mirror of
https://github.com/openai/codex.git
synced 2026-11-13 14:46:14 +00:00
Project executor skills through World State (#30088)
## Why A selected executor environment can be unavailable in one model step and ready in the next. The model should see its skills only while that environment is ready, without rescanning stable files on every sample. The product assumption is simple: - an environment ID names one stable logical environment; - the selected root contents do not change during the thread. ## Behavior ```text E1 unavailable -> do not show E1 skills E1 ready -> discover once, cache, show through World State E1 unavailable -> hide skills, keep cache E1 ready again -> reuse cache, show skills again resume -> create a new thread cache and discover again ``` The cache key is the full `SelectedCapabilityRoot`. Availability does not invalidate it; dropping the extension's thread state does. The step supplies the ready selected roots directly. They do not have to be turn environments: ```text turn environment: laptop selected root: worker:/plugins/lint-fix worker ready -> lint-fix skills are visible ``` ## What changes - Keeps executor skill catalogs in the existing skills extension. - Passes the roots resolved as ready for the step into World State contributors. - Loads each ready selected root at most once per thread. - Contributes the executor catalog as the `skills` World State section. - Uses the exact step catalog for explicit skill selection and body reads. - Leaves host and orchestrator skill behavior where it already lives. Taking a step snapshot itself does not add an RPC. Executor filesystem calls happen only on the first discovery of a stable root for that thread. ## What does not change - No filesystem watcher or content-based invalidation. - No retry/generation framework. - No skill runtime migration into core. - No general rewrite of the skills extension. ## Stack 1. Extension-owned World State sections. 2. **This PR:** project cached executor skills through World State. 3. Pin one MCP runtime to each model step. 4. Project selected MCP/app/connector metadata by environment availability. 5. One end-to-end integration scenario.
This commit is contained in:
8 files changed
+322
-70
No files matched your search
@@ -18,6 +18,7 @@ use crate::catalog::SkillProviderResult;
|
||||
use crate::catalog::SkillReadResult;
|
||||
use crate::catalog::SkillResourceId;
|
||||
use crate::catalog::SkillSourceKind;
|
||||
use crate::provider::SkillListQuery;
|
||||
use crate::provider::SkillReadRequest;
|
||||
use crate::sources::SkillProviders;
|
||||
|
||||
@@ -26,21 +27,17 @@ const MAX_CACHED_ORCHESTRATOR_CONTENT_BYTES: usize = 8 * 1024 * 1024;
|
||||
|
||||
pub(crate) struct SkillsThreadState {
|
||||
config: Mutex<SkillsExtensionConfig>,
|
||||
selected_roots: Vec<SelectedCapabilityRoot>,
|
||||
orchestrator_skills_available: bool,
|
||||
executor_cache: Mutex<Vec<CachedExecutorCatalog>>,
|
||||
orchestrator_cache: Mutex<Option<Arc<OrchestratorGenerationCache>>>,
|
||||
}
|
||||
|
||||
impl SkillsThreadState {
|
||||
pub(crate) fn new(
|
||||
config: SkillsExtensionConfig,
|
||||
selected_roots: Vec<SelectedCapabilityRoot>,
|
||||
orchestrator_skills_available: bool,
|
||||
) -> Self {
|
||||
pub(crate) fn new(config: SkillsExtensionConfig, orchestrator_skills_available: bool) -> Self {
|
||||
Self {
|
||||
config: Mutex::new(config),
|
||||
selected_roots,
|
||||
orchestrator_skills_available,
|
||||
executor_cache: Mutex::new(Vec::new()),
|
||||
orchestrator_cache: Mutex::new(None),
|
||||
}
|
||||
}
|
||||
@@ -59,14 +56,33 @@ impl SkillsThreadState {
|
||||
.unwrap_or_else(std::sync::PoisonError::into_inner) = config;
|
||||
}
|
||||
|
||||
pub(crate) fn selected_roots(&self) -> &[SelectedCapabilityRoot] {
|
||||
&self.selected_roots
|
||||
}
|
||||
|
||||
pub(crate) fn orchestrator_skills_enabled(&self) -> bool {
|
||||
self.orchestrator_skills_available && self.config().orchestrator_skills_enabled
|
||||
}
|
||||
|
||||
/// Returns catalogs for stable selected roots.
|
||||
///
|
||||
/// The first catalog returned for a root remains cached until this thread state is dropped.
|
||||
/// Environment availability only controls whether the root is projected into the current
|
||||
/// step; it never invalidates the cache. There is intentionally no filesystem watcher or
|
||||
/// content-based invalidation because selected environment roots are treated as stable.
|
||||
pub(crate) async fn executor_catalog_snapshot(
|
||||
&self,
|
||||
providers: &SkillProviders,
|
||||
mut query: SkillListQuery,
|
||||
) -> SkillCatalog {
|
||||
let roots = std::mem::take(&mut query.executor_roots);
|
||||
let mut catalog = SkillCatalog::default();
|
||||
for root in roots {
|
||||
query.executor_roots = vec![root.clone()];
|
||||
catalog.extend(
|
||||
self.executor_root_catalog(providers, root, query.clone())
|
||||
.await,
|
||||
);
|
||||
}
|
||||
catalog
|
||||
}
|
||||
|
||||
pub(crate) async fn orchestrator_catalog_snapshot(
|
||||
&self,
|
||||
mcp_resources: Option<&McpResourceClient>,
|
||||
@@ -140,6 +156,42 @@ impl SkillsThreadState {
|
||||
*cache = Some(Arc::clone(&next_cache));
|
||||
next_cache
|
||||
}
|
||||
|
||||
async fn executor_root_catalog(
|
||||
&self,
|
||||
providers: &SkillProviders,
|
||||
root: SelectedCapabilityRoot,
|
||||
query: SkillListQuery,
|
||||
) -> SkillCatalog {
|
||||
if let Some(cached) = self
|
||||
.executor_cache
|
||||
.lock()
|
||||
.unwrap_or_else(std::sync::PoisonError::into_inner)
|
||||
.iter()
|
||||
.find(|cached| cached.root == root)
|
||||
{
|
||||
return cached.catalog.clone();
|
||||
}
|
||||
|
||||
let discovered = providers.list_executor_for_turn(query).await;
|
||||
let mut cache = self
|
||||
.executor_cache
|
||||
.lock()
|
||||
.unwrap_or_else(std::sync::PoisonError::into_inner);
|
||||
if let Some(cached) = cache.iter().find(|cached| cached.root == root) {
|
||||
return cached.catalog.clone();
|
||||
}
|
||||
cache.push(CachedExecutorCatalog {
|
||||
root,
|
||||
catalog: discovered.clone(),
|
||||
});
|
||||
discovered
|
||||
}
|
||||
}
|
||||
|
||||
struct CachedExecutorCatalog {
|
||||
root: SelectedCapabilityRoot,
|
||||
catalog: SkillCatalog,
|
||||
}
|
||||
|
||||
struct OrchestratorGenerationCache {
|
||||
@@ -204,3 +256,6 @@ pub(crate) struct SkillsTurnState {
|
||||
pub(crate) warnings: Vec<String>,
|
||||
pub(crate) main_prompts_injected: bool,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Default)]
|
||||
pub(crate) struct ExecutorSkillsStepState(pub(crate) SkillCatalog);
|
||||
Reference in new issue
Block a user