Switch @lead model to ollama-cloud/kimi-k3:cloud

.gitea/workflows/scripts/agents.json

@@ -25,7 +25,7 @@
     "desc": "Senior dev — complex, multi-file implementation (GLM-5.2 via Ollama Cloud, text-only)."
   },
   "lead": {
-    "model": "xai/grok-4.5",
+    "model": "ollama-cloud/kimi-k3:cloud",
     "vision": true,
     "mode": "pr",
     "skills": [

.gitea/workflows/scripts/install-opencode.sh

@@ -39,7 +39,7 @@ SKILLS="${SKILLS:-[]}"
 PERM=$(jq -nc --argjson s "$SKILLS" '
   {skill: ( {"*":"deny"} + (reduce $s[] as $k ({}; . + {($k):"allow"})) )}')
 # Three OpenAI-compatible providers: local self-hosted ollama (ornith) + Ollama Cloud
-# (gemma4/kimi-k2.7-code/glm-5.2/minimax-m3) + xAI (grok-4.5). The provider `models:` maps are
+# (gemma4/kimi-k2.7-code/kimi-k3/glm-5.2/minimax-m3) + xAI (grok-4.5). The provider `models:` maps are
 # DERIVED from agents.json (the single source of truth, shared with route.sh) so every model an
 # agent is routed to is always declared in the provider config. `ollama-cloud/` prefix models go to
 # the cloud provider; `ollama/` prefix models go to the local provider; `xai/` prefix models go to