Fix UTF-8 panics and inconsistent retry logic

- Fix 7 UTF-8 byte slicing panics that crash on multi-byte characters:
  - acd.rs: extract_topic_from_text() [..50] slice
  - streaming.rs: log_stream_error() [..500] slice
  - tools/acd.rs: rehydrate message truncation [..2000] slice
  - history.rs: git commit message truncation [..69] slice
  - planner.rs: commit summary/description truncation [..69] slices
  - llm.rs: requirements summary line truncation [..117] slice

- All now use chars().count() and chars().take(N).collect() for
  UTF-8 safe truncation

- Fix inconsistent retry logic in task_execution.rs:
  - Previously only retried on Timeout errors
  - Now retries on ALL recoverable errors (rate limits, network,
    server errors, model busy, token limits, context length)
  - Added error-specific base delays (rate limit: 5s, server: 2s, etc.)
  - Added exponential backoff with ±20% jitter
  - Consistent with autonomous mode retry behavior

crates/g3-core/src/tools/acd.rs

@@ -93,8 +93,9 @@ pub async fn execute_rehydrate<W: UiWriter>(
         };
         
         // Truncate very long messages for readability
-        let content = if msg.content.len() > 2000 {
-            format!("{}... [truncated, {} chars total]", &msg.content[..2000], msg.content.len())
+        let content = if msg.content.chars().count() > 2000 {
+            let chars: String = msg.content.chars().take(2000).collect();
+            format!("{}... [truncated, {} chars total]", chars, msg.content.chars().count())
         } else {
             msg.content.clone()
         };