diff --git a/.kilo/EVOLUTION_LOG.md b/.kilo/EVOLUTION_LOG.md
index be784ea..605cd0f 100644
--- a/.kilo/EVOLUTION_LOG.md
+++ b/.kilo/EVOLUTION_LOG.md
@@ -557,7 +557,7 @@ No specialized agent existed for live server incident response, forensics, malwa
 
 ### Implementation
 - Created: `.kilo/agents/incident-responder.md`
-- Model: ollama-cloud/kimi-k2.6:cloud
+- Model: ollama-cloud/kimi-k2.6
 - Permissions: read, edit, write, bash: allow; task: deny-by-default with code-skeptic + orchestrator allow
 
 ### Skills Created
diff --git a/.kilo/KILO_SPEC.md b/.kilo/KILO_SPEC.md
index e79f507..adca432 100644
--- a/.kilo/KILO_SPEC.md
+++ b/.kilo/KILO_SPEC.md
@@ -441,26 +441,26 @@ Provider availability depends on configuration. Common providers include:
 | `@FrontendDeveloper` | Handles UI implementation with multimodal capabilities. | ollama-cloud/kimi-k2.5 |
 | `@BackendDeveloper` | Backend specialist for Node. | ollama-cloud/deepseek-v3.2 |
 | `@GoDeveloper` | Go backend specialist for Gin, Echo, APIs, and database integration. | ollama-cloud/qwen3-coder:480b |
-| `@DevopsEngineer` | DevOps specialist for Docker, Kubernetes, CI/CD pipeline automation, and infrastructure management. | ollama-cloud/kimi-k2.6:cloud |
+| `@DevopsEngineer` | DevOps specialist for Docker, Kubernetes, CI/CD pipeline automation, and infrastructure management. | ollama-cloud/kimi-k2.6 |
 | `@CodeSkeptic` | Adversarial code reviewer. | ollama-cloud/minimax-m2.5 |
 | `@TheFixer` | Iteratively fixes bugs based on specific error reports and test failures. | ollama-cloud/minimax-m2.5 |
 | `@PerformanceEngineer` | Reviews code for performance issues. | ollama-cloud/nemotron-3-super |
 | `@SecurityAuditor` | Scans for security vulnerabilities, OWASP Top 10, dependency CVEs, and hardcoded secrets. | ollama-cloud/nemotron-3-super |
 | `@VisualTester` | Visual regression testing agent that compares screenshots and detects UI differences using pixelmatch and image diff. | ollama-cloud/qwen3-coder:480b |
-| `@Orchestrator` | Main dispatcher. | ollama-cloud/kimi-k2.6:cloud |
+| `@Orchestrator` | Main dispatcher. | ollama-cloud/kimi-k2.6 |
 | `@ReleaseManager` | Manages git operations, semantic versioning, branching, and deployments. | ollama-cloud/devstral-2:123b |
 | `@Evaluator` | Scores agent effectiveness after task completion for continuous improvement. | ollama-cloud/nemotron-3-super |
 | `@PromptOptimizer` | Improves agent system prompts based on performance failures. | ollama-cloud/glm-5.1 |
 | `@ProductOwner` | Manages issue checklists, status labels, tracks progress and coordinates with human users. | ollama-cloud/glm-5.1 |
-| `@AgentArchitect` | Creates, modifies, and reviews new agents, workflows, and skills based on capability gap analysis. | ollama-cloud/kimi-k2.6:cloud |
+| `@AgentArchitect` | Creates, modifies, and reviews new agents, workflows, and skills based on capability gap analysis. | ollama-cloud/kimi-k2.6 |
 | `@CapabilityAnalyst` | Analyzes task requirements against available agents, workflows, and skills. | ollama-cloud/nemotron-3-super |
 | `@WorkflowArchitect` | Creates and maintains workflow definitions with complete architecture, Gitea integration, and quality gates. | ollama-cloud/gpt-oss:120b |
 | `@MarkdownValidator` | Validates and corrects Markdown descriptions for Gitea issues. | ollama-cloud/nemotron-3-nano:30b |
-| `@BrowserAutomation` | Browser automation agent using Playwright MCP for E2E testing, form filling, navigation, and web interaction. | ollama-cloud/kimi-k2.6:cloud |
+| `@BrowserAutomation` | Browser automation agent using Playwright MCP for E2E testing, form filling, navigation, and web interaction. | ollama-cloud/kimi-k2.6 |
 | `@Planner` | Advanced task planner using Chain of Thought, Tree of Thoughts, and Plan-Execute-Reflect. | ollama-cloud/nemotron-3-super |
 | `@Reflector` | Self-reflection agent using Reflexion pattern - learns from mistakes. | ollama-cloud/nemotron-3-super |
 | `@MemoryManager` | Manages agent memory systems - short-term (context), long-term (vector store), and episodic (experiences). | ollama-cloud/nemotron-3-super |
-| `@IncidentResponder` | Server incident response, live forensics, malware removal, hardening, and SSH-based cleanup. | ollama-cloud/kimi-k2.6:cloud |
+| `@IncidentResponder` | Server incident response, live forensics, malware removal, hardening, and SSH-based cleanup. | ollama-cloud/kimi-k2.6 |
 
 
 
diff --git a/.kilo/agents/agent-architect.md b/.kilo/agents/agent-architect.md
index c37ab41..d57dde2 100755
--- a/.kilo/agents/agent-architect.md
+++ b/.kilo/agents/agent-architect.md
@@ -1,7 +1,7 @@
 ---
 name: Agent Architect
 mode: subagent
-model: ollama-cloud/kimi-k2.6:cloud
+model: ollama-cloud/kimi-k2.6
 description: Creates, modifies, and reviews new agents, workflows, and skills based on capability gap analysis. Tier 2 meta-agent with self-cascade enabled.
