## What changed
- Add the `apply_patch_preserve_line_endings` feature, disabled by default, to
preserve CRLF, CR, and mixed line endings when `apply_patch` updates files.
- Apply the feature consistently to built-in patch handling and patches invoked
through shell, user-shell, unified-exec, and app-server command execution.
- Keep the active feature configuration authoritative over inherited, shell
snapshot, and client-provided environment values.
## Testing
- Cover line-ending behavior with the feature enabled and disabled for custom
tool calls, shell heredocs, command execution, and the `apply_patch` CLI.
GitOrigin-RevId: 531a7c66761959c650270559f57941929f03e6c4
## Why
Deferred environments can become ready after a turn starts. Guardian approval
reviews must use the environment selected for the current step so their working
directory and permission context are not taken from the stale turn snapshot.
## What changed
- Carry `StepContext` through tool execution and approval handling.
- Add a Guardian review context that pairs the parent turn with the current
step's environment snapshot.
- Use that snapshot for Guardian prompts, reviewer sessions, and delegated
reviewer threads while retaining turn-level fallbacks for callers without a
step context.
## Testing
Added an integration test that makes a deferred remote environment ready before
an escalated command and verifies Guardian receives that environment's working
directory and denied-read policy instead of the initial local environment's.
GitOrigin-RevId: 779096bc7d0e0c7453a009c02141029714b9b407
## Why
Hook configurations can mark command handlers as asynchronous, but Codex previously skipped those handlers outside `SessionEnd`.
## What changed
- Run asynchronous command hooks in the background with a per-session concurrency limit, while keeping `SessionEnd` hooks synchronous.
- Prevent asynchronous hooks from blocking, stopping, rewriting, or otherwise controlling the operation that launched them.
- Deliver warnings and additional context at safe turn boundaries: inject results into an active turn after sampling, or buffer them ahead of the next user prompt when the session is idle.
- Preserve in-flight hooks across configuration reloads, scope spilled output to the thread, and abort outstanding work during session shutdown.
## Testing
Add unit and integration coverage for background scheduling, concurrency, output parsing, active and idle result delivery, configuration reloads, and shutdown cleanup.
GitOrigin-RevId: 8094552e4afe7b47b09a61bb575bb20f4e491d8d
## What changed
- Filter saved `allow` prefix rules from the execution policy for cyber-specialized models and models listed in `auto_review.ignore_rules`, while preserving prompt, forbidden, network, and host-executable policy entries.
- Apply the filtered policy consistently to permission instructions, shell commands, unified exec, and the zsh-fork backend.
- Limit cyber-model command approvals to one-time decisions without proposing reusable policy amendments. General models continue to honor saved prefixes, including after switching models within a thread.
## Testing
- Add policy-level coverage for filtering allow-prefix rules while retaining restrictive and network rules.
- Add end-to-end coverage across shell and unified exec paths, zsh-fork execution, user and automatic review, and model switching.
GitOrigin-RevId: f3bd3872424291b12354ec415f33986ec369a368
## What changed
- Add the managed `auto_review.required_on_models` requirement, unioning model slugs across requirement layers and exposing the result through `configRequirements/read`.
- Force listed models to use `on-request` approvals with the `auto_review` reviewer. Downgrade Full Access to workspace-write when starting a protected session, and reject incompatible runtime overrides or use when automatic review is disabled.
- Preserve these protections across thread starts, resumes, forks, model changes, turn overrides, MCP approvals, and TUI session attachment.
## Testing
- Add coverage for layered model requirements and exact provider-alias matching.
- Add app-server tests for protected thread lifecycle operations, unsafe setting overrides, legacy thread upgrades, disabled automatic review, and requirements API output.
GitOrigin-RevId: c4b1d52c3b5b75e86880725412b8f0812e0dfcd9
## What changed
- Add the effective permission profile as `sandbox_mode` in turn metadata for regular, prewarm, compaction, and detached memory requests.
- Reserve `sandbox_mode` so client-provided metadata cannot override the computed value.
## Testing
- Cover metadata headers and request bodies for read-only and danger-full-access modes.
GitOrigin-RevId: 13c690cc99bc2691023f281ca527af049bb1286f
## What changed
- Add `HostSkillsSnapshot::load_skill_prompts` so the skills extension owns reading and rendering selected host skills.
- Keep explicit invocation telemetry, unreadable-skill warnings, plugin prompt ordering, and suppression of host prompts superseded by provider prompts.
