Commit Graph
188 Commits
Author SHA1 Message Date
jif fbb2f9dbec Use step environment snapshots for subagent inheritance (#55331)
## What changed

- Remove `subagent_thread_environments` and the separate configured environment bindings. Spawned agents inherit the invoking step's environment snapshot.
- Retain environment selections across child eviction without retaining executor bindings. Reload V2 children against the parent's captured environments, requiring matching environment IDs, working directories, and workspace roots while preserving permission validation.

GitOrigin-RevId: d820c63ea20f5834ed88071d16c60683f2545406
2026-10-19 17:43:31 +00:00
jif d70c2c2cdf Add configured thread environment inheritance for subagents (#55327)
## Why

Temporary environment attachments for a parent's turn should not become a child's persistent environment configuration or survive child eviction.

## What changed

- Add the default-disabled `subagent_thread_environments` feature flag. When enabled, subagents inherit configured thread environments captured with the spawning step instead of active turn selections.
- Track configured bindings separately from turn attachments, preserving pending configuration ownership when turn selections change.
- Retain configured bindings across child eviction and reload, excluding temporary attachments. Preserve the child's workspace when the parent switches workspaces, while enforcing current roots and permissions when the parent still configures the same workspace.

## Testing

Extend coverage for both multi-agent versions, forked children, empty configured environments, pending configuration, and legacy inheritance. Add eviction and reload cases covering temporary attachments, workspace changes, deferred executor startup, and permission validation.

GitOrigin-RevId: 4533645503d5f863a9ccc064386ed7ca169d98b7
2026-10-19 17:16:22 +00:00
Charlie Marsh 1cc7dc8f2a Share additional tool declarations across response item clones (#54945)
## Why

Cloning `ResponseItem::AdditionalTools` deep-copies its tool declarations for history and request copies.

## What changed

Store `tools` in an `Arc<[serde_json::Value]>` so clones share immutable declarations. Update constructors and existing test fixtures to use the shared representation.

GitOrigin-RevId: eb8831774afb45fe8431a796f34ae9d1243e884a
2026-10-17 23:17:51 +00:00
pakrym-oai ce0323f2f2 Support typed content in contextual prompt fragments (#54776)
## Why

Contextual fragments and extension-owned world-state sections currently return strings, limiting them to text content.

## What changed

- Return `ContentItem` from fragment bodies and rendering, preserving classification and attribution. Apply text markers only to `InputText`; pass other content through unchanged.
- Allow extension prompt and world-state contributions to carry typed content, and preserve media in context-window hints.
- Hash non-text world-state fragments by their serialized content and role while retaining the existing text hashing behavior.
- Add shared content-to-tool-output conversion that preserves image references, image detail, and audio.

## Testing

Add coverage for typed world-state hashing and preservation of image content and attribution. Expand code-mode output tests to cover input text, output text, file-backed and inline images, and audio.

GitOrigin-RevId: 2ed00d466a3f169b151202f3eef71e667ea64be1
2026-10-17 04:02:21 +00:00
rhan-oai cb03f28a40 Refresh model instructions in incremental-tool context windows (#53872)
## Why

Incremental-tool windows recorded base instructions only at setup, so a catalog refresh for the same model could leave active instructions stale. Instruction changes need to reach the model without rewriting the existing history prefix.

## What changed

- Track model identity and instruction content independently, appending a `model_instructions` developer message when either changes. Explicitly mark replacement or removal of base instructions, and avoid repeating unchanged updates.
- Start new windows after compaction with the latest model instructions while preserving custom base instructions.
- Preserve the recorded window base during local compaction retries, including empty instructions, and rebuild current model instructions when reconstructing child context.

## Testing

Add integration tests and request snapshots for catalog refreshes, instruction removal, model switches, compaction, restart, and forks. Extend regression coverage for legacy snapshots and local compaction retries.

GitOrigin-RevId: eeca69067b4d9cd91c817732d79b4d5c1faa18b9
2026-10-14 05:36:44 +00:00
jif 4e7ef7d19d Keep spawned children provisional until the spawn result returns (#53654)
## Why

Cancellation after initial input admission could leave a child registered even though the spawn caller had not received its result.

## What changed

Resolve the child's status and configuration before committing reservations and releasing provisional ownership. This keeps cancellation cleanup active through the final awaits and lets the spawn result return without yielding after commitment. Cancellation after the result returns does not retract the accepted child.

