colinislit
983807d833
refactor(cortex): Epic 0 - Extract patient search hooks & components (E0.S1-S4)
...
DRY refactor: Extract reusable patient search logic from ZoekenBlock.
New files:
- lib/cortex/hooks/use-patient-search.ts (116 lines)
Debounced patient search with abort controller
- lib/cortex/hooks/use-patient-selection.ts (98 lines)
FHIR fetch + store update flow
- lib/fhir/patient-mapper.ts (109 lines)
FHIR Patient to DB Patient mapping + utilities
- components/cortex/shared/patient-list-item.tsx (114 lines)
Reusable patient list item with loading states
Refactored:
- ZoekenBlock: 349 -> 127 lines (-64%)
Documentation:
- docs/intent/patient-search/ux-analyse-patient-selectie.md
- docs/intent/patient-search/bouwplan-patient-selectie-v1.md
CLAUDE.md updated with Cortex architecture documentation.
Epic 0 complete: 4/4 stories (4 SP)
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-03 11:40:23 +01:00
colinislit
52e07aaf80
fix(cortex): update date handling in API and UI components
...
- Adjusted date handling in the agenda API to ensure optional parameters for start, end, and label are correctly processed.
- Enhanced chat input and action parser to support optional date labels for relative dates.
- Updated agenda components to handle date ranges and loading states more effectively.
- Improved error handling and loading indicators in the agenda block for better user experience.
This commit ensures consistency in date handling across the application, aligning with the new requirements for relative date inputs.
2026-01-02 09:21:37 +01:00
colinislit
011815072b
refactor(cortex): consistente datumbepaling met referenceDate parameter
...
SOC: Parser en entity-extractor accepteren nu optionele referenceDate
parameter. Caller bepaalt wat "nu" is, niet de functies intern.
Wijzigingen:
- parseRelativeDate(input, referenceDate?) - referenceDate parameter
- extractEntities(input, intent, referenceDate?) - doorgeeft aan parser
- API routes gebruiken new Date() als referenceDate
Verwijderd (YAGNI):
- lib/utils/server-date.ts - wrapper om new Date() was overbodig
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-02 08:49:20 +01:00
colinislit
6add89dc51
feat(cortex): Epic 5 - Integration & Polish complete (MVP DONE)
...
Epic 5 completes the Cortex V2 MVP with end-to-end integration:
E5.S1 - Feature Flag Guards
- ActionChainCard wrapped with CORTEX_MULTI_INTENT flag
- ClarificationCard wrapped with CORTEX_V2_ENABLED flag
- NudgeToast wrapped with CORTEX_NUDGE flag
- V1 UI remains functional when flags disabled
E5.S2 - Chain Execution Flow
- handleConfirmAction routes actions to artifacts via routeIntentToArtifact()
- Nudge evaluation triggered after successful action completion
- Sequential chain execution with auto-advance useEffect
- Chain auto-completes when all actions done
E5.S3 - Integration Tests (21 tests)
- Scenario 1: Simple input → Reflex handles (4 tests)
- Scenario 2: Multi-intent → Orchestrator handles (4 tests)
- Scenario 3: Context-dependent → Pronoun resolution (4 tests)
- Scenario 4: Wondzorg → Nudge suggestion (4 tests)
- Scenario 5: Graceful fallback (3 tests)
- Scenario 6: Chain building (2 tests)
E5.S4 - Demo Script
- 5-minute demo flow with exact phrases
- 5 scenes: Reflex speed, Multi-intent, Pronoun, Nudge, Clarification
- Backup scenarios documented
- Test phrases reference included
Files changed:
- components/cortex/chat/chat-panel.tsx (feature flags + execution)
- components/cortex/command-center/command-center.tsx (NudgeToast flag)
- lib/cortex/__tests__/cortex-v2.test.ts (NEW - 21 integration tests)
- docs/intent/demo-script-cortex-v2.md (NEW - demo documentation)
- docs/intent/bouwplan-cortex-v2.md (v1.5 - MVP complete)
MVP Status: 26/26 stories, 48/48 SP - 100% COMPLETE
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-01 13:16:20 +01:00
colinislit
4b759c9b3d
feat(cortex): Epic 4 - Nudge MVP (Layer 3) complete
...
Proactive suggestions after successful actions - proof of concept.
