test: migrate consumers to inbox and owned-run APIs
This commit is contained in:
@@ -16,10 +16,10 @@
|
||||
- `ctx.llm.listModels(provider: string): Promise<LlmModelInfo[]>` 发现某个已注册提供方当前公布的模型。
|
||||
- `ctx.llm.resolveModelInfo(provider: string, model: string, signal?: AbortSignal): Promise<LlmResolvedModelInfo>` 从拥有精确路由的适配器解析经校验的确切模型身份、可用上下文和推理(reasoning)元数据;异步适配器可选地支持取消。
|
||||
- `ctx.llm.resolveCallConfig(config: LlmCallConfig, signal?: AbortSignal): Promise<LlmCallConfig>` 校验显式推理强度,并填入适配器配置的默认值,但不自动调整。
|
||||
- `ctx.llm.prepareCall(config: LlmCallConfig, signal?: AbortSignal): Promise<PreparedLlmCall>` 解析配置并将其当前适配器注册捕获为一次可取消、一次性调用。
|
||||
- `ctx.llm.prepareCall(config: LlmCallConfig, signal?: AbortSignal): Promise<PreparedLlmCall>` 解析配置,并将当前适配器注册及不可变重试策略捕获为一次可取消、一次性调用。
|
||||
- `ctx.llm.stream(options: GenerateOptions): AsyncIterable<StreamChunk>` 将一次模型调用流式输出为原始分片(token 级增量)。消费方使用 `BlockAssembler` 将分片组装为块/消息。
|
||||
|
||||
`LlmService` 保留来自最终适配器选择、同步 dispatch、iterator 构造与迭代的错误,并将其溯源绑定到该次模型调用返回的精确流句柄。`isLlmAdapterFailure(stream, value)` 只报告该调用最终适配器边界的错误;`llmFailureOf(stream, value)` 返回关联的不可变 `LlmFailure`;`llmRetryPolicyOf(stream)` 返回在该边界选中的确切注册所对应的不可变策略,即使之后释放或替换路由也不变。未到达最终适配器的调用没有服务策略。嵌套模型调用、`llm/stream` middleware 和下游消费方失败对外层调用仍未分类。分类绝不替换或更改适配器原有的带代码 `Error`。
|
||||
`LlmService` 将最终适配器选择、同步 dispatch、iterator 构造与迭代中的失败规范化为流协议唯一的终止形式:`finish { kind: 'error' | 'aborted', failure }`。部分增量输出后发生失败时,内容块可能仍未闭合;消费方会丢弃这些不完整输出。`llm/stream` middleware、嵌套调用、适配器清理和下游消费方的错误仍会抛出,因为它们属于插件或消费方失败,而非模型请求结果。已准备调用会暴露随其确切适配器注册一同捕获的不可变重试策略;完全由 middleware 处理的路由没有服务策略。
|
||||
|
||||
提供方与模型元数据是发现接口,不是路由白名单。`registerAdapter()` 仍拥有提供方排他性,并为每条路由捕获适配器的重试策略;适配器则可以接受 `listModels()` 中不存在的模型 id,消费方禁止因模型未列出而拒绝请求。返回的 selector 元数据与输入脱离,无效或重复适配器配置项会以 `INVALID_ADAPTER` 或 `INVALID_CATALOG` 失败。
|
||||
|
||||
@@ -44,7 +44,7 @@
|
||||
|
||||
消息内容是类型化内容块数组:`text`、`reasoning`、`tool-call`、`tool-result`。联合从可合并扩展的 `ContentBlockMap` 派生,因此插件可以通过 declaration merging 添加块类型。assistant 消息使用模型来源,其中携带提供方/模型溯源与可选适配器私有回放状态。dispatch 前,`LlmService` 只在历史提供方路由与目标提供方路由当前由完全相同的适配器实例拥有时才保留该状态;随后由适配器判定能否在模型/提供方间恢复或转换该状态。核心块集只包含每条已发布路径都支持的块。多模态内容(图像、音频等)没有核心块类型;需要它的功能会通过 map 添加,并一并添加相应的适配器/UI/压缩(compaction)支持。
|
||||
|
||||
流式输出是原始分片协议(`block-start`、`text-delta`、`reasoning-delta`、`tool-call-delta`、`block-end`、`usage`、`finish`)。`BlockAssembler` 是将分片组装为块/消息的唯一共享实现。
|
||||
流式输出是原始分片协议(`block-start`、`text-delta`、`reasoning-delta`、`tool-call-delta`、`block-end`、`usage`、`finish`)。每个适配器结果都以一个终止 `finish` 到达消费方;运行故障使用其 `error` 或 `aborted` 原因,而不会跨流 API 抛出。`BlockAssembler` 是将分片组装为块/消息的唯一共享实现。
|
||||
|
||||
### 调用配置(`call-config.ts`)
|
||||
|
||||
@@ -67,7 +67,7 @@
|
||||
|
||||
### 真实适配器
|
||||
|
||||
两个适配器使用不同内部机制实现 `LlmAdapter`:[`@deepseek-ai/dsh-llm-deepseek`](../llm-deepseek) 针对 `deepseek` 路由使用直接 fetch 加 `eventsource-parser` SSE(Server-Sent Events)分帧,[`@deepseek-ai/dsh-llm-pi-ai`](../llm-pi-ai) 则通过 `@earendil-works/pi-ai` 动态解析已配置提供方/模型对。两者都遵循 `StreamChunk` 约定,定义见 `types.ts`:usage 先于 finish,工具参数保持原始字符串,错误使用两种已批准路径之一。设计理由见 [双 LLM 适配器](../../../.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md)。
|
||||
两个适配器使用不同内部机制实现 `LlmAdapter`:[`@deepseek-ai/dsh-llm-deepseek`](../llm-deepseek) 针对 `deepseek` 路由使用直接 fetch 加 `eventsource-parser` SSE(Server-Sent Events)分帧,[`@deepseek-ai/dsh-llm-pi-ai`](../llm-pi-ai) 则通过 `@earendil-works/pi-ai` 动态解析已配置提供方/模型对。两者都遵循 `types.ts` 中的 `StreamChunk` 约定:usage 先于 finish,工具参数保持原始字符串。适配器实现在内部可以抛出异常或发出失败 finish;`LlmService` 会将两者都暴露为终止失败 finish。适配器理由见[双 LLM 适配器](../../../.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md),服务边界见[终止失败决策](../../../.agents/notes/implemented/architecture/2026-07-29-terminal-llm-stream-failures.md)。
|
||||
|
||||
## 模型体验
|
||||
|
||||
|
||||
@@ -510,9 +510,12 @@ export class LlmService extends Service {
|
||||
let completed = false
|
||||
try {
|
||||
while (true) {
|
||||
let item: IteratorResult<StreamChunk>
|
||||
let item: { done: true } | { done: false; value: StreamChunk }
|
||||
try {
|
||||
item = await iterator.next()
|
||||
const next = await iterator.next()
|
||||
item = next.done
|
||||
? { done: true }
|
||||
: { done: false, value: next.value }
|
||||
} catch (error: unknown) {
|
||||
completed = true
|
||||
yield adapterFailureChunk(error, options.signal)
|
||||
@@ -527,8 +530,7 @@ export class LlmService extends Service {
|
||||
yield item.value
|
||||
}
|
||||
} finally {
|
||||
// oxlint-disable-next-line typescript/no-unnecessary-condition -- the iteration catch sets its latch before entering finally.
|
||||
if (!completed && !iterationFailed) {
