771 Commits

• Honor client-resolved service tier defaults (#23537)

  ## Why
  
  Model catalog responses can now advertise a nullable
  `default_service_tier` for each model. Codex needs to preserve three
  distinct states all the way from config/app-server inputs to inference:
  
  - no explicit service tier, so the client may apply the current model
  catalog default when FastMode is enabled
  - explicit `default`, meaning the user intentionally wants standard
  routing
  - explicit catalog tier ids such as `priority`, `flex`, or future tiers
  
  Keeping those states distinct prevents the UI from showing one tier
  while core sends another, especially after model switches or app-server
  `thread/start` / `turn/start` updates.
  
  ## What Changed
  
  - Plumbed `default_service_tier` through model catalog protocol types,
  app-server model responses, generated schemas, model cache fixtures, and
  provider/model-manager conversions.
  - Added the request-only `default` service tier sentinel and normalized
  legacy config spelling so `fast` in `config.toml` still materializes as
  the runtime/request id `priority`.
  - Moved catalog default resolution to the TUI/client side, including
  recomputing the effective service tier when model/FastMode-dependent
  surfaces change.
  - Updated app-server thread lifecycle config construction so
  `serviceTier: null` preserves explicit standard-routing intent by
  mapping to `default` instead of internal `None`.
  - Kept core responsible for validating explicit tiers against the
  current model and stripping `default` before `/v1/responses`, without
  applying catalog defaults itself.
  
  ## Validation
  
  - `CARGO_INCREMENTAL=0 cargo build -p codex-cli`
  - `CARGO_INCREMENTAL=0 cargo test -p codex-app-server model_list`
  - `cargo test -p codex-tui service_tier`
  - `cargo test -p codex-protocol service_tier_for_request`
  - `cargo test -p codex-core get_service_tier`
  - `RUST_MIN_STACK=8388608 CARGO_INCREMENTAL=0 cargo test -p codex-core
  service_tier`

  Shijie Rao · 2026-05-20 15:57:50 -07:00
  370b13afc9
• feat: add turn_id and truncation_policy to extension tool calls (#23666)

  ## Why
  
  Extension-owned tools currently receive a stripped `ToolCall` with only
  `call_id`, `tool_name`, and `payload`.
  That makes extension work that needs turn-local execution context
  awkward, especially web-search extension work that needs the active
  `truncation_policy` at tool invocation time.
  
  Reconstructing that value from config or `ExtensionData` would be
  indirect and could drift from the actual turn context, so the cleaner
  fix is to pass the needed turn metadata directly on the extension-facing
  invocation type.
  
  ## What changed
  
  - added `turn_id` and `truncation_policy` to `codex_tools::ToolCall`
  - populated those fields when core adapts `ToolInvocation` into an
  extension tool call
  - added a focused adapter test that verifies extension executors receive
  the forwarded turn metadata
  - updated the memories extension tests to construct the richer
  `ToolCall`
  - added the `codex-utils-output-truncation` dependency to `codex-tools`
  and refreshed lockfiles
  
  ## Testing
  
  - `cargo test -p codex-tools`
  - `cargo test -p codex-memories-extension`
  - `cargo test -p codex-core passes_turn_fields_to_extension_call`
  - `just bazel-lock-update`
  - `just bazel-lock-check`

  jif-oai · 2026-05-20 20:14:41 +02:00
  c5bd131567
• [codex] Hide deferred tools from code mode prompt (#23605)

  ## Why
  
  `code_mode_only_guides_all_tools_search_and_calls_deferred_app_tools`
  was failing because code-mode prompt generation used the same nested
  tool spec list for both the model-visible `exec` guide and the runtime
  `ALL_TOOLS` surface. That allowed deferred MCP/app tools, such as
  `calendar_timezone_option_99`, to leak into the `exec` description even
  though they should only be discoverable through `ALL_TOOLS` at runtime.
  
  ## What changed
  
  Split code-mode nested tool planning into two sets in
  `core/src/tools/spec_plan.rs`:
  
  - runtime nested tool specs still include deferred tools, so
  `tools[...]` and `ALL_TOOLS` can call them
  - `exec` prompt docs only render non-deferred tools, so deferred app
  tools stay out of the model-visible guide
  
  ## Validation
  
  - `cargo test -p codex-core --test all
  code_mode_only_guides_all_tools_search_and_calls_deferred_app_tools --
  --nocapture`
  - looped the same focused test 5 additional times with `cargo test -q -p
  codex-core --test all
  code_mode_only_guides_all_tools_search_and_calls_deferred_app_tools`

  pakrym-oai · 2026-05-20 08:09:45 -07:00
  a52c91d8b5
• [codex] Preserve raw code-mode exec output by default (#23564)

  ## Why
  Code mode can use nested unified exec calls as data sources. When those
  calls omit `max_output_tokens`, code mode should receive raw command
  output so the script can parse or summarize it itself. When code mode
  does provide `max_output_tokens`, that explicit nested budget should be
  respected, including values above the default unified exec limit, rather
  than being capped before code mode sees the result.
  
  ## What
  - Preserve direct unified exec truncation behavior, while letting
  code-mode exec/write_stdin keep `max_output_tokens` as `None` unless
  explicitly supplied.
  - Make code-mode tool results use raw output when no explicit limit is
  present, and use the explicit nested limit directly when one is
  specified.
  - Refactor unified exec output formatting so `truncated_output` takes
  the caller-selected token budget.
  - Add e2e integration coverage for explicit nested exec limits, omitted
  nested exec limits, outer exec limit propagation, omitted-limit outputs
  that exceed both the default and a small truncation policy, explicit
  nested limits above those caps, and high explicit limits that still
  compact larger command output.
  - Reuse the code-mode turn setup helper while directly asserting the
  exact exec output item in each test.
  
  ## Testing
  - `just fmt`
  - `git diff --check`
  - Not run locally per repo guidance; CI should validate the e2e
  integration tests.

  Ahmed Ibrahim · 2026-05-20 04:02:14 +00:00
  5a4202ad90
• Fix stale background terminal poll events (#23231)

  ## Why
  
  Issue #23214 reports `/ps` showing no background terminals while the
  status line still says it is waiting for a background terminal. The race
  is in core: `write_stdin` can poll a process that exits before the
  response returns. The process manager correctly returns `process_id:
  None`, but the handler still emitted a `TerminalInteraction` event using
  the requested session id, causing clients to believe a dead process was
  still being polled.
  
