mathias/hyperguild
1
0
Fork 0
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files

179
ingestion/internal/api/handler.go
View File

@@ -11,6 +11,7 @@ import (
"strings"
"time"
"github.com/mathiasbq/hyperguild/ingestion/internal/pipeline"
"github.com/mathiasbq/hyperguild/ingestion/internal/search"
)
@@ -18,11 +19,15 @@ import (
type Handler struct {
brainDir string
logger *slog.Logger
pipeline pipeline.Config
}
// NewHandler constructs a Handler. brainDir is the absolute path to brain/.
func NewHandler(brainDir string, logger *slog.Logger) *Handler {
return &Handler{brainDir: brainDir, logger: logger}
func NewHandler(brainDir string, logger *slog.Logger, pipelineCfg pipeline.Config) *Handler {
if logger == nil {
logger = slog.Default()
}
return &Handler{brainDir: brainDir, logger: logger, pipeline: pipelineCfg}
}
type queryRequest struct {
@@ -37,15 +42,32 @@ type writeRequest struct {
Domain string `json:"domain,omitempty"`
}
type ingestRequest struct {
Content string `json:"content"`
Source string `json:"source"`
DryRun bool `json:"dry_run"`
}
type ingestPathRequest struct {
Path string `json:"path"`
Source string `json:"source"`
DryRun bool `json:"dry_run"`
}
type ingestResponse struct {
Pages []string `json:"pages"`
Warnings []string `json:"warnings"`
}
// Query handles POST /query — full-text search across the brain wiki.
func (h *Handler) Query(w http.ResponseWriter, r *http.Request) {
var req queryRequest
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
http.Error(w, "invalid JSON", http.StatusBadRequest)
writeError(w, http.StatusBadRequest, "invalid JSON")
return
}
if strings.TrimSpace(req.Query) == "" {
http.Error(w, "query is required", http.StatusBadRequest)
writeError(w, http.StatusBadRequest, "query is required")
return
}
if req.Limit == 0 {
@@ -55,22 +77,22 @@ func (h *Handler) Query(w http.ResponseWriter, r *http.Request) {
results, err := search.Query(h.brainDir, req.Query, req.Limit)
if err != nil {
h.logger.Error("query failed", "err", err)
http.Error(w, "search error", http.StatusInternalServerError)
writeError(w, http.StatusInternalServerError, "search error")
return
}
writeJSON(w, map[string]any{"results": results})
}
// Write handles POST /write — write raw content to brain/raw/.
// Write handles POST /write — write raw content to brain/knowledge/.
func (h *Handler) Write(w http.ResponseWriter, r *http.Request) {
var req writeRequest
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
http.Error(w, "invalid JSON", http.StatusBadRequest)
writeError(w, http.StatusBadRequest, "invalid JSON")
return
}
if req.Content == "" {
http.Error(w, "content is required", http.StatusBadRequest)
writeError(w, http.StatusBadRequest, "content is required")
return
}
@@ -81,7 +103,7 @@ func (h *Handler) Write(w http.ResponseWriter, r *http.Request) {
rawDir := filepath.Join(h.brainDir, "knowledge")
if err := os.MkdirAll(rawDir, 0o755); err != nil {
http.Error(w, "failed to create raw dir", http.StatusInternalServerError)
writeError(w, http.StatusInternalServerError, "failed to create raw dir")
return
}
@@ -106,7 +128,7 @@ func (h *Handler) Write(w http.ResponseWriter, r *http.Request) {
dest := filepath.Join(rawDir, base)
if err := os.WriteFile(dest, []byte(finalContent), 0o644); err != nil {
h.logger.Error("write failed", "err", err)
http.Error(w, "write error", http.StatusInternalServerError)
writeError(w, http.StatusInternalServerError, "write error")
return
}
@@ -114,7 +136,144 @@ func (h *Handler) Write(w http.ResponseWriter, r *http.Request) {
writeJSON(w, map[string]string{"path": filepath.ToSlash(rel)})
}
// Ingest handles POST /ingest — run the pipeline on provided content.
func (h *Handler) Ingest(w http.ResponseWriter, r *http.Request) {
var req ingestRequest
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
