@protolabsai/proto 0.30.0 → 0.31.0

package/cli.js

@@ -155944,7 +155944,7 @@ var init_pipeline = __esm({
         this.converter = new OpenAIContentConverter(this.contentGeneratorConfig.model, this.contentGeneratorConfig.schemaCompliance, this.contentGeneratorConfig.modalities ?? {});
       }
       async execute(request3, userPromptId) {
-        const effectiveModel = this.contentGeneratorConfig.model;
+        const effectiveModel = this.resolveEffectiveModel(request3);
         this.converter.setModel(effectiveModel);
         this.converter.setModalities(this.contentGeneratorConfig.modalities ?? {});
         return this.executeWithErrorHandling(request3, userPromptId, false, effectiveModel, async (openaiRequest) => {
@@ -155956,7 +155956,7 @@ var init_pipeline = __esm({
         });
       }
       async executeStream(request3, userPromptId) {
-        const effectiveModel = this.contentGeneratorConfig.model;
+        const effectiveModel = this.resolveEffectiveModel(request3);
         this.converter.setModel(effectiveModel);
         this.converter.setModalities(this.contentGeneratorConfig.modalities ?? {});
         return this.executeWithErrorHandling(request3, userPromptId, true, effectiveModel, async (openaiRequest, context2) => {
@@ -156306,6 +156306,22 @@ var init_pipeline = __esm({
         context2.duration = Date.now() - context2.startTime;
         this.config.errorHandler.handle(error40, context2, request3);
       }
+      /**
+       * Resolve which model to actually send to the upstream. Defaults to the
+       * configured model. Callers may opt into using `request.model` instead by
+       * setting `request.config.allowModelOverride = true` — the request.model
+       * string is used verbatim and the caller takes responsibility for it being
+       * valid/available on the backend (e.g. recap → "protolabs/fast" alias).
+       */
+      resolveEffectiveModel(request3) {
+        const configured = this.contentGeneratorConfig.model;
+        const allowOverride = request3.config?.["allowModelOverride"] === true;
+        const requested = request3.model;
+        if (allowOverride && typeof requested === "string" && requested.length > 0) {
+          return requested;
+        }
+        return configured;
+      }
       /**
        * Create request context with common properties
        */
@@ -169067,7 +169083,7 @@ __export(geminiContentGenerator_exports, {
   createGeminiContentGenerator: () => createGeminiContentGenerator
 });
 function createGeminiContentGenerator(config2, gcConfig) {
-  const version2 = "0.30.0";
+  const version2 = "0.31.0";
   const userAgent2 = config2.userAgent || `QwenCode/${version2} (${process.platform}; ${process.arch})`;
   const baseHeaders = {
     "User-Agent": userAgent2
@@ -284998,6 +285014,13 @@ var init_followup = __esm({
 });
 
 // packages/core/dist/src/recap/recapGenerator.js
+function pickRecapModel(config2) {
+  const available = config2.getModelsConfig().getAllConfiguredModels();
+  if (available.some((m3) => m3.id === PREFERRED_RECAP_MODEL_ID)) {
+    return { model: PREFERRED_RECAP_MODEL_ID, isOverride: true };
+  }
+  return { model: config2.getModel(), isOverride: false };
+}
 async function generateRecap(config2, conversationHistory, abortSignal) {
   if (conversationHistory.length === 0)
     return null;
@@ -285007,9 +285030,10 @@ async function generateRecap(config2, conversationHistory, abortSignal) {
       ...recent,
       { role: "user", parts: [{ text: RECAP_PROMPT }] }
     ];
+    const { model, isOverride } = pickRecapModel(config2);
     const generator = config2.getContentGenerator();
     const response = await generator.generateContent({
-      model: config2.getModel(),
+      model,
       contents,
       config: {
         abortSignal,
@@ -285018,7 +285042,11 @@ async function generateRecap(config2, conversationHistory, abortSignal) {
         // tool-stripping path. Without this, assistant turns containing
         // tool_calls — i.e. most of the agent's actual work — are dropped
         // before the request leaves, starving the recap of context.
-        tools: []
+        tools: [],
+        // Opt into the model override path in the OpenAI pipeline. Pipeline
+        // ignores request.model by default for safety; for recap we know the
+        // alias resolves on the gateway, so honor it.
+        ...isOverride ? { allowModelOverride: true } : {}
       }
     }, "recap");
     const text = response.candidates?.[0]?.content?.parts?.map((p2) => p2.text ?? "").join("").trim();
@@ -285032,7 +285060,7 @@ async function generateRecap(config2, conversationHistory, abortSignal) {
     return null;
   }
 }
-var debugLogger99, RECENT_MESSAGE_WINDOW, RECAP_PROMPT;
+var debugLogger99, RECENT_MESSAGE_WINDOW, PREFERRED_RECAP_MODEL_ID, RECAP_PROMPT;
 var init_recapGenerator = __esm({
   "packages/core/dist/src/recap/recapGenerator.js"() {
     "use strict";
@@ -285040,11 +285068,13 @@ var init_recapGenerator = __esm({
     init_debugLogger();
     debugLogger99 = createDebugLogger("RECAP");
     RECENT_MESSAGE_WINDOW = 30;
+    PREFERRED_RECAP_MODEL_ID = "protolabs/fast";
     RECAP_PROMPT = `That last agent turn was long. Summarize where we are so the user can pick back up cold.
 
 Write exactly 1-3 short sentences. Lead with the high-level goal \u2014 what they're building or debugging, not implementation details. Then state the concrete current status or next step. No status reports, no commit recaps, no apologies.
 
 Reply with ONLY the recap text \u2014 no headers, no quotes, no preamble.`;
+    __name(pickRecapModel, "pickRecapModel");
     __name(generateRecap, "generateRecap");
   }
 });
@@ -414963,7 +414993,7 @@ __name(getPackageJson, "getPackageJson");
 // packages/cli/src/utils/version.ts
 async function getCliVersion() {
   const pkgJson = await getPackageJson();
-  return "0.30.0";
+  return "0.31.0";
 }
 __name(getCliVersion, "getCliVersion");
 
@@ -422735,7 +422765,7 @@ var formatDuration = /* @__PURE__ */ __name((milliseconds) => {
 
 // packages/cli/src/generated/git-commit.ts
 init_esbuild_shims();
-var GIT_COMMIT_INFO = "482391a6a";
+var GIT_COMMIT_INFO = "d77ab4b1b";
 
 // packages/cli/src/utils/systemInfo.ts
 async function getNpmVersion() {
@@ -490901,7 +490931,7 @@ var QwenAgent = class {
   async initialize(args2) {
     this.clientCapabilities = args2.clientCapabilities;
     const authMethods = buildAuthMethods();
-    const version2 = "0.30.0";
+    const version2 = "0.31.0";
     return {
       protocolVersion: PROTOCOL_VERSION,
       agentInfo: {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@protolabsai/proto",
-  "version": "0.30.0",
+  "version": "0.31.0",
   "description": "proto - AI-powered coding agent",
   "repository": {
     "type": "git",
@@ -21,7 +21,7 @@
     "bundled"
   ],
   "config": {
-    "sandboxImageUri": "ghcr.io/qwenlm/qwen-code:0.30.0"
+    "sandboxImageUri": "ghcr.io/qwenlm/qwen-code:0.31.0"
   },
   "dependencies": {},
   "optionalDependencies": {