gheim 0.1.8 → 0.1.10

package/dist/esm/openai/index.js

@@ -1,11 +1,3 @@
-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 = {
   private_person: "PERSON",
@@ -164,10 +156,40 @@ function trimSpan(text, start, end) {
     return null;
   return { start, end };
 }
+var WORD_CHAR = /[\p{L}\p{N}_]/u;
+var isWordChar = (ch) => ch !== undefined && WORD_CHAR.test(ch);
+function snapToWords(text, spans) {
+  const snapped = spans.map((sp) => {
+    let { start, end } = sp;
+    while (start > 0 && isWordChar(text[start - 1]) && isWordChar(text[start]))
+      start -= 1;
+    while (end < text.length && isWordChar(text[end - 1]) && isWordChar(text[end]))
+      end += 1;
+    return start === sp.start && end === sp.end ? sp : { ...sp, start, end, text: text.slice(start, end) };
+  });
+  snapped.sort((a, b) => a.start - b.start || a.end - b.end);
+  const merged = [];
+  const lastByLabel = new Map;
+  for (const sp of snapped) {
+    const i = lastByLabel.get(sp.label);
+    const prev = i === undefined ? undefined : merged[i];
+    if (i !== undefined && prev !== undefined && sp.start <= prev.end) {
+      const end = Math.max(prev.end, sp.end);
+      const wPrev = prev.end - prev.start;
+      const wSp = sp.end - sp.start;
+      const score = ((prev.score ?? 1) * wPrev + (sp.score ?? 1) * wSp) / (wPrev + wSp);
+      merged[i] = { ...prev, end, text: text.slice(prev.start, end), score };
+    } else {
+      lastByLabel.set(sp.label, merged.length);
+      merged.push(sp);
+    }
+  }
+  return merged.sort((a, b) => a.start - b.start || a.end - b.end);
+}
 
 // src/detectors/remote.ts
 var DEFAULT_BASE_URL = "https://api.gheim.ch";
-var DEFAULT_MODEL = "openai/privacy-filter";
+var DEFAULT_MODEL = "joelbarmettler/gheim-ch-560m";
 
 class RemoteDetector {
   baseUrl;
@@ -412,10 +434,7 @@ class LocalDetector {
         });
       }
     }
-    for (const spans of out) {
-      spans.sort((a, b) => a.start - b.start || a.end - b.end);
-    }
-    return out;
+    return out.map((spans, i) => snapToWords(texts[i] ?? "", spans));
   }
   async chunkText(text, tokenizer) {
     if (tokenizer) {
@@ -692,21 +711,136 @@ function maskSpans(text, spans) {
   return chars.join("");
 }
 
