Commit Graph
857 Commits
Author SHA1 Message Date
Dylan Hurd a57b398351 Require approval for input to escalated terminals (#40978)
## What changed

- Add the `write_stdin_approval` feature flag, disabled by default, to require a fresh approval before sending non-empty input to an escalated unified-exec terminal.
- Route these reviews through hooks, Guardian, app-server, and the TUI as `writeStdin` approvals while keeping the parent command item unchanged.
- Preserve the terminal environment, launch directory, and escalation state across turns, and revalidate the process identity after approval before writing input.

## Testing

- Cover approval routing, policy decisions, process reuse, terminal identity preservation, app-server events, analytics, and TUI rendering.

GitOrigin-RevId: 4ba29eaae6208e934737ba078c96e589c7c2164d
2026-08-26 21:39:05 +00:00
Francis Chalissery 7276d67081 Expose resumable misalignment details through app server (#40952)
## Why

App-server clients need the explanation and steering instruction returned with a
misalignment policy violation to offer a user-confirmed continuation. Missing or
incomplete details must continue to behave as a terminal block.

## What changed

- Parse optional misalignment classification, explanation, and steering details
  from streamed and HTTP Responses errors and propagate them through core errors.
- Include the details in live app-server `error` and `turn/completed` payloads and
  export the corresponding protocol schemas and TypeScript types.
- Keep explanations and steering messages out of serialized rollout events and
  redact them from debug output.
- Document how clients can resume with `turn/start` after user confirmation.

## Testing

- Cover streamed, HTTP, and WebSocket-wrapped errors, including malformed and
  classification-only details.
- Verify live app-server notifications expose resumable details without writing
  the explanation or steering message to the rollout.

GitOrigin-RevId: 329258a444c2cd91d0c57ab1720830b33ddcfac5
2026-08-26 18:42:44 +00:00
rka-oai 0e9a2bae52 Enable clock tools for persistent reasoning turns (#40942)
## What changed

- Default the current-time reminder and interruptible `clock.sleep` tool on for
  turns using persistent reasoning effort.
- Preserve explicit `features.current_time_reminder` settings and managed
  requirements, and gate reminder recording on the resolved feature state.

## Testing

- Cover configured, persistent, ordinary-effort, explicitly disabled, and
  managed-disabled clock setups.
- Verify review turns do not expose clock tools or current-time reminders.

GitOrigin-RevId: 4ff8805807ceeef374abd962b1d9e7c37f1fbd83
2026-08-26 18:06:12 +00:00
sayan-oai 7625bd5665 Honor environment-resolved workspace roots (#40912)
## What changed

- Add effective workspace roots to `EnvironmentConfig` and use them when
  materializing permission profiles and filesystem context.
- Preserve selection roots for thread-owned configurations while allowing a
  ready environment attachment to supply its resolved roots.
- Propagate resolved roots to child environments and validate both command and
  `apply_patch` writes in owner-provided secondary workspaces.

GitOrigin-RevId: 1832c168ce1fc37fa67efc2a472998ab4f448c70
2026-08-26 16:28:35 +00:00
jif d4998d611a Record reviewed actions with security risk scores (#40901)
## What changed

- Add optional `call_id` and `action` fields to `SecurityRiskScore` so a persisted score identifies the tool call and bounded action that produced it.
- Populate the fields after Guardian V2 classifies an action while leaving fail-closed and legacy scores without provenance.

## Testing

- Verify scores preserve action details for direct tool calls and nested code-mode calls.
- Verify rollout serialization retains the new fields.

GitOrigin-RevId: fce69af37f368cecf1d9bce42bfc38a969e969b7
2026-08-26 15:02:21 +00:00
jif 62fb56ee56 Route Guardian inference through dedicated endpoints (#40892)
## What changed

- Add the opt-in `features.guardianv2.free_guardian` setting to route eligible
  Guardian reviews to `/guardian` and asynchronous classifications to
  `/guardian-classifier`.
- Support endpoint selection for both HTTP and WebSocket Responses clients,
  including endpoint-aware connection reuse.
- Keep `/responses` for API-key authentication, custom provider URLs,
  non-Guardian models, and configurations where the option is disabled.
- Omit routing hints and `service_tier` from requests sent to the dedicated
  Guardian endpoints.

## Testing

- Cover route selection across authentication modes, provider URLs, HTTP
  fallback, WebSocket review sessions, and classifier sampling.

