## Summary
This fixes plugin manifest parsing for MCP servers declared as an object
directly in `plugin.json`.
Before this change, Codex modeled `mcpServers` as only a string path,
for example:
```json
{
"name": "counter-sample",
"version": "1.1.1",
"mcpServers": "./.mcp.json"
}
```
Some migrated plugins instead provide the server map directly in the
manifest:
```json
{
"name": "counter-sample",
"version": "1.1.1",
"description": "Plugin that declares MCP servers in the manifest",
"mcpServers": {
"counter": {
"type": "http",
"url": "https://sample.example/counter/mcp"
}
}
}
```
That object form previously failed during install/load with an error
like:
```text
failed to parse plugin manifest: invalid type: map, expected a string
```
## What changed
- Add a manifest representation for `mcpServers` as either
`Path(Resource)` or `Object(map)`.
- Parse `plugin.json` `mcpServers` as either a string path or an object.
- Route object-valued MCP server maps through the existing plugin MCP
config parser instead of adding a second parser.
- Apply existing per-plugin MCP server policy to object-valued MCP
servers the same way as file-backed MCP servers.
- Include object-valued MCP server names in plugin telemetry/capability
metadata.
- Support object-valued MCP config for executor plugins without
requiring a `.mcp.json` filesystem read.
- Update the bundled plugin-creator validator and `plugin-json-spec.md`
so generated-plugin validation accepts the same object-valued shape.
## Compatibility
Existing plugin manifests that use `"mcpServers": "./.mcp.json"`
continue to work. Plugins can now also use the object shape shown above.
## Tests
Added coverage for the new manifest attribute shape at the install,
normal load, telemetry, and executor-provider layers:
- `install_accepts_manifest_mcp_server_objects`
- `load_plugins_loads_manifest_mcp_server_objects`
- `plugin_telemetry_metadata_uses_manifest_mcp_server_objects`
- `reads_manifest_object_config_without_executor_file_system_access`
Also smoke-tested the plugin-creator validator against both supported
forms:
- `mcpServers` as a direct object in `plugin.json`
- `mcpServers` as `"./.mcp.json"` with a companion `.mcp.json`
## Validation
- `just test -p codex-plugin`
- `just test -p codex-core-plugins`
- `just test -p codex-mcp-extension`
- `just bazel-lock-update`
- `just bazel-lock-check`
- `just fmt`
- `git diff --check`
- Focused rename/object-form rerun: `just test -p codex-core-plugins
manager::tests::load_plugins_loads_manifest_mcp_server_objects
manager::tests::plugin_telemetry_metadata_uses_manifest_mcp_server_objects
store::tests::install_accepts_manifest_mcp_server_objects`
- Focused executor rerun: `just test -p codex-mcp-extension
executor_plugin::provider::tests::reads_manifest_object_config_without_executor_file_system_access`
- `python3
codex-rs/skills/src/assets/samples/plugin-creator/scripts/validate_plugin.py
/private/tmp/codex-validator-object`
- `python3
codex-rs/skills/src/assets/samples/plugin-creator/scripts/validate_plugin.py
/private/tmp/codex-validator-path`
## Why
`fs/readFile` buffers the entire file in one response, which makes large
remote reads expensive and prevents callers from applying backpressure.
We need an opt-in streaming path with bounded block sizes while
preserving the existing single-call API for small and sandboxed reads.
## What changed
- Add `ExecServerClient::stream`, returning a named `FileReadStream`
that implements `futures::Stream` and yields immutable 1 MiB byte
blocks.
- Add internal `fs/open`, `fs/readBlock`, and `fs/close` RPCs.
`fs/readBlock` accepts an explicit offset and length.
- Keep unsandboxed files open between block reads, cap open handles per
connection, and clean them up on EOF, error, stream drop, explicit
close, or connection shutdown.
- Reject platform-sandboxed streaming opens instead of turning the
one-shot sandbox helper into a persistent server. Existing `fs/readFile`
behavior is unchanged.
## Testing
- `just test -p codex-exec-server`
- Integration coverage for 1 MiB chunking, exact block-boundary EOF,
sandbox rejection, and continued reads from the opened file after path
replacement.
- Handle-manager coverage for non-sequential offsets, variable block
lengths, the 128-handle limit, and capacity release after close.
## Why
Multi-agent v2 messages need a consistent, model-visible envelope that
identifies what kind of interaction occurred, who sent it, and which
agent it targets. Previously, encrypted deliveries exposed only
`encrypted_content`, while child completion used the legacy
`<subagent_notification>` shape. That meant the client could not
consistently present `NEW_TASK`, `MESSAGE`, and `FINAL_ANSWER` using the
same format.
This change adds the routing envelope as plaintext while keeping task
and message payloads encrypted. No new Responses API field is required:
an encrypted delivery is represented as an `input_text` header
immediately followed by its existing `encrypted_content` item.
Every envelope now follows this shape:
```text
Message Type: <NEW_TASK | MESSAGE | FINAL_ANSWER>
Task name: <recipient agent path>
Sender: <author agent path>
Payload:
<message payload>
```
## Message types
### `NEW_TASK`
`NEW_TASK` is used when the recipient should begin a new turn, including
an initial `spawn_agent` task and a later `followup_task`.
