## Why
Runtime filesystem grants, such as those used for plugin metrics, could trigger unnecessary approval for `write_stdin` and prevent input when sandbox approval was disabled.
## What changed
Include retained runtime grants in the baseline permission comparison for stdin review. Continue requiring review for additional agent permissions, sandbox bypasses, and policy changes. Update the approval description to report current permissions when only runtime grants are present.
## Testing
Extend unit coverage to ensure runtime grants do not require review or mask agent filesystem and network grants, and that sandbox bypasses still require review. Add local and remote plugin regression cases that send stdin and verify metric emission with sandbox approval disabled.
GitOrigin-RevId: 989098bdc7fbf839786c01f11cbf02999bae1cc1
## What changed
Return post metadata from the in-memory message board after updating board state when no notification recipients remain. This avoids constructing an unused notification preview, including when the author is the only requested recipient.
## Testing
Run the existing post-and-search model-context scenario against both disk and in-memory message boards, checking that post metadata and search results reach the model without self-notifications.
GitOrigin-RevId: dcf07a5fd55738fbcd6edd3dce3f6fb8fc910eaf
## Why
The network command can yield before its request reaches Guardian, allowing a parent request to consume the mock response intended for Guardian.
## What changed
Update `guardian_receives_exact_trigger_for_single_network_request` to match parent and Guardian requests separately. Have the parent poll running processes with `write_stdin` until they exit, and bound the wait for turn completion to 30 seconds. Preserve the assertion that Guardian receives exactly the original call ID and command.
GitOrigin-RevId: f39e9461c3628fbab00ba241f828d318b17975b5
## Why
Reused Guardian sessions already contain previously delivered instructions. Follow-up reviews can avoid repeating that evidence, but must deliver it again if it changes or compaction removes it.
## What changed
- Track retained source identity, revision, and completeness in host-owned history metadata, preserving revisions during replay.
- Omit retained instructions from synchronous review inputs only when the same complete revision remains in reviewer history.
- Restore missing evidence after reviewer compaction, enforcing the request budget before persisting additions. Classify restored evidence as context rather than new user authorization.
- Keep source-order labels stable across eviction and retain full delivery for legacy records without reliable provenance.
## Testing
Add coverage for consecutive-review deduplication, changed revisions, missing or incomplete metadata, and restoring compacted evidence exactly once. Extend compaction and resume coverage to verify retained revisions.
GitOrigin-RevId: e90fca16cde0a0970da36dd873af2ca1dbaaf4d3
## What changed
- Stop sending `includeExtensions=true` when fetching installed plugins and remove extension metadata from remote plugin models.
- Remove `PluginSummary.extensions` and the associated extension declaration types from the app-server protocol.
- Update generated JSON schemas, TypeScript and Python bindings, and precomputed protocol exports to match.
GitOrigin-RevId: 56509437b6bdf58d99badff68e86bcf7f09fe036
## What changed
Add app-server integration coverage for awaiting `request_permissions` and then running `exec_command` in the same code-mode cell:
- Verify that turn- and session-scoped write grants allow the command to create a file, including grant propagation to Windows command approval requests.
- Verify that `strictAutoReview` immediately triggers review for a command needing no additional access and returns the reviewer's denial rationale.
GitOrigin-RevId: 02c958071db4e9ba667be9ba95fbb3a506ae1572
## Why
Tool suggestions could pass unchecked `install_url` values to the app link view for opening in a browser.
## What changed
Reuse the external URL validator to require HTTPS URLs with a host and no embedded credentials. Decline suggestions with invalid URLs on the requesting thread without showing a popup.
## Testing
Add a regression test covering malformed URLs, unsupported schemes, embedded credentials, and a valid HTTPS URL. Verify that rejected suggestions leave the popup unchanged and resolve on the requesting thread, while the valid URL opens on confirmation.
GitOrigin-RevId: e47bf09868ec81aeaf1ffed8330039b69c60e093
## Why
The sample hardcoded file-based credential storage and omitted configured auth routing and login restrictions. It should use the configured credentials, including secure storage in `cargo run` builds.
## What changed
- Load authentication settings through the shared bootstrap path and re-export the required helpers and types from `codex-core-api`.
- Honor CLI and MCP credential stores, `features.secret_auth_storage`, auth routing, the ChatGPT base URL, and system proxy settings.