 color: "#8B5CF6"
 permission:
diff --git a/.kilo/agents/devops-engineer.md b/.kilo/agents/devops-engineer.md
index 2e7fbd9..38d4b52 100755
--- a/.kilo/agents/devops-engineer.md
+++ b/.kilo/agents/devops-engineer.md
@@ -1,7 +1,7 @@
 ---
 description: DevOps specialist for Docker, Kubernetes, CI/CD pipeline automation, and infrastructure management (GNS-2 Tier 1)
 mode: subagent
-model: ollama-cloud/kimi-k2.6:cloud
+model: ollama-cloud/kimi-k2.6
 color: "#FF6B35"
 permission:
   read: allow
diff --git a/.kilo/agents/incident-responder.md b/.kilo/agents/incident-responder.md
index b8ae74e..54fe63d 100644
--- a/.kilo/agents/incident-responder.md
+++ b/.kilo/agents/incident-responder.md
@@ -1,7 +1,7 @@
 ---
 description: Server incident response and system hardening specialist. Handles live forensics, malware removal, persistence hunting, SSH-based server cleanup, and post-incident hardening. Works with any OS and panel.
 mode: subagent
-model: ollama-cloud/kimi-k2.6:cloud
+model: ollama-cloud/kimi-k2.6
 color: "#B91C1C"
 permission:
   read: allow
diff --git a/.kilo/agents/orchestrator.md b/.kilo/agents/orchestrator.md
index a99cba4..a4cc5c1 100755
--- a/.kilo/agents/orchestrator.md
+++ b/.kilo/agents/orchestrator.md
@@ -1,7 +1,7 @@
 ---
 description: Main dispatcher. Routes tasks between agents based on Issue status and manages the workflow state machine. IF:90 for optimal routing accuracy. (GNS-2 Tier 1)
 mode: all
-model: ollama-cloud/kimi-k2.6:cloud
+model: ollama-cloud/kimi-k2.6
 variant: thinking
 color: "#7C3AED"
 permission:
diff --git a/.kilo/agents/the-fixer.md b/.kilo/agents/the-fixer.md
index c361003..3e9691a 100755
--- a/.kilo/agents/the-fixer.md
+++ b/.kilo/agents/the-fixer.md
@@ -1,7 +1,7 @@
 ---
 description: Iteratively fixes bugs based on specific error reports and test failures (GNS-2 Tier 1)
 mode: all
-model: ollama-cloud/kimi-k2.6:cloud
+model: ollama-cloud/kimi-k2.6
 color: "#F59E0B"
 permission:
   read: allow
diff --git a/.kilo/capability-index.yaml b/.kilo/capability-index.yaml
index 9a7c4f7..757fef4 100644
--- a/.kilo/capability-index.yaml
+++ b/.kilo/capability-index.yaml
@@ -23,7 +23,7 @@ agents:
     - orchestrator
     fallback_models:
     - ollama-cloud/qwen3-coder:480b
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - groq/llama-3.1-8b-instant
     - ollama-cloud/deepseek-v4-pro-max
     failover_strategy: downgraded
@@ -98,7 +98,7 @@ agents:
     - security-auditor
     - orchestrator
     fallback_models:
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - openrouter/qwen/qwen3.6-plus:free
     - groq/llama-3.1-8b-instant
     - ollama-cloud/minimax-m2.5
@@ -138,7 +138,7 @@ agents:
     - orchestrator
     fallback_models:
     - openrouter/qwen/qwen3.6-plus:free
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - groq/llama-3.1-8b-instant
     - ollama-cloud/minimax-m2.5
     failover_strategy: downgraded
@@ -166,7 +166,7 @@ agents:
     - code-skeptic
     - orchestrator
     fallback_models:
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - openrouter/qwen/qwen3.6-plus:free
     - groq/llama-3.1-8b-instant
     - ollama-cloud/deepseek-v4-pro-max
@@ -200,7 +200,7 @@ agents:
     - orchestrator
     fallback_models:
     - ollama-cloud/deepseek-v4-pro-max
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - groq/llama-3.1-8b-instant
     - openrouter/qwen/qwen3.6-plus:free
     failover_strategy: downgraded
@@ -230,7 +230,7 @@ agents:
     - visual-tester
     - orchestrator
     fallback_models:
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - openrouter/qwen/qwen3.6-plus:free
     - groq/llama-3.1-8b-instant
     - ollama-cloud/deepseek-v4-pro-max
@@ -252,14 +252,14 @@ agents:
     - ci_cd_config
     forbidden:
     - application_code
-    model: ollama-cloud/kimi-k2.6:cloud
+    model: ollama-cloud/kimi-k2.6
     mode: subagent
     delegates_to:
     - code-skeptic
     - security-auditor
