feat: implement high-intelligence model rotation pool (v8.0) and align infrastructure

app.py

@@ -4,25 +4,21 @@ import logging
 import asyncio
 import time
 import re
-import random
 from typing import List, Dict, Any, Optional
-from fastapi import FastAPI, Request
+from fastapi import FastAPI
 from pydantic import BaseModel
 import httpx
 from dotenv import load_dotenv
 
 load_dotenv()
 
-# Vera Engine - Scalable Multi-Agent Reliability Build (v7.0)
+# Vera Engine - High-Intelligence Model Rotation Pool (v8.0)
 logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger("VeraOrchestrator")
+logger = logging.getLogger("VeraArchitect")
 
 app = FastAPI()
 
-# --- 1. Infrastructure & Testing Mode ---
-# If FAST_TEST=true, skip cloud tiers for local debugging speed.
-FAST_TEST = os.getenv("FAST_TEST", "false").lower() == "true"
-
+# --- 1. Infrastructure & Elasticity ---
 class ContextPayload(BaseModel):
     scope: Optional[str] = None
     context_id: Optional[str] = None
@@ -71,22 +67,33 @@ class Agent:
     def check_health(self):
         if not self.is_healthy and time.time() > self.cooldown_until:
             self.is_healthy = True
-            logger.info(f"Agent {self.name} is healthy again")
         return self.is_healthy and len(self.keys) > 0
 
 class LocalAgent(Agent):
     def __init__(self):
         super().__init__("LocalOllama", "ollama", "llama3.2", 5)
-        self.keys = ["local"] # Placeholder
+        self.keys = ["local"]
     def check_health(self): return True
 
-# Initialize Registry
+# Initialize High-Intelligence Registry
 AGENT_REGISTRY: List[Agent] = [
+    # Tier 1: Cloud Speed
     Agent("Cloud-OpenRouter-Laguna", "openrouter", "poolside/laguna-m.1:free", 1),
     Agent("Cloud-OpenRouter-Hy3", "openrouter", "tencent/hy3:free", 1),
-    Agent("Cloud-Gemini-Flash", "gemini", "gemini-2.0-flash-exp", 2),
+    
+    # Tier 2: Intelligence Pool (Sequential Rotation)
+    Agent("Cloud-Gemini-3-Lead", "gemini", "gemini-3-flash", 2),
+    Agent("Cloud-Gemini-2.5-Stable", "gemini", "gemini-2.5-flash", 2),
+    Agent("Cloud-Gemini-2.5-Lite", "gemini", "gemini-2.5-flash-lite", 2),
+    Agent("Cloud-Gemma-4-Reasoning", "gemini", "gemma-4-31b-it", 2),
+    
+    # Tier 3: Throughput
     Agent("Cloud-Groq-Llama", "groq", "llama-3.3-70b-versatile", 3),
+    
+    # Tier 4: Fallback
     Agent("Cloud-DeepSeek-Chat", "deepseek", "deepseek-chat", 4),
+    
+    # Tier 5: Local
     LocalAgent()
 ]
 
@@ -95,25 +102,18 @@ llm_semaphore_local = asyncio.Semaphore(1)
 
 # --- 3. Orchestration Logic ---
 async def call_llm_chain(prompt: str, system: str = "") -> Optional[Dict]:
-    if FAST_TEST:
-        logger.info("FAST_TEST enabled: Skipping cloud tiers.")
-        return await call_local_agent(AGENT_REGISTRY[-1], prompt, system)
-
     json_suffix = "\n\nRETURN JSON ONLY: {\"body\": \"...\", \"cta\": \"...\", \"rationale\": \"...\"}"
     full_system = system + json_suffix
 
-    # Iterate through tiers
     for tier in range(1, 6):
-        tier_agents = [a for p, a in enumerate(AGENT_REGISTRY) if a.tier == tier and a.check_health()]
+        tier_agents = [a for a in AGENT_REGISTRY if a.tier == tier and a.check_health()]
         for agent in tier_agents:
             res = await execute_agent(agent, prompt, full_system if agent.tier < 5 else system)
             if res: return res
     return None
 
 async def execute_agent(agent: Agent, prompt: str, system: str) -> Optional[Dict]:
-    if agent.provider == "ollama":
-        return await call_local_agent(agent, prompt, system)
-    
+    if agent.provider == "ollama": return await call_local_agent(agent, prompt, system)
     key = await agent.get_key()
     if not key: return None
 