For a root agent spawning `/root/worker`, the request contains a
plaintext envelope followed by the encrypted task:
```json
{
"type": "agent_message",
"author": "/root",
"recipient": "/root/worker",
"content": [
{
"type": "input_text",
"text": "Message Type: NEW_TASK\nTask name: /root/worker\nSender: /root\nPayload:\n"
},
{
"type": "encrypted_content",
"encrypted_content": "<encrypted task payload>"
}
]
}
```
Conceptually, the model receives:
```text
Message Type: NEW_TASK
Task name: /root/worker
Sender: /root
Payload:
Review the authentication changes and report any regressions.
```
### `MESSAGE`
`MESSAGE` is used for a queued `send_message` delivery. It communicates
with an existing agent without starting a new turn.
For `/root/worker` reporting progress to the root agent, the request
contains:
```json
{
"type": "agent_message",
"author": "/root/worker",
"recipient": "/root",
"content": [
{
"type": "input_text",
"text": "Message Type: MESSAGE\nTask name: /root\nSender: /root/worker\nPayload:\n"
},
{
"type": "encrypted_content",
"encrypted_content": "<encrypted message payload>"
}
]
}
```
Conceptually, the model receives:
```text
Message Type: MESSAGE
Task name: /root
Sender: /root/worker
Payload:
The protocol tests pass; I am checking the resume path now.
```
### `FINAL_ANSWER`
`FINAL_ANSWER` is emitted when a child agent reaches a terminal state
and reports its result to its parent. Completion payloads are already
available locally, so the complete envelope is represented as plaintext
rather than as a plaintext header plus encrypted content.
For `/root/worker` completing work for the root agent, the request
contains:
```json
{
"type": "agent_message",
"author": "/root/worker",
"recipient": "/root",
"content": [
{
"type": "input_text",
"text": "Message Type: FINAL_ANSWER\nTask name: /root\nSender: /root/worker\nPayload:\nNo regressions found."
}
]
}
```
The model-visible form is:
```text
Message Type: FINAL_ANSWER
Task name: /root
Sender: /root/worker
Payload:
No regressions found.
```
Errored, shut down, and missing agents also use `FINAL_ANSWER`, with a
terminal-status description in the payload.
## What changed
- Render `NEW_TASK` or `MESSAGE` in
`InterAgentCommunication::to_model_input_item`, based on whether the
encrypted delivery starts a turn.
- Replace the multi-agent v2 `<subagent_notification>` completion
payload with a model-visible `FINAL_ANSWER` envelope.
- Document `Task name`, `Sender`, and `Payload` consistently in the
multi-agent developer instructions.
- Prevent local-only history projections from treating an encrypted
message's plaintext header as the complete assistant message.
- Preserve rollout-trace interaction edges when an agent message
contains both plaintext and encrypted content.
Legacy multi-agent behavior remains unchanged.
## Verification
- `just test -p codex-protocol`
- `just test -p codex-rollout-trace`
- `just test -p codex-web-search-extension`
- `just test -p codex-core
encrypted_multi_agent_v2_spawn_sends_agent_message_to_child`
- `just test -p codex-core
plaintext_multi_agent_v2_completion_sends_agent_message`
- `just test -p codex-core
multi_agent_v2_followup_task_completion_notifies_parent_on_every_turn`
- `just test -p codex-core
multi_agent_v2_completion_queues_message_for_direct_parent`
The workspace denies `clippy::expect_used` in production. Although
`clippy.toml` allows `expect` in tests, Bazel Clippy compiles
integration-test helper code in a way that does not receive that
exemption, which encouraged verbose `unwrap_or_else(... panic!(...))`
and equivalent `match`/`let else` forms.
This allows `clippy::expect_used` once at each integration-test crate
root (including aggregated suites and test-support libraries), then
replaces manual panic-based Result and Option unwraps with
`expect`/`expect_err`. Standalone `tests/*.rs` files remain their own
crate roots. Intentional assertion and unexpected-variant panics remain
unchanged, and the production `expect_used = "deny"` lint remains in
place.
The cleanup is mechanical and net-negative in line count.
## Why
Progress towards letting app-server and exec-server run on different
platforms, specifically for sandbox configuration.
## What
- Make the filesystem path containment hierarchy generic, defaulting to
`AbsolutePathBuf` for now.
- Have clients specify `AbsolutePathBuf` or `PathUri` directly where
needed.
- Use `PathUri` throughout exec-server filesystem protocol and trait
boundaries.
- Implement `From` for conversion to path URIs and `TryFrom` for
fallible conversion to absolute paths through the generic type
hierarchy.
## Description
This PR adds an optional `metadata` field to `ResponseItem` for
Responses API calls. Only mechanical plumbing, no actual values
populated and sent yet. Turns out just adding a new field to
`ResponseItem` has quite a large blast radius already.
This change is backwards compatible because `metadata` is optional and
omitted when absent, so existing response items and rollout history
without it still deserialize and requests that do not set it keep the
same wire shape. For provider compatibility, we strip out `metadata`
before non-OpenAI Responses requests so Azure and AWS Bedrock never see
this field.
My followup PR here will actually make use of it to start storing and
passing along `turn_id`: https://github.com/openai/codex/pull/28360
## What changed
- Added `ResponseItemMetadata` with optional `turn_id`, plus optional
`metadata` on Responses API item variants and inter-agent communication.
