Add a configurable skill catalog token budget (#38978)

## What changed

- Add `[skills].max_context_tokens` to override the token budget used to render the available-skills catalog.
- Require a positive value and cap configured budgets at 10,000 tokens.
- Preserve the existing default of 2% of the model context window when the option is unset.

## Testing

- Cover configuration parsing, override behavior, the 10,000-token cap, and catalog rendering within the configured budget.

GitOrigin-RevId: f29ddcb57fc2d800c0006d03e1c33cbe3ab6272d
This commit is contained in:
jif authored and copyberry committed 2026-08-17 10:01:59 +00:00
1 parent c6058ccaa9
commit 632e35ce8d
19 files changed
+126 -7

No files matched your search

+4
View File
@@ -358,6 +358,7 @@ fn parses_bundled_skills_config() {
r#"
[skills]
include_instructions = false
max_context_tokens = 1200
[skills.bundled]
enabled = false
@@ -370,9 +371,12 @@ enabled = false
Some(SkillsConfig {
bundled: Some(BundledSkillsConfig { enabled: false }),
include_instructions: Some(false),
max_context_tokens: std::num::NonZeroUsize::new(1_200),
config: Vec::new(),
})
);
assert!(toml::from_str::<ConfigToml>("[skills]\nmax_context_tokens = 0\n").is_err());
}
#[test]