New Jeremy 2.5 Pro

Bump multer from 2.0.0 to 2.0.1

package-lock.json

@@ -74,7 +74,7 @@
                 "mime-types": "^2.1.35",
                 "moment": "^2.30.1",
                 "morphdom": "^2.7.4",
-                "multer": "^2.0.0",
+                "multer": "^2.0.1",
                 "node-fetch": "^3.3.2",
                 "node-persist": "^4.0.4",
                 "open": "^8.4.2",
@@ -3376,20 +3376,34 @@
             "license": "MIT"
         },
         "node_modules/concat-stream": {
-            "version": "1.6.2",
-            "resolved": "https://registry.npmjs.org/concat-stream/-/concat-stream-1.6.2.tgz",
-            "integrity": "sha512-27HBghJxjiZtIk3Ycvn/4kbJk/1uZuJFfuPEns6LaEvpvG1f0hTea8lilrouyo9mVc2GWdcEZ8OLoGmSADlrCw==",
+            "version": "2.0.0",
+            "resolved": "https://registry.npmjs.org/concat-stream/-/concat-stream-2.0.0.tgz",
+            "integrity": "sha512-MWufYdFw53ccGjCA+Ol7XJYpAlW6/prSMzuPOTRnJGcGzuhLn4Scrz7qf6o8bROZ514ltazcIFJZevcfbo0x7A==",
             "engines": [
-                "node >= 0.8"
+                "node >= 6.0"
             ],
             "license": "MIT",
             "dependencies": {
                 "buffer-from": "^1.0.0",
                 "inherits": "^2.0.3",
-                "readable-stream": "^2.2.2",
+                "readable-stream": "^3.0.2",
                 "typedarray": "^0.0.6"
             }
         },
+        "node_modules/concat-stream/node_modules/readable-stream": {
+            "version": "3.6.2",
+            "resolved": "https://registry.npmjs.org/readable-stream/-/readable-stream-3.6.2.tgz",
+            "integrity": "sha512-9u/sniCrY3D5WdsERHzHE4G2YCXqoG5FTHUiCC4SIbr6XcLZBY05ya9EKjYek9O5xOAwjGq+1JdGBAS7Q9ScoA==",
+            "license": "MIT",
+            "dependencies": {
+                "inherits": "^2.0.3",
+                "string_decoder": "^1.1.1",
+                "util-deprecate": "^1.0.1"
+            },
+            "engines": {
+                "node": ">= 6"
+            }
+        },
         "node_modules/content-disposition": {
             "version": "0.5.4",
             "resolved": "https://registry.npmjs.org/content-disposition/-/content-disposition-0.5.4.tgz",
@@ -6076,18 +6090,18 @@
             "license": "MIT"
         },
         "node_modules/multer": {
-            "version": "2.0.0",
-            "resolved": "https://registry.npmjs.org/multer/-/multer-2.0.0.tgz",
-            "integrity": "sha512-bS8rPZurbAuHGAnApbM9d4h1wSoYqrOqkE+6a64KLMK9yWU7gJXBDDVklKQ3TPi9DRb85cRs6yXaC0+cjxRtRg==",
+            "version": "2.0.1",
+            "resolved": "https://registry.npmjs.org/multer/-/multer-2.0.1.tgz",
+            "integrity": "sha512-Ug8bXeTIUlxurg8xLTEskKShvcKDZALo1THEX5E41pYCD2sCVub5/kIRIGqWNoqV6szyLyQKV6mD4QUrWE5GCQ==",
             "license": "MIT",
             "dependencies": {
                 "append-field": "^1.0.0",
-                "busboy": "^1.0.0",
-                "concat-stream": "^1.5.2",
-                "mkdirp": "^0.5.4",
+                "busboy": "^1.6.0",
+                "concat-stream": "^2.0.0",
+                "mkdirp": "^0.5.6",
                 "object-assign": "^4.1.1",
-                "type-is": "^1.6.4",
-                "xtend": "^4.0.0"
+                "type-is": "^1.6.18",
+                "xtend": "^4.0.2"
             },
             "engines": {
                 "node": ">= 10.16.0"

package.json

@@ -64,7 +64,7 @@
         "mime-types": "^2.1.35",
         "moment": "^2.30.1",
         "morphdom": "^2.7.4",
-        "multer": "^2.0.0",
+        "multer": "^2.0.1",
         "node-fetch": "^3.3.2",
         "node-persist": "^4.0.4",
         "open": "^8.4.2",

