## Why
Native Codex currently teaches multi-agent concurrency through the
`spawn_agent` tool description, while bridge-driven evals frame the same
limit as a shared pool of active agent slots. That mismatch makes the
model-facing story harder to reason about, especially because the
tool-level wording does not make it explicit that the limit covers the
whole agent team, including the current agent.
This change gives native Codex the same mental model: tell the root
agent and subagents how many active slots exist, and remove the separate
`spawn_agent` limit wording.
## What changed
- Extend the built-in `multi_agent_v2` root and subagent usage hints
with shared-slot guidance derived from the resolved
`max_concurrent_threads_per_session` value.
- Keep the complete default hints in `MultiAgentV2Config` so initial
context and forked histories consume the same canonical strings.
- Drop the redundant `spawn_agent` description text and remove the
now-unused limit plumbing from the tool spec path.
## Testing
- `just test -p codex-core usage_hint`
- `just test -p codex-core
multi_agent_v2_default_session_thread_cap_counts_root`
- `just test -p codex-core
multi_agent_v2_default_usage_hints_use_configured_thread_cap`
- `just test -p codex-core
spawn_agent_tool_v2_requires_task_name_and_lists_visible_models`
- `just test -p codex-core
multi_agent_feature_selects_one_agent_tool_family`
## Why
Remote compaction v2 is ready to become the default for providers that
already support remote compaction. Leaving it behind an
under-development opt-in keeps eligible sessions on the legacy
remote-compaction path.
This does not broaden provider eligibility: OpenAI and Azure move to v2,
while Bedrock and OSS providers retain their existing local-compaction
behavior.
## What changed
- Mark `remote_compaction_v2` stable and enable it by default.
- Make tests that intentionally cover legacy remote compaction
explicitly disable v2.
- Update parity coverage so v2 exercises the production default and only
legacy mode opts out.
## Verification
- `just test -p codex-core
auto_compact_runs_after_resume_when_token_usage_is_over_limit
auto_compact_counts_encrypted_reasoning_before_last_user
auto_compact_runs_when_reasoning_header_clears_between_turns
responses_lite_compact_request_uses_lite_transport_contract`
## Why
#27198 made the extension-owned `codex_apps` MCP connection the hosted
plugin runtime, but its `mcp/skill` resources still bypassed the skills
extension. App-server could list and read those resources through
generic MCP APIs, but a thread with no selected environment did not
expose them in the model's skills catalog or load their `SKILL.md`
through `$skill`.
Hosted skills should stay remote while using the same typed catalog,
source authority, deduplication, bounded contextual catalog, and
selected-skill prompt injection as host and executor skills. They should
not be downloaded or exposed as ambient filesystem paths.
## What changed
- Add a session-scoped `McpResourceClient` over the replaceable MCP
connection manager so resource list/read calls follow startup and
refresh replacements.
- Add a `BackendSkillProvider` that pages `codex_apps` resources,
accepts bounded and validated `mcp/skill` entries, and reads a selected
skill's `SKILL.md` through the same MCP connection.
- Register the remote provider in app-server and include it in the
skills catalog even when a thread has no selected capability roots or
executor.
- Contribute hosted skill metadata through the bounded
`AvailableSkillsInstructions` developer-context path, exclude remote
entries from per-turn catalog injection, and classify `<skills>`
messages as contextual developer content so rollback can trim and
rebuild them correctly.
## Testing
- Extend the app-server MCP resource integration test with
`environments: []` to exercise two-page discovery, filter a
non-`mcp/skill` resource, verify the escaped developer catalog entry and
user-role `<skill>` fragment containing the fetched `SKILL.md`, and
preserve generic MCP resource reads.
- Add core event-mapping coverage that classifies `<skills>` developer
messages as contextual history.
## Summary
- replace raw compaction `error` analytics with `codex_error_kind` and
`codex_error_http_status_code`
- derive compaction error telemetry from `CodexErr` using the same
`CodexErrKind` mapping and HTTP status helper used by turn events
- remove the pre-compact hook stop reason from the internal compaction
outcome now that it is no longer emitted as raw analytics text
## Why
Compaction `error` was a raw `CodexErr::to_string()` value, which can
carry free-form provider or user-derived text. Structured Codex error
fields preserve useful low-cardinality telemetry without sending the raw
string.
## Validation
- `just fmt`
- `just test -p codex-analytics`
- `just test -p codex-core
compact::tests::build_token_limited_compacted_history_appends_summary_message`
Attempted `just test -p codex-core`; the changed crate compiled, but the
full target failed in unrelated environment-dependent tests such as
missing helper binaries and shell snapshot timeouts.
## Why
Dynamic tools maintained a separate search-text builder even though the
shared tool search path already derives the same metadata from
`ToolSpec`. Using the shared path removes duplicate behavior before
adding explicit namespaces.
## What changed
- Build dynamic-tool search entries with
`ToolSearchInfo::from_tool_spec`.
- Remove the custom search-text state and its implementation-only unit
test.
The old search text included the tool name, its space-separated form,
description, namespace, and top-level parameter names. The shared
builder preserves all of those terms and also indexes namespace
descriptions and nested schema metadata.
## Test plan
- `just test -p codex-core
tool_search_returns_deferred_dynamic_tool_and_routes_follow_up_call`
## Summary
- add nullable `cached_input_tokens` to the compaction analytics event
- populate it from response usage for compaction v2
- leave it `null` for other compaction implementations
This adds visibility into prompt-cache usage for v2 compaction without
changing compaction behavior.
## Testing
- `just test -p codex-analytics`
- `just test -p codex-core
collect_compaction_output_accepts_additional_output_items`
## Why
The token budget feature can inject remaining-context notices into
model-visible context, but the model does not have a direct way to ask
for that same remaining-token fragment on demand.
This PR adds a small model tool for the token budget feature so the
model can request the current remaining context window message without
duplicating the fragment format.
## What changed
- Adds a `get_context_remaining` direct-model tool behind
`Feature::TokenBudget`.
- Renders the tool output through `TokenBudgetRemainingContext`,
matching the existing budget message shape.
- Registers the tool alongside `new_context` in the token budget tool
set.
- Adds integration coverage that verifies the tool is exposed and
returns the same `<token_budget>` remaining fragment already present in
context.
## Validation
- `just test -p codex-core token_budget`
## Summary
- snapshot `comp_hash` into `TurnContext` when the turn is created and
use that snapshot as the downstream source of truth
- persist the turn hash in rollout context and recover it into
previous-turn settings during resume and fork replay
- compact existing history with the previous model only when both
adjacent turns provide hashes and the values differ
- record `comp_hash_changed` as the compaction reason
- cover ordinary transitions, resume, and missing-hash compatibility
with end-to-end tests
## Why
History produced under one compaction-compatible model configuration may
not be safe to carry directly into another. Compacting at the turn
boundary converts that history before context updates and the new user
message are added. Persisting the turn snapshot in `TurnContextItem`
makes the same protection work after resuming a rollout.
A missing hash is not treated as evidence of incompatibility. `None →
Some`, `Some → None`, and `None → None` do not trigger compaction; only
`Some(previous) → Some(current)` with unequal values does.
## Stack
- depends on #27532
- #27532 is based directly on `main`
## Testing
- `just test -p codex-core pre_sampling_compact_` — 6 passed
- `just test -p codex-core
turn_context_item_uses_turn_context_comp_hash_snapshot` — passed
- `just fix -p codex-core -p codex-protocol -p codex-analytics -p
codex-models-manager`
## Summary
- Add auth mode state to `PluginsManager`.