GitOrigin-RevId: 9c88673c710d009e0239559b9245a4e6c4f4befc
2026-08-26 14:36:48 +00:00
jif 10d5a603ae Persist Guardian V2 risk scores without restoring them (#40884)
## What changed

- Append accepted Guardian V2 classification results to rollout history for non-ephemeral threads.
- Keep resumed and forked threads from restoring a persisted score into active Guardian state.

## Testing

- Verify that asynchronous scoring records the resulting `SecurityRiskScore` rollout item.
- Seed resume and fork tests with a persisted score and verify that approvals ignore it.

GitOrigin-RevId: 40d63a2ea7e7cf6398402c6aed7d5e5727dc9d68
2026-08-26 13:54:36 +00:00
Abhinav a26f1806a4 Use issuing step settings for approval decisions (#40821)
## Why

Tool actions and approval retries can outlive the step that issued them. If approval handling reads newer turn settings, a delayed action can use the wrong approval policy or reviewer.

## What changed

- Capture the approval policy and reviewer in `GuardianReviewContext` from the issuing step.
- Use step settings for command, patch, permission, sandbox-retry, and remote-network approval decisions.
- Use the active task's published settings for background network approvals and long-lived Unix shell interception.
- Preserve explicit MCP reviewer overrides.

## Testing

Added regression coverage for permission requests, same-turn network policy changes, delayed commands after a new turn starts, sandbox retries, patch policy selection, and MCP reviewer overrides.

GitOrigin-RevId: b7e84a2e1e79a71502272b15b5ef5b0e5643f8b0
2026-08-26 06:51:58 +00:00
Abhinav 04907ab95a Use step settings for MCP request metadata (#40807)
## Why

MCP tool calls can be issued by a model step whose settings differ from the
turn's initial settings. Request metadata must describe the issuing step.

## What changed

- Build MCP tool-call metadata from the captured `StepContext` model and its
  effective reasoning effort.
- Populate `node_repl_disabled` from the issuing step while leaving turn-owned
  Responses metadata unchanged.
- Apply the same step-scoped values to MCP requests emitted by stop hooks.

## Testing

Add coverage for configured and model-default reasoning effort, model changes,
Node REPL restrictions, and preservation of the original step and turn
metadata.

GitOrigin-RevId: f9cce52fbe559f15437bd19d699b657229c0d145
2026-08-26 05:58:04 +00:00
sayan-oai e24190caa9 Use turn environment settings for sandbox execution (#40771)
## Why

Tool execution can use an environment whose sandbox configuration differs from the turn-wide configuration. Sandbox selection and process setup need to follow the environment that owns the tool request.

## What changed

- Source Windows sandbox level, legacy Landlock mode, and Windows private desktop settings from the selected turn environment across tool orchestration, unified exec, patch application, and zsh fork escalation.
- Preserve Windows sandbox level overrides in restorable thread settings and invalidate MCP configuration when that level changes.

## Testing

- Add a resume test that verifies an elevated Windows sandbox override survives thread restoration.

GitOrigin-RevId: 9d8fc46404919f5ae97c9ed712c0932a1f095e36
2026-08-26 03:28:57 +00:00
pakrym-oai 75cb7c903d Preserve MCP tool output as content items (#40737)
## What changed

- Convert unstructured MCP results into typed function-call output items instead of serializing the entire content array as a text string.
- Keep structured MCP results as serialized text and preserve media, encrypted content, and unknown content through their existing item conversions.
- Drop empty text items during output truncation so they do not consume API array slots.

## Testing

- Cover text-only, mixed unstructured, structured, and image-sanitized MCP results.
- Verify empty text items are discarded under byte- and token-based truncation policies.

GitOrigin-RevId: fa1c5b7dee6f003a094265379dcabdd060386a48
2026-08-25 23:42:50 +00:00
sayan-oai 4213b38f3c Honor attachment-owned permissions for MCP servers (#40728)
## Why

MCP servers attached to executor environments must retain their owner's
permission profile instead of inheriting the thread-wide sandbox authority.

## What changed

- Resolve and capture a permission profile for each enabled MCP server when
  publishing the runtime, and reject calls or elicitations when that authority
  is unavailable.
- Use the captured server profile for tool approval decisions, elicitation, and
  sandbox metadata, including after runtime refreshes.
- Materialize `:workspace_roots` from `PathUri` values so permissions preserve
  the path convention of remote executor environments.
- Give threadless app discovery and resource reads an explicit default
  permission profile.

## Testing

Added coverage for per-server elicitation authority, unresolved attachments,
runtime refreshes, restricted tool calls, and foreign-platform workspace roots.

