3310 Commits

• chore: make token usage async (#23305)

  Make the `TokenUsageContributor` async. This will be required for future
  extension and it's basically free

  jif-oai · 2026-05-18 15:59:06 +02:00
  b631d92170
• chore: goal resumed metrics (#23301)

  Add metrics for goal resume

  jif-oai · 2026-05-18 15:19:23 +02:00
  500ef67ed1
• chore: isolate thread goal storage behind GoalStore (#23295)

  ## Why
  
  Thread goal persistence is being prepared for a dedicated storage
  boundary. Before that split, goal-specific reads, writes, accounting,
  and cleanup were exposed directly on `StateRuntime`, so core and
  app-server callsites stayed coupled to the full runtime instead of a
  goal-specific store.
  
  This PR introduces that boundary without changing the goal wire API or
  current persistence behavior. Callers now go through
  `StateRuntime::thread_goals()` and the new `GoalStore`, while
  `GoalStore` still uses the existing state DB pool underneath.
  
  ## What changed
  
  - Added `GoalStore` in `state/src/runtime/goals.rs` and exposed it from
  `StateRuntime` via `thread_goals()`.
  - Moved thread-goal reads, writes, status updates, pause, delete, and
  usage accounting onto `GoalStore`.
  - Updated core session goal handling, app-server goal RPCs, resume
  snapshots, and goal tests to use the store boundary.
  - Kept thread deletion responsible for cascading goal cleanup by
  deleting the goal through the store only after a thread row is removed.
  
  ## Testing
  
  - Existing goal persistence, resume, and accounting tests were updated
  to exercise the new `GoalStore` access path.

  jif-oai · 2026-05-18 14:47:05 +02:00
  7ee7fe239f
• Make extension lifecycle hooks async (#23291)

  ## Why
  
  Extension lifecycle hooks sit on the host/extension boundary, but the
  current trait surface only allows synchronous callbacks. That forces
  extensions that need to seed, rehydrate, observe, or flush
  extension-owned state during thread and turn transitions to either block
  inside the callback or move async work into separate host plumbing.
  
  This PR makes those lifecycle callbacks awaitable so extension
  implementations can perform async work directly at the lifecycle point
  where the host already has the relevant session, thread, or turn stores
  available.
  
  ## What changed
  
  - Makes `ThreadLifecycleContributor` and `TurnLifecycleContributor`
  async in `codex-extension-api`.
  - Awaits thread start/resume/stop and turn start/stop/abort lifecycle
  callbacks from `codex-core`.
  - Updates the guardian and memories extensions to implement the async
  lifecycle trait surface.
  - Updates the existing lifecycle tests to use async contributor
  implementations.
  - Adds `async-trait` to the crates that now expose or implement these
  async object-safe lifecycle traits.
  
  ## Testing
  
  - Existing `codex-core` lifecycle tests were updated to cover async
  implementations for thread stop and turn abort ordering.

  jif-oai · 2026-05-18 13:53:58 +02:00
  9531e932ef
• test: reduce core sandbox policy test setup (#23036)

  ## Why
  
  `SandboxPolicy` is a legacy compatibility shape, but several core tests
  still used it for ordinary turn setup even when the runtime path now
  carries `PermissionProfile`. With the first cleanup PR merged, this
  follow-up trims more core test scaffolding so remaining `SandboxPolicy`
  matches are easier to classify as production compatibility,
  legacy-boundary coverage, or explicit conversion tests.
  
  ## What Changed
  
  - Updated apply-patch handler and runtime tests to pass
  `PermissionProfile` directly.
  - Changed sandboxing test helpers to build permission profiles without
  first creating `SandboxPolicy` values.
  - Converted request-permissions integration turns to pass
  `PermissionProfile` through the test helper, leaving legacy sandbox
  projection at the `Op::UserTurn` boundary.
  - Converted unified exec integration helpers and direct turn submissions
  to use `PermissionProfile` values instead of `SandboxPolicy` setup.
  - Removed now-unused `SandboxPolicy` imports from the touched core
  tests.
  
  ## Test Plan
  
  - `just fmt`
  - `cargo test -p codex-core --lib tools::sandboxing::tests`
  - `cargo test -p codex-core --lib tools::runtimes::apply_patch::tests`
  - `cargo test -p codex-core --lib tools::handlers::apply_patch::tests`
  - `cargo test -p codex-core --lib unified_exec::process_manager::tests`
  - `cargo test -p codex-core --test all request_permissions::`
  - `cargo test -p codex-core --test all unified_exec::`
  - `just fix -p codex-core`

  Michael Bolin · 2026-05-17 08:39:41 -07:00
  0a83353ca3
• Make multi-agent v2 tool namespace configurable (#23147)

  ## Summary
  - Add `features.multi_agent_v2.tool_namespace` with config/schema
  validation for Responses-compatible namespace values.
  - Thread the resolved namespace into `ToolsConfig` for normal turns and
  review turns.
  - Wrap MultiAgentV2 tool specs and registry names in the configured
  namespace when namespace tools are supported, while falling back to the
  plain tool names when they are not.
  
  ## Validation
  - `just fmt`
  - `just write-config-schema`
  - `cargo test -p codex-features multi_agent_v2_feature_config --
  --nocapture`
  - `cargo test -p codex-core test_build_specs_multi_agent_v2 --
  --nocapture`
  - `cargo test -p codex-core multi_agent_v2_config -- --nocapture`
  - `cargo test -p codex-core
  multi_agent_v2_rejects_invalid_tool_namespace -- --nocapture`
  - `cargo test -p codex-tools`
  - `git diff --check`

  jif-oai · 2026-05-17 15:27:43 +02:00
  545ede569c
• multiagent: trim model-visible description, cap to 5 models (#23069)

  ## Why
  
  The `spawn_agent` model override guidance is uncapped and bloating
  context. We need to trim down each entry and cap total entries.
  
  picked 5 as cap, we can change
  
  ## What changed
  
  - Cap the model override summaries shown in `spawn_agent` to the first 5
  picker-visible models, preserving the existing priority ordering from
  the models manager.
  - Condense each rendered entry to the actionable pieces the model needs:
    - use the model slug as the label
    - render compact reasoning effort lists with the default marked inline
  - render only service tier IDs, and omit the clause when no tiers are
  available
  - Update coverage so the compact formatter shape and the top-5 cap are
  exercised, and keep the end-to-end request assertion aligned with real
  model metadata.
  
  ## Example
  
  Before:
  
  `- gpt-5.4 ('gpt-5.4\'): Strong model for everyday coding. Default
  reasoning effort: medium. Supported reasoning efforts: low (Fast
  responses with lighter reasoning), medium (Balances speed and reasoning
  depth for everyday tasks), high (Greater reasoning depth for complex
  problems), xhigh (Extra high reasoning depth for complex problems).
  Supported service tiers: priority (Fast: 1.5x speed, increased usage).`
  
  After:
  
  `- 'gpt-5.4': Strong model for everyday coding. Reasoning efforts: low,
  medium (default), high, xhigh. Service tiers: priority.`

  sayan-oai · 2026-05-16 13:43:30 -07:00
  061a614d85
• test: construct permission profiles directly (#23030)

  ## Why
  
  `SandboxPolicy` is now a legacy compatibility shape, but several tests
  still built a `SandboxPolicy` only to immediately convert it into
  `PermissionProfile` for APIs that already accept canonical runtime
  permissions. Those detours make it harder to audit where legacy sandbox
  policy is still required, because boundary-only usages are mixed
  together with ordinary test setup.
  
  ## What Changed
  
  - Updated tests in `codex-core`, `codex-exec`, `codex-analytics`, and
  `codex-config` to construct `PermissionProfile` values directly when the
  code under test takes a permission profile.
  - Changed exec-policy, request-permissions, session, and sandbox test
  helpers to pass `PermissionProfile` through instead of converting from
  `SandboxPolicy` internally.
  - Left `SandboxPolicy` in place where tests are explicitly exercising
  legacy compatibility or request/response boundaries.
  
  ## Test Plan
  
  - `cargo test -p codex-analytics -p codex-config`
  - `cargo test -p codex-core --lib safety::tests`
  - `cargo test -p codex-core --lib exec_policy::tests::`
  - `cargo test -p codex-core --lib exec::tests`
  - `cargo test -p codex-core --lib guardian_review_session_config`
  - `cargo test -p codex-core --lib tools::network_approval::tests`
  - `cargo test -p codex-core --lib
  tools::runtimes::shell::unix_escalation::tests`
  - `cargo test -p codex-core --lib managed_network`
  - `cargo test -p codex-core --test all request_permissions::`
  - `cargo test -p codex-exec sandbox`
  
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/23030).
  * #23036
  * __->__ #23030

  Michael Bolin · 2026-05-16 12:12:37 -07:00
  d91bc15618
• Improve goal completion usage reporting (#22907)

  ## Why
  
  Goal completion follow-up turns currently receive a preformatted English
  usage sentence such as `time used: 2586 seconds`. That nudges the model
  to echo an awkward raw seconds count in the final reply, even though the
  tool result already exposes structured usage fields like
  `goal.timeUsedSeconds`, `goal.tokensUsed`, and `goal.tokenBudget`.
  
