| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| |
|
|
|
|
| |
Having LLM model per-agent is even more flexible than per-flow.
We can have some more complex tasks during patch generation with the most elaborate model,
but also some simpler ones with less elaborate models.
|
| |
|
|
|
| |
We may want to use a weaker model for some workflows.
Allow to use different models for different workflows.
|
| |
|
|
|
| |
Add race:harmful/benign label.
Set it automatically by confirmed AI jobs.
|
| |
|
|
|
|
| |
Lay down foundation for spanner DB migrations by adding Jobs.Correct field.
This will allow us to test deployment of such changes.
The field will be used to record results of manual assessment of AI job results.
|
| |
|
|
|
|
| |
Add workflow that can be used for moderation of UAF bugs (consistent/actionable reports),
such UAF bugs can be upstreammed automatically, even if they happened only once
and don't have a reproducer.
|
| |
|
|
|
|
|
|
| |
Support for:
- polling for AI jobs
- handling completion of AI jobs
- submitting job trajectory logs
- basic visualization for AI jobs
|
|
|
Start spanner emulator for tests.
Create isolated per-test instance+database.
Test that DDL migration scripts are work.
|