@@ -122,33 +122,18 @@ async def execute_agent(agent: Agent, prompt: str, system: str) -> Optional[Dict
             if agent.provider == "openrouter":
                 res = await client.post("https://openrouter.ai/api/v1/chat/completions",
                     headers={"Authorization": f"Bearer {key}", "HTTP-Referer": "https://vera.ai", "X-Title": "Vera Platinum"},
-                    json={
-                        "model": agent.model,
-                        "messages": [{"role": "system", "content": system}, {"role": "user", "content": prompt}],
-                        "response_format": {"type": "json_object"}
-                    }, timeout=5.0) # Tightened to 5s for chain speed
-            
+                    json={"model": agent.model, "messages": [{"role": "system", "content": system}, {"role": "user", "content": prompt}], "response_format": {"type": "json_object"}}, timeout=7.0)
             elif agent.provider == "gemini":
                 url = f"https://generativelanguage.googleapis.com/v1beta/models/{agent.model}:generateContent?key={key}"
-                res = await client.post(url, json={"contents": [{"parts": [{"text": f"System: {system}\n\nUser: {prompt}"}]}]}, timeout=5.0)
-            
+                res = await client.post(url, json={"contents": [{"parts": [{"text": f"System: {system}\n\nUser: {prompt}"}]}]}, timeout=7.0)
             elif agent.provider == "groq":
                 res = await client.post("https://api.groq.com/openai/v1/chat/completions",
                     headers={"Authorization": f"Bearer {key}"},
-                    json={
-                        "model": agent.model,
-                        "messages": [{"role": "system", "content": system}, {"role": "user", "content": prompt}],
-                        "response_format": {"type": "json_object"}
-                    }, timeout=5.0)
-
+                    json={"model": agent.model, "messages": [{"role": "system", "content": system}, {"role": "user", "content": prompt}], "response_format": {"type": "json_object"}}, timeout=7.0)
             elif agent.provider == "deepseek":
                 res = await client.post("https://api.deepseek.com/chat/completions",
                     headers={"Authorization": f"Bearer {key}"},
-                    json={
-                        "model": agent.model,
-                        "messages": [{"role": "system", "content": system}, {"role": "user", "content": prompt}],
-                        "response_format": {"type": "json_object"}
-                    }, timeout=5.0)
+                    json={"model": agent.model, "messages": [{"role": "system", "content": system}, {"role": "user", "content": prompt}], "response_format": {"type": "json_object"}}, timeout=7.0)
 
             if res.status_code == 200:
                 if agent.provider == "gemini":
@@ -156,33 +141,21 @@ async def execute_agent(agent: Agent, prompt: str, system: str) -> Optional[Dict
                     text = re.sub(r'```json\n?|\n?```', '', text).strip()
                     return json.loads(text)
                 return json.loads(res.json()["choices"][0]["message"]["content"])
-            
-            if res.status_code in [401, 429]:
-                agent.rotate_key()
-            else:
-                agent.mark_unhealthy()
-        except Exception:
-            pass
+            if res.status_code in [401, 429]: agent.rotate_key()
+            else: agent.mark_unhealthy()
+        except: pass
     return None
 
 async def call_local_agent(agent: Agent, prompt: str, system: str) -> Optional[Dict]:
     async with llm_semaphore_local:
-        logger.info(f"Local Inference: {agent.model}")
-        payload = {
-            "model": agent.model,
-            "prompt": f"System: {system}\nStrict Grounding. No Fabrication. Context: {prompt}\nUser: Return JSON message.",
-            "stream": False, "format": "json", "options": {"num_predict": 80, "temperature": 0.1}
-        }
+        payload = {"model": agent.model, "prompt": f"System: {system}\nContext: {prompt}\nUser: Return JSON message.", "stream": False, "format": "json", "options": {"num_predict": 80, "temperature": 0.1}}
         async with httpx.AsyncClient() as client:
             try:
-                # 28s here + overhead must be < 30s. If FAST_TEST=true, we skip cloud so we have full 30s.
-                res = await client.post("http://127.0.0.1:11434/api/generate", json=payload, timeout=28.0)
+                res = await client.post("http://127.0.0.1:11434/api/generate", json=payload, timeout=90.0)
                 if res.status_code == 200: return json.loads(res.json().get('response', '{}'))
-            except Exception as e:
-                logger.error(f"Local Model Error: {e}")
-                return None
+            except: return None
 
