Merge remote-tracking branch 'origin/master' into worktree/web-session-model-selector
# Conflicts: # .agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml # .agents/notes/implemented/architecture/2026-07-23-client-plugin-loading-model.i18n.yaml # apps/cli/src/web.ts # apps/web/tests/session-title.snapshot.ts # apps/web/tests/smoke-fixture.e2e.ts # packages/client/connection/src/client/api.ts # packages/client/connection/src/client/fixture.ts # packages/client/connection/src/client/index.ts # packages/client/runtime/src/client/index.ts # packages/client/runtime/src/client/sessions/conversation.ts # packages/client/runtime/src/client/sessions/session.ts # packages/client/runtime/tests/fake-api.ts # packages/client/ui-conversation/src/client/contract/slots.ts # packages/client/ui-conversation/src/client/index.ts # packages/client/ui-conversation/src/client/skeleton/ConversationRoot.tsx # packages/client/ui-conversation/src/client/skeleton/InputBar.module.css # packages/client/ui-conversation/src/client/skeleton/InputBar.tsx # packages/client/ui-conversation/tests/chat-stats-bash-sample.spec.tsx # packages/client/ui-conversation/tests/chat-toolview-slot.spec.tsx # packages/client/ui-conversation/tests/chat-view.spec.tsx # packages/client/ui-conversation/tests/gate-branch-tails.spec.tsx # packages/client/ui-conversation/tests/skeleton-branches.spec.tsx # packages/client/ui-conversation/tests/skeleton.spec.tsx # packages/host/apiproxy/README.md # packages/host/apiproxy/src/api-proxy.ts # packages/host/apiproxy/src/api/rpc.schema.ts # packages/host/apiproxy/src/api/rpc.ts # packages/host/apiproxy/tests/api-proxy-models.spec.ts # packages/host/apiproxy/tests/rpc-schemas.spec.ts # packages/host/runtime/README.md # packages/llm/llm-deepseek/README.md # scripts/translation-pairing.manifest.json # tsconfig.client.json
This commit is contained in:
Yichen Jiang
@@ -49,7 +49,7 @@ Every request carries the shared attribution header from dsh-llm's `attributionH
|
||||
|
||||
## Errors
|
||||
|
||||
Non-2xx responses throw `LlmError` with stable codes: `AUTH` (401/403), `QUOTA` (a response whose provider details identify exhausted quota, balance, or credits), `RATE_LIMIT` (other 429s), `CONTEXT_WINDOW_EXCEEDED` (a 400 whose provider code, type, or message identifies context overflow), `INVALID_REQUEST` (other 400s), `SERVER` (5xx), `HTTP_<status>` otherwise. Its serializable `failure` retains the HTTP status plus a valid positive `Retry-After` seconds/date delay and `x-request-id` / `x-deepseek-request-id` when present. A pre-response transport failure (DNS, refused connection, TLS, proxy) throws `TRANSPORT` naming the configured endpoint and chaining the original rejection as `cause`; caller aborts throw `ABORTED`, and the loop's cancellation signal remains authoritative. Protocol violations throw `STREAM_CLOSED` (no `[DONE]`) or `MALFORMED_RESPONSE` (bad JSON payload). Unknown wire `finish_reason`s (e.g. `content_filter`, `insufficient_system_resource`) become `finish {kind: 'error', failure}` chunks.
|
||||
Non-2xx responses throw `LlmError` with stable codes: `AUTH` (401/403), `QUOTA` (a response whose provider details identify exhausted quota, balance, or credits), `RATE_LIMIT` (other 429s), `CONTEXT_WINDOW_EXCEEDED` (a 400 whose provider code, type, or message identifies context overflow), `INVALID_REQUEST` (other 400s), `SERVER` (5xx), `HTTP_<status>` otherwise. Its serializable `failure` retains the HTTP status plus a valid positive `Retry-After` seconds/date delay and `x-request-id` / `x-deepseek-request-id` when present. A pre-response transport failure (DNS, refused connection, TLS, proxy) throws `TRANSPORT` naming the configured endpoint and chaining the original rejection as `cause`; caller aborts throw `ABORTED`, and the loop's cancellation signal remains authoritative. Protocol violations throw `STREAM_CLOSED` (no `[DONE]`) or `MALFORMED_RESPONSE` (bad JSON payload). Unknown wire `finish_reason`s (e.g. `content_filter`, `insufficient_system_resource`) become `finish {kind: 'error', failure}` chunks, and a completed stream whose `stop` (or absent) finish opened no content blocks becomes a `finish {kind: 'error'}` with code `EMPTY_RESPONSE` (retried by default policy).
|
||||
|
||||
## Testing
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
* @module dsh-llm-deepseek/translate
|
||||
*/
|
||||
|
||||
import { CallId, LlmError } from '@deepseek-ai/dsh-llm'
|
||||
import { CallId, EMPTY_RESPONSE_CODE, LlmError } from '@deepseek-ai/dsh-llm'
|
||||
import type { ContentBlock, FinishReason, StreamChunk, TokenUsage } from '@deepseek-ai/dsh-llm'
|
||||
import { DONE } from './sse.ts'
|
||||
import type { WireChunk, WireUsage } from './types.ts'
|
||||
@@ -80,6 +80,8 @@ function closeBlock(block: OpenBlock): ContentBlock {
|
||||
* Malformed JSON payloads abort the stream with `MALFORMED_RESPONSE`.
|
||||
* @param payloads - SSE data payloads from {@link parseSse}, `[DONE]`-terminated.
|
||||
* @returns deltas as they arrive; `block-end`s, `usage`, and `finish` are all deferred to the `[DONE]` sentinel.
