Commit Graph
9374 Commits
Author SHA1 Message Date
Charlie Marsh f0904922f6 Reduce retained MCP result data in TUI history (#39023)
## Why

MCP tool results can contain multi-megabyte image, audio, or resource bodies,
even though TUI history renders only summaries for those content types.

## What changed

- Project completed MCP results into width-independent display data, dropping
  media and resource bodies that history does not render.
- Preserve text output, JSON fallbacks, error state, Node REPL rendering, and
  the fully decoded image-output marker.
- Add tests covering width-dependent rendering, image validation, and Node REPL
  text fields on non-text and unknown content blocks.

GitOrigin-RevId: 2cfddf0864093e6837a4431e541f7a9cab544a68
2026-08-17 16:46:26 +00:00
Charlie Marsh 0841d9bba5 Hang soft-break whitespace in the TUI composer (#39022)
## Why

Keeping overflowing separators with the following word can add whitespace-only
rows and make composer wrapping differ from the queued-input preview.

## What changed

- Hang breakable whitespace from the preceding visual row at soft word breaks
  while preserving the underlying editable text.
- Keep indentation, trailing whitespace, mandatory breaks, and nonbreaking spaces
  visible and editable according to their existing semantics.
- Align cursor placement, scrolling, vertical navigation, masked rendering, and
  styled overlays with the visible wrapped content, including after resizes.

## Testing

Add focused wrapping, rendering, cursor, editing, scrolling, navigation, Unicode
separator, long whitespace-run, and resize coverage.

GitOrigin-RevId: 7fbdb0a4bf33cfee20c4c19dca5aee74df4f892c
2026-08-17 16:39:37 +00:00
Eric Traut 09bc28f348 Restrict Windows IDE pipe client impersonation (#39020)
## Why

Windows named pipe servers can impersonate connected clients. IDE context
connections only require the server to identify the client, so they should not
grant broader impersonation rights.

## What changed

Open Windows IDE context pipes with `SECURITY_SQOS_PRESENT` and
`SECURITY_IDENTIFICATION`, limiting the server's impersonation token to the
identification level.

## Testing

Add a Windows regression test that connects to a named pipe, asks the server to
impersonate the client, and verifies that the resulting token has the
`SecurityIdentification` level.

GitOrigin-RevId: 51ef080f3367857987e03b0113a476040ea40e56
2026-08-17 16:34:21 +00:00
Eric Traut 02360b48d1 Isolate MCP resource headers during OAuth requests (#39019)
## Why

Headers configured for an MCP resource can contain credentials and must not be
forwarded to a different origin during OAuth discovery, registration, or token
exchange.

## What changed

- Apply configured resource headers only to OAuth requests on the MCP resource
  origin, while allowing OAuth-generated headers to take precedence.
- Follow credentialed OAuth redirects only when each destination remains on the
  resource origin. Preserve redirect method semantics, the overall timeout, the
  response size limit, and a maximum of 10 redirects.
- Use the Codex MCP user agent for requests to authorization-server origins.

## Testing

Add coverage for cross-origin header isolation, same-origin dynamic client
registration redirects, OAuth header precedence, token refresh, timeout
accounting, and response size limits.

GitOrigin-RevId: 609d06e2b065e4aa9ca5382b4ae60455f9e26db9
2026-08-17 16:29:47 +00:00
sayan-oai 32a383c0ba Move MCP policy types into codex-protocol (#39017)
## What changed

- Define MCP server identities, matchers, requirements, and per-plugin MCP requirements in the new `codex_protocol::mcp_policy` module.
- Keep requirement validation and matching against `McpServerConfig` in `codex-config`.
- Re-export the moved types from `codex-config` to preserve existing consumers.

GitOrigin-RevId: ad8a107e3085191241a5766f061dd004103e21e6
2026-08-17 16:20:52 +00:00
jif 21cfd369ef Add task context to shadow skill selection (#39008)
## Why

Short continuation prompts such as `continue` do not contain enough context for
skill selection on their own.

## What changed

- Add the `task_context_fusion_v1` shadow selector, combining the current request
  with up to two prior substantive requests and recently relevant skills.
- Record explicit skill intent and successful skill invocations for future turns,
  while excluding same-turn observations from predictions.
- Bound retained requests, augmented queries, and skill history, including safe
  truncation at UTF-8 character boundaries.