GitOrigin-RevId: 6b188d4b08b29e9971ff7aa68a7785a0cdf9e394
2026-08-25 22:50:49 +00:00
vkg-oai 5ca4175295 Rename host instruction payload to Instructions (#40709)
## What changed

Rename the `UserInstructions` type to `Instructions` across the extension API,
its core API re-export, and all consumers. This keeps loading behavior and the
`LoadedUserInstructions` provider interface unchanged.

GitOrigin-RevId: 1ac236b34c31718e7aa38ff5eae5e9b179aeedd8
2026-08-25 21:20:51 +00:00
faizan-oai 94967e03e5 Add per-turn cyber access program selection (#40687)
## What changed

- Add the experimental `turn/start.cyberAccessProgram` option with `standard`,
  `daybreakBlue`, and `daybreakRed` values.
- Forward the selection as `access_programs.cyber` on Responses, WebSocket,
  and remote-compaction requests made with ChatGPT authentication, while
  omitting it for API-key and custom-provider requests.
- Preserve the per-turn selection across recovery, compaction, and child-agent
  turns without making it a persistent thread setting.

## Testing

- Cover app-server forwarding, authentication boundaries, WebSocket reuse,
  turn recovery, compaction, and child-agent inheritance.

GitOrigin-RevId: d2eb468f365b2214c5099bc21741cf30f8bd2eb5
2026-08-25 19:54:52 +00:00
pakrym-oai 538900ee76 Add turn trigger metadata (#40665)
## What changed

- Add an optional `turnTrigger` field to app-server `turn/start` requests and
  expose it in the generated protocol schemas.
- Propagate non-empty trigger values to Responses request metadata as the
  reserved `turn_trigger` field, while preserving the original value when a
  request steers an active turn.
- Classify turns started by queue dispatch, goal continuation, retry recovery,
  and realtime handoff.

## Testing

- Cover HTTP and WebSocket metadata forwarding, steering behavior, reserved
  metadata handling, and the built-in trigger classifications.

GitOrigin-RevId: c12fe2c522286db21b76081ae6154fbf6bfb3639
2026-08-25 18:11:04 +00:00
iceweasel-oai ba9567daf3 Propagate temporary directories into sandbox policy contexts (#40660)
## Why

Filesystem policies containing `:tmpdir` need executor-local directory bindings,
including when execution occurs in a remote environment.

## What changed

- Cache temporary directories reported by remote executors and discover the
  equivalent directories for local environments.
- Preserve the cached directories across inherited environment selection and
  include them in `FileSystemSandboxContext`.
- Add `FileSystemSandboxPolicyContext` and a context accessor so filesystem
  policy entries can be resolved with the executor-owned current directory,
  workspace roots, and temporary directories.

## Testing

Extend environment-selection tests to cover local, remote, and inherited
temporary-directory policy context.

GitOrigin-RevId: 36335af3465c529f024bf69293af288803dd582d
2026-08-25 18:04:01 +00:00
joeflorencio-openai a10c8127f7 Add live turn settings updates (#40653)
## What changed

- Add a feature-gated `TurnSettings` operation that can update the model,
  reasoning effort, reasoning summary, and service tier for subsequent steps of
  a named running turn without changing future thread settings.
- Report whether an update was applied, rejected, or lost its live target.
- Revalidate managed constraints and preserve the turn's admitted approval and
  Guardian safety properties before publishing an updated settings snapshot.

## Testing

- Cover sparse updates, step capture and ordering, target replacement, managed
  policy changes, model metadata safety, and separation from future settings.

GitOrigin-RevId: ecaaaa95b4fd4ec9d62265bef551582dddb36d78
2026-08-25 17:44:50 +00:00
joeflorencio-openai 68301fa45f Snapshot resolved settings for each model step (#40651)
## Why

Thread settings can change while a turn is running, and delegated review or
compaction steps can select a different model. Each request needs a consistent
set of settings resolved against the model that will execute it.

## What changed

- Capture immutable resolved settings for each model step, including model
  metadata, reasoning options, service tier, approvals, and personality.
- Keep in-flight steps on their captured settings while applying thread updates
  to subsequent work.
- Resolve inherited reasoning summaries and filter service tiers against the
  selected model and feature configuration for review and compaction steps.

## Testing

Added coverage for settings updates during paused turns, model changes,
previous-model compaction, review-model defaults, and service-tier filtering.

