## Why
On X11, a clipboard owner can answer an image request with text, causing the image read to fail even though text is available. Submitting or queueing a draft while its clipboard read is pending can also send it without the intended paste.
## What changed
- Enable `Ctrl+V` text fallback on local Linux outside SSH and WSL, and allow `Shift+Insert` text fallback across platforms.
- Try text after eligible Linux image-read failures. Report the original image error if the fallback yields no text.
- Keep pending pastes alive across key releases. While a paste targets the current draft, intercept submit and queue shortcuts and show a reminder to review the draft before sending.
## Testing
Extend clipboard worker coverage to exercise submit during an active read and queue after a read completes but before its text reaches the draft. Snapshot the pending-paste reminder.
GitOrigin-RevId: 21bec5e405e13631a2a72f440482338611307ff3
## What changed
Recognize Orca from `TERM_PROGRAM=Orca` and report it in `codex doctor`.
Render Markdown links as clickable labels in Orca and keep destinations
visible under terminal multiplexers. Enable Kitty graphics for pet images
only when Orca advertises `ORCA_IMAGE_PROTOCOL=kitty` and the session
passes the direct-terminal checks.
## Testing
Cover Orca detection, Markdown link rendering and multiplexer fallback,
and pet image capability checks.
GitOrigin-RevId: 978a9cd99a8090bfe9198611e9ae7e0dd2709c3b
## Why
The docked Command Center has a fixed width, and mouse clicks can
focus the pane but cannot open a task. Moving between the task list
and the conversation should work with the workspace shortcuts.
## What changed
- Open or focus Command Center with `leader a` by default. Use the
workspace pane shortcuts to move between Command Center and the
conversation, with matching Agents bindings taking precedence in
Command Center.
- Drag the divider to resize Command Center. Show each docked task's
status and Git branch, when available, on a second line. Click either
line to open the task, or click **Show more** to load older tasks.
- Animate the dock opening and closing.
## Testing
Extend the TUI tests to cover mouse activation and workspace keyboard
navigation, including preservation of the conversation draft and
reading position.
GitOrigin-RevId: e78aa4afb68e9971de51859221ce996b13750e13
## Why
Opening the Agent Command Center in a modal interrupts the conversation
view. Docking it keeps the transcript and draft visible while browsing
tasks when the terminal has room for both panes.
## What changed
With `features.tui_workspace` enabled in owned transcript mode, the
Command Center opens to the left of the conversation on wide terminals.
On narrow terminals, the focused pane fills the screen. Opening a task
returns focus to the conversation and keeps the dock open. Other
transcript modes continue to use the modal Command Center.
## Testing
Add coverage for draft and reading-position preservation, wide and narrow
layouts, queued results arriving after a focus change, and selecting a
new session when its task appears in the dock.
GitOrigin-RevId: d07c9cad3bb8685167b5995e550c406948d7a6e3
## Why
When the resolved permission and approval guidance is blank, the initial
context still includes a developer message containing only the permissions
wrapper.
## What changed
Omit that message when the guidance is empty or whitespace-only. Keep a
permissions checkpoint so later turns can report newly saved command
prefixes. Continue sending bundled approval guidance when it applies.
## Testing
Cover blank and bundled approval guidance and later command-prefix updates
with and without per-environment context. Update Guardian request snapshots
to reflect the omitted empty message.
GitOrigin-RevId: b1e2b6377733ec34b875b51d800922e15c267571
## What changed
Pass `None` for the resumed working directory when the TUI reads
effective reasoning summary settings, so the call matches the
`startup_config_cwd` signature.
Update the indexed search rollout snapshot to expect
`stream_options.reasoning_summary_delivery` set to `sequential_cutoff`.
GitOrigin-RevId: 66225aa15dcfe5da43b397a96a7da4b4712f0b55
## Why
A client can attach to a Rex session after Codex starts. A successful
native clipboard write can update the host clipboard without reaching
the attached client.
