Commit Graph
4455 Commits
Author SHA1 Message Date
Dylan Hurd d06dc73290 Route intercepted exec approvals through shared review (#37851)
## What changed

- Send Unix `execve` approvals intercepted by the zsh fork through the shared approval pipeline, including permission hooks, Guardian review, user prompts, and telemetry.
- Resolve the active turn and its auto-review setting when an intercepted command needs approval, so commands sent to persistent terminals use the current turn's reviewer.
- Give each intercepted command a distinct approval ID and propagate an aborted approval as a turn abort.

## Testing

- Cover Guardian review for intercepted `unified_exec` commands and persistent terminals across turns.
- Verify repeated identical intercepted commands receive separate user approvals.

GitOrigin-RevId: e6cccf160637e4246aff4714c22f08c90b65306d
2026-08-10 17:24:51 +00:00
jif 97729885d4 Expose the session ID to shell commands (#37848)
## What changed

- Set `CODEX_SESSION_ID` to the shared root-session ID for shell tool calls,
  unified exec processes, and user shell commands.
- Preserve `CODEX_SESSION_ID` when restoring a shell snapshot, alongside the
  existing runtime-owned environment variables.

GitOrigin-RevId: 5228867d25507105c7edf11607a8298958c3b917
2026-08-10 17:02:19 +00:00
jif 4996cf05af Preserve environments when reloading V2 agents (#37847)
## What changed

- Restore a V2 agent's inherited environment selections when reloading its
  thread after residency eviction.
- Keep the restored execution environment and its tools available when the
  agent receives a follow-up task.

## Testing

- Add an integration test that evicts and reloads a V2 agent, then verifies
  its environment selection and `exec_command` tool are preserved.

GitOrigin-RevId: a5d4ad0fa465c717b32b7ae6807486429187a41d
2026-08-10 16:57:09 +00:00
felixxia-oai 3b67b03a3f Run plugin and skill tests on Windows (#37836)
## Why

The plugin and skill test suites were excluded wholesale on Windows, even though
most cases do not depend on POSIX behavior.

## What changed

- Make generated TOML and JSON fixtures escape Windows paths correctly.
- Use Windows-safe path canonicalization and normalize advertised skill paths.
- Select test environments through the environment-aware builders.
- Run the suites on Windows while narrowly skipping cases that execute POSIX
  commands or require matching host and executor path conventions.

GitOrigin-RevId: aadf31013c2bf9bac728adc4dd96f572d4a3bf3f
2026-08-10 14:45:55 +00:00
jif d109393270 Track running unified exec processes at turn completion (#37828)
## What changed

Add the `codex.turn.unified_exec.running_processes` counter and increment it
by the number of background terminal processes remaining when a turn finishes.

GitOrigin-RevId: 82a33b89533960d86cef95360fa122836c8aa84d
2026-08-10 13:39:23 +00:00
Charlie Marsh 1c042dd4d8 Keep multi-workspace skill listings consistent (#37812)
## Why

A single `skills/list` request should use one view of shared skill roots across
all requested workspaces while still applying each workspace's skill rules.

## What changed

- Add a request-scoped host skills view that reuses non-plugin root snapshots
  across `cwd` entries without persisting them across requests.
- Resolve user-scoped plugin skill roots once per request, then apply workspace
  skill configuration separately for each `cwd`.
- Make `forceReload` refresh plugin roots before building the request-scoped
  view so subsequent entries see the refreshed skills.

## Testing

Expanded `skills/list` and host skills service tests to cover multiple ordered
workspaces, per-workspace skill rules, request-local snapshots, cached results,
and forced plugin-root refreshes.

GitOrigin-RevId: eedd3a4c3e213b7f30df6cacd3adf23ba2967437
2026-08-10 11:27:22 +00:00
jif 09f47c8785 Simplify package-based skill reads (#37808)
## What changed

- Make `package` the only required argument to `skills.read`, resolving the
  owning orchestrator or executor catalog automatically.
- Default omitted `resource` values to the package's main `SKILL.md`.
- Render orchestrator skills as package locators and instruct the model to read
  them directly without first calling `skills.list`.
- Update skill extension and app-server coverage for direct main-resource
  reads, referenced resources, aliases, and the revised tool schema.

