Software Updates

Fix 7 meeting bugs: Yen logo blend, non-overlapping layout, 2-phase voice, guest Hey Yen stale closure, missing notes route, rounded YenPanel, allowGuestYenRef

Fix build error: rename branding.ts to branding.tsx (file contains JSX)

Fix overlapping UI: subtitle-aware offsets for Yen+chat panels; white Yen logo; context-aware invocation; block same-lang translation; meetings open in new tab

Fix in-meeting chat sidebar layout: flex-col container so messages scroll and input pins to bottom

Logo refresh + meeting UX: circular Yen logo, subtitle overlay, invite dual-action

• Added public/yen-logo.png (black cursive Yen script on transparent bg)
• admin/yen page: all 4 logo instances → circular dark navy (#0b1527) circle with Yen logo (rounded-full + overflow-hidden + ring-1) Empty-state hero circle is now h-20 w-20 (larger than before)
• YenBubble FAB: gradient rose→indigo replaced with dark navy circle + Yen logo. Panel header + message avatars + empty-state all updated.
• Meeting toolbar Yen button: Sparkles icon replaced with Yen logo PNG (filter:invert so black→white to match other toolbar icons, 70% opacity when inactive, 100% when active)

Fix 400 error + chat panel height + toggle + sentence case

• FIX 1 — 400 'Invalid value: function_call' (CRITICAL — Yen broken):
• The llm-adapter was using the OpenAI Responses API for ALL OpenAI-
• compatible providers, including xAI. But the Responses API is only
• supported at api.openai.com — xAI (api.x.ai) and all other compat
• hosts only speak Chat Completions. When failover or primary hit xAI,
• the adapter sent Responses API format (input[] with type:function_call
• items), which xAI rejected with 400 'Invalid value: function_call'.
• Fix: added apiStyle: 'responses_api' | 'chat_completions' to
• ModelAssignment. OpenAI assignments get responses_api; xAI gets
• chat_completions. Added full Chat Completions path in llm-adapter:
• callOpenAIChatCompletions() + streamOpenAIChatCompletions(). Dispatch
• in callLLM/streamLLM routes to correct path based on apiStyle.
• FIX 2 — Yen chat panel opened as small window (height not constrained):
• YenChatPanel is 'absolute top-0 bottom-0 left-0' — but for top/bottom
• to constrain height, the element needs a positioned ancestor (relative/
• absolute/fixed). The left column div was position:static, so the panel
• had no containing block and height was auto (content-only). The panel
• appeared as a small box the height of its header + input.
• Fix: added 'relative' class to the left column div. YenChatPanel now
• fills the full height of the column (top:0 to bottom:0).
• FIX 3 — Toggle switch knob moved outside the pill boundary:
• Both subtitle toggles used 'top-1 w-4 h-4 translate-x-1/translate-x-6'.
• The container is w-11 h-6 (44x24px). With translate-x-6 (24px) and
• a 16px knob, the right edge was at 40px — technically inside 44px but
• visually hugging the rounded edge. Changed to 'top-0.5 left-0.5 w-5 h-5
• translate-x-0/translate-x-5': 2px padding on all sides, visually clean.
• FIX 4 — Subtitle text forced lowercase (Deepgram returns all-lowercase):
• subtitle-panel.tsx had textTransform:'lowercase' as the default (non-
• caps) case, making all-caps mode the only way to see capitalised text.
• Fix: changed default to textTransform:'none' and added sentenceCase()
• helper that capitalises the first letter of the string and after . ! ?
• Applied to all transcript text and translations.

