fix: emergency automation fix - stop runaway trading loops

- Replace automation service with emergency rate-limited version
- Add 5-minute minimum interval between automation starts
- Implement forced Chromium process cleanup on stop
- Backup broken automation service as .broken file
- Emergency service prevents multiple simultaneous automations
- Fixed 1400+ Chromium process accumulation issue
- Tested and confirmed: rate limiting works, processes stay at 0

lib/ai-analysis.ts

@@ -80,6 +80,7 @@ export interface AnalysisResult {
 }
 
 export class AIAnalysisService {
+  private lastApiCall: number = 0
   async analyzeScreenshot(filenameOrPath: string): Promise<AnalysisResult | null> {
     try {
       let imagePath: string
@@ -594,30 +595,49 @@ Analyze all provided screenshots comprehensively and return only the JSON respon
 
       console.log(`🤖 Sending ${filenamesOrPaths.length} screenshots to OpenAI for multi-layout analysis...`)
       
-      const response = await openai.chat.completions.create({
-        model: "gpt-4o-mini", // Cost-effective model with vision capabilities
-        messages,
-        max_tokens: 2000,
-        temperature: 0.1
-      })
-
-      const content = response.choices[0]?.message?.content
-      if (!content) {
-        throw new Error('No response from OpenAI')
+      // Add rate limiting check to prevent 429 errors
+      const now = Date.now()
+      if (this.lastApiCall && (now - this.lastApiCall) < 2000) {
+        const waitTime = 2000 - (now - this.lastApiCall)
+        console.log(`⏳ Rate limiting: waiting ${waitTime}ms before OpenAI call`)
+        await new Promise(resolve => setTimeout(resolve, waitTime))
       }
-
-      console.log('🔍 Raw OpenAI response:', content.substring(0, 200) + '...')
-
-      // Parse JSON response
-      const jsonMatch = content.match(/\{[\s\S]*\}/)
-      if (!jsonMatch) {
-        throw new Error('No JSON found in response')
-      }
-
-      const analysis = JSON.parse(jsonMatch[0])
-      console.log('✅ Multi-layout analysis parsed successfully')
       
-      return analysis as AnalysisResult
+      try {
+        const response = await openai.chat.completions.create({
+          model: "gpt-4o-mini", // Cost-effective model with vision capabilities
+          messages,
+          max_tokens: 2000,
+          temperature: 0.1
+        })
+        
+        this.lastApiCall = Date.now()
+        
+        const content = response.choices[0]?.message?.content
+        if (!content) {
+          throw new Error('No response from OpenAI')
+        }
+
+        console.log('🔍 Raw OpenAI response:', content.substring(0, 200) + '...')
+
+        // Parse JSON response
+        const jsonMatch = content.match(/\{[\s\S]*\}/)
+        if (!jsonMatch) {
+          throw new Error('No JSON found in response')
+        }
+
+        const analysis = JSON.parse(jsonMatch[0])
+        console.log('✅ Multi-layout analysis parsed successfully')
+        
+        return analysis as AnalysisResult
+      } catch (error: any) {
+        if (error.status === 429) {
+          console.log('⏳ OpenAI rate limit hit - will retry on next cycle')
+          // Don't throw the error, just return null to skip this cycle gracefully
+          return null
+        }
+        throw error
+      }
 
     } catch (error: any) {
       console.error('❌ Multi-screenshot AI analysis failed:', error.message)