gheim 0.1.0 → 0.1.2

package/dist/esm/index.js

@@ -1,5 +1,10 @@
-import { createRequire } from "node:module";
-var __require = /* @__PURE__ */ createRequire(import.meta.url);
+var __require = /* @__PURE__ */ ((x) => typeof require !== "undefined" ? require : typeof Proxy !== "undefined" ? new Proxy(x, {
+  get: (a, b) => (typeof require !== "undefined" ? require : a)[b]
+}) : x)(function(x) {
+  if (typeof require !== "undefined")
+    return require.apply(this, arguments);
+  throw Error('Dynamic require of "' + x + '" is not supported');
+});
 
 // src/core/sentinels.ts
 var LABEL_TO_TAG = {
@@ -37,98 +42,6 @@ function isPossibleSentinelPrefix(buffer) {
   return PARTIAL_SENTINEL_RE.test(buffer);
 }
 
-// src/normalizers.ts
-import { createRequire as createRequire2 } from "node:module";
-var _require = null;
-var _requireResolved = false;
-function _getRequire() {
-  if (_requireResolved)
-    return _require;
-  _requireResolved = true;
-  try {
-    _require = createRequire2(import.meta.url);
-  } catch {
-    _require = null;
-  }
-  return _require;
-}
-function loadSync(name, errMsg) {
-  const req = _getRequire();
-  if (!req)
-    throw new Error(errMsg);
-  try {
-    return req(name);
-  } catch {
-    throw new Error(errMsg);
-  }
-}
-function loadPhoneLib() {
-  return loadSync("libphonenumber-js", "the e164 normalizer requires libphonenumber-js. " + "Install with: bun add libphonenumber-js");
-}
-function e164(opts = {}) {
-  const lib = loadPhoneLib();
-  return (s) => {
-    try {
-      const parsed = lib.parsePhoneNumberFromString(s, opts.region);
-      if (!parsed || !parsed.isValid())
-        return null;
-      return parsed.format("E.164");
-    } catch {
-      return null;
-    }
-  };
-}
-function loadChrono(opts) {
-  const mod = loadSync("chrono-node", "the isoDate normalizer requires chrono-node. " + "Install with: bun add chrono-node");
-  if (opts.locale) {
-    const localeParser = mod[opts.locale];
-    if (localeParser)
-      return localeParser;
-  }
-  return mod;
-}
-function isoDate(opts = {}) {
-  const parser = loadChrono(opts);
-  return (s) => {
-    const d = parser.parseDate(s);
-    if (!d)
-      return null;
-    return d.toISOString().slice(0, 10);
-  };
-}
-function germanTransliteration() {
-  const table = {
-    ä: "ae",
-    Ä: "ae",
-    ö: "oe",
-    Ö: "oe",
-    ü: "ue",
-    Ü: "ue",
-    ß: "ss"
-  };
-  return (s) => {
-    let out = "";
-    for (const ch of s.normalize("NFKC")) {
-      out += table[ch] ?? ch;
-    }
-    return out.toLowerCase().split(/\s+/).filter(Boolean).join(" ");
-  };
-}
-var BUILTINS = {
-  e164: () => e164(),
-  iso_date: () => isoDate(),
-  german: () => germanTransliteration()
-};
-function resolveNormalizer(spec) {
-  if (typeof spec === "function")
-    return spec;
-  const factory = BUILTINS[spec];
-  if (!factory) {
-    throw new Error(`unknown built-in normalizer: ${JSON.stringify(spec)}. ` + `Available: ${Object.keys(BUILTINS).join(", ")}, or pass a callable.`);
-  }
-  return factory();
-}
-
 // src/core/session.ts
 function normalizeSurface(s) {
   return s.normalize("NFKC").toLowerCase().split(/\s+/).filter(Boolean).join(" ");
@@ -141,8 +54,8 @@ class Session {
   resolvedNormalizers = {};
   constructor(opts = {}) {
     if (opts.normalizers) {
-      for (const [label, spec] of Object.entries(opts.normalizers)) {
-        this.resolvedNormalizers[label] = resolveNormalizer(spec);
+      for (const [label, fn] of Object.entries(opts.normalizers)) {
+        this.resolvedNormalizers[label] = fn;
       }
     }
   }
@@ -166,8 +79,11 @@ class Session {
     return sentinel;
   }
   applySpans(text, spans) {
+    return this.applySpansDetailed(text, spans).redacted;
+  }
+  applySpansDetailed(text, spans) {
     if (spans.length === 0)
-      return text;
+      return { redacted: text, merged: [] };
     const sorted = [...spans].sort((a, b) => a.start - b.start || b.end - b.start - (a.end - a.start));