E4.S1 - Protocol Rules (lib/cortex/nudge.ts)
- ProtocolRule and ProtocolCondition types
- Condition operators: equals, contains, matches, exists
- 2 hardcoded rules: wondzorg-controle, medicatie-controle
E4.S2 - evaluateNudge Function
- evaluateNudge(input) returns NudgeSuggestion[]
- checkCondition() helper for rule matching
- Priority sorting (high → medium → low)
E4.S3 - NudgeToast Component
- Countdown progress bar with auto-dismiss (5 min)
- Priority-based styling (low/medium/high)
- Accept and dismiss buttons
- Framer Motion animations
E4.S4 - Integration
- NudgeToast rendered in CommandCenter (fixed position)
- Trigger added in DagnotatieBlock after successful save
- Accept opens corresponding artifact with prefilled data
Demo flow:
1. Create dagnotitie with "wond" in content
2. Save → NudgeToast appears
3. Click "Ja, inplannen" → Appointment artifact opens
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-01 12:42:49 +01:00
colinislit
42d64761ec
feat(cortex): Epic 3 - UI Components complete
...
Epic 3 delivers the visual layer for multi-intent flows and clarification:
E3.S1 - ActionChainCard (3 SP)
- Container for multi-intent chain display
- Header with AI/Local source badge and action count
- Original user input context
- Stacked ActionItems with Framer Motion animations
- Collapsible AI reasoning section
- Status-dependent styling (pending/executing/completed/partial/failed)
E3.S2 - ActionItem (2 SP)
- 6 status icons (pending, confirming, executing, success, failed, skipped)
- Dutch intent labels via shared intent-labels.ts
- Confidence badge with color coding (green ≥90%, amber ≥70%, red <70%)
- Entity summary formatting
- Confirmation buttons for confirming status
- Retry button for failed + recoverable actions
E3.S3 - ClarificationCard (2 SP)
- Amber-themed styling for question context
- Header with HelpCircle icon
- Original user input display
- Responsive options grid (2 cols desktop, 1 col mobile)
- Dismiss button and cancel link
- Framer Motion entry/exit animations
E3.S4 - ProcessingIndicator (1 SP)
- 3 variants: spinner, skeleton, pulse
- 3 sizes: sm, md, lg
- Configurable message
- InlineSpinner export for buttons
Integration in ChatPanel (v4.0):
- V2 store hooks for activeChain, pendingClarification
- Event handlers for confirm/skip/retry/dismiss
- Conditional rendering with AnimatePresence
New files:
- lib/cortex/intent-labels.ts
- components/cortex/chat/action-chain-card.tsx
- components/cortex/chat/action-item.tsx
- components/cortex/chat/clarification-card.tsx
- components/cortex/chat/processing-indicator.tsx
Modified:
- components/cortex/chat/chat-panel.tsx (v3.0 → v4.0)
- docs/intent/bouwplan-cortex-v2.md (v1.2 → v1.3)
Progress: 35/48 SP (73%) - E0, E1, E2, E3 complete
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-01 12:02:15 +01:00
colinislit
b36df63d03
feat(cortex): Epic 2 - Intent Orchestrator (Layer 2) complete
...
Implements AI-powered multi-intent classification for Cortex V2.
When Reflex Arc (Layer 1) detects complexity, it escalates to
the Orchestrator for intelligent classification using Claude 3.5 Haiku.
E2.S1 - System prompt for Orchestrator
- ORCHESTRATOR_SYSTEM_PROMPT constant with Dutch instructions
- Multi-intent detection (en, daarna, ook, eerst, vervolgens)
- Pronoun resolution rules (hij/zij → active patient)
- JSON-only output format specification
E2.S2 - Context formatting for AI
- formatContextForPrompt() with emoji structure
- Dutch labels for shifts and views
- Graceful null handling, token limiting (max 5 agenda, 3 recent)
E2.S3 - AI classification endpoint
- classifyWithOrchestrator() calling Claude 3.5 Haiku
- Builds IntentChain from AI response
- Tracks tokens used and processing time
E2.S4 - IntentChain parsing with Zod
- parseAIResponse() with Zod schema validation
- Strips markdown code blocks
- Partial extraction for malformed responses
- Graceful fallback to intent: 'unknown'
E2.S5 - POST /api/cortex/classify hybrid endpoint
- Reflex first, escalate to Orchestrator if needed
- Response includes handledBy: 'reflex' | 'orchestrator'
- Auth check, feature flag check, request validation
E2.S6 - Graceful fallback
- buildFallbackChain() with confidence cap (0.6)
- buildChainFromReflex() for simple chains
- classifyWithTimeout() wrapper (5s default)
New files:
- lib/cortex/orchestrator.ts (~780 lines)
- app/api/cortex/classify/route.ts (~180 lines)
Key deliverable: "Zeg Jan af en maak notitie" correctly
parsed into 2 actions in an IntentChain.
