Files
hyperguild/ingestion/internal/mcp/handlers.go
Mathias Bergqvist bd0c1d75fd feat(ingestion): implement session_log MCP tool
Appends a JSON line to brainDir/sessions/<session_id>.jsonl using the
session package copied in Task 2. Required for upcoming pass-rate
logging.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-01 13:04:40 +02:00

257 lines
8.1 KiB
Go

package mcp
import (
"context"
"encoding/json"
"fmt"
"path/filepath"
"strings"
"time"
"github.com/mathiasbq/hyperguild/ingestion/internal/api"
"github.com/mathiasbq/hyperguild/ingestion/internal/extract"
"github.com/mathiasbq/hyperguild/ingestion/internal/pipeline"
"github.com/mathiasbq/hyperguild/ingestion/internal/search"
"github.com/mathiasbq/hyperguild/ingestion/internal/session"
)
// tools returns the tool descriptors. Handler bodies for each tool are filled
// in subsequent tasks; this file currently only provides the descriptors.
func (s *Server) tools() []map[string]any {
str := func(desc string) map[string]any {
return map[string]any{"type": "string", "description": desc}
}
int_ := func(desc string) map[string]any {
return map[string]any{"type": "integer", "description": desc}
}
schema := func(required []string, props map[string]any) json.RawMessage {
b, _ := json.Marshal(map[string]any{
"type": "object", "required": required, "properties": props,
})
return b
}
return []map[string]any{
{
"name": "brain_query",
"description": "BM25 full-text search across brain/knowledge/ and brain/wiki/ markdown files.",
"inputSchema": schema([]string{"query"}, map[string]any{
"query": str("search terms"),
"limit": int_("max results, default 5"),
}),
},
{
"name": "brain_write",
"description": "Write a raw knowledge note to brain/knowledge/.",
"inputSchema": schema([]string{"content"}, map[string]any{
"content": str("markdown content"),
"filename": str("optional filename"),
"type": str("optional frontmatter type"),
"domain": str("optional frontmatter domain"),
}),
},
{
"name": "brain_ingest_raw",
"description": "Ingest pre-structured pages into the brain wiki, bypassing the LLM extraction step.",
"inputSchema": schema([]string{"source", "pages"}, map[string]any{
"source": str("source name"),
"pages": map[string]any{"type": "array"},
"dry_run": map[string]any{"type": "boolean"},
}),
},
{
"name": "brain_ingest",
"description": "Ingest content into the brain wiki via the LLM extraction pipeline.",
"inputSchema": schema([]string{}, map[string]any{
"content": str("raw content; required when path is empty"),
"source": str("source name; required when path is empty"),
"path": str("file path; mutually exclusive with content+source"),
"dry_run": map[string]any{"type": "boolean"},
}),
},
{
"name": "session_log",
"description": "Append a structured entry to brain/sessions/<session_id>.jsonl.",
"inputSchema": schema([]string{"session_id"}, map[string]any{
"session_id": str("session identifier"),
"skill": str("skill name"),
"phase": str("phase within the skill"),
"project_root": str("absolute project root"),
"final_status": str("ok | error | skipped"),
"file_path": str("optional file produced"),
"model_used": str("optional model identifier"),
"duration_ms": int_("optional duration in ms"),
"message": str("optional free-text"),
}),
},
}
}
type brainQueryArgs struct {
Query string `json:"query"`
Limit int `json:"limit,omitempty"`
}
func (s *Server) brainQuery(ctx context.Context, args json.RawMessage) (json.RawMessage, error) {
var a brainQueryArgs
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")
}
if a.Limit == 0 {
a.Limit = 5
}
results, err := search.Query(s.brainDir, a.Query, a.Limit)
if err != nil {
return nil, fmt.Errorf("search: %w", err)
}
return json.Marshal(map[string]any{"results": results})
}
type brainWriteArgs struct {
Content string `json:"content"`
Filename string `json:"filename,omitempty"`
Type string `json:"type,omitempty"`
Domain string `json:"domain,omitempty"`
}
func (s *Server) brainWrite(ctx context.Context, args json.RawMessage) (json.RawMessage, error) {
