conversation-folders-package
Run the following command in DeepSeek Harness:
dsh plugin install choocoo/conversation-folders-package
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install choocoo/conversation-folders-package in your terminal to automatically install the plugin (source: https://github.com/choocoo/conversation-folders-package) into the web profile; it attaches to the sidebar after restarting DSH.
About this plugin
For a long time the DSH sidebar offered only a flat Project → Conversations structure, making it easy to lose track of sessions once the list grew. conversation-folders-package adds a Project → Folder → Conversation hierarchy so you can create, rename, and delete folders to organize conversations by topic, phase, or whatever grouping makes sense to you, then move sessions in and out of those groups at will.
Beyond grouping, the plugin ships a content search box at the top of the sidebar that matches against message text, and an archive action that hides finished or temporary sessions from view while keeping their logs on disk under ~/.dsh/storages/convfolders.json. Recovery of archived items can be handled through community archive-management plugins.
As the only DSH plugin that provides manual, project-level two-tier folder grouping, it complements cross-project session movers like dsh-session-move and the two can coexist. It is well suited for power users who accumulate many conversations, prefer organizing them by hand, and want a lightweight, build-free installation.
Use Cases
- Grouping large volumes of conversations by phase or topic
- Quickly locating a conversation that contains a specific message
- Hiding temporary or completed sessions to keep the sidebar tidy
Best For
- Developers with many conversations who need manual topic-based organization
- Users who prefer a lightweight, local-only solution without heavy build chains
- Power users who pair it with cross-project session movers
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.