588 Commits

• Support original-detail metadata on MCP image outputs (#17714)

  ## Summary
  - honor `_meta["codex/imageDetail"] == "original"` on MCP image content
  and map it to `detail: "original"` where supported
  - strip that detail back out when the active model does not support
  original-detail image inputs
  - update code-mode `image(...)` to accept individual MCP image blocks
  - teach `js_repl` / `codex.emitImage(...)` to preserve the same hint
  from raw MCP image outputs
  - document the new `_meta` contract and add generic RMCP-backed coverage
  across protocol, core, code-mode, and js_repl paths

  Curtis 'Fjord' Hawthorne · 2026-04-15 14:43:33 -07:00
  9e2fc31854
• register all mcp tools with namespace (#17404)

  stacked on #17402.
  
  MCP tools returned by `tool_search` (deferred tools) get registered in
  our `ToolRegistry` with a different format than directly available
  tools. this leads to two different ways of accessing MCP tools from our
  tool catalog, only one of which works for each. fix this by registering
  all MCP tools with the namespace format, since this info is already
  available.
  
  also, direct MCP tools are registered to responsesapi without a
  namespace, while deferred MCP tools have a namespace. this means we can
  receive MCP `FunctionCall`s in both formats from namespaces. fix this by
  always registering MCP tools with namespace, regardless of deferral
  status.
  
  make code mode track `ToolName` provenance of tools so it can map the
  literal JS function name string to the correct `ToolName` for
  invocation, rather than supporting both in core.
  
  this lets us unify to a single canonical `ToolName` representation for
  each MCP tool and force everywhere to use that one, without supporting
  fallbacks.

  sayan-oai · 2026-04-15 21:02:59 +08:00
  0df7e9a820
• nit: stable test (#17924)
  jif-oai · 2026-04-15 12:05:50 +01:00
  544b4e39e3
• Adjust default tool search result caps (#17684)

  ## Summary
  
  - Allows selected MCP results to return a larger default result set.
  - Keeps the existing default cap for other MCP results.
  - Applies the cap consistently when higher explicit limits are
  requested.
  
  ## Testing
  
  - `cargo test -p codex-core tool_search`
  - Ran a local CLI smoke test with two stdio MCP servers exposing 100
  tools each; the selected-server query returned 20 tools and the
  regular-server query returned 8.

  malone hedges · 2026-04-14 14:57:19 -07:00
  78835d7e63
• Spread AbsolutePathBuf (#17792)

  Mechanical change to promote absolute paths through code.

  pakrym-oai · 2026-04-14 14:26:10 -07:00
  dd1321d11b
• Route apply_patch through the environment filesystem (#17674)

  ## Summary
  - route apply_patch runtime execution through the selected Environment
  filesystem instead of the local self-exec path
  - keep the standalone apply_patch command surface intact while restoring
  its launcher/test/docs contract
  - add focused apply_patch filesystem sandbox regression coverage
  
  ## Validation
  - remote devbox Bazel run in progress
  - passed: //codex-rs/apply-patch:apply-patch-unit-tests
  --test_filter=test_read_file_utf8_with_context_reports_invalid_utf8
  - in progress / follow-up: focused core and exec Bazel test slices on
  dev
  
  ## Follow-up under review
  - remote pre-verification and approval/retry behavior still need
  explicit scrutiny for delete/update flows
  - runtime sandbox-denial classification may need a tighter assertion
  path than rendered stderr matching
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  starr-openai · 2026-04-14 12:49:02 -07:00
  c24124b37d
• Always enable original image detail on supported models (#17665)

  ## Summary
  
  This PR removes `image_detail_original` as a runtime experiment and
  makes original image detail available whenever the selected model
  supports it.
  
  Concretely, this change:
  - drops the `image_detail_original` feature flag from the feature
  registry and generated config schema
  - makes tool-emitted image detail depend only on
  `ModelInfo.supports_image_detail_original`
  - updates `view_image` and `code_mode`/`js_repl` image emission to use
  that capability check directly
  - removes now-redundant experiment-specific tests and instruction
  coverage
  - keeps backward compatibility for existing configs by silently ignoring
  a stale `features.image_detail_original` entry
  
  The net effect is that `detail: "original"` is always available on
  supported models, without requiring an experiment toggle.

  Curtis 'Fjord' Hawthorne · 2026-04-14 08:15:56 -07:00
  f030ab62eb
• Add supports_parallel_tool_calls flag to included mcps (#17667)

  ## Why
  
  For more advanced MCP usage, we want the model to be able to emit
  parallel MCP tool calls and have Codex execute eligible ones
  concurrently, instead of forcing all MCP calls through the serial block.
  