- Preserve managed login-method and ChatGPT workspace restrictions while keeping the sample's built-in execution settings.
- Document the sample's authentication configuration behavior.
GitOrigin-RevId: b49883537acbebf9266b3970d2709e8e7d1bf217
## Why
When a container denies fresh `/proc` mounts, the existing sandbox fallback retains the caller's `/proc` while creating a new PID namespace. Process IDs inside the sandbox can then differ from those exposed by `/proc`, breaking process lookups.
## What changed
- Add `codex exec-server --linux-sandbox-pid-namespace=inherit` to reuse the caller's PID namespace and `/proc` for both process and filesystem helpers. Repository config and command environment variables cannot enable it.
- Keep `isolate` as the default, preserving the existing mount fallback and compatibility with older helpers. Inheritance requires an updated helper and omits `--unshare-pid` and `--as-pid-1`.
- Preserve other sandbox restrictions. With `:minimal`, bind the inherited `/proc` read-only with its container masks and apply explicit filesystem denials afterward.
Inheritance is intended for dedicated environments: it allows sandboxed commands to signal other same-UID processes, including the executor.
## Testing
Add unit and integration coverage for namespace flags, denied proc mounts, consistent process IDs, retained sandbox restrictions, and startup-only selection across process and filesystem helpers.
GitOrigin-RevId: dd13f2b9286d7edcf366b3a42a455f4d78daaf27
## Why
Refreshing the MCP catalog with unchanged tool metadata recreated handlers and forced the tool search index to rebuild.
## What changed
Cache handlers by canonical tool name and reuse them when tool metadata, agent plugin status, and the input schema size limit are unchanged. Replace handlers when those inputs change and evict tools removed from the catalog, preserving search index reuse across equivalent bindings.
## Testing
Extend the deferred tool world state test to verify that an unchanged catalog refresh captures a new binding without rebuilding the search index, and that removing all deferred tools stops advertising `tool_search`.
GitOrigin-RevId: 150866f635e9ee817d7ca44fb76e724a3f7608a5
## What changed
- Record successful spawn phase durations in `codex.multi_agent.spawn.phase.duration_ms`, covering residency reservation and fork context when applicable, child creation, durability waits, input admission, and total latency.
- Count spawn failures from the V1 and V2 tool handlers in `codex.multi_agent.spawn.failure`, grouped by bounded error categories.
- Use bounded labels for fork mode, multi-agent version, product SKU, and successful-spawn history mode. Emit phase timings only after a successful spawn.
## Testing
Add in-memory metrics tests for phase durations and labels, plus a tool-handler test verifying that a thread-limit failure emits one counter increment with the expected labels.
GitOrigin-RevId: 04cba9042b9b34acdf57376ace5288c3f741f3b2
## What changed
Prepare each MCP call from the selected server's current client and catalog instead of building a full runtime binding. Match the advertised tool by server, tool name, and connector ID, and enforce current tool filters and model visibility.
Preserve the advertised `callable_namespace` and `callable_name` while using current schema, annotations, approval metadata, timeout, and permission authority for execution.
GitOrigin-RevId: 703a90926fc72bd446d83ac974162aee6439f363
## Why
Queued voice answers could reappear as text under a newer question when speech failed, the pending queue overflowed, or voice stopped, including answers already spoken as paraphrases.
## What changed
Filter recovered and replayed speech by the current input generation, preserving that generation across conversation resets. Keep text fallbacks for answers still awaiting turn completion so delayed user transcripts do not discard unspoken answers.
## Testing
Add regression coverage for paraphrased answers, queue overflow, stop and replay, failed delivery for current versus superseded input, and delayed transcripts.
GitOrigin-RevId: b7b230910bf4fdb4ae93f7de8ca2222a19c55d7f
## Why
A `.git` pointer can resolve to a Git directory inside another writable root. Broader Seatbelt grants or later bubblewrap mounts can leave that directory writable despite its metadata protections.
## What changed
Include resolved Git directories in read-only exclusions for broader writable roots on Linux and macOS. Resolve symlink aliases when locating exclusion targets and retain explicit policy overrides.
## Testing
Add regression tests for Git directories reached directly or through symlink aliases in another writable root, and for linked worktree metadata under the macOS temporary directory. Verify that metadata writes are denied while ordinary files in the surrounding writable root remain writable.