- Sync the plugin manager auth mode when `ThreadManager` is created and
when account auth changes.
- Route plugin load outcomes through an auth-aware projection hook so
follow-up plugin filtering can stay inside `core-plugins`.
## Motivation
This prepares plugin capability loading to be configured by auth mode,
such as hiding or exposing app/MCP-backed plugin surfaces based on
whether the user is using ChatGPT auth or API-key auth, without leaking
those details outside the plugin manager.
## Tests
- `just fmt`
- `just test -p codex-core-plugins`
- `env -u CODEX_SANDBOX_NETWORK_DISABLED -u CODEX_SANDBOX just test -p
codex-core thread_manager::tests`
- `env -u CODEX_SANDBOX_NETWORK_DISABLED -u CODEX_SANDBOX just test -p
codex-app-server`
## Summary
- Strip image `detail` fields from every Responses Lite request.
- Apply stripping to message images and function/custom tool-output
images.
- Transform only the formatted request copy without mutating stored
history.
- Preserve image URLs byte-for-byte, including HTTP(S) URLs, without
downloading, validating, or resizing them.
- Preserve all image `detail` fields for non-Responses-Lite models.
## Motivation
Responses Lite does not support image `detail` tags, so Codex must omit
them whenever `model_info.use_responses_lite` is enabled. This transport
requirement is independent of the `resize_all_images` feature.
Stored history retains the original detail values. This keeps
request-specific formatting isolated from conversation state and
preserves the information for local image preparation and
non-Responses-Lite requests.
#### [git stack](https://github.com/magus/git-stack-cli)
- ✅ `1` https://github.com/openai/codex/pull/27245
- ✅ `2` https://github.com/openai/codex/pull/27247
- 👉 `3` https://github.com/openai/codex/pull/27246
- ⏳ `4` https://github.com/openai/codex/pull/27266
## Summary
- add optional `comp_hash` metadata to `ModelInfo`
- update `ModelInfo` fixtures for the shared schema change
- keep older model responses compatible by defaulting the field to
`None`
## Why
The models endpoint needs an opaque identifier for compaction-compatible
model configurations. This PR only exposes that value in model metadata;
it does not add it to turn context or change runtime behavior.
Follow-up #27520 carries the value through turn context and rollouts,
then uses it to trigger compaction.
## Stack
- based directly on `main`
- replaces #27519, which was accidentally merged into the wrong base
branch
- functionality follow-up: #27520
## Testing
- `just test -p codex-protocol
model_info_defaults_availability_nux_to_none_when_omitted`
- `just fix -p codex-core -p codex-protocol -p codex-analytics -p
codex-models-manager`
## Why
Codex needs to manage Amazon Bedrock API key credentials through the
existing auth lifecycle instead of introducing a separate auth manager
or provider-specific credential file. Treating Bedrock API key login as
a primary auth mode gives it the same persistence, keyring, reload, and
logout behavior as the existing OpenAI API key and ChatGPT modes.
The credential is valid only for the `amazon-bedrock` model provider.
OpenAI-compatible providers must reject this auth mode rather than
treating the Bedrock key as an OpenAI bearer token.
## What changed
- Added `bedrockApiKey` as an app-server `AuthMode` and
`CodexAuth::BedrockApiKey` as a primary `AuthManager` mode.
- Added `BedrockApiKeyAuth`, containing the API key and AWS region, to
the existing `AuthDotJson` payload stored in `$CODEX_HOME/auth.json` or
the configured keyring backend.
- Added `login_with_bedrock_api_key(...)`, parallel to
`login_with_api_key(...)`, which replaces the current stored login with
Bedrock credentials.
- Reused generic auth reload and logout behavior instead of adding a
Bedrock-specific auth manager or logout path.
- Updated login restrictions, status reporting, diagnostics, telemetry
classification, generated app-server schemas, and auth fixtures for the
new mode.
- Added explicit errors when Bedrock API key auth is selected with an
OpenAI-compatible model provider.
This PR establishes managed storage and auth-mode behavior. Routing the
managed key and region into Amazon Bedrock requests will be in follow-up
PRs.
## Why
The token budget feature tells the model how much room remains in the
current context window. When the model decides the current window is no
longer useful, it needs a way to ask Codex to start over with a fresh
context window without spending tokens on a compaction summary.
This PR adds that model-requestable escape hatch on top of #27438.
## What changed
- Added a direct-model-only `new_context` tool behind
`Feature::TokenBudget`.
- Stores the tool request on `AutoCompactWindow` and consumes it after
sampling so the next follow-up request in the same turn starts in the
new window.
- Starts the new window as a no-summary compaction checkpoint that
contains only fresh initial context, not preserved conversation history.
- Keeps the new window aligned with token-budget startup context,
including the `Current context window Z` message.
- Added integration coverage and a snapshot showing the same-turn
`new_context` flow into a fresh full-context follow-up request.
## Validation
- `just test -p codex-core token_budget`
## Why
The model should be able to see bounded context-window budget metadata
when the `token_budget` feature is enabled. The full-window message is
only injected with full context, while normal turns get a smaller
follow-up only when reported usage first crosses a budget threshold.
## What changed
- Added the `TokenBudget` feature flag.
- Added `<token_budget>` developer fragments for full context-window
metadata and current-window remaining tokens.
- Inserted the threshold message during normal turn handling by
comparing token usage before and after sampling, avoiding persistent
threshold bookkeeping.
- Added core integration coverage for full-context-only metadata and
25/50/75 percent threshold messages.
## Verification
- `just test -p codex-core token_budget`
- `git diff --check`
## Summary
Adds complete client-side image preparation behind the default-off
`resize_all_images` feature flag.
When enabled, local image producers defer decoding and resizing. Images
are prepared centrally before insertion into conversation history,
covering user input, `view_image`, and structured tool-output images.
## Behavior
- Processes base64 `data:` images in messages and function/custom tool
outputs.
- Leaves non-data URLs, including HTTP(S) URLs, unchanged.
- Applies image-detail budgets:
- `high` and omitted: 2048px maximum dimension and 2.5K 32px patches.
- `original`: 6000px maximum dimension and 10K 32px patches.
- `auto`: uses the same 2048px / 2.5K-patch budget as high.
- `low`: unsupported and replaced with an actionable placeholder.
- Preserves original image bytes when no resize or format conversion is
needed.
- Enforces the shared 1 GiB encoded and decoded data-URL sanity limits.
- Replaces only an image that fails preparation, preserving sibling
content and tool-output metadata.
- Uses bounded placeholders distinguishing generic processing failures,
oversized images, and unsupported `low` detail.
- Prepares resumed and forked history before installing it as live
history without modifying persisted rollouts.
## Flag-Off Behavior
When `resize_all_images` is disabled:
- Existing local user-input and `view_image` processing remains
unchanged.
- Existing decoding and error behavior remains unchanged.
- Arbitrary tool-output images are not processed.
- HTTP(S) image URLs continue to be forwarded unchanged.
#### [git stack](https://github.com/magus/git-stack-cli)
- ✅ `1` https://github.com/openai/codex/pull/27245
- 👉 `2` https://github.com/openai/codex/pull/27247
- ⏳ `3` https://github.com/openai/codex/pull/27246
- ⏳ `4` https://github.com/openai/codex/pull/27266
## Summary
Turn diff updates repeatedly rendered and serialized the entire
accumulated diff after every `apply_patch`. The event path also rendered
once before updating the tracker solely to test whether a diff existed.
In production feedback CODEX-20PW, 2,589 patches across 72 paths
produced 401 notifications totaling 441 MB, with the hottest paths
patched 518 and 495 times.
This change:
- replaces the pre-update render with a cheap cached-state check
- caches each rendered file diff by path and content revision, so an
update only invokes Myers for affected paths
- caches the deterministic aggregate diff so event emission and turn
completion reuse it without recomputation
- preserves invalidation and net-zero clear notifications
- applies a 100 ms per-file `similar` timeout; ordinary files complete
far below this threshold, while pathological rewrites fall back to a
coarse unified hunk that still represents the exact final contents
The 100 ms deadline bounds synchronous tool-completion latency while
leaving substantial headroom for normal diffs. The regression test
applies the fallback diff through the repository's patch parser and
verifies byte-for-byte final contents.
## Validation
- `cargo test -p codex-core turn_diff_tracker::tests` (14 passed)
- `cargo test -p codex-core tools::events::tests` (4 passed)
- `just fix -p codex-core`
- `just fmt`
Focused coverage verifies that 42 updates across two files perform 42
file renders rather than repeatedly rendering the accumulated set,
unchanged paths are not re-diffed, clear events remain correct, and a
48,000-line near-total rewrite returns promptly and applies to the exact
expected result. The full `codex-core` suite was not used as the final
gate because an unrelated existing multi-agent test hit a stack overflow
when run during investigation.
## Bug context
- Sentry feedback: CODEX-20PW
- Correlation IDs: `019eb2a9-13d2-74e0-b690-27ee224ffb6d`,
`019e9ad7-09c3-7cb2-b728-ee3acba103ab`
## Why
When a realtime session is open without an active frontend-model
handoff, completed Codex assistant messages are currently dropped. That
prevents the frontend model from hearing orchestrator preambles and
final responses produced by typed turns or other non-handoff work, which
makes the two models present as disconnected personas.
Active handoffs already forward each completed assistant message,
including preambles. This change leaves those V1 and V2 paths intact and
fills only the no-active-handoff gap.
## What changed
- Send standalone V1 assistant messages through
`conversation.handoff.append` with a stable synthetic handoff ID
- Send standalone V2 assistant messages as normal `[BACKEND]`
`conversation.item.create` message items, then enqueue `response.create`
so the frontend model responds
- Preserve the existing active V1 and V2 transport and completion
behavior
- Continue excluding user messages from realtime mirroring
- Skip empty output and cap each complete context injection, including
its V2 prefix, at 1,000 tokens
- Add end-to-end coverage for both wire formats, V2 response creation,
preambles, final responses, and truncation
## Test plan
- CI
## Why
Recent MCP runtime overlay changes replace same-name configured server
entries with compatibility or extension-provided configs. Those
replacement configs default to enabled, so an MCP server explicitly
configured with `enabled = false` could be initialized anyway.
The connection manager still filters disabled servers correctly, but the
configured disabled state was lost before initialization reached that
filter.
## What changed
- Remember MCP servers that are disabled in the configured view before
applying runtime fallbacks and extension overlays.
- Restore `enabled = false` for those servers after overlays, while
leaving all other overlay fields and `Remove` precedence unchanged.
- Add focused extension-backed regression coverage for a disabled
`codex_apps` server.
## Testing
- `just fmt`
- `just test -p codex-mcp-extension`
- `just fix -p codex-core`
- `just fix -p codex-mcp-extension`
The full workspace `just test` suite was not run.
## Summary
- skip the local `openai-curated` marketplace before marketplace loading
when tool-suggest discovery uses remote plugins
- preserve existing marketplace listing behavior for all other callers
and when remote plugins are disabled
- add regression coverage proving the curated marketplace is excluded
before its malformed manifest can be read
## Why
Tool-suggest discovery previously loaded every local `openai-curated`
plugin manifest and only discarded that marketplace afterward when
remote plugins were enabled. The remote catalog is used in that mode, so
the local scan consumed CPU without contributing discoverable plugins.
## Impact
Remote-plugin tool suggestion discovery no longer reads the local
curated marketplace and its plugin manifests. `openai-bundled`,
configured marketplaces, normal `plugin/list` behavior, and local
curated discovery when remote plugins are disabled are unchanged.
## Validation
- `just test -p codex-core-plugins
list_marketplaces_can_skip_openai_curated_before_loading`
- `just test -p codex-core
list_tool_suggest_discoverable_plugins_omits_openai_curated_when_remote_enabled`
- `just fmt`
- `git diff --check`
## Why
Local integration-heavy `codex-core` CLI tests can time out or be
interrupted after spawning `codex exec`. Stopping only the direct child
is not enough: `codex exec` can leave grandchildren behind, including
`python3`/`python3.12` processes that get reparented to PID 1 and keep
running after the test is gone.
This PR fixes that failure mode directly for the affected CLI
integration tests, without changing production code or reducing local
test concurrency.
## What
- Run the `cli_stream` `codex exec` subprocesses through a small private
wrapper in `core/tests/suite/cli_stream.rs`.
- Spawn those subprocesses in their own process group before execution.
- Keep `.output()`-style stdout/stderr capture and the existing
30-second timeout behavior.
- Own each spawned process with a drop guard that kills the whole
process group on success, timeout, panic, or other early return.
The switch from `assert_cmd::Command` to `std::process::Command` is only
for these subprocess launches; `assert_cmd` does not expose a pre-spawn
hook for setting the process group.
## Verification
- `just test -p codex-core --test all responses_mode_stream_cli`
This is limited to core integration tests; it does not change production
`src` code paths.
Summary
- Propagate cached remote plugin IDs through Codex plugin discovery.
- Inject `remote_plugin_id` and connector IDs into
`request_plugin_install` elicitation `_meta` from the resolved plugin.
- Keep the remote plugin ID out of the model-facing tool schema,
arguments, and result.
Validation
- `just test -p codex-tools`
- `just test -p codex-core-plugins`
- `just test -p codex-core
list_tool_suggest_discoverable_plugins_includes_cached_remote_global_plugins`
- `just fix -p codex-tools`
- `just fix -p codex-core-plugins`
- `just fix -p codex-core`
- `git diff --check`
- `just test -p codex-core` was also attempted: 2,581 passed, 55 failed,
and 1 timed out across unrelated sandbox/environment-sensitive
integration tests.
## Background
Codex can use **Auto Review** for permission requests. Instead of asking
the user immediately, Codex starts a separate locked-down reviewer
session called **Guardian**, which returns a structured `allow` or
`deny` assessment.
The Guardian reviewer is itself a Codex session, so its model request
can fail for transient infrastructure reasons such as model overload,
HTTP connection failure, or response-stream disconnect. Today, any such
failure immediately ends the Auto Review attempt and blocks the action.
This PR adds bounded retries for failures that the existing protocol
explicitly identifies as transient.
Linear context:
[CA-539](https://linear.app/openai/issue/CA-539/retry-auto-review-infrastructure-failures-and-fall-back-to-manual)
## What changes
A Guardian review can now make at most **three total attempts**:
1. Run the review normally.
2. Retry after a jittered delay of roughly 180–220 ms if the first
attempt fails with an eligible error.
3. Retry after a jittered delay of roughly 360–440 ms if the second
attempt also fails with an eligible error.
All attempts share the original review deadline. Jitter spreads retries
from concurrent clients to reduce synchronized load during broader
outages. The retries do not reset the user's maximum wait time, and the
backoff waits terminate early if the review is cancelled or the deadline
expires.
Before retrying, the existing Guardian session lifecycle decides whether
the session remains usable. Healthy trunks are reused, broken trunks are
removed by the existing cleanup path, and ephemeral sessions continue to
clean themselves up.
