scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-12 23:01:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 88

chore: synchronize generated proxy API types

Browse source
This commit is contained in:
Hayden Moulds 2026-09-11 12:40:02 +10:00
parent 5b9244105c
commit 22b4656cb5
No known key found for this signature in database
2 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
litellm/proxy/proxy_server.py
View file

@ -10834,7 +10834,7 @@ async def model_info(
fallback_type=None,
llm_router=llm_router,
)
return {**response, "id": internal_to_public.get(resolved_model_id, model_id)}
return {**response, "id": internal_to_public.get(resolved_model_id, model_id)} # mutable-ok: response id differs
def _blocked_response_usage(original_response: object | None) -> "litellm.Usage":

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

@ -35064,7 +35064,7 @@ export interface components {
classification_prompt?: string | null;
/**
* Classifier Context Budget Chars
* @description Maximum characters of prior-turn text quoted to the LLM classifier, across the whole context window, per classification call. Turns are taken newest first and quoted whole while they fit, so a conversation small enough to quote entirely is never cut; once the budget runs out the older turns are dropped whole and only the turn straddling the boundary is truncated, into whatever space is left. The current ask and the caller's system prompt sit outside this budget and are always sent in full, as does the numbering each quoted turn carries. A budget under 120 leaves no room to quote a turn and suppresses the block; set classifier_context_window_size to 0 to turn context off deliberately. Only applies when classifier_type is 'llm'.
* @description Maximum characters of prior-turn text quoted to the LLM classifier, across the whole context window, per classification call. Turns are taken newest first and quoted whole while they fit, so a conversation small enough to quote entirely is never cut; once the budget runs out the older turns are dropped whole and only the turn straddling the boundary is truncated, into whatever space is left. The current ask and, except for Claude Code requests, the extracted system-role text sit outside this budget and are sent in full, as does the numbering each quoted turn carries. A budget under 120 leaves no room to quote a turn and suppresses the block; set classifier_context_window_size to 0 to turn context off deliberately. Only applies when classifier_type is 'llm'.
* @default 8000
*/
classifier_context_budget_chars: number;
@ -35081,7 +35081,7 @@ export interface components {
classifier_context_per_turn_chars?: number | null;
/**
* Classifier Context Window Size
* @description Number of prior user turns (tool output and harness reminders excluded) to include as context in the LLM classifier prompt, so a follow-up like 'now do the same for the streaming path' is classified against what it refers to. Counts turns of both roles when classifier_context_include_assistant_turns is enabled. These turns are sent to the classifier model, which may be a different deployment or provider than the routed completion model; that call already carries the current user ask and the caller's system prompt in full. Set to 0 to send neither prior turns nor any conversation context beyond the current ask. Only applies when classifier_type is 'llm'.
* @description Number of prior user turns (tool output and harness reminders excluded) to include as context in the LLM classifier prompt, so a follow-up like 'now do the same for the streaming path' is classified against what it refers to. Counts turns of both roles when classifier_context_include_assistant_turns is enabled. These turns are sent to the classifier model, which may be a different deployment or provider than the routed completion model; that call carries the current user ask and, except for Claude Code requests, the extracted system-role text in full. Claude Code system text is omitted to avoid classifying harness instructions; the routed completion still receives it. Set to 0 to send neither prior turns nor any conversation context beyond the current ask. Only applies when classifier_type is 'llm'.
* @default 3
*/
classifier_context_window_size: number;