Real Anthropic Claude integration per explicit product decision: a
ticket's AI session diagnoses the problem via a structured-output call,
applies a DB-configurable confidence-band policy (FR-005), and on
"proceed" reasons and acts through a small permission/risk-gated tool
system (FR-011/FR-012), optionally walking a matching runbook step by
step with the application — never the model — owning the step index
(FR-015/FR-016). Resolution requires real tool evidence, never customer
claims alone (FR-018) — verifyProductResolution is a documented
fail-closed placeholder mirroring the existing malware-scanner precedent,
since no real per-product operational signal exists yet.
AISupportSession.status mirrors onto Ticket.status through 003-ticketing's
existing AI_ANALYZING/AI_TROUBLESHOOTING/AI_VERIFYING/AI_RESOLVED/
HUMAN_ESCALATION state machine, discovered during planning to have been
built anticipating this exact feature. Two circular module dependencies
(escalation<->sessions, tools<->sessions) were designed around rather than
found as bugs: escalation is a pure summary formatter with no state
dependencies of its own, and tools stays a clean leaf module with zero
dependency on ai-support/sessions. Ticket creation enqueues the first
diagnosis turn via the existing queue infrastructure (off the hot path of
the inbound SaaS integration endpoint); a human actor changing ticket
status ends the AI session via the event-bus scaffold that existed in
this codebase but had never been wired to anything.
A real Prisma limitation was found and fixed before it reached tests:
compound-unique upsert rejects null for a nullable key column, so
AIConfidencePolicy uses find-then-update/create instead, same fix class
004 already used for the same underlying limitation.
Adds 9 unit tests (confidence-band, tool-policy-gate, runbook-step-
advance) and 6 integration test files, including the two constitution-
required standing E2E scenarios. AI-independent tests were run against
real Postgres/Redis/MinIO (88 passed, 0 failed across the full suite,
including every pre-existing 002/003/004 test). The AI-dependent tests
compile and skip cleanly via describe.skipIf but were not run against a
live model — no ANTHROPIC_API_KEY was available in this session; a real
key must be supplied before this feature can actually run.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
003-ticketing's ticket-state-machine.ts already defines AI_ANALYZING/
AI_TROUBLESHOOTING/AI_VERIFYING/AI_RESOLVED/HUMAN_ESCALATION ticket
statuses, clearly authored anticipating this feature. Corrects the plan
before implementation: AISupportSession.status now drives Ticket.status
through the existing ticketsService.updateStatus (reusing its optimistic
concurrency), instead of an isolated status field the rest of the system
never sees. Also clarifies that knowledge retrieval is an in-process
service call through knowledge's index.ts, not an HTTP loopback.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Phase 4 of the roadmap: AI session/diagnosis, confidence-band policy,
permission/risk-gated tool system, runbook execution, and evidence-based
verification. Per explicit decision, reasoning integrates a real LLM
provider (Anthropic Claude) rather than a mock.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
