## What changed
- Replace Rust `1.99.1` pins with `1.95.0` across Cargo, Bazel, CI, release workflows, and Windows setup, and update the Bazel lockfile.
- Adjust Rust APIs, borrowing, and lint-related code for the pinned toolchain, and box MCP tool dispatch to bound compiler async-layout query depth.
- Update the halfwidth sound mark snapshot and allow optional symbol hash suffixes in the code mode host package smoke test.
GitOrigin-RevId: 75460c3d0465dc601811e619bce373a4f7ff2912
## What changed
Add session options for client- or server-owned output truncation and optional `max_output_tokens` budgets for wait and terminate observations. Introduce `TerminateRequest` and update session implementations and callers to use it.
Extend the stdio and gRPC schemas with optional truncation settings and budgets, and define the `bounded-output-v1` capability. Existing sessions retain client-side truncation; providers reject server mode by default. This change defines the contracts without enabling server-side truncation.
## Testing
Extend protocol serialization coverage for `outputTruncation: "server"` while preserving existing wire shapes when optional fields are absent.
GitOrigin-RevId: 22145897ea16d385c5ba9e7549109f7a669fceb4
## What changed
Extract patch parsing, verification, and permission assessment into request preparation helpers used by the tool handler and intercepted shell patches. Execute the prepared `ApplyPatchRequest` through the existing runtime and derive auto-approval status from its approval requirement.
Move approval action construction onto `ApplyPatchRequest` and update the existing approval tests to use the new helpers.
GitOrigin-RevId: 7f07d38f0dbf2a971c94b897281651b7a174fd05
## What changed
Introduce `PreparedPermissionRequest` to encapsulate argument parsing, path resolution, permission normalization, and approval action construction. Pass the prepared request, including the selected environment ID, into session permission handling.
## Testing
Extend the selected-environment path resolution test to assert that the prepared approval action carries the expected environment, reason, and resolved permissions, matching the emitted permission request.
GitOrigin-RevId: ebd34fad0e5d4c9f98330d17a6254325526b8c78
## Why
Commands that fall back without using a shell snapshot should remain associated with their configured snapshot mode in telemetry.
## What changed
Add a `shell_snapshot_mode` telemetry tag to `exec_command` with values `disabled`, `v1`, or `v2`. Give `v2` precedence when enabled. The tag records configuration, not whether a command actually used a snapshot.
## Testing
Add parameterized coverage for all four combinations of snapshot feature flags using a non-login command, which cannot use V2 snapshots.
GitOrigin-RevId: 2dd9e79b9e02448938166254ea1b988034a81b5e
## Why
Automatic reviews and user prompts previously invalidated critical-path captures even when their owning tool invocation was known.
## What changed
Record automatic review time as `auto_review` and waits for approvals, permission requests, and user input as `user_wait` when `CriticalPathTiming` is enabled. Bind timing to the owning invocation before asynchronous work begins, and use the triggering tool's identity for network approvals. Continue invalidating captures when a wait cannot be attributed.
## Testing
Add coverage for cancellation, reused call IDs, network ownership, and disabled capture. Update the automatic review integration test to verify attributed review duration.
GitOrigin-RevId: 0a1f5feebd0c4f5ed67dc058e832ec5f8818db02
## Why
`PermissionRequest` and `PostToolUse` hook inputs could report the turn's working directory instead of the local command's execution directory. This also affected commands whose results were collected in a later turn after the working directory changed.
## What changed
- Report the local command's execution directory in hook input `cwd`, consistent with `PreToolUse`.
- Preserve the original directory through `write_stdin` approvals and delayed completion, including network permission requests.
- Retain the host directory for remote commands and keep hook process working directories unchanged.
## Testing
Add coverage for relative and absolute workdirs, approval denials, command rewrites, completion and stdin approval across turns, remote command fallback, network approvals, and Unix and Windows path formatting.
GitOrigin-RevId: ef5dad2a0634dda9edb2f841ef4fe49ae0d1187d
## What changed
Instrument the returned tool runtime future with the same dispatch span as the spawned dispatch task, keeping completion and cancellation handling in that span.