The review still emits one logical lifecycle to clients. Recoverable
intermediate failures do not produce warnings or terminal events.
## Retry policy
### Retried up to twice
- model/server overload
- HTTP connection failure
- response-stream connection failure
- response-stream disconnect
- internal server error
- a final reviewer message that cannot be parsed as the required
Guardian assessment
### Not retried
- bad or invalid requests
- authentication failures
- usage limits
- cyber-policy failures
- errors without a structured category
- a request that already exhausted the lower-level Responses retry
budget
- a completed Guardian turn with no assessment payload
- prompt-construction failures
- Guardian review timeout
- cancellation or abort
- a valid `deny` assessment
The session-error classification uses `ErrorEvent.codex_error_info`; it
does not inspect error-message strings.
## Implementation notes
- `wait_for_guardian_review` preserves the complete `ErrorEvent`,
including structured `codex_error_info`.
- Guardian session failures preserve the original message and optional
structured `CodexErrorInfo`.
- The retry policy classifies the explicitly transient `CodexErrorInfo`
variants; unknown, absent, and deterministic categories are not retried.
- The Guardian session manager receives the caller's deadline rather
than creating a new timeout per attempt.
- Analytics record the final `attempt_count`.
- Retry orchestration does not add a separate session-cleanup protocol;
it relies on the existing trunk and ephemeral lifecycle decisions.
## Automated testing
Focused Guardian coverage verifies:
- every supported transient `CodexErrorInfo` is classified as retryable,
while absent and non-transient categories are not;
- structured transient session failure -> retry -> approval with the
healthy trunk reused;
- two invalid Guardian responses -> third attempt -> approval, with
exactly three requests;
- three invalid responses -> existing fail-closed result, with exactly
three requests and one terminal lifecycle;
- valid denial, missing payload, invalid request, timeout, cancellation,
and prompt/session construction failures are not retried;
- retry eligibility ends after the third attempt;
- retry delays use the shared exponential backoff helper and remain
within the expected jitter bounds;
- cancellation and deadline expiry interrupt the backoff wait;
- healthy trunks are reused across retryable failures;
- broken event streams remove the trunk through the existing lifecycle
cleanup;
- an ephemeral retry does not disturb a concurrent trunk review.
Validation performed:
- `just test -p codex-core guardian_review_
guardian_ephemeral_retry_preserves_parallel_trunk_and_fork_history
run_review_removes_trunk_when_event_stream_is_broken` — **42 passed**;
- `just test -p codex-analytics` — **71 passed**;
- scoped Clippy fixes for `codex-core` and `codex-analytics` passed.
A prior full `codex-core` run had unrelated environment-sensitive
failures outside Guardian coverage.
## Manual QA
The focused integration tests use the local mock Responses server to
inspect exact request counts and emitted lifecycle events. They confirm
that retries are internal, a successful later attempt supplies the final
decision, non-retryable failures issue only one request, and exhausted
retries emit only one terminal result.
## Why
Clients can archive and unarchive threads today, but there is no
app-server API for permanently removing a thread. Deletion also needs to
cover the full session tree: deleting a main thread should remove
spawned subagent threads and the related local metadata instead of
leaving orphaned rollout files, goals, or subagent state behind.
## What
- Adds the v2 `thread/delete` request and `thread/deleted` notification,
with the response shape kept consistent with `thread/archive`.
- Implements local hard delete for active and archived rollout files.
- Deletes the requested thread's state DB row as the commit point, then
best-effort cleans associated state including spawned descendants,
goals, spawn edges, logs, dynamic tools, and agent job assignments.
- Updates app-server API docs and generated protocol schema/TypeScript
fixtures.
## Summary
Codex Apps needs app-server as the source of truth for chat-started
background terminals instead of guessing from local process trees.
This PR adds experimental v2 APIs to list and terminate background
terminals for a loaded thread using app-server process ids, so clients
can manage background terminals without local PID discovery.
## Changes
- `thread/backgroundTerminals/list` returns paginated background
terminal records with `itemId`, app-server `processId`, `command`,
`cwd`, nullable `osPid`, nullable `cpuPercent`, and nullable `rssKb`.
- `thread/backgroundTerminals/terminate` terminates one running
background terminal by app-server `processId` and returns whether a
process was terminated.
- Background terminal list and terminate operations use unified-exec
process manager state as their source of truth.
## Why
We're now [discouraging use of
`async_trait`](https://github.com/openai/codex/pull/20242).
Removing use of `async_trait` from `ToolExecutor` yields a `codex_core`
debug test build speedup of ~78% (from 227.5s to 50.3s) on my machine.
Stacked on #27299, this PR applies the trait change after the handler
bodies have been outlined.
## What
Changed `ToolExecutor::handle` to return an explicit boxed
`ToolExecutorFuture` instead of using `async_trait`.
Updated ToolExecutor implementors to return `Box::pin(...)`, reexported
the future alias through `codex-tools` and `codex-extension-api`, and
removed `codex-tools` direct `async-trait` dependency.
## Why
We're now [discouraging use of
`async_trait`](https://github.com/openai/codex/pull/20242).
Removing use of `async_trait` from `ToolExecutor` yields a `codex_core`
debug test build speedup of ~78% (from 227.5s to 50.3s) on my machine.
For ease of reviewing, this is a prefactor to extract trait method
implementations to inherent methods. This will prevent changing
indentation from creating a huge diff.
## What
Outlined existing `ToolExecutor::handle` bodies into inherent async
`handle_call` methods across core and extension tool handlers.
The trait methods still use `async_trait` and now delegate to
`self.handle_call(...).await`; handler behavior is unchanged.
## Why
Compaction window identity is part of session history, not model-client
transport state. Persisting it with the compacted rollout item lets
resumed threads continue from the reconstructed window without keeping
mutable window state on `ModelClient`.
## What changed
- Added `window_id` to `CompactedItem` and stamp it when
`replace_compacted_history` installs compacted history.
- Moved auto-compact window id ownership into `AutoCompactWindow` /
`SessionState`; `ModelClient` now receives the request window id from
callers instead of storing it.
- Returned `window_id` from rollout reconstruction for resume.
Reconstruction uses the newest surviving compacted item's stored
`window_id` when present, and falls back to the legacy compacted-item
count when it is absent.
- Kept fork startup at the fresh default window id and updated direct
model-client tests to pass explicit test window ids.
## Validation
- `cargo check -p codex-core --tests`
## Summary
We originally addressed startup prewarming holding the read side of
`RwLock<McpConnectionManager>` by snapshotting tool-list state. Review
feedback identified the broader ownership problem: the outer
synchronization should only publish or retrieve the current manager,
while MCP operations rely on the manager's internal synchronization. A
follow-up preserved operation retirement with a separate gate, but
further review questioned whether that synchronization was actually
required and whether we could support latest-wins replacement instead.
This PR now stores the current MCP manager in `ArcSwap`. Each operation
uses `load_full()` to obtain an owned `Arc<McpConnectionManager>`, then
performs MCP I/O without retaining the publication mechanism. Refresh
cancels obsolete startup work, constructs a replacement, and atomically
publishes it. New operations see the latest manager, while operations
that already loaded the previous manager retain a valid handle. Refresh
happens at a turn boundary, so there should be no active user tool calls
to drain.
Git history supports dropping the outer `RwLock`. It was introduced in
`03ffe4d595` on November 17, 2025 for non-blocking MCP startup: the
session published an empty manager, startup initialized that same object
while holding the write lock, and readers waited for initialization.
`7cd2e84026` on February 19, 2026 removed that two-phase initialization
in favor of constructing a fresh manager and swapping it in, explicitly
noting that `Option` or `OnceCell` could replace the placeholder design.
