Files
deepseek-harness/packages/vision/tool-image-recognition/tsconfig.json
T
Pine 457304e619 feat(vision): add the model-facing recognition consumer
Registers the recognize_image tool and a bundled image-recognition skill,
and hooks agent/pre-step to deterministically inject the skill body when a
step input carries an image (content block or image path/URL), so the model
recognizes the image before continuing the task.

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-14 10:57:38 +08:00

40 lines
630 B
JSON

{
"extends": "../../../tsconfig.base.json",
"compilerOptions": {
"rootDir": "src",
"outDir": "lib/types"
},
"include": [
"src"
],
"references": [
{
"path": "../../../vendor/cordis"
},
{
"path": "../../../vendor/schemastery"
},
{
"path": "../image-recognition"
},
{
"path": "../../core/agent"
},
{
"path": "../../core/session"
},
{
"path": "../../llm/llm"
},
{
"path": "../../core/tools"
},
{
"path": "../../skill/skill"
},
{
"path": "../../runtime-diagnostics/invariants"
}
]
}