## Testing
Extend the detached code-mode callback test to assert that the router's `dispatch_tool_call_with_state` span has `dispatch_tool_call_with_code_mode_result` as its parent.
GitOrigin-RevId: e4d4bef26563554bf703b3e4f05490e25d8eb0ad
## What changed
Add the default-disabled `critical_path_timing` feature to capture dependency paths for root-agent turns. Connect direct tool dispatch, execution-lock handoffs, and completed tool batches to turn timing so overlapping work shares its common history without double counting.
Omit captures for unsupported dependencies, including CodeMode, agent communication, approval review, and user waits. Settle aborted tasks before freezing timing, invalidate captures on forced teardown, and apply runtime feature changes only to future turns.
## Testing
Add coverage for serial and overlapping tool dispatch, execution-lock dependency handoffs, cancellation, unsupported paths, frozen timing after completion, and configuration refresh boundaries.
GitOrigin-RevId: 71458b654b1c4a05799886928b449c948ea33109
## Why
`PreToolUse` hooks receive the host working directory even when a local
`exec_command` call specifies a different `workdir`. This prevents hooks from
seeing the directory in which the command will execute.
## What changed
- Share working-directory resolution between command execution and hook input,
using the selected environment and the command's `workdir`.
- Report the resolved local directory in the hook input's `cwd`. Keep hook
processes in the host directory and retain the host `cwd` for remote commands.
- Reject invalid environment selections or paths before running hooks and record
failures in tool-result telemetry.
## Testing
Add unit and integration coverage for default, empty, relative, and absolute
working directories; Windows path conventions; remote commands; hook denial and
input rewriting; and invalid arguments that fail without running hooks.
GitOrigin-RevId: 97f71f6d3e21a5d95a7abf5384f06f4993241797
## What changed
Introduce `CapturedStream` to keep retained output text and omitted-byte counts together. Use its shared renderer for unified exec logs and model-facing output, preserving omission markers and truncation notices.
GitOrigin-RevId: 045d925df1e31945755196dafed5f78ed507b33b
## What changed
Move `HeadTailBuffer` and `format_output_omission_marker` into the new
`codex-utils-head-tail-buffer` crate, exposing the buffer API with an explicit
const-generic byte budget. Update core callers to use the crate and add Cargo
and Bazel definitions.
Move the existing buffer tests alongside the implementation, preserving the
prefix/suffix retention and omission-marker behavior.
GitOrigin-RevId: ff488d0a0a62c39c0e11c11ebb539166cc4c6e74
## What changed
- Emit `codex.turn_profile` events with finalized sampling request and retry counts when turns complete or abort, and preserve the caller's tracing span for detached extension interrupts.
- Add conversation and turn identifiers to turn and tool dispatch spans, identify tool sources, and include dispatch-to-result-ready duration on tool completion events.
- Emit `codex.skill_read.source_selected` before cache or provider access, recording the selected cloud or executor source, skill and plugin identity, resource kind, and continuation status.
## Testing
Add regression coverage for trace correlation, tool completion timing, turn profile counters on completion and interruption, detached interrupt span propagation, and skill source attribution including cached cloud reads.
GitOrigin-RevId: db78aa270bbcb8dc9e4558d202c109ad54141811
## Why
Tool readiness waits, execution-lock waits, and result-ready events occur outside the dispatch span. Tracing should cover the full spawned dispatch task while retaining caller context when TRACE spans are disabled.
## What changed
- Instrument the entire spawned task with the dispatch span, falling back to the current span when it is disabled.
- Add child spans for readiness waits and parallel or exclusive execution-lock waits.
- Record `turn_id` and `codex.tool.phase = "dispatch"` on the dispatch span.
## Testing
Add regression tests that dispatch an unknown tool through the spawned task and verify that `codex.tool_result_ready` retains caller context at both INFO and TRACE levels, with the dispatch span present only at TRACE.
