Commit Graph

9672 Commits

Author SHA1 Message Date
Krish Chainani
8b61c50ebe Run allowlisted executor plugin stop hooks (#40009)
## What changed

- Discover inline hooks from executor-provided plugin manifests and accept only
  the bundled Computer Use `Stop` hook for `node_repl.turn_ended`.
- Add the accepted hook to the current step's hook engine with
  executor-scoped provenance.
- Run executor-scoped hooks in the background after regular stop-hook
  decisions, without delaying turn completion, applying control effects, or
  exposing them in hook summaries. Skip them when regular hooks only block
  continuation.

## Testing

- Added coverage for manifest filtering and option preservation.
- Added coverage for background execution, interaction with regular stop
  hooks, and non-blocking turn completion.

GitOrigin-RevId: c0f75f83a23ba8a83bb3a5d5997c4882aacc32d6
2026-08-21 21:01:59 +00:00
alexsong-oai
e77c2a90af Implement Amazon Bedrock setup in the app server (#40007)
## What changed

- Implement `account/bedrock/discover` to report AWS profiles and available environment credentials.
- Implement `account/bedrock/setup` for validated AWS profiles and environment credentials, persisting the selected region and profile in the Bedrock provider configuration.
- Resolve Bedrock authentication according to the selected credential source, and clear stale profile configuration when using a Codex-managed Bedrock API key.

## Testing

- Cover profile and environment discovery, setup validation and persistence, conflicting credentials, and authentication-source precedence.

GitOrigin-RevId: 16d700cb0843df768c2fdb6d0c8d26c3402e93df
2026-08-21 20:57:17 +00:00
felixxia-oai
51d8d12236 Synchronize Git enrichment tests explicitly (#40006)
## What changed

- Track Git enrichment completion with a watch channel and unblock waiters when enrichment finishes or is canceled.
- Let the test sync tool wait for the current turn's enrichment with a bounded timeout.
- Replace polling in metadata tests and wait for enrichment before asserting workspace metadata in the guardian integration test.

GitOrigin-RevId: 8d35f75a0ebfe412674e1e797c6a13c03b1ea373
2026-08-21 20:53:30 +00:00
jif
dbe9dac1ae Route escalated commands through synchronous Guardian review (#40005)
## Why

Commands requesting `sandbox_permissions=require_escalated` need a full Guardian review even when they are not marked as retries.

## What changed

- Treat escalated command requests, along with retries, as requiring synchronous Guardian review.
- Bypass extension approval and Guardian V2 shortcuts for these requests.

## Testing

Add an integration test that installs an auto-approving extension and verifies that an escalated command still reaches Guardian and honors its denial.

GitOrigin-RevId: 30eed273460f3c3c6b24d1ce2d29889e34513afd
2026-08-21 20:45:42 +00:00
sayan-oai
ad9e8097fd Preserve managed deny-read rules across permission updates (#40004)
## Why

Runtime permission updates must not weaken managed filesystem `deny_read`
requirements.

## What changed

- Retain managed deny-read rules separately and merge them into updated
  permission profiles.
- Reject permission profiles and legacy sandbox policies that conflict with a
  managed denied path.
- Apply the same constraint when `command/exec` handles a request-specific
  sandbox policy.

## Testing

- Cover thread permission updates with managed deny-read requirements.
- Cover `command/exec` enforcement for managed and user-defined denies,
  including conflicting policy and profile overrides.

GitOrigin-RevId: 5e387b9c1bf1650a21753a74a3338bd33df7d0ce
2026-08-21 20:15:23 +00:00
rafael-oai
0f1a30b5c2 Expose browser and computer-use requirements through app-server (#40000)
## What changed

- Expand `configRequirements/read` with the Browser/Computer Use umbrella
  policy and the complete browser-use policy, including origin-specific access,
  download, upload, auto-review, and approval controls.
- Return computer-use persistent approval, default app access, macOS bundle ID
  rules, and Windows AUMID and executable rules.
- Export the corresponding v2 protocol types and generated JSON and TypeScript
  schemas.

## Testing

- Extend the config requirements RPC test to cover the new browser and
  platform-specific computer-use fields.

GitOrigin-RevId: d1be93388701b06312a26853d640401b63b4d535
2026-08-21 19:56:52 +00:00
Benjamin Carlsson
9cdc66904f Hide Fast mode status for unsupported models (#39999)
## Why

The `fast-mode` status item showed `Fast off` even when the selected model did not support Fast mode.

