Commit Graph
5508 Commits
Author SHA1 Message Date
jackz 2c3156adf4 Honor custom OTLP metrics exporters when analytics is disabled (#52278)
## Why

Disabling OpenAI analytics also disabled explicitly configured OTLP metrics collectors. Users should be able to export metrics to their own collectors independently of `analytics.enabled`.

## What changed

Apply the analytics preference only to the built-in `statsig` metrics exporter. Keep custom OTLP HTTP and gRPC exporters enabled regardless of that preference, and use `otel.metrics_exporter = "none"` to disable metrics export. Clarify these settings in config documentation and the schema.

## Testing

Cover exporter selection across explicit and default analytics preferences. Update app-server and daemon telemetry tests to verify custom metrics export with analytics disabled, and worktree tests to disable metrics through the exporter setting.

GitOrigin-RevId: 0c61f0f01e2b694db642ac7e7fd1dac9965c7d96
2026-10-08 21:18:24 +00:00
ningyi-oai 515c291d87 Preserve large arguments in executed tool call metadata (#52268)
## Why

Fixed argument limits truncated recorded tool calls even when their metadata fit within the available message budget.

## What changed

- Remove the 8 KiB per-call and 32 KiB per-output argument limits for direct calls and Code Mode.
- Preserve full recorded arguments while retaining message metadata budgets, pending-call limits, and the direct metadata retention limit.
- Rename the normalization helper to `normalize_executed_tool_call_completeness`; it now only clears completeness when calls or tool names were lost.

## Testing

Update regression coverage for large arguments, escaped inputs, reserved-key wrappers, and argument and result metadata preservation across Code Mode waits.

GitOrigin-RevId: 8c199ccf39191d5d44eef02d28b1773654735b43
2026-10-08 20:40:47 +00:00
Alex Zamoshchin c9e0fffbbc Enable parallel execution for read-only tools (#52245)
## Why

Tools that do not opt into parallel execution acquire an exclusive scheduler lock, serializing independent reads.

## What changed

Allow skill listing and reading, memory listing, reading and searching, conversation history search and reading, plugin listing, agent listing, current time, remaining context, and `get_goal` to run in parallel. Keep goal creation and updates serialized.

## Testing

Add `cloud_skill_reads_run_in_parallel`, which uses a barrier to require two cloud skill reads to overlap and verifies that each returns the expected resource contents.

GitOrigin-RevId: 97b5634f1f84be2ba092be89e6e9c634ca75c07b
2026-10-08 19:29:47 +00:00
Adam Perry @ OpenAI 845345b1dd Preserve subagent capabilities independently of forked history (#52241)
## Why

Subagents should retain the spawning turn's selected skills and plugin choices whether `fork_turns` is `none` or `all`. Capability selection should not depend on copied conversation metadata.

## What changed

- Use a shared child startup path for fresh and history-forked agents, inheriting selected capability roots from the spawning environment snapshot.
- Pass the spawning turn's `disabled_plugin_ids` through both spawn handlers. When omitted, inherit the parent's current choices; explicit lists, including an empty list, override them.
- Resolve the parent before startup so inherited client MCP settings apply even when only the session source identifies the parent.
- Carry plugin choices into delegates with inherited isolation and preserve saved capability roots when resuming a child.

## Testing

Add regression coverage for executor skill listing and reading, plugin MCP registration with both history modes, plugin overrides, capability-root precedence and isolation, and restoring saved child settings after parent settings change.

GitOrigin-RevId: 2a6891a9bc6372fd2d1f30add2b5611f96b60594
2026-10-08 19:21:57 +00:00
virajrai-oai bfe0fb9bb9 Fix config rebuild call in the Windows MXC preference test (#52225)
Remove the obsolete `default_zsh_path` argument from the call to
`Config::rebuild_with_session_layers` in
`local_mxc_preference_preserves_configured_backend` to match its current
signature.

GitOrigin-RevId: ddb7a73535cc605917971b974333d69bf3a92a93
2026-10-08 18:55:41 +00:00
stevenlee-oai 89d68bc8d2 Add configurable default plugin activation policy (#52220)
## What changed

Support `plugins._default.enabled` with explicit per-plugin `enabled` overrides. Omission preserves existing source and account enablement; configuration cannot activate a plugin disabled at its source. Plugin settings such as remembered tool approvals inherit the default unless `enabled` is explicitly set.

Apply the policy to plugin skills, MCP servers, Apps, and hooks, including selected executor roots and runtime configuration refreshes. Preserve the latest plugin policy when adding MCP dependencies and rebuild hooks when concurrent configuration updates replace their inputs.

Report effective enablement in `plugin/list`, `plugin/installed`, `plugin/read`, and `plugin/share/list`. Remote installation still installs disabled packages, but skips MCP and Apps authentication setup without writing an enablement override.

## Testing

Add regression coverage for default inheritance and explicit overrides, source-disabled plugins, policy refreshes during active turns, disabled or malformed selected plugin roots, and remote installation authentication behavior.

GitOrigin-RevId: 83b70c5b47fc95474fec292f248683f1f887221e
2026-10-08 18:42:58 +00:00
tongzhou wang ad54b75574 Track source attribution for individual context parts (#52195)
## What changed

- Add `ContentItemMetadata` to distinguish user input, developer instructions, `AGENTS.md`, skills, harness context, and tool-supplied context independently of message role and content classification.
- Keep attribution attached to content through prompt assembly, history processing, and hook-output spilling. Distinguish command hooks from MCP hooks and retain tool namespaces when known.
- Treat missing historical attribution as unknown and send per-content metadata only to Responses Lite.