GitOrigin-RevId: 18026750af58347c38a4c2752cdd6165d73a3eab
## What changed
- Include ready environments' configured hooks in lifecycle events and execute command hooks using each owner's shell, working directory, shell environment policy, and managed network policy.
- Resolve tool environments before `PreToolUse` and use those targets for tool hooks, execution, and permission review. Route MCP hooks by server ownership and file-copy hooks to both endpoints.
- Preserve environment, MCP server, and terminal session selectors across hook input rewrites, rejecting attempts to switch targets.
## Testing
Add regression coverage for permission-request selector preservation, MCP resource hook ownership, and file-copy hooks that rewrite paths while preserving source and target environments.
GitOrigin-RevId: 31a3a6830523965285dab451cfc866c620ef6c83
## What changed
- Read optional tool descriptions and parameter schemas for `history`, `notes`, `new_context`, and `get_context_remaining` from the acting model's catalog messages.
- Support catalog namespace descriptions for history and notes, preserving explicit empty and whitespace descriptions.
- Share catalog override handling across native tools and MCP resource helpers. Keep bundled schemas when overrides are invalid, preserve encrypted parameters, and leave tool identity and transport fields unchanged.
## Testing
Add coverage for sparse catalog serialization, schema fallback and encryption preservation, per-step tool definitions, and context tool updates when switching models. Extend outgoing-request tests to verify history and notes overrides while retaining history image attachments.
GitOrigin-RevId: 1adac8b5009f95c91adba491f20a4e2e2dc91475
## What changed
- Add `environment_hooks` to `EnvironmentConfig` for hooks from an environment's effective managed requirements. Initialize it empty for inferred thread configurations and report the handler count in debug output.
- Move `HookEventsToml`, `MatcherGroup`, and `HookHandlerConfig` into `codex_protocol::hooks`, with re-exports from `codex_config::hook_config`.
- Validate MCP hook input recursively to reject nulls and integers outside the signed 64-bit range without converting through `toml::Value`.
GitOrigin-RevId: 410506c8e2b89c9519c81d86b44ccd760d751693
## Why
Managed network policies need to require approval for selected hosts even when an exact or wildcard allow rule matches them.
## What changed
- Add `experimental_network.review_domains` to managed requirements and route matching hosts through the existing network approval flow. Explicit denials retain precedence, and approved connections still undergo DNS and local-address checks.
- Preserve review patterns across environment policy attachments and remote proxy configuration. Reject execution on an exec-server that lacks the `networkProxyReviewDomains` capability when review patterns are present.
- Expose `reviewDomains` through the app-server requirements API and generated schemas, and show `review_domains` in debug configuration output.
- Update approval reasons to say that network access requires approval rather than assuming the host is absent from the allowlist.
## Testing
Extend coverage for review precedence over exact and wildcard allows, explicit denials, DNS checks after local and remote approvals, approval hooks, policy merging, remote configuration round trips, and requirements API serialization.
GitOrigin-RevId: 4a861061a0ed80b3537d3b72f2caecb0db2a4f0b
## Why
Remote credential masking previously fell back to unmasked execution whenever custom credential providers were configured.
## What changed
- Transport configured provider rules to the executor-local network proxy, where credential values and destination context are resolved.
- Advertise `credentialMaskingCustomProviders` and negotiate masking support. Keep the warning and unmasked fallback for executors that support only built-in providers.
- Discard provider rules when masking is disabled and omit their contents from debug output.
## Testing
Extend coverage for capability compatibility, provider configuration round trips, and fallback on older executors. Exercise configured-provider masking in remote request history and verify that masked placeholders are restored to real credentials in upstream request headers.
GitOrigin-RevId: b036f56900b343ddccc17b5293c82bc1f3426237
## What changed
- Store `logs_2.sqlite` in `log_dir` when explicitly configured, unless a managed `sqlite_home` requirement applies. Keep other databases in `sqlite_home` and preserve the existing SQLite log location when `log_dir` is unset.
- Initialize and lock the selected log directory only when opening its database, so an unavailable directory does not prevent authentication commands from loading configuration. Share the cleanup lock across configuration clones and allow failed initialization to be retried.
