feat(llm): add per-provider retry policies

packages/llm/llm-deepseek/src/adapter.ts

@@ -5,12 +5,14 @@
  * @module dsh-llm-deepseek/adapter
  */
 
-import { attributionHeaders, CONTEXT_WINDOW_EXCEEDED_CODE, isContextWindowExceededError, isQuotaExceededError, LlmAdapter, LlmError, ProviderRequestId, QUOTA_EXCEEDED_CODE } from '@deepseek-ai/dsh-llm'
+import { attributionHeaders, CONTEXT_WINDOW_EXCEEDED_CODE, isContextWindowExceededError, isQuotaExceededError, LlmAdapter, LlmError, ProviderRequestId, QUOTA_EXCEEDED_CODE, resolveRetryPolicy } from '@deepseek-ai/dsh-llm'
 import type {
   GenerateOptions,
   LlmModelContext,
   LlmModelInfo,
   LlmProviderInfo,
+  ResolvedRetryPolicy,
+  RetryPolicyConfig,
   StreamChunk,
 } from '@deepseek-ai/dsh-llm'
 import { idleWatchdog, MAX_TIMER_DELAY_MS, timeoutOf } from '@deepseek-ai/dsh-timeout'
@@ -46,6 +48,8 @@ export interface DeepSeekAdapterOptions {
   models?: readonly DeepSeekCatalogModel[]
   /** Maximum provider idle time while one stream read is outstanding. */
   streamIdleTimeoutMs?: number
+  /** Provider-owned model-request retry policy; omission uses normal defaults. */
+  retryPolicy?: RetryPolicyConfig
 }
 
 /** Default maximum idle interval while an adapter stream read is outstanding. */
@@ -95,6 +99,7 @@ export function httpErrorCode(status: number, error?: WireError['error']): strin
  */
 export class DeepSeekAdapter extends LlmAdapter {
   private readonly streamIdleTimeoutMs: number
+  private readonly retryPolicy: ResolvedRetryPolicy
 
   constructor(private readonly options: DeepSeekAdapterOptions) {
     super()
@@ -110,12 +115,17 @@ export class DeepSeekAdapter extends LlmAdapter {
         `llm-deepseek: streamIdleTimeoutMs must be a positive finite number no greater than ${MAX_TIMER_DELAY_MS}`,
       )
     }
+    this.retryPolicy = resolveRetryPolicy(options.retryPolicy, 'llm-deepseek: retryPolicy')
   }
 
   override providerInfo(provider: string): LlmProviderInfo {
     return { id: provider, name: 'DeepSeek' }
   }
 
+  override providerRetryPolicy(_provider: string): ResolvedRetryPolicy {
+    return this.retryPolicy
+  }
+
   override listModels(provider: string): Promise<readonly LlmModelInfo[]> {
     return Promise.resolve((this.options.models ?? []).map(model => ({
       provider,

packages/llm/llm-deepseek/src/index.ts

@@ -7,7 +7,8 @@
 
 import type { Context } from 'cordis'
 import z from 'schemastery'
-import type {} from '@deepseek-ai/dsh-llm'
+import { RetryPolicySchema } from '@deepseek-ai/dsh-llm'
+import type { RetryPolicyConfig } from '@deepseek-ai/dsh-llm'
 import { MAX_TIMER_DELAY_MS } from '@deepseek-ai/dsh-timeout'
 import { DEFAULT_STREAM_IDLE_TIMEOUT_MS, DeepSeekAdapter } from './adapter.ts'
 import type { DeepSeekCatalogModel } from './adapter.ts'
@@ -46,6 +47,8 @@ export interface Config {
   models?: DeepSeekCatalogModel[]
   /** Maximum provider idle time while one stream read is outstanding (default five minutes). */
   streamIdleTimeoutMs?: number
+  /** Provider-owned model-request retry policy; omission uses normal defaults. */
+  retryPolicy?: RetryPolicyConfig
 }
 
 const catalogModel: z<DeepSeekCatalogModel> = z.object({
@@ -63,6 +66,7 @@ export const Config: z<Config> = z.object({
   defaultContextWindow: z.number().step(1).min(1),
   models: z.array(catalogModel).default(DEFAULT_MODELS),
   streamIdleTimeoutMs: z.number().min(Number.MIN_VALUE).max(MAX_TIMER_DELAY_MS).default(DEFAULT_STREAM_IDLE_TIMEOUT_MS),
+  retryPolicy: RetryPolicySchema,
 })
 
 /** Public API default; the internal endpoint comes from $DEEPSEEK_BASE_URL. */
@@ -111,5 +115,6 @@ export function apply(ctx: Context, config: Config): void {
       : { defaultContextWindow: config.defaultContextWindow },
     models: resolveModels(config.models),
     streamIdleTimeoutMs: config.streamIdleTimeoutMs ?? DEFAULT_STREAM_IDLE_TIMEOUT_MS,
+    ...config.retryPolicy === undefined ? {} : { retryPolicy: config.retryPolicy },
   }))
 }