merge

## Summary
Per the [latest MCP
spec](https://modelcontextprotocol.io/specification/2025-06-18/basic#meta),
the `_meta` field is reserved for metadata. In the [Typescript
Schema](0695a497eb/schema/2025-06-18/schema.ts (L37-L40)),
`progressToken` is defined as a value to be attached to subsequent
notifications for that request.

The
[CallToolRequestParams](0695a497eb/schema/2025-06-18/schema.ts (L806-L817))
extends this definition but overwrites the params field. This ambiguity
makes our generated type definitions tricky, so I'm going to skip
`progressToken` field for now and just send back the `requestId`
instead.
 
In a future PR, we can clarify, update our `generate_mcp_types.py`
script, and update our progressToken logic accordingly.

## Testing
- [x] Added unit tests
- [x] Manually tested with mcp client

.devcontainer/devcontainer.json

@@ -21,7 +21,7 @@
       "settings": {
         "terminal.integrated.defaultProfile.linux": "bash"
       },
-      "extensions": ["rust-lang.rust-analyzer"]
+      "extensions": ["rust-lang.rust-analyzer", "tamasfe.even-better-toml"]
     }
   }
 }

.github/actions/codex/bun.lock

@@ -8,8 +8,8 @@
         "@actions/github": "^6.0.1",
       },
       "devDependencies": {
-        "@types/bun": "^1.2.18",
-        "@types/node": "^24.0.13",
+        "@types/bun": "^1.2.19",
+        "@types/node": "^24.1.0",
         "prettier": "^3.6.2",
         "typescript": "^5.8.3",
       },
@@ -48,15 +48,15 @@
 
     "@octokit/types": ["@octokit/types@13.10.0", "", { "dependencies": { "@octokit/openapi-types": "^24.2.0" } }, "sha512-ifLaO34EbbPj0Xgro4G5lP5asESjwHracYJvVaPIyXMuiuXLlhic3S47cBdTb+jfODkTE5YtGCLt3Ay3+J97sA=="],
 
-    "@types/bun": ["@types/bun@1.2.18", "", { "dependencies": { "bun-types": "1.2.18" } }, "sha512-Xf6RaWVheyemaThV0kUfaAUvCNokFr+bH8Jxp+tTZfx7dAPA8z9ePnP9S9+Vspzuxxx9JRAXhnyccRj3GyCMdQ=="],
+    "@types/bun": ["@types/bun@1.2.19", "", { "dependencies": { "bun-types": "1.2.19" } }, "sha512-d9ZCmrH3CJ2uYKXQIUuZ/pUnTqIvLDS0SK7pFmbx8ma+ziH/FRMoAq5bYpRG7y+w1gl+HgyNZbtqgMq4W4e2Lg=="],
 
-    "@types/node": ["@types/node@24.0.13", "", { "dependencies": { "undici-types": "~7.8.0" } }, "sha512-Qm9OYVOFHFYg3wJoTSrz80hoec5Lia/dPp84do3X7dZvLikQvM1YpmvTBEdIr/e+U8HTkFjLHLnl78K/qjf+jQ=="],
+    "@types/node": ["@types/node@24.1.0", "", { "dependencies": { "undici-types": "~7.8.0" } }, "sha512-ut5FthK5moxFKH2T1CUOC6ctR67rQRvvHdFLCD2Ql6KXmMuCrjsSsRI9UsLCm9M18BMwClv4pn327UvB7eeO1w=="],
 
     "@types/react": ["@types/react@19.1.8", "", { "dependencies": { "csstype": "^3.0.2" } }, "sha512-AwAfQ2Wa5bCx9WP8nZL2uMZWod7J7/JSplxbTmBQ5ms6QpqNYm672H0Vu9ZVKVngQ+ii4R/byguVEUZQyeg44g=="],
 
     "before-after-hook": ["before-after-hook@2.2.3", "", {}, "sha512-NzUnlZexiaH/46WDhANlyR2bXRopNg4F/zuSA3OpZnllCUgRaOF2znDioDWrmbNVsuZk6l9pMquQB38cfBZwkQ=="],
 
-    "bun-types": ["bun-types@1.2.18", "", { "dependencies": { "@types/node": "*" }, "peerDependencies": { "@types/react": "^19" } }, "sha512-04+Eha5NP7Z0A9YgDAzMk5PHR16ZuLVa83b26kH5+cp1qZW4F6FmAURngE7INf4tKOvCE69vYvDEwoNl1tGiWw=="],
+    "bun-types": ["bun-types@1.2.19", "", { "dependencies": { "@types/node": "*" }, "peerDependencies": { "@types/react": "^19" } }, "sha512-uAOTaZSPuYsWIXRpj7o56Let0g/wjihKCkeRqUBhlLVM/Bt+Fj9xTo+LhC1OV1XDaGkz4hNC80et5xgy+9KTHQ=="],
 
     "csstype": ["csstype@3.1.3", "", {}, "sha512-M1uQkMl8rQK/szD0LNhtqxIPLpimGm8sOBwU7lLnCpSbTyY3yeU1Vc7l4KT5zT4s/yOxHH5O7tIuuLOCnLADRw=="],
 
@@ -82,6 +82,8 @@
 
     "@octokit/plugin-rest-endpoint-methods/@octokit/types": ["@octokit/types@12.6.0", "", { "dependencies": { "@octokit/openapi-types": "^20.0.0" } }, "sha512-1rhSOfRa6H9w4YwK0yrf5faDaDTb+yLyBUKOCV4xtCDB5VmIPqd/v9yr9o6SAzOAlRxMiRiCic6JVM1/kunVkw=="],
 
+    "bun-types/@types/node": ["@types/node@24.0.13", "", { "dependencies": { "undici-types": "~7.8.0" } }, "sha512-Qm9OYVOFHFYg3wJoTSrz80hoec5Lia/dPp84do3X7dZvLikQvM1YpmvTBEdIr/e+U8HTkFjLHLnl78K/qjf+jQ=="],
+
     "@octokit/plugin-paginate-rest/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@20.0.0", "", {}, "sha512-EtqRBEjp1dL/15V7WiX5LJMIxxkdiGJnabzYx5Apx4FkQIFgAfKumXeYAqqJCj1s+BMX4cPFIFC4OLCR6stlnA=="],
 
     "@octokit/plugin-rest-endpoint-methods/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@20.0.0", "", {}, "sha512-EtqRBEjp1dL/15V7WiX5LJMIxxkdiGJnabzYx5Apx4FkQIFgAfKumXeYAqqJCj1s+BMX4cPFIFC4OLCR6stlnA=="],

.github/actions/codex/package.json

@@ -13,8 +13,8 @@
         "@actions/github": "^6.0.1"
     },
     "devDependencies": {
-        "@types/bun": "^1.2.18",
-        "@types/node": "^24.0.13",
+        "@types/bun": "^1.2.19",
+        "@types/node": "^24.1.0",
         "prettier": "^3.6.2",
         "typescript": "^5.8.3"
     }

.github/workflows/rust-release.yml

@@ -93,7 +93,7 @@ jobs:
           sudo apt install -y musl-tools pkg-config
 
       - name: Cargo build
-        run: cargo build --target ${{ matrix.target }} --release --all-targets --all-features
+        run: cargo build --target ${{ matrix.target }} --release --bin codex --bin codex-exec --bin codex-linux-sandbox
 
       - name: Stage artifacts
         shell: bash

.vscode/launch.json

@@ -0,0 +1,18 @@
+{
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "Cargo launch",
+            "cargo": {
+                "cwd": "${workspaceFolder}/codex-rs",
+                "args": [
+                    "build",
+                    "--bin=codex-tui"
+                ]
+            },
+            "args": []
+        }
+    ]
+}

.vscode/settings.json

@@ -0,0 +1,10 @@
+{
+    "rust-analyzer.checkOnSave": true,
+    "rust-analyzer.check.command": "clippy",
+    "rust-analyzer.check.extraArgs": ["--all-features", "--tests"],
+    "rust-analyzer.rustfmt.extraArgs": ["--config", "imports_granularity=Item"],
+    "[rust]": {
+        "editor.defaultFormatter": "rust-lang.rust-analyzer",
+        "editor.formatOnSave": true,
+    }
+}

AGENTS.md

@@ -3,3 +3,7 @@
 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.
+
+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.
+
+When making individual changes prefer running tests on individual files or projects first.

codex-cli/bin/codex.js

@@ -15,7 +15,6 @@
  *      current platform / architecture, an error is thrown.
  */
 
-import { spawnSync } from "child_process";
 import fs from "fs";
 import path from "path";
 import { fileURLToPath, pathToFileURL } from "url";
@@ -35,7 +34,7 @@ const wantsNative = fs.existsSync(path.join(__dirname, "use-native")) ||
     : false);
 
 // Try native binary if requested.
-if (wantsNative) {
+if (wantsNative && process.platform !== 'win32') {
   const { platform, arch } = process;
 
   let targetTriple = null;
@@ -74,22 +73,76 @@ if (wantsNative) {
   }
 
   const binaryPath = path.join(__dirname, "..", "bin", `codex-${targetTriple}`);
-  const result = spawnSync(binaryPath, process.argv.slice(2), {
+
+  // Use an asynchronous spawn instead of spawnSync so that Node is able to
+  // respond to signals (e.g. Ctrl-C / SIGINT) while the native binary is
+  // executing. This allows us to forward those signals to the child process
+  // and guarantees that when either the child terminates or the parent
+  // receives a fatal signal, both processes exit in a predictable manner.
+  const { spawn } = await import("child_process");
+
+  const child = spawn(binaryPath, process.argv.slice(2), {
     stdio: "inherit",
   });
 
-  const exitCode = typeof result.status === "number" ? result.status : 1;
-  process.exit(exitCode);
-}
+  child.on("error", (err) => {
+    // Typically triggered when the binary is missing or not executable.
+    // Re-throwing here will terminate the parent with a non-zero exit code
+    // while still printing a helpful stack trace.
+    // eslint-disable-next-line no-console
+    console.error(err);
+    process.exit(1);
+  });
 
-// Fallback: execute the original JavaScript CLI.
+  // Forward common termination signals to the child so that it shuts down
+  // gracefully. In the handler we temporarily disable the default behavior of
+  // exiting immediately; once the child has been signaled we simply wait for
+  // its exit event which will in turn terminate the parent (see below).
+  const forwardSignal = (signal) => {
+    if (child.killed) {
+      return;
+    }
+    try {
+      child.kill(signal);
+    } catch {
+      /* ignore */
+    }
+  };
 
-// Resolve the path to the compiled CLI bundle
-const cliPath = path.resolve(__dirname, "../dist/cli.js");
-const cliUrl = pathToFileURL(cliPath).href;
+  ["SIGINT", "SIGTERM", "SIGHUP"].forEach((sig) => {
+    process.on(sig, () => forwardSignal(sig));
+  });
 
-// Load and execute the CLI
-(async () => {
+  // When the child exits, mirror its termination reason in the parent so that
+  // shell scripts and other tooling observe the correct exit status.
+  // Wrap the lifetime of the child process in a Promise so that we can await
+  // its termination in a structured way. The Promise resolves with an object
+  // describing how the child exited: either via exit code or due to a signal.
+  const childResult = await new Promise((resolve) => {
+    child.on("exit", (code, signal) => {
+      if (signal) {
+        resolve({ type: "signal", signal });
+      } else {
+        resolve({ type: "code", exitCode: code ?? 1 });
+      }
+    });
+  });
+
+  if (childResult.type === "signal") {
+    // Re-emit the same signal so that the parent terminates with the expected
+    // semantics (this also sets the correct exit code of 128 + n).
+    process.kill(process.pid, childResult.signal);
+  } else {
+    process.exit(childResult.exitCode);
+  }
+} else {
+  // Fallback: execute the original JavaScript CLI.
+
+  // Resolve the path to the compiled CLI bundle
+  const cliPath = path.resolve(__dirname, "../dist/cli.js");
+  const cliUrl = pathToFileURL(cliPath).href;
+
+  // Load and execute the CLI
   try {
     await import(cliUrl);
   } catch (err) {
@@ -97,4 +150,4 @@ const cliUrl = pathToFileURL(cliPath).href;
     console.error(err);
     process.exit(1);
   }
-})();
+}

codex-cli/src/approvals.ts

@@ -370,11 +370,26 @@ export function isSafeCommand(
         reason: "View file with line numbers",
         group: "Reading files",
       };
-    case "rg":
+    case "rg": {
+      // Certain ripgrep options execute external commands or invoke other
+      // processes, so we must reject them.
+      const isUnsafe = command.some(
+        (arg: string) =>
+          UNSAFE_OPTIONS_FOR_RIPGREP_WITHOUT_ARGS.has(arg) ||
+          [...UNSAFE_OPTIONS_FOR_RIPGREP_WITH_ARGS].some(
+            (opt) => arg === opt || arg.startsWith(`${opt}=`),
+          ),
+      );
+
+      if (isUnsafe) {
+        break;
+      }
+
       return {
         reason: "Ripgrep search",
         group: "Searching",
       };
+    }
     case "find": {
       // Certain options to `find` allow executing arbitrary processes, so we
       // cannot auto-approve them.
@@ -495,6 +510,22 @@ const UNSAFE_OPTIONS_FOR_FIND_COMMAND: ReadonlySet<string> = new Set([
   "-fprintf",
 ]);
 
+// Ripgrep options that are considered unsafe because they may execute
+// arbitrary commands or spawn auxiliary processes.
+const UNSAFE_OPTIONS_FOR_RIPGREP_WITH_ARGS: ReadonlySet<string> = new Set([
+  // Executes an arbitrary command for each matching file.
+  "--pre",
+  // Allows custom hostname command which could leak environment details.
+  "--hostname-bin",
+]);
+
+const UNSAFE_OPTIONS_FOR_RIPGREP_WITHOUT_ARGS: ReadonlySet<string> = new Set([
+  // Enables searching inside archives which triggers external decompression
+  // utilities – reject out of an abundance of caution.
+  "--search-zip",
+  "-z",
+]);
+
 // ---------------- Helper utilities for complex shell expressions -----------------
 
 // A conservative allow-list of bash operators that do not, on their own, cause

codex-cli/tests/approvals.test.ts

@@ -44,6 +44,14 @@ describe("canAutoApprove()", () => {
       group: "Navigating",
       runInSandbox: false,
     });
+
+    // Ripgrep safe invocation.
+    expect(check(["rg", "TODO"])).toEqual({
+      type: "auto-approve",
+      reason: "Ripgrep search",
+      group: "Searching",
+      runInSandbox: false,
+    });
   });
 
   test("simple safe commands within a `bash -lc` call", () => {
@@ -67,6 +75,24 @@ describe("canAutoApprove()", () => {
     });
   });
 
+  test("ripgrep unsafe flags", () => {
+    // Flags that do not take arguments
+    expect(check(["rg", "--search-zip", "TODO"])).toEqual({ type: "ask-user" });
+    expect(check(["rg", "-z", "TODO"])).toEqual({ type: "ask-user" });
+
+    // Flags that take arguments (provided separately)
+    expect(check(["rg", "--pre", "cat", "TODO"])).toEqual({ type: "ask-user" });
+    expect(check(["rg", "--hostname-bin", "hostname", "TODO"])).toEqual({
+      type: "ask-user",
+    });
+
+    // Flags that take arguments in = form
+    expect(check(["rg", "--pre=cat", "TODO"])).toEqual({ type: "ask-user" });
+    expect(check(["rg", "--hostname-bin=hostname", "TODO"])).toEqual({
+      type: "ask-user",
+    });
+  });
+
   test("bash -lc commands with unsafe redirects", () => {
     expect(check(["bash", "-lc", "echo hello > file.txt"])).toEqual({
       type: "ask-user",

codex-rs/Cargo.lock

@@ -399,6 +399,15 @@ version = "2.6.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6099cdc01846bc367c4e7dd630dc5966dccf36b652fae7a74e17b640411a91b2"
 
+[[package]]
+name = "block-buffer"
+version = "0.10.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3078c7629b62d3f0439517fa394996acacc5cbc91c5a20d8c658e77abd503a71"
+dependencies = [
+ "generic-array",
+]
+
 [[package]]
 name = "bstr"
 version = "1.12.0"
@@ -454,18 +463,18 @@ checksum = "df8670b8c7b9dae1793364eafadf7239c40d669904660c5960d74cfd80b46a53"
 
 [[package]]
 name = "castaway"
-version = "0.2.3"
+version = "0.2.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0abae9be0aaf9ea96a3b1b8b1b55c602ca751eba1b1500220cea4ecbafe7c0d5"
+checksum = "dec551ab6e7578819132c713a93c022a05d60159dc86e7a7050223577484c55a"
 dependencies = [
  "rustversion",
 ]
 
 [[package]]
 name = "cc"
-version = "1.2.29"
+version = "1.2.30"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5c1599538de2394445747c8cf7935946e3cc27e9625f889d979bfb2aaf569362"
+checksum = "deec109607ca693028562ed836a5f1c4b8bd77755c4e132fc5ce11b0b6211ae7"
 dependencies = [
  "jobserver",
  "libc",
@@ -561,9 +570,9 @@ checksum = "b94f61472cee1439c0b966b47e3aca9ae07e45d070759512cd390ea2bebc6675"
 
 [[package]]
 name = "clipboard-win"
-version = "5.4.0"
+version = "5.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "15efe7a882b08f34e38556b14f2fb3daa98769d06c7f0c1b076dfd0d983bc892"
+checksum = "bde03770d3df201d4fb868f2c9c59e66a3e4e2bd06692a0fe701e7103c7e84d4"
 dependencies = [
  "error-code",
 ]
@@ -596,6 +605,18 @@ dependencies = [
  "tree-sitter-bash",
 ]
 
+[[package]]
+name = "codex-arg0"
+version = "0.0.0"
+dependencies = [
+ "anyhow",
+ "codex-apply-patch",
+ "codex-core",
+ "codex-linux-sandbox",
+ "dotenvy",
+ "tokio",
+]
+
 [[package]]
 name = "codex-chatgpt"
 version = "0.0.0"
@@ -619,11 +640,11 @@ dependencies = [
  "anyhow",
  "clap",
  "clap_complete",
+ "codex-arg0",
  "codex-chatgpt",
  "codex-common",
  "codex-core",
  "codex-exec",
- "codex-linux-sandbox",
  "codex-login",
  "codex-mcp-server",
  "codex-tui",
@@ -640,7 +661,7 @@ dependencies = [
  "clap",
  "codex-core",
  "serde",
- "toml 0.9.1",
+ "toml 0.9.2",
 ]
 
 [[package]]
@@ -654,35 +675,41 @@ dependencies = [
  "bytes",
  "codex-apply-patch",
  "codex-mcp-client",
+ "core_test_support",
  "dirs",
  "env-flags",
  "eventsource-stream",
  "fs2",
  "futures",
  "landlock",
+ "libc",
  "maplit",
  "mcp-types",
  "mime_guess",
  "openssl-sys",
  "predicates",
  "pretty_assertions",
- "rand 0.9.1",
+ "rand 0.9.2",
  "reqwest",
  "seccompiler",
  "serde",
  "serde_json",
- "strum_macros 0.27.1",
+ "sha1",
+ "shlex",
+ "strum_macros 0.27.2",
  "tempfile",
  "thiserror 2.0.12",
  "time",
  "tokio",
  "tokio-test",
  "tokio-util",
- "toml 0.9.1",
+ "toml 0.9.2",
  "tracing",
  "tree-sitter",
  "tree-sitter-bash",
  "uuid",
+ "walkdir",
+ "whoami",
  "wildmatch",
  "wiremock",
 ]
@@ -692,14 +719,17 @@ name = "codex-exec"
 version = "0.0.0"
 dependencies = [
  "anyhow",
+ "assert_cmd",
  "chrono",
  "clap",
+ "codex-arg0",
  "codex-common",
  "codex-core",
- "codex-linux-sandbox",
  "owo-colors",
+ "predicates",
  "serde_json",
  "shlex",
+ "tempfile",
  "tokio",
  "tracing",
  "tracing-subscriber",
@@ -744,6 +774,7 @@ version = "0.0.0"
 dependencies = [
  "anyhow",
  "clap",
+ "codex-common",
  "codex-core",
  "landlock",
  "libc",
@@ -781,17 +812,24 @@ name = "codex-mcp-server"
 version = "0.0.0"
 dependencies = [
  "anyhow",
+ "assert_cmd",
+ "codex-arg0",
  "codex-core",
- "codex-linux-sandbox",
  "mcp-types",
+ "mcp_test_support",
  "pretty_assertions",
  "schemars 0.8.22",
  "serde",
  "serde_json",
+ "shlex",
+ "tempfile",
  "tokio",
- "toml 0.9.1",
+ "tokio-test",
+ "toml 0.9.2",
  "tracing",
  "tracing-subscriber",
+ "uuid",
+ "wiremock",
 ]
 
 [[package]]
@@ -802,10 +840,10 @@ dependencies = [
  "base64 0.22.1",
  "clap",
  "codex-ansi-escape",
+ "codex-arg0",
  "codex-common",
  "codex-core",
  "codex-file-search",
- "codex-linux-sandbox",
  "codex-login",
  "color-eyre",
  "crossterm",
@@ -818,10 +856,12 @@ dependencies = [
  "ratatui",
  "ratatui-image",
  "regex-lite",
+ "reqwest",
+ "serde",
  "serde_json",
  "shlex",
- "strum 0.27.1",
- "strum_macros 0.27.1",
+ "strum 0.27.2",
+ "strum_macros 0.27.2",
  "tokio",
  "tracing",
  "tracing-appender",
@@ -830,6 +870,7 @@ dependencies = [
  "tui-markdown",
  "tui-textarea",
  "unicode-segmentation",
+ "unicode-width 0.1.14",
  "uuid",
 ]
 
@@ -933,10 +974,29 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
 
 [[package]]
-name = "crc32fast"
-version = "1.4.2"
+name = "core_test_support"
+version = "0.0.0"
+dependencies = [
+ "codex-core",
+ "serde_json",
+ "tempfile",
+ "tokio",
+]
+
+[[package]]
+name = "cpufeatures"
+version = "0.2.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a97769d94ddab943e4510d138150169a2758b5ef3eb191a9ee688de3e23ef7b3"
+checksum = "59ed5838eebb26a2bb2e58f6d5b5316989ae9d08bab10e0e6d103e656d1b0280"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "crc32fast"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9481c1c90cbf2ac953f07c8d4a58aa3945c425b7185c9154d67a65e4230da511"
 dependencies = [
  "cfg-if",
 ]
@@ -1006,6 +1066,16 @@ version = "0.2.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "460fbee9c2c2f33933d720630a6a0bac33ba7053db5344fac858d4b8952d77d5"
 
+[[package]]
+name = "crypto-common"
+version = "0.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1bfb12502f3fc46cca1bb51ac28df9d618d813cdc3d2f25b9fe775a34af26bb3"
+dependencies = [
+ "generic-array",
+ "typenum",
+]
+
 [[package]]
 name = "ctor"
 version = "0.1.26"
@@ -1156,6 +1226,16 @@ version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6184e33543162437515c2e2b48714794e37845ec9851711914eec9d308f6ebe8"
 
+[[package]]
+name = "digest"
+version = "0.10.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292"
+dependencies = [
+ "block-buffer",
+ "crypto-common",
+]
+
 [[package]]
 name = "dirs"
 version = "6.0.0"
@@ -1225,6 +1305,12 @@ version = "0.3.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "fea41bba32d969b513997752735605054bc0dfa92b4c56bf1189f2e174be7a10"
 
+[[package]]
+name = "dotenvy"
+version = "0.15.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1aaf95b3e5c8f23aa320147307562d361db0ae0d51242340f558153b4eb2439b"
+
 [[package]]
 name = "dupe"
 version = "0.9.1"
@@ -1457,7 +1543,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0ce92ff622d6dadf7349484f42c93271a0d49b7cc4d466a936405bacbe10aa78"
 dependencies = [
  "cfg-if",
- "rustix 1.0.7",
+ "rustix 1.0.8",
  "windows-sys 0.59.0",
 ]
 
@@ -1645,6 +1731,16 @@ dependencies = [
  "byteorder",
 ]
 
+[[package]]
+name = "generic-array"
+version = "0.14.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85649ca51fd72272d7821adaf274ad91c288277713d9c18820d8499a7ff69e9a"
+dependencies = [
+ "typenum",
+ "version_check",
+]
+
 [[package]]
 name = "getopts"
 version = "0.2.23"
@@ -1896,9 +1992,9 @@ dependencies = [
 
 [[package]]
 name = "hyper-util"
-version = "0.1.15"
+version = "0.1.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7f66d5bd4c6f02bf0542fad85d626775bab9258cf795a4256dcaf3161114d1df"
+checksum = "8d9b05277c7e8da2c93a568989bb6207bef0112e8d17df7a6eda4a3cf143bc5e"
 dependencies = [
  "base64 0.22.1",
  "bytes",
@@ -1912,7 +2008,7 @@ dependencies = [
  "libc",
  "percent-encoding",
  "pin-project-lite",
- "socket2",
+ "socket2 0.6.0",
  "system-configuration",
  "tokio",
  "tower-service",
@@ -2165,9 +2261,9 @@ dependencies = [
 
 [[package]]
 name = "instability"
-version = "0.3.7"
+version = "0.3.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0bf9fed6d91cfb734e7476a06bde8300a1b94e217e1b523b6f0cd1a01998c71d"
+checksum = "435d80800b936787d62688c927b6490e887c7ef5ff9ce922c6c6050fca75eb9a"
 dependencies = [
  "darling",
  "indoc",
@@ -2198,9 +2294,9 @@ dependencies = [
 
 [[package]]
 name = "io-uring"
-version = "0.7.8"
+version = "0.7.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b86e202f00093dcba4275d4636b93ef9dd75d025ae560d2521b45ea28ab49013"
+checksum = "d93587f37623a1a17d94ef2bc9ada592f5465fe7732084ab7beefabe5c77c0c4"
 dependencies = [
  "bitflags 2.9.1",
  "cfg-if",
@@ -2404,9 +2500,9 @@ dependencies = [
 
 [[package]]
 name = "libredox"
-version = "0.1.4"
+version = "0.1.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1580801010e535496706ba011c15f8532df6b42297d2e471fec38ceadd8c0638"
+checksum = "4488594b9328dee448adb906d8b126d9b7deb7cf5c22161ee591610bb1be83c0"
 dependencies = [
  "bitflags 2.9.1",
  "libc",
@@ -2539,6 +2635,22 @@ dependencies = [
  "serde_json",
 ]
 
+[[package]]
+name = "mcp_test_support"
+version = "0.0.0"
+dependencies = [
+ "anyhow",
+ "assert_cmd",
+ "codex-mcp-server",
+ "mcp-types",
+ "pretty_assertions",
+ "serde_json",
+ "shlex",
+ "tempfile",
+ "tokio",
+ "wiremock",
+]
+
 [[package]]
 name = "memchr"
 version = "2.7.5"
@@ -3214,9 +3326,9 @@ dependencies = [
 
 [[package]]
 name = "rand"
-version = "0.9.1"
+version = "0.9.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9fbfd9d094a40bf3ae768db9361049ace4c0e04a4fd6b359518bd7b73a73dd97"
+checksum = "6db2770f06117d490610c7488547d543617b21bfa07796d7a12f6f1bd53850d1"
 dependencies = [
  "rand_chacha 0.9.0",
  "rand_core 0.9.3",
@@ -3263,8 +3375,7 @@ dependencies = [
 [[package]]
 name = "ratatui"
 version = "0.29.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eabd94c2f37801c20583fc49dd5cd6b0ba68c716787c2dd6ed18571e1e63117b"
+source = "git+https://github.com/nornagon/ratatui?branch=nornagon-v0.29.0-patch#bca287ddc5d38fe088c79e2eda22422b96226f2e"
 dependencies = [
  "bitflags 2.9.1",
  "cassowary",
@@ -3369,9 +3480,9 @@ dependencies = [
 
 [[package]]
 name = "redox_syscall"
-version = "0.5.13"
+version = "0.5.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0d04b7d0ee6b4a0207a0a7adb104d23ecb0b47d6beae7152d0fa34b692b29fd6"
+checksum = "7e8af0dde094006011e6a740d4879319439489813bd0bcdc7d821beaeeff48ec"
 dependencies = [
  "bitflags 2.9.1",
 ]
@@ -3519,9 +3630,9 @@ dependencies = [
 
 [[package]]
 name = "rgb"
-version = "0.8.51"
+version = "0.8.52"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a457e416a0f90d246a4c3288bd7a25b2304ca727f253f95be383dd17af56be8f"
+checksum = "0c6a884d2998352bb4daf0183589aec883f16a6da1f4dde84d8e2e9a5409a1ce"
 
 [[package]]
 name = "ring"
@@ -3597,22 +3708,22 @@ dependencies = [
 
 [[package]]
 name = "rustix"
-version = "1.0.7"
+version = "1.0.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c71e83d6afe7ff64890ec6b71d6a69bb8a610ab78ce364b3352876bb4c801266"
+checksum = "11181fbabf243db407ef8df94a6ce0b2f9a733bd8be4ad02b4eda9602296cac8"
 dependencies = [
  "bitflags 2.9.1",
  "errno",
  "libc",
  "linux-raw-sys 0.9.4",
- "windows-sys 0.59.0",
+ "windows-sys 0.60.2",
 ]
 
 [[package]]
 name = "rustls"
-version = "0.23.28"
+version = "0.23.29"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7160e3e10bf4535308537f3c4e1641468cd0e485175d6163087c0393c7d46643"
+checksum = "2491382039b29b9b11ff08b76ff6c97cf287671dbb74f0be44bda389fffe9bd1"
 dependencies = [
  "once_cell",
  "rustls-pki-types",
@@ -3632,9 +3743,9 @@ dependencies = [
 
 [[package]]
 name = "rustls-webpki"
-version = "0.103.3"
+version = "0.103.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e4a72fe2bcf7a6ac6fd7d0b9e5cb68aeb7d4c0a0271730218b3e92d43b4eb435"
+checksum = "0a17884ae0c1b773f1ccd2bd4a8c72f16da897310a98b0e84bf349ad5ead92fc"
 dependencies = [
  "ring",
  "rustls-pki-types",
@@ -3860,9 +3971,9 @@ dependencies = [
 
 [[package]]
 name = "serde_json"
-version = "1.0.140"
+version = "1.0.141"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "20068b6e96dc6c9bd23e01df8827e6c7e1f2fddd43c21810382803c136b99373"
+checksum = "30b9eff21ebe718216c6ec64e1d9ac57087aad11efc64e32002bce4a0d4c03d3"
 dependencies = [
  "indexmap 2.10.0",
  "itoa",
@@ -3944,6 +4055,17 @@ dependencies = [
  "syn 2.0.104",
 ]
 
+[[package]]
+name = "sha1"
+version = "0.10.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e3bf829a2d51ab4a5ddf1352d8470c140cadc8301b2ae1789db023f01cedd6ba"
+dependencies = [
+ "cfg-if",
+ "cpufeatures",
+ "digest",
+]
+
 [[package]]
 name = "sharded-slab"
 version = "0.1.7"
@@ -4044,6 +4166,16 @@ dependencies = [
  "windows-sys 0.52.0",
 ]
 
+[[package]]
+name = "socket2"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "233504af464074f9d066d7b5416c5f9b894a5862a6506e306f7b816cdd6f1807"
+dependencies = [
+ "libc",
+ "windows-sys 0.59.0",
+]
+
 [[package]]
 name = "stable_deref_trait"
 version = "1.2.0"
@@ -4187,9 +4319,9 @@ dependencies = [
 
 [[package]]
 name = "strum"
-version = "0.27.1"
+version = "0.27.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f64def088c51c9510a8579e3c5d67c65349dcf755e5479ad3d010aa6454e2c32"
+checksum = "af23d6f6c1a224baef9d3f61e287d2761385a5b88fdab4eb4c6f11aeb54c4bcf"
 
 [[package]]
 name = "strum_macros"
@@ -4206,14 +4338,13 @@ dependencies = [
 
 [[package]]
 name = "strum_macros"
-version = "0.27.1"
+version = "0.27.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c77a8c5abcaf0f9ce05d62342b7d298c346515365c36b673df4ebe3ced01fde8"
+checksum = "7695ce3845ea4b33927c055a39dc438a45b059f7c1b3d91d38d10355fb8cbca7"
 dependencies = [
  "heck",
  "proc-macro2",
  "quote",
- "rustversion",
  "syn 2.0.104",
 ]
 
@@ -4336,7 +4467,7 @@ dependencies = [
  "fastrand",
  "getrandom 0.3.3",
  "once_cell",
- "rustix 1.0.7",
+ "rustix 1.0.8",
  "windows-sys 0.59.0",
 ]
 
@@ -4357,7 +4488,7 @@ version = "0.4.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "45c6481c4829e4cc63825e62c49186a34538b7b2750b73b266581ffb612fb5ed"
 dependencies = [
- "rustix 1.0.7",
+ "rustix 1.0.8",
  "windows-sys 0.59.0",
 ]
 
@@ -4503,7 +4634,7 @@ dependencies = [
  "pin-project-lite",
  "signal-hook-registry",
  "slab",
- "socket2",
+ "socket2 0.5.10",
  "tokio-macros",
  "windows-sys 0.52.0",
 ]
@@ -4590,9 +4721,9 @@ dependencies = [
 
 [[package]]
 name = "toml"
-version = "0.9.1"
+version = "0.9.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0207d6ed1852c2a124c1fbec61621acb8330d2bf969a5d0643131e9affd985a5"
+checksum = "ed0aee96c12fa71097902e0bb061a5e1ebd766a6636bb605ba401c45c1650eac"
 dependencies = [
  "indexmap 2.10.0",
  "serde",
@@ -4636,18 +4767,18 @@ dependencies = [
 
 [[package]]
 name = "toml_parser"
-version = "1.0.0"
+version = "1.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b5c1c469eda89749d2230d8156a5969a69ffe0d6d01200581cdc6110674d293e"
+checksum = "97200572db069e74c512a14117b296ba0a80a30123fbbb5aa1f4a348f639ca30"
 dependencies = [
  "winnow",
 ]
 
 [[package]]
 name = "toml_writer"
-version = "1.0.0"
+version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b679217f2848de74cabd3e8fc5e6d66f40b7da40f8e1954d92054d9010690fd5"
+checksum = "fcc842091f2def52017664b53082ecbbeb5c7731092bad69d2c63050401dfd64"
 
 [[package]]
 name = "tower"
@@ -4780,9 +4911,9 @@ dependencies = [
 
 [[package]]
 name = "tree-sitter"
-version = "0.25.6"
+version = "0.25.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a7cf18d43cbf0bfca51f657132cc616a5097edc4424d538bae6fa60142eaf9f0"
+checksum = "6d7b8994f367f16e6fa14b5aebbcb350de5d7cbea82dc5b00ae997dd71680dd2"
 dependencies = [
  "cc",
  "regex",
@@ -4851,6 +4982,12 @@ dependencies = [
  "unicode-width 0.2.0",
 ]
 
+[[package]]
+name = "typenum"
+version = "1.18.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1dccffe3ce07af9386bfd29e80c0ab1a8205a2fc34e4bcd40364df902cfa8f3f"
+
 [[package]]
 name = "unicase"
 version = "2.8.1"
@@ -5018,6 +5155,12 @@ dependencies = [
  "wit-bindgen-rt",
 ]
 
+[[package]]
+name = "wasite"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b8dad83b4f25e74f184f64c43b150b91efe7647395b42289f38e50566d82855b"
+
 [[package]]
 name = "wasm-bindgen"
 version = "0.2.100"
@@ -5118,6 +5261,17 @@ version = "0.1.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a751b3277700db47d3e574514de2eced5e54dc8a5436a3bf7a0b248b2cee16f3"
 
+[[package]]
+name = "whoami"
+version = "1.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6994d13118ab492c3c80c1f81928718159254c53c472bf9ce36f8dae4add02a7"
+dependencies = [
+ "redox_syscall",
+ "wasite",
+ "web-sys",
+]
+
 [[package]]
 name = "wildmatch"
 version = "2.4.0"
@@ -5446,9 +5600,9 @@ checksum = "271414315aff87387382ec3d271b52d7ae78726f5d44ac98b4f4030c91880486"
 
 [[package]]
 name = "winnow"
-version = "0.7.11"
+version = "0.7.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "74c7b26e3480b707944fc872477815d29a8e429d2f93a1ce000f5fa84a15cbcd"
+checksum = "f3edebf492c8125044983378ecb5766203ad3b4c2f7a922bd7dd207f6d443e95"
 dependencies = [
  "memchr",
 ]

codex-rs/Cargo.toml

@@ -3,6 +3,7 @@ resolver = "2"
 members = [
     "ansi-escape",
     "apply-patch",
+    "arg0",
     "cli",
     "common",
     "core",
@@ -40,3 +41,8 @@ strip = "symbols"
 
 # See https://github.com/openai/codex/issues/1411 for details.
 codegen-units = 1
+
+[patch.crates-io]
+# ratatui = { path = "../../ratatui" }
+ratatui = { git = "https://github.com/nornagon/ratatui", branch = "nornagon-v0.29.0-patch" }
+

codex-rs/apply-patch/Cargo.toml

@@ -14,7 +14,7 @@ workspace = true
 anyhow = "1"
 similar = "2.7.0"
 thiserror = "2.0.12"
-tree-sitter = "0.25.3"
+tree-sitter = "0.25.8"
 tree-sitter-bash = "0.25.0"
 
 [dev-dependencies]

codex-rs/arg0/Cargo.toml

@@ -0,0 +1,19 @@
+[package]
+name = "codex-arg0"
+version = { workspace = true }
+edition = "2024"
+
+[lib]
+name = "codex_arg0"
+path = "src/lib.rs"
+
+[lints]
+workspace = true
+
+[dependencies]
+anyhow = "1"
+codex-apply-patch = { path = "../apply-patch" }
+codex-core = { path = "../core" }
+codex-linux-sandbox = { path = "../linux-sandbox" }
+dotenvy = "0.15.7"
+tokio = { version = "1", features = ["rt-multi-thread"] }

codex-rs/arg0/src/lib.rs

@@ -0,0 +1,89 @@
+use std::future::Future;
+use std::path::Path;
+use std::path::PathBuf;
+
+/// While we want to deploy the Codex CLI as a single executable for simplicity,
+/// we also want to expose some of its functionality as distinct CLIs, so we use
+/// the "arg0 trick" to determine which CLI to dispatch. This effectively allows
+/// us to simulate deploying multiple executables as a single binary on Mac and
+/// Linux (but not Windows).
+///
+/// When the current executable is invoked through the hard-link or alias named
+/// `codex-linux-sandbox` we *directly* execute
+/// [`codex_linux_sandbox::run_main`] (which never returns). Otherwise we:
+///
+/// 1.  Use [`dotenvy::from_path`] and [`dotenvy::dotenv`] to modify the
+///     environment before creating any threads.
+/// 2.  Construct a Tokio multi-thread runtime.
+/// 3.  Derive the path to the current executable (so children can re-invoke the
+///     sandbox) when running on Linux.
+/// 4.  Execute the provided async `main_fn` inside that runtime, forwarding any
+///     error. Note that `main_fn` receives `codex_linux_sandbox_exe:
+///     Option<PathBuf>`, as an argument, which is generally needed as part of
+///     constructing [`codex_core::config::Config`].
+///
+/// This function should be used to wrap any `main()` function in binary crates
+/// in this workspace that depends on these helper CLIs.
+pub fn arg0_dispatch_or_else<F, Fut>(main_fn: F) -> anyhow::Result<()>
+where
+    F: FnOnce(Option<PathBuf>) -> Fut,
+    Fut: Future<Output = anyhow::Result<()>>,
+{
+    // Determine if we were invoked via the special alias.
+    let mut args = std::env::args_os();
+    let argv0 = args.next().unwrap_or_default();
+    let exe_name = Path::new(&argv0)
+        .file_name()
+        .and_then(|s| s.to_str())
+        .unwrap_or("");
+
+    if exe_name == "codex-linux-sandbox" {
+        // Safety: [`run_main`] never returns.
+        codex_linux_sandbox::run_main();
+    }
+
+    let argv1 = args.next().unwrap_or_default();
+    if argv1 == "--codex-run-as-apply-patch" {
+        let patch_arg = args.next().and_then(|s| s.to_str().map(|s| s.to_owned()));
+        let exit_code = match patch_arg {
+            Some(patch_arg) => {
+                let mut stdout = std::io::stdout();
+                let mut stderr = std::io::stderr();
+                match codex_apply_patch::apply_patch(&patch_arg, &mut stdout, &mut stderr) {
+                    Ok(()) => 0,
+                    Err(_) => 1,
+                }
+            }
+            None => {
+                eprintln!("Error: --codex-run-as-apply-patch requires a UTF-8 PATCH argument.");
+                1
+            }
+        };
+        std::process::exit(exit_code);
+    }
+
+    // This modifies the environment, which is not thread-safe, so do this
+    // before creating any threads/the Tokio runtime.
+    load_dotenv();
+
+    // Regular invocation – create a Tokio runtime and execute the provided
+    // async entry-point.
+    let runtime = tokio::runtime::Runtime::new()?;
+    runtime.block_on(async move {
+        let codex_linux_sandbox_exe: Option<PathBuf> = if cfg!(target_os = "linux") {
+            std::env::current_exe().ok()
+        } else {
+            None
+        };
+
+        main_fn(codex_linux_sandbox_exe).await
+    })
+}
+
+/// Load env vars from ~/.codex/.env and `$(pwd)/.env`.
+fn load_dotenv() {
+    if let Ok(codex_home) = codex_core::config::find_codex_home() {
+        dotenvy::from_path(codex_home.join(".env")).ok();
+    }
+    dotenvy::dotenv().ok();
+}

codex-rs/chatgpt/src/apply_command.rs

@@ -1,3 +1,5 @@
+use std::path::PathBuf;
+
 use clap::Parser;
 use codex_common::CliConfigOverrides;
 use codex_core::config::Config;
@@ -17,7 +19,10 @@ pub struct ApplyCommand {
     #[clap(flatten)]
     pub config_overrides: CliConfigOverrides,
 }
-pub async fn run_apply_command(apply_cli: ApplyCommand) -> anyhow::Result<()> {
+pub async fn run_apply_command(
+    apply_cli: ApplyCommand,
+    cwd: Option<PathBuf>,
+) -> anyhow::Result<()> {
     let config = Config::load_with_cli_overrides(
         apply_cli
             .config_overrides
@@ -29,10 +34,13 @@ pub async fn run_apply_command(apply_cli: ApplyCommand) -> anyhow::Result<()> {
     init_chatgpt_token_from_auth(&config.codex_home).await?;
 
     let task_response = get_task(&config, apply_cli.task_id).await?;
-    apply_diff_from_task(task_response).await
+    apply_diff_from_task(task_response, cwd).await
 }
 
-pub async fn apply_diff_from_task(task_response: GetTaskResponse) -> anyhow::Result<()> {
+pub async fn apply_diff_from_task(
+    task_response: GetTaskResponse,
+    cwd: Option<PathBuf>,
+) -> anyhow::Result<()> {
     let diff_turn = match task_response.current_diff_task_turn {
         Some(turn) => turn,
         None => anyhow::bail!("No diff turn found"),
@@ -42,13 +50,17 @@ pub async fn apply_diff_from_task(task_response: GetTaskResponse) -> anyhow::Res
         _ => None,
     });
     match output_diff {
-        Some(output_diff) => apply_diff(&output_diff.diff).await,
+        Some(output_diff) => apply_diff(&output_diff.diff, cwd).await,
         None => anyhow::bail!("No PR output item found"),
     }
 }
 
-async fn apply_diff(diff: &str) -> anyhow::Result<()> {
-    let toplevel_output = tokio::process::Command::new("git")
+async fn apply_diff(diff: &str, cwd: Option<PathBuf>) -> anyhow::Result<()> {
+    let mut cmd = tokio::process::Command::new("git");
+    if let Some(cwd) = cwd {
+        cmd.current_dir(cwd);
+    }
+    let toplevel_output = cmd
         .args(vec!["rev-parse", "--show-toplevel"])
         .output()
         .await?;

codex-rs/chatgpt/tests/apply_command_e2e.rs

@@ -78,17 +78,7 @@ async fn test_apply_command_creates_fibonacci_file() {
         .await
         .expect("Failed to load fixture");
 
-    let original_dir = std::env::current_dir().expect("Failed to get current dir");
-    std::env::set_current_dir(repo_path).expect("Failed to change directory");
-    struct DirGuard(std::path::PathBuf);
-    impl Drop for DirGuard {
-        fn drop(&mut self) {
-            let _ = std::env::set_current_dir(&self.0);
-        }
-    }
-    let _guard = DirGuard(original_dir);
-
-    apply_diff_from_task(task_response)
+    apply_diff_from_task(task_response, Some(repo_path.to_path_buf()))
         .await
         .expect("Failed to apply diff from task");
 
@@ -173,7 +163,7 @@ console.log(fib(10));
         .await
         .expect("Failed to load fixture");
 
-    let apply_result = apply_diff_from_task(task_response).await;
+    let apply_result = apply_diff_from_task(task_response, Some(repo_path.to_path_buf())).await;
 
     assert!(
         apply_result.is_err(),

codex-rs/cli/Cargo.toml

@@ -18,12 +18,12 @@ workspace = true
 anyhow = "1"
 clap = { version = "4", features = ["derive"] }
 clap_complete = "4"
+codex-arg0 = { path = "../arg0" }
 codex-chatgpt = { path = "../chatgpt" }
 codex-core = { path = "../core" }
 codex-common = { path = "../common", features = ["cli"] }
 codex-exec = { path = "../exec" }
 codex-login = { path = "../login" }
-codex-linux-sandbox = { path = "../linux-sandbox" }
 codex-mcp-server = { path = "../mcp-server" }
 codex-tui = { path = "../tui" }
 serde_json = "1"

codex-rs/cli/src/main.rs

@@ -2,6 +2,7 @@ use clap::CommandFactory;
 use clap::Parser;
 use clap_complete::Shell;
 use clap_complete::generate;
+use codex_arg0::arg0_dispatch_or_else;
 use codex_chatgpt::apply_command::ApplyCommand;
 use codex_chatgpt::apply_command::run_apply_command;
 use codex_cli::LandlockCommand;
@@ -92,7 +93,7 @@ struct LoginCommand {
 }
 
 fn main() -> anyhow::Result<()> {
-    codex_linux_sandbox::run_with_sandbox(|codex_linux_sandbox_exe| async move {
+    arg0_dispatch_or_else(|codex_linux_sandbox_exe| async move {
         cli_main(codex_linux_sandbox_exe).await?;
         Ok(())
     })
@@ -105,7 +106,8 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
         None => {
             let mut tui_cli = cli.interactive;
             prepend_config_flags(&mut tui_cli.config_overrides, cli.config_overrides);
-            codex_tui::run_main(tui_cli, codex_linux_sandbox_exe)?;
+            let usage = codex_tui::run_main(tui_cli, codex_linux_sandbox_exe)?;
+            println!("{}", codex_core::protocol::FinalOutput::from(usage));
         }
         Some(Subcommand::Exec(mut exec_cli)) => {
             prepend_config_flags(&mut exec_cli.config_overrides, cli.config_overrides);
@@ -145,7 +147,7 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
         },
         Some(Subcommand::Apply(mut apply_cli)) => {
             prepend_config_flags(&mut apply_cli.config_overrides, cli.config_overrides);
-            run_apply_command(apply_cli).await?;
+            run_apply_command(apply_cli, None).await?;
         }
     }
 

codex-rs/cli/src/proto.rs

@@ -4,6 +4,7 @@ use std::sync::Arc;
 use clap::Parser;
 use codex_common::CliConfigOverrides;
 use codex_core::Codex;
+use codex_core::CodexSpawnOk;
 use codex_core::config::Config;
 use codex_core::config::ConfigOverrides;
 use codex_core::protocol::Submission;
@@ -35,7 +36,7 @@ pub async fn run_main(opts: ProtoCli) -> anyhow::Result<()> {
 
     let config = Config::load_with_cli_overrides(overrides_vec, ConfigOverrides::default())?;
     let ctrl_c = notify_on_sigint();
-    let (codex, _init_id) = Codex::spawn(config, ctrl_c.clone()).await?;
+    let CodexSpawnOk { codex, .. } = Codex::spawn(config, ctrl_c.clone()).await?;
     let codex = Arc::new(codex);
 
     // Task that reads JSON lines from stdin and forwards to Submission Queue

codex-rs/common/src/config_override.rs

@@ -64,7 +64,11 @@ impl CliConfigOverrides {
                 // `-c model=o3` without the quotes.
                 let value: Value = match parse_toml_value(value_str) {
                     Ok(v) => v,
-                    Err(_) => Value::String(value_str.to_string()),
+                    Err(_) => {
+                        // Strip leading/trailing quotes if present
+                        let trimmed = value_str.trim().trim_matches(|c| c == '"' || c == '\'');
+                        Value::String(trimmed.to_string())
+                    }
                 };
 
                 Ok((key.to_string(), value))

codex-rs/config.md

@@ -92,6 +92,32 @@ http_headers = { "X-Example-Header" = "example-value" }
 env_http_headers = { "X-Example-Features": "EXAMPLE_FEATURES" }
 ```
 
+### Per-provider network tuning
+
+The following optional settings control retry behaviour and streaming idle timeouts **per model provider**. They must be specified inside the corresponding `[model_providers.<id>]` block in `config.toml`. (Older releases accepted top‑level keys; those are now ignored.)
+
+Example:
+
+```toml
+[model_providers.openai]
+name = "OpenAI"
+base_url = "https://api.openai.com/v1"
+env_key = "OPENAI_API_KEY"
+# network tuning overrides (all optional; falls back to built‑in defaults)
+request_max_retries = 4            # retry failed HTTP requests
+stream_max_retries = 10            # retry dropped SSE streams
+stream_idle_timeout_ms = 300000    # 5m idle timeout
+```
+
+#### request_max_retries
+How many times Codex will retry a failed HTTP request to the model provider. Defaults to `4`.
+
+#### stream_max_retries
+Number of times Codex will attempt to reconnect when a streaming response is interrupted. Defaults to `10`.
+
+#### stream_idle_timeout_ms
+How long Codex will wait for activity on a streaming response before treating the connection as lost. Defaults to `300_000` (5 minutes).
+
 ## model_provider
 
 Identifies which provider to use from the `model_providers` map. Defaults to `"openai"`. You can override the `base_url` for the built-in `openai` provider via the `OPENAI_BASE_URL` environment variable.
@@ -444,7 +470,7 @@ Currently, `"vscode"` is the default, though Codex does not verify VS Code is in
 
 ## hide_agent_reasoning
 
-Codex intermittently emits "reasoning" events that show the model’s internal "thinking" before it produces a final answer. Some users may find these events distracting, especially in CI logs or minimal terminal output.
+Codex intermittently emits "reasoning" events that show the model's internal "thinking" before it produces a final answer. Some users may find these events distracting, especially in CI logs or minimal terminal output.
 
 Setting `hide_agent_reasoning` to `true` suppresses these events in **both** the TUI as well as the headless `exec` sub-command:
 
@@ -472,14 +498,5 @@ Options that are specific to the TUI.
 