- Leave existing logs in place. Read legacy logs for diagnostic submissions when the current query returns no logs, attaching them as `codex-logs-legacy.log`. Continue retention cleanup and page reclamation for both locations, with independent maintenance locks and filesystem checks.
## Testing
Add coverage for configuration routing and managed requirements, deferred initialization and lock lifetimes, authentication with an unavailable log directory, legacy log attachments, and cleanup of current and legacy databases.
GitOrigin-RevId: 48216694596d738eff1b3c5eef6c4e7ada6d0137
## Why
Mailbox preemption can discard completed response items and lose the response ID needed for incremental continuation. Buffered tool calls must also wait for queued agent messages to be read.
## What changed
- Gracefully interrupt and drain Responses Lite streams, retaining completed items and the response ID for the next request.
- Cancel buffered tool calls before dispatch and suppress partial items that may be discarded during the drain.
- Keep user steering queued until draining finishes. Include pending mail in follow-up requests after disconnects and preserve content-filter recovery guidance.
## Testing
Add WebSocket regression coverage for buffered completion, interrupts without acknowledgement, buffered tools and partial items, user steering during draining, disconnects, and content-filter recovery.
GitOrigin-RevId: c9d3fb87a81850e5686e07f28103e2ff4378ddec
## What changed
Store `RolloutItem::SessionMeta` and `RolloutItem::Compacted` payloads in `Box` values and update their producers, consumers, and test fixtures. Preserve the existing serialized rollout format.
GitOrigin-RevId: 59fcc4beb47d23160872dcb6e95ace9b142d3d11
## Why
Sessions using the same MCP catalog can repeat schema normalization and retain duplicate tool specifications.
## What changed
Split immutable MCP tool metadata and normalized specifications from per-handler caches, and reuse matching definitions within each `McpManager`. Require matching tool metadata, agent-plugin mode, and schema budget before reuse.
Keep shared definitions behind weak references and prune expired entries on cache misses so completed sessions do not keep their schemas alive. Build definitions outside the shared index lock.
GitOrigin-RevId: 02345359a1b0d297ca56f2f469de88aba89106f1
## Why
Disabled or failed protected shell snapshots prevent commands from running when credential masking is enabled.
## What changed
Restore unmasked credentials and continue execution when a protected shell snapshot is unavailable. Log and emit a warning explaining that the command will run with unmasked credentials.
## Testing
Extend `brokered_shell_snapshot_fallback` coverage for disabled and failed snapshots, including managed feature settings. Verify the warning, successful execution with restored credentials, continued filesystem sandbox and network policy enforcement, and masking recovery after snapshot storage is repaired.
GitOrigin-RevId: 28561e571b2a043d0b6cfa248c9ba2a61dd558ba
## What changed
Add an `incremental_tools` attribute to `codex.tools.registered` using the effective mode for the current sampling request. Compute the mode once and reuse it for registration metrics and prompt construction across transport retries.
## Testing
Extend integration tests to verify the attribute for incremental and non-incremental requests, including when the feature flag is enabled but the Responses API does not support incremental tools. Assert registration sample counts and retain coverage that stream retries do not duplicate registration metrics.
GitOrigin-RevId: e5b7a1075fe722ef6bdf900ae07e2b1b06aecfb5
## What changed
- Update Cargo and Bazel toolchain pins, CI and release workflows, and Windows setup from Rust `1.95.0` to `1.99.1`.
- Adapt Rust code to updated APIs and lint requirements, including `try_update` and `as_chunks`, and refresh the halfwidth sound marks snapshot.
- Update `webpki-root-certs` from `1.0.5` to `1.0.10` in the Cargo and Bazel lockfiles.
GitOrigin-RevId: e1aaed63b7e72bb8c8bbe25b32c6329c9a37b6c3
## What changed
Add `MessageLifecycleContributor` hooks to capture extension state when local agent control publishes a message and notify contributors when the recipient commits it to history, before sampling.