## Testing

Add a regression test that cancels spawn during the final status lookup after input admission and verifies that the child is unregistered, terminated, and unloaded, and that shutdown completes. Extend the provisional-child cancellation test to cover both native V1 and V2 callers.

GitOrigin-RevId: 028b873ad4c1fac2c4b5d1dc823b4561ff19e6bf
2026-10-13 12:42:53 +00:00
pakrym-oai 5ef96ab278 Add opt-in output token replay for OpenAI requests (#52742)
## What changed

- Add the disabled-by-default `output_token_replay` feature to request `output.encrypted_content` from OpenAI providers.
- Preserve encrypted message and tool-call output, message and function-call status, and output-text `annotations` and `logprobs` through history and replay. Update the generated protocol schemas and SDK types.
- Strip output ciphertext from requests to other providers while retaining it in stored history, including after replay is disabled. Remove encrypted content from memory extraction inputs.

## Testing

Add integration coverage for the feature/provider combinations, metadata replay across follow-up requests, and history preservation when resuming with replay disabled.

GitOrigin-RevId: 77729a021b6771933402aebe74ece8eb39c057e2
2026-10-10 01:25:00 +00:00
Alex Kira e4490eff65 Allow model catalogs to override incremental tool notices (#52736)
## What changed

Add `model_messages.tools.incremental_tools` overrides for the update hint, tool and namespace removal headers, and namespace instruction update and clearing messages. Missing, null, or over-512-byte values fall back to bundled wording; empty strings omit static text while retaining runtime names and instructions.

Substitute `{name}` in namespace message templates and append runtime instructions verbatim. Wording changes alone do not trigger tool catalog updates.

## Testing

Extend unit tests and MCP request-history snapshots to cover custom wording, empty notices, tool removal and restoration, and namespace instruction changes and clearing without repeating unchanged tools or notices.

GitOrigin-RevId: 22dea0a6fb4cfcd646f5e65346424834c8b7d5a2
2026-10-10 01:14:28 +00:00
jif a06545b311 Add opt-in history prefix preservation for full agent forks (#52535)
## What changed

Add `preserve_fork_prefix` to the multi-agent v2 configuration, defaulting to `false`. When enabled, full forks retain the parent's model-visible history, including commentary and tool records, and append the child's instructions. Legacy compaction without a reusable context baseline still rebuilds the child context.

Mark copied history as inherited, complete unfinished tool calls in the fork snapshot, and exclude inherited manual approvals from authorization review while retaining them in model context.

## Testing

Add coverage for preserved request prefixes, child instructions, legacy and paginated histories, Code Mode, missing inherited tool outputs, compaction fallback, and approval isolation across checkpoint replay. Update the noisy helper failure test to read its response before starting cleanup.

GitOrigin-RevId: ce9235dfa111c88d6ce66cb93d564fb63b326489
2026-10-09 11:08:24 +00:00
Alex Kira 0b755b1945 Emit one developer notice per incremental namespace update batch (#52295)
## What changed

Move incremental tool guidance out of namespace descriptions and into a developer message preceding each namespace declaration batch after the initial catalog. The notice covers newly added namespaces as well as changed ones, explaining that earlier tools remain available unless explicitly removed and that newer definitions replace earlier ones.

Retain the notice alongside tool declarations in full-history agent forks, and discard it when legacy compaction forks rebuild those declarations.

## Testing

Add unit coverage for multiple new namespaces sharing one notice. Update request-history snapshots for tool changes, removals and restoration, and regular Responses requests. Extend resume and fork tests to cover notice preservation without duplication and removal when rebuilding declarations.

GitOrigin-RevId: 05f79f5eb378a355cf935eabf63951015a9b454b
2026-10-08 22:01:24 +00:00
Adam Perry @ OpenAI 845345b1dd Preserve subagent capabilities independently of forked history (#52241)
## Why

Subagents should retain the spawning turn's selected skills and plugin choices whether `fork_turns` is `none` or `all`. Capability selection should not depend on copied conversation metadata.

## What changed

- Use a shared child startup path for fresh and history-forked agents, inheriting selected capability roots from the spawning environment snapshot.
- Pass the spawning turn's `disabled_plugin_ids` through both spawn handlers. When omitted, inherit the parent's current choices; explicit lists, including an empty list, override them.
- Resolve the parent before startup so inherited client MCP settings apply even when only the session source identifies the parent.
- Carry plugin choices into delegates with inherited isolation and preserve saved capability roots when resuming a child.

