billion-context-dsh 0.2.22 → 0.2.23

package/README.en.md

@@ -3,7 +3,7 @@
 [English](./README.en.md) | [中文](./README.md)
 
 > **⚠️ Beta notice — not for production use**
-> This project (**v0.2.22**) 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 (**v0.2.23**) 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 ⭐:
@@ -100,7 +100,7 @@ This only installs the package into your project/global store; it does **not** t
 **Install from the git source (`github:` spec — the form the plugin store shows).** The prebuilt `dist/` artifacts are committed to this repository, so a git-source install also works out of the box — **no build step needed**, and pnpm 11's default build-script blocking (`allowBuilds`) never applies to this package:
 
 ```bash
-dsh plugin --profile web add github:Tyan66666/billion-context-dsh#v0.2.22
+dsh plugin --profile web add github:Tyan66666/billion-context-dsh#v0.2.23
 ```
 
 Prefer a `#<tag>` ref to get artifacts identical to that npm release; without a ref you get the latest default-branch build. Only building the repo yourself (`npm run build`) requires approving build scripts. Background and trade-offs: [docs/git-source-install-design.md](docs/git-source-install-design.md) (issue #92).

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（**v0.2.22**）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（**v0.2.23**）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>
@@ -99,7 +99,7 @@ npm install billion-context-dsh
 **git 源安装（`github:` 规格，插件商店展示的形态）。** 预构建产物 `dist/` 已提交到仓库，从 git 源安装同样开箱即用——**无需任何构建步骤**，pnpm 11 默认拦截构建脚本（`allowBuilds`）的机制对这个包不构成障碍：
 
 ```bash
-dsh plugin --profile web add github:Tyan66666/billion-context-dsh#v0.2.22
+dsh plugin --profile web add github:Tyan66666/billion-context-dsh#v0.2.23
 ```
 
 建议带 `#<tag>` 安装，拿到与对应 npm 版本完全一致的产物；不带 ref 则装默认分支的最新构建。只有 clone 仓库自行从源码构建（`npm run build`）才需要放行构建。背景与方案取舍见 [docs/git-source-install-design.md](docs/git-source-install-design.md)（issue #92）。

package/dist/index.js

@@ -3404,7 +3404,7 @@ function sessionEventsOf(session) {
 function eventAtOf(session, seq) {
   const eventAt = session.eventAt;
   if (typeof eventAt === "function") return eventAt.call(session, seq);
-  return session.events[seq];
+  return sessionEventsOf(session)?.[seq];
 }
 
 // src/messages.ts
@@ -4720,7 +4720,7 @@ var DEFAULT_PROMPTS = {
     header: "Surface: {surface}",
     title: "Compressible ranges ({count}, oldest first; exact surface seqs \u2014 usable as-is):",
     line: "  - seq {start}..{end} \u2014 {count} messages, ~{tokens} tokens [tool {toolPct}% | text {textPct}%]{media}",
-    footer: "Compress with: compress({ content: [{ startSeq, endSeq, summary }] }) \u2014 content is an array: batch multiple unrelated segments in one call, each entry its own block. Keep ranges disjoint.\nSnapshot taken at nudge time: the seqs go stale once the surface moves (a later compress shadows them), so re-run acp_status for fresh refs before compressing."
+    footer: "Compress with: compress({ content: [{ startSeq, endSeq, summary }] }) \u2014 content is an array: batch multiple unrelated segments in one call, each entry its own block. Keep ranges disjoint.\nSnapshot taken at nudge time: the seqs go stale once the surface moves (a later compress shadows them), so re-run acp_status for fresh refs before compressing.\nBefore you compress any row above, confirm it is truly consumed \u2014 if a span still holds live task state (where you are in the task / open TODOs, paths already ruled out, artifacts already done and where they live), carry that state into your summary or keep the span live. Compressing an in-progress span without carrying its state forces a full re-run afterward."
   },
   tools: {
     compress: 'Replace older conversation ranges with dense summaries you write. Each message seq is a surface reference. Single range: compress({ content: [{ startSeq, endSeq, summary }] }). Batch multiple unrelated ranges in one call (each content entry becomes its own block); keep ranges disjoint. Never compress content the current step is actively using. Compress boundaries are SURFACE SEQS (acp_status Surface: row, latest nudge table) \u2014 NOT the block refs (bN, e.g. b1) that acp_status COMPRESSED BLOCKS shows, which are for decompress only. Drilldown mN refs (e.g. m00306) are ALSO accepted as startSeq/endSeq \u2014 they are auto-mapped to the live surface seq; an unknown mN (never assigned on the current surface) fails with guidance. Seq refs must come from the CURRENT surface (acp_status or the latest nudge): a span whose edges were shadowed by an earlier compress is auto-remapped to its still-live content, a fully compressed span is reported as already compressed, and invented/other-session seqs fail with guidance. Good compression moments: stage or subtask completion whose details you have fully consumed and will not re-check, strategy switches, intermediate milestones, and wrapping up failed exploration \u2014 when the details are consumed and no longer critical for the task ahead. Before compressing, ask: will I need to re-verify any detail from this range in this task? If yes, keep it live. When you write a summary, turn dead-end exploration into a conclusion (what was tried, why it failed, the next step) \u2014 not a blow-by-blow; and keep the summary the ONLY record: self-contained, so a later reader (or you, after decompress) can continue without the original. Optional verifiedReadings: string[] per content entry records acceptance readings that are already green (e.g. "t0-fastpath 8/8") \u2014 stored structurally on the compaction event so later steps need not re-run them.',
@@ -4763,7 +4763,7 @@ Tiered compression: each compressed block appears on the surface as one summary
 