     const merged = mergeAdjacent(text, sorted);
     const out = [];
@@ -183,7 +99,7 @@ class Session {
       cursor = end;
     }
     out.push(text.slice(cursor));
-    return out.join("");
+    return { redacted: out.join(""), merged };
   }
   restore(text) {
     if (Object.keys(this.mapping).length === 0)
@@ -381,8 +297,10 @@ class LocalDetector {
   chunkTokens;
   chunkOverlapTokens;
   batchSize;
+  actualDevice = null;
   _pipeline = null;
   _loadPromise = null;
+  _onProgress;
   constructor(opts = {}) {
     this.model = opts.model ?? DEFAULT_MODEL2;
     this.device = opts.device ?? "auto";
@@ -391,11 +309,13 @@ class LocalDetector {
     this.chunkTokens = opts.chunkTokens ?? DEFAULT_CHUNK_TOKENS;
     this.chunkOverlapTokens = opts.chunkOverlapTokens ?? DEFAULT_OVERLAP_TOKENS;
     this.batchSize = opts.batchSize ?? DEFAULT_BATCH_SIZE;
+    this._onProgress = opts.onProgress;
     if (this.chunkOverlapTokens >= this.chunkTokens) {
       throw new Error(`chunkOverlapTokens (${this.chunkOverlapTokens}) must be smaller than chunkTokens (${this.chunkTokens})`);
     }
     if (opts.pipelineInstance) {
       this._pipeline = opts.pipelineInstance;
+      this.actualDevice = this.device === "auto" ? null : this.device;
     }
   }
   async load() {
@@ -404,24 +324,70 @@ class LocalDetector {
     if (this._loadPromise)
       return this._loadPromise;
     this._loadPromise = (async () => {
-      let mod;
-      try {
-        mod = await import("@huggingface/transformers");
-      } catch (e) {
-        throw new Error("LocalDetector requires `@huggingface/transformers`. Install with: bun add @huggingface/transformers");
+      const mod = await loadTransformersJs();
+      const sequence = await this._planDeviceSequence();
+      let lastErr;
+      for (let i = 0;i < sequence.length; i++) {
+        const dev = sequence[i] ?? "wasm";
+        try {
+          const pipe = await mod.pipeline("token-classification", this.model, {
+            device: dev,
+            dtype: this.dtype,
+            progress_callback: this._onProgress ? (raw) => this._emitProgress(raw, dev) : undefined
+          });
+          this._pipeline = pipe;
+          this.actualDevice = dev;
+          return pipe;
+        } catch (e) {
+          lastErr = e;
+          if (i < sequence.length - 1)
+            continue;
+          throw e;
+        }
       }
-      const pipe = await mod.pipeline("token-classification", this.model, {
-        device: this.device,
-        dtype: this.dtype
-      });
-      this._pipeline = pipe;
-      return pipe;
+      throw lastErr ?? new Error("LocalDetector.load(): no candidate backends");
     })();
     return this._loadPromise;
   }
+  async _planDeviceSequence() {
+    if (this.device !== "auto")
+      return [this.device];
+    const seq = [];
+    const nav = typeof navigator !== "undefined" ? navigator : null;
+    if (nav?.gpu?.requestAdapter) {
+      try {
+        const adapter = await nav.gpu.requestAdapter();
+        if (adapter)
+          seq.push("webgpu");
+      } catch {}
+    }
+    seq.push("wasm");
+    return seq;
+  }
+  _emitProgress(raw, device) {
+    if (!this._onProgress)
+      return;
+    const event = {
+      phase: raw.status ?? "progress",
+      device
+    };
+    if (raw.file)
+      event.file = raw.file;
+    if (raw.status === "progress") {
+      if (raw.loaded != null)
+        event.loadedBytes = raw.loaded;
+      if (raw.total != null)
+        event.totalBytes = raw.total;
+      if (raw.progress != null) {
+        const norm = raw.progress > 1 ? raw.progress / 100 : raw.progress;
+        event.fraction = Math.max(0, Math.min(1, norm));
+      }
+    }
+    this._onProgress(event);
+  }
   async detect(text, opts) {
     if (opts?.model && opts.model !== this.model) {
-      throw new Error(`LocalDetector was constructed with model='${this.model}'; per-call model override ('${opts.model}') not supported.`);
