feat(links): support ModelScope and TensorArt as model sources

A model file could only ever be linked to huggingface.co: `set_hf_url`
validated the URL with a huggingface-only regex, the agent fetched the card
from a hardcoded HF URL, and the readme processor built every relative image
path off `https://huggingface.co/{repo}/resolve/main`. ModelScope publishes the
same model-card convention (README.md + YAML frontmatter, often carrying
`base_model:` and `trigger_words:`) behind a public, key-less API, so the
enrichment pipeline could already serve it - it was the plumbing that was
HF-shaped, not the idea.

Make the external source a first-class, provider-driven concept:

- New `py/services/model_sources/` registry. A `ModelSource` owns URL
  recognition (lenient for stored values, strict for user input), the
  canonical page URL, model-card fetching, the asset base URL and the
  capability flags. `HuggingFaceSource` is the previous logic relocated;
  `ModelScopeSource` reads `/models/{o}/{n}/resolve/{master|main}/README.md`
  and falls back to `/api/v1/models/{o}/{n}/repo`. `TensorArtSource` is
  link-only on purpose: tensor.art answers plain HTTP clients with a
  Cloudflare challenge and its internal API (ap-east-1.tensorart.cloud /
  cn.tensorart.net) rejects every /v1/model/* route with "invalid
  authorization header", so it declares supports_enrichment=False rather than
  failing silently later.
- Metadata gains `source_platform` + `source_url`; `hf_url` stays as a
  read/write alias, written only for Hugging Face, so existing sidecars,
  cached rows and third-party consumers keep working. Normalisation runs at
  the scanner, the persistent cache (both directions, plus two new columns
  behind an ALTER migration) and the linking handler - which is what stops a
  user who switches sources from leaving a stale `hf_url` on a ModelScope
  model.
- The agent pipeline keys off the provider instead of `hf_url`: the fast-fail
  gate now explains *why* a model is skipped (no source / unknown source /
  source without a reachable card), the prompt context exposes
  source_url/source_id/source_label/asset_base_url while still filling the
  legacy hf_url/repo aliases, and the four README image extractors take a
  base_url (defaulting to HF) so relative paths resolve against the right
  site. Version grouping generalises to hf: / ms: / ta: keys.
- `POST /api/lm/set-hf-url` keeps its path and its legacy payload keys but
  accepts `source_url`, validates against every provider and returns the
  platform. `GET /api/lm/model-sources` lets the UI render the supported-site
  list from the server.
- Frontend: a `modelSourceHelpers` mirror of the registry drives the link
  dialog, the card/modal globe (branded "View on ModelScope/TensorArt"), the
  version-group key and the enrichment gate; the versions tab no longer sends
  ms:/ta: keys to the CivitAI API.

TensorArt stays in the list because provenance is worth keeping even when the
card is unreadable - the dialog says so plainly ("Sites that don't expose one
(currently TensorArt) can only be linked") and the context menu disables
enrichment with a matching tooltip, instead of the user getting
"Unsupported URL".

Verified against the real ModelScope API: jj3550945163/Krea-2-LORA returns a
1882-byte card whose frontmatter carries base_model/tags/trigger_words, and
relative images resolve to .../resolve/master/....

Tests: backend 2815 passed; frontend 1130 JS + 91 Vue passed; pytest
tests/i18n and a Jinja compile pass over templates/. The nine locales carry
[TODO: Translate] for the new strings, completed in the next commit.