|
||||
if (!completed) {
|
||||
const close = iterator.return?.bind(iterator)
|
||||
if (close) await close()
|
||||
}
|
||||
|
||||
@@ -6,11 +6,8 @@ import LlmService, {
|
||||
HarnessError,
|
||||
isContextWindowExceededError,
|
||||
isQuotaExceededError,
|
||||
isLlmAdapterFailure,
|
||||
LlmAdapter,
|
||||
LlmError,
|
||||
llmFailureOf,
|
||||
llmRetryPolicyOf,
|
||||
ProviderRequestId,
|
||||
ReasoningEffortId,
|
||||
resolveRetryPolicy,
|
||||
@@ -93,6 +90,12 @@ const SCRIPT: StreamChunk[] = [
|
||||
{ type: 'finish', reason: { kind: 'stop' } },
|
||||
]
|
||||
|
||||
async function collect(stream: AsyncIterable<StreamChunk>): Promise<StreamChunk[]> {
|
||||
const chunks: StreamChunk[] = []
|
||||
for await (const chunk of stream) chunks.push(chunk)
|
||||
return chunks
|
||||
}
|
||||
|
||||
describe('LlmService', () => {
|
||||
it('recognizes structured and model-capacity context-window overflow details', () => {
|
||||
expect(isContextWindowExceededError('context_length_exceeded maximum context length')).toBe(true)
|
||||
@@ -217,69 +220,58 @@ describe('LlmService', () => {
|
||||
)
|
||||
})
|
||||
|
||||
it('keeps the serving registration policy on an in-flight call after route replacement', async () => {
|
||||
it('keeps a prepared registration and retry policy after route replacement', async () => {
|
||||
const oldPolicy = resolveRetryPolicy({ mode: 'always' }, 'old retryPolicy')
|
||||
const newPolicy = resolveRetryPolicy({ mode: 'normal', maxRetries: 0 }, 'new retryPolicy')
|
||||
const entered = Promise.withResolvers<undefined>()
|
||||
const release = Promise.withResolvers<undefined>()
|
||||
const failure = new LlmError('old route failed', 'AUTH')
|
||||
const oldAdapter = new class extends LlmAdapter {
|
||||
const oldFailure = new LlmError('old route failed', 'AUTH')
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
const disposeOld = ctx.llm.registerAdapter(['route'], new class extends ThrowingAdapter {
|
||||
override providerRetryPolicy(): typeof oldPolicy {
|
||||
return oldPolicy
|
||||
}
|
||||
}(oldFailure))
|
||||
const prepared = await ctx.llm.prepareCall({ provider: 'route', model: 'model' })
|
||||
|
||||
async * stream(_options: GenerateOptions): AsyncIterable<StreamChunk> {
|
||||
entered.resolve(undefined)
|
||||
await release.promise
|
||||
throw failure
|
||||
}
|
||||
}()
|
||||
const newAdapter = new class extends ScriptedAdapter {
|
||||
disposeOld()
|
||||
ctx.llm.registerAdapter(['route'], new class extends ScriptedAdapter {
|
||||
override providerRetryPolicy(): typeof newPolicy {
|
||||
return newPolicy
|
||||
}
|
||||
}(SCRIPT)
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
const disposeOld = ctx.llm.registerAdapter(['route'], oldAdapter)
|
||||
const stream = ctx.llm.stream({ provider: 'route', model: 'model', messages: [] })
|
||||
const outcome = (async (): Promise<unknown> => {
|
||||
try {
|
||||
for await (const _chunk of stream) { /* drain */ }
|
||||
} catch (error: unknown) {
|
||||
return error
|
||||
}
|
||||
return undefined
|
||||
})()
|
||||
await entered.promise
|
||||
}(SCRIPT))
|
||||
|
||||
disposeOld()
|
||||
ctx.llm.registerAdapter(['route'], newAdapter)
|
||||
release.resolve(undefined)
|
||||
|
||||
expect(await outcome).toBe(failure)
|
||||
expect(llmRetryPolicyOf(stream)).toBe(oldPolicy)
|
||||
const chunks = await collect(prepared.stream({ ...prepared.config, messages: [] }))
|
||||
expect(chunks.at(-1)).toEqual({
|
||||
type: 'finish',
|
||||
reason: {
|
||||
kind: 'error',
|
||||
failure: { message: 'old route failed', code: 'AUTH' },
|
||||
},
|
||||
})
|
||||
expect(prepared.retryPolicy).toBe(oldPolicy)
|
||||
expect(ctx.llm.providerRetryPolicy('route')).toBe(newPolicy)
|
||||
})
|
||||
|
||||
it('throws NO_ADAPTER for unregistered providers', async () => {
|
||||
it('normalizes an unregistered provider to a terminal failure', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
const stream = ctx.llm.stream({ provider: 'nope', model: 'any-model', messages: [] })
|
||||
let caught: unknown
|
||||
try {
|
||||
for await (const _ of stream) { /* drain */ }
|
||||
} catch (error: unknown) {
|
||||
caught = error
|
||||
}
|
||||
expect(caught).toBeInstanceOf(LlmError)
|
||||
expect((caught as LlmError).code).toBe('NO_ADAPTER')
|
||||
expect((caught as LlmError).message).toContain('no adapter registered')
|
||||
expect(isLlmAdapterFailure(stream, caught)).toBe(true)
|
||||
expect(llmRetryPolicyOf(stream)).toBeUndefined()
|
||||
|
||||