  The main design choice was where to thread the config. I made this
  server-level because parallel safety depends on the MCP server
  implementation. Codex reads the flag from `mcp_servers`, threads the
  opted-in server names into `ToolRouter`, and checks the parsed
  `ToolPayload::Mcp { server, .. }` at execution time. That avoids relying
  on model-visible tool names, which can be incomplete in
  deferred/search-tool paths or ambiguous for similarly named
  servers/tools.
  
  ## What was added
  
  Added `supports_parallel_tool_calls` for MCP servers.
  
  Before:
  
  ```toml
  [mcp_servers.docs]
  command = "docs-server"
  ```
  
  After:
  
  ```toml
  [mcp_servers.docs]
  command = "docs-server"
  supports_parallel_tool_calls = true
  ```
  
  MCP calls remain serial by default. Only tools from opted-in servers are
  eligible to run in parallel. Docs also now warn to enable this only when
  the server’s tools are safe to run concurrently, especially around
  shared state or read/write races.
  
  ## Testing
  
  Tested with a local stdio MCP server exposing real delay tools. The
  model/Responses side was mocked only to deterministically emit two MCP
  calls in the same turn.
  
  Each test called `query_with_delay` and `query_with_delay_2` with `{
  "seconds": 25 }`.
  
  | Build/config | Observed | Wall time |
  | --- | --- | --- |
  | main with flag enabled | serial | `58.79s` |
  | PR with flag enabled | parallel | `31.73s` |
  | PR without flag | serial | `56.70s` |
  
  PR with flag enabled showed both tools start before either completed;
  main and PR-without-flag completed the first delay before starting the
  second.
  
  Also added an integration test.
  
  Additional checks:
  
  - `cargo test -p codex-tools` passed
  - `cargo test -p codex-core
  mcp_parallel_support_uses_exact_payload_server` passed
  - `git diff --check` passed

  josiah-openai · 2026-04-13 15:16:34 -07:00
  937dd3812d
• Use AbsolutePathBuf in skill loading and codex_home (#17407)

  Helps with FS migration later

  pakrym-oai · 2026-04-13 10:26:51 -07:00
  ac82443d07
• Make forked agent spawns keep parent model config (#17247)

  ## Summary
  
  When a `spawn_agent` call does a full-history fork, keep the parent's
  effective agent type and model configuration instead of applying child
  role/model overrides.
  
  This is the minimal config-inheritance slice of #16055. Prompt-cache key
  inheritance and MCP tool-surface stability are split into follow-up PRs.
  
  ## Design
  
  - Reject `agent_type`, `model`, and `reasoning_effort` for v1
  `fork_context` spawns.
  - Reject `agent_type`, `model`, and `reasoning_effort` for v2
  `fork_turns = "all"` spawns.
  - Keep v2 partial-history forks (`fork_turns = "N"`) configurable;
  requested model/reasoning overrides and role config still apply there.
  - Keep non-forked spawn behavior unchanged.
  
  ## Tests
  
  - `cargo +1.93.1 test -p codex-core spawn_agent_fork_context --lib`
  - `cargo +1.93.1 test -p codex-core multi_agent_v2_spawn_fork_turns
  --lib`
  - `cargo +1.93.1 test -p codex-core
  multi_agent_v2_spawn_partial_fork_turns_allows_agent_type_override
  --lib`

  friel-openai · 2026-04-13 15:28:40 +00:00
  776246c3f5
• Build remote exec env from exec-server policy (#17216)

  ## Summary
  - add an exec-server `envPolicy` field; when present, the server starts
  from its own process env and applies the shell environment policy there
  - keep `env` as the exact environment for local/embedded starts, but
  make it an overlay for remote unified-exec starts
  - move the shell-environment-policy builder into `codex-config` so Core
  and exec-server share the inherit/filter/set/include behavior
  - overlay only runtime/sandbox/network deltas from Core onto the
  exec-server-derived env
  
  ## Why
  Remote unified exec was materializing the shell env inside Core and
  forwarding the whole map to exec-server, so remote processes could
  inherit the orchestrator machine's `HOME`, `PATH`, etc. This keeps the
  base env on the executor while preserving Core-owned runtime additions
  like `CODEX_THREAD_ID`, unified-exec defaults, network proxy env, and
  sandbox marker env.
  
