Files
roboco/tests/unit/services/test_sentinel_engine.py
T
401f8a2cc9 feat(board): Board Programs — the complete twelve-program catalog (Phases 1-3) (#699)
* feat(board): Pest Control — the first project-scoped Board Program

The Product Owner hunts latent defects (what the org records but nobody
reads): a weekly cycle — accelerated off-schedule when the trailing-7-day
rework rate crosses pest_rework_threshold, with the cheap dedup/scope gates
evaluated before the metrics queries — opens one held exploration task
against the least-recently-explored opted-in project (deterministic
round-robin; opted_in_projects gains a stable ORDER BY), with server-
assembled evidence in the spawn prompt (rework hotspots, recurring-findings
and waived-minor ledger aggregates, all capped) plus prior-cycle LEARN
context. The PO calls the new PO-only propose_bug_hunt verb once: ≤5 items,
evidence required per item, targets validated against pest_control
participation. CEO decides per item — approve materializes a BACKLOG task
(source pest_control, never auto-starts), reject records the reason; both
feed the LEARN ledger by exploration task id; all-terminal completes the
cycle. Telegram queue pushes carry working Approve/Reject handlers
mirroring the roadmap kind. Doctrine: board.md Pest Control section +
product-owner verb entry + regenerated verb tables.

* feat(panel): Pest Control review queue

Command Center gains the pest review queue (per-item approve/reject with
reason, mirroring the roadmap queue); the Programs card and the project
settings participates-in checkboxes pick the new program up registry-driven
— the settings section renders for the first time now that a project-scoped
program exists.

* feat(board): Periscope — HoM market-research brief program

Weekly org-scoped cycle: a solo HoM spawn researches the market (web
research with mandatory source URLs — uncited findings are rejected) and
files one structured brief via the new HoM-only propose_market_brief verb:
headline, cited findings, threats/opportunities, positioning note, all
soup-checked and screened through the injection guard at persist time
(web-derived text later reaches prompts; flags recorded, content never
dropped). A brief is a report, not a proposal: the verb completes the
exploration in the same call (the x_feature asymmetry), the cycle ledger
auto-closes, and the CEO gets a best-effort notification with no
approve/reject surface (periscope deliberately never joins Telegram's
action kinds). The latest brief is injected into the roadmap exploration
prompt — Periscope feeds Printer, the first cross-role program input.

* feat(panel): Market Briefs tab (read-only)

Business page gains a Market Briefs tab listing Periscope briefs —
headline, cited findings, threats/opportunities — read-only by design; a
report has nothing to approve.

* feat(board): Coroner — event-triggered Auditor postmortems

The first EVENT program: no cron — three best-effort hooks open an autopsy
when a task bounces to its 3rd revision (the audit chokepoint), is
cancelled after work started, or is budget-blocked; all gated on arming +
one-open-autopsy dedup, none can fail the underlying transition. A solo
Auditor spawn reads the incident (server-assembled findings + transition
context) and files one propose_postmortem: incident summary, root cause,
failed stage (validated against the real status vocabulary), and ONE
process change — a playbook-kind change drafts via PlaybookService
directly into the normal pending-curation queue; the briefed draft_playbook
manifest grant was deliberately NOT added, preserving the existing
'auditor curates but never drafts' invariant test. Complete-at-propose
(report asymmetry), cycle ledger auto-closes, CEO notified link-only.
Integrated as a union with Periscope across the shared program surfaces.

* feat(panel): Coroner postmortems card

Read-only postmortems list under Business → Programs — incident, root
cause, failed stage, process change; nothing to approve, the process-change
artifact (a draft playbook) rides the existing curation queue.

* feat(board): Sentinel — Auditor drift-watch quality reports

Weekly org-scoped cycle: a solo Auditor spawn receives a server-assembled
drift context (waived-findings trend, open findings by severity,
conventions-violation hotspots, top spend — all capped, pure ORM) and files
one propose_quality_report: headline, 1-7 area-validated items with
evidence and suggested actions, overall assessment. Report semantics —
complete-at-propose, cycle auto-closes, CEO notified display-only (never on
Telegram's approve/reject surface); items are structured so a later
convert-to-task control is cheap. Integration adopts Sentinel's module-
level dict-dispatch for board-program routing (xenon-driven), folding all
prior programs in; app router mounting extracted to a helper for the same
budget.