     - orchestrator
     fallback_models:
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - ollama-cloud/deepseek-v4-pro-max
     - ollama-cloud/glm-5.1
     failover_strategy: downgraded
@@ -287,7 +287,7 @@ agents:
     - lead-developer
     - orchestrator
     fallback_models:
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - ollama-cloud/minimax-m2.5
     - groq/llama-3.1-8b-instant
     - ollama-cloud/deepseek-v4-pro-max
@@ -318,7 +318,7 @@ agents:
     - ollama-cloud/qwen3-coder:480b
     - ollama-cloud/deepseek-v4-pro-max
     - groq/llama-3.1-8b-instant
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     failover_strategy: mixed
     reasoning_effort: medium
   security-auditor:
@@ -343,7 +343,7 @@ agents:
     - orchestrator
     fallback_models:
     - ollama-cloud/deepseek-v4-pro-max
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - ollama-cloud/glm-5.1
     failover_strategy: downgraded
     reasoning_effort: high
@@ -370,7 +370,7 @@ agents:
     fallback_models:
     - ollama-cloud/deepseek-v4-pro-max
     - ollama-cloud/glm-5.1
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     failover_strategy: downgraded
     reasoning_effort: medium
   the-fixer:
@@ -386,13 +386,13 @@ agents:
     - resolution_notes
     forbidden:
     - feature_development
-    model: ollama-cloud/kimi-k2.6:cloud
+    model: ollama-cloud/kimi-k2.6
     mode: subagent
     delegates_to:
     - code-skeptic
     - orchestrator
     fallback_models:
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - ollama-cloud/qwen3-coder:480b
     - groq/llama-3.1-8b-instant
     - ollama-cloud/deepseek-v4-pro-max
@@ -417,7 +417,7 @@ agents:
     delegates_to:
     - orchestrator
     fallback_models:
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - ollama-cloud/deepseek-v4-pro-max
     - groq/llama-3.1-8b-instant
     - openrouter/qwen/qwen3.6-plus:free
@@ -457,7 +457,7 @@ agents:
     - the-fixer
     - orchestrator
     fallback_models:
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - ollama-cloud/deepseek-v4-pro-max
     - groq/llama-3.1-8b-instant
     - openrouter/qwen/qwen3.6-plus:free
@@ -484,7 +484,7 @@ agents:
     fallback_models:
     - ollama-cloud/glm-5.1
     - ollama-cloud/deepseek-v4-pro-max
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     failover_strategy: downgraded
     reasoning_effort: high
   capability-analyst:
@@ -508,7 +508,7 @@ agents:
     - orchestrator
     fallback_models:
     - ollama-cloud/deepseek-v4-pro-max
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - openrouter/qwen/qwen3.6-plus:free
     failover_strategy: downgraded
     reasoning_effort: low
@@ -527,7 +527,7 @@ agents:
     forbidden:
     - code_writing
     - code_review
-    model: ollama-cloud/kimi-k2.6:cloud
+    model: ollama-cloud/kimi-k2.6
     variant: thinking
     mode: all
     delegates_to:
@@ -591,7 +591,7 @@ agents:
     - evaluator
     fallback_models:
     - ollama-cloud/deepseek-v4-pro-max
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - groq/llama-3.1-8b-instant
     - ollama-cloud/glm-5
     failover_strategy: downgraded
@@ -620,7 +620,7 @@ agents:
     - orchestrator
     fallback_models:
     - ollama-cloud/deepseek-v4-pro-max
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - openrouter/qwen/qwen3.6-plus:free
     failover_strategy: downgraded
     reasoning_effort: low
@@ -643,7 +643,7 @@ agents:
     delegates_to: []
     fallback_models:
     - openrouter/qwen/qwen3.6-plus:free
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - ollama-cloud/deepseek-v4-pro-max
     failover_strategy: downgraded
     reasoning_effort: low
@@ -694,7 +694,7 @@ agents:
     delegates_to:
     - prompt-optimizer
     fallback_models:
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - ollama-cloud/deepseek-v4-pro-max
     - groq/llama-3.1-8b-instant
     - openrouter/qwen/qwen3.6-plus:free
