## Why
Account changes during asynchronous request setup can invalidate the credentials selected for a generation request.
## What changed
- Restart HTTP request setup if the auth owner changes during the budget check.
- Validate the WebSocket connection's retained auth owner with `AuthOwner::is_current()` after budget checks.
## Testing
Add regression coverage for account switches during HTTP budget checks and external credential changes before WebSocket request setup, in both dual-header and assertion-only runtime auth modes.
GitOrigin-RevId: 7a1e1475a40aa2d34cd94f60f729ad697f3f7028
## Why
The rate-limit model switch prompt can remain visible after account usage falls below the warning threshold.
## What changed
Use fresh account usage reads to clear pending prompts when all reported usage windows fall below 90%. If the prompt is already visible, replace it with a recovery notice that counts down for five seconds before dismissing. Users can also dismiss the notice with Enter or Esc.
Ignore stale account reads when detecting recovery and preserve the recovery state when backend banners replace the prompt.
## Testing
Add regression tests and a snapshot covering pending prompt cancellation, stale reads, the recovery notice countdown, automatic dismissal, and manual dismissal with Enter or Esc.
GitOrigin-RevId: 9408f7cc7b49c52535f00d8a476f208fe4872bdf
## Why
An error recorded before a turn starts can cause a successful turn to be reported as failed.
## What changed
Reset `TurnSummary` on `TurnStarted`, preserving the new turn's `started_at` timestamp while clearing accumulated errors, command start times, and the last agent message.
## Testing
Extend turn completion tests to cover clearing an error recorded before turn start and retaining an error recorded during the turn.
GitOrigin-RevId: 19989b55d20df7b9a265bd0a1dfb3f00b6e8a9c5
## Why
Matching API workload identity metadata alone can preserve a credential source across session-family or provider and mapping revision changes.
## What changed
- Compare API workload identity tokens using OAuth source claims so ordinary token refreshes preserve the source while session or identity changes retire it.
- Include `wif_runtime_authorization_version`, `wif_provider_revision`, and `wif_mapping_revision` in source comparisons.
- Reject API workload identity exchange tokens without parseable source claims and nonempty `iss` and `session_id` values. Evict rejected credentials so a subsequent resolve exchanges them again.
## Testing
Add regression coverage for refresh continuity, session-family and revision changes, and rejection and re-exchange of tokens with missing, empty, or whitespace-only `session_id` values.
GitOrigin-RevId: 67189c27efae8a233250a320e6d4fac71d865e90
## Why
SQLite 3.54 fixes `RUSTSEC-2026-0459` when opening a database with a WAL, while retaining the WAL-reset corruption fix.
## What changed
- Upgrade `libsqlite3-sys` to `0.39.1` and require SQLite 3.54 or newer with a compile-time assertion in `codex-state`.
- Pin `sqlx-core` and `sqlx-sqlite` to the same upstream revision that supports the newer SQLite dependency, and allow that Git source in `cargo-deny`.
- Refresh the Cargo and Bazel lockfiles.
GitOrigin-RevId: 768224af79de9b71b21d14912ff01a1176ad37c3
## Why
Aggregate resource listings omitted dormant MCP servers, leaving callers without their names for explicit queries.
## What changed
Include a sorted `deferredServers` list in aggregate `list_mcp_resources` and `list_mcp_resource_templates` results alongside resources from ready servers. Apply the listing filters to deferred servers and omit the field when empty. Discovery leaves dormant servers unstarted; callers can query them by passing `server` explicitly.
## Testing
Extend the resource discovery scenario for direct calls and Code Mode to verify deferred server names, confirm discovery leaves the server unstarted, and then list and read resources by server name.
GitOrigin-RevId: f95b8beb64bb1329f4ae3245e8c375614fcb3360
## Why
Background terminals kept the terminal program status at `Working` after a turn completed, preventing it from reporting `Done` or returning to `Idle` when acknowledged.
## What changed
Stop treating running background processes as active work when computing terminal program status. Background terminals remain visible in the TUI while the status follows the turn lifecycle.
## Testing
Update the lifecycle regression test to complete a turn with a background terminal still running and assert the `Done` → `Idle` transition on acknowledgment.
GitOrigin-RevId: cb995947e6868d6128736a621f268ebfe3891eec
## Why
URLs in fullscreen Markdown transcripts could split across rows even when the full URL would fit on its own row.
## What changed
Mark non-code Markdown lines containing URL-like text with the `UrlAware` wrap policy so transcript layout preserves fitting URLs on a single row.
## Testing
Add a regression snapshot showing a documentation URL moving intact to the next row after introductory text. Update the conversation snapshot and copy-on-select test dimensions for the changed wrapping.
GitOrigin-RevId: 4812c83483cff412406a71ae6745977c5384c7da
## Why
Custom providers with gateway OAuth and an explicit model catalog should be able to discover models without an API key or API key model discovery enabled.
## What changed
- Enable catalog refreshes for custom gateway providers when `model_catalog_url` and `base_url` have the same origin.
- Reuse gateway credentials without starting an interactive login during catalog refreshes.
- Keep an unrelated saved API key from making gateway catalog discovery depend on the API key discovery setting.
## Testing
Add an app-server test for discovering a gateway catalog after OAuth login with no API key. Update coverage for catalog invalidation after gateway credentials require login, including across manager restarts, with API key discovery disabled.
GitOrigin-RevId: b133c428cb45a9037e4b2ef13ff2f9473ed96636
## What changed
Simplify the post-denial rule in the Guardian policy template: user re-approval after seeing the concrete risk sets `user_authorization` to `high`. Remove repeated qualifiers about explicit approval of the exact action and certainty that approval came from the user; the authorization scoring guidance still covers those requirements.
Update the Guardian extra-policy review snapshot to match the revised prompt.
GitOrigin-RevId: 63643222e8f9c46c9d902ac8f5d1e11d24fafe9c
## What changed
Add experimental `deferOutput.mcpToolCall` support to `thread/items/list` requests scoped to a `turnId`. Successful, completed MCP calls with nonempty, unannotated plain-text results can return empty `result.content` with `outputDeferred: true`. Clients can retrieve the saved output through `thread/items/read`; connector identity remains on the listed item.
Keep rich results, JSON or fenced text, app UI results, and built-in `codex_app` results inline. Preserve plain-text output when creating bounded previews of oversized MCP results so those previews remain eligible for deferral. Reads return the saved preview when output exceeds the 64 KiB history limit.
## Testing
Extend thread history integration coverage for independent and combined command/MCP deferral, experimental capability gating, excluded result types, connector identity, oversized previews, and retrieval of deferred items.
GitOrigin-RevId: 5c160b30a4eac2a9b70e3fa65b6dbd83e935338b
## What changed
Set `plugins_mcp.product_sku` to `"codex"` in cloud thread prewarm requests for both default environments and selected projects.
## Testing
Update request payload assertions to verify the Codex plugins configuration alongside managed environment defaults, model overrides, and deferred project readiness.
GitOrigin-RevId: c4ab95aa8e3440c816c5cd136444a038f4532eb9
## What changed
- Pass goal objectives as untrusted `goal_objective` context instead of embedding them in continuation instructions. Direct the model to use `get_goal` if the objective is missing or truncated.
- Inject newly created objectives into their originating active turn without dropping unrelated client context. Render them as tool outputs when `UntrustedAsToolOutput` is enabled.
- Queue additional context together with automatic turn input so both reach the first model request.
## Testing
Extend app-server coverage to verify that model-written objectives appear as tool outputs at creation and continuation, without duplicating them in user messages. Update steering and Python SDK tests to check objective preservation and delivery alongside continuation instructions.
GitOrigin-RevId: 6f44f6d6c895bb4dc378c9cf84d6470ccc885c67
## Why
After Cloud thread history is replayed in the TUI, notifications for the same completed assistant items can render their text again.
