Merge remote-tracking branch 'origin/main' into streaming

Stream models thoughts and responses instead of waiting for the whole
thing to come through. Very rough right now, but I'm making the risk call to push through.

.github/actions/codex/bun.lock

@@ -11,7 +11,7 @@
         "@types/bun": "^1.2.19",
         "@types/node": "^24.1.0",
         "prettier": "^3.6.2",
-        "typescript": "^5.8.3",
+        "typescript": "^5.9.2",
       },
     },
   },
@@ -68,7 +68,7 @@
 
     "tunnel": ["tunnel@0.0.6", "", {}, "sha512-1h/Lnq9yajKY2PEbBadPXj3VxsDDu844OnaAo52UVmIzIvwwtBPIuNvkjuzBlTWpfJyUbG3ez0KSBibQkj4ojg=="],
 
-    "typescript": ["typescript@5.8.3", "", { "bin": { "tsc": "bin/tsc", "tsserver": "bin/tsserver" } }, "sha512-p1diW6TqL9L07nNxvRMM7hMMw4c5XOo/1ibL4aAIGmSAt9slTE1Xgw5KWuof2uTOvCg9BY7ZRi+GaF+7sfgPeQ=="],
+    "typescript": ["typescript@5.9.2", "", { "bin": { "tsc": "bin/tsc", "tsserver": "bin/tsserver" } }, "sha512-CWBzXQrc/qOkhidw1OzBTQuYRbfyxDXJMVJ1XNwUHGROVmuaeiEm3OslpZ1RV96d7SKKjZKrSJu3+t/xlw3R9A=="],
 
     "undici": ["undici@5.29.0", "", { "dependencies": { "@fastify/busboy": "^2.0.0" } }, "sha512-raqeBD6NQK4SkWhQzeYKd1KmIG6dllBOTt55Rmkt4HtI9mwdWtJljnrXjAFUBLTSN67HWrOIZ3EPF4kjUw80Bg=="],
 

.github/actions/codex/package.json

@@ -16,6 +16,6 @@
         "@types/bun": "^1.2.19",
         "@types/node": "^24.1.0",
         "prettier": "^3.6.2",
-        "typescript": "^5.8.3"
+        "typescript": "^5.9.2"
     }
 }

AGENTS.md

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

codex-cli/bin/codex.js

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

codex-cli/src/utils/agent/sandbox/macos-seatbelt.ts

@@ -147,4 +147,8 @@ const READ_ONLY_SEATBELT_POLICY = `
   (sysctl-name "kern.version")
   (sysctl-name "sysctl.proc_cputype")
   (sysctl-name-prefix "hw.perflevel")
-)`.trim();
+)
+
+; Added on top of Chrome profile
+; Needed for python multiprocessing on MacOS for the SemLock
+(allow ipc-posix-sem)`.trim();

codex-rs/Cargo.lock

@@ -661,7 +661,7 @@ dependencies = [
  "clap",
  "codex-core",
  "serde",
- "toml 0.9.2",
+ "toml 0.9.4",
 ]
 
 [[package]]
@@ -695,9 +695,11 @@ dependencies = [
  "reqwest",
  "seccompiler",
  "serde",
+ "serde_bytes",
  "serde_json",
  "sha1",
  "shlex",
+ "similar",
  "strum_macros 0.27.2",
  "tempfile",
  "thiserror 2.0.12",
@@ -705,7 +707,7 @@ dependencies = [
  "tokio",
  "tokio-test",
  "tokio-util",
- "toml 0.9.2",
+ "toml 0.9.4",
  "tracing",
  "tree-sitter",
  "tree-sitter-bash",
@@ -829,7 +831,7 @@ dependencies = [
  "tempfile",
  "tokio",
  "tokio-test",
- "toml 0.9.2",
+ "toml 0.9.4",
  "tracing",
  "tracing-subscriber",
  "uuid",
@@ -842,6 +844,7 @@ version = "0.0.0"
 dependencies = [
  "anyhow",
  "base64 0.22.1",
+ "chrono",
  "clap",
  "codex-ansi-escape",
  "codex-arg0",
@@ -857,23 +860,28 @@ dependencies = [
  "mcp-types",
  "path-clean",
  "pretty_assertions",
+ "rand 0.8.5",
  "ratatui",
  "ratatui-image",
  "regex-lite",
+ "reqwest",
+ "serde",
  "serde_json",
  "shlex",
  "strum 0.27.2",
  "strum_macros 0.27.2",
+ "supports-color",
+ "textwrap 0.16.2",
  "tokio",
  "tracing",
  "tracing-appender",
  "tracing-subscriber",
  "tui-input",
  "tui-markdown",
- "tui-textarea",
  "unicode-segmentation",
  "unicode-width 0.1.14",
  "uuid",
+ "vt100",
 ]
 
 [[package]]
@@ -1466,7 +1474,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "778e2ac28f6c47af28e4907f13ffd1e1ddbd400980a9abd7c8df189bf578a5ad"
 dependencies = [
  "libc",
- "windows-sys 0.60.2",
+ "windows-sys 0.52.0",
 ]
 
 [[package]]
@@ -1546,7 +1554,7 @@ checksum = "0ce92ff622d6dadf7349484f42c93271a0d49b7cc4d466a936405bacbe10aa78"
 dependencies = [
  "cfg-if",
  "rustix 1.0.8",
- "windows-sys 0.59.0",
+ "windows-sys 0.52.0",
 ]
 
 [[package]]
@@ -1749,7 +1757,7 @@ version = "0.2.23"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cba6ae63eb948698e300f645f87c70f76630d505f23b8907cf1e193ee85048c1"
 dependencies = [
- "unicode-width 0.2.0",
+ "unicode-width 0.2.1",
 ]
 
 [[package]]
@@ -2010,7 +2018,7 @@ dependencies = [
  "libc",
  "percent-encoding",
  "pin-project-lite",
- "socket2 0.6.0",
+ "socket2",
  "system-configuration",
  "tokio",
  "tower-service",
@@ -2329,9 +2337,15 @@ checksum = "e04d7f318608d35d4b61ddd75cbdaee86b023ebe2bd5a66ee0915f0bf93095a9"
 dependencies = [
  "hermit-abi",
  "libc",
- "windows-sys 0.59.0",
+ "windows-sys 0.52.0",
 ]
 
+[[package]]
+name = "is_ci"
+version = "1.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7655c9839580ee829dfacba1d1278c2b7883e50a277ff7541299489d6bdfdc45"
+
 [[package]]
 name = "is_terminal_polyfill"
 version = "1.70.1"
@@ -3379,7 +3393,7 @@ dependencies = [
 [[package]]
 name = "ratatui"
 version = "0.29.0"
-source = "git+https://github.com/nornagon/ratatui?branch=nornagon-v0.29.0-patch#bca287ddc5d38fe088c79e2eda22422b96226f2e"
+source = "git+https://github.com/nornagon/ratatui?branch=nornagon-v0.29.0-patch#9b2ad1298408c45918ee9f8241a6f95498cdbed2"
 dependencies = [
  "bitflags 2.9.1",
  "cassowary",
@@ -3393,7 +3407,7 @@ dependencies = [
  "strum 0.26.3",
  "unicode-segmentation",
  "unicode-truncate",
- "unicode-width 0.2.0",
+ "unicode-width 0.2.1",
 ]
 
 [[package]]
@@ -3707,7 +3721,7 @@ dependencies = [
  "errno",
  "libc",
  "linux-raw-sys 0.4.15",
- "windows-sys 0.59.0",
+ "windows-sys 0.52.0",
 ]
 
 [[package]]
@@ -3720,7 +3734,7 @@ dependencies = [
  "errno",
  "libc",
  "linux-raw-sys 0.9.4",
- "windows-sys 0.60.2",
+ "windows-sys 0.52.0",
 ]
 
 [[package]]
@@ -3951,6 +3965,15 @@ dependencies = [
  "serde_derive",
 ]
 
+[[package]]
+name = "serde_bytes"
+version = "0.11.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8437fd221bde2d4ca316d61b90e337e9e702b3820b87d63caa9ba6c02bd06d96"
+dependencies = [
+ "serde",
+]
+
 [[package]]
 name = "serde_derive"
 version = "1.0.219"
@@ -3975,9 +3998,9 @@ dependencies = [
 
 [[package]]
 name = "serde_json"
-version = "1.0.141"
+version = "1.0.142"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "30b9eff21ebe718216c6ec64e1d9ac57087aad11efc64e32002bce4a0d4c03d3"
+checksum = "030fedb782600dcbd6f02d479bf0d817ac3bb40d644745b769d6a96bc3afc5a7"
 dependencies = [
  "indexmap 2.10.0",
  "itoa",
@@ -4161,14 +4184,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "67b1b7a3b5fe4f1376887184045fcf45c69e92af734b7aaddc05fb777b6fbd03"
 
 [[package]]
-name = "socket2"
-version = "0.5.10"
+name = "smawk"
+version = "0.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e22376abed350d73dd1cd119b57ffccad95b4e585a7cda43e286245ce23c0678"
-dependencies = [
- "libc",
- "windows-sys 0.52.0",
-]
+checksum = "b7c388c1b5e93756d0c740965c41e8822f866621d41acbdf6336a6a168f8840c"
 
 [[package]]
 name = "socket2"
@@ -4222,7 +4241,7 @@ dependencies = [
  "starlark_syntax",
  "static_assertions",
  "strsim 0.10.0",
- "textwrap",
+ "textwrap 0.11.0",
  "thiserror 1.0.69",
 ]
 
@@ -4358,6 +4377,15 @@ version = "2.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "13c2bddecc57b384dee18652358fb23172facb8a2c51ccc10d74c157bdea3292"
 
+[[package]]
+name = "supports-color"
+version = "3.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c64fc7232dd8d2e4ac5ce4ef302b1d81e0b80d055b9d77c7c4f51f6aa4c867d6"
+dependencies = [
+ "is_ci",
+]
+
 [[package]]
 name = "syn"
 version = "1.0.109"
@@ -4472,7 +4500,7 @@ dependencies = [
  "getrandom 0.3.3",
  "once_cell",
  "rustix 1.0.8",
- "windows-sys 0.59.0",
+ "windows-sys 0.52.0",
 ]
 
 [[package]]
@@ -4511,6 +4539,17 @@ dependencies = [
  "unicode-width 0.1.14",
 ]
 
+[[package]]
+name = "textwrap"
+version = "0.16.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c13547615a44dc9c452a8a534638acdf07120d4b6847c8178705da06306a3057"
+dependencies = [
+ "smawk",
+ "unicode-linebreak",
+ "unicode-width 0.2.1",
+]
+
 [[package]]
 name = "thiserror"
 version = "1.0.69"
@@ -4625,9 +4664,9 @@ dependencies = [
 
 [[package]]
 name = "tokio"
-version = "1.46.1"
+version = "1.47.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0cc3a2344dafbe23a245241fe8b09735b521110d30fcefbbd5feb1797ca35d17"
+checksum = "89e49afdadebb872d3145a5638b59eb0691ea23e46ca484037cfab3b76b95038"
 dependencies = [
  "backtrace",
  "bytes",
@@ -4638,9 +4677,9 @@ dependencies = [
  "pin-project-lite",
  "signal-hook-registry",
  "slab",
- "socket2 0.5.10",
+ "socket2",
  "tokio-macros",
- "windows-sys 0.52.0",
+ "windows-sys 0.59.0",
 ]
 
 [[package]]
@@ -4725,9 +4764,9 @@ dependencies = [
 
 [[package]]
 name = "toml"
-version = "0.9.2"
+version = "0.9.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ed0aee96c12fa71097902e0bb061a5e1ebd766a6636bb605ba401c45c1650eac"
+checksum = "41ae868b5a0f67631c14589f7e250c1ea2c574ee5ba21c6c8dd4b1485705a5a1"
 dependencies = [
  "indexmap 2.10.0",
  "serde",
@@ -4956,7 +4995,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "911e93158bf80bbc94bad533b2b16e3d711e1132d69a6a6980c3920a63422c19"
 dependencies = [
  "ratatui",
- "unicode-width 0.2.0",
+ "unicode-width 0.2.1",
 ]
 
 [[package]]
@@ -4975,17 +5014,6 @@ dependencies = [
  "tracing",
 ]
 
-[[package]]
-name = "tui-textarea"
-version = "0.7.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0a5318dd619ed73c52a9417ad19046724effc1287fb75cdcc4eca1d6ac1acbae"
-dependencies = [
- "crossterm",
- "ratatui",
- "unicode-width 0.2.0",
-]
-
 [[package]]
 name = "typenum"
 version = "1.18.0"
@@ -5004,6 +5032,12 @@ version = "1.0.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5a5f39404a5da50712a4c1eecf25e90dd62b613502b7e925fd4e4d19b5c96512"
 
+[[package]]
+name = "unicode-linebreak"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3b09c83c3c29d37506a3e260c08c03743a6bb66a9cd432c6934ab501a190571f"
+
 [[package]]
 name = "unicode-segmentation"
 version = "1.12.0"
@@ -5029,9 +5063,9 @@ checksum = "7dd6e30e90baa6f72411720665d41d89b9a3d039dc45b8faea1ddd07f617f6af"
 
 [[package]]
 name = "unicode-width"
-version = "0.2.0"
+version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1fc81956842c57dac11422a97c3b8195a1ff727f06e85c84ed2e8aa277c9a0fd"
+checksum = "4a1a07cc7db3810833284e8d372ccdc6da29741639ecc70c9ec107df0fa6154c"
 
 [[package]]
 name = "unicode-xid"
@@ -5116,6 +5150,27 @@ version = "0.9.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
 
+[[package]]
+name = "vt100"
+version = "0.16.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "054ff75fb8fa83e609e685106df4faeffdf3a735d3c74ebce97ec557d5d36fd9"
+dependencies = [
+ "itoa",
+ "unicode-width 0.2.1",
+ "vte",
+]
+
+[[package]]
+name = "vte"
+version = "0.15.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a5924018406ce0063cd67f8e008104968b74b563ee1b85dde3ed1f7cb87d3dbd"
+dependencies = [
+ "arrayvec",
+ "memchr",
+]
+
 [[package]]
 name = "wait-timeout"
 version = "0.2.1"
@@ -5304,7 +5359,7 @@ version = "0.1.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cf221c93e13a30d793f7645a0e7762c55d169dbb0a49671918a2319d289b10bb"
 dependencies = [
- "windows-sys 0.59.0",
+ "windows-sys 0.52.0",
 ]
 
 [[package]]

codex-rs/common/src/sandbox_summary.rs

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

codex-rs/config.md

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

codex-rs/core/Cargo.toml

@@ -31,8 +31,10 @@ rand = "0.9"
 reqwest = { version = "0.12", features = ["json", "stream"] }
 serde = { version = "1", features = ["derive"] }
 serde_json = "1"
+serde_bytes = "0.11"
 sha1 = "0.10.6"
 shlex = "1.3.0"
+similar = "2.7.0"
 strum_macros = "0.27.2"
 thiserror = "2.0.12"
 time = { version = "0.3", features = ["formatting", "local-offset", "macros"] }
@@ -44,7 +46,7 @@ tokio = { version = "1", features = [
     "signal",
 ] }
 tokio-util = "0.7.14"
-toml = "0.9.2"
+toml = "0.9.4"
 tracing = { version = "0.1.41", features = ["log"] }
 tree-sitter = "0.25.8"
 tree-sitter-bash = "0.25.0"

codex-rs/core/prompt.md

@@ -9,8 +9,10 @@ You MUST adhere to the following criteria when executing the task:
 - Analyzing code for vulnerabilities is allowed.
 - Showing user code and tool call details is allowed.
 - User instructions may overwrite the _CODING GUIDELINES_ section in this developer message.
+- `user_instructions` are not part of the user's request, but guidance for how to complete the task.
+- Do not cite `user_instructions` back to the user unless a specific piece is relevant.
 - Do not use \`ls -R\`, \`find\`, or \`grep\` - these are slow in large repos. Use \`rg\` and \`rg --files\`.
-- Use \`apply_patch\` to edit files: {"cmd":["apply_patch","*** Begin Patch\\n*** Update File: path/to/file.py\\n@@ def example():\\n- pass\\n+ return 123\\n*** End Patch"]}
+- Use \`apply_patch\` to edit files: {"command":["apply_patch","*** Begin Patch\\n*** Update File: path/to/file.py\\n@@ def example():\\n- pass\\n+ return 123\\n*** End Patch"]}
 - If completing the user's task requires writing or modifying files:
   - Your code and final answer should follow these _CODING GUIDELINES_:
     - Fix the problem at the root cause rather than applying surface-level patches, when possible.
@@ -40,16 +42,16 @@ You MUST adhere to the following criteria when executing the task:
 
 Your patch language is a stripped‑down, file‑oriented diff format designed to be easy to parse and safe to apply. You can think of it as a high‑level envelope:
 
-**_ Begin Patch
+*** Begin Patch
 [ one or more file sections ]
-_** End Patch
+*** End Patch
 
 Within that envelope, you get a sequence of file operations.
 You MUST include a header to specify the action you are taking.
 Each operation starts with one of three headers:
 
-**_ Add File: <path> - create a new file. Every following line is a + line (the initial contents).
-_** Delete File: <path> - remove an existing file. Nothing follows.
+*** Add File: <path> - create a new file. Every following line is a + line (the initial contents).
+*** Delete File: <path> - remove an existing file. Nothing follows.
 \*\*\* Update File: <path> - patch an existing file in place (optionally with a rename).
 
 May be immediately followed by \*\*\* Move to: <new path> if you want to rename the file.
@@ -63,28 +65,28 @@ Within a hunk each line starts with:
   At the end of a truncated hunk you can emit \*\*\* End of File.
 
 Patch := Begin { FileOp } End
-Begin := "**_ Begin Patch" NEWLINE
-End := "_** End Patch" NEWLINE
+Begin := "*** Begin Patch" NEWLINE
+End := "*** End Patch" NEWLINE
 FileOp := AddFile | DeleteFile | UpdateFile
-AddFile := "**_ Add File: " path NEWLINE { "+" line NEWLINE }
-DeleteFile := "_** Delete File: " path NEWLINE
-UpdateFile := "**_ Update File: " path NEWLINE [ MoveTo ] { Hunk }
-MoveTo := "_** Move to: " newPath NEWLINE
+AddFile := "*** Add File: " path NEWLINE { "+" line NEWLINE }
+DeleteFile := "*** Delete File: " path NEWLINE
+UpdateFile := "*** Update File: " path NEWLINE [ MoveTo ] { Hunk }
+MoveTo := "*** Move to: " newPath NEWLINE
 Hunk := "@@" [ header ] NEWLINE { HunkLine } [ "*** End of File" NEWLINE ]
 HunkLine := (" " | "-" | "+") text NEWLINE
 
 A full patch can combine several operations:
 
-**_ Begin Patch
-_** Add File: hello.txt
+*** Begin Patch
+*** Add File: hello.txt
 +Hello world
-**_ Update File: src/app.py
-_** Move to: src/main.py
+*** Update File: src/app.py
+*** Move to: src/main.py
 @@ def greet():
 -print("Hi")
 +print("Hello, world!")
-**_ Delete File: obsolete.txt
-_** End Patch
+*** Delete File: obsolete.txt
+*** End Patch
 
 It is important to remember:
 
@@ -101,7 +103,7 @@ Plan updates
 
 A tool named `update_plan` is available. Use it to keep an up‑to‑date, step‑by‑step plan for the task so you can follow your progress. When making your plans, keep in mind that you are a deployed coding agent - `update_plan` calls should not involve doing anything that you aren't capable of doing. For example, `update_plan` calls should NEVER contain tasks to merge your own pull requests. Only stop to ask the user if you genuinely need their feedback on a change.
 
-- At the start of the task, call `update_plan` with an initial plan: a short list of 1‑sentence steps with a `status` for each step (`pending`, `in_progress`, or `completed`). There should always be exactly one `in_progress` step until everything is done.
+- At the start of any nontrivial task, call `update_plan` with an initial plan: a short list of 1‑sentence steps with a `status` for each step (`pending`, `in_progress`, or `completed`). There should always be exactly one `in_progress` step until everything is done.
 - Whenever you finish a step, call `update_plan` again, marking the finished step as `completed` and the next step as `in_progress`.
 - If your plan needs to change, call `update_plan` with the revised steps and include an `explanation` describing the change.
 - When all steps are complete, make a final `update_plan` call with all steps marked `completed`.

codex-rs/core/src/chat_completions.rs

@@ -40,7 +40,7 @@ pub(crate) async fn stream_chat_completions(
     let full_instructions = prompt.get_full_instructions(model);
     messages.push(json!({"role": "system", "content": full_instructions}));
 
-    if let Some(instr) = &prompt.user_instructions {
+    if let Some(instr) = &prompt.get_formatted_user_instructions() {
         messages.push(json!({"role": "user", "content": instr}));
     }
 
@@ -120,7 +120,7 @@ pub(crate) async fn stream_chat_completions(
 
     debug!(
         "POST to {}: {}",
-        provider.get_full_url(),
+        provider.get_full_url(&None),
         serde_json::to_string_pretty(&payload).unwrap_or_default()
     );
 
@@ -129,7 +129,7 @@ pub(crate) async fn stream_chat_completions(
     loop {
         attempt += 1;
 
-        let req_builder = provider.create_request_builder(client)?;
+        let req_builder = provider.create_request_builder(client, &None).await?;
 
         let res = req_builder
             .header(reqwest::header::ACCEPT, "text/event-stream")
@@ -260,6 +260,11 @@ async fn process_chat_sse<S>(
                 .and_then(|d| d.get("content"))
                 .and_then(|c| c.as_str())
             {
+                // Emit a delta so downstream consumers can stream text live.
+                let _ = tx_event
+                    .send(Ok(ResponseEvent::OutputTextDelta(content.to_string())))
+                    .await;
+
                 let item = ResponseItem::Message {
                     role: "assistant".to_string(),
                     content: vec![ContentItem::OutputText {
@@ -439,11 +444,14 @@ 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;
+                Poll::Ready(Some(Ok(ResponseEvent::OutputTextDelta(delta)))) => {
+                    // Forward deltas unchanged so callers can stream text
+                    // live while still receiving a single aggregated
+                    // OutputItemDone at the end of the turn.
+                    return Poll::Ready(Some(Ok(ResponseEvent::OutputTextDelta(delta))));
+                }
+                Poll::Ready(Some(Ok(ResponseEvent::ReasoningSummaryDelta(delta)))) => {
+                    return Poll::Ready(Some(Ok(ResponseEvent::ReasoningSummaryDelta(delta))));
                 }
             }
         }

codex-rs/core/src/client.rs

@@ -30,7 +30,6 @@ use crate::config::Config;
 use crate::config_types::ReasoningEffort as ReasoningEffortConfig;
 use crate::config_types::ReasoningSummary as ReasoningSummaryConfig;
 use crate::error::CodexErr;
-use crate::error::EnvVarError;
 use crate::error::Result;
 use crate::flags::CODEX_RS_SSE_FIXTURE;
 use crate::model_provider_info::ModelProviderInfo;
@@ -122,24 +121,11 @@ impl ModelClient {
             return stream_from_fixture(path, self.provider.clone()).await;
         }
 
-        let auth = self.auth.as_ref().ok_or_else(|| {
-            CodexErr::EnvVar(EnvVarError {
-                var: "OPENAI_API_KEY".to_string(),
-                instructions: Some("Create an API key (https://platform.openai.com) and export it as an environment variable.".to_string()),
-            })
-        })?;
+        let auth = self.auth.clone();
 
-        let store = prompt.store && auth.mode != AuthMode::ChatGPT;
+        let auth_mode = auth.as_ref().map(|a| a.mode);
 
-        let base_url = match self.provider.base_url.clone() {
-            Some(url) => url,
-            None => match auth.mode {
-                AuthMode::ChatGPT => "https://chatgpt.com/backend-api/codex".to_string(),
-                AuthMode::ApiKey => "https://api.openai.com/v1".to_string(),
-            },
-        };
-
-        let token = auth.get_token().await?;
+        let store = prompt.store && auth_mode != Some(AuthMode::ChatGPT);
 
         let full_instructions = prompt.get_full_instructions(&self.config.model);
         let tools_json = create_tools_json_for_responses_api(
@@ -158,11 +144,11 @@ impl ModelClient {
         };
 
         let mut input_with_instructions = Vec::with_capacity(prompt.input.len() + 1);
-        if let Some(ui) = &prompt.user_instructions {
+        if let Some(ui) = prompt.get_formatted_user_instructions() {
             input_with_instructions.push(ResponseItem::Message {
                 id: None,
                 role: "user".to_string(),
-                content: vec![ContentItem::InputText { text: ui.clone() }],
+                content: vec![ContentItem::InputText { text: ui }],
             });
         }
         input_with_instructions.extend(prompt.input.clone());
@@ -180,35 +166,36 @@ impl ModelClient {
             include,
         };
 
-        trace!(
-            "POST to {}: {}",
-            self.provider.get_full_url(),
-            serde_json::to_string(&payload)?
-        );
-
         let mut attempt = 0;
         let max_retries = self.provider.request_max_retries();
 
+        trace!(
+            "POST to {}: {}",
+            self.provider.get_full_url(&auth),
+            serde_json::to_string(&payload)?
+        );
+
         loop {
             attempt += 1;
 
             let mut req_builder = self
-                .client
-                .post(format!("{base_url}/responses"))
+                .provider
+                .create_request_builder(&self.client, &auth)
+                .await?;
+
+            req_builder = req_builder
                 .header("OpenAI-Beta", "responses=experimental")
                 .header("session_id", self.session_id.to_string())
-                .bearer_auth(&token)
                 .header(reqwest::header::ACCEPT, "text/event-stream")
                 .json(&payload);
 
-            if auth.mode == AuthMode::ChatGPT {
-                if let Some(account_id) = auth.get_account_id().await {
-                    req_builder = req_builder.header("chatgpt-account-id", account_id);
-                }
+            if let Some(auth) = auth.as_ref()
+                && auth.mode == AuthMode::ChatGPT
+                && let Some(account_id) = auth.get_account_id().await
+            {
+                req_builder = req_builder.header("chatgpt-account-id", account_id);
             }
 
-            req_builder = self.provider.apply_http_headers(req_builder);
-
             let originator = self
                 .config
                 .internal_originator

codex-rs/core/src/client_common.rs

@@ -17,6 +17,10 @@ use tokio::sync::mpsc;
 /// with this content.
 const BASE_INSTRUCTIONS: &str = include_str!("../prompt.md");
 
+/// wraps user instructions message in a tag for the model to parse more easily.
+const USER_INSTRUCTIONS_START: &str = "<user_instructions>\n\n";
+const USER_INSTRUCTIONS_END: &str = "\n\n</user_instructions>";
+
 /// API request payload for a single model turn.
 #[derive(Default, Debug, Clone)]
 pub struct Prompt {
@@ -49,6 +53,12 @@ impl Prompt {
         }
         Cow::Owned(sections.join("\n"))
     }
+
+    pub(crate) fn get_formatted_user_instructions(&self) -> Option<String> {
+        self.user_instructions
+            .as_ref()
+            .map(|ui| format!("{USER_INSTRUCTIONS_START}{ui}{USER_INSTRUCTIONS_END}"))
+    }
 }
 
 #[derive(Debug)]

codex-rs/core/src/codex.rs

@@ -48,6 +48,7 @@ use crate::error::SandboxErr;
 use crate::exec::ExecParams;
 use crate::exec::ExecToolCallOutput;
 use crate::exec::SandboxType;
+use crate::exec::StdoutStream;
 use crate::exec::process_exec_tool_call;
 use crate::exec_env::create_env;
 use crate::mcp_connection_manager::McpConnectionManager;
@@ -84,11 +85,13 @@ use crate::protocol::SandboxPolicy;
 use crate::protocol::SessionConfiguredEvent;
 use crate::protocol::Submission;
 use crate::protocol::TaskCompleteEvent;
+use crate::protocol::TurnDiffEvent;
 use crate::rollout::RolloutRecorder;
 use crate::safety::SafetyCheck;
 use crate::safety::assess_command_safety;
 use crate::safety::assess_safety_for_untrusted_command;
 use crate::shell;
+use crate::turn_diff_tracker::TurnDiffTracker;
 use crate::user_notification::UserNotification;
 use crate::util::backoff;
 
@@ -120,7 +123,7 @@ impl Codex {
         let resume_path = config.experimental_resume.clone();
         info!("resume_path: {resume_path:?}");
         let (tx_sub, rx_sub) = async_channel::bounded(64);
-        let (tx_event, rx_event) = async_channel::bounded(1600);
+        let (tx_event, rx_event) = async_channel::unbounded();
 
         let user_instructions = get_user_instructions(&config).await;
 