@@ -717,7 +717,7 @@ agents:
     mode: subagent
     delegates_to: []
     fallback_models:
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - ollama-cloud/deepseek-v4-pro-max
     - openrouter/qwen/qwen3.6-plus:free
     failover_strategy: downgraded
@@ -757,7 +757,7 @@ agents:
     - integration_plan
     forbidden:
     - agent_execution
-    model: ollama-cloud/kimi-k2.6:cloud
+    model: ollama-cloud/kimi-k2.6
     variant: thinking
     mode: subagent
     delegates_to:
@@ -765,7 +765,7 @@ agents:
     - requirement-refiner
     - system-analyst
     fallback_models:
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - ollama-cloud/deepseek-v4-pro-max
     - openrouter/qwen/qwen3.6-plus:free
     failover_strategy: downgraded
@@ -792,7 +792,7 @@ agents:
     delegates_to: []
     fallback_models:
     - ollama-cloud/deepseek-v4-pro-max
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - ollama-cloud/glm-5.1
     failover_strategy: downgraded
     reasoning_effort: xhigh
@@ -883,7 +883,7 @@ agents:
     - system-analyst
     - orchestrator
     fallback_models:
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - ollama-cloud/glm-5
     - openrouter/qwen/qwen3.6-plus:free
     failover_strategy: downgraded
@@ -912,13 +912,13 @@ agents:
     forbidden:
     - code_writing
     - deployment
-    model: ollama-cloud/kimi-k2.6:cloud
+    model: ollama-cloud/kimi-k2.6
     mode: subagent
     delegates_to:
     - code-skeptic
     - orchestrator
     fallback_models:
-    - ollama-cloud/kimi-k2.6:cloud
+    - ollama-cloud/kimi-k2.6
     - ollama-cloud/deepseek-v4-pro-max
     - ollama-cloud/glm-5.1
     failover_strategy: downgraded
diff --git a/.kilo/commands/evolution.md b/.kilo/commands/evolution.md
index a80baf5..db9007f 100644
--- a/.kilo/commands/evolution.md
+++ b/.kilo/commands/evolution.md
@@ -339,7 +339,7 @@ $ /evolution research
 |-------|---------|-------|-------------|-------|---|--------|
 | planner | nemotron-3-super | 80 | deepseek-v4-pro-max | 88 | +8 | high |
 | go-developer | qwen3-coder | 85 | deepseek-v4-pro-max | 88 | +3 | medium |
-| [built-in] debug | glm-5.1 | 88 | kimi-k2.6:cloud | 90 | +2 | high |
+| [built-in] debug | glm-5.1 | 88 | kimi-k2.6 | 90 | +2 | high |
 
 ### Output
 ✅ agent-evolution/data/model-research-latest.json (28 models, 11 recommendations)
diff --git a/.kilo/kilo.jsonc b/.kilo/kilo.jsonc
index 07be968..8ec50d4 100644
--- a/.kilo/kilo.jsonc
+++ b/.kilo/kilo.jsonc
@@ -4,11 +4,11 @@
   "skills": {
     "paths": [".kilo/skills"]
   },
-  "model": "ollama-cloud/kimi-k2.6:cloud",
+  "model": "ollama-cloud/kimi-k2.6",
   "default_agent": "orchestrator",
   "agent": {
     "orchestrator": {
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "variant": "thinking",
       "description": "Main dispatcher. Routes tasks between agents based on Issue status. IF:92 for optimal routing.",
       "mode": "all",
diff --git a/.kilo/rules/evolutionary-sync.md b/.kilo/rules/evolutionary-sync.md
index ac36e0a..ed12be2 100644
--- a/.kilo/rules/evolutionary-sync.md
+++ b/.kilo/rules/evolutionary-sync.md
@@ -55,7 +55,7 @@ After running `--fix`, you MUST verify:
 □ `AGENTS.md` — category tables updated
 □ `.kilo/capability-index.yaml` — model fields updated
 □ No old models leaked (grep for previous model IDs)
-□ `ollama-cloud/kimi-k2.6` → always `:cloud` suffix
+□ `ollama-cloud/kimi-k2.6` — no `:cloud` suffix (model renamed)
 □ model-benchmarks.json — metadata.generated updated
 □ model-research-latest.json — validates against schema
 □ agent-versions.json — history entries added for all model changes
@@ -205,26 +205,26 @@ Example:
 ```
 feat: evolutionary agent model upgrades based on recommendation matrix
 
-- devops-engineer: deepseek-v3.2 → kimi-k2.6:cloud (★88)
-- browser-automation: glm-5 → kimi-k2.6:cloud (★86)
+- devops-engineer: deepseek-v3.2 → kimi-k2.6 (★88)
+- browser-automation: glm-5 → kimi-k2.6 (★86)
 - ...