GitOrigin-RevId: 6971f1cf35008d23eaeb0d02a9c61bee7cf83b12
## What changed
- Recognize `promax` in authentication, account responses, and backend rate limits; update generated schemas and client types.
- Display `prolite` as “Pro”, `pro` as “Pro (More)”, and `promax` as “Pro (Max)” in account labels, status, and analytics.
- Include Pro Max in experimental context eligibility, paid-plan tooltips, and usage-limit guidance for purchasing credits.
## Testing
Extend coverage for Pro Max plan parsing, account and rate-limit responses, experimental context eligibility, and plan display names. Update the login token test to expect “Pro (More)”.
GitOrigin-RevId: 197e00fa7a99cbce125c8f1d43a451ec1ed5c1fb
## Why
`active_turn_environment_selections()` returns the selections captured at turn start, so it does not reflect later environment settings updates.
## What changed
Add `CodexThread::current_turn_environment_selections(expected_turn_id)` to read the running turn's current selections, including environments that are still starting or have failed. Return `None` when the requested turn is no longer active or has been cancelled.
## Testing
Add a regression test covering selection updates, mismatched turn IDs, and completed turns, while verifying that the initial selection snapshot remains unchanged.
GitOrigin-RevId: bb526a686d549209142150ffde99ad1444add205
## Why
Btrfs subvolumes can report an `st_dev` that differs from the device in `/proc/self/mountinfo`, causing daemon socket mount validation to reject valid mounts.
## What changed
Allow the mismatch only when the opened directory and its uniquely identified mount are both verified as Btrfs. Discover socket directory aliases using both device identities while retaining checks that reject unsafe directory and socket bind mounts.
## Testing
Add regression tests for aliases under both device numbers, unverified or inconsistent filesystems, unavailable or missing mount IDs, duplicate mount IDs, and unsafe bind mounts.
GitOrigin-RevId: 921d6465b7a97022573a42412606a26560cc086a
## What changed
- Recognize `flex_unavailable` in HTTP 429 responses and streamed `error` and `response.failed` events. End normal turns without retries and report `Flex capacity unavailable.`
- Expose `flexUnavailable` through the core and app-server protocols and generated schemas and SDK types.
- Keep Flex capacity failures eligible for Guardian review and sampler retries, with a distinct telemetry classification.
- Map unexpected HTTP responses to `HttpConnectionFailed`, preserving their status codes.
## Testing
Add regression coverage for terminal Flex failures over HTTP, SSE, and WebSocket, HTTP 504 status preservation after a stream retry, and protocol serialization. Update Guardian retry and sampler recovery tests to cover Flex failures.
GitOrigin-RevId: f2e03a6d2d36a6d9748c35952e40397f8670d121
## What changed
Keep `x-amzn-mantle-client-agent: codex` in the Amazon Bedrock Runtime provider instead of clearing the headers inherited from the Amazon Bedrock provider.
## Testing
Update provider construction expectations and extend the API provider header test to cover both Amazon Bedrock providers.
GitOrigin-RevId: eab07f347b53f0a6ba2e224a39590f49f181363e
## What changed
- Default `MALLOC_CONF` to `thp:always` for Cargo child processes, including tests and `cargo run`, while preserving an explicitly set value, even if empty.
- Patch `rules_rust` to request transparent huge pages for `codex-rs/` compilation with Linux GNU `rustc` on x86_64 and aarch64. Check policy on the execution worker and enable the setting only when seccomp is disabled, transparent huge pages are permitted, and no allocator, preload, or sanitizer configuration conflicts are detected. Leave the environment unchanged when policy cannot be determined.
GitOrigin-RevId: 3a9b2572ec9e1f30e2f719f30c885914c165eccd
## Why
Removing tool-result metadata alone can leave requests above the 15 MiB message budget when recorded tool calls and arguments occupy the remaining space. If trimming loses calls or arguments from a Code Mode cell, later waits must not report its call inventory as complete.
## What changed
- Bound all optional tool-call observations against the serialized HTTP or WebSocket message size, preserving ordinary tool outputs and continuation history.
- Shed generic result metadata, sources, and recorded arguments before resource-access evidence, retaining tool names and smaller metadata where possible.
- Invalidate completeness across affected cell outputs and later waits when the outgoing copy loses calls or arguments.
- Preserve size-limit omission markers for direct tool-result metadata when they fit, while continuing to exclude that metadata from custom providers.