Fix 3 persistent bugs: tile dismiss, shipping state inference, lookup resilience

• BUG 1 — Yen tile X still not clickable (stacking context):
• The tile lives inside 'absolute inset-0 flex gap-1' which had NO
• z-index, so it defaulted to z-auto (0). The title bar is a SIBLING
• at z-30 — it painted over the entire tile including the X button.
• The previous fix (z-10→z-40 inside the tile) was irrelevant because
• z-40 only applied within the tile's local stacking context.
• Fix: (a) Moved dismiss button OUT of YenMeetingTile, rendering it as
• a sibling element in the parent at z-40 — same stacking context as
• the z-30 title bar, so it wins. (b) Added z-0 to the video container
• so it participates in the parent stacking context explicitly.
• BUG 3 — Shipping fails for Miami / certain ZIPs:
• ShipStation carriers require toState for reliable rate lookups. When
• the model omitted toState (common — it only passes ZIP), carriers
• returned errors silently. Added zipPrefixToState() that auto-infers
• the US state from the first 3 digits of any ZIP code. Also added
• toCity to the tool schema + API call so carriers get full address
• context. Tool description now says ALWAYS provide toState.
• BUG 4 — Stella lookup still failing (unguarded queries):
• workerProfile.findMany() and emailContact.findMany() had NO
• .catch(() => []) — if either table/migration doesn't exist in prod,
• the exception killed the ENTIRE execLookupClient function, hiding
• results from buckets that DID succeed (User, JewelryProject).
• Fix: added .catch(() => []) to both queries, matching the pattern
• already used on the other two buckets.

Fix 4 Yen/meeting bugs: tile dismiss, chat input, shipping origin, lookup

• BUG 1 — Yen tile X button never worked:
• Dismiss button was z-10 inside a stacking context where the title bar
• is z-30. When user hovers (which keeps the title bar visible), the bar
• ate the click. Fixed: z-10 → z-40 in yen-meeting-tile.tsx.
• BUG 2 — No text input/confirm in Yen chat panel after voice trigger:
• publicMode=true caused the panel to 'return null' before rendering,
• leaving the host with no way to type follow-ups or confirm actions.
• Fixed: remove the early null-return. Panel now always renders when
• open; the 'Broadcasting' badge still communicates public mode.
• BUG 3 — Shipping rates used wrong origin (Cartersville/Austin, not user-specified):
• Both the meeting yen-chat get_shipping_options tool (ShipStation) and
• the general yen chat getShippingRates tool (ShipEngine) had hardcoded
• ship-from with no origin parameters in the schema. The model couldn't
• pass 'from Greenville SC' even when the user said it explicitly.
• Fixed: added fromCity/fromState/fromZip params to both tool schemas
• and handlers. Origin defaults to studio but overrides when provided.
• BUG 4 — Stella's email not found (lookup silently failed):
• execLookupClient was querying User.firstName, User.lastName,
• User.jobTitle, User.department — columns that don't exist in the DB
• schema. Prisma threw 'column does not exist', which was caught and
• returned as 'Could not search contacts: ...' — model then asked for
• the email. Fixed: User query now only uses name + email (guaranteed).
• WorkerProfile + JewelryProject buckets get individual .catch(() => [])
• so one missing table never kills the whole lookup.

Add @mention autocomplete to live meeting invite panel

• Typing '@' in the invite name field triggers the existing suggest-participants API (team / past guests / clients)
• Debounced 180ms — won't fire on every keystroke
• Dropdown shows avatar initial, full name, email, and colored kind badge (blue=team, teal=client, amber=guest)
• Arrow keys + Enter for keyboard navigation; Escape to dismiss
• Selecting a suggestion prefills both name AND email fields
• X clear button resets the field and re-focuses
• @-less input: plain text mode, no suggestions (new guest names)
• Panel close + 'Invite another' both clear autocomplete state
• Zero changes to invite/join/token flow — guests still get full LiveKit permissions via the signed token at /g/[token]

Remove Opus entirely — Sonnet is the hard ceiling

• OPUS_MODEL constant removed from model-router.ts
• isOpusAllowed() helper removed
• Opus removed from HIGH_STAKES failover chain
• Opus confirmation wall removed from yen/chat route
• YEN_MODEL_OPUS env var no longer referenced anywhere
• Pricing table in header updated — Opus entry removed
• Header comment updated: 'Sonnet is the hard ceiling. No Katura use case justifies Opus.'

Demote Opus from automatic primary to last-resort confirmation wall

• Opus is no longer the primary model for HIGH_STAKES when YEN_ALLOW_OPUS=true. Sonnet is now the ceiling for all automatic routing.
• In the failover chain, Opus moves to dead last — only reachable if every other provider (Sonnet, Grok-4, GPT) fails AND YEN_ALLOW_OPUS=true.
• New Opus pre-flight in yen/chat route: if the chain contains an Opus assignment and opusApproved != true, returns HTTP 402 with cost warning instead of calling the model. UI must re-POST with opusApproved: true.
• Cost warning includes estimated $/call for both Opus and Sonnet so the user can make an informed decision.