## What changed

- Hide the Fast mode status value when the current model is known not to support Fast mode.
- Continue showing the value for supported and uncatalogued models.

## Testing

- Cover visibility updates when switching among supported, unsupported, and uncatalogued models.
- Update the footer snapshot to verify that an unsupported model omits the Fast mode value.

GitOrigin-RevId: c297655189efc719b2097c2aa415029b01d6873e
2026-08-21 19:47:49 +00:00
Benjamin Carlsson
df6a54ee85 Add a response target picker to /copy (#39997)
## What changed

- Open a picker for `/copy` with the whole response plus each fenced code block and blockquote from the latest response.
- Label code blocks by language, show content previews, and preserve source whitespace and nested quote Markdown when copying an individual target.
- Keep the picker from disturbing terminal scrollback or queued input, retain clipboard leases, and avoid writing copied content to the session log.

## Testing

- Add coverage for target extraction, picker navigation and cancellation, exact copied content, plan responses, queued input, scrollback preservation, clipboard failures, and session logging.

GitOrigin-RevId: 77a35bc99f4f45932d39914f9a709b30fe8cd7c2
2026-08-21 19:23:26 +00:00
rafael-oai
950dd184a1 Expand browser and computer use requirements (#39995)
## What changed

- Add a top-level `allow_browser_and_computer_use` requirement.
- Support browser requirements for history access, automatic review, persistent approvals, and default or per-origin access policies.
- Support computer-use requirements for persistent approvals, default app access, macOS bundle IDs, Windows AUMIDs, and Windows executables.
- Preserve these settings and their sources when composing layered requirements.

## Testing

- Cover deserialization, empty-value detection, source propagation, and layered TOML merging for the new requirements.

GitOrigin-RevId: d14a10b64465f1c54e9bcc3795dc93031e6b029b
2026-08-21 19:20:09 +00:00
Won Park
56012fafb8 Add Guardian internal session support (#39994)
## What changed

- Add an extension API for spawning host-owned internal sessions and a
  `ThreadReadyInput` lifecycle callback that runs after thread registration.
- Add Guardian reviewer session scaffolding that records the parent thread and
  effective model, plus the under-development `guardian_ext` feature flag.
- Start internal sessions with fresh history while preserving parent lineage,
  shared session controls, and internal-thread visibility rules.
- Scope internal-session prompt cache keys to their source and parent thread,
  and expose `guardian` as an internal session source.

## Testing

- Cover internal-session spawning, parent metadata, history isolation, prompt
  cache keys, and extension spawner argument forwarding.

GitOrigin-RevId: 682dae80397d62bb36247796b447042e760ca364
2026-08-21 19:11:05 +00:00
andrewgu-oai
79b7606803 Keep credentials out of app-server logs (#39993)
## Why

App-server logs can be persisted or included in submitted diagnostics, so credentials used by model providers, authentication refreshes, and attestation requests must not appear in diagnostic output.

## What changed

- Add `RedactedString`, which preserves serialization and string access while replacing debug output with `<redacted>`.
- Use it for model-provider bearer tokens, header and query values, authentication command arguments, and attestation tokens.
- Avoid logging JSON-RPC error payloads and parser or authentication errors that may echo credentials; retain safe context such as error codes and categories.

## Testing

- Add an app-server regression test that exercises provider credentials, refreshed authentication tokens, and attestation tokens, then verifies none appear in persisted SQLite or submitted diagnostic logs.

GitOrigin-RevId: 8c50408adf94d93847658b1320682cf3b637d2cc
2026-08-21 19:04:32 +00:00
Benjamin Carlsson
45a3edc02a Keep keymap action descriptions stable while navigating (#39992)
## What changed

- Use one binding-aware description for each keymap action instead of swapping
  in separate text for the selected item.
- Keep the action menu content unchanged as the selection moves between items.
- Update key and key-chord replacement descriptions to name the affected
  binding directly.

## Testing

- Extend the keymap action menu test to move through every item and verify that
  the rendered picker remains unchanged.

