melchizedek-agents 1.15.1 → 1.15.2

package/CHANGELOG.md

@@ -4,6 +4,20 @@ Consumers of the package read this file; it records changes to the
 **published API surface** (the exports map in `package.json`, the bins,
 the starter pack and the templates), not the repo's full history.
 
+## 1.15.2 — 2026-11-06
+
+**Fixed: a turn's usage and cost left out `generate_image`.** The tool called
+Gemini's image model outside the tracer, so its tokens never reached the
+turn's usage or the ledger's `cost_usd`. The call is now an `llm.request`
+through `traceLlmGeneration`, like every other model call: its tokens count in
+the turn's usage, it counts against `max_steps`, and a cancelled turn stops it
+before the request. Migration 0024 adds the price row for
+`gemini-3.1-flash-image-preview` ($0.50 in, $60.00 out at the image rate,
+$3.00 thinking, from Google's page for `gemini-3.1-flash-image`;
+`verified_at` NULL, since the preview id is not listed). A typical image costs
+about $0.08. Apply it with `npx melchizedek-db apply` before upgrading; without it,
+a turn that made an image prices NULL.
+
 ## 1.15.1 — 2026-11-06
 
 **Fixed: a conversation stuck on Anthropic after an approval** (ADR 0155).

package/db/migrations/0024_image_model_pricing.sql

@@ -0,0 +1,28 @@
+-- ============================================================================
+-- 0024_image_model_pricing — a price row for the image model generate_image
+--                            calls (extends ADR 0136)
+-- ============================================================================
+-- Rows only, in 0017's column layout (USD per million tokens). generate_image
+-- (lib/tools/generateImageTool.ts) now traces its call as an llm.request, so
+-- the turn's usage holds gemini-3.1-flash-image-preview; without a row the
+-- whole turn prices NULL.
+--
+-- gemini-3.1-flash-image-preview: Google's Gemini API pricing page
+-- (aistudio.google.com/docs/pricing, checked 2026-11-06) lists the model as
+-- gemini-3.1-flash-image, standard tier: $0.50 in, $3.00 text and thinking
+-- out, $60.00 image out. The preview id is not on the page, so verified_at
+-- stays NULL (0015's convention). A flat row has one output rate: it holds
+-- the image rate, since nearly all of the call's output is the image, so the
+-- few text tokens beside it are overcounted. Thinking bills at $3.00.
+--
+-- New rows never overwrite a row that exists: an operator's own rates
+-- survive. Nothing secret, nothing personal. Idempotent; safe to re-run.
+-- ============================================================================
+
+INSERT INTO model_pricing (model, input_per_mtok, output_per_mtok, thinking_per_mtok, cache_read_per_mtok, cache_write_per_mtok, verified_at, source, note) VALUES
+  ('gemini-3.1-flash-image-preview', 0.50, 60.00, 3.00, NULL, NULL, NULL, 'aistudio.google.com/docs/pricing (as gemini-3.1-flash-image), checked 2026-11-06', 'output at the image rate; text output ($3.00) is overcounted; preview id not on the page')
+ON CONFLICT (model) DO NOTHING;
+
+INSERT INTO melchizedek_schema_version (version, name)
+VALUES (24, '0024_image_model_pricing')
+ON CONFLICT (version) DO NOTHING;

package/dist/lib/tools/generateImageTool.d.ts

@@ -14,7 +14,13 @@
  * The contract is an own Tool (lib/tools/tool.ts); `generateImageTool` is the
  * own Tool the registry lists, made from it by asTool.
  */
+import { GoogleGenAI } from '@google/genai';
 import { z } from 'zod';
+export declare const IMAGE_MODEL = "gemini-3.1-flash-image-preview";
+/** Makes the Gemini client; a test swaps it for a stub. */
+export declare const imageClient: {
+    create: (apiKey: string) => Pick<GoogleGenAI, 'models'>;
+};
 export declare const generateImageContract: import("./toolContract.ts").DefinedTool<z.ZodObject<{
     prompt: z.ZodString;
     style: z.ZodOptional<z.ZodString>;