GitOrigin-RevId: 9faf57a8d0935566a15094931eaabaa8f0613e9e
2026-08-10 11:10:01 +00:00
Charlie Marsh beeba1d2fc Share model-visible tool specs across prompts (#37807)
## Why

Building a prompt cloned every model-visible `ToolSpec`, even though the tool
set is immutable for the lifetime of its router.

## What changed

- Store model-visible tool specs as an `Arc<[ToolSpec]>` in `ToolRouter` and
  `Prompt` so prompt construction only clones the shared pointer.
- Keep separately built routers on distinct shared slices so refreshed tool
  sets remain independent.

## Testing

Extend router tests to verify allocation sharing within a router, allocation
separation across rebuilt routers, and the existing deferred-tool filtering.

GitOrigin-RevId: 1e04cd7c4d1b3fa0b494c5c51670232d38ba8ebb
2026-08-10 10:50:49 +00:00
Charlie Marsh c9c6c0daa9 Add a feature flag to preserve apply_patch line endings (#37758)
## What changed

- Add the `apply_patch_preserve_line_endings` feature, disabled by default, to
  preserve CRLF, CR, and mixed line endings when `apply_patch` updates files.
- Apply the feature consistently to built-in patch handling and patches invoked
  through shell, user-shell, unified-exec, and app-server command execution.
- Keep the active feature configuration authoritative over inherited, shell
  snapshot, and client-provided environment values.

## Testing

- Cover line-ending behavior with the feature enabled and disabled for custom
  tool calls, shell heredocs, command execution, and the `apply_patch` CLI.

GitOrigin-RevId: 531a7c66761959c650270559f57941929f03e6c4
2026-08-10 01:44:30 +00:00
sayan-oai 420accf199 Use the step context for command approval prefix rules (#37641)
## What changed

Read `allow_prefix_rules` from the turn attached to the active step context
when selecting the exec policy and constructing unified exec approval requests.

GitOrigin-RevId: d2d26e88b9cefa28bb2df5b9f71aa7b30b7ea331
2026-08-09 00:29:14 +00:00
sayan-oai dd43a9967f Use step environments for Guardian approval reviews (#37618)
## Why

Deferred environments can become ready after a turn starts. Guardian approval
reviews must use the environment selected for the current step so their working
directory and permission context are not taken from the stale turn snapshot.

## What changed

- Carry `StepContext` through tool execution and approval handling.
- Add a Guardian review context that pairs the parent turn with the current
  step's environment snapshot.
- Use that snapshot for Guardian prompts, reviewer sessions, and delegated
  reviewer threads while retaining turn-level fallbacks for callers without a
  step context.

## Testing

Added an integration test that makes a deferred remote environment ready before
an escalated command and verifies Guardian receives that environment's working
directory and denied-read policy instead of the initial local environment's.

GitOrigin-RevId: 779096bc7d0e0c7453a009c02141029714b9b407
2026-08-08 20:07:27 +00:00
cooper-oai c4513cb982 Prevent launch context from reaching child processes (#37607)
## Why

Model-reachable child processes should not inherit Codex launch context.

## What changed

- Treat `OPENAI_FEDERATION_RULE_ID` and `OPENAI_IDENTITY_TOKEN_FILE` as non-inheritable environment variables, with case-insensitive matching.
- Remove them after shell environment policy overrides and before spawning commands across execution, MCP, hooks, Git helpers, and remote helper processes.

## Testing

- Cover inherited and explicitly configured variants, including mixed-case names.
- Verify the variables are absent from real child environments and app-server command and process execution.

GitOrigin-RevId: 2535527893985fef0995617f4c5b2462bea7c136
2026-08-08 16:58:26 +00:00
Abhinav 6f647caa9b Support asynchronous command hooks (#37533)
## Why

Hook configurations can mark command handlers as asynchronous, but Codex previously skipped those handlers outside `SessionEnd`.

## What changed

- Run asynchronous command hooks in the background with a per-session concurrency limit, while keeping `SessionEnd` hooks synchronous.
- Prevent asynchronous hooks from blocking, stopping, rewriting, or otherwise controlling the operation that launched them.
- Deliver warnings and additional context at safe turn boundaries: inject results into an active turn after sampling, or buffer them ahead of the next user prompt when the session is idle.
- Preserve in-flight hooks across configuration reloads, scope spilled output to the thread, and abort outstanding work during session shutdown.

