feat: schema_version 3 with DE/EN field descriptions

Signed-off-by: flemming-it <sf@flemming.it>

module.yaml

@@ -1,54 +1,93 @@
-schema_version: 2
+schema_version: 3
 provider: fai
 name: text-anonymize
 version: 0.1.0
 
-# Capability provided by this module.
 provides:
   - capability: text.anonymize
     version: 0.1.0
 
-# Inputs the invoke function accepts.
 inputs:
-  # The text to anonymize. Plain UTF-8, any length the host
+  text:
-  # tolerates as a Payload::Text (operator policy caps).
+    type: text
-  text: text
+    description:
-  # Optional newline-separated list of additional bare terms
+      en: |
-  # (operator-supplied — names of people, organisations, or
+        The text to anonymize. Plain UTF-8, any length the host
-  # places that the regex patterns won't catch) to redact in
+        tolerates as a Payload::Text (operator policy caps).
-  # addition to the built-in categories. Empty string disables
+      de: |
-  # this extension. Each line is matched whole-word
+        Der zu anonymisierende Text. UTF-8, in jeder Länge die
-  # (case-insensitive).
+        der Host als Payload::Text zulässt (operator policy).
-  custom_terms: text
+  custom_terms:
+    type: text
+    description:
+      en: |
+        Optional newline-separated list of additional bare terms
+        (operator-supplied names of people, organisations, or
+        places the regex patterns won't catch) to redact in
+        addition to the built-in categories. Empty string
+        disables this extension. Each line is matched
+        whole-word, case-insensitive.
+      de: |
+        Optional zeilengetrennte Liste zusätzlicher Begriffe
+        (operator-gepflegte Namen von Personen, Organisationen
+        oder Orten, die die Regex-Patterns nicht abfangen), die
+        zusätzlich zu den eingebauten Kategorien geschwärzt
+        werden. Leer = Erweiterung aus. Jede Zeile wird
+        wortweise, case-insensitive, gematcht.
 
-# Outputs produced.
 outputs:
-  # The anonymized text. Each detected entity is replaced
+  anonymized:
-  # with a token of the shape ⟦TYPE_N⟧ where TYPE is the
+    type: text
-  # category (EMAIL, PHONE, IBAN, BIC, IPV4, GERMAN_TAX_ID,
+    description:
-  # NAME, CUSTOM) and N is a stable counter starting at 1
+      en: |
-  # per category, in order of first occurrence. The opening
+        The anonymized text. Each detected entity is replaced
-  # / closing characters are U+27E6 / U+27E7 (mathematical
+        with a token of the shape ⟦TYPE_N⟧ where TYPE is the
-  # white square brackets) so the token never collides with
+        category (EMAIL, PHONE, IBAN, BIC, IPV4, GERMAN_TAX_ID,
-  # plain `[…]` already present in the source.
+        NAME, CUSTOM) and N is a stable counter starting at 1
-  anonymized: text
+        per category, in order of first occurrence. The
-  # JSON report describing each redaction:
+        opening / closing characters are U+27E6 / U+27E7
-  #   {
+        (mathematical white square brackets) so the token never
-  #     "redactions": [
+        collides with plain […] already present in the source.
-  #       { "type": "EMAIL", "token": "⟦EMAIL_1⟧",
+      de: |
-  #         "original": "foo@bar.de", "offset": 42 }
+        Der anonymisierte Text. Jede erkannte Entität wird durch
-  #     ],
+        einen Token der Form ⟦TYPE_N⟧ ersetzt, wobei TYPE die
-  #     "counts": { "EMAIL": 3, "PHONE": 1, ... }
+        Kategorie ist (EMAIL, PHONE, IBAN, BIC, IPV4,
-  #   }
+        GERMAN_TAX_ID, NAME, CUSTOM) und N ein stabiler Zähler
-  # The full `original` text is included so the operator can
+        je Kategorie. Die Klammerzeichen sind U+27E6 / U+27E7,
-  # run a verify-pass against the redacted file (compliance:
+        damit der Token nie mit normalen […] aus der Quelle
-  # GDPR Art. 32(1)(a) "ability to undo" requirement). Hub
+        kollidiert.
-  # operators that want a pseudo-anonymisation-only flow can
+  report:
-  # discard this output downstream.
+    type: json
-  report: json
+    description:
+      en: |
+        JSON report describing each redaction:
+          {
+            "redactions": [
+              { "type": "EMAIL", "token": "⟦EMAIL_1⟧",
+                "original": "foo@bar.de", "offset": 42 }
+            ],
+            "counts": { "EMAIL": 3, "PHONE": 1, ... }
+          }
+        The full `original` text is included so the operator can
+        run a verify-pass against the redacted file (compliance:
+        GDPR Art. 32(1)(a) "ability to undo" requirement). Hub
+        operators that want a pseudo-anonymisation-only flow can
+        discard this output downstream.
+      de: |
+        JSON-Report mit jeder Schwärzung:
+          {
+            "redactions": [
+              { "type": "EMAIL", "token": "⟦EMAIL_1⟧",
+                "original": "foo@bar.de", "offset": 42 }
+            ],
+            "counts": { "EMAIL": 3, "PHONE": 1, ... }
+          }
+        Der vollständige `original`-Text ist enthalten, damit
+        Operatoren eine Verify-Pass gegen die geschwärzte Datei
+        fahren können (DSGVO Art. 32(1)(a) "Wiederherstellungs-
+        fähigkeit"). Wer Pseudo-Anonymisierung allein will,
+        verwirft diesen Output nachgelagert.
 
-# Permissions required.
-#
 # Pure-Rust, regex-only, in-WASM. No filesystem, no network,
-# no LLM. The empty list makes that explicit.
+# no LLM.
 permissions: []