Merge branch 'main' into codex-concurrent-simple

We are not recording the summary in the history.

AGENTS.md

@@ -2,7 +2,9 @@
 
 In the codex-rs folder where the rust code lives:
 
-- Never add or modify any code related to `CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR`. You operate in a sandbox where `CODEX_SANDBOX_NETWORK_DISABLED=1` will be set whenever you use the `shell` tool. Any existing code that uses `CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR` was authored with this fact in mind. It is often used to early exit out of tests that the author knew you would not be able to run given your sandbox limitations.
+- Never add or modify any code related to `CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR` or `CODEX_SANDBOX_ENV_VAR`.
+  - You operate in a sandbox where `CODEX_SANDBOX_NETWORK_DISABLED=1` will be set whenever you use the `shell` tool. Any existing code that uses `CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR` was authored with this fact in mind. It is often used to early exit out of tests that the author knew you would not be able to run given your sandbox limitations.
+  - Similarly, when you spawn a process using Seatbelt (`/usr/bin/sandbox-exec`), `CODEX_SANDBOX=seatbelt` will be set on the child process. Integration tests that want to run Seatbelt themselves cannot be run under Seatbelt, so checks for `CODEX_SANDBOX=seatbelt` are also often used to early exit out of tests, as appropriate.
 
 Before creating a pull request with changes to `codex-rs`, run `just fmt` (in `codex-rs` directory) to format the code and `just fix` (in `codex-rs` directory) to fix any linter issues in the code, ensure the test suite passes by running `cargo test --all-features` in the `codex-rs` directory.
 

SUMMARY.md

@@ -0,0 +1,21 @@
+You are a summarization assistant. A conversation follows between a user and a coding-focused AI (Codex). Your task is to generate a clear summary capturing:
+
+• High-level objective or problem being solved  
+• Key instructions or design decisions given by the user  
+• Main code actions or behaviors from the AI  
+• Important variables, functions, modules, or outputs discussed  
+• Any unresolved questions or next steps
+
+Produce the summary in a structured format like:
+
+**Objective:** …
+
+**User instructions:** … (bulleted)
+
+**AI actions / code behavior:** … (bulleted)
+
+**Important entities:** … (e.g. function names, variables, files)
+
+**Open issues / next steps:** … (if any)
+
+**Summary (concise):** (one or two sentences)

codex-cli/bin/codex.js

@@ -83,6 +83,7 @@ if (wantsNative && process.platform !== 'win32') {
 
   const child = spawn(binaryPath, process.argv.slice(2), {
     stdio: "inherit",
+    env: { ...process.env, CODEX_MANAGED_BY_NPM: "1" },
   });
 
   child.on("error", (err) => {

codex-rs/Cargo.lock

@@ -695,6 +695,7 @@ dependencies = [
  "reqwest",
  "seccompiler",
  "serde",
+ "serde_bytes",
  "serde_json",
  "sha1",
  "shlex",
@@ -842,6 +843,7 @@ version = "0.0.0"
 dependencies = [
  "anyhow",
  "base64 0.22.1",
+ "chrono",
  "clap",
  "codex-ansi-escape",
  "codex-arg0",
@@ -860,6 +862,8 @@ dependencies = [
  "ratatui",
  "ratatui-image",
  "regex-lite",
+ "reqwest",
+ "serde",
  "serde_json",
  "shlex",
  "strum 0.27.2",
@@ -2643,6 +2647,7 @@ version = "0.0.0"
 dependencies = [
  "anyhow",
  "assert_cmd",
+ "codex-core",
  "codex-mcp-server",
  "mcp-types",
  "pretty_assertions",
@@ -2650,6 +2655,7 @@ dependencies = [
  "shlex",
  "tempfile",
  "tokio",
+ "uuid",
  "wiremock",
 ]
 
@@ -3949,6 +3955,15 @@ dependencies = [
  "serde_derive",
 ]
 
+[[package]]
+name = "serde_bytes"
+version = "0.11.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8437fd221bde2d4ca316d61b90e337e9e702b3820b87d63caa9ba6c02bd06d96"
+dependencies = [
+ "serde",
+]
+
 [[package]]
 name = "serde_derive"
 version = "1.0.219"

codex-rs/cli/src/concurrent/mod.rs

@@ -0,0 +1,584 @@
+use std::fs::File;
+use std::io::Write;
+use std::path::Path;
+use std::path::PathBuf;
+use std::process::Command;
+use std::process::Stdio;
+use std::sync::OnceLock;
+
+use tokio::process::Command as TokioCommand;
+use tokio::sync::Semaphore;
+
+use anyhow::Context;
+use codex_common::CliConfigOverrides;
+use codex_exec::Cli as ExecCli;
+
+// Serialize git worktree add operations across tasks to avoid repository lock contention.
+static GIT_WORKTREE_ADD_SEMAPHORE: OnceLock<Semaphore> = OnceLock::new();
+
+#[derive(Debug, Clone)]
+pub struct ConcurrentRunResult {
+    pub branch: String,
+    pub worktree_dir: PathBuf,
+    pub log_file: Option<PathBuf>,
+    pub exec_exit_code: Option<i32>,
+    pub _had_changes: bool,
+    pub _applied_changes: Option<usize>,
+}
+
+fn compute_codex_home() -> PathBuf {
+    if let Ok(val) = std::env::var("CODEX_HOME") {
+        if !val.is_empty() {
+            return PathBuf::from(val);
+        }
+    }
+    // Fallback to default (~/.codex) without requiring it to already exist.
+    codex_core::config::find_codex_home().unwrap_or_else(|_| {
+        let mut p = std::env::var_os("HOME")
+            .map(PathBuf::from)
+            .unwrap_or_default();
+        if p.as_os_str().is_empty() {
+            return PathBuf::from(".codex");
+        }
+        p.push(".codex");
+        p
+    })
+}
+
+fn slugify_prompt(prompt: &str, max_len: usize) -> String {
+    let mut out = String::with_capacity(prompt.len());
+    let mut prev_hyphen = false;
+    for ch in prompt.chars() {
+        let c = ch.to_ascii_lowercase();
+        let keep = matches!(c, 'a'..='z' | '0'..='9');
+        if keep {
+            out.push(c);
+            prev_hyphen = false;
+        } else if c.is_ascii_whitespace() || matches!(c, '-' | '_' | '+') {
+            if !prev_hyphen && !out.is_empty() {
+                out.push('-');
+                prev_hyphen = true;
+            }
+        } else {
+            // skip other punctuation/symbols
+        }
+        if out.len() >= max_len {
+            break;
+        }
+    }
+    // Trim trailing hyphens
+    while out.ends_with('-') {
+        out.pop();
+    }
+    if out.is_empty() {
+        "task".to_string()
+    } else {
+        out
+    }
+}
+
+fn git_output(repo_dir: &Path, args: &[&str]) -> anyhow::Result<String> {
+    let out = Command::new("git")
+        .args(args)
+        .current_dir(repo_dir)
+        .output()
+        .with_context(|| format!("running git {args:?}"))?;
+    if !out.status.success() {
+        anyhow::bail!(
+            "git {:?} failed with status {}: {}",
+            args,
+            out.status,
+            String::from_utf8_lossy(&out.stderr)
+        );
+    }
+    Ok(String::from_utf8_lossy(&out.stdout).trim().to_string())
+}
+
+fn git_capture_stdout(repo_dir: &Path, args: &[&str]) -> anyhow::Result<Vec<u8>> {
+    let out = Command::new("git")
+        .args(args)
+        .current_dir(repo_dir)
+        .output()
+        .with_context(|| format!("running git {args:?}"))?;
+    if !out.status.success() {
+        anyhow::bail!(
+            "git {:?} failed with status {}: {}",
+            args,
+            out.status,
+            String::from_utf8_lossy(&out.stderr)
+        );
+    }
+    Ok(out.stdout)
+}
+
+fn count_files_in_patch(diff: &[u8]) -> usize {
+    // Count occurrences of lines starting with "diff --git ", which mark file boundaries.
+    // This works for text and binary patches produced by `git diff --binary`.
+    let mut count = 0usize;
+    for line in diff.split(|&b| b == b'\n') {
+        if line.starts_with(b"diff --git ") {
+            count += 1;
+        }
+    }
+    count
+}
+
+pub async fn run_concurrent_flow(
+    prompt: String,
+    cli_config_overrides: CliConfigOverrides,
+    codex_linux_sandbox_exe: Option<PathBuf>,
+    automerge: bool,
+    quiet: bool,
+) -> anyhow::Result<ConcurrentRunResult> {
+    let cwd = std::env::current_dir()?;
+
+    // Ensure we are in a git repo and find repo root.
+    let repo_root_str = git_output(&cwd, &["rev-parse", "--show-toplevel"]);
+    let repo_root = match repo_root_str {
+        Ok(p) => PathBuf::from(p),
+        Err(err) => {
+            eprintln!("Not inside a Git repo: {err}");
+            std::process::exit(1);
+        }
+    };
+
+    // Determine current branch and original head commit.
+    let current_branch = git_output(&repo_root, &["rev-parse", "--abbrev-ref", "HEAD"])
+        .unwrap_or_else(|_| "HEAD".to_string());
+    let original_head =
+        git_output(&repo_root, &["rev-parse", "HEAD"]).context("finding original HEAD commit")?;
+
+    // Build worktree target path under $CODEX_HOME/worktrees/<repo>/<branch>
+    let mut codex_home = compute_codex_home();
+    codex_home.push("worktrees");
+    // repo name = last component of repo_root
+    let repo_name = repo_root
+        .file_name()
+        .map(|s| s.to_string_lossy().to_string())
+        .unwrap_or_else(|| "repo".to_string());
+    codex_home.push(repo_name.clone());
+
+    // Prepare branch name: codex/<slug>, retrying with a numeric suffix to avoid races.
+    let slug = slugify_prompt(&prompt, 64);
+    let mut branch: String;
+    let worktree_dir: PathBuf;
+    let mut attempt: u32 = 1;
+    loop {
+        branch = if attempt == 1 {
+            format!("codex/{slug}")
+        } else {
+            format!("codex/{slug}-{attempt}")
+        };
+
+        let mut candidate_dir = codex_home.clone();
+        candidate_dir.push(&branch);
+
+        // Create parent directories for candidate path.
+        if let Some(parent) = candidate_dir.parent() {
+            std::fs::create_dir_all(parent)?;
+        }
+
+        if !quiet {
+            println!(
+                "Creating worktree at {} with branch {}",
+                candidate_dir.display(),
+                branch
+            );
+        }
+
+        // Try to add worktree with new branch from current HEAD
+        let worktree_path_str = candidate_dir.to_string_lossy().to_string();
+        let add_status = Command::new("git")
+            .arg("worktree")
+            .arg("add")
+            .arg("-b")
+            .arg(&branch)
+            .arg(&worktree_path_str)
+            .current_dir(&repo_root)
+            .status()?;
+        if add_status.success() {
+            worktree_dir = candidate_dir;
+            break;
+        }
+
+        attempt += 1;
+        if attempt > 50 {
+            anyhow::bail!("Failed to create git worktree after multiple attempts");
+        }
+        // Retry with a new branch name.
+    }
+
+    // Either run codex exec inline (verbose) or as a subprocess with logs redirected.
+    let mut log_file: Option<PathBuf> = None;
+    let mut exec_exit_code: Option<i32> = None;
+    if quiet {
+        let exe = std::env::current_exe()
+            .map_err(|e| anyhow::anyhow!("failed to locate current executable: {e}"))?;
+
+        // Prepare logs directory: $CODEX_HOME/logs/<repo_name>
+        let mut logs_dir = compute_codex_home();
+        logs_dir.push("logs");
+        logs_dir.push(&repo_name);
+        std::fs::create_dir_all(&logs_dir)?;
+
+        let sanitized_branch = branch.replace('/', "_");
+        let log_path = logs_dir.join(format!("{sanitized_branch}.log"));
+        let log_f = File::create(&log_path)?;
+        log_file = Some(log_path.clone());
+
+        let mut cmd = Command::new(exe);
+        cmd.arg("exec")
+            .arg("--full-auto")
+            .arg("--cd")
+            .arg(worktree_dir.as_os_str())
+            .stdout(Stdio::from(log_f.try_clone()?))
+            .stderr(Stdio::from(log_f));
+
+        // Forward any root-level config overrides.
+        for ov in cli_config_overrides.raw_overrides.iter() {
+            cmd.arg("-c").arg(ov);
+        }
+
+        // Append the prompt last (positional argument).
+        cmd.arg(&prompt);
+
+        let status = cmd.status()?;
+        exec_exit_code = status.code();
+        if !status.success() && !quiet {
+            eprintln!("codex exec failed with exit code {exec_exit_code:?}");
+        }
+    } else {
+        // Build an ExecCli to run in full-auto mode at the worktree directory.
+        let mut exec_cli = ExecCli {
+            images: vec![],
+            model: None,
+            sandbox_mode: None,
+            config_profile: None,
+            full_auto: true,
+            dangerously_bypass_approvals_and_sandbox: false,
+            cwd: Some(worktree_dir.clone()),
+            skip_git_repo_check: false,
+            config_overrides: CliConfigOverrides::default(),
+            color: Default::default(),
+            json: false,
+            last_message_file: None,
+            prompt: Some(prompt.clone()),
+        };
+
+        // Prepend any root-level config overrides.
+        super::prepend_config_flags(&mut exec_cli.config_overrides, cli_config_overrides);
+
+        // Run codex exec
+        if let Err(e) = codex_exec::run_main(exec_cli, codex_linux_sandbox_exe).await {
+            eprintln!("codex exec failed: {e}");
+            // Do not attempt to bring changes on failure; leave worktree for inspection.
+            return Err(e);
+        }
+    }
+
+    // Auto-commit changes in the worktree if any
+    let status_out = Command::new("git")
+        .args(["status", "--porcelain"])
+        .current_dir(&worktree_dir)
+        .output()?;
+    let status_text = String::from_utf8_lossy(&status_out.stdout);
+    let had_changes = !status_text.trim().is_empty();
+    if had_changes {
+        // Stage and commit
+        if !Command::new("git")
+            .args(["add", "-A"])
+            .current_dir(&worktree_dir)
+            .status()?
+            .success()
+        {
+            anyhow::bail!("git add failed in worktree");
+        }
+        let commit_message = format!("Codex concurrent: {prompt}");
+        if !Command::new("git")
+            .args(["commit", "-m", &commit_message])
+            .current_dir(&worktree_dir)
+            .status()?
+            .success()
+        {
+            if !quiet {
+                eprintln!("No commit created (maybe no changes)");
+            }
+        } else if !quiet {
+            println!("Committed changes in worktree branch {branch}");
+        }
+    } else if !quiet {
+        println!("No changes detected in worktree; skipping commit.");
+    }
+
+    if !automerge {
+        if !quiet {
+            println!(
+                "Auto-merge disabled; leaving changes in worktree {} on branch {}.",
+                worktree_dir.display(),
+                branch
+            );
+            println!(
+                "You can review and manually merge from that branch into {current_branch} when ready."
+            );
+            println!("Summary: Auto-merge disabled.");
+        }
+        return Ok(ConcurrentRunResult {
+            branch,
+            worktree_dir,
+            log_file,
+            exec_exit_code,
+            _had_changes: had_changes,
+            _applied_changes: None,
+        });
+    }
+
+    // Bring the changes into the main working tree as UNSTAGED modifications.
+    // We generate a patch from the original HEAD to the worktree branch tip, then apply with 3-way merge.
+    if !quiet {
+        println!("Applying changes from {branch} onto {current_branch} as unstaged modifications");
+    }
+    let range = format!("{original_head}..{branch}");
+    let mut diff_bytes =
+        git_capture_stdout(&repo_root, &["diff", "--binary", "--full-index", &range])?;
+
+    // Fallback: if there is nothing in the commit range (e.g., commit didn't happen),
+    // try to capture uncommitted changes from the worktree working tree.
+    if diff_bytes.is_empty() && had_changes {
+        // If we saw changes earlier but no commit diff was produced, fall back to working tree diff.
+        // This captures unstaged changes relative to HEAD in the worktree.
+        diff_bytes =
+            git_capture_stdout(&worktree_dir, &["diff", "--binary", "--full-index", "HEAD"])?;
+    }
+
+    if diff_bytes.is_empty() {
+        if !quiet {
+            println!("Summary: 0 changes detected.");
+        }
+        return Ok(ConcurrentRunResult {
+            branch,
+            worktree_dir,
+            log_file,
+            exec_exit_code,
+            _had_changes: had_changes,
+            _applied_changes: Some(0),
+        });
+    }
+
+    let changed_files = count_files_in_patch(&diff_bytes);
+
+    let mut child = Command::new("git")
+        .arg("apply")
+        .arg("-3")
+        .stdin(Stdio::piped())
+        .stdout(Stdio::inherit())
+        .stderr(Stdio::inherit())
+        .current_dir(&repo_root)
+        .spawn()
+        .context("spawning git apply")?;
+    if let Some(stdin) = child.stdin.as_mut() {
+        stdin
+            .write_all(&diff_bytes)
+            .context("writing patch to git apply stdin")?;
+    }
+    let status = child.wait().context("waiting for git apply")?;
+    if !status.success() {
+        if !quiet {
+            eprintln!(
+                "Applying changes failed. You can manually inspect {} and apply diffs.",
+                worktree_dir.display()
+            );
+            println!("Summary: Apply failed.");
+        }
+    } else {
+        if !quiet {
+            println!("Changes applied to working tree (unstaged).");
+            println!("Summary: Applied {changed_files} files changed.");
+        }
+
+        // Cleanup: remove the worktree and delete the temporary branch.
+        if !quiet {
+            println!(
+                "Cleaning up worktree {} and branch {}",
+                worktree_dir.display(),
+                branch
+            );
+        }
+        let worktree_path_str = worktree_dir.to_string_lossy().to_string();
+        let remove_status = Command::new("git")
+            .args(["worktree", "remove", &worktree_path_str])
+            .current_dir(&repo_root)
+            .status();
+        match remove_status {
+            Ok(s) if s.success() => {
+                // removed
+            }
+            _ => {
+                if !quiet {
+                    eprintln!("git worktree remove failed; retrying with --force");
+                }
+                let _ = Command::new("git")
+                    .args(["worktree", "remove", "--force", &worktree_path_str])
+                    .current_dir(&repo_root)
+                    .status();
+            }
+        }
+
+        let del_status = Command::new("git")
+            .args(["branch", "-D", &branch])
+            .current_dir(&repo_root)
+            .status();
+        if let Ok(s) = del_status {
+            if !s.success() && !quiet {
+                eprintln!("Failed to delete branch {branch}");
+            }
+        } else if !quiet {
+            eprintln!("Error running git branch -D {branch}");
+        }
+    }
+
+    Ok(ConcurrentRunResult {
+        branch,
+        worktree_dir,
+        log_file,
+        exec_exit_code,
+        _had_changes: had_changes,
+        _applied_changes: Some(changed_files),
+    })
+}
+
+/// A Send-friendly variant used for best-of-n: run quietly (logs redirected) and do not auto-merge.
+/// This intentionally avoids referencing non-Send types from codex-exec.
+pub async fn run_concurrent_flow_quiet_no_automerge(
+    prompt: String,
+    cli_config_overrides: CliConfigOverrides,
+    _codex_linux_sandbox_exe: Option<PathBuf>,
+) -> anyhow::Result<ConcurrentRunResult> {
+    let cwd = std::env::current_dir()?;
+
+    let repo_root_str = git_output(&cwd, &["rev-parse", "--show-toplevel"]);
+    let repo_root = match repo_root_str {
+        Ok(p) => PathBuf::from(p),
+        Err(err) => {
+            eprintln!("Not inside a Git repo: {err}");
+            std::process::exit(1);
+        }
+    };
+
+    // Capture basic repo info (not used further in quiet/no-automerge flow).
+
+    let mut codex_home = compute_codex_home();
+    codex_home.push("worktrees");
+    let repo_name = repo_root
+        .file_name()
+        .map(|s| s.to_string_lossy().to_string())
+        .unwrap_or_else(|| "repo".to_string());
+    codex_home.push(repo_name.clone());
+
+    let slug = slugify_prompt(&prompt, 64);
+    let mut branch: String;
+    let worktree_dir: PathBuf;
+    // Serialize worktree creation to avoid git repo lock contention across tasks.
+    {
+        let semaphore = GIT_WORKTREE_ADD_SEMAPHORE.get_or_init(|| Semaphore::new(1));
+        let _permit = semaphore.acquire().await.expect("semaphore closed");
+
+        let mut attempt: u32 = 1;
+        loop {
+            branch = if attempt == 1 {
+                format!("codex/{slug}")
+            } else {
+                format!("codex/{slug}-{attempt}")
+            };
+
+            let mut candidate_dir = codex_home.clone();
+            candidate_dir.push(&branch);
+
+            if let Some(parent) = candidate_dir.parent() {
+                std::fs::create_dir_all(parent)?;
+            }
+
+            let worktree_path_str = candidate_dir.to_string_lossy().to_string();
+            let add_status = TokioCommand::new("git")
+                .arg("worktree")
+                .arg("add")
+                .arg("-b")
+                .arg(&branch)
+                .arg(&worktree_path_str)
+                .current_dir(&repo_root)
+                .status()
+                .await?;
+            if add_status.success() {
+                worktree_dir = candidate_dir;
+                break;
+            }
+            attempt += 1;
+            if attempt > 50 {
+                anyhow::bail!("Failed to create git worktree after multiple attempts");
+            }
+        }
+    }
+
+    // Run the CLI in quiet mode (logs redirected).
+    let exe = std::env::current_exe()
+        .map_err(|e| anyhow::anyhow!("failed to locate current executable: {e}"))?;
+
+    let mut logs_dir = compute_codex_home();
+    logs_dir.push("logs");
+    logs_dir.push(&repo_name);
+    std::fs::create_dir_all(&logs_dir)?;
+
+    let sanitized_branch = branch.replace('/', "_");
+    let log_path = logs_dir.join(format!("{sanitized_branch}.log"));
+    let log_f = File::create(&log_path)?;
+    let log_file = Some(log_path.clone());
+
+    let mut cmd = TokioCommand::new(exe);
+    cmd.arg("exec")
+        .arg("--full-auto")
+        .arg("--cd")
+        .arg(worktree_dir.as_os_str())
+        .stdout(Stdio::from(log_f.try_clone()?))
+        .stderr(Stdio::from(log_f));
+    for ov in cli_config_overrides.raw_overrides.iter() {
+        cmd.arg("-c").arg(ov);
+    }
+    cmd.arg(&prompt);
+
+    let status = cmd.status().await?;
+    let exec_exit_code = status.code();
+
+    // Auto-commit changes in the worktree if any
+    let status_out = TokioCommand::new("git")
+        .args(["status", "--porcelain"])
+        .current_dir(&worktree_dir)
+        .output()
+        .await?;
+    let status_text = String::from_utf8_lossy(&status_out.stdout);
+    let had_changes = !status_text.trim().is_empty();
+    if had_changes {
+        if !TokioCommand::new("git")
+            .args(["add", "-A"])
+            .current_dir(&worktree_dir)
+            .status()
+            .await?
+            .success()
+        {
+            anyhow::bail!("git add failed in worktree");
+        }
+        let commit_message = format!("Codex concurrent: {prompt}");
+        let _ = TokioCommand::new("git")
+            .args(["commit", "-m", &commit_message])
+            .current_dir(&worktree_dir)
+            .status()
+            .await?;
+    }
+
+    Ok(ConcurrentRunResult {
+        branch,
+        worktree_dir,
+        log_file,
+        exec_exit_code,
+        _had_changes: had_changes,
+        _applied_changes: None,
+    })
+}

codex-rs/cli/src/main.rs

@@ -17,6 +17,7 @@ use codex_tui::Cli as TuiCli;
 use std::path::PathBuf;
 
 use crate::proto::ProtoCli;
+mod concurrent;
 
