feat(vault): Obsidian vault V2 — janitor, archival, weekly report, KB ingest, Bases + sync runbook (#482)

* 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>
This commit is contained in:
Renzo F
2026-07-11 15:51:19 +02:00
committed by GitHub
co-authored by Renn F
parent e211a3c15e
commit d03181ab48
56 changed files with 3681 additions and 101 deletions
+87
View File
@@ -7,6 +7,8 @@ underlying verb; the flag off must short-circuit before any writer call;
from __future__ import annotations
from datetime import UTC, datetime
from types import SimpleNamespace
from typing import TYPE_CHECKING, cast
from unittest.mock import AsyncMock, MagicMock, patch
from uuid import uuid4
@@ -16,6 +18,12 @@ from roboco.models.base import JournalEntryType
from roboco.services.a2a import A2AService
from roboco.services.journal import JournalService
from roboco.services.task import TaskService
from roboco.services.vault_writer import VaultWriter
if TYPE_CHECKING:
from pathlib import Path
from roboco.db.tables import TaskTable
def _entry_row(*, is_private: bool = False, task_id: object | None = None) -> MagicMock:
@@ -185,3 +193,82 @@ def test_task_transition_seam_touches_status_team_pr(
pr_number=7,
pr_url="https://github.com/x/y/pull/7",
)
# --- materialize-on-create seam ---------------------------------------------- #
def _fresh_task_stub() -> TaskTable:
stub = SimpleNamespace(
id=uuid4(),
title="Fresh task",
description="Just created.",
status="pending",
team="backend",
priority=2,
task_type="code",
acceptance_criteria=[],
pr_number=None,
pr_url=None,
project_id=None,
parent_task_id=None,
dependency_ids=None,
batch_id=None,
completed_at=None,
updated_at=None,
created_at=datetime.now(UTC),
)
return cast("TaskTable", stub)
def _create_seam_service() -> TaskService:
svc = TaskService.__new__(TaskService)
svc.log = MagicMock()
svc.session = MagicMock()
object.__setattr__(svc, "get", AsyncMock(return_value=None))
object.__setattr__(svc, "get_subtasks", AsyncMock(return_value=[]))
return svc
@pytest.mark.asyncio
async def test_create_seam_noop_when_flag_off(
monkeypatch: pytest.MonkeyPatch,
) -> None:
monkeypatch.setattr(settings, "obsidian_vault_enabled", False)
svc = _create_seam_service()
with patch("roboco.services.vault_writer.get_vault_writer") as get_writer:
await svc._materialize_vault_note(_fresh_task_stub())
get_writer.assert_not_called()
@pytest.mark.asyncio
async def test_create_seam_writer_failure_does_not_raise(
monkeypatch: pytest.MonkeyPatch,
) -> None:
monkeypatch.setattr(settings, "obsidian_vault_enabled", True)
svc = _create_seam_service()
writer = MagicMock()
writer.write_task.side_effect = OSError("disk full")
with patch("roboco.services.vault_writer.get_vault_writer", return_value=writer):
await svc._materialize_vault_note(_fresh_task_stub())
writer.write_task.assert_called_once()
@pytest.mark.asyncio
async def test_create_seam_materializes_note_in_tmp_vault(
monkeypatch: pytest.MonkeyPatch, tmp_path: Path
) -> None:
monkeypatch.setattr(settings, "obsidian_vault_enabled", True)
svc = _create_seam_service()
task = _fresh_task_stub()
with patch(
"roboco.services.vault_writer.get_vault_writer",
return_value=VaultWriter(tmp_path),
):
await svc._materialize_vault_note(task)
note = VaultWriter(tmp_path).find_task_note(str(task.id))
assert note is not None
text = note.read_text(encoding="utf-8")
assert "status: pending" in text
# Narrative stays Auditor-owned: only the placeholder is rendered.
assert "_Pending Auditor curation._" in text