## Why
HTTP sampling can attach private connector result bodies, but Responses
WebSocket sampling leaves them out. WebSocket requests need the same
destination and account checks before sending those bodies.
## What changed
Apply the existing HTTP eligibility checks to each WebSocket attempt and
attach only result bodies that belong to the current account and match
the input being sent, including when that input is an incremental update.
Keep prewarm requests free of private result bodies. Update
`tungstenite` and `tokio-tungstenite` to keep sensitive payload bytes
out of frame diagnostics.
## Testing
Add regression coverage for connector results reaching the server while
staying out of request observers and client logs. Cover custom-provider
requests and retries across an account change with results from both
Code Mode `exec` and `wait`.
GitOrigin-RevId: df5ec8608e59bb3a0444fafd5268279e669ccb55
## Why
The existing GPT-6 migration guidance points to the earlier Astra
quickstart. Explicit GPT-6.2 Astra and Sol requests need guidance for
the selected model and its endpoint requirements.
## What changed
Direct both GPT-6.2 targets to the shared migration quickstart and
document that both support Responses and Chat Completions, with tool
calling requiring Responses. Refresh the fallback model guidance and
point onboarding examples to the model selection guide. Specify model
choices for legacy Chat Completions examples, Codex CLI
examples, and configuration shared with the IDE extension.
GitOrigin-RevId: 14000eedac4f2a4169bb76212cb74d8342b5752e
## Why
Launch errors and timeouts can be hard to diagnose without knowing which
stage the launcher reached or how long each stage took.
## What changed
Log MXC launch phases by process ID in the Windows sandbox runtime log.
Distinguish filesystem helper launches from regular commands and record
filesystem grant counts, preparation, spawn, and wait durations, and
launch outcomes or errors.
Reuse the runtime log's rolling file appender across entries in the same
launcher process.
GitOrigin-RevId: 8d55261fc9efeab8afe4b5be67b5aacb6868f3da
## Why
A turn interrupted during setup can be discarded before it runs. Starting
the worktree scan during setup can spend time scanning for a turn that
will never send a model request.
## What changed
Collect `HEAD` and remote URLs in the background after turn setup, and
start the worktree status scan only after the turn is admitted to run.
Model requests use the latest available Git metadata while collection
continues, and later requests can include the worktree status once it
is available.
Use shared background Git root discovery for the memory extraction
change probe and pass the resolved root into the probe.
## Testing
Regression tests cover requests proceeding while status is blocked,
later requests carrying the updated `HEAD`, remote URL, and dirty
status, and an interrupted wake skipping the worktree scan.
GitOrigin-RevId: 00f465a5621d672d8b6d9063c384fb62e493c79f
## What changed
Add `ToolLifecycleContributor::mcp_tool_request_meta` so an extension can
use thread and turn data and the captured tool registration to attach an
entry to the outgoing request's `_meta`. Codex rejects duplicate keys.
Expose the registering plugin's package ID in `McpToolContext` so
contributors can scope metadata to that plugin.
Export `PERSISTED_MCP_RESULT_MAX_BYTES`, the existing 64 KiB limit for
untruncated MCP results in durable history.
## Testing
Extend the multi-environment MCP scenario to check that only the call
for the selected plugin receives the metadata and that the result
callback sees the same plugin context.
GitOrigin-RevId: 25a2afc5402a5c9323de184313d614aede3692fb
## What changed
Pass the resolved result-body destination into sampling, where its owner
is used to select retained bodies for the turn. Check that the capture
owner is current under the retention lock before converting an MCP
result and again before retaining its body.
## Testing
Extend the request-budget integration test for direct calls and Code Mode
to check when executed calls carry result metadata. Cover ungranted and
custom endpoints, independent model credentials, hosted Apps OAuth and
header overrides, and disabled result-body passthrough. Check that the
shared configuration preserves metadata on a subsequent turn.
GitOrigin-RevId: 8e5ac88ba323d10e0f3e696d4ae356d52bdf22a3
## What changed
Allow config server bundle and auth loaders to discover authorization and
token endpoints, plus an optional device authorization endpoint, from OAuth
metadata when callers enable discovery and omit `config_server.oauth`.
