794 Commits

• guardian initial feedback / tweaks (#13897)

  ## Summary
  - remove the remaining model-visible guardian-specific `on-request`
  prompt additions so enabling the feature does not change the main
  approval-policy instructions
  - neutralize user-facing guardian wording to talk about automatic
  approval review / approval requests rather than a second reviewer or
  only sandbox escalations
  - tighten guardian retry-context handling so agent-authored
  `justification` stays in the structured action JSON and is not also
  injected as raw retry context
  - simplify guardian review plumbing in core by deleting dead
  prompt-append paths and trimming some request/transcript setup code
  
  ## Notable Changes
  - delete the dead `permissions/approval_policy/guardian.md` append path
  and stop threading `guardian_approval_enabled` through model-facing
  developer-instruction builders
  - rename the experimental feature copy to `Automatic approval review`
  and update the `/experimental` snapshot text accordingly
  - make approval-review status strings generic across shell, patch,
  network, and MCP review types
  - forward real sandbox/network retry reasons for shell and unified-exec
  guardian review, but do not pass agent-authored justification as raw
  retry context
  - simplify `guardian.rs` by removing the one-field request wrapper,
  deduping reasoning-effort selection, and cleaning up transcript entry
  collection
  
  ## Testing
  - `just fmt`
  - full validation left to CI
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Charley Cunningham · 2026-03-09 09:25:24 -07:00
  f23fcd6ced
• Add request permissions tool (#13092)

  Adds a built-in `request_permissions` tool and wires it through the
  Codex core, protocol, and app-server layers so a running turn can ask
  the client for additional permissions instead of relying on a static
  session policy.
  
  The new flow emits a `RequestPermissions` event from core, tracks the
  pending request by call ID, forwards it through app-server v2 as an
  `item/permissions/requestApproval` request, and resumes the tool call
  once the client returns an approved subset of the requested permission
  profile.

  Jack Mousseau · 2026-03-08 20:23:06 -07:00
  e6b93841c5
• fix(core) patch otel test (#14014)

  ## Summary
  This test was missing the turn completion event in the responses stream,
  so it was hanging. This PR fixes the issue
  
  ## Testing
  - [x] This does update the test

  Dylan Hurd · 2026-03-08 19:06:30 -07:00
  f41b1638c9
• app-server: include experimental skill metadata in exec approval requests (#13929)

  ## Summary
  
  This change surfaces skill metadata on command approval requests so
  app-server clients can tell when an approval came from a skill script
  and identify the originating `SKILL.md`.
  
  - add `skill_metadata` to exec approval events in the shared protocol
  - thread skill metadata through core shell escalation and delegated
  approval handling for skill-triggered approvals
  - expose the field in app-server v2 as experimental `skillMetadata`
  - regenerate the JSON/TypeScript schemas and cover the new field in
  protocol, transport, core, and TUI tests
  
  ## Why
  
  Skill-triggered approvals already carry skill context inside core, but
  app-server clients could not see which skill caused the prompt. Sending
  the skill metadata with the approval request makes it possible for
  clients to present better approval UX and connect the prompt back to the
  relevant skill definition.
  
  
  ## example event in app-server-v2
  verified that we see this event when experimental api is on:
  ```
  < {
  <   "id": 11,
  <   "method": "item/commandExecution/requestApproval",
  <   "params": {
  <     "additionalPermissions": {
  <       "fileSystem": null,
  <       "macos": {
  <         "accessibility": false,
  <         "automations": {
  <           "bundle_ids": [
  <             "com.apple.Notes"
  <           ]
  <         },
  <         "calendar": false,
  <         "preferences": "read_only"
  <       },
  <       "network": null
  <     },
  <     "approvalId": "25d600ee-5a3c-4746-8d17-e2e61fb4c563",
  <     "availableDecisions": [
  <       "accept",
  <       "acceptForSession",
  <       "cancel"
  <     ],
  <     "command": "/Applications/ChatGPT.app/Contents/Resources/CodexAppServer_CodexAppServerBundledSkills.bundle/Contents/Resources/skills/apple-notes/scripts/notes_info",
  <     "commandActions": [
  <       {
  <         "command": "/Applications/ChatGPT.app/Contents/Resources/CodexAppServer_CodexAppServerBundledSkills.bundle/Contents/Resources/skills/apple-notes/scripts/notes_info",
  <         "type": "unknown"
  <       }
  <     ],
  <     "cwd": "/Applications/ChatGPT.app/Contents/Resources/CodexAppServer_CodexAppServerBundledSkills.bundle/Contents/Resources/skills/apple-notes",
  <     "itemId": "call_jZp3xFpNg4D8iKAD49cvEvZy",
  <     "skillMetadata": {
  <       "pathToSkillsMd": "/Applications/ChatGPT.app/Contents/Resources/CodexAppServer_CodexAppServerBundledSkills.bundle/Contents/Resources/skills/apple-notes/SKILL.md"
  <     },
  <     "threadId": "019ccc10-b7d3-7ff2-84fe-3a75e7681e69",
  <     "turnId": "019ccc10-b848-76f1-81b3-4a1fa225493f"
  <   }
  < }`
  ```
  
  & verified that this is the event when experimental api is off:
  ```
  < {
  <   "id": 13,
  <   "method": "item/commandExecution/requestApproval",
  <   "params": {
  <     "approvalId": "5fbbf776-261b-4cf8-899b-c125b547f2c0",
  <     "availableDecisions": [
  <       "accept",
  <       "acceptForSession",
  <       "cancel"
  <     ],
  <     "command": "/Applications/ChatGPT.app/Contents/Resources/CodexAppServer_CodexAppServerBundledSkills.bundle/Contents/Resources/skills/apple-notes/scripts/notes_info",
  <     "commandActions": [
  <       {
  <         "command": "/Applications/ChatGPT.app/Contents/Resources/CodexAppServer_CodexAppServerBundledSkills.bundle/Contents/Resources/skills/apple-notes/scripts/notes_info",
  <         "type": "unknown"
  <       }
  <     ],
  <     "cwd": "/Users/celia/code/codex/codex-rs",
  <     "itemId": "call_OV2DHzTgYcbYtWaTTBWlocOt",
  <     "threadId": "019ccc16-2a2b-7be1-8500-e00d45b892d4",
  <     "turnId": "019ccc16-2a8e-7961-98ec-649600e7d06a"
  <   }
  < }
  ```

  Celia Chen · 2026-03-08 18:07:46 -07:00
  340f9c9ecb
• Stabilize shell serialization tests (#13877)

  ## What changed
  - The duration-recording fixture sleep was reduced from a large
  artificial delay to `0.2s`, and the assertion floor was lowered to
  `0.1s`.
  - The shell tool fixtures now force `login = false` so they do not
  invoke login-shell startup paths.
  
  ## Why this fixes the flake
  - The old tests were paying for two kinds of noise that had nothing to
  do with the feature being validated: oversized sleep time and variable
  shell initialization cost.
  - Login shells can pick up runner-specific startup files and incur
  inconsistent startup latency.
  - The test only needs to prove that we record a nontrivial duration and
  preserve shell output. A shorter fixture delay plus a non-login shell
  keeps that coverage while removing runner-dependent wall-clock variance.
  
