Codex CLI 0.153.0: unified_exec drops structured command outcomes from rollouts and PostToolUse

[normancates]

What version of Codex CLI is running?

0.153.0

What subscription do you have?

Pro

Which model were you using?

GPT 5.6 Sol High

What platform is your computer?

Microsoft Windows NT 10.0.26200.0 x64

What terminal emulator and version are you using (if applicable)?

Powershell

Codex doctor report

{
  "schemaVersion": 1,
  "generatedAt": "1788530724s since unix epoch",
  "overallStatus": "warning",
  "codexVersion": "0.153.0",
  "checks": {
    "app_server.status": {
      "id": "app_server.status",
      "category": "app-server",
      "status": "ok",
      "summary": "background server is not running",
      "details": {
        "control socket": "C:\\Users\\norma\\.codex\\app-server-control\\app-server-control.sock",
        "daemon state dir": "C:\\Users\\norma\\.codex\\app-server-daemon",
        "mode": "ephemeral",
        "pid file": "C:\\Users\\norma\\.codex\\app-server-daemon\\app-server.pid (missing)",
        "settings": "C:\\Users\\norma\\.codex\\app-server-daemon\\settings.json (missing)",
        "status": "not running",
        "update-loop pid file": "C:\\Users\\norma\\.codex\\app-server-daemon\\app-server-updater.pid (missing)"
      },
      "remediation": null,
      "durationMs": 0
    },
    "auth.credentials": {
      "id": "auth.credentials",
      "category": "auth",
      "status": "ok",
      "summary": "auth is configured",
      "details": {
        "auth env vars present": "OPENAI_API_KEY",
        "auth file": "C:\\Users\\norma\\.codex\\auth.json",
        "auth storage mode": "File",
        "stored API key": "false",
        "stored ChatGPT tokens": "true",
        "stored agent identity": "false",
        "stored auth mode": "chatgpt"
      },
      "remediation": null,
      "durationMs": 0
    },
    "config.load": {
      "id": "config.load",
      "category": "config",
      "status": "ok",
      "summary": "config loaded",
      "details": {
        "CODEX_HOME": "C:\\Users\\norma\\.codex",
        "config.toml": "C:\\Users\\norma\\.codex\\config.toml",
        "config.toml parse": "ok",
        "cwd": "S:\\development\\GitHubRepo\\ai-agent-config",
        "enabled feature flags": "<redacted>",
        "feature flag overrides": "none",
        "feature flags enabled": "48",
        "log dir": "C:\\Users\\norma\\.codex\\log",
        "mcp servers": "3",
        "model": "gpt-5.6-sol",
        "model provider": "openai",
        "sqlite home": "C:\\Users\\norma\\.codex"
      },
      "remediation": null,
      "durationMs": 0
    },
    "desktop.app.version": {
      "id": "desktop.app.version",
      "category": "desktop",
      "status": "ok",
      "summary": "the desktop application is installed",
      "details": {
        "log directory": "$HOME\\AppData\\Local\\Codex/Logs",
        "running": "false",
        "version": "26.825.6671.0"
      },
      "remediation": null,
      "durationMs": 0
    },
    "desktop.app_server.handshake": {
      "id": "desktop.app_server.handshake",
      "category": "desktop",
      "status": "ok",
      "summary": "the desktop application is not running",
      "details": {},
      "remediation": null,
      "durationMs": 0
    },
    "desktop.security.enforcement": {
      "id": "desktop.security.enforcement",
      "category": "desktop",
      "status": "ok",
      "summary": "no locally visible recent Codex security enforcement was found",
      "details": {},
      "remediation": null,
      "durationMs": 0
    },
    "git.environment": {
      "id": "git.environment",
      "category": "git",
      "status": "ok",
      "summary": "git version 2.52.0.windows.1",
      "details": {
        ".git entry": "directory",
        "PATH git #1": "C:\\Program Files\\Git\\cmd\\git.exe",
        "PATH git entries": "1",
        "git branch": "main",
        "git build options": "git version 2.52.0.windows.1; cpu: x86_64; built from commit: 2912d8e9b8253723974b7baf1c890273b1a1c5bd; sizeof-long: 4; sizeof-size_t: 8; shell-path: D:/git-sdk-64-build-installers/usr/bin/sh; rust: disabled; feature: fsmonitor--daemon; libcurl: 8.17.0; OpenSSL: OpenSSL 3.5.4 30 Sep 2025; zlib: 1.3.1; SHA-1: SHA1_DC; SHA-256: SHA256_BLK; default-ref-format: files; default-hash: sha1",
