Commit Graph
363 Commits
Author SHA1 Message Date
felixxia-oai 29aa1df62e Retain assistant context for Guardian authorization reviews (#47582)
## Why

Ordinary user replies can depend on preceding assistant messages. Losing those messages during compaction can leave Guardian without the context needed to interpret a reply's scope.

## What changed

- Retain original assistant messages, including commentary, with their recorded order across checkpoints and resume. Exclude compaction output from this evidence.
- Include assistant context in local and delegated reviews as untrusted context, with separate storage limits and lower budget priority than user instructions.
- Prefer assistant context preceding ordinary replies when selecting bounded root evidence, and report unavailable context without inferring what a reply refers to.
- Preserve inherited context scope and remove assistant evidence beyond rollback boundaries, including during rollout migration.

## Testing

Extend coverage for compaction and resume, checkpoint migration, queued-input ordering and rollback, role labeling, and evidence budgets that preserve user restrictions while dropping assistant context.

GitOrigin-RevId: 886189b0be29ffc3d324b56f5d0b673d6b8d84da
2026-09-23 16:15:55 +00:00
jif 0b23f365f8 Route agent lookups and V2 context through AgentControl (#47536)
## Why

V2 tools and model context need to use the controller's agent tree even when the session's local runtime has no registry entries.

## What changed

- Add target resolution and direct-child path lookup to `AgentControl`.
- Move lazy root registration into the controller's resolution and listing methods.
- Build V2 subagent context from controller-provided paths, keeping formatting and size limits in the session layer and preserving loaded-first ordering.

## Testing

Extend the V2 spawn and messaging test with an empty session-local registry to cover relative-path resolution, message delivery, and subagent environment context through the controller.

GitOrigin-RevId: c935b34a6d3314e968ba451ff981cf2a223bbfa8
2026-09-23 11:07:41 +00:00
jif 27969c0ae9 Route session agent operations through AgentControl (#47520)
## What changed

- Store `Arc<dyn AgentControl>` in session services and route agent tools, turn admission, usage accounting, completion notifications, and shared settings through the trait.
- Add `AgentControlInit` so delegated and guardian sessions inherit the parent's controller and local runtime.
- Move local registry and context helpers to `LocalAgentRuntime`, keep resume, close, inspection, and status subscriptions on the local controller, and simplify synchronous and infallible trait methods.

GitOrigin-RevId: ad3f213eb483ac524bde56d769f20a78f20989a0
2026-09-23 09:39:30 +00:00
vkg-oai 78fdcd2311 Overlap agent metadata reads when resuming a V2 root (#47369)
## Why

Restoring persisted V2 agent identities reads descendant metadata serially, making each storage read wait for the previous one.

## What changed

Read up to eight descendants concurrently while registering identities in graph order, preserving path and nickname reservation order. Skip identities already registered and continue restoring after individual read failures.

## Testing

Add a cold-resume regression test that gates child metadata reads to verify overlap, completes reads out of order to check deterministic path reservation, and injects a read failure. It also verifies that child runtimes remain unloaded until requested.

GitOrigin-RevId: ae90f24875966be83208884937621a6a9eb0d848
2026-09-22 21:42:11 +00:00
Owen Lin 5121aeff13 Overlap subagent spawn persistence and clean up cancelled children (#47348)
## Why

Forked subagent startup serializes history persistence and spawn-edge writes. Cancellation during startup can also leave a provisional child behind.

## What changed

- Defer copied-history durability so it can run alongside spawn-edge persistence, while still awaiting both before submitting the child's initial input.
- Commit agent and residency reservations and notify clients only after initial input is accepted.
- Guard provisional children so cancellation or startup failure removes and shuts them down, discards their stored state, and closes their spawn edge after any pending edge write finishes.

## Testing

Add coverage for cancellation at the child-history durability barrier, checking child termination, removal, and edge closure. Extend fork-context tests in legacy and paginated history modes to verify inherited context can be read from storage after spawn acknowledgment without flushing the live child first.

GitOrigin-RevId: e02dda57efc32b7237bb7af0ce5e5844922890c3
2026-09-22 19:39:18 +00:00
Owen Lin 286d4ecf44 Persist resume metadata in compaction checkpoints (#47323)
## Why

Compaction companion records do not represent all resume state, including the last started turn and previous turn settings. The selected multi-agent runtime also needs a persisted value when no companion turn context is present.

## What changed

- Add optional `resume_metadata` to `CompactedItem`, recording the multi-agent version, last started turn ID, and previous turn settings. Preserve the distinction between absent metadata and explicitly empty values while retaining compatibility with older records.
- Capture this metadata under the settings persistence lock alongside the compaction checkpoint.
- Rewrite inherited metadata to use the child agent's runtime, and clear previous turn settings when the child must rebuild context.
- Clear pending continuation state before delivering acceptance of standalone settings updates, while holding the persistence lock.

## Testing

Add coverage for metadata round trips with empty values, legacy reader compatibility, checkpoint companion records, inherited fork metadata, and continuation invalidation while settings event delivery is blocked.

