scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-16 23:41:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 102

chore(ui): regenerate dashboard API types after merging main

Browse source
This commit is contained in:
mateo-berri 2026-09-15 11:19:50 -07:00
parent ce40b5773d
commit 9bba2df58f
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
ui/litellm-dashboard/src/lib/http/schema.d.ts generated vendored
View file

@ -35541,7 +35541,7 @@ export interface components {
default_model?: string | null;
/**
* Deployment Affinity
* @description When True and a session_id is resolvable on the request, pin the deployment chosen inside each routed model group and reuse it whenever the session returns to that group, without pinning which group the session routes to. Independent of session_affinity, which pins the model group instead (and always carries this deployment pin with it): with session_affinity off, every turn is still classified on its own merits while a session that escalates to a stronger tier and comes back still lands on the deployment it used before, which is what keeps a provider prompt cache warm. Pins are held per model group, so switching tiers does not disturb the pin left behind in the previous group. On by default because re-shuffling a conversation across deployments of the same model discards that cache for no benefit; set False to keep every turn load-balanced across the group, which is what a deployment set with tight per-deployment rate limits wants. Inert when no session_id is resolvable, since there is nothing to key a pin on, and suppressed when plugins are configured, for the same reason session_affinity is.
* @description When True and a client session_id is resolvable, reuse the session's chosen model for each classified tier and its deployment within each model group. With session_affinity off, every turn is still classified: moving to another tier leaves the previous tier's model pin intact for a later return. Pins yield to current candidate, context, modality, and availability constraints. Adaptive selection chooses the initial model from its eligible pool, then reuses that choice per tier. This reduces avoidable provider prompt-cache misses; it does not guarantee cache hits. Set False to select models and load-balance deployments on every turn, unless session_affinity or user_turn classification requires a pin. Inert without a client session_id and suppressed when plugins are configured.
* @default true
*/
deployment_affinity: boolean;
@ -35685,7 +35685,7 @@ export interface components {
session_affinity: boolean;
/**
* Session Affinity Ttl Seconds
* @description TTL for the session affinity pin; refreshed on every cache hit. Bounds both the session_affinity model pin and the deployment_affinity deployment pin, so it measures idle time for the session's routing decisions rather than total session length
* @description TTL for the session affinity pin; refreshed on every cache hit. Bounds both the session_affinity model pin and the deployment_affinity per-tier model and deployment pins, so it measures idle time for the session's routing decisions rather than total session length
* @default 3600
*/
session_affinity_ttl_seconds: number;