Carry shared delivery state through submissions, input queues, and mailbox eviction with `PendingAgentMessage`. Notify consumption at most once per delivery, release captured state when consumed or abandoned, and drop pending mail outside queue locks. Preserve the serialized message format without republishing restored history.
## Testing
Extend the mailbox eviction test to verify that publication state survives eviction and retained messages are consumed before the first resumed model sample.
GitOrigin-RevId: 9a1f6832bd48ec646a3fd179485c095e8dcc72cc
## What changed
- Add `CodeModeCellTiming` notifications for yielded executions, terminal waits, and unavailable cells, with thread, call, and cell identifiers.
- Measure how long completed results remain buffered before retrieval and carry `result_buffered_for` through the runtime, stdio protocol, and gRPC response metadata. Immediate delivery reports zero; waits without a completed result report no buffering measurement.
- Default missing buffering data to zero for compatibility with older hosts.
## Testing
Extend runtime tests to verify buffering duration with a paused clock and retrieval through termination. Add gRPC conversion tests for nanosecond precision, optional metadata, and the distinction between immediate delivery and no completed result.
GitOrigin-RevId: 60c0c5a3affa69ac3779bf1812fca50f5748af76
## What changed
Classify messages from code-mode collaboration calls as `AgentMessage::Plaintext` so they receive the context wrapper for plaintext messages. Apply this to `spawn_agent`, `send_message`, and `followup_task`.
## Testing
Add a regression test that spawns an agent through `exec` and verifies that the child receives the task as plaintext with sender and recipient attribution.
GitOrigin-RevId: 495c70ea13fd2bb06989e5aacab60beed0c19a56
## Why
Temporary environment attachments for a parent turn should not become a
subagent's persistent environments. Children also need to retain their
configured executor bindings when their runtime is evicted and reloaded.
## What changed
- Add the disabled-by-default `subagent_thread_environments` feature flag.
When enabled, both subagent implementations inherit configured thread
environments captured with the invoking step, excluding turn-only attachments.
- Track configured bindings separately from active turn attachments, preserving
pending configuration ownership and sharing completed executor startup.
- Retain configured selections and bindings across idle eviction. Reload children
using retained bindings when the parent changes workspace, while continuing to
validate current parent roots and permissions for matching workspaces.
## Testing
Extend regression coverage for configured, empty, forked, pending, and legacy
inheritance; temporary attachment removal across eviction; and reload behavior
with changed workspaces, deferred startup, and restricted permissions.
GitOrigin-RevId: 15692ecd99deb38002014b44fd859d793bd54373
## What changed
- Remove `subagent_thread_environments` and the separate configured environment bindings. Spawned agents inherit the invoking step's environment snapshot.
- Retain environment selections across child eviction without retaining executor bindings. Reload V2 children against the parent's captured environments, requiring matching environment IDs, working directories, and workspace roots while preserving permission validation.
GitOrigin-RevId: d820c63ea20f5834ed88071d16c60683f2545406
## Why
Temporary environment attachments for a parent's turn should not become a child's persistent environment configuration or survive child eviction.
## What changed
- Add the default-disabled `subagent_thread_environments` feature flag. When enabled, subagents inherit configured thread environments captured with the spawning step instead of active turn selections.
- Track configured bindings separately from turn attachments, preserving pending configuration ownership when turn selections change.
- Retain configured bindings across child eviction and reload, excluding temporary attachments. Preserve the child's workspace when the parent switches workspaces, while enforcing current roots and permissions when the parent still configures the same workspace.
## Testing
Extend coverage for both multi-agent versions, forked children, empty configured environments, pending configuration, and legacy inheritance. Add eviction and reload cases covering temporary attachments, workspace changes, deferred executor startup, and permission validation.
GitOrigin-RevId: 4533645503d5f863a9ccc064386ed7ca169d98b7
## What changed
- Build executor skill catalogs from discovery V2 inventories without reopening host paths or falling back to legacy discovery.
- Merge Cloud and executor skills by remote plugin identity and skill name, retaining Cloud metadata and accepted provider read routes. Apply plugin selection and disablement before merging.
- Share a stable catalog across each step's rendering, list/read tools, and explicit and implicit skill invocations.
- Preserve unmatched executor entries when Cloud catalogs are unavailable or partial; only complete Cloud catalogs disable unmatched remote entries.
- Bind discovery caches to captured environments and executor sessions, and refresh MCP when V2 inventories change. Preserve pending invalidations when forced MCP refreshes fail.
## Testing
Add regression coverage for V2 inventory sharing and refresh, environment isolation, catalog merging, partial Cloud results, disabled plugins, and catalog consistency across steps and read routes.
GitOrigin-RevId: 842bdcbc9e19364dd69a9abf9e48330b7425a76c
## What changed
- Add `PreModelRequest` and `PostModelRequest` hooks around model request attempts, including retries. Pass model, session, turn, and optional subagent context; report completion, failure, or cancellation with errors and token usage when available.
- Treat hook output as diagnostic data without allowing it to veto requests or alter model context. Wait for synchronous post-request hooks before dispatching tools, while asynchronous hooks allow streaming tool dispatch to continue.
- Apply memory-consolidation hook filtering and expose the new events through configuration, protocol schemas, generated clients, and the hooks browser.
## Testing
Add integration coverage for failures and retries, ignored control directives, cancellation, synchronous and asynchronous tool ordering, interrupted-turn resume and token accounting, and memory-consolidation filtering. Update hook schema fixtures and hooks browser snapshots.
GitOrigin-RevId: 6ed7b39fc8bb94cf467e350d07d97fcc729c21ce
## Why
Contextual fragments and extension-owned world-state sections currently return strings, limiting them to text content.
## What changed
- Return `ContentItem` from fragment bodies and rendering, preserving classification and attribution. Apply text markers only to `InputText`; pass other content through unchanged.
- Allow extension prompt and world-state contributions to carry typed content, and preserve media in context-window hints.
- Hash non-text world-state fragments by their serialized content and role while retaining the existing text hashing behavior.
- Add shared content-to-tool-output conversion that preserves image references, image detail, and audio.
## Testing
Add coverage for typed world-state hashing and preservation of image content and attribution. Expand code-mode output tests to cover input text, output text, file-backed and inline images, and audio.
GitOrigin-RevId: 2ed00d466a3f169b151202f3eef71e667ea64be1
## Why
Schema strings and sequences do not grow after construction, and most schema nodes do not contain maps. Retaining collection capacity and inline optional maps adds unnecessary memory overhead.
## What changed
Store `JsonSchema` strings and sequences as boxed strings and slices, and box optional property and definition maps. Adapt constructors, schema consumers, and existing test expectations to the new representation while preserving the serialized JSON Schema format.
GitOrigin-RevId: 0a249b1ae32932cbbfe3c575c32bfd20b060c303
## Why
MCP tool calls reported every aborted approval as "user cancelled MCP tool call", including interrupted requests and automatic cancellations in `exec` mode.
## What changed
Carry `user`, `interrupted`, or `non_interactive` cancellation reasons through MCP approval metadata and resolution. Mark explicit TUI cancellations as user actions, interrupted requests as interruptions, and automatic `exec` cancellations as non-interactive.
Use the reason to report when a call was cancelled before approval or because interactive approval is unavailable in `exec` mode. Preserve the existing cancellation message for clients that omit the reason.
## Testing
Update tests to verify that a closed approval response carries the interruption reason and that `exec` cancellation responses include the non-interactive reason.
GitOrigin-RevId: be2a5f7fef539b5db2add53b46aea27e2b8a66fc
## Why
Dynamic tool calls should remain independent while waiting for client responses, so one pending call does not block another from reaching the client.
## What changed
Enable parallel execution in `DynamicToolHandler`, allowing code mode programs to issue concurrent dynamic tool calls with `Promise.all`.
## Testing
Add a code mode regression test that waits for two dynamic tool requests before responding, resolves them in reverse order, and verifies that `Promise.all` preserves the expected result order.