package/dist/lib/tools/generateImageTool.js

@@ -21,7 +21,12 @@ import { z } from 'zod';
 import { asTool, defineTool } from './toolContract.js';
 import { outputsDir } from '../paths.js';
 import { credentialValue } from '../models/credentialSource.js';
-const IMAGE_MODEL = 'gemini-3.1-flash-image-preview';
+import { traceLlmGeneration } from '../observability/tracer.js';
+export const IMAGE_MODEL = 'gemini-3.1-flash-image-preview';
+/** Makes the Gemini client; a test swaps it for a stub. */
+export const imageClient = {
+    create: (apiKey) => new GoogleGenAI({ apiKey }),
+};
 export const generateImageContract = defineTool({
     name: 'generate_image',
     description: 'Generates a real image from a structured payload and saves it to the outputs/ directory. ' +
@@ -42,7 +47,7 @@ export const generateImageContract = defineTool({
         }
         // Sizes and which options are set, never their values: the prompt carries the person's words.
         console.log(`[ImageTool] Parameters - prompt ${prompt.length} chars; set: ${[style && 'style', aspect_ratio && 'aspect_ratio', color_palette && 'color_palette'].filter(Boolean).join(', ') || 'none'}`);
-        const ai = new GoogleGenAI({ apiKey });
+        const ai = imageClient.create(apiKey);
         // Build a rich prompt that bakes in the structured parameters.
         const parts = [prompt];
         if (style)
@@ -54,13 +59,28 @@ export const generateImageContract = defineTool({
         const fullPrompt = parts.join('. ');
         try {
             console.log(`[ImageTool] Sending generateContent request to Gemini API (Model: ${IMAGE_MODEL})...`);
-            const response = await ai.models.generateContent({
-                model: IMAGE_MODEL,
-                contents: [{ role: 'user', parts: [{ text: fullPrompt }] }],
-                config: {
-                    responseModalities: ['IMAGE', 'TEXT'],
-                },
-            });
+            // Traced as one llm.request like every other model call, so the image
+            // model's tokens reach the turn's usage and the ledger prices them
+            // (model_pricing); it also counts against the turn's step budget and stops on cancel.
+            let response;
+            async function* call() {
+                response = await ai.models.generateContent({
+                    model: IMAGE_MODEL,
+                    contents: [{ role: 'user', parts: [{ text: fullPrompt }] }],
+                    config: {
+                        responseModalities: ['IMAGE', 'TEXT'],
+                    },
+                });
+                yield { usageMetadata: response.usageMetadata };
+            }
+            const request = () => ({ model: IMAGE_MODEL, messages: [{ role: 'user', parts: [{ type: 'text', text: fullPrompt }] }] });
+            for await (const r of traceLlmGeneration({ provider: 'gemini', model: IMAGE_MODEL, request }, call())) {
+                // A refused call (the step budget, a cancelled turn) never reaches the API.
+                if (r.errorCode)
+                    return `[generate_image ERROR] Model: ${IMAGE_MODEL} - ${r.errorMessage || r.errorCode}`;
+            }
+            if (!response)
+                return `No image data returned. Model used: ${IMAGE_MODEL}`;
             console.log("[ImageTool] Received response from Gemini API.");
             const candidates = response.candidates ?? [];
             console.log(`[ImageTool] Candidates found: ${candidates.length}`);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "melchizedek-agents",
-  "version": "1.15.1",
+  "version": "1.15.2",
   "description": "A multi-model, multi-agent orchestration framework — YAML-defined syndicates on the engine's own agent loop, Supabase or Postgres session persistence, pgvector long-term memory. Companion repo to the lyceumagents.com curriculum.",
   "type": "module",
   "license": "MIT",