oira666_pi-limits-wait 0.5.1 → 0.5.2

package/README.md

@@ -81,7 +81,7 @@ Fallback behavior:
 4. If that model later becomes rate-limited too, the extension starts again from the same ordered list.
 5. Rate-limit reset times are remembered only in memory, so known-limited models are skipped until their countdown expires. This memory is cleared when Pi restarts.
 
-When the settings are loaded, the extension shows the full usable fallback model list. When models become rate-limited, it reports the wait in chat notifications.
+The extension rereads these files before every LLM call, so changes made during a long-running task take effect on the next LLM call without restarting Pi or using `/reload`. Tool calls do not trigger a settings read. When the settings are loaded, the extension shows the full usable fallback model list. When models become rate-limited, it reports the wait in chat notifications.
 
 ## Environment variables
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oira666_pi-limits-wait",
-  "version": "0.5.1",
+  "version": "0.5.2",
   "description": "Extension for PI that allows to automatically wait for limits to reset and retry the request",
   "type": "module",
   "license": "MIT",

package/src/stream.ts

@@ -28,6 +28,7 @@ import {
 } from "./models.js";
 import { withAttemptResponseObserver } from "./response-observer.js";
 import { errorMessageWithCauses, getRetryableError, isAbortMessage, parseRetryDelayMs, retryAfterHeaderMs } from "./retry-errors.js";
+import { loadFallbackSettings } from "./settings.js";
 import { state } from "./state.js";
 import type { FallbackModel, RetryableError, RuntimeStreamSimpleFn } from "./types.js";
 import { clearModelStatus, freezingEnabled, reasonLabel, waitForRetry } from "./ui.js";
@@ -173,6 +174,11 @@ export function streamWithLimitsRetry(
     ? AbortSignal.any([options.signal, ownerSignal])
     : options?.signal ?? ownerSignal;
 
+  // A long-running agent task can make many LLM calls between tool calls.
+  // Refresh here—not only in before_agent_start—so project settings edited
+  // during that task take effect on the next LLM call without /reload.
+  if (state.sharedCtx?.modelRegistry) loadFallbackSettings(state.sharedCtx);
+
   void (async () => {
     let committed = false;
     let finished = false;