Commit Graph
13974 Commits
Author SHA1 Message Date
Charlie Marsh 548dd628df Specialize OpenTelemetry providers for HTTP traces and metrics (#62854)
## Why

The code-mode host exports traces over OTLP/HTTP, and the elevated Windows
Filtering Platform setup helper exports Statsig metrics. Both used the
general-purpose provider, which made exporter builders for unused signals
and transports reachable from those binaries.

## What changed

Add `OtelProvider::try_new_http_traces` for the code-mode host and
`OtelProvider::try_new_http_metrics` for the Windows setup helper. Select
exporter builders at compile time so each constructor reaches only the
builders it needs. Both constructors reject unsupported signals and gRPC
configuration. The metrics constructor also accepts Statsig.

## Testing

Add unit tests for unsupported signals and gRPC configuration. Exercise
the specialized constructors in the HTTP loopback tests for trace delivery
on a current-thread Tokio runtime and cumulative metrics export.

GitOrigin-RevId: 875916791f0176839764c51b5ab289d5dc45a4d2
2026-11-20 22:39:52 +00:00
Charlie Marsh 63598243af Limit guardian response resampling to one retry (#62852)
## Why

When the retried response also meets the guardian's resampling criteria,
it can trigger another model request and keep the turn from finishing.

## What changed

Consume the original prompt when scheduling the retry. The second
verdict stays buffered until completion and is replayed after usage
accounting, even if it also meets the resampling criteria. Usage from
the discarded first response still counts toward spending.

GitOrigin-RevId: f8ded8f31bd7d9e440c0c92a92a80480acec61d2
2026-11-20 22:24:30 +00:00
Dmitriy Kovalenko 4c153c26c0 Reduce allocations when preparing tool schemas and catalogs (#62849)
## Why

Tool schema budget checks cloned the schema and allocated a JSON buffer
just to measure its size. Building a Responses Lite catalog also cloned
tool definitions before serializing them.

## What changed

- Deserialize schemas from borrowed JSON during compaction, count
  serialized bytes without allocating a buffer, and reuse the parsed
  schema when it fits the budget.
- Serialize borrowed tool specs and namespace members directly, and pass
  filtered specs as an iterator. Preserve the serialized namespace field
  order because the bytes contribute to the `additional_tools` item ID.

## Testing

- Compare the exact serialized Responses Lite catalog against the
  expected namespace layout.
- Add a `tool_catalog` benchmark for connector schema preparation and
  Responses Lite catalog encoding with 1 and 64 tool specs.

GitOrigin-RevId: 6bd03a12fcedd4abfa8c3a03f298243483e98c63
2026-11-20 22:10:45 +00:00
swastik-oai 9735367e18 Return an assessment for explicit Guardian reviews (#62846)
## Why

An explicit `thread/guardianReview` request could return a null assessment when live execution would skip approval, leaving callers without a verdict on the recorded action.

## What changed

Require `assessment` on every successful `thread/guardianReview` response. Review eligible recorded calls even when a command is allowlisted, an MCP tool is configured for automatic approval or has a remembered approval, or the policy disables permission requests. The review runs without executing the call or granting permissions.

Include the MCP server's owning environment permissions in the review context, matching live review.

## Testing

Cover allowlisted commands, permission requests with prompting disabled, and automatically approved MCP tools. Compare live and recorded MCP review input for a server whose owning environment has denied paths.

GitOrigin-RevId: 54689dc043d77f940e10d29842308340f6937980
2026-11-20 21:58:11 +00:00
rhan-oai 2b5111917c Tag all multi-agent role instructions consistently (#62842)
## Why

Only catalog role instructions carried the `<multi_agent_role>` tag,
so the same guidance appeared in different formats depending on its source.

## What changed

Render bundled, catalog, and configured root and subagent guidance as
`multi_agent.role_instructions` developer messages. Wrap the guidance in
`<multi_agent_role>` tags and preserve configured text that's already tagged.
Match untagged parent guidance by its body when filtering forked history.

## Testing

Update prompt and session assertions for tagged role instructions, and keep
the cold-resume test exercising a rollout with legacy untagged guidance.

GitOrigin-RevId: 60c55b5d7227811b92bd1bf125f1cd3a965720fd
2026-11-20 21:42:17 +00:00
Charlie Marsh 5bee962f5e Reuse one syntax highlighter when building TUI Markdown styles (#62840)
## Why

Building Markdown styles clones the active syntax theme and constructs a new
highlighter for each foreground lookup.

## What changed

Borrow the active theme and use one highlighter for all foreground lookups
in `MarkdownStyles`. Preserve the readability adjustment for text styles
and the accent-color fallback for inline code.

GitOrigin-RevId: 8ddfad7e61e2dc7968398ff3bdecd3b389c1bb07
2026-11-20 21:29:06 +00:00
mpc-oai df6064096a Load managed cloud config for plugin add and list (#62837)
## Why

`codex plugin add` and `codex plugin list` loaded configuration without
the managed cloud configuration layer, so plugin discovery and
installation could miss settings supplied by that layer.

## What changed

Use the shared cloud-aware configuration builder for add and list,
passing through CLI overrides. Keep `codex plugin remove` on the local
configuration loader and use the loaded configuration's Codex home
for all three commands.

GitOrigin-RevId: 5ebe94de30e553c57ae6296a2ddb91792260a61f
2026-11-20 21:08:57 +00:00
tigrantsat-openai 1c0c806028 Record MCP tool call outcomes in traces (#62833)
## Why

A successful JSON-RPC exchange can still return a failed tool result.
MCP error metrics count that failure, but the trace span can lack an
error status. Dropped calls can also leave spans without an outcome.

## What changed

Record `codex.mcp.call.outcome` on `mcp.tools.call` spans and mark
failures with OpenTelemetry error status using the same classification
as the metrics. Record `interrupted` when the call future is dropped
before completion, including before its first poll.

Capture the numeric JSON-RPC error code in `rpc.jsonrpc.error_code`
when available, leaving server error messages and data out of the span.

## Testing

Extend in-memory telemetry tests to check that spans and metrics agree
on error classification and that span attributes omit sensitive test
values. Cover success and cancellation before the first poll and while
the call is pending.

GitOrigin-RevId: 57fcdc36f19cfc2f227c1ec964a932f3cf7eaa04
2026-11-20 20:38:01 +00:00
Ryan Taylor a1afa12273 Let required hooks block continuation on failure (#62831)
## Why

A required hook check can fail to run or return a usable result. Continuing
after that failure can let an action proceed without a completed check.

## What changed

Add per-handler `onFailure` for command and MCP tool hooks. The default
`continue` preserves existing behavior. On supported synchronous hooks,
`block` applies the event's blocking behavior and reports the reason while
preserving failure diagnostics. For example, a failed `PreToolUse` check
prevents the tool from running, while a failed `PostToolUse` check withholds
the result of a tool that already ran.

Expose the policy in the app-server's `configRequirements/read` response.

## Testing

Add tests for command and MCP failures under both policies, and scenario
coverage for blocked tool execution, withheld results, and completion after
a `Stop` hook recovers.

GitOrigin-RevId: 20d6ebda0094382fe052bbf34338edb994cc7bd3
2026-11-20 20:24:34 +00:00
ioanbudea-OAI 0a0b1021f0 Apply elastic Guardian budgets to retained user and sender evidence (#62829)
## Why

Fixed retention limits could discard long user instructions or leave
older sender messages out of Guardian review even when the configured
elastic budget had room for them.

## What changed

- Apply the configured retained-instruction entry limit when capturing
  and restoring user messages. Fixed-budget reviewers use the fixed
  retention window for both user and assistant messages.
- Build elastic sender snapshots at delivery using the receiver's sender
  evidence budget. Give recent user messages first claim on space, then
  include preceding assistant context where it fits. Mark omitted
  evidence and save the snapshot for review and rollback.

## Testing

Add coverage for cross-host delivery after compaction, large sender
snapshots through checkpoint restore and rollback, and how synchronous
and asynchronous reviewers read saved or empty sender snapshots.

GitOrigin-RevId: f0b01a2d558e3286335efac85a4f8645dd9b954b
2026-11-20 20:11:57 +00:00
ioanbudea-OAI ab7a93771e Honor Guardian retention settings for assistant messages (#62828)
## Why

The fixed retention window can discard assistant messages before elastic
Guardian reviews can use them as context for a user's reply.

## What changed

Apply the thread's Guardian retention policy when recording assistant messages,
including confirmed messages sent through the user messaging tool. Keep full
text within the configured record limit and the overall assistant history byte
budget. Preserve an incomplete marker when a confirmed delivery exceeds the
record limit.

Recover the thread's retention settings from saved history and compaction
checkpoints. Fixed-budget reviews continue to use the fixed retention window.

## Testing

Add coverage for record limits during capture and restore, thread-owned
settings recovery, and replay of oversized confirmed deliveries.

GitOrigin-RevId: e828f06824ce6712910a9cc5ef42a438d1ddf27e
2026-11-20 20:10:51 +00:00
ioanbudea-OAI 7fcb825b46 Persist Guardian retention limits in thread settings (#62827)
## What changed

At session startup, derive `assistant_record_bytes` from the Sync Elastic
per-entry token limit for retained user instructions. Use the default
section limit when the configuration omits that section.

Store the resolved byte limit in the optional `guardian_retention` field
of `ThreadSettingsSnapshot` and update the app-server schema. Fixed-mode
snapshots omit the field, and older snapshots can still be read.

GitOrigin-RevId: a8de88c5bd0e35c4a114577e70fb0c858acb13c9
2026-11-20 20:08:33 +00:00
vishnu-oai 60fc55bb69 Enable OAuth discovery by default for config servers (#62824)
## Why

Config servers that publish OAuth metadata still required administrators
to configure OAuth endpoints explicitly for Codex to use them.

## What changed

- Discover OAuth metadata when `config_server.oauth` is omitted. Use
  explicit settings when provided, and fetch managed configuration
  anonymously when discovery finds no metadata.
- Have the Git credential helper resolve the config server before
  fetching managed configuration. It refuses explicit or discovered
  OAuth so it can apply workspace policy without opening the OS keyring.
- Apply local network policy to discovery during `codex logout`.

## Testing

Cover app-server recovery after a discovery failure, Git credential
helper rejection of explicit OAuth without a network request, and
logout discovery blocked by local network policy.

GitOrigin-RevId: 1ad84effef48fd9b56371ee177bd53c54f3e87b8
2026-11-20 19:16:07 +00:00
ioanbudea-OAI 4e9ce8fa9e Upgrade Bazel to 9.3.3 (#62820)
Refresh `MODULE.bazel.lock` with the registry hashes and module extension
digests recorded for Bazel 9.3.3.

GitOrigin-RevId: c7f50510531b456c0e547e8b7cb15d4bdbcca0bb
2026-11-20 18:46:14 +00:00
jfoo-oai 51f4b8af01 Include native USD in ChatGPT turn cost telemetry (#62810)
## Why

When a turn incurs usage priced directly in USD, reporting only the
credit-converted estimate understates its cost.

## What changed

Sum `estimated_usage_usd_micros` and `native_usage_usd_micros` for
settled turns. Default an omitted native USD field to zero for legacy
responses. Suppress the total when either component is unavailable
(including explicit null), either is negative, or their sum overflows.

## Testing

Cover omitted and null native USD values, zero costs, negative amounts,
and overflow in backend client tests. Verify that the combined amount
reaches the OTLP exporter in the app-server integration test.

GitOrigin-RevId: 8709e48329db813cd66baf270ee3f1bcfd87cb03
2026-11-20 17:59:03 +00:00
yitaoh-oai 4360c5f813 Remove model-selected Search MCP routing (#62808)
## What changed

Use the turn's effective `web_search` mode for standalone and hosted
web search. Remove model-selected Search MCP discovery, fallback, and
provider tracking across thread resumes.

Remove `web_search_provider` from model metadata, the
`tools.client_search_provider` hint from configuration, and the
`hosted_search_policy` feature flag. Update the app-server schemas and
generated SDK types to match.

GitOrigin-RevId: 59e3371f4a43d532a484db52d5998f6770292028
2026-11-20 17:46:32 +00:00
Felipe Coury d402acbeba Reset TUI thread-switch state on reconnect (#62807)
## Why

Reconnect replaces the app event queue, so queued thread-switch events can be
discarded while their resets are still counted as pending.

## What changed

- Clear the pending thread-switch reset count when replacing the event queue
  and use a shared accessor for the displayed thread during reconnect.
- Box the app event dispatch future and extract helpers for choosing the side
  conversation target and rendering the composer pane.

GitOrigin-RevId: 6bb14443952262b6a0df7fdf05db053038c7ce2d
2026-11-20 17:45:15 +00:00
Charlie Marsh bb5b9c6240 Read Responses WebSocket messages during blocked uploads (#62771)
## Why

When a server stops reading a request, the client's WebSocket write can
stall. If the server sends a Ping or rejects the request while the write
is blocked, the client can leave that message unread until the write
fails or times out.

## What changed

Poll for incoming messages before each outgoing frame and while a write
is pending. On subsequent polls, give the pending write first use of
Tokio's cooperative budget and cap read-ahead across the entire upload.

## Testing

Add regression tests for Pong delivery before upload completion, early
size-limit closes, and bounded read-ahead without write starvation.
Cover error precedence for buffered peer replies, local send failures,
and network policy revocation, plus token usage when a close arrives
before an interrupt can be sent.

GitOrigin-RevId: c018c25dcdc70b64835b07935caede5e34dfa8f2
2026-11-20 14:26:42 +00:00
Charlie Marsh 9f2b87495b Recover server replies after Responses WebSocket write failures (#62749)
## Why

A server can reject an oversized request after reading just the first
frame header. If the upload then fails with a broken pipe, the write
error can hide the server's message-too-large close.

## What changed

After a write fails partway through an upload, drain immediately
readable replies within the send deadline and a bounded read budget.
Use those replies to surface server errors, including
`WebsocketMessageTooLarge`. Treat a close seen before the first frame
as belonging to the idle connection, and retire the socket after a
failed send.

## Testing

Add regression tests for size-limit closes on an idle socket, just
before the first frame, and after a partial first-frame write fails
with pings and pongs ahead of the close.

