Commit Graph
5673 Commits
Author SHA1 Message Date
ioanbudea-OAI a05444bbeb Refresh managed Guardian policy independently of MCP (#62276)
## Why

Managed approval requirements can change while an MCP runtime is still in use.
Later turns need to honor those changes without restarting MCP, while in-flight
MCP actions need to retain the mandatory review requirements of their issuing
turn.

## What changed

- Add `CodexThread::refresh_guardian_policy` to apply managed policy updates to
  an existing thread. MCP configuration refreshes preserve the active Guardian
  policy, including when a policy update lands while MCP configuration is loading.
- Resolve MCP tool and elicitation reviewers against the issuing turn's policy.
  Live requirements can still require Guardian review, and a live policy change
  cannot waive mandatory review captured by the turn.

## Testing

Extend coverage for overlapping Guardian and MCP refreshes and for an existing
MCP runtime that must prompt the user on the next turn after a policy update
allows only the `user` reviewer.

GitOrigin-RevId: 5a1649f917313f6fb152a206bc89986fe6345481
2026-11-18 13:08:51 +00:00
Zahan Malkani 29cb67623c Gate local realtime frame history on paginated storage (#62271)
## Why

Legacy rollout migration rewrites rolled-back history and can disrupt
the realtime stream. Enroll local threads once they use paginated history
so the stream stays intact.

## What changed

- Add the off-by-default `features.realtime_frames_local` flag for
  paginated local threads with a state database. Accept runtime updates
  through the app server and keep threads enrolled once they have a
  persisted canonical session start.
- Add thread-store APIs to recover a realtime session and look up the
  latest session ID from durable history. Route frame completion through
  a store seal so completion acknowledges durable writes.
- Add a local seal for accepted model input that writes source frames
  before the input and lets callers retry an uncertain flush without
  appending the input twice.

## Testing

Cover enrollment for legacy and paginated threads, continued enrollment
after disabling the flag, and retrying a local input seal after a failed
directory sync.

GitOrigin-RevId: 2012feeca3857da90f9b026f077b31a26d15191b
2026-11-18 12:55:14 +00:00
Zahan Malkani 4389a526d5 Derive realtime input receipts from thread history (#62251)
## Why

Accepted handoffs and saved transcript chunks need to appear in realtime
history. Their text can come from the same user message that model history
uses, avoiding a second persisted copy for the receipt.

## What changed

- Reconstruct `turnInputAccepted` and transcript chunk receipts from user
  messages annotated with realtime provenance. Use the stored observation
  time when restoring the realtime clock.
- Replace `sessionEndInputSaved` in the app-server protocol with
  `sessionInputSaved` and a `reason` of `chunk` or `sessionEnd`. Update the
  generated schemas and bindings.

## Testing

Add coverage for reconstructing both receipt types, preserving rollout
order in paginated realtime history, and restoring observation time
across a restart after wall-clock rollback.

GitOrigin-RevId: fcb4e0e539f4e4066726e83fa1e945fb659a2ca8
2026-11-18 11:01:02 +00:00
Zahan Malkani 6d9f0199ed Refactor realtime handoff and history access (#62245)
## What changed

Move realtime text routing into `realtime_handoff` and keep it on the shared start-or-steer path. Extract UTF-8-safe range selection for realtime delegation truncation.

Use `RolloutItem` accessors for realtime timestamps and items in recording, clock restoration, and thread history reads. Pass annotated response items to turn-boundary checks in core and migration rollback so callers can work directly with history envelopes.

GitOrigin-RevId: 3dd37cf91ee5abdca84e87b7d7e304749d9baf04
2026-11-18 09:55:30 +00:00
cazhang-oai ca21fe65d1 Tag Guardian review counts with turn origin (#62225)
## Why

Guardian review counts need a way to distinguish automation-triggered
turns from other turns, including when a subagent requests the review.

## What changed

Add a `turn_origin` tag to the `codex.guardian.review` counter based on
the trigger recorded when the turn started. Recognized automation
triggers map to `automation`, missing or empty triggers map to
`unknown`, and all other values map to `other`. This keeps the set of
metric labels bounded.

## Testing

Cover trigger classification for both allow and deny verdicts and
verify that a later user turn on the same thread is counted separately
from an automation turn in both main and subagent threads.

GitOrigin-RevId: 6a5808798df7d184203cea18e60a94a82d71f036
2026-11-18 08:20:26 +00:00
viyatb-oai bcff988bd1 Resolve Linux sandbox mode once before launching the helper (#62215)
## Why

Managed proxy routes require bubblewrap's network namespace even when
`features.use_legacy_landlock` is enabled. WSL1 compatibility checks and
helper arguments need to agree on the effective mode.

## What changed

Resolve bubblewrap or legacy Landlock once and use that mode for both the
WSL1 check and the `codex-linux-sandbox` arguments. Use Linux sandbox
naming for the shared launcher and CLI code, and preserve the published
analytics category for a missing helper executable.

## Testing

Unit tests exercise the production argument builder, including managed
network context serialization when legacy Landlock is requested. They
also cover which sandbox configurations WSL1 accepts and rejects.

