5219 Commits

This Branch

This Branch

All Branches

• feat: /resume per ID/name (#17222)

  Support `/resume 00000-0000-0000-00000000` from the TUI (equivalent for
  the name)

  jif-oai · 2026-04-09 14:21:27 +01:00
  6c5471feb2
• [codex] Defer steering until after sampling the model post-compaction (#17163)

  ## Summary
  - keep pending steered input buffered until the active user prompt has
  received a model response
  - keep steering pending across auto-compact when there is real
  model/tool continuation to resume
  - allow queued steering to follow compaction immediately when the prior
  model response was already final
  - keep pending-input follow-up owned by `run_turn` instead of folding it
  into `SamplingRequestResult`
  - add regression coverage for mid-turn compaction, final-response
  compaction, and compaction triggered before the next request after tool
  output
  
  ## Root Cause
  Steered input was drained at the top of every `run_turn` loop. After
  auto-compaction, the loop continued and immediately appended any pending
  steer after the compact summary, making a queued prompt look like the
  newest task instead of letting the model first resume interrupted
  model/tool work.
  
  ## Implementation Notes
  This patch keeps the follow-up signals separated:
  
  - `SamplingRequestResult.needs_follow_up` means model/tool continuation
  is needed
  - `sess.has_pending_input().await` means queued user steering exists
  - `run_turn` computes the combined loop condition from those two signals
  
  In `run_turn`:
  
  ```rust
  let has_pending_input = sess.has_pending_input().await;
  let needs_follow_up = model_needs_follow_up || has_pending_input;
  ```
  
  After auto-compact we choose whether the next request may drain
  steering:
  
  ```rust
  can_drain_pending_input = !model_needs_follow_up;
  ```
  
  That means:
  
  - model/tool continuation + pending steer: compact -> resume once
  without draining steer
  - completed model answer + pending steer: compact -> drain/send the
  steer immediately
  - fresh user prompt: do not drain steering before the model has answered
  the prompt once
  
  The drain is still only `sess.get_pending_input().await`; when
  `can_drain_pending_input` is false, core uses an empty local vec and
  leaves the steer pending in session state.
  
  ## Validation
  - PASS `cargo test -p codex-core --test all steered_user_input --
  --nocapture`
  - PASS `just fmt`
  - PASS `git diff --check`
  - NOT PASSING HERE `just fix -p codex-core` currently stops before
  linting this change on an unrelated mainline test-build error:
  `core/src/tools/spec_tests.rs` initializes `ToolsConfigParams` without
  `image_generation_tool_auth_allowed`; this PR does not touch that file.

  jgershen-oai · 2026-04-09 02:08:41 -07:00
  8f705b0702
• make webrtc the default experience (#17188)

  ## Summary
  - make realtime default to the v2 WebRTC path
  - keep partial realtime config tables inheriting
  `RealtimeConfig::default()`
  
  ## Validation
  - CI found a stale config-test expectation; fixed in 974ba51bb3
  - just fmt
  - git diff --check
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Ahmed Ibrahim · 2026-04-08 23:52:32 -07:00
  84a24fe333
• Skip update prompts for source builds (#17186)

  Addresses #17166
  
  Problem: Source builds report version 0.0.0, so the TUI update path can
  treat any released Codex version as upgradeable and show startup or
  popup prompts.
  
  Solution: Skip both TUI update prompt entry points when the running CLI
  version is the source-build sentinel 0.0.0.

  Eric Traut · 2026-04-08 22:26:05 -07:00
  23f4cd8459
• Default realtime startup to v2 model (#17183)

  - Default realtime sessions to v2 and gpt-realtime-1.5 when no override
  is configured.
  - Add Op::RealtimeConversationStart integration coverage and keep
  v1-specific tests explicit.
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Ahmed Ibrahim · 2026-04-08 22:11:30 -07:00
  1fdb695e42
• Add TUI notification condition config (#17175)

  Problem: TUI desktop notifications are hard-gated on terminal focus, so
  terminal/IDE hosts that want in-focus notifications cannot opt in.
  
  Solution: Add a flat `[tui] notification_condition` setting (`unfocused`
  by default, `always` opt-in), carry grouped TUI notification settings
  through runtime config, apply method + condition together in the TUI,
  and regenerate the config schema.