Hot reload later reused the existing lock to publish a replacement, but
I found no indication that the lock was introduced to guarantee
in-flight tool calls finish before refresh or shutdown.
Terminal shutdown remains separate from refresh: it aborts startup
prewarming and active tasks before shutting down the current manager, so
tool calls may be interrupted and no model WebSocket work continues
after shutdown. Focused regression coverage exercises pending tool-list
cancellation, deferred refresh, and startup-prewarm shutdown.
## Why
Extension contributors are registered behind `dyn Trait` objects, so
native `async fn`/RPITIT methods would make these traits
non-object-safe. Spell out the boxed, `Send` future contract directly so
`extension-api` no longer needs `async-trait` while retaining the
existing runtime model.
## What changed
- add a shared `ExtensionFuture` alias and use it for asynchronous
contributor methods
- migrate production and test implementations to return `Box::pin(async
move { ... })`
- remove `async-trait` dependencies where they are no longer used,
keeping it dev-only where unrelated test executors still require it
## Behavior
No behavior change is intended. Contributor futures remain boxed,
`Send`, dynamically dispatched, and lazily executed; cancellation and
callback ordering stay unchanged.
## Testing
- `just test -p codex-extension-api` (11 passed)
- affected extension crates (64 passed)
- targeted `codex-core` contributor tests (14 passed)
- `just fmt`
- `just bazel-lock-update`
- `just bazel-lock-check`
A broad local `codex-core` run compiled successfully but encountered
unrelated sandbox and missing test-binary fixture failures; CI will run
the full checks.
## Summary
- tag legacy multi-agent spawn metrics with `version=v1`
- tag multi-agent v2 spawn metrics with `version=v2`
## Why
`codex.multi_agent.spawn` is emitted by both runtimes, so the existing
metric cannot distinguish v2 adoption from aggregate multi-agent
spawning. The bounded version tag makes that breakdown directly
queryable without changing the counter's success-only semantics.
## Validation
- `just fmt`
- `git diff --check`
- Tests and Clippy were intentionally left to CI.
## Stack
- Base: #27191
- This PR is the third vertical and should be reviewed against
`jif/external-plugins-2`, not `main`.
## Why
#27191 moves the host-owned Apps MCP registration behind an extension
contributor, but deliberately preserves the existing endpoint-selection
feature while that contribution contract lands. App-server can therefore
resolve the server through extensions, yet the hosted plugin endpoint is
still selected through temporary `apps_mcp_path_override` plumbing.
That is not the long-term plugin model. A plugin can bundle skills,
connectors, MCP servers, and hooks, and those components do not all need
the same source or execution environment. In particular, an
authenticated HTTP MCP server can expose plugin capabilities directly
from a backend without an executor or an orchestrator filesystem.
This PR completes that hosted vertical. App-server's MCP extension now
owns the aggregate hosted plugin runtime at `/ps/mcp`. Connector actions
continue to arrive as MCP tools, while backend-provided skills arrive as
MCP resources and use Codex's existing resource list/read paths. No
second backend client, skill filesystem, or generic plugin activation
framework is introduced.
The backend route remains the hosted implementation. This change
replaces Codex's temporary endpoint-selection mechanism, not the service
behind the endpoint.
## What changed
### Hosted plugin runtime
The MCP extension now contributes `codex_apps` as the hosted plugin
runtime rather than as a configurable Apps endpoint:
- `https://chatgpt.com` resolves to
`https://chatgpt.com/backend-api/ps/mcp`;
- a bare custom ChatGPT base resolves to `/api/codex/ps/mcp`;
- the existing product-SKU header and ChatGPT authentication behavior
are preserved;
- executor availability is never consulted for this streamable HTTP
transport.
The same MCP connection carries both component shapes supported by the
hosted endpoint:
- connector actions are discovered and invoked as MCP tools;
- hosted skills are enumerated and read as MCP resources through the
existing `list_mcp_resources` and `read_mcp_resource` paths.
This keeps component access in the subsystem that already owns the
protocol instead of downloading backend skills into an orchestrator
filesystem or inventing a parallel hosted-skill client.
### Explicit runtime ordering
`McpManager` now resolves the reserved `codex_apps` entry in three
ordered phases:
1. install the legacy Apps fallback for compatibility;
2. apply ordered extension `Set` or `Remove` overlays;
3. apply the final ChatGPT-auth gate without synthesizing the server
again.
This ordering is important:
- an ordinary configured or plugin MCP server cannot claim the
auth-bearing `codex_apps` name;
- an extension-contributed hosted runtime wins over the fallback;
- an extension `Remove` remains authoritative;
- a host without the MCP extension retains the legacy Apps endpoint and
current local-only behavior.
The temporary `legacy_apps_mcp_loader_enabled` coordination flag is no
longer needed.
### Remove the path override
The `apps_mcp_path_override` feature and its runtime plumbing are
removed, including:
- the feature registry entry and structured feature config;
- `Config` and `McpConfig` fields;
- config schema output;
- config-lock materialization;
- URL override handling in `codex-mcp`.
Existing boolean and structured forms still deserialize as ignored
compatibility input. They are omitted from new serialized config, and
config-lock comparison normalizes the removed input so older locks
remain replayable.
### App-server coverage
App-server MCP fixtures now serve the hosted route at
`/api/codex/ps/mcp`. Existing resource-read and tool/elicitation flows
therefore exercise the extension-owned endpoint rather than succeeding
through the legacy fallback.
The stack also adds the missing `codex_chatgpt::connectors` re-export
for the manager-backed connector helper introduced in #27191.
## Compatibility
- App-server installs the extension and uses `/ps/mcp` for the hosted
runtime.
- CLI and other hosts that do not install the extension retain the
legacy Apps endpoint.
- Apps disabled or non-ChatGPT authentication removes `codex_apps` from
the effective runtime view.
- Existing local plugins, local skills, executor-selected skills,
configured MCP servers, and MCP OAuth behavior are otherwise unchanged.
- Backend plugin enablement remains account/workspace state owned by the
hosted endpoint; this PR does not add thread-local backend plugin
selection.
## Architectural fit
The stack now proves two independent runtime shapes:
1. #27184 resolves filesystem-backed skills through the executor that
owns a selected root.
2. #27191 and this PR resolve a backend-hosted HTTP MCP through an
extension with no executor.
Together they preserve the intended separation:
- selection identifies a plugin/root when explicit selection is needed;
- each component's owning extension resolves its concrete access
mechanism;
- execution stays with the runtime required by that component;
- existing skills, MCP, connector, and hook subsystems remain the
downstream consumers.
## Planned follow-ups
1. **Executor stdio MCP:** selecting an executor plugin registers a
manifest-declared stdio MCP server and executes it in the environment
that owns the plugin.
2. **Optional backend selection:** only if CCA needs thread-local
selection distinct from backend account/workspace enablement, add a
concrete backend-owned capability location and surface those selected
skills through the skills catalog.
3. **Connector metadata and hooks:** activate those plugin components
through their existing owning subsystems, with executor hooks remaining
environment-bound.
4. **Propagation and persistence:** define explicit resume, fork,
subagent, refresh, and environment-removal semantics once selected roots
have multiple real consumers.
5. **Local convergence:** migrate legacy local skill, MCP, connector,
and hook paths behind their owning extensions one vertical at a time,
then remove duplicate core managers and compatibility plumbing after
parity.