  ## Scope
  - Test-only change.

  Ahmed Ibrahim · 2026-03-08 13:37:41 -07:00
  1f150eda8b
• seatbelt: honor split filesystem sandbox policies (#13448)

  ## Why
  
  After `#13440` and `#13445`, macOS Seatbelt policy generation was still
  deriving filesystem and network behavior from the legacy `SandboxPolicy`
  projection.
  
  That projection loses explicit unreadable carveouts and conflates split
  network decisions, so the generated Seatbelt policy could still be wider
  than the split policy that Codex had already computed.
  
  ## What changed
  
  - added Seatbelt entrypoints that accept `FileSystemSandboxPolicy` and
  `NetworkSandboxPolicy` directly
  - built read and write policy stanzas from access roots plus excluded
  subpaths so explicit unreadable carveouts survive into the generated
  Seatbelt policy
  - switched network policy generation to consult `NetworkSandboxPolicy`
  directly
  - failed closed when managed-network or proxy-constrained sessions do
  not yield usable loopback proxy endpoints
  - updated the macOS callers and test helpers that now need to carry the
  split policies explicitly
  
  ## Verification
  
  - added regression coverage in `core/src/seatbelt.rs` for unreadable
  carveouts under both full-disk and scoped-readable policies
  - verified the current PR state with `just clippy`
  
  
  
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/13448).
  * #13453
  * #13452
  * #13451
  * #13449
  * __->__ #13448
  * #13445
  * #13440
  * #13439
  
  ---------
  
  Co-authored-by: viyatb-oai <viyatb@openai.com>

  Michael Bolin · 2026-03-08 00:35:19 +00:00
  bf5c2f48a5
• fix(ci) fix guardian ci (#13911)

  ## Summary
  #13910 was merged with some unused imports, let's fix this
  
  ## Testing
  - [x] Let's make sure CI is green
  
  ---------
  
  Co-authored-by: Charles Cunningham <ccunningham@openai.com>
  Co-authored-by: Codex <noreply@openai.com>

  Dylan Hurd · 2026-03-07 23:34:56 +00:00
  92f7541624
• Add guardian approval MVP (#13692)

  ## Summary
  - add the guardian reviewer flow for `on-request` approvals in command,
  patch, sandbox-retry, and managed-network approval paths
  - keep guardian behind `features.guardian_approval` instead of exposing
  a public `approval_policy = guardian` mode
  - route ordinary `OnRequest` approvals to the guardian subagent when the
  feature is enabled, without changing the public approval-mode surface
  
  ## Public model
  - public approval modes stay unchanged
  - guardian is enabled via `features.guardian_approval`
  - when that feature is on, `approval_policy = on-request` keeps the same
  approval boundaries but sends those approval requests to the guardian
  reviewer instead of the user
  - `/experimental` only persists the feature flag; it does not rewrite
  `approval_policy`
  - CLI and app-server no longer expose a separate `guardian` approval
  mode in this PR
  
  ## Guardian reviewer
  - the reviewer runs as a normal subagent and reuses the existing
  subagent/thread machinery
  - it is locked to a read-only sandbox and `approval_policy = never`
  - it does not inherit user/project exec-policy rules
  - it prefers `gpt-5.4` when the current provider exposes it, otherwise
  falls back to the parent turn's active model
  - it fail-closes on timeout, startup failure, malformed output, or any
  other review error
  - it currently auto-approves only when `risk_score < 80`
  
  ## Review context and policy
  - guardian mirrors `OnRequest` approval semantics rather than
  introducing a separate approval policy
  - explicit `require_escalated` requests follow the same approval surface
  as `OnRequest`; the difference is only who reviews them
  - managed-network allowlist misses that enter the approval flow are also
  reviewed by guardian
  - the review prompt includes bounded recent transcript history plus
  recent tool call/result evidence
  - transcript entries and planned-action strings are truncated with
  explicit `<guardian_truncated ... />` markers so large payloads stay
  bounded
  - apply-patch reviews include the full patch content (without
  duplicating the structured `changes` payload)
  - the guardian request layout is snapshot-tested using the same
  model-visible Responses request formatter used elsewhere in core
  
  ## Guardian network behavior
  - the guardian subagent inherits the parent session's managed-network
  allowlist when one exists, so it can use the same approved network
  surface while reviewing
  - exact session-scoped network approvals are copied into the guardian
  session with protocol/port scope preserved
  - those copied approvals are now seeded before the guardian's first turn
  is submitted, so inherited approvals are available during any immediate
  review-time checks
  
  ## Out of scope / follow-ups
  - the sandbox-permission validation split was pulled into a separate PR
  and is not part of this diff
  - a future follow-up can enable `serde_json` preserve-order in
  `codex-core` and then simplify the guardian action rendering further
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Charley Cunningham · 2026-03-07 05:40:10 -08:00
  e84ee33cc0
• feat: simplify DB further (#13771)
  jif-oai · 2026-03-07 03:48:36 -08:00
  cf143bf71e
• fix(core): respect reject policy by approval source for skill scripts (#13816)

  ## Summary
  - distinguish reject-policy handling for prefix-rule approvals versus
  sandbox approvals in Unix shell escalation
  - keep prompting for skill-script execution when `rules=true` but
  `sandbox_approval=false`, instead of denying the command up front
  - add regression coverage for both skill-script reject-policy paths in
  `codex-rs/core/tests/suite/skill_approval.rs`

  Celia Chen · 2026-03-06 21:43:14 -08:00
  b0ce16c47a
• sandboxing: plumb split sandbox policies through runtime (#13439)

  ## Why
  
  `#13434` introduces split `FileSystemSandboxPolicy` and
  `NetworkSandboxPolicy`, but the runtime still made most execution-time
  sandbox decisions from the legacy `SandboxPolicy` projection.
  
  That projection loses information about combinations like unrestricted
  filesystem access with restricted network access. In practice, that
  means the runtime can choose the wrong platform sandbox behavior or set
  the wrong network-restriction environment for a command even when config
  has already separated those concerns.
  
  This PR carries the split policies through the runtime so sandbox
  selection, process spawning, and exec handling can consult the policy
  that actually matters.
  
  ## What changed
  
  - threaded `FileSystemSandboxPolicy` and `NetworkSandboxPolicy` through
  `TurnContext`, `ExecRequest`, sandbox attempts, shell escalation state,
  unified exec, and app-server exec overrides
  - updated sandbox selection in `core/src/sandboxing/mod.rs` and
  `core/src/exec.rs` to key off `FileSystemSandboxPolicy.kind` plus
  `NetworkSandboxPolicy`, rather than inferring behavior only from the
  legacy `SandboxPolicy`
  - updated process spawning in `core/src/spawn.rs` and the platform
  wrappers to use `NetworkSandboxPolicy` when deciding whether to set
  `CODEX_SANDBOX_NETWORK_DISABLED`
  - kept additional-permissions handling and legacy `ExternalSandbox`
  compatibility projections aligned with the split policies, including
  explicit user-shell execution and Windows restricted-token routing
  - updated callers across `core`, `app-server`, and `linux-sandbox` to
  pass the split policies explicitly
  
  ## Verification
  
  - added regression coverage in `core/tests/suite/user_shell_cmd.rs` to
  verify `RunUserShellCommand` does not inherit
  `CODEX_SANDBOX_NETWORK_DISABLED` from the active turn
  - added coverage in `core/src/exec.rs` for Windows restricted-token
  sandbox selection when the legacy projection is `ExternalSandbox`
  - updated Linux sandbox coverage in
  `linux-sandbox/tests/suite/landlock.rs` to exercise the split-policy
  exec path
  - verified the current PR state with `just clippy`
  
  
  
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/13439).
  * #13453
  * #13452
  * #13451
  * #13449
  * #13448
  * #13445
  * #13440
  * __->__ #13439
  
  ---------
  
  Co-authored-by: viyatb-oai <viyatb@openai.com>

  Michael Bolin · 2026-03-07 02:30:21 +00:00
  22ac6b9aaa
• Allow full web search tool config (#13675)

  Previously, we could only configure whether web search was on/off.
  
