Commit Graph
5508 Commits
Author SHA1 Message Date
jif bfdbf01bfa Move agent message board host integration to app-server (#59162)
## What changed

Move the board host adapter and `install_agent_message_board` from `codex-core` to `codex-app-server`, using public core runtime interfaces. Update extension registration, test callers, dependencies, and installation documentation to use the new location.

Format `CHANNEL_POST` notification payloads in the host adapter and retain recognition of legacy board notices in core. Expose `MULTI_AGENT_V2_NAMESPACE_DESCRIPTION` for host extensions to share with native tools.

GitOrigin-RevId: 679b5751de102bff80e6b9d4b0728a84fbdedd85
2026-11-03 13:38:59 +00:00
felixxia-oai 6163584549 Move Guardian unit tests into their owning crates (#59159)
## What changed

- Move approval-request and prompt-composition tests from `core` to `guardian-reviewer`.
- Move transcript collection, budgeting, and approval-reason truncation tests to `guardian-context`, removing the test-only rendering helper from `core`.
- Move the managed-feature reviewer configuration test to `guardian-v2`.

GitOrigin-RevId: 1886a10cd6aba07b7ca2bcce28d45e0a698111a6
2026-11-03 13:32:14 +00:00
jif 4a971492e7 Expose thread APIs for message board access (#59154)
## What changed

- Add `CodexThread` methods for reading the registration source, resolving agent references, and reading the configured clock.
- Replace the board-specific thread lookup with public `ThreadManager::get_thread_with_extension`, which requires matching typed extension data and never loads a missing runtime.
- Update the local message board host to use these APIs and thread startup metadata instead of accessing session internals directly.

GitOrigin-RevId: 143b798cc710e079e20be59a84d05738a3bc6a0b
2026-11-03 13:17:38 +00:00
jif f05aa41da6 Route message-board notifications through agent mailboxes (#59139)
## Why

Board notifications were skipped when recipients had no active turn accepting mailbox delivery. Queue them through the ordinary agent-message path so idle recipients can receive them in a later turn.

## What changed

- Submit board notices as `Op::InterAgentCommunication` with `trigger_turn` disabled, preserving normal mailbox scheduling without reopening finalized answers.
- Hold a residency guard through dispatch of submitted agent messages to coordinate delivery with agent eviction.
- Update board tool descriptions to describe the host's notification queueing and wake policy.

## Testing

Update local and HTTP board scenarios to cover queued idle notices, delivery after a finalized answer, and mailbox delivery before a pending tool call. Extend residency coverage to verify that submission waits for the eviction gate and queued messages survive eviction.

GitOrigin-RevId: a77137fc40932f5903852e14742483844e07c9bc
2026-11-03 12:33:26 +00:00
felixxia-oai 3b5483307d Parse Guardian review responses once (#59136)
## What changed

Introduce `GuardianReviewResponse` to retain both the parsed assessment and the original response text. Reuse the stored result for authorization checks, denial reconsideration, review record capture, and final assessment extraction instead of reparsing the response.

Preserve raw text for review records and keep invalid responses as completed turns so history and session reuse remain unchanged.

## Testing

Extend review record coverage to wrapped denials and invalid responses, and verify that invalid assessments remain retryable while missing assessments do not.

GitOrigin-RevId: 50c19e788a8d57f951c6140d66306b3538515adc
2026-11-03 12:20:21 +00:00
jif 86b2eca691 Allow dangerous-command review when sandbox approvals are disabled (#59120)
## Why

Setting granular `sandbox_approval` to `false` also blocked approval requests for dangerous commands such as `rm -f`, even when they requested no additional permissions. Reviewing a dangerous command should remain possible within the existing permission profile.

## What changed

Allow heuristic dangerous-command approval requests with `sandbox_approval = false` when execution stays within current permissions. Do not propose reusable execution-policy amendments for these approvals, since reusable allow rules can bypass the sandbox on later calls.

Keep escalation requests, explicit policy rules, and Windows execution without required sandbox protection subject to their existing approval restrictions. Clarify the meaning of `sandbox_approval` in the protocol and generated schemas.

## Testing

Add coverage for POSIX and Windows approval decisions, approval and denial of deletion commands, preservation of read-only restrictions, and separate dangerous-command approval after turn-scoped or session-scoped write grants.

GitOrigin-RevId: 90adc137c7b7d3f3ee68efb1f6bea531229e7834
2026-11-03 11:14:59 +00:00
jif 62d650d527 Preserve worker permissions across sibling-triggered reloads (#59115)
## Why

Waking an evicted worker from a sibling should preserve the worker's effective permissions, including runtime grants, denials, and network restrictions that a profile name alone cannot reconstruct.

