## Why
Streaming answers and plans need to wrap to the conversation's allocated width, which can differ from the terminal width. Resizing while reading earlier output should not report new activity unless new output has arrived.
## What changed
Reflow live streams when preparing the owned conversation layout, using its allocated width. Update the observed live revision after presentation-only reflow so it does not trigger `New activity`, while preserving notifications for unseen output.
## Testing
Add regression coverage for streaming answer and plan tables across width changes, including a narrow-layout snapshot, preservation of the reading position, and activity notifications when new output arrives before a resize.
GitOrigin-RevId: a9831c5a1a5ffb7477e7868d4ecca430d6ee50f3
## What changed
- Add `currentAccountOnly` to `thread/list` and `thread/search`, defaulting to `false`, and enable it for TUI history discovery, resume pickers, and task mentions.
- Mark newly created threads as account-scoped and require each recorded creator user or account ID to match the current login. Older threads and threads without creator IDs remain shared; API-key logins continue to see all local history.
- Preserve account scope through resume and revert, including fallback to original rollout metadata when an older binary drops the marker. Forks receive new-thread scope.
- Skip unreadable rollout headers in scoped discovery and filter search candidates before reading snippets. Direct access by thread ID remains available.
## Testing
Add coverage for account matching, shared legacy history, list page refilling, search pagination, API-key visibility, and scope preservation across reverts. Extend rollout lookup coverage to compressed active and archived files.
GitOrigin-RevId: aa374f5e69165be5a71c0716ded1b105f5fb51e0
## What changed
Expose `launch_in_memory()` and `LocalServer` to run a loopback HTTP endpoint with generated bearer credentials. Runners register a shared in-memory board per session through `add_board(session_id, host)`, using `MessageBoardHost` for membership, clocks, and notifications without a SQLite registry.
The handle exposes the endpoint and authorization header for MCP configuration, including plugin endpoint overrides. Dropping it cancels HTTP and MCP sessions; `shutdown().await` also waits for completion.
## Testing
Extend the parent/child HTTP integration scenario to cover the in-memory launcher, plugin endpoint overrides, host-provided timestamps, authentication and invalid identity rejection, and operation without creating a SQLite board database.
GitOrigin-RevId: e1cae295724a35f4eded290ba8a4e19926b98c13
## What changed
Add a `message-board` plugin with connection metadata for the HTTP MCP server. It defaults to `http://127.0.0.1:7777/mcp`, uses `CODEX_MESSAGE_BOARD_TOKEN` for bearer authentication, and marks the server as required.
Document installation and endpoint overrides through `mcp_servers.codex_message_board`. Installing the plugin does not start the server.
## Testing
Extend the HTTP board integration scenario to cover both direct configuration and plugin installation, verifying that a child can post a decision and its restarted parent can discover the same board and read it. Add a plugin context snapshot and include the plugin resources in Bazel test data.
GitOrigin-RevId: d6cf797caaa4dbdcd45114c2ad0a6bd695cf056f
## What changed
- Add `codex-message-board-mcp` to serve discussion tools at `/mcp` through ordinary MCP configuration, backed by the existing SQLite board and a read-only Codex registry.
- Require bearer authentication and validate `threadId` and `sessionId` metadata against persisted agent membership. Support additional allowed HTTP hosts with `--allowed-host`.
- Expose a reusable `serve_http` library entry point and scope retry deduplication to the caller within an MCP session.
## Testing
Add integration coverage for a child posting and its restarted parent reading the persisted board, including reads while a database writer lock is held. Cover invalid tokens, disallowed hosts, missing caller metadata, invalid membership, and startup without an existing registry.
GitOrigin-RevId: 5e3d71eaaf120169e2585acd0b5f84df1b402f00
## What changed
Allow `guardian_review` to assess a final recorded `request_permissions` call without granting permissions. Build the review action using the same permission request preparation as live review, while continuing to reject earlier permission requests in the recorded history.
Return no assessment when the approval policy is `never` or granular policy disables permission requests.
## Testing
Add coverage comparing live and direct permission review inputs, plus tests that disallowed requests return no assessment without contacting the reviewer.
