yao/tools/tools.go
Max 54607e26b7 feat(agent): enhance image content handling and vision support
- Added support for processing image content in the agent, providing placeholder text when image parsing fails.
- Implemented a fallback mechanism to utilize vision tools for image analysis, improving the handling of image content.
- Updated tests to validate the new image handling behavior, ensuring correct responses when vision support is unavailable.
- Enhanced system prompts to guide users on using the new `image_read` tool for image analysis, improving user experience.
2026-05-04 13:46:30 +08:00

69 lines
1.9 KiB
Go

package tools
import (
_ "embed"
"encoding/json"
"github.com/yaoapp/gou/mcp"
mcpTypes "github.com/yaoapp/gou/mcp/types"
"github.com/yaoapp/gou/process"
"github.com/yaoapp/kun/log"
"github.com/yaoapp/yao/tools/docs"
"github.com/yaoapp/yao/tools/proc"
"github.com/yaoapp/yao/tools/vision"
"github.com/yaoapp/yao/tools/webfetch"
"github.com/yaoapp/yao/tools/websearch"
)
//go:embed mcps/web.json
var mcpWebDSL []byte
//go:embed mcps/process.json
var mcpProcessDSL []byte
//go:embed mcps/doc.json
var mcpDocDSL []byte
//go:embed mcps/vision.json
var mcpVisionDSL []byte
func init() {
process.RegisterGroup("tools", map[string]process.Handler{
"web_search": websearch.Handler,
"web_fetch": webfetch.Handler,
"process_call": proc.Handler,
"process_allowed": proc.AllowedHandler,
"doc_list": docs.ListHandler,
"doc_inspect": docs.InspectHandler,
"doc_validate": docs.ValidateHandler,
"image_read": vision.Handler,
})
registerMCPServer(mcpWebDSL, "yao-web",
websearch.SchemaJSON, webfetch.SchemaJSON)
registerMCPServer(mcpProcessDSL, "yao-process",
proc.SchemaJSON, proc.AllowedSchemaJSON)
registerMCPServer(mcpDocDSL, "yao-doc",
docs.ListSchemaJSON, docs.InspectSchemaJSON, docs.ValidateSchemaJSON)
registerMCPServer(mcpVisionDSL, "yao-vision",
vision.SchemaJSON)
}
func registerMCPServer(dsl []byte, id string, schemas ...[]byte) {
mapping := &mcpTypes.MappingData{
Tools: map[string]*mcpTypes.ToolSchema{},
Resources: map[string]*mcpTypes.ResourceSchema{},
Prompts: map[string]*mcpTypes.PromptSchema{},
}
for _, raw := range schemas {
var s mcpTypes.ToolSchema
if err := json.Unmarshal(raw, &s); err != nil {
log.Error("[tools] failed to parse schema: %s", err.Error())
continue
}
mapping.Tools[s.Name] = &s
}
if _, err := mcp.LoadClientSourceWithType(string(dsl), id, "", mapping); err != nil {
log.Error("[tools] failed to register MCP server %s: %s", id, err.Error())
}
}