@@ -361,7 +364,11 @@ impl Session {
         }
     }
 
-    async fn notify_exec_command_begin(&self, exec_command_context: ExecCommandContext) {
+    async fn on_exec_command_begin(
+        &self,
+        turn_diff_tracker: &mut TurnDiffTracker,
+        exec_command_context: ExecCommandContext,
+    ) {
         let ExecCommandContext {
             sub_id,
             call_id,
@@ -373,11 +380,15 @@ impl Session {
             Some(ApplyPatchCommandContext {
                 user_explicitly_approved_this_action,
                 changes,
-            }) => EventMsg::PatchApplyBegin(PatchApplyBeginEvent {
-                call_id,
-                auto_approved: !user_explicitly_approved_this_action,
-                changes,
-            }),
+            }) => {
+                turn_diff_tracker.on_patch_begin(&changes);
+
+                EventMsg::PatchApplyBegin(PatchApplyBeginEvent {
+                    call_id,
+                    auto_approved: !user_explicitly_approved_this_action,
+                    changes,
+                })
+            }
             None => EventMsg::ExecCommandBegin(ExecCommandBeginEvent {
                 call_id,
                 command: command_for_display.clone(),
@@ -391,15 +402,21 @@ impl Session {
         let _ = self.tx_event.send(event).await;
     }
 
-    async fn notify_exec_command_end(
+    #[allow(clippy::too_many_arguments)]
+    async fn on_exec_command_end(
         &self,
+        turn_diff_tracker: &mut TurnDiffTracker,
         sub_id: &str,
         call_id: &str,
-        stdout: &str,
-        stderr: &str,
-        exit_code: i32,
+        output: &ExecToolCallOutput,
         is_apply_patch: bool,
     ) {
+        let ExecToolCallOutput {
+            stdout,
+            stderr,
+            duration,
+            exit_code,
+        } = output;
         // Because stdout and stderr could each be up to 100 KiB, we send
         // truncated versions.
         const MAX_STREAM_OUTPUT: usize = 5 * 1024; // 5KiB
@@ -411,14 +428,15 @@ impl Session {
                 call_id: call_id.to_string(),
                 stdout,
                 stderr,
-                success: exit_code == 0,
+                success: *exit_code == 0,
             })
         } else {
             EventMsg::ExecCommandEnd(ExecCommandEndEvent {
                 call_id: call_id.to_string(),
                 stdout,
                 stderr,
-                exit_code,
+                duration: *duration,
+                exit_code: *exit_code,
             })
         };
 
@@ -427,6 +445,20 @@ impl Session {
             msg,
         };
         let _ = self.tx_event.send(event).await;
+
+        // If this is an apply_patch, after we emit the end patch, emit a second event
+        // with the full turn diff if there is one.
+        if is_apply_patch {
+            let unified_diff = turn_diff_tracker.get_unified_diff();
+            if let Ok(Some(unified_diff)) = unified_diff {
+                let msg = EventMsg::TurnDiff(TurnDiffEvent { unified_diff });
+                let event = Event {
+                    id: sub_id.into(),
+                    msg,
+                };
+                let _ = self.tx_event.send(event).await;
+            }
+        }
     }
 
     /// Helper that emits a BackgroundEvent with the given message. This keeps
@@ -669,7 +701,7 @@ async fn submission_loop(
                 cwd,
                 resume_path,
             } => {
-                info!(
+                debug!(
                     "Configuring session: model={model}; provider={provider:?}; resume={resume_path:?}"
                 );
                 if !cwd.is_absolute() {
@@ -1000,6 +1032,10 @@ async fn run_task(sess: Arc<Session>, sub_id: String, input: Vec<InputItem>) {
         .await;
 
     let last_agent_message: Option<String>;
+    // Although from the perspective of codex.rs, TurnDiffTracker has the lifecycle of a Task which contains
+    // many turns, from the perspective of the user, it is a single turn.
+    let mut turn_diff_tracker = TurnDiffTracker::new();
+
     loop {
         // Note that pending_input would be something like a message the user
         // submitted through the UI while the model was running. Though the UI
@@ -1031,7 +1067,7 @@ async fn run_task(sess: Arc<Session>, sub_id: String, input: Vec<InputItem>) {
                 })
             })
             .collect();
-        match run_turn(&sess, sub_id.clone(), turn_input).await {
+        match run_turn(&sess, &mut turn_diff_tracker, sub_id.clone(), turn_input).await {
             Ok(turn_output) => {
                 let mut items_to_record_in_conversation_history = Vec::<ResponseItem>::new();
                 let mut responses = Vec::<ResponseInputItem>::new();
@@ -1157,6 +1193,7 @@ async fn run_task(sess: Arc<Session>, sub_id: String, input: Vec<InputItem>) {
 
 async fn run_turn(
     sess: &Session,
+    turn_diff_tracker: &mut TurnDiffTracker,
     sub_id: String,
     input: Vec<ResponseItem>,
 ) -> CodexResult<Vec<ProcessedResponseItem>> {
@@ -1171,7 +1208,7 @@ async fn run_turn(
 
     let mut retries = 0;
     loop {
-        match try_run_turn(sess, &sub_id, &prompt).await {
+        match try_run_turn(sess, turn_diff_tracker, &sub_id, &prompt).await {
             Ok(output) => return Ok(output),
             Err(CodexErr::Interrupted) => return Err(CodexErr::Interrupted),
             Err(CodexErr::EnvVar(var)) => return Err(CodexErr::EnvVar(var)),
@@ -1217,6 +1254,7 @@ struct ProcessedResponseItem {
 
 async fn try_run_turn(
     sess: &Session,
+    turn_diff_tracker: &mut TurnDiffTracker,
     sub_id: &str,
     prompt: &Prompt,
 ) -> CodexResult<Vec<ProcessedResponseItem>> {
@@ -1304,7 +1342,8 @@ async fn try_run_turn(
         match event {
             ResponseEvent::Created => {}
             ResponseEvent::OutputItemDone(item) => {
-                let response = handle_response_item(sess, sub_id, item.clone()).await?;
+                let response =
+                    handle_response_item(sess, turn_diff_tracker, sub_id, item.clone()).await?;
 
                 output.push(ProcessedResponseItem { item, response });
             }
@@ -1322,9 +1361,24 @@ async fn try_run_turn(
                         .ok();
                 }
 
+                let unified_diff = turn_diff_tracker.get_unified_diff();
+                if let Ok(Some(unified_diff)) = unified_diff {
+                    let msg = EventMsg::TurnDiff(TurnDiffEvent { unified_diff });
+                    let event = Event {
+                        id: sub_id.to_string(),
+                        msg,
+                    };
+                    let _ = sess.tx_event.send(event).await;
+                }
+
                 return Ok(output);
             }
             ResponseEvent::OutputTextDelta(delta) => {
+                {
+                    let mut st = sess.state.lock().unwrap();
+                    st.history.append_assistant_text(&delta);
+                }
+
                 let event = Event {
                     id: sub_id.to_string(),
                     msg: EventMsg::AgentMessageDelta(AgentMessageDeltaEvent { delta }),
@@ -1372,7 +1426,7 @@ async fn run_compact_task(
     let mut retries = 0;
 
     loop {
-        let attempt_result = drain_to_completed(&sess, &prompt).await;
+        let attempt_result = drain_to_completed(&sess, &sub_id, &prompt).await;
 
         match attempt_result {
             Ok(()) => break,
@@ -1426,6 +1480,7 @@ async fn run_compact_task(
 
 async fn handle_response_item(
     sess: &Session,
+    turn_diff_tracker: &mut TurnDiffTracker,
     sub_id: &str,
     item: ResponseItem,
 ) -> CodexResult<Option<ResponseInputItem>> {
@@ -1463,7 +1518,17 @@ async fn handle_response_item(
             ..
         } => {
             info!("FunctionCall: {arguments}");
-            Some(handle_function_call(sess, sub_id.to_string(), name, arguments, call_id).await)
+            Some(
+                handle_function_call(
+                    sess,
+                    turn_diff_tracker,
+                    sub_id.to_string(),
+                    name,
+                    arguments,
+                    call_id,
+                )
+                .await,
+            )
         }
         ResponseItem::LocalShellCall {
             id,
@@ -1498,6 +1563,7 @@ async fn handle_response_item(
                 handle_container_exec_with_params(
                     exec_params,
                     sess,
+                    turn_diff_tracker,
                     sub_id.to_string(),
                     effective_call_id,
                 )
@@ -1515,6 +1581,7 @@ async fn handle_response_item(
 
 async fn handle_function_call(
     sess: &Session,
+    turn_diff_tracker: &mut TurnDiffTracker,
     sub_id: String,
     name: String,
     arguments: String,
@@ -1528,7 +1595,8 @@ async fn handle_function_call(
                     return *output;
                 }
             };
-            handle_container_exec_with_params(params, sess, sub_id, call_id).await
+            handle_container_exec_with_params(params, sess, turn_diff_tracker, sub_id, call_id)
+                .await
         }
         "update_plan" => handle_update_plan(sess, arguments, sub_id, call_id).await,
         _ => {
@@ -1602,6 +1670,7 @@ fn maybe_run_with_user_profile(params: ExecParams, sess: &Session) -> ExecParams
 async fn handle_container_exec_with_params(
     params: ExecParams,
     sess: &Session,
+    turn_diff_tracker: &mut TurnDiffTracker,
     sub_id: String,
     call_id: String,
 ) -> ResponseInputItem {
@@ -1749,7 +1818,7 @@ async fn handle_container_exec_with_params(
             },
         ),
     };
-    sess.notify_exec_command_begin(exec_command_context.clone())
+    sess.on_exec_command_begin(turn_diff_tracker, exec_command_context.clone())
         .await;
 
     let params = maybe_run_with_user_profile(params, sess);
@@ -1759,6 +1828,11 @@ async fn handle_container_exec_with_params(
         sess.ctrl_c.clone(),
         &sess.sandbox_policy,
         &sess.codex_linux_sandbox_exe,
+        Some(StdoutStream {
+            sub_id: sub_id.clone(),
+            call_id: call_id.clone(),
+            tx_event: sess.tx_event.clone(),
+        }),
     )
     .await;
 
@@ -1769,23 +1843,22 @@ async fn handle_container_exec_with_params(
                 stdout,
                 stderr,
                 duration,
-            } = output;
+            } = &output;
 
-            sess.notify_exec_command_end(
+            sess.on_exec_command_end(
+                turn_diff_tracker,
                 &sub_id,
                 &call_id,
-                &stdout,
-                &stderr,
-                exit_code,
+                &output,
                 exec_command_context.apply_patch.is_some(),
             )
             .await;
 
-            let is_success = exit_code == 0;
+            let is_success = *exit_code == 0;
             let content = format_exec_output(
-                if is_success { &stdout } else { &stderr },
-                exit_code,
-                duration,
+                if is_success { stdout } else { stderr },
+                *exit_code,
+                *duration,
             );
 
             ResponseInputItem::FunctionCallOutput {
@@ -1797,7 +1870,15 @@ async fn handle_container_exec_with_params(
             }
         }
         Err(CodexErr::Sandbox(error)) => {
-            handle_sandbox_error(params, exec_command_context, error, sandbox_type, sess).await
+            handle_sandbox_error(
+                turn_diff_tracker,
+                params,
+                exec_command_context,
+                error,
+                sandbox_type,
+                sess,
+            )
+            .await
         }
         Err(e) => {
             // Handle non-sandbox errors
@@ -1813,6 +1894,7 @@ async fn handle_container_exec_with_params(
 }
 
 async fn handle_sandbox_error(
+    turn_diff_tracker: &mut TurnDiffTracker,
     params: ExecParams,
     exec_command_context: ExecCommandContext,
     error: SandboxErr,
@@ -1844,7 +1926,8 @@ async fn handle_sandbox_error(
     // include additional metadata on the command to indicate whether non-zero
     // exit codes merit a retry.
 
-    // For now, we categorically ask the user to retry without sandbox.
+    // For now, we categorically ask the user to retry without sandbox and
+    // emit the raw error as a background event.
     sess.notify_background_event(&sub_id, format!("Execution failed: {error}"))
         .await;
 
@@ -1869,7 +1952,8 @@ async fn handle_sandbox_error(
             sess.notify_background_event(&sub_id, "retrying command without sandbox")
                 .await;
 
-            sess.notify_exec_command_begin(exec_command_context).await;
+            sess.on_exec_command_begin(turn_diff_tracker, exec_command_context)
+                .await;
 
             // This is an escalated retry; the policy will not be
             // examined and the sandbox has been set to `None`.
@@ -1879,6 +1963,11 @@ async fn handle_sandbox_error(
                 sess.ctrl_c.clone(),
                 &sess.sandbox_policy,
                 &sess.codex_linux_sandbox_exe,
+                Some(StdoutStream {
+                    sub_id: sub_id.clone(),
+                    call_id: call_id.clone(),
+                    tx_event: sess.tx_event.clone(),
+                }),
             )
             .await;
 
@@ -1889,23 +1978,22 @@ async fn handle_sandbox_error(
                         stdout,
                         stderr,
                         duration,
-                    } = retry_output;
+                    } = &retry_output;
 
-                    sess.notify_exec_command_end(
+                    sess.on_exec_command_end(
+                        turn_diff_tracker,
                         &sub_id,
                         &call_id,
-                        &stdout,
-                        &stderr,
-                        exit_code,
+                        &retry_output,
                         is_apply_patch,
                     )
                     .await;
 
-                    let is_success = exit_code == 0;
+                    let is_success = *exit_code == 0;
                     let content = format_exec_output(
-                        if is_success { &stdout } else { &stderr },
-                        exit_code,
-                        duration,
+                        if is_success { stdout } else { stderr },
+                        *exit_code,
+                        *duration,
                     );
 
                     ResponseInputItem::FunctionCallOutput {
@@ -1990,7 +2078,7 @@ fn get_last_assistant_message_from_turn(responses: &[ResponseItem]) -> Option<St
     })
 }
 
-async fn drain_to_completed(sess: &Session, prompt: &Prompt) -> CodexResult<()> {
+async fn drain_to_completed(sess: &Session, sub_id: &str, prompt: &Prompt) -> CodexResult<()> {
     let mut stream = sess.client.clone().stream(prompt).await?;
     loop {
         let maybe_event = stream.next().await;
@@ -2000,7 +2088,32 @@ async fn drain_to_completed(sess: &Session, prompt: &Prompt) -> CodexResult<()>
             ));
         };
         match event {
-            Ok(ResponseEvent::Completed { .. }) => return Ok(()),
+            Ok(ResponseEvent::OutputItemDone(item)) => {
+                // Record only to in-memory conversation history; avoid state snapshot.
+                let mut state = sess.state.lock().unwrap();
+                state.history.record_items(std::slice::from_ref(&item));
+            }
+            Ok(ResponseEvent::Completed {
+                response_id: _,
+                token_usage,
+            }) => {
+                let token_usage = match token_usage {
+                    Some(usage) => usage,
+                    None => {
+                        return Err(CodexErr::Stream(
+                            "token_usage was None in ResponseEvent::Completed".into(),
+                        ));
+                    }
+                };
+                sess.tx_event
+                    .send(Event {
+                        id: sub_id.to_string(),
+                        msg: EventMsg::TokenCount(token_usage),
+                    })
+                    .await
+                    .ok();
+                return Ok(());
+            }
             Ok(_) => continue,
             Err(e) => return Err(e),
         }

codex-rs/core/src/config.rs

@@ -356,6 +356,7 @@ impl ConfigToml {
                 Some(s) => SandboxPolicy::WorkspaceWrite {
                     writable_roots: s.writable_roots.clone(),
                     network_access: s.network_access,
+                    include_default_writable_roots: true,
                 },
                 None => SandboxPolicy::new_workspace_write_policy(),
             },
@@ -479,10 +480,12 @@ impl Config {
         // Load base instructions override from a file if specified. If the
         // path is relative, resolve it against the effective cwd so the
         // behaviour matches other path-like config values.
-        let file_base_instructions = Self::get_base_instructions(
-            cfg.experimental_instructions_file.as_ref(),
-            &resolved_cwd,
-        )?;
+        let experimental_instructions_path = config_profile
+            .experimental_instructions_file
+            .as_ref()
+            .or(cfg.experimental_instructions_file.as_ref());
+        let file_base_instructions =
+            Self::get_base_instructions(experimental_instructions_path, &resolved_cwd)?;
         let base_instructions = base_instructions.or(file_base_instructions);
 
         let config = Self {
@@ -727,6 +730,7 @@ writable_roots = [
             SandboxPolicy::WorkspaceWrite {
                 writable_roots: vec![PathBuf::from("/tmp")],
                 network_access: false,
+                include_default_writable_roots: true,
             },
             sandbox_workspace_write_cfg.derive_sandbox_policy(sandbox_mode_override)
         );

codex-rs/core/src/config_profile.rs

@@ -1,4 +1,5 @@
 use serde::Deserialize;
+use std::path::PathBuf;
 
 use crate::config_types::ReasoningEffort;
 use crate::config_types::ReasoningSummary;
@@ -17,4 +18,5 @@ pub struct ConfigProfile {
     pub model_reasoning_effort: Option<ReasoningEffort>,
     pub model_reasoning_summary: Option<ReasoningSummary>,
     pub chatgpt_base_url: Option<String>,
+    pub experimental_instructions_file: Option<PathBuf>,
 }

codex-rs/core/src/conversation_history.rs

@@ -24,9 +24,52 @@ impl ConversationHistory {
         I::Item: std::ops::Deref<Target = ResponseItem>,
     {
         for item in items {
-            if is_api_message(&item) {
-                // Note agent-loop.ts also does filtering on some of the fields.
-                self.items.push(item.clone());
+            if !is_api_message(&item) {
+                continue;
+            }
+
+            // Merge adjacent assistant messages into a single history entry.
+            // This prevents duplicates when a partial assistant message was
+            // streamed into history earlier in the turn and the final full
+            // message is recorded at turn end.
+            match (&*item, self.items.last_mut()) {
+                (
+                    ResponseItem::Message {
+                        role: new_role,
+                        content: new_content,
+                        ..
+                    },
+                    Some(ResponseItem::Message {
+                        role: last_role,
+                        content: last_content,
+                        ..
+                    }),
+                ) if new_role == "assistant" && last_role == "assistant" => {
+                    append_text_content(last_content, new_content);
+                }
+                _ => {
+                    self.items.push(item.clone());
+                }
+            }
+        }
+    }
+
+    /// Append a text `delta` to the latest assistant message, creating a new
+    /// assistant entry if none exists yet (e.g. first delta for this turn).
+    pub(crate) fn append_assistant_text(&mut self, delta: &str) {
+        match self.items.last_mut() {
+            Some(ResponseItem::Message { role, content, .. }) if role == "assistant" => {
+                append_text_delta(content, delta);
+            }
+            _ => {
+                // Start a new assistant message with the delta.
+                self.items.push(ResponseItem::Message {
+                    id: None,
+                    role: "assistant".to_string(),
+                    content: vec![crate::models::ContentItem::OutputText {
+                        text: delta.to_string(),
+                    }],
+                });
             }
         }
     }
@@ -72,3 +115,140 @@ fn is_api_message(message: &ResponseItem) -> bool {
         ResponseItem::Other => false,
     }
 }
+
+/// Helper to append the textual content from `src` into `dst` in place.
+fn append_text_content(
+    dst: &mut Vec<crate::models::ContentItem>,
+    src: &Vec<crate::models::ContentItem>,
+) {
+    for c in src {
+        if let crate::models::ContentItem::OutputText { text } = c {
+            append_text_delta(dst, text);
+        }
+    }
+}
+
+/// Append a single text delta to the last OutputText item in `content`, or
+/// push a new OutputText item if none exists.
+fn append_text_delta(content: &mut Vec<crate::models::ContentItem>, delta: &str) {
+    if let Some(crate::models::ContentItem::OutputText { text }) = content
+        .iter_mut()
+        .rev()
+        .find(|c| matches!(c, crate::models::ContentItem::OutputText { .. }))
+    {
+        text.push_str(delta);
+    } else {
+        content.push(crate::models::ContentItem::OutputText {
+            text: delta.to_string(),
+        });
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::models::ContentItem;
+
+    fn assistant_msg(text: &str) -> ResponseItem {
+        ResponseItem::Message {
+            id: None,
+            role: "assistant".to_string(),
+            content: vec![ContentItem::OutputText {
+                text: text.to_string(),
+            }],
+        }
+    }
+
+    fn user_msg(text: &str) -> ResponseItem {
+        ResponseItem::Message {
+            id: None,
+            role: "user".to_string(),
+            content: vec![ContentItem::OutputText {
+                text: text.to_string(),
+            }],
+        }
+    }
+
+    #[test]
+    fn merges_adjacent_assistant_messages() {
+        let mut h = ConversationHistory::default();
+        let a1 = assistant_msg("Hello");
+        let a2 = assistant_msg(", world!");
+        h.record_items([&a1, &a2]);
+
+        let items = h.contents();
+        assert_eq!(
+            items,
+            vec![ResponseItem::Message {
+                id: None,
+                role: "assistant".to_string(),
+                content: vec![ContentItem::OutputText {
+                    text: "Hello, world!".to_string()
+                }]
+            }]
+        );
+    }
+
+    #[test]
+    fn append_assistant_text_creates_and_appends() {
+        let mut h = ConversationHistory::default();
+        h.append_assistant_text("Hello");
+        h.append_assistant_text(", world");
+
+        // Now record a final full assistant message and verify it merges.
+        let final_msg = assistant_msg("!");
+        h.record_items([&final_msg]);
+
+        let items = h.contents();
+        assert_eq!(
+            items,
+            vec![ResponseItem::Message {
+                id: None,
+                role: "assistant".to_string(),
+                content: vec![ContentItem::OutputText {
+                    text: "Hello, world!".to_string()
+                }]
+            }]
+        );
+    }
+
+    #[test]
+    fn filters_non_api_messages() {
+        let mut h = ConversationHistory::default();
+        // System message is not an API message; Other is ignored.
+        let system = ResponseItem::Message {
+            id: None,
+            role: "system".to_string(),
+            content: vec![ContentItem::OutputText {
+                text: "ignored".to_string(),
+            }],
+        };
+        h.record_items([&system, &ResponseItem::Other]);
+
+        // User and assistant should be retained.
+        let u = user_msg("hi");
+        let a = assistant_msg("hello");
+        h.record_items([&u, &a]);
+
+        let items = h.contents();
+        assert_eq!(
+            items,
+            vec![
+                ResponseItem::Message {
+                    id: None,
+                    role: "user".to_string(),
+                    content: vec![ContentItem::OutputText {
+                        text: "hi".to_string()
+                    }]
+                },
+                ResponseItem::Message {
+                    id: None,
+                    role: "assistant".to_string(),
+                    content: vec![ContentItem::OutputText {
+                        text: "hello".to_string()
+                    }]
+                }
+            ]
+        );
+    }
+}

codex-rs/core/src/exec.rs

@@ -10,6 +10,7 @@ use std::sync::Arc;
 use std::time::Duration;
 use std::time::Instant;
 
+use async_channel::Sender;
 use tokio::io::AsyncRead;
 use tokio::io::AsyncReadExt;
 use tokio::io::BufReader;
@@ -19,10 +20,15 @@ use tokio::sync::Notify;
 use crate::error::CodexErr;
 use crate::error::Result;
 use crate::error::SandboxErr;
+use crate::protocol::Event;
+use crate::protocol::EventMsg;
+use crate::protocol::ExecCommandOutputDeltaEvent;
+use crate::protocol::ExecOutputStream;
 use crate::protocol::SandboxPolicy;
 use crate::seatbelt::spawn_command_under_seatbelt;
 use crate::spawn::StdioPolicy;
 use crate::spawn::spawn_child_async;
+use serde_bytes::ByteBuf;
 
 // Maximum we send for each stream, which is either:
 // - 10KiB OR
@@ -56,18 +62,26 @@ pub enum SandboxType {
     LinuxSeccomp,
 }
 
+#[derive(Clone)]
+pub struct StdoutStream {
+    pub sub_id: String,
+    pub call_id: String,
+    pub tx_event: Sender<Event>,
+}
+
 pub async fn process_exec_tool_call(
     params: ExecParams,
     sandbox_type: SandboxType,
     ctrl_c: Arc<Notify>,
     sandbox_policy: &SandboxPolicy,
     codex_linux_sandbox_exe: &Option<PathBuf>,
+    stdout_stream: Option<StdoutStream>,
 ) -> Result<ExecToolCallOutput> {
     let start = Instant::now();
 
     let raw_output_result: std::result::Result<RawExecToolCallOutput, CodexErr> = match sandbox_type
     {
-        SandboxType::None => exec(params, sandbox_policy, ctrl_c).await,
+        SandboxType::None => exec(params, sandbox_policy, ctrl_c, stdout_stream.clone()).await,
         SandboxType::MacosSeatbelt => {
             let ExecParams {
                 command,
@@ -83,7 +97,7 @@ pub async fn process_exec_tool_call(
                 env,
             )
             .await?;
-            consume_truncated_output(child, ctrl_c, timeout_ms).await
+            consume_truncated_output(child, ctrl_c, timeout_ms, stdout_stream.clone()).await
         }
         SandboxType::LinuxSeccomp => {
             let ExecParams {
@@ -106,7 +120,7 @@ pub async fn process_exec_tool_call(
             )
             .await?;
 
-            consume_truncated_output(child, ctrl_c, timeout_ms).await
+            consume_truncated_output(child, ctrl_c, timeout_ms, stdout_stream).await
         }
     };
     let duration = start.elapsed();
@@ -126,11 +140,7 @@ pub async fn process_exec_tool_call(
 
             let exit_code = raw_output.exit_status.code().unwrap_or(-1);
 
-            // NOTE(ragona): This is much less restrictive than the previous check. If we exec
-            // a command, and it returns anything other than success, we assume that it may have
-            // been a sandboxing error and allow the user to retry. (The user of course may choose
-            // not to retry, or in a non-interactive mode, would automatically reject the approval.)
-            if exit_code != 0 && sandbox_type != SandboxType::None {
+            if exit_code != 0 && is_likely_sandbox_denied(sandbox_type, exit_code) {
                 return Err(CodexErr::Sandbox(SandboxErr::Denied(
                     exit_code, stdout, stderr,
                 )));
@@ -209,6 +219,26 @@ fn create_linux_sandbox_command_args(
     linux_cmd
 }
 
+/// We don't have a fully deterministic way to tell if our command failed
+/// because of the sandbox - a command in the user's zshrc file might hit an
+/// error, but the command itself might fail or succeed for other reasons.
+/// For now, we conservatively check for 'command not found' (exit code 127),
+/// and can add additional cases as necessary.
+fn is_likely_sandbox_denied(sandbox_type: SandboxType, exit_code: i32) -> bool {
+    if sandbox_type == SandboxType::None {
+        return false;
+    }
+
+    // Quick rejects: well-known non-sandbox shell exit codes
+    // 127: command not found, 2: misuse of shell builtins
+    if exit_code == 127 {
+        return false;
+    }
+
+    // For all other cases, we assume the sandbox is the cause
+    true
+}
+
 #[derive(Debug)]
 pub struct RawExecToolCallOutput {
     pub exit_status: ExitStatus,
@@ -233,6 +263,7 @@ async fn exec(
     }: ExecParams,
     sandbox_policy: &SandboxPolicy,
     ctrl_c: Arc<Notify>,
+    stdout_stream: Option<StdoutStream>,
 ) -> Result<RawExecToolCallOutput> {
     let (program, args) = command.split_first().ok_or_else(|| {
         CodexErr::Io(io::Error::new(
@@ -251,7 +282,7 @@ async fn exec(
         env,
     )
     .await?;
-    consume_truncated_output(child, ctrl_c, timeout_ms).await
+    consume_truncated_output(child, ctrl_c, timeout_ms, stdout_stream).await
 }
 
 /// Consumes the output of a child process, truncating it so it is suitable for
@@ -260,6 +291,7 @@ pub(crate) async fn consume_truncated_output(
     mut child: Child,
     ctrl_c: Arc<Notify>,
     timeout_ms: Option<u64>,
+    stdout_stream: Option<StdoutStream>,
 ) -> Result<RawExecToolCallOutput> {
     // Both stdout and stderr were configured with `Stdio::piped()`
     // above, therefore `take()` should normally return `Some`.  If it doesn't
@@ -280,11 +312,15 @@ pub(crate) async fn consume_truncated_output(
         BufReader::new(stdout_reader),
         MAX_STREAM_OUTPUT,
         MAX_STREAM_OUTPUT_LINES,
+        stdout_stream.clone(),
+        false,
     ));
     let stderr_handle = tokio::spawn(read_capped(
         BufReader::new(stderr_reader),
         MAX_STREAM_OUTPUT,
         MAX_STREAM_OUTPUT_LINES,
+        stdout_stream.clone(),
+        true,
     ));
 
     let interrupted = ctrl_c.notified();
@@ -318,10 +354,12 @@ pub(crate) async fn consume_truncated_output(
     })
 }
 
-async fn read_capped<R: AsyncRead + Unpin>(
+async fn read_capped<R: AsyncRead + Unpin + Send + 'static>(
     mut reader: R,
     max_output: usize,
     max_lines: usize,
+    stream: Option<StdoutStream>,
+    is_stderr: bool,
 ) -> io::Result<Vec<u8>> {
     let mut buf = Vec::with_capacity(max_output.min(8 * 1024));
     let mut tmp = [0u8; 8192];
@@ -335,6 +373,25 @@ async fn read_capped<R: AsyncRead + Unpin>(
             break;
         }
 
+        if let Some(stream) = &stream {
+            let chunk = tmp[..n].to_vec();
+            let msg = EventMsg::ExecCommandOutputDelta(ExecCommandOutputDeltaEvent {
+                call_id: stream.call_id.clone(),
+                stream: if is_stderr {
+                    ExecOutputStream::Stderr
+                } else {
+                    ExecOutputStream::Stdout
+                },
+                chunk: ByteBuf::from(chunk),
+            });
+            let event = Event {
+                id: stream.sub_id.clone(),
+                msg,
+            };
+            #[allow(clippy::let_unit_value)]
+            let _ = stream.tx_event.send(event).await;
+        }
+
         // Copy into the buffer only while we still have byte and line budget.
         if remaining_bytes > 0 && remaining_lines > 0 {
             let mut copy_len = 0;

codex-rs/core/src/lib.rs

@@ -38,12 +38,14 @@ pub mod plan_tool;
 mod project_doc;
 pub mod protocol;
 mod rollout;
-mod safety;
+pub(crate) mod safety;
 pub mod seatbelt;
 pub mod shell;
 pub mod spawn;
+pub mod turn_diff_tracker;
 mod user_notification;
 pub mod util;
 
 pub use apply_patch::CODEX_APPLY_PATCH_ARG1;
 pub use client_common::model_supports_reasoning_summaries;
+pub use safety::get_platform_sandbox;

codex-rs/core/src/model_provider_info.rs

@@ -5,8 +5,11 @@
 //!   2. User-defined entries inside `~/.codex/config.toml` under the `model_providers`
 //!      key. These override or extend the defaults at runtime.
 