GitOrigin-RevId: cb5935202b0980e657b023f840a0186cea5e0b74
## What changed
Allow `guardian_review` to assess recorded native `apply_patch` calls alongside `exec_command` calls. Use the existing patch preparation and approval logic without applying the patch, and skip assessment when approval is unnecessary.
## Testing
Add coverage that compares direct and live patch review inputs, verifies that an allow decision leaves files unchanged, and checks that writable files skip review without writes or model requests.
GitOrigin-RevId: 8634ad8c00a67bcac9e7930ebf89c02707c3a6f7
## What changed
- Add `model_messages.plugins` overrides for generic usage guidance, selected-plugin hints, and recommendation introductions, with independent fallback to bundled wording for missing or invalid fields.
- Validate text limits and required template placeholders while keeping plugin identities, available capabilities, and eligibility controlled by the client.
- Track generic guidance changes across model switches and session resume, emitting replacement or retirement notices and supporting legacy snapshots and retained history.
## Testing
Add unit and scenario coverage for sparse overrides, literal text preservation, template validation, UTF-8 size bounds, capability filtering, recommendation fallback, and guidance recovery after resume.
GitOrigin-RevId: 148b658c2d8490c9d0dc208addbee1be5342a5f5
## What changed
Add the disabled-by-default `cli_resume_account_check` feature. When enabled for `codex-tui` and `codex_exec`, reject resuming or attaching to a local thread if its recorded creator user or workspace differs from the current ChatGPT account. Return an error directing the user to sign in with the original account.
Carry creator IDs through stored thread metadata and check them before loading resume history. Preserve existing behavior for untagged threads, other clients, and authentication modes without a comparable ChatGPT account.
## Testing
Add integration coverage for account and workspace mismatches, matching accounts, legacy and paginated history, ID and path lookup, and the feature's default and bypass behavior. Verify that switching back to the original account permits attachment to a loaded thread and that creator metadata remains unchanged.
GitOrigin-RevId: a3ab089254703417dde0890a5f8d6326c4cbb75a
## Why
Timestamp-only cursors can skip threads that share the last result's timestamp, including rollout files created in the same second.
## What changed
- Include thread IDs as tie-breakers in time-sorted listing and search cursors, and use them when resuming filesystem scans and database queries.
- Share filesystem sort-key and cursor construction so continuation cursors match the listing order, including filename-based creation times.
- Preserve support for legacy timestamp-only cursors and their existing behavior of skipping ties.
## Testing
Update regression coverage for pagination through filesystem timestamp ties, legacy cursors, thread IDs in database fallback cursors, and search cursors for all time-based sort keys.
GitOrigin-RevId: 455b95452849e6ffe20a27d7bdcec864f2e8135a
## Why
Input accepted while a regular turn was flushing its transcript could miss the final pending-input check and remain unprocessed when the turn completed.
## What changed
Check pending input atomically with closing steer admission. If input was accepted, resume sampling in the same turn while preserving MCP startup requirements, and complete the turn with the updated answer.
## Testing
Add a regression test that pauses the final flush, submits a steer, and verifies that the model receives it exactly once before the same turn completes with the answer to the steer.
GitOrigin-RevId: 193db3ab6916a86e97c3845590598fd8fbe47081
## What changed
Add `modelProvider/config/write` to create custom gateways and patch existing custom gateway, Bedrock, and GCP settings. Return the saved provider using the same safe summary as `modelProvider/list`.
Omitted fields retain their values; explicit `null` clears nullable user overrides. Apply patches through the shared configuration queue with last-write-wins semantics, enforce field editability and validation, and preserve unexposed authentication settings.
Saving leaves provider selection and authentication unchanged. Saving the provider used by `model/list` invalidates its catalog for the next access. Include documentation and generated JSON, TypeScript, and Python protocol types.
## Testing
Add coverage for gateway creation and ID allocation, patch and null semantics, configuration policy enforcement, authentication preservation, and catalog refresh after active-provider edits. Extend Python protocol tests to verify wire round trips and reject mismatched provider IDs or fields.
