## Why
Stdio servers without `CODEX_MCP_PROTOCOL_VERSION` use the legacy handshake, even when they support MCP `2026-07-28`.
## What changed
- Add the disabled-by-default `mcp_connection_sharing` feature to enable discovery for eligible local stdio servers.
- Recover from failed or late discovery with a fresh handshake when needed, waiting for the previous helper to release resources before restarting.
- Retain a working legacy connection when an upgrade attempt fails for the same account, except on authentication errors.
- Keep tool catalogs separate by protocol and invalidate legacy catalogs when discovery negotiates the modern protocol.
## Testing
Add regression coverage for failed and late discovery, legacy fallback, protocol-specific catalog reuse, message limits, and Windows descendant cleanup.
GitOrigin-RevId: 36c675ef3b81d32fccf06ccbddda2312cfe602c9
## What changed
Include critical-path capture status and duration totals in `codex_turn_event`, with categories for inference, auto review, user wait, tools, overhead, and unknown time. Count sampling and compaction as inference.
Distinguish `disabled`, `incomplete`, and `complete` capture. Emit null durations for disabled or incomplete capture so missing measurements are not reported as zero. Freeze the completion timestamp so repeated terminal notifications preserve the original measurement window.
## Testing
Add core and analytics tests for capture status, duration reporting, rounding, and repeated completion. Add app-server integration coverage for completed and interrupted turns with default, enabled, and disabled capture.
GitOrigin-RevId: c6c867120ee563ac48584c2f4b12df23acbabe06
## 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
## What changed
Add `untrusted_as_tool_output` as an under-development feature, disabled by default, and expose it in the configuration schema. The flag is intended for rendering client-supplied untrusted context as standalone named tool outputs.
GitOrigin-RevId: 6fe630c8d380a87edb48e08887215c1ec17447ed
## 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
## Why
Executors older than `0.164.0` can advertise V2 discovery support without implementing the final contract. Enabling V2 also suppressed V1 discovery for incompatible executors, hiding selected capability roots and skills.
## What changed
Require both the V2 capability flag and an executor version of at least `0.164.0` before issuing `capabilities/discoverV2`. Share this compatibility check between session discovery and the exec-server client. Fall back to V1 when incompatible executors provide no V2 snapshots, clearing any previously stored V2 inventory.
## Testing
Add coverage for version boundaries, prereleases, missing and malformed versions, and transport recovery for compatible executors. Verify that an older executor retains selected plugins and skill instructions through V1 with V2 enabled.
GitOrigin-RevId: 93adf52fc91f02b58fd14f8ff3b093712b3346b8
## What changed
Consume local stdout and stderr receivers directly with `tokio::select!`, removing the intermediate broadcast channel and its lag-related chunk skipping. Drain both streams until they close.
Pass `ExecOutputStream` through local and remote output collection to `OutputBuffers::push_chunk`, while retaining combined output buffers.
## Testing
Update output-buffer tests for the stream argument and exercise stderr chunks in pushed-event and replay test fixtures.
GitOrigin-RevId: be7804fd30cefeb812e372454665923ba051ddb4
## What changed
Support `model_providers.gcp.credential_file` as an absolute path to a Google Application Default Credentials (ADC) file. Pass it as `GOOGLE_APPLICATION_CREDENTIALS` in the provider auth command's environment, retaining the override for token refreshes without changing the parent process environment.
Validate the path before merging GCP defaults and preserve the setting in thread configuration serialization.
## Testing
Add coverage for invalid paths, configuration round trips, separate provider token caches, and credential overrides retained after a `401` refresh. Include a Windows regression test for credential paths containing command metacharacters.
GitOrigin-RevId: d9a1d4b3775a9a4c4325dddaa153d92a2d1430a0
## What changed
Add `features.rollout_budget.enforce_limit`, defaulting to `true`. Setting it to `false` keeps shared usage accounting and budget reminders active while allowing turns to continue after the budget is exhausted.
## Testing
Extend coverage to check enforced and advisory budgets on the current and subsequent turns, including a zero-remaining-budget reminder in advisory mode. Verify that configuration defaults to enforcing the limit.