const chunks = await collect(ctx.llm.stream({
|
||||
provider: 'nope',
|
||||
model: 'any-model',
|
||||
messages: [],
|
||||
}))
|
||||
|
||||
expect(chunks.at(-1)).toMatchObject({
|
||||
type: 'finish',
|
||||
reason: {
|
||||
kind: 'error',
|
||||
failure: { code: 'NO_ADAPTER', message: expect.stringContaining('no adapter registered') },
|
||||
},
|
||||
})
|
||||
})
|
||||
|
||||
it.each(['done', 'value'] as const)('tags a throwing IteratorResult.%s getter without replacing its Error', async (field) => {
|
||||
it.each(['done', 'value'] as const)('normalizes a throwing IteratorResult.%s getter', async (field) => {
|
||||
const original = new LlmError(`${field} getter failed`, 'RESULT_GETTER_FAILED')
|
||||
const result = field === 'done' ? {} : { done: false }
|
||||
Object.defineProperty(result, field, { get: () => { throw original } })
|
||||
@@ -295,31 +287,30 @@ describe('LlmService', () => {
|
||||
})
|
||||
const adapter = new class extends LlmAdapter {
|
||||
stream(_options: GenerateOptions): AsyncIterable<StreamChunk> {
|
||||
return {
|
||||
[Symbol.asyncIterator](): AsyncIterator<StreamChunk> {
|
||||
return iterator
|
||||
},
|
||||
}
|
||||
return { [Symbol.asyncIterator]: () => iterator }
|
||||
}
|
||||
}()
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['test-model'], adapter)
|
||||
ctx.llm.registerAdapter(['test'], adapter)
|
||||
|
||||
const stream = ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] })
|
||||
let caught: unknown
|
||||
try {
|
||||
for await (const _chunk of stream) { /* drain */ }
|
||||
} catch (error: unknown) {
|
||||
caught = error
|
||||
}
|
||||
const chunks = await collect(ctx.llm.stream({
|
||||
provider: 'test',
|
||||
model: 'test',
|
||||
messages: [],
|
||||
}))
|
||||
|
||||
expect(caught).toBe(original)
|
||||
expect(isLlmAdapterFailure(stream, caught)).toBe(true)
|
||||
expect(chunks.at(-1)).toEqual({
|
||||
type: 'finish',
|
||||
reason: {
|
||||
kind: 'error',
|
||||
failure: { message: `${field} getter failed`, code: 'RESULT_GETTER_FAILED' },
|
||||
},
|
||||
})
|
||||
expect(cleanupLookups).toBe(0)
|
||||
})
|
||||
|
||||
it.each(['dispatch', 'iterator'] as const)('tags synchronous adapter %s failures without replacing their Error', async (boundary) => {
|
||||
it.each(['dispatch', 'iterator'] as const)('normalizes synchronous adapter %s failures', async (boundary) => {
|
||||
const original = new LlmError(`${boundary} failed`, 'BOUNDARY_FAILED')
|
||||
const adapter = new class extends LlmAdapter {
|
||||
stream(_options: GenerateOptions): AsyncIterable<StreamChunk> {
|
||||
@@ -329,339 +320,63 @@ describe('LlmService', () => {
|
||||
}()
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['test-model'], adapter)
|
||||
ctx.llm.registerAdapter(['test'], adapter)
|
||||
|
||||
const stream = ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] })
|
||||
let caught: unknown
|
||||
try {
|
||||
for await (const _chunk of stream) { /* drain */ }
|
||||
} catch (error: unknown) {
|
||||
caught = error
|
||||
}
|
||||
const chunks = await collect(ctx.llm.stream({
|
||||
provider: 'test',
|
||||
model: 'test',
|
||||
messages: [],
|
||||
}))
|
||||
|
||||
expect(caught).toBe(original)
|
||||
expect(isLlmAdapterFailure(stream, caught)).toBe(true)
|
||||
expect(llmFailureOf(stream, caught)).toEqual({
|
||||
message: `${boundary} failed`,
|
||||
code: 'BOUNDARY_FAILED',
|
||||
expect(chunks.at(-1)).toEqual({
|
||||
type: 'finish',
|
||||
reason: {
|
||||
kind: 'error',
|
||||
failure: { message: `${boundary} failed`, code: 'BOUNDARY_FAILED' },
|
||||
},
|
||||
})
|
||||
})
|
||||
|
||||
it('keeps structured provider facts beside a frozen third-party Error', async () => {
|
||||
const original = new LlmError('provider busy', 'RATE_LIMIT', {
|
||||
it('preserves structured LlmError facts in the terminal failure', async () => {
|
||||
const failure = new LlmError('provider busy', 'RATE_LIMIT', {
|
||||
status: 429,
|
||||
providerRetryAfterMs: 1_500,
|
||||
requestId: ProviderRequestId('req-7'),
|
||||
})
|
||||
Object.freeze(original)
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['test-provider'], new ThrowingAdapter(original))
|
||||
ctx.llm.registerAdapter(['test'], new ThrowingAdapter(failure))
|
||||
|
||||
const stream = ctx.llm.stream({ provider: 'test-provider', model: 'test-model', messages: [] })
|
||||
let caught: unknown
|
||||
try {
|
||||
for await (const _chunk of stream) { /* drain */ }
|
||||
} catch (error: unknown) {
|
||||
caught = error
|
||||
}
|
||||