GitOrigin-RevId: 850fe2c48ef5274944400efb5a859d720179c923
## What changed
- Add `modelProvider/list` to return OpenAI and explicitly configured providers, provider-specific settings, and the selected default provider.
- Report `canEdit` and `canChangeDefault` based on configuration requirements, layer precedence, and whether user configuration is enabled.
- Describe gateway authentication without resolving credentials, and omit endpoint URLs that are unsuitable for display.
- Document the API and update generated JSON schemas, TypeScript types, and Python models.
## Testing
Add app-server tests for provider discovery, authentication modes, unsafe URL suppression, and configuration editability, plus a Python wire-format round-trip test.
GitOrigin-RevId: 8ba26637cd6bdd075e0e815e88aeeb04c53a2364
## Why
`start_or_steer_turn` rejected agent messages, preventing callers from submitting follow-up work through the turn input API.
## What changed
Route `TurnInput::InterAgentCommunication` through native agent message delivery and return `TurnInputSubmission::Accepted`, without implying an immediate turn ID. These submissions request work regardless of `trigger_turn`, retain the recipient's settings, and forward turn-start options.
Wrap plaintext messages with agent context while preserving encrypted content. Reject submissions to idle recipients when the host is draining.
## Testing
Add scenario tests and snapshots covering queued-message ordering, encrypted follow-ups, preemption at reasoning boundaries, and follow-ups arriving before or after a final answer. Extend drain-gate coverage to agent submissions with parent-turn lineage.
GitOrigin-RevId: 92d49465f97bb366babbf1b1bc18a1e8a6c6ed1c
## Why
MCP startup alone should not block `/fork`, and rejecting a fork while foreground work is pending should preserve the draft and its image attachments.
## What changed
- Defer `/fork` draft consumption until dispatch validates the thread state, as for `/review`.
- Allow `/fork` during MCP startup when no user turn or review is pending or running, and clear the composer after validation succeeds.
- Preserve drafts and attachments when these commands are rejected in side conversations.
## Testing
Extend regression coverage for `/fork` and `/review` draft preservation during MCP startup, successful fork dispatch and composer clearing, rejection during an active review, and attachment preservation in side conversations.
GitOrigin-RevId: d152ba6659e4507d8750cb6bd3073d9f8b293538
## Why
Accepting the startup update prompt exits before connecting to an app server, so launch telemetry previously reported `unconfirmed`.
## What changed
Record `app_server_mode=update_requested` when handing off to the updater. Continue recording `in_process`, `local_daemon`, or `remote` after a successful connection, and use `unconfirmed` for other early exits.
## Testing
Extend the launch telemetry test to verify exactly one recording for a connection, an update handoff, or an early return.
GitOrigin-RevId: 10dd29246218e1a86a396ab073305402a0b44d38
## Why
Live paginated history retains completed assistant text even when summaries only need the latest message. Release older text for threads with persisted history while preserving full resume responses.
## What changed
- Evict superseded assistant text from live turn state while preserving corrected items and the latest assistant message.
- Restore evicted text for full resume responses from prepared history pages, fetching remaining items by ID in bounded batches. Return an error if saved text is missing.
- Only load the active turn when it belongs in the requested initial page, and use the item ID index for targeted history reads.
## Testing
Add reducer coverage for text eviction and corrected messages. Extend running-thread resume coverage to compare full and summary items with live notifications, exercise restoration when the prepared page lacks the active turn, and check missing-text errors.
GitOrigin-RevId: 3229c0cea820f117dc6331312f1e6056a8d1d52c
## What changed
Add `BackendSessions` helpers to name the displayed listening backend, find the first listening backend, and cycle through listening backends in registration order. Cycling wraps around, skips closed streams, and excludes the current backend. Display names use `Local` for the initial session and `Backend N` for additional sessions; a closed displayed stream has no name.
## Testing
Extend backend session tests to cover cycling with a single backend, wraparound across three backends, and skipping a closed stream.
GitOrigin-RevId: e8f3fcc38a178b6b91d385d65d899fdd042062c5
## What changed
- Group threads needing approval first in `/subagents`, mark them with `(needs approval)`, and initially select the first waiting thread.
