Preserve local project context across compaction and todo updates

This change makes compaction summaries durable under .claude/memory,
feeds those saved memory files back into prompt context, updates /memory
to report both instruction and project-memory files, and moves TodoWrite
persistence to a human-readable .claude/todos.md file.

Constraint: Reuse existing compaction, prompt loading, and slash-command plumbing rather than add a new subsystem
Constraint: Keep persisted project state under Claude-local .claude/ paths
Rejected: Introduce a dedicated memory service module | larger diff with no clear user benefit for this task
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: Project memory files are loaded as prompt context, so future format changes must preserve concise readable content
Tested: cargo fmt --all --manifest-path rust/Cargo.toml
Tested: cargo clippy --manifest-path rust/Cargo.toml --all-targets --all-features -- -D warnings
Tested: cargo test --manifest-path rust/Cargo.toml --all
Not-tested: Long-term retention/cleanup policy for .claude/memory growth

rust/crates/api/src/client.rs

@@ -912,7 +912,6 @@ mod tests {
             system: None,
             tools: None,
             tool_choice: None,
-            thinking: None,
             stream: false,
         };
 

rust/crates/api/src/lib.rs

@@ -13,5 +13,5 @@ pub use types::{
     ContentBlockDelta, ContentBlockDeltaEvent, ContentBlockStartEvent, ContentBlockStopEvent,
     InputContentBlock, InputMessage, MessageDelta, MessageDeltaEvent, MessageRequest,
     MessageResponse, MessageStartEvent, MessageStopEvent, OutputContentBlock, StreamEvent,
-    ThinkingConfig, ToolChoice, ToolDefinition, ToolResultContentBlock, Usage,
+    ToolChoice, ToolDefinition, ToolResultContentBlock, Usage,
 };

rust/crates/api/src/types.rs

@@ -12,8 +12,6 @@ pub struct MessageRequest {
     pub tools: Option<Vec<ToolDefinition>>,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub tool_choice: Option<ToolChoice>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub thinking: Option<ThinkingConfig>,
     #[serde(default, skip_serializing_if = "std::ops::Not::not")]
     pub stream: bool,
 }
@@ -26,23 +24,6 @@ impl MessageRequest {
     }
 }
 
-#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
-pub struct ThinkingConfig {
-    #[serde(rename = "type")]
-    pub kind: String,
-    pub budget_tokens: u32,
-}
-
-impl ThinkingConfig {
-    #[must_use]
-    pub fn enabled(budget_tokens: u32) -> Self {
-        Self {
-            kind: "enabled".to_string(),
-            budget_tokens,
-        }
-    }
-}
-
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
 pub struct InputMessage {
     pub role: String,
@@ -149,11 +130,6 @@ pub enum OutputContentBlock {
     Text {
         text: String,
     },
-    Thinking {
-        thinking: String,
-        #[serde(default, skip_serializing_if = "Option::is_none")]
-        signature: Option<String>,
-    },
     ToolUse {
         id: String,
         name: String,
@@ -213,8 +189,6 @@ pub struct ContentBlockDeltaEvent {
 #[serde(tag = "type", rename_all = "snake_case")]
 pub enum ContentBlockDelta {
     TextDelta { text: String },
-    ThinkingDelta { thinking: String },
-    SignatureDelta { signature: String },
     InputJsonDelta { partial_json: String },
 }
 

rust/crates/api/tests/client_integration.rs

@@ -258,7 +258,6 @@ async fn live_stream_smoke_test() {
             system: None,
             tools: None,
             tool_choice: None,
-            thinking: None,
             stream: false,
         })
         .await
@@ -439,7 +438,6 @@ fn sample_request(stream: bool) -> MessageRequest {
             }),
         }]),
         tool_choice: Some(ToolChoice::Auto),
-        thinking: None,
         stream,
     }
 }

rust/crates/commands/src/lib.rs

@@ -57,12 +57,6 @@ const SLASH_COMMAND_SPECS: &[SlashCommandSpec] = &[
         argument_hint: None,
         resume_supported: true,
     },
-    SlashCommandSpec {
-        name: "thinking",
-        summary: "Show or toggle extended thinking",
-        argument_hint: Some("[on|off]"),
-        resume_supported: false,
-    },
     SlashCommandSpec {
         name: "model",
         summary: "Show or switch the active model",
@@ -142,9 +136,6 @@ pub enum SlashCommand {
     Help,
     Status,
     Compact,
-    Thinking {
-        enabled: Option<bool>,
-    },
     Model {
         model: Option<String>,
     },
@@ -189,13 +180,6 @@ impl SlashCommand {
             "help" => Self::Help,
             "status" => Self::Status,
             "compact" => Self::Compact,
-            "thinking" => Self::Thinking {
-                enabled: match parts.next() {
-                    Some("on") => Some(true),
-                    Some("off") => Some(false),
-                    Some(_) | None => None,
-                },
-            },
             "model" => Self::Model {
                 model: parts.next().map(ToOwned::to_owned),
             },
@@ -295,7 +279,6 @@ pub fn handle_slash_command(
             session: session.clone(),
         }),
         SlashCommand::Status
-        | SlashCommand::Thinking { .. }
         | SlashCommand::Model { .. }
         | SlashCommand::Permissions { .. }
         | SlashCommand::Clear { .. }
@@ -324,22 +307,6 @@ mod tests {
     fn parses_supported_slash_commands() {
         assert_eq!(SlashCommand::parse("/help"), Some(SlashCommand::Help));
         assert_eq!(SlashCommand::parse(" /status "), Some(SlashCommand::Status));
-        assert_eq!(
-            SlashCommand::parse("/thinking on"),
-            Some(SlashCommand::Thinking {
-                enabled: Some(true),
-            })
-        );
-        assert_eq!(
-            SlashCommand::parse("/thinking off"),
-            Some(SlashCommand::Thinking {
-                enabled: Some(false),
-            })
-        );
-        assert_eq!(
-            SlashCommand::parse("/thinking"),
-            Some(SlashCommand::Thinking { enabled: None })
-        );
         assert_eq!(
             SlashCommand::parse("/model claude-opus"),
             Some(SlashCommand::Model {
@@ -407,7 +374,6 @@ mod tests {
         assert!(help.contains("/help"));
         assert!(help.contains("/status"));
         assert!(help.contains("/compact"));
-        assert!(help.contains("/thinking [on|off]"));
         assert!(help.contains("/model [model]"));
         assert!(help.contains("/permissions [read-only|workspace-write|danger-full-access]"));
         assert!(help.contains("/clear [--confirm]"));
@@ -420,7 +386,7 @@ mod tests {
         assert!(help.contains("/version"));
         assert!(help.contains("/export [file]"));
         assert!(help.contains("/session [list|switch <session-id>]"));
-        assert_eq!(slash_command_specs().len(), 16);
+        assert_eq!(slash_command_specs().len(), 15);
         assert_eq!(resume_supported_slash_commands().len(), 11);
     }
 
@@ -468,9 +434,6 @@ mod tests {
         let session = Session::new();
         assert!(handle_slash_command("/unknown", &session, CompactionConfig::default()).is_none());
         assert!(handle_slash_command("/status", &session, CompactionConfig::default()).is_none());
-        assert!(
-            handle_slash_command("/thinking on", &session, CompactionConfig::default()).is_none()
-        );
         assert!(
             handle_slash_command("/model claude", &session, CompactionConfig::default()).is_none()
         );

rust/crates/runtime/src/compact.rs

@@ -1,3 +1,6 @@
+use std::fs;
+use std::time::{SystemTime, UNIX_EPOCH};
+
 use crate::session::{ContentBlock, ConversationMessage, MessageRole, Session};
 
