feat(combos): default-enable vision/audio adapter with mimo fallback

- Enable vision + audioInput capacity-adapter pools by default for new
  and existing users (mergeWithDefaults backward-compat)
- Fall back to oc/mimo-v2.5-free when an enabled pool has no models
  configured, both in the backend resolver and the combos UI (auto
  refill on removing the last model from a pool)
- Hide PDF/Video from the Vision Adapter UI (PDF never implemented,
  Video lacks translator support) while keeping the settings shape
- Exclude combos from the model picker when opened from the Vision
  Adapter section
- mimo-v2.5 registry entry now declares audioInput/videoInput
- Simplify combo strategy and Vision Adapter descriptions
This commit is contained in:
decolua
2026-08-05 16:09:42 +07:00
parent cd13d904d7
commit 8e59093db7
5 changed files with 391 additions and 4 deletions

View File

@@ -279,7 +279,7 @@ export const PATTERN_CAPABILITIES = [
{ pattern: "*minimax*", caps: { reasoning: true, thinkingFormat: "minimax", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 131072 } },
// ── Xiaomi MiMo (vision, 1M / 262K ctx) ──────────────────────────
{ pattern: "*mimo*v2.5*", caps: { vision: true, contextWindow: 1048576, maxOutput: 131072 } },
{ pattern: "*mimo*v2.5*", caps: { vision: true, audioInput: true, videoInput: true, contextWindow: 1048576, maxOutput: 131072 } },
{ pattern: "*mimo*omni*", caps: { vision: true, audioInput: true, contextWindow: 262144, maxOutput: 131072 } },
{ pattern: "*mimo*", caps: { vision: true, contextWindow: 262144, maxOutput: 131072 } },