Discovery uses the bootstrap HTTP policy, times out after five seconds,
and keeps the discovered settings in memory. Existing managed-config
entry points pass `ConfigServerDiscovery::Disabled`.
If bundle loader initialization fails, report the error on the first read
and retry on later reads until a loader and its refresh worker can start.
## Testing
Add tests for endpoint parsing and defaults, the discovery timeout,
explicit OAuth precedence, disabled discovery, and local network policy.
GitOrigin-RevId: 7cb72054147ec34f985d55dfe708fccfafcb4ba3
## What changed
Let in-process sessions and hosts using stdio or gRPC supply trusted
JavaScript helpers. Run each helper before the cell's module in the same V8
context, only when the cell exposes a unique matching binding with the
expected tool name and namespace.
Report ambiguous bindings and preload failures as bounded cell errors.
Suppress V8 diagnostics on stdout so they cannot corrupt stdio protocol frames.
## Testing
Add coverage for per-session helper selection, exact tool matching, ambiguous
bindings, and bounded compile and execution errors. A stdio subprocess test
checks that a failed preload leaves another session on the same connection
usable. Allow more time for existing CLI and MCP integration tests to connect,
start their test server, or shut down.
GitOrigin-RevId: f9f037de7f9d6018ae755b38475c4131ca7ba1f0
## Why
Result body capture covered direct Apps calls, leaving eligible calls made inside Code Mode without their result bodies in follow-up sampling metadata.
## What changed
Capture eligible nested MCP results and bind them to the originating `exec` or `wait` output for the current turn. Send `tool_result` and `tool_result_call_id` together when both fit the request budget. Keep the bodies out of conversation history and reclaim capture capacity when the output binding is lost.
Require analytics to be enabled and the provider to allow request metadata before starting turn-level capture. Check the call's credentials at dispatch and again when recording the result.
## Testing
Add coverage for yielded and finished outputs, late results, retries with replacement output items, capture budget recovery, and the request size boundary for sending the body and call ID together.
GitOrigin-RevId: 0983261ac39021099d14efa5c9a9acac47ac9269
## Why
The Responses client checks the gateway URL and request headers before
allowing connector result bodies to be attached. Provider query parameters
can also change the request while leaving those checks satisfied.
## What changed
Require an empty provider query parameter map, or no map, when selecting
a connector result destination. Check the ChatGPT credential variants
directly and retain the current auth owner for thread grant verification.
## Testing
Extend the client setup test to check that a custom provider URL is
ineligible even with refreshed ChatGPT credentials. Extend the enterprise
MCP lifecycle test to check that the configured provider receives the
account bearer token and executed tool-call metadata. Allow HTTP client
tests to cache a direct system proxy decision as well as a proxied route.
GitOrigin-RevId: 1e7e77ec6e65263eaff658ba39943ec51230d332
## Why
Callers of `CodexThread::inject_response_items` each compile a copy of
its concrete future, duplicating compilation work.
## What changed
Return a `BoxFuture` from `CodexThread::inject_response_items` so the
concrete future stays in the core crate. Raise the core integration
test crate's recursion limit to 256.
GitOrigin-RevId: 2ccb280c7887278fc8011c37df35df84c47b3e35
## Why
Clients sampling a thread could only use the source thread's model.
## What changed
Add an optional `model` field to the experimental `thread/sample`
request. Omitting it or passing `null` inherits the source thread's
model. When an override is supplied, the server uses the selected
model's capabilities to decide whether to apply the requested
reasoning effort.
## Testing
Add an app-server integration test that checks model selection and
reasoning effort for the overridden sample, then verifies that a
subsequent sample and a follow-up turn use the source model.
GitOrigin-RevId: f5c54ca3d693d31e1f3e0628a520583330a5d56d
## Why
Remote runners can block bubblewrap from creating a nested network
namespace, preventing the shell from starting and reaching the
filesystem checks.
## What changed
Enable network access in `denied_read_in_second_workspace_root` so the
test can exercise denied reads across both workspace roots without
requiring a nested network namespace.
