0532f00d84
Capability tables are hand-maintained, so a model gains vision or a wider context only when someone notices and edits the file. This adds a daily sync that fills the gap for models already in the registry. How it decides: - Modalities (vision/pdf/audio/video) belong to the MODEL — every gateway serving glm-5.3-flash serves the same weights — so they are keyed by model id and shared. A majority of sources must declare one, which keeps out lone mis-declarations: minimax-m2.5 (1 of 45), glm-4.7 (1 of 44) and gpt-oss-120b (2 of 76) are text-only despite a reseller claiming vision. - Context/output limits belong to the GATEWAY — each truncates differently (glm-5 ships as 202752/16384 on one host and 204800/131072 on another) — so they are keyed by provider + model and only the matching provider's own numbers are trusted. Both layers are strictly additive and sit BELOW the hand-written tables, which short-circuit first. A capability already true stays true. Mechanics: worker thread (the 4MB parse would block the loop ~20ms), ETag so an unchanged catalog costs one empty request, 60s startup delay, 30min backoff on failure, MODEL_CATALOG_SYNC=off to disable. Only the ~57KB delta is kept; lookups cost ~0.1us via an mtime-guarded cache. capabilities.js is bundled into the browser through useModelCaps, so it cannot import node:fs — the server injects the reader via setCatalogSource() from instrumentation. visionPatterns.js is the last resort: a model nobody has catalogued yet still accepts images when its id says so (qwen3-vl-plus, glm-4.6v, llava), with image-generation and embedding ids excluded. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
43 lines
1.6 KiB
JavaScript
43 lines
1.6 KiB
JavaScript
// Name-based vision detection — last resort when neither the catalog file nor
|
|
// the capability tables know a model. Vendors put the modality in the id
|
|
// ("qwen3-vl-plus", "glm-4.6v", "deepseek-v4-flash-vision-exp"), so a custom or
|
|
// freshly released model still gets image input instead of silently dropping it.
|
|
//
|
|
// Only ever turns vision ON. Never used to turn a declared capability off.
|
|
|
|
const SEP = "[-_/:.]";
|
|
|
|
// Image GENERATION, video generation, and non-chat models also carry these
|
|
// words but take no image input — checked first so they can never match.
|
|
const NOT_VISION = new RegExp(
|
|
[
|
|
`(^|${SEP})(image|img)(${SEP}|$)`,
|
|
"stable-image", "gen[0-9]_image", "nanobanana", "imagine",
|
|
"t2v", "i2v", "flux", "dall", "sdxl", "diffusion",
|
|
"embed", "rerank", "guard", "moderation",
|
|
"tts", "stt", "whisper", "voice", "speech", "audio",
|
|
].join("|"),
|
|
"i"
|
|
);
|
|
|
|
// Explicit modality words, plus the "<digit>v" suffix vendors use for vision
|
|
// variants (glm-4.6v, glm-5v-turbo). The digit-v branch requires a dotted
|
|
// version so the never-shipped `gpt-4v` cannot match.
|
|
const VISION_NAME = new RegExp(
|
|
[
|
|
`(^|${SEP})(vision|vl|vlm|multimodal|omni|visual)(${SEP}|$)`,
|
|
`[0-9]\\.[0-9]+v(${SEP}|$)`,
|
|
`(^|${SEP})glm-[0-9]+v(${SEP}|$)`,
|
|
"(^|[-_/:.])(llava|pixtral|internvl|cogvlm|minicpm-v|moondream|idefics|fuyu)",
|
|
].join("|"),
|
|
"i"
|
|
);
|
|
|
|
// Does this model id look like a vision model? Name signal only.
|
|
export function looksLikeVisionModel(modelId) {
|
|
if (!modelId) return false;
|
|
const id = String(modelId).toLowerCase();
|
|
if (NOT_VISION.test(id)) return false;
|
|
return VISION_NAME.test(id);
|
|
}
|