  Eric Traut · 2026-04-08 21:50:02 -07:00
  6dc5391c7c
• Add realtime voice selection (#17176)

  - Add realtime voice selection for realtime/start.
  - Expose the supported v1/v2 voice lists and cover explicit, configured,
  default, and invalid voice paths.

  Ahmed Ibrahim · 2026-04-08 20:19:15 -07:00
  2f9090be62
• Move default realtime prompt into core (#17165)

  - Adds a core-owned realtime backend prompt template and preparation
  path.
  - Makes omitted realtime start prompts use the core default, while null
  or empty prompts intentionally send empty instructions.
  - Covers the core realtime path and app-server v2 path with integration
  coverage.
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Ahmed Ibrahim · 2026-04-08 19:34:40 -07:00
  4c2a1ae31b
• Fix stale thread-name resume lookups (#16646)

  Addresses #15943
  
  Problem: Name-based resume could stop on a newer session_index entry
  whose rollout was never persisted, shadowing an older saved thread with
  the same name.
  
  Solution: Materialize rollouts before indexing thread names and make
  name lookup skip unresolved entries until it finds a persisted rollout.

  Eric Traut · 2026-04-08 18:51:29 -07:00
  36586eafed
• Support Warp for OSC 9 notifications (#17174)

  Problem: Warp supports OSC 9 notifications, but the TUI's automatic
  notification backend selection did not recognize its
  `TERM_PROGRAM=WarpTerminal` environment value.
  
  Solution: Treat `TERM_PROGRAM=WarpTerminal` as OSC 9-capable when
  choosing the TUI desktop notification backend.

  Eric Traut · 2026-04-08 18:49:31 -07:00
  4dca906e19
• Add WebRTC realtime app-server e2e tests (#17093)

  Summary:
  - add app-server WebRTC realtime e2e harness
  - cover v1 handoff and v2 codex tool delegation over sideband
  
  Validation:
  - just fmt
  - git diff --check
  - local tests not run; relying on PR CI

  Ahmed Ibrahim · 2026-04-08 18:38:21 -07:00
  22d07e7f8f
• Auto-approve MCP server elicitations in Full Access mode (#17164)

  Currently, when a MCP server sends an elicitation to Codex running in
  Full Access (`sandbox_policy: DangerFullAccess` + `approval_policy:
  Never`), the elicitations are auto-cancelled.
  
  This PR updates the automatic handling of MCP elicitations to be
  consistent with other approvals in full-access, where they are
  auto-approved. Because MCP elicitations may actually require user input,
  this mechanism is limited to empty form elicitations.
  
  ## Changeset
  - Add policy helper shared with existing MCP tool call approval
  auto-approve
  - Update `ElicitationRequestManager` to auto-approve elicitations in
  full access when `can_auto_accept_elicitation` is true.
  - Add tests
  
  Co-authored-by: Codex <noreply@openai.com>

  Leo Shimonaka · 2026-04-08 16:41:02 -07:00
  01537f0bd2
• Update guardian output schema (#17061)

  ## Summary
  - Update guardian output schema to separate risk, authorization,
  outcome, and rationale.
  - Feed guardian rationale into rejection messages.
  - Split the guardian policy into template and tenant-config sections.
  
  ## Validation
  - `cargo test -p codex-core mcp_tool_call`
  - `env -u CODEX_SANDBOX_NETWORK_DISABLED INSTA_UPDATE=always cargo test
  -p codex-core guardian::`
  
  ---------
  
  Co-authored-by: Owen Lin <owen@openai.com>

  maja-openai · 2026-04-08 15:47:29 -07:00
  dcbc91fd39
• Add top-level exec-server subcommand (#17162)

  ## Summary
  - add a top-level `codex exec-server` subcommand, marked experimental in
  CLI help
  - launch an adjacent or PATH-provided `codex-exec-server`, with a
  source-tree `cargo run -p codex-exec-server --` fallback
  - cover the new subcommand parser path
  
  ## Validation
  - `just fmt`
  - `git diff --check`
  - not run: Rust test suite
  
  Co-authored-by: Codex <noreply@openai.com>
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  starr-openai · 2026-04-08 15:38:07 -07:00
  49677ec71f
• Attach WebRTC realtime starts to sideband websocket (#17057)

  Summary:
  - parse the realtime call Location header and join that call over the
  direct realtime WebSocket
  - keep WebRTC starts alive on the existing realtime conversation path
  