GitOrigin-RevId: f30b7feaa7e2fdb5b65fc3c53b37fd7a7fe27903
2026-09-22 16:35:30 +00:00
jif 5c07856e25 Separate local agent runtime state from controller handles (#47301)
## What changed

Extract `LocalAgentRuntime` from `LocalAgentControl` to hold the shared registry, residency state, execution limiter, rollout budget, service tier, instruction provider, and thread-manager bindings. Keep session identity on the controller handle.

Store the runtime in `SessionServices` and use it to bind controllers for child startup, resume, delegation, and guardian reviews. Route ownership checks and residency handling through the shared runtime, preserving registry identity across handles. Update existing test fixtures to keep the controller and runtime paired.

GitOrigin-RevId: 846094657cbdf736da3149f0a1c96b4e01423dfe
2026-09-22 14:48:28 +00:00
jif c6c09fe29f Consolidate agent operations in the AgentControl implementation (#47292)
## What changed

Move `spawn`, `send`, and `inspect` into the `AgentControl` implementation for `LocalAgentControl`, removing the forwarding methods and the `spawn_request` module. Update tool handlers and existing tests to use the trait methods, and remove redundant boxing at spawn call sites.

Preserve spawn validation, message attribution, runtime loading, and queue-only delivery semantics.

GitOrigin-RevId: 6027d4d97d0dfb6763dc97ef92a2d7ef58de945d
2026-09-22 13:47:56 +00:00
jif 16bb1b9d7e Implement AgentControl for LocalAgentControl (#47271)
## What changed

Add an adapter that delegates the shared controller interface to existing local agent operations, including lifecycle management, message delivery, status observation, budget accounting, and shared settings.

Align the trait signatures and documentation with local behavior: separate advisory capacity checks from execution tracking, preserve best-effort completion reporting, and return optional guardian evidence. Use `SessionId` for controller identity and replace paginated queries with loaded-agent listing by path prefix, removing the obsolete types and exports.

GitOrigin-RevId: 15bb7135e0f180d207390f6f2e75f63b9058816a
2026-09-22 12:19:05 +00:00
jif ac7634b9f7 Stream agent snapshots from local status subscriptions (#47267)
## What changed

- Return `StatusSubscription` streams of `AgentInfo` snapshots from local status subscriptions, including agent metadata and configuration.
- Emit the initial snapshot before subsequent coalesced updates. Use a weak thread reference and retain the last observed configuration so published final updates remain available after the runtime is dropped.
- Update completion notifications and `wait_agent` to consume snapshot streams, propagate subscription errors from `wait_agent`, and fall back to the latest status when a stream ends.

## Testing

Update the shutdown subscription test to verify that shutdown before the first poll preserves the initial `PendingInit` snapshot followed by `Shutdown`.

GitOrigin-RevId: beb46952cbcc9bddf65a4d6603fea939d5ace8b9
2026-09-22 11:44:00 +00:00
jif fdd89e78ac Return agent snapshots from close_agent (#47252)
## What changed

Return an `AgentInfo` snapshot captured before shutdown, including metadata for known unloaded agents. Use the snapshot's status and metadata in the tool's completion event and its status in `previous_status`, replacing the separate status subscription.

Preserve the pre-close status for error reporting when shutdown removes the target before a descendant fails to close. Propagate unexpected thread lookup errors before attempting shutdown.

GitOrigin-RevId: bdbd877aaf0389e830d6a7e84a5e14bb7d47277a
2026-09-22 10:58:32 +00:00
jif c46aa58a7b Centralize agent resume handling in LocalAgentControl (#47244)
## What changed

Add `LocalAgentControl::resume_agent` to reuse an existing thread or restore it from its rollout when lookup returns `ThreadNotFound`. Return the agent's current status, metadata, and configuration snapshot.

Route the `resume_agent` tool through this method, replacing its status-based resume check and separate restoration helper.

GitOrigin-RevId: 2ae0572a030f169eca1760ba0aff1fb9e2ab6651
2026-09-22 10:27:19 +00:00
jif acc20df49f Prevent V2 agent eviction from racing with queued messages (#47240)
## Why

Accepted inter-agent messages can still be waiting in the submission queue when a worker appears idle. Evicting that worker can lose the queued work, while cancelling an eviction caller can leave shutdown unfinished and allow delivery to a closing runtime.

## What changed

- Pin V2 recipients until queued submissions are handled or dropped, and verify that delivery targets the registered runtime.
- Move `Submission` into core so it can carry the residency guard through queue handoffs.
- Give eviction exclusive access to each runtime and keep it counted against capacity until removal. Run teardown in a separate task so it completes even if its caller is cancelled, and remove registry and residency entries together.

## Testing

Add a regression test covering queued follow-up delivery, eviction refusal while mail is pending, cancelled eviction completing teardown, rejection of late delivery, and capacity reuse after removal.

GitOrigin-RevId: d6de3d68cb6b911942e9ddfc05c65b3741b796b2
2026-09-22 09:50:48 +00:00
jif f908e5a968 Route multi-agent spawning through SpawnRequest (#47235)
## What changed

- Route both multi-agent spawn handlers through `LocalAgentControl::spawn`, accepting user input or an agent message.
- Centralize spawn message attribution and canonical path validation, and require message input to use `TriggerTurn`.
- Return the child's configuration snapshot alongside `LiveAgent`, so handlers obtain effective settings directly from spawning without a separate lookup.
- Update child test fixtures to use the shared spawn entry point.

