chore(ai): passive z.ai provider HTTP telemetry (#175)
Investigate the intermittent (~20-30%) long-turn failure "Lost connection to the AI provider" = AI_RetryError / read ECONNRESET on the gitmost->z.ai link (browser-agnostic, mid-turn). Pure instrumentation, no behavior change: - ai-http-diagnostics.ts: a passive fetch wrapper injected into the OpenAI-compatible (z.ai) client. Per provider HTTP call it logs time-to-headers/status on success, and on a pre-response rejection the latency, error code/cause, request-body size and idle-gap since the previous call. The Response is returned untouched (streaming intact), errors rethrown unchanged; no retry/timeout/dispatcher. - ai.service.ts: wire the instrumented fetch into the openai case only. Lets us classify the reset as connection-phase vs mid-stream before choosing a fix, without repeating the reverted RetryAgent (#140). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
@@ -14,6 +14,8 @@ import { AiNotConfiguredException } from './ai-not-configured.exception';
|
||||
import { AiEmbeddingNotConfiguredException } from './ai-embedding-not-configured.exception';
|
||||
import { AiSttNotConfiguredException } from './ai-stt-not-configured.exception';
|
||||
import { describeProviderError } from './ai-error.util';
|
||||
// DIAGNOSTIC (provider ECONNRESET investigation) — temporary.
|
||||
import { createDiagnosticFetch } from './ai-http-diagnostics';
|
||||
import { AiProviderCredentialsRepo } from '@docmost/db/repos/ai-chat/ai-provider-credentials.repo';
|
||||
import { SecretBoxService } from '../crypto/secret-box';
|
||||
import { AiDriver } from './ai.types';
|
||||
@@ -43,6 +45,13 @@ export interface ChatModelOverride {
|
||||
export class AiService {
|
||||
private readonly logger = new Logger(AiService.name);
|
||||
|
||||
// DIAGNOSTIC (provider ECONNRESET investigation) — temporary: passive
|
||||
// instrumentation of the OpenAI-compatible provider HTTP calls (z.ai).
|
||||
// Logs call timing/outcome only — no behavior change.
|
||||
private readonly aiDiagnosticFetch = createDiagnosticFetch(
|
||||
'AiService:provider-http',
|
||||
);
|
||||
|
||||
constructor(
|
||||
private readonly aiSettings: AiSettingsService,
|
||||
private readonly aiProviderCredentialsRepo: AiProviderCredentialsRepo,
|
||||
@@ -140,7 +149,13 @@ export class AiService {
|
||||
// Responses API (/responses), which OpenAI-compatible gateways
|
||||
// (OpenRouter, etc.) reject on multi-turn requests (history with
|
||||
// assistant messages) → 400.
|
||||
return createOpenAI({ apiKey, baseURL: baseUrl }).chat(chatModel);
|
||||
// DIAGNOSTIC (provider ECONNRESET investigation) — temporary: pass the
|
||||
// passive instrumented fetch (logging only; no behavior change).
|
||||
return createOpenAI({
|
||||
apiKey,
|
||||
baseURL: baseUrl,
|
||||
fetch: this.aiDiagnosticFetch,
|
||||
}).chat(chatModel);
|
||||
case 'gemini':
|
||||
return createGoogleGenerativeAI({ apiKey })(chatModel);
|
||||
case 'ollama':
|
||||
|
||||
Reference in New Issue
Block a user