        "git exec path": "C:/Program Files/Git/mingw64/libexec/git-core",
        "git version": "git version 2.52.0.windows.1",
        "repo detected": "true",
        "repo root": "S:\\development\\GitHubRepo\\ai-agent-config",
        "selected git": "C:\\Program Files\\Git\\cmd\\git.exe"
      },
      "remediation": null,
      "durationMs": 49
    },
    "git.worktree.dev_drive": {
      "id": "git.worktree.dev_drive",
      "category": "git",
      "status": "warning",
      "summary": "this worktree is not on a Windows Dev Drive; moving it to a trusted Dev Drive can significantly improve repository and filesystem performance",
      "details": {},
      "remediation": "create a trusted Windows Dev Drive for source repositories: https://learn.microsoft.com/en-us/<redacted>",
      "durationMs": 0
    },
    "installation": {
      "id": "installation",
      "category": "install",
      "status": "ok",
      "summary": "installation looks consistent",
      "details": {
        "PATH codex #1": "C:\\Users\\norma\\AppData\\Local\\Programs\\OpenAI\\Codex\\bin\\codex.exe",
        "current executable": "C:\\Users\\norma\\AppData\\Local\\Programs\\OpenAI\\Codex\\bin\\codex.exe",
        "install context": "standalone (windows, package C:\\Users\\norma\\.codex\\packages\\standalone\\releases\\0.153.0-x86_64-pc-windows-msvc, bin C:\\Users\\norma\\.codex\\packages\\standalone\\releases\\0.153.0-x86_64-pc-windows-msvc\\bin, resources C:\\Users\\norma\\.codex\\packages\\standalone\\releases\\0.153.0-x86_64-pc-windows-msvc\\codex-resources, path C:\\Users\\norma\\.codex\\packages\\standalone\\releases\\0.153.0-x86_64-pc-windows-msvc\\codex-path)",
        "managed by Vite+": "false",
        "managed by bun": "false",
        "managed by npm": "false",
        "managed by pnpm": "false",
        "managed package root": "not set"
      },
      "remediation": null,
      "durationMs": 28
    },
    "mcp.config": {
      "id": "mcp.config",
      "category": "mcp",
      "status": "ok",
      "summary": "MCP configuration is locally consistent",
      "details": {
        "configured servers": "3",
        "disabled servers": "1",
        "stdio servers": "3"
      },
      "remediation": null,
      "durationMs": 0
    },
    "network.env": {
      "id": "network.env",
      "category": "network",
      "status": "ok",
      "summary": "network-related environment looks readable",
      "details": {
        "managed proxy": "not configured",
        "proxy env vars": "none",
        "respect system proxy": "disabled"
      },
      "remediation": null,
      "durationMs": 0
    },
    "network.provider_reachability": {
      "id": "network.provider_reachability",
      "category": "reachability",
      "status": "ok",
      "summary": "active provider endpoints are reachable over HTTP",
      "details": {
        "ChatGPT inference URL": "https://chatgpt.com/backend-api/<redacted> reachable (HTTP 405)",
        "desktop assets CDN": "https://persistent.oaistatic.com/codex-app-prod/<redacted> reachable (HTTP 200)",
        "reachability mode": "ChatGPT auth"
      },
      "remediation": null,
      "durationMs": 135
    },
    "network.websocket_reachability": {
      "id": "network.websocket_reachability",
      "category": "websocket",
      "status": "ok",
      "summary": "Responses WebSocket handshake succeeded",
      "details": {
        "DNS": "2 IPv4, 2 IPv6, first IPv4",
        "auth mode": "chatgpt",
        "connect timeout": "15000 ms",
        "endpoint": "wss://chatgpt.com/backend-api/<redacted>",
        "handshake result": "HTTP 101 Switching Protocols",
        "model provider": "openai",
        "provider name": "OpenAI",
        "proxy env vars": "none",
        "reasoning header": "false",
        "server model present": "false",
        "supports websockets": "true",
        "wire API": "responses"
      },
      "remediation": null,
      "durationMs": 645
    },
    "runtime.provenance": {
      "id": "runtime.provenance",
      "category": "runtime",
      "status": "ok",
      "summary": "running standalone on windows-x86_64",
      "details": {
        "commit": "unknown",
        "current executable": "C:\\Users\\norma\\AppData\\Local\\Programs\\OpenAI\\Codex\\bin\\codex.exe",
