Commit Graph
11480 Commits
Author SHA1 Message Date
Charlie Marsh 0bc73bbeb1 Add opt-in protocol discovery for local stdio MCP servers (#57210)
## Why

Stdio servers without `CODEX_MCP_PROTOCOL_VERSION` use the legacy handshake, even when they support MCP `2026-07-28`.

## What changed

- Add the disabled-by-default `mcp_connection_sharing` feature to enable discovery for eligible local stdio servers.
- Recover from failed or late discovery with a fresh handshake when needed, waiting for the previous helper to release resources before restarting.
- Retain a working legacy connection when an upgrade attempt fails for the same account, except on authentication errors.
- Keep tool catalogs separate by protocol and invalidate legacy catalogs when discovery negotiates the modern protocol.

## Testing

Add regression coverage for failed and late discovery, legacy fallback, protocol-specific catalog reuse, message limits, and Windows descendant cleanup.

GitOrigin-RevId: 36c675ef3b81d32fccf06ccbddda2312cfe602c9
2026-10-26 19:37:06 +00:00
taohong-oai 33b16a9306 Report turn critical-path timing in analytics (#57209)
## What changed

Include critical-path capture status and duration totals in `codex_turn_event`, with categories for inference, auto review, user wait, tools, overhead, and unknown time. Count sampling and compaction as inference.

Distinguish `disabled`, `incomplete`, and `complete` capture. Emit null durations for disabled or incomplete capture so missing measurements are not reported as zero. Freeze the completion timestamp so repeated terminal notifications preserve the original measurement window.

## Testing

Add core and analytics tests for capture status, duration reporting, rounding, and repeated completion. Add app-server integration coverage for completed and interrupted turns with default, enabled, and disabled capture.

GitOrigin-RevId: c6c867120ee563ac48584c2f4b12df23acbabe06
2026-10-26 19:35:31 +00:00
Eric Traut 57b4c60463 Propagate installer download failures in standalone Unix updates (#57208)
## Why

The standalone Unix update pipeline could return success when `curl` failed because the shell consuming its output exited successfully.

## What changed

Download the installer into a shell variable and evaluate it only after a successful download, preserving `CODEX_NON_INTERACTIVE=1`. Update the displayed update command to match.

## Testing

Add a Unix regression test that forces an installer download failure and asserts a nonzero exit status. Update the update-available snapshot for the new command.

GitOrigin-RevId: cf6ce0dae483203e3609bb35f35eb04bb3096c28
2026-10-26 19:29:16 +00:00
taohong-oai 7c997fe2de Attribute approval waits to tool critical-path timing (#57207)
## Why

Automatic reviews and user prompts previously invalidated critical-path captures even when their owning tool invocation was known.

## What changed

Record automatic review time as `auto_review` and waits for approvals, permission requests, and user input as `user_wait` when `CriticalPathTiming` is enabled. Bind timing to the owning invocation before asynchronous work begins, and use the triggering tool's identity for network approvals. Continue invalidating captures when a wait cannot be attributed.

## Testing

Add coverage for cancellation, reused call IDs, network ownership, and disabled capture. Update the automatic review integration test to verify attributed review duration.

GitOrigin-RevId: 0a1f5feebd0c4f5ed67dc058e832ec5f8818db02
2026-10-26 19:28:51 +00:00
Eric Traut e1c87d1c2d Ignore the crypto-bigint timing advisory in dependency checks (#57206)
Add `RUSTSEC-2026-0387` to the `cargo audit` and `cargo deny` ignore lists for `crypto-bigint` 0.5.5, pulled in through `elliptic-curve` 0.13.8.

Document the affected dependency paths and the potential timing leakage during private-key or session-secret operations. Remove the exceptions when those paths use `crypto-bigint` 0.7.6 or later.

GitOrigin-RevId: 7ff42c9b127900ddf772bf1cc88947f6e7dfcd10
2026-10-26 19:28:25 +00:00
Alex Kira 85f29b453a Register the untrusted_as_tool_output feature flag (#57204)
## What changed

Add `untrusted_as_tool_output` as an under-development feature, disabled by default, and expose it in the configuration schema. The flag is intended for rendering client-supplied untrusted context as standalone named tool outputs.

GitOrigin-RevId: 6fe630c8d380a87edb48e08887215c1ec17447ed
2026-10-26 19:27:29 +00:00
Andrei Eternal beb34ce8d0 Preserve command cwd in permission and post-tool hooks (#57203)
## Why

`PermissionRequest` and `PostToolUse` hook inputs could report the turn's working directory instead of the local command's execution directory. This also affected commands whose results were collected in a later turn after the working directory changed.