 ```toml
 [tui]
-# This will make it so that Codex does not try to process mouse events, which
-# means your Terminal's native drag-to-text to text selection and copy/paste
-# should work. The tradeoff is that Codex will not receive any mouse events, so
-# it will not be possible to use the mouse to scroll conversation history.
-#
-# Note that most terminals support holding down a modifier key when using the
-# mouse to support text selection. For example, even if Codex mouse capture is
-# enabled (i.e., this is set to `false`), you can still hold down alt while
-# dragging the mouse to select text.
-disable_mouse_capture = true  # defaults to `false`
+# More to come here
 ```

codex-rs/core/Cargo.toml

@@ -22,13 +22,16 @@ env-flags = "0.1.1"
 eventsource-stream = "0.2.3"
 fs2 = "0.4.3"
 futures = "0.3"
+libc = "0.2.174"
 mcp-types = { path = "../mcp-types" }
 mime_guess = "2.0"
 rand = "0.9"
 reqwest = { version = "0.12", features = ["json", "stream"] }
 serde = { version = "1", features = ["derive"] }
 serde_json = "1"
-strum_macros = "0.27.1"
+sha1 = "0.10.6"
+shlex = "1.3.0"
+strum_macros = "0.27.2"
 thiserror = "2.0.12"
 time = { version = "0.3", features = ["formatting", "local-offset", "macros"] }
 tokio = { version = "1", features = [
@@ -39,12 +42,14 @@ tokio = { version = "1", features = [
     "signal",
 ] }
 tokio-util = "0.7.14"
-toml = "0.9.1"
+toml = "0.9.2"
 tracing = { version = "0.1.41", features = ["log"] }
-tree-sitter = "0.25.3"
+tree-sitter = "0.25.8"
 tree-sitter-bash = "0.25.0"
 uuid = { version = "1", features = ["serde", "v4"] }
 wildmatch = "2.4.0"
+whoami = "1.6.0"
+
 
 [target.'cfg(target_os = "linux")'.dependencies]
 landlock = "0.4.1"
@@ -60,9 +65,11 @@ openssl-sys = { version = "*", features = ["vendored"] }
 
 [dev-dependencies]
 assert_cmd = "2"
+core_test_support = { path = "tests/common" }
 maplit = "1.0.2"
 predicates = "3"
 pretty_assertions = "1.4.1"
 tempfile = "3"
 tokio-test = "0.4"
+walkdir = "2.5.0"
 wiremock = "0.6"

codex-rs/core/README.md

@@ -2,9 +2,18 @@
 
 This crate implements the business logic for Codex. It is designed to be used by the various Codex UIs written in Rust.
 
-Though for non-Rust UIs, we are also working to define a _protocol_ for talking to Codex. See:
+## Dependencies
 
-- [Specification](../docs/protocol_v1.md)
-- [Rust types](./src/protocol.rs)
+Note that `codex-core` makes some assumptions about certain helper utilities being available in the environment. Currently, this
 
-You can use the `proto` subcommand using the executable in the [`cli` crate](../cli) to speak the protocol using newline-delimited-JSON over stdin/stdout.
+### macOS
+
+Expects `/usr/bin/sandbox-exec` to be present.
+
+### Linux
+
+Expects the binary containing `codex-core` to run the equivalent of `codex debug landlock` when `arg0` is `codex-linux-sandbox`. See the `codex-arg0` crate for details.
+
+### All Platforms
+
+Expects the binary containing `codex-core` to simulate the virtual `apply_patch` CLI when `arg1` is `--codex-run-as-apply-patch`. See the `codex-arg0` crate for details.

codex-rs/core/src/apply_patch.rs

@@ -0,0 +1,406 @@
+use crate::codex::Session;
+use crate::models::FunctionCallOutputPayload;
+use crate::models::ResponseInputItem;
+use crate::protocol::Event;
+use crate::protocol::EventMsg;
+use crate::protocol::FileChange;
+use crate::protocol::PatchApplyBeginEvent;
+use crate::protocol::PatchApplyEndEvent;
+use crate::protocol::ReviewDecision;
+use crate::safety::SafetyCheck;
+use crate::safety::assess_patch_safety;
+use anyhow::Context;
+use codex_apply_patch::AffectedPaths;
+use codex_apply_patch::ApplyPatchAction;
+use codex_apply_patch::ApplyPatchFileChange;
+use codex_apply_patch::print_summary;
+use std::collections::HashMap;
+use std::path::Path;
+use std::path::PathBuf;
+
+pub(crate) async fn apply_patch(
+    sess: &Session,
+    sub_id: String,
+    call_id: String,
+    action: ApplyPatchAction,
+) -> ResponseInputItem {
+    let writable_roots_snapshot = {
+        #[allow(clippy::unwrap_used)]
+        let guard = sess.writable_roots.lock().unwrap();
+        guard.clone()
+    };
+
+    let auto_approved = match assess_patch_safety(
+        &action,
+        sess.approval_policy,
+        &writable_roots_snapshot,
+        &sess.cwd,
+    ) {
+        SafetyCheck::AutoApprove { .. } => true,
+        SafetyCheck::AskUser => {
+            // Compute a readable summary of path changes to include in the
+            // approval request so the user can make an informed decision.
+            let rx_approve = sess
+                .request_patch_approval(sub_id.clone(), call_id.clone(), &action, None, None)
+                .await;
+            match rx_approve.await.unwrap_or_default() {
+                ReviewDecision::Approved | ReviewDecision::ApprovedForSession => false,
+                ReviewDecision::Denied | ReviewDecision::Abort => {
+                    return ResponseInputItem::FunctionCallOutput {
+                        call_id,
+                        output: FunctionCallOutputPayload {
+                            content: "patch rejected by user".to_string(),
+                            success: Some(false),
+                        },
+                    };
+                }
+            }
+        }
+        SafetyCheck::Reject { reason } => {
+            return ResponseInputItem::FunctionCallOutput {
+                call_id,
+                output: FunctionCallOutputPayload {
+                    content: format!("patch rejected: {reason}"),
+                    success: Some(false),
+                },
+            };
+        }
+    };
+
+    // Verify write permissions before touching the filesystem.
+    let writable_snapshot = {
+        #[allow(clippy::unwrap_used)]
+        sess.writable_roots.lock().unwrap().clone()
+    };
+
+    if let Some(offending) = first_offending_path(&action, &writable_snapshot, &sess.cwd) {
+        let root = offending.parent().unwrap_or(&offending).to_path_buf();
+
+        let reason = Some(format!(
+            "grant write access to {} for this session",
+            root.display()
+        ));
+
+        let rx = sess
+            .request_patch_approval(
+                sub_id.clone(),
+                call_id.clone(),
+                &action,
+                reason.clone(),
+                Some(root.clone()),
+            )
+            .await;
+
+        if !matches!(
+            rx.await.unwrap_or_default(),
+            ReviewDecision::Approved | ReviewDecision::ApprovedForSession
+        ) {
+            return ResponseInputItem::FunctionCallOutput {
+                call_id,
+                output: FunctionCallOutputPayload {
+                    content: "patch rejected by user".to_string(),
+                    success: Some(false),
+                },
+            };
+        }
+
+        // user approved, extend writable roots for this session
+        #[allow(clippy::unwrap_used)]
+        sess.writable_roots.lock().unwrap().push(root);
+    }
+
+    let _ = sess
+        .tx_event
+        .send(Event {
+            id: sub_id.clone(),
+            msg: EventMsg::PatchApplyBegin(PatchApplyBeginEvent {
+                call_id: call_id.clone(),
+                auto_approved,
+                changes: convert_apply_patch_to_protocol(&action),
+            }),
+        })
+        .await;
+
+    let mut stdout = Vec::new();
+    let mut stderr = Vec::new();
+    // Enforce writable roots. If a write is blocked, collect offending root
+    // and prompt the user to extend permissions.
+    let mut result = apply_changes_from_apply_patch_and_report(&action, &mut stdout, &mut stderr);
+
+    if let Err(err) = &result {
+        if err.kind() == std::io::ErrorKind::PermissionDenied {
+            // Determine first offending path.
+            let offending_opt = action
+                .changes()
+                .iter()
+                .flat_map(|(path, change)| match change {
+                    ApplyPatchFileChange::Add { .. } => vec![path.as_ref()],
+                    ApplyPatchFileChange::Delete => vec![path.as_ref()],
+                    ApplyPatchFileChange::Update {
+                        move_path: Some(move_path),
+                        ..
+                    } => {
+                        vec![path.as_ref(), move_path.as_ref()]
+                    }
+                    ApplyPatchFileChange::Update {
+                        move_path: None, ..
+                    } => vec![path.as_ref()],
+                })
+                .find_map(|path: &Path| {
+                    // ApplyPatchAction promises to guarantee absolute paths.
+                    if !path.is_absolute() {
+                        panic!("apply_patch invariant failed: path is not absolute: {path:?}");
+                    }
+
+                    let writable = {
+                        #[allow(clippy::unwrap_used)]
+                        let roots = sess.writable_roots.lock().unwrap();
+                        roots.iter().any(|root| path.starts_with(root))
+                    };
+                    if writable {
+                        None
+                    } else {
+                        Some(path.to_path_buf())
+                    }
+                });
+
+            if let Some(offending) = offending_opt {
+                let root = offending.parent().unwrap_or(&offending).to_path_buf();
+
+                let reason = Some(format!(
+                    "grant write access to {} for this session",
+                    root.display()
+                ));
+                let rx = sess
+                    .request_patch_approval(
+                        sub_id.clone(),
+                        call_id.clone(),
+                        &action,
+                        reason.clone(),
+                        Some(root.clone()),
+                    )
+                    .await;
+                if matches!(
+                    rx.await.unwrap_or_default(),
+                    ReviewDecision::Approved | ReviewDecision::ApprovedForSession
+                ) {
+                    // Extend writable roots.
+                    #[allow(clippy::unwrap_used)]
+                    sess.writable_roots.lock().unwrap().push(root);
+                    stdout.clear();
+                    stderr.clear();
+                    result = apply_changes_from_apply_patch_and_report(
+                        &action,
+                        &mut stdout,
+                        &mut stderr,
+                    );
+                }
+            }
+        }
+    }
+
+    // Emit PatchApplyEnd event.
+    let success_flag = result.is_ok();
+    let _ = sess
+        .tx_event
+        .send(Event {
+            id: sub_id.clone(),
+            msg: EventMsg::PatchApplyEnd(PatchApplyEndEvent {
+                call_id: call_id.clone(),
+                stdout: String::from_utf8_lossy(&stdout).to_string(),
+                stderr: String::from_utf8_lossy(&stderr).to_string(),
+                success: success_flag,
+            }),
+        })
+        .await;
+
+    match result {
+        Ok(_) => ResponseInputItem::FunctionCallOutput {
+            call_id,
+            output: FunctionCallOutputPayload {
+                content: String::from_utf8_lossy(&stdout).to_string(),
+                success: None,
+            },
+        },
+        Err(e) => ResponseInputItem::FunctionCallOutput {
+            call_id,
+            output: FunctionCallOutputPayload {
+                content: format!("error: {e:#}, stderr: {}", String::from_utf8_lossy(&stderr)),
+                success: Some(false),
+            },
+        },
+    }
+}
+
+/// Return the first path in `hunks` that is NOT under any of the
+/// `writable_roots` (after normalising). If all paths are acceptable,
+/// returns None.
+fn first_offending_path(
+    action: &ApplyPatchAction,
+    writable_roots: &[PathBuf],
+    cwd: &Path,
+) -> Option<PathBuf> {
+    let changes = action.changes();
+    for (path, change) in changes {
+        let candidate = match change {
+            ApplyPatchFileChange::Add { .. } => path,
+            ApplyPatchFileChange::Delete => path,
+            ApplyPatchFileChange::Update { move_path, .. } => move_path.as_ref().unwrap_or(path),
+        };
+
+        let abs = if candidate.is_absolute() {
+            candidate.clone()
+        } else {
+            cwd.join(candidate)
+        };
+
+        let mut allowed = false;
+        for root in writable_roots {
+            let root_abs = if root.is_absolute() {
+                root.clone()
+            } else {
+                cwd.join(root)
+            };
+            if abs.starts_with(&root_abs) {
+                allowed = true;
+                break;
+            }
+        }
+
+        if !allowed {
+            return Some(candidate.clone());
+        }
+    }
+    None
+}
+
+pub(crate) fn convert_apply_patch_to_protocol(
+    action: &ApplyPatchAction,
+) -> HashMap<PathBuf, FileChange> {
+    let changes = action.changes();
+    let mut result = HashMap::with_capacity(changes.len());
+    for (path, change) in changes {
+        let protocol_change = match change {
+            ApplyPatchFileChange::Add { content } => FileChange::Add {
+                content: content.clone(),
+            },
+            ApplyPatchFileChange::Delete => FileChange::Delete,
+            ApplyPatchFileChange::Update {
+                unified_diff,
+                move_path,
+                new_content: _new_content,
+            } => FileChange::Update {
+                unified_diff: unified_diff.clone(),
+                move_path: move_path.clone(),
+            },
+        };
+        result.insert(path.clone(), protocol_change);
+    }
+    result
+}
+
+fn apply_changes_from_apply_patch_and_report(
+    action: &ApplyPatchAction,
+    stdout: &mut impl std::io::Write,
+    stderr: &mut impl std::io::Write,
+) -> std::io::Result<()> {
+    match apply_changes_from_apply_patch(action) {
+        Ok(affected_paths) => {
+            print_summary(&affected_paths, stdout)?;
+        }
+        Err(err) => {
+            writeln!(stderr, "{err:?}")?;
+        }
+    }
+
+    Ok(())
+}
+
+fn apply_changes_from_apply_patch(action: &ApplyPatchAction) -> anyhow::Result<AffectedPaths> {
+    let mut added: Vec<PathBuf> = Vec::new();
+    let mut modified: Vec<PathBuf> = Vec::new();
+    let mut deleted: Vec<PathBuf> = Vec::new();
+
+    let changes = action.changes();
+    for (path, change) in changes {
+        match change {
+            ApplyPatchFileChange::Add { content } => {
+                if let Some(parent) = path.parent() {
+                    if !parent.as_os_str().is_empty() {
+                        std::fs::create_dir_all(parent).with_context(|| {
+                            format!("Failed to create parent directories for {}", path.display())
+                        })?;
+                    }
+                }
+                std::fs::write(path, content)
+                    .with_context(|| format!("Failed to write file {}", path.display()))?;
+                added.push(path.clone());
+            }
+            ApplyPatchFileChange::Delete => {
+                std::fs::remove_file(path)
+                    .with_context(|| format!("Failed to delete file {}", path.display()))?;
+                deleted.push(path.clone());
+            }
+            ApplyPatchFileChange::Update {
+                unified_diff: _unified_diff,
+                move_path,
+                new_content,
+            } => {
+                if let Some(move_path) = move_path {
+                    if let Some(parent) = move_path.parent() {
+                        if !parent.as_os_str().is_empty() {
+                            std::fs::create_dir_all(parent).with_context(|| {
+                                format!(
+                                    "Failed to create parent directories for {}",
+                                    move_path.display()
+                                )
+                            })?;
+                        }
+                    }
+
+                    std::fs::rename(path, move_path)
+                        .with_context(|| format!("Failed to rename file {}", path.display()))?;
+                    std::fs::write(move_path, new_content)?;
+                    modified.push(move_path.clone());
+                    deleted.push(path.clone());
+                } else {
+                    std::fs::write(path, new_content)?;
+                    modified.push(path.clone());
+                }
+            }
+        }
+    }
+
+    Ok(AffectedPaths {
+        added,
+        modified,
+        deleted,
+    })
+}
+
+pub(crate) fn get_writable_roots(cwd: &Path) -> Vec<PathBuf> {
+    let mut writable_roots = Vec::new();
+    if cfg!(target_os = "macos") {
+        // On macOS, $TMPDIR is private to the user.
+        writable_roots.push(std::env::temp_dir());
+
+        // Allow pyenv to update its shims directory. Without this, any tool
+        // that happens to be managed by `pyenv` will fail with an error like:
+        //
+        //   pyenv: cannot rehash: $HOME/.pyenv/shims isn't writable
+        //
+        // which is emitted every time `pyenv` tries to run `rehash` (for
+        // example, after installing a new Python package that drops an entry
+        // point). Although the sandbox is intentionally read‑only by default,
+        // writing to the user's local `pyenv` directory is safe because it
+        // is already user‑writable and scoped to the current user account.
+        if let Ok(home_dir) = std::env::var("HOME") {
+            let pyenv_dir = PathBuf::from(home_dir).join(".pyenv");
+            writable_roots.push(pyenv_dir);
+        }
+    }
+
+    writable_roots.push(cwd.to_path_buf());
+
+    writable_roots
+}

codex-rs/core/src/bash.rs

@@ -0,0 +1,219 @@
+use tree_sitter::Parser;
+use tree_sitter::Tree;
+use tree_sitter_bash::LANGUAGE as BASH;
+
+/// Parse the provided bash source using tree-sitter-bash, returning a Tree on
+/// success or None if parsing failed.
+pub fn try_parse_bash(bash_lc_arg: &str) -> Option<Tree> {
+    let lang = BASH.into();
+    let mut parser = Parser::new();
+    #[expect(clippy::expect_used)]
+    parser.set_language(&lang).expect("load bash grammar");
+    let old_tree: Option<&Tree> = None;
+    parser.parse(bash_lc_arg, old_tree)
+}
+
+/// Parse a script which may contain multiple simple commands joined only by
+/// the safe logical/pipe/sequencing operators: `&&`, `||`, `;`, `|`.
+///
+/// Returns `Some(Vec<command_words>)` if every command is a plain word‑only
+/// command and the parse tree does not contain disallowed constructs
+/// (parentheses, redirections, substitutions, control flow, etc.). Otherwise
+/// returns `None`.
+pub fn try_parse_word_only_commands_sequence(tree: &Tree, src: &str) -> Option<Vec<Vec<String>>> {
+    if tree.root_node().has_error() {
+        return None;
+    }
+
+    // List of allowed (named) node kinds for a "word only commands sequence".
+    // If we encounter a named node that is not in this list we reject.
+    const ALLOWED_KINDS: &[&str] = &[
+        // top level containers
+        "program",
+        "list",
+        "pipeline",
+        // commands & words
+        "command",
+        "command_name",
+        "word",
+        "string",
+        "string_content",
+        "raw_string",
+        "number",
+    ];
+    // Allow only safe punctuation / operator tokens; anything else causes reject.
+    const ALLOWED_PUNCT_TOKENS: &[&str] = &["&&", "||", ";", "|", "\"", "'"];
+
+    let root = tree.root_node();
+    let mut cursor = root.walk();
+    let mut stack = vec![root];
+    let mut command_nodes = Vec::new();
+    while let Some(node) = stack.pop() {
+        let kind = node.kind();
+        if node.is_named() {
+            if !ALLOWED_KINDS.contains(&kind) {
+                return None;
+            }
+            if kind == "command" {
+                command_nodes.push(node);
+            }
+        } else {
+            // Reject any punctuation / operator tokens that are not explicitly allowed.
+            if kind.chars().any(|c| "&;|".contains(c)) && !ALLOWED_PUNCT_TOKENS.contains(&kind) {
+                return None;
+            }
+            if !(ALLOWED_PUNCT_TOKENS.contains(&kind) || kind.trim().is_empty()) {
+                // If it's a quote token or operator it's allowed above; we also allow whitespace tokens.
+                // Any other punctuation like parentheses, braces, redirects, backticks, etc are rejected.
+                return None;
+            }
+        }
+        for child in node.children(&mut cursor) {
+            stack.push(child);
+        }
+    }
+
+    let mut commands = Vec::new();
+    for node in command_nodes {
+        if let Some(words) = parse_plain_command_from_node(node, src) {
+            commands.push(words);
+        } else {
+            return None;
+        }
+    }
+    Some(commands)
+}
+
+fn parse_plain_command_from_node(cmd: tree_sitter::Node, src: &str) -> Option<Vec<String>> {
+    if cmd.kind() != "command" {
+        return None;
+    }
+    let mut words = Vec::new();
+    let mut cursor = cmd.walk();
+    for child in cmd.named_children(&mut cursor) {
+        match child.kind() {
+            "command_name" => {
+                let word_node = child.named_child(0)?;
+                if word_node.kind() != "word" {
+                    return None;
+                }
+                words.push(word_node.utf8_text(src.as_bytes()).ok()?.to_owned());
+            }
+            "word" | "number" => {
+                words.push(child.utf8_text(src.as_bytes()).ok()?.to_owned());
+            }
+            "string" => {
+                if child.child_count() == 3
+                    && child.child(0)?.kind() == "\""
+                    && child.child(1)?.kind() == "string_content"
+                    && child.child(2)?.kind() == "\""
+                {
+                    words.push(child.child(1)?.utf8_text(src.as_bytes()).ok()?.to_owned());
+                } else {
+                    return None;
+                }
+            }
+            "raw_string" => {
+                let raw_string = child.utf8_text(src.as_bytes()).ok()?;
+                let stripped = raw_string
+                    .strip_prefix('\'')
+                    .and_then(|s| s.strip_suffix('\''));
+                if let Some(s) = stripped {
+                    words.push(s.to_owned());
+                } else {
+                    return None;
+                }
+            }
+            _ => return None,
+        }
+    }
+    Some(words)
+}
+
+#[cfg(test)]
+mod tests {
+    #![allow(clippy::unwrap_used)]
+    use super::*;
+
+    fn parse_seq(src: &str) -> Option<Vec<Vec<String>>> {
+        let tree = try_parse_bash(src)?;
+        try_parse_word_only_commands_sequence(&tree, src)
+    }
+
+    #[test]
+    fn accepts_single_simple_command() {
+        let cmds = parse_seq("ls -1").unwrap();
+        assert_eq!(cmds, vec![vec!["ls".to_string(), "-1".to_string()]]);
+    }
+
+    #[test]
+    fn accepts_multiple_commands_with_allowed_operators() {
+        let src = "ls && pwd; echo 'hi there' | wc -l";
+        let cmds = parse_seq(src).unwrap();
+        let expected: Vec<Vec<String>> = vec![
+            vec!["wc".to_string(), "-l".to_string()],
+            vec!["echo".to_string(), "hi there".to_string()],
+            vec!["pwd".to_string()],
+            vec!["ls".to_string()],
+        ];
+        assert_eq!(cmds, expected);
+    }
+
+    #[test]
+    fn extracts_double_and_single_quoted_strings() {
+        let cmds = parse_seq("echo \"hello world\"").unwrap();
+        assert_eq!(
+            cmds,
+            vec![vec!["echo".to_string(), "hello world".to_string()]]
+        );
+
+        let cmds2 = parse_seq("echo 'hi there'").unwrap();
+        assert_eq!(
+            cmds2,
+            vec![vec!["echo".to_string(), "hi there".to_string()]]
+        );
+    }
+
+    #[test]
+    fn accepts_numbers_as_words() {
+        let cmds = parse_seq("echo 123 456").unwrap();
+        assert_eq!(
+            cmds,
+            vec![vec![
+                "echo".to_string(),
+                "123".to_string(),
+                "456".to_string()
+            ]]
+        );
+    }
+
+    #[test]
+    fn rejects_parentheses_and_subshells() {
+        assert!(parse_seq("(ls)").is_none());
+        assert!(parse_seq("ls || (pwd && echo hi)").is_none());
+    }
+
+    #[test]
+    fn rejects_redirections_and_unsupported_operators() {
+        assert!(parse_seq("ls > out.txt").is_none());
+        assert!(parse_seq("echo hi & echo bye").is_none());
+    }
+
+    #[test]
+    fn rejects_command_and_process_substitutions_and_expansions() {
+        assert!(parse_seq("echo $(pwd)").is_none());
+        assert!(parse_seq("echo `pwd`").is_none());
+        assert!(parse_seq("echo $HOME").is_none());
+        assert!(parse_seq("echo \"hi $USER\"").is_none());
+    }
+
+    #[test]
+    fn rejects_variable_assignment_prefix() {
+        assert!(parse_seq("FOO=bar ls").is_none());
+    }
+
+    #[test]
+    fn rejects_trailing_operator_parse_error() {
+        assert!(parse_seq("ls &&").is_none());
+    }
+}

codex-rs/core/src/chat_completions.rs

@@ -21,8 +21,6 @@ use crate::client_common::ResponseEvent;
 use crate::client_common::ResponseStream;
 use crate::error::CodexErr;
 use crate::error::Result;
-use crate::flags::OPENAI_REQUEST_MAX_RETRIES;
-use crate::flags::OPENAI_STREAM_IDLE_TIMEOUT_MS;
 use crate::models::ContentItem;
 use crate::models::ResponseItem;
 use crate::openai_tools::create_tools_json_for_chat_completions_api;
@@ -43,7 +41,7 @@ pub(crate) async fn stream_chat_completions(
 
     for item in &prompt.input {
         match item {
-            ResponseItem::Message { role, content } => {
+            ResponseItem::Message { role, content, .. } => {
                 let mut text = String::new();
                 for c in content {
                     match c {
@@ -60,6 +58,7 @@ pub(crate) async fn stream_chat_completions(
                 name,
                 arguments,
                 call_id,
+                ..
             } => {
                 messages.push(json!({
                     "role": "assistant",
@@ -121,6 +120,7 @@ pub(crate) async fn stream_chat_completions(
     );
 
     let mut attempt = 0;
+    let max_retries = provider.request_max_retries();
     loop {
         attempt += 1;
 
@@ -134,9 +134,13 @@ pub(crate) async fn stream_chat_completions(
 
         match res {
             Ok(resp) if resp.status().is_success() => {
-                let (tx_event, rx_event) = mpsc::channel::<Result<ResponseEvent>>(16);
+                let (tx_event, rx_event) = mpsc::channel::<Result<ResponseEvent>>(1600);
                 let stream = resp.bytes_stream().map_err(CodexErr::Reqwest);
-                tokio::spawn(process_chat_sse(stream, tx_event));
+                tokio::spawn(process_chat_sse(
+                    stream,
+                    tx_event,
+                    provider.stream_idle_timeout(),
+                ));
                 return Ok(ResponseStream { rx_event });
             }
             Ok(res) => {
@@ -146,7 +150,7 @@ pub(crate) async fn stream_chat_completions(
                     return Err(CodexErr::UnexpectedStatus(status, body));
                 }
 
-                if attempt > *OPENAI_REQUEST_MAX_RETRIES {
+                if attempt > max_retries {
                     return Err(CodexErr::RetryLimit(status));
                 }
 
@@ -162,7 +166,7 @@ pub(crate) async fn stream_chat_completions(
                 tokio::time::sleep(delay).await;
             }
             Err(e) => {
-                if attempt > *OPENAI_REQUEST_MAX_RETRIES {
+                if attempt > max_retries {
                     return Err(e.into());
                 }
                 let delay = backoff(attempt);
@@ -175,14 +179,15 @@ pub(crate) async fn stream_chat_completions(
 /// Lightweight SSE processor for the Chat Completions streaming format. The
 /// output is mapped onto Codex's internal [`ResponseEvent`] so that the rest
 /// of the pipeline can stay agnostic of the underlying wire format.
-async fn process_chat_sse<S>(stream: S, tx_event: mpsc::Sender<Result<ResponseEvent>>)
-where
+async fn process_chat_sse<S>(
+    stream: S,
+    tx_event: mpsc::Sender<Result<ResponseEvent>>,
+    idle_timeout: Duration,
+) where
     S: Stream<Item = Result<Bytes>> + Unpin,
 {
     let mut stream = stream.eventsource();
 
-    let idle_timeout = *OPENAI_STREAM_IDLE_TIMEOUT_MS;
-
     // State to accumulate a function call across streaming chunks.
     // OpenAI may split the `arguments` string over multiple `delta` events
     // until the chunk whose `finish_reason` is `tool_calls` is emitted. We
@@ -255,6 +260,7 @@ where
                     content: vec![ContentItem::OutputText {
                         text: content.to_string(),
                     }],
+                    id: None,
                 };
 
                 let _ = tx_event.send(Ok(ResponseEvent::OutputItemDone(item))).await;
@@ -296,6 +302,7 @@ where
                     "tool_calls" if fn_call_state.active => {
                         // Build the FunctionCall response item.
                         let item = ResponseItem::FunctionCall {
+                            id: None,
                             name: fn_call_state.name.clone().unwrap_or_else(|| "".to_string()),
                             arguments: fn_call_state.arguments.clone(),
                             call_id: fn_call_state.call_id.clone().unwrap_or_else(String::new),
@@ -398,6 +405,7 @@ where
                 }))) => {
                     if !this.cumulative.is_empty() {
                         let aggregated_item = crate::models::ResponseItem::Message {
+                            id: None,
                             role: "assistant".to_string(),
                             content: vec![crate::models::ContentItem::OutputText {
                                 text: std::mem::take(&mut this.cumulative),
@@ -426,6 +434,12 @@ where
                     // will never appear in a Chat Completions stream.
                     continue;
                 }
+                Poll::Ready(Some(Ok(ResponseEvent::OutputTextDelta(_))))
+                | Poll::Ready(Some(Ok(ResponseEvent::ReasoningSummaryDelta(_)))) => {
+                    // Deltas are ignored here since aggregation waits for the
+                    // final OutputItemDone.
+                    continue;
+                }
             }
         }
     }

codex-rs/core/src/client.rs

@@ -15,6 +15,7 @@ use tokio_util::io::ReaderStream;
 use tracing::debug;
 use tracing::trace;
 use tracing::warn;
+use uuid::Uuid;
 
 use crate::chat_completions::AggregateStreamExt;
 use crate::chat_completions::stream_chat_completions;
@@ -29,8 +30,6 @@ use crate::config_types::ReasoningSummary as ReasoningSummaryConfig;
 use crate::error::CodexErr;
 use crate::error::Result;
 use crate::flags::CODEX_RS_SSE_FIXTURE;
-use crate::flags::OPENAI_REQUEST_MAX_RETRIES;
-use crate::flags::OPENAI_STREAM_IDLE_TIMEOUT_MS;
 use crate::model_provider_info::ModelProviderInfo;
 use crate::model_provider_info::WireApi;
 use crate::models::ResponseItem;
@@ -44,6 +43,7 @@ pub struct ModelClient {
     config: Arc<Config>,
     client: reqwest::Client,
     provider: ModelProviderInfo,
+    session_id: Uuid,
     effort: ReasoningEffortConfig,
     summary: ReasoningSummaryConfig,
 }
@@ -54,11 +54,13 @@ impl ModelClient {
         provider: ModelProviderInfo,
         effort: ReasoningEffortConfig,
         summary: ReasoningSummaryConfig,
+        session_id: Uuid,
     ) -> Self {
         Self {
             config,
             client: reqwest::Client::new(),
             provider,
+            session_id,
             effort,
             summary,
         }
@@ -109,12 +111,21 @@ impl ModelClient {
         if let Some(path) = &*CODEX_RS_SSE_FIXTURE {
             // short circuit for tests
             warn!(path, "Streaming from fixture");
-            return stream_from_fixture(path).await;
+            return stream_from_fixture(path, self.provider.clone()).await;
         }
 
         let full_instructions = prompt.get_full_instructions(&self.config.model);
         let tools_json = create_tools_json_for_responses_api(prompt, &self.config.model)?;
         let reasoning = create_reasoning_param_for_request(&self.config, self.effort, self.summary);
+
+        // Request encrypted COT if we are not storing responses,
+        // otherwise reasoning items will be referenced by ID
+        let include = if !prompt.store && reasoning.is_some() {
+            vec!["reasoning.encrypted_content".to_string()]
+        } else {
+            vec![]
+        };
+
         let payload = ResponsesApiRequest {
             model: &self.config.model,
             instructions: &full_instructions,
@@ -123,9 +134,10 @@ impl ModelClient {
             tool_choice: "auto",
             parallel_tool_calls: false,
             reasoning,
-            previous_response_id: prompt.prev_id.clone(),
             store: prompt.store,
+            // TODO: make this configurable
             stream: true,
+            include,
         };
 
         trace!(
@@ -135,6 +147,7 @@ impl ModelClient {
         );
 
         let mut attempt = 0;
+        let max_retries = self.provider.request_max_retries();
         loop {
             attempt += 1;
 
@@ -142,17 +155,33 @@ impl ModelClient {
                 .provider
                 .create_request_builder(&self.client)?
                 .header("OpenAI-Beta", "responses=experimental")
+                .header("session_id", self.session_id.to_string())
                 .header(reqwest::header::ACCEPT, "text/event-stream")
                 .json(&payload);
 
             let res = req_builder.send().await;
+            if let Ok(resp) = &res {
+                trace!(
+                    "Response status: {}, request-id: {}",
+                    resp.status(),
+                    resp.headers()
+                        .get("x-request-id")
+                        .map(|v| v.to_str().unwrap_or_default())
+                        .unwrap_or_default()
+                );
+            }
+
             match res {
                 Ok(resp) if resp.status().is_success() => {
-                    let (tx_event, rx_event) = mpsc::channel::<Result<ResponseEvent>>(16);
+                    let (tx_event, rx_event) = mpsc::channel::<Result<ResponseEvent>>(1600);
 
                     // spawn task to process SSE
                     let stream = resp.bytes_stream().map_err(CodexErr::Reqwest);
-                    tokio::spawn(process_sse(stream, tx_event));
+                    tokio::spawn(process_sse(
+                        stream,
+                        tx_event,
+                        self.provider.stream_idle_timeout(),
+                    ));
 
                     return Ok(ResponseStream { rx_event });
                 }
@@ -171,7 +200,7 @@ impl ModelClient {
                         return Err(CodexErr::UnexpectedStatus(status, body));
                     }
 
-                    if attempt > *OPENAI_REQUEST_MAX_RETRIES {
+                    if attempt > max_retries {
                         return Err(CodexErr::RetryLimit(status));
                     }
 
@@ -188,7 +217,7 @@ impl ModelClient {
                     tokio::time::sleep(delay).await;
                 }
                 Err(e) => {
-                    if attempt > *OPENAI_REQUEST_MAX_RETRIES {
+                    if attempt > max_retries {
                         return Err(e.into());
                     }
                     let delay = backoff(attempt);
@@ -197,6 +226,10 @@ impl ModelClient {
             }
         }
     }
+
+    pub fn get_provider(&self) -> ModelProviderInfo {
+        self.provider.clone()
+    }
 }
 
 #[derive(Debug, Deserialize, Serialize)]
@@ -205,6 +238,7 @@ struct SseEvent {
     kind: String,
     response: Option<Value>,
     item: Option<Value>,
+    delta: Option<String>,
 }
 
 #[derive(Debug, Deserialize)]
@@ -247,14 +281,16 @@ struct ResponseCompletedOutputTokensDetails {
     reasoning_tokens: u64,
 }
 
-async fn process_sse<S>(stream: S, tx_event: mpsc::Sender<Result<ResponseEvent>>)
-where
+async fn process_sse<S>(
+    stream: S,
+    tx_event: mpsc::Sender<Result<ResponseEvent>>,
+    idle_timeout: Duration,
+) where
     S: Stream<Item = Result<Bytes>> + Unpin,
 {
     let mut stream = stream.eventsource();
 
     // If the stream stays completely silent for an extended period treat it as disconnected.
-    let idle_timeout = *OPENAI_STREAM_IDLE_TIMEOUT_MS;
     // The response id returned from the "complete" message.
     let mut response_completed: Option<ResponseCompleted> = None;
 
@@ -315,7 +351,7 @@ where
             // duplicated `output` array embedded in the `response.completed`
             // payload.  That produced two concrete issues:
             //   1. No real‑time streaming – the user only saw output after the
-            //      entire turn had finished, which broke the “typing” UX and
+            //      entire turn had finished, which broke the "typing" UX and
             //      made long‑running turns look stalled.
             //   2. Duplicate `function_call_output` items – both the
             //      individual *and* the completed array were forwarded, which
@@ -337,11 +373,40 @@ where
                     return;
                 }
             }
+            "response.output_text.delta" => {
+                if let Some(delta) = event.delta {
+                    let event = ResponseEvent::OutputTextDelta(delta);
+                    if tx_event.send(Ok(event)).await.is_err() {
+                        return;
+                    }
+                }
+            }
+            "response.reasoning_summary_text.delta" => {
+                if let Some(delta) = event.delta {
+                    let event = ResponseEvent::ReasoningSummaryDelta(delta);
+                    if tx_event.send(Ok(event)).await.is_err() {
+                        return;
+                    }
+                }
+            }
             "response.created" => {
                 if event.response.is_some() {
                     let _ = tx_event.send(Ok(ResponseEvent::Created {})).await;
                 }
             }
+            "response.failed" => {
+                if let Some(resp_val) = event.response {
+                    let error = resp_val
+                        .get("error")
+                        .and_then(|v| v.get("message"))
+                        .and_then(|v| v.as_str())
+                        .unwrap_or("response.failed event received");
+
+                    let _ = tx_event
+                        .send(Err(CodexErr::Stream(error.to_string())))
+                        .await;
+                }
+            }
             // Final response completed – includes array of output items & id
             "response.completed" => {
                 if let Some(resp_val) = event.response {
@@ -360,10 +425,8 @@ where
             | "response.function_call_arguments.delta"
             | "response.in_progress"
             | "response.output_item.added"
-            | "response.output_text.delta"
             | "response.output_text.done"
             | "response.reasoning_summary_part.added"
-            | "response.reasoning_summary_text.delta"
             | "response.reasoning_summary_text.done" => {
                 // Currently, we ignore these events, but we handle them
                 // separately to skip the logging message in the `other` case.
@@ -374,8 +437,11 @@ where
 }
 
 /// used in tests to stream from a text SSE file
-async fn stream_from_fixture(path: impl AsRef<Path>) -> Result<ResponseStream> {
-    let (tx_event, rx_event) = mpsc::channel::<Result<ResponseEvent>>(16);
+async fn stream_from_fixture(
+    path: impl AsRef<Path>,
+    provider: ModelProviderInfo,
+) -> Result<ResponseStream> {
+    let (tx_event, rx_event) = mpsc::channel::<Result<ResponseEvent>>(1600);
     let f = std::fs::File::open(path.as_ref())?;
     let lines = std::io::BufReader::new(f).lines();
 
@@ -388,7 +454,11 @@ async fn stream_from_fixture(path: impl AsRef<Path>) -> Result<ResponseStream> {
 
     let rdr = std::io::Cursor::new(content);
     let stream = ReaderStream::new(rdr).map_err(CodexErr::Io);
-    tokio::spawn(process_sse(stream, tx_event));
+    tokio::spawn(process_sse(
+        stream,
+        tx_event,
+        provider.stream_idle_timeout(),
+    ));
     Ok(ResponseStream { rx_event })
 }
 
@@ -408,7 +478,10 @@ mod tests {
 
     /// Runs the SSE parser on pre-chunked byte slices and returns every event
     /// (including any final `Err` from a stream-closure check).
-    async fn collect_events(chunks: &[&[u8]]) -> Vec<Result<ResponseEvent>> {
+    async fn collect_events(
+        chunks: &[&[u8]],
+        provider: ModelProviderInfo,
+    ) -> Vec<Result<ResponseEvent>> {
         let mut builder = IoBuilder::new();
         for chunk in chunks {
             builder.read(chunk);
@@ -417,7 +490,7 @@ mod tests {
         let reader = builder.build();
         let stream = ReaderStream::new(reader).map_err(CodexErr::Io);
         let (tx, mut rx) = mpsc::channel::<Result<ResponseEvent>>(16);
-        tokio::spawn(process_sse(stream, tx));
+        tokio::spawn(process_sse(stream, tx, provider.stream_idle_timeout()));
 
         let mut events = Vec::new();
         while let Some(ev) = rx.recv().await {
@@ -428,7 +501,10 @@ mod tests {
 
     /// Builds an in-memory SSE stream from JSON fixtures and returns only the
     /// successfully parsed events (panics on internal channel errors).
-    async fn run_sse(events: Vec<serde_json::Value>) -> Vec<ResponseEvent> {
+    async fn run_sse(
+        events: Vec<serde_json::Value>,
+        provider: ModelProviderInfo,
+    ) -> Vec<ResponseEvent> {
         let mut body = String::new();
         for e in events {
             let kind = e
@@ -444,7 +520,7 @@ mod tests {
 
         let (tx, mut rx) = mpsc::channel::<Result<ResponseEvent>>(8);
         let stream = ReaderStream::new(std::io::Cursor::new(body)).map_err(CodexErr::Io);
-        tokio::spawn(process_sse(stream, tx));
+        tokio::spawn(process_sse(stream, tx, provider.stream_idle_timeout()));
 
         let mut out = Vec::new();
         while let Some(ev) = rx.recv().await {
@@ -489,7 +565,25 @@ mod tests {
         let sse2 = format!("event: response.output_item.done\ndata: {item2}\n\n");
         let sse3 = format!("event: response.completed\ndata: {completed}\n\n");
 
-        let events = collect_events(&[sse1.as_bytes(), sse2.as_bytes(), sse3.as_bytes()]).await;
+        let provider = ModelProviderInfo {
+            name: "test".to_string(),
+            base_url: "https://test.com".to_string(),
+            env_key: Some("TEST_API_KEY".to_string()),
+            env_key_instructions: None,
+            wire_api: WireApi::Responses,
+            query_params: None,
+            http_headers: None,
+            env_http_headers: None,
+            request_max_retries: Some(0),
+            stream_max_retries: Some(0),
+            stream_idle_timeout_ms: Some(1000),
+        };
+
+        let events = collect_events(
+            &[sse1.as_bytes(), sse2.as_bytes(), sse3.as_bytes()],
+            provider,
+        )
+        .await;
 
         assert_eq!(events.len(), 3);
 
@@ -530,8 +624,21 @@ mod tests {
         .to_string();
 
         let sse1 = format!("event: response.output_item.done\ndata: {item1}\n\n");
+        let provider = ModelProviderInfo {
+            name: "test".to_string(),
+            base_url: "https://test.com".to_string(),
+            env_key: Some("TEST_API_KEY".to_string()),
+            env_key_instructions: None,
+            wire_api: WireApi::Responses,
+            query_params: None,
+            http_headers: None,
+            env_http_headers: None,
+            request_max_retries: Some(0),
+            stream_max_retries: Some(0),
+            stream_idle_timeout_ms: Some(1000),
+        };
 
-        let events = collect_events(&[sse1.as_bytes()]).await;
+        let events = collect_events(&[sse1.as_bytes()], provider).await;
 
         assert_eq!(events.len(), 2);
 
@@ -619,7 +726,21 @@ mod tests {
             let mut evs = vec![case.event];
             evs.push(completed.clone());
 
-            let out = run_sse(evs).await;
+            let provider = ModelProviderInfo {
+                name: "test".to_string(),
+                base_url: "https://test.com".to_string(),
+                env_key: Some("TEST_API_KEY".to_string()),
+                env_key_instructions: None,
+                wire_api: WireApi::Responses,
+                query_params: None,
+                http_headers: None,
+                env_http_headers: None,
+                request_max_retries: Some(0),
+                stream_max_retries: Some(0),
+                stream_idle_timeout_ms: Some(1000),
+            };
+
+            let out = run_sse(evs, provider).await;
             assert_eq!(out.len(), case.expected_len, "case {}", case.name);
             assert!(
                 (case.expect_first)(&out[0]),

codex-rs/core/src/client_common.rs

@@ -22,8 +22,6 @@ const BASE_INSTRUCTIONS: &str = include_str!("../prompt.md");
 pub struct Prompt {
     /// Conversation context input items.
     pub input: Vec<ResponseItem>,
-    /// Optional previous response ID (when storage is enabled).
-    pub prev_id: Option<String>,
     /// Optional instructions from the user to amend to the built-in agent
     /// instructions.
     pub user_instructions: Option<String>,
@@ -34,11 +32,18 @@ pub struct Prompt {
     /// the "fully qualified" tool name (i.e., prefixed with the server name),
     /// which should be reported to the model in place of Tool::name.
     pub extra_tools: HashMap<String, mcp_types::Tool>,
+
+    /// Optional override for the built-in BASE_INSTRUCTIONS.
+    pub base_instructions_override: Option<String>,
 }
 
 impl Prompt {
     pub(crate) fn get_full_instructions(&self, model: &str) -> Cow<'_, str> {
-        let mut sections: Vec<&str> = vec![BASE_INSTRUCTIONS];
+        let base = self
+            .base_instructions_override
+            .as_deref()
+            .unwrap_or(BASE_INSTRUCTIONS);
+        let mut sections: Vec<&str> = vec![base];
         if let Some(ref user) = self.user_instructions {
             sections.push(user);
         }
@@ -57,6 +62,8 @@ pub enum ResponseEvent {
         response_id: String,
         token_usage: Option<TokenUsage>,
     },
+    OutputTextDelta(String),
+    ReasoningSummaryDelta(String),
 }
 
 #[derive(Debug, Serialize)]
@@ -124,11 +131,10 @@ pub(crate) struct ResponsesApiRequest<'a> {
     pub(crate) tool_choice: &'static str,
     pub(crate) parallel_tool_calls: bool,
     pub(crate) reasoning: Option<Reasoning>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub(crate) previous_response_id: Option<String>,
     /// true when using the Responses API.
     pub(crate) store: bool,
     pub(crate) stream: bool,
+    pub(crate) include: Vec<String>,
 }
 
 use crate::config::Config;

codex-rs/core/src/codex_wrapper.rs

@@ -1,20 +1,35 @@
 use std::sync::Arc;
 
 use crate::Codex;
+use crate::CodexSpawnOk;
 use crate::config::Config;
 use crate::protocol::Event;
 use crate::protocol::EventMsg;
 use crate::util::notify_on_sigint;
 use tokio::sync::Notify;
+use uuid::Uuid;
+
+/// Represents an active Codex conversation, including the first event
+/// (which is [`EventMsg::SessionConfigured`]).
+pub struct CodexConversation {
+    pub codex: Codex,
+    pub session_id: Uuid,
+    pub session_configured: Event,
+    pub ctrl_c: Arc<Notify>,
+}
 
 /// Spawn a new [`Codex`] and initialize the session.
 ///
 /// Returns the wrapped [`Codex`] **and** the `SessionInitialized` event that
 /// is received as a response to the initial `ConfigureSession` submission so
 /// that callers can surface the information to the UI.
-pub async fn init_codex(config: Config) -> anyhow::Result<(Codex, Event, Arc<Notify>)> {
+pub async fn init_codex(config: Config) -> anyhow::Result<CodexConversation> {
     let ctrl_c = notify_on_sigint();
-    let (codex, init_id) = Codex::spawn(config, ctrl_c.clone()).await?;
+    let CodexSpawnOk {
+        codex,
+        init_id,
+        session_id,
+    } = Codex::spawn(config, ctrl_c.clone()).await?;
 
     // The first event must be `SessionInitialized`. Validate and forward it to
     // the caller so that they can display it in the conversation history.
@@ -33,5 +48,10 @@ pub async fn init_codex(config: Config) -> anyhow::Result<(Codex, Event, Arc<Not
         ));
     }
 
-    Ok((codex, event, ctrl_c))
+    Ok(CodexConversation {
+        codex,
+        session_id,
+        session_configured: event,
+        ctrl_c,
+    })
 }

codex-rs/core/src/config.rs

@@ -63,7 +63,10 @@ pub struct Config {
     pub disable_response_storage: bool,
 
     /// User-provided instructions from instructions.md.
-    pub instructions: Option<String>,
+    pub user_instructions: Option<String>,
+
+    /// Base instructions override.
+    pub base_instructions: Option<String>,
 
     /// Optional external notifier command. When set, Codex will spawn this
     /// program after each completed *turn* (i.e. when the agent finishes
@@ -137,6 +140,9 @@ pub struct Config {
 
     /// Base URL for requests to ChatGPT (as opposed to the OpenAI API).
     pub chatgpt_base_url: String,
+
+    /// Experimental rollout resume path (absolute path to .jsonl; undocumented).
+    pub experimental_resume: Option<PathBuf>,
 }
 
 impl Config {
@@ -321,6 +327,12 @@ pub struct ConfigToml {
 
     /// Base URL for requests to ChatGPT (as opposed to the OpenAI API).
     pub chatgpt_base_url: Option<String>,
+
+    /// Experimental rollout resume path (absolute path to .jsonl; undocumented).
+    pub experimental_resume: Option<PathBuf>,
+
+    /// Experimental path to a file whose contents replace the built-in BASE_INSTRUCTIONS.
+    pub experimental_instructions_file: Option<PathBuf>,
 }
 
 impl ConfigToml {
@@ -353,6 +365,7 @@ pub struct ConfigOverrides {
     pub model_provider: Option<String>,
     pub config_profile: Option<String>,
     pub codex_linux_sandbox_exe: Option<PathBuf>,
+    pub base_instructions: Option<String>,
 }
 
 impl Config {
@@ -363,7 +376,7 @@ impl Config {
         overrides: ConfigOverrides,
         codex_home: PathBuf,
     ) -> std::io::Result<Self> {
-        let instructions = Self::load_instructions(Some(&codex_home));
+        let user_instructions = Self::load_instructions(Some(&codex_home));
 
         // Destructure ConfigOverrides fully to ensure all overrides are applied.
         let ConfigOverrides {
@@ -374,6 +387,7 @@ impl Config {
             model_provider,
             config_profile: config_profile_key,
             codex_linux_sandbox_exe,
+            base_instructions,
         } = overrides;
 
         let config_profile = match config_profile_key.as_ref().or(cfg.profile.as_ref()) {
@@ -448,6 +462,13 @@ impl Config {
                 .as_ref()
                 .map(|info| info.max_output_tokens)
         });
+
+        let experimental_resume = cfg.experimental_resume;
+
+        let base_instructions = base_instructions.or(Self::get_base_instructions(
+            cfg.experimental_instructions_file.as_ref(),
+        ));
+
         let config = Self {
             model,
             model_context_window,
@@ -466,7 +487,8 @@ impl Config {
                 .or(cfg.disable_response_storage)
                 .unwrap_or(false),
             notify: cfg.notify,
-            instructions,
+            user_instructions,
+            base_instructions,
             mcp_servers: cfg.mcp_servers,
             model_providers,
             project_doc_max_bytes: cfg.project_doc_max_bytes.unwrap_or(PROJECT_DOC_MAX_BYTES),
@@ -494,6 +516,8 @@ impl Config {
                 .chatgpt_base_url
                 .or(cfg.chatgpt_base_url)
                 .unwrap_or("https://chatgpt.com/backend-api/".to_string()),
+
+            experimental_resume,
         };
         Ok(config)
     }
@@ -514,6 +538,15 @@ impl Config {
             }
         })
     }
+
+    fn get_base_instructions(path: Option<&PathBuf>) -> Option<String> {
+        let path = path.as_ref()?;
+
+        std::fs::read_to_string(path)
+            .ok()
+            .map(|s| s.trim().to_string())
+            .filter(|s| !s.is_empty())
+    }
 }
 
 fn default_model() -> String {
@@ -528,7 +561,7 @@ fn default_model() -> String {
 ///   function will Err if the path does not exist.
 /// - If `CODEX_HOME` is not set, this function does not verify that the
 ///   directory exists.
-fn find_codex_home() -> std::io::Result<PathBuf> {
+pub fn find_codex_home() -> std::io::Result<PathBuf> {
     // Honor the `CODEX_HOME` environment variable when it is set to allow users
     // (and tests) to override the default location.
     if let Ok(val) = std::env::var("CODEX_HOME") {
@@ -682,6 +715,9 @@ name = "OpenAI using Chat Completions"
 base_url = "https://api.openai.com/v1"
 env_key = "OPENAI_API_KEY"
 wire_api = "chat"
+request_max_retries = 4            # retry failed HTTP requests
+stream_max_retries = 10            # retry dropped SSE streams
+stream_idle_timeout_ms = 300000    # 5m idle timeout
 
 [profiles.o3]
 model = "o3"
@@ -722,6 +758,9 @@ disable_response_storage = true
             query_params: None,
             http_headers: None,
             env_http_headers: None,
+            request_max_retries: Some(4),
+            stream_max_retries: Some(10),
+            stream_idle_timeout_ms: Some(300_000),
         };
         let model_provider_map = {
             let mut model_provider_map = built_in_model_providers();
@@ -784,7 +823,7 @@ disable_response_storage = true
                 sandbox_policy: SandboxPolicy::new_read_only_policy(),
                 shell_environment_policy: ShellEnvironmentPolicy::default(),
                 disable_response_storage: false,
-                instructions: None,
+                user_instructions: None,
                 notify: None,
                 cwd: fixture.cwd(),
                 mcp_servers: HashMap::new(),
@@ -800,6 +839,8 @@ disable_response_storage = true
                 model_reasoning_summary: ReasoningSummary::Detailed,
                 model_supports_reasoning_summaries: false,
                 chatgpt_base_url: "https://chatgpt.com/backend-api/".to_string(),
+                experimental_resume: None,
+                base_instructions: None,
             },
             o3_profile_config
         );
@@ -830,7 +871,7 @@ disable_response_storage = true
             sandbox_policy: SandboxPolicy::new_read_only_policy(),
             shell_environment_policy: ShellEnvironmentPolicy::default(),
             disable_response_storage: false,
-            instructions: None,
+            user_instructions: None,
             notify: None,
             cwd: fixture.cwd(),
             mcp_servers: HashMap::new(),
@@ -846,6 +887,8 @@ disable_response_storage = true
             model_reasoning_summary: ReasoningSummary::default(),
             model_supports_reasoning_summaries: false,
             chatgpt_base_url: "https://chatgpt.com/backend-api/".to_string(),
+            experimental_resume: None,
+            base_instructions: None,
         };
 
         assert_eq!(expected_gpt3_profile_config, gpt3_profile_config);
@@ -891,7 +934,7 @@ disable_response_storage = true
             sandbox_policy: SandboxPolicy::new_read_only_policy(),
             shell_environment_policy: ShellEnvironmentPolicy::default(),
             disable_response_storage: true,
-            instructions: None,
+            user_instructions: None,
             notify: None,
             cwd: fixture.cwd(),
             mcp_servers: HashMap::new(),
@@ -907,6 +950,8 @@ disable_response_storage = true
             model_reasoning_summary: ReasoningSummary::default(),
             model_supports_reasoning_summaries: false,
             chatgpt_base_url: "https://chatgpt.com/backend-api/".to_string(),
+            experimental_resume: None,
+            base_instructions: None,
         };
 
         assert_eq!(expected_zdr_profile_config, zdr_profile_config);

codex-rs/core/src/config_types.rs

@@ -76,20 +76,7 @@ pub enum HistoryPersistence {
 
 /// Collection of settings that are specific to the TUI.
 #[derive(Deserialize, Debug, Clone, PartialEq, Default)]
-pub struct Tui {
-    /// By default, mouse capture is enabled in the TUI so that it is possible
-    /// to scroll the conversation history with a mouse. This comes at the cost
-    /// of not being able to use the mouse to select text in the TUI.
-    /// (Most terminals support a modifier key to allow this. For example,
-    /// text selection works in iTerm if you hold down the `Option` key while
-    /// clicking and dragging.)
-    ///
-    /// Setting this option to `true` disables mouse capture, so scrolling with
-    /// the mouse is not possible, though the keyboard shortcuts e.g. `b` and
-    /// `space` still work. This allows the user to select text in the TUI
-    /// using the mouse without needing to hold down a modifier key.
-    pub disable_mouse_capture: bool,
-}
+pub struct Tui {}
 
 #[derive(Deserialize, Debug, Clone, Copy, PartialEq, Default)]
 #[serde(rename_all = "kebab-case")]
@@ -143,6 +130,8 @@ pub struct ShellEnvironmentPolicyToml {
 
     /// List of regular expressions.
     pub include_only: Option<Vec<String>>,
+
+    pub experimental_use_profile: Option<bool>,
 }
 
 pub type EnvironmentVariablePattern = WildMatchPattern<'*', '?'>;
@@ -171,6 +160,9 @@ pub struct ShellEnvironmentPolicy {
 
     /// Environment variable names to retain in the environment.
     pub include_only: Vec<EnvironmentVariablePattern>,
+
+    /// If true, the shell profile will be used to run the command.
+    pub use_profile: bool,
 }
 
 impl From<ShellEnvironmentPolicyToml> for ShellEnvironmentPolicy {
@@ -190,6 +182,7 @@ impl From<ShellEnvironmentPolicyToml> for ShellEnvironmentPolicy {
             .into_iter()
             .map(|s| EnvironmentVariablePattern::new_case_insensitive(&s))
             .collect();
+        let use_profile = toml.experimental_use_profile.unwrap_or(false);
 
         Self {
             inherit,
@@ -197,6 +190,7 @@ impl From<ShellEnvironmentPolicyToml> for ShellEnvironmentPolicy {