-# --- 4. Utilities & Core Logic ---
+# --- 4. Core Logic ---
 def prune_message(text: str) -> str:
     text = text.replace("\n", " ").strip()
     if len(text) <= 315: return text
@@ -203,45 +176,24 @@ async def compose(category: dict, merchant: dict, trigger: dict, customer: Optio
     hinglish_note = "USE NATURAL HINGLISH (50% English words, 50% Hindi script/transliteration)." if 'hi' in lang_pref else "USE PROFESSIONAL ENGLISH."
     
     primary_metric = list(m.items())[0] if m else None
-    verbatim_source = str(payload)[:150] if payload else None
-    evidence_block = ""
-    if primary_metric: evidence_block += f"MANDATORY METRIC: '{primary_metric[0]}' is {primary_metric[1]}. "
-    if verbatim_source: evidence_block += f"MANDATORY CITATION: '{verbatim_source}'. "
-
-    beats = category.get("seasonal_beats", [])
-    knowledge_anchor = f"INDUSTRY CONTEXT: {beats[0].get('note', '')}. " if beats else ""
+    evidence_block = f"MANDATORY METRIC: '{primary_metric[0]}' is {primary_metric[1]}. MANDATORY CITATION: '{str(payload)[:150]}'." if primary_metric else "Use curiosity hook."
 
     sys_prompt = f"""Role: Elite Growth Strategist. Target: {prefix} {owner_name} in {ident.get('locality')}.
-Objective: Compose high-impact WhatsApp message.
-RULES:
-1. TRIGGER PRIMACY: Address trigger '{trigger.get('kind')}' first.
-2. NO FABRICATION: Use only context numbers. EVIDENCE: {evidence_block}
-3. CONTEXT: {knowledge_anchor}
-4. TONE: {hinglish_note} Professional clinical-peer tone for dentists.
-5. LIMIT: 280-310 characters."""
-
-    prompt = f"CONTEXT: {json.dumps({'merchant': ident, 'perf': m, 'trigger': trigger, 'customer': customer})}"
+Objective: WhatsApp growth message.
+RULES: 1. TRIGGER PRIMACY: Address {trigger.get('kind')}. 2. NO FABRICATION. {evidence_block} 3. TONE: {hinglish_note} 4. LIMIT: 280-310 chars."""
+    prompt = f"CONTEXT: {json.dumps({'merchant': ident, 'trigger': trigger})}"
     res = await call_llm_chain(prompt, system=sys_prompt)
     if not res:
-        v, c = m.get('views', '?'), m.get('calls', '?')
-        body = f"{prefix} {owner_name}, noticed {v} views and {c} calls in {ident.get('locality')}. Important growth update found. Review now?"
-        res = {"body": body, "cta": "Reply YES", "rationale": "Hard Fallback"}
+        res = {"body": f"{prefix} {owner_name}, noticed update in {ident.get('locality')}. Review growth opportunity now?", "cta": "Reply YES", "rationale": "Hard Fallback"}
     res["body"] = prune_message(res.get("body", ""))
     return res
 
 # --- 5. Endpoints ---
-@app.on_event("startup")
-async def startup_event():
-    logger.info("Initializing Agent Registry...")
-    for agent in AGENT_REGISTRY:
-        logger.info(f"Agent {agent.name} initialized with {len(agent.keys)} keys")
-
 @app.get("/v1/healthz")
 async def healthz(): return {"status": "ok"}
 
 @app.get("/v1/metadata")
-async def metadata():
-    return {"team_name": "Vera Lead Solver", "version": "7.0", "engine": "Multi-Agent-Orchestrator"}
+async def metadata(): return {"team_name": "Vera Lead Solver", "version": "8.0", "engine": "High-Intelligence-Registry"}
 