GitOrigin-RevId: 26eada1e5efde4a31190628f4696c6beb400454d
## Why
Repeated tool output, such as the same image returned in several results,
can consume the trace bundle budget. When output bytes are unavailable,
the surrounding result can still carry terminal metadata and conversation
links.
## What changed
- Store JSON string values of at least 64 KiB, measured after encoding,
separately from their tool result or runtime event. Identical encoded
values share one record per bundle, while each occurrence retains its
position and complete captures reconstruct the original JSON bytes.
- Keep separate compression shards open for content and surrounding
records. Budget for the serialized event and fall back to a single
capped or omitted payload when the split layout or its references
exceed the applicable limit.
- Track missing values separately from literal `null` so reduction can
preserve surviving terminal metadata and keep tool output IDs attached
to their original items.
## Testing
Add regression tests for shared image and text payloads, byte-for-byte
reconstruction, recording completion under tight bundle limits, and
reduction with missing output.
GitOrigin-RevId: a003197ea998639b6c2ae27f408990c0186406bd
## Why
Cloud turn and item pages can reflect different points in time. A reply
restored from history may still be unfinished even when its turn is marked
complete. When the final text arrives, the TUI can leave a stale prefix in
the transcript or put the final reply after intervening tool output.
## What changed
Track Cloud replies by turn and item across history replay, pagination, and
live streaming. Reserve a transcript position even for an unfinished reply
with no visible text. When it completes, replace its fragments in place or
remove them if the final text contains only hidden directives. Keep late
completions from interrupting another reply's stream.
Preserve transcript order when choosing the latest copyable reply. When a
turn completion notification has no response text, fall back to the latest
completed response from that turn.
## Testing
Cover replies restored from older history pages, late completions during
another stream, and directive-only completions that remove a visible prefix.
Check the resulting transcript order, copy text, and notification fallback.
GitOrigin-RevId: a0abb75bf1378524461a519fe9a0656e15bca4bf
## Testing
Add a regression test that checks that hovering over a saved chat's
preview highlights both its title and preview without moving the
selection. Moving to the title keeps the highlight without requesting
another redraw, and moving to the Side chats heading clears it.
GitOrigin-RevId: d54501f28c00112281389f67bb3671dfa6b18513
## What changed
Add the off-by-default `features.connector_tool_result_passthrough` flag. For direct ChatGPT Apps calls, capture eligible text and structured content from the original MCP result before tool output processing. Attach the captured body to the matching executed-tool record on follow-up HTTP Responses requests to the ChatGPT Codex endpoint when the request uses the same authenticated account and turn.
Bound captured bodies in memory for the originating turn. Enabling passthrough alone scopes executed-tool metadata to calls with a captured result ID.
## Testing
Add coverage for same-turn HTTP delivery, omission on later turns or after an account change, and omission of shell-call metadata on HTTP and WebSocket requests when only passthrough is enabled.
GitOrigin-RevId: 410c81559bfc15022b896cf006cb631f3fd9454e
## Why
The pointer shape can signal that transcript links are clickable, but the
text itself does not change on hover. A foreground change makes the
clickable region visible.
## What changed
Change the foreground color of hovered transcript and status-line
links, transcript disclosure controls, and the warning notice. Use the
rendered link spans so the highlight follows the visible text, including
wide characters. Recompute the highlight on redraw so it follows the
content under a stationary pointer as the transcript scrolls or updates.
## Testing
Add a mouse-motion regression test that checks highlight and restore
behavior for transcript links, including wide characters and Markdown
table links, as well as status-line links, disclosure controls, and the
warning notice. The test also checks that a URL in the editable draft
keeps its original styling.
GitOrigin-RevId: 4c7da58705e2ad4c710ec6c55727d5a064f3cf1f
## Why
The telemetry-only integrity checks duplicate policy preparation already
performed by sandbox enforcement.
## What changed
Disable integrity checks at the shared entry point for exec-server and legacy
local execution. Command launches now skip integrity dependency discovery,
policy preparation, and telemetry.