             exclude,
             r#set,
             include_only,
+            use_profile,
         }
     }
 }

codex-rs/core/src/conversation_history.rs

@@ -1,12 +1,7 @@
 use crate::models::ResponseItem;
 
-/// Transcript of conversation history that is needed:
-/// - for ZDR clients for which previous_response_id is not available, so we
-///   must include the transcript with every API call. This must include each
-///   `function_call` and its corresponding `function_call_output`.
-/// - for clients using the "chat completions" API as opposed to the
-///   "responses" API.
-#[derive(Debug, Clone)]
+/// Transcript of conversation history
+#[derive(Debug, Clone, Default)]
 pub(crate) struct ConversationHistory {
     /// The oldest items are at the beginning of the vector.
     items: Vec<ResponseItem>,
@@ -35,6 +30,11 @@ impl ConversationHistory {
             }
         }
     }
+
+    /// Clears the conversation history.
+    pub(crate) fn clear(&mut self) {
+        self.items.clear();
+    }
 }
 
 /// Anything that is not a system message or "reasoning" message is considered
@@ -44,7 +44,36 @@ fn is_api_message(message: &ResponseItem) -> bool {
         ResponseItem::Message { role, .. } => role.as_str() != "system",
         ResponseItem::FunctionCallOutput { .. }
         | ResponseItem::FunctionCall { .. }
-        | ResponseItem::LocalShellCall { .. } => true,
-        ResponseItem::Reasoning { .. } | ResponseItem::Other => false,
+        | ResponseItem::LocalShellCall { .. }
+        | ResponseItem::Reasoning { .. } => true,
+        ResponseItem::Other => false,
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::models::ResponseItem;
+
+    #[test]
+    fn clear_removes_all_items() {
+        let mut hist = ConversationHistory::new();
+
+        use crate::models::ContentItem;
+
+        let items = [ResponseItem::Message {
+            role: "user".into(),
+            content: vec![ContentItem::InputText {
+                text: "hello".into(),
+            }],
+        }];
+
+        hist.record_items(items.iter());
+
+        assert_eq!(hist.contents().len(), 1, "sanity – item should be present");
+
+        hist.clear();
+
+        assert!(hist.contents().is_empty(), "all items should be removed");
     }
 }

codex-rs/core/src/exec.rs

@@ -17,6 +17,7 @@ use tokio::io::BufReader;
 use tokio::process::Child;
 use tokio::process::Command;
 use tokio::sync::Notify;
+use tracing::trace;
 
 use crate::error::CodexErr;
 use crate::error::Result;
@@ -82,7 +83,8 @@ pub async fn process_exec_tool_call(
 ) -> Result<ExecToolCallOutput> {
     let start = Instant::now();
 
-    let raw_output_result = match sandbox_type {
+    let raw_output_result: std::result::Result<RawExecToolCallOutput, CodexErr> = match sandbox_type
+    {
         SandboxType::None => exec(params, sandbox_policy, ctrl_c).await,
         SandboxType::MacosSeatbelt => {
             let ExecParams {
@@ -372,6 +374,10 @@ async fn spawn_child_async(
     stdio_policy: StdioPolicy,
     env: HashMap<String, String>,
 ) -> std::io::Result<Child> {
+    trace!(
+        "spawn_child_async: {program:?} {args:?} {arg0:?} {cwd:?} {sandbox_policy:?} {stdio_policy:?} {env:?}"
+    );
+
     let mut cmd = Command::new(&program);
     #[cfg(unix)]
     cmd.arg0(arg0.map_or_else(|| program.to_string_lossy().to_string(), String::from));
@@ -384,6 +390,31 @@ async fn spawn_child_async(
         cmd.env(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR, "1");
     }
 
+    // If this Codex process dies (including being killed via SIGKILL), we want
+    // any child processes that were spawned as part of a `"shell"` tool call
+    // to also be terminated.
+
+    // This relies on prctl(2), so it only works on Linux.
+    #[cfg(target_os = "linux")]
+    unsafe {
+        cmd.pre_exec(|| {
+            // This prctl call effectively requests, "deliver SIGTERM when my
+            // current parent dies."
+            if libc::prctl(libc::PR_SET_PDEATHSIG, libc::SIGTERM) == -1 {
+                return Err(io::Error::last_os_error());
+            }
+
+            // Though if there was a race condition and this pre_exec() block is
+            // run _after_ the parent (i.e., the Codex process) has already
+            // exited, then the parent is the _init_ process (which will never
+            // die), so we should just terminate the child process now.
+            if libc::getppid() == 1 {
+                libc::raise(libc::SIGTERM);
+            }
+            Ok(())
+        });
+    }
+
     match stdio_policy {
         StdioPolicy::RedirectForShellTool => {
             // Do not create a file descriptor for stdin because otherwise some

codex-rs/core/src/flags.rs

@@ -11,14 +11,6 @@ env_flags! {
     pub OPENAI_TIMEOUT_MS: Duration = Duration::from_millis(300_000), |value| {
         value.parse().map(Duration::from_millis)
     };
-    pub OPENAI_REQUEST_MAX_RETRIES: u64 = 4;
-    pub OPENAI_STREAM_MAX_RETRIES: u64 = 10;
-
-    // We generally don't want to disconnect; this updates the timeout to be five minutes
-    // which matches the upstream typescript codex impl.
-    pub OPENAI_STREAM_IDLE_TIMEOUT_MS: Duration = Duration::from_millis(300_000), |value| {
-        value.parse().map(Duration::from_millis)
-    };
 
     /// Fixture path for offline tests (see client.rs).
     pub CODEX_RS_SSE_FIXTURE: Option<&str> = None;

codex-rs/core/src/git_info.rs

@@ -0,0 +1,307 @@
+use std::path::Path;
+
+use serde::Deserialize;
+use serde::Serialize;
+use tokio::process::Command;
+use tokio::time::Duration as TokioDuration;
+use tokio::time::timeout;
+
+/// Timeout for git commands to prevent freezing on large repositories
+const GIT_COMMAND_TIMEOUT: TokioDuration = TokioDuration::from_secs(5);
+
+#[derive(Serialize, Deserialize, Clone)]
+pub struct GitInfo {
+    /// Current commit hash (SHA)
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub commit_hash: Option<String>,
+    /// Current branch name
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub branch: Option<String>,
+    /// Repository URL (if available from remote)
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub repository_url: Option<String>,
+}
+
+/// Collect git repository information from the given working directory using command-line git.
+/// Returns None if no git repository is found or if git operations fail.
+/// Uses timeouts to prevent freezing on large repositories.
+/// All git commands (except the initial repo check) run in parallel for better performance.
+pub async fn collect_git_info(cwd: &Path) -> Option<GitInfo> {
+    // Check if we're in a git repository first
+    let is_git_repo = run_git_command_with_timeout(&["rev-parse", "--git-dir"], cwd)
+        .await?
+        .status
+        .success();
+
+    if !is_git_repo {
+        return None;
+    }
+
+    // Run all git info collection commands in parallel
+    let (commit_result, branch_result, url_result) = tokio::join!(
+        run_git_command_with_timeout(&["rev-parse", "HEAD"], cwd),
+        run_git_command_with_timeout(&["rev-parse", "--abbrev-ref", "HEAD"], cwd),
+        run_git_command_with_timeout(&["remote", "get-url", "origin"], cwd)
+    );
+
+    let mut git_info = GitInfo {
+        commit_hash: None,
+        branch: None,
+        repository_url: None,
+    };
+
+    // Process commit hash
+    if let Some(output) = commit_result {
+        if output.status.success() {
+            if let Ok(hash) = String::from_utf8(output.stdout) {
+                git_info.commit_hash = Some(hash.trim().to_string());
+            }
+        }
+    }
+
+    // Process branch name
+    if let Some(output) = branch_result {
+        if output.status.success() {
+            if let Ok(branch) = String::from_utf8(output.stdout) {
+                let branch = branch.trim();
+                if branch != "HEAD" {
+                    git_info.branch = Some(branch.to_string());
+                }
+            }
+        }
+    }
+
+    // Process repository URL
+    if let Some(output) = url_result {
+        if output.status.success() {
+            if let Ok(url) = String::from_utf8(output.stdout) {
+                git_info.repository_url = Some(url.trim().to_string());
+            }
+        }
+    }
+
+    Some(git_info)
+}
+
+/// Run a git command with a timeout to prevent blocking on large repositories
+async fn run_git_command_with_timeout(args: &[&str], cwd: &Path) -> Option<std::process::Output> {
+    let result = timeout(
+        GIT_COMMAND_TIMEOUT,
+        Command::new("git").args(args).current_dir(cwd).output(),
+    )
+    .await;
+
+    match result {
+        Ok(Ok(output)) => Some(output),
+        _ => None, // Timeout or error
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    #![allow(clippy::expect_used)]
+    #![allow(clippy::unwrap_used)]
+
+    use super::*;
+
+    use std::fs;
+    use std::path::PathBuf;
+    use tempfile::TempDir;
+
+    // Helper function to create a test git repository
+    async fn create_test_git_repo(temp_dir: &TempDir) -> PathBuf {
+        let repo_path = temp_dir.path().to_path_buf();
+
+        // Initialize git repo
+        Command::new("git")
+            .args(["init"])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to init git repo");
+
+        // Configure git user (required for commits)
+        Command::new("git")
+            .args(["config", "user.name", "Test User"])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to set git user name");
+
+        Command::new("git")
+            .args(["config", "user.email", "test@example.com"])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to set git user email");
+
+        // Create a test file and commit it
+        let test_file = repo_path.join("test.txt");
+        fs::write(&test_file, "test content").expect("Failed to write test file");
+
+        Command::new("git")
+            .args(["add", "."])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to add files");
+
+        Command::new("git")
+            .args(["commit", "-m", "Initial commit"])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to commit");
+
+        repo_path
+    }
+
+    #[tokio::test]
+    async fn test_collect_git_info_non_git_directory() {
+        let temp_dir = TempDir::new().expect("Failed to create temp dir");
+        let result = collect_git_info(temp_dir.path()).await;
+        assert!(result.is_none());
+    }
+
+    #[tokio::test]
+    async fn test_collect_git_info_git_repository() {
+        let temp_dir = TempDir::new().expect("Failed to create temp dir");
+        let repo_path = create_test_git_repo(&temp_dir).await;
+
+        let git_info = collect_git_info(&repo_path)
+            .await
+            .expect("Should collect git info from repo");
+
+        // Should have commit hash
+        assert!(git_info.commit_hash.is_some());
+        let commit_hash = git_info.commit_hash.unwrap();
+        assert_eq!(commit_hash.len(), 40); // SHA-1 hash should be 40 characters
+        assert!(commit_hash.chars().all(|c| c.is_ascii_hexdigit()));
+
+        // Should have branch (likely "main" or "master")
+        assert!(git_info.branch.is_some());
+        let branch = git_info.branch.unwrap();
+        assert!(branch == "main" || branch == "master");
+
+        // Repository URL might be None for local repos without remote
+        // This is acceptable behavior
+    }
+
+    #[tokio::test]
+    async fn test_collect_git_info_with_remote() {
+        let temp_dir = TempDir::new().expect("Failed to create temp dir");
+        let repo_path = create_test_git_repo(&temp_dir).await;
+
+        // Add a remote origin
+        Command::new("git")
+            .args([
+                "remote",
+                "add",
+                "origin",
+                "https://github.com/example/repo.git",
+            ])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to add remote");
+
+        let git_info = collect_git_info(&repo_path)
+            .await
+            .expect("Should collect git info from repo");
+
+        // Should have repository URL
+        assert_eq!(
+            git_info.repository_url,
+            Some("https://github.com/example/repo.git".to_string())
+        );
+    }
+
+    #[tokio::test]
+    async fn test_collect_git_info_detached_head() {
+        let temp_dir = TempDir::new().expect("Failed to create temp dir");
+        let repo_path = create_test_git_repo(&temp_dir).await;
+
+        // Get the current commit hash
+        let output = Command::new("git")
+            .args(["rev-parse", "HEAD"])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to get HEAD");
+        let commit_hash = String::from_utf8(output.stdout).unwrap().trim().to_string();
+
+        // Checkout the commit directly (detached HEAD)
+        Command::new("git")
+            .args(["checkout", &commit_hash])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to checkout commit");
+
+        let git_info = collect_git_info(&repo_path)
+            .await
+            .expect("Should collect git info from repo");
+
+        // Should have commit hash
+        assert!(git_info.commit_hash.is_some());
+        // Branch should be None for detached HEAD (since rev-parse --abbrev-ref HEAD returns "HEAD")
+        assert!(git_info.branch.is_none());
+    }
+
+    #[tokio::test]
+    async fn test_collect_git_info_with_branch() {
+        let temp_dir = TempDir::new().expect("Failed to create temp dir");
+        let repo_path = create_test_git_repo(&temp_dir).await;
+
+        // Create and checkout a new branch
+        Command::new("git")
+            .args(["checkout", "-b", "feature-branch"])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to create branch");
+
+        let git_info = collect_git_info(&repo_path)
+            .await
+            .expect("Should collect git info from repo");
+
+        // Should have the new branch name
+        assert_eq!(git_info.branch, Some("feature-branch".to_string()));
+    }
+
+    #[test]
+    fn test_git_info_serialization() {
+        let git_info = GitInfo {
+            commit_hash: Some("abc123def456".to_string()),
+            branch: Some("main".to_string()),
+            repository_url: Some("https://github.com/example/repo.git".to_string()),
+        };
+
+        let json = serde_json::to_string(&git_info).expect("Should serialize GitInfo");
+        let parsed: serde_json::Value = serde_json::from_str(&json).expect("Should parse JSON");
+
+        assert_eq!(parsed["commit_hash"], "abc123def456");
+        assert_eq!(parsed["branch"], "main");
+        assert_eq!(
+            parsed["repository_url"],
+            "https://github.com/example/repo.git"
+        );
+    }
+
+    #[test]
+    fn test_git_info_serialization_with_nones() {
+        let git_info = GitInfo {
+            commit_hash: None,
+            branch: None,
+            repository_url: None,
+        };
+
+        let json = serde_json::to_string(&git_info).expect("Should serialize GitInfo");
+        let parsed: serde_json::Value = serde_json::from_str(&json).expect("Should parse JSON");
+
+        // Fields with None values should be omitted due to skip_serializing_if
+        assert!(!parsed.as_object().unwrap().contains_key("commit_hash"));
+        assert!(!parsed.as_object().unwrap().contains_key("branch"));
+        assert!(!parsed.as_object().unwrap().contains_key("repository_url"));
+    }
+}

codex-rs/core/src/is_safe_command.rs

@@ -1,31 +1,57 @@
-use tree_sitter::Parser;
-use tree_sitter::Tree;
-use tree_sitter_bash::LANGUAGE as BASH;
+use crate::bash::try_parse_bash;
+use crate::bash::try_parse_word_only_commands_sequence;
 
 pub fn is_known_safe_command(command: &[String]) -> bool {
     if is_safe_to_call_with_exec(command) {
         return true;
     }
 
-    // TODO(mbolin): Also support safe commands that are piped together such
-    // as `cat foo | wc -l`.
-    matches!(
-        command,
-        [bash, flag, script]
-            if bash == "bash"
-            && flag == "-lc"
-            && try_parse_bash(script).and_then(|tree|
-                try_parse_single_word_only_command(&tree, script)).is_some_and(|parsed_bash_command| is_safe_to_call_with_exec(&parsed_bash_command))
-    )
+    // Support `bash -lc "..."` where the script consists solely of one or
+    // more "plain" commands (only bare words / quoted strings) combined with
+    // a conservative allow‑list of shell operators that themselves do not
+    // introduce side effects ( "&&", "||", ";", and "|" ). If every
+    // individual command in the script is itself a known‑safe command, then
+    // the composite expression is considered safe.
+    if let [bash, flag, script] = command {
+        if bash == "bash" && flag == "-lc" {
+            if let Some(tree) = try_parse_bash(script) {
+                if let Some(all_commands) = try_parse_word_only_commands_sequence(&tree, script) {
+                    if !all_commands.is_empty()
+                        && all_commands
+                            .iter()
+                            .all(|cmd| is_safe_to_call_with_exec(cmd))
+                    {
+                        return true;
+                    }
+                }
+            }
+        }
+    }
+
+    false
 }
 
 fn is_safe_to_call_with_exec(command: &[String]) -> bool {
     let cmd0 = command.first().map(String::as_str);
 
     match cmd0 {
+        #[rustfmt::skip]
         Some(
-            "cat" | "cd" | "echo" | "grep" | "head" | "ls" | "pwd" | "rg" | "tail" | "wc" | "which",
-        ) => true,
+            "cat" |
+            "cd" |
+            "echo" |
+            "false" |
+            "grep" |
+            "head" |
+            "ls" |
+            "nl" |
+            "pwd" |
+            "tail" |
+            "true" |
+            "wc" |
+            "which") => {
+            true
+        },
 
         Some("find") => {
             // Certain options to `find` can delete files, write to files, or
@@ -46,6 +72,29 @@ fn is_safe_to_call_with_exec(command: &[String]) -> bool {
                 .any(|arg| UNSAFE_FIND_OPTIONS.contains(&arg.as_str()))
         }
 
+        // Ripgrep
+        Some("rg") => {
+            const UNSAFE_RIPGREP_OPTIONS_WITH_ARGS: &[&str] = &[
+                // Takes an arbitrary command that is executed for each match.
+                "--pre",
+                // Takes a command that can be used to obtain the local hostname.
+                "--hostname-bin",
+            ];
+            const UNSAFE_RIPGREP_OPTIONS_WITHOUT_ARGS: &[&str] = &[
+                // Calls out to other decompression tools, so do not auto-approve
+                // out of an abundance of caution.
+                "--search-zip",
+                "-z",
+            ];
+
+            !command.iter().any(|arg| {
+                UNSAFE_RIPGREP_OPTIONS_WITHOUT_ARGS.contains(&arg.as_str())
+                    || UNSAFE_RIPGREP_OPTIONS_WITH_ARGS
+                        .iter()
+                        .any(|&opt| arg == opt || arg.starts_with(&format!("{opt}=")))
+            })
+        }
+
         // Git
         Some("git") => matches!(
             command.get(1).map(String::as_str),
@@ -72,90 +121,7 @@ fn is_safe_to_call_with_exec(command: &[String]) -> bool {
     }
 }
 
-fn try_parse_bash(bash_lc_arg: &str) -> Option<Tree> {
-    let lang = BASH.into();
-    let mut parser = Parser::new();
-    #[expect(clippy::expect_used)]
-    parser.set_language(&lang).expect("load bash grammar");
-
-    let old_tree: Option<&Tree> = None;
-    parser.parse(bash_lc_arg, old_tree)
-}
-
-/// If `tree` represents a single Bash command whose name and every argument is
-/// an ordinary `word`, return those words in order; otherwise, return `None`.
-///
-/// `src` must be the exact source string that was parsed into `tree`, so we can
-/// extract the text for every node.
-pub fn try_parse_single_word_only_command(tree: &Tree, src: &str) -> Option<Vec<String>> {
-    // Any parse error is an immediate rejection.
-    if tree.root_node().has_error() {
-        return None;
-    }
-
-    // (program …) with exactly one statement
-    let root = tree.root_node();
-    if root.kind() != "program" || root.named_child_count() != 1 {
-        return None;
-    }
-
-    let cmd = root.named_child(0)?; // (command …)
-    if cmd.kind() != "command" {
-        return None;
-    }
-
-    let mut words = Vec::new();
-    let mut cursor = cmd.walk();
-
-    for child in cmd.named_children(&mut cursor) {
-        match child.kind() {
-            // The command name node wraps one `word` child.
-            "command_name" => {
-                let word_node = child.named_child(0)?; // make sure it's only a word
-                if word_node.kind() != "word" {
-                    return None;
-                }
-                words.push(word_node.utf8_text(src.as_bytes()).ok()?.to_owned());
-            }
-            // Positional‑argument word (allowed).
-            "word" | "number" => {
-                words.push(child.utf8_text(src.as_bytes()).ok()?.to_owned());
-            }
-            "string" => {
-                if child.child_count() == 3
-                    && child.child(0)?.kind() == "\""
-                    && child.child(1)?.kind() == "string_content"
-                    && child.child(2)?.kind() == "\""
-                {
-                    words.push(child.child(1)?.utf8_text(src.as_bytes()).ok()?.to_owned());
-                } else {
-                    // Anything else means the command is *not* plain words.
-                    return None;
-                }
-            }
-            "concatenation" => {
-                // TODO: Consider things like `'ab\'a'`.
-                return None;
-            }
-            "raw_string" => {
-                // Raw string is a single word, but we need to strip the quotes.
-                let raw_string = child.utf8_text(src.as_bytes()).ok()?;
-                let stripped = raw_string
-                    .strip_prefix('\'')
-                    .and_then(|s| s.strip_suffix('\''));
-                if let Some(stripped) = stripped {
-                    words.push(stripped.to_owned());
-                } else {
-                    return None;
-                }
-            }
-            // Anything else means the command is *not* plain words.
-            _ => return None,
-        }
-    }
-
-    Some(words)
-}
+// (bash parsing helpers implemented in crate::bash)
 
 /* ----------------------------------------------------------
 Example
@@ -193,6 +159,7 @@ fn is_valid_sed_n_arg(arg: Option<&str>) -> bool {
         _ => false,
     }
 }
+
 #[cfg(test)]
 mod tests {
     #![allow(clippy::unwrap_used)]
@@ -209,6 +176,11 @@ mod tests {
         assert!(is_safe_to_call_with_exec(&vec_str(&[
             "sed", "-n", "1,5p", "file.txt"
         ])));
+        assert!(is_safe_to_call_with_exec(&vec_str(&[
+            "nl",
+            "-nrz",
+            "Cargo.toml"
+        ])));
 
         // Safe `find` command (no unsafe options).
         assert!(is_safe_to_call_with_exec(&vec_str(&[
@@ -245,6 +217,40 @@ mod tests {
         }
     }
 
+    #[test]
+    fn ripgrep_rules() {
+        // Safe ripgrep invocations – none of the unsafe flags are present.
+        assert!(is_safe_to_call_with_exec(&vec_str(&[
+            "rg",
+            "Cargo.toml",
+            "-n"
+        ])));
+
+        // Unsafe flags that do not take an argument (present verbatim).
+        for args in [
+            vec_str(&["rg", "--search-zip", "files"]),
+            vec_str(&["rg", "-z", "files"]),
+        ] {
+            assert!(
+                !is_safe_to_call_with_exec(&args),
+                "expected {args:?} to be considered unsafe due to zip-search flag",
+            );
+        }
+
+        // Unsafe flags that expect a value, provided in both split and = forms.
+        for args in [
+            vec_str(&["rg", "--pre", "pwned", "files"]),
+            vec_str(&["rg", "--pre=pwned", "files"]),
+            vec_str(&["rg", "--hostname-bin", "pwned", "files"]),
+            vec_str(&["rg", "--hostname-bin=pwned", "files"]),
+        ] {
+            assert!(
+                !is_safe_to_call_with_exec(&args),
+                "expected {args:?} to be considered unsafe due to external-command flag",
+            );
+        }
+    }
+
     #[test]
     fn bash_lc_safe_examples() {
         assert!(is_known_safe_command(&vec_str(&["bash", "-lc", "ls"])));
@@ -277,6 +283,30 @@ mod tests {
         ])));
     }
 
+    #[test]
+    fn bash_lc_safe_examples_with_operators() {
+        assert!(is_known_safe_command(&vec_str(&[
+            "bash",
+            "-lc",
+            "grep -R \"Cargo.toml\" -n || true"
+        ])));
+        assert!(is_known_safe_command(&vec_str(&[
+            "bash",
+            "-lc",
+            "ls && pwd"
+        ])));
+        assert!(is_known_safe_command(&vec_str(&[
+            "bash",
+            "-lc",
+            "echo 'hi' ; ls"
+        ])));
+        assert!(is_known_safe_command(&vec_str(&[
+            "bash",
+            "-lc",
+            "ls | wc -l"
+        ])));
+    }
+
     #[test]
     fn bash_lc_unsafe_examples() {
         assert!(
@@ -290,44 +320,29 @@ mod tests {
 
         assert!(
             !is_known_safe_command(&vec_str(&["bash", "-lc", "find . -name file.txt -delete"])),
-            "Unsafe find option should not be auto‑approved."
-        );
-    }
-
-    #[test]
-    fn test_try_parse_single_word_only_command() {
-        let script_with_single_quoted_string = "sed -n '1,5p' file.txt";
-        let parsed_words = try_parse_bash(script_with_single_quoted_string)
-            .and_then(|tree| {
-                try_parse_single_word_only_command(&tree, script_with_single_quoted_string)
-            })
-            .unwrap();
-        assert_eq!(
-            vec![
-                "sed".to_string(),
-                "-n".to_string(),
-                // Ensure the single quotes are properly removed.
-                "1,5p".to_string(),
-                "file.txt".to_string()
-            ],
-            parsed_words,
+            "Unsafe find option should not be auto-approved."
         );
 
-        let script_with_number_arg = "ls -1";
-        let parsed_words = try_parse_bash(script_with_number_arg)
-            .and_then(|tree| try_parse_single_word_only_command(&tree, script_with_number_arg))
-            .unwrap();
-        assert_eq!(vec!["ls", "-1"], parsed_words,);
+        // Disallowed because of unsafe command in sequence.
+        assert!(
+            !is_known_safe_command(&vec_str(&["bash", "-lc", "ls && rm -rf /"])),
+            "Sequence containing unsafe command must be rejected"
+        );
 
-        let script_with_double_quoted_string_with_no_funny_stuff_arg = "grep -R \"Cargo.toml\" -n";
-        let parsed_words = try_parse_bash(script_with_double_quoted_string_with_no_funny_stuff_arg)
-            .and_then(|tree| {
-                try_parse_single_word_only_command(
-                    &tree,
-                    script_with_double_quoted_string_with_no_funny_stuff_arg,
-                )
-            })
-            .unwrap();
-        assert_eq!(vec!["grep", "-R", "Cargo.toml", "-n"], parsed_words);
+        // Disallowed because of parentheses / subshell.
+        assert!(
+            !is_known_safe_command(&vec_str(&["bash", "-lc", "(ls)"])),
+            "Parentheses (subshell) are not provably safe with the current parser"
+        );
+        assert!(
+            !is_known_safe_command(&vec_str(&["bash", "-lc", "ls || (pwd && echo hi)"])),
+            "Nested parentheses are not provably safe with the current parser"
+        );
+
+        // Disallowed redirection.
+        assert!(
+            !is_known_safe_command(&vec_str(&["bash", "-lc", "ls > out.txt"])),
+            "> redirection should be rejected"
+        );
     }
 }

codex-rs/core/src/lib.rs

@@ -5,11 +5,14 @@
 // the TUI or the tracing stack).
 #![deny(clippy::print_stdout, clippy::print_stderr)]
 
+mod apply_patch;
+mod bash;
 mod chat_completions;
 mod client;
 mod client_common;
 pub mod codex;
 pub use codex::Codex;
+pub use codex::CodexSpawnOk;
 pub mod codex_wrapper;
 pub mod config;
 pub mod config_profile;
@@ -19,6 +22,7 @@ pub mod error;
 pub mod exec;
 pub mod exec_env;
 mod flags;
+pub mod git_info;
 mod is_safe_command;
 mod mcp_connection_manager;
 mod mcp_tool_call;
@@ -34,6 +38,7 @@ mod project_doc;
 pub mod protocol;
 mod rollout;
 mod safety;
+pub mod shell;
 mod user_notification;
 pub mod util;
 

codex-rs/core/src/mcp_connection_manager.rs

@@ -7,6 +7,8 @@
 //! `"<server><MCP_TOOL_NAME_DELIMITER><tool>"` as the key.
 
 use std::collections::HashMap;
+use std::collections::HashSet;
+use std::ffi::OsString;
 use std::time::Duration;
 
 use anyhow::Context;
@@ -16,8 +18,13 @@ use codex_mcp_client::McpClient;
 use mcp_types::ClientCapabilities;
 use mcp_types::Implementation;
 use mcp_types::Tool;
+
+use serde_json::json;
+use sha1::Digest;
+use sha1::Sha1;
 use tokio::task::JoinSet;
 use tracing::info;
+use tracing::warn;
 
 use crate::config_types::McpServerConfig;
 
@@ -26,7 +33,8 @@ use crate::config_types::McpServerConfig;
 ///
 /// OpenAI requires tool names to conform to `^[a-zA-Z0-9_-]+$`, so we must
 /// choose a delimiter from this character set.
-const MCP_TOOL_NAME_DELIMITER: &str = "__OAI_CODEX_MCP__";
+const MCP_TOOL_NAME_DELIMITER: &str = "__";
+const MAX_TOOL_NAME_LENGTH: usize = 64;
 
 /// Timeout for the `tools/list` request.
 const LIST_TOOLS_TIMEOUT: Duration = Duration::from_secs(10);
@@ -35,16 +43,42 @@ const LIST_TOOLS_TIMEOUT: Duration = Duration::from_secs(10);
 /// spawned successfully.
 pub type ClientStartErrors = HashMap<String, anyhow::Error>;
 
-fn fully_qualified_tool_name(server: &str, tool: &str) -> String {
-    format!("{server}{MCP_TOOL_NAME_DELIMITER}{tool}")
+fn qualify_tools(tools: Vec<ToolInfo>) -> HashMap<String, ToolInfo> {
+    let mut used_names = HashSet::new();
+    let mut qualified_tools = HashMap::new();
+    for tool in tools {
+        let mut qualified_name = format!(
+            "{}{}{}",
+            tool.server_name, MCP_TOOL_NAME_DELIMITER, tool.tool_name
+        );
+        if qualified_name.len() > MAX_TOOL_NAME_LENGTH {
+            let mut hasher = Sha1::new();
+            hasher.update(qualified_name.as_bytes());
+            let sha1 = hasher.finalize();
+            let sha1_str = format!("{sha1:x}");
+
+            // Truncate to make room for the hash suffix
+            let prefix_len = MAX_TOOL_NAME_LENGTH - sha1_str.len();
+
+            qualified_name = format!("{}{}", &qualified_name[..prefix_len], sha1_str);
+        }
+
+        if used_names.contains(&qualified_name) {
+            warn!("skipping duplicated tool {}", qualified_name);
+            continue;
+        }
+
+        used_names.insert(qualified_name.clone());
+        qualified_tools.insert(qualified_name, tool);
+    }
+
+    qualified_tools
 }
 
-pub(crate) fn try_parse_fully_qualified_tool_name(fq_name: &str) -> Option<(String, String)> {
-    let (server, tool) = fq_name.split_once(MCP_TOOL_NAME_DELIMITER)?;
-    if server.is_empty() || tool.is_empty() {
-        return None;
-    }
-    Some((server.to_string(), tool.to_string()))
+struct ToolInfo {
+    server_name: String,
+    tool_name: String,
+    tool: Tool,
 }
 
 /// A thin wrapper around a set of running [`McpClient`] instances.
@@ -57,7 +91,7 @@ pub(crate) struct McpConnectionManager {
     clients: HashMap<String, std::sync::Arc<McpClient>>,
 
     /// Fully qualified tool name -> tool instance.
-    tools: HashMap<String, Tool>,
+    tools: HashMap<String, ToolInfo>,
 }
 
 impl McpConnectionManager {
@@ -79,12 +113,27 @@ impl McpConnectionManager {
 
         // Launch all configured servers concurrently.
         let mut join_set = JoinSet::new();
+        let mut errors = ClientStartErrors::new();
 
         for (server_name, cfg) in mcp_servers {
-            // TODO: Verify server name: require `^[a-zA-Z0-9_-]+$`?
+            // Validate server name before spawning
+            if !is_valid_mcp_server_name(&server_name) {
+                let error = anyhow::anyhow!(
+                    "invalid server name '{}': must match pattern ^[a-zA-Z0-9_-]+$",
+                    server_name
+                );
+                errors.insert(server_name, error);
+                continue;
+            }
+
             join_set.spawn(async move {
                 let McpServerConfig { command, args, env } = cfg;
-                let client_res = McpClient::new_stdio_client(command, args, env).await;
+                let client_res = McpClient::new_stdio_client(
+                    command.into(),
+                    args.into_iter().map(OsString::from).collect(),
+                    env,
+                )
+                .await;
                 match client_res {
                     Ok(client) => {
                         // Initialize the client.
@@ -93,10 +142,14 @@ impl McpConnectionManager {
                                 experimental: None,
                                 roots: None,
                                 sampling: None,
+                                // https://modelcontextprotocol.io/specification/2025-06-18/client/elicitation#capabilities
+                                // indicates this should be an empty object.
+                                elicitation: Some(json!({})),
                             },
                             client_info: Implementation {
                                 name: "codex-mcp-client".to_owned(),
                                 version: env!("CARGO_PKG_VERSION").to_owned(),
+                                title: Some("Codex".into()),
                             },
                             protocol_version: mcp_types::MCP_SCHEMA_VERSION.to_owned(),
                         };
@@ -117,7 +170,6 @@ impl McpConnectionManager {
 
         let mut clients: HashMap<String, std::sync::Arc<McpClient>> =
             HashMap::with_capacity(join_set.len());
-        let mut errors = ClientStartErrors::new();
 
         while let Some(res) = join_set.join_next().await {
             let (server_name, client_res) = res?; // JoinError propagation
@@ -132,7 +184,9 @@ impl McpConnectionManager {
             }
         }
 
-        let tools = list_all_tools(&clients).await?;
+        let all_tools = list_all_tools(&clients).await?;
+
+        let tools = qualify_tools(all_tools);
 
         Ok((Self { clients, tools }, errors))
     }
@@ -140,7 +194,10 @@ impl McpConnectionManager {
     /// Returns a single map that contains **all** tools. Each key is the
     /// fully-qualified name for the tool.
     pub fn list_all_tools(&self) -> HashMap<String, Tool> {
-        self.tools.clone()
+        self.tools
+            .iter()
+            .map(|(name, tool)| (name.clone(), tool.tool.clone()))
+            .collect()
     }
 
     /// Invoke the tool indicated by the (server, tool) pair.
@@ -162,13 +219,19 @@ impl McpConnectionManager {
             .await
             .with_context(|| format!("tool call failed for `{server}/{tool}`"))
     }
+
+    pub fn parse_tool_name(&self, tool_name: &str) -> Option<(String, String)> {
+        self.tools
+            .get(tool_name)
+            .map(|tool| (tool.server_name.clone(), tool.tool_name.clone()))
+    }
 }
 
 /// Query every server for its available tools and return a single map that
 /// contains **all** tools. Each key is the fully-qualified name for the tool.
-pub async fn list_all_tools(
+async fn list_all_tools(
     clients: &HashMap<String, std::sync::Arc<McpClient>>,
-) -> Result<HashMap<String, Tool>> {
+) -> Result<Vec<ToolInfo>> {
     let mut join_set = JoinSet::new();
 
     // Spawn one task per server so we can query them concurrently. This
@@ -185,18 +248,19 @@ pub async fn list_all_tools(
         });
     }
 
-    let mut aggregated: HashMap<String, Tool> = HashMap::with_capacity(join_set.len());
+    let mut aggregated: Vec<ToolInfo> = Vec::with_capacity(join_set.len());
 
     while let Some(join_res) = join_set.join_next().await {
         let (server_name, list_result) = join_res?;
         let list_result = list_result?;
 
         for tool in list_result.tools {
-            // TODO(mbolin): escape tool names that contain invalid characters.
-            let fq_name = fully_qualified_tool_name(&server_name, &tool.name);
-            if aggregated.insert(fq_name.clone(), tool).is_some() {
-                panic!("tool name collision for '{fq_name}': suspicious");
-            }
+            let tool_info = ToolInfo {
+                server_name: server_name.clone(),
+                tool_name: tool.name.clone(),
+                tool,
+            };
+            aggregated.push(tool_info);
         }
     }
 
@@ -208,3 +272,99 @@ pub async fn list_all_tools(
 
     Ok(aggregated)
 }
+
+fn is_valid_mcp_server_name(server_name: &str) -> bool {
+    !server_name.is_empty()
+        && server_name
+            .chars()
+            .all(|c| c.is_ascii_alphanumeric() || c == '_' || c == '-')
+}
+
+#[cfg(test)]
+#[allow(clippy::unwrap_used)]
+mod tests {
+    use super::*;
+    use mcp_types::ToolInputSchema;
+
+    fn create_test_tool(server_name: &str, tool_name: &str) -> ToolInfo {
+        ToolInfo {
+            server_name: server_name.to_string(),
+            tool_name: tool_name.to_string(),
+            tool: Tool {
+                annotations: None,
+                description: Some(format!("Test tool: {tool_name}")),
+                input_schema: ToolInputSchema {
+                    properties: None,
+                    required: None,
+                    r#type: "object".to_string(),
+                },
+                name: tool_name.to_string(),
+                output_schema: None,
+                title: None,
+            },
+        }
+    }
+
+    #[test]
+    fn test_qualify_tools_short_non_duplicated_names() {
+        let tools = vec![
+            create_test_tool("server1", "tool1"),
+            create_test_tool("server1", "tool2"),
+        ];
+
+        let qualified_tools = qualify_tools(tools);
+
+        assert_eq!(qualified_tools.len(), 2);
+        assert!(qualified_tools.contains_key("server1__tool1"));
+        assert!(qualified_tools.contains_key("server1__tool2"));
+    }
+
+    #[test]
+    fn test_qualify_tools_duplicated_names_skipped() {
+        let tools = vec![
+            create_test_tool("server1", "duplicate_tool"),
+            create_test_tool("server1", "duplicate_tool"),
+        ];
+
+        let qualified_tools = qualify_tools(tools);
+
+        // Only the first tool should remain, the second is skipped
+        assert_eq!(qualified_tools.len(), 1);
+        assert!(qualified_tools.contains_key("server1__duplicate_tool"));
+    }
+
+    #[test]
+    fn test_qualify_tools_long_names_same_server() {
+        let server_name = "my_server";
+
+        let tools = vec![
+            create_test_tool(
+                server_name,
+                "extremely_lengthy_function_name_that_absolutely_surpasses_all_reasonable_limits",
+            ),
+            create_test_tool(
+                server_name,
+                "yet_another_extremely_lengthy_function_name_that_absolutely_surpasses_all_reasonable_limits",
+            ),
+        ];
+
+        let qualified_tools = qualify_tools(tools);
+
+        assert_eq!(qualified_tools.len(), 2);
+
+        let mut keys: Vec<_> = qualified_tools.keys().cloned().collect();
+        keys.sort();
+
+        assert_eq!(keys[0].len(), 64);
+        assert_eq!(
+            keys[0],
+            "my_server__extremely_lena02e507efc5a9de88637e436690364fd4219e4ef"
+        );
+
+        assert_eq!(keys[1].len(), 64);
+        assert_eq!(
+            keys[1],
+            "my_server__yet_another_e1c3987bd9c50b826cbe1687966f79f0c602d19ca"
+        );
+    }
+}

codex-rs/core/src/model_provider_info.rs

@@ -9,6 +9,7 @@ use serde::Deserialize;
 use serde::Serialize;
 use std::collections::HashMap;
 use std::env::VarError;
+use std::time::Duration;
 
 use crate::error::EnvVarError;
 use crate::openai_api_key::get_openai_api_key;
@@ -16,6 +17,9 @@ use crate::openai_api_key::get_openai_api_key;
 /// 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;
 
 /// Wire protocol that the provider speaks. Most third-party services only
 /// implement the classic OpenAI Chat Completions JSON schema, whereas OpenAI
@@ -26,7 +30,7 @@ const OPENAI_ORIGINATOR_HEADER: &str = "codex_cli_rs";
 #[derive(Debug, Clone, Copy, Default, PartialEq, Eq, Serialize, Deserialize)]
 #[serde(rename_all = "lowercase")]
 pub enum WireApi {
-    /// The experimental “Responses” API exposed by OpenAI at `/v1/responses`.
+    /// The experimental "Responses" API exposed by OpenAI at `/v1/responses`.
     Responses,
 
     /// Regular Chat Completions compatible with `/v1/chat/completions`.
@@ -64,6 +68,16 @@ pub struct ModelProviderInfo {
     /// value should be used. If the environment variable is not set, or the
     /// value is empty, the header will not be included in the request.
     pub env_http_headers: Option<HashMap<String, String>>,
+
+    /// Maximum number of times to retry a failed HTTP request to this provider.
+    pub request_max_retries: Option<u64>,
+
+    /// Number of times to retry reconnecting a dropped streaming response before failing.
+    pub stream_max_retries: Option<u64>,
+
+    /// Idle timeout (in milliseconds) to wait for activity on a streaming response before treating
+    /// the connection as lost.
+    pub stream_idle_timeout_ms: Option<u64>,
 }
 
 impl ModelProviderInfo {
@@ -161,6 +175,25 @@ impl ModelProviderInfo {
             None => Ok(None),
         }
     }
+
+    /// Effective maximum number of request retries for this provider.
+    pub fn request_max_retries(&self) -> u64 {
+        self.request_max_retries
+            .unwrap_or(DEFAULT_REQUEST_MAX_RETRIES)
+    }
+
+    /// Effective maximum number of stream reconnection attempts for this provider.
+    pub fn stream_max_retries(&self) -> u64 {
+        self.stream_max_retries
+            .unwrap_or(DEFAULT_STREAM_MAX_RETRIES)
+    }
+
+    /// Effective idle timeout for streaming responses.
+    pub fn stream_idle_timeout(&self) -> Duration {
+        self.stream_idle_timeout_ms
+            .map(Duration::from_millis)
+            .unwrap_or(Duration::from_millis(DEFAULT_STREAM_IDLE_TIMEOUT_MS))
+    }
 }
 
 /// Built-in default provider list.
@@ -205,6 +238,10 @@ pub fn built_in_model_providers() -> HashMap<String, ModelProviderInfo> {
                         .into_iter()
                         .collect(),
                 ),
+                // Use global defaults for retry/timeout unless overridden in config.toml.
+                request_max_retries: None,
+                stream_max_retries: None,
+                stream_idle_timeout_ms: None,
             },
         ),
     ]
@@ -234,6 +271,9 @@ base_url = "http://localhost:11434/v1"
             query_params: None,
             http_headers: None,
             env_http_headers: None,
+            request_max_retries: None,
+            stream_max_retries: None,
+            stream_idle_timeout_ms: None,
         };
 
         let provider: ModelProviderInfo = toml::from_str(azure_provider_toml).unwrap();
@@ -259,6 +299,9 @@ query_params = { api-version = "2025-04-01-preview" }
             }),
             http_headers: None,
             env_http_headers: None,
+            request_max_retries: None,
+            stream_max_retries: None,
+            stream_idle_timeout_ms: None,
         };
 
         let provider: ModelProviderInfo = toml::from_str(azure_provider_toml).unwrap();
@@ -287,6 +330,9 @@ env_http_headers = { "X-Example-Env-Header" = "EXAMPLE_ENV_VAR" }
             env_http_headers: Some(maplit::hashmap! {
                 "X-Example-Env-Header".to_string() => "EXAMPLE_ENV_VAR".to_string(),
             }),
+            request_max_retries: None,
+            stream_max_retries: None,
+            stream_idle_timeout_ms: None,
         };
 
         let provider: ModelProviderInfo = toml::from_str(azure_provider_toml).unwrap();

codex-rs/core/src/models.rs

@@ -3,6 +3,7 @@ use std::collections::HashMap;
 use base64::Engine;
 use mcp_types::CallToolResult;
 use serde::Deserialize;
+use serde::Deserializer;
 use serde::Serialize;
 use serde::ser::Serializer;
 
@@ -37,12 +38,14 @@ pub enum ContentItem {
 #[serde(tag = "type", rename_all = "snake_case")]
 pub enum ResponseItem {
     Message {
+        id: Option<String>,
         role: String,
         content: Vec<ContentItem>,
     },
     Reasoning {
         id: String,
         summary: Vec<ReasoningItemReasoningSummary>,
+        encrypted_content: Option<String>,
     },
     LocalShellCall {
         /// Set when using the chat completions API.
@@ -53,6 +56,7 @@ pub enum ResponseItem {
         action: LocalShellAction,
     },
     FunctionCall {
+        id: Option<String>,
         name: String,
         // The Responses API returns the function call arguments as a *string* that contains
         // JSON, not as an already‑parsed object. We keep it as a raw string here and let
@@ -78,7 +82,11 @@ pub enum ResponseItem {
 impl From<ResponseInputItem> for ResponseItem {
     fn from(item: ResponseInputItem) -> Self {
         match item {
-            ResponseInputItem::Message { role, content } => Self::Message { role, content },
+            ResponseInputItem::Message { role, content } => Self::Message {
+                role,
+                content,
+                id: None,
+            },
             ResponseInputItem::FunctionCallOutput { call_id, output } => {
                 Self::FunctionCallOutput { call_id, output }
             }
@@ -177,7 +185,7 @@ pub struct ShellToolCallParams {
     pub timeout_ms: Option<u64>,
 }
 
-#[derive(Deserialize, Debug, Clone)]
+#[derive(Debug, Clone)]
 pub struct FunctionCallOutputPayload {
     pub content: String,
     #[expect(dead_code)]
@@ -205,6 +213,19 @@ impl Serialize for FunctionCallOutputPayload {
     }
 }
 
+impl<'de> Deserialize<'de> for FunctionCallOutputPayload {
+    fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
+    where
+        D: Deserializer<'de>,
+    {
+        let s = String::deserialize(deserializer)?;
+        Ok(FunctionCallOutputPayload {
+            content: s,
+            success: None,
+        })
+    }
+}
+
 // Implement Display so callers can treat the payload like a plain string when logging or doing
 // trivial substring checks in tests (existing tests call `.contains()` on the output). Display
 // returns the raw `content` field.

codex-rs/core/src/project_doc.rs

@@ -27,16 +27,16 @@ const PROJECT_DOC_SEPARATOR: &str = "\n\n--- project-doc ---\n\n";
 /// string of instructions.
 pub(crate) async fn get_user_instructions(config: &Config) -> Option<String> {
     match find_project_doc(config).await {
-        Ok(Some(project_doc)) => match &config.instructions {
+        Ok(Some(project_doc)) => match &config.user_instructions {
             Some(original_instructions) => Some(format!(
                 "{original_instructions}{PROJECT_DOC_SEPARATOR}{project_doc}"
             )),
             None => Some(project_doc),
         },
-        Ok(None) => config.instructions.clone(),
+        Ok(None) => config.user_instructions.clone(),
         Err(e) => {
             error!("error trying to find project doc: {e:#}");
-            config.instructions.clone()
+            config.user_instructions.clone()
         }
     }
 }
@@ -159,7 +159,7 @@ mod tests {
         config.cwd = root.path().to_path_buf();
         config.project_doc_max_bytes = limit;
 
-        config.instructions = instructions.map(ToOwned::to_owned);
+        config.user_instructions = instructions.map(ToOwned::to_owned);
         config
     }
 

codex-rs/core/src/protocol.rs

@@ -4,13 +4,15 @@
 //! between user and agent.
 
 use std::collections::HashMap;
+use std::fmt;
 use std::path::Path;
 use std::path::PathBuf;
-use std::str::FromStr;
+use std::str::FromStr; // Added for FinalOutput Display implementation
 
 use mcp_types::CallToolResult;
 use serde::Deserialize;
 use serde::Serialize;
+use strum_macros::Display;
 use uuid::Uuid;
 
 use crate::config_types::ReasoningEffort as ReasoningEffortConfig;
@@ -33,6 +35,8 @@ pub struct Submission {
 #[allow(clippy::large_enum_variant)]
 #[non_exhaustive]
 pub enum Op {
+    /// Erase all conversation history for the current session.
+    EraseConversationHistory,
     /// Configure the model session.
     ConfigureSession {
         /// Provider identifier ("openai", "openrouter", ...).
@@ -44,8 +48,12 @@ pub enum Op {
         model_reasoning_effort: ReasoningEffortConfig,
         model_reasoning_summary: ReasoningSummaryConfig,
 
-        /// Model instructions
-        instructions: Option<String>,
+        /// Model instructions that are appended to the base instructions.
+        user_instructions: Option<String>,
+
+        /// Base instructions override.
+        base_instructions: Option<String>,
+
         /// When to escalate for approval for execution
         approval_policy: AskForApproval,
         /// How to sandbox commands executed in the system
@@ -69,6 +77,10 @@ pub enum Op {
         /// `ConfigureSession` operation so that the business-logic layer can
         /// operate deterministically.
         cwd: std::path::PathBuf,
+
+        /// Path to a rollout file to resume from.
+        #[serde(skip_serializing_if = "Option::is_none")]
+        resume_path: Option<std::path::PathBuf>,
     },
 
     /// Abort current task.
@@ -108,18 +120,23 @@ pub enum Op {
 
     /// Request a single history entry identified by `log_id` + `offset`.
     GetHistoryEntryRequest { offset: usize, log_id: u64 },
+
+    /// Request to shut down codex instance.
+    Shutdown,
 }
 
 /// Determines the conditions under which the user is consulted to approve
 /// running the command proposed by Codex.
-#[derive(Debug, Clone, Copy, Default, PartialEq, Eq, Hash, Serialize, Deserialize)]
+#[derive(Debug, Clone, Copy, Default, PartialEq, Eq, Hash, Serialize, Deserialize, Display)]
 #[serde(rename_all = "kebab-case")]
+#[strum(serialize_all = "kebab-case")]
 pub enum AskForApproval {
     /// Under this policy, only "known safe" commands—as determined by
     /// `is_safe_command()`—that **only read files** are auto‑approved.
     /// Everything else will ask the user to approve.
     #[default]
     #[serde(rename = "untrusted")]
+    #[strum(serialize = "untrusted")]
     UnlessTrusted,
 
     /// *All* commands are auto‑approved, but they are expected to run inside a
@@ -263,8 +280,9 @@ pub struct Event {
 }
 
 /// Response event from the agent
-#[derive(Debug, Clone, Deserialize, Serialize)]
+#[derive(Debug, Clone, Deserialize, Serialize, Display)]
 #[serde(tag = "type", rename_all = "snake_case")]
+#[strum(serialize_all = "snake_case")]
 pub enum EventMsg {
     /// Error while executing a submission
     Error(ErrorEvent),
@@ -282,9 +300,15 @@ pub enum EventMsg {
     /// Agent text output message
     AgentMessage(AgentMessageEvent),
 
+    /// Agent text output delta message
+    AgentMessageDelta(AgentMessageDeltaEvent),
+
     /// Reasoning event from agent.
     AgentReasoning(AgentReasoningEvent),
 
+    /// Agent reasoning delta event from agent.
+    AgentReasoningDelta(AgentReasoningDeltaEvent),
+
     /// Ack the client's configure message.
     SessionConfigured(SessionConfiguredEvent),
 
@@ -312,6 +336,9 @@ pub enum EventMsg {
 
     /// Response to GetHistoryEntryRequest.
     GetHistoryEntryResponse(GetHistoryEntryResponseEvent),
+
+    /// Notification that the agent is shutting down.
+    ShutdownComplete,
 }
 
 // Individual event payload types matching each `EventMsg` variant.
@@ -335,16 +362,56 @@ pub struct TokenUsage {
     pub total_tokens: u64,
 }
 
+#[derive(Debug, Clone, Deserialize, Serialize)]
+pub struct FinalOutput {
+    pub token_usage: TokenUsage,
+}
+
+impl From<TokenUsage> for FinalOutput {
+    fn from(token_usage: TokenUsage) -> Self {
+        Self { token_usage }
+    }
+}
+
+impl fmt::Display for FinalOutput {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        let u = &self.token_usage;
+        write!(
+            f,
+            "Token usage: total={} input={}{} output={}{}",
+            u.total_tokens,
+            u.input_tokens,
+            u.cached_input_tokens
+                .map(|c| format!(" (cached {c})"))
+                .unwrap_or_default(),
+            u.output_tokens,
+            u.reasoning_output_tokens
+                .map(|r| format!(" (reasoning {r})"))
+                .unwrap_or_default()
+        )
+    }
+}
+
 #[derive(Debug, Clone, Deserialize, Serialize)]
 pub struct AgentMessageEvent {
     pub message: String,
 }
 
+#[derive(Debug, Clone, Deserialize, Serialize)]
+pub struct AgentMessageDeltaEvent {
+    pub delta: String,
+}
+
 #[derive(Debug, Clone, Deserialize, Serialize)]
 pub struct AgentReasoningEvent {
     pub text: String,
 }
 
+#[derive(Debug, Clone, Deserialize, Serialize)]
+pub struct AgentReasoningDeltaEvent {
+    pub delta: String,
+}
+
 #[derive(Debug, Clone, Deserialize, Serialize)]
 pub struct McpToolCallBeginEvent {
     /// Identifier so this can be paired with the McpToolCallEnd event.
@@ -398,6 +465,8 @@ pub struct ExecCommandEndEvent {
 
 #[derive(Debug, Clone, Deserialize, Serialize)]
 pub struct ExecApprovalRequestEvent {
+    /// Identifier for the associated exec call, if available.
+    pub call_id: String,
     /// The command to be executed.
     pub command: Vec<String>,
     /// The command's working directory.
@@ -409,6 +478,8 @@ pub struct ExecApprovalRequestEvent {
 
 #[derive(Debug, Clone, Deserialize, Serialize)]
 pub struct ApplyPatchApprovalRequestEvent {
+    /// Responses API call id for the associated patch apply call, if available.
+    pub call_id: String,
     pub changes: HashMap<PathBuf, FileChange>,
     /// Optional explanatory reason (e.g. request for extra write access).
     #[serde(skip_serializing_if = "Option::is_none")]

codex-rs/core/src/rollout.rs

@@ -1,33 +1,57 @@
-//! Functionality to persist a Codex conversation *rollout* – a linear list of
-//! [`ResponseItem`] objects exchanged during a session – to disk so that
-//! sessions can be replayed or inspected later (mirrors the behaviour of the
-//! upstream TypeScript implementation).
+//! Persist Codex session rollouts (.jsonl) so sessions can be replayed or inspected later.
 
 use std::fs::File;
 use std::fs::{self};
 use std::io::Error as IoError;
+use std::path::Path;
 
+use serde::Deserialize;
 use serde::Serialize;
+use serde_json::Value;
 use time::OffsetDateTime;
 use time::format_description::FormatItem;
 use time::macros::format_description;
 use tokio::io::AsyncWriteExt;
 use tokio::sync::mpsc::Sender;
 use tokio::sync::mpsc::{self};
+use tokio::sync::oneshot;
+use tracing::info;
+use tracing::warn;
 use uuid::Uuid;
 
 use crate::config::Config;
+use crate::git_info::GitInfo;
+use crate::git_info::collect_git_info;
 use crate::models::ResponseItem;
 
-/// Folder inside `~/.codex` that holds saved rollouts.
 const SESSIONS_SUBDIR: &str = "sessions";
 
+#[derive(Serialize, Deserialize, Clone, Default)]
+pub struct SessionMeta {
+    pub id: Uuid,
+    pub timestamp: String,
+    pub instructions: Option<String>,
+}
+
 #[derive(Serialize)]
-struct SessionMeta {
-    id: String,
-    timestamp: String,
+struct SessionMetaWithGit {
+    #[serde(flatten)]
+    meta: SessionMeta,
     #[serde(skip_serializing_if = "Option::is_none")]
-    instructions: Option<String>,
+    git: Option<GitInfo>,
+}
+
+#[derive(Serialize, Deserialize, Default, Clone)]
+pub struct SessionStateSnapshot {}
+
+#[derive(Serialize, Deserialize, Default, Clone)]
+pub struct SavedSession {
+    pub session: SessionMeta,
+    #[serde(default)]
+    pub items: Vec<ResponseItem>,
+    #[serde(default)]
+    pub state: SessionStateSnapshot,
+    pub session_id: Uuid,
 }
 
 /// Records all [`ResponseItem`]s for a session and flushes them to disk after
@@ -41,7 +65,13 @@ struct SessionMeta {
 /// ```
 #[derive(Clone)]
 pub(crate) struct RolloutRecorder {
-    tx: Sender<String>,
+    tx: Sender<RolloutCmd>,
+}
+
+enum RolloutCmd {
+    AddItems(Vec<ResponseItem>),
+    UpdateState(SessionStateSnapshot),
+    Shutdown { ack: oneshot::Sender<()> },
 }
 
 impl RolloutRecorder {
@@ -59,7 +89,6 @@ impl RolloutRecorder {
             timestamp,
         } = create_log_file(config, uuid)?;
 
-        // Build the static session metadata JSON first.
         let timestamp_format: &[FormatItem] = format_description!(
             "[year]-[month]-[day]T[hour]:[minute]:[second].[subsecond digits:3]Z"
         );
@@ -67,48 +96,33 @@ impl RolloutRecorder {
             .format(timestamp_format)
             .map_err(|e| IoError::other(format!("failed to format timestamp: {e}")))?;
 
-        let meta = SessionMeta {
-            timestamp,
-            id: session_id.to_string(),
-            instructions,
-        };
+        // Clone the cwd for the spawned task to collect git info asynchronously
+        let cwd = config.cwd.clone();
 
         // A reasonably-sized bounded channel. If the buffer fills up the send
         // future will yield, which is fine – we only need to ensure we do not
-        // perform *blocking* I/O on the caller’s thread.
-        let (tx, mut rx) = mpsc::channel::<String>(256);
+        // perform *blocking* I/O on the caller's thread.
+        let (tx, rx) = mpsc::channel::<RolloutCmd>(256);
 
         // Spawn a Tokio task that owns the file handle and performs async
         // writes. Using `tokio::fs::File` keeps everything on the async I/O
         // driver instead of blocking the runtime.
-        tokio::task::spawn(async move {
-            let mut file = tokio::fs::File::from_std(file);
+        tokio::task::spawn(rollout_writer(
+            tokio::fs::File::from_std(file),
+            rx,
+            Some(SessionMeta {
+                timestamp,
+                id: session_id,
+                instructions,
+            }),
+            cwd,
+        ));
 
-            while let Some(line) = rx.recv().await {
-                // Write line + newline, then flush to disk.
-                if let Err(e) = file.write_all(line.as_bytes()).await {
-                    tracing::warn!("rollout writer: failed to write line: {e}");
-                    break;
-                }
-                if let Err(e) = file.write_all(b"\n").await {