## Testing

Update request and history assertions to cover attribution persistence and Responses Lite metadata handling.

GitOrigin-RevId: 24e56005f5bdb98bf82f2b3943f29c4c81f3d587
2026-10-08 17:56:54 +00:00
iceweasel-oai f90a578f76 Enforce managed MXC requirements on Windows (#52193)
## What changed

Add `windows.require_mxc` to managed requirements. When set to `true` on Windows, reject configurations whose effective local sandbox backend is not MXC without changing the selected backend.

Validate after cloud configuration loads and outside startup recovery fallbacks. Apply the check to app-server startup and configuration loads, in-process bootstrap, session creation, sandbox debugging, and runtime configuration refreshes.

## Testing

Extend configuration tests to cover required and optional MXC selection, separately loaded policy requirements, and runtime refresh validation. Expand app-server startup tests to cover local and cloud MXC requirements, cloud preference selection, and failures without default-config recovery.

GitOrigin-RevId: 16456611bfd9df77e7f959b52515f1885b59ac75
2026-10-08 17:48:32 +00:00
Michael Bolin 78a19f5ab5 Expose a verified sandbox launcher to local MCP servers (#52182)
## Why

MCP servers receiving sandbox state need a usable Codex executable to launch commands with the issuing call's policy. HTTP and remote servers cannot assume access to the host's filesystem.

## What changed

- Include optional `codexExecutable` metadata for local stdio servers when the host supplies an absolute, UTF-8 path to a CLI supporting `sandbox --sandbox-state-json`. Cache capability probes by executable path and bound them to five seconds.
- Document forwarding the sandbox state unchanged and requiring an explicit opt-out rather than silently falling back to PATH lookup or unsandboxed execution when the launcher is absent.
- Honor `useMxc` from forwarded sandbox state when selecting the Windows sandbox backend and network proxy policies, preserving a parent's selection made through CLI overrides.

## Testing

Add coverage for launcher eligibility across local, remote, and HTTP servers, invalid or missing executable paths, and binaries without sandbox-state support. Extend metadata integration and serialization tests to cover the optional launcher field, legacy state, and unknown future fields.

GitOrigin-RevId: ea8cd3770616e5a620b423a01052a7bc828bceb9
2026-10-08 17:25:09 +00:00
surajs-oai 8c818cbed4 Make environment context date and timezone configurable (#52164)
## What changed

Add `include_environment_context_time`, enabled by default. Setting it to `false` omits `<current_date>` and `<timezone>` while retaining the rest of the environment context, and skips the clock read used to populate the date.

## Testing

Extend configuration, session context, and external time provider tests to cover enabled and disabled time fields, context updates across turns, and current-time reminder behavior.

GitOrigin-RevId: 5071ce1701c044b680624d0cdbba7e0bc2b5bbe6
2026-10-08 16:27:10 +00:00
jif cd85a26cae Remove the patched zsh shell execution backend (#52160)
## What changed

- Use the standard shell executor and remove the zsh fork escalation runtime, `codex-execve-wrapper`, and `shell-escalation` crate.
- Ignore `shell_zsh_fork` and `unified_exec_zsh_fork`, emit migration notices for legacy configuration, and warn when ignoring managed requirements for these flags.
- Keep the active session's `apply_patch` alias directory readable under restricted filesystem permissions.

## Testing

Add coverage for legacy configuration startup and shell execution, migration notice rendering, active alias directory selection, and nested `apply_patch` execution while other files in `CODEX_HOME` remain unreadable.

GitOrigin-RevId: 43af461fea32b4980550ee7237effd2bc0646ed8
2026-10-08 16:19:09 +00:00
Leonardo Di Donato 9b738582b1 Expose originating tool call metadata in command environments (#52119)
## Why

Command processes need thread and tool call labels for correlation, without stale values from inherited environments or cached shell snapshots.

## What changed

- Export the originating `exec_command` call ID as `CODEX_TOOL_CALL_ID`; later `write_stdin` calls leave it unchanged.
- Apply executor metadata as `CODEX_THREAD_ID` and `CODEX_TOOL_CALL_ID` after environment policies, overlays, and snapshot replay. Clear omitted fields when metadata is present; without metadata, preserve thread context and remove the call ID.
- Exclude both IDs from newly captured snapshots and omit the call ID from capture and validation helpers.
- Preserve empty call IDs, omit NUL-containing IDs, and handle case-insensitive environment names on Windows. Document that these labels support correlation, not authorization.

## Testing

Add regression coverage for metadata precedence, missing and invalid IDs, snapshot capture and replay, local and remote execution with pipes and TTYs, sandboxed remote execution, and preservation of the originating call ID across later input.

GitOrigin-RevId: 1027212b5d495d8e7cfac0f498c3134e060aa897
2026-10-08 13:45:19 +00:00
jif 2fdf047c96 Fix idle cleanup for disconnected multi-agent v2 children (#52081)
## Why

Persisted multi-agent v2 children created after the client disconnects need lifecycle listeners so their runtimes can be released once idle. Listener attachment must also wait for an earlier runtime's cleanup to finish.