## Testing

Add unit and extension tests for continuation prompts, explicit intent, turn
isolation, cold thread state, bounded history, and unchanged control selectors.

GitOrigin-RevId: 72eca3f0d64620a0d24e95d5675f126ac982f8c7
2026-08-17 13:29:57 +00:00
jif def7ed5572 Wait for Guardian score progress in approval tests (#39007)
## Why

Guardian stores a `SecurityRiskScore` before advancing its scored-tool-call
counter. Waiting only for the score can therefore let the test continue while
the asynchronous sampler is still updating its progress state.

## What changed

Wait for `latest_scored_tool_call` to advance before exercising Guardian v2
approval decisions, and reuse the same progress tracker for the subsequent
assertions.

GitOrigin-RevId: 3d92c9a3ccf52f4f43a2454aac60d2479258c1c8
2026-08-17 13:26:19 +00:00
xli-oai 04caa22c82 Emit API-key turn cost telemetry from app-server (#39006)
## What changed

- Track app-server turn lifecycle events for OpenAI API-key sessions when OTLP telemetry export is enabled.
- Query the turn-cost endpoint after completed or aborted turns and emit `codex.turn_cost` with the estimated USD cost, interruption state, model, speed, and reasoning effort.
- Preserve provider organization and project headers, wait for all observed responses to be priced, and retry pending or transiently failed queries with bounded tracking.
- Re-probe availability after authentication changes and shut the worker down with other app-server background tasks.

## Testing

- Cover late API-key login, transient probe failures, telemetry after thread removal, and turns with multiple responses.
- Verify turn-cost requests use API-key authentication and provider scope headers and deserialize priced response data.

GitOrigin-RevId: a303162a54798b554fcb2e9e2b372e1cf9f49f39
2026-08-17 13:20:58 +00:00
felixxia-oai 02e9bfaac7 Disable Guardian V2 for managed automatic reviewers (#39005)
## Why

Guardian V2 should not override a managed approval-reviewer policy that excludes
the user reviewer.

## What changed

- Force `features.guardianv2` off when `allowed_approvals_reviewers` does not
  include `user`, for both local requirements and cloud config bundles.
- Preserve Guardian V2 when the user reviewer remains allowed or when only
  legacy Guardian feature settings are present.
- Return the effective disabled value through `config/read`.

## Testing

Added coverage for cloud requirements and the app-server config RPC.

GitOrigin-RevId: 82b6d0aaf47fbaa58ae349d4e56777cd442f5807
2026-08-17 13:16:05 +00:00
jif 8e89e98cf6 Ignore stale Guardian tool risk scores (#39001)
## What changed

- Track the latest tool call and latest scored tool call for each Guardian v2 thread.
- Skip approval review when the score lags by more than `max_tool_call_lag` tool calls.
- Add `max_tool_call_lag` to the Guardian v2 configuration and schema, with a default of three.

## Testing

- Cover approval review at, above, and after recovering from the configured lag limit.
- Cover deserialization of `max_tool_call_lag`.

GitOrigin-RevId: fd870e143d95ee76491180e2aed742717248ff78
2026-08-17 13:06:15 +00:00
jif 4885eb6c52 Retry transient Guardian sampling failures (#38997)
## Why

Guardian sampling can encounter temporary connection or service failures while
opening a WebSocket, starting a request, or consuming its response stream.

## What changed

- Retry transient transport, streaming, rate-limit, and server failures up to
  two times across the full sampling flow.
- Recover from unauthorized responses through the configured auth manager and
  discard pooled connections that may contain stale credentials.
- Allow sampler initialization to continue when its initial WebSocket prewarm
  fails, so the first sample can establish a fresh connection.

## Testing

Added coverage for recovery after prewarm failures and `503` responses, and for
stopping once the transient retry budget is exhausted.

GitOrigin-RevId: af74c2df95c4241184ca641ef4418db6aa4ab695
2026-08-17 12:45:50 +00:00
Alex Zamoshchin 3666a46ea3 Remove the workspace settings gate for apps and plugins (#38994)
## What changed

- Stop fetching the ChatGPT workspace `enable_plugins` setting.
- Let the effective Codex feature configuration control app and plugin APIs,
  plugin-provided skills and hooks, and experimental feature reporting.