## What changed

- Report the local command's execution directory in hook input `cwd`, consistent with `PreToolUse`.
- Preserve the original directory through `write_stdin` approvals and delayed completion, including network permission requests.
- Retain the host directory for remote commands and keep hook process working directories unchanged.

## Testing

Add coverage for relative and absolute workdirs, approval denials, command rewrites, completion and stdin approval across turns, remote command fallback, network approvals, and Unix and Windows path formatting.

GitOrigin-RevId: ef5dad2a0634dda9edb2f841ef4fe49ae0d1187d
2026-10-26 19:21:08 +00:00
trpcic-openai 536d1f5b68 Preserve the tool dispatch span across runtime futures (#57202)
## What changed

Instrument the returned tool runtime future with the same dispatch span as the spawned dispatch task, keeping completion and cancellation handling in that span.

## Testing

Extend the detached code-mode callback test to assert that the router's `dispatch_tool_call_with_state` span has `dispatch_tool_call_with_code_mode_result` as its parent.

GitOrigin-RevId: e4d4bef26563554bf703b3e4f05490e25d8eb0ad
2026-10-26 19:20:44 +00:00
taohong-oai f371f9701f Capture direct-tool critical paths behind a feature flag (#57201)
## What changed

Add the default-disabled `critical_path_timing` feature to capture dependency paths for root-agent turns. Connect direct tool dispatch, execution-lock handoffs, and completed tool batches to turn timing so overlapping work shares its common history without double counting.

Omit captures for unsupported dependencies, including CodeMode, agent communication, approval review, and user waits. Settle aborted tasks before freezing timing, invalidate captures on forced teardown, and apply runtime feature changes only to future turns.

## Testing

Add coverage for serial and overlapping tool dispatch, execution-lock dependency handoffs, cancellation, unsupported paths, frozen timing after completion, and configuration refresh boundaries.

GitOrigin-RevId: 71458b654b1c4a05799886928b449c948ea33109
2026-10-26 19:19:10 +00:00
cassirer-openai 36021e1ad5 Truncate rollout JSON summaries at UTF-8 character boundaries (#57199)
## Why

Truncating a JSON summary at the 240-byte limit can panic when the cutoff falls inside a multibyte UTF-8 character.

## What changed

Truncate at the nearest preceding character boundary before appending `...`.

## Testing

Extend the JSON tool-call reuse test with multibyte arguments and assert the truncated summary and original payload reference.

GitOrigin-RevId: e4b2af17eb6e3abaeb042772944305c6e1744bdf
2026-10-26 19:11:53 +00:00
Andrei Eternal fe15bd38de Report the local command working directory in PreToolUse hooks (#57198)
## Why

`PreToolUse` hooks receive the host working directory even when a local
`exec_command` call specifies a different `workdir`. This prevents hooks from
seeing the directory in which the command will execute.

## What changed

- Share working-directory resolution between command execution and hook input,
  using the selected environment and the command's `workdir`.
- Report the resolved local directory in the hook input's `cwd`. Keep hook
  processes in the host directory and retain the host `cwd` for remote commands.
- Reject invalid environment selections or paths before running hooks and record
  failures in tool-result telemetry.

## Testing

Add unit and integration coverage for default, empty, relative, and absolute
working directories; Windows path conventions; remote commands; hook denial and
input rewriting; and invalid arguments that fail without running hooks.

GitOrigin-RevId: 97f71f6d3e21a5d95a7abf5384f06f4993241797
2026-10-26 19:11:28 +00:00
Felipe Coury 60e4d10ad9 Clarify skill toggle summaries in the TUI (#57197)
## What changed

Omit zero-count actions and use singular or plural wording when summarizing skill changes. For example, show `Disabled 1 skill` instead of `0 skills enabled, 1 skills disabled`.

## Testing

Add a snapshot test covering enable-only, disable-only, mixed, and unchanged skill states, including no summary when nothing changes.

GitOrigin-RevId: ff68c799f29ceb8736e6941778d29a3f8d500b70
2026-10-26 19:11:01 +00:00
Charlie Marsh 7d1492ffab Isolate MCP inputs and timeouts for callers sharing a connection (#57196)
## Why

Concurrent requests on a shared MCP connection need to route prompts to their own callers and pause only their own timeouts while awaiting input.

## What changed

- Add `call_tool_with_elicitation` and `read_resource_with_elicitation` with per-request callbacks and timeout pause state, requiring MCP protocol `2026-07-28`.
- Share continuation handling between tool calls and resource reads, and assign globally unique input IDs across requests and connections.
- Add `enable_request_cancellation` to extend cancellation on dropped response futures to catalog, resource, and custom requests.

## Testing

Add or extend tests for concurrent form and URL input routing, unique prompt IDs, independent native verification cancellation and timeouts, resource continuations, and remote cancellation when resource or custom request futures are dropped.