Wire general yen/chat through failover + add ensemble mode for HIGH_STAKES

• yen/chat (general sidebar) now routes anthropic/openai through callLLMWithFailover — automatic xAI/Grok fallback on 5xx/429/timeout
• Classifier runs once per request; spend records against actual served model + classified task class (no more hardcoded CORE_ASSISTANT)
• Groq/Ollama keep legacy single-shot path (local/free dev only)
• New callLLMEnsemble() runs the whole chain in parallel for HIGH_STAKES, picks consensus by tool-call agreement → text centrality → first success
• Opt-in via YEN_ENSEMBLE_MODE=true (~3x cost, ~90¢/call)
• Strategy doc updated with ensemble section + new env flag

xAI provider + failover + deterministic classifier

• Add 'xai' provider (XAI_API_KEY, https://api.x.ai/v1)
• Add grok-4-fast ($0.20/$0.50) and grok-4 ($3/$15) models
• New getFailoverChain(task) returns ordered fallback list
• ROUTING/EXTRACTION now prefer Grok-4-fast (cheapest output anywhere)
• HIGH_STAKES chain: Sonnet → Grok-4 → GPT-5.4 (third opinion)
• CLIENT_WRITING unchanged: Claude is still the velvet glove
• OpenAI clients now use assignment.baseUrl (xAI works as drop-in)
• xAI dispatches through OpenAI Responses API path (compatible)
• New callLLMWithFailover() and streamLLMWithFailover()
• isRetryableError() classifies 5xx/429/timeout/connection errors
• onFailover callback for observability + cost tracking
• classifyRequest({query, context, hint}) — zero-cost, microseconds
• Risk catalogs: legal, financial, compliance, PII keywords
• Auto-escalates to HIGH_STAKES on any risk signal
• Verb-based natural classification (writing/summary/routing)
• Length-based escalation: >20K tokens requires standard tier
• Caller hint as floor — never downgrades below requested tier
• Classifies every query before model selection
• Uses streamLLMWithFailover with full chain
• Records spend against actually-served model (post-failover)
• recordSpend now uses classification.taskClass (was hardcoded)
• Logs escalation reasons for audit trail
• Adds 'xai' to PROVIDER_COLORS (orange)
• Provider detection now recognizes grok-* models
• Adds 'import type React' to fix React.ElementType reference
• Full provider matrix + failover behavior + classifier rules
• Pricing reference, env vars, end-to-end flow diagram
• Cost & output wins per optimization
• Future work: ensemble voting, A/B testing, per-tenant routing

enterprise-grade AI usage dashboard

• Add byTaskClass breakdown (EXTRACTION/ROUTING/SUMMARY/etc.)
• Add byProvider aggregation (OpenAI vs Anthropic split)
• Add previousPeriodTotals + trend % (cost/calls/tokens vs prior period)
• Add avgCostPerCall to byModel and byTaskClass
• Add provider field to byModel rows
• Add memoryHealth from memory-graph.ts getMemoryHealth()
• Add routingConfig snapshot showing active model assignments
• Add approvalRequired + fraction to budget response
• Fix BigInt literal compat (BigInt(0) vs 0n)
• Daily sparkline now includes totalIn/totalOut per day
• Period selector tabs (Today / This Week / This Month)
• KPI cards with trend indicators vs previous period
• Budget progress bar with color thresholds + approval warning
• Provider split stacked bar (emerald=OpenAI, violet=Anthropic)
• Task class table with unit economics (avg cost/call)
• Enhanced By Model table with provider dot + avg/call
• By Source table now shows task class labels
• Memory Graph Health card (nodes, types, durability, confidence)
• Active Routing Config table (task → model → tier badge)
• Token Rate Limits with per-user and team-wide progress bars
• Loading spinner on period change (non-blocking)

wire streaming loop through streamLLM adapter

• Add streamLLM / LLMMessage / LLMToolDef imports
• Add LLM_TOOLS constant mapping Anthropic.Tool[] → LLMToolDef[]
• Convert thread messages to LLMMessage[] format
• Replace agentic loop with StreamEvent consumer
• Tool execution functions and SSE surface unchanged
• Remove direct Anthropic client instantiation from handler

