merge: resolve multi-model conflicts with trends and export endpoints

Keeps model selection, analytics trends, and CSV export endpoints.

SPARC/api.py

@@ -41,6 +41,7 @@ class CompanyAnalysisResponse(BaseModel):
     patent_count: int
     success: bool
     error: str | None = None
+    model: str | None = None
     timestamp: datetime
 
 
@@ -54,6 +55,15 @@ class BatchAnalysisResponse(BaseModel):
     timestamp: datetime
 
 
+class CompanyAnalysisRequest(BaseModel):
+    """Request model for single company analysis with optional model selection."""
+
+    model: str | None = Field(
+        default=None,
+        description="LLM model to use (e.g. 'anthropic/claude-3.5-sonnet', 'openai/gpt-4o'). Defaults to server config.",
+    )
+
+
 class BatchAnalysisRequest(BaseModel):
     """Request model for batch company analysis."""
 
@@ -63,6 +73,10 @@ class BatchAnalysisRequest(BaseModel):
     max_workers: int = Field(
         default=3, ge=1, le=5, description="Max concurrent analyses"
     )
+    model: str | None = Field(
+        default=None,
+        description="LLM model to use for all analyses in this batch. Defaults to server config.",
+    )
 
 
 class JobStatus(BaseModel):
@@ -140,6 +154,7 @@ def _convert_result(result: CompanyAnalysisResult) -> CompanyAnalysisResponse:
         patent_count=result.patent_count,
         success=result.success,
         error=result.error,
+        model=result.model,
         timestamp=result.timestamp,
     )
 
@@ -453,6 +468,104 @@ async def get_analytics(
     )
 
 
+# ============== Model Selection Endpoints ==============
+
+# Supported models via OpenRouter
+SUPPORTED_MODELS = [
+    {"id": "anthropic/claude-3.5-sonnet", "name": "Claude 3.5 Sonnet", "provider": "Anthropic"},
+    {"id": "openai/gpt-4o", "name": "GPT-4o", "provider": "OpenAI"},
+    {"id": "openai/gpt-4o-mini", "name": "GPT-4o Mini", "provider": "OpenAI"},
+    {"id": "google/gemini-pro-1.5", "name": "Gemini Pro 1.5", "provider": "Google"},
+    {"id": "meta-llama/llama-3.1-70b-instruct", "name": "Llama 3.1 70B", "provider": "Meta"},
+]
+
+
+@app.get("/models", tags=["System"])
+async def list_models():
+    """List supported LLM models for analysis.
+
+    Returns the available models that can be passed as the `model` field
+    in analysis requests. The default model is determined by the `MODEL`
+    environment variable on the server.
+    """
+    return {
+        "models": SUPPORTED_MODELS,
+        "default": config.model,
+    }
+
+
+@app.get("/analytics/trends", tags=["Analytics"])
+async def get_analytics_trends(
+    days: int = Query(default=90, ge=7, le=365),
+    _: UserResponse = Depends(get_current_user),
+):
+    """Get trend data for patent analysis over time.
+
+    Returns two datasets:
+    - ``by_month``: analysis count per company per month
+    - ``by_type_over_time``: analysis type distribution per month
+
+    Args:
+        days: Number of days to look back (default 90)
+
+    Returns:
+        Trend data suitable for time-series and distribution charts
+    """
+    db = get_db_client()
+
+    with db.get_conn() as conn:
+        with conn.cursor() as cur:
+            # Analyses per company per month
+            cur.execute(
+                """
+                SELECT
+                    TO_CHAR(timestamp, 'YYYY-MM') AS month,
+                    company_name,
+                    COUNT(*) AS count
+                FROM llm_messages
+                WHERE timestamp >= NOW() - INTERVAL '%s days'
+                    AND is_cached = FALSE
+                    AND company_name IS NOT NULL
+                GROUP BY month, company_name
+                ORDER BY month
+                """,
+                (days,),
+            )
+            by_month_rows = cur.fetchall()
+
+            # Analysis type distribution per month
+            cur.execute(
+                """
+                SELECT
+                    TO_CHAR(timestamp, 'YYYY-MM') AS month,
+                    analysis_type,
+                    COUNT(*) AS count
+                FROM llm_messages
+                WHERE timestamp >= NOW() - INTERVAL '%s days'
+                    AND is_cached = FALSE
+                GROUP BY month, analysis_type
+                ORDER BY month
+                """,
+                (days,),
+            )
+            by_type_rows = cur.fetchall()
+
+    by_month = [
+        {"month": row[0], "company_name": row[1], "count": row[2]}
+        for row in by_month_rows
+    ]
+    by_type_over_time = [
+        {"month": row[0], "analysis_type": row[1], "count": row[2]}
+        for row in by_type_rows
+    ]
+
+    return {
+        "by_month": by_month,
+        "by_type_over_time": by_type_over_time,
+        "period_days": days,
+    }
+
+
 # ============== Export Endpoints ==============
 