## What changed

Retain the worker's effective configuration during eviction. On sender-driven reloads, restore its permissions and approvals reviewer while keeping the current wake configuration for other settings.

## Testing

Add regression coverage comparing loaded and reloaded workers with read-only, named, and legacy permission settings. Verify that worker permissions, active profiles, and network policies survive sibling wakeups and that parent and sender permissions remain unchanged.

GitOrigin-RevId: ffc353154535362cfbfbbe2b7fc43e08b42cf9b9
2026-11-03 10:44:27 +00:00
dpatel-oai 33ffb6f905 Normalize saved chat settings after model catalog refreshes (#59111)
## Why

Existing chats can retain reasoning effort and service tier selections that a refreshed provider catalog no longer supports.

## What changed

- Apply fresh provider catalogs to saved settings in open and resumed chats, and normalize incoming settings before capturing the next turn.
- Replace unsupported ranked reasoning efforts with the highest supported level at or below the selection. For unsupported `ultra` or `persistent` selections, use the model's supported default when available. Reset unsupported `priority` and `ultrafast` service tiers to `default`.
- Retire incompatible reasoning effort pins using each step's captured model metadata, preserving running steps and the live pin during compaction.
- Publish catalog updates only from successful provider responses for the current identity, and refresh retained originator catalogs through the periodic refresh worker.

## Testing

Add coverage for setting correction, reasoning effort pins, resumed chats, stale queued settings, retained history, refresh failures, identity changes, and isolated originator notifications.

GitOrigin-RevId: 2ef4605c4acba98db3fe9d0328e2752084e900a2
2026-11-03 10:01:36 +00:00
jif a805143486 Add opt-in reconsideration of Guardian denials (#59107)
## What changed

Add the disabled-by-default `guardian_denial_reconsideration` feature to reconsider a synchronous Guardian denial once before publishing the final decision. The follow-up uses the same review session, evidence, model settings, and original deadline, without compacting the retained context.

Only a valid second assessment replaces the denial. Invalid or failed follow-ups keep the original denial and discard the review session; cancellation and timeout retain their normal outcomes.

Allow a custom developer message through `auto_review.experimental_denial_reconsideration_prompt`, limited to 1,000 UTF-8 bytes. Omitted or blank values use the built-in prompt, which grants no new authorization and preserves the security policy.

## Testing

Add scenario coverage for feature gating, unchanged approvals, reconsidered approvals and denials, invalid assessments, failed follow-ups, custom prompts, and retained context. Extend cancellation coverage to reconsideration and config tests to prompt normalization and byte-limit validation.

GitOrigin-RevId: 61c45d5a948e3e5684c4b4048d6e90fd3f1f2476
2026-11-03 09:51:25 +00:00
rishab 29eed28082 Enforce strict third-party tool deferral in Code Mode Only (#59071)
## What changed

Restore `code_mode_only_strict_3p_tools` as an opt-in feature under development. When the effective tool mode is Code Mode Only, keep eligible MCP/app and client-supplied dynamic tools deferred and callable through `exec`, regardless of `deferLoading`, `omit_tools_from`, or namespace exclusion and direct-only settings.

Preserve hidden tools, tool policy restrictions, and built-in tool classification. Log conflicting exposure settings without adding warnings to the model prompt. Leave other effective tool modes unaffected.

## Testing

Add coverage for exposure overrides, model mode overrides, built-in name collisions, and hidden or denied tools. Update integration coverage for app access restrictions and MCP catalog refreshes that preserve the cached prompt prefix while `exec` uses the current tools.

GitOrigin-RevId: 0cb085ba9d23bebc48dbc3fa298b982de0a66c47
2026-11-03 06:05:55 +00:00
Dmitriy Kovalenko 3f958ac2fe Run Bazel CI locally without BuildBuddy credentials (#59055)
## What changed

- Remove automatic BuildBuddy configuration and credential forwarding from Bazel CI, release, SDK, and voice builds. Strip remote execution CI configs in the shared wrapper while retaining explicit remote configurations for local use.
- Use native Windows host tools and audio dependencies for Windows Bazel actions, forwarding the required toolchain and environment settings.
- Initialize message-board MCP servers through a per-session `OnceCell` so server startup does not hold the shared registry lock across an await.
- Expose the message-board test helper to the core Bazel package and update the runtime-auth test call for the `reauth` argument.