GitOrigin-RevId: c93c1fea720f76c772b0e3452ddc8c01fb1a08d8
## Why
Remote credential masking previously supported only Bash commands without login startup or shell snapshots, leaving Zsh commands with unmasked credentials.
## What changed
- Enable masking for Zsh login commands using shell snapshots on Linux and macOS.
- Capture trusted startup profiles per launch, bind the credential broker to the resulting environment, and replace credentials and supported aliases with placeholders before snapshot replay.
- Preserve explicit environment overrides, credential unsets, and launcher-managed proxy settings during replay.
- Warn and fall back to unmasked startup when a snapshot cannot safely replay credentials; stop execution if protected snapshot restoration fails.
## Testing
Extend remote execution tests for inherited and profile-defined credentials, overrides, destination changes, and unsupported-profile fallback. Add a Zsh scenario snapshot showing a credential placeholder in command output.
GitOrigin-RevId: 83193d6cbc05f3deb0d6d0b9ae80974b353ce900
## What changed
Add optional `inputImages` metadata containing each referenced local image's path and SHA-256 hash of the bytes read before normalization. Compute the hash from the same bytes used to prepare the edit request.
Preserve this metadata through completion events, persisted thread history, resume, and legacy rollout migration. Update app-server schemas and generated TypeScript and Python types; older items continue to deserialize without the field.
## Testing
Add coverage for input ordering, changed contents at the same path, unreadable or invalid references, serialization, persisted history and resume, and legacy migration.
GitOrigin-RevId: 522be8ec1e39c9b2bbe5b9ccb37ea67d17f0e21a
## What changed
- Upload generated images to the attachment store and expose `fileId` in image-generation items when available, with inline `result` fallback on upload or decoding failure.
- Preserve file references through legacy events, persisted rollouts, thread history, and task output summaries. Keep model-facing image preparation separate.
- Add attachment request tags and mark generated-image uploads with `usage=image_gen`, preserving the thread's ephemeral setting.
- Update public schemas and SDK types to accept either image representation, retain the Python `ImageGenerationThreadItem` alias, and prefer `fileId` when reading records containing both fields.
## Testing
Add coverage for file-backed generation and rollout persistence, legacy history replay, inline and transitional serialization, task output visibility, and Python SDK alias compatibility.
GitOrigin-RevId: f7a2bb5707e2f277348a547a988bc33c8e96d891
## What changed
Negotiate executor support for `credential_masking` and enable built-in credential brokerage in executor-local network proxies. Supported non-login Bash commands on Linux and macOS receive credential placeholders, with real credentials injected by the proxy for matching destinations.
Retain credential mappings across process launches within the same executor session, scoped by environment, conversation, and broker configuration. Keep credentials and destination context on the executor.
Fall back to unmasked execution for unsupported shells or shell startup, and for configured credential providers. Emit warnings when masking is unavailable, preserving shell profiles and snapshots.
## Testing
Add coverage for capability negotiation, fallback behavior, mapping reuse and isolation, proxy credential injection, and keeping executor credentials out of model-visible request history. Test warning, removal, and rejection modes for credentials left unmasked during preparation.
GitOrigin-RevId: f64e916a5de8350fa0d289d3440ec29761accd75
## Why
Guardian approval covers the permissions of the reviewed action. A retry outside the sandbox needs a fresh review of its broader permissions.
## What changed
- Track the initial approval source so Guardian approval does not preapprove an escalated retry, while preserving existing user and hook approval behavior.
- For exec retries that can run without the sandbox, set the approval action to `RequireEscalated` and clear `additional_permissions` so review and caching reflect the retry's actual permissions.
GitOrigin-RevId: 06f8d53745a7bcfe9fdb5628ff9e85da6060547d
## Why
With granular sandbox approvals disabled, `write_stdin` rejected input to terminals retaining additional permissions even when those permissions were still granted.
## What changed
Let input reach approval review when the terminal's retained permissions match active grants for its environment. Require identical filesystem grants, including entry order, and an active network grant when retained permissions enable network access. Each input still requires review.