|
||||
* A `stop` (or absent) finish with no opened blocks is a degenerate provider completion and maps to an
|
||||
* `EMPTY_RESPONSE` error finish instead of a successful empty message.
|
||||
*/
|
||||
export async function* translate(payloads: AsyncIterable<string>): AsyncGenerator<StreamChunk> {
|
||||
let nextIndex = 0
|
||||
@@ -102,7 +104,16 @@ export async function* translate(payloads: AsyncIterable<string>): AsyncGenerato
|
||||
yield { type: 'block-end', index: block.index, block: closeBlock(block) }
|
||||
}
|
||||
if (pendingUsage) yield { type: 'usage', usage: pendingUsage }
|
||||
yield { type: 'finish', reason: pendingFinish ?? { kind: 'stop' } }
|
||||
const reason = pendingFinish ?? { kind: 'stop' as const }
|
||||
yield {
|
||||
type: 'finish',
|
||||
reason: reason.kind === 'stop' && order.length === 0
|
||||
? {
|
||||
kind: 'error',
|
||||
failure: { message: 'model returned a completed response with no content', code: EMPTY_RESPONSE_CODE },
|
||||
}
|
||||
: reason,
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { BlockAssembler, LlmError } from '@deepseek-ai/dsh-llm'
|
||||
import { BlockAssembler, EMPTY_RESPONSE_CODE, LlmError } from '@deepseek-ai/dsh-llm'
|
||||
import type { StreamChunk } from '@deepseek-ai/dsh-llm'
|
||||
import { DONE } from '../src/sse.ts'
|
||||
import { mapFinishReason, mapUsage, translate } from '../src/translate.ts'
|
||||
@@ -203,7 +203,50 @@ describe('translate: finish and usage handling', () => {
|
||||
|
||||
it('handles chunks with no choices at all', async () => {
|
||||
const chunks = await collect(translate(feed({}, DONE)))
|
||||
expect(chunks).toEqual([{ type: 'finish', reason: { kind: 'stop' } }])
|
||||
expect(chunks).toEqual([{
|
||||
type: 'finish',
|
||||
reason: {
|
||||
kind: 'error',
|
||||
failure: { message: 'model returned a completed response with no content', code: EMPTY_RESPONSE_CODE },
|
||||
},
|
||||
}])
|
||||
})
|
||||
|
||||
it('classifies an explicit stop with no opened blocks as EMPTY_RESPONSE, after usage', async () => {
|
||||
const chunks = await collect(translate(feed(
|
||||
firstChunk,
|
||||
{ choices: [{ delta: {}, finish_reason: 'stop' }], usage: { prompt_tokens: 7, completion_tokens: 0 } },
|
||||
DONE,
|
||||
)))
|
||||
expect(chunks).toEqual([
|
||||
{ type: 'usage', usage: { inputTokens: 7, outputTokens: 0 } },
|
||||
{
|
||||
type: 'finish',
|
||||
reason: {
|
||||
kind: 'error',
|
||||
failure: { message: 'model returned a completed response with no content', code: EMPTY_RESPONSE_CODE },
|
||||
},
|
||||
},
|
||||
])
|
||||
})
|
||||
|
||||
it('keeps a reasoning-only stream a successful stop (any opened block counts)', async () => {
|
||||
const chunks = await collect(translate(feed(
|
||||
firstChunk,
|
||||
{ choices: [{ delta: { content: null, reasoning_content: 'mull' } }] },
|
||||
{ choices: [{ delta: {}, finish_reason: 'stop' }] },
|
||||
DONE,
|
||||
)))
|
||||
expect(chunks.at(-1)).toEqual({ type: 'finish', reason: { kind: 'stop' } })
|
||||
})
|
||||
|
||||
it('leaves non-stop finishes unclassified even with no opened blocks', async () => {
|
||||
const chunks = await collect(translate(feed(
|
||||
firstChunk,
|
||||
{ choices: [{ delta: {}, finish_reason: 'length' }] },
|
||||
DONE,
|
||||
)))
|
||||
expect(chunks.at(-1)).toEqual({ type: 'finish', reason: { kind: 'max-tokens' } })
|
||||
})
|
||||
})
|
||||
|
||||
|
||||
@@ -45,7 +45,7 @@ If a listener rewrites assembled assistant content, the loop drops replay state
|
||||
## Vocabulary differences
|
||||
|
||||
- pi-ai tool-call arguments are parsed objects; the harness stores raw JSON strings. The adapter parses input and re-stringifies output.
|
||||
- pi-ai reports failures as in-stream error events; these map to `finish {kind:'error'|'aborted', failure}` chunks. Provider-specific error text distinguishes terminal `QUOTA` from transient `RATE_LIMIT`, while text and usage signals evaluated against the resolved model's context window normalize overflow to `CONTEXT_WINDOW_EXCEEDED`.
|
||||
- pi-ai reports failures as in-stream error events; these map to `finish {kind:'error'|'aborted', failure}` chunks. Provider-specific error text distinguishes terminal `QUOTA` from transient `RATE_LIMIT`, while text and usage signals evaluated against the resolved model's context window normalize overflow to `CONTEXT_WINDOW_EXCEEDED`. A terminal `stop` whose message carries no content blocks maps to a `finish {kind:'error'}` with code `EMPTY_RESPONSE` (retried by default policy) instead of a successful empty message.
|
||||
- pi-ai folds reasoning tokens into output usage; there is no separate reasoning count to map.
|
||||
- `GenerateOptions.stop` is rejected with `UNSUPPORTED_OPTION` because pi-ai's common streaming surface cannot guarantee it across providers.
