chore: merge executor worktree (worktree-agent-a4899913938a2f6e7)

This commit is contained in:
lorentz 2026-07-15 07:44:22 -04:00
commit 829cdd4d1d
3 changed files with 462 additions and 0 deletions

View file

@ -0,0 +1,108 @@
---
phase: 15-data-model-detection-ticket-evidence
plan: 02
subsystem: services
tags: [detection, phishing-triage, evidence, postgres, autotask, sha256]
# Dependency graph
requires:
- phase: 15-01
provides: "reports table (ticket_id UNIQUE FK, content_hash, matched_patterns JSONB, evidence JSONB)"
provides:
- "lib/services/phishing-detector.ts — KNOWN_PHISHING_PATTERNS, matchesPhishingPatterns, computePhishingContentHash, gatherTicketEvidence, detectPhishingTicket"
- "One shared detection entry point (detectPhishingTicket) for both the webhook path and cron sweep in Plan 03"
affects: [15-03-webhook-and-sweep, 16-message-parsing]
# Tech tracking
tech-stack:
added: []
patterns:
- "Case-insensitive substring matcher via .toLowerCase()+.includes() only (no RegExp/eval) — mirrors robotic-classifier.evaluateContains"
- "sha256 content-hash over only the fields that define reprocessing eligibility (title+description), excluding bump-prone fields — mirrors analyzer/preprocessor.computeContentHash"
- "Check-before-write idempotency: SELECT existing content_hash, skip evidence-gathering and write entirely when unchanged — mirrors analyzer/persistence.findExistingAnalysisByContentHash"
key-files:
created: [lib/services/phishing-detector.ts, lib/services/phishing-detector.test.ts]
modified: []
key-decisions:
- "Split Task 1 pure-logic implementation from Task 2 evidence/orchestration into two separate commits (test -> feat -> feat) even though both live in the same file, so the TDD RED/GREEN gate sequence is unambiguous in git history"
- "Autotask client instantiated as a lazy module-level singleton with env-var config, mirroring ticket-reconciliation-service.ts's getClient() pattern, rather than introducing a shared factory (out of scope for this plan)"
- "Idempotency guard compares stored reports.content_hash to the freshly computed hash BEFORE gathering evidence, so an unchanged ticket never re-queries ticket_notes/time_entries/Autotask attachments"
patterns-established:
- "Pattern: detector modules expose pure matching/hashing functions separately from the async DB/API orchestration function, so vitest can cover the pure logic without mocking postgresClient or AutotaskClient"
requirements-completed: [DETECT-01, DETECT-02, EVID-01]
# Metrics
duration: 13min
completed: 2026-07-15
---
# Phase 15 Plan 02: Phishing Detector Summary
**`lib/services/phishing-detector.ts` — a single deterministic detection core matching 8 locked DETECT-01 patterns, sha256 content-hashing for D-04 idempotent reprocessing, and EVID-01 evidence capture (company/notes/time-entries/attachment-metadata) upserted into the Plan 01 `reports` table via `ON CONFLICT (ticket_id)`.**
## Performance
- **Duration:** 13 min
- **Started:** 2026-07-15T11:41:00Z
- **Completed:** 2026-07-15T11:47:59Z
- **Tasks:** 2 completed
- **Files modified:** 2
## Accomplishments
- Implemented `KNOWN_PHISHING_PATTERNS` (the 8 locked DETECT-01 strings verbatim) and `matchesPhishingPatterns` — case-insensitive substring matching (`.toLowerCase()` + `.includes()` only, no `RegExp`/`eval`), returning both a `flagged` boolean and the exact subset of patterns present.
- Implemented `computePhishingContentHash` — sha256 over `{ title, description }` only, stable for identical input, changes on either field, and normalizes `null` description to `''`.
- Wrote and ran a 17-assertion vitest suite (`phishing-detector.test.ts`) covering all 8 patterns individually, the negative case, case-insensitivity, matched[] exactness, and hash stability/change/null-normalization — RED confirmed (module didn't exist) before GREEN implementation.
