ak-gemini 2.3.0 → 2.4.1

package/base.js

@@ -37,11 +37,13 @@ const THINKING_SUPPORTED_MODELS = [
 ];
 
 /**
- * Model pricing per million tokens (Paid Tier Standard, base rate, as of May 2026).
+ * Model pricing per million tokens (Paid Tier Standard, base rate, as of July 2026).
  * Source: https://ai.google.dev/gemini-api/docs/pricing
  *
  * NOTES:
  * - Pro models use tiered pricing (≤200k vs >200k context). Listed rate is ≤200k base tier.
+ * - Gemma models (e.g. Gemma 4) are intentionally excluded — they are open models with
+ *   no paid per-token tier on the Gemini API (Vertex deployments bill by compute).
  * - Image-output tokens on Nano Banana models bill at $60/M (1.5 Flash Image) or $120/M (3 Pro Image).
  *   Only text-input/text-output rates are modelled here; image-output cost is NOT included in estimateCost().
  * - Audio input is more expensive on most models — listed rate covers text/image/video input.
@@ -52,6 +54,7 @@ const MODEL_PRICING = {
 	'gemini-3.1-flash-lite': { input: 0.25, output: 1.50 },
 	// Gemini 3.x preview
 	'gemini-3.1-pro-preview': { input: 2.00, output: 12.00 }, // ≤200k tier
+	'gemini-3-pro-preview': { input: 2.00, output: 12.00 },   // ≤200k tier; launch rate (superseded by 3.1, off the pricing page)
 	'gemini-3-flash-preview': { input: 0.50, output: 3.00 },
 	'gemini-3.1-flash-lite-preview': { input: 0.25, output: 1.50 },
 	'gemini-3.1-flash-image-preview': { input: 0.50, output: 3.00 }, // text-only; image-output is $60/M
@@ -155,6 +158,13 @@ class BaseGemini {
 		if (this.serviceTier) this.chatConfig['serviceTier'] = this.serviceTier;
 		if (this.includeServerSideToolInvocations) this.chatConfig['includeServerSideToolInvocations'] = true;
 
+		// ── Sampling Shortcuts ──
+		// Top-level sugar for chatConfig sampling knobs; wins over chatConfig
+		// (same precedence as the maxOutputTokens promotion below)
+		for (const key of ['temperature', 'topP', 'topK']) {
+			if (options[key] !== undefined) this.chatConfig[key] = options[key];
+		}
+
 		// Apply systemPrompt to chatConfig
 		if (this.systemPrompt) {
 			this.chatConfig.systemInstruction = this.systemPrompt;
@@ -321,6 +331,7 @@ class BaseGemini {
 	 * @param {string} [opts.contextKey='CONTEXT'] - Key for optional context
 	 * @param {string} [opts.explanationKey='EXPLANATION'] - Key for optional explanations
 	 * @param {string} [opts.systemPromptKey='SYSTEM'] - Key for system prompt overrides in examples
+	 * @param {'json'|'text'} [opts.format='json'] - Model-turn format: 'json' wraps answers in a {data} envelope (Transformer protocol); 'text' stores ANSWER verbatim (prose agents like Chat)
 	 * @returns {Promise<Array>} The updated chat history
 	 */
 	async seed(examples, opts = {}) {
@@ -336,6 +347,7 @@ class BaseGemini {
 		const contextKey = opts.contextKey || 'CONTEXT';
 		const explanationKey = opts.explanationKey || 'EXPLANATION';
 		const systemPromptKey = opts.systemPromptKey || 'SYSTEM';
+		const format = opts.format || 'json';
 
 		// Check for system prompt override in examples
 		const instructionExample = examples.find(ex => ex[systemPromptKey]);
@@ -367,9 +379,15 @@ class BaseGemini {
 				userText += promptText;
 			}
 
