Refactor scrolling methods in ScrollState to accept an amount parameter

- Updated `scroll_up` and `scroll_down` methods to take an `amount` parameter for more flexible scrolling.
- Removed the `AgentMode` enum and related methods from the types module to simplify state management.
- Modified `AppStateRest` to remove the `mode` field and adjusted related logic.
- Enhanced `run_subagent` to build tool definitions and handle API key resolution from configuration.
- Updated command parsing to reflect changes in login handling.
- Removed onboarding overlays and related logic from input handling and rendering.
- Improved status bar to reflect connection status and agent readiness.
- Adjusted workflow panel rendering to simplify phase status display.
- Refactored edit log initialization to load from disk if available.
- Updated settings structure to use a HashMap for API keys.
- Enhanced error handling in LlmClient for authentication issues.

src/service/provider.rs

@@ -121,7 +121,9 @@ impl LlmClient {
             match result {
                 Ok((msg, usage)) => return Ok((msg, usage)),
                 Err(e) => {
-                    if attempt >= max_retries {
+                    let err_str = e.to_string();
+                    let is_auth_error = err_str.contains("API error 401") || err_str.contains("API error 403");
+                    if attempt >= max_retries || is_auth_error {
                         return Err(e);
                     }
                     eprintln!("Warning: {}. Retrying {}/{}...", e, attempt, max_retries);
@@ -143,7 +145,7 @@ impl LlmClient {
         tools: Option<Vec<ToolDef>>,
         temperature: Option<f32>,
         max_tokens: Option<u32>,
-        mut on_event: impl FnMut(&StreamEvent),
+        mut on_event: impl FnMut(&StreamEvent) -> bool,
     ) -> Result<(ChatMessage, Option<(u64, u64)>)> {
         let req = ChatRequest {
             model: self.model.clone(),
@@ -164,14 +166,16 @@ impl LlmClient {
 
         loop {
             attempt += 1;
-            let mut wrapped = |event: &StreamEvent| {
+            let mut wrapped = |event: &StreamEvent| -> bool {
                 started = true;
-                on_event(event);
+                on_event(event)
             };
             match self.try_stream_once(&req, &url, &mut wrapped) {
                 Ok(result) => return Ok(result),
                 Err(e) => {
-                    if started || attempt >= max_retries {
+                    let err_str = e.to_string();
+                    let is_auth_error = err_str.contains("API error 401") || err_str.contains("API error 403");
+                    if started || attempt >= max_retries || is_auth_error {
                         return Err(e);
                     }
                     eprintln!("Warning: {}. Retrying {}/{}...", e, attempt, max_retries);
@@ -185,7 +189,7 @@ impl LlmClient {
         &self,
         req: &ChatRequest,
         url: &str,
-        on_event: &mut dyn FnMut(&StreamEvent),
+        on_event: &mut dyn FnMut(&StreamEvent) -> bool,
     ) -> Result<(ChatMessage, Option<(u64, u64)>)> {
         use std::io::Read;
 
@@ -237,7 +241,9 @@ impl LlmClient {
             byte_buf.drain(..valid_len);
 
             for event in parser.feed(&text) {
-                on_event(&event);
+                if !on_event(&event) {
+                    anyhow::bail!("aborted");
+                }
                 match &event {
                     StreamEvent::Usage { prompt_tokens, completion_tokens, .. } => {
                         usage = Some((*prompt_tokens, *completion_tokens));