## Testing
Add regression coverage for HTTP and WebSocket message budgets, unchanged tool results and history, resource-evidence retention, direct-call omission markers, and Code Mode waits after argument truncation.
GitOrigin-RevId: 538dc9d8c11b0830ec70327422f98a1803122e85
## Why
Editing recent conversation images failed when the selected images included a file reference from a message or tool output.
## What changed
Use `ImageReference` in `ImageEditRequest` to accept both `image_url` and `file_id` inputs. Pass file references from conversation history through to image edit requests while preserving image selection order.
## Testing
Update tests to cover file references from messages and tool outputs, and serialization of mixed inline and file references in image edit requests.
GitOrigin-RevId: 2764bf36a81a62ddd25cf9df27346a434a10c449
## What changed
Show the startup tip beneath the session header in the fullscreen transcript, with wrapping on narrow terminals. Remove rotating tips and startup announcements from above the composer, leaving that area for usage warnings.
## Testing
Add startup transcript snapshots at 80 and 32 columns and assert that compact tooltip rendering preserves styled links. Update usage-warning tests to verify composer geometry and recovery without rotating tips.
GitOrigin-RevId: b5e79a46147d112cd50802b0702537deb9b87001
## Why
Dropping the last board handle releases its state but leaves a stale entry in
`InMemoryMessageBoards`, allowing registry entries to accumulate across sessions.
## What changed
Prune entries whose state has no remaining strong references whenever a board is
opened, while preserving shared state for live boards.
## Testing
Add a regression test that repeatedly opens and drops boards, checks that expired
entries are removed, and verifies that reopening a live board shares its state.
GitOrigin-RevId: c3f1c27b42ee17915f0ece01b85a22d0fdf632ce
## What changed
Select checksum-pinned `rusty_v8` 150.4.0 release archives and matching Rust bindings for x64 and arm64 macOS and GNU Linux when pointer compression and the V8 sandbox are enabled.
Add `--//:rusty_v8_from_source=true` to select source-built archives and bindings together for custom V8 C++ flags or instrumentation. Fall back to the existing source path when the sandbox or pointer compression settings differ from the published artifacts, and retain source builds for musl Linux and Windows GNU.
On GNU Linux, weaken the ten shared `std::logic_error` and `std::runtime_error` constructor and assignment symbols in the Bazel output so toolchain libc++ definitions take precedence. Preserve the checksum-verified inputs and constructors accepting `std::__Cr::string`.
Document artifact selection, source overrides, and checksum maintenance.
GitOrigin-RevId: cedd474c739ae16e07a78f35459d2c383e5781d8
## What changed
Increase `MAX_ROOT_MESSAGES` from 8 to 16 so Guardian subagent authorization reviews can include more root conversation context.
## Testing
Update authorization integration tests to exercise the larger message limit, preserve late user authorization and question context, and expect incomplete root instructions when retained user messages exceed the cap.
GitOrigin-RevId: facc55f424a4d7e29626f4161ecfe031021b30c2
## Why
Ephemeral sessions cannot use the SQLite-backed agent message board. An in-memory backend lets agents share discussions without creating durable board storage.
## What changed
- Add the opt-in `message_board_in_memory` setting to the multi-agent v2 configuration, allowing the board to run in ephemeral sessions when both required features are enabled.
- Share board state across agents in the same tree and release it when the last handle is dropped.
- Implement channels, posts, subscriptions, notifications, search, and paginated reads through the existing `AgentMessageBoard` interface, including request deduplication.
## Testing
Add coverage for shared handles, concurrent request deduplication, tree isolation, and state release. Run existing query and tool test cases against both backends, and extend the parent/child scenario to verify ephemeral board sharing without creating a board database.
GitOrigin-RevId: d0b2083f8ea5b1c5a3a70f258ef738b87ea74cef
## What changed
Remove the Windows sandbox audit module and its exported scan-and-deny helper, including the associated tests. Remove the config edit variant and builder method for acknowledging `hide_world_writable_warning`.
GitOrigin-RevId: c9cfc9b276d46c45d5788fe8d29b2bc4e422001c
## Why
Plugin identity and skill ownership need to be available independently of MCP data, including for plugins without servers or connectors. Hosted plugins have no executor root and should not own executor skills.
