## 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
## 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
## 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
## Why
A thread can reserve a turn slot and assign a turn ID while it still
waits for host admission. Callers need to distinguish a pending turn
from one cleared to execute.
## What changed
Add `turn_admission_state()` to report `Idle`, `Pending` with an optional
turn ID, or `Admitted` with a turn ID in a single snapshot. Host-managed
turns become admitted after a grant is installed. Native turns are
admitted synchronously, including when no execution guard is needed.
The current slot retains its admitted state through finishing.
Reject superseded submissions before they can overwrite an owned slot,
and verify that a host grant still belongs to the current turn and task
before recording admission.
## Testing
Cover the admission state while a host decision is pending, after an
interrupt, during execution after a grant, and after the slot returns
to idle. Cover native admission without a host guard.
GitOrigin-RevId: 0633dc036aef99433505559c92b0b1b26a023352
## Why
Applying client context at submission time lets input stopped by a hook
affect the conversation. A queued prompt that is later blocked can also
supersede the context attached to an earlier accepted prompt.
## What changed
Keep each context update with its submitted input and apply updates in
delivery order after the input passes its hooks. Preserve context-only
submissions when a turn is suspended for host handoff before inference.
For experimental `additionalContext` on `turn/start` and `turn/steer`,
omission or `null` keeps the current set. A supplied map replaces it on
delivery, and `{}` clears it while preserving conversation history.
## Testing
Add regression coverage for context on prompts stopped by hooks, context
on accepted queued prompts, context-only host handoff, and context
delivery when continuing an idle thread.
GitOrigin-RevId: 160f4f90d9aebf5eb3ea4a939c67265a1c6422da
## Why
A remote exec-server connection could fail during setup if the transport
closed before the client received the initialization response. Callers
waiting for readiness received the failure even if a new connection
could succeed moments later.
## What changed
Share retries among callers during startup, reconnect, and connection
refresh. After a retryable transport or initialization failure, use
backoff and allow new attempts for up to five seconds. Attempts already
underway can finish after that window.
Keep the registry's existing retry policy and reuse the provisioning
deadline across transport retries.
## Testing
Add regression coverage for shared startup recovery after a WebSocket
closes during initialization, registry retry limits and authentication
failures, and child-process cleanup when stdio initialization is
cancelled.
GitOrigin-RevId: 56004badb67f4e5df8d939f2bc6cdfa46246fdb0
## Why
Large file reads over stdio previously allocated both a base64 string
and a complete JSON response before writing to stdout.
## What changed
Keep file contents as bytes until the stdio writer encodes them
directly into the newline-delimited JSON response through a bounded
buffer. Clients still receive the same `dataBase64` field.
## Testing
Compare streamed output byte for byte with the eagerly encoded
response for empty files, inputs that require base64 padding, and
files larger than the write buffer. Check that JSON-RPC conversion
preserves the request ID and base64 payload.
GitOrigin-RevId: 730f201f0905fd15e32b6e9c5b2ef02ca21c7532
## Why
When Windows security policy blocks the sandbox account from signing in,
commands cannot start. The runner error previously gave users only the
failing API call and the numeric error code.
## What changed
For `ERROR_LOGON_TYPE_NOT_GRANTED` (1385), explain the policy denial and
point users to the “Allow log on locally” and “Deny log on locally” settings.
Advise users on managed PCs to contact their administrator.
## Testing
Add a regression test that checks the error explanation and verifies that
the denial does not trigger a sandbox credential refresh.
GitOrigin-RevId: b638bf3d103dc4aec72f2f9c13cb2c8825594e96
## What changed
Stop collecting cumulative MCP tool attribution, sending it in Responses
API request metadata, and writing it to rollout checkpoints.
Use `model_search_state` for search provider history in new rollouts. When
reading older rollouts, decode `mcp_attribution` only to determine whether
Search MCP may have been used. Treat malformed or error attribution as
possible Search MCP use so native search fallback stays disabled.
## Testing
Add a history test that distinguishes legacy Search MCP use, an explicit
record of no use, and missing attribution.
GitOrigin-RevId: a145b5b6b7d2f423d989af10623ef21120f49d4d
## Why
Guardian inherits the actor's inference provider by default. Hosts that run
actors on a different provider need to route Guardian reviews independently
and resolve reviewer policy and model capabilities from the Guardian provider.
## What changed
- Share the selected provider and its model catalog between asynchronous
scoring and blocking approval reviews. Use the provider's preferred
reviewer and resolve policy from managed requirements or reviewer model
metadata.