  Fixes #23214.
  
  ## What changed
  
  - Suppress `TerminalInteraction` events for empty `write_stdin` polls
  once `response.process_id` is `None`.
  - Continue emitting interactions for non-empty stdin, even if that input
  causes the process to exit before the response returns.
  - Extend the unified exec integration test to assert completed empty
  polls do not emit terminal interactions.
  
  ## Verification
  
  - `cargo test -p codex-core --test all
  unified_exec_emits_one_begin_and_one_end_event`
  - `cargo test -p codex-core --test all
  unified_exec_emits_terminal_interaction_for_write_stdin`
  
  `cargo test -p codex-core` currently aborts in unrelated
  `agent::control::tests::resume_agent_from_rollout_uses_edge_data_when_descendant_metadata_source_is_stale`
  with a reproducible stack overflow.

  Eric Traut · 2026-05-19 20:48:37 -07:00
  e43a2e297f
• test: fix multi-agent service tier assertion (#23576)

  ## Why
  
  `openai/codex#22169` added a regression test that expects an invalid
  child `service_tier` to be rejected, but the test used
  `Result::expect_err` on `SpawnAgentHandler::handle`. That requires the
  `Ok` type to implement `Debug`, and this handler returns `Box<dyn
  ToolOutput>`, so Bazel failed while compiling `codex-core` tests before
  it could run them.
  
  ## What changed
  
  - Capture the handler result and assert on `result.err()` instead of
  calling `expect_err`.
  - Keep the same `FunctionCallError::RespondToModel` assertion for the
  rejected service tier.
  
  ## Verification
  
  - `cargo test -p codex-core
  spawn_agent_role_service_tier_does_not_hide_invalid_spawn_request`

  Michael Bolin · 2026-05-19 16:47:20 -07:00
  c58c84d6ee
• [codex] Honor role-defined spawn service tiers (#22169)

  ## Why
  Custom agent roles are ordinary config layers, so a role file can
  already express `service_tier` just like other config values. The
  spawned-agent tier path needs to preserve that effective role config and
  follow the same precedence pattern as model/reasoning.
  
  ## What changed
  - Apply an explicit spawn-time `service_tier` onto the child config
  before role application, so a role config layer can override it just
  like role-defined model/reasoning settings do.
  - Validate the final effective child tier after the final child model is
  known, while still falling back to the parent tier when no child tier
  survives.
  - Add focused integration coverage for both v1 and v2 proving role TOML
  loads a service tier, spawned children keep that role-configured tier,
  and a role tier wins over a conflicting spawn-time tier.
  
  ## Validation
  - `just fmt`
  - `git diff --check`
  - Local Rust tests not run, per repo guidance; CI should exercise the
  new coverage.

  Ahmed Ibrahim · 2026-05-19 22:40:41 +00:00
  c53da029bc
• Split plugin install discovery into list and request tools (#23372)

  ## Summary
  - Add `list_available_plugins_to_install` as the inventory step for
  plugin and connector install suggestions.
  - Slim `request_plugin_install` so it only handles the actual
  elicitation, instead of carrying the full discoverable list in its
  prompt.
  - Emit send-time telemetry when an install elicitation is dispatched,
  including requested tool identity in the event payload.
  - Emit install-result telemetry through `SessionTelemetry`, including
  tool type, user response action, and completion status.
  - Update registration and tests to cover the new two-step flow while
  keeping the existing `tool_suggest` feature gate unchanged.
  
  ## Testing
  - `just fmt`
  - `cargo test -p codex-tools`
  - `cargo test -p codex-core request_plugin_install`
  - `cargo test -p codex-core list_available_plugins_to_install`
  - `cargo test -p codex-core
  install_suggestion_tools_can_be_registered_without_search_tool`
  - `cargo test -p codex-otel
  manager_records_plugin_install_suggestion_metric`
  - `cargo test -p codex-otel
  manager_records_plugin_install_elicitation_sent_metric`
  - `just fix -p codex-core`
  - `just fix -p codex-tools`
  - `just fix -p codex-otel`
  - `cargo check -p codex-core`

  Matthew Zeng · 2026-05-19 14:45:37 -07:00
  8335b56c33
• Make deny canonical for filesystem permission entries (#23493)

  ## Why
  Filesystem permission profiles used `none` for deny-read entries, which
  is less direct than the action the entry actually represents. This
  change makes `deny` the canonical filesystem permission spelling while
  preserving compatibility for older configs that still send `none`.
  
  ## What changed
  - rename `FileSystemAccessMode::None` to `Deny`
  - serialize and generate schemas with `deny` as the canonical value
  - retain `none` only as a legacy input alias for temporary config
  compatibility
  - update filesystem glob diagnostics and regression coverage to use the
  canonical spelling
  - refresh config and app-server schema fixtures to match the new wire
  shape
  
  ## Validation
  - `cargo test -p codex-protocol`
  - `cargo test -p codex-app-server-protocol`
  - `cargo test -p codex-core config_toml_deserializes_permission_profiles
  --lib`
  - `cargo test -p codex-core
  read_write_glob_patterns_still_reject_non_subpath_globs --lib`
  
  Earlier in the session, a broad `cargo test -p codex-core` run reached
  unrelated pre-existing failures in timing/snapshot/git-info tests under
  this environment; the targeted surfaces touched by this PR passed
  cleanly.

  viyatb-oai · 2026-05-19 11:03:47 -07:00
  3c76081876
• chore: namespace v1 sub-agent tools (#23475)

  ## Why
  
  The v1 sub-agent tools are a single tool family, but they were exposed
  as separate flat function tools. This makes the model-visible surface
  less clearly grouped and leaves the legacy names in the same flat
  namespace as newer agent tooling.
  
  ## What
  
  - Wraps the v1 `spawn_agent`, `send_input`, `resume_agent`,
  `wait_agent`, and `close_agent` specs in the `multi_agent_v1` namespace.
  - Registers the corresponding handlers with namespaced runtime tool
  names.
  - Updates tool-planning, deferred tool search, and sub-agent
  notification tests to assert the namespace shape and child `spawn_agent`
  lookup.
  
