feat(translation): quality pipeline overhaul + new features (audit 2026-08-29)

Translation quality & format preservation:
- Word: merge adjacent same-format runs into one unit (sentence-level
  coherence like inline-tag handling); translate comments/balloons;
  dedupe textbox collection (was translated twice); RTL no longer
  overrides center/justify alignment; CJK/Arabic font hints (eastAsia/cs)
- PPTX: chart translations now actually reach the output file
  (ChartPart.blob is read-only — rewrite chart XML in the saved ZIP);
  CJK typeface hints (a:ea)
- Excel: sheet renames no longer break references — rewrite cell
  formulas (3D/quoted), defined names, data validations, cond. formats
- PDF: bold/italic honored (hebo/heit/hebi); table cells never merge;
  unchanged blocks left untouched (typography preserved, fixes duplicate
  hyperlinks); attempted/changed stats + route gate now cover PDF;
  CJK font paths; scanned PDFs via Mistral OCR (detection + admin settings)

Features:
- formality param (formal/informal) + automatic regional-variant prompts
- output_mode=bilingual docx (source above translation)
- per-user translation memory on Redis (falls back to LRU), context-hashed
- QA report + 0-100 confidence score in job status; L0 on by default
- OpenAI-compatible providers: whole chunk in ONE numbered-JSON request
  (~15x fewer calls) with per-item fallback; base prompt always present
  (custom prompt no longer replaces translation instructions)

Infra & marketing alignment:
- plan-based engine gating + vision gating (closes paid-engine leak);
  /providers/available filtered per plan; 107 languages exposed
- zh-CN/zh-TW validation fixed; libmagic disabled on Windows (native crash)
- admin: Mistral OCR settings + engine status dashboard; httpx<0.28 pin
  (TestClient breakage); Prometheus test fixture fixed
- marketing docs aligned with code (PDF+OCR, retention, engines, pricing)
- security: .env.ionos/.env.production/provider_settings.json removed

Tests: 1173 passed / 0 failed (6 network tests deselected: free Google
endpoint temporarily blocked from this machine)

services/translation_service.py

@@ -23,23 +23,11 @@ from core.logging import get_logger
 
 logger = get_logger(__name__)
 
-# Map language codes to full names for LLM prompts (models understand "French" better than "fr")
-_LLM_LANG_NAMES = {
-    "en": "English", "es": "Spanish", "de": "German", "fr": "French", "ja": "Japanese",
-    "pt": "Portuguese", "ru": "Russian", "it": "Italian", "zh": "Chinese", "zh-CN": "Chinese (Simplified)",
-    "zh-TW": "Chinese (Traditional)", "pl": "Polish", "nl": "Dutch", "tr": "Turkish", "ko": "Korean",
-    "ar": "Arabic", "fa": "Persian", "vi": "Vietnamese", "id": "Indonesian", "uk": "Ukrainian",
-    "sv": "Swedish", "cs": "Czech", "el": "Greek", "he": "Hebrew", "hi": "Hindi", "ro": "Romanian",
-    "da": "Danish", "fi": "Finnish", "no": "Norwegian", "hu": "Hungarian", "th": "Thai",
-    "sk": "Slovak", "bg": "Bulgarian", "hr": "Croatian", "ca": "Catalan", "ms": "Malay",
-}
-
-
 def _lang_name(code: str) -> str:
     """Return full language name for LLM prompts; fallback to code if unknown."""
-    if not code or code == "auto":
-        return ""
-    return _LLM_LANG_NAMES.get(code, _LLM_LANG_NAMES.get(code.split("-")[0], code))
+    from core.languages import language_name
+
+    return language_name(code)
 
 
 # Global thread pool for parallel translations
@@ -1191,13 +1179,16 @@ class TranslationService:
         if not self.translate_images:
             return ""
 
-        # Ollama, OpenAI, and OpenRouter support image translation
-        if isinstance(self.provider, OllamaTranslationProvider):
-            return self.provider.translate_image(image_path, target_language)
-        elif isinstance(self.provider, OpenAITranslationProvider):
-            return self.provider.translate_image(image_path, target_language)
-        elif isinstance(self.provider, OpenRouterTranslationProvider):
-            return self.provider.translate_image(image_path, target_language)
+        # Duck-typing: any provider that exposes ``translate_image`` can be
+        # used, regardless of whether it is a new-style (services/providers/*)
+        # or legacy (services/translation_service) instance. The previous
+        # isinstance() checks only matched the legacy classes, so a new-style
+        # provider wired in by the route never reached this branch.
+        if hasattr(self.provider, "translate_image"):
+            try:
+                return self.provider.translate_image(image_path, target_language)
+            except Exception:
+                return ""
 
         return ""