@staticeng/opencode-litellm 0.2.2 → 0.2.4

package/README.md

@@ -48,12 +48,15 @@ Shared or synchronized OpenCode configuration should use the published package n
 | `providerOverrides` | `{}` | Provider-level deep-merge overrides. |
 | `includeModes` | `chat`, `responses` | LiteLLM modes to include. |
 | `includeModels` | all included modes | Optional allowlist by model name. |
+| `includeBackends` | unset | Optional exact allowlist by `model_info.backend`, unioned with `includeModels` pins. |
 | `excludeModels` | none | Optional denylist by model name. |
 | `timeoutMs` | `30000` | Per-request discovery timeout. |
 | `strict` | `false` | Throw on fetch/mapping failures instead of warning. |
 
 The LiteLLM key must have permission to call `GET /model/info` and root `GET /model_group/info`.
 
+When `includeBackends` is present, models are candidates when `model_info.backend` exactly and case-sensitively matches an entry or their exact model name is pinned by `includeModels`. Backend values are not trimmed, normalized, or partially matched; missing and non-string values do not match. An empty `includeBackends` matches no backends, so without model pins it includes no models. `excludeModels` always wins over backend matches and pins, and candidates must still pass `includeModes` (or the default `chat` and `responses` modes). When `includeBackends` is omitted, `includeModels` retains its historical behavior: a non-empty array is a model-name allowlist, while an omitted or empty array imposes no model-name allowlist.
+
 ## Overrides
 
 LiteLLM metadata does not expose every OpenCode model field. The plugin includes exact built-in contracts for the currently approved GPT-5.4, GPT-5.5, GPT-5.6, DeepSeek V4 Flash, and Qwen3.8 aliases. Use `overrides` to customize those defaults or to add metadata for unknown models.
@@ -98,9 +101,12 @@ The built-in mode matrix is:
 | GPT-5.5 | `none`, `low`, `medium`, `high`, `xhigh` | `medium` |
 | GPT-5.6 Luna / Sol / Terra | `none`, `low`, `medium`, `high`, `xhigh`, `max` | `medium` |
 | DeepSeek V4 Flash | `off`, `low`, `high`, `max` | `max` |
-| Qwen3.8 | `off`, `low`, `medium`, `xhigh` | `xhigh` |
+| Qwen3.8 27B refusal dial | `off`, `low`, `medium`, `xhigh` | `xhigh` |
+| Qwen3.8 Flash Next | `off`, `low` | `low` |
+
+DeepSeek `off` sends canonical `none`. Qwen `off` sends only `chat_template_kwargs.enable_thinking=false`, with no reasoning effort. `ultra` is not generated by a built-in contract. For requests without an explicit named variant, the plugin supplies the row's contract default through model options; an explicit variant is merged afterward and wins. Qwen's explicit `off` cleanup removes the model's default effort before serialization. The `variantDefault` compatibility marker is UI-only and is stripped before requests for exact built-in aliases.
 
-DeepSeek `off` sends canonical `none`. Qwen `off` sends only `chat_template_kwargs.enable_thinking=false`, with no reasoning effort. `ultra` is not generated by a built-in contract. For requests without an explicit named variant, the plugin supplies the row's contract default through model options; an explicit variant is merged afterward and wins. Qwen's explicit `off` cleanup removes the default `xhigh` effort before serialization. The `variantDefault` compatibility marker is UI-only and is stripped before requests for exact built-in aliases.
+The exact dynamically discovered alias `qwen3.8-flash-next` also receives verified static metadata that overrides incomplete or conflicting LiteLLM group metadata: text and image input, text output, attachment, reasoning, tool calling, and a 262144-token context. Its output limit remains unknown and is represented by the package's `0` sentinel; pricing and other modalities are not supplied. The contract is still discovery-gated and never creates the alias when LiteLLM omits it.
 
 Normal GPT-5.3 Codex and GPT-5.3 Codex Spark aliases are retired and filtered even if stale discovery metadata still reports them. Unlisted aliases such as `defend/gpt-5.5` do not inherit a contract.
 

package/dist/mapping.js

@@ -169,8 +169,16 @@ function allowedByFilters(model, options) {
         return false;
     if (isRetiredModelAlias(name))
         return false;
-    if (options.includeModels?.length && !options.includeModels.includes(name))
+    const pinned = options.includeModels?.includes(name) ?? false;
+    if (options.includeBackends !== undefined) {
+        const backend = model.model_info?.backend;
+        const backendMatched = typeof backend === "string" && options.includeBackends.includes(backend);
+        if (!backendMatched && !pinned)
+            return false;
+    }
+    else if (options.includeModels?.length && !pinned) {
         return false;
+    }
     if (options.excludeModels?.includes(name))
         return false;
     const modelMode = mode(model);
@@ -274,12 +282,23 @@ function contractDefaults(name, tombstones = false) {
         const disabled = entry.family === "DeepSeek V4 Flash"
             ? ["medium", "xhigh"]
             : entry.family === "Qwen3.8"
-                ? ["none", "minimal", "high", "max"]
+                ? ["none", "minimal", "low", "medium", "high", "xhigh", "max", ...(entry.metadata ? ["ultra"] : [])].filter((effort) => !entry.modes.some((mode) => mode.id === effort))
                 : [];
         for (const effort of disabled)
             variants[effort] = { disabled: true };
     }
     return {
+        ...(entry.metadata
+            ? {
+                modalities: {
+                    input: [...entry.metadata.modalities.input],
+                    output: [...entry.metadata.modalities.output],
+                },
+                attachment: entry.metadata.attachment,
+                tool_call: entry.metadata.tool_call,
+                limit: { ...entry.metadata.limit },
+            }
+            : {}),
         reasoning: true,
         options: { ...defaultMode.legacy, variantDefault: entry.variantDefault },
         variants,
@@ -320,7 +339,9 @@ function generatedModel(model, tombstones = false) {
         ...(supportsReasoning(model) && reasoningVariants(model) ? { variants: reasoningVariants(model) } : {}),
         ...(model.model_info?.supports_function_calling || model.model_info?.supports_tool_choice ? { tool_call: true } : {}),
     };
-    return deepMerge(generated, contractDefaults(name, tombstones));
+    const defaults = contractDefaults(name, tombstones);
+    const merged = deepMerge(generated, defaults);
+    return defaults?.limit ? { ...merged, limit: { ...defaults.limit } } : merged;
 }
 function finalizedModel(model, override) {
     const input = supportedModalities(model.modalities?.input ?? [TEXT_MODALITY]);