public/index.html

@@ -2098,8 +2098,8 @@
                                             <div class="toggle-description justifyLeft marginBot5" data-source="claude" data-i18n="Allocates a portion of the response length for thinking (min: 1024 tokens, low: 10%, medium: 25%, high: 50%, max: 95%), but minimum 1024 tokens. Auto does not request thinking.">
                                                 Allocates a portion of the response length for thinking (min: 1024 tokens, low: 10%, medium: 25%, high: 50%, max: 95%), but minimum 1024 tokens. Auto does not request thinking.
                                             </div>
-                                            <div class="toggle-description justifyLeft marginBot5" data-source="makersuite,vertexai" data-i18n="Allocates a portion of the response length for thinking (min: 0 tokens, low: 10%, medium: 25%, high: 50%, max: 24576 tokens). Auto lets the model decide.">
-                                                Allocates a portion of the response length for thinking (min: 0 tokens, low: 10%, medium: 25%, high: 50%, max: 24576 tokens). Auto lets the model decide.
+                                            <div class="toggle-description justifyLeft marginBot5" data-source="makersuite,vertexai" data-i18n="Allocates a portion of the response length for thinking (Flash 2.5/Pro 2.5) (min: 0/128 tokens, low: 10%, medium: 25%, high: 50%, max: 24576/32768 tokens). Auto lets the model decide.">
+                                                Allocates a portion of the response length for thinking (Flash 2.5/Pro 2.5) (min: 0/128 tokens, low: 10%, medium: 25%, high: 50%, max: 24576/32768 tokens). Auto lets the model decide.
                                             </div>
                                         </div>
                                     </div>
@@ -3190,6 +3190,7 @@
                                 <h4 data-i18n="Google Model">Google Model</h4>
                                 <select id="model_google_select">
                                     <optgroup label="Gemini 2.5">
+                                        <option value="gemini-2.5-pro-preview-06-05">gemini-2.5-pro-preview-06-05</option>
                                         <option value="gemini-2.5-pro-preview-05-06">gemini-2.5-pro-preview-05-06</option>
                                         <option value="gemini-2.5-pro-preview-03-25">gemini-2.5-pro-preview-03-25</option>
                                         <option value="gemini-2.5-pro-exp-03-25">gemini-2.5-pro-exp-03-25</option>
@@ -3336,6 +3337,7 @@
 
                                     <!-- Full Version Models -->
                                     <optgroup id="vertexai_full_gemini_25" label="Gemini 2.5" data-mode="full">
+                                        <option value="gemini-2.5-pro-preview-06-05">gemini-2.5-pro-preview-06-05</option>
                                         <option value="gemini-2.5-pro-preview-05-06">gemini-2.5-pro-preview-05-06</option>
                                         <option value="gemini-2.5-pro-preview-03-25">gemini-2.5-pro-preview-03-25</option>
                                         <option value="gemini-2.5-pro-exp-03-25">gemini-2.5-pro-exp-03-25</option>

public/scripts/extensions/caption/settings.html

@@ -85,6 +85,7 @@
                         <option data-type="anthropic" value="claude-3-opus-20240229">claude-3-opus-20240229</option>
                         <option data-type="anthropic" value="claude-3-sonnet-20240229">claude-3-sonnet-20240229</option>
                         <option data-type="anthropic" value="claude-3-haiku-20240307">claude-3-haiku-20240307</option>
+                        <option data-type="google" value="gemini-2.5-pro-preview-06-05">gemini-2.5-pro-preview-06-05</option>
                         <option data-type="google" value="gemini-2.5-pro-preview-05-06">gemini-2.5-pro-preview-05-06</option>
                         <option data-type="google" value="gemini-2.5-pro-preview-03-25">gemini-2.5-pro-preview-03-25</option>
                         <option data-type="google" value="gemini-2.5-pro-exp-03-25">gemini-2.5-pro-exp-03-25</option>
@@ -116,6 +117,7 @@
                         <option data-type="google" value="gemini-1.5-flash-8b-exp-0827">gemini-1.5-flash-8b-exp-0827</option>
                         <option data-type="google" value="learnlm-2.0-flash-experimental">learnlm-2.0-flash-experimental</option>
                         <option data-type="google" value="learnlm-1.5-pro-experimental">learnlm-1.5-pro-experimental</option>
+                        <option data-type="vertexai" value="gemini-2.5-pro-preview-06-05">gemini-2.5-pro-preview-06-05</option>
                         <option data-type="vertexai" value="gemini-2.5-pro-preview-05-06">gemini-2.5-pro-preview-05-06</option>
                         <option data-type="vertexai" value="gemini-2.5-pro-preview-03-25">gemini-2.5-pro-preview-03-25</option>
                         <option data-type="vertexai" value="gemini-2.5-flash-preview-05-20">gemini-2.5-flash-preview-05-20</option>

