diff --git a/4-Infrastructure/shim/break_glass_mcp.py b/4-Infrastructure/shim/break_glass_mcp.py index b3a027bd..aa3e96f4 100644 --- a/4-Infrastructure/shim/break_glass_mcp.py +++ b/4-Infrastructure/shim/break_glass_mcp.py @@ -28,48 +28,80 @@ OPENROUTER_BASE = "https://openrouter.ai/api/v1" PANELS = { "lean_proof": { "analysis_models": [ - "anthropic/claude-opus-4.8", - "deepseek/deepseek-v4-pro", - "google/gemini-3.1-pro-preview", + "anthropic/claude-opus-4.8", # Lean expertise, formal proof + "deepseek/deepseek-v4-pro", # Best math reasoning + "openai/gpt-5.5", # Widest training data + "cohere/command-a-03-2026", # Structured output, tool-use optimized + "google/gemini-3.1-pro-preview", # Different thinking style + "zhipu/glm-5.2", # 753B, genuinely different architecture + "moonshotai/kimi-k2.6", # Strong code, different training + "deepseek/deepseek-v4-flash", # Fast, good for quick iterations ], "judge": "anthropic/claude-opus-4.8", - "budget": 1.00, + "budget": 2.50, }, "code_bug": { "analysis_models": [ - "openai/gpt-5.5", - "anthropic/claude-opus-4.8", - "moonshotai/kimi-k2.6", + "openai/gpt-5.5", # Breadth, ops knowledge + "anthropic/claude-opus-4.8", # Depth, precision + "deepseek/deepseek-v4-pro", # Math/code reasoning + "moonshotai/kimi-k2.6", # Different code style + "cohere/command-a-03-2026", # Structured output + "deepseek/deepseek-v4-flash", # Fast iterations ], "judge": "anthropic/claude-opus-4.8", - "budget": 0.75, + "budget": 1.80, }, "architecture": { "analysis_models": [ - "anthropic/claude-opus-4.8", - "openai/gpt-5.5", - "google/gemini-3.1-pro-preview", + "anthropic/claude-opus-4.8", # Deep reasoning + "openai/gpt-5.5", # Breadth + "deepseek/deepseek-v4-pro", # Math rigor + "cohere/command-a-03-2026", # Structured output + "google/gemini-3.1-pro-preview", # Different perspective + "zhipu/glm-5.2", # Architectural diversity + "moonshotai/kimi-k2.6", # Code-first thinking + "deepseek/deepseek-v4-flash", # Quick iterations + ], + "judge": "anthropic/claude-opus-4.8", + "budget": 2.50, + }, + "math_novel": { + "analysis_models": [ + "deepseek/deepseek-v4-pro", # Best math reasoning + "anthropic/claude-opus-4.8", # Formal rigor + "google/gemini-3.1-pro-preview", # Breadth + "cohere/command-a-03-2026", # Structured output + "zhipu/glm-5.2", # Different math tradition + "deepseek/deepseek-v4-flash", # Quick checks + ], + "judge": "anthropic/claude-opus-4.8", + "budget": 2.00, + }, + "infra_debug": { + "analysis_models": [ + "openai/gpt-5.5", # Ops knowledge + "anthropic/claude-opus-4.8", # Precision + "deepseek/deepseek-v4-pro", # Systems reasoning + "cohere/command-a-03-2026", # Structured tool chains + "deepseek/deepseek-v4-flash", # Quick checks ], "judge": "anthropic/claude-opus-4.8", "budget": 1.50, }, - "math_novel": { + "hard_wall": { "analysis_models": [ - "deepseek/deepseek-v4-pro", "anthropic/claude-opus-4.8", - "google/gemini-3.1-pro-preview", - ], - "judge": "anthropic/claude-opus-4.8", - "budget": 1.00, - }, - "infra_debug": { - "analysis_models": [ + "deepseek/deepseek-v4-pro", "openai/gpt-5.5", - "anthropic/claude-opus-4.8", - "deepseek/deepseek-v4-pro", + "cohere/command-a-03-2026", + "google/gemini-3.1-pro-preview", + "zhipu/glm-5.2", + "moonshotai/kimi-k2.6", + "deepseek/deepseek-v4-flash", ], "judge": "anthropic/claude-opus-4.8", - "budget": 0.75, + "budget": 3.50, }, } @@ -118,6 +150,8 @@ def classify_problem(problem: str) -> str: return "math_novel" if any(w in lower for w in ["infra", "deploy", "k3s", "docker", "ssh"]): return "infra_debug" + if any(w in lower for w in ["stuck", "wall", "impossible", "no idea", "tried everything"]): + return "hard_wall" return "code_bug"