## Verification
Coverage in this change exercises:
- extension-owned `/backend-api/ps/mcp` registration without an
executor;
- preservation of the legacy endpoint in hosts without the extension;
- extension `Set` and `Remove` precedence over the legacy fallback;
- ChatGPT-auth gating for the reserved server;
- hosted MCP resource reads with and without an active thread;
- connector tool invocation and MCP elicitation through the hosted
route;
- ignored boolean and structured forms of the removed path override;
- config-lock replay compatibility for the removed feature.
`cargo check -p codex-features -p codex-mcp-extension -p
codex-app-server` passes. Tests and Clippy were not run locally under
the current development instruction; CI provides the full validation
pass.
## Why
Required MCP server startup was enforced in `Session::new` after
`McpConnectionManager` had already created the clients. That split let
other manager construction paths bypass the same requirement and exposed
manager internals solely so the session could validate them. Keeping
required-server readiness in the constructor gives every caller one
consistent startup contract.
## What changed
- make `McpConnectionManager::new` return `anyhow::Result<Self>` and
fail when an enabled, required server cannot initialize
- pass the startup cancellation token into the constructor so
required-server waits remain cancellable
- propagate constructor failures through resource reads, connector
discovery, and MCP status collection
- preserve the active manager and cancellation token when a refreshed
replacement fails
- keep required-startup failure collection private and cover the
constructor error contract directly
## Validation
- updated the focused connection-manager test to assert the complete
required-server startup error
- local tests not run; relying on CI
## Why
Codex app-server latency traces do not granularly cover turn
orchestration, sampling-request preparation, and tool-loading work.
These spans help separate local coordination/setup costs from model
streaming and tool execution.
## What changed
- Add `run_turn.*` spans around sampling-request input preparation and
post-sampling state collection
- Add function-level trace spans around turn setup, hook execution,
compaction, prompt construction, and MCP tool exposure
- Add `built_tools.*` spans around plugin loading and discoverable-tool
loading
## Verification
Trigger Codex rollout and observe new spans are included
## Why
Clients need to select a realtime session configuration for an
individual start without rewriting persisted configuration or restarting
the app-server process.
## What Changed
- Add optional `model` and `version` fields to `thread/realtime/start`
- Forward those optional values through the realtime start operation and
apply them only for that session
- Preserve existing configured/default behavior when the new fields are
omitted
- Update generated protocol schema and app-server documentation
## Validation
- Added/updated protocol serialization coverage for the new optional
request fields
- Added focused core coverage for a session override taking precedence
over configured realtime selection
- Added focused app-server coverage that a request override reaches the
realtime WebSocket handshake
## Why
- Local profiling shows `append_tool_search_executor` averages ~113ms
per call. Adding a span lets us track this cost as we optimize in
follow-up PRs, either by reducing the work or avoiding repeated rebuilds
when inputs have not changed.
- While we're here, we can add spans to `build_tool_router` and other
sub-calls which code analysis shows may have additional opportunities
for improvement.
## What changed
Add function-level trace spans around `build_tool_router`,
`build_tool_specs_and_registry`, `add_tool_sources`,
`append_tool_search_executor`, and
`build_model_visible_specs_and_registry`
## Verification
Trigger Codex rollout and observe new spans are included
## Why
The realtime frontend model and the backing Codex thread should present
one coherent assistant. Raw typed messages, steers, and worker reports
belong to the orchestrator; the frontend model should receive the
orchestrator's user-facing result rather than a second copy of those
inputs.
Today normal `turn/start` input is automatically inserted into the
realtime conversation, while `turn/steer` is not. Besides creating
inconsistent context, this can make the frontend model react
independently before Codex has produced the response it should speak.
## What changed
- Remove automatic accepted-user-input mirroring into realtime
- Remove the mirror-only echo-suppression flag and dead V2 prefix helper
- Preserve explicit app-to-realtime text injection and FEM-to-Codex
delegation
- Replace the positive mirror tests and obsolete snapshots with a
negative routing regression test
## Test plan
- `cargo test -p codex-core
conversation_user_text_turn_is_not_sent_to_realtime`
- `cargo test -p codex-core
conversation_startup_context_is_truncated_and_sent_once_per_start`
- `cargo test -p codex-core inbound_handoff_request_starts_turn`
## Why
A long-running unified exec process started with `tty: false` could not
be interrupted via `write_stdin`: ordinary non-TTY stdin writes are
rejected once stdin is closed, but an exact U+0003 payload should still
map to a process interrupt. The interrupt should flow through the same
process lifecycle path as a real signal so Codex preserves
process-reported output and exit metadata instead of fabricating a
Ctrl-C exit code or tearing down the session early.
## What Changed
- Add `process/signal` to exec-server with `ProcessSignal::Interrupt`
and an empty response.
- Add a non-consuming `ProcessHandle::signal` path for spawned
processes; on Unix it sends SIGINT to the process group and leaves
terminate/hard-kill unchanged.
- Route non-TTY U+0003 `write_stdin` through `process.signal(...)`
instead of `terminate`, then let the normal post-write collection path
drain output and observe exit.
- Add exec-server coverage where a shell `trap INT` handler prints the
signal and exits with its own code.
- Add unified exec coverage where a `tty: false` process traps SIGINT,
emits output, and exits with its own code.
## Validation
- `just test -p codex-exec-server
exec_process_signal_interrupts_process`
- `just test -p codex-exec-server`
- `just test -p codex-core
write_stdin_ctrl_c_interrupts_non_tty_session`
## Why
Global instruction behavior spans thread creation, resume, forks,
subagents, and compaction. Characterization coverage is needed before
changing those semantics so preserved history can be distinguished from
newly loaded configuration.
## What changed
- Extends the existing `agents_md` suite with fresh-thread, warning,
resume, fork, and subagent lifecycle coverage.
- Extends the existing `compact` suite with manual, mid-turn, and
remote-v2 compaction coverage.
- Asserts rendered instruction fragments, reported source paths, and
structured request history before and after instruction-file mutations.
## Stack
- Base: #27184
- This PR is the second vertical and should be reviewed against
`jif/external-plugins-1`, not `main`.
## Why
CCA is moving toward a split runtime where the orchestrator may have no
filesystem or executor, but it still needs to activate remotely hosted
plugin components. HTTP MCP servers are the simplest complete example:
they need configuration and host authentication, but they do not need an
executor process.
The Apps MCP endpoint is currently synthesized by a special-purpose
loader inside the MCP runtime. That works locally, but it leaves hosted
MCP activation outside the extension model being established in #27184.
It also makes the Apps path a poor foundation for plugins whose skills,
MCP servers, connectors, and hooks may come from different sources or
execute in different places.
This PR moves that one behavior behind an extension-owned contribution
while preserving the existing local fallback. It deliberately does not
introduce a generic plugin activation framework.
## What changed
### MCP extension contribution
`codex-extension-api` gains an ordered `McpServerContributor` contract.
A contributor returns typed `Set` or `Remove` overlays for MCP server
configuration; later contributors win for the names they own.
The contract stays at the existing MCP configuration boundary.
Extensions do not create a second connection manager or transport
abstraction.
### Hosted Apps MCP extension
A new `codex-mcp-extension` contributes the reserved `codex_apps` server
from the existing Apps feature, ChatGPT base URL, path override, and
product SKU configuration.
When `apps_mcp_path_override` is enabled for `https://chatgpt.com`, the
resulting streamable HTTP endpoint is
`https://chatgpt.com/backend-api/ps/mcp`. The existing ChatGPT-auth gate
remains authoritative, so this server can run in an orchestrator-only
process without being exposed for API-key sessions.
