In https://github.com/openai/codex/actions/runs/27308011621,
publishing the npm tarballs serially took 147 seconds. Six platform
packages and the responses API proxy are independent.
Publish those packages concurrently, then publish the root CLI wrapper
and SDK in dependency order. Individual platform publishes took 19 to
23 seconds, so this should reduce total release time by nearly two
minutes.
## Why
`ext/skills` currently depends on `codex-core` for two host concerns:
reading the concrete `Config` type and borrowing core-owned
model-context fragment types. That coupling prevents the extension from
being assembled independently above core and leaves context that belongs
to the skills feature owned by core.
This stacked PR introduces the host boundary needed for the broader
extension migration while intentionally preserving existing skills
behavior. It is stacked on #27404.
## What changed
- Adds a small public `SkillsExtensionConfig` view and makes skills
installation generic over the host config type.
- Requires the host to map its config into that view; app-server
supplies the current `Config` values.
- Moves the available-skills and selected-skill context fragment
implementations into `ext/skills`, preserving their roles, markers, and
rendered bytes.
- Removes the direct `codex-core` dependency from
`codex-skills-extension`.
- Keeps local discovery, invocation, side effects, and the
`codex-core-skills` compatibility types unchanged for later staged PRs.
## Behavior
This adds no capability and is intended to have no user-visible or
model-visible behavior change. The install API and ownership boundary
change internally; emitted skills context remains byte-for-byte
compatible.
## Validation
- Updates the skills extension integration coverage to use a host-owned
test config.
- Asserts the complete rendered catalog and selected-skill fragments,
including their roles and markers.
- `just bazel-lock-check`
- Rust tests and Clippy were not run locally per request; CI will run
them.
## Why
Hosted skills introduced by #27388 use opaque `skill://` resource
identifiers, but the skills catalog rendered every locator as a `file`
and told the model that every skill body lived on disk. That can send
the model toward filesystem tools for a resource that must instead be
read through its owning authority.
The catalog should describe how each source is accessed without changing
the underlying discovery or invocation behavior.
## What changed
- Render host skills as `file`, executor-owned skills as `environment
resource`, orchestrator-owned skills as `orchestrator resource`, and
custom-provider skills as `custom resource`.
- Update the shared no-alias guidance to describe source locators rather
than assuming every skill is stored on the host filesystem.
- Direct orchestrator resources through `skills.list` and `skills.read`,
and explicitly tell the model not to treat `skill://` identifiers as
filesystem paths.
- Preserve the existing filesystem and alias behavior for local skills.
## Scope
This PR changes only model-visible catalog rendering and guidance. It
does not change skill discovery, selection, prompt injection, provider
routing, catalog caching or refresh behavior, resource validation, or
the `skills.*` tool contract.
## Verification
- Extended skills-extension coverage for host-file and executor-resource
labels.
- Extended the no-executor app-server flow to assert
orchestrator-resource wording and non-filesystem guidance.
## Why
PR #27388 lets models read child resources referenced by backend plugin
skills without an executor. The integration fixture should prove that
real flow: the injected `SKILL.md` advertises a child `skill://`
resource, and `skills.read` resolves that exact resource through the
backend provider.
This is stacked on #27388.
## What changed
- Adds a child-resource link to the backend skill fixture and asserts
that it reaches model context.
- Tightens the end-to-end skills test around `skills.list` followed by
`skills.read` for the referenced resource.
- Splits the existing app-server `mcpResource/read` coverage into a
focused test so the generic RPC path remains covered independently.
## Validation
- Adds app-server integration coverage for both the referenced backend
skill resource and the generic MCP resource read path.
## 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
PR #27387 makes backend plugin skills discoverable and invocable without
an executor, but resources referenced by those skills still sit behind
the generic MCP resource surface. The model needs a skills-owned API
that preserves the provider authority and package boundary instead of
treating remote resources like local files.
This is stacked on #27387.
