Files
breakpilot-compliance/admin-compliance/app/api/sdk/drafting-engine/chat/route.ts
Benjamin Admin 3707ffe799
All checks were successful
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-ai-compliance (push) Successful in 37s
CI / test-python-backend-compliance (push) Successful in 37s
CI / test-python-document-crawler (push) Successful in 23s
CI / test-python-dsms-gateway (push) Successful in 21s
feat: DSK/BfDI RAG-Ingest, TOM-Control-Library 180, Risk-Engine-Spec, RAG-Query-Optimierung
- Crawler erweitert: +26 neue Dokumente (DSK KP 1-20, SDM V3.1, BfDI Loeschkonzept, BayLDA TOM-Checkliste)
- RAG-Queries optimiert: 18 Queries mit EDPB/DSK/WP-Referenzen fuer besseres Retrieval
- Chat-Route: queryRAG nutzt jetzt Collection + Query-Boost aus DOCUMENT_RAG_CONFIG
- TOM Control Library: 180 Controls in 12 Domaenen (ISO Annex-A Style, tom_controls_v1.json)
- Risk Engine Spec: Impact/Likelihood 0-10, Score 0-100, 4 Tiers, Loeschfristen-Engine
- Soul-Files: DSK-Kurzpapiere, SDM V3.1, BfDI als primaere deutsche Quellen
- Manifest CSV: eu_de_privacy_manifest.csv mit Lizenz-Ampel (gruen/gelb/rot)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-05 12:03:57 +01:00

157 lines
5.5 KiB
TypeScript

/**
* Drafting Engine Chat API
*
* Verbindet das DraftingEngineWidget mit dem LLM Backend.
* Unterstuetzt alle 4 Modi: explain, ask, draft, validate.
* Nutzt State-Projection fuer token-effiziente Kontextgabe.
*/
import { NextRequest, NextResponse } from 'next/server'
import { queryRAG } from '@/lib/sdk/drafting-engine/rag-query'
import { DOCUMENT_RAG_CONFIG } from '@/lib/sdk/drafting-engine/rag-config'
import { readSoulFile } from '@/lib/sdk/agents/soul-reader'
import type { ScopeDocumentType } from '@/lib/sdk/compliance-scope-types'
const OLLAMA_URL = process.env.OLLAMA_URL || 'http://host.docker.internal:11434'
const LLM_MODEL = process.env.COMPLIANCE_LLM_MODEL || 'qwen2.5vl:32b'
// Fallback SOUL prompt (used when .soul.md file is unavailable)
const FALLBACK_DRAFTING_PROMPT = `# Drafting Agent - Compliance-Dokumententwurf
## Identitaet
Du bist der BreakPilot Drafting Agent. Du hilfst Nutzern des AI Compliance SDK,
DSGVO-konforme Compliance-Dokumente zu entwerfen und Konsistenz sicherzustellen.
## Strikte Constraints
- Gib praxisnahe Hinweise, KEINE konkrete Rechtsberatung
- Kommuniziere auf Deutsch, sachlich und verstaendlich
- Fuelle fehlende Informationen mit [PLATZHALTER: ...] Markierung`
export async function POST(request: NextRequest) {
try {
const body = await request.json()
const {
message,
history = [],
sdkStateProjection,
mode = 'explain',
documentType,
} = body
if (!message || typeof message !== 'string') {
return NextResponse.json({ error: 'Message is required' }, { status: 400 })
}
// 1. Query RAG for legal context (use type-specific collection + query boost if available)
const ragConfig = documentType ? DOCUMENT_RAG_CONFIG[documentType as ScopeDocumentType] : undefined
const ragQuery = ragConfig ? `${ragConfig.query} ${message}` : message
const ragContext = await queryRAG(ragQuery, 3, ragConfig?.collection)
// 2. Build system prompt with mode-specific instructions + state projection
const soulPrompt = await readSoulFile('drafting-agent')
let systemContent = soulPrompt || FALLBACK_DRAFTING_PROMPT
// Mode-specific instructions
const modeInstructions: Record<string, string> = {
explain: '\n\n## Aktueller Modus: EXPLAIN\nBeantworte Fragen verstaendlich mit Quellenangaben.',
ask: '\n\n## Aktueller Modus: ASK\nAnalysiere Luecken und stelle gezielte Fragen. Eine Frage pro Antwort.',
draft: `\n\n## Aktueller Modus: DRAFT\nEntwirf strukturierte Dokument-Sections. Dokumenttyp: ${documentType || 'nicht spezifiziert'}.\nAntworte mit JSON wenn ein Draft angefragt wird.`,
validate: '\n\n## Aktueller Modus: VALIDATE\nPruefe Cross-Dokument-Konsistenz. Gib Errors, Warnings und Suggestions zurueck.',
}
systemContent += modeInstructions[mode] || modeInstructions.explain
// Add state projection context
if (sdkStateProjection) {
systemContent += `\n\n## SDK-State Projektion (${mode}-Kontext)\n${JSON.stringify(sdkStateProjection, null, 0).slice(0, 3000)}`
}
// Add RAG context
if (ragContext) {
systemContent += `\n\n## Relevanter Rechtskontext\n${ragContext}`
}
// 3. Build messages array
const messages = [
{ role: 'system', content: systemContent },
...history.slice(-10).map((h: { role: string; content: string }) => ({
role: h.role === 'user' ? 'user' : 'assistant',
content: h.content,
})),
{ role: 'user', content: message },
]
// 4. Call LLM with streaming
const ollamaResponse = await fetch(`${OLLAMA_URL}/api/chat`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
model: LLM_MODEL,
messages,
stream: true,
options: {
temperature: mode === 'draft' ? 0.2 : 0.3,
num_predict: mode === 'draft' ? 16384 : 8192,
},
}),
signal: AbortSignal.timeout(120000),
})
if (!ollamaResponse.ok) {
const errorText = await ollamaResponse.text()
console.error('LLM error:', ollamaResponse.status, errorText)
return NextResponse.json(
{ error: `LLM nicht erreichbar (Status ${ollamaResponse.status})` },
{ status: 502 }
)
}
// 5. Stream response back
const encoder = new TextEncoder()
const stream = new ReadableStream({
async start(controller) {
const reader = ollamaResponse.body!.getReader()
const decoder = new TextDecoder()
try {
while (true) {
const { done, value } = await reader.read()
if (done) break
const chunk = decoder.decode(value, { stream: true })
const lines = chunk.split('\n').filter((l) => l.trim())
for (const line of lines) {
try {
const json = JSON.parse(line)
if (json.message?.content) {
controller.enqueue(encoder.encode(json.message.content))
}
} catch {
// Partial JSON, skip
}
}
}
} catch (error) {
console.error('Stream error:', error)
} finally {
controller.close()
}
},
})
return new NextResponse(stream, {
headers: {
'Content-Type': 'text/plain; charset=utf-8',
'Cache-Control': 'no-cache',
'Connection': 'keep-alive',
},
})
} catch (error) {
console.error('Drafting engine chat error:', error)
return NextResponse.json(
{ error: 'Verbindung zum LLM fehlgeschlagen.' },
{ status: 503 }
)
}
}