+      throw new Error(`LocalDetector was constructed with model='${this.model}'; ` + `per-call model override ('${opts.model}') not supported.`);
     }
     if (!text)
       return [];
@@ -430,7 +396,7 @@ class LocalDetector {
   }
   async detectBatch(texts, opts) {
     if (opts?.model && opts.model !== this.model) {
-      throw new Error(`LocalDetector was constructed with model='${this.model}'; per-call model override ('${opts.model}') not supported.`);
+      throw new Error(`LocalDetector was constructed with model='${this.model}'; ` + `per-call model override ('${opts.model}') not supported.`);
     }
     if (texts.length === 0)
       return [];
@@ -591,6 +557,13 @@ function chunkByChars(text, chunkChars, overlapChars) {
 function normalizeWord(word) {
   return word.replace(/##/g, "").trim();
 }
+async function loadTransformersJs() {
+  try {
+    return await import("@huggingface/transformers");
+  } catch {
+    throw new Error("LocalDetector requires `@huggingface/transformers`. Install with: bun add @huggingface/transformers");
+  }
+}
 // src/detectors/index.ts
 function defaultDetector() {
   const hasKey = typeof process !== "undefined" && Boolean(process.env?.GHEIM_API_KEY);
@@ -645,10 +618,11 @@ async function* deanonymizeStream(chunks, session) {
 }
 
 // src/index.ts
-var VERSION = "0.1.0";
+var VERSION = "0.1.2";
 export {
   renderSentinel,
   parseSentinel,
+  mergeAdjacent,
   labelTag,
   isPossibleSentinelPrefix,
   defaultDetector,

package/dist/esm/openai/index.js

@@ -1,5 +1,10 @@
-import { createRequire } from "node:module";
-var __require = /* @__PURE__ */ createRequire(import.meta.url);
+var __require = /* @__PURE__ */ ((x) => typeof require !== "undefined" ? require : typeof Proxy !== "undefined" ? new Proxy(x, {
+  get: (a, b) => (typeof require !== "undefined" ? require : a)[b]
+}) : x)(function(x) {
+  if (typeof require !== "undefined")
+    return require.apply(this, arguments);
+  throw Error('Dynamic require of "' + x + '" is not supported');
+});
 
 // src/core/sentinels.ts
 var LABEL_TO_TAG = {
@@ -228,8 +233,10 @@ class LocalDetector {
   chunkTokens;
   chunkOverlapTokens;
   batchSize;
+  actualDevice = null;
   _pipeline = null;
   _loadPromise = null;
+  _onProgress;
   constructor(opts = {}) {
     this.model = opts.model ?? DEFAULT_MODEL2;
     this.device = opts.device ?? "auto";
@@ -238,11 +245,13 @@ class LocalDetector {
     this.chunkTokens = opts.chunkTokens ?? DEFAULT_CHUNK_TOKENS;
     this.chunkOverlapTokens = opts.chunkOverlapTokens ?? DEFAULT_OVERLAP_TOKENS;
     this.batchSize = opts.batchSize ?? DEFAULT_BATCH_SIZE;
+    this._onProgress = opts.onProgress;
     if (this.chunkOverlapTokens >= this.chunkTokens) {
       throw new Error(`chunkOverlapTokens (${this.chunkOverlapTokens}) must be smaller than chunkTokens (${this.chunkTokens})`);
     }
     if (opts.pipelineInstance) {
       this._pipeline = opts.pipelineInstance;
+      this.actualDevice = this.device === "auto" ? null : this.device;
     }
   }
   async load() {
@@ -251,24 +260,70 @@ class LocalDetector {
     if (this._loadPromise)
       return this._loadPromise;
     this._loadPromise = (async () => {
-      let mod;
-      try {
-        mod = await import("@huggingface/transformers");
-      } catch (e) {
-        throw new Error("LocalDetector requires `@huggingface/transformers`. Install with: bun add @huggingface/transformers");
+      const mod = await loadTransformersJs();
+      const sequence = await this._planDeviceSequence();
+      let lastErr;
+      for (let i = 0;i < sequence.length; i++) {
+        const dev = sequence[i] ?? "wasm";
+        try {
+          const pipe = await mod.pipeline("token-classification", this.model, {
+            device: dev,
+            dtype: this.dtype,
+            progress_callback: this._onProgress ? (raw) => this._emitProgress(raw, dev) : undefined
+          });
+          this._pipeline = pipe;
+          this.actualDevice = dev;
+          return pipe;
+        } catch (e) {