## What changed
Use shared terminal detection to select OSC 52 forwarding in Rex, even
when native copying succeeds. Keep environment-based routing for tmux,
Herdr, and SSH. Use the same terminal detector to recognize VS Code for
keyboard handling, with the existing Windows probe as a fallback.
## Testing
Cover OSC 52 selection for Rex without SSH or tmux and verify that
forwarding runs after a successful native copy.
GitOrigin-RevId: 47db5868d87aaf2aeee9cdd59307aa1be532c11e
## Why
Low-level transport errors can clutter stderr and include endpoint
URLs with credentials. An optional HTTP MCP server can also still be
starting when its tools are omitted from a turn.
## What changed
- Warn once per Streamable HTTP connection when startup fails or the
server is omitted from the turn because startup is still pending.
Include the server name and a short reason without the raw transport
error.
- Filter redundant MCP worker errors from default `codex exec` stderr
and preserve caller control through `RUST_LOG`.
- Add server context to errors when startup blocks a tool call or
resource operation, when a tool call finds a disconnected server,
or when HTTP session recovery fails.
## Testing
Add regression coverage for startup warnings, credential omission,
explicit `RUST_LOG` diagnostics, and an optional server that becomes
ready in time to be included in the turn.
GitOrigin-RevId: 1fd012a5e73f205c3d8735adde395c36672c205c
## What changed
Choose Auto, Concise, Detailed, or None under Sessions in `/config`.
The picker saves `model_reasoning_summary` through the connected app server
for new chats. The panel shows the effective value and reports when a config
or launch setting overrides the saved choice.
## Testing
Add coverage for the picker and for saving Auto explicitly when the setting
was previously unset. Verify that the active chat keeps its setting and
that the panel reflects a profile override.
GitOrigin-RevId: cd027a6b16879a656b8d8b21488f0588c98f9077
## Why
The TUI left the reasoning summary unset on turn submission, so OpenAI
requests could use `concise` even when the user had chosen no summary
setting. Embedded WebSocket prewarming and the first turn need to use
the same summary setting to reuse the warmup response.
## What changed
- Send the configured `model_reasoning_summary` with TUI turns, defaulting
to `auto` for OpenAI providers. Use the same fallback when prewarming
through the in-process app server.
- Read reasoning summary settings and custom provider definitions from
the app server's effective config while honoring explicit launch
settings. When resuming a remote session, use its working directory
for the config lookup unless a remote directory override is set.
## Testing
Cover summary defaults and explicit settings in Responses requests,
and verify that the first embedded WebSocket turn uses `auto` and
reuses the warmup response.
GitOrigin-RevId: 1a2edfa44abdd031691a0d421eba077b0796ebe1
## What changed
Mark `concurrent_reasoning_summaries` as stable and enable it by default.
When requesting reasoning summaries from OpenAI, Codex now sets
`stream_options.reasoning_summary_delivery` to `sequential_cutoff` by
default.
## Testing
Exercise summary rendering with the default configuration and update
request assertions and snapshots to expect `sequential_cutoff`. Explicitly
disable the feature in tests that exercise legacy reasoning events.
GitOrigin-RevId: 04310fd271ced11c3a22e8ff6275a387c9c22fc2
## Why
The rollout trace reducer assigns ordinal IDs to reduced transcript nodes
and uses Responses item IDs to match wire items to those nodes. Using
strings for both lets callers mix up the two kinds of IDs.
## What changed
Make `ConversationItemId` a Rust newtype for transcript nodes and use
`ResponseItemId` for receipt and agent delivery lookups. Carry the typed
transcript IDs through snapshot reconciliation, compaction, and links to
tool calls, code cells, and agent interactions. Continue serializing
transcript IDs as strings such as `conversation_item:9`.
GitOrigin-RevId: 28a36266bc88e1cbc036d99a90b3f88e6966d328
## Why
Model catalogs could provide guidance for Plan and for Default after Plan,
but had no field for the turns before the first Plan turn.
## What changed
Add optional `collaboration_modes.initial` guidance. Codex uses it in
Default before the first Plan turn when the field is nonempty and no
caller-supplied instructions take precedence.
