dsh-worklog
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
Related Plugins
Memory layer for coding agents that indexes local session history and auto-recalls relevant context before edits, commands, and failures, with no manual search needed.
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.