GitOrigin-RevId: ad5a3cd0e289726828a694d00c20870e2d1108c6
2026-10-26 19:10:13 +00:00
cassirer-openai b6a4378862 Classify rollout tool calls by their runtime handler (#57194)
## Why

Tool interception and MCP aliases can route a requested callable to a different handler. Rollout traces need to reflect the handler that actually executes, including when an `exec_command` invocation is intercepted as `apply_patch`.

## What changed

Carry an explicit `ToolCallKind` in runtime-start events and use it to update the tool call's execution classification. This replaces MCP-specific payload inspection while preserving the original callable summary and invocation for intercepted patch and aliased MCP calls.

## Testing

Add a regression test verifying that an intercepted `exec_command` is recorded as `ApplyPatch`, retains its original summary and invocation, completes successfully, and creates no terminal operations or sessions.

GitOrigin-RevId: 0e72f3ef55cda2796e779efd16241e4a0dbf0c5b
2026-10-26 19:04:02 +00:00
cassirer-openai cfc11bfab3 Preserve failed write_stdin calls in rollout trace replay (#57193)
## Why

Invalid model arguments to `write_stdin` represent a tool failure, but parsing them could fail rollout trace replay.

## What changed

Skip terminal operation creation when dispatched `write_stdin` arguments cannot be parsed or lack a usable `session_id`. Preserve the generic tool call and its error, including the original arguments, so replay can continue.

## Testing

Add a regression test covering malformed JSON and missing or null `session_id` values. Verify that replay retains the failed call's arguments and error without creating terminal operations or sessions.

GitOrigin-RevId: 967e975a88072c169eb3e391d5c62e807d608fbf
2026-10-26 19:03:36 +00:00
Anthony Tafoya 6654f7a7ab Gate capability discovery V2 on executor version (#57192)
## Why

Executors older than `0.164.0` can advertise V2 discovery support without implementing the final contract. Enabling V2 also suppressed V1 discovery for incompatible executors, hiding selected capability roots and skills.

## What changed

Require both the V2 capability flag and an executor version of at least `0.164.0` before issuing `capabilities/discoverV2`. Share this compatibility check between session discovery and the exec-server client. Fall back to V1 when incompatible executors provide no V2 snapshots, clearing any previously stored V2 inventory.

## Testing

Add coverage for version boundaries, prereleases, missing and malformed versions, and transport recovery for compatible executors. Verify that an older executor retains selected plugins and skill instructions through V1 with V2 enabled.

GitOrigin-RevId: 93adf52fc91f02b58fd14f8ff3b093712b3346b8
2026-10-26 19:03:08 +00:00
Adam Perry @ OpenAI 245691b2dc Read unified exec output directly from stdout and stderr (#57191)
## What changed

Consume local stdout and stderr receivers directly with `tokio::select!`, removing the intermediate broadcast channel and its lag-related chunk skipping. Drain both streams until they close.

Pass `ExecOutputStream` through local and remote output collection to `OutputBuffers::push_chunk`, while retaining combined output buffers.

## Testing

Update output-buffer tests for the stream argument and exercise stderr chunks in pushed-event and replay test fixtures.

GitOrigin-RevId: be7804fd30cefeb812e372454665923ba051ddb4
2026-10-26 19:01:45 +00:00
alexsong-oai be7cd6fd9e Add a credential file override for GCP provider authentication (#57188)
## What changed

Support `model_providers.gcp.credential_file` as an absolute path to a Google Application Default Credentials (ADC) file. Pass it as `GOOGLE_APPLICATION_CREDENTIALS` in the provider auth command's environment, retaining the override for token refreshes without changing the parent process environment.

Validate the path before merging GCP defaults and preserve the setting in thread configuration serialization.

## Testing

Add coverage for invalid paths, configuration round trips, separate provider token caches, and credential overrides retained after a `401` refresh. Include a Windows regression test for credential paths containing command metacharacters.

GitOrigin-RevId: d9a1d4b3775a9a4c4325dddaa153d92a2d1430a0
2026-10-26 18:33:05 +00:00
nvogt-oai 77eb019ad0 Allow advisory rollout budgets with optional limit enforcement (#57187)
## What changed

Add `features.rollout_budget.enforce_limit`, defaulting to `true`. Setting it to `false` keeps shared usage accounting and budget reminders active while allowing turns to continue after the budget is exhausted.

## Testing

Extend coverage to check enforced and advisory budgets on the current and subsequent turns, including a zero-remaining-budget reminder in advisory mode. Verify that configuration defaults to enforcing the limit.

