hyperguild/ingestion/internal/mcp/brain_update_test.go

package mcp_test

import (
	"context"
	"encoding/json"
	"os"
	"path/filepath"
	"strings"
	"testing"
	"time"

	"github.com/mathiasbq/hyperguild/ingestion/internal/mcp"
	"github.com/mathiasbq/hyperguild/ingestion/internal/vectorstore"
	"github.com/stretchr/testify/assert"
	"github.com/stretchr/testify/require"
)

// callResult parses the JSON text payload of a successful tool call.
func callResult(t *testing.T, resp map[string]any) map[string]any {
	t.Helper()
	require.Nil(t, resp["error"], "tool returned error: %v", resp["error"])
	text := resp["result"].(map[string]any)["content"].([]any)[0].(map[string]any)["text"].(string)
	var out map[string]any
	require.NoError(t, json.Unmarshal([]byte(text), &out))
	return out
}

func TestBrainUpdateSupersedesExisting(t *testing.T) {
	brainDir := t.TempDir()
	srv := mcp.NewServer(brainDir, nil, nil, nil)

	// Seed via brain_write so the note carries real frontmatter.
	callResult(t, toolCall(t, srv, "brain_write", map[string]any{
		"content": "# Old\n\nold body\n", "filename": "val-vol",
		"wing": "jepa-fx", "hall": "facts",
	}))

	out := callResult(t, toolCall(t, srv, "brain_update", map[string]any{
		"wing": "jepa-fx", "hall": "facts", "slug": "val-vol",
		"content": "# New\n\nnew body\n", "reason": "facts changed",
	}))
	assert.Equal(t, "wiki/jepa-fx/facts/val-vol.md", out["path"])
	assert.Equal(t, out["path"], out["id"])
	assert.NotEmpty(t, out["content_hash"])
	assert.Equal(t, true, out["superseded"])

	got, err := os.ReadFile(filepath.Join(brainDir, "wiki/jepa-fx/facts/val-vol.md"))
	require.NoError(t, err)
	s := string(got)
	assert.Contains(t, s, "# New")
	assert.NotContains(t, s, "old body")
	assert.Contains(t, s, "wing: jepa-fx")
	assert.Contains(t, s, "supersede_reason: facts changed")
	assert.Contains(t, s, "supersedes:")
}

func TestBrainUpdateMissingTargetErrorsNoCreate(t *testing.T) {
	brainDir := t.TempDir()
	srv := mcp.NewServer(brainDir, nil, nil, nil)

	resp := toolCall(t, srv, "brain_update", map[string]any{
		"wing": "jepa-fx", "hall": "facts", "slug": "ghost",
		"content": "x\n",
	})
	require.NotNil(t, resp["error"])
	assert.Contains(t, resp["error"].(map[string]any)["message"].(string), "does not exist")
	_, statErr := os.Stat(filepath.Join(brainDir, "wiki/jepa-fx/facts/ghost.md"))
	assert.True(t, os.IsNotExist(statErr))
}

func TestBrainUpdateByFullPath(t *testing.T) {
	brainDir := t.TempDir()
	srv := mcp.NewServer(brainDir, nil, nil, nil)
	callResult(t, toolCall(t, srv, "brain_write", map[string]any{
		"content": "old\n", "filename": "n", "wing": "a", "hall": "facts",
	}))

	out := callResult(t, toolCall(t, srv, "brain_update", map[string]any{
		"slug": "wiki/a/facts/n.md", "content": "fresh\n",
	}))
	assert.Equal(t, "wiki/a/facts/n.md", out["path"])
}

func TestBrainGetByIDAndPath(t *testing.T) {
	brainDir := t.TempDir()
	srv := mcp.NewServer(brainDir, nil, nil, nil)
	w := callResult(t, toolCall(t, srv, "brain_write", map[string]any{
		"content": "# Body\n\ntext\n", "filename": "n", "wing": "a", "hall": "facts",
	}))
	id := w["id"].(string)
	hash := w["content_hash"].(string)
	require.NotEmpty(t, id)
	require.NotEmpty(t, hash)

