mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-22 16:25:58 +00:00
* fix(desktop): extend read aloud timeout Hermes Desktop Read Aloud can show a false failure after 15s even when backend TTS synthesis succeeds. The Desktop renderer bridge request to /api/audio/speak blocks until provider synthesis, audio file read, and base64 response encoding finish, so larger messages or slower remote TTS providers can legitimately exceed the default 15s Electron backend timeout (DEFAULT_FETCH_TIMEOUT_MS in hardening.ts). Give only the blocking Read Aloud request a bounded TTS-specific timeout (180s floor, 600s cap, text-length scaling). Normal Desktop API requests keep the short default so real backend hangs still fail promptly. Salvage of #39286 rebased onto current main (original branch conflicted in apps/desktop/src/hermes.ts and hermes.test.ts against the newly-added STARTUP_REQUEST_TIMEOUT_MS / PROMPT_SUBMIT_REQUEST_TIMEOUT_MS constants and model-options tests). Both additions coexist; no behavior changed. Co-authored-by: Ruslan Vasylev <ruslan.vasylev.vfx@gmail.com> * fix(desktop): extend read aloud + transcription timeouts Hermes Desktop Read Aloud can show a false failure after 15s even when backend TTS synthesis succeeds. The Desktop renderer bridge request to /api/audio/speak blocks until provider synthesis, audio file read, and base64 response encoding finish, so larger messages or slower remote TTS providers can legitimately exceed the default 15s Electron backend timeout (DEFAULT_FETCH_TIMEOUT_MS in hardening.ts). /api/audio/transcribe is the sibling blocking endpoint with the same bug class: it blocks on provider STT + file handling + encoding behind the same 15s default, so long clips / remote providers hit the same spurious timeout. Give both requests a bounded, endpoint-specific timeout (180s floor, 600s cap) — speak scales on text length, transcribe on the base64 payload length. Every other Desktop API request keeps the short default so real backend hangs still fail promptly. Salvage of #39286 rebased onto current main. The original PR was scoped to /api/audio/speak only; this extends it to also close the transcribe twin per OutThisLife's review suggestion on #39286, closing the whole 'audio endpoints time out at 15s' class in one shot. Co-authored-by: Ruslan Vasylev <ruslan.vasylev.vfx@gmail.com> --------- Co-authored-by: Ruslan Vasylev <ruslan.vasylev.vfx@gmail.com>
This commit is contained in:
Austin Pickett
GitHub
parent
183712ab82
commit
2bb531b67a
2 changed files with 106 additions and 4 deletions
|
|
@ -1,6 +1,12 @@
|
|||
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
|
||||
|
||||
import {
|
||||
AUDIO_SPEAK_MAX_REQUEST_TIMEOUT_MS,
|
||||
AUDIO_SPEAK_MIN_REQUEST_TIMEOUT_MS,
|
||||
AUDIO_TRANSCRIBE_MAX_REQUEST_TIMEOUT_MS,
|
||||
AUDIO_TRANSCRIBE_MIN_REQUEST_TIMEOUT_MS,
|
||||
audioSpeakRequestTimeoutMs,
|
||||
audioTranscribeRequestTimeoutMs,
|
||||
getCronJobs,
|
||||
getGlobalModelInfo,
|
||||
getGlobalModelOptions,
|
||||
|
|
@ -12,7 +18,9 @@ import {
|
|||
listAllProfileSessions,
|
||||
listSessions,
|
||||
listSidebarSessions,
|
||||
resetSidebarBatchCapability
|
||||
resetSidebarBatchCapability,
|
||||
speakText,
|
||||
transcribeAudio
|
||||
} from './hermes'
|
||||
import { refreshActiveProfile } from './store/profile'
|
||||
|
||||
|
|
@ -23,7 +31,7 @@ const emptySessionsResponse = {
|
|||
total: 0
|
||||
}
|
||||
|
||||
describe('Hermes REST session helpers', () => {
|
||||
describe('Hermes REST helpers', () => {
|
||||
let api: ReturnType<typeof vi.fn>
|
||||
|
||||
beforeEach(() => {
|
||||
|
|
@ -322,6 +330,62 @@ describe('Hermes REST session helpers', () => {
|
|||
})
|
||||
})
|
||||
|
||||
it('bounds blocking TTS synthesis timeouts by text length', () => {
|
||||
expect(audioSpeakRequestTimeoutMs('short message')).toBe(AUDIO_SPEAK_MIN_REQUEST_TIMEOUT_MS)
|
||||
expect(audioSpeakRequestTimeoutMs('x'.repeat(8_000))).toBe(280_000)
|
||||
expect(audioSpeakRequestTimeoutMs('x'.repeat(100_000))).toBe(AUDIO_SPEAK_MAX_REQUEST_TIMEOUT_MS)
|
||||
})
|
||||
|
||||
it('uses an extended timeout for blocking TTS synthesis', async () => {
|
||||
api.mockResolvedValueOnce({
|
||||
data_url: 'data:audio/mpeg;base64,AA==',
|
||||
mime_type: 'audio/mpeg',
|
||||
ok: true,
|
||||
provider: 'openai'
|
||||
})
|
||||
|
||||
await expect(speakText('Read this aloud')).resolves.toEqual({
|
||||
data_url: 'data:audio/mpeg;base64,AA==',
|