- Keep Guardian review history independent of actor compaction when the
host selects a provider. Preserve inherited routing when no provider is
selected.
## Testing
Add integration coverage for separate actor and Guardian endpoints, catalog
isolation when both share an endpoint, and routing after resuming a compacted
thread.
GitOrigin-RevId: 1eb15421f746a58eefe27257e86d948de31bcf86
## What changed
Choose the full config or shell environment filter schema inside the
diagnostics module. Config loaders call the helper for the validation
that failed without passing a deserialization type or the
`config.toml` filename. Both helpers use the same layer traversal and
source location reporting.
GitOrigin-RevId: 5dcc7984b907e3769904c303cd08577c6faf4769
## Why
A Guardian policy refresh could leave a thread using its previous restrictions
if the new policy disallowed its current model. A refresh could also report
success after its managed policy source changed before publication.
## What changed
- Use the app server's configuration manager to load Guardian policy from
current local and managed configuration. Report an error when the policy
source changes before publication or a live thread rejects the update.
- Apply updated reviewer and model restrictions even when they block the
current model. Keep automatic work queued while the model is blocked and
wake it when a later refresh permits it. Allow a new turn to supply a
compliant replacement model.
## Testing
Regression tests cover policy changes during thread startup and live refresh,
queued work resuming after a blocking policy is lifted, and updated policy
text reaching Guardian reviews without reconnecting MCP.
GitOrigin-RevId: c7d3e119aa409342cc2fa18946ce2b6a4392e0e3
## Why
Sidebar previews load a snapshot of the file when opened, so edits on disk
leave the open tab showing stale content.
## What changed
Watch each previewed file’s parent directory through the app server so the
preview refreshes even when an editor saves by atomically replacing the file.
Poll every three seconds when a watch cannot be registered, and resubscribe
when reconnecting to the same backend.
Preserve the text preview’s reading position across reloads, including when
the file temporarily becomes unreadable and then returns.
## Testing
The sidebar test covers atomic saves and recovery after moving a directory
away and back. It checks that the tab shows updated content at the existing
reading position.
GitOrigin-RevId: d5f7507d1a81a118fb10a0febf5e274c18f19d81
## Why
On macOS, `lsof` can warn about inaccessible mounts even when its search
is scoped to the releases directory. Treating every warning as an
inspection failure can prevent the installer from pruning unused releases.
## What changed
Keep `lsof` matches when stderr contains only complete mount warnings
for paths outside the releases tree and its ancestors, on devices
different from the releases directory. Continue to reject warnings
that could affect release inspection, incomplete warnings, and
unexpected errors.
## Testing
Extend the mocked macOS `lsof` test to verify that an unrelated mount
warning preserves matches and that same-device, ancestor-mount,
truncated, and mixed diagnostics fail inspection.
GitOrigin-RevId: 006e2a38335c33ce7c974f74d3bb871d818fdd1f
## Why
An unsupported `\underbrace` leaves the display equation as LaTeX source,
so readers have to interpret which terms each label groups.
## What changed
Render `\underbrace{expression}_{label}` with a Unicode brace that spans
the expression's terminal columns and a label centered below it. Keep
surrounding math aligned with the expression. Inline math, unsupported
arguments, and layouts that exceed the available width still use the
existing fallback.
## Testing
Add a snapshot for labeled Boolean clauses, short expressions, and labels
wider than their expressions. Check fallback for inline, malformed,
nested, multiline, and over-width cases.
GitOrigin-RevId: 8fbe92d512d06c73cf21247343ad869743bebd0c
## What changed
Request emoji presentation for the cloud marker in thread labels.
Preserve the emoji variation selector immediately after the cloud
symbol in Unicode terminal titles and keep GNU Screen titles ASCII.
## Testing
Update rendering snapshots for the task overview, side panes, mentions,
resume picker, and thread identity displays. Extend the terminal title
test to cover the cloud marker in both title encodings.
GitOrigin-RevId: 15959a0760f63a45d8fff917df2e008cda7536a5
## Why
A serving probe that reports no review needed can bypass async scoring.
Keeping the async path active lets Guardian compare the two signals
while using the existing approval policy.
## What changed
Treat streamed review flags as observations. Match each flag to its
response item, carry the enclosing item's flag into Code Mode tool
calls, and discard the flag when a pre-tool hook rewrites the payload.
Emit correlated `codex.guardian_probe_comparison` logs for tool calls,
async classification outcomes, and synchronous review results.
## Testing
Update integration tests to expect async scoring even when a probe
reports no review needed, and verify that Code Mode retains the probe
across yield and resume.