## What changed
Track completed assistant items rendered from Cloud history by turn and item ID, and ignore subsequent starts, text deltas, and completions for those items. Apply this tracking when resuming threads and replaying thread snapshots, while allowing unfinished items and new turns to continue streaming.
## Testing
Extend the Cloud resume picker test to cover repeated notifications for completed messages, continued streaming in an active turn, and responses in a later turn. Retain coverage for queued user message reconciliation without resubmission.
GitOrigin-RevId: 1a829a2964586d876339c7c759022e4d366c8b2e
## Why
A queued cloud stream disconnect can outlive a successful reopen of the same conversation, causing an obsolete reconnect error to reach the TUI.
## What changed
Represent cloud reply stream losses with `AppServerEvent::ThreadStreamDisconnected` and filter queued losses superseded by a successful attachment to the same thread. Preserve losses for other threads and any newer disconnects; failed reopen attempts do not supersede pending losses.
Continue displaying current stream disconnects through the TUI's error notification handler.
## Testing
Add regression coverage for successful and failed reopens, disconnect ordering across threads, and TUI handling of disconnect events from the active and foreign backends.
GitOrigin-RevId: 640332b817970717fc816ab5a32bf658c01233bf
## Why
Failed Cloud turns can contain an error without any items. Loading history through item pages alone can omit these older failures from the full transcript.
## What changed
- Add a `FullTranscript` hydration scope that fetches remaining Cloud turn metadata in pages of 100 after loading items.
- Deduplicate overlapping turn pages while preserving chronological order and already loaded items.
- Use the new scope for session transcripts while retaining `Complete` hydration for exports.
## Testing
Add a regression test covering older itemless failures, overlapping turn pages, repeated pagination cursors, transcript ordering, and item-only exports.
GitOrigin-RevId: 51183e35984aa0183d044061768555bb6f5d1189
## What changed
- Show latest user-prompt previews beneath saved side-chat titles, fetching previews only for visible entries when the chooser refreshes.
- Keep cached chats available during discovery, show loading and refresh status, and offer an inline retry action on failure.
- Preserve the selected chat across list updates and prevent asynchronous changes or held activation keys from opening an unintended entry. Account for preview rows in paging and mouse selection.
- Explain that side chats become available after the first main-chat message, and let `Ctrl+C` dismiss the chooser while preserving the main draft.
- Separate tabs with noninteractive gaps and improve hover styling for tabs, overflow arrows, and the add button.
## Testing
Extend integration tests and snapshots for discovery failures and retries, refreshed prompt previews, activation guards, variable-height paging, draft preservation, and tab hover states across light, dark, and fallback colors.
GitOrigin-RevId: 34423f5aeccb566682f7aa219f54ca5c7c8304fb
## What changed
Set `deferred_environment` to `true` in cloud thread prewarm requests when a project is selected. Omit the field for default thread prewarming.
## Testing
Update the prewarm request encoding test to verify that only requests with a selected project include the deferred readiness flag.
GitOrigin-RevId: e10a646ebde9cc3acbdb01b304af0f73ecc1dbeb
## Why
Command center search only filtered tasks already loaded for browsing, leaving older tasks undiscoverable without manually loading more history.
## What changed
- Scan history on the active backend for case-insensitive matches in task names, previews, and working directories, using a separate paging cursor for each query.
- Add loading, retry, and `Show more matches` states. Cancel superseded searches and ignore stale results.
- Keep history matches separate from browse results and restore the previous selection when leaving search.
- Preserve the original task preview for search while displaying the latest prompt in task details.
## Testing
Extend discovery and command center tests to cover older history matches, fresh queries after browse pagination is exhausted, selection restoration, actions on search results, loading and retry states, and separate original previews and latest prompts.
GitOrigin-RevId: 9864ee006a14bd232e9cfd7ab2ee099c84667597
## Why
Clients attaching to a shared app server can miss startup notifications and have a different local MCP configuration. Waiting for locally configured servers can leave the TUI stuck in a busy state.
## What changed
- Track only reported MCP servers for shared app servers and subagents, settling startup once observed starts complete.
- Handle standalone terminal updates without reopening startup, while reporting failures and cancellations even when their starts were missed.