- Implemented `gatherTicketEvidence` — parameterized `$1` queries against `companies`, `ticket_notes`, and `time_entries`, plus Autotask attachment metadata (`fullPath`/`title`/`contentType` only, never base64 `data`), with the Autotask call wrapped in try/catch so an API failure degrades to an empty attachments array instead of throwing.
- Implemented `detectPhishingTicket` — the shared orchestration entry point: matches, hashes, checks the D-04 idempotency guard (SELECT existing `content_hash`, skip gathering/writing when unchanged), then upserts one `reports` row via `ON CONFLICT (ticket_id) DO UPDATE ... RETURNING id`, binding `requester_contact_id` from `ticket.contact_id` and `created_by_contact_id` from `ticket.created_by_contact_id`.
## Task Commits
Each task was committed atomically, with Task 1 following the full TDD RED/GREEN gate sequence:
1. **Task 1 (RED): add failing tests for pattern matcher + content hash** - `0e7daf9` (test)
2. **Task 1 (GREEN): implement phishing pattern matcher + content hash** - `aabf532` (feat)
3. **Task 2: add evidence capture + detectPhishingTicket orchestration** - `15d0caa` (feat)
**Plan metadata:** (this SUMMARY.md commit)
_Note: Task 1 is TDD — test → feat. No REFACTOR commit was needed; the GREEN implementation was already clean._
## Files Created/Modified
- `lib/services/phishing-detector.ts` - Pure matcher/hash functions (`KNOWN_PHISHING_PATTERNS`, `matchesPhishingPatterns`, `computePhishingContentHash`) plus evidence capture and orchestration (`gatherTicketEvidence`, `detectPhishingTicket`) — the shared detection core for Plan 03's webhook and cron-sweep callers
- `lib/services/phishing-detector.test.ts` - 17 vitest assertions covering all 8 locked patterns individually, negative case, case-insensitivity, matched[] exactness, and content-hash stability/change/null-normalization
## Decisions Made
- Split Task 1's pure-logic commit from Task 2's evidence/orchestration commit even though both extend the same file, so the RED (`test(...)`) → GREEN (`feat(...)`) gate sequence required by the TDD workflow is unambiguous in `git log`, and Task 2's orchestration work is its own reviewable `feat(...)` commit.
- Reused the `ticket-reconciliation-service.ts` lazy-singleton pattern for the AutotaskClient (env-var config, module-level cache) rather than introducing a new factory — no existing `getAutotaskClient()`/`isAutotaskConfigured()` factory was present to reuse, and adding one was out of scope for this plan.
- Idempotency check queries only `id, content_hash` from `reports` (not the full row) and returns immediately on a hash match, before any evidence-gathering queries run — this is what makes the D-04 guarantee ("reprocessing only when content hash changed") cheap for the common case of an unchanged ticket being re-scanned by the cron sweep.
## Deviations from Plan
None - plan executed exactly as written. The plan's own Task 1 instruction ("Do not add DB access in this task — pure functions only") was honored by writing only the pure matcher/hash functions in the first commit, then extending the same file with DB/API-touching code in Task 2's commit, exactly as the plan's two-task structure specifies.
## Issues Encountered
None.
## User Setup Required
None - no external service configuration required. The detector uses the existing `AUTOTASK_*` env vars already configured elsewhere in the codebase (no new credentials introduced).
## Next Phase Readiness
- `detectPhishingTicket(ticket)` is ready to be called from both the Autotask webhook handler and a cron sweep in Plan 03 — same underlying logic, no duplicated matching/hashing/idempotency code between the two callers.
- The reports upsert path is fully wired against the Plan 01 schema (`ON CONFLICT (ticket_id)`, `content_hash`, `matched_patterns` JSONB, `evidence` JSONB) — verified via `npx tsc --noEmit --pretty` and the passing vitest suite; no live DB write was exercised in this plan (that happens when Plan 03 wires a real ticket through the detector against the dev Postgres instance).
- No blockers for Plan 03.