const chunks = await collect(ctx.llm.stream({
|
||||
provider: 'test',
|
||||
model: 'test',
|
||||
messages: [],
|
||||
}))
|
||||
|
||||
expect(caught).toBe(original)
|
||||
expect(llmFailureOf(stream, caught)).toEqual({
|
||||
message: 'provider busy',
|
||||
code: 'RATE_LIMIT',
|
||||
status: 429,
|
||||
providerRetryAfterMs: 1_500,
|
||||
requestId: ProviderRequestId('req-7'),
|
||||
})
|
||||
})
|
||||
|
||||
it('does not trust retry facts carried by an unknown third-party Error', async () => {
|
||||
const carried = { message: 'busy', code: 'SERVER', status: 503 }
|
||||
const original = Object.assign(new Error('busy'), { failure: carried })
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['test-provider'], new ThrowingAdapter(original))
|
||||
|
||||
const stream = ctx.llm.stream({ provider: 'test-provider', model: 'test-model', messages: [] })
|
||||
await expect((async () => {
|
||||
for await (const _chunk of stream) { /* drain */ }
|
||||
})()).rejects.toBe(original)
|
||||
const facts = llmFailureOf(stream, original)
|
||||
carried.status = 500
|
||||
|
||||
expect(facts).toEqual({ message: 'busy', code: 'UNKNOWN' })
|
||||
expect(Object.isFrozen(facts)).toBe(true)
|
||||
expect(facts).not.toBe(carried)
|
||||
})
|
||||
|
||||
it('keeps validated failure facts across package copies with matching own codes', async () => {
|
||||
const original = Object.assign(new Error('provider busy'), {
|
||||
code: 'RATE_LIMIT',
|
||||
failure: {
|
||||
message: 'provider busy',
|
||||
code: 'RATE_LIMIT',
|
||||
status: 429,
|
||||
providerRetryAfterMs: 1_500,
|
||||
requestId: 'req-cross-copy',
|
||||
expect(chunks.at(-1)).toEqual({
|
||||
type: 'finish',
|
||||
reason: {
|
||||
kind: 'error',
|
||||
failure: {
|
||||
message: 'provider busy',
|
||||
code: 'RATE_LIMIT',
|
||||
status: 429,
|
||||
providerRetryAfterMs: 1_500,
|
||||
requestId: ProviderRequestId('req-7'),
|
||||
},
|
||||
},
|
||||
})
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['test-provider'], new ThrowingAdapter(original))
|
||||
|
||||
const stream = ctx.llm.stream({ provider: 'test-provider', model: 'test-model', messages: [] })
|
||||
await expect((async () => {
|
||||
for await (const _chunk of stream) { /* drain */ }
|
||||
})()).rejects.toBe(original)
|
||||
expect(llmFailureOf(stream, original)).toEqual({
|
||||
message: 'provider busy',
|
||||
code: 'RATE_LIMIT',
|
||||
status: 429,
|
||||
providerRetryAfterMs: 1_500,
|
||||
requestId: 'req-cross-copy',
|
||||
})
|
||||
})
|
||||
|
||||
it('keeps an unknown SDK Error exact without trusting its private code or accessors', async () => {
|
||||
const original = Object.assign(new Error('socket closed'), { code: 'ECONNRESET' })
|
||||
Object.defineProperty(original, 'failure', {
|
||||
get() { throw new Error('SDK failure accessor must not run') },
|
||||
})
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['test-provider'], new ThrowingAdapter(original))
|
||||
|
||||
const stream = ctx.llm.stream({ provider: 'test-provider', model: 'test-model', messages: [] })
|
||||
await expect((async () => {
|
||||
for await (const _chunk of stream) { /* drain */ }
|
||||
})()).rejects.toBe(original)
|
||||
|
||||
expect(original.code).toBe('ECONNRESET')
|
||||
expect(llmFailureOf(stream, original)).toEqual({ message: 'socket closed', code: 'UNKNOWN' })
|
||||
})
|
||||
|
||||
it('keeps an SDK Error exact when its message accessor is hostile', async () => {
|
||||
const original = Object.defineProperty(new Error(), 'message', {
|
||||
get() { throw new Error('SDK message accessor trap') },
|
||||
})
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['test-provider'], new ThrowingAdapter(original))
|
||||
const stream = ctx.llm.stream({ provider: 'test-provider', model: 'test-model', messages: [] })
|
||||
|
||||
await expect((async () => {
|
||||
for await (const _chunk of stream) { /* drain */ }
|
||||
})()).rejects.toBe(original)
|
||||
expect(llmFailureOf(stream, original)).toEqual({ message: 'LLM adapter failed', code: 'UNKNOWN' })
|
||||
})
|
||||
|
||||
it('keeps an SDK Error exact without trusting accessor-backed carried facts', async () => {
|
||||
const original = Object.assign(new Error('busy'), {
|
||||
failure: { message: 'busy', code: 'SERVER', status: 503 },
|
||||
})
|
||||
Object.defineProperty(original, 'code', {
|
||||
get() { throw new Error('SDK code accessor must not escape') },
|
||||
})
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['test-provider'], new ThrowingAdapter(original))