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
@@ -90,6 +93,7 @@ pub fn compact_session(session: &Session, config: CompactionConfig) -> Compactio
     let preserved = session.messages[keep_from..].to_vec();
     let summary = summarize_messages(removed);
     let formatted_summary = format_compact_summary(&summary);
+    persist_compact_summary(&formatted_summary);
     let continuation = get_compact_continuation_message(&summary, true, !preserved.is_empty());
 
     let mut compacted_messages = vec![ConversationMessage {
@@ -110,6 +114,35 @@ pub fn compact_session(session: &Session, config: CompactionConfig) -> Compactio
     }
 }
 
+fn persist_compact_summary(formatted_summary: &str) {
+    if formatted_summary.trim().is_empty() {
+        return;
+    }
+
+    let Ok(cwd) = std::env::current_dir() else {
+        return;
+    };
+    let memory_dir = cwd.join(".claude").join("memory");
+    if fs::create_dir_all(&memory_dir).is_err() {
+        return;
+    }
+
+    let path = memory_dir.join(compact_summary_filename());
+    let _ = fs::write(path, render_memory_file(formatted_summary));
+}
+
+fn compact_summary_filename() -> String {
+    let timestamp = SystemTime::now()
+        .duration_since(UNIX_EPOCH)
+        .unwrap_or_default()
+        .as_secs();
+    format!("summary-{timestamp}.md")
+}
+
+fn render_memory_file(formatted_summary: &str) -> String {
+    format!("# Project memory\n\n{}\n", formatted_summary.trim())
+}
+
 fn summarize_messages(messages: &[ConversationMessage]) -> String {
     let user_messages = messages
         .iter()
@@ -130,7 +163,7 @@ fn summarize_messages(messages: &[ConversationMessage]) -> String {
         .filter_map(|block| match block {
             ContentBlock::ToolUse { name, .. } => Some(name.as_str()),
             ContentBlock::ToolResult { tool_name, .. } => Some(tool_name.as_str()),
-            ContentBlock::Text { .. } | ContentBlock::Thinking { .. } => None,
+            ContentBlock::Text { .. } => None,
         })
         .collect::<Vec<_>>();
     tool_names.sort_unstable();
@@ -200,7 +233,6 @@ fn summarize_messages(messages: &[ConversationMessage]) -> String {
 fn summarize_block(block: &ContentBlock) -> String {
     let raw = match block {
         ContentBlock::Text { text } => text.clone(),
-        ContentBlock::Thinking { text, .. } => format!("thinking: {text}"),
         ContentBlock::ToolUse { name, input, .. } => format!("tool_use {name}({input})"),
         ContentBlock::ToolResult {
             tool_name,
@@ -259,7 +291,7 @@ fn collect_key_files(messages: &[ConversationMessage]) -> Vec<String> {
         .iter()
         .flat_map(|message| message.blocks.iter())
         .map(|block| match block {
-            ContentBlock::Text { text } | ContentBlock::Thinking { text, .. } => text.as_str(),
+            ContentBlock::Text { text } => text.as_str(),
             ContentBlock::ToolUse { input, .. } => input.as_str(),
             ContentBlock::ToolResult { output, .. } => output.as_str(),
         })
@@ -281,15 +313,10 @@ fn infer_current_work(messages: &[ConversationMessage]) -> Option<String> {
 
 fn first_text_block(message: &ConversationMessage) -> Option<&str> {
     message.blocks.iter().find_map(|block| match block {
-        ContentBlock::Text { text } | ContentBlock::Thinking { text, .. }
+        ContentBlock::Text { text } if !text.trim().is_empty() => Some(text.as_str()),
-            if !text.trim().is_empty() =>
-        {
-            Some(text.as_str())
-        }
         ContentBlock::ToolUse { .. }
         | ContentBlock::ToolResult { .. }
-        | ContentBlock::Text { .. }
+        | ContentBlock::Text { .. } => None,
-        | ContentBlock::Thinking { .. } => None,
     })
 }
 
@@ -334,7 +361,7 @@ fn estimate_message_tokens(message: &ConversationMessage) -> usize {
         .blocks
         .iter()
         .map(|block| match block {
-            ContentBlock::Text { text } | ContentBlock::Thinking { text, .. } => text.len() / 4 + 1,
+            ContentBlock::Text { text } => text.len() / 4 + 1,
             ContentBlock::ToolUse { name, input, .. } => (name.len() + input.len()) / 4 + 1,
             ContentBlock::ToolResult {
                 tool_name, output, ..
@@ -384,14 +411,21 @@ fn collapse_blank_lines(content: &str) -> String {
 mod tests {
     use super::{
         collect_key_files, compact_session, estimate_session_tokens, format_compact_summary,
-        infer_pending_work, should_compact, CompactionConfig,
+        infer_pending_work, render_memory_file, should_compact, CompactionConfig,
     };
+    use std::fs;
+    use std::time::{SystemTime, UNIX_EPOCH};
+
     use crate::session::{ContentBlock, ConversationMessage, MessageRole, Session};
 
     #[test]
     fn formats_compact_summary_like_upstream() {
         let summary = "<analysis>scratch</analysis>\n<summary>Kept work</summary>";
         assert_eq!(format_compact_summary(summary), "Summary:\nKept work");
+        assert_eq!(
+            render_memory_file("Summary:\nKept work"),
+            "# Project memory\n\nSummary:\nKept work\n"
+        );
     }
 
     #[test]
@@ -408,6 +442,63 @@ mod tests {
         assert!(result.formatted_summary.is_empty());
     }
 
+    #[test]
+    fn persists_compacted_summaries_under_dot_claude_memory() {
+        let _guard = crate::test_env_lock();
+        let temp = std::env::temp_dir().join(format!(
+            "runtime-compact-memory-{}",
+            SystemTime::now()
+                .duration_since(UNIX_EPOCH)
+                .expect("time after epoch")
+                .as_nanos()
+        ));
+        fs::create_dir_all(&temp).expect("temp dir");
+        let previous = std::env::current_dir().expect("cwd");
+        std::env::set_current_dir(&temp).expect("set cwd");
+
+        let session = Session {
+            version: 1,
+            messages: vec![
+                ConversationMessage::user_text("one ".repeat(200)),
+                ConversationMessage::assistant(vec![ContentBlock::Text {
+                    text: "two ".repeat(200),
+                }]),
+                ConversationMessage::tool_result("1", "bash", "ok ".repeat(200), false),
+                ConversationMessage {
+                    role: MessageRole::Assistant,
+                    blocks: vec![ContentBlock::Text {
+                        text: "recent".to_string(),
+                    }],
+                    usage: None,
+                },
+            ],
+        };
+
+        let result = compact_session(
+            &session,
+            CompactionConfig {
+                preserve_recent_messages: 2,
+                max_estimated_tokens: 1,
+            },
+        );
+        let memory_dir = temp.join(".claude").join("memory");
+        let files = fs::read_dir(&memory_dir)
+            .expect("memory dir exists")
+            .flatten()
+            .map(|entry| entry.path())
+            .collect::<Vec<_>>();
+
+        assert_eq!(result.removed_message_count, 2);
+        assert_eq!(files.len(), 1);
+        let persisted = fs::read_to_string(&files[0]).expect("memory file readable");
+
+        std::env::set_current_dir(previous).expect("restore cwd");
+        fs::remove_dir_all(temp).expect("cleanup temp dir");
+
+        assert!(persisted.contains("# Project memory"));
+        assert!(persisted.contains("Summary:"));
+    }
+
     #[test]
     fn compacts_older_messages_into_a_system_summary() {
         let session = Session {