- Remove the legacy prompt injection and fragment implementation from `codex-core-skills`.
## Testing
- Cover prompt truncation without an installed skills extension, skill/plugin ordering, selective provider supersession, unreadable skills, and contextual fragment detection.
GitOrigin-RevId: 9c8b84ad54b90d174abc287ab49cc5a231e9e1aa
## What changed
- Stop adding `code_mode_tool_names` to Responses Lite turn metadata.
- Keep `code_mode_tool_names` reserved so client metadata cannot reintroduce the removed, unbounded inventory.
- Use the opt-in `tool_namespaces_info` metadata, including each function's `code_mode_name`, when authoritative tool details are requested.
## Testing
- Update Responses Lite and code-mode tests to verify the opt-in namespace metadata and normalized code-mode names.
GitOrigin-RevId: cbfb9af984de71c7cc175d0cd47ae799a5275309
## What changed
- Add opt-in `tool_namespaces_info` metadata for Responses Lite turns when
`tool_registry.turn_metadata_includes_tool_info` is enabled.
- Describe each model-visible function's namespace, direct and deferred
exposure, Code Mode name, and harness or MCP ownership.
- Reject visible namespaces shared by different owners when strict collision
checking and tool inventory metadata are enabled.
- Keep tool inventories out of compatibility headers and metadata sent to MCP
servers.
## Testing
- Cover opt-in behavior, MCP exposure details, namespace ownership collisions,
reserved metadata handling, and Responses Lite request serialization.
GitOrigin-RevId: 6a6965d2ba98e29444fdfbb4ccec6aafcf0391e6
## Why
Long executor and orchestrator resource identifiers can consume enough of the
skills context budget to omit otherwise available skills.
## What changed
- Add source-aware root aliases for executor, orchestrator, and host skill
catalogs, including catalogs with a single shared root.
- Select the best combination of aliased catalogs under the shared metadata
budget while accounting for root tables and alias usage instructions.
- Explain how to expand shortened `skill://` locators and accept the resulting
description-shortening warning in app-server coverage.
## Testing
- Add rendering and production-turn coverage for singleton, executor,
orchestrator, host, and combined catalog aliases.
GitOrigin-RevId: c1bc1f3d371eae9526232674060235272cc28f16
## What changed
- Classify HTTP connection failures separately from other network errors without exposing request URLs.
- For sampling requests, retry connection failures with exponential delays from 5 to 60 seconds and show a `Reconnecting... waiting for network` stream error.
- Preserve the normal stream retry budget while waiting for the provider to become reachable. Keep the existing bounded retry behavior for other retryable errors.
## Testing
- Verify connection errors are classified without leaking URL contents.
- Verify a turn recovers after its provider becomes reachable and still applies the configured retry limit to a subsequent incomplete stream.
GitOrigin-RevId: 646553290c865a1332abd30c4a64ed9266bbfc6f
## Why
Interrupting a turn should also stop code-mode work that the turn left running.
## What changed
- Add the disabled-by-default `code_mode_interrupt` feature.
- When an interrupted turn has the feature enabled, terminate all active code-mode cells and propagate cancellation through nested tool calls.
- Keep the reusable code-mode session alive so its stored state remains available to later turns.
## Testing
Add an integration test that interrupts a long-running nested tool, verifies that active and background cells are removed, and confirms that session state is preserved.
GitOrigin-RevId: 2b8634776a89b636318a39b9e9ad2eefc07cead8
## What changed
- Preserve executor-native working directories, workspace roots, and permission profiles when preparing remote `exec_command` requests instead of resolving them through the host platform.
- Send sandbox intent to the remote executor, including a restricted-token default for Windows executors and `-NoProfile` for elevated PowerShell commands.
- Reject intercepted cross-platform `apply_patch` commands when filesystem writes are restricted, while continuing to allow them for unsandboxed or full-disk-write profiles.
## Testing
Extended remote unified-exec coverage for foreign Windows workspaces, elevated PowerShell, sandbox metadata, and restricted and unrestricted intercepted patches.
GitOrigin-RevId: 9fd328879fa2c15594fd58e40b6b32e8ba0847e7
## What changed
- Add the tool call ID to `_meta.callId` for every MCP tool request.
- Rename `features.tool_registry.include_tool_metadata` to
`features.tool_registry.turn_metadata_includes_tool_info` to clarify that the
setting controls authoritative tool information in per-turn metadata.
- Update config parsing, schema generation, and session config locking for the
renamed setting.