---
*Phase: 15-data-model-detection-ticket-evidence*
*Completed: 2026-07-15*
## Self-Check: PASSED
- FOUND: lib/services/phishing-detector.ts
- FOUND: lib/services/phishing-detector.test.ts
- FOUND: .planning/phases/15-data-model-detection-ticket-evidence/15-02-SUMMARY.md
- FOUND: commit 0e7daf9
- FOUND: commit aabf532
- FOUND: commit 15d0caa

View file

@ -0,0 +1,106 @@
import { describe, it, expect } from 'vitest';
import {
KNOWN_PHISHING_PATTERNS,
matchesPhishingPatterns,
computePhishingContentHash,
} from './phishing-detector';
describe('KNOWN_PHISHING_PATTERNS', () => {
it('has exactly 8 locked patterns', () => {
expect(KNOWN_PHISHING_PATTERNS).toHaveLength(8);
});
});
describe('matchesPhishingPatterns', () => {
it('flags a title containing "Phishing Report"', () => {
const result = matchesPhishingPatterns('Fwd: Phishing Report', null);
expect(result.flagged).toBe(true);
expect(result.matched).toContain('Phishing Report');
});
it('flags a title containing "Spam Alert"', () => {
const result = matchesPhishingPatterns('Spam Alert - user reported', null);
expect(result.flagged).toBe(true);
expect(result.matched).toContain('Spam Alert');
});
it('flags a title containing "Phishing Alert - Email Security Report"', () => {
const result = matchesPhishingPatterns('Phishing Alert - Email Security Report', null);
expect(result.flagged).toBe(true);
expect(result.matched).toContain('Phishing Alert - Email Security Report');
});
it('flags a description containing "KnowBe4 Phish Alert Report"', () => {
const result = matchesPhishingPatterns(null, 'This is a KnowBe4 Phish Alert Report for review');
expect(result.flagged).toBe(true);
expect(result.matched).toContain('KnowBe4 Phish Alert Report');
});
it('flags a description containing "Source: KnowBe4 Phish Alert Button"', () => {
const result = matchesPhishingPatterns(null, 'Source: KnowBe4 Phish Alert Button');
expect(result.flagged).toBe(true);
expect(result.matched).toContain('Source: KnowBe4 Phish Alert Button');
});
it('flags a description containing "userSubmissionsReportMessage"', () => {
const result = matchesPhishingPatterns(null, 'Generated by userSubmissionsReportMessage flow');
expect(result.flagged).toBe(true);
expect(result.matched).toContain('userSubmissionsReportMessage');
});
it('flags a description containing "reported message destinations"', () => {
const result = matchesPhishingPatterns(null, 'See reported message destinations below');
expect(result.flagged).toBe(true);
expect(result.matched).toContain('reported message destinations');
});
it('flags a description containing "Microsoft directly"', () => {
const result = matchesPhishingPatterns(null, 'This message was reported to Microsoft directly');
expect(result.flagged).toBe(true);
expect(result.matched).toContain('Microsoft directly');
});
it('does not flag a ticket with none of the patterns', () => {
const result = matchesPhishingPatterns('Re: order confirmation', 'please review invoice');
expect(result.flagged).toBe(false);
expect(result.matched).toEqual([]);
});
it('matches case-insensitively', () => {
const result = matchesPhishingPatterns('SPAM ALERT from user', null);
expect(result.flagged).toBe(true);
expect(result.matched).toContain('Spam Alert');
});
it('returns only the patterns actually present in matched[]', () => {
const result = matchesPhishingPatterns('Phishing Report', 'unrelated body text');
expect(result.matched).toEqual(['Phishing Report']);
});
it('checks both title and description for a match', () => {
const result = matchesPhishingPatterns('Unrelated subject', 'Spam Alert triggered');
expect(result.flagged).toBe(true);
expect(result.matched).toContain('Spam Alert');
});
});
describe('computePhishingContentHash', () => {
it('is stable for identical title+description', () => {
expect(computePhishingContentHash('t', 'd')).toBe(computePhishingContentHash('t', 'd'));
});
it('changes when the title changes', () => {
expect(computePhishingContentHash('t', 'd')).not.toBe(computePhishingContentHash('t2', 'd'));
});
it('changes when the description changes', () => {
expect(computePhishingContentHash('t', 'd')).not.toBe(computePhishingContentHash('t', 'd2'));
});
it('is defined and stable when description is null', () => {
const hash1 = computePhishingContentHash('t', null);
const hash2 = computePhishingContentHash('t', null);
expect(hash1).toBeTruthy();
expect(hash1).toBe(hash2);
});
});

View file

@ -0,0 +1,248 @@
/**
* Phishing Detector
*
* Shared detection core called by both the webhook path (Plan 03) and the
* cron sweep (Plan 03). Matches a ticket's title+description against the 8
* locked DETECT-01 patterns, computes a content hash for D-04 idempotency,
* gathers EVID-01 evidence, and upserts a single `reports` row per candidate
* ticket reprocessing only when the content hash changed.