GitOrigin-RevId: 619ab9d3eef965de6bc6cb13ff8a33132018abcf
2026-11-18 07:23:25 +00:00
Ruslan Nigmatullin 86d0e458e3 Prevent duplicate initial context when injection races the first turn (#62206)
## Why

A first user turn and a concurrent raw response-item injection can both
observe that the session has no reference context. Both can then append
the initial prompt prefix and persist a full world-state snapshot.

## What changed

Allow context preparation to run concurrently, then serialize publication
of the initial prefix and its checkpoints. If injection publishes first,
the user turn computes its context updates against the published baseline.
If the user turn publishes first, injection appends only the
caller-provided items.

## Testing

Add an integration test that forces the overlap in both preparation
orders. It checks the first request's world-state updates, verifies that
the follow-up request contains the initial instructions and injected
content once each, and checks that history contains one full snapshot.

GitOrigin-RevId: b66f9c6ccc5d42a2be0e852b4d83b78adbc9e5b2
2026-11-18 06:35:41 +00:00
viyatb-oai a4495dd5c9 Keep sandbox preparation with the command through launch (#62205)
## What changed

- Keep the prepared `SandboxExecRequest` intact in core and let
  `command/exec` borrow the prepared command for streaming. Windows
  restricted-token commands continue through the dedicated sandbox launcher.
- Move runtime read-path selection for exec-server commands and filesystem
  helpers into `SandboxManager`. It derives the paths from the executor's
  binaries and, for managed process launches, finds the generated proxy CA
  bundle in the command environment.

GitOrigin-RevId: 8c9d278496d84589bc4a7b7d0ed08cb1b8e6ba21
2026-11-18 06:22:36 +00:00
viyatb-oai 89feadf3cc Preserve saved sandbox permissions when resuming codex exec (#62194)
## Why

`codex exec resume` sends the current process's sandbox defaults as
overrides. A session started with `:read-only` can therefore resume with
workspace write access when the configured default is `:workspace`.

## What changed

- Restore the saved permission selection, working directory, and workspace
  roots by default. Honor explicit overrides and append directories requested
  with `--add-dir` to the resumed workspace roots.
- Recover built-in read-only permissions from older history without widening
  current read access. Require an explicit permission selection when a saved
  named profile cannot be loaded or saved read-only access cannot be restored.
- Report sandbox permissions and writable roots from the running thread.

## Testing

Add regression coverage for a denied write on the first resumed shell call,
legacy read-only history, explicit permission overrides, and workspace root
preservation with and without `--add-dir`.

GitOrigin-RevId: ed2cf3132f9ce34570661f801c9534a55696e3a5
2026-11-18 05:13:56 +00:00
Adam Perry @ OpenAI 8e1fc8e059 Route turn and response checkpoints through the rollout budget policy (#62190)
## What changed

Move rollout work admission into `RolloutWorkGate` and route compaction
deferral through `ThreadBudgetPolicy`. Use `TurnWork` to check the budget
when accepting a sampling response and to handle checkpoints after stop
hooks, compaction, and sampling errors. Pass sampling charges and response
completion through `ResponseWork`.

The existing budget check still rejects responses after exhaustion. The
new checkpoints leave retry, completion, compaction, and charge handling
behavior unchanged.

GitOrigin-RevId: 7526416b8ce24ca84035494aeb2a23abd8ca3ddc
2026-11-18 04:41:01 +00:00
viyatb-oai 6ee9bc1ba7 Select process sandboxes during launch preparation (#62183)
## Why

Workspace-relative permission rules need to resolve against the execution
host's workspace roots so a grant applies to the intended directory.
Restricted launches also need to check that the host can provide the
required sandbox.

## What changed

- Select the platform sandbox while preparing a launch, using the permission
  profile, network requirements, and Windows sandbox settings.
- Pass workspace roots into policy resolution for local commands and shell
  snapshots. Already-bound command profiles validate their concrete paths
  without resolving Windows launcher hints on hosts that do not use them.
- Share local launch preparation between tool commands and shell snapshots,
  and require a platform sandbox for exec-server launches that request one.

## Testing

Cover network-only restrictions and verify that a
`:workspace_roots` write grant allows writes to the configured subdirectory
under the command's working directory while denying writes to a sibling file
and the corresponding subdirectory under the parent. Exercise the path grant
through both app-server command execution and WebSocket exec-server execution.

GitOrigin-RevId: 492fe7ab8deddf30cfd2e2bdabf28d02d67e00c5
2026-11-18 03:59:37 +00:00
Sean Huang f09fb197f5 Remove Python from MCP permission request hook tests (#62172)
The MCP permission request hook tests depend on a Python interpreter to
run their fixture, so running them requires Python on the host or in
Bazel's test inputs.

Run the Rust test binary as the hook subprocess. It reads the hook
payload from stdin, appends it to the JSON Lines log, and writes the
configured response to stdout. Drop the Python runtime and files from
the core Bazel test dependencies.

GitOrigin-RevId: b9e26384c6b455b0f0936c7009a445d3eabfe2c6
2026-11-18 02:56:01 +00:00
Owen Lin 06789c7618 Preserve web search provider ownership across thread resumes (#62144)
## Why

Search MCP and native web search produce provider-specific references.
Switching providers after a thread resumes can mix those references and
break follow-up calls that use them.