GitOrigin-RevId: bbd2bd08ca444c76c28c5213ae077ad85bc50f27
2026-08-21 18:47:03 +00:00
Tamir Duberstein
f6519a355a Preserve TUI event ordering during active-thread draining (#39991)
## Why

Draining every queued active-thread event in one foreground pass can overrun the
frame budget. Buffered thread events can also race ahead of queued replay and
startup app events, causing the TUI to switch views before the corresponding
history and operations have been applied.

## What changed

- Bound active-thread draining to one target frame interval and leave remaining
  notifications queued for a later frame.
- Prioritize queued app events over active-thread events so replay state is
  applied before buffered closures or other thread notifications.
- Block startup input only for pending requests, rather than ordinary queued
  notifications whose draining yielded at the frame deadline.
- Leave selected side-thread closure handling to the foreground event loop.

## Testing

Added tests covering deadline-limited notification draining and foreground
handling of a selected side thread closing.

GitOrigin-RevId: 41080d3df13ca308eec1ea0fbb0ba067a4640c4c
2026-08-21 18:43:37 +00:00
felixxia-oai
51ebf5b184 Truncate Guardian instructions after rendering the policy (#39985)
## Why

Legacy classifier prompts without a `{{ tenant_policy_config }}` placeholder
append the security policy during rendering. Truncating the prompt before and
after that step can unnecessarily truncate the final classifier instructions
twice.

## What changed

Keep configured classifier instructions intact until the policy has been
rendered, then apply `max_classifier_instruction_tokens` once to the complete
prompt.

## Testing

Add an extension test that verifies the bounded developer message sent for a
legacy prompt with an appended policy.

GitOrigin-RevId: 3d776a159340f4dffb6e3c2d7a10b33392fa2240
2026-08-21 17:54:23 +00:00
felixxia-oai
c517cc6d84 Bypass risk scoring for models that require automatic review (#39981)
## Why

Models listed in `auto_review.required_on_models` must always use the full
automatic review path, regardless of any cached Guardian v2 risk score.

## What changed

- Skip Guardian v2 risk classification for models that require automatic
  review and clear any cached `SecurityRiskScore` before review routing.
- Count thread lookup failures as failed scoring attempts so stale scores
  cannot continue approving later tool calls.

## Testing

- Verify required-review models do not start a classifier and always run full
  reviews.
- Verify failed thread lookups advance score lag and fall back to strict review.

GitOrigin-RevId: 048d9a80ac2a282e05437a3abb0c46ec21391be8
2026-08-21 17:33:45 +00:00
sayan-oai
f580dd886f Enforce environment network policies for remote execution (#39980)
## Why

`EnvironmentConfig.network_policy` could describe attachment-owned traffic
restrictions, but core rejected every configured policy because execution did
not enforce it.

## What changed

- Resolve each remote environment's network policy for the selected command
  and apply it to the execution-scoped proxy.
- Compose owner rules with controller constraints and saved network decisions
  while preserving inherited domain and Unix-socket denials.
- Keep strict allowlists non-expandable, allow reviewable policies to use
  network approvals, and reject sandbox escalation that would bypass an owner
  policy.
- Reject policies for local execution, disabled managed enforcement, or a
  disabled controller proxy.

## Testing

Added coverage for policy composition, scoped remote proxy behavior, approval
and denial flows, offline execution, and unsupported environment authority.

GitOrigin-RevId: d9331f616df24de6cd13ed68196f0ff7b0ca4dd9
2026-08-21 17:29:41 +00:00
jif
8edb95f274 Preserve MCP compatibility with older executors (#39979)
## Why

Older executors do not support resolving HTTP header values from their own
environment. Sending environment-backed bearer tokens to them can prevent MCP
servers from starting.

## What changed

- Advertise executor support for environment-backed HTTP headers with the
  `httpHeaderEnvVars` capability.
- Delegate bearer-token resolution only when the selected executor advertises
  that capability; otherwise, resolve tokens available in the host environment.
- Exclude executor-owned MCP servers that require environment-backed bearer
  tokens when the executor cannot resolve them, while retaining compatible
  host-owned and executor-owned servers.

## Testing

Added protocol and environment-variable coverage plus an end-to-end test that
simulates an older executor and verifies compatible MCP servers remain usable.