*
* One deterministic, testable detector with no duplicated matching logic
* between callers (CONTEXT.md discretion: "both call the same underlying
* logic").
*/
import { createHash } from 'crypto';
import { postgresClient } from './postgres-client';
import { AutotaskClient } from './autotask-client';
// =============================================================================
// Pure detection logic — pattern matcher + content hash
// =============================================================================
/**
* The 8 locked DETECT-01 patterns (case-insensitive substring match).
*/
export const KNOWN_PHISHING_PATTERNS: readonly string[] = [
'Phishing Report',
'Spam Alert',
'Phishing Alert - Email Security Report',
'KnowBe4 Phish Alert Report',
'Source: KnowBe4 Phish Alert Button',
'userSubmissionsReportMessage',
'reported message destinations',
'Microsoft directly',
];
/**
* Case-insensitive substring match against the locked pattern list mirrors
* robotic-classifier.evaluateContains (.toLowerCase() + .includes() only,
* NO regex, NO eval).
*/
export function matchesPhishingPatterns(
title: string | null,
description: string | null
): { flagged: boolean; matched: string[] } {
const haystack = `${title ?? ''} ${description ?? ''}`.toLowerCase();
const matched = KNOWN_PHISHING_PATTERNS.filter((pattern) =>
haystack.includes(pattern.toLowerCase())
);
return { flagged: matched.length > 0, matched };
}
/**
* sha256 over title+description only (D-04) does NOT include
* last_activity_date, status, or any bump-prone field, so status/assignee
* churn never forces reprocessing.
*/
export function computePhishingContentHash(
title: string | null,
description: string | null
): string {
return createHash('sha256')
.update(JSON.stringify({ title: title ?? '', description: description ?? '' }))
.digest('hex');
}
// =============================================================================
// Evidence capture + orchestration
// =============================================================================
export interface DetectableTicket {
id: number;
ticket_number: string | null;
title: string | null;
description: string | null;
company_id: number | null;
contact_id?: number | null;
created_by_contact_id?: number | null;
}
interface EvidenceNote {
id: number;
title: string | null;
description: string | null;
note_type: number | null;
creator_resource_id: number | null;
created_at: string;
}
interface EvidenceTimeEntry {
id: number;
resource_id: number | null;
entry_date: string | null;
hours_worked: number | null;
start_date_time: string | null;
end_date_time: string | null;
}
interface EvidenceAttachment {
fullPath: string;
title: string;
contentType?: string;
}
export interface EvidencePayload {
company_name: string | null;
notes: EvidenceNote[];
time_entries: EvidenceTimeEntry[];
attachments: EvidenceAttachment[];
}
let _autotaskClient: AutotaskClient | null = null;
function getAutotaskClient(): AutotaskClient {
if (!_autotaskClient) {
_autotaskClient = new AutotaskClient({
apiUrl: process.env.AUTOTASK_API_URL || '',
username: process.env.AUTOTASK_USERNAME || '',
password: process.env.AUTOTASK_SECRET || '',
apiIntegrationCode: process.env.AUTOTASK_API_INTEGRATION_CODE || '',
});
}
return _autotaskClient;
}
/**
* Gather EVID-01 evidence for a candidate ticket: company name, ticket notes,
* time entries, and attachment metadata (never base64 `data` content fetch
* is Phase 16).