  This PR enables sending along a web search config, which includes all
  the stuff responsesapi supports: filters, location, etc.

  Rohan Mehta · 2026-03-07 00:50:50 +00:00
  61098c7f51
• fix(core): skip exec approval for permissionless skill scripts (#13791)

  ## Summary
  
  - Treat skill scripts with no permission profile, or an explicitly empty
  one, as permissionless and run them with the turn's existing sandbox
  instead of forcing an exec approval prompt.
  - Keep the approval flow unchanged for skills that do declare additional
  permissions.
  - Update the skill approval tests to assert that permissionless skill
  scripts do not prompt on either the initial run or a rerun.
  
  ## Why
  
  Permissionless skills should inherit the current turn sandbox directly.
  Prompting for exec approval in that case adds friction without granting
  any additional capability.

  Celia Chen · 2026-03-06 16:40:41 -08:00
  8b81284975
• chore(otel): rename OtelManager to SessionTelemetry (#13808)

  ## Summary
  This is a purely mechanical refactor of `OtelManager` ->
  `SessionTelemetry` to better convey what the struct is doing. No
  behavior change.
  
  ## Why
  
  `OtelManager` ended up sounding much broader than what this type
  actually does. It doesn't manage OTEL globally; it's the session-scoped
  telemetry surface for emitting log/trace events and recording metrics
  with consistent session metadata (`app_version`, `model`, `slug`,
  `originator`, etc.).
  
  `SessionTelemetry` is a more accurate name, and updating the call sites
  makes that boundary a lot easier to follow.
  
  ## Validation
  
  - `just fmt`
  - `cargo test -p codex-otel`
  - `cargo test -p codex-core`

  Owen Lin · 2026-03-06 16:23:30 -08:00
  289ed549cf
• Add realtime startup context override (#13796)

  - add experimental_realtime_ws_startup_context to override or disable
  realtime websocket startup context
  - preserve generated startup context when unset and cover the new
  override paths in tests

  Ahmed Ibrahim · 2026-03-06 16:00:30 -08:00
  a11c59f634
• config: add initial support for the new permission profile config language in config.toml (#13434)

  ## Why
  
  `SandboxPolicy` currently mixes together three separate concerns:
  
  - parsing layered config from `config.toml`
  - representing filesystem sandbox state
  - carrying basic network policy alongside filesystem choices
  
  That makes the existing config awkward to extend and blocks the new TOML
  proposal where `[permissions]` becomes a table of named permission
  profiles selected by `default_permissions`. (The idea is that if
  `default_permissions` is not specified, we assume the user is opting
  into the "traditional" way to configure the sandbox.)
  
  This PR adds the config-side plumbing for those profiles while still
  projecting back to the legacy `SandboxPolicy` shape that the current
  macOS and Linux sandbox backends consume.
  
  It also tightens the filesystem profile model so scoped entries only
  exist for `:project_roots`, and so nested keys must stay within a
  project root instead of using `.` or `..` traversal.
  
  This drops support for the short-lived `[permissions.network]` in
  `config.toml` because now that would be interpreted as a profile named
  `network` within `[permissions]`.
  
  ## What Changed
  
  - added `PermissionsToml`, `PermissionProfileToml`,
  `FilesystemPermissionsToml`, and `FilesystemPermissionToml` so config
  can parse named profiles under `[permissions.<profile>.filesystem]`
  - added top-level `default_permissions` selection, validation for
  missing or unknown profiles, and compilation from a named profile into
  split `FileSystemSandboxPolicy` and `NetworkSandboxPolicy` values
  - taught config loading to choose between the legacy `sandbox_mode` path
  and the profile-based path without breaking legacy users
  - introduced `codex-protocol::permissions` for the split filesystem and
  network sandbox types, and stored those alongside the legacy projected
  `sandbox_policy` in runtime `Permissions`
  - modeled `FileSystemSpecialPath` so only `ProjectRoots` can carry a
  nested `subpath`, matching the intended config syntax instead of
  allowing invalid states for other special paths
  - restricted scoped filesystem maps to `:project_roots`, with validation
  that nested entries are non-empty descendant paths and cannot use `.` or
  `..` to escape the project root
  - kept existing runtime consumers working by projecting
  `FileSystemSandboxPolicy` back into `SandboxPolicy`, with an explicit
  error for profiles that request writes outside the workspace root
  - loaded proxy settings from top-level `[network]`
  - regenerated `core/config.schema.json`
  
  ## Verification
  
  - added config coverage for profile deserialization,
  `default_permissions` selection, top-level `[network]` loading, network
  enablement, rejection of writes outside the workspace root, rejection of
  nested entries for non-`:project_roots` special paths, and rejection of
  parent-directory traversal in `:project_roots` maps
  - added protocol coverage for the legacy bridge rejecting non-workspace
  writes
  
  ## Docs
  
  - update the Codex config docs on developers.openai.com/codex to
  document named `[permissions.<profile>]` entries, `default_permissions`,
  scoped `:project_roots` syntax, the descendant-path restriction for
  nested `:project_roots` entries, and top-level `[network]` proxy
  configuration
  
  
  
  
  
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/13434).
  * #13453
  * #13452
  * #13451
  * #13449
  * #13448
  * #13445
  * #13440
  * #13439
  * __->__ #13434

  Michael Bolin · 2026-03-06 15:39:13 -08:00
  f82678b2a4
• feat: structured plugin parsing (#13711)

  #### What
  
  Add structured `@plugin` parsing and TUI support for plugin mentions.
  
  - Core: switch from plain-text `@display_name` parsing to structured
  `plugin://...` mentions via `UserInput::Mention` and
  `[$...](plugin://...)` links in text, same pattern as apps/skills.
  - TUI: add plugin mention popup, autocomplete, and chips when typing
  `$`. Load plugin capability summaries and feed them into the composer;
  plugin mentions appear alongside skills and apps.
  - Generalize mention parsing to a sigil parameter, still defaults to `$`
  
  <img width="797" height="119" alt="image"
  src="https://github.com/user-attachments/assets/f0fe2658-d908-4927-9139-73f850805ceb"
  />
  
  Builds on #13510. Currently clients have to build their own `id` via
  `plugin@marketplace` and filter plugins to show by `enabled`, but we
  will add `id` and `available` as fields returned from `plugin/list`
  soon.
  
  ####Tests
  
  Added tests, verified locally.

  sayan-oai · 2026-03-06 11:08:36 -08:00
  8a54d3caaa
• Clarify sandbox permission override helper semantics (#13703)

  ## Summary
  Today `SandboxPermissions::requires_additional_permissions()` does not
  actually mean "is `WithAdditionalPermissions`". It returns `true` for
  any non-default sandbox override, including `RequireEscalated`. That
  broad behavior is relied on in multiple `main` callsites.
  