## Testing

Add unit and integration coverage for background scheduling, concurrency, output parsing, active and idle result delivery, configuration reloads, and shutdown cleanup.

GitOrigin-RevId: 8094552e4afe7b47b09a61bb575bb20f4e491d8d
2026-08-08 04:24:12 +00:00
andrewgu-oai e734a1a5c1 Ignore reusable command approvals for cyber models (#37516)
## What changed

- Filter saved `allow` prefix rules from the execution policy for cyber-specialized models and models listed in `auto_review.ignore_rules`, while preserving prompt, forbidden, network, and host-executable policy entries.
- Apply the filtered policy consistently to permission instructions, shell commands, unified exec, and the zsh-fork backend.
- Limit cyber-model command approvals to one-time decisions without proposing reusable policy amendments. General models continue to honor saved prefixes, including after switching models within a thread.

## Testing

- Add policy-level coverage for filtering allow-prefix rules while retaining restrictive and network rules.
- Add end-to-end coverage across shell and unified exec paths, zsh-fork execution, user and automatic review, and model switching.

GitOrigin-RevId: f3bd3872424291b12354ec415f33986ec369a368
2026-08-08 00:59:39 +00:00
Won Park c2bcb9a26b Reuse parent compactions in Guardian review sessions (#37513)
## What changed

- Add the under-development `guardian_reuse_parent_compaction` feature.
- Restart Guardian review sessions after parent history rewrites and seed them with the latest encrypted compaction that has a response item ID.
- Keep the existing reviewer when a rewritten history has no reusable compaction, preserving authorization and restriction context held by that session.

## Testing

- Cover reuse-key invalidation and compaction eligibility.
- Verify review-session behavior across parent compaction and a subsequent summary-free history reset.

GitOrigin-RevId: 891805d3c3dca34ddda6e3bfc5097be4ff164267
2026-08-07 23:49:12 +00:00
viyatb-oai 208f05b233 Enforce automatic review for managed models (#37511)
## What changed

- Add the managed `auto_review.required_on_models` requirement, unioning model slugs across requirement layers and exposing the result through `configRequirements/read`.
- Force listed models to use `on-request` approvals with the `auto_review` reviewer. Downgrade Full Access to workspace-write when starting a protected session, and reject incompatible runtime overrides or use when automatic review is disabled.
- Preserve these protections across thread starts, resumes, forks, model changes, turn overrides, MCP approvals, and TUI session attachment.

## Testing

- Add coverage for layered model requirements and exact provider-alias matching.
- Add app-server tests for protected thread lifecycle operations, unsafe setting overrides, legacy thread upgrades, disabled automatic review, and requirements API output.

GitOrigin-RevId: c4b1d52c3b5b75e86880725412b8f0812e0dfcd9
2026-08-07 23:43:14 +00:00
sayan-oai 4ca25a2c4e Include sandbox mode in response metadata (#37507)
## What changed

- Add the effective permission profile as `sandbox_mode` in turn metadata for regular, prewarm, compaction, and detached memory requests.
- Reserve `sandbox_mode` so client-provided metadata cannot override the computed value.

## Testing

- Cover metadata headers and request bodies for read-only and danger-full-access modes.

GitOrigin-RevId: 13c690cc99bc2691023f281ca527af049bb1286f
2026-08-07 22:41:20 +00:00
felixxia-oai 45f8cafa4e Remove the codex-core-skills crate (#37505)
## What changed

- Move `SkillLoadOutcome` and its implicit-path indexing into
  `codex-skills-extension`.
- Import shared skill types directly from `codex-skills` and keep the skill
  prompt size limit with the extension renderer that uses it.
- Remove `codex-core-skills` from the Cargo workspace and dependent crates.

GitOrigin-RevId: 4e9e84909fa2f692bcc94af990bb4671affd776f
2026-08-07 21:36:33 +00:00
felixxia-oai beac16cccd Move host skill prompt injection into the skills extension (#37503)
## What changed

- Add `HostSkillsSnapshot::load_skill_prompts` so the skills extension owns reading and rendering selected host skills.
- Keep explicit invocation telemetry, unreadable-skill warnings, plugin prompt ordering, and suppression of host prompts superseded by provider prompts.
- Remove the legacy prompt injection and fragment implementation from `codex-core-skills`.