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
* @module dsh-llm-pi-ai/stream
|
||||
*/
|
||||
|
||||
import { CallId, CONTEXT_WINDOW_EXCEEDED_CODE, isContextWindowExceededError, isQuotaExceededError, LlmError, QUOTA_EXCEEDED_CODE } from '@deepseek-ai/dsh-llm'
|
||||
import { CallId, CONTEXT_WINDOW_EXCEEDED_CODE, EMPTY_RESPONSE_CODE, isContextWindowExceededError, isQuotaExceededError, LlmError, QUOTA_EXCEEDED_CODE } from '@deepseek-ai/dsh-llm'
|
||||
import type { FinishReason, StreamChunk, TokenUsage } from '@deepseek-ai/dsh-llm'
|
||||
import { isContextOverflow } from '@earendil-works/pi-ai'
|
||||
import type { AssistantMessage, AssistantMessageEvent, Usage as PiUsage } from '@earendil-works/pi-ai'
|
||||
@@ -48,7 +48,8 @@ function classifyPiAiError(message: string): string {
|
||||
* @param contextWindow - resolved catalog capacity for usage-based overflow detection.
|
||||
* @returns the mapped harness reason. Recognized error text, `stop` usage above
|
||||
* `contextWindow`, and zero-output `length` usage that fills the window map
|
||||
* to `CONTEXT_WINDOW_EXCEEDED`.
|
||||
* to `CONTEXT_WINDOW_EXCEEDED`; a `stop` with no content blocks maps to an
|
||||
* `EMPTY_RESPONSE` error.
|
||||
*/
|
||||
export function mapStopReason(message: AssistantMessage, contextWindow?: number): FinishReason {
|
||||
const piAiOverflow = isContextOverflow(message, contextWindow)
|
||||
@@ -66,7 +67,19 @@ export function mapStopReason(message: AssistantMessage, contextWindow?: number)
|
||||
}
|
||||
|
||||
switch (message.stopReason) {
|
||||
case 'stop': return { kind: 'stop' }
|
||||
case 'stop':
|
||||
// A terminal stop that produced no content blocks is a degenerate
|
||||
// provider completion, not a successful (empty) assistant message.
|
||||
if (message.content.length === 0) {
|
||||
return {
|
||||
kind: 'error',
|
||||
failure: {
|
||||
message: `model "${message.model}" returned a completed response with no content`,
|
||||
code: EMPTY_RESPONSE_CODE,
|
||||
},
|
||||
}
|
||||
}
|
||||
return { kind: 'stop' }
|
||||
case 'length': return { kind: 'max-tokens' }
|
||||
case 'toolUse': return { kind: 'tool-calls' }
|
||||
case 'aborted': return {
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { CallId, CONTEXT_WINDOW_EXCEEDED_CODE, LlmError } from '@deepseek-ai/dsh-llm'
|
||||
import { CallId, CONTEXT_WINDOW_EXCEEDED_CODE, EMPTY_RESPONSE_CODE, LlmError } from '@deepseek-ai/dsh-llm'
|
||||
import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm'
|
||||
import type { AssistantMessage, AssistantMessageEvent, Usage } from '@earendil-works/pi-ai'
|
||||
import { toPiContext } from '../src/context.ts'
|
||||
@@ -520,7 +520,22 @@ describe('mapStopReason / mapUsage', () => {
|
||||
['toolUse', { kind: 'tool-calls' }],
|
||||
['aborted', { kind: 'aborted', failure: { message: 'pi-ai stream aborted', code: 'ABORTED' } }],
|
||||
] as const)('maps %s', (stopReason, expected) => {
|
||||
expect(mapStopReason(assistant({ stopReason }))).toEqual(expected)
|
||||
expect(mapStopReason(assistant({ stopReason, content: [{ type: 'text', text: 'ok' }] }))).toEqual(expected)
|
||||
})
|
||||
|
||||
it('classifies a completed stop with no content as an EMPTY_RESPONSE error', () => {
|
||||
expect(mapStopReason(assistant({ stopReason: 'stop' }))).toEqual({
|
||||
kind: 'error',
|
||||
failure: {
|
||||
message: 'model "deepseek-v4-flash" returned a completed response with no content',
|
||||
code: EMPTY_RESPONSE_CODE,
|
||||
},
|
||||
})
|
||||
})
|
||||
|
||||
it('keeps a thinking-only stop successful (any block counts as content)', () => {
|
||||
expect(mapStopReason(assistant({ stopReason: 'stop', content: [{ type: 'thinking', thinking: 'mull' }] })))
|
||||
.toEqual({ kind: 'stop' })
|
||||
})
|
||||
|
||||
it('defaults the error message when pi-ai omits it', () => {
|
||||
@@ -580,7 +595,9 @@ describe('mapStopReason / mapUsage', () => {
|
||||
})
|
||||
|
||||
it('uses the resolved context window for silent and length-stop overflows', () => {
|
||||
const silent = assistant({ stopReason: 'stop', usage: usage(101, 0) })
|
||||
// Non-empty content keeps the no-window branch on the successful stop path
|
||||
// (an empty stop is EMPTY_RESPONSE, covered above); overflow wins over both.
|
||||
const silent = assistant({ stopReason: 'stop', usage: usage(101, 0), content: [{ type: 'text', text: 'x' }] })
|
||||
expect(mapStopReason(silent)).toEqual({ kind: 'stop' })
|
||||
expect(mapStopReason(silent, 100)).toEqual({
|
||||
kind: 'error',
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
Function plugin that retries selected transient model-request failures on the agent loop's closed-step recovery seam. It does not wrap `ctx.llm.stream()`: every adapter call remains one provider attempt, and every retry opens a fresh numbered step.