+class CustomPattern {
+  label;
+  group;
+  name;
+  regex;
+  validator;
+  constructor(opts) {
+    if (!/^[A-Za-z][A-Za-z0-9_]*$/.test(opts.label)) {
+      throw new Error(`CustomPattern label ${JSON.stringify(opts.label)} must start with a letter and contain ` + "only letters, digits and underscores (it becomes a <TAG_1> placeholder).");
+    }
+    this.label = opts.label;
+    this.name = opts.name ?? opts.label;
+    this.group = opts.group ?? 0;
+    this.validator = opts.validator;
+    const source = typeof opts.regex === "string" ? opts.regex : opts.regex.source;
+    const base = typeof opts.regex === "string" ? opts.flags ?? "i" : opts.regex.flags;
+    const flags = [...new Set([...base, "g", "d"])].join("");
+    this.regex = new RegExp(source, flags);
+    const groups = (new RegExp(`${source}|`, flags.replace(/[gd]/g, "")).exec("") ?? []).length - 1;
+    if (!Number.isInteger(this.group) || this.group < 0 || this.group > groups) {
+      throw new Error(`CustomPattern ${JSON.stringify(this.name)}: group ${this.group} does not exist ` + `(the pattern has ${groups}).`);
+    }
+  }
+  find(text) {
+    const out = [];
+    this.regex.lastIndex = 0;
+    let m;
+    while ((m = this.regex.exec(text)) !== null) {
+      if (m[0] === "") {
+        this.regex.lastIndex++;
+        continue;
+      }
+      const range = m.indices[this.group];
+      if (!range || range[0] === range[1])
+        continue;
+      const [start, end] = range;
+      const value = text.slice(start, end);
+      if (this.validator && !this.validator(value))
+        continue;
+      out.push({ start, end, label: this.label, text: value, score: 1 });
+    }
+    return out;
+  }
+}
+var NAME_PART = /[A-ZÀ-Ý][\p{L}\p{N}_'’-]{3,}/gu;
+var HONORIFICS = new Set([
+  "frau",
+  "herr",
+  "herrn",
+  "madame",
+  "monsieur",
+  "signora",
+  "signor",
+  "signore",
+  "dott",
+  "dottor",
+  "dottoressa",
+  "doktor",
+  "docteur",
+  "prof",
+  "professor",
+  "mister",
+  "miss",
+  "mrs"
+]);
+function escapeRegExp(s) {
+  return s.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
+}
+function propagateNames(text, spans, surnames) {
+  const names = new Set;
+  for (const sp of spans) {
+    if (sp.label !== "private_person")
+      continue;
+    const value = text.slice(sp.start, sp.end).trim();
+    if (value.length >= 4)
+      names.add(value);
+    if (surnames) {
+      for (const part of value.match(NAME_PART) ?? []) {
+        if (!HONORIFICS.has(part.toLowerCase()))
+          names.add(part);
+      }
+    }
+  }
+  let result = [...spans];
+  for (const name of [...names].sort((a, b) => b.length - a.length)) {
+    const re = new RegExp(`(?<![\\p{L}\\p{N}_])${escapeRegExp(name)}(?![\\p{L}\\p{N}_])`, "gu");
+    let m;
+    while ((m = re.exec(text)) !== null) {
+      const start = m.index;
+      const end = start + m[0].length;
+      const hits = result.filter((sp) => start < sp.end && sp.start < end);
+      if (hits.some((sp) => sp.start <= start && end <= sp.end))
+        continue;
+      if (hits.some((sp) => sp.start < start || end < sp.end))
+        continue;
+      result = result.filter((sp) => !hits.includes(sp));
+      result.push({ start, end, label: "private_person", text: m[0], score: 1 });
+    }
+  }
+  return result;
+}
+
 class CompositeDetector {
   model;
+  patterns;
+  propagateNames;
+  propagateSurnames;
   constructor(opts) {
     if (!opts || !opts.model) {
       throw new Error("CompositeDetector requires { model: Detector } — pass any object with " + "a .detect(text) method (e.g. new LocalDetector({...})).");
     }
     this.model = opts.model;
+    this.patterns = opts.patterns ?? [];
+    this.propagateNames = opts.propagateNames ?? true;
+    this.propagateSurnames = opts.propagateSurnames ?? false;
   }
   async detect(text, opts) {
     if (!text)
       return [];
     const regexSpans = findRegexSpans(text);
+    const extra = this.patterns.flatMap((p) => p.find(text));
+    extra.sort((a, b) => a.start !== b.start ? a.start - b.start : b.end - b.start - (a.end - a.start));
+    for (const sp of extra) {
+      if (!regexSpans.some((o) => sp.start < o.end && o.start < sp.end))
+        regexSpans.push(sp);
+    }
+    regexSpans.sort((a, b) => a.start - b.start);
     const masked = maskSpans(text, regexSpans);
     const modelSpans = await this.model.detect(masked, opts);
-    const out = [...regexSpans];
+    let out = [...regexSpans];
     const regexRanges = regexSpans.map((s) => [s.start, s.end]);
     for (const sp of modelSpans) {
       const overlaps = regexRanges.some(([rs, re]) => sp.start < re && rs < sp.end);
@@ -714,6 +848,8 @@ class CompositeDetector {
         continue;
       out.push(sp);
     }
+    if (this.propagateNames)
+      out = propagateNames(text, out, this.propagateSurnames);
     out.sort((a, b) => a.start !== b.start ? a.start - b.start : b.end - b.start - (a.end - a.start));
     return out;
   }
@@ -803,7 +939,7 @@ class CalibratedDetector {
     if (!text)
       return [];
     await this.load();
-    return this._detectChunked(text);
+    return snapToWords(text, await this._detectChunked(text));
   }
   async _detectChunked(text) {
     if (text.length <= 1500) {
@@ -870,15 +1006,21 @@ class CalibratedDetector {
           maxIdx = i;
         }
       }
-      tokenLabels.push({ id, label: this._id2label[maxIdx] ?? "O" });
+      let denom = 0;
+      for (let i = 0;i < row.length; i++)
+        denom += Math.exp(row[i] - maxVal);
+      tokenLabels.push({ id, label: this._id2label[maxIdx] ?? "O", prob: 1 / denom });
     }
     const spans = [];
     let cursor = 0;
     let groupIds = [];
+    let groupProbs = [];
     let groupCat = null;
     const flush = () => {
       if (groupCat === null || groupIds.length === 0)
         return;
+      const score = groupProbs.reduce((a, b) => a + b, 0) / groupProbs.length;
+      groupProbs = [];
       const surface = normalizeDecoded(tokenizer.decode(groupIds, { skip_special_tokens: true }));
       groupIds = [];
       const cat = groupCat;
@@ -900,17 +1042,19 @@ class CalibratedDetector {
         end: e + charOffset,
         label: cat,
         text: text.slice(s, e),
-        score: 1
+        score
       });
     };
-    for (const { id, label } of tokenLabels) {
+    for (const { id, label, prob } of tokenLabels) {
       const cat = label === "O" ? null : label.split("-", 2)[1] ?? null;
       if (cat === groupCat && cat !== null) {
         groupIds.push(id);
+        groupProbs.push(prob);
       } else {
         flush();
         if (cat !== null) {
           groupIds.push(id);
+          groupProbs.push(prob);
           groupCat = cat;
         }
       }
@@ -996,7 +1140,7 @@ function readLogits(tensor) {
 // src/detectors/index.ts
 function defaultDetector() {
   const hasKey = typeof process !== "undefined" && Boolean(process.env?.GHEIM_API_KEY);
-  return hasKey ? new RemoteDetector : new CalibratedDetector;
+  return hasKey ? new RemoteDetector : new CompositeDetector({ model: new CalibratedDetector });
 }
 
 // src/core/session.ts
@@ -1775,11 +1919,11 @@ async function* deanonymizeOpenAIStream(stream, session) {
   }
 }
 export {
-  deanonymizeOpenAIStream,
-  deanonymizeOpenAIResponse,
-  anonymizeOpenAIMessages,
-  STRICT_REASONS,
-  OpenAI,
+  AsyncOpenAI,
   GheimStrictError,
-  AsyncOpenAI
+  OpenAI,
+  STRICT_REASONS,
+  anonymizeOpenAIMessages,
+  deanonymizeOpenAIResponse,
+  deanonymizeOpenAIStream
 };

package/dist/types/detectors/base.d.ts

@@ -25,4 +25,17 @@ export interface Detector {
         model?: string;
     }): Promise<Span[]>;
 }
+/**
+ * Widen spans that start or end inside a word to the whole word, then merge
+ * same-label spans that overlap or touch.
+ *
+ * A token classifier sometimes tags only part of a word (`gano` of `Lugano`,
+ * `Zbind` + `en` of `Zbinden`), and a window boundary can cut a word in half.
+ * Masking a fragment leaves the rest of the word readable and splits one entity
+ * into two placeholders. A span is widened only when the characters on both
+ * sides of its edge are word characters, so edges at spaces or punctuation
+ * (`Gay` in `Gay-Crosier`) are left alone. The merged span's score is the
+ * length-weighted mean of its parts.
+ */
+export declare function snapToWords(text: string, spans: Span[]): Span[];
 //# sourceMappingURL=base.d.ts.map