## Testing
Add a request snapshot test that covers initial guidance on a new thread,
retains it after resume, and verifies the switch to Plan guidance and then
to Default guidance when leaving Plan.
GitOrigin-RevId: bb9e83aeb60af54fc2ee1bf9ce5acbb8a354ffb8
## What changed
Add `features.web_search_indexed_default` to let restricted turns use
`indexed` search in place of the implicit `cached` default when the
provider and managed requirements allow it. Full-access turns still
prefer `live` search when allowed, and an explicit `indexed` selection
retains its existing precedence.
Forward the flag through the TUI and keep the default implicit when
launch overrides disable legacy search flags.
## Testing
Cover mode selection across permission profiles, explicit settings, and
managed requirements. Verify that the first model request advertises
indexed search and that permission changes take effect on the next turn.
GitOrigin-RevId: 08a6279c447c517c50b9e6a544ecdf681b81bf50
## Why
Legacy MCP servers can reject `server/discover` before JSON-RPC dispatch
because they require a session ID or reject the requested protocol version.
Their HTTP 400 response can be empty or lack a matching JSON-RPC request ID,
leaving Codex unable to start the legacy handshake.
## What changed
Retry with a sessionless `initialize` when the initial sessionless
`server/discover` receives HTTP 400 without an authentication challenge or
a JSON-RPC error code that requires validation. Preserve fallback for
recognized legacy rejections and give structured protocol version offers
precedence over error text. Once a server offers a modern version, surface
a rejected follow-up probe as a discovery failure.
## Testing
Extend mock-server coverage to verify that legacy fallback establishes a
fresh session and uses it for `tools/list`. Cover authentication challenges,
malformed and uncorrelated JSON-RPC errors, and failures after a modern
version offer.
GitOrigin-RevId: edc573e38c63b837462f1b8d84e2d8abdf62cb3e
## Why
The metadata budget check only needs the serialized byte count.
Using `serde_json::to_vec` allocated a buffer for JSON that was
immediately discarded.
## What changed
Use `serialized_json_bytes` to count the JSON bytes for the executed tool
call list and its accompanying metadata fields. Keep the existing wire
size accounting and serialization error fallback.
GitOrigin-RevId: 1767507eeb52677439e7fce1cbaa24dbec913024
## Why
Dispatched invocations, model-visible Responses calls, and Code Mode's
per-cell runtime calls use IDs with different roles. A dedicated Rust type
makes the dispatch identity explicit in APIs that carry it.
## What changed
Add `codex-tool-call-id` and use its `ToolCallId` across core tool dispatch,
nested Code Mode calls, and rollout tracing. The type wraps a string and
continues to serialize as a string.
GitOrigin-RevId: 119de57a9af840c4de72895adc9acdd0ed15b4fd
## What changed
Record whether an explicit `web_search` setting matches the effective
mode after applying configuration requirements. Mark the thread manager
sample's disabled mode as explicit.
Accept `indexed` in the TypeScript SDK's `WebSearchMode` type.
## Testing
Extend the SDK test to verify that both `cached` and `indexed` are passed
to `codex exec` as `web_search` config overrides.
GitOrigin-RevId: 0cf98c9a32f4da31fecc50da71acb601f6043b47
## What changed
Set the `cot_removed` tag from the latest completed sampling
request on the live thread. Use `true` for reported reasoning removals
and `false` for an explicitly empty report. Omit the tag when no report
is available and discard any caller-supplied value.
Clear the stored result when thread history is replaced. A resumed
session starts without a stored result.
## Testing
Cover tag values in saved reports across tool calls, compaction, and
session resume. Verify that failed compaction preserves the last
sampling result.
GitOrigin-RevId: f1568567a6b4a62685569478fc7194f4357cb605
## Why
Managed requirements from different sources could not be combined when one
used `[permissions.network]` and another used `[network_proxy]` or
`[experimental_network]`.
## What changed
Allow these tables to compose across sources. The highest-priority list of
each kind replaces lower lists of that kind, while keyed `domains` entries
update individual selectors by source priority. A deny wins when a selector
appears in both surviving lists. A surviving `allowed_domains = []` clears
lower-priority grants, while an empty `domains` map contributes no updates.