|
||||
const stream = ctx.llm.stream({ provider: 'test-provider', model: 'test-model', messages: [] })
|
||||
|
||||
await expect((async () => {
|
||||
for await (const _chunk of stream) { /* drain */ }
|
||||
})()).rejects.toBe(original)
|
||||
expect(llmFailureOf(stream, original)).toEqual({ message: 'busy', code: 'UNKNOWN' })
|
||||
})
|
||||
|
||||
it('does not trust carried facts matched only by an inherited code', async () => {
|
||||
class InheritedCodeError extends Error {
|
||||
get code(): string { return 'SERVER' }
|
||||
}
|
||||
const original = Object.assign(new InheritedCodeError('busy'), {
|
||||
failure: { message: 'busy', code: 'SERVER', status: 503 },
|
||||
})
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['test-provider'], new ThrowingAdapter(original))
|
||||
const stream = ctx.llm.stream({ provider: 'test-provider', model: 'test-model', messages: [] })
|
||||
|
||||
await expect((async () => {
|
||||
for await (const _chunk of stream) { /* drain */ }
|
||||
})()).rejects.toBe(original)
|
||||
expect(llmFailureOf(stream, original)).toEqual({ message: 'busy', code: 'UNKNOWN' })
|
||||
})
|
||||
|
||||
it('keeps an SDK Error exact when code descriptor inspection is trapped', async () => {
|
||||
const target = Object.assign(new Error('busy'), {
|
||||
code: 'SERVER',
|
||||
failure: { message: 'busy', code: 'SERVER', status: 503 },
|
||||
})
|
||||
const original = new Proxy(target, {
|
||||
getOwnPropertyDescriptor(value, property) {
|
||||
if (property === 'code') throw new Error('SDK code descriptor trap')
|
||||
return Reflect.getOwnPropertyDescriptor(value, property)
|
||||
},
|
||||
})
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['test-provider'], new ThrowingAdapter(original))
|
||||
const stream = ctx.llm.stream({ provider: 'test-provider', model: 'test-model', messages: [] })
|
||||
|
||||
await expect((async () => {
|
||||
for await (const _chunk of stream) { /* drain */ }
|
||||
})()).rejects.toBe(original)
|
||||
expect(llmFailureOf(stream, original)).toEqual({ message: 'busy', code: 'UNKNOWN' })
|
||||
})
|
||||
|
||||
it('falls back safely when SDK objects trap failure inspection or expose malformed facts', async () => {
|
||||
const propertyTrap = new Proxy(new HarnessError('descriptor trapped', 'SERVER'), {
|
||||
getOwnPropertyDescriptor(target, property) {
|
||||
if (property === 'failure') throw new Error('SDK descriptor trap')
|
||||
return Reflect.getOwnPropertyDescriptor(target, property)
|
||||
},
|
||||
})
|
||||
const throwingFacts = Object.create(null) as Record<string, unknown>
|
||||
Object.defineProperty(throwingFacts, 'message', {
|
||||
get() { throw new Error('SDK fact getter trap') },
|
||||
})
|
||||
const carrying = (message: string, failure: unknown): HarnessError => Object.defineProperty(
|
||||
new HarnessError(message, 'SERVER'),
|
||||
'failure',
|
||||
{ value: failure },
|
||||
)
|
||||
const factGetter = carrying('fact getter failed', throwingFacts)
|
||||
const malformed = carrying('malformed facts', { message: 'provider busy', code: 'SERVER', requestId: 1 })
|
||||
const primitive = carrying('primitive facts', 1)
|
||||
const nullFacts = carrying('null facts', null)
|
||||
const mismatched = carrying('mismatched facts', { message: 'busy', code: 'RATE_LIMIT' })
|
||||
|
||||
for (const [original, expectedMessage] of [
|
||||
[propertyTrap, 'descriptor trapped'],
|
||||
[factGetter, 'fact getter failed'],
|
||||
[malformed, 'malformed facts'],
|
||||
[primitive, 'primitive facts'],
|
||||
[nullFacts, 'null facts'],
|
||||
[mismatched, 'mismatched facts'],
|
||||
] as const) {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['test-provider'], new ThrowingAdapter(original))
|
||||
const stream = ctx.llm.stream({ provider: 'test-provider', model: 'test-model', messages: [] })
|
||||
|
||||
await expect((async () => {
|
||||
for await (const _chunk of stream) { /* drain */ }
|
||||
})()).rejects.toBe(original)
|
||||
expect(llmFailureOf(stream, original)).toEqual({ message: expectedMessage, code: 'SERVER' })
|
||||
}
|
||||
})
|
||||
|
||||
it('retains a stable code from a HarnessError without requiring LlmError facts', async () => {
|
||||
const original = new HarnessError('stable adapter failure', 'ADAPTER_STABLE')
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['test-provider'], new ThrowingAdapter(original))
|
||||
const stream = ctx.llm.stream({ provider: 'test-provider', model: 'test-model', messages: [] })
|
||||
|
||||
await expect((async () => {
