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
2026-04-01 00:58:36 +00:00
11 changed files with 339 additions and 390 deletions
--- a/rust/crates/api/src/client.rs
+++ b/rust/crates/api/src/client.rs
@@ -912,7 +912,6 @@ mod tests {
            system: None,
            tools: None,
            tool_choice: None,
-            thinking: None,
            stream: false,
        };

--- a/rust/crates/api/src/lib.rs
+++ b/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,
 };
--- a/rust/crates/api/src/types.rs
+++ b/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 },
 }

--- a/rust/crates/api/tests/client_integration.rs
+++ b/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,
    }
 }
--- a/rust/crates/commands/src/lib.rs
+++ b/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()
        );
--- a/rust/crates/runtime/src/compact.rs
+++ b/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, .. }
-            if !text.trim().is_empty() =>
-        {
-            Some(text.as_str())
-        }
+        ContentBlock::Text { text } if !text.trim().is_empty() => Some(text.as_str()),
        ContentBlock::ToolUse { .. }
        | ContentBlock::ToolResult { .. }
-        | ContentBlock::Text { .. }
-        | ContentBlock::Thinking { .. } => None,
+        | ContentBlock::Text { .. } => 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 {
--- a/rust/crates/runtime/src/conversation.rs
+++ b/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) => {
-                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::TextDelta(delta) => text.push_str(&delta),
            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,
-        RuntimeError, StaticToolExecutor,
+        ApiClient, ApiRequest, AssistantEvent, ConversationRuntime, RuntimeError,
+        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;
--- a/rust/crates/runtime/src/prompt.rs
+++ b/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,
-        ContextFile, ProjectContext, SystemPromptBuilder, SYSTEM_PROMPT_DYNAMIC_BOUNDARY,
+        render_instruction_content, render_instruction_files, render_memory_files,
+        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();
--- a/rust/crates/runtime/src/session.rs
+++ b/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")?,
--- a/rust/crates/rusty-claude-cli/src/main.rs
+++ b/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,
-    ToolResultContentBlock,
+    StreamEvent as ApiStreamEvent, ToolChoice, ToolDefinition, 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, thinking)?
+        } => LiveCli::new(model, false, allowed_tools, permission_mode)?
            .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, thinking)?,
+        } => run_repl(model, allowed_tools, permission_mode)?,
        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(
-        model,
-        true,
-        allowed_tools,
-        permission_mode,
-        thinking_enabled,
-    )?;
+    let mut cli = LiveCli::new(model, true, allowed_tools, permission_mode)?;
    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() {
-        lines.push("Discovered files".to_string());
-        lines.push(
-            "  No CLAUDE instruction files discovered in the current directory ancestry."
-                .to_string(),
-        );
-    } else {
-        lines.push("Discovered files".to_string());
-        for (index, file) in project_context.instruction_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
-            ));
-        }
-    }
+    append_memory_section(
+        &mut lines,
+        "Instruction files",
+        &project_context.instruction_files,
+        "No CLAUDE instruction files discovered in the current directory ancestry.",
+    );
+    append_memory_section(
+        &mut lines,
+        "Project memory files",
+        &project_context.memory_files,
+        "No persisted project memory files discovered in .claude/memory.",
+    );
    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(
-                                block,
-                                &mut stdout,
-                                &mut events,
-                                &mut pending_tool,
-                                &mut pending_thinking_signature,
-                            )?;
+                            push_output_block(block, &mut stdout, &mut events, &mut pending_tool)?;
                        }
                    }
                    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(
-            block,
-            out,
-            &mut events,
-            &mut pending_tool,
-            &mut pending_thinking_signature,
-        )?;
+        push_output_block(block, out, &mut events, &mut pending_tool)?;
        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 {
-                    ContentBlock::Text { text } => {
-                        Some(InputContentBlock::Text { text: text.clone() })
-                    }
-                    ContentBlock::Thinking { .. } => None,
-                    ContentBlock::ToolUse { id, name, input } => Some(InputContentBlock::ToolUse {
+                .map(|block| match block {
+                    ContentBlock::Text { text } => InputContentBlock::Text { text: text.clone() },
+                    ContentBlock::ToolUse { id, name, input } => 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);
    }

--- a/rust/crates/tools/src/lib.rs
+++ b/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(
-        &store_path,
-        serde_json::to_string_pretty(&persisted).map_err(|error| error.to_string())?,
-    )
-    .map_err(|error| error.to_string())?;
+    std::fs::write(&store_path, render_todo_markdown(&persisted))
+        .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()