package/dist/types/detectors/base.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"base.d.ts","sourceRoot":"","sources":["../../../src/detectors/base.ts"],"names":[],"mappings":"AAAA,gEAAgE;AAEhE;;;;;GAKG;AACH,wBAAgB,QAAQ,CACtB,IAAI,EAAE,MAAM,EACZ,KAAK,EAAE,MAAM,EACb,GAAG,EAAE,MAAM,GACV;IAAE,KAAK,EAAE,MAAM,CAAC;IAAC,GAAG,EAAE,MAAM,CAAA;CAAE,GAAG,IAAI,CAKvC;AAED,MAAM,WAAW,IAAI;IACnB,6CAA6C;IAC7C,KAAK,EAAE,MAAM,CAAC;IACd,yDAAyD;IACzD,KAAK,EAAE,MAAM,CAAC;IACd,iBAAiB;IACjB,GAAG,EAAE,MAAM,CAAC;IACZ,sDAAsD;IACtD,IAAI,EAAE,MAAM,CAAC;IACb,KAAK,CAAC,EAAE,MAAM,CAAC;CAChB;AAED,MAAM,WAAW,QAAQ;IACvB,MAAM,CAAC,IAAI,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE;QAAE,KAAK,CAAC,EAAE,MAAM,CAAA;KAAE,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC;CAClE"}
+{"version":3,"file":"base.d.ts","sourceRoot":"","sources":["../../../src/detectors/base.ts"],"names":[],"mappings":"AAAA,gEAAgE;AAEhE;;;;;GAKG;AACH,wBAAgB,QAAQ,CACtB,IAAI,EAAE,MAAM,EACZ,KAAK,EAAE,MAAM,EACb,GAAG,EAAE,MAAM,GACV;IAAE,KAAK,EAAE,MAAM,CAAC;IAAC,GAAG,EAAE,MAAM,CAAA;CAAE,GAAG,IAAI,CAKvC;AAED,MAAM,WAAW,IAAI;IACnB,6CAA6C;IAC7C,KAAK,EAAE,MAAM,CAAC;IACd,yDAAyD;IACzD,KAAK,EAAE,MAAM,CAAC;IACd,iBAAiB;IACjB,GAAG,EAAE,MAAM,CAAC;IACZ,sDAAsD;IACtD,IAAI,EAAE,MAAM,CAAC;IACb,KAAK,CAAC,EAAE,MAAM,CAAC;CAChB;AAED,MAAM,WAAW,QAAQ;IACvB,MAAM,CAAC,IAAI,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE;QAAE,KAAK,CAAC,EAAE,MAAM,CAAA;KAAE,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC;CAClE;AAKD;;;;;;;;;;;GAWG;AACH,wBAAgB,WAAW,CAAC,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,IAAI,EAAE,GAAG,IAAI,EAAE,CA0B/D"}

package/dist/types/detectors/calibrated.d.ts

@@ -1,31 +1,3 @@
-/**
- * Calibrated detector — subtracts a constant `oBias` from the O-class
- * logit before argmax. Originally introduced to recover the v1 model's
- * "single-category mode" pathology (Müller + IBAN co-occurrence flipped
- * the person prediction to O); the v3 / gheim-ch-560m training pipeline
- * largely resolved that pathology, but the calibration still buys a
- * small precision/recall improvement and remains the default.
- *
- * Sweep on gheim-ch-560m (see eval/calibration_sweep.json):
- * `oBias=0.5` is the Pareto-clean default — probe perfect-rate is flat
- * at 91.5% across bias 0.0 and 0.5, and test char-F1 lifts by 0.27pp.
- * Higher biases (1.0–1.5) trade test F1 for marginal probe gains.
- *
- * A separate sweep on the int8 ONNX path via `transformers.js`
- * (eval/calibration_sweep_q8.json) showed a much larger calibration
- * effect (+1.4pp probe, +0.43pp char-F1 at 0.5). That gap is not a
- * property of the int8 quantisation — Python `onnxruntime` on the same
- * int8 file gives 91.0% probe perfect-rate, essentially fp32-equivalent
- * — but of a runtime divergence inside `onnxruntime-web` / WASM that
- * the calibration partially papers over. The reliable fix is to use the
- * `model_fp16.onnx` variant when WebGPU is available (which is what
- * LocalDetector's default `dtype: "auto"` does); int8 should be treated
- * as a low-RAM fallback. See eval/q8_quality_report.md for the
- * diagnostic.
- *
- * `defaultDetector()` returns this with oBias=0.5, so users get the
- * better behavior automatically.
- */
 import type { Detector, Span } from "./base.ts";
 import type { LocalDetectorLoadEvent } from "./local.ts";
 /** Constructor options for {@link CalibratedDetector}. */

package/dist/types/detectors/calibrated.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"calibrated.d.ts","sourceRoot":"","sources":["../../../src/detectors/calibrated.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;GA2BG;AACH,OAAO,KAAK,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,WAAW,CAAC;AAChD,OAAO,KAAK,EAAE,sBAAsB,EAAE,MAAM,YAAY,CAAC;AAMzD,0DAA0D;AAC1D,MAAM,WAAW,yBAAyB;IACxC,kEAAkE;IAClE,KAAK,CAAC,EAAE,MAAM,CAAC;IACf;;;;;;;;;OASG;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,iEAAiE;IACjE,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,kEAAkE;IAClE,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,yDAAyD;IACzD,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,wDAAwD;IACxD,kBAAkB,CAAC,EAAE,MAAM,CAAC;IAC5B,8EAA8E;IAC9E,cAAc,CAAC,EAAE,OAAO,CAAC;IACzB,4EAA4E;IAC5E,UAAU,CAAC,EAAE,CAAC,KAAK,EAAE,sBAAsB,KAAK,IAAI,CAAC;CACtD;AA4CD,uDAAuD;AACvD,qBAAa,kBAAmB,YAAW,QAAQ;IACjD,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC;IACxB,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,QAAQ,CAAC,kBAAkB,EAAE,MAAM,CAAC;IACpC,QAAQ,CAAC,cAAc,EAAE,OAAO,CAAC;IACjC,oEAAoE;IACpE,YAAY,EAAE,MAAM,GAAG,IAAI,CAAQ;IACnC;sEACkE;IAClE,WAAW,EAAE,MAAM,GAAG,IAAI,CAAQ;IAClC,OAAO,CAAC,MAAM,CAA8B;IAC5C,OAAO,CAAC,UAAU,CAAkC;IACpD,OAAO,CAAC,SAAS,CAA8B;IAC/C,OAAO,CAAC,IAAI,CAAK;IACjB,OAAO,CAAC,YAAY,CAA8B;IAClD,OAAO,CAAC,QAAQ,CAAC,WAAW,CAAC,CAA0C;gBAE3D,IAAI,GAAE,yBAA8B;IAiB1C,IAAI,IAAI,OAAO,CAAC,IAAI,CAAC;IAoDrB,MAAM,CAAC,IAAI,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE;QAAE,KAAK,CAAC,EAAE,MAAM,CAAA;KAAE,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC;YAYxD,cAAc;YA0Bd,aAAa;IA6F3B,OAAO,CAAC,aAAa;CAiBtB"}
+{"version":3,"file":"calibrated.d.ts","sourceRoot":"","sources":["../../../src/detectors/calibrated.ts"],"names":[],"mappings":"AA6BA,OAAO,KAAK,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,WAAW,CAAC;AAChD,OAAO,KAAK,EAAE,sBAAsB,EAAE,MAAM,YAAY,CAAC;AAMzD,0DAA0D;AAC1D,MAAM,WAAW,yBAAyB;IACxC,kEAAkE;IAClE,KAAK,CAAC,EAAE,MAAM,CAAC;IACf;;;;;;;;;OASG;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,iEAAiE;IACjE,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,kEAAkE;IAClE,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,yDAAyD;IACzD,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,wDAAwD;IACxD,kBAAkB,CAAC,EAAE,MAAM,CAAC;IAC5B,8EAA8E;IAC9E,cAAc,CAAC,EAAE,OAAO,CAAC;IACzB,4EAA4E;IAC5E,UAAU,CAAC,EAAE,CAAC,KAAK,EAAE,sBAAsB,KAAK,IAAI,CAAC;CACtD;AA4CD,uDAAuD;AACvD,qBAAa,kBAAmB,YAAW,QAAQ;IACjD,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC;IACxB,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,QAAQ,CAAC,kBAAkB,EAAE,MAAM,CAAC;IACpC,QAAQ,CAAC,cAAc,EAAE,OAAO,CAAC;IACjC,oEAAoE;IACpE,YAAY,EAAE,MAAM,GAAG,IAAI,CAAQ;IACnC;sEACkE;IAClE,WAAW,EAAE,MAAM,GAAG,IAAI,CAAQ;IAClC,OAAO,CAAC,MAAM,CAA8B;IAC5C,OAAO,CAAC,UAAU,CAAkC;IACpD,OAAO,CAAC,SAAS,CAA8B;IAC/C,OAAO,CAAC,IAAI,CAAK;IACjB,OAAO,CAAC,YAAY,CAA8B;IAClD,OAAO,CAAC,QAAQ,CAAC,WAAW,CAAC,CAA0C;gBAE3D,IAAI,GAAE,yBAA8B;IAiB1C,IAAI,IAAI,OAAO,CAAC,IAAI,CAAC;IAoDrB,MAAM,CAAC,IAAI,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE;QAAE,KAAK,CAAC,EAAE,MAAM,CAAA;KAAE,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC;YAYxD,cAAc;YA0Bd,aAAa;IAuG3B,OAAO,CAAC,aAAa;CAiBtB"}