 

SPARC/llm.py

@@ -40,12 +40,13 @@ class LLMAnalyzer:
         else:
             self.client = None
 
-    def analyze_patent_content(self, patent_content: str, company_name: str) -> str:
+    def analyze_patent_content(self, patent_content: str, company_name: str, model: str | None = None) -> str:
         """Analyze patent content to estimate company innovation and performance.
 
         Args:
           patent_content: Minimized patent text (abstract, claims, summary)
           company_name: Name of the company for context
+          model: Optional model override (e.g. "openai/gpt-4o"). Defaults to config.
 
         Returns:
           Analysis text describing innovation quality and potential impact
@@ -63,6 +64,8 @@ Patent Content:
 
 Provide a concise analysis (2-3 paragraphs) focusing on what this patent reveals about the company's technical direction and competitive advantage."""
 
+        effective_model = model or self.model
+
         if self.test_mode:
             logger.debug("TEST MODE - Prompt that would be sent to LLM:\n%s", prompt)
             return "[TEST MODE - No API call made]"
@@ -81,7 +84,7 @@ Provide a concise analysis (2-3 paragraphs) focusing on what this patent reveals
                     response=cached["response"],
                     company_name=company_name,
                     analysis_type="single_patent",
-                    model=self.model,
+                    model=effective_model,
                     metadata={
                         "patent_content_length": len(patent_content),
                         "cache_hit": True,
@@ -94,7 +97,7 @@ Provide a concise analysis (2-3 paragraphs) focusing on what this patent reveals
         # Call API if no cache hit and client is available
         if self.client:
             response = self.client.chat.completions.create(
-                model=self.model,
+                model=effective_model,
                 max_tokens=1024,
                 messages=[{"role": "user", "content": prompt}],
             )
@@ -106,7 +109,7 @@ Provide a concise analysis (2-3 paragraphs) focusing on what this patent reveals
                 response=response_text,
                 company_name=company_name,
                 analysis_type="single_patent",
-                model=self.model,
+                model=effective_model,
                 metadata={"patent_content_length": len(patent_content)},
                 token_usage={
                     "prompt_tokens": response.usage.prompt_tokens,
@@ -124,13 +127,13 @@ Provide a concise analysis (2-3 paragraphs) focusing on what this patent reveals
             response=placeholder,
             company_name=company_name,
             analysis_type="single_patent",
-            model=self.model,
+            model=effective_model,
             metadata={"patent_content_length": len(patent_content), "pending": True}
         )
         return placeholder
-       
+
     def analyze_patent_portfolio(
-        self, patents_data: list[Dict[str, str]], company_name: str
+        self, patents_data: list[Dict[str, str]], company_name: str, model: str | None = None
     ) -> str:
         """Analyze multiple patents to estimate overall company performance.
 
@@ -165,13 +168,16 @@ Patent Portfolio:
 
 Provide a comprehensive analysis (4-5 paragraphs) with a final verdict on the company's innovation strength and performance outlook."""
 
+        effective_model = model or self.model
+
         if self.test_mode:
             logger.debug("TEST MODE - Portfolio prompt:\n%s", prompt)
             return "[TEST MODE]"
 
         metadata = {
             "patent_count": len(patents_data),
-            "patent_ids": [p['patent_id'] for p in patents_data]
+            "patent_ids": [p['patent_id'] for p in patents_data],
+            "model": effective_model,
         }
 