||||
mime_type: 'audio/mpeg',
|
||||
ok: true,
|
||||
provider: 'openai'
|
||||
})
|
||||
|
||||
expect(api).toHaveBeenCalledWith({
|
||||
body: { text: 'Read this aloud' },
|
||||
method: 'POST',
|
||||
path: '/api/audio/speak',
|
||||
timeoutMs: AUDIO_SPEAK_MIN_REQUEST_TIMEOUT_MS
|
||||
})
|
||||
})
|
||||
|
||||
it('bounds blocking transcription timeouts by payload length', () => {
|
||||
expect(audioTranscribeRequestTimeoutMs('data:audio/webm;base64,AA==')).toBe(AUDIO_TRANSCRIBE_MIN_REQUEST_TIMEOUT_MS)
|
||||
expect(audioTranscribeRequestTimeoutMs('x'.repeat(3_000_000))).toBe(300_000)
|
||||
expect(audioTranscribeRequestTimeoutMs('x'.repeat(9_000_000))).toBe(AUDIO_TRANSCRIBE_MAX_REQUEST_TIMEOUT_MS)
|
||||
})
|
||||
|
||||
it('uses an extended timeout for blocking transcription', async () => {
|
||||
api.mockResolvedValueOnce({
|
||||
ok: true,
|
||||
provider: 'openai',
|
||||
text: 'transcribed text'
|
||||
})
|
||||
|
||||
await expect(transcribeAudio('data:audio/webm;base64,AA==', 'audio/webm')).resolves.toEqual({
|
||||
ok: true,
|
||||
provider: 'openai',
|
||||
text: 'transcribed text'
|
||||
})
|
||||
|
||||
expect(api).toHaveBeenCalledWith({
|
||||
body: { data_url: 'data:audio/webm;base64,AA==', mime_type: 'audio/webm' },
|
||||
method: 'POST',
|
||||
path: '/api/audio/transcribe',
|
||||
timeoutMs: AUDIO_TRANSCRIBE_MIN_REQUEST_TIMEOUT_MS
|
||||
})
|
||||
})
|
||||
|
||||
it('defaults model options to configured providers only', async () => {
|
||||
await getGlobalModelOptions()
|
||||
|
||||
|
|
|
|||
|
|
@ -84,6 +84,36 @@ const SESSION_LIST_REQUEST_TIMEOUT_MS = 60_000
|
|||
// agent-turn ceiling (agent.gateway_timeout = 1800s) so the ack timeout only
|
||||
// ever fires when the turn itself would have been abandoned server-side.
|
||||
export const PROMPT_SUBMIT_REQUEST_TIMEOUT_MS = 1_800_000
|
||||
export const AUDIO_SPEAK_MIN_REQUEST_TIMEOUT_MS = 180_000
|
||||
export const AUDIO_SPEAK_MAX_REQUEST_TIMEOUT_MS = 600_000
|
||||
const AUDIO_SPEAK_TIMEOUT_MS_PER_CHAR = 35
|
||||
|
||||
export function audioSpeakRequestTimeoutMs(text: string): number {
|
||||
const estimated = Math.max(
|
||||
AUDIO_SPEAK_MIN_REQUEST_TIMEOUT_MS,
|
||||
Math.ceil(String(text || '').length * AUDIO_SPEAK_TIMEOUT_MS_PER_CHAR)
|
||||
)
|
||||
|
||||
return Math.min(AUDIO_SPEAK_MAX_REQUEST_TIMEOUT_MS, estimated)
|
||||
}
|
||||
|
||||
export const AUDIO_TRANSCRIBE_MIN_REQUEST_TIMEOUT_MS = 180_000
|
||||
export const AUDIO_TRANSCRIBE_MAX_REQUEST_TIMEOUT_MS = 600_000
|
||||
// The transcribe payload is the base64 audio data URL itself, so its string
|
||||
// length tracks clip size. ~0.1ms/char keeps short clips at the floor while
|
||||
// letting multi-minute recordings scale toward the cap (a base64 char is
|
||||
// ~0.75 bytes, so at 128kbps ≈ 21k chars/s of audio this budgets ~2s of
|
||||
// timeout per 1s of audio before the cap clamps it).
|
||||
const AUDIO_TRANSCRIBE_TIMEOUT_MS_PER_CHAR = 0.1
|
||||
|
||||
export function audioTranscribeRequestTimeoutMs(dataUrl: string): number {
|
||||
const estimated = Math.max(
|
||||
AUDIO_TRANSCRIBE_MIN_REQUEST_TIMEOUT_MS,
|
||||
Math.ceil(String(dataUrl || '').length * AUDIO_TRANSCRIBE_TIMEOUT_MS_PER_CHAR)
|
||||
)
|
||||
|
||||
return Math.min(AUDIO_TRANSCRIBE_MAX_REQUEST_TIMEOUT_MS, estimated)
|
||||
}
|
||||
|
||||
export type {
|
||||
ActionResponse,
|
||||
|
|
@ -1346,7 +1376,11 @@ export function transcribeAudio(dataUrl: string, mimeType?: string): Promise<Aud
|
|||
body: {
|
||||
data_url: dataUrl,
|
||||
mime_type: mimeType
|
||||
}
|
||||
},
|
||||
// Transcription blocks until provider STT, file handling, and response
|
||||
// encoding finish. Remote providers and long clips regularly exceed the
|
||||
// default 15s Electron backend timeout.
|
||||
timeoutMs: audioTranscribeRequestTimeoutMs(dataUrl)
|
||||
})
|
||||
}
|
||||
|
||||
|
|
@ -1354,7 +1388,11 @@ export function speakText(text: string): Promise<AudioSpeakResponse> {
|
|||
return window.hermesDesktop.api<AudioSpeakResponse>({
|
||||
path: '/api/audio/speak',
|
||||
method: 'POST',
|
||||
body: { text }
|
||||
body: { text },
|
||||
// TTS blocks until provider synthesis, file read, and base64 encoding
|
||||
// finish. Remote providers and large messages regularly exceed the
|
||||
// default 15s Electron backend timeout.
|
||||
timeoutMs: audioSpeakRequestTimeoutMs(text)
|
||||
})
|
||||
}
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue