Commit Graph
4948 Commits
Author SHA1 Message Date
Adam Perry @ OpenAI 55e5158e18 Improve tracing for nested tool calls and exec processes (#41950)
## Why

Code-mode callbacks can outlive their initial request and run in separate tasks,
so their trace context must be preserved explicitly.

## What changed

- Preserve the execution context for code-mode callbacks and add spans for
  nested tool invocations in the runtime and dispatch broker.
- Propagate each tool invocation span as the parent of its streamed gRPC
  callback, falling back to the outer execution context when needed.
- Add a `codex.exec_server.process` span for each process lifetime, including
  its process ID and completion result, without retaining the request span.

GitOrigin-RevId: a6059e34d895416f5517e51dad6ca0078355adca
2026-09-01 01:00:50 +00:00
Adam Perry @ OpenAI c2e5692e2c Expand extension permission regression coverage (#41946)
## What changed

- Verify image-generation extensions rebind permissions on every turn, preserving session grants while expiring turn-only grants.
- Cover executor skill reference reads under current filesystem permissions, including paginated reads, permission changes, and edits between pages.
- Verify oversized live executor skill prompts emit a warning without replacing previously injected prompt content.

GitOrigin-RevId: 1fc8eef409fa65db4bb1ab6a00408fe72c9e938f
2026-09-01 00:42:19 +00:00
Benjamin Carlsson 9c7edd4bc3 Add Vim undo to the TUI composer (#41941)
## Why

Composer drafts include attachments, mention targets, and deferred paste payloads in addition to visible text. Vim undo needs to restore that complete state as a single edit.

## What changed

- Add bounded, draft-level Vim undo history, with `u` as the configurable default binding in normal mode.
- Group complete Vim commands and insert sessions into undo steps, including direct composer changes such as pastes and attachments.
- Preserve undo, repeat, and search state when a reverse-history preview is canceled, and start fresh history when another prompt is accepted.

## Testing

- Cover grouped edits, custom bindings, history and search interactions, attachments, and large paste payloads.

GitOrigin-RevId: 12ecdb3c34a2d66f5d856aa2f82dc15bd91b230b
2026-09-01 00:21:22 +00:00
jif 13d75cd1c3 Attach failed Guardian reviews to diagnostic reports (#41936)
## What changed

- Retain bounded, process-local records for failed Guardian reviews, including the reviewed action, decision, status, model, instructions, and reviewer history.
- Add recent records from the reported thread and its descendants to log-enabled report uploads as `auto-review-failures.jsonl`.
- Preserve the action and decision while omitting oversized reviewer context, and exclude successful, ephemeral, and capture-disabled reviews.

## Testing

- Cover denied and invalid decisions, cleaned-up ephemeral reviewers, descendant-thread selection, record count and byte limits, and oversized-context fallback.

GitOrigin-RevId: 5f12f7605041c3c84e826e6bac1cf06b1518ab24
2026-08-31 23:44:41 +00:00
Jennifer Zhao 981d6b652b Omit undersized WAV output from Code Mode (#41934)
## Why

Audio models cannot reliably encode tool-generated clips shorter than 25 ms.

## What changed

- Measure the available audio frames in base64-encoded PCM and IEEE float WAV outputs.
- Replace clips under 25 ms with explanatory text while preserving surrounding Code Mode output.
- Leave clips at or above the threshold and unrecognized audio formats unchanged.

## Testing

- Cover the duration boundary across multiple sample rates and all supported `audio()` input forms.
- Verify bounded and truncated WAV chunks, output after `yield_control()`, and end-to-end mixed text and audio output.

GitOrigin-RevId: 342b4bdbc65db4238580f9cdc372763c2576eca5
2026-08-31 23:36:04 +00:00
Charlie Marsh a62ff9a5d4 Report configured sandbox policy consistently (#41933)
## Why

Sandbox diagnostics could report `read-only` when a configured writable root did not yet exist, because policy labeling used filesystem-aware runtime root resolution.

## What changed

- Derive diagnostic policy labels from configured writable roots without inspecting the filesystem. Runtime sandbox authorization continues to use filesystem-aware resolution.
- Capture sandbox labels once per turn and reuse them for response metadata and tool-result metrics.

## Testing

Add coverage for missing project roots, denied roots, and deny rules on project subpaths.

