dsh-kaomoji 0.1.1 → 0.1.3

package/CHANGELOG.md

@@ -7,6 +7,21 @@ and this project adheres to [Semantic Versioning](https://semver.org/lang/zh-CN/
 
 ## [Unreleased]
 
+## [0.1.3] - 2026-09-13
+
+### Fixed
+
+- `maxPerTurn` 之前对输出没有实际约束力：提示词写死「一个」，调到 2/3 也不会变。
+  现在 `frequent` 会按该上限在回复里分散放置多个颜文字，`auto` 在存在多个
+  情绪点时也会用到上限；回复很短时自动少放。
+
+## [0.1.2] - 2026-09-10
+
+### Changed
+
+- `auto` 模式的适用范围明确包含日常推荐、购物建议和实用 how-to 回答：这类
+  对话式回答同样会带一个颜文字，只有纯代码、正式技术交付和高风险内容跳过。
+
 ## [0.1.1] - 2026-09-10
 
 ### Added

package/README.en.md

@@ -26,7 +26,7 @@ largest Japanese kaomoji sites.
   instead of inventing malformed faces.
 - **12 mood buckets** — happy, love, sad, cry, angry, surprised, confused,
   shy, playful, encourage, thanks, sorry.
-- **Three frequency modes** — `auto` (default; friendly/casual/empathetic replies get one), `frequent`, `off`.
+- **Three frequency modes** — `auto` (default; greetings, casual chat, recommendations and empathetic replies get one), `frequent`, `off`.
 - **Placement control** — `inline` after the mood-matching sentence (default)
   or `end` of the reply.
 - **Visual settings card** under Settings → General, saved live without a restart.
@@ -102,9 +102,9 @@ Example `cordis.patch.yml`:
 
 | Key | Type | Default | Description |
 | --- | --- | --- | --- |
-| `mode` | `'off' \| 'auto' \| 'frequent'` | `'auto'` | `off` disables; `auto` adds one to friendly/casual/empathetic replies; `frequent` adds one to every conversational reply (code-only/formal replies excluded) |
+| `mode` | `'off' \| 'auto' \| 'frequent'` | `'auto'` | `off` disables; `auto` adds one to greetings, casual chat, recommendations and empathetic replies; `frequent` adds one to every conversational reply (code-only/formal replies excluded) |
 | `placement` | `'inline' \| 'end'` | `'inline'` | Put the kaomoji after the best-matching sentence, or at the reply end |
-| `maxPerTurn` | `number` (1–5) | `1` | Max kaomoji per reply |
+| `maxPerTurn` | `number` (1–5) | `1` | Max kaomoji per reply; `frequent` distributes that many across different sentences (fewer in very short replies) |
 | `customPrompt` | `string` | `''` | Extra style/scene guidance; cannot change mode, whitelist or limits |
 | `settingsFile` | `string` | `~/.dsh/dsh-kaomoji.json` | (advanced) user-settings file path |
 | `settingsAuthority` | `'trusted-host' \| 'loopback'` | `'trusted-host'` | Settings RPC trust scope: by default the local Host plus declared trusted hosts (Tailscale/LAN) may write; set `loopback` to restrict to the local machine |

package/README.md

@@ -17,7 +17,7 @@
 - **纯提示词方案**：不截断、不改写模型流，也不额外调用模型，稳定且对 KV 缓存友好。
 - **白名单防乱码**：模型只会从词库中逐字符复制颜文字，不会凭印象拼出坏字符。
 - **情绪分桶**：内置 12 个情绪分类（开心 / 心动 / 难过 / 大哭 / 生气 / 惊讶 / 困惑 / 害羞 / 俏皮 / 鼓励 / 感谢 / 道歉），并随规则给出可用样例。
-- **三种频率模式**：`auto`（智能：友好的寒暄/闲聊/共情回复都会带一个，默认）/ `frequent`（每条对话回复都带）/ `off`（关闭）。
+- **三种频率模式**：`auto`（智能：寒暄/闲聊/推荐建议/共情回复都会带一个，默认）/ `frequent`（每条对话回复都带）/ `off`（关闭）。
 - **放置位置可选**：贴在情绪最贴切的句子后（`inline`，默认）或固定在回复末尾（`end`）。
 - **可视化配置卡片**：卡片位于「设置 → 通用设置」，保存即生效、无需重启。
 - **零第三方运行时依赖**：只用 dsh 自带的 `systemPrompt` 服务与 Node 标准库。
@@ -118,9 +118,9 @@ pnpm add file:C:\path\to\dsh-kaomoji
 