 /// Codex CLI
 ///
@@ -32,6 +33,22 @@ struct MultitoolCli {
     #[clap(flatten)]
     pub config_overrides: CliConfigOverrides,
 
+    /// Experimental:Launch a concurrent task in a separate Git worktree using the given prompt.
+    /// Creates worktree under $CODEX_HOME/worktrees/<repo>/codex/<slug> and runs `codex exec` in full-auto mode.
+    #[arg(long = "concurrent", value_name = "PROMPT")]
+    pub concurrent: Option<String>,
+
+    /// When using --concurrent, also attempt to auto-merge the resulting changes
+    /// back into the current working tree as unstaged modifications via
+    /// a 3-way git apply. Disable with --automerge=false.
+    #[arg(long = "automerge", default_value_t = true, action = clap::ArgAction::Set)]
+    pub automerge: bool,
+
+    /// Run the same --concurrent prompt N times in separate worktrees and keep them all.
+    /// Intended to generate multiple candidate solutions without auto-merging.
+    #[arg(long = "best-of-n", value_name = "N", default_value_t = 1)]
+    pub best_of_n: usize,
+
     #[clap(flatten)]
     interactive: TuiCli,
 
@@ -116,6 +133,87 @@ fn main() -> anyhow::Result<()> {
 async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()> {
     let cli = MultitoolCli::parse();
 
+    // Handle --concurrent at the root level.
+    if let Some(prompt) = cli.concurrent.clone() {
+        if cli.subcommand.is_some() {
+            eprintln!("--concurrent cannot be used together with a subcommand");
+            std::process::exit(2);
+        }
+        let runs = if cli.best_of_n == 0 { 1 } else { cli.best_of_n };
+        if runs > 1 {
+            println!(
+                "Running best-of-n with {runs} runs; auto-merge will be disabled and worktrees kept."
+            );
+
+            // Launch all runs concurrently and collect results as they finish.
+            let mut join_set = tokio::task::JoinSet::new();
+            for _ in 0..runs {
+                let prompt = prompt.clone();
+                let overrides = cli.config_overrides.clone();
+                let sandbox = codex_linux_sandbox_exe.clone();
+                join_set.spawn(async move {
+                    concurrent::run_concurrent_flow_quiet_no_automerge(prompt, overrides, sandbox)
+                        .await
+                });
+            }
+
+            let mut results: Vec<concurrent::ConcurrentRunResult> = Vec::with_capacity(runs);
+            while let Some(join_result) = join_set.join_next().await {
+                match join_result {
+                    Ok(Ok(res)) => {
+                        println!(
+                            "task finished for branch: {}\n, directory: {}",
+                            res.branch,
+                            res.worktree_dir.display()
+                        );
+                        results.push(res);
+                    }
+                    Ok(Err(err)) => {
+                        eprintln!("concurrent task failed: {err}");
+                    }
+                    Err(join_err) => {
+                        eprintln!("failed to join concurrent task: {join_err}");
+                    }
+                }
+            }
+
+            println!("\nBest-of-n summary:");
+            for r in &results {
+                let status = match r.exec_exit_code {
+                    Some(0) => "OK",
+                    Some(_code) => "FAIL",
+                    None => "OK",
+                };
+                let log = r
+                    .log_file
+                    .as_ref()
+                    .map(|p| p.to_string_lossy().to_string())
+                    .unwrap_or_else(|| "<no log>".to_string());
+                println!(
+                    "[{status}] branch={} worktree={} log={}",
+                    r.branch,
+                    r.worktree_dir.display(),
+                    log
+                );
+            }
+        } else {
+            concurrent::run_concurrent_flow(
+                prompt,
+                cli.config_overrides,
+                codex_linux_sandbox_exe,
+                cli.automerge,
+                false,
+            )
+            .await?;
+        }
+        return Ok(());
+    }
+
+    if cli.best_of_n > 1 {
+        eprintln!("--best-of-n requires --concurrent <PROMPT>");
+        std::process::exit(2);
+    }
+
     match cli.subcommand {
         None => {
             let mut tui_cli = cli.interactive;

codex-rs/common/src/sandbox_summary.rs

@@ -7,6 +7,7 @@ pub fn summarize_sandbox_policy(sandbox_policy: &SandboxPolicy) -> String {
         SandboxPolicy::WorkspaceWrite {
             writable_roots,
             network_access,
+            include_default_writable_roots,
         } => {
             let mut summary = "workspace-write".to_string();
             if !writable_roots.is_empty() {
@@ -19,6 +20,9 @@ pub fn summarize_sandbox_policy(sandbox_policy: &SandboxPolicy) -> String {
                         .join(", ")
                 ));
             }
+            if !*include_default_writable_roots {
+                summary.push_str(" (exact writable roots)");
+            }
             if *network_access {
                 summary.push_str(" (network access enabled)");
             }

codex-rs/config.md

@@ -259,6 +259,8 @@ disk, but attempts to write a file or access the network will be blocked.
 
 A more relaxed policy is `workspace-write`. When specified, the current working directory for the Codex task will be writable (as well as `$TMPDIR` on macOS). Note that the CLI defaults to using the directory where it was spawned as `cwd`, though this can be overridden using `--cwd/-C`.
 