+use codex_login::AuthMode;
+use codex_login::CodexAuth;
 use serde::Deserialize;
 use serde::Serialize;
+use std::borrow::Cow;
 use std::collections::HashMap;
 use std::env::VarError;
 use std::time::Duration;
@@ -88,25 +91,30 @@ impl ModelProviderInfo {
     /// When `require_api_key` is true and the provider declares an `env_key`
     /// but the variable is missing/empty, returns an [`Err`] identical to the
     /// one produced by [`ModelProviderInfo::api_key`].
-    pub fn create_request_builder<'a>(
+    pub async fn create_request_builder<'a>(
         &'a self,
         client: &'a reqwest::Client,
+        auth: &Option<CodexAuth>,
     ) -> crate::error::Result<reqwest::RequestBuilder> {
-        let url = self.get_full_url();
+        let auth: Cow<'_, Option<CodexAuth>> = if auth.is_some() {
+            Cow::Borrowed(auth)
+        } else {
+            Cow::Owned(self.get_fallback_auth()?)
+        };
+
+        let url = self.get_full_url(&auth);
 
         let mut builder = client.post(url);
 
-        let api_key = self.api_key()?;
-        if let Some(key) = api_key {
-            builder = builder.bearer_auth(key);
+        if let Some(auth) = auth.as_ref() {
+            builder = builder.bearer_auth(auth.get_token().await?);
         }
 
         Ok(self.apply_http_headers(builder))
     }
 
-    pub(crate) fn get_full_url(&self) -> String {
-        let query_string = self
-            .query_params
+    fn get_query_string(&self) -> String {
+        self.query_params
             .as_ref()
             .map_or_else(String::new, |params| {
                 let full_params = params
@@ -115,16 +123,29 @@ impl ModelProviderInfo {
                     .collect::<Vec<_>>()
                     .join("&");
                 format!("?{full_params}")
-            });
+            })
+    }
+
+    pub(crate) fn get_full_url(&self, auth: &Option<CodexAuth>) -> String {
+        let default_base_url = if matches!(
+            auth,
+            Some(CodexAuth {
+                mode: AuthMode::ChatGPT,
+                ..
+            })
+        ) {
+            "https://chatgpt.com/backend-api/codex"
+        } else {
+            "https://api.openai.com/v1"
+        };
+        let query_string = self.get_query_string();
         let base_url = self
             .base_url
             .clone()
-            .unwrap_or("https://api.openai.com/v1".to_string());
+            .unwrap_or(default_base_url.to_string());
 
         match self.wire_api {
-            WireApi::Responses => {
-                format!("{base_url}/responses{query_string}")
-            }
+            WireApi::Responses => format!("{base_url}/responses{query_string}"),
             WireApi::Chat => format!("{base_url}/chat/completions{query_string}"),
         }
     }
@@ -132,10 +153,7 @@ impl ModelProviderInfo {
     /// Apply provider-specific HTTP headers (both static and environment-based)
     /// onto an existing `reqwest::RequestBuilder` and return the updated
     /// builder.
-    pub fn apply_http_headers(
-        &self,
-        mut builder: reqwest::RequestBuilder,
-    ) -> reqwest::RequestBuilder {
+    fn apply_http_headers(&self, mut builder: reqwest::RequestBuilder) -> reqwest::RequestBuilder {
         if let Some(extra) = &self.http_headers {
             for (k, v) in extra {
                 builder = builder.header(k, v);
@@ -157,7 +175,7 @@ impl ModelProviderInfo {
     /// If `env_key` is Some, returns the API key for this provider if present
     /// (and non-empty) in the environment. If `env_key` is required but
     /// cannot be found, returns an error.
-    fn api_key(&self) -> crate::error::Result<Option<String>> {
+    pub fn api_key(&self) -> crate::error::Result<Option<String>> {
         match &self.env_key {
             Some(env_key) => {
                 let env_value = std::env::var(env_key);
@@ -198,6 +216,14 @@ impl ModelProviderInfo {
             .map(Duration::from_millis)
             .unwrap_or(Duration::from_millis(DEFAULT_STREAM_IDLE_TIMEOUT_MS))
     }
+
+    fn get_fallback_auth(&self) -> crate::error::Result<Option<CodexAuth>> {
+        let api_key = self.api_key()?;
+        if let Some(api_key) = api_key {
+            return Ok(Some(CodexAuth::from_api_key(api_key)));
+        }
+        Ok(None)
+    }
 }
 
 /// Built-in default provider list.

codex-rs/core/src/models.rs

@@ -9,7 +9,7 @@ use serde::ser::Serializer;
 
 use crate::protocol::InputItem;
 
-#[derive(Debug, Clone, Serialize, Deserialize)]
+#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
 #[serde(tag = "type", rename_all = "snake_case")]
 pub enum ResponseInputItem {
     Message {
@@ -26,7 +26,7 @@ pub enum ResponseInputItem {
     },
 }
 
-#[derive(Debug, Clone, Serialize, Deserialize)]
+#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
 #[serde(tag = "type", rename_all = "snake_case")]
 pub enum ContentItem {
     InputText { text: String },
@@ -34,7 +34,7 @@ pub enum ContentItem {
     OutputText { text: String },
 }
 
-#[derive(Debug, Clone, Serialize, Deserialize)]
+#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
 #[serde(tag = "type", rename_all = "snake_case")]
 pub enum ResponseItem {
     Message {
@@ -107,7 +107,7 @@ impl From<ResponseInputItem> for ResponseItem {
     }
 }
 
-#[derive(Debug, Clone, Serialize, Deserialize)]
+#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
 #[serde(rename_all = "snake_case")]
 pub enum LocalShellStatus {
     Completed,
@@ -115,13 +115,13 @@ pub enum LocalShellStatus {
     Incomplete,
 }
 
-#[derive(Debug, Clone, Serialize, Deserialize)]
+#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
 #[serde(tag = "type", rename_all = "snake_case")]
 pub enum LocalShellAction {
     Exec(LocalShellExecAction),
 }
 
-#[derive(Debug, Clone, Serialize, Deserialize)]
+#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
 pub struct LocalShellExecAction {
     pub command: Vec<String>,
     pub timeout_ms: Option<u64>,
@@ -130,7 +130,7 @@ pub struct LocalShellExecAction {
     pub user: Option<String>,
 }
 
-#[derive(Debug, Clone, Serialize, Deserialize)]
+#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
 #[serde(tag = "type", rename_all = "snake_case")]
 pub enum ReasoningItemReasoningSummary {
     SummaryText { text: String },
@@ -185,10 +185,9 @@ pub struct ShellToolCallParams {
     pub timeout_ms: Option<u64>,
 }
 
-#[derive(Debug, Clone)]
+#[derive(Debug, Clone, PartialEq)]
 pub struct FunctionCallOutputPayload {
     pub content: String,
-    #[expect(dead_code)]
     pub success: Option<bool>,
 }
 

codex-rs/core/src/protocol.rs

@@ -13,6 +13,7 @@ use std::time::Duration;
 use mcp_types::CallToolResult;
 use serde::Deserialize;
 use serde::Serialize;
+use serde_bytes::ByteBuf;
 use strum_macros::Display;
 use uuid::Uuid;
 
@@ -179,9 +180,29 @@ pub enum SandboxPolicy {
         /// default.
         #[serde(default)]
         network_access: bool,
+
+        /// When set to `true`, will include defaults like the current working
+        /// directory and TMPDIR (on macOS). When `false`, only `writable_roots`
+        /// are used. (Mainly used for testing.)
+        #[serde(default = "default_true")]
+        include_default_writable_roots: bool,
     },
 }
 
+/// A writable root path accompanied by a list of subpaths that should remain
+/// read‑only even when the root is writable. This is primarily used to ensure
+/// top‑level VCS metadata directories (e.g. `.git`) under a writable root are
+/// not modified by the agent.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct WritableRoot {
+    pub root: PathBuf,
+    pub read_only_subpaths: Vec<PathBuf>,
+}
+
+fn default_true() -> bool {
+    true
+}
+
 impl FromStr for SandboxPolicy {
     type Err = serde_json::Error;
 
@@ -203,6 +224,7 @@ impl SandboxPolicy {
         SandboxPolicy::WorkspaceWrite {
             writable_roots: vec![],
             network_access: false,
+            include_default_writable_roots: true,
         }
     }
 
@@ -228,27 +250,51 @@ impl SandboxPolicy {
         }
     }
 
-    /// Returns the list of writable roots that should be passed down to the
-    /// Landlock rules installer, tailored to the current working directory.
-    pub fn get_writable_roots_with_cwd(&self, cwd: &Path) -> Vec<PathBuf> {
+    /// Returns the list of writable roots (tailored to the current working
+    /// directory) together with subpaths that should remain read‑only under
+    /// each writable root.
+    pub fn get_writable_roots_with_cwd(&self, cwd: &Path) -> Vec<WritableRoot> {
         match self {
             SandboxPolicy::DangerFullAccess => Vec::new(),
             SandboxPolicy::ReadOnly => Vec::new(),
-            SandboxPolicy::WorkspaceWrite { writable_roots, .. } => {
-                let mut roots = writable_roots.clone();
-                roots.push(cwd.to_path_buf());
+            SandboxPolicy::WorkspaceWrite {
+                writable_roots,
+                include_default_writable_roots,
+                ..
+            } => {
+                // Start from explicitly configured writable roots.
+                let mut roots: Vec<PathBuf> = writable_roots.clone();
 
-                // Also include the per-user tmp dir on macOS.
-                // Note this is added dynamically rather than storing it in
-                // writable_roots because writable_roots contains only static
-                // values deserialized from the config file.
-                if cfg!(target_os = "macos") {
-                    if let Some(tmpdir) = std::env::var_os("TMPDIR") {
-                        roots.push(PathBuf::from(tmpdir));
+                // Optionally include defaults (cwd and TMPDIR on macOS).
+                if *include_default_writable_roots {
+                    roots.push(cwd.to_path_buf());
+
+                    // Also include the per-user tmp dir on macOS.
+                    // Note this is added dynamically rather than storing it in
+                    // `writable_roots` because `writable_roots` contains only static
+                    // values deserialized from the config file.
+                    if cfg!(target_os = "macos") {
+                        if let Some(tmpdir) = std::env::var_os("TMPDIR") {
+                            roots.push(PathBuf::from(tmpdir));
+                        }
                     }
                 }
 
+                // For each root, compute subpaths that should remain read-only.
                 roots
+                    .into_iter()
+                    .map(|writable_root| {
+                        let mut subpaths = Vec::new();
+                        let top_level_git = writable_root.join(".git");
+                        if top_level_git.is_dir() {
+                            subpaths.push(top_level_git);
+                        }
+                        WritableRoot {
+                            root: writable_root,
+                            read_only_subpaths: subpaths,
+                        }
+                    })
+                    .collect()
             }
         }
     }
@@ -323,6 +369,9 @@ pub enum EventMsg {
     /// Notification that the server is about to execute a command.
     ExecCommandBegin(ExecCommandBeginEvent),
 
+    /// Incremental chunk of output from a running command.
+    ExecCommandOutputDelta(ExecCommandOutputDeltaEvent),
+
     ExecCommandEnd(ExecCommandEndEvent),
 
     ExecApprovalRequest(ExecApprovalRequestEvent),
@@ -338,6 +387,8 @@ pub enum EventMsg {
     /// Notification that a patch application has finished.
     PatchApplyEnd(PatchApplyEndEvent),
 
+    TurnDiff(TurnDiffEvent),
+
     /// Response to GetHistoryEntryRequest.
     GetHistoryEntryResponse(GetHistoryEntryResponseEvent),
 
@@ -474,6 +525,26 @@ pub struct ExecCommandEndEvent {
     pub stderr: String,
     /// The command's exit code.
     pub exit_code: i32,
+    /// The duration of the command execution.
+    pub duration: Duration,
+}
+
+#[derive(Debug, Clone, Deserialize, Serialize)]
+#[serde(rename_all = "snake_case")]
+pub enum ExecOutputStream {
+    Stdout,
+    Stderr,
+}
+
+#[derive(Debug, Clone, Deserialize, Serialize)]
+pub struct ExecCommandOutputDeltaEvent {
+    /// Identifier for the ExecCommandBegin that produced this chunk.
+    pub call_id: String,
+    /// Which stream produced this chunk.
+    pub stream: ExecOutputStream,
+    /// Raw bytes from the stream (may not be valid UTF-8).
+    #[serde(with = "serde_bytes")]
+    pub chunk: ByteBuf,
 }
 
 #[derive(Debug, Clone, Deserialize, Serialize)]
@@ -529,6 +600,11 @@ pub struct PatchApplyEndEvent {
     pub success: bool,
 }
 
+#[derive(Debug, Clone, Deserialize, Serialize)]
+pub struct TurnDiffEvent {
+    pub unified_diff: String,
+}
+
 #[derive(Debug, Clone, Deserialize, Serialize)]
 pub struct GetHistoryEntryResponseEvent {
     pub offset: usize,

codex-rs/core/src/seatbelt.rs

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

codex-rs/core/src/seatbelt_base_policy.sbpl

@@ -65,3 +65,7 @@
   (sysctl-name "sysctl.proc_cputype")
   (sysctl-name-prefix "hw.perflevel")
 )
+
+; Added on top of Chrome profile
+; Needed for python multiprocessing on MacOS for the SemLock
+(allow ipc-posix-sem)