GitOrigin-RevId: deeac8dae5714cc7c10d030cade6f3bfbfc8d3a7
2026-10-26 18:31:49 +00:00
viyatb-oai af2e52c858 Fail closed on unreadable glob search root metadata errors (#57186)
## Why

Linux sandbox deny-glob expansion silently skipped search roots when metadata lookup failed, potentially discarding a deny rule.

## What changed

Return a fatal error with the search root and underlying error when metadata lookup fails, except for missing or non-directory roots, which still have no matches. Continue following directory symlinks.

## Testing

Add regression tests for symlink-loop metadata errors stopping expansion before scanning, absent and non-directory roots being skipped, and symlink roots expanding to both logical and canonical paths without ripgrep.

GitOrigin-RevId: bd97804ec5b599376c525addaacce6b1f29f9895
2026-10-26 18:31:21 +00:00
Adam Perry @ OpenAI 090bea7b71 Centralize unified exec output rendering (#57185)
## What changed

Introduce `CapturedStream` to keep retained output text and omitted-byte counts together. Use its shared renderer for unified exec logs and model-facing output, preserving omission markers and truncation notices.

GitOrigin-RevId: 045d925df1e31945755196dafed5f78ed507b33b
2026-10-26 18:29:53 +00:00
Alex Kira 8ebd272491 Add optional names to untrusted additional context (#57181)
## What changed

- Add an optional `name` to `AdditionalContextEntry` across the protocol, app-server schemas, and generated clients.
- Accept names matching `[a-z][a-z0-9_]{0,63}` only for `untrusted` context. Reject invalid names and names on `application` context before admitting turn input, returning invalid-request errors from `turn/start` and `turn/steer`.
- Preserve existing model-input rendering and deduplicate context when only its name changes.

## Testing

Add coverage for valid name boundaries, callers that omit `name`, invalid-name rejection without admitting input, and deduplication across name changes.

GitOrigin-RevId: 2caffa6fddd40ddb178733b335f520f317239edd
2026-10-26 18:23:07 +00:00
viyatb-oai 457441bca9 Add constraint-aware standalone network proxy configuration (#57180)
## What changed

- Export `StaticNetworkProxyConfig` to parse and serialize network policy with constraints, and validate them before building proxy state.
- Add `--strict` and `from_slice_strict` for managed callers, requiring explicit `constraints` and rejecting unknown fields at every typed level. Default parsing permits top-level `metadata` and omitted constraints while still rejecting unknown policy fields.
- Match allowed Unix socket paths case-sensitively when validating constraints.
- Bound configuration file reads to the size limit plus one byte.

## Testing

Add coverage for constraint round trips, weakened policy rejection, exact socket path matching, parsing modes, and CLI flag selection. Exercise automatic MITM enablement through both parsers.

GitOrigin-RevId: c45d094624240f23dd4659128e72a4208d5d5f1c
2026-10-26 18:22:40 +00:00
cooper-oai b8f6d25ce7 Consolidate async header authentication in apply_auth_headers (#57179)
## What changed

Remove `AuthProvider::resolve_auth_headers` and use `apply_auth_headers` as the async interface for header-only authentication. Migrate providers, callers, and existing tests to the shared interface, passing an empty `HeaderMap` when only authentication headers are needed.

Document that providers may refresh credentials asynchronously and that callers must use the returned header map so providers can remove superseded credentials.

GitOrigin-RevId: 42449de6fddd2be2c50c475c8e92628493197007
2026-10-26 18:22:11 +00:00
lsingh-oai 3d1001e865 Route FedRAMP API keys to government endpoints by default (#57178)
## Why

API keys with FedRAMP issuance markers previously used commercial endpoint defaults without a FedRAMP request header.

## What changed

- Recognize `sk-proj-fedramp-` and `sk-svcacct-fedramp-` prefixes as routing hints and send `X-OpenAI-Fedramp: true`, preserving the complete key for authentication.
- Select `https://gov.api.openai.com/v1` for default OpenAI API routing and `https://gov.chatgpt.com/backend-api/` for default ChatGPT backend requests, including model discovery and analytics.
- Preserve explicit endpoint overrides, including an explicitly configured commercial default URL.
- Resolve provider routing and authentication from the same credential snapshot, and apply key-dependent routing to realtime WebSocket startup.

## Testing

Add regression coverage for prefix recognition, unchanged key storage and authorization, provider credential precedence, endpoint overrides, credential rotation, model discovery, analytics routing, and realtime request preparation.

GitOrigin-RevId: a62576ce205c34e067532b8e6c0e431f87a157e2
2026-10-26 18:20:30 +00:00
ioanbudea-OAI 83a9600acb Defer Guardian Node REPL output truncation until prompt preparation (#57176)
## What changed

Preserve complete Node REPL tool outputs during synchronous transcript collection and apply the configured output token limit during prompt preparation, after full or delta transcript selection.