  The naming is security-sensitive because `SandboxPermissions` is used on
  shell-like tool calls to tell the executor how a single command should
  relate to the turn sandbox:
  - `UseDefault`: run with the turn sandbox unchanged
  - `RequireEscalated`: request execution outside the sandbox
  - `WithAdditionalPermissions`: stay sandboxed but widen permissions for
  that command only
  
  ## Problem
  The old helper name reads as if it only applies to the
  `WithAdditionalPermissions` variant. In practice it means "this command
  requested any explicit sandbox override."
  
  That ambiguity made it easy to read production checks incorrectly and
  made the guardian change look like a standalone `main` fix when it is
  not.
  
  On `main` today:
  - `shell` and `unified_exec` intentionally reject any explicit
  `sandbox_permissions` request unless approval policy is `OnRequest`
  - `exec_policy` intentionally treats any explicit sandbox override as
  prompt-worthy in restricted sandboxes
  - tests intentionally serialize both `RequireEscalated` and
  `WithAdditionalPermissions` as explicit sandbox override requests
  
  So changing those callsites from the broad helper to a narrow
  `WithAdditionalPermissions` check would be a behavior change, not a pure
  cleanup.
  
  ## What This PR Does
  - documents `SandboxPermissions` as a per-command sandbox override, not
  a generic permissions bag
  - adds `requests_sandbox_override()` for the broad meaning: anything
  except `UseDefault`
  - adds `uses_additional_permissions()` for the narrow meaning: only
  `WithAdditionalPermissions`
  - keeps `requires_additional_permissions()` as a compatibility alias to
  the broad meaning for now
  - updates the current broad callsites to use the accurately named broad
  helper
  - adds unit coverage that locks in the semantics of all three helpers
  
  ## What This PR Does Not Do
  This PR does not change runtime behavior. That is intentional.
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Charley Cunningham · 2026-03-06 09:57:48 -08:00
  cb1a182bbe
• Enabling CWD Saving for Image-Gen (#13607)

  Codex now saves the generated image on to your current working
  directory.

  Won Park · 2026-03-06 00:47:21 -08:00
  ee1a20258a
• Replay thread rollback from rollout history (#13615)

  - Replay thread rollback from the persisted rollout history instead of
  truncating in-memory state.\n- Add rollback coverage, including
  rollback-behind-compaction snapshot coverage.

  Ahmed Ibrahim · 2026-03-05 16:40:09 -08:00
  629cb15bc6
• Refine realtime startup context formatting (#13560)

  ## Summary
  - group recent work by git repo when available, otherwise by directory
  - render recent work as bounded user asks with per-thread cwd context
  - exclude hidden files and directories from workspace trees

  Ahmed Ibrahim · 2026-03-05 16:31:20 -08:00
  6cf0ed4e79
• add @plugin mentions (#13510)

  ## Note-- added plugin mentions via @, but that conflicts with file
  mentions
  
  depends and builds upon #13433.
  
  - introduces explicit `@plugin` mentions. this injects the plugin's mcp
  servers, app names, and skill name format into turn context as a dev
  message.
  - we do not yet have UI for these mentions, so we currently parse raw
  text (as opposed to skills and apps which have UI chips, autocomplete,
  etc.) this depends on a `plugins/list` app-server endpoint we can feed
  the UI with, which is upcoming
  - also annotate mcp and app tool descriptions with the plugin(s) they
  come from. this gives the model a first class way of understanding what
  tools come from which plugins, which will help implicit invocation.
  
  ### Tests
  Added and updated tests, unit and integration. Also confirmed locally a
  raw `@plugin` injects the dev message, and the model knows about its
  apps, mcps, and skills.

  sayan-oai · 2026-03-06 00:03:39 +00:00
  4e77ea0ec7
• feat(core): persist trace_id for turns in RolloutItem::TurnContext (#13602)

  This PR adds a durable trace linkage for each turn by storing the active
  trace ID on the rollout TurnContext record stored in session rollout
  files.
  
  Before this change, we propagated trace context at runtime but didn’t
  persist a stable per-turn trace key in rollout history. That made
  after-the-fact debugging harder (for example, mapping a historical turn
  to the corresponding trace in datadog). This sets us up for much easier
  debugging in the future.
  
  ### What changed
  - Added an optional `trace_id` to TurnContextItem (rollout schema).
  - Added a small OTEL helper to read the current span trace ID.
  - Captured `trace_id` when creating `TurnContext` and included it in
  `to_turn_context_item()`.
  - Updated tests and fixtures that construct TurnContextItem so
  older/no-trace cases still work.
  
  ### Why this approach
  TurnContext is already the canonical durable per-turn metadata in
  rollout. This keeps ownership clean: trace linkage lives with other
  persisted turn metadata.

  Owen Lin · 2026-03-05 13:26:48 -08:00
  aa3fe8abf8
• Persist initialized js_repl bindings after failed cells (#13482)

  ## Summary
  
  - Change `js_repl` failed-cell persistence so later cells keep prior
  bindings plus only the current-cell bindings whose initialization
  definitely completed before the throw.
  - Preserve initialized lexical bindings across failed cells via
  module-namespace readability, including top-level destructuring that
  partially succeeds before a later throw.
  - Preserve hoisted `var` and `function` bindings only when execution
  clearly reached their declaration site, and preserve direct top-level
  pre-declaration `var` writes and updates through explicit write-site
  markers.
  - Preserve top-level `for...in` / `for...of` `var` bindings when the
  loop body executes at least once, using a first-iteration guard to avoid
  per-iteration bookkeeping overhead.
  - Keep prior module state intact across link-time failures and
  evaluation failures before the prelude runs, while still allowing failed
  cells that already recreated prior bindings to persist updates to those
  existing bindings.
  - Hide internal commit hooks from user `js_repl` code after the prelude
  aliases them, so snippets cannot spoof committed bindings by calling the
  raw `import.meta` hooks directly.
  - Add focused regression coverage for the supported failed-cell
  behaviors and the intentionally unsupported boundaries.
  - Update `js_repl` docs and generated instructions to describe the new,
  narrower failed-cell persistence model.
  
  ## Motivation
  
  We saw `js_repl` drop bindings that had already been initialized
  successfully when a later statement in the same cell threw, for example:
  
      const { context: liveContext, session } =
        await initializeGoogleSheetsLiveForTab(tab);
      // later statement throws
  
  That was surprising in practice because successful earlier work
  disappeared from the next cell.
  
  This change makes failed-cell persistence more useful without trying to
  model every possible partially executed JavaScript edge case. The
  resulting behavior is narrower and easier to reason about:
  
  - prior bindings are always preserved
  - lexical bindings persist when their initialization completed before
  the throw
  - hoisted `var` / `function` bindings persist only when execution
  clearly reached their declaration or a supported top-level `var` write
  site
  - failed cells that already recreated prior bindings can persist writes
  to those existing bindings even if they introduce no new bindings
  
  The detailed edge-case matrix stays in `docs/js_repl.md`. The
  model-facing `project_doc` guidance is intentionally shorter and focused
  on generation-relevant behavior.
  