GitOrigin-RevId: 43545926f6f7e0f3b1091eb29d34647f6372bc4a
2026-08-21 17:21:30 +00:00
viyatb-oai
696b4502df Allow semaphore limit queries in the macOS sandbox (#39976)
## Why

Python's `ProcessPoolExecutor` queries `SEM_NSEMS_MAX` through `sysconf`, which reads the `kern.sysv.semmns` sysctl on macOS.

## What changed

- Allow reads of `kern.sysv.semmns` in the base Seatbelt policy.
- Verify `/usr/bin/getconf SEM_NSEMS_MAX` succeeds with both read-only and workspace-write sandbox policies.

GitOrigin-RevId: ab3ae92dc8991729f90a47c1994eedb6c7a2b9cd
2026-08-21 17:16:51 +00:00
jif
d12a7f3fd8 Preserve root user authorization in subagent Guardian reviews (#39975)
## Why

MultiAgent V2 workers can be reviewed after the root conversation has received
new user authorization that is absent from the worker's own transcript. Guardian
reviews need that genuine user context without treating forwarded or
assistant-authored claims as authorization.

## What changed

- Add the bounded root conversation to Guardian prompts for worker reviews.
- Preserve user and assistant roles, and explicitly treat only root user messages
  as authorization evidence.
- Exclude summaries, review artifacts, and assistant commentary from the root
  conversation evidence.
- Apply the same evidence to both core Guardian prompts and Guardian V2
  classification.

## Testing

Add an integration test covering late root-user authorization, forged role text,
forwarded agent claims, and filtered synthetic authorization.

GitOrigin-RevId: 8846de69ba214a88f58f70675798d324e213427c
2026-08-21 17:12:42 +00:00
zm-oai
41ab01a2ea Fix elevated Windows sandbox setup activation (#39971)
## Why

Sandbox setup runs on a Tokio worker thread without a Windows message loop, so
`ShellExecuteExW` requires synchronous activation when launching the elevated
setup helper.

## What changed

Add `SEE_MASK_NOASYNC` to the shell execution flags while retaining
`SEE_MASK_NOCLOSEPROCESS` for helper process tracking.

GitOrigin-RevId: 875cc1d49bb19f92f940633b6315711143beeae7
2026-08-21 16:56:42 +00:00
felixxia-oai
16e2722c50 Consolidate code mode output helper tests (#39969)
## What changed

- Cover object serialization through the `text()` helper directly in the code
  mode runtime suite.
- Remove redundant core integration coverage for serialized text and rejected
  image outputs.

GitOrigin-RevId: f465b8361e9d725a7246994d9c41e9d01c969011
2026-08-21 16:50:34 +00:00
Zanie Blue
3432d3f2c9 Upgrade pnpm to 10.34.5 (#39967)
## What changed

- Pin pnpm 10.34.5 across the root, dev container, CLI, TypeScript SDK,
  and responses API proxy packages.
- Scope the allowed build for `@modelcontextprotocol/conformance` to its
  pinned GitHub tarball and refresh its lockfile resolution metadata.

GitOrigin-RevId: 28e385f8f07bd064888f763b16aa3c902e66c5f1
2026-08-21 16:45:05 +00:00
jif
e482cc66ae Keep Guardian reviews isolated from executor MCP servers (#39962)
## Why

Executor-owned MCP configuration can include required servers that are unavailable. Guardian review sessions should not attempt to discover those servers or let them block an approval review.

## What changed

- Skip projecting MCP servers from selected executors when the session source is a Guardian reviewer.
- Preserve executor MCP discovery for regular thread sessions.

## Testing

Added an app-server integration test that configures an unreachable required executor MCP server and verifies that Guardian can still review an escalated command and return its decision.

GitOrigin-RevId: 5b712a3ee04e6896d5ca0cff39a32dd8e0fe0132
2026-08-21 15:44:52 +00:00
jif
8ce27647fb Test browser MCP bearer tokens over executor WebSockets (#39961)
## Why

Browser MCP bearer tokens live in the executor environment and are not
inherited when an executor is spawned.

## What changed

Update the executor MCP integration test to launch `exec-server` over a
WebSocket, provide the bearer token only to that process, and configure the
MCP server with `bearer_token_env_var`. Register the running executor by URL
and verify the token is absent from the app-server test environment.

GitOrigin-RevId: 319b073d2eb1dbca015d4e6fea8ca714e78f3246
2026-08-21 15:34:19 +00:00
jif
4e6ef3b418 Stop advertising shell snapshots from local exec servers (#39958)
Set the local exec-server's `shellSnapshotV2` capability to `false` on all
platforms.