+          lastErr = e;
+          if (i < sequence.length - 1)
+            continue;
+          throw e;
+        }
       }
-      const pipe = await mod.pipeline("token-classification", this.model, {
-        device: this.device,
-        dtype: this.dtype
-      });
-      this._pipeline = pipe;
-      return pipe;
+      throw lastErr ?? new Error("LocalDetector.load(): no candidate backends");
     })();
     return this._loadPromise;
   }
+  async _planDeviceSequence() {
+    if (this.device !== "auto")
+      return [this.device];
+    const seq = [];
+    const nav = typeof navigator !== "undefined" ? navigator : null;
+    if (nav?.gpu?.requestAdapter) {
+      try {
+        const adapter = await nav.gpu.requestAdapter();
+        if (adapter)
+          seq.push("webgpu");
+      } catch {}
+    }
+    seq.push("wasm");
+    return seq;
+  }
+  _emitProgress(raw, device) {
+    if (!this._onProgress)
+      return;
+    const event = {
+      phase: raw.status ?? "progress",
+      device
+    };
+    if (raw.file)
+      event.file = raw.file;
+    if (raw.status === "progress") {
+      if (raw.loaded != null)
+        event.loadedBytes = raw.loaded;
+      if (raw.total != null)
+        event.totalBytes = raw.total;
+      if (raw.progress != null) {
+        const norm = raw.progress > 1 ? raw.progress / 100 : raw.progress;
+        event.fraction = Math.max(0, Math.min(1, norm));
+      }
+    }
+    this._onProgress(event);
+  }
   async detect(text, opts) {
     if (opts?.model && opts.model !== this.model) {
-      throw new Error(`LocalDetector was constructed with model='${this.model}'; per-call model override ('${opts.model}') not supported.`);
+      throw new Error(`LocalDetector was constructed with model='${this.model}'; ` + `per-call model override ('${opts.model}') not supported.`);
     }
     if (!text)
       return [];
@@ -277,7 +332,7 @@ class LocalDetector {
   }
   async detectBatch(texts, opts) {
     if (opts?.model && opts.model !== this.model) {
-      throw new Error(`LocalDetector was constructed with model='${this.model}'; per-call model override ('${opts.model}') not supported.`);
+      throw new Error(`LocalDetector was constructed with model='${this.model}'; ` + `per-call model override ('${opts.model}') not supported.`);
     }
     if (texts.length === 0)
       return [];
@@ -438,102 +493,17 @@ function chunkByChars(text, chunkChars, overlapChars) {
 function normalizeWord(word) {
   return word.replace(/##/g, "").trim();
 }
-// src/detectors/index.ts
-function defaultDetector() {
-  const hasKey = typeof process !== "undefined" && Boolean(process.env?.GHEIM_API_KEY);
-  return hasKey ? new RemoteDetector : new LocalDetector;
-}
-
-// src/normalizers.ts
-import { createRequire as createRequire2 } from "node:module";
-var _require = null;
-var _requireResolved = false;
-function _getRequire() {
-  if (_requireResolved)
-    return _require;
-  _requireResolved = true;
-  try {
-    _require = createRequire2(import.meta.url);
-  } catch {
-    _require = null;
-  }
-  return _require;
-}
-function loadSync(name, errMsg) {
-  const req = _getRequire();
-  if (!req)
-    throw new Error(errMsg);
+async function loadTransformersJs() {
   try {
-    return req(name);
+    return await import("@huggingface/transformers");
   } catch {
-    throw new Error(errMsg);
+    throw new Error("LocalDetector requires `@huggingface/transformers`. Install with: bun add @huggingface/transformers");
   }
 }
-function loadPhoneLib() {
-  return loadSync("libphonenumber-js", "the e164 normalizer requires libphonenumber-js. " + "Install with: bun add libphonenumber-js");
-}
-function e164(opts = {}) {
-  const lib = loadPhoneLib();
-  return (s) => {
-    try {
-      const parsed = lib.parsePhoneNumberFromString(s, opts.region);
-      if (!parsed || !parsed.isValid())
-        return null;
-      return parsed.format("E.164");
-    } catch {
-      return null;
-    }
-  };
-}
-function loadChrono(opts) {