        "install method": "standalone (windows, package C:\\Users\\norma\\.codex\\packages\\standalone\\releases\\0.153.0-x86_64-pc-windows-msvc, bin C:\\Users\\norma\\.codex\\packages\\standalone\\releases\\0.153.0-x86_64-pc-windows-msvc\\bin, resources C:\\Users\\norma\\.codex\\packages\\standalone\\releases\\0.153.0-x86_64-pc-windows-msvc\\codex-resources, path C:\\Users\\norma\\.codex\\packages\\standalone\\releases\\0.153.0-x86_64-pc-windows-msvc\\codex-path)",
        "platform": "windows-x86_64",
        "version": "0.153.0"
      },
      "remediation": null,
      "durationMs": 0
    },
    "runtime.search": {
      "id": "runtime.search",
      "category": "search",
      "status": "ok",
      "summary": "search is OK (bundled)",
      "details": {
        "search command": "C:\\Users\\norma\\.codex\\packages\\standalone\\releases\\0.153.0-x86_64-pc-windows-msvc\\codex-path\\rg.exe",
        "search command readiness": "file exists",
        "search provider": "bundled"
      },
      "remediation": null,
      "durationMs": 0
    },
    "sandbox.helpers": {
      "id": "sandbox.helpers",
      "category": "sandbox",
      "status": "ok",
      "summary": "sandbox configuration is readable",
      "details": {
        "approval policy": "OnRequest",
        "codex-linux-sandbox helper": "none",
        "denied-read restrictions": "false",
        "execve wrapper helper": "none",
        "filesystem sandbox": "restricted",
        "network sandbox": "restricted",
        "sandbox backend": "<redacted>"
      },
      "remediation": null,
      "durationMs": 0
    },
    "security.endpoint": {
      "id": "security.endpoint",
      "category": "security",
      "status": "warning",
      "summary": "endpoint protection detected; Codex exclusions are unverified",
      "details": {
        "Codex exclusions": "not verified",
        "endpoint products": "Microsoft Defender",
        "exclusion targets": "signed Codex app; codex.exe; codex-windows-sandbox-setup.exe; codex-command-runner.exe; codex-code-mode-host.exe"
      },
      "issues": [
        {
          "severity": "warning",
          "cause": "Microsoft Defender can interfere with Codex. Verify Codex exclusions.",
          "measured": "not verified",
          "expected": "Codex application and helper exclusions",
          "remedy": "Microsoft Defender: Add a certificate or executable-path exclusion for Codex and its helpers. If Attack Surface Reduction blocks Codex, add a rule exclusion. If Controlled Folder Access blocks Codex, allow the app.",
          "fields": [
            "Codex exclusions"
          ]
        }
      ],
      "remediation": "ask your security administrator to verify Codex exclusions and required helper allowances",
      "durationMs": 12
    },
    "state.paths": {
      "id": "state.paths",
      "category": "state",
      "status": "ok",
      "summary": "state paths and databases are inspectable",
      "details": {
        "CODEX_HOME": "C:\\Users\\norma\\.codex (dir)",
        "active rollout files": "204 files, 1005319599 total bytes, 4928037 average bytes",
        "archived rollout files": "0 files, 0 total bytes, 0 average bytes",
        "goals DB": "C:\\Users\\norma\\.codex\\goals_1.sqlite (file)",
        "goals DB integrity": "ok",
        "log DB": "C:\\Users\\norma\\.codex\\logs_2.sqlite (file)",
        "log DB integrity": "ok",
        "log dir": "C:\\Users\\norma\\.codex\\log (missing)",
        "memories DB": "C:\\Users\\norma\\.codex\\memories_1.sqlite (file)",
        "memories DB integrity": "ok",
        "queue DB": "C:\\Users\\norma\\.codex\\queue_1.sqlite (file)",
        "queue DB integrity": "ok",
        "sqlite home": "C:\\Users\\norma\\.codex (dir)",
        "standalone release cache": "2 entries in C:\\Users\\norma\\.codex\\packages\\standalone\\releases",
        "state DB": "C:\\Users\\norma\\.codex\\state_5.sqlite (file)",
        "state DB integrity": "ok",
        "thread history DB": "C:\\Users\\norma\\.codex\\thread_history_1.sqlite (file)",
        "thread history DB integrity": "ok"
      },
      "remediation": null,
      "durationMs": 142
    },
    "state.rollout_db_parity": {
      "id": "state.rollout_db_parity",
      "category": "threads",
      "status": "warning",
