feat(image_gen): upgrade Recraft V3 → V4 Pro, Nano Banana → Pro (#11406)

* feat(image_gen): upgrade Recraft V3 → V4 Pro, Nano Banana → Pro

Upstream asked for these two upgrades ASAP — the old entries show
stale models when newer, higher-quality versions are available on FAL.

Recraft V3 → Recraft V4 Pro
  ID:    fal-ai/recraft-v3 → fal-ai/recraft/v4/pro/text-to-image
  Price: $0.04/image → $0.25/image (6x — V4 Pro is premium tier)
  Schema: V4 dropped the required `style` enum entirely; defaults
          handle taste now. Added `colors` and `background_color`
          to supports for brand-palette control. `seed` is not
          supported by V4 per the API docs.

Nano Banana → Nano Banana Pro
  ID:    fal-ai/nano-banana → fal-ai/nano-banana-pro
  Price: $0.08/image → $0.15/image (1K); $0.30 at 4K
  Schema: Aspect ratio family unchanged. Added `resolution`
          (1K/2K/4K, default 1K for billing predictability),
          `enable_web_search` (real-time info grounding, +$0.015),
          and `limit_generations` (force exactly 1 image).
  Architecture: Gemini 2.5 Flash → Gemini 3 Pro Image. Quality
                and reasoning depth improved; slower (~6s → ~8s).

Migration: users who had the old IDs in `image_gen.model` will
fall through the existing 'unknown model → default' warning path
in `_resolve_fal_model()` and get the Klein 9B default on the next
run. Re-run `hermes tools` → Image Generation to pick the new
version. No silent cost-upgrade aliasing — the 2-6x price jump
on these tiers warrants explicit user re-selection.

Portal note: both new model IDs need to be allowlisted on the
Nous fal-queue-gateway alongside the previous 7 additions, or
users on Nous Subscription will see the 'managed gateway rejected
model' error we added previously (which is clear and
self-remediating, just noisy).

* docs: wrap '<1s' in backticks to unblock MDX compilation

Docusaurus's MDX parser treats unquoted '<' as the start of JSX, and
'<1s' fails because '1' isn't a valid tag-name start character. This
was broken on main since PR #11265 (never noticed because
docs-site-checks was failing on OTHER issues at the time and we
admin-merged through it).

Wrapping in backticks also gives the cell monospace styling which
reads more cleanly alongside the inline-code model ID in the same row.

The other '<1s' occurrence (line 52) is inside a fenced code block
and is already safe — code fences bypass MDX parsing.

tools/image_generation_tool.py

@@ -134,11 +134,11 @@ FAL_MODELS: Dict[str, Dict[str, Any]] = {
         },
         "upscale": False,
     },
-    "fal-ai/nano-banana": {
-        "display": "Nano Banana (Gemini 2.5 Flash Image)",
-        "speed": "~6s",
-        "strengths": "Gemini 2.5, consistency",
-        "price": "$0.08/image",
+    "fal-ai/nano-banana-pro": {
+        "display": "Nano Banana Pro (Gemini 3 Pro Image)",
+        "speed": "~8s",
+        "strengths": "Gemini 3 Pro, reasoning depth, text rendering",
+        "price": "$0.15/image (1K)",
         "size_style": "aspect_ratio",
         "sizes": {
             "landscape": "16:9",
@@ -149,10 +149,14 @@ FAL_MODELS: Dict[str, Dict[str, Any]] = {
             "num_images": 1,
             "output_format": "png",
             "safety_tolerance": "5",
+            # "1K" is the cheapest tier; 4K doubles the per-image cost.
+            # Users on Nous Subscription should stay at 1K for predictable billing.
+            "resolution": "1K",
         },
         "supports": {
             "prompt", "aspect_ratio", "num_images", "output_format",
-            "safety_tolerance", "seed", "sync_mode",
+            "safety_tolerance", "seed", "sync_mode", "resolution",
+            "enable_web_search", "limit_generations",
         },
         "upscale": False,
     },
@@ -202,11 +206,11 @@ FAL_MODELS: Dict[str, Dict[str, Any]] = {
         },
         "upscale": False,
     },
-    "fal-ai/recraft-v3": {
-        "display": "Recraft V3",
+    "fal-ai/recraft/v4/pro/text-to-image": {
+        "display": "Recraft V4 Pro",
         "speed": "~8s",
-        "strengths": "Vector, brand styles",
-        "price": "$0.04/image",
+        "strengths": "Design, brand systems, production-ready",
+        "price": "$0.25/image",
         "size_style": "image_size_preset",
         "sizes": {
             "landscape": "landscape_16_9",
@@ -214,10 +218,12 @@ FAL_MODELS: Dict[str, Dict[str, Any]] = {
             "portrait": "portrait_16_9",
         },
         "defaults": {
-            "style": "realistic_image",
+            # V4 Pro dropped V3's required `style` enum — defaults handle taste now.
+            "enable_safety_checker": False,
         },
         "supports": {
-            "prompt", "image_size", "style",
+            "prompt", "image_size", "enable_safety_checker",
+            "colors", "background_color",
         },
         "upscale": False,
     },