  Validation:
  - just fmt
  - git diff --check
  - cargo check -p codex-api
  - cargo check -p codex-core --tests
  - local cargo tests not run; relying on PR CI

  Ahmed Ibrahim · 2026-04-08 15:25:42 -07:00
  794a0240f9
• Wire realtime WebRTC native media into Bazel (#17145)

  - Builds codex-realtime-webrtc through the normal Bazel Rust macro so
  native macOS WebRTC sources are included.\n- Shares the macOS -ObjC link
  flag with Bazel targets that can link libwebrtc.
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Ahmed Ibrahim · 2026-04-08 15:15:55 -07:00
  19bd018300
• Fix ToolsConfigParams initializer in tool registry test (#17154)

  ## Summary
  - add the missing `image_generation_tool_auth_allowed` field to the new
  tool registry plan test initializer
  
  ## Validation
  - `just fmt`
  - `cargo test -p codex-tools image_generation`
  - `cargo test -p codex-tools --no-run`

  Won Park · 2026-04-08 14:05:24 -07:00
  56dfe41605
• Fix missing fields (#17149)

  Fix missing `image_generation_tool_auth_allowed` in two locations.

  canvrno-oai · 2026-04-08 13:53:53 -07:00
  58ad79b60e
• [codex] Support remote exec cwd in TUI startup (#17142)

  When running with remote executor the cwd is the remote path. Today we
  check for existence of a local directory on startup and attempt to load
  config from it.
  
  For remote executors don't do that.

  pakrym-oai · 2026-04-08 13:09:28 -07:00
  e4d6702b87
• Add sandbox support to filesystem APIs (#16751)

  ## Summary
  - add optional `sandboxPolicy` support to the app-server filesystem
  request surface
  - thread sandbox-aware filesystem options through app-server and
  exec-server adapters
  - enforce sandboxed read/write access in the filesystem abstraction with
  focused local and remote coverage
  
  ## Validation
  - `cargo test -p codex-app-server-protocol`
  - `cargo test -p codex-exec-server file_system`
  - `cargo test -p codex-app-server suite::v2::fs`
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  starr-openai · 2026-04-08 12:10:48 -07:00
  f383cc980d
• release ready, enabling only for siwc users (#17046)

  **Disabling Image-Gen for Non-SIWC Codex Users**
  
  We are only enabling image-gen feature for SIWC Codex users until there
  comes a fix in ResponsesAPI to omit output from responses.completed, to
  prevent the following issues:
  
  1. websocket blows up due to heavier load (images) than before (text) 
  2. http parser streams through n^2 of n-base64 bytes (sum of base64s of
  all images generated in turn) that causes long delays in
  turn_completion.

  Won Park · 2026-04-08 11:22:39 -07:00
  e003f84e1e
• fix(debug-config, guardian): fix /debug-config rendering and guardian… (#17138)

  ## Description
  
  This PR fixes `/debug-config` so it shows more of the active
  requirements state, including reviewer requirements and managed feature
  pins. This made it clear that legacy MDM config was setting
  `approvals_reviewer = "guardian_subagent"` and that we were translating
  that into a requirements constraint.
  
  Also, translate `approvals_reviewer = "guardian_subagent"` (from legacy
  managed_config.toml) to `allowed_approvals_reviewers: guardian_subagent,
  user` instead of `allowed_approvals_reviewers: guardian_subagent`.
  
  Example `/debug-config`:
  ```
  Config layer stack (lowest precedence first):
    1. system (/etc/codex/config.toml) (enabled)
    2. user (/Users/owen/.codex/config.toml) (enabled)
    3. project (/Users/owen/repos/codex/.codex/config.toml) (enabled)
    4. legacy managed_config.toml (MDM) (enabled)
       MDM value:
         ...
  
         # Enable Guardian Mode
         features.guardian_approval = true
         approvals_reviewer = "guardian_subagent"
  
  Requirements:
    - allowed_approvals_reviewers: guardian_subagent, user (source: MDM managed_config.toml (legacy))
    - features: apps=true, plugins=true (source: cloud requirements)
  ```
  
  Before this PR, the `Requirements` section showed None.