## What changed

- Start lifecycle listeners for persisted v2 children even when no initialized clients are connected, and defer attachment until pending unload cleanup completes.
- Keep ephemeral children loaded so follow-up tasks retain their model context.
- Raise the default `thread_unload_delay_secs` from 60 seconds to 1800 seconds (30 minutes), updating the configuration documentation and sample.

## Testing

Add regression coverage for children spawned after disconnect with zero- and one-second unload delays, including waiting for pending cleanup, keeping running threads loaded, releasing idle runtimes, and preserving an ephemeral child's earlier reply across a follow-up. Update configuration tests for the new default and explicit overrides.

GitOrigin-RevId: 2fecc77b5c03237aa8fd7eacc4bd119b99d36e0a
2026-10-08 11:52:25 +00:00
ioanbudea-OAI be2e129ecd Require assessment text in the Guardian parser (#52065)
All callers already check that an assessment payload is present before parsing it. Change `parse_guardian_assessment` to accept `&str` instead of `Option<&str>` and remove its redundant missing-payload check.

Update the callers and existing parser tests to pass text directly.

GitOrigin-RevId: e4fb4bf7aca5b20f25f5b27300ce9a6f22c97939
2026-10-08 11:01:28 +00:00
felixxia-oai 624b45c4dc Run Guardian conversation classifiers concurrently and preserve action order (#52061)
## Why

A conversation classifier waiting for preparation or full response completion can block newer classifications. Concurrent reviews also need to prevent a later action's evidence or low-risk score from being reused for an earlier action.

## What changed

- Run conversation classifications independently, forking the latest compatible completed history from an earlier action. Only a valid completion with a newer action index can replace retained history.
- Keep admission and observation ordering atomic, and hold capacity permits through full response completion.
- Reject cached low-risk scores from later actions for tool-linked approvals, including initial approval checks.
- Track originating tool-call IDs separately from approval display IDs, preserving stdin write provenance and excluding synthetic MCP elicitation IDs from tool ordering.

## Testing

Add regression coverage for delayed preparation, capacity admission, out-of-order completion, cancellation, invalid retained output, and history snapshots. Exercise pending approval ordering in both `snapshot` and `conversation` modes, and verify linked and unlinked MCP elicitation provenance.

GitOrigin-RevId: 097476ccb3b8718369a69f55c3c39132f7f1a4c1
2026-10-08 10:42:28 +00:00
jif b12ac84be9 Add regression coverage for cancelled agent reloads (#52040)
## What changed

Add `cancelled_v2_send_finishes_reload_registration` to verify that cancelling a multi-agent V2 send during an evicted child's reload does not cancel registration. The test checks that the thread-created notification arrives and evicted-environment state is cleared.

Evict and reload the child again with only one child slot available to catch leaked residency pins or reservations, and verify that only the subsequent follow-up message is delivered.

GitOrigin-RevId: ce6ed90d0049245370f26d8dbb35b9f1cd0b3063
2026-10-08 09:48:47 +00:00
jif d2a6dac20b Preserve agent state when unloading idle multi-agent v2 children (#52034)
## What changed

- Route app-server idle unloading of multi-agent v2 children through local eviction that preserves unread mail and environment selections for reload.
- Hold residency pins through input submission so newly reloaded children cannot be evicted before receiving their work.
- Guard listener cleanup against replacement runtimes and subscriptions, and reject local eviction of host-controlled threads.

## Testing

Add coverage for unsubscribe-driven eviction followed by `followup_task`, verifying restored conversation context and exactly-once delivery of queued mail. Extend tests to check that residency pins block eviction and that rejected host eviction preserves the thread and mailbox.

GitOrigin-RevId: e36723730af683d2081e495e637f0e6d23548b8d
2026-10-08 09:39:33 +00:00
iceweasel-oai ea27864f99 Log Windows sandbox availability and backend selection (#51974)
## What changed

Record local MXC availability and the selected Windows sandbox backend at app-server and session startup. Log the backend again when an accepted session settings update changes the Windows sandbox level, using a blocking task for the log write.

Selection entries distinguish `mxc`, `disabled`, `unelevated`, and `elevated` in the sandbox logs under `.sandbox` in Codex home.

## Testing

Update the remote thread persistence assertion to allow the `.sandbox` directory on Windows, since startup logs are not thread persistence artifacts.

GitOrigin-RevId: 4130b59ac7761223775ac9b6afb096abb7fb4615
2026-10-08 06:31:56 +00:00
tongzhou wang e974aad3b1 Support model-specific function description prefixes (#51930)
## What changed

Add `functions_namespace_functions_description_prefixes` to model tool messages, keyed by unqualified tool name. Prepend this guidance to descriptions in the `functions` namespace across direct declarations, Code Mode documentation, and tool-search results, including custom tools.

Trim prefixes, ignore empty values and unavailable functions, and enforce a combined 256-byte UTF-8 limit including separators for reachable tools. Keep overrides local to each step, preserve search ranking text, and retain runtime caches for unaffected tools.

## Testing

Extend coverage for direct and indirect descriptions, clearing prefixes when switching models, namespace scoping for deferred dynamic tools, and tool-search cache reuse and reset.

GitOrigin-RevId: f434e37cec010764fe3e09fb12c339e933b3c21c
2026-10-08 03:20:54 +00:00
mandal-OAI 82e70121f8 Honor the user input setting for asynchronous questions (#51908)
## Why

Disabling `experimental_request_user_input_enabled` previously left `request_user_input_async` available when the model advertised support for it.