- Suppress duplicate diagnostics until an observed retry or notification lag, and include all received outcomes in each active round's summary.
## Testing
Add regression coverage for attachment before, during, and after startup; idle keyboard behavior after startup settles; terminal-only failures and cancellations; and repeated failures after retries or notification lag.
GitOrigin-RevId: e19f23c212f2f3cee1adeb5c3b94a508aa599242
## What changed
Only allow the cancel action to dismiss the agents overview when a chat is displayed or a startup thread is pending. Hide the `esc back` footer hint when there is no chat to return to, while retaining back hints for help and metadata editing.
## Testing
Add coverage for returning to a chat that is still starting and for pressing Escape in the overview after cancelling folder trust. Update snapshots and test setup to reflect whether a chat is available.
GitOrigin-RevId: af259330eb2a743fde449bbbd47c7f0eb6fa937e
## What changed
Show a startup warning when the active model matches the CLI model override but is missing from the ChatGPT model list, for ChatGPT accounts using the OpenAI provider. Suggest checking the spelling or choosing another model with `/model`, while preserving the selected model and submitting queued startup input.
Reuse the transcript-visible warning helper for this notice and existing usage warnings.
## Testing
Extend the startup test to check the warning text, preserved model selection, and queued input submission.
GitOrigin-RevId: bb1e8c415346bf271e25ef4e8571c13b4bc2c8c8
## What changed
- Add `CodexThread::agent_tree_id()` to identify a loaded agent tree. The root and native children share an ID; loading a new tree produces a new ID even when reusing a persisted thread ID.
- Add `EnvironmentManager::remove_environment()` to unregister an environment while preserving existing handles and the default environment ID.
## Testing
Extend tests to check tree IDs across child creation, forks, warm reuse, and cold reloads, and to verify environment removal and re-registration.
GitOrigin-RevId: 43944ed6766374508d9862cd5d333bc4cb67c338
## What changed
Add `exec_tools_update_hint` and `exec_tools_removed_definitions_header` to `model_messages.tools.incremental_tools` and use them when rendering Code Mode catalog updates and removals.
Overrides are literal strings limited to 512 UTF-8 bytes per field. Missing, null, or oversized values use the existing bundled wording. Empty strings omit the guidance while retaining changed definitions and removal keys. Wording changes alone do not trigger catalog updates.
## Testing
Extend unit coverage for defaults, null fields, independent fallback, and UTF-8 byte limits. Add scenario assertions and a snapshot covering custom and empty wording, model switches, catalog changes, and restoration after compaction.
GitOrigin-RevId: da9e00fdb5197a2b5fa39ce533ba87c76ff3e82c
## Why
Custom-provider sign-in previously required a saved gateway configuration and stopped at an error when none existed.
## What changed
- Add “Create a custom provider or gateway” to the sign-in picker, reusing the settings form and provider-write handling.
- Return to the picker after saving, highlight the new provider, and require explicit selection before setting it as the default and completing sign-in.
- Preserve entered fields after validation failures and keep the focused field or Save action visible in short terminals.
- Use consistent custom-provider and gateway wording across sign-in, settings, and validation messages.
## Testing
Add onboarding tests and snapshots for an empty picker, creation, validation retries, short-terminal rendering, and explicit default selection. Extend app-server coverage for rejecting the reserved `ollama-chat` provider ID.
GitOrigin-RevId: 339ac5807c5eecdae08df4dbd89874ea7c764d35
## What changed
- Add configurable `sidebar_up` and `sidebar_down` actions to cycle through tabs with wraparound while the sidebar has focus. Default leader shortcuts use `Shift-Tab` / `Tab`, `Up` / `Down`, and `k` / `j`.
- Support mouse-wheel tab switching over the tab strip and clickable overflow arrows when tabs do not fit.
- Show previous/next tab shortcuts in the leader HUD and keymap picker, and preserve pane zoom when switching tabs.