-                    tracing::warn!("rollout writer: failed to write newline: {e}");
-                    break;
-                }
-                if let Err(e) = file.flush().await {
-                    tracing::warn!("rollout writer: failed to flush: {e}");
-                    break;
-                }
-            }
-        });
-
-        let recorder = Self { tx };
-        // Ensure SessionMeta is the first item in the file.
-        recorder.record_item(&meta).await?;
-        Ok(recorder)
+        Ok(Self { tx })
     }
 
-    /// Append `items` to the rollout file.
     pub(crate) async fn record_items(&self, items: &[ResponseItem]) -> std::io::Result<()> {
+        let mut filtered = Vec::new();
         for item in items {
             match item {
                 // Note that function calls may look a bit strange if they are
@@ -117,27 +131,114 @@ impl RolloutRecorder {
                 ResponseItem::Message { .. }
                 | ResponseItem::LocalShellCall { .. }
                 | ResponseItem::FunctionCall { .. }
-                | ResponseItem::FunctionCallOutput { .. } => {}
-                ResponseItem::Reasoning { .. } | ResponseItem::Other => {
+                | ResponseItem::FunctionCallOutput { .. }
+                | ResponseItem::Reasoning { .. } => filtered.push(item.clone()),
+                ResponseItem::Other => {
                     // These should never be serialized.
                     continue;
                 }
             }
-            self.record_item(item).await?;
         }
-        Ok(())
+        if filtered.is_empty() {
+            return Ok(());
+        }
+        self.tx
+            .send(RolloutCmd::AddItems(filtered))
+            .await
+            .map_err(|e| IoError::other(format!("failed to queue rollout items: {e}")))
     }
 
-    async fn record_item(&self, item: &impl Serialize) -> std::io::Result<()> {
-        // Serialize the item to JSON first so that the writer thread only has
-        // to perform the actual write.
-        let json = serde_json::to_string(item)
-            .map_err(|e| IoError::other(format!("failed to serialize response items: {e}")))?;
-
+    pub(crate) async fn record_state(&self, state: SessionStateSnapshot) -> std::io::Result<()> {
         self.tx
-            .send(json)
+            .send(RolloutCmd::UpdateState(state))
             .await
-            .map_err(|e| IoError::other(format!("failed to queue rollout item: {e}")))
+            .map_err(|e| IoError::other(format!("failed to queue rollout state: {e}")))
+    }
+
+    pub async fn resume(
+        path: &Path,
+        cwd: std::path::PathBuf,
+    ) -> std::io::Result<(Self, SavedSession)> {
+        info!("Resuming rollout from {path:?}");
+        let text = tokio::fs::read_to_string(path).await?;
+        let mut lines = text.lines();
+        let meta_line = lines
+            .next()
+            .ok_or_else(|| IoError::other("empty session file"))?;
+        let session: SessionMeta = serde_json::from_str(meta_line)
+            .map_err(|e| IoError::other(format!("failed to parse session meta: {e}")))?;
+        let mut items = Vec::new();
+        let mut state = SessionStateSnapshot::default();
+
+        for line in lines {
+            if line.trim().is_empty() {
+                continue;
+            }
+            let v: Value = match serde_json::from_str(line) {
+                Ok(v) => v,
+                Err(_) => continue,
+            };
+            if v.get("record_type")
+                .and_then(|rt| rt.as_str())
+                .map(|s| s == "state")
+                .unwrap_or(false)
+            {
+                if let Ok(s) = serde_json::from_value::<SessionStateSnapshot>(v.clone()) {
+                    state = s
+                }
+                continue;
+            }
+            match serde_json::from_value::<ResponseItem>(v.clone()) {
+                Ok(item) => match item {
+                    ResponseItem::Message { .. }
+                    | ResponseItem::LocalShellCall { .. }
+                    | ResponseItem::FunctionCall { .. }
+                    | ResponseItem::FunctionCallOutput { .. }
+                    | ResponseItem::Reasoning { .. } => items.push(item),
+                    ResponseItem::Other => {}
+                },
+                Err(e) => {
+                    warn!("failed to parse item: {v:?}, error: {e}");
+                }
+            }
+        }
+
+        let saved = SavedSession {
+            session: session.clone(),
+            items: items.clone(),
+            state: state.clone(),
+            session_id: session.id,
+        };
+
+        let file = std::fs::OpenOptions::new()
+            .append(true)
+            .read(true)
+            .open(path)?;
+
+        let (tx, rx) = mpsc::channel::<RolloutCmd>(256);
+        tokio::task::spawn(rollout_writer(
+            tokio::fs::File::from_std(file),
+            rx,
+            None,
+            cwd,
+        ));
+        info!("Resumed rollout successfully from {path:?}");
+        Ok((Self { tx }, saved))
+    }
+
+    pub async fn shutdown(&self) -> std::io::Result<()> {
+        let (tx_done, rx_done) = oneshot::channel();
+        match self.tx.send(RolloutCmd::Shutdown { ack: tx_done }).await {
+            Ok(_) => rx_done
+                .await
+                .map_err(|e| IoError::other(format!("failed waiting for rollout shutdown: {e}"))),
+            Err(e) => {
+                warn!("failed to send rollout shutdown command: {e}");
+                Err(IoError::other(format!(
+                    "failed to send rollout shutdown command: {e}"
+                )))
+            }
+        }
     }
 }
 
@@ -153,13 +254,15 @@ struct LogFileInfo {
 }
 
 fn create_log_file(config: &Config, session_id: Uuid) -> std::io::Result<LogFileInfo> {
-    // Resolve ~/.codex/sessions and create it if missing.
-    let mut dir = config.codex_home.clone();
-    dir.push(SESSIONS_SUBDIR);
-    fs::create_dir_all(&dir)?;
-
+    // Resolve ~/.codex/sessions/YYYY/MM/DD and create it if missing.
     let timestamp = OffsetDateTime::now_local()
         .map_err(|e| IoError::other(format!("failed to get local time: {e}")))?;
+    let mut dir = config.codex_home.clone();
+    dir.push(SESSIONS_SUBDIR);
+    dir.push(timestamp.year().to_string());
+    dir.push(format!("{:02}", u8::from(timestamp.month())));
+    dir.push(format!("{:02}", timestamp.day()));
+    fs::create_dir_all(&dir)?;
 
     // Custom format for YYYY-MM-DDThh-mm-ss. Use `-` instead of `:` for
     // compatibility with filesystems that do not allow colons in filenames.
@@ -183,3 +286,77 @@ fn create_log_file(config: &Config, session_id: Uuid) -> std::io::Result<LogFile
         timestamp,
     })
 }
+
+async fn rollout_writer(
+    file: tokio::fs::File,
+    mut rx: mpsc::Receiver<RolloutCmd>,
+    mut meta: Option<SessionMeta>,
+    cwd: std::path::PathBuf,
+) -> std::io::Result<()> {
+    let mut writer = JsonlWriter { file };
+
+    // If we have a meta, collect git info asynchronously and write meta first
+    if let Some(session_meta) = meta.take() {
+        let git_info = collect_git_info(&cwd).await;
+        let session_meta_with_git = SessionMetaWithGit {
+            meta: session_meta,
+            git: git_info,
+        };
+
+        // Write the SessionMeta as the first item in the file
+        writer.write_line(&session_meta_with_git).await?;
+    }
+
+    // Process rollout commands
+    while let Some(cmd) = rx.recv().await {
+        match cmd {
+            RolloutCmd::AddItems(items) => {
+                for item in items {
+                    match item {
+                        ResponseItem::Message { .. }
+                        | ResponseItem::LocalShellCall { .. }
+                        | ResponseItem::FunctionCall { .. }
+                        | ResponseItem::FunctionCallOutput { .. }
+                        | ResponseItem::Reasoning { .. } => {
+                            writer.write_line(&item).await?;
+                        }
+                        ResponseItem::Other => {}
+                    }
+                }
+            }
+            RolloutCmd::UpdateState(state) => {
+                #[derive(Serialize)]
+                struct StateLine<'a> {
+                    record_type: &'static str,
+                    #[serde(flatten)]
+                    state: &'a SessionStateSnapshot,
+                }
+                writer
+                    .write_line(&StateLine {
+                        record_type: "state",
+                        state: &state,
+                    })
+                    .await?;
+            }
+            RolloutCmd::Shutdown { ack } => {
+                let _ = ack.send(());
+            }
+        }
+    }
+
+    Ok(())
+}
+
+struct JsonlWriter {
+    file: tokio::fs::File,
+}
+
+impl JsonlWriter {
+    async fn write_line(&mut self, item: &impl serde::Serialize) -> std::io::Result<()> {
+        let mut json = serde_json::to_string(item)?;
+        json.push('\n');
+        let _ = self.file.write_all(json.as_bytes()).await;
+        self.file.flush().await?;
+        Ok(())
+    }
+}

codex-rs/core/src/shell.rs

@@ -0,0 +1,204 @@
+use shlex;
+
+#[derive(Debug, PartialEq, Eq)]
+pub struct ZshShell {
+    shell_path: String,
+    zshrc_path: String,
+}
+
+#[derive(Debug, PartialEq, Eq)]
+pub enum Shell {
+    Zsh(ZshShell),
+    Unknown,
+}
+
+impl Shell {
+    pub fn format_default_shell_invocation(&self, command: Vec<String>) -> Option<Vec<String>> {
+        match self {
+            Shell::Zsh(zsh) => {
+                if !std::path::Path::new(&zsh.zshrc_path).exists() {
+                    return None;
+                }
+
+                let mut result = vec![zsh.shell_path.clone(), "-c".to_string()];
+                if let Ok(joined) = shlex::try_join(command.iter().map(|s| s.as_str())) {
+                    result.push(format!("source {} && ({joined})", zsh.zshrc_path));
+                } else {
+                    return None;
+                }
+                Some(result)
+            }
+            Shell::Unknown => None,
+        }
+    }
+}
+
+#[cfg(target_os = "macos")]
+pub async fn default_user_shell() -> Shell {
+    use tokio::process::Command;
+    use whoami;
+
+    let user = whoami::username();
+    let home = format!("/Users/{user}");
+    let output = Command::new("dscl")
+        .args([".", "-read", &home, "UserShell"])
+        .output()
+        .await
+        .ok();
+    match output {
+        Some(o) => {
+            if !o.status.success() {
+                return Shell::Unknown;
+            }
+            let stdout = String::from_utf8_lossy(&o.stdout);
+            for line in stdout.lines() {
+                if let Some(shell_path) = line.strip_prefix("UserShell: ") {
+                    if shell_path.ends_with("/zsh") {
+                        return Shell::Zsh(ZshShell {
+                            shell_path: shell_path.to_string(),
+                            zshrc_path: format!("{home}/.zshrc"),
+                        });
+                    }
+                }
+            }
+
+            Shell::Unknown
+        }
+        _ => Shell::Unknown,
+    }
+}
+
+#[cfg(not(target_os = "macos"))]
+pub async fn default_user_shell() -> Shell {
+    Shell::Unknown
+}
+
+#[cfg(test)]
+#[cfg(target_os = "macos")]
+mod tests {
+    use super::*;
+    use std::process::Command;
+
+    #[tokio::test]
+    #[expect(clippy::unwrap_used)]
+    async fn test_current_shell_detects_zsh() {
+        let shell = Command::new("sh")
+            .arg("-c")
+            .arg("echo $SHELL")
+            .output()
+            .unwrap();
+
+        let home = std::env::var("HOME").unwrap();
+        let shell_path = String::from_utf8_lossy(&shell.stdout).trim().to_string();
+        if shell_path.ends_with("/zsh") {
+            assert_eq!(
+                default_user_shell().await,
+                Shell::Zsh(ZshShell {
+                    shell_path: shell_path.to_string(),
+                    zshrc_path: format!("{home}/.zshrc",),
+                })
+            );
+        }
+    }
+
+    #[tokio::test]
+    async fn test_run_with_profile_zshrc_not_exists() {
+        let shell = Shell::Zsh(ZshShell {
+            shell_path: "/bin/zsh".to_string(),
+            zshrc_path: "/does/not/exist/.zshrc".to_string(),
+        });
+        let actual_cmd = shell.format_default_shell_invocation(vec!["myecho".to_string()]);
+        assert_eq!(actual_cmd, None);
+    }
+
+    #[expect(clippy::unwrap_used)]
+    #[tokio::test]
+    async fn test_run_with_profile_escaping_and_execution() {
+        let shell_path = "/bin/zsh";
+
+        let cases = vec![
+            (
+                vec!["myecho"],
+                vec![shell_path, "-c", "source ZSHRC_PATH && (myecho)"],
+                Some("It works!\n"),
+            ),
+            (
+                vec!["bash", "-lc", "echo 'single' \"double\""],
+                vec![
+                    shell_path,
+                    "-c",
+                    "source ZSHRC_PATH && (bash -lc \"echo 'single' \\\"double\\\"\")",
+                ],
+                Some("single double\n"),
+            ),
+        ];
+        for (input, expected_cmd, expected_output) in cases {
+            use std::collections::HashMap;
+            use std::path::PathBuf;
+            use std::sync::Arc;
+
+            use tokio::sync::Notify;
+
+            use crate::exec::ExecParams;
+            use crate::exec::SandboxType;
+            use crate::exec::process_exec_tool_call;
+            use crate::protocol::SandboxPolicy;
+
+            // create a temp directory with a zshrc file in it
+            let temp_home = tempfile::tempdir().unwrap();
+            let zshrc_path = temp_home.path().join(".zshrc");
+            std::fs::write(
+                &zshrc_path,
+                r#"
+                    set -x
+                    function myecho {
+                        echo 'It works!'
+                    }
+                    "#,
+            )
+            .unwrap();
+            let shell = Shell::Zsh(ZshShell {
+                shell_path: shell_path.to_string(),
+                zshrc_path: zshrc_path.to_str().unwrap().to_string(),
+            });
+
+            let actual_cmd = shell
+                .format_default_shell_invocation(input.iter().map(|s| s.to_string()).collect());
+            let expected_cmd = expected_cmd
+                .iter()
+                .map(|s| {
+                    s.replace("ZSHRC_PATH", zshrc_path.to_str().unwrap())
+                        .to_string()
+                })
+                .collect();
+
+            assert_eq!(actual_cmd, Some(expected_cmd));
+            // Actually run the command and check output/exit code
+            let output = process_exec_tool_call(
+                ExecParams {
+                    command: actual_cmd.unwrap(),
+                    cwd: PathBuf::from(temp_home.path()),
+                    timeout_ms: None,
+                    env: HashMap::from([(
+                        "HOME".to_string(),
+                        temp_home.path().to_str().unwrap().to_string(),
+                    )]),
+                },
+                SandboxType::None,
+                Arc::new(Notify::new()),
+                &SandboxPolicy::DangerFullAccess,
+                &None,
+            )
+            .await
+            .unwrap();
+
+            assert_eq!(output.exit_code, 0, "input: {input:?} output: {output:?}");
+            if let Some(expected) = expected_output {
+                assert_eq!(
+                    output.stdout, expected,
+                    "input: {input:?} output: {output:?}"
+                );
+            }
+        }
+    }
+}

codex-rs/core/tests/cli_stream.rs

@@ -2,7 +2,11 @@
 
 use assert_cmd::Command as AssertCommand;
 use codex_core::exec::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
+use std::time::Duration;
+use std::time::Instant;
 use tempfile::TempDir;
+use uuid::Uuid;
+use walkdir::WalkDir;
 use wiremock::Mock;
 use wiremock::MockServer;
 use wiremock::ResponseTemplate;
@@ -71,8 +75,8 @@ async fn chat_mode_stream_cli() {
     println!("Stderr:\n{}", String::from_utf8_lossy(&output.stderr));
     assert!(output.status.success());
     let stdout = String::from_utf8_lossy(&output.stdout);
-    assert!(stdout.contains("hi"));
-    assert_eq!(stdout.matches("hi").count(), 1);
+    let hi_lines = stdout.lines().filter(|line| line.trim() == "hi").count();
+    assert_eq!(hi_lines, 1, "Expected exactly one line with 'hi'");
 
     server.verify().await;
 }
@@ -117,3 +121,364 @@ async fn responses_api_stream_cli() {
     let stdout = String::from_utf8_lossy(&output.stdout);
     assert!(stdout.contains("fixture hello"));
 }
+
+/// End-to-end: create a session (writes rollout), verify the file, then resume and confirm append.
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn integration_creates_and_checks_session_file() {
+    // Honor sandbox network restrictions for CI parity with the other tests.
+    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;
+    }
+
+    // 1. Temp home so we read/write isolated session files.
+    let home = TempDir::new().unwrap();
+
+    // 2. Unique marker we'll look for in the session log.
+    let marker = format!("integration-test-{}", Uuid::new_v4());
+    let prompt = format!("echo {marker}");
+
+    // 3. Use the same offline SSE fixture as responses_api_stream_cli so the test is hermetic.
+    let fixture =
+        std::path::Path::new(env!("CARGO_MANIFEST_DIR")).join("tests/cli_responses_fixture.sse");
+
+    // 4. Run the codex CLI through cargo (ensures the right bin is built) and invoke `exec`,
+    //    which is what records a session.
+    let mut cmd = AssertCommand::new("cargo");
+    cmd.arg("run")
+        .arg("-p")
+        .arg("codex-cli")
+        .arg("--quiet")
+        .arg("--")
+        .arg("exec")
+        .arg("--skip-git-repo-check")
+        .arg("-C")
+        .arg(env!("CARGO_MANIFEST_DIR"))
+        .arg(&prompt);
+    cmd.env("CODEX_HOME", home.path())
+        .env("OPENAI_API_KEY", "dummy")
+        .env("CODEX_RS_SSE_FIXTURE", &fixture)
+        // Required for CLI arg parsing even though fixture short-circuits network usage.
+        .env("OPENAI_BASE_URL", "http://unused.local");
+
+    let output = cmd.output().unwrap();
+    assert!(
+        output.status.success(),
+        "codex-cli exec failed: {}",
+        String::from_utf8_lossy(&output.stderr)
+    );
+
+    // Wait for sessions dir to appear.
+    let sessions_dir = home.path().join("sessions");
+    let dir_deadline = Instant::now() + Duration::from_secs(5);
+    while !sessions_dir.exists() && Instant::now() < dir_deadline {
+        std::thread::sleep(Duration::from_millis(50));
+    }
+    assert!(sessions_dir.exists(), "sessions directory never appeared");
+
+    // Find the session file that contains `marker`.
+    let deadline = Instant::now() + Duration::from_secs(10);
+    let mut matching_path: Option<std::path::PathBuf> = None;
+    while Instant::now() < deadline && matching_path.is_none() {
+        for entry in WalkDir::new(&sessions_dir) {
+            let entry = match entry {
+                Ok(e) => e,
+                Err(_) => continue,
+            };
+            if !entry.file_type().is_file() {
+                continue;
+            }
+            if !entry.file_name().to_string_lossy().ends_with(".jsonl") {
+                continue;
+            }
+            let path = entry.path();
+            let Ok(content) = std::fs::read_to_string(path) else {
+                continue;
+            };
+            let mut lines = content.lines();
+            if lines.next().is_none() {
+                continue;
+            }
+            for line in lines {
+                if line.trim().is_empty() {
+                    continue;
+                }
+                let item: serde_json::Value = match serde_json::from_str(line) {
+                    Ok(v) => v,
+                    Err(_) => continue,
+                };
+                if item.get("type").and_then(|t| t.as_str()) == Some("message") {
+                    if let Some(c) = item.get("content") {
+                        if c.to_string().contains(&marker) {
+                            matching_path = Some(path.to_path_buf());
+                            break;
+                        }
+                    }
+                }
+            }
+        }
+        if matching_path.is_none() {
+            std::thread::sleep(Duration::from_millis(50));
+        }
+    }
+
+    let path = match matching_path {
+        Some(p) => p,
+        None => panic!("No session file containing the marker was found"),
+    };
+
+    // Basic sanity checks on location and metadata.
+    let rel = match path.strip_prefix(&sessions_dir) {
+        Ok(r) => r,
+        Err(_) => panic!("session file should live under sessions/"),
+    };
+    let comps: Vec<String> = rel
+        .components()
+        .map(|c| c.as_os_str().to_string_lossy().into_owned())
+        .collect();
+    assert_eq!(
+        comps.len(),
+        4,
+        "Expected sessions/YYYY/MM/DD/<file>, got {rel:?}"
+    );
+    let year = &comps[0];
+    let month = &comps[1];
+    let day = &comps[2];
+    assert!(
+        year.len() == 4 && year.chars().all(|c| c.is_ascii_digit()),
+        "Year dir not 4-digit numeric: {year}"
+    );
+    assert!(
+        month.len() == 2 && month.chars().all(|c| c.is_ascii_digit()),
+        "Month dir not zero-padded 2-digit numeric: {month}"
+    );
+    assert!(
+        day.len() == 2 && day.chars().all(|c| c.is_ascii_digit()),
+        "Day dir not zero-padded 2-digit numeric: {day}"
+    );
+    if let Ok(m) = month.parse::<u8>() {
+        assert!((1..=12).contains(&m), "Month out of range: {m}");
+    }
+    if let Ok(d) = day.parse::<u8>() {
+        assert!((1..=31).contains(&d), "Day out of range: {d}");
+    }
+
+    let content =
+        std::fs::read_to_string(&path).unwrap_or_else(|_| panic!("Failed to read session file"));
+    let mut lines = content.lines();
+    let meta_line = lines
+        .next()
+        .ok_or("missing session meta line")
+        .unwrap_or_else(|_| panic!("missing session meta line"));
+    let meta: serde_json::Value = serde_json::from_str(meta_line)
+        .unwrap_or_else(|_| panic!("Failed to parse session meta line as JSON"));
+    assert!(meta.get("id").is_some(), "SessionMeta missing id");
+    assert!(
+        meta.get("timestamp").is_some(),
+        "SessionMeta missing timestamp"
+    );
+
+    let mut found_message = false;
+    for line in lines {
+        if line.trim().is_empty() {
+            continue;
+        }
+        let Ok(item) = serde_json::from_str::<serde_json::Value>(line) else {
+            continue;
+        };
+        if item.get("type").and_then(|t| t.as_str()) == Some("message") {
+            if let Some(c) = item.get("content") {
+                if c.to_string().contains(&marker) {
+                    found_message = true;
+                    break;
+                }
+            }
+        }
+    }
+    assert!(
+        found_message,
+        "No message found in session file containing the marker"
+    );
+
+    // Second run: resume and append.
+    let orig_len = content.lines().count();
+    let marker2 = format!("integration-resume-{}", Uuid::new_v4());
+    let prompt2 = format!("echo {marker2}");
+    // Cross‑platform safe resume override.  On Windows, backslashes in a TOML string must be escaped
+    // or the parse will fail and the raw literal (including quotes) may be preserved all the way down
+    // to Config, which in turn breaks resume because the path is invalid. Normalize to forward slashes
+    // to sidestep the issue.
+    let resume_path_str = path.to_string_lossy().replace('\\', "/");
+    let resume_override = format!("experimental_resume=\"{resume_path_str}\"");
+    let mut cmd2 = AssertCommand::new("cargo");
+    cmd2.arg("run")
+        .arg("-p")
+        .arg("codex-cli")
+        .arg("--quiet")
+        .arg("--")
+        .arg("exec")
+        .arg("--skip-git-repo-check")
+        .arg("-c")
+        .arg(&resume_override)
+        .arg("-C")
+        .arg(env!("CARGO_MANIFEST_DIR"))
+        .arg(&prompt2);
+    cmd2.env("CODEX_HOME", home.path())
+        .env("OPENAI_API_KEY", "dummy")
+        .env("CODEX_RS_SSE_FIXTURE", &fixture)
+        .env("OPENAI_BASE_URL", "http://unused.local");
+
+    let output2 = cmd2.output().unwrap();
+    assert!(output2.status.success(), "resume codex-cli run failed");
+
+    // The rollout writer runs on a background async task; give it a moment to flush.
+    let mut new_len = orig_len;
+    let deadline = Instant::now() + Duration::from_secs(5);
+    let mut content2 = String::new();
+    while Instant::now() < deadline {
+        if let Ok(c) = std::fs::read_to_string(&path) {
+            let count = c.lines().count();
+            if count > orig_len {
+                content2 = c;
+                new_len = count;
+                break;
+            }
+        }
+        std::thread::sleep(Duration::from_millis(50));
+    }
+    if content2.is_empty() {
+        // last attempt
+        content2 = std::fs::read_to_string(&path).unwrap();
+        new_len = content2.lines().count();
+    }
+    assert!(new_len > orig_len, "rollout file did not grow after resume");
+    assert!(content2.contains(&marker), "rollout lost original marker");
+    assert!(
+        content2.contains(&marker2),
+        "rollout missing resumed marker"
+    );
+}
+
+/// Integration test to verify git info is collected and recorded in session files.
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn integration_git_info_unit_test() {
+    // This test verifies git info collection works independently
+    // without depending on the full CLI integration
+
+    // 1. Create temp directory for git repo
+    let temp_dir = TempDir::new().unwrap();
+    let git_repo = temp_dir.path().to_path_buf();
+
+    // 2. Initialize a git repository with some content
+    let init_output = std::process::Command::new("git")
+        .args(["init"])
+        .current_dir(&git_repo)
+        .output()
+        .unwrap();
+    assert!(init_output.status.success(), "git init failed");
+
+    // Configure git user (required for commits)
+    std::process::Command::new("git")
+        .args(["config", "user.name", "Integration Test"])
+        .current_dir(&git_repo)
+        .output()
+        .unwrap();
+
+    std::process::Command::new("git")
+        .args(["config", "user.email", "test@example.com"])
+        .current_dir(&git_repo)
+        .output()
+        .unwrap();
+
+    // Create a test file and commit it
+    let test_file = git_repo.join("test.txt");
+    std::fs::write(&test_file, "integration test content").unwrap();
+
+    std::process::Command::new("git")
+        .args(["add", "."])
+        .current_dir(&git_repo)
+        .output()
+        .unwrap();
+
+    let commit_output = std::process::Command::new("git")
+        .args(["commit", "-m", "Integration test commit"])
+        .current_dir(&git_repo)
+        .output()
+        .unwrap();
+    assert!(commit_output.status.success(), "git commit failed");
+
+    // Create a branch to test branch detection
+    std::process::Command::new("git")
+        .args(["checkout", "-b", "integration-test-branch"])
+        .current_dir(&git_repo)
+        .output()
+        .unwrap();
+
+    // Add a remote to test repository URL detection
+    std::process::Command::new("git")
+        .args([
+            "remote",
+            "add",
+            "origin",
+            "https://github.com/example/integration-test.git",
+        ])
+        .current_dir(&git_repo)
+        .output()
+        .unwrap();
+
+    // 3. Test git info collection directly
+    let git_info = codex_core::git_info::collect_git_info(&git_repo).await;
+
+    // 4. Verify git info is present and contains expected data
+    assert!(git_info.is_some(), "Git info should be collected");
+
+    let git_info = git_info.unwrap();
+
+    // Check that we have a commit hash
+    assert!(
+        git_info.commit_hash.is_some(),
+        "Git info should contain commit_hash"
+    );
+    let commit_hash = git_info.commit_hash.as_ref().unwrap();
+    assert_eq!(commit_hash.len(), 40, "Commit hash should be 40 characters");
+    assert!(
+        commit_hash.chars().all(|c| c.is_ascii_hexdigit()),
+        "Commit hash should be hexadecimal"
+    );
+
+    // Check that we have the correct branch
+    assert!(git_info.branch.is_some(), "Git info should contain branch");
+    let branch = git_info.branch.as_ref().unwrap();
+    assert_eq!(
+        branch, "integration-test-branch",
+        "Branch should match what we created"
+    );
+
+    // Check that we have the repository URL
+    assert!(
+        git_info.repository_url.is_some(),
+        "Git info should contain repository_url"
+    );
+    let repo_url = git_info.repository_url.as_ref().unwrap();
+    assert_eq!(
+        repo_url, "https://github.com/example/integration-test.git",
+        "Repository URL should match what we configured"
+    );
+
+    println!("✅ Git info collection test passed!");
+    println!("   Commit: {commit_hash}");
+    println!("   Branch: {branch}");
+    println!("   Repo: {repo_url}");
+
+    // 5. Test serialization to ensure it works in SessionMeta
+    let serialized = serde_json::to_string(&git_info).unwrap();
+    let deserialized: codex_core::git_info::GitInfo = serde_json::from_str(&serialized).unwrap();
+
+    assert_eq!(git_info.commit_hash, deserialized.commit_hash);
+    assert_eq!(git_info.branch, deserialized.branch);
+    assert_eq!(git_info.repository_url, deserialized.repository_url);
+
+    println!("✅ Git info serialization test passed!");
+}

codex-rs/core/tests/client.rs

@@ -0,0 +1,174 @@
+use codex_core::Codex;
+use codex_core::CodexSpawnOk;
+use codex_core::ModelProviderInfo;
+use codex_core::exec::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
+use codex_core::protocol::EventMsg;
+use codex_core::protocol::InputItem;
+use codex_core::protocol::Op;
+use codex_core::protocol::SessionConfiguredEvent;
+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;
+
+/// Build minimal SSE stream with completed marker using the JSON fixture.
+fn sse_completed(id: &str) -> String {
+    load_sse_fixture_with_id("tests/fixtures/completed_template.json", id)
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn includes_session_id_and_model_headers_in_request() {
+    #![allow(clippy::unwrap_used)]
+
+    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;
+    }
+
+    // Mock server
+    let server = MockServer::start().await;
+
+    // First request – must NOT include `previous_response_id`.
+    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 {
+        name: "openai".into(),
+        base_url: format!("{}/v1", server.uri()),
+        // Environment variable that should exist in the test environment.
+        // ModelClient will return an error if the environment variable for the
+        // provider is not set.
+        env_key: Some("PATH".into()),
+        env_key_instructions: None,
+        wire_api: codex_core::WireApi::Responses,
+        query_params: None,
+        http_headers: Some(
+            [("originator".to_string(), "codex_cli_rs".to_string())]
+                .into_iter()
+                .collect(),
+        ),
+        env_http_headers: None,
+        request_max_retries: Some(0),
+        stream_max_retries: Some(0),
+        stream_idle_timeout_ms: None,
+    };
+
+    // Init session
+    let codex_home = TempDir::new().unwrap();
+    let mut config = load_default_config_for_test(&codex_home);
+    config.model_provider = model_provider;
+    let ctrl_c = std::sync::Arc::new(tokio::sync::Notify::new());
+    let CodexSpawnOk { codex, .. } = Codex::spawn(config, ctrl_c.clone()).await.unwrap();
+
+    codex
+        .submit(Op::UserInput {
+            items: vec![InputItem::Text {
+                text: "hello".into(),
+            }],
+        })
+        .await
+        .unwrap();
+
+    let EventMsg::SessionConfigured(SessionConfiguredEvent { session_id, .. }) =
+        wait_for_event(&codex, |ev| matches!(ev, EventMsg::SessionConfigured(_))).await
+    else {
+        unreachable!()
+    };
+
+    let current_session_id = Some(session_id.to_string());
+    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
+
+    // get request from the server
+    let request = &server.received_requests().await.unwrap()[0];
+    let request_body = request.headers.get("session_id").unwrap();
+    let originator = request.headers.get("originator").unwrap();
+
+    assert!(current_session_id.is_some());
+    assert_eq!(
+        request_body.to_str().unwrap(),
+        current_session_id.as_ref().unwrap()
+    );
+    assert_eq!(originator.to_str().unwrap(), "codex_cli_rs");
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn includes_base_instructions_override_in_request() {
+    #![allow(clippy::unwrap_used)]
+
+    // Mock server
+    let server = MockServer::start().await;
+
+    // First request – must NOT include `previous_response_id`.
+    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 {
+        name: "openai".into(),
+        base_url: format!("{}/v1", server.uri()),
+        // Environment variable that should exist in the test environment.
+        // ModelClient will return an error if the environment variable for the
+        // provider is not set.
+        env_key: Some("PATH".into()),
+        env_key_instructions: None,
+        wire_api: codex_core::WireApi::Responses,
+        query_params: None,
+        http_headers: None,
+        env_http_headers: None,
+        request_max_retries: Some(0),
+        stream_max_retries: Some(0),
+        stream_idle_timeout_ms: None,
+    };
+
+    let codex_home = TempDir::new().unwrap();
+    let mut config = load_default_config_for_test(&codex_home);
+
+    config.base_instructions = Some("test instructions".to_string());
+    config.model_provider = model_provider;
+
+    let ctrl_c = std::sync::Arc::new(tokio::sync::Notify::new());
+    let CodexSpawnOk { codex, .. } = Codex::spawn(config, 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_body = request.body_json::<serde_json::Value>().unwrap();
+
+    assert!(
+        request_body["instructions"]
+            .as_str()
+            .unwrap()
+            .contains("test instructions")
+    );
+}

codex-rs/core/tests/common/Cargo.toml

@@ -0,0 +1,13 @@
+[package]
+name = "core_test_support"
+version = { workspace = true }
+edition = "2024"
+
+[lib]
+path = "lib.rs"
+
+[dependencies]
+codex-core = { path = "../.." }
+serde_json = "1"
+tempfile = "3"
+tokio = { version = "1", features = ["time"] }

codex-rs/core/tests/common/lib.rs

@@ -1,9 +1,5 @@
 #![allow(clippy::expect_used)]
 
-// Helpers shared by the integration tests.  These are located inside the
-// `tests/` tree on purpose so they never become part of the public API surface
-// of the `codex-core` crate.
-
 use tempfile::TempDir;
 
 use codex_core::config::Config;
@@ -30,7 +26,6 @@ pub fn load_default_config_for_test(codex_home: &TempDir) -> Config {
 /// with only a `type` field results in an event with no `data:` section. This
 /// makes it trivial to extend the fixtures as OpenAI adds new event kinds or
 /// fields.
-#[allow(dead_code)]
 pub fn load_sse_fixture(path: impl AsRef<std::path::Path>) -> String {
     let events: Vec<serde_json::Value> =
         serde_json::from_reader(std::fs::File::open(path).expect("read fixture"))
@@ -55,7 +50,6 @@ pub fn load_sse_fixture(path: impl AsRef<std::path::Path>) -> String {
 /// fixture template with the supplied identifier before parsing. This lets a
 /// single JSON template be reused by multiple tests that each need a unique
 /// `response_id`.
-#[allow(dead_code)]
 pub fn load_sse_fixture_with_id(path: impl AsRef<std::path::Path>, id: &str) -> String {
     let raw = std::fs::read_to_string(path).expect("read fixture template");
     let replaced = raw.replace("__ID__", id);
@@ -76,3 +70,23 @@ pub fn load_sse_fixture_with_id(path: impl AsRef<std::path::Path>, id: &str) ->
         })
         .collect()
 }
+
+pub async fn wait_for_event<F>(
+    codex: &codex_core::Codex,
+    mut predicate: F,
+) -> codex_core::protocol::EventMsg
+where
+    F: FnMut(&codex_core::protocol::EventMsg) -> bool,
+{
+    use tokio::time::Duration;
+    use tokio::time::timeout;
+    loop {
+        let ev = timeout(Duration::from_secs(1), codex.next_event())
+            .await
+            .expect("timeout waiting for event")
+            .expect("stream ended unexpectedly");
+        if predicate(&ev.msg) {
+            return ev.msg;
+        }
+    }
+}

codex-rs/core/tests/live_agent.rs

@@ -20,15 +20,15 @@
 use std::time::Duration;
 
 use codex_core::Codex;
+use codex_core::CodexSpawnOk;
 use codex_core::error::CodexErr;
 use codex_core::protocol::AgentMessageEvent;
 use codex_core::protocol::ErrorEvent;
 use codex_core::protocol::EventMsg;
 use codex_core::protocol::InputItem;
 use codex_core::protocol::Op;
-mod test_support;
+use core_test_support::load_default_config_for_test;
 use tempfile::TempDir;
-use test_support::load_default_config_for_test;
 use tokio::sync::Notify;
 use tokio::time::timeout;
 
@@ -45,23 +45,12 @@ async fn spawn_codex() -> Result<Codex, CodexErr> {
         "OPENAI_API_KEY must be set for live tests"
     );
 
-    // Environment tweaks to keep the tests snappy and inexpensive while still
-    // exercising retry/robustness logic.
-    //
-    // NOTE: Starting with the 2024 edition `std::env::set_var` is `unsafe`
-    // because changing the process environment races with any other threads
-    // that might be performing environment look-ups at the same time.
-    // Restrict the unsafety to this tiny block that happens at the very
-    // beginning of the test, before we spawn any background tasks that could
-    // observe the environment.
-    unsafe {
-        std::env::set_var("OPENAI_REQUEST_MAX_RETRIES", "2");
-        std::env::set_var("OPENAI_STREAM_MAX_RETRIES", "2");
-    }
-
     let codex_home = TempDir::new().unwrap();
-    let config = load_default_config_for_test(&codex_home);
-    let (agent, _init_id) = Codex::spawn(config, std::sync::Arc::new(Notify::new())).await?;
+    let mut config = load_default_config_for_test(&codex_home);
+    config.model_provider.request_max_retries = Some(2);
+    config.model_provider.stream_max_retries = Some(2);
+    let CodexSpawnOk { codex: agent, .. } =
+        Codex::spawn(config, std::sync::Arc::new(Notify::new())).await?;
 
     Ok(agent)
 }
@@ -79,7 +68,7 @@ async fn live_streaming_and_prev_id_reset() {
 
     let codex = spawn_codex().await.unwrap();
 
-    // ---------- Task 1 ----------
+    // ---------- Task 1 ----------
     codex
         .submit(Op::UserInput {
             items: vec![InputItem::Text {
@@ -113,7 +102,7 @@ async fn live_streaming_and_prev_id_reset() {
         "Agent did not stream any AgentMessage before TaskComplete"
     );
 
-    // ---------- Task 2 (same session) ----------
+    // ---------- Task 2 (same session) ----------
     codex
         .submit(Op::UserInput {
             items: vec![InputItem::Text {

codex-rs/core/tests/previous_response_id.rs

@@ -1,166 +0,0 @@
-use std::time::Duration;
-
-use codex_core::Codex;
-use codex_core::ModelProviderInfo;
-use codex_core::exec::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
-use codex_core::protocol::ErrorEvent;
-use codex_core::protocol::EventMsg;
-use codex_core::protocol::InputItem;
-use codex_core::protocol::Op;
-mod test_support;
-use serde_json::Value;
-use tempfile::TempDir;
-use test_support::load_default_config_for_test;
-use test_support::load_sse_fixture_with_id;
-use tokio::time::timeout;
-use wiremock::Match;
-use wiremock::Mock;
-use wiremock::MockServer;
-use wiremock::Request;
-use wiremock::ResponseTemplate;
-use wiremock::matchers::method;
-use wiremock::matchers::path;
-
-/// Matcher asserting that JSON body has NO `previous_response_id` field.
-struct NoPrevId;
-
-impl Match for NoPrevId {
-    fn matches(&self, req: &Request) -> bool {
-        serde_json::from_slice::<Value>(&req.body)
-            .map(|v| v.get("previous_response_id").is_none())
-            .unwrap_or(false)
-    }
-}
-
-/// Matcher asserting that JSON body HAS a `previous_response_id` field.
-struct HasPrevId;
-
-impl Match for HasPrevId {
-    fn matches(&self, req: &Request) -> bool {
-        serde_json::from_slice::<Value>(&req.body)
-            .map(|v| v.get("previous_response_id").is_some())
-            .unwrap_or(false)
-    }
-}
-
-/// Build minimal SSE stream with completed marker using the JSON fixture.
-fn sse_completed(id: &str) -> String {
-    load_sse_fixture_with_id("tests/fixtures/completed_template.json", id)
-}
-
-#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-async fn keeps_previous_response_id_between_tasks() {
-    #![allow(clippy::unwrap_used)]
-
-    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;
-    }
-
-    // Mock server
-    let server = MockServer::start().await;
-
-    // First request – must NOT include `previous_response_id`.
-    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"))
-        .and(NoPrevId)
-        .respond_with(first)
-        .expect(1)
-        .mount(&server)
-        .await;
-
-    // Second request – MUST include `previous_response_id`.
-    let second = ResponseTemplate::new(200)
-        .insert_header("content-type", "text/event-stream")
-        .set_body_raw(sse_completed("resp2"), "text/event-stream");
-
-    Mock::given(method("POST"))
-        .and(path("/v1/responses"))
-        .and(HasPrevId)
-        .respond_with(second)
-        .expect(1)
-        .mount(&server)
-        .await;
-
-    // Environment
-    // Update environment – `set_var` is `unsafe` starting with the 2024
-    // edition so we group the calls into a single `unsafe { … }` block.
-    unsafe {
-        std::env::set_var("OPENAI_REQUEST_MAX_RETRIES", "0");
-        std::env::set_var("OPENAI_STREAM_MAX_RETRIES", "0");
-    }
-    let model_provider = ModelProviderInfo {
-        name: "openai".into(),
-        base_url: format!("{}/v1", server.uri()),
-        // Environment variable that should exist in the test environment.
-        // ModelClient will return an error if the environment variable for the
-        // provider is not set.
-        env_key: Some("PATH".into()),
-        env_key_instructions: None,
-        wire_api: codex_core::WireApi::Responses,
-        query_params: None,
-        http_headers: None,
-        env_http_headers: None,
-    };
-
-    // Init session
-    let codex_home = TempDir::new().unwrap();
-    let mut config = load_default_config_for_test(&codex_home);
-    config.model_provider = model_provider;
-    let ctrl_c = std::sync::Arc::new(tokio::sync::Notify::new());
-    let (codex, _init_id) = Codex::spawn(config, ctrl_c.clone()).await.unwrap();
-
-    // Task 1 – triggers first request (no previous_response_id)
-    codex
-        .submit(Op::UserInput {
-            items: vec![InputItem::Text {
-                text: "hello".into(),
-            }],
-        })
-        .await
-        .unwrap();
-
-    // Wait for TaskComplete
-    loop {
-        let ev = timeout(Duration::from_secs(1), codex.next_event())
-            .await
-            .unwrap()
-            .unwrap();
-        if matches!(ev.msg, EventMsg::TaskComplete(_)) {
-            break;
-        }
-    }
-
-    // Task 2 – should include `previous_response_id` (triggers second request)
-    codex
-        .submit(Op::UserInput {
-            items: vec![InputItem::Text {
-                text: "again".into(),
-            }],
-        })
-        .await
-        .unwrap();
-
-    // Wait for TaskComplete or error
-    loop {
-        let ev = timeout(Duration::from_secs(1), codex.next_event())
-            .await
-            .unwrap()
-            .unwrap();
-        match ev.msg {
-            EventMsg::TaskComplete(_) => break,
-            EventMsg::Error(ErrorEvent { message }) => {
-                panic!("unexpected error: {message}")
-            }
-            _ => {
-                // Ignore other events.
-            }
-        }
-    }
-}

codex-rs/core/tests/stream_no_completed.rs

@@ -4,16 +4,16 @@
 use std::time::Duration;
 
 use codex_core::Codex;
+use codex_core::CodexSpawnOk;
 use codex_core::ModelProviderInfo;
 use codex_core::exec::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
 use codex_core::protocol::EventMsg;
 use codex_core::protocol::InputItem;
 use codex_core::protocol::Op;
-mod test_support;
+use core_test_support::load_default_config_for_test;
+use core_test_support::load_sse_fixture;
+use core_test_support::load_sse_fixture_with_id;
 use tempfile::TempDir;
-use test_support::load_default_config_for_test;
-use test_support::load_sse_fixture;
-use test_support::load_sse_fixture_with_id;
 use tokio::time::timeout;
 use wiremock::Mock;
 use wiremock::MockServer;
@@ -70,19 +70,8 @@ async fn retries_on_early_close() {
         .mount(&server)
         .await;
 
-    // Environment
-    //
-    // As of Rust 2024 `std::env::set_var` has been made `unsafe` because
-    // mutating the process environment is inherently racy when other threads
-    // are running.  We therefore have to wrap every call in an explicit
-    // `unsafe` block.  These are limited to the test-setup section so the
-    // scope is very small and clearly delineated.
-
-    unsafe {
-        std::env::set_var("OPENAI_REQUEST_MAX_RETRIES", "0");
-        std::env::set_var("OPENAI_STREAM_MAX_RETRIES", "1");
-        std::env::set_var("OPENAI_STREAM_IDLE_TIMEOUT_MS", "2000");
-    }
+    // Configure retry behavior explicitly to avoid mutating process-wide
+    // environment variables.
 
     let model_provider = ModelProviderInfo {
         name: "openai".into(),
@@ -96,13 +85,17 @@ async fn retries_on_early_close() {
         query_params: None,
         http_headers: None,
         env_http_headers: None,
+        // exercise retry path: first attempt yields incomplete stream, so allow 1 retry
+        request_max_retries: Some(0),
+        stream_max_retries: Some(1),
+        stream_idle_timeout_ms: Some(2000),
     };
 
     let ctrl_c = std::sync::Arc::new(tokio::sync::Notify::new());
     let codex_home = TempDir::new().unwrap();
     let mut config = load_default_config_for_test(&codex_home);
     config.model_provider = model_provider;
-    let (codex, _init_id) = Codex::spawn(config, ctrl_c).await.unwrap();
+    let CodexSpawnOk { codex, .. } = Codex::spawn(config, ctrl_c).await.unwrap();
 
     codex
         .submit(Op::UserInput {

codex-rs/exec/Cargo.toml

@@ -18,13 +18,13 @@ workspace = true
 anyhow = "1"
 chrono = "0.4.40"
 clap = { version = "4", features = ["derive"] }
+codex-arg0 = { path = "../arg0" }
 codex-core = { path = "../core" }
 codex-common = { path = "../common", features = [
     "cli",
     "elapsed",
     "sandbox_summary",
 ] }
-codex-linux-sandbox = { path = "../linux-sandbox" }
 owo-colors = "4.2.0"
 serde_json = "1"
 shlex = "1.3.0"
@@ -37,3 +37,8 @@ tokio = { version = "1", features = [
 ] }
 tracing = { version = "0.1.41", features = ["log"] }
 tracing-subscriber = { version = "0.3.19", features = ["env-filter"] }
+
+[dev-dependencies]
+assert_cmd = "2"
+predicates = "3"
+tempfile = "3.13.0"

codex-rs/exec/src/cli.rs

@@ -51,6 +51,10 @@ pub struct Cli {
     #[arg(long = "color", value_enum, default_value_t = Color::Auto)]
     pub color: Color,
 
+    /// Print events to stdout as JSONL.
+    #[arg(long = "json", default_value_t = false)]
+    pub json: bool,
+
     /// Specifies file where the last message from the agent should be written.
     #[arg(long = "output-last-message")]
     pub last_message_file: Option<PathBuf>,

codex-rs/exec/src/event_processor.rs

@@ -1,492 +1,70 @@
-use codex_common::elapsed::format_elapsed;
+use std::path::Path;
+
 use codex_common::summarize_sandbox_policy;
 use codex_core::WireApi;
 use codex_core::config::Config;
 use codex_core::model_supports_reasoning_summaries;
-use codex_core::protocol::AgentMessageEvent;
-use codex_core::protocol::BackgroundEventEvent;
-use codex_core::protocol::ErrorEvent;
 use codex_core::protocol::Event;
-use codex_core::protocol::EventMsg;
-use codex_core::protocol::ExecCommandBeginEvent;
-use codex_core::protocol::ExecCommandEndEvent;
-use codex_core::protocol::FileChange;
-use codex_core::protocol::McpToolCallBeginEvent;
-use codex_core::protocol::McpToolCallEndEvent;
-use codex_core::protocol::PatchApplyBeginEvent;
-use codex_core::protocol::PatchApplyEndEvent;
-use codex_core::protocol::SessionConfiguredEvent;
-use codex_core::protocol::TokenUsage;
-use owo_colors::OwoColorize;
-use owo_colors::Style;
-use shlex::try_join;
-use std::collections::HashMap;
-use std::time::Instant;
 
-/// This should be configurable. When used in CI, users may not want to impose
-/// a limit so they can see the full transcript.
-const MAX_OUTPUT_LINES_FOR_EXEC_TOOL_CALL: usize = 20;
-
-pub(crate) struct EventProcessor {
-    call_id_to_command: HashMap<String, ExecCommandBegin>,
-    call_id_to_patch: HashMap<String, PatchApplyBegin>,
-
-    /// Tracks in-flight MCP tool calls so we can calculate duration and print
-    /// a concise summary when the corresponding `McpToolCallEnd` event is
-    /// received.
-    call_id_to_tool_call: HashMap<String, McpToolCallBegin>,
-
-    // To ensure that --color=never is respected, ANSI escapes _must_ be added
-    // using .style() with one of these fields. If you need a new style, add a
-    // new field here.
-    bold: Style,
-    italic: Style,
-    dimmed: Style,
-
-    magenta: Style,
-    red: Style,
-    green: Style,
-    cyan: Style,
-
-    /// Whether to include `AgentReasoning` events in the output.
-    show_agent_reasoning: bool,
+pub(crate) enum CodexStatus {
+    Running,
+    InitiateShutdown,
+    Shutdown,
 }
 
-impl EventProcessor {
-    pub(crate) fn create_with_ansi(with_ansi: bool, show_agent_reasoning: bool) -> Self {
-        let call_id_to_command = HashMap::new();
-        let call_id_to_patch = HashMap::new();
-        let call_id_to_tool_call = HashMap::new();
+pub(crate) trait EventProcessor {
+    /// Print summary of effective configuration and user prompt.
+    fn print_config_summary(&mut self, config: &Config, prompt: &str);
 
-        if with_ansi {
-            Self {
-                call_id_to_command,
-                call_id_to_patch,
-                bold: Style::new().bold(),
-                italic: Style::new().italic(),
-                dimmed: Style::new().dimmed(),
-                magenta: Style::new().magenta(),
-                red: Style::new().red(),
-                green: Style::new().green(),
-                cyan: Style::new().cyan(),
-                call_id_to_tool_call,
-                show_agent_reasoning,
-            }
-        } else {
-            Self {
-                call_id_to_command,
-                call_id_to_patch,
-                bold: Style::new(),
-                italic: Style::new(),
-                dimmed: Style::new(),
-                magenta: Style::new(),
-                red: Style::new(),
-                green: Style::new(),
-                cyan: Style::new(),
-                call_id_to_tool_call,
-                show_agent_reasoning,
-            }
+    /// Handle a single event emitted by the agent.
+    fn process_event(&mut self, event: Event) -> CodexStatus;
+}
+
+pub(crate) fn create_config_summary_entries(config: &Config) -> Vec<(&'static str, String)> {
+    let mut entries = vec![
+        ("workdir", config.cwd.display().to_string()),
+        ("model", config.model.clone()),
+        ("provider", config.model_provider_id.clone()),
+        ("approval", config.approval_policy.to_string()),
+        ("sandbox", summarize_sandbox_policy(&config.sandbox_policy)),
+    ];
+    if config.model_provider.wire_api == WireApi::Responses
+        && model_supports_reasoning_summaries(config)
+    {
+        entries.push((
+            "reasoning effort",
+            config.model_reasoning_effort.to_string(),
+        ));
+        entries.push((
+            "reasoning summaries",
+            config.model_reasoning_summary.to_string(),
+        ));
+    }
+
+    entries
+}
+
+pub(crate) fn handle_last_message(
+    last_agent_message: Option<&str>,
+    last_message_path: Option<&Path>,
+) {
+    match (last_message_path, last_agent_message) {
+        (Some(path), Some(msg)) => write_last_message_file(msg, Some(path)),
+        (Some(path), None) => {
+            write_last_message_file("", Some(path));
+            eprintln!(
+                "Warning: no last agent message; wrote empty content to {}",
+                path.display()
+            );
         }
+        (None, _) => eprintln!("Warning: no file to write last message to."),
     }
 }
 
-struct ExecCommandBegin {
-    command: Vec<String>,
-    start_time: Instant,
-}
-
-/// Metadata captured when an `McpToolCallBegin` event is received.
-struct McpToolCallBegin {
-    /// Formatted invocation string, e.g. `server.tool({"city":"sf"})`.
-    invocation: String,
-    /// Timestamp when the call started so we can compute duration later.
-    start_time: Instant,
-}
-
-struct PatchApplyBegin {
-    start_time: Instant,
-    auto_approved: bool,
-}
-
-// Timestamped println helper. The timestamp is styled with self.dimmed.
-#[macro_export]
-macro_rules! ts_println {
-    ($self:ident, $($arg:tt)*) => {{
-        let now = chrono::Utc::now();
-        let formatted = now.format("[%Y-%m-%dT%H:%M:%S]");
-        print!("{} ", formatted.style($self.dimmed));
-        println!($($arg)*);
-    }};
-}
-
-impl EventProcessor {
-    /// Print a concise summary of the effective configuration that will be used
-    /// for the session. This mirrors the information shown in the TUI welcome
-    /// screen.
-    pub(crate) fn print_config_summary(&mut self, config: &Config, prompt: &str) {
-        const VERSION: &str = env!("CARGO_PKG_VERSION");
-        ts_println!(
-            self,
-            "OpenAI Codex v{} (research preview)\n--------",
-            VERSION
-        );
-
-        let mut entries = vec![
-            ("workdir", config.cwd.display().to_string()),
-            ("model", config.model.clone()),
-            ("provider", config.model_provider_id.clone()),
-            ("approval", format!("{:?}", config.approval_policy)),
-            ("sandbox", summarize_sandbox_policy(&config.sandbox_policy)),
-        ];
-        if config.model_provider.wire_api == WireApi::Responses
-            && model_supports_reasoning_summaries(config)
-        {
-            entries.push((
-                "reasoning effort",
-                config.model_reasoning_effort.to_string(),
-            ));
-            entries.push((
-                "reasoning summaries",
-                config.model_reasoning_summary.to_string(),
-            ));
-        }
-
-        for (key, value) in entries {
-            println!("{} {}", format!("{key}:").style(self.bold), value);
-        }
-
-        println!("--------");
-
-        // Echo the prompt that will be sent to the agent so it is visible in the
-        // transcript/logs before any events come in. Note the prompt may have been
-        // read from stdin, so it may not be visible in the terminal otherwise.
-        ts_println!(
-            self,
-            "{}\n{}",
-            "User instructions:".style(self.bold).style(self.cyan),
-            prompt
-        );
-    }
-
-    pub(crate) fn process_event(&mut self, event: Event) {
-        let Event { id: _, msg } = event;
-        match msg {
-            EventMsg::Error(ErrorEvent { message }) => {
-                let prefix = "ERROR:".style(self.red);
-                ts_println!(self, "{prefix} {message}");
-            }
-            EventMsg::BackgroundEvent(BackgroundEventEvent { message }) => {
-                ts_println!(self, "{}", message.style(self.dimmed));
-            }
-            EventMsg::TaskStarted | EventMsg::TaskComplete(_) => {
-                // Ignore.
-            }
-            EventMsg::TokenCount(TokenUsage { total_tokens, .. }) => {
-                ts_println!(self, "tokens used: {total_tokens}");
-            }
-            EventMsg::AgentMessage(AgentMessageEvent { message }) => {
-                ts_println!(
-                    self,
-                    "{}\n{message}",
-                    "codex".style(self.bold).style(self.magenta)
-                );
-            }
-            EventMsg::ExecCommandBegin(ExecCommandBeginEvent {
-                call_id,
-                command,
-                cwd,
-            }) => {
-                self.call_id_to_command.insert(
-                    call_id.clone(),
-                    ExecCommandBegin {
-                        command: command.clone(),
-                        start_time: Instant::now(),
-                    },
-                );
-                ts_println!(
-                    self,
-                    "{} {} in {}",
-                    "exec".style(self.magenta),
-                    escape_command(&command).style(self.bold),
-                    cwd.to_string_lossy(),
-                );
-            }
-            EventMsg::ExecCommandEnd(ExecCommandEndEvent {
-                call_id,
-                stdout,
-                stderr,
-                exit_code,
-            }) => {
-                let exec_command = self.call_id_to_command.remove(&call_id);
-                let (duration, call) = if let Some(ExecCommandBegin {
-                    command,
-                    start_time,
-                }) = exec_command
-                {
-                    (
-                        format!(" in {}", format_elapsed(start_time)),
-                        format!("{}", escape_command(&command).style(self.bold)),
-                    )
-                } else {
-                    ("".to_string(), format!("exec('{call_id}')"))
-                };
-
-                let output = if exit_code == 0 { stdout } else { stderr };
-                let truncated_output = output
-                    .lines()
-                    .take(MAX_OUTPUT_LINES_FOR_EXEC_TOOL_CALL)
-                    .collect::<Vec<_>>()
-                    .join("\n");
-                match exit_code {
