Confirm Opus 4.8 provenance (Claude Code, Max); fresh Turnstile token per sync batch

Turnstile tokens are single-use — the old implementation memoized one
token forever, so every batch after the first would fail verification.
Each sync now runs a fresh invisible challenge, and vote syncing is
debounced 2.5s so rapid ballots coalesce into one batch + one challenge.
OG count 16 -> 17 ran.

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

README.en.md

@@ -18,6 +18,7 @@ One-shot LLM eval cases by NAGI STUDIO: same prompt, different model x harness x
 |---|---|---|---|---|
 | Claude Fable 5 | Anthropic | Claude Web App | Max | 02 |
 | Claude Fable 5 | Anthropic | Claude Code | Max | 02 |
+| Claude Opus 4.8 | Anthropic | Claude Code | Max | 01 |
 | GPT-5.5 Pro | OpenAI | ChatGPT Web | Extended Pro | 02 |
 | GPT-5.5 | OpenAI | Codex CLI (no skills) | xhigh | 02 |
 | Gemini 3.1 Pro | Google | AntiGravity | High | 02 |
@@ -33,7 +34,7 @@ One-shot LLM eval cases by NAGI STUDIO: same prompt, different model x harness x
 | Kimi K2.6 | Moonshot AI | Kimi Code (local) | Thinking | 02 |
 | MiniMax M3 | MiniMax | MiniMax Code Web | Thinking | 01 |
 
-Pending: Claude Opus 4.8 · Mistral Medium 3.5 · GLM-5.1 · Qwen3.7-Max (PRs welcome)
+Pending: Mistral Medium 3.5 · GLM-5.1 · Qwen3.7-Max (PRs welcome)
 
 > This table is a hand-maintained snapshot; the site's registry section is generated live from `models/*.json` and is authoritative.
 

README.md

@@ -18,6 +18,7 @@ NAGI STUDIO 的 LLM 测评案例集：同一段提示词，不同「模型 × Ha
 |---|---|---|---|---|
 | Claude Fable 5 | Anthropic | Claude 网页版 | Max | 02 |
 | Claude Fable 5 | Anthropic | Claude Code | Max | 02 |
+| Claude Opus 4.8 | Anthropic | Claude Code | Max | 01 |
 | GPT-5.5 Pro | OpenAI | ChatGPT 网页版 | Extended Pro | 02 |
 | GPT-5.5 | OpenAI | Codex CLI（无 skill） | xhigh | 02 |
 | Gemini 3.1 Pro | Google | AntiGravity | High | 02 |
@@ -33,7 +34,7 @@ NAGI STUDIO 的 LLM 测评案例集：同一段提示词，不同「模型 × Ha
 | Kimi K2.6 | Moonshot AI | Kimi Code（本地） | Thinking | 02 |
 | MiniMax M3 | MiniMax | MiniMax Code 网页版 | Thinking | 01 |
 
-待测：Claude Opus 4.8 · Mistral Medium 3.5 · GLM-5.1 · Qwen3.7-Max（欢迎 PR 补充）
+待测：Mistral Medium 3.5 · GLM-5.1 · Qwen3.7-Max（欢迎 PR 补充）
 
 > 此表为人工维护的快照；站点上的「模型阵容」表由 `models/*.json` 实时生成，以站点为准。
 

models/claude-opus-4-8.json

@@ -5,10 +5,12 @@
   "runs": {
     "pelican-cycling": {
       "note": {
-        "zh": "以 Claude Opus 4.8 一次生成；运行环境与思考档位待维护者补充。",
-        "en": "Generated in one shot by Claude Opus 4.8; harness and effort level to be confirmed by the maintainer."
+        "zh": "在 Claude Code 中以 Claude Opus 4.8（Max 思考配额）一次生成。",
+        "en": "Generated in one shot by Claude Opus 4.8 (Max effort) inside Claude Code."
       },
       "contributor": "Nagi-ovo"
     }
-  }
+  },
+  "harness": "Claude Code",
+  "effort": "Max"
 }