feat(httpapi): default search backend is var/bin/brain-search.

bin/brain/serve.go is the command; bin/serve.go stays as a tagged
deprecation shim. Tests fail if the default path still names Python.

AGENTS.md

@@ -36,11 +36,9 @@ PLAN.md       decisions + execution + open questions
 docs/         published docs
 skills/       in-project agent skills (vendored, no external links)
 bin/          self-describing tools bin/{subject}/{method}.go (shebang)
-bin/brain/    search.go (deduction); libs in internal/brain
+bin/brain/    search.go, serve.go; libs in internal/brain and internal/httpapi
 internal/     shared Go (brain/rank is cgo-free)
-bin/serve.go  async Go HTTP server entry (self-executing go run shebang)
-bin/watch/    corpus watcher Go package (mtimes, no inotify deps)
-bin/server/   async Go HTTP server (goroutines, bounded worker pool)
+bin/watch/    corpus watcher (internal via bin/brain/watch later)
 bin/mail/     mail pipeline: sync (Go), import (md), index_mail (rebuild)
 bin/tools/    vendored python libs behind bin/* (kblib, yamlout, websearch)
 bin/docker-entrypoint  container entrypoint (brain index|search|serve|watch)

bin/brain/serve.go

@@ -0,0 +1,26 @@
+//usr/bin/env go run -tags=brain_serve "$0" "$@"; exit
+//go:build brain_serve
+//
+// bin/brain/serve.go - HTTP API for the 2dph brain.
+//
+//	KB_ROOT=/path/to/2dph ./bin/brain/serve.go
+//	KB_SEARCH_CMD=... KB_WORKERS=4 KB_PORT=8630 ./bin/brain/serve.go
+//
+// Default search backend is var/bin/brain-search (Go), not Python.
+// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
+package main
+
+import (
+	"os"
+
+	"github.com/eSlider/2dph/internal/httpapi"
+)
+
+func main() {
+	if os.Getenv("KB_ROOT") == "" {
+		if wd, err := os.Getwd(); err == nil {
+			os.Setenv("KB_ROOT", wd)
+		}
+	}
+	httpapi.Run()
+}

bin/doc.go

@@ -0,0 +1,2 @@
+// Deprecated shebang mains at bin root (serve.go is tagged brain_serve).
+package main

bin/serve.go

@@ -1,27 +1,22 @@
-//usr/bin/env go run "$0" "$@"; exit
-// bin/serve.go - async Go HTTP server for the 2dph brain (see bin/server).
+//usr/bin/env go run -tags=brain_serve "$0" "$@"; exit
+//go:build brain_serve
 //
-//	KB_ROOT=/path/to/2dph ./bin/serve.go        # serve the brain
-//	KB_SEARCH_CMD=... KB_WORKERS=4 KB_PORT=8630 ./bin/serve.go
-//
-// Shebang trick: the first line is a Go `//` comment; when executed, env runs
-// `go run "$0"` so this file doubles as an executable script. The real code
-// lives in the importable package (module path, never a relative import).
-// NOTE: never run `gofmt -w` on this file - it rewrites `//usr/bin/env` to
-// `// usr/...` and breaks the shebang.
+// bin/serve.go — deprecated; use bin/brain/serve.go.
 package main
 
 import (
+	"fmt"
 	"os"
 
-	"github.com/eSlider/2dph/bin/server"
+	"github.com/eSlider/2dph/internal/httpapi"
 )
 
 func main() {
-	if env := os.Getenv("KB_ROOT"); env == "" {
+	fmt.Fprintln(os.Stderr, "bin/serve.go is deprecated; use bin/brain/serve.go")
+	if os.Getenv("KB_ROOT") == "" {
 		if wd, err := os.Getwd(); err == nil {
 			os.Setenv("KB_ROOT", wd)
 		}
 	}
-	server.Run()
+	httpapi.Run()
 }

