## What changed
- Add a `codex-diagnostics` crate that snapshots the process ID, available
resident-memory measurements, and registered process-wide gauges.
- Provide guards that update gauges for the lifetime of measured objects.
- Track live `CodexThread` instances with the `core.threads.live` gauge.
## Testing
- Add unit coverage for gauge registration, guard lifetimes, process memory
snapshots, and live-thread reporting.
GitOrigin-RevId: 3236b086bd4ebe31ed4768ab87a5fa288b0891b0
## What changed
- Add nullable `multiAgentVersion` metadata to v2 `model/list` responses.
- Represent supported values as `disabled`, `v1`, or `v2` in the Rust API and generated JSON Schema and TypeScript exports.
- Forward the value from model catalog presets through app-server responses.
## Testing
- Extend the remote model catalog test fixture with a `v2` multi-agent version.
GitOrigin-RevId: bd3b2bbe0a3b562b4d1f03df7da2a73a35713978
## Why
Applying `project_doc_max_bytes` independently to every selected environment
allows the total project instruction payload to grow with the number of
environments.
## What changed
Treat `project_doc_max_bytes` as one shared byte budget. Consume it in selected
environment order, truncate the entry that reaches the remaining limit, and
skip later environments once the budget is exhausted.
Update the configuration descriptions to document the aggregate limit.
## Testing
Add unit and integration coverage for partial and exhausted budgets across
multiple environments.
GitOrigin-RevId: 4664bdf1f23b66986349d503f44cf51560b9024f
## What changed
- Add the `environmentConfig/read` RPC for selecting literal TOML paths from executor-local config and requirements layers.
- Return layer precedence, cloud insertion points, source and base-directory metadata, and executor home and hostname context without normalizing path-bearing values.
- Expose the operation through both remote clients and local `Environment` instances, with invalid selectors reported as invalid parameters.
## Testing
- Cover projected remote config reads and rejection of empty selectors.
GitOrigin-RevId: fee15bf833de6bcb2058d405ed5b1d5d928d7218
## What changed
- Add `load_local_config_layers` to return raw configuration and requirements layers with their sources, base directories, precedence order, and cloud insertion positions.
- Support projecting layer stacks to selected TOML paths while preserving non-table override blockers and adjusting cloud insertion positions when empty layers are removed.
- Reuse project discovery and trust handling for local reads, including linked-worktree hooks, without resolving relative paths or including profiles, session flags, thread layers, or cloud-provided values.
## Testing
- Cover layer ordering, raw relative paths, legacy requirements, trust filtering, projection semantics, and untrusted linked-worktree hook handling.
GitOrigin-RevId: a1098af5650ac44e5a230ba9a5fe918927986d05
## What changed
Rename `features.tool_registry.include_tool_namespaces_info` to
`features.tool_registry.include_tool_metadata` across configuration parsing,
schema generation, resolved configuration locking, and tests. Update its
description to cover authoritative tool information in request metadata.
GitOrigin-RevId: 93b404483b71fed04031d767a41ac2bb70b836b2
## What changed
- Add `features.tool_registry.include_tool_namespaces_info` to the TOML model,
generated schema, and resolved runtime configuration. The setting defaults to
`false` and controls whether per-turn request metadata includes the resolved
tool namespace inventory.
- Preserve the resolved setting in session configuration locks.
- Cover top-level and profile-scoped strict configuration, deserialization,
resolution, and lock-file persistence.
GitOrigin-RevId: 74124086c0d7de30094b411001f0ec0af490935d
## What changed
- Add an Active/Archived status control to the resume picker and use it when listing sessions.
- Restore an archived session before resuming it, with inline error handling and duplicate-request prevention while restoration is pending.
- Keep directory filtering available for archived sessions and hide the archive shortcut while viewing them.
## Testing
- Add coverage for archived-session filtering, successful restoration, failure and retry behavior, toolbar rendering, and keyboard navigation.
GitOrigin-RevId: db3f5935e0f0bba12a110ba9c7aaf9d40abd4a4f
## What changed
- Add a `Ctrl+A` action and footer hint for archiving the selected session in the resume picker.
