mirror of
https://github.com/pchuan98/codex.git
synced 2026-07-01 00:31:56 +08:00
jif
89ac3ec27c
## 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.
313 lines
7.1 KiB
JSON
Generated
313 lines
7.1 KiB
JSON
Generated
{
|
|
"$schema": "http://json-schema.org/draft-07/schema#",
|
|
"definitions": {
|
|
"AbsolutePathBuf": {
|
|
"description": "A path that is guaranteed to be absolute and normalized (though it is not guaranteed to be canonicalized or exist on the filesystem).\n\nIMPORTANT: When deserializing an `AbsolutePathBuf`, a base path must be set using [AbsolutePathBufGuard::new]. If no base path is set, the deserialization will fail unless the path being deserialized is already absolute.",
|
|
"type": "string"
|
|
},
|
|
"ApprovalsReviewer": {
|
|
"description": "Configures who approval requests are routed to for review. Examples include sandbox escapes, blocked network access, MCP approval prompts, and ARC escalations. Defaults to `user`. `auto_review` uses a carefully prompted subagent to gather relevant context and apply a risk-based decision framework before approving or denying the request. The legacy value `guardian_subagent` is accepted for compatibility.",
|
|
"enum": [
|
|
"user",
|
|
"auto_review",
|
|
"guardian_subagent"
|
|
],
|
|
"type": "string"
|
|
},
|
|
"AskForApproval": {
|
|
"oneOf": [
|
|
{
|
|
"enum": [
|
|
"untrusted",
|
|
"on-failure",
|
|
"on-request",
|
|
"never"
|
|
],
|
|
"type": "string"
|
|
},
|
|
{
|
|
"additionalProperties": false,
|
|
"properties": {
|
|
"granular": {
|
|
"properties": {
|
|
"mcp_elicitations": {
|
|
"type": "boolean"
|
|
},
|
|
"request_permissions": {
|
|
"default": false,
|
|
"type": "boolean"
|
|
},
|
|
"rules": {
|
|
"type": "boolean"
|
|
},
|
|
"sandbox_approval": {
|
|
"type": "boolean"
|
|
},
|
|
"skill_approval": {
|
|
"default": false,
|
|
"type": "boolean"
|
|
}
|
|
},
|
|
"required": [
|
|
"mcp_elicitations",
|
|
"rules",
|
|
"sandbox_approval"
|
|
],
|
|
"type": "object"
|
|
}
|
|
},
|
|
"required": [
|
|
"granular"
|
|
],
|
|
"title": "GranularAskForApproval",
|
|
"type": "object"
|
|
}
|
|
]
|
|
},
|
|
"CapabilityRootLocation": {
|
|
"description": "Location used to resolve a selected capability root.",
|
|
"oneOf": [
|
|
{
|
|
"description": "A path owned by an execution environment.",
|
|
"properties": {
|
|
"environmentId": {
|
|
"type": "string"
|
|
},
|
|
"path": {
|
|
"type": "string"
|
|
},
|
|
"type": {
|
|
"enum": [
|
|
"environment"
|
|
],
|
|
"title": "EnvironmentCapabilityRootLocationType",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"environmentId",
|
|
"path",
|
|
"type"
|
|
],
|
|
"title": "EnvironmentCapabilityRootLocation",
|
|
"type": "object"
|
|
}
|
|
]
|
|
},
|
|
"DynamicToolSpec": {
|
|
"properties": {
|
|
"deferLoading": {
|
|
"type": "boolean"
|
|
},
|
|
"description": {
|
|
"type": "string"
|
|
},
|
|
"inputSchema": true,
|
|
"name": {
|
|
"type": "string"
|
|
},
|
|
"namespace": {
|
|
"type": [
|
|
"string",
|
|
"null"
|
|
]
|
|
}
|
|
},
|
|
"required": [
|
|
"description",
|
|
"inputSchema",
|
|
"name"
|
|
],
|
|
"type": "object"
|
|
},
|
|
"Personality": {
|
|
"enum": [
|
|
"none",
|
|
"friendly",
|
|
"pragmatic"
|
|
],
|
|
"type": "string"
|
|
},
|
|
"SandboxMode": {
|
|
"enum": [
|
|
"read-only",
|
|
"workspace-write",
|
|
"danger-full-access"
|
|
],
|
|
"type": "string"
|
|
},
|
|
"SelectedCapabilityRoot": {
|
|
"description": "A user-selected root that can expose one or more runtime capabilities.",
|
|
"properties": {
|
|
"id": {
|
|
"description": "Stable identifier supplied by the capability selection platform.",
|
|
"type": "string"
|
|
},
|
|
"location": {
|
|
"allOf": [
|
|
{
|
|
"$ref": "#/definitions/CapabilityRootLocation"
|
|
}
|
|
],
|
|
"description": "Where the selected root can be resolved."
|
|
}
|
|
},
|
|
"required": [
|
|
"id",
|
|
"location"
|
|
],
|
|
"type": "object"
|
|
},
|
|
"ThreadSource": {
|
|
"enum": [
|
|
"user",
|
|
"subagent",
|
|
"memory_consolidation"
|
|
],
|
|
"type": "string"
|
|
},
|
|
"ThreadStartSource": {
|
|
"enum": [
|
|
"startup",
|
|
"clear"
|
|
],
|
|
"type": "string"
|
|
},
|
|
"TurnEnvironmentParams": {
|
|
"properties": {
|
|
"cwd": {
|
|
"$ref": "#/definitions/AbsolutePathBuf"
|
|
},
|
|
"environmentId": {
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"cwd",
|
|
"environmentId"
|
|
],
|
|
"type": "object"
|
|
}
|
|
},
|
|
"properties": {
|
|
"approvalPolicy": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/definitions/AskForApproval"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
]
|
|
},
|
|
"approvalsReviewer": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/definitions/ApprovalsReviewer"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"description": "Override where approval requests are routed for review on this thread and subsequent turns."
|
|
},
|
|
"baseInstructions": {
|
|
"type": [
|
|
"string",
|
|
"null"
|
|
]
|
|
},
|
|
"config": {
|
|
"additionalProperties": true,
|
|
"type": [
|
|
"object",
|
|
"null"
|
|
]
|
|
},
|
|
"cwd": {
|
|
"type": [
|
|
"string",
|
|
"null"
|
|
]
|
|
},
|
|
"developerInstructions": {
|
|
"type": [
|
|
"string",
|
|
"null"
|
|
]
|
|
},
|
|
"ephemeral": {
|
|
"type": [
|
|
"boolean",
|
|
"null"
|
|
]
|
|
},
|
|
"model": {
|
|
"type": [
|
|
"string",
|
|
"null"
|
|
]
|
|
},
|
|
"modelProvider": {
|
|
"type": [
|
|
"string",
|
|
"null"
|
|
]
|
|
},
|
|
"personality": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/definitions/Personality"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
]
|
|
},
|
|
"sandbox": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/definitions/SandboxMode"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
]
|
|
},
|
|
"serviceName": {
|
|
"type": [
|
|
"string",
|
|
"null"
|
|
]
|
|
},
|
|
"serviceTier": {
|
|
"type": [
|
|
"string",
|
|
"null"
|
|
]
|
|
},
|
|
"sessionStartSource": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/definitions/ThreadStartSource"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
]
|
|
},
|
|
"threadSource": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/definitions/ThreadSource"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"description": "Optional client-supplied analytics source classification for this thread."
|
|
}
|
|
},
|
|
"title": "ThreadStartParams",
|
|
"type": "object"
|
|
} |