codex-rs/core/src/shell.rs

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

codex-rs/core/src/spawn.rs

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

codex-rs/core/src/turn_diff_tracker.rs

@@ -0,0 +1,887 @@
+use std::collections::HashMap;
+use std::fs;
+use std::path::Path;
+use std::path::PathBuf;
+use std::process::Command;
+
+use anyhow::Context;
+use anyhow::Result;
+use anyhow::anyhow;
+use sha1::digest::Output;
+use uuid::Uuid;
+
+use crate::protocol::FileChange;
+
+const ZERO_OID: &str = "0000000000000000000000000000000000000000";
+const DEV_NULL: &str = "/dev/null";
+
+struct BaselineFileInfo {
+    path: PathBuf,
+    content: Vec<u8>,
+    mode: FileMode,
+    oid: String,
+}
+
+/// Tracks sets of changes to files and exposes the overall unified diff.
+/// Internally, the way this works is now:
+/// 1. Maintain an in-memory baseline snapshot of files when they are first seen.
+///    For new additions, do not create a baseline so that diffs are shown as proper additions (using /dev/null).
+/// 2. Keep a stable internal filename (uuid) per external path for rename tracking.
+/// 3. To compute the aggregated unified diff, compare each baseline snapshot to the current file on disk entirely in-memory
+///    using the `similar` crate and emit unified diffs with rewritten external paths.
+#[derive(Default)]
+pub struct TurnDiffTracker {
+    /// Map external path -> internal filename (uuid).
+    external_to_temp_name: HashMap<PathBuf, String>,
+    /// Internal filename -> baseline file info.
+    baseline_file_info: HashMap<String, BaselineFileInfo>,
+    /// Internal filename -> external path as of current accumulated state (after applying all changes).
+    /// This is where renames are tracked.
+    temp_name_to_current_path: HashMap<String, PathBuf>,
+    /// Cache of known git worktree roots to avoid repeated filesystem walks.
+    git_root_cache: Vec<PathBuf>,
+}
+
+impl TurnDiffTracker {
+    pub fn new() -> Self {
+        Self::default()
+    }
+
+    /// Front-run apply patch calls to track the starting contents of any modified files.
+    /// - Creates an in-memory baseline snapshot for files that already exist on disk when first seen.
+    /// - For additions, we intentionally do not create a baseline snapshot so that diffs are proper additions.
+    /// - Also updates internal mappings for move/rename events.
+    pub fn on_patch_begin(&mut self, changes: &HashMap<PathBuf, FileChange>) {
+        for (path, change) in changes.iter() {
+            // Ensure a stable internal filename exists for this external path.
+            if !self.external_to_temp_name.contains_key(path) {
+                let internal = Uuid::new_v4().to_string();
+                self.external_to_temp_name
+                    .insert(path.clone(), internal.clone());
+                self.temp_name_to_current_path
+                    .insert(internal.clone(), path.clone());
+
+                // If the file exists on disk now, snapshot as baseline; else leave missing to represent /dev/null.
+                let baseline_file_info = if path.exists() {
+                    let mode = file_mode_for_path(path);
+                    let mode_val = mode.unwrap_or(FileMode::Regular);
+                    let content = blob_bytes(path, &mode_val).unwrap_or_default();
+                    let oid = if mode == Some(FileMode::Symlink) {
+                        format!("{:x}", git_blob_sha1_hex_bytes(&content))
+                    } else {
+                        self.git_blob_oid_for_path(path)
+                            .unwrap_or_else(|| format!("{:x}", git_blob_sha1_hex_bytes(&content)))
+                    };
+                    Some(BaselineFileInfo {
+                        path: path.clone(),
+                        content,
+                        mode: mode_val,
+                        oid,
+                    })
+                } else {
+                    Some(BaselineFileInfo {
+                        path: path.clone(),
+                        content: vec![],
+                        mode: FileMode::Regular,
+                        oid: ZERO_OID.to_string(),
+                    })
+                };
+
+                if let Some(baseline_file_info) = baseline_file_info {
+                    self.baseline_file_info
+                        .insert(internal.clone(), baseline_file_info);
+                }
+            }
+
+            // Track rename/move in current mapping if provided in an Update.
+            if let FileChange::Update {
+                move_path: Some(dest),
+                ..
+            } = change
+            {
+                let uuid_filename = match self.external_to_temp_name.get(path) {
+                    Some(i) => i.clone(),
+                    None => {
+                        // This should be rare, but if we haven't mapped the source, create it with no baseline.
+                        let i = Uuid::new_v4().to_string();
+                        self.baseline_file_info.insert(
+                            i.clone(),
+                            BaselineFileInfo {
+                                path: path.clone(),
+                                content: vec![],
+                                mode: FileMode::Regular,
+                                oid: ZERO_OID.to_string(),
+                            },
+                        );
+                        i
+                    }
+                };
+                // Update current external mapping for temp file name.
+                self.temp_name_to_current_path
+                    .insert(uuid_filename.clone(), dest.clone());
+                // Update forward file_mapping: external current -> internal name.
+                self.external_to_temp_name.remove(path);
+                self.external_to_temp_name
+                    .insert(dest.clone(), uuid_filename);
+            };
+        }
+    }
+
+    fn get_path_for_internal(&self, internal: &str) -> Option<PathBuf> {
+        self.temp_name_to_current_path
+            .get(internal)
+            .cloned()
+            .or_else(|| {
+                self.baseline_file_info
+                    .get(internal)
+                    .map(|info| info.path.clone())
+            })
+    }
+
+    /// Find the git worktree root for a file/directory by walking up to the first ancestor containing a `.git` entry.
+    /// Uses a simple cache of known roots and avoids negative-result caching for simplicity.
+    fn find_git_root_cached(&mut self, start: &Path) -> Option<PathBuf> {
+        let dir = if start.is_dir() {
+            start
+        } else {
+            start.parent()?
+        };
+
+        // Fast path: if any cached root is an ancestor of this path, use it.
+        if let Some(root) = self
+            .git_root_cache
+            .iter()
+            .find(|r| dir.starts_with(r))
+            .cloned()
+        {
+            return Some(root);
+        }
+
+        // Walk up to find a `.git` marker.
+        let mut cur = dir.to_path_buf();
+        loop {
+            let git_marker = cur.join(".git");
+            if git_marker.is_dir() || git_marker.is_file() {
+                if !self.git_root_cache.iter().any(|r| r == &cur) {
+                    self.git_root_cache.push(cur.clone());
+                }
+                return Some(cur);
+            }
+
+            // On Windows, avoid walking above the drive or UNC share root.
+            #[cfg(windows)]
+            {
+                if is_windows_drive_or_unc_root(&cur) {
+                    return None;
+                }
+            }
+
+            if let Some(parent) = cur.parent() {
+                cur = parent.to_path_buf();
+            } else {
+                return None;
+            }
+        }
+    }
+
+    /// Return a display string for `path` relative to its git root if found, else absolute.
+    fn relative_to_git_root_str(&mut self, path: &Path) -> String {
+        let s = if let Some(root) = self.find_git_root_cached(path) {
+            if let Ok(rel) = path.strip_prefix(&root) {
+                rel.display().to_string()
+            } else {
+                path.display().to_string()
+            }
+        } else {
+            path.display().to_string()
+        };
+        s.replace('\\', "/")
+    }
+
+    /// Ask git to compute the blob SHA-1 for the file at `path` within its repository.
+    /// Returns None if no repository is found or git invocation fails.
+    fn git_blob_oid_for_path(&mut self, path: &Path) -> Option<String> {
+        let root = self.find_git_root_cached(path)?;
+        // Compute a path relative to the repo root for better portability across platforms.
+        let rel = path.strip_prefix(&root).unwrap_or(path);
+        let output = Command::new("git")
+            .arg("-C")
+            .arg(&root)
+            .arg("hash-object")
+            .arg("--")
+            .arg(rel)
+            .output()
+            .ok()?;
+        if !output.status.success() {
+            return None;
+        }
+        let s = String::from_utf8_lossy(&output.stdout).trim().to_string();
+        if s.len() == 40 { Some(s) } else { None }
+    }
+
+    /// Recompute the aggregated unified diff by comparing all of the in-memory snapshots that were
+    /// collected before the first time they were touched by apply_patch during this turn with
+    /// the current repo state.
+    pub fn get_unified_diff(&mut self) -> Result<Option<String>> {
+        let mut aggregated = String::new();
+
+        // Compute diffs per tracked internal file in a stable order by external path.
+        let mut baseline_file_names: Vec<String> =
+            self.baseline_file_info.keys().cloned().collect();
+        // Sort lexicographically by full repo-relative path to match git behavior.
+        baseline_file_names.sort_by_key(|internal| {
+            self.get_path_for_internal(internal)
+                .map(|p| self.relative_to_git_root_str(&p))
+                .unwrap_or_default()
+        });
+
+        for internal in baseline_file_names {
+            aggregated.push_str(self.get_file_diff(&internal).as_str());
+            if !aggregated.ends_with('\n') {
+                aggregated.push('\n');
+            }
+        }
+
+        if aggregated.trim().is_empty() {
+            Ok(None)
+        } else {
+            Ok(Some(aggregated))
+        }
+    }
+
+    fn get_file_diff(&mut self, internal_file_name: &str) -> String {
+        let mut aggregated = String::new();
+
+        // Snapshot lightweight fields only.
+        let (baseline_external_path, baseline_mode, left_oid) = {
+            if let Some(info) = self.baseline_file_info.get(internal_file_name) {
+                (info.path.clone(), info.mode, info.oid.clone())
+            } else {
+                (PathBuf::new(), FileMode::Regular, ZERO_OID.to_string())
+            }
+        };
+        let current_external_path = match self.get_path_for_internal(internal_file_name) {
+            Some(p) => p,
+            None => return aggregated,
+        };
+
+        let current_mode = file_mode_for_path(&current_external_path).unwrap_or(FileMode::Regular);
+        let right_bytes = blob_bytes(&current_external_path, &current_mode);
+
+        // Compute displays with &mut self before borrowing any baseline content.
+        let left_display = self.relative_to_git_root_str(&baseline_external_path);
+        let right_display = self.relative_to_git_root_str(&current_external_path);
+
+        // Compute right oid before borrowing baseline content.
+        let right_oid = if let Some(b) = right_bytes.as_ref() {
+            if current_mode == FileMode::Symlink {
+                format!("{:x}", git_blob_sha1_hex_bytes(b))
+            } else {
+                self.git_blob_oid_for_path(&current_external_path)
+                    .unwrap_or_else(|| format!("{:x}", git_blob_sha1_hex_bytes(b)))
+            }
+        } else {
+            ZERO_OID.to_string()
+        };
+
+        // Borrow baseline content only after all &mut self uses are done.
+        let left_present = left_oid.as_str() != ZERO_OID;
+        let left_bytes: Option<&[u8]> = if left_present {
+            self.baseline_file_info
+                .get(internal_file_name)
+                .map(|i| i.content.as_slice())
+        } else {
+            None
+        };
+
+        // Fast path: identical bytes or both missing.
+        if left_bytes == right_bytes.as_deref() {
+            return aggregated;
+        }
+
+        aggregated.push_str(&format!("diff --git a/{left_display} b/{right_display}\n"));
+
+        let is_add = !left_present && right_bytes.is_some();
+        let is_delete = left_present && right_bytes.is_none();
+
+        if is_add {
+            aggregated.push_str(&format!("new file mode {current_mode}\n"));
+        } else if is_delete {
+            aggregated.push_str(&format!("deleted file mode {baseline_mode}\n"));
+        } else if baseline_mode != current_mode {
+            aggregated.push_str(&format!("old mode {baseline_mode}\n"));
+            aggregated.push_str(&format!("new mode {current_mode}\n"));
+        }
+
+        let left_text = left_bytes.and_then(|b| std::str::from_utf8(b).ok());
+        let right_text = right_bytes
+            .as_deref()
+            .and_then(|b| std::str::from_utf8(b).ok());
+
+        let can_text_diff = matches!(
+            (left_text, right_text, is_add, is_delete),
+            (Some(_), Some(_), _, _) | (_, Some(_), true, _) | (Some(_), _, _, true)
+        );
+
+        if can_text_diff {
+            let l = left_text.unwrap_or("");
+            let r = right_text.unwrap_or("");
+
+            aggregated.push_str(&format!("index {left_oid}..{right_oid}\n"));
+
+            let old_header = if left_present {
+                format!("a/{left_display}")
+            } else {
+                DEV_NULL.to_string()
+            };
+            let new_header = if right_bytes.is_some() {
+                format!("b/{right_display}")
+            } else {
+                DEV_NULL.to_string()
+            };
+
+            let diff = similar::TextDiff::from_lines(l, r);
+            let unified = diff
+                .unified_diff()
+                .context_radius(3)
+                .header(&old_header, &new_header)
+                .to_string();
+
+            aggregated.push_str(&unified);
+        } else {
+            aggregated.push_str(&format!("index {left_oid}..{right_oid}\n"));
+            let old_header = if left_present {
+                format!("a/{left_display}")
+            } else {
+                DEV_NULL.to_string()
+            };
+            let new_header = if right_bytes.is_some() {
+                format!("b/{right_display}")
+            } else {
+                DEV_NULL.to_string()
+            };
+            aggregated.push_str(&format!("--- {old_header}\n"));
+            aggregated.push_str(&format!("+++ {new_header}\n"));
+            aggregated.push_str("Binary files differ\n");
+        }
+        aggregated
+    }
+}
+
+/// Compute the Git SHA-1 blob object ID for the given content (bytes).
+fn git_blob_sha1_hex_bytes(data: &[u8]) -> Output<sha1::Sha1> {
+    // Git blob hash is sha1 of: "blob <len>\0<data>"
+    let header = format!("blob {}\0", data.len());
+    use sha1::Digest;
+    let mut hasher = sha1::Sha1::new();
+    hasher.update(header.as_bytes());
+    hasher.update(data);
+    hasher.finalize()
+}
+
+#[derive(Clone, Copy, Debug, PartialEq, Eq)]
+enum FileMode {
+    Regular,
+    #[cfg(unix)]
+    Executable,
+    Symlink,
+}
+
+impl FileMode {
+    fn as_str(&self) -> &'static str {
+        match self {
+            FileMode::Regular => "100644",
+            #[cfg(unix)]
+            FileMode::Executable => "100755",
+            FileMode::Symlink => "120000",
+        }
+    }
+}
+
+impl std::fmt::Display for FileMode {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.write_str(self.as_str())
+    }
+}
+
+#[cfg(unix)]
+fn file_mode_for_path(path: &Path) -> Option<FileMode> {
+    use std::os::unix::fs::PermissionsExt;
+    let meta = fs::symlink_metadata(path).ok()?;
+    let ft = meta.file_type();
+    if ft.is_symlink() {
+        return Some(FileMode::Symlink);
+    }
+    let mode = meta.permissions().mode();
+    let is_exec = (mode & 0o111) != 0;
+    Some(if is_exec {
+        FileMode::Executable
+    } else {
+        FileMode::Regular
+    })
+}
+
+#[cfg(not(unix))]
+fn file_mode_for_path(_path: &Path) -> Option<FileMode> {
+    // Default to non-executable on non-unix.
+    Some(FileMode::Regular)
+}
+
+fn blob_bytes(path: &Path, mode: &FileMode) -> Option<Vec<u8>> {
+    if path.exists() {
+        let contents = if *mode == FileMode::Symlink {
+            symlink_blob_bytes(path)
+                .ok_or_else(|| anyhow!("failed to read symlink target for {}", path.display()))
+        } else {
+            fs::read(path)
+                .with_context(|| format!("failed to read current file for diff {}", path.display()))
+        };
+        contents.ok()
+    } else {
+        None
+    }
+}
+
+#[cfg(unix)]
+fn symlink_blob_bytes(path: &Path) -> Option<Vec<u8>> {
+    use std::os::unix::ffi::OsStrExt;
+    let target = std::fs::read_link(path).ok()?;
+    Some(target.as_os_str().as_bytes().to_vec())
+}
+
+#[cfg(not(unix))]
+fn symlink_blob_bytes(_path: &Path) -> Option<Vec<u8>> {
+    None
+}
+
+#[cfg(windows)]
+fn is_windows_drive_or_unc_root(p: &std::path::Path) -> bool {
+    use std::path::Component;
+    let mut comps = p.components();
+    matches!(
+        (comps.next(), comps.next(), comps.next()),
+        (Some(Component::Prefix(_)), Some(Component::RootDir), None)
+    )
+}
+
+#[cfg(test)]
+mod tests {
+    #![allow(clippy::unwrap_used)]
+    use super::*;
+    use pretty_assertions::assert_eq;
+    use tempfile::tempdir;
+
+    /// Compute the Git SHA-1 blob object ID for the given content (string).
+    /// This delegates to the bytes version to avoid UTF-8 lossy conversions here.
+    fn git_blob_sha1_hex(data: &str) -> String {
+        format!("{:x}", git_blob_sha1_hex_bytes(data.as_bytes()))
+    }
+
+    fn normalize_diff_for_test(input: &str, root: &Path) -> String {
+        let root_str = root.display().to_string().replace('\\', "/");
+        let replaced = input.replace(&root_str, "<TMP>");
+        // Split into blocks on lines starting with "diff --git ", sort blocks for determinism, and rejoin
+        let mut blocks: Vec<String> = Vec::new();
+        let mut current = String::new();
+        for line in replaced.lines() {
+            if line.starts_with("diff --git ") && !current.is_empty() {
+                blocks.push(current);
+                current = String::new();
+            }
+            if !current.is_empty() {
+                current.push('\n');
+            }
+            current.push_str(line);
+        }
+        if !current.is_empty() {
+            blocks.push(current);
+        }
+        blocks.sort();
+        let mut out = blocks.join("\n");
+        if !out.ends_with('\n') {
+            out.push('\n');
+        }
+        out
+    }
+
+    #[test]
+    fn accumulates_add_and_update() {
+        let mut acc = TurnDiffTracker::new();
+
+        let dir = tempdir().unwrap();
+        let file = dir.path().join("a.txt");
+
+        // First patch: add file (baseline should be /dev/null).
+        let add_changes = HashMap::from([(
+            file.clone(),
+            FileChange::Add {
+                content: "foo\n".to_string(),
+            },
+        )]);
+        acc.on_patch_begin(&add_changes);
+
+        // Simulate apply: create the file on disk.
+        fs::write(&file, "foo\n").unwrap();
+        let first = acc.get_unified_diff().unwrap().unwrap();
+        let first = normalize_diff_for_test(&first, dir.path());
+        let expected_first = {
+            let mode = file_mode_for_path(&file).unwrap_or(FileMode::Regular);
+            let right_oid = git_blob_sha1_hex("foo\n");
+            format!(
+                r#"diff --git a/<TMP>/a.txt b/<TMP>/a.txt
+new file mode {mode}
+index {ZERO_OID}..{right_oid}
+--- {DEV_NULL}
++++ b/<TMP>/a.txt
+@@ -0,0 +1 @@
++foo
+"#,
+            )
+        };
+        assert_eq!(first, expected_first);
+
+        // Second patch: update the file on disk.
+        let update_changes = HashMap::from([(
+            file.clone(),
+            FileChange::Update {
+                unified_diff: "".to_owned(),
+                move_path: None,
+            },
+        )]);
+        acc.on_patch_begin(&update_changes);
+
+        // Simulate apply: append a new line.
+        fs::write(&file, "foo\nbar\n").unwrap();
+        let combined = acc.get_unified_diff().unwrap().unwrap();
+        let combined = normalize_diff_for_test(&combined, dir.path());
+        let expected_combined = {
+            let mode = file_mode_for_path(&file).unwrap_or(FileMode::Regular);
+            let right_oid = git_blob_sha1_hex("foo\nbar\n");
+            format!(
+                r#"diff --git a/<TMP>/a.txt b/<TMP>/a.txt
+new file mode {mode}
+index {ZERO_OID}..{right_oid}
+--- {DEV_NULL}
++++ b/<TMP>/a.txt
+@@ -0,0 +1,2 @@
++foo
++bar
+"#,
+            )
+        };
+        assert_eq!(combined, expected_combined);
+    }
+
+    #[test]
+    fn accumulates_delete() {
+        let dir = tempdir().unwrap();
+        let file = dir.path().join("b.txt");
+        fs::write(&file, "x\n").unwrap();
+
+        let mut acc = TurnDiffTracker::new();
+        let del_changes = HashMap::from([(file.clone(), FileChange::Delete)]);
+        acc.on_patch_begin(&del_changes);
+
+        // Simulate apply: delete the file from disk.
+        let baseline_mode = file_mode_for_path(&file).unwrap_or(FileMode::Regular);
+        fs::remove_file(&file).unwrap();
+        let diff = acc.get_unified_diff().unwrap().unwrap();
+        let diff = normalize_diff_for_test(&diff, dir.path());
+        let expected = {
+            let left_oid = git_blob_sha1_hex("x\n");
+            format!(
+                r#"diff --git a/<TMP>/b.txt b/<TMP>/b.txt
+deleted file mode {baseline_mode}
+index {left_oid}..{ZERO_OID}
+--- a/<TMP>/b.txt
++++ {DEV_NULL}
+@@ -1 +0,0 @@
+-x
+"#,
+            )
+        };
+        assert_eq!(diff, expected);
+    }
+
+    #[test]
+    fn accumulates_move_and_update() {
+        let dir = tempdir().unwrap();
+        let src = dir.path().join("src.txt");
+        let dest = dir.path().join("dst.txt");
+        fs::write(&src, "line\n").unwrap();
+
+        let mut acc = TurnDiffTracker::new();
+        let mv_changes = HashMap::from([(
+            src.clone(),
+            FileChange::Update {
+                unified_diff: "".to_owned(),
+                move_path: Some(dest.clone()),
+            },
+        )]);
+        acc.on_patch_begin(&mv_changes);
+
+        // Simulate apply: move and update content.
+        fs::rename(&src, &dest).unwrap();
+        fs::write(&dest, "line2\n").unwrap();
+
+        let out = acc.get_unified_diff().unwrap().unwrap();
+        let out = normalize_diff_for_test(&out, dir.path());
+        let expected = {
+            let left_oid = git_blob_sha1_hex("line\n");
+            let right_oid = git_blob_sha1_hex("line2\n");
+            format!(
+                r#"diff --git a/<TMP>/src.txt b/<TMP>/dst.txt
+index {left_oid}..{right_oid}
+--- a/<TMP>/src.txt
++++ b/<TMP>/dst.txt
+@@ -1 +1 @@
+-line
++line2
+"#
+            )
+        };
+        assert_eq!(out, expected);
+    }
+
+    #[test]
+    fn move_without_1change_yields_no_diff() {
+        let dir = tempdir().unwrap();
+        let src = dir.path().join("moved.txt");
+        let dest = dir.path().join("renamed.txt");
+        fs::write(&src, "same\n").unwrap();
+
+        let mut acc = TurnDiffTracker::new();
+        let mv_changes = HashMap::from([(
+            src.clone(),
+            FileChange::Update {
+                unified_diff: "".to_owned(),
+                move_path: Some(dest.clone()),
+            },
+        )]);
+        acc.on_patch_begin(&mv_changes);
+
+        // Simulate apply: move only, no content change.
+        fs::rename(&src, &dest).unwrap();
+
+        let diff = acc.get_unified_diff().unwrap();
+        assert_eq!(diff, None);
+    }
+
+    #[test]
+    fn move_declared_but_file_only_appears_at_dest_is_add() {
+        let dir = tempdir().unwrap();
+        let src = dir.path().join("src.txt");
+        let dest = dir.path().join("dest.txt");
+        let mut acc = TurnDiffTracker::new();
+        let mv = HashMap::from([(
+            src.clone(),
+            FileChange::Update {
+                unified_diff: "".into(),
+                move_path: Some(dest.clone()),
+            },
+        )]);
+        acc.on_patch_begin(&mv);
+        // No file existed initially; create only dest
+        fs::write(&dest, "hello\n").unwrap();
+        let diff = acc.get_unified_diff().unwrap().unwrap();
+        let diff = normalize_diff_for_test(&diff, dir.path());
+        let expected = {
+            let mode = file_mode_for_path(&dest).unwrap_or(FileMode::Regular);
+            let right_oid = git_blob_sha1_hex("hello\n");
+            format!(
+                r#"diff --git a/<TMP>/src.txt b/<TMP>/dest.txt
+new file mode {mode}
+index {ZERO_OID}..{right_oid}
+--- {DEV_NULL}
++++ b/<TMP>/dest.txt
+@@ -0,0 +1 @@
++hello
+"#,
+            )
+        };
+        assert_eq!(diff, expected);
+    }
+
+    #[test]
+    fn update_persists_across_new_baseline_for_new_file() {
+        let dir = tempdir().unwrap();
+        let a = dir.path().join("a.txt");
+        let b = dir.path().join("b.txt");
+        fs::write(&a, "foo\n").unwrap();
+        fs::write(&b, "z\n").unwrap();
+
+        let mut acc = TurnDiffTracker::new();
+
+        // First: update existing a.txt (baseline snapshot is created for a).
+        let update_a = HashMap::from([(
+            a.clone(),
+            FileChange::Update {
+                unified_diff: "".to_owned(),
+                move_path: None,
+            },
+        )]);
+        acc.on_patch_begin(&update_a);
+        // Simulate apply: modify a.txt on disk.
+        fs::write(&a, "foo\nbar\n").unwrap();
+        let first = acc.get_unified_diff().unwrap().unwrap();
+        let first = normalize_diff_for_test(&first, dir.path());
+        let expected_first = {
+            let left_oid = git_blob_sha1_hex("foo\n");
+            let right_oid = git_blob_sha1_hex("foo\nbar\n");
+            format!(
+                r#"diff --git a/<TMP>/a.txt b/<TMP>/a.txt
+index {left_oid}..{right_oid}
+--- a/<TMP>/a.txt
++++ b/<TMP>/a.txt
+@@ -1 +1,2 @@
+ foo
++bar
+"#
+            )
+        };
+        assert_eq!(first, expected_first);
+
+        // Next: introduce a brand-new path b.txt into baseline snapshots via a delete change.
+        let del_b = HashMap::from([(b.clone(), FileChange::Delete)]);
+        acc.on_patch_begin(&del_b);
+        // Simulate apply: delete b.txt.
+        let baseline_mode = file_mode_for_path(&b).unwrap_or(FileMode::Regular);
+        fs::remove_file(&b).unwrap();
+
+        let combined = acc.get_unified_diff().unwrap().unwrap();
+        let combined = normalize_diff_for_test(&combined, dir.path());
+        let expected = {
+            let left_oid_a = git_blob_sha1_hex("foo\n");
+            let right_oid_a = git_blob_sha1_hex("foo\nbar\n");
+            let left_oid_b = git_blob_sha1_hex("z\n");
+            format!(
+                r#"diff --git a/<TMP>/a.txt b/<TMP>/a.txt
+index {left_oid_a}..{right_oid_a}
+--- a/<TMP>/a.txt
++++ b/<TMP>/a.txt
+@@ -1 +1,2 @@
+ foo
++bar
+diff --git a/<TMP>/b.txt b/<TMP>/b.txt
+deleted file mode {baseline_mode}
+index {left_oid_b}..{ZERO_OID}
+--- a/<TMP>/b.txt
++++ {DEV_NULL}
+@@ -1 +0,0 @@
+-z
+"#,
+            )
+        };
+        assert_eq!(combined, expected);
+    }
+
+    #[test]
+    fn binary_files_differ_update() {
+        let dir = tempdir().unwrap();
+        let file = dir.path().join("bin.dat");
+
+        // Initial non-UTF8 bytes
+        let left_bytes: Vec<u8> = vec![0xff, 0xfe, 0xfd, 0x00];
+        // Updated non-UTF8 bytes
+        let right_bytes: Vec<u8> = vec![0x01, 0x02, 0x03, 0x00];
+
+        fs::write(&file, &left_bytes).unwrap();
+
+        let mut acc = TurnDiffTracker::new();
+        let update_changes = HashMap::from([(
+            file.clone(),
+            FileChange::Update {
+                unified_diff: "".to_owned(),
+                move_path: None,
+            },
+        )]);
+        acc.on_patch_begin(&update_changes);
+
+        // Apply update on disk
+        fs::write(&file, &right_bytes).unwrap();
+
+        let diff = acc.get_unified_diff().unwrap().unwrap();
+        let diff = normalize_diff_for_test(&diff, dir.path());
+        let expected = {
+            let left_oid = format!("{:x}", git_blob_sha1_hex_bytes(&left_bytes));
+            let right_oid = format!("{:x}", git_blob_sha1_hex_bytes(&right_bytes));
+            format!(
+                r#"diff --git a/<TMP>/bin.dat b/<TMP>/bin.dat
+index {left_oid}..{right_oid}
+--- a/<TMP>/bin.dat
++++ b/<TMP>/bin.dat
+Binary files differ
+"#
+            )
+        };
+        assert_eq!(diff, expected);
+    }
+
+    #[test]
+    fn filenames_with_spaces_add_and_update() {
+        let mut acc = TurnDiffTracker::new();
+
+        let dir = tempdir().unwrap();
+        let file = dir.path().join("name with spaces.txt");
+
+        // First patch: add file (baseline should be /dev/null).
+        let add_changes = HashMap::from([(
+            file.clone(),
+            FileChange::Add {
+                content: "foo\n".to_string(),
+            },
+        )]);
+        acc.on_patch_begin(&add_changes);
+
+        // Simulate apply: create the file on disk.
+        fs::write(&file, "foo\n").unwrap();
+        let first = acc.get_unified_diff().unwrap().unwrap();
+        let first = normalize_diff_for_test(&first, dir.path());
+        let expected_first = {
+            let mode = file_mode_for_path(&file).unwrap_or(FileMode::Regular);
+            let right_oid = git_blob_sha1_hex("foo\n");
+            format!(
+                r#"diff --git a/<TMP>/name with spaces.txt b/<TMP>/name with spaces.txt
+new file mode {mode}
+index {ZERO_OID}..{right_oid}
+--- {DEV_NULL}
++++ b/<TMP>/name with spaces.txt
+@@ -0,0 +1 @@
++foo
+"#,
+            )
+        };
+        assert_eq!(first, expected_first);
+
+        // Second patch: update the file on disk.
+        let update_changes = HashMap::from([(
+            file.clone(),
+            FileChange::Update {
+                unified_diff: "".to_owned(),
+                move_path: None,
+            },
+        )]);
+        acc.on_patch_begin(&update_changes);
+
+        // Simulate apply: append a new line with a space.
+        fs::write(&file, "foo\nbar baz\n").unwrap();
+        let combined = acc.get_unified_diff().unwrap().unwrap();
+        let combined = normalize_diff_for_test(&combined, dir.path());
+        let expected_combined = {
+            let mode = file_mode_for_path(&file).unwrap_or(FileMode::Regular);
+            let right_oid = git_blob_sha1_hex("foo\nbar baz\n");
+            format!(
+                r#"diff --git a/<TMP>/name with spaces.txt b/<TMP>/name with spaces.txt
+new file mode {mode}
+index {ZERO_OID}..{right_oid}
+--- {DEV_NULL}
++++ b/<TMP>/name with spaces.txt
+@@ -0,0 +1,2 @@
++foo
++bar baz
+"#,
+            )
+        };
+        assert_eq!(combined, expected_combined);
+    }
+}

codex-rs/core/tests/client.rs

@@ -4,6 +4,7 @@ use chrono::Utc;
 use codex_core::Codex;
 use codex_core::CodexSpawnOk;
 use codex_core::ModelProviderInfo;
+use codex_core::WireApi;
 use codex_core::built_in_model_providers;
 use codex_core::protocol::EventMsg;
 use codex_core::protocol::InputItem;
@@ -21,8 +22,10 @@ use tempfile::TempDir;
 use wiremock::Mock;
 use wiremock::MockServer;
 use wiremock::ResponseTemplate;
+use wiremock::matchers::header_regex;
 use wiremock::matchers::method;
 use wiremock::matchers::path;
+use wiremock::matchers::query_param;
 
 /// Build minimal SSE stream with completed marker using the JSON fixture.
 fn sse_completed(id: &str) -> String {
@@ -373,9 +376,90 @@ async fn includes_user_instructions_message_in_request() {
         request_body["input"][0]["content"][0]["text"]
             .as_str()
             .unwrap()
-            .starts_with("be nice")
+            .starts_with("<user_instructions>\n\nbe nice")
+    );
+    assert!(
+        request_body["input"][0]["content"][0]["text"]
+            .as_str()
+            .unwrap()
+            .ends_with("</user_instructions>")
     );
 }
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn azure_overrides_assign_properties_used_for_responses_url() {
+    #![allow(clippy::unwrap_used)]
+
+    let existing_env_var_with_random_value = if cfg!(windows) { "USERNAME" } else { "USER" };
+
+    // 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");
+
+    // Expect POST to /openai/responses with api-version query param
+    Mock::given(method("POST"))
+        .and(path("/openai/responses"))
+        .and(query_param("api-version", "2025-04-01-preview"))
+        .and(header_regex("Custom-Header", "Value"))
+        .and(header_regex(
+            "Authorization",
+            format!(
+                "Bearer {}",
+                std::env::var(existing_env_var_with_random_value).unwrap()
+            )
+            .as_str(),
+        ))
+        .respond_with(first)
+        .expect(1)
+        .mount(&server)
+        .await;
+
+    let provider = ModelProviderInfo {
+        name: "custom".to_string(),
+        base_url: Some(format!("{}/openai", server.uri())),
+        // Reuse the existing environment variable to avoid using unsafe code
+        env_key: Some(existing_env_var_with_random_value.to_string()),
+        query_params: Some(std::collections::HashMap::from([(
+            "api-version".to_string(),
+            "2025-04-01-preview".to_string(),
+        )])),
+        env_key_instructions: None,
+        wire_api: WireApi::Responses,
+        http_headers: Some(std::collections::HashMap::from([(
+            "Custom-Header".to_string(),
+            "Value".to_string(),
+        )])),
+        env_http_headers: None,
+        request_max_retries: None,
+        stream_max_retries: None,
+        stream_idle_timeout_ms: None,
+        requires_auth: false,
+    };
+
+    // Init session
+    let codex_home = TempDir::new().unwrap();
+    let mut config = load_default_config_for_test(&codex_home);
+    config.model_provider = provider;
+
+    let ctrl_c = std::sync::Arc::new(tokio::sync::Notify::new());
+    let CodexSpawnOk { codex, .. } = Codex::spawn(config, None, 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;
+}
+
 fn auth_from_token(id_token: String) -> CodexAuth {
     CodexAuth::new(
         None,

codex-rs/core/tests/exec.rs

@@ -0,0 +1,69 @@
+#![cfg(target_os = "macos")]
+#![expect(clippy::expect_used)]
+
+use std::collections::HashMap;
+use std::sync::Arc;
+
+use codex_core::exec::ExecParams;
+use codex_core::exec::SandboxType;
+use codex_core::exec::process_exec_tool_call;
+use codex_core::protocol::SandboxPolicy;
+use codex_core::spawn::CODEX_SANDBOX_ENV_VAR;
+use tempfile::TempDir;
+use tokio::sync::Notify;
+
+use codex_core::get_platform_sandbox;
+
+async fn run_test_cmd(tmp: TempDir, cmd: Vec<&str>, should_be_ok: bool) {
+    if std::env::var(CODEX_SANDBOX_ENV_VAR) == Ok("seatbelt".to_string()) {
+        eprintln!("{CODEX_SANDBOX_ENV_VAR} is set to 'seatbelt', skipping test.");
+        return;
+    }
+
+    let sandbox_type = get_platform_sandbox().expect("should be able to get sandbox type");
+    assert_eq!(sandbox_type, SandboxType::MacosSeatbelt);
+
+    let params = ExecParams {
+        command: cmd.iter().map(|s| s.to_string()).collect(),
+        cwd: tmp.path().to_path_buf(),
+        timeout_ms: Some(1000),
+        env: HashMap::new(),
+    };
+
+    let ctrl_c = Arc::new(Notify::new());
+    let policy = SandboxPolicy::new_read_only_policy();
+
+    let result = process_exec_tool_call(params, sandbox_type, ctrl_c, &policy, &None, None).await;
+
+    assert!(result.is_ok() == should_be_ok);
+}
+
+/// Command succeeds with exit code 0 normally
+#[tokio::test]
+async fn exit_code_0_succeeds() {
+    let tmp = TempDir::new().expect("should be able to create temp dir");
+    let cmd = vec!["echo", "hello"];
+
+    run_test_cmd(tmp, cmd, true).await
+}
+
+/// Command not found returns exit code 127, this is not considered a sandbox error
+#[tokio::test]
+async fn exit_command_not_found_is_ok() {
+    let tmp = TempDir::new().expect("should be able to create temp dir");
+    let cmd = vec!["/bin/bash", "-c", "nonexistent_command_12345"];
+    run_test_cmd(tmp, cmd, true).await
+}
+
+/// Writing a file fails and should be considered a sandbox error
+#[tokio::test]
+async fn write_file_fails_as_sandbox_error() {
+    let tmp = TempDir::new().expect("should be able to create temp dir");
+    let path = tmp.path().join("test.txt");
+    let cmd = vec![
+        "/user/bin/touch",
+        path.to_str().expect("should be able to get path"),
+    ];
+
+    run_test_cmd(tmp, cmd, false).await;
+}

codex-rs/core/tests/exec_stream_events.rs

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

codex-rs/core/tests/live_agent.rs

@@ -177,8 +177,7 @@ async fn live_shell_function_call() {
         match ev.msg {
             EventMsg::ExecCommandBegin(codex_core::protocol::ExecCommandBeginEvent {
                 command,
-                call_id: _,
-                cwd: _,
+                ..
             }) => {
                 assert_eq!(command, vec!["echo", MARKER]);
                 saw_begin = true;
@@ -186,8 +185,7 @@ async fn live_shell_function_call() {
             EventMsg::ExecCommandEnd(codex_core::protocol::ExecCommandEndEvent {
                 stdout,
                 exit_code,
-                call_id: _,
-                stderr: _,
+                ..
             }) => {
                 assert_eq!(exit_code, 0, "echo returned non‑zero exit code");
                 assert!(stdout.contains(MARKER));

codex-rs/core/tests/sandbox.rs

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

codex-rs/exec/src/event_processor.rs

@@ -44,20 +44,14 @@ pub(crate) fn create_config_summary_entries(config: &Config) -> Vec<(&'static st
     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."),
+pub(crate) fn handle_last_message(last_agent_message: Option<&str>, output_file: &Path) {
+    let message = last_agent_message.unwrap_or_default();
+    write_last_message_file(message, Some(output_file));
+    if last_agent_message.is_none() {
+        eprintln!(
+            "Warning: no last agent message; wrote empty content to {}",
+            output_file.display()
+        );
     }
 }
 

codex-rs/exec/src/event_processor_with_human_output.rs

@@ -20,6 +20,7 @@ use codex_core::protocol::PatchApplyEndEvent;
 use codex_core::protocol::SessionConfiguredEvent;
 use codex_core::protocol::TaskCompleteEvent;
 use codex_core::protocol::TokenUsage;
+use codex_core::protocol::TurnDiffEvent;
 use owo_colors::OwoColorize;
 use owo_colors::Style;
 use shlex::try_join;
@@ -106,7 +107,6 @@ impl EventProcessorWithHumanOutput {
 
 struct ExecCommandBegin {
     command: Vec<String>,
-    start_time: Instant,
 }
 
 struct PatchApplyBegin {
@@ -170,10 +170,9 @@ impl EventProcessor for EventProcessorWithHumanOutput {
                 // Ignore.
             }
             EventMsg::TaskComplete(TaskCompleteEvent { last_agent_message }) => {
-                handle_last_message(
-                    last_agent_message.as_deref(),
-                    self.last_message_path.as_deref(),
-                );
+                if let Some(output_file) = self.last_message_path.as_deref() {
+                    handle_last_message(last_agent_message.as_deref(), output_file);
+                }
                 return CodexStatus::InitiateShutdown;
             }
             EventMsg::TokenCount(TokenUsage { total_tokens, .. }) => {
@@ -228,7 +227,6 @@ impl EventProcessor for EventProcessorWithHumanOutput {
                     call_id.clone(),
                     ExecCommandBegin {
                         command: command.clone(),
-                        start_time: Instant::now(),
                     },
                 );
                 ts_println!(
@@ -239,20 +237,19 @@ impl EventProcessor for EventProcessorWithHumanOutput {
                     cwd.to_string_lossy(),
                 );
             }
+            EventMsg::ExecCommandOutputDelta(_) => {}
             EventMsg::ExecCommandEnd(ExecCommandEndEvent {
                 call_id,
                 stdout,
                 stderr,
+                duration,
                 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
+                let (duration, call) = if let Some(ExecCommandBegin { command, .. }) = exec_command
                 {
                     (
-                        format!(" in {}", format_elapsed(start_time)),
+                        format!(" in {}", format_duration(duration)),
                         format!("{}", escape_command(&command).style(self.bold)),
                     )
                 } else {
@@ -402,6 +399,7 @@ impl EventProcessor for EventProcessorWithHumanOutput {
                 stdout,
                 stderr,
                 success,
+                ..
             }) => {
                 let patch_begin = self.call_id_to_patch.remove(&call_id);
 
