Commit Graph
6154 Commits
Author SHA1 Message Date
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
jif 0712633d37 Release message-board state before HTTP shutdown returns (#58933)
## Why

Connected legacy MCP sessions and HTTP keep-alive connections can retain message-board state after shutdown. Pending board bindings also need cancellation before they can dispatch a tool call.

## What changed

Explicitly close MCP sessions after HTTP drains and track binding factories and handlers until they release their state. Cancel pending bindings during shutdown while allowing already-dispatched board operations to finish. Clarify that `LocalServer::shutdown` waits for cleanup, while dropping the server initiates it.

## Testing

Add regression coverage for shutdown with a connected legacy client, a paused board binding, and an unauthenticated keep-alive connection. Assert that shutdown releases the board host before returning.

GitOrigin-RevId: 7fbc9415e579a21f0c0fcf7bbb7db239b3aea886
2026-11-02 17:16:07 +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
jif 8806313db4 Scope local history discovery to the current ChatGPT account (#58918)
## What changed

- Add `currentAccountOnly` to `thread/list` and `thread/search`, defaulting to `false`, and enable it for TUI history discovery, resume pickers, and task mentions.
- Mark newly created threads as account-scoped and require each recorded creator user or account ID to match the current login. Older threads and threads without creator IDs remain shared; API-key logins continue to see all local history.
- Preserve account scope through resume and revert, including fallback to original rollout metadata when an older binary drops the marker. Forks receive new-thread scope.
- Skip unreadable rollout headers in scoped discovery and filter search candidates before reading snippets. Direct access by thread ID remains available.

## Testing

Add coverage for account matching, shared legacy history, list page refilling, search pagination, API-key visibility, and scope preservation across reverts. Extend rollout lookup coverage to compressed active and archived files.

GitOrigin-RevId: aa374f5e69165be5a71c0716ded1b105f5fb51e0
2026-11-02 16:00:20 +00:00
jif 6c4fa86838 Add an in-memory launcher for the message-board MCP server (#58909)
## What changed

Expose `launch_in_memory()` and `LocalServer` to run a loopback HTTP endpoint with generated bearer credentials. Runners register a shared in-memory board per session through `add_board(session_id, host)`, using `MessageBoardHost` for membership, clocks, and notifications without a SQLite registry.

The handle exposes the endpoint and authorization header for MCP configuration, including plugin endpoint overrides. Dropping it cancels HTTP and MCP sessions; `shutdown().await` also waits for completion.

## Testing

Extend the parent/child HTTP integration scenario to cover the in-memory launcher, plugin endpoint overrides, host-provided timestamps, authentication and invalid identity rejection, and operation without creating a SQLite board database.

GitOrigin-RevId: e1cae295724a35f4eded290ba8a4e19926b98c13
2026-11-02 15:29:45 +00:00
jif 517960e0ed Package the message board MCP connection as a plugin (#58908)
## What changed

Add a `message-board` plugin with connection metadata for the HTTP MCP server. It defaults to `http://127.0.0.1:7777/mcp`, uses `CODEX_MESSAGE_BOARD_TOKEN` for bearer authentication, and marks the server as required.

Document installation and endpoint overrides through `mcp_servers.codex_message_board`. Installing the plugin does not start the server.

## Testing

Extend the HTTP board integration scenario to cover both direct configuration and plugin installation, verifying that a child can post a decision and its restarted parent can discover the same board and read it. Add a plugin context snapshot and include the plugin resources in Bazel test data.

GitOrigin-RevId: d6cf797caaa4dbdcd45114c2ad0a6bd695cf056f
2026-11-02 15:28:37 +00:00
jif 18c6dbe52b Add a standalone HTTP MCP server for the agent message board (#58904)
## What changed

- Add `codex-message-board-mcp` to serve discussion tools at `/mcp` through ordinary MCP configuration, backed by the existing SQLite board and a read-only Codex registry.
- Require bearer authentication and validate `threadId` and `sessionId` metadata against persisted agent membership. Support additional allowed HTTP hosts with `--allowed-host`.
- Expose a reusable `serve_http` library entry point and scope retry deduplication to the caller within an MCP session.

## Testing

Add integration coverage for a child posting and its restarted parent reading the persisted board, including reads while a database writer lock is held. Cover invalid tokens, disallowed hosts, missing caller metadata, invalid membership, and startup without an existing registry.