  ## What changed
  
  - Replace the preformatted completion usage sentence with guidance to
  read the structured goal fields from the tool result.
  - Preserve token-budget reporting while allowing the model to phrase
  elapsed time in a concise, human-friendly way that fits the response
  language.
  - Update core coverage for both the generated completion guidance and
  the session flow that forwards it back to the model.
  
  ## Verification
  
  Previously, it would have output a final message indicating that it
  "worked for 303 seconds". Now it shows the following:
  
  <img width="286" height="35" alt="image"
  src="https://github.com/user-attachments/assets/d7011880-9449-46a7-856f-4e50ae00eb45"
  />

  Eric Traut · 2026-05-16 11:49:40 -07:00
  941e7f825e
• core: set permission profiles from snapshots (#22920)

  ## Why
  
  #22891 moved the TUI turn-command path to pass `ActivePermissionProfile`
  instead of the full `PermissionProfile`, but the remaining
  config/session bridge still accepted the concrete `PermissionProfile`
  and active profile id as separate arguments. That shape made it too easy
  for future callers to update the concrete profile and active profile id
  out of sync.
  
  This PR makes the trusted session snapshot path pass one coherent value
  into `Permissions`, while keeping `requirements.toml` enforcement owned
  by the existing constrained permission state.
  
  ## What Changed
  
  - Added `PermissionProfileSnapshot` as the public snapshot value for
  trusted session/config synchronization.
  - Changed `Permissions::set_permission_profile_from_session_snapshot()`
  and `replace_permission_profile_from_session_snapshot()` to take a
  `PermissionProfileSnapshot`.
  - Updated the replacement path to derive its constrained
  `PermissionProfile` from the snapshot, so callers cannot pass a separate
  profile that disagrees with the snapshot.
  - Removed the internal tuple-style
  `PermissionProfileState::set_active_permission_profile()` mutation path.
  - Updated core session projection and TUI call sites to construct
  explicit legacy or active snapshots.
  - Documented the snapshot constructors so legacy use and id/profile
  mismatch hazards are called out at the API boundary.
  - Added a focused config test that verifies snapshot updates still
  respect existing permission constraints.
  
  ## How To Review
  
  1. Start with `codex-rs/core/src/config/resolved_permission_profile.rs`;
  `PermissionProfileSnapshot` is the public wrapper, while
  `ResolvedPermissionProfile` stays internal.
  2. Check `codex-rs/core/src/config/mod.rs` to confirm both
  session-snapshot setters validate through `PermissionProfileState` and
  no longer accept loose profile/id pairs.
  3. Skim `codex-rs/core/src/session/session.rs` for the session
  projection path; it now builds the snapshot before installing it.
  4. Skim the TUI changes as call-site migration from loose argument pairs
  to explicit snapshot construction.
  
  ## Verification
  
  - `cargo test -p codex-core
  permission_snapshot_setter_preserves_permission_constraints`
  - `cargo test -p codex-tui status_permissions_`
  - `cargo test -p codex-tui
  session_configured_preserves_profile_workspace_roots`
  - `just fix -p codex-core -p codex-tui`

  Michael Bolin · 2026-05-16 07:26:18 -07:00
  108234b5eb
• Preserve image detail in app-server inputs (#20693)

  ## Summary
  
  - Add optional image detail to user image inputs across core, app-server
  v2, thread history/event mapping, and the generated app-server
  schemas/types.
  - Preserve requested detail when serializing Responses image inputs:
  omitted detail stays on the existing `high` default, while explicit
  `original` keeps local images on the original-resolution path.
  - Support `high`/`original` consistently for tool image outputs,
  including MCP `codex/imageDetail`, code-mode image helpers, and
  `view_image`.

  Curtis 'Fjord' Hawthorne · 2026-05-15 15:04:04 -07:00
  8543e39885
• core: construct test permission profiles directly (#22795)

  ## Why
  
  The core migration is trying to make `PermissionProfile` the shape tests
  and runtime code reason about, leaving `SandboxPolicy` only where legacy
  behavior is explicitly under test. The local
  `permission_profile_for_sandbox_policy()` test helpers kept new
  permission-profile tests mentally tied to the old sandbox model even
  when the equivalent profile is straightforward.
  
  ## What Changed
  
  - Removed the `permission_profile_for_sandbox_policy()` helper from the
  network proxy spec tests and session tests.
  - Replaced legacy conversions for read-only, workspace-write, and
  full-access cases with `PermissionProfile::read_only()`,
  `PermissionProfile::workspace_write()`, and
  `PermissionProfile::Disabled`.
  - Constructed the external-sandbox session test's
  `PermissionProfile::External` directly, while preserving the legacy
  `SandboxPolicy` only where the test still exercises legacy config update
  behavior.
  
  ## How To Review
  
  This PR is intentionally test-only. Review the two touched files and
  check that each replacement preserves the old legacy mapping:
  
  - `SandboxPolicy::new_read_only_policy()` ->
  `PermissionProfile::read_only()`
  - `SandboxPolicy::new_workspace_write_policy()` ->
  `PermissionProfile::workspace_write()`
  - `SandboxPolicy::DangerFullAccess` -> `PermissionProfile::Disabled`
  - `SandboxPolicy::ExternalSandbox { network_access: Restricted }` ->
  `PermissionProfile::External { network: Restricted }`
  
  ## Verification
  
  - `cargo test -p codex-core
  requirements_allowed_domains_are_a_baseline_for_user_allowlist`
  - `cargo test -p codex-core
  start_managed_network_proxy_applies_execpolicy_network_rules`
  - `cargo test -p codex-core
  session_configured_reports_permission_profile_for_external_sandbox`
  - `cargo test -p codex-core
  managed_network_proxy_decider_survives_full_access_start`
  - `just fix -p codex-core`
  
  
  
  
  
  
  
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/22795).
  * #22891
  * __->__ #22795

  Michael Bolin · 2026-05-15 13:09:25 -07:00
  8df2d96860
• Forward apps MCP product SKU from Codex config (#22872)

  This adds `apps_mcp_product_sku` as a toplevel config.toml key. We pass
  the given value as a header when listing MCPs for the client, allowing
  connectors to be filtered per product entry point.
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Boyang Niu · 2026-05-15 11:52:14 -07:00
  c15613f2b6
• telemetry: tag sandboxes from permission profiles (#22791)

  ## Why
  
  Sandbox telemetry tags should be derived from the active permission
  profile, not from a legacy `SandboxPolicy`, so the tagging code stays
  aligned with the permissions migration and does not preserve a
  policy-shaped production helper only for tests.
  
  ## What Changed
  
  - Removed the production `sandbox_tag(&SandboxPolicy, ...)` helper.
  - Updated sandbox tag tests to construct the relevant
  `PermissionProfile` values directly.
  - Kept the platform-specific sandbox tag behavior under the existing
  `permission_profile_sandbox_tag` path.
  
  ## How To Review
  
  The production change is in `codex-rs/core/src/sandbox_tags.rs`. Most of
  the diff is test cleanup that replaces legacy policy setup with
  permission profiles, so review the expected tag assertions rather than
  the old helper mechanics.
  
  ## Verification
  
  - `cargo test -p codex-core sandbox_tag`
  
  
  
  
  
  
  
  
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/22791).
  * #22795
  * #22792
  * __->__ #22791

  Michael Bolin · 2026-05-15 10:58:50 -07:00
  4c80435eba
• context: remove legacy permissions instructions helper (#22790)

  ## Why
  
  The permissions instruction builder should consume the new permissions
  model directly. Keeping a `SandboxPolicy` conversion helper in this path
  encourages new code to route through legacy sandbox policy values even
  when the caller already has a `PermissionProfile`.
  
  ## What Changed
  
  - Removed `PermissionsInstructions::from_policy`.
  - Removed the test that exercised that legacy helper.
  - Left the existing profile-based instruction coverage in place.
  
  ## How To Review
  
  Review `codex-rs/core/src/context/permissions_instructions.rs` first.
  This PR is intentionally narrow: the production behavior should be
  unchanged for profile callers, and the deleted surface was only a
  convenience adapter from `SandboxPolicy`.
  
