sscoble/pi-mono
1
0
Fork 0
mirror of https://github.com/badlogic/pi-mono.git synced 2026-11-05 23:37:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

feat(ai,coding-agent): add image input limits (closes #9631)

Browse source
This commit is contained in:
Armin Ronacher 2026-09-20 22:59:16 +02:00
parent 3390bd9363
commit f5c946480c
20 changed files with 415 additions and 40 deletions
Download patch file Download diff file Expand all files Collapse all files

39
packages/ai/scripts/generate-models.ts
View file

@ -400,6 +400,16 @@ const OPENAI_LONG_CONTEXT_PRICING_MODEL_IDS = new Set([
"gpt-6-astra",
]);
// Keep the generated default no less restrictive than coding-agent's historical
// image preprocessing. Provider limits can narrow this profile, but unknown
// providers retain the cache-safe 2000px / 4.5 MiB behavior.
const DEFAULT_IMAGE_RESIZE = {
maxWidth: 2000,
maxHeight: 2000,
maxBytes: 4.5 * 1024 * 1024,
jpegQuality: 80,
} as const;
function withOpenAiLongContextPricing(cost: Model<Api>["cost"]): Model<Api>["cost"] {
return {
...cost,
@ -947,6 +957,34 @@ function applyPromptCacheMetadata(model: Model<Api>): void {
// behavior; a documented TTL alone does not establish full cache loss.
}
function applyImageInputMetadata(model: Model<Api>): void {
if (!model.input.includes("image")) return;
const providerLimits: Model<Api>["inputLimits"] =
model.provider === "anthropic"
? {
maxRequestBytes: 32 * 1024 * 1024,
images: { maxPerRequest: model.contextWindow === 200000 ? 100 : 600 },
}
: model.provider === "amazon-bedrock"
? { images: { maxPerMessage: 20 } }
: model.provider === "openai"
? { maxRequestBytes: 512 * 1024 * 1024, images: { maxPerRequest: 1500 } }
: model.provider === "google"
? { maxRequestBytes: 20 * 1024 * 1024, images: { maxPerRequest: 3600 } }
: undefined;
const configuredImages = model.inputLimits?.images;
model.inputLimits = {
...providerLimits,
...model.inputLimits,
images: {
...providerLimits?.images,
...configuredImages,
resize: { ...DEFAULT_IMAGE_RESIZE, ...configuredImages?.resize },
},
};
}
function isGemma4Model(modelId: string): boolean {
return /gemma-?4/.test(modelId.toLowerCase());
}
@ -3099,6 +3137,7 @@ async function generateModels() {
applyOpenAIResponsesTranscriptMetadata(model);
applyOpenAIExplicitPromptCacheMetadata(model);
applyPromptCacheMetadata(model);
applyImageInputMetadata(model);
}
applyAnthropicAllowedFallbackModelMetadata(allModels.filter(isAnthropicFallbackMetadataModel));