DoD M7 (spec §F5 + §F6 + §F8 + tasks/todo.md M7) covered end-to-end:
Backend
- New migration `91a4e7c6d2f3` adds `mission_tests.last_actor_id` (FK users
ON DELETE SET NULL) and `ix_mission_tests_updated_at` for the polling query.
- `detection_levels`: 4 default rows seeded at boot, `GET /detection-levels`
read-only (CRUD lands in M8).
- `mission_tests` service + `missions` API extension:
- `GET /missions/{id}/tests/{test_id}` — full detail incl. evidence list
- `PUT /missions/{id}/tests/{test_id}` — patch red/blue fields with per-field
perm classification (`mission.write_red_fields` vs `mission.write_blue_fields`)
- `POST /missions/{id}/tests/{test_id}/transition` — pending↔skipped/blocked
and pending→executed→reviewed_by_blue (+ undo paths), side-aware perm gate
that fires *before* idempotency, `executed_at` auto-stamped on the way in
- `GET /missions/{id}/activity?since=<ISO>` — drives the 15 s polling badge
- `evidence` service + top-level `/evidence/<id>` API:
- Streaming upload, SHA256 chunk-by-chunk, 25 MB cap, ext+MIME whitelist
- Content-addressed storage at ${EVIDENCE_DIR}/<mission>/<test>/<sha256><ext>
- Atomic `os.replace`, hex-validated SHA path component, root-dir guard
- Membership-aware (404 on miss/forbidden, no existence leak)
- `/diag/reset` now wipes ${EVIDENCE_DIR}/* in test mode (symlink-safe) and
re-seeds detection levels as a safety net.
Frontend
- `lib/missions.ts` — M7 types + queryKey factory + state-machine matrix.
- `pages/MissionTestPage.tsx` — two-zone layout: red border (command, output,
comment, mark-executed + override toggle) and cyan border (detection-level
select, comment, drag-and-drop evidence dropzone). Last-touched badge polls
/activity every 15 s, gated on document.visibilityState. Per-field disable
based on the user's red/blue perms (server stays the arbiter).
- `pages/MissionDetailPage.tsx` — test rows link to the new per-test page.
- `App.tsx` — registers /missions/:id/tests/:testId behind RequireAuth.
- `HomePage.tsx` — hero + roadmap card bumped to M7; next is M8.
Tests
- `backend/tests/test_mission_tests.py` — 27 pytest tests (red/blue field
gating, state-machine matrix incl. idempotent-side enforcement, executed_at
override, 24/26 MB upload + SHA256, MIME/ext whitelist, soft-delete hide,
activity polling with URL-encoded `since`, membership 404 vs admin bypass,
cross-mission evidence access).
- `e2e/tests/m7-execution.spec.ts` — 5 Playwright tests against the live stack
(red-only/blue-only API gating, mark-executed + reviewed_by_blue side
enforcement, 24 MB/26 MB upload + SHA256 round-trip, SPA per-test page save
+ transition, non-member 404 message). afterAll restores stable admin and
re-syncs MITRE.
Docs
- CHANGELOG.md: M7 section + post-M7 review-pass subsection.
- README.md: status, feature blurb, roadmap, testing-m7 link.
- tasks/testing-m7.md: manual + automated procedure with transition matrix
and perm-gating table.
- tasks/lessons.md: M7 retrospectives (LogRecord `created` trap, URL-encoded
query timestamps, perm-before-flush, atomic move, polling visibility gate).
Test count: 133 pytest / 49 Playwright, all green.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
162 lines
6.9 KiB
Python
162 lines
6.9 KiB
Python
"""Operational diagnostics. No auth in v1 (M0/M1 only expose non-sensitive
|
|
counts and the current Alembic revision).
|
|
|
|
The `/diag/reset` endpoint is **test-only** — it requires `APP_ENV=test` and
|
|
is the bedrock of the e2e suite (clean DB + freshly minted install token).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
import shutil
|
|
from pathlib import Path
|
|
|
|
from flask import Blueprint, abort, jsonify
|
|
from sqlalchemy import text
|
|
from sqlalchemy.exc import SQLAlchemyError
|
|
|
|
from app.core.config import settings
|
|
from app.core.install_token import regenerate_install_token
|
|
from app.db.session import get_engine
|
|
from app.services.detection_levels import seed_detection_levels
|
|
|
|
bp = Blueprint("diag", __name__, url_prefix="/diag")
|
|
log = logging.getLogger("metamorph.diag")
|
|
|
|
|
|
@bp.get("/db")
|
|
def db_diag():
|
|
"""Return the Alembic revision and the count of public-schema tables."""
|
|
try:
|
|
with get_engine().connect() as conn:
|
|
revision = conn.execute(
|
|
text("SELECT version_num FROM alembic_version")
|
|
).scalar()
|
|
table_count = conn.execute(
|
|
text(
|
|
"SELECT count(*) FROM information_schema.tables "
|
|
"WHERE table_schema='public' AND table_type='BASE TABLE'"
|
|
)
|
|
).scalar_one()
|
|
except SQLAlchemyError as e:
|
|
log.warning("metamorph.diag.db_unreachable", extra={"error": str(e)})
|
|
return jsonify({"reachable": False, "error": "database_unreachable"}), 503
|
|
|
|
return jsonify(
|
|
{
|
|
"reachable": True,
|
|
"alembic_revision": revision,
|
|
"table_count": int(table_count),
|
|
}
|
|
)
|
|
|
|
|
|
@bp.post("/reset")
|
|
def reset_test_state():
|
|
"""TEST-ONLY: wipe users/auth tables and mint a fresh install token.