  ## Validation
  - `just fmt`
  - `git diff --check`
  - `cargo test -p codex-exec-server --lib`
  - `cargo test -p codex-core --lib unified_exec::process_manager::tests`
  - `cargo test -p codex-core --lib exec_env::tests`
  - `cargo test -p codex-core --lib exec_env_tests` (compile-only; filter
  matched 0 tests)
  - `cargo test -p codex-config --lib shell_environment` (compile-only;
  filter matched 0 tests)
  - `just bazel-lock-update`
  
  ## Known local validation issue
  - `just bazel-lock-check` is not runnable in this checkout: it invokes
  `./scripts/check-module-bazel-lock.sh`, which is missing.
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>
  Co-authored-by: pakrym-oai <pakrym@openai.com>

  jif-oai · 2026-04-13 09:59:08 +01:00
  bacb92b1d7
• Run exec-server fs operations through sandbox helper (#17294)

  ## Summary
  - run exec-server filesystem RPCs requiring sandboxing through a
  `codex-fs` arg0 helper over stdin/stdout
  - keep direct local filesystem execution for `DangerFullAccess` and
  external sandbox policies
  - remove the standalone exec-server binary path in favor of top-level
  arg0 dispatch/runtime paths
  - add sandbox escape regression coverage for local and remote filesystem
  paths
  
  ## Validation
  - `just fmt`
  - `git diff --check`
  - remote devbox: `cd codex-rs && bazel test --bes_backend=
  --bes_results_url= //codex-rs/exec-server:all` (6/6 passed)
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  starr-openai · 2026-04-12 18:36:03 -07:00
  d626dc3895
• Add MCP tool wall time to model output (#17406)

  Include MCP wall time in the output so the model is aware of how long
  it's calls are taking.

  pakrym-oai · 2026-04-12 18:26:15 -07:00
  7c1e41c8b6
• [codex] Support flattened deferred MCP tool calls (#17556)

  ## Summary
  - register flattened handler aliases for deferred MCP tools
  - cover the node_repl-shaped deferred MCP call path in tool registry
  tests
  
  ## Root Cause
  Deferred MCP tools were registered only under their namespaced handler
  key, e.g. `mcp__node_repl__:js`. If the model/bridge emitted the
  flattened qualified name `mcp__node_repl__js`, core parsed it as an MCP
  payload but dispatch looked up the flattened handler key and returned
  `unsupported call` before reaching the MCP handler.
  
  ## Validation
  - `just fmt`
  - `cargo test -p codex-tools
  search_tool_registers_deferred_mcp_flattened_handlers`
  - `cargo test -p codex-core
  search_tool_registers_namespaced_mcp_tool_aliases`
  - `git diff --check`

  Francis Chalissery · 2026-04-12 13:19:36 -07:00
  720932ca3d
• changing decision semantics after guardian timeout (#17486)

  **Summary**
  
  This PR treats Guardian timeouts as distinct from explicit denials in
  the core approval paths.
  Timeouts now return timeout-specific guidance instead of Guardian
  policy-rejection messaging.
  It updates the command, shell, network, and MCP approval flows and adds
  focused test coverage.

  Won Park · 2026-04-12 00:00:50 -07:00
  ba839c23f3
• chore: refactor name and namespace to single type (#17402)

  avoid passing them both around, unify on a type. this now also keys
  `ToolRegistry`.
  
  tests pass

  sayan-oai · 2026-04-11 23:06:22 +00:00
  1325bcd3f6
• Fix thread/list cwd filtering for Windows verbatim paths (#17414)

  Addresses #17302
  
  Problem: `thread/list` compared cwd filters with raw path equality, so
  `resume --last` could miss Windows sessions when the saved cwd used a
  verbatim path form and the current cwd did not.
  
  Solution: Normalize cwd comparisons through the existing path comparison
  utilities before falling back to direct equality, and add Windows
  regression coverage for verbatim paths. I made this a general utility
  function and replaced all of the duplicated instance of it across the
  code base.

  Eric Traut · 2026-04-10 23:08:02 -07:00
  e9e7ef3d36
• representing guardian review timeouts in protocol types (#17381)

  ## Summary
  
  - Add `TimedOut` to Guardian/review carrier types:
    - `ReviewDecision::TimedOut`
    - `GuardianAssessmentStatus::TimedOut`
    - app-server v2 `GuardianApprovalReviewStatus::TimedOut`
  - Regenerate app-server JSON/TypeScript schemas for the new wire shape.
  - Wire the new status through core/app-server/TUI mappings with
  conservative fail-closed handling.
  - Keep `TimedOut` non-user-selectable in the approval UI.
  
  **Does not change runtime behavior yet; emitting `TimeOut` and
  parent-model timeout messaging will come in followup PRs**

  Won Park · 2026-04-10 20:02:33 -07:00
  37aac89a6d
• fix(guardian, app-server): introduce guardian review ids (#17298)

  ## Description
  
  This PR introduces `review_id` as the stable identifier for guardian
  reviews and exposes it in app-server `item/autoApprovalReview/started`
  and `item/autoApprovalReview/completed` events.
  