  ## Verification
  
  - `cargo test -p codex-core builds_permissions_from_profile`
  
  
  
  
  
  
  
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/22790).
  * #22795
  * #22792
  * #22791
  * __->__ #22790

  Michael Bolin · 2026-05-15 10:11:16 -07:00
  aeca1cba6f
• Ignore configured hooks in git helpers (#22843)

  ## What
  - Internal Git helper commands now ignore configured hook directories
  during repository bookkeeping.
  
  ## Why
  - These helper flows should stay consistent even when a repository has
  hook-directory configuration of its own.
  
  ## How
  - Pass a command-local `core.hooksPath` override in the shared helper
  path and the Git-info helper path.
  - Add regressions for the baseline index rewrite flow and the metadata
  status flow.
  
  ## Validation
  - `cargo fmt --manifest-path
  /Users/bookholt/code/codex/codex-rs/Cargo.toml --all --check`
  - `cargo test --manifest-path
  /Users/bookholt/code/codex/codex-rs/Cargo.toml -p codex-git-utils`
  - `cargo test --manifest-path
  /Users/bookholt/code/codex/codex-rs/Cargo.toml -p codex-core
  test_get_has_changes_`

  Chris Bookholt · 2026-05-15 10:07:54 -07:00
  9facdccb37
• guardian: use permission profile for review sandbox (#22789)

  ## Why
  
  `SandboxPolicy` is being pushed back toward legacy config loading and
  compatibility boundaries. Guardian review sessions already want the
  built-in read-only permission behavior; carrying that as an active
  `PermissionProfile` makes the review sandbox follow the new permissions
  path instead of configuring the child session through the legacy policy
  API.
  
  ## What Changed
  
  - Configure the guardian review session with
  `PermissionProfile::read_only()`.
  - Send the read-only profile through the guardian child `Op::UserTurn`.
  - Keep the legacy `sandbox_policy` field populated with
  `SandboxPolicy::new_read_only_policy()` declared next to the profile so
  the two remain visibly in sync until the compatibility field goes away.
  
  ## How To Review
  
  Start in `codex-rs/core/src/guardian/review_session.rs`. The important
  check is that both the guardian config and the child turn now use the
  read-only permission profile, while the remaining
  `SandboxPolicy::ReadOnly` assignment is only the compatibility field
  required by the current turn protocol.
  
  ## Verification
  
  - `cargo test -p codex-core
  guardian_review_session_config_clears_parent_developer_instructions`
  
  
  
  
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/22789).
  * #22795
  * #22792
  * #22791
  * #22790
  * __->__ #22789

  Michael Bolin · 2026-05-15 08:59:31 -07:00
  68ccfdc905
• Move memory prompt injection to app-server extension (#22841)

  ## Why
  
  Memory prompt injection should be owned by the extension path that
  app-server composes at runtime, not by an inlined special case inside
  `codex-core`. This keeps `codex-core` focused on session orchestration
  while allowing the memories extension to own its app-server prompt
  behavior.
  
  ## What Changed
  
  - Registers `codex-memories-extension` in the app-server extension
  registry.
  - Moves the memory developer-instruction injection out of
  `core/src/session/mod.rs` and into the memories extension prompt
  contributor.
  - Adds config-change handling so the extension keeps its per-thread
  memory settings in sync after startup.
  - Leaves memories read/retrieval tools unregistered for now so this PR
  only changes prompt injection.
  - Removes the stale `cargo-shear` ignore now that app-server depends on
  the extension crate.
  
  ## Validation
  
  Not run locally; validation is left to CI.

  jif-oai · 2026-05-15 16:19:34 +02:00
  cccde930ce
• Run compact hooks for remote compaction v2 (#22828)

  ## Why
  
  Remote compaction v2 is the `/responses` implementation of
  session-history compaction, but it still needs to preserve the
  observable contract of the legacy `/responses/compact` path. In
  particular, users and integrations that rely on `PreCompact` and
  `PostCompact` hooks should not see different behavior when
  `remote_compaction_v2` is enabled.
  
  ## What Changed
  
  - Runs `PreCompact` before issuing the remote compaction v2 request,
  including `Interrupted` analytics when a pre-hook stops execution.
  - Runs `PostCompact` after a successful v2 compaction and aborts the
  turn if the post-hook stops execution.
  - Adds `compact_remote_parity` coverage that compares legacy and v2
  compaction across manual transcript shapes, automatic pre-turn
  compaction, automatic mid-turn compaction, hook payloads, replacement
  history, follow-up request payloads, and API-key `service_tier=fast`
  behavior.
  - Registers the new parity suite under `core/tests/suite`.
  
  Relevant code:
  
  -
  [`compact_remote_v2.rs`](https://github.com/openai/codex/blob/af63745cb502183a6fc447d0240f8150934d70b7/codex-rs/core/src/compact_remote_v2.rs)
  -
  [`compact_remote_parity.rs`](https://github.com/openai/codex/blob/af63745cb502183a6fc447d0240f8150934d70b7/codex-rs/core/tests/suite/compact_remote_parity.rs)
  
  ## Verification
  
  - Added `core/tests/suite/compact_remote_parity.rs` to assert parity
  between legacy remote compaction and remote compaction v2 for the
  affected request, hook, rollout-history, and follow-up paths.
  - Existing `compact_remote_v2` unit coverage still exercises v2
  replacement-history retention and compaction-output collection.

  jif-oai · 2026-05-15 15:26:21 +02:00
  5d30764fe9
• Remove zombie tools spec module (#22820)

  ## Summary
  
  - move tool_user_shell_type out of the old tools::spec module and call
  it from tools directly
  - attach the remaining spec planning model tests under spec_plan
  - delete core/src/tools/spec.rs
  
  ## Tests
  
  - just fmt
  - cargo test -p codex-core tools::spec_plan
  
  Note: a broader cargo test -p codex-core run on the earlier PR-head
  worktree still hit the pre-existing stack overflow in
  agent::control::tests::spawn_agent_fork_last_n_turns_keeps_only_recent_turns.

  jif-oai · 2026-05-15 13:44:58 +02:00
  c03cea4ca2
• Simplify tool executor and registry plumbing (#22636)

  ## Why
  
  The tool runtime path still had a typed output associated type on
  `ToolExecutor`, plus a core-only `RegisteredTool` adapter and
  extension-only executor aliases. That made every new shared tool runtime
  carry extra adapter plumbing before it could participate in core
  dispatch, extension tools, hook payloads, telemetry, and model-visible
  spec generation.
  
  This PR moves output erasure to the shared executor boundary so core and
  extension tools can use the same execution contract directly.
  
  ## What Changed
  
  - Changed `codex_tools::ToolExecutor` to return `Box<dyn ToolOutput>`
  instead of an associated `Output` type.
  - Removed the extension-specific `ExtensionToolExecutor` /
  `ExtensionToolOutput` aliases and exposed `ToolExecutor<ToolCall>` plus
  `ToolOutput` through `codex-extension-api`.
  - Reworked core tool registration around `CoreToolRuntime` and
  `ToolRegistry::from_tools`, removing the extra `RegisteredTool` /
  `ToolRegistryBuilder` layer.
  - Consolidated model-visible spec planning and registry construction in
  `core/src/tools/spec_plan.rs`, including deferred tool search and
  code-mode-only filtering.
  - Added `ToolOutput` helpers for post-tool-use hook ids and inputs so
  MCP, unified exec, extension, and other boxed outputs preserve the same
  hook payload behavior.
  - Updated core handlers, memories tools, and the related
  registry/spec/router tests to use the simplified contract.
  
  ## Test Coverage
  
  - Updated coverage for tool spec planning, registry lookup, deferred
  tool search registration, extension tool routing, post-tool-use hook
  payloads, dispatch tracing, guardian output extraction, and memories
  extension tool execution.

  jif-oai · 2026-05-15 11:47:54 +02:00
  6f1a01fbdd
• [codex] Use compaction_trigger item for remote compaction v2 (#22809)

  ## Why
  
  Remote compaction v2 was still using `context_compaction` as both the
  request trigger and the compacted output shape. The Responses API now
  has the landed contract for this flow: Codex sends a dedicated `{
  "type": "compaction_trigger" }` input item, and the backend returns the
  standard `compaction` output item with encrypted content.
  
  This aligns the v2 path with that wire contract while preserving the
  existing local compacted-history post-processing behavior.
  
  ## What changed
  
  - Add `ResponseItem::CompactionTrigger` and regenerate the app-server
  protocol schema fixtures.
  - Send `compaction_trigger` from `remote_compaction_v2` instead of a
  payload-less `context_compaction`.
  - Collect exactly one backend `compaction` output item, then reuse the
  existing compacted-history rebuilding path.
  - Treat the trigger item as a transient request marker rather than model
  output or persisted rollout/memory content.
  
