- lib/claude/client.ts: replace Anthropic SDK with openai package pointed at DeepSeek baseURL
- 4 AI routes: port tool definitions, tool_choice, and output parsing to OpenAI function-calling format
- Drop thinking:{type:'adaptive'} (no DeepSeek equivalent); model string → deepseek-chat
- settings/route.ts: add DEEPSEEK_API_KEY to ALLOWED_KEYS
- migration: seed DEEPSEEK_API_KEY placeholder row in app_settings
- tests: update 3 AI route tests to mock createDeepSeekClient + OpenAI response shape
Voyage AI embedding path untouched (DeepSeek has no embeddings endpoint).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CPf5Rc8QPx6V8KLEEgfKEQ
- /api/incidents/[id]/similar: embedding backfill on a closed incident hit
the closure-lock trigger and turned the whole request into a 503; now
skips persistence for closed incidents (vector still used for the query)
- addenda: cap body at 5000 chars; include body text in audit_log entry
- admin users PATCH: 404 when target user does not exist (was silent ok)
- extract shared requireAdmin to lib/auth/require-admin.ts (was duplicated
in admin users + sites routes)
- extract escapeCsv/rowsToCsv to lib/csv.ts (was duplicated in dashboard
export route and lib/reports/jkkp8.ts)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CPf5Rc8QPx6V8KLEEgfKEQ
- Add new migration 20260711000013_match_incidents_auth_guard.sql that
replaces match_incidents with an inline auth guard: callers without
hse/admin role receive PGRST301 Forbidden, closing the SECURITY
DEFINER RLS bypass.
- Wrap anthropic.messages.create() in try/catch returning 503 in all
four AI routes: quality-check, triage-suggest, rca-draft, similar.
- Wrap JSON.parse(inc.embedding) and embedText() in similar/route.ts
in a shared try/catch returning 503 Embedding service unavailable.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FFDuBhMKvoWjrWT3ZnGmmr
Adds POST /api/incidents/ai/quality-check using Claude tool_use to score incident descriptions 1-10. Report form blocks submission when score < 6, shows amber feedback with suggestions, and offers a 'Submit anyway' override.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FFDuBhMKvoWjrWT3ZnGmmr
adminandClaude Sonnet 4.6