  ## Supported Failed-Cell Behavior
  
  - Prior bindings remain available after a failed cell.
  - Initialized lexical bindings remain available after a failed cell.
  - Top-level destructuring like `const { a, b } = ...` preserves names
  whose initialization completed before a later throw.
  - Hoisted `function` bindings persist when execution reached the
  declaration statement before the throw.
  - Direct top-level pre-declaration `var` writes and updates persist, for
  example:
    - `x = 1`
    - `x += 1`
    - `x++`
  - short-circuiting logical assignments only persist when the write
  branch actually runs
  - Non-empty top-level `for...in` / `for...of` `var` loops persist their
  loop bindings.
  - Failed cells can persist updates to existing carried bindings after
  the prelude has run, even when the cell commits no new bindings.
  - Link failures and eval failures before the prelude do not poison
  `@prev`.
  
  ## Intentionally Unsupported Failed-Cell Cases
  
  - Hoisted function reads before the declaration, such as `foo(); ...;
  function foo() {}`
  - Aliasing or inference-based recovery from reads before declaration
  - Nested writes inside already-instrumented assignment RHS expressions
  - Destructuring-assignment recovery for hoisted `var`
  - Partial `var` destructuring recovery
  - Pre-declaration `undefined` reads for hoisted `var`
  - Empty top-level `for...in` / `for...of` loop vars
  - Nested or scope-sensitive pre-declaration `var` writes outside direct
  top-level expression statements

  Curtis 'Fjord' Hawthorne · 2026-03-05 11:01:46 -08:00
  657841e7f5
• chore: add web_search_tool_type for image support (#13538)

  add `web_search_tool_type` on model_info that can be populated from
  backend. will be used to filter which models can use `web_search` with
  images and which cant.
  
  added small unit test.

  sayan-oai · 2026-03-05 07:02:27 +00:00
  03d55f0e6f
• feat: track plugins mcps/apps and add plugin info to user_instructions (#13433)

  ### first half of changes, followed by #13510
  
  Track plugin capabilities as derived summaries on `PluginLoadOutcome`
  for enabled plugins with at least one skill/app/mcp.
  
  Also add `Plugins` section to `user_instructions` injected on session
  start. These introduce the plugins concept and list enabled plugins, but
  do NOT currently include paths to enabled plugins or details on what
  apps/mcps the plugins contain (current plan is to inject this on
  @-mention). that can be adjusted in a follow up and based on evals.
  
  ### tests
  Added/updated tests, confirmed locally that new `Plugins` section +
  currently enabled plugins show up in `user_instructions`.

  sayan-oai · 2026-03-04 19:46:13 -08:00
  d44398905b
• image-gen-event/client_processing (#13512)

  enabling client-side to process with image-generation capabilities
  (setting app-server)

  Won Park · 2026-03-04 16:54:38 -08:00
  229e6d0347
• Prefix handoff messages with role (#13505)

  Format handoff context by prefixing each message with its role (for
  example "user:" and "assistant:") before forwarding to the agent.

  Ahmed Ibrahim · 2026-03-04 15:37:31 -08:00
  294079b0b1
• image-gen-core (#13290)

  Core tool-calling for image-gen, handles requesting and receiving logic
  for images using response API

  Won Park · 2026-03-03 23:11:28 -08:00
  fa2306b303
• support 'flex' tier in app-server in addition to 'fast' (#13391)
  Val Kharitonov · 2026-03-03 22:46:05 -08:00
  4f6c4bb143
• core: box wrapper futures to reduce stack pressure (#13429)

  Follow-up to [#13388](https://github.com/openai/codex/pull/13388). This
  uses the same general fix pattern as
  [#12421](https://github.com/openai/codex/pull/12421), but in the
  `codex-core` compact/resume/fork path.
  
  ## Why
  
  `compact_resume_after_second_compaction_preserves_history` started
  overflowing the stack on Windows CI after `#13388`.
  
  The important part is that this was not a compaction-recursion bug. The
  test exercises a path with several thin `async fn` wrappers around much
  larger thread-spawn, resume, and fork futures. When one `async fn`
  awaits another inline, the outer future stores the callee future as part
  of its own state machine. In a long wrapper chain, that means a caller
  can accidentally inline a lot more state than the source code suggests.
  
  That is exactly what was happening here:
  
  - `ThreadManager` convenience methods such as `start_thread`,
  `resume_thread_from_rollout`, and `fork_thread` were inlining the larger
  spawn/resume futures beneath them.
  - `core_test_support::test_codex` added another wrapper layer on top of
  those same paths.
  - `compact_resume_fork` adds a few more helpers, and this particular
  test drives the resume/fork path multiple times.
  
  On Windows, that was enough to push both the libtest thread and Tokio
  worker threads over the edge. The previous 8 MiB test-thread workaround
  proved the failure was stack-related, but it did not address the
  underlying future size.
  
  ## How This Was Debugged
  
  The useful debugging pattern here was to turn the CI-only failure into a
  local low-stack repro.
  
  1. First, remove the explicit large-stack harness so the test runs on
  the normal `#[tokio::test]` path.
  2. Build the test binary normally.
  3. Re-run the already-built `tests/all` binary directly with
  progressively smaller `RUST_MIN_STACK` values.
  
  Running the built binary directly matters: it keeps the reduced stack
  size focused on the test process instead of also applying it to `cargo`
  and `rustc`.
  
  That made it possible to answer two questions quickly:
  
  - Does the failure still reproduce without the workaround? Yes.
  - Does boxing the wrapper futures actually buy back stack headroom? Also
  yes.
  
  After this change, the built test binary passes with
  `RUST_MIN_STACK=917504` and still overflows at `786432`, which is enough
  evidence to justify removing the explicit 8 MiB override while keeping a
  deterministic low-stack repro for future debugging.
  
  If we hit a similar issue again, the first places to inspect are thin
  `async fn` wrappers that mostly forward into a much larger async
  implementation.
  
  ## `Box::pin()` Primer
  
  `async fn` compiles into a state machine. If a wrapper does this:
  
  ```rust
  async fn wrapper() {
      inner().await;
  }
  ```
  
  then `wrapper()` stores the full `inner()` future inline as part of its
  own state.
  
  If the wrapper instead does this:
  
  ```rust
  async fn wrapper() {
      Box::pin(inner()).await;
  }
  ```
  
  then the child future lives on the heap, and the outer future only
  stores a pinned pointer to it. That usually trades one allocation for a
  substantially smaller outer future, which is exactly the tradeoff we
  want when the problem is stack pressure rather than raw CPU time.
  
  Useful references:
  
  -
  [`Box::pin`](https://doc.rust-lang.org/std/boxed/struct.Box.html#method.pin)
  - [Async book:
  Pinning](https://rust-lang.github.io/async-book/04_pinning/01_chapter.html)
  
  ## What Changed
  
  - Boxed the wrapper futures in `core/src/thread_manager.rs` around
  `start_thread`, `resume_thread_from_rollout`, `fork_thread`, and the
  corresponding `ThreadManagerState` spawn helpers so callers no longer
  inline the full spawn/resume state machine through multiple layers.
  - Boxed the matching test-only wrapper futures in
  `core/tests/common/test_codex.rs` and
  `core/tests/suite/compact_resume_fork.rs`, which sit directly on top of
  the same path.
  - Restored `compact_resume_after_second_compaction_preserves_history` in
  `core/tests/suite/compact_resume_fork.rs` to a normal `#[tokio::test]`
  and removed the explicit `TEST_STACK_SIZE_BYTES` thread/runtime sizing.
  - Simplified a tiny helper in `compact_resume_fork` by making
  `fetch_conversation_path()` synchronous, which removes one more
  unnecessary future layer from the test path.
  