GitOrigin-RevId: 46aebf0f07cd47e093e48663e41207cdf9a38c9f
2026-08-17 12:26:59 +00:00
jif ea10ae7d0f Evaluate recent and character-routed skill selection (#38993)
## What changed

- Add shadow selectors that fuse recently invoked skills with character routing-card matches using reciprocal rank fusion.
- Add a second variant that also incorporates weighted lexical matches.
- Record both variants in the existing shadow-selection experiment, capped at 50 candidates.

## Testing

- Cover cold starts, duplicate removal, short exact matches, deterministic ranking, result limits, and truncation metadata.
- Extend the skills integration test to verify both selectors recover a skill invoked on an earlier turn.

GitOrigin-RevId: 4ff9e91da8cb49ecbce54ab8e760820616e1a1d3
2026-08-17 12:13:20 +00:00
felixxia-oai 8bf50439f2 Source Guardian v2 defaults from the model catalog (#38990)
## What changed

- Add optional `guardian_v2` model-message defaults for classifier instructions,
  review thresholds, reasoning effort, transcript selection and limits, and
  action and compaction token limits.
- Apply those defaults when Guardian v2 samples a tool call, while preserving
  explicit `[features.guardianv2]` settings over catalog values.
- Preserve the new catalog configuration when applying model overrides.

## Testing

- Cover model-catalog serialization and model override behavior.
- Verify that sampling uses catalog defaults while retaining local overrides.

GitOrigin-RevId: 4ae9ec235c647acbca05a20b7c4b87a4e1331161
2026-08-17 11:44:56 +00:00
jif 37cf6c84c0 Include images in Guardian v2 transcripts (#38987)
## What changed

- Add the `features.guardianv2.transcript.include_images` opt-in setting.
- Include recent images from user and assistant messages and configured tool outputs in Guardian v2 sampling requests.
- Bound image context to the four most recent images and 8 MiB total, and omit image detail hints when constructing the sampling request.

## Testing

- Cover configuration parsing and image forwarding from messages and tool outputs.

GitOrigin-RevId: b0ae6b6182535fd084ea103ed01dc3c803d7d1f7
2026-08-17 10:56:13 +00:00
felixxia-oai 53aa7bb1aa Bound Guardian v2 parent compaction context (#38980)
## What changed

- Add `max_parent_compaction_tokens`, defaulting to 25,000 tokens, to the Guardian v2 feature configuration.
- Reuse the latest encrypted parent compaction only when its complete serialized item fits within the configured limit.
- Fail closed with the maximum action-risk score when the latest encrypted compaction is oversized, instead of sampling with older context.

## Testing

- Cover exact-boundary and oversized compaction items, including oversized passthrough metadata.
- Verify that an oversized latest compaction bypasses sampling and prevents approval.

GitOrigin-RevId: 0b308e7bec0f41d46433dfdf656948cee5cba667
2026-08-17 10:18:24 +00:00
jif 632e35ce8d Add a configurable skill catalog token budget (#38978)
## What changed

- Add `[skills].max_context_tokens` to override the token budget used to render the available-skills catalog.
- Require a positive value and cap configured budgets at 10,000 tokens.
- Preserve the existing default of 2% of the model context window when the option is unset.

## Testing

- Cover configuration parsing, override behavior, the 10,000-token cap, and catalog rendering within the configured budget.

GitOrigin-RevId: f29ddcb57fc2d800c0006d03e1c33cbe3ab6272d
2026-08-17 10:01:59 +00:00
iceweasel-oai c6058ccaa9 Stop loading legacy managed config on Windows (#38947)
## What changed

- Ignore the default `CODEX_HOME/managed_config.toml` on Windows and exclude it
  from local managed-configuration detection.
- Emit a startup warning when the deprecated file exists, directing users to
  `%ProgramData%\OpenAI\Codex\requirements.toml` for enforced settings or
  `config.toml` for defaults.
- Preserve explicit managed-config path overrides and Unix legacy-file support.

## Testing

- Add Windows tests covering ignored legacy settings, the startup warning, and
  managed-configuration detection through `requirements.toml`.

GitOrigin-RevId: a61d9d9912b13817ba82807a486c9ed92e49c7bc
2026-08-17 05:52:32 +00:00
sayan-oai e38290846c Enforce environment-specific command policies (#38942)
## What changed

- Add an optional restrictive execution policy to `EnvironmentConfig` and merge it over the active command policy for shell execution and approval decisions.
- Reject environment policies that contain allow rules, so environment configuration can only tighten command access.
- Include the environment policy fingerprint in cached approval keys so policy changes require fresh session approvals.

## Testing

- Cover restrictions overriding saved prefix approvals, policy changes invalidating session approvals, and environment overlays remaining effective when model-specific prefix filtering is active.

GitOrigin-RevId: e94f877549ed5e0f577b8cb52f3c1872c58f029d
2026-08-17 04:37:50 +00:00
Anton Panasenko 89e297729e Prevent Noise auth tokens from reaching child processes (#38941)
## Why

`CODEX_EXEC_SERVER_NOISE_AUTH_TOKEN` is an execution-server credential and
must not be exposed to model-reachable commands or command hooks, including
when shell environment policy explicitly sets a case variant of the name.

## What changed

- Add `CODEX_EXEC_SERVER_NOISE_AUTH_TOKEN` to the shared list of
  non-inheritable environment variables.
- Keep the environment variable constant in `codex-protocol` so the exec
  server and environment scrubber use the same definition.
- Verify case-insensitive removal after policy overrides for shell commands
  and command hooks.

GitOrigin-RevId: 759b224b6a7fb4f56f7b1a6d94ffbb0b188c658f
2026-08-17 04:17:45 +00:00
Anton Panasenko 3b4569a920 Add experimental app-server project APIs (#38940)
## What changed

- Add SQLite-backed `project/list`, `project/read`, `project/create`,
  `project/import`, `project/update`, `project/move`, and `project/delete`
  endpoints with ordered roots, metadata, manual positioning, pagination, and
  idempotent creation.
- Add project assignment to thread start, metadata updates, list filtering,
  and fork inheritance. Project deletion clears assignments without deleting
  threads.
- Emit `project/changed` and `thread/project/updated` notifications after
  committed changes, and export the new protocol schemas and TypeScript types.

## Testing

- Cover project lifecycle and ordering, idempotency, atomic imports, cursor and
  filter validation, thread assignment, deletion, and fork inheritance.

GitOrigin-RevId: 47ae621be01ab8ef70a74a629fb29a5c5709ea33
2026-08-17 04:01:37 +00:00
Eric Traut 1f41cc5d92 Compact successful command activity in the TUI (#38921)
## What changed

- Group consecutive successful agent and unified-exec startup commands into a compact `Ran N commands` entry while preserving their full transcript.
- Flush command groups at interaction boundaries, after failures, and after 32 completed commands. Keep manual shell commands and failed or declined commands visible.
- Apply the same grouping rules when replaying thread history without duplicating command starts or disturbing unrelated active commands.

## Testing

- Add TUI coverage for live and replayed grouping, transcript preservation, failures, overlapping commands, group limits, and interaction boundaries.

GitOrigin-RevId: d6602a20201644012fcff3d6cecf4690024383a9
2026-08-17 00:32:09 +00:00
iceweasel-oai 935b1c4e3d Reject obsolete app-server permission profile fields (#38919)
## Why

App-server request deserialization otherwise ignores unknown fields, so clients using the removed `permissionProfile` field could have their requested permission settings silently ignored.

## What changed

- Reject `permissionProfile` with an invalid-params error on `thread/start`, `thread/resume`, `thread/fork`, and `turn/start`.
- Direct clients to select a named profile through `permissions` instead.
- Continue accepting unrelated unknown fields for forward compatibility.

## Testing

- Cover rejection of the obsolete field on all four affected methods and verify that the connection remains usable.
- Cover successful `thread/start` requests that combine named `permissions` with an unknown field.

GitOrigin-RevId: a63764fb899bc5f212d60617dc32e911bde8073e
2026-08-17 00:25:19 +00:00
chess c8ddb210d2 Improve codex doctor network diagnostics (#38918)
## What changed

- Probe the configured Responses inference endpoint with Codex's route-aware HTTP client, including configured proxy and custom CA behavior.
- Classify TLS, proxy authentication, proxy configuration, resolution, and timeout failures into actionable diagnostics.
- Report privacy-safe macOS system proxy state and suggest enabling `respect_system_proxy` when a configured proxy is otherwise unused.
- Preserve system-root fallback when a custom CA is invalid, and account for provider-specific API key configuration when selecting the probe route.

