Merge pinned master into status bar token metrics
This commit is contained in:
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write packages/llm/llm-retry/README.md
|
||||
README.md: 7a86652a794e70c4dfd00ab7427730387e3ec949
|
||||
README.zh.md: c66c04806597c11b5c64dcb01443bb84f489e0f5
|
||||
README.md: 8de3ea8c9321f04f5af1b0d7ab361f73eaabc822
|
||||
README.zh.md: 978854e9466e271535a10fcea406d0dcb5607285
|
||||
|
||||
@@ -8,7 +8,7 @@ Each provider adapter owns an optional nested `retryPolicy`, captured when its r
|
||||
|
||||
Both modes use bounded exponential backoff with symmetric jitter. A valid `providerRetryAfterMs` at or below `maxDelayMs` replaces local backoff without jitter. An over-cap provider delay makes normal mode delegate, while always mode uses its configured local backoff so it cannot terminate on that instruction.
|
||||
|
||||
Before waiting, the plugin appends a non-surface `llm/retry` event with the provider, mode, canonical resolved-policy key, failure, and scheduled delay. The key includes every behavior-affecting field and sorts normal-mode codes because eligibility uses set membership. Retry numbers continue only across events with the same provider and complete policy key, so a route replacement with different limits, code membership, or backoff starts its own history. Normal events include the finite maximum; always events omit it, and UIs render `∞`. After the wait, the listener returns `{ kind: 'retry' }`, and the loop closes the failed turn and opens a retry turn over the same durable history. Cancellation and plugin disposal abort active backoff, drain active delegated recovery before applying the abort, and make a callback captured before disposal fail closed.
|
||||
Before waiting, the plugin appends a non-surface `llm/retry` event with the provider, mode, canonical resolved-policy key, failure, and scheduled delay. Its payload is available from the browser-safe `@deepseek-ai/dsh-llm-retry/types` subpath, so remote renderers can consume the durable status without loading the policy runtime. The key includes every behavior-affecting field and sorts normal-mode codes because eligibility uses set membership. Retry numbers continue only across events with the same provider and complete policy key, so a route replacement with different limits, code membership, or backoff starts its own history. Normal events include the finite maximum; always events omit it, and UIs render `∞`. After the wait, the listener returns `{ kind: 'retry' }`, and the loop closes the failed turn and opens a retry turn over the same durable history. Cancellation and plugin disposal abort active backoff, drain active delegated recovery before applying the abort, and make a callback captured before disposal fail closed.
|
||||
|
||||
The separately published `./invariant` companion checks that every retry record names the current open turn and latest closed step, matches the failed request's durable provider, carries non-empty provider and policy identities, has mode-specific bounds, a unique step record, the correct provider-policy retry number, and a bounded timer delay. Full jitter may schedule zero milliseconds at its lower boundary.
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
|
||||
两种 mode 都使用带对称 jitter 的有界指数退避。有效 `providerRetryAfterMs` 不超过 `maxDelayMs` 时会替换本地退避,并且不加 jitter。超出上限的提供方延迟会使 normal mode 继续委托;always mode 则改用已配置的本地退避,避免该指令终止重试。
|
||||
|
||||