- Refresh the open picker and approval notice as requests and agent metadata change, preserving the selected thread when rows move.
- Use consistent agent labels across the picker and approval notice, preferring agent paths and using UUID suffixes to distinguish unnamed agents.
- Track approval requests that arrive before thread metadata and refresh pending approvals after reconnecting.
## Testing
Extend the picker test and snapshots to cover approvals arriving while the picker is open, agent paths arriving later, and selection staying on the same thread after reordering.
GitOrigin-RevId: b7dd943d151ce98d1978f7c6b9f5e16903b9075b
## What changed
- Build native voice SDK and runtime artifacts with Bazel for Linux GNU, macOS, and Windows on x64 and ARM64, then configure Cargo jobs to consume them. Keep musl builds in a separate job without these inputs.
- Validate artifact receipts against the target, source commit, and source manifest; verify SDK file hashes and relocate pkg-config metadata. Package the runtime and plugins with nextest archives and restore `CODEX_TEST_VOICE_RUNTIME` when running shards.
- Prepare native Windows voice tools for argument-comment linting and install ARM64 DotSlash on Windows ARM64. Reduce archive disk usage, bound Linux ARM64 build concurrency, and correct the JUnit artifact path.
- Recognize TLS errors wrapped directly in `io::Error`. Make TLS fallback fixtures select the native backend explicitly, allow the MCP test server's non-loopback address, and isolate skill-root tests from ancestor Git markers. Install `git` in remote test containers and filter MCP discovery assertions to POST requests.
## Testing
Add tests for relocated voice inputs, Windows ARM64 import libraries with host-native pkgconf, and rejection of mismatched receipts or corrupt SDK files. Extend untrusted-certificate coverage to an explicitly selected rustls backend.
GitOrigin-RevId: da3ff690b94906edc1f8f60a3c7feda1bf66134a
## What changed
Split conversation rendering into preparation, painting, and post-draw steps. Use the supplied conversation bounds for transcript wrapping, composer layout, suggestion overlays, cursor placement, and the empty-state animation.
Preserve surrounding text and image placements during input-triggered redraws. Keep centered dialogs relative to the full viewport and restore neighboring content when they close.
## Testing
Extend regression tests and add a snapshot for conversations rendered at an offset, covering selection, link hit testing, cursor placement, scroll preservation, neighboring images, and dialog dismissal.
GitOrigin-RevId: 0dbca3f8d1064f2d58856c3bc77a4dab1c099cdd
## What changed
Detect GNU screen via `STY` when `TMUX` is absent and wrap OSC 52 clipboard sequences in DCS passthrough strings. Split the sequence into 252-byte chunks to stay below screen's older 256-byte string limit while forwarding one continuous OSC 52 sequence to the outer terminal.
Prepare the terminal sequence in the clipboard worker and retain it for deferred delivery.
## Testing
Add coverage for short text and a longer Unicode payload, checking that each passthrough chunk stays below the limit and that reassembling the chunks reproduces the complete OSC 52 sequence.
GitOrigin-RevId: 1a042ed4fed817179e98459f4f4b2b847b160721
## What changed
Keep unpinned tasks ordered by descending update time within each status group as tasks arrive, change status, or refresh. Clearing a search or status filter also reflects timestamp changes to hidden tasks.
Keep pinned tasks at the top of their respective status groups in pin order, and mark their titles with 📌 instead of placing them in a separate Pinned group when grouping by status.
## Testing
Update ordering tests and snapshots to cover arrivals, status transitions, rediscovered tasks, filters, pins, and adjacent selection after hiding tasks.
GitOrigin-RevId: 2f3320a17b1932294f421dd28af848f0e0be45ef
## What changed
Bundle the started thread, configuration, and local settings in
`PreparedFreshSession`, and move session activation into `adopt_fresh_session`.
The helper preserves input state, switches threads, applies settings, names the
session, and attaches the chat widget with a caller-supplied presentation.