Require mirrored domain declarations to agree on how they compose with other
domain sources. Unix socket path rules still require a single network table
spelling across sources.
Carry equivalent denied selector spellings into the effective proxy policy.
When local binding is disabled, an attached executor's explicit local grant
must also satisfy the controller's allowlist constraints. The standalone
proxy can still narrow a wildcard to an explicit local grant.
## Testing
Cover mixed table spellings, list replacement and clearing, conflicting
mirrors, equivalent IPv6 spellings, and local grants in standalone and
attached proxy modes.
GitOrigin-RevId: b3d550d9f462564c89663ea4b15e723f0ea76881
## Why
App-server clients that prepare threads for later use need to be able
to skip Daybreak propagation for an individual thread when the server
configuration enables it.
## What changed
With `experimentalApi`, pass `daybreakProgramPropagationEnrolled: false`
to `thread/start` to opt a new root thread out. Managed requirements
take precedence. Omitting the field or passing `null` or `true` uses the
configured enrollment rule.
The same field on `Thread` reports actual enrollment for the live
session, including in the start response and `thread/started`
notification. Reusing a live session preserves its enrollment. A thread
returned from stored metadata alone reports `null`, and resuming it
from storage in a new session reports `false`.
## Testing
App-server tests cover enrollment under enabled, required, and disabled
configuration, as well as reporting across live reads and resumes,
unload, and resume from storage. A core test checks that opting out
prevents native helpers from inheriting the root's saved Daybreak choice.
GitOrigin-RevId: f9aae9ff76702b1e5a38d45120cd889a26f8ece5
## Why
A slow cloud skill lookup can delay MCP startup even after the plugin
catalog is ready. If the refresh is canceled while waiting for skills,
it can miss the chance to prewarm those servers before the first turn.
## What changed
Queue MCP prewarm as soon as plugin discovery changes or clears the
catalog. Skill discovery alone leaves the MCP server set unchanged.
At the end of the refresh, queue a retry for eligible MCP startup
failures. If discovery is canceled, check for those failures the next
time the catalog lock is acquired. Reuse pending handshakes and leave
authentication failures and Apps-managed reconnects to their existing
recovery paths.
## Testing
Add regression tests for first-turn tool availability after cancellation,
startup recovery with cloud plugins disabled, and a single retry for a
persistent startup failure.
GitOrigin-RevId: f92162d1629358953d8810d20244e55f07416a01
## Why
App-server clients lose metadata supplied by the image backend when
Codex turns the response into a completed image generation item.
## What changed
Expose the backend's `image_metadata` as optional `imageMetadata` in
app-server items and preserve nested values through thread persistence,
resume, and legacy history replay and migration. Keep this metadata out
of model tool output.
Omit empty metadata and discard non-object, oversized, or deeply nested
metadata without dropping the generated image.
## Testing
Extend coverage for per-image parsing, metadata limits, and round trips
through app-server completion, persisted history, and thread resume.
GitOrigin-RevId: 7211a9db1149cb05e6176b08b0462ca173ac72d5
## Why
The TUI creates WebRTC calls locally, and that request path did not use
runtime agent authentication even when runtime agent instances were enabled.
## What changed
- Reuse local credential and runtime managers across calls while the login
configuration stays the same. Reload first-party credentials before
creating a call and keep network policy under the primary account owner's
control.
- Use the shared provider request resolver for call authentication and HTTP
transport. Apply the WebRTC base URL override before resolving credentials
so runtime authentication is selected for the actual destination.
## Testing
Add mock-server coverage for concurrent calls sharing a runtime with fresh
assertions, credential changes, and both dual-header and assertion-only
modes. Cover the feature toggle, custom call destinations, network policy
permits, and provider credentials when the local login file is malformed.
GitOrigin-RevId: 6503b3375c79d3126911d1d7c1aea898face37b9
## Why
When an organization's configuration server requires a new OAuth grant,
clients need a way to sign in before the app server starts so they can
load and validate the required settings.