-                    0 => {
-                        let title = format!("{call} succeeded{duration}:");
-                        ts_println!(self, "{}", title.style(self.green));
-                    }
-                    _ => {
-                        let title = format!("{call} exited {exit_code}{duration}:");
-                        ts_println!(self, "{}", title.style(self.red));
-                    }
-                }
-                println!("{}", truncated_output.style(self.dimmed));
-            }
-            EventMsg::McpToolCallBegin(McpToolCallBeginEvent {
-                call_id,
-                server,
-                tool,
-                arguments,
-            }) => {
-                // Build fully-qualified tool name: server.tool
-                let fq_tool_name = format!("{server}.{tool}");
-
-                // Format arguments as compact JSON so they fit on one line.
-                let args_str = arguments
-                    .as_ref()
-                    .map(|v: &serde_json::Value| {
-                        serde_json::to_string(v).unwrap_or_else(|_| v.to_string())
-                    })
-                    .unwrap_or_default();
-
-                let invocation = if args_str.is_empty() {
-                    format!("{fq_tool_name}()")
-                } else {
-                    format!("{fq_tool_name}({args_str})")
-                };
-
-                self.call_id_to_tool_call.insert(
-                    call_id.clone(),
-                    McpToolCallBegin {
-                        invocation: invocation.clone(),
-                        start_time: Instant::now(),
-                    },
-                );
-
-                ts_println!(
-                    self,
-                    "{} {}",
-                    "tool".style(self.magenta),
-                    invocation.style(self.bold),
-                );
-            }
-            EventMsg::McpToolCallEnd(tool_call_end_event) => {
-                let is_success = tool_call_end_event.is_success();
-                let McpToolCallEndEvent { call_id, result } = tool_call_end_event;
-                // Retrieve start time and invocation for duration calculation and labeling.
-                let info = self.call_id_to_tool_call.remove(&call_id);
-
-                let (duration, invocation) = if let Some(McpToolCallBegin {
-                    invocation,
-                    start_time,
-                    ..
-                }) = info
-                {
-                    (format!(" in {}", format_elapsed(start_time)), invocation)
-                } else {
-                    (String::new(), format!("tool('{call_id}')"))
-                };
-
-                let status_str = if is_success { "success" } else { "failed" };
-                let title_style = if is_success { self.green } else { self.red };
-                let title = format!("{invocation} {status_str}{duration}:");
-
-                ts_println!(self, "{}", title.style(title_style));
-
-                if let Ok(res) = result {
-                    let val: serde_json::Value = res.into();
-                    let pretty =
-                        serde_json::to_string_pretty(&val).unwrap_or_else(|_| val.to_string());
-
-                    for line in pretty.lines().take(MAX_OUTPUT_LINES_FOR_EXEC_TOOL_CALL) {
-                        println!("{}", line.style(self.dimmed));
-                    }
-                }
-            }
-            EventMsg::PatchApplyBegin(PatchApplyBeginEvent {
-                call_id,
-                auto_approved,
-                changes,
-            }) => {
-                // Store metadata so we can calculate duration later when we
-                // receive the corresponding PatchApplyEnd event.
-                self.call_id_to_patch.insert(
-                    call_id.clone(),
-                    PatchApplyBegin {
-                        start_time: Instant::now(),
-                        auto_approved,
-                    },
-                );
-
-                ts_println!(
-                    self,
-                    "{} auto_approved={}:",
-                    "apply_patch".style(self.magenta),
-                    auto_approved,
-                );
-
-                // Pretty-print the patch summary with colored diff markers so
-                // it’s easy to scan in the terminal output.
-                for (path, change) in changes.iter() {
-                    match change {
-                        FileChange::Add { content } => {
-                            let header = format!(
-                                "{} {}",
-                                format_file_change(change),
-                                path.to_string_lossy()
-                            );
-                            println!("{}", header.style(self.magenta));
-                            for line in content.lines() {
-                                println!("{}", line.style(self.green));
-                            }
-                        }
-                        FileChange::Delete => {
-                            let header = format!(
-                                "{} {}",
-                                format_file_change(change),
-                                path.to_string_lossy()
-                            );
-                            println!("{}", header.style(self.magenta));
-                        }
-                        FileChange::Update {
-                            unified_diff,
-                            move_path,
-                        } => {
-                            let header = if let Some(dest) = move_path {
-                                format!(
-                                    "{} {} -> {}",
-                                    format_file_change(change),
-                                    path.to_string_lossy(),
-                                    dest.to_string_lossy()
-                                )
-                            } else {
-                                format!("{} {}", format_file_change(change), path.to_string_lossy())
-                            };
-                            println!("{}", header.style(self.magenta));
-
-                            // Colorize diff lines. We keep file header lines
-                            // (--- / +++) without extra coloring so they are
-                            // still readable.
-                            for diff_line in unified_diff.lines() {
-                                if diff_line.starts_with('+') && !diff_line.starts_with("+++") {
-                                    println!("{}", diff_line.style(self.green));
-                                } else if diff_line.starts_with('-')
-                                    && !diff_line.starts_with("---")
-                                {
-                                    println!("{}", diff_line.style(self.red));
-                                } else {
-                                    println!("{diff_line}");
-                                }
-                            }
-                        }
-                    }
-                }
-            }
-            EventMsg::PatchApplyEnd(PatchApplyEndEvent {
-                call_id,
-                stdout,
-                stderr,
-                success,
-            }) => {
-                let patch_begin = self.call_id_to_patch.remove(&call_id);
-
-                // Compute duration and summary label similar to exec commands.
-                let (duration, label) = if let Some(PatchApplyBegin {
-                    start_time,
-                    auto_approved,
-                }) = patch_begin
-                {
-                    (
-                        format!(" in {}", format_elapsed(start_time)),
-                        format!("apply_patch(auto_approved={auto_approved})"),
-                    )
-                } else {
-                    (String::new(), format!("apply_patch('{call_id}')"))
-                };
-
-                let (exit_code, output, title_style) = if success {
-                    (0, stdout, self.green)
-                } else {
-                    (1, stderr, self.red)
-                };
-
-                let title = format!("{label} exited {exit_code}{duration}:");
-                ts_println!(self, "{}", title.style(title_style));
-                for line in output.lines() {
-                    println!("{}", line.style(self.dimmed));
-                }
-            }
-            EventMsg::ExecApprovalRequest(_) => {
-                // Should we exit?
-            }
-            EventMsg::ApplyPatchApprovalRequest(_) => {
-                // Should we exit?
-            }
-            EventMsg::AgentReasoning(agent_reasoning_event) => {
-                if self.show_agent_reasoning {
-                    ts_println!(
-                        self,
-                        "{}\n{}",
-                        "thinking".style(self.italic).style(self.magenta),
-                        agent_reasoning_event.text
-                    );
-                }
-            }
-            EventMsg::SessionConfigured(session_configured_event) => {
-                let SessionConfiguredEvent {
-                    session_id,
-                    model,
-                    history_log_id: _,
-                    history_entry_count: _,
-                } = session_configured_event;
-
-                ts_println!(
-                    self,
-                    "{} {}",
-                    "codex session".style(self.magenta).style(self.bold),
-                    session_id.to_string().style(self.dimmed)
-                );
-
-                ts_println!(self, "model: {}", model);
-                println!();
-            }
-            EventMsg::GetHistoryEntryResponse(_) => {
-                // Currently ignored in exec output.
-            }
+fn write_last_message_file(contents: &str, last_message_path: Option<&Path>) {
+    if let Some(path) = last_message_path {
+        if let Err(e) = std::fs::write(path, contents) {
+            eprintln!("Failed to write last message file {path:?}: {e}");
         }
     }
 }
-
-fn escape_command(command: &[String]) -> String {
-    try_join(command.iter().map(|s| s.as_str())).unwrap_or_else(|_| command.join(" "))
-}
-
-fn format_file_change(change: &FileChange) -> &'static str {
-    match change {
-        FileChange::Add { .. } => "A",
-        FileChange::Delete => "D",
-        FileChange::Update {
-            move_path: Some(_), ..
-        } => "R",
-        FileChange::Update {
-            move_path: None, ..
-        } => "M",
-    }
-}

codex-rs/exec/src/event_processor_with_human_output.rs

@@ -0,0 +1,540 @@
+use codex_common::elapsed::format_elapsed;
+use codex_core::config::Config;
+use codex_core::protocol::AgentMessageDeltaEvent;
+use codex_core::protocol::AgentMessageEvent;
+use codex_core::protocol::AgentReasoningDeltaEvent;
+use codex_core::protocol::BackgroundEventEvent;
+use codex_core::protocol::ErrorEvent;
+use codex_core::protocol::Event;
+use codex_core::protocol::EventMsg;
+use codex_core::protocol::ExecCommandBeginEvent;
+use codex_core::protocol::ExecCommandEndEvent;
+use codex_core::protocol::FileChange;
+use codex_core::protocol::McpToolCallBeginEvent;
+use codex_core::protocol::McpToolCallEndEvent;
+use codex_core::protocol::PatchApplyBeginEvent;
+use codex_core::protocol::PatchApplyEndEvent;
+use codex_core::protocol::SessionConfiguredEvent;
+use codex_core::protocol::TaskCompleteEvent;
+use codex_core::protocol::TokenUsage;
+use owo_colors::OwoColorize;
+use owo_colors::Style;
+use shlex::try_join;
+use std::collections::HashMap;
+use std::io::Write;
+use std::path::PathBuf;
+use std::time::Instant;
+
+use crate::event_processor::CodexStatus;
+use crate::event_processor::EventProcessor;
+use crate::event_processor::create_config_summary_entries;
+use crate::event_processor::handle_last_message;
+
+/// This should be configurable. When used in CI, users may not want to impose
+/// a limit so they can see the full transcript.
+const MAX_OUTPUT_LINES_FOR_EXEC_TOOL_CALL: usize = 20;
+pub(crate) struct EventProcessorWithHumanOutput {
+    call_id_to_command: HashMap<String, ExecCommandBegin>,
+    call_id_to_patch: HashMap<String, PatchApplyBegin>,
+
+    /// Tracks in-flight MCP tool calls so we can calculate duration and print
+    /// a concise summary when the corresponding `McpToolCallEnd` event is
+    /// received.
+    call_id_to_tool_call: HashMap<String, McpToolCallBegin>,
+
+    // To ensure that --color=never is respected, ANSI escapes _must_ be added
+    // using .style() with one of these fields. If you need a new style, add a
+    // new field here.
+    bold: Style,
+    italic: Style,
+    dimmed: Style,
+
+    magenta: Style,
+    red: Style,
+    green: Style,
+    cyan: Style,
+
+    /// Whether to include `AgentReasoning` events in the output.
+    show_agent_reasoning: bool,
+    answer_started: bool,
+    reasoning_started: bool,
+    last_message_path: Option<PathBuf>,
+}
+
+impl EventProcessorWithHumanOutput {
+    pub(crate) fn create_with_ansi(
+        with_ansi: bool,
+        config: &Config,
+        last_message_path: Option<PathBuf>,
+    ) -> Self {
+        let call_id_to_command = HashMap::new();
+        let call_id_to_patch = HashMap::new();
+        let call_id_to_tool_call = HashMap::new();
+
+        if with_ansi {
+            Self {
+                call_id_to_command,
+                call_id_to_patch,
+                bold: Style::new().bold(),
+                italic: Style::new().italic(),
+                dimmed: Style::new().dimmed(),
+                magenta: Style::new().magenta(),
+                red: Style::new().red(),
+                green: Style::new().green(),
+                cyan: Style::new().cyan(),
+                call_id_to_tool_call,
+                show_agent_reasoning: !config.hide_agent_reasoning,
+                answer_started: false,
+                reasoning_started: false,
+                last_message_path,
+            }
+        } else {
+            Self {
+                call_id_to_command,
+                call_id_to_patch,
+                bold: Style::new(),
+                italic: Style::new(),
+                dimmed: Style::new(),
+                magenta: Style::new(),
+                red: Style::new(),
+                green: Style::new(),
+                cyan: Style::new(),
+                call_id_to_tool_call,
+                show_agent_reasoning: !config.hide_agent_reasoning,
+                answer_started: false,
+                reasoning_started: false,
+                last_message_path,
+            }
+        }
+    }
+}
+
+struct ExecCommandBegin {
+    command: Vec<String>,
+    start_time: Instant,
+}
+
+/// Metadata captured when an `McpToolCallBegin` event is received.
+struct McpToolCallBegin {
+    /// Formatted invocation string, e.g. `server.tool({"city":"sf"})`.
+    invocation: String,
+    /// Timestamp when the call started so we can compute duration later.
+    start_time: Instant,
+}
+
+struct PatchApplyBegin {
+    start_time: Instant,
+    auto_approved: bool,
+}
+
+// Timestamped println helper. The timestamp is styled with self.dimmed.
+#[macro_export]
+macro_rules! ts_println {
+    ($self:ident, $($arg:tt)*) => {{
+        let now = chrono::Utc::now();
+        let formatted = now.format("[%Y-%m-%dT%H:%M:%S]");
+        print!("{} ", formatted.style($self.dimmed));
+        println!($($arg)*);
+    }};
+}
+
+impl EventProcessor for EventProcessorWithHumanOutput {
+    /// Print a concise summary of the effective configuration that will be used
+    /// for the session. This mirrors the information shown in the TUI welcome
+    /// screen.
+    fn print_config_summary(&mut self, config: &Config, prompt: &str) {
+        const VERSION: &str = env!("CARGO_PKG_VERSION");
+        ts_println!(
+            self,
+            "OpenAI Codex v{} (research preview)\n--------",
+            VERSION
+        );
+
+        let entries = create_config_summary_entries(config);
+
+        for (key, value) in entries {
+            println!("{} {}", format!("{key}:").style(self.bold), value);
+        }
+
+        println!("--------");
+
+        // Echo the prompt that will be sent to the agent so it is visible in the
+        // transcript/logs before any events come in. Note the prompt may have been
+        // read from stdin, so it may not be visible in the terminal otherwise.
+        ts_println!(
+            self,
+            "{}\n{}",
+            "User instructions:".style(self.bold).style(self.cyan),
+            prompt
+        );
+    }
+
+    fn process_event(&mut self, event: Event) -> CodexStatus {
+        let Event { id: _, msg } = event;
+        match msg {
+            EventMsg::Error(ErrorEvent { message }) => {
+                let prefix = "ERROR:".style(self.red);
+                ts_println!(self, "{prefix} {message}");
+            }
+            EventMsg::BackgroundEvent(BackgroundEventEvent { message }) => {
+                ts_println!(self, "{}", message.style(self.dimmed));
+            }
+            EventMsg::TaskStarted => {
+                // Ignore.
+            }
+            EventMsg::TaskComplete(TaskCompleteEvent { last_agent_message }) => {
+                handle_last_message(
+                    last_agent_message.as_deref(),
+                    self.last_message_path.as_deref(),
+                );
+                return CodexStatus::InitiateShutdown;
+            }
+            EventMsg::TokenCount(TokenUsage { total_tokens, .. }) => {
+                ts_println!(self, "tokens used: {total_tokens}");
+            }
+            EventMsg::AgentMessageDelta(AgentMessageDeltaEvent { delta }) => {
+                if !self.answer_started {
+                    ts_println!(self, "{}\n", "codex".style(self.italic).style(self.magenta));
+                    self.answer_started = true;
+                }
+                print!("{delta}");
+                #[allow(clippy::expect_used)]
+                std::io::stdout().flush().expect("could not flush stdout");
+            }
+            EventMsg::AgentReasoningDelta(AgentReasoningDeltaEvent { delta }) => {
+                if !self.show_agent_reasoning {
+                    return CodexStatus::Running;
+                }
+                if !self.reasoning_started {
+                    ts_println!(
+                        self,
+                        "{}\n",
+                        "thinking".style(self.italic).style(self.magenta),
+                    );
+                    self.reasoning_started = true;
+                }
+                print!("{delta}");
+                #[allow(clippy::expect_used)]
+                std::io::stdout().flush().expect("could not flush stdout");
+            }
+            EventMsg::AgentMessage(AgentMessageEvent { message }) => {
+                // if answer_started is false, this means we haven't received any
+                // delta. Thus, we need to print the message as a new answer.
+                if !self.answer_started {
+                    ts_println!(
+                        self,
+                        "{}\n{}",
+                        "codex".style(self.italic).style(self.magenta),
+                        message,
+                    );
+                } else {
+                    println!();
+                    self.answer_started = false;
+                }
+            }
+            EventMsg::ExecCommandBegin(ExecCommandBeginEvent {
+                call_id,
+                command,
+                cwd,
+            }) => {
+                self.call_id_to_command.insert(
+                    call_id.clone(),
+                    ExecCommandBegin {
+                        command: command.clone(),
+                        start_time: Instant::now(),
+                    },
+                );
+                ts_println!(
+                    self,
+                    "{} {} in {}",
+                    "exec".style(self.magenta),
+                    escape_command(&command).style(self.bold),
+                    cwd.to_string_lossy(),
+                );
+            }
+            EventMsg::ExecCommandEnd(ExecCommandEndEvent {
+                call_id,
+                stdout,
+                stderr,
+                exit_code,
+            }) => {
+                let exec_command = self.call_id_to_command.remove(&call_id);
+                let (duration, call) = if let Some(ExecCommandBegin {
+                    command,
+                    start_time,
+                }) = exec_command
+                {
+                    (
+                        format!(" in {}", format_elapsed(start_time)),
+                        format!("{}", escape_command(&command).style(self.bold)),
+                    )
+                } else {
+                    ("".to_string(), format!("exec('{call_id}')"))
+                };
+
+                let output = if exit_code == 0 { stdout } else { stderr };
+                let truncated_output = output
+                    .lines()
+                    .take(MAX_OUTPUT_LINES_FOR_EXEC_TOOL_CALL)
+                    .collect::<Vec<_>>()
+                    .join("\n");
+                match exit_code {
+                    0 => {
+                        let title = format!("{call} succeeded{duration}:");
+                        ts_println!(self, "{}", title.style(self.green));
+                    }
+                    _ => {
+                        let title = format!("{call} exited {exit_code}{duration}:");
+                        ts_println!(self, "{}", title.style(self.red));
+                    }
+                }
+                println!("{}", truncated_output.style(self.dimmed));
+            }
+            EventMsg::McpToolCallBegin(McpToolCallBeginEvent {
+                call_id,
+                server,
+                tool,
+                arguments,
+            }) => {
+                // Build fully-qualified tool name: server.tool
+                let fq_tool_name = format!("{server}.{tool}");
+
+                // Format arguments as compact JSON so they fit on one line.
+                let args_str = arguments
+                    .as_ref()
+                    .map(|v: &serde_json::Value| {
+                        serde_json::to_string(v).unwrap_or_else(|_| v.to_string())
+                    })
+                    .unwrap_or_default();
+
+                let invocation = if args_str.is_empty() {
+                    format!("{fq_tool_name}()")
+                } else {
+                    format!("{fq_tool_name}({args_str})")
+                };
+
+                self.call_id_to_tool_call.insert(
+                    call_id.clone(),
+                    McpToolCallBegin {
+                        invocation: invocation.clone(),
+                        start_time: Instant::now(),
+                    },
+                );
+
+                ts_println!(
+                    self,
+                    "{} {}",
+                    "tool".style(self.magenta),
+                    invocation.style(self.bold),
+                );
+            }
+            EventMsg::McpToolCallEnd(tool_call_end_event) => {
+                let is_success = tool_call_end_event.is_success();
+                let McpToolCallEndEvent { call_id, result } = tool_call_end_event;
+                // Retrieve start time and invocation for duration calculation and labeling.
+                let info = self.call_id_to_tool_call.remove(&call_id);
+
+                let (duration, invocation) = if let Some(McpToolCallBegin {
+                    invocation,
+                    start_time,
+                    ..
+                }) = info
+                {
+                    (format!(" in {}", format_elapsed(start_time)), invocation)
+                } else {
+                    (String::new(), format!("tool('{call_id}')"))
+                };
+
+                let status_str = if is_success { "success" } else { "failed" };
+                let title_style = if is_success { self.green } else { self.red };
+                let title = format!("{invocation} {status_str}{duration}:");
+
+                ts_println!(self, "{}", title.style(title_style));
+
+                if let Ok(res) = result {
+                    let val: serde_json::Value = res.into();
+                    let pretty =
+                        serde_json::to_string_pretty(&val).unwrap_or_else(|_| val.to_string());
+
+                    for line in pretty.lines().take(MAX_OUTPUT_LINES_FOR_EXEC_TOOL_CALL) {
+                        println!("{}", line.style(self.dimmed));
+                    }
+                }
+            }
+            EventMsg::PatchApplyBegin(PatchApplyBeginEvent {
+                call_id,
+                auto_approved,
+                changes,
+            }) => {
+                // Store metadata so we can calculate duration later when we
+                // receive the corresponding PatchApplyEnd event.
+                self.call_id_to_patch.insert(
+                    call_id.clone(),
+                    PatchApplyBegin {
+                        start_time: Instant::now(),
+                        auto_approved,
+                    },
+                );
+
+                ts_println!(
+                    self,
+                    "{} auto_approved={}:",
+                    "apply_patch".style(self.magenta),
+                    auto_approved,
+                );
+
+                // Pretty-print the patch summary with colored diff markers so
+                // it's easy to scan in the terminal output.
+                for (path, change) in changes.iter() {
+                    match change {
+                        FileChange::Add { content } => {
+                            let header = format!(
+                                "{} {}",
+                                format_file_change(change),
+                                path.to_string_lossy()
+                            );
+                            println!("{}", header.style(self.magenta));
+                            for line in content.lines() {
+                                println!("{}", line.style(self.green));
+                            }
+                        }
+                        FileChange::Delete => {
+                            let header = format!(
+                                "{} {}",
+                                format_file_change(change),
+                                path.to_string_lossy()
+                            );
+                            println!("{}", header.style(self.magenta));
+                        }
+                        FileChange::Update {
+                            unified_diff,
+                            move_path,
+                        } => {
+                            let header = if let Some(dest) = move_path {
+                                format!(
+                                    "{} {} -> {}",
+                                    format_file_change(change),
+                                    path.to_string_lossy(),
+                                    dest.to_string_lossy()
+                                )
+                            } else {
+                                format!("{} {}", format_file_change(change), path.to_string_lossy())
+                            };
+                            println!("{}", header.style(self.magenta));
+
+                            // Colorize diff lines. We keep file header lines
+                            // (--- / +++) without extra coloring so they are
+                            // still readable.
+                            for diff_line in unified_diff.lines() {
+                                if diff_line.starts_with('+') && !diff_line.starts_with("+++") {
+                                    println!("{}", diff_line.style(self.green));
+                                } else if diff_line.starts_with('-')
+                                    && !diff_line.starts_with("---")
+                                {
+                                    println!("{}", diff_line.style(self.red));
+                                } else {
+                                    println!("{diff_line}");
+                                }
+                            }
+                        }
+                    }
+                }
+            }
+            EventMsg::PatchApplyEnd(PatchApplyEndEvent {
+                call_id,
+                stdout,
+                stderr,
+                success,
+            }) => {
+                let patch_begin = self.call_id_to_patch.remove(&call_id);
+
+                // Compute duration and summary label similar to exec commands.
+                let (duration, label) = if let Some(PatchApplyBegin {
+                    start_time,
+                    auto_approved,
+                }) = patch_begin
+                {
+                    (
+                        format!(" in {}", format_elapsed(start_time)),
+                        format!("apply_patch(auto_approved={auto_approved})"),
+                    )
+                } else {
+                    (String::new(), format!("apply_patch('{call_id}')"))
+                };
+
+                let (exit_code, output, title_style) = if success {
+                    (0, stdout, self.green)
+                } else {
+                    (1, stderr, self.red)
+                };
+
+                let title = format!("{label} exited {exit_code}{duration}:");
+                ts_println!(self, "{}", title.style(title_style));
+                for line in output.lines() {
+                    println!("{}", line.style(self.dimmed));
+                }
+            }
+            EventMsg::ExecApprovalRequest(_) => {
+                // Should we exit?
+            }
+            EventMsg::ApplyPatchApprovalRequest(_) => {
+                // Should we exit?
+            }
+            EventMsg::AgentReasoning(agent_reasoning_event) => {
+                if self.show_agent_reasoning {
+                    if !self.reasoning_started {
+                        ts_println!(
+                            self,
+                            "{}\n{}",
+                            "codex".style(self.italic).style(self.magenta),
+                            agent_reasoning_event.text,
+                        );
+                    } else {
+                        println!();
+                        self.reasoning_started = false;
+                    }
+                }
+            }
+            EventMsg::SessionConfigured(session_configured_event) => {
+                let SessionConfiguredEvent {
+                    session_id,
+                    model,
+                    history_log_id: _,
+                    history_entry_count: _,
+                } = session_configured_event;
+
+                ts_println!(
+                    self,
+                    "{} {}",
+                    "codex session".style(self.magenta).style(self.bold),
+                    session_id.to_string().style(self.dimmed)
+                );
+
+                ts_println!(self, "model: {}", model);
+                println!();
+            }
+            EventMsg::GetHistoryEntryResponse(_) => {
+                // Currently ignored in exec output.
+            }
+            EventMsg::ShutdownComplete => return CodexStatus::Shutdown,
+        }
+        CodexStatus::Running
+    }
+}
+
+fn escape_command(command: &[String]) -> String {
+    try_join(command.iter().map(|s| s.as_str())).unwrap_or_else(|_| command.join(" "))
+}
+
+fn format_file_change(change: &FileChange) -> &'static str {
+    match change {
+        FileChange::Add { .. } => "A",
+        FileChange::Delete => "D",
+        FileChange::Update {
+            move_path: Some(_), ..
+        } => "R",
+        FileChange::Update {
+            move_path: None, ..
+        } => "M",
+    }
+}

codex-rs/exec/src/event_processor_with_json_output.rs

@@ -0,0 +1,64 @@
+use std::collections::HashMap;
+use std::path::PathBuf;
+
+use codex_core::config::Config;
+use codex_core::protocol::Event;
+use codex_core::protocol::EventMsg;
+use codex_core::protocol::TaskCompleteEvent;
+use serde_json::json;
+
+use crate::event_processor::CodexStatus;
+use crate::event_processor::EventProcessor;
+use crate::event_processor::create_config_summary_entries;
+use crate::event_processor::handle_last_message;
+
+pub(crate) struct EventProcessorWithJsonOutput {
+    last_message_path: Option<PathBuf>,
+}
+
+impl EventProcessorWithJsonOutput {
+    pub fn new(last_message_path: Option<PathBuf>) -> Self {
+        Self { last_message_path }
+    }
+}
+
+impl EventProcessor for EventProcessorWithJsonOutput {
+    fn print_config_summary(&mut self, config: &Config, prompt: &str) {
+        let entries = create_config_summary_entries(config)
+            .into_iter()
+            .map(|(key, value)| (key.to_string(), value))
+            .collect::<HashMap<String, String>>();
+        #[allow(clippy::expect_used)]
+        let config_json =
+            serde_json::to_string(&entries).expect("Failed to serialize config summary to JSON");
+        println!("{config_json}");
+
+        let prompt_json = json!({
+            "prompt": prompt,
+        });
+        println!("{prompt_json}");
+    }
+
+    fn process_event(&mut self, event: Event) -> CodexStatus {
+        match event.msg {
+            EventMsg::AgentMessageDelta(_) | EventMsg::AgentReasoningDelta(_) => {
+                // Suppress streaming events in JSON mode.
+                CodexStatus::Running
+            }
+            EventMsg::TaskComplete(TaskCompleteEvent { last_agent_message }) => {
+                handle_last_message(
+                    last_agent_message.as_deref(),
+                    self.last_message_path.as_deref(),
+                );
+                CodexStatus::InitiateShutdown
+            }
+            EventMsg::ShutdownComplete => CodexStatus::Shutdown,
+            _ => {
+                if let Ok(line) = serde_json::to_string(&event) {
+                    println!("{line}");
+                }
+                CodexStatus::Running
+            }
+        }
+    }
+}

codex-rs/exec/src/lib.rs

@@ -1,14 +1,16 @@
 mod cli;
 mod event_processor;
+mod event_processor_with_human_output;
+mod event_processor_with_json_output;
 
 use std::io::IsTerminal;
 use std::io::Read;
-use std::path::Path;
 use std::path::PathBuf;
 use std::sync::Arc;
 
 pub use cli::Cli;
-use codex_core::codex_wrapper;
+use codex_core::codex_wrapper::CodexConversation;
+use codex_core::codex_wrapper::{self};
 use codex_core::config::Config;
 use codex_core::config::ConfigOverrides;
 use codex_core::config_types::SandboxMode;
@@ -19,12 +21,16 @@ use codex_core::protocol::InputItem;
 use codex_core::protocol::Op;
 use codex_core::protocol::TaskCompleteEvent;
 use codex_core::util::is_inside_git_repo;
-use event_processor::EventProcessor;
+use event_processor_with_human_output::EventProcessorWithHumanOutput;
+use event_processor_with_json_output::EventProcessorWithJsonOutput;
 use tracing::debug;
 use tracing::error;
 use tracing::info;
 use tracing_subscriber::EnvFilter;
 
+use crate::event_processor::CodexStatus;
+use crate::event_processor::EventProcessor;
+
 pub async fn run_main(cli: Cli, codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()> {
     let Cli {
         images,
@@ -36,6 +42,7 @@ pub async fn run_main(cli: Cli, codex_linux_sandbox_exe: Option<PathBuf>) -> any
         skip_git_repo_check,
         color,
         last_message_file,
+        json: json_mode,
         sandbox_mode: sandbox_mode_cli_arg,
         prompt,
         config_overrides,
@@ -104,6 +111,7 @@ pub async fn run_main(cli: Cli, codex_linux_sandbox_exe: Option<PathBuf>) -> any
         cwd: cwd.map(|p| p.canonicalize().unwrap_or(p)),
         model_provider: None,
         codex_linux_sandbox_exe,
+        base_instructions: None,
     };
     // Parse `-c` overrides.
     let cli_kv_overrides = match config_overrides.parse_overrides() {
@@ -115,8 +123,16 @@ pub async fn run_main(cli: Cli, codex_linux_sandbox_exe: Option<PathBuf>) -> any
     };
 
     let config = Config::load_with_cli_overrides(cli_kv_overrides, overrides)?;
-    let mut event_processor =
-        EventProcessor::create_with_ansi(stdout_with_ansi, !config.hide_agent_reasoning);
+    let mut event_processor: Box<dyn EventProcessor> = if json_mode {
+        Box::new(EventProcessorWithJsonOutput::new(last_message_file.clone()))
+    } else {
+        Box::new(EventProcessorWithHumanOutput::create_with_ansi(
+            stdout_with_ansi,
+            &config,
+            last_message_file.clone(),
+        ))
+    };
+
     // Print the effective configuration and prompt so users can see what Codex
     // is using.
     event_processor.print_config_summary(&config, &prompt);
@@ -140,9 +156,14 @@ pub async fn run_main(cli: Cli, codex_linux_sandbox_exe: Option<PathBuf>) -> any
         .with_writer(std::io::stderr)
         .try_init();
 
-    let (codex_wrapper, event, ctrl_c) = codex_wrapper::init_codex(config).await?;
+    let CodexConversation {
+        codex: codex_wrapper,
+        session_configured,
+        ctrl_c,
+        ..
+    } = codex_wrapper::init_codex(config).await?;
     let codex = Arc::new(codex_wrapper);
-    info!("Codex initialized with event: {event:?}");
+    info!("Codex initialized with event: {session_configured:?}");
 
     let (tx, mut rx) = tokio::sync::mpsc::unbounded_channel::<Event>();
     {
@@ -210,40 +231,17 @@ pub async fn run_main(cli: Cli, codex_linux_sandbox_exe: Option<PathBuf>) -> any
 
     // Run the loop until the task is complete.
     while let Some(event) = rx.recv().await {
-        let (is_last_event, last_assistant_message) = match &event.msg {
-            EventMsg::TaskComplete(TaskCompleteEvent { last_agent_message }) => {
-                (true, last_agent_message.clone())
+        let shutdown: CodexStatus = event_processor.process_event(event);
+        match shutdown {
+            CodexStatus::Running => continue,
+            CodexStatus::InitiateShutdown => {
+                codex.submit(Op::Shutdown).await?;
+            }
+            CodexStatus::Shutdown => {
+                break;
             }
-            _ => (false, None),
-        };
-        event_processor.process_event(event);
-        if is_last_event {
-            handle_last_message(last_assistant_message, last_message_file.as_deref())?;
-            break;
         }
     }
 
     Ok(())
 }
-
-fn handle_last_message(
-    last_agent_message: Option<String>,
-    last_message_file: Option<&Path>,
-) -> std::io::Result<()> {
-    match (last_agent_message, last_message_file) {
-        (Some(last_agent_message), Some(last_message_file)) => {
-            // Last message and a file to write to.
-            std::fs::write(last_message_file, last_agent_message)?;
-        }
-        (None, Some(last_message_file)) => {
-            eprintln!(
-                "Warning: No last message to write to file: {}",
-                last_message_file.to_string_lossy()
-            );
-        }
-        (_, None) => {
-            // No last message and no file to write to.
-        }
-    }
-    Ok(())
-}

codex-rs/exec/src/main.rs

@@ -10,6 +10,7 @@
 //! This allows us to ship a completely separate set of functionality as part
 //! of the `codex-exec` binary.
 use clap::Parser;
+use codex_arg0::arg0_dispatch_or_else;
 use codex_common::CliConfigOverrides;
 use codex_exec::Cli;
 use codex_exec::run_main;
@@ -24,7 +25,7 @@ struct TopCli {
 }
 
 fn main() -> anyhow::Result<()> {
-    codex_linux_sandbox::run_with_sandbox(|codex_linux_sandbox_exe| async move {
+    arg0_dispatch_or_else(|codex_linux_sandbox_exe| async move {
         let top_cli = TopCli::parse();
         // Merge root-level overrides into inner CLI struct so downstream logic remains unchanged.
         let mut inner = top_cli.inner;

codex-rs/exec/tests/apply_patch.rs

@@ -0,0 +1,38 @@
+use anyhow::Context;
+use assert_cmd::prelude::*;
+use std::fs;
+use std::process::Command;
+use tempfile::tempdir;
+
+/// While we may add an `apply-patch` subcommand to the `codex` CLI multitool
+/// at some point, we must ensure that the smaller `codex-exec` CLI can still
+/// emulate the `apply_patch` CLI.
+#[test]
+fn test_standalone_exec_cli_can_use_apply_patch() -> anyhow::Result<()> {
+    let tmp = tempdir()?;
+    let relative_path = "source.txt";
+    let absolute_path = tmp.path().join(relative_path);
+    fs::write(&absolute_path, "original content\n")?;
+
+    Command::cargo_bin("codex-exec")
+        .context("should find binary for codex-exec")?
+        .arg("--codex-run-as-apply-patch")
+        .arg(
+            r#"*** Begin Patch
+*** Update File: source.txt
+@@
+-original content
++modified by apply_patch
+*** End Patch"#,
+        )
+        .current_dir(tmp.path())
+        .assert()
+        .success()
+        .stdout("Success. Updated the following files:\nM source.txt\n")
+        .stderr(predicates::str::is_empty());
+    assert_eq!(
+        fs::read_to_string(absolute_path)?,
+        "modified by apply_patch\n"
+    );
+    Ok(())
+}

codex-rs/justfile

@@ -23,3 +23,10 @@ file-search *args:
 # format code
 fmt:
     cargo fmt -- --config imports_granularity=Item
+
+fix:
+    cargo clippy --fix --all-features --tests --allow-dirty
+
+install:
+    rustup show active-toolchain
+    cargo fetch

codex-rs/linux-sandbox/Cargo.toml

@@ -14,13 +14,16 @@ path = "src/lib.rs"
 [lints]
 workspace = true
 
-[dependencies]
+[target.'cfg(target_os = "linux")'.dependencies]
 anyhow = "1"
 clap = { version = "4", features = ["derive"] }
+codex-common = { path = "../common", features = ["cli"] }
 codex-core = { path = "../core" }
-tokio = { version = "1", features = ["rt-multi-thread"] }
+libc = "0.2.172"
+landlock = "0.4.1"
+seccompiler = "0.5.0"
 
-[dev-dependencies]
+[target.'cfg(target_os = "linux")'.dev-dependencies]
 tempfile = "3"
 tokio = { version = "1", features = [
     "io-std",
@@ -29,8 +32,3 @@ tokio = { version = "1", features = [
     "rt-multi-thread",
     "signal",
 ] }
-
-[target.'cfg(target_os = "linux")'.dependencies]
-libc = "0.2.172"
-landlock = "0.4.1"
-seccompiler = "0.5.0"

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

@@ -4,57 +4,8 @@ mod landlock;
 mod linux_run_main;
 
 #[cfg(target_os = "linux")]
-pub use linux_run_main::run_main;
-
-use std::future::Future;
-use std::path::PathBuf;
-
-/// Helper that consolidates the common boilerplate found in several Codex
-/// binaries (`codex`, `codex-exec`, `codex-tui`) around dispatching to the
-/// `codex-linux-sandbox` sub-command.
-///
-/// When the current executable is invoked through the hard-link or alias
-/// named `codex-linux-sandbox` we *directly* execute [`run_main`](crate::run_main)
-/// (which never returns). Otherwise we:
-/// 1.  Construct a Tokio multi-thread runtime.
-/// 2.  Derive the path to the current executable (so children can re-invoke
-///     the sandbox) when running on Linux.
-/// 3.  Execute the provided async `main_fn` inside that runtime, forwarding
-///     any error.
-///
-/// This function eliminates duplicated code across the various `main.rs`
-/// entry-points.
-pub fn run_with_sandbox<F, Fut>(main_fn: F) -> anyhow::Result<()>
-where
-    F: FnOnce(Option<PathBuf>) -> Fut,
-    Fut: Future<Output = anyhow::Result<()>>,
-{
-    use std::path::Path;
-
-    // Determine if we were invoked via the special alias.
-    let argv0 = std::env::args().next().unwrap_or_default();
-    let exe_name = Path::new(&argv0)
-        .file_name()
-        .and_then(|s| s.to_str())
-        .unwrap_or("");
-
-    if exe_name == "codex-linux-sandbox" {
-        // Safety: [`run_main`] never returns.
-        crate::run_main();
-    }
-
-    // Regular invocation – create a Tokio runtime and execute the provided
-    // async entry-point.
-    let runtime = tokio::runtime::Runtime::new()?;
-    runtime.block_on(async move {
-        let codex_linux_sandbox_exe: Option<PathBuf> = if cfg!(target_os = "linux") {
-            std::env::current_exe().ok()
-        } else {
-            None
-        };
-
-        main_fn(codex_linux_sandbox_exe).await
-    })
+pub fn run_main() -> ! {
+    linux_run_main::run_main();
 }
 
 #[cfg(not(target_os = "linux"))]

codex-rs/mcp-client/src/main.rs

@@ -10,6 +10,7 @@
 //! program. The utility connects, issues a `tools/list` request and prints the
 //! server's response as pretty JSON.
 
+use std::ffi::OsString;
 use std::time::Duration;
 
 use anyhow::Context;
@@ -37,7 +38,7 @@ async fn main() -> Result<()> {
         .try_init();
 
     // Collect command-line arguments excluding the program name itself.
-    let mut args: Vec<String> = std::env::args().skip(1).collect();
+    let mut args: Vec<OsString> = std::env::args_os().skip(1).collect();
 
     if args.is_empty() || args[0] == "--help" || args[0] == "-h" {
         eprintln!("Usage: mcp-client <program> [args..]\n\nExample: mcp-client codex-mcp-server");
@@ -57,10 +58,12 @@ async fn main() -> Result<()> {
             experimental: None,
             roots: None,
             sampling: None,
+            elicitation: None,
         },
         client_info: Implementation {
             name: "codex-mcp-client".to_owned(),
             version: env!("CARGO_PKG_VERSION").to_owned(),
+            title: Some("Codex".to_string()),
         },
         protocol_version: MCP_SCHEMA_VERSION.to_owned(),
     };

codex-rs/mcp-client/src/mcp_client.rs

@@ -12,6 +12,7 @@
 //! issue requests and receive strongly-typed results.
 
 use std::collections::HashMap;
+use std::ffi::OsString;
 use std::sync::Arc;
 use std::sync::atomic::AtomicI64;
 use std::sync::atomic::Ordering;
@@ -82,8 +83,8 @@ impl McpClient {
     /// Caller is responsible for sending the `initialize` request. See
     /// [`initialize`](Self::initialize) for details.
     pub async fn new_stdio_client(
-        program: String,
-        args: Vec<String>,
+        program: OsString,
+        args: Vec<OsString>,
         env: Option<HashMap<String, String>>,
     ) -> std::io::Result<Self> {
         let mut child = Command::new(program)

codex-rs/mcp-server/Cargo.toml

@@ -16,12 +16,13 @@ workspace = true
 
 [dependencies]
 anyhow = "1"
+codex-arg0 = { path = "../arg0" }
 codex-core = { path = "../core" }
-codex-linux-sandbox = { path = "../linux-sandbox" }
 mcp-types = { path = "../mcp-types" }
 schemars = "0.8.22"
 serde = { version = "1", features = ["derive"] }
 serde_json = "1"
+shlex = "1.3.0"
 toml = "0.9"
 tracing = { version = "0.1.41", features = ["log"] }
 tracing-subscriber = { version = "0.3", features = ["fmt", "env-filter"] }
@@ -32,6 +33,12 @@ tokio = { version = "1", features = [
     "rt-multi-thread",
     "signal",
 ] }
+uuid = { version = "1", features = ["serde", "v4"] }
 
 [dev-dependencies]
+assert_cmd = "2"
+mcp_test_support = { path = "tests/common" }
 pretty_assertions = "1.4.1"
+tempfile = "3"
+tokio-test = "0.4"
+wiremock = "0.6"

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

@@ -7,15 +7,16 @@ use mcp_types::ToolInputSchema;
 use schemars::JsonSchema;
 use schemars::r#gen::SchemaSettings;
 use serde::Deserialize;
+use serde::Serialize;
 use std::collections::HashMap;
 use std::path::PathBuf;
 
 use crate::json_to_toml::json_to_toml;
 
 /// Client-supplied configuration for a `codex` tool-call.
-#[derive(Debug, Clone, Deserialize, JsonSchema)]
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema, Default)]
 #[serde(rename_all = "kebab-case")]
-pub(crate) struct CodexToolCallParam {
+pub struct CodexToolCallParam {
     /// The *initial user prompt* to start the Codex conversation.
     pub prompt: String,
 
@@ -45,13 +46,17 @@ pub(crate) struct CodexToolCallParam {
     /// CODEX_HOME/config.toml.
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub config: Option<HashMap<String, serde_json::Value>>,
+
+    /// The set of instructions to use instead of the default ones.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub base_instructions: Option<String>,
 }
 
 /// Custom enum mirroring [`AskForApproval`], but has an extra dependency on
 /// [`JsonSchema`].
-#[derive(Debug, Clone, Deserialize, JsonSchema)]
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
 #[serde(rename_all = "kebab-case")]
-pub(crate) enum CodexToolCallApprovalPolicy {
+pub enum CodexToolCallApprovalPolicy {
     Untrusted,
     OnFailure,
     Never,
@@ -69,9 +74,9 @@ impl From<CodexToolCallApprovalPolicy> for AskForApproval {
 
 /// Custom enum mirroring [`SandboxMode`] from config_types.rs, but with
 /// `JsonSchema` support.
-#[derive(Debug, Clone, Deserialize, JsonSchema)]
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
 #[serde(rename_all = "kebab-case")]
-pub(crate) enum CodexToolCallSandboxMode {
+pub enum CodexToolCallSandboxMode {
     ReadOnly,
     WorkspaceWrite,
     DangerFullAccess,
@@ -108,7 +113,10 @@ pub(crate) fn create_tool_for_codex_tool_call_param() -> Tool {
 
     Tool {
         name: "codex".to_string(),
+        title: Some("Codex".to_string()),
         input_schema: tool_input_schema,
+        // TODO(mbolin): This should be defined.
+        output_schema: None,
         description: Some(
             "Run a Codex session. Accepts configuration parameters matching the Codex Config struct.".to_string(),
         ),
@@ -131,6 +139,7 @@ impl CodexToolCallParam {
             approval_policy,
             sandbox,
             config: cli_overrides,
+            base_instructions,
         } = self;
 
         // Build the `ConfigOverrides` recognised by codex-core.
@@ -142,6 +151,7 @@ impl CodexToolCallParam {
             sandbox_mode: sandbox.map(Into::into),
             model_provider: None,
             codex_linux_sandbox_exe,
+            base_instructions,
         };
 
         let cli_overrides = cli_overrides
@@ -156,6 +166,47 @@ impl CodexToolCallParam {
     }
 }
 
+#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
+#[serde(rename_all = "camelCase")]
+pub struct CodexToolCallReplyParam {
+    /// The *session id* for this conversation.
+    pub session_id: String,
+
+    /// The *next user prompt* to continue the Codex conversation.
+    pub prompt: String,
+}
+
+/// Builds a `Tool` definition for the `codex-reply` tool-call.
+pub(crate) fn create_tool_for_codex_tool_call_reply_param() -> Tool {
+    let schema = SchemaSettings::draft2019_09()
+        .with(|s| {
+            s.inline_subschemas = true;
+            s.option_add_null_type = false;
+        })
+        .into_generator()
+        .into_root_schema_for::<CodexToolCallReplyParam>();
+
+    #[expect(clippy::expect_used)]
+    let schema_value =
+        serde_json::to_value(&schema).expect("Codex reply tool schema should serialise to JSON");
+
+    let tool_input_schema =
+        serde_json::from_value::<ToolInputSchema>(schema_value).unwrap_or_else(|e| {
+            panic!("failed to create Tool from schema: {e}");
+        });
+
+    Tool {
+        name: "codex-reply".to_string(),
+        title: Some("Codex Reply".to_string()),
+        input_schema: tool_input_schema,
+        output_schema: None,
+        description: Some(
+            "Continue a Codex session by providing the session id and prompt.".to_string(),
+        ),
+        annotations: None,
+    }
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
@@ -179,6 +230,7 @@ mod tests {
         let tool_json = serde_json::to_value(&tool).expect("tool serializes");
         let expected_tool_json = serde_json::json!({
           "name": "codex",
+          "title": "Codex",
           "description": "Run a Codex session. Accepts configuration parameters matching the Codex Config struct.",
           "inputSchema": {
             "type": "object",
@@ -222,6 +274,10 @@ mod tests {
                 "description": "The *initial user prompt* to start the Codex conversation.",
                 "type": "string"
               },
+              "base-instructions": {
+                "description": "The set of instructions to use instead of the default ones.",
+                "type": "string"
+              },
             },
             "required": [
               "prompt"
@@ -230,4 +286,34 @@ mod tests {
         });
         assert_eq!(expected_tool_json, tool_json);
     }
+
+    #[test]
+    fn verify_codex_tool_reply_json_schema() {
+        let tool = create_tool_for_codex_tool_call_reply_param();
+        #[expect(clippy::expect_used)]
+        let tool_json = serde_json::to_value(&tool).expect("tool serializes");
+        let expected_tool_json = serde_json::json!({
+          "description": "Continue a Codex session by providing the session id and prompt.",
+          "inputSchema": {
+            "properties": {
+              "prompt": {
+                "description": "The *next user prompt* to continue the Codex conversation.",
+                "type": "string"
+              },
+              "sessionId": {
+                "description": "The *session id* for this conversation.",
+                "type": "string"
+              },
+            },
+            "required": [
+              "prompt",
+              "sessionId",
+            ],
+            "type": "object",
+          },
+          "name": "codex-reply",
+          "title": "Codex Reply",
+        });
+        assert_eq!(expected_tool_json, tool_json);
+    }
 }

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

@@ -2,33 +2,35 @@
 //! Tokio task. Separated from `message_processor.rs` to keep that file small
 //! and to make future feature-growth easier to manage.
 
+use std::collections::HashMap;
+use std::sync::Arc;
+
+use codex_core::Codex;
+use codex_core::codex_wrapper::CodexConversation;
 use codex_core::codex_wrapper::init_codex;
 use codex_core::config::Config as CodexConfig;
 use codex_core::protocol::AgentMessageEvent;
-use codex_core::protocol::Event;
+use codex_core::protocol::ApplyPatchApprovalRequestEvent;
 use codex_core::protocol::EventMsg;
+use codex_core::protocol::ExecApprovalRequestEvent;
 use codex_core::protocol::InputItem;
 use codex_core::protocol::Op;
 use codex_core::protocol::Submission;
 use codex_core::protocol::TaskCompleteEvent;
 use mcp_types::CallToolResult;
-use mcp_types::CallToolResultContent;
-use mcp_types::JSONRPC_VERSION;
-use mcp_types::JSONRPCMessage;
-use mcp_types::JSONRPCResponse;
+use mcp_types::ContentBlock;
 use mcp_types::RequestId;
 use mcp_types::TextContent;
-use tokio::sync::mpsc::Sender;
+use serde_json::json;
+use tokio::sync::Mutex;
+use uuid::Uuid;
 
-/// Convert a Codex [`Event`] to an MCP notification.
-fn codex_event_to_notification(event: &Event) -> JSONRPCMessage {
-    #[expect(clippy::expect_used)]
-    JSONRPCMessage::Notification(mcp_types::JSONRPCNotification {
-        jsonrpc: JSONRPC_VERSION.into(),
-        method: "codex/event".into(),
-        params: Some(serde_json::to_value(event).expect("Event must serialize")),
-    })
-}
+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;
+
+pub(crate) const INVALID_PARAMS_ERROR_CODE: i64 = -32602;
 
 /// Run a complete Codex session and stream events back to the client.
 ///
@@ -38,33 +40,43 @@ pub async fn run_codex_tool_session(
     id: RequestId,
     initial_prompt: String,
     config: CodexConfig,
-    outgoing: Sender<JSONRPCMessage>,
+    outgoing: Arc<OutgoingMessageSender>,
+    session_map: Arc<Mutex<HashMap<Uuid, Arc<Codex>>>>,
+    running_requests_id_to_codex_uuid: Arc<Mutex<HashMap<RequestId, Uuid>>>,
 ) {
-    let (codex, first_event, _ctrl_c) = match init_codex(config).await {
+    let CodexConversation {
+        codex,
+        session_configured,
+        session_id,
+        ..
+    } = match init_codex(config).await {
         Ok(res) => res,
         Err(e) => {
             let result = CallToolResult {
-                content: vec![CallToolResultContent::TextContent(TextContent {
+                content: vec![ContentBlock::TextContent(TextContent {
                     r#type: "text".to_string(),
                     text: format!("Failed to start Codex session: {e}"),
                     annotations: None,
                 })],
                 is_error: Some(true),
+                structured_content: None,
             };
-            let _ = outgoing
-                .send(JSONRPCMessage::Response(JSONRPCResponse {
-                    jsonrpc: JSONRPC_VERSION.into(),
-                    id,
-                    result: result.into(),
-                }))
-                .await;
+            outgoing.send_response(id.clone(), result.into()).await;
             return;
         }
     };
+    let codex = Arc::new(codex);
 
-    // Send initial SessionConfigured event.
-    let _ = outgoing
-        .send(codex_event_to_notification(&first_event))
+    // update the session map so we can retrieve the session in a reply, and then drop it, since
+    // we no longer need it for this function
+    session_map.lock().await.insert(session_id, codex.clone());
+    drop(session_map);
+
+    outgoing
+        .send_event_as_notification(
+            &session_configured,
+            Some(OutgoingNotificationMeta::new(Some(id.clone()))),
+        )
         .await;
 
     // Use the original MCP request ID as the `sub_id` for the Codex submission so that
@@ -74,9 +86,12 @@ pub async fn run_codex_tool_session(
         RequestId::String(s) => s.clone(),
         RequestId::Integer(n) => n.to_string(),
     };
-
+    running_requests_id_to_codex_uuid
+        .lock()
+        .await
+        .insert(id.clone(), session_id);
     let submission = Submission {
-        id: sub_id,
+        id: sub_id.clone(),
         op: Op::UserInput {
             items: vec![InputItem::Text {
                 text: initial_prompt.clone(),
@@ -86,93 +101,158 @@ pub async fn run_codex_tool_session(
 
     if let Err(e) = codex.submit_with_id(submission).await {
         tracing::error!("Failed to submit initial prompt: {e}");
+        // unregister the id so we don't keep it in the map
+        running_requests_id_to_codex_uuid.lock().await.remove(&id);
+        return;
     }
 
-    let mut last_agent_message: Option<String> = None;
+    run_codex_tool_session_inner(codex, outgoing, id, running_requests_id_to_codex_uuid).await;
+}
+
+pub async fn run_codex_tool_session_reply(
+    codex: Arc<Codex>,
+    outgoing: Arc<OutgoingMessageSender>,
+    request_id: RequestId,
+    prompt: String,