  ## Verification
  
  - Updated `codex-core` coverage for the v1 multi-agent tool plan,
  deferred tool search output, and sub-agent tool descriptions.

  jif-oai · 2026-05-19 19:46:17 +02:00
  05b8ce4354
• Defer v1 multi-agent tools behind tool search (#23144)

  Summary: defer v1 multi-agent tools when tool_search and namespace tools
  are available; keep concise searchable descriptions and move the v1
  usage guidance into developer instructions; add targeted coverage.
  Testing: not run per request; ran just fmt.

  jif-oai · 2026-05-19 15:04:35 +02:00
  b3ae3de405
• Remove ToolsConfig from tool planning (#22835)

  ## Why
  
  `codex-tools` is meant to hold reusable tool primitives, but
  `ToolsConfig` had become a second copy of core runtime decisions instead
  of a small shared contract. It carried provider capabilities, auth/model
  gates, permission and environment state, web/search/image feature gates,
  multi-agent settings, and goal availability from core into `codex-tools`
  ([definition](https://github.com/openai/codex/blob/22dd9ad3929253ed24d7ee4f10f238e95ab25f37/codex-rs/tools/src/tool_config.rs#L97),
  [stored on each
  `TurnContext`](https://github.com/openai/codex/blob/22dd9ad3929253ed24d7ee4f10f238e95ab25f37/codex-rs/core/src/session/turn_context.rs#L87)).
  Every session/context variant then had to build and mutate that snapshot
  before assembling tools.
  
  This PR removes that master object instead of renaming it. Tool planning
  now reads the live `TurnContext`, where `codex-core` already owns those
  decisions, while `codex-tools` keeps only reusable primitives and a
  generic `ToolSetBuilder`/`ToolSet` accumulator.
  
  ## What Changed
  
  - Removed `ToolsConfig` / `ToolsConfigParams` from `codex-tools`; the
  crate keeps the shared helpers that still belong there, including
  request-user-input mode selection, shell backend/type resolution,
  `UnifiedExecShellMode`, and `ToolEnvironmentMode`.
  - Replaced config-snapshot planning with `ToolRouter::from_turn_context`
  and a `spec_plan` pipeline over `CoreToolPlanContext`, deriving provider
  capabilities, auth gates, model support, feature gates, environment
  count, goal support, multi-agent options, web search, and image
  generation from the authoritative turn state.
  - Added generic `codex_tools::ToolSetBuilder` / `ToolSet`, plus the
  small core adapter needed to accumulate `CoreToolRuntime` values and
  hosted model specs.
  - Added the `tool_family::shell` registration module and moved
  shell/unified-exec/memory accounting call sites to read the narrow
  per-turn fields directly.
  - Narrowed `TurnContext` to the remaining explicit per-turn fields
  needed by planning: `available_models`, `unified_exec_shell_mode`, and
  `goal_tools_supported`.
  - Reworked MCP exposure and tool-search setup so deferred/direct MCP
  behavior is driven by the current turn rather than a precomputed config
  snapshot.
  - Replaced the large expected-spec fixture tests with focused
  behavior-level coverage for shell tools, environments, goal and
  agent-job gates, MCP direct/deferred exposure, tool search,
  request-plugin-install, code mode, multi-agent mode, hosted tools, and
  extension executor dispatch.
  
  ## Verification
  
  - `cargo check -p codex-tools`
  - `cargo check -p codex-core --lib`
  - `cargo test -p codex-tools`
  - `cargo test -p codex-core spec_plan --lib`
  - `cargo test -p codex-core router --lib`

  jif-oai · 2026-05-19 11:24:09 +02:00
  05e171094d
• [1 of 7] Add thread settings to UserInput (#23080)

  **Stack position:** [1 of 7]
  
  ## Summary
  
  The first three PRs in this stack are a cleanup pass before the actual
  thread settings API work.
  
  Today, core has several overlapping "user input" ops: `UserInput`,
  `UserInputWithTurnContext`, and `UserTurn`. They differ mostly in how
  much next-turn state they carry, which makes the later queued thread
  settings update harder to reason about and review.
  
  This PR starts that cleanup by adding the shared
  `ThreadSettingsOverrides` payload and allowing `Op::UserInput` to carry
  it. Existing variants remain in place here, so this layer is mostly a
  behavior-preserving API shape change plus mechanical constructor
  updates.
  
  ## End State After PR3
  
  By the end of PR3, `Op::UserInput` is the only "user input" core op. It
  can carry optional thread settings overrides for callers that need to
  update stored defaults with a turn, while callers without updates use
  empty settings. `Op::UserInputWithTurnContext` and `Op::UserTurn` are
  deleted.
  
  ## End State After PR5
  
  By the end of PR5, core will have only two ops for this area:
  
  - `Op::UserInput` for user-input-bearing submissions.
  - `Op::ThreadSettings` for settings-only updates.
  
  ## Stack
  
  1. [1 of 7] [Add thread settings to
  UserInput](https://github.com/openai/codex/pull/23080) (this PR)
  2. [2 of 7] [Remove
  UserInputWithTurnContext](https://github.com/openai/codex/pull/23081)
  3. [3 of 7] [Remove
  UserTurn](https://github.com/openai/codex/pull/23075)
  4. [4 of 7] [Placeholder for OverrideTurnContext
  cleanup](https://github.com/openai/codex/pull/23087)
  5. [5 of 7] [Replace OverrideTurnContext with
  ThreadSettings](https://github.com/openai/codex/pull/22508)
  6. [6 of 7] [Add app-server thread settings
  API](https://github.com/openai/codex/pull/22509)
  7. [7 of 7] [Sync TUI thread
  settings](https://github.com/openai/codex/pull/22510)

  Eric Traut · 2026-05-18 18:48:35 -07:00
  84d941d07f
• Remove ToolSearch feature toggle (#23389)

  ## Summary
  - mark `ToolSearch` as removed and ignore stale config writes for its
  legacy key
  - make search tool exposure depend only on model capability, not a
  feature toggle
  - remove app-server enablement support and prune now-obsolete test
  coverage/setup
  
  ## Verification
  - `cargo test -p codex-features`
  - `cargo test -p codex-tools`
  - `cargo test -p codex-core search_tool_requires_model_capability`
  - `cargo test -p codex-app-server experimental_feature_enablement_set_`
  
  ## Notes
  - This keeps the legacy config key as a no-op for compatibility while
  removing the ability to toggle the behavior off cleanly.
  - No developer-facing docs update outside the touched app-server README
  was needed.

  sayan-oai · 2026-05-19 01:24:39 +00:00
  daa11820b0
• cleanup: Remove skill env var dependency prompting (#22721)

  Deletes the skill env var dependency prompt feature and its runtime
  path. env_var entries in skill dependency metadata are now silently
  ignored during skill loading.

  xl-openai · 2026-05-19 01:24:19 +00:00
  6b54ced108
• [codex] Move pending input into input queue (#22728)

  ## Why
  
  Pending model input was split across `Session`, `TurnState`, and the
  agent mailbox. That made it easy for new paths to manage queued user
  input or mailbox delivery outside the intended ownership boundary.
  