  ## Verification
  
  - `cargo test -p codex-protocol compaction_trigger`
  - `cargo test -p codex-core remote_compact_v2`
  - `cargo test -p codex-core compact_remote_v2`
  - `cargo test -p codex-core
  responses_websocket_sends_response_processed_after_remote_compaction_v2`
  - `just write-app-server-schema`
  - `cargo test -p codex-app-server-protocol schema_fixtures`

  jif-oai · 2026-05-15 11:40:35 +02:00
  0322ac3df8
• app-server: use permission ids and runtime workspace roots (#22611)

  ## Why
  
  This PR builds on [#22610](https://github.com/openai/codex/pull/22610)
  and is the app-server side of the migration from mutable per-turn
  `SandboxPolicy` replacement toward selecting immutable permission
  profiles by id plus mutable runtime workspace roots.
  
  Once permission profiles can carry their own immutable
  `workspace_roots`, app-server no longer needs to mutate the selected
  `PermissionProfile` just to represent thread-specific filesystem
  context. The mutable part now lives on the thread as explicit
  `runtimeWorkspaceRoots`, while `:workspace_roots` remains symbolic until
  the sandbox is realized for a turn.
  
  ## What Changed
  
  - Replaced the v2 permission-selection wrapper surface with plain
  profile ids for `thread/start`, `thread/resume`, `thread/fork`, and
  `turn/start`.
  - Removed the API surface for profile modifications
  (`PermissionProfileSelectionParams`,
  `PermissionProfileModificationParams`,
  `ActivePermissionProfileModification`).
  - Added experimental `runtimeWorkspaceRoots` fields to the thread
  lifecycle and turn-start APIs.
  - Threaded runtime workspace roots through core session/thread
  snapshots, turn overrides, app-server request handling, and command
  execution permission resolution.
  - Kept session permission state symbolic so later runtime root updates
  and cwd-only implicit-root retargeting rebind `:workspace_roots`
  correctly.
  - Updated the embedded clients just enough to send and restore the new
  thread state.
  - Refreshed the generated schema/TypeScript artifacts and the app-server
  README to match the new contract.
  
  ## Verification
  
  Targeted coverage for this layer lives in:
  
  - `codex-rs/app-server-protocol/src/protocol/v2/tests.rs`
  - `codex-rs/app-server/tests/suite/v2/thread_start.rs`
  - `codex-rs/app-server/tests/suite/v2/thread_resume.rs`
  - `codex-rs/app-server/tests/suite/v2/turn_start.rs`
  - `codex-rs/core/src/session/tests.rs`
  
  The key regression checks exercise that:
  
  - `runtimeWorkspaceRoots` resolve against the effective cwd on thread
  start.
  - Profile-declared workspace roots are excluded from the runtime
  workspace roots returned by app-server.
  - A turn-level runtime workspace-root update persists onto the thread
  and is returned by `thread/resume`.
  - A named permission profile selected on one turn remains symbolic so a
  later runtime-root-only turn update changes the actual sandbox writes.
  - A cwd-only turn update retargets the implicit runtime cwd root while
  preserving additional runtime roots.
  - The protocol fixtures and generated client artifacts stay in sync with
  the string-based permission selection contract.
  
  
  
  
  
  
  
  
  
  
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/22611).
  * #22612
  * __->__ #22611

  Michael Bolin · 2026-05-14 23:00:05 -07:00
  8a5306ff88
• [codex] Add opaque desktop config namespace (#22584)

  ## Summary
  - reserve an explicit opaque `desktop` namespace in `ConfigToml`
  - expose `desktop` directly in the app-server v2 `config/read` response
  - keep `config/value/write` and `config/batchWrite` as the only mutation
  seam for paths like `desktop.someKey`
  - regenerate the config/app-server schema outputs and document the new
  contract
  
  ## Why
  The desktop settings work wants one durable, user-editable home for
  app-owned preferences in `~/.codex/config.toml`, without forcing Rust to
  model every individual desktop setting key.
  
  This PR is only the enabling Rust/app-server layer. It gives the
  Electron app a first-class config namespace it can read and write
  through the existing config APIs, while leaving the actual desktop
  migration to the app PR.
  
  ## Behavior and design notes
  - **Opaque but explicit:** `desktop` is first-class at the typed config
  root, while its children remain app-owned and open-ended.
  - **Strict validation still works:** arbitrary nested `desktop.*` keys
  are accepted instead of being rejected as unknown config.
  - **Existing config APIs stay the seam:** `config/read` returns the bag,
  and dotted writes such as `desktop.someKey` continue to flow through
  `config/value/write` / `config/batchWrite` rather than a bespoke RPC.
  - **No new consumer behavior:** Core/TUI do not start depending on
  desktop preferences. This only preserves and exposes the namespace for
  callers that intentionally use it.
  - **Same persistence machinery:** hand-edited `config.toml` keeps using
  the existing TOML edit/write path; this PR does not introduce a second
  serializer or side channel.
  - **TOML-friendly values:** the namespace is intended for ordinary
  JSON-shaped setting values that map cleanly into TOML: strings, numbers,
  booleans, arrays, and nested object/table values. This PR does not add
  special handling for TOML-only edge cases such as datetimes.
  
  ## Layering semantics
  Reads keep using the ordinary effective config pipeline, so `desktop`
  participates in the same layered `config/read` behavior as the rest of
  `ConfigToml`. Writes still target user config through the existing
  config service.
  
  ## Why this is the shape
  The alternative would be teaching Rust about each desktop setting as it
  is added. That would make ordinary app preferences into a cross-repo
  change, which is exactly the coupling we want to avoid.
  
  This keeps the contract small:
  1. Rust owns one opaque `desktop` namespace in `config.toml`.
  2. The desktop app owns the schema and meaning of individual keys inside
  it.
  3. The existing config APIs remain the transport and mutation surface.
  
  That is the piece the desktop settings PR needs in order to move forward
  cleanly.
  
  ## Verification
  - `cargo test -p codex-config strict_config_accepts_opaque_desktop_keys`
  - `cargo test -p codex-core
  desktop_toml_round_trips_opaque_nested_values`
  - `cargo test -p codex-core config_schema_matches_fixture`
  - `cargo test -p codex-app-server-protocol`
  - `cargo test -p codex-app-server --test all desktop_settings`

  guinness-oai · 2026-05-15 02:34:21 +00:00
  4f2918dd7f
• permissions: resolve profile identity with constraints (#22683)

  ## Why
  
  This PR is the invariant-cleanup layer that follows the workspace-roots
  base merged in [#22610](https://github.com/openai/codex/pull/22610).
  
  #22610 adds `[permissions.<id>.workspace_roots]` and keeps runtime
  workspace roots separate from the raw permission profile, but its
  in-memory representation is intentionally transitional: `Permissions`
  still carries the selected profile identity next to a constrained
  `PermissionProfile`. That makes APIs such as
  `set_constrained_permission_profile_with_active_profile()` fragile
  because the id and value only mean the right thing when every caller
  keeps them in sync.
  
  This PR introduces a single resolved profile state so profile identity,
  `extends`, the profile value, and profile-declared workspace roots
  travel together. The next PR,
  [#22611](https://github.com/openai/codex/pull/22611), builds on this by
  changing the app-server turn API to select permission profiles by id
  plus runtime workspace roots.
  
  ## Stack Context
  
  - #22610, now merged: adds profile-declared `workspace_roots`, runtime
  workspace roots, and `:workspace_roots` materialization.
  - This PR: replaces the parallel active-profile/profile-value fields
  with `PermissionProfileState`.
  - #22611: switches app-server turn updates toward profile ids plus
  runtime workspace roots.
  - #22612: updates TUI/exec summaries to show the effective workspace
  roots.
  
  Keeping this separate from #22611 is deliberate: reviewers can validate
  the internal state invariant before reviewing the app-server protocol
  migration.
  
  ## What Changed
  
  - Added `ResolvedPermissionProfile::{Legacy, BuiltIn, Named}` and
  `PermissionProfileState`.
  - Typed built-in profile ids with `BuiltInPermissionProfileId`.
  - Moved selected profile identity and profile-declared workspace roots
  into the resolved state.
  - Replaced `Permissions` parallel profile fields with one
  `permission_profile_state`.
  - Removed `set_constrained_permission_profile_with_active_profile()`
  from session sync paths.
  - Kept trusted session replay/`SessionConfigured` compatibility through
  explicit session snapshot helpers.
  - Updated session configuration, MCP initialization, app-server, exec,
  TUI, and guardian call sites to consume `&PermissionProfile` directly.
  