## Testing

Add regression coverage for executor skill listing and reading, plugin MCP registration with both history modes, plugin overrides, capability-root precedence and isolation, and restoring saved child settings after parent settings change.

GitOrigin-RevId: 2a6891a9bc6372fd2d1f30add2b5611f96b60594
2026-10-08 19:21:57 +00:00
jif b12ac84be9 Add regression coverage for cancelled agent reloads (#52040)
## What changed

Add `cancelled_v2_send_finishes_reload_registration` to verify that cancelling a multi-agent V2 send during an evicted child's reload does not cancel registration. The test checks that the thread-created notification arrives and evicted-environment state is cleared.

Evict and reload the child again with only one child slot available to catch leaked residency pins or reservations, and verify that only the subsequent follow-up message is delivered.

GitOrigin-RevId: ce6ed90d0049245370f26d8dbb35b9f1cd0b3063
2026-10-08 09:48:47 +00:00
jif d2a6dac20b Preserve agent state when unloading idle multi-agent v2 children (#52034)
## What changed

- Route app-server idle unloading of multi-agent v2 children through local eviction that preserves unread mail and environment selections for reload.
- Hold residency pins through input submission so newly reloaded children cannot be evicted before receiving their work.
- Guard listener cleanup against replacement runtimes and subscriptions, and reject local eviction of host-controlled threads.

## Testing

Add coverage for unsubscribe-driven eviction followed by `followup_task`, verifying restored conversation context and exactly-once delivery of queued mail. Extend tests to check that residency pins block eviction and that rejected host eviction preserves the thread and mailbox.

GitOrigin-RevId: e36723730af683d2081e495e637f0e6d23548b8d
2026-10-08 09:39:33 +00:00
keith thornhill 24edd7b890 Expose detailed agent tree shutdown failure reports (#51515)
## Why

Agent tree shutdown previously returned a generic error without identifying which operation or thread failed, making cleanup failures difficult to diagnose.

## What changed

- Add `AgentTreeShutdown::wait_detailed()` and public report types while preserving the existing `wait()` result and error message.
- Record operation, optional thread ID, and either an abandoned teardown guard or a failed phase with a payload-free error category across session cleanup, child spawn cleanup, and resident eviction.
- Give each tree a correlation ID, log each failure, and retain up to 64 failures with a count of additional failures omitted. Record failures before releasing tree membership so all completed waiters observe the same report.

## Testing

Add unit coverage for aborted and completed teardown, cloned guard context, concurrent and repeated waiters, omitted failure counts, and report formatting without raw error payloads. Extend integration coverage for successful tree shutdown and persistence writer failures, including compatibility with `wait()`.

GitOrigin-RevId: 68784af28b63e875b00a55d78729f0cc5b01ac15
2026-10-06 23:28:55 +00:00
Adam Perry @ OpenAI 9479e1fdb7 Bind capability roots to environment selections (#51493)
## Why

Capability discovery needs the roots captured with each environment snapshot. Threads sharing an executor can select different roots, and changing environment order must preserve executor skill aliases.

## What changed

- Attach the receiving thread's capability roots when constructing `TurnEnvironmentSelection` at startup and settings updates, including roots loaded from saved history.
- Resolve capability roots from environment snapshots while preserving their original order. Retain startup roots so deselecting and reselecting an environment restores its capabilities.
- Match inherited configuration by environment and workspace so differences in capability root metadata do not interrupt configuration propagation.

## Testing

Add regression coverage for root ordering across environment states and configuration changes, independent root selections on a shared executor, reselection with startup or saved roots, active turn updates, and pending configuration failures reaching child and grandchild threads.

GitOrigin-RevId: 4f2e4bb414d27195a6752406117a6050718a1198
2026-10-06 22:39:32 +00:00
pakrym-oai e79c498b5e Preserve tool declaration mode across resumed context windows (#51480)
## Why

Changing the incremental tools setting on resume should not move tool declarations and base instructions within an existing context window.

## What changed

- Determine the current window's tool declaration mode from its history, and apply the incremental tools setting when building a new window after compaction or a context reset.
- Use that mode consistently for sampling, remote compaction, startup prewarm, prompt debugging, and Guardian input budgeting.
- Preserve tool declarations alongside their comparison baseline in full-history agent forks, including compacted histories; remove them together when rebuilding context.