internal/httpapi/server.go

@@ -2,15 +2,10 @@
 //
 // Async by design: every request runs on its own goroutine, and CPU-heavy
 // searches are serialized through a bounded worker pool (a counting
-// semaphore) so N requests can't spawn N Python interpreters at once.
+// semaphore) so N requests can't spawn N search processes at once.
 //
-// Used by bin/serve.go which is a self-executing shebang script:
-//
-//	///usr/bin/env go run "$0" "$@"; exit
-//	package main
-//	import "github.com/eSlider/2dph/bin/server"
-//	func main() { server.Run() }
-package server
+// Used by bin/brain/serve.go.
+package httpapi
 
 import (
 	"context"
@@ -100,8 +95,8 @@ func writeRaw(w http.ResponseWriter, code int, body []byte) {
 	w.Write(body)
 }
 
-// brainSearcher shells out to bin/kb/search --json. A single python search
-// is bounded and short-lived; the worker pool keeps at most N live.
+// brainSearcher shells out to the Go brain-search binary (not Python).
+// A single search is bounded and short-lived; the worker pool keeps at most N live.
 type brainSearcher struct {
 	cmdPath string
 	timeout time.Duration
@@ -122,15 +117,18 @@ func (b *brainSearcher) Search(ctx context.Context, query string, limit int) ([]
 	return out, nil
 }
 
-// Run starts the HTTP server. Reads env: KB_SEARCH_CMD (default bin/kb/search,
-// relative to the repo root given by KB_ROOT), KB_WORKERS (default 4), KB_PORT
-// (default 8630).
+func defaultSearchCmd(root string) string {
+	if env := os.Getenv("KB_SEARCH_CMD"); env != "" {
+		return env
+	}
+	return filepath.Join(root, "var", "bin", "brain-search")
+}
+
+// Run starts the HTTP server. Reads env: KB_SEARCH_CMD (default
+// $KB_ROOT/var/bin/brain-search), KB_WORKERS (default 4), KB_PORT (default 8630).
 func Run() {
 	root := os.Getenv("KB_ROOT")
-	searchPath := os.Getenv("KB_SEARCH_CMD")
-	if searchPath == "" {
-		searchPath = filepath.Join(root, "bin", "kb", "search")
-	}
+	searchPath := defaultSearchCmd(root)
 	workers := 4
 	if raw := os.Getenv("KB_WORKERS"); raw != "" {
 		if n, err := strconv.Atoi(raw); err == nil && n > 0 {
@@ -147,7 +145,7 @@ func Run() {
 	searcher := &brainSearcher{cmdPath: searchPath, timeout: 60 * time.Second}
 	handler := NewServer(searcher, workers)
 	addr := "127.0.0.1:" + strconv.Itoa(port)
-	log.Printf("serve: %s (workers=%d)", addr, workers)
+	log.Printf("serve: %s (workers=%d cmd=%s)", addr, workers, searchPath)
 	if err := http.ListenAndServe(addr, handler); err != nil {
 		log.Fatal(err)
 	}

internal/httpapi/server_test.go

@@ -1,10 +1,11 @@
-package server
+package httpapi
 
 import (
 	"context"
 	"encoding/json"
 	"net/http"
 	"net/http/httptest"
+	"strings"
 	"sync"
 	"sync/atomic"
 	"testing"
@@ -141,6 +142,17 @@ func TestSearchRejectsBadLimit(t *testing.T) {
 	}
 }
 
+func TestDefaultSearchCmdIsBrainNotPython(t *testing.T) {
+	t.Setenv("KB_SEARCH_CMD", "")
+	cmd := defaultSearchCmd("/repo")
+	if strings.Contains(strings.ToLower(cmd), "python") {
+		t.Fatalf("search path still python: %s", cmd)
+	}
+	if !strings.Contains(cmd, "brain") {
+		t.Fatalf("search path must be the Go brain binary, got %s", cmd)
+	}
+}
+
 func TestSearchTimeout(t *testing.T) {
 	fs := &fakeSearcher{delay: time.Second}
 	h := NewServer(fs, 1)