`start_fresh_session` delegates to the helper with
`ThreadAttachPresentation::Fresh`, preserving its existing behavior.
GitOrigin-RevId: c4fdb6b5024a024f6baa48610e62a8e6628de30a
## Why
Failed snapshot assertions should print their diffs without leaving `.snap.new` files after a passing retry. The OTLP loopback collector should stop once exporter shutdown completes instead of waiting for its deadline.
## What changed
- Set `INSTA_UPDATE=no` for Bazel CI tests, including the local configuration used when no BuildBuddy API key is available.
- Initialize the OTLP provider before starting the collector's deadline in the Tokio bounded-shutdown test.
- Signal the collector to stop after shutdown and join its thread before propagating any shutdown error.
GitOrigin-RevId: 55b050822ec923894c9edbc8f039f35f693a4b7e
## Why
The session picker can list conversations from multiple backends, but selecting a conversation owned by another backend was rejected.
## What changed
- Resume selected conversations through their owning backend, preparing the destination before replacing the current conversation. Preserve drafts and restore the destination's settings, account state, model catalog, and workspace services.
- Block backend switches during an active turn and retain the current conversation when destination preparation fails.
- Queue background backend requests until that backend is displayed, removing requests that are resolved or disconnected. Isolate background events from the displayed conversation while continuing to deliver notifications to a background voice session.
- Track backend ownership for thread detachment, startup results, and reconnect attempts.
- Remove the `yaml-rust` advisory exception from `codex-rs/deny.toml`.
## Testing
Add regression coverage for backend handoff errors, detaching through the source connection, clearing stale provider errors, deferred request delivery and cleanup, and voice-session closure on a background backend.
GitOrigin-RevId: 1bba84f16831af1d5295c1404f48803ce0608d3d
## Why
When a response fails with incomplete output, attempted tool calls can appear only in the terminal response payload. Failed inference traces previously omitted those items, losing evidence of the attempted call.
## What changed
Retain output items marked `incomplete` on `ResponseIncompleteError` and include recognized items in failed inference traces, deduplicating by item ID. Keep these items out of streamed output, tool dispatch, and the continuation cache, and omit their payloads from the error's debug representation.
## Testing
Add tests for retaining only incomplete output from terminal responses and recording attempted calls in failed traces without streaming them or creating tool calls. Cover unknown response item types being skipped.
GitOrigin-RevId: 594f6a37a5af543694f19fcffe0c164cb2addb36
## What changed
Introduce `ContextBudgeting::Elastic` to prepare captured root conversation and Node REPL evidence without the fixed per-section request caps. Elastic preparation preserves message text and candidates for later allocation while retaining storage omission notices and legacy source deduplication.
Keep `ContextBudgeting::Fixed` as the default and use it at existing call sites.
## Testing
Add tests covering elastic root message preservation and legacy source deduplication, plus REPL text, images, and omission counts in text-only and multimodal modes.
GitOrigin-RevId: ce4fae9d725694456525a413fb511166df6f5e2c
## What changed
- Add terminal file hyperlinks to viewed image filenames and transcript paths, including older history loaded through pagination.
- Enable links only for local workspaces outside SSH sessions. Require a local regular file with a recognized image extension on both the original and resolved paths, and reject Windows reparse points.
- Preserve links when summaries are truncated or transcript paths wrap.
## Testing
Add coverage for local versus remote workspace links and for hyperlink destinations and column ranges in compact and expanded image rows.
GitOrigin-RevId: a7dff255c280ad4e609644e6f5ef5e130d9a55fb
## What changed
- Add `prepare_elastic_entries` to cap required and optional supporting text before allocating whole optional entries. Measure rendered content, including JSON escaping, metadata, and framing, while preserving truncation markers.
- Keep exact planned-action JSON, images, audio, and opaque native payloads whole. Mark shortened sources incomplete and record truncation sizes.
- Expose token estimation and synchronous delivery preparation on `PreparedElasticContext` so deduplication uses the capped representations.
## Testing
Add tests for required and optional entry caps, transcript metadata preservation, unchanged short entries and opaque payloads, and exact action preservation with rejection when the request budget cannot accommodate the action.
