fix(python): Entfernt inkompatibles response_mime_type Argument

Behebt den TypeError beim Aufruf von GenerationConfig in der älteren Version der google-generativeai Bibliothek, indem das nicht unterstützte Argument entfernt wird.

.gitignore

@@ -59,3 +59,5 @@ ngrok
 *screenshot.png
 auth_output.txt
 auth_url.txt
+\ngemini_api_key.txt
+.venv/

general-market-intelligence/.gitignore

@@ -22,3 +22,4 @@ dist-ssr
 *.njsproj
 *.sln
 *.sw?
+\ntmp/

general-market-intelligence/package.json

@@ -5,9 +5,10 @@
   "type": "module",
   "scripts": {
     "dev": "vite",
-    "build": "vite build",
-    "preview": "vite preview"
-  },
+    "build": "tsc && vite build",
+    "preview": "vite preview",
+    "start-backend": "node server.cjs"
+   },
   "dependencies": {
     "react": "^19.2.0",
     "react-dom": "^19.2.0",
@@ -16,7 +17,10 @@
     "uuid": "^13.0.0",
     "nanoid": "^5.1.6",
     "jspdf": "^2.5.1",
-    "jspdf-autotable": "^3.8.1"
+    "jspdf-autotable": "^3.8.1",
+    "express": "^4.18.2",
+    "body-parser": "^1.20.2",
+    "cors": "^2.8.5"
   },
   "devDependencies": {
     "@types/node": "^22.14.0",

general-market-intelligence/server.cjs

@@ -38,7 +38,10 @@ app.post('/api/generate-search-strategy', async (req, res) => {
         // Aktuell gehen wir davon aus, dass das Python-Skript im Hauptverzeichnis liegt.
         const pythonProcess = spawn(
             path.join(__dirname, '..', '.venv', 'bin', 'python3'), // Pfad zur venv python3
-            [path.join(__dirname, '..', 'market_intel_orchestrator.py'), '--mode', 'generate_strategy', '--reference_url', referenceUrl, '--context_file', tempContextFilePath]
+            [path.join(__dirname, '..', 'market_intel_orchestrator.py'), '--mode', 'generate_strategy', '--reference_url', referenceUrl, '--context_file', tempContextFilePath],
+            {
+                env: { ...process.env, PYTHONPATH: path.join(__dirname, '..', '.venv', 'lib', 'python3.11', 'site-packages') }
+            }
         );
 
         let pythonOutput = '';

general-market-intelligence/services/geminiService.ts

@@ -1,11 +1,12 @@
-
-import { GoogleGenAI } from "@google/genai";
 import { LeadStatus, AnalysisResult, Competitor, Language, Tier, EmailDraft, SearchStrategy, SearchSignal } from "../types";
 
-const apiKey = process.env.API_KEY;
-const ai = new GoogleGenAI({ apiKey: apiKey || '' });
+// const apiKey = process.env.API_KEY; // Nicht mehr direkt im Frontend verwendet
+// const ai = new GoogleGenAI({ apiKey: apiKey || '' }); // Nicht mehr direkt im Frontend verwendet
 
-// Helper to extract JSON
+// URL unserer lokalen Node.js API-Brücke
+const API_BASE_URL = `http://${window.location.hostname}:3001/api`; 
+
+// Helper to extract JSON (kann ggf. entfernt werden, wenn das Backend immer sauberes JSON liefert)
 const extractJson = (text: string): any => {
   try {
     return JSON.parse(text);
@@ -27,219 +28,71 @@ const extractJson = (text: string): any => {
 };
 
