idx_dirty_sources_next_attempt ON dirty_sources(next_attempt_at);
-- ============================================================
-- 2. Rebuild documents with updated CHECK constraint
-- ============================================================
-- 2a. Backup junction table data
CREATE TEMP TABLE _doc_labels_backup AS SELECT * FROM document_labels;
CREATE TEMP TABLE _doc_paths_backup AS SELECT * FROM document_paths;
-- 2b. Drop all triggers that reference documents
DROP TRIGGER IF EXISTS documents_ai;
DROP TRIGGER IF EXISTS documents_ad;
DROP TRIGGER IF EXISTS documents_au;
DROP TRIGGER IF EXISTS documents_embeddings_ad;
-- 2c. Drop junction tables (they have FK references to documents)
DROP TABLE IF EXISTS document_labels;
DROP TABLE IF EXISTS document_paths;
-- 2d. Create new documents table with 'note' in CHECK constraint
CREATE TABLE documents_new (
id INTEGER PRIMARY KEY,
source_type TEXT NOT NULL CHECK (source_type IN ('issue','merge_request','discussion','note')),
source_id INTEGER NOT NULL,
project_id INTEGER NOT NULL REFERENCES projects(id),
author_username TEXT,
label_names TEXT,
created_at INTEGER,
updated_at INTEGER,
url TEXT,
title TEXT,
content_text TEXT NOT NULL,
content_hash TEXT NOT NULL,
labels_hash TEXT NOT NULL DEFAULT '',
paths_hash TEXT NOT NULL DEFAULT '',
is_truncated INTEGER NOT NULL DEFAULT 0,
truncated_reason TEXT CHECK (
truncated_reason IN (
'token_limit_middle_drop','single_note_oversized','first_last_oversized',
'hard_cap_oversized'
)
OR truncated_reason IS NULL
),
UNIQUE(source_type, source_id)
);
-- 2e. Copy all existing data
INSERT INTO documents_new SELECT * FROM documents;
-- 2f. Swap tables
DROP TABLE documents;
ALTER TABLE documents_new RENAME TO documents;
-- 2g. Recreate all indexes on documents
CREATE INDEX idx_documents_project_updated ON documents(project_id, updated_at);
CREATE INDEX idx_documents_author ON documents(author_username);
CREATE INDEX idx_documents_source ON documents(source_type, source_id);
CREATE INDEX idx_documents_hash ON documents(content_hash);
-- 2h. Recreate junction tables
CREATE TABLE document_labels (
document_id INTEGER NOT NULL REFERENCES documents(id) ON DELETE CASCADE,
label_name TEXT NOT NULL,
PRIMARY KEY(document_id, label_name)
) WITHOUT ROWID;
CREATE INDEX idx_document_labels_label ON document_labels(label_name);
CREATE TABLE document_paths (
document_id INTEGER NOT NULL REFERENCES documents(id) ON DELETE CASCADE,
path TEXT NOT NULL,
PRIMARY KEY(document_id, path)
) WITHOUT ROWID;
CREATE INDEX idx_document_paths_path ON document_paths(path);
-- 2i. Restore junction table data from backups
INSERT INTO document_labels SELECT * FROM _doc_labels_backup;
INSERT INTO document_paths SELECT * FROM _doc_paths_backup;
-- 2j. Recreate FTS triggers (from migration 008)
CREATE TRIGGER documents_ai AFTER INSERT ON documents BEGIN
INSERT INTO documents_fts(rowid, title, content_text)
VALUES (new.id, COALESCE(new.title, ''), new.content_text);
END;
CREATE TRIGGER documents_ad AFTER DELETE ON documents BEGIN
INSERT INTO documents_fts(documents_fts, rowid, title, content_text)
VALUES('delete', old.id, COALESCE(old.title, ''), old.content_text);
END;
CREATE TRIGGER documents_au AFTER UPDATE ON documents
WHEN old.title IS NOT new.title OR old.content_text != new.content_text
BEGIN
INSERT INTO documents_fts(documents_fts, rowid, title, content_text)
VALUES('delete', old.id, COALESCE(old.title, ''), old.content_text);
INSERT INTO documents_fts(rowid, title, content_text)
VALUES (new.id, COALESCE(new.title, ''), new.content_text);
END;
-- 2k. Recreate embeddings cleanup trigger (from migration 009)
CREATE TRIGGER documents_embeddings_ad AFTER DELETE ON documents BEGIN
DELETE FROM embeddings
WHERE rowid >= old.id * 1000
AND rowid < (old.id + 1) * 1000;
END;
-- 2l. Rebuild FTS index to ensure consistency after table swap
INSERT INTO documents_fts(documents_fts) VALUES('rebuild');
-- ============================================================
-- 3. Defense triggers: clean up documents when notes are
-- deleted or flipped to system notes
-- ============================================================
CREATE TRIGGER notes_ad_cleanup AFTER DELETE ON notes
WHEN old.is_system = 0
BEGIN
DELETE FROM documents WHERE source_type = 'note' AND source_id = old.id;
END;
CREATE TRIGGER notes_au_system_cleanup AFTER UPDATE OF is_system ON notes
WHEN NEW.is_system = 1 AND OLD.is_system = 0
BEGIN
DELETE FROM documents WHERE source_type = 'note' AND source_id = OLD.id;
END;
-- ============================================================
-- 4. Drop temp backup tables
-- ============================================================
DROP TABLE IF EXISTS _doc_labels_backup;
DROP TABLE IF EXISTS _doc_paths_backup;