## Testing

Add request snapshots covering legacy resume, migration after remote compaction or a context reset, disabling incremental tools, and tool updates after restart. Extend agent fork and WebSocket startup prewarm tests to cover retained declarations and incremental tools.

GitOrigin-RevId: 7c46849a1788027a8435082e4d1f7e7f48d2700c
2026-10-06 21:28:13 +00:00
Steve Coffey b0a6b8d86f Record resolved model and reasoning effort in sub-agent activity (#51463)
## What changed

Add `model` and `reasoningEffort` to `subAgentActivity` items for multi-agent v2 spawns. Capture startup settings before the child begins its turn and resolve the reported effort against model metadata, including model defaults, while preserving the child's configured effort.

Carry these fields through live notifications, persisted activity, thread history, and legacy rollout migration. Update the JSON schemas and generated TypeScript and Python types. Older records and other activity kinds retain null values.

## Testing

Add coverage for resolved spawn settings matching the child's request across legacy and paginated history, preserving configured effort, forwarding metadata through events and history, and reading and migrating older records without the new fields.

GitOrigin-RevId: a9e4241ae21bb8db1ead293f78ffba8257cca0ae
2026-10-06 19:29:40 +00:00
Eddie Chen cfc946f4e1 Expose and persist turn lineage across the app server (#51415)
## Why

Clients starting delegated work need to attribute descendant turns to the original turn and retain that attribution through completion and history reads.

## What changed

- Accept optional `parentTurnId` and `rootTurnId` in `turn/start`, and expose `rootTurnId` on returned turns and lifecycle notifications.
- Default new turns to their own root when none is supplied. Preserve the active turn's root when steering, ignoring incoming lineage fields.
- Carry root IDs through completion, interruption, recovery, and fork boundaries, and persist them for paginated history reads. Leave unknown roots null in older history.
- Update protocol schemas and generated TypeScript and Python bindings.

## Testing

Extend coverage for default and explicit roots, steering without changing lineage, interrupted and recovered turns, history reads after restart in both history modes, nested fork pagination, and compatibility with older database writers.

GitOrigin-RevId: f1a570a12bd11742929fd2e8b017e5d35aa07dcb
2026-10-06 16:56:39 +00:00
Eddie Chen 551bd409eb Preserve turn attribution across recovery and compaction (#51402)
## Why

Recovering an interrupted turn replaced its original trigger with `retry` and restored only its root lineage from model context. Turns suspended before that context was written could lose their attribution entirely.

## What changed

- Persist regular-turn attribution in `TurnStartedEvent` and compaction resume metadata, including the trigger, parent and root turn IDs, and initiating agent path.
- Restore matching attribution during recovery, keep unknown triggers absent, and retain the model-context root fallback for older records.
- Reconstruct attribution from surviving turns across rollback and late completion or abort events, and clear inherited attribution when spawning a forked agent.

## Testing

Add coverage for repeated cold recovery, suspension before context persistence, legacy rollouts, fresh attribution on subsequent turns, compaction checkpoints, rollback, and late terminal events.

GitOrigin-RevId: 85b5763e8fbd48a1ea2c07cfda8196e63c2cd33a
2026-10-06 15:50:27 +00:00
jif c0c230e673 Add bounded diagnostics for agent spawn failures (#51355)
## Why

Spawn failures can share an error kind and message despite different causes, such as execution and residency capacity limits. Telemetry needs enough detail to distinguish these failures without using error messages or correlation IDs as metric labels.

## What changed

- Add `AgentErrorContext` annotations for capacity limits, registry rejections, runtime availability, and spawn stages. Preserve the first annotation so outer stages retain the more precise failure origin.
- Add bounded `detail` and `error_kind` labels to spawn failure metrics, using `unknown` when no context is available.
- Emit spawn failure trace events with these classifications and the call and turn IDs for both multi-agent versions.

## Testing

Add tests for distinct capacity and registry failure contexts, preservation of manager, fork, and shutdown errors, and metric aggregation across different error messages and correlation IDs. Verify that annotations preserve existing error kinds and user-visible messages.