writeError(w, http.StatusBadRequest, "invalid JSON")
return
}
if strings.TrimSpace(req.Content) == "" {
writeError(w, http.StatusBadRequest, "content is required")
return
}
if strings.TrimSpace(req.Source) == "" {
writeError(w, http.StatusBadRequest, "source is required")
return
}
result, err := pipeline.Run(r.Context(), h.pipeline, h.brainDir, req.Content, req.Source, req.DryRun)
if err != nil {
h.logger.Error("ingest failed", "source", req.Source, "err", err)
writeError(w, http.StatusInternalServerError, fmt.Sprintf("ingest error: %v", err))
return
}
pages := result.Pages
if pages == nil {
pages = []string{}
}
warnings := result.Warnings
if warnings == nil {
warnings = []string{}
}
writeJSON(w, ingestResponse{Pages: pages, Warnings: warnings})
}
// supportedExtensions lists file extensions that IngestPath will process.
var supportedExtensions = map[string]bool{
".md": true,
".txt": true,
".pdf": true,
}
// IngestPath handles POST /ingest-path — ingest a file or directory.
func (h *Handler) IngestPath(w http.ResponseWriter, r *http.Request) {
var req ingestPathRequest
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
writeError(w, http.StatusBadRequest, "invalid JSON")
return
}
if strings.TrimSpace(req.Path) == "" {
writeError(w, http.StatusBadRequest, "path is required")
return
}
info, err := os.Stat(req.Path)
if err != nil {
writeError(w, http.StatusBadRequest, fmt.Sprintf("path not accessible: %v", err))
return
}
var allPages []string
var allWarnings []string
if info.IsDir() {
err = filepath.WalkDir(req.Path, func(path string, d os.DirEntry, walkErr error) error {
if walkErr != nil {
return walkErr
}
if d.IsDir() {
return nil
}
ext := strings.ToLower(filepath.Ext(path))
if !supportedExtensions[ext] {
return nil
}
content, readErr := os.ReadFile(path)
if readErr != nil {
allWarnings = append(allWarnings, fmt.Sprintf("read %s: %v", path, readErr))
return nil
}
source := req.Source
if source == "" {
source = filepath.Base(path)
}
result, runErr := pipeline.Run(r.Context(), h.pipeline, h.brainDir, string(content), source, req.DryRun)
if runErr != nil {
allWarnings = append(allWarnings, fmt.Sprintf("ingest %s: %v", path, runErr))
return nil
}
allPages = append(allPages, result.Pages...)
allWarnings = append(allWarnings, result.Warnings...)
return nil
})
if err != nil {
h.logger.Error("walk dir failed", "path", req.Path, "err", err)
writeError(w, http.StatusInternalServerError, fmt.Sprintf("walk error: %v", err))
return
}
} else {
ext := strings.ToLower(filepath.Ext(req.Path))
if !supportedExtensions[ext] {
writeError(w, http.StatusBadRequest, fmt.Sprintf("unsupported file extension: %s", ext))
return
}
content, readErr := os.ReadFile(req.Path)
if readErr != nil {
writeError(w, http.StatusInternalServerError, fmt.Sprintf("read file: %v", readErr))
return
}
source := req.Source
if source == "" {
source = filepath.Base(req.Path)
}
result, runErr := pipeline.Run(r.Context(), h.pipeline, h.brainDir, string(content), source, req.DryRun)
if runErr != nil {
h.logger.Error("ingest-path failed", "path", req.Path, "err", runErr)
writeError(w, http.StatusInternalServerError, fmt.Sprintf("ingest error: %v", runErr))
return
}
allPages = result.Pages
allWarnings = result.Warnings
}
if allPages == nil {
allPages = []string{}
}
if allWarnings == nil {
allWarnings = []string{}
}
writeJSON(w, ingestResponse{Pages: allPages, Warnings: allWarnings})
}
func writeJSON(w http.ResponseWriter, v any) {
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(v) //nolint:errcheck
}
func writeError(w http.ResponseWriter, code int, msg string) {
w.Header().Set("Content-Type", "application/json")
w.WriteHeader(code)
json.NewEncoder(w).Encode(map[string]string{"error": msg}) //nolint:errcheck
}

141
ingestion/internal/api/handler_test.go
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)
}