locales/es.json

@@ -139,6 +139,7 @@
             "viewOnCivitai": "Ver en CivitAI",
             "notAvailableFromCivitai": "No disponible en CivitAI",
             "viewOnHuggingFace": "Ver en Hugging Face",
+            "viewOnSource": "[TODO: Translate] View on {source}",
             "sendToWorkflow": "Enviar a ComfyUI (Clic: Añadir, Shift+Clic: Reemplazar)",
             "copyLoRASyntax": "Copiar sintaxis de LoRA",
             "checkpointNameCopied": "Nombre del checkpoint copiado",
@@ -874,7 +875,7 @@
             "checkUpdates": "Comprobar actualizaciones",
             "linkModel": "Vincular modelo",
             "linkCivitai": "Re-vincular a CivitAI",
-            "linkHuggingFace": "Vincular a HuggingFace",
+            "linkModelSource": "[TODO: Translate] Link to Model Source",
             "copySyntax": "Copiar sintaxis de LoRA",
             "copyFilename": "Copiar nombre de archivo del modelo",
             "copyRecipeSyntax": "Copiar sintaxis de receta",
@@ -1596,13 +1597,17 @@
             "pathPlaceholder": "Escribe la ruta de la carpeta o selecciona del árbol de abajo...",
             "root": "Raíz"
         },
-        "linkHuggingFace": {
-            "title": "Vincular a HuggingFace",
-            "infoText": "Pegue la URL del repositorio de HuggingFace para asociar este modelo. Esto permite el enriquecimiento de metadatos con IA.",
-            "urlLabel": "URL del repositorio de HuggingFace:",
-            "urlPlaceholder": "https://huggingface.co/user/repo",
-            "helpText": "Ingrese la URL completa del repositorio de HuggingFace.",
-            "confirmAction": "Guardar y vincular"
+        "linkModelSource": {
+            "title": "[TODO: Translate] Link to Model Source",
+            "infoText": "[TODO: Translate] Paste the model page URL to associate this model with its source. Linking enables AI-powered metadata enrichment for Hugging Face and ModelScope models.",
+            "urlLabel": "[TODO: Translate] Model Page URL:",
+            "urlPlaceholder": "[TODO: Translate] https://huggingface.co/user/repo",
+            "helpText": "[TODO: Translate] Enter the full URL of the model page. Supported sites:",
+            "enrichNote": "[TODO: Translate] Note: AI metadata enrichment requires an accessible model card. TensorArt pages are not readable by the backend, so only the link is stored.",
+            "urlRequired": "[TODO: Translate] Please enter a model page URL.",
+            "invalidUrl": "[TODO: Translate] Unsupported URL. Supported sites: Hugging Face, ModelScope, TensorArt.",
+            "linking": "[TODO: Translate] Linking model source...",
+            "confirmAction": "[TODO: Translate] Save & Link"
         },
         "relinkCivitai": {
             "title": "Re-vincular a CivitAI",
@@ -1847,7 +1852,7 @@
                 "empty": "Aún no hay historial de versiones para este modelo.",
                 "error": "No se pudieron cargar las versiones.",
                 "missingModelId": "Este modelo no tiene un ID de modelo de CivitAI.",
-                "hfGroupInfo": "Este es un grupo de modelos de HuggingFace. Abra la biblioteca para ver todas las versiones en la cuadrícula.",
+                "sourceGroupInfo": "[TODO: Translate] This is a {source} model group. Open the library to see all versions in the grid.",
                 "confirm": {
                     "delete": "¿Eliminar esta versión de tu biblioteca?"
                 },
@@ -2483,7 +2488,9 @@
             "linkCivArchSuccess": "Modelo re-vinculado exitosamente mediante CivitArchive",
             "fetchMetadataFirst": "Por favor obtén metadatos de CivitAI primero",
             "noCivitaiInfo": "No hay información de CivitAI disponible",
-            "missingHash": "Hash del modelo no disponible"
+            "missingHash": "Hash del modelo no disponible",
+            "enrichNeedsSource": "[TODO: Translate] Link this model to a model source first (Link Model → Link to Model Source)",
+            "enrichUnsupportedSource": "[TODO: Translate] AI enrichment is not available for {source} models"
         },
         "exampleImages": {
             "pathUpdated": "Ruta de imágenes de ejemplo actualizada exitosamente",