gate: add kunchenguid/no-mistakes for all Nix harnesses

- home.nix: add home.activation.noMistakes (declarative install to
  ~/.no-mistakes/bin + daemon via launchd, global config fallback
  agent: [pi, opencode, grok, claude, codex] covering every harness
  declared in Nix; fix shadowing of jonathanong npm no-mistakes)
- ~/.no-mistakes/config.yaml: switched from auto to ordered fallback,
  pi first (firstmate crewmates), then opencode/grok
- home/.pi/agent/*, home/.grok/config.toml, home/.config/opencode2:
  align to oMLX/qwen3.6-35b local model (was mixed Talos/genesis)
- rebuild.sh: ensure grok-build upgrade and OpenCode 1.x install on
  rebuild (stable CLI for free-tier, opencode2 beta is 426 there)
- dotfiles repo: no-mistakes init (gate at
  ~/.no-mistakes/repos/916cb6ded81b.git, remote no-mistakes)

home/.config/opencode2/opencode.json

@@ -1,52 +1,8 @@
 {
   "$schema": "https://opencode.ai/config.json",
-  "model": "talos/ornith-worker-1",
+  "model": "omlx/qwen3.6-35b",
   "autoupdate": false,
   "providers": {
-    "talos": {
-      "name": "Talos Cluster",
-      "package": "@opencode-ai/ai/providers/openai-compatible",
-      "settings": {
-        "baseURL": "http://10.37.0.165:30081/v1"
-      },
-      "models": {
-        "ornith-worker-1": {
-          "modelID": "ornith-worker-1",
-          "name": "Ornith Worker 1 (RTX 4070 Super)",
-          "capabilities": {
-            "tools": true,
-            "input": ["text"],
-            "output": ["text"]
-          },
-          "limit": {
-            "context": 132768,
-            "output": 65536
-          }
-        }
-      }
-    },
-    "talos-worker-2": {
-      "name": "Talos Worker 2",
-      "package": "@opencode-ai/ai/providers/openai-compatible",
-      "settings": {
-        "baseURL": "http://10.37.0.219:30082/v1"
-      },
-      "models": {
-        "genesis-hermes-worker-2": {
-          "modelID": "/models/Hermes3.6-35B-A3B-Uncensored-Genesis-V6-APEX.gguf",
-          "name": "Genesis Hermes V6 APEX (RTX 3080 12GB, vision)",
-          "capabilities": {
-            "tools": true,
-            "input": ["text"],
-            "output": ["text"]
-          },
-          "limit": {
-            "context": 131072,
-            "output": 65536
-          }
-        }
-      }
-    },
     "omlx": {
       "name": "oMLX (Local)",
       "package": "@opencode-ai/ai/providers/openai-compatible",
@@ -54,48 +10,9 @@
         "baseURL": "http://localhost:8000/v1"
       },
       "models": {
-        "ornith-35b": {
-          "modelID": "Ornith-35B",
-          "name": "Ornith 35B (Qwen3.5 MoE, 4-bit, 131K ctx)",
-          "capabilities": {
-            "tools": true,
-            "input": ["text"],
-            "output": ["text"]
-          },
-          "limit": {
-            "context": 131072,
-            "output": 65536
-          }
-        },
-        "ornith-5bit": {
-          "modelID": "Ornith-1.0-35B-5bit-mlx",
-          "name": "Ornith 35B (5-bit, 262K ctx)",
-          "capabilities": {
-            "tools": true,
-            "input": ["text"],
-            "output": ["text"]
-          },
-          "limit": {
-            "context": 262144,
-            "output": 65536
-          }
-        },
-        "ternary-bonsai": {
-          "modelID": "Ternary-Bonsai-27B-mlx-2bit",
-          "name": "Ternary Bonsai 27B (2-bit, ternary weights)",
-          "capabilities": {
-            "tools": true,
-            "input": ["text"],
-            "output": ["text"]
-          },
-          "limit": {
-            "context": 131072,
-            "output": 65536
-          }
-        },
-        "dagger-qwen36-27b": {
-          "modelID": "Dagger-Qwen3.6-27B-MLX",
-          "name": "Dagger Qwen3.6 27B MLX (M5, 32GB)",
+        "qwen3.6-35b": {
+          "modelID": "Jundot/Qwen3.6-35B-A3B-oQ4-mtp",
+          "name": "Qwen 3.6 35B (o4-mtp)",
           "capabilities": {
             "tools": true,
             "input": ["text"],