View File

@@ -0,0 +1,173 @@
/**
* Capacity Adapter — global fallback pools of models per input-modality capability
* (vision / pdf / audioInput / videoInput).
*
* The pool models are appended as extra fallback candidates behind whatever models
* were already going to be tried (a combo's members, or a single target model).
* combo.js's existing reorderByCapabilities then floats a capable pool model to the
* front only when none of the original models can handle the request — so this
* never overrides a combo that already has a member covering the capability.
*/
import { getCapabilitiesForModel } from "../providers/capabilities.js";
const CAPABILITY_KEYS = ["vision", "pdf", "audioInput", "videoInput"];
const HARD_CAPS = new Set(CAPABILITY_KEYS);
const DEFAULT_FALLBACK_MODEL = "oc/mimo-v2.5-free";
// Normalize a capability entry to { enabled, roundRobin, models }. Backward-compat:
// accept the legacy array form [{model, enabled}] (treated as enabled, fallback).
function normalizeCapEntry(entry) {
if (Array.isArray(entry)) {
return { enabled: true, roundRobin: false, models: entry.map((e) => e?.model || e).filter(Boolean) };
}
if (entry && typeof entry === "object") {
return {
enabled: entry.enabled !== false,
roundRobin: !!entry.roundRobin,
models: Array.isArray(entry.models) ? entry.models.filter(Boolean) : [],
};
}
return { enabled: false, roundRobin: false, models: [] };
}
// Resolve one capability's full config. Enabled pools with no models fall back
// to DEFAULT_FALLBACK_MODEL so the toggle is never a no-op.
export function getCapacityAdapterConfig(cap, settings) {
const entry = normalizeCapEntry(settings?.capacityAdapter?.[cap]);
if (entry.enabled && entry.models.length === 0) {
return { ...entry, models: [DEFAULT_FALLBACK_MODEL] };
}
return entry;
}
// Flatten enabled models across all capability pools, in priority order, deduped.
export function getCapacityAdapterModels(settings) {
const seen = new Set();
const models = [];
for (const cap of CAPABILITY_KEYS) {
const { enabled, models: pool } = getCapacityAdapterConfig(cap, settings);
if (!enabled) continue;
for (const m of pool) {
if (!seen.has(m)) {
seen.add(m);
models.push(m);
}
}
}
return models;
}
// Strategy for a capability: "round-robin" when enabled+roundRobin, else "fallback".
export function getCapacityAdapterStrategy(cap, settings) {
const { enabled, roundRobin } = getCapacityAdapterConfig(cap, settings);
return enabled && roundRobin ? "round-robin" : "fallback";
}
// Strategy from the request's required capabilities: picks the first capability
// whose adapter pool is enabled and can satisfy a hard requirement.
export function getActiveAdapterStrategy(requiredCapabilities, settings) {
const hard = [...(requiredCapabilities || [])].filter((c) => HARD_CAPS.has(c));
for (const cap of hard) {
const { enabled, models } = getCapacityAdapterConfig(cap, settings);
if (!enabled || models.length === 0) continue;
return getCapacityAdapterStrategy(cap, settings);
}
return "fallback";
}
function modelSatisfies(modelStr, requiredHard) {
const slash = modelStr.indexOf("/");
const provider = slash > 0 ? modelStr.slice(0, slash) : "";
const model = slash > 0 ? modelStr.slice(slash + 1) : modelStr;
const caps = getCapabilitiesForModel(provider, model);
return requiredHard.every((c) => caps[c] === true);
}
// Prepend capacity-adapter models as priority candidates when NONE of the
// original models (combo members, or the single target model) can satisfy the
// request's required capabilities. Adapter models go FIRST (priority); the
// original models follow as fallback. Leaves `models` untouched when the
// original list already covers it (combo.js's reorderByCapabilities handles
// that case via autoSwitch).
export function augmentModelsWithCapacityAdapter(models, requiredCapabilities, settings) {
const hard = [...(requiredCapabilities || [])].filter((c) => HARD_CAPS.has(c));
if (hard.length === 0 || !Array.isArray(models) || models.length === 0) return models;
if (models.some((m) => modelSatisfies(m, hard))) return models;
const pool = getCapacityAdapterModels(settings).filter((m) => !models.includes(m) && modelSatisfies(m, hard));
if (pool.length === 0) return models;
return [...pool, ...models];
}
const CHARS_PER_TOKEN = 4; // rough estimate; avoids pulling in a tokenizer dependency
const HEAD_KEEP = 6; // messages after system kept verbatim before dropping the middle
function blockLength(content) {
if (typeof content === "string") return content.length;
if (Array.isArray(content)) {
return content.reduce((sum, b) => sum + (typeof b?.text === "string" ? b.text.length : 50), 0);
}
return 0;
}
// Trim history to fit a (possibly smaller) context window by dropping the MIDDLE.
// Preserves: all system/instruction messages (head), and the trailing user run
// carrying the media the switch happened for (tail). Older middle turns between
// the head instructions and the current turn are dropped first.
export function stripHistoryForContext(body, contextWindow) {
const key = Array.isArray(body.messages) ? "messages"
: Array.isArray(body.input) ? "input"
: Array.isArray(body.contents) ? "contents"
: null;
if (!key) return body;
const arr = body[key];
if (!arr || arr.length === 0) return body;
const isSystem = (r) => r === "system" || r === "developer";
const systemMsgs = arr.filter((m) => isSystem(m?.role));
const rest = arr.filter((m) => !isSystem(m?.role));
if (rest.length === 0) return body;
const isAssistant = (r) => r === "assistant" || r === "model";
let i = rest.length - 1;
while (i >= 0 && !isAssistant(rest[i]?.role)) i--;
const tail = rest.slice(i + 1); // current user turn (has media) — always kept
const older = rest.slice(0, i + 1); // everything before it
if (older.length === 0) return body;
const contentOf = (m) => m.content ?? m.parts;
// Cap at 80% of the adapter model's context window — leaves room for the response.
const budgetChars = (contextWindow || 200000) * 0.8 * CHARS_PER_TOKEN;
// Prefer keeping the first HEAD_KEEP messages (initial instructions/context) verbatim;
// only trim further if even that exceeds the adapter model's context window.
const headKept = older.slice(0, HEAD_KEEP);
let total = systemMsgs.concat(headKept, tail).reduce((s, m) => s + blockLength(contentOf(m)), 0);
// If head + tail overflow, drop head turns from the end (closest to middle) first.
let head = headKept;
while (total > budgetChars && head.length > 0) {
const dropped = head.pop();
total -= blockLength(contentOf(dropped));
}
if (head.length === older.length) return body;
return { ...body, [key]: [...systemMsgs, ...head, ...tail] };
}
// Wrap a handleSingleModel callback so calls to a capacity-adapter model strip
// history to fit its context window first. No-op passthrough when the pool is empty.
export function withCapacityAdapterStripping(handleSingleModel, adapterModels) {
const adapterSet = new Set(adapterModels);
if (adapterSet.size === 0) return handleSingleModel;
return (body, modelStr, ...rest) => {
if (adapterSet.has(modelStr)) {
const slash = modelStr.indexOf("/");
const provider = slash > 0 ? modelStr.slice(0, slash) : "";
const model = slash > 0 ? modelStr.slice(slash + 1) : modelStr;
const { contextWindow } = getCapabilitiesForModel(provider, model);
body = stripHistoryForContext(body, contextWindow);
}
return handleSingleModel(body, modelStr, ...rest);
};
}