- Send archive requests through the app server, remove successfully archived sessions from the picker, and surface failures inline.
- Prevent duplicate actions while an archive is pending, preserve configured keybindings, and direct users to `/archive` when they select the current session.
- Ignore archive notifications for untracked side threads so they do not appear in agent navigation.
## Testing
- Cover successful, repeated, rejected, and failed archive requests, shortcut conflicts, footer rendering, and untracked-thread notifications.
GitOrigin-RevId: 20ea21c804a9685e46484d67df967859f9be4651
## What changed
- On cold `thread/resume`, restore the latest approval policy from persisted
thread settings instead of falling back to the current configured default.
- Preserve the precedence of an explicit request override over the persisted
policy.
- Account for settings applied during a turn when the subsequent compacted turn
context contains a stale policy.
## Testing
- Add unit coverage for selecting the latest persisted policy.
- Add app-server tests for legacy and paginated history, including explicit
resume overrides.
GitOrigin-RevId: 9127a3c53a90f16d67957ded9e7430e79180fc60
## What changed
- Add `codex exec fork <SESSION_ID> [PROMPT]` for creating a new thread from
an existing session ID or thread name.
- Allow creating the fork without starting a turn, or immediately continue it
with a prompt and optional images.
- Preserve the source thread ID in the emitted session configuration while
leaving the source session unchanged.
## Testing
- Add CLI parsing coverage and an end-to-end test for promptless and prompted
forks, thread naming, copied history, and unsupported promptless options.
GitOrigin-RevId: b8f28b238a1526cc486c5beb886a63f68b8e7986
## Why
A local stdio MCP server can exit while its descendants remain alive. Cleaning up
only the server process can therefore leak processes after client shutdown.
## What changed
- Contain locally launched MCP servers in non-breakaway Windows job objects and
terminate the job during shutdown so descendants exit with the server.
- Preserve compatibility when job creation or assignment is unavailable by
retrying without containment and terminating an owned process handle instead.
- Use the process-group member fallback when terminating piped processes on
macOS.
## Testing
- Cover descendant cleanup and breakaway prevention for both local MCP protocol
modes on Windows.
- Cover the Windows nested-job assignment fallback and verify the suspended
process resumes before handle-based termination.
GitOrigin-RevId: 33d3cc122de8f7ce0ae69a649b12ea0ff64b7c6f
## What changed
- Parse `mcp_tool` hook handlers with a server, tool, JSON input, and optional timeout and status message.
- Return managed MCP tool hooks from `configRequirements/read` and include the handler in the generated protocol schemas.
- Skip MCP tool hooks during discovery with an explicit warning until execution is supported.
## Testing
- Cover MCP tool hook deserialization, including nested and null JSON input values.
- Extend the config requirements RPC test to verify the new handler shape.
GitOrigin-RevId: ff7e2d12b75b486c54d63469af547a29f9b31418
## What changed
- Show `Ask Codex to do anything` in the main conversation input.
- Show `Ask a follow-up question` in side conversation inputs.
- Remove randomized example prompt selection and update the side conversation snapshots.
GitOrigin-RevId: 2f6d310cf80bfa9743b7695621892a821eda4a18
## What changed
- Add `/export` with clipboard and file destinations, including a default filename prompt and support for an explicit path argument.
- Export the complete conversation history as structured Markdown, preserving user and assistant messages, plans, reasoning, activity, image labels, file changes, and MCP tool details while honoring reasoning visibility.
- Fall back to legacy history loading when pagination is unavailable, and use the visible transcript for ephemeral sessions.
- Resolve relative and home-relative paths without overwriting an existing file, and report export or copy results in the conversation.
## Testing
- Cover Markdown rendering, hidden review prompts, activity details, complete paginated and legacy history loading, destination prompts, status messages, path resolution, and overwrite protection.
GitOrigin-RevId: c2815fc2430d7a555da75d7038cc1ac08157b82e
## What changed
- Clamp `wait_agent` timeout requests below `min_wait_timeout_ms` instead of rejecting them.
- Include the timeout adjustment in the wait result message and document it in the tool output schema.
## Testing
- Update the handler test to verify the configured minimum is honored and the adjustment is reported.
- Update the schema test for the expanded result message.
GitOrigin-RevId: 2b4a770ed6d1e9c45b351b479f5ae50c9a3d5388
## What changed
- Honor `CODEX_AGENT_IDENTITY_AUTHAPI_BASE_URL` and
`CODEX_AGENT_IDENTITY_JWKS_BASE_URL` when registering and verifying agent
identities.
- Normalize override values by trimming whitespace and trailing slashes.
- Preserve ChatGPT environment validation, while allowing a custom launcher
configuration when its ChatGPT and JWKS base URLs match and an AuthAPI
override is explicitly configured.
## Testing
Added coverage for explicit staging overrides, custom launcher compatibility,
and rejection of overrides that would bypass environment validation.
GitOrigin-RevId: c557c8167ec101c2993f65aad3fcb3bf25785d51
## Why
App-server integration tests can encounter a transient `ExecutableFileBusy`
error while starting their server process.
## What changed
Retry that specific spawn failure up to twice with a 10 ms delay, while
returning all other spawn errors immediately.
GitOrigin-RevId: 0982a9fe66bae4c41f556c845d12fb515dbf752c
## What changed
- Add `features.code_mode.default_exec_yield_time_ms`, defaulting to 30 seconds.
- Apply the configured default to code-mode `exec` calls that omit `yield_time_ms` and reflect it in the tool description.
- Remove the `code_mode_buffered_exec` compatibility feature flag.
## Testing
- Cover config loading and tool descriptions for both default and custom yield timeouts.
GitOrigin-RevId: 581ffc737b04721c7b5fc81260b1da1cf7d87523
## What changed
- Add `ThreadManager::with_thread_id_generator` to configure ID allocation for new root, child, and forked threads.
- Keep the standard UUIDv7 generator as the default and preserve stored IDs when resuming threads.
- Add `ThreadId::from_u128` for constructing identifiers from UUID-compatible values.
## Testing
- Cover default allocation, custom IDs across roots, child agents, and forks, and ID preservation on resume.
GitOrigin-RevId: 6c38c862e30a50bad944a994bcbccf7d1e7ada24
## Why
Binding the full host filesystem into a network-isolated Bubblewrap sandbox also
inherits the host's device tree.
## What changed
- Overlay `/dev` with Bubblewrap's minimal device filesystem while preserving
the root bind's `nodev` behavior.
- Bind `/dev/shm` back into the sandbox when available so host and sandbox
processes can continue to share memory files.
## Testing
Add a managed-proxy integration test that verifies standard device nodes remain
usable, `/dev` is not the host directory, and `/dev/shm` writes are shared with
the host.
GitOrigin-RevId: 1d91fe44affd792d2777adae8f2cce6d85d14103
## What changed
- Add `codex migrate-rollouts` with dry-run inspection by default, explicit `--apply`, thread filtering, optional I/O throttling, progress output, and JSON or verbose reports.
- Add the disabled-by-default `background_paginated_rollout_migration` feature to migrate legacy local sessions at startup before rollout compression begins.
- Persist a migration cursor and skipped-file fingerprints so later startups avoid full rescans while retrying changed files and recovering pending migrations.
- Coordinate migration with live writers and emit metrics for manual and startup runs.
## Testing
- Cover startup cursor advancement and lookback, pending migration recovery, live-writer coordination, changed empty rollouts, and progress reporting.
GitOrigin-RevId: 276ac506c50ebec5140fd319faca1bb998172061
## Why
Forked subagents can inherit a parent's compacted history, but their context-window metadata needs to identify the child and start a distinct window lineage.
## What changed
- Always identify context windows by agent name and remove the `features.token_budget.mode` setting.
- Persist the agent path in world state and emit context-window metadata as a standalone developer message when the identity changes.
- Reset inherited compaction metadata to the forked subagent's initial context window and restore that window in session state.
## Testing
Extend the full-history subagent test to verify parent and child world-state snapshots, agent identities, distinct window IDs, and the reset child checkpoint.