GitOrigin-RevId: 9f9278df08041a62215f9ec3d38688c78fc5e0e2
2026-09-22 09:32:22 +00:00
peilin-openai ac98537678 Track cumulative MCP attribution across requests and thread history (#47081)
## What changed

- Record each MCP source and its first turn, including connector and plugin identifiers when available. Cover direct and Code Mode calls, including returned errors and results that are not printed.
- Persist cumulative attribution checkpoints and restore them across compaction, resume, and forks, including forks limited to recent turns.
- Attach fresh attribution to Responses API `client_metadata` under `mcp_attribution`, outside model-visible content. Restrict transmission to allowed OpenAI HTTPS destinations for both HTTP and WebSocket requests.
- Report `attribution_error` for legacy history without checkpoints, malformed or conflicting attribution, and serialized attribution exceeding 16 KiB.

## Testing

Add coverage for source deduplication, checkpoint persistence and restoration, recent-turn forks, direct and Code Mode calls, destination filtering, and the serialized size limit.

GitOrigin-RevId: fd285e152ca9e24bfa000debb20013709d67a86e
2026-09-21 18:19:07 +00:00
felixxia-oai f585f13a12 Preserve ordered assistant context in Guardian reviews (#47030)
## Why

Guardian's retained root context appended assistant messages after user evidence and omitted questions sent through User Messaging. This could leave subagent authorization reviews with missing or misplaced conversational context.

## What changed

- Record assistant messages and function calls in the same order sequence as accepted user inputs, then merge retained review context by recorded position while prioritizing user evidence within the message budget.
- Capture bounded User Messaging text after input hooks when a send succeeds, and match it to the original call for assistant context.
- Label assistant context without a recorded position explicitly and clear parent assistant and tool positions when forking agent history.
- Clarify that recorded order does not establish delivery order or pair ordinary replies with questions; assistant messages remain untrusted context.

## Testing

Add coverage for hook-rewritten messages, failed or unconfirmed sends, queued replies with delayed tool results, ordering across resume, and removal of inherited assistant positions from forked history.

GitOrigin-RevId: ac717cf0f5efe4b05c18f2d8370dd48453ac4e35
2026-09-21 13:30:55 +00:00
jif 7d99ee82d7 Add agent inspection without restoring unloaded runtimes (#47010)
## Why

Agent inspection needs to distinguish registered but unloaded agents from missing identities and backend failures without restoring a runtime.

## What changed

- Add inspection returning `AgentInfo` with metadata, status, and configuration for loaded agents, or metadata for unloaded agents.
- Use inspection for configuration snapshots and to capture an agent's state before interruption.
- Add `AgentInfo` accessors and share V2 error mapping between interruption and messaging tools, preserving the distinction between invalid requests and a dropped thread manager.

## Testing

Extend the V2 reload test helper to assert that inspecting a registered, unloaded agent returns `AgentInfo::Unloaded` and leaves its runtime unloaded.

GitOrigin-RevId: fa897264ff3ff3ec6cc76259d8482be55dec0c0a
2026-09-21 11:50:27 +00:00
jif 3938a27c1d Route agent delivery through captured send requests (#46994)
## What changed

Replace `LocalAgentControl::deliver_message` with `send(SendRequest)`, accepting both user input and agent messages with captured resume configuration and turn options. Resolve target references relative to the caller's registered identity and return recipient metadata and a submission ID in `DeliveryReceipt`.

Migrate the V2 messaging tools to the new entry point and use receipt metadata for activity events. Preserve recipient reload behavior, non-waking queue-only messages, and rejection of follow-up tasks targeting the root agent.

## Testing

Update the cold-resume and sibling-reload tests to exercise `SendRequest` while checking instruction inheritance.

GitOrigin-RevId: 8fd330b8a9c3510483110ed05c4c9d3d616db237
2026-09-21 10:11:53 +00:00
vinh-gpt e24ac448b3 Allow thread instruction providers to share updates with subagents (#46577)
## Why

Subagents inherit applied instruction snapshots, so later provider updates do not reach running descendants. Hosts need an explicit way to share current thread instructions across an agent tree.

## What changed

- Add `ThreadInstructionsProvider::share_with_subagents()`, defaulting to `false`. Opted-in descendants refresh instructions at their next model-request boundary.
- Retain shared providers across root unloads and descendant reloads. Let a resumed root replace the provider for surviving descendants, or preserve their last shared instructions when it supplies a non-sharing provider.
- Keep providers scoped to their root tree and preserve snapshot-only instructions for root forks and isolated sessions, including Guardian reviews.

## Testing

Add coverage for child and grandchild instruction updates and clearing, provider replacement after root restart, lazy descendant reloads, default snapshot inheritance, and isolation between roots and Guardian sessions.

GitOrigin-RevId: 44c9fb7fe9ae1f96156bdf3c47ab6c4a81bd65e9
2026-09-19 02:15:20 +00:00
jif e416eadf7f Encapsulate rollout budget accounting in LocalAgentControl (#46559)
## What changed

Replace direct access to the shared rollout budget with controller methods for
recording token usage, retrieving pending reminders, and marking reminders as
delivered. Move the `SessionBudgetExceeded` check into the controller and update
session and guardian callers, preserving reminder acknowledgment after insertion
into conversation history.