-			if (answerValue) modelResponse.data = answerValue;
-			if (explanationValue) modelResponse.explanation = explanationValue;
-			const modelText = JSON.stringify(modelResponse, null, 2);
+			let modelText;
+			if (format === 'text') {
+				modelText = isJSON(answerValue) ? JSON.stringify(answerValue, null, 2) : String(answerValue || '');
+				if (explanationValue) log.warn('seed(): EXPLANATION has no representation in text format; ignored.');
+			} else {
+				if (answerValue) modelResponse.data = answerValue;
+				if (explanationValue) modelResponse.explanation = explanationValue;
+				modelText = JSON.stringify(modelResponse, null, 2);
+			}
 
 			if (userText.trim().length && modelText.trim().length > 0) {
 				historyToAdd.push({ role: 'user', parts: [{ text: userText.trim() }] });

package/chat.js

@@ -47,6 +47,19 @@ class Chat extends BaseGemini {
 		log.debug(`Chat created with model: ${this.modelName}`);
 	}
 
+	/**
+	 * Seeds the conversation with example pairs stored as plain prose turns.
+	 * Chat is a prose agent — model turns are stored verbatim, not wrapped in
+	 * Transformer's {data} JSON envelope.
+	 *
+	 * @param {import('./types').TransformationExample[]} [examples]
+	 * @param {import('./types').SeedOptions} [opts={}]
+	 * @returns {Promise<Array>} The updated chat history
+	 */
+	async seed(examples, opts = {}) {
+		return super.seed(examples, { format: 'text', ...opts });
+	}
+
 	/**
 	 * Send a text message and get a response. Adds to conversation history.
 	 *

package/index.cjs

@@ -338,6 +338,8 @@ var MODEL_PRICING = {
   // Gemini 3.x preview
   "gemini-3.1-pro-preview": { input: 2, output: 12 },
   // ≤200k tier
+  "gemini-3-pro-preview": { input: 2, output: 12 },
+  // ≤200k tier; launch rate (superseded by 3.1, off the pricing page)
   "gemini-3-flash-preview": { input: 0.5, output: 3 },
   "gemini-3.1-flash-lite-preview": { input: 0.25, output: 1.5 },
   "gemini-3.1-flash-image-preview": { input: 0.5, output: 3 },
@@ -398,6 +400,9 @@ var BaseGemini = class {
     };
     if (this.serviceTier) this.chatConfig["serviceTier"] = this.serviceTier;
     if (this.includeServerSideToolInvocations) this.chatConfig["includeServerSideToolInvocations"] = true;
+    for (const key of ["temperature", "topP", "topK"]) {
+      if (options[key] !== void 0) this.chatConfig[key] = options[key];
+    }
     if (this.systemPrompt) {
       this.chatConfig.systemInstruction = this.systemPrompt;
     } else if (this.systemPrompt === null && options.systemPrompt === void 0) {
@@ -531,6 +536,7 @@ var BaseGemini = class {
    * @param {string} [opts.contextKey='CONTEXT'] - Key for optional context
    * @param {string} [opts.explanationKey='EXPLANATION'] - Key for optional explanations
    * @param {string} [opts.systemPromptKey='SYSTEM'] - Key for system prompt overrides in examples
+   * @param {'json'|'text'} [opts.format='json'] - Model-turn format: 'json' wraps answers in a {data} envelope (Transformer protocol); 'text' stores ANSWER verbatim (prose agents like Chat)
    * @returns {Promise<Array>} The updated chat history
    */
   async seed(examples, opts = {}) {
@@ -544,6 +550,7 @@ var BaseGemini = class {
     const contextKey = opts.contextKey || "CONTEXT";
     const explanationKey = opts.explanationKey || "EXPLANATION";
     const systemPromptKey = opts.systemPromptKey || "SYSTEM";
+    const format = opts.format || "json";
     const instructionExample = examples.find((ex) => ex[systemPromptKey]);
     if (instructionExample) {
       logger_default.debug(`Found system prompt in examples; reinitializing chat.`);
@@ -572,9 +579,15 @@ ${contextText}
         let promptText = isJSON(promptValue) ? JSON.stringify(promptValue, null, 2) : promptValue;
         userText += promptText;
       }
-      if (answerValue) modelResponse.data = answerValue;
-      if (explanationValue) modelResponse.explanation = explanationValue;
-      const modelText = JSON.stringify(modelResponse, null, 2);
+      let modelText;
+      if (format === "text") {
+        modelText = isJSON(answerValue) ? JSON.stringify(answerValue, null, 2) : String(answerValue || "");
+        if (explanationValue) logger_default.warn("seed(): EXPLANATION has no representation in text format; ignored.");
+      } else {
+        if (answerValue) modelResponse.data = answerValue;
+        if (explanationValue) modelResponse.explanation = explanationValue;
+        modelText = JSON.stringify(modelResponse, null, 2);
+      }
       if (userText.trim().length && modelText.trim().length > 0) {
         historyToAdd.push({ role: "user", parts: [{ text: userText.trim() }] });
         historyToAdd.push({ role: "model", parts: [{ text: modelText.trim() }] });
@@ -938,7 +951,8 @@ var Transformer = class extends base_default {
       answerKey: this.answerKey,
       contextKey: this.contextKey,
       explanationKey: this.explanationKey,
-      systemPromptKey: this.systemPromptKey
+      systemPromptKey: this.systemPromptKey,
+      format: "json"
     });
   }
   // ── Primary Send Method ──────────────────────────────────────────────────
@@ -1216,6 +1230,18 @@ var Chat = class extends base_default {
     super(options);
     logger_default.debug(`Chat created with model: ${this.modelName}`);
   }
+  /**
+   * Seeds the conversation with example pairs stored as plain prose turns.
+   * Chat is a prose agent — model turns are stored verbatim, not wrapped in
+   * Transformer's {data} JSON envelope.
+   *
+   * @param {import('./types').TransformationExample[]} [examples]
+   * @param {import('./types').SeedOptions} [opts={}]
+   * @returns {Promise<Array>} The updated chat history
+   */
+  async seed(examples, opts = {}) {
+    return super.seed(examples, { format: "text", ...opts });
+  }
   /**
    * Send a text message and get a response. Adds to conversation history.
    *