## Testing
Ignore the command-launch integration cases for checker errors and timeouts
while runtime checks are paused. Keep the isolated checker tests.
GitOrigin-RevId: e29d3538e5c8fc943c1a265d75508ee904bfc166
## What changed
Allow callers to attach eligible Apps tool results as `tool_result` on
selected executed tool calls in Responses HTTP and WebSocket requests.
Keep text content and optional object-valued `structuredContent`, with
a 1 MiB per-result limit and a 15 MiB budget for the enriched message.
Attach results after request observers receive the original JSON. Keep
result IDs local and suppress WebSocket payload tracing for enriched
frames. Preserve the enriched HTTP body on retries to the original
endpoint and retry with the original JSON on HTTP 307 and 308 redirects.
Codex's default request construction supplies no result bodies.
## Testing
Add coverage for result eligibility and size limits, HTTP retry and
redirect behavior, and TLS fallback without forwarding the enriched
body to a redirect destination.
GitOrigin-RevId: c3f2f86f31349e40fcb699d48637c3cbbbe38837
## Why
Custom status lines previously depended on a feature flag in the TUI
client's configuration. When the TUI connects to a separate app server,
that flag can differ from the setting in the server's active profile.
## What changed
Add **Custom status line** to `/experimental` as an opt-in feature. Save
the toggle on the connected app server, restart the TUI, then use
`/statusline` to choose a provider.
Read `tui_extensions_statusline` from the app server's effective
configuration at startup. Keep that value when switching conversations
or reloading local status line preferences, so toggling the feature
takes effect on the next TUI launch.
## Testing
Add a menu snapshot and regression coverage for saving the toggle in a
server profile while preserving the active provider across a thread
change.
GitOrigin-RevId: 4025c9771e560d6d7b1e6bd97236bffc44201556
## Why
Proxy settings are bound to the command's execution environment. Preparing
them again at launch can overwrite the settings already bound to the
command, including credentials prepared for its shell.
## What changed
Have `SandboxManager` prepare the proxy environment and sandbox network
context together when the caller hasn't supplied a prepared route. Pass
the prepared environment through to the child and use the prepared
context for sandbox policy, including macOS Seatbelt's proxy ports and
Unix socket rules.
## Testing
Add regression coverage for preserving shell-specific credentials and
environment-bound proxy settings, reporting proxy setup errors for the
requested environment, and deriving Seatbelt rules from the prepared
route.
GitOrigin-RevId: 7a9b5822d8d53f6c93e6318a19222bf06abf0da0
## What changed
Use `Overlay::input_transcript` to determine which overlay handles
transcript interaction keys and which keymap context applies during
search and selection. Apply runtime keymap bindings through `Overlay`
so the app can refresh them without matching the transcript variant
directly.
GitOrigin-RevId: 3592ddb62a6bddb760e2923604faff41a28cd150
## Why
The sandbox denial check can spend 20 ms waiting for more output even
after the stream has closed and all denial context is available.
## What changed
Classify the buffered output immediately if the stream is already closed.
While the stream is open, wait up to 20 ms for new output or closure.
Register for the closure notification before rechecking the stream state
so closure during setup wakes the check.
## Testing
Paused-clock tests cover output closed before or during the check,
preservation of the timeout for open streams, and classification of
sandboxed and unsandboxed failures. The remote process-event suite adds
a direct sandbox denial case with a `process/closed` event.
GitOrigin-RevId: 1f3029055d70ff4cd63939564872fe5d37240a33
## What changed
Allow prompts longer than 4,000 bytes to pass `thread/sample` request
validation. Both `expectedTurnId` and `prompt` must still be nonblank.
GitOrigin-RevId: 59b97d351e2a02378b83aa9f2d4e649dd57169af
## Why
A TUI connected to an app server on another platform can receive workspace
roots that its own filesystem cannot represent. For example, a Windows
drive path from the server cannot be stored as a native absolute path on
a Unix client.
## What changed
Keep `runtimeWorkspaceRoots` as native path strings on the wire for thread
start, resume, and fork. Validate absolute paths on the server and store
the returned roots as `PathUri` values in the TUI. Use the session's roots
for active remote forks, including side chats, and preserve permissions
for those roots in the TUI's permission display.