## Testing

Replace the shared-budget pointer assertion with a behavioral check: recording
25 output tokens in a reviewer session leaves 75 tokens in the parent session's
budget reminder when the initial budget is 100 tokens.

GitOrigin-RevId: 003bc2b56e526787c1864c09729bbad1006e243d
2026-09-19 01:34:59 +00:00
sayan-oai c7828dd010 Keep step settings and approval environments consistent (#46556)
## Why

Background processes can outlive their launching turn. Their approval reviews need the originating environment's filesystem restrictions, even when the active turn uses a different environment. Remote restrictions must also be resolved using executor paths rather than the local filesystem.

## What changed

- Capture settings and environment selections together in `StepInputs`. Preserve the captured selection during active model updates while allowing environment startup to finish.
- Carry environment IDs into Guardian network and `execve` requests, and use the owning process's environment with current review settings. Refresh environment readiness for network requests that fall back to the active turn.
- Resolve remote denied paths and globs using the executor's policy context. Decline automatic approval when the request's environment is unavailable or an explicitly denied temporary directory cannot be resolved.

## Testing

Add regression coverage for active model updates retaining their environment while the next turn adopts a new selection, background approvals using their owning environment, newly ready network environments, and remote denied paths and globs, including Windows paths and missing temporary-directory metadata.

GitOrigin-RevId: b620d4b030c597a4f430fe0500864fa5469db3d4
2026-09-19 01:27:26 +00:00
jif c6f5d9e9b5 Return LiveAgent records from agent listing (#46553)
## What changed

Return thread IDs, metadata, and status from `LocalAgentControl::list_agents` using the shared `LiveAgent` type. Move conversion to `ListedAgent` into the tool handler, preserving the `list_agents` response fields and the thread ID fallback for agents without a path.

GitOrigin-RevId: c935cf96ab2a370645a4b74e3306540fc2d168a5
2026-09-19 01:21:09 +00:00
jif 7a15548c6a Move child completion routing into the agent controller (#46552)
## What changed

Have `Session` capture terminal child state in an `AgentTurnOutcome` and delegate delivery to `LocalAgentControl`. Move parent notification and completion activity routing into `agent/control/completion.rs`, so routing no longer takes the child's live `TurnContext`.

Preserve best-effort, queue-only parent delivery, completion activity for the initiating agent, and result tracing only after successful delivery.

GitOrigin-RevId: e06871d92c9ca8660de29f50356cf7c37f7e5199
2026-09-19 01:19:55 +00:00
jif c026e7a622 Expose a backend-independent agent control contract (#46547)
## What changed

Add a public, object-safe `AgentControl` trait and request/response types for coordinating an agent tree independently of where its threads run. Define contracts for lifecycle operations, message delivery, status observation, execution admission, usage accounting, shared configuration, and guardian evidence.

Move shared agent types out of the local controller and export them from `codex-core`. Let `AgentExecutionGuard` own a backend-provided reservation while preserving the local limiter's release-on-drop behavior. Include `root_thread_id` in `GuardianRootSnapshot` to identify the source of authorization evidence.

## Testing

Add tests for reservation release when a guard is dropped or a turn is cancelled, and extend the guardian authorization test to assert the root thread identity. Check trait object safety at compile time.

GitOrigin-RevId: 9385c9fbfd189f08429539fd89061ef8c9efe0d9
2026-09-19 01:03:55 +00:00
jif 7fb599de8c Rename AgentControl to LocalAgentControl (#46513)
GitOrigin-RevId: a8e8a5c818a1751c5d2667f5af87e481482fc7db
2026-09-18 23:39:30 +00:00
sayan-oai c775dd3c33 Defer environment selection changes until the next turn (#46310)
## Why

Updating environment selections while a turn is running must not redirect its tools or prevent its pending environment setup from completing.

## What changed

- Store future environment selections separately from active environments, and activate them when preparing new work with no task running.
- Keep turn contexts and MCP workspace roots tied to the active environment snapshot. Report saved selections through thread settings and `environment_selections()`.
- Route environment configuration and failure callbacks to matching active or future selections so each can finish setup independently.
- Stop the running task before manual compaction adopts the saved environments.

## Testing

Add regression tests that preserve a running task's working directory and workspace roots, then adopt the saved selection for the next task. Add remote environment coverage showing that future setup can complete while the active turn waits, with each turn receiving its own capability roots.

GitOrigin-RevId: 09a6b90131d2ab2441ce2fe9b0368a3668889f31
2026-09-17 21:47:23 +00:00
jif e269f2164c Include sender user messages in Guardian delegation reviews (#46179)
## Why

A delegated task can omit restrictions from the sender's user messages. Guardian needs that context when reviewing actions in the receiving thread.

## What changed

- When thread-owned Guardian context is enabled, capture up to three recent local user messages when a `send_message_to_thread` delivery from `codex_app` or `codex_tui` is accepted.
- Provide a bounded snapshot to synchronous and asynchronous reviewers, with explicit notices for unavailable evidence and a reminder that historical context does not transfer permission. Keep the snapshot out of the worker prompt.
- Retain snapshots with their deliveries across replay, compaction, and rollback, and strip them from forked agent history.

