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
@@ -0,0 +1,41 @@
"""Vault janitor knobs — archival window + weekly-report flag (mirrors the
vault-intake flag test idiom)."""
from __future__ import annotations
import os
from unittest import mock
import pytest
from pydantic import ValidationError
from roboco.config import Settings
from roboco.services.settings import FEATURE_FLAGS, validate_setting
_DEFAULT_ARCHIVE_DAYS = 30
def test_vault_janitor_defaults() -> None:
s = Settings()
assert s.vault_archive_days == _DEFAULT_ARCHIVE_DAYS
assert s.vault_report_enabled is True
def test_vault_archive_days_reads_env_var() -> None:
with mock.patch.dict(os.environ, {"ROBOCO_VAULT_ARCHIVE_DAYS": "0"}):
assert Settings().vault_archive_days == 0
def test_vault_archive_days_rejects_negative() -> None:
with (
mock.patch.dict(os.environ, {"ROBOCO_VAULT_ARCHIVE_DAYS": "-1"}),
pytest.raises(ValidationError),
):
Settings()
def test_vault_report_flag_registered_in_feature_flags() -> None:
assert "vault_report_enabled" in [key for key, _ in FEATURE_FLAGS]
def test_vault_report_flag_validates_as_bool() -> None:
validate_setting("vault_report_enabled", "false")
+141
View File
@@ -0,0 +1,141 @@
"""Vault KB ingest knobs — dirs/interval defaults + the reserved-dir overlap
guard (mirrors the vault-janitor flag test idiom)."""
from __future__ import annotations
import os
from unittest import mock
import pytest
from pydantic import ValidationError
from roboco.config import Settings
from roboco.services.settings import FEATURE_FLAGS, validate_setting
_DEFAULT_INTERVAL = 900
def test_vault_kb_defaults() -> None:
s = Settings()
assert s.vault_kb_enabled is False
assert s.vault_kb_dirs == "RoboCo/Notes"
assert s.vault_kb_interval_seconds == _DEFAULT_INTERVAL
def test_vault_kb_interval_rejects_below_minimum() -> None:
with (
mock.patch.dict(os.environ, {"ROBOCO_VAULT_KB_INTERVAL_SECONDS": "30"}),
pytest.raises(ValidationError),
):
Settings()
def test_vault_kb_flag_registered_in_feature_flags() -> None:
assert "vault_kb_enabled" in [key for key, _ in FEATURE_FLAGS]
def test_vault_kb_flag_validates_as_bool() -> None:
validate_setting("vault_kb_enabled", "true")
def test_vault_kb_dirs_clean_config_passes() -> None:
with mock.patch.dict(
os.environ,
{"ROBOCO_VAULT_KB_ENABLED": "true", "ROBOCO_VAULT_KB_DIRS": "RoboCo/Notes"},
):
assert Settings().vault_kb_dirs == "RoboCo/Notes"
def test_vault_kb_dirs_overlap_with_intake_dir_rejected() -> None:
with (
mock.patch.dict(
os.environ,
{
"ROBOCO_VAULT_KB_ENABLED": "true",
"ROBOCO_VAULT_KB_DIRS": "RoboCo/Inbox",
},
),
pytest.raises(ValidationError),
):
Settings()
@pytest.mark.parametrize(
"kb_dirs",
[
"RoboCo/Tasks",
"RoboCo/Tasks/Sub", # nests under a reserved dir
"RoboCo", # nests OVER every reserved dir (reverse direction)
".obsidian",
"RoboCo/Notes,RoboCo/Journals", # one clean entry, one reserved
],
)
def test_vault_kb_dirs_reserved_overlap_rejected(kb_dirs: str) -> None:
with (
mock.patch.dict(
os.environ,
{"ROBOCO_VAULT_KB_ENABLED": "true", "ROBOCO_VAULT_KB_DIRS": kb_dirs},
),
pytest.raises(ValidationError),
):
Settings()
@pytest.mark.parametrize(
"kb_dirs",
[
"/etc", # absolute path
"/etc/passwd",
"../sibling_secret_dir", # leading traversal
"RoboCo/Notes/..", # trailing traversal
"RoboCo/../../outside", # embedded traversal
"RoboCo/Notes,../outside", # one clean entry, one traversal
".", # vault root itself — would rglob every projection dir
"./", # vault root, trailing-slash spelling
"./RoboCo/Tasks", # dot-prefixed reserved dir must not evade overlap
],
)
def test_vault_kb_dirs_traversal_rejected(kb_dirs: str) -> None:
"""Absolute paths and '..' segments would let KB ingest read files
entirely outside the vault into the fleet-retrievable corpus."""
with (
mock.patch.dict(
os.environ,
{"ROBOCO_VAULT_KB_ENABLED": "true", "ROBOCO_VAULT_KB_DIRS": kb_dirs},
),
pytest.raises(ValidationError),
):
Settings()
def test_vault_kb_dirs_dot_prefixed_clean_entry_passes() -> None:
"""'./RoboCo/Notes' normalizes to a clean, non-reserved subfolder."""
with mock.patch.dict(
os.environ,
{
"ROBOCO_VAULT_KB_ENABLED": "true",
"ROBOCO_VAULT_KB_DIRS": "./RoboCo/Notes",
},
):
assert Settings().vault_kb_dirs == "./RoboCo/Notes"
def test_vault_kb_dirs_dotted_name_is_not_traversal() -> None:
"""A '..' inside a segment name (not a whole segment) is a legal dir name."""
with mock.patch.dict(
os.environ,
{
"ROBOCO_VAULT_KB_ENABLED": "true",
"ROBOCO_VAULT_KB_DIRS": "RoboCo/my..notes",
},
):
assert Settings().vault_kb_dirs == "RoboCo/my..notes"
def test_vault_kb_disabled_skips_dir_validation() -> None:
"""An invalid vault_kb_dirs is only enforced when vault_kb_enabled — off
by default, so a stale/misconfigured env value never blocks startup."""
with mock.patch.dict(
os.environ,
{"ROBOCO_VAULT_KB_ENABLED": "false", "ROBOCO_VAULT_KB_DIRS": "RoboCo/Tasks"},
):
assert Settings().vault_kb_dirs == "RoboCo/Tasks"