feat: split photo-import into vision recognition + text generation

The photo-import flow used one vision-capable model to both read the
photo and structure the full recipe (quantities, steps, timing) in a
single call. Split it into two: a vision model recognizes what's in
the picture, then a text model reconstructs the recipe from that
description — same pattern the pantry photo-scan already uses for
recognition, and lets structuring use whichever model is actually
configured for text generation. Still counts as one AI-quota unit.

v0.37.0

apps/web/messages/en.json

@@ -187,7 +187,8 @@
     "versionRestored": "Recipe restored to version {version}",
     "versionDetailLoading": "Loading...",
     "versionDetailSummary": "{ingredients, plural, one {1 ingredient} other {{ingredients} ingredients}}, {steps, plural, one {1 step} other {{steps} steps}}",
-    "analyzingPhoto": "Analyzing photo…",
+    "recognizingPhoto": "Recognizing what's in the photo…",
+    "writingRecipe": "Writing the recipe…",
     "pairMealTooltip": "Pair meal",
     "historyTooltip": "History",
     "translateTooltip": "Translate",