## Testing
Cover thread startup with workspace and writable roots from another
platform, remote root retention through start, turn, resume, and fork,
and server rejection of relative roots.
GitOrigin-RevId: 1e9e3bff64a6e7ddadb941f16c4952c44724af54
## Why
A TUI connected to an app server on a different operating system could
fail to decode a workspace-write policy. For example, a Unix client could
reject a Windows writable root such as `C:\extra` because it is relative
under Unix path rules.
## What changed
Keep `writableRoots` as path strings on the wire. Use path URIs to
preserve server paths when displaying thread permissions, and forward
the original sandbox policy to the first turn of a child thread that
inherits a legacy policy. The app server validates that each writable
root is absolute on its host before enforcing a policy supplied to
`command/exec` or `turn/start`.
## Testing
Cover writable roots from another platform in permission profile
templates, their round trip through thread lifecycle responses, and
rejection of home-relative roots during enforcement conversion.
GitOrigin-RevId: 57365b977bfced6c6ee864a0e54f25e8f9d09981
## Why
A remote app server can report a working directory in a different path
convention from the client. Decoding a Windows drive path as a client-native
absolute path can make a Unix client reject the thread response.
## What changed
Keep thread `cwd` values as server-native strings in summaries, settings,
and start, resume, and fork responses. Preserve the JSON and generated SDK
types. In the TUI, store the session directory as a `PathUri` using the
server's path convention when available. Use that directory to match diff
and skill results and to display the project name in the terminal title.
## Testing
Add regression coverage for foreign-path response round trips, diff results
matched against a remote session directory, and terminal titles derived
from a Windows path. Verify that the server rejects a working directory
that cannot be encoded as UTF-8.
GitOrigin-RevId: 600f0b531939db4cd4ec884de166224082995e00
## Why
The denial reconsideration feature only applied to standalone reviews, so
attached Guardian reviews could deny an action after a single verdict even
when the feature was enabled.
## What changed
Move denial reconsideration into the shared verdict runner so attached
reviews can also take one additional sample on a denial. Keep the first
denial and its rationale if the second sample runs past the review deadline.
## Testing
Extend the app-server integration test to verify that attached reviews
sample denials exactly twice with identical input, can approve on the
second sample, and retain the first denial and its rationale on timeout.
GitOrigin-RevId: 06cc730d08dc755863f715362328aa48d15678f0
## What changed
Set `features.guardianv3.message_board_in_memory = true` to give each
new or cleared root thread an in-memory SQLite board. The housekeeper
and reviewer share the board until the last handle closes. The reviewer
can read evidence and update its own subscriptions. On-disk storage
remains the default.
With in-memory storage enabled, the attached reviewer is unavailable
on resumed roots because evidence intake starts at the end of history
and a fresh board has no earlier evidence.
## Testing
Exercise evidence catch-up and later post delivery with both storage
modes. Check that only the on-disk mode creates a database file, the
reviewer cannot update channels, and a cold resume skips evidence intake
in memory mode.
GitOrigin-RevId: 338f44720fca510b2baf40fd4b3a4b30245d4fc2
## Why
Guardian V3 uses fixed guidance for grouping evidence into board channels
and deciding when to retrieve more evidence. Longer routing instructions
also leave less room for evidence in the model's context window.
## What changed
Under `features.guardianv3`, add `housekeeper.routing_instructions` and
`reviewer.retrieval_instructions` to customize those strategies while
preserving the routing format and the reviewer's board and authorization
rules. Blank or omitted instructions use the built-in guidance.
Add an optional `max_instruction_tokens` cap that validates each custom
prompt separately using an estimated token count. Ignore both prompts and
the cap in project config. The `housekeeper.batch_timeout_ms` setting
controls the per-batch routing timeout and defaults to 90 seconds.
Size routing batches to fit the model's input window after accounting for
the prompt and response schema. Route the largest fitting prefix of whole
evidence records within the tool-output budget and leave the rest pending.