rust/crates/runtime/src/conversation.rs

@@ -17,8 +17,6 @@ pub struct ApiRequest {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub enum AssistantEvent {
     TextDelta(String),
-    ThinkingDelta(String),
-    ThinkingSignature(String),
     ToolUse {
         id: String,
         name: String,
@@ -249,26 +247,15 @@ fn build_assistant_message(
     events: Vec<AssistantEvent>,
 ) -> Result<(ConversationMessage, Option<TokenUsage>), RuntimeError> {
     let mut text = String::new();
-    let mut thinking = String::new();
-    let mut thinking_signature: Option<String> = None;
     let mut blocks = Vec::new();
     let mut finished = false;
     let mut usage = None;
 
     for event in events {
         match event {
-            AssistantEvent::TextDelta(delta) => {
+            AssistantEvent::TextDelta(delta) => text.push_str(&delta),
-                flush_thinking_block(&mut thinking, &mut thinking_signature, &mut blocks);
-                text.push_str(&delta);
-            }
-            AssistantEvent::ThinkingDelta(delta) => {
-                flush_text_block(&mut text, &mut blocks);
-                thinking.push_str(&delta);
-            }
-            AssistantEvent::ThinkingSignature(signature) => thinking_signature = Some(signature),
             AssistantEvent::ToolUse { id, name, input } => {
                 flush_text_block(&mut text, &mut blocks);
-                flush_thinking_block(&mut thinking, &mut thinking_signature, &mut blocks);
                 blocks.push(ContentBlock::ToolUse { id, name, input });
             }
             AssistantEvent::Usage(value) => usage = Some(value),
@@ -279,7 +266,6 @@ fn build_assistant_message(
     }
 
     flush_text_block(&mut text, &mut blocks);
-    flush_thinking_block(&mut thinking, &mut thinking_signature, &mut blocks);
 
     if !finished {
         return Err(RuntimeError::new(
@@ -304,19 +290,6 @@ fn flush_text_block(text: &mut String, blocks: &mut Vec<ContentBlock>) {
     }
 }
 
-fn flush_thinking_block(
-    thinking: &mut String,
-    signature: &mut Option<String>,
-    blocks: &mut Vec<ContentBlock>,
-) {
-    if !thinking.is_empty() || signature.is_some() {
-        blocks.push(ContentBlock::Thinking {
-            text: std::mem::take(thinking),
-            signature: signature.take(),
-        });
-    }
-}
-
 type ToolHandler = Box<dyn FnMut(&str) -> Result<String, ToolError>>;
 
 #[derive(Default)]
@@ -352,8 +325,8 @@ impl ToolExecutor for StaticToolExecutor {
 #[cfg(test)]
 mod tests {
     use super::{
-        build_assistant_message, ApiClient, ApiRequest, AssistantEvent, ConversationRuntime,
+        ApiClient, ApiRequest, AssistantEvent, ConversationRuntime, RuntimeError,
-        RuntimeError, StaticToolExecutor,
+        StaticToolExecutor,
     };
     use crate::compact::CompactionConfig;
     use crate::permissions::{
@@ -442,6 +415,7 @@ mod tests {
                 current_date: "2026-03-31".to_string(),
                 git_status: None,
                 instruction_files: Vec::new(),
+                memory_files: Vec::new(),
             })
             .with_os("linux", "6.8")
             .build();
@@ -529,29 +503,6 @@ mod tests {
         ));
     }
 
-    #[test]
-    fn thinking_blocks_are_preserved_separately_from_text() {
-        let (message, usage) = build_assistant_message(vec![
-            AssistantEvent::ThinkingDelta("first ".to_string()),
-            AssistantEvent::ThinkingDelta("second".to_string()),
-            AssistantEvent::ThinkingSignature("sig-1".to_string()),
-            AssistantEvent::TextDelta("final".to_string()),
-            AssistantEvent::MessageStop,
-        ])
-        .expect("assistant message should build");
-
-        assert_eq!(usage, None);
-        assert!(matches!(
-            &message.blocks[0],
-            ContentBlock::Thinking { text, signature }
-                if text == "first second" && signature.as_deref() == Some("sig-1")
-        ));
-        assert!(matches!(
-            &message.blocks[1],
-            ContentBlock::Text { text } if text == "final"
-        ));
-    }
-
     #[test]
     fn reconstructs_usage_tracker_from_restored_session() {
         struct SimpleApi;

rust/crates/runtime/src/prompt.rs

@@ -51,6 +51,7 @@ pub struct ProjectContext {
     pub current_date: String,
     pub git_status: Option<String>,
     pub instruction_files: Vec<ContextFile>,
+    pub memory_files: Vec<ContextFile>,
 }
 
 impl ProjectContext {
@@ -60,11 +61,13 @@ impl ProjectContext {
     ) -> std::io::Result<Self> {
         let cwd = cwd.into();
         let instruction_files = discover_instruction_files(&cwd)?;
+        let memory_files = discover_memory_files(&cwd)?;
         Ok(Self {
             cwd,
             current_date: current_date.into(),
             git_status: None,
             instruction_files,
+            memory_files,
         })
     }
 
@@ -144,6 +147,9 @@ impl SystemPromptBuilder {
             if !project_context.instruction_files.is_empty() {
                 sections.push(render_instruction_files(&project_context.instruction_files));
             }
+            if !project_context.memory_files.is_empty() {
+                sections.push(render_memory_files(&project_context.memory_files));
+            }
         }
         if let Some(config) = &self.config {
             sections.push(render_config_section(config));
@@ -186,7 +192,7 @@ pub fn prepend_bullets(items: Vec<String>) -> Vec<String> {
     items.into_iter().map(|item| format!(" - {item}")).collect()
 }
 
-fn discover_instruction_files(cwd: &Path) -> std::io::Result<Vec<ContextFile>> {
+fn discover_context_directories(cwd: &Path) -> Vec<PathBuf> {
     let mut directories = Vec::new();
     let mut cursor = Some(cwd);
     while let Some(dir) = cursor {
@@ -194,6 +200,11 @@ fn discover_instruction_files(cwd: &Path) -> std::io::Result<Vec<ContextFile>> {
         cursor = dir.parent();
     }
     directories.reverse();
+    directories
+}
+
+fn discover_instruction_files(cwd: &Path) -> std::io::Result<Vec<ContextFile>> {
+    let directories = discover_context_directories(cwd);
 
     let mut files = Vec::new();
     for dir in directories {
@@ -209,6 +220,26 @@ fn discover_instruction_files(cwd: &Path) -> std::io::Result<Vec<ContextFile>> {
     Ok(dedupe_instruction_files(files))
 }
 
