hyperguild/ingestion/internal/api/handler_test.go

// ingestion/internal/api/handler_test.go
package api_test

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

	"github.com/stretchr/testify/assert"
	"github.com/stretchr/testify/require"

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

// stubComplete returns a fixed JSON RawPage so tests never call a real LLM.
func stubComplete(_ context.Context, _, _ string) (string, error) {
	return `[{"title":"Test Source","type":"source","subtype":"article","content":"## Summary\n\nSome content here.\n"}]`, nil
}

func stubPipelineCfg() pipeline.Config {
	return pipeline.Config{
		Complete:  stubComplete,
		ChunkSize: 0,
		Schema:    "# Test Schema\nwiki/sources/, wiki/concepts/, wiki/entities/",
	}
}

func setup(t *testing.T) (string, *api.Handler) {
	t.Helper()
	dir := t.TempDir()
	require.NoError(t, os.MkdirAll(filepath.Join(dir, "knowledge"), 0o755))
	require.NoError(t, os.WriteFile(
		filepath.Join(dir, "knowledge", "tdd.md"),
		[]byte("---\ntitle: TDD\ndomain: software\n---\n\nTest-driven development is a discipline.\n"),
		0o644,
	))
	logger := slog.New(slog.NewTextHandler(os.Stderr, nil))
	return dir, api.NewHandler(dir, logger, stubPipelineCfg())
}

// ---------------------------------------------------------------------------
// Existing tests (Write / Query)
// ---------------------------------------------------------------------------

func TestQuery_ReturnsResults(t *testing.T) {
	_, h := setup(t)
	body, _ := json.Marshal(map[string]any{"query": "test driven", "limit": 5})
	req := httptest.NewRequest(http.MethodPost, "/query", bytes.NewReader(body))
	rec := httptest.NewRecorder()

	h.Query(rec, req)

	assert.Equal(t, http.StatusOK, rec.Code)
	var resp map[string]any
	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &resp))
	results := resp["results"].([]any)
	assert.NotEmpty(t, results)
}

func TestWrite_CreatesWikiFile(t *testing.T) {
	dir, h := setup(t)
	body, _ := json.Marshal(map[string]any{
		"content":  "# Test note\n\nSome content.",
		"filename": "test-note",
		"wing":     "homelab",
		"hall":     "facts",
	})
	req := httptest.NewRequest(http.MethodPost, "/write", bytes.NewReader(body))
	rec := httptest.NewRecorder()

	h.Write(rec, req)

	assert.Equal(t, http.StatusOK, rec.Code)
	var resp map[string]string
	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &resp))
	assert.NotEmpty(t, resp["path"])

	content, err := os.ReadFile(filepath.Join(dir, "wiki", "homelab", "facts", "test-note.md"))
	require.NoError(t, err)
	assert.Contains(t, string(content), "Some content.")
}

// TestWrite_RequiresWingAndHall is the HTTP-contract counterpart of
// TestWriteNote_RequiresWingAndHall: a caller (e.g. the MCP brain_write
// handler) that omits wing/hall gets a 400, not a silent legacy write.
func TestWrite_RequiresWingAndHall(t *testing.T) {
	_, h := setup(t)
	body, _ := json.Marshal(map[string]any{"content": "no destination"})
	req := httptest.NewRequest(http.MethodPost, "/write", bytes.NewReader(body))
	rec := httptest.NewRecorder()

	h.Write(rec, req)

	assert.Equal(t, http.StatusBadRequest, rec.Code)
}

func TestQuery_RequiresQuery(t *testing.T) {
	_, h := setup(t)
	body, _ := json.Marshal(map[string]any{"limit": 5})
	req := httptest.NewRequest(http.MethodPost, "/query", bytes.NewReader(body))
	rec := httptest.NewRecorder()

	h.Query(rec, req)

	assert.Equal(t, http.StatusBadRequest, rec.Code)
}

func TestWriteNote_HallRouteIncludesSourceTypeWhenSet(t *testing.T) {
	dir := t.TempDir()

	rel, err := api.WriteNote(dir, api.WriteNoteOptions{
		Content:    "# Claude session abc (koala)\n\nBody.\n",
		Filename:   "session-koala-abc",
		Wing:       "claude-sessions",
		Hall:       "facts",
		SourceType: "internal",
	})
	require.NoError(t, err)

	got, err := os.ReadFile(filepath.Join(dir, filepath.FromSlash(rel)))
	require.NoError(t, err)
	assert.Contains(t, string(got), "source_type: internal")
	assert.Contains(t, string(got), "wing: claude-sessions")
}

func TestWriteNote_HallFactsDefaultsSourceTypeInternalWhenUnset(t *testing.T) {
	dir := t.TempDir()

	rel, err := api.WriteNote(dir, api.WriteNoteOptions{
		Content: "manually captured fact.\n",
		Wing:    "agentsquad",
		Hall:    "facts",
	})
	require.NoError(t, err)

	got, err := os.ReadFile(filepath.Join(dir, filepath.FromSlash(rel)))
	require.NoError(t, err)
	// Most hall=facts entries are first-party (an eval/benchmark the agent ran
	// itself), not external claims — default to internal, require explicit
	// opt-out for the rare case that does need a citation (brain-gardener#7).
	assert.Contains(t, string(got), "source_type: internal")
}

func TestWriteNote_HallFactsPreservesExplicitExternalSourceType(t *testing.T) {
	dir := t.TempDir()

	rel, err := api.WriteNote(dir, api.WriteNoteOptions{
		Content:    "vendor pricing claim, needs a citation.\n",
		Wing:       "agentsquad",
		Hall:       "facts",
		SourceType: "external",
	})
	require.NoError(t, err)

	got, err := os.ReadFile(filepath.Join(dir, filepath.FromSlash(rel)))
	require.NoError(t, err)
	assert.Contains(t, string(got), "source_type: external")
}

func TestWriteNote_HallRouteOmitsSourceTypeForNonFactsHalls(t *testing.T) {
	dir := t.TempDir()

	rel, err := api.WriteNote(dir, api.WriteNoteOptions{
		Content: "a decision record.\n",
		Wing:    "agentsquad",
		Hall:    "decisions",
	})
	require.NoError(t, err)

	got, err := os.ReadFile(filepath.Join(dir, filepath.FromSlash(rel)))
	require.NoError(t, err)
	assert.NotContains(t, string(got), "source_type")
}

func TestWriteNote_HallRouteMergesExistingFrontmatterInsteadOfStacking(t *testing.T) {
	dir := t.TempDir()

	rel, err := api.WriteNote(dir, api.WriteNoteOptions{
		Content:  "---\ntitle: act_runner host-executor\ntags: [gitea-actions, act_runner]\n---\n\n# Body\n\nSome content.\n",
		Filename: "act-runner-host-executor",
		Wing:     "homelab",
		Hall:     "failures",
	})
	require.NoError(t, err)

	got, err := os.ReadFile(filepath.Join(dir, filepath.FromSlash(rel)))
	require.NoError(t, err)
	body := string(got)

	// exactly one frontmatter block: only two "---" delimiter lines total
	assert.Equal(t, 2, strings.Count(body, "---\n"), "expected a single merged frontmatter block, not stacked blocks")
	assert.Contains(t, body, "wing: homelab")
	assert.Contains(t, body, "hall: failures")
	assert.Contains(t, body, "title: act_runner host-executor")
	assert.Contains(t, body, "tags: [gitea-actions, act_runner]")
	assert.Contains(t, body, "# Body")
}

// TestWriteNote_RequiresWingAndHall pins the post-legacy-removal contract
// (hyperguild#79 / ADR-0012): with the knowledge/ fallback gone, wing+hall
// is the only valid destination, so omitting either is a caller error, not
// a silent fallback.
func TestWriteNote_RequiresWingAndHall(t *testing.T) {
	cases := []struct {
		name string
		wing string
		hall string
	}{
		{"neither set", "", ""},
		{"wing only", "homelab", ""},
		{"hall only", "", "facts"},
	}
	for _, tc := range cases {
		t.Run(tc.name, func(t *testing.T) {
			dir := t.TempDir()
			_, err := api.WriteNote(dir, api.WriteNoteOptions{
				Content: "body",
				Wing:    tc.wing,
				Hall:    tc.hall,
			})
			require.Error(t, err)
			assert.Contains(t, err.Error(), "wing and hall are required")
		})
	}
}

func TestWrite_GeneratesFilenameIfAbsent(t *testing.T) {
	dir, h := setup(t)
	body, _ := json.Marshal(map[string]any{
		"content": "auto name",
		"wing":    "homelab",
		"hall":    "facts",
	})
	req := httptest.NewRequest(http.MethodPost, "/write", bytes.NewReader(body))
	rec := httptest.NewRecorder()

	h.Write(rec, req)

	assert.Equal(t, http.StatusOK, rec.Code)
	entries, err := os.ReadDir(filepath.Join(dir, "wiki", "homelab", "facts"))
	require.NoError(t, err)
	require.Len(t, entries, 1)
	assert.True(t, strings.HasSuffix(entries[0].Name(), ".md"))
}

// TestWrite_CLIPayloadRoundTrips exercises the real Handler.Write (not a
// hand-rolled mock) over an actual HTTP round trip, POSTing the exact JSON
// envelope cmd/hyperguild's brainClient.Write sends: {wing, hall, filename,
// content}. cmd/hyperguild lives in a separate Go module from ingestion
// (no shared go.work), so a Go-level test can't import brainClient
// directly — this test instead pins the wire contract from the server
// side and proves a real `hyperguild brain write <wing> <hall> <slug>`
// invocation writes a real file with real frontmatter under wiki/<wing>/<hall>/.
// A prior version of this contract test on the client side (in
// cmd/hyperguild/http_test.go) used only an httptest.NewServer with a
// hand-rolled mock body, so it stayed green through a regression where the
// server required wing/hall but the client never sent them (hyperguild#79
// PR review).
func TestWrite_CLIPayloadRoundTrips(t *testing.T) {
	dir, h := setup(t)
	srv := httptest.NewServer(http.HandlerFunc(h.Write))
	defer srv.Close()

	payload, err := json.Marshal(struct {
		Wing     string `json:"wing"`
		Hall     string `json:"hall"`
		Filename string `json:"filename"`
		Content  string `json:"content"`
	}{Wing: "homelab", Hall: "facts", Filename: "cli-roundtrip", Content: "# CLI roundtrip\n\nReal write.\n"})
	require.NoError(t, err)

	resp, err := http.Post(srv.URL+"/write", "application/json", bytes.NewReader(payload)) //nolint:noctx
	require.NoError(t, err)
	defer resp.Body.Close() //nolint:errcheck

	assert.Equal(t, http.StatusOK, resp.StatusCode)
	var out struct {
		Path string `json:"path"`
	}
	require.NoError(t, json.NewDecoder(resp.Body).Decode(&out))
	assert.Equal(t, "wiki/homelab/facts/cli-roundtrip.md", out.Path)

	written, err := os.ReadFile(filepath.Join(dir, "wiki", "homelab", "facts", "cli-roundtrip.md"))
	require.NoError(t, err)
	assert.Contains(t, string(written), "wing: homelab")
	assert.Contains(t, string(written), "hall: facts")
	assert.Contains(t, string(written), "Real write.")
}

// ---------------------------------------------------------------------------
// POST /ingest
// ---------------------------------------------------------------------------

func TestIngest_Validation(t *testing.T) {
	cases := []struct {
		name string
		body map[string]any
	}{
		{"missing content", map[string]any{"source": "test-source"}},
		{"missing source", map[string]any{"content": "some content"}},
		{"whitespace content", map[string]any{"content": "   ", "source": "test-source"}},
		{"whitespace source", map[string]any{"content": "some content", "source": "  "}},
	}
	for _, tc := range cases {
		t.Run(tc.name, func(t *testing.T) {
			_, h := setup(t)
			body, _ := json.Marshal(tc.body)
			req := httptest.NewRequest(http.MethodPost, "/ingest", bytes.NewReader(body))
			rec := httptest.NewRecorder()

			h.Ingest(rec, req)

			assert.Equal(t, http.StatusBadRequest, rec.Code)
		})
	}
}

func TestIngest_Success(t *testing.T) {
	_, h := setup(t)
	body, _ := json.Marshal(map[string]any{
		"content": "some content about shape-up methodology",
		"source":  "shape-up-book",
		"dry_run": true,
	})
	req := httptest.NewRequest(http.MethodPost, "/ingest", bytes.NewReader(body))
	rec := httptest.NewRecorder()

	h.Ingest(rec, req)

	require.Equal(t, http.StatusOK, rec.Code)
	var resp map[string]any
	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &resp))
	pages, ok := resp["pages"]
	require.True(t, ok, "response must have pages field")
	pagesSlice, ok := pages.([]any)
	require.True(t, ok, "pages must be an array")
	assert.NotEmpty(t, pagesSlice)
}

// ---------------------------------------------------------------------------
// POST /ingest-path
// ---------------------------------------------------------------------------

func TestIngestPath_MissingPath(t *testing.T) {
	_, h := setup(t)
	body, _ := json.Marshal(map[string]any{"source": "test-source"})
	req := httptest.NewRequest(http.MethodPost, "/ingest-path", bytes.NewReader(body))
	rec := httptest.NewRecorder()

	h.IngestPath(rec, req)

	assert.Equal(t, http.StatusBadRequest, rec.Code)
}

func TestIngestPath_File(t *testing.T) {
	_, h := setup(t)

	// Create a temp file with content
	dir := t.TempDir()
	f := filepath.Join(dir, "doc.md")
	require.NoError(t, os.WriteFile(f, []byte("# Hello\nThis is markdown content."), 0o644))

	body, _ := json.Marshal(map[string]any{
		"path":    f,
		"source":  "test-doc",
		"dry_run": true,
	})
	req := httptest.NewRequest(http.MethodPost, "/ingest-path", bytes.NewReader(body))
	rec := httptest.NewRecorder()

	h.IngestPath(rec, req)

	require.Equal(t, http.StatusOK, rec.Code)
	var resp map[string]any
	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &resp))
	pages, ok := resp["pages"]
	require.True(t, ok, "response must have pages field")
	pagesSlice, ok := pages.([]any)
	require.True(t, ok, "pages must be an array")
	assert.NotEmpty(t, pagesSlice)
}

// ---------------------------------------------------------------------------
// POST /ingest-raw
// ---------------------------------------------------------------------------

func TestIngestRaw_Validation(t *testing.T) {
	cases := []struct {
		name string
		body map[string]any
	}{
		{"missing source", map[string]any{"pages": []any{map[string]any{"title": "X", "type": "concept", "content": "x"}}}},
		{"missing pages", map[string]any{"source": "test-source"}},
		{"empty pages", map[string]any{"source": "test-source", "pages": []any{}}},
	}
	for _, tc := range cases {
		t.Run(tc.name, func(t *testing.T) {
			_, h := setup(t)
			body, _ := json.Marshal(tc.body)
			req := httptest.NewRequest(http.MethodPost, "/ingest-raw", bytes.NewReader(body))
			rec := httptest.NewRecorder()

			h.IngestRaw(rec, req)

			assert.Equal(t, http.StatusBadRequest, rec.Code)
		})
	}
}

func TestIngestRaw_Success(t *testing.T) {
	dir, h := setup(t)
	body, _ := json.Marshal(map[string]any{
		"source": "test-article",
		"pages": []any{
			map[string]any{"title": "Test Article", "type": "source", "subtype": "article", "domain": "Testing", "content": "## Summary\n\nThis is a test article about [[Test Concept]].\n"},
			map[string]any{"title": "Test Concept", "type": "concept", "domain": "Testing", "content": "A concept for testing.\n"},
		},
	})
	req := httptest.NewRequest(http.MethodPost, "/ingest-raw", bytes.NewReader(body))
	rec := httptest.NewRecorder()

	h.IngestRaw(rec, req)

	require.Equal(t, http.StatusOK, rec.Code)
	var resp map[string]any
	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &resp))
	pages := resp["pages"].([]any)
	assert.Len(t, pages, 2)

	// Verify files were written
	sourcePath := filepath.Join(dir, "wiki", "sources", "test-article.md")
	assert.FileExists(t, sourcePath)
	conceptPath := filepath.Join(dir, "wiki", "concepts", "test-concept.md")
	assert.FileExists(t, conceptPath)
}

func TestIngestRaw_DryRun(t *testing.T) {
	dir, h := setup(t)
	body, _ := json.Marshal(map[string]any{
		"source": "dry-run-test",
		"pages": []any{
			map[string]any{"title": "Dry Run Source", "type": "source", "subtype": "article", "content": "Content."},
		},
		"dry_run": true,
	})
	req := httptest.NewRequest(http.MethodPost, "/ingest-raw", bytes.NewReader(body))
	rec := httptest.NewRecorder()

	h.IngestRaw(rec, req)

	require.Equal(t, http.StatusOK, rec.Code)
	var resp map[string]any
	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &resp))
	pages := resp["pages"].([]any)
	assert.NotEmpty(t, pages)

	// Verify no files were written
	sourcePath := filepath.Join(dir, "wiki", "sources", "dry-run-test.md")
	assert.NoFileExists(t, sourcePath)
}

func TestIngestPath_Directory(t *testing.T) {
	_, h := setup(t)

	// Create a temp dir with one .md file
	dir := t.TempDir()
	require.NoError(t, os.WriteFile(filepath.Join(dir, "notes.md"), []byte("# Notes\nSome notes."), 0o644))

	body, _ := json.Marshal(map[string]any{
		"path":    dir,
		"dry_run": true,
	})
	req := httptest.NewRequest(http.MethodPost, "/ingest-path", bytes.NewReader(body))
	rec := httptest.NewRecorder()

	h.IngestPath(rec, req)

	require.Equal(t, http.StatusOK, rec.Code)
	var resp map[string]any
	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &resp))
	pages, ok := resp["pages"]
	require.True(t, ok, "response must have pages field")
	pagesSlice, ok := pages.([]any)
	require.True(t, ok, "pages must be an array")
	assert.NotEmpty(t, pagesSlice)
}