         # Check cache first
@@ -188,7 +194,7 @@ Provide a comprehensive analysis (4-5 paragraphs) with a final verdict on the co
                     response=cached["response"],
                     company_name=company_name,
                     analysis_type="portfolio",
-                    model=self.model,
+                    model=effective_model,
                     metadata={
                         **metadata,
                         "cache_hit": True,
@@ -202,7 +208,7 @@ Provide a comprehensive analysis (4-5 paragraphs) with a final verdict on the co
         if self.client:
             try:
                 response = self.client.chat.completions.create(
-                    model=self.model,
+                    model=effective_model,
                     max_tokens=2048,
                     messages=[{"role": "user", "content": prompt}],
                 )
@@ -215,7 +221,7 @@ Provide a comprehensive analysis (4-5 paragraphs) with a final verdict on the co
                     response=response_text,
                     company_name=company_name,
                     analysis_type="portfolio",
-                    model=self.model,
+                    model=effective_model,
                     metadata=metadata,
                     token_usage={
                         "prompt_tokens": response.usage.prompt_tokens,
@@ -235,7 +241,7 @@ Provide a comprehensive analysis (4-5 paragraphs) with a final verdict on the co
             response=placeholder,
             company_name=company_name,
             analysis_type="portfolio",
-            model=self.model,
+            model=effective_model,
             metadata={**metadata, "pending": True}
         )
         return placeholder

SPARC/types.py

@@ -24,6 +24,7 @@ class CompanyAnalysisResult:
     patent_count: int
     success: bool
     error: str | None = None
+    model: str | None = None
     timestamp: datetime = field(default_factory=datetime.now)
 
 

frontend/package.json

@@ -7,6 +7,8 @@
     "dev": "vite",
     "build": "tsc -b && vite build",
     "lint": "eslint .",
+    "generate": "openapi-typescript http://localhost:8000/api/openapi.json -o src/api/schema.d.ts",
+    "generate:local": "openapi-typescript src/api/openapi.json -o src/api/schema.d.ts",
     "typecheck": "tsc --noEmit",
     "preview": "vite preview"
   },
@@ -31,6 +33,7 @@
     "globals": "^15.8.0",
     "postcss": "^8.4.39",
     "tailwindcss": "^3.4.4",
+    "openapi-typescript": "^7.0.0",
     "typescript": "~5.5.3",
     "typescript-eslint": "^8.0.0",
     "vite": "^5.3.3"

frontend/src/api/client.ts

@@ -144,11 +144,22 @@ export const exportApi = {
 };
 
 // Analytics API
+export interface TrendData {
+  by_month: Array<{ month: string; company_name: string; count: number }>;
+  by_type_over_time: Array<{ month: string; analysis_type: string; count: number }>;
+  period_days: number;
+}
+
 export const analyticsApi = {
   getAnalytics: async (days = 30): Promise<Analytics> => {
     const response = await api.get<Analytics>(`/analytics?days=${days}`);
     return response.data;
   },
+
+  getTrends: async (days = 90): Promise<TrendData> => {
+    const response = await api.get<TrendData>(`/analytics/trends?days=${days}`);
+    return response.data;
+  },
 };
 
 // Admin API

frontend/src/pages/Analytics.tsx

@@ -2,7 +2,7 @@ import { useState } from 'react';
 import { useQuery } from '@tanstack/react-query';
 import { analyticsApi } from '../api/client';
 import { AlertCircle, Database } from 'lucide-react';
-import { PieChart, Pie, Cell, BarChart, Bar, XAxis, YAxis, Tooltip, ResponsiveContainer, Legend } from 'recharts';
+import { PieChart, Pie, Cell, BarChart, Bar, LineChart, Line, XAxis, YAxis, Tooltip, ResponsiveContainer, Legend } from 'recharts';
 
 const COLORS = ['#6366f1', '#0ea5e9', '#10b981', '#f59e0b', '#ef4444', '#8b5cf6', '#ec4899', '#14b8a6'];
 
@@ -14,6 +14,11 @@ export function AnalyticsPage() {
     queryFn: () => analyticsApi.getAnalytics(days),
   });
 