  Owen Lin · 2026-04-08 11:08:09 -07:00
  e794457a59
• Use AbsolutePathBuf for exec cwd plumbing (#17063)

  ## Summary
  - Carry `AbsolutePathBuf` through tool cwd parsing/resolution instead of
  resolving workdirs to raw `PathBuf`s.
  - Type exec/sandbox request cwd fields as `AbsolutePathBuf` through
  `ExecParams`, `ExecRequest`, `SandboxCommand`, and unified exec runtime
  requests.
  - Keep `PathBuf` conversions at external/event boundaries and update
  existing tests/fixtures for the typed cwd.
  
  ## Validation
  - `cargo check -p codex-core --tests`
  - `cargo check -p codex-sandboxing --tests`
  - `cargo test -p codex-sandboxing`
  - `cargo test -p codex-core --lib tools::handlers::`
  - `just fix -p codex-sandboxing`
  - `just fix -p codex-core`
  - `just fmt`
  
  Full `codex-core` test suite was not run locally; per repo guidance I
  kept local validation targeted.

  pakrym-oai · 2026-04-08 10:54:12 -07:00
  35b5720e8d
• Add WebRTC media transport to realtime TUI (#17058)

  Adds the `[realtime].transport = "webrtc"` TUI media path using a new
  `codex-realtime-webrtc` crate, while leaving app-server as the
  signaling/event source.\n\nLocal checks: fmt, diff-check, dependency
  tree only; test signal should come from CI.
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Ahmed Ibrahim · 2026-04-08 10:26:55 -07:00
  d90a348870
• [mcp] Support server-driven elicitations (#17043)

  - [x] Enables MCP elicitation for custom servers, not just Codex Apps
  - [x] Adds an RMCP service wrapper to preserve elicitation _meta
  - [x] Round-trips response _meta for persist/approval choices
  - [x] Updates TUI empty-schema elicitations into message-only approval
  prompts

  Matthew Zeng · 2026-04-08 10:18:58 -07:00
  7b6486a145
• Add realtime transport config (#17097)

  Adds realtime.transport config with websocket as the default and webrtc
  wired through the effective config.
  
  Co-authored-by: Codex <noreply@openai.com>

  Ahmed Ibrahim · 2026-04-08 09:53:53 -07:00
  06d88b7e81
• Skip MCP auth probing for disabled servers (#17098)

  Addresses #16971
  
  Problem: Disabled MCP servers were still queried for streamable HTTP
  auth status during MCP inventory, so unreachable disabled entries could
  add startup latency.
  
  Solution: Return `Unsupported` immediately for disabled MCP server
  configs before bearer token/OAuth status discovery.

  Eric Traut · 2026-04-08 09:36:07 -07:00
  18171b1931
• Fix TUI crash when resuming the current thread (#17086)

  Problem: Resuming the live TUI thread through `/resume` could
  unsubscribe and reconnect the same app-server thread, leaving the UI
  crashed or disconnected.
  
  Solution: No-op `/resume` only when the selected thread is the currently
  attached active thread; keep the normal resume path for
  stale/displayed-only threads so recovery and reattach still work.

  Eric Traut · 2026-04-08 09:35:54 -07:00
  5c95e4588e
• Show global AGENTS.md in /status (#17091)

  Addresses #3793
  
  Problem: /status only reported project-level AGENTS files, so sessions
  with a loaded global $CODEX_HOME/AGENTS.md still showed Agents.md as
  <none>.
  
  Solution: Track the global instructions file loaded during config
  initialization and prepend that path to the /status Agents.md summary,
  with coverage for AGENTS.md, AGENTS.override.md, and global-plus-project
  ordering.

  Eric Traut · 2026-04-08 09:04:32 -07:00
  dc5feb916d
• Configure multi_agent_v2 spawn agent hints (#17071)

  Allow multi_agent_v2 features to have its own temporary configuration
  under `[features.multi_agent_v2]`
  
  ```
  [features.multi_agent_v2]
  enabled = true
  usage_hint_enabled = false
  usage_hint_text = "Custom delegation guidance."
  hide_spawn_agent_metadata = true
  ```
  
  Absent `usage_hint_text` means use the default hint.
  
