fix(model): stop sending hidden form.provider as modelFactory on single-add + relocate generate_backfill_sql.py

backend/services/model_health_service.py

@@ -38,8 +38,17 @@ def _normalize_embedding_url(base_url: str) -> str:
 def _infer_model_factory(model_type: str, base_url: str, current_factory: Optional[str] = None) -> Optional[str]:
     """Infer model_factory from base_url if not already set or is generic.
 
-    Uses the shared W11 host map so embedding and LLM/VLM inference do not drift.
+    For embedding/multi_embedding, uses legacy logic (only dashscope) to avoid
+    changing existing behavior. For other types (VLM), uses extended inference
+    so tokenpony URLs can be recognized for catalog healthcheck.
     """
+    # Embedding types: keep legacy behavior (only dashscope)
+    if model_type in EMBEDDING_TYPES:
+        if "dashscope" in base_url.lower():
+            return DASHSCOPE_MODEL_FACTORY
+        return current_factory
+
+    # Non-embedding types (VLM, etc): use extended inference
     try:
         from services.model_capacity_suggestion_service import pick_provider_from_base_url
 

scripts/generate_backfill_sql.py → deploy/sql/migrations/generate_backfill_sql.py

@@ -2,7 +2,7 @@
 """Generate idempotent backfill SQL from capability_profiles.CATALOG.
 
 Usage:
-    python scripts/generate_backfill_sql.py > docker/sql/v2.2.x_MMDD_backfill_from_catalog.sql
+    python deploy/sql/migrations/generate_backfill_sql.py > deploy/sql/migrations/v2.2.x_MMDD_backfill_from_catalog.sql
 
 Run whenever capability_profiles.py changes, then commit the generated SQL.
 """
@@ -12,7 +12,7 @@
 from datetime import date
 from collections import namedtuple
 
-_project_root = os.path.join(os.path.dirname(__file__), "..")
+_project_root = os.path.join(os.path.dirname(__file__), "..", "..", "..")
 sys.path.insert(0, os.path.join(_project_root, "backend"))
 
 # Stub SDK types to avoid pulling in the full nexent SDK dependency chain
@@ -80,7 +80,7 @@
     today = date.today().strftime("%Y-%m-%d")
     lines: list[str] = []
 
-    lines.append(f"-- Generated by scripts/generate_backfill_sql.py on {today}")
+    lines.append(f"-- Generated by deploy/sql/migrations/generate_backfill_sql.py on {today}")
     lines.append(f"-- Catalog revision: {CATALOG_REVISION}")
     lines.append(f"-- Catalog entries: {len(CATALOG)}")
     lines.append("--")
@@ -120,15 +120,15 @@
     # --------------------------------------------------------------
     # Phase 1a: catalog match + bare -> fill capacity + tag
     # --------------------------------------------------------------
     lines.append("-- ============================================================")
     lines.append("-- Phase 1a: Backfill bare rows that match approved catalog entries")
     lines.append("-- ============================================================")
     lines.append("")
     lines.append("DO $$")
     lines.append("DECLARE")
     lines.append("    v_updated INTEGER := 0;")
     lines.append("    v_total   INTEGER := 0;")
     lines.append("    c_active_flag     CONSTANT TEXT := 'N';")
     lines.append("    c_source_profile  CONSTANT TEXT := 'profile';")
     lines.append("BEGIN")
 
@@ -144,26 +144,26 @@
             repo_match = _sql_repo_match(repo)
             escaped_name = _sql_str(name)
 
             lines.append(f"    UPDATE nexent.model_record_t")
             lines.append(f"       SET context_window_tokens = COALESCE(context_window_tokens,")
             lines.append(f"           GREATEST({_sql_int(ctx)}, COALESCE(max_output_tokens, 0) + 1)),")
             lines.append(f"           max_output_tokens = COALESCE(max_output_tokens,")
             lines.append(f"           LEAST({_sql_int(mout)}, COALESCE(context_window_tokens, {_sql_int(ctx)}) - 1)),")
             lines.append(f"           default_output_reserve_tokens = COALESCE(default_output_reserve_tokens,")
             lines.append(f"           LEAST({_sql_int(reserve)}, COALESCE(max_output_tokens, {_sql_int(mout)}))),")
             lines.append(f"           capacity_source = COALESCE(capacity_source, c_source_profile),")
             lines.append(f"           capability_profile_version = COALESCE(capability_profile_version, '{version}')")
             lines.append(f"     WHERE LOWER(model_factory) = '{_sql_str(provider.lower())}'")
             lines.append(f"       AND {repo_match}")
             lines.append(f"       AND model_name = '{escaped_name}'")
             lines.append(f"       AND delete_flag = c_active_flag")
             lines.append(f"       AND (context_window_tokens IS NULL OR max_output_tokens IS NULL);")
             lines.append(f"    GET DIAGNOSTICS v_updated = ROW_COUNT;")
             lines.append(f"    v_total := v_total + v_updated;")
             lines.append("")
 