  Internally, guardian rejection state is now keyed by `review_id` instead
  of the reviewed tool item ID. `target_item_id` is still included when a
  review maps to a concrete thread item, but it is no longer overloaded as
  the review lifecycle identifier.
  
  ## Motivation
  
  We'd like to give users the ability to preempt a guardian review while
  it's running (approve or decline).
  
  However, we can't implement the API that allows the user to override a
  running guardian review because we didn't have a unique `review_id` per
  guardian review. Using `target_item_id` is not correct since:
  - with execve reviews, there can be multiple execve calls (and therefore
  guardian reviews) per shell command
  - with network policy reviews, there is no target item ID
  
  The PR that actually implements user overrides will use `review_id` as
  the stable identifier.

  Owen Lin · 2026-04-10 16:21:02 -07:00
  a3be74143a
• feat: description multi-agent v2 (#17338)
  jif-oai · 2026-04-10 15:31:32 +01:00
  d39a722865
• fix: support split carveouts in windows elevated sandbox (#14568)

  ## Summary
  - preserve legacy Windows elevated sandbox behavior for existing
  policies
  - add elevated-only support for split filesystem policies that can be
  represented as readable-root overrides, writable-root overrides, and
  extra deny-write carveouts
  - resolve those elevated filesystem overrides during sandbox transform
  and thread them through setup and policy refresh
  - keep failing closed for explicit unreadable (`none`) carveouts and
  reopened writable descendants under read-only carveouts
  - for explicit read-only-under-writable-root carveouts, materialize
  missing carveout directories during elevated setup before applying the
  deny-write ACL
  - document the elevated vs restricted-token support split in the core
  README
  
  ## Example
  Given a split filesystem policy like:
  
  ```toml
  ":root" = "read"
  ":cwd" = "write"
  "./docs" = "read"
  "C:/scratch" = "write"
  ```
  
  the elevated backend now provisions the readable-root overrides,
  writable-root overrides, and extra deny-write carveouts during setup and
  refresh instead of collapsing back to the legacy workspace-only shape.
  
  If a read-only carveout under a writable root is missing at setup time,
  elevated setup creates that carveout as an empty directory before
  applying its deny-write ACE; otherwise the sandboxed command could
  create it later and bypass the carveout. This is only for explicit
  policy carveouts. Best-effort workspace protections like `.codex/` and
  `.agents/` still skip missing directories.
  
  A policy like:
  
  ```toml
  "/workspace" = "write"
  "/workspace/docs" = "read"
  "/workspace/docs/tmp" = "write"
  ```
  
  still fails closed, because the elevated backend does not reopen
  writable descendants under read-only carveouts yet.
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  viyatb-oai · 2026-04-09 17:34:52 -07:00
  b976e701a8
• [mcp] Expand tool search to custom MCPs. (#16944)

  - [x] Expand tool search to custom MCPs.
  - [x] Rename several variables/fields to be more generic.
  
  Updated tool & server name lifecycles:
  
  **Raw Identity**
  
  ToolInfo.server_name is raw MCP server name.
  ToolInfo.tool.name is raw MCP tool name.
  MCP calls route back to raw via parse_tool_name() returning
  (tool.server_name, tool.tool.name).
  mcpServerStatus/list now groups by raw server and keys tools by
  Tool.name: mod.rs:599
  App-server just forwards that grouped raw snapshot:
  codex_message_processor.rs:5245
  
  **Callable Names**
  
  On list-tools, we create provisional callable_namespace / callable_name:
  mcp_connection_manager.rs:1556
  For non-app MCP, provisional callable name starts as raw tool name.
  For codex-apps, provisional callable name is sanitized and strips
  connector name/id prefix; namespace includes connector name.
  Then qualify_tools() sanitizes callable namespace + name to ASCII alnum
  / _ only: mcp_tool_names.rs:128
  Note: this is stricter than Responses API. Hyphen is currently replaced
  with _ for code-mode compatibility.
  
  **Collision Handling**
  
  We do initially collapse example-server and example_server to the same
  base.
  Then qualify_tools() detects distinct raw namespace identities behind
  the same sanitized namespace and appends a hash to the callable
  namespace: mcp_tool_names.rs:137
  Same idea for tool-name collisions: hash suffix goes on callable tool
  name.
  Final list_all_tools() map key is callable_namespace + callable_name:
  mcp_connection_manager.rs:769
  
  **Direct Model Tools**
  
  Direct MCP tool declarations use the full qualified sanitized key as the
  Responses function name.
  The raw rmcp Tool is converted but renamed for model exposure.
  