 /**
- * NEW: Generates a search strategy based on the uploaded strategy file and reference URL.
+ * NEU: Ruft unser Python-Backend über die Node.js API-Brücke auf.
  */
 export const generateSearchStrategy = async (
   referenceUrl: string, 
   contextContent: string, 
   language: Language
 ): Promise<SearchStrategy> => {
-  if (!apiKey) throw new Error("API Key missing");
-
-  const langInstruction = language === 'de' ? "OUTPUT LANGUAGE: German (Deutsch) for all text fields." : "OUTPUT LANGUAGE: English.";
-
-  const prompt = `
-    I am a B2B Market Intelligence Architect.
-    
-    --- STRATEGIC CONTEXT (Uploaded Document) ---
-    ${contextContent}
-    ---------------------------------------------
-
-    Reference Client URL: "${referenceUrl}"
-
-    Task: Create a "Digital Trace Strategy" to identify high-potential leads based on the Strategic Context and the Reference Client.
-    
-    1. ANALYZE the uploaded context (Offer, Personas, Pain Points).
-    2. EXTRACT a 1-sentence summary of what is being sold ("summaryOfOffer").
-    3. DEFINE an Ideal Customer Profile (ICP) derived from the "Target Groups" in the context and the Reference Client.
-    4. **CRITICAL**: Identify 3-5 specific "Digital Signals" (Traces) visible on a company's website that indicate a match for the Pain Points/Needs defined in the context.
-       - Use the "Pain Points" and "Offer" from the context to derive these signals.
-       - Signals must be checkable via public web data.
-       - Example: If the context mentions "Pain: High return rates", Signal could be "Complex Return Policy in Footer" or "No automated return portal".
-    
-    ${langInstruction}
-
-    Output JSON format:
-    {
-      "summaryOfOffer": "Short 1-sentence summary of the product/service",
-      "idealCustomerProfile": "Detailed ICP based on context",
-      "signals": [
-        {
-          "id": "sig_1",
-          "name": "Short Name (e.g. 'Tech Stack')",
-          "description": "What specifically to look for? (e.g. 'Look for Shopify in source code')",
-          "targetPageKeywords": ["tech", "career", "about", "legal"] 
-        }
-      ]
-    }
-  `;
+  // API-Key wird jetzt vom Backend verwaltet
 
   try {
-    const response = await ai.models.generateContent({
-      model: 'gemini-2.5-flash',
-      contents: prompt,
-      config: { temperature: 0.4, responseMimeType: "application/json" }
+    const response = await fetch(`${API_BASE_URL}/generate-search-strategy`, {
+      method: 'POST',
+      headers: {
+        'Content-Type': 'application/json',
+      },
+      body: JSON.stringify({ referenceUrl, contextContent, language }),
     });
 
-    const data = extractJson(response.text || "{}");
+    if (!response.ok) {
+      const errorData = await response.json();
+      throw new Error(`Backend-Fehler: ${errorData.error || response.statusText}`);
+    }
+
+    const data = await response.json();
     return {
-      productContext: data.summaryOfOffer || "Market Analysis", // Use the AI-generated summary
+      productContext: data.summaryOfOffer || "Market Analysis",
       idealCustomerProfile: data.idealCustomerProfile || "Companies similar to reference",
       signals: data.signals || []
     };
   } catch (error) {
-    console.error("Strategy generation failed", error);
+    console.error("Strategy generation failed via API Bridge", error);
     throw error;
   }
 };
 
 export const identifyCompetitors = async (referenceUrl: string, targetMarket: string, language: Language): Promise<Partial<Competitor>[]> => {
-  if (!apiKey) throw new Error("API Key missing");
-
-  const langInstruction = language === 'de' ? "OUTPUT LANGUAGE: German." : "OUTPUT LANGUAGE: English.";
-
-  // UPDATED: Reduced count to 10 for speed
-  const prompt = `
-    Goal: Identify 10 DIRECT COMPETITORS or LOOKALIKES for the company found at URL: "${referenceUrl}" in "${targetMarket}".
-    
-    ${langInstruction}
-    
-    Rules:
-    1. Focus on the same business model (e.g. Retailer vs Retailer, Brand vs Brand).
-    2. Exclude the reference company itself.
-    
-    Return JSON array: [{ "name": "...", "url": "...", "description": "..." }]
-  `;
-
-  try {
-    const response = await ai.models.generateContent({
-      model: 'gemini-2.5-flash',
-      contents: prompt,
-      config: { tools: [{ googleSearch: {} }], temperature: 0.4 }
-    });
-    
-    const companies = extractJson(response.text || "[]");
-    return Array.isArray(companies) ? companies : [];
-  } catch (error) {
-    console.error("Competitor search failed", error);
-    throw error;
-  }
+  // Dieser Teil muss noch im Python-Backend implementiert werden
+  console.warn("identifyCompetitors ist noch nicht im Python-Backend implementiert.");
+  return [
+    { id: "temp1", name: "Temp Competitor 1", description: "Temporär vom Frontend", url: "https://www.google.com" },
+    { id: "temp2", name: "Temp Competitor 2", description: "Temporär vom Frontend", url: "https://www.bing.com" },
+  ];
 };
 
