@staticeng/opencode-litellm 0.2.4 → 0.2.6

package/README.md

@@ -61,7 +61,7 @@ When `includeBackends` is present, models are candidates when `model_info.backen
 
 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.
 
-When LiteLLM publishes `model_info.supported_reasoning_efforts`, the plugin maps that list to OpenCode variants automatically for unknown models. Known contracts use exact alias membership and win over absent, incomplete, or conflicting discovery metadata. No substring, suffix, provider namespace, or base-model inference is used.
+When LiteLLM publishes `model_info.supported_reasoning_efforts`, the plugin maps that list to OpenCode variants automatically. Known contracts contribute their approved defaults; discovered extra efforts remain available unless that exact contract explicitly closes discovery. Currently only `qwen3.8-flash-next` closes discovery so unverified efforts cannot become active. No substring, suffix, provider namespace, or base-model inference is used.
 
 ```json
 {
@@ -93,6 +93,31 @@ When LiteLLM publishes `model_info.supported_reasoning_efforts`, the plugin maps
 
 Overrides win over built-in contracts and generated values through a recursive deep merge. Model overrides are applied first and provider overrides last. Arrays and scalar values are replaced rather than concatenated.
 
+### GPT Transport
+
+GPT models use `@ai-sdk/openai` and the Responses API through the configured
+LiteLLM base URL (for example, `/v1/responses`). Other models retain
+`@ai-sdk/openai-compatible` and Chat Completions. No OpenAI OAuth endpoint or
+direct upstream URL is introduced.
+
+Selection matches a final `gpt-` plus digit segment (case-insensitive), including
+namespaced aliases, in the routable model name, `base_model`, or
+`litellm_params.model`. Opaque deployment IDs do not override a named alias.
+The routable ID is preserved. O-series and non-GPT models are not migrated merely
+because discovery reports `mode: responses`. Explicit model `provider.npm`
+overrides still win; V2 uses the corresponding `api.package`.
+
+Legacy reasoning options remain `reasoningEffort` (OpenCode places them under
+`providerOptions.openai` for this SDK). V2 GPT request defaults and variants use
+Responses wire bodies: `reasoning: { effort }`, not `reasoning_effort`.
+Use an OpenCode release with AI SDK 5 or newer, where the OpenAI SDK's
+`languageModel()` defaults to Responses. Tests pin the SDK versions used by
+OpenCode at qualification time; these are development dependencies only.
+
+After upgrading, pin the exact plugin version and restart only when active
+sessions can safely stop. Existing processes retain their loaded plugin; do not
+clear global caches to upgrade one plugin.
+
 The built-in mode matrix is:
 
 | Contract | Modes in order | Default |
@@ -102,9 +127,9 @@ The built-in mode matrix is:
 | GPT-5.6 Luna / Sol / Terra | `none`, `low`, `medium`, `high`, `xhigh`, `max` | `medium` |
 | DeepSeek V4 Flash | `off`, `low`, `high`, `max` | `max` |
 | Qwen3.8 27B refusal dial | `off`, `low`, `medium`, `xhigh` | `xhigh` |
-| Qwen3.8 Flash Next | `off`, `low` | `low` |
+| Qwen3.8 Flash Next | `off`, `low`, `medium`, `xhigh` | `xhigh` |
 
-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. Flash Next activates exactly `off`, `low`, `medium`, and `xhigh`: discovered extras such as `ultra` are suppressed, V2 omits `minimal`, `high`, and `max`, and the legacy OpenCode surface disables unsupported generic choices. 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.
 
 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.
 

package/dist/mapping.js

@@ -111,6 +111,10 @@ function enrichMetadata(existing, incoming, key) {
 function modelName(model) {
     return asString(model.model_name) ?? asString(model.litellm_params?.model) ?? asString(model.model_info?.id);
 }
+function usesGPTResponses(model) {
+    // Match a GPT family segment, not an incidental substring or an opaque deployment ID.
+    return [modelName(model), model.model_info?.base_model, model.litellm_params?.model].some((name) => typeof name === "string" && /(?:^|\/)gpt-\d[^/]*$/i.test(name));
+}
 export function mergeModelInfo(deployments, groups) {
     const byName = new Map();
     for (const model of [...deployments, ...groups]) {
@@ -327,16 +331,19 @@ function generatedModel(model, tombstones = false) {
     if (!name)
         return undefined;
     const mappedModalities = modalities(model);
+    const discoveredVariants = supportsReasoning(model) ? reasoningVariants(model) : undefined;
+    const suppressDiscoveredVariants = modelContract(name)?.suppressDiscoveredVariants === true;
     const generated = {
         id: name,
         name,
+        ...(usesGPTResponses(model) ? { provider: { npm: "@ai-sdk/openai" } } : {}),
         ...(asString(model.model_info?.base_model) ? { family: asString(model.model_info?.base_model) } : {}),
         ...(cost(model) ? { cost: cost(model) } : {}),
         ...(limit(model) ? { limit: limit(model) } : {}),
         modalities: mappedModalities,
         ...(mappedModalities.input.includes("image") || mappedModalities.input.includes("pdf") ? { attachment: true } : {}),
         ...(supportsReasoning(model) ? { reasoning: true } : {}),
-        ...(supportsReasoning(model) && reasoningVariants(model) ? { variants: reasoningVariants(model) } : {}),
+        ...(discoveredVariants && !suppressDiscoveredVariants ? { variants: discoveredVariants } : {}),
         ...(model.model_info?.supports_function_calling || model.model_info?.supports_tool_choice ? { tool_call: true } : {}),