GitOrigin-RevId: 4faca33e62b736e7cd2b9587e7992b0723f915fb
2026-08-21 15:29:35 +00:00
jif
3882ced09c Add in-memory shell snapshots to unified exec (#39957)
## What changed

- Add the under-development `shell_snapshot_v2` feature and advertise executor support through environment capabilities.
- Use executor-managed, in-memory snapshots for eligible direct `bash`, `zsh`, and `sh` login commands, while applying the configured shell environment policy and avoiding duplicate automatic startup-file effects.
- Keep file-backed snapshots available for user-shell commands and fall back to the existing execution path when in-memory snapshots are unsupported or inapplicable.

## Testing

- Cover policy filtering, snapshot reuse without snapshot files, automatic startup files, local and remote execution, and legacy user-shell snapshots.

GitOrigin-RevId: 4ad6cdf13824913ac8c393ba38b9844230677579
2026-08-21 15:24:56 +00:00
Benjamin Carlsson
d446960657 Support voice-aware configuration and version-skew builds (#39953)
## What changed

- Add `chat.toggle_voice_mute` to the configurable TUI keymap and generated configuration schema.
- Let the exec-server version-skew harness build the voice-enabled CLI on Debian-like Linux hosts without preinstalled development metadata by assembling a temporary package sysroot.
- Preserve the existing build path on other Linux environments when the Debian package tools are unavailable.

## Testing

- Add a shell test that verifies a non-Debian Linux environment without voice metadata still proceeds to the Cargo build.

GitOrigin-RevId: 95c5ebc3f85d152a5217dee561286f2be662f79a
2026-08-21 15:19:48 +00:00
jif
054588acfe Honor required MCP servers from selected executors (#39952)
## What changed

- Preserve the `required` setting on HTTP MCP servers discovered from a selected executor.
- Cover delayed startup for a required executor MCP server and verify its tool is available on the first turn.

GitOrigin-RevId: df66e12233b8e1aaa7744e29c154157af8dc4776
2026-08-21 15:15:05 +00:00
jif
00a7b888b2 Discover HTTP MCP servers from selected executors (#39941)
## What changed

- Read `mcp_servers` configuration and requirements from each selected remote
  executor and add eligible HTTP servers to the thread's MCP runtime.
- Bind discovered servers to the thread's concrete executor snapshot and apply
  environment MCP policy and requirements. Discovery is best effort, and
  executor-local servers are not treated as required at startup.
- Ignore unsupported stdio servers and HTTP configurations that depend on
  environment-provided headers or header helpers.

## Testing

- Added an app-server integration test covering discovery, authenticated HTTP
  tool invocation, requirements enforcement, and exclusion of stdio servers.

GitOrigin-RevId: 6e1cdcebdbb1cc21a5a2285fbc5617d8d5997182
2026-08-21 14:23:33 +00:00
felixxia-oai
275ef855fa Allow more time for local code-mode host startup (#39940)
## What changed

Use a 30-second handshake timeout for locally spawned code-mode hosts while
retaining the existing 10-second timeout for WebSocket connections.

GitOrigin-RevId: de1801c062b5c71d4c7b2c33a53b51e0b672445e
2026-08-21 14:14:00 +00:00
Tamir Duberstein
748d8ac834 Bound unified exec output delta frames (#39937)
## What changed

- Cap each `ExecCommandOutputDelta` frame at 8 KiB and stop building frames once the per-call delta quota is exhausted.
- Preserve complete UTF-8 scalars across producer chunks while passing malformed or incomplete trailing bytes through without losing them.
- Append all process output to the transcript independently of delta emission.

## Testing

- Cover split multibyte characters, malformed and trailing bytes, frame and event limits, transcript preservation, and interactive PTY output.

GitOrigin-RevId: ef4100e353df01569a8fbae650c70f439920a2fd
2026-08-21 14:04:33 +00:00
jif
7f9832d0d0 Enforce issuer binding for MCP OAuth endpoints (#39935)
## Why

Interactive MCP OAuth must not trust authorization metadata that could route an
authorization code or PKCE verifier to an unrelated token endpoint.