GitOrigin-RevId: fca4b3b305379f1bf26a5cac75ee0dd1747ac1f6
2026-08-25 17:41:22 +00:00
joeflorencio-openai ba6cf9c692 Make automatic turn admission atomic with settings updates (#40648)
## Why

Turn settings can change after an input request previews its overrides. Automatic idle work could therefore make a Plan-mode admission decision from stale settings or apply a sparse override built from an outdated collaboration mode.

## What changed

- Evaluate automatic turn admission against both the current and proposed configuration under the settings publication lock.
- Reject automatic work that would enter or leave Plan mode without committing settings or triggering runtime configuration effects.
- Keep model and reasoning-effort overrides sparse until they are merged with the configuration being committed.
- Continue allowing explicit user and recovery turns to make valid mode transitions.

## Testing

Add coverage for concurrent settings changes, sparse model and effort updates, commit-time constraint validation, atomic Plan-mode rejection, and subsequent explicit user submission.

GitOrigin-RevId: 234f06de116bdce7c3a3fb5cac3d15583304a253
2026-08-25 17:30:45 +00:00
joeflorencio-openai 1d64085e67 Validate step settings against proposed permissions (#40647)
## Why

Model requirements must be evaluated against the permissions that will apply
after a settings update. Validating against the current profile can reject a
valid model-and-permission update or allow a later permission-only update to
invalidate the selected model.

## What changed

- Group model, reasoning, service-tier, personality, and approval inputs into
  `StepSettings`, with a single apply-and-validate path.
- Apply permission and environment changes before validating step settings, so
  auto-review requirements use the proposed effective permissions.
- Revalidate existing step settings when permission or environment changes alter
  their constraints, and commit the update only when the complete candidate is
  valid.

## Testing

Added unit and integration coverage for atomic model/permission updates,
permission-only revalidation, environment-derived constraints, and both
standalone and turn-start settings operations.

GitOrigin-RevId: f50dfbd300484a09acc51ee4607278f300ca1cd9
2026-08-25 17:27:04 +00:00
joeflorencio-openai 4e883ce36e Keep settings operations bound to their committed snapshot (#40645)
## Why

Post-commit work can overlap with another settings write. Reading the session
again afterward could make a settings operation report or use the later state
instead of the state that it committed.

## What changed

- Return the committed configuration and `ThreadSettingsSnapshot` from session
  settings updates.
- Use that commit result when creating a turn and emitting
  `ThreadSettingsApplied`, while retaining current-state snapshots for
  synthesized fork history.
- Route turn-start updates through the shared settings update path.

## Testing

Add coverage for standalone and turn-start updates that pause after committing,
restore different settings concurrently, and verify that each operation keeps
its original configuration and notification snapshot.

GitOrigin-RevId: cee5be9536d2840170893e6eb0c64cd039fb0a96
2026-08-25 17:20:37 +00:00
Alex Zamoshchin 304c8de4c6 Allow extensions to skip host skill discovery (#40631)
## What changed

- Add the under-development `skip_host_skill_discovery` feature to bypass host
  skill snapshots during session warmup and turn setup.
- Let skill invocation contributors declare whether they require host-owned
  skills. Preserve host discovery when no contributors are registered or any
  contributor requires it.
- Keep executor and orchestrator skill catalogs and instruction loading
  available when host discovery is skipped.

## Testing

- Cover executor-only, orchestrator, mixed-contributor, and legacy host-skill
  behavior.

GitOrigin-RevId: 48169403090b234e1a304c6523633fd867df454a
2026-08-25 16:00:02 +00:00
chess ed42068c45 Add a turn-scoped service tier override (#40616)
## What changed

- Add `serviceTierForTurn` to `turn/start` so a newly started turn can override the service tier without changing the thread's saved tier.
- Treat `"default"` as standard speed and omitted or `null` values as inheriting the thread tier.
- Keep `serviceTier` authoritative for subsequent turns when both fields are supplied, and ignore the turn-scoped override when steering an active turn.

## Testing

- Extend the app-server turn-start test to verify both the one-turn `"default"` override and inheritance on the following turn.

GitOrigin-RevId: 4c2c4db21d8d31617a7a6e6df65bf54834e72383
2026-08-25 14:04:32 +00:00
jif 7c6eb0eef1 Scope stop hooks for memory consolidation (#40587)
## Why

Background memory consolidation must honor managed completion policies without
running project completion checks or sending user-facing notifications.

## What changed

- Add a memory-consolidation stop target that selects managed policy hooks and
  executor-scoped cleanup while excluding user, project, session, and plugin
  stop hooks.
- End memory consolidation with an error when a managed stop hook rejects it,
  and propagate that turn error into agent status.
- Disable legacy completion notifications for the background memory worker.

