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
+129
View File
@@ -13,9 +13,13 @@ import yaml
from roboco.services.vault_writer import (
A2AMessageData,
AgentNoteData,
BottleneckRow,
JournalNoteData,
OrgReportData,
StageTimingRow,
TaskLinkRef,
TaskNoteData,
TeamReworkRow,
VaultWriter,
)
@@ -233,3 +237,128 @@ def test_existing_narrative_preserved_when_curated(tmp_path: Path) -> None:
writer.existing_narrative("roboco-api", "11112222-3333-4444-5555-666677778888")
== "Shipped cleanly, one rework cycle."
)
# --- archive-awareness ------------------------------------------------------ #
_ARCHIVE_YEAR = 2025
def test_write_task_archived_lands_in_archive_year_dir(tmp_path: Path) -> None:
writer = VaultWriter(tmp_path)
path = writer.write_task(_task_data(status="completed", archive_year=_ARCHIVE_YEAR))
assert path == (
tmp_path
/ "RoboCo"
/ "Archive"
/ str(_ARCHIVE_YEAR)
/ "Tasks"
/ "roboco-api"
/ "Add user authentication endpoint (11112222).md"
)
def test_write_task_archival_moves_live_note_without_duplicate(
tmp_path: Path,
) -> None:
writer = VaultWriter(tmp_path)
live = writer.write_task(_task_data())
archived = writer.write_task(
_task_data(status="completed", archive_year=_ARCHIVE_YEAR)
)
assert not live.exists()
assert archived.exists()
assert len(list(tmp_path.rglob("*(11112222).md"))) == 1
def test_find_task_note_locates_archived_note(tmp_path: Path) -> None:
writer = VaultWriter(tmp_path)
path = writer.write_task(_task_data(status="completed", archive_year=_ARCHIVE_YEAR))
assert writer.find_task_note("11112222-3333-4444-5555-666677778888") == path
def test_existing_narrative_survives_archival(tmp_path: Path) -> None:
writer = VaultWriter(tmp_path)
writer.write_task(_task_data(narrative="Curated before archival."))
writer.write_task(
_task_data(
status="completed",
archive_year=_ARCHIVE_YEAR,
narrative="Curated before archival.",
)
)
assert (
writer.existing_narrative("roboco-api", "11112222-3333-4444-5555-666677778888")
== "Curated before archival."
)
def test_touch_task_frontmatter_reaches_archived_note(tmp_path: Path) -> None:
writer = VaultWriter(tmp_path)
path = writer.write_task(_task_data(status="completed", archive_year=_ARCHIVE_YEAR))
touched = writer.touch_task_frontmatter(
task_id="11112222-3333-4444-5555-666677778888",
status="cancelled",
team="backend",
pr_number=None,
pr_url=None,
)
assert touched is True
assert "status: cancelled" in path.read_text(encoding="utf-8")
# --- weekly org-report ------------------------------------------------------- #
def _report_data() -> OrgReportData:
return OrgReportData(
week="2026-W28",
tasks_completed=5,
tasks_created=8,
completion_rate=0.625,
avg_cycle_hours=12.5,
rework_rate=0.2,
rework_cost_usd=1.23,
total_cost_usd=42.5,
total_tokens=123456,
stages=(StageTimingRow("in_progress", 3600.0, 4),),
bottlenecks=(BottleneckRow("awaiting_qa", 7200.0, 0.5),),
by_team_rework=(TeamReworkRow("backend", 0.1),),
)
def test_write_org_report_layout_and_frontmatter(tmp_path: Path) -> None:
writer = VaultWriter(tmp_path)
path = writer.write_org_report(_report_data())
assert path == tmp_path / "RoboCo" / "Reports" / "2026-W28.md"
text = path.read_text(encoding="utf-8")
fm, _, body = text.removeprefix("---\n").partition("\n---\n")
frontmatter = yaml.safe_load(fm)
assert frontmatter == {
"week": "2026-W28",
"tasks_completed": 5,
"tasks_created": 8,
"completion_rate": 0.625,
"avg_cycle_hours": 12.5,
"rework_rate": 0.2,
"rework_cost_usd": 1.23,
"total_cost_usd": 42.5,
"total_tokens": 123456,
}
assert "## Velocity" in body
assert "## Cycle time by stage" in body
assert "| in_progress | 1.0 | 4 |" in body
assert "## Top bottlenecks" in body
assert "| awaiting_qa | 50% |" in body
assert "## Rework" in body
assert "| backend | 10% |" in body
assert "## Cost" in body
assert "$42.50" in body
def test_write_org_report_same_week_overwrites(tmp_path: Path) -> None:
writer = VaultWriter(tmp_path)
p1 = writer.write_org_report(_report_data())
p2 = writer.write_org_report(_report_data())
assert p1 == p2
assert len(list((tmp_path / "RoboCo" / "Reports").glob("*.md"))) == 1