## Testing

Update transcript assertions to verify that oversized Node REPL outputs remain intact during collection and are truncated to the selected token cap when rendered.

GitOrigin-RevId: 30ced935c04db456a277f7e58281d45e0e2047dd
2026-10-26 18:15:37 +00:00
smurching-oai ec513795a6 Integrate config-server policies with startup and authentication (#57175)
## What changed

- Use the managed configuration loader in CLI, exec, TUI, and app-server configuration flows so `requirements.toml` can select a config server.
- Sign in to the config server when needed during interactive TUI startup and CLI login, reload configuration after CLI sign-in, and clear config-server credentials on CLI logout.
- Preserve the app-server's config-server settings and refresh worker across OpenAI login and logout.
- Require config-server settings to be applied when loading CLI and doctor configuration.

## Testing

Add app-server integration tests using a local HTTPS config server to verify managed provider and instruction settings at startup, preservation across API-key login and logout, and cache reuse after restart and thread resume.

GitOrigin-RevId: 27ee81f7943d2290a5c3fcc0ac556579ec63f8b4
2026-10-26 18:14:57 +00:00
viyatb-oai 619531225b Add scoped request-body secret substitution to MITM hooks (#57174)
## What changed

- Add `body_secret_substitution` actions to version 2 MITM configuration, replacing exact opaque placeholders with secrets from environment variables or files within the matching hook's scope.
- Bound body size, expansion, replacement count, and search work. Reject overlapping matches, compressed payloads, trailers, and supplied payload-integrity headers.
- Recompute `Content-Length` and substitute before SigV4 signing so signatures cover the transmitted body.

## Testing

Add coverage for markers split across chunks, expansion limits, invalid payloads, overlapping bindings, secret redaction, and search limits. Add a TLS forwarding test that verifies hook scope and independently checks the signature of the substituted body.

GitOrigin-RevId: fa95c9ae0c8fc8f695e03c0e87a0a4875d8418fd
2026-10-26 18:14:26 +00:00
Charlie Marsh a797dd7c6f Expose lifecycle timestamps on app-server thread items (#57172)
## What changed

- Add nullable `startedAtMs` and `completedAtMs` fields to `ThreadItem` in live notifications and turn history. Values are Unix milliseconds when recorded.
- Preserve recorded item times through history reconstruction, pagination, and resume, including command start times recorded during approval.
- Separate the Rust item payload into `ThreadItemPayload` while keeping the JSON payload flat, and update consumers, schemas, and generated TypeScript and Python types.

## Testing

Extend coverage for timestamp serialization, history reconstruction, paginated reads and resume, and persisted Python SDK items.

GitOrigin-RevId: ecbcee95af52db7c807b46a6e9deb30e5fba1f80
2026-10-26 18:13:00 +00:00
cooper-oai cf29971d93 Integrate runtime authentication into model requests (#57171)
## What changed

- Add opt-in runtime authentication through `ModelClient::with_runtime_auth`, requiring the provider and runtime manager to share the selected OpenAI credentials.
- Keep runtime identity, credentials, routing, and transport selection consistent for each request and its retries, signing a fresh assertion for each attempt.
- Apply authentication asynchronously to WebSocket handshakes, replace stale authentication headers, and reconnect when the runtime changes.
- Reject account, organization, or project selectors that conflict with the registered runtime, and preserve gateway OAuth composition.

## Testing

Add coverage for dual-header and assertion-only authentication, HTTP retries, runtime replacement and account switches, stale WebSocket headers, selector mismatches, gateway OAuth failures, transport revocation, and Realtime compatibility.

GitOrigin-RevId: 45b9efc2c80481406a0f6f6396a8cdd21d933c12
2026-10-26 18:06:07 +00:00
smurching-oai 6e319d2ca7 Clarify config loader APIs and share interactive login setup (#57169)
## What changed

- Rename ChatGPT-specific bundle loaders to `chatgpt_config_bundle_loader*` and use managed-config terminology for shared loader plumbing.
- Pass `Config` directly when updating the app-server's managed configuration loader.
- Share configuration loading, logging setup, and result handling between browser and device-code login.
- Expose the CLI cloud-config helpers and `provider_uses_first_party_auth_path` through their library APIs.

## Testing

Extend CLI login coverage to verify that `forced_login_method="api"` rejects both `login` and `login --device-auth` while preserving saved API-key credentials.

GitOrigin-RevId: 9e8fa6110dc80882ba365e550b48ac77da604940
2026-10-26 18:05:05 +00:00
trpcic-openai c21153bd92 Track CUA tool call starts and deduplicate lifecycle events (#57167)
## What changed

Emit `codex_cua_tool_call_started` for `js` MCP calls on Node REPL-backed connectors. Include start time, tool identity, plugin and connector IDs, and available thread and response attribution without recording tool arguments.