## What changed
- Add `McpServerContributor::selected_plugins` to declare executor plugin identities with deferred MCP data. Let the host assign server attribution and precedence across contributors.
- Represent hosted connectors with `HostedPluginConnectors` and make `SelectedPluginIdentity::selected_root_id` optional instead of assigning synthetic roots to hosted plugins.
- Resolve executor contributions before reading hosted connectors, and clear stale hosted state on account changes before executor loading can wait.
- Preserve connector declarations from disabled plugins so Apps can hide those connectors.
## Testing
Add coverage for account changes while executor loading is pending. Update tests to verify hosted identities have no executor root and disabled plugins hide their connectors even when plugin IDs differ from root IDs.
GitOrigin-RevId: e7f511264c5874c1b56d5f3e4a46820724046db0
## Why
Callers need to await acceptance or rejection of thread settings without consuming the thread event stream. Acceptance must precede event delivery because the caller may hold a lock needed by the event consumer.
## What changed
- Add `CodexThread::update_thread_settings` and re-export `ThreadSettingsOverrides` from `core-api`.
- Add an optional reply channel to `Op::ThreadSettings`. Return validation failures as `InvalidRequest` through that channel, retaining error events for callers without a reply channel.
- Reply to successful updates before emitting `ThreadSettingsApplied`, while holding the settings persistence lock through notification.
## Testing
Extend settings constraint coverage to direct replies, including rejection without an error event and successful notification. Verify that acceptance and continuation invalidation precede blocked event delivery, while checkpointing waits for notification.
GitOrigin-RevId: e09b0d3cc4b6750709c173371632f19619e5c250
## Why
Fixed schema budgets can strip parameter descriptions from large MCP tools or render their Code Mode input types as `unknown`. Allow larger budgets to preserve that guidance.
## What changed
- Add `mcp_servers.<name>.tool_input_schema_max_bytes` to configure the UTF-8 byte threshold for best-effort input schema compaction, retaining the 5,000-byte default.
- Add `features.code_mode.tool_input_schema_max_bytes` for rendered input types. Use the largest of the 16,000-byte default, the Code Mode setting, and the ordinary MCP server's explicit setting.
- Apply rendering budgets to prompt declarations and the runtime tool catalog, and avoid reusing cached declarations after the Code Mode budget changes.
## Testing
Add coverage for UTF-8 compaction thresholds, budget precedence, configuration round trips, and preservation of parameter guidance in both the Code Mode prompt and `ALL_TOOLS`.
GitOrigin-RevId: 0ef2823a614d4794e636f518b09c0b03a5239b45
## Why
Required MCP servers can block startup while establishing a live connection even when a usable tool catalog is already cached.
## What changed
- Add per-server `startup_readiness = "catalog"` to expose cached tools while the connection starts, retaining `"connection"` as the default.
- Allow an eligible cached catalog to satisfy required-server startup validation and model binding capture. Explicit server or plugin requirements still wait for a live connection, and tool execution still requires the current connection.
- Check tool filters and model visibility when accepting cached catalogs, and preserve cached catalog revisions for binding reuse.
- Serialize the new setting, expose it in the configuration schema, and trace startup readiness at validation and model binding gates.
GitOrigin-RevId: a1cbdf1757ebb5824cffe2cc56408be49711c422
Remove the basic-session restriction from the early return in
`maybe_run_previous_model_inline_compact`. When the model is unchanged and
no compaction compatibility hash change is detected, all session sources now
skip rebuilding the previous model's turn context and checking its limits.
GitOrigin-RevId: 75044856609603859b12e6668c7bae488ce0f7f5
## Why
Saved model selections can outlive their catalog entries. Removing GPT-5.4 needs to preserve a migration path without applying it to other providers that may still support the same model slug.
## What changed
- Remove `gpt-5.4` from the bundled catalog and `openai.gpt-5.4` from the Bedrock catalogs, including GovCloud.
- Add fallback migration prompts to GPT-6 Sol for saved GPT-5.4 selections on OpenAI and Amazon Bedrock. Scope fallback migrations, including the existing GPT-5.4 Mini migration, to their owning providers while honoring catalog metadata.
- Update tests that depend on bundled GPT-5.4 metadata to use GPT-5.5 or explicit model overrides.
## Testing
Extend migration tests to cover catalog metadata precedence, acknowledged targets, missing or hidden replacements, and preserving the provider while saving the replacement model and its default reasoning effort. Update Bedrock catalog assertions and picker snapshots.
