billion-context-dsh 0.2.5 → 0.2.7

package/README.en.md

@@ -3,7 +3,7 @@
 [English](./README.en.md) | [中文](./README.md)
 
 > **⚠️ Beta notice — not for production use**
-> This project (**v0.2.5**) is a work-in-progress beta. The [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) itself is also in **public beta**. **Do not use either in engineering / production environments** — expect breaking changes and rough edges.
+> This project (**v0.2.7**) is a work-in-progress beta. The [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) itself is also in **public beta**. **Do not use either in engineering / production environments** — expect breaking changes and rough edges.
 
 <p align="center">
 <strong>Built with gratitude on top of these projects</strong> — please give them a ⭐:
@@ -150,7 +150,7 @@ A walkthrough of the ACP philosophy this project inherits — how active context
 | `decompress` | Restore a previously compressed block's original content (read-only); accepts the `bN` ref shown by acp_status or a compaction id |
 | `search_context` | Search compressed block summaries and originals by keyword (acp-kernel hybrid retrieval: stemming + CJK bigrams + fuzzy); hits link back to the owning block |
 | `acp_status` | CONTEXT BREAKDOWN (tool/text/summaries shares of the visible total) + compressed-block ledger + nudge decision line; no context-window rows. Drilldown supported: `scope:"compressed"` per block, `scope:"uncompressed"` + `view:"messages"`/`"ranges"` per message/range, with `tool` filter, `sort` order and `limit` cap. Drilldown row refs are kernel ids (mN) — feed them straight to `compress` as `startSeq`/`endSeq` (auto-mapped to the live surface seq); `Surface:` seqs work too |
-| `/acp` | status / compress / decompress from the command bar |
+| `/acp` | status / compress / decompress from the command bar; status also shows human-side window info (estimated context, window source, compressed-block ledger, and **nudge arbitration** — `nudge: idle/ACTIVE — reason` plus how many tokens remain until the next nudge, decided by the same kernel turn as the nudge path) |
 
 ## Upstream & credits
 

package/README.md

@@ -3,7 +3,7 @@
 [中文](./README.md) | [English](./README.en.md)
 
 > **⚠️ 测试版声明——请勿用于生产环境**
-> 本项目（**v0.2.5**）仍处于开发中的测试版。[DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) 本身也处于**公开测试版**阶段。**请勿将两者用于工程化 / 生产环境**——预期会有破坏性变更与粗糙之处。
+> 本项目（**v0.2.7**）仍处于开发中的测试版。[DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) 本身也处于**公开测试版**阶段。**请勿将两者用于工程化 / 生产环境**——预期会有破坏性变更与粗糙之处。
 
 <p align="center">
 <strong>衷心感谢以下项目——请给它们一个 ⭐：</strong>
@@ -151,7 +151,7 @@ DSH 的每个模型请求都派生自其 append-only 会话日志（*surface*）
 | `decompress` | 恢复已压缩块的原始内容（只读）；接受 acp_status 显示的 `bN` 或 compaction id |
 | `search_context` | 按关键词搜索压缩块摘要与原文（acp-kernel hybrid 检索：词干化 + CJK bigram + 模糊）；命中回链所属块 |
 | `acp_status` | CONTEXT BREAKDOWN（tool/text/summaries 占可见总量）+ 压缩块账本 + nudge 决策行；不含上下文窗口。支持钻取：`scope:"compressed"` 逐块、`scope:"uncompressed"` + `view:"messages"`/`"ranges"` 逐消息/区间，`tool` 过滤、`sort` 排序、`limit` 截断。钻取行 ref 是内核 mN——可直接作为 `compress` 的 `startSeq`/`endSeq`（自动映射为 live surface seq）；`Surface:` 的 seq 同样可用 |
-| `/acp` | 从命令栏执行 status / compress / decompress |
+| `/acp` | 从命令栏执行 status / compress / decompress；status 额外展示 human-side 窗口信息（estimated context、context window 来源、压缩账本、**nudge 仲裁**——`nudge: idle/ACTIVE — reason` 及距下一次 nudge 还差多少 token，与 nudge 路径同一内核判定） |
 
 ## 上游项目与致谢
 

package/dist/index.js

@@ -4242,8 +4242,9 @@ async function statusText(env, agent) {
   const session = agent.session;
   const ledger = rebuildBlockLedger(session.events);
   const totalTokens = ledger.reduce((sum, block) => sum + block.shadowedTokenCount, 0);
-  const coreMessages = eventsToCoreMessages(surfaceEventsOf(session));
-  const estimated = resolveTokenCount(agent, coreMessages);
+  const coreMessages = allLogMessages(session);
+  const surfaceMessages = eventsToCoreMessages(surfaceEventsOf(session));
+  const estimated = resolveTokenCount(agent, surfaceMessages);
   const window = env.windowFor === void 0 ? { limit: env.modelContextLimit, source: "explicit" } : await env.windowFor(agent);
   const limit = window.limit;
   const lines = [
@@ -4253,7 +4254,20 @@ async function statusText(env, agent) {
     `  estimated context: ${estimated} / ${limit} (${Math.round(estimated / limit * 100)}%)`,
     `  context window: ${limit} (${windowSourceLabel(window)})`
   ];
-  for (const block of ledger.slice(0, 10)) {
+  const state = structuredClone(env.store.stateFor(session));
+  const config = kernelConfigFor({ ...env, modelContextLimit: limit });
+  const turn = env.kernel.processTurn({ messages: coreMessages, state, config, tokenCount: estimated });
+  const nudge = turn.nudge;
+  if (nudge !== void 0) {
+    const label = nudge.shouldInject ? nudge.tier !== null ? `ACTIVE [T${nudge.tier}]` : "ACTIVE" : "idle";
+    lines.push(`  nudge: ${label} \u2014 ${nudge.reason}`);
+    if (!nudge.shouldInject) {
+      const maxPct = config.nudge.maxContextLimitPct;
+      const toNudge = Math.max(0, Math.round(maxPct * limit - estimated));
+      lines.push(`  next nudge: ~${toNudge.toLocaleString()} tokens to go (usage ${Math.round(nudge.contextUsage * 100)}% \u2192 ${Math.round(maxPct * 100)}% line)`);
+    }
+  }
+  for (const block of ledger) {
     const tier = block.tier > 1 ? ` [T${block.tier}]` : "";
     lines.push(`  - ${block.blockId.slice(0, 8)}${tier}: seqs ${block.start}..${block.end} \u2014 ${block.summary.slice(0, 80)}`);
   }