GitOrigin-RevId: 5e3d71eaaf120169e2585acd0b5f84df1b402f00
2026-11-02 15:09:22 +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
cassirer-openai 7656a23b8d Preserve incomplete response output in failed inference traces (#58456)
## Why

When a response fails with incomplete output, attempted tool calls can appear only in the terminal response payload. Failed inference traces previously omitted those items, losing evidence of the attempted call.

## What changed

Retain output items marked `incomplete` on `ResponseIncompleteError` and include recognized items in failed inference traces, deduplicating by item ID. Keep these items out of streamed output, tool dispatch, and the continuation cache, and omit their payloads from the error's debug representation.

## Testing

Add tests for retaining only incomplete output from terminal responses and recording attempted calls in failed traces without streaming them or creating tool calls. Cover unknown response item types being skipped.

GitOrigin-RevId: 594f6a37a5af543694f19fcffe0c164cb2addb36
2026-10-30 23:55:47 +00:00
ioanbudea-OAI 26cc286314 Add elastic budgeting for Guardian context preparation (#58454)
## What changed

Introduce `ContextBudgeting::Elastic` to prepare captured root conversation and Node REPL evidence without the fixed per-section request caps. Elastic preparation preserves message text and candidates for later allocation while retaining storage omission notices and legacy source deduplication.

Keep `ContextBudgeting::Fixed` as the default and use it at existing call sites.

## Testing

Add tests covering elastic root message preservation and legacy source deduplication, plus REPL text, images, and omission counts in text-only and multimodal modes.

GitOrigin-RevId: ce4fae9d725694456525a413fb511166df6f5e2c
2026-10-30 23:54:38 +00:00
goodman-oai 22fbf8de8e Preserve Apps usage instructions in model catalog messages (#58441)
## What changed

Add optional `ModelMessages.apps` and `AppsMessages.usage_instructions` fields to carry model catalog wording without runtime interpretation. Missing or null values become `None`, and strings retain their exact contents, including empty strings, whitespace, and template-like text.

## Testing

Add serialization coverage for nullable and literal Apps values, and extend existing tests to verify Apps messages survive model response round trips and base instruction overrides.

GitOrigin-RevId: 49b516656255e07b91f8f4679e2acb8e1b03f9e1
2026-10-30 22:02:26 +00:00
Hung 2546265e3e Add audio file references with explicit runtime rejection (#58430)
## What changed

- Allow audio inputs to carry uploaded file references via `fileId` in the app-server API and `file_id` in model content, preserving existing inline audio shapes and Python class names.
- Preserve mixed inline and file-backed audio ordering through history reconstruction and migration, and budget file-backed audio conservatively when duration is unknown.
- Keep uploaded audio disabled at runtime: reject it before inference or raw history injection, preserve accompanying text, and prevent rejected attachments from reaching follow-up or resumed requests.

## Testing

Add coverage for wire-format round trips, SDK compatibility, mixed audio history ordering, and rejection during turn start, steering, task completion, and raw injection.

GitOrigin-RevId: 70895c47a2494c0c9936348ad1250eb1b7b892a6
2026-10-30 20:53:25 +00:00
Matthew Zeng b9858217d8 Support app settings in plugin configuration (#58428)
## What changed

Allow connector-wide app settings under `plugins.<plugin>.apps.<connector>` for plugins enabled by configuration. Merge these settings field by field, giving earlier plugin names precedence and applying explicit top-level `apps` fields last. Ignore nested `_default` settings.

Expose the merged app settings and their field origins through the config API. Keep app policy changes from invalidating the loaded-plugin cache.

## Testing

Add coverage for plugin enablement, merge precedence, field origins, config API output, cache reuse, and disabling an app through plugin configuration during explicit plugin mentions.

GitOrigin-RevId: a275319815915dc618ee606b10e0844248dbccb5
2026-10-30 20:39:47 +00:00
swastik-oai 8801b9a8a6 Simplify recorded exec command review (#58418)
## What changed

Inline validation and command preparation in `review_tool_call`, removing the
`RecordedExecCall` helper. Use the tool invocation's call ID for approval actions
and return `GuardianReviewResult` directly from the review future, including when
no assessment is required.

GitOrigin-RevId: aafd01f640d46dc542a649bc5b31b3cfba7bedb8
2026-10-30 19:26:26 +00:00
rhan-oai 6df44f08dd Expose non-consuming input activity waits to hosts (#58411)
## Why

Host-owned tools need to wait for agent messages or steering input with the same behavior as native `wait_agent`, including when native multi-agent support is disabled.