GitOrigin-RevId: f739795da423b9622db2a416be6c52b01b8e7a71
## What changed
Connect the existing composer suggestion UI to generation when `tui.prompt_suggestions` is enabled. Request suggestions after successful live turns with known reasoning-summary settings, skipping replayed or duplicate completions and turns with queued follow-ups.
Generate suggestions in hidden, ephemeral forks of the completed turn, preserving conversation context and exposed live settings. Keep fork events out of the visible conversation and reject requests for user interaction. Cancel generation after 30 seconds, interrupt unsuccessful requests, and unsubscribe temporary threads.
Clear suggestions on new submissions, thread changes, reconnects, and feature disablement. Let Escape dismiss suggestions before entering backtrack mode.
## Testing
Add tests for live-turn eligibility and deduplication, preserved request prefixes and settings, hidden fork behavior, startup cancellation, and timeout cleanup.
GitOrigin-RevId: 92ddf3b06448adcc6f4330914cbd8102bff98046
## What changed
Use `127.0.0.1` instead of `localhost` in the OAuth callback URI and local login success URL.
## Testing
Update login and app-server tests to check the callback address, verify that the success redirect shares the callback origin, and assert that the token exchange uses the same `redirect_uri` as the authorization request.
GitOrigin-RevId: a27dd63dca34b9de81fb937da47c753d5dd1ac90
## Why
File blob uploads previously failed immediately on HTTP 502 and 504 responses, even though these transient gateway errors can recover on retry.
## What changed
Treat HTTP 502 and 504 as retryable alongside 503, using the existing attempt limit, upload deadline, and server-provided retry delays.
## Testing
Expand upload retry tests to cover recovery from 502 and 504, mixed transient responses, exhausted attempts, and retry delays exceeding the remaining budget. Verify that 403, 409, and 500 responses are not retried, including responses without an Azure error code.
GitOrigin-RevId: a8e2f6bcf69338fb6d24f4c2d1ee333fb77bdbc0
## What changed
- Export `ProjectTrustPath` and make `ProjectTrustLookup::from_paths` accept an explicit working directory and optional repository root instead of an arbitrary sequence of path pairs.
- Defer repository-root canonicalization until neither working-directory key matches, avoiding unnecessary filesystem access while preserving lookup precedence.
## Testing
Extend the active-project regression test to cover repository-root fallback and ensure a working-directory entry without a trust level takes precedence over a trusted root. Adapt the existing POSIX and Windows lookup tests to the new API.
GitOrigin-RevId: ba5dc0df1ef9d5109933df00c055eef04434601f
## Why
Elevated Windows sandbox setup rejected `danger-full-access` as an incompatible permission profile before registered Core could reach the provisioning service.
## What changed
Allow `PermissionProfile::Disabled` to reach service provisioning when registered Core is requested. Keep legacy full-access setup on the shared setup path and retain permission validation before provisioning for restricted profiles.
## Testing
Add Windows-only regression cases covering full-access and supported restricted profiles reaching the service, unsupported restricted permissions failing before provisioning, and legacy full-access setup skipping the service. Each case checks the completion error and verifies that the configuration file remains unchanged.
GitOrigin-RevId: 5ba190da6f8b1c6ef665015acdb9428718a724dc
## Why
Global deny globs such as `/**/.env` unnecessarily block directory renames and removals on macOS. Moving an ancestor does not let a matching basename escape these rules.
## What changed
Skip ancestor unlink restrictions for root-anchored recursive globs with a literal basename. Keep matching files protected and extend the deny to descendants of matching directories. Preserve ancestor protection for scoped, multi-component, and nonliteral patterns.
## Testing
Add Seatbelt tests covering directory moves and removals, continued protection after moves, symlink access, matching directory descendants, and files created after policy generation. Verify that scoped and nonliteral deny patterns still block ancestor moves.
GitOrigin-RevId: 4e8ea601e8ea98c4da5e3a3fe0d8ce2c63013bc5
## Why
Expanded recursive deny lists can exceed the Windows command-line limit, preventing sandbox wrappers and setup helpers from launching.
## What changed
- Use chunked environment transport for wrapper and non-elevating setup payloads above 24,000 UTF-16 code units, preserving the existing argument protocol for smaller requests.
