keplergl / kepler.gl / 20488704248

62%

push

github

fix(ai-assistant): clear LLM history on restart chat (#3262)

* Fix AI Assistant restart to prevent token waste

When clicking 'Restart Chat', the LLM provider was still receiving the
entire conversation history in API calls, wasting tokens and increasing
costs.

Root cause: @openassistant library uses singleton instances that persist
across React component remounts, maintaining internal messageHistory.

Solution:
- Extract restartChat function from useAssistant hook
- Call it to clear library's internal singleton message cache
- Force React component remount using key prop
- Clear Redux message state

This eliminates token waste and reduces API costs for all users.

Signed-off-by: Akash Rai <akashtooop@gmail.com>

* fix: remove unnecessary useEffect for ref assignment

Apply code review feedback - direct ref assignment is preferred
over useEffect for updating refs in component body.

Signed-off-by: Akash Rai <akashtooop@gmail.com>

---------

Signed-off-by: Akash Rai <akashtooop@gmail.com>

6353 of 12237 branches covered (51.92%)

Branch coverage included in aggregate %.

13047 of 19235 relevant lines covered (67.83%)

81.68 hits per line