## What changed

Require the user input setting to be enabled before registering `request_user_input_async`, while preserving the root-agent restriction and support for both current and legacy model capability names.

## Testing

Add parameterized tests covering enabled and disabled settings, current and legacy capability names, missing capabilities, and subagents. Also verify that `send_message_to_user_async` remains available to root agents independently of the user input setting.

GitOrigin-RevId: 27156a3fe7da38d10fccb6384f28e755c39abc39
2026-10-08 02:06:58 +00:00
pakrym-oai fac5d0ba91 Report specific reasons for WebSocket continuation failures (#51895)
## Why

Full WebSocket requests previously used the generic `other` reason when continuation failed because request properties or input changed, obscuring why incremental reuse was unavailable.

## What changed

- Report specific reasons for changed request properties, shortened or mismatched input, and missing response state or response IDs.
- Add `previous_item_type` and `current_item_type` labels to continuation metrics and failure traces. Diagnostics use bounded labels without request contents or identifiers.
- Centralize response item type names in `ResponseItem::item_type()` and reuse them for output logging.

## Testing

Add coverage for unavailable response state and empty response IDs. Expand WebSocket tests to check fallback reasons and item types for rewritten or shortened input, replaced input, changed model, and changed output schema, including precedence when multiple properties change.

GitOrigin-RevId: 3951853dfe87d40b7046af6f6a8efd5d4f5b06d1
2026-10-08 01:02:21 +00:00
Alex Kira 70efa82b09 Record metrics for incremental tool updates (#51893)
## What changed

Record `codex.tools.incremental_updates` through session telemetry with an `action` tag for `added`, `removed`, and `schema_changed`. Definition changes include description edits.

Exclude initial catalogs, unchanged tools, and namespace headers from the counts. Count each removed namespace member even when the removal notice lists only the namespace.

## Testing

Extend the namespace transition snapshot test with in-memory metric assertions covering additions, removals, definition changes, and excluded initial or unchanged catalogs.

GitOrigin-RevId: 0fadb40a3aa7abf5ef1757811ebfb5749505b3d9
2026-10-08 00:56:11 +00:00
ningyi-oai 35a9b70444 Preserve tool call completeness when recorded arguments are truncated (#51892)
## Why

Truncating recorded arguments does not lose the call inventory. Clearing `tool_calls_complete` in that case incorrectly treats retained calls and tool names as incomplete.

## What changed

Define `tool_calls_complete` as completeness of the ordered call inventory, independent of recorded arguments. Preserve it for direct tool outputs and Code Mode cells when argument limits or message budgets truncate arguments, including across later waits. Continue clearing completeness when calls are omitted or tool names are truncated.

## Testing

Update protocol, recorder, and integration tests to verify completeness survives argument truncation and message budgeting. Add coverage confirming that omitted calls and truncated tool names still clear completeness.

GitOrigin-RevId: 1534dbfabbd1291b840dd6fb6738ed51bcd4c0c4
2026-10-08 00:54:27 +00:00
liame-oai ec8251c545 Add experimental prediction forks that inherit parent context (#51884)
## Why

Prediction forks need to preserve the parent's effective context and request settings to maximize prompt-cache reuse.

## What changed

- Add `experimentalPredictionMode` to `thread/fork` for ephemeral forks of loaded, persisted parents. Reject configuration overrides, `path`, `lastTurnId`, and `beforeTurnId` in this mode.
- Inherit the parent's effective configuration, tools, environments, collaboration settings, disabled plugins, and persisted history.
- Enable `features.reasoning_effort_override` on the fork while preserving the parent's request-effort baseline, including when overrides were disabled on the parent.
- Report the fork's effective model, service tier, and reasoning effort in the response.

## Testing

Add coverage for matching parent and fork requests and prompt-cache keys across legacy and paginated history, invalid fork parameters, and reasoning-effort inheritance. Add a context snapshot for identical parent and fork continuations.

GitOrigin-RevId: 46b41f2ac331562b441dadff1a0a9f926c94880d
2026-10-08 00:09:03 +00:00
Eric Traut f73a478c87 Keep global app-server config independent of the launch directory (#51872)
## Why

Global requests can inherit project settings from the app-server's launch directory. This can prevent marketplace removal or expose project-only feature settings, and config reloads can fail if that directory is deleted.

## What changed

- Load configuration without project context when no working directory is supplied, using `CODEX_HOME` to materialize `Config.cwd`.
- Use global configuration for marketplace mutations, marketplace upgrade reloads, and MCP requests without thread context.
- Pass the launch directory explicitly during startup to preserve project-aware startup configuration.

## Testing

Update regression tests to verify that marketplace removal ignores launch-project configuration and leaves the project config intact. Extend feature-list coverage to verify that global requests ignore project features, thread requests retain them, and global requests work after the launch directory is deleted on Unix.

GitOrigin-RevId: b77063a7ea0b09fd0a79cfc4040db9f1d02606b3
2026-10-07 23:19:26 +00:00
Alex Kira fbe97c7929 Record tool registration metrics for each sampling request (#51868)
## What changed

Add the `codex.tools.registered` histogram to count finalized tool registrations by `exposure` and `tool_mode`, including zero counts for empty exposure categories. Record it once per sampling request before transport retries, excluding hosted tools. These counts describe the registered inventory, not model visibility or tool reachability.