GitOrigin-RevId: ccbdb8c32a1f44bfa63ae4d2ae1f9cc408e66b9c
2026-08-31 23:29:20 +00:00
jif 4ac20a7f74 Increase Guardian message transcript limits (#41931)
## What changed

- Raise the Guardian message transcript budget from 10,000 to 20,000 tokens.
- Raise the per-message entry limit from 2,000 to 5,000 tokens.

GitOrigin-RevId: 93a92e3d806fd3bf005e6c27964babd7ed2f948e
2026-08-31 23:26:25 +00:00
iceweasel-oai c4350b4ca2 Use executor path context for permission preapproval (#41928)
## Why

Permission grants can belong to an executor whose path convention differs from
the local host, such as a Windows remote environment. Matching those grants
against a host-native working directory can reject valid permissions.

## What changed

- Normalize, materialize, and compare additional filesystem permissions using
  the selected executor's URI-based sandbox context.
- Apply the same context-aware preapproval flow to `exec_command`,
  `apply_patch`, and extension tools.
- Fail closed when symbolic temporary-directory or project-root permissions
  cannot be resolved from executor metadata, while accepting opaque working
  directory URIs when requested paths use the executor's convention.

## Testing

- Added coverage for reusing a Windows permission grant from a non-Windows
  host, resolving symbolic temporary-directory grants, and normalizing paths
  with an opaque Windows working directory.

GitOrigin-RevId: aee54350a25430a0443f8319e2bb0bbdc4f44282
2026-08-31 22:58:26 +00:00
Adam Perry @ OpenAI 9127f21890 Test repository-wide Rust formatter discovery (#41925)
## What changed

- Exercise Rust source discovery through a mocked `git ls-files` call, including files outside `codex-rs`, paths containing spaces, and stale entries that no longer exist.
- Assert that the formatter invokes `rustfmt` from `codex-rs` with the repository configuration in both format and check modes.
- Keep the multiline argument-comment lint fixture stable under formatting and update affected Rust test files to the expected style.

GitOrigin-RevId: 0cfffde1bb91bf620d2118bed1efc68466c0cca6
2026-08-31 22:47:53 +00:00
guinness-oai 64c9cde458 Record realtime conversation history in Core (#41924)
## Why

Realtime history should be recorded consistently for every Core host, including
when no app-server event listener is attached.

## What changed

- Move transcript segmentation, session boundaries, and backing-agent artifact
  promotion into Core for paginated threads.
- Persist canonical realtime items through the thread store in event order and
  emit dedicated history lifecycle events for hosts to present.
- Translate those Core events into the existing app-server realtime item
  notifications without app-server persisting the items a second time.

## Testing

- Cover Core-only persistence across repeated sessions, ephemeral sessions,
  accepted and rejected steering, typed input ordering, and artifact promotion.
- Verify app-server notifications correspond to the persisted timeline.

GitOrigin-RevId: 7cbef14129d77f6d6d7099b733be91f5279c55f5
2026-08-31 22:38:23 +00:00
Zahan Malkani 34c4f7e72d Allow per-call sideband endpoints for existing realtime calls (#41923)
## What changed

- Add an in-process `sideband_base_url` override to `ConversationStartTransport::ExistingCall`, while keeping app-server requests on the configured or default endpoint.
- Prefer the per-call endpoint when attaching and reconnecting a sideband, falling back to `experimental_realtime_ws_base_url` when no override is supplied.
- Preserve runtime authentication headers on the selected endpoint without adding bearer authorization.

## Testing

- Cover configured and per-call endpoint selection, authentication headers, call-specific handshake paths, and reconnect behavior.

GitOrigin-RevId: 16c439fe0a9ff8bcdda4ec615bb9983e30935052
2026-08-31 22:29:40 +00:00
olliem-oai 865bbf9a69 Source Guardian REPL policy from model metadata (#41919)
## What changed

- Add `auto_review.node_repl_policy` to model messages for `node_repl` and `cua_repl` reviews.
- Use the reviewer model's configured policy, falling back to the bundled policy when the field is absent and skipping injection when it is explicitly empty.
- Include the effective policy in Guardian session reuse checks and reject unsafe parent-model fallback transitions that would change it.

## Testing

- Cover catalog, bundled, and explicitly empty policies across Node and CUA review paths.
- Verify that policy changes invalidate cached reviewer sessions and incompatible fallback transitions.

GitOrigin-RevId: 51c0bdfed9b464091b6eb47d91ca5a0990d7a315
2026-08-31 22:08:44 +00:00
Tamir Duberstein 9a4b78579a Move the config schema generator into a dedicated crate (#41915)
## What changed

- Add the `codex-config-schema` workspace and Bazel crate for the
  `codex-write-config-schema` binary.
- Preserve `codex-rs/core/config.schema.json` as the default output location.
- Update `just write-config-schema` to run the new crate and remove the schema
  generator's `clap` dependency and binary target from `codex-core`.

GitOrigin-RevId: 7447f97d6e44d1077b16d2d850f8a8add9117ea6
2026-08-31 21:27:51 +00:00
Owen Lin 5f79a92e39 Persist response token usage in rollout history (#41912)
## Why

Resumed threads need to continue per-turn and per-thread token totals without scanning arbitrarily far beyond the latest compaction checkpoint.

## What changed

- Add durable `TokenUsageRecord` rollout items with response, turn, thread, session, and root-turn attribution.
- Restore accumulated usage on resume and snapshot the latest record plus the compaction response ID in compaction checkpoints.
- Preserve root-turn lineage in persisted turn context, while ensuring forked child threads start with their own usage totals.

## Testing

- Cover usage accumulation across multiple responses and resumed turns.
- Cover local and remote compaction checkpoints, invalid remote compaction output, rollout reconstruction, and fork isolation.

GitOrigin-RevId: ef9e0c4a9102a08a2c382be4cdac68c84353c90a
2026-08-31 21:15:38 +00:00
iceweasel-oai b51b07785b Make permission transforms aware of executor path context (#41909)
## What changed

- Add context-aware normalization, materialization, and intersection helpers for additional filesystem permissions.
- Resolve project roots, home-relative deny globs, temporary directories, and filesystem roots from the executor's `FileSystemSandboxPolicyContext` while preserving URI path conventions and symlinked paths.
- Keep deny constraints when intersecting grants across POSIX, Windows, and UNC paths, and reject incompatible path conventions when executor context is available.

## Testing

- Cover cross-convention validation, empty temporary-directory contexts, home-relative deny globs, and rooted deny globs for POSIX, Windows, and UNC paths.

GitOrigin-RevId: 14fd866a17a0ac4a595aa4f0e2fb82bfae1a8838
2026-08-31 20:50:44 +00:00
Bryan Ashley f88ff940c0 Load bounded context after empty wake turns (#41901)
## Why

Paginated threads can accumulate wake turns with no user-message boundary. The
reverse context scan could not use those turns as a bounded replay cutoff, even
when a compaction and its resume state provided everything needed to reconstruct
the latest model context.

## What changed

Treat a full world-state snapshot that survives the latest compaction as a
durable baseline when it is paired with a compatible turn context. This lets the
scan stop at empty wake turns while still scanning further back for patches,
snapshots before compaction, or missing and mismatched turn contexts.

## Testing

Add coverage for repeated empty wake turns and verify that bounded replay
matches full rollout reconstruction across successive compaction windows.

GitOrigin-RevId: ae90c5f939c660ea539fbfc11128cc7259efaa9c
2026-08-31 19:30:05 +00:00
felixxia-oai 032d15cba7 Use shared transcript collection for Guardian reviews (#41870)
## What changed

- Build Guardian review transcripts with `codex-guardian-context` while preserving Guardian-specific filtering and transcript budgets.
- Apply per-entry truncation during collection, including the larger limit for Node REPL output.
- Retain standalone function and custom tool outputs even when their matching calls are unavailable.

## Testing

- Update Guardian transcript tests to cover shared entry types, Node REPL truncation limits, standalone tool outputs, and recent-tool retention.

GitOrigin-RevId: ec73e80c09fe63c3cf100684cb15574d5d6c2c95
2026-08-31 15:56:32 +00:00
jif 2c8cfbf44f Keep history extension tools out of Guardian reviews (#41861)
## What changed

- Initialize Guardian reviewer subthreads with empty extension data.
- Remove the special registration that exposed inherited read-only `history`
  tools in the Guardian tool plan.

GitOrigin-RevId: 7700f033faab125d59d11bc2d82955c67689e3c3
2026-08-31 15:19:38 +00:00
jif 09f4c45068 Preserve user text when Guardian history drops oversized images (#41858)
## Why

User messages with images larger than the Guardian history budget were skipped
entirely, removing any accompanying instructions from retained review context.

## What changed

- Retain the text and message metadata from oversized user messages while omitting
  their images.
- Keep the existing behavior for other oversized history items.

## Testing

- Cover text and metadata retention, content ordering, and the integration path
  with an image larger than the 4 MiB history budget.

GitOrigin-RevId: 91d99609a8d096b87d0f2b1d149f577a00dce699
2026-08-31 15:02:40 +00:00
jif 98a8425e22 Preserve Guardian user answers from current history (#41857)
## What changed

Match recorded user-input tool calls against both the current conversation and
retained review history when collecting Guardian review evidence. This keeps
answers available when their original tool call exists in either history.

GitOrigin-RevId: e511e2d252d31fa8658c34db19f0151699e9a34a
2026-08-31 14:54:13 +00:00
Benjamin Carlsson 9d19c7426e Box the session startup future at its API boundary (#41853)
## What changed

- Make `Session::spawn` return a `BoxFuture` while preserving lazy session
  initialization.
- Prevent the startup wrapper from being inlined so callers do not expose its
  concrete future.
- Await the returned future directly at session creation call sites.

GitOrigin-RevId: 5432745aae1c934b16202716a8d49a8553de2018
2026-08-31 14:43:39 +00:00
jif 305eed102d Preserve Guardian user answers across compaction (#41852)
## Why

Compaction removes the original `request_user_input` tool call from model-visible history, causing its trusted user answer to be omitted from subsequent Guardian reviews.

## What changed

Match recorded user answers against retained review history so they remain available through compaction and review-history eviction. Explicit rollback still removes the associated answer.

## Testing

Extend the Guardian history integration test to verify trusted user answers survive compaction and eviction but not rollback.

GitOrigin-RevId: 00681ee8df51cf36421b6fdc5446565dff3776fe
2026-08-31 14:34:37 +00:00
jif 1c1e17782a Preserve Guardian review evidence across compaction (#41846)
## Why

Context compaction can replace original conversation items that Guardian still needs to review approval-sensitive actions.

## What changed

- Retain a bounded, chronological review history independently of the model's compacted history.
- Keep separate limits for user messages and other transcript items so tool traffic cannot evict user instructions.
- Use the retained evidence for synchronous and asynchronous Guardian transcripts, while resetting it after rollback or history reconstruction.

## Testing

- Cover retention through compaction and eviction, reset behavior after rollback, independent size limits, and asynchronous transcript construction.

GitOrigin-RevId: c5851e992820504fc18de8cfec7f6f9f1b69f316
2026-08-31 13:57:59 +00:00
Tamir Duberstein e45226e771 Use the async stack budget for approval reviews (#41840)
## What changed

- Define the shared 16 MiB thread stack budget in `codex-async-utils`.
- Use it for both the async main/runtime threads and the dedicated approval-review thread.

GitOrigin-RevId: c825669e1545bcfaeaaaa07066dc63874f46630f
2026-08-31 13:44:12 +00:00
pmccrary-oai d58d0e5841 Allow models to enable token budgeting by default (#41803)
## What changed

- Add model metadata flags for enabling token budgeting and its history-notes extension.
- Apply those activation defaults once at thread startup when the user has not explicitly configured token budgeting, while respecting managed feature requirements.
- Continue resolving model-owned prompts for the active model so model switches can use their own token-budget guidance.

## Testing

- Update the token-budget integration test to verify that model metadata activates the feature without manual configuration.

GitOrigin-RevId: 73a32623eaeabb9243e240c43da7a5e7e93e9a19
2026-08-31 08:31:23 +00:00
rka-oai a9519cbcdd Make the update_plan tool opt-in (#41744)
## What changed

- Default `tools.update_plan.enabled` to `false`; users can explicitly enable it to expose `update_plan`.
- Remove bundled `update_plan` guidance from model, collaboration-mode, multi-agent, compaction, prewarm, and goal-continuation prompts when the tool is disabled.
- Preserve custom base instructions, model catalog instructions, collaboration policies, and user goal text even when they mention planning or `update_plan`.

## Testing

- Cover default and explicitly enabled tool registration, prompt consistency across request paths, and preservation of custom instructions.

GitOrigin-RevId: a53964e6e72f98e2557dd3090fdb7caccb956527
2026-08-31 00:53:30 +00:00
pmccrary-oai b7cd519c76 Mark history ingestion requests in turn metadata (#41743)
## What changed

- Set `history_ingest_requested` to `true` in Responses turn metadata when the
  history-notes token-budget extension is enabled.
- Reserve the metadata key so caller-provided metadata cannot override the
  core-owned value, and omit it when the extension is disabled.

GitOrigin-RevId: e750bcb729292c407e1d443857cdb584a88aac97
2026-08-31 00:36:47 +00:00
Eric Traut 94cbbddafc Support package-style MCP server names (#41700)
## What changed

- Allow MCP server names to contain `:`, `@`, `/`, and `.`, enabling names such as `npm:@modelcontextprotocol/server-sequential.thinking`.
- Preserve these names across `mcp add`, `get`, `list`, and `remove`, runtime tool namespaces, and OAuth credential lookup.
- Quote non-bare server names in generated `config.toml` recovery hints and keep similarly escaped OAuth credential names isolated.

## Testing

- Add CLI and runtime round-trip coverage for npm-style names.
- Add snapshot coverage for quoted recovery hints and a regression test for OAuth credential-name collisions.

GitOrigin-RevId: 97e9353cdbc544db4eb2377ddbfa1d2d539b1e04
2026-08-30 16:45:34 +00:00
jif 88f776588f Set working directories for environment MCP tests (#41683)
## Why

Environment-backed stdio MCP servers have no host-local working-directory
fallback, so their test fixtures must provide a workspace explicitly.

## What changed

- Set the fixture workspace as `cwd` for environment-backed MCP servers across
  the core integration tests.
- Reuse the same test environment when configuring MCP servers and building
  fixtures that need an explicit working directory.

GitOrigin-RevId: e38f2029e01fc1377cdc34d01a392ad310419766
2026-08-30 14:04:06 +00:00
jif 0a12b855a0 Preserve Guardian authorization across history compaction (#41660)
## Why

Compaction and host-injected context can rewrite the model-visible conversation
without changing what the user authorized. Treating those updates as authorization
changes prevents Guardian from reusing an otherwise valid review.

## What changed

- Track a host-owned user-message revision separately from the conversation history
  generation.
- Advance the revision for genuine user messages and history resets, while preserving
  it across compaction and internal context injection.
- Use message content-kind metadata to distinguish host context from user input,
  conservatively treating unknown or incomplete metadata as user authorization.

## Testing

Added coverage that cached Guardian authorization survives compaction and internal
context, but is invalidated by user input and rollback.

GitOrigin-RevId: c7960fa182d1686042c23764d2abc58acbc4b882
2026-08-30 11:56:24 +00:00
rka-oai 28327355b8 Update tests for default-enabled update_plan (#41630)
## What changed

- Cover the default, explicitly enabled, and explicitly disabled states of
  `tools.update_plan.enabled`.
- Verify prompt tool lists remain consistent across requests, including when
  custom base and developer instructions are configured.
- Explicitly enable `update_plan` in existing fixtures that depend on the tool.

GitOrigin-RevId: 3be279cb5195dfc5892c2c8ff6a1461fac879309
2026-08-30 07:40:36 +00:00
Benjamin Carlsson 63d213884d Add Vim search motions to the composer (#41586)
## What changed

- Add draft-local forward and backward literal search with `/` and `?`, plus
  wrapped repeat navigation with `n` and `N`.
- Support search motions after delete, change, and yank operators, while keeping
  queries separate from the draft and skipping atomic elements and partial
  grapheme matches.
- Render and edit the query in the composer footer, highlight matches, and add
  configurable `tui.keymap.vim_search` bindings to the keymap picker and schema.

## Testing

- Cover navigation, wrapping, operator composition, repeat behavior, Unicode
  graphemes, atomic elements, query editing, paste handling, and rendering.

GitOrigin-RevId: 087b080ff8fd74e48456c6b899c07ea5eed38e0c
2026-08-30 00:42:00 +00:00
rhan-oai b8c86376a2 Fix proactive multi-agent instruction grammar (#41570)
GitOrigin-RevId: ae5f9e112a30142b0cb6be0a9e2197d05c28291b
2026-08-29 20:42:12 +00:00
rhan-oai f5636bb733 Restore thread cwd from owned settings snapshots (#41567)
## Why

Resuming a thread without an explicit `cwd` should restore that thread's latest
retained setting. Forked history can contain settings copied from another
thread, while compaction can move the latest setting outside the replay window.

## What changed

- Record the owning thread ID on new settings snapshots and only use snapshots
  owned by the resumed thread when restoring `cwd`. Older snapshots without an
  owner remain readable but do not override the startup `cwd`.
- Checkpoint the current settings after compaction and serialize checkpoints
  with settings updates so the retained history contains an accepted, current
  snapshot.
- Cover resume behavior across compaction, forks, reverts, legacy histories,
  and concurrent settings updates.

GitOrigin-RevId: 1efc9cf55472d6b88c465c4efe44672a232dbf64
2026-08-29 19:57:06 +00:00
Eric Traut 4210c08def Preserve turn lineage across goal continuations (#41562)
## Why

Automatic goal continuations should remain attributable to the turn that created the goal. External input, hook context, or goal edits can make that attribution ambiguous and must not leave stale lineage metadata behind.

## What changed

- Carry the trusted root and previous parent turn through successive automatic goal continuations.
- Invalidate stored lineage when external context reaches an active turn or when a goal is edited or cleared.
- Preserve lineage for async hook results only when they belong to the receiving turn.

## Testing

- Cover goal continuations across intervening user turns and external objective edits.
- Cover active, buffered, and externally injected hook or response context.

GitOrigin-RevId: 22ccc07961cd0ed8f4b17912b7efa416b342bf50
2026-08-29 18:51:11 +00:00
Tamir Duberstein 6478a751fd Organize bundled Rust resources under asset directories (#41477)
## Why

The `core` and `tui` Bazel targets treated nearly their entire crate trees as
compile-time data, mixing embedded runtime resources with source files and test
fixtures.

## What changed

- Move embedded resources for `core` and `tui` into dedicated `assets/`
  directories and update their `include_str!` paths.
- Restrict Bazel compile data to explicit asset and frame directories.
- Move test-only prompts into `tests/fixtures`, resolve the core prompt through
  `find_resource!`, and reuse the integration-test file glob when assembling
  Bazel test data.

GitOrigin-RevId: eee9b0e41df77ea2604215a7f7333a6fe8317bfa
2026-08-29 06:05:28 +00:00
Charlie Marsh 0b45b171ca Preserve permissions when updating session metadata (#41464)
## What changed

- Defer legacy sandbox policy projection until a working-directory change may require rebinding project-root writes.
- Keep client name and version updates from resolving filesystem paths or altering the existing permission snapshot.

## Testing

- Add regression coverage for updating client metadata with a managed, restricted filesystem policy that includes both a writable path and a nested denied path.

GitOrigin-RevId: d84dbcd09b9d1961a11b2889d79479e30eb54149
2026-08-29 03:59:21 +00:00
rhan-oai 3c062df036 Source async user message descriptions from the model catalog (#41461)
## What changed

- Add model message metadata for built-in tool descriptions.
- Use the active step model's catalog description for `send_user_message_async`, including after a mid-turn model change.
- Fall back to the built-in description when catalog metadata is absent, while preserving an explicitly empty description.

## Testing

- Cover catalog serialization, fallback and empty-value behavior, and model changes within a turn.

GitOrigin-RevId: 72b953214ab9708931065321debf12133f8d2d40
2026-08-29 03:44:01 +00:00
rhan-oai 03861e69ef Source proactive multi-agent instructions from the model catalog (#41457)
## What changed

- Add an optional `proactive` multi-agent mode message to model metadata.
- Use the catalog's proactive message for `Ultra` reasoning when no general mode hint is configured. A missing value falls back to the built-in proactive instructions, while an empty value suppresses the mode message.
- Keep explicit mode behavior for other reasoning efforts and refresh the applicable catalog message when the model changes.

## Testing

- Cover proactive overrides, built-in fallback, empty-value suppression, mode-hint precedence, non-`Ultra` behavior, and model switches.

GitOrigin-RevId: da0a9ebd9b58cf04ef13a703c210e5da2eed0884
2026-08-29 03:28:19 +00:00
Samuel Yuan 2181224dad Support app targets in executor plugin hooks (#41456)
## What changed

- Admit the curated remote Browser plugin's `Stop` and `SubagentStop` hooks when its listed `browser.turn_ended` tool matches the expected connector and is enabled by app policy.
- Carry trusted app routing metadata and the MCP environment through hook registration and execution.
- Register hooks from multiple executor environments, while deduplicating cleanup calls that share an event, MCP environment, server, and tool.

## Testing

- Cover Browser and Computer Use cleanup through separate MCP routes, including user- and managed-policy disablement.
- Verify routing metadata, environment selection, multi-environment registration, and target deduplication.

GitOrigin-RevId: 66de088fd201b9ed0db8b97c23d33de88135120d
2026-08-29 03:14:35 +00:00
Adam Perry @ OpenAI 48e22a5fa0 Report code mode host request durations (#41452)
## Why

Code mode wall time should measure the host operation itself, without including
client-side response delays or idle time between requests.

## What changed

- Measure each execute, wait, and terminate request in the code mode host.
- Carry the duration through the stdio and gRPC protocols and use it for
  model-visible wall time.
- Emit a structured `codex.code_mode.host_timing` event correlated with the
  conversation, turn, tool call, and cell.

## Testing

- Cover successful and failed execution timing, delayed response reads,
  repeated waits, termination, and missing cells across stdio and gRPC.
- Verify timing survives protocol serialization and is reflected in app-server
  model output and structured telemetry.

GitOrigin-RevId: d24af30c3fc5820521b4beba1f9970714dad6482
2026-08-29 02:52:58 +00:00
victor-openai eec4a23cb1 Support openai/elicitation form requests (#41447)
## What changed

- Advertise `openai/elicitation` form support when the client declares an
  object-valued `form` capability, without deriving it from the legacy
  `openai/form` capability.
- Handle `openai/elicitation/create` requests in `form` mode and forward their
  metadata and opaque schema through app-server as `openaiForm`, preserving
  `x-openai-*` annotations.
- Keep legacy form handling independent and have the TUI automatically decline
  the new form requests it cannot render.

## Testing

- Add an app-server round-trip test for capability negotiation, request
  forwarding, and accepted responses.
- Extend MCP capability filtering coverage for `openai/elicitation.form`.

GitOrigin-RevId: 88f39257bffafe4ee98a9c910e38507843cd7eeb
2026-08-29 02:43:10 +00:00
Krish Chainani c2abf869d5 Run executor hooks for interrupted turns (#41432)
## Why

Executor-scoped cleanup hooks need to observe an interrupted turn as well as a
normally completed one.

## What changed

- Allow bundled executor plugins to register the allowlisted `Interrupt` hook
  alongside `Stop`, while preserving multiple allowed hook entries from the
  selected executor environment.
- Run interrupt hooks with the interrupted turn's last step discovery and turn
  metadata. Turns without a step context do not reuse discovery from an earlier
  turn.
- Keep executor-scoped interrupt hooks asynchronous and omit public hook
  lifecycle events for them, matching executor `Stop` hook behavior.

## Testing

Added coverage for hook filtering and registration, interrupt execution and
metadata propagation, environment selection, and turns without a step context.

GitOrigin-RevId: f0c536b3382a37cf3bf693c4573d21f6f66ace4e
2026-08-28 23:03:05 +00:00
Krish Chainani 0d22692962 Retain the last selected step context for each turn (#41429)
## What changed

- Store the most recently captured execution `StepContext` in the active turn state.
- Keep speculative model-fallback captures from replacing that context, and update it only when the fallback is selected for remote compaction.
- Preserve the retained context when a turn completes or is interrupted.

## Testing

- Add coverage for completed and interrupted turns, successful primary compaction, fallback compaction, and interruption while a fallback is running.