package/dist/types/detectors/composite.d.ts

@@ -29,11 +29,58 @@
  * detector.
  */
 import type { Detector, Span } from "./base.ts";
+/** Options for {@link CustomPattern}. */
+export interface CustomPatternOptions {
+    /** Label of the spans this rule produces. It becomes the placeholder tag
+     *  (`insurance_card` -> `<INSURANCE_CARD_1>`), so it must start with a
+     *  letter and contain only letters, digits and underscores. Reuse a
+     *  built-in label such as `account_number` to share its tag. */
+    label: string;
+    /** Pattern to search for. A string is compiled with `flags`; a RegExp
+     *  keeps its own flags. */
+    regex: string | RegExp;
+    /** Capture group that is the PII itself (0 = whole match). Lets a label
+     *  word anchor the match without being masked (`Pass-Nr. (X1234567)`). */
+    group?: number;
+    /** Flags for a string pattern. Default `"i"`. `g` and `d` are always added. */
+    flags?: string;
+    /** Receives the PII text; return false to reject the match (a checksum,
+     *  or a case check, since JS has no scoped `(?i:...)` flag). */
+    validator?: (value: string) => boolean;
+    /** Optional name for error messages. */
+    name?: string;
+}
+/** A user-supplied regex rule for formats that are specific to one
+ *  deployment (insurance card numbers, hospital record numbers, internal
+ *  case IDs, ...). Nothing in the library is domain-specific: the caller
+ *  passes the rules it needs to {@link CompositeDetector}.
+ *
+ *  Matches run in the regex front-end next to the built-in rules: the text
+ *  is masked before the model sees it, and a match wins over any model span
+ *  it overlaps. */
+export declare class CustomPattern {
+    readonly label: string;
+    readonly group: number;
+    readonly name: string;
+    private readonly regex;
+    private readonly validator;
+    constructor(opts: CustomPatternOptions);
+    /** Every non-empty, validated match of the PII group in `text`. */
+    find(text: string): Span[];
+}
 /** Options for {@link CompositeDetector}. */
 export interface CompositeDetectorOptions {
     /** Inner detector — usually a {@link LocalDetector}. Anything with
      *  a `detect(text) → Promise<Span[]>` method works. */
     model: Detector;
+    /** Extra regex rules for formats specific to your deployment. */
+    patterns?: CustomPattern[];
+    /** Mask every other occurrence of a string the model found as a person,
+     *  so a name caught once is not leaked by a later occurrence. Default true. */
+    propagateNames?: boolean;
+    /** With `propagateNames`: also propagate the individual capitalised parts
+     *  of each detected name. Higher recall, more false positives. Default false. */
+    propagateSurnames?: boolean;
 }
 /** Regex front-end (with checksum validation) + model on the remainder.
  *
@@ -48,6 +95,9 @@ export interface CompositeDetectorOptions {
  */
 export declare class CompositeDetector implements Detector {
     readonly model: Detector;
+    readonly patterns: readonly CustomPattern[];
+    readonly propagateNames: boolean;
+    readonly propagateSurnames: boolean;
     constructor(opts: CompositeDetectorOptions);
     /** Two-pass detection: regex first (with checksum), then model on
      *  the masked remainder. Returns a single overlap-resolved span list. */

