feat(identify): detect China TC260 AIGC label (Doubao et al.)

China-served generators embed an XMP <TC260:AIGC>{"Label":"1",...} block
(China's mandatory AI-content labeling, TC260 standard). Doubao (ByteDance)
uses it -- verified on the real #13 sample. It's none of C2PA / SynthID /
imwatermark / IPTC, so identify() previously returned unknown.

- metadata: AIGC_MARKERS + aigc_label() (json-decodes the HTML-entity-encoded
  block); has_ai_metadata + get_ai_metadata now surface it.
- identify: new 'aigc' signal -> is_ai True, platform 'China AIGC-labeled
  generator (TC260; e.g. Doubao)', carries the ContentProducer code.
- Container-agnostic raw-byte scan, so it covers the whole China-AIGC ecosystem
  (Jimeng/Kling/Qwen/Ernie share the standard).
- Tests: synthetic TC260 block (metadata + identify). Docs updated.

Addresses #13.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/remove_ai_watermarks/identify.py

@@ -24,8 +24,10 @@ from typing import TYPE_CHECKING
 
 from remove_ai_watermarks.metadata import (
     AI_METADATA_KEYS,
+    AIGC_MARKERS,
     C2PA_UUID,
     IPTC_AI_MARKERS,
+    aigc_label,
     exif_generator,
     get_ai_metadata,
 )
@@ -219,6 +221,15 @@ def identify(image_path: Path, *, check_visible: bool = True, check_invisible: b
         if platform is None:
             platform = "Made-with-AI tag (e.g. Meta AI); platform not specified"
 
+    # ── China TC260 AIGC label (Doubao and other China-served gens) ──
+    aigc = any(m in head for m in AIGC_MARKERS)
+    if aigc:
+        producer = (aigc_label(image_path) or {}).get("ContentProducer", "")
+        signals.append(Signal("aigc", f"TC260 AIGC label{f' (producer {producer})' if producer else ''}", "high"))
+        watermarks.append("China AIGC label (TC260 standard)")
+        if platform is None:
+            platform = "China AIGC-labeled generator (TC260; e.g. Doubao)"
+
     # ── Local diffusion parameters (Stable Diffusion / ComfyUI) ──────
     local_keys = sorted(k for k in meta if k.lower() in _LOCAL_GEN_KEYS)
     if local_keys:
@@ -247,7 +258,9 @@ def identify(image_path: Path, *, check_visible: bool = True, check_invisible: b
     # ── Verdict so far (metadata + embedded watermark) ──────────────
     invisible_wm = any(s.name == "invisible_watermark" for s in signals)
     exif_gen = any(s.name == "exif_generator" for s in signals)
-    ai_from_metadata = bool((has_c2pa and (c2pa_is_ai or synthid)) or iptc or local_keys or invisible_wm or exif_gen)
+    ai_from_metadata = bool(
+        (has_c2pa and (c2pa_is_ai or synthid)) or iptc or aigc or local_keys or invisible_wm or exif_gen
+    )
 
     # ── Visible Gemini sparkle (fallback for stripped-metadata case) ─
     if check_visible and (conf := _visible_sparkle(image_path)) is not None and conf >= _SPARKLE_THRESHOLD:

src/remove_ai_watermarks/metadata.py

@@ -73,6 +73,17 @@ IPTC_AI_MARKERS: tuple[bytes, ...] = (
     b"compositeWithTrainedAlgorithmicMedia",
 )
 
+# China's mandatory AI-content labeling (TC260, the national cybersecurity
+# standards committee). AI generators serving China embed an XMP block in the
+# TC260 namespace -- ``<TC260:AIGC>{"Label":"1",...}``. Doubao (ByteDance) uses
+# this; the same standard is mandatory for Jimeng, Kling, Qwen, Ernie, etc.,
+# so the marker covers the whole China-AIGC-labeled ecosystem. Container-
+# agnostic (XMP is text), so a raw-byte scan catches it in PNG/JPEG/etc.
+AIGC_MARKERS: tuple[bytes, ...] = (
+    b"tc260.org.cn/ns/AIGC",
+    b"TC260:AIGC",
+)
+
 STANDARD_METADATA_KEYS: frozenset[str] = frozenset(
     [
         "Author",
@@ -139,9 +150,35 @@ def has_ai_metadata(image_path: Path) -> bool:
         return True
     if C2PA_UUID in data:
         return True
+    if any(marker in data for marker in AIGC_MARKERS):
+        return True
     return any(marker in data for marker in IPTC_AI_MARKERS)
 
 
+def aigc_label(image_path: Path) -> dict[str, str] | None:
+    """Parse a China TC260 ``<TC260:AIGC>`` AI-labeling block, if present.
+
+    Returns the decoded JSON (e.g. ``{"Label": "1", "ContentProducer": ...}``)
+    or None. The block is XMP text (HTML-entity encoded), so it is found by a
+    container-agnostic raw-byte scan and works for PNG/JPEG/WebP alike.
+    """
+    import html
+    import json
+    import re
+
+    with open(image_path, "rb") as f:
+        data = f.read(1024 * 1024)
+    match = re.search(rb"<TC260:AIGC>(.*?)</TC260:AIGC>", data, re.DOTALL)
+    if not match:
+        return None
+    raw = html.unescape(match.group(1).decode("utf-8", "replace"))
+    try:
+        parsed = json.loads(raw)
+    except ValueError:
+        return None
+    return {str(k): str(v) for k, v in parsed.items()} if isinstance(parsed, dict) else None
+
+
 def synthid_source(image_path: Path) -> str | None:
     """Return the vendor name(s) if the image carries a SynthID pixel watermark.
 
@@ -286,6 +323,11 @@ def get_ai_metadata(image_path: Path) -> dict[str, str]:
     # fall back to the format-agnostic source check for the SynthID verdict.
     if "synthid_watermark" not in result and (vendor := synthid_source(image_path)):
         result.setdefault("synthid_watermark", synthid_verdict(vendor))
+
+    # China TC260 AI-content label (Doubao and other China-served generators).
+    if aigc := aigc_label(image_path):
+        producer = aigc.get("ContentProducer", "")
+        result["aigc_label"] = f"China AIGC label (TC260){f'; producer {producer}' if producer else ''}"
     return result