GitOrigin-RevId: 5bbe3d32f6ce408622f38e559fddeab05b8ccb65
2026-10-06 12:32:27 +00:00
jif 6221a217e2 Remove partial-history subagent forks (#51329)
## What changed

- Limit multi-agent V2 `fork_turns` guidance to `all` and `none`. Accept legacy positive integer strings as full-history forks instead of truncating parent history.
- Remove partial-history fork handling and telemetry, and direct model override usage to `fork_turns: "none"`.
- Strip inherited `multi_agent.role_instructions` and `multi_agent.usage_hint` content by kind, including persisted hints whose wording predates the current bundled instructions.

## Testing

Update regression coverage for legacy `"1"` and `"3"` values inheriting full history, invalid and zero values being rejected, and stale parent hints being removed from compacted history with both marked and unmarked instructions.

GitOrigin-RevId: 8f6017dc66ad8deefd7745399ef76e1bb1435bb2
2026-10-06 10:39:16 +00:00
rb-oai 989c01a41a Handle partial answers consistently across agent workflows (#51249)
## Why

Partial answers contain answer fragments while a turn is still in progress. Treating them as final answers defers mailbox delivery and can count empty fragments as empty final responses; filtering them from forked histories and guardian transcripts loses answer content.

## What changed

- Allow mailbox preemption after `partial_answer` messages and keep mailbox delivery open.
- Preserve partial answers in forked agent histories and include them as protected assistant entries in guardian transcripts.
- Exclude empty partial answers from empty-final-response accounting for goals.

## Testing

Add regression coverage for partial-answer phases in live events, sampling continuations, follow-up requests, and forked child requests, plus mailbox preemption, goal accounting, and guardian transcript inclusion.

GitOrigin-RevId: 208c8933e211b42b6c2d0bec6952527b8c9c120e
2026-10-06 03:27:04 +00:00
Adam Perry @ OpenAI 2dbcab90e2 Separate environment requests from runtime selections (#51221)
## What changed

Introduce `TurnEnvironmentRequest` for caller-supplied environment input and construct `TurnEnvironmentSelection` at session startup and app-server settings boundaries. Update thread startup, default environments, and inherited environment handoffs to use requests, with explicit conversions when reusing runtime selections.

Move the environment types into `protocol::environment` while retaining their `protocol` re-exports. Update test fixtures and existing tests to build request inputs separately from runtime selections.

GitOrigin-RevId: 12e7daaece95aae136afae8b055b4dbaebdffc75
2026-10-06 01:39:50 +00:00
Bryan Ashley 9d53dd91b5 Prevent shared instruction providers from delegating to themselves (#50093)
## Why

Reloading an unloaded root from a surviving child can supply the shared instruction wrapper already registered for that root. Replacing its underlying provider with that same wrapper makes instruction loading recurse into itself.

## What changed

Reuse the existing wrapper without replacing its provider when both are the same `Arc`. Continue to accept distinct replacement providers.

## Testing

Extend regression coverage to reload the root from a surviving child and verify that shared instructions still update. Check wrapper reuse, replacement with a distinct shared provider, and freezing the shared snapshot when switching to a provider that does not share with subagents.

GitOrigin-RevId: 7b6b2f9031f206e203f6fa14e1478a36b305ec39
2026-10-01 20:44:54 +00:00
ke-oai e4e33a56b0 Enable dynamic tool inheritance for fresh V2 subagents (#50082)
## Why

Subagents spawned without forked history do not receive their parent's client-defined dynamic tools, preventing them from using those tools for delegated work.

## What changed

Add the disabled-by-default `multi_agent_v2_dynamic_tools` feature flag. When enabled, fresh V2 subagents inherit the parent's dynamic tool definitions and persist them in session metadata.

## Testing

Add coverage for V1 and V2 feature gating, tool persistence, and a fresh V2 subagent calling an inherited tool and receiving its result without inheriting parent history. Update TUI assertions and a snapshot to reflect blank-line separation and question text in recovered answers.

GitOrigin-RevId: a17a16bf5570f54ce922c1521cffb883022354f2
2026-10-01 19:45:28 +00:00
Owen Lin 8e44ad94b0 Add coordinated shutdown for local agent trees (#49814)
## What changed

Expose `ThreadManager::request_agent_tree_shutdown` and an `AgentTreeShutdown::wait` handle. Requests reject new starts in the shared runtime, cancel pending startup, and signal every session in that tree, including delegates outside the thread registry. Waiting covers admitted operations and session teardown, and reports cleanup or persistence writer failures. Other root trees remain unaffected; registry removal and persistence handoff remain caller responsibilities.

