Standardized models: MacBook=qwen3.5:4b-mlx, GamingPC=ornith:latest across all configs

core/orchestrator.py

@@ -169,7 +169,7 @@ def _call_deepseek(prompt: str, model: str = "deepseek-chat", system: str = "",
     raise RuntimeError(f"DeepSeek API error {r.status_code}: {r.text[:200]}")
 
 
-def llm_chat(prompt: str, model: str = "qwen3.5:4b", host: str = OLLAMA_MACBOOK,
+def llm_chat(prompt: str, model: str = "qwen3.5:4b-mlx", host: str = OLLAMA_MACBOOK,
              system: str = "", temperature: float = 0.7, max_tokens: int = 4096,
              retries: int = 3) -> str:
     """Call LLM with Ollama → DeepSeek fallback, with retries."""
@@ -212,7 +212,7 @@ def llm_chat(prompt: str, model: str = "qwen3.5:4b", host: str = OLLAMA_MACBOOK,
     raise RuntimeError(f"All LLM hosts failed for model {model}")
 
 
-def llm_json(prompt: str, model: str = "qwen3.5:4b", host: str = OLLAMA_MACBOOK,
+def llm_json(prompt: str, model: str = "qwen3.5:4b-mlx", host: str = OLLAMA_MACBOOK,
              system: str = "You are a JSON-only API. Always respond with valid JSON. No markdown, no explanation.",
              temperature: float = 0.3) -> dict:
     """Call LLM and parse JSON response."""
@@ -233,7 +233,7 @@ def dual_llm_research(prompt: str, system: str = "") -> tuple[str, dict]:
                        system=system, temperature=0.3, max_tokens=4096)
     
     def call_qwen():
-        return llm_chat(prompt, model="qwen3.5:4b", host=OLLAMA_MACBOOK,
+        return llm_chat(prompt, model="qwen3.5:4b-mlx", host=OLLAMA_MACBOOK,
                        system=system, temperature=0.3, max_tokens=2048)
     
     with concurrent.futures.ThreadPoolExecutor(max_workers=2) as executor:
@@ -429,7 +429,7 @@ Cover these verticals: AI/ML, general tech, science, cryptocurrency, Linux, gami
 Respond with a JSON array of strings, each a compelling article title."""
     
     try:
-        result = llm_json(prompt, model="qwen3.5:4b", temperature=0.8)
+        result = llm_json(prompt, model="qwen3.5:4b-mlx", temperature=0.8)
         if isinstance(result, list):
             return result
         return list(result.values())[0] if result else []
@@ -481,7 +481,7 @@ Vertical assignment rules:
 Respond with a JSON array of objects. No markdown, no explanation."""
 
     try:
-        result = llm_json(prompt, model="qwen3.5:4b", temperature=0.3)
+        result = llm_json(prompt, model="qwen3.5:4b-mlx", temperature=0.3)
         if isinstance(result, list):
             # Apply algorithmic boost on top of LLM scores
             return _apply_learning_boost(result, learning_insights)
@@ -634,7 +634,7 @@ Be accurate. Cite real sources. No hallucinations. Respond with ONLY valid JSON.
                            system="You are an expert research analyst. You produce accurate, well-cited research. Never fabricate information.")
     except Exception as e:
         log.error(f"Research LLM failed: {e}. Falling back to MacBook.")
-        result = llm_json(research_prompt, model="qwen3.5:4b",
+        result = llm_json(research_prompt, model="qwen3.5:4b-mlx",
                            system="You are an expert research analyst. Be accurate and honest.")
 
     # Store knowledge package
@@ -864,7 +864,7 @@ Generate an outline appropriate for this format.
 Respond with JSON:
 {{"sections": [{{"heading": "...", "subsections": ["..."]}}, ...], "faq_questions": ["..."], "cta": "..."}}"""
 
-    outline = llm_json(outline_prompt, model="qwen3.5:4b", temperature=0.5)
+    outline = llm_json(outline_prompt, model="qwen3.5:4b-mlx", temperature=0.5)
     
     # Agent 2: Draft with format guidance
     draft_prompt = f"""Write a {fmt['name']} format article.
@@ -903,14 +903,14 @@ ARTICLE:
 {draft}
 
 Return the edited article in full Markdown. No JSON wrapper.""",
-        model="qwen3.5:4b", temperature=0.3, max_tokens=8192)
+        model="qwen3.5:4b-mlx", temperature=0.3, max_tokens=8192)
     
     # Agent 4: SEO
     seo = llm_json(f"""Optimize this article for SEO.
 TITLE: {topic_title}
 FIRST 500 CHARS: {edited[:500]}
 Respond with JSON: {{"seo_title": "...", "seo_description": "...", "keywords": ["..."]}}""",
-        model="qwen3.5:4b", temperature=0.3)
+        model="qwen3.5:4b-mlx", temperature=0.3)
     
     # Agent 5: Real Fact Check (web-verified)
     factcheck = real_fact_check(edited, topic_title)
@@ -931,7 +931,7 @@ ARTICLE:
 {edited}
 
 Return the expanded article in full Markdown. No JSON wrapper.""",
-                model="qwen3.5:4b", temperature=0.5, max_tokens=8192)
+                model="qwen3.5:4b-mlx", temperature=0.5, max_tokens=8192)
             passed, issues = quality_gate(edited, topic_title, vertical)
         
         if not passed: