From 576e8fe8d6c93fbe963eee8d3a94af343753de25 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=C2=A8NW=C2=A8?= <¨neroworld@mail.ru¨>
Date: Sun, 5 Apr 2026 13:06:53 +0100
Subject: [PATCH] fix: sync KILO_SPEC.md agent models with actual agent
 definitions

- Update HistoryMiner to nemotron-3-super (was gpt-oss:20b)
- Update SDETEngineer and LeadDeveloper to qwen3-coder:480b (was qwen3-coder:free)
- Update SecurityAuditor to nemotron-3-super (was deepseek-v3.2)
- Update ReleaseManager to devstral-2:123b (was devstral-2)
- Update Evaluator to nemotron-3-super (was gpt-oss:120b)
- Update PromptOptimizer to qwen/qwen3.6-plus:free (was openrouter/qwen/...)
- Update ProductOwner to glm-5 (was openrouter/qwen/...)
- Update AgentArchitect to nemotron-3-super (was gpt-oss:120b)
- Update CapabilityAnalyst to nemotron-3-super (was gpt-oss:120b)
- Update MarkdownValidator to nemotron-3-nano:30b (was qwen3.6-plus:free)
- Add missing agents: BrowserAutomation, VisualTester, Planner, Reflector, MemoryManager
- Fix workflow commands models to match actual command files
- Add missing /research command
---
 .kilo/KILO_SPEC.md | 49 +++++++++++++++++++++++++---------------------
 1 file changed, 27 insertions(+), 22 deletions(-)

diff --git a/.kilo/KILO_SPEC.md b/.kilo/KILO_SPEC.md
index 1847e08..567e7d0 100644
--- a/.kilo/KILO_SPEC.md
+++ b/.kilo/KILO_SPEC.md
@@ -416,28 +416,32 @@ Provider availability depends on configuration. Common providers include:
 | Agent | Role | Model |
 |-------|------|-------|
 | `@RequirementRefiner` | Converts vague ideas to strict User Stories | ollama-cloud/kimi-k2-thinking |
-| `@HistoryMiner` | Finds duplicates and past solutions in git | ollama-cloud/gpt-oss:20b |
+| `@HistoryMiner` | Finds duplicates and past solutions in git | ollama-cloud/nemotron-3-super |
 | `@SystemAnalyst` | Designs technical specifications | qwen/qwen3.6-plus:free |
-| `@SDETEngineer` | Writes tests following TDD | qwen/qwen3-coder:free |
-| `@LeadDeveloper` | Primary code writer | qwen/qwen3-coder:free |
+| `@SDETEngineer` | Writes tests following TDD | ollama-cloud/qwen3-coder:480b |
+| `@LeadDeveloper` | Primary code writer | ollama-cloud/qwen3-coder:480b |
 | `@FrontendDeveloper` | UI implementation with multimodal | ollama-cloud/kimi-k2.5 |
 | `@CodeSkeptic` | Adversarial code reviewer | ollama-cloud/minimax-m2.5 |
 | `@TheFixer` | Iteratively fixes bugs | ollama-cloud/minimax-m2.5 |
 | `@PerformanceEngineer` | Reviews for performance issues | ollama-cloud/nemotron-3-super |
-| `@SecurityAuditor` | Scans for vulnerabilities | ollama-cloud/deepseek-v3.2 |
-| `@ReleaseManager` | Git operations and deployments | ollama-cloud/devstral-2 |
-| `@Evaluator` | Scores agent effectiveness | ollama-cloud/gpt-oss:120b |
-| `@PromptOptimizer` | Improves agent prompts | openrouter/qwen/qwen3.6-plus:free |
-| `@ProductOwner` | Manages issue checklists | openrouter/qwen/qwen3.6-plus:free |
+| `@SecurityAuditor` | Scans for vulnerabilities | ollama-cloud/nemotron-3-super |
+| `@ReleaseManager` | Git operations and deployments | ollama-cloud/devstral-2:123b |
+| `@Evaluator` | Scores agent effectiveness | ollama-cloud/nemotron-3-super |
+| `@PromptOptimizer` | Improves agent prompts | qwen/qwen3.6-plus:free |
+| `@ProductOwner` | Manages issue checklists | ollama-cloud/glm-5 |
 | `@Orchestrator` | Routes tasks between agents | ollama-cloud/glm-5 |
-| `@AgentArchitect` | Manages agent network per Kilo.ai spec | ollama-cloud/gpt-oss:120b |
-| `@CapabilityAnalyst` | Analyzes task coverage, identifies gaps | ollama-cloud/gpt-oss:120b |
-| `@MarkdownValidator` | Validates Markdown for Gitea issues | qwen/qwen3.6-plus:free |
-| `@FrontendDeveloper` | UI implementation with multimodal | ollama-cloud/kimi-k2.5 |
+| `@AgentArchitect` | Manages agent network per Kilo.ai spec | ollama-cloud/nemotron-3-super |
+| `@CapabilityAnalyst` | Analyzes task coverage, identifies gaps | ollama-cloud/nemotron-3-super |
+| `@MarkdownValidator` | Validates Markdown for Gitea issues | ollama-cloud/nemotron-3-nano:30b |
 | `@BackendDeveloper` | Node.js, Express, APIs, database specialist | ollama-cloud/deepseek-v3.2 |
 | `@GoDeveloper` | Go, Gin, Echo, concurrent systems specialist | ollama-cloud/qwen3-coder:480b |
 | `@DevOpsEngineer` | Docker, Kubernetes, CI/CD, infrastructure | ollama-cloud/deepseek-v3.2 |
 | `@WorkflowArchitect` | Creates workflow definitions with complete architecture | ollama-cloud/gpt-oss:120b |
+| `@BrowserAutomation` | Playwright E2E testing, browser automation | ollama-cloud/glm-5 |
+| `@VisualTester` | Visual regression testing with pixelmatch | ollama-cloud/glm-5 |
+| `@Planner` | Task decomposition, CoT, ToT planning | ollama-cloud/nemotron-3-super |
+| `@Reflector` | Self-reflection, lesson extraction | ollama-cloud/nemotron-3-super |
+| `@MemoryManager` | Memory systems, context retrieval | ollama-cloud/nemotron-3-super |
 