GitOrigin-RevId: 5d5c1f4d71fa841090dea8eec8006380981fb65b
2026-11-03 04:08:59 +00:00
Adam Perry @ OpenAI 7e8143a897 Tie executor attachments to environment selection lifetimes (#59043)
## Why

Removing an executor must detach its selection even when older turn snapshots still reference it. Connection events queued for a removed attachment must not leak into a later selection of the same executor.

## What changed

- Introduce `EnvironmentAttachment` with a detach signal shared by turn snapshots and a guard owned by the selection.
- Preserve attachments across workspace and configuration changes, while giving reselections and child threads independent attachment lifetimes.
- Stop forwarding connection events on detach and discard buffered events from detached attachments.
- Activate initial attachments after `SessionConfigured`, using configured bindings for startup discovery.

## Testing

Add coverage for discarding buffered connection events on reselection and extend snapshot tests to verify immediate detachment, fresh attachments on reselection, and independent parent and child lifetimes.

GitOrigin-RevId: 6cf882e0d17a296030c13d80c6e2866c80e04638
2026-11-03 02:37:20 +00:00
aojiao-oai 16ddd538bd Expose assistant content token counts in completion notifications (#59041)
## What changed

Add optional `contentTokenCount` metadata to `item/completed` notifications, carrying the producer-supplied token count for each completed assistant message in default and plan modes. Counts include any sampled footer and are `null` when unavailable.

Keep this telemetry separate from stored thread items and omit it from subsequent model requests. Update the protocol schemas and generated TypeScript and Python types.

## Testing

Add coverage for per-message counts, including zero, in default and plan modes; missing and malformed metadata; backward-compatible notification decoding; and exclusion from subsequent model requests.

GitOrigin-RevId: 35973037a42650fa2d7569da8e88cb81215cf971
2026-11-03 02:26:29 +00:00
yitaoh-oai e839b828fb Resolve model-selected search providers with policy-aware fallback (#59036)
## Why

Search discovery must account for the active model's supported tools while honoring host search restrictions. Automatic fallback must also preserve the provider that owns existing browsing references.

## What changed

- Resolve search from model metadata, client configuration, and managed requirements, exposing the selected provider's tools.
- Discover hosted search with the model's supported tools and carry the discovered invocation context into calls.
- Allow native fallback for eligible discovery failures only when search policy permits it and hosted search has not already been used. Do not replay failed hosted invocations through native search.
- Keep native fallback references on native search across later turns, discovery recovery, and resume. Release unused fallback offers and coordinate background calls to prevent conflicting provider use.

## Testing

Add app-server and core scenario coverage for provider selection, discovery failures, search restrictions, reference continuity, resume, and concurrent background search. Include a snapshot covering discovery and call history across a model switch.

GitOrigin-RevId: 0f22605722daaa424c4fa34660654cde5a6db049
2026-11-03 02:08:56 +00:00
yitaoh-oai b26f682672 Add web search provider metadata and configuration (#59033)
## What changed

- Add optional `ModelInfo.web_search_provider` metadata with `standalone` and `search_mcp` values.
- Add `tools.client_search_provider` and expose its value as `client_search_provider` in app-server configuration responses, with updated JSON schemas, TypeScript types, and Python bindings.
- Register the `hosted_search_policy` feature flag as under development and disabled by default.

GitOrigin-RevId: 263c3f81a61b50f8bb53ff338b9de8186db316e0
2026-11-03 01:58:18 +00:00
sayan-oai f58acd6ede Use prepared MCP owner permissions in Guardian reviews (#59028)
## Why

An MCP server's environment permissions can change after a tool step captures its context. Guardian reviews of direct MCP calls could therefore miss denied paths present in the permissions used to prepare the call.

## What changed

Pass the prepared server environment's sandbox context through MCP approvals and use it to build Guardian's permission evidence, including denied paths and globs resolved for that environment. Keep the sandbox context out of serialized approval actions.

## Testing

Add a regression test that updates a remote MCP owner's permissions after the step starts and verifies that Guardian sees the owner's denied temporary directory. Extend the approval JSON test to verify that supplying sandbox context preserves the serialized action shape.

GitOrigin-RevId: cab0d7c60112a97adf98e5548cdc066b260bb073
2026-11-03 01:41:16 +00:00
rishab 80a8710546 Remove strict third-party tool deferral in Code Mode Only (#59025)
## What changed

Mark `code_mode_only_strict_3p_tools` as removed and stop overriding MCP/app and dynamic tool exposure settings. Code Mode Only now honors `omit_tools_from`, namespace exclusions, direct-only namespaces, and dynamic tool deferral settings without strict-mode exceptions.

## Testing

Update coverage for exposure settings, hidden and policy-denied tools, app access restrictions, and deferred MCP catalog refreshes that preserve the cached prefix while `exec` uses the current tools.