+On macOS (and soon Linux), all writable roots (including `cwd`) that contain a `.git/` folder _as an immediate child_ will configure the `.git/` folder to be read-only while the rest of the Git repository will be writable. This means that commands like `git commit` will fail, by default (as it entails writing to `.git/`), and will require Codex to ask for permission.
+
 ```toml
 # same as `--sandbox workspace-write`
 sandbox_mode = "workspace-write"

codex-rs/core/Cargo.toml

@@ -31,6 +31,7 @@ rand = "0.9"
 reqwest = { version = "0.12", features = ["json", "stream"] }
 serde = { version = "1", features = ["derive"] }
 serde_json = "1"
+serde_bytes = "0.11"
 sha1 = "0.10.6"
 shlex = "1.3.0"
 strum_macros = "0.27.2"

codex-rs/core/src/client.rs

@@ -207,7 +207,14 @@ impl ModelClient {
                 }
             }
 
-            let req_builder = self.provider.apply_http_headers(req_builder);
+            req_builder = self.provider.apply_http_headers(req_builder);
+
+            let originator = self
+                .config
+                .internal_originator
+                .as_deref()
+                .unwrap_or("codex_cli_rs");
+            req_builder = req_builder.header("originator", originator);
 
             let res = req_builder.send().await;
             if let Ok(resp) = &res {

codex-rs/core/src/codex.rs

@@ -4,7 +4,6 @@
 use std::borrow::Cow;
 use std::collections::HashMap;
 use std::collections::HashSet;
-use std::path::Path;
 use std::path::PathBuf;
 use std::sync::Arc;
 use std::sync::Mutex;
@@ -49,6 +48,7 @@ use crate::error::SandboxErr;
 use crate::exec::ExecParams;
 use crate::exec::ExecToolCallOutput;
 use crate::exec::SandboxType;
+use crate::exec::StdoutStream;
 use crate::exec::process_exec_tool_call;
 use crate::exec_env::create_env;
 use crate::mcp_connection_manager::McpConnectionManager;
@@ -92,7 +92,6 @@ use crate::safety::assess_safety_for_untrusted_command;
 use crate::shell;
 use crate::user_notification::UserNotification;
 use crate::util::backoff;
-use tokio::fs;
 
 /// The high-level interface to the Codex system.
 /// It operates as a queue pair where you send submissions and receive events.
@@ -444,6 +443,12 @@ impl Session {
         let _ = self.tx_event.send(event).await;
     }
 
+    /// Build the full turn input by concatenating the current conversation
+    /// history with additional items for this turn.
+    pub fn turn_input_with_history(&self, extra: Vec<ResponseItem>) -> Vec<ResponseItem> {
+        [self.state.lock().unwrap().history.contents(), extra].concat()
+    }
+
     /// Returns the input if there was no task running to inject into
     pub fn inject_input(&self, input: Vec<InputItem>) -> Result<(), Vec<InputItem>> {
         let mut state = self.state.lock().unwrap();
@@ -566,6 +571,25 @@ impl AgentTask {
             handle,
         }
     }
+    fn compact(
+        sess: Arc<Session>,
+        sub_id: String,
+        input: Vec<InputItem>,
+        compact_instructions: String,
+    ) -> Self {
+        let handle = tokio::spawn(run_compact_task(
+            Arc::clone(&sess),
+            sub_id.clone(),
+            input,
+            compact_instructions,
+        ))
+        .abort_handle();
+        Self {
+            sess,
+            sub_id,
+            handle,
+        }
+    }
 
     fn abort(self) {
         if !self.handle.is_finished() {
@@ -886,6 +910,31 @@ async fn submission_loop(
                     }
                 });
             }
+            Op::Compact => {
+                let sess = match sess.as_ref() {
+                    Some(sess) => sess,
+                    None => {
+                        send_no_session_event(sub.id).await;
+                        continue;
+                    }
+                };
+
+                // Create a summarization request as user input
+                const SUMMARIZATION_PROMPT: &str = include_str!("../../../SUMMARY.md");
+
+                // Attempt to inject input into current task
+                if let Err(items) = sess.inject_input(vec![InputItem::Text {
+                    text: "Start Summarization".to_string(),
+                }]) {
+                    let task = AgentTask::compact(
+                        sess.clone(),
+                        sub.id,
+                        items,
+                        SUMMARIZATION_PROMPT.to_string(),
+                    );
+                    sess.set_task(task);
+                }
+            }
             Op::Shutdown => {
                 info!("Shutting down Codex instance");
 
@@ -947,21 +996,7 @@ async fn run_task(sess: Arc<Session>, sub_id: String, input: Vec<InputItem>) {
         return;
     }
 
-    let mut effective_input = input;
-    let is_first_turn = {
-        let st = sess.state.lock().unwrap();
-        st.history.contents().is_empty()
-    };
-    if is_first_turn {
-        if let Some(env_text) = get_initial_env_context(&sess.cwd).await {
-            let mut prefixed = Vec::with_capacity(effective_input.len() + 1);
-            prefixed.push(InputItem::Text { text: env_text });
-            prefixed.extend(effective_input.into_iter());
-            effective_input = prefixed;
-        }
-    }
-
-    let initial_input_for_turn = ResponseInputItem::from(effective_input);
+    let initial_input_for_turn: ResponseInputItem = ResponseInputItem::from(input);
     sess.record_conversation_items(&[initial_input_for_turn.clone().into()])
         .await;
 
@@ -982,8 +1017,7 @@ async fn run_task(sess: Arc<Session>, sub_id: String, input: Vec<InputItem>) {
         // conversation history on each turn. The rollout file, however, should
         // only record the new items that originated in this turn so that it
         // represents an append-only log without duplicates.
-        let turn_input: Vec<ResponseItem> =
-            [sess.state.lock().unwrap().history.contents(), pending_input].concat();
+        let turn_input: Vec<ResponseItem> = sess.turn_input_with_history(pending_input);
 
         let turn_input_messages: Vec<String> = turn_input
             .iter()
@@ -1122,128 +1156,6 @@ async fn run_task(sess: Arc<Session>, sub_id: String, input: Vec<InputItem>) {
     sess.tx_event.send(event).await.ok();
 }
 
-async fn get_initial_env_context(cwd: &Path) -> Option<String> {
-    const MAX_LINES: usize = 50;
-
-    let mut dir = match fs::read_dir(cwd).await {
-        Ok(d) => d,
-        Err(_) => return None,
-    };
-
-    let mut lines = Vec::with_capacity(MAX_LINES);
-    let mut seen = 0usize;
-    let mut truncated = false;
-    loop {
-        match dir.next_entry().await {
-            Ok(Some(entry)) => {
-                let name = entry.file_name();
-                let name = name.to_string_lossy();
-                if name.starts_with('.') {
-                    continue;
-                }
-                seen += 1;
-                if lines.len() < MAX_LINES {
-                    lines.push(name.to_string());
-                } else {
-                    truncated = true;
-                    break;
-                }
-            }
-            Ok(None) => break,
-            Err(_) => return None,
-        }
-    }
-
-    if lines.is_empty() {
-        return None;
-    }
-
-    let mut out = String::new();
-    out.push_str("Environment snapshot (output of `ls | head -n 50` in cwd):\n");
-    out.push_str(&format!("{}\n\n", cwd.display()));
-    for line in &lines {
-        out.push_str(line);
-        out.push('\n');
-    }
-    if truncated || seen > lines.len() {
-        out.push_str("… (truncated)\n");
-    }
-    Some(out)
-}
-
-#[cfg(test)]
-mod tests {
-    #![allow(clippy::expect_used, clippy::unwrap_used)]
-    use super::get_initial_env_context;
-    use std::fs;
-    use tempfile::TempDir;
-
-    #[tokio::test]
-    async fn env_context_truncates_after_50_visible_entries() {
-        let tmp = TempDir::new().unwrap();
-
-        // Create 65 non-hidden files and a few hidden ones. Dotfiles should be skipped.
-        for i in 0..65u32 {
-            fs::write(tmp.path().join(format!("file_{i:03}.txt")), b"x").unwrap();
-        }
-        fs::write(tmp.path().join(".hidden_a"), b"x").unwrap();
-        fs::write(tmp.path().join(".hidden_b"), b"x").unwrap();
-
-        let ctx = get_initial_env_context(tmp.path())
-            .await
-            .expect("should produce context");
-
-        // Header and cwd should be present.
-        assert!(ctx.starts_with("Environment snapshot (output of `ls | head -n 50` in cwd):\n"));
-        assert!(ctx.contains(&format!("{}\n\n", tmp.path().display())));
-
-        // Count listed entries (exclude header/cwd/blank and possible truncation marker)
-        let mut count = 0usize;
-        let mut saw_truncated = false;
-        for line in ctx.lines().skip(2) {
-            if line.is_empty() {
-                continue;
-            }
-            if line == "… (truncated)" {
-                saw_truncated = true;
-                break;
-            }
-            count += 1;
-        }
-        assert_eq!(count, 50, "should list exactly 50 visible entries");
-        assert!(
-            saw_truncated,
-            "should indicate truncation when more than 50 entries exist"
-        );
-    }
-
-    #[tokio::test]
-    async fn env_context_no_truncation_when_fewer_than_50() {
-        let tmp = TempDir::new().unwrap();
-        // 3 visible + 1 hidden
-        for name in ["a.txt", "b.txt", "c.txt", ".secret"] {
-            fs::write(tmp.path().join(name), b"x").unwrap();
-        }
-
-        let ctx = get_initial_env_context(tmp.path())
-            .await
-            .expect("should produce context");
-
-        let mut lines = ctx.lines().skip(2).filter(|l| !l.is_empty());
-        let mut names = Vec::new();
-        for l in &mut lines {
-            if l == "… (truncated)" {
-                panic!("should not be truncated");
-            }
-            names.push(l.to_string());
-        }
-
-        // Hidden should be excluded; only 3 visible entries.
-        assert_eq!(names.len(), 3);
-        assert!(names.iter().all(|n| n != ".secret"));
-    }
-}
-
 async fn run_turn(
     sess: &Session,
     sub_id: String,
@@ -1431,6 +1343,88 @@ async fn try_run_turn(
     }
 }
 
+async fn run_compact_task(
+    sess: Arc<Session>,
+    sub_id: String,
+    input: Vec<InputItem>,
+    compact_instructions: String,
+) {
+    let start_event = Event {
+        id: sub_id.clone(),
+        msg: EventMsg::TaskStarted,
+    };
+    if sess.tx_event.send(start_event).await.is_err() {
+        return;
+    }
+
+    let initial_input_for_turn: ResponseInputItem = ResponseInputItem::from(input);
+    let turn_input: Vec<ResponseItem> =
+        sess.turn_input_with_history(vec![initial_input_for_turn.clone().into()]);
+
+    let prompt = Prompt {
+        input: turn_input,
+        user_instructions: None,
+        store: !sess.disable_response_storage,
+        extra_tools: HashMap::new(),
+        base_instructions_override: Some(compact_instructions.clone()),
+    };
+
+    let max_retries = sess.client.get_provider().stream_max_retries();
+    let mut retries = 0;
+
+    loop {
+        let attempt_result = drain_to_completed(&sess, &sub_id, &prompt).await;
+
+        match attempt_result {
+            Ok(()) => break,
+            Err(CodexErr::Interrupted) => return,
+            Err(e) => {
+                if retries < max_retries {
+                    retries += 1;
+                    let delay = backoff(retries);
+                    sess.notify_background_event(
+                        &sub_id,
+                        format!(
+                            "stream error: {e}; retrying {retries}/{max_retries} in {delay:?}…"
+                        ),
+                    )
+                    .await;
+                    tokio::time::sleep(delay).await;
+                    continue;
+                } else {
+                    let event = Event {
+                        id: sub_id.clone(),
+                        msg: EventMsg::Error(ErrorEvent {
+                            message: e.to_string(),
+                        }),
+                    };
+                    sess.send_event(event).await;
+                    return;
+                }
+            }
+        }
+    }
+
+    sess.remove_task(&sub_id);
+    let event = Event {
+        id: sub_id.clone(),
+        msg: EventMsg::AgentMessage(AgentMessageEvent {
+            message: "Compact task completed".to_string(),
+        }),
+    };
+    sess.send_event(event).await;
+    let event = Event {
+        id: sub_id.clone(),
+        msg: EventMsg::TaskComplete(TaskCompleteEvent {
+            last_agent_message: None,
+        }),
+    };
+    sess.send_event(event).await;
+
+    let mut state = sess.state.lock().unwrap();
+    state.history.keep_last_messages(1);
+}
+
 async fn handle_response_item(
     sess: &Session,
     sub_id: &str,
@@ -1766,6 +1760,11 @@ async fn handle_container_exec_with_params(
         sess.ctrl_c.clone(),
         &sess.sandbox_policy,
         &sess.codex_linux_sandbox_exe,
+        Some(StdoutStream {
+            sub_id: sub_id.clone(),
+            call_id: call_id.clone(),
+            tx_event: sess.tx_event.clone(),
+        }),
     )
     .await;
 
@@ -1886,6 +1885,11 @@ async fn handle_sandbox_error(
                 sess.ctrl_c.clone(),
                 &sess.sandbox_policy,
                 &sess.codex_linux_sandbox_exe,
+                Some(StdoutStream {
+                    sub_id: sub_id.clone(),
+                    call_id: call_id.clone(),
+                    tx_event: sess.tx_event.clone(),
+                }),
             )
             .await;
 
@@ -1996,3 +2000,45 @@ fn get_last_assistant_message_from_turn(responses: &[ResponseItem]) -> Option<St
         }
     })
 }
+
+async fn drain_to_completed(sess: &Session, sub_id: &str, prompt: &Prompt) -> CodexResult<()> {
+    let mut stream = sess.client.clone().stream(prompt).await?;
+    loop {
+        let maybe_event = stream.next().await;
+        let Some(event) = maybe_event else {
+            return Err(CodexErr::Stream(
+                "stream closed before response.completed".into(),
+            ));
+        };
+        match event {
+            Ok(ResponseEvent::OutputItemDone(item)) => {
+                // Record only to in-memory conversation history; avoid state snapshot.
+                let mut state = sess.state.lock().unwrap();
+                state.history.record_items(std::slice::from_ref(&item));
+            }
+            Ok(ResponseEvent::Completed {
+                response_id: _,
+                token_usage,
+            }) => {
+                let token_usage = match token_usage {
+                    Some(usage) => usage,
+                    None => {
+                        return Err(CodexErr::Stream(
+                            "token_usage was None in ResponseEvent::Completed".into(),
+                        ));
+                    }
+                };
+                sess.tx_event
+                    .send(Event {
+                        id: sub_id.to_string(),
+                        msg: EventMsg::TokenCount(token_usage),
+                    })
+                    .await
+                    .ok();
+                return Ok(());
+            }
+            Ok(_) => continue,
+            Err(e) => return Err(e),
+        }
+    }
+}

codex-rs/core/src/config.rs

@@ -146,6 +146,9 @@ pub struct Config {
 
     /// Include an experimental plan tool that the model can use to update its current plan and status of each step.
     pub include_plan_tool: bool,
+
+    /// The value for the `originator` header included with Responses API requests.
+    pub internal_originator: Option<String>,
 }
 
 impl Config {
@@ -336,6 +339,9 @@ pub struct ConfigToml {
 
     /// Experimental path to a file whose contents replace the built-in BASE_INSTRUCTIONS.
     pub experimental_instructions_file: Option<PathBuf>,
+
+    /// The value for the `originator` header included with Responses API requests.
+    pub internal_originator: Option<String>,
 }
 
 impl ConfigToml {
@@ -350,6 +356,7 @@ impl ConfigToml {
                 Some(s) => SandboxPolicy::WorkspaceWrite {
                     writable_roots: s.writable_roots.clone(),
                     network_access: s.network_access,
+                    include_default_writable_roots: true,
                 },
                 None => SandboxPolicy::new_workspace_write_policy(),
             },
@@ -529,6 +536,7 @@ impl Config {
 
             experimental_resume,
             include_plan_tool: include_plan_tool.unwrap_or(false),
+            internal_originator: cfg.internal_originator,
         };
         Ok(config)
     }
@@ -720,6 +728,7 @@ writable_roots = [
             SandboxPolicy::WorkspaceWrite {
                 writable_roots: vec![PathBuf::from("/tmp")],
                 network_access: false,
+                include_default_writable_roots: true,
             },
             sandbox_workspace_write_cfg.derive_sandbox_policy(sandbox_mode_override)
         );
@@ -887,6 +896,7 @@ disable_response_storage = true
                 experimental_resume: None,
                 base_instructions: None,
                 include_plan_tool: false,
+                internal_originator: None,
             },
             o3_profile_config
         );
@@ -936,6 +946,7 @@ disable_response_storage = true
             experimental_resume: None,
             base_instructions: None,
             include_plan_tool: false,
+            internal_originator: None,
         };
 
         assert_eq!(expected_gpt3_profile_config, gpt3_profile_config);
@@ -1000,6 +1011,7 @@ disable_response_storage = true
             experimental_resume: None,
             base_instructions: None,
             include_plan_tool: false,
+            internal_originator: None,
         };
 
         assert_eq!(expected_zdr_profile_config, zdr_profile_config);

codex-rs/core/src/conversation_history.rs

@@ -30,6 +30,34 @@ impl ConversationHistory {
             }
         }
     }
+
+    pub(crate) fn keep_last_messages(&mut self, n: usize) {
+        if n == 0 {
+            self.items.clear();
+            return;
+        }
+
+        // Collect the last N message items (assistant/user), newest to oldest.
+        let mut kept: Vec<ResponseItem> = Vec::with_capacity(n);
+        for item in self.items.iter().rev() {
+            if let ResponseItem::Message { role, content, .. } = item {
+                kept.push(ResponseItem::Message {
+                    // we need to remove the id or the model will complain that messages are sent without
+                    // their reasonings
+                    id: None,
+                    role: role.clone(),
+                    content: content.clone(),
+                });
+                if kept.len() == n {
+                    break;
+                }
+            }
+        }
+
+        // Preserve chronological order (oldest to newest) within the kept slice.
+        kept.reverse();
+        self.items = kept;
+    }
 }
 
 /// Anything that is not a system message or "reasoning" message is considered

codex-rs/core/src/exec.rs

@@ -10,6 +10,7 @@ use std::sync::Arc;
 use std::time::Duration;
 use std::time::Instant;
 
+use async_channel::Sender;
 use tokio::io::AsyncRead;
 use tokio::io::AsyncReadExt;
 use tokio::io::BufReader;
@@ -19,10 +20,15 @@ use tokio::sync::Notify;
 use crate::error::CodexErr;
 use crate::error::Result;
 use crate::error::SandboxErr;
+use crate::protocol::Event;
+use crate::protocol::EventMsg;
+use crate::protocol::ExecCommandOutputDeltaEvent;
+use crate::protocol::ExecOutputStream;
 use crate::protocol::SandboxPolicy;
 use crate::seatbelt::spawn_command_under_seatbelt;
 use crate::spawn::StdioPolicy;
 use crate::spawn::spawn_child_async;
+use serde_bytes::ByteBuf;
 
 // Maximum we send for each stream, which is either:
 // - 10KiB OR
@@ -56,18 +62,26 @@ pub enum SandboxType {
     LinuxSeccomp,
 }
 
+#[derive(Clone)]
+pub struct StdoutStream {
+    pub sub_id: String,
+    pub call_id: String,
+    pub tx_event: Sender<Event>,
+}
+
 pub async fn process_exec_tool_call(
     params: ExecParams,
     sandbox_type: SandboxType,
     ctrl_c: Arc<Notify>,
     sandbox_policy: &SandboxPolicy,
     codex_linux_sandbox_exe: &Option<PathBuf>,
+    stdout_stream: Option<StdoutStream>,
 ) -> Result<ExecToolCallOutput> {
     let start = Instant::now();
 
     let raw_output_result: std::result::Result<RawExecToolCallOutput, CodexErr> = match sandbox_type
     {
-        SandboxType::None => exec(params, sandbox_policy, ctrl_c).await,
+        SandboxType::None => exec(params, sandbox_policy, ctrl_c, stdout_stream.clone()).await,
         SandboxType::MacosSeatbelt => {
             let ExecParams {
                 command,
@@ -83,7 +97,7 @@ pub async fn process_exec_tool_call(
                 env,
             )
             .await?;
-            consume_truncated_output(child, ctrl_c, timeout_ms).await
+            consume_truncated_output(child, ctrl_c, timeout_ms, stdout_stream.clone()).await
         }
         SandboxType::LinuxSeccomp => {
             let ExecParams {
@@ -106,7 +120,7 @@ pub async fn process_exec_tool_call(
             )
             .await?;
 
-            consume_truncated_output(child, ctrl_c, timeout_ms).await
+            consume_truncated_output(child, ctrl_c, timeout_ms, stdout_stream).await
         }
     };
     let duration = start.elapsed();
@@ -233,6 +247,7 @@ async fn exec(
     }: ExecParams,
     sandbox_policy: &SandboxPolicy,
     ctrl_c: Arc<Notify>,
+    stdout_stream: Option<StdoutStream>,
 ) -> Result<RawExecToolCallOutput> {
     let (program, args) = command.split_first().ok_or_else(|| {
         CodexErr::Io(io::Error::new(
@@ -251,7 +266,7 @@ async fn exec(
         env,
     )
     .await?;
-    consume_truncated_output(child, ctrl_c, timeout_ms).await
+    consume_truncated_output(child, ctrl_c, timeout_ms, stdout_stream).await
 }
 
 /// Consumes the output of a child process, truncating it so it is suitable for
@@ -260,6 +275,7 @@ pub(crate) async fn consume_truncated_output(
     mut child: Child,
     ctrl_c: Arc<Notify>,
     timeout_ms: Option<u64>,
+    stdout_stream: Option<StdoutStream>,
 ) -> Result<RawExecToolCallOutput> {
     // Both stdout and stderr were configured with `Stdio::piped()`
     // above, therefore `take()` should normally return `Some`.  If it doesn't
@@ -280,11 +296,15 @@ pub(crate) async fn consume_truncated_output(
         BufReader::new(stdout_reader),
         MAX_STREAM_OUTPUT,
         MAX_STREAM_OUTPUT_LINES,
+        stdout_stream.clone(),
+        false,
     ));
     let stderr_handle = tokio::spawn(read_capped(
         BufReader::new(stderr_reader),
         MAX_STREAM_OUTPUT,
         MAX_STREAM_OUTPUT_LINES,
+        stdout_stream.clone(),
+        true,
     ));
 
     let interrupted = ctrl_c.notified();
@@ -318,10 +338,12 @@ pub(crate) async fn consume_truncated_output(
     })
 }
 
-async fn read_capped<R: AsyncRead + Unpin>(
+async fn read_capped<R: AsyncRead + Unpin + Send + 'static>(
     mut reader: R,
     max_output: usize,
     max_lines: usize,
+    stream: Option<StdoutStream>,
+    is_stderr: bool,
 ) -> io::Result<Vec<u8>> {
     let mut buf = Vec::with_capacity(max_output.min(8 * 1024));
     let mut tmp = [0u8; 8192];
@@ -335,6 +357,25 @@ async fn read_capped<R: AsyncRead + Unpin>(
             break;
         }
 
+        if let Some(stream) = &stream {
+            let chunk = tmp[..n].to_vec();
+            let msg = EventMsg::ExecCommandOutputDelta(ExecCommandOutputDeltaEvent {
+                call_id: stream.call_id.clone(),
+                stream: if is_stderr {
+                    ExecOutputStream::Stderr
+                } else {
+                    ExecOutputStream::Stdout
+                },
+                chunk: ByteBuf::from(chunk),
+            });
+            let event = Event {
+                id: stream.sub_id.clone(),
+                msg,
+            };
+            #[allow(clippy::let_unit_value)]
+            let _ = stream.tx_event.send(event).await;
+        }
+
         // Copy into the buffer only while we still have byte and line budget.
         if remaining_bytes > 0 && remaining_lines > 0 {
             let mut copy_len = 0;

codex-rs/core/src/model_provider_info.rs

@@ -12,10 +12,6 @@ use std::env::VarError;
 use std::time::Duration;
 
 use crate::error::EnvVarError;
-
-/// Value for the `OpenAI-Originator` header that is sent with requests to
-/// OpenAI.
-const OPENAI_ORIGINATOR_HEADER: &str = "codex_cli_rs";
 const DEFAULT_STREAM_IDLE_TIMEOUT_MS: u64 = 300_000;
 const DEFAULT_STREAM_MAX_RETRIES: u64 = 10;
 const DEFAULT_REQUEST_MAX_RETRIES: u64 = 4;
@@ -229,15 +225,9 @@ pub fn built_in_model_providers() -> HashMap<String, ModelProviderInfo> {
             wire_api: WireApi::Responses,
             query_params: None,
             http_headers: Some(
-                [
-                    (
-                        "originator".to_string(),
-                        OPENAI_ORIGINATOR_HEADER.to_string(),
-                    ),
-                    ("version".to_string(), env!("CARGO_PKG_VERSION").to_string()),
-                ]
-                .into_iter()
-                .collect(),
+                [("version".to_string(), env!("CARGO_PKG_VERSION").to_string())]
+                    .into_iter()
+                    .collect(),
             ),
             env_http_headers: Some(
                 [

codex-rs/core/src/protocol.rs

@@ -13,6 +13,7 @@ use std::time::Duration;
 use mcp_types::CallToolResult;
 use serde::Deserialize;
 use serde::Serialize;
+use serde_bytes::ByteBuf;
 use strum_macros::Display;
 use uuid::Uuid;
 
@@ -121,6 +122,10 @@ pub enum Op {
     /// Request a single history entry identified by `log_id` + `offset`.
     GetHistoryEntryRequest { offset: usize, log_id: u64 },
 
+    /// Request the agent to summarize the current conversation context.
+    /// The agent will use its existing context (either conversation history or previous response id)
+    /// to generate a summary which will be returned as an AgentMessage event.
+    Compact,
     /// Request to shut down codex instance.
     Shutdown,
 }
@@ -175,9 +180,29 @@ pub enum SandboxPolicy {
         /// default.
         #[serde(default)]
         network_access: bool,
+
+        /// When set to `true`, will include defaults like the current working
+        /// directory and TMPDIR (on macOS). When `false`, only `writable_roots`
+        /// are used. (Mainly used for testing.)
+        #[serde(default = "default_true")]
+        include_default_writable_roots: bool,
     },
 }
 
+/// A writable root path accompanied by a list of subpaths that should remain
+/// read‑only even when the root is writable. This is primarily used to ensure
+/// top‑level VCS metadata directories (e.g. `.git`) under a writable root are
+/// not modified by the agent.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct WritableRoot {
+    pub root: PathBuf,
+    pub read_only_subpaths: Vec<PathBuf>,
+}
+
+fn default_true() -> bool {
+    true
+}
+
 impl FromStr for SandboxPolicy {
     type Err = serde_json::Error;
 
@@ -199,6 +224,7 @@ impl SandboxPolicy {
         SandboxPolicy::WorkspaceWrite {
             writable_roots: vec![],
             network_access: false,
+            include_default_writable_roots: true,
         }
     }
 
@@ -224,27 +250,51 @@ impl SandboxPolicy {
         }
     }
 
-    /// Returns the list of writable roots that should be passed down to the
-    /// Landlock rules installer, tailored to the current working directory.
-    pub fn get_writable_roots_with_cwd(&self, cwd: &Path) -> Vec<PathBuf> {
+    /// Returns the list of writable roots (tailored to the current working
+    /// directory) together with subpaths that should remain read‑only under
+    /// each writable root.
+    pub fn get_writable_roots_with_cwd(&self, cwd: &Path) -> Vec<WritableRoot> {
         match self {