等待前,插件会追加一条不进入表层的 `llm/retry` 事件,其中包含提供方、mode、已解析策略的规范 key、失败和计划延迟。该 key 包含所有影响行为的字段,并对 normal mode 的 code 排序,因为合格性采用集合成员关系判断。只有提供方与完整策略 key 都相同的事件才会延续重试编号;因此,用限制、code 成员关系或退避不同的路由替换后,会开始自己的历史。normal 事件包含有限上限;always 事件省略该上限,UI 会渲染 `∞`。等待结束后,监听器返回 `{ kind: 'retry' }`,循环关闭失败轮次,并在同一持久历史上开启重试轮次。取消与插件 dispose 会中止活跃退避,在应用中止前排空活跃的委托恢复,并使 dispose 前捕获的 callback 只能以失败结束。
|
||||
等待前,插件会追加一条不进入表层的 `llm/retry` 事件,其中包含提供方、mode、已解析策略的规范 key、失败和计划延迟。该载荷由可安全用于浏览器的 `@deepseek-ai/dsh-llm-retry/types` 子路径导出,因此远程渲染器无需加载策略运行时即可使用该持久状态。该 key 包含所有影响行为的字段,并对 normal mode 的 code 排序,因为合格性采用集合成员关系判断。只有提供方与完整策略 key 都相同的事件才会延续重试编号;因此,用限制、code 成员关系或退避不同的路由替换后,会开始自己的历史。normal 事件包含有限上限;always 事件省略该上限,UI 会渲染 `∞`。等待结束后,监听器返回 `{ kind: 'retry' }`,循环关闭失败轮次,并在同一持久历史上开启重试轮次。取消与插件 dispose 会中止活跃退避,在应用中止前排空活跃的委托恢复,并使 dispose 前捕获的 callback 只能以失败结束。
|
||||
|
||||
单独发布的 `./invariant` 配套模块会检查每个重试记录是否指向当前开启轮次及其最新已关闭步骤,是否与失败请求的持久提供方匹配,是否携带非空的提供方与策略标识,是否满足 mode 特定边界,是否拥有唯一步骤记录和正确的提供方策略重试编号,以及是否携带有界定时器延迟。完整 jitter 可以在下界调度为零毫秒。
|
||||
|
||||
|
||||
@@ -15,11 +15,16 @@
|
||||
"types": "./lib/types/invariant.d.ts",
|
||||
"default": "./lib/invariant.js"
|
||||
},
|
||||
"./types": {
|
||||
"types": "./lib/types/types.d.ts",
|
||||
"default": "./lib/types/types.js"
|
||||
},
|
||||
"./package.json": "./package.json"
|
||||
},
|
||||
"files": [
|
||||
"lib/index.js",
|
||||
"lib/invariant.js",
|
||||
"lib/types/**/*.js",
|
||||
"lib/types/**/*.d.ts",
|
||||
"lib/types/**/*.d.ts.map",
|
||||
"src"
|
||||
|
||||
@@ -38,6 +38,8 @@ declare module '@deepseek-ai/dsh-session' {
|
||||
}
|
||||
}
|
||||
|
||||
export type { LlmRetryEventData } from './types.ts'
|
||||
|
||||
export const name = 'llm-retry'
|
||||
export const inject = ['agents']
|
||||
|
||||
|
||||
25
packages/llm/llm-retry/src/types.ts
Normal file
25
packages/llm/llm-retry/src/types.ts
Normal file
@@ -0,0 +1,25 @@
|
||||
import type { LlmFailure } from '@deepseek-ai/dsh-llm/types'
|
||||
|
||||
/** Durable payload recorded before one provider-routed model-request retry wait. */
|
||||
export type LlmRetryEventData =
|
||||
| {
|
||||
turn: number
|
||||
step: number
|
||||
provider: string
|
||||
mode: 'normal'
|
||||
policyKey: string
|
||||
retry: number
|
||||
maxRetries: number
|
||||
delayMs: number
|
||||
failure: LlmFailure
|
||||
}
|
||||
| {
|
||||
turn: number
|
||||
step: number
|
||||
provider: string
|
||||
mode: 'always'
|
||||
policyKey: string
|
||||
retry: number
|
||||
delayMs: number
|
||||
failure: LlmFailure
|
||||
}
|
||||
@@ -12,7 +12,8 @@ import type {
|
||||
StreamChunk,
|
||||
} from '@deepseek-ai/dsh-llm'
|
||||
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
|
||||
import type { SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import type { SessionEvent, SessionEventMap } from '@deepseek-ai/dsh-session'
|
||||
import type { LlmRetryEventData } from '@deepseek-ai/dsh-llm-retry/types'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry, { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
|
||||
import AgentRegistry from '@deepseek-ai/dsh-agent'
|
||||
@@ -22,6 +23,10 @@ import * as retry from '../src/index.ts'
|
||||
|
||||
type ScriptEntry = Error | Iterable<StreamChunk> | AsyncIterable<StreamChunk>
|
||||
|
||||
it('keeps the browser-safe retry payload identical to the session event', () => {
|
||||
expectTypeOf<LlmRetryEventData>().toEqualTypeOf<SessionEventMap['llm/retry']>()
|
||||
})
|
||||
|
||||
class ScriptedAdapter extends LlmAdapter {
|
||||
readonly requests: GenerateOptions[] = []
|
||||
private retryPolicies: Readonly<Record<string, ResolvedRetryPolicy | undefined>> = {}
|
||||
|
||||
Reference in New Issue
Block a user