@@ -431,6 +429,10 @@ impl EventProcessor for EventProcessorWithHumanOutput {
                     println!("{}", line.style(self.dimmed));
                 }
             }
+            EventMsg::TurnDiff(TurnDiffEvent { unified_diff }) => {
+                ts_println!(self, "{}", "turn diff:".style(self.magenta));
+                println!("{unified_diff}");
+            }
             EventMsg::ExecApprovalRequest(_) => {
                 // Should we exit?
             }

codex-rs/exec/src/event_processor_with_json_output.rs

@@ -46,10 +46,9 @@ impl EventProcessor for EventProcessorWithJsonOutput {
                 CodexStatus::Running
             }
             EventMsg::TaskComplete(TaskCompleteEvent { last_agent_message }) => {
-                handle_last_message(
-                    last_agent_message.as_deref(),
-                    self.last_message_path.as_deref(),
-                );
+                if let Some(output_file) = self.last_message_path.as_deref() {
+                    handle_last_message(last_agent_message.as_deref(), output_file);
+                }
                 CodexStatus::InitiateShutdown
             }
             EventMsg::ShutdownComplete => CodexStatus::Shutdown,

codex-rs/execpolicy/Cargo.toml

@@ -26,7 +26,7 @@ multimap = "0.10.0"
 path-absolutize = "3.1.1"
 regex-lite = "0.1"
 serde = { version = "1.0.194", features = ["derive"] }
-serde_json = "1.0.110"
+serde_json = "1.0.142"
 serde_with = { version = "3", features = ["macros"] }
 
 [dev-dependencies]

codex-rs/file-search/Cargo.toml

@@ -17,5 +17,5 @@ clap = { version = "4", features = ["derive"] }
 ignore = "0.4.23"
 nucleo-matcher = "0.3.1"
 serde = { version = "1", features = ["derive"] }
-serde_json = "1.0.110"
+serde_json = "1.0.142"
 tokio = { version = "1", features = ["full"] }

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

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

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

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

codex-rs/login/src/lib.rs

@@ -22,7 +22,7 @@ const SOURCE_FOR_PYTHON_SERVER: &str = include_str!("./login_with_chatgpt.py");
 const CLIENT_ID: &str = "app_EMoamEEZ73f0CkXaXp7hrann";
 pub const OPENAI_API_KEY_ENV_VAR: &str = "OPENAI_API_KEY";
 
-#[derive(Clone, Debug, PartialEq)]
+#[derive(Clone, Debug, PartialEq, Copy)]
 pub enum AuthMode {
     ApiKey,
     ChatGPT,

codex-rs/login/src/login_with_chatgpt.py

@@ -458,6 +458,7 @@ class _ApiKeyHTTPServer(http.server.HTTPServer):
             "code_challenge": self.pkce.code_challenge,
             "code_challenge_method": "S256",
             "id_token_add_organizations": "true",
+            "codex_cli_simplified_flow": "true",
             "state": self.state,
         }
         return f"{self.issuer}/oauth/authorize?" + urllib.parse.urlencode(params)
@@ -686,6 +687,7 @@ LOGIN_SUCCESS_HTML = """<!DOCTYPE html>
         justify-content: center;
         position: relative;
         background: white;
+
         font-family: system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, 'Open Sans', 'Helvetica Neue', sans-serif;
       }
       .inner-container {
@@ -703,6 +705,7 @@ LOGIN_SUCCESS_HTML = """<!DOCTYPE html>
         align-items: center;
         gap: 20px;
         display: flex;
+        margin-top: 15vh;
       }
       .svg-wrapper {
         position: relative;
@@ -710,9 +713,9 @@ LOGIN_SUCCESS_HTML = """<!DOCTYPE html>
       .title {
         text-align: center;
         color: var(--text-primary, #0D0D0D);
-        font-size: 28px;
+        font-size: 32px;
         font-weight: 400;
-        line-height: 36.40px;
+        line-height: 40px;
         word-wrap: break-word;
       }
       .setup-box {
@@ -785,16 +788,26 @@ LOGIN_SUCCESS_HTML = """<!DOCTYPE html>
         word-wrap: break-word;
         text-decoration: none;
       }
+      .logo {
+        display: flex;
+        align-items: center;
+        justify-content: center;
+        width: 4rem;
+        height: 4rem;
+        border-radius: 16px;
+        border: .5px solid rgba(0, 0, 0, 0.1);
+        box-shadow: rgba(0, 0, 0, 0.1) 0px 4px 16px 0px;
+        box-sizing: border-box;
+        background-color: rgb(255, 255, 255);
+      }
     </style>
   </head>
   <body>
     <div class="container">
       <div class="inner-container">
         <div class="content">
-          <div data-svg-wrapper class="svg-wrapper">
-            <svg width="56" height="56" viewBox="0 0 56 56" fill="none" xmlns="http://www.w3.org/2000/svg">
-              <path d="M4.6665 28.0003C4.6665 15.1137 15.1132 4.66699 27.9998 4.66699C40.8865 4.66699 51.3332 15.1137 51.3332 28.0003C51.3332 40.887 40.8865 51.3337 27.9998 51.3337C15.1132 51.3337 4.6665 40.887 4.6665 28.0003ZM37.5093 18.5088C36.4554 17.7672 34.9999 18.0203 34.2583 19.0742L24.8508 32.4427L20.9764 28.1808C20.1095 27.2272 18.6338 27.1569 17.6803 28.0238C16.7267 28.8906 16.6565 30.3664 17.5233 31.3199L23.3566 37.7366C23.833 38.2606 24.5216 38.5399 25.2284 38.4958C25.9353 38.4517 26.5838 38.089 26.9914 37.5098L38.0747 21.7598C38.8163 20.7059 38.5632 19.2504 37.5093 18.5088Z" fill="var(--green-400, #04B84C)"/>
-            </svg>
+          <div class="logo">
+            <svg xmlns="http://www.w3.org/2000/svg" width="32" height="32" fill="none" viewBox="0 0 32 32"><path stroke="#000" stroke-linecap="round" stroke-width="2.484" d="M22.356 19.797H17.17M9.662 12.29l1.979 3.576a.511.511 0 0 1-.005.504l-1.974 3.409M30.758 16c0 8.15-6.607 14.758-14.758 14.758-8.15 0-14.758-6.607-14.758-14.758C1.242 7.85 7.85 1.242 16 1.242c8.15 0 14.758 6.608 14.758 14.758Z"></path></svg>
           </div>
           <div class="title">Signed in to Codex CLI</div>
         </div>

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

@@ -258,10 +258,12 @@ async fn run_codex_tool_session_inner(
                     | EventMsg::McpToolCallBegin(_)
                     | EventMsg::McpToolCallEnd(_)
                     | EventMsg::ExecCommandBegin(_)
+                    | EventMsg::ExecCommandOutputDelta(_)
                     | EventMsg::ExecCommandEnd(_)
                     | EventMsg::BackgroundEvent(_)
                     | EventMsg::PatchApplyBegin(_)
                     | EventMsg::PatchApplyEnd(_)
+                    | EventMsg::TurnDiff(_)
                     | EventMsg::GetHistoryEntryResponse(_)
                     | EventMsg::PlanUpdate(_)
                     | EventMsg::ShutdownComplete => {

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

@@ -0,0 +1,122 @@
+use std::sync::Arc;
+
+use crate::exec_approval::handle_exec_approval_request;
+use crate::outgoing_message::OutgoingMessageSender;
+use crate::outgoing_message::OutgoingNotificationMeta;
+use crate::patch_approval::handle_patch_approval_request;
+use codex_core::Codex;
+use codex_core::protocol::AgentMessageEvent;
+use codex_core::protocol::ApplyPatchApprovalRequestEvent;
+use codex_core::protocol::EventMsg;
+use codex_core::protocol::ExecApprovalRequestEvent;
+use mcp_types::RequestId;
+use tracing::error;
+
+pub async fn run_conversation_loop(
+    codex: Arc<Codex>,
+    outgoing: Arc<OutgoingMessageSender>,
+    request_id: RequestId,
+) {
+    let request_id_str = match &request_id {
+        RequestId::String(s) => s.clone(),
+        RequestId::Integer(n) => n.to_string(),
+    };
+
+    // Stream events until the task needs to pause for user interaction or
+    // completes.
+    loop {
+        match codex.next_event().await {
+            Ok(event) => {
+                outgoing
+                    .send_event_as_notification(
+                        &event,
+                        Some(OutgoingNotificationMeta::new(Some(request_id.clone()))),
+                    )
+                    .await;
+
+                match event.msg {
+                    EventMsg::ExecApprovalRequest(ExecApprovalRequestEvent {
+                        command,
+                        cwd,
+                        call_id,
+                        reason: _,
+                    }) => {
+                        handle_exec_approval_request(
+                            command,
+                            cwd,
+                            outgoing.clone(),
+                            codex.clone(),
+                            request_id.clone(),
+                            request_id_str.clone(),
+                            event.id.clone(),
+                            call_id,
+                        )
+                        .await;
+                        continue;
+                    }
+                    EventMsg::Error(_) => {
+                        error!("Codex runtime error");
+                    }
+                    EventMsg::ApplyPatchApprovalRequest(ApplyPatchApprovalRequestEvent {
+                        call_id,
+                        reason,
+                        grant_root,
+                        changes,
+                    }) => {
+                        handle_patch_approval_request(
+                            call_id,
+                            reason,
+                            grant_root,
+                            changes,
+                            outgoing.clone(),
+                            codex.clone(),
+                            request_id.clone(),
+                            request_id_str.clone(),
+                            event.id.clone(),
+                        )
+                        .await;
+                        continue;
+                    }
+                    EventMsg::TaskComplete(_) => {}
+                    EventMsg::SessionConfigured(_) => {
+                        tracing::error!("unexpected SessionConfigured event");
+                    }
+                    EventMsg::AgentMessageDelta(_) => {
+                        // TODO: think how we want to support this in the MCP
+                    }
+                    EventMsg::AgentReasoningDelta(_) => {
+                        // TODO: think how we want to support this in the MCP
+                    }
+                    EventMsg::AgentMessage(AgentMessageEvent { .. }) => {
+                        // TODO: think how we want to support this in the MCP
+                    }
+                    EventMsg::TaskStarted
+                    | EventMsg::TokenCount(_)
+                    | EventMsg::AgentReasoning(_)
+                    | EventMsg::McpToolCallBegin(_)
+                    | EventMsg::McpToolCallEnd(_)
+                    | EventMsg::ExecCommandBegin(_)
+                    | EventMsg::ExecCommandEnd(_)
+                    | EventMsg::TurnDiff(_)
+                    | EventMsg::BackgroundEvent(_)
+                    | EventMsg::ExecCommandOutputDelta(_)
+                    | EventMsg::PatchApplyBegin(_)
+                    | EventMsg::PatchApplyEnd(_)
+                    | EventMsg::GetHistoryEntryResponse(_)
+                    | EventMsg::PlanUpdate(_)
+                    | EventMsg::ShutdownComplete => {
+                        // For now, we do not do anything extra for these
+                        // events. Note that
+                        // send(codex_event_to_notification(&event)) above has
+                        // already dispatched these events as notifications,
+                        // though we may want to do give different treatment to
+                        // individual events in the future.
+                    }
+                }
+            }
+            Err(e) => {
+                error!("Codex runtime error: {e}");
+            }
+        }
+    }
+}

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

@@ -18,7 +18,7 @@ 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)]
+#[derive(Debug, Deserialize, Serialize)]
 pub struct ExecApprovalElicitRequestParams {
     // These fields are required so that `params`
     // conforms to ElicitRequestParams.

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

@@ -17,6 +17,7 @@ use tracing_subscriber::EnvFilter;
 
 mod codex_tool_config;
 mod codex_tool_runner;
+mod conversation_loop;
 mod exec_approval;
 mod json_to_toml;
 pub mod mcp_protocol;

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

@@ -172,15 +172,22 @@ pub enum ToolCallResponseResult {
 }
 
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
-pub struct ConversationCreateResult {
-    pub conversation_id: ConversationId,
-    pub model: String,
+#[serde(untagged)]
+pub enum ConversationCreateResult {
+    Ok {
+        conversation_id: ConversationId,
+        model: String,
+    },
+    Error {
+        message: String,
+    },
 }
 
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
 pub struct ConversationStreamResult {}
 
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
+// TODO: remove this status because we have is_error field in the response.
 #[serde(tag = "status", rename_all = "camelCase")]
 pub enum ConversationSendMessageResult {
     Ok,
@@ -491,7 +498,7 @@ mod tests {
             request_id: RequestId::Integer(1),
             is_error: None,
             result: Some(ToolCallResponseResult::ConversationCreate(
-                ConversationCreateResult {
+                ConversationCreateResult::Ok {
                     conversation_id: ConversationId(uuid!("d0f6ecbe-84a2-41c1-b23d-b20473b25eab")),
                     model: "o3".into(),
                 },
@@ -515,6 +522,35 @@ mod tests {
         assert_eq!(req_id, RequestId::Integer(1));
     }
 
+    #[test]
+    fn response_error_conversation_create_full_schema() {
+        let env = ToolCallResponse {
+            request_id: RequestId::Integer(2),
+            is_error: Some(true),
+            result: Some(ToolCallResponseResult::ConversationCreate(
+                ConversationCreateResult::Error {
+                    message: "Failed to initialize session".into(),
+                },
+            )),
+        };
+        let req_id = env.request_id.clone();
+        let observed = to_val(&CallToolResult::from(env));
+        let expected = json!({
+            "content": [
+                { "type": "text", "text": "{\"message\":\"Failed to initialize session\"}" }
+            ],
+            "isError": true,
+            "structuredContent": {
+                "message": "Failed to initialize session"
+            }
+        });
+        assert_eq!(
+            observed, expected,
+            "error response (ConversationCreate) must match"
+        );
+        assert_eq!(req_id, RequestId::Integer(2));
+    }
+
     #[test]
     fn response_success_conversation_stream_empty_result_object() {
         let env = ToolCallResponse {

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

@@ -11,6 +11,7 @@ use crate::mcp_protocol::ToolCallRequestParams;
 use crate::mcp_protocol::ToolCallResponse;
 use crate::mcp_protocol::ToolCallResponseResult;
 use crate::outgoing_message::OutgoingMessageSender;
+use crate::tool_handlers::create_conversation::handle_create_conversation;
 use crate::tool_handlers::send_message::handle_send_message;
 
 use codex_core::Codex;
@@ -67,6 +68,10 @@ impl MessageProcessor {
         self.session_map.clone()
     }
 
+    pub(crate) fn outgoing(&self) -> Arc<OutgoingMessageSender> {
+        self.outgoing.clone()
+    }
+
     pub(crate) fn running_session_ids(&self) -> Arc<Mutex<HashSet<Uuid>>> {
         self.running_session_ids.clone()
     }
@@ -349,6 +354,9 @@ impl MessageProcessor {
     }
     async fn handle_new_tool_calls(&self, request_id: RequestId, params: ToolCallRequestParams) {
         match params {
+            ToolCallRequestParams::ConversationCreate(args) => {
+                handle_create_conversation(self, request_id, args).await;
+            }
             ToolCallRequestParams::ConversationSendMessage(args) => {
                 handle_send_message(self, request_id, args).await;
             }

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

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

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

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

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

@@ -89,14 +89,18 @@ async fn shell_command_approval_triggers_elicitation() -> anyhow::Result<()> {
     // 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 params = serde_json::from_value::<ExecApprovalElicitRequestParams>(
+        elicitation_request
+            .params
+            .clone()
+            .ok_or_else(|| anyhow::anyhow!("elicitation_request.params must be set"))?,
+    )?;
     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(),
+        params.codex_event_id.clone(),
     )?;
     assert_eq!(expected_elicitation_request, elicitation_request);
 

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

@@ -14,6 +14,7 @@ use assert_cmd::prelude::*;
 use codex_core::protocol::InputItem;
 use codex_mcp_server::CodexToolCallParam;
 use codex_mcp_server::CodexToolCallReplyParam;
+use codex_mcp_server::mcp_protocol::ConversationCreateArgs;
 use codex_mcp_server::mcp_protocol::ConversationId;
 use codex_mcp_server::mcp_protocol::ConversationSendMessageArgs;
 use codex_mcp_server::mcp_protocol::ToolCallRequestParams;
@@ -200,6 +201,41 @@ impl McpProcess {
         .await
     }
 
+    pub async fn send_conversation_create_tool_call(
+        &mut self,
+        prompt: &str,
+        model: &str,
+        cwd: &str,
+    ) -> anyhow::Result<i64> {
+        let params = ToolCallRequestParams::ConversationCreate(ConversationCreateArgs {
+            prompt: prompt.to_string(),
+            model: model.to_string(),
+            cwd: cwd.to_string(),
+            approval_policy: None,
+            sandbox: None,
+            config: None,
+            profile: None,
+            base_instructions: None,
+        });
+        self.send_request(
+            mcp_types::CallToolRequest::METHOD,
+            Some(serde_json::to_value(params)?),
+        )
+        .await
+    }
+
+    pub async fn send_conversation_create_with_args(
+        &mut self,
+        args: ConversationCreateArgs,
+    ) -> anyhow::Result<i64> {
+        let params = ToolCallRequestParams::ConversationCreate(args);
+        self.send_request(
+            mcp_types::CallToolRequest::METHOD,
+            Some(serde_json::to_value(params)?),
+        )
+        .await
+    }
+
     async fn send_request(
         &mut self,
         method: &str,

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

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

codex-rs/tui/Cargo.toml

@@ -11,12 +11,17 @@ path = "src/main.rs"
 name = "codex_tui"
 path = "src/lib.rs"
 
+[features]
+# Enable vt100-based tests (emulator) when running with `--features vt100-tests`.
+vt100-tests = []
+
 [lints]
 workspace = true
 
 [dependencies]
 anyhow = "1"
 base64 = "0.22.1"
+chrono = { version = "0.4", features = ["serde"] }
 clap = { version = "4", features = ["derive"] }
 codex-ansi-escape = { path = "../ansi-escape" }
 codex-arg0 = { path = "../arg0" }
@@ -41,10 +46,14 @@ ratatui = { version = "0.29.0", features = [
 ] }
 ratatui-image = "8.0.0"
 regex-lite = "0.1"
+reqwest = { version = "0.12", features = ["json"] }
+serde = { version = "1", features = ["derive"] }
 serde_json = { version = "1", features = ["preserve_order"] }
 shlex = "1.3.0"
 strum = "0.27.2"
 strum_macros = "0.27.2"
+supports-color = "3.0.2"
+textwrap = "0.16.2"
 tokio = { version = "1", features = [
     "io-std",
     "macros",
@@ -57,7 +66,6 @@ tracing-appender = "0.2.3"
 tracing-subscriber = { version = "0.3.19", features = ["env-filter"] }
 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"
@@ -67,3 +75,6 @@ uuid = "1"
 [dev-dependencies]
 insta = "1.43.1"
 pretty_assertions = "1"
+rand = "0.8"
+chrono = { version = "0.4", features = ["serde"] }
+vt100 = "0.16.2"

codex-rs/tui/src/app.rs

@@ -438,14 +438,15 @@ impl App<'_> {
             );
             self.pending_history_lines.clear();
         }
-        match &mut self.app_state {
+        terminal.draw(|frame| match &mut self.app_state {
             AppState::Chat { widget } => {
-                terminal.draw(|frame| frame.render_widget_ref(&**widget, frame.area()))?;
+                if let Some((x, y)) = widget.cursor_pos(frame.area()) {
+                    frame.set_cursor_position((x, y));
+                }
+                frame.render_widget_ref(&**widget, frame.area())
             }
-            AppState::GitWarning { screen } => {
-                terminal.draw(|frame| frame.render_widget_ref(&*screen, frame.area()))?;
-            }
-        }
+            AppState::GitWarning { screen } => frame.render_widget_ref(&*screen, frame.area()),
+        })?;
         Ok(())
     }
 

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

@@ -1,8 +1,5 @@
 use std::collections::HashMap;
 
-use tui_textarea::CursorMove;
-use tui_textarea::TextArea;
-
 use crate::app_event::AppEvent;
 use crate::app_event_sender::AppEventSender;
 use codex_core::protocol::Op;
@@ -67,59 +64,52 @@ impl ChatComposerHistory {
 
     /// Should Up/Down key presses be interpreted as history navigation given
     /// the current content and cursor position of `textarea`?
-    pub fn should_handle_navigation(&self, textarea: &TextArea) -> bool {
+    pub fn should_handle_navigation(&self, text: &str, cursor: usize) -> bool {
         if self.history_entry_count == 0 && self.local_history.is_empty() {
             return false;
         }
 
-        if textarea.is_empty() {
+        if text.is_empty() {
             return true;
         }
 
         // Textarea is not empty – only navigate when cursor is at start and
         // text matches last recalled history entry so regular editing is not
         // hijacked.
-        let (row, col) = textarea.cursor();
-        if row != 0 || col != 0 {
+        if cursor != 0 {
             return false;
         }
 
-        let lines = textarea.lines();
-        matches!(&self.last_history_text, Some(prev) if prev == &lines.join("\n"))
+        matches!(&self.last_history_text, Some(prev) if prev == text)
     }
 
     /// Handle <Up>. Returns true when the key was consumed and the caller
     /// should request a redraw.
-    pub fn navigate_up(&mut self, textarea: &mut TextArea, app_event_tx: &AppEventSender) -> bool {
+    pub fn navigate_up(&mut self, app_event_tx: &AppEventSender) -> Option<String> {
         let total_entries = self.history_entry_count + self.local_history.len();
         if total_entries == 0 {
-            return false;
+            return None;
         }
 
         let next_idx = match self.history_cursor {
             None => (total_entries as isize) - 1,
-            Some(0) => return true, // already at oldest
+            Some(0) => return None, // already at oldest
             Some(idx) => idx - 1,
         };
 
         self.history_cursor = Some(next_idx);
-        self.populate_history_at_index(next_idx as usize, textarea, app_event_tx);
-        true
+        self.populate_history_at_index(next_idx as usize, app_event_tx)
     }
 
     /// Handle <Down>.
-    pub fn navigate_down(
-        &mut self,
-        textarea: &mut TextArea,
-        app_event_tx: &AppEventSender,
-    ) -> bool {
+    pub fn navigate_down(&mut self, app_event_tx: &AppEventSender) -> Option<String> {
         let total_entries = self.history_entry_count + self.local_history.len();
         if total_entries == 0 {
-            return false;
+            return None;
         }
 
         let next_idx_opt = match self.history_cursor {
-            None => return false, // not browsing
+            None => return None, // not browsing
             Some(idx) if (idx as usize) + 1 >= total_entries => None,
             Some(idx) => Some(idx + 1),
         };
@@ -127,16 +117,15 @@ impl ChatComposerHistory {
         match next_idx_opt {
             Some(idx) => {
                 self.history_cursor = Some(idx);
-                self.populate_history_at_index(idx as usize, textarea, app_event_tx);
+                self.populate_history_at_index(idx as usize, app_event_tx)
             }
             None => {
                 // Past newest – clear and exit browsing mode.
                 self.history_cursor = None;
                 self.last_history_text = None;
-                self.replace_textarea_content(textarea, "");
+                Some(String::new())
             }
         }
-        true
     }
 
     /// Integrate a GetHistoryEntryResponse event.
@@ -145,19 +134,18 @@ impl ChatComposerHistory {
         log_id: u64,
         offset: usize,
         entry: Option<String>,
-        textarea: &mut TextArea,
-    ) -> bool {
+    ) -> Option<String> {
         if self.history_log_id != Some(log_id) {
-            return false;
+            return None;
         }
-        let Some(text) = entry else { return false };
+        let text = entry?;
         self.fetched_history.insert(offset, text.clone());
 
         if self.history_cursor == Some(offset as isize) {
-            self.replace_textarea_content(textarea, &text);
-            return true;
+            self.last_history_text = Some(text.clone());
+            return Some(text);
         }
-        false
+        None
     }
 
     // ---------------------------------------------------------------------
@@ -167,21 +155,20 @@ impl ChatComposerHistory {
     fn populate_history_at_index(
         &mut self,
         global_idx: usize,
-        textarea: &mut TextArea,
         app_event_tx: &AppEventSender,
-    ) {
+    ) -> Option<String> {
         if global_idx >= self.history_entry_count {
             // Local entry.
             if let Some(text) = self
                 .local_history
                 .get(global_idx - self.history_entry_count)
             {
-                let t = text.clone();
-                self.replace_textarea_content(textarea, &t);
+                self.last_history_text = Some(text.clone());
+                return Some(text.clone());
             }
         } else if let Some(text) = self.fetched_history.get(&global_idx) {
-            let t = text.clone();
-            self.replace_textarea_content(textarea, &t);
+            self.last_history_text = Some(text.clone());
+            return Some(text.clone());
         } else if let Some(log_id) = self.history_log_id {
             let op = Op::GetHistoryEntryRequest {
                 offset: global_idx,
@@ -189,14 +176,7 @@ impl ChatComposerHistory {
             };
             app_event_tx.send(AppEvent::CodexOp(op));
         }
-    }
-
-    fn replace_textarea_content(&mut self, textarea: &mut TextArea, text: &str) {
-        textarea.select_all();
-        textarea.cut();
-        let _ = textarea.insert_str(text);
-        textarea.move_cursor(CursorMove::Jump(0, 0));
-        self.last_history_text = Some(text.to_string());
+        None
     }
 }
 
@@ -217,11 +197,9 @@ mod tests {
         // Pretend there are 3 persistent entries.
         history.set_metadata(1, 3);
 
-        let mut textarea = TextArea::default();
-
         // First Up should request offset 2 (latest) and await async data.
-        assert!(history.should_handle_navigation(&textarea));
-        assert!(history.navigate_up(&mut textarea, &tx));
+        assert!(history.should_handle_navigation("", 0));
+        assert!(history.navigate_up(&tx).is_none()); // don't replace the text yet
 
         // Verify that an AppEvent::CodexOp with the correct GetHistoryEntryRequest was sent.
         let event = rx.try_recv().expect("expected AppEvent to be sent");
@@ -235,14 +213,15 @@ mod tests {
             },
             history_request1
         );
-        assert_eq!(textarea.lines().join("\n"), ""); // still empty
 
         // Inject the async response.
-        assert!(history.on_entry_response(1, 2, Some("latest".into()), &mut textarea));
-        assert_eq!(textarea.lines().join("\n"), "latest");
+        assert_eq!(
+            Some("latest".into()),
+            history.on_entry_response(1, 2, Some("latest".into()))
+        );
 
         // Next Up should move to offset 1.
-        assert!(history.navigate_up(&mut textarea, &tx));
+        assert!(history.navigate_up(&tx).is_none()); // don't replace the text yet
 
         // Verify second CodexOp event for offset 1.
         let event2 = rx.try_recv().expect("expected second event");
@@ -257,7 +236,9 @@ mod tests {
             history_request_2
         );
 
-        history.on_entry_response(1, 1, Some("older".into()), &mut textarea);
-        assert_eq!(textarea.lines().join("\n"), "older");
+        assert_eq!(
+            Some("older".into()),
+            history.on_entry_response(1, 1, Some("older".into()))
+        );
     }
 }

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

@@ -25,8 +25,6 @@ pub(crate) struct CommandPopup {
     command_filter: String,
     all_commands: Vec<(&'static str, SlashCommand)>,
     selected_idx: Option<usize>,
-    // Index of the first visible row in the filtered list.
-    scroll_top: usize,
 }
 
 impl CommandPopup {
@@ -35,7 +33,6 @@ impl CommandPopup {
             command_filter: String::new(),
             all_commands: built_in_slash_commands(),
             selected_idx: None,
-            scroll_top: 0,
         }
     }
 
@@ -69,28 +66,26 @@ impl CommandPopup {
             0 => None,
             _ => Some(self.selected_idx.unwrap_or(0).min(matches_len - 1)),
         };
-
-        self.adjust_scroll(matches_len);
     }
 
     /// Determine the preferred height of the popup. This is the number of
-    /// rows required to show at most MAX_POPUP_ROWS commands.
+    /// rows required to show **at most** `MAX_POPUP_ROWS` commands plus the
+    /// table/border overhead (one line at the top and one at the bottom).
     pub(crate) fn calculate_required_height(&self) -> u16 {
         self.filtered_commands().len().clamp(1, MAX_POPUP_ROWS) as u16
     }
 
     /// Return the list of commands that match the current filter. Matching is
-    /// performed using a case-insensitive prefix comparison on the command name.
+    /// performed using a *prefix* comparison on the command name.
     fn filtered_commands(&self) -> Vec<&SlashCommand> {
-        let filter = self.command_filter.as_str();
         self.all_commands
             .iter()
             .filter_map(|(_name, cmd)| {
-                if filter.is_empty() {
-                    return Some(cmd);
-                }
-                let name = cmd.command();
-                if name.len() >= filter.len() && name[..filter.len()].eq_ignore_ascii_case(filter) {
+                if self.command_filter.is_empty()
+                    || cmd
+                        .command()
+                        .starts_with(&self.command_filter.to_ascii_lowercase())
+                {
                     Some(cmd)
                 } else {
                     None
@@ -101,30 +96,26 @@ impl CommandPopup {
 