package/dist/types/detectors/composite.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"composite.d.ts","sourceRoot":"","sources":["../../../src/detectors/composite.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA6BG;AACH,OAAO,KAAK,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,WAAW,CAAC;AAiNhD,6CAA6C;AAC7C,MAAM,WAAW,wBAAwB;IACvC;2DACuD;IACvD,KAAK,EAAE,QAAQ,CAAC;CACjB;AAED;;;;;;;;;;GAUG;AACH,qBAAa,iBAAkB,YAAW,QAAQ;IAChD,QAAQ,CAAC,KAAK,EAAE,QAAQ,CAAC;gBAEb,IAAI,EAAE,wBAAwB;IAU1C;6EACyE;IACnE,MAAM,CAAC,IAAI,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE;QAAE,KAAK,CAAC,EAAE,MAAM,CAAA;KAAE,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC;CAmBvE"}
+{"version":3,"file":"composite.d.ts","sourceRoot":"","sources":["../../../src/detectors/composite.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA6BG;AACH,OAAO,KAAK,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,WAAW,CAAC;AAiNhD,yCAAyC;AACzC,MAAM,WAAW,oBAAoB;IACnC;;;oEAGgE;IAChE,KAAK,EAAE,MAAM,CAAC;IACd;+BAC2B;IAC3B,KAAK,EAAE,MAAM,GAAG,MAAM,CAAC;IACvB;8EAC0E;IAC1E,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,+EAA+E;IAC/E,KAAK,CAAC,EAAE,MAAM,CAAC;IACf;oEACgE;IAChE,SAAS,CAAC,EAAE,CAAC,KAAK,EAAE,MAAM,KAAK,OAAO,CAAC;IACvC,wCAAwC;IACxC,IAAI,CAAC,EAAE,MAAM,CAAC;CACf;AAED;;;;;;;mBAOmB;AACnB,qBAAa,aAAa;IACxB,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IACtB,OAAO,CAAC,QAAQ,CAAC,KAAK,CAAS;IAC/B,OAAO,CAAC,QAAQ,CAAC,SAAS,CAA2C;gBAEzD,IAAI,EAAE,oBAAoB;IA0BtC,mEAAmE;IACnE,IAAI,CAAC,IAAI,EAAE,MAAM,GAAG,IAAI,EAAE;CAoB3B;AAwDD,6CAA6C;AAC7C,MAAM,WAAW,wBAAwB;IACvC;2DACuD;IACvD,KAAK,EAAE,QAAQ,CAAC;IAChB,iEAAiE;IACjE,QAAQ,CAAC,EAAE,aAAa,EAAE,CAAC;IAC3B;mFAC+E;IAC/E,cAAc,CAAC,EAAE,OAAO,CAAC;IACzB;qFACiF;IACjF,iBAAiB,CAAC,EAAE,OAAO,CAAC;CAC7B;AAED;;;;;;;;;;GAUG;AACH,qBAAa,iBAAkB,YAAW,QAAQ;IAChD,QAAQ,CAAC,KAAK,EAAE,QAAQ,CAAC;IACzB,QAAQ,CAAC,QAAQ,EAAE,SAAS,aAAa,EAAE,CAAC;IAC5C,QAAQ,CAAC,cAAc,EAAE,OAAO,CAAC;IACjC,QAAQ,CAAC,iBAAiB,EAAE,OAAO,CAAC;gBAExB,IAAI,EAAE,wBAAwB;IAa1C;6EACyE;IACnE,MAAM,CAAC,IAAI,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE;QAAE,KAAK,CAAC,EAAE,MAAM,CAAA;KAAE,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC;CA8BvE"}

package/dist/types/detectors/index.d.ts

@@ -3,16 +3,20 @@ export { DEFAULT_BASE_URL, DEFAULT_MODEL as REMOTE_DEFAULT_MODEL, RemoteDetector
 export type { RemoteDetectorOptions } from "./remote.ts";
 export { LocalDetector } from "./local.ts";
 export type { LocalDetectorOptions, LocalDetectorLoadEvent } from "./local.ts";
-export { CompositeDetector } from "./composite.ts";
-export type { CompositeDetectorOptions } from "./composite.ts";
+export { CompositeDetector, CustomPattern } from "./composite.ts";
+export type { CompositeDetectorOptions, CustomPatternOptions } from "./composite.ts";
 export { CalibratedDetector } from "./calibrated.ts";
 export type { CalibratedDetectorOptions } from "./calibrated.ts";
 import type { Detector } from "./base.ts";
 /** Pick a reasonable default: remote when `GHEIM_API_KEY` is set in env,
- *  else a calibrated local model.
+ *  else the composite detector (checksum regex front-end + calibrated local
+ *  model).
  *
- *  The calibrated default (`oBias=0.5`) is Pareto-clean on gheim-ch-560m:
- *  +0.27pp test char-F1 with no probe cost (91.5% perfect at both 0.0
- *  and 0.5). See eval/calibration_sweep.json. */
+ *  The calibrated model alone (`oBias=0.5`) is Pareto-clean on
+ *  gheim-ch-560m: +0.27pp test char-F1 with no probe cost (91.5% perfect at
+ *  both 0.0 and 0.5). See eval/calibration_sweep.json. The composite adds
+ *  what a token classifier cannot verify: checksummed IBAN / AHV / VAT /
+ *  card numbers, phone numbers, and repeated occurrences of a name it found
+ *  once. Use `new CalibratedDetector()` for the model alone. */
 export declare function defaultDetector(): Detector;
 //# sourceMappingURL=index.d.ts.map

package/dist/types/detectors/index.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/detectors/index.ts"],"names":[],"mappings":"AAAA,YAAY,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,WAAW,CAAC;AAChD,OAAO,EACL,gBAAgB,EAChB,aAAa,IAAI,oBAAoB,EACrC,cAAc,GACf,MAAM,aAAa,CAAC;AACrB,YAAY,EAAE,qBAAqB,EAAE,MAAM,aAAa,CAAC;AACzD,OAAO,EAAE,aAAa,EAAE,MAAM,YAAY,CAAC;AAC3C,YAAY,EAAE,oBAAoB,EAAE,sBAAsB,EAAE,MAAM,YAAY,CAAC;AAC/E,OAAO,EAAE,iBAAiB,EAAE,MAAM,gBAAgB,CAAC;AACnD,YAAY,EAAE,wBAAwB,EAAE,MAAM,gBAAgB,CAAC;AAC/D,OAAO,EAAE,kBAAkB,EAAE,MAAM,iBAAiB,CAAC;AACrD,YAAY,EAAE,yBAAyB,EAAE,MAAM,iBAAiB,CAAC;AAEjE,OAAO,KAAK,EAAE,QAAQ,EAAE,MAAM,WAAW,CAAC;AAI1C;;;;;iDAKiD;AACjD,wBAAgB,eAAe,IAAI,QAAQ,CAI1C"}
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/detectors/index.ts"],"names":[],"mappings":"AAAA,YAAY,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,WAAW,CAAC;AAChD,OAAO,EACL,gBAAgB,EAChB,aAAa,IAAI,oBAAoB,EACrC,cAAc,GACf,MAAM,aAAa,CAAC;AACrB,YAAY,EAAE,qBAAqB,EAAE,MAAM,aAAa,CAAC;AACzD,OAAO,EAAE,aAAa,EAAE,MAAM,YAAY,CAAC;AAC3C,YAAY,EAAE,oBAAoB,EAAE,sBAAsB,EAAE,MAAM,YAAY,CAAC;AAC/E,OAAO,EAAE,iBAAiB,EAAE,aAAa,EAAE,MAAM,gBAAgB,CAAC;AAClE,YAAY,EAAE,wBAAwB,EAAE,oBAAoB,EAAE,MAAM,gBAAgB,CAAC;AACrF,OAAO,EAAE,kBAAkB,EAAE,MAAM,iBAAiB,CAAC;AACrD,YAAY,EAAE,yBAAyB,EAAE,MAAM,iBAAiB,CAAC;AAEjE,OAAO,KAAK,EAAE,QAAQ,EAAE,MAAM,WAAW,CAAC;AAK1C;;;;;;;;;gEASgE;AAChE,wBAAgB,eAAe,IAAI,QAAQ,CAM1C"}

