dsh-personal-center

dsh-personal-center A local, offline personal center for DeepSeek Harness — usage stats, cost estimation, custom instructions, global font size, and a desktop pet.

A local plugin for DeepSeek Harness (DSH) desktop / web. Adds a Personal Center section to Settings, with three tabs: Token Usage — real usage stats: today / cumulative tokens, session count, tool calls, a GitHub-style activity heatmap (daily / weekly / cumulative), per-provider breakdown (with per-model detail), top tools, and session review; with sub-tabs (Overview / Review / Model Cost). Personalization — global custom instructions (like ChatGPT / Codex "Personalization → Custom instructions"), applied to all chats on this machine. Desktop Pet — bitmap (black / blue whale) and vector ("round black / round blue") skins, driven by your real usage (5 emotions), with a session-status overview (double-click a session to jump into it).

Model cost estimation lives inside Token Usage: per-model pricing (peak / off-peak, per currency, official presets) plus cache-hit-rate stats.

100% local — no network, no reading chat content. See PRIVACY.md. Bilingual UI (中文 / English), follows DSH's language automatically. 📸 Screenshots Four tabs (v1.0) Feature details Five emotion animations (happy / busy / tired / wallet-pain / dozing): New actions (v0.8.0) (thinking / waiting / celebrate / drag / wave): ✨ Features Token Usage (statistics) Today overview: token consumption / sessions / tool calls; Cumulative data: total tokens / longest chat / total sessions / cache-hit rate / estimated cost; Token activity: GitHub-contribution-style heatmap with daily / weekly / cumulative views; Per-provider breakdown: grouped by provider with subtotals plus per-model detail (tokens, requests, cache-hit rate, cost) — multiple providers and models tracked separately; Top tools: sorted by call count (including MCP tools in mcp form); Session review: recent sessions (title / date / duration / tokens / cache-hit rate), auto-excludes archived sessions.

Data source: aggregates local session logs (session.v4 / session.v3 / legacy) in real time — numbers only, never reads content. See docs/common/DESIGN.md. Model Cost (estimation) Per-model cost per million tokens, split by currency (¥/$); Peak / off-peak pricing (DeepSeek official: Beijing 9:00–12:00 & 14:00–18:00 peak, off-peak = half); Built-in presets (deepseek / kimi / gemini / gpt) with provider→model autocomplete, editable; Shows this week / this month / cumulative cost. Personalization (layered instructions: v0.7) Global instructions (identity baseline): identity / working principles / response preferences, applied to every chat on this machine; Per-workspace instructions (project-specific): each workspace gets its own instructions, injected by longest-prefix cwd match as "global + workspace" merged text; unconfigured workspaces fall back to global only; Template library: 5 built-in templates (PM / developer / writing / translator / general assistant), one-click apply to global or current workspace; save / edit / delete your own; Injection preview: live "global + current workspace" merged text + ≈token estimate at the bottom; All local (settings.yaml)