## What changed

- Add `CodexThread::wait_for_input_activity` and export `InputWaitOutcome` through core and core-api, sharing the wait implementation with `wait_agent`.
- Distinguish notifying agent messages from steering input, with steering taking precedence when both are pending. Passive response items do not wake waits.
- Observe input without consuming it. Waits remain active after the original turn ends, support independent observers, and can be cancelled by dropping the future.

## Testing

Add coverage for pending and incoming input, agent-message classification, cancellation, independent observers, timeouts, and input arriving after the original turn completes or is interrupted.

GitOrigin-RevId: d0c0bd776c3b6fd4ba3021603d87eaaf1d93976f
2026-10-30 18:34:10 +00:00
Alex Daley 0e31c29e25 Enable deferred tool world state by default (#58410)
## What changed

Mark `deferred_tool_world_state` as stable and enable it by default. Deferred tool namespaces now appear in the developer `<tools>` context instead of the `tool_search` description. Explicitly disabling the feature preserves discovery metadata in the search description.

## Testing

Update tool discovery tests to cover the default behavior and explicit opt-out, and refresh request snapshots for the deferred namespace context.

GitOrigin-RevId: d58e369ea22754cee593c26a5ca011e41ba56e79
2026-10-30 18:33:14 +00:00
rhan-oai 615be37b2b Add host-inherited thread instructions and execution policies (#58406)
## What changed

- Add `StartThreadOptions` setters for captured thread instructions and execution policy snapshots. Captured instructions replace the live thread provider; empty text clears the thread contribution. Hosts must supply inherited settings again on cold resume.
- Install inherited policies in independent managers only when the destination ignores user and project rules, has no additional policy files, and has matching managed requirements. Preserve managed command restrictions, host executable mappings, and network denials, including restrictions that absolute-path rules could otherwise bypass.
- Reject inherited startup settings for isolated sessions and reject combining local and transported execution policies.

## Testing

Add coverage for policy inheritance through children and grandchildren, incompatible or weakened policies, absolute-path amendments, and captured instructions overriding or clearing live instructions on startup and resume. An execution integration test checks that an inherited allow rule runs without approval while a managed denial still blocks execution.

GitOrigin-RevId: c1147992fe5bb5ba4bcf981c08fcfcb6f6bca8a1
2026-10-30 18:20:57 +00:00
chetan-oai 8cb81f6490 Add an option to suppress incremental model change announcements (#58405)
## What changed

Add the default-off `suppress_model_change_announcements` feature flag. When enabled, incremental context updates omit the model ID announcement after a model switch while still delivering changed base instructions and tool definitions.

Advance the model snapshot even when a switch emits no context update, so subsequent turns recognize the current model.

## Testing

Add coverage for omitted and explicit flag values, snapshot advancement without repeated updates, and request history across model switches, repeated turns, and compaction with announcements suppressed.

GitOrigin-RevId: 89c70f1e9d7981fd945fb8e41b1f98492717a07e
2026-10-30 18:19:38 +00:00
Dmitriy Kovalenko 7a030b9769 Fix context token estimates for responses without usable usage (#58404)
## Why

Retained output from failed responses or responses without usage data can be omitted from context token estimates, delaying automatic compaction even as reasoning accumulates.

## What changed

Track the history boundary covered by the last usable usage report and estimate all items added after it. Spending-only updates preserve that boundary, while successful usage reports cover the request input even when the response contains no output items. Avoid counting unreported reasoning twice and align recomputed context counts and remote compaction estimates with the boundary.

## Testing

Add unit coverage for initial input, empty responses, spending-only updates, and reasoning accounting. Add regression coverage verifying that accumulated unreported reasoning triggers compaction for incomplete responses with or without usage and completed responses without usage.

GitOrigin-RevId: 80c0b800c7236ff40ae53fdd18320e0d06e026ab
2026-10-30 18:12:39 +00:00
rhan-oai 5be57bedd0 Add scoped host metadata hooks for MCP tool requests (#58395)
## What changed

Expose `McpToolRequestMetaHook` and `McpToolRequestMetaProvider` so hosts can supply a per-invocation `_meta` value using the thread, turn, and call IDs. Apply the hook before dispatch only when the tool, server name, source, and full transport configuration match the selected local MCP registration.