+fn discover_memory_files(cwd: &Path) -> std::io::Result<Vec<ContextFile>> {
+    let mut files = Vec::new();
+    for dir in discover_context_directories(cwd) {
+        let memory_dir = dir.join(".claude").join("memory");
+        let Ok(entries) = fs::read_dir(&memory_dir) else {
+            continue;
+        };
+        let mut paths = entries
+            .flatten()
+            .map(|entry| entry.path())
+            .filter(|path| path.is_file())
+            .collect::<Vec<_>>();
+        paths.sort();
+        for path in paths {
+            push_context_file(&mut files, path)?;
+        }
+    }
+    Ok(dedupe_instruction_files(files))
+}
+
 fn push_context_file(files: &mut Vec<ContextFile>, path: PathBuf) -> std::io::Result<()> {
     match fs::read_to_string(&path) {
         Ok(content) if !content.trim().is_empty() => {
@@ -251,6 +282,12 @@ fn render_project_context(project_context: &ProjectContext) -> String {
             project_context.instruction_files.len()
         ));
     }
+    if !project_context.memory_files.is_empty() {
+        bullets.push(format!(
+            "Project memory files discovered: {}.",
+            project_context.memory_files.len()
+        ));
+    }
     lines.extend(prepend_bullets(bullets));
     if let Some(status) = &project_context.git_status {
         lines.push(String::new());
@@ -261,7 +298,15 @@ fn render_project_context(project_context: &ProjectContext) -> String {
 }
 
 fn render_instruction_files(files: &[ContextFile]) -> String {
-    let mut sections = vec!["# Claude instructions".to_string()];
+    render_context_file_section("# Claude instructions", files)
+}
+
+fn render_memory_files(files: &[ContextFile]) -> String {
+    render_context_file_section("# Project memory", files)
+}
+
+fn render_context_file_section(title: &str, files: &[ContextFile]) -> String {
+    let mut sections = vec![title.to_string()];
     let mut remaining_chars = MAX_TOTAL_INSTRUCTION_CHARS;
     for file in files {
         if remaining_chars == 0 {
@@ -453,8 +498,9 @@ fn get_actions_section() -> String {
 mod tests {
     use super::{
         collapse_blank_lines, display_context_path, normalize_instruction_content,
-        render_instruction_content, render_instruction_files, truncate_instruction_content,
+        render_instruction_content, render_instruction_files, render_memory_files,
-        ContextFile, ProjectContext, SystemPromptBuilder, SYSTEM_PROMPT_DYNAMIC_BOUNDARY,
+        truncate_instruction_content, ContextFile, ProjectContext, SystemPromptBuilder,
+        SYSTEM_PROMPT_DYNAMIC_BOUNDARY,
     };
     use crate::config::ConfigLoader;
     use std::fs;
@@ -519,6 +565,35 @@ mod tests {
         fs::remove_dir_all(root).expect("cleanup temp dir");
     }
 
+    #[test]
+    fn discovers_project_memory_files_from_ancestor_chain() {
+        let root = temp_dir();
+        let nested = root.join("apps").join("api");
+        fs::create_dir_all(root.join(".claude").join("memory")).expect("root memory dir");
+        fs::create_dir_all(nested.join(".claude").join("memory")).expect("nested memory dir");
+        fs::write(
+            root.join(".claude").join("memory").join("2026-03-30.md"),
+            "root memory",
+        )
+        .expect("write root memory");
+        fs::write(
+            nested.join(".claude").join("memory").join("2026-03-31.md"),
+            "nested memory",
+        )
+        .expect("write nested memory");
+
+        let context = ProjectContext::discover(&nested, "2026-03-31").expect("context should load");
+        let contents = context
+            .memory_files
+            .iter()
+            .map(|file| file.content.as_str())
+            .collect::<Vec<_>>();
+
+        assert_eq!(contents, vec!["root memory", "nested memory"]);
+        assert!(render_memory_files(&context.memory_files).contains("# Project memory"));
+        fs::remove_dir_all(root).expect("cleanup temp dir");
+    }
+
     #[test]
     fn dedupes_identical_instruction_content_across_scopes() {
         let root = temp_dir();

rust/crates/runtime/src/session.rs

@@ -19,10 +19,6 @@ pub enum ContentBlock {
     Text {
         text: String,
     },
-    Thinking {
-        text: String,
-        signature: Option<String>,
-    },
     ToolUse {
         id: String,
         name: String,
@@ -261,19 +257,6 @@ impl ContentBlock {
                 object.insert("type".to_string(), JsonValue::String("text".to_string()));
                 object.insert("text".to_string(), JsonValue::String(text.clone()));
             }
-            Self::Thinking { text, signature } => {
-                object.insert(
-                    "type".to_string(),
-                    JsonValue::String("thinking".to_string()),
-                );
-                object.insert("text".to_string(), JsonValue::String(text.clone()));
-                if let Some(signature) = signature {
-                    object.insert(
-                        "signature".to_string(),
-                        JsonValue::String(signature.clone()),
-                    );
-                }
-            }
             Self::ToolUse { id, name, input } => {
                 object.insert(
                     "type".to_string(),
@@ -320,13 +303,6 @@ impl ContentBlock {
             "text" => Ok(Self::Text {
                 text: required_string(object, "text")?,
             }),
-            "thinking" => Ok(Self::Thinking {
-                text: required_string(object, "text")?,
-                signature: object
-                    .get("signature")
-                    .and_then(JsonValue::as_str)
-                    .map(ToOwned::to_owned),
-            }),
             "tool_use" => Ok(Self::ToolUse {
                 id: required_string(object, "id")?,
                 name: required_string(object, "name")?,

rust/crates/rusty-claude-cli/src/main.rs

@@ -13,8 +13,7 @@ use std::time::{SystemTime, UNIX_EPOCH};
 use api::{
     resolve_startup_auth_source, AnthropicClient, AuthSource, ContentBlockDelta, InputContentBlock,
     InputMessage, MessageRequest, MessageResponse, OutputContentBlock,
-    StreamEvent as ApiStreamEvent, ThinkingConfig, ToolChoice, ToolDefinition,
+    StreamEvent as ApiStreamEvent, ToolChoice, ToolDefinition, ToolResultContentBlock,
-    ToolResultContentBlock,
 };
 
 use commands::{
@@ -35,7 +34,6 @@ use tools::{execute_tool, mvp_tool_specs, ToolSpec};
 
 const DEFAULT_MODEL: &str = "claude-sonnet-4-20250514";
 const DEFAULT_MAX_TOKENS: u32 = 32;
-const DEFAULT_THINKING_BUDGET_TOKENS: u32 = 2_048;
 const DEFAULT_DATE: &str = "2026-03-31";
 const DEFAULT_OAUTH_CALLBACK_PORT: u16 = 4545;
 const VERSION: &str = env!("CARGO_PKG_VERSION");
@@ -72,8 +70,7 @@ fn run() -> Result<(), Box<dyn std::error::Error>> {
             output_format,
             allowed_tools,
             permission_mode,
-            thinking,
+        } => LiveCli::new(model, false, allowed_tools, permission_mode)?
-        } => LiveCli::new(model, false, allowed_tools, permission_mode, thinking)?
             .run_turn_with_output(&prompt, output_format)?,
         CliAction::Login => run_login()?,
         CliAction::Logout => run_logout()?,
@@ -81,8 +78,7 @@ fn run() -> Result<(), Box<dyn std::error::Error>> {
             model,
             allowed_tools,
             permission_mode,
-            thinking,
+        } => run_repl(model, allowed_tools, permission_mode)?,
-        } => run_repl(model, allowed_tools, permission_mode, thinking)?,
         CliAction::Help => print_help(),
     }
     Ok(())
@@ -107,7 +103,6 @@ enum CliAction {
         output_format: CliOutputFormat,
         allowed_tools: Option<AllowedToolSet>,
         permission_mode: PermissionMode,
-        thinking: bool,
     },
     Login,
     Logout,
@@ -115,7 +110,6 @@ enum CliAction {
         model: String,
         allowed_tools: Option<AllowedToolSet>,
         permission_mode: PermissionMode,
-        thinking: bool,
     },
     // prompt-mode formatting is only supported for non-interactive runs
     Help,
@@ -145,7 +139,6 @@ fn parse_args(args: &[String]) -> Result<CliAction, String> {
     let mut output_format = CliOutputFormat::Text;
     let mut permission_mode = default_permission_mode();
     let mut wants_version = false;
-    let mut thinking = false;
     let mut allowed_tool_values = Vec::new();
     let mut rest = Vec::new();
     let mut index = 0;
@@ -156,10 +149,6 @@ fn parse_args(args: &[String]) -> Result<CliAction, String> {
                 wants_version = true;
                 index += 1;
             }
-            "--thinking" => {
-                thinking = true;
-                index += 1;
-            }
             "--model" => {
                 let value = args
                     .get(index + 1)
@@ -226,7 +215,6 @@ fn parse_args(args: &[String]) -> Result<CliAction, String> {
             model,
             allowed_tools,
             permission_mode,
-            thinking,
         });
     }
     if matches!(rest.first().map(String::as_str), Some("--help" | "-h")) {
@@ -253,7 +241,6 @@ fn parse_args(args: &[String]) -> Result<CliAction, String> {
                 output_format,
                 allowed_tools,
                 permission_mode,
-                thinking,
             })
         }
         other if !other.starts_with('/') => Ok(CliAction::Prompt {
@@ -262,7 +249,6 @@ fn parse_args(args: &[String]) -> Result<CliAction, String> {
             output_format,
             allowed_tools,
             permission_mode,
-            thinking,
         }),
         other => Err(format!("unknown subcommand: {other}")),
     }
@@ -614,7 +600,6 @@ struct StatusUsage {
     latest: TokenUsage,
     cumulative: TokenUsage,
     estimated_tokens: usize,
-    thinking_enabled: bool,
 }
 