GitOrigin-RevId: deeac8dae5714cc7c10d030cade6f3bfbfc8d3a7
## 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
- Add an optional `name` to `AdditionalContextEntry` across the protocol, app-server schemas, and generated clients.
- Accept names matching `[a-z][a-z0-9_]{0,63}` only for `untrusted` context. Reject invalid names and names on `application` context before admitting turn input, returning invalid-request errors from `turn/start` and `turn/steer`.
- Preserve existing model-input rendering and deduplicate context when only its name changes.
## Testing
Add coverage for valid name boundaries, callers that omit `name`, invalid-name rejection without admitting input, and deduplication across name changes.
GitOrigin-RevId: 2caffa6fddd40ddb178733b335f520f317239edd
## Why
API keys with FedRAMP issuance markers previously used commercial endpoint defaults without a FedRAMP request header.
## What changed
- Recognize `sk-proj-fedramp-` and `sk-svcacct-fedramp-` prefixes as routing hints and send `X-OpenAI-Fedramp: true`, preserving the complete key for authentication.
- Select `https://gov.api.openai.com/v1` for default OpenAI API routing and `https://gov.chatgpt.com/backend-api/` for default ChatGPT backend requests, including model discovery and analytics.
- Preserve explicit endpoint overrides, including an explicitly configured commercial default URL.
- Resolve provider routing and authentication from the same credential snapshot, and apply key-dependent routing to realtime WebSocket startup.
## Testing
Add regression coverage for prefix recognition, unchanged key storage and authorization, provider credential precedence, endpoint overrides, credential rotation, model discovery, analytics routing, and realtime request preparation.
GitOrigin-RevId: a62576ce205c34e067532b8e6c0e431f87a157e2
## What changed
Preserve complete Node REPL tool outputs during synchronous transcript collection and apply the configured output token limit during prompt preparation, after full or delta transcript selection.
## Testing
Update transcript assertions to verify that oversized Node REPL outputs remain intact during collection and are truncated to the selected token cap when rendered.
GitOrigin-RevId: 30ced935c04db456a277f7e58281d45e0e2047dd
## What changed
- Add `body_secret_substitution` actions to version 2 MITM configuration, replacing exact opaque placeholders with secrets from environment variables or files within the matching hook's scope.
- Bound body size, expansion, replacement count, and search work. Reject overlapping matches, compressed payloads, trailers, and supplied payload-integrity headers.
- Recompute `Content-Length` and substitute before SigV4 signing so signatures cover the transmitted body.
## Testing
Add coverage for markers split across chunks, expansion limits, invalid payloads, overlapping bindings, secret redaction, and search limits. Add a TLS forwarding test that verifies hook scope and independently checks the signature of the substituted body.
GitOrigin-RevId: fa95c9ae0c8fc8f695e03c0e87a0a4875d8418fd
## What changed
- Add nullable `startedAtMs` and `completedAtMs` fields to `ThreadItem` in live notifications and turn history. Values are Unix milliseconds when recorded.
- Preserve recorded item times through history reconstruction, pagination, and resume, including command start times recorded during approval.
- Separate the Rust item payload into `ThreadItemPayload` while keeping the JSON payload flat, and update consumers, schemas, and generated TypeScript and Python types.
## Testing
Extend coverage for timestamp serialization, history reconstruction, paginated reads and resume, and persisted Python SDK items.
GitOrigin-RevId: ecbcee95af52db7c807b46a6e9deb30e5fba1f80
## What changed
- Add opt-in runtime authentication through `ModelClient::with_runtime_auth`, requiring the provider and runtime manager to share the selected OpenAI credentials.
- Keep runtime identity, credentials, routing, and transport selection consistent for each request and its retries, signing a fresh assertion for each attempt.
- Apply authentication asynchronously to WebSocket handshakes, replace stale authentication headers, and reconnect when the runtime changes.
- Reject account, organization, or project selectors that conflict with the registered runtime, and preserve gateway OAuth composition.
## Testing
Add coverage for dual-header and assertion-only authentication, HTTP retries, runtime replacement and account switches, stale WebSocket headers, selector mismatches, gateway OAuth failures, transport revocation, and Realtime compatibility.