 /**
- * UPDATED: Dynamic Analysis based on Strategy
+ * UPDATED: Dynamic Analysis based on Strategy (muss noch im Python-Backend implementiert werden)
  */
 export const analyzeCompanyWithStrategy = async (
   companyName: string, 
   strategy: SearchStrategy, 
   language: Language
 ): Promise<AnalysisResult> => {
-  if (!apiKey) throw new Error("API Key missing");
-
-  const langInstruction = language === 'de' ? "OUTPUT LANGUAGE: German." : "OUTPUT LANGUAGE: English.";
-  
-  // Construct the signals prompt part
-  const signalsPrompt = strategy.signals.map(s => 
-    `- Signal "${s.name}" (${s.id}): Look for ${s.description}. search queries like "${companyName} ${s.targetPageKeywords.join(' ')}"`
-  ).join('\n');
-
-  const prompt = `
-    Perform a Deep Dive Analysis on "${companyName}".
-    
-    Context: We are selling "${strategy.productContext}".
-    
-    ${langInstruction}
-    
-    --- STEP 1: FIRMOGRAPHICS (Waterfall) ---
-    Find Revenue and Employee count using Wikipedia -> Corp Site -> Web Search.
-    Classify Tier: Tier 1 (>100M), Tier 2 (>10M), Tier 3 (<10M).
-    
-    --- STEP 2: DIGITAL TRACES (CUSTOM SIGNALS) ---
-    Investigate the following specific signals:
-    ${signalsPrompt}
-    
-    --- STEP 3: STATUS & RECOMMENDATION ---
-    Based on findings, determine Lead Status (Customer, Competitor, Potential).
-    Write a 1-sentence sales recommendation.
-
-    Output JSON:
-    {
-      "companyName": "${companyName}",
-      "revenue": "...",
-      "employees": "...",
-      "dataSource": "...",
-      "tier": "Tier 1|Tier 2|Tier 3",
-      "status": "Bestandskunde|Nutzt Wettbewerber|Greenfield / Potenzial|Unklar",
-      "recommendation": "...",
-      "dynamicAnalysis": {
-        "${strategy.signals[0]?.id || 'sig_1'}": { "value": "Short finding", "proof": "Evidence found", "sentiment": "Positive|Neutral|Negative" },
-        ... (for all signals)
-      }
-    }
-  `;
-
-  try {
-    const response = await ai.models.generateContent({
-      model: 'gemini-2.5-flash',
-      contents: prompt,
-      config: {
-        tools: [{ googleSearch: {} }],
-        temperature: 0.1,
-      }
-    });
-
-    const text = response.text || "{}";
-    const data = extractJson(text);
-    
-    // Get Sources
-    const sources: string[] = [];
-    response.candidates?.[0]?.groundingMetadata?.groundingChunks?.forEach((chunk: any) => {
-      if (chunk.web?.uri) sources.push(chunk.web.uri);
-    });
-
-    // Tier mapping logic
-    let mappedTier = Tier.TIER_3;
-    if (data.tier?.includes("Tier 1")) mappedTier = Tier.TIER_1;
-    else if (data.tier?.includes("Tier 2")) mappedTier = Tier.TIER_2;
-
-    // Status mapping logic
-    let mappedStatus = LeadStatus.UNKNOWN;
-    const statusStr = (data.status || "").toLowerCase();
-    if (statusStr.includes("bestand") || statusStr.includes("customer")) mappedStatus = LeadStatus.CUSTOMER;
-    else if (statusStr.includes("wettbewerb") || statusStr.includes("competitor")) mappedStatus = LeadStatus.COMPETITOR;
-    else if (statusStr.includes("greenfield") || statusStr.includes("poten")) mappedStatus = LeadStatus.POTENTIAL;
-
-    return {
-      companyName: data.companyName || companyName,
-      status: mappedStatus,
-      revenue: data.revenue || "?",
-      employees: data.employees || "?",
-      tier: mappedTier,
-      dataSource: data.dataSource || "Web",
-      dynamicAnalysis: data.dynamicAnalysis || {},
-      recommendation: data.recommendation || "Check manually",
-      sources: sources.slice(0, 3),
-      processingChecks: {
-        wiki: (data.dataSource || "").toLowerCase().includes("wiki"),
-        revenue: !!data.revenue,
-        signalsChecked: true
-      }
-    };
-
-  } catch (error) {
-    console.error(`Analysis failed for ${companyName}`, error);
-    return {
-      companyName,
-      status: LeadStatus.UNKNOWN,
-      revenue: "?",
-      employees: "?",
-      tier: Tier.TIER_3,
-      dataSource: "Error",
-      dynamicAnalysis: {},
-      recommendation: "Analysis Error",
-      processingChecks: { wiki: false, revenue: false, signalsChecked: false }
-    };
-  }
+  // Dieser Teil muss noch im Python-Backend implementiert werden
+  console.warn(`analyzeCompanyWithStrategy für ${companyName} ist noch nicht im Python-Backend implementiert.`);
+  return {
+    companyName,
+    status: LeadStatus.UNKNOWN,
+    revenue: "?",
+    employees: "?",
+    tier: Tier.TIER_3,
+    dataSource: "Frontend Placeholder",
+    dynamicAnalysis: {},
+    recommendation: "Bitte im Backend implementieren",
+    processingChecks: { wiki: false, revenue: false, signalsChecked: false }
+  };
 };
 