             SandboxPolicy::DangerFullAccess => Vec::new(),
             SandboxPolicy::ReadOnly => Vec::new(),
-            SandboxPolicy::WorkspaceWrite { writable_roots, .. } => {
-                let mut roots = writable_roots.clone();
-                roots.push(cwd.to_path_buf());
+            SandboxPolicy::WorkspaceWrite {
+                writable_roots,
+                include_default_writable_roots,
+                ..
+            } => {
+                // Start from explicitly configured writable roots.
+                let mut roots: Vec<PathBuf> = writable_roots.clone();
 
-                // Also include the per-user tmp dir on macOS.
-                // Note this is added dynamically rather than storing it in
-                // writable_roots because writable_roots contains only static
-                // values deserialized from the config file.
-                if cfg!(target_os = "macos") {
-                    if let Some(tmpdir) = std::env::var_os("TMPDIR") {
-                        roots.push(PathBuf::from(tmpdir));
+                // Optionally include defaults (cwd and TMPDIR on macOS).
+                if *include_default_writable_roots {
+                    roots.push(cwd.to_path_buf());
+
+                    // Also include the per-user tmp dir on macOS.
+                    // Note this is added dynamically rather than storing it in
+                    // `writable_roots` because `writable_roots` contains only static
+                    // values deserialized from the config file.
+                    if cfg!(target_os = "macos") {
+                        if let Some(tmpdir) = std::env::var_os("TMPDIR") {
+                            roots.push(PathBuf::from(tmpdir));
+                        }
                     }
                 }
 
+                // For each root, compute subpaths that should remain read-only.
                 roots
+                    .into_iter()
+                    .map(|writable_root| {
+                        let mut subpaths = Vec::new();
+                        let top_level_git = writable_root.join(".git");
+                        if top_level_git.is_dir() {
+                            subpaths.push(top_level_git);
+                        }
+                        WritableRoot {
+                            root: writable_root,
+                            read_only_subpaths: subpaths,
+                        }
+                    })
+                    .collect()
             }
         }
     }
@@ -319,6 +369,9 @@ pub enum EventMsg {
     /// Notification that the server is about to execute a command.
     ExecCommandBegin(ExecCommandBeginEvent),
 
+    /// Incremental chunk of output from a running command.
+    ExecCommandOutputDelta(ExecCommandOutputDeltaEvent),
+
     ExecCommandEnd(ExecCommandEndEvent),
 
     ExecApprovalRequest(ExecApprovalRequestEvent),
@@ -472,6 +525,24 @@ pub struct ExecCommandEndEvent {
     pub exit_code: i32,
 }
 
+#[derive(Debug, Clone, Deserialize, Serialize)]
+#[serde(rename_all = "snake_case")]
+pub enum ExecOutputStream {
+    Stdout,
+    Stderr,
+}
+
+#[derive(Debug, Clone, Deserialize, Serialize)]
+pub struct ExecCommandOutputDeltaEvent {
+    /// Identifier for the ExecCommandBegin that produced this chunk.
+    pub call_id: String,
+    /// Which stream produced this chunk.
+    pub stream: ExecOutputStream,
+    /// Raw bytes from the stream (may not be valid UTF-8).
+    #[serde(with = "serde_bytes")]
+    pub chunk: ByteBuf,
+}
+
 #[derive(Debug, Clone, Deserialize, Serialize)]
 pub struct ExecApprovalRequestEvent {
     /// Identifier for the associated exec call, if available.

codex-rs/core/src/seatbelt.rs

@@ -4,6 +4,7 @@ use std::path::PathBuf;
 use tokio::process::Child;
 
 use crate::protocol::SandboxPolicy;
+use crate::spawn::CODEX_SANDBOX_ENV_VAR;
 use crate::spawn::StdioPolicy;
 use crate::spawn::spawn_child_async;
 
@@ -20,10 +21,11 @@ pub async fn spawn_command_under_seatbelt(
     sandbox_policy: &SandboxPolicy,
     cwd: PathBuf,
     stdio_policy: StdioPolicy,
-    env: HashMap<String, String>,
+    mut env: HashMap<String, String>,
 ) -> std::io::Result<Child> {
     let args = create_seatbelt_command_args(command, sandbox_policy, &cwd);
     let arg0 = None;
+    env.insert(CODEX_SANDBOX_ENV_VAR.to_string(), "seatbelt".to_string());
     spawn_child_async(
         PathBuf::from(MACOS_PATH_TO_SEATBELT_EXECUTABLE),
         args,
@@ -50,16 +52,38 @@ fn create_seatbelt_command_args(
             )
         } else {
             let writable_roots = sandbox_policy.get_writable_roots_with_cwd(cwd);
-            let (writable_folder_policies, cli_args): (Vec<String>, Vec<String>) = writable_roots
-                .iter()
-                .enumerate()
-                .map(|(index, root)| {
-                    let param_name = format!("WRITABLE_ROOT_{index}");
-                    let policy: String = format!("(subpath (param \"{param_name}\"))");
-                    let cli_arg = format!("-D{param_name}={}", root.to_string_lossy());
-                    (policy, cli_arg)
-                })
-                .unzip();
+
+            let mut writable_folder_policies: Vec<String> = Vec::new();
+            let mut cli_args: Vec<String> = Vec::new();
+
+            for (index, wr) in writable_roots.iter().enumerate() {
+                // Canonicalize to avoid mismatches like /var vs /private/var on macOS.
+                let canonical_root = wr.root.canonicalize().unwrap_or_else(|_| wr.root.clone());
+                let root_param = format!("WRITABLE_ROOT_{index}");
+                cli_args.push(format!(
+                    "-D{root_param}={}",
+                    canonical_root.to_string_lossy()
+                ));
+
+                if wr.read_only_subpaths.is_empty() {
+                    writable_folder_policies.push(format!("(subpath (param \"{root_param}\"))"));
+                } else {
+                    // Add parameters for each read-only subpath and generate
+                    // the `(require-not ...)` clauses.
+                    let mut require_parts: Vec<String> = Vec::new();
+                    require_parts.push(format!("(subpath (param \"{root_param}\"))"));
+                    for (subpath_index, ro) in wr.read_only_subpaths.iter().enumerate() {
+                        let canonical_ro = ro.canonicalize().unwrap_or_else(|_| ro.clone());
+                        let ro_param = format!("WRITABLE_ROOT_{index}_RO_{subpath_index}");
+                        cli_args.push(format!("-D{ro_param}={}", canonical_ro.to_string_lossy()));
+                        require_parts
+                            .push(format!("(require-not (subpath (param \"{ro_param}\")))"));
+                    }
+                    let policy_component = format!("(require-all {} )", require_parts.join(" "));
+                    writable_folder_policies.push(policy_component);
+                }
+            }
+
             if writable_folder_policies.is_empty() {
                 ("".to_string(), Vec::<String>::new())
             } else {
@@ -88,9 +112,201 @@ fn create_seatbelt_command_args(
     let full_policy = format!(
         "{MACOS_SEATBELT_BASE_POLICY}\n{file_read_policy}\n{file_write_policy}\n{network_policy}"
     );
+
     let mut seatbelt_args: Vec<String> = vec!["-p".to_string(), full_policy];
     seatbelt_args.extend(extra_cli_args);
     seatbelt_args.push("--".to_string());
     seatbelt_args.extend(command);
     seatbelt_args
 }
+
+#[cfg(test)]
+mod tests {
+    #![expect(clippy::expect_used)]
+    use super::MACOS_SEATBELT_BASE_POLICY;
+    use super::create_seatbelt_command_args;
+    use crate::protocol::SandboxPolicy;
+    use pretty_assertions::assert_eq;
+    use std::fs;
+    use std::path::Path;
+    use std::path::PathBuf;
+    use tempfile::TempDir;
+
+    #[test]
+    fn create_seatbelt_args_with_read_only_git_subpath() {
+        // Create a temporary workspace with two writable roots: one containing
+        // a top-level .git directory and one without it.
+        let tmp = TempDir::new().expect("tempdir");
+        let PopulatedTmp {
+            root_with_git,
+            root_without_git,
+            root_with_git_canon,
+            root_with_git_git_canon,
+            root_without_git_canon,
+        } = populate_tmpdir(tmp.path());
+
+        // Build a policy that only includes the two test roots as writable and
+        // does not automatically include defaults like cwd or TMPDIR.
+        let policy = SandboxPolicy::WorkspaceWrite {
+            writable_roots: vec![root_with_git.clone(), root_without_git.clone()],
+            network_access: false,
+            include_default_writable_roots: false,
+        };
+
+        let args = create_seatbelt_command_args(
+            vec!["/bin/echo".to_string(), "hello".to_string()],
+            &policy,
+            tmp.path(),
+        );
+
+        // Build the expected policy text using a raw string for readability.
+        // Note that the policy includes:
+        // - the base policy,
+        // - read-only access to the filesystem,
+        // - write access to WRITABLE_ROOT_0 (but not its .git) and WRITABLE_ROOT_1.
+        let expected_policy = format!(
+            r#"{MACOS_SEATBELT_BASE_POLICY}
+; allow read-only file operations
+(allow file-read*)
+(allow file-write*
+(require-all (subpath (param "WRITABLE_ROOT_0")) (require-not (subpath (param "WRITABLE_ROOT_0_RO_0"))) ) (subpath (param "WRITABLE_ROOT_1"))
+)
+"#,
+        );
+
+        let expected_args = vec![
+            "-p".to_string(),
+            expected_policy,
+            format!(
+                "-DWRITABLE_ROOT_0={}",
+                root_with_git_canon.to_string_lossy()
+            ),
+            format!(
+                "-DWRITABLE_ROOT_0_RO_0={}",
+                root_with_git_git_canon.to_string_lossy()
+            ),
+            format!(
+                "-DWRITABLE_ROOT_1={}",
+                root_without_git_canon.to_string_lossy()
+            ),
+            "--".to_string(),
+            "/bin/echo".to_string(),
+            "hello".to_string(),
+        ];
+
+        assert_eq!(args, expected_args);
+    }
+
+    #[test]
+    fn create_seatbelt_args_for_cwd_as_git_repo() {
+        // Create a temporary workspace with two writable roots: one containing
+        // a top-level .git directory and one without it.
+        let tmp = TempDir::new().expect("tempdir");
+        let PopulatedTmp {
+            root_with_git,
+            root_with_git_canon,
+            root_with_git_git_canon,
+            ..
+        } = populate_tmpdir(tmp.path());
+
+        // Build a policy that does not specify any writable_roots, but does
+        // use the default ones (cwd and TMPDIR) and verifies the `.git` check
+        // is done properly for cwd.
+        let policy = SandboxPolicy::WorkspaceWrite {
+            writable_roots: vec![],
+            network_access: false,
+            include_default_writable_roots: true,
+        };
+
+        let args = create_seatbelt_command_args(
+            vec!["/bin/echo".to_string(), "hello".to_string()],
+            &policy,
+            root_with_git.as_path(),
+        );
+
+        let tmpdir_env_var = if cfg!(target_os = "macos") {
+            std::env::var("TMPDIR")
+                .ok()
+                .map(PathBuf::from)
+                .and_then(|p| p.canonicalize().ok())
+                .map(|p| p.to_string_lossy().to_string())
+        } else {
+            None
+        };
+        let tempdir_policy_entry = if tmpdir_env_var.is_some() {
+            " (subpath (param \"WRITABLE_ROOT_1\"))"
+        } else {
+            ""
+        };
+
+        // Build the expected policy text using a raw string for readability.
+        // Note that the policy includes:
+        // - the base policy,
+        // - read-only access to the filesystem,
+        // - write access to WRITABLE_ROOT_0 (but not its .git) and WRITABLE_ROOT_1.
+        let expected_policy = format!(
+            r#"{MACOS_SEATBELT_BASE_POLICY}
+; allow read-only file operations
+(allow file-read*)
+(allow file-write*
+(require-all (subpath (param "WRITABLE_ROOT_0")) (require-not (subpath (param "WRITABLE_ROOT_0_RO_0"))) ){tempdir_policy_entry}
+)
+"#,
+        );
+
+        let mut expected_args = vec![
+            "-p".to_string(),
+            expected_policy,
+            format!(
+                "-DWRITABLE_ROOT_0={}",
+                root_with_git_canon.to_string_lossy()
+            ),
+            format!(
+                "-DWRITABLE_ROOT_0_RO_0={}",
+                root_with_git_git_canon.to_string_lossy()
+            ),
+        ];
+
+        if let Some(p) = tmpdir_env_var {
+            expected_args.push(format!("-DWRITABLE_ROOT_1={p}"));
+        }
+
+        expected_args.extend(vec![
+            "--".to_string(),
+            "/bin/echo".to_string(),
+            "hello".to_string(),
+        ]);
+
+        assert_eq!(args, expected_args);
+    }
+
+    struct PopulatedTmp {
+        root_with_git: PathBuf,
+        root_without_git: PathBuf,
+        root_with_git_canon: PathBuf,
+        root_with_git_git_canon: PathBuf,
+        root_without_git_canon: PathBuf,
+    }
+
+    fn populate_tmpdir(tmp: &Path) -> PopulatedTmp {
+        let root_with_git = tmp.join("with_git");
+        let root_without_git = tmp.join("no_git");
+        fs::create_dir_all(&root_with_git).expect("create with_git");
+        fs::create_dir_all(&root_without_git).expect("create no_git");
+        fs::create_dir_all(root_with_git.join(".git")).expect("create .git");
+
+        // Ensure we have canonical paths for -D parameter matching.
+        let root_with_git_canon = root_with_git.canonicalize().expect("canonicalize with_git");
+        let root_with_git_git_canon = root_with_git_canon.join(".git");
+        let root_without_git_canon = root_without_git
+            .canonicalize()
+            .expect("canonicalize no_git");
+        PopulatedTmp {
+            root_with_git,
+            root_without_git,
+            root_with_git_canon,
+            root_with_git_git_canon,
+            root_without_git_canon,
+        }
+    }
+}

codex-rs/core/src/shell.rs

@@ -220,6 +220,7 @@ mod tests {
                 Arc::new(Notify::new()),
                 &SandboxPolicy::DangerFullAccess,
                 &None,
+                None,
             )
             .await
             .unwrap();

codex-rs/core/src/spawn.rs

@@ -17,6 +17,11 @@ use crate::protocol::SandboxPolicy;
 /// attributes, so this may change in the future.
 pub const CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR: &str = "CODEX_SANDBOX_NETWORK_DISABLED";
 
+/// Should be set when the process is spawned under a sandbox. Currently, the
+/// value is "seatbelt" for macOS, but it may change in the future to
+/// accommodate sandboxing configuration and other sandboxing mechanisms.
+pub const CODEX_SANDBOX_ENV_VAR: &str = "CODEX_SANDBOX";
+
 #[derive(Debug, Clone, Copy)]
 pub enum StdioPolicy {
     RedirectForShellTool,

codex-rs/core/tests/client.rs

@@ -95,8 +95,8 @@ async fn includes_session_id_and_model_headers_in_request() {
     // get request from the server
     let request = &server.received_requests().await.unwrap()[0];
     let request_session_id = request.headers.get("session_id").unwrap();
-    let request_originator = request.headers.get("originator").unwrap();
     let request_authorization = request.headers.get("authorization").unwrap();
+    let request_originator = request.headers.get("originator").unwrap();
 
     assert!(current_session_id.is_some());
     assert_eq!(
@@ -170,6 +170,59 @@ async fn includes_base_instructions_override_in_request() {
     );
 }
 
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn originator_config_override_is_used() {
+    #![allow(clippy::unwrap_used)]
+
+    // Mock server
+    let server = MockServer::start().await;
+
+    let first = ResponseTemplate::new(200)
+        .insert_header("content-type", "text/event-stream")
+        .set_body_raw(sse_completed("resp1"), "text/event-stream");
+
+    Mock::given(method("POST"))
+        .and(path("/v1/responses"))
+        .respond_with(first)
+        .expect(1)
+        .mount(&server)
+        .await;
+
+    let model_provider = ModelProviderInfo {
+        base_url: Some(format!("{}/v1", server.uri())),
+        ..built_in_model_providers()["openai"].clone()
+    };
+
+    let codex_home = TempDir::new().unwrap();
+    let mut config = load_default_config_for_test(&codex_home);
+    config.model_provider = model_provider;
+    config.internal_originator = Some("my_override".to_string());
+
+    let ctrl_c = std::sync::Arc::new(tokio::sync::Notify::new());
+    let CodexSpawnOk { codex, .. } = Codex::spawn(
+        config,
+        Some(CodexAuth::from_api_key("Test API Key".to_string())),
+        ctrl_c.clone(),
+    )
+    .await
+    .unwrap();
+
+    codex
+        .submit(Op::UserInput {
+            items: vec![InputItem::Text {
+                text: "hello".into(),
+            }],
+        })
+        .await
+        .unwrap();
+
+    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
+
+    let request = &server.received_requests().await.unwrap()[0];
+    let request_originator = request.headers.get("originator").unwrap();
+    assert_eq!(request_originator.to_str().unwrap(), "my_override");
+}
+
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
 async fn chatgpt_auth_sends_correct_request() {
     #![allow(clippy::unwrap_used)]
@@ -235,8 +288,8 @@ async fn chatgpt_auth_sends_correct_request() {
     // get request from the server
     let request = &server.received_requests().await.unwrap()[0];
     let request_session_id = request.headers.get("session_id").unwrap();
-    let request_originator = request.headers.get("originator").unwrap();
     let request_authorization = request.headers.get("authorization").unwrap();
+    let request_originator = request.headers.get("originator").unwrap();
     let request_chatgpt_account_id = request.headers.get("chatgpt-account-id").unwrap();
     let request_body = request.body_json::<serde_json::Value>().unwrap();
 

codex-rs/core/tests/compact.rs

@@ -0,0 +1,254 @@
+#![expect(clippy::unwrap_used)]
+
+use codex_core::Codex;
+use codex_core::CodexSpawnOk;
+use codex_core::ModelProviderInfo;
+use codex_core::built_in_model_providers;
+use codex_core::protocol::EventMsg;
+use codex_core::protocol::InputItem;
+use codex_core::protocol::Op;
+use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
+use codex_login::CodexAuth;
+use core_test_support::load_default_config_for_test;
+use core_test_support::wait_for_event;
+use serde_json::Value;
+use tempfile::TempDir;
+use wiremock::Mock;
+use wiremock::MockServer;
+use wiremock::ResponseTemplate;
+use wiremock::matchers::method;
+use wiremock::matchers::path;
+
+use pretty_assertions::assert_eq;
+
+// --- Test helpers -----------------------------------------------------------
+
+/// Build an SSE stream body from a list of JSON events.
+fn sse(events: Vec<Value>) -> String {
+    use std::fmt::Write as _;
+    let mut out = String::new();
+    for ev in events {
+        let kind = ev.get("type").and_then(|v| v.as_str()).unwrap();
+        writeln!(&mut out, "event: {kind}").unwrap();
+        if !ev.as_object().map(|o| o.len() == 1).unwrap_or(false) {
+            write!(&mut out, "data: {ev}\n\n").unwrap();
+        } else {
+            out.push('\n');
+        }
+    }
+    out
+}
+
+/// Convenience: SSE event for a completed response with a specific id.
+fn ev_completed(id: &str) -> Value {
+    serde_json::json!({
+        "type": "response.completed",
+        "response": {
+            "id": id,
+            "usage": {"input_tokens":0,"input_tokens_details":null,"output_tokens":0,"output_tokens_details":null,"total_tokens":0}
+        }
+    })
+}
+
+/// Convenience: SSE event for a single assistant message output item.
+fn ev_assistant_message(id: &str, text: &str) -> Value {
+    serde_json::json!({
+        "type": "response.output_item.done",
+        "item": {
+            "type": "message",
+            "role": "assistant",
+            "id": id,
+            "content": [{"type": "output_text", "text": text}]
+        }
+    })
+}
+
+fn sse_response(body: String) -> ResponseTemplate {
+    ResponseTemplate::new(200)
+        .insert_header("content-type", "text/event-stream")
+        .set_body_raw(body, "text/event-stream")
+}
+
+async fn mount_sse_once<M>(server: &MockServer, matcher: M, body: String)
+where
+    M: wiremock::Match + Send + Sync + 'static,
+{
+    Mock::given(method("POST"))
+        .and(path("/v1/responses"))
+        .and(matcher)
+        .respond_with(sse_response(body))
+        .expect(1)
+        .mount(server)
+        .await;
+}
+
+const FIRST_REPLY: &str = "FIRST_REPLY";
+const SUMMARY_TEXT: &str = "SUMMARY_ONLY_CONTEXT";
+const SUMMARIZE_TRIGGER: &str = "Start Summarization";
+const THIRD_USER_MSG: &str = "next turn";
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn summarize_context_three_requests_and_instructions() {
+    if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
+        println!(
+            "Skipping test because it cannot execute when network is disabled in a Codex sandbox."
+        );
+        return;
+    }
+
+    // Set up a mock server that we can inspect after the run.
+    let server = MockServer::start().await;
+
+    // SSE 1: assistant replies normally so it is recorded in history.
+    let sse1 = sse(vec![
+        ev_assistant_message("m1", FIRST_REPLY),
+        ev_completed("r1"),
+    ]);
+
+    // SSE 2: summarizer returns a summary message.
+    let sse2 = sse(vec![
+        ev_assistant_message("m2", SUMMARY_TEXT),
+        ev_completed("r2"),
+    ]);
+
+    // SSE 3: minimal completed; we only need to capture the request body.
+    let sse3 = sse(vec![ev_completed("r3")]);
+
+    // Mount three expectations, one per request, matched by body content.
+    let first_matcher = |req: &wiremock::Request| {
+        let body = std::str::from_utf8(&req.body).unwrap_or("");
+        body.contains("\"text\":\"hello world\"")
+            && !body.contains(&format!("\"text\":\"{SUMMARIZE_TRIGGER}\""))
+    };
+    mount_sse_once(&server, first_matcher, sse1).await;
+
+    let second_matcher = |req: &wiremock::Request| {
+        let body = std::str::from_utf8(&req.body).unwrap_or("");
+        body.contains(&format!("\"text\":\"{SUMMARIZE_TRIGGER}\""))
+    };
+    mount_sse_once(&server, second_matcher, sse2).await;
+
+    let third_matcher = |req: &wiremock::Request| {
+        let body = std::str::from_utf8(&req.body).unwrap_or("");
+        body.contains(&format!("\"text\":\"{THIRD_USER_MSG}\""))
+    };
+    mount_sse_once(&server, third_matcher, sse3).await;
+
+    // Build config pointing to the mock server and spawn Codex.
+    let model_provider = ModelProviderInfo {
+        base_url: Some(format!("{}/v1", server.uri())),
+        ..built_in_model_providers()["openai"].clone()
+    };
+    let home = TempDir::new().unwrap();
+    let mut config = load_default_config_for_test(&home);
+    config.model_provider = model_provider;
+    let ctrl_c = std::sync::Arc::new(tokio::sync::Notify::new());
+    let CodexSpawnOk { codex, .. } = Codex::spawn(
+        config,
+        Some(CodexAuth::from_api_key("dummy".to_string())),
+        ctrl_c.clone(),
+    )
+    .await
+    .unwrap();
+
+    // 1) Normal user input – should hit server once.
+    codex
+        .submit(Op::UserInput {
+            items: vec![InputItem::Text {
+                text: "hello world".into(),
+            }],
+        })
+        .await
+        .unwrap();
+    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
+
+    // 2) Summarize – second hit with summarization instructions.
+    codex.submit(Op::Compact).await.unwrap();
+    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
+
+    // 3) Next user input – third hit; history should include only the summary.
+    codex
+        .submit(Op::UserInput {
+            items: vec![InputItem::Text {
+                text: THIRD_USER_MSG.into(),
+            }],
+        })
+        .await
+        .unwrap();
+    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
+
+    // Inspect the three captured requests.
+    let requests = server.received_requests().await.unwrap();
+    assert_eq!(requests.len(), 3, "expected exactly three requests");
+
+    let req1 = &requests[0];
+    let req2 = &requests[1];
+    let req3 = &requests[2];
+
+    let body1 = req1.body_json::<serde_json::Value>().unwrap();
+    let body2 = req2.body_json::<serde_json::Value>().unwrap();
+    let body3 = req3.body_json::<serde_json::Value>().unwrap();
+
+    // System instructions should change for the summarization turn.
+    let instr1 = body1.get("instructions").and_then(|v| v.as_str()).unwrap();
+    let instr2 = body2.get("instructions").and_then(|v| v.as_str()).unwrap();
+    assert_ne!(
+        instr1, instr2,
+        "summarization should override base instructions"
+    );
+    assert!(
+        instr2.contains("You are a summarization assistant"),
+        "summarization instructions not applied"
+    );
+
+    // The summarization request should include the injected user input marker.
+    let input2 = body2.get("input").and_then(|v| v.as_array()).unwrap();
+    // The last item is the user message created from the injected input.
+    let last2 = input2.last().unwrap();
+    assert_eq!(last2.get("type").unwrap().as_str().unwrap(), "message");
+    assert_eq!(last2.get("role").unwrap().as_str().unwrap(), "user");
+    let text2 = last2["content"][0]["text"].as_str().unwrap();
+    assert!(text2.contains(SUMMARIZE_TRIGGER));
+
+    // Third request must contain only the summary from step 2 as prior history plus new user msg.
+    let input3 = body3.get("input").and_then(|v| v.as_array()).unwrap();
+    println!("third request body: {body3}");
+    assert!(
+        input3.len() >= 2,
+        "expected summary + new user message in third request"
+    );
+
+    // Collect all (role, text) message tuples.
+    let mut messages: Vec<(String, String)> = Vec::new();
+    for item in input3 {
+        if item["type"].as_str() == Some("message") {
+            let role = item["role"].as_str().unwrap_or_default().to_string();
+            let text = item["content"][0]["text"]
+                .as_str()
+                .unwrap_or_default()
+                .to_string();
+            messages.push((role, text));
+        }
+    }
+
+    // Exactly one assistant message should remain after compaction and the new user message is present.
+    let assistant_count = messages.iter().filter(|(r, _)| r == "assistant").count();
+    assert_eq!(
+        assistant_count, 1,
+        "exactly one assistant message should remain after compaction"
+    );
+    assert!(
+        messages
+            .iter()
+            .any(|(r, t)| r == "user" && t == THIRD_USER_MSG),
+        "third request should include the new user message"
+    );
+    assert!(
+        !messages.iter().any(|(_, t)| t.contains("hello world")),
+        "third request should not include the original user input"
+    );
+    assert!(
+        !messages.iter().any(|(_, t)| t.contains(SUMMARIZE_TRIGGER)),
+        "third request should not include the summarize trigger"
+    );
+}

codex-rs/core/tests/env_snapshot.rs

@@ -1,189 +0,0 @@
-#![allow(clippy::expect_used, clippy::unwrap_used)]
-
-use codex_core::Codex;
-use codex_core::CodexSpawnOk;
-use codex_core::ModelProviderInfo;
-use codex_core::built_in_model_providers;
-use codex_core::protocol::EventMsg;
-use codex_core::protocol::InputItem;
-use codex_core::protocol::Op;
-use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
-use codex_login::CodexAuth;
-use core_test_support::load_default_config_for_test;
-use core_test_support::load_sse_fixture_with_id;
-use core_test_support::wait_for_event;
-use tempfile::TempDir;
-use wiremock::Mock;
-use wiremock::MockServer;
-use wiremock::ResponseTemplate;
-use wiremock::matchers::method;