## Testing

- Cover hook selection, executor cleanup, managed rejection, agent error
  status, and notification suppression.

GitOrigin-RevId: be350679ddcde2dde8a408b0972f08facff01a37
2026-08-25 10:29:26 +00:00
Adam Perry @ OpenAI 8444cf63b5 Derive sandbox contexts from turn environments (#40551)
## What changed

- Add Windows sandbox mode, private-desktop behavior, and legacy Landlock selection to each `EnvironmentConfig`.
- Centralize sandbox context construction on `TurnEnvironment`, preserving environment-owned permissions, paths, and backend settings while applying additional permission grants.
- Use the environment-derived context for project instructions, capability discovery, file uploads, and filesystem-oriented tools.

## Testing

- Verify capability discovery uses the selected environment's permission profile and sandbox backends when they differ from the thread defaults.

GitOrigin-RevId: 7ae2fed90c8ada950f2e8431e571e9b2c793c291
2026-08-25 05:16:45 +00:00
pmccrary-oai 3a469a297d Route extension hints into context-window metadata (#40533)
## What changed

- Add a `ContextWindow` prompt slot for thread-scoped extension contributions.
- Include fragments in that slot in the token-budget context-window message.
- Keep the MCP `notes/thread_hint` bridge when the native history-notes extension is disabled, without falling back to it after a native request failure.

GitOrigin-RevId: befcb7cc8570b846094b2b542a112b186b39a30a
2026-08-25 03:38:24 +00:00
Dylan Hurd 9c9675d3d0 Represent terminal input in approval reviews (#40528)
## What changed

- Add a `writeStdin` Guardian action carrying the approval, process, input, and working-directory details.
- Distinguish `command` and `writeStdin` execution approval requests while defaulting missing kinds to `command` for compatibility with older events.
- Render terminal-input review progress, denials, timeouts, and retry actions in the TUI, and record the action separately in analytics.
- Keep terminal-input reviews as child approvals so they do not change the parent command item's lifecycle or reconstructed history.

## Testing

- Cover Guardian serialization, app-server protocol conversion, command history reconstruction, analytics classification, and TUI review flows for terminal input.

GitOrigin-RevId: b083d5e2963bdd23b928644ec03c7eb68ebf2950
2026-08-25 03:08:33 +00:00
guinness-oai 41ca88e95c Persist realtime events in the thread timeline (#40508)
## Why

Clients need a bounded view of realtime conversations that preserves the order of speech, agent work, and turn lifecycle events without loading the full thread history.

## What changed

- Persist realtime session boundaries, transcript segments, and promoted agent items in paginated thread rollouts.
- Add the experimental `thread/timeline/list` API to page ordinary items, realtime items, and turn boundaries in canonical rollout order. Include `activeRealtimeSessionAtPageStart` so each page can be rendered independently.
- Emit typed `thread/realtime/item/started`, `thread/realtime/item/transcript/delta`, and `thread/realtime/item/completed` notifications around durable realtime items.
- Keep the existing `thread/items/list` response and legacy thread history behavior unchanged.

## Testing

- Cover mixed timeline pagination, realtime-session state at page boundaries, rollout replay, subagent history prefixes, transcript streaming, steering, and promoted agent artifacts.

GitOrigin-RevId: faa2c420192d63e060e8fb32446e3c797422656e
2026-08-25 01:03:20 +00:00
Won Park 8476434a97 Harden internal Guardian session isolation (#40497)
## Why

Internal Guardian reviews must remain independent of parent-session customization while still honoring managed execution and environment restrictions.

## What changed

- Apply the restricted Guardian session path to both internal and subagent review sources.
- Start internal reviews without inherited user instructions, extensions, MCP servers, or multi-agent behavior.
- Preserve managed execution policy and selected environment constraints while exposing only the allowed review tools. Honor shell feature restrictions across every selected environment and retain code mode when enabled.

## Testing

- Cover internal review isolation from parent state and managed instructions.
- Cover optional tool filtering, managed shell restrictions, code mode, and secondary environment profiles.

GitOrigin-RevId: edbf7d8a6fe3ee8213a1c75bc8ec331a1cf49006
2026-08-24 23:23:18 +00:00
hefuc-oai 1e9e916923 Honor disabled managed network configuration (#40489)
## Why

Managed network requirements can remain present when `enabled = false`, but a
disabled configuration should not create or expose an active proxy runtime.