  **Tool Search / Deferred**
  
  Tool search result namespace = final ToolInfo.callable_namespace:
  tool_search.rs:85
  Tool search result nested name = final ToolInfo.callable_name:
  tool_search.rs:86
  Deferred tool handler is registered as "{namespace}:{name}":
  tool_registry_plan.rs:248
  When a function call comes back, core recombines namespace + name, looks
  up the full qualified key, and gets the raw server/tool for MCP
  execution: codex.rs:4353
  
  **Separate Legacy Snapshot**
  
  collect_mcp_snapshot_from_manager_with_detail() still returns a map
  keyed by qualified callable name.
  mcpServerStatus/list no longer uses that; it uses
  McpServerStatusSnapshot, which is raw-inventory shaped.

  Matthew Zeng · 2026-04-09 13:34:52 -07:00
  d7f99b0fa6
• Forward app-server turn clientMetadata to Responses (#16009)

  ## Summary
  App-server v2 already receives turn-scoped `clientMetadata`, but the
  Rust app-server was dropping it before the outbound Responses request.
  This change keeps the fix lightweight by threading that metadata through
  the existing turn-metadata path rather than inventing a new transport.
  
  ## What we're trying to do and why
  We want turn-scoped metadata from the app-server protocol layer,
  especially fields like Hermes/GAAS run IDs, to survive all the way to
  the actual Responses API request so it is visible in downstream
  websocket request logging and analytics.
  
  The specific bug was:
  - app-server protocol uses camelCase `clientMetadata`
  - Responses transport already has an existing turn metadata carrier:
  `x-codex-turn-metadata`
  - websocket transport already rewrites that header into
  `request.request_body.client_metadata["x-codex-turn-metadata"]`
  - but the Rust app-server never parsed or stored `clientMetadata`, so
  nothing from the app-server request was making it into that existing
  path
  
  This PR fixes that without adding a new header or a second metadata
  channel.
  
  ## How we did it
  ### Protocol surface
  - Add optional `clientMetadata` to v2 `TurnStartParams` and
  `TurnSteerParams`
  - Regenerate the JSON schema / TypeScript fixtures
  - Update app-server docs to describe the field and its behavior
  
  ### Runtime plumbing
  - Add a dedicated core op for app-server user input carrying turn-scoped
  metadata: `Op::UserInputWithClientMetadata`
  - Wire `turn/start` and `turn/steer` through that op / signature path
  instead of dropping the metadata at the message-processor boundary
  - Store the metadata in `TurnMetadataState`
  
  ### Transport behavior
  - Reuse the existing serialized `x-codex-turn-metadata` payload
  - Merge the new app-server `clientMetadata` into that JSON additively
  - Do **not** replace built-in reserved fields already present in the
  turn metadata payload
  - Keep websocket behavior unchanged at the outer shape level: it still
  sends only `client_metadata["x-codex-turn-metadata"]`, but that JSON
  string now contains the merged fields
  - Keep HTTP fallback behavior unchanged except that the existing
  `x-codex-turn-metadata` header now includes the merged fields too
  
  ### Request shape before / after
  Before, a websocket `response.create` looked like:
  ```json
  {
    "type": "response.create",
    "client_metadata": {
      "x-codex-turn-metadata": "{\"session_id\":\"...\",\"turn_id\":\"...\"}"
    }
  }
  ```
  Even if the app-server caller supplied `clientMetadata`, it was not
  represented there.
  
  After, the same request shape is preserved, but the serialized payload
  now includes the new turn-scoped fields:
  ```json
  {
    "type": "response.create",
    "client_metadata": {
      "x-codex-turn-metadata": "{\"session_id\":\"...\",\"turn_id\":\"...\",\"fiber_run_id\":\"fiber-start-123\",\"origin\":\"gaas\"}"
    }
  }
  ```
  
  ## Validation
  ### Targeted tests added / updated
  - protocol round-trip coverage for `clientMetadata` on `turn/start` and
  `turn/steer`
  - protocol round-trip coverage for `Op::UserInputWithClientMetadata`
  - `TurnMetadataState` merge test proving client metadata is added
  without overwriting reserved built-in fields
  - websocket request-shape test proving outbound `response.create`
  contains merged metadata inside
  `client_metadata["x-codex-turn-metadata"]`
  - app-server integration tests proving:
  - `turn/start` forwards `clientMetadata` into the outbound Responses
  request path
    - websocket warmup + real turn request both behave correctly
    - `turn/steer` updates the follow-up request metadata
  
