AI Agent Hub
Back to plugins
🧠

dsh-worklog

Memory Updated 2026.09.10

Run the following command in DeepSeek Harness:

dsh plugin install aijunjiang/dsh-worklog

Paste the following prompt into your AI chat to install this plugin:

Run dsh plugin install aijunjiang/dsh-worklog in your terminal to install the plugin; the full source code is hosted at https://github.com/aijunjiang/dsh-worklog.

About this plugin

Working in DSH day to day, your conversations scatter across workspaces, SSH routes, and long-closed sessions. When it is time to review what you actually did over the past week or month, there is no single place to look. dsh-worklog pulls every session together and slices them into per-turn dialogue nodes, generating a concise summary for each, then lays them out on a calendar that shows daily session count and duration at a glance.

Summaries rely on a fingerprint cache with incremental recomputation: unchanged nodes are reused as-is, and only newly active ones are re-summarized, so you are not burning tokens on repeated work. On the reporting side, pick a single day or a date range on the calendar, select the entries you care about, and generate a daily, weekly, monthly, or semi-annual report as copy-ready Markdown. A conversation that spans multiple days stays aggregated as one project. The summarization model is independently configurable, supporting the built-in DSH backend, any OpenAI-compatible API, or the Anthropic API, with a fully customizable prompt and an on-demand force-rescan button.

If you juggle multiple threads in DSH each day, work across environments, code, research, or write, and need to produce a progress update for your team or a personal retrospective on a regular cadence, dsh-worklog turns the manual scroll-through-chats chore into a one-click action.

Use Cases

  • Compiling a well-structured weekly progress report for your team every Friday
  • Reviewing task volume and session duration at month-end or half-year milestones
  • Consolidating work across multiple SSH workspaces into a single retrospective view

Best For

  • Individual developers juggling parallel coding or research threads in DSH daily
  • Team engineering leads who must deliver weekly, monthly, or semi-annual summaries on a fixed cadence
  • Remote collaborators whose sessions spread across workspaces and SSH routes, making manual progress tracking impractical