 ```
 
 ## Cloud Model Suffix Check
 
-When using `ollama-cloud/kimi-k2.6` models, ALWAYS include `:cloud` suffix:
+When using `ollama-cloud/kimi-k2.6` models, use the bare model ID (the `:cloud` suffix was removed in the model rename):
 
 ```yaml
 # ✅ Correct
-model: ollama-cloud/kimi-k2.6:cloud
+model: ollama-cloud/kimi-k2.6
 
-# ❌ Wrong — missing cloud suffix
+# ❌ Wrong — stale :cloud suffix
 model: ollama-cloud/kimi-k2.6
 ```
 
 Verification:
 ```bash
-grep -r "kimi-k2\.6[^:]" .kilo/agents/ kilo-meta.json kilo.jsonc
+grep -r "kimi-k2\.6:cloud" .kilo/agents/ kilo-meta.json kilo.jsonc
 # should return nothing
 ```
 
@@ -292,5 +292,5 @@ Add to `.github/workflows/ci.yml`:
 - DO NOT update agent model without updating all sync targets
 - DO NOT add new agent without updating orchestrator permissions
 - DO NOT skip running sync script after changes
-- DO NOT use `kimi-k2.6` without `:cloud` suffix
+- DO NOT use `kimi-k2.6:cloud` — the `:cloud` suffix is obsolete
 - DO NOT commit if `sync-agents.js --check` fails
\ No newline at end of file
diff --git a/.kilo/rules/global.md b/.kilo/rules/global.md
index c7c3295..a510f1d 100644
--- a/.kilo/rules/global.md
+++ b/.kilo/rules/global.md
@@ -83,6 +83,46 @@ Key checks:
 - Safe command allowlist: `git`, `cat`, `ls`, `grep`, `find`, `node`, `python3`, `bun`, `docker` (non-privileged)
 - Forbidden: `curl`, `wget`, `eval`, `exec`, `source`, `sh`, `bash`, `sudo`, `rm -rf`, `>` redirection to system paths
 
+## Tooling Infrastructure — Use What Exists
+
+Before attempting to install ANY browser automation or testing tool, check the project's existing infrastructure.
+
+### Playwright / Visual Testing
+The project already has a complete visual testing stack:
+- **Image**: `mcr.microsoft.com/playwright:v1.52.0-noble`
+- **Compose**: `docker/docker-compose.web-testing.yml`
+- **Scripts**: `tests/scripts/capture-screenshots.js`, `tests/scripts/console-error-monitor-standalone.js`
+- **Reports**: `tests/reports/visual-test-report.json`
+
+**Command patterns**:
+```bash
+# Console error check
+cd /home/swp/Projects/APAW && \
+  TARGET_URL=http://host.docker.internal:8089 \
+  docker compose -f docker/docker-compose.web-testing.yml run --rm console-monitor
+
+# Screenshot capture
+cd /home/swp/Projects/APAW && \
+  TARGET_URL=http://host.docker.internal:8089 \
+  docker compose -f docker/docker-compose.web-testing.yml run --rm screenshot-current
+
+# Full visual comparison
+cd /home/swp/Projects/APAW && \
+  TARGET_URL=http://host.docker.internal:8089 \
+  docker compose -f docker/docker-compose.web-testing.yml run --rm visual-tester
+```
+
+### Prohibited Actions
+- ❌ NEVER install `playwright`, `selenium`, `puppeteer`, `chromedriver` on the host
+- ❌ NEVER run `pip install playwright` or `npm install playwright` on the host
+- ❌ NEVER use `firefox --headless --screenshot` (SWGL errors, unreliable)
+- ❌ NEVER pull new Playwright images without checking existing ones first
+- ✅ ALWAYS use the existing Docker compose services
+- ✅ If Docker service fails, report failure — do not attempt host-level fallback
+
+### Rationale
+Host-level browser automation requires X11/display stack, GPU drivers, and sandbox configs that break in headless environments. The Docker stack was explicitly built to solve this. Host-level installation is always a waste of tokens and time.