  ### Commands run
  - `just write-app-server-schema`
  - `cargo test -p codex-app-server-protocol`
  - `cargo test -p codex-protocol`
  - `cargo test -p codex-core
  turn_metadata_state_merges_client_metadata_without_replacing_reserved_fields
  --lib`
  - `cargo test -p codex-core --test all
  responses_websocket_preserves_custom_turn_metadata_fields`
  - `cargo test -p codex-app-server --test all client_metadata`
  - `cargo test -p codex-app-server --test all
  turn_start_forwards_client_metadata_to_responses_websocket_request_body_v2
  -- --nocapture`
  - `just fmt`
  - `just fix -p codex-core -p codex-protocol -p codex-app-server-protocol
  -p codex-app-server`
  - `just fix -p codex-exec -p codex-tui-app-server`
  - `just argument-comment-lint`
  
  ### Full suite note
  `cargo test` in `codex-rs` still fails in:
  -
  `suite::v2::turn_interrupt::turn_interrupt_resolves_pending_command_approval_request`
  
  I verified that same failure on a clean detached `HEAD` worktree with an
  isolated `CARGO_TARGET_DIR`, so it is not caused by this patch.

  neil-oai · 2026-04-09 11:52:37 -07:00
  a92a5085bd
• Skip local shell snapshots for remote unified exec (#17217)

  ## Summary
  - detect remote exec-server sessions in the unified-exec runtime
  - bypass the local shell-snapshot bootstrap only for those remote
  sessions
  - preserve existing local snapshot wrapping, PowerShell UTF-8 prefixing,
  sandbox orchestration, and zsh-fork handling
  
  ## Why
  The shell snapshot file is currently captured and stored next to Core.
  If Core wraps a remote command with `. /path/to/local/snapshot`, the
  process starts on the executor and tries to source a path from the
  orchestrator filesystem. This keeps remote commands from receiving that
  known-local path until shell snapshots are captured/restored on the
  executor side.
  
  ## Validation
  - `just fmt`
  - `git diff --check`
  - `cargo test -p codex-core --lib tools::runtimes::tests`
  
  Co-authored-by: Codex <noreply@openai.com>

  jif-oai · 2026-04-09 17:30:18 +01:00
  c0b5d8d24a
• Update guardian output schema (#17061)

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

  maja-openai · 2026-04-08 15:47:29 -07:00
  dcbc91fd39
• Fix missing fields (#17149)

  Fix missing `image_generation_tool_auth_allowed` in two locations.

  canvrno-oai · 2026-04-08 13:53:53 -07:00
  58ad79b60e
• release ready, enabling only for siwc users (#17046)

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

  Won Park · 2026-04-08 11:22:39 -07:00
  e003f84e1e
• Use AbsolutePathBuf for exec cwd plumbing (#17063)

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

  pakrym-oai · 2026-04-08 10:54:12 -07:00
  35b5720e8d
• Configure multi_agent_v2 spawn agent hints (#17071)

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

  pakrym-oai · 2026-04-08 08:42:18 -07:00
  4c07dd4d25
• Render namespace description for tools (#16879)
  Vivian Fang · 2026-04-08 02:39:40 -07:00
  d47b755aa2
• Support anyOf and enum in JsonSchema (#16875)

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

  Vivian Fang · 2026-04-08 01:07:55 -07:00
  ea516f9a40
• fix: refresh network proxy settings when sandbox mode changes (#17040)

  ## Summary
  
  Fix network proxy sessions so changing sandbox mode recomputes the
  effective managed network policy and applies it to the already-running
  per-session proxy.
  
  ## Root Cause
  
  `danger_full_access_denylist_only` injects `"*"` only while building the
  proxy spec for Full Access. Sessions built that spec once at startup, so
  a later permission switch to Full Access left the live proxy in its
  original restricted policy. Switching back needed the same recompute
  path to remove the synthetic wildcard again.
  
  ## What Changed
  
  - Preserve the original managed network proxy config/requirements so the
  effective spec can be recomputed for a new sandbox policy.
  - Refresh the current session proxy when sandbox settings change, then
  reapply exec-policy network overlays.
  - Add an in-place proxy state update path while rejecting
  listener/port/SOCKS changes that cannot be hot-reloaded.
  - Keep runtime proxy settings cheap to snapshot and update.
  - Add regression coverage for workspace-write -> Full Access ->
  workspace-write.

  viyatb-oai · 2026-04-08 03:07:55 +00:00
  3c1adbabcd
• [codex] Apply patches through executor filesystem (#17048)

  ## Summary
  - run apply_patch through the executor filesystem when a remote
  environment is present instead of shelling out to the local process
  - thread the executor FileSystem into apply_patch interception and keep
  existing local behavior for non-remote turns
  - make the apply_patch integration harness use the executor filesystem
  for setup/assertions
  - add remote-aware skips for turn-diff coverage that still reads the
  test-runner filesystem
  
  ## Why
  Remote apply_patch needed to mutate the remote workspace instead of the
  local checkout. The tests also needed to seed and assert workspace state
  through the same filesystem abstraction so local and remote runs
  exercise the same behavior.
  