## What
- Adds one `skills` namespace with bounded `list` and `read` tools for
remote skill providers.
- Revalidates `authority + package` against the live remote catalog on
every read, then routes the opaque resource ID back through that
provider.
- Allows the backend provider to read canonical child `skill://`
resources while rejecting cross-package, non-canonical, query, fragment,
and traversal-shaped URIs.
- Caps each serialized tool result at 8 KB. Lists are paginated; reads
return an opaque continuation cursor.
- Marks the JSON output as external context so memory generation can
apply its normal suppression policy.
- Deliberately does not add `skills.search`; that waits for a bounded
plugin-service search contract.
## Tool contract
Pseudo-Python matching the wire shape:
```python
from typing import Literal, NotRequired, TypedDict
class RemoteSkillAuthority(TypedDict):
kind: Literal["remote"]
id: str # e.g. "codex_apps"
class RemoteSkill(TypedDict):
authority: RemoteSkillAuthority
package: str # opaque provider-owned package ID
name: str
description: str
main_resource: str # opaque provider-owned SKILL.md ID
class SkillsListParams(TypedDict):
cursor: NotRequired[str]
class SkillsListResult(TypedDict):
skills: list[RemoteSkill]
next_cursor: str | None
warnings: list[str]
truncated: bool
class SkillsReadParams(TypedDict):
authority: RemoteSkillAuthority # copied from skills.list
package: str # copied from skills.list
resource: str # provider-owned child resource ID
cursor: NotRequired[str] # copy next_cursor to continue
class SkillsReadResult(TypedDict):
resource: str
contents: str
next_cursor: str | None
truncated: bool
class Skills:
def list(self, params: SkillsListParams) -> SkillsListResult: ...
def read(self, params: SkillsReadParams) -> SkillsReadResult: ...
```
There is one namespace for all remote skills, not one tool or MCP server
per skill. No resource ID is converted into a filesystem path.
## Backend dependency
`/ps/mcp` must support direct reads of child resources such as
`skill://plugin_demo/deploy/references/deploy.md`. This PR implements
and tests the Codex side of that contract; production child reads remain
dependent on the corresponding plugin-service support. Search remains
out of scope until that service exposes a bounded search/resource API.
## Validation
- Added an app-server integration test covering `skills.list` followed
by `skills.read` with no executor.
- Ran `just fmt`.
- Ran `just bazel-lock-update` and `just bazel-lock-check`.
- Did not run Rust tests or Clippy locally, per request; CI will run
them.
## 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`
## Summary
- cache the first remote skill catalog outcome per thread, including
failures
- preserve discovery errors as catalog warnings
- update the existing cache regression test to verify failed discovery
is attempted once
## Why
A failed or hanging `codex_apps` `resources/list` call could run once
while building initial context and immediately again while contributing
first-turn input. With the discovery timeout, an ordinary Apps turn
could wait up to 20 seconds before inference and retry again on later
turns even when no remote skill was mentioned.
Caching a warning-only empty catalog preserves graceful degradation
while preventing repeated synchronous discovery attempts.
## Testing
- `just fmt`
- Tests and Clippy not run per request; CI will validate the change.
## 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
- Increase the cloud config bundle background refresh interval from 5
minutes to 15 minutes.
- Increase the local cloud config bundle cache TTL from 30 minutes to 1
hour.
## Why
- Reduce background cloud config fetch frequency while keeping cached
workspace-managed policies available longer between refreshes.
## Validation
- `just fmt`
- `cargo test -p codex-cloud-config`
## 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`
## Summary
- Preserve ICC profiles and EXIF metadata when resizing and re-encoding
prompt images.
- Retain EXIF orientation metadata without rotating or otherwise
modifying the pixel data locally.
- Support metadata preservation for PNG, JPEG, and WebP outputs.
- Continue returning the original bytes when an image does not require
re-encoding.
This intentionally preserves the metadata most important for rendering
prompt images faithfully. Other format-specific metadata is not copied.