package/dist/types/detectors/local.d.ts

@@ -1,17 +1,3 @@
-/**
- * Local detector — runs the privacy-filter model in-process via @huggingface/transformers.
- *
- * Works in Node and the browser (with `device: 'webgpu'` for the latter).
- * `@huggingface/transformers` is an *optional peer dependency* — only needed
- * when this detector is actually instantiated.
- *
- * Long inputs (more tokens than the model's positional limit, typically
- * 512 for BERT/XLM-R/roberta encoders) are split into overlapping sliding
- * windows; spans from each window are reprojected to the original character
- * offsets and deduplicated. Without this, anything past ~512 tokens would
- * be silently truncated by the underlying pipeline. Multiple inputs and
- * within-input chunks are batched together for one forward pass.
- */
 import type { Detector, Span } from "./base.ts";
 export declare const DEFAULT_MODEL = "joelbarmettler/gheim-ch-560m";
 /** transformers.js token-classification options used by this detector. */

package/dist/types/detectors/local.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"local.d.ts","sourceRoot":"","sources":["../../../src/detectors/local.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;GAaG;AACH,OAAO,KAAK,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,WAAW,CAAC;AAEhD,eAAO,MAAM,aAAa,iCAAiC,CAAC;AAQ5D,0EAA0E;AAC1E,MAAM,WAAW,oBAAoB;IACnC,mEAAmE;IACnE,KAAK,CAAC,EAAE,MAAM,CAAC;IACf;;;;;;;;;OASG;IACH,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB;;;;;;;;OAQG;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,wDAAwD;IACxD,mBAAmB,CAAC,EAAE,MAAM,CAAC;IAC7B,+EAA+E;IAC/E,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB;;;OAGG;IACH,kBAAkB,CAAC,EAAE,MAAM,CAAC;IAC5B;;;OAGG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,6DAA6D;IAC7D,gBAAgB,CAAC,EAAE,OAAO,CAAC;IAC3B;;;;;OAKG;IACH,UAAU,CAAC,EAAE,CAAC,KAAK,EAAE,sBAAsB,KAAK,IAAI,CAAC;CACtD;AAED,uFAAuF;AACvF,MAAM,WAAW,sBAAsB;IACrC,yBAAyB;IACzB,KAAK,EAAE,UAAU,GAAG,UAAU,GAAG,UAAU,GAAG,OAAO,GAAG,MAAM,CAAC;IAC/D,6CAA6C;IAC7C,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,6DAA6D;IAC7D,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,4DAA4D;IAC5D,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB;wEACoE;IACpE,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB;;+EAE2E;IAC3E,MAAM,CAAC,EAAE,MAAM,CAAC;CACjB;AAED,UAAU,aAAa;IACrB,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,GAAG,CAAC,EAAE,MAAM,CAAC;IACb,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,KAAK,CAAC,EAAE,MAAM,CAAC;CAChB;AAED,KAAK,gBAAgB,GAAG,CACtB,IAAI,EAAE,MAAM,GAAG,MAAM,EAAE,EACvB,IAAI,CAAC,EAAE;IAAE,oBAAoB,CAAC,EAAE,MAAM,CAAC;IAAC,UAAU,CAAC,EAAE,MAAM,CAAA;CAAE,KAC1D,OAAO,CAAC,aAAa,EAAE,GAAG,aAAa,EAAE,EAAE,CAAC,CAAC;AAwBlD,qBAAa,aAAc,YAAW,QAAQ;IAC5C,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,kFAAkF;IAClF,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC;IACxB,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,QAAQ,CAAC,mBAAmB,EAAE,MAAM,CAAC;IACrC,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,QAAQ,CAAC,kBAAkB,EAAE,MAAM,CAAC;IACpC,QAAQ,CAAC,SAAS,EAAE,MAAM,CAAC;IAC3B;;0CAEsC;IACtC,YAAY,EAAE,MAAM,GAAG,IAAI,CAAQ;IACnC;;;gDAG4C;IAC5C,WAAW,EAAE,MAAM,GAAG,IAAI,CAAQ;IAClC,OAAO,CAAC,SAAS,CAAiC;IAClD,OAAO,CAAC,YAAY,CAA0C;IAC9D,OAAO,CAAC,QAAQ,CAAC,WAAW,CAAC,CAA0C;gBAE3D,IAAI,GAAE,oBAAyB;IAuB3C;;;;gFAI4E;IAC5E,OAAO,CAAC,aAAa;IAKrB;;;;;OAKG;IACG,IAAI,IAAI,OAAO,CAAC,gBAAgB,CAAC;IAoCvC;;;;;;;;OAQG;YACW,mBAAmB;IAsBjC,mFAAmF;IACnF,OAAO,CAAC,aAAa;IAqBf,MAAM,CAAC,IAAI,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE;QAAE,KAAK,CAAC,EAAE,MAAM,CAAA;KAAE,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC;IAYtE;;;;;OAKG;IACG,WAAW,CAAC,KAAK,EAAE,MAAM,EAAE,EAAE,IAAI,CAAC,EAAE;QAAE,KAAK,CAAC,EAAE,MAAM,CAAA;KAAE,GAAG,OAAO,CAAC,IAAI,EAAE,EAAE,CAAC;YAyFlE,SAAS;CAkBxB"}
+{"version":3,"file":"local.d.ts","sourceRoot":"","sources":["../../../src/detectors/local.ts"],"names":[],"mappings":"AAeA,OAAO,KAAK,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,WAAW,CAAC;AAEhD,eAAO,MAAM,aAAa,iCAAiC,CAAC;AAQ5D,0EAA0E;AAC1E,MAAM,WAAW,oBAAoB;IACnC,mEAAmE;IACnE,KAAK,CAAC,EAAE,MAAM,CAAC;IACf;;;;;;;;;OASG;IACH,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB;;;;;;;;OAQG;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,wDAAwD;IACxD,mBAAmB,CAAC,EAAE,MAAM,CAAC;IAC7B,+EAA+E;IAC/E,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB;;;OAGG;IACH,kBAAkB,CAAC,EAAE,MAAM,CAAC;IAC5B;;;OAGG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,6DAA6D;IAC7D,gBAAgB,CAAC,EAAE,OAAO,CAAC;IAC3B;;;;;OAKG;IACH,UAAU,CAAC,EAAE,CAAC,KAAK,EAAE,sBAAsB,KAAK,IAAI,CAAC;CACtD;AAED,uFAAuF;AACvF,MAAM,WAAW,sBAAsB;IACrC,yBAAyB;IACzB,KAAK,EAAE,UAAU,GAAG,UAAU,GAAG,UAAU,GAAG,OAAO,GAAG,MAAM,CAAC;IAC/D,6CAA6C;IAC7C,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,6DAA6D;IAC7D,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,4DAA4D;IAC5D,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB;wEACoE;IACpE,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB;;+EAE2E;IAC3E,MAAM,CAAC,EAAE,MAAM,CAAC;CACjB;AAED,UAAU,aAAa;IACrB,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,GAAG,CAAC,EAAE,MAAM,CAAC;IACb,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,KAAK,CAAC,EAAE,MAAM,CAAC;CAChB;AAED,KAAK,gBAAgB,GAAG,CACtB,IAAI,EAAE,MAAM,GAAG,MAAM,EAAE,EACvB,IAAI,CAAC,EAAE;IAAE,oBAAoB,CAAC,EAAE,MAAM,CAAC;IAAC,UAAU,CAAC,EAAE,MAAM,CAAA;CAAE,KAC1D,OAAO,CAAC,aAAa,EAAE,GAAG,aAAa,EAAE,EAAE,CAAC,CAAC;AAwBlD,qBAAa,aAAc,YAAW,QAAQ;IAC5C,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,kFAAkF;IAClF,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC;IACxB,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,QAAQ,CAAC,mBAAmB,EAAE,MAAM,CAAC;IACrC,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,QAAQ,CAAC,kBAAkB,EAAE,MAAM,CAAC;IACpC,QAAQ,CAAC,SAAS,EAAE,MAAM,CAAC;IAC3B;;0CAEsC;IACtC,YAAY,EAAE,MAAM,GAAG,IAAI,CAAQ;IACnC;;;gDAG4C;IAC5C,WAAW,EAAE,MAAM,GAAG,IAAI,CAAQ;IAClC,OAAO,CAAC,SAAS,CAAiC;IAClD,OAAO,CAAC,YAAY,CAA0C;IAC9D,OAAO,CAAC,QAAQ,CAAC,WAAW,CAAC,CAA0C;gBAE3D,IAAI,GAAE,oBAAyB;IAuB3C;;;;gFAI4E;IAC5E,OAAO,CAAC,aAAa;IAKrB;;;;;OAKG;IACG,IAAI,IAAI,OAAO,CAAC,gBAAgB,CAAC;IAoCvC;;;;;;;;OAQG;YACW,mBAAmB;IAsBjC,mFAAmF;IACnF,OAAO,CAAC,aAAa;IAqBf,MAAM,CAAC,IAAI,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE;QAAE,KAAK,CAAC,EAAE,MAAM,CAAA;KAAE,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC;IAYtE;;;;;OAKG;IACG,WAAW,CAAC,KAAK,EAAE,MAAM,EAAE,EAAE,IAAI,CAAC,EAAE;QAAE,KAAK,CAAC,EAAE,MAAM,CAAA;KAAE,GAAG,OAAO,CAAC,IAAI,EAAE,EAAE,CAAC;YAsFlE,SAAS;CAkBxB"}