  ## Review Guide
  
  Start with `codex-rs/core/src/config/resolved_permission_profile.rs`; it
  is the new invariant boundary. Then review
  `codex-rs/core/src/config/mod.rs` to see how config loading records
  active profile identity and profile workspace roots. The remaining
  call-site changes are mostly mechanical fallout from
  `Permissions::permission_profile()` returning `&PermissionProfile`
  instead of `&Constrained<PermissionProfile>`.
  
  ## Verification
  
  The existing config/session coverage now constructs and asserts through
  `PermissionProfileState`. The workspace-root config test also asserts
  that profile-declared roots are preserved in the resolved state, which
  is the behavior #22611 relies on when runtime roots become mutable
  through the app-server API.
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/22683).
  * #22612
  * #22611
  * __->__ #22683

  Michael Bolin · 2026-05-14 18:47:44 -07:00
  3c6d727810
• Stabilize compact rollback follow-up test (#22303)

  ## Summary
  - add the missing response.created event to the mocked empty follow-up
  response in the compact rollback test
  - keep the fix scoped to the flaky mocked stream shape, without
  increasing timeouts
  
  ## Recent flakes on main
  - `snapshot_rollback_followup_turn_trims_context_updates` failed in
  `rust-ci-full` on `main` in the Ubuntu remote test job on 2026-05-14:
  https://github.com/openai/codex/actions/runs/25891434395/job/76095284830
  - The same `compact_resume_fork` suite also failed recently on `main`
  with `snapshot_rollback_past_compaction_replays_append_only_history`,
  which has the same mocked Responses stream shape sensitivity this PR is
  tightening:
  https://github.com/openai/codex/actions/runs/25892437363/job/76098329098
  
  ## Verification
  - env -u CODEX_SANDBOX_NETWORK_DISABLED cargo test -p codex-core --test
  all snapshot_rollback_followup_turn_trims_context_updates -- --nocapture
  - repeated the same focused test 3 consecutive times locally
  - UV_CACHE_DIR=/private/tmp/uv-cache-codex-fmt just fmt

  Dylan Hurd · 2026-05-14 18:43:18 -07:00
  06bb508547
• Add user_input_requested_during_turn to MCP turn metadata (#22237)

  ## Why
  - Similar change as https://github.com/openai/codex/pull/21219
  - Without change: MCP tool calls receive
  `_meta["x-codex-turn-metadata"]` with various key values.
  - Issue: MCP servers currently do not know if user input was requested
  during the turn (Ex: Model decides to prompt the user for approval
  mid-turn before making a possibly risky tool call). MCP servers may want
  to know this when tracking latency metrics because these instances are
  inflated.
  
  ## What Changed
  - With change: MCP turn metadata now includes
  `user_input_requested_during_turn` when a model-visible
  `request_user_input` call happened earlier in the turn, propagated in
  `_meta["x-codex-turn-metadata"]`.
  - `mark_turn_user_input_requested()` is called when user input is
  requested through either MCP elicitation (`mcp.rs`) or the
  `request_user_input` tool (`mod.rs`).
  - MCP tool call `_meta` is now built immediately before execution
  (`mcp_tool_call.rs`) so user input requested earlier in the same turn,
  including within the same tool call via elicitation, is reflected in the
  metadata.
  - Normal `/responses` turn metadata headers are unchanged.
  
  ## Verification
  - `codex-rs/core/src/session/mcp_tests.rs`
  - `codex-rs/core/src/tools/handlers/request_user_input_tests.rs`
  - `codex-rs/core/src/turn_metadata_tests.rs`
  - `codex-rs/core/tests/suite/search_tool.rs`

  mchen-oai · 2026-05-15 01:26:50 +00:00
  10cf1f79dd
• permissions: support workspace roots in profiles (#22610)

  ## Why
  
  This is the configuration/model half of the alternative permissions
  migration we discussed as a comparison point for
  [#22401](https://github.com/openai/codex/pull/22401) and
  [#22402](https://github.com/openai/codex/pull/22402).
  
  The old `workspace-write` model mixes three concerns that we want to
  keep separate:
  - reusable profile rules that should stay immutable once selected
  - user/runtime workspace roots from `cwd`, `--add-dir`, and legacy
  workspace-write config
  - internal Codex writable roots such as memories, which should not be
  shown as user workspace roots
  
  This PR gives permission profiles first-class `workspace_roots` so users
  can opt multiple repositories into the same `:workspace_roots` rules
  without using broad absolute-path write grants. It also starts
  separating the raw selected profile from the effective runtime profile
  by making `Permissions` expose explicit accessors instead of public
  mutable fields.
  
  A representative `config.toml` looks like this:
  
  ```toml
  default_permissions = "dev"
  
  [permissions.dev.workspace_roots]
  "~/code/openai" = true
  "~/code/developers-website" = true
  
  [permissions.dev.filesystem.":workspace_roots"]
  "." = "write"
  ".codex" = "read"
  ".git" = "read"
  ".vscode" = "read"
  ```
  
  If Codex starts in `~/code/codex` with that profile selected, the
  effective workspace-root set becomes:
  - `~/code/codex` from the runtime `cwd`
  - `~/code/openai` from the profile
  - `~/code/developers-website` from the profile
  
  The `:workspace_roots` rules are materialized across each root, so
  `.git`, `.codex`, and `.vscode` stay scoped the same way everywhere.
  Runtime additions such as `--add-dir` can still layer on later stack
  entries without mutating the selected profile.
  
  ## Stack Shape
  
  This PR intentionally stops before the profile-identity cleanup in
  [#22683](https://github.com/openai/codex/pull/22683) so the base review
  stays focused on config loading, workspace-root materialization, and
  compatibility with legacy `workspace-write`.
  
  The representation in this PR is therefore transitional: `Permissions`
  carries enough state to distinguish the raw constrained profile from the
  effective runtime profile, and there are still call sites that must keep
  the active profile identity and constrained profile value in sync. The
  follow-up PR replaces that with a single resolved profile state
  (`ResolvedPermissionProfile` / `PermissionProfileState`) that keeps the
  profile id, immutable `PermissionProfile`, and profile-declared
  workspace roots together. That follow-up removes APIs such as
  `set_constrained_permission_profile_with_active_profile()` where
  separate arguments could drift out of sync.
  
  Downstream PRs then build on this base to switch app-server turn updates
  to profile ids plus runtime workspace roots and to finish the
  user-visible summary behavior. Reviewers should judge this PR as the
  workspace-roots foundation, not as the final in-memory shape of selected
  permission profiles.
  
  ## Review Guide
  
  Suggested review order:
  
  1. Start with `codex-rs/core/src/config/mod.rs`.
  This is the main shape change in the base slice. `Permissions` now
  stores a private raw `Constrained<PermissionProfile>` plus runtime
  `workspace_roots`. Callers use `permission_profile()` when they need the
  raw constrained value and `effective_permission_profile()` when they
  need a materialized runtime profile. As noted above,
  [#22683](https://github.com/openai/codex/pull/22683) replaces this
  transitional shape with a resolved profile state that keeps identity and
  profile data together.
  
  2. Review `codex-rs/config/src/permissions_toml.rs` and
  `codex-rs/core/src/config/permissions.rs`.
  These add `[permissions.<id>.workspace_roots]`, resolve enabled entries
  relative to the policy cwd, and keep `:workspace_roots` deny-read glob
  patterns symbolic until the actual roots are known.
  
  3. Review `codex-rs/protocol/src/permissions.rs` and
  `codex-rs/protocol/src/models.rs`.
  These add the policy/profile materialization helpers that expand exact
  `:workspace_roots` entries and scoped deny-read globs over every
  workspace root. This is also where `ActivePermissionProfileModification`
  is removed from the core model.
  
  4. Review the legacy bridge in
  `Config::load_from_base_config_with_overrides` and
  `Config::set_legacy_sandbox_policy`.
  This is where legacy `workspace-write` roots become runtime workspace
  roots, while Codex internal writable roots stay internal and do not
  appear as user-facing workspace roots.
  
  5. Then skim downstream call sites.
  The interesting pattern is raw-vs-effective access: state/proxy/bwrap
  paths keep the raw constrained profile, while execution, summaries, and
  user-visible status use the effective profile and workspace-root list.
  