|
||||
for await (const _chunk of stream) { /* drain */ }
|
||||
})()).rejects.toBe(original)
|
||||
expect(llmFailureOf(stream, original)).toEqual({
|
||||
message: 'stable adapter failure',
|
||||
code: 'ADAPTER_STABLE',
|
||||
})
|
||||
expect(llmFailureOf(stream, 'not an Error')).toBeUndefined()
|
||||
expect(llmFailureOf({ [Symbol.asyncIterator]: () => stream[Symbol.asyncIterator]() }, original)).toBeUndefined()
|
||||
})
|
||||
|
||||
it('keeps a nested adapter failure scoped to the nested model call', async () => {
|
||||
const original = new LlmError('nested provider failed', 'NESTED_FAILED')
|
||||
const outer = new RecordingAdapter(SCRIPT)
|
||||
const nested = new ThrowingAdapter(original)
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['outer'], outer)
|
||||
ctx.llm.registerAdapter(['nested'], nested)
|
||||
let nestedStream: AsyncIterable<StreamChunk> | undefined
|
||||
ctx.on('llm/stream', (options, next) => {
|
||||
if (options.provider !== 'outer') return next()
|
||||
return (async function* () {
|
||||
nestedStream = ctx.llm.stream({ provider: 'nested', model: 'nested', messages: [] })
|
||||
yield * nestedStream
|
||||
})()
|
||||
})
|
||||
|
||||
const outerStream = ctx.llm.stream({ provider: 'outer', model: 'outer', messages: [] })
|
||||
let caught: unknown
|
||||
try {
|
||||
for await (const _chunk of outerStream) { /* drain */ }
|
||||
} catch (error: unknown) {
|
||||
caught = error
|
||||
}
|
||||
|
||||
expect(caught).toBe(original)
|
||||
expect(nestedStream).toBeDefined()
|
||||
expect(isLlmAdapterFailure(nestedStream!, caught)).toBe(true)
|
||||
expect(isLlmAdapterFailure(outerStream, caught)).toBe(false)
|
||||
expect(outer.lastOptions).toBeUndefined()
|
||||
})
|
||||
|
||||
it('keeps call scopes distinct when middleware reuses an iterable', async () => {
|
||||
const firstFailure = new LlmError('first provider failed', 'FIRST_FAILED')
|
||||
const secondFailure = new LlmError('second provider failed', 'SECOND_FAILED')
|
||||
const delegates: AsyncIterable<StreamChunk>[] = []
|
||||
const shared: AsyncIterable<StreamChunk> = {
|
||||
[Symbol.asyncIterator](): AsyncIterator<StreamChunk> {
|
||||
const delegate = delegates.shift()
|
||||
if (delegate === undefined) throw new Error('shared stream has no call delegate')
|
||||
return delegate[Symbol.asyncIterator]()
|
||||
},
|
||||
}
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['first'], new ThrowingAdapter(firstFailure))
|
||||
ctx.llm.registerAdapter(['second'], new ThrowingAdapter(secondFailure))
|
||||
ctx.on('llm/stream', (_options, next) => {
|
||||
delegates.push(next())
|
||||
return shared
|
||||
})
|
||||
|
||||
const firstStream = ctx.llm.stream({ provider: 'first', model: 'first', messages: [] })
|
||||
const secondStream = ctx.llm.stream({ provider: 'second', model: 'second', messages: [] })
|
||||
const catchFailure = async (stream: AsyncIterable<StreamChunk>): Promise<unknown> => {
|
||||
try {
|
||||
for await (const _chunk of stream) { /* drain */ }
|
||||
} catch (error: unknown) {
|
||||
return error
|
||||
}
|
||||
return new Error('expected adapter to fail')
|
||||
}
|
||||
|
||||
expect(firstStream).not.toBe(secondStream)
|
||||
const firstCaught = await catchFailure(firstStream)
|
||||
expect(firstCaught).toBe(firstFailure)
|
||||
expect(isLlmAdapterFailure(firstStream, firstCaught)).toBe(true)
|
||||
expect(isLlmAdapterFailure(secondStream, firstCaught)).toBe(false)
|
||||
const secondCaught = await catchFailure(secondStream)
|
||||
expect(secondCaught).toBe(secondFailure)
|
||||
expect(isLlmAdapterFailure(secondStream, secondCaught)).toBe(true)
|
||||
expect(isLlmAdapterFailure(firstStream, secondCaught)).toBe(false)
|
||||
expect(delegates).toHaveLength(0)
|
||||
})
|
||||
|
||||
it('propagates a rejected next promptly without awaiting a non-settling return', async () => {
|
||||
const original = new LlmError('provider failed', 'PROVIDER_FAILED')
|
||||
let cleanupCalls = 0
|
||||
it('normalizes arbitrary adapter rejections without throwing them downstream', async () => {
|
||||
const adapter = new class extends LlmAdapter {
|
||||
stream(_options: GenerateOptions): AsyncIterable<StreamChunk> {
|
||||
return {
|
||||
[Symbol.asyncIterator](): AsyncIterator<StreamChunk> {
|
||||
return {
|
||||
next: () => Promise.reject(original),
|
||||
return: () => {
|
||||
cleanupCalls += 1
|
||||
return new Promise<IteratorResult<StreamChunk>>(() => {})
|
||||
},
|
||||
// Third-party adapters can reject with arbitrary values.