+
 ### Config File Protection
 - Editing files in `.kilo/` (agents, rules, skills) requires explicit permission prompt
 - `kilo.jsonc` is read-only for all agents except orchestrator in explicit config-sync mode
diff --git a/.kilo/shared/self-evolution.md b/.kilo/shared/self-evolution.md
index c58e80a..d23ccf1 100644
--- a/.kilo/shared/self-evolution.md
+++ b/.kilo/shared/self-evolution.md
@@ -162,4 +162,4 @@ After each evolution:
 - [ ] kilo.jsonc manually verified (sync script does not guarantee this)
 - [ ] sync-agents.js --check passes
 - [ ] No stale models leaked (grep for previous model IDs)
-- [ ] Cloud model suffix correct (kimi-k2.6:cloud, not kimi-k2.6)
+- [ ] Cloud model suffix correct (kimi-k2.6, not kimi-k2.6:cloud)
diff --git a/agent-evolution/data/model-benchmarks.json b/agent-evolution/data/model-benchmarks.json
index 0425abb..c17d33f 100644
--- a/agent-evolution/data/model-benchmarks.json
+++ b/agent-evolution/data/model-benchmarks.json
@@ -1003,7 +1003,7 @@
     },
     {
       "agent": "devops-engineer",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "provider": "Ollama Cloud",
       "category": "Process",
       "badge_type": "nemotron",
@@ -1053,7 +1053,7 @@
     },
     {
       "agent": "the-fixer",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "provider": "Ollama Cloud",
       "category": "Process",
       "badge_type": "minimax",
@@ -1103,7 +1103,7 @@
     },
     {
       "agent": "orchestrator",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "provider": "Ollama Cloud",
       "category": "Process",
       "badge_type": "kimi",
@@ -1183,7 +1183,7 @@
     },
     {
       "agent": "agent-architect",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "provider": "Ollama Cloud",
       "category": "Process",
       "badge_type": "glm",
@@ -1302,7 +1302,7 @@
       "agent": "devops \u2192 K2.6",
       "from_model": "deepseek-v3.2",
       "from_provider": "",
-      "to_model": "kimi-k2.6:cloud \u2705",
+      "to_model": "kimi-k2.6 \u2705",
       "to_provider": "Ollama Cloud",
       "impact": "low",
       "quality_change": "+35%",
diff --git a/agent-evolution/docs/bidirectional-data-flow.md b/agent-evolution/docs/bidirectional-data-flow.md
index 83c3a5b..867d667 100644
--- a/agent-evolution/docs/bidirectional-data-flow.md
+++ b/agent-evolution/docs/bidirectional-data-flow.md
@@ -173,7 +173,7 @@ bun run agent-evolution/scripts/build-research-dashboard.ts
     "ollama-cloud/qwen3.5-122b": 66,
     "ollama-cloud/qwen3-coder-next": 80,
     "openrouter/qwen/qwen3.6-plus:free": 88,
-    "ollama-cloud/kimi-k2.6:cloud": 90
+    "ollama-cloud/kimi-k2.6": 90
   }
 }
 ```
@@ -317,13 +317,13 @@ Step 4: Log + Dashboard
 
 ### Облачный суффикс
 
-При использовании `ollama-cloud/kimi-k2.6` ВСЕГДА с суффиксом `:cloud`:
+При использовании `ollama-cloud/kimi-k2.6` суффикс `:cloud` был удалён при переименовании модели:
 
 ```yaml
 # Правильно
-model: "ollama-cloud/kimi-k2.6:cloud"
+model: "ollama-cloud/kimi-k2.6"
 
-# Неправильно — отсутствует суффикс
+# Неправильно — устаревший суффикс
 model: "ollama-cloud/kimi-k2.6"
 ```
 
@@ -341,7 +341,7 @@ model: "ollama-cloud/kimi-k2.6"
 □ Sync: sync-agents.js --fix обновил все .md файлы
 □ Check: sync-agents.js --check проходит
 □ Старые модели: grep не находит предыдущие model IDs
-□ Суффикс: kimi-k2.6:cloud (с :cloud)
+□ Суффикс: kimi-k2.6 (без :cloud)
 □ Дашборд: build-research-dashboard.ts сгенерировал свежий HTML
 □ Открыть: research-dashboard.html показывает актуальные данные
 □ Гит: все изменения add и commit
@@ -427,7 +427,7 @@ go-developer
 
 [built-in] debug
   FROM: glm-5.1 (Ollama)
-  TO:   kimi-k2.6:cloud (Ollama Cloud)
+  TO:   kimi-k2.6 (Ollama Cloud)
   DELTA: +2 (88 → 90)
   IMPACT: high
 
diff --git a/agent-evolution/ideas/apaw_agent_model_research_v3.html b/agent-evolution/ideas/apaw_agent_model_research_v3.html
index 5e9251e..2111a04 100644
--- a/agent-evolution/ideas/apaw_agent_model_research_v3.html
+++ b/agent-evolution/ideas/apaw_agent_model_research_v3.html
@@ -433,7 +433,7 @@ const cfg = [
     {a:'python-developer',m:'qwen3-coder:480b',p:'Ollama',cat:'Core Dev',b:'qwen',fit:90,s:'optimal'},
     {a:'sdet-engineer',m:'qwen3-coder:480b',p:'Ollama',cat:'QA',b:'qwen',fit:88,s:'optimal'},
     // GLM-5.1 (8 agents) — SWE-Pro 58.4 #1!