-use wiremock::matchers::path;
-
-#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn first_turn_includes_environment_snapshot() {
-    if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
-        println!(
-            "Skipping test because it cannot execute when network is disabled in a Codex sandbox."
-        );
-        return;
-    }
-
-    // Create a temporary working directory with a few files (including a hidden one).
-    let cwd = TempDir::new().unwrap();
-    std::fs::write(cwd.path().join("a.txt"), b"x").unwrap();
-    std::fs::write(cwd.path().join("b.txt"), b"x").unwrap();
-    std::fs::write(cwd.path().join(".hidden"), b"x").unwrap();
-
-    // Mock Responses API server that immediately completes the turn.
-    let server = MockServer::start().await;
-    let sse = load_sse_fixture_with_id("tests/fixtures/completed_template.json", "resp1");
-    let first = ResponseTemplate::new(200)
-        .insert_header("content-type", "text/event-stream")
-        .set_body_raw(sse, "text/event-stream");
-    Mock::given(method("POST"))
-        .and(path("/v1/responses"))
-        .respond_with(first)
-        .mount(&server)
-        .await;
-
-    let model_provider = ModelProviderInfo {
-        base_url: Some(format!("{}/v1", server.uri())),
-        ..built_in_model_providers()["openai"].clone()
-    };
-
-    // Initialize session using the temp cwd and the mock provider.
-    let codex_home = TempDir::new().unwrap();
-    let mut config = load_default_config_for_test(&codex_home);
-    config.model_provider = model_provider;
-    config.cwd = cwd.path().to_path_buf();
-
-    let ctrl_c = std::sync::Arc::new(tokio::sync::Notify::new());
-    let CodexSpawnOk { codex, .. } = Codex::spawn(
-        config,
-        Some(CodexAuth::from_api_key("Test API Key".to_string())),
-        ctrl_c.clone(),
-    )
-    .await
-    .unwrap();
-
-    // Submit a simple user message – the agent should inject the environment snapshot as
-    // an additional content item at the start of the first user message.
-    codex
-        .submit(Op::UserInput {
-            items: vec![InputItem::Text {
-                text: "hello".into(),
-            }],
-        })
-        .await
-        .unwrap();
-
-    // Wait for the task to complete so the request is dispatched.
-    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
-
-    // Read the captured request and verify the first message content includes the snapshot.
-    let request = &server.received_requests().await.unwrap()[0];
-    let body = request.body_json::<serde_json::Value>().unwrap();
-
-    // We expect the first (and only) input item to be a user message with multiple content entries.
-    let first_input = &body["input"][0];
-    assert_eq!(first_input["role"], "user");
-
-    // The first content item should be the injected environment snapshot.
-    let first_text = first_input["content"][0]["text"].as_str().unwrap();
-    assert!(first_text.starts_with("Environment snapshot (output of `ls | head -n 50` in cwd):"));
-    // It should reference the cwd and include visible files, but not hidden ones.
-    assert!(first_text.contains(&cwd.path().display().to_string()));
-    assert!(first_text.contains("a.txt"));
-    assert!(first_text.contains("b.txt"));
-    assert!(!first_text.contains(".hidden"));
-
-    // The user's original message should appear in the second content item.
-    let second_text = first_input["content"][1]["text"].as_str().unwrap();
-    assert_eq!(second_text, "hello");
-}
-
-#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn snapshot_is_not_injected_on_second_turn() {
-    if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
-        println!(
-            "Skipping test because it cannot execute when network is disabled in a Codex sandbox."
-        );
-        return;
-    }
-
-    // Prepare cwd with a couple of files (and a hidden one).
-    let cwd = TempDir::new().unwrap();
-    std::fs::write(cwd.path().join("first.txt"), b"x").unwrap();
-    std::fs::write(cwd.path().join("second.txt"), b"x").unwrap();
-    std::fs::write(cwd.path().join(".dot"), b"x").unwrap();
-
-    // Mock server that accepts two requests and completes both.
-    let server = MockServer::start().await;
-    let sse = load_sse_fixture_with_id("tests/fixtures/completed_template.json", "resp1");
-    let responder = ResponseTemplate::new(200)
-        .insert_header("content-type", "text/event-stream")
-        .set_body_raw(sse, "text/event-stream");
-    Mock::given(method("POST"))
-        .and(path("/v1/responses"))
-        .respond_with(responder)
-        .expect(2)
-        .mount(&server)
-        .await;
-
-    let model_provider = ModelProviderInfo {
-        base_url: Some(format!("{}/v1", server.uri())),
-        ..built_in_model_providers()["openai"].clone()
-    };
-
-    let codex_home = TempDir::new().unwrap();
-    let mut config = load_default_config_for_test(&codex_home);
-    config.model_provider = model_provider;
-    config.cwd = cwd.path().to_path_buf();
-
-    let ctrl_c = std::sync::Arc::new(tokio::sync::Notify::new());
-    let CodexSpawnOk { codex, .. } = Codex::spawn(
-        config,
-        Some(CodexAuth::from_api_key("Test API Key".to_string())),
-        ctrl_c.clone(),
-    )
-    .await
-    .unwrap();
-
-    // First user message.
-    codex
-        .submit(Op::UserInput {
-            items: vec![InputItem::Text {
-                text: "first".into(),
-            }],
-        })
-        .await
-        .unwrap();
-    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
-
-    // Second user message.
-    codex
-        .submit(Op::UserInput {
-            items: vec![InputItem::Text {
-                text: "second".into(),
-            }],
-        })
-        .await
-        .unwrap();
-    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
-
-    // Verify the second request's last user message does not include the environment snapshot.
-    let requests = server.received_requests().await.unwrap();
-    assert!(
-        requests.len() >= 2,
-        "expected two requests to the mock server"
-    );
-    let second_req = &requests[1];
-    let body = second_req.body_json::<serde_json::Value>().unwrap();
-
-    let input = body["input"].as_array().expect("input array");
-    let last = input.last().expect("at least one input item");
-    assert_eq!(last["role"], "user");
-    let last_text = last["content"][0]["text"].as_str().unwrap();
-    // Should be exactly the submitted text, without the snapshot header prefix.
-    assert_eq!(last_text, "second");
-}

codex-rs/core/tests/exec_stream_events.rs

@@ -0,0 +1,143 @@
+#![cfg(unix)]
+
+use std::collections::HashMap;
+use std::path::PathBuf;
+use std::sync::Arc;
+
+use async_channel::Receiver;
+use codex_core::exec::ExecParams;
+use codex_core::exec::SandboxType;
+use codex_core::exec::StdoutStream;
+use codex_core::exec::process_exec_tool_call;
+use codex_core::protocol::Event;
+use codex_core::protocol::EventMsg;
+use codex_core::protocol::ExecCommandOutputDeltaEvent;
+use codex_core::protocol::ExecOutputStream;
+use codex_core::protocol::SandboxPolicy;
+use tokio::sync::Notify;
+
+fn collect_stdout_events(rx: Receiver<Event>) -> Vec<u8> {
+    let mut out = Vec::new();
+    while let Ok(ev) = rx.try_recv() {
+        if let EventMsg::ExecCommandOutputDelta(ExecCommandOutputDeltaEvent {
+            stream: ExecOutputStream::Stdout,
+            chunk,
+            ..
+        }) = ev.msg
+        {
+            out.extend_from_slice(&chunk);
+        }
+    }
+    out
+}
+
+#[tokio::test]
+async fn test_exec_stdout_stream_events_echo() {
+    let (tx, rx) = async_channel::unbounded::<Event>();
+
+    let stdout_stream = StdoutStream {
+        sub_id: "test-sub".to_string(),
+        call_id: "call-1".to_string(),
+        tx_event: tx,
+    };
+
+    let cmd = vec![
+        "/bin/sh".to_string(),
+        "-c".to_string(),
+        // Use printf for predictable behavior across shells
+        "printf 'hello-world\n'".to_string(),
+    ];
+
+    let params = ExecParams {
+        command: cmd,
+        cwd: std::env::current_dir().unwrap_or_else(|_| PathBuf::from(".")),
+        timeout_ms: Some(5_000),
+        env: HashMap::new(),
+    };
+
+    let ctrl_c = Arc::new(Notify::new());
+    let policy = SandboxPolicy::new_read_only_policy();
+
+    let result = process_exec_tool_call(
+        params,
+        SandboxType::None,
+        ctrl_c,
+        &policy,
+        &None,
+        Some(stdout_stream),
+    )
+    .await;
+
+    let result = match result {
+        Ok(r) => r,
+        Err(e) => panic!("process_exec_tool_call failed: {e}"),
+    };
+
+    assert_eq!(result.exit_code, 0);
+    assert_eq!(result.stdout, "hello-world\n");
+
+    let streamed = collect_stdout_events(rx);
+    // We should have received at least the same contents (possibly in one chunk)
+    assert_eq!(String::from_utf8_lossy(&streamed), "hello-world\n");
+}
+
+#[tokio::test]
+async fn test_exec_stderr_stream_events_echo() {
+    let (tx, rx) = async_channel::unbounded::<Event>();
+
+    let stdout_stream = StdoutStream {
+        sub_id: "test-sub".to_string(),
+        call_id: "call-2".to_string(),
+        tx_event: tx,
+    };
+
+    let cmd = vec![
+        "/bin/sh".to_string(),
+        "-c".to_string(),
+        // Write to stderr explicitly
+        "printf 'oops\n' 1>&2".to_string(),
+    ];
+
+    let params = ExecParams {
+        command: cmd,
+        cwd: std::env::current_dir().unwrap_or_else(|_| PathBuf::from(".")),
+        timeout_ms: Some(5_000),
+        env: HashMap::new(),
+    };
+
+    let ctrl_c = Arc::new(Notify::new());
+    let policy = SandboxPolicy::new_read_only_policy();
+
+    let result = process_exec_tool_call(
+        params,
+        SandboxType::None,
+        ctrl_c,
+        &policy,
+        &None,
+        Some(stdout_stream),
+    )
+    .await;
+
+    let result = match result {
+        Ok(r) => r,
+        Err(e) => panic!("process_exec_tool_call failed: {e}"),
+    };
+
+    assert_eq!(result.exit_code, 0);
+    assert_eq!(result.stdout, "");
+    assert_eq!(result.stderr, "oops\n");
+
+    // Collect only stderr delta events
+    let mut err = Vec::new();
+    while let Ok(ev) = rx.try_recv() {
+        if let EventMsg::ExecCommandOutputDelta(ExecCommandOutputDeltaEvent {
+            stream: ExecOutputStream::Stderr,
+            chunk,
+            ..
+        }) = ev.msg
+        {
+            err.extend_from_slice(&chunk);
+        }
+    }
+    assert_eq!(String::from_utf8_lossy(&err), "oops\n");
+}

codex-rs/core/tests/sandbox.rs

@@ -0,0 +1,195 @@
+#![cfg(target_os = "macos")]
+#![expect(clippy::expect_used)]
+
+use std::collections::HashMap;
+use std::path::Path;
+use std::path::PathBuf;
+
+use codex_core::protocol::SandboxPolicy;
+use codex_core::seatbelt::spawn_command_under_seatbelt;
+use codex_core::spawn::CODEX_SANDBOX_ENV_VAR;
+use codex_core::spawn::StdioPolicy;
+use tempfile::TempDir;
+
+struct TestScenario {
+    repo_parent: PathBuf,
+    file_outside_repo: PathBuf,
+    repo_root: PathBuf,
+    file_in_repo_root: PathBuf,
+    file_in_dot_git_dir: PathBuf,
+}
+
+struct TestExpectations {
+    file_outside_repo_is_writable: bool,
+    file_in_repo_root_is_writable: bool,
+    file_in_dot_git_dir_is_writable: bool,
+}
+
+impl TestScenario {
+    async fn run_test(&self, policy: &SandboxPolicy, expectations: TestExpectations) {
+        if std::env::var(CODEX_SANDBOX_ENV_VAR) == Ok("seatbelt".to_string()) {
+            eprintln!("{CODEX_SANDBOX_ENV_VAR} is set to 'seatbelt', skipping test.");
+            return;
+        }
+
+        assert_eq!(
+            touch(&self.file_outside_repo, policy).await,
+            expectations.file_outside_repo_is_writable
+        );
+        assert_eq!(
+            self.file_outside_repo.exists(),
+            expectations.file_outside_repo_is_writable
+        );
+
+        assert_eq!(
+            touch(&self.file_in_repo_root, policy).await,
+            expectations.file_in_repo_root_is_writable
+        );
+        assert_eq!(
+            self.file_in_repo_root.exists(),
+            expectations.file_in_repo_root_is_writable
+        );
+
+        assert_eq!(
+            touch(&self.file_in_dot_git_dir, policy).await,
+            expectations.file_in_dot_git_dir_is_writable
+        );
+        assert_eq!(
+            self.file_in_dot_git_dir.exists(),
+            expectations.file_in_dot_git_dir_is_writable
+        );
+    }
+}
+
+/// If the user has added a workspace root that is not a Git repo root, then
+/// the user has to specify `--skip-git-repo-check` or go through some
+/// interstitial that indicates they are taking on some risk because Git
+/// cannot be used to backup their work before the agent begins.
+///
+/// Because the user has agreed to this risk, we do not try find all .git
+/// folders in the workspace and block them (though we could change our
+/// position on this in the future).
+#[tokio::test]
+async fn if_parent_of_repo_is_writable_then_dot_git_folder_is_writable() {
+    let tmp = TempDir::new().expect("should be able to create temp dir");
+    let test_scenario = create_test_scenario(&tmp);
+    let policy = SandboxPolicy::WorkspaceWrite {
+        writable_roots: vec![test_scenario.repo_parent.clone()],
+        network_access: false,
+        include_default_writable_roots: false,
+    };
+
+    test_scenario
+        .run_test(
+            &policy,
+            TestExpectations {
+                file_outside_repo_is_writable: true,
+                file_in_repo_root_is_writable: true,
+                file_in_dot_git_dir_is_writable: true,
+            },
+        )
+        .await;
+}
+
+/// When the writable root is the root of a Git repository (as evidenced by the
+/// presence of a .git folder), then the .git folder should be read-only if
+/// the policy is `WorkspaceWrite`.
+#[tokio::test]
+async fn if_git_repo_is_writable_root_then_dot_git_folder_is_read_only() {
+    let tmp = TempDir::new().expect("should be able to create temp dir");
+    let test_scenario = create_test_scenario(&tmp);
+    let policy = SandboxPolicy::WorkspaceWrite {
+        writable_roots: vec![test_scenario.repo_root.clone()],
+        network_access: false,
+        include_default_writable_roots: false,
+    };
+
+    test_scenario
+        .run_test(
+            &policy,
+            TestExpectations {
+                file_outside_repo_is_writable: false,
+                file_in_repo_root_is_writable: true,
+                file_in_dot_git_dir_is_writable: false,
+            },
+        )
+        .await;
+}
+
+/// Under DangerFullAccess, all writes should be permitted anywhere on disk,
+/// including inside the .git folder.
+#[tokio::test]
+async fn danger_full_access_allows_all_writes() {
+    let tmp = TempDir::new().expect("should be able to create temp dir");
+    let test_scenario = create_test_scenario(&tmp);
+    let policy = SandboxPolicy::DangerFullAccess;
+
+    test_scenario
+        .run_test(
+            &policy,
+            TestExpectations {
+                file_outside_repo_is_writable: true,
+                file_in_repo_root_is_writable: true,
+                file_in_dot_git_dir_is_writable: true,
+            },
+        )
+        .await;
+}
+
+/// Under ReadOnly, writes should not be permitted anywhere on disk.
+#[tokio::test]
+async fn read_only_forbids_all_writes() {
+    let tmp = TempDir::new().expect("should be able to create temp dir");
+    let test_scenario = create_test_scenario(&tmp);
+    let policy = SandboxPolicy::ReadOnly;
+
+    test_scenario
+        .run_test(
+            &policy,
+            TestExpectations {
+                file_outside_repo_is_writable: false,
+                file_in_repo_root_is_writable: false,
+                file_in_dot_git_dir_is_writable: false,
+            },
+        )
+        .await;
+}
+
+fn create_test_scenario(tmp: &TempDir) -> TestScenario {
+    let repo_parent = tmp.path().to_path_buf();
+    let repo_root = repo_parent.join("repo");
+    let dot_git_dir = repo_root.join(".git");
+
+    std::fs::create_dir(&repo_root).expect("should be able to create repo root");
+    std::fs::create_dir(&dot_git_dir).expect("should be able to create .git dir");
+
+    TestScenario {
+        file_outside_repo: repo_parent.join("outside.txt"),
+        repo_parent,
+        file_in_repo_root: repo_root.join("repo_file.txt"),
+        repo_root,
+        file_in_dot_git_dir: dot_git_dir.join("dot_git_file.txt"),
+    }
+}
+
+/// Note that `path` must be absolute.
+async fn touch(path: &Path, policy: &SandboxPolicy) -> bool {
+    assert!(path.is_absolute(), "Path must be absolute: {path:?}");
+    let mut child = spawn_command_under_seatbelt(
+        vec![
+            "/usr/bin/touch".to_string(),
+            path.to_string_lossy().to_string(),
+        ],
+        policy,
+        std::env::current_dir().expect("should be able to get current dir"),
+        StdioPolicy::RedirectForShellTool,
+        HashMap::new(),
+    )
+    .await
+    .expect("should be able to spawn command under seatbelt");
+    child
+        .wait()
+        .await
+        .expect("should be able to wait for child process")
+        .success()
+}

codex-rs/exec/src/event_processor_with_human_output.rs

@@ -239,6 +239,7 @@ impl EventProcessor for EventProcessorWithHumanOutput {
                     cwd.to_string_lossy(),
                 );
             }
+            EventMsg::ExecCommandOutputDelta(_) => {}
             EventMsg::ExecCommandEnd(ExecCommandEndEvent {
                 call_id,
                 stdout,

codex-rs/linux-sandbox/src/landlock.rs

@@ -36,7 +36,11 @@ pub(crate) fn apply_sandbox_policy_to_current_thread(
     }
 
     if !sandbox_policy.has_full_disk_write_access() {
-        let writable_roots = sandbox_policy.get_writable_roots_with_cwd(cwd);
+        let writable_roots = sandbox_policy
+            .get_writable_roots_with_cwd(cwd)
+            .into_iter()
+            .map(|writable_root| writable_root.root)
+            .collect();
         install_filesystem_landlock_rules_on_current_thread(writable_roots)?;
     }
 

codex-rs/linux-sandbox/tests/landlock.rs

@@ -49,6 +49,7 @@ async fn run_cmd(cmd: &[&str], writable_roots: &[PathBuf], timeout_ms: u64) {
     let sandbox_policy = SandboxPolicy::WorkspaceWrite {
         writable_roots: writable_roots.to_vec(),
         network_access: false,
+        include_default_writable_roots: true,
     };
     let sandbox_program = env!("CARGO_BIN_EXE_codex-linux-sandbox");
     let codex_linux_sandbox_exe = Some(PathBuf::from(sandbox_program));
@@ -59,6 +60,7 @@ async fn run_cmd(cmd: &[&str], writable_roots: &[PathBuf], timeout_ms: u64) {
         ctrl_c,
         &sandbox_policy,
         &codex_linux_sandbox_exe,
+        None,
     )
     .await
     .unwrap();
@@ -149,6 +151,7 @@ async fn assert_network_blocked(cmd: &[&str]) {
         ctrl_c,
         &sandbox_policy,
         &codex_linux_sandbox_exe,
+        None,
     )
     .await;
 

codex-rs/login/src/login_with_chatgpt.py

@@ -686,6 +686,7 @@ LOGIN_SUCCESS_HTML = """<!DOCTYPE html>
         justify-content: center;
         position: relative;
         background: white;
+
         font-family: system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, 'Open Sans', 'Helvetica Neue', sans-serif;
       }
       .inner-container {
@@ -703,6 +704,7 @@ LOGIN_SUCCESS_HTML = """<!DOCTYPE html>
         align-items: center;
         gap: 20px;
         display: flex;
+        margin-top: 15vh;
       }
       .svg-wrapper {
         position: relative;
@@ -710,9 +712,9 @@ LOGIN_SUCCESS_HTML = """<!DOCTYPE html>
       .title {
         text-align: center;
         color: var(--text-primary, #0D0D0D);
-        font-size: 28px;
+        font-size: 32px;
         font-weight: 400;
-        line-height: 36.40px;
+        line-height: 40px;
         word-wrap: break-word;
       }
       .setup-box {
@@ -785,16 +787,26 @@ LOGIN_SUCCESS_HTML = """<!DOCTYPE html>
         word-wrap: break-word;
         text-decoration: none;
       }
+      .logo {
+        display: flex;
+        align-items: center;
+        justify-content: center;
+        width: 4rem;
+        height: 4rem;
+        border-radius: 16px;
+        border: .5px solid rgba(0, 0, 0, 0.1);
+        box-shadow: rgba(0, 0, 0, 0.1) 0px 4px 16px 0px;
+        box-sizing: border-box;
+        background-color: rgb(255, 255, 255);
+      }
     </style>
   </head>
   <body>
     <div class="container">
       <div class="inner-container">
         <div class="content">
-          <div data-svg-wrapper class="svg-wrapper">
-            <svg width="56" height="56" viewBox="0 0 56 56" fill="none" xmlns="http://www.w3.org/2000/svg">
-              <path d="M4.6665 28.0003C4.6665 15.1137 15.1132 4.66699 27.9998 4.66699C40.8865 4.66699 51.3332 15.1137 51.3332 28.0003C51.3332 40.887 40.8865 51.3337 27.9998 51.3337C15.1132 51.3337 4.6665 40.887 4.6665 28.0003ZM37.5093 18.5088C36.4554 17.7672 34.9999 18.0203 34.2583 19.0742L24.8508 32.4427L20.9764 28.1808C20.1095 27.2272 18.6338 27.1569 17.6803 28.0238C16.7267 28.8906 16.6565 30.3664 17.5233 31.3199L23.3566 37.7366C23.833 38.2606 24.5216 38.5399 25.2284 38.4958C25.9353 38.4517 26.5838 38.089 26.9914 37.5098L38.0747 21.7598C38.8163 20.7059 38.5632 19.2504 37.5093 18.5088Z" fill="var(--green-400, #04B84C)"/>
-            </svg>
+          <div class="logo">
+            <svg xmlns="http://www.w3.org/2000/svg" width="32" height="32" fill="none" viewBox="0 0 32 32"><path stroke="#000" stroke-linecap="round" stroke-width="2.484" d="M22.356 19.797H17.17M9.662 12.29l1.979 3.576a.511.511 0 0 1-.005.504l-1.974 3.409M30.758 16c0 8.15-6.607 14.758-14.758 14.758-8.15 0-14.758-6.607-14.758-14.758C1.242 7.85 7.85 1.242 16 1.242c8.15 0 14.758 6.608 14.758 14.758Z"></path></svg>
           </div>
           <div class="title">Signed in to Codex CLI</div>
         </div>

codex-rs/mcp-server/src/codex_tool_runner.rs

@@ -258,6 +258,7 @@ async fn run_codex_tool_session_inner(
                     | EventMsg::McpToolCallBegin(_)
                     | EventMsg::McpToolCallEnd(_)
                     | EventMsg::ExecCommandBegin(_)
+                    | EventMsg::ExecCommandOutputDelta(_)
                     | EventMsg::ExecCommandEnd(_)
                     | EventMsg::BackgroundEvent(_)
                     | EventMsg::PatchApplyBegin(_)

codex-rs/mcp-server/src/conversation_loop.rs

@@ -0,0 +1,121 @@
+use std::sync::Arc;
+
+use crate::exec_approval::handle_exec_approval_request;
+use crate::outgoing_message::OutgoingMessageSender;
+use crate::outgoing_message::OutgoingNotificationMeta;
+use crate::patch_approval::handle_patch_approval_request;
+use codex_core::Codex;
+use codex_core::protocol::AgentMessageEvent;
+use codex_core::protocol::ApplyPatchApprovalRequestEvent;
+use codex_core::protocol::EventMsg;
+use codex_core::protocol::ExecApprovalRequestEvent;
+use mcp_types::RequestId;
+use tracing::error;
+
+pub async fn run_conversation_loop(
+    codex: Arc<Codex>,
+    outgoing: Arc<OutgoingMessageSender>,
+    request_id: RequestId,
+) {
+    let request_id_str = match &request_id {
+        RequestId::String(s) => s.clone(),
+        RequestId::Integer(n) => n.to_string(),
+    };
+
+    // Stream events until the task needs to pause for user interaction or
+    // completes.
+    loop {
+        match codex.next_event().await {
+            Ok(event) => {
+                outgoing
+                    .send_event_as_notification(
+                        &event,
+                        Some(OutgoingNotificationMeta::new(Some(request_id.clone()))),
+                    )
+                    .await;
+
+                match event.msg {
+                    EventMsg::ExecApprovalRequest(ExecApprovalRequestEvent {
+                        command,
+                        cwd,
+                        call_id,
+                        reason: _,
+                    }) => {
+                        handle_exec_approval_request(
+                            command,
+                            cwd,
+                            outgoing.clone(),
+                            codex.clone(),
+                            request_id.clone(),
+                            request_id_str.clone(),
+                            event.id.clone(),
+                            call_id,
+                        )
+                        .await;
+                        continue;
+                    }
+                    EventMsg::Error(_) => {
+                        error!("Codex runtime error");
+                    }
+                    EventMsg::ApplyPatchApprovalRequest(ApplyPatchApprovalRequestEvent {
+                        call_id,
+                        reason,
+                        grant_root,
+                        changes,
+                    }) => {
+                        handle_patch_approval_request(
+                            call_id,
+                            reason,
+                            grant_root,
+                            changes,
+                            outgoing.clone(),
+                            codex.clone(),
+                            request_id.clone(),
+                            request_id_str.clone(),
+                            event.id.clone(),
+                        )
+                        .await;
+                        continue;
+                    }
+                    EventMsg::TaskComplete(_) => {}
+                    EventMsg::SessionConfigured(_) => {
+                        tracing::error!("unexpected SessionConfigured event");
+                    }
+                    EventMsg::AgentMessageDelta(_) => {
+                        // TODO: think how we want to support this in the MCP
+                    }
+                    EventMsg::AgentReasoningDelta(_) => {
+                        // TODO: think how we want to support this in the MCP
+                    }
+                    EventMsg::AgentMessage(AgentMessageEvent { .. }) => {
+                        // TODO: think how we want to support this in the MCP
+                    }
+                    EventMsg::TaskStarted
+                    | EventMsg::TokenCount(_)
+                    | EventMsg::AgentReasoning(_)
+                    | EventMsg::McpToolCallBegin(_)
+                    | EventMsg::McpToolCallEnd(_)
+                    | EventMsg::ExecCommandBegin(_)
+                    | EventMsg::ExecCommandEnd(_)
+                    | EventMsg::BackgroundEvent(_)
+                    | EventMsg::ExecCommandOutputDelta(_)
+                    | EventMsg::PatchApplyBegin(_)
+                    | EventMsg::PatchApplyEnd(_)
+                    | EventMsg::GetHistoryEntryResponse(_)
+                    | EventMsg::PlanUpdate(_)
+                    | EventMsg::ShutdownComplete => {
+                        // For now, we do not do anything extra for these
+                        // events. Note that
+                        // send(codex_event_to_notification(&event)) above has
+                        // already dispatched these events as notifications,
+                        // though we may want to do give different treatment to
+                        // individual events in the future.
+                    }
+                }
+            }
+            Err(e) => {
+                error!("Codex runtime error: {e}");
+            }
+        }
+    }
+}

codex-rs/mcp-server/src/lib.rs

@@ -17,12 +17,14 @@ use tracing_subscriber::EnvFilter;
 
 mod codex_tool_config;
 mod codex_tool_runner;
+mod conversation_loop;
 mod exec_approval;
 mod json_to_toml;
-mod mcp_protocol;
-mod message_processor;
+pub mod mcp_protocol;
+pub(crate) mod message_processor;
 mod outgoing_message;
 mod patch_approval;
+pub(crate) mod tool_handlers;
 
 use crate::message_processor::MessageProcessor;
 use crate::outgoing_message::OutgoingMessage;

codex-rs/mcp-server/src/mcp_protocol.rs

@@ -7,7 +7,10 @@ use serde::Serialize;
 use strum_macros::Display;