View File

@@ -5,7 +5,7 @@ import { DndContext, closestCenter, KeyboardSensor, PointerSensor, useSensor, us
import { arrayMove, SortableContext, sortableKeyboardCoordinates, useSortable, verticalListSortingStrategy } from "@dnd-kit/sortable";
import { CSS } from "@dnd-kit/utilities";
import { restrictToVerticalAxis, restrictToParentElement } from "@dnd-kit/modifiers";
import { Card, Button, Modal, Input, CardSkeleton, ModelSelectModal, ConfirmModal, CapacityBadges, Select } from "@/shared/components";
import { Card, Button, Modal, Input, CardSkeleton, ModelSelectModal, ConfirmModal, CapacityBadges, Select, Toggle } from "@/shared/components";
import { useCopyToClipboard } from "@/shared/hooks/useCopyToClipboard";
import { useModelCaps } from "@/shared/hooks/useModelCaps";
import { isOpenAICompatibleProvider, isAnthropicCompatibleProvider } from "@/shared/constants/providers";
@@ -13,6 +13,37 @@ import { isOpenAICompatibleProvider, isAnthropicCompatibleProvider } from "@/sha
// Validate combo name: only a-z, A-Z, 0-9, -, _
const VALID_NAME_REGEX = /^[a-zA-Z0-9_.\-]+$/;
// Capacity adapter: global fallback pools of models per input-modality capability.
// A request needing a capability the target model/combo lacks switches straight
// to the first enabled model here instead of erroring or dropping the data.
const CAPACITY_ADAPTER_CAPS = [
{ key: "vision", label: "Vision", icon: "visibility", desc: "Images" },
// pdf, videoInput temporarily hidden — no translator support yet for those blocks.
{ key: "audioInput", label: "Audio", icon: "graphic_eq", desc: "Audio input" },
];
const DEFAULT_FALLBACK_MODEL = "oc/mimo-v2.5-free";
const EMPTY_CAP_ENTRY = { enabled: true, roundRobin: false, models: [] };
const EMPTY_CAPACITY_ADAPTER = {
vision: { ...EMPTY_CAP_ENTRY },
pdf: { ...EMPTY_CAP_ENTRY },
audioInput: { ...EMPTY_CAP_ENTRY },
videoInput: { ...EMPTY_CAP_ENTRY },
};
// Backward-compat: legacy stored form was an array of {model, enabled}.
function normalizeCapEntry(entry) {
if (Array.isArray(entry)) {
return { enabled: true, roundRobin: false, models: entry.map((e) => e?.model || e).filter(Boolean) };
}
if (entry && typeof entry === "object") {
return {
enabled: entry.enabled !== false,
roundRobin: !!entry.roundRobin,
models: Array.isArray(entry.models) ? entry.models.filter(Boolean) : [],
};
}
return { ...EMPTY_CAP_ENTRY };
}
export default function CombosPage() {
const [combos, setCombos] = useState([]);
const [loading, setLoading] = useState(true);
@@ -20,6 +51,7 @@ export default function CombosPage() {
const [editingCombo, setEditingCombo] = useState(null);
const [activeProviders, setActiveProviders] = useState([]);
const [comboStrategies, setComboStrategies] = useState({});
const [capacityAdapter, setCapacityAdapter] = useState(EMPTY_CAPACITY_ADAPTER);
const { getCaps } = useModelCaps();
const [confirmState, setConfirmState] = useState(null);
const { copied, copy } = useCopyToClipboard();
@@ -45,6 +77,12 @@ export default function CombosPage() {
setActiveProviders(providersData.connections || []);
}
setComboStrategies(settingsData.comboStrategies || {});
const rawAdapter = settingsData.capacityAdapter || {};
const normalized = {};
for (const cap of CAPACITY_ADAPTER_CAPS) {
normalized[cap.key] = normalizeCapEntry(rawAdapter[cap.key]);
}
setCapacityAdapter(normalized);
} catch (error) {
console.log("Error fetching data:", error);
} finally {
@@ -52,6 +90,19 @@ export default function CombosPage() {
}
};
const handleSetCapacityAdapter = async (next) => {
setCapacityAdapter(next);
try {
await fetch("/api/settings", {
method: "PATCH",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({ capacityAdapter: next }),
});
} catch (error) {
console.log("Error updating capacity adapter:", error);
}
};
const handleCreate = async (data) => {
try {
const res = await fetch("/api/combos", {
@@ -154,7 +205,6 @@ export default function CombosPage() {
<li><span className="font-medium text-text-main">Fallback</span> tries models in order (next on failure)</li>
<li><span className="font-medium text-text-main">Round Robin</span> rotates models across requests to spread load</li>
<li><span className="font-medium text-text-main">Fusion</span> queries all models in parallel, then a judge synthesizes one answer. Best quality, but costs the most: every request bills all panel models + the judge (N+1 calls)</li>
<li><span className="font-medium text-text-main">Capacity auto-switch</span> sends image/PDF/audio requests to a model that supports them first</li>
</ul>
</div>
<Button icon="add" onClick={() => setShowCreateModal(true)} className="w-full sm:w-auto whitespace-nowrap">
@@ -195,6 +245,14 @@ export default function CombosPage() {
</div>
)}
{/* Capacity Adapter */}
<CapacityAdapterSection
capacityAdapter={capacityAdapter}
onChange={handleSetCapacityAdapter}
activeProviders={activeProviders}
getCaps={getCaps}
/>
{/* Create Modal - Use key to force remount and reset state */}
{showCreateModal && (
<ComboFormModal
@@ -351,6 +409,149 @@ function ComboCard({ combo, getCaps, activeProviders = [], copied, onCopy, onEdi
);
}