Reject metadata key collisions and propagate provider errors to the tool caller without dispatching the call.

## Testing

Add integration coverage for matching registrations, different contributors and routing headers, unrelated tools and servers, provider failures, and existing metadata keys.

GitOrigin-RevId: 2bf51c375a04617d61b24ca1cbbcaa810fb06720
2026-10-30 17:32:09 +00:00
rhan-oai cbe16d525c Expose parent context for host-managed child startup (#58390)
## What changed

Replace `PreparedThreadSpawn` with `PreparedChildContext`. `CodexThread::prepare_child` now captures parent inputs from a live tool invocation without requiring a child request. Hosts choose the child's name, role, and history, bind destination services, and apply child settings.

Expose captured instructions, environments, permissions, approval settings, disabled plugins, current inheritable dynamic tools, and an execution-policy snapshot with its original managed requirements. Retain those requirements across MCP configuration refreshes so hosts can assess policy-source compatibility.

Remove `ThreadManager::create_prepared_child`; `CodexThread::create_child` handles reserved child startup on the parent's manager with invocation-bound cancellation and cleanup.

## Testing

Add coverage for execution-policy snapshots and managed requirements after MCP refresh. Update child-spawn tests to verify captured instructions and permissions, current dynamic-tool declarations, and fresh versus forked history.

GitOrigin-RevId: f15b595b44997fa70cd0c9be0e92f470e1f333e1
2026-10-30 17:08:41 +00:00
rhan-oai 483d98a441 Scope agent MCP metadata to a host-selected plugin registration (#58378)
## What changed

Add `AgentMcpMetadataRecipient` as a thread extension that lets the host select which MCP plugin registration receives `x-codex-root-turn-id` and `x-codex-cyber-access-program` in tool-call metadata.

Require an exact match on the plugin ID, installed root, server name, and transport configuration in the `local` MCP environment. Omit both keys without host opt-in or when the registration does not match, including same-name user overrides. Send JSON null for unset values on matching registrations.

## Testing

Add unit tests for registration matching and integration coverage for host opt-in, same-name user overrides, and an unset access program.

GitOrigin-RevId: eaa44e17b29aa0bdec6f6ed9faa86b8fc931faad
2026-10-30 16:00:24 +00:00
swastik-oai a4b4082b5f Apply PreToolUse hooks before direct Guardian review policy checks (#58368)
## Why

Direct Guardian review checked recorded `exec_command` calls without applying `PreToolUse` hooks, so approval decisions could miss hook rewrites or denials.

## What changed

Run the shared `PreToolUse` hook handling before evaluating approval requirements. Use the rewritten arguments for policy checks and the Guardian approval request, and return an error when a hook blocks the call, even if policy would otherwise skip review.

## Testing

Add regression tests covering rewritten commands that require approval and hook denials for policy-allowed commands. Verify the rewritten approval request, hook events and recorded denial context, and that reviewed commands are not executed.

GitOrigin-RevId: 3ec7700f695e422ac59c903c285acc0cf633b915
2026-10-30 15:28:20 +00:00
ioanbudea-OAI dc40446064 Preserve model metadata origin through runtime resolution (#58361)
## What changed

Return `CatalogModel` from model lookups, keeping metadata together with its `Bundled`, `Provider`, `ExplicitConfig`, or `Synthetic` origin through config overrides and runtime snapshots. Replace `used_fallback_model_metadata` checks with explicit `Synthetic` origin checks.

Share the underlying `Arc<ModelInfo>` with extension stores and use copy-on-write for metadata changes. Keep origin tracking outside serialized model metadata.

## Testing

Extend coverage for origin retention across cache reloads, namespaced model lookups, catalog fallback, and config overrides. Verify that step snapshots and extension stores share the same model metadata allocation.

GitOrigin-RevId: bb6130c94a7a795aa168ee24664a1dd453579fba
2026-10-30 15:11:02 +00:00
swastik-oai 85d042c71a Extract pre-tool-use hook handling into a helper (#58357)
## What changed

Move hook execution and input updates into `apply_pre_tool_use`, with distinct errors for blocked calls, failures, and cancellation. Preserve dispatch error reporting and clear the serving assessment when a hook changes the invocation payload.

GitOrigin-RevId: d3c5b37692970b739393cb0c998f6cff0ff39af2
2026-10-30 15:02:16 +00:00
bkotsopoulos 9630b2e019 Allow Apps catalog discovery before the initial tool inventory completes (#58352)
## Why

Plugin and skill catalog reads currently wait for the Apps server's initial `tools/list` to finish, even after its MCP transport is initialized.