## Testing

Add an integration test covering a stream retry, direct and deferred namespace tools, a model-only tool, and hosted web search. Verify that registrations are recorded once, hosted tools are excluded, and metric labels contain no tool names or descriptions.

GitOrigin-RevId: 02b450743886e3d487d6c3bcda12eb65f6d1104b
2026-10-07 23:11:18 +00:00
iceweasel-oai cba716c0f1 Run sandbox integrity checks before commands and filesystem operations (#51843)
## What changed

Wire existing sandbox integrity checks into local command preparation, exec-server process preparation, and sandboxed filesystem helper and file-open operations. Make execution request preparation asynchronous so callers can await the checks.

The checks remain observational: failures and timeouts do not prevent command execution.

## Testing

Add regression tests that launch a real command after checker preparation fails or exceeds its timeout, verifying successful output and exit status.

GitOrigin-RevId: a82399f8aeb8b08f9965e6121b4c7f460552af3f
2026-10-07 21:52:43 +00:00
iceweasel-oai 622e9e3696 Preserve sandbox overrides across execution requests (#51786)
## What changed

Move `SandboxOverride` into the shared protocol and carry the controller's selection through tool attempts, execution requests, and exec-server process and filesystem sandbox preparation. Include it as `sandboxOverride` in filesystem sandbox contexts for observation without granting broader permissions or altering sandbox commands.

Default missing values to `NoOverride` and omit that value when serializing to preserve compatibility with existing requests.

## Testing

Extend tests to cover override propagation, wire round-trips for all three variants, and deserialization of requests without `sandboxOverride`.

GitOrigin-RevId: 2f438cf4aef1134e3149959d14aa731682168ae5
2026-10-07 17:59:22 +00:00
zbarsky-openai 9dd798805f Prevent recursive Tokio tracing in telemetry and SQLite logs (#51775)
## Why

Tokio runtime tracing can cause SQLite log writes to enqueue more writes and exporter activity to generate further OTLP exports.

## What changed

- Exclude `tokio` and `runtime` spans from OTLP export alongside `h2` spans.
- Limit `tokio::` and `runtime::` targets to `INFO` in the default log filter, and reject their `TRACE` events directly in the SQLite sink even without an outer filter.
- Box and pin the session-loop future before spawning it.
- Reorder tracing and Tokio test attributes, restrict the skills concurrency test's subscriber to the catalog-refresh span, and use the default log filter in the SQLite formatter comparison test.

GitOrigin-RevId: f545013a2469088d7f9890c1f46bb93eb5446d2d
2026-10-07 17:28:32 +00:00
Owen Lin 4d53e6ba0e Reuse MCP handler metadata for cache comparisons (#51755)
## What changed

Remove the duplicate tool metadata stored in `CachedMcpHandler` and compare incoming metadata directly with `McpHandler::tool_info()`.

Preserve complete agent plugin namespace descriptions in the handler, applying the existing 1,000-byte limit when building tool specs and search metadata. Truncation continues to respect UTF-8 character boundaries.

## Testing

Extend the agent plugin namespace description test to verify that the handler retains the full description while search output remains bounded.

GitOrigin-RevId: d0a9d5f6796143315235e658e77e059657e85f13
2026-10-07 16:35:05 +00:00
jif 2dae757b87 Load persisted sender context for Guardian reviews (#51734)
## Why

Guardian cannot capture sender instructions from another host when the sender thread is absent from the receiver's local runtime.

## What changed

Fall back to the authenticated thread store to reconstruct sender history without resuming the sender. Respect compaction and rollback, and label persisted evidence to indicate that newer unpersisted messages may be missing.

Limit storage reads to five seconds and capture sender context before acquiring the active-turn lock. Bind the captured evidence to the turn that accepts the delivery, allowing an existing turn to finish while the read is pending.

## Testing

Add cross-host scenarios for legacy and paginated history that verify sender evidence reaches only Guardian and excludes rolled-back permissions. Add a gated storage-read test that verifies turn completion remains unblocked and evidence is bound to the newly accepted turn.

GitOrigin-RevId: fe896f4e82fe3e32017fe4884846f3fa90a87949
2026-10-07 15:47:21 +00:00
swastik-oai 0a2a64e942 Honor tool-description-first ordering in Code Mode (#51704)
## What changed

Apply `code_mode_tool_description_first` when preparing nested tool definitions for Code Mode execution and tool search. When enabled, place each tool's description before its namespace description; otherwise, preserve namespace-first ordering.

Reuse cached MCP definitions only when both the input schema budget and description-order setting match.

## Testing

Extend deferred app tool integration tests to cover both description orders with and without ranked search, including consistency between search results and `ALL_TOOLS`. Extend the MCP cache test to reject reuse when the description-order setting changes.

GitOrigin-RevId: 1e3f84d2d95c200aef21ad710d367274b2169b4b
2026-10-07 14:32:44 +00:00
olliem-oai 3421c660d0 Roll back stale Guardian reviews before reusing reviewer history (#51683)
## Why

Authorization updates during a pending Guardian approval can invalidate its decision. Retries need the updated guidance without inheriting the invalidated review or losing earlier valid context.