-  const mod = loadSync("chrono-node", "the isoDate normalizer requires chrono-node. " + "Install with: bun add chrono-node");
-  if (opts.locale) {
-    const localeParser = mod[opts.locale];
-    if (localeParser)
-      return localeParser;
-  }
-  return mod;
-}
-function isoDate(opts = {}) {
-  const parser = loadChrono(opts);
-  return (s) => {
-    const d = parser.parseDate(s);
-    if (!d)
-      return null;
-    return d.toISOString().slice(0, 10);
-  };
-}
-function germanTransliteration() {
-  const table = {
-    ä: "ae",
-    Ä: "ae",
-    ö: "oe",
-    Ö: "oe",
-    ü: "ue",
-    Ü: "ue",
-    ß: "ss"
-  };
-  return (s) => {
-    let out = "";
-    for (const ch of s.normalize("NFKC")) {
-      out += table[ch] ?? ch;
-    }
-    return out.toLowerCase().split(/\s+/).filter(Boolean).join(" ");
-  };
-}
-var BUILTINS = {
-  e164: () => e164(),
-  iso_date: () => isoDate(),
-  german: () => germanTransliteration()
-};
-function resolveNormalizer(spec) {
-  if (typeof spec === "function")
-    return spec;
-  const factory = BUILTINS[spec];
-  if (!factory) {
-    throw new Error(`unknown built-in normalizer: ${JSON.stringify(spec)}. ` + `Available: ${Object.keys(BUILTINS).join(", ")}, or pass a callable.`);
-  }
-  return factory();
+// src/detectors/index.ts
+function defaultDetector() {
+  const hasKey = typeof process !== "undefined" && Boolean(process.env?.GHEIM_API_KEY);
+  return hasKey ? new RemoteDetector : new LocalDetector;
 }
 
 // src/core/session.ts
@@ -548,8 +518,8 @@ class Session {
   resolvedNormalizers = {};
   constructor(opts = {}) {
     if (opts.normalizers) {
-      for (const [label, spec] of Object.entries(opts.normalizers)) {
-        this.resolvedNormalizers[label] = resolveNormalizer(spec);
+      for (const [label, fn] of Object.entries(opts.normalizers)) {
+        this.resolvedNormalizers[label] = fn;
       }
     }
   }
@@ -573,8 +543,11 @@ class Session {
     return sentinel;
   }
   applySpans(text, spans) {
+    return this.applySpansDetailed(text, spans).redacted;
+  }
+  applySpansDetailed(text, spans) {
     if (spans.length === 0)
-      return text;
+      return { redacted: text, merged: [] };
     const sorted = [...spans].sort((a, b) => a.start - b.start || b.end - b.start - (a.end - a.start));
     const merged = mergeAdjacent(text, sorted);
     const out = [];
@@ -590,7 +563,7 @@ class Session {
       cursor = end;
     }
     out.push(text.slice(cursor));
-    return out.join("");
+    return { redacted: out.join(""), merged };
   }
   restore(text) {
     if (Object.keys(this.mapping).length === 0)
@@ -823,6 +796,16 @@ function restoreChatResponse(response, session) {
     if (msg && typeof msg.content === "string") {
       msg.content = session.restore(msg.content);
     }
+    if (msg && typeof msg.reasoning === "string") {
+      msg.reasoning = session.restore(msg.reasoning);
+    }
+    if (msg && Array.isArray(msg.reasoning_details)) {
+      for (const r of msg.reasoning_details) {
+        if (r && typeof r.text === "string") {
+          r.text = session.restore(r.text);
+        }
+      }
+    }
     for (const tc of msg?.tool_calls ?? []) {
       const fn = tc.function;
       if (fn && typeof fn.arguments === "string") {
@@ -837,6 +820,16 @@ function patchChatChunk(chunk, buf) {
     if (typeof delta.content === "string") {
       delta.content = buf.feed(delta.content);
     }
+    if (typeof delta.reasoning === "string") {
+      delta.reasoning = buf.feed(delta.reasoning);
+    }
+    if (Array.isArray(delta.reasoning_details)) {
+      for (const r of delta.reasoning_details) {
+        if (r && typeof r.text === "string") {
+          r.text = buf.feed(r.text);
+        }
+      }
+    }
   }
 }
 function makeChatTailChunk(template, content) {
@@ -1163,9 +1156,20 @@ class OpenAI {
   gheimStrict;
   _clientPromise;
   constructor(opts = {}) {
-    const detector = opts.gheimDetector ?? defaultDetector();
