feat(openai): add GPT Image 2 (image-generation modality) (#71)

Introduces image-generation models as a first-class [[models]] entry via
a new `modality` field on the model schema ("text" default, "image",
"audio"). When modality != "text", context_window / max_output_tokens
are optional since no conventional context gate exists — OpenAI's
gpt-image-2 docs omit them.

Adds `image_input_cost_per_m` / `image_output_cost_per_m` alongside
existing text token cost fields to cover the 4-price structure OpenAI
uses for image generation (text $5/$10, image $8/$30 per 1M tokens).

Validator updated to:
- accept any modality in {text, image, audio}
- require context_window/max_output_tokens only for modality=text
- range-check the two new cost fields

gpt-image-2 entry added to providers/openai.toml with pricing sourced
from https://developers.openai.com/api/docs/pricing. Snapshot
gpt-image-2-2026-04-21 listed as alias.

providers/openai.toml

@@ -1,5 +1,5 @@
 # OpenAI — https://openai.com
-# Models: 17 (including 2 Codex variants)
+# Models: 18 (including 2 Codex variants + 1 image-generation model)
 
 [provider]
 id = "openai"
@@ -237,3 +237,21 @@ supports_vision = true
 supports_streaming = true
 supports_thinking = true
 aliases = ["codex-o4"]
+
+# Image generation — priced per token (text + image), no conventional context
+# window. Snapshot gpt-image-2-2026-04-21 released 2026-04-21.
+# Source: https://developers.openai.com/api/docs/models/gpt-image-2
+# Pricing: https://developers.openai.com/api/docs/pricing
+[[models]]
+id = "gpt-image-2"
+display_name = "GPT Image 2"
+tier = "frontier"
+modality = "image"
+input_cost_per_m = 5.00
+output_cost_per_m = 10.00
+image_input_cost_per_m = 8.00
+image_output_cost_per_m = 30.00
+supports_tools = false
+supports_vision = true
+supports_streaming = false
+aliases = ["gpt-image-2-2026-04-21"]

schema.toml

@@ -72,30 +72,50 @@ description = "Capability tier: frontier (cutting-edge, most capable), smart (co
 options = ["frontier", "smart", "balanced", "fast", "local"]
 example = "smart"
 
+[provider.sections.models.fields.modality]
+type = "string"
+required = false
+description = "Model modality. 'text' (default) is a chat/LLM; 'image' is an image-generation model (context_window/max_output_tokens become optional); 'audio' is a speech model."
+options = ["text", "image", "audio"]
+default = "text"
+example = "text"
+
 [provider.sections.models.fields.context_window]
 type = "number"
 required = true
-description = "Maximum input tokens"
+description = "Maximum input tokens. Required for modality='text'; optional for image/audio models where no published context gate exists."
 example = 128000
 
 [provider.sections.models.fields.max_output_tokens]
 type = "number"
 required = true
-description = "Maximum output tokens"
+description = "Maximum output tokens. Required for modality='text'; optional for image/audio models."
 example = 16384
 
 [provider.sections.models.fields.input_cost_per_m]
 type = "number"
 required = true
-description = "USD per million input tokens (0.0 for free/local)"
+description = "USD per million text input tokens (0.0 for free/local)"
 example = 2.5
 
 [provider.sections.models.fields.output_cost_per_m]
 type = "number"
 required = true
-description = "USD per million output tokens (0.0 for free/local)"
+description = "USD per million text output tokens (0.0 for free/local)"
 example = 10.0
 
+[provider.sections.models.fields.image_input_cost_per_m]
+type = "number"
+required = false
+description = "USD per million image input tokens (for image/multimodal models)"
+example = 8.0
+
+[provider.sections.models.fields.image_output_cost_per_m]
+type = "number"
+required = false
+description = "USD per million image output tokens (for image-generation models)"
+example = 30.0
+
 [provider.sections.models.fields.last_verified]
 type = "string"
 required = false

scripts/validate.py

@@ -34,6 +34,7 @@ except ImportError:
         sys.exit(1)
 
 VALID_TIERS = {"frontier", "smart", "balanced", "fast", "local"}
+VALID_MODALITIES = {"text", "image", "audio"}
 VALID_HAND_CATEGORIES = {
     "communication", "content", "data", "development",
     "devops", "finance", "productivity", "research", "social",
@@ -41,11 +42,14 @@ VALID_HAND_CATEGORIES = {
 VALID_SKILL_RUNTIMES = {"promptonly", "python", "node", "shell"}
 
 REQUIRED_PROVIDER_FIELDS = {"id", "display_name", "api_key_env", "base_url", "key_required"}
-REQUIRED_MODEL_FIELDS = {
+
+# Required for all modalities.
+REQUIRED_MODEL_FIELDS_COMMON = {
     "id", "display_name", "tier",
-    "context_window", "max_output_tokens",
     "input_cost_per_m", "output_cost_per_m",
 }
+# Additionally required when modality='text' (the default).
+REQUIRED_MODEL_FIELDS_TEXT_ONLY = {"context_window", "max_output_tokens"}
 
 VALID_CONTENT_TYPES = {"providers", "agents", "hands", "mcp", "skills", "plugins", "aliases"}
 
@@ -79,7 +83,18 @@ def validate_provider_file(filepath: Path) -> list[str]:
 
     for i, model in enumerate(models):
         label = model.get("id", f"models[{i}]")
-        for field in REQUIRED_MODEL_FIELDS:
+
+        modality = model.get("modality", "text")
+        if modality not in VALID_MODALITIES:
+            errors.append(
+                f"{filepath.name}: Model '{label}' invalid modality '{modality}' "
+                f"(valid: {', '.join(sorted(VALID_MODALITIES))})"
+            )
+
+        required_fields = set(REQUIRED_MODEL_FIELDS_COMMON)
+        if modality == "text":
+            required_fields |= REQUIRED_MODEL_FIELDS_TEXT_ONLY
+        for field in required_fields:
             if field not in model:
                 errors.append(f"{filepath.name}: Model '{label}' missing field '{field}'")
 
@@ -87,7 +102,12 @@ def validate_provider_file(filepath: Path) -> list[str]:
         if tier is not None and tier not in VALID_TIERS:
             errors.append(f"{filepath.name}: Model '{label}' invalid tier '{tier}'")
 
-        for cost_field in ("input_cost_per_m", "output_cost_per_m"):
+        for cost_field in (
+            "input_cost_per_m",
+            "output_cost_per_m",
+            "image_input_cost_per_m",
+            "image_output_cost_per_m",
+        ):
             val = model.get(cost_field)
             if val is not None and (not isinstance(val, (int, float)) or val < 0):
                 errors.append(f"{filepath.name}: Model '{label}' invalid {cost_field}: {val}")