## Testing

- Cover prompt truncation without an installed skills extension, skill/plugin ordering, selective provider supersession, unreadable skills, and contextual fragment detection.

GitOrigin-RevId: 9c8b84ad54b90d174abc287ab49cc5a231e9e1aa
2026-08-07 21:04:16 +00:00
rka-oai 8e4b10446e Remove the legacy code-mode tool metadata inventory (#37500)
## What changed

- Stop adding `code_mode_tool_names` to Responses Lite turn metadata.
- Keep `code_mode_tool_names` reserved so client metadata cannot reintroduce the removed, unbounded inventory.
- Use the opt-in `tool_namespaces_info` metadata, including each function's `code_mode_name`, when authoritative tool details are requested.

## Testing

- Update Responses Lite and code-mode tests to verify the opt-in namespace metadata and normalized code-mode names.

GitOrigin-RevId: cbfb9af984de71c7cc175d0cd47ae799a5275309
2026-08-07 20:26:08 +00:00
rka-oai 2b1811e562 Include tool namespace inventory in turn metadata (#37492)
## What changed

- Add opt-in `tool_namespaces_info` metadata for Responses Lite turns when
  `tool_registry.turn_metadata_includes_tool_info` is enabled.
- Describe each model-visible function's namespace, direct and deferred
  exposure, Code Mode name, and harness or MCP ownership.
- Reject visible namespaces shared by different owners when strict collision
  checking and tool inventory metadata are enabled.
- Keep tool inventories out of compatibility headers and metadata sent to MCP
  servers.

## Testing

- Cover opt-in behavior, MCP exposure details, namespace ownership collisions,
  reserved metadata handling, and Responses Lite request serialization.

GitOrigin-RevId: 6a6965d2ba98e29444fdfbb4ccec6aafcf0391e6
2026-08-07 19:32:15 +00:00
rphilizaire-openai ba94150c2a Alias resource-backed skill locators under context pressure (#37489)
## Why

Long executor and orchestrator resource identifiers can consume enough of the
skills context budget to omit otherwise available skills.

## What changed

- Add source-aware root aliases for executor, orchestrator, and host skill
  catalogs, including catalogs with a single shared root.
- Select the best combination of aliased catalogs under the shared metadata
  budget while accounting for root tables and alias usage instructions.
- Explain how to expand shortened `skill://` locators and accept the resulting
  description-shortening warning in app-server coverage.

## Testing

- Add rendering and production-turn coverage for singleton, executor,
  orchestrator, host, and combined catalog aliases.

GitOrigin-RevId: c1bc1f3d371eae9526232674060235272cc28f16
2026-08-07 19:09:46 +00:00
jif 27e4a05cd3 Expose runtime activity in server diagnostics (#37486)
## What changed

- Add lifecycle-backed gauges for in-flight and queued app requests, pending server requests and mailbox messages, active turns, and live MCP connections.
- Register each gauge on first use and decrement it when the tracked work or resource is dropped.
- Document the new `server/diagnostics` gauge names and account for the diagnostics request itself in the response example and test.

GitOrigin-RevId: 4bb82a3918af0b502d149b5d761ad669b2083f39
2026-08-07 18:38:24 +00:00
jif 5a0d0929e2 Keep response streams alive through connection failures (#37485)
## What changed

- Classify HTTP connection failures separately from other network errors without exposing request URLs.
- For sampling requests, retry connection failures with exponential delays from 5 to 60 seconds and show a `Reconnecting... waiting for network` stream error.
- Preserve the normal stream retry budget while waiting for the provider to become reachable. Keep the existing bounded retry behavior for other retryable errors.

## Testing

- Verify connection errors are classified without leaking URL contents.
- Verify a turn recovers after its provider becomes reachable and still applies the configured retry limit to a subsequent incomplete stream.

GitOrigin-RevId: 646553290c865a1332abd30c4a64ed9266bbfc6f
2026-08-07 18:33:46 +00:00
pakrym-oai 509565820f Interrupt active code-mode cells with their turn (#37483)
## Why

Interrupting a turn should also stop code-mode work that the turn left running.

## What changed

- Add the disabled-by-default `code_mode_interrupt` feature.
- When an interrupted turn has the feature enabled, terminate all active code-mode cells and propagate cancellation through nested tool calls.
- Keep the reusable code-mode session alive so its stored state remains available to later turns.