multi-model routing: OpenAI + Claude per task class

• Routes by provider + model per task class
• EXTRACTION/ROUTING → OpenAI nano ($0.20/$1.25)
• SUMMARY/CORE_ASSISTANT → OpenAI mini ($0.75/$4.50)
• CLIENT_WRITING/HIGH_STAKES → Claude Sonnet ($3/$15)
• Falls back to Anthropic-only if no OPENAI_API_KEY
• Updated pricing: Haiku $1/$5, Sonnet $3/$15, Opus $5/$25
• Unified callLLM() + streamLLM() over both providers
• OpenAI: Responses API (not legacy Chat Completions)
• Anthropic: Messages API via SDK
• Normalized tool definitions, responses, streaming events
• Extraction now uses EXTRACTION task class (was SUMMARY)
• Both extraction + summary wired through llm-adapter
• Provider-agnostic: routes to nano/mini when OpenAI available
• Added checkMonthlyBudget() before streaming (was missing)
• Added recordSpend() after response with token tracking
• Memory writeback now passes clientId/projectId
• Hoisted meeting lookup IDs for both retrieval and writeback
• Applied Virgil corrections (Responses API, advisory classifier)
• Applied Codex audit findings (6 bugs fixed)
• Updated implementation status

add multi-model routing plan (OpenAI + Claude)

wire memory + validation into live meeting Yen

• Load KV memories (loadRelevantMemories) + graph memories (buildMemoryContext) before every Claude call in yen-chat route
• Inject client/project-scoped memory into system prompt
• Add 6-point validation checklist (names, live data, fabrication guard)
• Post-response memory writeback via processTranscriptIntoMemory
• Update YEN-CAPABILITY-AUDIT.md with implementation status

Yen capability audit — strengths, weaknesses, and roadmap to agent

no eager autocomplete + Yen system prompt overhaul + weather dispatch

• Remove eager load of all contacts when instant meeting modal opens
• Suggestions only appear when user has typed ≥1 character
• onFocus no longer fetches empty query
• Replaced rule-list style with a real PA persona: proactive, autonomous, acts-then-confirms rather than asks-permission-to-try
• 'Use the transcript' — explicitly instructed to scan meeting context for names/emails mentioned earlier in the call
• Lookup before email: silently call lookup_client without announcing it; only ask for email if lookup AND transcript both yield nothing
• 'Incomplete sentences are okay' — Yen should infer intent from context rather than waiting for a grammatically complete request
• Tools described by trigger pattern, not as a checklist
• Removed bureaucratic preamble ('Great question!', 'Certainly!')

private Yen mode + listening indicator + weather tool + guest speaking language

• Sparkles toolbar button now opens Yen in PRIVATE mode (publicMode=false) so no tile is broadcast to other participants
• Voice-triggered 'Hey Yen' still fires publicly (tile visible to all)
• Host now has full interactive YenChatPanel in private mode (confirm/ decline/type context) without guests seeing anything
• 'Yen is listening…' pulsing amber badge appears at top-center of meeting room from wake-word detection until query fires
• Hold phrases (wait/also/forgot etc) extend the wait by +1500ms
• Logic simplified to shared firePendingQuery() callback
• New get_weather tool added to yen-chat route and panel labels
• Uses Open-Meteo geocoding + forecast APIs (free, no API key needed)
• Returns current conditions: temp (°F), feels-like, wind, humidity, condition description, peak rain probability for the day
• Pre-join screen now shows a speaking-language picker (17 languages) so guests explicitly set which language they speak, not guessed from browser locale
• Settings panel (gear icon) inside the live room also has an 'I'm speaking' section to change STT language mid-call, which stops and restarts Deepgram with the new language code
• spokenLanguage is now stateful in both GuestRoomClient and RoomContent