- Preserved item metadata through response-item rewrites such as
truncation, missing tool-output synthesis, compaction history
rebuilding, visible-history conversion, rollout/resume, and generated
app-server schemas/types.
- Strip item metadata from non-OpenAI Responses requests while
preserving it for OpenAI-shaped requests.
- Updated the mechanical fixture/test construction churn required by the
new optional field.
## Why
Hosted orchestrator skills are read through the remote MCP resource
server. Within one thread, the same catalog or skill resource can be
requested multiple times by prompt injection and the `skills.list` /
`skills.read` tools. Re-fetching adds latency and can make those
surfaces observe different remote contents during the same thread.
This is a follow-up to #28333: orchestrator skills remain limited to
threads without a local executor, and those threads now get a stable
per-thread view of the remote skill data they use.
## What changed
- Reuse the existing per-thread orchestrator catalog snapshot for
`skills.list` and `skills.read` availability checks.
- Cache successful orchestrator resource reads by authority, package,
and resource so prompt injection and tool calls share the same contents.
- Keep the cache memory-only and bounded to 100 resources and 8 MiB per
thread.
- Leave host and executor skill reads unchanged, and do not cache failed
remote reads.
## Verification
- Extended the app-server MCP resource integration test to read the same
hosted skill resource twice and verify that the remote server receives
one read.
- The same test verifies that catalog discovery and the selected skill's
main prompt are each fetched only once per thread.
## Why
App-server threads without a local executor need orchestrator-owned
skills from the hosted `codex_apps` MCP server. Threads with the local
executor already discover installed skills from the local filesystem.
After the orchestrator skill provider was enabled for every app-server
thread, local-executor threads also received the hosted skill catalog
and the `skills.list` and `skills.read` tools. This changed the existing
local behavior and could expose a second hosted copy of a skill that was
already installed locally.
## What changed
- Expose the thread's selected execution environments to extensions at
thread startup.
- Enable orchestrator skills only when the reserved local environment is
not selected.
- Apply that decision consistently to hosted skill catalog discovery,
explicit skill injection, and the `skills.list` and `skills.read` tools.
## Verification
- The existing no-executor app-server test continues to verify hosted
skill discovery, invocation, and child-resource reads.
- A new app-server test verifies that local-executor threads do not
receive hosted skill context or `skills.*` tools.
## Why
**In short:** this PR discovers MCP registrations by reading a selected
plugin's `.mcp.json` on its executor. #27884 then resolves those
registrations in the shared catalog.
`thread/start.selectedCapabilityRoots` can select a plugin root owned by
an executor, and Codex can resolve that package through the executor
filesystem. MCP declarations inside the selected plugin are still
ignored.
This PR adds the source-specific discovery layer on top of the
selected-plugin catalog boundary in #27884:
```text
selected capability root
|
v
resolve the plugin through its executor filesystem
|
v
read and normalize its MCP config through the same filesystem
|
v
contribute stdio registrations bound to that environment ID
```
The existing MCP launcher and connection manager remain unchanged. MCP
config parsing is shared with local plugins through #27863.
## What changed
- Added an executor plugin MCP provider in the MCP extension.
- Retained only the exact filesystem capability used for package
resolution and reused it for the selected plugin's MCP config, with no
host-filesystem fallback or unrelated process/HTTP authority.
- Read either the manifest-declared MCP config or the default
`.mcp.json`; a missing default file means the plugin has no MCP servers.
- Accepted stdio servers only for this first vertical. Executor-owned
HTTP declarations are skipped with a warning until their placement
semantics are defined.
- Normalized stdio registrations with the owning environment's stable
logical ID and plugin-root working directory.
- Resolved environment-variable names on the owning executor and
rejected explicit local forwarding for non-local plugins.
- Froze discovered declarations once per active thread runtime, then
applied current managed plugin and MCP requirements when contributing
them.
- Carried the selected root ID, display name, and selection order into
the catalog contribution defined by #27884.
## Behavior and scope
There is intentionally no production behavior change yet. This PR
provides the executor provider and contribution boundary, but app-server
does not install it in this change. Existing local plugin MCP loading is
unchanged, and no MCP process is launched by this PR alone.
## Assumptions
- The selected root ID is the plugin policy identity; the manifest
display name is presentation metadata.
- An environment ID is a stable logical authority. Reconnection or
replacement under the same ID does not change ownership.
- Selected plugin packages and their manifests are trusted inputs.
- The selected package and MCP discovery snapshot remain frozen for the
active thread runtime.
## Follow-up
The next PR installs this contributor in app-server and adds an
end-to-end test proving that a selected plugin MCP tool launches on its
owning executor, can be called by the model, survives an explicit MCP
refresh, and is invisible when its root was not selected.
Resume, fork, environment removal or ID changes, dynamic catalog reload,
and executor-owned HTTP MCP placement remain separate lifecycle
decisions.
## Verification
Focused tests cover executor-only filesystem reads, missing and
malformed config, stdio filtering and normalization, managed
requirements, package attribution, and selection order. CI owns
execution of the test suite.
## Why
**In short:** this PR resolves already-discovered MCP registrations. It
does not read selected plugins or discover their MCP servers.
