feat(llm): add per-provider retry policies

packages/llm/llm-pi-ai/src/adapter.ts

@@ -13,7 +13,7 @@ import type {
   SimpleStreamOptions,
 } from '@earendil-works/pi-ai'
 import { attributionHeaders, LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm'
-import type { GenerateOptions, LlmModelContext, LlmModelInfo, StreamChunk } from '@deepseek-ai/dsh-llm'
+import type { GenerateOptions, LlmModelContext, LlmModelInfo, ResolvedRetryPolicy, StreamChunk } from '@deepseek-ai/dsh-llm'
 import { idleWatchdog, timeoutOf } from '@deepseek-ai/dsh-timeout'
 import { resolveProfiles } from './config.ts'
 import type { PiAiProviderProfile, ResolvedPiAiProviderProfile } from './config.ts'
@@ -30,7 +30,10 @@ export interface PiAiAdapterOptions {
  * Resolve a catalog model dynamically and apply only the configured endpoint
  * override, preserving the catalog's API/capability/compatibility metadata.
  */
-function resolveModel(profile: PiAiProviderProfile, modelId: string): Model<Api> {
+function resolveModel(
+  profile: Omit<PiAiProviderProfile, 'retryPolicy'>,
+  modelId: string,
+): Model<Api> {
   const model = getBuiltinModels(profile.provider as BuiltinProvider).find(candidate => candidate.id === modelId) as Model<Api> | undefined
   if (model === undefined) {
     throw new LlmError(`pi-ai provider "${profile.provider}" has no catalog model "${modelId}"`, 'UNKNOWN_MODEL')
@@ -39,7 +42,7 @@ function resolveModel(profile: PiAiProviderProfile, modelId: string): Model<Api>
 }
 
 /** Copy profile stream knobs into pi-ai's common option vocabulary. */
-function profileOptions(profile: PiAiProviderProfile): SimpleStreamOptions {
+function profileOptions(profile: Omit<PiAiProviderProfile, 'retryPolicy'>): SimpleStreamOptions {
   return {
     ...profile.apiKey === undefined ? {} : { apiKey: profile.apiKey },
     ...profile.reasoning === undefined ? {} : { reasoning: profile.reasoning },
@@ -75,6 +78,10 @@ export class PiAiAdapter extends LlmAdapter {
     this.profiles = new Map(resolveProfiles(options.profiles).map(profile => [profile.provider, profile]))
   }
 
+  override providerRetryPolicy(provider: string): ResolvedRetryPolicy | undefined {
+    return this.profiles.get(provider)?.retryPolicy
+  }
+
   override listModels(provider: string): Promise<readonly LlmModelInfo[]> {
     const profile = this.profiles.get(provider)
     if (profile === undefined) {

packages/llm/llm-pi-ai/src/config.ts

@@ -8,6 +8,8 @@ import { getBuiltinProviders } from '@earendil-works/pi-ai/providers/all'
 import type { CacheRetention, ThinkingBudgets, ThinkingLevel, Transport } from '@earendil-works/pi-ai'
 import z from 'schemastery'
 import { MAX_TIMER_DELAY_MS } from '@deepseek-ai/dsh-timeout'
+import { resolveRetryPolicy, RetryPolicySchema } from '@deepseek-ai/dsh-llm'
+import type { ResolvedRetryPolicy, RetryPolicyConfig } from '@deepseek-ai/dsh-llm'
 
 /** Default maximum idle interval while an adapter stream read is outstanding. */
 export const DEFAULT_STREAM_IDLE_TIMEOUT_MS = 300_000
@@ -36,12 +38,16 @@ export interface PiAiProviderProfile {
   websocketConnectTimeoutMs?: number
   /** Maximum provider idle time while one stream read is outstanding. */
   streamIdleTimeoutMs?: number
+  /** Provider-owned model-request retry policy; omission uses normal defaults. */
+  retryPolicy?: RetryPolicyConfig
 }
 
 /** Validated profile with every adapter-owned default resolved. */
-export interface ResolvedPiAiProviderProfile extends PiAiProviderProfile {
+export interface ResolvedPiAiProviderProfile extends Omit<PiAiProviderProfile, 'retryPolicy'> {
   /** Positive finite provider-idle interval after defaulting. */
   streamIdleTimeoutMs: number
+  /** Immutable retry policy captured with this provider route. */
+  retryPolicy: ResolvedRetryPolicy
 }
 
 /** Plugin configuration: the non-empty provider profiles this instance owns. */
@@ -69,6 +75,7 @@ const profile = z.object({
   timeoutMs: z.natural(),
   websocketConnectTimeoutMs: z.natural(),
   streamIdleTimeoutMs: z.number().min(Number.MIN_VALUE).max(MAX_TIMER_DELAY_MS).default(DEFAULT_STREAM_IDLE_TIMEOUT_MS),
+  retryPolicy: RetryPolicySchema,
 })
 
 /** Runtime schema for {@link Config}. */
@@ -115,6 +122,10 @@ export function resolveProfiles(profiles: readonly PiAiProviderProfile[]): Resol
     return {
       ...source,
       streamIdleTimeoutMs,
+      retryPolicy: resolveRetryPolicy(
+        source.retryPolicy,
+        `llm-pi-ai: provider "${source.provider}" retryPolicy`,
+      ),
       ...source.headers === undefined ? {} : { headers: { ...source.headers } },
       ...source.thinkingBudgets === undefined ? {} : { thinkingBudgets: { ...source.thinkingBudgets } },
     }

packages/llm/llm-pi-ai/src/index.ts

@@ -10,6 +10,9 @@
  *     providers:
  *       - provider: openai
  *         apiKey: !!js process.env.OPENAI_API_KEY
+ *         retryPolicy:
+ *           mode: normal
+ *           maxRetries: 2
  *       - provider: anthropic
  *         apiKey: !!js process.env.ANTHROPIC_API_KEY
  *       - provider: openrouter
@@ -36,6 +39,6 @@ export const inject = ['llm']
 /** Register one generic pi-ai adapter for all configured provider routes. */
 export function apply(ctx: Context, config: Config): void {
   const profiles = resolveProfiles(config.providers)
-  const adapter = new PiAiAdapter({ profiles })
+  const adapter = new PiAiAdapter({ profiles: config.providers })
   ctx.llm.registerAdapter(profiles.map(entry => entry.provider), adapter)
 }