skills: resolve per-turn catalogs from turn input context (#26106)

## Why

The skills extension needs the resolved turn environments to build a
real per-turn `SkillListQuery`. The previous `TurnLifecycleContributor`
hook only had a turn id, so it could only seed a placeholder query and
never carry the executor authorities that executor-scoped skill routing
will need.

Moving catalog resolution onto `TurnInputContributor` puts the skills
extension on the same turn-preparation path that already has the
environment ids and working directories for the submitted turn, while
keeping the actual prompt injection work for follow-up changes.

## What changed

- switch `ext/skills` from `TurnLifecycleContributor` to
`TurnInputContributor`
- build `executor_authorities` from `TurnInputContext.environments` and
pass them through `SkillListQuery`
- keep storing the resolved catalog in `SkillsTurnState`, but drop the
placeholder query helper that no longer matches the real data flow
- update the extension TODOs to reflect that per-turn catalog resolution
now happens in the turn-input contributor, and that prompt/context
injection still needs to move later

## Testing

- Not run locally.
This commit is contained in:
jif
2026-06-03 13:32:55 +02:00
committed by GitHub
parent 51493157cd
commit 3389fa554e
35 changed files with 92 additions and 74 deletions
+6 -2
View File
@@ -628,7 +628,7 @@ async fn build_extension_turn_input_items(
let mut items = Vec::new();
for contributor in contributors {
let contributed_items = contributor
let contributed_fragments = contributor
.contribute(
input.clone(),
&sess.services.session_extension_data,
@@ -638,7 +638,11 @@ async fn build_extension_turn_input_items(
.or_cancel(cancellation_token)
.await
.ok()?;
items.extend(contributed_items);
items.extend(
contributed_fragments
.into_iter()
.map(ContextualUserFragment::into_boxed_response_item),
);
}
Some(items)