mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
* feat(vault): V2 — create-seam + drift janitor, archival, weekly org-report, KB ingest, Bases views + sync runbook Implements the vault V2 canonical spec end to end (the splice guard shipped separately and is reused at KB-ingest time): - materialize-on-create: TaskService.create writes each task's note best-effort from the moment it exists; the transition-touch stops no-oping on live work - drift janitor (services/vault_janitor.py + hourly _vault_janitor_loop): daily changed-task re-projection, random drift sample, archival pass — restart-proof via RoboCo/_meta/.janitor_state.json, 200/cycle caps, per-item isolation, processed-only resume markers, self-repairing state file - archival: vault_archive_days (30, 0=off) moves old terminal tasks' notes to RoboCo/Archive/<year>/Tasks/<project>/ — one write_task code path for janitor and rebuild, id8 lookup across Tasks/+Archive/, alias links keep moves safe - weekly org-report: VaultWriter.write_org_report renders Reports/<ISO-week>.md from MetricsService/UsageService (numbers duplicated into frontmatter for trend queries), once per ISO week, with a best-effort CEO notification - KB ingest: IndexType.VAULT_NOTES + VaultNotesIndexPlugin + _vault_kb_loop embed the CEO's RoboCo/Notes into the RAG corpus — injection guard as a hard gate (flagged notes quarantined with an idempotent callout), traversal- and symlink-contained at both config and engine layers, content-hash dedup, 50-ingest/cycle cap, frontmatter stripped; reaches roboco_kb_search, the mentor default domain, claim-time briefings (kind vault_note), and the panel KB browser; no migration (chunks table auto-creates; migration 030's CHUNK_TABLES tuple appended per the chunks_playbooks precedent) - Bases views (Task Board.base, Reports.base — schema verified against the Obsidian docs) + the Mac sync runbook vault asset - config/flags/compose: vault_archive_days, vault_report_enabled (flags card), vault_kb_enabled (flags card; NAS compose arms it, registry ships it off), vault_kb_dirs (+ overlap/traversal validator), vault_kb_interval_seconds - e2e smoke (tests/e2e_smoke/test_vault_v2.py): real create-seam, real janitor cycle incl. archival + state, real KB engine + real guard * docs: vault V2 sweep — map, RAG corpus, CLAUDE.md - docs/map/vault.md: V1+V2 — janitor/archival/report/KB data flows, new files, config, health posture - docs/map/orchestrator.md + task-service.md: the two new loops, the create seam, the three janitor queries - docs/rag/architecture/obsidian-vault.md: agent-facing what-changed (notes from creation, archive link-safety, CEO notes retrievable, weekly report) - docs/rag/architecture/config-reference.md: the five new settings - CLAUDE.md: vault paragraph covers V1+V2; flags-card list mentions the vault report/KB flags --------- Co-authored-by: Renn F <rennf93@users.noreply.github.com>
118 lines
4.3 KiB
Python
118 lines
4.3 KiB
Python
"""Align RAG chunk tables with the in-house vector-store schema.
|
|
|
|
The in-house vector store (which replaced piragi) reads and writes a ``content``
|
|
column and a ``created_at`` column on every ``chunks_<index_type>`` table, and
|
|
provisions those tables at runtime with ``CREATE TABLE IF NOT EXISTS``. On a
|
|
database that already carried the piragi-era tables — column named ``text``, no
|
|
``created_at`` — that runtime DDL is a silent no-op, so the new engine never
|
|
reshapes them and every ingest/search/list fails with
|
|
``column "content" of relation "chunks_<type>" does not exist``.
|
|
|
|
These tables hold derived chunks AND non-rebuildable agent knowledge
|
|
(journals, decisions, errors, learnings, reviews) that a docs
|
|
reindex cannot regenerate, so this migration ALTERs in place — renaming
|
|
``text`` -> ``content`` and adding ``created_at`` — rather than dropping data.
|
|
The legacy ``chunk_index`` / integer ``id`` columns are left untouched: the
|
|
engine never references them and dropping them would be a needless destructive
|
|
change.