## Motivation
Client-side resizing previously discarded image metadata during
re-encoding. This could lose color-profile information and EXIF
orientation needed by downstream image consumers.
#### [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
## 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
Default tool search text currently derives identity from both `ToolName`
and `ToolSpec`. For function and namespace specs, this indexes the same
names more than once and also adds a flattened `{namespace}{name}` token
that is not model-visible.
## What changed
- Derive default search text entirely from `ToolSpec` while preserving
names, descriptions, namespace metadata, and recursive schema metadata.
- Keep the default search-text builder private and remove the unused
`ToolName` argument.
- Add coverage for the exact search text generated for a namespaced tool
with nested schema metadata.
## Example
For the `codex_app` namespace and `automation_update` tool (schema terms
omitted):
- Before: `codex_appautomation_update automation update codex_app
codex_app Manage Codex automations. automation_update automation update
...`
- After: `codex_app Manage Codex automations. automation_update
automation update ...`
## Testing
- `just test -p codex-tools`
## Summary
- Expand the hosted web search prompt with explicit Markdown-link
citation guidance.
- Keep internal `turnX` reference IDs out of final responses and place
citations next to supported claims.
## Context
https://openai.slack.com/archives/C0AU83S0ZQU/p1781133381448499?thread_ts=1780352049.512299&cid=C0AU83S0ZQU
## Test plan
- Confirmed `codex-rs/ext/web-search/web_run_description.md` exactly
matches the supplied target prompt.
- `UV_CACHE_DIR=/tmp/codex-uv-cache
PATH=/tmp/codex-just/bin:/home/dev-user/.rustup/toolchains/1.95.0-x86_64-unknown-linux-gnu/bin:$PATH
python3 scripts/format.py --check`
- `git diff --check`
## 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`
## Why
The TUI still reached through `codex-app-server-client::legacy_core` for
process telemetry setup and personality migration, exposing core-only
details after the TUI moved onto the app-server layer.
This is part of our ongoing efforts to whittle away at the legacy_core
shim that was left over after migrating the TUI to the app server.
This change is just a refactor/rename and should be behavior-neutral and
low risk.
## What changed
- expose OTEL provider construction through the app-server client and
keep the small process/SQLite telemetry adapters local to the TUI
- collapse personality migration results to the config-reload decision
the TUI needs
- remove the `legacy_core::otel_init` and
`legacy_core::personality_migration` subnamespaces
## 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
The app server exposes `thread/delete`, but users cannot invoke it from
the CLI or TUI. Because deletion is irreversible, the user-facing
commands need deliberate confirmation and safer handling of name-based
targets.
- Add `codex delete <SESSION>` with interactive confirmation,
restricting `--force` to UUID targets.
- Resolve exact names across active and archived sessions, including
renamed sessions, and validate prompted UUID targets before
confirmation.
- Add a `/delete` command with a confirmation popup that warns the
current session and its subagent threads will be permanently deleted.
## Manual testing
- Deleted by UUID with `--force` and verified the rollout, session-index
entry, and database row were removed.
- Exercised name-based confirmation for both cancellation and
affirmative deletion; cancellation preserved the session and
confirmation removed it.
- Verified deletion refuses to proceed without `--force`, while
`--force` rejects names, including duplicate names.
- Verified duplicate-name confirmation displays the concrete UUID
selected.
- Deleted an archived session by name.
- Verified an already-missing UUID fails before displaying a
confirmation prompt.
- Exercised `/delete` in the TUI: the popup defaults to No, cancellation
preserves the session, and confirmation deletes the session and exits.
- Verified that `codex delete` works for both archived and non-archived
sessions.
## Why
The TUI now sits on the app-server layer, but
`app-server-client::legacy_core` still exposed core test helpers solely
for TUI tests. We've been whittling away the remaining dependencies.
This is the next step on that journey.
There is no functional change — just a refactor, and this affects only
test code, so it should be low risk.