Keep rejecting input when retained authority is no longer covered or the approval policy changes to `Never`.
## Testing
Add regression coverage for user and Guardian review, turn grant expiry, session grants, and switching to `Never`. Cover filesystem restrictions, protected metadata, symlinks, and ordered denials, and verify that rejected input never reaches the terminal.
GitOrigin-RevId: 9abf7da8d03b1526d26ca2a718e36349a255330b
## Why
Environment tool availability and selectors should remain stable as selected environments become ready.
## What changed
- Keep configured environment tools advertised even when no execution environment is ready, and derive `environment_id` selectors from all selected environments.
- Return guidance to wait when an environment is unavailable, while preserving errors for unknown environment IDs. Require a usable primary environment for `write_stdin`.
- Always include `shell` and `login` in the `exec_command` schema and mark `stable_environment_tools` as removed.
## Testing
Update integration tests to expect environment tools with empty or starting environments, and remove explicit feature opt-ins from affected scenarios.
GitOrigin-RevId: 1590c1b5be16a39e4a370663c552b881602545b5
## Why
Native extensions need configured Responses metadata for request attribution, but extension calls used the MCP metadata template, which omits it. Image requests also did not forward the turn metadata to the backend.
## What changed
Use the Responses metadata template for native extension calls while continuing to exclude tool inventory. Forward the resulting metadata in the `x-codex-turn-metadata` header on image generation and edit requests.
## Testing
Extend metadata tests to cover configured values in extension calls and app-server tests to verify `display_name` and `turn_trigger` on image generation and edit requests, including a Unicode display name.
GitOrigin-RevId: a2ffaa4d15259c662917612391b8717ee34b9c6c
## What changed
- Preserve approval resolution sources through tool errors and tag cancelled MCP approvals with `error_type=approval`, `error_code=cancelled`, and `approval_source` (`guardian`, `user`, `hook`, or `unknown`). The source identifies the reviewer, not who caused cancellation.
- Record `context_changed` when validating a Guardian allow against changed authorization or review context, even when a concurrent stop or history reset determines the outcome. Retain the flag across retries and fresh-checkpoint recovery, and include it in the Guardian review counter.
GitOrigin-RevId: a19a986a7565f9a78a9bb2eaabdb5651834d28b8
## Why
Prediction forks need to retain their parent's context even when it exceeds the automatic compaction threshold. Compaction or context resets can otherwise replace the history used for the prediction.
## What changed
- Apply a thread-local `AutoCompactionDisabled` policy to experimental prediction forks without changing model or skill budgets.
- Skip automatic compaction before, during, and after turns, including context-limit recovery, and suppress new token-budget reminders.
- Reject `new_context` requests for these threads and report context-limit failures without compacting their history.
## Testing
Add regression tests for legacy and paginated prediction forks across compaction thresholds, unchanged parent compaction and skill/tool inputs, context-limit failures, and rejected context resets. Add a request-history snapshot verifying inherited context and reminders survive without compaction or additional reminders after a tool call.
GitOrigin-RevId: 7df374287f4142f776981bb6c22e5caa564d74a5
## What changed
Move child configuration, task path construction, fork usage hints, and backend spawning into `core::thread_spawn`. Add request, result, and error types that distinguish preparation failures from backend errors.
Route the v2 `spawn_agent` handler through the shared helper while retaining tool-specific telemetry, activity events, and response formatting in the handler.
GitOrigin-RevId: a09a8f66beb41c1403220750d236a12717dbfc6c
## What changed
Add `features.multi_agent_v2.disable_native_tools` to hide native multi-agent tools while keeping the V2 runtime and its instructions enabled for host-provided tools. The option defaults to `false`, preserving existing tool exposure.
## Testing
Extend configuration parsing tests for the new option and parameterize the multi-agent catalog scenario to cover both settings. Add a snapshot showing native tools are absent while the V2 runtime and instructions remain enabled.
GitOrigin-RevId: 21a53584d2395bb678813c876a8b7927bea61c90
Anthony Tafoya