 **Note:** For AgentArchitect, use `subagent_type: "system-analyst"` with prompt "You are Agent Architect..." (workaround for unsupported agent-architect type).
 
@@ -447,21 +451,22 @@ Provider availability depends on configuration. Common providers include:
 |---------|-------------|-------|
 | `/landing-page` | Create landing page CMS from HTML mockups | ollama-cloud/kimi-k2.5 |
 | `/commerce` | Create e-commerce site with products, cart, payments | qwen/qwen3-coder:free |
-| `/blog` | Create blog/CMS with posts, comments, SEO | qwen/qeen3-coder:free |
+| `/blog` | Create blog/CMS with posts, comments, SEO | qwen/qwen3-coder:free |
 | `/booking` | Create booking system for services/appointments | qwen/qwen3-coder:free |
 | `/workflow` | Run complete workflow with quality gates | ollama-cloud/glm-5 |
 | `/pipeline` | Run full agent pipeline for issue | - |
-| `/feature` | Full feature development pipeline | qwen/qwen3-coder:free |
-| `/code` | Quick code generation | qwen/qwen3-coder:free |
-| `/debug` | Analyzes and fixes bugs | openai/gpt-oss-20b |
+| `/feature` | Full feature development pipeline | openrouter/qwen/qwen3-coder:free |
+| `/code` | Quick code generation | openrouter/qwen/qwen3-coder:free |
+| `/debug` | Analyzes and fixes bugs | ollama-cloud/gpt-oss:20b |
 | `/ask` | Answers codebase questions | openai/qwen3-32b |
-| `/plan` | Creates detailed task plans | qwen/qwen3-coder:free |
+| `/plan` | Creates detailed task plans | openrouter/qwen/qwen3-coder:free |
 | `/e2e-test` | Run E2E tests with browser automation | - |
-| `/status` | Check pipeline status for issue | - |
-| `/evaluate` | Generate performance report | - |
-| `/review` | Code review workflow | - |
-| `/review-watcher` | Auto-validate review results | - |
-| `/hotfix` | Hotfix workflow | - |
+| `/status` | Check pipeline status for issue | qwen/qwen3.6-plus:free |
+| `/evaluate` | Generate performance report | ollama-cloud/gpt-oss:120b |
+| `/review` | Code review workflow | openrouter/minimax/minimax-m2.5:free |
+| `/review-watcher` | Auto-validate review results | ollama-cloud/glm-5 |
+| `/hotfix` | Hotfix workflow | openrouter/minimax/minimax-m2.5:free |
+| `/research` | Run research and self-improvement | ollama-cloud/glm-5 |
 
 ### Workflow Pipeline