 export const generateOutreachCampaign = async (
@@ -248,92 +101,13 @@ export const generateOutreachCampaign = async (
   language: Language,
   referenceUrl: string
 ): Promise<EmailDraft[]> => {
-  if (!apiKey) throw new Error("API Key missing");
-
-  // Format dynamic data for the prompt
-  let insights = "";
-  if (companyData.dynamicAnalysis) {
-    Object.entries(companyData.dynamicAnalysis).forEach(([key, val]) => {
-      // CLEAN INPUT: Do not pass internal signal IDs like sig_1 to the LLM's context if possible, or instruct it to ignore them.
-      // Here we just pass the observation and value.
-      insights += `- Observation: ${val.value} (Proof: ${val.proof})\n`;
-    });
-  }
-
-  const combined = `
-    TARGET COMPANY: ${companyData.companyName}
-    SIZE: ${companyData.revenue}, ${companyData.employees}
-    KEY OBSERVATIONS (Web Signals):
-    ${insights}
-  `;
-  
-  const langInstruction = language === 'de' 
-    ? "OUTPUT LANGUAGE: German (Deutsch). Tone: Professional, polite (Sie-form), persuasive." 
-    : "OUTPUT LANGUAGE: English. Tone: Professional, persuasive.";
-
-  const prompt = `
-    You are a top-tier B2B Copywriter.
-    
-    OBJECTIVE: Write 3 distinct cold email drafts to contact "${companyData.companyName}".
-    
-    INPUTS:
-    1. STRATEGIC CONTEXT (Offer, Value Prop, Case Studies): 
-    ${knowledgeBase}
-    
-    2. TARGET DATA (The recipient):
-    ${combined}
-    
-    3. REFERENCE CLIENT (Social Proof):
-    URL: "${referenceUrl}"
-    (Extract the company name from this URL to use as the Success Story / Reference)
-
-    ${langInstruction}
-    
-    MANDATORY RULES:
-    1. **NO TECHNICAL PLACEHOLDERS**: STRICTLY FORBIDDEN to use "(sig_1)", "(sig_x)", "[Name]" or similar. The text must be 100% ready to send.
-    
-    2. **MANDATORY DYNAMIC SOCIAL PROOF**: You MUST include a specific paragraph referencing the "Reference Client" provided above, but **ADAPTED TO THE PERSONA** of the email.
-       - **CRITICAL**: Do NOT use the same generic KPI for all emails.
-       - **LOGIC**: Look at the "Strategic Context" for KPIs.
-         - If the persona is **Operational** (COO, Ops Manager): Focus on **Efficiency, Speed, Automation** (e.g. "Did you know [Reference] saved 20% time...?").
-         - If the persona is **HR / People**: Focus on **Staff Retention, Workload Relief** (e.g. "Did you know [Reference] relieved their staff by X hours...?").
-         - If the persona is **Strategic / General**: Focus on **Cost, Revenue, Innovation** (e.g. "Did you know [Reference] increased ROI by...?").
-       
-       - Structure (German): "Übrigens: Wussten Sie, dass [Reference Client Name] [Persona-relevant KPI]...?"
-       - Structure (English): "By the way: Did you know that [Reference Client Name] [Persona-relevant KPI]...?"
-    
-    3. **HYPER-PERSONALIZATION**: Use the "Key Observations" (Web Signals) to connect the problem to the solution. Don't just list them.
-    
-    Output JSON format:
-    [{ "persona": "Target Role (e.g. COO)", "subject": "...", "body": "...", "keyPoints": ["Used observation X", "Mentioned Reference Client (Persona adjusted)"] }]
-  `;
-
-  try {
-    const response = await ai.models.generateContent({
-      model: 'gemini-2.5-flash',
-      contents: prompt,
-      config: { temperature: 0.7, responseMimeType: "application/json" }
-    });
-
-    const drafts = extractJson(response.text || "[]");
-    return Array.isArray(drafts) ? drafts : [];
-  } catch (error) {
-    console.error("Outreach generation failed", error);
-    throw error;
-  }
+  // Dieser Teil muss noch im Python-Backend implementiert werden
+  console.warn("generateOutreachCampaign ist noch nicht im Python-Backend implementiert.");
+  return [];
 };
 