GitOrigin-RevId: 356ccd572f952b5a80ff9a0c31085330b9fe6e8b
2026-11-03 01:31:10 +00:00
Dmitriy Kovalenko 036e160181 Allow concurrent readers of the installation ID (#59021)
## Why

Resolving an existing installation ID takes an exclusive file lock, unnecessarily serializing readers.

## What changed

Read `installation_id` under a shared lock. If its contents are missing or invalid, acquire an exclusive lock and reread the file before generating a UUID, so an ID initialized by another process is reused.

## Testing

Extend the existing UUID reuse test to verify that resolution completes while another shared lock is held on Unix and still restores file permissions to `0o644`.

GitOrigin-RevId: e787d775eddb4d05653d42e809816be9536a94a3
2026-11-03 01:18:58 +00:00
sayan-oai 0585dcb5db Preserve sandbox context in prepared MCP calls (#59020)
## Why

MCP permission profiles need the directory context used to interpret them. Prepared calls must retain that context alongside their captured permissions across runtime refreshes.

## What changed

- Store each server's permission source as thread permissions or a captured environment `FileSystemSandboxContext`.
- Capture environment working directories, home and temporary directories, and materialized workspace roots. Retain the host working directory for thread permissions.
- Expose the captured source through `PreparedMcpCall::permission_source()`, while keeping hosted Apps on thread permissions even when a local environment is attached.

## Testing

Extend binding tests to verify that prepared calls retain environment sandbox paths across refreshes and expose the host working directory for thread permissions. Update elicitation coverage to include hosted Apps with an attached local environment.

GitOrigin-RevId: 87e94605daece324786eebc07b62a507d35e5ced
2026-11-03 01:08:08 +00:00
Ben Romano dec38fc9bb Add WebSocket connection metrics with reauthentication labels (#59018)
## What changed

- Record connection attempts and durations as `codex.websocket.connect` and `codex.websocket.connect.duration_ms`, labeled with `success`, `reauth`, and the configured `product_sku` when present.
- Detect reauthentication by comparing the current auth revision with the last successful connection, preserving that revision across connection resets. Include `auth.reauth` in connection logs and traces.
- Populate session telemetry with the configured product SKU.

## Testing

Extend tests to check reauthentication labels after account switches, product SKU labels for restored sessions, and failed-handshake counts, durations, and labels.

GitOrigin-RevId: 53a38b4460ab9021058dfe2fe104d0441993b18a
2026-11-03 00:59:43 +00:00
Benjamin Carlsson 26f73fba8f Add host cycling and saved defaults for new TUI conversations (#59007)
## What changed

- With multi-backend support enabled, show the current host before the first submission and use `leader b` to cycle through available connections. Expose the shortcut as `tui.keymap.global.change_host`.
- Preserve the conversation name and composer draft, including cursor position, attachments, pending pastes, and literal versus shell-command interpretation of `!`.
- Save explicit host choices in user-only `tui.default_hosts`, scoped to the local project and user identity. Use the saved host for new conversations, falling back to the first available connection when it is unavailable.
- Prepare the destination and check directory trust before replacing the current conversation. Block switching during voice calls and active turns, and remove replaced blank conversations from the session overview.

## Testing

Add coverage for shortcut visibility and remapping, draft and name preservation, project/user preference isolation, unavailable-host fallback, destination trust and startup failures, and voice-call guards.

GitOrigin-RevId: def7b088951336bec8fe3962954fba9b861f91c6
2026-11-02 23:19:03 +00:00
rhan-oai 52b4526275 Allow hosted child threads to inherit a root session ID (#59000)
## What changed

Expose `InheritedSessionId` so a host can supply a root session ID through `ExtensionDataInit` when starting a fresh child thread. The child retains its distinct thread ID, and the inherited session ID is persisted in rollout metadata and restored on resume.

Reject inherited session IDs for resumed, forked, or native agent threads, and reject an inherited session ID that equals the child thread ID.

## Testing

Add an integration test covering distinct child identity, inherited session metadata, and restoration after shutdown and resume.

GitOrigin-RevId: e3462433f9d8a0bba24251ee2b6d5329557ddb31
2026-11-02 22:45:22 +00:00
andrewgu-oai dd2df0aa9d Deliver environment hook decisions while output reads are queued (#58996)
## Why

A completed environment hook can be held up by a queued output-read RPC when its executor is busy, delaying the hook's decision.

## What changed

- Race pushed process events against output polling so a complete, ordered event stream can deliver the hook's output and exit status immediately. Retain polling as a fallback when events are incomplete or unavailable.
- Include launch-parameter preparation in the hook's timeout budget.