## What changed

- Require an advertised issuer to match the origin that served authorization
  metadata.
- Validate authorization and token endpoint origins before starting both
  pre-registered and dynamically registered client flows.
- Allow delegated endpoint origins when the server advertises issuer-bound
  authorization responses, while retaining narrow compatibility exceptions for
  existing providers.

## Testing

Add coverage for rejected untrusted metadata, accepted issuer-bound delegation,
legacy provider exceptions, and both client registration paths.

GitOrigin-RevId: 43c9f94c9f6ba2d23d7e373576cf9fa26861cfc3
2026-08-21 13:28:28 +00:00
jif
9c3da20b3f Track remote MCP header environment variables (#39930)
## Why

Remote HTTP MCP connections can source header values from the host environment,
so those variables must remain part of the connection identity even when the MCP
server runs in an executor environment.

## What changed

- Track `env_http_headers` variables for remote HTTP MCP connections.
- Continue tracking `bearer_token_env_var` only for local environments, where the
  host resolves the token.

## Testing

Add coverage that verifies remote connections track host header variables without
tracking executor bearer-token variables, while local connections track both.

GitOrigin-RevId: 8fe175c54a101721a27b76495dcd298f0c2bc6a3
2026-08-21 13:22:25 +00:00
jif
93c54bca38 Resolve HTTP MCP bearer tokens in executor environments (#39926)
## Why

Executor-owned HTTP MCP servers need to read their bearer credentials from the
selected executor environment instead of the host process.

## What changed

- Preserve `bearer_token_env_var` for executor-owned HTTP MCP configurations and
  resolve it when the executor sends each request.
- Extend delegated HTTP headers with executor-local environment references while
  rejecting missing, empty, or protected credential variables.
- Keep transport-provided bearer authentication compatible with MCP redirect and
  OAuth handling without sending a placeholder authorization value.

## Testing

- Cover authenticated executor-owned MCP requests end to end.
- Cover delegated header resolution and rejection of protected variables.
- Cover parsing executor-owned bearer configuration and transport-provided bearer
  behavior.

GitOrigin-RevId: 442bf7382198ffb69eba797eb36d4c74faabda88
2026-08-21 12:50:15 +00:00
jif
ff0e95007c Honor request PATH in exec-server shell snapshots (#39917)
## What changed

- Apply all per-request environment overrides, including `PATH`, after restoring
  the captured shell environment.
- Remove `runtime_path_prepends` from `ShellSnapshotRequest` and the associated
  PATH replay and deduplication logic.
- Keep the shell snapshot integration test's runtime PATH setup in the command
  being executed.

GitOrigin-RevId: a6f8d2e144bf9977c7434bc58b60ac972f7e0449
2026-08-21 12:08:02 +00:00
Zahan Malkani
536f86e5cc Support attaching to existing realtime calls (#39876)
## Why

Clients that create and negotiate realtime calls themselves need Codex to join
those calls without creating another call or overwriting the client-owned
session configuration.

## What changed

- Add the `existingCall` transport to `thread/realtime/start`, accepting a
  client-provided `callId` and optional `realtimeSessionId`.
- Attach Codex over the call's sideband WebSocket without SDP negotiation or a
  session update, and reconnect that sideband while preserving transcript
  state.
- Default existing calls to realtime v1, support v1 and v3, and reject v2 or
  options that would reconfigure the client-owned session.
- Encode call IDs as a single URL path segment for v3 sideband connections.

## Testing

Add protocol, app-server, core, reconnection, authentication-header, and URL
encoding coverage for existing-call attachments.

GitOrigin-RevId: 2046b70566f98efa55381bb1e461ea3cc68256c5
2026-08-21 06:41:28 +00:00
Eric Traut
2aaefa32b0 Add keybindings for cycling TUI permission modes (#39873)
## What changed

- Add unbound `previous_permission_mode` and `next_permission_mode` actions to
  `tui.keymap.chat` so users can configure shortcuts that cycle through the
  available built-in permission modes.
- Apply shortcut selections only to the active session, without writing them
  to `config.toml`, and report update failures in the transcript.
- Exclude modes disallowed by managed requirements or platform safety checks,
  reject printable-key bindings, and ignore these bindings in project config.

## Testing

- Cover mode cycling, unavailable modes, session-only updates, server errors,
  stale threads, keymap validation, and project-config sanitization.