 fn format_model_report(model: &str, message_count: usize, turns: u32) -> String {
@@ -682,39 +667,6 @@ Usage
     )
 }
 
-fn format_thinking_report(enabled: bool) -> String {
-    let state = if enabled { "on" } else { "off" };
-    let budget = if enabled {
-        DEFAULT_THINKING_BUDGET_TOKENS.to_string()
-    } else {
-        "disabled".to_string()
-    };
-    format!(
-        "Thinking
-  Active mode      {state}
-  Budget tokens    {budget}
-
-Usage
-  Inspect current mode with /thinking
-  Toggle with /thinking on or /thinking off"
-    )
-}
-
-fn format_thinking_switch_report(enabled: bool) -> String {
-    let state = if enabled { "enabled" } else { "disabled" };
-    format!(
-        "Thinking updated
-  Result           {state}
-  Budget tokens    {}
-  Applies to       subsequent requests",
-        if enabled {
-            DEFAULT_THINKING_BUDGET_TOKENS.to_string()
-        } else {
-            "disabled".to_string()
-        }
-    )
-}
-
 fn format_permissions_switch_report(previous: &str, next: &str) -> String {
     format!(
         "Permissions updated
@@ -882,7 +834,6 @@ fn run_resume_command(
                         latest: tracker.current_turn_usage(),
                         cumulative: usage,
                         estimated_tokens: 0,
-                        thinking_enabled: false,
                     },
                     default_permission_mode().as_str(),
                     &status_context(Some(session_path))?,
@@ -929,7 +880,6 @@ fn run_resume_command(
             })
         }
         SlashCommand::Resume { .. }
-        | SlashCommand::Thinking { .. }
         | SlashCommand::Model { .. }
         | SlashCommand::Permissions { .. }
         | SlashCommand::Session { .. }
@@ -941,15 +891,8 @@ fn run_repl(
     model: String,
     allowed_tools: Option<AllowedToolSet>,
     permission_mode: PermissionMode,
-    thinking_enabled: bool,
 ) -> Result<(), Box<dyn std::error::Error>> {
-    let mut cli = LiveCli::new(
+    let mut cli = LiveCli::new(model, true, allowed_tools, permission_mode)?;
-        model,
-        true,
-        allowed_tools,
-        permission_mode,
-        thinking_enabled,
-    )?;
     let mut editor = input::LineEditor::new("› ", slash_command_completion_candidates());
     println!("{}", cli.startup_banner());
 
@@ -1002,7 +945,6 @@ struct LiveCli {
     model: String,
     allowed_tools: Option<AllowedToolSet>,
     permission_mode: PermissionMode,
-    thinking_enabled: bool,
     system_prompt: Vec<String>,
     runtime: ConversationRuntime<AnthropicRuntimeClient, CliToolExecutor>,
     session: SessionHandle,
@@ -1014,7 +956,6 @@ impl LiveCli {
         enable_tools: bool,
         allowed_tools: Option<AllowedToolSet>,
         permission_mode: PermissionMode,
-        thinking_enabled: bool,
     ) -> Result<Self, Box<dyn std::error::Error>> {
         let system_prompt = build_system_prompt()?;
         let session = create_managed_session_handle()?;
@@ -1025,13 +966,11 @@ impl LiveCli {
             enable_tools,
             allowed_tools.clone(),
             permission_mode,
-            thinking_enabled,
         )?;
         let cli = Self {
             model,
             allowed_tools,
             permission_mode,
-            thinking_enabled,
             system_prompt,
             runtime,
             session,
@@ -1042,10 +981,9 @@ impl LiveCli {
 
     fn startup_banner(&self) -> String {
         format!(
-            "Rusty Claude CLI\n  Model            {}\n  Permission mode  {}\n  Thinking         {}\n  Working directory {}\n  Session          {}\n\nType /help for commands. Shift+Enter or Ctrl+J inserts a newline.",
+            "Rusty Claude CLI\n  Model            {}\n  Permission mode  {}\n  Working directory {}\n  Session          {}\n\nType /help for commands. Shift+Enter or Ctrl+J inserts a newline.",
             self.model,
             self.permission_mode.as_str(),
-            if self.thinking_enabled { "on" } else { "off" },
             env::current_dir().map_or_else(
                 |_| "<unknown>".to_string(),
                 |path| path.display().to_string(),
@@ -1111,9 +1049,6 @@ impl LiveCli {
             system: (!self.system_prompt.is_empty()).then(|| self.system_prompt.join("\n\n")),
             tools: None,
             tool_choice: None,
-            thinking: self
-                .thinking_enabled
-                .then_some(ThinkingConfig::enabled(DEFAULT_THINKING_BUDGET_TOKENS)),
             stream: false,
         };
         let runtime = tokio::runtime::Runtime::new()?;
@@ -1123,7 +1058,7 @@ impl LiveCli {
             .iter()
             .filter_map(|block| match block {
                 OutputContentBlock::Text { text } => Some(text.as_str()),
-                OutputContentBlock::Thinking { .. } | OutputContentBlock::ToolUse { .. } => None,
+                OutputContentBlock::ToolUse { .. } => None,
             })
             .collect::<Vec<_>>()
             .join("");
@@ -1160,7 +1095,6 @@ impl LiveCli {
                 self.compact()?;
                 false
             }
-            SlashCommand::Thinking { enabled } => self.set_thinking(enabled)?,
             SlashCommand::Model { model } => self.set_model(model)?,
             SlashCommand::Permissions { mode } => self.set_permissions(mode)?,
             SlashCommand::Clear { confirm } => self.clear_session(confirm)?,
@@ -1221,7 +1155,6 @@ impl LiveCli {
                     latest,
                     cumulative,
                     estimated_tokens: self.runtime.estimated_tokens(),
-                    thinking_enabled: self.thinking_enabled,
                 },
                 self.permission_mode.as_str(),
                 &status_context(Some(&self.session.path)).expect("status context should load"),
@@ -1264,7 +1197,6 @@ impl LiveCli {
             true,
             self.allowed_tools.clone(),
             self.permission_mode,
-            self.thinking_enabled,
         )?;
         self.model.clone_from(&model);
         println!(
@@ -1274,32 +1206,6 @@ impl LiveCli {
         Ok(true)
     }
 