  ## Validation
  - `just fmt`
  - `git diff --check`
  - `cargo check -p core_test_support --tests`
  - `cargo test -p codex-core --test all
  suite::shell_serialization::apply_patch_custom_tool_call -- --nocapture`
  - `cargo test -p codex-core --test all
  suite::apply_patch_cli::apply_patch_cli_updates_file_appends_trailing_newline
  -- --nocapture`
  - remote `cargo test -p codex-core --test all apply_patch_cli --
  --nocapture` (229 passed)

  pakrym-oai · 2026-04-07 16:35:02 -07:00
  600c3e49e0
• fix(app-server) revert null instructions changes (#17047)
  Dylan Hurd · 2026-04-07 15:18:34 -07:00
  6c36e7d688
• [codex] Migrate apply_patch to executor filesystem (#17027)

  - Migrate apply-patch verification and application internals to use the
  async `ExecutorFileSystem` abstraction from `exec-server`.
  - Convert apply-patch `cwd` handling to `AbsolutePathBuf` through the
  verifier/parser/handler boundary.
  
  Doesn't change how the tool itself works.

  pakrym-oai · 2026-04-07 21:20:22 +00:00
  e9702411ab
• fix(core) revert Command line in unified exec output (#17031)

  ## Summary
  https://github.com/openai/codex/pull/13860 changed the serialized output
  format of Unified Exec. This PR reverts those changes and some related
  test changes
  
  ## Testing
  - [x] Update tests
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Dylan Hurd · 2026-04-07 13:35:40 -07:00
  d45513ce5a
• [codex] Make AbsolutePathBuf joins infallible (#16981)

  Having to check for errors every time join is called is painful and
  unnecessary.

  pakrym-oai · 2026-04-07 10:52:08 -07:00
  f1a2b920f9
• fix(guardian): don't throw away transcript when over budget (#16956)

  ## Description
  
  This PR changes guardian transcript compaction so oversized
  conversations no longer collapse into a nearly empty placeholder.
  
  Before this change, if the retained user history alone exceeded the
  message budget, guardian would replace the entire transcript with
  `<transcript omitted to preserve budget for planned action>`!
  
  That meant approvals, especially network approvals, could lose the
  recent tool call and tool result that explained what guardian was
  actually reviewing. Now we keep a compact but usable transcript instead
  of dropping it all.
  
  ### Before
  ```
  The following is the Codex agent history whose request action you are assessing...
  >>> TRANSCRIPT START
  <transcript omitted to preserve budget for planned action>
  >>> TRANSCRIPT END
  
  Conversation transcript omitted due to size.
  
  The Codex agent has requested the following action:
  >>> APPROVAL REQUEST START
  Retry reason:
  Sandbox blocked outbound network access.
  
  Assess the exact planned action below. Use read-only tool checks when local state matters.
  Planned action JSON:
  {
    "tool": "network_access",
    "target": "https://example.com:443",
    "host": "example.com",
    "protocol": "https",
    "port": 443
  }
  >>> APPROVAL REQUEST END
  ```
  
  ### After
  ```
  The following is the Codex agent history whose request action you are assessing...
  >>> TRANSCRIPT START
  [1] user: Please investigate why uploads to example.com are failing and retry if needed.
  [8] user: If the request looks correct, go ahead and try again with network access.
  [9] tool shell call: {"command":["curl","-X","POST","https://example.com/upload"],"cwd":"/repo"}
  [10] tool shell result: sandbox blocked outbound network access
  >>> TRANSCRIPT END
  
  Some conversation entries were omitted.
  
  The Codex agent has requested the following action:
  >>> APPROVAL REQUEST START
  Retry reason:
  Sandbox blocked outbound network access.
  
  Assess the exact planned action below. Use read-only tool checks when local state matters.
  Planned action JSON:
  {
    "tool": "network_access",
    "target": "https://example.com:443",
    "host": "example.com",
    "protocol": "https",
    "port": 443
  }
  >>> APPROVAL REQUEST END
  ```

  Owen Lin · 2026-04-07 10:19:16 -07:00
  0b9e42f6f7
• Fix nested exec thread ID restore (#16882)

  Addresses #15527
  
  Problem: Nested `codex exec` commands could source a shell snapshot that
  re-exported the parent `CODEX_THREAD_ID`, so commands inside the nested
  session were attributed to the wrong thread.
  
