feat(ingestion): implement brain_ingest_raw MCP tool

Wraps pipeline.RunRaw directly. Same dry-run semantics as the HTTP
/ingest-raw endpoint. Test exercises a single concept page; asserts
returned path and that no file is written under dry_run.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Mathias Bergqvist
2026-05-01 10:28:05 +02:00
parent e4a94df4fc
commit 809d435480
3 changed files with 68 additions and 0 deletions

View File

@@ -6,6 +6,7 @@ import (
"fmt"
"github.com/mathiasbq/hyperguild/ingestion/internal/api"
"github.com/mathiasbq/hyperguild/ingestion/internal/pipeline"
"github.com/mathiasbq/hyperguild/ingestion/internal/search"
)
@@ -122,3 +123,35 @@ func (s *Server) brainWrite(ctx context.Context, args json.RawMessage) (json.Raw
}
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})
}

View File

@@ -94,3 +94,36 @@ func TestBrainWriteAcceptsDoubleDotInName(t *testing.T) {
_, err := os.Stat(filepath.Join(brainDir, "knowledge", "notes..draft.md"))
require.NoError(t, err, "filename with embedded .. should be allowed")
}
func TestBrainIngestRawDryRun(t *testing.T) {
brainDir := t.TempDir()
require.NoError(t, os.MkdirAll(filepath.Join(brainDir, "wiki", "concepts"), 0o755))
srv := mcp.NewServer(brainDir, nil, nil)
resp := toolCall(t, srv, "brain_ingest_raw", map[string]any{
"source": "test-source",
"dry_run": true,
"pages": []map[string]any{
{
"title": "Test Concept",
"type": "concept",
"content": "## Definition\nA test concept.",
},
},
})
require.Nil(t, resp["error"])
result := resp["result"].(map[string]any)
content := result["content"].([]any)
text := content[0].(map[string]any)["text"].(string)
var parsed struct {
Pages []string `json:"pages"`
}
require.NoError(t, json.Unmarshal([]byte(text), &parsed))
require.NotEmpty(t, parsed.Pages, "expected at least one page path")
assert.Contains(t, parsed.Pages[0], "wiki/concepts/test-concept.md")
// dry_run: no file should exist
_, err := os.Stat(filepath.Join(brainDir, "wiki", "concepts", "test-concept.md"))
assert.True(t, os.IsNotExist(err))
}

View File

@@ -120,6 +120,8 @@ func (s *Server) handleCall(ctx context.Context, name string, args json.RawMessa
return s.brainQuery(ctx, args)
case "brain_write":
return s.brainWrite(ctx, args)
case "brain_ingest_raw":
return s.brainIngestRaw(ctx, args)
default:
return nil, fmt.Errorf("unknown tool: %s", name)
}