test(sandbox-policy): refresh merged web evidence

.agents/notes/implemented/feature/2026-07-30-current-sandbox-policy-context.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-30-current-sandbox-policy-context.md
-2026-07-30-current-sandbox-policy-context.md: 20920dd5842cd6e97a1b5d9f80a3646d57e0eec8
-2026-07-30-current-sandbox-policy-context.zh.md: b03e6f49df10db8fbe576613dd3ab64059d87c99
+2026-07-30-current-sandbox-policy-context.md: 87b67ede9576dafc8151925e676d789f1f5a160e
+2026-07-30-current-sandbox-policy-context.zh.md: fd0c5161174c5e94439bc13a9be240c43502b5f5

.agents/notes/implemented/feature/2026-07-30-current-sandbox-policy-context.md

@@ -32,7 +32,7 @@ After the cache-safe delivery change, commit `10d4e0ff7b68d38fc4403403b644aac442
 
 Both positive controls therefore failed the pre-registered sensitivity gate. The formal twelve-session Candidate A and B arms were not run, and these experiments do not select or validate the current wording. They establish that the earlier five-of-twelve result is not reproducible under this task and current tool guidance, and that a stronger positive control or different task distribution is required before making model-behavior rate claims. Deterministic tests below establish truthful request construction and replay only.
 
-The cache-safe delivery rework then supplied a separate, non-statistical acceptance comparison over the neutral Web task `Create the relative path policy-neutral.txt ...`; it does not replace the pre-registered twelve-session experiment. Candidate A's categorical read-only statement produced a text refusal with zero tool calls. Candidate B added one composition-conditioned sentence only for enforced families whose tools expose escalation. A fresh real-provider run then issued an ordinary `write`, observed the read-only denial, retried the same operation in the same turn with `sandbox_permissions: "workspace-write"`, received approval, read the file back, and verified the exact contents. It made no speculative escalation. Across the permission switches and four mutation steps, cache reads were 14,848–15,872 tokens while uncached input was 59–251 tokens per request, directly demonstrating the stable-prefix benefit.
+The cache-safe delivery rework then supplied a separate, non-statistical acceptance comparison over the neutral Web task `Create the relative path policy-neutral.txt ...`; it does not replace the pre-registered twelve-session experiment. Candidate A's categorical read-only statement produced a text refusal with zero tool calls. Candidate B added one composition-conditioned sentence only for enforced families whose tools expose escalation. A fresh real-provider run then issued an ordinary `write`, observed the read-only denial, retried the same operation in the same turn with `sandbox_permissions: "workspace-write"`, received approval, read the file back, and verified the exact contents. It made no speculative escalation. Across the permission switches and four mutation steps, cache reads were 14,848–15,872 tokens while uncached input was 59–306 tokens per request, directly demonstrating the stable-prefix benefit.
 
 ## Alternatives considered
 

.agents/notes/implemented/feature/2026-07-30-current-sandbox-policy-context.zh.md

@@ -32,7 +32,7 @@ Status: implemented
 
 因此，两项阳性对照均未通过预先登记的灵敏度门槛。Candidate A 与 B 的正式十二会话实验组均未运行，这些实验不选择也不验证当前措辞。它们说明先前十二次中五次的结果无法在本任务与当前工具引导下复现；在声明模型行为率之前，需要更强的阳性对照或不同的任务分布。下述确定性测试只证明请求构造与回放真实一致。
 
-随后，缓存安全交付重做针对中性 Web 任务 `Create the relative path policy-neutral.txt ...` 提供了一次独立的非统计验收对比；它不取代预先登记的十二会话实验。Candidate A 的绝对化只读声明导致模型以纯文本拒绝，工具调用为零。Candidate B 只针对受强制执行、且其工具公开升权能力的家族增加一句按组合条件化的文案。随后一次全新的真实提供方运行先发出普通 `write`，观察到只读拒绝，再在同一轮次用 `sandbox_permissions: "workspace-write"` 重试同一操作，获得批准、读回文件并核验确切内容。它没有进行推测性升权。在权限切换和四个变更步骤中，每个请求的缓存读取为 14,848–15,872 个 token，未缓存输入为 59–251 个 token，直接证明了稳定前缀的收益。
+随后，缓存安全交付重做针对中性 Web 任务 `Create the relative path policy-neutral.txt ...` 提供了一次独立的非统计验收对比；它不取代预先登记的十二会话实验。Candidate A 的绝对化只读声明导致模型以纯文本拒绝，工具调用为零。Candidate B 只针对受强制执行、且其工具公开升权能力的家族增加一句按组合条件化的文案。随后一次全新的真实提供方运行先发出普通 `write`，观察到只读拒绝，再在同一轮次用 `sandbox_permissions: "workspace-write"` 重试同一操作，获得批准、读回文件并核验确切内容。它没有进行推测性升权。在权限切换和四个变更步骤中，每个请求的缓存读取为 14,848–15,872 个 token，未缓存输入为 59–306 个 token，直接证明了稳定前缀的收益。
 
 ## 曾考虑的替代方案