## Testing

Add an integration test that interrupts a long-running nested tool, verifies that active and background cells are removed, and confirms that session state is preserved.

GitOrigin-RevId: 2b8634776a89b636318a39b9e9ad2eefc07cead8
2026-08-07 18:22:42 +00:00
iceweasel-oai 511262b984 Delegate remote process sandboxing to the executor (#37480)
## What changed

- Preserve executor-native working directories, workspace roots, and permission profiles when preparing remote `exec_command` requests instead of resolving them through the host platform.
- Send sandbox intent to the remote executor, including a restricted-token default for Windows executors and `-NoProfile` for elevated PowerShell commands.
- Reject intercepted cross-platform `apply_patch` commands when filesystem writes are restricted, while continuing to allow them for unsandboxed or full-disk-write profiles.

## Testing

Extended remote unified-exec coverage for foreign Windows workspaces, elevated PowerShell, sandbox metadata, and restricted and unrestricted intercepted patches.

GitOrigin-RevId: 9fd328879fa2c15594fd58e40b6b32e8ba0847e7
2026-08-07 18:05:17 +00:00
tongzhou wang 248d8c0e22 Include call IDs in MCP requests and clarify metadata config (#37477)
## What changed

- Add the tool call ID to `_meta.callId` for every MCP tool request.
- Rename `features.tool_registry.include_tool_metadata` to
  `features.tool_registry.turn_metadata_includes_tool_info` to clarify that the
  setting controls authoritative tool information in per-turn metadata.
- Update config parsing, schema generation, and session config locking for the
  renamed setting.

## Testing

- Cover `callId` metadata for custom, plugin, and Codex Apps MCP calls.
- Update strict-config, config-loading, feature-config, and config-lock tests for
  the renamed setting.

GitOrigin-RevId: ac0e58c489b03bd9b55a356f545de86c8ecaf865
2026-08-07 17:44:05 +00:00
felixxia-oai b3278e96cb Move skill config rule resolution into codex-config (#37466)
## What changed

- Define skill config selectors, ordered rules, and layer-stack parsing in `codex-config`.
- Resolve disabled skill paths from generic skill name/path pairs, so configuration logic no longer depends on `SkillMetadata`.
- Update plugin and host skill consumers to use the `codex-config` API and consolidate the rule tests with the skill config tests.

GitOrigin-RevId: 3fe67869708df2652befe28d58cdeba933256f84
2026-08-07 16:20:38 +00:00
felixxia-oai 3b366654f1 Remove the unused remote skills client (#37461)
## What changed

- Remove the unused `core-skills` client for listing and exporting remote
  skills.
- Remove its `codex-core-skills` and `codex-core` exports and dependencies that
  are no longer needed.

GitOrigin-RevId: 747f760dc97da3d4dea10d619a2341f43410d0bf
2026-08-07 15:38:22 +00:00
felixxia-oai 33e365b19e Remove the legacy core skill loader (#37457)
## What changed

- Use `HostSkillRoot` throughout host root resolution and loading, including plugin roots.
- Remove the duplicate loader, root snapshot, and product-filtering implementation from `core-skills` now that loading is owned by the skills extension.
- Move and expand loader coverage for discovery, namespaces, filesystem routing, root merging, symlinks, and frontmatter parsing.

## Testing

- Added focused unit and integration tests under `ext/skills` and `skills` for the consolidated loader behavior.

GitOrigin-RevId: 214d06d59bf3033ee0f220ea5959ee4feff66782
2026-08-07 15:16:06 +00:00
felixxia-oai a9d59d8b8e Respect plugin skill availability in tool suggestions (#37447)
## Why

Plugin suggestions should report skills only when the plugin has an enabled skill.

## What changed

- Load suggestion metadata through the shared plugin skill-root loader.
- Apply skill configuration when setting `has_skills` on suggestion candidates.

## Testing

Added coverage for local plugin suggestions with the plugin skill both enabled and disabled.

GitOrigin-RevId: bceb14528c9042b474eaad6efaf919bef72e0ca4
2026-08-07 14:17:14 +00:00
jif 964a227d8c Preserve base instruction provenance across sessions (#37446)
## Why

Persisted base instructions need to retain whether they were explicitly customized or generated from a model template. Without that distinction, forks and config-lock replays can treat model-generated instructions as custom and keep the wrong template after a model or personality change.