function CapacityAdapterSection({ capacityAdapter, onChange, activeProviders, getCaps }) {
return (
<div className="flex flex-col gap-3">
<div className="flex flex-col gap-3 sm:flex-row sm:items-center sm:justify-between">
<div className="min-w-0">
<p className="text-sm font-medium">Vision Adapter</p>
<p className="text-xs text-text-muted mt-0.5">
Your model can&apos;t read image/audio? Auto-switches to a model in the pool below.
</p>
<ul className="mt-1.5 text-[11px] text-text-muted flex flex-col gap-0.5">
<li><span className="font-medium text-text-main">Vision</span> images (png, jpg, webp, )</li>
<li><span className="font-medium text-text-main">Audio</span> audio input</li>
</ul>
</div>
</div>
<div className="flex flex-col gap-4">
{CAPACITY_ADAPTER_CAPS.map((cap) => (
<CapacityAdapterCap
key={cap.key}
cap={cap}
entry={capacityAdapter[cap.key] || EMPTY_CAP_ENTRY}
onChange={(entry) => onChange({ ...capacityAdapter, [cap.key]: entry })}
activeProviders={activeProviders}
getCaps={getCaps}
/>
))}
</div>
</div>
);
}
function CapacityAdapterCap({ cap, entry, onChange, activeProviders, getCaps }) {
const [showModelSelect, setShowModelSelect] = useState(false);
const { enabled, roundRobin, models } = entry;
const patch = (p) => onChange({ ...entry, ...p });
const handleAdd = (model) => {
if (models.includes(model.value)) return;
patch({ models: [...models, model.value] });
};
const handleRemove = (index) => {
const next = models.filter((_, i) => i !== index);
patch({ models: next.length === 0 ? [DEFAULT_FALLBACK_MODEL] : next });
};
const handleMove = (index, delta) => {
const target = index + delta;
if (target < 0 || target >= models.length) return;
const next = [...models];
[next[index], next[target]] = [next[target], next[index]];
patch({ models: next });
};
return (
<Card padding="sm" className={`group ${!enabled ? "opacity-50" : ""}`}>
<div className="flex min-w-0 flex-col gap-3 sm:flex-row sm:items-center sm:justify-between">
{/* Master toggle + icon + label + chips */}
<div className="flex min-w-0 flex-1 items-start gap-2.5 sm:items-center">
<Toggle
checked={enabled}
onChange={(v) => patch({ enabled: v })}
aria-label={`Enable ${cap.label} adapter`}
/>
<div className="size-8 rounded-lg bg-primary/10 flex items-center justify-center shrink-0">
<span className="material-symbols-outlined text-primary text-[18px]">{cap.icon}</span>
</div>
<div className="min-w-0 flex-1">
<div className="flex items-center gap-1.5">
<code className="font-mono text-sm font-medium">{cap.label}</code>
<span className="text-[10px] text-text-muted"> {cap.desc}</span>
</div>
<div className="mt-1 flex min-w-0 flex-wrap items-center gap-1">
{models.length === 0 ? (
<span className="text-xs text-text-muted italic">No models</span>
) : (
models.slice(0, 3).map((model, index) => (
<code
key={`${model}-${index}`}
className="group/chip inline-flex items-center gap-1 rounded bg-black/5 px-1.5 py-0.5 font-mono text-xs text-text-muted dark:bg-white/5"
>
<span>{model}</span>
<CapacityBadges caps={getCaps?.(model)} />
<button onClick={() => handleMove(index, -1)} disabled={index === 0} className={`leading-none opacity-0 group-hover/chip:opacity-100 ${index === 0 ? "text-text-muted/20" : "text-text-muted hover:text-primary"}`}>
<span className="material-symbols-outlined text-[12px]">arrow_upward</span>
</button>
<button onClick={() => handleMove(index, 1)} disabled={index === models.length - 1} className={`leading-none opacity-0 group-hover/chip:opacity-100 ${index === models.length - 1 ? "text-text-muted/20" : "text-text-muted hover:text-primary"}`}>
<span className="material-symbols-outlined text-[12px]">arrow_downward</span>
</button>
<button onClick={() => handleRemove(index)} className="leading-none opacity-0 group-hover/chip:opacity-100 text-text-muted hover:text-red-500">
<span className="material-symbols-outlined text-[12px]">close</span>
</button>
</code>
))
)}
{models.length > 3 && (
<span className="text-[10px] text-text-muted">+{models.length - 3} more</span>
)}
</div>
</div>
</div>
{/* Actions: Round-robin toggle + Add Model */}
<div className="flex w-full flex-col gap-2 sm:w-auto sm:flex-row sm:items-center sm:gap-3 sm:shrink-0">
<label className="flex items-center gap-1.5 text-xs text-text-muted cursor-pointer select-none">
<Toggle
checked={roundRobin}
onChange={(v) => patch({ roundRobin: v })}
disabled={!enabled}
aria-label={`Round-robin ${cap.label} adapter`}
/>
<span>Round</span>
</label>
<Button
icon="add"
variant="ghost"
size="sm"
onClick={() => setShowModelSelect(true)}
disabled={!enabled}
title={`Add ${cap.label} model`}
>
Add Model
</Button>
</div>
</div>
{showModelSelect && (
<ModelSelectModal
isOpen={showModelSelect}
onClose={() => setShowModelSelect(false)}
onSelect={handleAdd}
activeProviders={activeProviders}
title={`Add ${cap.label} Model`}
addedModelValues={models}
capFilter={cap.key}
closeOnSelect={false}
/>
)}
</Card>
);
}
function ModelItem({ id, index, model, isFirst, isLast, onEdit, onMoveUp, onMoveDown, onRemove }) {
const { attributes, listeners, setNodeRef, transform, isDragging } = useSortable({ id });
const style = {