## What changed
- remove the `legacy_core::test_support` re-export and call
model-manager test helpers directly
- keep the bundled model-preset cache local to TUI test support
- import constraint types directly from `codex-config`
## Summary
- remove the redundant `needsAuth` field from `AppSummary` and generated
app-server schemas
- stop `plugin/read` from querying Apps MCP solely to hydrate unused
connector auth state
- preserve `plugin/install.appsNeedingAuth` membership and
`app/list.isAccessible` as the authentication signals
## Why
Codex App and TUI do not consume `plugin/read.plugin.apps[].needsAuth`.
Hydrating it could establish an Apps MCP connection and discover tools
on a cold `plugin/read` request, adding avoidable latency. The plugin
APIs are still marked under development, so removing this wire field is
preferable to retaining a misleading default.
## Verification
- `just write-app-server-schema`
- `just fmt`
- `just test -p codex-app-server-protocol`
- `just test -p codex-app-server
plugin_install_uses_remote_apps_needing_auth_response`
- `just test -p codex-app-server
plugin_install_returns_apps_needing_auth`
- `just test -p codex-app-server
plugin_read_returns_plugin_details_with_bundle_contents`
- `just test -p codex-tui
plugin_detail_popup_snapshot_shows_install_actions_and_capability_summaries`
- `$xin-build` simplify and debug reviews
## 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
Bazel compiles Cargo build scripts in the exec configuration. For
`openssl-sys`, that means the target-specific optional `openssl-src`
dependency can disappear when producing musl release binaries, even
though the build script still needs the vendored source crate.
## What changed
Patch `rules_rs` to expose its existing unconditional
`build_script_deps` input through `crate.annotation`, then annotate
`openssl-sys` with the pinned `openssl-src` target. Target-derived build
dependencies continue to use the existing selected dependency path.
## Validation
- `just bazel-lock-check`
Stack: 2 of 6. Follows #27321.
## Why
Currently, the analytics reducer omits `codex_turn_event` for internally
started subagent turns
- It uses `TurnState.connection_id` to select app-server client and
runtime metadata
- `turn/start` sets this field for client-started turns, while internal
subagent turns bypass that path
- Spawned child threads inherit the correct connection, but turn
emission does not use thread state
## What Changed
- Keeps explicit `TurnState.connection_id` authoritative for
client-started turns
- Falls back to the matching thread’s inherited connection when the turn
connection is absent
- Preserves completeness gates, event schema, and post-emission state
removal
- Extends subagent lifecycle test coverage
## Verification
- `just test -p codex-analytics` (71 tests passed)
- `just fix -p codex-analytics`
- `just fmt`
## Summary
Add shared image-processing primitives needed for centralized image
preparation in a follow-up PR.
- Add `load_data_url_for_prompt` for decoding and preparing base64 image
data URLs.
- Add configurable maximum-dimension and 32px patch-budget resizing.
- Enforce a 1 GiB sanity limit on both encoded and decoded data-URL
representations.
- Preserve original PNG, JPEG, and WebP bytes when resizing is
unnecessary.
- Preserve the existing GIF-to-PNG behavior.
- Move image utility tests into the existing sidecar test module.
## Behavior
This PR is intended to be runtime behavior-preserving.
Existing production callers continue using
`PromptImageMode::ResizeToFit` and `PromptImageMode::Original` with
their existing semantics. The new data-URL entrypoint and configurable
resize mode have no production callers in this PR; they are used by the
next PR in the stack.
This PR does not change user-input handling, `view_image`, history
insertion, request construction, HTTP image URL forwarding, or
app-server behavior.
#### [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
## Why
Exec-server observability needs current-value measurements in addition
to counters. The reusable OTEL client should expose that primitive
without coupling it to exec-server runtime behavior.
## What changed
- Adds integer gauge instruments, with optional descriptions.
- Caches gauges by name and description so instrument metadata remains
part of the declaration identity.
- Covers gauge values, descriptions, merged attributes, and OTLP HTTP
export.