- Share the transport with the MXC launcher, supporting payloads up to 16 MiB with Unicode-safe chunking and validation.
- Keep transport variables out of the workload environment and remove inherited chunks before launching setup helpers.
## Testing
Add coverage for transport boundaries, Unicode round trips, malformed payload rejection, environment cleanup, and large payloads crossing Windows process creation. Extend the elevated sandbox integration test with 1,000 nested denied files to verify read restrictions and `AGENTS.md` discovery with a payload exceeding the command-line limit.
GitOrigin-RevId: 8ef92fdc7d534143f0eac76036a2173a6f585d08
Accept `service_name` and the expected originator as test parameters, passing
`service_name` through `ThreadStartParams`. Retain the existing case that
expects `TEST_ORIGINATOR` when no service name is provided.
GitOrigin-RevId: 71097dcfe45496216cf3e765999ed0abd0a0cd71
## Why
V8 artifact fetching always downloaded the checksum manifest, requiring network access even when all cached files were valid.
## What changed
Reuse a cached manifest when it is not a symlink and matches the checkout's trusted SHA-256 pin. Continue verifying both the archive and bindings against that manifest, downloading replacements when needed.
Refresh missing, invalid, or symlinked manifests. Preserve existing cache contents if the refresh is interrupted, and reject downloaded manifests that do not match the current pin.
## Testing
Add regression coverage for network-free cache reuse, manifest refresh, corrupt artifact repair, changed pins, symlink replacement, interrupted downloads, and source or paired artifact overrides. All 12 tests in `scripts/codex_package/test_v8.py` pass.
GitOrigin-RevId: d3bdb1ae5f6bc48dd6d081df33dec8db9d3257a8
## Why
Agent messages arriving during a response can interrupt sampling at reasoning or commentary boundaries, cutting off remaining tool calls.
## What changed
Add the disabled-by-default `defer_mailbox_preemption` feature flag. When enabled, sampling continues past these boundaries and queued agent messages reach the next model request alongside completed tool results.
## Testing
Add streaming scenarios and snapshots for reasoning and commentary boundaries with deferral enabled and disabled. Verify that deferral preserves the planned tool call and that both queued messages arrive in order in the next request.
GitOrigin-RevId: d6846dd73b3afb47e7293f3b1aa2abcd04e37853
## Why
Thread startup can prewarm the Responses WebSocket before the creating client is registered with the thread, leaving the handshake unable to request attestation from that client.
## What changed
Reserve a thread ID and register the creating connection before starting the thread, including for ephemeral threads. Remove the thread state if startup fails.
## Testing
Extend the attestation round-trip test to cover persistent and ephemeral threads. Handle attestation requests while awaiting `thread/start` and `turn/start` responses, and verify the WebSocket handshake includes the expected `x-oai-attestation` header.
GitOrigin-RevId: 1bdb38bac641253eed58a2431658ab54d93819c5
## What changed
Add `tui.prompt_suggestions`, defaulting to `false`, along with suggestion request state, a generation prompt, and strict parsing of single-line suggestions up to 240 characters. Suggestion generation is not connected yet.
Keep suggestions outside the draft and render them dimly in an empty, focused composer. `Tab` accepts a suggestion for editing, a separate `Enter` submits, and `Escape` cancels pending suggestions. Respect active key bindings, popups, attachments, paste bursts, and interactive transcript footers; ignore stale results and cancel suggestions when a task starts.
## Testing
Add parser tests, composer interaction tests, and snapshots covering acceptance, dismissal, stale results, input precedence, wrapping, and transcript search layout.
GitOrigin-RevId: 868001a0fc3e6fd8c11ef1650aabc477fa36e03d
Normalize the legacy setting so existing `tui.whimsy` values control the
starfield effect. If both keys appear in the same config layer, the explicit
`tui.effects.starfield` value takes precedence.
GitOrigin-RevId: 2884dbd643690d500ed8d1493ce47950d93d6ab3
## What changed
Represent legacy and canonical config keys as full paths, allowing aliases to target nested tables within the legacy key's containing table. Create missing destination tables, preserve existing canonical values, and skip insertion when an intermediate value is not a table.
Keep the existing `memories` and `agents` alias mappings unchanged.
GitOrigin-RevId: 9ef17e9d1b6adf6299777ed0051cb301fd245073
jif