     /// Move the selection cursor one step up.
     pub(crate) fn move_up(&mut self) {
-        let matches = self.filtered_commands();
-        let len = matches.len();
-        if len == 0 {
-            self.selected_idx = None;
-            self.scroll_top = 0;
-            return;
+        if let Some(len) = self.filtered_commands().len().checked_sub(1) {
+            if len == usize::MAX {
+                return;
+            }
         }
 
-        match self.selected_idx {
-            Some(idx) if idx > 0 => self.selected_idx = Some(idx - 1),
-            Some(_) => self.selected_idx = Some(len - 1), // wrap to last
-            None => self.selected_idx = Some(0),
+        if let Some(idx) = self.selected_idx {
+            if idx > 0 {
+                self.selected_idx = Some(idx - 1);
+            }
+        } else if !self.filtered_commands().is_empty() {
+            self.selected_idx = Some(0);
         }
-
-        self.adjust_scroll(len);
     }
 
     /// Move the selection cursor one step down.
     pub(crate) fn move_down(&mut self) {
-        let matches = self.filtered_commands();
-        let matches_len = matches.len();
+        let matches_len = self.filtered_commands().len();
         if matches_len == 0 {
             self.selected_idx = None;
-            self.scroll_top = 0;
             return;
         }
 
@@ -132,15 +123,11 @@ impl CommandPopup {
             Some(idx) if idx + 1 < matches_len => {
                 self.selected_idx = Some(idx + 1);
             }
-            Some(_idx_last) => {
-                self.selected_idx = Some(0);
-            }
             None => {
                 self.selected_idx = Some(0);
             }
+            _ => {}
         }
-
-        self.adjust_scroll(matches_len);
     }
 
     /// Return currently selected command, if any.
@@ -148,26 +135,6 @@ impl CommandPopup {
         let matches = self.filtered_commands();
         self.selected_idx.and_then(|idx| matches.get(idx).copied())
     }
-
-    fn adjust_scroll(&mut self, matches_len: usize) {
-        if matches_len == 0 {
-            self.scroll_top = 0;
-            return;
-        }
-        let visible_rows = MAX_POPUP_ROWS.min(matches_len);
-        if let Some(sel) = self.selected_idx {
-            if sel < self.scroll_top {
-                self.scroll_top = sel;
-            } else {
-                let bottom = self.scroll_top + visible_rows - 1;
-                if sel > bottom {
-                    self.scroll_top = sel + 1 - visible_rows;
-                }
-            }
-        } else {
-            self.scroll_top = 0;
-        }
-    }
 }
 
 impl WidgetRef for CommandPopup {
@@ -175,8 +142,10 @@ impl WidgetRef for CommandPopup {
         let matches = self.filtered_commands();
 
         let mut rows: Vec<Row> = Vec::new();
+        let visible_matches: Vec<&SlashCommand> =
+            matches.into_iter().take(MAX_POPUP_ROWS).collect();
 
-        if matches.is_empty() {
+        if visible_matches.is_empty() {
             rows.push(Row::new(vec![
                 Cell::from(""),
                 Cell::from("No matching commands").add_modifier(Modifier::ITALIC),
@@ -184,32 +153,10 @@ impl WidgetRef for CommandPopup {
         } else {
             let default_style = Style::default();
             let command_style = Style::default().fg(Color::LightBlue);
-            let max_rows_from_area = area.height as usize;
-            let visible_rows = MAX_POPUP_ROWS
-                .min(matches.len())
-                .min(max_rows_from_area.max(1));
-
-            let mut start_idx = self.scroll_top.min(matches.len().saturating_sub(1));
-            if let Some(sel) = self.selected_idx {
-                if sel < start_idx {
-                    start_idx = sel;
-                } else if visible_rows > 0 {
-                    let bottom = start_idx + visible_rows - 1;
-                    if sel > bottom {
-                        start_idx = sel + 1 - visible_rows;
-                    }
-                }
-            }
-
-            for (global_idx, cmd) in matches
-                .iter()
-                .enumerate()
-                .skip(start_idx)
-                .take(visible_rows)
-            {
+            for (idx, cmd) in visible_matches.iter().enumerate() {
                 rows.push(Row::new(vec![
                     Cell::from(Line::from(vec![
-                        if Some(global_idx) == self.selected_idx {
+                        if Some(idx) == self.selected_idx {
                             Span::styled(
                                 "›",
                                 Style::default().bg(Color::DarkGray).fg(Color::LightCyan),
@@ -241,67 +188,3 @@ impl WidgetRef for CommandPopup {
         table.render(area, buf);
     }
 }
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use ratatui::buffer::Buffer;
-    use ratatui::layout::Rect;
-
-    #[test]
-    fn move_down_wraps_to_top() {
-        let mut popup = CommandPopup::new();
-        // Show all commands by simulating composer input starting with '/'.
-        popup.on_composer_text_change("/".to_string());
-        let len = popup.filtered_commands().len();
-        assert!(len > 0);
-
-        // Move to last item.
-        for _ in 0..len.saturating_sub(1) {
-            popup.move_down();
-        }
-        // Next move_down should wrap to index 0.
-        popup.move_down();
-        assert_eq!(popup.selected_idx, Some(0));
-    }
-
-    #[test]
-    fn move_up_wraps_to_bottom() {
-        let mut popup = CommandPopup::new();
-        popup.on_composer_text_change("/".to_string());
-        let len = popup.filtered_commands().len();
-        assert!(len > 0);
-
-        // Initial selection is 0; moving up should wrap to last.
-        popup.move_up();
-        assert_eq!(popup.selected_idx, Some(len - 1));
-    }
-
-    #[test]
-    fn respects_tiny_terminal_height_when_rendering() {
-        let mut popup = CommandPopup::new();
-        popup.on_composer_text_change("/".to_string());
-        assert!(popup.filtered_commands().len() >= 3);
-
-        let area = Rect::new(0, 0, 50, 2);
-        let mut buf = Buffer::empty(area);
-        popup.render(area, &mut buf);
-
-        let mut non_empty_rows = 0u16;
-        for y in 0..area.height {
-            let mut row_has_content = false;
-            for x in 0..area.width {
-                let c = buf[(x, y)].symbol();
-                if !c.trim().is_empty() {
-                    row_has_content = true;
-                    break;
-                }
-            }
-            if row_has_content {
-                non_empty_rows += 1;
-            }
-        }
-
-        assert_eq!(non_empty_rows, 2);
-    }
-}

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

@@ -108,6 +108,7 @@ impl FileSearchPopup {
             .map(|file_match| file_match.path.as_str())
     }
 
+    /// Preferred height (rows) including border.
     pub(crate) fn calculate_required_height(&self) -> u16 {
         // Row count depends on whether we already have matches. If no matches
         // yet (e.g. initial search or query with no results) reserve a single

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

@@ -0,0 +1,45 @@
+use ratatui::buffer::Buffer;
+use ratatui::layout::Rect;
+use ratatui::text::Line;
+use ratatui::widgets::Paragraph;
+use ratatui::widgets::WidgetRef;
+
+/// Minimal rendering-only widget for the transient ring rows.
+pub(crate) struct LiveRingWidget {
+    max_rows: u16,
+    rows: Vec<Line<'static>>, // newest at the end
+}
+
+impl LiveRingWidget {
+    pub fn new() -> Self {
+        Self {
+            max_rows: 3,
+            rows: Vec::new(),
+        }
+    }
+
+    pub fn set_max_rows(&mut self, n: u16) {
+        self.max_rows = n.max(1);
+    }
+
+    pub fn set_rows(&mut self, rows: Vec<Line<'static>>) {
+        self.rows = rows;
+    }
+
+    pub fn desired_height(&self, _width: u16) -> u16 {
+        let len = self.rows.len() as u16;
+        len.min(self.max_rows)
+    }
+}
+
+impl WidgetRef for LiveRingWidget {
+    fn render_ref(&self, area: Rect, buf: &mut Buffer) {
+        if area.height == 0 {
+            return;
+        }
+        let visible = self.rows.len().saturating_sub(self.max_rows as usize);
+        let slice = &self.rows[visible..];
+        let para = Paragraph::new(slice.to_vec());
+        para.render_ref(area, buf);
+    }
+}

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

@@ -4,12 +4,12 @@ use crate::app_event::AppEvent;
 use crate::app_event_sender::AppEventSender;
 use crate::user_approval_widget::ApprovalRequest;
 use bottom_pane_view::BottomPaneView;
-use bottom_pane_view::ConditionalUpdate;
 use codex_core::protocol::TokenUsage;
 use codex_file_search::FileMatch;
 use crossterm::event::KeyEvent;
 use ratatui::buffer::Buffer;
 use ratatui::layout::Rect;
+use ratatui::text::Line;
 use ratatui::widgets::WidgetRef;
 
 mod approval_modal_view;
@@ -18,7 +18,9 @@ mod chat_composer;
 mod chat_composer_history;
 mod command_popup;
 mod file_search_popup;
+mod live_ring_widget;
 mod status_indicator_view;
+mod textarea;
 
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
 pub(crate) enum CancellationEvent {
@@ -29,6 +31,7 @@ pub(crate) enum CancellationEvent {
 pub(crate) use chat_composer::ChatComposer;
 pub(crate) use chat_composer::InputResult;
 
+use crate::status_indicator_widget::StatusIndicatorWidget;
 use approval_modal_view::ApprovalModalView;
 use status_indicator_view::StatusIndicatorView;
 
@@ -36,7 +39,7 @@ use status_indicator_view::StatusIndicatorView;
 pub(crate) struct BottomPane<'a> {
     /// Composer is retained even when a BottomPaneView is displayed so the
     /// input state is retained when the view is closed.
-    composer: ChatComposer<'a>,
+    composer: ChatComposer,
 
     /// If present, this is displayed instead of the `composer`.
     active_view: Option<Box<dyn BottomPaneView<'a> + 'a>>,
@@ -45,6 +48,19 @@ pub(crate) struct BottomPane<'a> {
     has_input_focus: bool,
     is_task_running: bool,
     ctrl_c_quit_hint: bool,
+
+    /// Optional live, multi‑line status/"live cell" rendered directly above
+    /// the composer while a task is running. Unlike `active_view`, this does
+    /// not replace the composer; it augments it.
+    live_status: Option<StatusIndicatorWidget>,
+
+    /// Optional transient ring shown above the composer. This is a rendering-only
+    /// container used during development before we wire it to ChatWidget events.
+    live_ring: Option<live_ring_widget::LiveRingWidget>,
+
+    /// True if the active view is the StatusIndicatorView that replaces the
+    /// composer during a running task.
+    status_view_active: bool,
 }
 
 pub(crate) struct BottomPaneParams {
@@ -54,6 +70,7 @@ pub(crate) struct BottomPaneParams {
 }
 
 impl BottomPane<'_> {
+    const BOTTOM_PAD_LINES: u16 = 2;
     pub fn new(params: BottomPaneParams) -> Self {
         let enhanced_keys_supported = params.enhanced_keys_supported;
         Self {
@@ -67,14 +84,52 @@ impl BottomPane<'_> {
             has_input_focus: params.has_input_focus,
             is_task_running: false,
             ctrl_c_quit_hint: false,
+            live_status: None,
+            live_ring: None,
+            status_view_active: false,
         }
     }
 
     pub fn desired_height(&self, width: u16) -> u16 {
-        self.active_view
+        let overlay_status_h = self
+            .live_status
             .as_ref()
-            .map(|v| v.desired_height(width))
-            .unwrap_or(self.composer.desired_height())
+            .map(|s| s.desired_height(width))
+            .unwrap_or(0);
+        let ring_h = self
+            .live_ring
+            .as_ref()
+            .map(|r| r.desired_height(width))
+            .unwrap_or(0);
+
+        let view_height = if let Some(view) = self.active_view.as_ref() {
+            // Add a single blank spacer line between live ring and status view when active.
+            let spacer = if self.live_ring.is_some() && self.status_view_active {
+                1
+            } else {
+                0
+            };
+            spacer + view.desired_height(width)
+        } else {
+            self.composer.desired_height(width)
+        };
+
+        overlay_status_h
+            .saturating_add(ring_h)
+            .saturating_add(view_height)
+            .saturating_add(Self::BOTTOM_PAD_LINES)
+    }
+
+    pub fn cursor_pos(&self, area: Rect) -> Option<(u16, u16)> {
+        // Hide the cursor whenever an overlay view is active (e.g. the
+        // status indicator shown while a task is running, or approval modal).
+        // In these states the textarea is not interactable, so we should not
+        // show its caret.
+        if self.active_view.is_some() {
+            None
+        } else {
+            self.composer.cursor_pos(area)
+        }
     }
 
     /// Forward a key event to the active view or the composer.
@@ -83,10 +138,6 @@ impl BottomPane<'_> {
             view.handle_key_event(self, key_event);
             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.request_redraw();
             InputResult::None
@@ -112,10 +163,6 @@ impl BottomPane<'_> {
             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();
             }
@@ -135,19 +182,37 @@ impl BottomPane<'_> {
         }
     }
 
-    /// Update the status indicator text (only when the `StatusIndicatorView` is
-    /// active).
+    /// Update the status indicator text. Prefer replacing the composer with
+    /// the StatusIndicatorView so the input pane shows a single-line status
+    /// like: `▌ Working waiting for model`.
     pub(crate) fn update_status_text(&mut self, text: String) {
-        if let Some(view) = &mut self.active_view {
-            match view.update_status_text(text) {
-                ConditionalUpdate::NeedsRedraw => {
-                    self.request_redraw();
-                }
-                ConditionalUpdate::NoRedraw => {
-                    // No redraw needed.
-                }
+        let mut handled_by_view = false;
+        if let Some(view) = self.active_view.as_mut() {
+            if matches!(
+                view.update_status_text(text.clone()),
+                bottom_pane_view::ConditionalUpdate::NeedsRedraw
+            ) {
+                handled_by_view = true;
+            }
+        } else {
+            let mut v = StatusIndicatorView::new(self.app_event_tx.clone());
+            v.update_text(text.clone());
+            self.active_view = Some(Box::new(v));
+            self.status_view_active = true;
+            handled_by_view = true;
+        }
+
+        // Fallback: if the current active view did not consume status updates,
+        // present an overlay above the composer.
+        if !handled_by_view {
+            if self.live_status.is_none() {
+                self.live_status = Some(StatusIndicatorWidget::new(self.app_event_tx.clone()));
+            }
+            if let Some(status) = &mut self.live_status {
+                status.update_text(text);
             }
         }
+        self.request_redraw();
     }
 
     pub(crate) fn show_ctrl_c_quit_hint(&mut self) {
@@ -173,27 +238,23 @@ impl BottomPane<'_> {
     pub fn set_task_running(&mut self, running: bool) {
         self.is_task_running = running;
 
-        match (running, self.active_view.is_some()) {
-            (true, false) => {
-                // Show status indicator overlay.
+        if running {
+            if self.active_view.is_none() {
                 self.active_view = Some(Box::new(StatusIndicatorView::new(
                     self.app_event_tx.clone(),
                 )));
-                self.request_redraw();
+                self.status_view_active = true;
             }
-            (false, true) => {
-                if let Some(mut view) = self.active_view.take() {
-                    if view.should_hide_when_task_is_done() {
-                        // Leave self.active_view as None.
-                        self.request_redraw();
-                    } else {
-                        // Preserve the view.
-                        self.active_view = Some(view);
-                    }
+            self.request_redraw();
+        } else {
+            self.live_status = None;
+            // Drop the status view when a task completes, but keep other
+            // modal views (e.g. approval dialogs).
+            if let Some(mut view) = self.active_view.take() {
+                if !view.should_hide_when_task_is_done() {
+                    self.active_view = Some(view);
                 }
-            }
-            _ => {
-                // No change.
+                self.status_view_active = false;
             }
         }
     }
@@ -235,6 +296,7 @@ impl BottomPane<'_> {
         // Otherwise create a new approval modal overlay.
         let modal = ApprovalModalView::new(request, self.app_event_tx.clone());
         self.active_view = Some(Box::new(modal));
+        self.status_view_active = false;
         self.request_redraw()
     }
 
@@ -268,15 +330,80 @@ impl BottomPane<'_> {
         self.composer.on_file_search_result(query, matches);
         self.request_redraw();
     }
+
+    /// Set the rows and cap for the transient live ring overlay.
+    pub(crate) fn set_live_ring_rows(&mut self, max_rows: u16, rows: Vec<Line<'static>>) {
+        let mut w = live_ring_widget::LiveRingWidget::new();
+        w.set_max_rows(max_rows);
+        w.set_rows(rows);
+        self.live_ring = Some(w);
+    }
+
+    pub(crate) fn clear_live_ring(&mut self) {
+        self.live_ring = None;
+    }
+
+    // Removed restart_live_status_with_text – no longer used by the current streaming UI.
 }
 
 impl WidgetRef for &BottomPane<'_> {
     fn render_ref(&self, area: Rect, buf: &mut Buffer) {
-        // Show BottomPaneView if present.
-        if let Some(ov) = &self.active_view {
-            ov.render(area, buf);
-        } else {
-            (&self.composer).render_ref(area, buf);
+        let mut y_offset = 0u16;
+        if let Some(ring) = &self.live_ring {
+            let live_h = ring.desired_height(area.width).min(area.height);
+            if live_h > 0 {
+                let live_rect = Rect {
+                    x: area.x,
+                    y: area.y,
+                    width: area.width,
+                    height: live_h,
+                };
+                ring.render_ref(live_rect, buf);
+                y_offset = live_h;
+            }
+        }
+        // Spacer between live ring and status view when active
+        if self.live_ring.is_some() && self.status_view_active && y_offset < area.height {
+            // Leave one empty line
+            y_offset = y_offset.saturating_add(1);
+        }
+        if let Some(status) = &self.live_status {
+            let live_h = status.desired_height(area.width).min(area.height);
+            if live_h > 0 {
+                let live_rect = Rect {
+                    x: area.x,
+                    y: area.y,
+                    width: area.width,
+                    height: live_h,
+                };
+                status.render_ref(live_rect, buf);
+                y_offset = live_h;
+            }
+        }
+
+        if let Some(view) = &self.active_view {
+            if y_offset < area.height {
+                // Reserve bottom padding lines; keep at least 1 line for the view.
+                let avail = area.height - y_offset;
+                let pad = BottomPane::BOTTOM_PAD_LINES.min(avail.saturating_sub(1));
+                let view_rect = Rect {
+                    x: area.x,
+                    y: area.y + y_offset,
+                    width: area.width,
+                    height: avail - pad,
+                };
+                view.render(view_rect, buf);
+            }
+        } else if y_offset < area.height {
+            let composer_rect = Rect {
+                x: area.x,
+                y: area.y + y_offset,
+                width: area.width,
+                // Reserve bottom padding
+                height: (area.height - y_offset)
+                    - BottomPane::BOTTOM_PAD_LINES.min((area.height - y_offset).saturating_sub(1)),
+            };
+            (&self.composer).render_ref(composer_rect, buf);
         }
     }
 }
@@ -285,6 +412,9 @@ impl WidgetRef for &BottomPane<'_> {
 mod tests {
     use super::*;
     use crate::app_event::AppEvent;
+    use ratatui::buffer::Buffer;
+    use ratatui::layout::Rect;
+    use ratatui::text::Line;
     use std::path::PathBuf;
     use std::sync::mpsc::channel;
 
@@ -311,4 +441,200 @@ mod tests {
         assert!(pane.ctrl_c_quit_hint_visible());
         assert_eq!(CancellationEvent::Ignored, pane.on_ctrl_c());
     }
+
+    #[test]
+    fn live_ring_renders_above_composer() {
+        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,
+            enhanced_keys_supported: false,
+        });
+
+        // Provide 4 rows with max_rows=3; only the last 3 should be visible.
+        pane.set_live_ring_rows(
+            3,
+            vec![
+                Line::from("one".to_string()),
+                Line::from("two".to_string()),
+                Line::from("three".to_string()),
+                Line::from("four".to_string()),
+            ],
+        );
+
+        let area = Rect::new(0, 0, 10, 5);
+        let mut buf = Buffer::empty(area);
+        (&pane).render_ref(area, &mut buf);
+
+        // Extract the first 3 rows and assert they contain the last three lines.
+        let mut lines: Vec<String> = Vec::new();
+        for y in 0..3 {
+            let mut s = String::new();
+            for x in 0..area.width {
+                s.push(buf[(x, y)].symbol().chars().next().unwrap_or(' '));
+            }
+            lines.push(s.trim_end().to_string());
+        }
+        assert_eq!(lines, vec!["two", "three", "four"]);
+    }
+
+    #[test]
+    fn status_indicator_visible_with_live_ring() {
+        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,
+            enhanced_keys_supported: false,
+        });
+
+        // Simulate task running which replaces composer with the status indicator.
+        pane.set_task_running(true);
+        pane.update_status_text("waiting for model".to_string());
+
+        // Provide 2 rows in the live ring (e.g., streaming CoT) and ensure the
+        // status indicator remains visible below them.
+        pane.set_live_ring_rows(
+            2,
+            vec![
+                Line::from("cot1".to_string()),
+                Line::from("cot2".to_string()),
+            ],
+        );
+
+        // Allow some frames so the dot animation is present.
+        std::thread::sleep(std::time::Duration::from_millis(120));
+
+        // Height should include both ring rows, 1 spacer, and the 1-line status.
+        let area = Rect::new(0, 0, 30, 4);
+        let mut buf = Buffer::empty(area);
+        (&pane).render_ref(area, &mut buf);
+
+        // Top two rows are the live ring.
+        let mut r0 = String::new();
+        let mut r1 = String::new();
+        for x in 0..area.width {
+            r0.push(buf[(x, 0)].symbol().chars().next().unwrap_or(' '));
+            r1.push(buf[(x, 1)].symbol().chars().next().unwrap_or(' '));
+        }
+        assert!(r0.contains("cot1"), "expected first live row: {r0:?}");
+        assert!(r1.contains("cot2"), "expected second live row: {r1:?}");
+
+        // Row 2 is the spacer (blank)
+        let mut r2 = String::new();
+        for x in 0..area.width {
+            r2.push(buf[(x, 2)].symbol().chars().next().unwrap_or(' '));
+        }
+        assert!(r2.trim().is_empty(), "expected blank spacer line: {r2:?}");
+
+        // Bottom row is the status line; it should contain the left bar and "Working".
+        let mut r3 = String::new();
+        for x in 0..area.width {
+            r3.push(buf[(x, 3)].symbol().chars().next().unwrap_or(' '));
+        }
+        assert_eq!(buf[(0, 3)].symbol().chars().next().unwrap_or(' '), '▌');
+        assert!(
+            r3.contains("Working"),
+            "expected Working header in status line: {r3:?}"
+        );
+    }
+
+    #[test]
+    fn bottom_padding_present_for_status_view() {
+        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,
+            enhanced_keys_supported: false,
+        });
+
+        // Activate spinner (status view replaces composer) with no live ring.
+        pane.set_task_running(true);
+        pane.update_status_text("waiting for model".to_string());
+
+        // Use height == desired_height; expect 1 status row at top and 2 bottom padding rows.
+        let height = pane.desired_height(30);
+        assert!(
+            height >= 3,
+            "expected at least 3 rows with bottom padding; got {height}"
+        );
+        let area = Rect::new(0, 0, 30, height);
+        let mut buf = Buffer::empty(area);
+        (&pane).render_ref(area, &mut buf);
+
+        // Top row contains the status header
+        let mut top = String::new();
+        for x in 0..area.width {
+            top.push(buf[(x, 0)].symbol().chars().next().unwrap_or(' '));
+        }
+        assert_eq!(buf[(0, 0)].symbol().chars().next().unwrap_or(' '), '▌');
+        assert!(
+            top.contains("Working"),
+            "expected Working header on top row: {top:?}"
+        );
+
+        // Bottom two rows are blank padding
+        let mut r_last = String::new();
+        let mut r_last2 = String::new();
+        for x in 0..area.width {
+            r_last.push(buf[(x, height - 1)].symbol().chars().next().unwrap_or(' '));
+            r_last2.push(buf[(x, height - 2)].symbol().chars().next().unwrap_or(' '));
+        }
+        assert!(
+            r_last.trim().is_empty(),
+            "expected last row blank: {r_last:?}"
+        );
+        assert!(
+            r_last2.trim().is_empty(),
+            "expected second-to-last row blank: {r_last2:?}"
+        );
+    }
+
+    #[test]
+    fn bottom_padding_shrinks_when_tiny() {
+        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,
+            enhanced_keys_supported: false,
+        });
+
+        pane.set_task_running(true);
+        pane.update_status_text("waiting for model".to_string());
+
+        // Height=2 → pad shrinks to 1; bottom row is blank, top row has spinner.
+        let area2 = Rect::new(0, 0, 20, 2);
+        let mut buf2 = Buffer::empty(area2);
+        (&pane).render_ref(area2, &mut buf2);
+        let mut row0 = String::new();
+        let mut row1 = String::new();
+        for x in 0..area2.width {
+            row0.push(buf2[(x, 0)].symbol().chars().next().unwrap_or(' '));
+            row1.push(buf2[(x, 1)].symbol().chars().next().unwrap_or(' '));
+        }
+        assert!(
+            row0.contains("Working"),
+            "expected Working header on row 0: {row0:?}"
+        );
+        assert!(
+            row1.trim().is_empty(),
+            "expected bottom padding on row 1: {row1:?}"
+        );
+
+        // Height=1 → no padding; single row is the spinner.
+        let area1 = Rect::new(0, 0, 20, 1);
+        let mut buf1 = Buffer::empty(area1);
+        (&pane).render_ref(area1, &mut buf1);
+        let mut only = String::new();
+        for x in 0..area1.width {
+            only.push(buf1[(x, 0)].symbol().chars().next().unwrap_or(' '));
+        }
+        assert!(
+            only.contains("Working"),
+            "expected Working header with no padding: {only:?}"
+        );
+    }
 }

codex-rs/tui/src/chatwidget.rs

@@ -1,7 +1,6 @@
 use std::collections::HashMap;
 use std::path::PathBuf;
 use std::sync::Arc;
-use std::time::Duration;
 
 use codex_core::codex_wrapper::CodexConversation;
 use codex_core::codex_wrapper::init_codex;
@@ -43,8 +42,10 @@ use crate::exec_command::strip_bash_lc_and_escape;
 use crate::history_cell::CommandOutput;
 use crate::history_cell::HistoryCell;
 use crate::history_cell::PatchEventType;
+use crate::live_wrap::RowBuilder;
 use crate::user_approval_widget::ApprovalRequest;
 use codex_file_search::FileMatch;
+use ratatui::style::Stylize;
 
 struct RunningCommand {
     command: Vec<String>,
@@ -65,6 +66,10 @@ pub(crate) struct ChatWidget<'a> {
     // at once into scrollback so the history contains a single message.
     answer_buffer: String,
     running_commands: HashMap<String, RunningCommand>,
+    live_builder: RowBuilder,
+    current_stream: Option<StreamKind>,
+    stream_header_emitted: bool,
+    live_max_rows: u16,
 }
 
 struct UserMessage {
@@ -72,6 +77,12 @@ struct UserMessage {
     image_paths: Vec<PathBuf>,
 }
 
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+enum StreamKind {
+    Answer,
+    Reasoning,
+}
+
 impl From<String> for UserMessage {
     fn from(text: String) -> Self {
         Self {
@@ -152,6 +163,10 @@ impl ChatWidget<'_> {
             reasoning_buffer: String::new(),
             answer_buffer: String::new(),
             running_commands: HashMap::new(),
+            live_builder: RowBuilder::new(80),
+            current_stream: None,
+            stream_header_emitted: false,
+            live_max_rows: 3,
         }
     }
 
