d159a1507e
- There seems to be a root model bug where the model will preemptively bail on conversations without trying harder. Typically the stops are VERY obvious and bug-looking where you need to prmopt the model to "continue". - This PR attempts to fix the above by running a 2.0-flash request (don't need somethign more powerful) at the end of every full interaction to see who should speak (user or model). - Add tests for nextSpeakerChecker Fixes https://b.corp.google.com/issues/416826051 |
||
|---|---|---|
| .. | ||
| src | ||
| README.md | ||
| index.ts | ||
| package.json | ||
| tsconfig.json | ||
README.md
Nested package template. Either fill this out with "backend" functionality or create similar packages that you want built separate from the CLI.
To use this package from another dependent package in this monorepo:
- add
"@gemini-code/server"to the dependent package'spackage.json - import in a dependenant by calling
import { } from "@gemini-code/server"