## Testing

- Cover inference endpoint selection, invalid custom CA fallback, proxy authentication failures, TLS classification, and macOS proxy reporting.

GitOrigin-RevId: c30a3ca5a332119e2b2f8c65341ef9b2251a28a2
2026-08-17 00:09:44 +00:00
iceweasel-oai 772e88c8ae Honor legacy :project_roots permission entries (#38916)
## Why

Permission profiles written before the rename to `:workspace_roots` can still
contain `:project_roots`. Treating that token as unknown ignores its entries and
can drop filesystem restrictions.

## What changed

- Parse `:project_roots` as an alias for `:workspace_roots`.
- Cover deny rules and read-only subpath carveouts in legacy profiles.

GitOrigin-RevId: 10aafc9e15372d1a8bcc2dbcf3ad7cc987f4e67e
2026-08-17 00:05:54 +00:00
Benjamin Carlsson cd8dc1e9b6 Stop rendering columns after filling their area (#38913)
## What changed

Stop visiting remaining `ColumnRenderable` children once the render position
reaches the bottom of the available area.

GitOrigin-RevId: 5b7f2c657f65879119b1b840e82f47b1c5f9e3db
2026-08-16 23:05:11 +00:00
Benjamin Carlsson 2bc43d516e Edit queued messages with Vim history-up (#38907)
## What changed

- When the composer is empty in Vim normal mode, make the configured history-up binding restore the latest queued follow-up for editing.
- Remove the restored message from the queue so submitting the edited version replaces it instead of creating a duplicate.
- Preserve normal history navigation when the composer has text or a popup is active, and honor remapped Vim bindings.

## Testing

- Add TUI tests covering repeated edit-and-requeue cycles and a remapped history-up binding.

GitOrigin-RevId: 0b04dd964d3fc6fdcd10712aa4d5fd81cbbd2255
2026-08-16 21:48:41 +00:00
sayan-oai 6c108912ee Honor per-environment shell variable policies (#38902)
## What changed

- Carry `ShellEnvironmentPolicy` in each resolved `EnvironmentConfig` and use
  the selected turn environment's policy for shell commands, user shell tasks,
  and unified exec.
- Infer the policy from the thread configuration when an environment does not
  provide its own resolved configuration.
- Redact the policy from `EnvironmentConfig` debug output because it can contain
  explicit environment variable values.

## Testing

- Verify shell handlers and unified exec filter inherited variables according
  to the selected environment while preserving its explicit overrides.

GitOrigin-RevId: 9f6a52aa4af60e5f17251a0e1b11e1926b779055
2026-08-16 20:35:05 +00:00
sayan-oai f85e81d30b Move requirements policy ownership to execpolicy (#38899)
## What changed

- Define and export `RequirementsExecPolicy` from `codex-execpolicy`, alongside the
  underlying `Policy` type.
- Re-export the type from `codex-config` so existing config consumers retain the
  same API.
- Preserve its order-independent equality and `AsRef<Policy>` behavior.

GitOrigin-RevId: e94c56b36824d07f2bc7ba14ce40bdb770d4ab46
2026-08-16 20:27:05 +00:00
Benjamin Carlsson ed32158e90 Add working-directory commands to the TUI (#38894)
## What changed

- Add `/cd [path]` for changing an idle local session's working directory while preserving conversation history. Relative paths resolve from the current directory, and omitting the path selects `~`.
- Reload project configuration, instructions, permissions, keybindings, file search, and hooks for the destination before replacing the active session.
- Reject unsafe transitions, including active or queued work, background terminals, remote environments, untrusted destinations, and incompatible permission profiles.
- Add `/pwd` and its `/cwd` alias to display the current working directory, and discard asynchronous results left over from the previous directory.

## Testing

- Cover command parsing, aliases, default paths, session eligibility, transition failures, history preservation, destination policy loading, hooks, and stale events.

GitOrigin-RevId: 1a987c029f157a087ba02c0f26e022260409132b
2026-08-16 19:48:07 +00:00
Benjamin Carlsson 375996d3f5 Restore thread timestamp maxima independently (#38893)
## What changed

Load the persisted maxima for `updated_at_ms` and `recency_at_ms` with separate
scalar subqueries during state initialization. This restores each timestamp
counter independently when the maxima belong to different threads.