|
||||
|
||||
The default policy permits two retries for `RATE_LIMIT`, `SERVER`, `TIMEOUT`, and `TRANSPORT`, using bounded exponential backoff from 500 ms to 10 seconds with 10 percent jitter. Delay bounds must fit Node's supported timer range. A valid `providerRetryAfterMs` replaces local backoff when it is within the configured cap; an over-cap instruction delegates to the next recovery policy instead.
|
||||
The default policy permits two retries for `EMPTY_RESPONSE`, `RATE_LIMIT`, `SERVER`, `TIMEOUT`, and `TRANSPORT`, using bounded exponential backoff from 500 ms to 10 seconds with 10 percent jitter. `EMPTY_RESPONSE` is the adapters' classification of a degenerate provider completion (a terminal stop with zero content blocks); the attempt produced nothing durable, so repeating it is safe. Delay bounds must fit Node's supported timer range. A valid `providerRetryAfterMs` replaces local backoff when it is within the configured cap; an over-cap instruction delegates to the next recovery policy instead.
|
||||
|
||||
Before waiting, the plugin appends a non-surface `llm/retry` event with the failure and scheduled delay. Cancellation and plugin disposal abort the wait; disposal drains the plugin's active backoffs, and a callback captured before disposal fails closed if invoked afterward.
|
||||
|
||||
@@ -15,7 +15,7 @@ The separately published `./invariant` companion checks that every retry record
|
||||
initialDelayMs: 500
|
||||
maxDelayMs: 10000
|
||||
jitterRatio: 0.1
|
||||
retryableCodes: [RATE_LIMIT, SERVER, TIMEOUT, TRANSPORT]
|
||||
retryableCodes: [EMPTY_RESPONSE, RATE_LIMIT, SERVER, TIMEOUT, TRANSPORT]
|
||||
```
|
||||
|
||||
## Model Experience
|
||||
|
||||
@@ -41,8 +41,11 @@
|
||||
"@cordisjs/plugin-loader": "workspace:^",
|
||||
"@deepseek-ai/dsh-agent": "workspace:^",
|
||||
"@deepseek-ai/dsh-agent-loop": "workspace:^",
|
||||
"@deepseek-ai/dsh-agent-loop-testkit": "workspace:^",
|
||||
"@deepseek-ai/dsh-invariants": "workspace:^",
|
||||
"@deepseek-ai/dsh-llm": "workspace:^",
|
||||
"@deepseek-ai/dsh-llm-deepseek": "workspace:^",
|
||||
"@deepseek-ai/dsh-llm-mock-server": "workspace:^",
|
||||
"@deepseek-ai/dsh-session": "workspace:^",
|
||||
"@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^",
|
||||
"@deepseek-ai/dsh-session-persistence-sqlite": "workspace:^",
|
||||
|
||||
@@ -33,7 +33,7 @@ const DEFAULT_MAX_TRANSIENT_RETRIES = 2
|
||||
const DEFAULT_INITIAL_DELAY_MS = 500
|
||||
const DEFAULT_MAX_DELAY_MS = 10_000
|
||||
const DEFAULT_JITTER_RATIO = 0.1
|
||||
const DEFAULT_RETRYABLE_CODES = Object.freeze(['RATE_LIMIT', 'SERVER', 'TIMEOUT', 'TRANSPORT'])
|
||||
const DEFAULT_RETRYABLE_CODES = Object.freeze(['EMPTY_RESPONSE', 'RATE_LIMIT', 'SERVER', 'TIMEOUT', 'TRANSPORT'])
|
||||
|
||||
/** Deployment-owned limits and classification for transient request recovery. */
|
||||
export interface Config {
|
||||
|
||||
@@ -114,7 +114,7 @@ describe('real Loader composition', () => {
|
||||
loaded.llm.registerAdapter(['mock'], adapter)
|
||||
const agent = loaded.agentLoop.create(SessionId('loader-retry'), { provider: 'mock', model: 'mock' })
|
||||
const idle = waitForIdle(loaded, agent)
|
||||
agent.send([{ type: 'text', text: 'recover' }])
|
||||
agent.followup([{ type: 'text', text: 'recover' }])
|
||||
await idle
|
||||
|
||||
expect(adapter.requests).toBe(2)
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
import { afterEach, describe, expect, it, vi } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import type { Fiber } from 'cordis'
|
||||
import LlmService, { CallId, LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm'
|
||||
import LlmService, { CallId, EMPTY_RESPONSE_CODE, LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm'
|
||||
import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
|
||||
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
|
||||
import type { SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
@@ -51,6 +51,25 @@ function textResponse(text: string): StreamChunk[] {
|
||||
]
|
||||
}
|
||||
|
||||
/**
|
||||
* A degenerate empty provider completion as an error finish chunk. Both
|
||||
* adapters emit this shape and the EMPTY_RESPONSE code (the field the policy
|
||||
* routes on); the message text here is the deepseek adapter's phrasing (pi-ai
|
||||
* qualifies it with the model name).