  ## Verification
  
  - `cargo test -p codex-core --test all
  suite::compact_resume_fork::compact_resume_after_second_compaction_preserves_history
  -- --exact --nocapture`
  - `cargo test -p codex-core --test all suite::compact_resume_fork --
  --nocapture`
  - Re-ran the built `codex-core` `tests/all` binary directly with reduced
  stack sizes:
    - `RUST_MIN_STACK=917504` passes
    - `RUST_MIN_STACK=786432` still overflows
  - `cargo test -p codex-core`
  - Still fails locally in unrelated existing integration areas that
  expect the `codex` / `test_stdio_server` binaries or hit the existing
  `search_tool` wiremock mismatches.

  Michael Bolin · 2026-03-04 05:44:52 +00:00
  7134220f3c
• config: enforce enterprise feature requirements (#13388)

  ## Why
  
  Enterprises can already constrain approvals, sandboxing, and web search
  through `requirements.toml` and MDM, but feature flags were still only
  configurable as managed defaults. That meant an enterprise could suggest
  feature values, but it could not actually pin them.
  
  This change closes that gap and makes enterprise feature requirements
  behave like the other constrained settings. The effective feature set
  now stays consistent with enterprise requirements during config load,
  when config writes are validated, and when runtime code mutates feature
  flags later in the session.
  
  It also tightens the runtime API for managed features. `ManagedFeatures`
  now follows the same constraint-oriented shape as `Constrained<T>`
  instead of exposing panic-prone mutation helpers, and production code
  can no longer construct it through an unconstrained `From<Features>`
  path.
  
  The PR also hardens the `compact_resume_fork` integration coverage on
  Windows. After the feature-management changes,
  `compact_resume_after_second_compaction_preserves_history` was
  overflowing the libtest/Tokio thread stacks on Windows, so the test now
  uses an explicit larger-stack harness as a pragmatic mitigation. That
  may not be the ideal root-cause fix, and it merits a parallel
  investigation into whether part of the async future chain should be
  boxed to reduce stack pressure instead.
  
  ## What Changed
  
  Enterprises can now pin feature values in `requirements.toml` with the
  requirements-side `features` table:
  
  ```toml
  [features]
  personality = true
  unified_exec = false
  ```
  
  Only canonical feature keys are allowed in the requirements `features`
  table; omitted keys remain unconstrained.
  
  - Added a requirements-side pinned feature map to
  `ConfigRequirementsToml`, threaded it through source-preserving
  requirements merge and normalization in `codex-config`, and made the
  TOML surface use `[features]` (while still accepting legacy
  `[feature_requirements]` for compatibility).
  - Exposed `featureRequirements` from `configRequirements/read`,
  regenerated the JSON/TypeScript schema artifacts, and updated the
  app-server README.
  - Wrapped the effective feature set in `ManagedFeatures`, backed by
  `ConstrainedWithSource<Features>`, and changed its API to mirror
  `Constrained<T>`: `can_set(...)`, `set(...) -> ConstraintResult<()>`,
  and result-returning `enable` / `disable` / `set_enabled` helpers.
  - Removed the legacy-usage and bulk-map passthroughs from
  `ManagedFeatures`; callers that need those behaviors now mutate a plain
  `Features` value and reapply it through `set(...)`, so the constrained
  wrapper remains the enforcement boundary.
  - Removed the production loophole for constructing unconstrained
  `ManagedFeatures`. Non-test code now creates it through the configured
  feature-loading path, and `impl From<Features> for ManagedFeatures` is
  restricted to `#[cfg(test)]`.
  - Rejected legacy feature aliases in enterprise feature requirements,
  and return a load error when a pinned combination cannot survive
  dependency normalization.
  - Validated config writes against enterprise feature requirements before
  persisting changes, including explicit conflicting writes and
  profile-specific feature states that normalize into invalid
  combinations.
  - Updated runtime and TUI feature-toggle paths to use the constrained
  setter API and to persist or apply the effective post-constraint value
  rather than the requested value.
  - Updated the `core_test_support` Bazel target to include the bundled
  core model-catalog fixtures in its runtime data, so helper code that
  resolves `core/models.json` through runfiles works in remote Bazel test
  environments.
  - Renamed the core config test coverage to emphasize that effective
  feature values are normalized at runtime, while conflicting persisted
  config writes are rejected.
  - Ran `compact_resume_after_second_compaction_preserves_history` inside
  an explicit 8 MiB test thread and Tokio runtime worker stack, following
  the existing larger-stack integration-test pattern, to keep the Windows
  `compact_resume_fork` test slice from aborting while a parallel
  investigation continues into whether some of the underlying async
  futures should be boxed.
  
  ## Verification
  
  - `cargo test -p codex-config`
  - `cargo test -p codex-core feature_requirements_ -- --nocapture`
  - `cargo test -p codex-core
  load_requirements_toml_produces_expected_constraints -- --nocapture`
  - `cargo test -p codex-core
  compact_resume_after_second_compaction_preserves_history -- --nocapture`
  - `cargo test -p codex-core compact_resume_fork -- --nocapture`
  - Re-ran the built `codex-core` `tests/all` binary with
  `RUST_MIN_STACK=262144` for
  `compact_resume_after_second_compaction_preserves_history` to confirm
  the explicit-stack harness fixes the deterministic low-stack repro.
  - `cargo test -p codex-core`
  - This still fails locally in unrelated integration areas that expect
  the `codex` / `test_stdio_server` binaries or hit existing `search_tool`
  wiremock mismatches.
  
  ## Docs
  
  `developers.openai.com/codex` should document the requirements-side
  `[features]` table for enterprise and MDM-managed configuration,
  including that it only accepts canonical feature keys and that
  conflicting config writes are rejected.

  Michael Bolin · 2026-03-04 04:40:22 +00:00
  bfff0c729f
• feat: load plugin apps (#13401)

  load plugin-apps from `.app.json`.
  
  make apps runtime-mentionable iff `codex_apps` MCP actually exposes
  tools for that `connector_id`.
  
  if the app isn't available, it's filtered out of runtime connector set,
  so no tools are added and no app-mentions resolve.
  
  right now we don't have a clean cli-side error for an app not being
  installed. can look at this after.
  
  ### Tests
  Added tests, tested locally that using a plugin that bundles an app
  picks up the app.

  sayan-oai · 2026-03-03 16:29:15 -08:00
  082682a628
• Make js_repl image output controllable (#13331)

  ## Summary
  
  Instead of always adding inner function call outputs to the model
  context, let js code decide which ones to return.
  
  - Stop auto-hoisting nested tool outputs from `codex.tool(...)` into the
  outer `js_repl` function output.
  - Keep `codex.tool(...)` return values unchanged as structured JS
  objects.
  - Add `codex.emitImage(...)` as the explicit path for attaching an image
  to the outer `js_repl` function output.
  - Support emitting from a direct image URL, a single `input_image` item,
  an explicit `{ bytes, mimeType }` object, or a raw tool response object
  containing exactly one image.
  - Preserve existing `view_image` original-resolution behavior when JS
  emits the raw `view_image` tool result.
  - Suppress the special `ViewImageToolCall` event for `js_repl`-sourced
  `view_image` calls so nested inspection stays side-effect free until JS
  explicitly emits.
  - Update the `js_repl` docs and generated project instructions with both
  recommended patterns:
    - `await codex.emitImage(codex.tool("view_image", { path }))`
  - `await codex.emitImage({ bytes: await page.screenshot({ type: "jpeg",
  quality: 85 }), mimeType: "image/jpeg" })`
  
  #### [git stack](https://github.com/magus/git-stack-cli)
  - ✅ `1` https://github.com/openai/codex/pull/13050
  - 👉 `2` https://github.com/openai/codex/pull/13331
  - ⏳ `3` https://github.com/openai/codex/pull/13049

  Curtis 'Fjord' Hawthorne · 2026-03-03 16:25:59 -08:00
  c4cb594e73
• Add under-development original-resolution view_image support (#13050)

  ## Summary
  
  Add original-resolution support for `view_image` behind the
  under-development `view_image_original_resolution` feature flag.
  