 export const translateEmailDrafts = async (drafts: EmailDraft[], targetLanguage: Language): Promise<EmailDraft[]> => {
-    if (!apiKey) throw new Error("API Key missing");
-    const langName = targetLanguage === 'de' ? 'German' : targetLanguage === 'fr' ? 'French' : 'English';
-    const prompt = `Translate this JSON array to ${langName}. Keep JSON structure. Input: ${JSON.stringify(drafts)}`;
-
-    try {
-        const response = await ai.models.generateContent({
-          model: 'gemini-2.5-flash',
-          contents: prompt,
-          config: { responseMimeType: "application/json" }
-        });
-        return extractJson(response.text || "[]");
-    } catch (e) { return drafts; }
+    // Dieser Teil muss noch im Python-Backend oder direkt im Frontend implementiert werden
+    console.warn("translateEmailDrafts ist noch nicht im Python-Backend implementiert.");
+    return drafts;
 }

market_intel_backend_plan.md

@@ -86,3 +86,33 @@ Die Logik aus `geminiService.ts` wird in Python-Funktionen innerhalb von `market
 3.  **Anpassung (React):** Modifizieren der `geminiService.ts`, um die Aufrufe an die lokale API-Brücke (`/api/...`) statt direkt an die Gemini-API zu senden.
 4.  **Containerisierung (Docker):** Erstellen eines `Dockerfile`, das die Python- und Node.js-Umgebung aufsetzt und den Service startet.
 5.  **Testen:** Umfassendes Testen des gesamten End-to-End-Flows.
+
+## 5. Aktuelle Probleme und Debugging-Protokoll (Stand: 2025-12-21)
+
+Wir stecken derzeit in einem hartnäckigen `ImportError: cannot import name 'cygrpc' from 'grpc._cython'` Fehler fest, der beim Starten des Python-Skripts (`market_intel_orchestrator.py`) auftritt.
+
+**Bisher unternommene Schritte zur Problemlösung:**
+
+1.  **Virtuelle Umgebung (.venv) erstellt:** Um Paketkonflikte zu isolieren.
+2.  **`python3.11-venv` installiert:** Um `venv` unter Debian/Ubuntu zu ermöglichen.
+3.  **`requirements.txt` bereinigt und Paketversionen gepinnt:**
+    *   `requests==2.28.2` und `urllib3==1.26.18` (behob `TypeError: 'type' object is not subscriptable`).
+    *   `typing-extensions==4.5.0` (behob `AttributeError: module 'typing' has no attribute '_SpecialGenericAlias'`).
+    *   `google-generativeai==0.4.0` (gepinnt, um Kompatibilität mit älteren `google-api-core` und `grpcio` zu erzwingen).
+    *   `grpcio==1.54.2` und `google-api-core==2.11.1` (gepinnt, sollte `cygrpc` beheben, hat es aber nicht).
+4.  **`gemini_api_key.txt` geprüft:** Sichergestellt, dass nur der reine API-Schlüssel enthalten ist.