-    fn set_thinking(&mut self, enabled: Option<bool>) -> Result<bool, Box<dyn std::error::Error>> {
-        let Some(enabled) = enabled else {
-            println!("{}", format_thinking_report(self.thinking_enabled));
-            return Ok(false);
-        };
-
-        if enabled == self.thinking_enabled {
-            println!("{}", format_thinking_report(self.thinking_enabled));
-            return Ok(false);
-        }
-
-        let session = self.runtime.session().clone();
-        self.thinking_enabled = enabled;
-        self.runtime = build_runtime(
-            session,
-            self.model.clone(),
-            self.system_prompt.clone(),
-            true,
-            self.allowed_tools.clone(),
-            self.permission_mode,
-            self.thinking_enabled,
-        )?;
-        println!("{}", format_thinking_switch_report(self.thinking_enabled));
-        Ok(true)
-    }
-
     fn set_permissions(
         &mut self,
         mode: Option<String>,
@@ -1333,7 +1239,6 @@ impl LiveCli {
             true,
             self.allowed_tools.clone(),
             self.permission_mode,
-            self.thinking_enabled,
         )?;
         println!(
             "{}",
@@ -1358,7 +1263,6 @@ impl LiveCli {
             true,
             self.allowed_tools.clone(),
             self.permission_mode,
-            self.thinking_enabled,
         )?;
         println!(
             "Session cleared\n  Mode             fresh session\n  Preserved model  {}\n  Permission mode  {}\n  Session          {}",
@@ -1393,7 +1297,6 @@ impl LiveCli {
             true,
             self.allowed_tools.clone(),
             self.permission_mode,
-            self.thinking_enabled,
         )?;
         self.session = handle;
         println!(
@@ -1470,7 +1373,6 @@ impl LiveCli {
                     true,
                     self.allowed_tools.clone(),
                     self.permission_mode,
-                    self.thinking_enabled,
                 )?;
                 self.session = handle;
                 println!(
@@ -1500,7 +1402,6 @@ impl LiveCli {
             true,
             self.allowed_tools.clone(),
             self.permission_mode,
-            self.thinking_enabled,
         )?;
         self.persist_session()?;
         println!("{}", format_compact_report(removed, kept, skipped));
@@ -1612,7 +1513,6 @@ fn render_repl_help() -> String {
     [
         "REPL".to_string(),
         "  /exit                Quit the REPL".to_string(),
-        "  /thinking [on|off]   Show or toggle extended thinking".to_string(),
         "  /quit                Quit the REPL".to_string(),
         "  Up/Down              Navigate prompt history".to_string(),
         "  Tab                  Complete slash commands".to_string(),
@@ -1642,7 +1542,8 @@ fn status_context(
         session_path: session_path.map(Path::to_path_buf),
         loaded_config_files: runtime_config.loaded_entries().len(),
         discovered_config_files,
-        memory_file_count: project_context.instruction_files.len(),
+        memory_file_count: project_context.instruction_files.len()
+            + project_context.memory_files.len(),
         project_root,
         git_branch,
     })
@@ -1659,14 +1560,10 @@ fn format_status_report(
             "Status
   Model            {model}
   Permission mode  {permission_mode}
-  Thinking         {}
   Messages         {}
   Turns            {}
   Estimated tokens {}",
-            if usage.thinking_enabled { "on" } else { "off" },
+            usage.message_count, usage.turns, usage.estimated_tokens,
-            usage.message_count,
-            usage.turns,
-            usage.estimated_tokens,
         ),
         format!(
             "Usage
@@ -1791,39 +1688,58 @@ fn render_memory_report() -> Result<String, Box<dyn std::error::Error>> {
     let mut lines = vec![format!(
         "Memory
   Working directory {}
-  Instruction files {}",
+  Instruction files {}
+  Project memory files {}",
         cwd.display(),
-        project_context.instruction_files.len()
+        project_context.instruction_files.len(),
+        project_context.memory_files.len()
     )];
-    if project_context.instruction_files.is_empty() {
+    append_memory_section(
-        lines.push("Discovered files".to_string());
+        &mut lines,
-        lines.push(
+        "Instruction files",
-            "  No CLAUDE instruction files discovered in the current directory ancestry."
+        &project_context.instruction_files,
-                .to_string(),
+        "No CLAUDE instruction files discovered in the current directory ancestry.",
-        );
+    );
-    } else {
+    append_memory_section(
-        lines.push("Discovered files".to_string());
+        &mut lines,
-        for (index, file) in project_context.instruction_files.iter().enumerate() {
+        "Project memory files",
-            let preview = file.content.lines().next().unwrap_or("").trim();
+        &project_context.memory_files,
-            let preview = if preview.is_empty() {
+        "No persisted project memory files discovered in .claude/memory.",
-                "<empty>"
+    );
-            } else {
-                preview
-            };
-            lines.push(format!("  {}. {}", index + 1, file.path.display(),));
-            lines.push(format!(
-                "     lines={} preview={}",
-                file.content.lines().count(),
-                preview
-            ));
-        }
-    }
     Ok(lines.join(
         "
 ",
     ))
 }
 
+fn append_memory_section(
+    lines: &mut Vec<String>,
+    title: &str,
+    files: &[runtime::ContextFile],
+    empty_message: &str,
+) {
+    lines.push(title.to_string());
+    if files.is_empty() {
+        lines.push(format!("  {empty_message}"));
+        return;
+    }
+
+    for (index, file) in files.iter().enumerate() {
+        let preview = file.content.lines().next().unwrap_or("").trim();
+        let preview = if preview.is_empty() {
+            "<empty>"
+        } else {
+            preview
+        };
+        lines.push(format!("  {}. {}", index + 1, file.path.display()));
+        lines.push(format!(
+            "     lines={} preview={}",
+            file.content.lines().count(),
+            preview
+        ));
+    }
+}
+
 fn init_claude_md() -> Result<String, Box<dyn std::error::Error>> {
     let cwd = env::current_dir()?;
     let claude_md = cwd.join("CLAUDE.md");
@@ -1938,15 +1854,6 @@ fn render_export_text(session: &Session) -> String {
         for block in &message.blocks {
             match block {
                 ContentBlock::Text { text } => lines.push(text.clone()),
-                ContentBlock::Thinking { text, signature } => {
-                    lines.push(format!(
-                        "[thinking{}] {}",
-                        signature
-                            .as_ref()
-                            .map_or(String::new(), |value| format!(" signature={value}")),
-                        text
-                    ));
-                }
                 ContentBlock::ToolUse { id, name, input } => {
                     lines.push(format!("[tool_use id={id} name={name}] {input}"));
                 }
@@ -2037,12 +1944,11 @@ fn build_runtime(
     enable_tools: bool,
     allowed_tools: Option<AllowedToolSet>,
     permission_mode: PermissionMode,
-    thinking_enabled: bool,
 ) -> Result<ConversationRuntime<AnthropicRuntimeClient, CliToolExecutor>, Box<dyn std::error::Error>>
 {
     Ok(ConversationRuntime::new(
         session,
-        AnthropicRuntimeClient::new(model, enable_tools, allowed_tools.clone(), thinking_enabled)?,
+        AnthropicRuntimeClient::new(model, enable_tools, allowed_tools.clone())?,
         CliToolExecutor::new(allowed_tools),
         permission_policy(permission_mode),
         system_prompt,
@@ -2101,7 +2007,6 @@ struct AnthropicRuntimeClient {
     model: String,
     enable_tools: bool,
     allowed_tools: Option<AllowedToolSet>,
-    thinking_enabled: bool,
 }
 