GitOrigin-RevId: 23008fb03d15d501e5d602f0584f70b473c2c2e8
## What changed
Add optional `ModelMessages.apps` and `AppsMessages.usage_instructions` fields to carry model catalog wording without runtime interpretation. Missing or null values become `None`, and strings retain their exact contents, including empty strings, whitespace, and template-like text.
## Testing
Add serialization coverage for nullable and literal Apps values, and extend existing tests to verify Apps messages survive model response round trips and base instruction overrides.
GitOrigin-RevId: 49b516656255e07b91f8f4679e2acb8e1b03f9e1
## What changed
- Add tab switching with keyboard navigation and a `.viz-carousel` variant picker with previous/next controls and screen reader announcements.
- Support touch tooltip toggling and tooltip triggers inside shadow roots.
- Refresh typography, tables, buttons, and form controls; add widget and progress styles and larger touch targets.
## Testing
Add a viewer snapshot test covering embedded tab and carousel scripts, generated control markup, and selected CSS rules.
GitOrigin-RevId: 3b85ef816fe307e8ac9903f176a0b81430e48f3f
## What changed
Map audio size, data, format, and sample-rate validation failures to `InvalidAudioInput` for HTTP 400 responses and streamed errors. Preserve the provider's message, falling back to `Invalid audio input.` when it is absent or blank.
Classify these errors as non-retryable and expose them as `BadRequest`. Redact their messages in doctor diagnostics and group them as invalid requests in telemetry.
## Testing
Add coverage for all six audio validation codes across HTTP errors, streamed `error` events, and `response.failed` events, checking error classification, message preservation, and the absence of retries. Extend doctor diagnostic redaction coverage for `InvalidAudioInput`.
GitOrigin-RevId: 0a59964bcabd83997bdb32fc9318a5482dac33b0
## What changed
- Allow audio inputs to carry uploaded file references via `fileId` in the app-server API and `file_id` in model content, preserving existing inline audio shapes and Python class names.
- Preserve mixed inline and file-backed audio ordering through history reconstruction and migration, and budget file-backed audio conservatively when duration is unknown.
- Keep uploaded audio disabled at runtime: reject it before inference or raw history injection, preserve accompanying text, and prevent rejected attachments from reaching follow-up or resumed requests.
## Testing
Add coverage for wire-format round trips, SDK compatibility, mixed audio history ordering, and rejection during turn start, steering, task completion, and raw injection.
GitOrigin-RevId: 70895c47a2494c0c9936348ad1250eb1b7b892a6
## What changed
Allow connector-wide app settings under `plugins.<plugin>.apps.<connector>` for plugins enabled by configuration. Merge these settings field by field, giving earlier plugin names precedence and applying explicit top-level `apps` fields last. Ignore nested `_default` settings.
Expose the merged app settings and their field origins through the config API. Keep app policy changes from invalidating the loaded-plugin cache.
## Testing
Add coverage for plugin enablement, merge precedence, field origins, config API output, cache reuse, and disabling an app through plugin configuration during explicit plugin mentions.
GitOrigin-RevId: a275319815915dc618ee606b10e0844248dbccb5
## What changed
Move OpenAI API key, Amazon Bedrock, and Google Cloud Vertex AI options under “Sign in another way” during onboarding. Keep ChatGPT and device code sign-in on the main menu, and let `Esc` return from the alternative methods menu.
Guard activation keys across menu transitions so holding `Enter` or a numeric shortcut cannot advance through multiple steps or save a prefilled API key without a fresh confirmation.
## Testing
Add regression coverage for held activation keys and update onboarding tests and snapshots for submenu navigation, provider availability, and returning with `Esc`.
GitOrigin-RevId: b5aa56e48f10b490cc8f04b5d4288d21b76d2c61
## What changed
Inline validation and command preparation in `review_tool_call`, removing the
`RecordedExecCall` helper. Use the tool invocation's call ID for approval actions
and return `GuardianReviewResult` directly from the review future, including when
no assessment is required.
