fix(edge): stop short clips waiting a minute on the NAS and make the OpenAI STT fallback usable

A five-second phone recording took over a minute: stt-proxy waited up to
60 s for the self-hosted gateway, whose GPU endpoint was off and whose NAS CPU
Whisper needs 30-90 s per clip. With a direct provider configured the gateway
now gets 5 s plus the clip length (30 s cap).

The direct OpenAI fallback never produced a result. The production key held
characters that are not valid in an HTTP header, so every request threw while
being built; provider keys are now stripped of BOM/zero-width characters and a
still-invalid key counts as not configured. whisper-1 verbose_json reports the
language by name, which the result contract rejected; names now map to codes.
Fail-closed responses list each provider's failure (status or error class,
no secrets) so an outage can be diagnosed without log access.

server/supabase/functions/generate-meeting-document/index.ts

@@ -7,6 +7,7 @@ import {
   parseProviderDocumentResult,
 } from '../_shared/meeting-document-contract.ts'
 import { buildMeetingDocumentSystemPrompt } from '../_shared/generative-ai-safety.ts'
+import { readProviderKey } from '../_shared/provider-key.ts'
 
 interface ClaimResult {
   claimed: boolean
@@ -105,7 +106,7 @@ Deno.serve(async (request: Request) => {
     const body = parseGenerateMeetingDocumentRequest(rawBody)
     idempotencyKey = body.idempotencyKey
 
-    const providerKey = Deno.env.get('ANTHROPIC_API_KEY')?.trim() ?? ''
+    const providerKey = readProviderKey('ANTHROPIC_API_KEY')
     if (providerKey.length === 0) {
       return json(503, { error: 'provider_unavailable' })
     }