The resolved MCP catalog currently builds config and auto-discovered
plugin registrations before runtime contributors are applied. A
thread-selected plugin needs a distinct precedence tier in that same
initial resolution pass: otherwise a disabled lower-precedence winner
can leave stale name-level state behind, and the winning MCP tools
cannot be attributed to the selected package reliably.
This PR adds that catalog boundary before executor discovery is
connected.
## What changed
- Added an explicit selected-plugin registration tier between
auto-discovered plugins and explicit config.
- Collected selected-plugin contributions before the initial catalog
build, while leaving compatibility and generic extension overlays in
their existing runtime phase.
- Retained the winning plugin ID and display name directly on
plugin-owned catalog registrations.
- Derived MCP tool provenance from the winning catalog entry instead of
joining against local-only plugin summaries.
- Retained the winning selected server's tool approval policy in the
running connection manager, so a selected registration cannot inherit
approval behavior from a losing local plugin.
- Kept remembered approval session-scoped for selected plugins until
there is an authority-aware persistence contract; Codex will not write
approval back to an unrelated local plugin.
- Preserved existing name-level disabled vetoes for discovered plugins
and config, while keeping a selected package's own disabled registration
scoped to that registration.
- Preserved deterministic selection order and existing config,
compatibility, and extension precedence.
The resulting order is:
```text
auto-discovered plugin
< selected plugin
< explicit config
< compatibility registration
< extension overlay
```
## Behavior and scope
This is a catalog and provenance change only. No production host
contributes selected-plugin MCP registrations yet, so existing local MCP
behavior remains unchanged.
The stacked follow-up, #27870, installs the executor plugin provider
that produces these registrations. App-server activation remains a
separate final step.
## Verification
Focused tests cover precedence, deterministic selected-plugin conflicts,
disabled-veto behavior across catalog phases, managed requirements
before selected-plugin resolution, winning-server approval policy, and
attribution when local and selected packages share an ID or server name.
CI owns execution of the test suite.
## Intent
Keep Bazel and Starlark files consistently formatted without requiring
contributors to install or version buildifier themselves.
## Implementation
- Add a SHA-256-pinned, cross-platform DotSlash manifest for buildifier
v8.5.1.
- Run buildifier from the shared `just fmt` and `just fmt-check` driver,
with Windows-safe explicit DotSlash invocation.
- Provision DotSlash in formatting CI and contributor devcontainers, and
document the source-build prerequisite.
- Apply the initial mechanical buildifier formatting baseline.
## Why
`PathUri::from_abs_path` can fail for absolute paths that do not have a
normal `file:` URI representation, forcing filesystem call sites to
handle a conversion error even though the original path can be preserved
losslessly.
## What
Make `from_abs_path` infallible and migrate its callers. Unrepresentable
paths use `file:///%00/bad/path/<base64>`, encoding Unix bytes or
Windows UTF-16LE; `to_abs_path` validates and decodes that fallback. The
leading encoded null reserves a namespace that cannot collide with a
real Unix or Windows path, and fallback URIs remain opaque to lexical
path operations.
## Validation
Added path-URI coverage for Unix null and non-UTF-8 paths, Windows
device/verbatim and non-Unicode paths, serialization, malformed
fallbacks, opaque lexical operations, invalid native payloads, and
literal `/bad/path` collision resistance.
## Why
Multi-agent v2 `send_message` deliveries already reach the receiving
model as typed `agent_message` items with encrypted content.
Child-completion notifications are generated by Codex itself, so their
content is plaintext and previously fell back to a serialized JSON
envelope inside an assistant message.
With plaintext `input_text` supported for `agent_message`, both delivery
paths can use the same model-visible type while preserving explicit
author and recipient metadata.
## What changed
- add plaintext `input_text` support to `AgentMessageInputContent` and
regenerate the affected app-server schemas
- preserve `InterAgentCommunication` as structured mailbox input instead
of converting it to assistant text
- record delivered communications as typed `agent_message` history items
- persist a dedicated rollout item so local delivery metadata such as
`trigger_turn` remains available without leaking into the Responses
request
- reconstruct typed agent messages on resume and preserve fork-turn
truncation behavior
- remove request-time assistant-content parsing
- preserve plaintext and encrypted inter-agent deliveries in stage-one
memory inputs
- normalize and link plaintext and encrypted agent messages in rollout
traces without treating inbound messages as child results
- cover the real MultiAgent V2 child-completion path end to end with
deterministic mailbox synchronization
## Verification
- `just test -p codex-core
plaintext_multi_agent_v2_completion_sends_agent_message`
- `just test -p codex-core input_queue_drains_mailbox_in_delivery_order
record_initial_history_reconstructs_typed_inter_agent_message
fork_turn_positions_use_inter_agent_delivery_metadata`
- `just test -p codex-memories-write
serializes_inter_agent_communications_for_memory`
- `just test -p codex-rollout-trace
agent_messages_preserve_routing_and_content
sub_agent_started_activity_creates_spawn_edge`
- `just test -p codex-rollout-trace
agent_result_edge_falls_back_to_child_thread_without_result_message`
- `just test -p codex-protocol -p codex-rollout -p
codex-app-server-protocol`
## Why
`ExecutorFileSystem::get_metadata` reports file kind and timestamps but
not size. Internal callers that need to enforce a size limit therefore
have to read the complete file first, which is especially wasteful for
remote filesystems.