|
|
|
|
Refuses unless `APP_ENV=test`. Used by the Playwright suite to start each
|
|
auth scenario from a deterministic state.
|
|
"""
|
|
# NOTE: this endpoint is the test-suite reset hook. Allowed in `dev` too so
|
|
# the e2e suite can run against a normal `make up` stack, but in dev it is
|
|
# destructive — equivalent to `make clean` for the auth tables. Production
|
|
# (APP_ENV=prod/staging) is locked out.
|
|
if settings.APP_ENV not in ("dev", "test"):
|
|
abort(403, description="diag/reset is only available in dev/test")
|
|
if settings.APP_ENV == "dev":
|
|
log.warning("metamorph.diag.reset_in_dev_environment")
|
|
|
|
try:
|
|
with get_engine().begin() as conn:
|
|
# Auth + RBAC + settings reset.
|
|
conn.execute(
|
|
text(
|
|
"TRUNCATE users, refresh_tokens, invitations, invitation_groups, "
|
|
"user_groups, settings, groups RESTART IDENTITY CASCADE"
|
|
)
|
|
)
|
|
# Mission catalogue reset (M6). Truncated before the template tables
|
|
# below because `mission_scenarios.source_scenario_template_id` and
|
|
# `mission_tests.source_test_template_id` are ON DELETE SET NULL — a
|
|
# cascade-truncate of templates would attempt to null those columns
|
|
# and stall on the constraint check. Wiping the mission tables first
|
|
# avoids that round-trip; cascades from `missions` then take care of
|
|
# members, scenarios, tests, mitre_tags, categories.
|
|
conn.execute(
|
|
text(
|
|
"TRUNCATE mission_test_mitre_tags, mission_tests, "
|
|
"mission_scenarios, mission_categories, mission_members, "
|
|
"missions RESTART IDENTITY CASCADE"
|
|
)
|
|
)
|
|
# Template catalogue reset (M5). The MITRE truncate below cascades to
|
|
# the polymorphic tag join, but the template rows themselves must be
|
|
# wiped first because `scenario_template_tests.test_template_id` is
|
|
# ON DELETE RESTRICT.
|
|
conn.execute(
|
|
text(
|
|
"TRUNCATE scenario_template_tests, scenario_templates, "
|
|
"test_template_mitre_tags, test_templates "
|
|
"RESTART IDENTITY CASCADE"
|
|
)
|
|
)
|
|
# MITRE reference reset — kept in sync with `settings` so a freshly
|
|
# reset stack has `GET /mitre/status` and `GET /mitre/tactics` agree
|
|
# ("no data, no last_sync"). The e2e suite re-syncs via /mitre/sync
|
|
# when it needs catalogue data.
|
|
conn.execute(
|
|
text(
|
|
"TRUNCATE mitre_technique_tactics, mitre_subtechniques, "
|
|
"mitre_techniques, mitre_tactics RESTART IDENTITY CASCADE"
|
|
)
|
|
)
|
|
# Detection levels (M7) are reference data seeded at boot — they
|
|
# are explicitly preserved here, but the seed is re-run below to
|
|
# cover the edge case where an operator hand-tweaked the rows
|
|
# before invoking the reset. The seed is idempotent.
|
|
except SQLAlchemyError as e:
|
|
log.error("metamorph.diag.reset_failed", extra={"error": str(e)})
|
|
return jsonify({"reset": False, "error": "database_error"}), 500
|
|
|
|
# M7: wipe the evidence directory so an e2e suite that uploads bytes does
|
|
# not accumulate files across runs. Only in `test`; in `dev` we keep the
|
|
# files (operator likely wants to inspect what they uploaded by hand).
|
|
if settings.APP_ENV == "test":
|
|
evidence_root = Path(settings.EVIDENCE_DIR)
|
|
if evidence_root.exists():
|
|
for child in evidence_root.iterdir():
|
|
# Symlinks are unlinked, never followed — a hostile or
|
|
# accidental symlink inside the evidence dir must NOT cause
|
|
# rmtree to recurse into an unrelated tree.
|
|
try:
|
|
if child.is_symlink() or not child.is_dir():
|
|
child.unlink(missing_ok=True)
|
|
else:
|
|
shutil.rmtree(child)
|
|
except OSError as e:
|
|
log.warning(
|
|
"metamorph.diag.evidence_cleanup_failed",
|
|
extra={"path": str(child), "error": str(e)},
|
|
)
|
|
|
|
# Detection levels were preserved during the wipe; re-run the seed to
|
|
# cover the off-chance an operator has deleted some rows manually.
|
|
seed_detection_levels()
|
|
|
|
token = regenerate_install_token()
|
|
|
|
# Clear the in-memory rate-limit counters so the e2e suite that follows can
|
|
# log in repeatedly without hitting `/auth/login`/`/auth/refresh` limits.
|
|
# The limiter uses `memory://` in dev (cf. `app/core/rate_limit.py`).
|
|
try:
|
|
from app.core.rate_limit import limiter # noqa: PLC0415 — avoid import cycle
|
|
|
|
if limiter.enabled:
|
|
limiter.reset()
|
|
except Exception as e: # noqa: BLE001
|
|
log.warning("metamorph.diag.rate_limit_reset_failed", extra={"error": str(e)})
|
|
|
|
log.warning("metamorph.diag.reset_completed")
|
|
return jsonify({"reset": True, "install_token": token})
|