Suppress duplicate starts and replayed completions for CUA calls while retaining the existing MCP completion event. A completion received without a start does not prevent a later valid lifecycle from being recorded.

## Testing

Add a lifecycle regression test covering missing starts, duplicate notifications, replay after completion, attribution fields, timestamps, and exclusion of tool arguments from serialized events.

GitOrigin-RevId: 68554ad76c636bb3c2be38bda56f5ea6da8d9830
2026-10-26 17:57:13 +00:00
Dmitriy Kovalenko 2d3de37834 Surface automatic marketplace update failures as startup warnings (#57166)
## Why

Automatic marketplace update failures were only logged, leaving users without a visible startup warning.

## What changed

Send marketplace update errors and task startup failures through app-server warning notifications. Queue background warnings until a client initializes in both standalone and in-process servers, and centralize startup configuration warning delivery.

## Testing

Add a TUI integration test and snapshot covering two marketplace name mismatch failures, the warning count, and navigation between their details with `F2` and the arrow keys.

GitOrigin-RevId: af55a5555affd9d89ac15a546163daeaafd3b3e8
2026-10-26 17:56:43 +00:00
alexsong-oai 970111f6cb Allow configuring GCP project and location in provider settings (#56560)
## Why

Deriving a Vertex AI endpoint previously required environment variables. Allow the project and location to be specified directly in GCP provider configuration.

## What changed

- Add `model_providers.gcp.project_id` and `model_providers.gcp.location`, with each taking precedence over its corresponding environment variable. Keep `global` as the default location and preserve explicit `base_url` overrides.
- Validate configured endpoint fields and preserve them through thread configuration serialization.
- Apply built-in GCP defaults, including default command authentication, when checking managed provider requirements so unchanged requirements are accepted.

## Testing

Add coverage for endpoint precedence, invalid explicit configuration, provider construction, thread configuration round trips, and managed GCP requirement checks, including repeated model listing.

GitOrigin-RevId: c3704bcc0b7d4872374e2cae623fd24d75fb02b4
2026-10-23 18:50:54 +00:00
felixxia-oai 7848e3393c Remove Guardian snapshot-specific context helpers (#56559)
## What changed

Remove snapshot instruction deduplication, separate retained-assistant framing, and the associated omission-metadata special cases. Use `retain_new_instructions` in transcript rendering tests and replace the test-only Decisions snapshot adapter with the conversation adapter.

## Testing

Extend retained-source delivery and incomplete-metadata coverage to both synchronous and asynchronous context profiles. Keep Decisions HTTP, eviction, and cancellation tests exercising the conversation adapter.

GitOrigin-RevId: 3906f7d7349f73931e570ffa649377c3a235317a
2026-10-23 18:50:29 +00:00
felixxia-oai 2d86506823 Exercise retained sampling in Guardian transport tests (#56557)
## Why

The transport tests used a separate, test-only snapshot sampler instead of the production retained sampler, leaving them exercising different response ownership and cancellation paths.

## What changed

Route the transport test helper through `sample_retained` and remove snapshot execution, its active-request supersession bookkeeping, and test-only compaction compatibility fields. Simplify request-token metrics to reflect the remaining admitted-request path.

## Testing

Update tests to verify early score delivery while the retained response remains pending, WebSocket cancellation and connection reuse, and HTTP cancellation before headers or during response draining. Assert that HTTP cancellation releases classification permits.

GitOrigin-RevId: 33250103ff376af6bcd0f81ef27cdcf057f2bc5f
2026-10-23 18:48:35 +00:00
felixxia-oai 4b1cf9a4c9 Use conversations for all Guardian v2 async classification (#56556)
## What changed

- Always use the retained conversation backend for asynchronous classification; keep snapshot sampling test-only.
- Accept legacy `async_classifier_mode` values in configuration and model metadata but ignore them. Emit a startup warning when `[features.guardianv2].async_classifier_mode` is configured.
- Ignore legacy classifier mode differences when checking model-switch compatibility, and fail closed if the conversation backend is missing.

## Testing

Update coverage for legacy configuration warnings, model-switch compatibility, retained approval-review context, and conversation-based scoring.

GitOrigin-RevId: 5e8bb7e4e6e7d1589572f38bfe2498c9fa6825a0
2026-10-23 18:48:10 +00:00
ioanbudea-OAI 5deceaa927 Apply sync Guardian message limits during transcript preparation (#56555)
## What changed

Defer truncation of synchronous Guardian assistant and reasoning entries until `ContextProfile::prepare_transcript`, so the resolved profile's message limit applies before rendering and retention accounting. Keep encrypted agent messages whole when they fit, or replace them with an omission notice at the same transcript position when they exceed the limit.