package/dist/types/detectors/remote.d.ts

@@ -1,7 +1,7 @@
 /** Remote detector — calls a gheim-server (or compatible) over HTTP. */
 import { type Detector, type Span } from "./base.ts";
 export declare const DEFAULT_BASE_URL = "https://api.gheim.ch";
-export declare const DEFAULT_MODEL = "openai/privacy-filter";
+export declare const DEFAULT_MODEL = "joelbarmettler/gheim-ch-560m";
 export interface RemoteDetectorOptions {
     baseUrl?: string;
     apiKey?: string;

package/dist/types/detectors/remote.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"remote.d.ts","sourceRoot":"","sources":["../../../src/detectors/remote.ts"],"names":[],"mappings":"AAAA,wEAAwE;AACxE,OAAO,EAAE,KAAK,QAAQ,EAAE,KAAK,IAAI,EAAY,MAAM,WAAW,CAAC;AAE/D,eAAO,MAAM,gBAAgB,yBAAyB,CAAC;AACvD,eAAO,MAAM,aAAa,0BAA0B,CAAC;AAErD,MAAM,WAAW,qBAAqB;IACpC,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,wEAAwE;IACxE,cAAc,CAAC,EAAE,OAAO,CAAC;IACzB,KAAK,CAAC,EAAE,OAAO,KAAK,CAAC;CACtB;AAED,qBAAa,cAAe,YAAW,QAAQ;IAC7C,OAAO,CAAC,QAAQ,CAAC,OAAO,CAAS;IACjC,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAS;IACjC,OAAO,CAAC,QAAQ,CAAC,KAAK,CAAS;IAC/B,OAAO,CAAC,QAAQ,CAAC,cAAc,CAAU;IACzC,OAAO,CAAC,QAAQ,CAAC,SAAS,CAAe;gBAE7B,IAAI,GAAE,qBAA0B;IAUtC,MAAM,CAAC,IAAI,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE;QAAE,KAAK,CAAC,EAAE,MAAM,CAAA;KAAE,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC;CA+BvE"}
+{"version":3,"file":"remote.d.ts","sourceRoot":"","sources":["../../../src/detectors/remote.ts"],"names":[],"mappings":"AAAA,wEAAwE;AACxE,OAAO,EAAE,KAAK,QAAQ,EAAE,KAAK,IAAI,EAAY,MAAM,WAAW,CAAC;AAE/D,eAAO,MAAM,gBAAgB,yBAAyB,CAAC;AACvD,eAAO,MAAM,aAAa,iCAAiC,CAAC;AAE5D,MAAM,WAAW,qBAAqB;IACpC,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,wEAAwE;IACxE,cAAc,CAAC,EAAE,OAAO,CAAC;IACzB,KAAK,CAAC,EAAE,OAAO,KAAK,CAAC;CACtB;AAED,qBAAa,cAAe,YAAW,QAAQ;IAC7C,OAAO,CAAC,QAAQ,CAAC,OAAO,CAAS;IACjC,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAS;IACjC,OAAO,CAAC,QAAQ,CAAC,KAAK,CAAS;IAC/B,OAAO,CAAC,QAAQ,CAAC,cAAc,CAAU;IACzC,OAAO,CAAC,QAAQ,CAAC,SAAS,CAAe;gBAE7B,IAAI,GAAE,qBAA0B;IAUtC,MAAM,CAAC,IAAI,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE;QAAE,KAAK,CAAC,EAAE,MAAM,CAAA;KAAE,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC;CA+BvE"}