package/dist/model-contracts.js

@@ -12,7 +12,7 @@ function effortModes(ids) {
         v2Body: freezeJson({ reasoning_effort: id }),
     })));
 }
-function contract(family, aliases, modes, defaultMode) {
+function contract(family, aliases, modes, defaultMode, metadata) {
     if (!modes.some((mode) => mode.id === defaultMode))
         throw new Error(`Model contract ${family} has an invalid default`);
     return Object.freeze({
@@ -22,6 +22,7 @@ function contract(family, aliases, modes, defaultMode) {
         defaultMode,
         reasoning: true,
         variantDefault: false,
+        ...(metadata ? { metadata } : {}),
     });
 }
 const GPT_STANDARD_MODES = effortModes(["none", "low", "medium", "high", "xhigh"]);
@@ -43,6 +44,16 @@ const QWEN_MODES = Object.freeze([
     Object.freeze({ id: "medium", legacy: freezeJson({ reasoningEffort: "medium" }), v2Body: freezeJson({ reasoning_effort: "medium" }) }),
     Object.freeze({ id: "xhigh", legacy: freezeJson({ reasoningEffort: "xhigh" }), v2Body: freezeJson({ reasoning_effort: "xhigh" }) }),
 ]);
+const QWEN_FLASH_NEXT_MODES = Object.freeze(QWEN_MODES.slice(0, 2));
+const QWEN_FLASH_NEXT_METADATA = Object.freeze({
+    modalities: Object.freeze({
+        input: Object.freeze(["text", "image"]),
+        output: Object.freeze(["text"]),
+    }),
+    attachment: true,
+    tool_call: true,
+    limit: Object.freeze({ context: 262144, output: 0 }),
+});
 const chatGptAliases = (model) => Object.freeze([
     model,
     `chatgpt/${model}`,
@@ -58,6 +69,7 @@ export const MODEL_CONTRACTS = Object.freeze([
     contract("GPT-5.6 Terra", chatGptAliases("gpt-5.6-terra"), GPT_MAX_MODES, "medium"),
     contract("DeepSeek V4 Flash", ["deepseek-v4-flash-fp8-mtp", "deepseek-v4-flash-fp8-mtp-norefusal"], DEEPSEEK_MODES, "max"),
     contract("Qwen3.8", ["qwen3.8-27b-refusal-dial"], QWEN_MODES, "xhigh"),
+    contract("Qwen3.8", ["qwen3.8-flash-next"], QWEN_FLASH_NEXT_MODES, "low", QWEN_FLASH_NEXT_METADATA),
 ]);
 export const RETIRED_MODEL_ALIASES = Object.freeze([
     ...chatGptAliases("gpt-5.3-codex"),

package/dist/types.d.ts

@@ -4,6 +4,18 @@ export type ModelContractMode = Readonly<{
     legacy: Readonly<JsonObject>;
     v2Body: Readonly<JsonObject>;
 }>;
+export type ModelContractMetadata = Readonly<{
+    modalities: Readonly<{
+        input: readonly string[];
+        output: readonly string[];
+    }>;
+    attachment: boolean;
+    tool_call: boolean;
+    limit: Readonly<{
+        context: number;
+        output: number;
+    }>;
+}>;
 export type ModelContract = Readonly<{
     family: string;
     aliases: readonly string[];
@@ -11,6 +23,7 @@ export type ModelContract = Readonly<{
     defaultMode: string;
     reasoning: true;
     variantDefault: false;
+    metadata?: ModelContractMetadata;
 }>;
 export type OpenCodeModel = JsonObject & {
     id?: string;
@@ -110,6 +123,8 @@ export type LiteLLMPluginOptions = {
     includeModes?: string[];
     excludeModels?: string[];
     includeModels?: string[];
+    /** Exact model_info.backend matches, unioned with includeModels pins. */
+    includeBackends?: string[];
     timeoutMs?: number;
     strict?: boolean;
 };
@@ -121,6 +136,7 @@ export type LiteLLMModelInfo = JsonObject & {
     model_info?: JsonObject & {
         id?: string;
         base_model?: string;
+        backend?: unknown;
         mode?: string;
         input_cost_per_token?: number | string;
         output_cost_per_token?: number | string;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@staticeng/opencode-litellm",
-  "version": "0.2.2",
+  "version": "0.2.4",
   "description": "OpenCode plugin that discovers LiteLLM models at runtime.",
   "type": "module",
   "license": "MIT",