## Testing
Extend sidebar interaction tests and snapshots to cover overflow arrows, mouse-wheel navigation, leader shortcuts, repeated custom bindings, draft preservation, and scroll handling where the leader HUD overlaps the tab strip.
GitOrigin-RevId: 39ccb40f40560d1be850397f9597e765caa996a3
## Why
Skill completion inserts a trailing space, leaving unwanted whitespace when the next typed character is punctuation, such as `$rustdoc ,`.
## What changed
Replace the space inserted by skill completion when immediately followed by common closing punctuation, producing `$rustdoc,` instead. Support both skill mention pickers, including full-width punctuation and `》`, while preserving skill bindings.
Preserve existing draft whitespace and keep the separator for pasted text or punctuation entered after cursor navigation. Classify buffered punctuation as typing or a paste burst before deciding whether to remove the space.
## Testing
Add regression tests for punctuation, existing spacing, cursor navigation, and paste bursts, plus a snapshot covering `》`, recovery state, and preserved skill bindings.
GitOrigin-RevId: 8988add8092e8cb5f0618ef834590d52a81ad576
## What changed
Count tool and namespace-instruction entry deltas in `codex.tools.exec_entry_updates`, tagged by `added`, `schema_changed`, or `removed`. Entry replacements count as `schema_changed`; full catalog declarations do not count as entry deltas.
Record rendered UTF-8 batch sizes in `codex.tools.exec_update_bytes`, including hints and framing but excluding full declarations and removal notices.
## Testing
Extend the namespace transition test to verify action counts, UTF-8 byte totals, and metric behavior when exec is hidden, restored, or unchanged.
GitOrigin-RevId: 22070b84230296d78a67b83641cbc02157d84419
## What changed
- Cover incremental exec tool settings and catalog changes across resume, fork, tool mode switches, and compaction.
- Verify that adopting background compaction preserves live exec declarations, tool metadata updates, and retained conversation order after a model catalog refresh.
- Include an `exec` namespace in the top-level tool catalog ordering and snapshot round-trip test.
GitOrigin-RevId: 3df603b98a006abb55a5095b299080f036576242
## Why
Recovered answer history needs presentation instructions alongside the moderation flag so clients can apply the intended display behavior.
## What changed
- Add optional `display` metadata with an `action` and optional `blockType`, `cyberTrustedAccess`, and `checkTrustedContacts` fields.
- Carry display metadata through final answers, legacy events, thread history reconstruction, and legacy rollout migration.
- Expose the metadata in the app-server protocol and update generated JSON schemas, TypeScript types, and Python SDK models. Missing display fields remain compatible with existing stored moderation data; the app-server emits absent optional values as `null`.
## Testing
Extend the final-answer moderation test to cover display metadata in answer items and legacy events. Add serialization coverage for missing display data, nullable fields, and preservation of an explicit `false` value.
GitOrigin-RevId: b798a2ecc53c2a94c7659ef3d9663b3143b70a1a
## Why
Changes to nested tools should update the model's catalog without repeating the full `functions.exec` declaration or rewriting retained context.
## What changed
Pass structured exec definitions through the tool router into the session's tool world state. Enable granular updates for Responses Lite in `CodeModeOnly` when both `IncrementalTools` and `IncrementalExecTools` are enabled.
Append changed tool definitions, namespace instructions, and removals as developer messages. Keep common exec instructions and shared types frozen until compaction, then install the latest full catalog.
## Testing
Add feature-gating coverage and a scenario snapshot covering tool additions and removals, namespace instruction changes, eager/deferred transitions, re-enabling tools, retained context, and catalog restoration after compaction.
GitOrigin-RevId: bbf850d4e5018388eeb4c09345d885d776962e09
## What changed
Render stable entries for nested tool definitions and namespace instructions alongside the full `functions.exec` description. Add optional catalog tracking that emits complete replacements for added or changed entries and explicit notices for removed entries, while keeping the existing exec declaration unchanged.
Preserve entry hashes while exec is unavailable, then restore the full catalog and withdraw removed entries when it returns. Keep the existing snapshot format for ordinary tool catalogs.
