762 Commits

• Fix: Claude models return incomplete responses due to empty finish_reason handling (#6728)

  ## Summary
  Fixes streaming issue where Claude models return only 1-4 characters
  instead of full responses when used through certain API
  providers/proxies.
  
  ## Environment
  - **OS**: Windows
  - **Models affected**: Claude models (e.g., claude-haiku-4-5-20251001)
  - **API Provider**: AAAI API proxy (https://api.aaai.vip/v1)
  - **Working models**: GLM, Google models work correctly
  
  ## Problem
  When using Claude models in both TUI and exec modes, only 1-4 characters
  are displayed despite the backend receiving the full response. Debug
  logs revealed that some API providers send SSE chunks with an empty
  string finish_reason during active streaming, rather than null or
  omitting the field entirely.
  
  The current code treats any non-null finish_reason as a termination
  signal, causing the stream to exit prematurely after the first chunk.
  The problematic chunks contain finish_reason with an empty string
  instead of null.
  
  ## Solution
  Fix empty finish_reason handling in chat_completions.rs by adding a
  check to only process non-empty finish_reason values. This ensures empty
  strings are ignored and streaming continues normally.
  
  ## Testing
  - Tested on Windows with Claude Haiku model via AAAI API proxy
  - Full responses now received and displayed correctly in both TUI and
  exec modes
  - Other models (GLM, Google) continue to work as expected
  - No regression in existing functionality
  
  ## Impact
  - Improves compatibility with API providers that send empty
  finish_reason during streaming
  - Enables Claude models to work correctly in Windows environment
  - No breaking changes to existing functionality
  
  ## Related Issues
  This fix resolves the issue where Claude models appeared to return
  incomplete responses. The root cause was identified as a compatibility
  issue in parsing SSE responses from certain API providers/proxies,
  rather than a model-specific problem. This change improves overall
  robustness when working with various API endpoints.
  
  ---------
  
  Co-authored-by: Eric Traut <etraut@openai.com>

  dulikaifazr · 2025-11-16 19:50:36 -08:00
  de1768d3ba
• Tighten panic on double truncation (#6701)
  Ahmed Ibrahim · 2025-11-15 07:28:59 +00:00
  3f1c4b9add
• Improve compact (#6692)

  This PR does the following:
  - Add compact prefix to the summary
  - Change the compaction prompt
  - Allow multiple compaction for long running tasks
  - Filter out summary messages on the following compaction
  
  Considerations:
  - Filtering out the summary message isn't the most clean
  - Theoretically, we can end up in infinite compaction loop if the user
  messages > compaction limit . However, that's not possible in today's
  code because we have hard cap on user messages.
  - We need to address having multiple user messages because it confuses
  the model.
  
  Testing:
  - Making sure that after compact we always end up with one user message
  (task) and one summary, even on multiple compaction.

  Ahmed Ibrahim · 2025-11-15 07:17:51 +00:00
  0b28e72b66
• Refactor truncation helpers into its own file (#6683)

  That's to centralize the truncation in one place. Next step would be to
  make only two methods public: one with bytes/lines and one with tokens.

  Ahmed Ibrahim · 2025-11-15 06:44:23 +00:00
  94dfb211af
• Handle "Don't Trust" directory selection in onboarding (#4941)

  Fixes #4940
  Fixes #4892
  
  When selecting "No, ask me to approve edits and commands" during
  onboarding, the code wasn't applying the correct approval policy,
  causing Codex to block all write operations instead of requesting
  approval.
  
  This PR fixes the issue by persisting the "DontTrust" decision in
  config.toml as `trust_level = "untrusted"` and handling it in the
  sandbox and approval policy logic, so Codex correctly asks for approval
  before making changes.
  
  ## Before (bug)
  <img width="709" height="500" alt="bef"
  src="https://github.com/user-attachments/assets/5aced26d-d810-4754-879a-89d9e4e0073b"
  />
  
  ## After (fixed)
  <img width="713" height="359" alt="aft"
  src="https://github.com/user-attachments/assets/9887bbcb-a9a5-4e54-8e76-9125a782226b"
  />
  
  ---------
  
  Co-authored-by: Eric Traut <etraut@openai.com>

  Vinicius da Motta · 2025-11-14 15:23:35 -08:00
  89ecc00b79
• Ignore unified_exec_respects_workdir_override (#6693)
  pakrym-oai · 2025-11-14 15:00:31 -08:00
  018a2d2e50
• Order outputs before inputs (#6691)