This adds the missing internal metadata so consumers can reject
oversized files before transferring or buffering them. The field is
named `size`, matching VS Code's `FileStat.size` filesystem convention.
## What changed
- add `size: u64` to internal `FileMetadata`
- populate it from the underlying filesystem metadata
- carry it through sandbox-helper and remote exec-server responses
- cover files, directories, symlink targets, and sandboxed reads across
local and remote filesystem implementations
The new field is intentionally not exposed through the app-server API.
## Testing
- `just test -p codex-exec-server get_metadata`
- `just test -p codex-exec-server
file_system_sandboxed_metadata_and_read_allow_readable_root`
- `just test -p codex-core-plugins`
- `just test -p codex-skills-extension`
## Why
Standalone image generation emitted a started item but no terminal item
when the backend failed. Clients could leave the operation unresolved or
render it as successful.
## What changed
- Emit a terminal image-generation item with `status: "failed"` when
generation or editing fails.
- Skip image persistence for failed terminal items.
- Render failed image generation distinctly in TUI history.
- Preserve the status when handling live and replayed terminal items.
## Looks for TUI, App-Side change needed
<img width="867" height="89" alt="image"
src="https://github.com/user-attachments/assets/9e32342f-a982-411e-8498-456639fc468a"
/>
## Validation
- `just test -p codex-image-generation-extension`
- App-server image-generation tests
- Core stream-event tests
- TUI image-generation lifecycle and snapshot tests
- Scoped Clippy and formatting
## Why
`selectedCapabilityRoots` belongs to one thread, but MCP contributors
previously received only the global Codex config. That left no clean way
for a selected executor capability to contribute MCP servers to its own
thread.
## What this PR does
- Gives MCP contributors a small context containing the config and, for
a running thread, its frozen host-seeded inputs.
- Uses the same thread inputs during startup, status queries, refreshes,
and skill dependency checks.
- Keeps threadless MCP operations and the existing hosted Apps behavior
unchanged.
- Adds coverage showing that two threads resolve independent
registrations and that later lifecycle mutations do not change the
frozen MCP inputs.
This PR does not discover plugin manifests, add MCP servers, or launch
anything new. It only establishes the thread-scoped registration
boundary.
## Follow-ups
- Resolve selected executor plugin roots through their owning
environment filesystem.
- Convert their stdio MCP declarations into environment-bound
registrations and add an executor MCP end-to-end test.
## Verification
- `just fmt`
- `cargo check --tests -p codex-protocol -p codex-extension-api -p
codex-mcp-extension -p codex-core -p codex-app-server`
Tests and Clippy were not run.
## Why
First-party async traits should expose their `Send` contracts explicitly
without requiring `async_trait`. This completes the migration pattern
established in #27303 and #27304.
## What changed
- Replaced the remaining first-party `async_trait` traits with native
return-position `impl Future + Send` where statically dispatched and
explicit boxed `Send` futures where object safety is required.
- Kept implementations behavior-preserving, outlining existing async
bodies into inherent methods where that keeps the diff reviewable.
- Removed all direct first-party `async-trait` dependencies and the
workspace dependency declaration.
- Added a cargo-deny policy that permits `async-trait` only through the
remaining transitive wrapper crates.
- Updated `rand` from 0.8.5 to 0.8.6 to resolve RUSTSEC-2026-0097 and
keep the full cargo-deny check passing.
## Validation
- `just test -p codex-exec-server`: 216 passed, 2 skipped.
- `just test -p codex-model-provider`: 39 passed.
- `just test -p codex-core` and `just test`: changed tests passed;
remaining failures are environment-sensitive suites unrelated to this
migration.
- `cargo deny check`
- `just fix`
- `just fmt`
- `cargo shear`
- `just bazel-lock-check`
## Why
`main` stopped compiling when #27498 passed an `AbsolutePathBuf` to the
`ExecutorFileSystem` API migrated to `PathUri` by #27653.
## What
Convert referenced image paths to `PathUri` before filesystem reads,
declare the internal path-URI dependency, and refresh `Cargo.lock`.
## Why
Image generation used `std::fs::read` for referenced image paths, which
did not support environment-backed filesystems or their sandbox context.
## What changed
- Expose optional turn environments to extension tool calls.
- Include each environment’s ID, working directory, filesystem, and
sandbox context.
- Read referenced images through the selected environment filesystem.
- Keep sandbox usage at the extension call site so extensions can choose
the appropriate access mode.
- Consolidate image request construction into one async function.
- Add coverage for successful environment reads and read failures.
## Validation
- `cargo check -p codex-image-generation-extension --tests`
- `just fmt`
- `just bazel-lock-update`
- `just bazel-lock-check`
`just test -p codex-image-generation-extension` could not complete
because the build exhausted available disk space.
## Why
MCP servers currently come from user config, local plugins,
compatibility Apps synthesis, and host extensions. Those sources were
composed by mutating a shared map, leaving registration identity,
precedence, removal, and provenance implicit in assembly order.
Before adding executor-owned MCPs, Codex needs one durable resolution
boundary above `McpConnectionManager`. This PR introduces that boundary
while preserving current server configuration, policy, and runtime
behavior. Executor-scoped registrations and explicit policy layers
remain follow-ups.
## What changed
- Add typed `McpServerRegistration` inputs and an immutable
`ResolvedMcpCatalog` in `codex-mcp`.