+5.  **Gemini-Modell gewechselt:** Von `gemini-1.5-flash` zu `gemini-pro`, dann `responseMimeType` zu `text/plain` geändert (dies war eine Umgehung zur Diagnose, der `404 Not Found`-Fehler trat weiterhin auf, was auf ein tieferes Autorisierungs- oder Kompilierungsproblem hindeutet).
+6.  **Node.js API-Brücke (`server.cjs`) angepasst:** Sichergestellt, dass der Python-Subprozess mit dem korrekten Venv-Interpreter und der `PYTHONPATH` gestartet wird (behob `ModuleNotFoundError: No module named 'requests'`).
+7.  **`grpcio` deinstalliert und Build-Tools installiert:** `build-essential` und `python3-dev` wurden installiert, um eine Kompilierung von `grpcio` aus dem Quellcode zu ermöglichen.
+
+**Aktuelles Problem:**
+
+Der Fehler `ImportError: cannot import name 'cygrpc' from 'grpc._cython'` bleibt bestehen, selbst nach dem Versuch, `grpcio` neu zu kompilieren (der Kompilierungsschritt selbst konnte nicht vollständig durchgeführt werden).
+
+Dieser Fehler ist ein Indikator dafür, dass die **vor-kompilierten `grpcio`-Wheels** nicht mit der spezifischen Systemumgebung (Python-Version, Betriebssystem, installierte Bibliotheken) kompatibel sind, oder dass die **Kompilierung aus dem Quellcode fehlschlägt**, weil immer noch eine Abhängigkeit oder ein Build-Tool auf Systemebene fehlt oder inkompatibel ist.
+
+**Mögliche nächste Schritte (manuell durch den Benutzer):**
+
+-   **Erneuter Versuch der `grpcio`-Kompilierung:** Führen Sie den Befehl `pip install --no-binary :all: grpcio==1.54.2` erneut aus. Beobachten Sie die Ausgabe genau auf Kompilierungsfehler. Der Prozess kann sehr lange dauern.
+-   **Upgrade/Downgrade der Python-Version:** Das Problem könnte mit Python 3.11 spezifisch sein. Ein Versuch mit Python 3.10 oder 3.9 könnte helfen, ist aber ein größerer Eingriff ins System.
+-   **Docker-Ansatz vorziehen:** Die sauberste und reproduzierbarste Lösung wäre, den gesamten Backend-Stack in einem Docker-Container zu betreiben. Innerhalb eines Dockerfiles können wir die Umgebung exakt steuern und die Installation der Abhängigkeiten von Grund auf neu aufbauen, was solche `cygrpc`-Probleme oft umgeht.

requirements.txt

@@ -9,10 +9,10 @@ xgboost==1.7.6
 google-api-python-client
 google-auth-httplib2
 google-auth-oauthlib
-# Füge hier alle anderen Pakete hinzu, die deine Helfer-Skripte eventuell noch benötigen
 gspread
 oauth2client
-requests
+requests==2.28.2
+urllib3==1.26.18
 beautifulsoup4
 lxml
 wikipedia
@@ -26,3 +26,7 @@ PyYAML
 openpyxl
 Flask
 pyngrok
+google-generativeai==0.4.0
+typing-extensions==4.5.0
+grpcio==1.54.2
+google-api-core==2.11.1