## Testing
- Cover `callId` metadata for custom, plugin, and Codex Apps MCP calls.
- Update strict-config, config-loading, feature-config, and config-lock tests for
the renamed setting.
GitOrigin-RevId: ac0e58c489b03bd9b55a356f545de86c8ecaf865
## Why
Plugin suggestions should report skills only when the plugin has an enabled skill.
## What changed
- Load suggestion metadata through the shared plugin skill-root loader.
- Apply skill configuration when setting `has_skills` on suggestion candidates.
## Testing
Added coverage for local plugin suggestions with the plugin skill both enabled and disabled.
GitOrigin-RevId: bceb14528c9042b474eaad6efaf919bef72e0ca4
## Why
Persisted base instructions need to retain whether they were explicitly customized or generated from a model template. Without that distinction, forks and config-lock replays can treat model-generated instructions as custom and keep the wrong template after a model or personality change.
## What changed
- Record custom or model provenance with base instructions in rollouts and config locks.
- Preserve custom instructions across model changes, while allowing model-generated instructions to follow the selected model and personality.
- Keep legacy rollouts without provenance compatible and propagate provenance through forks and spawned agents.
## Testing
- Cover provenance serialization and legacy rollout decoding.
- Cover role personality changes, forked model changes, config-lock replay, and multi-agent configuration.
GitOrigin-RevId: 801c26559835f558027ce5112700c0cd31fcb21b
## What changed
- Inject the host skill loader into `PluginsManager` so plugin discovery and agent turns use the same loading and product-policy behavior.
- Share plugin skill snapshots across those paths, preserving a consistent view of skills across workspaces.
- Apply migrated-command precedence after product filtering, allowing an eligible migrated command to replace a filtered native skill with the same name.
## Testing
- Add coverage for product-restricted plugin skills, native-versus-migrated command precedence, and the skills exposed to agent turns.
GitOrigin-RevId: f5ef0d0766ebeeb30d73ffaf044d003c2906ea4d
## 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
## 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
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
## 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
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
## 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
## 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
- 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
## What changed
- Move tool mention parsing, skill-name counting, and implicit invocation detection into `codex-skills` and expose them through its public API.
- Decouple implicit invocation detection from `SkillLoadOutcome` with an `ImplicitSkillLookup` trait, while preserving the existing `core-skills` interface through re-exports.
- Cover remote plugin attribution for both implicit `SKILL.md` reads and skill script runs.
GitOrigin-RevId: f3da85c9821868638ccfd2fc2e01e0869d2fd437
## What changed
- Add `session_source()` to `McpServerContributionContext` for thread-scoped MCP resolution.
- Propagate each thread's `SessionSource` through initial setup, per-step resolution, and runtime refreshes.
## Testing
- Verify global contexts omit the source while thread-scoped contexts retain it.
- Verify MCP contributors observe distinct sources for a root thread and its spawned subagent.
GitOrigin-RevId: 23da1509858e023fbd9e2d179034ddc83553f17b
## What changed
- Load ordinary recursive host skill roots with the skills extension's host loader.
- Keep plugin-specific roots on the existing loader so plugin snapshot caching and namespacing continue to work.
- Merge both kinds of root snapshots through the existing precedence and deduplication logic, including discovery paths and source filesystem mappings.
- Move `HostSkillsSnapshot` into the skills extension as the owner of host skill loading.
## Testing
- Cover merged host and plugin catalogs, precedence for symlinked roots, discovery paths, and end-to-end rendering and invocation of host, repository, and plugin skills.
GitOrigin-RevId: c18080afb917c33c57bc17e36b40dd0f3c72d1d7
## What changed
- Add end-to-end coverage for a remote environment whose provisioning status is
reported ready before it is selected for a turn.
- Verify that `wait_for_environment` makes remote execution tools and selected
capability-root context available once the transport is ready.
- Update pending-environment and relay tests to cover separate materialization
and readiness reporting, including deferred connection and reconnection.
GitOrigin-RevId: d86d66e8f722e9bafac88b93d93e7c5244a7156e
## What changed
- Move the orchestrator skill catalog from thread context into its own
`orchestrator_skills` world-state section so unchanged catalogs remain
incremental across turns.
- Discover executor, orchestrator, and host catalogs together and render them
against one context-window-aware metadata budget, preserving executor entries
before orchestrator and host entries under pressure.
- Emit catalog metrics and budget warnings when each world-state section is
rendered.