Yen wake-word normalization + follow-up voice commands + build fix

• yen-chat/route.ts line 316: wrap ?? expr in parens to fix Turbopack 'nullish coalescing requires parens when mixing with logical operators'
• Deepgram finals now have phonetic Yen variants (Ian, Jan, Jen, Yan…) replaced with canonical 'Yen' in transcript, subtitles, and broadcast captions — 'hey Ian can you…' appears as 'Hey Yen can you…'
• While accumulating a Yen query, if a final contains hold phrases (wait, hold on, not done, also, forgot to mention, let me add, etc.) the silence timer resets and buffering continues — Yen won't fire prematurely mid-sentence
• 'Yen, the email is X' / 'Yen, I forgot to mention Y' detected via YEN_FOLLOWUP_RE while yenChatOpen=true → auto-submitted as new message in the current thread via yenFollowUp state
• YenChatPanel now accepts followUp/onFollowUpConsumed props and fires submitQuery when a new follow-up arrives

increase Yen silence buffer to 3s + improve team member lookup

• YEN_SILENCE_MS: 1800 → 3000ms so Yen waits longer before firing, giving Deepgram time to emit all finals before the query is submitted
• execLookupClient now searches User.firstName, User.lastName, User.jobTitle, User.department fields so employees like Stella (CMO) are found by first name or job title
• Also queries WorkerProfile table (firstName, lastName, preferredName, jobTitle, department) with link back to User.email
• Result label now shows job title + department for team members so Claude can confirm 'Stella · Chief Marketing Officer' before sending

add 'ian' to Yen wake word regex + improve ShipStation city zip inference

• Deepgram transcribes 'Yen' as 'Ian' — added 'ian' to the phonetic regex alternation in both host (meeting-room-client) and guest (guest-room-client) wake word detectors
• Updated ShipStation tool description to instruct Claude to infer city-specific zip codes when a city+state is given (e.g. Greenville SC → 29601) instead of falling back to generic country defaults
• Reinforced shipping guideline in system prompt

ShipStation international rates + Yen team-member lookup

• Fix origin ZIP: 10036 (NYC) → 30120 (Cartersville, GA — Katura studio)
• Fix international rates: don't pass toState for non-US destinations — carriers reject foreign state codes and return empty rate lists
• Better no-rates error message includes per-carrier error detail so the host can see exactly which carriers failed and why
• Tool description: explicit per-country postal code defaults including Brazil (01310100 = São Paulo), Canada, UK, AU, DE, FR, JP, MX; tell Claude to NEVER refuse without calling the tool first
• Tool description: clarify toState is US-domestic only — OMIT for non-US
• lookup_client tool description rewritten to clearly state it covers Katura team members, employees, and staff (not just clients)
• Explicit examples: 'email Stella', 'contact Austin' → lookup_client first
• System prompt: TEAM & CONTACT LOOKUP section with direct instruction to always call lookup_client before send_email when a person is named
• System prompt: Katura studio location (Cartersville, GA, ZIP 30120) explicitly stated so shipping context is always clear
• Multi-address disambiguation example updated with correct Stella email (contatoluiseagency@gmail.com)

Yen no-double-window, invite autocomplete, PDF/email minutes

• When publicMode=true (voice-triggered Hey Yen), YenChatPanel returns null visually — API effects still run, onResponseDone still fires for tile update. Only YenMeetingTile is visible; no duplicate private panel.
• New GET /api/admin/meetings/suggest-participants?q= — returns up to 12 suggestions from team members (role!=CUSTOMER), past meeting guests (MeetingInvite), and top clients (CUSTOMER + totalSpent/totalOrders).
• Instant-launch modal now shows suggestion chips that populate on focus and update live as the user types; debounced 200ms; chips auto-filter already-added addresses; click to add without typing full email.
• MinutesActions client component: 'Download PDF' button calls window.print() (browser Save-as-PDF), 'Email Minutes' opens an inline dialog.
• New POST /api/admin/meetings/[id]/email-minutes — builds a full-fidelity HTML email (summary, action items table, decisions, open questions, risks, follow-ups, participants) and sends via Brevo from yen@katura1999.com.
• MinutesActions added to the minutes page footer (only shown when minutes exist).

