Optimise planner and workflow agent caching
Open
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 5
- Forks
- 10
- Avg merge
- 2d 20h
- Merged PRs (30d)
- 17
Description
Caching is not fully optimised in the planner and workflow agents. By optimising prompt ordering and cache breakpoints, we could speed up and lower the costs of the global assistant. Any inefficiency in the workflow agent will become more urgent to fix with the launch of the global assistant.
Implement caching properly and measure Time to First Token and estimate token cost before & after.
Contributor guide
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 locating the planner and workflow agent caching and establish baseline Time to First Token and estimated token cost. Optimize prompt ordering and cache breakpoints, then record before-and-after measurements showing improved caching, latency, or cost.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook
- Domain
- ai, performance
- Issue type
- Refactor
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 40/100