## What changed

- Record custom or model provenance with base instructions in rollouts and config locks.
- Preserve custom instructions across model changes, while allowing model-generated instructions to follow the selected model and personality.
- Keep legacy rollouts without provenance compatible and propagate provenance through forks and spawned agents.

## Testing

- Cover provenance serialization and legacy rollout decoding.
- Cover role personality changes, forked model changes, config-lock replay, and multi-agent configuration.

GitOrigin-RevId: 801c26559835f558027ce5112700c0cd31fcb21b
2026-08-07 14:08:13 +00:00
felixxia-oai e58d9ef447 Unify plugin skill loading with the host skill service (#37444)
## What changed

- Inject the host skill loader into `PluginsManager` so plugin discovery and agent turns use the same loading and product-policy behavior.
- Share plugin skill snapshots across those paths, preserving a consistent view of skills across workspaces.
- Apply migrated-command precedence after product filtering, allowing an eligible migrated command to replace a filtered native skill with the same name.

## Testing

- Add coverage for product-restricted plugin skills, native-versus-migrated command precedence, and the skills exposed to agent turns.

GitOrigin-RevId: f5ef0d0766ebeeb30d73ffaf044d003c2906ea4d
2026-08-07 13:54:24 +00:00
jif a7dcd20d38 Add process diagnostics snapshots (#37434)
## What changed

- Add a `codex-diagnostics` crate that snapshots the process ID, available
  resident-memory measurements, and registered process-wide gauges.
- Provide guards that update gauges for the lifetime of measured objects.
- Track live `CodexThread` instances with the `core.threads.live` gauge.

## Testing

- Add unit coverage for gauge registration, guard lifetimes, process memory
  snapshots, and live-thread reporting.

GitOrigin-RevId: 3236b086bd4ebe31ed4768ab87a5fa288b0891b0
2026-08-07 11:30:17 +00:00
jif 85e0661c3b Cap project instructions across environments (#37424)
## Why

Applying `project_doc_max_bytes` independently to every selected environment
allows the total project instruction payload to grow with the number of
environments.

## What changed

Treat `project_doc_max_bytes` as one shared byte budget. Consume it in selected
environment order, truncate the entry that reaches the remaining limit, and
skip later environments once the budget is exhausted.

Update the configuration descriptions to document the aggregate limit.

## Testing

Add unit and integration coverage for partial and exhausted budgets across
multiple environments.

GitOrigin-RevId: 4664bdf1f23b66986349d503f44cf51560b9024f
2026-08-07 09:50:43 +00:00
sayan-oai 957f8eedee Add a loader for executor-local config layers (#37406)
## What changed

- Add `load_local_config_layers` to return raw configuration and requirements layers with their sources, base directories, precedence order, and cloud insertion positions.
- Support projecting layer stacks to selected TOML paths while preserving non-table override blockers and adjusting cloud insertion positions when empty layers are removed.
- Reuse project discovery and trust handling for local reads, including linked-worktree hooks, without resolving relative paths or including profiles, session flags, thread layers, or cloud-provided values.

## Testing

- Cover layer ordering, raw relative paths, legacy requirements, trust filtering, projection semantics, and untrusted linked-worktree hook handling.

GitOrigin-RevId: a1098af5650ac44e5a230ba9a5fe918927986d05
2026-08-07 08:28:10 +00:00
rka-oai c87a218bd3 Rename the tool registry metadata setting (#37400)
## What changed

Rename `features.tool_registry.include_tool_namespaces_info` to
`features.tool_registry.include_tool_metadata` across configuration parsing,
schema generation, resolved configuration locking, and tests. Update its
description to cover authoritative tool information in request metadata.

GitOrigin-RevId: 93b404483b71fed04031d767a41ac2bb70b836b2
2026-08-07 07:35:37 +00:00
rka-oai 4ee41929ea Add tool namespace metadata configuration (#37389)
## What changed

- Add `features.tool_registry.include_tool_namespaces_info` to the TOML model,
  generated schema, and resolved runtime configuration. The setting defaults to
  `false` and controls whether per-turn request metadata includes the resolved
  tool namespace inventory.
- Preserve the resolved setting in session configuration locks.
- Cover top-level and profile-scoped strict configuration, deserialization,
  resolution, and lock-file persistence.