 | 配置项 | 类型 | 默认值 | 说明 |
 | --- | --- | --- | --- |
-| `mode` | `'off' \| 'auto' \| 'frequent'` | `'auto'` | `off` 关闭；`auto` 友好的寒暄/闲聊/共情回复都会带一个；`frequent` 每条对话回复都带一个（两者都跳过纯代码 / 正式技术交付） |
+| `mode` | `'off' \| 'auto' \| 'frequent'` | `'auto'` | `off` 关闭；`auto` 寒暄/闲聊/推荐建议/共情回复都会带一个；`frequent` 每条对话回复都带一个（两者都跳过纯代码 / 正式技术交付） |
 | `placement` | `'inline' \| 'end'` | `'inline'` | 放在情绪最贴切的句子/短段后，或固定在回复末尾 |
-| `maxPerTurn` | `number`（1–5） | `1` | 每条回复最多允许的颜文字数量 |
+| `maxPerTurn` | `number`（1–5） | `1` | 每条回复的颜文字数量上限；`frequent` 会按这个数量分散放在不同句子后，回复太短时自动减少 |
 | `customPrompt` | `string` | `''` | 附加风格/场景说明；不能改变模式、白名单或数量上限 |
 | `settingsFile` | `string` | `~/.dsh/dsh-kaomoji.json` | （进阶）用户设置持久化文件路径 |
 | `settingsAuthority` | `'trusted-host' \| 'loopback'` | `'trusted-host'` | 设置 RPC 信任范围：默认允许本机与 Host 声明的受信主机（Tailscale/局域网）保存设置；改成 `loopback` 则仅本机可改 |

package/lib/client.js

@@ -56,7 +56,7 @@ window.__ModuleLoader__.load({
       "mode.off": "关闭",
       "mode.off.desc": "不使用颜文字",
       "mode.auto": "智能",
-      "mode.auto.desc": "友好的寒暄、闲聊、共情回复都会带一个",
+      "mode.auto.desc": "寒暄、闲聊、推荐建议、共情回复都会带一个",
       "mode.frequent": "高频",
       "mode.frequent.desc": "每条对话回复都带一个（纯代码/正式交付除外）",
       "field.placement": "放置位置",
@@ -81,7 +81,7 @@ window.__ModuleLoader__.load({
       "mode.off": "Off",
       "mode.off.desc": "No kaomoji",
       "mode.auto": "Smart",
-      "mode.auto.desc": "Friendly greetings, casual chat and empathetic replies get one",
+      "mode.auto.desc": "Greetings, casual chat, recommendations and empathetic replies get one",
       "mode.frequent": "Frequent",
       "mode.frequent.desc": "One kaomoji in every conversational reply (code-only/formal excluded)",
       "field.placement": "Placement",

package/lib/index.js

@@ -144,20 +144,32 @@ export function buildGuidance(config) {
   const settings = normalizeConfig(config);
   if (settings.mode === "off") return "";
 
+  const cap = settings.maxPerTurn;
   const modeLines = {
     auto: [
-      "Most friendly, casual, empathetic, or playful replies should include one fitting kaomoji.",
+      "Most conversational replies should include a fitting kaomoji — greetings, casual chat, empathy, everyday recommendations or shopping advice, and practical how-to answers.",
+      cap === 1
+        ? "Use one kaomoji in those replies."
+        : `Use one kaomoji when the mood fits, and up to ${String(cap)} when the reply has several distinct emotional beats.`,
       "Skip it only when the reply is purely code, a formal/technical deliverable, or serious/high-stakes content.",
-      "One per reply is usually enough; never replace real content with it.",
     ],
     frequent: [
-      "In every conversational reply — except code-only output, formal/technical deliverables, or tool calls — include one fitting kaomoji.",
+      "In every conversational reply — except code-only output, formal/technical deliverables, or tool calls — include fitting kaomoji.",
+      cap === 1
+        ? "Use exactly one kaomoji."
+        : `Use ${String(cap)} kaomoji, one after each of ${String(cap)} different emotion-carrying sentences; use fewer only when the reply is very short.`,
     ],
   };
-  const placementLine =
-    settings.placement === "end"
+  const placementLine = settings.placement === "end"
+    ? cap === 1
       ? "Put the kaomoji at the very end of the reply (same line after a space, or on its own line)."
-      : "Put it right after the sentence or short paragraph whose mood it matches best.";
+      : "Put each kaomoji at the end of a different paragraph (after the sentence it matches), not all on the final line."
+    : cap === 1
+      ? "Put it right after the sentence or short paragraph whose mood it matches best."
+      : "Put each kaomoji right after a different sentence or short paragraph whose mood it matches best.";
+  const spreadLine = cap > 1
+    ? "Distribute the kaomoji across the reply; never put two in the same sentence, and do not stack them all at the very end."
+    : "Never replace real content with a kaomoji.";
 
   const poolLines = CATALOG.map(
     (group) => `${group.label}: ${group.examples.join(" | ")}`,
@@ -168,7 +180,8 @@ export function buildGuidance(config) {
     "[dsh-kaomoji] Kaomoji guidance for this reply:",
     ...modeLines[settings.mode],
     placementLine,
-    `Use at most ${String(settings.maxPerTurn)} kaomoji per reply.`,
+    spreadLine,
+    `Never exceed ${String(cap)} kaomoji in one reply.`,
     "Never place a kaomoji inside code blocks, inline code, links, tables, or tool output.",
     "Use only the literal kaomoji listed below, copied character-for-character; do not invent, mutate, or re-combine them.",
     ...poolLines,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-kaomoji",
-  "version": "0.1.1",
+  "version": "0.1.3",
   "description": "Add mood-aware Japanese kaomoji to DeepSeek Harness (dsh) replies; prompt-injection plugin with a curated library from kaomojiya.org.",
   "type": "module",
   "main": "lib/index.js",