src/endpoints/backends/chat-completions.js

@@ -414,7 +414,6 @@ async function sendMakerSuiteRequest(request, response) {
         ];
 
         const isThinkingConfigModel = m => /^gemini-2.5-(flash|pro)/.test(m);
-        const isThinkingBudgetModel = m => /^gemini-2.5-flash/.test(m);
 
         const noSearchModels = [
             'gemini-2.0-flash-lite',
@@ -470,11 +469,9 @@ async function sendMakerSuiteRequest(request, response) {
         if (isThinkingConfigModel(model)) {
             const thinkingConfig = { includeThoughts: includeReasoning };
 
-            if (isThinkingBudgetModel(model)) {
-                const thinkingBudget = calculateGoogleBudgetTokens(generationConfig.maxOutputTokens, reasoningEffort);
-                if (Number.isInteger(thinkingBudget)) {
-                    thinkingConfig.thinkingBudget = thinkingBudget;
-                }
+            const thinkingBudget = calculateGoogleBudgetTokens(generationConfig.maxOutputTokens, reasoningEffort, model);
+            if (Number.isInteger(thinkingBudget)) {
+                thinkingConfig.thinkingBudget = thinkingBudget;
             }
 
             generationConfig.thinkingConfig = thinkingConfig;

src/prompt-converters.js

@@ -992,32 +992,73 @@ export function calculateClaudeBudgetTokens(maxTokens, reasoningEffort, stream)
  * Calculate the Google budget tokens for a given reasoning effort.
  * @param {number} maxTokens Maximum tokens
  * @param {string} reasoningEffort Reasoning effort
+ * @param {string} model Model name
  * @returns {number?} Budget tokens
  */
-export function calculateGoogleBudgetTokens(maxTokens, reasoningEffort) {
-    let budgetTokens = 0;
+export function calculateGoogleBudgetTokens(maxTokens, reasoningEffort, model) {
+    function getFlashBudget() {
+        let budgetTokens = 0;
 
-    switch (reasoningEffort) {
-        case REASONING_EFFORT.auto:
-            return null;
-        case REASONING_EFFORT.min:
-            budgetTokens = 0;
-            break;
-        case REASONING_EFFORT.low:
-            budgetTokens = Math.floor(maxTokens * 0.1);
-            break;
-        case REASONING_EFFORT.medium:
-            budgetTokens = Math.floor(maxTokens * 0.25);
-            break;
-        case REASONING_EFFORT.high:
-            budgetTokens = Math.floor(maxTokens * 0.5);
-            break;
-        case REASONING_EFFORT.max:
-            budgetTokens = maxTokens;
-            break;
+        switch (reasoningEffort) {
+            case REASONING_EFFORT.auto:
+                return null;
+            case REASONING_EFFORT.min:
+                budgetTokens = 0;
+                break;
+            case REASONING_EFFORT.low:
+                budgetTokens = Math.floor(maxTokens * 0.1);
+                break;
+            case REASONING_EFFORT.medium:
+                budgetTokens = Math.floor(maxTokens * 0.25);
+                break;
+            case REASONING_EFFORT.high:
+                budgetTokens = Math.floor(maxTokens * 0.5);
+                break;
+            case REASONING_EFFORT.max:
+                budgetTokens = maxTokens;
+                break;
+        }
+
+        budgetTokens = Math.min(budgetTokens, 24576);
+
+        return budgetTokens;
     }
 
-    budgetTokens = Math.min(budgetTokens, 24576);
+    function getProBudget() {
+        let budgetTokens = 0;
 
-    return budgetTokens;
+        switch (reasoningEffort) {
+            case REASONING_EFFORT.auto:
+                return null;
+            case REASONING_EFFORT.min:
+                budgetTokens = 128;
+                break;
+            case REASONING_EFFORT.low:
+                budgetTokens = Math.floor(maxTokens * 0.1);
+                break;
+            case REASONING_EFFORT.medium:
+                budgetTokens = Math.floor(maxTokens * 0.25);
+                break;
+            case REASONING_EFFORT.high:
+                budgetTokens = Math.floor(maxTokens * 0.5);
+                break;
+            case REASONING_EFFORT.max:
+                budgetTokens = maxTokens;
+                break;
+        }
+
+        budgetTokens = Math.max(Math.min(budgetTokens, 32768), 128);
+
+        return budgetTokens;
+    }
+
+    if (model.includes('flash')) {
+        return getFlashBudget();
+    }
+
+    if (model.includes('pro')) {
+        return getProBudget();
+    }
+
+    return null;
 }