phraser: the backend types move to server.go (V-397)

Verbatim move: backend, borrowedBackend, llamaProc, lineTail, extractPort
and listenRE. The spawn functions follow in the next commit.

internal/phraser/llmphraser.go

@@ -12,7 +12,6 @@ import (
 	"net/http"
 	"os"
 	"os/exec"
-	"regexp"
 	"strings"
 	"sync"
 	"syscall"
@@ -25,8 +24,6 @@ import (
 	"github.com/kami/maven/internal/router"
 )
 
-var listenRE = regexp.MustCompile(`listening on (https?://\S+)`)
-
 // errEmptyResponse — the server answered and said nothing. Separate from a
 // transport failure: the model is up and produced no tokens, which is still not
 // an answer and must not score as one.
@@ -218,41 +215,6 @@ func loadNudgeTemplates() *NudgeTemplates {
 	return nt
 }
 
-// backend — one llama-server this phraser talks to. Two implementations: a
-// llamaProc we spawned and must reap, and a borrowedBackend someone else owns.
-type backend interface {
-	BaseURL() string
-	Close() error
-}
-
-// borrowedBackend — a server started and owned by someone else (the phrasing
-// scorer's shared llama-server). Closing it is a no-op by construction.
-type borrowedBackend string
-
-func (b borrowedBackend) BaseURL() string { return string(b) }
-func (b borrowedBackend) Close() error    { return nil }
-
-// llamaProc — a llama-server child process plus the goroutine reading its
-// stderr. Close kills and reaps it; see the Pdeathsig note in spawnLlamaServer.
-type llamaProc struct {
-	base   string
-	cmd    *exec.Cmd
-	cancel context.CancelFunc
-	wg     sync.WaitGroup
-}
-
-func (l *llamaProc) BaseURL() string { return l.base }
-
-func (l *llamaProc) Close() error {
-	l.cancel()
-	if l.cmd != nil && l.cmd.Process != nil {
-		_ = l.cmd.Process.Kill()
-		_ = l.cmd.Wait() // reap the process — without Wait, the child becomes a zombie
-	}
-	l.wg.Wait()
-	return nil
-}
-
 // spawnLlamaServer starts one llama-server for cfg and waits until it says which
 // address it is listening on. ctx owns the process lifetime, so it must be the
 // daemon's context, not a request's.
@@ -376,34 +338,6 @@ func startLlamaProc(ctx context.Context, cfg Config) (*llamaProc, error) {
 	}
 }
 
-// lineTail keeps the last few startup lines so a server that dies before it
-// listens can say why in the error, not just "EOF". Written by the reader
-// goroutine and read by whoever gives up on startup, so it takes a lock.
-type lineTail struct {
-	mu    sync.Mutex
-	lines []string
-}
-
-const lineTailMax = 12
-
-func (t *lineTail) add(line string) {
-	t.mu.Lock()
-	defer t.mu.Unlock()
-	t.lines = append(t.lines, line)
-	if len(t.lines) > lineTailMax {
-		t.lines = t.lines[len(t.lines)-lineTailMax:]
-	}
-}
-
-func (t *lineTail) String() string {
-	t.mu.Lock()
-	defer t.mu.Unlock()
-	if len(t.lines) == 0 {
-		return "(no output)"
-	}
-	return strings.Join(t.lines, " | ")
-}
-
 // BaseURL is the llama-server this phraser talks to right now. It changes when
 // the model is swapped, so callers that cache it must register an observer
 // (OnSwap) rather than keeping the string forever.
@@ -1155,11 +1089,3 @@ func buildNudgePrompt(c loop.Candidate) string {
 
 	return strings.Join(ctxParts, "\n") + "\n\n" + tail
 }
-
-func extractPort(listen string) string {
-	_, port, _ := strings.Cut(listen, ":")
-	if port == "" {
-		return "0"
-	}
-	return port
-}

internal/phraser/server.go

@@ -0,0 +1,87 @@
+// phraser/server.go — the llama-server this phraser talks to: the child
+// process it may own, and the startup handshake that waits for the port.
+//
+// Nothing here knows what a prompt is. Split out of llmphraser.go so the
+// phrasing paths and the process lifetime read as two subjects.
+package phraser
+
+import (
+	"context"
+	"os/exec"
+	"regexp"
+	"strings"
+	"sync"
+)
+
+var listenRE = regexp.MustCompile(`listening on (https?://\S+)`)
+
+// backend — one llama-server this phraser talks to. Two implementations: a
+// llamaProc we spawned and must reap, and a borrowedBackend someone else owns.
+type backend interface {
+	BaseURL() string
+	Close() error
+}
+
+// borrowedBackend — a server started and owned by someone else (the phrasing
+// scorer's shared llama-server). Closing it is a no-op by construction.
+type borrowedBackend string
+
+func (b borrowedBackend) BaseURL() string { return string(b) }
+func (b borrowedBackend) Close() error    { return nil }
+
+// llamaProc — a llama-server child process plus the goroutine reading its
+// stderr. Close kills and reaps it; see the Pdeathsig note in spawnLlamaServer.
+type llamaProc struct {
+	base   string
+	cmd    *exec.Cmd
+	cancel context.CancelFunc
+	wg     sync.WaitGroup
+}
+
+func (l *llamaProc) BaseURL() string { return l.base }
+
+func (l *llamaProc) Close() error {
+	l.cancel()
+	if l.cmd != nil && l.cmd.Process != nil {
+		_ = l.cmd.Process.Kill()
+		_ = l.cmd.Wait() // reap the process — without Wait, the child becomes a zombie
+	}
+	l.wg.Wait()
+	return nil
+}
+
+// lineTail keeps the last few startup lines so a server that dies before it
+// listens can say why in the error, not just "EOF". Written by the reader
+// goroutine and read by whoever gives up on startup, so it takes a lock.
+type lineTail struct {
+	mu    sync.Mutex
+	lines []string
+}
+
+const lineTailMax = 12
+
+func (t *lineTail) add(line string) {
+	t.mu.Lock()
+	defer t.mu.Unlock()
+	t.lines = append(t.lines, line)
+	if len(t.lines) > lineTailMax {
+		t.lines = t.lines[len(t.lines)-lineTailMax:]
+	}
+}
+
+func (t *lineTail) String() string {
+	t.mu.Lock()
+	defer t.mu.Unlock()
+	if len(t.lines) == 0 {
+		return "(no output)"
+	}
+	return strings.Join(t.lines, " | ")
+}
+
+func extractPort(listen string) string {
+	_, port, _ := strings.Cut(listen, ":")
+	if port == "" {
+		return "0"
+	}
+	return port
+}