## Testing

Extend the executor ownership test to hold the owner's RPC slot while a `PreToolUse` hook finishes. Cover both allowing and blocking commands, checking that the decision arrives before the slot is released and that only the owning executor receives the hook.

GitOrigin-RevId: bc80b99a2a32379e3c2eafefe6db66a6a20f4048
2026-11-02 22:09:34 +00:00
Charlie Marsh 4460449921 Keep HTTP fallback active for the rest of the session (#58989)
## What changed

Once Responses requests fall back to HTTP after exhausting WebSocket retries or receiving HTTP 426, keep subsequent requests and turns on HTTP for the remainder of the session. Clear cached WebSocket state and remove background recovery probes, recovery trials, and their acknowledgement timeout.

## Testing

Update fallback tests to verify that a second turn stays on HTTP without additional WebSocket attempts. Adjust retry and `Retry-After` request-count assertions to exclude background probes.

GitOrigin-RevId: a4f6376604527c14db8d60f79bd21c3aaf289f70
2026-11-02 21:37:17 +00:00
Won Park ac21e58790 Respect delivery boundaries for injected agent messages (#58988)
## Why

Injected agent messages need to reach active sampling before stale tool calls execute, while messages queued around a final answer must wait for the next task without requesting another response.

## What changed

- Include injected `agent_message` items in mailbox preemption checks when the matching turn still accepts mail and `DeferMailboxPreemption` is disabled.
- Treat injected agent messages as queue-only mail so they do not reopen delivery after a final answer or force a follow-up response.

## Testing

Add a streaming scenario and context snapshot covering idle injection, active sampling preemption, deferred delivery around a final answer, and preservation of message payloads and ordering before the next task.

GitOrigin-RevId: 70f49cbe5074725c11e1fcb33eea05e0e92e17f7
2026-11-02 21:35:56 +00:00
jif 9da07658e2 Move agent message-board backend construction into the extension (#58986)
## What changed

Add `BoardBackend` so the core adapter selects the configured backend and supplies a `MessageBoardHost`, while the extension opens MCP, connected, remote, in-memory, and local boards at thread startup.

Move remote credential handling, HTTP client construction, and backend installation into `codex-agent-message-board-extension`, preserving existing notification delivery semantics.

GitOrigin-RevId: 98fa5525f142596c6cc6b203198fd537546c01d5
2026-11-02 21:22:16 +00:00
rhan-oai 40cf168567 Allow hosts to restrict a thread's root-only capabilities (#58984)
## Why

Hosts need to apply subagent-style capability restrictions without changing a thread's session attribution, agent lineage, or permission profile.

## What changed

Add the public `RestrictRootCapabilities` marker to thread startup extension data. Capture the restriction once at startup and apply it alongside the restrictions native subagents already receive. Hosts must supply the marker again when cold-resuming a restricted thread.

Use the restriction to gate user-input and plugin-install requests, async user messaging, legacy MCP tool approvals, and Full Access MCP form input. Exclude inherited user messages from Guardian's retained authorization context for restricted threads, including after cold resume.

## Testing

Add coverage for host-restricted tool registration, MCP approval rejection, Full Access form-input handling, and inherited instruction authorization after cold resume. Update handler tests to exercise the shared restriction flag.

GitOrigin-RevId: 4d6d7102a20dc747431c7511a74a204c773e8420
2026-11-02 21:09:37 +00:00
bkotsopoulos 66e3b5a02c Record turn critical path metrics and trace fields (#58980)
## What changed

- Add critical path capture status and duration fields to `codex.turn_profile` traces.
- Emit capture counts for complete and incomplete profiles, and total and component duration histograms for complete profiles, tagged by product SKU and reasoning effort. Record metrics once per turn timing state and skip disabled captures.
- Extend critical path histogram boundaries up to two hours to cover long turns.

## Testing

Add coverage for duplicate reporting, disabled and incomplete captures, product SKU normalization, trace fields, component durations, and extended histogram boundaries.

GitOrigin-RevId: 5b1af9255f1c4a376b61c81eb68c7a74b01ae9ae
2026-11-02 20:57:23 +00:00
rhan-oai c725e472e5 Add usage accounting for host-owned agent runtimes (#58975)
## Why

Host-owned runtimes skip controller rollout-budget accounting. Give hosts an optional callback to account for inference spending and signal budget exhaustion.