GitOrigin-RevId: 2feeb1961992b425dbec06129015dbe4c44ff3f2
2026-11-20 12:22:56 +00:00
Charlie Marsh 1c297f8997 Flush idle Responses WebSocket pongs under backpressure (#62742)
## Why

An idle Responses WebSocket still needs to answer server pings when the
write buffer is full. The pong must finish flushing once the peer drains
the socket, even if no further messages or requests arrive.

## What changed

Have the WebSocket pump flush automatically queued pongs and retry pending
flushes as the socket becomes writable. Bound incoming polling and the
number of pongs tracked while a flush is pending.

## Testing

Add an in-memory WebSocket test that forces a partial pong write and
checks that the peer receives the full heartbeat reply without further
traffic.

GitOrigin-RevId: 12865842c80a8a25a5e107be690f9c3962ce9775
2026-11-20 12:06:32 +00:00
cassirer-openai 076ac7856b Link agent tool calls to delivered messages in rollout traces (#62709)
## Why

Matching messages by text can link a tool call to an earlier message
with the same content. A recipient can also accept a message without
ever including it in a model request.

## What changed

Record the originating tool call ID when the recipient adds a spawn,
task assignment, or message to its history. On replay, use that ID to
link the accepted message to its sender even if the recipient records
it before the sender tool finishes.

Keep the interaction edge pointed at the recipient thread until the
message appears in a model request. Track distinct conversation items
across history resets and count repeated prompt prefixes only once.

## Testing

Replay tests cover identical message text, receipt before tool
completion, and messages observed again after compaction.

GitOrigin-RevId: ccab7c33993ba5fce7fceb733dc90c9d428ec78f
2026-11-20 08:49:07 +00:00
Eric Traut 0e8c7683c4 Match TUI task mentions by displayed title (#62691)
## What changed

Use state database-backed `thread/list` requests for task mentions without
searching conversation contents. Merge title-filtered results with recent
threads by thread ID so a full filtered page cannot crowd out recent
candidates. Native Cloud uses the recent list because it lacks a title filter.

Fuzzy-match the displayed title in the picker. Keep the working directory
visible as a description and exclude it from matching.

## Testing

Cover remote listing, retention of recent candidates when the filtered page
is full, and fallback when the filtered request times out. Check that a
directory-only match stays out of the picker.

GitOrigin-RevId: ec2a5ae9f046e533104251fd82f6683343854ee0
2026-11-20 07:15:35 +00:00
Eric Traut 0f3a4756f9 Let administrators disable Codex daemon updates (#62690)
## Why

The daemon's automatic update preference still permits manual updates.
Administrators need a policy that covers both paths.

## What changed

Set `features.daemon_updates = false` in managed `requirements.toml` or
local MDM policy to block scheduled updates and manual daemon package
replacements. Updates are allowed by default. User configuration cannot
override the policy, and cloud-delivered requirements reject the setting.

When policy blocks updates, the TUI hides update actions in `/daemon`,
suppresses update offers in version notices, and directs users to their
administrator where a newer daemon is required.

## Testing

Add coverage for the default, disabled, and invalid policy cases,
rejection of the setting in cloud requirements, and the TUI with daemon
updates disabled.

GitOrigin-RevId: de9e50c4acc4dc8e83bbd2b9a5e902deb8c6f477
2026-11-20 07:14:27 +00:00
Eric Traut 45ace810b3 Copy pasted image files into temporary TUI attachments (#62687)
## Why

A pasted image path could become unreadable before submission if the
original file was moved or deleted.

## What changed

Copy the image into a private temporary file at paste time and use that
copy as the attachment. Apply a 1 GiB limit when saving image files and
clipboard PNGs. If copying a pasted image path fails, show an error and
preserve the draft.

## Testing

Cover attachment readability after deleting the original file and verify
that an oversized image paste reports an error and preserves the draft.

GitOrigin-RevId: 5f797979f36173fb3355345e0f124b81fcf86d01
2026-11-20 07:03:05 +00:00
ding-oai b059ce11f9 Allow hosts to route selected analytics events (#62684)
## Why

The analytics client sends eligible events through HTTP. Hosts that
embed Codex need a way to deliver specific event types themselves while
keeping HTTP delivery for the rest of the batch.

## What changed

Add `AnalyticsEventsClient::new_with_event_transport` so hosts can opt
in and select eligible events by wire type. The transport receives the
complete wire payload and the event's product SKU, when available.
Events stay on the HTTP path unless the transport returns `Handled`,
which suppresses a duplicate HTTP send.

Disabled analytics and local file capture bypass the transport.
Rebinding the client to a new auth context restores HTTP delivery.

## Testing

Add tests for mixed batches that verify HTTP payloads and product
attribution, plus coverage for auth eligibility, local capture,
analytics opt-out, and auth rebinding.

GitOrigin-RevId: 27ba3fe54050754b5f844f00e7e761a4d7bcb8c0
2026-11-20 06:37:15 +00:00
Anthony Tafoya 2fb728da7d Retry executor discovery V2 failures with backoff (#62679)
## Why

Discovery could retry transport failures on successive lookups while
caching server errors until invalidation. That could repeat requests
against an unhealthy executor or leave a session without an inventory
after the server recovered.

## What changed

Cache failed discovery loads per context and return the cached error
during cooldown. The first lookup after cooldown retries, with delays
doubling from 1 second up to 30 seconds on consecutive failures.
Successful inventories are reused, canceled loads add no cooldown, and
explicit refresh clears the cooldown for the next lookup without
interrupting in-flight readers.

Compare discovery snapshots to detect inventory changes so recovered
plugins and MCP capabilities can become available without an explicit
refresh.

## Testing

Cover backoff timing, shared results for concurrent callers,
cancellation, and refresh bypassing cooldown. Exercise recovery after
failed prewarming and verify that MCP inventory updates after recovery.

GitOrigin-RevId: 6de34bb8957a0b24ee874e2447157bd3af562430
2026-11-20 06:05:04 +00:00
Vivian Fang ea8ccc1d20 Keep explicitly pinned history outside the carryover token budget (#62677)
## Why

An exhausted carryover budget could drop explicitly pinned items, and an
oversized pin could crowd out ordinary user messages during local compaction.

## What changed

Preserve eligible pins in full and in their original order for the current
thread, child threads, or both, according to their retention policy. Apply
the carryover budget to the remaining history, including items retained by
features without an explicit pin.

## Testing

Add regression tests for destination-specific pins at zero budget and for
keeping an ordinary user message alongside an oversized pin during local
compaction.

GitOrigin-RevId: fc8529bcc254d8e7a4a010337ce760e94daa4bef
2026-11-20 05:28:11 +00:00
Anthony Tafoya 15c5444e87 Force executor capability rescans after V2 cache invalidation (#62675)
## Why

Invalidating Codex's discovery cache could still return stale inventory
if the executor reused its cached snapshot before its file watcher
reported a change.

## What changed

Add an optional `forceReload` flag to `capabilities/discoverV2` that
makes the executor rescan its files. Codex sends it on the next lookup
of each invalidated context. Explicit reloads also replace the matching
cache entry so subsequent ordinary requests can reuse the fresh result.

## Testing

Add coverage for discovering a newly added skill before the watcher
runs, forwarding the reload flag after invalidation, and reusing
refreshed results.

GitOrigin-RevId: c98f2b8d4772e10b74ff09dd382ad8386857158f
2026-11-20 05:18:42 +00:00
Anthony Tafoya ffa05c8bfb Prewarm executor capability discovery during remote startup (#62674)
## Why

Step-time discovery can make the first step that needs a remote executor
inventory wait for a discovery round trip. Starting discovery during
environment setup lets deferred turns begin sampling while the inventory
is being fetched.

## What changed

When executor capability discovery V2 is enabled, prewarm the thread's
discovery cache for supported remote executors before marking their
environments ready. Reserve cache capacity for all selected environments
so the first step can reuse their inventories.

Give each prewarm up to five seconds and let environment startup proceed
after discovery errors or a timeout. Step-time discovery reuses cached
successes and permanent errors and can retry transient failures and
timed-out loads.

## Testing

Add integration coverage for deferred readiness and cache reuse after
success, permanent errors, transient failures, and timeouts. Also cover
cache retention across multiple environments and session startup when
discovery receives no reply.

GitOrigin-RevId: d07fc78bd42953a4caf9e4b39528db8a254eb2b8
2026-11-20 05:17:34 +00:00
Vivian Fang a0a30c40e8 Add thread and child retention policies for injected items (#62654)
## Why

The `always` policy ties retention across context windows to inheritance by
spawned agents. Callers need to control those behaviors independently.

## What changed

- `alwaysInThread` carries items across context windows in the current thread
  and excludes them from spawned agents, including full-history forks.
- `alwaysInChildren` passes items still in the parent's context to spawned
  agents and leaves each thread's context-window retention to the usual rules.
- `always` continues to apply in both scopes, including for items saved by
  older versions. Retained tool calls and outputs must be adjacent, with the
  call first and the same retention policy on both items.

## Testing

Extend integration coverage for retention across remote compaction, inheritance
by spawned agents, and injection through the app server.

GitOrigin-RevId: aafede69cfbe149aa52292e6029d248d4bdf6401
2026-11-20 02:59:58 +00:00
Felipe Coury e787cf7024 Return file sizes from fs/getMetadata (#62653)
## What changed

Add `sizeBytes` to the app server's metadata response so clients can
read a file's size in bytes from its metadata. The field reports the
target file's size for symlinks to regular files and is `null` for
paths that resolve to directories or other non-regular files. The
protocol schemas and generated Python SDK model accept responses from
older servers that omit the field.

## Testing

Cover byte counts for regular files and symlinks to files, explicit
`null` for directories, and decoding responses that omit `sizeBytes`.

GitOrigin-RevId: fcc7bda9e55bd0584c1eff4af059422af282da9f
2026-11-20 02:42:43 +00:00
Felipe Coury 2c1b4c7c35 Fix standalone release pruning on macOS with GNU coreutils (#62648)
GNU `stat` can take precedence on `PATH` and interprets `-f` differently
from macOS `stat`, causing the installer's device checks to fail.

Use the system `stat` for both device checks before pruning old releases.

GitOrigin-RevId: 180b62ba6e2ea4ec4419c2d6e51ba4d6ce819a2d
2026-11-20 02:20:47 +00:00
Owen Lin 10ca17496f Pass inherited history visibility to the thread store (#62644)
## What changed

Add `InheritedHistoryVisibility` to `CreateThreadParams` and pass it through
prepared forks. `Full` is the default and remains the mode used by app-server
forks. `ModelContextOnly` requests that `list_turns` and `list_items` omit
inherited history. The local thread store rejects that mode as unsupported.

## Testing

Add a regression test that requests `ModelContextOnly` through a prepared fork
and checks that the local store's unsupported-operation error reaches the caller.

GitOrigin-RevId: de675d6b83ca610eca5a304b9622b312d64828f6
2026-11-20 02:02:55 +00:00
Ian MacLeod 983feef7a1 Shrink npm release tarballs with libdeflate (#62643)
## Why

Smaller npm tarballs reduce the size of the release packages. The
tarballs are already gzip-compressed, so the artifact upload can skip
its own compression pass.

## What changed

Recompress staged npm tarballs in parallel with `libdeflate-gzip` before
upload. Verify that each candidate decompresses to the exact original
tar stream and replace the original only when the candidate is smaller.
Set the upload's `compression-level` to `0`.

GitOrigin-RevId: 77bc61cdcd4d605e352dcc1380beb1654815f424
2026-11-20 02:02:19 +00:00
Ian MacLeod 64026788f3 Hide the warning navigation hint for a single warning (#62642)
Show the TUI warning navigation hint only when there are multiple
warnings to browse. Update the single-warning snapshots to reflect the
shorter footer.

GitOrigin-RevId: 8bcea7841d9fd84e037f59a6afa3e4ef2de6f01e
2026-11-20 02:01:03 +00:00
Brent Traut 7642e80723 Release persisted MCP tool results from active-turn memory (#62641)
## Why

Active turns in paginated threads retain completed MCP tool results in
memory even when history can supply the same payloads. History can also
store a truncated preview, so dropping a result requires checking that
the full payload is recoverable.

## What changed

For persisted paginated threads, check successful MCP calls in batches
and release an active-turn result only when the stored result matches
it exactly. When resuming with full history, fetch released results by
item ID so a stale history page cannot supply an older result.

## Testing

Add a regression test that restores the latest result despite a stale
page and checks that truncated, metadata-mismatched, missing, and failed
results remain in memory.

GitOrigin-RevId: 49f6f1414201e4327433043050d65a1f4adc9720
2026-11-20 01:49:15 +00:00
Anthony Tafoya e720e6c80b Reuse executor Discovery V2 inventories across turns (#62640)
## Why

Starting a turn discarded the discovery cache and forced MCP to rebuild
from a fresh inventory even when the executor context was unchanged.
An MCP refresh could also discover a different inventory from the one
the step had already captured.

## What changed

Keep a per-thread cache keyed by environment, executor session, working
directory, and sandbox. Explicit invalidation reloads discovery on the
next lookup and lets in-flight readers finish with their captured results.

Use the step's captured inventory for MCP reconciliation and bind it
with the current MCP policy. Apply the binding's plugin policy when
selecting skills and hooks.

## Testing

Cover cache reuse across turns, lazy invalidation during in-flight
discovery, and MCP refresh with a captured inventory after a server
has been revoked.

GitOrigin-RevId: 8d4087dffdb3d6feef2456918a08ae7724cf18e4
2026-11-20 01:48:00 +00:00
pash-openai 9224da4ce1 Defer queue-only mail after a retained final answer (#62639)
## Why

A WebSocket response can still complete with a final answer while Codex drains it after a mailbox interrupt. Treating the interrupt alone as a reason to resample reopens the turn even when the pending mail can wait.

## What changed

Recheck whether pending mail requires preemption after the drain. When the drain retains a final answer, queue-only mail waits for the next turn's sampling boundary. User steering can still reopen the current turn.

## Testing

Add WebSocket regression cases for queue-only mail after both empty and nonempty final answers, and for user steering received during the drain.

