← Back to list

whale-persona

Persona engine for DeepSeek Harness: one config.json drives the AI's self-name (per model, per tier), how it addresses you, relationship stance, character text, per-item work contracts with individual toggles, thinking-chain language, appearance and reply tone (both opt-in and per-model overridable), and long-term memory gated by human confirmation - the AI can only append proposed candidates, a human confirm line flips them into effect, and the log is physically append-only and replayable. Confirmed entries are injected as a quoted data-not-instructions block; entries tagged with a kind can instead be routed to arbitrary files on confirmation and never reach the prompt. Three prompt sections re-evaluate from disk on every assembly, so edits apply on the next step with no restart. Persona presets are shareable JSON snapshots (imports and exports SillyTavern character cards, v2/v3 read, v2 written) and deliberately never carry memory. Zero runtime dependencies, no network, no shell; any error degrades to an empty section rather than a broken session. Ships blank - installing changes nothing until you write something.

人设引擎（DeepSeek Harness）：一份 config.json 管住 AI 的自称（可按具体模型指定，未命中回落 flash / pro 两档）、对你的称呼、关系立场、性格正文、逐条可勾选的工作契约、思维链语言、形象与回复语气（两段均 opt-in、均可按模型覆盖），以及由人工确认闸门把关的长期记忆——AI 只能追加 status:"proposed" 候选，人执行一行 confirm 才转正，日志物理只追加、按行序重放。已确认条目以「数据而非指令」的引号块注入；带 kind 的条目改为在确认那一刻按路由追加进指定文件、永不进提示词。三段提示词每次装配都从磁盘重新求值，改配置下一步生效、不用重启。人设预设是可分享的 JSON 快照（导入导出酒馆角色卡：v2/v3 可读、v2 可写），且刻意不携带记忆。零运行时依赖、不联网、不执行命令；任何异常降级为空段，最坏是「没有人设」而不是会话起不来。出厂空白——不写配置就什么都不改变。