## What changed

- Validate authorization while the reviewer is reserved, before publishing its history checkpoint.
- Roll back stale attempts to the last committed review, preserving earlier valid reviews across repeated invalidations.
- Pin the issuing action's repository instruction snapshot for reviewers and retries, avoiding fresh instruction discovery through disconnected executors.
- Treat stale authorization as a request for a new review rather than a failed decision.

## Testing

Add regression coverage for repeated approval invalidation, retention of earlier valid context, exclusion of stale decisions, and execution of the pending action exactly once. Extend the disconnected-executor test to verify that retries retain repository instructions and use updated authorization.

GitOrigin-RevId: 0bff6cc551fee1f0905082eb97ccdecaa8628867
2026-10-07 13:05:06 +00:00
jif b17c74cfd5 Record telemetry for AGENTS.md changes made by apply_patch (#51652)
## What changed

Increment `codex.agents_md.edit` for committed `apply_patch` changes to `AGENTS.md` and `AGENTS.override.md`, matching filenames case-insensitively and tagging the counter with the normalized filename.

Count additions, deletions, updates, and distinct move destinations, including changes committed before a later patch failure.

GitOrigin-RevId: bcbfa671acb37a2a24fe7e4effc9318981a22ec7
2026-10-07 11:19:12 +00:00
jif 30bdfec59d Persist Guardian review failures for reports across restarts (#51651)
## Why

Failed Guardian review evidence was process-local, so restarting Codex lost the context needed for later diagnostic reports.

## What changed

- Persist failed-review records in SQLite before reviewer cleanup, retaining at most 64 records globally, eight per thread, and 8 MiB of evidence. Delete persisted evidence when its reviewed thread is deleted.
- Recover and deduplicate persisted and in-memory records for the reported task tree when uploading `auto-review-failures.jsonl`.
- Bound persistence attempts to 250 ms and retain an in-memory fallback when storage is unavailable. Keep capture gated by user opt-in and non-ephemeral sessions, and export evidence only when logs are included.

## Testing

Add coverage for persistence across reopen and process restart, retention limits, cascading deletion, busy-storage fallback, and report uploads with and without logs, including SQLite log failures.

GitOrigin-RevId: ea2da1818d4a5da3da29f211042ca45e834342bc
2026-10-07 11:18:05 +00:00
Nick Steele a6baf8867c Signal abandonment of unanswered MCP elicitations (#51611)
## Why

Published MCP elicitation requests could lose their response waiter without notifying the event consumer that the request was no longer answerable.

## What changed

- Add `ElicitationAbandoned` with the original server name and response token for requests published through unbounded event channels.
- Emit abandonment exactly once when a waiter is dropped, response delivery fails, or the MCP runtime shuts down.
- Close the elicitation router during shutdown, reject new requests on unbounded sources, and wait for terminal deliveries before shutdown completes. Preserve bounded sources' request-only behavior and backpressure.

## Testing

Add router tests for ordered, exactly-once abandonment, closed receivers, failed response delivery, shutdown coordination, and bounded-channel backpressure. Add a core integration scenario verifying that a pending form's abandonment precedes `ShutdownComplete`.

GitOrigin-RevId: 53fe9f4a8b32f7324be180288aa492f31f4d2057
2026-10-07 07:57:14 +00:00
mikelam-oai 18e28fe1b9 Complete dynamic tool lifecycles on cancellation (#51556)
## Why

Interrupting a turn or terminating a Code Mode cell can drop a pending dynamic tool handler before it publishes its completion. Cancellation needs to settle the call in live events and persisted history without allowing a late response into model context.

## What changed

- Let dynamic tool handlers observe cancellation and publish their terminal item before dispatch finishes. Calls cancelled while awaiting a response complete with a failed item and a cancellation error.
- Keep readiness, dispatch admission, registry lock waits, hooks, and output processing cancellable so cancellation can finish even when a hook is blocked.
- Report an aborted tool lifecycle outcome when cancellation interrupts dispatch, including before handler execution.

## Testing

Add regression tests for turn interruption with pending calls or blocked hooks, cell termination with persisted failure and late-response exclusion, cancellation before dispatch admission, and exactly one completion when a response races cancellation.

GitOrigin-RevId: 0112fc74c8652c91503ed5bbfb334ae2e26930ef
2026-10-07 03:07:51 +00:00
iceweasel-oai e95abcdf49 Add a Windows MXC sandbox opt-out (#51547)
## What changed

Add `windows.allow_mxc` to configuration and its JSON schema. Setting it to `false` blocks automatic MXC selection even when `features.prefer_mxc` is enabled, and rejects explicit `windows.sandbox = "mxc"` configuration with a clear error. Omitting the setting preserves existing behavior.

## Testing

Extend configuration tests to cover disabling automatic MXC selection and rejecting explicit MXC configuration when `windows.allow_mxc = false`.

GitOrigin-RevId: bf7c0648cfcb3cc1d0dc41b9faffcb8078672780
2026-10-07 01:52:09 +00:00
Zahan Malkani 4aaee872e3 Add completion-aware realtime attachment and session-scoped detach (#51539)
## Why

A delayed detach or cleanup from an older realtime conversation must not close its replacement or end the replacement's history segment. Realtime start parameters can also contain credentials in text and transport endpoints, so diagnostics should avoid exposing them.