  For better caching performance all output items should be rendered in
  the order they were produced before all new input items (for example,
  all function_call before all function_call_output).

  pakrym-oai · 2025-11-14 14:54:11 -08:00
  cfcc87a953
• Enable TUI notifications by default (#6633)

  ## Summary
  - default the `tui.notifications` setting to enabled so desktop
  notifications work out of the box
  - update configuration tests and documentation to reflect the new
  default
  
  ## Testing
  - `cargo test -p codex-core` *(fails:
  `exec::tests::kill_child_process_group_kills_grandchildren_on_timeout`
  is flaky in this sandbox because the spawned grandchild process stays
  alive)*
  - `cargo test -p codex-core
  exec::tests::kill_child_process_group_kills_grandchildren_on_timeout`
  *(fails: same sandbox limitation as above)*
  
  ------
  [Codex
  Task](https://chatgpt.com/codex/tasks/task_i_69166f811144832c9e8aaf8ee2642373)

  Jeremy Rose · 2025-11-14 09:28:09 -08:00
  799364de87
• feat: cache tokenizer (#6609)
  jif-oai · 2025-11-14 17:05:00 +01:00
  f17b392470
• feat: better UI for unified_exec (#6515)

  <img width="376" height="132" alt="Screenshot 2025-11-12 at 17 36 22"
  src="https://github.com/user-attachments/assets/ce693f0d-5ca0-462e-b170-c20811dcc8d5"
  />

  jif-oai · 2025-11-14 16:31:12 +01:00
  63c8c01f40
• tests: replace mount_sse_once_match with mount_sse_once for SSE mocking (#6640)
  pakrym-oai · 2025-11-13 18:04:05 -08:00
  6c384eb9c6
• Promote shared helpers for suite tests (#6460)

  ## Summary
  - add `TestCodex::submit_turn_with_policies` and extend the response
  helpers with reusable tool-call utilities
  - update the grep_files, read_file, list_dir, shell_serialization, and
  tools suites to rely on the shared helpers instead of local copies
  - make the list_dir helper return `anyhow::Result` so clippy no longer
  warns about `expect`
  
  ## Testing
  - `just fix -p codex-core`
  - `cargo test -p codex-core --test all
  suite::grep_files::grep_files_tool_collects_matches`
  - `cargo test -p codex-core
  suite::grep_files::grep_files_tool_collects_matches -- --ignored`
  (filter requests ignored tests so nothing runs, but the build stays
  clean)
  
  
  ------
  [Codex
  Task](https://chatgpt.com/codex/tasks/task_i_69112d53abac83219813cab4d7cb6446)

  Ahmed Ibrahim · 2025-11-13 17:12:10 -08:00
  2a6e9b20df
• Use shared network gating helper in chat completion tests (#6461)

  ## Summary
  - replace the bespoke network check in the chat completion payload and
  SSE tests with the existing `skip_if_no_network!` helper so they follow
  the same gating convention as the rest of the suite
  
  ## Testing
  - `just fmt`
  
  
  ------
  [Codex
  Task](https://chatgpt.com/codex/tasks/task_i_69112d4cb9f08321ba773e8ccf39778e)

  Ahmed Ibrahim · 2025-11-13 17:11:43 -08:00
  f3c6b1334b
• Avoid double truncation (#6631)

  1. Avoid double truncation by giving 10% above the tool default constant
  2. Add tests that fails when const = 1

  Ahmed Ibrahim · 2025-11-13 16:59:31 -08:00
  9890ceb939
• Revert "Revert "Overhaul shell detection and centralize command generation for unified exec"" (#6607)

  Reverts openai/codex#6606

  pakrym-oai · 2025-11-13 16:45:17 -08:00
  7b027e7536
• [App-server] add new v2 events:item/reasoning/delta, item/agentMessage/delta & item/reasoning/summaryPartAdded (#6559)

  core event to app server event mapping:
  1. `codex/event/reasoning_content_delta` ->
  `item/reasoning/summaryTextDelta`.
  2. `codex/event/reasoning_raw_content_delta` ->
  `item/reasoning/textDelta`
  3. `codex/event/agent_message_content_delta` →
  `item/agentMessage/delta`.
  4. `codex/event/agent_reasoning_section_break` ->
  `item/reasoning/summaryPartAdded`.
  