## What changed

Persist whether a thread has used Search MCP, native web search, or
neither. Restore that state from response history, including compacted
history, and use legacy attribution and fallback markers for older
threads. When resumed history lacks a search state or legacy attribution
checkpoint, withhold native fallback unless a legacy marker identifies
native search.

Require every Search MCP call to claim the thread's search provider
before execution, including calls retained by Code Mode.

## Testing

Cover resuming a thread with Search MCP references after discovery
becomes unavailable, both with a saved search state and with imported
history that lacks search checkpoints.

GitOrigin-RevId: 100d21c92b0bdbf737ec36c3474f0bc020df8efc
2026-11-18 00:45:07 +00:00
felixxia-oai 18d82cf7eb Add reusable per-agent reviewer conversations to Guardian v3 (#62134)
## What changed

Give the root agent and subagents with a board identity their own Guardian
reviewer reservation. Each new reviewer thread starts with empty history
and uses the acting agent's live message-board retrieval tools.

Keep one reservation active per agent and retain the conversation only
when the caller marks it reusable. Reuse requires matching reviewer settings
and history-reset version. Dropping a reservation retires its thread.

## Testing

Add an integration test that checks thread reuse after a reusable
disposition, replacement after an unfinished reservation is dropped, and
exclusion of legacy subagents without a board identity.

GitOrigin-RevId: c7bccf4651ad4e04c42d9aee1d9e8de24b5b48df
2026-11-17 23:48:01 +00:00
felixxia-oai c2595ad343 Add live evidence retrieval for Guardian v3 reviewers (#62133)
## Why

A captured board view limits evidence searches to the review's cutoff. A
verdict reviewer needs to be able to check for later evidence, including
restrictions or revocations, before deciding on an action.

## What changed

Add a live `guardian_board` binding that lets reviewers search and read
any Guardian evidence channel, including channels they do not follow.
Search also matches text inside JSON-encoded tool arguments.

Reviewers can list their own subscriptions with `subscribed_channels`
and subscribe or unsubscribe by channel. Subscriptions control delivery
of future evidence. Earlier posts are available through search and read
tools.

Let review setup and prewarming select guidance for the installed
retrieval tools. The live board guidance explains how to find original
user messages and assess their authority. Share the provider-scoped
reviewer header setup through the core Guardian review API.

## Testing

Cover searches beyond the captured cutoff and in unsubscribed channels,
paginated listing of the reviewer's own subscriptions, and channel-only
subscription changes in both live and captured views.

GitOrigin-RevId: c2e1c6c849346cd3d6e316bcf17e44260fcd4c8e
2026-11-17 23:47:24 +00:00
jif e73da8bd1b Preserve base and developer instructions in host child preparation (#62128)
## Why

Hosts preparing a child thread lacked the parent's effective base
instructions and the developer instructions a native subagent would inherit.
Hosts also need the base instruction provenance to preserve custom text
while letting model-owned instructions resolve for the child's model.

## What changed

Include effective base instruction text and provenance in
`PreparedChildContext`. Share developer instruction selection with native
subagent creation so host preparation uses the configured V2 subagent
override when present and falls back to the parent turn's developer
instructions otherwise.

## Testing

Add integration coverage that starts a child on a different model and
checks that custom base instructions persist, model-owned instructions
resolve for the child model, and the V2 override takes precedence over
the parent developer instructions.

GitOrigin-RevId: 0e151e343e58d995c8901a9ba819cb7f60d248f5
2026-11-17 23:31:58 +00:00
Shuo 8dcd56d0cb Add external header auth for existing realtime calls (#62114)
## What changed

Add `RealtimeExistingCallAuth` to `RealtimeAttachmentOptions`, with model-provider authentication as the default. Embedding hosts can explicitly select `ExternalHeaders` for existing calls to use header-based credentials and the host's transport without adding model-provider headers or performing runtime agent registration.

Require an explicit, nonempty sideband URL and header-based authentication for this mode. Destination authorization remains the trusted host's responsibility, and application network policy still applies.

## Testing

Add integration coverage for external-header and model-provider authentication through event delivery, reconnect, and detach. Verify that model-provider credentials are excluded in external-header mode and that invalid authentication, missing URLs, and network policy denials reject the attachment before a WebSocket handshake.

GitOrigin-RevId: 2c915e1cf76a3563f58f751272db1ec50718d925
2026-11-17 22:00:20 +00:00
Abhinav 8fca6ffb92 Support OTel header helpers in local managed requirements (#62110)
## What changed

- Allow system `requirements.toml` and MDM requirements to set `otel.headers_helper` and `otel.headers_helper_refresh_interval_ms`, and expose both fields through the requirements API.
- Require an absolute executable path and run managed helpers directly from their installation directory. Reject helper settings from cloud requirements.
- Restrict managed helper headers to OTLP HTTP exporters with nonempty endpoints configured in the same requirements layer. Replacing the helper or an exporter revokes the previous binding.
- Document deployment and rollback requirements, including client compatibility and pausing affected exports until a failed helper recovers.