## What changed

Add the disabled-by-default `features.apps_early_resource_discovery` flag. When enabled, host-owned Apps requests for `mcp/plugin` and `mcp/skill` resources can use the initialized transport while the initial tool inventory is pending. Server readiness still waits for the inventory to complete, and retries use normal readiness.

Bound early client acquisition by the configured startup timeout, propagate startup failures and cancellation, and reject pages if the connection, authentication scope, or resource cache generation changes during discovery.

## Testing

Add coverage for gated discovery, concurrent plugin and skill reads, startup timeouts and failures, cancellation, cache invalidation, and account switches. Verify that early discovery reuses a single handshake and tool inventory, including with the newer MCP protocol and connection sharing enabled.

GitOrigin-RevId: 955b1f6d43b733bdf9763c1caf2ce6913c686c81
2026-10-30 14:47:56 +00:00
Charlie Marsh 80f469ce8a Serialize manual network approval prompts per endpoint (#58351)
## Why

Concurrent executions accessing the same endpoint can produce duplicate network approval prompts before a session decision is recorded.

## What changed

- Queue manual prompts by environment, host, protocol, and port while keeping execution decisions separate.
- After a one-time approval or denial, let the next execution prompt. Reuse committed session grants and deny rules without another prompt.
- Keep tool results paused while requests are queued and attribute the wait to the triggering tool call.

## Testing

Extend coverage for concurrent requests, one-time and session decisions, independent ports, queued cancellation and timing, and isolation between local and remote environments.

GitOrigin-RevId: ebf580dddc39a9a9dc3b0d1acfa21438fbc6e100
2026-10-30 14:40:59 +00:00
Charlie Marsh 4969675f01 Resolve network approval prompts when their requests end (#58350)
## Why

A network request can disappear while its approval prompt is still pending. Leaving that prompt active allows a late cancellation to interrupt the turn even though the request no longer needs approval.

## What changed

- Track network prompt lifetimes in core and notify the app server when a prompt is resolved or withdrawn.
- Cancel the corresponding server request, emit `serverRequest/resolved`, and release its permission guard. Resolve outstanding network prompts during thread shutdown as well.
- Claim a live pending approval and validate its originating turn before applying a decision, so stale responses cannot interrupt a turn or persist policy changes.
- Distinguish network approvals that require the originating turn from proxy approvals that can be serviced by a later active turn.

## Testing

Extend regression coverage for disconnected network requests, late cancellation responses, turn completion during review, shutdown cleanup, mismatched turn IDs, and command approvals from background code running during a later turn.

GitOrigin-RevId: 78f656d92607ec21ddd0c5d781ed0947588cb2eb
2026-10-30 14:40:32 +00:00
guinness-oai c9750d7f50 Preserve realtime V3 transcripts in conversation history (#58221)
## Why

Long realtime conversations could lose speech when active transcripts and handoff transcript fields were truncated.

## What changed

- Record completed V3 transcript chunks in model and client history once the active transcript exceeds 4 KiB, without triggering inference.
- Keep unfinished utterances pending to preserve conversation order, and persist completed chunks before subsequent handoffs.
- Preserve full V3 transcript text at handoff and session-end tail flush, and avoid adding handoff input already recorded in transcript history.

## Testing

Add integration coverage for long transcripts, XML escaping, recording before handoff without inference, repeated handoff input, and both session-end tail flush settings.

GitOrigin-RevId: 62218b811809c4cf5b16fb0247a335eb474f9ab9
2026-10-30 02:43:02 +00:00
alexsong-oai cc2f80d515 Add file-backed storage for gateway OAuth credentials (#58219)
## What changed

Allow gateway OAuth configuration to select `credentials_store = "file"` to persist credentials in plaintext at `$CODEX_HOME/secrets/gateway_oauth.json`. Keep `keyring` as the default.

Read, update, and delete file-backed credentials by credential ID, using atomic writes and the existing cross-process lock. Preserve the serialized provider identity when using the default store.

## Testing

Add an app-server test that completes gateway OAuth login with file storage, verifies Unix file permissions are `0600`, and checks that login remains successful after a server restart.