- Retain each registration's complete `McpServerConfig`, including its
environment binding, while recording its source and provenance.
- Preserve the existing structural precedence between plugin, config,
compatibility, and ordered extension sources.
- Resolve equal-precedence actions by contribution order; provenance IDs
are used only for diagnostics and cannot affect the winner.
- Preserve extension removals and the existing name-scoped `enabled =
false` veto.
- Report same-tier conflicts with every contender and the final catalog
outcome, including whether the winning action registers or removes the
server.
- Require MCP contributors to provide a stable diagnostic identity.
- Derive materialized server maps and plugin ownership from the resolved
catalog.
`McpConnectionManager`, transport startup, tool calls, and resource
routing continue to consume the same effective `McpServerConfig` values.
## Scope
This PR does not add new MCP capabilities or change user-visible
behavior. It does not add executor plugin discovery, thread-scoped
registrations, dynamic refresh generations, or new user/managed policy
semantics.
## Verification
- Added focused catalog coverage for source precedence, complete
configuration preservation, disabled vetoes, plugin ownership,
contribution-order tie breaking, removal outcomes, and conflict
diagnostics.
- Extended hosted Apps coverage for ordered extension removal and
Apps-disabled hosts with and without the hosted extension installed.
- `cargo check -p codex-mcp --tests -p codex-extension-api -p
codex-core`
## Why
We want to remove implicit use of `$CODEX_HOME` from `codex-core` and
make embedders responsible for supplying user-level instructions. This
also ensures user instructions load when no primary environment is
selected.
## What changed
Stacked on #27415, which makes `codex exec` surface thread-scoped
runtime warnings.
- Added `UserInstructionsProvider` to `codex-extension-api`, with
absolute source attribution and recoverable loading warnings.
- Added `codex-home` with the filesystem-backed provider for
`AGENTS.override.md` and `AGENTS.md`, preserving precedence, fallback,
trimming, lossy UTF-8 handling, and the existing uncapped global
instruction size.
- Removed global instruction loading from `Config` and require
`ThreadManager` callers to inject a provider.
- Load provider instructions once for each fresh root runtime, including
runtimes without a primary environment. Running sessions retain their
snapshot, while child agents inherit the parent snapshot without
invoking the provider.
- Keep provider instructions separate while loading project `AGENTS.md`,
then assemble the model-visible instructions with the existing ordering,
source attribution, warning, and turn-context behavior.
- Wired the Codex home provider through the CLI, app server, MCP server,
core facade, and thread-manager sample.
## Validation
- `just test -p codex-home -p codex-extension-api`
- `just test -p codex-core agents_md`
- `just test -p codex-core guardian`
- `just test -p codex-app-server
thread_start_without_selected_environment_includes_only_global_instruction_source`
- `just test -p codex-exec warning`
- `just bazel-lock-check`
## Why
We're moving exec-server to use PathUri for its internal path
representations.
## What
Move `ExecutorFileSystem` APIs to use `PathUri` instead of
`AbsolutePathBuf`. Future changes will convert higher-level parts of
exec-server.
We're switching to using a static encoding of the host path in
`PathUri`. We may need a type like this again but we can add it when
it's more compelling.
Stacked on #27454.
## 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 #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.
## 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
- 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
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.
## 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
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.
## 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
- Currently, there is no analytics event for `/goal` behavior
- Existing events cannot identify goal execution or its resulting
outcome
- The original update in
[#26182](https://github.com/openai/codex/pull/26182) was implemented
before `/goal` moved into `codex-goal-extension`.
## What Changed
- Adds `codex_goal_event` serialization and enrichment to
`codex-analytics`
- Emits goal events from the canonical `codex-goal-extension` mutation
and accounting paths:
- `created` when a new logical goal is persisted
- `usage_accounted` when cumulative goal usage is persisted
- `status_changed` when the stored goal status changes
- `cleared` when the goal is deleted
- Preserves causal `turn_id` for turn driven events and uses null
attribution for external or idle lifecycle events
- Changes goal deletion to return the deleted row so `cleared` retains
the stable goal ID
## Event Details
Includes standard analytics metadata along with goal specific fields:
- `goal_id`: Stable ID stored in the local SQLite goal row and shared
across the goal's events
- `event_kind`: Observed operation (see the 4 lifecycle events cited in
the above bullet)
- `goal_status`: Resulting or last stored status: `active`, `paused`,
`blocked`, `usage_limited`, etc.
- `has_token_budget`: Indicates whether a token budget is configured
- `turn_id`: Causal turn ID, or null when no causal turn exists
- `cumulative_tokens_accounted`: Cumulative tokens on `usage_accounted`
events; null otherwise
- `cumulative_time_accounted_seconds`: Cumulative active time on
`usage_accounted` events; null otherwise
## Validation
- `just test -p codex-analytics -p codex-state -p codex-goal-extension`
- `just test -p codex-core -E 'test(/goal/)'`
- `just test -p codex-app-server`
- `cargo build -p codex-analytics -p codex-core -p codex-state -p
codex-app-server`
## 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
Users have indicated that they want an agent to be able to create a new
goal for itself after completing the previous goal. Currently, that's
not possible because agents cannot overwrite an existing goal even if
it's complete. This PR removes this limitation and allows `create_goal`
to overwrite an existing goal if it is in the `complete` state.
