Files
openclaw/src/image-generation/types.ts
Dave Nicoll 6e79ca3cbc fix(fal): route grok-imagine and nano-banana-2-lite edits to correct endpoints (#98688)
* fix(fal): route grok-imagine and nano-banana-2-lite edits to correct endpoints

The fal image-generation provider appends '/image-to-image' to any model
that isn't 'openai/gpt-image-*' or 'fal-ai/nano-banana-*' when reference
images are supplied. That's wrong for two models fal serves:

- `xai/grok-imagine-image`: fal 404s on '/image-to-image'. The real edit
  endpoint is '/quality/edit'. The endpoint also expects lowercase
  resolution values ('1k'/'2k' only) and a distinct aspect_ratio enum.

- `google/nano-banana-2-lite`: fal 404s on '/image-to-image'. The real
  edit endpoint is '/edit'. The endpoint does not accept a 'resolution'
  parameter.

Add schema entries for both models so ensureFalModelPath and
applyFalImageGeometry pick the right suffix and body shape. Introduce
resolution allowlist support ('resolutions: readonly string[]') and
lowercase transform ('resolutionCase: "lower"') on the schema; existing
schemas keep their behaviour (nb2 still forwards uppercase resolution
unchanged; flux/gpt-image/nb2/krea untouched). Refactor
ensureFalModelPath to consult schema.appendEditPath instead of hardcoded
prefix checks so future models only need a schema entry.

Tested:
- Existing 49 fal unit tests still pass; added 9 new tests covering the
  two new endpoints and their guard conditions (32 -> 34 tests in the
  image-generation-provider suite).
- Live fal.ai calls confirm both endpoints return 200 with real
  reference images; the buggy old URLs still return 404.

* fix(fal): preserve standard edit routing

* fix(image): apply inferred resolution per model

* fix(image): preserve provider reference limits

* fix(image): resolve reference limits per model

* fix(fal): preserve nano banana family limits

* test(ios): stub generated file list helper

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-07-01 20:42:25 -07:00

145 lines
4.3 KiB
TypeScript

/** Shared image-generation request, provider, capability, and result contracts. */
import type { MediaNormalizationEntry } from "../../packages/media-generation-core/src/normalization.js";
import type { AuthProfileStore } from "../agents/auth-profiles/types.js";
import type { OpenClawConfig } from "../config/types.openclaw.js";
import type { SsrFPolicy } from "../infra/net/ssrf.js";
/** Binary image asset returned by an image-generation provider. */
export type GeneratedImageAsset = {
buffer: Buffer;
mimeType: string;
fileName?: string;
revisedPrompt?: string;
metadata?: Record<string, unknown>;
};
export type ImageGenerationResolution = "1K" | "2K" | "4K";
export type ImageGenerationQuality = "low" | "medium" | "high" | "auto";
export type ImageGenerationOutputFormat = "png" | "jpeg" | "webp";
export type ImageGenerationBackground = "transparent" | "opaque" | "auto";
export type ImageGenerationOpenAIBackground = ImageGenerationBackground;
export type ImageGenerationOpenAIModeration = "low" | "auto";
export type ImageGenerationOpenAIOptions = {
background?: ImageGenerationOpenAIBackground;
moderation?: ImageGenerationOpenAIModeration;
outputCompression?: number;
user?: string;
};
export type ImageGenerationProviderOptions = Record<string, unknown> & {
openai?: ImageGenerationOpenAIOptions;
};
type ImageGenerationIgnoredOverrideKey =
| "size"
| "aspectRatio"
| "resolution"
| "quality"
| "outputFormat"
| "background";
export type ImageGenerationIgnoredOverride = {
key: ImageGenerationIgnoredOverrideKey;
value: string;
};
export type ImageGenerationSourceImage = {
buffer: Buffer;
mimeType: string;
fileName?: string;
metadata?: Record<string, unknown>;
};
export type ImageGenerationProviderConfiguredContext = {
cfg?: OpenClawConfig;
agentDir?: string;
};
/** Runtime request passed to an image-generation provider implementation. */
export type ImageGenerationRequest = {
provider: string;
model: string;
prompt: string;
cfg: OpenClawConfig;
agentDir?: string;
authStore?: AuthProfileStore;
timeoutMs?: number;
count?: number;
size?: string;
aspectRatio?: string;
resolution?: ImageGenerationResolution;
quality?: ImageGenerationQuality;
outputFormat?: ImageGenerationOutputFormat;
background?: ImageGenerationBackground;
inputImages?: ImageGenerationSourceImage[];
providerOptions?: ImageGenerationProviderOptions;
ssrfPolicy?: SsrFPolicy;
};
export type ImageGenerationResult = {
images: GeneratedImageAsset[];
model?: string;
metadata?: Record<string, unknown>;
};
type ImageGenerationModeCapabilities = {
maxCount?: number;
supportsSize?: boolean;
supportsAspectRatio?: boolean;
supportsResolution?: boolean;
};
type ImageGenerationEditCapabilities = ImageGenerationModeCapabilities & {
enabled: boolean;
maxInputImages?: number;
maxInputImagesByModel?: Readonly<Record<string, number>>;
maxInputImagesByModelPrefix?: Readonly<Record<string, number>>;
};
type ImageGenerationGeometryCapabilities = {
sizes?: string[];
sizesByModel?: Record<string, string[]>;
aspectRatios?: string[];
aspectRatiosByModel?: Record<string, string[]>;
resolutions?: ImageGenerationResolution[];
resolutionsByModel?: Record<string, ImageGenerationResolution[]>;
};
type ImageGenerationOutputCapabilities = {
qualities?: ImageGenerationQuality[];
formats?: ImageGenerationOutputFormat[];
backgrounds?: ImageGenerationBackground[];
};
export type ImageGenerationNormalization = {
size?: MediaNormalizationEntry<string>;
aspectRatio?: MediaNormalizationEntry<string>;
resolution?: MediaNormalizationEntry<ImageGenerationResolution>;
};
export type ImageGenerationProviderCapabilities = {
generate: ImageGenerationModeCapabilities;
edit: ImageGenerationEditCapabilities;
geometry?: ImageGenerationGeometryCapabilities;
output?: ImageGenerationOutputCapabilities;
};
export type ImageGenerationProvider = {
id: string;
aliases?: string[];
label?: string;
defaultModel?: string;
/** Default provider operation timeout in milliseconds when caller/config omit timeoutMs. */
defaultTimeoutMs?: number;
models?: string[];
capabilities: ImageGenerationProviderCapabilities;
isConfigured?: (ctx: ImageGenerationProviderConfiguredContext) => boolean;
generateImage: (req: ImageGenerationRequest) => Promise<ImageGenerationResult>;
};