GitOrigin-RevId: 45b9efc2c80481406a0f6f6396a8cdd21d933c12
## Why
Deriving a Vertex AI endpoint previously required environment variables. Allow the project and location to be specified directly in GCP provider configuration.
## What changed
- Add `model_providers.gcp.project_id` and `model_providers.gcp.location`, with each taking precedence over its corresponding environment variable. Keep `global` as the default location and preserve explicit `base_url` overrides.
- Validate configured endpoint fields and preserve them through thread configuration serialization.
- Apply built-in GCP defaults, including default command authentication, when checking managed provider requirements so unchanged requirements are accepted.
## Testing
Add coverage for endpoint precedence, invalid explicit configuration, provider construction, thread configuration round trips, and managed GCP requirement checks, including repeated model listing.
GitOrigin-RevId: c3704bcc0b7d4872374e2cae623fd24d75fb02b4
## What changed
- Always use the retained conversation backend for asynchronous classification; keep snapshot sampling test-only.
- Accept legacy `async_classifier_mode` values in configuration and model metadata but ignore them. Emit a startup warning when `[features.guardianv2].async_classifier_mode` is configured.
- Ignore legacy classifier mode differences when checking model-switch compatibility, and fail closed if the conversation backend is missing.
## Testing
Update coverage for legacy configuration warnings, model-switch compatibility, retained approval-review context, and conversation-based scoring.
GitOrigin-RevId: 5e8bb7e4e6e7d1589572f38bfe2498c9fa6825a0
## What changed
Defer truncation of synchronous Guardian assistant and reasoning entries until `ContextProfile::prepare_transcript`, so the resolved profile's message limit applies before rendering and retention accounting. Keep encrypted agent messages whole when they fit, or replace them with an omission notice at the same transcript position when they exceed the limit.
## Testing
Extend coverage to verify that oversized-action reviews retain assistant commentary and final-answer evidence up to the synchronous message cap, and that encrypted-message omission produces equivalent output through synchronous transcript collection.
GitOrigin-RevId: e17fbfa7b7131559b0599ac1d57987a8d94e137c
## What changed
- Expose `aws_sigv4` actions in version 2 MITM permissions configuration and the config schema, rejecting multiple signing actions per hook.
- Give local managed commands placeholder AWS credentials for the selected signing pair, and mask configured credentials in environment values and protected shell snapshots.
- Set `AWS_CA_BUNDLE` to the managed proxy CA bundle when unset, and require `features.credential_masking` for local AWS signing hooks.
- Validate placeholders against every configured signing pair to prevent overlap with real credentials.
## Testing
Extend configuration, signing, and TLS forwarding tests to cover action resolution, invalid signing configuration, credential masking, CA trust, snapshot protection, and exclusion of local AWS defaults from remote environments.
GitOrigin-RevId: 81dfdea30ebde74829882b38891ea41e9737058a
## Why
Listing hooks by working directory alone omits hooks supplied by a thread's selected execution environments, including hooks that can block a turn.
## What changed
- Add `threadId` to `hooks/list` to return a loaded thread's current hook inventory, including selected, ready environments. Reject requests that also specify `cwds`.
- Expose `environmentId` in hook metadata and have the TUI hooks browser query the current thread and label environment-owned hooks. Keep working-directory lookup for startup review.
- Represent environment hook source paths with `PathUri` and use `LegacyAppPathString` in hook run summaries to preserve native path conventions.
## Testing
Add coverage for listing a blocking environment hook and removing it after environment failure, delivering prompt input and reporting exit status in PowerShell and Bash, and running `PreToolUse` hooks only on the command's owning executor. Extend remote network tests to verify that environment hooks use the command's network policy while retaining their filesystem access.
GitOrigin-RevId: 97229e22793df51f4bd502c1f9e19f0c52fb2305
## 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
Preserve tool outputs during sync transcript collection and apply the profile's `tool_tokens` limit during transcript preparation, matching tool-call handling. Keep async and Node REPL output truncation unchanged.