  This PR consolidates the model-facing input lifecycle behind the session
  input queue so turn-local pending input, next-turn queued items, and
  mailbox delivery coordination are owned in one place.
  
  ## What Changed
  
  - Added `session/input_queue.rs` to own pending input queues and mailbox
  delivery coordination.
  - Removed the standalone `agent/mailbox.rs` channel wrapper and store
  mailbox items directly in the input queue.
  - Moved pending-input mutations off `TurnState`; `TurnState` now exposes
  the queue-owned storage directly for now.
  - Routed abort cleanup, mailbox delivery phase changes, next-turn queued
  items, and active-turn pending input through `InputQueue`.
  - Boxed stack-heavy agent resume/fork startup futures that the refactor
  pushed over the default test stack.
  - Updated session, task, goal, stream-event, and multi-agent call sites
  and tests to use the new queue ownership.
  
  ## Verification
  
  - `cargo test -p codex-core --lib agent::control::tests`
  - `cargo test -p codex-core --lib
  agent::control::tests::resume_closed_child_reopens_open_descendants --
  --exact`
  - `cargo test -p codex-core --lib
  agent::control::tests::spawn_agent_fork_last_n_turns_keeps_only_recent_turns
  -- --exact`
  - `cargo test -p codex-core --lib
  agent::control::tests::resume_thread_subagent_restores_stored_nickname_and_role
  -- --exact`
  - `cargo test -p codex-core` was also run; it completed with 1814
  passed, 4 ignored, and one timeout in
  `agent::control::tests::resume_thread_subagent_restores_stored_nickname_and_role`,
  which passed when rerun in isolation.

  pakrym-oai · 2026-05-18 15:43:01 -07:00
  afa0101ae2
• Add tool lifecycle extension contributor (#23309)

  ## Why
  
  Extensions that need to track runtime progress currently have no typed
  host signal for tool execution. The goal extension in particular needs
  to observe tool attempts without inspecting tool payloads, owning tool
  implementations, or staying coupled to core-only runtime plumbing.
  
  This adds a narrow lifecycle contributor API for host-owned tool
  execution: extensions can observe when an accepted tool call starts and
  how it finishes, while policy hooks and tool handlers continue to own
  payload rewriting, blocking, and execution.
  
  Relevant code:
  
  -
  [`ToolLifecycleContributor`](https://github.com/openai/codex/blob/3ad2850ffc7d8a1da19c65a92425637a59098f1b/codex-rs/ext/extension-api/src/contributors.rs#L119)
  defines the extension-facing observer contract.
  -
  [`tool_lifecycle.rs`](https://github.com/openai/codex/blob/3ad2850ffc7d8a1da19c65a92425637a59098f1b/codex-rs/ext/extension-api/src/contributors/tool_lifecycle.rs)
  defines the typed start/finish inputs, source, and outcome enums.
  - [`notify_tool_start` /
  `notify_tool_finish`](https://github.com/openai/codex/blob/3ad2850ffc7d8a1da19c65a92425637a59098f1b/codex-rs/core/src/tools/lifecycle.rs)
  bridges core tool dispatch into the extension registry.
  
  ## What Changed
  
  - Added `ToolLifecycleContributor` to `codex-extension-api`, including:
    - `ToolStartInput`
    - `ToolFinishInput`
    - `ToolCallSource`
    - `ToolCallOutcome`
  - Added registration and lookup support on `ExtensionRegistryBuilder` /
  `ExtensionRegistry`.
  - Wired core tool dispatch to notify lifecycle contributors for:
    - accepted tool starts
    - completed tool calls, including the tool output success marker
    - pre-tool-use blocks
    - failures before or after the handler runs
    - cancellation/abort in the parallel tool path
  - Registered the goal extension as a lifecycle contributor and added the
  outcome filter it will use for goal progress accounting.
  
  ## Test Coverage
  
  - Added `dispatch_notifies_tool_lifecycle_contributors` to cover
  lifecycle notification ordering and outcomes for successful and
  handler-failed tool calls.

  jif-oai · 2026-05-18 21:55:57 +02:00
  c69cde3547
• fix: default unknown tool schemas to empty schemas (#22380)

  ## Why
  
  Some tool providers, especially MCP servers and dynamic tool sources,
  can supply schema nodes that omit `type` and have no recognized JSON
  Schema shape hints. Previously, `sanitize_json_schema` filled those
  unknown nodes in as `string`, which made the schema parseable but
  invented a scalar constraint that the provider did not specify. For
  description-only fields, that could incorrectly steer tool arguments
  away from the provider's actual accepted shape.
  
  The Responses API accepts permissive empty schemas such as `{}` at
  nested property positions, so Codex should preserve that permissive
  meaning instead of coercing unknown schema nodes into a misleading
  scalar type.
  
  ## What Changed
  
  - Changed the no-hints fallback in `codex-rs/tools/src/json_schema.rs`
  to clear unrecognized object schema nodes to `{}`.
  - Empty schemas now remain `{}` rather than becoming `type: "string"`.
  - Description-only or otherwise metadata-only nested property schemas
  now become `{}` while surrounding object/array/string/number inference
  still applies when recognized hints are present.
  - Updated `codex-tools` and `codex-core` tests to cover top-level empty
  schemas, nested empty schemas, metadata-only malformed schemas, dynamic
  tools, and MCP tool specs.
  
  ## Verification
  
  - `cargo test -p codex-tools`
  - `cargo test -p codex-core
  test_mcp_tool_property_missing_type_defaults_to_empty_schema`
  - Manually verified the real Responses API behavior for both
  empty-schema positions:
  - Top-level function `parameters: {}` is accepted and echoed back as
  `{"type":"object","properties":{}}`; when forced to call the tool,
  Responses emitted empty object arguments: `"arguments": "{}"`.
  - Nested property schema `{}` is accepted and preserved as `{}`; when
  forced to call a tool with `metadata.extra`, Responses emitted
  `"arguments": "{\"metadata\":{\"extra\":\"codex schema sanitizer
  behavior\"}}"`.

