Load selected executor skills through extensions (#27184)

## 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.
This commit is contained in:
jif
2026-06-09 19:51:54 +02:00
committed by GitHub
Unverified
parent 1026e9de1b
commit 89ac3ec27c
46 changed files with 1460 additions and 127 deletions
+15
View File
@@ -21,6 +21,7 @@ use codex_app_server_protocol::ThreadHistoryBuilder;
use codex_app_server_protocol::TurnStatus;
use codex_core_plugins::PluginsManager;
use codex_exec_server::EnvironmentManager;
use codex_extension_api::ExtensionDataInit;
use codex_extension_api::ExtensionRegistry;
use codex_extension_api::empty_extension_registry;
use codex_features::Feature;
@@ -182,6 +183,7 @@ pub struct StartThreadOptions {
pub metrics_service_name: Option<String>,
pub parent_trace: Option<W3cTraceContext>,
pub environments: Vec<TurnEnvironmentSelection>,
pub thread_extension_init: ExtensionDataInit,
}
pub(crate) struct ResumeThreadWithHistoryOptions {
@@ -576,6 +578,7 @@ impl ThreadManager {
metrics_service_name: None,
parent_trace: None,
environments,
thread_extension_init: ExtensionDataInit::default(),
}))
.await
}
@@ -614,6 +617,7 @@ impl ThreadManager {
/*inherited_exec_policy*/ None,
options.parent_trace,
options.environments,
options.thread_extension_init,
/*user_shell_override*/ None,
))
.await
@@ -702,6 +706,7 @@ impl ThreadManager {
/*inherited_exec_policy*/ None,
parent_trace,
environments,
/*thread_extension_init*/ ExtensionDataInit::default(),
/*user_shell_override*/ None,
))
.await
@@ -728,6 +733,7 @@ impl ThreadManager {
/*metrics_service_name*/ None,
/*parent_trace*/ None,
environments,
/*thread_extension_init*/ ExtensionDataInit::default(),
/*user_shell_override*/ Some(user_shell_override),
))
.await
@@ -763,6 +769,7 @@ impl ThreadManager {
/*inherited_exec_policy*/ None,
/*parent_trace*/ None,
environments,
/*thread_extension_init*/ ExtensionDataInit::default(),
/*user_shell_override*/ Some(user_shell_override),
))
.await
@@ -931,6 +938,7 @@ impl ThreadManager {
/*metrics_service_name*/ None,
parent_trace,
environments,
/*thread_extension_init*/ ExtensionDataInit::default(),
/*user_shell_override*/ None,
))
.await
@@ -1136,6 +1144,7 @@ impl ThreadManagerState {
inherited_exec_policy,
/*parent_trace*/ None,
environments,
/*thread_extension_init*/ ExtensionDataInit::default(),
/*user_shell_override*/ None,
))
.await
@@ -1172,6 +1181,7 @@ impl ThreadManagerState {
inherited_exec_policy,
/*parent_trace*/ None,
environments,
/*thread_extension_init*/ ExtensionDataInit::default(),
/*user_shell_override*/ None,
))
.await
@@ -1209,6 +1219,7 @@ impl ThreadManagerState {
inherited_exec_policy,
/*parent_trace*/ None,
environments,
/*thread_extension_init*/ ExtensionDataInit::default(),
/*user_shell_override*/ None,
))
.await
@@ -1229,6 +1240,7 @@ impl ThreadManagerState {
metrics_service_name: Option<String>,
parent_trace: Option<W3cTraceContext>,
environments: Vec<TurnEnvironmentSelection>,
thread_extension_init: ExtensionDataInit,
user_shell_override: Option<crate::shell::Shell>,
) -> CodexResult<NewThread> {
Box::pin(self.spawn_thread_with_source(
@@ -1246,6 +1258,7 @@ impl ThreadManagerState {
/*inherited_exec_policy*/ None,
parent_trace,
environments,
thread_extension_init,
user_shell_override,
))
.await
@@ -1268,6 +1281,7 @@ impl ThreadManagerState {
inherited_exec_policy: Option<Arc<crate::exec_policy::ExecPolicyManager>>,
parent_trace: Option<W3cTraceContext>,
environments: Vec<TurnEnvironmentSelection>,
thread_extension_init: ExtensionDataInit,
user_shell_override: Option<crate::shell::Shell>,
) -> CodexResult<NewThread> {
let is_resumed_thread = matches!(&initial_history, InitialHistory::Resumed(_));
@@ -1332,6 +1346,7 @@ impl ThreadManagerState {
user_shell_override,
parent_trace,
environment_selections,
thread_extension_init,
analytics_events_client: self.analytics_events_client.clone(),
thread_store: Arc::clone(&self.thread_store),
attestation_provider: self.attestation_provider.clone(),