* feat(panel): Quality Reports tab (read-only)

Business page gains the Sentinel quality-reports tab — headline, per-area
observations with evidence and suggested actions; read-only, a report has
nothing to approve.

* feat(board): Spackle — gap-fill audit program

Biweekly project-scoped PO cycle over the half-shipped surface area: API
routes without panel surfaces (and vice versa), armed flags without docs,
docs promises the code doesn't keep, dead-end tabs — the inventory diffing
is the PO's own read-tool work, ordered by the spawn prompt with file:line
citations required; the server injects only prior-cycle LEARN and the
rotation target. Rotation is now a shared module-level helper
(pick_rotation_target, parameterized by source) both project-scoped
engines use — pest_control delegates to it, behavior-identical, with a
cross-pollution test proving the two programs' rotations stay independent.
propose_gap_fill mirrors the bug-hunt verb (≤5 items, two-sided evidence
required, participation gate); per-item CEO decide materializes BACKLOG
source=spackle tasks; full Telegram kind incl. approve/reject handlers.
All seven program routers now mount from one helper.

* feat(panel): Spackle gap-fill review queue

Command Center gains the gap-fill queue mirroring the pest-control one —
per-item approve/reject with the two-sided gap evidence rendered.

* feat(board): Scales — monthly portfolio rebalance

Org-scoped PO cycle over the stale backlog: the spawn receives a capped
stale-task snapshot (BACKLOG/PENDING unclaimed >30 days) plus the charter
and prior-cycle LEARN, and files one propose_rebalance — 1-7 items, each a
resolvable task_ref with action reprioritize (validated new priority) or
cancel, rationale required. Per-item CEO decide: approve EXECUTES the
action (audited priority update, or the normal cancel path) — the first
program whose materializer mutates existing tasks instead of creating
them; reject records the reason; LEARN by exploration task id;
all-terminal completes the cycle. Full Telegram decide-kind wiring.
Integrated as the eight-program union (registry, dict dispatch, routers
helper, teardown enumerations).

* feat(panel): Scales rebalance review queue

Command Center gains the rebalance queue — per-item approve/reject with
the action, target task, and rationale rendered.

* feat(board): Mirror — quarterly positioning audit

Project-scoped HoM cycle over messaging surfaces: README claims vs shipped
reality, docs-site promises vs code, charter alignment — the audit is the
HoM's own read-tool work with citations required; the server injects the
charter, prior-cycle LEARN, and the shared rotation target. propose_
messaging_fixes mirrors the gap-fill verb (≤5 items, drift evidence naming
claim + contradicting reality, participation gate); per-item CEO decide
materializes BACKLOG source=mirror documentation tasks; full Telegram
decide-kind wiring. Nine-program union across the shared surfaces.

* feat(panel): Mirror messaging-fixes review queue

* feat(board): Megaphone — HoM standing editorial calendar

Cron cycle (3 days, org-scoped, gated on X credentials — drafting content
nobody can post is pointless): the HoM receives a shipped-this-week digest
plus Unreleased changelog bullets and files one propose_editorial_post
(angle-validated, ≤280, brand voice) that materializes a held x_editorial
draft through the SAME X-queue origination chokepoint release posts use —
zero new approval surface, notifications and CEO decide for free.
Complete-at-propose; cycle auto-closes. Ten-program union.

* feat(panel): x_editorial source labels in the X queue surfaces

* feat(board): Librarian — proactive playbook mining

Biweekly org-scoped Auditor cycle: mines recurring non-private learning
journals (≥2-count grouping with a recency fallback) against the existing
playbook-title inventory and files one propose_playbook_drafts — 1-3
drafts, each with the repeated-pattern evidence that justifies it,
duplicate titles rejected in-batch and against the live store. Drafts are
created via PlaybookService directly (the Coroner precedent — the
'auditor curates but never drafts' do-verb invariant stays intact and
tested) and land in the normal pending-curation queue the Auditor's own
triage already surfaces; no new panel surface. Complete-at-propose;
display-only CEO notification. Eleven-program union.