-    this.gheimStrict = opts.gheimStrict ?? true;
-    this._clientPromise = opts.openaiClient ? Promise.resolve(opts.openaiClient) : loadOpenAI(opts.clientOptions);
+    const {
+      gheimDetector,
+      gheimStrict,
+      openaiClient,
+      clientOptions,
+      ...passthrough
+    } = opts;
+    const detector = gheimDetector ?? defaultDetector();
+    this.gheimStrict = gheimStrict ?? true;
+    const innerOpts = {
+      ...clientOptions ?? {},
+      ...passthrough
+    };
+    this._clientPromise = openaiClient ? Promise.resolve(openaiClient) : loadOpenAI(innerOpts);
     this._clientPromise.then((c) => {
       this.raw = c;
     });

package/dist/types/core/session.d.ts

@@ -1,15 +1,24 @@
 /** Session state — mirrors gheim-py's Session. */
 import type { Span } from "../detectors/base.ts";
-import type { Normalizer } from "../normalizers.ts";
+/** A surface canonicaliser. Maps a raw surface to a canonical key, or
+ *  null to fall back to the default NFKC + lowercase key. Re-declared
+ *  locally so this module doesn't pull in `gheim/normalizers` (which
+ *  uses Node's `createRequire` and breaks browser bundlers). */
+export type Normalizer = (s: string) => string | null;
 /** Constructor options for Session. */
 export interface SessionOptions {
     /**
      * Optional per-label canonical-form normalizers. Maps a label name
-     * (e.g. "private_phone") to either a built-in name ("e164" /
-     * "iso_date") or a callable Normalizer. Surfaces that fail to parse
-     * fall back to the default NFKC+lowercase key. See ./normalizers.ts.
+     * (e.g. "private_phone") to a callable Normalizer. Surfaces that fail
+     * to parse fall back to the default NFKC+lowercase key.
+     *
+     * Built-in factories (e164, isoDate, germanTransliteration) live in
+     * the `gheim/normalizers` subpath — they pull in optional peer deps
+     * (`libphonenumber-js`, `chrono-node`) so they're not loaded by
+     * default to keep the browser bundle small and avoid Node-only
+     * imports leaking into the main entry.
      */
-    normalizers?: Record<string, string | Normalizer>;
+    normalizers?: Record<string, Normalizer>;
 }
 export declare class Session {
     /** Sentinel string ("<PERSON_1>") → original surface form. */
@@ -19,7 +28,19 @@ export declare class Session {
     private resolvedNormalizers;
     constructor(opts?: SessionOptions);
     allocate(label: string, surface: string): string;
-    applySpans(text: string, spans: Span[]): string;
+    applySpans(text: string, spans: readonly (Span | MergedSpan)[]): string;
+    /**
+     * Like {@link applySpans} but also returns the post-merge span list. UI
+     * consumers (segment rendering, bar overlays) typically need both the
+     * redacted text and the merged spans so they can highlight the redacted
+     * runs at their original character positions; without this method they'd
+     * have to call {@link mergeAdjacent} again on the same input. Pure
+     * convenience — no extra cost over `applySpans`.
+     */
+    applySpansDetailed(text: string, spans: readonly (Span | MergedSpan)[]): {
+        redacted: string;
+        merged: MergedSpan[];
+    };
     restore(text: string): string;
     toJSON(): {
         mapping: Record<string, string>;
@@ -28,4 +49,19 @@ export declare class Session {
         mapping: Record<string, string>;
     }, opts?: SessionOptions): Session;
 }
+/** A span after merge: same shape as input, but no `text`/`score` carried. */
+export interface MergedSpan {
+    start: number;
+    end: number;
+    label: string;
+}
+/** Merge runs of adjacent same-label spans (BPE-split surface fix).
+ *
+ * Two same-label spans separated by ≤ MERGE_GAP characters of pure
+ * whitespace (or directly touching) collapse into one. Models tokenize
+ * a phone like "+41 44 268 12 34" into many single-space-separated
+ * pieces with the same label; merging recovers the original entity so
+ * the demo and SDK both see one PHONE span instead of five.