## Testing

Add a regression test that reopens the state database and verifies both
independent maxima are restored.

GitOrigin-RevId: aeb9cc005d52c4a02dc7a220a817e6d40c0e01d4
2026-08-16 19:37:39 +00:00
Tin Kadoic 9ded177ce7 Identify Mac mini hosts in remote control handshakes (#38840)
## What changed

- On macOS, inspect the hardware profile before opening a remote-control WebSocket and send `x-codex-host-device-kind: mac_mini` when the machine name is exactly `Mac mini`.
- Cache successful detection results, bound the profile lookup to two seconds, and omit the header on other platforms or when detection fails.

## Testing

- Add parser coverage for Mac mini, other machine names, empty profiles, and malformed profile data.

GitOrigin-RevId: d2a4589bec0c879957f14ab4a195fd54747cc122
2026-08-16 06:48:59 +00:00
Benjamin Carlsson 9bfaf7a076 Share editor keymaps across TUI composer components (#38837)
## What changed

- Store the editor portion of `RuntimeKeymap` in an `Arc` so the chat composer
  and its embedded textarea use the same keymap snapshot.
- Initialize the textarea from the composer's default runtime keymap and keep
  custom binding updates shared between both components.
- Use copy-on-write when tests and binding resolution need to mutate editor
  bindings.

## Testing

- Verify that applying custom editor bindings shares the same keymap allocation
  with the composer and textarea.

GitOrigin-RevId: 7f3b0afd6cc784e23deee8819e5c2c37a3709c68
2026-08-16 05:59:34 +00:00
viyatb-oai 73abda8bfe Isolate external editor buffers from sandbox-writable paths (#38830)
## Why

External editor buffers can contain the current composer text and should not be
placed in directories exposed as writable by a restricted filesystem policy.

## What changed

- Create editor buffer files under a protected `editor` directory, trying the
  configured Codex home, the default Codex home, and a workspace fallback.
- Reject candidates that overlap writable roots or resolve through symbolic
  links, while preserving external editor support for full-disk-write policies.
- Surface an editor error when no protected directory is available.

## Testing

Add coverage for writable roots, aliases, symbolic links, fallback selection,
temporary-directory grants, full-disk-write policies, and editor invocation.

GitOrigin-RevId: df1029d81b327678991ab84ffd1077f0e5855631
2026-08-16 03:14:17 +00:00
chess c7a95f84b3 Add endpoint protection checks to codex doctor (#38827)
## Why

Endpoint protection products can interfere with Codex, but existing doctor reports do not identify them or explain which Codex exclusions need verification.

## What changed

- Detect supported endpoint protection products on macOS and Windows and add the results to the doctor environment report.
- Warn when detected products have unverified Codex exclusions, with product-specific remediation for CrowdStrike Falcon, BeyondTrust Privilege Management, Microsoft Defender, SentinelOne, and Jamf Protect.
- Distinguish complete, partial, and unavailable inspection results without requiring remediation when no product is detected.

## Testing

- Cover empty, unavailable, partial, single-product, and multi-product inspection results.
- Verify the structured JSON contract and human-readable report output.

GitOrigin-RevId: 684c69684ed73235d92d398f5294cc1b274278df
2026-08-16 02:35:50 +00:00
Benjamin Carlsson 49db349ffd Avoid allocating per character when decorating hyperlinks (#38823)
Encode each character into a stack buffer before appending it to the
decorated span, avoiding a temporary `String` allocation for every character.

GitOrigin-RevId: 72ec1ad5363391dffee089f04073d827d8c459bf
2026-08-16 01:34:51 +00:00
Benjamin Carlsson 1ba9ce8910 Avoid cloning TUI history span content (#38822)
GitOrigin-RevId: f189b7afa5c585c4456a2f4ee795827ec4d79907
2026-08-16 01:31:22 +00:00
Anton Panasenko fcdae21073 Support metadata staging for reserved thread IDs (#38819)
## Why

Callers need to associate host-owned state with a thread before Core starts it.