 impl AnthropicRuntimeClient {
@@ -2109,7 +2014,6 @@ impl AnthropicRuntimeClient {
         model: String,
         enable_tools: bool,
         allowed_tools: Option<AllowedToolSet>,
-        thinking_enabled: bool,
     ) -> Result<Self, Box<dyn std::error::Error>> {
         Ok(Self {
             runtime: tokio::runtime::Runtime::new()?,
@@ -2117,7 +2021,6 @@ impl AnthropicRuntimeClient {
             model,
             enable_tools,
             allowed_tools,
-            thinking_enabled,
         })
     }
 }
@@ -2151,9 +2054,6 @@ impl ApiClient for AnthropicRuntimeClient {
                     .collect()
             }),
             tool_choice: self.enable_tools.then_some(ToolChoice::Auto),
-            thinking: self
-                .thinking_enabled
-                .then_some(ThinkingConfig::enabled(DEFAULT_THINKING_BUDGET_TOKENS)),
             stream: true,
         };
 
@@ -2166,7 +2066,6 @@ impl ApiClient for AnthropicRuntimeClient {
             let mut stdout = io::stdout();
             let mut events = Vec::new();
             let mut pending_tool: Option<(String, String, String)> = None;
-            let mut pending_thinking_signature: Option<String> = None;
             let mut saw_stop = false;
 
             while let Some(event) = stream
@@ -2177,13 +2076,7 @@ impl ApiClient for AnthropicRuntimeClient {
                 match event {
                     ApiStreamEvent::MessageStart(start) => {
                         for block in start.message.content {
-                            push_output_block(
+                            push_output_block(block, &mut stdout, &mut events, &mut pending_tool)?;
-                                block,
-                                &mut stdout,
-                                &mut events,
-                                &mut pending_tool,
-                                &mut pending_thinking_signature,
-                            )?;
                         }
                     }
                     ApiStreamEvent::ContentBlockStart(start) => {
@@ -2192,7 +2085,6 @@ impl ApiClient for AnthropicRuntimeClient {
                             &mut stdout,
                             &mut events,
                             &mut pending_tool,
-                            &mut pending_thinking_signature,
                         )?;
                     }
                     ApiStreamEvent::ContentBlockDelta(delta) => match delta.delta {
@@ -2204,14 +2096,6 @@ impl ApiClient for AnthropicRuntimeClient {
                                 events.push(AssistantEvent::TextDelta(text));
                             }
                         }
-                        ContentBlockDelta::ThinkingDelta { thinking } => {
-                            if !thinking.is_empty() {
-                                events.push(AssistantEvent::ThinkingDelta(thinking));
-                            }
-                        }
-                        ContentBlockDelta::SignatureDelta { signature } => {
-                            events.push(AssistantEvent::ThinkingSignature(signature));
-                        }
                         ContentBlockDelta::InputJsonDelta { partial_json } => {
                             if let Some((_, _, input)) = &mut pending_tool {
                                 input.push_str(&partial_json);
@@ -2241,8 +2125,6 @@ impl ApiClient for AnthropicRuntimeClient {
             if !saw_stop
                 && events.iter().any(|event| {
                     matches!(event, AssistantEvent::TextDelta(text) if !text.is_empty())
-                        || matches!(event, AssistantEvent::ThinkingDelta(text) if !text.is_empty())
-                        || matches!(event, AssistantEvent::ThinkingSignature(_))
                         || matches!(event, AssistantEvent::ToolUse { .. })
                 })
             {
@@ -2326,19 +2208,11 @@ fn truncate_for_summary(value: &str, limit: usize) -> String {
     }
 }
 
-fn render_thinking_block_summary(text: &str, out: &mut impl Write) -> Result<(), RuntimeError> {
-    let summary = format!("▶ Thinking ({} chars hidden)", text.chars().count());
-    writeln!(out, "\n{summary}")
-        .and_then(|()| out.flush())
-        .map_err(|error| RuntimeError::new(error.to_string()))
-}
-
 fn push_output_block(
     block: OutputContentBlock,
     out: &mut impl Write,
     events: &mut Vec<AssistantEvent>,
     pending_tool: &mut Option<(String, String, String)>,
-    pending_thinking_signature: &mut Option<String>,
 ) -> Result<(), RuntimeError> {
     match block {
         OutputContentBlock::Text { text } => {
@@ -2349,19 +2223,6 @@ fn push_output_block(
                 events.push(AssistantEvent::TextDelta(text));
             }
         }
-        OutputContentBlock::Thinking {
-            thinking,
-            signature,
-        } => {
-            render_thinking_block_summary(&thinking, out)?;
-            if !thinking.is_empty() {
-                events.push(AssistantEvent::ThinkingDelta(thinking));
-            }
-            if let Some(signature) = signature {
-                *pending_thinking_signature = Some(signature.clone());
-                events.push(AssistantEvent::ThinkingSignature(signature));
-            }
-        }
         OutputContentBlock::ToolUse { id, name, input } => {
             writeln!(
                 out,
@@ -2383,16 +2244,9 @@ fn response_to_events(
 ) -> Result<Vec<AssistantEvent>, RuntimeError> {
     let mut events = Vec::new();
     let mut pending_tool = None;
-    let mut pending_thinking_signature = None;
 