  ## What Changed
  
  - added `[permissions.<id>.workspace_roots]` to the config model and
  schema
  - added runtime `workspace_roots` state to `Config`/`Permissions` and
  `ConfigOverrides`
  - made `Permissions` profile fields private and replaced direct mutation
  with accessors/setters
  - added `PermissionProfile` and `FileSystemSandboxPolicy` helpers for
  materializing `:workspace_roots` exact paths and deny-read globs across
  all roots
  - moved legacy additional writable roots into runtime workspace-root
  state instead of active profile modifications
  - removed `ActivePermissionProfileModification` and its app-server
  protocol/schema export
  - updated sandbox/status summary paths so internal writable roots are
  not reported as user workspace roots
  
  ## Verification Strategy
  
  The targeted tests cover the behavior at the layers where regressions
  are most likely:
  - `codex-rs/core/src/config/config_tests.rs` verifies config loading,
  legacy workspace-root seeding, effective profile materialization, and
  memory-root handling.
  - `codex-rs/core/src/config/permissions_tests.rs` verifies profile
  `workspace_roots` parsing and `:workspace_roots` scoped/glob
  compilation.
  - `codex-rs/protocol/src/permissions.rs` unit tests verify exact and
  glob materialization over multiple workspace roots.
  - `codex-rs/tui/src/status/tests.rs` and
  `codex-rs/utils/sandbox-summary/src/sandbox_summary.rs` verify the
  user-facing summaries show effective workspace roots and hide internal
  writes.
  
  I also ran `cargo check --tests` locally after the latest stack refresh
  to catch cross-crate API breakage from the private-field/accessor
  changes.
  
  
  
  
  
  
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/22610).
  * #22612
  * #22611
  * #22683
  * __->__ #22610

  Michael Bolin · 2026-05-14 18:25:23 -07:00
  c25d905f61
• [codex] Remove experimental instructions file config (#22724)

  ## Summary
  
  Remove the deprecated `experimental_instructions_file` config setting
  from the typed config surface and the remaining deprecation-notice
  plumbing. `model_instructions_file` remains the supported setting and
  its loading path is unchanged.
  
  The setting was deprecated when it was renamed to
  `model_instructions_file` on January 20, 2026 in
  https://github.com/openai/codex/pull/9555.
  
  ## Changes
  
  - Remove `experimental_instructions_file` from `ConfigToml` and
  `ConfigProfile`.
  - Delete the custom config-layer scan and session deprecation notice for
  the removed setting.
  - Stop clearing the removed field from generated session config locks.
  - Remove the obsolete deprecation-notice test case while keeping
  `model_instructions_file` coverage intact.
  
  ## Validation
  
  - `just write-config-schema`
  - `just fmt`
  - `cargo test -p codex-config`
  - `cargo test -p codex-core model_instructions_file`
  - `just fix -p codex-core`
  - `git diff --check`
  
  Co-authored-by: Codex <noreply@openai.com>

  Dylan Hurd · 2026-05-14 18:04:26 -07:00
  7dbe1c9498
• Remove SSE fixture loaders (#22684)

  ## Why
  
  The Responses API test support already has structured SSE event
  builders. Keeping separate JSON fixture loaders made small mock streams
  harder to read and left an on-disk fixture for a single event.
  
  ## What changed
  
  - Removed `load_sse_fixture` and `load_sse_fixture_with_id_from_str`
  from `core_test_support`.
  - Deleted the one `tests/fixtures/incomplete_sse.json` Responses API
  fixture.
  - Replaced the remaining call sites with `responses::sse(...)` and
  existing event helpers.
  
  ## Validation
  
  - `cargo test -p codex-core --test all
  stream_no_completed::retries_on_early_close`
  - `cargo test -p codex-core --test all
  history_dedupes_streamed_and_final_messages_across_turns`
  - `cargo test -p codex-core --test all review::`

  pakrym-oai · 2026-05-15 00:40:32 +00:00
  4bff020a96
• Trim TUI legacy core helper usage (#22695)

  ## Why
  
  The TUI still had a few low-risk dependencies flowing through the
  transitional `legacy_core` namespace after the app-server migration.
  These helpers either already have clearer non-core owners or are
  presentation logic that does not belong in `codex-core`, so moving them
  out reduces the compatibility surface without changing product behavior.
  
  ## What changed
  
  This is a low-risk change, almost completely mechanical in nature.
  
  - Route TUI Codex-home lookup through `codex-utils-home-dir`, use
  `Config::log_dir` directly, and call
  `codex-sandboxing::system_bwrap_warning` without going through
  `legacy_core`.
  - Move shared `codex resume` hint formatting from `codex-core` into
  `codex-utils-cli`.
  - Update CLI and TUI call sites to use the shared CLI utility, and keep
  the resume-command behavior covered by tests in its new home.
  
  ## Verification
  
  - `cargo test -p codex-utils-cli`
  - `cargo test -p codex-utils-cli resume_command`

  Eric Traut · 2026-05-14 16:54:59 -07:00
  3dc278b68e
• chore(config) rm windows_wsl_setup_acknowledged (#22717)

  ## Summary
  Remove dead code from a notice that no longer exists.
  
  ## Testing
  - [x] Unit tests pass.

  Dylan Hurd · 2026-05-14 23:25:15 +00:00
  85915a2a21
• chore(features) rm Feature::ApplyPatchFreeform (#22711)

  ## Summary
  Removes the feature since this is effectively on by default in all cases
  where we should use it, or can be configured via models.json.
  
  ## Testing
  - [x] unit tests pass

  Dylan Hurd · 2026-05-14 16:15:56 -07:00
  51b0e94105
• [codex] Support multiple forced ChatGPT workspaces (#18161)

  ## Summary
  
  This change lets `forced_chatgpt_workspace_id` accept multiple workspace
  IDs instead of a single value.
  
  It keeps the existing config key name, adds backward-compatible parsing
  for a single string in `config.toml`, and normalizes the setting into an
  allowed workspace list across login enforcement, app-server config
  surfaces, and local ChatGPT auth helpers.
  
  ## Why
  
  Workspace-restricted deployments may need to allow more than one ChatGPT
  workspace without dropping the guardrail entirely.
  
  ## Server-side impact
  
  Codex's local server and app-server protocol needed changes because they
  previously assumed a single workspace ID. The local login flow now
  matches the auth backend interface by sending the allowed workspace list
  as a single comma-separated `allowed_workspace_id` query parameter.
  
  ## Validation
  
  This was tested with:
  
  - A single workspace config
  - With multi-workspace configs
  - With multiple workspaces in the config
  - The user only being a part of a subset of them
  
  All were successful.
  
  Automated coverage:
  
  - `cargo test -p codex-login`
  - `cargo test -p codex-app-server-protocol`
  - `cargo test -p codex-tui local_chatgpt_auth`
  - `cargo test --locked -p codex-app-server
  login_account_chatgpt_includes_forced_workspace_allowlist_query_param`

  rreichel3-oai · 2026-05-14 17:11:36 -04:00
  02a7205250
• tests: isolate codex home for live cli (#22563)

  ## Why
  
  Some core integration-test paths were creating Codex state under ambient
  `~/.codex`. In environments where `HOME=/tmp`, that showed up as
  `/tmp/.codex`, which is host-level shared state and makes these tests
  environment/order sensitive.
  
  The affected paths were:
  
  - `core/tests/suite/live_cli.rs`: `run_live()` spawned the real CLI with
  a temp cwd, but without an isolated home, so the child resolved Codex
  home from ambient `HOME`.
  - core / exec-server integration test binaries using
  `configure_test_binary_dispatch(...)`: their startup ctor installs arg0
  helper aliases like `apply_patch` and `codex-linux-sandbox`. Full
  `arg0_dispatch()` also installs aliases from ambient Codex-home
  resolution, so test-binary startup could create `CODEX_HOME/tmp/arg0`;
  with `HOME=/tmp`, that became `/tmp/.codex/tmp/arg0/...`.
  
  ## What changed
  
  - `live_cli` now gives the spawned CLI a temp `HOME` and temp
  `CODEX_HOME`.
  - arg0 alias setup now has an explicit-home form,
  `prepend_path_entry_for_codex_aliases_in(...)`, so test helpers can
  place alias state under a temp directory without relying on ambient
  `CODEX_HOME`.
  - helper re-entry behavior is preserved with
  `dispatch_arg0_if_needed()`, so aliases like `apply_patch` and
  `codex-linux-sandbox` still dispatch correctly before test alias
  installation.
  - core test support keeps the temp Codex home alive for the lifetime of
  the test binary, matching the alias lifetime.
  
  ## Verification
  
  Verified on `dev2` with `HOME=/tmp` that the focused core test-binary
  startup path no longer recreates `/tmp/.codex`.
  