View File

@@ -17,7 +17,14 @@ const DEFAULT_SETTINGS = {
comboStrategy: "fallback",
comboStickyRoundRobinLimit: 1,
comboStrategies: {},
capacityAdapter: {
vision: { enabled: true, roundRobin: false, models: [] },
pdf: { enabled: false, roundRobin: false, models: [] },
audioInput: { enabled: true, roundRobin: false, models: [] },
videoInput: { enabled: false, roundRobin: false, models: [] },
},
requireLogin: true,
requireApiKey: true,
tunnelDashboardAccess: true,
authMode: "password",
oidcIssuerUrl: "",

View File

@@ -30,6 +30,7 @@ export default function ModelSelectModal({
title = "Select Model",
modelAliases = {},
kindFilter = null,
capFilter = null,
addedModelValues = [],
closeOnSelect = true,
}) {
@@ -397,7 +398,7 @@ export default function ModelSelectModal({
// Filter combos by search query (and hide combos when kindFilter is set — combos are LLM-only by design)
const filteredCombos = useMemo(() => {
if (kindFilter) return [];
if (kindFilter || capFilter) return [];
if (!searchQuery.trim()) return combos;
const query = searchQuery.toLowerCase();
return combos.filter(c => c.name.toLowerCase().includes(query));
@@ -417,6 +418,11 @@ export default function ModelSelectModal({
const filtered = {};
Object.entries(groupedModels).forEach(([providerId, group]) => {
let models = group.models;
// Filter by input-modality capability (vision/pdf/audioInput/videoInput).
if (capFilter) {
models = models.filter((m) => getCaps(m.value)?.[capFilter] === true);
if (models.length === 0) return;
}
if (query) {
const providerNameMatches = group.name.toLowerCase().includes(query);
models = models.filter(