## Testing
Cover prompt validation, project config filtering, feature toggle merging,
and default retrieval guidance. Exercise custom prompts in model requests
and verify that routing reduces a batch under context pressure or stops
without advancing the cursor when even one record cannot fit.
GitOrigin-RevId: 83b3fcd23c680e90d2b2aea82a4a290633729658
## Why
Cloning a `ConfigLayerStack` copied every layer's TOML data, even when
the new snapshot only needed to replace one layer.
## What changed
Store immutable layer entries in `Arc` so snapshots can share them.
Replacing a user or session layer updates only the new snapshot's list.
GitOrigin-RevId: aa32fa5e3864c60743c0cad6922b274d55abbda3
## What changed
Mark `mcp_lazy_stdio_startup` stable and enable it by default. When a
tool catalog is already cached, Codex can expose tools from an optional
stdio MCP server and defer starting the server until the first tool
call. Required servers still establish a live connection at startup.
## Testing
Exercise lazy startup with the default configuration in the tool-cache
test and explicitly disable the feature for the eager-start control.
Update the code mode and working-directory tests to proceed without
waiting for an optional server when its catalog is cached.
GitOrigin-RevId: a65d83fd1a4c141dba3c10e68b138539aa0a44f0
## Why
When a file preview fails, the generic error can leave users guessing
which file failed, especially when the sidebar truncates the tab label.
## What changed
Show the filename and directory in the failed preview. Give users
specific guidance for missing files and permission errors, and retain
the error details for other failures. If the file link cannot be
resolved, include the original path in the chat error.
Preserve typed filesystem RPC errors so the preview can classify
failures from `fs/readFile`, and strip the server's diagnostic payload
before the errors can reach TUI logs.
## Testing
Cover narrow-pane error rendering, missing-file and permission error
classification, unresolved links, and diagnostic payload removal for
remote file reads.
GitOrigin-RevId: 1db35c831bb112d67e8c0171a85a20d02cc15a08
## Why
A connected account or app can choose an approval reviewer, but that
setting applies across its tools. Users may want to review calendar
event creation themselves while keeping automatic review for other tools.
## What changed
Set `approvals_reviewer` on an individual app tool in `config.toml`:
```toml
[apps.calendar.tools.calendar_create_event]
approvals_reviewer = "user"
```
Codex matches the tool by raw name first and falls back to its title.
The tool's reviewer takes precedence over the connected account, app,
app defaults, and session settings, subject to managed requirements.
This applies to tool-call approval prompts and MCP approval requests
that match a verified app tool invocation. The app-server
`config/read` response also exposes the per-tool setting.
## Testing
Extend coverage for reviewer precedence, tool title fallback, managed
review requirements, tool-call approval routing, strict MCP elicitation,
and app-server config reads.
GitOrigin-RevId: c92bd39b9e708dada9d314c19a446b4c580edf91
## What changed
Reserve `[permissions.credentials]` in `requirements.toml` for shared
credential policy. The table currently accepts no settings and should be
omitted. Empty tables and legacy profile definitions with profile fields
produce a migration error that tells administrators to rename the managed
profile and update references. Profiles named `credentials` remain valid
in `config.toml`.
Accept an empty `[permissions.<profile>.credentials]` table in named
profiles in both files and expose it in the `config.toml` schema.
## Testing
Add regression coverage for rejecting direct and inherited selection of a
user profile through an empty managed credentials table, preserving MCP
configuration reads, and enforcing network policy inheritance checks for
legacy managed profiles.
GitOrigin-RevId: 33dcca30b37d3f07ce670967342199f5302e1d98
## Why
The `incomplete` status alone gives no indication of which timing dependency was missing or which operation prevented capture.
## What changed
Emit deduplicated `critical_path_incomplete_reasons` in turn analytics for incomplete captures. Reasons cover unsupported Code Mode and agent operations, unattributed reviews and user waits, missing turn starts, and forced teardown, with an `unclassified` fallback. External tools that share a built-in name can still invalidate capture without being classified as the built-in operation.
During interruption, use the task's join result to distinguish forced teardown from normal completion so a task that already finished can still report a complete path.