GitOrigin-RevId: c3cfdf1e732b7b7bfe8f53fcac19a37e593bbfab
2026-08-21 06:19:23 +00:00
Eric Traut
44e95c857f Allow session configuration with codex agents (#39870)
## Why

`codex agents` rejected invocation-specific configuration, preventing the
dashboard from applying settings when starting a shared thread.

## What changed

- Accept interactive options such as model, approval, sandbox, search, working
  directory, and configuration overrides when opening the agents dashboard.
- Forward supported session-flag configuration into threads started through an
  embedded or remote app server, while excluding unrelated values.
- Continue to reject initial prompts and images, along with local provider and
  additional-directory settings that cannot be applied to a remote server.

## Testing

- Cover accepted dashboard options and rejected incompatible inputs.
- Verify that explicit feature and sandbox overrides reach shared threads in
  both embedded and remote modes.

GitOrigin-RevId: f10aa1e16ff62b49d55679e987d9e458438ba3f8
2026-08-21 06:08:26 +00:00
Benjamin Carlsson
9ab176f488 Limit pending input preview wrapping work (#39864)
## Why

Pending input previews display at most three wrapped rows, but previously wrapped every logical line before truncating the result. This made rendering do unnecessary work for very large multiline inputs.

## What changed

Limit pending steers, rejected steers, and queued follow-up inputs to four source lines before wrapping: three for the preview and one to detect overflow and render the ellipsis.

## Testing

Keep multiline preview coverage for queued messages and pending steers, including blank lines near the truncation boundary.

GitOrigin-RevId: 4c300b13532983ff9c3bdfbd62d6ca722ea3a5aa
2026-08-21 05:35:35 +00:00
richardopenai
2151d3a5b7 Reset registry retries when refreshing Noise bundles (#39852)
## Why

Refreshing a Noise rendezvous bundle after an unauthorized handshake inherited
the initial registry lookup's retry count. If that lookup had exhausted its
retries, a transient registry error during the refresh failed immediately.

## What changed

Reset the registry retry count along with the operation deadline before
requesting a replacement bundle after a `401` handshake response.

## Testing

Extend the initial Noise connection test to exhaust the first lookup's retry
budget, receive a `401`, then verify that an offline replacement lookup is
retried and connects successfully.

GitOrigin-RevId: bcfad50ea32d69855f1c2c4c461022b3ecbbd941
2026-08-21 03:47:37 +00:00
Brandon Zhang
27c05a52e0 Include context window IDs in response metadata (#39847)
## What changed

- Add `context_window_id` to turn metadata for sampling and compaction requests, using the UUID for the model-visible context window.
- Keep the ID stable for requests in the same context window and advance it after compaction, independently of the existing thread-generation `window_id`.
- Reserve `context_window_id` so client metadata cannot override it.

## Testing

- Cover HTTP and WebSocket metadata, remote compaction, token-budget context alignment, resume behavior, and post-compaction window changes.

GitOrigin-RevId: 55cceea377ad509c8dd96ad668f2b5703ea46a63
2026-08-21 03:31:56 +00:00
Dylan Hurd
bd19459358 Ignore project instructions for untrusted projects (#39837)
## What changed

- Skip project-scoped `AGENTS.md` discovery when the active project is untrusted, while preserving user-level instructions.
- Include the active project trust level in the instruction cache key so runtime trust changes reload the applicable instructions.
- Preserve updated project trust metadata during runtime configuration refreshes.

## Testing

Add coverage for initially untrusted projects and for switching between trusted and untrusted states at runtime.

GitOrigin-RevId: 284bf7693943f585013fb5fe4b6aa3309bc50cf3
2026-08-21 02:33:50 +00:00
pmccrary-oai
d8ec270183 Rename the history notes extension config option (#39830)
## What changed

Rename the token-budget configuration key and its Rust field from
`use_history_notes_history` to `use_history_notes_extension`. Update the config
schema, extension gating, explicit-setting detection, and tests to use the new
name consistently.

GitOrigin-RevId: b6a514e23f02095fcd1d35dc42eeb7394b800c77
2026-08-21 01:51:48 +00:00
pmccrary-oai
daa48072f4 Add history and notes tools for token-budget sessions (#39827)
## Why

Token-budget sessions need a way to recover prior conversation context and preserve working state across context-window transitions.

