agent: Overwrite files more cautiously (#30649)

1. The `edit_file` tool tended to use `create_or_overwrite` a bit too
often, leading to corruption of long files. This change replaces the
boolean flag with an `EditFileMode` enum, which helps Agent make a more
deliberate choice when overwriting files.

With this change, the pass rate of the new eval increased from 10% to
100%.

2. eval: Added ability to run eval on top of an existing thread. Threads
can now be loaded from JSON files in the `SerializedThread` format,
which makes it easy to use real threads as starting points for
tests/evals.

3. Don't try to restore tool cards when running in headless or eval mode
-- we don't have a window to properly do this.

Release Notes:

- N/A

crates/agent/src/agent.rs

@@ -49,7 +49,7 @@ pub use crate::context::{ContextLoadResult, LoadedContext};
 pub use crate::inline_assistant::InlineAssistant;
 use crate::slash_command_settings::SlashCommandSettings;
 pub use crate::thread::{Message, MessageSegment, Thread, ThreadEvent};
-pub use crate::thread_store::{TextThreadStore, ThreadStore};
+pub use crate::thread_store::{SerializedThread, TextThreadStore, ThreadStore};
 pub use agent_diff::{AgentDiffPane, AgentDiffToolbar};
 pub use context_store::ContextStore;
 pub use ui::preview::{all_agent_previews, get_agent_preview};

crates/agent/src/thread.rs

@@ -458,7 +458,7 @@ impl Thread {
         tools: Entity<ToolWorkingSet>,
         prompt_builder: Arc<PromptBuilder>,
         project_context: SharedProjectContext,
-        window: &mut Window,
+        window: Option<&mut Window>, // None in headless mode
         cx: &mut Context<Self>,
     ) -> Self {
         let next_message_id = MessageId(

crates/agent/src/thread_store.rs

@@ -386,6 +386,25 @@ impl ThreadStore {
         })
     }
 
+    pub fn create_thread_from_serialized(
+        &mut self,
+        serialized: SerializedThread,
+        cx: &mut Context<Self>,
+    ) -> Entity<Thread> {
+        cx.new(|cx| {
+            Thread::deserialize(
+                ThreadId::new(),
+                serialized,
+                self.project.clone(),
+                self.tools.clone(),
+                self.prompt_builder.clone(),
+                self.project_context.clone(),
+                None,
+                cx,
+            )
+        })
+    }
+
     pub fn open_thread(
         &self,
         id: &ThreadId,
@@ -411,7 +430,7 @@ impl ThreadStore {
                         this.tools.clone(),
                         this.prompt_builder.clone(),
                         this.project_context.clone(),
-                        window,
+                        Some(window),
                         cx,
                     )
                 })

crates/agent/src/tool_use.rs

@@ -54,15 +54,19 @@ impl ToolUseState {
     /// Constructs a [`ToolUseState`] from the given list of [`SerializedMessage`]s.
     ///
     /// Accepts a function to filter the tools that should be used to populate the state.
+    ///
+    /// If `window` is `None` (e.g., when in headless mode or when running evals),
+    /// tool cards won't be deserialized
     pub fn from_serialized_messages(
         tools: Entity<ToolWorkingSet>,
         messages: &[SerializedMessage],
         project: Entity<Project>,
-        window: &mut Window,
+        window: Option<&mut Window>, // None in headless mode
         cx: &mut App,
     ) -> Self {
         let mut this = Self::new(tools);
         let mut tool_names_by_id = HashMap::default();
+        let mut window = window;
 
         for message in messages {
             match message.role {
@@ -107,12 +111,17 @@ impl ToolUseState {
                                 },
                             );
 
-                            if let Some(tool) = this.tools.read(cx).tool(tool_use, cx) {
-                                if let Some(output) = tool_result.output.clone() {
-                                    if let Some(card) =
-                                        tool.deserialize_card(output, project.clone(), window, cx)
-                                    {
-                                        this.tool_result_cards.insert(tool_use_id, card);
+                            if let Some(window) = &mut window {
+                                if let Some(tool) = this.tools.read(cx).tool(tool_use, cx) {
+                                    if let Some(output) = tool_result.output.clone() {
+                                        if let Some(card) = tool.deserialize_card(
+                                            output,
+                                            project.clone(),
+                                            window,
+                                            cx,
+                                        ) {
+                                            this.tool_result_cards.insert(tool_use_id, card);
+                                        }
                                     }
                                 }
                             }