feat(ingestion): add /ingest and /ingest-path HTTP handlers

Wires pipeline.Run into the HTTP layer so callers can ingest raw text
or files/directories without touching the filesystem directly. Rewrites
main.go to parse LLM and watcher env vars and build pipeline.Config.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Mathias Bergqvist
2026-04-22 22:54:28 +02:00
parent 78531bb238
commit a25bb18c54
3 changed files with 356 additions and 21 deletions

View File

@@ -3,6 +3,7 @@ package api_test
import (
"bytes"
"context"
"encoding/json"
"log/slog"
"net/http"
@@ -12,11 +13,26 @@ import (
"strings"
"testing"
"github.com/mathiasbq/hyperguild/ingestion/internal/api"
"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 page so tests never call a real LLM.
func stubComplete(_ context.Context, _, _ string) (string, error) {
return `[{"path":"wiki/sources/test-source.md","content":"# Test Source\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()
@@ -27,9 +43,13 @@ func setup(t *testing.T) (string, *api.Handler) {
0o644,
))
logger := slog.New(slog.NewTextHandler(os.Stderr, nil))
return dir, api.NewHandler(dir, logger)
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})
@@ -112,3 +132,120 @@ func TestWrite_GeneratesFilenameIfAbsent(t *testing.T) {
assert.Len(t, entries, 2)
assert.True(t, strings.HasSuffix(entries[1].Name(), ".md"))
}
// ---------------------------------------------------------------------------
// POST /ingest
// ---------------------------------------------------------------------------
func TestIngest_MissingContent(t *testing.T) {
_, h := setup(t)
body, _ := json.Marshal(map[string]any{"source": "test-source"})
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_MissingSource(t *testing.T) {
_, h := setup(t)
body, _ := json.Marshal(map[string]any{"content": "some content"})
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)
}
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)
}