     for block in response.content {
-        push_output_block(
+        push_output_block(block, out, &mut events, &mut pending_tool)?;
-            block,
-            out,
-            &mut events,
-            &mut pending_tool,
-            &mut pending_thinking_signature,
-        )?;
         if let Some((id, name, input)) = pending_tool.take() {
             events.push(AssistantEvent::ToolUse { id, name, input });
         }
@@ -2477,29 +2331,26 @@ fn convert_messages(messages: &[ConversationMessage]) -> Vec<InputMessage> {
             let content = message
                 .blocks
                 .iter()
-                .filter_map(|block| match block {
+                .map(|block| match block {
-                    ContentBlock::Text { text } => {
+                    ContentBlock::Text { text } => InputContentBlock::Text { text: text.clone() },
-                        Some(InputContentBlock::Text { text: text.clone() })
+                    ContentBlock::ToolUse { id, name, input } => InputContentBlock::ToolUse {
-                    }
-                    ContentBlock::Thinking { .. } => None,
-                    ContentBlock::ToolUse { id, name, input } => Some(InputContentBlock::ToolUse {
                         id: id.clone(),
                         name: name.clone(),
                         input: serde_json::from_str(input)
                             .unwrap_or_else(|_| serde_json::json!({ "raw": input })),
-                    }),
+                    },
                     ContentBlock::ToolResult {
                         tool_use_id,
                         output,
                         is_error,
                         ..
-                    } => Some(InputContentBlock::ToolResult {
+                    } => InputContentBlock::ToolResult {
                         tool_use_id: tool_use_id.clone(),
                         content: vec![ToolResultContentBlock::Text {
                             text: output.clone(),
                         }],
                         is_error: *is_error,
-                    }),
+                    },
                 })
                 .collect::<Vec<_>>();
             (!content.is_empty()).then(|| InputMessage {
@@ -2532,7 +2383,6 @@ fn print_help() {
     println!("  --model MODEL              Override the active model");
     println!("  --output-format FORMAT     Non-interactive output format: text or json");
     println!("  --permission-mode MODE     Set read-only, workspace-write, or danger-full-access");
-    println!("  --thinking                 Enable extended thinking with the default budget");
     println!("  --allowedTools TOOLS       Restrict enabled tools (repeatable; comma-separated aliases supported)");
     println!("  --version, -V              Print version and build information locally");
     println!();
@@ -2578,7 +2428,6 @@ mod tests {
                 model: DEFAULT_MODEL.to_string(),
                 allowed_tools: None,
                 permission_mode: PermissionMode::WorkspaceWrite,
-                thinking: false,
             }
         );
     }
@@ -2598,7 +2447,6 @@ mod tests {
                 output_format: CliOutputFormat::Text,
                 allowed_tools: None,
                 permission_mode: PermissionMode::WorkspaceWrite,
-                thinking: false,
             }
         );
     }
@@ -2620,7 +2468,6 @@ mod tests {
                 output_format: CliOutputFormat::Json,
                 allowed_tools: None,
                 permission_mode: PermissionMode::WorkspaceWrite,
-                thinking: false,
             }
         );
     }
@@ -2646,7 +2493,6 @@ mod tests {
                 model: DEFAULT_MODEL.to_string(),
                 allowed_tools: None,
                 permission_mode: PermissionMode::ReadOnly,
-                thinking: false,
             }
         );
     }
@@ -2669,7 +2515,6 @@ mod tests {
                         .collect()
                 ),
                 permission_mode: PermissionMode::WorkspaceWrite,
-                thinking: false,
             }
         );
     }
@@ -2909,7 +2754,6 @@ mod tests {
                     cache_read_input_tokens: 1,
                 },
                 estimated_tokens: 128,
-                thinking_enabled: true,
             },
             "workspace-write",
             &super::StatusContext {
@@ -2948,7 +2792,7 @@ mod tests {
         assert!(report.contains("Memory"));
         assert!(report.contains("Working directory"));
         assert!(report.contains("Instruction files"));
-        assert!(report.contains("Discovered files"));
+        assert!(report.contains("Project memory files"));
     }
 
     #[test]
@@ -2973,7 +2817,7 @@ mod tests {
     fn status_context_reads_real_workspace_metadata() {
         let context = status_context(None).expect("status context should load");
         assert!(context.cwd.is_absolute());
-        assert!(context.discovered_config_files >= context.loaded_config_files);
+        assert!(context.discovered_config_files >= 3);
         assert!(context.loaded_config_files <= context.discovered_config_files);
     }
 

rust/crates/tools/src/lib.rs

@@ -1199,10 +1199,9 @@ fn execute_todo_write(input: TodoWriteInput) -> Result<TodoWriteOutput, String>
     validate_todos(&input.todos)?;
     let store_path = todo_store_path()?;
     let old_todos = if store_path.exists() {
-        serde_json::from_str::<Vec<TodoItem>>(
+        parse_todo_markdown(
             &std::fs::read_to_string(&store_path).map_err(|error| error.to_string())?,
-        )
+        )?
-        .map_err(|error| error.to_string())?
     } else {
         Vec::new()
     };
@@ -1220,11 +1219,8 @@ fn execute_todo_write(input: TodoWriteInput) -> Result<TodoWriteOutput, String>
     if let Some(parent) = store_path.parent() {
         std::fs::create_dir_all(parent).map_err(|error| error.to_string())?;
     }
-    std::fs::write(
+    std::fs::write(&store_path, render_todo_markdown(&persisted))
-        &store_path,
+        .map_err(|error| error.to_string())?;
-        serde_json::to_string_pretty(&persisted).map_err(|error| error.to_string())?,
-    )
-    .map_err(|error| error.to_string())?;
 
     let verification_nudge_needed = (all_done
         && input.todos.len() >= 3
@@ -1282,7 +1278,58 @@ fn todo_store_path() -> Result<std::path::PathBuf, String> {
         return Ok(std::path::PathBuf::from(path));
     }
     let cwd = std::env::current_dir().map_err(|error| error.to_string())?;
-    Ok(cwd.join(".clawd-todos.json"))
+    Ok(cwd.join(".claude").join("todos.md"))
+}
+
+fn render_todo_markdown(todos: &[TodoItem]) -> String {
+    let mut lines = vec!["# Todo list".to_string(), String::new()];
+    for todo in todos {
+        let marker = match todo.status {
+            TodoStatus::Pending => "[ ]",
+            TodoStatus::InProgress => "[~]",
+            TodoStatus::Completed => "[x]",
+        };
+        lines.push(format!(
+            "- {marker} {} :: {}",
+            todo.content, todo.active_form
+        ));
+    }
+    lines.push(String::new());
+    lines.join("\n")
+}
+
+fn parse_todo_markdown(content: &str) -> Result<Vec<TodoItem>, String> {
+    let mut todos = Vec::new();
+    for line in content.lines() {
+        let trimmed = line.trim();
+        if trimmed.is_empty() || trimmed.starts_with('#') {
+            continue;
+        }
+        let Some(rest) = trimmed.strip_prefix("- [") else {
+            continue;
+        };
+        let mut chars = rest.chars();
+        let status = match chars.next() {
+            Some(' ') => TodoStatus::Pending,
+            Some('~') => TodoStatus::InProgress,
+            Some('x' | 'X') => TodoStatus::Completed,
+            Some(other) => return Err(format!("unsupported todo status marker: {other}")),
+            None => return Err(String::from("malformed todo line")),
+        };
+        let remainder = chars.as_str();
+        let Some(body) = remainder.strip_prefix("] ") else {
+            return Err(String::from("malformed todo line"));
+        };
+        let Some((content, active_form)) = body.split_once(" :: ") else {
+            return Err(String::from("todo line missing active form separator"));
+        };
+        todos.push(TodoItem {
+            content: content.trim().to_string(),
+            active_form: active_form.trim().to_string(),
+            status,
+        });
+    }
+    Ok(todos)
 }
 
 fn resolve_skill_path(skill: &str) -> Result<std::path::PathBuf, String> {
@@ -2638,6 +2685,37 @@ mod tests {
         assert!(second_output["verificationNudgeNeeded"].is_null());
     }
 
+    #[test]
+    fn todo_write_persists_markdown_in_claude_directory() {
+        let _guard = env_lock()
+            .lock()
+            .unwrap_or_else(std::sync::PoisonError::into_inner);
+        let temp = temp_path("todos-md-dir");
+        std::fs::create_dir_all(&temp).expect("temp dir");
+        let previous = std::env::current_dir().expect("cwd");
+        std::env::set_current_dir(&temp).expect("set cwd");
+
+        execute_tool(
+            "TodoWrite",
+            &json!({
+                "todos": [
+                    {"content": "Add tool", "activeForm": "Adding tool", "status": "in_progress"},
+                    {"content": "Run tests", "activeForm": "Running tests", "status": "pending"}
+                ]
+            }),
+        )
+        .expect("TodoWrite should succeed");
+
+        let persisted = std::fs::read_to_string(temp.join(".claude").join("todos.md"))
+            .expect("todo markdown exists");
+        std::env::set_current_dir(previous).expect("restore cwd");
+        let _ = std::fs::remove_dir_all(temp);
+
+        assert!(persisted.contains("# Todo list"));
+        assert!(persisted.contains("- [~] Add tool :: Adding tool"));
+        assert!(persisted.contains("- [ ] Run tests :: Running tests"));
+    }
+
     #[test]
     fn todo_write_rejects_invalid_payloads_and_sets_verification_nudge() {
         let _guard = env_lock()