## What changed

- Add `AgentUsageAccounting`, `AgentUsageReport`, and `UsageAccountingDecision`, captured at startup and supported by host child spawn reservations.
- Await per-response usage reports with thread and turn attribution, including provider budget units and foreground and background compaction usage.
- Map host exhaustion to `SessionBudgetExceeded` and accounting failures to fatal errors without retrying inference. Preserve the original error for incomplete responses.
- Keep controller accounting unchanged and leave accounting disabled for host-owned runtimes without a provider.

## Testing

Add coverage for usage attribution, child accounting, budget exhaustion, nonretryable accounting failures, incomplete responses, and compaction reporting, including background usage charged once to its originating turn.

GitOrigin-RevId: 887703f50fe882497e4e8cb33259072935ec82e0
2026-11-02 20:37:55 +00:00
jif 9c23d93d5b Add opt-in MCP discovery for in-memory agent message boards (#58973)
## What changed

Enable `multi_agent_v2` and the new `agent_message_board_mcp` feature to automatically start a temporary, tree-scoped HTTP MCP message board without plugin or endpoint configuration. The MCP feature defaults off and takes precedence over `agent_message_board`.

Share board state across parent and child agents while retaining each caller's host binding. Keep the server alive while participating threads remain, and serialize board tool calls through the MCP server configuration.

## Testing

Extend the HTTP board integration scenario to cover automatic discovery, parent-child message sharing, child subscriptions and posts after the parent unloads, serialized mutations, and absence of a persistent board database.

GitOrigin-RevId: 613183c14b2ab67dfb1aaf3a3abf338376d1cc05
2026-11-02 20:34:35 +00:00
rhan-oai d893b14475 Add host-owned turn admission to the agent runtime (#58963)
## What changed

Add `AgentRuntimeOwnership::Host` and an `AgentTurnAdmission` provider so hosts can acquire execution capacity before runtime tasks run, including root turns. Require the provider at startup and retain its execution guard for the task lifetime. Controller ownership remains the default; host ownership skips controller rollout-budget accounting, budget reminders, and subagent roster context.

Keep pending admission interruptible without blocking input submission. Report admission failures through the turn lifecycle, record accepted input before exposing the error, and unwind task setup such as review mode. Preserve recoverable input during suspension. On interruption, skip prompts that still require a `UserPromptSubmit` hook rather than recording them without inspection.

## Testing

Add integration tests for missing-provider startup cleanup, denial and immediate retry, steering during admission, cancellation, execution guard lifetime, submit-hook handling, suspension recovery, and review-mode cleanup. Add a context snapshot verifying retained input reaches the next admitted turn.

GitOrigin-RevId: 9ee85fad2ecfbfb38735bac8ef88888fb179a967
2026-11-02 20:10:37 +00:00
ioanbudea-OAI 9ede2e87ce Preserve Guardian budget policy through review recovery (#58962)
## Why

Deduplicating against optional transcript entries can remove retained instructions or required tool calls even though the optional copies may later be evicted. Elastic instruction caps can also report evidence loss for revisions already delivered in full.

## What changed

- Capture the review's budget policy and use it for feasibility checks, admission, and restoration after compaction.
- Prefer required and protected native messages over optional duplicates, and use only complete, required pending transcript entries as proof of instruction delivery.
- Match elastic instruction duplicates by source revision and discard truncation observations for copies already delivered in full.

## Testing

Extend coverage for compaction recovery under fixed and elastic budgets, required and protected tool-call deduplication, and capped instruction duplicates covered by complete delivery metadata.

GitOrigin-RevId: fe456e645cdba6f782fb16ad582702d3b7ed012c
2026-11-02 20:10:12 +00:00
rhan-oai 2fa67f03f3 Allow volatile World State sections to refresh after compaction (#58956)
## Why

Host-provided context such as budget reminders can become stale while compaction runs. Replaying a captured value or retaining its comparison snapshot can prevent the next step from emitting a fresh reminder, even when the remaining budget has changed.

## What changed

- Add `WorldStateSectionContribution::without_full_context()` to omit a section's fragment and comparison snapshot from initial and compacted context rebuilds while preserving ordinary step updates.
- Reset comparison state after prefix compaction for sections excluded at either capture or installation, including when their messages survive in the live suffix.
- Include step World State updates when building debug prompt input.

## Testing

Add regression coverage for budget reminders refreshing after remote compaction within the same threshold, unchanged request prefixes within a context window, refreshes with a retained live suffix, and step reminders in debug prompts.

GitOrigin-RevId: ea4456755e16c93b5d16e8c762b26a33f8571a86
2026-11-02 19:38:59 +00:00
felixxia-oai ac9372e521 Add a thread-store builder with host cleanup support (#58954)
## What changed

Replace `thread_store_from_config` with `ThreadStoreBuilder`, exported through `codex_core` and `codex_core_api`, and migrate callers to the builder.