+  const trendsQuery = useQuery({
+    queryKey: ['analytics-trends', days],
+    queryFn: () => analyticsApi.getTrends(days),
+  });
+
   if (isLoading) {
     return (
       <div className="space-y-6">
@@ -189,6 +194,114 @@ export function AnalyticsPage() {
           </div>
         )}
       </div>
+
+      {/* Trend Charts */}
+      {trendsQuery.data && (
+        <div className="space-y-6">
+          <h3 className="text-lg font-semibold text-text-primary border-b-2 border-primary/30 pb-2">
+            Trends Over Time
+          </h3>
+
+          <div className="grid grid-cols-1 lg:grid-cols-2 gap-6">
+            {/* Patent count over time per company (line chart) */}
+            {trendsQuery.data.by_month.length > 0 && (() => {
+              // Pivot data: each month as a row, companies as columns
+              const companies = [...new Set(trendsQuery.data!.by_month.map(d => d.company_name))];
+              const months = [...new Set(trendsQuery.data!.by_month.map(d => d.month))].sort();
+              const pivoted = months.map(month => {
+                const row: Record<string, string | number> = { month };
+                for (const c of companies) {
+                  const entry = trendsQuery.data!.by_month.find(d => d.month === month && d.company_name === c);
+                  row[c] = entry?.count || 0;
+                }
+                return row;
+              });
+
+              return (
+                <div className="bg-bg-card/60 border border-primary/15 rounded-2xl p-6">
+                  <h4 className="text-md font-semibold text-text-primary mb-4">Analyses per Company Over Time</h4>
+                  <ResponsiveContainer width="100%" height={300}>
+                    <LineChart data={pivoted}>
+                      <XAxis dataKey="month" stroke="#94a3b8" fontSize={12} />
+                      <YAxis stroke="#94a3b8" fontSize={12} />
+                      <Tooltip
+                        contentStyle={{
+                          backgroundColor: '#1e293b',
+                          border: '1px solid rgba(99, 102, 241, 0.3)',
+                          borderRadius: '8px',
+                        }}
+                        labelStyle={{ color: '#f8fafc' }}
+                      />
+                      <Legend />
+                      {companies.map((company, idx) => (
+                        <Line
+                          key={company}
+                          type="monotone"
+                          dataKey={company}
+                          stroke={COLORS[idx % COLORS.length]}
+                          strokeWidth={2}
+                          dot={{ r: 4 }}
+                          name={company.toUpperCase()}
+                        />
+                      ))}
+                    </LineChart>
+                  </ResponsiveContainer>
+                </div>
+              );
+            })()}
+
+            {/* Analysis type distribution over time (stacked bar) */}
+            {trendsQuery.data.by_type_over_time.length > 0 && (() => {
+              const types = [...new Set(trendsQuery.data!.by_type_over_time.map(d => d.analysis_type))];
+              const months = [...new Set(trendsQuery.data!.by_type_over_time.map(d => d.month))].sort();
+              const pivoted = months.map(month => {
+                const row: Record<string, string | number> = { month };
+                for (const t of types) {
+                  const entry = trendsQuery.data!.by_type_over_time.find(d => d.month === month && d.analysis_type === t);
+                  row[t] = entry?.count || 0;
+                }
+                return row;
+              });
+
+              return (
+                <div className="bg-bg-card/60 border border-primary/15 rounded-2xl p-6">
+                  <h4 className="text-md font-semibold text-text-primary mb-4">Analysis Types Over Time</h4>
+                  <ResponsiveContainer width="100%" height={300}>
+                    <BarChart data={pivoted}>
+                      <XAxis dataKey="month" stroke="#94a3b8" fontSize={12} />
+                      <YAxis stroke="#94a3b8" fontSize={12} />
+                      <Tooltip
+                        contentStyle={{
+                          backgroundColor: '#1e293b',
+                          border: '1px solid rgba(99, 102, 241, 0.3)',
+                          borderRadius: '8px',
+                        }}
+                        labelStyle={{ color: '#f8fafc' }}
+                      />
+                      <Legend />
+                      {types.map((type, idx) => (
+                        <Bar
+                          key={type}
+                          dataKey={type}
+                          stackId="types"
+                          fill={COLORS[idx % COLORS.length]}
+                          name={type}
+                        />
+                      ))}
+                    </BarChart>
+                  </ResponsiveContainer>
+                </div>
+              );
+            })()}
+          </div>
+
+          {trendsQuery.data.by_month.length === 0 && (
+            <div className="text-text-secondary text-center py-8">
+              No trend data available yet. Run analyses over multiple days to see trends.
+            </div>
+          )}
+        </div>
+      )}
     </div>
   );
 }