+    running_requests_id_to_codex_uuid: Arc<Mutex<HashMap<RequestId, Uuid>>>,
+    session_id: Uuid,
+) {
+    running_requests_id_to_codex_uuid
+        .lock()
+        .await
+        .insert(request_id.clone(), session_id);
+    if let Err(e) = codex
+        .submit(Op::UserInput {
+            items: vec![InputItem::Text { text: prompt }],
+        })
+        .await
+    {
+        tracing::error!("Failed to submit user input: {e}");
+        // unregister the id so we don't keep it in the map
+        running_requests_id_to_codex_uuid
+            .lock()
+            .await
+            .remove(&request_id);
+        return;
+    }
+
+    run_codex_tool_session_inner(
+        codex,
+        outgoing,
+        request_id,
+        running_requests_id_to_codex_uuid,
+    )
+    .await;
+}
+
+async fn run_codex_tool_session_inner(
+    codex: Arc<Codex>,
+    outgoing: Arc<OutgoingMessageSender>,
+    request_id: RequestId,
+    running_requests_id_to_codex_uuid: Arc<Mutex<HashMap<RequestId, Uuid>>>,
+) {
+    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) => {
-                let _ = outgoing.send(codex_event_to_notification(&event)).await;
+                outgoing
+                    .send_event_as_notification(
+                        &event,
+                        Some(OutgoingNotificationMeta::new(Some(request_id.clone()))),
+                    )
+                    .await;
 
-                match &event.msg {
-                    EventMsg::AgentMessage(AgentMessageEvent { message }) => {
-                        last_agent_message = Some(message.clone());
-                    }
-                    EventMsg::ExecApprovalRequest(_) => {
-                        let result = CallToolResult {
-                            content: vec![CallToolResultContent::TextContent(TextContent {
-                                r#type: "text".to_string(),
-                                text: "EXEC_APPROVAL_REQUIRED".to_string(),
-                                annotations: None,
-                            })],
-                            is_error: None,
-                        };
-                        let _ = outgoing
-                            .send(JSONRPCMessage::Response(JSONRPCResponse {
-                                jsonrpc: JSONRPC_VERSION.into(),
-                                id: id.clone(),
-                                result: result.into(),
-                            }))
-                            .await;
-                        break;
-                    }
-                    EventMsg::ApplyPatchApprovalRequest(_) => {
-                        let result = CallToolResult {
-                            content: vec![CallToolResultContent::TextContent(TextContent {
-                                r#type: "text".to_string(),
-                                text: "PATCH_APPROVAL_REQUIRED".to_string(),
-                                annotations: None,
-                            })],
-                            is_error: None,
-                        };
-                        let _ = outgoing
-                            .send(JSONRPCMessage::Response(JSONRPCResponse {
-                                jsonrpc: JSONRPC_VERSION.into(),
-                                id: id.clone(),
-                                result: result.into(),
-                            }))
-                            .await;
-                        break;
-                    }
-                    EventMsg::TaskComplete(TaskCompleteEvent {
-                        last_agent_message: _,
+                match event.msg {
+                    EventMsg::ExecApprovalRequest(ExecApprovalRequestEvent {
+                        command,
+                        cwd,
+                        call_id,
+                        reason: _,
                     }) => {
-                        let result = if let Some(msg) = last_agent_message {
-                            CallToolResult {
-                                content: vec![CallToolResultContent::TextContent(TextContent {
-                                    r#type: "text".to_string(),
-                                    text: msg,
-                                    annotations: None,
-                                })],
-                                is_error: None,
-                            }
-                        } else {
-                            CallToolResult {
-                                content: vec![CallToolResultContent::TextContent(TextContent {
-                                    r#type: "text".to_string(),
-                                    text: String::new(),
-                                    annotations: None,
-                                })],
-                                is_error: None,
-                            }
+                        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(err_event) => {
+                        // Return a response to conclude the tool call when the Codex session reports an error (e.g., interruption).
+                        let result = json!({
+                            "error": err_event.message,
+                        });
+                        outgoing.send_response(request_id.clone(), result).await;
+                        break;
+                    }
+                    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(TaskCompleteEvent { last_agent_message }) => {
+                        let text = match last_agent_message {
+                            Some(msg) => msg.clone(),
+                            None => "".to_string(),
                         };
-                        let _ = outgoing
-                            .send(JSONRPCMessage::Response(JSONRPCResponse {
-                                jsonrpc: JSONRPC_VERSION.into(),
-                                id: id.clone(),
-                                result: result.into(),
-                            }))
+                        let result = CallToolResult {
+                            content: vec![ContentBlock::TextContent(TextContent {
+                                r#type: "text".to_string(),
+                                text,
+                                annotations: None,
+                            })],
+                            is_error: None,
+                            structured_content: None,
+                        };
+                        outgoing
+                            .send_response(request_id.clone(), result.into())
                             .await;
+                        // unregister the id so we don't keep it in the map
+                        running_requests_id_to_codex_uuid
+                            .lock()
+                            .await
+                            .remove(&request_id);
                         break;
                     }
                     EventMsg::SessionConfigured(_) => {
                         tracing::error!("unexpected SessionConfigured event");
                     }
-                    EventMsg::Error(_)
-                    | EventMsg::TaskStarted
+                    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(_)
@@ -182,7 +262,8 @@ pub async fn run_codex_tool_session(
                     | EventMsg::BackgroundEvent(_)
                     | EventMsg::PatchApplyBegin(_)
                     | EventMsg::PatchApplyEnd(_)
-                    | EventMsg::GetHistoryEntryResponse(_) => {
+                    | EventMsg::GetHistoryEntryResponse(_)
+                    | EventMsg::ShutdownComplete => {
                         // For now, we do not do anything extra for these
                         // events. Note that
                         // send(codex_event_to_notification(&event)) above has
@@ -194,19 +275,18 @@ pub async fn run_codex_tool_session(
             }
             Err(e) => {
                 let result = CallToolResult {
-                    content: vec![CallToolResultContent::TextContent(TextContent {
+                    content: vec![ContentBlock::TextContent(TextContent {
                         r#type: "text".to_string(),
                         text: format!("Codex runtime error: {e}"),
                         annotations: None,
                     })],
                     is_error: Some(true),
+                    // TODO(mbolin): Could present the error in a more
+                    // structured way.
+                    structured_content: None,
                 };
-                let _ = outgoing
-                    .send(JSONRPCMessage::Response(JSONRPCResponse {
-                        jsonrpc: JSONRPC_VERSION.into(),
-                        id: id.clone(),
-                        result: result.into(),
-                    }))
+                outgoing
+                    .send_response(request_id.clone(), result.into())
                     .await;
                 break;
             }

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

@@ -0,0 +1,149 @@
+use std::path::PathBuf;
+use std::sync::Arc;
+
+use codex_core::Codex;
+use codex_core::protocol::Op;
+use codex_core::protocol::ReviewDecision;
+use mcp_types::ElicitRequest;
+use mcp_types::ElicitRequestParamsRequestedSchema;
+use mcp_types::JSONRPCErrorError;
+use mcp_types::ModelContextProtocolRequest;
+use mcp_types::RequestId;
+use serde::Deserialize;
+use serde::Serialize;
+use serde_json::json;
+use tracing::error;
+
+use crate::codex_tool_runner::INVALID_PARAMS_ERROR_CODE;
+
+/// Conforms to [`mcp_types::ElicitRequestParams`] so that it can be used as the
+/// `params` field of an [`ElicitRequest`].
+#[derive(Debug, Serialize)]
+pub struct ExecApprovalElicitRequestParams {
+    // These fields are required so that `params`
+    // conforms to ElicitRequestParams.
+    pub message: String,
+
+    #[serde(rename = "requestedSchema")]
+    pub requested_schema: ElicitRequestParamsRequestedSchema,
+
+    // These are additional fields the client can use to
+    // correlate the request with the codex tool call.
+    pub codex_elicitation: String,
+    pub codex_mcp_tool_call_id: String,
+    pub codex_event_id: String,
+    pub codex_call_id: String,
+    pub codex_command: Vec<String>,
+    pub codex_cwd: PathBuf,
+}
+
+// TODO(mbolin): ExecApprovalResponse does not conform to ElicitResult. See:
+// - https://github.com/modelcontextprotocol/modelcontextprotocol/blob/f962dc1780fa5eed7fb7c8a0232f1fc83ef220cd/schema/2025-06-18/schema.json#L617-L636
+// - https://modelcontextprotocol.io/specification/draft/client/elicitation#protocol-messages
+// It should have "action" and "content" fields.
+#[derive(Debug, Serialize, Deserialize)]
+pub struct ExecApprovalResponse {
+    pub decision: ReviewDecision,
+}
+
+#[allow(clippy::too_many_arguments)]
+pub(crate) async fn handle_exec_approval_request(
+    command: Vec<String>,
+    cwd: PathBuf,
+    outgoing: Arc<crate::outgoing_message::OutgoingMessageSender>,
+    codex: Arc<Codex>,
+    request_id: RequestId,
+    tool_call_id: String,
+    event_id: String,
+    call_id: String,
+) {
+    let escaped_command =
+        shlex::try_join(command.iter().map(|s| s.as_str())).unwrap_or_else(|_| command.join(" "));
+    let message = format!(
+        "Allow Codex to run `{escaped_command}` in `{cwd}`?",
+        cwd = cwd.to_string_lossy()
+    );
+
+    let params = ExecApprovalElicitRequestParams {
+        message,
+        requested_schema: ElicitRequestParamsRequestedSchema {
+            r#type: "object".to_string(),
+            properties: json!({}),
+            required: None,
+        },
+        codex_elicitation: "exec-approval".to_string(),
+        codex_mcp_tool_call_id: tool_call_id.clone(),
+        codex_event_id: event_id.clone(),
+        codex_call_id: call_id,
+        codex_command: command,
+        codex_cwd: cwd,
+    };
+    let params_json = match serde_json::to_value(&params) {
+        Ok(value) => value,
+        Err(err) => {
+            let message = format!("Failed to serialize ExecApprovalElicitRequestParams: {err}");
+            error!("{message}");
+
+            outgoing
+                .send_error(
+                    request_id.clone(),
+                    JSONRPCErrorError {
+                        code: INVALID_PARAMS_ERROR_CODE,
+                        message,
+                        data: None,
+                    },
+                )
+                .await;
+
+            return;
+        }
+    };
+
+    let on_response = outgoing
+        .send_request(ElicitRequest::METHOD, Some(params_json))
+        .await;
+
+    // Listen for the response on a separate task so we don't block the main agent loop.
+    {
+        let codex = codex.clone();
+        let event_id = event_id.clone();
+        tokio::spawn(async move {
+            on_exec_approval_response(event_id, on_response, codex).await;
+        });
+    }
+}
+
+async fn on_exec_approval_response(
+    event_id: String,
+    receiver: tokio::sync::oneshot::Receiver<mcp_types::Result>,
+    codex: Arc<Codex>,
+) {
+    let response = receiver.await;
+    let value = match response {
+        Ok(value) => value,
+        Err(err) => {
+            error!("request failed: {err:?}");
+            return;
+        }
+    };
+
+    // Try to deserialize `value` and then make the appropriate call to `codex`.
+    let response = serde_json::from_value::<ExecApprovalResponse>(value).unwrap_or_else(|err| {
+        error!("failed to deserialize ExecApprovalResponse: {err}");
+        // If we cannot deserialize the response, we deny the request to be
+        // conservative.
+        ExecApprovalResponse {
+            decision: ReviewDecision::Denied,
+        }
+    });
+
+    if let Err(err) = codex
+        .submit(Op::ExecApproval {
+            id: event_id,
+            decision: response.decision,
+        })
+        .await
+    {
+        error!("failed to submit ExecApproval: {err}");
+    }
+}

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

@@ -13,13 +13,26 @@ use tokio::sync::mpsc;
 use tracing::debug;
 use tracing::error;
 use tracing::info;
+use tracing_subscriber::EnvFilter;
 
 mod codex_tool_config;
 mod codex_tool_runner;
+mod exec_approval;
 mod json_to_toml;
 mod message_processor;
+mod outgoing_message;
+mod patch_approval;
 
 use crate::message_processor::MessageProcessor;
+use crate::outgoing_message::OutgoingMessage;
+use crate::outgoing_message::OutgoingMessageSender;
+
+pub use crate::codex_tool_config::CodexToolCallParam;
+pub use crate::codex_tool_config::CodexToolCallReplyParam;
+pub use crate::exec_approval::ExecApprovalElicitRequestParams;
+pub use crate::exec_approval::ExecApprovalResponse;
+pub use crate::patch_approval::PatchApprovalElicitRequestParams;
+pub use crate::patch_approval::PatchApprovalResponse;
 
 /// Size of the bounded channels used to communicate between tasks. The value
 /// is a balance between throughput and memory usage – 128 messages should be
@@ -31,11 +44,12 @@ pub async fn run_main(codex_linux_sandbox_exe: Option<PathBuf>) -> IoResult<()>
     // control the log level with `RUST_LOG`.
     tracing_subscriber::fmt()
         .with_writer(std::io::stderr)
+        .with_env_filter(EnvFilter::from_default_env())
         .init();
 
     // Set up channels.
     let (incoming_tx, mut incoming_rx) = mpsc::channel::<JSONRPCMessage>(CHANNEL_CAPACITY);
-    let (outgoing_tx, mut outgoing_rx) = mpsc::channel::<JSONRPCMessage>(CHANNEL_CAPACITY);
+    let (outgoing_tx, mut outgoing_rx) = mpsc::channel::<OutgoingMessage>(CHANNEL_CAPACITY);
 
     // Task: read from stdin, push to `incoming_tx`.
     let stdin_reader_handle = tokio::spawn({
@@ -63,16 +77,15 @@ pub async fn run_main(codex_linux_sandbox_exe: Option<PathBuf>) -> IoResult<()>
 
     // Task: process incoming messages.
     let processor_handle = tokio::spawn({
-        let mut processor = MessageProcessor::new(outgoing_tx.clone(), codex_linux_sandbox_exe);
+        let outgoing_message_sender = OutgoingMessageSender::new(outgoing_tx);
+        let mut processor = MessageProcessor::new(outgoing_message_sender, codex_linux_sandbox_exe);
         async move {
             while let Some(msg) = incoming_rx.recv().await {
                 match msg {
-                    JSONRPCMessage::Request(r) => processor.process_request(r),
-                    JSONRPCMessage::Response(r) => processor.process_response(r),
-                    JSONRPCMessage::Notification(n) => processor.process_notification(n),
-                    JSONRPCMessage::BatchRequest(b) => processor.process_batch_request(b),
+                    JSONRPCMessage::Request(r) => processor.process_request(r).await,
+                    JSONRPCMessage::Response(r) => processor.process_response(r).await,
+                    JSONRPCMessage::Notification(n) => processor.process_notification(n).await,
                     JSONRPCMessage::Error(e) => processor.process_error(e),
-                    JSONRPCMessage::BatchResponse(b) => processor.process_batch_response(b),
                 }
             }
 
@@ -83,7 +96,8 @@ pub async fn run_main(codex_linux_sandbox_exe: Option<PathBuf>) -> IoResult<()>
     // Task: write outgoing messages to stdout.
     let stdout_writer_handle = tokio::spawn(async move {
         let mut stdout = io::stdout();
-        while let Some(msg) = outgoing_rx.recv().await {
+        while let Some(outgoing_message) = outgoing_rx.recv().await {
+            let msg: JSONRPCMessage = outgoing_message.into();
             match serde_json::to_string(&msg) {
                 Ok(json) => {
                     if let Err(e) = stdout.write_all(json.as_bytes()).await {

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

@@ -1,7 +1,8 @@
+use codex_arg0::arg0_dispatch_or_else;
 use codex_mcp_server::run_main;
 
 fn main() -> anyhow::Result<()> {
-    codex_linux_sandbox::run_with_sandbox(|codex_linux_sandbox_exe| async move {
+    arg0_dispatch_or_else(|codex_linux_sandbox_exe| async move {
         run_main(codex_linux_sandbox_exe).await?;
         Ok(())
     })

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

@@ -1,19 +1,22 @@
+use std::collections::HashMap;
 use std::path::PathBuf;
+use std::sync::Arc;
 
 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::outgoing_message::OutgoingMessageSender;
 
+use codex_core::Codex;
 use codex_core::config::Config as CodexConfig;
+use codex_core::protocol::Submission;
 use mcp_types::CallToolRequestParams;
 use mcp_types::CallToolResult;
-use mcp_types::CallToolResultContent;
 use mcp_types::ClientRequest;
-use mcp_types::JSONRPC_VERSION;
-use mcp_types::JSONRPCBatchRequest;
-use mcp_types::JSONRPCBatchResponse;
+use mcp_types::ContentBlock;
 use mcp_types::JSONRPCError;
 use mcp_types::JSONRPCErrorError;
-use mcp_types::JSONRPCMessage;
 use mcp_types::JSONRPCNotification;
 use mcp_types::JSONRPCRequest;
 use mcp_types::JSONRPCResponse;
@@ -24,30 +27,35 @@ use mcp_types::ServerCapabilitiesTools;
 use mcp_types::ServerNotification;
 use mcp_types::TextContent;
 use serde_json::json;
-use tokio::sync::mpsc;
+use tokio::sync::Mutex;
 use tokio::task;
+use uuid::Uuid;
 
 pub(crate) struct MessageProcessor {
-    outgoing: mpsc::Sender<JSONRPCMessage>,
+    outgoing: Arc<OutgoingMessageSender>,
     initialized: bool,
     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>>>,
 }
 
 impl MessageProcessor {
     /// Create a new `MessageProcessor`, retaining a handle to the outgoing
     /// `Sender` so handlers can enqueue messages to be written to stdout.
     pub(crate) fn new(
-        outgoing: mpsc::Sender<JSONRPCMessage>,
+        outgoing: OutgoingMessageSender,
         codex_linux_sandbox_exe: Option<PathBuf>,
     ) -> Self {
         Self {
-            outgoing,
+            outgoing: Arc::new(outgoing),
             initialized: false,
             codex_linux_sandbox_exe,
+            session_map: Arc::new(Mutex::new(HashMap::new())),
+            running_requests_id_to_codex_uuid: Arc::new(Mutex::new(HashMap::new())),
         }
     }
 
-    pub(crate) fn process_request(&mut self, request: JSONRPCRequest) {
+    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();
 
@@ -62,10 +70,10 @@ impl MessageProcessor {
         // Dispatch to a dedicated handler for each request type.
         match client_request {
             ClientRequest::InitializeRequest(params) => {
-                self.handle_initialize(request_id, params);
+                self.handle_initialize(request_id, params).await;
             }
             ClientRequest::PingRequest(params) => {
-                self.handle_ping(request_id, params);
+                self.handle_ping(request_id, params).await;
             }
             ClientRequest::ListResourcesRequest(params) => {
                 self.handle_list_resources(params);
@@ -89,10 +97,10 @@ impl MessageProcessor {
                 self.handle_get_prompt(params);
             }
             ClientRequest::ListToolsRequest(params) => {
-                self.handle_list_tools(request_id, params);
+                self.handle_list_tools(request_id, params).await;
             }
             ClientRequest::CallToolRequest(params) => {
-                self.handle_call_tool(request_id, params);
+                self.handle_call_tool(request_id, params).await;
             }
             ClientRequest::SetLevelRequest(params) => {
                 self.handle_set_level(params);
@@ -104,12 +112,14 @@ impl MessageProcessor {
     }
 
     /// Handle a standalone JSON-RPC response originating from the peer.
-    pub(crate) fn process_response(&mut self, response: JSONRPCResponse) {
+    pub(crate) async fn process_response(&mut self, response: JSONRPCResponse) {
         tracing::info!("<- response: {:?}", response);
+        let JSONRPCResponse { id, result, .. } = response;
+        self.outgoing.notify_client_response(id, result).await
     }
 
     /// Handle a fire-and-forget JSON-RPC notification.
-    pub(crate) fn process_notification(&mut self, notification: JSONRPCNotification) {
+    pub(crate) async fn process_notification(&mut self, notification: JSONRPCNotification) {
         let server_notification = match ServerNotification::try_from(notification) {
             Ok(n) => n,
             Err(e) => {
@@ -122,7 +132,7 @@ impl MessageProcessor {
         // handler so additional logic can be implemented incrementally.
         match server_notification {
             ServerNotification::CancelledNotification(params) => {
-                self.handle_cancelled_notification(params);
+                self.handle_cancelled_notification(params).await;
             }
             ServerNotification::ProgressNotification(params) => {
                 self.handle_progress_notification(params);
@@ -145,42 +155,12 @@ impl MessageProcessor {
         }
     }
 
-    /// Handle a batch of requests and/or notifications.
-    pub(crate) fn process_batch_request(&mut self, batch: JSONRPCBatchRequest) {
-        tracing::info!("<- batch request containing {} item(s)", batch.len());
-        for item in batch {
-            match item {
-                mcp_types::JSONRPCBatchRequestItem::JSONRPCRequest(req) => {
-                    self.process_request(req);
-                }
-                mcp_types::JSONRPCBatchRequestItem::JSONRPCNotification(note) => {
-                    self.process_notification(note);
-                }
-            }
-        }
-    }
-
     /// Handle an error object received from the peer.
     pub(crate) fn process_error(&mut self, err: JSONRPCError) {
         tracing::error!("<- error: {:?}", err);
     }
 
-    /// Handle a batch of responses/errors.
-    pub(crate) fn process_batch_response(&mut self, batch: JSONRPCBatchResponse) {
-        tracing::info!("<- batch response containing {} item(s)", batch.len());
-        for item in batch {
-            match item {
-                mcp_types::JSONRPCBatchResponseItem::JSONRPCResponse(resp) => {
-                    self.process_response(resp);
-                }
-                mcp_types::JSONRPCBatchResponseItem::JSONRPCError(err) => {
-                    self.process_error(err);
-                }
-            }
-        }
-    }
-
-    fn handle_initialize(
+    async fn handle_initialize(
         &mut self,
         id: RequestId,
         params: <mcp_types::InitializeRequest as ModelContextProtocolRequest>::Params,
@@ -189,19 +169,12 @@ impl MessageProcessor {
 
         if self.initialized {
             // Already initialised: send JSON-RPC error response.
-            let error_msg = JSONRPCMessage::Error(JSONRPCError {
-                jsonrpc: JSONRPC_VERSION.into(),
-                id,
-                error: JSONRPCErrorError {
-                    code: -32600, // Invalid Request
-                    message: "initialize called more than once".to_string(),
-                    data: None,
-                },
-            });
-
-            if let Err(e) = self.outgoing.try_send(error_msg) {
-                tracing::error!("Failed to send initialization error: {e}");
-            }
+            let error = JSONRPCErrorError {
+                code: -32600, // Invalid Request
+                message: "initialize called more than once".to_string(),
+                data: None,
+            };
+            self.outgoing.send_error(id, error).await;
             return;
         }
 
@@ -223,38 +196,34 @@ impl MessageProcessor {
             protocol_version: params.protocol_version.clone(),
             server_info: mcp_types::Implementation {
                 name: "codex-mcp-server".to_string(),
-                version: mcp_types::MCP_SCHEMA_VERSION.to_string(),
+                version: env!("CARGO_PKG_VERSION").to_string(),
+                title: Some("Codex".to_string()),
             },
         };
 
-        self.send_response::<mcp_types::InitializeRequest>(id, result);
+        self.send_response::<mcp_types::InitializeRequest>(id, result)
+            .await;
     }
 
-    fn send_response<T>(&self, id: RequestId, result: T::Result)
+    async fn send_response<T>(&self, id: RequestId, result: T::Result)
     where
         T: ModelContextProtocolRequest,
     {
         // result has `Serialized` instance so should never fail
         #[expect(clippy::unwrap_used)]
-        let response = JSONRPCMessage::Response(JSONRPCResponse {
-            jsonrpc: JSONRPC_VERSION.into(),
-            id,
-            result: serde_json::to_value(result).unwrap(),
-        });
-
-        if let Err(e) = self.outgoing.try_send(response) {
-            tracing::error!("Failed to send response: {e}");
-        }
+        let result = serde_json::to_value(result).unwrap();
+        self.outgoing.send_response(id, result).await;
     }
 
-    fn handle_ping(
+    async fn handle_ping(
         &self,
         id: RequestId,
         params: <mcp_types::PingRequest as mcp_types::ModelContextProtocolRequest>::Params,
     ) {
         tracing::info!("ping -> params: {:?}", params);
         let result = json!({});
-        self.send_response::<mcp_types::PingRequest>(id, result);
+        self.send_response::<mcp_types::PingRequest>(id, result)
+            .await;
     }
 
     fn handle_list_resources(
@@ -307,21 +276,25 @@ impl MessageProcessor {
         tracing::info!("prompts/get -> params: {:?}", params);
     }
 
-    fn handle_list_tools(
+    async fn handle_list_tools(
         &self,
         id: RequestId,
         params: <mcp_types::ListToolsRequest as mcp_types::ModelContextProtocolRequest>::Params,
     ) {
         tracing::trace!("tools/list -> {params:?}");
         let result = ListToolsResult {
-            tools: vec![create_tool_for_codex_tool_call_param()],
+            tools: vec![
+                create_tool_for_codex_tool_call_param(),
+                create_tool_for_codex_tool_call_reply_param(),
+            ],
             next_cursor: None,
         };
 
-        self.send_response::<mcp_types::ListToolsRequest>(id, result);
+        self.send_response::<mcp_types::ListToolsRequest>(id, result)
+            .await;
     }
 
-    fn handle_call_tool(
+    async fn handle_call_tool(
         &self,
         id: RequestId,
         params: <mcp_types::CallToolRequest as mcp_types::ModelContextProtocolRequest>::Params,
@@ -329,28 +302,36 @@ impl MessageProcessor {
         tracing::info!("tools/call -> params: {:?}", params);
         let CallToolRequestParams { name, arguments } = params;
 
-        // We only support the "codex" tool for now.
-        if name != "codex" {
-            // Tool not found – return error result so the LLM can react.
-            let result = CallToolResult {
-                content: vec![CallToolResultContent::TextContent(TextContent {
-                    r#type: "text".to_string(),
-                    text: format!("Unknown tool '{name}'"),
-                    annotations: None,
-                })],
-                is_error: Some(true),
-            };
-            self.send_response::<mcp_types::CallToolRequest>(id, result);
-            return;
+        match name.as_str() {
+            "codex" => self.handle_tool_call_codex(id, arguments).await,
+            "codex-reply" => {
+                self.handle_tool_call_codex_session_reply(id, arguments)
+                    .await
+            }
+            _ => {
+                let result = CallToolResult {
+                    content: vec![ContentBlock::TextContent(TextContent {
+                        r#type: "text".to_string(),
+                        text: format!("Unknown tool '{name}'"),
+                        annotations: None,
+                    })],
+                    is_error: Some(true),
+                    structured_content: None,
+                };
+                self.send_response::<mcp_types::CallToolRequest>(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 {
             Some(json_val) => match serde_json::from_value::<CodexToolCallParam>(json_val) {
                 Ok(tool_cfg) => match tool_cfg.into_config(self.codex_linux_sandbox_exe.clone()) {
                     Ok(cfg) => cfg,
                     Err(e) => {
                         let result = CallToolResult {
-                            content: vec![CallToolResultContent::TextContent(TextContent {
+                            content: vec![ContentBlock::TextContent(TextContent {
                                 r#type: "text".to_owned(),
                                 text: format!(
                                     "Failed to load Codex configuration from overrides: {e}"
@@ -358,27 +339,31 @@ impl MessageProcessor {
                                 annotations: None,
                             })],
                             is_error: Some(true),
+                            structured_content: None,
                         };
-                        self.send_response::<mcp_types::CallToolRequest>(id, result);
+                        self.send_response::<mcp_types::CallToolRequest>(id, result)
+                            .await;
                         return;
                     }
                 },
                 Err(e) => {
                     let result = CallToolResult {
-                        content: vec![CallToolResultContent::TextContent(TextContent {
+                        content: vec![ContentBlock::TextContent(TextContent {
                             r#type: "text".to_owned(),
                             text: format!("Failed to parse configuration for Codex tool: {e}"),
                             annotations: None,
                         })],
                         is_error: Some(true),
+                        structured_content: None,
                     };
-                    self.send_response::<mcp_types::CallToolRequest>(id, result);
+                    self.send_response::<mcp_types::CallToolRequest>(id, result)
+                        .await;
                     return;
                 }
             },
             None => {
                 let result = CallToolResult {
-                    content: vec![CallToolResultContent::TextContent(TextContent {
+                    content: vec![ContentBlock::TextContent(TextContent {
                         r#type: "text".to_string(),
                         text:
                             "Missing arguments for codex tool-call; the `prompt` field is required."
@@ -386,21 +371,147 @@ impl MessageProcessor {
                         annotations: None,
                     })],
                     is_error: Some(true),
+                    structured_content: None,
                 };
-                self.send_response::<mcp_types::CallToolRequest>(id, result);
+                self.send_response::<mcp_types::CallToolRequest>(id, result)
+                    .await;
                 return;
             }
         };
 
-        // Clone outgoing sender to move into async task.
+        // Clone outgoing and session map to move into async task.
         let outgoing = self.outgoing.clone();
+        let session_map = self.session_map.clone();
+        let running_requests_id_to_codex_uuid = self.running_requests_id_to_codex_uuid.clone();
 
         // Spawn an async task to handle the Codex session so that we do not
         // block the synchronous message-processing loop.
         task::spawn(async move {
             // Run the Codex session and stream events back to the client.
-            crate::codex_tool_runner::run_codex_tool_session(id, initial_prompt, config, outgoing)
+            crate::codex_tool_runner::run_codex_tool_session(
+                id,
+                initial_prompt,
+                config,
+                outgoing,
+                session_map,
+                running_requests_id_to_codex_uuid,
+            )
+            .await;
+        });
+    }
+
+    async fn handle_tool_call_codex_session_reply(
+        &self,
+        request_id: RequestId,
+        arguments: Option<serde_json::Value>,
+    ) {
+        tracing::info!("tools/call -> params: {:?}", arguments);
+
+        // parse arguments
+        let CodexToolCallReplyParam { session_id, prompt } = match arguments {
+            Some(json_val) => match serde_json::from_value::<CodexToolCallReplyParam>(json_val) {
+                Ok(params) => params,
+                Err(e) => {
+                    tracing::error!("Failed to parse Codex tool call reply parameters: {e}");
+                    let result = CallToolResult {
+                        content: vec![ContentBlock::TextContent(TextContent {
+                            r#type: "text".to_owned(),
+                            text: format!("Failed to parse configuration for Codex tool: {e}"),
+                            annotations: None,
+                        })],
+                        is_error: Some(true),
+                        structured_content: None,
+                    };
+                    self.send_response::<mcp_types::CallToolRequest>(request_id, result)
+                        .await;
+                    return;
+                }
+            },
+            None => {
+                tracing::error!(
+                    "Missing arguments for codex-reply tool-call; the `session_id` and `prompt` fields are required."
+                );
+                let result = CallToolResult {
+                    content: vec![ContentBlock::TextContent(TextContent {
+                        r#type: "text".to_owned(),
+                        text: "Missing arguments for codex-reply tool-call; the `session_id` and `prompt` fields are required.".to_owned(),
+                        annotations: None,
+                    })],
+                    is_error: Some(true),
+                    structured_content: None,
+                };
+                self.send_response::<mcp_types::CallToolRequest>(request_id, result)
+                    .await;
+                return;
+            }
+        };
+        let session_id = match Uuid::parse_str(&session_id) {
+            Ok(id) => id,
+            Err(e) => {
+                tracing::error!("Failed to parse session_id: {e}");
+                let result = CallToolResult {
+                    content: vec![ContentBlock::TextContent(TextContent {
+                        r#type: "text".to_owned(),
+                        text: format!("Failed to parse session_id: {e}"),
+                        annotations: None,
+                    })],
+                    is_error: Some(true),
+                    structured_content: None,
+                };
+                self.send_response::<mcp_types::CallToolRequest>(request_id, result)
+                    .await;
+                return;
+            }
+        };
+
+        // load codex from session map
+        let session_map_mutex = Arc::clone(&self.session_map);
+
+        // Clone outgoing and session map to move into async task.
+        let outgoing = self.outgoing.clone();
+        let running_requests_id_to_codex_uuid = self.running_requests_id_to_codex_uuid.clone();
+
+        let codex = {
+            let session_map = session_map_mutex.lock().await;
+            match session_map.get(&session_id).cloned() {
+                Some(c) => c,
+                None => {
+                    tracing::warn!("Session not found for session_id: {session_id}");
+                    let result = CallToolResult {
+                        content: vec![ContentBlock::TextContent(TextContent {
+                            r#type: "text".to_owned(),
+                            text: format!("Session not found for session_id: {session_id}"),
+                            annotations: None,
+                        })],
+                        is_error: Some(true),
+                        structured_content: None,
+                    };
+                    outgoing
+                        .send_response(request_id, serde_json::to_value(result).unwrap_or_default())
+                        .await;
+                    return;
+                }
+            }
+        };
+
+        // Spawn the long-running reply handler.
+        tokio::spawn({
+            let codex = codex.clone();
+            let outgoing = outgoing.clone();
+            let prompt = prompt.clone();
+            let running_requests_id_to_codex_uuid = running_requests_id_to_codex_uuid.clone();
+
+            async move {
+                crate::codex_tool_runner::run_codex_tool_session_reply(
+                    codex,
+                    outgoing,
+                    request_id,
+                    prompt,
+                    running_requests_id_to_codex_uuid,
+                    session_id,
+                )
                 .await;
+            }
         });
     }
 
@@ -422,11 +533,58 @@ impl MessageProcessor {
     // Notification handlers
     // ---------------------------------------------------------------------
 
-    fn handle_cancelled_notification(
+    async fn handle_cancelled_notification(
         &self,
         params: <mcp_types::CancelledNotification as mcp_types::ModelContextProtocolNotification>::Params,
     ) {
-        tracing::info!("notifications/cancelled -> params: {:?}", params);
+        let request_id = params.request_id;
+        // Create a stable string form early for logging and submission id.
+        let request_id_string = match &request_id {
+            RequestId::String(s) => s.clone(),
+            RequestId::Integer(i) => i.to_string(),
+        };
+
+        // Obtain the session_id while holding the first lock, then release.
+        let session_id = {
+            let map_guard = self.running_requests_id_to_codex_uuid.lock().await;
+            match map_guard.get(&request_id) {
+                Some(id) => *id, // Uuid is Copy
+                None => {
+                    tracing::warn!("Session not found for request_id: {}", request_id_string);
+                    return;
+                }
+            }
+        };
+        tracing::info!("session_id: {session_id}");
+
+        // Obtain the Codex Arc while holding the session_map lock, then release.
+        let codex_arc = {
+            let sessions_guard = self.session_map.lock().await;
+            match sessions_guard.get(&session_id) {
+                Some(codex) => Arc::clone(codex),
+                None => {
+                    tracing::warn!("Session not found for session_id: {session_id}");
+                    return;
+                }
+            }
+        };
+
+        // Submit interrupt to Codex.
+        let err = codex_arc
+            .submit_with_id(Submission {
+                id: request_id_string,
+                op: codex_core::protocol::Op::Interrupt,
+            })
+            .await;
+        if let Err(e) = err {
+            tracing::error!("Failed to submit interrupt to Codex: {e}");
+            return;
+        }
+        // unregister the id so we don't keep it in the map
+        self.running_requests_id_to_codex_uuid
+            .lock()
+            .await
+            .remove(&request_id);
     }
 
     fn handle_progress_notification(

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

@@ -0,0 +1,331 @@
+use std::collections::HashMap;
+use std::sync::atomic::AtomicI64;
+use std::sync::atomic::Ordering;
+
+use codex_core::protocol::Event;
+use mcp_types::JSONRPC_VERSION;
+use mcp_types::JSONRPCError;
+use mcp_types::JSONRPCErrorError;
+use mcp_types::JSONRPCMessage;
+use mcp_types::JSONRPCNotification;
+use mcp_types::JSONRPCRequest;
+use mcp_types::JSONRPCResponse;
+use mcp_types::RequestId;
+use mcp_types::Result;
+use serde::Serialize;
+use tokio::sync::Mutex;
+use tokio::sync::mpsc;
+use tokio::sync::oneshot;
+use tracing::warn;
+
+/// Sends messages to the client and manages request callbacks.
+pub(crate) struct OutgoingMessageSender {
+    next_request_id: AtomicI64,
+    sender: mpsc::Sender<OutgoingMessage>,
+    request_id_to_callback: Mutex<HashMap<RequestId, oneshot::Sender<Result>>>,
+}
+
+impl OutgoingMessageSender {
+    pub(crate) fn new(sender: mpsc::Sender<OutgoingMessage>) -> Self {
+        Self {
+            next_request_id: AtomicI64::new(0),
+            sender,
+            request_id_to_callback: Mutex::new(HashMap::new()),
+        }
+    }
+
+    pub(crate) async fn send_request(
+        &self,
+        method: &str,
+        params: Option<serde_json::Value>,
+    ) -> oneshot::Receiver<Result> {
+        let id = RequestId::Integer(self.next_request_id.fetch_add(1, Ordering::Relaxed));
+        let outgoing_message_id = id.clone();
+        let (tx_approve, rx_approve) = oneshot::channel();
+        {
+            let mut request_id_to_callback = self.request_id_to_callback.lock().await;
+            request_id_to_callback.insert(id, tx_approve);
+        }
+
+        let outgoing_message = OutgoingMessage::Request(OutgoingRequest {
+            id: outgoing_message_id,
+            method: method.to_string(),
+            params,
+        });
+        let _ = self.sender.send(outgoing_message).await;
+        rx_approve
+    }
+
+    pub(crate) async fn notify_client_response(&self, id: RequestId, result: Result) {
+        let entry = {
+            let mut request_id_to_callback = self.request_id_to_callback.lock().await;
+            request_id_to_callback.remove_entry(&id)
+        };
+
+        match entry {
+            Some((id, sender)) => {
+                if let Err(err) = sender.send(result) {
+                    warn!("could not notify callback for {id:?} due to: {err:?}");
+                }
+            }
+            None => {
+                warn!("could not find callback for {id:?}");
+            }
+        }
+    }
+
+    pub(crate) async fn send_response(&self, id: RequestId, result: Result) {
+        let outgoing_message = OutgoingMessage::Response(OutgoingResponse { id, result });
+        let _ = self.sender.send(outgoing_message).await;
+    }
+
+    pub(crate) async fn send_event_as_notification(
+        &self,
+        event: &Event,
+        meta: Option<OutgoingNotificationMeta>,
+    ) {
+        #[allow(clippy::expect_used)]
+        let event_json = serde_json::to_value(event).expect("Event must serialize");
+
+        let params = if let Ok(params) = serde_json::to_value(OutgoingNotificationParams {
+            meta,
+            event: event_json.clone(),
+        }) {
+            params
+        } else {
+            warn!("Failed to serialize event as OutgoingNotificationParams");
+            event_json
+        };
+
+        let outgoing_message = OutgoingMessage::Notification(OutgoingNotification {
+            method: "codex/event".to_string(),
+            params: Some(params.clone()),
+        });
+        let _ = self.sender.send(outgoing_message).await;
+
+        self.send_event_as_notification_new_schema(event, Some(params.clone()))
+            .await;
+    }
+
+    // should be backwards compatible.
+    // it will replace send_event_as_notification eventually.
+    async fn send_event_as_notification_new_schema(
+        &self,
+        event: &Event,
+        params: Option<serde_json::Value>,
+    ) {
+        let outgoing_message = OutgoingMessage::Notification(OutgoingNotification {
+            method: event.msg.to_string(),
+            params,
+        });
+        let _ = self.sender.send(outgoing_message).await;
+    }
+    pub(crate) async fn send_error(&self, id: RequestId, error: JSONRPCErrorError) {
+        let outgoing_message = OutgoingMessage::Error(OutgoingError { id, error });
+        let _ = self.sender.send(outgoing_message).await;
+    }
+}
+
+/// Outgoing message from the server to the client.
+pub(crate) enum OutgoingMessage {
+    Request(OutgoingRequest),
+    Notification(OutgoingNotification),
+    Response(OutgoingResponse),
+    Error(OutgoingError),
+}
+
+impl From<OutgoingMessage> for JSONRPCMessage {
+    fn from(val: OutgoingMessage) -> Self {
+        use OutgoingMessage::*;
+        match val {
+            Request(OutgoingRequest { id, method, params }) => {
+                JSONRPCMessage::Request(JSONRPCRequest {
+                    jsonrpc: JSONRPC_VERSION.into(),
+                    id,
+                    method,
+                    params,
+                })
+            }
+            Notification(OutgoingNotification { method, params }) => {
+                JSONRPCMessage::Notification(JSONRPCNotification {
+                    jsonrpc: JSONRPC_VERSION.into(),
+                    method,
+                    params,
+                })
+            }
+            Response(OutgoingResponse { id, result }) => {
+                JSONRPCMessage::Response(JSONRPCResponse {
+                    jsonrpc: JSONRPC_VERSION.into(),
+                    id,
+                    result,
+                })
+            }
+            Error(OutgoingError { id, error }) => JSONRPCMessage::Error(JSONRPCError {
+                jsonrpc: JSONRPC_VERSION.into(),
+                id,
+                error,
+            }),
+        }
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Serialize)]
+pub(crate) struct OutgoingRequest {
+    pub id: RequestId,
+    pub method: String,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub params: Option<serde_json::Value>,
+}
+
+#[derive(Debug, Clone, PartialEq, Serialize)]
+pub(crate) struct OutgoingNotification {
+    pub method: String,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub params: Option<serde_json::Value>,
+}
+
+#[derive(Debug, Clone, PartialEq, Serialize)]
+pub(crate) struct OutgoingNotificationParams {
+    #[serde(rename = "_meta", default, skip_serializing_if = "Option::is_none")]
+    pub meta: Option<OutgoingNotificationMeta>,
+
+    #[serde(flatten)]
+    pub event: serde_json::Value,
+}
+
+// Additional mcp-specific data to be added to a [`codex_core::protocol::Event`] as notification.params._meta
+// MCP Spec: https://modelcontextprotocol.io/specification/2025-06-18/basic#meta
+// Typescript Schema: https://github.com/modelcontextprotocol/modelcontextprotocol/blob/0695a497eb50a804fc0e88c18a93a21a675d6b3e/schema/2025-06-18/schema.ts
+#[derive(Debug, Clone, PartialEq, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub(crate) struct OutgoingNotificationMeta {
+    pub request_id: Option<RequestId>,
+}
+
+impl OutgoingNotificationMeta {
+    pub(crate) fn new(request_id: Option<RequestId>) -> Self {
+        Self { request_id }
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Serialize)]
+pub(crate) struct OutgoingResponse {
+    pub id: RequestId,
+    pub result: Result,
+}
+
+#[derive(Debug, Clone, PartialEq, Serialize)]
+pub(crate) struct OutgoingError {
+    pub error: JSONRPCErrorError,
+    pub id: RequestId,
+}
+
+#[cfg(test)]
+mod tests {
+    #![allow(clippy::unwrap_used)]
+
+    use codex_core::protocol::EventMsg;
+    use codex_core::protocol::SessionConfiguredEvent;
+    use pretty_assertions::assert_eq;
+    use serde_json::json;
+    use uuid::Uuid;
+
+    use super::*;
+
+    #[tokio::test]
+    async fn test_send_event_as_notification() {
+        let (outgoing_tx, mut outgoing_rx) = mpsc::channel::<OutgoingMessage>(2);
+        let outgoing_message_sender = OutgoingMessageSender::new(outgoing_tx);
+
+        let event = Event {
+            id: "1".to_string(),
+            msg: EventMsg::SessionConfigured(SessionConfiguredEvent {
+                session_id: Uuid::new_v4(),
+                model: "gpt-4o".to_string(),
+                history_log_id: 1,
+                history_entry_count: 1000,
+            }),
+        };
+
+        outgoing_message_sender
+            .send_event_as_notification(&event, None)
+            .await;
+
+        let result = outgoing_rx.recv().await.unwrap();
+        let OutgoingMessage::Notification(OutgoingNotification { method, params }) = result else {
+            panic!("expected Notification for first message");
+        };
+        assert_eq!(method, "codex/event");
+
+        let Ok(expected_params) = serde_json::to_value(&event) else {
+            panic!("Event must serialize");
+        };
+        assert_eq!(params, Some(expected_params.clone()));
+
+        let result2 = outgoing_rx.recv().await.unwrap();
+        let OutgoingMessage::Notification(OutgoingNotification {
+            method: method2,
+            params: params2,
+        }) = result2
+        else {
+            panic!("expected Notification for second message");
+        };
+        assert_eq!(method2, event.msg.to_string());
+        assert_eq!(params2, Some(expected_params));
+    }
+
+    #[tokio::test]
+    async fn test_send_event_as_notification_with_meta() {
+        let (outgoing_tx, mut outgoing_rx) = mpsc::channel::<OutgoingMessage>(2);
+        let outgoing_message_sender = OutgoingMessageSender::new(outgoing_tx);
+
+        let session_configured_event = SessionConfiguredEvent {
+            session_id: Uuid::new_v4(),
+            model: "gpt-4o".to_string(),
+            history_log_id: 1,
+            history_entry_count: 1000,
+        };
+        let event = Event {
+            id: "1".to_string(),
+            msg: EventMsg::SessionConfigured(session_configured_event.clone()),
+        };
+        let meta = OutgoingNotificationMeta {
+            request_id: Some(RequestId::String("123".to_string())),
+        };
+
+        outgoing_message_sender
+            .send_event_as_notification(&event, Some(meta))
+            .await;
+
+        let result = outgoing_rx.recv().await.unwrap();
+        let OutgoingMessage::Notification(OutgoingNotification { method, params }) = result else {
+            panic!("expected Notification for first message");
+        };
+        assert_eq!(method, "codex/event");
+        let expected_params = json!({
+            "_meta": {
+                "requestId": "123",
+            },
+            "id": "1",
+            "msg": {
+                "session_id": session_configured_event.session_id,
+                "model": session_configured_event.model,
+                "history_log_id": session_configured_event.history_log_id,
+                "history_entry_count": session_configured_event.history_entry_count,
+                "type": "session_configured",
+            }
+        });
+        assert_eq!(params.unwrap(), expected_params);
+
+        let result2 = outgoing_rx.recv().await.unwrap();
+        let OutgoingMessage::Notification(OutgoingNotification {
+            method: method2,
+            params: params2,
+        }) = result2
+        else {
+            panic!("expected Notification for second message");
+        };
+        assert_eq!(method2, event.msg.to_string());
+        assert_eq!(params2.unwrap(), expected_params);
+    }
+}

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

@@ -0,0 +1,150 @@
+use std::collections::HashMap;
+use std::path::PathBuf;
+use std::sync::Arc;
+
+use codex_core::Codex;
+use codex_core::protocol::FileChange;
+use codex_core::protocol::Op;
+use codex_core::protocol::ReviewDecision;
+use mcp_types::ElicitRequest;
+use mcp_types::ElicitRequestParamsRequestedSchema;
+use mcp_types::JSONRPCErrorError;
+use mcp_types::ModelContextProtocolRequest;
+use mcp_types::RequestId;
+use serde::Deserialize;
+use serde::Serialize;
+use serde_json::json;
+use tracing::error;
+
+use crate::codex_tool_runner::INVALID_PARAMS_ERROR_CODE;
+use crate::outgoing_message::OutgoingMessageSender;
+
+#[derive(Debug, Serialize)]
+pub struct PatchApprovalElicitRequestParams {
+    pub message: String,
+    #[serde(rename = "requestedSchema")]
+    pub requested_schema: ElicitRequestParamsRequestedSchema,
+    pub codex_elicitation: String,
+    pub codex_mcp_tool_call_id: String,
+    pub codex_event_id: String,
+    pub codex_call_id: String,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub codex_reason: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub codex_grant_root: Option<PathBuf>,
+    pub codex_changes: HashMap<PathBuf, FileChange>,
+}
+
+#[derive(Debug, Deserialize, Serialize)]
+pub struct PatchApprovalResponse {
+    pub decision: ReviewDecision,
+}
+
+#[allow(clippy::too_many_arguments)]
+pub(crate) async fn handle_patch_approval_request(
+    call_id: String,
+    reason: Option<String>,
+    grant_root: Option<PathBuf>,
+    changes: HashMap<PathBuf, FileChange>,
+    outgoing: Arc<OutgoingMessageSender>,
+    codex: Arc<Codex>,
+    request_id: RequestId,
+    tool_call_id: String,
+    event_id: String,
+) {
+    let mut message_lines = Vec::new();
+    if let Some(r) = &reason {
+        message_lines.push(r.clone());
+    }
+    message_lines.push("Allow Codex to apply proposed code changes?".to_string());
+
+    let params = PatchApprovalElicitRequestParams {
+        message: message_lines.join("\n"),
+        requested_schema: ElicitRequestParamsRequestedSchema {
+            r#type: "object".to_string(),
+            properties: json!({}),
+            required: None,
+        },
+        codex_elicitation: "patch-approval".to_string(),
+        codex_mcp_tool_call_id: tool_call_id.clone(),
+        codex_event_id: event_id.clone(),
+        codex_call_id: call_id,
+        codex_reason: reason,
+        codex_grant_root: grant_root,
+        codex_changes: changes,
+    };
+    let params_json = match serde_json::to_value(&params) {
+        Ok(value) => value,
+        Err(err) => {
+            let message = format!("Failed to serialize PatchApprovalElicitRequestParams: {err}");
+            error!("{message}");
+
+            outgoing
+                .send_error(
+                    request_id.clone(),
+                    JSONRPCErrorError {
+                        code: INVALID_PARAMS_ERROR_CODE,
+                        message,
+                        data: None,
+                    },
+                )
+                .await;
+
+            return;
+        }
+    };
+
+    let on_response = outgoing
+        .send_request(ElicitRequest::METHOD, Some(params_json))
+        .await;
+
+    // Listen for the response on a separate task so we don't block the main agent loop.
+    {
+        let codex = codex.clone();
+        let event_id = event_id.clone();
+        tokio::spawn(async move {
+            on_patch_approval_response(event_id, on_response, codex).await;
+        });
+    }
+}
+
+pub(crate) async fn on_patch_approval_response(
+    event_id: String,
+    receiver: tokio::sync::oneshot::Receiver<mcp_types::Result>,
+    codex: Arc<Codex>,
+) {
+    let response = receiver.await;
+    let value = match response {
+        Ok(value) => value,
+        Err(err) => {
+            error!("request failed: {err:?}");
+            if let Err(submit_err) = codex
+                .submit(Op::PatchApproval {
+                    id: event_id.clone(),
+                    decision: ReviewDecision::Denied,
+                })
+                .await
+            {
+                error!("failed to submit denied PatchApproval after request failure: {submit_err}");
+            }
+            return;
+        }
+    };
+
+    let response = serde_json::from_value::<PatchApprovalResponse>(value).unwrap_or_else(|err| {
+        error!("failed to deserialize PatchApprovalResponse: {err}");
+        PatchApprovalResponse {
+            decision: ReviewDecision::Denied,
+        }
+    });
+
+    if let Err(err) = codex
+        .submit(Op::PatchApproval {
+            id: event_id,
+            decision: response.decision,
+        })
+        .await
+    {
+        error!("failed to submit PatchApproval: {err}");
+    }
+}

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

@@ -0,0 +1,440 @@
+use std::collections::HashMap;
+use std::env;
+use std::path::Path;
+use std::path::PathBuf;
+
+use codex_core::exec::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
+use codex_core::protocol::FileChange;
+use codex_core::protocol::ReviewDecision;
+use codex_mcp_server::CodexToolCallParam;
+use codex_mcp_server::ExecApprovalElicitRequestParams;
+use codex_mcp_server::ExecApprovalResponse;
+use codex_mcp_server::PatchApprovalElicitRequestParams;
+use codex_mcp_server::PatchApprovalResponse;
+use mcp_types::ElicitRequest;
+use mcp_types::ElicitRequestParamsRequestedSchema;
+use mcp_types::JSONRPC_VERSION;
+use mcp_types::JSONRPCRequest;
+use mcp_types::JSONRPCResponse;
+use mcp_types::ModelContextProtocolRequest;
+use mcp_types::RequestId;
+use pretty_assertions::assert_eq;
+use serde_json::json;
+use tempfile::TempDir;
+use tokio::time::timeout;
+use wiremock::MockServer;
+
+use mcp_test_support::McpProcess;
+use mcp_test_support::create_apply_patch_sse_response;
+use mcp_test_support::create_final_assistant_message_sse_response;