## What changed

- Start the managed network proxy only when its effective specification is
  enabled.
- Clear an existing proxy when a permission-profile refresh disables managed
  networking.
- Keep remote executor launches free of managed-network proxy settings when the
  requirements explicitly disable the feature.

## Testing

Added session and unified-exec coverage for initial startup and refresh with
disabled managed networking.

GitOrigin-RevId: f76699802e079eb746d5b1ea6547d19a4bfb7715
2026-08-24 22:51:36 +00:00
Eddie Chen 49880081fe Add root turn IDs to turn and tool analytics (#40486)
## Why

Analytics need to associate subagent activity with the top-level turn that
caused it, while avoiding a stale association when steering makes that origin
ambiguous.

## What changed

- Add `root_turn_id` to turn and tool-item analytics events.
- Read the root from live turn metadata when each event is built, reporting
  `null` when the root is unknown or ambiguous.
- Propagate the metadata through control-tool and code-mode completion facts so
  correlated and background tool events retain the correct root.

## Testing

- Cover root IDs for top-level turns, subagent turns, correlated code-mode
  calls, and tool events emitted after turn completion.
- Verify that queued and subsequent events report `null` after the live root is
  invalidated.

GitOrigin-RevId: 42fd76541c3c716cec74787d47b50adb2d22e6d2
2026-08-24 22:30:59 +00:00
pakrym-oai 4aa52f2cb2 Gate content item kinds behind a feature flag (#40450)
## What changed

- Add the under-development `content_item_kinds` feature, disabled by default.
- Strip content item classifications from Responses input when the feature is
  disabled while preserving other passthrough metadata.

## Testing

- Add coverage that disables the feature and verifies requests omit content item
  kinds without removing the turn ID.

GitOrigin-RevId: f938feb2895d766d979b1666fc7b97fd128fe8a7
2026-08-24 18:22:13 +00:00
jif 2126f93617 Route peer agent completion activity to the initiating turn (#40449)
## What changed

- Record the initiating agent path when inter-agent communication triggers a turn.
- Emit completed subagent activity to that agent's turn instead of always using the completed agent's parent thread.
- Keep parent-directed completion messages unchanged.

## Testing

Added a multi-agent v2 regression test where one sibling requests follow-up work from another and receives the resulting completion activity on the requesting turn.

GitOrigin-RevId: 949dd1116cccdd461c66a9b213a5bcd554cb3720
2026-08-24 18:15:04 +00:00
jif b705b6b076 Report completed sub-agent activity on parent turns (#40437)
## Why

A Multi-Agent V2 child can finish after the parent turn that spawned it, so its
successful completion needs to remain associated with that parent turn in
notifications and history.

## What changed

- Add `completed` to `SubAgentActivityKind` and emit the corresponding started
  and completed item events on the spawning parent turn when a child succeeds.
- Persist completed activity as a canonical turn item in both legacy and
  paginated history, and expose it through app-server history and schemas.
- Render completed activity as terminal in the TUI without counting it as a
  separate tool call or tool-runtime event.

## Testing

- Cover successful completion in legacy and paginated history, late updates to
  completed parent turns, TUI rendering, analytics, and rollout tracing.
- Verify that terminal child errors do not emit completed activity.

GitOrigin-RevId: 6c71eb8b10e7327611c6af84f70e294e27d94d02
2026-08-24 17:07:21 +00:00
pakrym-oai 60821c5043 Represent Guardian policy as a contextual fragment (#40420)
## What changed

- Add a `GuardianPolicy` contextual fragment that renders as a standalone
  developer message with the `guardian.policy` content kind.
- Use the fragment when rebuilding Guardian context and verify that its content
  kind remains attached after history compaction.

GitOrigin-RevId: f7028fb29a48ad2453437f3d3a4405fcab7a2fd7
2026-08-24 15:42:16 +00:00
jif 339751715c Use snapshot session sources for MCP projection (#40368)
## What changed

Pass the session source associated with each MCP configuration snapshot into
selected-environment server projection. This keeps Guardian reviewer isolation
decisions aligned with the snapshot being projected instead of rereading the
session's mutable configuration.

GitOrigin-RevId: 61fd891fec13f62cfea9886d13e2f94f6f60922f
2026-08-24 09:14:32 +00:00
pakrym-oai a70974c1a0 Preserve developer instruction annotations in subagent forks (#40297)
## What changed

- Add a dedicated contextual fragment for developer instructions that emits the
  `generic.developer_instructions` content kind.
- Use the fragment when adding child-specific developer instructions to a
  full-history subagent fork, preserving their classification and ensuring they
  reach the child exactly once without appearing in the parent request.