### One resolved runtime view
`McpManager` now distinguishes three views:
- **configured:** config- and plugin-backed servers before extension
overlays;
- **runtime:** configured servers plus host-installed extension
contributions;
- **effective:** runtime servers after auth gating and compatibility
built-ins.
App-server installs the hosted MCP extension and uses the runtime view
for thread startup, refresh, status, threadless resource reads,
connector discovery, and MCP OAuth lookup. This keeps
`mcpServer/oauth/login` consistent with the servers exposed by the other
MCP APIs. The hosted Apps server itself continues to use existing
ChatGPT host authentication rather than MCP OAuth.
## Compatibility
Hosts that do not install the MCP extension retain the existing Apps MCP
synthesis path. This preserves current local-only, CLI, and
standalone-host behavior while app-server exercises the extension path.
Disabling Apps removes the reserved `codex_apps` entry, and losing
ChatGPT auth removes it from the effective runtime view. Executor
availability is not consulted for this HTTP transport.
## Follow-ups
The next vertical will resolve a manifest-declared stdio MCP server from
an executor-selected plugin root and execute it in the environment that
owns that root. Later verticals can add backend-owned skills, connector
metadata, hooks, durable selection semantics, and incremental local
convergence without changing the component-specific runtime boundaries
introduced here.
## Verification
Focused coverage was added for:
- contributing the hosted Apps MCP at `/backend-api/ps/mcp` without an
executor;
- requiring ChatGPT auth in the effective runtime view;
- removing a reserved configured Apps server when the Apps feature is
disabled.
`cargo check -p codex-app-server -p codex-mcp-extension -p
codex-extension-api -p codex-mcp` passed. Tests and Clippy were not run
locally under the current development instruction; CI provides the full
validation pass.
## Why
- `ThreadSource` currently defines a closed set of core-owned values
- Product features also create threads for background or scheduled work
- Adding every product-specific value to the core enum would require
repeated `codex-rs` protocol changes
- Feature-backed values let product callers provide precise attribution
while preserving the existing core classifications
## What Changed
- Adds `ThreadSource::Feature(String)` for app-owned thread source
values
- Represents all app-server v2 thread sources as scalar strings, so a
feature source is supplied as `"automation"`
- Persists and emits the feature's plain string label, so `"automation"`
produces `thread_source="automation"` in analytics
- Keeps `user`, `subagent`, and `memory_consolidation` as explicit
core-owned values and regenerates the app-server schemas and TypeScript
bindings
## Verification
- `just write-app-server-schema`
- `cargo check --workspace`
- `just test -p codex-protocol
feature_thread_source_serializes_as_its_app_owned_label`
- `just test -p codex-app-server-protocol
thread_sources_round_trip_as_scalar_labels`
- `cargo test -p codex-analytics
thread_initialized_event_serializes_expected_shape`
- `just fmt`
## Why
CCA is moving toward a split runtime where the orchestrator may not have
a filesystem, while executors can expose preinstalled plugins and
skills. A thread therefore needs to select capabilities without asking
app-server or core to interpret executor-owned paths through the
orchestrator's filesystem.
The longer-term model is broader than executor skills:
- A plugin is a bundle of skills, MCP servers, connectors/apps, and
hooks.
- A plugin root can be local, executor-owned, or hosted by a backend.
- Components inside one plugin can use different access and execution
mechanisms. A skill may be read from a filesystem or through backend
tools; an HTTP MCP server can run without an executor; a stdio MCP
server or hook needs an execution environment.
- Core should carry generic extension initialization data. The extension
that owns a component should discover it, expose it to the model, and
invoke it through the appropriate runtime.
This PR establishes that architecture through one complete vertical:
selecting a root on an executor, discovering the skills beneath it,
exposing those skills to the model, and reading an explicitly invoked
`SKILL.md` through the same executor.
## Contract
`thread/start` gains an experimental `selectedCapabilityRoots` field:
```json
{
"selectedCapabilityRoots": [
{
"id": "deploy-plugin@1",
"location": {
"type": "environment",
"environmentId": "workspace",
"path": "/opt/codex/plugins/deploy"
}
}
]
}
```
The root is intentionally not classified as a "plugin" or "skill" in the
API. It can point at a standalone skill, a directory containing several
skills, or a plugin containing skills and other components. This PR only
teaches the skills extension how to consume it; later extensions can
resolve MCP, connector, and hook components from the same selection.
The platform-supplied `id` is stable selection identity. The location
says which runtime owns the root and gives that runtime an opaque path.
App-server does not inspect or canonicalize the path.
## What changed
### Generic thread extension initialization
App-server converts selected roots into `ExtensionDataInit`. Core
carries that generic initialization value until the final thread ID is
known, then creates thread-scoped `ExtensionData` before lifecycle
contributors run.
This keeps `Session` and core independent of the capability-selection
contract. The initialization value is consumed during construction; it
is not retained as another long-lived `Session` field.
### Executor-backed skills
The skills extension now owns an `ExecutorSkillProvider` that:
- resolves the selected environment through `EnvironmentManager`
- discovers, canonicalizes, and reads skills through that environment's
`ExecutorFileSystem`
- contributes the bounded selected-skill catalog as stable developer
context
- reads an explicitly invoked skill body through the authority that
listed it
- warns when an environment or root is unavailable
- never falls back to the orchestrator filesystem for an executor-owned
root
Skill catalog and instruction fragments have hard byte bounds, which
also bound them below the 10K-token per-item context limit. If a
selected executor skill has the same name as a legacy local skill, the
executor selection owns that invocation and the local body is not
injected a second time.
Existing local and bundled skill loading remains in place. Omitting
`selectedCapabilityRoots` therefore preserves current local-only
behavior.
## Current semantics
- Only environment-owned locations are represented in this first
contract.
- Roots are resolved by the destination extension, not by app-server or
core.
- An unavailable executor or invalid root produces a warning and no
capabilities from that root; it does not trigger a local-filesystem
fallback.
- Selection applies to a newly started active thread.
- MCP servers, connectors, and hooks beneath a selected plugin root are
not activated yet.
- Selection is not yet persisted or inherited across resume, fork, or
subagent creation. Existing local capabilities continue to behave as
they do today in those flows.
## Planned vertical follow-ups
1. **Hosted HTTP MCP:** add an extension-backed HTTP MCP source that
works without an executor, then replace the special-purpose MCP plugins
loader with that implementation.
2. **Executor MCP:** register and execute stdio MCP servers through the
environment that owns the selected plugin root.
3. **Backend skills:** add a hosted skill source whose catalog and
bodies are accessed through extension tools rather than a filesystem.
4. **Connectors and hooks:** activate those components through their
owning extensions, using the same selected-root boundary and
component-specific runtime.
5. **Durable selection:** define the desired-selection lifecycle,
persist it, and make resume, fork, and subagent inheritance explicit
rather than accidental.
6. **Local convergence:** incrementally route existing local plugin,
skill, and MCP loading through the same extension model while preserving
current local behavior.
Each follow-up remains reviewable as an end-to-end capability. The
platform selects roots, generic thread extension data carries the
selection, and the owning extension resolves and operates its component.
## Verification
Coverage added for:
- app-server end-to-end discovery and explicit invocation of a skill
inside an executor-selected plugin root
- exclusive invocation when a selected executor skill collides with a
local skill name
- executor filesystem authority for discovery, canonicalization, and
reads
- thread extension initialization before lifecycle contributors run
- stable executor catalog context, explicit invocation, context
rebuilding, hidden skills, and preserved host/remote catalog behavior
Targeted protocol, core-skills, skills-extension, core lifecycle, and
app-server executor-skill tests were run during development.