## What changed
`create_goal` now replaces the existing goal only when its status is
`complete`. The replacement is performed atomically in the goal store,
creates a fresh active goal with reset usage, and continues to reject
creation while any unfinished goal exists. App server clients see a
single `thread/goal/updated` event when the previous goal is replaced
with the new one.
The tool description and error message now reflect these semantics.
## What didn't change
Agents are not allowed to create a new goal (overwrite their existing
goal) if an existing goal is still active, blocked, paused, or in any
other state other than "completed".
## Why
`codex-extension-api` defines contracts shared by extension crates and
their hosts, but it had no direct test suite. Host and feature tests
cover downstream behavior, while regressions in the API crate's own
typed state, registry ordering, and capability adapters could go
unnoticed.
## What
- Add public-surface integration tests for `ExtensionData`, including
concurrent initialization and poison recovery.
- Cover contributor registration order, approval short-circuiting, event
sink retention, no-op response injection, and closure-based agent
spawning.
- Add the test-only dependencies used by the suite.
## Validation
- `just test -p codex-extension-api`
- `just argument-comment-lint -p codex-extension-api`
- `just bazel-lock-check`
## 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.
## Summary
- Update the web search tool prompt to require Markdown links for cited
sources.
- Explicitly tell the model not to use `turnX`-style citations in
responses.
## Context
https://openai.slack.com/archives/C0AU83S0ZQU/p1780964147777649?thread_ts=1780352049.512299&cid=C0AU83S0ZQU
## Test plan
- `git diff --check`
- `python3 scripts/format.py --check` (fails only on Rust formatter
setup: rustup cannot create temp files under `/home/dev-user/.rustup`;
Just and Python formatter checks pass when using temp cache dirs)
## Why
Image edits should use the exact images selected by the model instead of
inferring edit inputs from conversation history.
## What changed
- Replaced the image tool's `action` argument with optional
`referenced_image_paths`.
- Treats omitted or empty references as generation and populated
references as editing.
- Reads referenced absolute image paths and packages them as image data
URLs for the edit request.
- Removed the previous history-selection and image-count heuristics.
- Updated direct and code-mode tool instructions and calls.
- Added an app-server integration test covering an attached image routed
to the image edit endpoint.
## Validation
- Tested end-to-end on local `just codex` with copy pasted image,
attached image, etc.
- `just test -p codex-image-generation-extension`
- `just test -p codex-app-server
standalone_image_edit_uses_attached_model_visible_image`
- `just fix -p codex-image-generation-extension`
- `just bazel-lock-check`
## Summary
- add contains_external_context() to tool output so other tools can be
opted out of influencing memory when disable_on_external_context=true
- Classify standalone web-search output as external context (to match
behavior as hosted web search)
- Verify with integration test
## What
- Consume plaintext `output` from standalone search while retaining
optional `encrypted_output` parsing.
- Expose `web.run` to code mode and return search output to nested
JavaScript calls.
- Cover direct and code-mode standalone search paths with integration
tests.
## Why
`/v1/alpha/search` now returns plaintext output, which code mode needs
to consume standalone search results.
## Test plan
- `just test -p codex-api`
- `just test -p codex-web-search-extension`
- `just test -p codex-core code_mode_can_call_standalone_web_search`
- `just test -p codex-app-server
standalone_web_search_round_trips_output`
## Summary
Responses Lite does not execute hosted Responses tools, so models using
it must route web search and image generation through Codex-owned
executors & standalone Response's API endpoints.
This PR is stacked on #26487.
## Validation
- `cargo test -p codex-core responses_lite_ --lib`
- `cargo test -p codex-core
standalone_executors_remain_hidden_without_flags_or_responses_lite
--lib`
- `cargo test -p codex-core
hosted_tools_follow_provider_auth_model_and_config_gates --lib`
- `cargo test -p codex-web-search-extension -p
codex-image-generation-extension`
- `cargo test -p codex-app-server --test all standalone_`
- `cargo fmt --all -- --check`
## Why
Terminal turn errors can leave a goal active. Automatic goal
continuation may then repeatedly hit a permanent failure, including
compaction requests rejected with HTTP 400, and consume excessive
tokens.
This PR changes the goal extension to treat all turn-ending errors
(including non-retryable errors and retryable errors that have exceeded
their retry count) as "blocking" for the goal. The downside to this
change is that there are some errors that may eventually succeed (e.g. a
429 due to a service outage), and previously the goal runtime would have
kept the agent going in these situations.
## What changed
- Block the current active goal when a turn ends with an error other
than a usage-limit error.
- Preserve the existing `usage_limited` transition for usage-limit
errors.
- Share progress accounting, guarded state updates, metrics, and event
emission in the goal runtime.
## Stack
1. [#26547](https://github.com/openai/codex/pull/26547) - [1 of 2] Align
goal extension with core behavior
2. [#26548](https://github.com/openai/codex/pull/26548) - [2 of 2] Move
goal runtime to extension
## Why
The goal runtime is moving out of `codex-core` and into
`codex-goal-extension`. This first PR brings the extension back in line
with the current core behavior before the follow-up PR switches
app-server sessions over to the extension, so that review can focus on
ownership and wiring rather than hidden behavior drift.