  Solution: Reapply the live command env's `CODEX_THREAD_ID` after
  sourcing the snapshot.

  Eric Traut · 2026-04-07 09:26:22 -07:00
  feb4f0051a
• Stabilize flaky multi-agent followup interrupt test (#16739)

  Problem: The multi-agent followup interrupt test polled history before
  interrupt cleanup and mailbox wakeup were guaranteed to settle, which
  made it flaky under CI scheduling variance.
  
  Solution: Wait for the child turn's `TurnAborted(Interrupted)` event
  before asserting that the redirected assistant envelope is recorded and
  no plain user message is left behind.

  Eric Traut · 2026-04-07 09:24:14 -07:00
  3b32de4fab
• chore: keep request_user_input tool to persist cache on multi-agents (#17009)
  jif-oai · 2026-04-07 16:53:31 +01:00
  4cc6818996
• [codex] reduce module visibility (#16978)

  ## Summary
  - reduce public module visibility across Rust crates, preferring private
  or crate-private modules with explicit crate-root public exports
  - update external call sites and tests to use the intended public crate
  APIs instead of reaching through module trees
  - add the module visibility guideline to AGENTS.md
  
  ## Validation
  - `cargo check --workspace --all-targets --message-format=short` passed
  before the final fix/format pass
  - `just fix` completed successfully
  - `just fmt` completed successfully
  - `git diff --check` passed

  pakrym-oai · 2026-04-07 08:03:35 -07:00
  413c1e1fdf
• chore: hide nickname for debug flag (#17007)
  jif-oai · 2026-04-07 11:31:13 +01:00
  99f167e6bf
• chore: send_message and followup_task do not return anything (#17008)
  jif-oai · 2026-04-07 11:26:36 +01:00
  68e16baabe
• feat: drop agent ID from v2 (#17005)
  jif-oai · 2026-04-07 10:56:01 +01:00
  2a8c3a2a52
• Honor null thread instructions (#16964)

  - Treat explicit null thread instructions as a blank-slate override
  while preserving omitted-field fallback behavior.
  - Preserve null through rollout resume/fork and keep explicit empty
  strings distinct.
  - Add app-server v2 start/fork coverage for the tri-state instruction
  params.

  Ahmed Ibrahim · 2026-04-07 04:10:19 +00:00
  24c598e8a9
• Disable env-bound tools when exec server is none (#16349)

  ## Summary
  - make `CODEX_EXEC_SERVER_URL=none` map to an explicit disabled
  environment mode instead of inferring from a missing URL
  - expose environment capabilities (`exec_enabled`, `filesystem_enabled`)
  so tool building can gate behavior explicitly and future
  multi-environment work has a clearer seam
  - suppress env-backed tools when the relevant capability is unavailable,
  including exec tools, `js_repl`, `apply_patch`, `list_dir`, and
  `view_image`
  - keep handler/runtime backstops so disabled environments still reject
  execution if a tool path somehow bypasses registration
  
  ## Testing
  - `just fmt`
  - `cargo test -p codex-exec-server`
  - `cargo test -p codex-tools
  disabled_environment_omits_environment_backed_tools`
  - `cargo test -p codex-tools
  environment_capabilities_gate_exec_and_filesystem_tools_independently`
  - remote devbox Bazel build via `codex-applied-devbox`:
  `//codex-rs/cli:cli`

  starr-openai · 2026-04-06 17:22:06 -07:00
  a504d8f0fa
• [codex-analytics] add protocol-native turn timestamps (#16638)

  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/16638).
  * #16870
  * #16706
  * #16659
  * #16641
  * #16640
  * __->__ #16638

  rhan-oai · 2026-04-06 16:22:59 -07:00
  756c45ec61
• Add spawn context for MultiAgentV2 children (#16746)
  Ahmed Ibrahim · 2026-04-03 19:56:59 -07:00
  8a19dbb177
• remove temporary ownership re-exports (#16626)

  Stacked on #16508.
  
  This removes the temporary `codex-core` / `codex-login` re-export shims
  from the ownership split and rewrites callsites to import directly from
  `codex-model-provider-info`, `codex-models-manager`, `codex-api`,
  `codex-protocol`, `codex-feedback`, and `codex-response-debug-context`.
  
  No behavior change intended; this is the mechanical import cleanup layer
  split out from the ownership move.
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Ahmed Ibrahim · 2026-04-03 00:33:34 -07:00
  af8a9d2d2b