|
||||
*/
|
||||
function emptyCompletion(): StreamChunk[] {
|
||||
return [
|
||||
{ type: 'usage', usage: { inputTokens: 0, outputTokens: 0 } },
|
||||
{
|
||||
type: 'finish',
|
||||
reason: {
|
||||
kind: 'error',
|
||||
failure: { message: 'model returned a completed response with no content', code: EMPTY_RESPONSE_CODE },
|
||||
},
|
||||
},
|
||||
]
|
||||
}
|
||||
|
||||
async function harness(
|
||||
adapter: LlmAdapter,
|
||||
config: retry.Config = {},
|
||||
@@ -129,7 +148,7 @@ describe('bounded transient retry policy', () => {
|
||||
})
|
||||
})
|
||||
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
agent.followup([{ type: 'text', text: 'go' }])
|
||||
const event = await scheduled
|
||||
|
||||
expect(event.data).toEqual({
|
||||
@@ -158,6 +177,39 @@ describe('bounded transient retry policy', () => {
|
||||
})
|
||||
})
|
||||
|
||||
it('retries an EMPTY_RESPONSE error finish under the default retryable codes', async () => {
|
||||
vi.useFakeTimers()
|
||||
const adapter = new ScriptedAdapter([
|
||||
emptyCompletion(),
|
||||
textResponse('recovered'),
|
||||
])
|
||||
// No retryableCodes override: this proves the default policy covers the
|
||||
// adapters' empty-completion classification end to end (finish-chunk error
|
||||
// delivery, not a thrown stream error).
|
||||
;({ ctx: context } = await harness(adapter))
|
||||
const agent = context.agentLoop.create(SessionId('retry-empty-response'), { provider: 'mock', model: 'mock' })
|
||||
const scheduled = waitForRetry(context, agent, 1)
|
||||
|
||||
agent.followup([{ type: 'text', text: 'go' }])
|
||||
const event = await scheduled
|
||||
expect(event.data.failure).toEqual({
|
||||
message: 'model returned a completed response with no content',
|
||||
code: EMPTY_RESPONSE_CODE,
|
||||
})
|
||||
|
||||
const idle = waitForIdle(context, agent)
|
||||
await vi.advanceTimersByTimeAsync(500)
|
||||
await idle
|
||||
|
||||
expect(adapter.requests).toHaveLength(2)
|
||||
expect(agent.session.events.filter(event => event.type === 'assistant/message').map(event => event.data.step))
|
||||
.toEqual([2])
|
||||
expect(agent.session.deriveMessages().at(-1)).toMatchObject({
|
||||
role: 'assistant',
|
||||
content: [{ type: 'text', text: 'recovered' }],
|
||||
})
|
||||
})
|
||||
|
||||
it('leaves partial failed chunks on their step without committing a message or tool side effect', async () => {
|
||||
vi.useFakeTimers()
|
||||
const adapter = new ScriptedAdapter([
|
||||
@@ -178,7 +230,7 @@ describe('bounded transient retry policy', () => {
|
||||
const agent = context.agentLoop.create(SessionId('retry-partial'), { provider: 'mock', model: 'mock' })
|
||||
const scheduled = waitForRetry(context, agent, 1)
|
||||
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
agent.followup([{ type: 'text', text: 'go' }])
|
||||
await scheduled
|
||||
const idle = waitForIdle(context, agent)
|
||||
await vi.advanceTimersByTimeAsync(500)
|
||||
@@ -213,7 +265,7 @@ describe('bounded transient retry policy', () => {
|
||||
const agent = context.agentLoop.create(SessionId('retry-exhausted'), { provider: 'mock', model: 'mock' })
|
||||
const first = waitForRetry(context, agent, 1)
|
||||
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
agent.followup([{ type: 'text', text: 'go' }])
|
||||
expect((await first).data.delayMs).toBe(450)
|
||||
|
||||
const second = waitForRetry(context, agent, 2)
|
||||
@@ -246,7 +298,7 @@ describe('bounded transient retry policy', () => {
|
||||
const agent = context.agentLoop.create(SessionId('retry-zero-delay'), { provider: 'mock', model: 'mock' })
|
||||
const scheduled = waitForRetry(context, agent, 1)
|
||||
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
agent.followup([{ type: 'text', text: 'go' }])
|
||||
expect((await scheduled).data.delayMs).toBe(0)
|
||||
|
||||
const idle = waitForIdle(context, agent)
|
||||
@@ -264,7 +316,7 @@ describe('bounded transient retry policy', () => {
|
||||
;({ ctx: context } = await harness(accepted, { jitterRatio: 1 }))
|
||||
const acceptedAgent = context.agentLoop.create(SessionId('retry-after-accepted'), { provider: 'mock', model: 'mock' })
|
||||
const scheduled = waitForRetry(context, acceptedAgent, 1)
|
||||
acceptedAgent.send([{ type: 'text', text: 'go' }])
|
||||
acceptedAgent.followup([{ type: 'text', text: 'go' }])
|
||||
expect((await scheduled).data.delayMs).toBe(2_000)
|
||||
const acceptedIdle = waitForIdle(context, acceptedAgent)
|
||||
await vi.advanceTimersByTimeAsync(2_000)
|
||||
@@ -278,7 +330,7 @@ describe('bounded transient retry policy', () => {
|
||||
;({ ctx: context } = await harness(rejected))
|
||||
const rejectedAgent = context.agentLoop.create(SessionId('retry-after-rejected'), { provider: 'mock', model: 'mock' })
|
||||
const rejectedIdle = waitForIdle(context, rejectedAgent)
|
||||
rejectedAgent.send([{ type: 'text', text: 'go' }])
|
||||
rejectedAgent.followup([{ type: 'text', text: 'go' }])
|
||||
await rejectedIdle
|
||||
expect(rejected.requests).toHaveLength(1)
|
||||
expect(rejectedAgent.session.events.some(event => event.type === 'llm/retry')).toBe(false)