GitOrigin-RevId: 6584201e57b3d2fba0ce626b89a8b3b0b3c752db
## What changed
- Add an `x-codex-routing-hint` header containing the request model and, when selected, the service tier.
- Send the hint on Responses HTTP requests, remote compaction requests, and WebSocket handshakes, including prewarm connections.
- Limit the header to Codex-backend authentication with the OpenAI provider, omitting it for API-key and provider-specific credential paths.
## Testing
- Cover routing hints for HTTP, remote compaction, WebSocket streaming, and tiered prewarming, along with the credential paths where the header must be absent.
GitOrigin-RevId: d8d415d7fadddecf9a132d05920b856a35ac9960
## Why
Subagents can leave cached MCP servers deferred indefinitely, causing the TUI to keep showing MCP startup as running after every server that reported startup has settled.
## What changed
- Clear configured MCP startup expectations for active subagent threads so their status is driven by actual startup notifications.
- Preserve configured-server startup tracking for primary threads and side conversations.
## Testing
Add coverage for active and resumed subagents with deferred servers, plus the existing side-conversation behavior.
GitOrigin-RevId: 4d929a162dd067b4a76351652a764a79ce60f31f
## Why
Bazel test binaries can reside on a different filesystem from the default
temporary directory, forcing executable staging to fall back from hard links to
expensive copies.
## What changed
Create the app-server test install layout under Bazel's `TEST_TMPDIR` when it is
set. Continue using the default temporary directory outside that environment.
GitOrigin-RevId: 63172fbf913ddba06c7b9543b5bf0fea249c903c
## Why
Converting each environment's working directory to a host-native path caused
turn-input contributors to omit environments with foreign path formats.
## What changed
- Expose `TurnInputEnvironment.cwd` as a `PathUri`.
- Pass every turn environment to contributors without host-path conversion.
## Testing
Added an integration test that submits a foreign working-directory URI and
verifies the contributor receives the environment unchanged.
GitOrigin-RevId: a122526be47f5331614381e9c6e4b85087a96bed
## What changed
- Recognize structured `visualize` content references alongside the existing inline visualization directive in cached, streaming, and finalized TUI rendering.
- Resolve absolute visualization paths only when they belong to the active thread directory, and show the existing unavailable fallback for incomplete, invalid, or out-of-scope references.
- Let embedded visualizations inherit host color, typography, and radius tokens while retaining standalone defaults and legacy aliases. Keep Lucide icons at a stable size when model-authored chart styles are present.
## Testing
- Cover content-reference fallback, replay, render-cache bypass, and canonical streaming behavior.
GitOrigin-RevId: 887d13647df11c23d519e64d0958fdc41ef3f472
## What changed
- Remove the separate deferred registration handle, direct readiness publisher,
and Noise environment upsert API from `EnvironmentManager`.
- Use `report_environment_provisioning_status` and
`materialize_pending_noise_environment` as the provisioning flow while keeping
ordinary environments isolated from provisioning reports.
- Cover readiness updates, invalid reports, duplicate materialization, and
conflicts with ordinary environments in the deferred environment tests.
GitOrigin-RevId: d14207c0abb0636d331be4f875fec6e53f3d2fe6
## Why
An account change can select different OpenTelemetry collector settings. The
long-running app server needs to stop exporting telemetry with the previous
account's configuration.
## What changed
- Rebuild and install the log, trace, and metrics exporters when authentication
changes, and shut down the previous provider without blocking the app server.
- Make cached global metrics clients and the tracing layer follow the replacement
provider so existing callers continue exporting through the current account's
configuration.
- Clear the cached cloud configuration loader after login and logout so telemetry
reloads from the new account context.
## Testing
- Add an app-server integration test that switches accounts and verifies logs,
traces, and metrics reach the new collector while trace context is preserved.
- Add a metrics test covering cached clients after provider replacement.
GitOrigin-RevId: a74359777a35edbee5bbe0b2baccc155074cb172
## What changed
- Build connector install URLs from `CODEX_APP_SERVER_CHATGPT_BASE_URL`, falling back to `https://chatgpt.com` when it is unset.
