Fix Twilio voice-call startup so accepted media streams register immediately, realtime transcription readiness gates only the initial greeting, and early inbound media is preserved while STT connects.
Fixes#75197.
Thanks @PfanP and @donkeykong91.
Trace to db09f68ce5 (Support SecretRef for voice-call credentials and bundled
plugin SecretInputs #72607). The reference page docs/reference/secretref-credential-surface.md
listed the new entries in the same SHA, but docs/plugins/voice-call.md showed
only plain-string credentials without pointing to the SecretRef surface.
The voice-call plugin doc was 664 lines with a flat install/setup
walkthrough, three flat 'Realtime' / 'Streaming' / 'TTS' provider
config blocks each shown twice, an italicised webhook-security
section in Title Case, and a duplicate-Voice Call body H1.
Restructure for scan-first reading without losing operational detail:
- Wrap Quick start in a Steps component (install -> configure ->
verify -> smoke), with the 'install from npm' vs 'install from
local folder' choice as a nested Tabs.
- Surface the public-webhook-URL constraint as a Warning at the top
of Quick start so readers see it before they hit setup.
- Move provider exposure caveats, streaming connection caps, and
legacy config migration notes into a single AccordionGroup so
the Configuration section reads as the canonical config plus
collapsible operational details.
- Convert the Realtime, Streaming, and TTS provider examples to
Tabs with one tab per provider (Google/OpenAI for realtime;
OpenAI/xAI for streaming; Core/ElevenLabs/OpenAI override for TTS),
removing the previous duplicate-block-per-provider pattern.
- Convert the realtime tool-policy bullet list to a 3-row table.
- Convert the agent tool action list and gateway RPC list into
small tables (action -> args).
- Surface inboundPolicy caller-ID weakness, microsoft-not-supported
for telephony, and realtime+streaming exclusivity as Warning
callouts where they were previously buried inline.
- Sentence-case 'Webhook security' (was Title Case), drop the
duplicate body H1, and refresh the Related list to alphabetical
sentence-case.
Provider names, env vars, defaults, models, voice ids, command
flags, and field semantics are unchanged. Pure restructure plus
Mintlify component upgrades.
- concepts/streaming.md: remove '# Streaming + chunking'.
- reference/session-management-compaction.md: remove Title Case H1
'# Session Management & Compaction (Deep Dive)'.
- plugins/voice-call.md: remove '# Voice Call (plugin)'.
CLI pages keep their command-formatted body H1s since that is the repo
convention and the formatting is not expressible in frontmatter.
Fixes outbound Twilio realtime conversations so the TwiML fetch returns the realtime <Connect><Stream> path for outbound directions and the answered-call path does not overwrite it with legacy <Say> TwiML.
Local proof:
- pnpm test extensions/voice-call/src/manager.notify.test.ts extensions/voice-call/src/webhook.test.ts
- pnpm check:changed
- pnpm check
- pnpm build
- local VoiceCallWebhookServer + CallManager smoke for Direction=outbound-api
Closes#68713.