This PR only adds the gauge primitive. It does not add second-based
duration histograms or exec-server adoption.
## Stack
1. #26091: counter descriptions
2. **#27057: gauge instruments**
3. #27058: second-based duration histograms
Related independent coverage: #27059 tests OTLP HTTP log and trace event
export.
## Validation
- `just test -p codex-otel`
- `just fix -p codex-otel`
- `just fmt`
## 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
The release job already downloads every workflow artifact into `dist`,
but npm staging creates a new cache and downloads the six target
artifacts again.
Reuse `dist` as the staging script's artifact cache while preserving the
existing download fallback for missing artifacts and standalone callers.
The script retains ownership of temporary caches but does not delete a
caller-provided directory.
In https://github.com/openai/codex/actions/runs/27242495616, the
duplicate
download transferred 3.3 GiB and took 4 minutes 13 seconds. This should
reduce total release time by about 4 minutes.
## 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
External-agent import should be discoverable and deliberate without
blocking startup or claiming the public `codex [PROMPT]` CLI namespace.
The slash command keeps the flow local to the interactive TUI and reuses
the existing app-server import API.
## What changed
- add the user-facing `/import` slash command
- detect external-agent importable items only when the command is
invoked
- run imports through the embedded local app-server
- show start and completion messages, refresh configuration, and block
duplicate imports while one is pending
- reject the flow for unsupported remote and local-daemon sessions
## Validation
- `just test -p codex-tui external_agent_config_migration` (10 passed)
- manually exercised an isolated TUI fixture with existing
external-agent setup and session data using a fresh `CODEX_HOME`
- verified picker customization, plugin and session detection, import
completion, repeated invocation, and imported-session resume context
- the broader `just test -p codex-tui` run passed 2,805 tests, with 2
unrelated guardian feature-flag failures and 4 skipped tests
## Draft follow-ups
- review whether completion messaging should remain attached to the
initiating chat if the user switches chats during an import
- review shutdown semantics for an in-progress background import
## Stack
1. [#27064](https://github.com/openai/codex/pull/27064): remove the
startup migration flow
2. [#27065](https://github.com/openai/codex/pull/27065): extract the
picker renderer
3. [#27070](https://github.com/openai/codex/pull/27070): add the
external-agent import picker UX
4. [#27071](https://github.com/openai/codex/pull/27071): expose the flow
through `/import`
**This PR is stack item 4.** Draft while the lower stack dependencies
are reviewed.
## Intent
Keep release-specific Bazel helpers out of the shared Rust crate
definitions and colocate them with Bazel platform configuration.
## Implementation
Moves `multiplatform_binaries` and its platform list from `defs.bzl`
into `bazel/platforms/release_binaries.bzl` and updates the CLI load
site. Behavior is unchanged.
## Validation
- `bazel query //codex-rs/cli:release_binaries`
Stack: 1 of 6.
## Why
Users need to understand what external-agent data Codex detected, what
is selected, and how to proceed before an import begins. The updated
picker makes focus, selection state, and the submission path explicit
while preserving the existing import backend.
## What changed
- replace the old migration prompt with a two-step external-agent import
picker
- add a customize view with explicit item focus, selection state,
counts, and a review action
- separate detected import data into a view model
- add Unix and Windows snapshots for prompt, item-focus, and
action-focus states
## Validation
- `just test -p codex-tui external_agent_config_migration` (10 passed)
- manually exercised an isolated TUI fixture covering customization,
selection toggles, review, import, repeated invocation, and session
resume
- the broader `just test -p codex-tui` run passed 2,805 tests, with 2
unrelated guardian feature-flag failures and 4 skipped tests
## Review note
This is the largest layer in the stack because the interaction state,
rendering changes, and required snapshots move together. It remains a
draft in case reviewers prefer a further presentation/state split.