- Strip a trailing slash or `/backend-api` suffix before appending the `/apps/<slug>/<connector-id>` path.
- Add a test covering install URL generation with the configured origin.
GitOrigin-RevId: 854d15b7e322d2359684f974aaf27fe28205dd5a
## Why
An OAuth-backed Streamable HTTP MCP server can fail startup when its stored credentials are rejected. If a client then completes OAuth sign-in and replaces those credentials, the failed server needs to become available without restarting the Codex session.
## What changed
- Track the credential store and OAuth tokens used for each MCP connection, and detect replacements after authentication failures.
- Refresh affected MCP servers before the next turn and include their recovered tools in the model request.
- Classify HTTP authentication challenges and rejected refresh tokens as requiring reauthentication, with sign-in guidance appropriate to local and client-managed environments.
## Testing
- Cover recovery from expired credentials through an externally written replacement token.
- Cover authentication-error classification, startup messaging, and `Auto` store migration from file credentials to the keyring.
GitOrigin-RevId: 9b090089d4e7a44ffc182f4e25da20a18e97b70f
## Why
Environment readiness can change between sampling requests. Extension turn-input contributors should receive the same refreshed environment snapshot used by the current step.
## What changed
Build `TurnInputContext.environments` from `StepContext` so newly ready environments are included in extension input for the current request.
GitOrigin-RevId: ee4444072162317974cd2bbfd57ffcf9a9445391
## Why
During inline-mode resize reflow, replayed history can overlap a zero- or
one-row history region and leave stale terminal characters visible in the
composer. Resetting the previous render buffer is insufficient because
default-style spaces may still compare equal and be skipped.
## What changed
- Mark every cell in an invalidated viewport for unconditional repainting.
- Invalidate the viewport after flushing pending history when history can
overlap it.
## Testing
Add regression coverage for repainting spaces over stale cells and a manual
`tmux` resize smoke test for preserving visible multiline draft text.
GitOrigin-RevId: 5a8a480e2fc50c801561de6a4598a3ab8c12b8d6
## Why
Checking the tool search cache currently rebuilds search metadata for every deferred tool, even when an immutable tool runtime has not changed.
## What changed
- Track immutable deferred tools by runtime identity and dynamic tools by their current search metadata.
- Rebuild the search handler when the deferred registry, dynamic metadata, or source-listing mode changes.
- Keep only weak references to immutable runtimes in the cache.
## Testing
Added unit coverage for immutable handler reuse, registry and exposure changes, source-listing changes, and refreshed dynamic tool metadata.
GitOrigin-RevId: 024c6f4498d431e7bbfaecde420f77fcf8c0dba7
## Why
MCP tool handlers and their Code Mode definitions are immutable for the lifetime
of a stable MCP binding, so rebuilding them for every sampling step repeats schema
construction unnecessarily.
## What changed
- Cache MCP handlers per session and reuse them while the same binding remains
active, invalidating the cache when the binding changes.
- Lazily cache schema-free Code Mode definitions on MCP handlers while continuing
to rebuild definitions for step-local tools whose specifications may change.
- Reapply current app enablement, tool policy, exposure, and plugin schema budgets
whenever cached handlers are registered for a step.
## Testing
- Cover handler and Code Mode definition reuse, binding invalidation, changing app
policy, stable continuation schemas, and step-local custom tool updates.
GitOrigin-RevId: 69c5011fb97c08580ac476e7fb2286b1e92e0359
## What changed
- Carry plugin identity, namespace, root, and discovery mode through host skill loading.
- Apply the owning plugin namespace and IDs to loaded skill metadata.
- Respect direct-child discovery for Agent Plugins and reject skills that resolve outside the plugin root or are not regular files.
- Preserve recursive discovery and symlink behavior for legacy plugin roots, and allow the full 64-character namespace plus 64-character skill name.
## Testing
Add host-loader coverage for plugin metadata, namespace ownership, direct-child filtering, path containment, recursive symlinks, shared assets, and maximum-length qualified names.
