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

Author: teknium1

tests/tools/test_image_generation.py

@@ -107,16 +107,16 @@ class TestAspectRatioFamily:
     """Nano-banana uses aspect_ratio enum, NOT image_size."""
 
     def test_nano_banana_landscape_uses_aspect_ratio(self, image_tool):
-        p = image_tool._build_fal_payload("fal-ai/nano-banana", "hello", "landscape")
+        p = image_tool._build_fal_payload("fal-ai/nano-banana-pro", "hello", "landscape")
         assert p["aspect_ratio"] == "16:9"
         assert "image_size" not in p
 
     def test_nano_banana_square_uses_aspect_ratio(self, image_tool):
-        p = image_tool._build_fal_payload("fal-ai/nano-banana", "hello", "square")
+        p = image_tool._build_fal_payload("fal-ai/nano-banana-pro", "hello", "square")
         assert p["aspect_ratio"] == "1:1"
 
     def test_nano_banana_portrait_uses_aspect_ratio(self, image_tool):
-        p = image_tool._build_fal_payload("fal-ai/nano-banana", "hello", "portrait")
+        p = image_tool._build_fal_payload("fal-ai/nano-banana-pro", "hello", "portrait")
         assert p["aspect_ratio"] == "9:16"
 
 
@@ -164,13 +164,17 @@ def test_gpt_image_strips_unsupported_overrides(self, image_tool):
         assert "num_inference_steps" not in p
 
     def test_recraft_has_minimal_payload(self, image_tool):
-        # Recraft supports prompt, image_size, style only.
-        p = image_tool._build_fal_payload("fal-ai/recraft-v3", "hi", "landscape")
-        assert set(p.keys()) <= {"prompt", "image_size", "style"}
+        # Recraft V4 Pro supports prompt, image_size, enable_safety_checker,
+        # colors, background_color (no seed, no style — V4 dropped V3's style enum).
+        p = image_tool._build_fal_payload("fal-ai/recraft/v4/pro/text-to-image", "hi", "landscape")
+        assert set(p.keys()) <= {
+            "prompt", "image_size", "enable_safety_checker",
+            "colors", "background_color",
+        }
 
     def test_nano_banana_never_gets_image_size(self, image_tool):
         # Common bug: translator accidentally setting both image_size and aspect_ratio.
-        p = image_tool._build_fal_payload("fal-ai/nano-banana", "hi", "landscape", seed=1)
+        p = image_tool._build_fal_payload("fal-ai/nano-banana-pro", "hi", "landscape", seed=1)
         assert "image_size" not in p
         assert p["aspect_ratio"] == "16:9"
 
@@ -285,9 +289,9 @@ def test_env_var_fallback_when_no_config(self, image_tool, monkeypatch):
     def test_config_wins_over_env_var(self, image_tool, monkeypatch):
         monkeypatch.setenv("FAL_IMAGE_MODEL", "fal-ai/z-image/turbo")
         with patch("hermes_cli.config.load_config",
-                   return_value={"image_gen": {"model": "fal-ai/nano-banana"}}):
+                   return_value={"image_gen": {"model": "fal-ai/nano-banana-pro"}}):
             mid, _ = image_tool._resolve_fal_model()
-        assert mid == "fal-ai/nano-banana"
+        assert mid == "fal-ai/nano-banana-pro"
 
 
 # ---------------------------------------------------------------------------
@@ -387,10 +391,10 @@ def test_4xx_translates_to_value_error_with_remediation(self, image_tool, monkey
                             lambda gw: mock_managed_client)
 
         with pytest.raises(ValueError) as exc_info:
-            image_tool._submit_fal_request("fal-ai/nano-banana", {"prompt": "x"})
+            image_tool._submit_fal_request("fal-ai/nano-banana-pro", {"prompt": "x"})
 
         msg = str(exc_info.value)
-        assert "fal-ai/nano-banana" in msg
+        assert "fal-ai/nano-banana-pro" in msg
         assert "403" in msg
         assert "FAL_KEY" in msg
         assert "hermes tools" in msg

tools/image_generation_tool.py

@@ -134,11 +134,11 @@
         },
         "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 @@
             "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,
     },
@@ -202,22 +206,24 @@
         },
         "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",
             "square": "square_hd",
             "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,
     },

website/docs/user-guide/features/image-generation.md

@@ -1,6 +1,6 @@
 ---
 title: Image Generation
-description: Generate images via FAL.ai — 8 models including FLUX 2, GPT-Image, Nano Banana, Ideogram, and more, selectable via `hermes tools`.
+description: Generate images via FAL.ai — 8 models including FLUX 2, GPT-Image, Nano Banana Pro, Ideogram, Recraft V4 Pro, and more, selectable via `hermes tools`.
 sidebar_label: Image Generation
 sidebar_position: 6
 ---
@@ -13,13 +13,13 @@ Hermes Agent generates images from text prompts via FAL.ai. Eight models are sup
 