GitOrigin-RevId: 74124086c0d7de30094b411001f0ec0af490935d
2026-08-07 06:29:09 +00:00
Abhinav 81b9bc2109 Recognize MCP tool hook configurations (#37363)
## What changed

- Parse `mcp_tool` hook handlers with a server, tool, JSON input, and optional timeout and status message.
- Return managed MCP tool hooks from `configRequirements/read` and include the handler in the generated protocol schemas.
- Skip MCP tool hooks during discovery with an explicit warning until execution is supported.

## Testing

- Cover MCP tool hook deserialization, including nested and null JSON input values.
- Extend the config requirements RPC test to verify the new handler shape.

GitOrigin-RevId: ff7e2d12b75b486c54d63469af547a29f9b31418
2026-08-07 03:30:29 +00:00
Adam Perry @ OpenAI 4d7e3e90d9 Clamp short wait_agent timeouts to the configured minimum (#37357)
## What changed

- Clamp `wait_agent` timeout requests below `min_wait_timeout_ms` instead of rejecting them.
- Include the timeout adjustment in the wait result message and document it in the tool output schema.

## Testing

- Update the handler test to verify the configured minimum is honored and the adjustment is reported.
- Update the schema test for the expanded result message.

GitOrigin-RevId: 2b4a770ed6d1e9c45b351b479f5ae50c9a3d5388
2026-08-07 02:34:46 +00:00
pakrym-oai d0c8f422ea Configure the default code-mode exec yield timeout (#37352)
## What changed

- Add `features.code_mode.default_exec_yield_time_ms`, defaulting to 30 seconds.
- Apply the configured default to code-mode `exec` calls that omit `yield_time_ms` and reflect it in the tool description.
- Remove the `code_mode_buffered_exec` compatibility feature flag.

## Testing

- Cover config loading and tool descriptions for both default and custom yield timeouts.

GitOrigin-RevId: 581ffc737b04721c7b5fc81260b1da1cf7d87523
2026-08-07 01:41:54 +00:00
keith thornhill 9457f8f734 Allow ThreadManager to customize thread ID generation (#37350)
## What changed

- Add `ThreadManager::with_thread_id_generator` to configure ID allocation for new root, child, and forked threads.
- Keep the standard UUIDv7 generator as the default and preserve stored IDs when resuming threads.
- Add `ThreadId::from_u128` for constructing identifiers from UUID-compatible values.

## Testing

- Cover default allocation, custom IDs across roots, child agents, and forks, and ID preservation on resume.

GitOrigin-RevId: 6c38c862e30a50bad944a994bcbccf7d1e7ada24
2026-08-07 01:36:22 +00:00
Owen Lin 4bb7ee3472 Add rollout migration tooling and background migration (#37348)
## What changed

- Add `codex migrate-rollouts` with dry-run inspection by default, explicit `--apply`, thread filtering, optional I/O throttling, progress output, and JSON or verbose reports.
- Add the disabled-by-default `background_paginated_rollout_migration` feature to migrate legacy local sessions at startup before rollout compression begins.
- Persist a migration cursor and skipped-file fingerprints so later startups avoid full rescans while retrying changed files and recovering pending migrations.
- Coordinate migration with live writers and emit metrics for manual and startup runs.

## Testing

- Cover startup cursor advancement and lookback, pending migration recovery, live-writer coordination, changed empty rollouts, and progress reporting.

GitOrigin-RevId: 276ac506c50ebec5140fd319faca1bb998172061
2026-08-07 01:26:42 +00:00
Boyang Niu 69b6152c17 Track context windows per agent (#37347)
## Why

Forked subagents can inherit a parent's compacted history, but their context-window metadata needs to identify the child and start a distinct window lineage.

## What changed

- Always identify context windows by agent name and remove the `features.token_budget.mode` setting.
- Persist the agent path in world state and emit context-window metadata as a standalone developer message when the identity changes.
- Reset inherited compaction metadata to the forked subagent's initial context window and restore that window in session state.

## Testing

Extend the full-history subagent test to verify parent and child world-state snapshots, agent identities, distinct window IDs, and the reset child checkpoint.