@@ -235,58 +250,45 @@ impl ChatWidget<'_> {
 
                 self.request_redraw();
             }
-            EventMsg::AgentMessage(AgentMessageEvent { message }) => {
-                // Final assistant answer. Prefer the fully provided message
-                // from the event; if it is empty fall back to any accumulated
-                // delta buffer (some providers may only stream deltas and send
-                // an empty final 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.add_to_history(HistoryCell::new_agent_message(&self.config, full));
-                }
+            EventMsg::AgentMessage(AgentMessageEvent { message: _ }) => {
+                // Final assistant answer: commit all remaining rows and close with
+                // a blank line. Use the final text if provided, otherwise rely on
+                // streamed deltas already in the builder.
+                self.finalize_stream(StreamKind::Answer);
                 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.begin_stream(StreamKind::Answer);
                 self.answer_buffer.push_str(&delta);
+                self.stream_push_and_maybe_commit(&delta);
+                self.request_redraw();
             }
             EventMsg::AgentReasoningDelta(AgentReasoningDeltaEvent { delta }) => {
-                // Buffer only – disable incremental reasoning streaming so we
-                // avoid truncated intermediate lines. Full text emitted on
-                // AgentReasoning.
+                // Stream CoT into the live pane; keep input visible and commit
+                // overflow rows incrementally to scrollback.
+                self.begin_stream(StreamKind::Reasoning);
                 self.reasoning_buffer.push_str(&delta);
+                self.stream_push_and_maybe_commit(&delta);
+                self.request_redraw();
             }
-            EventMsg::AgentReasoning(AgentReasoningEvent { text }) => {
-                // 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.add_to_history(HistoryCell::new_agent_reasoning(&self.config, full));
-                }
+            EventMsg::AgentReasoning(AgentReasoningEvent { text: _ }) => {
+                // Final reasoning: commit remaining rows and close with a blank.
+                self.finalize_stream(StreamKind::Reasoning);
                 self.request_redraw();
             }
             EventMsg::TaskStarted => {
                 self.bottom_pane.clear_ctrl_c_quit_hint();
                 self.bottom_pane.set_task_running(true);
+                // Replace composer with single-line spinner while waiting.
+                self.bottom_pane
+                    .update_status_text("waiting for model".to_string());
                 self.request_redraw();
             }
             EventMsg::TaskComplete(TaskCompleteEvent {
                 last_agent_message: _,
             }) => {
                 self.bottom_pane.set_task_running(false);
+                self.bottom_pane.clear_live_ring();
                 self.request_redraw();
             }
             EventMsg::TokenCount(token_usage) => {
@@ -299,8 +301,8 @@ impl ChatWidget<'_> {
                 self.bottom_pane.set_task_running(false);
             }
             EventMsg::PlanUpdate(update) => {
+                // Commit plan updates directly to history (no status-line preview).
                 self.add_to_history(HistoryCell::new_plan_update(update));
-                self.request_redraw();
             }
             EventMsg::ExecApprovalRequest(ExecApprovalRequestEvent {
                 call_id: _,
@@ -308,8 +310,7 @@ impl ChatWidget<'_> {
                 cwd,
                 reason,
             }) => {
-                // Print the command to the history so it is visible in the
-                // transcript *before* the modal asks for approval.
+                // Log a background summary immediately so the history is chronological.
                 let cmdline = strip_bash_lc_and_escape(&command);
                 let text = format!(
                     "command requires approval:\n$ {cmdline}{reason}",
@@ -345,7 +346,6 @@ impl ChatWidget<'_> {
                 // approval dialog) and avoids surprising the user with a modal
                 // prompt before they have seen *what* is being requested.
                 // ------------------------------------------------------------------
-
                 self.add_to_history(HistoryCell::new_patch_event(
                     PatchEventType::ApprovalRequest,
                     changes,
@@ -374,13 +374,12 @@ impl ChatWidget<'_> {
                 );
                 self.add_to_history(HistoryCell::new_active_exec_command(command));
             }
+            EventMsg::ExecCommandOutputDelta(_) => {}
             EventMsg::PatchApplyBegin(PatchApplyBeginEvent {
                 call_id: _,
                 auto_approved,
                 changes,
             }) => {
-                // Even when a patch is auto‑approved we still display the
-                // summary so the user can follow along.
                 self.add_to_history(HistoryCell::new_patch_event(
                     PatchEventType::ApplyBegin { auto_approved },
                     changes,
@@ -389,9 +388,11 @@ impl ChatWidget<'_> {
             EventMsg::ExecCommandEnd(ExecCommandEndEvent {
                 call_id,
                 exit_code,
+                duration,
                 stdout,
                 stderr,
             }) => {
+                // Compute summary before moving stdout into the history cell.
                 let cmd = self.running_commands.remove(&call_id);
                 self.add_to_history(HistoryCell::new_completed_exec_command(
                     cmd.map(|cmd| cmd.command).unwrap_or_else(|| vec![call_id]),
@@ -399,7 +400,7 @@ impl ChatWidget<'_> {
                         exit_code,
                         stdout,
                         stderr,
-                        duration: Duration::from_secs(0),
+                        duration,
                     },
                 ));
             }
@@ -441,14 +442,15 @@ impl ChatWidget<'_> {
                 self.app_event_tx.send(AppEvent::ExitRequest);
             }
             event => {
-                self.add_to_history(HistoryCell::new_background_event(format!("{event:?}")));
+                let text = format!("{event:?}");
+                self.add_to_history(HistoryCell::new_background_event(text.clone()));
+                self.update_latest_log(text);
             }
         }
     }
 
     /// Update the live log preview while a task is running.
     pub(crate) fn update_latest_log(&mut self, line: String) {
-        // Forward only if we are currently showing the status indicator.
         self.bottom_pane.update_status_text(line);
     }
 
@@ -508,6 +510,101 @@ impl ChatWidget<'_> {
         self.bottom_pane
             .set_token_usage(self.token_usage.clone(), self.config.model_context_window);
     }
+
+    pub fn cursor_pos(&self, area: Rect) -> Option<(u16, u16)> {
+        self.bottom_pane.cursor_pos(area)
+    }
+}
+
+impl ChatWidget<'_> {
+    fn begin_stream(&mut self, kind: StreamKind) {
+        if self.current_stream != Some(kind) {
+            self.current_stream = Some(kind);
+            self.stream_header_emitted = false;
+            // Clear any previous live content; we're starting a new stream.
+            self.live_builder = RowBuilder::new(self.live_builder.width());
+            // Ensure the waiting status is visible (composer replaced).
+            self.bottom_pane
+                .update_status_text("waiting for model".to_string());
+        }
+    }
+
+    fn stream_push_and_maybe_commit(&mut self, delta: &str) {
+        self.live_builder.push_fragment(delta);
+
+        // Commit overflow rows (small batches) while keeping the last N rows visible.
+        let drained = self
+            .live_builder
+            .drain_commit_ready(self.live_max_rows as usize);
+        if !drained.is_empty() {
+            let mut lines: Vec<ratatui::text::Line<'static>> = Vec::new();
+            if !self.stream_header_emitted {
+                match self.current_stream {
+                    Some(StreamKind::Reasoning) => {
+                        lines.push(ratatui::text::Line::from("thinking".magenta().italic()));
+                    }
+                    Some(StreamKind::Answer) => {
+                        lines.push(ratatui::text::Line::from("codex".magenta().bold()));
+                    }
+                    None => {}
+                }
+                self.stream_header_emitted = true;
+            }
+            for r in drained {
+                lines.push(ratatui::text::Line::from(r.text));
+            }
+            self.app_event_tx.send(AppEvent::InsertHistory(lines));
+        }
+
+        // Update the live ring overlay lines (text-only, newest at bottom).
+        let rows = self
+            .live_builder
+            .display_rows()
+            .into_iter()
+            .map(|r| ratatui::text::Line::from(r.text))
+            .collect::<Vec<_>>();
+        self.bottom_pane
+            .set_live_ring_rows(self.live_max_rows, rows);
+    }
+
+    fn finalize_stream(&mut self, kind: StreamKind) {
+        if self.current_stream != Some(kind) {
+            // Nothing to do; either already finalized or not the active stream.
+            return;
+        }
+        // Flush any partial line as a full row, then drain all remaining rows.
+        self.live_builder.end_line();
+        let remaining = self.live_builder.drain_rows();
+        // TODO: Re-add markdown rendering for assistant answers and reasoning.
+        // When finalizing, pass the accumulated text through `markdown::append_markdown`
+        // to build styled `Line<'static>` entries instead of raw plain text lines.
+        if !remaining.is_empty() || !self.stream_header_emitted {
+            let mut lines: Vec<ratatui::text::Line<'static>> = Vec::new();
+            if !self.stream_header_emitted {
+                match kind {
+                    StreamKind::Reasoning => {
+                        lines.push(ratatui::text::Line::from("thinking".magenta().italic()));
+                    }
+                    StreamKind::Answer => {
+                        lines.push(ratatui::text::Line::from("codex".magenta().bold()));
+                    }
+                }
+                self.stream_header_emitted = true;
+            }
+            for r in remaining {
+                lines.push(ratatui::text::Line::from(r.text));
+            }
+            // Close the block with a blank line for readability.
+            lines.push(ratatui::text::Line::from(""));
+            self.app_event_tx.send(AppEvent::InsertHistory(lines));
+        }
+
+        // Clear the live overlay and reset state for the next stream.
+        self.live_builder = RowBuilder::new(self.live_builder.width());
+        self.bottom_pane.clear_live_ring();
+        self.current_stream = None;
+        self.stream_header_emitted = false;
+    }
 }
 
 impl WidgetRef for &ChatWidget<'_> {

codex-rs/tui/src/history_cell.rs

@@ -1,5 +1,4 @@
 use crate::exec_command::strip_bash_lc_and_escape;
-use crate::markdown::append_markdown;
 use crate::text_block::TextBlock;
 use crate::text_formatting::format_and_truncate_tool_result;
 use base64::Engine;
@@ -68,12 +67,7 @@ pub(crate) enum HistoryCell {
     /// Message from the user.
     UserPrompt { view: TextBlock },
 
-    /// Message from the agent.
-    AgentMessage { view: TextBlock },
-
-    /// Reasoning event from the agent.
-    AgentReasoning { view: TextBlock },
-
+    // AgentMessage and AgentReasoning variants were unused and have been removed.
     /// An exec tool call that has not finished yet.
     ActiveExecCommand { view: TextBlock },
 
@@ -128,8 +122,6 @@ impl HistoryCell {
         match self {
             HistoryCell::WelcomeMessage { view }
             | HistoryCell::UserPrompt { view }
-            | HistoryCell::AgentMessage { view }
-            | HistoryCell::AgentReasoning { view }
             | HistoryCell::BackgroundEvent { view }
             | HistoryCell::GitDiffOutput { view }
             | HistoryCell::ErrorEvent { view }
@@ -231,28 +223,6 @@ impl HistoryCell {
         }
     }
 
-    pub(crate) fn new_agent_message(config: &Config, message: String) -> Self {
-        let mut lines: Vec<Line<'static>> = Vec::new();
-        lines.push(Line::from("codex".magenta().bold()));
-        append_markdown(&message, &mut lines, config);
-        lines.push(Line::from(""));
-
-        HistoryCell::AgentMessage {
-            view: TextBlock::new(lines),
-        }
-    }
-
-    pub(crate) fn new_agent_reasoning(config: &Config, text: String) -> Self {
-        let mut lines: Vec<Line<'static>> = Vec::new();
-        lines.push(Line::from("thinking".magenta().italic()));
-        append_markdown(&text, &mut lines, config);
-        lines.push(Line::from(""));
-
-        HistoryCell::AgentReasoning {
-            view: TextBlock::new(lines),
-        }
-    }
-
     pub(crate) fn new_active_exec_command(command: Vec<String>) -> Self {
         let command_escaped = strip_bash_lc_and_escape(&command);
 
@@ -545,24 +515,17 @@ impl HistoryCell {
         } else {
             for (idx, PlanItemArg { step, status }) in plan.into_iter().enumerate() {
                 let num = idx + 1;
-                let (icon, style): (&str, Style) = match status {
-                    StepStatus::Completed => ("✓", Style::default().fg(Color::Green)),
-                    StepStatus::InProgress => (
-                        "▶",
-                        Style::default()
-                            .fg(Color::Yellow)
-                            .add_modifier(Modifier::BOLD),
-                    ),
-                    StepStatus::Pending => ("○", Style::default().fg(Color::Gray)),
+                let icon_span: Span = match status {
+                    StepStatus::Completed => Span::from("✓").fg(Color::Green),
+                    StepStatus::InProgress => Span::from("▶").fg(Color::Yellow).bold(),
+                    StepStatus::Pending => Span::from("○").fg(Color::Gray),
                 };
-                let prefix = vec![
-                    Span::raw(format!("{num:>2}. [")),
-                    Span::styled(icon.to_string(), style),
-                    Span::raw("] "),
-                ];
-                let mut spans = prefix;
-                spans.push(Span::raw(step));
-                lines.push(Line::from(spans));
+                lines.push(Line::from(vec![
+                    format!("{num:>2}. [").into(),
+                    icon_span,
+                    "] ".into(),
+                    step.into(),
+                ]));
             }
         }
 

codex-rs/tui/src/insert_history.rs

@@ -14,7 +14,6 @@ use crossterm::style::SetBackgroundColor;
 use crossterm::style::SetColors;
 use crossterm::style::SetForegroundColor;
 use ratatui::layout::Size;
-use ratatui::prelude::Backend;
 use ratatui::style::Color;
 use ratatui::style::Modifier;
 use ratatui::text::Line;
@@ -22,6 +21,20 @@ use ratatui::text::Span;
 
 /// Insert `lines` above the viewport.
 pub(crate) fn insert_history_lines(terminal: &mut tui::Tui, lines: Vec<Line>) {
+    let mut out = std::io::stdout();
+    insert_history_lines_to_writer(terminal, &mut out, lines);
+}
+
+/// Like `insert_history_lines`, but writes ANSI to the provided writer. This
+/// is intended for testing where a capture buffer is used instead of stdout.
+pub fn insert_history_lines_to_writer<B, W>(
+    terminal: &mut crate::custom_terminal::Terminal<B>,
+    writer: &mut W,
+    lines: Vec<Line>,
+) where
+    B: ratatui::backend::Backend,
+    W: Write,
+{
     let screen_size = terminal.backend().size().unwrap_or(Size::new(0, 0));
     let cursor_pos = terminal.get_cursor_position().ok();
 
@@ -32,10 +45,22 @@ pub(crate) fn insert_history_lines(terminal: &mut tui::Tui, lines: Vec<Line>) {
         // If the viewport is not at the bottom of the screen, scroll it down to make room.
         // Don't scroll it past the bottom of the screen.
         let scroll_amount = wrapped_lines.min(screen_size.height - area.bottom());
-        terminal
-            .backend_mut()
-            .scroll_region_down(area.top()..screen_size.height, scroll_amount)
-            .ok();
+
+        // Emit ANSI to scroll the lower region (from the top of the viewport to the bottom
+        // of the screen) downward by `scroll_amount` lines. We do this by:
+        //   1) Limiting the scroll region to [area.top()+1 .. screen_height] (1-based bounds)
+        //   2) Placing the cursor at the top margin of that region
+        //   3) Emitting Reverse Index (RI, ESC M) `scroll_amount` times
+        //   4) Resetting the scroll region back to full screen
+        let top_1based = area.top() + 1; // Convert 0-based row to 1-based for DECSTBM
+        queue!(writer, SetScrollRegion(top_1based..screen_size.height)).ok();
+        queue!(writer, MoveTo(0, area.top())).ok();
+        for _ in 0..scroll_amount {
+            // Reverse Index (RI): ESC M
+            queue!(writer, Print("\x1bM")).ok();
+        }
+        queue!(writer, ResetScrollRegion).ok();
+
         let cursor_top = area.top().saturating_sub(1);
         area.y += scroll_amount;
         terminal.set_viewport_area(area);
@@ -59,23 +84,23 @@ pub(crate) fn insert_history_lines(terminal: &mut tui::Tui, lines: Vec<Line>) {
     // ││                            ││
     // │╰────────────────────────────╯│
     // └──────────────────────────────┘
-    queue!(std::io::stdout(), SetScrollRegion(1..area.top())).ok();
+    queue!(writer, SetScrollRegion(1..area.top())).ok();
 
     // NB: we are using MoveTo instead of set_cursor_position here to avoid messing with the
     // terminal's last_known_cursor_position, which hopefully will still be accurate after we
     // fetch/restore the cursor position. insert_history_lines should be cursor-position-neutral :)
-    queue!(std::io::stdout(), MoveTo(0, cursor_top)).ok();
+    queue!(writer, MoveTo(0, cursor_top)).ok();
 
     for line in lines {
-        queue!(std::io::stdout(), Print("\r\n")).ok();
-        write_spans(&mut std::io::stdout(), line.iter()).ok();
+        queue!(writer, Print("\r\n")).ok();
+        write_spans(writer, line.iter()).ok();
     }
 
-    queue!(std::io::stdout(), ResetScrollRegion).ok();
+    queue!(writer, ResetScrollRegion).ok();
 
     // Restore the cursor position to where it was before we started.
     if let Some(cursor_pos) = cursor_pos {
-        queue!(std::io::stdout(), MoveTo(cursor_pos.x, cursor_pos.y)).ok();
+        queue!(writer, MoveTo(cursor_pos.x, cursor_pos.y)).ok();
     }
 }
 
@@ -88,19 +113,25 @@ fn wrapped_line_count(lines: &[Line], width: u16) -> u16 {
 }
 
 fn line_height(line: &Line, width: u16) -> u16 {
-    use unicode_width::UnicodeWidthStr;
-    // get the total display width of the line, accounting for double-width chars
-    let total_width = line
+    // Use the same visible-width slicing semantics as the live row builder so
+    // our pre-scroll estimation matches how rows will actually wrap.
+    let w = width.max(1) as usize;
+    let mut rows = 0u16;
+    let mut remaining = line
         .spans
         .iter()
-        .map(|span| span.content.width())
-        .sum::<usize>();
-    // divide by width to get the number of lines, rounding up
-    if width == 0 {
-        1
-    } else {
-        (total_width as u16).div_ceil(width).max(1)
+        .map(|s| s.content.as_ref())
+        .collect::<Vec<_>>()
+        .join("");
+    while !remaining.is_empty() {
+        let (_prefix, suffix, taken) = crate::live_wrap::take_prefix_by_width(&remaining, w);
+        rows = rows.saturating_add(1);
+        if taken >= remaining.len() {
+            break;
+        }
+        remaining = suffix.to_string();
     }
+    rows.max(1)
 }
 
 #[derive(Debug, Clone, PartialEq, Eq)]
@@ -216,18 +247,18 @@ where
 {
     let mut fg = Color::Reset;
     let mut bg = Color::Reset;
-    let mut modifier = Modifier::empty();
+    let mut last_modifier = Modifier::empty();
     for span in content {
-        let mut next_modifier = modifier;
-        next_modifier.insert(span.style.add_modifier);
-        next_modifier.remove(span.style.sub_modifier);
-        if next_modifier != modifier {
+        let mut modifier = Modifier::empty();
+        modifier.insert(span.style.add_modifier);
+        modifier.remove(span.style.sub_modifier);
+        if modifier != last_modifier {
             let diff = ModifierDiff {
-                from: modifier,
-                to: next_modifier,
+                from: last_modifier,
+                to: modifier,
             };
             diff.queue(&mut writer)?;
-            modifier = next_modifier;
+            last_modifier = modifier;
         }
         let next_fg = span.style.fg.unwrap_or(Color::Reset);
         let next_bg = span.style.bg.unwrap_or(Color::Reset);
@@ -250,3 +281,45 @@ where
         SetAttribute(crossterm::style::Attribute::Reset),
     )
 }
+
+#[cfg(test)]
+mod tests {
+    #![allow(clippy::unwrap_used)]
+    use super::*;
+
+    #[test]
+    fn writes_bold_then_regular_spans() {
+        use ratatui::style::Stylize;
+
+        let spans = ["A".bold(), "B".into()];
+
+        let mut actual: Vec<u8> = Vec::new();
+        write_spans(&mut actual, spans.iter()).unwrap();
+
+        let mut expected: Vec<u8> = Vec::new();
+        queue!(
+            expected,
+            SetAttribute(crossterm::style::Attribute::Bold),
+            Print("A"),
+            SetAttribute(crossterm::style::Attribute::NormalIntensity),
+            Print("B"),
+            SetForegroundColor(CColor::Reset),
+            SetBackgroundColor(CColor::Reset),
+            SetAttribute(crossterm::style::Attribute::Reset),
+        )
+        .unwrap();
+
+        assert_eq!(
+            String::from_utf8(actual).unwrap(),
+            String::from_utf8(expected).unwrap()
+        );
+    }
+
+    #[test]
+    fn line_height_counts_double_width_emoji() {
+        let line = Line::from("😀😀😀"); // each emoji ~ width 2
+        assert_eq!(line_height(&line, 4), 2);
+        assert_eq!(line_height(&line, 2), 3);
+        assert_eq!(line_height(&line, 6), 1);
+    }
+}

codex-rs/tui/src/lib.rs

@@ -25,13 +25,14 @@ mod bottom_pane;
 mod chatwidget;
 mod citation_regex;
 mod cli;
-mod custom_terminal;
+pub mod custom_terminal;
 mod exec_command;
 mod file_search;
 mod get_git_diff;
 mod git_warning_screen;
 mod history_cell;
-mod insert_history;
+pub mod insert_history;
+pub mod live_wrap;
 mod log_layer;
 mod markdown;
 mod slash_command;
@@ -41,6 +42,11 @@ mod text_formatting;
 mod tui;
 mod user_approval_widget;
 
+#[cfg(not(debug_assertions))]
+mod updates;
+#[cfg(not(debug_assertions))]
+use color_eyre::owo_colors::OwoColorize;
+
 pub use cli::Cli;
 
 pub async fn run_main(
@@ -139,6 +145,38 @@ pub async fn run_main(
         .with(tui_layer)
         .try_init();
 
+    #[allow(clippy::print_stderr)]
+    #[cfg(not(debug_assertions))]
+    if let Some(latest_version) = updates::get_upgrade_version(&config) {
+        let current_version = env!("CARGO_PKG_VERSION");
+        let exe = std::env::current_exe()?;
+        let managed_by_npm = std::env::var_os("CODEX_MANAGED_BY_NPM").is_some();
+
+        eprintln!(
+            "{} {current_version} -> {latest_version}.",
+            "✨⬆️ Update available!".bold().cyan()
+        );
+
+        if managed_by_npm {
+            let npm_cmd = "npm install -g @openai/codex@latest";
+            eprintln!("Run {} to update.", npm_cmd.cyan().on_black());
+        } else if cfg!(target_os = "macos")
+            && (exe.starts_with("/opt/homebrew") || exe.starts_with("/usr/local"))
+        {
+            let brew_cmd = "brew upgrade codex";
+            eprintln!("Run {} to update.", brew_cmd.cyan().on_black());
+        } else {
+            eprintln!(
+                "See {} for the latest releases and installation options.",
+                "https://github.com/openai/codex/releases/latest"
+                    .cyan()
+                    .on_black()
+            );
+        }
+
+        eprintln!("");
+    }
+
     let show_login_screen = should_show_login_screen(&config);
     if show_login_screen {
         std::io::stdout()

codex-rs/tui/src/live_wrap.rs

@@ -0,0 +1,290 @@
+use unicode_width::UnicodeWidthChar;
+use unicode_width::UnicodeWidthStr;
+
+/// A single visual row produced by RowBuilder.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct Row {
+    pub text: String,
+    /// True if this row ends with an explicit line break (as opposed to a hard wrap).
+    pub explicit_break: bool,
+}
+
+impl Row {
+    pub fn width(&self) -> usize {
+        self.text.width()
+    }
+}
+
+/// Incrementally wraps input text into visual rows of at most `width` cells.
+///
+/// Step 1: plain-text only. ANSI-carry and styled spans will be added later.
+pub struct RowBuilder {
+    target_width: usize,
+    /// Buffer for the current logical line (until a '\n' is seen).
+    current_line: String,
+    /// Output rows built so far for the current logical line and previous ones.
+    rows: Vec<Row>,
+}
+
+impl RowBuilder {
+    pub fn new(target_width: usize) -> Self {
+        Self {
+            target_width: target_width.max(1),
+            current_line: String::new(),
+            rows: Vec::new(),
+        }
+    }
+
+    pub fn width(&self) -> usize {
+        self.target_width
+    }
+
+    pub fn set_width(&mut self, width: usize) {
+        self.target_width = width.max(1);
+        // Rewrap everything we have (simple approach for Step 1).
+        let mut all = String::new();
+        for row in self.rows.drain(..) {
+            all.push_str(&row.text);
+            if row.explicit_break {
+                all.push('\n');
+            }
+        }
+        all.push_str(&self.current_line);
+        self.current_line.clear();
+        self.push_fragment(&all);
+    }
+
+    /// Push an input fragment. May contain newlines.
+    pub fn push_fragment(&mut self, fragment: &str) {
+        if fragment.is_empty() {
+            return;
+        }
+        let mut start = 0usize;
+        for (i, ch) in fragment.char_indices() {
+            if ch == '\n' {
+                // Flush anything pending before the newline.
+                if start < i {
+                    self.current_line.push_str(&fragment[start..i]);
+                }
+                self.flush_current_line(true);
+                start = i + ch.len_utf8();
+            }
+        }
+        if start < fragment.len() {
+            self.current_line.push_str(&fragment[start..]);
+            self.wrap_current_line();
+        }
+    }
+
+    /// Mark the end of the current logical line (equivalent to pushing a '\n').
+    pub fn end_line(&mut self) {
+        self.flush_current_line(true);
+    }
+
+    /// Drain and return all produced rows.
+    pub fn drain_rows(&mut self) -> Vec<Row> {
+        std::mem::take(&mut self.rows)
+    }
+
+    /// Return a snapshot of produced rows (non-draining).
+    pub fn rows(&self) -> &[Row] {
+        &self.rows
+    }
+
+    /// Rows suitable for display, including the current partial line if any.
+    pub fn display_rows(&self) -> Vec<Row> {
+        let mut out = self.rows.clone();
+        if !self.current_line.is_empty() {
+            out.push(Row {
+                text: self.current_line.clone(),
+                explicit_break: false,
+            });
+        }
+        out
+    }
+
+    /// Drain the oldest rows that exceed `max_keep` display rows (including the
+    /// current partial line, if any). Returns the drained rows in order.
+    pub fn drain_commit_ready(&mut self, max_keep: usize) -> Vec<Row> {
+        let display_count = self.rows.len() + if self.current_line.is_empty() { 0 } else { 1 };
+        if display_count <= max_keep {
+            return Vec::new();
+        }
+        let to_commit = display_count - max_keep;
+        let commit_count = to_commit.min(self.rows.len());
+        let mut drained = Vec::with_capacity(commit_count);
+        for _ in 0..commit_count {
+            drained.push(self.rows.remove(0));
+        }
+        drained
+    }
+
+    fn flush_current_line(&mut self, explicit_break: bool) {
+        // Wrap any remaining content in the current line and then finalize with explicit_break.
+        self.wrap_current_line();
+        // If the current line ended exactly on a width boundary and is non-empty, represent
+        // the explicit break as an empty explicit row so that fragmentation invariance holds.
+        if explicit_break {
+            if self.current_line.is_empty() {
+                // We ended on a boundary previously; add an empty explicit row.
+                self.rows.push(Row {
+                    text: String::new(),
+                    explicit_break: true,
+                });
+            } else {
+                // There is leftover content that did not wrap yet; push it now with the explicit flag.
+                let mut s = String::new();
+                std::mem::swap(&mut s, &mut self.current_line);
+                self.rows.push(Row {
+                    text: s,
+                    explicit_break: true,
+                });
+            }
+        }
+        // Reset current line buffer for next logical line.
+        self.current_line.clear();
+    }
+
+    fn wrap_current_line(&mut self) {
+        // While the current_line exceeds width, cut a prefix.
+        loop {
+            if self.current_line.is_empty() {
+                break;
+            }
+            let (prefix, suffix, taken) =
+                take_prefix_by_width(&self.current_line, self.target_width);
+            if taken == 0 {
+                // Avoid infinite loop on pathological inputs; take one scalar and continue.
+                if let Some((i, ch)) = self.current_line.char_indices().next() {
+                    let len = i + ch.len_utf8();
+                    let p = self.current_line[..len].to_string();
+                    self.rows.push(Row {
+                        text: p,
+                        explicit_break: false,
+                    });
+                    self.current_line = self.current_line[len..].to_string();
+                    continue;
+                }
+                break;
+            }
+            if suffix.is_empty() {
+                // Fits entirely; keep in buffer (do not push yet) so we can append more later.
+                break;
+            } else {
+                // Emit wrapped prefix as a non-explicit row and continue with the remainder.
+                self.rows.push(Row {
+                    text: prefix,
+                    explicit_break: false,
+                });
+                self.current_line = suffix.to_string();
+            }
+        }
+    }
+}
+
+/// Take a prefix of `text` whose visible width is at most `max_cols`.
+/// Returns (prefix, suffix, prefix_width).
+pub fn take_prefix_by_width(text: &str, max_cols: usize) -> (String, &str, usize) {
+    if max_cols == 0 || text.is_empty() {
+        return (String::new(), text, 0);
+    }
+    let mut cols = 0usize;
+    let mut end_idx = 0usize;
+    for (i, ch) in text.char_indices() {
+        let ch_width = UnicodeWidthChar::width(ch).unwrap_or(0);
+        if cols.saturating_add(ch_width) > max_cols {
+            break;
+        }
+        cols += ch_width;
+        end_idx = i + ch.len_utf8();
+        if cols == max_cols {
+            break;
+        }
+    }
+    let prefix = text[..end_idx].to_string();
+    let suffix = &text[end_idx..];
+    (prefix, suffix, cols)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use pretty_assertions::assert_eq;
+
+    #[test]
+    fn rows_do_not_exceed_width_ascii() {
+        let mut rb = RowBuilder::new(10);
+        rb.push_fragment("hello whirl this is a test");
+        let rows = rb.rows().to_vec();
+        assert_eq!(
+            rows,
+            vec![
+                Row {
+                    text: "hello whir".to_string(),
+                    explicit_break: false
+                },
+                Row {
+                    text: "l this is ".to_string(),
+                    explicit_break: false
+                }
+            ]
+        );
+    }
+
+    #[test]
+    fn rows_do_not_exceed_width_emoji_cjk() {
+        // 😀 is width 2; 你/好 are width 2.
+        let mut rb = RowBuilder::new(6);
+        rb.push_fragment("😀😀 你好");
+        let rows = rb.rows().to_vec();
+        // At width 6, we expect the first row to fit exactly two emojis and a space
+        // (2 + 2 + 1 = 5) plus one more column for the first CJK char (2 would overflow),
+        // so only the two emojis and the space fit; the rest remains buffered.
+        assert_eq!(
+            rows,
+            vec![Row {
+                text: "😀😀 ".to_string(),
+                explicit_break: false
+            }]
+        );
+    }
+
+    #[test]
+    fn fragmentation_invariance_long_token() {
+        let s = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"; // 26 chars
+        let mut rb_all = RowBuilder::new(7);
+        rb_all.push_fragment(s);
+        let all_rows = rb_all.rows().to_vec();
+
+        let mut rb_chunks = RowBuilder::new(7);
+        for i in (0..s.len()).step_by(3) {
+            let end = (i + 3).min(s.len());
+            rb_chunks.push_fragment(&s[i..end]);
+        }
+        let chunk_rows = rb_chunks.rows().to_vec();
+
+        assert_eq!(all_rows, chunk_rows);
+    }
+
+    #[test]
+    fn newline_splits_rows() {
+        let mut rb = RowBuilder::new(10);
+        rb.push_fragment("hello\nworld");
+        let rows = rb.display_rows();
+        assert!(rows.iter().any(|r| r.explicit_break));
+        assert_eq!(rows[0].text, "hello");
+        // Second row should begin with 'world'
+        assert!(rows.iter().any(|r| r.text.starts_with("world")));
+    }
+
+    #[test]
+    fn rewrap_on_width_change() {
+        let mut rb = RowBuilder::new(10);
+        rb.push_fragment("abcdefghijK");
+        assert!(!rb.rows().is_empty());
+        rb.set_width(5);
+        for r in rb.rows() {
+            assert!(r.width() <= 5);
+        }
+    }
+}

codex-rs/tui/src/markdown.rs

@@ -1,3 +1,4 @@
+use crate::citation_regex::CITATION_REGEX;
 use codex_core::config::Config;
 use codex_core::config_types::UriBasedFileOpener;
 use ratatui::text::Line;
@@ -5,8 +6,7 @@ use ratatui::text::Span;
 use std::borrow::Cow;
 use std::path::Path;
 