+use mcp_test_support::create_mock_chat_completions_server;
+use mcp_test_support::create_shell_sse_response;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+/// Test that a shell command that is not on the "trusted" list triggers an
+/// elicitation request to the MCP and that sending the approval runs the
+/// command, as expected.
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn test_shell_command_approval_triggers_elicitation() {
+    if 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;
+    }
+
+    // Apparently `#[tokio::test]` must return `()`, so we create a helper
+    // function that returns `Result` so we can use `?` in favor of `unwrap`.
+    if let Err(err) = shell_command_approval_triggers_elicitation().await {
+        panic!("failure: {err}");
+    }
+}
+
+async fn shell_command_approval_triggers_elicitation() -> anyhow::Result<()> {
+    // We use `git init` because it will not be on the "trusted" list.
+    let shell_command = vec!["git".to_string(), "init".to_string()];
+    let workdir_for_shell_function_call = TempDir::new()?;
+
+    let McpHandle {
+        process: mut mcp_process,
+        server: _server,
+        dir: _dir,
+    } = create_mcp_process(vec![
+        create_shell_sse_response(
+            shell_command.clone(),
+            Some(workdir_for_shell_function_call.path()),
+            Some(5_000),
+            "call1234",
+        )?,
+        create_final_assistant_message_sse_response("Enjoy your new git repo!")?,
+    ])
+    .await?;
+
+    // Send a "codex" tool request, which should hit the completions endpoint.
+    // In turn, it should reply with a tool call, which the MCP should forward
+    // as an elicitation.
+    let codex_request_id = mcp_process
+        .send_codex_tool_call(CodexToolCallParam {
+            prompt: "run `git init`".to_string(),
+            ..Default::default()
+        })
+        .await?;
+    let elicitation_request = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp_process.read_stream_until_request_message(),
+    )
+    .await??;
+
+    // This is the first request from the server, so the id should be 0 given
+    // how things are currently implemented.
+    let elicitation_request_id = RequestId::Integer(0);
+    let expected_elicitation_request = create_expected_elicitation_request(
+        elicitation_request_id.clone(),
+        shell_command.clone(),
+        workdir_for_shell_function_call.path(),
+        codex_request_id.to_string(),
+        // Internal Codex id: empirically it is 1, but this is
+        // admittedly an internal detail that could change.
+        "1".to_string(),
+    )?;
+    assert_eq!(expected_elicitation_request, elicitation_request);
+
+    // Accept the `git init` request by responding to the elicitation.
+    mcp_process
+        .send_response(
+            elicitation_request_id,
+            serde_json::to_value(ExecApprovalResponse {
+                decision: ReviewDecision::Approved,
+            })?,
+        )
+        .await?;
+
+    // Verify the original `codex` tool call completes and that `git init` ran
+    // successfully.
+    let codex_response = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp_process.read_stream_until_response_message(RequestId::Integer(codex_request_id)),
+    )
+    .await??;
+    assert_eq!(
+        JSONRPCResponse {
+            jsonrpc: JSONRPC_VERSION.into(),
+            id: RequestId::Integer(codex_request_id),
+            result: json!({
+                "content": [
+                    {
+                        "text": "Enjoy your new git repo!",
+                        "type": "text"
+                    }
+                ]
+            }),
+        },
+        codex_response
+    );
+
+    assert!(
+        workdir_for_shell_function_call.path().join(".git").is_dir(),
+        ".git folder should have been created"
+    );
+
+    Ok(())
+}
+
+fn create_expected_elicitation_request(
+    elicitation_request_id: RequestId,
+    command: Vec<String>,
+    workdir: &Path,
+    codex_mcp_tool_call_id: String,
+    codex_event_id: String,
+) -> anyhow::Result<JSONRPCRequest> {
+    let expected_message = format!(
+        "Allow Codex to run `{}` in `{}`?",
+        shlex::try_join(command.iter().map(|s| s.as_ref()))?,
+        workdir.to_string_lossy()
+    );
+    Ok(JSONRPCRequest {
+        jsonrpc: JSONRPC_VERSION.into(),
+        id: elicitation_request_id,
+        method: ElicitRequest::METHOD.to_string(),
+        params: Some(serde_json::to_value(&ExecApprovalElicitRequestParams {
+            message: expected_message,
+            requested_schema: ElicitRequestParamsRequestedSchema {
+                r#type: "object".to_string(),
+                properties: json!({}),
+                required: None,
+            },
+            codex_elicitation: "exec-approval".to_string(),
+            codex_mcp_tool_call_id,
+            codex_event_id,
+            codex_command: command,
+            codex_cwd: workdir.to_path_buf(),
+            codex_call_id: "call1234".to_string(),
+        })?),
+    })
+}
+
+/// Test that patch approval triggers an elicitation request to the MCP and that
+/// sending the approval applies the patch, as expected.
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn test_patch_approval_triggers_elicitation() {
+    if 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;
+    }
+
+    if let Err(err) = patch_approval_triggers_elicitation().await {
+        panic!("failure: {err}");
+    }
+}
+
+async fn patch_approval_triggers_elicitation() -> anyhow::Result<()> {
+    let cwd = TempDir::new()?;
+    let test_file = cwd.path().join("destination_file.txt");
+    std::fs::write(&test_file, "original content\n")?;
+
+    let patch_content = format!(
+        "*** Begin Patch\n*** Update File: {}\n-original content\n+modified content\n*** End Patch",
+        test_file.as_path().to_string_lossy()
+    );
+
+    let McpHandle {
+        process: mut mcp_process,
+        server: _server,
+        dir: _dir,
+    } = create_mcp_process(vec![
+        create_apply_patch_sse_response(&patch_content, "call1234")?,
+        create_final_assistant_message_sse_response("Patch has been applied successfully!")?,
+    ])
+    .await?;
+
+    // Send a "codex" tool request that will trigger the apply_patch command
+    let codex_request_id = mcp_process
+        .send_codex_tool_call(CodexToolCallParam {
+            cwd: Some(cwd.path().to_string_lossy().to_string()),
+            prompt: "please modify the test file".to_string(),
+            ..Default::default()
+        })
+        .await?;
+    let elicitation_request = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp_process.read_stream_until_request_message(),
+    )
+    .await??;
+
+    let elicitation_request_id = RequestId::Integer(0);
+
+    let mut expected_changes = HashMap::new();
+    expected_changes.insert(
+        test_file.as_path().to_path_buf(),
+        FileChange::Update {
+            unified_diff: "@@ -1 +1 @@\n-original content\n+modified content\n".to_string(),
+            move_path: None,
+        },
+    );
+
+    let expected_elicitation_request = create_expected_patch_approval_elicitation_request(
+        elicitation_request_id.clone(),
+        expected_changes,
+        None, // No grant_root expected
+        None, // No reason expected
+        codex_request_id.to_string(),
+        "1".to_string(),
+    )?;
+    assert_eq!(expected_elicitation_request, elicitation_request);
+
+    // Accept the patch approval request by responding to the elicitation
+    mcp_process
+        .send_response(
+            elicitation_request_id,
+            serde_json::to_value(PatchApprovalResponse {
+                decision: ReviewDecision::Approved,
+            })?,
+        )
+        .await?;
+
+    // Verify the original `codex` tool call completes
+    let codex_response = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp_process.read_stream_until_response_message(RequestId::Integer(codex_request_id)),
+    )
+    .await??;
+    assert_eq!(
+        JSONRPCResponse {
+            jsonrpc: JSONRPC_VERSION.into(),
+            id: RequestId::Integer(codex_request_id),
+            result: json!({
+                "content": [
+                    {
+                        "text": "Patch has been applied successfully!",
+                        "type": "text"
+                    }
+                ]
+            }),
+        },
+        codex_response
+    );
+
+    let file_contents = std::fs::read_to_string(test_file.as_path())?;
+    assert_eq!(file_contents, "modified content\n");
+
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn test_codex_tool_passes_base_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;
+    }
+
+    // Apparently `#[tokio::test]` must return `()`, so we create a helper
+    // function that returns `Result` so we can use `?` in favor of `unwrap`.
+    if let Err(err) = codex_tool_passes_base_instructions().await {
+        panic!("failure: {err}");
+    }
+}
+
+async fn codex_tool_passes_base_instructions() -> anyhow::Result<()> {
+    #![allow(clippy::unwrap_used)]
+
+    let server =
+        create_mock_chat_completions_server(vec![create_final_assistant_message_sse_response(
+            "Enjoy!",
+        )?])
+        .await;
+
+    // Run `codex mcp` with a specific config.toml.
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+    let mut mcp_process = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp_process.initialize()).await??;
+
+    // Send a "codex" tool request, which should hit the completions endpoint.
+    let codex_request_id = mcp_process
+        .send_codex_tool_call(CodexToolCallParam {
+            prompt: "How are you?".to_string(),
+            base_instructions: Some("You are a helpful assistant.".to_string()),
+            ..Default::default()
+        })
+        .await?;
+
+    let codex_response = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp_process.read_stream_until_response_message(RequestId::Integer(codex_request_id)),
+    )
+    .await??;
+    assert_eq!(
+        JSONRPCResponse {
+            jsonrpc: JSONRPC_VERSION.into(),
+            id: RequestId::Integer(codex_request_id),
+            result: json!({
+                "content": [
+                    {
+                        "text": "Enjoy!",
+                        "type": "text"
+                    }
+                ]
+            }),
+        },
+        codex_response
+    );
+
+    let requests = server.received_requests().await.unwrap();
+    let request = requests[0].body_json::<serde_json::Value>().unwrap();
+    let instructions = request["messages"][0]["content"].as_str().unwrap();
+    assert!(instructions.starts_with("You are a helpful assistant."));
+
+    Ok(())
+}
+
+fn create_expected_patch_approval_elicitation_request(
+    elicitation_request_id: RequestId,
+    changes: HashMap<PathBuf, FileChange>,
+    grant_root: Option<PathBuf>,
+    reason: Option<String>,
+    codex_mcp_tool_call_id: String,
+    codex_event_id: String,
+) -> anyhow::Result<JSONRPCRequest> {
+    let mut message_lines = Vec::new();
+    if let Some(r) = &reason {
+        message_lines.push(r.clone());
+    }
+    message_lines.push("Allow Codex to apply proposed code changes?".to_string());
+
+    Ok(JSONRPCRequest {
+        jsonrpc: JSONRPC_VERSION.into(),
+        id: elicitation_request_id,
+        method: ElicitRequest::METHOD.to_string(),
+        params: Some(serde_json::to_value(&PatchApprovalElicitRequestParams {
+            message: message_lines.join("\n"),
+            requested_schema: ElicitRequestParamsRequestedSchema {
+                r#type: "object".to_string(),
+                properties: json!({}),
+                required: None,
+            },
+            codex_elicitation: "patch-approval".to_string(),
+            codex_mcp_tool_call_id,
+            codex_event_id,
+            codex_reason: reason,
+            codex_grant_root: grant_root,
+            codex_changes: changes,
+            codex_call_id: "call1234".to_string(),
+        })?),
+    })
+}
+
+/// This handle is used to ensure that the MockServer and TempDir are not dropped while
+/// the McpProcess is still running.
+pub struct McpHandle {
+    pub process: McpProcess,
+    /// Retain the server for the lifetime of the McpProcess.
+    #[allow(dead_code)]
+    server: MockServer,
+    /// Retain the temporary directory for the lifetime of the McpProcess.
+    #[allow(dead_code)]
+    dir: TempDir,
+}
+
+async fn create_mcp_process(responses: Vec<String>) -> anyhow::Result<McpHandle> {
+    let server = create_mock_chat_completions_server(responses).await;
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+    let mut mcp_process = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp_process.initialize()).await??;
+    Ok(McpHandle {
+        process: mcp_process,
+        server,
+        dir: codex_home,
+    })
+}
+
+/// Create a Codex config that uses the mock server as the model provider.
+/// It also uses `approval_policy = "untrusted"` so that we exercise the
+/// elicitation code path for shell commands.
+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 = "untrusted"
+sandbox_policy = "read-only"
+
+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/common/Cargo.toml

@@ -0,0 +1,24 @@
+[package]
+name = "mcp_test_support"
+version = { workspace = true }
+edition = "2024"
+
+[lib]
+path = "lib.rs"
+
+[dependencies]
+anyhow = "1"
+assert_cmd = "2"
+codex-mcp-server = { path = "../.." }
+mcp-types = { path = "../../../mcp-types" }
+pretty_assertions = "1.4.1"
+serde_json = "1"
+shlex = "1.3.0"
+tempfile = "3"
+tokio = { version = "1", features = [
+    "io-std",
+    "macros",
+    "process",
+    "rt-multi-thread",
+] }
+wiremock = "0.6"

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

@@ -0,0 +1,9 @@
+mod mcp_process;
+mod mock_model_server;
+mod responses;
+
+pub use mcp_process::McpProcess;
+pub use mock_model_server::create_mock_chat_completions_server;
+pub use responses::create_apply_patch_sse_response;
+pub use responses::create_final_assistant_message_sse_response;
+pub use responses::create_shell_sse_response;

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

@@ -0,0 +1,343 @@
+use std::path::Path;
+use std::process::Stdio;
+use std::sync::atomic::AtomicI64;
+use std::sync::atomic::Ordering;
+use tokio::io::AsyncBufReadExt;
+use tokio::io::AsyncWriteExt;
+use tokio::io::BufReader;
+use tokio::process::Child;
+use tokio::process::ChildStdin;
+use tokio::process::ChildStdout;
+
+use anyhow::Context;
+use assert_cmd::prelude::*;
+use codex_mcp_server::CodexToolCallParam;
+use codex_mcp_server::CodexToolCallReplyParam;
+use mcp_types::CallToolRequestParams;
+use mcp_types::ClientCapabilities;
+use mcp_types::Implementation;
+use mcp_types::InitializeRequestParams;
+use mcp_types::JSONRPC_VERSION;
+use mcp_types::JSONRPCMessage;
+use mcp_types::JSONRPCNotification;
+use mcp_types::JSONRPCRequest;
+use mcp_types::JSONRPCResponse;
+use mcp_types::ModelContextProtocolNotification;
+use mcp_types::ModelContextProtocolRequest;
+use mcp_types::RequestId;
+use pretty_assertions::assert_eq;
+use serde_json::json;
+use std::process::Command as StdCommand;
+use tokio::process::Command;
+
+pub struct McpProcess {
+    next_request_id: AtomicI64,
+    /// Retain this child process until the client is dropped. The Tokio runtime
+    /// will make a "best effort" to reap the process after it exits, but it is
+    /// not a guarantee. See the `kill_on_drop` documentation for details.
+    #[allow(dead_code)]
+    process: Child,
+    stdin: ChildStdin,
+    stdout: BufReader<ChildStdout>,
+}
+
+impl McpProcess {
+    pub async fn new(codex_home: &Path) -> anyhow::Result<Self> {
+        // Use assert_cmd to locate the binary path and then switch to tokio::process::Command
+        let std_cmd = StdCommand::cargo_bin("codex-mcp-server")
+            .context("should find binary for codex-mcp-server")?;
+
+        let program = std_cmd.get_program().to_owned();
+
+        let mut cmd = Command::new(program);
+
+        cmd.stdin(Stdio::piped());
+        cmd.stdout(Stdio::piped());
+        cmd.env("CODEX_HOME", codex_home);
+        cmd.env("RUST_LOG", "debug");
+
+        let mut process = cmd
+            .kill_on_drop(true)
+            .spawn()
+            .context("codex-mcp-server proc should start")?;
+        let stdin = process
+            .stdin
+            .take()
+            .ok_or_else(|| anyhow::format_err!("mcp should have stdin fd"))?;
+        let stdout = process
+            .stdout
+            .take()
+            .ok_or_else(|| anyhow::format_err!("mcp should have stdout fd"))?;
+        let stdout = BufReader::new(stdout);
+        Ok(Self {
+            next_request_id: AtomicI64::new(0),
+            process,
+            stdin,
+            stdout,
+        })
+    }
+
+    /// Performs the initialization handshake with the MCP server.
+    pub async fn initialize(&mut self) -> anyhow::Result<()> {
+        let request_id = self.next_request_id.fetch_add(1, Ordering::Relaxed);
+
+        let params = InitializeRequestParams {
+            capabilities: ClientCapabilities {
+                elicitation: Some(json!({})),
+                experimental: None,
+                roots: None,
+                sampling: None,
+            },
+            client_info: Implementation {
+                name: "elicitation test".into(),
+                title: Some("Elicitation Test".into()),
+                version: "0.0.0".into(),
+            },
+            protocol_version: mcp_types::MCP_SCHEMA_VERSION.into(),
+        };
+        let params_value = serde_json::to_value(params)?;
+
+        self.send_jsonrpc_message(JSONRPCMessage::Request(JSONRPCRequest {
+            jsonrpc: JSONRPC_VERSION.into(),
+            id: RequestId::Integer(request_id),
+            method: mcp_types::InitializeRequest::METHOD.into(),
+            params: Some(params_value),
+        }))
+        .await?;
+
+        let initialized = self.read_jsonrpc_message().await?;
+        assert_eq!(
+            JSONRPCMessage::Response(JSONRPCResponse {
+                jsonrpc: JSONRPC_VERSION.into(),
+                id: RequestId::Integer(request_id),
+                result: json!({
+                    "capabilities": {
+                        "tools": {
+                            "listChanged": true
+                        },
+                    },
+                    "serverInfo": {
+                        "name": "codex-mcp-server",
+                        "title": "Codex",
+                        "version": "0.0.0"
+                    },
+                    "protocolVersion": mcp_types::MCP_SCHEMA_VERSION
+                })
+            }),
+            initialized
+        );
+
+        // Send notifications/initialized to ack the response.
+        self.send_jsonrpc_message(JSONRPCMessage::Notification(JSONRPCNotification {
+            jsonrpc: JSONRPC_VERSION.into(),
+            method: mcp_types::InitializedNotification::METHOD.into(),
+            params: None,
+        }))
+        .await?;
+
+        Ok(())
+    }
+
+    /// Returns the id used to make the request so it can be used when
+    /// correlating notifications.
+    pub async fn send_codex_tool_call(
+        &mut self,
+        params: CodexToolCallParam,
+    ) -> anyhow::Result<i64> {
+        let codex_tool_call_params = CallToolRequestParams {
+            name: "codex".to_string(),
+            arguments: Some(serde_json::to_value(params)?),
+        };
+        self.send_request(
+            mcp_types::CallToolRequest::METHOD,
+            Some(serde_json::to_value(codex_tool_call_params)?),
+        )
+        .await
+    }
+
+    pub async fn send_codex_reply_tool_call(
+        &mut self,
+        session_id: &str,
+        prompt: &str,
+    ) -> anyhow::Result<i64> {
+        let codex_tool_call_params = CallToolRequestParams {
+            name: "codex-reply".to_string(),
+            arguments: Some(serde_json::to_value(CodexToolCallReplyParam {
+                prompt: prompt.to_string(),
+                session_id: session_id.to_string(),
+            })?),
+        };
+        self.send_request(
+            mcp_types::CallToolRequest::METHOD,
+            Some(serde_json::to_value(codex_tool_call_params)?),
+        )
+        .await
+    }
+
+    async fn send_request(
+        &mut self,
+        method: &str,
+        params: Option<serde_json::Value>,
+    ) -> anyhow::Result<i64> {
+        let request_id = self.next_request_id.fetch_add(1, Ordering::Relaxed);
+
+        let message = JSONRPCMessage::Request(JSONRPCRequest {
+            jsonrpc: JSONRPC_VERSION.into(),
+            id: RequestId::Integer(request_id),
+            method: method.to_string(),
+            params,
+        });
+        self.send_jsonrpc_message(message).await?;
+        Ok(request_id)
+    }
+
+    pub async fn send_response(
+        &mut self,
+        id: RequestId,
+        result: serde_json::Value,
+    ) -> anyhow::Result<()> {
+        self.send_jsonrpc_message(JSONRPCMessage::Response(JSONRPCResponse {
+            jsonrpc: JSONRPC_VERSION.into(),
+            id,
+            result,
+        }))
+        .await
+    }
+
+    async fn send_jsonrpc_message(&mut self, message: JSONRPCMessage) -> anyhow::Result<()> {
+        let payload = serde_json::to_string(&message)?;
+        self.stdin.write_all(payload.as_bytes()).await?;
+        self.stdin.write_all(b"\n").await?;
+        self.stdin.flush().await?;
+        Ok(())
+    }
+
+    async fn read_jsonrpc_message(&mut self) -> anyhow::Result<JSONRPCMessage> {
+        let mut line = String::new();
+        self.stdout.read_line(&mut line).await?;
+        let message = serde_json::from_str::<JSONRPCMessage>(&line)?;
+        Ok(message)
+    }
+    pub async fn read_stream_until_request_message(&mut self) -> anyhow::Result<JSONRPCRequest> {
+        loop {
+            let message = self.read_jsonrpc_message().await?;
+            eprint!("message: {message:?}");
+
+            match message {
+                JSONRPCMessage::Notification(_) => {
+                    eprintln!("notification: {message:?}");
+                }
+                JSONRPCMessage::Request(jsonrpc_request) => {
+                    return Ok(jsonrpc_request);
+                }
+                JSONRPCMessage::Error(_) => {
+                    anyhow::bail!("unexpected JSONRPCMessage::Error: {message:?}");
+                }
+                JSONRPCMessage::Response(_) => {
+                    anyhow::bail!("unexpected JSONRPCMessage::Response: {message:?}");
+                }
+            }
+        }
+    }
+
+    pub async fn read_stream_until_response_message(
+        &mut self,
+        request_id: RequestId,
+    ) -> anyhow::Result<JSONRPCResponse> {
+        loop {
+            let message = self.read_jsonrpc_message().await?;
+            eprint!("message: {message:?}");
+
+            match message {
+                JSONRPCMessage::Notification(_) => {
+                    eprintln!("notification: {message:?}");
+                }
+                JSONRPCMessage::Request(_) => {
+                    anyhow::bail!("unexpected JSONRPCMessage::Request: {message:?}");
+                }
+                JSONRPCMessage::Error(_) => {
+                    anyhow::bail!("unexpected JSONRPCMessage::Error: {message:?}");
+                }
+                JSONRPCMessage::Response(jsonrpc_response) => {
+                    if jsonrpc_response.id == request_id {
+                        return Ok(jsonrpc_response);
+                    }
+                }
+            }
+        }
+    }
+
+    pub async fn read_stream_until_configured_response_message(
+        &mut self,
+    ) -> anyhow::Result<String> {
+        let mut sid_old: Option<String> = None;
+        let mut sid_new: Option<String> = None;
+        loop {
+            let message = self.read_jsonrpc_message().await?;
+            eprint!("message: {message:?}");
+
+            match message {
+                JSONRPCMessage::Notification(notification) => {
+                    if let Some(params) = notification.params {
+                        // Back-compat schema: method == "codex/event" and msg.type == "session_configured"
+                        if notification.method == "codex/event" {
+                            if let Some(msg) = params.get("msg") {
+                                if msg.get("type").and_then(|v| v.as_str())
+                                    == Some("session_configured")
+                                {
+                                    if let Some(session_id) =
+                                        msg.get("session_id").and_then(|v| v.as_str())
+                                    {
+                                        sid_old = Some(session_id.to_string());
+                                    }
+                                }
+                            }
+                        }
+                        // New schema: method is the Display of EventMsg::SessionConfigured => "SessionConfigured"
+                        if notification.method == "session_configured" {
+                            if let Some(msg) = params.get("msg") {
+                                if let Some(session_id) =
+                                    msg.get("session_id").and_then(|v| v.as_str())
+                                {
+                                    sid_new = Some(session_id.to_string());
+                                }
+                            }
+                        }
+                    }
+
+                    if sid_old.is_some() && sid_new.is_some() {
+                        // Both seen, they must match
+                        assert_eq!(
+                            sid_old.as_ref().unwrap(),
+                            sid_new.as_ref().unwrap(),
+                            "session_id mismatch between old and new schema"
+                        );
+                        return Ok(sid_old.unwrap());
+                    }
+                }
+                JSONRPCMessage::Request(_) => {
+                    anyhow::bail!("unexpected JSONRPCMessage::Request: {message:?}");
+                }
+                JSONRPCMessage::Error(_) => {
+                    anyhow::bail!("unexpected JSONRPCMessage::Error: {message:?}");
+                }
+                JSONRPCMessage::Response(_) => {
+                    anyhow::bail!("unexpected JSONRPCMessage::Response: {message:?}");
+                }
+            }
+        }
+    }
+
+    pub async fn send_notification(
+        &mut self,
+        method: &str,
+        params: Option<serde_json::Value>,
+    ) -> anyhow::Result<()> {
+        self.send_jsonrpc_message(JSONRPCMessage::Notification(JSONRPCNotification {
+            jsonrpc: JSONRPC_VERSION.into(),
+            method: method.to_string(),
+            params,
+        }))
+        .await
+    }
+}

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

@@ -0,0 +1,47 @@
+use std::sync::atomic::AtomicUsize;
+use std::sync::atomic::Ordering;
+
+use wiremock::Mock;
+use wiremock::MockServer;
+use wiremock::Respond;
+use wiremock::ResponseTemplate;
+use wiremock::matchers::method;
+use wiremock::matchers::path;
+
+/// Create a mock server that will provide the responses, in order, for
+/// requests to the `/v1/chat/completions` endpoint.
+pub async fn create_mock_chat_completions_server(responses: Vec<String>) -> MockServer {
+    let server = MockServer::start().await;
+
+    let num_calls = responses.len();
+    let seq_responder = SeqResponder {
+        num_calls: AtomicUsize::new(0),
+        responses,
+    };
+
+    Mock::given(method("POST"))
+        .and(path("/v1/chat/completions"))
+        .respond_with(seq_responder)
+        .expect(num_calls as u64)
+        .mount(&server)
+        .await;
+
+    server
+}
+
+struct SeqResponder {
+    num_calls: AtomicUsize,
+    responses: Vec<String>,
+}
+
+impl Respond for SeqResponder {
+    fn respond(&self, _: &wiremock::Request) -> ResponseTemplate {
+        let call_num = self.num_calls.fetch_add(1, Ordering::SeqCst);
+        match self.responses.get(call_num) {
+            Some(response) => ResponseTemplate::new(200)
+                .insert_header("content-type", "text/event-stream")
+                .set_body_raw(response.clone(), "text/event-stream"),
+            None => panic!("no response for {call_num}"),
+        }
+    }
+}

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

@@ -0,0 +1,95 @@
+use serde_json::json;
+use std::path::Path;
+
+pub fn create_shell_sse_response(
+    command: Vec<String>,
+    workdir: Option<&Path>,
+    timeout_ms: Option<u64>,
+    call_id: &str,
+) -> anyhow::Result<String> {
+    // The `arguments`` for the `shell` tool is a serialized JSON object.
+    let tool_call_arguments = serde_json::to_string(&json!({
+        "command": command,
+        "workdir": workdir.map(|w| w.to_string_lossy()),
+        "timeout": timeout_ms
+    }))?;
+    let tool_call = json!({
+        "choices": [
+            {
+                "delta": {
+                    "tool_calls": [
+                        {
+                            "id": call_id,
+                            "function": {
+                                "name": "shell",
+                                "arguments": tool_call_arguments
+                            }
+                        }
+                    ]
+                },
+                "finish_reason": "tool_calls"
+            }
+        ]
+    });
+
+    let sse = format!(
+        "data: {}\n\ndata: DONE\n\n",
+        serde_json::to_string(&tool_call)?
+    );
+    Ok(sse)
+}
+
+pub fn create_final_assistant_message_sse_response(message: &str) -> anyhow::Result<String> {
+    let assistant_message = json!({
+        "choices": [
+            {
+                "delta": {
+                    "content": message
+                },
+                "finish_reason": "stop"
+            }
+        ]
+    });
+
+    let sse = format!(
+        "data: {}\n\ndata: DONE\n\n",
+        serde_json::to_string(&assistant_message)?
+    );
+    Ok(sse)
+}
+
+pub fn create_apply_patch_sse_response(
+    patch_content: &str,
+    call_id: &str,
+) -> anyhow::Result<String> {
+    // Use shell command to call apply_patch with heredoc format
+    let shell_command = format!("apply_patch <<'EOF'\n{patch_content}\nEOF");
+    let tool_call_arguments = serde_json::to_string(&json!({
+        "command": ["bash", "-lc", shell_command]
+    }))?;
+
+    let tool_call = json!({
+        "choices": [
+            {
+                "delta": {
+                    "tool_calls": [
+                        {
+                            "id": call_id,
+                            "function": {
+                                "name": "shell",
+                                "arguments": tool_call_arguments
+                            }
+                        }
+                    ]
+                },
+                "finish_reason": "tool_calls"
+            }
+        ]
+    });
+
+    let sse = format!(
+        "data: {}\n\ndata: DONE\n\n",
+        serde_json::to_string(&tool_call)?
+    );
+    Ok(sse)
+}

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

@@ -0,0 +1,176 @@
+#![cfg(unix)]
+// Support code lives in the `mcp_test_support` crate under tests/common.
+
+use std::path::Path;
+
+use codex_core::exec::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
+use codex_mcp_server::CodexToolCallParam;
+use mcp_types::JSONRPCResponse;
+use mcp_types::RequestId;
+use serde_json::json;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+use mcp_test_support::McpProcess;
+use mcp_test_support::create_mock_chat_completions_server;
+use mcp_test_support::create_shell_sse_response;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn test_shell_command_interruption() {
+    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;
+    }
+
+    if let Err(err) = shell_command_interruption().await {
+        panic!("failure: {err}");
+    }
+}
+
+async fn shell_command_interruption() -> anyhow::Result<()> {
+    // Use a cross-platform blocking command. On Windows plain `sleep` is not guaranteed to exist
+    // (MSYS/GNU coreutils may be absent) and the failure causes the tool call to finish immediately,
+    // which triggers a second model request before the test sends the explicit follow-up. That
+    // prematurely consumes the second mocked SSE response and leads to a third POST (panic: no response for 2).
+    // Powershell Start-Sleep is always available on Windows runners. On Unix we keep using `sleep`.
+    #[cfg(target_os = "windows")]
+    let shell_command = vec![
+        "powershell".to_string(),
+        "-Command".to_string(),
+        "Start-Sleep -Seconds 60".to_string(),
+    ];
+    #[cfg(not(target_os = "windows"))]
+    let shell_command = vec!["sleep".to_string(), "60".to_string()];
+    let workdir_for_shell_function_call = TempDir::new()?;
+
+    // Create mock server with a single SSE response: the long sleep command
+    let server = create_mock_chat_completions_server(vec![
+        create_shell_sse_response(
+            shell_command.clone(),
+            Some(workdir_for_shell_function_call.path()),
+            Some(60_000), // 60 seconds timeout in ms
+            "call_sleep",
+        )?,
+        create_shell_sse_response(
+            shell_command.clone(),
+            Some(workdir_for_shell_function_call.path()),
+            Some(60_000), // 60 seconds timeout in ms
+            "call_sleep",
+        )?,
+    ])
+    .await;
+
+    // Create Codex configuration
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), server.uri())?;
+    let mut mcp_process = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp_process.initialize()).await??;
+
+    // Send codex tool call that triggers "sleep 60"
+    let codex_request_id = mcp_process
+        .send_codex_tool_call(CodexToolCallParam {
+            cwd: None,
+            prompt: "First Run: run `sleep 60`".to_string(),
+            model: None,
+            profile: None,
+            approval_policy: None,
+            sandbox: None,
+            config: None,
+            base_instructions: None,
+        })
+        .await?;
+
+    let session_id = mcp_process
+        .read_stream_until_configured_response_message()
+        .await?;
+
+    // Give the command a moment to start
+    tokio::time::sleep(std::time::Duration::from_secs(1)).await;
+
+    // Send interrupt notification
+    mcp_process
+        .send_notification(
+            "notifications/cancelled",
+            Some(json!({ "requestId": codex_request_id })),
+        )
+        .await?;
+
+    // Expect Codex to return an error or interruption response
+    let codex_response: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp_process.read_stream_until_response_message(RequestId::Integer(codex_request_id)),
+    )
+    .await??;
+
+    assert!(
+        codex_response
+            .result
+            .as_object()
+            .map(|o| o.contains_key("error"))
+            .unwrap_or(false),
+        "Expected an interruption or error result, got: {codex_response:?}"
+    );
+
+    let codex_reply_request_id = mcp_process
+        .send_codex_reply_tool_call(&session_id, "Second Run: run `sleep 60`")
+        .await?;
+
+    // Give the command a moment to start
+    tokio::time::sleep(std::time::Duration::from_secs(1)).await;
+
+    // Send interrupt notification
+    mcp_process
+        .send_notification(
+            "notifications/cancelled",
+            Some(json!({ "requestId": codex_reply_request_id })),
+        )
+        .await?;
+
+    // Expect Codex to return an error or interruption response
+    let codex_response: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp_process.read_stream_until_response_message(RequestId::Integer(codex_reply_request_id)),
+    )
+    .await??;
+
+    assert!(
+        codex_response
+            .result
+            .as_object()
+            .map(|o| o.contains_key("error"))
+            .unwrap_or(false),
+        "Expected an interruption or error result, got: {codex_response:?}"
+    );
+    Ok(())
+}
+
+// ---------------------------------------------------------------------------
+// Helpers
+// ---------------------------------------------------------------------------
+
+fn create_config_toml(codex_home: &Path, server_uri: String) -> 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-types/README.md

@@ -2,7 +2,7 @@
 
 Types for Model Context Protocol. Inspired by https://crates.io/crates/lsp-types.
 
-As documented on https://modelcontextprotocol.io/specification/2025-03-26/basic:
+As documented on https://modelcontextprotocol.io/specification/2025-06-18/basic:
 
-- TypeScript schema is the source of truth: https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/schema/2025-03-26/schema.ts
-- JSON schema is amenable to automated tooling: https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/schema/2025-03-26/schema.json
+- TypeScript schema is the source of truth: https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/schema/2025-06-18/schema.ts
+- JSON schema is amenable to automated tooling: https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/schema/2025-06-18/schema.json

codex-rs/mcp-types/generate_mcp_types.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 # flake8: noqa: E501
 
+import argparse
 import json
 import subprocess
 import sys
@@ -13,10 +14,13 @@ from pathlib import Path
 # Helper first so it is defined when other functions call it.
 from typing import Any, Literal
 
-SCHEMA_VERSION = "2025-03-26"
+SCHEMA_VERSION = "2025-06-18"
 JSONRPC_VERSION = "2.0"
 
 STANDARD_DERIVE = "#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]\n"
+STANDARD_HASHABLE_DERIVE = (
+    "#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, Hash, Eq)]\n"
+)
 
 # Will be populated with the schema's `definitions` map in `main()` so that
 # helper functions (for example `define_any_of`) can perform look-ups while
@@ -26,19 +30,27 @@ DEFINITIONS: dict[str, Any] = {}
 CLIENT_REQUEST_TYPE_NAMES: list[str] = []
 # Concrete *Notification types that make up the ServerNotification enum.
 SERVER_NOTIFICATION_TYPE_NAMES: list[str] = []
+# Enum types that will need a `allow(clippy::large_enum_variant)` annotation in
+# order to compile without warnings.
+LARGE_ENUMS = {"ServerResult"}
 
 
 def main() -> int:
-    num_args = len(sys.argv)
-    if num_args == 1:
-        schema_file = (
-            Path(__file__).resolve().parent / "schema" / SCHEMA_VERSION / "schema.json"
-        )
-    elif num_args == 2:
-        schema_file = Path(sys.argv[1])
-    else:
-        print("Usage: python3 codegen.py <schema.json>")
-        return 1
+    parser = argparse.ArgumentParser(
+        description="Embed, cluster and analyse text prompts via the OpenAI API.",
+    )
+
+    default_schema_file = (
+        Path(__file__).resolve().parent / "schema" / SCHEMA_VERSION / "schema.json"
+    )
+    parser.add_argument(
+        "schema_file",
+        nargs="?",
+        default=default_schema_file,
+        help="schema.json file to process",
+    )
+    args = parser.parse_args()
+    schema_file = args.schema_file
 
     lib_rs = Path(__file__).resolve().parent / "src/lib.rs"
 
@@ -197,6 +209,8 @@ def add_definition(name: str, definition: dict[str, Any], out: list[str]) -> Non
         if name.endswith("Result"):
             out.extend(f"impl From<{name}> for serde_json::Value {{\n")
             out.append(f"    fn from(value: {name}) -> Self {{\n")
+            out.append("        // Leave this as it should never fail\n")
+            out.append("        #[expect(clippy::unwrap_used)]\n")
             out.append("        serde_json::to_value(value).unwrap()\n")
             out.append("    }\n")
             out.append("}\n\n")
@@ -211,20 +225,7 @@ def add_definition(name: str, definition: dict[str, Any], out: list[str]) -> Non
     any_of = definition.get("anyOf", [])
     if any_of:
         assert isinstance(any_of, list)
-        if name == "JSONRPCMessage":
-            # Special case for JSONRPCMessage because its definition in the
-            # JSON schema does not quite match how we think about this type
-            # definition in Rust.
-            deep_copied_any_of = json.loads(json.dumps(any_of))
-            deep_copied_any_of[2] = {
-                "$ref": "#/definitions/JSONRPCBatchRequest",
-            }
-            deep_copied_any_of[5] = {
-                "$ref": "#/definitions/JSONRPCBatchResponse",
-            }
-            out.extend(define_any_of(name, deep_copied_any_of, description))
-        else:
-            out.extend(define_any_of(name, any_of, description))
+        out.extend(define_any_of(name, any_of, description))
         return
 
     type_prop = definition.get("type", None)
@@ -393,7 +394,7 @@ def define_string_enum(
 
 
 def define_untagged_enum(name: str, type_list: list[str], out: list[str]) -> None:
-    out.append(STANDARD_DERIVE)
+    out.append(STANDARD_HASHABLE_DERIVE)
     out.append("#[serde(untagged)]\n")
     out.append(f"pub enum {name} {{\n")
     for simple_type in type_list:
@@ -439,6 +440,8 @@ def define_any_of(
     if serde := get_serde_annotation_for_anyof_type(name):
         out.append(serde + "\n")
 
+    if name in LARGE_ENUMS:
+        out.append("#[allow(clippy::large_enum_variant)]\n")
     out.append(f"pub enum {name} {{\n")
 
     if name == "ClientRequest":
@@ -596,6 +599,8 @@ def rust_prop_name(name: str, is_optional: bool) -> RustProp:
         prop_name = "r#type"
     elif name == "ref":
         prop_name = "r#ref"
+    elif name == "enum":
+        prop_name = "r#enum"
     elif snake_case := to_snake_case(name):
         prop_name = snake_case
         is_rename = True

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

@@ -10,7 +10,7 @@ use serde::Serialize;
 use serde::de::DeserializeOwned;
 use std::convert::TryFrom;
 
-pub const MCP_SCHEMA_VERSION: &str = "2025-03-26";
+pub const MCP_SCHEMA_VERSION: &str = "2025-06-18";
 pub const JSONRPC_VERSION: &str = "2.0";
 
 /// Paired request/response types for the Model Context Protocol (MCP).
@@ -35,6 +35,12 @@ fn default_jsonrpc() -> String {
 pub struct Annotations {
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub audience: Option<Vec<Role>>,
+    #[serde(
+        rename = "lastModified",
+        default,
+        skip_serializing_if = "Option::is_none"
+    )]
+    pub last_modified: Option<String>,
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub priority: Option<f64>,
 }
@@ -50,6 +56,14 @@ pub struct AudioContent {
     pub r#type: String, // &'static str = "audio"
 }
 
+/// Base interface for metadata with name (identifier) and title (display name) properties.
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
+pub struct BaseMetadata {
+    pub name: String,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub title: Option<String>,
+}
+
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub struct BlobResourceContents {
     pub blob: String,
@@ -58,6 +72,17 @@ pub struct BlobResourceContents {
     pub uri: String,
 }
 
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
+pub struct BooleanSchema {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub default: Option<bool>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub description: Option<String>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub title: Option<String>,
+    pub r#type: String, // &'static str = "boolean"
+}
+
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub enum CallToolRequest {}
 
@@ -75,29 +100,17 @@ pub struct CallToolRequestParams {
 }
 
 /// The server's response to a tool call.
-///
-/// Any errors that originate from the tool SHOULD be reported inside the result
-/// object, with `isError` set to true, _not_ as an MCP protocol-level error
-/// response. Otherwise, the LLM would not be able to see that an error occurred
-/// and self-correct.
-///
-/// However, any errors in _finding_ the tool, an error indicating that the
-/// server does not support tool calls, or any other exceptional conditions,
-/// should be reported as an MCP error response.
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub struct CallToolResult {
-    pub content: Vec<CallToolResultContent>,
+    pub content: Vec<ContentBlock>,
     #[serde(rename = "isError", default, skip_serializing_if = "Option::is_none")]
     pub is_error: Option<bool>,
-}
-
-#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
-#[serde(untagged)]
-pub enum CallToolResultContent {
-    TextContent(TextContent),
-    ImageContent(ImageContent),
-    AudioContent(AudioContent),
-    EmbeddedResource(EmbeddedResource),
+    #[serde(
+        rename = "structuredContent",
+        default,
+        skip_serializing_if = "Option::is_none"
+    )]
+    pub structured_content: Option<serde_json::Value>,
 }
 
 impl From<CallToolResult> for serde_json::Value {
@@ -127,6 +140,8 @@ pub struct CancelledNotificationParams {
 /// Capabilities a client may support. Known capabilities are defined here, in this schema, but this is not a closed set: any client can define its own, additional capabilities.
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub struct ClientCapabilities {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub elicitation: Option<serde_json::Value>,
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub experimental: Option<serde_json::Value>,
     #[serde(default, skip_serializing_if = "Option::is_none")]
@@ -194,6 +209,7 @@ pub enum ClientResult {
     Result(Result),
     CreateMessageResult(CreateMessageResult),
     ListRootsResult(ListRootsResult),
+    ElicitResult(ElicitResult),
 }
 
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
@@ -208,9 +224,18 @@ impl ModelContextProtocolRequest for CompleteRequest {
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub struct CompleteRequestParams {
     pub argument: CompleteRequestParamsArgument,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub context: Option<CompleteRequestParamsContext>,
     pub r#ref: CompleteRequestParamsRef,
 }
 
+/// Additional, optional context for completions
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
+pub struct CompleteRequestParamsContext {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub arguments: Option<serde_json::Value>,
+}
+
 /// The argument's information
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub struct CompleteRequestParamsArgument {
@@ -222,7 +247,7 @@ pub struct CompleteRequestParamsArgument {
 #[serde(untagged)]
 pub enum CompleteRequestParamsRef {
     PromptReference(PromptReference),
-    ResourceReference(ResourceReference),
+    ResourceTemplateReference(ResourceTemplateReference),
 }
 
 /// The server's response to a completion/complete request
@@ -248,6 +273,16 @@ impl From<CompleteResult> for serde_json::Value {
     }
 }
 
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
+#[serde(untagged)]
+pub enum ContentBlock {
+    TextContent(TextContent),
+    ImageContent(ImageContent),
+    AudioContent(AudioContent),
+    ResourceLink(ResourceLink),
+    EmbeddedResource(EmbeddedResource),
+}
+
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub enum CreateMessageRequest {}
 
@@ -325,6 +360,48 @@ impl From<CreateMessageResult> for serde_json::Value {
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub struct Cursor(String);
 
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
+pub enum ElicitRequest {}
+
+impl ModelContextProtocolRequest for ElicitRequest {
+    const METHOD: &'static str = "elicitation/create";
+    type Params = ElicitRequestParams;
+    type Result = ElicitResult;
+}
+
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
+pub struct ElicitRequestParams {
+    pub message: String,
+    #[serde(rename = "requestedSchema")]
+    pub requested_schema: ElicitRequestParamsRequestedSchema,
+}
+
+/// A restricted subset of JSON Schema.
+/// Only top-level properties are allowed, without nesting.
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
+pub struct ElicitRequestParamsRequestedSchema {
+    pub properties: serde_json::Value,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub required: Option<Vec<String>>,
+    pub r#type: String, // &'static str = "object"
+}
+
+/// The client's response to an elicitation request.
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
+pub struct ElicitResult {
+    pub action: String,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub content: Option<serde_json::Value>,
+}
+
+impl From<ElicitResult> for serde_json::Value {
+    fn from(value: ElicitResult) -> Self {
+        // Leave this as it should never fail
+        #[expect(clippy::unwrap_used)]
+        serde_json::to_value(value).unwrap()
+    }
+}
+
 /// The contents of a resource, embedded into a prompt or tool call result.
 ///
 /// It is up to the client how best to render embedded resources for the benefit
@@ -346,6 +423,18 @@ pub enum EmbeddedResourceResource {
 
 pub type EmptyResult = Result;
 
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
+pub struct EnumSchema {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub description: Option<String>,
+    pub r#enum: Vec<String>,
+    #[serde(rename = "enumNames", default, skip_serializing_if = "Option::is_none")]
+    pub enum_names: Option<Vec<String>>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub title: Option<String>,
+    pub r#type: String, // &'static str = "string"
+}
+
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub enum GetPromptRequest {}
 
@@ -389,10 +478,12 @@ pub struct ImageContent {
     pub r#type: String, // &'static str = "image"
 }
 
-/// Describes the name and version of an MCP implementation.
+/// Describes the name and version of an MCP implementation, with an optional title for UI representation.
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub struct Implementation {
     pub name: String,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub title: Option<String>,
     pub version: String,
 }
 
@@ -442,24 +533,6 @@ impl ModelContextProtocolNotification for InitializedNotification {
     type Params = Option<serde_json::Value>;
 }
 
-#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
-#[serde(untagged)]
-pub enum JSONRPCBatchRequestItem {
-    JSONRPCRequest(JSONRPCRequest),
-    JSONRPCNotification(JSONRPCNotification),
-}
-
-pub type JSONRPCBatchRequest = Vec<JSONRPCBatchRequestItem>;
-
-#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
-#[serde(untagged)]
-pub enum JSONRPCBatchResponseItem {
-    JSONRPCResponse(JSONRPCResponse),
-    JSONRPCError(JSONRPCError),
-}
-
-pub type JSONRPCBatchResponse = Vec<JSONRPCBatchResponseItem>;
-
 /// A response to a request that indicates an error occurred.
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub struct JSONRPCError {
@@ -483,10 +556,8 @@ pub struct JSONRPCErrorError {
 pub enum JSONRPCMessage {
     Request(JSONRPCRequest),
     Notification(JSONRPCNotification),
-    BatchRequest(JSONRPCBatchRequest),
     Response(JSONRPCResponse),
     Error(JSONRPCError),
-    BatchResponse(JSONRPCBatchResponse),
 }
 
 /// A notification which does not expect a response.
@@ -777,6 +848,19 @@ pub struct Notification {
     pub params: Option<serde_json::Value>,
 }
 
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
+pub struct NumberSchema {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub description: Option<String>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub maximum: Option<i64>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub minimum: Option<i64>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub title: Option<String>,
+    pub r#type: String,
+}
+
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub struct PaginatedRequest {
     pub method: String,
@@ -817,6 +901,17 @@ impl ModelContextProtocolRequest for PingRequest {
     type Result = Result;
 }
 
+/// Restricted schema definitions that only allow primitive types
+/// without nested objects or arrays.
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
+#[serde(untagged)]
+pub enum PrimitiveSchemaDefinition {
+    StringSchema(StringSchema),
+    NumberSchema(NumberSchema),
+    BooleanSchema(BooleanSchema),
+    EnumSchema(EnumSchema),
+}
+
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub enum ProgressNotification {}
 
@@ -836,7 +931,7 @@ pub struct ProgressNotificationParams {
     pub total: Option<f64>,
 }
 
-#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, Hash, Eq)]
 #[serde(untagged)]
 pub enum ProgressToken {
     String(String),
@@ -851,6 +946,8 @@ pub struct Prompt {
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub description: Option<String>,
     pub name: String,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub title: Option<String>,
 }
 
 /// Describes an argument that a prompt can accept.
@@ -861,6 +958,8 @@ pub struct PromptArgument {
     pub name: String,
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub required: Option<bool>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub title: Option<String>,
 }
 
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
@@ -877,23 +976,16 @@ impl ModelContextProtocolNotification for PromptListChangedNotification {
 /// resources from the MCP server.
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub struct PromptMessage {
-    pub content: PromptMessageContent,
+    pub content: ContentBlock,
     pub role: Role,
 }
 
-#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
-#[serde(untagged)]
-pub enum PromptMessageContent {
-    TextContent(TextContent),
-    ImageContent(ImageContent),
-    AudioContent(AudioContent),
-    EmbeddedResource(EmbeddedResource),
-}
-
 /// Identifies a prompt.
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub struct PromptReference {
     pub name: String,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub title: Option<String>,
     pub r#type: String, // &'static str = "ref/prompt"
 }
 
@@ -939,7 +1031,7 @@ pub struct Request {
     pub params: Option<serde_json::Value>,
 }
 
-#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize, Hash, Eq)]
 #[serde(untagged)]
 pub enum RequestId {
     String(String),
@@ -958,6 +1050,8 @@ pub struct Resource {
     pub name: String,
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub size: Option<i64>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub title: Option<String>,
     pub uri: String,
 }
 
@@ -969,6 +1063,26 @@ pub struct ResourceContents {
     pub uri: String,
 }
 
+/// A resource that the server is capable of reading, included in a prompt or tool call result.
+///
+/// Note: resource links returned by tools are not guaranteed to appear in the results of `resources/list` requests.
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
+pub struct ResourceLink {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub annotations: Option<Annotations>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub description: Option<String>,
+    #[serde(rename = "mimeType", default, skip_serializing_if = "Option::is_none")]
+    pub mime_type: Option<String>,
+    pub name: String,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub size: Option<i64>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub title: Option<String>,
+    pub r#type: String, // &'static str = "resource_link"
+    pub uri: String,
+}
+
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub enum ResourceListChangedNotification {}
 
@@ -977,13 +1091,6 @@ impl ModelContextProtocolNotification for ResourceListChangedNotification {
     type Params = Option<serde_json::Value>;
 }
 
-/// A reference to a resource or resource template definition.
-#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
-pub struct ResourceReference {
-    pub r#type: String, // &'static str = "ref/resource"
-    pub uri: String,
-}
-
 /// A template description for resources available on the server.
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub struct ResourceTemplate {
@@ -994,10 +1101,19 @@ pub struct ResourceTemplate {
     #[serde(rename = "mimeType", default, skip_serializing_if = "Option::is_none")]
     pub mime_type: Option<String>,
     pub name: String,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub title: Option<String>,
     #[serde(rename = "uriTemplate")]
     pub uri_template: String,
 }
 
+/// A reference to a resource or resource template definition.
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
+pub struct ResourceTemplateReference {
+    pub r#type: String, // &'static str = "ref/resource"
+    pub uri: String,
+}
+
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub enum ResourceUpdatedNotification {}
 
@@ -1140,6 +1256,7 @@ pub enum ServerRequest {
     PingRequest(PingRequest),
     CreateMessageRequest(CreateMessageRequest),
     ListRootsRequest(ListRootsRequest),
+    ElicitRequest(ElicitRequest),
 }
 
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
@@ -1172,6 +1289,21 @@ pub struct SetLevelRequestParams {
     pub level: LoggingLevel,
 }
 
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
+pub struct StringSchema {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub description: Option<String>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub format: Option<String>,
+    #[serde(rename = "maxLength", default, skip_serializing_if = "Option::is_none")]
+    pub max_length: Option<i64>,
+    #[serde(rename = "minLength", default, skip_serializing_if = "Option::is_none")]
+    pub min_length: Option<i64>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub title: Option<String>,
+    pub r#type: String, // &'static str = "string"
+}
+
 #[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
 pub enum SubscribeRequest {}
 
@@ -1213,6 +1345,25 @@ pub struct Tool {
     #[serde(rename = "inputSchema")]
     pub input_schema: ToolInputSchema,
     pub name: String,
+    #[serde(
+        rename = "outputSchema",
+        default,
+        skip_serializing_if = "Option::is_none"
+    )]
+    pub output_schema: Option<ToolOutputSchema>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub title: Option<String>,
+}
+
+/// An optional JSON Schema object defining the structure of the tool's output returned in
+/// the structuredContent field of a CallToolResult.
+#[derive(Debug, Clone, PartialEq, Deserialize, Serialize)]
+pub struct ToolOutputSchema {