## Testing

Add coverage for reviewer-only visibility, missing sender provenance, context-budget preservation, checkpoint replay and rollback, fork isolation, and input serialization that rejects harness metadata.

GitOrigin-RevId: 3870ba762aa81689713b56d4cb3b98566bffed88
2026-09-17 10:02:38 +00:00
rhan-oai 800d183e2d Use captured step settings when spawning subagents (#46075)
## Why

After a settings update during an active turn, spawned agents could inherit the turn's initial model and reasoning settings. Effort-only overrides could also be validated against the wrong model.

## What changed

Build child configuration from the invoking step's captured model, effective reasoning effort, and reasoning summary in both multi-agent versions. Validate effort-only overrides against that captured model's supported reasoning levels.

## Testing

Add regression coverage for spawning after an active-turn settings update in both multi-agent versions, including effort-only overrides. Update configuration tests to check captured settings and the model's default reasoning effort.

GitOrigin-RevId: 068bdb744149048829cdaa68d254b62e96e6e6af
2026-09-17 01:51:14 +00:00
rhan-oai a8c36ca6d2 Centralize model-message resolution and rendering in codex-prompts (#46026)
## What changed

- Add `ResolvedModelMessages` to resolve catalog text and bundled defaults while preserving explicit empty overrides and their source.
- Move base-instruction rendering, Guardian prompt composition, multi-agent role rendering, and `update_plan` guidance filtering into `codex-prompts`; migrate consumers to the shared APIs.
- Separate permission-profile resolution from prompt composition, and annotate Guardian policy and classifier instructions with content kinds.

## Testing

Add and update coverage for missing versus empty templates, literal overrides, multi-agent role composition, Guardian policy substitution and truncation, and preservation of permission path spellings and order.

GitOrigin-RevId: 52335bb7acec0f432d5c57acb2accd5f0276056e
2026-09-16 21:01:13 +00:00
Vivian Fang 5bf132cd52 Add opt-in nonfatal handling for clock read failures (#45825)
## Why

Clock provider failures can abort a turn while preparing time context or running clock tools. Allow turns to continue with an explicit indication that the current time is unavailable.

## What changed

- Add `features.nonfatal_clock_read_errors`, disabled by default, to report clock failures to the model without failing the turn.
- Emit a generic `failed to read current time` notice for context reads and tool errors, without exposing provider error details. Deduplicate context notices per turn and compaction window, and remove inherited notices from forked subagent context.
- Omit unavailable environment dates and explicitly clear previously visible dates with `<current_date status="unavailable" />`.
- Return external sleep clock failures to the model when the feature is enabled, preserving sleep item completion notifications.

## Testing

Add coverage for continued inference after clock failures, notice deduplication across compaction, subagent notice filtering, environment date removal and recovery, and sleep failures during initial and polling reads.

GitOrigin-RevId: a39c3723c06a6f786d8ad59d667e8b9f626c973e
2026-09-16 01:16:35 +00:00
rhan-oai 883af106b9 Retire the personality feature flag and document deprecated settings (#45809)
## What changed

- Accept and ignore `features.personality` in user configuration, profiles, and managed requirements.
- Remove feature gating from `personality = "none"`, which strips the literal `# Personality` section when preparing model catalog instructions. Preserve explicit base instructions and existing thread instructions.
- Document deprecated personality fields in configuration, app-server schemas, and the Python SDK: `friendly` and `pragmatic` no longer select a style, and `supportsPersonality` is always `false`.

## Testing

Add regression coverage for ignored legacy flag values and managed requirements, personality opt-out behavior with the flag absent or set to either value, role overrides, and preservation of explicit base instructions, including empty strings.

GitOrigin-RevId: 4e12c66b42bfc59d6f151a5b3c28fadc6654ae99
2026-09-15 23:39:40 +00:00
felixxia-oai c51cb968e4 Preserve Guardian evidence during checkpoint migration (#45789)
## Why

A checkpoint produced by a previous model may be incompatible with the selected Guardian reviewer. Legacy review must retain user restrictions and verified answers across compaction and restart until a compatible checkpoint is available.

## What changed

- Expose retained user evidence independently of whether Guardian reviews the legacy transcript or parent context.
- Resolve the selected reviewer's compaction compatibility hash during resume and remote compaction. Preserve the legacy transcript when checkpoint compatibility is unknown or mismatched.
- Activate parent-context review immediately after compatible compaction and invalidate pending reviews bound to the previous evidence policy. Ordinary compaction preserves pending reviews.
- Keep strict compatibility checks for previously migrated checkpoints whose complete legacy transcript is no longer available.

## Testing

Add coverage for mismatched checkpoint hashes, retained evidence during legacy review, and pending-review cancellation on migration. Add a request-history scenario covering a model switch, incompatible automatic compaction, restart, and compatible manual compaction with preserved user restrictions and verified answers.