This change provides the rendering and state support; runtime activation remains disabled.
## Testing
Add tests for definition rendering and namespace identity, batched additions and changes, removal notices, unchanged catalogs, and full catalog restoration after exec is hidden.
GitOrigin-RevId: f472bd3e8e770a8cad9663c72e290abe7d0473be
## What changed
- Save side chats as attachments to their parent conversation when local workspace history supports them, and let users reopen them from the sidebar after a restart.
- Show chat names or first-prompt previews in sidebar labels, and allow saved side chats to be renamed with `/rename`.
- Add tab close buttons, middle-click closing, and the configurable `close_sidebar_tab` shortcut, defaulting to `Ctrl-X W`. Closing a saved chat keeps it available in the picker; archiving removes it from Side chats.
- Confirm actions that stop running work, discard unsent input, or lose temporary history. Delete saved TUI side chats when deleting their parent conversation.
## Testing
Add coverage for reopening saved side chats after restart, archive handling, close confirmations, and preventing close-confirmation keys from accepting a replacement approval dialog.
GitOrigin-RevId: 3d47533d007286a7354660c08df13a83dd48d5d7
## Why
Code mode requests can fail before a `CodeCellStarted` event. Suppressing their dispatch traces loses the caller-facing error in that case.
## What changed
Record dispatch lifecycles for code mode custom payloads, preserving their results independently of code cell events.
## Testing
Update the incompatible-payload regression test to use the code mode tool name and verify that replay retains the failed tool call and result payload even when no code cells were recorded.
GitOrigin-RevId: 687a36cd7ba55665ed7abc88c36732597e7fb025
## What changed
- Honor `RuntimeAgentInstances` and the configured runtime auth mode for Analytics plan discovery and report requests to OpenAI endpoints.
- Share installation ID resolution and Codex runtime registration setup through `codex-runtime-agent-instance`.
- Preserve typed runtime authentication errors so expired credentials retain the “Sign in again to load Analytics” guidance.
## Testing
Add coverage for both runtime auth modes across regional and staging endpoints, fresh assertions for each request, sign-in guidance after bootstrap failure, redirect rejection, and invalid organization/project selectors.
GitOrigin-RevId: 50e0d959b3abd81ebe7a6a584e272f14cf52e504
## Why
Invalid assertions and paused or revoked runtime instances cannot recover through request retries or credential refresh. Permanent refresh-token failures also need to retain their sign-in error instead of becoming retryable stream errors.
## What changed
- Recognize terminal runtime denial codes in `401` and `403` response bodies and identity error headers, preserving HTTP diagnostics while stopping retries.
- Skip credential recovery for runtime denials in runtime-enabled model providers and backend requests, while preserving recovery for ordinary credential expiration.
- Propagate permanent refresh-token failures through runtime authentication as `RefreshTokenFailed` errors.
## Testing
Add coverage for body and header denials, preserved HTTP diagnostics, provider-scoped credential recovery, and cached permanent refresh failures. Complete-turn tests verify that runtime denials stop without retries or refreshes while expired credentials recover in both runtime authentication modes.
GitOrigin-RevId: 33f6f707454130e97e13f3b53e29d2c484602152
## Why
Security reminder requests need to use app-server's active authentication and HTTP runtime, with results bound to the login that fetched them.
## What changed
- Add `account/securitySetup/read`, returning an optional notice with account and user IDs, plus generated protocol schemas and bindings.
- Fetch reminders in app-server only for a matching saved ChatGPT login. Return `notice: null` for ineligible, unavailable, or timed-out reads, and discard results when the login changes during the request.
- Route TUI reminder reads through the new method while retaining notice validation and identity checks. Unsupported servers produce no reminder.
## Testing
Add coverage for shared runtime use across restarts, ineligible authentication modes, and login changes during a fetch. Update TUI coverage for unavailable, unsupported, and mismatched notices.
GitOrigin-RevId: 426fee7ce98df17970957c06876881bc5b005196
## What changed
Make `ModelRequestContributor::budget_exhausted` return an `ExtensionFuture` and await budget checks before HTTP and WebSocket generation. WebSocket warmup continues to skip budget checks.