  Also added a change in core to pass down content index, summary index
  and item id from events.
  
  Tested with the `git checkout owen/app_server_test_client && cargo run
  -p codex-app-server-test-client -- send-message-v2 "hello"` and verified
  that new events are emitted correctly.

  Celia Chen · 2025-11-14 00:25:01 +00:00
  b8ec97c0ef
• chore(core) Consolidate apply_patch tests (#6545)

  ## Summary
  Consolidates our apply_patch tests into one suite, and ensures each test
  case tests the various ways the harness supports apply_patch:
  1. Freeform custom tool call
  2. JSON function tool
  3. Simple shell call
  4. Heredoc shell call
  
  There are a few test cases that are specific to a particular variant,
  I've left those alone.
  
  ## Testing
  - [x] This adds a significant number of tests

  Dylan Hurd · 2025-11-13 15:52:39 -08:00
  2c1b693da4
• Update default yield time (#6610)

  10s for exec and 250ms for write_stdin

  pakrym-oai · 2025-11-13 10:24:41 -08:00
  0792a7953d
• Migrate prompt caching tests to test_codex (#6605)

  To hopefully fix the flakiness

  pakrym-oai · 2025-11-13 09:19:38 -08:00
  041d6ad902
• Revert "Overhaul shell detection and centralize command generation for unified exec" (#6606)

  Reverts openai/codex#6577

  pakrym-oai · 2025-11-13 08:43:00 -08:00
  e6995174c1
• Overhaul shell detection and centralize command generation for unified exec (#6577)

  This fixes command display for unified exec. All `cd`s and `ls`es are
  now parsed.
  
  <img width="452" height="237" alt="image"
  src="https://github.com/user-attachments/assets/ce92d81f-f74c-485a-9b34-1eaa29290ec6"
  />
  
  Deletes a ton of tests that were doing nothing from shell.rs.
  
  ---------
  
  Co-authored-by: Pavel Krymets <pavel@krymets.com>

  pakrym-oai · 2025-11-13 08:28:09 -08:00
  d28e912214
• feat: proxy context left after compaction (#6597)
  jif-oai · 2025-11-13 16:54:03 +01:00
  2a417c47ac
• chore(core) Update prompt for gpt-5.1 (#6588)

  ## Summary
  Updates the prompt for GPT-5.1

  Dylan Hurd · 2025-11-13 07:51:28 -08:00
  8dcbd29edd
• Default to explicit medium reasoning for 5.1 (#6593)
  pakrym-oai · 2025-11-13 07:58:42 +00:00
  34621166d5
• remove porcupine model slug (#6580)
  Ahmed Ibrahim · 2025-11-13 04:43:31 +00:00
  b1979b70a8
• Avoid hang when tool's process spawns grandchild that shares stderr/stdout (#6575)

  We've received many reports of codex hanging when calling certain tools.
  [Here](https://github.com/openai/codex/issues/3204) is one example. This
  is likely a major cause. The problem occurs when
  `consume_truncated_output` waits for `stdout` and `stderr` to be closed
  once the child process terminates. This normally works fine, but it
  doesn't handle the case where the child has spawned grandchild processes
  that inherits `stdout` and `stderr`.
  
  The fix was originally written by @md-oai in [this
  PR](https://github.com/openai/codex/pull/1852), which has gone stale.
  I've copied the original fix (which looks sound to me) and added an
  integration test to prevent future regressions.

  Eric Traut · 2025-11-12 20:08:12 -08:00
  73ed30d7e5
• Change model picker to include gpt5.1 (#6569)

  - Change the presets
  - Change the tests that make sure we keep the list of tools updated
  - Filter out deprecated models

  Ahmed Ibrahim · 2025-11-12 19:44:53 -08:00
  ad7eaa80f9
• Set verbosity to low for 5.1 (#6568)

  And improve test coverage

  pakrym-oai · 2025-11-13 01:40:52 +00:00
  f97874093e
• NUX for gpt5.1 (#6561)

  - Introducing a screen to inform users of model changes. 
  - Config name is being passed to be able to reuse this component in the
  future for future models

  Ahmed Ibrahim · 2025-11-13 01:24:21 +00:00
  e63ab0dd65
• [app-server] feat: thread/resume supports history, path, and overrides (#6483)

  This updates `thread/resume` to be at parity with v1's
  `ResumeConversationParams`. Turns out history is useful for codex cloud
  and path is useful for the VSCode extension. And config overrides are
  always useful.