GitOrigin-RevId: cdde821643ce39bd030d0c3753b3304b75161690
## Why
Subagents can reuse cached MCP tool definitions without starting every optional
server before any of its tools are used.
## What changed
- Defer startup for subagent-owned, optional MCP servers when their cache has at
least one visible, allowed tool, and trigger startup on the first operation
that needs the live client.
- Keep root sessions, required servers, selected plugin servers, and explicit
reconnects eager.
- Exclude empty catalogs from cache eligibility and keep dormant servers out of
the initial startup summary.
## Testing
- Extend MCP tool-cache coverage for eager root startup, unused and filtered
subagent servers, deferred startup status events, and startup that survives an
interrupted first tool call.
GitOrigin-RevId: e7528ff08312583a6747cbc6550ea5b6eabda9a6
## Why
A model switch on the first turn has no prior turn settings to compare, and rolling that turn back could leave its model instructions in history.
## What changed
- Track the model that supplied the session's base instructions so first-turn switches inject the target model's instructions, including the selected personality.
- Preserve inherited custom base instructions when starting from an empty fork.
- Remove first-turn model-switch developer content during rollback so retries and cold resumes do not retain or duplicate stale instructions.
## Testing
Add integration coverage for first-turn switches, personality changes, empty-prefix forks, rollback retries, and cold resume.
GitOrigin-RevId: 9df532e9e337521ad3b315b77f8c98e039fb384e
## Why
Multi-agent v2 rejected `agent_type` when `fork_turns` was `all`, forcing callers to choose between a configured role and the parent's full conversation context.
## What changed
- Apply an explicitly selected role to full-history forks, including its model and developer instructions.
- Preserve the parent's developer instructions when the selected role does not define its own.
- Keep the inherited conversation history and model-switch context intact.
- Update the `spawn_agent` schema to clarify that roles apply independently of history inheritance.
## Testing
- Cover full-history role overrides and developer-instruction precedence in multi-agent v2 tests.
GitOrigin-RevId: cd4f35e31d75f56289760f245bff38dd0233abe6
## What changed
Extend the executor-backed Streamable HTTP timeout test to cover both legacy
`initialize` and MCP 2026 `server/discover` requests. Verify that each stalled
handshake times out and releases the serial executor for subsequent requests.
GitOrigin-RevId: 3493904433c95265b9f645813723e890b7610abb
## Why
MITM hooks authorize requests before the upstream server parses them. Paths that
can be decoded or normalized to a different resource must not match an allowed
path, and hosts that require MITM inspection must not bypass it through the
plain HTTP proxy path.
## What changed
- Reject ambiguous hook paths, including traversal segments, backslashes,
malformed percent encodings, and encoded separators or percent signs.
- Block plain HTTP proxy requests for hosts whose policy always requires MITM,
recording the decision as `mitm_required`.
## Testing
- Cover safe and ambiguous path forms, encoded traversal through repository
allowlists, and absolute-form HTTPS requests sent to the HTTP proxy.
GitOrigin-RevId: 8812a980ac64a97cbac3a237376d29be5ded9220
## What changed
- Fetch the paginated installed-plugin snapshot without a `scope` query instead of issuing separate requests for global, user, and workspace plugins.
- Use the combined snapshot for installed-plugin caching and bundle synchronization while continuing to reconcile each scope's marketplace independently.
## Testing
- Cover pagination across mixed scopes, request query parameters, marketplace reconciliation, stale cache cleanup, and discoverable-plugin filtering.
GitOrigin-RevId: 7428a9db81d7ec04e65cc4b236b652278b200956
## What changed
- Add the gated `unified_image_budget` feature for models that support original image detail or Responses Lite.
- Apply one 6,000-pixel, 10,000-patch preprocessing limit regardless of legacy image detail hints.
- Hide detail controls from `view_image` and code mode while continuing to accept existing hints for compatibility.
- Preserve detail-based resizing and tool contracts for unsupported models.
## Testing
- Cover unified resizing limits, Responses Lite, legacy detail hints, unsupported models, and `view_image` integration in code mode.
GitOrigin-RevId: cb07bff1669a96599fdfd076b3d9ec80f2b6fff7
## What changed
- Add a storage-neutral queue extension for listing, adding, editing, reordering, deleting, and explicitly starting queued user messages.