GitOrigin-RevId: dc1d17922bd80bf65034cbc5aa3d97959e962dcc
2026-10-30 02:28:51 +00:00
Dmitriy Kovalenko b91cedc080 Centralize TOML config deserialization (#58198)
## What changed

- Add a non-inlined `TryFrom<toml::Value>` implementation for `ConfigToml` and route callers through it to share the generated deserializer in `codex-config`.
- Reuse the ignored-field deserialization helper for strict validation, returning path-aware errors while preserving existing fallbacks for CLI validation and ignored-config warnings.

GitOrigin-RevId: 0208b314416ad4d3d7fbf3a30560a0c8c4035abd
2026-10-30 00:36:00 +00:00
Dmitriy Kovalenko 98f79517ab Preserve remote read compatibility with older executors (#58195)
## Why

Older executors sandbox reads whenever a policy is supplied, even when the policy allows unrestricted reads. This can interfere with loading skills across executor versions.

## What changed

- Omit sandbox contexts from remote read operations when reads are unrestricted and explicit permission paths are valid for the target path convention. Retain contexts that require executor-side path validation.
- Check remote `windows_mxc` support before sending MXC sandbox contexts for reads or capability discovery, returning an update-executor error when unsupported.

## Testing

Add coverage for permission path validation across read operations, unsupported MXC requests, and skill loading over Noise with mismatched app and executor versions, including selected skill roots with capability discovery disabled.

GitOrigin-RevId: 4a2a7ccaa2ba4daac657bd84aea603404452be45
2026-10-29 23:56:17 +00:00
jamy-OAI 708e3e2c70 Allow providers to opt into Cyber access programs (#58190)
## Why

Cyber access program selection was restricted to the `openai` provider ID, preventing custom providers from accepting explicit program selections.

## What changed

- Add `capabilities.cyber_access_programs` to provider configuration and preserve it through remote thread configuration. Default to enabled for `openai` and disabled for other provider IDs, with explicit overrides taking precedence.
- Use the capability when forwarding `access_programs.cyber` and determining Daybreak availability in exec and the TUI. Refresh TUI eligibility when the server changes the selected provider.
- Preserve authentication, API-key feature gates, and catalog access checks; the capability does not grant program access.

## Testing

Add coverage for capability defaults and overrides, configuration round trips, custom-provider requests with both authentication types, API-key feature gating, compaction, WebSocket response reuse, exec selection, and TUI provider changes.

GitOrigin-RevId: 579f7c33c9e857ff5fedd08311aa8e3129740c1f
2026-10-29 23:24:52 +00:00
sayan-oai 94d89c74d6 Use turn-scoped permissions for standalone web search (#58189)
## Why

Standalone web search must use the same permission mode as hosted search. Permission changes during a turn should take effect on the next turn, without changing web access for searches in the active turn.

## What changed

Pass the turn's `WebSearchMode` to the web search extension and use it to determine tool availability and `external_web_access`, while retaining provider support checks and thread-level search settings.

## Testing

Add an app-server regression test that switches from cached search to Full Access while a turn is paused. Searches before and after the update keep `external_web_access` disabled in that turn; the next turn enables it.

GitOrigin-RevId: 9e3b8598f2e491388b7e7d4840c849155ae95e88
2026-10-29 23:24:28 +00:00
viyatb-oai dfcb5b5994 Support managed network requirements under permissions.network (#58182)
## What changed

Allow shared network constraints in `[permissions.network]` in `requirements.toml`, alongside `[permissions.filesystem]`. Apply them throughout configuration loading, network approvals, Windows sandbox policy validation, and `configRequirements/read`, and show their source in `/debug-config`.

Retain `[network_proxy]` and `[experimental_network]`, but reject mixing either with `[permissions.network]`, even across requirements layers. Preserve independent network and filesystem precedence and source attribution, and report unknown nested network fields.

Reserve `network` as a managed requirements table name and reject empty or profile-shaped tables with migration guidance. Profiles named `network` remain valid in `config.toml`. Document that policy publishers must keep using `[experimental_network]` until all readers support the chosen replacement.

## Testing

Add coverage for layered constraints and source attribution, conflicting spellings, profile-name migration errors, unknown-field diagnostics, and cloud validation. Extend API, project discovery, network approval, and Windows policy tests to cover `[permissions.network]`, and verify managed proxy settings remain independent of disabled feature configuration.

GitOrigin-RevId: 994dfca9abf5a7aea914276c0ded8b40d7ed0372
2026-10-29 22:36:06 +00:00