Resolve compaction policy per routed model
This commit is contained in:
@@ -6,7 +6,13 @@
|
||||
*/
|
||||
|
||||
import { attributionHeaders, CONTEXT_WINDOW_EXCEEDED_CODE, isContextWindowExceededError, LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm'
|
||||
import type { GenerateOptions, LlmModelInfo, LlmProviderInfo, StreamChunk } from '@deepseek-ai/dsh-llm'
|
||||
import type {
|
||||
GenerateOptions,
|
||||
LlmModelContext,
|
||||
LlmModelInfo,
|
||||
LlmProviderInfo,
|
||||
StreamChunk,
|
||||
} from '@deepseek-ai/dsh-llm'
|
||||
import { serializeRequest } from './serialize.ts'
|
||||
import type { RequestDefaults } from './serialize.ts'
|
||||
import { parseSse } from './sse.ts'
|
||||
@@ -21,6 +27,8 @@ export interface DeepSeekCatalogModel {
|
||||
name?: string
|
||||
/** Optional selector detail for deployments with similar model variants. */
|
||||
description?: string
|
||||
/** Known combined request/response context capacity; omitted when deployment metadata is unavailable. */
|
||||
contextWindow?: number
|
||||
}
|
||||
|
||||
/** Constructor options for {@link DeepSeekAdapter}; the plugin's `apply` resolves them from Config + environment. */
|
||||
@@ -79,6 +87,14 @@ export class DeepSeekAdapter extends LlmAdapter {
|
||||
})))
|
||||
}
|
||||
|
||||
override resolveModelContext(
|
||||
_provider: string,
|
||||
model: string,
|
||||
): Promise<LlmModelContext | undefined> {
|
||||
const contextWindow = this.options.models?.find(entry => entry.id === model)?.contextWindow
|
||||
return Promise.resolve(contextWindow === undefined ? undefined : { contextWindow })
|
||||
}
|
||||
|
||||
async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
|
||||
const body = serializeRequest(options, this.options.defaults ?? {})
|
||||
|
||||
|
||||
@@ -20,8 +20,8 @@ export const name = 'llm-deepseek'
|
||||
export const inject = ['llm']
|
||||
|
||||
const DEFAULT_MODELS: DeepSeekCatalogModel[] = [
|
||||
{ id: 'deepseek-v4-flash' },
|
||||
{ id: 'deepseek-v4-pro' },
|
||||
{ id: 'deepseek-v4-flash', contextWindow: 128_000 },
|
||||
{ id: 'deepseek-v4-pro', contextWindow: 128_000 },
|
||||
]
|
||||
|
||||
/**
|
||||
@@ -47,6 +47,7 @@ const catalogModel: z<DeepSeekCatalogModel> = z.object({
|
||||
id: z.string().required(),
|
||||
name: z.string(),
|
||||
description: z.string(),
|
||||
contextWindow: z.number().step(1).min(1),
|
||||
})
|
||||
|
||||
export const Config: z<Config> = z.object({
|
||||
@@ -68,12 +69,19 @@ function resolveModels(models: readonly DeepSeekCatalogModel[] | undefined): Dee
|
||||
if (model.name !== undefined && model.name.length === 0) {
|
||||
throw new Error(`llm-deepseek: catalog model "${model.id}" has an empty name`)
|
||||
}
|
||||
if (model.contextWindow !== undefined
|
||||
&& (!Number.isInteger(model.contextWindow) || model.contextWindow <= 0)) {
|
||||
throw new Error(
|
||||
`llm-deepseek: catalog model "${model.id}" contextWindow must be a positive integer`,
|
||||
)
|
||||
}
|
||||
if (seen.has(model.id)) throw new Error(`llm-deepseek: duplicate catalog model "${model.id}"`)
|
||||
seen.add(model.id)
|
||||
return {
|
||||
id: model.id,
|
||||
...model.name === undefined ? {} : { name: model.name },
|
||||
...model.description === undefined ? {} : { description: model.description },
|
||||
...model.contextWindow === undefined ? {} : { contextWindow: model.contextWindow },
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user