Retain tree membership through startup, cancelled spawn cleanup, residency eviction, and completion watchers. Release persistence resources before returning startup failures, and stop completion watchers during tree shutdown without reporting shutdown as a child result.

## Testing

Add coverage for tree isolation, children removed from the registry, delegate teardown, cancellation during required MCP initialization, aborted teardown, persistence writer failures, and successful retry after a failed resume releases its writer.

GitOrigin-RevId: a109e25adf23d20baf7595891099947050c6b6b5
2026-10-01 01:57:56 +00:00
felixxia-oai 92bc601ad6 Reuse unchanged history snapshots when resuming threads (#49600)
## Why

Resuming a thread rereads persisted history even when a preloaded snapshot is unchanged. Reusing that snapshot must still account for writes committed before writer ownership is acquired.

## What changed

- Carry optional, non-serialized revisions from stored history and model context through thread and agent resume paths.
- Validate the revision under writer ownership and reuse the shared snapshot when it matches. Reload stored history when the revision is missing or changed, while preserving explicit history overrides.
- Resolve the selected rollout before loading context, validate compressed snapshots before materialization, and enforce archived-thread restrictions on canonical paths.

## Testing

Extend coverage for snapshot reuse and late-write refresh in legacy and paginated histories, compressed rollout reuse, archived rollout symlinks, and cold child restoration that includes edits made after preloading history.

GitOrigin-RevId: e1fd7aee6ef2b30f41951e6b7e6b01c3e1420cab
2026-09-30 11:59:13 +00:00
sayan-oai 3749d1eff7 Preserve pending environments when spawning subagents (#49075)
## Why

Spawning a subagent before an environment was ready dropped the starting environment from the child's selections. The child needs to retain that environment and receive its configuration or failure when preparation finishes.

## What changed

- Pass the spawning step's environment snapshot to children, preserving ready and starting environments and configuration ownership.
- Propagate the original owner's first configuration result through descendants, applying each session's validation and leaving independently configured children unchanged.
- Preserve pending configuration waits across executor retries. Later owner updates do not overwrite the child's inherited configuration.

## Testing

Add regression coverage for fresh and forked subagents, readiness through turn-settings updates, failure propagation to children and grandchildren, child configuration precedence, and executor retries. Add a request snapshot showing a child using `wait_for_environment` before execution tools become available.

GitOrigin-RevId: a2afed740391f88d195596cfe28e418332b60d43
2026-09-28 20:42:04 +00:00
Won Park d7748e1185 Add opt-in structured errors for Guardian circuit-breaker interruptions (#48796)
## Why

Guardian denial-limit interruptions lack a structured error identifying the cause. Make this opt-in because older clients may not recognize the new error in shared history.

## What changed

- Add `auto_review.circuit_break_action = "strict"` to attach `TooManyDenials` to the interrupted turn. The default leaves the error unset.
- Expose `turn.error.codexErrorInfo = "tooManyDenials"` in app-server notifications and saved history, and update protocol schemas and generated types.
- Preserve the warning, denial limit, and interrupted status without emitting a separate error notification.

## Testing

Add an integration test covering omitted, `default`, and `strict` settings, checking warnings, live turn errors, the absence of separate error notifications, and persisted turn errors after restart.

GitOrigin-RevId: cb5d379e64728d4d7b9daf834c13756e4a70db31
2026-09-27 22:05:19 +00:00
felixxia-oai 21eb35513d Preserve independent Guardian history across parent compaction (#48779)
## Why

Guardian reviews need to retain original evidence across parent compaction when checkpoint reuse is disabled, including after resume and rollback.

## What changed

- Make disabling `guardian_reuse_parent_compaction` select a bounded, independent review transcript while preserving thread-owned authorization.
- Keep synchronous reviews and asynchronous scoring independent of parent checkpoints, and allow reviewer sessions to continue using transcript deltas across parent compaction.
- Persist transcript entries with rollback provenance while remaining compatible with older checkpoint readers and metadata-free checkpoints.
- Exclude compaction output from the transcript and synthetic summaries from rollback turn boundaries. Use acceptance ordering to remove rolled-back evidence even when persistence order differs.

## Testing

Add regression coverage for reviewer continuity, evidence retention across compaction and resume, rollback after local and remote compaction, and checkpoint serialization compatibility.