* feat(board): War Room — release campaign planning

EVENT program with a REAL originator (unlike coroner's stub): a release
publish hooks a campaign brief beside the release-post seam, and the CEO's
run-now originates on demand — the cron loop never fires it. The HoM
designs a 2-6 post arc (teaser → launch → follow-up → spotlight; 280-cap,
future strictly-ascending publish_after, stage vocabulary) and one
propose_campaign call materializes each post as a held x_campaign draft
through the X-queue chokepoint. V1 is manual-cadence by design: publish_
after renders as queue guidance and the CEO approves each post at its
moment — nothing auto-posts, ever; the auto-schedule upgrade is a
documented ceiling. Twelve-program union: full registry complete.

* feat(panel): x_campaign labels + publish-after guidance in the X queue

* feat(board): Barfly — adjacent-conversation replies

Cron cycle (2 days, org-scoped, X-credentials gated): the engine searches
X for conversations where RoboCo is relevant but unmentioned (new OAuth-
signed search_recent on the client; queries + candidate cap configurable),
screens every fetched tweet through the injection guard (stored unclamped
— a clamp was truncating the candidate under the envelope, caught by the
dev's own tests), dedupes via the existing x_seen_mentions ledger (no
migration; also prevents double-drafting against the mentions poll), and
opens one held HoM exploration carrying the screened candidates. propose_
conversation_replies enforces candidate-id-only replies (≤5, 280-cap);
each materializes a held x_barfly draft through the X-queue chokepoint,
threaded via a new in_reply_to seam on post_tweet that only x_barfly
drafts use. The X redraft machinery is now dict-dispatch over per-source
extractors with reply-ref carry for x_barfly. Thirteen-program registry.
War Room's test fakes gained the new abstract search_recent stub.

* feat(board): Dogfood — the PO walks the product

The fourteenth and final registry entry, completing the catalog. EVENT
program (release-publish hook beside the war-room hook + CEO run-now, both
through the same real originator; the cron loop never fires it), project-
scoped with shared rotation. The permission surface is the careful part:
the PO's dogfood spawn — and ONLY that spawn — gets the Playwright MCP
mounted, via a task-scoped fail-closed probe mirroring the video-authoring
precedent (a PO spawned for roadmap/pest/scales never sees browser tools;
tested both ways); the PM agent image bakes chromium unconditionally like
the ux image, the mount stays task-gated in code. The walk targets the
rotation target's live surfaces (panel_base_url only when the target is
the org's own project, honest degradation otherwise); propose_friction_
fixes files ≤5 walked-path-evidenced items; per-item CEO decide
materializes BACKLOG source=dogfood tasks; full Telegram decide kind.
Also: megaphone/librarian/war_room arming keys restored to the settings
validator — their panel toggles would have been rejected (dropped in
earlier unions; the same silent-arming class the drill killed once
already).

* feat(panel): Dogfood friction review queue

* chore(board): final whole-branch sweep fixes

The night's closing adversarial pass over the integrated fourteen-program
registry found ONE functional defect — the war-room test fakes' post_tweet
predated Barfly's in_reply_to_tweet_id kwarg (LSP violation, the only red
in an otherwise fully green gate) — plus doc/test drift, all fixed: the
source-parity test completes to fourteen (spackle/mirror were silently
absent while its neighboring comment claimed full coverage), the PO
identity doc gains its missing Dogfood verb, the auditor quick-list gains
propose_postmortem, three stale comments corrected (rotation docstring,
panel registry header, X source enumerations), the dogfood release-hook
gains the exception-swallow test its four sibling hooks already had, and
the CHANGELOG's Unreleased section documents the whole Board Programs
train. Full make quality: exit 0, all gates green.

* docs: full documentation sweep for the Board Programs train

CLAUDE.md's roadmap-engine entry superseded by the Board Program registry
entry (all fourteen programs, arming, scoping, LEARN, guardrails) with the
role verb tables and playwright row refreshed; docs/rag gains the agent-
facing architecture doc plus full propose_* call-shape sections in the
three board role docs, and corrects the strategy-engine section to shipped
reality (only idle→roadmap is wired); docs/map covers the registry + all
twelve engines with flags, gotchas, and drift notes. The 0.27.0 reference
inventory confirmed only the release-executor's canonical set carries the
version — left for the 0.28.0 cut.