|
||||
@@ -290,7 +342,7 @@ describe('bounded transient retry policy', () => {
|
||||
;({ ctx: context } = await harness(adapter))
|
||||
const agent = context.agentLoop.create(SessionId('retry-auth'), { provider: 'mock', model: 'mock' })
|
||||
const idle = waitForIdle(context, agent)
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
agent.followup([{ type: 'text', text: 'go' }])
|
||||
await idle
|
||||
expect(adapter.requests).toHaveLength(1)
|
||||
expect(agent.session.events.some(event => event.type === 'llm/retry')).toBe(false)
|
||||
@@ -307,7 +359,7 @@ describe('bounded transient retry policy', () => {
|
||||
context = mounted.ctx
|
||||
const agent = context.agentLoop.create(SessionId('retry-hmr'), { provider: 'mock', model: 'mock' })
|
||||
const scheduled = waitForRetry(context, agent, 1)
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
agent.followup([{ type: 'text', text: 'go' }])
|
||||
await scheduled
|
||||
const idle = waitForIdle(context, agent)
|
||||
|
||||
@@ -335,7 +387,7 @@ describe('bounded transient retry policy', () => {
|
||||
model: 'mock',
|
||||
})
|
||||
const idle = waitForIdle(context, agent)
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
agent.followup([{ type: 'text', text: 'go' }])
|
||||
await entered.promise
|
||||
|
||||
const disposing = mounted.retryFiber.dispose()
|
||||
@@ -376,7 +428,7 @@ describe('bounded transient retry policy', () => {
|
||||
model: 'mock',
|
||||
})
|
||||
const idle = waitForIdle(context, agent)
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
agent.followup([{ type: 'text', text: 'go' }])
|
||||
await captured.promise
|
||||
|
||||
await mounted.retryFiber.dispose()
|
||||
@@ -397,7 +449,7 @@ describe('bounded transient retry policy', () => {
|
||||
;({ ctx: context } = await harness(adapter))
|
||||
const agent = context.agentLoop.create(SessionId('retry-cancel'), { provider: 'mock', model: 'mock' })
|
||||
const scheduled = waitForRetry(context, agent, 1)
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
agent.followup([{ type: 'text', text: 'go' }])
|
||||
await scheduled
|
||||
const idle = waitForIdle(context, agent)
|
||||
agent.cancel({ kind: 'user' })
|
||||
@@ -426,7 +478,7 @@ describe('bounded transient retry policy', () => {
|
||||
const agent = context.agentLoop.create(SessionId('retry-pre-cancel'), { provider: 'mock', model: 'mock' })
|
||||
const idle = waitForIdle(context, agent)
|
||||
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
agent.followup([{ type: 'text', text: 'go' }])
|
||||
await idle
|
||||
|
||||
expect(adapter.requests).toHaveLength(1)
|
||||
@@ -450,7 +502,7 @@ describe('bounded transient retry policy', () => {
|
||||
})
|
||||
const idle = waitForIdle(context, agent)
|
||||
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
agent.followup([{ type: 'text', text: 'go' }])
|
||||
await idle
|
||||
|
||||
expect(adapter.requests).toHaveLength(1)
|
||||
|
||||
234
packages/llm/llm-retry/tests/transport-recovery.spec.ts
Normal file
234
packages/llm/llm-retry/tests/transport-recovery.spec.ts
Normal file
@@ -0,0 +1,234 @@
|
||||
import { createServer } from 'node:http'
|
||||
import type { AddressInfo } from 'node:net'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
|
||||
import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit'
|
||||
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
|
||||
import type { MockLlmBehavior, MockLlmServer } from '@deepseek-ai/dsh-llm-mock-server'
|
||||
import { startMockLlmServer } from '@deepseek-ai/dsh-llm-mock-server'
|
||||
import { SessionId } from '@deepseek-ai/dsh-session'
|
||||
import * as Retry from '../src/index.ts'
|
||||
|
||||
let context: Context | undefined
|
||||
const servers: MockLlmServer[] = []
|
||||
|
||||
afterEach(async () => {
|
||||
await context?.fiber.dispose()
|
||||
context = undefined
|
||||
await Promise.all(servers.splice(0).map(server => server.close()))
|
||||
})
|
||||
|
||||
async function start(
|
||||
sequence: readonly MockLlmBehavior[],
|
||||
options: Omit<Parameters<typeof startMockLlmServer>[0], 'sequence'> = {},
|
||||
): Promise<MockLlmServer> {
|
||||
const server = await startMockLlmServer({ sequence, ...options })
|
||||
servers.push(server)
|
||||
return server
|
||||
}
|
||||
|
||||
async function harness(
|
||||
baseURL: string,
|
||||
options: { streamIdleTimeoutMs?: number; initialDelayMs?: number } = {},
|
||||
): Promise<Context> {
|
||||
const ctx = new Context()
|
||||
await mountAgentLoopTestDependencies(ctx)
|
||||
await ctx.plugin(LlmDeepSeek, {
|
||||
apiKey: 'mock-key',
|
||||
baseURL,
|
||||
streamIdleTimeoutMs: options.streamIdleTimeoutMs ?? 1_000,
|
||||
})
|
||||
await ctx.plugin(Retry, {
|
||||
maxTransientRetries: 2,
|
||||
initialDelayMs: options.initialDelayMs ?? 10,
|
||||
maxDelayMs: options.initialDelayMs ?? 10,
|
||||
jitterRatio: 0,
|
||||
})
|
||||
await ctx.plugin(AgentLoop, { agents: [] })
|
||||
return ctx
|
||||
}
|
||||
|
||||
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
|
||||
return new Promise((resolve) => {
|
||||
const dispose = ctx.on('agent/status', (subject, status) => {