package/dist/types/index.d.ts

@@ -13,8 +13,8 @@ export { LABEL_TO_TAG, SENTINEL_RE, isPossibleSentinelPrefix, labelTag, parseSen
 export type { Sentinel } from "./core/sentinels.ts";
 export { StreamDeanonymizer } from "./core/stream.ts";
 export type { Detector, Span } from "./detectors/base.ts";
-export { DEFAULT_BASE_URL, REMOTE_DEFAULT_MODEL, RemoteDetector, LocalDetector, CompositeDetector, CalibratedDetector, defaultDetector, } from "./detectors/index.ts";
-export type { RemoteDetectorOptions, LocalDetectorOptions, LocalDetectorLoadEvent, CompositeDetectorOptions, CalibratedDetectorOptions, } from "./detectors/index.ts";
+export { DEFAULT_BASE_URL, REMOTE_DEFAULT_MODEL, RemoteDetector, LocalDetector, CompositeDetector, CustomPattern, CalibratedDetector, defaultDetector, } from "./detectors/index.ts";
+export type { RemoteDetectorOptions, LocalDetectorOptions, LocalDetectorLoadEvent, CompositeDetectorOptions, CustomPatternOptions, CalibratedDetectorOptions, } from "./detectors/index.ts";
 export { anonymizeMessages, anonymizeText, deanonymizeStream, deanonymizeText, } from "./plain.ts";
 export type { ChatMessage } from "./plain.ts";
 export declare const VERSION = "0.1.6";

package/dist/types/index.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../src/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AACH,OAAO,EAAE,OAAO,EAAE,MAAM,mBAAmB,CAAC;AAC5C,YAAY,EAAE,UAAU,EAAE,cAAc,EAAE,MAAM,mBAAmB,CAAC;AACpE,OAAO,EACL,YAAY,EACZ,WAAW,EACX,wBAAwB,EACxB,QAAQ,EACR,aAAa,EACb,cAAc,GACf,MAAM,qBAAqB,CAAC;AAC7B,YAAY,EAAE,QAAQ,EAAE,MAAM,qBAAqB,CAAC;AACpD,OAAO,EAAE,kBAAkB,EAAE,MAAM,kBAAkB,CAAC;AACtD,YAAY,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,qBAAqB,CAAC;AAC1D,OAAO,EACL,gBAAgB,EAChB,oBAAoB,EACpB,cAAc,EACd,aAAa,EACb,iBAAiB,EACjB,kBAAkB,EAClB,eAAe,GAChB,MAAM,sBAAsB,CAAC;AAC9B,YAAY,EACV,qBAAqB,EACrB,oBAAoB,EACpB,sBAAsB,EACtB,wBAAwB,EACxB,yBAAyB,GAC1B,MAAM,sBAAsB,CAAC;AAC9B,OAAO,EACL,iBAAiB,EACjB,aAAa,EACb,iBAAiB,EACjB,eAAe,GAChB,MAAM,YAAY,CAAC;AACpB,YAAY,EAAE,WAAW,EAAE,MAAM,YAAY,CAAC;AAK9C,eAAO,MAAM,OAAO,UAAU,CAAC;AAE/B,OAAO,EAAE,aAAa,EAAE,MAAM,mBAAmB,CAAC;AAClD,YAAY,EAAE,UAAU,EAAE,MAAM,mBAAmB,CAAC"}
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../src/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AACH,OAAO,EAAE,OAAO,EAAE,MAAM,mBAAmB,CAAC;AAC5C,YAAY,EAAE,UAAU,EAAE,cAAc,EAAE,MAAM,mBAAmB,CAAC;AACpE,OAAO,EACL,YAAY,EACZ,WAAW,EACX,wBAAwB,EACxB,QAAQ,EACR,aAAa,EACb,cAAc,GACf,MAAM,qBAAqB,CAAC;AAC7B,YAAY,EAAE,QAAQ,EAAE,MAAM,qBAAqB,CAAC;AACpD,OAAO,EAAE,kBAAkB,EAAE,MAAM,kBAAkB,CAAC;AACtD,YAAY,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,qBAAqB,CAAC;AAC1D,OAAO,EACL,gBAAgB,EAChB,oBAAoB,EACpB,cAAc,EACd,aAAa,EACb,iBAAiB,EACjB,aAAa,EACb,kBAAkB,EAClB,eAAe,GAChB,MAAM,sBAAsB,CAAC;AAC9B,YAAY,EACV,qBAAqB,EACrB,oBAAoB,EACpB,sBAAsB,EACtB,wBAAwB,EACxB,oBAAoB,EACpB,yBAAyB,GAC1B,MAAM,sBAAsB,CAAC;AAC9B,OAAO,EACL,iBAAiB,EACjB,aAAa,EACb,iBAAiB,EACjB,eAAe,GAChB,MAAM,YAAY,CAAC;AACpB,YAAY,EAAE,WAAW,EAAE,MAAM,YAAY,CAAC;AAK9C,eAAO,MAAM,OAAO,UAAU,CAAC;AAE/B,OAAO,EAAE,aAAa,EAAE,MAAM,mBAAmB,CAAC;AAClD,YAAY,EAAE,UAAU,EAAE,MAAM,mBAAmB,CAAC"}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gheim",
-  "version": "0.1.8",
+  "version": "0.1.10",
   "description": "PII round-trip for LLM APIs: anonymize before the request, de-anonymize the stream on the way back.",
   "license": "Apache-2.0",
   "author": "Joel Barmettler <joel.barmettler@gmail.com>",