* feat(board): human titles + descriptions on every program surface

Raw registry keys rendered as bare panel labels — an operator reading
x_feature had no idea what enabling or running it does. The registry
dataclass gains title/description (test-enforced non-empty for every
entry, unique titles), the API passes them through, and every surface
renders title-with-description-tooltip instead of the key: the Programs
card (label, toggle hint, run-now toast), and the project settings
participates-in/excluded-from checkboxes.

---------

Co-authored-by: Renn F <rennf93@users.noreply.github.com>
2026-07-25 17:13:32 +02:00

391 lines
12 KiB
Python

"""Sentinel engine: originate ONE held exploration cycle, deduped, never
authors content itself, and — like PeriscopeEngine — needs no per-project
opt-in to RUN (org-scoped: it reads org-wide drift signals, not a repo).
Mirrors test_periscope_engine.py: like periscope, the exploration task's
``project_id`` still resolves against the RoboCo project (a hard
TaskService._require_target_or_umbrella invariant every non-coordination
task carries) even though the program itself needs no per-project opt-in.
Also covers ``evidence_context``'s four aggregate sections, mirroring
test_pest_control_engine.py's evidence-gathering coverage.
"""
from __future__ import annotations
from datetime import UTC, datetime, timedelta
from typing import TYPE_CHECKING, cast
from uuid import uuid4
import pytest
import pytest_asyncio
from roboco.config import settings as cfg
from roboco.db.tables import (
AgentSpawnSessionTable,
AgentTable,
BoardProgramCycleTable,
ProjectConventionFindingTable,
ProjectTable,
SystemSettingTable,
TaskReviewFindingTable,
TaskTable,
)
from roboco.foundation import identity as _foundation
from roboco.models.base import (
AgentRole,
AgentStatus,
Complexity,
TaskNature,
TaskType,
Team,
)
from roboco.models.base import TaskStatus as TS
from roboco.services.sentinel_engine import SentinelEngine
from roboco.services.task import (
PERISCOPE_SOURCE,
PEST_CONTROL_SOURCE,
ROADMAP_SOURCE,
SENTINEL_SOURCE,
X_FEATURE_EXPLORATION_SOURCE,
TaskCreateRequest,
get_task_service,
)
from sqlalchemy import delete, select, update
if TYPE_CHECKING:
from uuid import UUID
from sqlalchemy.ext.asyncio import AsyncSession
SYSTEM_UUID = _foundation.AGENTS["system"].uuid
AUDITOR_UUID = _foundation.AGENTS["auditor"].uuid
SLUG = "roboco"
ONE = 1
@pytest_asyncio.fixture(autouse=True)
async def _purge_board_program_pollution(db_session: AsyncSession) -> None:
"""See test_board_program_engine.py's identical fixture: Board Program
settings-store rows / ledger rows / open exploration tasks are shared,
cross-test-persistent DB state. Purge before every test in this file."""
await db_session.execute(
delete(SystemSettingTable).where(SystemSettingTable.key.like("board_program.%"))
)
await db_session.execute(delete(BoardProgramCycleTable))
await db_session.execute(
update(TaskTable)
.where(
TaskTable.source.in_(
[
ROADMAP_SOURCE,
X_FEATURE_EXPLORATION_SOURCE,
PEST_CONTROL_SOURCE,
PERISCOPE_SOURCE,
SENTINEL_SOURCE,
]
),
TaskTable.status.notin_([TS.COMPLETED, TS.CANCELLED]),
)
.values(status=TS.CANCELLED)
)
await db_session.commit()
async def _seed(session: AsyncSession) -> None:
for uuid, slug, role, team in (
(SYSTEM_UUID, "system", AgentRole.SYSTEM, None),
(AUDITOR_UUID, "auditor", AgentRole.AUDITOR, None),
):
if await session.get(AgentTable, uuid) is None:
session.add(
AgentTable(
id=uuid,
name=slug,
slug=slug,
role=role,
team=team,
status=AgentStatus.ACTIVE,
model_config={},
system_prompt="x",
capabilities=[],
permissions={},
metrics={},
)
)
await session.flush()
session.add(
ProjectTable(
name="RoboCo",
slug=SLUG,
git_url="https://github.com/x/roboco.git",
default_branch="master",