## What changed

- Add `RealtimeConversationAttach` to report the connection attempt's result through a reply channel, using the sequential start path.
- Add `RealtimeConversationDetach` to close only the matching `realtime_session_id` after earlier starts finish. Detaching an older session leaves the replacement connected.
- Emit the previous conversation's close event before starting its replacement, and prevent stale fanout cleanup from closing or clearing the replacement's context.
- Limit `ConversationStartParams` debug output to output modality, initial item count, and protocol version.

## Testing

Add coverage for attachment completion after the handshake, stale detaches, failed replacement and retry, natural-close ordering, handoff history after replacement, and debug redaction for existing-call and WebRTC transports.

GitOrigin-RevId: 23aee6f70522f0b17e6aa9349dbbcc2ea985f233
2026-10-07 01:28:59 +00:00
zm-oai ed59a6c1cd Preserve the CLI MXC preference in executor config reads (#51525)
## Why

Executor config reads omitted the startup `features.prefer_mxc` override, so clients could not see the CLI sandbox preference.

## What changed

- Include the explicit CLI `features.prefer_mxc` value in `environmentConfig/read` as a `session-flags` layer, above project config and below legacy managed file and MDM config.
- Retain only this preference from startup overrides.
- Expose `windows_mxc_allowed_by_config` to share MXC eligibility checks after callers resolve the active permission profile.

## Testing

Add CLI and remote executor coverage for preference propagation and filtering, plus a unit test verifying that both legacy managed config sources retain precedence.

GitOrigin-RevId: 5ac6f5257f1e807c2f197dcf5dcb2385cedca0ea
2026-10-07 00:29:04 +00:00
Krish Chainani 19c4793964 Pass thread persistence intent to attachment uploads (#51517)
## Why

Attachment stores need to distinguish uploads from ephemeral threads, which intentionally skip durable persistence.

## What changed

Add `ephemeral` to `UploadRequest` and propagate the turn configuration through image preparation for messages, tool outputs, and history replay. Include the flag in debug output while keeping attachment bytes redacted.

## Testing

Extend the Guardian context-budget test to assert that a persistent Guardian uploads exactly one image with `ephemeral: false`. Update the attachment debug-output assertion to include the new field.

GitOrigin-RevId: 42814c514a571ed6798e4dcf79a22028ee4efc28
2026-10-06 23:44:17 +00:00
keith thornhill 24edd7b890 Expose detailed agent tree shutdown failure reports (#51515)
## Why

Agent tree shutdown previously returned a generic error without identifying which operation or thread failed, making cleanup failures difficult to diagnose.

## What changed

- Add `AgentTreeShutdown::wait_detailed()` and public report types while preserving the existing `wait()` result and error message.
- Record operation, optional thread ID, and either an abandoned teardown guard or a failed phase with a payload-free error category across session cleanup, child spawn cleanup, and resident eviction.
- Give each tree a correlation ID, log each failure, and retain up to 64 failures with a count of additional failures omitted. Record failures before releasing tree membership so all completed waiters observe the same report.

## Testing

Add unit coverage for aborted and completed teardown, cloned guard context, concurrent and repeated waiters, omitted failure counts, and report formatting without raw error payloads. Extend integration coverage for successful tree shutdown and persistence writer failures, including compatibility with `wait()`.

GitOrigin-RevId: 68784af28b63e875b00a55d78729f0cc5b01ac15
2026-10-06 23:28:55 +00:00
zm-oai 7efc49b258 Align Windows sandbox temp permissions with the child environment (#51512)
## Why

Windows temp grants could fall back to host `TEMP`/`TMP` values and bypass read-only or denied subpaths. Sandbox permissions must match the environment passed to the child process.

## What changed

- Resolve `:tmpdir` from absolute `TEMP`/`TMP` paths in the completed workload environment, preserving access modes and missing-path rules without falling back to host values.
- Deduplicate Windows environment keys case-insensitively in a deterministic order so permission resolution and the child environment select the same value.
- Use the resolved temp policy for elevated sandbox overrides across core execution, exec-server, and direct spawning.
- Launch direct-spawn sandbox wrappers with the supplied Codex executable, materializing an inner helper only when it is that executable.

## Testing

Add Windows regression coverage for temp-only writes, read-only and denied carveouts, mixed-case and duplicate environment keys, unavailable temp paths, and empty or missing write-root overrides. Exercise core execution and direct spawning, and extend exec-server RPC coverage to the elevated backend with temp values set through the environment policy.

GitOrigin-RevId: 16b8bd4702cc434fd743a08c75a3e4515780bff3
2026-10-06 23:21:06 +00:00
mtsui-oai 044da98b4a Expose selected environments to MCP contributors (#51503)
## Why

MCP contributors need the complete executor selection to distinguish an unavailable primary executor from a ready secondary. Ready capability roots alone do not preserve pending or failed selections.

## What changed

Add `with_selected_environments` and `selected_environments` to `McpServerContributionContext`, and pass the captured selections during thread MCP resolution and model-step plugin selection. Preserve priority order and pending or failed entries. Use `None` for threadless discovery and `Some(&[])` for an explicitly empty selection.

## Testing

Add regression coverage for executor ordering with pending and failed selections, environment context in model-step plugin selection, and the distinction between absent and explicitly empty selections.

GitOrigin-RevId: 2c1222fae72c7e2c75b2f40abfad3b2048cf9316
2026-10-06 23:07:48 +00:00
Adam Perry @ OpenAI 9479e1fdb7 Bind capability roots to environment selections (#51493)
## Why

Capability discovery needs the roots captured with each environment snapshot. Threads sharing an executor can select different roots, and changing environment order must preserve executor skill aliases.