GitOrigin-RevId: b52bfd7c21ce7ebed482174c8d7c327e50b1ada8
2026-09-15 20:41:39 +00:00
felixxia-oai 0c3a14bbc2 Preserve Guardian authorization evidence across checkpoint migration (#45782)
## Why

Older compaction checkpoints can lack a producer model hash. Enabling thread-owned Guardian context must accommodate those checkpoints without losing user instructions or verified answers.

## What changed

- Select review policy from each history snapshot independently of the session's evidence capture policy.
- Keep legacy review for checkpoints with missing or empty producer hashes when the transcript preserves the evidence. Preserve strict compatibility checks when review depends on retained-only evidence.
- Continue capturing retained instructions and answers during migration, while supplying legacy reviews with runtime answers and subagent reviews with root authorization evidence.
- Record producer model hashes on new compactions regardless of context mode.

## Testing

Add coverage for checkpoint migration across compaction and resume in both history storage modes, snapshot policy stability, retained-evidence preservation, and authorization revalidation for owning sessions and subagents.

GitOrigin-RevId: ec72b4a51d40729173e24ac1b53b7d516ddaa825
2026-09-15 20:08:36 +00:00
jif 40f01fbe08 Move spawned-agent interruption rules into AgentControl (#45676)
## What changed

Extract V2 interruption validation and dispatch into `AgentControl::interrupt_spawned_agent`, returning the agent path and previous status with typed validation and runtime errors. Update the `interrupt_agent` tool handler to delegate to it while retaining tool error mapping and activity emission.

Preserve rejection of root and self targets and successful handling of unloaded or already-dead runtimes without reloading them.

GitOrigin-RevId: 893bbc4f464596d0fee032a71702a4a4f6becf5c
2026-09-15 11:13:00 +00:00
jif 4415f985dc Move V2 agent message delivery into AgentControl (#45670)
## What changed

Extract target validation, runtime reloading, and message delivery from the V2 tool handler into `AgentControl::deliver_message`. Keep target resolution, analytics, and tool-facing error mapping in the handler.

Represent plaintext and encrypted payloads with `AgentMessage`, sharing communication construction with agent spawning. Preserve queue-only and follow-up turn semantics, target checks before reload, and turn metadata propagation.

GitOrigin-RevId: a88bcede015a17f6c11c7cad95ee58add5dc2820
2026-09-15 10:35:58 +00:00
jif b13164d86f Centralize child agent configuration in the agent module (#45669)
## What changed

Move shared spawn and resume configuration helpers into `agent::child_config` and route both multi-agent versions through `prepare_agent_spawn_config`.

Preserve each version's role and model precedence, full-history inheritance, service-tier selection, runtime policy, and default-role metadata for reloads. Return configuration errors as strings and convert them to `FunctionCallError::RespondToModel` at tool-handler boundaries.

GitOrigin-RevId: 9d539050aa44f94043a6487f1f6f1037de1d15ca
2026-09-15 10:07:37 +00:00
rhan-oai 132c739171 Retire Friendly and Pragmatic personality selection (#44946)
## What changed

- Use literal model instruction templates and the standard fallback prompt, ignoring legacy personality variables. Retain catalog decoding compatibility and report `supports_personality` as `false` for generated model presets.
- Stop emitting `<personality_spec>` developer messages and assigning an implicit Pragmatic configuration default.
- Filter Friendly/Pragmatic overrides from TUI requests while preserving explicit `personality = "none"`. With `features.personality` enabled, this opt-out still strips the model's personality section.
- Refresh inherited model instructions for agent roles only when the personality opt-out changes, preserving custom instructions.

## Testing

Update coverage for literal legacy templates, deprecated overrides on turn start and resume, role instruction refresh, and forwarding the explicit opt-out through thread start, resume, and fork requests.

GitOrigin-RevId: 1391db4e565e010569f0885f80013d1f86b45825
2026-09-12 00:22:04 +00:00
vkg-oai fc948f8c47 Add a provider for thread-scoped instructions (#44701)
## What changed

- Expose `ThreadInstructionsProvider` through `StartThreadOptions`. Load its snapshot at startup and model-request boundaries, composing it after global instructions and before repository instructions. Empty or blank output clears only the thread contribution.
- Reject thread instructions exceeding 10,000 estimated tokens independently of the repository instruction budget. Allow host-provided instructions without a filesystem source and rename the shared future type to `LoadInstructionsFuture`.
- Retain the provider across warm resumes; require hosts to supply it again for cold resumes and offline forks. Live forks and subagents inherit applied snapshots without inheriting the source thread's provider, including when the parent is unloaded during setup or reload.
- Include thread instructions in guardian reviewer inheritance and reuse decisions.

## Testing

Add coverage for composition and clearing, refresh within an active turn, size rejection before sampling, cancellation-safe refresh, fork and resume behavior, parent eviction, and reviewer reuse invalidation.

GitOrigin-RevId: 7be9a523cbbfd67704067dfd526188dad89a3c88
2026-09-11 01:57:54 +00:00
joeytrasatti-openai e004dc6a4b Preserve turn triggers across delegated agent work (#44659)
## Why

Delegated usage should retain the trigger of the turn that initiated it, including composer input and scheduled automation.