## Why
Multi-agent v2 identifies agents by canonical paths, but its tool
handlers still emitted the larger legacy collaboration begin/end events
built around nickname and role metadata. App-server, rollout-trace,
analytics, and TUI consumers therefore lacked one compact path-based
completion signal that behaved consistently across live events and
replay.
The TUI also needs a bounded `/agent` status surface for v2 agents. It
should use recent local activity for previews, refresh liveness without
loading full histories, and keep the legacy picker available when no
path-backed v2 agent is known.
## What changed
- Replace the v2 `spawn_agent`, `send_message`, `followup_task`, and
`interrupt_agent` legacy lifecycle emissions with a success-only
`SubAgentActivity` event. The event records the tool call ID, occurrence
time, affected thread, canonical agent path, and `started`,
`interacted`, or `interrupted` kind.
- Expose the activity as a completion-only app-server v2
`subAgentActivity` thread item in live notifications and reconstructed
history, regenerate the protocol schemas, and count it in sub-agent tool
analytics.
- Track canonical paths from live activity and loaded-thread metadata in
the TUI, and render the activity in live and replayed transcripts.
- Make `/agent` list running path-backed agents with summaries from
bounded local event buffers. Each summary is capped at 240 graphemes,
the scan is capped at six recent items, only the last three wrapped
lines are shown, and command output is omitted. Liveness falls back to
metadata-only `thread/read` when local turn state is unavailable.
- Persist the activity as a terminal rollout-trace runtime payload and
reduce it to the corresponding spawn, send, follow-up, or close
interaction edge. `interrupt_agent` is classified as a close-edge
operation.
- Preserve the legacy picker when no path-backed v2 agent is known.
## Compatibility
App-server v2 clients that consumed `collabAgentToolCall` begin/end
pairs for these tools must handle the new completion-only
`subAgentActivity` item. Legacy v1 collaboration behavior is unchanged.
## Screenshot
<img width="684" height="288" alt="Screenshot 2026-06-08 at 15 40 47"
src="https://github.com/user-attachments/assets/194b3cd0-619d-45fb-b587-cf3e2b1b8a1d"
/>
## Testing
- `just test -p codex-app-server-protocol`
- `just test -p codex-rollout-trace`
- Added focused coverage for activity analytics, terminal trace
serialization, spawn-edge reduction, `interrupt_agent` classification,
TUI status rendering without aggregated command output, and clearing
stale running state after a completed turn.
Codex forces `core.fsmonitor=false` on internal Git commands so a
repository cannot select an executable fsmonitor helper. This also
disables Git's built-in daemon for `status`, `diff`, and `ls-files`,
turning those worktree reads into full scans in large repositories.
Read the raw effective `core.fsmonitor` value and preserve it only when
Git interprets it as true and advertises built-in daemon support through
`git version --build-options`. Query uncommon boolean spellings back
through Git using the exact effective value. Unset, false, helper paths,
malformed values, probe failures, and unsupported Git builds continue to
force `core.fsmonitor=false`.
Centralize this policy in `git-utils` while keeping process execution in
the existing local and workspace-command adapters. Probe once per
worktree workflow and reuse the result for its Git commands, including
the TUI `/diff` path. Metadata-only commands and repository discovery
remain disabled without probing. Each probe and requested Git process
keeps its own existing timeout, and the decision is not cached because
layered and conditional Git configuration can change while Codex runs.
---------
Co-authored-by: Chris Bookholt <bookholt@openai.com>
## Why
`log_remote_compact_failure` was the only consumer of the
compact-request logging payload and most of the token-usage breakdown
fields. Once that failure log is removed, keeping the surrounding
carrier types leaves dead plumbing in the compaction path and context
manager.
## What changed
- Remove `log_remote_compact_failure`, `CompactRequestLogData`, and the
v2 wrapper that only fed that log.
- Let both remote compaction implementations return the original
compaction error directly.
- Replace `TotalTokenUsageBreakdown` with a narrow helper that returns
only the remaining value needed by compaction analytics.
- Keep `estimate_response_item_model_visible_bytes` private to the
context manager implementation.
## Validation
- `cargo check -p codex-core`
## Why
Thread cwd and environment selections are a single logical setting in
core: updating one without the other can silently desynchronize the
next-turn execution context. This change makes that relationship
explicit in the internal thread settings flow while preserving the
existing app-server public API shape.
## What changed
- Moved the cwd/environment pair through internal
`ThreadSettingsOverrides.environment_settings` instead of a top-level
internal `cwd` field.
- Kept `thread/settings/update` public params unchanged, with app-server
translating top-level `cwd` into the paired internal settings shape.
- Moved `Op::UserInput` environment overrides into thread settings so
user turns and settings updates use the same core path.
- Updated core, app-server, MCP, memories, sample, and test callsites to
construct the paired settings shape.
## Verification
- `git diff --check`
- Local test run starting after PR creation.
## Summary
- tighten the default multi-agent v2 root and subagent usage hints to
bias toward local work
- add a pre-call gate to the v2 spawn_agent description for independent,
bounded, parallelizable subtasks
## Validation
- just fmt
- started just test -p codex-core, but it was interrupted before
completion per follow-up request to commit and push immediately
## Why
Auto Review should remain the effective approval reviewer when settings
cross runtime boundaries. A config or app-server round trip must not
change the reviewer identity, and delegated work must not silently fall
back to user review.
This requires both a stable canonical serialized value and propagation
of the effective setting. `auto_review` is the canonical value across
protocol and app-server output, while `guardian_subagent` remains
accepted as backward-compatible input.
## What changed
- serialize `ApprovalsReviewer::AutoReview` consistently as
`auto_review` across core protocol and app-server v2
- continue accepting `guardian_subagent` when reading existing config or
client requests
- carry the active turn's approval reviewer into spawned agents
- update config/debug expectations and add delegated-task regression
coverage
## Scope
This does not change Guardian policy or remove compatibility with
existing `guardian_subagent` inputs. It preserves the selected reviewer
across serialization, config reloads, app-server settings, and delegated
task setup.
Related Guardian changes are split independently:
- #26231 adds denials and soft denials
- #26334 retries transient reviewer failures
- #26333 reuses narrowly scoped low-risk approvals
- #26232 adds TUI denial recovery
## Validation
- `just test -p codex-app-server-protocol` (224 passed)
- regression coverage for delegated task reviewer propagation
- serialization coverage for canonical `auto_review` output and legacy
`guardian_subagent` input
---------
Co-authored-by: saud-oai <saud@openai.com>
## Why
Compaction analytics adds retained image count and compaction summary
output tokens for v1.5 specifically.
## What changed
- Add nullable `retained_image_count` and `compaction_summary_tokens`
fields to `codex_compaction_event`.
- Populate them only for `responses_compaction_v2`: retained images come
from the retained v2 compacted history, and summary tokens come from
`response.completed.token_usage.output_tokens`.
- Leave local and legacy remote compaction events as `null` for these
detail fields.
## Verification
- `just fmt`
- `just fix -p codex-core`
- `just test -p codex-core
build_v2_compacted_history_counts_retained_input_images`
- `git diff --check`
jif ·
rhan-oai ·
sayan-oai ·
pakrym-oai ·
Ahmed Ibrahim ·
xl-openai ·
Curtis 'Fjord' Hawthorne ·
Celia Chen ·
Jeremy Rose ·
guinness-oai ·
e-provencher ·
Eric Traut ·
Alex Daley ·
kbazzi ·
Adam Perry @ OpenAI ·
Charlie Marsh ·
mchen-oai ·
marksteinbrick-oai ·
Tamir Duberstein ·
Boyang Niu ·
viyatb-oai ·