Allow hosts to register `with_additional_cleanup` for permanent deletion in local stores. The callback runs after successful agent-board cleanup and before rollout deletion, under the existing deletion locks. Document that cleanup must be idempotent and must avoid thread-store operations that reacquire those locks. In-memory stores do not invoke the callback.

Preserve the existing backend selection, startup rollout migration, and compression behavior.

GitOrigin-RevId: f2853d7de06fe12ef29451b204cf9fcbb349c359
2026-11-02 19:25:02 +00:00
Jiahao f381b64c11 Support caller-owned sideband channels for realtime attachments (#58953)
## What changed

Add `RealtimeSidebandTransport` and `Op::RealtimeConversationAttachStream` so callers can attach Core to an existing realtime call through bounded JSON channels without opening or reconnecting a socket.

Read events independently of outbound backpressure, enforce a 1 MiB message limit, and drain accepted input on detach or channel closure before flushing the transcript. Pending writes are never replayed.

## Testing

Add transport and Core integration tests covering delegation without a callback socket, stalled output, attachment replacement and detach, channel closure, oversized messages, and preservation of queued transcripts in history.

GitOrigin-RevId: 06b7d1dfe2388054438d72d925e510a959dfe106
2026-11-02 19:17:00 +00:00
Charlie Marsh 0a2dda4b5e Recover WebSocket transport after transient HTTP fallback (#58950)
## Why

A transient WebSocket failure previously kept the session on HTTP for its remaining lifetime, even if WebSocket connectivity recovered.

## What changed

- Probe WebSocket connectivity in the background during HTTP fallback, allowing a subsequent request to use a ready connection without delaying HTTP requests.
- Verify recovery with a real request and bound its first-response wait to five seconds. Keep HTTP 426 responses and recovery timeouts on HTTP for the rest of the session.
- Keep retries of an HTTP request on HTTP. If a recovered connection fails before output, replay the request over HTTP without consuming its ordinary retry budget; failures after output use normal retry accounting.
- Rate-limit recovery probes and honor `Retry-After` deadlines.

## Testing

Extend integration coverage for successful recovery within a turn, disconnects before and after output, full-context replay followed by incremental WebSocket requests, persistent HTTP 426 fallback, and retry deadlines.

GitOrigin-RevId: 1c139a4bbce1a67442db5622fd70ff0cc8056c9c
2026-11-02 19:02:50 +00:00
felixxia-oai 00df7f65ab Preserve Guardian sender context for cloud deliveries with orbit IDs (#58946)
## Why

Delegation messages containing `<source_orbit_id>` fail sender provenance parsing, leaving Guardian without the sender's instructions.

## What changed

Accept an optional `<source_orbit_id>` between `<source_thread_id>` and `<input>`, rejecting values containing `<`. Continue to derive sender authority from the source thread ID.

## Testing

Update the cross-host sender context scenario and snapshot to include orbit attribution. The scenario checks that sender evidence reaches Guardian after compaction and rollback without exposing it to the receiving agent.

GitOrigin-RevId: 463b18667384d30297245eedcd0f6bcbf683634e
2026-11-02 18:43:57 +00:00
Eric Traut 4515bc6df0 Fix model selection after provider setup (#58945)
## Why

After provider setup, new threads could still use the models manager created for the server's startup provider, leaving their default model inconsistent with the model picker.

## What changed

- Build a models manager from the thread's configuration when its provider differs from the startup provider.
- Invalidate the model catalog after successful Amazon Bedrock setup so subsequent model listings reflect the configured provider.

## Testing

Extend Bedrock and GCP setup integration tests to verify that a new thread's model matches the refreshed model listing. The Bedrock test also checks that the thread uses `amazon-bedrock`.

GitOrigin-RevId: 1db30ad040ba97e2f4f31c9e162a2b73af1377fa
2026-11-02 18:42:19 +00:00
Eric Traut a5c4092437 Retire the daemon_auto_start feature flag (#58940)
## What changed

Eligible interactive launches now start or reuse the shared daemon regardless of `features.daemon_auto_start`. Remote-control daemon eligibility also no longer checks this flag. Use `--no-daemon` to run without the shared background server.

Treat `daemon_auto_start` as removed: ignore configured values with a migration notice, ignore managed requirements with a warning, and hide the flag from experimental feature discovery. Remove its launch telemetry tag.

## Testing

Extend retired-feature requirement coverage and add a migration-notice snapshot. Update CLI and TUI integration tests for daemon startup and explicit `--no-daemon` usage.