GitOrigin-RevId: 715f56ba4a82d544ce59f0291bcd1a84dd2daa51
## Why
A fixed gap cannot keep two statusline groups at opposite edges as the terminal width changes.
## What changed
Set `justify: "between"` on a root `row` to distribute spare footer columns between its items on each line, in addition to the configured `gap`. Nested rows size to their content within the available width, so they can keep related fields together.
Use `justify: "start"` to pack items at the leading edge with the configured gap. Both explicit modes group adjacent bare strings into one item. Separate `text` or `row` elements can be positioned independently. Omitting `justify` preserves the existing gaps between authored children.
## Testing
Add renderer tests for edge alignment during resizing, spacing on wrapped lines, and root versus nested rows. Extend the row decoding tests and the TypeScript contract fixture to cover `justify`.
GitOrigin-RevId: 3319e688f3adfe6d35709ef279345f1db3eb9693
Return a pinned, boxed future from `try_load_managed_auth` so callers
store a pointer to the credential loading future in their async state
machines instead of embedding the full future.
GitOrigin-RevId: 898e4877cc197720d88fc36a566533c5594f4f38
## Why
Correlating a subagent's creation, turn attempts, and stop requests
helps explain what happened when those actions span workers.
## What changed
- Emit structured events and counters for successful spawns and accepted
`close_agent` and `interrupt_agent` calls. Count accepted stops even
when the target is already idle or unloaded.
- Track initial, follow-up, and resumed turn attempts for spawned
subagents. Record each start and at most one outcome per attempt:
completed, failed, interrupted, or suspended.
- Use thread, turn, and call IDs to correlate structured events while
keeping those IDs out of metric labels.
## Testing
Add coverage for lifecycle counts, duplicate outcomes, stop handling,
and event correlation across workers. Improve the Windows elevated
sandbox test for an approved `git pull` by provisioning the sandbox
before the turn and reporting setup or launch failures with diagnostics.
GitOrigin-RevId: bc1190302e1dffbdd79c7ac984b6debe1dac4a65
## Why
The stalled-helper test waits 10 real seconds to check the timeout.
## What changed
Use Tokio's paused clock and a named pipe to keep the helper blocked.
Assert that it reports the expected timeout after exactly 10 seconds
of virtual time. Keep executable paths with spaces covered by a
separate test.
GitOrigin-RevId: ceabf0697576c7944708e467dd0f1a33fd644f42
## Why
Steering can cancel a paused mock HTTP stream, realtime handoff and turn
events can arrive in either order, and streaming tools can run before the
response reports token usage. Tests that assume a fixed sequence can fail
depending on timing.
## What changed
- Pause the hooks test at assistant message completion so both queued prompts
enter the same batch before the turn resumes.
- Track the handoff and turn events in one pass, waiting for the matching
turn to complete on the unblocked path.
- Call `get_context_remaining` during the compaction fallback and assert
zero remaining tokens using the preceding response's usage.
GitOrigin-RevId: ec8a108517c819d7087681e8e2c7b5b57f4b341e
## What changed
Use `esc close` to show how to combine the Escape binding's display
label with the action text and use the shared shortcut styling in
views and mockups.
GitOrigin-RevId: 0bb0dc94e503932443076dbe2495e5494e3df5b2
## Why
An overflowing hook total could send a partial charge to the host, and
an overflow in native accounting could leave the posted balance infinite.
## What changed
Reject overflowing hook totals before reporting usage. Check both the
combined provider and hook charge and the cumulative rollout balance
before posting, preserving the previous balance on overflow. Native
budgets with limit enforcement enabled still stop new work on overflow.
## Testing
Update the hook overflow integration case to verify that the response's
tool is blocked and the host receives no usage report.
GitOrigin-RevId: 2ac80a6aa1d857924a8807df7bb70c6b7c107cd2
## What changed
Set `GN_ARGS` in the rusty_v8 release and V8 canary workflows so
`mksnapshot` can load the ICU data file from the build directory.
Code mode registers its own copy of the ICU data at runtime.
GitOrigin-RevId: a80adca7ce27906b31ae95c055f99b514cac5d9f
## Why
Process lifecycle handlers could overwrite each other's updates by reading
and replacing the entire state. For example, a rejected stdin write could
restore an older snapshot after the output collector recorded an exit code.
## What changed
Apply lifecycle transitions in place under the watch channel's write lock.
Rejected stdin writes and confirmed termination only mark the process as
exited, preserving any exit code already reported by the executor.
## Testing
Regression tests cover both closed stdin and unknown-process responses.
