feat(agent): 8-model Fusion panels with Cohere + GLM + hard_wall type

Revised panel selections (1-8 models per Fusion spec):
- lean_proof: 8 models (Opus, DeepSeek, GPT, Cohere, Gemini, GLM, Kimi, DS-Flash)
- code_bug: 6 models
- architecture: 8 models
- math_novel: 6 models
- infra_debug: 5 models
- hard_wall: 8 models (all, for truly stuck problems)

Added:
- Cohere Command A+ (structured output, tool-use optimized)
- GLM-5.2 (753B, genuinely different architecture)
- DeepSeek V4 Flash (fast iterations)
- hard_wall problem type (stuck/wall/impossible/tried everything)
- Budget cap per type (.50-.50)

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",
+            "anthropic/claude-opus-4.8",      # Lean expertise, formal proof
-            "deepseek/deepseek-v4-pro",
+            "deepseek/deepseek-v4-pro",        # Best math reasoning
-            "google/gemini-3.1-pro-preview",
+            "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",
+            "openai/gpt-5.5",                  # Breadth, ops knowledge
-            "anthropic/claude-opus-4.8",
+            "anthropic/claude-opus-4.8",       # Depth, precision
-            "moonshotai/kimi-k2.6",
+            "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",
+            "anthropic/claude-opus-4.8",       # Deep reasoning
-            "openai/gpt-5.5",
+            "openai/gpt-5.5",                  # Breadth
-            "google/gemini-3.1-pro-preview",
+            "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",
+            "deepseek/deepseek-v4-pro",
-        ],
-        "judge": "anthropic/claude-opus-4.8",
-        "budget": 1.00,
-    },
-    "infra_debug": {
-        "analysis_models": [
             "openai/gpt-5.5",
-            "anthropic/claude-opus-4.8",
+            "cohere/command-a-03-2026",
-            "deepseek/deepseek-v4-pro",
+            "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"