Progress: 27 SP / 48 SP (56%) - E0, E1, E2 complete
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-01 11:28:14 +01:00
colinislit
c1dc92035b
feat(cortex): Epic 1 - Reflex Arc (Layer 1) classifier
...
Implement fast local intent classification with escalation-aware logic.
Target: <20ms processing time for simple commands.
E1.S1 - Pattern Matching
- New reflex-classifier.ts with 7 intent types
- Top-2 match tracking for ambiguity detection
- Confidence thresholds (0.7) and ambiguity threshold (0.1)
E1.S2 - Escalation Triggers
- Multi-intent detection: "en", "daarna", "eerst", "vervolgens"
- Context-dependent pronouns: "hij", "zij", "hem", "haar", "zijn"
- Relative time expressions: "morgen", "overmorgen", "volgende week"
E1.S3 - Ambiguity Detection
- Top-2 score comparison (delta < 0.1 → escalate)
- secondBestIntent and secondBestConfidence tracking
- Low confidence escalation (< 0.7)
E1.S4 - Unit Tests
- 25 tests covering all scenarios
- Performance test: 100 classifications in <1ms
- Test runner: pnpm tsx (no Jest/Vitest setup required)
New files:
- lib/cortex/reflex-classifier.ts
- lib/cortex/__tests__/reflex-classifier.test.ts
Run tests: pnpm tsx lib/cortex/__tests__/reflex-classifier.test.ts
Progress: 14 SP / 48 SP (29%) - E0 + E1 complete
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2025-12-31 16:24:33 +01:00
colinislit
cf26022583
feat(cortex): Epic 0 - Foundation & Context voor V2 architectuur
...
Implementeert de basis voor de Cortex V2 three-layer architecture.
E0.S1 - CortexContext Types (lib/cortex/types.ts):
- EscalationReason type voor Reflex → Orchestrator
- LocalClassificationResult met ambiguity detection
- CortexContext voor AI classificatie context
- IntentChain en IntentAction voor multi-intent flows
- NudgeSuggestion voor proactieve suggesties
- CONFIDENCE_THRESHOLD (0.7) en AMBIGUITY_THRESHOLD (0.1)
- getCurrentShift() utility (DRY - herbruikbaar)
E0.S2 - Context API (app/api/cortex/context/route.ts):
- GET endpoint voor huidige context
- Haalt agenda vandaag op uit database
- Retourneert CortexContext object
E0.S3 - Feature Flags (lib/config/feature-flags.ts):
- CORTEX_V2_ENABLED, CORTEX_MULTI_INTENT
- CORTEX_NUDGE, CORTEX_LOGGING
- isFeatureEnabled() helper
- Dev mode: default true
E0.S4 - CortexStore V2 (stores/cortex-store.ts):
- Types geïmporteerd uit lib/cortex (DRY)
- ChatEntities type voor AI responses (string-based)
- V2 state: context, activeChain, chainHistory, suggestions
- V2 actions: chain management, nudge management, clarification
E0.S5 - Classification Logging (lib/cortex/logger.ts):
- PII sanitization (BSN, tel, namen, email)
- logClassification(), logEscalation(), logNudge()
- logPerformance() met threshold checks
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2025-12-31 12:46:35 +01:00
colinislit
2170b23348
refactor: rename swift → cortex in code and documentation
...
Complete rename of "swift" terminology to "cortex" across the codebase:
Code Changes:
- Rename directories: lib/swift → lib/cortex, components/swift → components/cortex
- Rename API routes: /api/swift/* → /api/cortex/*
- Rename page routes: /epd/swift → /epd/cortex
- Rename store: swift-store.ts → cortex-store.ts
Type Renames:
- SwiftIntent → CortexIntent
- SwiftStore → CortexStore
- useSwiftStore → useCortexStore
- SwiftContext → CortexContext
- useSwiftVoice → useCortexVoice
Documentation Updates (docs/intent/):
- Safety Net → Nudge (Layer 3 rename)
- SafetySuggestion → NudgeSuggestion
- evaluateSafetyNet → evaluateNudge
- SWIFT_* feature flags → CORTEX_*
- All path references updated to match new structure
Files affected: 47 files, ~700 lines changed
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2025-12-30 09:18:06 +01:00