 use uuid::Uuid;
 
+use mcp_types::CallToolResult;
+use mcp_types::ContentBlock;
 use mcp_types::RequestId;
+use mcp_types::TextContent;
 
 #[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
 #[serde(transparent)]
@@ -118,10 +121,47 @@ pub struct ToolCallResponse {
     pub request_id: RequestId,
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub is_error: Option<bool>,
-    #[serde(default, skip_serializing_if = "Option::is_none")]
+    #[serde(default, skip_serializing_if = "Option::is_none", flatten)]
     pub result: Option<ToolCallResponseResult>,
 }
 
+impl From<ToolCallResponse> for CallToolResult {
+    fn from(val: ToolCallResponse) -> Self {
+        let ToolCallResponse {
+            request_id: _request_id,
+            is_error,
+            result,
+        } = val;
+        match result {
+            Some(res) => match serde_json::to_value(&res) {
+                Ok(v) => CallToolResult {
+                    content: vec![ContentBlock::TextContent(TextContent {
+                        r#type: "text".to_string(),
+                        text: v.to_string(),
+                        annotations: None,
+                    })],
+                    is_error,
+                    structured_content: Some(v),
+                },
+                Err(e) => CallToolResult {
+                    content: vec![ContentBlock::TextContent(TextContent {
+                        r#type: "text".to_string(),
+                        text: format!("Failed to serialize tool result: {e}"),
+                        annotations: None,
+                    })],
+                    is_error: Some(true),
+                    structured_content: None,
+                },
+            },
+            None => CallToolResult {
+                content: vec![],
+                is_error,
+                structured_content: None,
+            },
+        }
+    }
+}
+
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
 #[serde(untagged)]
 pub enum ToolCallResponseResult {
@@ -132,17 +172,26 @@ pub enum ToolCallResponseResult {
 }
 
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
-pub struct ConversationCreateResult {
-    pub conversation_id: ConversationId,
-    pub model: String,
+#[serde(untagged)]
+pub enum ConversationCreateResult {
+    Ok {
+        conversation_id: ConversationId,
+        model: String,
+    },
+    Error {
+        message: String,
+    },
 }
 
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
 pub struct ConversationStreamResult {}
 
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
-pub struct ConversationSendMessageResult {
-    pub success: bool,
+// TODO: remove this status because we have is_error field in the response.
+#[serde(tag = "status", rename_all = "camelCase")]
+pub enum ConversationSendMessageResult {
+    Ok,
+    Error { message: String },
 }
 
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
@@ -449,16 +498,19 @@ mod tests {
             request_id: RequestId::Integer(1),
             is_error: None,
             result: Some(ToolCallResponseResult::ConversationCreate(
-                ConversationCreateResult {
+                ConversationCreateResult::Ok {
                     conversation_id: ConversationId(uuid!("d0f6ecbe-84a2-41c1-b23d-b20473b25eab")),
                     model: "o3".into(),
                 },
             )),
         };
-        let observed = to_val(&env);
+        let req_id = env.request_id.clone();
+        let observed = to_val(&CallToolResult::from(env));
         let expected = json!({
-            "requestId": 1,
-            "result": {
+            "content": [
+                { "type": "text", "text": "{\"conversation_id\":\"d0f6ecbe-84a2-41c1-b23d-b20473b25eab\",\"model\":\"o3\"}" }
+            ],
+            "structuredContent": {
                 "conversation_id": "d0f6ecbe-84a2-41c1-b23d-b20473b25eab",
                 "model": "o3"
             }
@@ -467,6 +519,36 @@ mod tests {
             observed, expected,
             "response (ConversationCreate) must match"
         );
+        assert_eq!(req_id, RequestId::Integer(1));
+    }
+
+    #[test]
+    fn response_error_conversation_create_full_schema() {
+        let env = ToolCallResponse {
+            request_id: RequestId::Integer(2),
+            is_error: Some(true),
+            result: Some(ToolCallResponseResult::ConversationCreate(
+                ConversationCreateResult::Error {
+                    message: "Failed to initialize session".into(),
+                },
+            )),
+        };
+        let req_id = env.request_id.clone();
+        let observed = to_val(&CallToolResult::from(env));
+        let expected = json!({
+            "content": [
+                { "type": "text", "text": "{\"message\":\"Failed to initialize session\"}" }
+            ],
+            "isError": true,
+            "structuredContent": {
+                "message": "Failed to initialize session"
+            }
+        });
+        assert_eq!(
+            observed, expected,
+            "error response (ConversationCreate) must match"
+        );
+        assert_eq!(req_id, RequestId::Integer(2));
     }
 
     #[test]
@@ -478,15 +560,17 @@ mod tests {
                 ConversationStreamResult {},
             )),
         };
-        let observed = to_val(&env);
+        let req_id = env.request_id.clone();
+        let observed = to_val(&CallToolResult::from(env));
         let expected = json!({
-            "requestId": 2,
-            "result": {}
+            "content": [ { "type": "text", "text": "{}" } ],
+            "structuredContent": {}
         });
         assert_eq!(
             observed, expected,
             "response (ConversationStream) must have empty object result"
         );
+        assert_eq!(req_id, RequestId::Integer(2));
     }
 
     #[test]
@@ -495,18 +579,20 @@ mod tests {
             request_id: RequestId::Integer(3),
             is_error: None,
             result: Some(ToolCallResponseResult::ConversationSendMessage(
-                ConversationSendMessageResult { success: true },
+                ConversationSendMessageResult::Ok,
             )),
         };
-        let observed = to_val(&env);
+        let req_id = env.request_id.clone();
+        let observed = to_val(&CallToolResult::from(env));
         let expected = json!({
-            "requestId": 3,
-            "result": { "success": true }
+            "content": [ { "type": "text", "text": "{\"status\":\"ok\"}" } ],
+            "structuredContent": { "status": "ok" }
         });
         assert_eq!(
             observed, expected,
             "response (ConversationSendMessageAccepted) must match"
         );
+        assert_eq!(req_id, RequestId::Integer(3));
     }
 
     #[test]
@@ -526,10 +612,13 @@ mod tests {
                 },
             )),
         };
-        let observed = to_val(&env);
+        let req_id = env.request_id.clone();
+        let observed = to_val(&CallToolResult::from(env));
         let expected = json!({
-            "requestId": 4,
-            "result": {
+            "content": [
+                { "type": "text", "text": "{\"conversations\":[{\"conversation_id\":\"67e55044-10b1-426f-9247-bb680e5fe0c8\",\"title\":\"Refactor config loader\"}],\"next_cursor\":\"next123\"}" }
+            ],
+            "structuredContent": {
                 "conversations": [
                     {
                         "conversation_id": "67e55044-10b1-426f-9247-bb680e5fe0c8",
@@ -543,6 +632,7 @@ mod tests {
             observed, expected,
             "response (ConversationsList with cursor) must match"
         );
+        assert_eq!(req_id, RequestId::Integer(4));
     }
 
     #[test]
@@ -552,15 +642,17 @@ mod tests {
             is_error: Some(true),
             result: None,
         };
-        let observed = to_val(&env);
+        let req_id = env.request_id.clone();
+        let observed = to_val(&CallToolResult::from(env));
         let expected = json!({
-            "requestId": 4,
+            "content": [],
             "isError": true
         });
         assert_eq!(
             observed, expected,
             "error response must omit `result` and include `isError`"
         );
+        assert_eq!(req_id, RequestId::Integer(4));
     }
 
     // ----- Notifications -----

codex-rs/mcp-server/src/message_processor.rs

@@ -1,4 +1,5 @@
 use std::collections::HashMap;
+use std::collections::HashSet;
 use std::path::PathBuf;
 use std::sync::Arc;
 
@@ -6,11 +7,17 @@ use crate::codex_tool_config::CodexToolCallParam;
 use crate::codex_tool_config::CodexToolCallReplyParam;
 use crate::codex_tool_config::create_tool_for_codex_tool_call_param;
 use crate::codex_tool_config::create_tool_for_codex_tool_call_reply_param;
+use crate::mcp_protocol::ToolCallRequestParams;
+use crate::mcp_protocol::ToolCallResponse;
+use crate::mcp_protocol::ToolCallResponseResult;
 use crate::outgoing_message::OutgoingMessageSender;
+use crate::tool_handlers::create_conversation::handle_create_conversation;
+use crate::tool_handlers::send_message::handle_send_message;
 
 use codex_core::Codex;
 use codex_core::config::Config as CodexConfig;
 use codex_core::protocol::Submission;
+use mcp_types::CallToolRequest;
 use mcp_types::CallToolRequestParams;
 use mcp_types::CallToolResult;
 use mcp_types::ClientRequest;
@@ -37,6 +44,7 @@ pub(crate) struct MessageProcessor {
     codex_linux_sandbox_exe: Option<PathBuf>,
     session_map: Arc<Mutex<HashMap<Uuid, Arc<Codex>>>>,
     running_requests_id_to_codex_uuid: Arc<Mutex<HashMap<RequestId, Uuid>>>,
+    running_session_ids: Arc<Mutex<HashSet<Uuid>>>,
 }
 
 impl MessageProcessor {
@@ -52,9 +60,22 @@ impl MessageProcessor {
             codex_linux_sandbox_exe,
             session_map: Arc::new(Mutex::new(HashMap::new())),
             running_requests_id_to_codex_uuid: Arc::new(Mutex::new(HashMap::new())),
+            running_session_ids: Arc::new(Mutex::new(HashSet::new())),
         }
     }
 
+    pub(crate) fn session_map(&self) -> Arc<Mutex<HashMap<Uuid, Arc<Codex>>>> {
+        self.session_map.clone()
+    }
+
+    pub(crate) fn outgoing(&self) -> Arc<OutgoingMessageSender> {
+        self.outgoing.clone()
+    }
+
+    pub(crate) fn running_session_ids(&self) -> Arc<Mutex<HashSet<Uuid>>> {
+        self.running_session_ids.clone()
+    }
+
     pub(crate) async fn process_request(&mut self, request: JSONRPCRequest) {
         // Hold on to the ID so we can respond.
         let request_id = request.id.clone();
@@ -300,6 +321,14 @@ impl MessageProcessor {
         params: <mcp_types::CallToolRequest as mcp_types::ModelContextProtocolRequest>::Params,
     ) {
         tracing::info!("tools/call -> params: {:?}", params);
+        // Serialize params into JSON and try to parse as new type
+        if let Ok(new_params) =
+            serde_json::to_value(&params).and_then(serde_json::from_value::<ToolCallRequestParams>)
+        {
+            // New tool call matched → forward
+            self.handle_new_tool_calls(id, new_params).await;
+            return;
+        }
         let CallToolRequestParams { name, arguments } = params;
 
         match name.as_str() {
@@ -323,6 +352,29 @@ impl MessageProcessor {
             }
         }
     }
+    async fn handle_new_tool_calls(&self, request_id: RequestId, params: ToolCallRequestParams) {
+        match params {
+            ToolCallRequestParams::ConversationCreate(args) => {
+                handle_create_conversation(self, request_id, args).await;
+            }
+            ToolCallRequestParams::ConversationSendMessage(args) => {
+                handle_send_message(self, request_id, args).await;
+            }
+            _ => {
+                let result = CallToolResult {
+                    content: vec![ContentBlock::TextContent(TextContent {
+                        r#type: "text".to_string(),
+                        text: "Unknown tool".to_string(),
+                        annotations: None,
+                    })],
+                    is_error: Some(true),
+                    structured_content: None,
+                };
+                self.send_response::<CallToolRequest>(request_id, result)
+                    .await;
+            }
+        }
+    }
 
     async fn handle_tool_call_codex(&self, id: RequestId, arguments: Option<serde_json::Value>) {
         let (initial_prompt, config): (String, CodexConfig) = match arguments {
@@ -631,4 +683,20 @@ impl MessageProcessor {
     ) {
         tracing::info!("notifications/message -> params: {:?}", params);
     }
+
+    pub(crate) async fn send_response_with_optional_error(
+        &self,
+        id: RequestId,
+        message: Option<ToolCallResponseResult>,
+        error: Option<bool>,
+    ) {
+        let response = ToolCallResponse {
+            request_id: id.clone(),
+            is_error: error,
+            result: message,
+        };
+        let result: CallToolResult = response.into();
+        self.send_response::<mcp_types::CallToolRequest>(id.clone(), result)
+            .await;
+    }
 }

codex-rs/mcp-server/src/tool_handlers/create_conversation.rs

@@ -0,0 +1,160 @@
+use std::collections::HashMap;
+use std::path::PathBuf;
+use std::sync::Arc;
+
+use codex_core::Codex;
+use codex_core::codex_wrapper::init_codex;
+use codex_core::config::Config as CodexConfig;
+use codex_core::config::ConfigOverrides;
+use codex_core::protocol::EventMsg;
+use codex_core::protocol::SessionConfiguredEvent;
+use mcp_types::RequestId;
+use tokio::sync::Mutex;
+use uuid::Uuid;
+
+use crate::conversation_loop::run_conversation_loop;
+use crate::json_to_toml::json_to_toml;
+use crate::mcp_protocol::ConversationCreateArgs;
+use crate::mcp_protocol::ConversationCreateResult;
+use crate::mcp_protocol::ConversationId;
+use crate::mcp_protocol::ToolCallResponseResult;
+use crate::message_processor::MessageProcessor;
+
+pub(crate) async fn handle_create_conversation(
+    message_processor: &MessageProcessor,
+    id: RequestId,
+    args: ConversationCreateArgs,
+) {
+    // Build ConfigOverrides from args
+    let ConversationCreateArgs {
+        prompt: _, // not used here; creation only establishes the session
+        model,
+        cwd,
+        approval_policy,
+        sandbox,
+        config,
+        profile,
+        base_instructions,
+    } = args;
+
+    // Convert config overrides JSON into CLI-style TOML overrides
+    let cli_overrides: Vec<(String, toml::Value)> = match config {
+        Some(v) => match v.as_object() {
+            Some(map) => map
+                .into_iter()
+                .map(|(k, v)| (k.clone(), json_to_toml(v.clone())))
+                .collect(),
+            None => Vec::new(),
+        },
+        None => Vec::new(),
+    };
+
+    let overrides = ConfigOverrides {
+        model: Some(model.clone()),
+        cwd: Some(PathBuf::from(cwd)),
+        approval_policy,
+        sandbox_mode: sandbox,
+        model_provider: None,
+        config_profile: profile,
+        codex_linux_sandbox_exe: None,
+        base_instructions,
+        include_plan_tool: None,
+    };
+
+    let cfg: CodexConfig = match CodexConfig::load_with_cli_overrides(cli_overrides, overrides) {
+        Ok(cfg) => cfg,
+        Err(e) => {
+            message_processor
+                .send_response_with_optional_error(
+                    id,
+                    Some(ToolCallResponseResult::ConversationCreate(
+                        ConversationCreateResult::Error {
+                            message: format!("Failed to load config: {e}"),
+                        },
+                    )),
+                    Some(true),
+                )
+                .await;
+            return;
+        }
+    };
+
+    // Initialize Codex session
+    let codex_conversation = match init_codex(cfg).await {
+        Ok(conv) => conv,
+        Err(e) => {
+            message_processor
+                .send_response_with_optional_error(
+                    id,
+                    Some(ToolCallResponseResult::ConversationCreate(
+                        ConversationCreateResult::Error {
+                            message: format!("Failed to initialize session: {e}"),
+                        },
+                    )),
+                    Some(true),
+                )
+                .await;
+            return;
+        }
+    };
+
+    // Expect SessionConfigured; if not, return error.
+    let EventMsg::SessionConfigured(SessionConfiguredEvent { model, .. }) =
+        &codex_conversation.session_configured.msg
+    else {
+        message_processor
+            .send_response_with_optional_error(
+                id,
+                Some(ToolCallResponseResult::ConversationCreate(
+                    ConversationCreateResult::Error {
+                        message: "Expected SessionConfigured event".to_string(),
+                    },
+                )),
+                Some(true),
+            )
+            .await;
+        return;
+    };
+
+    let effective_model = model.clone();
+
+    let session_id = codex_conversation.session_id;
+    let codex_arc = Arc::new(codex_conversation.codex);
+
+    // Store session for future calls
+    insert_session(
+        session_id,
+        codex_arc.clone(),
+        message_processor.session_map(),
+    )
+    .await;
+    // Run the conversation loop in the background so this request can return immediately.
+    let outgoing = message_processor.outgoing();
+    let spawn_id = id.clone();
+    tokio::spawn(async move {
+        run_conversation_loop(codex_arc.clone(), outgoing, spawn_id).await;
+    });
+
+    // Reply with the new conversation id and effective model
+    message_processor
+        .send_response_with_optional_error(
+            id,
+            Some(ToolCallResponseResult::ConversationCreate(
+                ConversationCreateResult::Ok {
+                    conversation_id: ConversationId(session_id),
+                    model: effective_model,
+                },
+            )),
+            Some(false),
+        )
+        .await;
+}
+
+async fn insert_session(
+    session_id: Uuid,
+    codex: Arc<Codex>,
+    session_map: Arc<Mutex<HashMap<Uuid, Arc<Codex>>>>,
+) {
+    let mut guard = session_map.lock().await;
+    guard.insert(session_id, codex);
+}

codex-rs/mcp-server/src/tool_handlers/mod.rs

@@ -0,0 +1,2 @@
+pub(crate) mod create_conversation;
+pub(crate) mod send_message;

codex-rs/mcp-server/src/tool_handlers/send_message.rs

@@ -0,0 +1,124 @@
+use std::collections::HashMap;
+use std::sync::Arc;
+
+use codex_core::Codex;
+use codex_core::protocol::Op;
+use codex_core::protocol::Submission;
+use mcp_types::RequestId;
+use tokio::sync::Mutex;
+use uuid::Uuid;
+
+use crate::mcp_protocol::ConversationSendMessageArgs;
+use crate::mcp_protocol::ConversationSendMessageResult;
+use crate::mcp_protocol::ToolCallResponseResult;
+use crate::message_processor::MessageProcessor;
+
+pub(crate) async fn handle_send_message(
+    message_processor: &MessageProcessor,
+    id: RequestId,
+    arguments: ConversationSendMessageArgs,
+) {
+    let ConversationSendMessageArgs {
+        conversation_id,
+        content: items,
+        parent_message_id: _,
+        conversation_overrides: _,
+    } = arguments;
+
+    if items.is_empty() {
+        message_processor
+            .send_response_with_optional_error(
+                id,
+                Some(ToolCallResponseResult::ConversationSendMessage(
+                    ConversationSendMessageResult::Error {
+                        message: "No content items provided".to_string(),
+                    },
+                )),
+                Some(true),
+            )
+            .await;
+        return;
+    }
+
+    let session_id = conversation_id.0;
+    let Some(codex) = get_session(session_id, message_processor.session_map()).await else {
+        message_processor
+            .send_response_with_optional_error(
+                id,
+                Some(ToolCallResponseResult::ConversationSendMessage(
+                    ConversationSendMessageResult::Error {
+                        message: "Session does not exist".to_string(),
+                    },
+                )),
+                Some(true),
+            )
+            .await;
+        return;
+    };
+
+    let running = {
+        let running_sessions = message_processor.running_session_ids();
+        let mut running_sessions = running_sessions.lock().await;
+        !running_sessions.insert(session_id)
+    };
+
+    if running {
+        message_processor
+            .send_response_with_optional_error(
+                id,
+                Some(ToolCallResponseResult::ConversationSendMessage(
+                    ConversationSendMessageResult::Error {
+                        message: "Session is already running".to_string(),
+                    },
+                )),
+                Some(true),
+            )
+            .await;
+        return;
+    }
+
+    let request_id_string = match &id {
+        RequestId::String(s) => s.clone(),
+        RequestId::Integer(i) => i.to_string(),
+    };
+
+    let submit_res = codex
+        .submit_with_id(Submission {
+            id: request_id_string,
+            op: Op::UserInput { items },
+        })
+        .await;
+
+    if let Err(e) = submit_res {
+        message_processor
+            .send_response_with_optional_error(
+                id,
+                Some(ToolCallResponseResult::ConversationSendMessage(
+                    ConversationSendMessageResult::Error {
+                        message: format!("Failed to submit user input: {e}"),
+                    },
+                )),
+                Some(true),
+            )
+            .await;
+        return;
+    }
+
+    message_processor
+        .send_response_with_optional_error(
+            id,
+            Some(ToolCallResponseResult::ConversationSendMessage(
+                ConversationSendMessageResult::Ok,
+            )),
+            Some(false),
+        )
+        .await;
+}
+
+pub(crate) async fn get_session(
+    session_id: Uuid,
+    session_map: Arc<Mutex<HashMap<Uuid, Arc<Codex>>>>,
+) -> Option<Arc<Codex>> {
+    let guard = session_map.lock().await;
+    guard.get(&session_id).cloned()
+}

codex-rs/mcp-server/tests/common/Cargo.toml

@@ -10,6 +10,7 @@ path = "lib.rs"
 anyhow = "1"
 assert_cmd = "2"
 codex-mcp-server = { path = "../.." }
+codex-core = { path = "../../../core" }
 mcp-types = { path = "../../../mcp-types" }
 pretty_assertions = "1.4.1"
 serde_json = "1"
@@ -22,3 +23,4 @@ tokio = { version = "1", features = [
     "rt-multi-thread",
 ] }
 wiremock = "0.6"
+uuid = { version = "1", features = ["serde", "v4"] }

codex-rs/mcp-server/tests/common/mcp_process.rs

@@ -11,8 +11,14 @@ use tokio::process::ChildStdout;
 
 use anyhow::Context;
 use assert_cmd::prelude::*;
+use codex_core::protocol::InputItem;
 use codex_mcp_server::CodexToolCallParam;
 use codex_mcp_server::CodexToolCallReplyParam;
+use codex_mcp_server::mcp_protocol::ConversationCreateArgs;
+use codex_mcp_server::mcp_protocol::ConversationId;
+use codex_mcp_server::mcp_protocol::ConversationSendMessageArgs;
+use codex_mcp_server::mcp_protocol::ToolCallRequestParams;
+
 use mcp_types::CallToolRequestParams;
 use mcp_types::ClientCapabilities;
 use mcp_types::Implementation;
@@ -29,6 +35,7 @@ use pretty_assertions::assert_eq;
 use serde_json::json;
 use std::process::Command as StdCommand;
 use tokio::process::Command;
+use uuid::Uuid;
 
 pub struct McpProcess {
     next_request_id: AtomicI64,
@@ -174,6 +181,61 @@ impl McpProcess {
         .await
     }
 
+    pub async fn send_user_message_tool_call(
+        &mut self,
+        message: &str,
+        session_id: &str,
+    ) -> anyhow::Result<i64> {
+        let params = ToolCallRequestParams::ConversationSendMessage(ConversationSendMessageArgs {
+            conversation_id: ConversationId(Uuid::parse_str(session_id)?),
+            content: vec![InputItem::Text {
+                text: message.to_string(),
+            }],
+            parent_message_id: None,
+            conversation_overrides: None,
+        });
+        self.send_request(
+            mcp_types::CallToolRequest::METHOD,
+            Some(serde_json::to_value(params)?),
+        )
+        .await
+    }
+
+    pub async fn send_conversation_create_tool_call(
+        &mut self,
+        prompt: &str,
+        model: &str,
+        cwd: &str,
+    ) -> anyhow::Result<i64> {
+        let params = ToolCallRequestParams::ConversationCreate(ConversationCreateArgs {
+            prompt: prompt.to_string(),
+            model: model.to_string(),
+            cwd: cwd.to_string(),
+            approval_policy: None,
+            sandbox: None,
+            config: None,
+            profile: None,
+            base_instructions: None,
+        });
+        self.send_request(
+            mcp_types::CallToolRequest::METHOD,
+            Some(serde_json::to_value(params)?),
+        )
+        .await
+    }
+
+    pub async fn send_conversation_create_with_args(
+        &mut self,
+        args: ConversationCreateArgs,
+    ) -> anyhow::Result<i64> {
+        let params = ToolCallRequestParams::ConversationCreate(args);
+        self.send_request(
+            mcp_types::CallToolRequest::METHOD,
+            Some(serde_json::to_value(params)?),
+        )
+        .await
+    }
+
     async fn send_request(
         &mut self,
         method: &str,

codex-rs/mcp-server/tests/create_conversation.rs

@@ -0,0 +1,128 @@
+#![allow(clippy::expect_used, clippy::unwrap_used)]
+
+use std::path::Path;
+
+use mcp_test_support::McpProcess;
+use mcp_test_support::create_final_assistant_message_sse_response;
+use mcp_test_support::create_mock_chat_completions_server;
+use mcp_types::JSONRPCResponse;
+use mcp_types::RequestId;
+use pretty_assertions::assert_eq;
+use serde_json::json;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn test_conversation_create_and_send_message_ok() {
+    // Mock server – we won't strictly rely on it, but provide one to satisfy any model wiring.
+    let responses = vec![
+        create_final_assistant_message_sse_response("Done").expect("build mock assistant message"),
+    ];
+    let server = create_mock_chat_completions_server(responses).await;
+
+    // Temporary Codex home with config pointing at the mock server.
+    let codex_home = TempDir::new().expect("create temp dir");
+    create_config_toml(codex_home.path(), &server.uri()).expect("write config.toml");
+
+    // Start MCP server process and initialize.
+    let mut mcp = McpProcess::new(codex_home.path())
+        .await
+        .expect("spawn mcp process");
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
+        .await
+        .expect("init timeout")
+        .expect("init failed");
+
+    // Create a conversation via the new tool.
+    let req_id = mcp
+        .send_conversation_create_tool_call("", "o3", "/repo")
+        .await
+        .expect("send conversationCreate");
+
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(req_id)),
+    )
+    .await
+    .expect("create response timeout")
+    .expect("create response error");
+
+    // Structured content must include status=ok, a UUID conversation_id and the model we passed.
+    let sc = &resp.result["structuredContent"];
+    let conv_id = sc["conversation_id"].as_str().expect("uuid string");
+    assert!(!conv_id.is_empty());
+    assert_eq!(sc["model"], json!("o3"));
+
+    // Now send a message to the created conversation and expect an OK result.
+    let send_id = mcp
+        .send_user_message_tool_call("Hello", conv_id)
+        .await
+        .expect("send message");
+
+    let send_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(send_id)),
+    )
+    .await
+    .expect("send response timeout")
+    .expect("send response error");
+    assert_eq!(
+        send_resp.result["structuredContent"],
+        json!({ "status": "ok" })
+    );
+
+    // avoid race condition by waiting for the mock server to receive the chat.completions request