var a brainWriteArgs
if err := json.Unmarshal(args, &a); err != nil {
return nil, fmt.Errorf("parse args: %w", err)
}
relPath, err := api.WriteNote(s.brainDir, a.Content, a.Filename, a.Type, a.Domain)
if err != nil {
return nil, err
}
return json.Marshal(map[string]string{"path": relPath})
}
type brainIngestRawArgs struct {
Source string `json:"source"`
Pages []pipeline.RawPage `json:"pages"`
DryRun bool `json:"dry_run,omitempty"`
}
func (s *Server) brainIngestRaw(ctx context.Context, args json.RawMessage) (json.RawMessage, error) {
var a brainIngestRawArgs
if err := json.Unmarshal(args, &a); err != nil {
return nil, fmt.Errorf("parse args: %w", err)
}
if a.Source == "" {
return nil, fmt.Errorf("source is required")
}
if len(a.Pages) == 0 {
return nil, fmt.Errorf("pages must be non-empty")
}
result, err := pipeline.RunRaw(s.brainDir, a.Source, a.Pages, a.DryRun)
if err != nil {
return nil, fmt.Errorf("ingest: %w", err)
}
pages := result.Pages
if pages == nil {
pages = []string{}
}
warnings := result.Warnings
if warnings == nil {
warnings = []string{}
}
return json.Marshal(map[string]any{"pages": pages, "warnings": warnings})
}
type brainIngestArgs struct {
Content string `json:"content,omitempty"`
Source string `json:"source,omitempty"`
Path string `json:"path,omitempty"`
DryRun bool `json:"dry_run,omitempty"`
}
func (s *Server) brainIngest(ctx context.Context, args json.RawMessage) (json.RawMessage, error) {
var a brainIngestArgs
if err := json.Unmarshal(args, &a); err != nil {
return nil, fmt.Errorf("parse args: %w", err)
}
if a.Path != "" && a.Content != "" {
return nil, fmt.Errorf("path and content+source are mutually exclusive")
}
if a.Path == "" && a.Content == "" {
return nil, fmt.Errorf("either path or content+source is required")
}
if s.pipeline.Complete == nil {
return nil, fmt.Errorf("LLM not configured: set INGEST_LLM_URL")
}
if a.Path != "" {
text, err := extract.Text(a.Path)
if err != nil {
return nil, fmt.Errorf("extract: %w", err)
}
source := a.Source
if source == "" {
source = filepath.Base(strings.TrimSuffix(a.Path, filepath.Ext(a.Path)))
}
return s.runIngest(ctx, text, source, a.DryRun)
}
if a.Source == "" {
return nil, fmt.Errorf("source is required when content is provided")
}
return s.runIngest(ctx, a.Content, a.Source, a.DryRun)
}
type sessionLogArgs struct {
SessionID string `json:"session_id"`
Skill string `json:"skill,omitempty"`
Phase string `json:"phase,omitempty"`
ProjectRoot string `json:"project_root,omitempty"`
FinalStatus string `json:"final_status,omitempty"`
FilePath string `json:"file_path,omitempty"`
ModelUsed string `json:"model_used,omitempty"`
DurationMs int64 `json:"duration_ms,omitempty"`
Message string `json:"message,omitempty"`
}
func (s *Server) sessionLog(ctx context.Context, args json.RawMessage) (json.RawMessage, error) {
var a sessionLogArgs
if err := json.Unmarshal(args, &a); err != nil {
return nil, fmt.Errorf("parse args: %w", err)
}
if a.SessionID == "" {
return nil, fmt.Errorf("session_id is required")
}
entry := session.Entry{
SessionID: a.SessionID,
Timestamp: time.Now().UTC(),
Skill: a.Skill,
Phase: a.Phase,
ProjectRoot: a.ProjectRoot,
FinalStatus: a.FinalStatus,
FilePath: a.FilePath,
ModelUsed: a.ModelUsed,
DurationMs: a.DurationMs,
Message: a.Message,
}
dir := filepath.Join(s.brainDir, "sessions")
if err := session.Append(dir, a.SessionID, entry); err != nil {
return nil, fmt.Errorf("append: %w", err)
}
return json.Marshal(map[string]string{"status": "ok", "session_id": a.SessionID})
}
func (s *Server) runIngest(ctx context.Context, content, source string, dryRun bool) (json.RawMessage, error) {
result, err := pipeline.Run(ctx, s.pipeline, s.brainDir, content, source, dryRun)
if err != nil {
return nil, fmt.Errorf("ingest: %w", err)
}
pages := result.Pages
if pages == nil {
pages = []string{}
}
warnings := result.Warnings
if warnings == nil {
warnings = []string{}
}
return json.Marshal(map[string]any{"pages": pages, "warnings": warnings})
}