Eight sub-phases per docs/ticket-analyzer-phase2-spec.md:
2.1 Schema (migration 070): analyzer_stage_executions table; source_snapshot,
aggregate_fingerprint, fingerprint_generated_at columns on analyzer_analyses.
model_traces marked LEGACY (kept for back-compat).
2.2 Every pipeline stage records a row to analyzer_stage_executions, success
or failure. Worker persists a status='failed' analyzer_analyses row when
the pipeline throws so partial stage records have a parent. Pipeline
exposes raw triage/sonnet/opus responses for downstream stages.
2.3 Stage 3 prompt updated with markdown formatting rules + banned filler
phrases. Added react-markdown + remark-gfm + @tailwindcss/typography.
New <AnalysisMarkdown> component replaces <ProseText>; coerces stray
headers to bold paragraphs.
2.4 Stage 6 fingerprint (Haiku) runs after persistence, failure-tolerant.
scripts/backfill-fingerprints.ts reconstructs Stage 6 input from the
legacy model_traces blob.
2.5 Browse UI rebuild at /analyzer/tickets: multi-select for client/issue/
queue/status/priority/assignee, sticky filter bar, active-filter chips,
bulk selection persisted via localStorage, "Analyze N selected" +
"Generate aggregate report" actions. New <MultiSelect> primitive.
Staleness uses last_activity_date > completed_at heuristic per spec C.1.
2.6 Aggregate reports (migration 071): runner is fire-and-forget, persists
SQL distributions immediately so UI shows partial state during the
Sonnet reduce call. Three endpoints, three pages (/analyzer/reports[/new
/:id]). IT Glue context fetcher capped at 200 doc titles.
2.7 Cost guards (migration 072): per-request $5 confirmation, soft-warn at
$20/day, hard-block at $50/day with ANALYZER_DAILY_COST_OVERRIDE_USERS
override. Every gating decision audited.
2.8 Runbook + build notes updated.
128 vitest tests passing, tsc clean. Migrations 070/071/072 idempotent
(IF NOT EXISTS). model_traces double-write retained — drop in a future
migration once aggregate reports have soaked.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- /analyzer/tickets — period chips (today/yesterday/this+last
week/30d/60d/all), client + issue-type Selects, debounced search,
per-row Analyze/Re-analyze plus View shortcut when an analysis
already exists.
- API: /api/analyzer/tickets/list (period/companyId/issueType/search,
paginated via COUNT(*) OVER) and /filter-options (companies that
actually have tickets, active issue types).
- ProseText helper in analysis-view splits on blank lines and renders
each chunk with leading-7 — Summary, Next Step, rationale, and
Post-Resolution now have proper paragraph rhythm. Next Step card
re-styled with bg-primary/5 tint, ArrowRight icon, and an indented
rationale block.
- Top-level "Analyzer" nav menu (Browse Tickets + Needs Review).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
docs/wulf-pulse-ticket-analyzer-runbook.md covers cost monitoring
queries, the $2 cost ceiling, IT Glue alias workflow, failure triage
(failed jobs vs needs_human_review), and manual ops (queue from psql,
force re-run, inspect model_traces). Calls out the manual migration
step for existing DBs and lists the unimplemented surfaces (no auto
retries, no viewed_at, no email_sent_at) so operators don't trip on
them. Linked from README.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
sendAnalysisShareEmail() reuses the existing nodemailer SMTP transport
(same path as magic-link/invitation mail). Share route persists the
audit row first, then attempts send; on failure returns
{share, emailSent:false, emailError} at HTTP 200 so the audit log
stays intact. Modal surfaces send failures as a warning toast.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