Yen silence buffer (1.8s gate), AI notes toggle respects checkbox

• Hey Yen now accumulates Deepgram finals for 1800ms of silence before submitting query — prevents premature fire on mid-sentence endpointing
• initialSubtitlesOn reads joinData.aiNotesEnabled instead of hardcoded true
• AI Notes checkbox in meeting settings now correctly prevents STT auto-start
• Yen buffer cleaned up in stopStt() and unexpected ws.onclose so orphaned timers can never fire after STT has been torn down

camera visibility, Yen tile crush, subtitle lowercase, font sync, email 400

• Remove adaptiveStream:true from both admin + guest LiveKitRoom → adaptiveStream blocks camera subscription until video element is in DOM, causing guest to never see host camera on initial load
• Guest SubtitlePanel: wrap in shrink-0 fixed-height (144px) container → without height constraint, accumulated captions grew to fill flex column, squeezing video + Yen tile section to 0px (full-screen subtitles bug)
• Subtitle textTransform: 'none' → 'lowercase' when caps=false
• Guest default font: font-display → font-narrow (matches admin default)
• Email 400 fix: fromAccountId falls back to user account if yen@ not in DB

meeting platform action items — subtitle caps off, condensed font top, ShipStation live rates, Safari camera, 30s timeout

• Subtitle all-caps OFF by default (both admin + guest rooms)
• Condensed font moved to top of SUBTITLE_FONTS list (both rooms)
• get_shipping_options now calls ShipStation API (getRatesFromAllCarriers) for real FedEx/UPS/USPS quotes
• Tool definition updated: accepts toCountry, toPostalCode, toState, weightOunces
• Claude infers zip codes from partial address info (system prompt)
• 30s timeout on agentic loop prevents infinite processing
• Safari camera fix: adaptiveStream + dynacast, explicit camera re-enable after connect
• Safari video: playsinline attribute enforcement via MutationObserver
• Guest chat panel: added missing open/onOpenChange props (fixes TS error)
• Guest font list: added Condensed + Humanist (parity with admin)

multi-email disambiguation + send from yen@katura1999.com

wire email send end-to-end — correct payload shape, fromAccountId, broader lookup_client

expand Hey Yen detection + fix video squeezing on resize

• ### Hey Yen — phonetic variant coverage
• The regex previously missed 'yin' (and 'yon', 'yean', 'yeun', 'jin')
• which are common Deepgram transcriptions of 'Yen'. Expanded to:
• yen|yan|yin|yon|yenn?|yean|yeun|jen(na?|a)?|jan[aei]?|jin[ae]?|yarn?|ge[mn]h?
• Also simplified the regex structure (removed duplicate/overlapping
• alternatives like yen[nah]? and yenh? which partially overlapped with yen).
• Applied in both admin room (host voice trigger) and guest room.
• ### Guest Hey Yen flow
• Guests with allowGuestYen=true now detect 'Hey Yen' in their own
• speech and broadcast a yen_guest_trigger data packet. The host's data
• handler receives it and opens YenChatPanel in publicMode, so the
• response is broadcast back to all participants as a tile — same
• experience as the host triggering it themselves.
• ### Video squeezing on subtitle panel resize
• LiveKit renders video with object-fit: contain by default, which
• letterboxes the video when the container changes aspect ratio.
• Added global CSS override:
• .lk-participant-tile video { object-fit: cover }
• Now the video always fills its tile regardless of container shape —
• no black bars or squeezed frames when dragging the subtitle panel.

quote camelCase column names in email composite index migration

• Prisma does not auto-convert field names to snake_case — only model names
• are mapped via @@map. The actual Postgres columns are camelCase
• (toAccountId, fromAccountId, sentAt, isRead) and must be double-quoted
• in raw SQL.
• Also ships: subtitle panel now shows 'Speaker is speaking…' during
• interim speech instead of raw partial words.

fix X close button + add post-response action flow

• YenMeetingTile onDismiss now also closes the chat panel (previously dismissed the video tile but left the slide-in panel open)
• handleClose and clearThread both reset postStage so the action buttons don't ghost after a re-open
• A new query is submitted
• The panel is closed
• The thread is cleared

dramatically speed up /admin/email with caching, lighter queries, and composite indexes