GitOrigin-RevId: cf1594bcf25553c08d53b86bee1dd151e4c5db64
## 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
## What changed
- Record time spent waiting for each stream event in `codex.response.receive_wait_ms` on the existing `handle_responses` span.
- Add trace spans for startup prewarm consumption, turn-start lifecycle callbacks, assistant text flushing, and response stream error handling.
- Include the turn ID and lifecycle phase on the turn-start span and the request type on the error-handling span.
GitOrigin-RevId: 7792508c830ef05b03aed01eb840ca7e6577ad0b
## 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
Preserve complete tool-call text when collecting synchronous Guardian context, then apply the profile's tool token limit when preparing the transcript. Calculate retained bytes and token usage from the truncated text.
## Testing
Extend the oversized-action regression test to verify that a subsequent review includes the previous call's arguments truncated to the 1,000-token history limit.
GitOrigin-RevId: 2b52505d9ccfa3651b3535e67cc12597be819459
## What changed
Move `GuardianToolDescriptions` into `codex-guardian-context` and carry structured tool and connector descriptions in `PlannedAction` instead of pre-rendered text. Prepare them during synchronous context composition, escaping closing tags before applying the existing 400-token limit to each source and rendering the untrusted-description fragment.
Keep descriptions optional under the context budget and preserve the complete action JSON. Reject descriptions that reach rendering without preparation.
## Testing
Strengthen the MCP approval integration test to assert the exact rendered descriptions, including independent truncation and escaped closing markers. Adapt the budget enforcement test to use structured descriptions.
GitOrigin-RevId: 4a9f1855f2958758b4be711914c00e4d954cee39
## What changed
Apply the 512-token approval reason cap in `guardian-context` when composing synchronous full and delta reviews, before request budget enforcement. Remove truncation from the requesting host and preserve exact action JSON.
## Testing
Extend the planned-action budget test to cover long approval reasons in both synchronous presentations, verifying that optional tool descriptions can be omitted without changing action arguments.
GitOrigin-RevId: 8cdb6aadd5f50194f63ebd2402193e69bed127cc
## What changed
Register `guardianv3` as an under-development feature disabled by default. Accept either a boolean toggle or a table with an optional `enabled` field, and include both forms in the configuration schema.
## Testing
Add coverage for boolean and table configuration, default behavior, and profile overrides, including inheritance when a profile omits `enabled`.
GitOrigin-RevId: 75333be61b2e336e22fef907d6363b70f9f7225b
## Why
Provider errors with code `model_not_found` should end the turn immediately and preserve the provider's message instead of triggering retries.
## What changed
- Recognize `model_not_found` in HTTP 400, 403, and 404 responses and in streamed `error` and `response.failed` events.
- Preserve the provider message and any available HTTP status, and expose `modelNotFound` through the app-server protocol and generated schemas and SDK types.
## Testing
Add coverage for HTTP classification, statusless stream errors, and terminal failures without retries across HTTP, SSE, and WebSocket responses. Verify that `thread/read` preserves the error reported by the live notification.
GitOrigin-RevId: 88f824ac03c8c9669915b1e40c67b76c08326fbe
## What changed
Add `auto_review.timeout_ms` to configure the overall Guardian review budget, including setup and retries. Keep the default at 90,000 milliseconds; setting it to `0` disables the review deadline while preserving cancellation, retry attempt limits, and independent transport timeouts.
Carry the configured deadline through review execution and report the configured budget in review telemetry, using zero for unlimited reviews.
## Testing
Add coverage for shared setup budgets, configured timeouts, cancellation with unlimited reviews, and retry attempt limits without a deadline.
GitOrigin-RevId: 00404e0cb2f2cfaf6de183d6e27f5e4a371942a8
## What changed
- Add `attachToSource` to `thread/fork` to persist a fork attached to its source without emitting `thread/started`. Attached forks require local storage and cannot use `ephemeral` or `deferGoalContinuation`.
- Hide attached threads from ordinary listings and add `attachedToThreadId` to `thread/list` for explicit discovery, including empty threads. Keep this relationship separate from spawned-agent parent and ancestor filters.
- Persist attachment metadata in rollouts and SQLite so it survives restarts and database recovery. Reject source deletion until its attached threads are deleted.