	// by id
	g1 := callResult(t, toolCall(t, srv, "brain_get", map[string]any{"id": id}))
	assert.Equal(t, id, g1["path"])
	assert.Equal(t, hash, g1["content_hash"], "content_hash must round-trip write→get")
	assert.Contains(t, g1["body"].(string), "# Body")
	fm := g1["frontmatter"].(map[string]any)
	assert.Equal(t, "a", fm["wing"])

	// by path
	g2 := callResult(t, toolCall(t, srv, "brain_get", map[string]any{"path": id}))
	assert.Equal(t, hash, g2["content_hash"])
}

func TestBrainGetMissingArgsErrors(t *testing.T) {
	srv := mcp.NewServer(t.TempDir(), nil, nil, nil)
	resp := toolCall(t, srv, "brain_get", map[string]any{})
	require.NotNil(t, resp["error"])
}

func TestBrainWriteReturnsHandle(t *testing.T) {
	brainDir := t.TempDir()
	srv := mcp.NewServer(brainDir, nil, nil, nil)
	out := callResult(t, toolCall(t, srv, "brain_write", map[string]any{
		"content": "# X\n\nbody\n", "filename": "x", "wing": "a", "hall": "facts",
	}))
	assert.Equal(t, "wiki/a/facts/x.md", out["path"])
	assert.Equal(t, out["path"], out["id"])
	assert.NotEmpty(t, out["content_hash"])
}

// --- retrieval-reflects-new-content: exercises the real mtime-driven Sync ---

type fakeVecStore struct {
	chunks  map[string][]float32
	deleted []string
}

func (f *fakeVecStore) KnownPathsWithTime(_ context.Context) (map[string]time.Time, error) {
	m := make(map[string]time.Time, len(f.chunks))
	for p := range f.chunks {
		m[p] = time.Unix(0, 0) // always stale → mtime(now) is always newer
	}
	return m, nil
}

func (f *fakeVecStore) Upsert(_ context.Context, path string, vec []float32) error {
	f.chunks[path] = vec
	return nil
}

func (f *fakeVecStore) Delete(_ context.Context, path string) error {
	delete(f.chunks, path)
	f.deleted = append(f.deleted, path)
	return nil
}

type fakeEmbedder struct{ seen []string }

func (e *fakeEmbedder) Embed(_ context.Context, text string) ([]float32, error) {
	e.seen = append(e.seen, text)
	return []float32{1, 0, 0}, nil
}

// TestBrainUpdateReembedsNewContent proves the supersede contract end to
// end against the actual embedding mechanism: brain_update rewrites the
// file, advancing its mtime, and the next vectorstore.Sync pass re-embeds
// the NEW body and drops the stale chunk. No stub of the re-index path.
func TestBrainUpdateReembedsNewContent(t *testing.T) {
	brainDir := t.TempDir()
	srv := mcp.NewServer(brainDir, nil, nil, nil)
	ctx := context.Background()

	callResult(t, toolCall(t, srv, "brain_write", map[string]any{
		"content":  "# Note\n\nthe OLD distinctive payload\n",
		"filename": "n", "wing": "a", "hall": "facts",
	}))

	store := &fakeVecStore{chunks: map[string][]float32{}}
	emb := &fakeEmbedder{}

	// First sync embeds the original content.
	_, err := vectorstore.Sync(ctx, brainDir, store, emb)
	require.NoError(t, err)
	require.NotEmpty(t, store.chunks)
	require.True(t, anyContains(emb.seen, "OLD distinctive payload"))

	callResult(t, toolCall(t, srv, "brain_update", map[string]any{
		"wing": "a", "hall": "facts", "slug": "n",
		"content": "# Note\n\nthe NEW distinctive payload\n",
	}))

	emb.seen = nil // only watch what the second pass embeds
	_, err = vectorstore.Sync(ctx, brainDir, store, emb)
	require.NoError(t, err)

	assert.True(t, anyContains(emb.seen, "NEW distinctive payload"),
		"Sync must re-embed the superseded body; saw %v", emb.seen)
	assert.False(t, anyContains(emb.seen, "OLD distinctive payload"),
		"the old body must not be re-embedded")
	assert.NotEmpty(t, store.deleted, "stale chunks must be deleted before re-embed")
}

func anyContains(ss []string, sub string) bool {
	for _, s := range ss {
		if strings.Contains(s, sub) {
			return true
		}
	}
	return false
}