GitOrigin-RevId: aafd01f640d46dc542a649bc5b31b3cfba7bedb8
## Why
Deleting `Yes` from `Yes! I agree.` should leave an ordinary message, without entering shell mode or treating the remaining `!` as a shell command on submission.
## What changed
- Activate shell mode when an edit inserts a leading `!`, rather than when deletion exposes one.
- Use the composer's shell-mode state to classify submissions and preserve that state when restoring the same draft.
- Keep input with whitespace before `!` in normal text mode.
## Testing
Add regression coverage for literal-bang submission and queueing, editing and rendering, Vim repeat and undo/redo, and cancelled history search. Update paste and startup-submission tests to distinguish literal bangs from shell commands.
GitOrigin-RevId: 05002c3e07edb47e0882465ad91b39d317d2c663
## Why
Host-owned tools need to wait for agent messages or steering input with the same behavior as native `wait_agent`, including when native multi-agent support is disabled.
## What changed
- Add `CodexThread::wait_for_input_activity` and export `InputWaitOutcome` through core and core-api, sharing the wait implementation with `wait_agent`.
- Distinguish notifying agent messages from steering input, with steering taking precedence when both are pending. Passive response items do not wake waits.
- Observe input without consuming it. Waits remain active after the original turn ends, support independent observers, and can be cancelled by dropping the future.
## Testing
Add coverage for pending and incoming input, agent-message classification, cancellation, independent observers, timeouts, and input arriving after the original turn completes or is interrupted.
GitOrigin-RevId: d0c0bd776c3b6fd4ba3021603d87eaaf1d93976f
## What changed
Mark `deferred_tool_world_state` as stable and enable it by default. Deferred tool namespaces now appear in the developer `<tools>` context instead of the `tool_search` description. Explicitly disabling the feature preserves discovery metadata in the search description.
## Testing
Update tool discovery tests to cover the default behavior and explicit opt-out, and refresh request snapshots for the deferred namespace context.
GitOrigin-RevId: d58e369ea22754cee593c26a5ca011e41ba56e79
## What changed
- Add `StartThreadOptions` setters for captured thread instructions and execution policy snapshots. Captured instructions replace the live thread provider; empty text clears the thread contribution. Hosts must supply inherited settings again on cold resume.
- Install inherited policies in independent managers only when the destination ignores user and project rules, has no additional policy files, and has matching managed requirements. Preserve managed command restrictions, host executable mappings, and network denials, including restrictions that absolute-path rules could otherwise bypass.
- Reject inherited startup settings for isolated sessions and reject combining local and transported execution policies.
## Testing
Add coverage for policy inheritance through children and grandchildren, incompatible or weakened policies, absolute-path amendments, and captured instructions overriding or clearing live instructions on startup and resume. An execution integration test checks that an inherited allow rule runs without approval while a managed denial still blocks execution.
GitOrigin-RevId: c1147992fe5bb5ba4bcf981c08fcfcb6f6bca8a1
## What changed
Add the default-off `suppress_model_change_announcements` feature flag. When enabled, incremental context updates omit the model ID announcement after a model switch while still delivering changed base instructions and tool definitions.
Advance the model snapshot even when a switch emits no context update, so subsequent turns recognize the current model.
## Testing
Add coverage for omitted and explicit flag values, snapshot advancement without repeated updates, and request history across model switches, repeated turns, and compaction with announcements suppressed.
GitOrigin-RevId: 89c70f1e9d7981fd945fb8e41b1f98492717a07e
## Why
Retained output from failed responses or responses without usage data can be omitted from context token estimates, delaying automatic compaction even as reasoning accumulates.
## What changed
Track the history boundary covered by the last usable usage report and estimate all items added after it. Spending-only updates preserve that boundary, while successful usage reports cover the request input even when the response contains no output items. Avoid counting unreported reasoning twice and align recomputed context counts and remote compaction estimates with the boundary.
## Testing
Add unit coverage for initial input, empty responses, spending-only updates, and reasoning accounting. Add regression coverage verifying that accumulated unreported reasoning triggers compaction for incomplete responses with or without usage and completed responses without usage.