- Dispatch queued messages in FIFO order when a thread becomes idle after a completed turn, while leaving them queued after interruptions or failures.
- Wait for user input to be persisted before removing its queue item, and report hook rejection, task termination, and persistence failures distinctly.
- Snapshot local image and audio attachments into validated data URLs before storing them, enforce input limits, and emit `ThreadQueueChanged` events after mutations.
## Testing
- Cover queue mutations, automatic and explicit dispatch, interruption and failure behavior, hook rejection, invalid records, input limits, and local attachment snapshotting.
GitOrigin-RevId: 14f39d7c8cbaccb767a6da84b82cced0edfcb4b9
## What changed
- Emit `codex_thread_archive_event` when a thread is successfully archived or
unarchived, including the thread ID, action, and producer timestamp.
- Route archive notifications through the analytics client while preserving
normal app-server notification delivery.
## Testing
- Extend app-server coverage for archive and unarchive analytics, including
descendant archives and a repeated archive request that fails without
producing another event.
GitOrigin-RevId: 0d973c232fd795b7cd6cddd47ecc9446234c44dd
## Why
The `cwd` recorded in a rollout can become stale after thread metadata is
updated, causing thread reads and lists to disagree with the persisted state.
## What changed
- Overlay a non-empty state database `cwd` when reading a thread by ID.
- Apply the same overlay when reading by rollout path, but only when the
metadata points to the requested rollout.
- Recompute the permission profile against the selected `cwd` and continue to
fall back to rollout metadata when the persisted `cwd` is empty or belongs to
another rollout.
## Testing
- Cover stale, empty, and mismatched persisted `cwd` metadata.
- Verify that `thread/read`, state-only `thread/list`, and `thread/resume`
report the persisted thread `cwd` while the resumed session uses its requested
live `cwd`.
GitOrigin-RevId: 50a3f187618ee3cadbad95196ee2976e2d5e9a5a
## Why
Legacy rollouts can contain historical rollbacks, compaction checkpoints, and
subagent copies of parent history. Migrating those records verbatim can change
the visible conversation or the model context used when a thread resumes, and
can retain large amounts of duplicated subagent history.
## What changed
- Plan and replay historical rollbacks by logical turn, preserving surviving
lifecycle events and the correct compaction anchor for future resumes.
- Migrate subagent rollouts from a safe bounded replay when possible and record
the history boundary so copied parent context is not projected as child turns.
- Include archived and compressed rollouts while keeping their storage form and
location intact.
- Tolerate malformed, partial, oversized, and empty JSONL records during the
migration scan.
## Testing
Add coverage for rollback and compaction combinations, subagent replay bounds,
archived and compressed rollouts, recovery, concurrent maintenance, and damaged
JSONL input.
GitOrigin-RevId: 3948e16d43f75df8571b0a92af12a181d1d08fdf
## What changed
- Add a Guardian circuit-breaker policy for models whose catalog specialty is
`cyber`.
- Interrupt those models after the first Guardian denial while retaining the
existing denial thresholds for other models.
- Centralize the `cyber` model-specialty identifier for use across core,
protocol, app-server, and TUI code.
## Testing
- Cover the cyber-specific threshold in the circuit-breaker unit tests.
- Verify end to end that a denied command is not executed and the turn is
interrupted after one denial.
GitOrigin-RevId: fad24c9e7aa280432580db1f0e39d13535779710
## Why
Resumed sessions need the current multi-agent usage instructions when configuration changes or the saved history predates usage-hint tracking.
## What changed
- Store multi-agent usage hints in world state and refresh changed or previously untracked hints before re-emitting the active multi-agent mode.
- Present `wait_agent` polling guidance in the overridable developer instructions only when the tool is enabled, instead of embedding it in the tool schema.
## Testing
- Cover cold resumes, changes to `wait_agent` availability, custom usage hints, message ordering, and tool-schema behavior.
GitOrigin-RevId: a9c6798d5dc2dedc8dadc49e0a80ff50a757ab83