  Owen Lin · 2025-11-12 22:02:43 +00:00
  964220ac94
• Do not double encode request bodies in logging (#6558)
  pakrym-oai · 2025-11-12 21:28:42 +00:00
  2f58e69997
• Add gpt-5.1 model definitions (#6551)
  pakrym-oai · 2025-11-12 12:44:36 -08:00
  ec69a4a810
• Fixed status output to use auth information from AuthManager (#6529)

  This PR addresses https://github.com/openai/codex/issues/6360. The root
  problem is that the TUI was directly loading the `auth.json` file to
  access the auth information. It should instead be using the AuthManager,
  which records the current auth information. The `auth.json` file can be
  overwritten at any time by other instances of the CLI or extension, so
  its information can be out of sync with the current instance. The
  `/status` command should always report the auth information associated
  with the current instance.
  
  An alternative fix for this bug was submitted by @chojs23 in [this
  PR](https://github.com/openai/codex/pull/6495). That approach was only a
  partial fix.

  Eric Traut · 2025-11-12 10:26:50 -08:00
  ad09c138b9
• feat: only wait for mutating tools for ghost commit (#6534)
  jif-oai · 2025-11-12 18:16:32 +00:00
  e00eb50db3
• Fix otel tests (#6541)

  Mount responses only once, remove unneeded retries and add a final
  assistant messages to complete the turn.

  pakrym-oai · 2025-11-12 16:35:34 +00:00
  7d9ad3effd
• feat: shell_command tool (#6510)

  This adds support for a new variant of the shell tool behind a flag. To
  test, run `codex` with `--enable shell_command_tool`, which will
  register the tool with Codex under the name `shell_command` that accepts
  the following shape:
  
  ```python
  {
    command: str
    workdir: str | None,
    timeout_ms: int | None,
    with_escalated_permissions: bool | None,
    justification: str | None,
  }
  ```
  
  This is comparable to the existing tool registered under
  `shell`/`container.exec`. The primary difference is that it accepts
  `command` as a `str` instead of a `str[]`. The `shell_command` tool
  executes by running `execvp(["bash", "-lc", command])`, though the exact
  arguments to `execvp(3)` depend on the user's default shell.
  
  The hypothesis is that this will simplify things for the model. For
  example, on Windows, instead of generating:
  
  ```json
  {"command": ["pwsh.exe", "-NoLogo", "-Command", "ls -Name"]}
  ```
  
  The model could simply generate:
  
  ```json
  {"command": "ls -Name"}
  ```
  
  As part of this change, I extracted some logic out of `user_shell.rs` as
  `Shell::derive_exec_args()` so that it can be reused in
  `codex-rs/core/src/tools/handlers/shell.rs`. Note the original code
  generated exec arg lists like:
  
  ```javascript
  ["bash", "-lc", command]
  ["zsh", "-lc", command]
  ["pwsh.exe", "-NoProfile", "-Command", command]
  ```
  
  Using `-l` for Bash and Zsh, but then specifying `-NoProfile` for
  PowerShell seemed inconsistent to me, so I changed this in the new
  implementation while also adding a `use_login_shell: bool` option to
  make this explicit. If we decide to add a `login: bool` to
  `ShellCommandToolCallParams` like we have for unified exec:
  
  
  https://github.com/openai/codex/blob/807e2c27f0a9f2e85c50e7e6df5533f0d9b853c7/codex-rs/core/src/tools/handlers/unified_exec.rs#L33-L34
  
  Then this should make it straightforward to support.

  Michael Bolin · 2025-11-12 08:18:57 -08:00
  29364f3a9b
• feat: warning switch model on resume (#6507)

  <img width="1259" height="40" alt="Screenshot 2025-11-11 at 14 01 41"
  src="https://github.com/user-attachments/assets/48ead3d2-d89c-4d8a-a578-82d9663dbd88"
  />

  jif-oai · 2025-11-12 11:13:37 +00:00
  530db0ad73
• Add unified exec escalation handling and tests (#6492)

  Similar implementation to the shell tool

  pakrym-oai · 2025-11-11 08:19:35 -08:00
  807e2c27f0
• nit: logs to trace (#6503)
  jif-oai · 2025-11-11 13:37:06 +00:00
  ad279eacdc
• Enable ghost_commit feature by default (#6041)