protected_branches=["master"],
assigned_cell=Team.BACKEND,
created_by=SYSTEM_UUID,
is_active=True,
)
)
await session.flush()
def _arm(session: AsyncSession, monkeypatch: pytest.MonkeyPatch) -> None:
session.add(SystemSettingTable(key="board_program.sentinel.enabled", value="true"))
monkeypatch.setattr(cfg, "self_heal_project_slug", SLUG)
# --------------------------------------------------------------------------- #
# run_cycle
# --------------------------------------------------------------------------- #
@pytest.mark.asyncio
async def test_disabled_creates_no_cycle(
db_session: AsyncSession, monkeypatch: pytest.MonkeyPatch
) -> None:
await _seed(db_session)
monkeypatch.setattr(cfg, "self_heal_project_slug", SLUG)
engine = SentinelEngine(db_session)
assert await engine.run_cycle() is None
assert await get_task_service(db_session).list_open_sentinel_cycles() == []
@pytest.mark.asyncio
async def test_no_legacy_flag_backdoor(
db_session: AsyncSession, monkeypatch: pytest.MonkeyPatch
) -> None:
"""No settings-store row at all = disabled — there is no legacy env flag
for sentinel to fall back to (unlike roadmap/x_feature)."""
await _seed(db_session)
monkeypatch.setattr(cfg, "self_heal_project_slug", SLUG)
engine = SentinelEngine(db_session)
assert await engine.run_cycle() is None
@pytest.mark.asyncio
async def test_enabled_originates_held_exploration_task(
db_session: AsyncSession, monkeypatch: pytest.MonkeyPatch
) -> None:
await _seed(db_session)
_arm(db_session, monkeypatch)
await db_session.flush()
engine = SentinelEngine(db_session)
task = await engine.run_cycle()
assert task is not None
open_cycles = await get_task_service(db_session).list_open_sentinel_cycles()
assert len(open_cycles) == ONE
cycle = open_cycles[0]
assert cycle.status == TS.PENDING
assert cycle.confirmed_by_human is False # HELD; board-dispatched only
assert cycle.assigned_to == AUDITOR_UUID
assert cycle.team == Team.BOARD
assert cycle.source == SENTINEL_SOURCE
assert "Sentinel" in cycle.title
@pytest.mark.asyncio
async def test_dedupe_one_open_cycle(
db_session: AsyncSession, monkeypatch: pytest.MonkeyPatch
) -> None:
await _seed(db_session)
_arm(db_session, monkeypatch)
await db_session.flush()
await SentinelEngine(db_session).run_cycle()
second = await SentinelEngine(db_session).run_cycle()
assert second is None
assert len(await get_task_service(db_session).list_open_sentinel_cycles()) == ONE
@pytest.mark.asyncio
async def test_settings_store_false_creates_no_cycle(
db_session: AsyncSession, monkeypatch: pytest.MonkeyPatch
) -> None:
await _seed(db_session)
monkeypatch.setattr(cfg, "self_heal_project_slug", SLUG)
db_session.add(
SystemSettingTable(key="board_program.sentinel.enabled", value="false")
)
await db_session.flush()
engine = SentinelEngine(db_session)
assert await engine.run_cycle() is None
@pytest.mark.asyncio
async def test_unresolvable_project_no_cycle(
db_session: AsyncSession, monkeypatch: pytest.MonkeyPatch
) -> None:
await _seed(db_session)
db_session.add(
SystemSettingTable(key="board_program.sentinel.enabled", value="true")
)
monkeypatch.setattr(cfg, "self_heal_project_slug", "no-such-project")
await db_session.flush()
engine = SentinelEngine(db_session)
assert await engine.run_cycle() is None
assert await get_task_service(db_session).list_open_sentinel_cycles() == []
@pytest.mark.asyncio
async def test_a_completed_cycle_unblocks_the_next_one(
db_session: AsyncSession, monkeypatch: pytest.MonkeyPatch
) -> None:
await _seed(db_session)
_arm(db_session, monkeypatch)
await db_session.flush()
first = await SentinelEngine(db_session).run_cycle()
assert first is not None
first.status = TS.COMPLETED
await db_session.flush()
second = await SentinelEngine(db_session).run_cycle()