+    let deadline = std::time::Instant::now() + DEFAULT_READ_TIMEOUT;
+    loop {
+        let requests = server.received_requests().await.unwrap_or_default();
+        if !requests.is_empty() {
+            break;
+        }
+        if std::time::Instant::now() >= deadline {
+            panic!("mock server did not receive the chat.completions request in time");
+        }
+        tokio::time::sleep(std::time::Duration::from_millis(10)).await;
+    }
+
+    // Verify the outbound request body matches expectations for Chat Completions.
+    let request = &server.received_requests().await.unwrap()[0];
+    let body = request
+        .body_json::<serde_json::Value>()
+        .expect("parse request body as JSON");
+    assert_eq!(body["model"], json!("o3"));
+    assert!(body["stream"].as_bool().unwrap_or(false));
+    let messages = body["messages"]
+        .as_array()
+        .expect("messages should be array");
+    let last = messages.last().expect("at least one message");
+    assert_eq!(last["role"], json!("user"));
+    assert_eq!(last["content"], json!("Hello"));
+
+    drop(server);
+}
+
+// Helper to create a config.toml pointing at the mock model server.
+fn create_config_toml(codex_home: &Path, server_uri: &str) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(
+        config_toml,
+        format!(
+            r#"
+model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "danger-full-access"
+
+model_provider = "mock_provider"
+
+[model_providers.mock_provider]
+name = "Mock provider for test"
+base_url = "{server_uri}/v1"
+wire_api = "chat"
+request_max_retries = 0
+stream_max_retries = 0
+"#
+        ),
+    )
+}

codex-rs/mcp-server/tests/send_message.rs

@@ -0,0 +1,163 @@
+#![allow(clippy::expect_used)]
+
+use std::path::Path;
+use std::thread::sleep;
+use std::time::Duration;
+
+use codex_mcp_server::CodexToolCallParam;
+use mcp_test_support::McpProcess;
+use mcp_test_support::create_final_assistant_message_sse_response;
+use mcp_test_support::create_mock_chat_completions_server;
+use mcp_types::JSONRPC_VERSION;
+use mcp_types::JSONRPCResponse;
+use mcp_types::RequestId;
+use pretty_assertions::assert_eq;
+use serde_json::json;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn test_send_message_success() {
+    // Spin up a mock completions server that immediately ends the Codex turn.
+    // Two Codex turns hit the mock model (session start + send-user-message). Provide two SSE responses.
+    let responses = vec![
+        create_final_assistant_message_sse_response("Done").expect("build mock assistant message"),
+        create_final_assistant_message_sse_response("Done").expect("build mock assistant message"),
+    ];
+    let server = create_mock_chat_completions_server(responses).await;
+
+    // Create a temporary Codex home with config pointing at the mock server.
+    let codex_home = TempDir::new().expect("create temp dir");
+    create_config_toml(codex_home.path(), &server.uri()).expect("write config.toml");
+
+    // Start MCP server process and initialize.
+    let mut mcp_process = McpProcess::new(codex_home.path())
+        .await
+        .expect("spawn mcp process");
+    timeout(DEFAULT_READ_TIMEOUT, mcp_process.initialize())
+        .await
+        .expect("init timed out")
+        .expect("init failed");
+
+    // Kick off a Codex session so we have a valid session_id.
+    let codex_request_id = mcp_process
+        .send_codex_tool_call(CodexToolCallParam {
+            prompt: "Start a session".to_string(),
+            ..Default::default()
+        })
+        .await
+        .expect("send codex tool call");
+
+    // Wait for the session_configured event to get the session_id.
+    let session_id = mcp_process
+        .read_stream_until_configured_response_message()
+        .await
+        .expect("read session_configured");
+
+    // The original codex call will finish quickly given our mock; consume its response.
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp_process.read_stream_until_response_message(RequestId::Integer(codex_request_id)),
+    )
+    .await
+    .expect("codex response timeout")
+    .expect("codex response error");
+
+    // Now exercise the send-user-message tool.
+    let send_msg_request_id = mcp_process
+        .send_user_message_tool_call("Hello again", &session_id)
+        .await
+        .expect("send send-message tool call");
+
+    let response: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp_process.read_stream_until_response_message(RequestId::Integer(send_msg_request_id)),
+    )
+    .await
+    .expect("send-user-message response timeout")
+    .expect("send-user-message response error");
+
+    assert_eq!(
+        JSONRPCResponse {
+            jsonrpc: JSONRPC_VERSION.into(),
+            id: RequestId::Integer(send_msg_request_id),
+            result: json!({
+                "content": [
+                    {
+                        "text": "{\"status\":\"ok\"}",
+                        "type": "text",
+                    }
+                ],
+                "isError": false,
+                "structuredContent": {
+                    "status": "ok"
+                }
+            }),
+        },
+        response
+    );
+    // wait for the server to hear the user message
+    sleep(Duration::from_secs(1));
+
+    // Ensure the server and tempdir live until end of test
+    drop(server);
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn test_send_message_session_not_found() {
+    // Start MCP without creating a Codex session
+    let codex_home = TempDir::new().expect("tempdir");
+    let mut mcp = McpProcess::new(codex_home.path()).await.expect("spawn");
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
+        .await
+        .expect("timeout")
+        .expect("init");
+
+    let unknown = uuid::Uuid::new_v4().to_string();
+    let req_id = mcp
+        .send_user_message_tool_call("ping", &unknown)
+        .await
+        .expect("send tool");
+
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(req_id)),
+    )
+    .await
+    .expect("timeout")
+    .expect("resp");
+
+    let result = resp.result.clone();
+    let content = result["content"][0]["text"].as_str().unwrap_or("");
+    assert!(content.contains("Session does not exist"));
+    assert_eq!(result["isError"], json!(true));
+}
+
+// ---------------------------------------------------------------------------
+// Helpers
+// ---------------------------------------------------------------------------
+
+fn create_config_toml(codex_home: &Path, server_uri: &str) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(
+        config_toml,
+        format!(
+            r#"
+model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "danger-full-access"
+
+model_provider = "mock_provider"
+
+[model_providers.mock_provider]
+name = "Mock provider for test"
+base_url = "{server_uri}/v1"
+wire_api = "chat"
+request_max_retries = 0
+stream_max_retries = 0
+"#
+        ),
+    )
+}

codex-rs/tui/Cargo.toml

@@ -17,6 +17,7 @@ workspace = true
 [dependencies]
 anyhow = "1"
 base64 = "0.22.1"
+chrono = { version = "0.4", features = ["serde"] }
 clap = { version = "4", features = ["derive"] }
 codex-ansi-escape = { path = "../ansi-escape" }
 codex-arg0 = { path = "../arg0" }
@@ -41,6 +42,8 @@ ratatui = { version = "0.29.0", features = [
 ] }
 ratatui-image = "8.0.0"
 regex-lite = "0.1"
+reqwest = { version = "0.12", features = ["json"] }
+serde = { version = "1", features = ["derive"] }
 serde_json = { version = "1", features = ["preserve_order"] }
 shlex = "1.3.0"
 strum = "0.27.2"
@@ -62,6 +65,8 @@ unicode-segmentation = "1.12.0"
 unicode-width = "0.1"
 uuid = "1"
 
+
+
 [dev-dependencies]
 insta = "1.43.1"
 pretty_assertions = "1"

codex-rs/tui/src/app.rs

@@ -10,13 +10,16 @@ use crate::tui;
 use codex_core::config::Config;
 use codex_core::protocol::Event;
 use codex_core::protocol::EventMsg;
-use codex_core::protocol::ExecApprovalRequestEvent;
+use codex_core::protocol::Op;
 use color_eyre::eyre::Result;
 use crossterm::SynchronizedUpdate;
 use crossterm::event::KeyCode;
 use crossterm::event::KeyEvent;
+use crossterm::event::KeyEventKind;
+use crossterm::terminal::supports_keyboard_enhancement;
 use ratatui::layout::Offset;
 use ratatui::prelude::Backend;
+use ratatui::text::Line;
 use std::path::PathBuf;
 use std::sync::Arc;
 use std::sync::atomic::AtomicBool;
@@ -55,9 +58,13 @@ pub(crate) struct App<'a> {
     /// True when a redraw has been scheduled but not yet executed.
     pending_redraw: Arc<AtomicBool>,
 
+    pending_history_lines: Vec<Line<'static>>,
+
     /// Stored parameters needed to instantiate the ChatWidget later, e.g.,
     /// after dismissing the Git-repo warning.
     chat_args: Option<ChatWidgetArgs>,
+
+    enhanced_keys_supported: bool,
 }
 
 /// Aggregate parameters needed to create a `ChatWidget`, as creation may be
@@ -67,6 +74,7 @@ struct ChatWidgetArgs {
     config: Config,
     initial_prompt: Option<String>,
     initial_images: Vec<PathBuf>,
+    enhanced_keys_supported: bool,
 }
 
 impl App<'_> {
@@ -80,6 +88,8 @@ impl App<'_> {
         let app_event_tx = AppEventSender::new(app_event_tx);
         let pending_redraw = Arc::new(AtomicBool::new(false));
 
+        let enhanced_keys_supported = supports_keyboard_enhancement().unwrap_or(false);
+
         // Spawn a dedicated thread for reading the crossterm event loop and
         // re-publishing the events as AppEvents, as appropriate.
         {
@@ -96,9 +106,7 @@ impl App<'_> {
                         if let Ok(event) = crossterm::event::read() {
                             match event {
                                 crossterm::event::Event::Key(key_event) => {
-                                    if key_event.kind == crossterm::event::KeyEventKind::Press {
-                                        app_event_tx.send(AppEvent::KeyEvent(key_event));
-                                    }
+                                    app_event_tx.send(AppEvent::KeyEvent(key_event));
                                 }
                                 crossterm::event::Event::Resize(_, _) => {
                                     app_event_tx.send(AppEvent::RequestRedraw);
@@ -134,6 +142,7 @@ impl App<'_> {
                     config: config.clone(),
                     initial_prompt,
                     initial_images,
+                    enhanced_keys_supported,
                 }),
             )
         } else {
@@ -142,6 +151,7 @@ impl App<'_> {
                 app_event_tx.clone(),
                 initial_prompt,
                 initial_images,
+                enhanced_keys_supported,
             );
             (
                 AppState::Chat {
@@ -154,12 +164,14 @@ impl App<'_> {
         let file_search = FileSearchManager::new(config.cwd.clone(), app_event_tx.clone());
         Self {
             app_event_tx,
+            pending_history_lines: Vec::new(),
             app_event_rx,
             app_state,
             config,
             file_search,
             pending_redraw,
             chat_args,
+            enhanced_keys_supported,
         }
     }
 
@@ -199,7 +211,7 @@ impl App<'_> {
         while let Ok(event) = self.app_event_rx.recv() {
             match event {
                 AppEvent::InsertHistory(lines) => {
-                    crate::insert_history::insert_history_lines(terminal, lines);
+                    self.pending_history_lines.extend(lines);
                     self.app_event_tx.send(AppEvent::RequestRedraw);
                 }
                 AppEvent::RequestRedraw => {
@@ -213,6 +225,7 @@ impl App<'_> {
                         KeyEvent {
                             code: KeyCode::Char('c'),
                             modifiers: crossterm::event::KeyModifiers::CONTROL,
+                            kind: KeyEventKind::Press,
                             ..
                         } => {
                             match &mut self.app_state {
@@ -227,6 +240,7 @@ impl App<'_> {
                         KeyEvent {
                             code: KeyCode::Char('d'),
                             modifiers: crossterm::event::KeyModifiers::CONTROL,
+                            kind: KeyEventKind::Press,
                             ..
                         } => {
                             match &mut self.app_state {
@@ -245,9 +259,15 @@ impl App<'_> {
                                 }
                             }
                         }
-                        _ => {
+                        KeyEvent {
+                            kind: KeyEventKind::Press | KeyEventKind::Repeat,
+                            ..
+                        } => {
                             self.dispatch_key_event(key_event);
                         }
+                        _ => {
+                            // Ignore Release key events for now.
+                        }
                     };
                 }
                 AppEvent::Paste(text) => {
@@ -274,10 +294,17 @@ impl App<'_> {
                             self.app_event_tx.clone(),
                             None,
                             Vec::new(),
+                            self.enhanced_keys_supported,
                         ));
                         self.app_state = AppState::Chat { widget: new_widget };
                         self.app_event_tx.send(AppEvent::RequestRedraw);
                     }
+                    SlashCommand::Compact => {
+                        if let AppState::Chat { widget } = &mut self.app_state {
+                            widget.clear_token_usage();
+                            self.app_event_tx.send(AppEvent::CodexOp(Op::Compact));
+                        }
+                    }
                     SlashCommand::Quit => {
                         break;
                     }
@@ -304,14 +331,41 @@ impl App<'_> {
                     }
                     #[cfg(debug_assertions)]
                     SlashCommand::TestApproval => {
+                        use std::collections::HashMap;
+
+                        use codex_core::protocol::ApplyPatchApprovalRequestEvent;
+                        use codex_core::protocol::FileChange;
+
                         self.app_event_tx.send(AppEvent::CodexEvent(Event {
                             id: "1".to_string(),
-                            msg: EventMsg::ExecApprovalRequest(ExecApprovalRequestEvent {
-                                call_id: "1".to_string(),
-                                command: vec!["git".into(), "apply".into()],
-                                cwd: self.config.cwd.clone(),
-                                reason: Some("test".to_string()),
-                            }),
+                            // msg: EventMsg::ExecApprovalRequest(ExecApprovalRequestEvent {
+                            //     call_id: "1".to_string(),
+                            //     command: vec!["git".into(), "apply".into()],
+                            //     cwd: self.config.cwd.clone(),
+                            //     reason: Some("test".to_string()),
+                            // }),
+                            msg: EventMsg::ApplyPatchApprovalRequest(
+                                ApplyPatchApprovalRequestEvent {
+                                    call_id: "1".to_string(),
+                                    changes: HashMap::from([
+                                        (
+                                            PathBuf::from("/tmp/test.txt"),
+                                            FileChange::Add {
+                                                content: "test".to_string(),
+                                            },
+                                        ),
+                                        (
+                                            PathBuf::from("/tmp/test2.txt"),
+                                            FileChange::Update {
+                                                unified_diff: "+test\n-test2".to_string(),
+                                                move_path: None,
+                                            },
+                                        ),
+                                    ]),
+                                    reason: None,
+                                    grant_root: Some(PathBuf::from("/tmp")),
+                                },
+                            ),
                         }));
                     }
                 },
@@ -363,6 +417,7 @@ impl App<'_> {
             AppState::Chat { widget } => widget.desired_height(size.width),
             AppState::GitWarning { .. } => 10,
         };
+
         let mut area = terminal.viewport_area;
         area.height = desired_height.min(size.height);
         area.width = size.width;
@@ -376,6 +431,13 @@ impl App<'_> {
             terminal.clear()?;
             terminal.set_viewport_area(area);
         }
+        if !self.pending_history_lines.is_empty() {
+            crate::insert_history::insert_history_lines(
+                terminal,
+                self.pending_history_lines.clone(),
+            );
+            self.pending_history_lines.clear();
+        }
         match &mut self.app_state {
             AppState::Chat { widget } => {
                 terminal.draw(|frame| frame.render_widget_ref(&**widget, frame.area()))?;
@@ -407,6 +469,7 @@ impl App<'_> {
                         self.app_event_tx.clone(),
                         args.initial_prompt,
                         args.initial_images,
+                        args.enhanced_keys_supported,
                     ));
                     self.app_state = AppState::Chat { widget };
                     self.app_event_tx.send(AppEvent::RequestRedraw);

codex-rs/tui/src/bottom_pane/approval_modal_view.rs

@@ -99,6 +99,7 @@ mod tests {
         let mut pane = BottomPane::new(super::super::BottomPaneParams {
             app_event_tx: AppEventSender::new(tx_raw2),
             has_input_focus: true,
+            enhanced_keys_supported: false,
         });
         assert_eq!(CancellationEvent::Handled, view.on_ctrl_c(&mut pane));
         assert!(view.queue.is_empty());

codex-rs/tui/src/bottom_pane/chat_composer.rs

@@ -41,6 +41,7 @@ pub(crate) struct ChatComposer<'a> {
     app_event_tx: AppEventSender,
     history: ChatComposerHistory,
     ctrl_c_quit_hint: bool,
+    use_shift_enter_hint: bool,
     dismissed_file_popup_token: Option<String>,
     current_file_query: Option<String>,
     pending_pastes: Vec<(String, String)>,
@@ -54,17 +55,24 @@ enum ActivePopup {
 }
 
 impl ChatComposer<'_> {
-    pub fn new(has_input_focus: bool, app_event_tx: AppEventSender) -> Self {
+    pub fn new(
+        has_input_focus: bool,
+        app_event_tx: AppEventSender,
+        enhanced_keys_supported: bool,
+    ) -> Self {
         let mut textarea = TextArea::default();
         textarea.set_placeholder_text(BASE_PLACEHOLDER_TEXT);
         textarea.set_cursor_line_style(ratatui::style::Style::default());
 
+        let use_shift_enter_hint = enhanced_keys_supported;
+
         let mut this = Self {
             textarea,
             active_popup: ActivePopup::None,
             app_event_tx,
             history: ChatComposerHistory::new(),
             ctrl_c_quit_hint: false,
+            use_shift_enter_hint,
             dismissed_file_popup_token: None,
             current_file_query: None,
             pending_pastes: Vec::new(),
@@ -712,11 +720,16 @@ impl WidgetRef for &ChatComposer<'_> {
                         Span::from(" to quit"),
                     ]
                 } else {
+                    let newline_hint_key = if self.use_shift_enter_hint {
+                        "Shift+⏎"
+                    } else {
+                        "Ctrl+J"
+                    };
                     vec![
                         Span::from(" "),
                         "⏎".set_style(key_hint_style),
                         Span::from(" send   "),
-                        "Shift+⏎".set_style(key_hint_style),
+                        newline_hint_key.set_style(key_hint_style),
                         Span::from(" newline   "),
                         "Ctrl+C".set_style(key_hint_style),
                         Span::from(" quit"),
@@ -890,7 +903,7 @@ mod tests {
 
         let (tx, _rx) = std::sync::mpsc::channel();
         let sender = AppEventSender::new(tx);
-        let mut composer = ChatComposer::new(true, sender);
+        let mut composer = ChatComposer::new(true, sender, false);
 
         let needs_redraw = composer.handle_paste("hello".to_string());
         assert!(needs_redraw);
@@ -913,7 +926,7 @@ mod tests {
 
         let (tx, _rx) = std::sync::mpsc::channel();
         let sender = AppEventSender::new(tx);
-        let mut composer = ChatComposer::new(true, sender);
+        let mut composer = ChatComposer::new(true, sender, false);
 
         let large = "x".repeat(LARGE_PASTE_CHAR_THRESHOLD + 10);
         let needs_redraw = composer.handle_paste(large.clone());
@@ -942,7 +955,7 @@ mod tests {
         let large = "y".repeat(LARGE_PASTE_CHAR_THRESHOLD + 1);
         let (tx, _rx) = std::sync::mpsc::channel();
         let sender = AppEventSender::new(tx);
-        let mut composer = ChatComposer::new(true, sender);
+        let mut composer = ChatComposer::new(true, sender, false);
 
         composer.handle_paste(large);
         assert_eq!(composer.pending_pastes.len(), 1);
@@ -978,7 +991,7 @@ mod tests {
 
         for (name, input) in test_cases {
             // Create a fresh composer for each test case
-            let mut composer = ChatComposer::new(true, sender.clone());
+            let mut composer = ChatComposer::new(true, sender.clone(), false);
 
             if let Some(text) = input {
                 composer.handle_paste(text);
@@ -1015,7 +1028,7 @@ mod tests {
 
         let (tx, _rx) = std::sync::mpsc::channel();
         let sender = AppEventSender::new(tx);
-        let mut composer = ChatComposer::new(true, sender);
+        let mut composer = ChatComposer::new(true, sender, false);
 
         // Define test cases: (paste content, is_large)
         let test_cases = [
@@ -1088,7 +1101,7 @@ mod tests {
 
         let (tx, _rx) = std::sync::mpsc::channel();
         let sender = AppEventSender::new(tx);
-        let mut composer = ChatComposer::new(true, sender);
+        let mut composer = ChatComposer::new(true, sender, false);
 
         // Define test cases: (content, is_large)
         let test_cases = [
@@ -1161,7 +1174,7 @@ mod tests {
 
         let (tx, _rx) = std::sync::mpsc::channel();
         let sender = AppEventSender::new(tx);
-        let mut composer = ChatComposer::new(true, sender);
+        let mut composer = ChatComposer::new(true, sender, false);
 
         // Define test cases: (cursor_position_from_end, expected_pending_count)
         let test_cases = [

codex-rs/tui/src/bottom_pane/mod.rs

@@ -50,12 +50,18 @@ pub(crate) struct BottomPane<'a> {
 pub(crate) struct BottomPaneParams {
     pub(crate) app_event_tx: AppEventSender,
     pub(crate) has_input_focus: bool,
+    pub(crate) enhanced_keys_supported: bool,
 }
 
 impl BottomPane<'_> {
     pub fn new(params: BottomPaneParams) -> Self {
+        let enhanced_keys_supported = params.enhanced_keys_supported;
         Self {
-            composer: ChatComposer::new(params.has_input_focus, params.app_event_tx.clone()),
+            composer: ChatComposer::new(
+                params.has_input_focus,
+                params.app_event_tx.clone(),
+                enhanced_keys_supported,
+            ),
             active_view: None,
             app_event_tx: params.app_event_tx,
             has_input_focus: params.has_input_focus,
@@ -298,6 +304,7 @@ mod tests {
         let mut pane = BottomPane::new(BottomPaneParams {
             app_event_tx: tx,
             has_input_focus: true,
+            enhanced_keys_supported: false,
         });
         pane.push_approval_request(exec_request());
         assert_eq!(CancellationEvent::Handled, pane.on_ctrl_c());

codex-rs/tui/src/bottom_pane/snapshots/codex_tui__bottom_pane__chat_composer__tests__backspace_after_pastes.snap

@@ -11,4 +11,4 @@ expression: terminal.backend()
 "▌                                                                                                   "
 "▌                                                                                                   "
 "▌                                                                                                   "
-" ⏎ send   Shift+⏎ newline   Ctrl+C quit                                                             "
+" ⏎ send   Ctrl+J newline   Ctrl+C quit                                                              "

codex-rs/tui/src/bottom_pane/snapshots/codex_tui__bottom_pane__chat_composer__tests__empty.snap

@@ -11,4 +11,4 @@ expression: terminal.backend()
 "▌                                                                                                   "
 "▌                                                                                                   "
 "▌                                                                                                   "
-" ⏎ send   Shift+⏎ newline   Ctrl+C quit                                                             "
+" ⏎ send   Ctrl+J newline   Ctrl+C quit                                                              "

codex-rs/tui/src/bottom_pane/snapshots/codex_tui__bottom_pane__chat_composer__tests__large.snap

@@ -11,4 +11,4 @@ expression: terminal.backend()
 "▌                                                                                                   "
 "▌                                                                                                   "
 "▌                                                                                                   "
-" ⏎ send   Shift+⏎ newline   Ctrl+C quit                                                             "
+" ⏎ send   Ctrl+J newline   Ctrl+C quit                                                              "

codex-rs/tui/src/bottom_pane/snapshots/codex_tui__bottom_pane__chat_composer__tests__multiple_pastes.snap

@@ -11,4 +11,4 @@ expression: terminal.backend()
 "▌                                                                                                   "
 "▌                                                                                                   "
 "▌                                                                                                   "
-" ⏎ send   Shift+⏎ newline   Ctrl+C quit                                                             "
+" ⏎ send   Ctrl+J newline   Ctrl+C quit                                                              "

codex-rs/tui/src/bottom_pane/snapshots/codex_tui__bottom_pane__chat_composer__tests__small.snap

@@ -11,4 +11,4 @@ expression: terminal.backend()
 "▌                                                                                                   "
 "▌                                                                                                   "
 "▌                                                                                                   "
-" ⏎ send   Shift+⏎ newline   Ctrl+C quit                                                             "
+" ⏎ send   Ctrl+J newline   Ctrl+C quit                                                              "

codex-rs/tui/src/chatwidget.rs

@@ -25,6 +25,7 @@ use codex_core::protocol::PatchApplyBeginEvent;
 use codex_core::protocol::TaskCompleteEvent;
 use codex_core::protocol::TokenUsage;
 use crossterm::event::KeyEvent;
+use crossterm::event::KeyEventKind;
 use ratatui::buffer::Buffer;
 use ratatui::layout::Rect;
 use ratatui::widgets::Widget;
@@ -94,6 +95,7 @@ impl ChatWidget<'_> {
         app_event_tx: AppEventSender,
         initial_prompt: Option<String>,
         initial_images: Vec<PathBuf>,
+        enhanced_keys_supported: bool,
     ) -> Self {
         let (codex_op_tx, mut codex_op_rx) = unbounded_channel::<Op>();
 