## What changed

Propagate `turn_trigger` through agent spawning and follow-up messages in both multi-agent tool implementations. Apply the supplied trigger when pending mailbox work starts a new turn.

## Testing

Extend tests to verify trigger propagation to spawned and nested agents, updated triggers on reused agents and peer follow-ups, and preservation of the active turn's trigger when steering.

GitOrigin-RevId: e8fea208587c633fec7cb3f1c0815ff91d1a44e5
2026-09-10 22:26:26 +00:00
Owen Lin 196964ef10 Preserve root turn attribution in turn-start events (#44611)
## Why

Persisted turn-start events lack the originating root turn ID, so they cannot directly associate child turns with the root turn that initiated them.

## What changed

- Add optional `root_turn_id` to `TurnStartedEvent`. Use the inherited root turn ID when available, otherwise the turn's own ID.
- Centralize turn-start emission for regular turns, shell commands, and manual compaction so they record attribution consistently.
- Carry attribution into `ThreadHistoryTurnChange` when processing turn-start events and retain it through completion in the history builder.
- Keep older records compatible by defaulting missing attribution to `None`.

## Testing

Add coverage for root and child turn attribution, persistence when tool collisions fail a turn before sampling, history change propagation, and deserialization of older turn-start records.

GitOrigin-RevId: 54a80b828ca7d1c4c19f13d468c01d052e1b9130
2026-09-10 18:24:13 +00:00
Matthew Zeng b5544d5732 Persist disabled plugin IDs in thread settings (#44332)
## What changed

- Add `disabled_plugin_ids` to thread startup options, settings overrides, snapshots, and persisted turn contexts. Omitted overrides preserve the current list; an empty list clears it.
- Restore the selection on resume and capture it before truncating history for a fork. Prefer the owning thread's latest settings snapshot, falling back only to the latest turn context so stale history cannot resurrect an older selection.
- Freeze the selection at turn admission and retain compatibility with histories that lack the new fields.

## Testing

Add coverage for owned settings, explicit clears, latest-turn fallback, and legacy snapshots. Extend settings tests to cover plugin selection during runtime restoration and compaction, and verify initial turn persistence without extra settings checkpoints in both history modes.

GitOrigin-RevId: 75ffbff5763cd93cc5ac69d73b08b237f59bc009
2026-09-09 23:23:59 +00:00
Abhinav b64de2f3ad Use the originating model when recording conversation history (#44243)
## Why

History recording used the model captured at turn start, so switching models within a turn could apply stale image preparation and tool-output truncation rules.

## What changed

Pass explicit model metadata through conversation recording. Record model responses and tool results using their originating step's settings, and capture the current model for pending input recorded during startup interruption or task completion.

## Testing

Add regression coverage for tool results across a model switch, explicit model selection for plain and annotated history, and image input retained during interruption and completion. Extend model-switching tests to verify that prepared media and item identity survive switching back to a multimodal model in live, resumed, and forked threads.

GitOrigin-RevId: 5bc750c30c334acb9b802cb80fdea01daffa84a1
2026-09-09 17:46:00 +00:00
rhan-oai 6515a72db7 Preserve runtime workspace roots across thread resume (#43848)
## Why

Resuming a thread should retain its selected workspace folders, including additional roots and explicit empty selections. Resume overrides also need to survive a subsequent resume when no turn has run.

## What changed

- Persist `runtime_workspace_roots` in startup metadata and thread settings snapshots, separately from explicit environment selections and permission-profile roots.
- Restore roots from the latest snapshot owned by the resumed thread, falling back to owned startup metadata only when no snapshot exists. Honor explicit `runtimeWorkspaceRoots` overrides, retarget the old `cwd` root when `cwd` changes, deduplicate roots, and validate restored paths for the current host.
- Checkpoint effective settings on resume and restored settings after revert. Reload resume configuration if saved workspace roots change during loading.
- Normalize Windows rollout path spellings when matching thread search results, preserving selection of the correct rollout after revert, including compressed rollouts.

## Testing

Add regression coverage for workspace restoration, empty and explicit overrides, foreign paths, compaction and revert, resume checkpoints without recency changes, concurrent settings persistence, and rollout search path matching.

GitOrigin-RevId: d98d9d34dd63934d441120916c61c12b69e7f062
2026-09-08 16:24:38 +00:00
jif d665e3bbc8 Include unloaded children in multi-agent v2 environment context (#43491)
## Why

After a cold resume and compaction, the subagent roster omitted children whose threads had not been loaded.

## What changed

Build the multi-agent v2 roster from registered direct children and render their full agent paths. Prioritize loaded children, sort alphabetically within each group, and cap the rendered roster at eight agents and 1,024 bytes. Preserve the existing behavior for other multi-agent versions.

## Testing

Extend the cold-resume integration test to check that post-compaction context includes unloaded children, excludes grandchildren, and lists a loaded child before an alphabetically earlier unloaded sibling.

GitOrigin-RevId: 745c1622133b9c01e61f4702e4b2ef6255417f39
2026-09-07 15:10:37 +00:00
felixxia-oai 16ff14c266 Retain inherited Guardian instructions in standalone forks (#43478)
## Why

A standalone root forked from a worker needs its inherited user instructions for Guardian review, including after compaction. Parent input counters belong to a different thread, and omitted parent answers may have restricted an inherited authorization.

