Add batched executor capability discovery (#33852)

## Why

Selected capability roots can contribute plugins, MCP servers, connectors, and
skills. Discovering each contribution separately requires repeated access to the
executor filesystem.

## What changed

- Add the `capabilityRoots/discoverV1` exec-server RPC to scan selected roots and
  materialize recognized plugin manifests, configuration files, skill
  instructions, and skill metadata in one bounded request.
- Add the opt-in `executor_capability_discovery` feature, with a thread-scoped
  cache and per-step snapshot shared by MCP and skill discovery.
- Parse MCP, connector, and skill contributions from the materialized snapshot,
  including serving cached skill instructions without another filesystem read.

## Testing

- Cover discovery limits, manifest precedence, root-local failures, cache reuse,
  plugin contributions, and parity with the existing environment skill loader.

GitOrigin-RevId: f98fd2321cafb58c596db02da1f83c09d8eb375d
This commit is contained in:
Bryan Ashley authored and copyberry committed 2026-07-17 15:45:48 +00:00
1 parent caa6e554d6
commit 08e30a2e4e
47 files changed
+1957 -47

No files matched your search

@@ -1,5 +1,7 @@
use std::collections::HashMap;
use std::io;
use codex_exec_server::CapabilityRootDiscovery;
use codex_exec_server::ExecutorFileSystem;
use codex_protocol::protocol::Product;
use codex_utils_path_uri::PathUri;
@@ -45,6 +47,19 @@ pub struct EnvironmentSkillMetadata {
pub policy: Option<SkillPolicy>,
}
/// Parsed executor skill plus the instructions already materialized by capability discovery.
#[derive(Clone, Debug, PartialEq, Eq)]
pub struct EnvironmentSkillSnapshot {
pub metadata: EnvironmentSkillMetadata,
pub instructions: String,
}
#[derive(Debug, Default)]
pub struct EnvironmentSkillSnapshotOutcome {
pub skills: Vec<EnvironmentSkillSnapshot>,
pub warnings: Vec<String>,
}
impl EnvironmentSkillMetadata {
pub fn allows_implicit_invocation(&self) -> bool {
self.policy
@@ -212,6 +227,130 @@ pub async fn load_environment_skills_from_root(
outcome
}
/// Parses an executor-produced manifest bundle without issuing additional filesystem requests.
pub fn load_environment_skills_from_discovery(
discovery: &CapabilityRootDiscovery,
restriction_product: Option<Product>,
) -> EnvironmentSkillSnapshotOutcome {
let mut outcome = EnvironmentSkillSnapshotOutcome {
warnings: discovery.warnings.clone(),
..Default::default()
};
if let Some(error) = &discovery.error {
outcome.warnings.push(error.clone());
return outcome;
}
let mut plugin_namespaces = HashMap::new();
for (plugin_root, name) in discovery.namespace_manifests.iter().filter_map(|manifest| {
#[derive(serde::Deserialize)]
struct ManifestName {
#[serde(default)]
name: String,
}
let plugin_root = manifest.path.parent()?.parent()?;
let parsed = serde_json::from_str::<ManifestName>(&manifest.contents).ok()?;
let name = if parsed.name.trim().is_empty() {
plugin_root.basename()?
} else {
parsed.name
};
Some((plugin_root, name))
}) {
// Exec-server orders manifests by the same precedence as local discovery. Preserve the
// first manifest if an older or alternate server returns duplicates for one plugin root.
plugin_namespaces.entry(plugin_root).or_insert(name);
}
for skill in &discovery.skills {
let plugin_namespace =
nearest_plugin_namespace(&skill.instructions.path, &plugin_namespaces);
let ParsedSkillFrontmatter {
name: base_name,
description,
short_description,
} = match parse_skill_frontmatter_metadata_inner(&skill.instructions.contents, || {
default_skill_name(&skill.instructions.path)
}) {
Ok(frontmatter) => frontmatter,
Err(error) => {
outcome.warnings.push(format!(
"Failed to load environment skill at {}: {error}",
skill.instructions.path
));
continue;
}
};
let name = plugin_namespace
.map(|namespace| format!("{namespace}:{base_name}"))
.unwrap_or(base_name);
if let Err(error) = validate_len(&name, MAX_QUALIFIED_NAME_LEN, "qualified name") {
outcome.warnings.push(format!(
"Failed to load environment skill at {}: {error}",
skill.instructions.path
));
continue;
}
let (dependencies, policy) = skill
.metadata
.as_ref()
.and_then(|metadata| {
serde_yaml::from_str::<SkillMetadataFile>(&metadata.contents)
.map_err(|error| {
tracing::warn!(
path = %metadata.path,
"ignoring invalid discovered skill metadata: {error}"
);
})
.ok()
})
.map(|metadata| {
(
resolve_dependencies(metadata.dependencies),
resolve_policy(metadata.policy),
)
})
.unwrap_or((None, None));
let metadata = EnvironmentSkillMetadata {
path_to_skills_md: skill.instructions.path.clone(),
name,
description,
short_description,
dependencies,
policy,
};
if metadata.matches_product_restriction(restriction_product) {
outcome.skills.push(EnvironmentSkillSnapshot {
metadata,
instructions: skill.instructions.contents.clone(),
});
}
}
outcome.skills.sort_by(|left, right| {
left.metadata.name.cmp(&right.metadata.name).then_with(|| {
left.metadata
.path_to_skills_md
.to_string()
.cmp(&right.metadata.path_to_skills_md.to_string())
})
});
outcome
}
fn nearest_plugin_namespace<'a>(
skill_path: &PathUri,
plugin_namespaces: &'a HashMap<PathUri, String>,
) -> Option<&'a str> {
let mut ancestor = skill_path.parent();
while let Some(path) = ancestor {
if let Some(namespace) = plugin_namespaces.get(&path) {
return Some(namespace);
}
ancestor = path.parent();
}
None
}
async fn read_skill_contents(
file_system: &dyn ExecutorFileSystem,
skill_path: &PathUri,