getpatter 0.6.0 → 0.6.1

package/dist/barge-in-strategies-X6ARMGIQ.mjs

@@ -0,0 +1,12 @@
+import {
+  MinWordsStrategy,
+  evaluateStrategies,
+  resetStrategies
+} from "./chunk-D4424JZR.mjs";
+import "./chunk-MVOQFAEO.mjs";
+import "./chunk-N565J3CF.mjs";
+export {
+  MinWordsStrategy,
+  evaluateStrategies,
+  resetStrategies
+};

package/dist/chunk-D4424JZR.mjs

@@ -0,0 +1,71 @@
+import {
+  getLogger
+} from "./chunk-MVOQFAEO.mjs";
+import {
+  init_esm_shims
+} from "./chunk-N565J3CF.mjs";
+
+// src/services/barge-in-strategies.ts
+init_esm_shims();
+var MinWordsStrategy = class {
+  minWords;
+  useInterim;
+  constructor(options) {
+    if (!Number.isFinite(options.minWords) || options.minWords < 1) {
+      throw new Error(
+        `minWords must be >= 1 (got ${String(options.minWords)})`
+      );
+    }
+    this.minWords = Math.floor(options.minWords);
+    this.useInterim = options.useInterim ?? true;
+  }
+  evaluate(ctx) {
+    if (ctx.isInterim && !this.useInterim) {
+      return false;
+    }
+    const threshold = ctx.agentSpeaking ? this.minWords : 1;
+    const wordCount = (ctx.transcript ?? "").trim().split(/\s+/).filter(Boolean).length;
+    return wordCount >= threshold;
+  }
+  async reset() {
+  }
+};
+async function evaluateStrategies(strategies, ctx) {
+  if (!strategies || strategies.length === 0) {
+    return false;
+  }
+  const safeCtx = {
+    transcript: ctx.transcript ?? "",
+    isInterim: ctx.isInterim,
+    agentSpeaking: ctx.agentSpeaking
+  };
+  for (const strategy of strategies) {
+    try {
+      const result = await strategy.evaluate(safeCtx);
+      if (result === true) return true;
+    } catch (err) {
+      getLogger().warn(
+        `BargeInStrategy ${strategy.constructor?.name ?? "unknown"} threw; treating as 'do not confirm': ${String(err)}`
+      );
+    }
+  }
+  return false;
+}
+async function resetStrategies(strategies) {
+  for (const strategy of strategies) {
+    if (typeof strategy.reset !== "function") continue;
+    try {
+      await strategy.reset();
+    } catch (err) {
+      getLogger().debug(
+        `BargeInStrategy ${strategy.constructor?.name ?? "unknown"}.reset() threw: ${String(err)}`
+      );
+    }
+  }
+}
+
+export {
+  MinWordsStrategy,
+  evaluateStrategies,
+  resetStrategies
+};

package/dist/{chunk-X3364LSI.mjs → chunk-RV7APPYE.mjs}

@@ -174,6 +174,11 @@ var OnnxModel = class {
     const data = out.data;
     return data[0] ?? 0;
   }
+  /** Reset the RNN hidden state + rolling context to a fresh inference. */
+  reset() {
+    this.context = new Float32Array(this.contextSize);
+    this.rnnState = new Float32Array(2 * 1 * 128);
+  }
 };
 var SileroVAD = class _SileroVAD {
   constructor(model, opts) {
@@ -213,7 +218,11 @@ var SileroVAD = class _SileroVAD {
     const model = new OnnxModel(runtime, session, sampleRate);
     return new _SileroVAD(model, {
       minSpeechDuration: options.minSpeechDuration ?? 0.25,
-      minSilenceDuration: options.minSilenceDuration ?? 0.1,
+      // Bumped 0.1 -> 0.4s after round 10f confirmed VAD speech_end fired on
+      // natural inter-sentence pauses < 250ms, causing double-talk dispatch.
+      // 400ms is the industry default for telephony and matches the new
+      // inter_utterance_gap_ms debounce in stream-handler.ts.
+      minSilenceDuration: options.minSilenceDuration ?? 0.4,
       prefixPaddingDuration: options.prefixPaddingDuration ?? 0.03,
       activationThreshold,
       deactivationThreshold,
@@ -233,7 +242,10 @@ var SileroVAD = class _SileroVAD {
    *   - `activationThreshold = 0.5` — upstream `threshold`
    *   - `deactivationThreshold = 0.35` — upstream `neg_threshold = threshold - 0.15`
    *   - `minSpeechDuration = 0.25` — upstream `min_speech_duration_ms = 250`
-   *   - `minSilenceDuration = 0.1` — upstream `min_silence_duration_ms = 100`
+   *   - `minSilenceDuration = 0.4` — telephony default (was 0.1, bumped after
+   *     round 10f found speech_end firing on inter-sentence pauses < 250 ms,
+   *     causing double-talk dispatch). 400 ms matches the industry telephony
+   *     default and the inter_utterance_gap_ms debounce in stream-handler.ts.
    *   - `prefixPaddingDuration = 0.03` — upstream `speech_pad_ms = 30`
    *
    * Override any field by passing `options`. Deployments that experience
@@ -356,6 +368,28 @@ var SileroVAD = class _SileroVAD {
     if (this.closed) return;
     this.closed = true;
   }
+  /**
+   * Reset all per-utterance state so the next ``processFrame`` starts from
+   * a clean SILENCE state.
+   *
+   * Called by the stream handler between agent turns to prevent a "stuck
+   * SPEECH" condition where PSTN echo / loopback kept the detector's
+   * probability above ``deactivationThreshold`` for the entire agent turn.
+   * Without this reset the next user utterance would never trigger a
+   * SILENCE→SPEECH transition and barge-in would feel "one-shot" (works
+   * once, then never again until the call ends).
+   *
+   * Safe to call any time including on a closed instance (no-op).
+   */
+  reset() {
+    if (this.closed) return;
+    this.pending = new Float32Array(0);
+    this.pubSpeaking = false;
+    this.speechThresholdDuration = 0;
+    this.silenceThresholdDuration = 0;
+    this.expFilter.reset();
+    this.model.reset();
+  }
 };
 
 export {