Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(tool-skill): teach the catalog about user-explicit skill injection

Browse Source 
Both catalog renderings now tell the model that a directly invoked skill
arrives as an inline <skill_content> block to follow without re-loading it
through the skill tool — the seam rule that keeps the user-explicit path
and the model-autonomous path from double-injecting one skill.
This commit is contained in:
Yichen Jiang
2026-08-08 00:55:37 +08:00
parent 85422f44dc
commit cc0f6e11b9
3 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
packages/skill/tool-skill/src/index.ts
View File

@@ -217,6 +217,7 @@ function renderCatalogMessage(entries: SkillCatalogSource['entries']): UserMessa
'</available_skills>',
'',
"If the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.",
'A user may also invoke a skill directly; its <skill_content> block then appears in this conversation. Follow it, and do not call the `skill` tool again for that skill.',
'</system-reminder>',
].join('\n'),
}],
@@ -235,6 +236,7 @@ function renderCatalogUpdate(entries: SkillCatalogSource['entries']): UserMessag
]
: [
'Use only names in this replacement catalog. If the user names a listed skill, or the task clearly matches its description, call the `skill` tool with the exact name before acting.',
'A user may also invoke a skill directly; its <skill_content> block then appears in this conversation. Follow it, and do not call the `skill` tool again for that skill.',
]
return createUserMessage({
content: [{

1
packages/skill/tool-skill/tests/tool-skill.spec.ts
View File

@@ -287,6 +287,7 @@ describe('dsh-tool-skill', () => {
'</available_skills>',
'',
"If the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.",
'A user may also invoke a skill directly; its <skill_content> block then appears in this conversation. Follow it, and do not call the `skill` tool again for that skill.',
'</system-reminder>',
].join('\n'),
}],