  When the flag is enabled and the target model is `gpt-5.3-codex` or
  newer, `view_image` now preserves original PNG/JPEG/WebP bytes and sends
  `detail: "original"` to the Responses API instead of using the legacy
  resize/compress path.
  
  ## What changed
  
  - Added `view_image_original_resolution` as an under-development feature
  flag.
  - Added `ImageDetail` to the protocol models and support for serializing
  `detail: "original"` on tool-returned images.
  - Added `PromptImageMode::Original` to `codex-utils-image`.
    - Preserves original PNG/JPEG/WebP bytes.
    - Keeps legacy behavior for the resize path.
  - Updated `view_image` to:
  - use the shared `local_image_content_items_with_label_number(...)`
  helper in both code paths
    - select original-resolution mode only when:
      - the feature flag is enabled, and
      - the model slug parses as `gpt-5.3-codex` or newer
  - Kept local user image attachments on the existing resize path; this
  change is specific to `view_image`.
  - Updated history/image accounting so only `detail: "original"` images
  use the docs-based GPT-5 image cost calculation; legacy images still use
  the old fixed estimate.
  - Added JS REPL guidance, gated on the same feature flag, to prefer JPEG
  at 85% quality unless lossless is required, while still allowing other
  formats when explicitly requested.
  - Updated tests and helper code that construct
  `FunctionCallOutputContentItem::InputImage` to carry the new `detail`
  field.
  
  ## Behavior
  
  ### Feature off
  - `view_image` keeps the existing resize/re-encode behavior.
  - History estimation keeps the existing fixed-cost heuristic.
  
  ### Feature on + `gpt-5.3-codex+`
  - `view_image` sends original-resolution images with `detail:
  "original"`.
  - PNG/JPEG/WebP source bytes are preserved when possible.
  - History estimation uses the GPT-5 docs-based image-cost calculation
  for those `detail: "original"` images.
  
  
  #### [git stack](https://github.com/magus/git-stack-cli)
  - 👉 `1` https://github.com/openai/codex/pull/13050
  - ⏳ `2` https://github.com/openai/codex/pull/13331
  - ⏳ `3` https://github.com/openai/codex/pull/13049

  Curtis 'Fjord' Hawthorne · 2026-03-03 15:56:54 -08:00
  b92146d48b
• Refactor plugin config and cache path (#13333)

  Update config.toml plugin entries to use
  <plugin_name>@<marketplace_name> as the key.
  Plugin now stays in
  [plugins/cache/marketplace-name/plugin-name/$version/]
  Clean up the plugin code structure.
  Add plugin install functionality (not used yet).

  xl-openai · 2026-03-03 15:00:18 -08:00
  9b004e2db1
• Revert "Revert "realtime prompt changes"" (#13398)

  Reverts openai/codex#13385

  Ahmed Ibrahim · 2026-03-03 14:41:26 -08:00
  041c896509
• Build delegated realtime handoff text from all messages (#13395)

  ## Summary
  - Route delegated realtime handoff turns from all handoff message texts,
  preserving order
  - Fallback to input_transcript only when no messages are present
  - Add regression coverage for multi-message handoff requests

  Ahmed Ibrahim · 2026-03-03 14:07:51 -08:00
  6bee02a346
• Remove Responses V1 websocket implementation (#13364)

  V2 is the way to go!

  pakrym-oai · 2026-03-03 11:32:53 -07:00
  69df12efb3
• add fast mode toggle (#13212)

  - add a local Fast mode setting in codex-core (similar to how model id
  is currently stored on disk locally)
  - send `service_tier=priority` on requests when Fast is enabled
  - add `/fast` in the TUI and persist it locally
  - feature flag

  pash-openai · 2026-03-02 20:29:33 -08:00
  2f5b01abd6
• chore: remove SkillMetadata.permissions and derive skill sandboxing from permission_profile (#13061)

  ## Summary
  
  This change removes the compiled permissions field from skill metadata
  and keeps permission_profile as the single source of truth.
  
  Skill loading no longer compiles skill permissions eagerly. Instead, the
  zsh-fork skill escalation path compiles `skill.permission_profile` when
  it needs to determine the sandbox to apply for a skill script.
  
    ## Behavior change
  
    For skills that declare:
  ```
    permissions: {}
  ```
  we now treat that the same as having no skill permissions override,
  instead of creating and using a default readonly sandbox. This change
  makes the behavior more intuitive:
  
    - only non-empty skill permission profiles affect sandboxing
  - omitting permissions and writing permissions: {} now mean the same
  thing
  - skill metadata keeps a single permissions representation instead of
  storing derived state too
  
  Overall, this makes skill sandbox behavior easier to understand and more
  predictable.

  Celia Chen · 2026-03-03 01:29:53 +00:00
  0bb152b01d
• Update realtime websocket API (#13265)

  - migrate the realtime websocket transport to the new session and
  handoff flow
  - make the realtime model configurable in config.toml and use API-key
  auth for the websocket
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Ahmed Ibrahim · 2026-03-02 16:05:40 -08:00
  b20b6aa46f
• feat: update memories config names (#13237)
  jif-oai · 2026-03-02 15:25:39 +00:00
  1905597017
• feat: polluted memories (#13008)

  Add a feature flag to disable memory creation for "polluted"

  jif-oai · 2026-03-02 11:57:32 +00:00
  b649953845
• Record realtime close marker on replacement (#13058)

  ## Summary
  - record a realtime close developer message when a new realtime session
  replaces an active one
  - assert the replacement marker through the mocked responses request
  path
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>
  Co-authored-by: Charles Cunningham <ccunningham@openai.com>

  Ahmed Ibrahim · 2026-03-01 13:54:12 -08:00
  0aeb55bf08
• feat: load from plugins (#12864)

  Support loading plugins.
  
  Plugins can now be enabled via [plugins.<name>] in config.toml. They are
  loaded as first-class entities through PluginsManager, and their default
  skills/ and .mcp.json contributions are integrated into the existing
  skills and MCP flows.

  xl-openai · 2026-03-01 10:50:56 -08:00
  752402c4fe
• core: adopt host_executable() rules in zsh-fork (#13046)

  ## Why
  
  [#12964](https://github.com/openai/codex/pull/12964) added
  `host_executable()` support to `codex-execpolicy`, but the zsh-fork
  interception path in `unix_escalation.rs` was still evaluating commands
  with the default exact-token matcher.
  
  That meant an intercepted absolute executable such as `/usr/bin/git
  status` could still miss basename rules like `prefix_rule(pattern =
  ["git", "status"])`, even when the policy also defined a matching
  `host_executable(name = "git", ...)` entry.
  
