Prompt for thinking after `call_measure()` and `run_sql()`
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 44
- Forks
- 1
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 142
Description
Along with outputs to call measure and run SQL, we should put invisible prompting that asks the agent to think for a bit and consider ways in which the intended output may misrepresent the reality, then make sure those are reflected in the agent's response to the user somehow.
It's a bit tricky to figure out from a given ellmer Chat object whether thinking is enabled or not, but I think we can get the 95% case pretty easily. If it's not enabled, we can ask the agent to jot notes inside of an XML tag that will be hidden from the user.
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 locating the call_measure() and run_sql() entry points and inspect how their outputs are passed to the agent. Check how an ellmer Chat object indicates whether thinking is enabled, then define the hidden prompting behavior for the remaining case. Done means both tool outputs encourage reflection and the relevant considerations reach the user-facing response.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, sql
- Domain
- ai, data
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100