• (to_account_id, folder, sent_at DESC) — inbox/folder view
• (from_account_id, folder, sent_at DESC) — sent/drafts view
• (to_account_id, is_read, folder) WHERE is_read=false AND folder='INBOX' — unread badge Migration SQL: scripts/db-migrations/prisma/add-email-composite-indexes.sql
• Inbox page load: ~3 DB queries → 1 (cached) + 1 inbox query
• Message list query: eliminates trackingEvents JOIN (potentially 50 joins/req)
• Bulk select-all archive: 50 HTTP requests → 1
• Repeat navigation: near-zero DB cost for sidebar (30s cache)

remove 8 empty stub files from root directory

• shipengine-rate-calculator.ts (empty stub, real file in scripts/shipping/)
• test-fedex-rates-direct.mjs (empty stub, real file in scripts/shipping/)
• test-fedex-rates.ts (empty stub, real file in scripts/shipping/)
• shipstation-test.ts (empty stub, real file in scripts/shipping/)
• VISUAL_GUIDE.txt (empty)
• NEXT_STEPS.txt (empty)
• .git-commit-msg.txt (empty)
• ShipStation-Tests.postman_collection.json (empty stub, real file in scripts/shipping/)
• Environment configs (.env*, .vercel*)
• Package/lock files (package.json, pnpm-*)
• Build/framework configs (next.config.ts, tsconfig.json, etc)
• Tooling configs (eslint, vitest, playwright, postcss)
• Documentation (README.md)
• Deployment config (vercel.json)

move shipengine docs and sql migrations to organized locations

• Move all 19 ShipEngine docs from root → docs/integrations/shipengine/ (CARRIER_IDS, DELIVERY_SUMMARY, FEDEX_TESTING, QUICK_ACTION, README_SHIPENGINE, REAL_RATE_TEST, SETUP-COMPLETE, INTEGRATION_STATUS, MIGRATION, QUICKSTART, REVIEW_COMPLETE, SETUP, SHIPPING_RATES, SHIPSTATION_*, WEBHOOKS_*, etc)
• Copy all Prisma SQL migrations → scripts/db-migrations/prisma/ (add-casting-reviews, add-order-timeline, fix-support-tickets, add-investors, add-analytics-perf, add-jewelry-project, enable-rls, plus 20260127/0121/0130 timestamped migrations and others)
• Move all cap-table migrations → scripts/db-migrations/cap-table/ (fix_company_entity, seed_cap_table, add_cap_compliance, repair_cap_table, etc)

reorganize docs and scripts into proper folder structure

• Move loose docs from root into appropriate subfolders
• Incident fixes (CONNECTION-POOL, CRON-AUTH, EMERGENCY, etc) → docs/fixes/
• Deployment & infrastructure (DEPLOYMENT-COMPLETE, INFRASTRUCTURE-HARDENING, etc) → docs/deployment/
• Meetings (MEETINGS-PAGINATION, MEETINGS-STRATEGY, DEEPGRAM-STT, etc) → docs/meetings/
• AI/Yen (YEN-CLAUDE-CAPABILITIES, YEN-MEMORY-ARCHITECTURE, etc) → docs/ai/
• Platform & K99 strategy (K99-*, KATURA-OPERATING-PLAN, etc) → docs/platform/
• Audit & reviews (ADMIN_AUDIT, CHECKOUT-AUDIT, SIDEBAR-CONSOLIDATION) → docs/audits/
• Business & brand (LUXURY_BRAND_STRATEGY, ANTAR_PROPOSAL, etc) → docs/marketing/
• Email, Stripe, Integrations moved to respective subfolders
• Changelog, reference docs → docs/reference/
• Database migration scripts → scripts/db-migrations/
• Shipping tests & Postman collection → scripts/shipping/
• ShipStation test scripts → scripts/

integrate ShipEngine real-time rates with insurance

• Replace ShipStation client with direct ShipEngine API calls
• Add dimensions (6x4x2in) for FedEx compatibility
• Add customs declarations for international shipments
• Insure packages for cartValue * 1.08 (incl. avg sales tax)
• Return insurance_amount as separate line item in response
• Deduplicate rates: one best rate per carrier
• Graceful fallback to static regional rates on API error
• Add getShippingRates tool to Yen (all carriers, insured)
• Update Yen system prompt with shipping capability
• Remove webhook HMAC secret (ShipEngine doesn't use it)
• FedEx transit note: One Balance accounts return no transit time via API

Replace pink sparkle icon with Katura dark blue logo in admin/yen interface