alvin-bot 4.15.0 → 4.15.1

package/CHANGELOG.md

@@ -2,6 +2,24 @@
 
 All notable changes to Alvin Bot are documented here.
 
+## [4.15.1] — 2026-04-16
+
+### 🐛 Patch: suppress `fallbackModel` when primary is Haiku
+
+v4.15.0 unconditionally set `fallbackModel: "haiku"` on every Agent SDK call as a rate-limit safety net. When the user switched to `claude-haiku` (via `/model claude-haiku` or a workspace `model: haiku`), the SDK rejected the request:
+
+> *Fallback model cannot be the same as the main model. Please specify a different model for fallbackModel option.*
+
+The provider registry treated this as a normal failure and cascaded to the next fallback — Ollama — which then had to cold-boot (~45 s for `gemma4:e4b`). Visible symptom: a sudden multi-second latency spike immediately after picking Haiku, followed by the bot answering via the local model instead of Claude.
+
+**Fix:** `src/providers/claude-sdk-provider.ts` now checks whether the resolved primary model contains `"haiku"` and omits `fallbackModel` in that case. Opus / Sonnet / `inherit` still get Haiku as fallback. No other provider paths affected.
+
+### Commits
+
+- `ec205b5` — fix(providers): v4.15.1 — don't set fallbackModel when primary is Haiku
+
+---
+
 ## [4.15.0] — 2026-04-16
 
 ### ✨ Feature: auto-latest Claude model selection + per-workspace overrides

package/dist/providers/claude-sdk-provider.js

@@ -133,6 +133,14 @@ export class ClaudeSDKProvider {
             // Aliases "opus" | "sonnet" | "haiku" auto-resolve to the latest tier.
             const rawModel = options.model ?? this.config.model;
             const modelOverride = rawModel && rawModel !== "inherit" ? rawModel : undefined;
+            // v4.15.1 — Suppress fallbackModel when the primary model is already
+            // Haiku. The Agent SDK rejects identical model/fallbackModel pairs with
+            // "Fallback model cannot be the same as the main model", which then
+            // cascades all the way down the provider fallback chain (→ Ollama
+            // on-demand boot → noticeable latency spike). For opus/sonnet/inherit,
+            // keep Haiku as the rate-limit fallback.
+            const primaryIsHaiku = (modelOverride ?? "").toLowerCase().includes("haiku");
+            const fallbackModel = primaryIsHaiku ? undefined : "haiku";
             const q = query({
                 prompt,
                 options: {
@@ -156,11 +164,11 @@ export class ClaudeSDKProvider {
                     maxTurns: 50,
                     betas: ["context-1m-2025-08-07"],
                     ...(modelOverride ? { model: modelOverride } : {}),
-                    // Always prefer Haiku as fallback on rate-limit/overload — cheap
-                    // and fast, keeps the bot responsive when the primary tier is
-                    // throttled. Users can disable this by setting model: "inherit"
-                    // and relying purely on CLI defaults.
-                    fallbackModel: "haiku",
+                    // Prefer Haiku as fallback on rate-limit/overload — cheap and
+                    // fast, keeps the bot responsive when the primary tier is
+                    // throttled. Omitted when the primary IS Haiku (SDK requires
+                    // distinct model/fallbackModel values — see v4.15.1 fix above).
+                    ...(fallbackModel ? { fallbackModel } : {}),
                 },
             });
             let accumulatedText = "";

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "alvin-bot",
-  "version": "4.15.0",
+  "version": "4.15.1",
   "description": "Alvin Bot \u2014 Your personal AI agent on Telegram, WhatsApp, Discord, Signal, and Web.",
   "type": "module",
   "main": "dist/index.js",