## What changed

- Add `ThreadManager::reserve_thread_id` and allow new threads to start with the reserved ID. Reject reserved IDs when resuming an existing thread.
- Let thread stores stage metadata for a reserved ID. The local store merges staged values into the first successful metadata update and then removes them.
- Clear staged metadata when an unmaterialized thread shuts down or is discarded, and require the state database for staging.

## Testing

- Cover reserved ID generation and resume validation.
- Cover metadata persistence, merging, rollout-compatible updates, cleanup, and invalid staging requests.

GitOrigin-RevId: 3f9bc48f0f7764011cc90ea01349e497dda0a9e3
2026-08-16 00:57:28 +00:00
Dane Schneider 5ba12929f8 Add raw config overrides to the TypeScript SDK (#38817)
## Why

Some TOML configuration, such as permission maps with literal path keys, cannot be represented safely through the SDK's structured dotted-key configuration.

## What changed

- Add `CodexOptions.configOverrides` for passing ordered `--config key=value` arguments to the Codex CLI unchanged.
- Apply raw overrides after structured `config` values, while preserving precedence for SDK-managed and thread-specific settings.
- Document raw permission-map configuration and cover literal keys, duplicate overrides, ordering, and resume behavior.

GitOrigin-RevId: 3b0f5824ba8cb77d0eecb11ed6f32ead8fc674f6
2026-08-16 00:31:54 +00:00
Channing Conger b3cc217378 Add a health endpoint to the code-mode gRPC listener (#38806)
## What changed

- Serve `GET /healthz` with a `200 OK` response over HTTP/1.1 and HTTP/2.
- Continue requiring HTTP/2 for all other requests so gRPC methods are not exposed over HTTP/1.1.

## Testing

- Add TCP listener integration coverage for HTTP/1.1 and HTTP/2 health checks and rejection of HTTP/1.1 gRPC requests.

GitOrigin-RevId: ae7bbf56323fbc76769375a6d8e90653e8adc860
2026-08-15 21:26:28 +00:00
viyatb-oai 899d1715c8 Route executor policy audits through log-only telemetry (#38800)
## Why

Forwarded network policy decisions are audit telemetry and should not be
written to the persistent state log.

## What changed

- Emit forwarded `codex.network_proxy.policy_decision` events on the
  `codex_otel.log_only` target, keeping them available to OTEL log export while
  excluding them from persistent logs.
- Assert the log-only target in the existing trusted-metadata audit test.

GitOrigin-RevId: 16d07c8f390245036e4fa092a876012ef2b2fdba
2026-08-15 19:34:50 +00:00
chess 6efcdad4c3 Add storage diagnostics to codex doctor (#38795)
## What changed

- Report available space for `CODEX_HOME` and the active worktree, warning below 5 GiB and failing below 1 GiB.
- On Windows, report whether the active Git worktree is on a trusted Dev Drive and provide remediation when it is not.
- Run attached doctor reports against the conversation workspace, including workspaces recovered from persisted thread metadata, while keeping the subprocess anchored in `CODEX_HOME` so deleted workspaces do not prevent it from starting.

## Testing

- Cover disk thresholds, measurement failures, missing paths, conversation workspace selection, command construction, Windows volume detection, and human-readable output.

GitOrigin-RevId: 0a99f9d278717e7d19936ffc504984b3a0958c25
2026-08-15 18:47:25 +00:00
Charlie Marsh a95a6fe333 Show resume and fork status during TUI startup (#38788)
## What changed

- Display a dimmed `Resuming session…` or `Forking session…` status above the provisional composer based on the requested session action.
- Update or clear the status after session selection resolves, while preserving the composer height and any startup draft text.

## Testing

- Add snapshot coverage for resume and fork loading states and transitions back to a fresh session.

GitOrigin-RevId: 9d37b2d0e390d28dee310dd7a5b9fa992db2c25c
2026-08-15 17:30:13 +00:00
joeflorencio-openai 00f6a8a60e Keep active-turn model settings stable across updates (#38785)
## Why

Thread settings can change while a turn is still active, including between sampling requests. Those updates should apply to the next turn instead of changing the model configuration partway through the current turn.

## What changed

- Snapshot the model, reasoning settings, service tier, approval settings, and model-attributed telemetry in `StepContext`.
- Build prompts, model requests, world state, tracing, and startup prewarms from that step-scoped snapshot.
- Share immutable model metadata between turn and step contexts.