|
||||
// oxlint-disable-next-line typescript/prefer-promise-reject-errors
|
||||
next: () => Promise.reject('plain provider failure'),
|
||||
}
|
||||
},
|
||||
}
|
||||
@@ -669,30 +384,73 @@ describe('LlmService', () => {
|
||||
}()
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['test-model'], adapter)
|
||||
ctx.llm.registerAdapter(['test'], adapter)
|
||||
|
||||
const stream = ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] })
|
||||
const failure = (async (): Promise<unknown> => {
|
||||
try {
|
||||
for await (const _chunk of stream) { /* drain */ }
|
||||
} catch (error: unknown) {
|
||||
return error
|
||||
}
|
||||
return new Error('expected adapter iteration to fail')
|
||||
})()
|
||||
let timer: ReturnType<typeof setTimeout> | undefined
|
||||
const timeout = new Promise<Error>((resolve) => {
|
||||
timer = setTimeout(() => { resolve(new Error('adapter failure did not settle promptly')) }, 100)
|
||||
const chunks = await collect(ctx.llm.stream({
|
||||
provider: 'test',
|
||||
model: 'test',
|
||||
messages: [],
|
||||
}))
|
||||
|
||||
expect(chunks.at(-1)).toEqual({
|
||||
type: 'finish',
|
||||
reason: {
|
||||
kind: 'error',
|
||||
failure: { message: 'plain provider failure', code: 'UNKNOWN' },
|
||||
},
|
||||
})
|
||||
const caught = await Promise.race([failure, timeout])
|
||||
if (timer !== undefined) clearTimeout(timer)
|
||||
|
||||
expect(caught).toBe(original)
|
||||
expect(isLlmAdapterFailure(stream, caught)).toBe(true)
|
||||
expect(cleanupCalls).toBe(0)
|
||||
})
|
||||
|
||||
it('awaits one adapter return on downstream close and leaves its rejection unclassified', async () => {
|
||||
it('maps adapter failure to aborted when the request signal is aborted', async () => {
|
||||
const controller = new AbortController()
|
||||
controller.abort('cancelled')
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['test'], new ThrowingAdapter(new Error('stopped')))
|
||||
|
||||
const chunks = await collect(ctx.llm.stream({
|
||||
provider: 'test',
|
||||
model: 'test',
|
||||
messages: [],
|
||||
signal: controller.signal,
|
||||
}))
|
||||
|
||||
expect(chunks.at(-1)).toMatchObject({
|
||||
type: 'finish',
|
||||
reason: { kind: 'aborted', failure: { message: 'stopped' } },
|
||||
})
|
||||
})
|
||||
|
||||
it('leaves middleware and consumer failures thrown', async () => {
|
||||
const middlewareFailure = new Error('middleware failed')
|
||||
const middlewareCtx = new Context()
|
||||
await middlewareCtx.plugin(LlmService)
|
||||
middlewareCtx.llm.registerAdapter(['test'], new ScriptedAdapter(SCRIPT))
|
||||
middlewareCtx.on('llm/stream', () => (async function* () {
|
||||
throw middlewareFailure
|
||||
})())
|
||||
await expect(collect(middlewareCtx.llm.stream({
|
||||
provider: 'test',
|
||||
model: 'test',
|
||||
messages: [],
|
||||
}))).rejects.toBe(middlewareFailure)
|
||||
|
||||
const consumerFailure = new Error('consumer failed')
|
||||
const consumerCtx = new Context()
|
||||
await consumerCtx.plugin(LlmService)
|
||||
consumerCtx.llm.registerAdapter(['test'], new ScriptedAdapter(SCRIPT))
|
||||
await expect((async () => {
|
||||
for await (const _chunk of consumerCtx.llm.stream({
|
||||
provider: 'test',
|
||||
model: 'test',
|
||||
messages: [],
|
||||
})) {
|
||||
throw consumerFailure
|
||||
}
|
||||
})()).rejects.toBe(consumerFailure)
|
||||
})
|
||||
|
||||
it('awaits adapter cleanup on downstream close and leaves cleanup failure thrown', async () => {
|
||||
const cleanup = new Error('cleanup failed')
|
||||
let cleanupCalls = 0
|
||||
const adapter = new class extends LlmAdapter {
|
||||
@@ -712,95 +470,18 @@ describe('LlmService', () => {
|
||||
}()
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['test-model'], adapter)
|
||||
ctx.llm.registerAdapter(['test'], adapter)
|
||||
|
||||
const stream = ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] })
|
||||
let caught: unknown
|
||||
try {
|
||||
for await (const _chunk of stream) break
|
||||
} catch (error: unknown) {
|
||||
caught = error
|
||||
}
|
||||
|
||||