  Also checked the exact `live_cli` test path under `HOME=/tmp`; on `dev2`
  it still hits the existing remote-only `cargo_bin("codex-rs")`
  resolution failure before spawning the child, but `/tmp/.codex` remains
  absent after the run.

  starr-openai · 2026-05-14 12:59:56 -07:00
  32b45a43e2
• Fix remote environment test fixtures (#22572)

  ## Why
  The Docker remote-env coverage was failing before it reached the
  behavior those tests are meant to exercise. The remote-aware test
  fixture only registered the remote environment, so tests that
  intentionally select both `local` and `remote` could not start a turn.
  After that was fixed, two tests exposed stale fixtures: the approval
  test was auto-approving under workspace-write, and the remote
  `view_image` test was writing invalid PNG bytes.
  
  ## What Changed
  - Added `EnvironmentManager::create_for_tests_with_local(...)` so tests
  can keep the provider default while also selecting `local` explicitly.
  - Updated `build_remote_aware()` to use that test-only manager when a
  remote exec-server URL is present.
  - Changed the remote apply-patch approval helper to use
  `SandboxPolicy::new_read_only_policy()` so the test actually exercises
  approval caching per environment.
  - Replaced the hardcoded remote `view_image` PNG blob with the existing
  `png_bytes(...)` helper so the test uses a valid image fixture.
  
  ## Validation
  Ran these isolated Docker remote-env tests on the devbox with
  `$remote-tests` setup:
  -
  `suite::remote_env::apply_patch_freeform_routes_to_selected_remote_environment`
  -
  `suite::remote_env::apply_patch_approvals_are_remembered_per_environment`
  -
  `suite::remote_env::apply_patch_intercepted_exec_command_routes_to_selected_remote_environment`
  -
  `suite::remote_env::exec_command_routes_to_selected_remote_environment`
  - `suite::view_image::view_image_routes_to_selected_remote_environment`
  
  All five pass.

  starr-openai · 2026-05-14 12:40:01 -07:00
  255748638c
• Support explicit MCP OAuth client IDs (#22575)

  ## Why
  Some MCP OAuth providers require a pre-registered public client ID and
  cannot rely on dynamic client registration. Codex already supports MCP
  OAuth, but it had no way to supply that client ID from config into the
  PKCE flow.
  
  ## What changed
  - add `oauth.client_id` under `[mcp_servers.<server>]` config, including
  config editing and schema generation
  - thread the configured client ID through CLI, app-server, plugin login,
  and MCP skill dependency OAuth entrypoints
  - configure RMCP authorization with the explicit client when present,
  while preserving the existing dynamic-registration path when it is
  absent
  - add focused coverage for config parsing/serialization and OAuth URL
  generation
  
  ## Verification
  - `cargo test -p codex-config -p codex-rmcp-client -p codex-mcp -p
  codex-core-plugins`
  - `cargo test -p codex-core blocking_replace_mcp_servers_round_trips
  --lib`
  - `cargo test -p codex-core
  replace_mcp_servers_streamable_http_serializes_oauth_resource --lib`
  - `cargo test -p codex-core config_schema_matches_fixture --lib`
  
  ## Notes
  Broader local package runs still hit unrelated pre-existing stack
  overflows in:
  - `codex-app-server::in_process_start_clamps_zero_channel_capacity`
  -
  `codex-core::resume_agent_from_rollout_uses_edge_data_when_descendant_metadata_source_is_stale`

  Matthew Zeng · 2026-05-14 11:52:43 -07:00
  d8ddeb6869
• [codex] Ignore fsmonitor config in Git metadata reads (#22652)

  ## Summary
  - keep Git metadata/status subprocesses independent of repository
  `core.fsmonitor` configuration
  - preserve existing working-tree state reporting while making the helper
  behavior more predictable
  - add regression coverage for `get_has_changes` when a repository
  defines an fsmonitor command
  
  ## Validation
  - `cargo fmt --all`
  - `cargo test -p codex-core test_get_has_changes_`
  - `cargo test -p codex-git-utils`

  Chris Bookholt · 2026-05-14 10:07:43 -07:00
  6ec8c4a6ec
• tests: avoid ambient temp sandbox roots (#22576)

  ## Why
  Some sandboxed integration tests enabled both ambient temp roots
  (`TMPDIR` and literal `/tmp`) even though they were not testing
  temp-root behavior. On Linux bwrap, making `/tmp` writable causes
  protected metadata mount targets such as `/tmp/.git`, `/tmp/.agents`,
  and `/tmp/.codex` to be synthesized. If a run is interrupted, those
  top-level markers can be left behind and contaminate later tests.
  
  ## What changed
  For the incidental integration tests that do not need ambient temp-root
  access, set `exclude_tmpdir_env_var` and `exclude_slash_tmp` to `true`.
  Dedicated protected-metadata coverage remains in the lower-level sandbox
  tests that use isolated temp roots.
  
  ## Verification
  Focused remote devbox repros passed with a watcher polling `/tmp/.git`,
  `/tmp/.agents`, and `/tmp/.codex`; no leaked markers were observed.

  starr-openai · 2026-05-14 10:04:24 -07:00
  8736e32657
• permissions: canonicalize workspace_roots and danger-full-access names (#22624)

  ## Why
  
  This is a small precursor to the larger permissions-migration work. Both
  the comparison stack in
  [#22401](https://github.com/openai/codex/pull/22401) /
  [#22402](https://github.com/openai/codex/pull/22402) and the alternate
  stack in [#22610](https://github.com/openai/codex/pull/22610) /
  [#22611](https://github.com/openai/codex/pull/22611) /
  [#22612](https://github.com/openai/codex/pull/22612) are easier to
  review if the terminology is already settled underneath them.
  
  Because `:project_roots` and `:danger-no-sandbox` have not shipped as
  stable user-facing surface area, carrying them forward as aliases would
  just add more migration logic to the later stacks. This PR removes that
  ambiguity now so the follow-on work can rely on one spelling for each
  built-in concept.
  
  ## What Changed
  
  - renamed the config-facing special filesystem key from `:project_roots`
  to `:workspace_roots`
  - dropped unpublished `:project_roots` parsing support in
  `core/src/config/permissions.rs`, so new config only recognizes
  `:workspace_roots`
  - renamed the built-in full-access permission profile id from
  `:danger-no-sandbox` to `:danger-full-access`
  - dropped unpublished `:danger-no-sandbox` support entirely, including
  the old active-profile canonicalization path, and added explicit
  rejection coverage for the legacy id
  - introduced shared built-in permission-profile id constants in
  `codex-rs/protocol/src/models.rs`
  - updated `core`, `app-server`, and `tui` call sites that special-case
  built-in profiles to use the shared constants and canonical ids
  - updated tests and the Linux sandbox README to use `:workspace_roots` /
  `:danger-full-access`
  
  ## Verification
  
  I focused verification on the three places this rename can regress:
  config parsing, active-profile identity surfaced back out of `core`, and
  user/server call sites that special-case built-in profiles.
  
  Targeted checks:
  
  -
  `config::tests::default_permissions_can_select_builtin_profile_without_permissions_table`
  -
  `config::tests::default_permissions_read_only_applies_additional_writable_roots_as_modifications`
  -
  `config::tests::default_permissions_can_select_builtin_full_access_profile`
  - `config::tests::legacy_danger_no_sandbox_is_rejected`
  - `workspace_root` filtered `codex-core` tests
  -
  `request_processors::thread_processor::thread_processor_tests::thread_processor_behavior_tests::requested_permissions_trust_project_uses_permission_profile_intent`
  -
  `suite::v2::turn_start::turn_start_rejects_invalid_permission_selection_before_starting_turn`
  - `status::tests::status_snapshot_shows_auto_review_permissions`
  -
  `status::tests::status_permissions_full_disk_managed_with_network_is_danger_full_access`
  -
  `app_server_session::tests::embedded_turn_permissions_use_active_profile_selection`

  Michael Bolin · 2026-05-14 08:45:54 -07:00
  01d93fd9fc
• Fix turn extension data task plumbing (#22646)

  ## Summary
  - carry the per-turn extension data through RunningTask so abort
  handling can rebuild SessionTaskContext
  - update stale test ExtensionData::new() callsites to pass the turn id
  
  ## Testing
  - Not run after PR branch creation; CI will cover.

  jif-oai · 2026-05-14 16:00:06 +02:00
  12bfb57139
• feat: add layered --profile-v2 config files (#17141)

  ## Why
  
  `--profile-v2 <name>` gives launchers and runtime entry points a named
  profile config without making each profile duplicate the base user
  config. The base `$CODEX_HOME/config.toml` still loads first, then
  `$CODEX_HOME/<name>.config.toml` layers above it and becomes the active
  writable user config for that session.
  