  ```
  [features]
  multi_agent_v2 = true
  ```
  
  still works as the boolean shorthand.

  pakrym-oai · 2026-04-08 08:42:18 -07:00
  4c07dd4d25
• codex debug 14 (guardian approved) (#17130)

  Removes lines 92-98 from core/templates/agents/orchestrator.md.

  jif-oai · 2026-04-08 14:14:32 +01:00
  2250fdd54a
• codex debug 12 (guardian approved) (#17128)

  Removes lines 78-84 from core/templates/agents/orchestrator.md.

  jif-oai · 2026-04-08 14:14:28 +01:00
  34fd336e7b
• codex debug 10 (guardian approved) (#17126)

  Removes lines 64-70 from core/templates/agents/orchestrator.md.

  jif-oai · 2026-04-08 14:14:24 +01:00
  6ee4680a81
• codex debug 8 (guardian approved) (#17124)

  Removes lines 50-56 from core/templates/agents/orchestrator.md.

  jif-oai · 2026-04-08 14:14:19 +01:00
  34422855bb
• codex debug 6 (guardian approved) (#17122)

  Removes lines 36-42 from core/templates/agents/orchestrator.md.

  jif-oai · 2026-04-08 14:14:15 +01:00
  9601f2af4b
• codex debug 4 (guardian approved) (#17120)

  Removes lines 22-28 from core/templates/agents/orchestrator.md.

  jif-oai · 2026-04-08 14:14:11 +01:00
  99a12b78c2
• codex debug 2 (guardian approved) (#17118)

  Removes lines 8-14 from core/templates/agents/orchestrator.md.

  jif-oai · 2026-04-08 14:14:06 +01:00
  11eff760d1
• codex debug 15 (guardian approved) (#17131)

  Removes lines 99-106 from core/templates/agents/orchestrator.md.

  jif-oai · 2026-04-08 14:11:01 +01:00
  2b65f24de6
• codex debug 13 (guardian approved) (#17129)

  Removes lines 85-91 from core/templates/agents/orchestrator.md.

  jif-oai · 2026-04-08 14:10:54 +01:00
  95d27bfe8c
• codex debug 11 (guardian approved) (#17127)

  Removes lines 71-77 from core/templates/agents/orchestrator.md.

  jif-oai · 2026-04-08 14:10:47 +01:00
  6e9ffa9a1c
• codex debug 9 (guardian approved) (#17125)

  Removes lines 57-63 from core/templates/agents/orchestrator.md.

  jif-oai · 2026-04-08 14:10:41 +01:00
  c39477a7d5
• codex debug 7 (guardian approved) (#17123)

  Removes lines 43-49 from core/templates/agents/orchestrator.md.

  jif-oai · 2026-04-08 14:10:34 +01:00
  cb77bbfed0
• codex debug 5 (guardian approved) (#17121)

  Removes lines 29-35 from core/templates/agents/orchestrator.md.

  jif-oai · 2026-04-08 14:10:28 +01:00
  5f1363d6d0
• codex debug 3 (guardian approved) (#17119)

  Removes lines 15-21 from core/templates/agents/orchestrator.md.

  jif-oai · 2026-04-08 14:10:22 +01:00
  8558e8aa51
• codex debug 1 (guardian approved) (#17117)

  Removes lines 1-7 from core/templates/agents/orchestrator.md.

  jif-oai · 2026-04-08 14:10:15 +01:00
  22c1fc0131
• feat: single app-server bootstrap in TUI (#16582)

  Before this, the TUI was starting 2 app-server. One to check the login
  status and one to actually start the session
  
  This PR make only one app-server startup and defer the login check in
  async, outside of the frame rendering path
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  jif-oai · 2026-04-08 13:49:06 +01:00
  2bbab7d8f9
• Render namespace description for tools (#16879)
  Vivian Fang · 2026-04-08 02:39:40 -07:00
  d47b755aa2
• Render function attribute descriptions (#16880)
  Vivian Fang · 2026-04-08 02:10:45 -07:00
  9091999c83
• Support anyOf and enum in JsonSchema (#16875)

  This brings us into better alignment with the JSON schema subset that is
  supported in
  <https://developers.openai.com/api/docs/guides/structured-outputs#supported-schemas>,
  and also allows us to render richer function signatures in code mode
  (e.g., anyOf{null, OtherObjectType})

  Vivian Fang · 2026-04-08 01:07:55 -07:00
  ea516f9a40
• Remove obsolete codex-cli README (#17096)

  Problem: codex-cli/README.md is obsolete and confusing to keep around.
  
  Solution: Delete codex-cli/README.md so the stale README is no longer
  present in the repository.

  Eric Traut · 2026-04-08 00:18:23 -07:00
  abc678f9e8