feat(llm): add per-provider retry policies

packages/examples/cli-demo/README.md

@@ -19,7 +19,6 @@ The package mounts no console logger, interactive UI, user-interaction service,
 | `skills` | owner defaults | skill registry, local provider, and model-facing skill tool |
 | `toolBash` | owner defaults | model-facing bash config, including this producer's background opt-in |
 | `toolTasks` | owner defaults | generic `task_output` wait bounds |
-| `llmRetry` | owner defaults | bounded transient model-request retry policy |
 | `persistenceRoot` | `./.sessions` | JSONL session root |
 | `persistenceCompression` | `'zstd'` | JSONL artifact encoding (`'zstd'` or raw `'none'`) |
 | `workspaceContext` | required | workspace-instruction byte budget, or `false` to disable loading |

packages/examples/cli-demo/src/index.ts

@@ -50,8 +50,6 @@ export interface Config {
   toolBash?: NonNullable<agentCore.Config['toolBash']>
   /** Generic background-task control-tool config forwarded through agent-spine-demo. */
   toolTasks?: NonNullable<agentCore.Config['toolTasks']>
-  /** Bounded transient model-request retry policy forwarded through agent-spine-demo. */
-  llmRetry?: NonNullable<agentCore.Config['llmRetry']>
   /** Controls automatic AGENTS.md/CLAUDE.md loading; configure a byte budget or set `false`. */
   workspaceContext: agentCore.Config['workspaceContext']
 }
@@ -74,7 +72,6 @@ export const Config: z<Config> = z.object({
   tools: ToolRegistry.Config,
   toolBash: agentCore.ToolBashConfigSchema,
   toolTasks: z.union([z.const(false), agentCore.ToolTasksConfigSchema]),
-  llmRetry: agentCore.LlmRetryConfigSchema,
   workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(),
 })
 /* jscpd:ignore-end */

packages/examples/cli-demo/tests/cli.spec.ts

@@ -3,7 +3,15 @@ import { tmpdir } from 'node:os'
 import { join, resolve } from 'node:path'
 import { Context } from 'cordis'
 import type { Agent } from '@deepseek-ai/dsh-agent'
-import { CallId, LlmAdapter, type GenerateOptions, type StreamChunk, type TokenUsage } from '@deepseek-ai/dsh-llm'
+import {
+  CallId,
+  LlmAdapter,
+  resolveRetryPolicy,
+  type GenerateOptions,
+  type ResolvedRetryPolicy,
+  type StreamChunk,
+  type TokenUsage,
+} from '@deepseek-ai/dsh-llm'
 import { SessionId, type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session'
 import { afterEach, describe, expect, it } from 'vitest'
 import * as cliDemo from '../src/index.ts'
@@ -20,11 +28,19 @@ type ScriptEntry = readonly StreamChunk[] | 'hang'
 class ScriptedAdapter extends LlmAdapter {
   readonly requests: GenerateOptions[] = []
   private cursor = 0
+  private readonly retryPolicy = resolveRetryPolicy({
+    mode: 'normal',
+    backoff: { initialDelayMs: 1, maxDelayMs: 1, jitterRatio: 0 },
+  }, 'cli test provider retryPolicy')
 
   constructor(private readonly script: readonly ScriptEntry[]) {
     super()
   }
 
+  override providerRetryPolicy(_provider: string): ResolvedRetryPolicy {
+    return this.retryPolicy
+  }
+
   async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
     this.requests.push(options)
     const entry = this.script[this.cursor++]
@@ -107,7 +123,6 @@ async function harness(script: readonly ScriptEntry[]): Promise<Harness> {
     persistenceRoot: root,
     skills: { local: { dshHome: join(skillHome, '.dsh'), agentsHome: join(skillHome, '.agents') } },
     workspaceContext: false,
-    llmRetry: { initialDelayMs: 1, maxDelayMs: 1, jitterRatio: 0 },
   })
   await new Promise(resolve => setTimeout(resolve, 80))
   ctx.llm.registerAdapter(['mock'], new ScriptedAdapter(script))