     };
     const defaults = contractDefaults(name, tombstones);
@@ -368,20 +375,26 @@ function v2Variants(model) {
         return undefined;
     return Object.entries(variants).map(([id, value]) => ({ id, body: v2VariantBody(value) }));
 }
-function contractV2Variants(name, override) {
+function contractV2Variants(name, model, override) {
     const entry = modelContract(name);
     if (!entry)
         return undefined;
     const variants = entry.modes.map((mode) => ({ id: mode.id, body: { ...mode.v2Body } }));
-    if (!isRecord(override?.variants))
-        return variants;
     const byID = new Map(variants.map((variant) => [variant.id, variant]));
-    for (const [id, value] of Object.entries(override.variants)) {
-        const current = byID.get(id);
-        byID.set(id, {
-            id,
-            body: deepMerge(current?.body ?? {}, v2VariantBody(value)),
-        });
+    if (isRecord(override?.variants)) {
+        for (const [id, value] of Object.entries(override.variants)) {
+            const current = byID.get(id);
+            byID.set(id, {
+                id,
+                body: deepMerge(current?.body ?? {}, v2VariantBody(value)),
+            });
+        }
+    }
+    if (!entry.suppressDiscoveredVariants && isRecord(model.variants)) {
+        for (const [id, value] of Object.entries(model.variants)) {
+            if (!byID.has(id))
+                byID.set(id, { id, body: v2VariantBody(value) });
+        }
     }
     return Array.from(byID.values());
 }
@@ -395,8 +408,8 @@ function v2Model(model, baseURL) {
         api: {
             ...(id ? { id } : {}),
             type: "aisdk",
-            package: "@ai-sdk/openai-compatible",
-            ...(baseURL ? { url: baseURL } : {}),
+            package: model.provider?.npm ?? "@ai-sdk/openai-compatible",
+            ...(model.provider?.api ?? baseURL ? { url: model.provider?.api ?? baseURL } : {}),
             settings: {},
         },
         capabilities: {
@@ -449,10 +462,33 @@ export function mapModelsV2(models, options = {}) {
     const legacy = mapModels(models, options);
     return Object.fromEntries(Object.entries(legacy).map(([name, model]) => {
         const mapped = v2Model(model, options.baseURL);
-        const variants = contractV2Variants(name, options.overrides?.[name]);
-        return [name, variants ? { ...mapped, variants } : mapped];
+        const variants = contractV2Variants(name, model, options.overrides?.[name]);
+        const result = variants ? { ...mapped, variants } : mapped;
+        if (mapped.api?.package === "@ai-sdk/openai") {
+            const body = responsesBody(isRecord(model.options) ? model.options : {});
+            result.request = { body };
+            result.variants = result.variants?.map((variant) => ({ ...variant, body: responsesBody(variant.body ?? {}) }));
+        }
+        return [name, result];
     }));
 }
+function responsesBody(options) {
+    const body = { ...options };
+    const effort = body.reasoningEffort ?? body.reasoning_effort;
+    const summary = body.reasoningSummary;
+    delete body.reasoningEffort;
+    delete body.reasoning_effort;
+    delete body.reasoningSummary;
+    delete body.variantDefault;
+    if (effort !== undefined || summary !== undefined) {
+        body.reasoning = {
+            ...(isRecord(body.reasoning) ? body.reasoning : {}),
+            ...(effort !== undefined ? { effort } : {}),
+            ...(summary !== undefined ? { summary } : {}),
+        };
+    }
+    return body;
+}
 export function buildProviderV2(models, options = {}) {
     return deepMerge({
         name: options.providerName ?? "LiteLLM",

package/dist/model-contracts.js

@@ -12,7 +12,7 @@ function effortModes(ids) {
         v2Body: freezeJson({ reasoning_effort: id }),
     })));
 }
-function contract(family, aliases, modes, defaultMode, metadata) {
+function contract(family, aliases, modes, defaultMode, metadata, suppressDiscoveredVariants = false) {
     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, metadata) {
         defaultMode,
         reasoning: true,
         variantDefault: false,
+        ...(suppressDiscoveredVariants ? { suppressDiscoveredVariants: true } : {}),
         ...(metadata ? { metadata } : {}),
     });
 }
@@ -44,7 +45,6 @@ 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"]),
@@ -69,7 +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),
+    contract("Qwen3.8", ["qwen3.8-flash-next"], QWEN_MODES, "xhigh", QWEN_FLASH_NEXT_METADATA, true),
 ]);
 export const RETIRED_MODEL_ALIASES = Object.freeze([
     ...chatGptAliases("gpt-5.3-codex"),

package/dist/types.d.ts

@@ -23,9 +23,14 @@ export type ModelContract = Readonly<{
     defaultMode: string;
     reasoning: true;
     variantDefault: false;
+    suppressDiscoveredVariants?: true;
     metadata?: ModelContractMetadata;
 }>;
 export type OpenCodeModel = JsonObject & {
+    provider?: {
+        npm?: string;
+        api?: string;
+    };
     id?: string;
     name?: string;
     cost?: {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@staticeng/opencode-litellm",
-  "version": "0.2.4",
+  "version": "0.2.6",
   "description": "OpenCode plugin that discovers LiteLLM models at runtime.",
   "type": "module",
   "license": "MIT",
@@ -30,6 +30,8 @@
     "@opencode-ai/plugin": "*"
   },
   "devDependencies": {
+    "@ai-sdk/openai": "3.0.84",
+    "@ai-sdk/openai-compatible": "2.0.41",
     "@opencode-ai/plugin": "latest",
     "@types/node": "^24.10.1",
     "typescript": "^5.9.3"