## Testing

Extend coverage to verify that oversized-action reviews retain assistant commentary and final-answer evidence up to the synchronous message cap, and that encrypted-message omission produces equivalent output through synchronous transcript collection.

GitOrigin-RevId: e17fbfa7b7131559b0599ac1d57987a8d94e137c
2026-10-23 18:41:23 +00:00
viyatb-oai 15fbcac045 Enable masked AWS credentials for local proxy signing (#56554)
## What changed

- Expose `aws_sigv4` actions in version 2 MITM permissions configuration and the config schema, rejecting multiple signing actions per hook.
- Give local managed commands placeholder AWS credentials for the selected signing pair, and mask configured credentials in environment values and protected shell snapshots.
- Set `AWS_CA_BUNDLE` to the managed proxy CA bundle when unset, and require `features.credential_masking` for local AWS signing hooks.
- Validate placeholders against every configured signing pair to prevent overlap with real credentials.

## Testing

Extend configuration, signing, and TLS forwarding tests to cover action resolution, invalid signing configuration, credential masking, CA trust, snapshot protection, and exclusion of local AWS defaults from remote environments.

GitOrigin-RevId: 81dfdea30ebde74829882b38891ea41e9737058a
2026-10-23 18:40:55 +00:00
andrewgu-oai c483edf177 Include environment hooks in thread hook listings (#56553)
## Why

Listing hooks by working directory alone omits hooks supplied by a thread's selected execution environments, including hooks that can block a turn.

## What changed

- Add `threadId` to `hooks/list` to return a loaded thread's current hook inventory, including selected, ready environments. Reject requests that also specify `cwds`.
- Expose `environmentId` in hook metadata and have the TUI hooks browser query the current thread and label environment-owned hooks. Keep working-directory lookup for startup review.
- Represent environment hook source paths with `PathUri` and use `LegacyAppPathString` in hook run summaries to preserve native path conventions.

## Testing

Add coverage for listing a blocking environment hook and removing it after environment failure, delivering prompt input and reporting exit status in PowerShell and Bash, and running `PreToolUse` hooks only on the command's owning executor. Extend remote network tests to verify that environment hooks use the command's network policy while retaining their filesystem access.

GitOrigin-RevId: 97229e22793df51f4bd502c1f9e19f0c52fb2305
2026-10-23 18:39:28 +00:00
Dmitriy Kovalenko 0d7f3ea03b Initialize SQLite databases with DELETE journaling on NFS (#56552)
## What changed

Choose `DELETE` journaling for new SQLite databases on NFS and `WAL` elsewhere, using the database's own directory to detect the filesystem. Probe a separately configured logs directory independently of the state directory.

Preserve journal modes for databases with an existing schema, and apply `synchronous = EXTRA` when initialization results in `DELETE` mode.

## Testing

Extend SQLite tests to cover NFS and non-NFS initialization, interrupted initialization, lazy pool connections, separate logs directories, and preservation of existing settings under a write lock.

GitOrigin-RevId: bde35861e517881b9ce23b28b199475cee70bd76
2026-10-23 18:30:44 +00:00
Benjamin Carlsson f970f4be67 Track resume picker pagination and selection metadata per backend (#56543)
## What changed

- Add a thread catalog that tracks cursors, pending requests, and exhaustion per backend, preserves cursors on errors for retry, and rejects stale completions after a reset.
- Tag listed rows with their backend and use that backend when selecting a session.
- Store history mode on each row, preserving updates from later duplicate pages.

## Testing

Add coverage for independent source pagination, retry cursors, stale completions, and selection routing. Extend the history-mode test to verify that later metadata updates are used when resuming.

GitOrigin-RevId: ed5cf33b2df0e91394682f58ad5b353b949255ff
2026-10-23 17:52:51 +00:00
Sean Huang 7c568b331b Extract the head-tail buffer into a utility crate (#56535)
## What changed

Move `HeadTailBuffer` and `format_output_omission_marker` into the new
`codex-utils-head-tail-buffer` crate, exposing the buffer API with an explicit
const-generic byte budget. Update core callers to use the crate and add Cargo
and Bazel definitions.

Move the existing buffer tests alongside the implementation, preserving the
prefix/suffix retention and omission-marker behavior.

GitOrigin-RevId: ff488d0a0a62c39c0e11c11ebb539166cc4c6e74
2026-10-23 17:35:25 +00:00
ioanbudea-OAI 0efc474605 Defer sync Guardian tool-output truncation to transcript preparation (#56533)
## What changed

Preserve tool outputs during sync transcript collection and apply the profile's `tool_tokens` limit during transcript preparation, matching tool-call handling. Keep async and Node REPL output truncation unchanged.