## Testing

Added an integration test that pauses an active turn, updates its thread settings, and verifies that all requests in the active turn retain the original settings while the next turn uses the updates.

GitOrigin-RevId: c51352218e463dcc9b7338566d16742292c49fbf
2026-08-15 16:58:08 +00:00
Eric Traut c4941302c7 Use paginated history for persistent exec threads (#38774)
## What changed

- Request paginated history when `codex exec` starts a persistent thread.
- Keep ephemeral threads unchanged and retry with legacy history when the configured thread store does not support pagination.
- Exercise paginated resume and fork persistence, including resumed history and fork ancestry without copying the source transcript.

## Testing

- Extend unit coverage for persistent and ephemeral thread start parameters.
- Add an integration test for the legacy-history fallback.

GitOrigin-RevId: 610a2db14524b127551e75b7aef541d44368f28a
2026-08-15 15:24:30 +00:00
cooper-oai 12933b6955 Forward workload identity context during token exchange (#38767)
## What changed

- Read optional workload identity context from `OPENAI_WORKLOAD_IDENTITY_CONTEXT` and forward it unchanged as the `workload_identity_context` token exchange field.
- Treat the context as sensitive by redacting it from session configuration debug output and removing it from model-reachable child environments.
- Include the context in workload identity session fingerprints so sessions with different values cannot share an exchange.

## Testing

- Cover request forwarding, debug redaction, session compatibility, and child-environment scrubbing.

GitOrigin-RevId: fb50700478cf54d9d604944a4ed3e77acc928a0f
2026-08-15 14:31:04 +00:00
Charlie Marsh a7edf37cb4 Remove the TUI test dependency on codex-cli (#38746)
## What changed

Remove the unused `codex-cli` dev-dependency and the no-op import that kept it
visible to `cargo-shear`. TUI tests continue to locate spawned binaries through
`codex-utils-cargo-bin`.

GitOrigin-RevId: ba5855590c6f0300845170f15f39d77c0611a60a
2026-08-15 11:01:30 +00:00
Charlie Marsh 3c7ae4a812 Scope TUI app directory state to the active context (#38743)
## Why

App directory data and in-flight requests can outlive the account, workspace, or thread that produced them, allowing stale apps to appear in the current TUI context.

## What changed

- Invalidate cached app data, dismiss the app picker, and start a fresh fetch when the account, workspace, or thread changes.
- Tag app directory fetches with their originating thread, workspace, and scope generation, and ignore queued requests or results that no longer match.
- Treat `AppListUpdated` notifications as revalidation signals instead of directly adopting their unscoped contents, with deduplication and a bounded error retry.

## Testing

Added coverage for stale request and result rejection, context invalidation, picker dismissal, and notification revalidation.

GitOrigin-RevId: f20930a0598a6abbdfb3c7826ec955346fe2da7a
2026-08-15 10:57:15 +00:00
Abhinav 85fc4def35 Add MCP tool handler support to the hooks engine (#38705)
## What changed

- Discover synchronous `mcp_tool` hook handlers and invoke their configured MCP server and tool through a supplied executor.
- Expand nested hook-event placeholders in MCP tool inputs while preserving JSON types, and process tool output through the existing hook output contract.
- Represent hook details as handler-specific metadata in `hooks/list`, including MCP server and tool fields, and show those details in the TUI hooks browser.
- Skip unsupported `SessionEnd` MCP hooks and runtimes without MCP invocation support with startup warnings.

## Testing

- Cover argument expansion, missing placeholders, MCP invocation and hook decisions, discovery warnings, `hooks/list` metadata, and TUI rendering.

GitOrigin-RevId: 295b845471fe92bd7ad7cd272fbcd2c3713912e0
2026-08-15 05:53:54 +00:00
kevinlin-openai 3685a61dad Normalize CRLF line endings in pasted text (#38704)
## Why

Replacing every carriage return with a line feed turns each CRLF pair into two
line breaks when text is pasted into the TUI composer.

## What changed

Normalize CRLF pairs before converting remaining bare carriage returns, so each
pasted line ending becomes a single line feed while existing line feeds remain
unchanged.

## Testing

Add a regression test covering mixed CRLF, bare CR, and LF line endings.

GitOrigin-RevId: 86c66d2a52fae52c9ae58c2f24a49eed685b60be
2026-08-15 05:43:44 +00:00