GitOrigin-RevId: 914b51f2de1afc91311667cc05718507717aaaa0
2026-11-20 01:35:36 +00:00
Joe Savona 78f6b11303 Add center and end alignment to status line rows (#62637)
## Why

Status line authors can start rows at the leading edge or distribute
extra space between items. They also need to center or right-align a
group while keeping its configured gaps.

## What changed

Add `justify: "center"` and `justify: "end"` to the row renderer and
TypeScript contract. Align each wrapped line independently within its
available width.

Leading padding uses the row background, stays outside hyperlink
targets, and leaves blank lines unpainted. When the last visible line
fills the width and more lines follow, the renderer can reclaim a
padding cell for the overflow ellipsis.

## Testing

Add rendering coverage for wrapped and nested rows, wide characters,
blank lines, hyperlink boundaries, and overflow. Extend the TypeScript
contract check to cover both new values.

GitOrigin-RevId: 85dd907fe60b5d2cfb759b32058d0876430dd9e6
2026-11-20 01:34:16 +00:00
Dmitriy Kovalenko f16c998db5 Reduce rollout scanning overhead when listing threads (#62636)
## Why

Thread summaries need the first session metadata and preview events. Reading
each line asynchronously and parsing unrelated records adds work to every
rollout scanned.

## What changed

Use the buffered rollout reader to scan each plain or compressed rollout in
one blocking task. After reading the first session metadata, skip JSON
parsing for lines without an `event_msg` marker or a Unicode escape that
could encode the event tag.

## Testing

Extend coverage for delayed user messages with escaped or numeric event
tags, preview reads that stop before invalid UTF-8 in plain and compressed
rollouts, and provider filtering for archived threads sorted by update time.

GitOrigin-RevId: 06c996ad3bcc290102f3ecab992e40364cb4dee9
2026-11-20 01:21:48 +00:00
Ruslan Nigmatullin 30607648d9 Centralize request and prefix ID handling in ThreadContextIds (#62635)
## What changed

Move ID derivation for base instructions and Responses Lite tool definitions
into `ThreadContextIds`. These items keep the same thread-scoped,
content-derived UUIDs when rebuilt for a request.

Invoke prefix ID assignment for newly rendered items during history
replacement and when publishing initial context into empty history.
The UUID allocator leaves these items to ordinary response item ID
allocation.

GitOrigin-RevId: f230a58e3264894bddfd5a250a4b6d1baeabecf0
2026-11-20 01:20:38 +00:00
Ruslan Nigmatullin 583ec348cf Centralize thread context ID allocation (#62633)
## Why

Response item IDs and context window IDs use separate generator callbacks.
A shared allocator gives history and inference a single API for both.

## What changed

Use `ThreadContextIds` to allocate response item IDs, retained-context
revisions, and compaction window IDs. Move initial window selection into
`InitialHistory` so resumed threads reuse a valid window ID from their
rollout. Give rollout reconstruction its own allocator.

Assign hook prompt IDs through the session's normal response item
recording path.

## Testing

Move the prefixed UUIDv7 item ID test to the allocator crate and add
coverage for JSON escaping in Guardian's item ID token budget.

GitOrigin-RevId: 31232f50648382033506d1f86815ce7c1de78378
2026-11-20 00:44:31 +00:00
XMLIU-oai ead489ac4d Retry Guardian model discovery in the background (#62627)
## Why

A failed catalog fetch can leave an explicitly configured Guardian provider
without a classifier. Waiting for another fetch during tool dispatch would
delay the tool call.

## What changed

When a tool call is observed and background scoring is allowed, retry
initializing the Guardian catalog without blocking dispatch. Allow only one
background retry at a time. Check catalog readiness against the current
credentials and schedule initialization if auth needs to be resolved first.

## Testing

Add a regression test that holds the catalog retry open while the first tool
call completes, then verifies that a later call is scored once discovery
succeeds. Cover full-access sessions and mandatory review requirements, where
background recovery is skipped.

GitOrigin-RevId: 2f07bb6bdcfbf22e512f0bd223845f149fa186b5
2026-11-20 00:15:13 +00:00
Ian MacLeod d0264b756e Share slash command argument range mapping in the TUI (#62624)
## What changed

Use `slash_args_elements` in both the chat composer and slash command
dispatch. The shared helper converts text element byte ranges to offsets
relative to the command arguments and clips them to the argument bounds.

GitOrigin-RevId: 72e2fa42bf0d3fc385a58cc13fb6741c896db900
2026-11-19 23:55:41 +00:00
tongzhou wang 26f70f9460 Handle rollout budget decisions in each accounting path (#62621)
Pass `SamplingUsage` into numeric usage accounting and let the host and
controller paths apply their budget decisions directly. Host-wide
exhaustion stops new work, while turn-only exhaustion returns
`SessionBudgetExceeded`. The controller still stops new work on budget
exhaustion when there is no native rollout budget.