## What changed

- Attach the receiving thread's capability roots when constructing `TurnEnvironmentSelection` at startup and settings updates, including roots loaded from saved history.
- Resolve capability roots from environment snapshots while preserving their original order. Retain startup roots so deselecting and reselecting an environment restores its capabilities.
- Match inherited configuration by environment and workspace so differences in capability root metadata do not interrupt configuration propagation.

## Testing

Add regression coverage for root ordering across environment states and configuration changes, independent root selections on a shared executor, reselection with startup or saved roots, active turn updates, and pending configuration failures reaching child and grandchild threads.

GitOrigin-RevId: 4f2e4bb414d27195a6752406117a6050718a1198
2026-10-06 22:39:32 +00:00
pakrym-oai 28cd3e2501 Remove obsolete fields from persisted turn context (#51492)
## What changed

Remove `workspace_roots`, `current_date`, `timezone`, `network`, `personality`, and `multi_agent_mode` from `TurnContextItem` and stop recording them in rollouts. Update the precomputed protocol schema accordingly.

Make `summary` optional when reading turn context and write `"none"` as a compatibility placeholder for older readers, rather than persisting the active reasoning-summary setting.

## Testing

Update protocol tests to cover omitted `summary` fields and compatibility-placeholder serialization. Extend compaction tests to verify that model requests retain the updated reasoning-summary setting after compaction while the rollout checkpoint records the placeholder.

GitOrigin-RevId: d49eabaa1b340be1d79f7f09115281a307ea8a64
2026-10-06 22:39:06 +00:00
Adam Perry @ OpenAI c9870d0157 Use PathUri for skill identity and path matching (#51482)
## Why

Skill selection and disabled-path matching need to recognize equivalent Windows paths across case and separator differences while preserving literal spaces, `%`, and `#` in native filenames.

## What changed

- Carry `PathUri` through skill metadata, discovery mappings, filesystem lookups, disabled-path sets, and invocation analytics.
- Match linked skill mentions and TUI selections by parsed path identity.
- Use `LegacyAppPathString` for app-server skill paths and regenerate schemas and SDK types, preserving native path strings on the wire.
- Preserve native catalog display paths and ordering. Keep host filesystem probes and configuration writes restricted to host-compatible paths.

## Testing

Add regression tests for Windows path identity and disabled-skill matching, literal filename characters, catalog resource reads, native path ordering, and foreign-path analytics normalization.

GitOrigin-RevId: c212916dc9fef0e7616542726e107f0d6a313267
2026-10-06 21:29:35 +00:00
pakrym-oai e79c498b5e Preserve tool declaration mode across resumed context windows (#51480)
## Why

Changing the incremental tools setting on resume should not move tool declarations and base instructions within an existing context window.

## What changed

- Determine the current window's tool declaration mode from its history, and apply the incremental tools setting when building a new window after compaction or a context reset.
- Use that mode consistently for sampling, remote compaction, startup prewarm, prompt debugging, and Guardian input budgeting.
- Preserve tool declarations alongside their comparison baseline in full-history agent forks, including compacted histories; remove them together when rebuilding context.

## Testing

Add request snapshots covering legacy resume, migration after remote compaction or a context reset, disabling incremental tools, and tool updates after restart. Extend agent fork and WebSocket startup prewarm tests to cover retained declarations and incremental tools.

GitOrigin-RevId: 7c46849a1788027a8435082e4d1f7e7f48d2700c
2026-10-06 21:28:13 +00:00
chess 5679e675f4 Keep submission logs useful without exposing payloads (#51467)
## Why

Submission diagnostics need approval and turn metadata without logging user input, tool responses, commands, paths, or instruction payloads.

## What changed

- Log thread and submission IDs, operation kind, and parent/root turn IDs as explicit fields.
- Give `Op` and `ThreadSettingsOverrides` selective `Debug` output that retains identifiers, approval decisions, and policy categories while omitting payloads.
- Preserve Guardian review identifiers and status when logging approval of a denied-action retry.

## Testing

Add an app-server integration test that verifies command approval, Guardian review, and turn policy metadata reach SQLite-backed diagnostic logs with `RUST_LOG=off`.

GitOrigin-RevId: 308acb7b70e4849cf31514b11e4d9b46eaf6a09b
2026-10-06 19:34:02 +00:00
felixxia-oai b2592701e1 Keep Guardian transcript records structured through budget recovery (#51466)
## What changed

Introduce `TranscriptRecord` and `PreparedTranscript` to retain attributed transcript text through preparation and composition. Cache rendered content, byte counts, and token estimates, refreshing them when text or framing changes.

Keep JSON records structured during budget recovery so truncation replaces only `text`, preserving metadata, field order, and framing without reparsing serialized JSON. Preserve whole-entry truncation for line transcripts and update synchronous and asynchronous consumers to use the preparation API.

## Testing

Expand coverage for cached estimates and delivery with escaped text, Unicode, and large payloads; metadata and framing preservation during recovery; and stable asynchronous history prefixes in both line and JSON formats.

GitOrigin-RevId: 8b3b5231ca4a6ee47d17dcc788ea68c56dd1a9bc
2026-10-06 19:31:24 +00:00