They verify that subsequent lifecycle updates preserve the exit code and
sandbox denial recovered from the final read, and that repeated calls to
`fail_and_terminate` preserve the first failure message.
GitOrigin-RevId: f090c0860c86b6e668c31d122d986ea4f4a119b6
## What changed
Apply the same Unicode combining tilde as `\tilde` when the
`\widetilde` argument is a single grapheme.
## Testing
Extend the Unicode math snapshot to cover both `\widetilde{I}` and
`\widetilde I` in fraction numerators.
GitOrigin-RevId: e6976f998bb0955ba9c73117bd19dd814b07399a
## Why
Local stdio discovery needs to accommodate legacy servers that return an
empty response to `server/discover`, take longer to initialize than the
discovery watchdog allows, or require `initialize` as their first request.
## What changed
Mark `mcp_connection_sharing` stable and enable it by default. Treat an
empty discovery response as an unsupported method and let legacy
initialization use the configured startup timeout. Give legacy restarts
a fresh timeout and keep modern version retries within the original
deadline.
## Testing
Cover empty discovery responses, slow initialization on the original
connection, and restarts after ignored or rejected initialization.
Explicitly select legacy mode in tests that depend on legacy behavior.
GitOrigin-RevId: 04d87ddfe02fac8491f879ce420bf294dc725128
## Why
The terminal renderer already supports line breaks in flowchart node
labels. The same syntax in an edge label causes the diagram to fall
back to source text.
## What changed
Treat `<br>`, `<br/>`, and `<br />` as line breaks in edge labels.
For example, `A -->|"Review<br/>order"| B` renders the label on two
lines. Reserve space for each line and preserve blank lines without
erasing edge connectors.
## Testing
Add snapshots for all four layout directions and update the terminal
Markdown snapshot to include a multiline edge label. Test blank lines
and terminal width limits.
GitOrigin-RevId: 277525d92c6c1f105bc34516893c67eccc22a22c
## Why
A stalled WebSocket write can leave the remote client's command queue
full. Shutdown can then wait indefinitely to enqueue its command,
before it reaches the timeout that allows it to abort the worker.
## What changed
Apply `SHUTDOWN_TIMEOUT` to enqueuing the shutdown command so the client
can reach the existing worker abort fallback even if the queue stays
full.
## Testing
Add a paused-time regression test that keeps the queue full with a
stalled worker and verifies that shutdown returns and the worker has
finished.
GitOrigin-RevId: d7c1a90442cd2619893144b20e43f6d87d5caa94
Pass the host's existing `&[UserInput]` into `TurnInputContext` to avoid
cloning the input when building extension turn items. Use the borrowed
slice directly for skill mention detection and shadow selection.
GitOrigin-RevId: f4983b584830e481d914f0c9aa1e39e78b965a19
## Why
Automatic mailbox wakes can start new turns while the app-server is
draining or has paused turn admission. Native child results still need
to reach the parent during drain so they can survive a daemon restart.
## What changed
- Require a turn admission permit for ordinary automatic mailbox wakes
and hold it through turn registration. Retry queued work when a
temporary pause ends. Explicit follow-ups and native child results can
still wake the parent during drain.
- Let `thread/inject_items` queue plain-text agent messages for native
child threads when native tools are enabled. Injected mail follows the
ordinary wake rules.
- Extract the remote app-server client, shared event and request types,
and WebSocket compression into `codex-app-server-remote-client` so
callers can use them without linking the app-server runtime.
## Testing
Cover delivery of queued mail when admission reopens, injection into
native child threads, and recovery of a child result after a daemon
restart.
GitOrigin-RevId: 4c5ceeca8829c2612cc2b6b74c03d0c7677a9244
## Why
Namespace-wide guidance can repeat on every entry in flat Code Mode listings. The existing prefix limit covers only reachable `functions` tools, leaving indirect namespace guidance outside the budget.
## What changed
- Add `builtin_tool_namespaces` to put guidance on namespace headers in Code Mode prompts and tool search responses, including headers shared with client tools. The selector applies to namespaces with a registered built-in tool and is omitted from flat listings. Overlapping selectors must agree after trimming.
- Validate all four prefix maps together against the selected model's `description_prefix_budget_bytes`, which defaults to 512. Count each trimmed value once in UTF-8 bytes, including unused selectors. Exclude keys, paragraph separators, and rendered copies.
## Testing
Cover shared headers, flat listings, and conflicting selectors. Exercise the default budget boundary with multibyte text and verify that a model can raise the limit.
GitOrigin-RevId: 1570c23ea1dbad6041cc8e48d0dc2b77f92596c7
Take the payload from the successful tool result and pass it directly
to the post-tool-use hooks.
