agentexec's wire contract, harness adapters and log forwarding no longer import the AI SDK; the in-process model loop, runtime, tool set and sampling helpers that do now live in agentexec/modelloop, used by the Gateway and archie-agent only.
58 lines
1.8 KiB
Go
58 lines
1.8 KiB
Go
package modelloop
|
|
|
|
import (
|
|
"errors"
|
|
"fmt"
|
|
|
|
"github.com/samcharles93/ai-sdk/chat"
|
|
|
|
protocol "github.com/samcharles93/archie-core/internal/tools/mcp"
|
|
)
|
|
|
|
// DefaultSamplingMaxTokens bounds a server-requested completion when the
|
|
// request does not set maxTokens. A sampling request is a delegated
|
|
// sub-completion, not a full turn, so one MCP server cannot spend a
|
|
// turn-sized output allowance on a single request.
|
|
const DefaultSamplingMaxTokens = 4096
|
|
|
|
// SamplingMessages converts sampling messages to chat messages. Non-text
|
|
// content and unknown roles are errors.
|
|
func SamplingMessages(req protocol.SamplingRequest) ([]chat.Message, error) {
|
|
if len(req.Messages) == 0 {
|
|
return nil, errors.New("mcp sampling: the request has no messages")
|
|
}
|
|
messages := make([]chat.Message, 0, len(req.Messages))
|
|
for i, message := range req.Messages {
|
|
if message.Content.Type != "" && message.Content.Type != "text" {
|
|
return nil, fmt.Errorf("mcp sampling: message %d has unsupported content type %q", i, message.Content.Type)
|
|
}
|
|
var role chat.Role
|
|
switch message.Role {
|
|
case "user":
|
|
role = chat.RoleUser
|
|
case "assistant":
|
|
role = chat.RoleAssistant
|
|
default:
|
|
return nil, fmt.Errorf("mcp sampling: message %d has unsupported role %q", i, message.Role)
|
|
}
|
|
messages = append(messages, chat.Message{Role: role, Content: message.Content.Text})
|
|
}
|
|
return messages, nil
|
|
}
|
|
|
|
// SamplingMaxTokens returns the request's maxTokens or the default, capped at
|
|
// the model's ceiling. Reasoning models get no bound.
|
|
func SamplingMaxTokens(requested, modelCeiling int, reasoning bool) int {
|
|
maxTokens := requested
|
|
if maxTokens <= 0 {
|
|
maxTokens = DefaultSamplingMaxTokens
|
|
}
|
|
if modelCeiling > 0 && maxTokens > modelCeiling {
|
|
maxTokens = modelCeiling
|
|
}
|
|
if reasoning {
|
|
return 0
|
|
}
|
|
return maxTokens
|
|
}
|