GitOrigin-RevId: cf1594bcf25553c08d53b86bee1dd151e4c5db64
2026-10-23 17:28:33 +00:00
Anthony Tafoya ea819e1f4d Record skill and plugin catalog sizes on publication (#56530)
## What changed

- Add `codex.skills.catalog.entries` and `codex.plugins.catalog.entries` histograms with `cloud` or `executor` stages and `complete`, `warning`, or `partial` status. Partial results take precedence over warnings.
- Exclude cached reads and repeated observations of unchanged failed skill discovery from metric samples.
- Mark executor skill catalogs partial when discovery fails, and clear unpublished executor plugin catalogs instead of publishing an empty result.

## Testing

Extend skill integration tests to check catalog counts and statuses, fresh discovery snapshots, partial discovery, and repeated reads without duplicate samples. Update plugin state tests to distinguish unpublished catalogs from empty discovery results.

GitOrigin-RevId: e25978ba9fce54e9660853b1d9673ddab6db5061
2026-10-23 17:17:50 +00:00
Andrei Eternal adca78ddae Remove the 1 MiB response limit for explicit model catalogs (#56525)
## What changed

Fetch catalogs configured with `model_catalog_url` without a response-body size limit, allowing responses larger than 1 MiB. Remove the oversized-response rejection test and update the catalog client documentation to drop the limit requirement.

GitOrigin-RevId: acd0dbbac5d548596b50faa309496de2db3588df
2026-10-23 16:56:38 +00:00
bkotsopoulos b82d542aef Add turn, tool, and skill attribution to traces (#56524)
## What changed

- Emit `codex.turn_profile` events with finalized sampling request and retry counts when turns complete or abort, and preserve the caller's tracing span for detached extension interrupts.
- Add conversation and turn identifiers to turn and tool dispatch spans, identify tool sources, and include dispatch-to-result-ready duration on tool completion events.
- Emit `codex.skill_read.source_selected` before cache or provider access, recording the selected cloud or executor source, skill and plugin identity, resource kind, and continuation status.

## Testing

Add regression coverage for trace correlation, tool completion timing, turn profile counters on completion and interruption, detached interrupt span propagation, and skill source attribution including cached cloud reads.

GitOrigin-RevId: db78aa270bbcb8dc9e4558d202c109ad54141811
2026-10-23 16:55:32 +00:00
Eric Traut 3985001067 Respect server approval policy defaults during TUI startup (#56516)
## Why

Fresh TUI sessions sent the locally resolved approval policy in `thread/start`, overriding the app server's configured default. Local constraints could also prevent the TUI from adopting the policy returned by the server.

## What changed

- Send explicit approval policy overrides at startup and otherwise let the server resolve the policy. Preserve the resolved-config behavior for selected profiles.
- Forward granular `approval_policy` overrides with their replacement and dotted-key merge semantics.
- Forward eligible projectless approval defaults only when allowed by the server's approval policy requirements.
- Accept the server's startup policy before submitting initial or queued input, including when local constraints would reject it.

## Testing

Extend startup tests to cover explicit override precedence, granular policy merging, projectless defaults, and use of the server's approval policy on the first turn.

GitOrigin-RevId: 995ce5f21b04b058d60c2ea80a139c0cf48c0e98
2026-10-23 16:18:43 +00:00
bkotsopoulos 810501d60d Add trace instrumentation for turn startup and response streaming (#56515)
## What changed

- Record time spent waiting for each stream event in `codex.response.receive_wait_ms` on the existing `handle_responses` span.
- Add trace spans for startup prewarm consumption, turn-start lifecycle callbacks, assistant text flushing, and response stream error handling.
- Include the turn ID and lifecycle phase on the turn-start span and the request type on the error-handling span.

GitOrigin-RevId: 7792508c830ef05b03aed01eb840ca7e6577ad0b
2026-10-23 16:09:06 +00:00
bkotsopoulos bca6f238cb Preserve tracing context throughout tool dispatch (#56514)
## Why

Tool readiness waits, execution-lock waits, and result-ready events occur outside the dispatch span. Tracing should cover the full spawned dispatch task while retaining caller context when TRACE spans are disabled.

## What changed

- Instrument the entire spawned task with the dispatch span, falling back to the current span when it is disabled.
- Add child spans for readiness waits and parallel or exclusive execution-lock waits.
- Record `turn_id` and `codex.tool.phase = "dispatch"` on the dispatch span.

## Testing

Add regression tests that dispatch an unknown tool through the spawned task and verify that `codex.tool_result_ready` retains caller context at both INFO and TRACE levels, with the dispatch span present only at TRACE.

GitOrigin-RevId: 18026750af58347c38a4c2752cdd6165d73a3eab
2026-10-23 16:07:55 +00:00