GitOrigin-RevId: bb7dbe82bbc7b565257b94a0473476326e60db12
## Why
Fallback lookups repeatedly parse the embedded model catalog even though
its contents are fixed for the lifetime of the process.
## What changed
Parse the bundled catalog once on first use. Borrow the shared catalog
for fallback lookups and copy it when building an owned snapshot or
merging remote models.
## Testing
Extend the API key discovery test to verify that a bundled model lookup
applies a request's `base_instructions` override and that a subsequent
lookup returns the original bundled model.
GitOrigin-RevId: 27c90b65667724312673c5d5ae01a3fc6b5b1416
## Why
Dividing total handler time by the call count gives a per-call mean
without averaging histogram export batches.
## What changed
Record `codex.exec_command.duration_total_ms` and
`codex.exec_command.calls` for built-in `exec_command` handler runs,
including failures. Measure from handler entry through command exit or
the first yield, including shell setup and startup. Exclude calls rejected
before the handler runs and retain tags such as `shell_snapshot_mode`,
`success`, and `product_sku` when available.
## Testing
Cover Statsig export of both counters and check that their counts and
duration totals match the tool duration histogram for eligible calls
within each tag set.
GitOrigin-RevId: 4bf6dc628bca5758999bf0ed5f67051f870a61e8
## Why
Clients need to distinguish a caller who must enroll in Daybreak from a
model that does not support it. The list of accepted access programs
alone cannot express that distinction.
## What changed
Carry the server-resolved status for each caller and model from the
model catalog into `model/list` as `availableAccessPrograms.daybreakAvailability`.
Update the JSON schemas, TypeScript bindings, and Python SDK to expose
the field.
Rust decoders use `default` for missing or unrecognized statuses. The
Python SDK also defaults missing statuses and preserves new strings
from newer hosts.
## Testing
Cover catalog decoding, app-server response serialization, and Python
SDK round trips with known, missing, and future status values.
GitOrigin-RevId: c1e5ddef68fd19b25e583bb6996a93fd78ab9d18
## Why
A thread can start while managed Guardian policy is being refreshed. Startup
and refresh need to coordinate so the thread does not register with policy
that the refresh has already superseded.
## What changed
Let hosts provide a `GuardianPolicyLoader` to `ThreadManager` for startup
and on-demand refresh. Pause thread registration while a refresh loads and
publishes policy. If publication overtakes a thread's startup configuration,
reload Guardian policy before registering the thread.
Apply the published policy to live threads concurrently. Once published, the
updates continue even if the refresh caller is canceled. Return an error if
any live thread rejects the update.
## Testing
Add regression coverage for an idle thread receiving the update while
another thread holds its session lock, and for reporting a live thread's
rejection of invalid Guardian configuration.
GitOrigin-RevId: ca0cfa2a30f0d45c4ac5ded3400e0e18177ede1d
## Why
Attached reviews used fixed evidence limits even when elastic budgeting
was configured. This could reject a pending tool call whose exact
arguments would fit within the review request's input budget.
## What changed
Use the configured budgeting policy to prepare the pending action and
permissions for attached reviews. With elastic budgeting enabled, check
whether the exact call fits when enforcing the final request budget.
## Testing
Add a regression test for a tool call that exceeds the fixed evidence
limit. Elastic budgeting rejects it when the request budget is too small
and preserves the original call when it fits.
GitOrigin-RevId: 42cc4a8682a98badfe6be95434703500403e7118
## Why
Boxing the thread startup future at each call site makes each caller
compile its own copy of the future.
## What changed
Return a `BoxFuture` from `spawn_thread` and move the startup logic into
`spawn_thread_inner`. Thread start, resume, and fork paths now await
`spawn_thread` directly.
GitOrigin-RevId: 5004651423551e173b1cc98b185c6a1dc2bc097e
## What changed
Remove the legacy framed stdio protocol and its client and server.
Local Codex launches the standalone host with `--listen grpc+stdio://`,
which is also the host's default. The `stdio` and `stdio://` aliases
now select gRPC over stdio. The `features.code_mode_host_grpc` setting
is deprecated and ignored.
Carry execution trace context into gRPC tool callbacks and
notifications. Reject oversized execute requests before sending them
so an encoding failure does not appear as a connection reset.
## Testing
Exercise gRPC callback cancellation, trace context across overlapping
yielded cells, and isolation of tool preload failures between sessions.
Check that both values of the deprecated feature setting are ignored.
GitOrigin-RevId: f5faff3901dc60958627f677f50cfad834291b69
## 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