*/
export async function gatherTicketEvidence(
ticket: DetectableTicket
): Promise<EvidencePayload> {
const companyResult = await postgresClient.query<{ company_name: string | null }>(
`SELECT company_name FROM companies WHERE id = $1`,
[ticket.company_id]
);
const company_name = companyResult.rows[0]?.company_name ?? null;
const notesResult = await postgresClient.query<EvidenceNote>(
`SELECT id, title, description, note_type, creator_resource_id, created_at
FROM ticket_notes
WHERE ticket_id = $1
ORDER BY created_at`,
[ticket.id]
);
const timeEntriesResult = await postgresClient.query<EvidenceTimeEntry>(
`SELECT id, resource_id, entry_date, hours_worked, start_date_time, end_date_time
FROM time_entries
WHERE ticket_id = $1
ORDER BY entry_date`,
[ticket.id]
);
let attachments: EvidenceAttachment[] = [];
try {
const rawAttachments = await getAutotaskClient().getAttachments('Tickets', ticket.id);
attachments = rawAttachments.map((attachment) => ({
fullPath: attachment.fullPath,
title: attachment.title,
contentType: attachment.contentType,
}));
} catch (error) {
console.error('[PHISHING-DETECT] Failed to fetch attachments for ticket', ticket.id, error);
attachments = [];
}
return {
company_name,
notes: notesResult.rows,
time_entries: timeEntriesResult.rows,
attachments,
};
}
export interface DetectPhishingResult {
flagged: boolean;
reportId?: string;
skippedUnchanged?: boolean;
}
/**
* Shared entry point called by both the webhook path and the cron sweep.
* Matches, hashes, checks the D-04 idempotency guard, gathers EVID-01
* evidence, and upserts one `reports` row per candidate ticket.
*/
export async function detectPhishingTicket(
ticket: DetectableTicket
): Promise<DetectPhishingResult> {
const { flagged, matched } = matchesPhishingPatterns(ticket.title, ticket.description);
if (!flagged) {
return { flagged: false };
}
const contentHash = computePhishingContentHash(ticket.title, ticket.description);
try {
const existing = await postgresClient.query<{ id: string; content_hash: string }>(
`SELECT id::text AS id, content_hash FROM reports WHERE ticket_id = $1`,
[ticket.id]
);
if (existing.rowCount && existing.rowCount > 0 && existing.rows[0].content_hash === contentHash) {
return { flagged: true, skippedUnchanged: true };
}
const evidence = await gatherTicketEvidence(ticket);
const upsertResult = await postgresClient.query<{ id: string }>(
`INSERT INTO reports (
ticket_id, ticket_number, company_id, company_name, requester_contact_id,
created_by_contact_id, title, description, matched_patterns, content_hash, evidence
)
VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9::jsonb, $10, $11::jsonb)
ON CONFLICT (ticket_id) DO UPDATE SET
ticket_number = EXCLUDED.ticket_number,
company_id = EXCLUDED.company_id,
company_name = EXCLUDED.company_name,
requester_contact_id = EXCLUDED.requester_contact_id,
created_by_contact_id = EXCLUDED.created_by_contact_id,
title = EXCLUDED.title,
description = EXCLUDED.description,
matched_patterns = EXCLUDED.matched_patterns,
content_hash = EXCLUDED.content_hash,
evidence = EXCLUDED.evidence,
updated_at = NOW()
RETURNING id::text AS id`,
[
ticket.id,
ticket.ticket_number,
ticket.company_id,
evidence.company_name,
ticket.contact_id ?? null,
ticket.created_by_contact_id ?? null,
ticket.title,
ticket.description,
JSON.stringify(matched),
contentHash,
JSON.stringify(evidence),
]
);
return { flagged: true, reportId: upsertResult.rows[0].id };
} catch (error) {
console.error('[PHISHING-DETECT] Failed to detect/persist report for ticket', ticket.id, error);
throw error;
}
}