apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-04-25 16:56:24 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

remove random selection policy — consumers can shuffle client-side

Browse source 
Plano should only handle ranking that requires server-side data
(cost metrics, latency). Random shuffling is trivial for callers.
This commit is contained in:
Adil Hafeez 2026-03-30 12:33:06 -07:00
parent 41e6b489f5
commit 5b869648c4
4 changed files with 1 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

3
docs/routing-api.md
View file

@ -41,7 +41,7 @@ POST /v1/chat/completions
| `name` | string | yes | Route identifier. Must match the LLM router's route classification. |
| `description` | string | yes | Natural language description used by the router to match user intent. |
| `models` | string[] | yes | Ordered candidate pool. At least one entry required. Must be declared in `model_providers`. |
| `selection_policy.prefer` | enum | yes | How to rank models: `cheapest`, `fastest`, `random`, or `none`. |
| `selection_policy.prefer` | enum | yes | How to rank models: `cheapest`, `fastest`, or `none`. |
### `selection_policy.prefer` values
@ -49,7 +49,6 @@ POST /v1/chat/completions
|---|---|
| `cheapest` | Sort by ascending cost from the metrics endpoint. Models with no data appended last. |
| `fastest` | Sort by ascending latency from the metrics endpoint. Models with no data appended last. |
| `random` | Shuffle the model list randomly on each request. |
| `none` | Return models in the order they were defined — no reordering. |
### Notes