 @app.post("/v1/context")
 def push_context(data: ContextPayload):
@@ -252,7 +204,6 @@ def push_context(data: ContextPayload):
 async def tick(req: TickRequest):
     tids = sorted(req.available_triggers, key=lambda t: contexts["trigger"].get(t, {}).get("kind", ""), reverse=True)
     results = []
-    # Sequential processing. Limit to 1 to stay under 30s.
     for tid in tids[:1]:
         res = await process_trigger(tid)
         if res: results.append(res)
@@ -265,44 +216,29 @@ async def process_trigger(trigger_id: str):
     category = contexts["category"].get(merchant.get("category_slug", ""), {"slug": "general"})
     customer = contexts["customer"].get(trigger.get("customer_id"))
     composed = await compose(category, merchant, trigger, customer)
-    is_customer_facing = trigger.get("scope") == "customer"
-
-    return {
-        "conversation_id": f"conv_{trigger_id}", "merchant_id": trigger.get("merchant_id"),
-        "customer_id": trigger.get("customer_id") if is_customer_facing else None,
-        "send_as": "merchant_on_behalf" if is_customer_facing else "vera",
-        "trigger_id": trigger_id, "template_name": "vera_platinum_v7",
-        "body": composed["body"], "cta": composed["cta"], "suppression_key": trigger_id,
-        "rationale": composed.get("rationale", "Orchestrated Inference")
-    }
+    return {"conversation_id": f"conv_{trigger_id}", "merchant_id": trigger.get("merchant_id"), "trigger_id": trigger_id, "body": composed["body"], "cta": composed["cta"]}
 
 AUTO_REPLY_PATTERNS = [r"thank you for contacting", r"we are currently away", r"automated message", r"business hours", r"auto-reply"]
-HOSTILE_PATTERNS = [r"stop", r"spam", r"useless", r"abuse", r"remove me"]
-INTENT_PATTERNS = [r"\bok\b", r"\byes\b", r"\bdo it\b", r"let'?s do it", r"\bsure\b", r"\bgo ahead\b"]
+HOSTILE_PATTERNS = [r"stop", r"spam", r"useless", r"abuse"]
+INTENT_PATTERNS = [r"\bok\b", r"\byes\b", r"\bdo it\b", r"let'?s do it", r"\bsure\b"]
 
 @app.post("/v1/reply")
 async def reply(req: Dict[str, Any]):
-    msg = req.get("message", "").lower()
-    turn = req.get("turn_number", 1)
+    msg, turn = req.get("message", "").lower(), req.get("turn_number", 1)
     for p in HOSTILE_PATTERNS:
-        if re.search(p, msg): return {"action": "end", "rationale": "Hostility detected."}
+        if re.search(p, msg): return {"action": "end", "rationale": "Hostility."}
     for p in AUTO_REPLY_PATTERNS:
         if re.search(p, msg):
             if turn > 2: return {"action": "end", "rationale": "Repeated auto-reply."}
             return {"action": "wait", "wait_seconds": 3600, "rationale": "Auto-reply wait."}
     for p in INTENT_PATTERNS:
         if re.search(p, msg):
-            sys = "Role: Vera AI. Merchant interest detected. Provide EXACT next step action. 15 words max."
-            res = await call_llm_chain(f"Merchant said: {msg}", system=sys)
-            body = res.get("body", "I'm setting that up for you now.") if res else "I'm setting that up now."
-            return {"action": "send", "body": body, "cta": "Reply YES", "rationale": "Intent Transition."}
+            res = await call_llm_chain(f"Merchant said: {msg}", system="Role: Vera AI. Interest detected. Provide EXACT next step action. 15 words max.")
+            return {"action": "send", "body": res.get("body", "I'm setting that up for you now.") if res else "I'm setting that up now.", "cta": "Reply YES"}
 
-    prompt = f"Merchant message: {req.get('message', '')}. Turn: {turn}. History: {req.get('history', [])}"
-    sys = "Role: Vera AI. If merchant says 'ok/yes/do it', provide EXACT next step action. Be concise."
-    res = await call_llm_chain(prompt, system=sys)
-    body = res.get("body", "I'm on it. Setting that up for you now. Ready?") if res else "Understood. I'll get that started. Ready?"
-    return {"action": "send", "body": body, "cta": "Reply YES"}
+    res = await call_llm_chain(f"Merchant: {msg}", system="Role: Vera AI. Growth Strategist. Be concise.")
+    return {"action": "send", "body": res.get("body", "Understood. Proceed?") if res else "Understood. Proceed?", "cta": "Reply YES"}
 
 if __name__ == "__main__":
     import uvicorn
-    uvicorn.run(app, host="0.0.0.0", port=int(os.environ.get("PORT", 8080)))
+    uvicorn.run(app, host="0.0.0.0", port=8080)