## Testing
Add coverage for analytics serialization, concurrent reason deduplication, tool name collisions, and interrupted tasks that finish normally or require forced teardown.
GitOrigin-RevId: fab9aa1ff881997a34dcf75adc5638133cedc7fe
## Why
If a provider keeps an SSE connection open after reporting a failure, Codex
can hit the idle timeout and lose the original error and its retry advice.
## What changed
End the SSE stream immediately on `response.failed` or a recognized
`error` event. Classify statusless quota, plan usage, invalid prompt, and
misalignment errors consistently across both event forms. Preserve
`Retry-After` for overload and capacity errors, preferring error-level
headers over event-level headers when both provide valid advice.
## Testing
Add SSE regression tests that hold the connection open and verify immediate
error delivery, terminal error handling, and retry delays. Extend WebSocket
coverage for statusless errors received before the close handshake.
GitOrigin-RevId: 69afd1d3b18ca3139e9b7ad98ae1481a432179f0
## Why
When the Responses API sends a policy rejection in an `error` event
without an HTTP status, the SSE client can wait until its idle timeout
to report the failure.
## What changed
Recognize `bio_policy` and `cyber_policy` in the shared terminal error
parser so both SSE and WebSocket clients surface the corresponding
policy error. Preserve the provider's message and use a default when
it is missing or blank. End the SSE stream as soon as the error arrives.
## Testing
Add SSE tests for both error codes, including when the stream stays
open, and WebSocket cases that verify both errors surface without a
close handshake.
GitOrigin-RevId: 1b46b6557a39a61a1bb10bdd0d8ede48ecd6fa13
## Why
Running each helper through `codex sandbox` keeps a separate Codex
supervisor process alive for each helper. A shared launcher lets one
supervisor manage multiple helpers concurrently.
## What changed
Add a launcher mode that multiplexes helper I/O and exit status over a
newline-delimited JSON protocol on stdin and stdout. Each helper uses
the host sandbox setup with its own configuration and network proxy.
The launcher applies backpressure to helper I/O, drains buffered output
on exit, and stops tracked helpers when the controller disconnects.
## Testing
Add integration coverage for per-helper filesystem isolation, stdin
backpressure, buffered output after helper exit, and controller
disconnect while output is blocked.
GitOrigin-RevId: a7f75fdedbe0928ff5b93a412c7223371d0f321a
## What changed
Split Seatbelt command startup from waiting for the command to exit.
The startup helper can pipe stdin, stdout, and stderr and returns a
handle that keeps the network proxy alive while the caller manages the
child process.
The sandbox CLI still inherits stdio, waits for the child, reports
Seatbelt denials when requested, and propagates the child's exit status.
GitOrigin-RevId: 6a52a1a539bc2861b2357e9e60fab61ee65265fb
## Why
A parent turn can acknowledge a child agent's final reply while a model
request is in flight. If the parent is interrupted before consuming the
queued reply, turn cleanup can discard it.
## What changed
Record queued agent messages in conversation history during interruption
and flush the rollout before emitting `TurnAborted`, even when the
interruption marker is disabled.
## Testing
Add a regression test that interrupts a parent while a child's final
reply is queued. The test checks that the reply is persisted when
`TurnAborted` arrives and appears exactly once in the next model request.
GitOrigin-RevId: 5bd828c4101942fa4fe7ba5040355a8244f02018
## Why
Using `uv run --frozen` keeps dependency resolution fixed but does not require
installed packages to match the hashes in `uv.lock`.
## What changed
Run Ruff for the Python SDK and repository scripts, and regenerate Python SDK
types during repository schema refreshes, through a shared runner. It exports
the selected locked dependencies, installs them into a temporary virtual
environment with `uv pip sync --require-hashes`, and runs the tool without
resyncing the environment.
## Testing
Update tests to check the formatter invocations and verify that only repository
schema refreshes invoke Python type generation through the runner.
GitOrigin-RevId: 4e84da5d227eb99c24efb9a1cc7647af82105536
## Why
The slash command menu helps users find commands, but leaves them to
recall fixed arguments such as `on` and `off` for `/raw`.