  ## Summary
  - enable the ghost_commit feature flag by default
  
  ## Testing
  - just fmt
  
  ------
  https://chatgpt.com/codex/tasks/task_i_6904ce2d0370832dbb3c2c09a90fb188

  jif-oai · 2025-11-11 09:20:46 +00:00
  052b052832
• Colocate more of bash parsing (#6489)

  Move a few callsites that were detecting `bash -lc` into a shared
  helper.

  pakrym-oai · 2025-11-11 02:38:36 +00:00
  bb7b0213a8
• Use codex-linux-sandbox in unified exec (#6480)

  Unified exec isn't working on Linux because we don't provide the correct
  arg0.
  
  The library we use for pty management doesn't allow setting arg0
  separately from executable. Use the same aliasing strategy we use for
  `apply_patch` for `codex-linux-sandbox`.
  
  Use `#[ctor]` hack to dispatch codex-linux-sandbox calls.
  
  
  Addresses https://github.com/openai/codex/issues/6450

  pakrym-oai · 2025-11-10 17:17:09 -08:00
  6c36318bd8
• feat: add workdir to unified_exec (#6466)
  jif-oai · 2025-11-10 19:53:36 +00:00
  f01f2ec9ee
• Add user command event types (#6246)

  adding new user command event, logic in TUI to render user command
  events

  zhao-oai · 2025-11-10 19:18:45 +00:00
  980886498c
• Add opt-out for rate limit model nudge (#6433)

  ## Summary
  - add a `hide_rate_limit_model_nudge` notice flag plus config edit
  plumbing so the rate limit reminder preference is persisted and
  documented
  - extend the chat widget prompt with a "never show again" option, and
  wire new app events so selecting it hides future nudges immediately and
  writes the config
  - add unit coverage and refresh the snapshot for the three-option prompt
  
  ## Testing
  - `just fmt`
  - `just fix -p codex-tui`
  - `just fix -p codex-core`
  - `cargo test -p codex-tui`
  - `cargo test -p codex-core` *(fails at
  `exec::tests::kill_child_process_group_kills_grandchildren_on_timeout`:
  grandchild process still alive)*
  
  ------
  [Codex
  Task](https://chatgpt.com/codex/tasks/task_i_6910d7f407748321b2661fc355416994)

  Ahmed Ibrahim · 2025-11-10 09:21:53 -08:00
  e743d251a7
• Move compact (#6454)
  jif-oai · 2025-11-10 11:59:48 +00:00
  50a77dc138
• Fix warning message phrasing (#6446)

  Small fix for sentence phrasing in the warning message
  
  Co-authored-by: AndrewNikolin <877163+AndrewNikolin@users.noreply.github.com>

  Andrew Nikolin · 2025-11-09 22:12:28 -08:00
  131c384361
• fix(seatbelt): Allow reading hw.physicalcpu (#6421)

  Allow reading `hw.physicalcpu` so numpy can be imported when running in
  the sandbox.
   
  resolves #6420

  Oliver Mannion · 2025-11-09 08:53:36 -08:00
  c07461e6f3
• Kill shell tool process groups on timeout (#5258)

  ## Summary
  - launch shell tool processes in their own process group so Codex owns
  the full tree
  - on timeout or ctrl-c, send SIGKILL to the process group before
  terminating the tracked child
  - document that the default shell/unified_exec timeout remains 1000 ms
  
  ## Original Bug
  Long-lived shell tool commands hang indefinitely because the timeout
  handler only terminated the direct child process; any grandchildren it
  spawned kept running and held the PTY open, preventing Codex from
  regaining control.
  
  ## Repro Original Bug
  Install next.js and run `next dev` (which is a long-running shell
  process with children). On openai:main, it will cause the agent to
  permanently get stuck here until human intervention. On this branch,
  this command will be terminated successfully after timeout_ms which will
  unblock the agent. This is a critical fix for unmonitored / lightly
  monitored agents that don't have immediate human observation to unblock
  them.
  
  ---------
  
  Co-authored-by: Michael Bolin <mbolin@openai.com>
  Co-authored-by: Michael Bolin <bolinfest@gmail.com>

  Luca King · 2025-11-07 17:54:35 -08:00
  a2fdfce02a
• Don't request approval for safe commands in unified exec (#6380)
  pakrym-oai · 2025-11-07 16:36:04 -08:00
  91b16b8682