billion-context 0.1.90 → 0.1.91-pr.615.438

package/README.md

@@ -50,6 +50,8 @@ Agent (Claude Code / Codex / Cursor / Aider ...)
 
 The proxy injects four context-management tools (`compress`, `decompress`, `search_context`, `acp_status`) into the conversation. The model calls `compress` when the conversation grows, and the proxy executes it server-side — the compressed ranges are folded into the conversation history before the next turn.
 
+An opt-in fifth tool, `absorb` (`compress.absorb.enabled: true` — see [CONFIGURATION.md](CONFIGURATION.md)), compresses **individual tool results the moment they arrive**: large results (builds, logs, greps) get a forced absorb instruction, the model distills each into a compact summary, and the original pair is hidden from the wire from the next turn on — keeping mid-session pressure lower between fold rounds (#605).
+
 ### Two compression modes — who executes `compress`
 
 The proxy runs in one of two modes, and **the mode decides who executes
@@ -344,6 +346,9 @@ Rules:
 - Both outbound paths are covered: `/bili/` path-mode (fetch) AND MITM CONNECT
   tunnels (the proxy's connection to the real upstream goes through the HTTP
   CONNECT proxy).
+- The auto-updater's own egress (npm registry check + tarball download) uses
+  the same decision for its hosts, so `bili update` and auto-update work on
+  hosts where npm is only reachable through the proxy (#609).
 
 Env override: `BILI_UPSTREAM_PROXY=http://127.0.0.1:20172` (higher priority than
 the config file). On Windows, common Clash/Mihomo static system proxies are

package/README.zh-CN.md

@@ -50,6 +50,8 @@ AI 编程助手的<strong>通用上下文压缩代理</strong>
 
 代理向对话注入四个上下文管理工具(`compress`、`decompress`、`search_context`、`acp_status`)。模型在对话增长时调用 `compress`,代理在服务端执行 —— 压缩后的范围在下一轮之前折叠进对话历史。
 
+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)。
+
 ## 该选哪个?
 
 按客户端选: