@kodelyth/voice-call 2026.5.39 → 2026.5.42

package/README.md

@@ -0,0 +1,167 @@
+# @klaw/voice-call
+
+Official Voice Call plugin for **Klaw**.
+
+Providers:
+
+- **Twilio** (Programmable Voice + Media Streams)
+- **Telnyx** (Call Control v2)
+- **Plivo** (Voice API + XML transfer + GetInput speech)
+- **Mock** (dev/no network)
+
+Docs: `https://klaw.kodelyth.com/plugins/voice-call`
+Plugin system: `https://klaw.kodelyth.com/plugin`
+
+## Install (local dev)
+
+### Option A: install via Klaw (recommended)
+
+```bash
+klaw plugins install @klaw/voice-call
+```
+
+Restart the Gateway afterwards.
+
+### Option B: copy into your global extensions folder (dev)
+
+```bash
+PLUGIN_HOME=~/.klaw/extensions
+mkdir -p "$PLUGIN_HOME"
+cp -R <local-plugin-checkout> "$PLUGIN_HOME/voice-call"
+cd "$PLUGIN_HOME/voice-call" && pnpm install
+```
+
+## Config
+
+Put under `plugins.entries.voice-call.config`:
+
+```json5
+{
+  provider: "twilio", // or "telnyx" | "plivo" | "mock"
+  fromNumber: "+15550001234",
+  toNumber: "+15550005678",
+  sessionScope: "per-phone", // or "per-call"
+
+  twilio: {
+    accountSid: "ACxxxxxxxx",
+    authToken: "your_token",
+  },
+
+  telnyx: {
+    apiKey: "KEYxxxx",
+    connectionId: "CONNxxxx",
+    // Telnyx webhook public key from the Telnyx Mission Control Portal
+    // (Base64 string; can also be set via TELNYX_PUBLIC_KEY).
+    publicKey: "...",
+  },
+
+  plivo: {
+    authId: "MAxxxxxxxxxxxxxxxxxxxx",
+    authToken: "your_token",
+  },
+
+  // Webhook server
+  serve: {
+    port: 3334,
+    path: "/voice/webhook",
+  },
+
+  // Public exposure (pick one):
+  // publicUrl: "https://example.ngrok.app/voice/webhook",
+  // tunnel: { provider: "ngrok" },
+  // tailscale: { mode: "funnel", path: "/voice/webhook" }
+
+  outbound: {
+    defaultMode: "notify", // or "conversation"
+  },
+
+  // Optional response agent workspace. Defaults to "main".
+  agentId: "main",
+
+  streaming: {
+    enabled: true,
+    // optional; if omitted, Voice Call picks the first registered
+    // realtime-transcription provider by autoSelectOrder
+    provider: "<realtime-transcription-provider-id>",
+    streamPath: "/voice/stream",
+    providers: {
+      "<realtime-transcription-provider-id>": {
+        // provider-owned options
+      },
+    },
+    preStartTimeoutMs: 5000,
+    maxPendingConnections: 32,
+    maxPendingConnectionsPerIp: 4,
+    maxConnections: 128,
+  },
+}
+```
+
+Notes:
+
+- Twilio/Telnyx/Plivo require a **publicly reachable** webhook URL.
+- `mock` is a local dev provider (no network calls).
+- Telnyx requires `telnyx.publicKey` (or `TELNYX_PUBLIC_KEY`) unless `skipSignatureVerification` is true.
+- If older configs still use `provider: "log"`, `twilio.from`, or legacy `streaming.*` OpenAI keys, run `klaw doctor --fix` to rewrite them.
+- advanced webhook, streaming, and tunnel notes: `https://klaw.kodelyth.com/plugins/voice-call`
+- `responseModel` is optional. When unset, voice responses use the runtime default model.
+- `sessionScope` defaults to `per-phone`, preserving caller memory across calls. Use `per-call` for reception, booking, IVR, and bridge flows where each carrier call should start fresh.
+- `realtime.consultThinkingLevel` is optional. When set, it overrides the thinking level used by the model behind realtime `klaw_agent_consult` calls.
+- `realtime.consultFastMode` is optional. When set, it toggles fast mode for realtime `klaw_agent_consult` calls.
+
+## Stale call reaper
+
+See the plugin docs for recommended ranges and production examples:
+`https://klaw.kodelyth.com/plugins/voice-call#stale-call-reaper`
+
+## TTS for calls
+
+Voice Call uses the core `messages.tts` configuration for
+streaming speech on calls. Override examples and provider caveats live here:
+`https://klaw.kodelyth.com/plugins/voice-call#tts-for-calls`
+
+## CLI
+
+```bash
+klaw voicecall call --to "+15555550123" --message "Hello from Klaw"
+klaw voicecall continue --call-id <id> --message "Any questions?"
+klaw voicecall speak --call-id <id> --message "One moment"
+klaw voicecall end --call-id <id>
+klaw voicecall status --json
+klaw voicecall status --call-id <id>
+klaw voicecall tail
+klaw voicecall expose --mode funnel
+```
+
+## Tool
+
+Tool name: `voice_call`
+
+Actions:
+
+- `initiate_call` (message, to?, mode?)
+- `continue_call` (callId, message)
+- `speak_to_user` (callId, message)
+- `end_call` (callId)
+- `get_status` (callId)
+
+## Gateway RPC
+
+- `voicecall.initiate` (to?, message, mode?)
+- `voicecall.continue` (callId, message)
+- `voicecall.speak` (callId, message)
+- `voicecall.end` (callId)
+- `voicecall.status` (callId)
+
+## Notes
+
+- Uses webhook signature verification for Twilio/Telnyx/Plivo.
+- Adds replay protection for Twilio and Plivo webhooks (valid duplicate callbacks are ignored safely).
+- Twilio speech turns include a per-turn token so stale/replayed callbacks cannot complete a newer turn.
+- `responseModel` / `responseSystemPrompt` control AI auto-responses.
+- Voice-call auto-responses enforce a spoken JSON contract (`{"spoken":"..."}`) and filter reasoning/meta output before playback.
+- While a Twilio stream is active, playback does not fall back to TwiML `<Say>`; stream-TTS failures fail the playback request.
+- Outbound conversation calls suppress barge-in only while the initial greeting is actively speaking, then re-enable normal interruption.
+- Twilio stream disconnect auto-end uses a short grace window so quick reconnects do not end the call.
+- Realtime provider selection is generic. Configure `streaming.provider` / `realtime.provider` and put provider-owned options under `providers.<id>`.
+- Runtime fallback still accepts the old voice-call keys for now, but migration is a doctor step and the compat shim is scheduled to go away in a future release.

package/api.ts

@@ -0,0 +1,16 @@
+export {
+  definePluginEntry,
+  fetchWithSsrFGuard,
+  type GatewayRequestHandlerOptions,
+  isBlockedHostnameOrIp,
+  isRequestBodyLimitError,
+  type KlawPluginApi,
+  readRequestBodyWithLimit,
+  requestBodyErrorToText,
+  type SessionEntry,
+  sleep,
+  TtsAutoSchema,
+  TtsConfigSchema,
+  TtsModeSchema,
+  TtsProviderSchema,
+} from "./runtime-api.js";

package/cli-metadata.ts

@@ -0,0 +1,10 @@
+import { definePluginEntry } from "klaw/plugin-sdk/plugin-entry";
+
+export default definePluginEntry({
+  id: "voice-call",
+  name: "Voice Call",
+  description: "Voice call channel plugin",
+  register(api) {
+    api.registerCli(() => {}, { commands: ["voicecall"] });
+  },
+});

package/config-api.ts

@@ -0,0 +1,12 @@
+// Narrow barrel for config compatibility helpers consumed outside the plugin.
+// Keep this separate from api.ts so config migration code does not pull in the
+// full runtime-oriented voice-call surface.
+
+export {
+  VOICE_CALL_LEGACY_CONFIG_REMOVAL_VERSION,
+  collectVoiceCallLegacyConfigIssues,
+  formatVoiceCallLegacyConfigWarnings,
+  migrateVoiceCallLegacyConfigInput,
+  normalizeVoiceCallLegacyConfigInput,
+  parseVoiceCallPluginConfig,
+} from "./src/config-compat.js";

package/dist/api.js

@@ -0,0 +1,2 @@
+import { TtsAutoSchema, TtsConfigSchema, TtsModeSchema, TtsProviderSchema, definePluginEntry, fetchWithSsrFGuard, isBlockedHostnameOrIp, isRequestBodyLimitError, readRequestBodyWithLimit, requestBodyErrorToText, sleep } from "./runtime-api.js";
+export { TtsAutoSchema, TtsConfigSchema, TtsModeSchema, TtsProviderSchema, definePluginEntry, fetchWithSsrFGuard, isBlockedHostnameOrIp, isRequestBodyLimitError, readRequestBodyWithLimit, requestBodyErrorToText, sleep };

package/dist/cli-metadata.js

@@ -0,0 +1,12 @@
+import { definePluginEntry } from "klaw/plugin-sdk/plugin-entry";
+//#region extensions/voice-call/cli-metadata.ts
+var cli_metadata_default = definePluginEntry({
+	id: "voice-call",
+	name: "Voice Call",
+	description: "Voice call channel plugin",
+	register(api) {
+		api.registerCli(() => {}, { commands: ["voicecall"] });
+	}
+});
+//#endregion
+export { cli_metadata_default as default };