  This PR adopts the new matching behavior in the zsh-fork runtime only.
  That keeps the rollout intentionally narrow: zsh-fork already requires
  explicit user opt-in, so it is a safer first caller to exercise the new
  `host_executable()` scheme before expanding it to other execpolicy call
  sites.
  
  It also brings zsh-fork back in line with the current `prefix_rule()`
  execution model. Until prefix rules can carry their own permission
  profiles, a matched `prefix_rule()` is expected to rerun the intercepted
  command unsandboxed on `allow`, or after the user accepts `prompt`,
  instead of merely continuing inside the inherited shell sandbox.
  
  ## What Changed
  
  - added `evaluate_intercepted_exec_policy()` in
  `core/src/tools/runtimes/shell/unix_escalation.rs` to centralize
  execpolicy evaluation for intercepted commands
  - switched intercepted direct execs in the zsh-fork path to
  `check_multiple_with_options(...)` with `MatchOptions {
  resolve_host_executables: true }`
  - added `commands_for_intercepted_exec_policy()` so zsh-fork policy
  evaluation works from intercepted `(program, argv)` data instead of
  reconstructing a synthetic command before matching
  - left shell-wrapper parsing intentionally disabled by default behind
  `ENABLE_INTERCEPTED_EXEC_POLICY_SHELL_WRAPPER_PARSING`, so
  path-sensitive matching relies on later direct exec interception rather
  than shell-script parsing
  - made matched `prefix_rule()` decisions rerun intercepted commands with
  `EscalationExecution::Unsandboxed`, while unmatched-command fallback
  keeps the existing sandbox-preserving behavior
  - extracted the zsh-fork test harness into
  `core/tests/common/zsh_fork.rs` so both the skill-focused and
  approval-focused integration suites can exercise the same runtime setup
  - limited this change to the intercepted zsh-fork path rather than
  changing every execpolicy caller at once
  - added runtime coverage in
  `core/src/tools/runtimes/shell/unix_escalation_tests.rs` for allowed and
  disallowed `host_executable()` mappings and the wrapper-parsing modes
  - added integration coverage in `core/tests/suite/approvals.rs` to
  verify a saved `prefix_rule(pattern=["touch"], decision="allow")` reruns
  under zsh-fork outside a restrictive `WorkspaceWrite` sandbox
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/13046).
  * #13065
  * __->__ #13046

  Michael Bolin · 2026-02-28 01:41:23 +00:00
  1a8d930267
• Unify rollout reconstruction with resume/fork TurnContext hydration (#12612)

  ## Summary
  
  This PR unifies rollout history reconstruction and resume/fork metadata
  hydration under a single `Session::reconstruct_history_from_rollout`
  implementation.
  
  The key change from main is that replay metadata now comes from the same
  reconstruction pass that rebuilds model-visible history, instead of
  doing a second bespoke rollout scan to recover `previous_model` /
  `reference_context_item`.
  
  ## What Changed
  
  ### Unified reconstruction output
  
  `reconstruct_history_from_rollout` now returns a single
  `RolloutReconstruction` bundle containing:
  
  - rebuilt `history`
  - `previous_model`
  - `reference_context_item`
  
  Resume and fork both consume that shared output directly.
  
  ### Reverse replay core
  
  The reconstruction logic moved into
  `codex-rs/core/src/codex/rollout_reconstruction.rs` and now scans
  rollout items newest-to-oldest.
  
  That reverse pass:
  
  - derives `previous_model`
  - derives whether `reference_context_item` is preserved or cleared
  - stops early once it has both resume metadata and a surviving
  `replacement_history` checkpoint
  
  History materialization is still bridged eagerly for now by replaying
  only the surviving suffix forward, which keeps the history result stable
  while moving the control flow toward the future lazy reverse loader
  design.
  
  ### Removed bespoke context lookup
  
  This deletes `last_rollout_regular_turn_context_lookup` and its separate
  compaction-aware scan.
  
  The previous model / baseline metadata is now computed from the same
  replay state that rebuilds history, so resume/fork cannot drift from the
  reconstructed transcript view.
  
  ### `TurnContextItem` persistence contract
  
  `TurnContextItem` is now treated as the replay source of truth for
  durable model-visible baselines.
  
  This PR keeps the following contract explicit:
  
  - persist `TurnContextItem` for the first real user turn so resume can
  recover `previous_model`
  - persist it for later turns that emit model-visible context updates
  - if mid-turn compaction reinjects full initial context into replacement
  history, persist a fresh `TurnContextItem` after `Compacted` so
  resume/fork can re-establish the baseline from the rewritten history
  - do not treat manual compaction or pre-sampling compaction as creating
  a new durable baseline on their own
  
  ## Behavior Preserved
  
  - rollback replay stays aligned with `drop_last_n_user_turns`
  - rollback skips only user turns
  - incomplete active user turns are dropped before older finalized turns
  when rollback applies
  - unmatched aborts do not consume the current active turn
  - missing abort IDs still conservatively clear stale compaction state
  - compaction clears `reference_context_item` until a later
  `TurnContextItem` re-establishes it
  - `previous_model` still comes from the newest surviving user turn that
  established one
  
  ## Tests
  
  Targeted validation run for the current branch shape:
  
  - `cd codex-rs && cargo test -p codex-core --lib
  codex::rollout_reconstruction_tests -- --nocapture`
  - `cd codex-rs && just fmt`
  
  The branch also extracts the rollout reconstruction tests into
  `codex-rs/core/src/codex/rollout_reconstruction_tests.rs` so this logic
  has a dedicated home instead of living inline in `codex.rs`.

  Charley Cunningham · 2026-02-27 13:50:45 -08:00
  695957a348
• fix: use AbsolutePathBuf for permission profile file roots (#12970)

  ## Why
  `PermissionProfile` should describe filesystem roots as absolute paths
  at the type level. Using `PathBuf` in `FileSystemPermissions` made the
  shared type too permissive and blurred together three different
  deserialization cases:
  
  - skill metadata in `agents/openai.yaml`, where relative paths should
  resolve against the skill directory
  - app-server API payloads, where callers should have to send absolute
  paths
  - local tool-call payloads for commands like `shell_command` and
  `exec_command`, where `additional_permissions.file_system` may
  legitimately be relative to the command `workdir`
  
  This change tightens the shared model without regressing the existing
  local command flow.
  
  ## What Changed
  - changed `protocol::models::FileSystemPermissions` and the app-server
  `AdditionalFileSystemPermissions` mirror to use `AbsolutePathBuf`
  - wrapped skill metadata deserialization in `AbsolutePathBufGuard`, so
  relative permission roots in `agents/openai.yaml` resolve against the
  containing skill directory
  - kept app-server/API deserialization strict, so relative
  `additionalPermissions.fileSystem.*` paths are rejected at the boundary
  - restored cwd/workdir-relative deserialization for local tool-call
  payloads by parsing `shell`, `shell_command`, and `exec_command`
  arguments under an `AbsolutePathBufGuard` rooted at the resolved command
  working directory
  - simplified runtime additional-permission normalization so it only
  canonicalizes and deduplicates absolute roots instead of trying to
  recover relative ones later
  - updated the app-server schema fixtures, `app-server/README.md`, and
  the affected transport/TUI tests to match the final behavior

  Michael Bolin · 2026-02-27 17:42:52 +00:00
  d09a7535ed
• fix: more stable notify script (#13011)
  jif-oai · 2026-02-27 16:05:44 +01:00
  8cf5b00aef