feat: implement bounded LLM request recovery

This commit is contained in:
Tianyi Cui
2026-07-20 03:34:19 +08:00
parent 7cf966fc0e
commit 3b0b0cefeb
115 changed files with 3311 additions and 366 deletions
+4 -3
View File
@@ -93,9 +93,10 @@ export class BasicCompactService extends CompactService {
}
})
ctx.on('agent/request-error', async (agent, _turn, _step, error, retryAttempt, signal, next) => {
if (error.code !== CONTEXT_WINDOW_EXCEEDED_CODE
|| retryAttempt >= this.config.maxOverflowRetries
ctx.on('agent/request-error', async (agent, _turn, _step, _error, failure, priorFailures, signal, next) => {
const priorOverflowFailures = priorFailures.filter(item => item.code === CONTEXT_WINDOW_EXCEEDED_CODE).length
if (failure.code !== CONTEXT_WINDOW_EXCEEDED_CODE
|| priorOverflowFailures >= this.config.maxOverflowRetries
|| signal.aborted) return next()
let generation: number
@@ -141,14 +141,10 @@ export function frameSummary(summary: readonly ContentBlock[]): ContentBlock[] {
/** Map a terminal summarization finish to its fail-closed error. */
function finishError(finish: FinishReason): Error | undefined {
switch (finish.kind) {
case 'error': {
const error = new Error(finish.message) as Error & { code?: string }
if (finish.code !== undefined) error.code = finish.code
return error
}
case 'error':
case 'aborted': {
const error = new Error('summarization stream aborted') as Error & { code?: string }
error.code = 'ABORTED'
const error = new Error(finish.failure.message) as Error & { code?: string }
error.code = finish.failure.code
return error
}
case 'max-tokens': {