-use crate::citation_regex::CITATION_REGEX;
-
+#[allow(dead_code)]
 pub(crate) fn append_markdown(
     markdown_source: &str,
     lines: &mut Vec<Line<'static>>,
@@ -15,6 +15,7 @@ pub(crate) fn append_markdown(
     append_markdown_with_opener_and_cwd(markdown_source, lines, config.file_opener, &config.cwd);
 }
 
+#[allow(dead_code)]
 fn append_markdown_with_opener_and_cwd(
     markdown_source: &str,
     lines: &mut Vec<Line<'static>>,
@@ -60,6 +61,7 @@ fn append_markdown_with_opener_and_cwd(
 /// ```text
 /// <scheme>://file<ABS_PATH>:<LINE>
 /// ```
+#[allow(dead_code)]
 fn rewrite_file_citations<'a>(
     src: &'a str,
     file_opener: UriBasedFileOpener,

codex-rs/tui/src/status_indicator_widget.rs

@@ -9,24 +9,22 @@ use std::thread;
 use std::time::Duration;
 
 use ratatui::buffer::Buffer;
-use ratatui::layout::Alignment;
 use ratatui::layout::Rect;
 use ratatui::style::Color;
 use ratatui::style::Modifier;
 use ratatui::style::Style;
-use ratatui::style::Stylize;
 use ratatui::text::Line;
 use ratatui::text::Span;
-use ratatui::widgets::Block;
-use ratatui::widgets::BorderType;
-use ratatui::widgets::Borders;
-use ratatui::widgets::Padding;
 use ratatui::widgets::Paragraph;
 use ratatui::widgets::WidgetRef;
+use unicode_width::UnicodeWidthStr;
 
 use crate::app_event::AppEvent;
 use crate::app_event_sender::AppEventSender;
 
+// We render the live text using markdown so it visually matches the history
+// cells. Before rendering we strip any ANSI escape sequences to avoid writing
+// raw control bytes into the back buffer.
 use codex_ansi_escape::ansi_escape_line;
 
 pub(crate) struct StatusIndicatorWidget {
@@ -34,6 +32,14 @@ pub(crate) struct StatusIndicatorWidget {
     /// time).
     text: String,
 
+    /// Animation state: reveal target `text` progressively like a typewriter.
+    /// We compute the currently visible prefix length based on the current
+    /// frame index and a constant typing speed.  The `base_frame` and
+    /// `reveal_len_at_base` form the anchor from which we advance.
+    last_target_len: usize,
+    base_frame: usize,
+    reveal_len_at_base: usize,
+
     frame_idx: Arc<AtomicUsize>,
     running: Arc<AtomicBool>,
     // Keep one sender alive to prevent the channel from closing while the
@@ -57,7 +63,7 @@ impl StatusIndicatorWidget {
             thread::spawn(move || {
                 let mut counter = 0usize;
                 while running_clone.load(Ordering::Relaxed) {
-                    std::thread::sleep(Duration::from_millis(200));
+                    std::thread::sleep(Duration::from_millis(100));
                     counter = counter.wrapping_add(1);
                     frame_idx_clone.store(counter, Ordering::Relaxed);
                     app_event_tx_clone.send(AppEvent::RequestRedraw);
@@ -66,9 +72,13 @@ impl StatusIndicatorWidget {
         }
 
         Self {
-            text: String::from("waiting for logs…"),
+            text: String::from("waiting for model"),
+            last_target_len: 0,
+            base_frame: 0,
+            reveal_len_at_base: 0,
             frame_idx,
             running,
+
             _app_event_tx: app_event_tx,
         }
     }
@@ -79,7 +89,67 @@ impl StatusIndicatorWidget {
 
     /// Update the line that is displayed in the widget.
     pub(crate) fn update_text(&mut self, text: String) {
-        self.text = text.replace(['\n', '\r'], " ");
+        // If the text hasn't changed, don't reset the baseline; let the
+        // animation continue advancing naturally.
+        if text == self.text {
+            return;
+        }
+        // Update the target text, preserving newlines so wrapping matches history cells.
+        // Strip ANSI escapes for the character count so the typewriter animation speed is stable.
+        let stripped = {
+            let line = ansi_escape_line(&text);
+            line.spans
+                .iter()
+                .map(|s| s.content.as_ref())
+                .collect::<Vec<_>>()
+                .join("")
+        };
+        let new_len = stripped.chars().count();
+
+        // Compute how many characters are currently revealed so we can carry
+        // this forward as the new baseline when target text changes.
+        let current_frame = self.frame_idx.load(std::sync::atomic::Ordering::Relaxed);
+        let shown_now = self.current_shown_len(current_frame);
+
+        self.text = text;
+        self.last_target_len = new_len;
+        self.base_frame = current_frame;
+        self.reveal_len_at_base = shown_now.min(new_len);
+    }
+
+    /// Reset the animation and start revealing `text` from the beginning.
+    #[cfg(test)]
+    pub(crate) fn restart_with_text(&mut self, text: String) {
+        let sanitized = text.replace(['\n', '\r'], " ");
+        let stripped = {
+            let line = ansi_escape_line(&sanitized);
+            line.spans
+                .iter()
+                .map(|s| s.content.as_ref())
+                .collect::<Vec<_>>()
+                .join("")
+        };
+
+        let new_len = stripped.chars().count();
+        let current_frame = self.frame_idx.load(std::sync::atomic::Ordering::Relaxed);
+
+        self.text = sanitized;
+        self.last_target_len = new_len;
+        self.base_frame = current_frame;
+        // Start from zero revealed characters for a fresh typewriter cycle.
+        self.reveal_len_at_base = 0;
+    }
+
+    /// Calculate how many characters should currently be visible given the
+    /// animation baseline and frame counter.
+    fn current_shown_len(&self, current_frame: usize) -> usize {
+        // Increase typewriter speed (~5x): reveal more characters per frame.
+        const TYPING_CHARS_PER_FRAME: usize = 7;
+        let frames = current_frame.saturating_sub(self.base_frame);
+        let advanced = self
+            .reveal_len_at_base
+            .saturating_add(frames.saturating_mul(TYPING_CHARS_PER_FRAME));
+        advanced.min(self.last_target_len)
     }
 }
 
@@ -92,100 +162,140 @@ impl Drop for StatusIndicatorWidget {
 
 impl WidgetRef for StatusIndicatorWidget {
     fn render_ref(&self, area: Rect, buf: &mut Buffer) {
-        let widget_style = Style::default();
-        let block = Block::default()
-            .padding(Padding::new(1, 0, 0, 0))
-            .borders(Borders::LEFT)
-            .border_type(BorderType::QuadrantOutside)
-            .border_style(widget_style.dim());
-        // Animated 3‑dot pattern inside brackets. The *active* dot is bold
-        // white, the others are dim.
-        const DOT_COUNT: usize = 3;
+        // Ensure minimal height
+        if area.height == 0 || area.width == 0 {
+            return;
+        }
+
+        // Build animated gradient header for the word "Working".
         let idx = self.frame_idx.load(std::sync::atomic::Ordering::Relaxed);
-        let phase = idx % (DOT_COUNT * 2 - 2);
-        let active = if phase < DOT_COUNT {
-            phase
-        } else {
-            (DOT_COUNT * 2 - 2) - phase
-        };
+        let header_text = "Working";
+        let header_chars: Vec<char> = header_text.chars().collect();
+        let padding = 4usize; // virtual padding around the word for smoother loop
+        let period = header_chars.len() + padding * 2;
+        let pos = idx % period;
+        let has_true_color = supports_color::on_cached(supports_color::Stream::Stdout)
+            .map(|level| level.has_16m)
+            .unwrap_or(false);
+        let band_half_width = 2.0; // width of the bright band in characters
 
         let mut header_spans: Vec<Span<'static>> = Vec::new();
+        for (i, ch) in header_chars.iter().enumerate() {
+            let i_pos = i as isize + padding as isize;
+            let pos = pos as isize;
+            let dist = (i_pos - pos).abs() as f32;
 
-        header_spans.push(Span::styled(
-            "Working ",
-            Style::default()
-                .fg(Color::White)
-                .add_modifier(Modifier::BOLD),
-        ));
+            let t = if dist <= band_half_width {
+                let x = std::f32::consts::PI * (dist / band_half_width);
+                0.5 * (1.0 + x.cos())
+            } else {
+                0.0
+            };
 
-        header_spans.push(Span::styled(
-            "[",
-            Style::default()
-                .fg(Color::White)
-                .add_modifier(Modifier::BOLD),
-        ));
-
-        for i in 0..DOT_COUNT {
-            let style = if i == active {
+            let brightness = 0.4 + 0.6 * t;
+            let level = (brightness * 255.0).clamp(0.0, 255.0) as u8;
+            let style = if has_true_color {
                 Style::default()
-                    .fg(Color::White)
+                    .fg(Color::Rgb(level, level, level))
                     .add_modifier(Modifier::BOLD)
             } else {
-                Style::default().dim()
+                // Bold makes dark gray and gray look the same, so don't use it when true color is not supported.
+                Style::default().fg(color_for_level(level))
             };
-            header_spans.push(Span::styled(".", style));
+
+            header_spans.push(Span::styled(ch.to_string(), style));
         }
 
-        header_spans.push(Span::styled(
-            "] ",
+        // Plain rendering: no borders or padding so the live cell is visually indistinguishable from terminal scrollback.
+        let inner_width = area.width as usize;
+
+        // Compose a single status line like: "▌ Working [•] waiting for model"
+        let mut spans: Vec<Span<'static>> = Vec::new();
+        spans.push(Span::styled("▌ ", Style::default().fg(Color::Cyan)));
+        // Gradient header
+        spans.extend(header_spans);
+        // Space after header
+        spans.push(Span::styled(
+            " ",
             Style::default()
                 .fg(Color::White)
                 .add_modifier(Modifier::BOLD),
         ));
 
-        // Ensure we do not overflow width.
-        let inner_width = block.inner(area).width as usize;
-
-        // Sanitize and colour‑strip the potentially colourful log text.  This
-        // ensures that **no** raw ANSI escape sequences leak into the
-        // back‑buffer which would otherwise cause cursor jumps or stray
-        // artefacts when the terminal is resized.
-        let line = ansi_escape_line(&self.text);
-        let mut sanitized_tail: String = line
-            .spans
-            .iter()
-            .map(|s| s.content.as_ref())
-            .collect::<Vec<_>>()
-            .join("");
-
-        // Truncate *after* stripping escape codes so width calculation is
-        // accurate. See UTF‑8 boundary comments above.
-        let header_len: usize = header_spans.iter().map(|s| s.content.len()).sum();
-
-        if header_len + sanitized_tail.len() > inner_width {
-            let available_bytes = inner_width.saturating_sub(header_len);
-
-            if sanitized_tail.is_char_boundary(available_bytes) {
-                sanitized_tail.truncate(available_bytes);
+        // Truncate spans to fit the width.
+        let mut acc: Vec<Span<'static>> = Vec::new();
+        let mut used = 0usize;
+        for s in spans {
+            let w = s.content.width();
+            if used + w <= inner_width {
+                acc.push(s);
+                used += w;
             } else {
-                let mut idx = available_bytes;
-                while idx < sanitized_tail.len() && !sanitized_tail.is_char_boundary(idx) {
-                    idx += 1;
-                }
-                sanitized_tail.truncate(idx);
+                break;
             }
         }
+        let lines = vec![Line::from(acc)];
 
-        let mut spans = header_spans;
+        // No-op once full text is revealed; the app no longer reacts to a completion event.
 
-        // Re‑apply the DIM modifier so the tail appears visually subdued
-        // irrespective of the colour information preserved by
-        // `ansi_escape_line`.
-        spans.push(Span::styled(sanitized_tail, Style::default().dim()));
-
-        let paragraph = Paragraph::new(Line::from(spans))
-            .block(block)
-            .alignment(Alignment::Left);
+        let paragraph = Paragraph::new(lines);
         paragraph.render_ref(area, buf);
     }
 }
+
+fn color_for_level(level: u8) -> Color {
+    if level < 128 {
+        Color::DarkGray
+    } else if level < 192 {
+        Color::Gray
+    } else {
+        Color::White
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::app_event::AppEvent;
+    use crate::app_event_sender::AppEventSender;
+    use std::sync::mpsc::channel;
+
+    #[test]
+    fn renders_without_left_border_or_padding() {
+        let (tx_raw, _rx) = channel::<AppEvent>();
+        let tx = AppEventSender::new(tx_raw);
+        let mut w = StatusIndicatorWidget::new(tx);
+        w.restart_with_text("Hello".to_string());
+
+        let area = ratatui::layout::Rect::new(0, 0, 30, 1);
+        // Allow a short delay so the typewriter reveals the first character.
+        std::thread::sleep(std::time::Duration::from_millis(120));
+        let mut buf = ratatui::buffer::Buffer::empty(area);
+        w.render_ref(area, &mut buf);
+
+        // Leftmost column has the left bar
+        let ch0 = buf[(0, 0)].symbol().chars().next().unwrap_or(' ');
+        assert_eq!(ch0, '▌', "expected left bar at col 0: {ch0:?}");
+    }
+
+    #[test]
+    fn working_header_is_present_on_last_line() {
+        let (tx_raw, _rx) = channel::<AppEvent>();
+        let tx = AppEventSender::new(tx_raw);
+        let mut w = StatusIndicatorWidget::new(tx);
+        w.restart_with_text("Hi".to_string());
+        // Ensure some frames elapse so we get a stable state.
+        std::thread::sleep(std::time::Duration::from_millis(120));
+
+        let area = ratatui::layout::Rect::new(0, 0, 30, 1);
+        let mut buf = ratatui::buffer::Buffer::empty(area);
+        w.render_ref(area, &mut buf);
+
+        // Single line; it should contain the animated "Working" header.
+        let mut row = String::new();
+        for x in 0..area.width {
+            row.push(buf[(x, 0)].symbol().chars().next().unwrap_or(' '));
+        }
+        assert!(row.contains("Working"), "expected Working header: {row:?}");
+    }
+}

codex-rs/tui/src/updates.rs

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

codex-rs/tui/tests/vt100_history.rs

@@ -0,0 +1,214 @@
+#![cfg(feature = "vt100-tests")]
+#![expect(clippy::expect_used)]
+
+use ratatui::backend::TestBackend;
+use ratatui::layout::Rect;
+use ratatui::style::Color;
+use ratatui::style::Style;
+use ratatui::text::Line;
+use ratatui::text::Span;
+
+// Small helper macro to assert a collection contains an item with a clearer
+// failure message.
+macro_rules! assert_contains {
+    ($collection:expr, $item:expr $(,)?) => {
+        assert!(
+            $collection.contains(&$item),
+            "Expected {:?} to contain {:?}",
+            $collection,
+            $item
+        );
+    };
+    ($collection:expr, $item:expr, $($arg:tt)+) => {
+        assert!($collection.contains(&$item), $($arg)+);
+    };
+}
+
+struct TestScenario {
+    width: u16,
+    height: u16,
+    term: codex_tui::custom_terminal::Terminal<TestBackend>,
+}
+
+impl TestScenario {
+    fn new(width: u16, height: u16, viewport: Rect) -> Self {
+        let backend = TestBackend::new(width, height);
+        let mut term = codex_tui::custom_terminal::Terminal::with_options(backend)
+            .expect("failed to construct terminal");
+        term.set_viewport_area(viewport);
+        Self {
+            width,
+            height,
+            term,
+        }
+    }
+
+    fn run_insert(&mut self, lines: Vec<Line<'static>>) -> Vec<u8> {
+        let mut buf: Vec<u8> = Vec::new();
+        codex_tui::insert_history::insert_history_lines_to_writer(&mut self.term, &mut buf, lines);
+        buf
+    }
+
+    fn screen_rows_from_bytes(&self, bytes: &[u8]) -> Vec<String> {
+        let mut parser = vt100::Parser::new(self.height, self.width, 0);
+        parser.process(bytes);
+        let screen = parser.screen();
+
+        let mut rows: Vec<String> = Vec::with_capacity(self.height as usize);
+        for row in 0..self.height {
+            let mut s = String::with_capacity(self.width as usize);
+            for col in 0..self.width {
+                if let Some(cell) = screen.cell(row, col) {
+                    if let Some(ch) = cell.contents().chars().next() {
+                        s.push(ch);
+                    } else {
+                        s.push(' ');
+                    }
+                } else {
+                    s.push(' ');
+                }
+            }
+            rows.push(s.trim_end().to_string());
+        }
+        rows
+    }
+}
+
+#[test]
+fn hist_001_basic_insertion_no_wrap() {
+    // Screen of 20x6; viewport is the last row (height=1 at y=5)
+    let area = Rect::new(0, 5, 20, 1);
+    let mut scenario = TestScenario::new(20, 6, area);
+
+    let lines = vec![Line::from("first"), Line::from("second")];
+    let buf = scenario.run_insert(lines);
+    let rows = scenario.screen_rows_from_bytes(&buf);
+    assert_contains!(rows, String::from("first"));
+    assert_contains!(rows, String::from("second"));
+    let first_idx = rows
+        .iter()
+        .position(|r| r == "first")
+        .expect("expected 'first' row to be present");
+    let second_idx = rows
+        .iter()
+        .position(|r| r == "second")
+        .expect("expected 'second' row to be present");
+    assert_eq!(second_idx, first_idx + 1, "rows should be adjacent");
+}
+
+#[test]
+fn hist_002_long_token_wraps() {
+    let area = Rect::new(0, 5, 20, 1);
+    let mut scenario = TestScenario::new(20, 6, area);
+
+    let long = "A".repeat(45); // > 2 lines at width 20
+    let lines = vec![Line::from(long.clone())];
+    let buf = scenario.run_insert(lines);
+    let mut parser = vt100::Parser::new(6, 20, 0);
+    parser.process(&buf);
+    let screen = parser.screen();
+
+    // Count total A's on the screen
+    let mut count_a = 0usize;
+    for row in 0..6 {
+        for col in 0..20 {
+            if let Some(cell) = screen.cell(row, col) {
+                if let Some(ch) = cell.contents().chars().next() {
+                    if ch == 'A' {
+                        count_a += 1;
+                    }
+                }
+            }
+        }
+    }
+
+    assert_eq!(
+        count_a,
+        long.len(),
+        "wrapped content did not preserve all characters"
+    );
+}
+
+#[test]
+fn hist_003_emoji_and_cjk() {
+    let area = Rect::new(0, 5, 20, 1);
+    let mut scenario = TestScenario::new(20, 6, area);
+
+    let text = String::from("😀😀😀😀😀 你好世界");
+    let lines = vec![Line::from(text.clone())];
+    let buf = scenario.run_insert(lines);
+    let rows = scenario.screen_rows_from_bytes(&buf);
+    let reconstructed: String = rows.join("").chars().filter(|c| *c != ' ').collect();
+    for ch in text.chars().filter(|c| !c.is_whitespace()) {
+        assert!(
+            reconstructed.contains(ch),
+            "missing character {ch:?} in reconstructed screen"
+        );
+    }
+}
+
+#[test]
+fn hist_004_mixed_ansi_spans() {
+    let area = Rect::new(0, 5, 20, 1);
+    let mut scenario = TestScenario::new(20, 6, area);
+
+    let line = Line::from(vec![
+        Span::styled("red", Style::default().fg(Color::Red)),
+        Span::raw("+plain"),
+    ]);
+    let buf = scenario.run_insert(vec![line]);
+    let rows = scenario.screen_rows_from_bytes(&buf);
+    assert_contains!(rows, String::from("red+plain"));
+}
+
+#[test]
+fn hist_006_cursor_restoration() {
+    let area = Rect::new(0, 5, 20, 1);
+    let mut scenario = TestScenario::new(20, 6, area);
+
+    let lines = vec![Line::from("x")];
+    let buf = scenario.run_insert(lines);
+    let s = String::from_utf8_lossy(&buf);
+    // CUP to 1;1 (ANSI: ESC[1;1H)
+    assert!(
+        s.contains("\u{1b}[1;1H"),
+        "expected final CUP to 1;1 in output, got: {s:?}"
+    );
+    // Reset scroll region
+    assert!(
+        s.contains("\u{1b}[r"),
+        "expected reset scroll region in output, got: {s:?}"
+    );
+}
+
+#[test]
+fn hist_005_pre_scroll_region_down() {
+    // Viewport not at bottom: y=3 (0-based), height=1
+    let area = Rect::new(0, 3, 20, 1);
+    let mut scenario = TestScenario::new(20, 6, area);
+
+    let lines = vec![Line::from("first"), Line::from("second")];
+    let buf = scenario.run_insert(lines);
+    let s = String::from_utf8_lossy(&buf);
+    // Expect we limited scroll region to [top+1 .. screen_height] => [4 .. 6] (1-based)
+    assert!(
+        s.contains("\u{1b}[4;6r"),
+        "expected pre-scroll SetScrollRegion 4..6, got: {s:?}"
+    );
+    // Expect we moved cursor to top of that region: row 3 (0-based) => CUP 4;1H
+    assert!(
+        s.contains("\u{1b}[4;1H"),
+        "expected cursor at top of pre-scroll region, got: {s:?}"
+    );
+    // Expect at least two Reverse Index commands (ESC M) for two inserted lines
+    let ri_count = s.matches("\u{1b}M").count();
+    assert!(
+        ri_count >= 1,
+        "expected at least one RI (ESC M), got: {s:?}"
+    );
+    // After pre-scroll, we set insertion scroll region to [1 .. new_top] => [1 .. 5]
+    assert!(
+        s.contains("\u{1b}[1;5r"),
+        "expected insertion SetScrollRegion 1..5, got: {s:?}"
+    );
+}

codex-rs/tui/tests/vt100_live_commit.rs

@@ -0,0 +1,101 @@
+#![cfg(feature = "vt100-tests")]
+
+use ratatui::backend::TestBackend;
+use ratatui::layout::Rect;
+use ratatui::text::Line;
+
+#[test]
+fn live_001_commit_on_overflow() {
+    let backend = TestBackend::new(20, 6);
+    let mut term = match codex_tui::custom_terminal::Terminal::with_options(backend) {
+        Ok(t) => t,
+        Err(e) => panic!("failed to construct terminal: {e}"),
+    };
+    let area = Rect::new(0, 5, 20, 1);
+    term.set_viewport_area(area);
+
+    // Build 5 explicit rows at width 20.
+    let mut rb = codex_tui::live_wrap::RowBuilder::new(20);
+    rb.push_fragment("one\n");
+    rb.push_fragment("two\n");
+    rb.push_fragment("three\n");
+    rb.push_fragment("four\n");
+    rb.push_fragment("five\n");
+
+    // Keep the last 3 in the live ring; commit the first 2.
+    let commit_rows = rb.drain_commit_ready(3);
+    let lines: Vec<Line<'static>> = commit_rows
+        .into_iter()
+        .map(|r| Line::from(r.text))
+        .collect();
+
+    let mut buf: Vec<u8> = Vec::new();
+    codex_tui::insert_history::insert_history_lines_to_writer(&mut term, &mut buf, lines);
+
+    let mut parser = vt100::Parser::new(6, 20, 0);
+    parser.process(&buf);
+    let screen = parser.screen();
+
+    // The words "one" and "two" should appear above the viewport.
+    let mut joined = String::new();
+    for row in 0..6 {
+        for col in 0..20 {
+            if let Some(cell) = screen.cell(row, col) {
+                if let Some(ch) = cell.contents().chars().next() {
+                    joined.push(ch);
+                } else {
+                    joined.push(' ');
+                }
+            }
+        }
+        joined.push('\n');
+    }
+    assert!(
+        joined.contains("one"),
+        "expected committed 'one' to be visible\n{joined}"
+    );
+    assert!(
+        joined.contains("two"),
+        "expected committed 'two' to be visible\n{joined}"
+    );
+    // The last three (three,four,five) remain in the live ring, not committed here.
+}
+
+#[test]
+fn live_002_pre_scroll_and_commit() {
+    let backend = TestBackend::new(20, 6);
+    let mut term = match codex_tui::custom_terminal::Terminal::with_options(backend) {
+        Ok(t) => t,
+        Err(e) => panic!("failed to construct terminal: {e}"),
+    };
+    // Viewport not at bottom: y=3
+    let area = Rect::new(0, 3, 20, 1);
+    term.set_viewport_area(area);
+
+    let mut rb = codex_tui::live_wrap::RowBuilder::new(20);
+    rb.push_fragment("alpha\n");
+    rb.push_fragment("beta\n");
+    rb.push_fragment("gamma\n");
+    rb.push_fragment("delta\n");
+
+    // Keep 3, commit 1.
+    let commit_rows = rb.drain_commit_ready(3);
+    let lines: Vec<Line<'static>> = commit_rows
+        .into_iter()
+        .map(|r| Line::from(r.text))
+        .collect();
+
+    let mut buf: Vec<u8> = Vec::new();
+    codex_tui::insert_history::insert_history_lines_to_writer(&mut term, &mut buf, lines);
+    let s = String::from_utf8_lossy(&buf);
+
+    // Expect a SetScrollRegion to [area.top()+1 .. screen_height] and a cursor move to top of that region.
+    assert!(
+        s.contains("\u{1b}[4;6r"),
+        "expected pre-scroll region 4..6, got: {s:?}"
+    );
+    assert!(
+        s.contains("\u{1b}[4;1H"),
+        "expected cursor CUP 4;1H, got: {s:?}"
+    );
+}