+ */
+export declare function mergeAdjacent(text: string, spans: readonly (Span | MergedSpan)[]): MergedSpan[];
 //# sourceMappingURL=session.d.ts.map

package/dist/types/core/session.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"session.d.ts","sourceRoot":"","sources":["../../../src/core/session.ts"],"names":[],"mappings":"AAAA,kDAAkD;AAClD,OAAO,KAAK,EAAE,IAAI,EAAE,MAAM,sBAAsB,CAAC;AAEjD,OAAO,KAAK,EAAE,UAAU,EAAE,MAAM,mBAAmB,CAAC;AAmBpD,uCAAuC;AACvC,MAAM,WAAW,cAAc;IAC7B;;;;;OAKG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,UAAU,CAAC,CAAC;CACnD;AAED,qBAAa,OAAO;IAClB,8DAA8D;IAC9D,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAM;IACrC,OAAO,CAAC,QAAQ,CAAkC;IAClD,OAAO,CAAC,QAAQ,CAAkC;IAClD,OAAO,CAAC,mBAAmB,CAAkC;gBAEjD,IAAI,GAAE,cAAmB;IAQrC,QAAQ,CAAC,KAAK,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,GAAG,MAAM;IAiBhD,UAAU,CAAC,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,IAAI,EAAE,GAAG,MAAM;IAoB/C,OAAO,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM;IAK7B,MAAM,IAAI;QAAE,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;KAAE;IAI7C,MAAM,CAAC,QAAQ,CACb,GAAG,EAAE;QAAE,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;KAAE,EACxC,IAAI,GAAE,cAAmB,GACxB,OAAO;CAqBX"}
+{"version":3,"file":"session.d.ts","sourceRoot":"","sources":["../../../src/core/session.ts"],"names":[],"mappings":"AAAA,kDAAkD;AAClD,OAAO,KAAK,EAAE,IAAI,EAAE,MAAM,sBAAsB,CAAC;AAGjD;;;gEAGgE;AAChE,MAAM,MAAM,UAAU,GAAG,CAAC,CAAC,EAAE,MAAM,KAAK,MAAM,GAAG,IAAI,CAAC;AAkBtD,uCAAuC;AACvC,MAAM,WAAW,cAAc;IAC7B;;;;;;;;;;OAUG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,UAAU,CAAC,CAAC;CAC1C;AAED,qBAAa,OAAO;IAClB,8DAA8D;IAC9D,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAM;IACrC,OAAO,CAAC,QAAQ,CAAkC;IAClD,OAAO,CAAC,QAAQ,CAAkC;IAClD,OAAO,CAAC,mBAAmB,CAAkC;gBAEjD,IAAI,GAAE,cAAmB;IAQrC,QAAQ,CAAC,KAAK,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,GAAG,MAAM;IAiBhD,UAAU,CAAC,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,SAAS,CAAC,IAAI,GAAG,UAAU,CAAC,EAAE,GAAG,MAAM;IAIvE;;;;;;;OAOG;IACH,kBAAkB,CAChB,IAAI,EAAE,MAAM,EACZ,KAAK,EAAE,SAAS,CAAC,IAAI,GAAG,UAAU,CAAC,EAAE,GACpC;QAAE,QAAQ,EAAE,MAAM,CAAC;QAAC,MAAM,EAAE,UAAU,EAAE,CAAA;KAAE;IAoB7C,OAAO,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM;IAK7B,MAAM,IAAI;QAAE,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;KAAE;IAI7C,MAAM,CAAC,QAAQ,CACb,GAAG,EAAE;QAAE,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;KAAE,EACxC,IAAI,GAAE,cAAmB,GACxB,OAAO;CAqBX;AAID,8EAA8E;AAC9E,MAAM,WAAW,UAAU;IACzB,KAAK,EAAE,MAAM,CAAC;IACd,GAAG,EAAE,MAAM,CAAC;IACZ,KAAK,EAAE,MAAM,CAAC;CACf;AAED;;;;;;;GAOG;AACH,wBAAgB,aAAa,CAC3B,IAAI,EAAE,MAAM,EACZ,KAAK,EAAE,SAAS,CAAC,IAAI,GAAG,UAAU,CAAC,EAAE,GACpC,UAAU,EAAE,CAqBd"}