GitOrigin-RevId: c7dee36ec8e88ba2f4fb4a9c0322e5c86a0caf0e
2026-08-28 22:26:23 +00:00
jif f9cdc90c2c Preserve context baselines across nested agent forks (#41424)
## What changed

- Treat a surviving full world-state snapshot as a context baseline when a fork removes the associated user message.
- Restore the previous turn settings and reference context from that baseline, without treating the segment as a user turn for rollback.
- Ignore partial snapshots and full snapshots superseded by compaction.

## Testing

- Cover resumed rollout reconstruction with removed task messages, partial snapshots, and compaction.
- Verify nested agents inherit developer instructions and environment context exactly once across history modes and compacted histories.

GitOrigin-RevId: 9f9f6992d7ea8cff9ac82a7fcdf0c8fb764db81c
2026-08-28 21:53:14 +00:00
pakrym-oai f742dabc6f Support per-tool MCP output limits (#41421)
## What changed

- Add a positive `output_token_limit` setting to each entry under an MCP server's `tools` configuration.
- Apply the most restrictive limit when plugin and user policies overlap, while keeping approval policy independent.
- Carry the effective MCP output budget in conversation history so tool output, post-tool hook responses, and resumed sessions use the same truncation limit.

## Testing

- Cover configuration parsing, serialization, schema validation, and plugin policy merging.
- Cover MCP output below and above the configured limit, post-tool hook responses, and session resume.

GitOrigin-RevId: d0beb4fca9ba6055d9e1d31c137373b465d50d61
2026-08-28 21:40:23 +00:00
Vivian Fang 03147407e3 Add app-server notification media filtering (#41416)
## What changed

- Add the disabled-by-default `omit_app_server_notification_media` feature.
- When enabled, remove inline image and audio content from `item/started`,
  `item/completed`, and `rawResponseItem/completed` notifications, including
  tool output and image-generation results.
- Keep the media in model input; the filter only changes app-server
  notifications.

## Testing

- Verify that image content is absent from all three notification types while
  the model request still receives it.

GitOrigin-RevId: 9a4434d18a3dac6d67c2e0c3723ff4595a9b3797
2026-08-28 21:06:35 +00:00
xl-openai d9511fb788 Refresh MCP HTTP helper headers after authorization failures (#41400)
## What changed

- Re-run the HTTP headers helper after a same-origin `POST` receives a `401` or `403`, and retry the request once when the effective headers changed.
- Share refreshes across concurrent rejected requests, retain the previous headers when refresh fails, and keep the retry within the original timeout.
- Allow helpers to supply `Authorization` while preserving explicit OAuth or bearer credentials, OAuth insufficient-scope challenges, and redirect safety checks.

## Testing

- Cover rotating helper headers for MCP tool calls and same-origin OAuth token refreshes.
- Cover concurrent rejections, failed and unchanged refreshes, retry limits, timeouts, and redirects.

GitOrigin-RevId: c662edefdb1cd2876d9d02545a72d5bd6739864f
2026-08-28 19:29:51 +00:00
jif b836aecd4d Preserve one-shot exec when unified exec is disabled (#41393)
## Why

Managed configuration can disable resumable unified execution while leaving shell tools enabled. This should not remove command execution entirely or grant access to retained processes.

## What changed

- Keep `exec_command` available in completion-only mode when `unified_exec` is disabled.
- Remove `tty`, `yield_time_ms`, `session_id`, and `write_stdin` from that mode, and add a `timeout_ms` argument.
- Terminate one-shot commands on timeout or turn cancellation, reporting timed-out commands with exit code 124.

## Testing

Added integration coverage for tool availability, timeout cleanup, and interruption cleanup under managed configuration.

GitOrigin-RevId: a382d34f922fdc4ba52889272c6db985abd42e47
2026-08-28 19:04:54 +00:00
Eddie Chen 60fc699560 Give Guardian classifications distinct turn identities (#41385)
## What changed

- Generate a UUIDv7 turn ID for each Guardian classification and preserve it across retries.
- Record the owning turn as `parent_turn_id` and propagate its trusted `root_turn_id` when known, including through the tool lifecycle extension API.
- Omit ambiguous or unknown root lineage and keep classification identities distinct when reusing Guardian sessions and WebSocket connections.

## Testing

- Cover classification metadata across retries, connection reuse, concurrent samples, auth refresh, and consecutive owning turns.

GitOrigin-RevId: 78757f2ad031844e4b545802f634c678a9ee2298
2026-08-28 18:23:47 +00:00