## What changed
- Have `--print-startup-config` return the `configServerLogin` action
when browser sign-in is required, and verify that the required server
settings were applied before returning startup requirements.
- Add `codex app-server --startup-oauth`, a dedicated stdio mode that
resolves the configuration server from local managed requirements,
sends the client a browser authorization URL, and handles the callback,
token exchange, and credential storage. Clients can cancel a pending
sign-in or rerun `--print-startup-config` after it succeeds.
## Testing
Add a test that checks the browser handoff URL and verifies that
cancellation completes the pending login request with `LoginFailed`.
GitOrigin-RevId: 00f10d28befe33539882f4f3c0d2baf868ceb4a1
## Why
At boot, the recorded Windows session may no longer exist or may not
have a user token yet. The sandbox service can retry restoration when a
session change signals sign-in.
## What changed
Treat missing sessions, missing tokens, and sessions belonging to
another user as owner unavailability. Search the other sessions for the
recorded owner's SID. If no session restores the owner, report the first
restoration error if one occurred, or let the service retry on a later
session change.
GitOrigin-RevId: c40971e70c6eee46068aafe534c0f0147d16bb77
## Why
Disabling native multi-agent tools also dropped the default guidance about
how many agents can be active in a session. That limit still matters for
agents running on a host that handles turn admission.
## What changed
When `multi_agent_v2.disable_native_tools` is set, root agents and
subagents receive only the configured
`multi_agent_v2.max_concurrent_threads_per_session` in their default role
guidance. Explicit role overrides retain precedence, and empty role text
still suppresses the guidance.
## Testing
Cover both roles with bundled and catalog-provided role text. Update the
request snapshots for explicit and proactive delegation to show the
concurrency hint with native tools hidden.
GitOrigin-RevId: e940e7a7886b69888002307c021607b19bb87cd0
## What changed
Add the optional `target` field to `account/gatewayOAuth/login`.
The startup protocol defines `{"kind":"configServer"}` as a target
for `--startup-oauth`, mutually exclusive with `modelProvider`.
The regular app-server login handler rejects explicit targets.
Define `StartupGatewayOAuthChangedNotification` with the target,
status, and authorization URL for the browser handoff. Export the
new types in the JSON schemas, TypeScript bindings, and Python SDK.
## Testing
Update the TUI device login regression test to expect `target: null`
when signing in to a resumed thread's saved gateway.
GitOrigin-RevId: fb3ce66a143cad9ad56c93f3ac37f8b6f1abdb0e
## Why
The Agents overview can go stale when Cloud threads change from another
client, especially when the TUI has no conversation stream attached.
## What changed
- Use Cloud stream notifications to update thread status and refresh the
thread list. Poll every 10 seconds while the overview is visible and
no stream is attached.
- Refresh the history already shown while preserving the `Show more`
cursor. Use fresh list metadata for thread names, recency, and unread
state, and restore rows when a refresh catches a missed unarchive.
## Testing
Cover Cloud inventory notifications, polling while detached, pagination
across refreshes, and recovery from a missed unarchive.
GitOrigin-RevId: 63c98438b6ddd2e47dd2d1f419c2a676508c6d91
## Why
Threads that stay in Default mode carry a collaboration-mode prompt even
though they have no Plan mode instructions to supersede.
## What changed
Omit bundled and model-catalog Default mode instructions until a thread
uses Plan mode. Emit Plan mode instructions on entry and Default mode
instructions when switching back. Preserve eligible caller-provided
instructions and carry the active mode through compaction and resume.
## Testing
Cover prompt contents before, during, and after Plan mode in core and
app-server tests, including compaction and resume in the core tests.
GitOrigin-RevId: b734767da15be53c4eccae71994e46eba63a9ecc
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
Refresh `MODULE.bazel.lock` with the registry hashes and module extension
digests recorded for Bazel 9.3.3.
GitOrigin-RevId: c7f50510531b456c0e547e8b7cb15d4bdbcca0bb
## 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
## 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
## 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
## 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
## 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