GitOrigin-RevId: 544b9a49a23e2becc68d9cecae347e4d00bbdea0
2026-11-19 23:24:47 +00:00
Charlie Marsh 5bdb5e8b3c Split in-memory execution policy rules into a separate crate (#62615)
## Why

Configuration, protocol, and prompt code use in-memory policies and
previously pulled in the Starlark parser through `codex-execpolicy`.

## What changed

Move policy construction, rule validation, and evaluation into
`codex-execpolicy-rules` and use it directly from those crates. Keep
Starlark policy loading and file updates in `codex-execpolicy`, which
re-exports the shared rule types and wraps rule validation errors while
preserving their source locations.

GitOrigin-RevId: 5bc70d3cd387b43a3ad1fcc56af96ad169ac8b13
2026-11-19 22:32:56 +00:00
rreichel3-oai db263d4f54 Refresh Guardian policy on config reload and account changes (#62614)
## Why

Running threads need to pick up changes to approval requirements and
Guardian policy when users reload configuration, sign in, or sign out.

## What changed

Refresh Guardian policy after publishing local config layers so the first
reload uses updated policy fallbacks. Attempt the refresh even if unrelated
user configuration fails to load.

Refresh policy after login while the account owner is still current, and
after logout. If reading account details fails after login, report the
error in the login completion notification and still send the account
update.

## Testing

Extend coverage for changing and removing Guardian policy requirements,
applying requirements despite a config load error, and picking up local
fallbacks on the first reload. Verify that a late low-risk score cannot
release a pending adaptive approval while stricter requirements apply.

GitOrigin-RevId: 95453807a06a0d3c39dcfd9a0f66fd63f41294b9
2026-11-19 22:31:45 +00:00
Alex Zamoshchin 6a8a81166a Refresh plugin recommendations after installed state changes (#62610)
## Why

Recommendation lookups poll the plugin service for a tooling-state marker even when the cached catalog can still be reused. Install flows and installed-plugin snapshots already give Codex signals to refresh recommendations.

## What changed

Remove tooling-state polling and refresh recommendations on the next lookup after a known install event or a change to the installed plugin inventory or enabled state. Invalidate all product SKUs for the affected plugin service and account scope. If the account changes while a remote install prompt is open, invalidate both account scopes when the user accepts.

Concurrent lookups share a catalog fetch. If a refresh fails, keep serving the last successful result when available and retry on the next lookup.

## Testing

Cover invalidation across accounts, backends, and product SKUs, retention of the last catalog after a failed refresh, and isolation from fetches that complete after invalidation. Update the remote install integration test to exercise the next turn without waiting for the poll interval.

GitOrigin-RevId: 5d2ba84d1118e9346308bf6225543e0e174f8125
2026-11-19 22:16:30 +00:00
ztanner-oai 6633c6e09a Apply backpressure to app-server request replay on thread resume (#62609)
## Why

When a client resumes a thread with many pending server requests, replay
can fill the connection's bounded outbound queue if the client reads
slowly. Replaying inline can also stall the thread listener.

## What changed

Replay pending requests in a background task after sending the
`thread/resume` response. Allow one outstanding replay write per
connection and wait for its write receipt to complete or be dropped
before sending the next request. This extends the write-receipt
backpressure used by `command/exec`.
https://github.com/openai/codex/pull/15547

A new resume replaces the previous replay for the same thread and
connection while honoring any outstanding write receipt. Unsubscribing
or disconnecting stops the replay. Before sending each request, check
that it is still pending and apply the human approval eligibility check
where required.

## Testing

Add a regression test with more pending requests than the outbound queue
can hold. It checks that a second resume succeeds while a replay write is
stalled, dropped write receipts let replay advance, and unsubscribe and
disconnect stop replay.

GitOrigin-RevId: 77fc415be0e7b50744f5ccfcaa09857359dd5c55
2026-11-19 22:15:23 +00:00
XMLIU-oai efcc0cf917 Enable Guardian V2 scoring with an explicit Guardian provider (#62607)
## Why

An explicit Guardian provider could handle approval reviews, but configuring it
disabled Guardian V2 scoring. This prevented automatic reviews from using
background scores from that provider.

## What changed

Route classification through the configured Guardian provider and use its
classifier catalog for instructions, reasoning effort, review thresholds, and
input limits. Apply the Guardian provider's API-key access policy to classifier
requests and ignore assessments from the actor's response stream when a
Guardian provider is configured.

Keep mandatory review requirements in force and skip background scoring in
User approval mode and Full Access.

## Testing

Extend coverage for separate actor and Guardian providers at startup and after
cold resume, including when both use the same model name. Cover catalog
settings, scoring restrictions, and provider-specific API-key policy.

GitOrigin-RevId: 5f83d1704bacc63033e144bba0d78752283cb590
2026-11-19 22:00:52 +00:00