If the account changes during the post-connect budget check, rebuild the request setup and reconnect before sending the WebSocket request.
## Testing
Update tests to cover a pending budget check that resolves to exhaustion, warmup connection reuse, and an account switch while the post-connect budget check is awaiting completion.
GitOrigin-RevId: 462c74b86a46a4b2276f901c69187fc7cbc3ff81
## What changed
Make `AgentServiceTier` reads asynchronous and have updates return a receipt for local acceptance. Await acceptance during root startup and settings updates outside state and registry locks, sharing the receipt with explicit same-tier retries.
Await shared-tier reads during child preparation, startup prewarm, and step capture. Allow cancellation while capturing a step, and keep host propagation independent of the acceptance wait.
## Testing
Extend the host-child WebSocket test to cover delayed acceptance, same-tier retries without duplicate updates, accessible settings while acceptance is pending, and tier inheritance during prewarm and subsequent steps.
GitOrigin-RevId: 0e2e1899834c37684e904c4a36e66344a0c6c7f3
## Why
Remote-control enrollment, refresh, and client-management requests used ChatGPT bearer authentication without resolving the configured runtime authentication mode.
## What changed
Pass the app server's runtime auth slot and mode into remote control, and resolve authentication and HTTP client policy for each request. Supported OpenAI destinations use fresh runtime assertions in `dual_header` or `assertion_only` mode, while custom destinations retain bearer authentication.
Wait for runtime authentication to initialize and reject unsupported OpenAI origins or mismatched registered accounts. Pairing continues to use its server token.
## Testing
Add transport and app-server integration coverage for both runtime auth modes, fresh assertions, shared runtime registration, network policy enforcement, account validation, redirect credential handling, and pairing token preservation.
GitOrigin-RevId: 5401cf565630ab84eaba71ff6040ac27f7b92461
## Why
An inherited turn can suppress a fork's configured developer instructions, leaving the first side-chat request without its developer policy.
## What changed
- Move shared side-conversation instructions and the history boundary into `codex-context-fragments`.
- Inject the developer policy before the user-role boundary when creating a TUI side-chat fork, while retaining the configured instructions.
- Distinguish attached and temporary policies, applying the worktree restriction only to temporary side chats.
- Add guidance to set up recurring monitors in the main chat or a new chat because temporary side chats cannot run scheduled updates.
## Testing
Add a TUI integration test that checks the first side-chat model request contains the policy and boundary. Add a core request-history snapshot covering an attached side chat that preserves inherited context, policy, and its prior answer after resuming from disk.
GitOrigin-RevId: 889cb317dc3327457cd9ef0879ec9f77dbfaeeba
## Why
Guardian Decisions requests used bearer keys directly, bypassing runtime authentication. Memory startup quota checks used the app-level auth manager instead of the thread's provider auth context.
## What changed
- Bind Decisions credentials to runtime authentication and use route-aware HTTP clients with sensitive header protection. Preserve workload identity credentials, reuse the saved-login runtime binding, and isolate explicit API key bindings.
- Select the staging Decisions endpoint when the ChatGPT environment is staging.
- Use the thread's `ProviderAuthContext` for memory startup and quota checks, preserving account-bound network policy and applying runtime authentication.
- Keep custom destinations independent of runtime assertions.
## Testing
Add regression tests for dual-header and assertion-only authentication, fresh Decisions assertions, saved versus explicit credential isolation, workload identity, staging routing, redirect header protection, and memory quota authentication with custom destinations.
GitOrigin-RevId: 27bc7821a1cad1f5d1d2a71680527ea91ace95db
## Why
Cloud messages previously accepted only plain text, and switching a draft to Cloud waited for session preparation without processing composer input.
## What changed
- Support ordered text and image parts in Cloud submissions and user-message summaries, preserving attachment placeholders, image detail, and client message IDs.
- Accept inline data URLs and uploaded file IDs, including image-only messages. Reject invalid references and text spans locally, and cap encoded image requests at 3.75 MiB while retaining the existing plain-text limit.