expect(caught).toBe(cleanup)
|
||||
expect(isLlmAdapterFailure(stream, caught)).toBe(false)
|
||||
await expect((async () => {
|
||||
for await (const _chunk of ctx.llm.stream({
|
||||
provider: 'test',
|
||||
model: 'test',
|
||||
messages: [],
|
||||
})) break
|
||||
})()).rejects.toBe(cleanup)
|
||||
expect(cleanupCalls).toBe(1)
|
||||
})
|
||||
|
||||
it('allows downstream close when the adapter iterator has no return method', async () => {
|
||||
const adapter = new class extends LlmAdapter {
|
||||
stream(_options: GenerateOptions): AsyncIterable<StreamChunk> {
|
||||
return {
|
||||
[Symbol.asyncIterator](): AsyncIterator<StreamChunk> {
|
||||
return { next: () => Promise.resolve({ done: false, value: SCRIPT[0]! }) }
|
||||
},
|
||||
}
|
||||
}
|
||||
}()
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['test-model'], adapter)
|
||||
|
||||
let chunks = 0
|
||||
for await (const _chunk of ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] })) {
|
||||
chunks += 1
|
||||
break
|
||||
}
|
||||
|
||||
expect(chunks).toBe(1)
|
||||
})
|
||||
|
||||
it('normalizes and tags non-Error adapter failures once', async () => {
|
||||
const adapter = new class extends LlmAdapter {
|
||||
stream(_options: GenerateOptions): AsyncIterable<StreamChunk> {
|
||||
return {
|
||||
[Symbol.asyncIterator](): AsyncIterator<StreamChunk> {
|
||||
// Third-party adapters can reject with arbitrary values.
|
||||
// oxlint-disable-next-line typescript/prefer-promise-reject-errors
|
||||
return { next: () => Promise.reject('plain provider failure') }
|
||||
},
|
||||
}
|
||||
}
|
||||
}()
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['test-model'], adapter)
|
||||
|
||||
const stream = ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] })
|
||||
let caught: unknown
|
||||
try {
|
||||
for await (const _chunk of stream) { /* drain */ }
|
||||
} catch (error: unknown) {
|
||||
caught = error
|
||||
}
|
||||
|
||||
expect(caught).toBeInstanceOf(HarnessError)
|
||||
expect(caught).toMatchObject({ code: 'UNKNOWN', cause: 'plain provider failure' })
|
||||
expect(isLlmAdapterFailure(stream, caught)).toBe(true)
|
||||
})
|
||||
|
||||
it('does not tag a failure thrown downstream while consuming adapter output', async () => {
|
||||
const downstream = new Error('consumer failed')
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
ctx.llm.registerAdapter(['test-model'], new ScriptedAdapter(SCRIPT))
|
||||
|
||||
const stream = ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] })
|
||||
let caught: unknown
|
||||
try {
|
||||
for await (const _chunk of stream) throw downstream
|
||||
} catch (error: unknown) {
|
||||
caught = error
|
||||
}
|
||||
|
||||
expect(caught).toBe(downstream)
|
||||
expect(isLlmAdapterFailure(stream, caught)).toBe(false)
|
||||
expect(isLlmAdapterFailure(new ScriptedAdapter(SCRIPT).stream({
|
||||
provider: 'unbound', model: 'unbound', messages: [],
|
||||
}), caught)).toBe(false)
|
||||
expect(isLlmAdapterFailure(stream, 'consumer failed')).toBe(false)
|
||||
})
|
||||
|
||||
it('unregisters adapters when the owning fiber is disposed (HMR safety)', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
@@ -1064,15 +745,15 @@ describe('LlmService', () => {
|
||||
ctx.llm.registerAdapter(['route'], adapter)
|
||||
const prepared = await ctx.llm.prepareCall({ provider: 'route', model: 'model' })
|
||||
expect(Object.isFrozen(prepared.config)).toBe(true)
|
||||
const stream = prepared.stream({
|
||||
expect(() => prepared.stream({
|
||||
...prepared.config,
|
||||
model: 'other',
|
||||
messages: [],
|
||||
})
|
||||
|
||||
await expect((async () => {
|
||||
for await (const _chunk of stream) { /* drain */ }
|
||||
})()).rejects.toMatchObject({ code: 'INVALID_PREPARED_CALL' })
|
||||
})).toThrow(expect.objectContaining({ code: 'INVALID_PREPARED_CALL' }))
|
||||
await collect(prepared.stream({
|
||||
...prepared.config,
|
||||
messages: [],
|
||||
}))
|
||||
expect(() => prepared.stream({
|
||||
...prepared.config,
|
||||
messages: [],
|
||||
|
||||
Reference in New Issue
Block a user