billion-context 0.1.106 → 0.1.107-pr.711.564

package/README.md

@@ -120,6 +120,17 @@ turn is a semantic mismatch the model tolerates (it is clearly marked
   summaries (their tool call isn't in the agent's history and the agent's view
   skips `acp_summary`) — but that needs the id match above, which doesn't occur.
 
+**Verifying that a compression actually landed.** After executing `compress`,
+the proxy emits a confirmation marker (`📦 [ACP] Compressed …`) as plain
+assistant text — but under sustained context pressure a model was observed
+*writing that marker format itself* without ever calling the tool (#717): 17
+fake "compressions" over ~2 hours while real usage climbed to 89%. A marker
+line visible in the transcript is therefore not proof of persistence — verify
+with `acp_status` (block count increased, compressible-range start advanced)
+before trusting it. As a backstop, the proxy strips any marker-shaped line the
+model emits on its own and logs a `[marker-echo]` warning, and both the nudge
+and the injected prompt state explicitly that markers are proxy-emitted only.
+
 
 ## Which do I need?
 

package/README.zh-CN.md

@@ -58,6 +58,8 @@ AI 编程助手的<strong>通用上下文压缩代理</strong>
 
 可选的第五个工具 `absorb`(`compress.absorb.enabled: true` —— 见 [CONFIGURATION.zh-CN.md](CONFIGURATION.zh-CN.md))对**各个工具结果即时压缩**:大结果(构建、日志、grep)被附带强制吸收指令,模型将各自蒸馏为紧凑摘要,原配对从下一轮起从线上隐藏 —— 使折叠轮之间的中间会话压力更低(#605)。
 
+**如何确认压缩真的生效了。** 代理执行 `compress` 后会以普通 assistant 文本发出确认标记(`📦 [ACP] Compressed …`)—— 但曾观察到模型在持续上下文压力下*自行书写该标记格式*而从未调用工具(#717):约 2 小时内 17 次假"压缩",真实用量一路爬到 89%。因此对话中看到的标记行本身不是持久化完成的证据 —— 请先用 `acp_status` 复核(块数 +1、可压缩区间起点前移)再采信。作为兜底,代理会剥离模型自发的标记形文本并记录 `[marker-echo]` 警告;注入的 nudge 与系统提示词也明确声明标记只由代理发出。
+
 ## 该选哪个?
 
 按客户端选: