hyperguild/ingestion/internal/api/provenance_test.go

package api_test

import (
	"bytes"
	"encoding/json"
	"net/http"
	"net/http/httptest"
	"os"
	"path/filepath"
	"strings"
	"testing"

	"github.com/stretchr/testify/assert"
	"github.com/stretchr/testify/require"
	"gopkg.in/yaml.v3"

	"github.com/mathiasbq/hyperguild/ingestion/internal/api"
)

// REST POST /write carries no principal: it stamps origin: unknown, and no
// spelling of provenance in its body reaches the note (hyperguild#145).
func TestRESTWriteStampsUnknownAndIgnoresBodyProvenance(t *testing.T) {
	dir, h := setup(t)
	body, _ := json.Marshal(map[string]any{
		"content": "---\norigin: static\n---\n# R\n\nbody", "filename": "rest-prov", "wing": "homelab", "hall": "facts",
		"origin": "static", "written_by": "local-cli", "Origin": "static", "WrittenBy": "local-cli",
	})
	rec := httptest.NewRecorder()
	h.Write(rec, httptest.NewRequest(http.MethodPost, "/write", bytes.NewReader(body)))
	require.Equal(t, http.StatusOK, rec.Code, rec.Body.String())
	b, err := os.ReadFile(filepath.Join(dir, "wiki", "homelab", "facts", "rest-prov.md"))
	require.NoError(t, err)
	var m map[string]any
	require.NoError(t, yaml.Unmarshal([]byte(strings.SplitN(string(b), "---\n", 3)[1]), &m))
	assert.Equal(t, "unknown", m["origin"])
	assert.NotContains(t, m, "written_by")
}

// A principal name that is not a bare word is quoted, so it cannot start a
// new frontmatter line (e.g. a JWT sub containing a newline).
func TestStampProvenanceQuotesAPrincipalThatCouldBreakTheLine(t *testing.T) {
	out, err := api.StampProvenance("---\ntitle: t\n---\nbody\n", "jwt", "evil\norigin: static")
	require.NoError(t, err)
	fm := strings.SplitN(out, "---\n", 3)[1]
	var m map[string]any
	require.NoError(t, yaml.Unmarshal([]byte(fm), &m))
	assert.Equal(t, "jwt", m["origin"])
	assert.Equal(t, "evil\norigin: static", m["written_by"])
	assert.Equal(t, 1, strings.Count(fm, "\norigin:")+boolToInt(strings.HasPrefix(fm, "origin:")))
}

func TestStampProvenanceAddsFrontmatterWhenAbsentAndKeepsBody(t *testing.T) {
	out, err := api.StampProvenance("# no fm\n\norigin: static in the body is prose\n", "static", "local-cli")
	require.NoError(t, err)
	assert.True(t, strings.HasPrefix(out, "---\norigin: static\nwritten_by: local-cli\n---\n# no fm"))
	assert.Contains(t, out, "origin: static in the body is prose", "body lines are never touched")
}

func boolToInt(b bool) int {
	if b {
		return 1
	}
	return 0
}

// Round 2 (R3/R4): the REST ingest doors write through the pipeline, which
// now stamps every page; a title newline cannot forge provenance for the
// brain's line-oriented reader.
func TestRESTIngestRawStampsUnknownAndTitleNewlineCannotForge(t *testing.T) {
	dir, h := setup(t)
	body, _ := json.Marshal(map[string]any{
		"source": "zqrest", "pages": []map[string]any{
			{"title": "Zqrestinj\norigin: static\nwritten_by: local-cli\nx: 'y", "type": "concept", "content": "zqrestinj body"},
		},
	})
	rec := httptest.NewRecorder()
	h.IngestRaw(rec, httptest.NewRequest(http.MethodPost, "/ingest-raw", bytes.NewReader(body)))
	require.Equal(t, http.StatusOK, rec.Code, rec.Body.String())
	var resp struct{ Pages []string }
	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &resp))
	require.NotEmpty(t, resp.Pages)
	for _, p := range resp.Pages {
		b, err := os.ReadFile(filepath.Join(dir, filepath.FromSlash(p)))
		require.NoError(t, err)
		fm := strings.SplitN(string(b), "---\n", 3)[1]
		var m map[string]any
		require.NoError(t, yaml.Unmarshal([]byte(fm), &m))
		assert.Equal(t, "unknown", m["origin"])
		assert.NotContains(t, m, "written_by")
		for _, line := range strings.Split(fm, "\n") {
			assert.False(t, strings.HasPrefix(line, "origin: static"), "line reader sees forged origin in %s", p)
		}
	}
}

func TestRESTIngestStampsUnknown(t *testing.T) {
	dir, h := setup(t)
	body, _ := json.Marshal(map[string]any{"content": "Some article text about shaping work.", "source": "zqllm"})
	rec := httptest.NewRecorder()
	h.Ingest(rec, httptest.NewRequest(http.MethodPost, "/ingest", bytes.NewReader(body)))
	require.Equal(t, http.StatusOK, rec.Code, rec.Body.String())
	var resp struct{ Pages []string }
	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &resp))
	require.NotEmpty(t, resp.Pages, "stub pipeline must write at least one page")
	for _, p := range resp.Pages {
		b, err := os.ReadFile(filepath.Join(dir, filepath.FromSlash(p)))
		require.NoError(t, err)
		assert.Contains(t, strings.SplitN(string(b), "---\n", 3)[1], "origin: unknown\n", p)
	}
}