opencode-qwen-cli-auth 2.2.7 → 2.2.8

package/dist/index.js

@@ -16,6 +16,7 @@ import { logError, logInfo, logWarn, LOGGING_ENABLED } from "./lib/logger.js";
 const CHAT_REQUEST_TIMEOUT_MS = 30000;
 const CHAT_MAX_RETRIES = 0;
 const CHAT_MAX_TOKENS_CAP = 2048;
+const CHAT_DEFAULT_MAX_TOKENS = 2048;
 const MAX_CONSECUTIVE_POLL_FAILURES = 3;
 const QUOTA_DEGRADE_MAX_TOKENS = 1024;
 const CLI_FALLBACK_TIMEOUT_MS = 8000;
@@ -99,6 +100,34 @@ function appendLimitedText(current, chunk) {
     }
     return next.slice(next.length - CLI_FALLBACK_MAX_BUFFER_CHARS);
 }
+function isRequestInstance(value) {
+    return typeof Request !== "undefined" && value instanceof Request;
+}
+async function normalizeFetchInvocation(input, init) {
+    const requestInit = init ? { ...init } : {};
+    let requestInput = input;
+    if (!isRequestInstance(input)) {
+        return { requestInput, requestInit };
+    }
+    requestInput = input.url;
+    if (!requestInit.method) {
+        requestInit.method = input.method;
+    }
+    if (!requestInit.headers) {
+        requestInit.headers = new Headers(input.headers);
+    }
+    if (requestInit.body === undefined) {
+        try {
+            requestInit.body = await input.clone().text();
+        }
+        catch (_error) {
+        }
+    }
+    if (!requestInit.signal) {
+        requestInit.signal = input.signal;
+    }
+    return { requestInput, requestInit };
+}
 function getHeaderValue(headers, headerName) {
     if (!headers) {
         return undefined;
@@ -553,7 +582,9 @@ async function sendWithTimeout(input, requestInit) {
     }
 }
 async function failFastFetch(input, init) {
-    const requestInit = init ? { ...init } : {};
+    const normalized = await normalizeFetchInvocation(input, init);
+    const requestInput = normalized.requestInput;
+    const requestInit = normalized.requestInit;
     const sourceSignal = requestInit.signal;
     const rawPayload = parseJsonRequestBody(requestInit);
     const sessionID = typeof rawPayload?.sessionID === "string" ? rawPayload.sessionID : undefined;
@@ -575,10 +606,14 @@ async function failFastFetch(input, init) {
             request_id: context.requestId,
             sessionID: context.sessionID,
             modelID: context.modelID,
+            max_tokens: typeof payload?.max_tokens === "number" ? payload.max_tokens : undefined,
+            max_completion_tokens: typeof payload?.max_completion_tokens === "number" ? payload.max_completion_tokens : undefined,
+            message_count: Array.isArray(payload?.messages) ? payload.messages.length : undefined,
+            stream: payload?.stream === true,
         });
     }
     try {
-        let response = await sendWithTimeout(input, requestInit);
+        let response = await sendWithTimeout(requestInput, requestInit);
         if (LOGGING_ENABLED) {
             logInfo("Qwen request response", {
                 request_id: context.requestId,
@@ -603,7 +638,7 @@ async function failFastFetch(input, init) {
                             attempt: 2,
                         });
                     }
-                    response = await sendWithTimeout(input, fallbackInit);
+                    response = await sendWithTimeout(requestInput, fallbackInit);
                     if (LOGGING_ENABLED) {
                         logInfo("Qwen request response", {
                             request_id: context.requestId,
@@ -886,21 +921,21 @@ export const QwenAuthPlugin = async (_input) => {
                     maxRetries: CHAT_MAX_RETRIES,
                 },
                 models: {
-                    "coder-model": {
-                        id: "coder-model",
-                        name: "Qwen Coder (Qwen 3.5 Plus)",
+                    "coder-model": {
+                        id: "coder-model",
+                        name: "Qwen Coder (Qwen 3.5 Plus)",
                         // Qwen does not support reasoning_effort from OpenCode UI
                         // Thinking is always enabled by default on server side (qwen3.5-plus)
                         reasoning: false,
-                        limit: { context: 1048576, output: 65536 },
+                        limit: { context: 1048576, output: CHAT_MAX_TOKENS_CAP },
                         cost: { input: 0, output: 0 },
                         modalities: { input: ["text"], output: ["text"] },
                     },
-                    "vision-model": {
-                        id: "vision-model",
-                        name: "Qwen VL Plus (vision)",
-                        reasoning: false,
-                        limit: { context: 131072, output: 8192 },
+                    "vision-model": {
+                        id: "vision-model",
+                        name: "Qwen VL Plus (vision)",
+                        reasoning: false,
+                        limit: { context: 131072, output: CHAT_MAX_TOKENS_CAP },
                         cost: { input: 0, output: 0 },
                         modalities: { input: ["text"], output: ["text"] },
                     },
@@ -915,12 +950,33 @@ export const QwenAuthPlugin = async (_input) => {
                 if (typeof output.options.timeout !== "number" || output.options.timeout > CHAT_REQUEST_TIMEOUT_MS) {
                     output.options.timeout = CHAT_REQUEST_TIMEOUT_MS;
                 }
+                if (typeof output.max_tokens !== "number" || output.max_tokens > CHAT_MAX_TOKENS_CAP) {
+                    output.max_tokens = CHAT_DEFAULT_MAX_TOKENS;
+                }
+                if (typeof output.max_completion_tokens !== "number" || output.max_completion_tokens > CHAT_MAX_TOKENS_CAP) {
+                    output.max_completion_tokens = CHAT_DEFAULT_MAX_TOKENS;
+                }
+                if (typeof output.maxTokens !== "number" || output.maxTokens > CHAT_MAX_TOKENS_CAP) {
+                    output.maxTokens = CHAT_DEFAULT_MAX_TOKENS;
+                }
+                if (typeof output.options.max_tokens !== "number" || output.options.max_tokens > CHAT_MAX_TOKENS_CAP) {
+                    output.options.max_tokens = CHAT_DEFAULT_MAX_TOKENS;
+                }
+                if (typeof output.options.max_completion_tokens !== "number" || output.options.max_completion_tokens > CHAT_MAX_TOKENS_CAP) {
+                    output.options.max_completion_tokens = CHAT_DEFAULT_MAX_TOKENS;
+                }
+                if (typeof output.options.maxTokens !== "number" || output.options.maxTokens > CHAT_MAX_TOKENS_CAP) {
+                    output.options.maxTokens = CHAT_DEFAULT_MAX_TOKENS;
+                }
                 if (LOGGING_ENABLED) {
                     logInfo("Applied chat.params hotfix", {
                         sessionID: input?.sessionID,
                         modelID: input?.model?.id,
                         timeout: output.options.timeout,
                         maxRetries: output.options.maxRetries,
+                        max_tokens: output.max_tokens,
+                        max_completion_tokens: output.max_completion_tokens,
+                        maxTokens: output.maxTokens,
                     });
                 }
             }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-qwen-cli-auth",
-  "version": "2.2.7",
+  "version": "2.2.8",
   "description": "Qwen OAuth authentication plugin for opencode - use your Qwen account instead of API keys",
   "main": "./dist/index.js",
   "types": "./dist/index.d.ts",