  Celia Chen · 2026-05-18 12:41:10 -07:00
  4dbca61e20
• goal: pause continuation loops on usage limits and blockers (#23094)

  Addresses #22833, #22245, #23067
  
  ## Why
  `/goal` can keep synthesizing turns even when the next turn cannot make
  meaningful progress. Hard usage exhaustion can replay failing turns, and
  repeated permission or external-resource blockers can keep burning
  tokens while waiting for user or system intervention.
  
  ## What changed
  - Add resumable `blocked` and `usageLimited` goal states. As with
  `paused`, goal continuation stops with these states.
  - Move to `usageLimited` after usage-limit failures.
  - Allow the built-in `update_goal` tool to set `blocked` only under
  explicit repeated-impasse guidance. Updated goal continuation prompt to
  specify that agent should use `blocked` only when it has made at least
  three attempts to get past an impasse.
  
  Most of the files touched by this PR are because of the small app server
  protocol update.
  
  ## Validation
  
  I manually reproduced a number of situations where an agent can run into
  a true impasse and verified that it properly enters `blocked` state. I
  then resumed and verified that it once again entered `blocked` state
  several turns later if the impasse still exists.
  
  I also manually reproduced the usage-limit condition by creating a
  simulated responses API endpoint that returns 429 errors with the
  appropriate error message. Verified that the goal runtime properly moves
  the goal into `usageLimited` state and TUI UI updates appropriately.
  Verified that `/goal resume` resumes (and immediately goes back into
  `ussageLImited` state if appropriate).
  
  
  ## Follow-up PRs
  
  Small changes will be needed to the GUI clients to properly handle the
  two new states.

  Eric Traut · 2026-05-18 11:28:53 -07:00
  0d344aca9b
• [codex] Remove legacy shell output formatting paths (#22706)

  ## Why
  
  The client and tool pipeline still carried compatibility code for legacy
  structured shell output. Current shell and apply_patch responses are
  already plain text for model consumption, so keeping a
  JSON-serialization path plus shell-item rewrite logic makes the request
  formatter and tests preserve a format we do not need anymore.
  
  ## What Changed
  
  - Removed the client-side shell output rewrite from
  `core/src/client_common.rs`.
  - Removed the structured exec-output formatter and the shell `freeform`
  switch so tool emitters use one model-facing formatter.
  - Collapsed apply_patch/shell serialization tests around the remaining
  plain-text output expectations and removed duplicate one-variant
  parameterized cases.
  - Kept the `ApplyPatchModelOutput::ShellCommandViaHeredoc` compatibility
  input shape, but no longer treats it as a separate output-format mode.
  
  ## Validation
  
  - `cargo test -p codex-core client_common`
  - `cargo test -p codex-core shell_serialization`
  - `cargo test -p codex-core apply_patch_cli`
  - `just fix -p codex-core`
  
  ## Documentation
  
  No external Codex documentation update is needed.

  pakrym-oai · 2026-05-18 09:57:54 -07:00
  82061660ae
• 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
• 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
• 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
• 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
• 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
• 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
• 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
• feat: namespace in ext (#22556)
  jif-oai · 2026-05-14 00:37:48 +02:00
  e6939e3969
• 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
• Avoid PowerShell profiles in elevated Windows sandbox (#21400)

  ## Why
  
  On Windows, elevated sandboxed commands run under a dedicated sandbox
  account while `HOME` / `USERPROFILE` can still point at the real user's
  profile directory. For PowerShell login shells, that combination can
  make the sandbox account try to load the real user's PowerShell profile
  script. If the sandbox account's execution policy differs from the real
  user's policy, startup can emit profile-loading errors before the
  requested command runs.
  
  For this backend, loading the profile is not a faithful user login
  shell: it is cross-account profile execution. Treating these PowerShell
  invocations as non-login shells avoids that invalid startup path.
  
  ## Why This Happens Late
  
  The normal `login` decision is resolved when shell argv is created, but
  that point is too early to make this Windows sandbox-specific decision.
  At argv creation time we do not yet know the actual sandbox attempt that
  will run the command. A turn can include sandboxed and unsandboxed
  attempts, and a broad turn-level override would also affect Full Access
  commands where the user's profile should remain available.
  
  Instead, this change carries the selected `ShellType` alongside the argv
  and applies the `-NoProfile` adjustment in the shell runtimes once the
  `SandboxAttempt` is known. That keeps the override scoped to actual
  `WindowsRestrictedToken` attempts with `WindowsSandboxLevel::Elevated`.
  
  The runtime uses the selected shell metadata rather than re-detecting
  PowerShell from argv. That avoids brittle parsing and covers PowerShell
  invocation shapes such as `-EncodedCommand`.
  
  ## What Changed
  
  - Carry selected shell metadata through `exec_command` / unified exec
  requests and shell tool requests.
  - Insert `-NoProfile` for PowerShell commands only when the runtime is
  about to execute a sandboxed elevated Windows attempt.
  - Add focused unit coverage for elevated Windows PowerShell,
  `-EncodedCommand`, existing `-NoProfile`, legacy restricted-token
  attempts, unsandboxed attempts, and non-PowerShell commands.
  
  ## Verification
  
  - `cargo test -p codex-core disable_powershell_profile_tests`
  - `cargo test -p codex-core test_get_command`
  - `cargo clippy --fix --tests --allow-dirty --allow-no-vcs -p
  codex-core`
  
  A full `cargo test -p codex-core` run was also attempted during
  development, but it still hit an unrelated stack overflow in
  `agent::control` tests before reaching this area.

  iceweasel-oai · 2026-05-13 21:37:50 +00:00
  8ae0c837f0
• clean up instructions (#22543)

  rm behavioral steering in tool docs for code mode.

  sayan-oai · 2026-05-13 14:28:57 -07:00
  3de4d7f238
• Use selected environment cwd for filesystem helpers (#22542)

  ## Why
  
  `TurnContext::cwd` is deprecated in favor of resolving paths from the
  selected turn environment cwd. A few filesystem-oriented paths were
  still constructing sandbox context from the legacy cwd and then mutating
  it afterward, or resolving local file paths through the deprecated
  helper.
  