## Testing

Add coverage for exporter layer boundaries, cloud policy rejection, relative path rejection, managed helper execution and recovery, missing executable diagnostics, and requirements API output.

GitOrigin-RevId: 271058010c2e3090eb97cb357b70be4dc41b43db
2026-11-17 21:10:09 +00:00
Tom 7457b7268f Preserve trace context during WebSocket startup prewarm (#62103)
## What changed

- Inject the current span's W3C trace headers into WebSocket handshakes.
- Promote `startup_prewarm` to an info span and fall back to the current span when it is disabled, preserving trace context in the spawned task.

## Testing

Add a regression test for `traceparent` and `tracestate` propagation through the handshake, prewarm request, and subsequent turn on the same connection. Verify that prewarm uses the startup trace while the turn uses its own trace, with the prewarm span both enabled and filtered out.

GitOrigin-RevId: 1e196e132a1991206469060ab80a474857fa7909
2026-11-17 19:24:17 +00:00
Adnan Hajar cb64621bf3 Normalize Bedrock Mantle commentary before replay (#62095)
## Why

Bedrock Mantle's reasoning prefix omits empty `annotations` on assistant commentary. Replayed commentary needs to preserve that form to keep the prefix stable.

## What changed

Add a provider hook to normalize completed output items before they enter model history. For Mantle, omit empty `annotations` from assistant commentary text while preserving nonempty annotations, final answers, and Bedrock Runtime output.

## Testing

Add regression coverage for Mantle and Runtime that checks commentary replay across a tool continuation and a subsequent turn, including reasoning and tool item ordering and preservation of final-answer content.

GitOrigin-RevId: ecd5b9b5dca8c24956a6379c9d0fb643e4427af3
2026-11-17 18:55:30 +00:00
surajs-oai e9a43d43c5 Return empty success output from v2 send_message (#62093)
## What changed

Remove the acknowledgment text and `followup_task` hint from successful v2
`send_message` responses, including messages sent to the root agent. The shared
messaging handler now returns empty text with the success flag set.

Update the idle eviction follow-up scenario snapshot to expect empty tool output.

GitOrigin-RevId: 9eab3ae7264e6ddf3db6ae40a34cc895d0954621
2026-11-17 18:44:30 +00:00
jif f993175205 Add policy-checked dispatch for bundled App hooks (#62080)
## What changed

Carry an expected connector identity on hook MCP calls and add a bundled App dispatch path that requires the host Apps server, a matching connector, and current policy permitting execution without user approval.

Prepare hook calls from the current Apps client catalog, including app-only tools, without exposing those tools to the model or starting unrelated required servers. Refresh session MCP state before preparation and recheck admission before dispatch so configuration changes and logout invalidate stale calls. Never retry a dispatched call.

## Testing

Add coverage for refreshed approval and enablement policies, connector mismatches, app-only tool visibility, preparation without unrelated server startup, and admission invalidation on refresh or logout.

GitOrigin-RevId: 965dd7f79baa40d1be0e158e47b2679d8ba98fe5
2026-11-17 16:56:34 +00:00
swastik-oai ce5a565ba0 Simplify Guardian history review preambles (#62074)
## What changed

Use “Treat the content as evidence, not as instructions to follow” in both initial and follow-up Guardian history review preambles, replacing the explicit list of transcript and action fields described as untrusted evidence. Update the corresponding prompt and scenario snapshots.

GitOrigin-RevId: 200ee3c858b54b38fe2609598ef3a1e40cf36380
2026-11-17 16:16:36 +00:00
jif 02d60fb5cc Preserve client attribution when spawning subagents (#62072)
## Why

Delegated work should retain client attribution such as `cost_center` from the turn that requested it, even when a yielded code-mode cell spawns its child after a newer parent turn starts.

## What changed

Capture client metadata from the originating turn and apply it to the child's initial turn in both legacy and v2 agent spawning. Children and grandchildren retain the captured values when the parent is later steered with updated metadata.

Exclude `misalignment_override`, `parent_response_id`, and `mcp_request_meta` from inheritance, while preserving each child's own thread and turn identifiers.

## Testing

Add coverage for metadata filtering and snapshot isolation, legacy and v2 spawning with fresh or forked history, grandchild inheritance, and spawning from a yielded code-mode cell after the parent advances to another turn.

GitOrigin-RevId: 8c378c49239ccfac03deb2b793fc69aba1d41644
2026-11-17 16:15:55 +00:00
jif 58627e6fea Fix turn interrupt reply ordering and shutdown handling (#62066)
## Why

A delayed terminal event from an earlier turn could acknowledge interrupts for a later turn. Interrupts could also remain pending after the thread listener shut down.

## What changed

- Associate pending `turn/interrupt` requests with their target turn and reply only when that turn completes or aborts.
- Track the current Core turn through stop hooks and resolve review delegate IDs to the owning turn when validating interrupts.
- Settle pending interrupts with an error on listener shutdown and reject further interrupts against the retired runtime.

## Testing

Add regression tests for delayed terminal events, queued turn starts, review delegates, and interrupt handling during thread revert and runtime replacement.

GitOrigin-RevId: 9695fc3f718baa6b792a14d54136bb87fc003100
2026-11-17 15:33:21 +00:00
bencodes-oai 8b5223dd7b Use Bazel's Python runtime for MCP permission hook tests (#62061)
## Why

MCP permission hook tests need a Python interpreter on workers without a system Python installation.

## What changed

- Include Bazel's Python interpreter and runtime files in core test dependencies, and allow file labels in `runfile_env`.
- Run permission hook scripts directly with `CARGO_BIN_EXE_python3`, falling back to the platform's Python command when unset.
- Use script bootstrapping so Python launchers start with their declared interpreter on lean workers.

## Testing

Add 15-second timeouts to two permission hook approval tests so they fail if approval waits for a reviewer instead of resolving through the hook.

GitOrigin-RevId: 2877be1411b47806a0eccf2838b521a732e2c98a
2026-11-17 15:10:58 +00:00
rhan-oai 5a4aff8431 Expand the spawn_agent model listing cap to 16 (#62051)
## What changed

Raise the model listing cap from 5 to 16 for `spawn_agent` tool descriptions, context catalogs, and unknown-model errors.

## Testing

Add coverage for both catalog modes to verify the 16-model limit, exclusion of hidden and unsupported models, description truncation in context, and matching model choices in unknown-model errors.

GitOrigin-RevId: 9ca20d4ec5bfd67f953c41dbad2b5f55fe2d5421
2026-11-17 14:20:08 +00:00
viyatb-oai 05ae1b0fdd Centralize sandbox network and shell credential setup (#62050)
## Why

A missing executor proxy launch config can still require managed networking. Only an explicitly disabled executor proxy should suppress that enforcement.

## What changed

- Prepare executor proxy launch settings and enforcement together, preserving the distinction between missing and disabled proxy configurations.
- Bundle sandbox enforcement, the live proxy, and the environment ID in `SandboxNetwork`, retaining the proxy through shell snapshot setup.
- Share shell-startup credential classification and application through `ShellStartupCredentials`, including protected `zsh` snapshots, supported `bash -c` commands, and unmasked fallback handling.

## Testing

Extend the exec-server sandbox preparation test to verify that an explicitly disabled proxy omits both the proxy launch config and managed-network enforcement.

GitOrigin-RevId: e2f3b543680c9184b6557b81de02a61f0a977e32
2026-11-17 13:52:56 +00:00
Sean Huang db9778b73c Distinguish image and tool audio attachment uploads (#62047)
## What changed

Introduce `UploadContent::Image` and `UploadContent::ToolAudio` in `UploadRequest`. Keep image filenames and policy tags on the image variant, and carry tool audio's declared MIME type explicitly instead of encoding its type and MIME metadata in tags.

Update image preparation, image generation, and tool audio callers to use the typed content. Preserve inline bytes for both variants and redact their payloads from debug output. Document that persistent backends must verify the declared audio MIME type against the uploaded bytes.

## Testing

Add coverage for inline tool audio byte preservation and audio debug redaction. Update integration assertions for typed image and audio uploads, and verify that Code Mode does not upload audio when `FileBackedToolAudio` is disabled.

GitOrigin-RevId: 7dbd69922b377aead2dc28d1e5b3938cce6343b7
2026-11-17 13:38:34 +00:00
cassirer-openai c826ca1286 Preserve accepted tool outputs and local resets in rollout traces (#61973)
## Why

Accepted tool outputs may never appear in a later inference request, and request preparation can strip their history IDs. Replay needs to retain these outputs and match them to later snapshots, including trimmed results and outputs with identical wire bodies.

## What changed

- Capture accepted function and custom tool outputs, preserving their acceptance order, identity, and tool provenance during replay.
- Record stripped tool output IDs alongside inference requests so replay can restore identity without changing the captured wire payload. Reuse accepted items and adopt their first model-visible snapshot bodies.
- Record compaction checkpoints for local context-window resets using the selected input and frozen installed history, including goal edits retained during installation.
- Exclude `configuration_update` items from normalized conversation history.

## Testing

Add replay coverage for outputs accepted without subsequent inference, trimmed results, identical outputs with distinct IDs, and acceptance before or after a request snapshot. Extend checkpoint coverage to verify that retained goal edits are captured and later edits do not alter the checkpoint.

GitOrigin-RevId: 70f737782f5000812f389a4e01b9f9690e39549f
2026-11-17 05:35:07 +00:00
Adam Perry @ OpenAI d8d840d32a Capture local attachments before queuing turn input (#61962)
## Why

Queued input can outlive its local attachment files. Reading those files only when rendering a model message can lose media submitted while turn admission is pending.

## What changed

- Introduce `ResolvedUserInput` to carry captured image bytes, audio data URLs, or read errors through session queues and agent input.
- Resolve client attachments on the submitting host before queuing, using a blocking task for local file reads.
- Render messages from captured payloads while preserving original paths and text spans for display, along with image position mappings.

## Testing

Add coverage for rendering and serialization after source files are removed, steered audio retained during pending admission, and local audio errors and display content.

GitOrigin-RevId: 4bbb6bda44167439a8cfdae15d3c476a7b1d336b
2026-11-17 04:08:00 +00:00
bkotsopoulos 65a4450886 Prewarm restored file images on cold resume (#61959)
## Why

Cold resumes warm only base instructions, leaving historical file images out of the WebSocket warm-up.

## What changed

- Add the disabled-by-default `restored_history_prewarm` feature flag.
- Start the WebSocket handshake while history loads, then build the warm-up from restored settings and history when it contains file images.
- Retain the socket and normalized-image cache but discard the image warm-up response ID, so generation resends the full current history and subsequent turns continue from the real response.
- Keep base warm-up for history without file images and defer image preparation to generation when the handshake falls back to HTTP.

## Testing

Add request-history tests and snapshots covering text-only history, interrupted and injected images, resuming with a vision model after image omission, and HTTP fallback without duplicate image resolution.

GitOrigin-RevId: 9a828f44ef0952f7335b5a8c0f7844a069f90d80
2026-11-17 03:48:25 +00:00
rhan-oai 44834c58fa Support turn-scoped exhaustion in host usage accounting (#61958)
## What changed

- Add `UsageAccountingDecision::ExhaustedForTurn` so hosts can fail the current response with `SessionBudgetExceeded` while leaving later turns and peer threads eligible.
- Preserve completed response output and token usage before reporting exhaustion, and track posted charges to avoid accounting twice.
- When steering or mailbox preemption stops a stream, wait for accounting of any completion already observed before starting a follow-up request, and propagate budget errors.

## Testing

Add coverage for preserving output and usage on turn exhaustion, successfully starting a later turn, and reporting turn exhaustion during steering.

GitOrigin-RevId: e673bf30775f27a057fdc39d8429b74ff22121db
2026-11-17 03:28:51 +00:00
Adam Perry @ OpenAI 5b3d2c7fce Extract user input preparation into codex-user-input (#61949)
## What changed

Move local attachment snapshotting and conversion from `UserInput` to model request content out of `codex-protocol` into a dedicated `codex-user-input` crate. Update core, the TUI, and the queue extension to use the new crate, replacing the `ResponseInputItem` conversion methods with `from_user_input`.

Move the associated attachment and message conversion tests alongside the implementation, preserving coverage for image positions, media labels, serialization, and error placeholders.

GitOrigin-RevId: 77d0f94a4cd4c2edc008b9e2e63a989995aab058
2026-11-17 02:43:52 +00:00
Ankush Gupta 0637230e89 Include enclosing tool context in nested Guardian approvals (#61946)
## Why

A nested MCP approval can arrive while its enclosing tool invocation is still running. Follow-up Guardian reviews may use a transcript delta that no longer includes that invocation, leaving out the context in which the nested action was requested.

## What changed

- Add the disabled-by-default `guardian_nested_approval_context` feature to include the host-verified enclosing tool name and arguments in synchronous nested approval requests, while preserving the nested action as the action under review.
- Match the enclosing invocation by call ID and omit ambiguous or unavailable evidence. Exclude Node REPL JavaScript preflight requests.
- Admit enclosing-call context only when it fits the remaining fixed or elastic budget, without displacing ordinary transcript evidence or screenshots.

## Testing

Add MCP elicitation coverage and a request-history snapshot for independent nested reviews and transcript deltas. Add tests for call-ID matching, budget-based omission, and screenshot priority.

GitOrigin-RevId: 9c44a0e8f29f84f84a5322b8362f910f2c91ac55
2026-11-17 02:31:45 +00:00
rhan-oai 34c7cbb454 Allow host-started forks to inherit the root session ID (#61945)
## Why

Host-started forks rejected `InheritedSessionId`, preventing hosts from assigning the root session ID to forked children as they already could for fresh children.

## What changed

Accept `InheritedSessionId` for new or forked threads started directly by the host. Resumed threads continue to use persisted session IDs, and native children continue to use their controller's session ID.

## Testing

Extend hosted-child tests to cover prepared forks, verify that inherited session IDs persist across resume while thread IDs remain distinct, and check that explicit session inheritance is rejected for resumed threads and native children.

GitOrigin-RevId: 90fd24a25e4e927c48395dfae7186bb7fd0e537e
2026-11-17 02:15:09 +00:00
viyatb-oai c656014177 Centralize exec-server launches in WrappedSandboxCommand (#61942)
## What changed

- Move process spawning and Windows token session preparation into `codex-sandboxing`. Keep filesystem overrides, proxy enforcement, and the restricting SID with the prepared command, and reject conversion to a plain command request when a Windows session launcher is required.
- Route shell snapshot capture and replay through the prepared command. Limit script replacement to the submitted shell invocation while preserving its sandbox, environment, and proxy.
- Pass borrowed launch facts to sandbox integrity checks, and distinguish explicitly supplied runtime readable paths from automatic proxy CA bundle discovery.

## Testing

Extend coverage for Windows TEMP permissions and managed proxy routing with empty workspace roots, native launch and prewarm input validation, and proxy availability after the process leader exits while a descendant holds stdout open.

GitOrigin-RevId: fe2bdb9e44f4fb273295fbde66b44bf01f0b7fbc
2026-11-17 02:02:21 +00:00
Chris Dong 1d97869412 Route turn-start client metadata through a dedicated helper (#61941)
## What changed

Add `apply_start_responsesapi_client_metadata` and use it in both turn-start paths. The helper delegates to `update_responsesapi_client_metadata`, preserving existing metadata behavior.

GitOrigin-RevId: 6eb677592492bec5847257ef7162d4002834570d
2026-11-17 02:01:50 +00:00
ningyi-oai cc356fd384 Preserve partial Git metadata when worktree status is slow (#61939)
## Why

Memory requests have a one-second Git metadata deadline. Waiting for all Git lookups together discards an already observed HEAD or remote URL when the worktree scan exceeds that deadline. Shared status scans can also describe a different HEAD from the independent lookup.

## What changed

- Publish HEAD, verified remote URLs, and worktree status incrementally, retaining available metadata at the memory request deadline.
- Read HEAD and change status together using Git porcelain v2, and reject status observations that conflict with an independently observed HEAD.
- Run a positive-only change probe over up to four recently modified root directories during memory extraction preparation. Use a completed probe only when full status is unknown and its HEAD matches the request metadata, without waiting for it before sending the request.

## Testing

Add coverage for partial metadata at the deadline, delayed lookups, stale and unborn HEAD observations, positive-only probes, shared scans, and porcelain parsing. Extend remote credential redaction coverage to partial clones.

GitOrigin-RevId: e7b7c250bfc0e23fb8962fcd5cd5febd7c69e2bd
2026-11-17 01:59:51 +00:00
jif f8e58064fc Preserve remote compaction summaries when interrupting child agents (#61916)
## Why

Child agents configured to interrupt at item boundaries should retain the summary when interrupted during remote compaction. An interrupt during post-turn compaction should also preserve the answer already completed.

## What changed

- Keep sampling interrupt registration active through summary installation, then honor the pending interrupt without running post-compaction hooks.
- Deliver an already completed answer when post-turn compaction is interrupted.
- Keep queued follow-ups for a new turn instead of continuing the interrupted turn.

## Testing

Add a streaming scenario test and context snapshot covering interrupts during mid-turn and post-turn remote compaction. Verify that resumed requests retain the summaries, the completed answer is delivered, and each queued follow-up starts a separate turn.

GitOrigin-RevId: 939eb8b3ed24dbdbff10c9f62226e38a0198fd6f
2026-11-16 23:58:12 +00:00
viyatb-oai c9df641eac Preserve native sandbox executable paths and PTY dispatch names (#61910)
## Why

Sandbox helpers with non-UTF-8 paths can lose their exact executable path when converted into command requests. PTY launches with a custom `argv[0]` can also try to execute the dispatch name instead of the configured program.

## What changed

- Carry native executable paths through sandbox requests, local execution, shell snapshots, and sandbox integrity checks.
- Use native Unix PTY spawning when `argv[0]` differs from the executable, preserving the dispatch name and controlling terminal setup.
- Preserve PTY executable lookup through the child environment's `PATH` and fallback to its home directory when the requested working directory is missing.

## Testing

Add regression coverage for non-UTF-8 sandbox helper paths, PTY dispatch names, child `HOME`/`PATH` lookup, controlling terminals, and exit-code preservation.

GitOrigin-RevId: 6a2af0486220d98195f5d67fde2597e3c4515e11
2026-11-16 23:26:42 +00:00
jif cff061fca9 Add opt-in item-boundary interrupts for subagents (#61909)
## What changed

Add the multi-agent v2 setting `interrupt_at_item_boundary`, disabled by default. When enabled, `interrupt_agent` lets a subagent finish and retain its current output item while cancelling tools immediately. Later output items are discarded, and retained tool calls that have not run receive an aborted result.

Wait for the interrupted turn's terminal event before starting follow-up input, and prevent idle contributors from restarting the interrupted child.

## Testing

Add streaming tests for retaining an assistant message or tool call, discarding later output, and preserving history and follow-up input when the child resumes. Update configuration and interrupt-routing tests.

GitOrigin-RevId: 8b2b9b1383bfb4eefea7369a40012bebc5fff07b
2026-11-16 23:26:07 +00:00
sayan-oai ce7079b506 Add opt-in UTC dates to environment context (#61897)
## What changed

Add the disabled-by-default `utc_environment_date` feature to compute the model-visible environment date in UTC and render it as `<current_date_utc>`. Preserve local dates when the feature is disabled.

Track the date's time basis in environment snapshots so switching to UTC emits an update even when the date is unchanged. Use the matching date tag when reporting an unavailable clock.

## Testing

Extend coverage for UTC midnight rollover, unchanged dates within a day, legacy snapshot refresh, and date removal and recovery. Update local and remote compaction snapshots to exercise the UTC date tag.

GitOrigin-RevId: 6e983d05ca2914629c9f8575e2efe3ed274a2f77
2026-11-16 22:27:05 +00:00
cassirer-openai ef6ce8100a Bound rollout trace capture with configurable storage limits (#61896)
## What changed

- Add `rollout_trace.max_payload_bytes` and `rollout_trace.max_bytes`, defaulting to 64 MiB per body or separated value and 256 MiB per bundle. Root and child threads share the bundle budget.
- Record explicit truncations and omissions when limits are reached, reserve space for later events, and stop at the last complete event if the event log fills.
- Reuse identical prepared-prompt items and store inline images separately from message structure. Preserve exact JSON bytes for complete composite payloads and surviving content and links in partial captures.
- Let reducers handle partial payloads while retaining lifecycle information and reporting `closed_with_partial_payloads` for closed bundles with incomplete captures.