## What changed
Show prefix-filtered suggestions for the first argument of supported
slash commands. For example, type `/mcp lo` and press `Tab` to complete
`/mcp login`. `Enter` and configured submit shortcuts still submit the
draft as typed.
Give mention completion priority and limit argument suggestions to
commands available in the current thread and connection state.
## Testing
Add tests for popup rendering, argument replacement, submit shortcuts,
and changes in thread availability and connection state.
GitOrigin-RevId: 8682c323064457dd9307b0a1520469011a8df9f3
## Why
The local native voice prefix build can run eight jobs in parallel.
Bazel needs to account for those jobs when scheduling other local
compile actions against the same CPU budget.
## What changed
Use the same job count for the native build and the macOS
`VoiceNativePrefix` action's CPU estimate.
GitOrigin-RevId: 0bda242b98bae8b3f3c412c95c85e398a0dfc9b2
## Why
The MCP tool call future reserves space for the large config reload
future even on ordinary calls that never reload configuration.
## What changed
Pin the reload future on the heap after successfully persisting a tool
approval. Ordinary MCP calls no longer carry the inline storage for it.
GitOrigin-RevId: a883f7619f520e730dda139d967c6a0f945b5df2
## Why
Read-only chats offer a Left Arrow shortcut to the command center when
agent navigation is available. Chats blocked by model provider errors
were missing that shortcut.
## What changed
Share notice rendering and shortcut availability between provider
errors and read-only threads. Show `← command center` on provider error
notices when the shortcut is available, and open it on a plain Left
Arrow press even when offline.
## Testing
Add a regression test that checks the shortcut hint, verifies that
repeat events leave the notice open, and confirms that opening the
command center preserves the draft both online and offline. Update
provider error snapshots to cover the new hint, including at narrow
terminal widths.
GitOrigin-RevId: be2ce80cade02c84baeff7fd48fa8973f0dcc1dc
## Why
Conversation search results can point users to saved transcripts. Users
need to be able to follow those links without leaving their terminal session.
## What changed
- Make Markdown links such as `[Review notes](codex://threads/<id>)`
open the linked conversation from chat and transcript views. In the
resume picker, follow the link to another transcript preview.
- Resolve nested agent links through their owning session and select the
requested agent. Show archived conversations in read-only mode and
let users explicitly reopen them.
- Include the Markdown link format in thread search results, including
archived results.
## Testing
Add coverage for thread link parsing and activation, nested agent
navigation, archived thread reopening, and mouse capture during
transcript preview transitions.
GitOrigin-RevId: 40a39c43acf643b97e066ba663aefcf9cda0bc81
## What changed
Update `mxc-sdk` and use its V1 API to launch commands in a
`ProcessContainer` with inherited stdio. Build the V1 request from Codex's
filesystem, network, UI, and environment settings.
Cache the SDK's ProcessContainer availability probe and surface failures
to create the security environment at launch. Let the SDK reject deny
paths the host cannot enforce and drop Codex's direct `flatbuffers`
dependency.
## Testing
Update the request-building tests to check the V1 filesystem and network
policies, including loopback access for proxied commands.
GitOrigin-RevId: 0fb9955b5df847595c142f5fd1da7a0cc83e1c28
## Why
Generic quota errors hide whether the project or organization spend limit
blocked a request. Reporting the scope tells users which limit to check.
## What changed
Recognize API key, project, and organization spend limit errors across
HTTP, SSE, and WebSocket responses. Show a message that names the scope and
treat the error as non-retryable, even when the provider sends
`Retry-After`. Apply the existing usage-limit handling to goals and
compaction.
Expose distinct `CodexErrorInfo` values in the app-server protocol and
generated bindings so clients can identify the limit in live errors and
failed turn history.
## Testing
Extend the transport tests to cover all three scopes and verify that they
stop retries. Extend the app-server test to check that the error survives
`thread/read` and that a subsequent turn can succeed in the same thread.
GitOrigin-RevId: 03341f7a78daa7540e7baa519f1a29ec07e34509