## Stack
1. [#27064](https://github.com/openai/codex/pull/27064): remove the
startup migration flow
2. [#27065](https://github.com/openai/codex/pull/27065): extract the
picker renderer
3. [#27070](https://github.com/openai/codex/pull/27070): add the
external-agent import picker UX
4. [#27071](https://github.com/openai/codex/pull/27071): expose the flow
through `/import`
**This PR is stack item 3.** Draft while the lower stack dependencies
are reviewed.
## 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.
## Why
The external-agent import picker is easier to review when its rendering
refactor lands separately from new state and interaction behavior. This
layer is intended to be behavior-neutral.
## What changed
- extract external-agent migration rendering into a dedicated `render`
module
- preserve existing behavior while separating presentation from
interaction logic
- establish a smaller foundation for the import picker UX in the next PR
## Validation
- `just test -p codex-tui external_agent_config_migration` (10 passed)
## Stack
1. [#27064](https://github.com/openai/codex/pull/27064): remove the
startup migration flow
2. [#27065](https://github.com/openai/codex/pull/27065): extract the
picker renderer
3. [#27070](https://github.com/openai/codex/pull/27070): add the
external-agent import picker UX
4. [#27071](https://github.com/openai/codex/pull/27071): expose the flow
through `/import`
**This PR is stack item 2.** Draft while the lower stack dependency is
reviewed.
## 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
External-agent import should be initiated deliberately instead of
interrupting eligible TUI startups. This cleanup removes the blocking
startup flow before the replacement import experience is introduced
later in the stack.
## What changed
- remove the startup-blocking external-agent migration prompt
- remove the now-unused external migration feature gate
- remove the obsolete TUI app-server migration wrappers
- retain the dormant picker behind a module-scoped dead-code allowance
until the next stack item wires it back in
- keep normal TUI startup focused on entering Codex immediately
## Validation
- `bazel build --config=clippy //codex-rs/tui:tui
//codex-rs/tui:tui-unit-tests-bin`
- `just test -p codex-tui external_agent_config_migration` (8 passed)
- `just test -p codex-tui` (2,786 passed, 12 unrelated local
environment-sensitive failures, 4 skipped)
- `just fix -p codex-tui`
- `just fmt`
## Stack
1. [#27064](https://github.com/openai/codex/pull/27064): remove the
startup migration flow
2. [#27065](https://github.com/openai/codex/pull/27065): extract the
picker renderer
3. [#27070](https://github.com/openai/codex/pull/27070): add the
external-agent import picker UX
4. [#27071](https://github.com/openai/codex/pull/27071): expose the flow
through `/import`
**This PR is stack item 1.**
Further investigation of the sqlite incidents showed that the problems
are due to corruption from the older version of SQLite that we recently
upgraded, and that the data is truly corrupted in the root database --
recovery of all data is not possible. Given that the data is
reconstructable from the rollouts on disk, we should just auto-backup
the database and let codex rebuild the rollout info from the disk
rollouts.
The new behavior is that appserver auto-backs-up and rebuilds (with logs
reflecting that behavior). The CLI now pops a message letting you know
this happened and the paths of the backed-up corrupt db and the new
database. There is also context added so that the desktop app can read
the rebuild info from it and inform the user with it.
Tamir DubersteinandGitHub
jifandGitHub
alexsong-oaiandGitHub
rhan-oaiandGitHub
sayan-oaiandGitHub
Curtis 'Fjord' HawthorneandGitHub
pakrym-oaiandGitHub
Ahmed IbrahimandGitHub
xl-openaiandGitHub
Celia ChenandGitHub
yuning-oaiandGitHub
Eric TrautandGitHub
Jeremy RoseandGitHub
Adam Perry @ OpenAIandGitHub
marksteinbrick-oaiandGitHub
richardopenaiandGitHub
guinness-oaiandGitHub
e-provencherandGitHub
stefanstokic-oaiandGitHub
Michael BolinandGitHub
Alex DaleyandGitHub
kbazziandGitHub
David de RegtandGitHub