      "summary": "rollout files and state DB thread inventory differ",
      "details": {
        "default model provider": "openai",
        "rollout DB active files": "204",
        "rollout DB active rows": "203",
        "rollout DB archive mismatches": "0",
        "rollout DB archived files": "0",
        "rollout DB archived rows": "0",
        "rollout DB duplicate DB paths": "0",
        "rollout DB duplicate rollout thread ids": "0",
        "rollout DB malformed file names": "0",
        "rollout DB missing active rows": "1",
        "rollout DB missing active sample": "C:\\Users\\norma\\.codex\\sessions\\2025\\12\\10\\rollout-2025-12-10T04-09-48-019b03a9-5680-7710-b9e5-96db617eebe8.jsonl",
        "rollout DB missing archived rows": "0",
        "rollout DB model providers": "openai=197, ollama-launch=5, ollama-launch-codex-app=1",
        "rollout DB rows": "203",
        "rollout DB scan cap reached": "false",
        "rollout DB scan errors": "0",
        "rollout DB sources": "vscode=135, subagent:other=52, cli=9, subagent:thread_spawn=4, exec=3",
        "rollout DB stale rows": "0"
      },
      "issues": [
        {
          "severity": "warning",
          "cause": "rollout files are missing from the state DB",
          "measured": "1 active, 0 archived",
          "expected": "every rollout file has a matching threads row",
          "remedy": null,
          "fields": []
        }
      ],
      "remediation": null,
      "durationMs": 109
    },
    "system.disk": {
      "id": "system.disk",
      "category": "disk",
      "status": "ok",
      "summary": "sufficient free disk space (28.8 GiB)",
      "details": {
        "CODEX_HOME available": "28.8 GiB",
        "failure threshold": "1.0 GiB",
        "warning threshold": "5.0 GiB",
        "worktree available": "3927.0 GiB"
      },
      "remediation": null,
      "durationMs": 0
    },
    "system.environment": {
      "id": "system.environment",
      "category": "system",
      "status": "ok",
      "summary": "OS language en-GB",
      "details": {
        "EDITOR": "not set",
        "VISUAL": "not set",
        "os": "Windows 10.0.26200 (Windows 11 Professional) [64-bit]",
        "os language": "en-GB",
        "os type": "Windows",
        "os version": "10.0.26200"
      },
      "remediation": null,
      "durationMs": 0
    },
    "terminal.env": {
      "id": "terminal.env",
      "category": "terminal",
      "status": "ok",
      "summary": "terminal metadata was detected",
      "details": {
        "WT_SESSION": "present",
        "color output": "enabled",
        "console input code page": "850",
        "console output code page": "850",
        "stderr console mode": "0x00000007 (VT processing: true)",
        "stderr is terminal": "true",
        "stdin is terminal": "true",
        "stdout console mode": "0x00000007 (VT processing: true)",
        "stdout is terminal": "true",
        "terminal": "Windows Terminal",
        "terminal size": "120x30"
      },
      "remediation": null,
      "durationMs": 0
    },
    "terminal.title": {
      "id": "terminal.title",
      "category": "title",
      "status": "ok",
      "summary": "terminal title default",
      "details": {
        "terminal title activity": "true",
        "terminal title items": "activity, project-name",
        "terminal title project source": "git repo root",
        "terminal title project value": "ai-agent-config",
        "terminal title source": "default"
      },
      "remediation": null,
      "durationMs": 0
    },
    "updates.status": {
      "id": "updates.status",
      "category": "updates",
      "status": "ok",
      "summary": "update configuration is locally consistent",
      "details": {
        "cached latest version": "0.153.0",
        "check for update on startup": "true",
        "desktop application": "OpenAI.Codex",
        "desktop latest build": "26.901.4073.0",
        "desktop update status": "available",
        "last checked at": "2026-09-03T20:20:29.104343100Z",
        "latest version": "0.153.2",
        "latest version status": "newer version is available",
        "update action": "standalone installer",
        "version cache": "C:\\Users\\norma\\.codex\\version.json"
      },
      "remediation": null,
      "durationMs": 714
    }
  }
}

