diff options
| author | Dmitry Vyukov <dvyukov@google.com> | 2026-01-15 20:53:57 +0100 |
|---|---|---|
| committer | Dmitry Vyukov <dvyukov@google.com> | 2026-01-20 21:12:57 +0000 |
| commit | 7f5908e77ae0e7fef4b7901341b8c2c4bbb74b28 (patch) | |
| tree | 2ccbc85132a170d046837de6bdd8be3317f94060 /dashboard/dashapi | |
| parent | 2494e18d5ced59fc7f0522749041e499d3082a9e (diff) | |
pkg/aflow: make LLM model per-agent rather than per-flow
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.
Diffstat (limited to 'dashboard/dashapi')
| -rw-r--r-- | dashboard/dashapi/ai.go | 5 |
1 files changed, 2 insertions, 3 deletions
diff --git a/dashboard/dashapi/ai.go b/dashboard/dashapi/ai.go index 8134e5744..dfa410402 100644 --- a/dashboard/dashapi/ai.go +++ b/dashboard/dashapi/ai.go @@ -14,9 +14,8 @@ type AIJobPollReq struct { } type AIWorkflow struct { - Type ai.WorkflowType - Name string - LLMModel string // LLM model that will be used to execute this workflow + Type ai.WorkflowType + Name string } type AIJobPollResp struct { |