## Testing

- Extend full-history subagent coverage to verify the child-only instructions'
  annotation, placement, and count.

GitOrigin-RevId: 82589d311535225fed76d500a19458fda72f40f2
2026-08-23 23:56:23 +00:00
pakrym-oai 479c8c8924 Preserve content kinds during image preparation (#40281)
## Why

Image preparation can rewrite message content, including replacing images that
cannot be processed with model-visible error text. The positional content-kind
metadata must stay aligned with those rewrites.

## What changed

- Process message images together with their content-kind annotations.
- Preserve existing kinds for unchanged and resized content.
- Classify failed-image placeholders as `images.preparation_error`.

## Testing

- Cover metadata preservation across successful, resized, and failed images.
- Verify Responses Lite sends `user.image` and `images.preparation_error` kinds.

GitOrigin-RevId: 1be7bcbe47014251019bfff0d826c9dfe3239dec
2026-08-23 22:23:40 +00:00
ashwinnathan-openai 6677fd827d Budget retained images during remote compaction (#40280)
## Why

Remote compaction's retained-message budget counted text but not images, so
image-heavy history could retain more context than the budget represented.

## What changed

- Add the opt-in `compaction_image_budget` feature to charge retained images
  using the existing image size estimate.
- Keep images and their adjacent labels atomic when truncating a boundary
  message, while preserving existing text, audio, metadata, and
  client-authored developer-message behavior.
- Stop backfilling older messages when an image at the truncation boundary
  does not fit.

## Testing

- Add unit coverage for image boundaries, annotations, audio, text-only
  messages, and client-authored developer messages.
- Add an integration test covering repeated remote compaction with the feature
  enabled, disabled, and left at its default.

GitOrigin-RevId: 88868bbd09d2858939dbae3f8402e1f497b4e3c6
2026-08-23 21:29:11 +00:00
pakrym-oai aec653daa9 Preserve annotations when omitting unsupported media (#40277)
## What changed

- Render omitted image and audio inputs as contextual fragments tagged with
  `images.unsupported` and `audio.unsupported` content kinds.
- Normalize message media through annotated content so metadata for surrounding
  content remains intact when switching to a model without media support.

## Testing

- Extend history and model-switching tests to verify content-kind annotations
  before and after unsupported media is replaced.

GitOrigin-RevId: 4ee6577f8b78bd5a850ee01ea9d4590c20272850
2026-08-23 20:14:26 +00:00
pakrym-oai 287587c32c Classify additional generated context fragments (#40275)
## What changed

- Represent compaction summaries and Guardian-approved actions as typed contextual fragments.
- Inject subagent notifications through the same fragment path.
- Annotate the resulting request items with `compaction.summary`, `guardian.approved_action`, and `multi_agent.subagent_notification` content kinds while preserving their existing roles and text.

## Testing

- Verify the content-kind metadata on compacted summaries, approved actions, and subagent notifications.

GitOrigin-RevId: 01c93e7f08b2dc1c1e85ba69e82bfb5f56e6cca5
2026-08-23 20:08:40 +00:00
Dylan Hurd c9b19deb09 Distinguish Guardian review threads from subagents (#40221)
## Why

Guardian reviews were reported with the generic `subagent` thread source, making them indistinguishable from other delegated threads in persisted metadata and analytics.

## What changed

- Add the `guardian_review` thread source to the core protocol and app-server schema.
- Assign it to Guardian reviewer sessions and propagate the configured source through turn metadata, rollouts, and analytics.
- Continue treating Guardian reviews like subagents for paginated history and trusted-provenance checks.

## Testing

- Cover protocol round trips, delegate source selection, emitted analytics, request metadata, and persisted rollout metadata.

GitOrigin-RevId: 07480c122715812874c9d3b48bb39fc5c86b2367
2026-08-23 10:06:57 +00:00
pakrym-oai 4582c0a498 Annotate user input and contextual fragments with content kinds (#40196)
## What changed

- Preserve each contextual fragment's `ContentItemKind` when converting it to a response message.
- Classify user text, image, and audio content as `user.text`, `user.image`, and `user.audio` in their original order.
- Give additional context key-specific `additional_content.<key>` kinds and retain annotations on generated messages such as image resize notices and interrupted-turn markers.

