billion-context-dsh 0.1.8 → 0.1.9

package/README.en.md

@@ -3,7 +3,7 @@
 [English](./README.en.md) | [中文](./README.md)
 
 > **⚠️ Beta notice — not for production use**
-> This project (**v0.1.8**) 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 (**v0.1.9**) 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 ⭐:
@@ -76,6 +76,20 @@ That's it. Then add a composition row where a compaction backend is expected —
         modelContextLimit: 128000   # optional; omit to auto-detect the model's real window (fallback 128000)
 ```
 
+**(Optional) Custom prompt copy — `config.prompts`.** Every model-visible prompt (normal/emergency nudge opener, tier line, range table, the ACP system-prompt section, the four tool descriptions) ships with built-in copy that you can override per slot through the composition row's `config`. Templates support named placeholders (e.g. `{pct}` for nudges, `{surface}` for the range table) and are **validated at construction**: a misspelled placeholder fails engine startup (fail-fast) instead of leaking a literal `{pct}` into the model context:
+
+```yaml
+      config:
+        modelContextLimit: 128000
+        prompts:
+          nudge:
+            normal: 'Context usage is at {pct}%. This is a suggestion, not a requirement — you decide.'  # custom nudge opener
+          tools:
+            acpStatus: 'Report the ACP block ledger: compressed blocks, reclaimed tokens, and current context pressure.'  # custom tool description
+```
+
+See [docs/configurable-prompts-design.md](docs/configurable-prompts-design.md) for the full slot list, per-slot placeholders, and the empty-string/`null` semantics. Deployments that omit `prompts` behave exactly as before (default copy byte-identical).
+
 **Per-mode — an agent preset's `compaction` realm.** First *disable (or delete) the realm's existing `dsh-compaction-basic` row*, then mount this engine — two backends cannot coexist in the same realm:
 
 ```yaml
@@ -151,6 +165,7 @@ This project reuses `acp-kernel`'s compression core and `billion-context-pi`'s d
 | `autoTools` | `true` | Register the four model tools on `ctx.tools` |
 | `autoCommand` | `true` | Register the `/acp` command on `ctx.commands` |
 | `autoNudge` | `true` | Inject the nudge into `agent/pre-step` |
+| `prompts` | — | (optional) Custom prompt copy: per-slot overrides for nudge / range table / system prompt / tool descriptions (template + named placeholders, validated at construction; see “Custom prompt copy” above and [docs/configurable-prompts-design.md](docs/configurable-prompts-design.md)) |
 
 ## Development
 

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（**v0.1.8**）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（**v0.1.9**）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>
@@ -78,6 +78,20 @@ npm install billion-context-dsh
         modelContextLimit: 128000   # 可选；省略时自动探测模型真实窗口（回退 128000）
 ```
 
+**（可选）自定义提示词文案 —— `config.prompts`。** 所有模型可见的提示词（普通/紧急 nudge 首句、tier 蒸馏行、范围表、ACP system prompt 段、四个工具描述）默认是内置文案，可通过组合行的 `config` 按槽位覆盖。模板支持命名占位符（如 nudge 的 `{pct}`、范围表的 `{surface}`），**构造期校验**：占位符拼写错误会在引擎启动时抛错（fail-fast），而不是把字面 `{pct}` 漏进模型上下文：
+
+```yaml
+      config:
+        modelContextLimit: 128000
+        prompts:
+          nudge:
+            normal: '上下文使用率 {pct}%。这是建议而非命令——由你决定是否压缩。'  # 中文 nudge 首句
+          tools:
+            acpStatus: '报告 ACP 块账本：压缩块数、回收 token、当前上下文压力。'  # 自定义工具描述
+```
+
+可配置槽位清单、每槽可用占位符、空串/`null` 语义见 [docs/configurable-prompts-design.md](docs/configurable-prompts-design.md)。未配置 `prompts` 的部署行为与以往完全一致（默认文案逐字节不变）。
+
 **单模式生效（agent preset 的 `compaction` realm）**。先在该 realm 内*禁用（或删除）原有的 `dsh-compaction-basic` 行*，再插入本引擎——同一 realm 内两个后端不能并存：
 
 ```yaml
@@ -153,6 +167,7 @@ DSH 的每个模型请求都派生自其 append-only 会话日志（*surface*）
 | `autoTools` | `true` | 在 `ctx.tools` 注册四个模型工具 |
 | `autoCommand` | `true` | 在 `ctx.commands` 注册 `/acp` 命令 |
 | `autoNudge` | `true` | 当内核建议时向 `agent/pre-step` 注入 nudge |
+| `prompts` | — | （可选）自定义提示词文案：nudge / 范围表 / system prompt / 工具描述按槽位覆盖（模板 + 命名占位符，构造期校验；见上文「自定义提示词文案」与 [docs/configurable-prompts-design.md](docs/configurable-prompts-design.md)） |
 
 ## 开发
 

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "billion-context-dsh",
-	"version": "0.1.8",
+	"version": "0.1.9",
 	"description": "Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.",
 	"type": "module",
 	"main": "dist/index.js",
@@ -28,7 +28,7 @@
 		"test": "node --import tsx --test tests/*.test.ts"
 	},
 	"dependencies": {
-		"acp-kernel": "0.0.23"
+		"acp-kernel": "0.0.24"
 	},
 	"peerDependencies": {
 		"@deepseek-ai/cordis": "^4.0.1",