Files
archie/internal/agentexec/modelloop/sampling.go
T
sam 2c447708e9 fix(archiegateway,agentexec,agentworker): rely on ai-sdk reasoning token selection
Bump github.com/samcharles93/ai-sdk v0.1.40 -> v0.1.41. ai-sdk now sends
max_completion_tokens for reasoning models and omits temperature when the
model rejects it, so the max_tokens workarounds are no longer needed: the
chat-turn bound is set directly and MCP sampling loses its reasoning
branch. Classic models keep their existing bounds.
2026-10-05 22:56:48 +11:00

57 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. The ai-sdk runtime picks max_completion_tokens or
// max_tokens from the model's catalog metadata, so there is no reasoning
// branch here.
func SamplingMaxTokens(requested, modelCeiling int) int {
maxTokens := requested
if maxTokens <= 0 {
maxTokens = DefaultSamplingMaxTokens
}
if modelCeiling > 0 && maxTokens > modelCeiling {
maxTokens = modelCeiling
}
return maxTokens
}