## Testing
Add coverage for legacy and paginated history, restart and missing or corrupt database recovery, filtered listings and pagination, resume, conflicting options, and deletion safeguards across store instances.
GitOrigin-RevId: 589f3174fc36f6054e75d65818360695645a5913
## 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
## Why
A pending agent-message wake can outlive an interrupt or a switch to Plan mode while model discovery is waiting. It must recheck whether it can start before consuming queued messages.
## What changed
- Revalidate reserved wakes after discovery and build the turn with the configuration selected during admission.
- Mark interrupted wake reservations as stopped so later agent messages cannot restart automatic work, while preserving queued messages for explicit turns.
- Keep finishing turns marked as running until completion is persisted, protecting their rollout writer from capacity eviction.
## Testing
Add regression tests for interrupts and Plan-mode changes during discovery, queued-message preservation, explicit follow-ups with `wake_on_agent_messages` disabled, and completion status and persistence with the feature enabled and disabled.
GitOrigin-RevId: afe1d57063a5ec491e8b16d6c62135caa69c0a3c
## 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
## Why
Model output alone does not establish that an item entered conversation history. Treating every response item as accepted can include discarded attempts, while relying on a later request misses accepted final output when a turn ends or is interrupted.
## What changed
- Record `HistoryItemAccepted` events and retain Responses item IDs, generating missing IDs consistently across item events.
- Build thread conversation history from request inputs, compaction checkpoints, and explicit acceptance. Keep unaccepted output accessible through its inference call.
- Preserve inference provenance across retries and late response records without overwriting newer request or compaction snapshots.
- Mark turns with errors as failed. Bump trace schemas to version 2 and reject incompatible bundles and event schemas during replay.
## Testing
Add reducer coverage for discarded attempts with identical text, late responses, compaction, inherited context, and legacy bundle rejection. Add CLI integration tests that run `debug trace-reduce` after success, stream failure, and interruption followed by shutdown, including responses without provider item IDs.
GitOrigin-RevId: 8e387a91d9b3f704df82847d630e6f0b08f998b3
## What changed
Add optional `writable_root` and `writable_roots` templates to model-catalog permission messages. Select the template by the number of displayed roots and substitute exactly one `{{ roots }}` placeholder with the existing formatted path list.
Fall back to the bundled sentence for missing, empty, invalid, or oversized templates. Preserve path contents, permission-path limits, and denied-read instructions. Update the permission wording when the selected model changes.
## Testing
Add coverage for template validation and size limits, singular/plural selection after path truncation, path preservation, sparse serialization, and model switches that append changed permissions once while preserving request history.
GitOrigin-RevId: 4dcfb7ff70b91db3dba3dda684b355b920e07974
## What changed
- Add discovery and listing APIs for environment-owned required hooks, with command and MCP execution routed to the owning environment.
- Use each environment's working directory in hook input, withhold controller transcript paths, and prevent environment hooks from granting permission requests.
- Resolve `command_windows` against the environment's platform and, when hooks are enabled, reject unloadable required hooks before accepting environment configurations at startup or readiness.
## Testing
Add regression coverage for invalid managed hook matchers at startup and readiness, successful readiness after correction, and per-hook working directory and transcript path scoping for `SubagentStop`.
GitOrigin-RevId: 1ac0ab3778ba608c72e5917fcbaebcc1d454887f
## 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
## What changed
- Add `masked` after the provider prefix in built-in dummy credentials, followed by at least 22 random alphanumeric characters. Stop copying punctuation from the real credential.
- Check built-in dummy candidates against observed credential owners and discoverable configured-provider aliases, and reject overlaps with existing dummy credentials. Allow configured patterns to match a built-in dummy's format when no credential identity collides.
## Testing
Extend regression coverage for short and opaque credentials, fresh dummy values, known and late credential collisions, alias discovery, header injection, and text restoration. Verify that explicit authorization values remain unchanged even when they resemble masked credentials.
GitOrigin-RevId: 5080176f3ecbcdbb18943eab30136e15a4a3985e
## Why
The sequential token fixture rewrites shared files when resolving credentials. Concurrent credential resolution needs a fixture that can return the same token independently for each caller.