|
|
|
|
The work runs inside a single plpgsql ``DO`` block that guards each step on
|
|
``information_schema`` at execution time. That keeps the migration idempotent
|
|
and safe whether a table is piragi-shaped, already engine-shaped, or absent
|
|
(e.g. ``chunks_code``, never populated) — and, unlike Python-side reflection,
|
|
it renders under ``alembic upgrade --sql`` (offline mode) where no live
|
|
connection exists.
|
|
|
|
Revision ID: 030_rag_chunks_content_schema
|
|
Revises: 029_project_quality_command
|
|
Create Date: 2026-06-15
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from alembic import op
|
|
|
|
revision = "030_rag_chunks_content_schema"
|
|
down_revision = "029_project_quality_command"
|
|
branch_labels = None
|
|
depends_on = None
|
|
|
|
# One per ``IndexType`` value at the time of writing. Hardcoded so the migration
|
|
# stays self-contained and never imports evolving application code; a unit test
|
|
# guards this tuple against the live ``IndexType`` enum so a newly added index
|
|
# type cannot silently escape the schema alignment.
|
|
CHUNK_TABLES = (
|
|
"chunks_code",
|
|
"chunks_documentation",
|
|
"chunks_journals",
|
|
"chunks_errors",
|
|
"chunks_standards",
|
|
"chunks_decisions",
|
|
"chunks_reviews",
|
|
"chunks_learnings",
|
|
"chunks_playbooks",
|
|
"chunks_vault_notes",
|
|
)
|
|
|
|
# SQL array literal of the table names (validated identifiers from the tuple).
|
|
_TABLES_SQL = ", ".join(f"'{name}'" for name in CHUNK_TABLES)
|
|
|
|
|
|
def upgrade() -> None:
|
|
op.execute(
|
|
f"""
|
|
DO $$
|
|
DECLARE
|
|
t text;
|
|
BEGIN
|
|
FOREACH t IN ARRAY ARRAY[{_TABLES_SQL}] LOOP
|
|
IF EXISTS (
|
|
SELECT 1 FROM information_schema.columns
|
|
WHERE table_schema = 'public'
|
|
AND table_name = t AND column_name = 'text'
|
|
) AND NOT EXISTS (
|
|
SELECT 1 FROM information_schema.columns
|
|
WHERE table_schema = 'public'
|
|
AND table_name = t AND column_name = 'content'
|
|
) THEN
|
|
EXECUTE format('ALTER TABLE %I RENAME COLUMN text TO content', t);
|
|
END IF;
|
|
EXECUTE format(
|
|
'ALTER TABLE IF EXISTS %I '
|
|
'ADD COLUMN IF NOT EXISTS created_at '
|
|
'TIMESTAMPTZ NOT NULL DEFAULT NOW()',
|
|
t
|
|
);
|
|
END LOOP;
|
|
END $$;
|
|
"""
|
|
)
|
|
|
|
|
|
def downgrade() -> None:
|
|
op.execute(
|
|
f"""
|
|
DO $$
|
|
DECLARE
|
|
t text;
|
|
BEGIN
|
|
FOREACH t IN ARRAY ARRAY[{_TABLES_SQL}] LOOP
|
|
EXECUTE format(
|
|
'ALTER TABLE IF EXISTS %I DROP COLUMN IF EXISTS created_at', t
|
|
);
|
|
IF EXISTS (
|
|
SELECT 1 FROM information_schema.columns
|
|
WHERE table_schema = 'public'
|
|
AND table_name = t AND column_name = 'content'
|
|
) AND NOT EXISTS (
|
|
SELECT 1 FROM information_schema.columns
|
|
WHERE table_schema = 'public'
|
|
AND table_name = t AND column_name = 'text'
|
|
) THEN
|
|
EXECUTE format('ALTER TABLE %I RENAME COLUMN content TO text', t);
|
|
END IF;
|
|
END LOOP;
|
|
END $$;
|
|
"""
|
|
)
|