## Testing
- Cover incremental orchestrator catalogs across production turns, combined
catalog budgeting, disabled and unavailable providers, caching, warnings, and
metrics.
GitOrigin-RevId: a0fb25d39dcaf43c978aff9da7972a1206f736e4
## What changed
- Add `include_apps_usage_instructions` to model metadata, defaulting to true for compatibility with existing metadata.
- Emit generic Apps guidance only when apps are available and the selected model enables it.
- Enable the capability for interactive model presets while leaving `codex-auto-review` and local models opted out.
## Testing
- Verify that missing metadata defaults to enabled and an explicit opt-out survives serialization.
GitOrigin-RevId: 6a20573cddfd3b80083d2b4b015829b49e6cc283
## Why
Symlinked skills have a canonical `SKILL.md` path that can differ from the path
under the configured skill root. A catalog entry that advertises the discovery
path must still select the canonical skill.
## What changed
- Track each loaded skill's discovery path alongside its canonical identity.
- Render discovery paths in the skill catalog and accept either form for
structured selections and linked skill mentions.
- Preserve enabled-state checks, deduplication, and product filtering when
resolving discovery paths.
## Testing
Added loader, catalog, mention-resolution, and end-to-end turn coverage for
skills discovered through directory symlinks.
GitOrigin-RevId: bae539b766cc3782c7c121a4276c337699cbb509
## What changed
- Add the disabled-by-default `image_resize_notice` feature.
- When enabled, append a developer message after resized images from user
messages or tool outputs. The notice identifies each image and reports its
original and prepared dimensions.
- Persist notices with new history while avoiding backfilled notices for images
processed when a session is resumed.
## Testing
- Cover notice placement, image numbering, failed images, user and tool image
sources, and resumed-session replay.
GitOrigin-RevId: 11dd808b3ad47eac35e9e2f4a4370f85d0122770
## What changed
- Select `gpt-5.6-luna` for Guardian approval reviews authenticated with an API key, while retaining `codex-auto-review` for ChatGPT authentication.
- Exercise API-key reviews through Responses Lite and fall back to the bundled Guardian policy when the selected model has no catalog-provided review policy.
- Refine the bundled policy's handling of trusted authorization, sensitive-data egress, credential probing, destructive command targets, and post-denial approval.
## Testing
- Cover provider model selection for API-key and ChatGPT authentication.
- Verify Guardian prewarming and review reuse with both Responses Lite and standard Responses requests.
GitOrigin-RevId: e35c43e1692fd643ab8faad1444c0d6a869b3e0c
## Why
The 4 KiB aggregate limit can truncate source metadata before it reaches the
model through the tool search description.
## What changed
Raise the aggregate source-description limit to 512 KiB while retaining the
existing character-boundary-safe truncation and bounded output.
## Testing
Expand unit and RMCP round-trip coverage to verify that substantially longer
Unicode descriptions remain complete within the new limit.
GitOrigin-RevId: 002760cdd2e8741e531b45f75f8624ef84334d24
## What changed
- Propagate the optional `modelSpecialty` field through the model catalog and
app-server `model/list` response.
- When a newly selected model has the `cyber` specialty, default an active TUI
thread to workspace-write permissions with on-request approval. Use auto
review when available, otherwise keep the user as reviewer, while respecting
configured permission requirements.
- Show a notice when auto review is applied and strengthen the full-access
warning for cyber models.
- Preserve explicitly selected permissions when only reasoning settings change.
## Testing
- Cover auto-review defaults, requirement-aware fallback behavior, permission
preservation across reasoning changes, and the new warning notice.
GitOrigin-RevId: 8f25b0082d3051d9ff91f7355921236d0f82f758
## What changed
- Treat different non-empty descriptions for the same tool namespace as a
collision when `error_on_tool_collisions` is enabled, including deferred
tools.
- Continue allowing multiple tools to share a namespace when their descriptions
match or are empty.
- Preserve the first non-empty namespace description when strict collision
checking is disabled.
## Testing
- Cover strict collisions across direct and deferred tools, valid shared
namespaces, relaxed description merging, and failure before model sampling.
GitOrigin-RevId: 788a2ae0eccb64c97995af7a208d9abb79edf2d0
## What changed
- Derive sandboxing, approval, and permission-profile environment variables from the selected turn environment for shell, unified exec, `apply_patch`, image viewing, and network approval flows.
- Materialize project-root permissions against every workspace root in that environment, allowing `apply_patch` to write to secondary workspace roots while preserving protected paths.
