Correct Kimi Code effort to Thinking; standardize worker docs on bunx

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

README.en.md

@@ -30,7 +30,7 @@ One-shot LLM eval cases by NAGI STUDIO: same prompt, different model x harness x
 | Doubao Seed 2.0 Pro | ByteDance | Doubao Web | Pro Mode | 01 |
 | Doubao Seed 2.0 Mini | ByteDance | Doubao Web | Fast Mode | 01 |
 | MiMo v2.5 Pro | Xiaomi | Claude Code | Max | 02 |
-| Kimi K2.6 | Moonshot AI | Kimi Code (local) | Default | 02 |
+| Kimi K2.6 | Moonshot AI | Kimi Code (local) | Thinking | 02 |
 | MiniMax M3 | MiniMax | MiniMax Code Web | Thinking | 01 |
 
 Pending: Mistral Medium 3.5 · GLM-5.1 · Qwen3.7-Max (PRs welcome)

README.md

@@ -30,7 +30,7 @@ NAGI STUDIO 的 LLM 测评案例集：同一段提示词，不同「模型 × Ha
 | Doubao Seed 2.0 Pro | ByteDance | 豆包网页版 | 超能模式 | 01 |
 | Doubao Seed 2.0 Mini | ByteDance | 豆包网页版 | 快速模式 | 01 |
 | MiMo v2.5 Pro | Xiaomi | Claude Code | Max | 02 |
-| Kimi K2.6 | Moonshot AI | Kimi Code（本地） | Default | 02 |
+| Kimi K2.6 | Moonshot AI | Kimi Code（本地） | Thinking | 02 |
 | MiniMax M3 | MiniMax | MiniMax Code 网页版 | Thinking | 01 |
 
 待测：Mistral Medium 3.5 · GLM-5.1 · Qwen3.7-Max（欢迎 PR 补充）

models/kimi-k2-6.json

@@ -3,7 +3,7 @@
   "vendor": "Moonshot AI",
   "order": 100,
   "harness": "Kimi Code",
-  "effort": "Default",
+  "effort": "Thinking",
   "runs": {
     "mythos-craft": {
       "note": {