  ## What changed
  
  - Make `TurnContext::file_system_sandbox_context` take the trusted cwd
  explicitly.
  - Pass the selected turn environment cwd directly from `apply_patch` and
  `view_image` call sites.
  - Restrict `spawn_agents_on_csv` to exactly one local environment and
  resolve input/output CSV paths from that local environment cwd.
  - Remove a redundant test setup assignment that only synchronized
  deprecated `TurnContext::cwd` with a replaced config.
  
  ## Validation
  
  - `cargo test -p codex-core view_image`
  - `cargo test -p codex-core
  maybe_persist_mcp_tool_approval_writes_project_config_for_project_server`
  - `cargo test -p codex-core parse_csv_supports_quotes_and_commas`
  - `git diff --check`

  pakrym-oai · 2026-05-13 13:18:56 -07:00
  3ac1d15598
• Deprecate TurnContext cwd and resolve_path (#22519)

  ## Why
  
  `TurnContext::cwd` and `TurnContext::resolve_path` are being phased out
  in favor of using the selected turn environment cwd directly.
  Deprecating both APIs makes any new direct dependency visible while
  preserving the existing migration path for current callers.
  
  ## What Changed
  
  - Marked `TurnContext::cwd` and `TurnContext::resolve_path` as
  deprecated with guidance to use the selected turn environment cwd
  instead.
  - Added exact `#[allow(deprecated)]` suppressions at each existing
  direct usage site, including tests, rather than adding crate-wide
  suppression.
  - Kept the change behavior-preserving: current cwd reads, writes, and
  path resolution continue to use the same values.
  
  ## Verification
  
  - `just fmt`
  - `cargo check -p codex-core`
  - `cargo check -p codex-core --tests`
  - `git diff --check`

  pakrym-oai · 2026-05-13 11:15:25 -07:00
  4454e1411b
• feat: expose multi-agent v2 as model-only tools (#22514)

  ## Why
  
  `code_mode_only` filters code-mode nested tools out of the top-level
  tool list. For multi-agent v2, we need a rollout shape where the
  collaboration tools remain callable as normal model tools without also
  being embedded into the code-mode `exec` tool declaration.
  
  Related to this:
  https://openai-corpws.slack.com/archives/C0AQLHB4U75/p1778660267922549
  
  ## What Changed
  
  - Adds `features.multi_agent_v2.non_code_mode_only`, including config
  resolution, profile override handling, and generated schema coverage.
  - Introduces `ToolExposure::DirectModelOnly` so a tool can be included
  in the initial model-visible list while staying out of the nested
  code-mode tool surface.
  - Applies that exposure to the multi-agent v2 tools when the new flag is
  set: `spawn_agent`, `send_message`, `followup_task`, `wait_agent`,
  `close_agent`, and `list_agents`.
  - Updates code-mode-only filtering so direct-model-only tools remain
  visible while ordinary nested code-mode tools are still hidden.
  
  ## Verification
  
  - Added config parsing/profile tests for `non_code_mode_only`.
  - Added tool spec coverage for the code-mode-only multi-agent v2
  exposure behavior.

  jif-oai · 2026-05-13 19:49:47 +02:00
  fc26af377f
• [codex] Remove unused legacy shell tools (#22246)

  ## Why
  
  Recent session history showed no active use of the raw `shell`,
  `local_shell`, or `container.exec` execution surfaces. Keeping those
  handlers/specs wired into core leaves duplicate shell execution paths
  alongside the supported `shell_command` and unified exec tools.
  
  ## What changed
  
  - Removed the raw `shell` handler/spec and its `ShellToolCallParams`
  protocol helper.
  - Removed the legacy `local_shell` and `container.exec` handler/spec
  plumbing while preserving persisted-history compatibility for old
  response items.
  - Normalized model/config `default` and `local` shell selections to
  `shell_command`.
  - Pruned tests that exercised removed raw-shell/local-shell/apply-patch
  variants and kept coverage on `shell_command`, unified exec, and
  freeform `apply_patch`.
  
  ## Verification
  
  - `git diff --check`
  - `cargo test -p codex-protocol`
  - `cargo test -p codex-tools`
  - `cargo test -p codex-core tools::handlers::shell`
  - `cargo test -p codex-core tools::spec`
  - `cargo test -p codex-core tools::router`
  - `cargo test -p codex-core
  active_call_preserves_triggering_command_context`
  - `cargo test -p codex-core guardian_tests`
  - `cargo test -p codex-core --test all shell_serialization`
  - `cargo test -p codex-core --test all apply_patch_cli`
  - `cargo test -p codex-core --test all shell_command_`
  - `cargo test -p codex-core --test all local_shell`
  - `cargo test -p codex-core --test all otel::`
  - `cargo test -p codex-core --test all hooks::`
  - `just fix -p codex-core`
  - `just fix -p codex-tools`

  pakrym-oai · 2026-05-13 16:43:25 +00:00
  83decfa300
• Introduce tool exposure for deferred registration (#22489)

  ## Why
  
  Deferred tools were tracked with separate side-channel filtering after
  tool specs had already been assembled. That made the registry
  responsible for executing tools while the router/spec planner separately
  decided whether those same tools should be exposed to the model up
  front.
  
  This PR makes exposure part of the tool handler contract so direct
  versus deferred availability travels with the executable tool
  registration.
  
  Next step will be to simplify registration
  
  ## What Changed
  
  - Adds `ToolExposure` to `codex-tools` and exposes it through
  `ToolExecutor`, defaulting tools to `Direct`.
  - Teaches dynamic tools and MCP handlers to mark deferred tools as
  `Deferred` at construction time.
  - Renames the registry object-safe wrapper from `AnyToolHandler` to
  `RegisteredTool` and uses `ToolExposure` when deciding whether to
  include a handler's spec in the initial model-visible tool list.
  - Refactors tool spec planning to derive direct specs and deferred
  search entries from registered handlers, removing the router's
  special-case deferred dynamic tool filtering.
  
  ## Verification
  
  - Not run.

  jif-oai · 2026-05-13 18:16:51 +02:00
  fdda59c00b
• Add service tier overrides to spawned agents (#22139)

  ## Why
  
  Spawned agents can already override `model` and `reasoning_effort`, but
  they have no equivalent way to opt into a model-supported service tier.
  That makes it impossible to preserve or intentionally select tiered
  execution behavior when delegating work to a sub-agent, even though the
  model catalog already advertises supported `service_tiers`.
  
