Auto-retry on transient provider errors (overloaded, rate limit, 5xx)

- Add retry logic with exponential backoff (2s, 4s, 8s) in AgentSession
- Disable Anthropic SDK built-in retries (maxRetries: 0) to allow app-level handling
- TUI shows retry status with Escape to cancel
- RPC mode: add set_auto_retry, abort_retry commands and auto_retry_start/end events
- Configurable via settings.json: retry.enabled, retry.maxRetries, retry.baseDelayMs
- Exclude context overflow errors from retry (handled by compaction)

fixes #157

packages/ai/CHANGELOG.md

@@ -2,6 +2,10 @@
 
 ## [Unreleased]
 
+### Changed
+
+- **Anthropic SDK retries disabled**: Set `maxRetries: 0` on Anthropic client to allow application-level retry handling. The SDK's built-in retries were interfering with coding-agent's retry logic. ([#157](https://github.com/badlogic/pi-mono/issues/157))
+
 ## [0.18.1] - 2025-12-10
 
 ### Added

packages/ai/src/providers/anthropic.ts

@@ -295,6 +295,7 @@ function createClient(
 			baseURL: model.baseUrl,
 			defaultHeaders,
 			dangerouslyAllowBrowser: true,
+			maxRetries: 0, // Disable SDK retries, handled by coding-agent
 		});
 
 		return { client, isOAuthToken: true };
@@ -311,6 +312,7 @@ function createClient(
 			baseURL: model.baseUrl,
 			dangerouslyAllowBrowser: true,
 			defaultHeaders,
+			maxRetries: 0, // Disable SDK retries, handled by coding-agent
 		});
 
 		return { client, isOAuthToken: false };