fix(skills): drop raw_content to avoid doubling skill payload

skill_view response went to the model verbatim; duplicating the SKILL.md
body as raw_content on every tool call added token cost with no agent-facing
benefit. Remove the field and update tests to assert on content only.

The slash/preload caller (agent/skill_commands.py) already falls back to
content when raw_content is absent, and it calls skill_view(preprocess=False)
anyway, so content is already unrendered on that path.
This commit is contained in:
teknium1 2026-04-24 15:09:18 -07:00 committed by Teknium
parent ead66f0c92
commit 2de8a7a229
2 changed files with 1 additions and 4 deletions

View file

@ -835,7 +835,6 @@ def _serve_plugin_skill(
"success": True,
"name": f"{namespace}:{bare}",
"content": f"{banner}{rendered_content}" if banner else rendered_content,
"raw_content": content,
"description": description,
"linked_files": None,
"readiness_status": SkillReadinessStatus.AVAILABLE.value,
@ -1335,7 +1334,6 @@ def skill_view(
"tags": tags,
"related_skills": related_skills,
"content": rendered_content,
"raw_content": content,
"path": rel_path,
"skill_dir": str(skill_dir) if skill_dir else None,
"linked_files": linked_files if linked_files else None,