 | Model | Speed | Strengths | Price |
 |---|---|---|---|
-| `fal-ai/flux-2/klein/9b` *(default)* | <1s | Fast, crisp text | $0.006/MP |
+| `fal-ai/flux-2/klein/9b` *(default)* | `<1s` | Fast, crisp text | $0.006/MP |
 | `fal-ai/flux-2-pro` | ~6s | Studio photorealism | $0.03/MP |
 | `fal-ai/z-image/turbo` | ~2s | Bilingual EN/CN, 6B params | $0.005/MP |
-| `fal-ai/nano-banana` | ~6s | Gemini 2.5, character consistency | $0.08/image |
+| `fal-ai/nano-banana-pro` | ~8s | Gemini 3 Pro, reasoning depth, text rendering | $0.15/image (1K) |
 | `fal-ai/gpt-image-1.5` | ~15s | Prompt adherence | $0.034/image |
 | `fal-ai/ideogram/v3` | ~5s | Best typography | $0.03–0.09/image |
-| `fal-ai/recraft-v3` | ~8s | Vector art, brand styles | $0.04/image |
+| `fal-ai/recraft/v4/pro/text-to-image` | ~8s | Design, brand systems, production-ready | $0.25/image |
 | `fal-ai/qwen-image` | ~12s | LLM-based, complex text | $0.02/MP |
 
 Prices are FAL's pricing at time of writing; check [fal.ai](https://fal.ai/) for current numbers.
@@ -87,7 +87,7 @@ Make me a futuristic cityscape, landscape orientation
 
 Every model accepts the same three aspect ratios from the agent's perspective. Internally, each model's native size spec is filled in automatically:
 
-| Agent input | image_size (flux/z-image/qwen/recraft/ideogram) | aspect_ratio (nano-banana) | image_size (gpt-image) |
+| Agent input | image_size (flux/z-image/qwen/recraft/ideogram) | aspect_ratio (nano-banana-pro) | image_size (gpt-image) |
 |---|---|---|---|
 | `landscape` | `landscape_16_9` | `16:9` | `1536x1024` |
 | `square` | `square_hd` | `1:1` | `1024x1024` |

website/docs/user-guide/features/overview.md

@@ -30,7 +30,7 @@ Hermes Agent includes a rich set of capabilities that extend far beyond basic ch
 - **[Voice Mode](voice-mode.md)** — Full voice interaction across CLI and messaging platforms. Talk to the agent using your microphone, hear spoken replies, and have live voice conversations in Discord voice channels.
 - **[Browser Automation](browser.md)** — Full browser automation with multiple backends: Browserbase cloud, Browser Use cloud, local Chrome via CDP, or local Chromium. Navigate websites, fill forms, and extract information.
 - **[Vision & Image Paste](vision.md)** — Multimodal vision support. Paste images from your clipboard into the CLI and ask the agent to analyze, describe, or work with them using any vision-capable model.
-- **[Image Generation](image-generation.md)** — Generate images from text prompts using FAL.ai. Eight models supported (FLUX 2 Klein/Pro, GPT-Image 1.5, Nano Banana, Ideogram V3, Recraft V3, Qwen, Z-Image Turbo); pick one via `hermes tools`.
+- **[Image Generation](image-generation.md)** — Generate images from text prompts using FAL.ai. Eight models supported (FLUX 2 Klein/Pro, GPT-Image 1.5, Nano Banana Pro, Ideogram V3, Recraft V4 Pro, Qwen, Z-Image Turbo); pick one via `hermes tools`.
 - **[Voice & TTS](tts.md)** — Text-to-speech output and voice message transcription across all messaging platforms, with five provider options: Edge TTS (free), ElevenLabs, OpenAI TTS, MiniMax, and NeuTTS.
 
 ## Integrations

website/docs/user-guide/features/tool-gateway.md

@@ -18,7 +18,7 @@ The **Tool Gateway** lets paid [Nous Portal](https://portal.nousresearch.com) su
 | Tool | What It Does | Direct Alternative |
 |------|--------------|--------------------|
 | **Web search & extract** | Search the web and extract page content via Firecrawl | `FIRECRAWL_API_KEY`, `EXA_API_KEY`, `PARALLEL_API_KEY`, `TAVILY_API_KEY` |
-| **Image generation** | Generate images via FAL (8 models: FLUX 2 Klein/Pro, GPT-Image, Nano Banana, Ideogram, Recraft, Qwen, Z-Image) | `FAL_KEY` |
+| **Image generation** | Generate images via FAL (8 models: FLUX 2 Klein/Pro, GPT-Image, Nano Banana Pro, Ideogram, Recraft V4 Pro, Qwen, Z-Image) | `FAL_KEY` |
 | **Text-to-speech** | Convert text to speech via OpenAI TTS | `VOICE_TOOLS_OPENAI_KEY`, `ELEVENLABS_API_KEY` |
 | **Browser automation** | Control cloud browsers via Browser Use | `BROWSER_USE_API_KEY`, `BROWSERBASE_API_KEY` |