@@ -139,6 +141,7 @@ impl ChatWidget<'_> {
             bottom_pane: BottomPane::new(BottomPaneParams {
                 app_event_tx,
                 has_input_focus: true,
+                enhanced_keys_supported,
             }),
             config,
             initial_user_message: create_initial_user_message(
@@ -157,7 +160,9 @@ impl ChatWidget<'_> {
     }
 
     pub(crate) fn handle_key_event(&mut self, key_event: KeyEvent) {
-        self.bottom_pane.clear_ctrl_c_quit_hint();
+        if key_event.kind == KeyEventKind::Press {
+            self.bottom_pane.clear_ctrl_c_quit_hint();
+        }
 
         match self.bottom_pane.handle_key_event(key_event) {
             InputResult::Submitted(text) => {
@@ -369,6 +374,7 @@ impl ChatWidget<'_> {
                 );
                 self.add_to_history(HistoryCell::new_active_exec_command(command));
             }
+            EventMsg::ExecCommandOutputDelta(_) => {}
             EventMsg::PatchApplyBegin(PatchApplyBeginEvent {
                 call_id: _,
                 auto_approved,
@@ -497,6 +503,12 @@ impl ChatWidget<'_> {
     pub(crate) fn token_usage(&self) -> &TokenUsage {
         &self.token_usage
     }
+
+    pub(crate) fn clear_token_usage(&mut self) {
+        self.token_usage = TokenUsage::default();
+        self.bottom_pane
+            .set_token_usage(self.token_usage.clone(), self.config.model_context_window);
+    }
 }
 
 impl WidgetRef for &ChatWidget<'_> {

codex-rs/tui/src/history_cell.rs

@@ -545,24 +545,17 @@ impl HistoryCell {
         } else {
             for (idx, PlanItemArg { step, status }) in plan.into_iter().enumerate() {
                 let num = idx + 1;
-                let (icon, style): (&str, Style) = match status {
-                    StepStatus::Completed => ("✓", Style::default().fg(Color::Green)),
-                    StepStatus::InProgress => (
-                        "▶",
-                        Style::default()
-                            .fg(Color::Yellow)
-                            .add_modifier(Modifier::BOLD),
-                    ),
-                    StepStatus::Pending => ("○", Style::default().fg(Color::Gray)),
+                let icon_span: Span = match status {
+                    StepStatus::Completed => Span::from("✓").fg(Color::Green),
+                    StepStatus::InProgress => Span::from("▶").fg(Color::Yellow).bold(),
+                    StepStatus::Pending => Span::from("○").fg(Color::Gray),
                 };
-                let prefix = vec![
-                    Span::raw(format!("{num:>2}. [")),
-                    Span::styled(icon.to_string(), style),
-                    Span::raw("] "),
-                ];
-                let mut spans = prefix;
-                spans.push(Span::raw(step));
-                lines.push(Line::from(spans));
+                lines.push(Line::from(vec![
+                    format!("{num:>2}. [").into(),
+                    icon_span,
+                    "] ".into(),
+                    step.into(),
+                ]));
             }
         }
 

codex-rs/tui/src/insert_history.rs

@@ -216,18 +216,18 @@ where
 {
     let mut fg = Color::Reset;
     let mut bg = Color::Reset;
-    let mut modifier = Modifier::empty();
+    let mut last_modifier = Modifier::empty();
     for span in content {
-        let mut next_modifier = modifier;
-        next_modifier.insert(span.style.add_modifier);
-        next_modifier.remove(span.style.sub_modifier);
-        if next_modifier != modifier {
+        let mut modifier = Modifier::empty();
+        modifier.insert(span.style.add_modifier);
+        modifier.remove(span.style.sub_modifier);
+        if modifier != last_modifier {
             let diff = ModifierDiff {
-                from: modifier,
-                to: next_modifier,
+                from: last_modifier,
+                to: modifier,
             };
             diff.queue(&mut writer)?;
-            modifier = next_modifier;
+            last_modifier = modifier;
         }
         let next_fg = span.style.fg.unwrap_or(Color::Reset);
         let next_bg = span.style.bg.unwrap_or(Color::Reset);
@@ -250,3 +250,37 @@ where
         SetAttribute(crossterm::style::Attribute::Reset),
     )
 }
+
+#[cfg(test)]
+mod tests {
+    #![allow(clippy::unwrap_used)]
+    use super::*;
+
+    #[test]
+    fn writes_bold_then_regular_spans() {
+        use ratatui::style::Stylize;
+
+        let spans = ["A".bold(), "B".into()];
+
+        let mut actual: Vec<u8> = Vec::new();
+        write_spans(&mut actual, spans.iter()).unwrap();
+
+        let mut expected: Vec<u8> = Vec::new();
+        queue!(
+            expected,
+            SetAttribute(crossterm::style::Attribute::Bold),
+            Print("A"),
+            SetAttribute(crossterm::style::Attribute::NormalIntensity),
+            Print("B"),
+            SetForegroundColor(CColor::Reset),
+            SetBackgroundColor(CColor::Reset),
+            SetAttribute(crossterm::style::Attribute::Reset),
+        )
+        .unwrap();
+
+        assert_eq!(
+            String::from_utf8(actual).unwrap(),
+            String::from_utf8(expected).unwrap()
+        );
+    }
+}

codex-rs/tui/src/lib.rs

@@ -41,6 +41,11 @@ mod text_formatting;
 mod tui;
 mod user_approval_widget;
 
+#[cfg(not(debug_assertions))]
+mod updates;
+#[cfg(not(debug_assertions))]
+use color_eyre::owo_colors::OwoColorize;
+
 pub use cli::Cli;
 
 pub async fn run_main(
@@ -139,6 +144,38 @@ pub async fn run_main(
         .with(tui_layer)
         .try_init();
 
+    #[allow(clippy::print_stderr)]
+    #[cfg(not(debug_assertions))]
+    if let Some(latest_version) = updates::get_upgrade_version(&config) {
+        let current_version = env!("CARGO_PKG_VERSION");
+        let exe = std::env::current_exe()?;
+        let managed_by_npm = std::env::var_os("CODEX_MANAGED_BY_NPM").is_some();
+
+        eprintln!(
+            "{} {current_version} -> {latest_version}.",
+            "✨⬆️ Update available!".bold().cyan()
+        );
+
+        if managed_by_npm {
+            let npm_cmd = "npm install -g @openai/codex@latest";
+            eprintln!("Run {} to update.", npm_cmd.cyan().on_black());
+        } else if cfg!(target_os = "macos")
+            && (exe.starts_with("/opt/homebrew") || exe.starts_with("/usr/local"))
+        {
+            let brew_cmd = "brew upgrade codex";
+            eprintln!("Run {} to update.", brew_cmd.cyan().on_black());
+        } else {
+            eprintln!(
+                "See {} for the latest releases and installation options.",
+                "https://github.com/openai/codex/releases/latest"
+                    .cyan()
+                    .on_black()
+            );
+        }
+
+        eprintln!("");
+    }
+
     let show_login_screen = should_show_login_screen(&config);
     if show_login_screen {
         std::io::stdout()

codex-rs/tui/src/slash_command.rs

@@ -13,6 +13,7 @@ pub enum SlashCommand {
     // DO NOT ALPHA-SORT! Enum order is presentation order in the popup, so
     // more frequently used commands should be listed first.
     New,
+    Compact,
     Diff,
     Quit,
     #[cfg(debug_assertions)]
@@ -24,6 +25,7 @@ impl SlashCommand {
     pub fn description(self) -> &'static str {
         match self {
             SlashCommand::New => "Start a new chat.",
+            SlashCommand::Compact => "Compact the chat history.",
             SlashCommand::Quit => "Exit the application.",
             SlashCommand::Diff => {
                 "Show git diff of the working directory (including untracked files)"

codex-rs/tui/src/updates.rs

@@ -0,0 +1,137 @@
+#![cfg(any(not(debug_assertions), test))]
+
+use chrono::DateTime;
+use chrono::Duration;
+use chrono::Utc;
+use serde::Deserialize;
+use serde::Serialize;
+use std::path::Path;
+use std::path::PathBuf;
+
+use codex_core::config::Config;
+
+pub fn get_upgrade_version(config: &Config) -> Option<String> {
+    let version_file = version_filepath(config);
+    let info = read_version_info(&version_file).ok();
+
+    if match &info {
+        None => true,
+        Some(info) => info.last_checked_at < Utc::now() - Duration::hours(20),
+    } {
+        // Refresh the cached latest version in the background so TUI startup
+        // isn’t blocked by a network call. The UI reads the previously cached
+        // value (if any) for this run; the next run shows the banner if needed.
+        tokio::spawn(async move {
+            check_for_update(&version_file)
+                .await
+                .inspect_err(|e| tracing::error!("Failed to update version: {e}"))
+        });
+    }
+
+    info.and_then(|info| {
+        let current_version = env!("CARGO_PKG_VERSION");
+        if is_newer(&info.latest_version, current_version).unwrap_or(false) {
+            Some(info.latest_version)
+        } else {
+            None
+        }
+    })
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone)]
+struct VersionInfo {
+    latest_version: String,
+    // ISO-8601 timestamp (RFC3339)
+    last_checked_at: DateTime<Utc>,
+}
+
+#[derive(Deserialize, Debug, Clone)]
+struct ReleaseInfo {
+    tag_name: String,
+}
+
+const VERSION_FILENAME: &str = "version.json";
+const LATEST_RELEASE_URL: &str = "https://api.github.com/repos/openai/codex/releases/latest";
+
+fn version_filepath(config: &Config) -> PathBuf {
+    config.codex_home.join(VERSION_FILENAME)
+}
+
+fn read_version_info(version_file: &Path) -> anyhow::Result<VersionInfo> {
+    let contents = std::fs::read_to_string(version_file)?;
+    Ok(serde_json::from_str(&contents)?)
+}
+
+async fn check_for_update(version_file: &Path) -> anyhow::Result<()> {
+    let ReleaseInfo {
+        tag_name: latest_tag_name,
+    } = reqwest::Client::new()
+        .get(LATEST_RELEASE_URL)
+        .header(
+            "User-Agent",
+            format!(
+                "codex/{} (+https://github.com/openai/codex)",
+                env!("CARGO_PKG_VERSION")
+            ),
+        )
+        .send()
+        .await?
+        .error_for_status()?
+        .json::<ReleaseInfo>()
+        .await?;
+
+    let info = VersionInfo {
+        latest_version: latest_tag_name
+            .strip_prefix("rust-v")
+            .ok_or_else(|| anyhow::anyhow!("Failed to parse latest tag name '{latest_tag_name}'"))?
+            .into(),
+        last_checked_at: Utc::now(),
+    };
+
+    let json_line = format!("{}\n", serde_json::to_string(&info)?);
+    if let Some(parent) = version_file.parent() {
+        tokio::fs::create_dir_all(parent).await?;
+    }
+    tokio::fs::write(version_file, json_line).await?;
+    Ok(())
+}
+
+fn is_newer(latest: &str, current: &str) -> Option<bool> {
+    match (parse_version(latest), parse_version(current)) {
+        (Some(l), Some(c)) => Some(l > c),
+        _ => None,
+    }
+}
+
+fn parse_version(v: &str) -> Option<(u64, u64, u64)> {
+    let mut iter = v.trim().split('.');
+    let maj = iter.next()?.parse::<u64>().ok()?;
+    let min = iter.next()?.parse::<u64>().ok()?;
+    let pat = iter.next()?.parse::<u64>().ok()?;
+    Some((maj, min, pat))
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn prerelease_version_is_not_considered_newer() {
+        assert_eq!(is_newer("0.11.0-beta.1", "0.11.0"), None);
+        assert_eq!(is_newer("1.0.0-rc.1", "1.0.0"), None);
+    }
+
+    #[test]
+    fn plain_semver_comparisons_work() {
+        assert_eq!(is_newer("0.11.1", "0.11.0"), Some(true));
+        assert_eq!(is_newer("0.11.0", "0.11.1"), Some(false));
+        assert_eq!(is_newer("1.0.0", "0.9.9"), Some(true));
+        assert_eq!(is_newer("0.9.9", "1.0.0"), Some(false));
+    }
+
+    #[test]
+    fn whitespace_is_ignored() {
+        assert_eq!(parse_version(" 1.2.3 \n"), Some((1, 2, 3)));
+        assert_eq!(is_newer(" 1.2.3 ", "1.2.2"), Some(true));
+    }
+}

codex-rs/tui/src/user_approval_widget.rs

@@ -7,23 +7,24 @@
 //! driven workflow – a fully‑fledged visual match is not required.
 
 use std::path::PathBuf;
+use std::sync::LazyLock;
 
 use codex_core::protocol::Op;
 use codex_core::protocol::ReviewDecision;
 use crossterm::event::KeyCode;
 use crossterm::event::KeyEvent;
+use crossterm::event::KeyEventKind;
 use ratatui::buffer::Buffer;
 use ratatui::layout::Rect;
 use ratatui::prelude::*;
 use ratatui::text::Line;
-use ratatui::text::Span;
-use ratatui::widgets::List;
+use ratatui::widgets::Block;
+use ratatui::widgets::BorderType;
+use ratatui::widgets::Borders;
 use ratatui::widgets::Paragraph;
 use ratatui::widgets::Widget;
 use ratatui::widgets::WidgetRef;
 use ratatui::widgets::Wrap;
-use tui_input::Input;
-use tui_input::backend::crossterm::EventHandler;
 
 use crate::app_event::AppEvent;
 use crate::app_event_sender::AppEventSender;
@@ -47,68 +48,62 @@ pub(crate) enum ApprovalRequest {
 
 /// Options displayed in the *select* mode.
 struct SelectOption {
-    label: &'static str,
-    decision: Option<ReviewDecision>,
-    /// `true` when this option switches the widget to *input* mode.
-    enters_input_mode: bool,
+    label: Line<'static>,
+    description: &'static str,
+    key: KeyCode,
+    decision: ReviewDecision,
 }
 
-// keep in same order as in the TS implementation
-const SELECT_OPTIONS: &[SelectOption] = &[
-    SelectOption {
-        label: "Yes (y)",
-        decision: Some(ReviewDecision::Approved),
+static COMMAND_SELECT_OPTIONS: LazyLock<Vec<SelectOption>> = LazyLock::new(|| {
+    vec![
+        SelectOption {
+            label: Line::from(vec!["Y".underlined(), "es".into()]),
+            description: "Approve and run the command",
+            key: KeyCode::Char('y'),
+            decision: ReviewDecision::Approved,
+        },
+        SelectOption {
+            label: Line::from(vec!["A".underlined(), "lways".into()]),
+            description: "Approve the command for the remainder of this session",
+            key: KeyCode::Char('a'),
+            decision: ReviewDecision::ApprovedForSession,
+        },
+        SelectOption {
+            label: Line::from(vec!["N".underlined(), "o".into()]),
+            description: "Do not run the command",
+            key: KeyCode::Char('n'),
+            decision: ReviewDecision::Denied,
+        },
+    ]
+});
 
-        enters_input_mode: false,
-    },
-    SelectOption {
-        label: "Yes, always approve this exact command for this session (a)",
-        decision: Some(ReviewDecision::ApprovedForSession),
-
-        enters_input_mode: false,
-    },
-    SelectOption {
-        label: "Edit or give feedback (e)",
-        decision: None,
-
-        enters_input_mode: true,
-    },
-    SelectOption {
-        label: "No, and keep going (n)",
-        decision: Some(ReviewDecision::Denied),
-
-        enters_input_mode: false,
-    },
-    SelectOption {
-        label: "No, and stop for now (esc)",
-        decision: Some(ReviewDecision::Abort),
-
-        enters_input_mode: false,
-    },
-];
-
-/// Internal mode the widget is in – mirrors the TypeScript component.
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-enum Mode {
-    Select,
-    Input,
-}
+static PATCH_SELECT_OPTIONS: LazyLock<Vec<SelectOption>> = LazyLock::new(|| {
+    vec![
+        SelectOption {
+            label: Line::from(vec!["Y".underlined(), "es".into()]),
+            description: "Approve and apply the changes",
+            key: KeyCode::Char('y'),
+            decision: ReviewDecision::Approved,
+        },
+        SelectOption {
+            label: Line::from(vec!["N".underlined(), "o".into()]),
+            description: "Do not apply the changes",
+            key: KeyCode::Char('n'),
+            decision: ReviewDecision::Denied,
+        },
+    ]
+});
 
 /// A modal prompting the user to approve or deny the pending request.
 pub(crate) struct UserApprovalWidget<'a> {
     approval_request: ApprovalRequest,
     app_event_tx: AppEventSender,
     confirmation_prompt: Paragraph<'a>,
+    select_options: &'a Vec<SelectOption>,
 
     /// Currently selected index in *select* mode.
     selected_option: usize,
 
-    /// State for the optional input widget.
-    input: Input,
-
-    /// Current mode.
-    mode: Mode,
-
     /// Set to `true` once a decision has been sent – the parent view can then
     /// remove this widget from its queue.
     done: bool,
@@ -116,7 +111,6 @@ pub(crate) struct UserApprovalWidget<'a> {
 
 impl UserApprovalWidget<'_> {
     pub(crate) fn new(approval_request: ApprovalRequest, app_event_tx: AppEventSender) -> Self {
-        let input = Input::default();
         let confirmation_prompt = match &approval_request {
             ApprovalRequest::Exec {
                 command,
@@ -132,25 +126,20 @@ impl UserApprovalWidget<'_> {
                     None => cwd.display().to_string(),
                 };
                 let mut contents: Vec<Line> = vec![
-                    Line::from(vec![
-                        Span::from(cwd_str).dim(),
-                        Span::from("$"),
-                        Span::from(format!(" {cmd}")),
-                    ]),
+                    Line::from(vec!["codex".bold().magenta(), " wants to run:".into()]),
+                    Line::from(vec![cwd_str.dim(), "$".into(), format!(" {cmd}").into()]),
                     Line::from(""),
                 ];
                 if let Some(reason) = reason {
                     contents.push(Line::from(reason.clone().italic()));
                     contents.push(Line::from(""));
                 }
-                contents.extend(vec![Line::from("Allow command?"), Line::from("")]);
                 Paragraph::new(contents).wrap(Wrap { trim: false })
             }
             ApprovalRequest::ApplyPatch {
                 reason, grant_root, ..
             } => {
-                let mut contents: Vec<Line> =
-                    vec![Line::from("Apply patch".bold()), Line::from("")];
+                let mut contents: Vec<Line> = vec![];
 
                 if let Some(r) = reason {
                     contents.push(Line::from(r.clone().italic()));
@@ -165,20 +154,19 @@ impl UserApprovalWidget<'_> {
                     contents.push(Line::from(""));
                 }
 
-                contents.push(Line::from("Allow changes?"));
-                contents.push(Line::from(""));
-
-                Paragraph::new(contents)
+                Paragraph::new(contents).wrap(Wrap { trim: false })
             }
         };
 
         Self {
+            select_options: match &approval_request {
+                ApprovalRequest::Exec { .. } => &COMMAND_SELECT_OPTIONS,
+                ApprovalRequest::ApplyPatch { .. } => &PATCH_SELECT_OPTIONS,
+            },
             approval_request,
             app_event_tx,
             confirmation_prompt,
             selected_option: 0,
-            input,
-            mode: Mode::Select,
             done: false,
         }
     }
@@ -194,9 +182,8 @@ impl UserApprovalWidget<'_> {
     /// captures input while visible, we don’t need to report whether the event
     /// was consumed—callers can assume it always is.
     pub(crate) fn handle_key_event(&mut self, key: KeyEvent) {
-        match self.mode {
-            Mode::Select => self.handle_select_key(key),
-            Mode::Input => self.handle_input_key(key),
+        if key.kind == KeyEventKind::Press {
+            self.handle_select_key(key);
         }
     }
 
@@ -208,58 +195,24 @@ impl UserApprovalWidget<'_> {
 
     fn handle_select_key(&mut self, key_event: KeyEvent) {
         match key_event.code {
-            KeyCode::Up => {
-                if self.selected_option == 0 {
-                    self.selected_option = SELECT_OPTIONS.len() - 1;
-                } else {
-                    self.selected_option -= 1;
-                }
+            KeyCode::Left => {
+                self.selected_option = (self.selected_option + self.select_options.len() - 1)
+                    % self.select_options.len();
             }
-            KeyCode::Down => {
-                self.selected_option = (self.selected_option + 1) % SELECT_OPTIONS.len();
-            }
-            KeyCode::Char('y') => {
-                self.send_decision(ReviewDecision::Approved);
-            }
-            KeyCode::Char('a') => {
-                self.send_decision(ReviewDecision::ApprovedForSession);
-            }
-            KeyCode::Char('n') => {
-                self.send_decision(ReviewDecision::Denied);
-            }
-            KeyCode::Char('e') => {
-                self.mode = Mode::Input;
+            KeyCode::Right => {
+                self.selected_option = (self.selected_option + 1) % self.select_options.len();
             }
             KeyCode::Enter => {
-                let opt = &SELECT_OPTIONS[self.selected_option];
-                if opt.enters_input_mode {
-                    self.mode = Mode::Input;
-                } else if let Some(decision) = opt.decision {
-                    self.send_decision(decision);
-                }
+                let opt = &self.select_options[self.selected_option];
+                self.send_decision(opt.decision);
             }
             KeyCode::Esc => {
                 self.send_decision(ReviewDecision::Abort);
             }
-            _ => {}
-        }
-    }
-
-    fn handle_input_key(&mut self, key_event: KeyEvent) {
-        // Handle special keys first.
-        match key_event.code {
-            KeyCode::Enter => {
-                let feedback = self.input.value().to_string();
-                self.send_decision_with_feedback(ReviewDecision::Denied, feedback);
-            }
-            KeyCode::Esc => {
-                // Cancel input – treat as deny without feedback.
-                self.send_decision(ReviewDecision::Denied);
-            }
-            _ => {
-                // Feed into input widget for normal editing.
-                let ct_event = crossterm::event::Event::Key(key_event);
-                self.input.handle_event(&ct_event);
+            other => {
+                if let Some(opt) = self.select_options.iter().find(|opt| opt.key == other) {
+                    self.send_decision(opt.decision);
+                }
             }
         }
     }
@@ -312,87 +265,68 @@ impl UserApprovalWidget<'_> {
     }
 
     pub(crate) fn desired_height(&self, width: u16) -> u16 {
-        self.get_confirmation_prompt_height(width - 2) + SELECT_OPTIONS.len() as u16 + 2
+        self.get_confirmation_prompt_height(width) + self.select_options.len() as u16
     }
 }
 
-const PLAIN: Style = Style::new();
-const BLUE_FG: Style = Style::new().fg(Color::LightCyan);
-
 impl WidgetRef for &UserApprovalWidget<'_> {
     fn render_ref(&self, area: Rect, buf: &mut Buffer) {
-        // Take the area, wrap it in a block with a border, and divide up the
-        // remaining area into two chunks: one for the confirmation prompt and
-        // one for the response.
-        let inner = area.inner(Margin::new(0, 2));
-
-        // Determine how many rows we can allocate for the static confirmation
-        // prompt while *always* keeping enough space for the interactive
-        // response area (select list or input field). When the full prompt
-        // would exceed the available height we truncate it so the response
-        // options never get pushed out of view. This keeps the approval modal
-        // usable even when the overall bottom viewport is small.
-
-        // Full height of the prompt (may be larger than the available area).
-        let full_prompt_height = self.get_confirmation_prompt_height(inner.width);
-
-        // Minimum rows that must remain for the interactive section.
-        let min_response_rows = match self.mode {
-            Mode::Select => SELECT_OPTIONS.len() as u16,
-            // In input mode we need exactly two rows: one for the guidance
-            // prompt and one for the single-line input field.
-            Mode::Input => 2,
-        };
-
-        // Clamp prompt height so confirmation + response never exceed the
-        // available space. `saturating_sub` avoids underflow when the area is
-        // too small even for the minimal layout – in this unlikely case we
-        // fall back to zero-height prompt so at least the options are
-        // visible.
-        let prompt_height = full_prompt_height.min(inner.height.saturating_sub(min_response_rows));
-
-        let chunks = Layout::default()
+        let prompt_height = self.get_confirmation_prompt_height(area.width);
+        let [prompt_chunk, response_chunk] = Layout::default()
             .direction(Direction::Vertical)
             .constraints([Constraint::Length(prompt_height), Constraint::Min(0)])
-            .split(inner);
-        let prompt_chunk = chunks[0];
-        let response_chunk = chunks[1];
+            .areas(area);
 
-        // Build the inner lines based on the mode. Collect them into a List of
-        // non-wrapping lines rather than a Paragraph for predictable layout.
-        let lines = match self.mode {
-            Mode::Select => SELECT_OPTIONS
-                .iter()
-                .enumerate()
-                .map(|(idx, opt)| {
-                    let (prefix, style) = if idx == self.selected_option {
-                        ("▶", BLUE_FG)
-                    } else {
-                        (" ", PLAIN)
-                    };
-                    Line::styled(format!("  {prefix} {}", opt.label), style)
-                })
-                .collect(),
-            Mode::Input => {
-                vec![
-                    Line::from("Give the model feedback on this command:"),
-                    Line::from(self.input.value()),
-                ]
-            }
+        let lines: Vec<Line> = self
+            .select_options
+            .iter()
+            .enumerate()
+            .map(|(idx, opt)| {
+                let style = if idx == self.selected_option {
+                    Style::new().bg(Color::Cyan).fg(Color::Black)
+                } else {
+                    Style::new().bg(Color::DarkGray)
+                };
+                opt.label.clone().alignment(Alignment::Center).style(style)
+            })
+            .collect();
+
+        let [title_area, button_area, description_area] = Layout::vertical([
+            Constraint::Length(1),
+            Constraint::Length(1),
+            Constraint::Min(0),
+        ])
+        .areas(response_chunk.inner(Margin::new(1, 0)));
+        let title = match &self.approval_request {
+            ApprovalRequest::Exec { .. } => "Allow command?",
+            ApprovalRequest::ApplyPatch { .. } => "Apply changes?",
         };
-
-        let border = ("◢◤")
-            .repeat((area.width / 2).into())
-            .fg(Color::LightYellow);
-
-        border.render_ref(area, buf);
-        Paragraph::new(" Execution Request ".bold().black().on_light_yellow())
-            .alignment(Alignment::Center)
-            .render_ref(area, buf);
+        Line::from(title).render(title_area, buf);
 
         self.confirmation_prompt.clone().render(prompt_chunk, buf);
-        List::new(lines).render_ref(response_chunk, buf);
+        let areas = Layout::horizontal(
+            lines
+                .iter()
+                .map(|l| Constraint::Length(l.width() as u16 + 2)),
+        )
+        .spacing(1)
+        .split(button_area);
+        for (idx, area) in areas.iter().enumerate() {
+            let line = &lines[idx];
+            line.render(*area, buf);
+        }
 
-        border.render_ref(Rect::new(0, area.y + area.height - 1, area.width, 1), buf);
+        Line::from(self.select_options[self.selected_option].description)
+            .style(Style::new().italic().fg(Color::DarkGray))
+            .render(description_area.inner(Margin::new(1, 0)), buf);
+
+        Block::bordered()
+            .border_type(BorderType::QuadrantOutside)
+            .border_style(Style::default().fg(Color::Cyan))
+            .borders(Borders::LEFT)
+            .render_ref(
+                Rect::new(0, response_chunk.y, 1, response_chunk.height),
+                buf,
+            );
     }
 }