GitOrigin-RevId: fea0852cc5537372854f4a34bacb6bfda6d13e88
2026-09-27 20:15:23 +00:00
jamy-OAI 5f3180c793 Preserve model and access program pairs during compaction (#48224)
## Why

Compaction using the previous model can inherit the current turn's access program, producing a model/program pair that the server rejects.

## What changed

- Persist `cyber_access_program` in previous-turn settings and restore it during rollout reconstruction.
- Use the previous turn's access program when compacting with its model, preserving an absent program instead of inheriting the current selection.
- Pass the selected access program into local compaction prompts.

## Testing

Add regression coverage for local and remote compaction after model switches, including resume, fork, rollback, and compaction checkpoints. Verify fallback and subsequent sampling use the current model/program pair, and API-key sessions do not inherit access-program authorization.

GitOrigin-RevId: eaa7162e8711446dc9eb1bfff194e711abd54d7e
2026-09-25 22:14:19 +00:00
Owen Lin 12cb14f7b7 Default local threads to paginated history (#47900)
## What changed

- Make `LocalThreadStore` default to paginated history while retaining explicit legacy mode.
- Explicitly use paginated history for Guardian review sessions and allow in-memory stores to create paginated threads.
- Rename full-history resume, fork, and subagent helpers to identify them as legacy APIs, and document the paginated alternatives.
- Reject `thread/revert` for ephemeral threads and prevent the TUI from replaying or attaching to ephemeral agent threads.

## Testing

Add coverage for preserving the default and explicitly selected history modes and conversation context across restart, and for retaining context after rejected ephemeral reverts. Extend Guardian checkpoint coverage across both history modes and verify that saved reviews use paginated history.

GitOrigin-RevId: 870239eb3757018159ee4f230a009c97d38ac5b7
2026-09-24 18:07:37 +00:00
peilin-openai 62197a65e5 Add diagnostic reasons to MCP attribution errors (#47899)
## Why

The `attribution_error` status does not explain why MCP attribution is incomplete. Preserve a diagnostic reason so callers can distinguish history and recorder errors from request serialization failures.

## What changed

- Add optional `error_reason` diagnostics to `McpAttribution`, retaining the first recorder error through checkpoints, compaction, resume, and fork.
- Identify missing or invalid checkpoints, conflicting sources, invalid sources, and poisoned recorder state. Use `restored_error_unknown` for older error checkpoints without a reason.
- Distinguish `payload_too_large` from `serialization_failed` in request metadata fallbacks.
- Tolerate missing, unknown, or malformed diagnostic reasons when reading history, without letting diagnostics determine attribution status.

## Testing

Add coverage for reason preservation, recorder poisoning, backward-compatible checkpoint decoding, resume and cold-fork restoration, and request metadata serialization, including oversized payloads.

GitOrigin-RevId: 389b9446fae119f793978f3e7e4a926677e84d8c
2026-09-24 18:06:07 +00:00
felixxia-oai 7b66c21f58 Remove obsolete Guardian context capture mode branches (#47690)
## What changed

Remove the session-level capture mode and make thread-owned retained context the default throughout history management. Simplify input ordering, compaction identity preservation, fork handling, and approval freshness checks by removing legacy capture branches.

Keep checkpoint compatibility review separate: unknown or incompatible checkpoints can still use legacy review while retaining user evidence. Set the already-removed `guardianv2.thread_context` feature's default to false and remove redundant opt-out test variants.

## Testing

Update checkpoint tests to exercise legacy review through restored checkpoint data. Adapt existing compaction, resume, rollback, and fork tests to use unconditional context capture.

GitOrigin-RevId: ab23a0d7aca71d5a103458cff8b0c68137dd9708
2026-09-23 22:51:13 +00:00
felixxia-oai 920e1a34dc Make Guardian thread context capture unconditional (#47689)
## What changed

Always use `GuardianContextMode::ThreadOwned` for session capture and subagent history forks, regardless of `guardianv2.thread_context`. Continue selecting reviewer policy from saved checkpoints, preserving legacy review for incompatible checkpoints and removing the feature gate from reviewer compaction compatibility checks.

## Testing

Update coverage for unconditional retained context across compaction, resume, and subagent forks. Exercise legacy review with saved checkpoints, and verify that local and managed opt-outs do not disable sender context capture or checkpoint migration.

GitOrigin-RevId: cd74e2029c83f12bc655b6563242d06f29dd46af
2026-09-23 22:50:48 +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
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 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 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
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 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