-    {a:'orchestrator',m:'kimi-k2.6:cloud',p:'Ollama Cloud',cat:'Process',b:'kimi',fit:92,s:'optimal'},
+    {a:'orchestrator',m:'kimi-k2.6',p:'Ollama Cloud',cat:'Process',b:'kimi',fit:92,s:'optimal'},
     {a:'evaluator',m:'glm-5.1',p:'Ollama',cat:'Process',b:'glm',fit:86,s:'optimal'},
     {a:'capability-analyst',m:'glm-5.1',p:'Ollama',cat:'Analysis',b:'glm',fit:85,s:'optimal'},
     {a:'architect-indexer',m:'glm-5.1',p:'Ollama',cat:'Analysis',b:'glm',fit:88,s:'optimal'},
@@ -442,7 +442,7 @@ const cfg = [
     {a:'requirement-refiner',m:'glm-5.1',p:'Ollama',cat:'Analysis',b:'glm',fit:88,s:'optimal'},
     {a:'workflow-architect',m:'glm-5.1',p:'Ollama',cat:'Workflow',b:'glm',fit:84,s:'good'},
     // Nemotron 3 Super (7 agents)
-    {a:'agent-architect',m:'kimi-k2.6:cloud',p:'Ollama Cloud',cat:'Meta',b:'kimi',fit:86,s:'optimal'},
+    {a:'agent-architect',m:'kimi-k2.6',p:'Ollama Cloud',cat:'Meta',b:'kimi',fit:86,s:'optimal'},
     {a:'security-auditor',m:'nemotron-3-super',p:'Ollama',cat:'Security',b:'nemotron',fit:76,s:'good'},
     {a:'performance-engineer',m:'nemotron-3-super',p:'Ollama',cat:'Performance',b:'nemotron',fit:78,s:'good'},
     {a:'history-miner',m:'nemotron-3-super',p:'Ollama',cat:'Analysis',b:'nemotron',fit:85,s:'optimal'},
@@ -450,7 +450,7 @@ const cfg = [
     {a:'planner',m:'nemotron-3-super',p:'Ollama',cat:'Cognitive',b:'nemotron',fit:80,s:'good'},
     {a:'reflector',m:'nemotron-3-super',p:'Ollama',cat:'Cognitive',b:'nemotron',fit:78,s:'good'},
     // GLM-5 (3 agents)
-    {a:'browser-automation',m:'kimi-k2.6:cloud',p:'Ollama Cloud',cat:'Testing',b:'kimi',fit:86,s:'optimal'},
+    {a:'browser-automation',m:'kimi-k2.6',p:'Ollama Cloud',cat:'Testing',b:'kimi',fit:86,s:'optimal'},
     {a:'product-owner',m:'glm-5.1',p:'Ollama',cat:'Management',b:'glm',fit:84,s:'optimal'},
     {a:'visual-tester',m:'qwen3-coder:480b',p:'Ollama',cat:'Testing',b:'qwen',fit:82,s:'optimal'},
     // Qwen 3.6+ FREE (2 agents)
@@ -460,7 +460,7 @@ const cfg = [
     {a:'code-skeptic',m:'minimax-m2.5',p:'Ollama',cat:'QA',b:'minimax',fit:85,s:'good'},
     {a:'the-fixer',m:'minimax-m2.5',p:'Ollama',cat:'Fixes',b:'minimax',fit:88,s:'optimal'},
     // DeepSeek V3.2 (1 agent)
-    {a:'devops-engineer',m:'kimi-k2.6:cloud',p:'Ollama Cloud',cat:'DevOps',b:'kimi',fit:88,s:'optimal'},
+    {a:'devops-engineer',m:'kimi-k2.6',p:'Ollama Cloud',cat:'DevOps',b:'kimi',fit:88,s:'optimal'},
     // Nemotron Nano (1 agent)
     {a:'markdown-validator',m:'nemotron-3-nano:30b',p:'Ollama',cat:'Validation',b:'nemotron',fit:70,s:'good'},
     // Built-in (from kilo.jsonc)
@@ -607,7 +607,7 @@ const recs = [
     // --- APPLIED (для справки) ---
     {a:"frontend-dev → M2.5",from:"qwen3-coder (90)",fromP:"Ollama",to:"MiniMax M2.5 (★92) ✅",toP:"Ollama",imp:"low",
      q:"+2%",sp:"=",ctx:"204K",prov:"Ollama",r:"Spec-writing, UI architect. APPLIED."},
-    {a:"devops → K2.6",from:"deepseek-v3.2",fromP:"",to:"kimi-k2.6:cloud ✅",toP:"Ollama Cloud",imp:"low",
+    {a:"devops → K2.6",from:"deepseek-v3.2",fromP:"",to:"kimi-k2.6 ✅",toP:"Ollama Cloud",imp:"low",
      q:"+35%",sp:"=",ctx:"256K",prov:"",r:"APPLIED."},
 
     // --- Fine-tuning ---
diff --git a/agent-evolution/research-dashboard.html b/agent-evolution/research-dashboard.html
index 597a0fb..2f21577 100644
--- a/agent-evolution/research-dashboard.html
+++ b/agent-evolution/research-dashboard.html
@@ -1425,7 +1425,7 @@ const EMBEDDED_DATA = {
     },
     {
       "agent": "devops-engineer",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "provider": "Ollama Cloud",
       "category": "Process",
       "badge_type": "nemotron",
@@ -1475,7 +1475,7 @@ const EMBEDDED_DATA = {
     },
     {
       "agent": "the-fixer",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "provider": "Ollama Cloud",
       "category": "Process",
       "badge_type": "minimax",
@@ -1525,7 +1525,7 @@ const EMBEDDED_DATA = {
     },
     {
       "agent": "orchestrator",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "provider": "Ollama Cloud",
       "category": "Process",
       "badge_type": "kimi",
@@ -1605,7 +1605,7 @@ const EMBEDDED_DATA = {
     },
     {
       "agent": "agent-architect",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "provider": "Ollama Cloud",
       "category": "Process",
       "badge_type": "glm",