GitOrigin-RevId: 80c0b800c7236ff40ae53fdd18320e0d06e026ab
## Why
Package managers search parent directories for project configuration and hooks, which can influence Codex updates launched from a project directory.
## What changed
Run non-Windows update commands with `/` as their working directory.
## Testing
Add a regression test using a fake `pnpm` executable to verify that updates run outside the project even when `TMPDIR` points into it.
GitOrigin-RevId: a39b36872a62f2404aadd0614e1486d0755636fc
## Why
Reduce idle RSS after Linux musl conversations unload by using roughly one jemalloc arena per four CPUs.
## What changed
Set `JEMALLOC_SYS_WITH_MALLOC_CONF` to `narenas_ratio:0.25` in both Cargo's environment and Bazel's `tikv-jemalloc-sys` build script environment.
GitOrigin-RevId: fa05961f88b2f2e8716b75f5582eecacb2fc5a8e
## What changed
Expose `McpToolRequestMetaHook` and `McpToolRequestMetaProvider` so hosts can supply a per-invocation `_meta` value using the thread, turn, and call IDs. Apply the hook before dispatch only when the tool, server name, source, and full transport configuration match the selected local MCP registration.
Reject metadata key collisions and propagate provider errors to the tool caller without dispatching the call.
## Testing
Add integration coverage for matching registrations, different contributors and routing headers, unrelated tools and servers, provider failures, and existing metadata keys.
GitOrigin-RevId: 2bf51c375a04617d61b24ca1cbbcaa810fb06720
## What changed
Replace `PreparedThreadSpawn` with `PreparedChildContext`. `CodexThread::prepare_child` now captures parent inputs from a live tool invocation without requiring a child request. Hosts choose the child's name, role, and history, bind destination services, and apply child settings.
Expose captured instructions, environments, permissions, approval settings, disabled plugins, current inheritable dynamic tools, and an execution-policy snapshot with its original managed requirements. Retain those requirements across MCP configuration refreshes so hosts can assess policy-source compatibility.
Remove `ThreadManager::create_prepared_child`; `CodexThread::create_child` handles reserved child startup on the parent's manager with invocation-bound cancellation and cleanup.
## Testing
Add coverage for execution-policy snapshots and managed requirements after MCP refresh. Update child-spawn tests to verify captured instructions and permissions, current dynamic-tool declarations, and fresh versus forked history.
GitOrigin-RevId: f15b595b44997fa70cd0c9be0e92f470e1f333e1
## What changed
Add `PreparedElasticContext::enforce_budget` to reserve existing context, required evidence, history, and an omission notice before allocating remaining tokens across optional evidence groups. Scale minimum reservations to fit, favor recent whole entries, and redistribute unused capacity while preserving retained content and order.
Account for shared section framing and keep images whole. Record omitted entries and reject requests when required evidence cannot fit. Supply defaults for unconfigured groups and rename allocation groups to match their source sections, retaining previous serialized names as aliases.
## Testing
Add unit tests for recent-entry selection, redistribution of packing gaps, whole-image retention, shared framing, default limits, and preservation of required instructions and historical approvals under tight budgets.
GitOrigin-RevId: a3c789a5936ec3f22893a31a0014c0902197a281
## What changed
Extract the inline storage predicate into a test helper in `codex-rs/v8-poc/src/lib.rs` and reuse it in the typed array contents test. Add coverage for disabled inline storage (a zero limit), empty arrays, and lengths at and above a nonzero limit.
GitOrigin-RevId: 3370ea41b58e0d0ff00266272ccc4fa331bcf38b
## Why
Workspace switching rewrites claims returned by `get_token_data()`, so comparing those tokens with the stored refresh generation can fail to recognize an unfinished ChatGPT refresh.
## What changed
Compare tokens from the current auth JSON with the unsettled refresh generation, preserving detection when workspace claims differ from the original ID token.
## Testing
Extend the refresh cancellation regression test to cover a workspace switch that retains the original ID and refresh tokens.
GitOrigin-RevId: 097311e4cdc22cde875589ef616daf60c6b8ef80
Felipe Coury