## What changed

- Add direct-model `history` tools for listing windows and items, reading items, and searching conversation contents.
- Add direct-model `notes` tools for listing, reading, searching, appending, and writing persistent notes.
- Route tool calls through the configured Codex backend with trusted session and agent context, bounded request arguments, and truncation-aware output handling.
- Expose the extension when `features.token_budget.use_history_notes_history` is enabled with an OpenAI provider and Codex backend authentication.

## Testing

- Cover tool registration, configuration changes, provider and authentication requirements, backend request context, encrypted output preservation, and request and response limits.

GitOrigin-RevId: 43b259f01014ba3f30803dd7cd5634942407a9bb
2026-08-21 01:24:52 +00:00
rka-oai
f20b63e85c Use Responses compaction for Amazon Bedrock (#39825)
## What changed

- Switch Amazon Bedrock remote compaction to `compaction_trigger` items sent through `/v1/responses`.
- Remove the legacy dedicated compaction protocol from provider capabilities.
- Default remote compaction to unsupported and explicitly enable it for OpenAI, Azure Responses, and Amazon Bedrock providers.

## Testing

- Cover manual and automatic Amazon Bedrock compaction requests and their compacted history.
- Verify remote-compaction capabilities for configured and Amazon Bedrock providers.

GitOrigin-RevId: cf9ba314595367518b37a85f334f0c105ce47e45
2026-08-21 00:53:52 +00:00
felixxia-oai
54201093d4 Preserve uncapped Guardian classifier instructions (#39822)
## Why

Guardian v2 applied an implicit token limit to classifier instructions even when
no limit was configured, which could truncate the rendered policy.

## What changed

- Leave classifier instructions unbounded by default.
- Continue honoring `max_classifier_instruction_tokens` from local or model
  configuration, with local configuration taking precedence.

## Testing

- Cover full policy rendering without a configured cap and truncation when an
  explicit cap is present.

GitOrigin-RevId: 70eb42d43858e0656129dd438b10b60940fd97c6
2026-08-21 00:16:39 +00:00
chess
67b2c8c6fb Defer legacy filesystem policy projection (#39813)
## Why

Applying session settings rebuilt and compared a legacy filesystem policy even
when the update could not trigger cwd-based policy rebinding.

## What changed

Compute the legacy projection only for cwd changes whose filesystem policy has
a rebindable project-root write entry. Preserve the existing equivalence check
before rederiving the policy.

GitOrigin-RevId: c428a5c54f1b5b1300be406cac374a6fd29bb9a8
2026-08-20 23:36:13 +00:00
chess
969efa5470 Avoid materializing writable-root carveouts for presence checks (#39812)
## What changed

- Add `FileSystemSandboxPolicy::has_writable_roots_with_cwd` to detect an
  effective writable root without constructing its read-only carveouts.
- Use the helper when classifying permission profiles and selecting patch
  rejection reasons.

## Testing

- Verify the presence check matches the existing materialized-root result
  across read-only, unrestricted, external, writable, denied, and unresolved
  special-path policies.

GitOrigin-RevId: 17ee490aa3180e05732133203f68544d9de5268b
2026-08-20 23:26:59 +00:00
Jeremy Rose
21facf2273 Restrict macOS preference reads to full-disk policies (#39811)
## Why

The macOS preferences service can expose data outside a sandbox's allowed
filesystem read roots.

## What changed

- Move the Seatbelt preference and `cfprefsd` grants into a separate policy
  section that is included only when filesystem reads are unrestricted.
- Remove the equivalent grants from the restricted platform defaults.

## Testing

- Verify both Seatbelt profiles include preference grants only for full-disk
  read policies, including policies with denied paths or globs.
- Verify a restricted sandbox cannot retrieve a preference whose plist is
  denied, while an unrestricted read policy can.

GitOrigin-RevId: 90388366a7302bca1830ad0439544be8babc7321
2026-08-20 23:18:55 +00:00
zm-oai
3cde5d4ccd Preserve WINDIR in core Windows shell environments (#39809)
## What changed

- Add `WINDIR` to the Windows core environment variable allowlist.
- Extend the Windows core-inheritance test to verify that a case-variant
  `WinDir` entry is retained.

GitOrigin-RevId: 0305d8fa882ba2705a7ce7661098cedac1339c43
2026-08-20 23:14:32 +00:00