Conversation tags feature
Nobody has claimed this yet.
- Dominant language
- Rust
- Stars
- 16
- Forks
- 3
- Avg merge
- 1d 1h
- Merged PRs (30d)
- 121
Description
We should introduce the concept of "tags" attached to conversations.
These tags will serve multiple purposes in the future (for which separate tracking issues will be created).
- tag-based conversation searching
- tag-based conversation management
- tag-based long-term memory system
- tag-based automation (add context X for any conversation with tag A, etc)
- tag-based agentic workflows (force MCP-based test runs for any workflow with tag X)
- etc...
To start, I think we should do two things, very similar to the existing conversation titles system:
- Add
tagstoConversation - I think we'll want key/value based tags, but support keyless tags by setting the key to an empty string.
- Show list of tags in
jp conversation showandjp conversation ls - Allow adding tags through
jp conversation edit - Auto-add tags to conversations using an LLM call (can be turned off) through our task-system already implemented in #18.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the existing conversation titles system and the Conversation model, then trace the entry points for jp conversation show, jp conversation ls, and jp conversation edit. Review the task-system implementation from issue #18 for automatic tagging. Done means tags are stored, displayed, editable, and optionally added through the LLM task flow.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- rust
- Domain
- ai, cli
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100