  ## What changed
  
  - Add optional `service_tier` to both legacy and `MultiAgentV2`
  `spawn_agent` tool inputs.
  - Show each picker-visible model's supported service tier ids and
  descriptions in the `spawn_agent` tool guidance.
  - Resolve service tier selection after the child agent's effective model
  is known.
  - Inherit the parent tier when omitted and still supported by the final
  child model; otherwise clear it.
  - Reject explicit unsupported tier requests with a model-facing error.
  - Keep explicit `service_tier` usable on full-history forks, while still
  honoring the existing model/reasoning fork restrictions.
  - Hide `service_tier` alongside other spawn metadata when
  `hide_spawn_agent_metadata` is enabled.
  
  ## Verification
  
  Added focused coverage for:
  
  - v1/v2 `spawn_agent` schema exposure for `service_tier`
  - tier descriptions in spawn guidance
  - hidden-metadata suppression
  - explicit supported tier selection
  - explicit unknown and unsupported tier rejection
  - inherited tier preservation or clearing based on child-model support
  - full-history fork acceptance for explicit service tiers in both v1 and
  v2
  
  Local Rust tests were not run in this workspace per repo guidance; the
  new coverage is included for CI.

  Ahmed Ibrahim · 2026-05-13 18:11:50 +03:00
  87de4e3290
• Refactor extension tools onto shared ToolExecutor (#22369)

  ## Why
  
  Extension tools were split across two public runtime contracts:
  `codex-tool-api` exposed `ToolBundle` plus its own call/spec/error
  types, while core native tools used `codex_tools::ToolExecutor`. That
  made contributed tool specs and execution behavior easy to drift apart
  and added another crate boundary for what should be one executable-tool
  seam.
  
  This PR makes `ToolExecutor` the single runtime contract and keeps
  extension-specific pinning in `codex-extension-api`.
  
  ## Remaining todo
  
  https://github.com/openai/codex/pull/22369/changes#diff-b935ea8245c3ce568a30cff660175fa6390b66b872ae409e1e2e965738250741R5
  Either generic `Invocation` or sub-extract the `ToolCall` and clean
  `ToolInvocation`
  
  ## What changed
  
  - Removed the `codex-tool-api` workspace crate and its dependencies from
  core and `codex-extension-api`.
  - Made `codex_tools::ToolExecutor` object-safe with `async_trait` so
  extension contributors can return a dyn executor.
  - Added the extension-facing aliases under
  `ext/extension-api/src/contributors/tools.rs`, including
  `ExtensionToolExecutor = dyn ToolExecutor<ToolCall, Output =
  ExtensionToolOutput>`.
  - Changed `ToolContributor::tools` to return extension executors
  directly instead of `ToolBundle`s.
  - Updated core’s extension tool handler/registry/router path to adapt
  those extension executors into the existing native `ToolInvocation`
  runtime path.
  - Added focused coverage for extension tools being registered,
  model-visible, dispatchable, and not replacing built-in tools.
  
  ## Verification
  
  - `cargo test -p codex-tools`
  - `cargo test -p codex-extension-api`

  jif-oai · 2026-05-13 12:12:06 +02:00
  9c5dfa7b1a
• feat: extract shared tool executor interface (#22359)

  ## Why
  
  Codex still models model-visible tools and executable behavior largely
  inside `codex-core`, which makes it harder to evolve the tool system
  toward a single reusable abstraction for built-ins, MCP-backed tools,
  dynamic tools, and later tools injected from outside core.
  
  This PR takes the next incremental step in that direction by moving the
  common execution-facing pieces out of core and separating them from
  core-only orchestration. The intent is to let shared tool abstractions
  improve in one place, while `codex-core` keeps the parts that are still
  inherently host-specific today, such as `ToolInvocation`, dispatch
  wiring, and hook integration.
  
  This PR is mostly moving things around. The only interesting piece is
  this abstraction:
  https://github.com/openai/codex/pull/22359/changes#diff-81af519002548ba51ed102bdaaf77e081d40a1e73a6e5f9b104bbbc96a6f1b3dR13
  
  ## What changed
  
  - Added `codex_tools::ToolExecutor<Invocation>` as the shared execution
  trait for model-visible tools.
  - Moved the reusable execution support types from `codex-core` into
  `codex-tools`:
    - `FunctionCallError`
    - `ToolPayload`
    - `ToolOutput`
  - Refactored core tool implementations so that execution behavior lives
  on `ToolExecutor<ToolInvocation>`, while `ToolHandler` remains the
  core-local extension point for hook payloads, telemetry tags, diff
  consumers, and other orchestration concerns.
  - Kept the registry and dispatch flow behaviorally unchanged while
  making the shared/extracted boundary explicit across built-in, MCP,
  dynamic, extension-backed, shell, and multi-agent tool handlers.
  
  ## Verification
  
  - `cargo test -p codex-tools`
  - `just fix -p codex-tools`
  - `just fix -p codex-core`
  - `cargo test -p codex-core` progressed through the updated tool
  surfaces and then hit the existing unrelated multi-agent stack overflow
  in
  `tools::handlers::multi_agents::tests::tool_handlers_cascade_close_and_resume_and_keep_explicitly_closed_subtrees_closed`.

  jif-oai · 2026-05-13 11:31:27 +02:00
  1824685a00
• chore: Keep view_image sandbox test in temp dir (#22355)

  ## Summary
  - move the `view_image` sandbox filesystem-read unit test onto a
  temporary cwd
  - keep the turn cwd and selected turn environment cwd aligned inside the
  test
  - avoid leaving `core/image.png` behind in the repo checkout after the
  test runs
  
  ## Root cause
  The test wrote `image.png` beneath `turn.cwd`, and the shared session
  test helper defaults that cwd to the current repo directory when no
  override is provided.
  
  ## Validation
  - `just fmt`
  - `cargo test -p codex-core
  tools::handlers::view_image::tests::handle_passes_sandbox_context_for_local_filesystem_reads`

  jif-oai · 2026-05-13 10:39:07 +02:00
  7e97da7c13
• Remove unavailable MCP placeholder tool backfill (#22439)

  ## Why
  
  `UnavailableDummyTools` kept synthetic placeholder tools alive for
  historical tool calls whose backing MCP tool was no longer available.
  That path adds stale model-visible tool specs and special routing at the
  point where unavailable MCP calls should use ordinary current-tool
  handling. This removes the runtime backfill instead of preserving a
  second compatibility lane.
  