 {tier3CondenseRules}
 
-When you write a summary, it becomes the ONLY record of that range: keep file paths, signatures, exact values, decisions, and error strings verbatim so a later reader (or you, after decompress) can continue without the original. Never reuse historical seqs \u2014 the surface moves as messages land and compress; verify with acp_status.`
+When you write a summary, it becomes the ONLY record of that range: keep file paths, signatures, exact values, decisions, and error strings verbatim so a later reader (or you, after decompress) can continue without the original. A mid-task compression must also hand off STATE, not just facts: where you are in the task and what remains (open TODOs), which approaches you already ruled out (dead ends), and which intermediate artifacts are already done and where they live \u2014 so the next step continues instead of re-running work you already did. Never reuse historical seqs \u2014 the surface moves as messages land and compress; verify with acp_status.`
 };
 var DEFAULT_RESOLVED = DEFAULT_PROMPTS;
 
@@ -4938,7 +4938,7 @@ function replaceTierTrigger(text, nudge, session, prompts) {
   const next = rest.match(/\n\nHOW TO COMPRESS/);
   const end = next !== null ? start + 2 + next.index : text.length;
   const targets = nudge.tierTargetBlocks;
-  const summarySeqs = targets.map((block) => summarySeqOfKernelBlock(session, block.blockId)).filter((seq) => seq !== null).sort((a, b) => a - b);
+  const summarySeqs = targets.map((block) => summarySeqOfKernelBlock(session, block.blockId)).filter((seq) => seq != null).sort((a, b) => a - b);
   const pending = nudge.tier === 2 ? nudge.breakdown?.pendingT2 : nudge.breakdown?.pendingT3;
   const tokens = typeof pending === "number" ? pending : 0;
   const tierValue = nudge.tier === null ? 2 : nudge.tier;
@@ -4986,7 +4986,7 @@ function renderNudgeFromTemplates(nudge, emergency, session, kernelView, prompts
   if (prompts.nudge.guidance !== "") parts.push("", prompts.nudge.guidance);
   if ((nudge.tier === 2 || nudge.tier === 3) && (nudge.tierTargetBlocks?.length ?? 0) > 0) {
     const targets = nudge.tierTargetBlocks;
-    const summarySeqs = targets.map((block) => summarySeqOfKernelBlock(session, block.blockId)).filter((seq) => seq !== null).sort((a, b) => a - b);
+    const summarySeqs = targets.map((block) => summarySeqOfKernelBlock(session, block.blockId)).filter((seq) => seq != null).sort((a, b) => a - b);
     const pending = nudge.tier === 2 ? nudge.breakdown?.pendingT2 : nudge.breakdown?.pendingT3;
     const tokens = typeof pending === "number" ? pending : 0;
     const tierLine = renderTemplate(prompts.nudge.tier, {