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub properties: Option<serde_json::Value>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub required: Option<Vec<String>>,
+    pub r#type: String, // &'static str = "object"
 }
 
 /// A JSON Schema object defining the expected parameters for the tool.

codex-rs/mcp-types/tests/initialize.rs

@@ -17,8 +17,8 @@ fn deserialize_initialize_request() {
         "method": "initialize",
         "params": {
             "capabilities": {},
-            "clientInfo": { "name": "acme-client", "version": "1.2.3" },
-            "protocolVersion": "2025-03-26"
+            "clientInfo": { "name": "acme-client", "title": "Acme", "version": "1.2.3" },
+            "protocolVersion": "2025-06-18"
         }
     }"#;
 
@@ -37,8 +37,8 @@ fn deserialize_initialize_request() {
         method: "initialize".into(),
         params: Some(json!({
             "capabilities": {},
-            "clientInfo": { "name": "acme-client", "version": "1.2.3" },
-            "protocolVersion": "2025-03-26"
+            "clientInfo": { "name": "acme-client", "title": "Acme", "version": "1.2.3" },
+            "protocolVersion": "2025-06-18"
         })),
     };
 
@@ -57,12 +57,14 @@ fn deserialize_initialize_request() {
                 experimental: None,
                 roots: None,
                 sampling: None,
+                elicitation: None,
             },
             client_info: Implementation {
                 name: "acme-client".into(),
+                title: Some("Acme".to_string()),
                 version: "1.2.3".into(),
             },
-            protocol_version: "2025-03-26".into(),
+            protocol_version: "2025-06-18".into(),
         }
     );
 }

codex-rs/rust-toolchain.toml

@@ -0,0 +1,3 @@
+[toolchain]
+channel = "1.88.0"
+components = [ "clippy", "rustfmt", "rust-src"]

codex-rs/tui/Cargo.toml

@@ -19,6 +19,7 @@ anyhow = "1"
 base64 = "0.22.1"
 clap = { version = "4", features = ["derive"] }
 codex-ansi-escape = { path = "../ansi-escape" }
+codex-arg0 = { path = "../arg0" }
 codex-core = { path = "../core" }
 codex-common = { path = "../common", features = [
     "cli",
@@ -26,7 +27,6 @@ codex-common = { path = "../common", features = [
     "sandbox_summary",
 ] }
 codex-file-search = { path = "../file-search" }
-codex-linux-sandbox = { path = "../linux-sandbox" }
 codex-login = { path = "../login" }
 color-eyre = "0.6.3"
 crossterm = { version = "0.28.1", features = ["bracketed-paste"] }
@@ -35,15 +35,16 @@ lazy_static = "1"
 mcp-types = { path = "../mcp-types" }
 path-clean = "1.0.1"
 ratatui = { version = "0.29.0", features = [
-    "unstable-widget-ref",
+    "scrolling-regions",
     "unstable-rendered-line-info",
+    "unstable-widget-ref",
 ] }
 ratatui-image = "8.0.0"
 regex-lite = "0.1"
 serde_json = { version = "1", features = ["preserve_order"] }
 shlex = "1.3.0"
-strum = "0.27.1"
-strum_macros = "0.27.1"
+strum = "0.27.2"
+strum_macros = "0.27.2"
 tokio = { version = "1", features = [
     "io-std",
     "macros",
@@ -58,7 +59,10 @@ tui-input = "0.14.0"
 tui-markdown = "0.3.3"
 tui-textarea = "0.7.0"
 unicode-segmentation = "1.12.0"
+unicode-width = "0.1"
 uuid = "1"
+reqwest = { version = "0.12", features = ["json"] }
+serde = { version = "1", features = ["derive"] }
 
 [dev-dependencies]
 insta = "1.43.1"

codex-rs/tui/src/app.rs

@@ -6,7 +6,6 @@ use crate::get_git_diff::get_git_diff;
 use crate::git_warning_screen::GitWarningOutcome;
 use crate::git_warning_screen::GitWarningScreen;
 use crate::login_screen::LoginScreen;
-use crate::mouse_capture::MouseCapture;
 use crate::scroll_event_helper::ScrollEventHelper;
 use crate::slash_command::SlashCommand;
 use crate::tui;
@@ -18,8 +17,16 @@ use crossterm::event::KeyEvent;
 use crossterm::event::MouseEvent;
 use crossterm::event::MouseEventKind;
 use std::path::PathBuf;
+use std::sync::Arc;
+use std::sync::atomic::AtomicBool;
+use std::sync::atomic::Ordering;
 use std::sync::mpsc::Receiver;
 use std::sync::mpsc::channel;
+use std::thread;
+use std::time::Duration;
+
+/// Time window for debouncing redraw requests.
+const REDRAW_DEBOUNCE: Duration = Duration::from_millis(10);
 
 /// Top-level application state: which full-screen view is currently active.
 #[allow(clippy::large_enum_variant)]
@@ -46,6 +53,9 @@ pub(crate) struct App<'a> {
 
     file_search: FileSearchManager,
 
+    /// True when a redraw has been scheduled but not yet executed.
+    pending_redraw: Arc<AtomicBool>,
+
     /// Stored parameters needed to instantiate the ChatWidget later, e.g.,
     /// after dismissing the Git-repo warning.
     chat_args: Option<ChatWidgetArgs>,
@@ -60,7 +70,7 @@ struct ChatWidgetArgs {
     initial_images: Vec<PathBuf>,
 }
 
-impl<'a> App<'a> {
+impl App<'_> {
     pub(crate) fn new(
         config: Config,
         initial_prompt: Option<String>,
@@ -70,6 +80,7 @@ impl<'a> App<'a> {
     ) -> Self {
         let (app_event_tx, app_event_rx) = channel();
         let app_event_tx = AppEventSender::new(app_event_tx);
+        let pending_redraw = Arc::new(AtomicBool::new(false));
         let scroll_event_helper = ScrollEventHelper::new(app_event_tx.clone());
 
         // Spawn a dedicated thread for reading the crossterm event loop and
@@ -77,32 +88,51 @@ impl<'a> App<'a> {
         {
             let app_event_tx = app_event_tx.clone();
             std::thread::spawn(move || {
-                while let Ok(event) = crossterm::event::read() {
-                    match event {
-                        crossterm::event::Event::Key(key_event) => {
-                            app_event_tx.send(AppEvent::KeyEvent(key_event));
-                        }
-                        crossterm::event::Event::Resize(_, _) => {
-                            app_event_tx.send(AppEvent::Redraw);
-                        }
-                        crossterm::event::Event::Mouse(MouseEvent {
-                            kind: MouseEventKind::ScrollUp,
-                            ..
-                        }) => {
-                            scroll_event_helper.scroll_up();
-                        }
-                        crossterm::event::Event::Mouse(MouseEvent {
-                            kind: MouseEventKind::ScrollDown,
-                            ..
-                        }) => {
-                            scroll_event_helper.scroll_down();
-                        }
-                        crossterm::event::Event::Paste(pasted) => {
-                            app_event_tx.send(AppEvent::Paste(pasted));
-                        }
-                        _ => {
-                            // Ignore any other events.
+                loop {
+                    // This timeout is necessary to avoid holding the event lock
+                    // that crossterm::event::read() acquires. In particular,
+                    // reading the cursor position (crossterm::cursor::position())
+                    // needs to acquire the event lock, and so will fail if it
+                    // can't acquire it within 2 sec. Resizing the terminal
+                    // crashes the app if the cursor position can't be read.
+                    if let Ok(true) = crossterm::event::poll(Duration::from_millis(100)) {
+                        if let Ok(event) = crossterm::event::read() {
+                            match event {
+                                crossterm::event::Event::Key(key_event) => {
+                                    app_event_tx.send(AppEvent::KeyEvent(key_event));
+                                }
+                                crossterm::event::Event::Resize(_, _) => {
+                                    app_event_tx.send(AppEvent::RequestRedraw);
+                                }
+                                crossterm::event::Event::Mouse(MouseEvent {
+                                    kind: MouseEventKind::ScrollUp,
+                                    ..
+                                }) => {
+                                    scroll_event_helper.scroll_up();
+                                }
+                                crossterm::event::Event::Mouse(MouseEvent {
+                                    kind: MouseEventKind::ScrollDown,
+                                    ..
+                                }) => {
+                                    scroll_event_helper.scroll_down();
+                                }
+                                crossterm::event::Event::Paste(pasted) => {
+                                    // Many terminals convert newlines to \r when
+                                    // pasting, e.g. [iTerm2][]. But [tui-textarea
+                                    // expects \n][tui-textarea]. This seems like a bug
+                                    // in tui-textarea IMO, but work around it for now.
+                                    // [tui-textarea]: https://github.com/rhysd/tui-textarea/blob/4d18622eeac13b309e0ff6a55a46ac6706da68cf/src/textarea.rs#L782-L783
+                                    // [iTerm2]: https://github.com/gnachman/iTerm2/blob/5d0c0d9f68523cbd0494dad5422998964a2ecd8d/sources/iTermPasteHelper.m#L206-L216
+                                    let pasted = pasted.replace("\r", "\n");
+                                    app_event_tx.send(AppEvent::Paste(pasted));
+                                }
+                                _ => {
+                                    // Ignore any other events.
+                                }
+                            }
                         }
+                    } else {
+                        // Timeout expired, no `Event` is available
                     }
                 }
             });
@@ -152,6 +182,7 @@ impl<'a> App<'a> {
             app_state,
             config,
             file_search,
+            pending_redraw,
             chat_args,
         }
     }
@@ -162,17 +193,42 @@ impl<'a> App<'a> {
         self.app_event_tx.clone()
     }
 
-    pub(crate) fn run(
-        &mut self,
-        terminal: &mut tui::Tui,
-        mouse_capture: &mut MouseCapture,
-    ) -> Result<()> {
+    /// Schedule a redraw if one is not already pending.
+    #[allow(clippy::unwrap_used)]
+    fn schedule_redraw(&self) {
+        // Attempt to set the flag to `true`. If it was already `true`, another
+        // redraw is already pending so we can return early.
+        if self
+            .pending_redraw
+            .compare_exchange(false, true, Ordering::SeqCst, Ordering::SeqCst)
+            .is_err()
+        {
+            return;
+        }
+
+        let tx = self.app_event_tx.clone();
+        let pending_redraw = self.pending_redraw.clone();
+        thread::spawn(move || {
+            thread::sleep(REDRAW_DEBOUNCE);
+            tx.send(AppEvent::Redraw);
+            pending_redraw.store(false, Ordering::SeqCst);
+        });
+    }
+
+    pub(crate) fn run(&mut self, terminal: &mut tui::Tui) -> Result<()> {
         // Insert an event to trigger the first render.
         let app_event_tx = self.app_event_tx.clone();
-        app_event_tx.send(AppEvent::Redraw);
+        app_event_tx.send(AppEvent::RequestRedraw);
 
         while let Ok(event) = self.app_event_rx.recv() {
             match event {
+                AppEvent::InsertHistory(lines) => {
+                    crate::insert_history::insert_history_lines(terminal, lines);
+                    self.app_event_tx.send(AppEvent::RequestRedraw);
+                }
+                AppEvent::RequestRedraw => {
+                    self.schedule_redraw();
+                }
                 AppEvent::Redraw => {
                     self.draw_next_frame(terminal)?;
                 }
@@ -185,9 +241,7 @@ impl<'a> App<'a> {
                         } => {
                             match &mut self.app_state {
                                 AppState::Chat { widget } => {
-                                    if widget.on_ctrl_c() {
-                                        self.app_event_tx.send(AppEvent::ExitRequest);
-                                    }
+                                    widget.on_ctrl_c();
                                 }
                                 AppState::Login { .. } | AppState::GitWarning { .. } => {
                                     // No-op.
@@ -199,7 +253,21 @@ impl<'a> App<'a> {
                             modifiers: crossterm::event::KeyModifiers::CONTROL,
                             ..
                         } => {
-                            self.app_event_tx.send(AppEvent::ExitRequest);
+                            match &mut self.app_state {
+                                AppState::Chat { widget } => {
+                                    if widget.composer_is_empty() {
+                                        self.app_event_tx.send(AppEvent::ExitRequest);
+                                    } else {
+                                        // Treat Ctrl+D as a normal key event when the composer
+                                        // is not empty so that it doesn't quit the application
+                                        // prematurely.
+                                        self.dispatch_key_event(key_event);
+                                    }
+                                }
+                                AppState::Login { .. } | AppState::GitWarning { .. } => {
+                                    self.app_event_tx.send(AppEvent::ExitRequest);
+                                }
+                            }
                         }
                         _ => {
                             self.dispatch_key_event(key_event);
@@ -235,12 +303,7 @@ impl<'a> App<'a> {
                             Vec::new(),
                         ));
                         self.app_state = AppState::Chat { widget: new_widget };
-                        self.app_event_tx.send(AppEvent::Redraw);
-                    }
-                    SlashCommand::ToggleMouseMode => {
-                        if let Err(e) = mouse_capture.toggle() {
-                            tracing::error!("Failed to toggle mouse mode: {e}");
-                        }
+                        self.app_event_tx.send(AppEvent::RequestRedraw);
                     }
                     SlashCommand::Quit => {
                         break;
@@ -266,6 +329,11 @@ impl<'a> App<'a> {
                             widget.add_diff_output(text);
                         }
                     }
+                    SlashCommand::Compact => {
+                        if let AppState::Chat { widget } = &mut self.app_state {
+                            widget.start_compact();
+                        }
+                    }
                 },
                 AppEvent::StartFileSearch(query) => {
                     self.file_search.on_user_query(query);
@@ -275,6 +343,11 @@ impl<'a> App<'a> {
                         widget.apply_file_search_result(query, matches);
                     }
                 }
+                AppEvent::CompactComplete(result) => {
+                    if let AppState::Chat { widget } = &mut self.app_state {
+                        widget.apply_compact_summary(result);
+                    }
+                }
             }
         }
         terminal.clear()?;
@@ -282,7 +355,18 @@ impl<'a> App<'a> {
         Ok(())
     }
 
+    pub(crate) fn token_usage(&self) -> codex_core::protocol::TokenUsage {
+        match &self.app_state {
+            AppState::Chat { widget } => widget.token_usage().clone(),
+            AppState::Login { .. } | AppState::GitWarning { .. } => {
+                codex_core::protocol::TokenUsage::default()
+            }
+        }
+    }
+
     fn draw_next_frame(&mut self, terminal: &mut tui::Tui) -> Result<()> {
+        // TODO: add a throttle to avoid redrawing too often
+
         match &mut self.app_state {
             AppState::Chat { widget } => {
                 terminal.draw(|frame| frame.render_widget_ref(&**widget, frame.area()))?;
@@ -320,7 +404,7 @@ impl<'a> App<'a> {
                         args.initial_images,
                     ));
                     self.app_state = AppState::Chat { widget };
-                    self.app_event_tx.send(AppEvent::Redraw);
+                    self.app_event_tx.send(AppEvent::RequestRedraw);
                 }
                 GitWarningOutcome::Quit => {
                     self.app_event_tx.send(AppEvent::ExitRequest);

codex-rs/tui/src/app_event.rs

@@ -1,6 +1,7 @@
 use codex_core::protocol::Event;
 use codex_file_search::FileMatch;
 use crossterm::event::KeyEvent;
+use ratatui::text::Line;
 
 use crate::slash_command::SlashCommand;
 
@@ -8,6 +9,10 @@ use crate::slash_command::SlashCommand;
 pub(crate) enum AppEvent {
     CodexEvent(Event),
 
+    /// Request a redraw which will be debounced by the [`App`].
+    RequestRedraw,
+
+    /// Actually draw the next frame.
     Redraw,
 
     KeyEvent(KeyEvent),
@@ -45,4 +50,11 @@ pub(crate) enum AppEvent {
         query: String,
         matches: Vec<FileMatch>,
     },
+
+    /// Result of the asynchronous `/compact` summarization.
+    CompactComplete(Result<String, String>),
+
+    /// Insert the most recently appended history entry directly into the
+    /// terminal scrollback. Carries already formatted lines.
+    InsertHistory(Vec<Line<'static>>),
 }

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

@@ -9,6 +9,7 @@ use crate::user_approval_widget::UserApprovalWidget;
 
 use super::BottomPane;
 use super::BottomPaneView;
+use super::CancellationEvent;
 
 /// Modal overlay asking the user to approve/deny a sequence of requests.
 pub(crate) struct ApprovalModalView<'a> {
@@ -46,12 +47,14 @@ impl<'a> BottomPaneView<'a> for ApprovalModalView<'a> {
         self.maybe_advance();
     }
 
-    fn is_complete(&self) -> bool {
-        self.current.is_complete() && self.queue.is_empty()
+    fn on_ctrl_c(&mut self, _pane: &mut BottomPane<'a>) -> CancellationEvent {
+        self.current.on_ctrl_c();
+        self.queue.clear();
+        CancellationEvent::Handled
     }
 
-    fn calculate_required_height(&self, area: &Rect) -> u16 {
-        self.current.get_height(area)
+    fn is_complete(&self) -> bool {
+        self.current.is_complete() && self.queue.is_empty()
     }
 
     fn render(&self, area: Rect, buf: &mut Buffer) {
@@ -63,3 +66,39 @@ impl<'a> BottomPaneView<'a> for ApprovalModalView<'a> {
         None
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::app_event::AppEvent;
+    use std::path::PathBuf;
+    use std::sync::mpsc::channel;
+
+    fn make_exec_request() -> ApprovalRequest {
+        ApprovalRequest::Exec {
+            id: "test".to_string(),
+            command: vec!["echo".to_string(), "hi".to_string()],
+            cwd: PathBuf::from("/tmp"),
+            reason: None,
+        }
+    }
+
+    #[test]
+    fn ctrl_c_aborts_and_clears_queue() {
+        let (tx_raw, _rx) = channel::<AppEvent>();
+        let tx = AppEventSender::new(tx_raw);
+        let first = make_exec_request();
+        let mut view = ApprovalModalView::new(first, tx);
+        view.enqueue_request(make_exec_request());
+
+        let (tx_raw2, _rx2) = channel::<AppEvent>();
+        let mut pane = BottomPane::new(super::super::BottomPaneParams {
+            app_event_tx: AppEventSender::new(tx_raw2),
+            has_input_focus: true,
+        });
+        assert_eq!(CancellationEvent::Handled, view.on_ctrl_c(&mut pane));
+        assert!(view.queue.is_empty());
+        assert!(view.current.is_complete());
+        assert!(view.is_complete());
+    }
+}

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

@@ -4,6 +4,7 @@ use ratatui::buffer::Buffer;
 use ratatui::layout::Rect;
 
 use super::BottomPane;
+use super::CancellationEvent;
 
 /// Type to use for a method that may require a redraw of the UI.
 pub(crate) enum ConditionalUpdate {
@@ -22,8 +23,10 @@ pub(crate) trait BottomPaneView<'a> {
         false
     }
 
-    /// Height required to render the view.
-    fn calculate_required_height(&self, area: &Rect) -> u16;
+    /// Handle Ctrl-C while this view is active.
+    fn on_ctrl_c(&mut self, _pane: &mut BottomPane<'a>) -> CancellationEvent {
+        CancellationEvent::Ignored
+    }
 
     /// Render the view: this will be displayed in place of the composer.
     fn render(&self, area: Rect, buf: &mut Buffer);

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

@@ -22,11 +22,6 @@ use crate::app_event::AppEvent;
 use crate::app_event_sender::AppEventSender;
 use codex_file_search::FileMatch;
 
-/// Minimum number of visible text rows inside the textarea.
-const MIN_TEXTAREA_ROWS: usize = 1;
-/// Rows consumed by the border.
-const BORDER_LINES: u16 = 2;
-
 const BASE_PLACEHOLDER_TEXT: &str = "send a message";
 /// If the pasted content exceeds this number of characters, replace it with a
 /// placeholder in the UI.
@@ -76,6 +71,11 @@ impl ChatComposer<'_> {
         this
     }
 
+    /// Returns true if the composer currently contains no user input.
+    pub(crate) fn is_empty(&self) -> bool {
+        self.textarea.is_empty()
+    }
+
     /// Update the cached *context-left* percentage and refresh the placeholder
     /// text. The UI relies on the placeholder to convey the remaining
     /// context when the composer is empty.
@@ -127,10 +127,6 @@ impl ChatComposer<'_> {
             .on_entry_response(log_id, offset, entry, &mut self.textarea)
     }
 
-    pub fn set_input_focus(&mut self, has_focus: bool) {
-        self.update_border(has_focus);
-    }
-
     pub fn handle_paste(&mut self, pasted: String) -> bool {
         let char_count = pasted.chars().count();
         if char_count > LARGE_PASTE_CHAR_THRESHOLD {
@@ -604,17 +600,6 @@ impl ChatComposer<'_> {
         self.dismissed_file_popup_token = None;
     }
 
-    pub fn calculate_required_height(&self, area: &Rect) -> u16 {
-        let rows = self.textarea.lines().len().max(MIN_TEXTAREA_ROWS);
-        let num_popup_rows = match &self.active_popup {
-            ActivePopup::Command(popup) => popup.calculate_required_height(area),
-            ActivePopup::File(popup) => popup.calculate_required_height(area),
-            ActivePopup::None => 0,
-        };
-
-        rows as u16 + BORDER_LINES + num_popup_rows
-    }
-
     fn update_border(&mut self, has_focus: bool) {
         struct BlockState {
             right_title: Line<'static>,
@@ -649,13 +634,6 @@ impl ChatComposer<'_> {
                 .border_style(bs.border_style),
         );
     }
-
-    pub(crate) fn is_popup_visible(&self) -> bool {
-        match self.active_popup {
-            ActivePopup::Command(_) | ActivePopup::File(_) => true,
-            ActivePopup::None => false,
-        }
-    }
 }
 
 impl WidgetRef for &ChatComposer<'_> {

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

@@ -72,8 +72,7 @@ impl ChatComposerHistory {
             return false;
         }
 
-        let lines = textarea.lines();
-        if lines.len() == 1 && lines[0].is_empty() {
+        if textarea.is_empty() {
             return true;
         }
 
@@ -85,6 +84,7 @@ impl ChatComposerHistory {
             return false;
         }
 
+        let lines = textarea.lines();
         matches!(&self.last_history_text, Some(prev) if prev == &lines.join("\n"))
     }
 

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

@@ -20,6 +20,12 @@ mod command_popup;
 mod file_search_popup;
 mod status_indicator_view;
 
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub(crate) enum CancellationEvent {
+    Ignored,
+    Handled,
+}
+
 pub(crate) use chat_composer::ChatComposer;
 pub(crate) use chat_composer::InputResult;
 
@@ -65,10 +71,8 @@ impl BottomPane<'_> {
             if !view.is_complete() {
                 self.active_view = Some(view);
             } else if self.is_task_running {
-                let height = self.composer.calculate_required_height(&Rect::default());
                 self.active_view = Some(Box::new(StatusIndicatorView::new(
                     self.app_event_tx.clone(),
-                    height,
                 )));
             }
             self.request_redraw();
@@ -82,6 +86,33 @@ impl BottomPane<'_> {
         }
     }
 
+    /// Handle Ctrl-C in the bottom pane. If a modal view is active it gets a
+    /// chance to consume the event (e.g. to dismiss itself).
+    pub(crate) fn on_ctrl_c(&mut self) -> CancellationEvent {
+        let mut view = match self.active_view.take() {
+            Some(view) => view,
+            None => return CancellationEvent::Ignored,
+        };
+
+        let event = view.on_ctrl_c(self);
+        match event {
+            CancellationEvent::Handled => {
+                if !view.is_complete() {
+                    self.active_view = Some(view);
+                } else if self.is_task_running {
+                    self.active_view = Some(Box::new(StatusIndicatorView::new(
+                        self.app_event_tx.clone(),
+                    )));
+                }
+                self.show_ctrl_c_quit_hint();
+            }
+            CancellationEvent::Ignored => {
+                self.active_view = Some(view);
+            }
+        }
+        event
+    }
+
     pub fn handle_paste(&mut self, pasted: String) {
         if self.active_view.is_none() {
             let needs_redraw = self.composer.handle_paste(pasted);
@@ -106,12 +137,6 @@ impl BottomPane<'_> {
         }
     }
 
-    /// Update the UI to reflect whether this `BottomPane` has input focus.
-    pub(crate) fn set_input_focus(&mut self, has_focus: bool) {
-        self.has_input_focus = has_focus;
-        self.composer.set_input_focus(has_focus);
-    }
-
     pub(crate) fn show_ctrl_c_quit_hint(&mut self) {
         self.ctrl_c_quit_hint = true;
         self.composer
@@ -138,10 +163,8 @@ impl BottomPane<'_> {
         match (running, self.active_view.is_some()) {
             (true, false) => {
                 // Show status indicator overlay.
-                let height = self.composer.calculate_required_height(&Rect::default());
                 self.active_view = Some(Box::new(StatusIndicatorView::new(
                     self.app_event_tx.clone(),
-                    height,
                 )));
                 self.request_redraw();
             }
@@ -162,6 +185,10 @@ impl BottomPane<'_> {
         }
     }
 
+    pub(crate) fn composer_is_empty(&self) -> bool {
+        self.composer.is_empty()
+    }
+
     pub(crate) fn is_task_running(&self) -> bool {
         self.is_task_running
     }
@@ -199,21 +226,8 @@ impl BottomPane<'_> {
     }
 
     /// Height (terminal rows) required by the current bottom pane.
-    pub fn calculate_required_height(&self, area: &Rect) -> u16 {
-        if let Some(view) = &self.active_view {
-            view.calculate_required_height(area)
-        } else {
-            self.composer.calculate_required_height(area)
-        }
-    }
-
     pub(crate) fn request_redraw(&self) {
-        self.app_event_tx.send(AppEvent::Redraw)
-    }
-
-    /// Returns true when a popup inside the composer is visible.
-    pub(crate) fn is_popup_visible(&self) -> bool {
-        self.active_view.is_none() && self.composer.is_popup_visible()
+        self.app_event_tx.send(AppEvent::RequestRedraw)
     }
 
     // --- History helpers ---
@@ -253,3 +267,34 @@ impl WidgetRef for &BottomPane<'_> {
         }
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::app_event::AppEvent;
+    use std::path::PathBuf;
+    use std::sync::mpsc::channel;
+
+    fn exec_request() -> ApprovalRequest {
+        ApprovalRequest::Exec {
+            id: "1".to_string(),
+            command: vec!["echo".into(), "ok".into()],
+            cwd: PathBuf::from("."),
+            reason: None,
+        }
+    }
+
+    #[test]
+    fn ctrl_c_on_modal_consumes_and_shows_quit_hint() {
+        let (tx_raw, _rx) = channel::<AppEvent>();
+        let tx = AppEventSender::new(tx_raw);
+        let mut pane = BottomPane::new(BottomPaneParams {
+            app_event_tx: tx,
+            has_input_focus: true,
+        });
+        pane.push_approval_request(exec_request());
+        assert_eq!(CancellationEvent::Handled, pane.on_ctrl_c());
+        assert!(pane.ctrl_c_quit_hint_visible());
+        assert_eq!(CancellationEvent::Ignored, pane.on_ctrl_c());
+    }
+}

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

@@ -1,5 +1,4 @@
 use ratatui::buffer::Buffer;
-use ratatui::layout::Rect;
 use ratatui::widgets::WidgetRef;
 
 use crate::app_event_sender::AppEventSender;
@@ -13,9 +12,9 @@ pub(crate) struct StatusIndicatorView {
 }
 
 impl StatusIndicatorView {
-    pub fn new(app_event_tx: AppEventSender, height: u16) -> Self {
+    pub fn new(app_event_tx: AppEventSender) -> Self {
         Self {
-            view: StatusIndicatorWidget::new(app_event_tx, height),
+            view: StatusIndicatorWidget::new(app_event_tx),
         }
     }
 
@@ -24,7 +23,7 @@ impl StatusIndicatorView {
     }
 }
 
-impl<'a> BottomPaneView<'a> for StatusIndicatorView {
+impl BottomPaneView<'_> for StatusIndicatorView {
     fn update_status_text(&mut self, text: String) -> ConditionalUpdate {
         self.update_text(text);
         ConditionalUpdate::NeedsRedraw
@@ -34,11 +33,7 @@ impl<'a> BottomPaneView<'a> for StatusIndicatorView {
         true
     }
 
-    fn calculate_required_height(&self, _area: &Rect) -> u16 {
-        self.view.get_height()
-    }
-
-    fn render(&self, area: Rect, buf: &mut Buffer) {
+    fn render(&self, area: ratatui::layout::Rect, buf: &mut Buffer) {
         self.view.render_ref(area, buf);
     }
 }

codex-rs/tui/src/chatwidget.rs

@@ -1,9 +1,12 @@
 use std::path::PathBuf;
 use std::sync::Arc;
 
+use codex_core::codex_wrapper::CodexConversation;
 use codex_core::codex_wrapper::init_codex;
 use codex_core::config::Config;
+use codex_core::protocol::AgentMessageDeltaEvent;
 use codex_core::protocol::AgentMessageEvent;
+use codex_core::protocol::AgentReasoningDeltaEvent;
 use codex_core::protocol::AgentReasoningEvent;
 use codex_core::protocol::ApplyPatchApprovalRequestEvent;
 use codex_core::protocol::ErrorEvent;
@@ -21,9 +24,6 @@ use codex_core::protocol::TaskCompleteEvent;
 use codex_core::protocol::TokenUsage;
 use crossterm::event::KeyEvent;
 use ratatui::buffer::Buffer;
-use ratatui::layout::Constraint;
-use ratatui::layout::Direction;
-use ratatui::layout::Layout;
 use ratatui::layout::Rect;
 use ratatui::widgets::Widget;
 use ratatui::widgets::WidgetRef;
@@ -34,8 +34,13 @@ use crate::app_event::AppEvent;
 use crate::app_event_sender::AppEventSender;
 use crate::bottom_pane::BottomPane;
 use crate::bottom_pane::BottomPaneParams;
+use crate::bottom_pane::CancellationEvent;
 use crate::bottom_pane::InputResult;
+use crate::compact::Role;
+use crate::compact::TranscriptEntry;
+use crate::compact::generate_compact_summary;
 use crate::conversation_history_widget::ConversationHistoryWidget;
+use crate::exec_command::strip_bash_lc_and_escape;
 use crate::history_cell::PatchEventType;
 use crate::user_approval_widget::ApprovalRequest;
 use codex_file_search::FileMatch;
@@ -45,16 +50,15 @@ pub(crate) struct ChatWidget<'a> {
     codex_op_tx: UnboundedSender<Op>,
     conversation_history: ConversationHistoryWidget,
     bottom_pane: BottomPane<'a>,
-    input_focus: InputFocus,
     config: Config,
     initial_user_message: Option<UserMessage>,
     token_usage: TokenUsage,
-}
-
-#[derive(Clone, Copy, Eq, PartialEq)]
-enum InputFocus {
-    HistoryPane,
-    BottomPane,
+    // Buffer for streaming assistant reasoning text; emitted on final event.
+    reasoning_buffer: String,
+    // Buffer for streaming assistant answer text; emitted on final event.
+    answer_buffer: String,
+    // Transcript of chat for `/compact` summarization.
+    transcript: Vec<TranscriptEntry>,
 }
 
 struct UserMessage {
@@ -92,7 +96,11 @@ impl ChatWidget<'_> {
         // Create the Codex asynchronously so the UI loads as quickly as possible.
         let config_for_agent_loop = config.clone();
         tokio::spawn(async move {
-            let (codex, session_event, _ctrl_c) = match init_codex(config_for_agent_loop).await {
+            let CodexConversation {
+                codex,
+                session_configured,
+                ..
+            } = match init_codex(config_for_agent_loop).await {
                 Ok(vals) => vals,
                 Err(e) => {
                     // TODO: surface this error to the user.
@@ -103,7 +111,7 @@ impl ChatWidget<'_> {
 
             // Forward the captured `SessionInitialized` event that was consumed
             // inside `init_codex()` so it can be rendered in the UI.
-            app_event_tx_clone.send(AppEvent::CodexEvent(session_event.clone()));
+            app_event_tx_clone.send(AppEvent::CodexEvent(session_configured.clone()));
             let codex = Arc::new(codex);
             let codex_clone = codex.clone();
             tokio::spawn(async move {
@@ -128,55 +136,37 @@ impl ChatWidget<'_> {
                 app_event_tx,
                 has_input_focus: true,
             }),
-            input_focus: InputFocus::BottomPane,
             config,
             initial_user_message: create_initial_user_message(
                 initial_prompt.unwrap_or_default(),
                 initial_images,
             ),
             token_usage: TokenUsage::default(),
+            reasoning_buffer: String::new(),
+            answer_buffer: String::new(),
+            transcript: Vec::new(),
         }
     }
 
     pub(crate) fn handle_key_event(&mut self, key_event: KeyEvent) {
         self.bottom_pane.clear_ctrl_c_quit_hint();
-        // Special-case <Tab>: normally toggles focus between history and bottom panes.
-        // However, when the slash-command popup is visible we forward the key
-        // to the bottom pane so it can handle auto-completion.
-        if matches!(key_event.code, crossterm::event::KeyCode::Tab)
-            && !self.bottom_pane.is_popup_visible()
-        {
-            self.input_focus = match self.input_focus {
-                InputFocus::HistoryPane => InputFocus::BottomPane,
-                InputFocus::BottomPane => InputFocus::HistoryPane,
-            };
-            self.conversation_history
-                .set_input_focus(self.input_focus == InputFocus::HistoryPane);
-            self.bottom_pane
-                .set_input_focus(self.input_focus == InputFocus::BottomPane);
-            self.request_redraw();
-            return;
-        }
 
-        match self.input_focus {
-            InputFocus::HistoryPane => {
-                let needs_redraw = self.conversation_history.handle_key_event(key_event);
-                if needs_redraw {
-                    self.request_redraw();
-                }
+        match self.bottom_pane.handle_key_event(key_event) {
+            InputResult::Submitted(text) => {
+                self.submit_user_message(text.into());
             }
-            InputFocus::BottomPane => match self.bottom_pane.handle_key_event(key_event) {
-                InputResult::Submitted(text) => {
-                    self.submit_user_message(text.into());
-                }
-                InputResult::None => {}
-            },
+            InputResult::None => {}
         }
     }
 
     pub(crate) fn handle_paste(&mut self, text: String) {
-        if matches!(self.input_focus, InputFocus::BottomPane) {
-            self.bottom_pane.handle_paste(text);
+        self.bottom_pane.handle_paste(text);
+    }
+
+    /// Emits the last entry's plain lines from conversation_history, if any.
+    fn emit_last_history_entry(&mut self) {
+        if let Some(lines) = self.conversation_history.last_entry_plain_lines() {
+            self.app_event_tx.send(AppEvent::InsertHistory(lines));
         }
     }
 
@@ -213,7 +203,14 @@ impl ChatWidget<'_> {
 
         // Only show text portion in conversation history for now.
         if !text.is_empty() {
-            self.conversation_history.add_user_message(text);
+            // Forward a copy for history and emit into scrollback.
+            self.conversation_history.add_user_message(text.clone());
+            self.emit_last_history_entry();
+            // Record in transcript for `/compact`.
+            self.transcript.push(TranscriptEntry {
+                role: Role::User,
+                text,
+            });
         }
         self.conversation_history.scroll_to_bottom();
     }
@@ -225,6 +222,10 @@ impl ChatWidget<'_> {
                 // Record session information at the top of the conversation.
                 self.conversation_history
                     .add_session_info(&self.config, event.clone());
+                // Immediately surface the session banner / settings summary in
+                // scrollback so the user can review configuration (model,
+                // sandbox, approvals, etc.) before interacting.
+                self.emit_last_history_entry();
 
                 // Forward history metadata to the bottom pane so the chat
                 // composer can navigate through past messages.
@@ -240,16 +241,53 @@ impl ChatWidget<'_> {
                 self.request_redraw();
             }
             EventMsg::AgentMessage(AgentMessageEvent { message }) => {
-                self.conversation_history
-                    .add_agent_message(&self.config, message);
+                // Final assistant answer. Prefer the fully provided message.
+                let full = if message.is_empty() {
+                    std::mem::take(&mut self.answer_buffer)
+                } else {
+                    self.answer_buffer.clear();
+                    message
+                };
+                if !full.is_empty() {
+                    self.conversation_history
+                        .add_agent_message(&self.config, full.clone());
+                    self.emit_last_history_entry();
+                    // Record final answer in transcript for `/compact`.
+                    self.transcript.push(TranscriptEntry {
+                        role: Role::Assistant,
+                        text: full,
+                    });
+                }
                 self.request_redraw();
             }
+            EventMsg::AgentMessageDelta(AgentMessageDeltaEvent { delta }) => {
+                // Buffer only – do not emit partial lines. This avoids cases
+                // where long responses appear truncated if the terminal
+                // wrapped early. The full message is emitted on
+                // AgentMessage.
+                self.answer_buffer.push_str(&delta);
+            }
+            EventMsg::AgentReasoningDelta(AgentReasoningDeltaEvent { delta }) => {
+                // Buffer only – disable incremental reasoning streaming so we
+                // avoid truncated intermediate lines. Full text emitted on
+                // AgentReasoning.
+                self.reasoning_buffer.push_str(&delta);
+            }
             EventMsg::AgentReasoning(AgentReasoningEvent { text }) => {
-                if !self.config.hide_agent_reasoning {
+                // Emit full reasoning text once. Some providers might send
+                // final event with empty text if only deltas were used.
+                let full = if text.is_empty() {
+                    std::mem::take(&mut self.reasoning_buffer)
+                } else {
+                    self.reasoning_buffer.clear();
+                    text
+                };
+                if !full.is_empty() {
                     self.conversation_history
-                        .add_agent_reasoning(&self.config, text);
-                    self.request_redraw();
+                        .add_agent_reasoning(&self.config, full);
+                    self.emit_last_history_entry();
                 }
+                self.request_redraw();
             }
             EventMsg::TaskStarted => {
                 self.bottom_pane.clear_ctrl_c_quit_hint();
@@ -268,14 +306,30 @@ impl ChatWidget<'_> {
                     .set_token_usage(self.token_usage.clone(), self.config.model_context_window);
             }
             EventMsg::Error(ErrorEvent { message }) => {
-                self.conversation_history.add_error(message);
+                self.conversation_history.add_error(message.clone());
+                self.emit_last_history_entry();
                 self.bottom_pane.set_task_running(false);
             }
             EventMsg::ExecApprovalRequest(ExecApprovalRequestEvent {
+                call_id: _,
                 command,
                 cwd,
                 reason,
             }) => {
+                // Print the command to the history so it is visible in the
+                // transcript *before* the modal asks for approval.
+                let cmdline = strip_bash_lc_and_escape(&command);
+                let text = format!(
+                    "command requires approval:\n$ {cmdline}{reason}",
+                    reason = reason
+                        .as_ref()
+                        .map(|r| format!("\n{r}"))
+                        .unwrap_or_default()
+                );
+                self.conversation_history.add_background_event(text);
+                self.emit_last_history_entry();
+                self.conversation_history.scroll_to_bottom();
+
                 let request = ApprovalRequest::Exec {
                     id,
                     command,
@@ -283,8 +337,10 @@ impl ChatWidget<'_> {
                     reason,
                 };
                 self.bottom_pane.push_approval_request(request);
+                self.request_redraw();
             }
             EventMsg::ApplyPatchApprovalRequest(ApplyPatchApprovalRequestEvent {
+                call_id: _,
                 changes,
                 reason,
                 grant_root,
@@ -302,6 +358,7 @@ impl ChatWidget<'_> {
 
                 self.conversation_history
                     .add_patch_event(PatchEventType::ApprovalRequest, changes);
+                self.emit_last_history_entry();
 
                 self.conversation_history.scroll_to_bottom();
 
@@ -321,6 +378,7 @@ impl ChatWidget<'_> {
             }) => {
                 self.conversation_history
                     .add_active_exec_command(call_id, command);
+                self.emit_last_history_entry();
                 self.request_redraw();
             }
             EventMsg::PatchApplyBegin(PatchApplyBeginEvent {
@@ -332,6 +390,7 @@ impl ChatWidget<'_> {
                 // summary so the user can follow along.
                 self.conversation_history
                     .add_patch_event(PatchEventType::ApplyBegin { auto_approved }, changes);
+                self.emit_last_history_entry();
                 if !auto_approved {
                     self.conversation_history.scroll_to_bottom();
                 }
@@ -355,6 +414,7 @@ impl ChatWidget<'_> {
             }) => {
                 self.conversation_history
                     .add_active_mcp_tool_call(call_id, server, tool, arguments);
+                self.emit_last_history_entry();
                 self.request_redraw();
             }
             EventMsg::McpToolCallEnd(mcp_tool_call_end_event) => {
@@ -375,9 +435,13 @@ impl ChatWidget<'_> {
                 self.bottom_pane
                     .on_history_entry_response(log_id, offset, entry.map(|e| e.text));
             }
+            EventMsg::ShutdownComplete => {
+                self.app_event_tx.send(AppEvent::ExitRequest);
+            }
             event => {
                 self.conversation_history
                     .add_background_event(format!("{event:?}"));
+                self.emit_last_history_entry();
                 self.request_redraw();
             }
         }
@@ -390,11 +454,13 @@ impl ChatWidget<'_> {
     }
 
     fn request_redraw(&mut self) {
-        self.app_event_tx.send(AppEvent::Redraw);
+        self.app_event_tx.send(AppEvent::RequestRedraw);
     }
 
     pub(crate) fn add_diff_output(&mut self, diff_output: String) {
-        self.conversation_history.add_diff_output(diff_output);
+        self.conversation_history
+            .add_diff_output(diff_output.clone());
+        self.emit_last_history_entry();
         self.request_redraw();
     }
 
@@ -416,41 +482,133 @@ impl ChatWidget<'_> {
         self.bottom_pane.on_file_search_result(query, matches);
     }
 
+    // (removed deprecated synchronous `compact` implementation)
+
+    /// Kick off an asynchronous summarization of the current transcript.
+    /// Returns immediately so the UI stays responsive.
+    pub(crate) fn start_compact(&mut self) {
+        // Show status indicator immediately.
+        self.bottom_pane.set_task_running(true);
+        self.bottom_pane
+            .update_status_text("Summarizing context…".to_string());
+        self.request_redraw();
+
+        // Clone data required for the background task.
+        let transcript = self.transcript.clone();
+        let model = self.config.model.clone();
+        let config_clone = self.config.clone();
+        let app_event_tx = self.app_event_tx.clone();
+
+        // Spawn the summarization on a blocking thread to avoid CPU-bound work
+        // stalling the async runtime (and thus the UI).
+        tokio::task::spawn_blocking(move || {
+            let rt = tokio::runtime::Handle::current();
+            rt.block_on(async move {
+                let result = generate_compact_summary(&transcript, &model, &config_clone).await;
+                let evt = match result {
+                    Ok(summary) => AppEvent::CompactComplete(Ok(summary)),
+                    Err(e) => AppEvent::CompactComplete(Err(format!("{e}"))),
+                };
+                app_event_tx.send(evt);
+            });
+        });
+    }
+
+    /// Apply the completed summary returned by the background task.
+    pub(crate) fn apply_compact_summary(&mut self, result: Result<String, String>) {
+        match result {
+            Ok(summary) => {
+                self.conversation_history.clear_agent_history();
+                self.transcript.clear();
+                // clear session history in backend
+                self.submit_op(Op::EraseConversationHistory);
+                self.conversation_history
+                    .add_agent_message(&self.config, summary.clone());
+                self.transcript = vec![TranscriptEntry {
+                    role: Role::Assistant,
+                    text: summary,
+                }];
+
+                // Re-configure the Codex session so that the backend agent starts with
+                // a clean conversation context.
+                let op = Op::ConfigureSession {
+                    provider: self.config.model_provider.clone(),
+                    model: self.config.model.clone(),
+                    model_reasoning_effort: self.config.model_reasoning_effort,
+                    model_reasoning_summary: self.config.model_reasoning_summary,
+                    user_instructions: self.config.user_instructions.clone(),
+                    base_instructions: self.config.base_instructions.clone(),
+                    approval_policy: self.config.approval_policy,
+                    sandbox_policy: self.config.sandbox_policy.clone(),
+                    disable_response_storage: self.config.disable_response_storage,
+                    notify: self.config.notify.clone(),
+                    cwd: self.config.cwd.clone(),
+                    resume_path: None,
+                };
+                self.submit_op(op);
+
+                // Reset the recorded token usage because we start a fresh
+                // conversation context. This ensures the *context remaining*
+                // indicator in the composer is updated immediately.
+                self.token_usage = TokenUsage::default();
+                self.bottom_pane
+                    .set_token_usage(self.token_usage.clone(), self.config.model_context_window);
+            }
+            Err(msg) => {
+                self.conversation_history.add_error(msg);
+            }
+        }
+
+        // Hide status indicator and refresh UI.
+        self.bottom_pane.set_task_running(false);
+        self.request_redraw();
+    }
+
     /// Handle Ctrl-C key press.
-    /// Returns true if the key press was handled, false if it was not.
-    /// If the key press was not handled, the caller should handle it (likely by exiting the process).
-    pub(crate) fn on_ctrl_c(&mut self) -> bool {
+    /// Returns CancellationEvent::Handled if the event was consumed by the UI, or
+    /// CancellationEvent::Ignored if the caller should handle it (e.g. exit).
+    pub(crate) fn on_ctrl_c(&mut self) -> CancellationEvent {
+        match self.bottom_pane.on_ctrl_c() {
+            CancellationEvent::Handled => return CancellationEvent::Handled,
+            CancellationEvent::Ignored => {}
+        }
         if self.bottom_pane.is_task_running() {
             self.bottom_pane.clear_ctrl_c_quit_hint();
             self.submit_op(Op::Interrupt);
-            false
+            self.answer_buffer.clear();
+            self.reasoning_buffer.clear();
+            CancellationEvent::Ignored
         } else if self.bottom_pane.ctrl_c_quit_hint_visible() {
-            true
+            self.submit_op(Op::Shutdown);
+            CancellationEvent::Handled
         } else {
             self.bottom_pane.show_ctrl_c_quit_hint();
-            false
+            CancellationEvent::Ignored
         }
     }
 
+    pub(crate) fn composer_is_empty(&self) -> bool {
+        self.bottom_pane.composer_is_empty()
+    }
+
     /// Forward an `Op` directly to codex.
     pub(crate) fn submit_op(&self, op: Op) {
         if let Err(e) = self.codex_op_tx.send(op) {
             tracing::error!("failed to submit op: {e}");
         }
     }
+
+    pub(crate) fn token_usage(&self) -> &TokenUsage {
+        &self.token_usage
+    }
 }
 
 impl WidgetRef for &ChatWidget<'_> {
     fn render_ref(&self, area: Rect, buf: &mut Buffer) {
-        let bottom_height = self.bottom_pane.calculate_required_height(&area);
-
-        let chunks = Layout::default()
-            .direction(Direction::Vertical)
-            .constraints([Constraint::Min(0), Constraint::Length(bottom_height)])
-            .split(area);
-
-        self.conversation_history.render(chunks[0], buf);
-        (&self.bottom_pane).render(chunks[1], buf);
+        // In the hybrid inline viewport mode we only draw the interactive
+        // bottom pane; history entries are injected directly into scrollback
+        // via `Terminal::insert_before`.
+        (&self.bottom_pane).render(area, buf);
     }
 }
 

codex-rs/tui/src/compact.rs

@@ -0,0 +1,91 @@
+use anyhow::Result;
+use anyhow::anyhow;
+use codex_core::config::Config;
+use codex_core::openai_api_key::get_openai_api_key;
+use serde::Serialize;
+
+#[derive(Clone)]
+pub enum Role {
+    User,
+    Assistant,
+}
+
+#[derive(Clone)]
+pub struct TranscriptEntry {
+    pub role: Role,
+    pub text: String,
+}
+
+impl TranscriptEntry {
+    fn role_str(&self) -> &'static str {
+        match self.role {
+            Role::User => "user",
+            Role::Assistant => "assistant",
+        }
+    }
+}
+
+#[derive(Serialize)]
+struct Message<'a> {
+    role: &'a str,
+    content: String,
+}
+
+#[derive(Serialize)]
+struct Payload<'a> {
+    model: &'a str,
+    messages: Vec<Message<'a>>,
+}
+
+/// Generate a concise summary of the provided transcript using the OpenAI chat
+/// completions API.
+pub async fn generate_compact_summary(
+    transcript: &[TranscriptEntry],
+    model: &str,
+    config: &Config,
+) -> Result<String> {
+    let conversation_text = transcript
+        .iter()
+        .map(|e| format!("{}: {}", e.role_str(), e.text))
+        .collect::<Vec<_>>()
+        .join("\n");
+
+    let messages = vec![
+        Message {
+            role: "assistant",
+            content: "You are an expert coding assistant. Your goal is to generate a concise, structured summary of the conversation below that captures all essential information needed to continue development after context replacement. Include tasks performed, code areas modified or reviewed, key decisions or assumptions, test results or errors, and outstanding tasks or next steps.".to_string(),
+        },
+        Message {
+            role: "user",
+            content: format!(
+                "Here is the conversation so far:\n{conversation_text}\n\nPlease summarize this conversation, covering:\n1. Tasks performed and outcomes\n2. Code files, modules, or functions modified or examined\n3. Important decisions or assumptions made\n4. Errors encountered and test or build results\n5. Remaining tasks, open questions, or next steps\nProvide the summary in a clear, concise format."
+            ),
+        },
+    ];
+
+    let api_key = get_openai_api_key().ok_or_else(|| anyhow!("OpenAI API key not set"))?;
+    let client = reqwest::Client::new();
+    let base = config.model_provider.base_url.trim_end_matches('/');
+    let url = format!("{}/chat/completions", base);
+
+    let payload = Payload { model, messages };
+    let res = client
+        .post(url)
+        .bearer_auth(api_key)
+        .json(&payload)
+        .send()
+        .await?;
+
+    let body: serde_json::Value = res.json().await?;
+    if let Some(summary) = body
+        .get("choices")
+        .and_then(|c| c.get(0))
+        .and_then(|c| c.get("message"))
+        .and_then(|m| m.get("content"))
+        .and_then(|v| v.as_str())
+    {
+        Ok(summary.to_string())
+    } else {
+        Ok("Unable to generate summary.".to_string())
+    }
+}

codex-rs/tui/src/conversation_history_widget.rs

@@ -5,8 +5,6 @@ use crate::history_cell::PatchEventType;
 use codex_core::config::Config;
 use codex_core::protocol::FileChange;
 use codex_core::protocol::SessionConfiguredEvent;
-use crossterm::event::KeyCode;
-use crossterm::event::KeyEvent;
 use ratatui::prelude::*;
 use ratatui::style::Style;
 use ratatui::widgets::*;
@@ -47,33 +45,6 @@ impl ConversationHistoryWidget {
         }
     }
 
-    pub(crate) fn set_input_focus(&mut self, has_input_focus: bool) {
-        self.has_input_focus = has_input_focus;
-    }
-
-    /// Returns true if it needs a redraw.
-    pub(crate) fn handle_key_event(&mut self, key_event: KeyEvent) -> bool {
-        match key_event.code {
-            KeyCode::Up | KeyCode::Char('k') => {
-                self.scroll_up(1);
-                true
-            }
-            KeyCode::Down | KeyCode::Char('j') => {
-                self.scroll_down(1);
-                true
-            }
-            KeyCode::PageUp | KeyCode::Char('b') => {
-                self.scroll_page_up();
-                true
-            }
-            KeyCode::PageDown | KeyCode::Char(' ') => {
-                self.scroll_page_down();
-                true
-            }
-            _ => false,
-        }
-    }
-
     /// Negative delta scrolls up; positive delta scrolls down.
     pub(crate) fn scroll(&mut self, delta: i32) {
         match delta.cmp(&0) {
@@ -122,53 +93,6 @@ impl ConversationHistoryWidget {
         }
     }
 
-    /// Scroll up by one full viewport height (Page Up).
-    fn scroll_page_up(&mut self) {
-        let viewport_height = self.last_viewport_height.get().max(1);
-
-        // If we are currently in the "stick to bottom" mode, first convert the
-        // implicit scroll position (`usize::MAX`) into an explicit offset that
-        // represents the very bottom of the scroll region.  This mirrors the
-        // logic from `scroll_up()`.
-        if self.scroll_position == usize::MAX {
-            self.scroll_position = self
-                .num_rendered_lines
-                .get()
-                .saturating_sub(viewport_height);
-        }
-
-        // Move up by a full page.
-        self.scroll_position = self.scroll_position.saturating_sub(viewport_height);
-    }
-
-    /// Scroll down by one full viewport height (Page Down).
-    fn scroll_page_down(&mut self) {
-        // Nothing to do if we're already stuck to the bottom.
-        if self.scroll_position == usize::MAX {
-            return;
-        }
-
-        let viewport_height = self.last_viewport_height.get().max(1);
-        let num_lines = self.num_rendered_lines.get();
-
-        // Calculate the maximum explicit scroll offset that is still within
-        // range. This matches the logic in `scroll_down()` and the render
-        // method.
-        let max_scroll = num_lines.saturating_sub(viewport_height);
-
-        // Attempt to move down by a full page.
-        let new_pos = self.scroll_position.saturating_add(viewport_height);
-
-        if new_pos >= max_scroll {
-            // We have reached (or passed) the bottom – switch back to
-            // automatic stick‑to‑bottom mode so that subsequent output keeps
-            // the viewport pinned.
-            self.scroll_position = usize::MAX;
-        } else {
-            self.scroll_position = new_pos;
-        }
-    }
-
     pub fn scroll_to_bottom(&mut self) {
         self.scroll_position = usize::MAX;
     }
@@ -198,6 +122,10 @@ impl ConversationHistoryWidget {
         self.add_to_history(HistoryCell::new_agent_message(config, message));
     }
 
+    pub fn clear_agent_history(&mut self) {
+        self.clear_all();
+    }
+
     pub fn add_agent_reasoning(&mut self, config: &Config, text: String) {
         self.add_to_history(HistoryCell::new_agent_reasoning(config, text));
     }
@@ -249,6 +177,16 @@ impl ConversationHistoryWidget {
         });
     }
 
+    fn clear_all(&mut self) {
+        self.entries.clear();
+    }
+
+    /// Return the lines for the most recently appended entry (if any) so the
+    /// parent widget can surface them via the new scrollback insertion path.
+    pub(crate) fn last_entry_plain_lines(&self) -> Option<Vec<Line<'static>>> {
+        self.entries.last().map(|e| e.cell.plain_lines())
+    }
+
     pub fn record_completed_exec_command(
         &mut self,
         call_id: String,
@@ -454,7 +392,7 @@ impl WidgetRef for ConversationHistoryWidget {
 
         {
             // Choose a thumb color that stands out only when this pane has focus so that the
-            // user’s attention is naturally drawn to the active viewport. When unfocused we show
+            // user's attention is naturally drawn to the active viewport. When unfocused we show
             // a low-contrast thumb so the scrollbar fades into the background without becoming
             // invisible.
             let thumb_style = if self.has_input_focus {