## What changed
Add `ProviderAuthCommandFixture::fixed_token`, which reads a token file using `cat` on Unix or `cmd.exe` on Windows without modifying it. Use it in the Vertex command-auth and guardian-request tests.
GitOrigin-RevId: 5bf5134f113b546a643a47012281fb960e885b15
## What changed
Select an originator-specific models manager before resolving thread model metadata. Supported originators send their own `originator` header and use separate in-memory catalogs and disk caches, so each thread receives the corresponding model instructions and tools.
Reuse managers for repeated originators and share the API-key model discovery setting across them. Unsupported originators retain the default manager and catalog.
## Testing
Add coverage for originator headers, concurrent catalog isolation, cache reuse across restarts, shared discovery policy, and the instructions and tools sent in actual turns.
GitOrigin-RevId: ae4aa51c8df2813a72fc8aed8978fd630e467069
## What changed
Add an optional `NetworkPolicyMetadataProvider` to the MCP runtime. Advertise `codex/network-policy-meta` only to trusted ChatGPT origins when a provider is available, and attach policy metadata only when the sending session also advertises support.
Strip caller-supplied policy metadata and derive restrictions from the call's captured permission profile and server environment. Resolve metadata against each session's capabilities, including after recovery, while retaining one policy snapshot per call. Fail the call before sending if policy resolution fails. Existing runtime callers leave the provider unset.
## Testing
Add tests for capability negotiation, trusted-origin restrictions, forged metadata removal, both tool dispatch paths, and policy snapshot reuse. Add HTTP session-recovery coverage for changing capabilities and policy-resolution failures while preserving caller metadata and read-only restrictions.
GitOrigin-RevId: 4b978f986abc0475fc67659be98fc01a2d6ce7cd
## Why
A requirements denial on a custom `codex_apps` registration could block the trusted hosted Apps replacement. Requirements filtering also lost whether a server had been explicitly disabled, which must remain effective across runtime overlays.
## What changed
- Track explicit disables separately from requirements denials, retaining the requirement source across catalog rebuilds and server materialization.
- Allow trusted host-owned Apps to bypass a previous registration's requirements denial while preserving explicit disables and blocking later custom replacements.
- Preserve combined explicit and requirements disables during repeated filtering, and reject those servers when preparing standalone MCP login HTTP clients.
## Testing
Extend regression coverage for hosted Apps replacements, later custom replacements, cloud catalog refreshes, repeated requirements filtering, and standalone login rejection.
GitOrigin-RevId: 736a13c40fbf7436b4d0682f70c335f33f45962f
## What changed
- Support `model_provider = "gcp"` with a Vertex AI endpoint derived from `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION`, defaulting to the `global` location.
- Obtain credentials through `gcloud auth application-default print-access-token` by default, and allow `base_url`, `auth`, and `http_headers` overrides under `model_providers.gcp`.
- Use a static model catalog tailored to Vertex AI, preserve function tools, namespaces, and client-side tool search, and support remote compaction V2. Disable unsupported reasoning summaries, Responses Lite, custom tools, web search, and image generation.
- Expose a `gcp` account type through the app-server protocol and generated clients without resolving credentials during account reads or requiring OpenAI authentication.
## Testing
Add coverage for endpoint resolution, configuration overrides, model catalog filtering, authenticated requests, unsupported request fields, missing credentials, account reporting across provider changes, and automatic remote compaction.
GitOrigin-RevId: 97a3158269e6dbc2605e2cf576998e09817ea12a
## Why
Resuming a thread with unchanged settings appended another `ThreadSettingsApplied` event to its rollout.
## What changed
Compare the effective settings with the latest persisted settings for the same thread before writing a checkpoint. Persist settings when they differ or no matching checkpoint exists, even if no turn follows the resume.
## Testing
Add a regression test that restarts the app server, resumes a materialized thread without overrides, and verifies that its persisted settings events remain unchanged.
GitOrigin-RevId: c545791ed3bb4020fa3da6d233607a9ba73e5c8d
Charlie Marsh