## Testing

Add coverage for payload reuse and byte-exact reconstruction, truncation, compressed bundle budgets, later events after omissions, readable prefixes after event-space exhaustion, and CLI capture-limit configuration and startup failures.

GitOrigin-RevId: be99a68da427414a7a12bf8209f232c1a0bbe545
2026-11-16 22:26:31 +00:00
RJ c0d47262f3 Acknowledge agent messages and clarify how to wake idle recipients (#61894)
## What changed

Return `Message accepted.` from the v2 `send_message` tool. For non-root recipients, also advise using `followup_task` when an idle agent should act immediately. Messages to the root agent receive only the acknowledgment.

## Testing

Assert the acknowledgment when a child messages the root agent, and update the idle-eviction follow-up snapshot to include the guidance for non-root recipients.

GitOrigin-RevId: bb0cf6039d9b693052a1747daa2e75fa25c13522
2026-11-16 22:07:07 +00:00
jif 3257e1b3eb Allow model metadata to control multi-agent tools in code mode (#61854)
## What changed

Add optional `multi_agent_tools_in_code_mode` model metadata to control whether native multi-agent tools follow the model's `tool_mode`. When `true`, expose them according to `Direct`, `CodeMode`, or `CodeModeOnly`; when `false`, keep them direct-only. When omitted, preserve the `multi_agent_v2.non_code_mode_only` runtime setting.

## Testing

Add coverage for metadata overrides and runtime fallback across all three tool modes, plus serialization and deserialization of absent, null, and boolean metadata values. Update the namespace-prefix integration scenario to enable code-mode tools through model metadata.

GitOrigin-RevId: be90f436066226bf9971cbd17f28c396341bb83a
2026-11-16 18:54:05 +00:00
viyatb-oai effad7568c Allow network policy to enable transparent TCP capture (#61851)
## What changed

- Add `transparent_tcp` to network configuration and managed requirements, defaulting to off. When enabled, route outbound TCP from managed Linux sandbox commands through the managed SOCKS5 proxy without requiring an executor startup flag.
- Propagate the setting through local and remote execution, require an enabled SOCKS5 proxy, and check the executor's `networkProxyTransparentTcp` capability before remote launches.
- Refresh the live proxy when switching between permission profiles with different network settings.

## Testing

Add coverage for configuration-driven sandbox capture, rejection of unsupported launch contexts, execution parameter propagation, and live permission profile changes.

GitOrigin-RevId: c4db87056de116f433a128806bef673802f35397
2026-11-16 18:19:16 +00:00
jif e5839cbc59 Preserve aggregate turn diffs across steering (#61820)
## Why

A steer can restart sampling within the same turn. Recreating the diff tracker loses earlier edits, and changing the working directory can change the meaning of relative diff paths.

## What changed

Keep the diff tracker for the lifetime of the turn and retain each environment's first display root. Refresh cached diff headers when new environments are added. Emit the final aggregate `TurnDiff` before `TurnComplete` instead of at sampling completion.

## Testing

Extend regression coverage for steering during the final flush, with and without additional patches and with a changed working directory. Check final diff ordering across continued sampling and header updates when adding an environment.

GitOrigin-RevId: fbd1ebef072d8486a324190c9125fc1446510802
2026-11-16 14:18:24 +00:00
felixxia-oai 0370e34fe8 Route Guardian housekeeping through its dedicated sampler (#61799)
## What changed

Use `HousekeeperSampler` for evidence routing instead of starting a separate review-session thread. The housekeeper now owns a tool-free model conversation, retains completed routing batches, and evicts whole batches under context-window pressure.

Commit sampled history only after all board writes succeed and the evidence cursor advances. Stop the worker after a routing error or an interrupted routing future. Cancel routing when the account changes while allowing accepted appends to finish before shutdown.

## Testing

Extend housekeeping integration coverage for retained history, whole-batch eviction, transient retries, retry exhaustion with `Retry-After`, HTTP fallback, credential renewal, command-token rotation, and shutdown waiting for accepted evidence appends.

GitOrigin-RevId: 316ab1b90529e2a5874e617855d38c41f232872a
2026-11-16 12:05:11 +00:00
felixxia-oai 9544f09e7b Wire Guardian V3 housekeeping into the app server (#61797)
## What changed

- Install Guardian V3 with a local message-board host when the server enables `features.guardianv3.enabled`, independently of thread overrides.
- Clear inherited user, thread, and project instructions from Guardian V3 private threads and skip repository instruction discovery.

## Testing

Add integration coverage for routing the first live message while the actor is still sampling, for both new and resumed threads. Verify that resumed history is skipped, `AGENTS.md` reaches only the actor, and thread overrides cannot enable or disable server-level housekeeping.

GitOrigin-RevId: 3f3ae1be404c9e17b73eea12c95f5a95c96052cf
2026-11-16 12:03:11 +00:00