TellToday/dsh-narrative-voice ↗★ 1
@dsh-user/narrative-voice
A DSH (DeepSeek Harness) bundle plugin that rewrites the ask_user_question tool description at prompt-assembly time with a fixed narrative-voice rule (default: the answerer narrates), toggled live via the /voice command. 适合想调整提问叙述方式的用户，命令即时生效，装后需重启进程
インストール
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:TellToday/dsh-narrative-voiceドキュメント
README 全文を読む ↗Usage
| Command | Effect |
|---|---|
/voice on | enable the rewrite (effective from the next message) |
/voice off | disable it (the tool description is restored) |
/voice user | switch to Scheme B (the answerer narrates) and enable |
/voice ai | switch to Scheme A (the AI narrates) and enable |
/voice | show the current state (on/off + the active scheme) |
The command is handled by the host's commands service (not by the model), so
it takes effect instantly — no HMR dependency, no restart.
Default configuration
| Key | Default | Meaning |
|---|---|---|
voice | user (Scheme B) | which narrative scheme to use |
defaultActive | true | enabled right after install |
To change the defaults (instead of switching at runtime with /voice), override
the row by id in the profile's patch file
$DSH_HOME/profiles/ /cordis.patch.yml. The patch replaces the whole
config, so list every key:
- id: narrative-voice
config:
voice: user # user (Scheme B: the answerer narrates) | ai (Scheme A: the AI narrates)
defaultActive: true # false = disabled by default, until /voice on
The config is validated by Config (a dependency-free Standard Schema
implementation): an invalid value fails the plugin load with a clear error.