## Testing

- Expand request-level coverage to verify content-kind annotations across mixed-modality turns, additional context, reminders, budgets, skills, model switching, subagents, and image resizing.

GitOrigin-RevId: 671e4545f39b335525c60d2a5df4608e8068cafc
2026-08-23 06:10:44 +00:00
pakrym-oai c4b434aae2 Preserve context annotations in merged messages (#40184)
## What changed

- Carry each contextual fragment's `ContentItemKind` through initial context assembly and world-state updates.
- Attach the classifications to merged response messages through `content_item_kinds`, preserving their order alongside the message content.
- Convert extension prompt fragments into annotated developer fragments and classify built-in developer and guardian instructions.

## Testing

- Add an integration test covering roles and content annotations in the first request.
- Update world-state and persisted-history tests to account for annotation metadata.

GitOrigin-RevId: 71c48dad5b17bffd47ba03263e3eb6d5e74fbf4b
2026-08-23 04:41:11 +00:00
pakrym-oai 546eed94ac Require content kinds for extension prompt fragments (#40177)
## What changed

- Require each `PromptFragment` to include a producer-owned `ContentItemKind`.
- Re-export `ContentItemKind` from `codex_extension_api` and assign stable kinds to skills, memories, examples, and test contributors.
- Limit prompt slots to developer policy and developer capabilities, and combine contributed fragments into a single developer update.

## Testing

- Update extension registry tests to verify fragment ordering with the new content-kind metadata.

GitOrigin-RevId: ef8624a9b4ae9dce025bca9c0954d91dd8075e85
2026-08-23 03:12:58 +00:00
richardopenai 4f39251a01 Add unfinished root turn suspension (#40038)
## Why

An active root turn needs to be stopped without marking it complete or aborted
before another runtime can recover the same turn ID.

## What changed

- Add `CodexThread::suspend_turn_and_shutdown` and `SuspendTurnOutcome`.
- Flush history, stop the active regular task, close the history writer, and
  shut down the session without recording a terminal turn event.
- Reject suspension when no supported turn is active or the loaded agent
  subtree still contains a live descendant.

## Testing

- Verify that suspension preserves unfinished history and allows the turn to be
  recovered under its original ID after the descendant guard is cleared.

GitOrigin-RevId: 1f9b019d07c51474ec2d991d263bc15cdd4f89ad
2026-08-22 00:42:19 +00:00
Ankush Gupta 970b7f2ff4 Preserve strict MCP auto-review outcomes (#40031)
## What changed

Propagate canonical denial, timeout, and abort responses from strict MCP
auto-review instead of replacing them with a generic decline. This preserves
the reviewer's action and metadata, including denial rationale, while still
failing closed when no canonical decision is available.

Update the fallback message to direct the agent to request explicit user
approval before proceeding.

## Testing

Add unit and app-server integration coverage for strict auto-review denials
and cancellations.

GitOrigin-RevId: d8126ab223ab546b95e2d984f6e4dd540a324a59
2026-08-21 23:14:28 +00:00
Won Park 6143217c67 Cancel Guardian reviews with their tool calls (#40021)
## What changed

Propagate tool cancellation tokens into Guardian approval reviews so interrupting a tool also aborts its pending review. Apply the same cancellation behavior to server-initiated MCP approval elicitation.

## Testing

Add integration coverage for cancellation from direct tool calls, code-mode turns, background code-mode cells, and MCP elicitation.

GitOrigin-RevId: cbee4b422bbcbf6984e415ef6409cee705beebdc
2026-08-21 21:51:12 +00:00
malsamiri-oai be6ebb1f6d Trace turn context creation and realtime state checks (#40017)
## What changed

- Add trace-level `turn_context.make` instrumentation around turn context
  construction.
- Add a trace-level `realtime_conversation.running_state` span around realtime
  conversation state checks.
- Skip recording function arguments in both spans.

GitOrigin-RevId: f0b905e75eb487432f56a2efdd65972f5322555d
2026-08-21 21:34:53 +00:00
Krish Chainani ab8768306f Preserve executor context for MCP stop hooks (#40012)
## What changed

- Scope executor-provided stop-hook calls to the MCP server environment that registered the hook, and reject calls when that environment does not match.
- Forward turn metadata with executor stop-hook requests while retaining the hook call's `threadId` metadata.

## Testing

- Cover environment matching for MCP tool calls and verify executor stop hooks receive their environment ID and request metadata.

GitOrigin-RevId: b544ea3a6ca1f61389fb4597978ed7aac27d529a
2026-08-21 21:17:42 +00:00