@@ -1724,7 +1724,7 @@ const EMBEDDED_DATA = {
       "agent": "devops → K2.6",
       "from_model": "deepseek-v3.2",
       "from_provider": "",
-      "to_model": "kimi-k2.6:cloud ✅",
+      "to_model": "kimi-k2.6 ✅",
       "to_provider": "Ollama Cloud",
       "impact": "low",
       "quality_change": "+35%",
diff --git a/kilo-meta.json b/kilo-meta.json
index 84cb667..f5ca979 100644
--- a/kilo-meta.json
+++ b/kilo-meta.json
@@ -68,7 +68,7 @@
     "devops-engineer": {
       "file": ".kilo/agents/devops-engineer.md",
       "description": "DevOps specialist for Docker, Kubernetes, CI/CD pipeline automation, and infrastructure management",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "mode": "subagent",
       "color": "#FF6B35",
       "category": "core"
@@ -84,7 +84,7 @@
     "the-fixer": {
       "file": ".kilo/agents/the-fixer.md",
       "description": "Iteratively fixes bugs based on specific error reports and test failures",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "mode": "all",
       "color": "#F59E0B",
       "category": "quality"
@@ -115,7 +115,7 @@
     "orchestrator": {
       "file": ".kilo/agents/orchestrator.md",
       "description": "Main dispatcher. Routes tasks between agents based on Issue status and manages the workflow state machine",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "mode": "all",
       "color": "#7C3AED",
       "category": "meta"
@@ -152,7 +152,7 @@
     "agent-architect": {
       "file": ".kilo/agents/agent-architect.md",
       "description": "Creates, modifies, and reviews new agents, workflows, and skills based on capability gap analysis",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "mode": "subagent",
       "category": "meta"
     },
@@ -251,7 +251,7 @@
     "incident-responder": {
       "file": ".kilo/agents/incident-responder.md",
       "description": "Server incident response and system hardening specialist. Handles live forensics, malware removal, persistence hunting, SSH-based server cleanup, and post-incident hardening. Works with any OS and panel.",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "mode": "subagent",
       "color": "#B91C1C",
       "category": "core"
diff --git a/kilo.jsonc b/kilo.jsonc
index dcdb761..7b0e9f4 100644
--- a/kilo.jsonc
+++ b/kilo.jsonc
@@ -198,7 +198,7 @@
     "the-fixer": {
       "description": "Iteratively fixes bugs based on specific error reports and test failures",
       "mode": "all",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "color": "#F59E0B",
       "permission": {
         "read": "allow",
@@ -218,7 +218,7 @@
     "performance-engineer": {
       "description": "Reviews code for performance issues. Focuses on efficiency, N+1 queries, memory leaks, and algorithmic complexity",
       "mode": "all",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "color": "#0D9488",
       "permission": {
         "read": "allow",
@@ -236,7 +236,7 @@
     "security-auditor": {
       "description": "Scans for security vulnerabilities, OWASP Top 10, dependency CVEs, and hardcoded secrets",
       "mode": "subagent",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "color": "#DC2626",
       "permission": {
         "read": "allow",
@@ -269,7 +269,7 @@
     "orchestrator": {
       "description": "Main dispatcher. Routes tasks between agents based on Issue status and manages the workflow state machine",
       "mode": "all",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "color": "#7C3AED",
       "permission": {
         "read": "allow",
@@ -376,7 +376,7 @@
     "agent-architect": {
       "description": "Creates, modifies, and reviews new agents, workflows, and skills based on capability gap analysis",
       "mode": "subagent",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "permission": {
         "read": "allow",
         "edit": "allow",
@@ -502,7 +502,7 @@
     "incident-responder": {
       "description": "Server incident response and system hardening specialist. Handles live forensics, malware removal, persistence hunting, SSH-based server cleanup, and post-incident hardening. Works with any OS and panel.",
       "mode": "subagent",
-      "model": "ollama-cloud/kimi-k2.6:cloud",
+      "model": "ollama-cloud/kimi-k2.6",
       "color": "#B91C1C",
       "permission": {
         "read": "allow",