  ## Is it safe to remove?
  
  The unavailable tools were added in #17853 after a CS issue when a
  previously-called MCP tool failed to load and was omitted from the CS
  spec. Now that we have tool search, I think this is resolved:
  - API merges tools from previous TST output into effective tool set so
  theyre always in CS spec
  - if an MCP tool surfaced by TST later becomes unavailable, the model
  can still call it and it will just return model-visible error
  - both TST output and function call output are dropped on compaction so
  model will not remember old calls to MCP post compaction
  
  ## What changed
  
  - Delete unavailable-tool collection, placeholder handler, router/spec
  plumbing, and obsolete placeholder coverage.
  - Keep `features.unavailable_dummy_tools` as a removed no-op feature
  tombstone so existing configs still parse cleanly.
  - Add an integration-style `tool_search` regression test showing that a
  deferred MCP tool surfaced through `tool_search` still routes through
  MCP and returns a model-visible tool-call error rather than `unsupported
  call`.
  
  ## Verification
  
  - `cargo test -p codex-core tool_search`

  sayan-oai · 2026-05-12 23:30:13 -07:00
  2304ec45ca
• Encapsulate tool search entries in handlers (#22261)

  ## Why
  
  This builds on the handler-owned spec refactor by moving deferred
  tool-search metadata to the same handlers that already own tool specs.
  The registry builder no longer needs a separate prebuilt
  `tool_search_entries` path; it can collect searchable entries from
  deferred handlers directly.
  
  ## What changed
  
  - Added `search_info()` to tool handlers and implemented it for MCP and
  dynamic handlers.
  - Reused handler `spec()` output when constructing tool-search entries,
  adapting it into the deferred `LoadableToolSpec` shape expected by
  `tool_search`.
  - Simplified `build_tool_registry_builder(...)` so `tool_search`
  registration is based on deferred handlers with search info.
  - Removed the old standalone search-entry builders and now-unused
  `codex-tools` discovery helper exports.
  
  ## Verification
  
  - `cargo test -p codex-core tools::handlers::tool_search::tests:: --
  --nocapture`
  - `cargo test -p codex-core tools::spec_plan::tests::search_tool --
  --nocapture`
  - `cargo test -p codex-core tools::spec::tests:: -- --nocapture`
  - `cargo test -p codex-core tools::spec_plan::tests:: -- --nocapture`
  - `cargo test -p codex-tools`
  - `just fix -p codex-core`
  - `just fix -p codex-tools`

  pakrym-oai · 2026-05-12 20:48:02 -07:00
  104fc14956
• tools: infer code-mode namespace descriptions from specs (#22406)

  ## Why
  
  Code mode already builds the merged nested `ToolSpec`s that feed the
  `exec` prompt. Keeping a separate `tool_namespaces` map in the planning
  path duplicated that metadata and left extra wrapper plumbing in
  `spec.rs`.
  
  ## What changed
  
  - derive code-mode namespace descriptions from the merged
  `ToolSpec::Namespace` entries before building the code-mode handlers
  - extract `build_code_mode_handlers(...)` so the code-mode-specific
  planning stays in one place
  - remove `tool_namespaces` from `ToolRegistryBuildParams`
  - delete the now-unused `McpToolPlanInputs` wrapper and related test
  helper plumbing
  
  ## Testing
  
  - `cargo test -p codex-core spec_plan`

  pakrym-oai · 2026-05-12 20:47:50 -07:00
  67c8486462
• hooks: use new session IDs instead of thread IDs for hooks, apply parent's session ID to subagents' hooks (#22268)

  ## Why
  
  hook semantics treat `session_id` as shared across a root session and
  its subagents. Codex hooks were still emitting the current thread ID,
  which made spawned agents look like independent sessions and made it
  harder for hook integrations to correlate work across a root thread and
  its spawned helpers
  
  This change makes hooks use Codex's existing shared session identity so
  hook `session_id` matches the root-thread session across spawned
  subagents.
  
  ## What Changed
  
  - switch hook payloads to use the existing shared session identity from
  core instead of the current thread ID
  - cover all hook surfaces that expose `session_id`, including
  `SessionStart`, tool hooks, compact hooks, prompt-submit hooks, stop
  hooks, and legacy after-agent dispatch

  Andrei Eternal · 2026-05-12 19:05:10 -07:00
  fbfbfe5fc5
• [codex] Remove tool search bucket limit override (#22381)

  ## Why
  
  `tool_search` still carries the server-specific result-cap path added in
  #17684 for `computer-use`: when the model omitted `limit`, a matching
  result expanded the search to 20 and then `limit_results_by_bucket`
  applied per-bucket caps. That makes default result handling depend on a
  one-off server exception instead of the single
  `TOOL_SEARCH_DEFAULT_LIMIT` path.
  
  This PR removes that custom branch so omitted `limit` values use the
  ordinary global default consistently. The implementation being retired
  is the pre-change bucketed search path in
  [`tool_search.rs`](https://github.com/openai/codex/blob/5e3ee5eddfa5333f2e0b011880abf0cbf92bd295/codex-rs/core/src/tools/handlers/tool_search.rs#L121-L190).
  
  ## What changed
  
  - Collapse `ToolSearchHandler::search` back to one BM25 search with the
  resolved limit.
  - Remove `limit_results_by_bucket`, the `computer-use` constants, and
  the omitted-limit plumbing that only existed for the override.
  - Drop dead `ToolSearchEntry::limit_bucket` metadata from deferred MCP
  and dynamic search entries.
  - Remove tests and helpers that only asserted the deleted override
  behavior.
  - Add direct handler-level unit coverage for omitted/default and
  explicit `tool_search` result limits.
  
  ## Validation
  
  - `cargo test -p codex-core tool_search`
  - The matching unit tests passed, including the new omitted/default and
  explicit result-limit coverage.
  - The broader `--test all` search-tool fixture phase then failed before
  sending mocked response requests in
  `tool_search_indexes_only_enabled_non_app_mcp_tools` and
  `tool_search_uses_non_app_mcp_server_instructions_as_namespace_description`.
  - `cargo test -p codex-core`
  - The touched tool-search coverage passed before the run later aborted
  in
  `tools::handlers::multi_agents::tests::tool_handlers_cascade_close_and_resume_and_keep_explicitly_closed_subtrees_closed`
  with a stack overflow.

  sayan-oai · 2026-05-13 00:46:07 +00:00
  1ae9867296