     lines.append("    RAISE NOTICE 'Phase 1a catalog backfill (bare): % row(s) updated', v_total;")
     lines.append("END $$;")
     lines.append("")
 
     # --------------------------------------------------------------
@@ -198,18 +198,18 @@
             repo_match = _sql_repo_match(repo)
             escaped_name = _sql_str(name)
 
             lines.append(f"    UPDATE nexent.model_record_t")
             lines.append(f"       SET capability_profile_version = '{version}',")
             lines.append(f"           capacity_source = CASE WHEN capacity_source = c_source_default THEN c_source_profile ELSE capacity_source END")
             lines.append(f"     WHERE LOWER(model_factory) = '{_sql_str(provider.lower())}'")
             lines.append(f"       AND {repo_match}")
             lines.append(f"       AND model_name = '{escaped_name}'")
             lines.append(f"       AND delete_flag = c_active_flag")
             lines.append(f"       AND context_window_tokens = {_sql_int(ctx)}")
             lines.append(f"       AND max_output_tokens = {_sql_int(mout)}")
             lines.append(f"       AND (capability_profile_version IS NULL OR (capability_profile_version = '{version}' AND capacity_source = c_source_default));")
             lines.append(f"    GET DIAGNOSTICS v_updated = ROW_COUNT;")
             lines.append(f"    v_total := v_total + v_updated;")
             lines.append("")
 
     lines.append("    RAISE NOTICE 'Phase 1b catalog tag (matching filled): % row(s) updated', v_total;")
@@ -228,13 +228,13 @@
     lines.append("    c_source_default  CONSTANT TEXT := 'default';")
     lines.append("BEGIN")
     lines.append("    UPDATE nexent.model_record_t")
     lines.append(f"       SET context_window_tokens = COALESCE(context_window_tokens,")
     lines.append(f"           GREATEST({_sql_int(DEFAULT_CONTEXT_WINDOW)}, COALESCE(max_output_tokens, 0) + 1)),")
     lines.append(f"           max_output_tokens = COALESCE(max_output_tokens,")
     lines.append(f"           LEAST({_sql_int(DEFAULT_MAX_OUTPUT)}, COALESCE(context_window_tokens, {_sql_int(DEFAULT_CONTEXT_WINDOW)}) - 1)),")
     lines.append(f"           default_output_reserve_tokens = COALESCE(default_output_reserve_tokens,")
     lines.append(f"           LEAST({_sql_int(DEFAULT_RESERVE)}, COALESCE(max_output_tokens, {_sql_int(DEFAULT_MAX_OUTPUT)}))),")
     lines.append(f"           capacity_source = COALESCE(capacity_source, c_source_default)")
     lines.append("     WHERE delete_flag = c_active_flag")
     lines.append("       AND COALESCE(model_type, 'llm') IN ('llm', 'vlm')")
     lines.append("       AND (context_window_tokens IS NULL OR max_output_tokens IS NULL);")

frontend/app/[locale]/models/components/model/ModelAddDialog.tsx

@@ -1171,7 +1171,6 @@ export const ModelAddDialog = ({
           apiKey: form.apiKey.trim() === "" ? "sk-no-api-key" : form.apiKey,
           maxTokens: maxTokensValue,
           displayName: form.displayName || form.name,
-          modelFactory: form.provider,
           ...(supportsCapacityFields ? buildCapacityPayload(form) : {}),
           ...acceptSignalKwargs,
         };
@@ -1214,7 +1213,6 @@ export const ModelAddDialog = ({
           apiKey: form.apiKey.trim() === "" ? "sk-no-api-key" : form.apiKey,
           maxTokens: maxTokensValue,
           displayName: form.displayName || form.name,
-          modelFactory: form.provider,
           ...(supportsCapacityFields ? buildCapacityPayload(form) : {}),
           ...acceptSignalKwargs,
         };