package/package.json

@@ -2,7 +2,7 @@
 	"name": "ak-gemini",
 	"author": "ak@mixpanel.com",
 	"description": "AK's Generative AI Helper for doing... everything",
-	"version": "2.3.0",
+	"version": "2.4.1",
 	"main": "index.js",
 	"files": [
 		"index.js",
@@ -65,7 +65,7 @@
 	],
 	"license": "ISC",
 	"dependencies": {
-		"@google/genai": "^2.6.0",
+		"@google/genai": "^2.10.0",
 		"dotenv": "^17.3.1",
 		"pino": "^10.3.1",
 		"pino-pretty": "^13.1.3"

package/transformer.js

@@ -141,7 +141,8 @@ class Transformer extends BaseGemini {
 			answerKey: this.answerKey,
 			contextKey: this.contextKey,
 			explanationKey: this.explanationKey,
-			systemPromptKey: this.systemPromptKey
+			systemPromptKey: this.systemPromptKey,
+			format: 'json'
 		});
 	}
 

package/types.d.ts

@@ -147,6 +147,12 @@ export interface BaseGeminiOptions {
   thinkingConfig?: ThinkingConfig | null;
   /** Maximum output tokens (default: 50000, null removes limit) */
   maxOutputTokens?: number | null;
+  /** Sampling temperature (shorthand for chatConfig.temperature; wins over chatConfig) */
+  temperature?: number;
+  /** Nucleus sampling (shorthand for chatConfig.topP; wins over chatConfig) */
+  topP?: number;
+  /** Top-k sampling (shorthand for chatConfig.topK; wins over chatConfig) */
+  topK?: number;
   /** Log level (default: based on NODE_ENV) */
   logLevel?: LogLevel;
 
@@ -563,6 +569,8 @@ export interface SeedOptions {
   contextKey?: string;
   explanationKey?: string;
   systemPromptKey?: string;
+  /** Model-turn format: 'json' wraps answers in a {data} envelope (Transformer protocol); 'text' stores ANSWER verbatim (prose agents like Chat). Default: 'json' */
+  format?: 'json' | 'text';
 }
 
 // ── Class Declarations ───────────────────────────────────────────────────────