feat(agent-models): apply CRITICAL+HIGH model migrations from research

Migrations based on model-research-2026-05-24:
- prompt-optimizer: qwen3.6-plus → qwen3.5-122b (CRITICAL, IF=92)
- memory-manager: qwen3.6-plus → deepseek-v4-pro-max (CRITICAL, 1M ctx)
- system-analyst: glm-5.1 → deepseek-v4-pro-max (HIGH, matrix +6)
- evaluator: glm-5.1 → qwen3.5-122b (HIGH, IF=92)
- pipeline-judge: glm-5.1 → kimi-k2.6 (HIGH, matrix +8, 1M ctx)
- workflow-architect: glm-5.1 → qwen3.5-122b (HIGH, IF=92)

7 files changed, 12 insertions(+), 12 deletions(-)

Closes: model-research data gaps for idle models

.kilo/agents/evaluator.md

@@ -1,7 +1,7 @@
 ---
 description: Scores agent effectiveness after task completion for continuous improvement. Tier 2 meta-agent with self-cascade enabled.
 mode: subagent
-model: ollama-cloud/glm-5.1
+model: ollama-cloud/qwen3.5-122b
 variant: thinking
 color: "#047857"
 permission:

.kilo/agents/memory-manager.md

@@ -1,7 +1,7 @@
 ---
 description: Manages agent memory systems - short-term (context), long-term (vector store), and episodic (experiences) (GNS-2 Tier 0)
 mode: subagent
-model: ollama-cloud/qwen3.6-plus
+model: ollama-cloud/deepseek-v4-pro-max
 color: "#8B5CF6"
 permission:
   read: allow

.kilo/agents/pipeline-judge.md

@@ -1,7 +1,7 @@
 ---
 description: Automated pipeline judge. Evaluates workflow execution by running tests, measuring token cost and wall-clock time. Produces objective fitness scores. Never writes code - only measures and scores. (GNS-2 Tier 0)
 mode: subagent
-model: ollama-cloud/glm-5.1
+model: ollama-cloud/kimi-k2.6
 color: "#DC2626"
 permission:
   read: allow

.kilo/agents/prompt-optimizer.md

@@ -1,7 +1,7 @@
 ---
 description: Improves agent system prompts based on performance failures. Meta-learner for prompt optimization (GNS-2 Tier 1)
 mode: subagent
-model: ollama-cloud/qwen3.6-plus
+model: ollama-cloud/qwen3.5-122b
 color: "#BE185D"
 permission:
   read: allow

.kilo/agents/system-analyst.md

@@ -1,7 +1,7 @@
 ---
 description: Designs technical specifications, data schemas, and API contracts before implementation (GNS-2 Tier 1)
 mode: subagent
-model: ollama-cloud/glm-5.1
+model: ollama-cloud/deepseek-v4-pro-max
 color: "#0891B2"
 permission:
   read: allow

.kilo/agents/workflow-architect.md

@@ -1,7 +1,7 @@
 ---
 description: Creates and maintains workflow definitions with complete architecture, Gitea integration, and quality gates (GNS-2 Tier 1)
 mode: subagent
-model: ollama-cloud/glm-5.1
+model: ollama-cloud/qwen3.5-122b
 variant: thinking
 color: "#EC4899"
 permission:

.kilo/capability-index.yaml

@@ -478,7 +478,7 @@ agents:
     - database_schemas
     forbidden:
     - implementation
-    model: ollama-cloud/glm-5.1
+    model: ollama-cloud/deepseek-v4-pro-max
     mode: subagent
     delegates_to: []
     fallback_models:
@@ -611,7 +611,7 @@ agents:
     - recommendations
     forbidden:
     - code_changes
-    model: ollama-cloud/glm-5.1
+    model: ollama-cloud/qwen3.5-122b
     variant: thinking
     mode: subagent
     delegates_to:
@@ -637,7 +637,7 @@ agents:
     - optimization_report
     forbidden:
     - agent_creation
-    model: ollama-cloud/qwen3.6-plus
+    model: ollama-cloud/qwen3.5-122b
     variant: instant
     mode: subagent
     delegates_to: []
@@ -689,7 +689,7 @@ agents:
     - code_writing
     - code_changes
     - prompt_changes
-    model: ollama-cloud/glm-5.1
+    model: ollama-cloud/kimi-k2.6
     mode: subagent
     delegates_to:
     - prompt-optimizer
@@ -712,7 +712,7 @@ agents:
     - command_files
     forbidden:
     - execution
-    model: ollama-cloud/glm-5.1
+    model: ollama-cloud/qwen3.5-122b
     variant: thinking
     mode: subagent
     delegates_to: []
@@ -839,7 +839,7 @@ agents:
     forbidden:
     - code_changes
     - implementation
-    model: ollama-cloud/qwen3.6-plus
+    model: ollama-cloud/deepseek-v4-pro-max
     mode: subagent
     delegates_to: []
     fallback_models: