@oh-my-pi/pi-mnemopi 17.3.4 → 17.3.7

package/CHANGELOG.md

@@ -2,6 +2,12 @@
 
 ## [Unreleased]
 
+## [17.3.5] - 2026-08-16
+
+### Fixed
+
+- Fixed an issue where transient provider failures (such as Anthropic overload or rate limit errors) were incorrectly treated as empty responses; these failures are now retried automatically before falling back.
+
 ## [17.3.4] - 2026-08-14
 
 ### Fixed

package/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@oh-my-pi/pi-mnemopi",
-	"version": "17.3.4",
+	"version": "17.3.7",
 	"description": "Local SQLite memory engine for Oh My Pi agents",
 	"homepage": "https://omp.sh",
 	"author": "Can Boluk",
@@ -39,10 +39,10 @@
 		"fmt": "biome format --write ."
 	},
 	"dependencies": {
-		"@oh-my-pi/pi-ai": "17.3.4",
-		"@oh-my-pi/pi-catalog": "17.3.4",
-		"@oh-my-pi/pi-natives": "17.3.4",
-		"@oh-my-pi/pi-utils": "17.3.4"
+		"@oh-my-pi/pi-ai": "17.3.7",
+		"@oh-my-pi/pi-catalog": "17.3.7",
+		"@oh-my-pi/pi-natives": "17.3.7",
+		"@oh-my-pi/pi-utils": "17.3.7"
 	},
 	"peerDependencies": {
 		"fastembed": "2.1.0",

package/src/core/local-llm.ts

@@ -5,9 +5,11 @@ import {
 	completeSimple,
 	type FetchImpl,
 	type Model,
+	retryTransientCompletion,
 	withAuth,
 } from "@oh-my-pi/pi-ai";
 import { ProviderHttpError } from "@oh-my-pi/pi-ai/error";
+import { fetchWithRetry } from "@oh-my-pi/pi-utils";
 import { type CompleteOptions, callHostLlm, getHostLlmBackend } from "./llm-backends";
 import {
 	getMnemopiRuntimeOptions,
@@ -186,16 +188,18 @@ export async function callConfiguredCompletion(
 		return null;
 	}
 	try {
-		const message = await completeSimple(
-			model,
-			{
-				messages: [{ role: "user", content: prompt, timestamp: Date.now() }],
-			},
-			{
-				apiKey: llmApiKey() || undefined,
-				maxTokens: opts.maxTokens ?? llmMaxTokens(),
-				temperature,
-			},
+		const message = await retryTransientCompletion(() =>
+			completeSimple(
+				model,
+				{
+					messages: [{ role: "user", content: prompt, timestamp: Date.now() }],
+				},
+				{
+					apiKey: llmApiKey() || undefined,
+					maxTokens: opts.maxTokens ?? llmMaxTokens(),
+					temperature,
+				},
+			),
 		);
 		return assistantText(message).trim() || null;
 	} catch {
@@ -350,11 +354,12 @@ export async function callRemoteLlm(
 			if (key !== "") {
 				headers.Authorization = `Bearer ${key}`;
 			}
-			const res = await fetchImpl(`${baseUrl}/chat/completions`, {
+			const res = await fetchWithRetry(`${baseUrl}/chat/completions`, {
 				method: "POST",
 				headers,
 				body,
 				signal: AbortSignal.timeout(60000),
+				fetch: fetchImpl,
 			});
 			if (res.status === 401) {
 				throw new ProviderHttpError("mnemopi remote LLM request unauthorized (401)", 401, { headers: res.headers });