## What Changed
- Updates the extension `create_goal` and `update_goal` tool
schemas/descriptions to match the current core wording for explicit
token budgets, blocked-goal audits, resumed blocked goals, and
system-owned budget/usage-limit transitions.
- Marks `codex-goal-extension` as the live `/goal` extension crate
rather than an unwired sketch.
- Looks up the live thread before reading goal state for idle
continuation, so continuation setup exits early when no live thread can
accept the automatic turn.
## Why
Multi-agent v2 currently routes agent instructions through normal tool
arguments and inter-agent context. That means the parent model can emit
plaintext task text, Codex can persist it in history/rollouts, and the
recipient can receive it as ordinary assistant-message JSON.
This changes the v2 path so agent instructions stay encrypted between
model calls: Responses encrypts the `message` argument returned by the
model, Codex forwards only that ciphertext, and Responses decrypts it
internally for the recipient model.
## What changed
- Mark the v2 `message` parameter as encrypted for `spawn_agent`,
`send_message`, and `followup_task`.
- Treat multi-agent v2 tool `message` values as ciphertext
unconditionally.
- Store v2 inter-agent task text in
`InterAgentCommunication.encrypted_content` with empty plaintext
`content`.
- Convert encrypted inter-agent communications into the Responses
`agent_message` input item before sending the child request.
- Preserve `agent_message` items across history, rollout, compaction,
telemetry, and app-server schema paths.
- Leave multi-agent v1 unchanged.
## Message shape
The model still calls the v2 tools with a `message` argument, but that
value is now ciphertext:
```json
{
"name": "spawn_agent",
"arguments": {
"task_name": "worker",
"message": "<ciphertext>"
}
}
```
Codex stores the task as encrypted inter-agent communication:
```json
{
"author": "/root",
"recipient": "/root/worker",
"content": "",
"encrypted_content": "<ciphertext>",
"trigger_turn": true
}
```
When Codex builds the recipient request, it forwards the ciphertext
using the new Responses input item:
```json
{
"type": "agent_message",
"author": "/root",
"recipient": "/root/worker",
"content": [
{
"type": "encrypted_content",
"encrypted_content": "<ciphertext>"
}
]
}
```
Responses decrypts that item internally for the recipient model.
## Context impact
- Parent context no longer carries plaintext v2 agent task instructions
from these tool arguments.
- Codex rollout/history stores ciphertext for v2 agent instructions.
- Recipient requests receive an `agent_message` item instead of
assistant commentary JSON for encrypted task delivery.
- Plaintext completion/status notifications are still plaintext because
they are Codex-generated status messages, not encrypted model tool
arguments.
## Validation
- `just test -p codex-tools`
- `just test -p codex-protocol`
- `just test -p codex-rollout`
- `just test -p codex-rollout-trace`
- `just test -p codex-otel`
- `just write-app-server-schema`
## Why
Standalone image generation returns image bytes to the model, but the
model also needs the host artifact path to reference the generated file
in follow-up work.
## What changed
- Append the default saved-image path hint alongside the generated image
tool output.
- Reuse the existing core image-generation hint text.
- Pass the thread ID and Codex home directory needed to compute the
artifact path.
- Add app-server and extension coverage for the model-visible hint.
## Validation
- `just fmt`
- `just bazel-lock-check`
- `just test -p codex-app-server
standalone_image_generation_returns_saved_path_hint_to_model`
## Why
The skills extension needs to become the path that exposes local host
skills without losing the behavior already owned by core skill loading.
Host skill discovery is not just `$CODEX_HOME/skills`: it also includes
config layers, bundled-skill settings, plugin roots, runtime extra
roots, and the filesystem for the selected primary environment.
Rather than making the extension reload host skills and risk drifting
from that authoritative load, this PR bridges the already-loaded
per-turn skills outcome into the extension. That lets the extension
advertise host skills and inject explicit `$skill` prompts while
preserving the same roots, disabled/hidden state, rendered paths, and
environment-backed file reads that the legacy path uses.
## What Changed
- Adds `HostLoadedSkills` in `core-skills` to wrap the turn's
`SkillLoadOutcome` and read `SKILL.md` through the filesystem that
loaded that skill.
- Stores `HostLoadedSkills` in turn extension data for normal turns and
review turns, so the skills extension can consume the loaded host
catalog without reloading it.
- Adds `HostSkillProvider` under `ext/skills/src/provider/host.rs`,
mapping host-loaded skill metadata into the skills-extension
catalog/read contract.
- Registers the host provider by default from
`codex_skills_extension::install()`.
- Preserves host skill metadata such as dependencies, disabled state,
hidden-from-prompt policy, and slash-normalized display paths.
- Passes host-loaded skills through `SkillListQuery` and
`SkillReadRequest` so explicit skill invocation reads only resources
from the loaded host catalog.
- Adds integration coverage for a real legacy
`$CODEX_HOME/skills/.../SKILL.md` skill being listed and injected
through the installed extension.
## Testing
- Added `installed_extension_loads_host_skills_from_legacy_roots` in
`ext/skills/tests/skills_extension.rs`.
- `just test -p codex-skills-extension`
charlesgong-openai ·
pakrym-oai ·
jif ·
Adam Perry @ OpenAI ·
Owen Lin ·
Won Park ·
yuning-oai ·
e-provencher ·
marksteinbrick-oai ·
Eric Traut ·
rka-oai ·