- Keep the composer editable and redraw the TUI while Cloud prepares a conversation. Carry the latest draft, attachments, and Vim mode into the destination, retain drafts on failure, and prevent submission to the outgoing session during the handoff.
- Preserve buffered paste input and pending clipboard reads across the handoff, with connection and failure hints.
## Testing
Add regression coverage for image wire encoding, receipt identity, validation and size boundaries, draft editing during successful and failed handoffs, clipboard completion, Vim state, and attachment recovery after rejected submissions.
GitOrigin-RevId: 0cbcde0ab89ba961780b5f88456057e6b6a19cd5
## Why
An open WebSocket can remain usable after its runtime is paused. Runtime-authenticated requests need a fresh handshake to revalidate access before submitting more work.
## What changed
- Reconnect before each runtime-authenticated Responses request and skip speculative preconnection. Preserve turn routing when the runtime identity is unchanged.
- Open a fresh connection for each runtime-authenticated Guardian classification instead of prewarming or reusing pooled sockets.
- Preserve HTTP fallback for unsupported upgrades and connection failures, while propagating authentication, authorization, rate-limit, and policy errors.
## Testing
Add regression coverage for pause and unpause behavior, credential changes, fresh assertions, and Guardian HTTP and WebSocket transports in both runtime authentication modes.
GitOrigin-RevId: 9f650147260da5cbbf5bb23dfff0af095fff3955
## Why
Child startup can lose remote model capabilities such as `tool_search` when the selected catalog is uninitialized or disk data is older than the parent's in-memory snapshot.
## What changed
- Initialize the final provider, auth, and originator catalog before resolving a child's startup model, then read it from memory.
- Preserve loaded catalogs, including empty responses and updates that failed to persist, without overwriting concurrent refreshes.
- Reuse catalogs across retry and WebSocket transport overrides while retaining routing and header distinctions.
## Testing
Add regression coverage for child tool search with warm, cold, and disabled caches; failed cache writes; concurrent refreshes; empty catalogs; and Guardian reviewer catalog reuse.
GitOrigin-RevId: 01d995a65b623cc7d6f26e2dc9b6e8cf380de782
## What changed
Raise the per-entry limit for plugin `interface.defaultPrompt` from 128 to 512 characters, retaining the maximum of three prompts. Update the protocol documentation and generated schemas and bindings to reflect the new limit.
## Testing
Update manifest coverage to accept a 512-character Unicode prompt and reject an over-limit prompt. Adjust the discovery warning test to use a 513-character prompt.
GitOrigin-RevId: 0ba3ceb253edf22a583f774492934b7c9b5ac231
## Why
Stale saved grants or malformed rules can cause valid network denials to be discarded. A failed rule write can also leave the in-memory policy inconsistent with native enforcement.
## What changed
- Add a helper to derive MCP network policy from controller and environment policies, permission profiles, approval settings, and saved rules. Preserve managed restrictions and conservatively deny traffic that requires review, request hooks, or DNS checks the metadata cannot express.
- Retain valid saved denials when grants violate managed constraints or a rule batch is malformed.
- Serialize runtime updates and persistence, publishing denials before the write so they remain effective if saving fails. Publish saved grants after a successful write.
- Extract validation of listener settings for running proxy updates.
## Testing
Add coverage for policy composition, mixed-executor local binding, native proxy denial parity, stale grants, malformed denials, failed persistence, and compatibility with trusted MCP servers without policy negotiation support.
GitOrigin-RevId: ef00632acb48a51fc582f18d20a3e713f953a191
Add `WindowsSandboxFilesystemOverrides::resolve` to select the elevated or
restricted-token resolver, and use it in core, exec-server, and direct-spawn
sandbox preparation. Pass the child environment through to the elevated
resolver.
Replace the exported unsupported-sandbox reason helper with a test-local
wrapper around the shared resolver.
GitOrigin-RevId: f1d404356a4f680ce81123bc8284508f27d4d6ab
Won Park