// --- brain#21: claim-property envelope on the write path -------------------

func TestWriteNote_PreservesClaimEnvelopeVerbatim(t *testing.T) {
	// writeHallNote already passes unknown keys through; this pins that
	// behaviour for the envelope specifically, so a future refactor of the
	// merge loop cannot silently drop it.
	dir := t.TempDir()

	rel, err := api.WriteNote(dir, api.WriteNoteOptions{
		Content: "---\nhalf_life: durable\napplies: universal\nclaim_provenance: asserted\n---\n\nA durable claim.\n",
		Wing:    "homelab",
		Hall:    "decisions",
	})
	require.NoError(t, err)

	got, err := os.ReadFile(filepath.Join(dir, filepath.FromSlash(rel)))
	require.NoError(t, err)
	assert.Contains(t, string(got), "half_life: durable")
	assert.Contains(t, string(got), "applies: universal")
	assert.Contains(t, string(got), "claim_provenance: asserted")
}

func TestWriteNote_RejectsInvalidClaimEnvelopeAndWritesNothing(t *testing.T) {
	// Fail closed: a value outside the enum must not land. A lint skips what
	// it cannot parse, so an unvalidated write produces a note that reads as
	// classified while nothing acts on it.
	dir := t.TempDir()

	_, err := api.WriteNote(dir, api.WriteNoteOptions{
		Content:  "---\nhalf_life: forever\nclaim_provenance: asserted\n---\n\nBody.\n",
		Filename: "bad-envelope",
		Wing:     "homelab",
		Hall:     "facts",
	})
	require.Error(t, err)
	assert.Contains(t, err.Error(), "half_life")

	_, statErr := os.Stat(filepath.Join(dir, "wiki/homelab/facts/bad-envelope.md"))
	assert.True(t, os.IsNotExist(statErr), "a rejected write must leave no file behind")
}

func TestWriteNote_RejectsClaimFieldWithoutProvenance(t *testing.T) {
	dir := t.TempDir()

	_, err := api.WriteNote(dir, api.WriteNoteOptions{
		Content:  "---\napplies: homelab\n---\n\nBody.\n",
		Filename: "no-provenance",
		Wing:     "homelab",
		Hall:     "facts",
	})
	require.Error(t, err)
	assert.Contains(t, err.Error(), "claim_provenance")

	_, statErr := os.Stat(filepath.Join(dir, "wiki/homelab/facts/no-provenance.md"))
	assert.True(t, os.IsNotExist(statErr))
}

// The HTTP POST /write door reaches WriteNote directly, without the
// BrainStore, so the unresolved-wikilink strip has to live in the primitive
// or that door stays ungated.
func TestWriteNote_UnwrapsUnresolvedWikilinks(t *testing.T) {
	dir := t.TempDir()
	_, err := api.WriteNote(dir, api.WriteNoteOptions{
		Content: "# Target\n\nbody\n", Filename: "target", Wing: "a", Hall: "facts",
	})
	require.NoError(t, err)

	rel, err := api.WriteNote(dir, api.WriteNoteOptions{
		Content:  "See [[target]] and [[gitea-ci]].\n",
		Filename: "src", Wing: "a", Hall: "facts",
	})
	require.NoError(t, err)

	got, err := os.ReadFile(filepath.Join(dir, filepath.FromSlash(rel)))
	require.NoError(t, err)
	assert.Contains(t, string(got), "[[target]]")
	assert.Contains(t, string(got), "and gitea-ci.")
	assert.NotContains(t, string(got), "[[gitea-ci]]")
}

func TestUpdateNote_UnwrapsUnresolvedWikilinks(t *testing.T) {
	dir := t.TempDir()
	_, err := api.WriteNote(dir, api.WriteNoteOptions{
		Content: "old\n", Filename: "n", Wing: "a", Hall: "facts",
	})
	require.NoError(t, err)

	rel, _, _, err := api.UpdateNote(dir, api.UpdateNoteOptions{
		Wing: "a", Hall: "facts", Slug: "n",
		Content: "Related: [[secret-hygiene]].\n", Reason: "r",
	})
	require.NoError(t, err)

	got, err := os.ReadFile(filepath.Join(dir, filepath.FromSlash(rel)))
	require.NoError(t, err)
	assert.Contains(t, string(got), "Related: secret-hygiene.")
	assert.NotContains(t, string(got), "[[secret-hygiene]]")
}