|
||||
if (subject !== agent || status !== 'idle') return
|
||||
dispose()
|
||||
resolve()
|
||||
})
|
||||
})
|
||||
}
|
||||
|
||||
function sendAndWait(ctx: Context, agent: Agent): Promise<void> {
|
||||
const idle = waitForIdle(ctx, agent)
|
||||
agent.followup([{ type: 'text', text: 'recover through the provider boundary' }])
|
||||
return idle
|
||||
}
|
||||
|
||||
function finalAssistantText(agent: Agent): string | undefined {
|
||||
const message = agent.session.deriveMessages().at(-1)
|
||||
if (message?.role !== 'assistant') return undefined
|
||||
return message.content
|
||||
.filter(block => block.type === 'text')
|
||||
.map(block => block.text)
|
||||
.join('')
|
||||
}
|
||||
|
||||
async function unusedPort(): Promise<number> {
|
||||
const server = createServer()
|
||||
await new Promise<void>((resolve) => { server.listen(0, '127.0.0.1', resolve) })
|
||||
const port = (server.address() as AddressInfo).port
|
||||
await new Promise<void>((resolve) => { server.close(() => { resolve() }) })
|
||||
return port
|
||||
}
|
||||
|
||||
describe('bounded retry through the real DeepSeek HTTP/SSE adapter', () => {
|
||||
it('recovers from a true refused connection after the endpoint starts during backoff', async () => {
|
||||
const port = await unusedPort()
|
||||
context = await harness(`http://127.0.0.1:${port}`, { initialDelayMs: 100 })
|
||||
const agent = context.agentLoop.create(SessionId('wire-refused'), {
|
||||
provider: 'deepseek',
|
||||
model: 'mock-model',
|
||||
})
|
||||
let recoveryServer: Promise<MockLlmServer> | undefined
|
||||
context.on('session/event', (session, event) => {
|
||||
if (session !== agent.session || event.type !== 'llm/retry' || event.data.retry !== 1) return
|
||||
recoveryServer = start(['success'], { port, apiKey: 'mock-key', successText: 'connected after retry' })
|
||||
})
|
||||
|
||||
await sendAndWait(context, agent)
|
||||
const server = await recoveryServer
|
||||
|
||||
expect(server).toBeDefined()
|
||||
expect(server?.requests).toHaveLength(1)
|
||||
expect(agent.session.events.filter(event => event.type === 'step/start').map(event => event.data.step))
|
||||
.toEqual([1, 2])
|
||||
expect(agent.session.events.filter(event => event.type === 'llm/retry').map(event => event.data.failure.code))
|
||||
.toEqual(['TRANSPORT'])
|
||||
expect(finalAssistantText(agent)).toBe('connected after retry')
|
||||
})
|
||||
|
||||
it.each([
|
||||
['stream_disconnect', 0] as const,
|
||||
['partial_disconnect', 2] as const,
|
||||
])('retries %s without committing failed chunks', async (behavior, failedChunkCount) => {
|
||||
const server = await start([behavior, 'success'], {
|
||||
apiKey: 'mock-key',
|
||||
partialText: 'discard me',
|
||||
chunkSize: 100,
|
||||
disconnectDelayMs: 20,
|
||||
successText: 'recovered response',
|
||||
})
|
||||
context = await harness(server.baseURL)
|
||||
const agent = context.agentLoop.create(SessionId(`wire-${behavior}`), {
|
||||
provider: 'deepseek',
|
||||
model: 'mock-model',
|
||||
})
|
||||
|
||||
await sendAndWait(context, agent)
|
||||
|
||||
expect(server.requests).toHaveLength(2)
|
||||
expect(server.requests[0]?.body).toEqual(server.requests[1]?.body)
|
||||
expect(agent.session.events.filter(event =>
|
||||
event.type === 'assistant/chunk' && event.data.step === 1,
|
||||
)).toHaveLength(failedChunkCount)
|
||||
expect(agent.session.events.filter(event => event.type === 'assistant/message').map(event => event.data.step))
|
||||
.toEqual([2])
|
||||
expect(agent.session.events.filter(event => event.type === 'llm/retry').map(event => event.data.failure.code))
|
||||
.toEqual(['TRANSPORT'])
|
||||
expect(finalAssistantText(agent)).toBe('recovered response')
|
||||
})
|
||||
|
||||
it('retries a wire-valid content-less completion without committing an empty message', async () => {
|
||||
const server = await start(['empty', 'success'], {
|
||||
apiKey: 'mock-key',
|
||||
successText: 'recovered from empty',
|
||||
})
|
||||
context = await harness(server.baseURL)
|
||||
const agent = context.agentLoop.create(SessionId('wire-empty'), {
|
||||
provider: 'deepseek',
|
||||
model: 'mock-model',
|
||||
})
|
||||
|
||||
await sendAndWait(context, agent)
|
||||
|
||||
expect(server.requests).toHaveLength(2)
|
||||
expect(server.requests[0]?.body).toEqual(server.requests[1]?.body)
|
||||
expect(agent.session.events.filter(event => event.type === 'llm/retry').map(event => event.data.failure.code))
|
||||
.toEqual(['EMPTY_RESPONSE'])
|
||||
expect(agent.session.events.filter(event => event.type === 'assistant/message').map(event => event.data.step))
|
||||
.toEqual([2])
|
||||
expect(agent.session.events.at(-1)).toMatchObject({
|
||||
type: 'turn/end',
|
||||
data: { reason: { kind: 'completed' } },
|
||||
})
|
||||
expect(finalAssistantText(agent)).toBe('recovered from empty')
|
||||
})
|
||||
|
||||
it('exposes a clean partial EOF as non-default-retryable STREAM_CLOSED', async () => {
|
||||
const server = await start(['partial_eof', 'success'], {
|
||||
apiKey: 'mock-key',
|
||||
partialText: 'discarded clean eof',
|
||||