## What changed

- Adopt inherited user instructions into thread-owned retained context for standalone roots, recovering surviving checkpoint messages when needed.
- Keep inherited instructions before local evidence without sharing local acceptance counters, and preserve that distinction during reconciliation and rollback.
- Mark parent verified answers as incomplete and treat recovered checkpoint instructions as incomplete excerpts.

## Testing

Add coverage for standalone forks from copied history and truncated checkpoints, retention through compaction and resume, inherited/local ordering collisions, and rollback scope.

GitOrigin-RevId: bf716e224a1d29d6c528ef0dd7cdb118a413a08c
2026-09-07 13:58:57 +00:00
felixxia-oai aa12ab45df Recover missing Guardian root instructions in acceptance order (#43472)
## Why

Incomplete retained checkpoints can omit root user instructions that still survive in live history. Queued input can also reach model history after a later-accepted answer, so recording order cannot reliably order grants and restrictions for subagent authorization reviews.

## What changed

- Reconcile retained evidence with surviving local user messages using source identity and persisted acceptance order, including answers present only in the checkpoint.
- Preserve checkpoint gaps and mark evidence incomplete when recovered instructions lack an order or conflict with an existing order.
- Restore the input-order counter from surviving local metadata so new instructions sort after recovered evidence, even without a retained checkpoint.

## Testing

Add unit coverage for source matching, acceptance ordering, persistent gaps, conflicting orders, and counter restoration. Extend subagent authorization tests to cover checkpoint resume, queued approvals, missing sources, and a subsequent revocation.

GitOrigin-RevId: 8bfbfd2c797d725796187e5cecf7f3f11a5f3380
2026-09-07 13:40:29 +00:00
felixxia-oai 8260619cb6 Centralize Guardian context mode and checkpoint policy (#43458)
## What changed

Resolve `GuardianContextMode` once at session construction and share it across history retention, replay, evidence capture, compaction, and review consumers.

Extract synchronous reviewer context policy and consolidate Guardian V2 parent checkpoint selection so sampling and fast approval use the same eligibility checks. Preserve legacy checkpoint omission and strict compatibility requirements for thread-owned context.

## Testing

Adapt existing review and history tests to the explicit context mode. Move checkpoint tests alongside the extracted selector, retaining coverage for latest-item identity, unusable checkpoints, and complete-item size limits.

GitOrigin-RevId: c73fb6fea556921acfffe758a5f709d7494019dd
2026-09-07 12:53:57 +00:00
felixxia-oai 4636819a35 Harden Guardian reviews after context compaction (#42852)
## Why

Guardian reviews must not lose user authorization constraints or reuse an
unreadable or incompatible parent checkpoint after compaction.

## What changed

- Retain bounded excerpts of oversized root user messages across compaction,
  resume, and rollback, and recover excerpts from legacy Guardian history when
  available.
- Require thread-owned Guardian review sessions and asynchronous scoring to
  reuse only non-empty checkpoints produced by a compatible review model.
- Fail closed instead of reviewing without the required checkpoint when reuse
  is disabled, compatibility is unknown, or checkpoint content is unusable.

## Testing

Expanded retained-context, review-session, asynchronous-scoring, and app-server
coverage for oversized instructions, legacy recovery, model incompatibility,
missing content, resume, rollback, and disabled checkpoint reuse.

GitOrigin-RevId: f30d837197e0d838e656a632109f490c38208f5e
2026-09-04 21:07:14 +00:00
felixxia-oai 9c4253ffc1 Retain user instructions in Guardian context (#42844)
## Why

Guardian reviews need the original user instructions even when compaction or
transcript selection removes them from the active conversation window.

## What changed

- Capture complete user messages in host-owned retained context and include them
  as ordered authorization evidence alongside verified answers.
- Omit oversized instructions atomically and emit an explicit incomplete-evidence
  notice instead of exposing a potentially misleading partial permission.
- Mark user messages inherited by forked agents so they remain model-visible
  without becoming child-local authorization.

## Testing

- Cover retained instructions across compaction, resume, rollback, and agent
  forks, including oversized evidence and legacy context behavior.

GitOrigin-RevId: 97122509d818c90d2f87c6a1b29c99c05ad0316e
2026-09-04 20:27:18 +00:00
felixxia-oai 87628df77a Preserve root authorization context in Guardian reviews (#42832)
## Why

Guardian reviews for delegated workers need the current root instructions and verified answers even after the parent context is compacted. Approvals must also become stale when that root authorization changes.

## What changed

- Build bounded root review evidence from retained context, preserving source order and answer scope while prioritizing user instructions over optional assistant context.
- Recover retained instructions from Guardian history after compaction and mark authorization incomplete when required instructions or answers are unavailable.
- Version root authorization in synchronous and reusable review sessions so an allow result is cancelled when its evidence changes.
- Strip parent-only Guardian approvals when forking worker history in retained-context mode.

## Testing

- Cover retained and legacy context modes, oversized evidence, message limits, parent compaction, and authorization changes during review.

GitOrigin-RevId: 658219b7cee08f2752adcea9966268fd21727976
2026-09-04 19:19:04 +00:00