GitOrigin-RevId: e0290e5acd4bc0169a0f71c3296c567e46269ce3
2026-11-02 18:31:19 +00:00
Alex Kira 1a604d58da Refine additional-context byte histogram buckets (#58939)
## Why

The previous histogram placed post-truncation values just over 4,000 bytes in a bucket ending at 8,000 bytes, obscuring their size near the truncation cap.

## What changed

Use logarithmic boundaries through 4 MiB for `codex.additional_context.value_bytes`, with an explicit 4 KiB boundary near the truncation cap.

## Testing

Add a regression test verifying that post-truncation samples between 4,024 and 4,043 bytes land in buckets ending at or below 4 KiB while preserving their sum and count.

GitOrigin-RevId: af268fc0de3d5ceb648ce51fced3918317f2457a
2026-11-02 18:05:13 +00:00
victor-openai 62bf900680 Skip attribution for direct MCP tool calls (#58938)
## Why

`CodexThread::call_mcp_tool` returns only the tool result, so computing attribution and creating a cached runtime binding for these calls is unnecessary.

## What changed

Add `McpRuntime::latest_call_tool_without_attribution` and use it for direct thread calls. Validate the call, wait for server startup, and dispatch through the latest connections without capturing an attribution binding.

## Testing

Extend the runtime binding cache test to verify that a successful call without attribution leaves the cached binding empty. Update the test server to return a successful tool result.

GitOrigin-RevId: 898e655d9a0174ddaf71c390757d6fc9a5a61780
2026-11-02 17:55:39 +00:00
Sean Huang 172d8fc593 Verify queued network approval wakeups before polling again (#58937)
## What changed

Strengthen the execution cancellation test to verify that a session approval wakes a queued request before it is polled again. Assert that the request remains unwoken while the session policy commit lock is held, then receives a wakeup after the grant completes.

Wait for the second request to hold a prompt queue reference and install a counting waker on its semaphore. Share `WakeCount` with the existing manual prompt wakeup tests.

GitOrigin-RevId: c559a7c31385000347cd1c7dace25e84d1099db9
2026-11-02 17:54:31 +00:00
ioanbudea-OAI a54329e235 Defer Guardian context trimming in elastic preparation (#58935)
## What changed

- Thread `ContextBudgeting` through synchronous context and image preparation. Elastic mode preserves candidates for later entry capping and allocation; existing reviewer callers continue to use `Fixed`.
- Defer transcript selection, supporting-text caps, and image budget admission in elastic mode while preserving exact planned actions. Mark host framing as protected and distinguish optional user messages from required manual approvals.
- Add `ElasticBudgetConfig` validation requiring section minimums, including fallback policies, to sum to `DEFAULT_MAX_INPUT_TOKENS`.

## Testing

Extend tests for elastic transcript preservation, deferred native tool-call limits, oversized planned actions, image allocation, and section minimum totals above and below the required budget.

GitOrigin-RevId: 46a4605e12e2bab5973097eb1caf5fd99f6640aa
2026-11-02 17:26:49 +00:00
swastik-oai 451787127c Support direct Guardian review of patches invoked through exec_command (#58931)
## Why

Direct Guardian review rejected recorded `exec_command` calls intercepted as `apply_patch`, even though normal execution could review those patches.

## What changed

Share intercepted patch preparation between execution and direct review so Guardian assesses the verified patch and its approval requirement without applying it.

## Testing

Extend the direct patch review scenario to cover `exec_command` heredocs alongside native `apply_patch` calls, asserting identical live and direct review inputs and no file writes after direct approval.

GitOrigin-RevId: af62cf66a3f01c65a65c15cfad3fc9cdd1f2bf19
2026-11-02 17:05:56 +00:00
swastik-oai f04090521d Support permission requests in direct Guardian review (#58903)
## 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
2026-11-02 15:07:54 +00:00
swastik-oai 84dfc209d2 Add native patch support to direct Guardian review (#58899)
## 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
2026-11-02 14:40:54 +00:00
goodman-oai aef7d276a4 Support model catalog overrides for plugin guidance (#58894)
## 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
2026-11-02 14:06:17 +00:00
jif 1e8b536dc7 Add a feature-gated account check for CLI thread resume (#58890)
## 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
2026-11-02 13:51:49 +00:00
Charlie Marsh ba0d0e1f74 Handle steers accepted during the final transcript flush (#58877)
## 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
2026-11-02 12:24:38 +00:00
Won Park 05c08d7655 Accept agent follow-ups through native turn input delivery (#58829)
## 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
2026-11-02 07:27:49 +00:00