assert second is not None
assert second.id != first.id
# --------------------------------------------------------------------------- #
# evidence_context
# --------------------------------------------------------------------------- #
@pytest.mark.asyncio
async def test_evidence_context_empty_when_nothing_to_report(
db_session: AsyncSession,
) -> None:
await db_session.execute(delete(TaskReviewFindingTable))
await db_session.execute(delete(ProjectConventionFindingTable))
await db_session.commit()
context = await SentinelEngine(db_session).evidence_context()
assert context == ""
async def _make_task(session: AsyncSession, *, title: str = "x") -> TaskTable:
await _seed(session)
project = (
await session.execute(select(ProjectTable).where(ProjectTable.slug == SLUG))
).scalar_one()
return await get_task_service(session).create(
TaskCreateRequest(
title=title,
description="x",
acceptance_criteria=["x"],
team=Team.BACKEND,
assigned_to=None,
created_by=SYSTEM_UUID,
task_type=TaskType.CODE,
nature=TaskNature.TECHNICAL,
estimated_complexity=Complexity.LOW,
project_id=cast("UUID", project.id),
status=TS.COMPLETED,
)
)
@pytest.mark.asyncio
async def test_evidence_context_renders_waived_trend(
db_session: AsyncSession,
) -> None:
await db_session.execute(delete(TaskReviewFindingTable))
task = await _make_task(db_session, title="waived-trend task")
now = datetime.now(UTC)
db_session.add(
TaskReviewFindingTable(
id=uuid4(),
task_id=task.id,
origin="qa",
round=1,
author_slug="qa-1",
file="roboco/services/task.py",
line=10,
severity="minor",
expected="x",
actual="y",
status="waived",
created_at=now - timedelta(days=1),
)
)
await db_session.flush()
context = await SentinelEngine(db_session).evidence_context()
assert "waived this week" in context
assert "1 waived this week" in context
@pytest.mark.asyncio
async def test_evidence_context_renders_open_findings_by_severity(
db_session: AsyncSession,
) -> None:
await db_session.execute(delete(TaskReviewFindingTable))
task = await _make_task(db_session, title="open-findings task")
db_session.add(
TaskReviewFindingTable(
id=uuid4(),
task_id=task.id,
origin="qa",
round=1,
author_slug="qa-1",
file="roboco/services/task.py",
line=10,
severity="blocker",
expected="x",
actual="y",
status="open",
)
)
await db_session.flush()
context = await SentinelEngine(db_session).evidence_context()
assert "Open findings by severity" in context
assert "blocker: 1 open" in context
@pytest.mark.asyncio
async def test_evidence_context_renders_conventions_hotspots(
db_session: AsyncSession,
) -> None:
await db_session.execute(delete(ProjectConventionFindingTable))
await _seed(db_session)
project = (
await db_session.execute(select(ProjectTable).where(ProjectTable.slug == SLUG))
).scalar_one()
db_session.add(
ProjectConventionFindingTable(
id=uuid4(),
project_id=project.id,
task_id=None,
file="roboco/api/routes/x.py",
line=5,
rule="thin_routes",
level="block",
message="model defined in router",
)
)
await db_session.flush()
context = await SentinelEngine(db_session).evidence_context()
assert "Conventions-violation hotspots" in context
assert "thin_routes: 1 violations" in context
@pytest.mark.asyncio
async def test_evidence_context_renders_top_task_and_project_spend(
db_session: AsyncSession,
) -> None:
task = await _make_task(db_session, title="expensive task")
db_session.add(
AgentSpawnSessionTable(
id=uuid4(),
agent_slug="be-dev-1",
team="backend",
role="developer",
model="claude-opus-4-8",
task_id=str(task.id),
estimated_cost_usd=12.5,
)
)
await db_session.flush()
context = await SentinelEngine(db_session).evidence_context()
assert "Top spend by task" in context
assert "expensive task: $12.50" in context
assert "Top spend by project" in context
assert f"{SLUG}: $12.50" in context