- Carry the selected environment's permission profile into spawned or resumed agents and Guardian permission context.
## Testing
- Add an integration test covering `apply_patch` writes in a secondary workspace root.
- Extend tool, Guardian, and multi-agent tests to distinguish environment permissions from thread-level permissions.
GitOrigin-RevId: e22da8974bcd3de1e724978b1a7790307a51e4bc
## What changed
- Track Agent Plugin manifests through plugin, skill, and MCP loading so their capabilities use format-specific behavior without changing legacy plugins.
- Discover only direct-child skills, exclude app and hook capabilities, isolate MCP data, and reject MCP configuration files that are non-regular or resolve outside the plugin root.
- Bound model-visible skill instructions, plugin instructions, MCP descriptions, schemas, individual tools, and the aggregate Agent Plugin MCP tool set.
- Stop MCP and OAuth redirects when Agent Plugins send configured or authorization headers, while retaining existing redirect behavior for legacy MCP servers.
## Testing
- Add coverage for capability filtering, skill discovery, isolated MCP data and reserved-path expansion, unsafe MCP configuration files, context limits, and redirect handling.
GitOrigin-RevId: c9af66b051269f3226628ca280a58d32c808c38f
## What changed
- Group top-level function and custom tool definitions into a single `functions` namespace for Responses Lite providers that support namespaced tools.
- Normalize missing, empty, and explicit `functions` namespaces to the same tool identity across registration, routing, lifecycle hooks, configuration, and tool search.
- Keep default tool names unprefixed in code mode, display output, and dispatch traces while preserving explicit non-default namespaces.
## Testing
- Add coverage for Responses Lite serialization, tool search results, namespace normalization and collision handling, routing, lifecycle events, and code-mode namespace policies.
GitOrigin-RevId: d48414005b5d22d39b11a198e19c47814d3a19f2
## What changed
- Track the first duplicate effective tool name while assembling the tool registry, including collisions introduced by external tools, code mode, and tool search.
- When `[features.tool_registry].error_on_tool_collisions` is enabled, fail the turn with a `duplicate tool: <namespace>.<name>` error before sending a model request.
- Continue allowing identical tool names in different namespaces, and preserve the existing collision behavior when strict checking is disabled.
## Testing
- Cover registry collision tracking, strict tool planning across tool sources, namespace isolation, failure before sampling, and pre-sampling compaction.
GitOrigin-RevId: 4cf83538fb513cec0b9c8b567780caaaadd3243d
## What changed
- Include top-level freeform tools in the tool-search index and mark them for deferred loading.
- Serialize searched freeform tools as Responses API `custom` tools and convert them back into executable tool specs after discovery.
- Cover indexing and the end-to-end search, load, and custom-call routing flow.
GitOrigin-RevId: 124a7705876067542e1bd609546adc9a8d0ef67e
## What changed
- Add the public asynchronous `ModelsCache` contract and cache entry/error types.
- Let model providers and `OpenAiModelsManager` accept caller-provided cache implementations while retaining the existing file-backed cache by default.
- Treat cache read failures as misses, keep cache write failures non-fatal, and support refreshing an entry's TTL after ETag revalidation.
- Continue to prefer an explicitly configured static model catalog over an injected cache.
## Testing
- Cover injected cache hits, read and write failures, TTL refreshes, and end-to-end model selection.
- Verify that the file-backed implementation satisfies the new cache contract and does not serve expired entries before revalidation.
GitOrigin-RevId: eef957a317910b8502a0c20f8fc112f689d5e389
## What changed
- Remove the hidden `PairProgramming` and `Execute` variants from `ModeKind`.
- Delete their unused prompt templates and simplify mode handling to cover only `Default` and `Plan`.
GitOrigin-RevId: 8d24e3f562a09e3071b2decae275d2b3871a1e9c
## What changed
- Add provider-owned remote compaction capabilities for unsupported, v1, and v2 protocols.
- Mark Amazon Bedrock as v1-only so manual and automatic compaction use `/v1/responses/compact`, even when the v2 feature is enabled.
- Preserve v2 support for OpenAI and Azure Responses providers and local compaction for unsupported providers.
## Testing
- Cover Amazon Bedrock manual and automatic remote compaction, including endpoint selection, authentication headers, model selection, and reuse of the compacted summary.
GitOrigin-RevId: d58093178605d1f8155b93d9a161408177f6ac72
Charlie Marsh