189ff89c34
Adds two new LLM-backed MCP tools to the ingestion service: - brain_answer(query): BM25 retrieval + LLM synthesis → answer + sources - brain_classify(text): classifies doc into type/title/tags via LLM Adds llm.Router for primary→fallback routing (berget.ai → iguana). Wired via BRAIN_LLM_PRIMARY_URL/BRAIN_LLM_FALLBACK_URL env vars; no-op when unset so existing deployments are unaffected. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
115 lines
3.0 KiB
Go
115 lines
3.0 KiB
Go
package mcp
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"fmt"
|
|
"strings"
|
|
|
|
"github.com/mathiasbq/hyperguild/ingestion/internal/search"
|
|
)
|
|
|
|
const (
|
|
answerSystemPrompt = `You are a knowledge assistant. Answer the question using ONLY the provided sources.
|
|
Cite source file paths inline when referencing specific content.
|
|
If the context does not contain enough information to answer, say so clearly.`
|
|
|
|
classifySystemPrompt = `Classify the document. Respond with JSON only, no markdown fences.
|
|
{"type":"...","title":"...","tags":["..."]}
|
|
Valid types: spec, plan, decision, note, wiki, log, code, unknown.`
|
|
)
|
|
|
|
type brainAnswerArgs struct {
|
|
Query string `json:"query"`
|
|
}
|
|
|
|
func (s *Server) brainAnswer(ctx context.Context, args json.RawMessage) (json.RawMessage, error) {
|
|
if s.answerLLM == nil {
|
|
return nil, fmt.Errorf("answer LLM not configured: set BRAIN_LLM_PRIMARY_URL")
|
|
}
|
|
var a brainAnswerArgs
|
|
if err := json.Unmarshal(args, &a); err != nil {
|
|
return nil, fmt.Errorf("parse args: %w", err)
|
|
}
|
|
if a.Query == "" {
|
|
return nil, fmt.Errorf("query is required")
|
|
}
|
|
|
|
results, err := search.Query(s.brainDir, a.Query, 10)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("search: %w", err)
|
|
}
|
|
if len(results) == 0 {
|
|
return json.Marshal(map[string]any{
|
|
"answer": "No relevant content found in brain.",
|
|
"sources": []string{},
|
|
})
|
|
}
|
|
|
|
var sb strings.Builder
|
|
sources := make([]string, 0, len(results))
|
|
for _, r := range results {
|
|
fmt.Fprintf(&sb, "<source path=%q>\n%s\n</source>\n\n", r.Path, r.Excerpt)
|
|
sources = append(sources, r.Path)
|
|
}
|
|
|
|
answer, err := s.answerLLM(ctx, answerSystemPrompt, sb.String()+"Question: "+a.Query)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("llm: %w", err)
|
|
}
|
|
|
|
return json.Marshal(map[string]any{
|
|
"answer": answer,
|
|
"sources": sources,
|
|
})
|
|
}
|
|
|
|
type brainClassifyArgs struct {
|
|
Text string `json:"text"`
|
|
}
|
|
|
|
type classifyResult struct {
|
|
Type string `json:"type"`
|
|
Title string `json:"title"`
|
|
Tags []string `json:"tags"`
|
|
}
|
|
|
|
func (s *Server) brainClassify(ctx context.Context, args json.RawMessage) (json.RawMessage, error) {
|
|
if s.answerLLM == nil {
|
|
return nil, fmt.Errorf("answer LLM not configured: set BRAIN_LLM_PRIMARY_URL")
|
|
}
|
|
var a brainClassifyArgs
|
|
if err := json.Unmarshal(args, &a); err != nil {
|
|
return nil, fmt.Errorf("parse args: %w", err)
|
|
}
|
|
if a.Text == "" {
|
|
return nil, fmt.Errorf("text is required")
|
|
}
|
|
|
|
text := a.Text
|
|
if len(text) > 3000 {
|
|
text = text[:3000]
|
|
}
|
|
|
|
raw, err := s.answerLLM(ctx, classifySystemPrompt, text)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("llm: %w", err)
|
|
}
|
|
|
|
// Strip markdown fences if model adds them despite the instruction.
|
|
raw = strings.TrimSpace(raw)
|
|
raw = strings.TrimPrefix(raw, "```json")
|
|
raw = strings.TrimPrefix(raw, "```")
|
|
raw = strings.TrimSuffix(raw, "```")
|
|
raw = strings.TrimSpace(raw)
|
|
|
|
var cr classifyResult
|
|
if err := json.Unmarshal([]byte(raw), &cr); err != nil {
|
|
return nil, fmt.Errorf("parse classify response %q: %w", raw, err)
|
|
}
|
|
if cr.Tags == nil {
|
|
cr.Tags = []string{}
|
|
}
|
|
return json.Marshal(cr)
|
|
}
|