GitOrigin-RevId: 6584201e57b3d2fba0ce626b89a8b3b0b3c752db
2026-08-07 01:05:33 +00:00
thorvald-oai 270d93268c Send model routing hints to the Codex backend (#37345)
## What changed

- Add an `x-codex-routing-hint` header containing the request model and, when selected, the service tier.
- Send the hint on Responses HTTP requests, remote compaction requests, and WebSocket handshakes, including prewarm connections.
- Limit the header to Codex-backend authentication with the OpenAI provider, omitting it for API-key and provider-specific credential paths.

## Testing

- Cover routing hints for HTTP, remote compaction, WebSocket streaming, and tiered prewarming, along with the credential paths where the header must be absent.

GitOrigin-RevId: d8d415d7fadddecf9a132d05920b856a35ac9960
2026-08-07 00:58:54 +00:00
jif bcea6447ee Preserve foreign cwd URIs for turn-input contributors (#37342)
## Why

Converting each environment's working directory to a host-native path caused
turn-input contributors to omit environments with foreign path formats.

## What changed

- Expose `TurnInputEnvironment.cwd` as a `PathUri`.
- Pass every turn environment to contributors without host-path conversion.

## Testing

Added an integration test that submits a foreign working-directory URI and
verifies the contributor receives the environment unchanged.

GitOrigin-RevId: a122526be47f5331614381e9c6e4b85087a96bed
2026-08-07 00:42:06 +00:00
jif b3ffe3d001 Recover MCP servers after OAuth reauthentication (#37337)
## Why

An OAuth-backed Streamable HTTP MCP server can fail startup when its stored credentials are rejected. If a client then completes OAuth sign-in and replaces those credentials, the failed server needs to become available without restarting the Codex session.

## What changed

- Track the credential store and OAuth tokens used for each MCP connection, and detect replacements after authentication failures.
- Refresh affected MCP servers before the next turn and include their recovered tools in the model request.
- Classify HTTP authentication challenges and rejected refresh tokens as requiring reauthentication, with sign-in guidance appropriate to local and client-managed environments.

## Testing

- Cover recovery from expired credentials through an externally written replacement token.
- Cover authentication-error classification, startup messaging, and `Auto` store migration from file credentials to the keyring.

GitOrigin-RevId: 9b090089d4e7a44ffc182f4e25da20a18e97b70f
2026-08-07 00:17:46 +00:00
jif 7257826ab2 Use step environments for extension turn input (#37336)
## Why

Environment readiness can change between sampling requests. Extension turn-input contributors should receive the same refreshed environment snapshot used by the current step.

## What changed

Build `TurnInputContext.environments` from `StepContext` so newly ready environments are included in extension input for the current request.

GitOrigin-RevId: ee4444072162317974cd2bbfd57ffcf9a9445391
2026-08-07 00:13:31 +00:00
jif 57f42a8113 Avoid cloning immutable metadata on tool search cache hits (#37279)
## Why

Checking the tool search cache currently rebuilds search metadata for every deferred tool, even when an immutable tool runtime has not changed.

## What changed

- Track immutable deferred tools by runtime identity and dynamic tools by their current search metadata.
- Rebuild the search handler when the deferred registry, dynamic metadata, or source-listing mode changes.
- Keep only weak references to immutable runtimes in the cache.

## Testing

Added unit coverage for immutable handler reuse, registry and exposure changes, source-listing changes, and refreshed dynamic tool metadata.

GitOrigin-RevId: 024c6f4498d431e7bbfaecde420f77fcf8c0dba7
2026-08-06 14:11:35 +00:00
jif e1831db7c3 Reuse MCP handlers across sampling steps (#37273)
## Why

MCP tool handlers and their Code Mode definitions are immutable for the lifetime
of a stable MCP binding, so rebuilding them for every sampling step repeats schema
construction unnecessarily.

## What changed

- Cache MCP handlers per session and reuse them while the same binding remains
  active, invalidating the cache when the binding changes.
- Lazily cache schema-free Code Mode definitions on MCP handlers while continuing
  to rebuild definitions for step-local tools whose specifications may change.
- Reapply current app enablement, tool policy, exposure, and plugin schema budgets
  whenever cached handlers are registered for a step.

## Testing

- Cover handler and Code Mode definition reuse, binding invalidation, changing app
  policy, stable continuation schemas, and step-local custom tool updates.

GitOrigin-RevId: 69c5011fb97c08580ac476e7fb2286b1e92e0359
2026-08-06 13:37:07 +00:00