  That keeps shared defaults, plugin/MCP setup, and managed/user
  constraints in one place while letting a named profile override only the
  pieces that need to differ.
  
  ## What Changed
  
  - Added the shared `--profile-v2 <name>` runtime option with validated
  plain names, now represented by `ProfileV2Name`.
  - Extended config layer state so the base user config and selected
  profile config are both `User` layers; APIs expose the active user layer
  and merged effective user config.
  - Threaded profile selection through runtime entry points: `codex`,
  `codex exec`, `codex review`, `codex resume`, `codex fork`, and `codex
  debug prompt-input`.
  - Made user-facing config writes go to the selected profile file when
  active, including TUI/settings persistence, app-server config writes,
  and MCP/app tool approval persistence.
  - Made plugin, marketplace, MCP, hooks, and config reload paths read
  from the merged user config so base and profile layers both participate.
  - Updated app-server config layer schemas to mark profile-backed user
  layers.
  
  ## Limits
  
  `--profile-v2` is still rejected for config-management subcommands such
  as feature, MCP, and marketplace edits. Those paths remain tied to the
  base `config.toml` until they have explicit profile-selection semantics.
  
  Some adjacent background writes may still update base or global state
  rather than the selected profile:
  
  - marketplace auto-upgrade metadata
  - automatic MCP dependency installs from skills
  - remote plugin sync or uninstall config edits
  - personality migration marker/default writes
  
  ## Verification
  
  Added targeted coverage for profile name validation, layer
  ordering/merging, selected-profile writes, app-server config writes,
  session hot reload, plugin config merging, hooks/config fixture updates,
  and MCP/app approval persistence.
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  jif-oai · 2026-05-14 15:16:15 +02:00
  deedf3b2c4
• Wire turn item contributors into stream output (#22494)

  ## Summary
  - run registered TurnItemContributor hooks for parsed stream output
  items
  - plumb the active turn extension store into stream item handling
  - preserve existing memory citation parsing as fallback after
  contributors run
  
  ## Tests
  - cargo test -p codex-core stream_events_utils -- --nocapture
  - just fmt
  - just fix -p codex-core
  - git diff --check

  jif-oai · 2026-05-14 14:48:17 +02:00
  17cd321c32
• feat: make ToolExecutor an async trait (#22560)

  ## Why
  
  `codex_tools::ToolExecutor` keeps a tool spec attached to its runtime
  handler, but extension tools still carried a parallel
  `ExtensionToolFuture` / `ExtensionToolExecutor` shape. That made
  extension-owned tools look different from host tools even though
  routing, registration, and execution need the same abstraction.
  
  This PR makes the shared executor contract directly async and lets
  extension tools implement it too, so host tools and extension tools can
  move through the same registration path.
  
  ## What changed
  
  - Changed `ToolExecutor::handle` to an `async fn` using `async-trait`,
  and updated built-in tool handlers to implement the async trait
  directly.
  - Replaced the bespoke `ExtensionToolFuture` contract with a marker
  `ExtensionToolExecutor` over `ToolExecutor<ToolCall, Output =
  JsonToolOutput>`, re-exporting `ToolExecutor` from
  `codex-extension-api`.
  - Updated the memories extension tools to implement the shared executor
  trait.
  - Split tool-router construction into collected executors plus hosted
  model specs, keeping hosted tools like web search and image generation
  separate from executable handlers.
  - Updated spec/router tests and extension-tool stubs for the new
  executor shape.
  
  ## Verification
  
  - Not run locally.

  jif-oai · 2026-05-14 11:23:57 +02:00
  6d65686313
• Simplify TUI startup test coverage (#22573)

  ## Why
  
  The TUI startup test surface had drifted into expensive, brittle
  coverage:
  
  - `tui/tests/suite/no_panic_on_startup.rs` was already ignored as flaky
  while still spawning a PTY to exercise malformed exec-policy rules.
  - `tui/tests/suite/model_availability_nux.rs` used a seeded session,
  cursor-query spoofing, and repeated interrupts to verify a narrow
  resume-path invariant.
  - `app/tests.rs` had started accumulating unrelated startup and summary
  coverage in one flat module even after the surrounding app code was
  split into feature modules.
  
  This keeps those behaviors covered while making the tests cheaper to
  understand and less likely to rot. It also preserves the malformed-rules
  regression from #8803 without requiring a terminal orchestration test.
  
  ## What changed
  
  - Replaced the malformed `rules` startup PTY case with a direct
  exec-policy loader regression:
  
  [`rules_path_file_returns_read_dir_error`](https://github.com/openai/codex/blob/21b6b5622f18b8cac0ea41fd083b3106778d9ffc/codex-rs/core/src/exec_policy_tests.rs#L264-L284)
  - Made the existing fresh-session-only startup tooltip behavior explicit
  with
  
  [`should_prepare_startup_tooltip_override`](https://github.com/openai/codex/blob/21b6b5622f18b8cac0ea41fd083b3106778d9ffc/codex-rs/tui/src/app/thread_routing.rs#L1272-L1279),
  then added focused coverage for the resume/fork gate and the persisted
  NUX counter.
  - Split startup and session-summary coverage out of
  `tui/src/app/tests.rs` into dedicated modules so the test layout better
  mirrors the current app architecture.
  - Converted one single-message goal validation snapshot into semantic
  assertions where layout was not the behavior under test.
  - Removed the two PTY-heavy suite files that the narrower tests now
  supersede.
  
  ## Verification
  
  - `cargo test -p codex-core rules_path_file_returns_read_dir_error`
  - `cargo test -p codex-tui startup_`
  - `cargo test -p codex-tui session_summary_`
  - `cargo test -p codex-tui
  goal_slash_command_rejects_oversized_objective`

  Eric Traut · 2026-05-13 18:16:54 -07:00
  35451ba79c
• chore(config) rm experimental_use_freeform_apply_patch (#22565)

  ## Summary
  Get rid of the `experimental_use_freeform_apply_patch` config option,
  since it is now encoded in model config. No deprecation message since it
  has been experimental this entire time.
  
  ## Testing
  - [x] Updated unit tests
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Dylan Hurd · 2026-05-13 17:52:15 -07:00
  e33cf9ae28
• Remove connector_openai prefix filtering (#22555)

  Remove unnecessary prefix filtering from codex
  
  ## Test Plan
  
  Test local cli build + make sure backend returns appropriate apps 
  
  ```
  cd ~/code/codex/codex-rs
  cargo build -p codex-cli --bin codex
  ./target/debug/codex
  ```
  
  Appropriate apps show up in my list

  Eric Ning · 2026-05-13 16:59:22 -07:00
  64d8f387f9
• feat: namespace in ext (#22556)
  jif-oai · 2026-05-14 00:37:48 +02:00
  e6939e3969
• Spill oversized PreToolUse additionalContext (#22529)

  # Why
  
  `PreToolUse.additionalContext` became model-visible after #20692, but
  the hook-output spilling path from #21069 never picked up that newer
  lane. As a result, oversized `PreToolUse` context could bypass the
  truncation/spill treatment that already applies to the other hook
  outputs Codex forwards to the model.
  
  # What
  
  - Run `PreToolUseOutcome.additional_contexts` through
  `maybe_spill_texts(...)`
  - Add an integration test proving a large `PreToolUse.additionalContext`
  is replaced with a truncated preview plus spill-file pointer, while the
  full text is preserved on disk.

  Abhinav · 2026-05-13 15:21:31 -07:00
  23bb524973
• Make multi_agent_v2 wait_agent timeouts configurable (#22528)

  ## Why
  
  `multi_agent_v2` already allowed configuring the minimum `wait_agent`
  timeout, but the default timeout and upper bound were still hard-coded.
  That made it hard to tune waits for subagent mailbox activity in
  sessions that need either faster wakeups or longer waits, and it meant
  the model-visible `wait_agent` schema could not fully reflect the
  resolved runtime limits.
  
  ## What Changed
  
  - Added `features.multi_agent_v2.max_wait_timeout_ms` and
  `features.multi_agent_v2.default_wait_timeout_ms` alongside the existing
  `min_wait_timeout_ms` setting.
  - Validated all three timeouts in config as `0..=3_600_000`, with
  `min_wait_timeout_ms <= default_wait_timeout_ms <= max_wait_timeout_ms`.
  - Thread and review session tool config now passes the resolved
  min/default/max values into the `wait_agent` tool schema.
  - `wait_agent` now uses the configured default when `timeout_ms` is
  omitted and rejects explicit values outside the configured min/max range
  instead of silently clamping them.
  - Updated the generated config schema and config-lock test coverage for
  the new fields.

  Andrey Mishchenko · 2026-05-13 14:43:06 -07:00
  7c57a59f51