What issue are you seeing?

With unified_exec enabled in Codex CLI 0.153.0, shell-command activity is no longer emitted as structured event_msg/item_completed CommandExecution records.

Instead, it is recorded as custom_tool_call and custom_tool_call_output. These replacement records do not contain the information previously available for command auditing:

• parsed_cmd read classification
• Command completion status
• Structured exit code
• Structured command output metadata

The PostToolUse hook receives the inner command with tool_name: "Bash", but tool_response contains only plain output text. It does not include the command’s exit code, even though the execution layer has that value internally.
This prevents checkpoint and audit integrations from reliably determining which files were read or whether commands failed. Empty results can incorrectly appear to mean “nothing failed” when the required outcome information was unavailable.

Setting in config.toml:

[features]
unified_exec = false

restores the structured CommandExecution records and makes the information available again.

What steps can reproduce the bug?

1. Confirm the affected version:
   codex --version
   Observed: codex-cli 0.153.0.
2. From a Git repository containing README.md, run a controlled session with unified exec enabled:
   codex --enable unified_exec -a never -C <repository> exec "Read README.md using the shell. Then run cmd.exe /d /c exit 7. Do not modify any files."
3. Inspect the newly created rollout under ~/.codex/sessions/.
4. Observe that command activity is represented by custom_tool_call and custom_tool_call_output, without structured read classification, command status, or exit code.
5. Repeat the same test with unified exec disabled:
   codex --disable unified_exec -a never -C <repository> exec "Read README.md using the shell. Then run cmd.exe /d /c exit 7. Do not modify any files."
6. Inspect the second rollout. It now contains structured item_completed CommandExecution records with parsed_cmd, status, and exit-code information.

In our controlled disabled-feature test, the generated checkpoint correctly reported:

files_read: ["README.md"]
commands_run: 2
failed_calls: 1
failures: 1

What is the expected behavior?

unified_exec should preserve structured observability equivalent to the previous command-execution path.
Rollout records and/or PostToolUse should provide, at minimum:

• Executed command
• Working directory
• Read/access classification or accessed paths
• Completion status
• Exit code
• Standard output and standard error, or equivalent aggregated output

Changing the execution backend should not make command failures and file reads unknowable to hook-based integrations. We would particularly like the structured command-result outputs restored so integrations do not need to infer outcomes from shell-output text.

Additional information

No response

[argszero]

Thanks for the detailed report with the A/B comparison (unified_exec on vs off) — that's the right way to isolate this. I dug into the current code and want to share what I found, because there's an important design contract at play on the PostToolUse side.

On the hook's tool_response lacking an exit code:

In codex-rs/core/src/tools/context.rs, ExecCommandToolOutput implements ToolOutput. Its post_tool_use_response (lines 404-412) does two things:

• Returns None when process_id.is_some() (a still-running / resumable PTY session) or when hook_command is None.
• Otherwise returns only Some(JsonValue::String(truncated_output)) — a flat string with no exit_code, even though self.exit_code is present on the struct (line 355) and is used in the sibling code_mode_result (line 421).

So the exit code is captured internally but deliberately not surfaced through the PostToolUse tool_response. And this is not an oversight — it's an asserted contract. In codex-rs/core/src/tools/handlers/unified_exec_tests.rs there are several tests that assert the plain-string shape exactly:

• exec_command_post_tool_use_payload_uses_output_for_noninteractive_one_shot_commands → tool_response: json!("three")
• exec_command_post_tool_use_payload_uses_output_for_interactive_completion → tool_response: json!("three")
• write_stdin_post_tool_use_payload_uses_original_exec_call_id_and_command_on_completion → tool_response: json!("finished\n")
• write_stdin_post_tool_use_payload_keeps_parallel_session_metadata_separate → tool_response: json!("beta\n") / json!("alpha\n")

So making tool_response include exit_code is a deliberate behavior change (it would break those tests and the hook contract), not a regression fix. That's the key question for maintainers: is a flat output string the intended PostToolUse contract for unified_exec, or should it be extended (e.g. to an object with output + exit_code) so checkpoint/audit integrations can determine failure status without resorting to the non-unified_exec path? If the latter, it's a small, contained change to post_tool_use_response plus updating those four tests.

Separately, the rollout-emission concern (custom_tool_call / custom_tool_call_output instead of structured CommandExecution records) is a distinct event-shape question that is worth investigating on its own — that's about how the unified_exec path serializes items into the rollout, not the hook payload. I'd suggest splitting that from the hook-contract question.

No change made — just surfacing the design tension so the fix direction is clear before any code is written.