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)

config.py

@@ -70,8 +70,8 @@ class Config:
 
     # ============== Quality Layer (L0) ==============
     # Track A1 of the dev plan — observability only, no behavior change.
-    # Set to "true" to enable. Default: false (opt-in).
-    QUALITY_L0_ENABLED = os.getenv("QUALITY_L0_ENABLED", "false").lower() == "true"
+    # Enabled by default since 2026-08-29: log-only, never blocks a job.
+    QUALITY_L0_ENABLED = os.getenv("QUALITY_L0_ENABLED", "true").lower() == "true"
     # Number of text samples to extract from the output file for L0 analysis.
     # Keep small to avoid overhead. 20 is enough to catch language confusion.
     QUALITY_L0_SAMPLE_SIZE = int(os.getenv("QUALITY_L0_SAMPLE_SIZE", "20"))
@@ -117,6 +117,22 @@ class Config:
     # Set to false to use the legacy aggressive-shrink strategy (NOT recommended).
     PDF_SMART_FIT_ENABLED = os.getenv("PDF_SMART_FIT_ENABLED", "true").lower() == "true"
 
+    # ============== Scanned PDF OCR (Mistral) ==============
+    # Image-only PDFs have no extractable text layer. When a PDF looks
+    # scanned, it is routed to the Mistral OCR API to recover the text
+    # before translation (output: clean re-typeset PDF).
+    # Pricing reference: ~$1 / 1000 pages — set MISTRAL_OCR_ENABLED=false
+    # to disable and reject scanned PDFs with an explicit error instead.
+    MISTRAL_API_KEY = os.getenv("MISTRAL_API_KEY", "").strip()
+    MISTRAL_OCR_MODEL = os.getenv("MISTRAL_OCR_MODEL", "mistral-ocr-latest")
+    MISTRAL_OCR_TIMEOUT = int(os.getenv("MISTRAL_OCR_TIMEOUT", "180"))
+    MISTRAL_OCR_ENABLED = os.getenv("MISTRAL_OCR_ENABLED", "true").lower() == "true"
+    # A page with fewer extractable characters than this is text-poor; it
+    # counts as a scan page only when raster images also cover most of it.
+    SCANNED_PDF_MIN_CHARS_PER_PAGE = int(
+        os.getenv("SCANNED_PDF_MIN_CHARS_PER_PAGE", "100")
+    )
+
 
     # ============== API Configuration ==============
     API_TITLE = "Document Translation API"