chunkSize: 100,
|
||||
})
|
||||
context = await harness(server.baseURL)
|
||||
const agent = context.agentLoop.create(SessionId('wire-partial-eof'), {
|
||||
provider: 'deepseek',
|
||||
model: 'mock-model',
|
||||
})
|
||||
|
||||
await sendAndWait(context, agent)
|
||||
|
||||
expect(server.requests).toHaveLength(1)
|
||||
expect(agent.session.events.filter(event =>
|
||||
event.type === 'assistant/chunk' && event.data.step === 1,
|
||||
)).toHaveLength(2)
|
||||
expect(agent.session.events.some(event => event.type === 'assistant/message')).toBe(false)
|
||||
expect(agent.session.events.some(event => event.type === 'llm/retry')).toBe(false)
|
||||
expect(agent.session.events.at(-1)).toMatchObject({
|
||||
type: 'turn/end',
|
||||
data: { reason: { kind: 'error', failure: { code: 'STREAM_CLOSED' } } },
|
||||
})
|
||||
})
|
||||
|
||||
it('turns a stalled body into TIMEOUT and succeeds on the next request', async () => {
|
||||
const server = await start(['stall', 'success'], {
|
||||
apiKey: 'mock-key',
|
||||
successText: 'recovered after timeout',
|
||||
})
|
||||
context = await harness(server.baseURL, { streamIdleTimeoutMs: 30 })
|
||||
const agent = context.agentLoop.create(SessionId('wire-stall'), {
|
||||
provider: 'deepseek',
|
||||
model: 'mock-model',
|
||||
})
|
||||
|
||||
await sendAndWait(context, agent)
|
||||
|
||||
expect(server.requests.map(record => record.behavior)).toEqual(['stall', 'success'])
|
||||
expect(agent.session.events.filter(event => event.type === 'llm/retry').map(event => event.data.failure.code))
|
||||
.toEqual(['TIMEOUT'])
|
||||
expect(finalAssistantText(agent)).toBe('recovered after timeout')
|
||||
})
|
||||
|
||||
it('stops after the configured transport retry budget is exhausted', async () => {
|
||||
const server = await start(['connection_reset', 'connection_reset', 'connection_reset'], {
|
||||
apiKey: 'mock-key',
|
||||
})
|
||||
context = await harness(server.baseURL)
|
||||
const agent = context.agentLoop.create(SessionId('wire-exhausted'), {
|
||||
provider: 'deepseek',
|
||||
model: 'mock-model',
|
||||
})
|
||||
|
||||
await sendAndWait(context, agent)
|
||||
|
||||
expect(server.requests).toHaveLength(3)
|
||||
expect(agent.session.events.filter(event => event.type === 'step/start')).toHaveLength(3)
|
||||
expect(agent.session.events.filter(event => event.type === 'llm/retry')).toHaveLength(2)
|
||||
expect(agent.session.events.at(-1)).toMatchObject({
|
||||
type: 'turn/end',
|
||||
data: { reason: { kind: 'error', failure: { code: 'TRANSPORT' } } },
|
||||
})
|
||||
})
|
||||
})
|
||||
@@ -54,6 +54,7 @@ Every product adapter sends application identity on provider HTTP requests. `att
|
||||
- `errorChain(value)` — renders a thrown value with its full `cause` chain and AggregateError members for diagnostic surfaces (UI notices, logger lines, durable `turn/end` messages), so transport wrappers like undici's `TypeError: fetch failed` surface the underlying `ECONNREFUSED`/DNS/TLS detail instead of masking it. Rendering only — route on `code`, never by parsing the result.
|
||||
- `CONTEXT_WINDOW_EXCEEDED_CODE` — the provider-neutral code both DeepSeek adapters use when a request exceeds the model context window, regardless of thrown-HTTP versus in-band finish delivery. `isContextWindowExceededError(detail)` is their shared conservative classifier for OpenAI-compatible provider detail.
|
||||
- `QUOTA_EXCEEDED_CODE` — the non-transient provider-neutral code for exhausted account quota, balance, credits, budget, or usage limits. `isQuotaExceededError(detail)` keeps those failures distinct from request-rate limits.
|
||||
- `EMPTY_RESPONSE_CODE` — the provider-neutral code both adapters use for a degenerate provider completion: a terminal `stop` that carried no content blocks at all. Classified as an error finish (not a successful empty message) because the attempt produced nothing durable; `dsh-llm-retry` retries it by default.
|
||||
|
||||
### Real adapters
|
||||
|
||||
|
||||
@@ -27,6 +27,17 @@ export const CONTEXT_WINDOW_EXCEEDED_CODE = 'CONTEXT_WINDOW_EXCEEDED'
|
||||
/** Canonical provider-neutral code for an exhausted account quota or balance. */
|
||||
export const QUOTA_EXCEEDED_CODE = 'QUOTA'
|
||||
|
||||
/**
|
||||
* Canonical provider-neutral code for a response that completed normally but
|
||||
* carried no content blocks at all. Providers occasionally emit a degenerate
|
||||
* completion (a terminal stop with zero output); adapters classify it as this
|
||||
* failure instead of yielding an empty assistant message, because an empty
|
||||
* message silently ends the turn with nothing for the user or the loop to act
|
||||
* on. The attempt produced nothing durable, so retry policy treats it as safe
|
||||
* to repeat.
|
||||
*/
|
||||
export const EMPTY_RESPONSE_CODE = 'EMPTY_RESPONSE'
|
||||
|
||||
/** Structured codes and plain phrases that explicitly name a context bound being exceeded. */
|
||||
const STRUCTURED_CONTEXT_OVERFLOW = new RegExp(
|
||||
String.raw`(?:^|[^a-z0-9])context[\s_-](?:length|window)[\s_-]`
|
||||
|
||||
Reference in New Issue
Block a user