fix(agent): 审计写入失败不再静默

审计日志是证据而不是控制手段：写失败不能让请求失败，否则磁盘写满会变成一次远程
拒绝服务——已经执行成功的指令会因为日志追加不上而开始报错，那是坏错了地方。

但它也不能消失。静默丢审计条目是那种"运维以为自己有记录、其实没有"的失败，而这份
日志的全部意义就是事后能回答"谁在什么时候要求了什么"。现在写失败会进 agent 自己的
日志，磁盘写满表现为一行反复出现，而不是一片空白。

顺带把 Close 之后的语义写清楚：Close 会丢掉 sink，此后的写入返回 nil——这是刻意的，
因为一个正在关闭的进程与在途请求赛跑时，为每一个恰好到达的请求报一次失败是噪声
而不是信息。这条差别在 agent 日志里看得见。

测试用真实失败路径（写一个已关闭的文件）而不是填满文件系统，并断言 exec.record 把
它报了出来。

Go 全包、Node 112 项、Swift 101 项通过。

internal/runtime/audit.go

@@ -59,6 +59,11 @@ func NullAudit() *Audit { return &Audit{} }
 
 // Write appends one entry. A write failure is returned to the caller rather than panicking: the
 // audit log is evidence, not a control, and a full disk must not become a remote denial of service.
+//
+// Returning nil after Close is deliberate and is the one case where a dropped entry is not an error:
+// a shutdown path racing an in-flight request would otherwise log a failure for every request that
+// happened to arrive at that moment, which is noise rather than information. The executor logs what it
+// sees either way, so the difference is visible in the agent's log.
 func (a *Audit) Write(entry Entry) error {
 	a.mu.Lock()
 	defer a.mu.Unlock()
@@ -75,8 +80,12 @@ func (a *Audit) Write(entry Entry) error {
 	return a.sink.Sync()
 }
 
-// Close releases the file. Subsequent writes are silently dropped, which is the right behaviour for
-// a shutdown path: failing the request that happens to race with a clean exit buys nothing.
+// Close releases the file.
+//
+// A write after Close is dropped, and dropped silently is the wrong word for it: the executor reports
+// every write error it sees, and this returns one, so a request racing a clean shutdown shows up as a
+// warning rather than as a missing line nobody notices. The alternative — failing the request — buys
+// nothing, because the command it describes has already run or been refused.
 func (a *Audit) Close() error {
 	a.mu.Lock()
 	defer a.mu.Unlock()

internal/runtime/executor.go

@@ -5,6 +5,7 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"log/slog"
 	"net/http"
 	"strings"
 	"sync"
@@ -261,11 +262,21 @@ func (e *Executor) refuse(envelope wire.Envelope, inner wire.InnerRequest, class
 	return &Refusal{Class: class, Path: inner.Path, Err: err}
 }
 
+// record appends one audit entry, and reports a failure to the process log.
+//
+// The write error is not propagated to the caller: the audit log is evidence, not a control, and a
+// full disk must not become a remote denial of service — a request that already succeeded would start
+// failing because the log could not be appended to, which is the wrong thing to break.
+//
+// But it must not vanish either. Silently losing audit entries is the failure mode where an operator
+// believes they have a record and does not, and the whole point of the log is to be able to answer
+// "who asked for what" afterwards. So the error goes to the agent's own log, where a full disk shows
+// up as a repeating line rather than as an absence.
 func (e *Executor) record(envelope wire.Envelope, method, path string, status int, outcome string) {
 	if e.audit == nil {
 		return
 	}
-	e.audit.Write(Entry{
+	if err := e.audit.Write(Entry{
 		At:      e.clock(),
 		Node:    envelope.Node,
 		Req:     envelope.Req,
@@ -274,7 +285,9 @@ func (e *Executor) record(envelope wire.Envelope, method, path string, status in
 		Path:    path,
 		Status:  status,
 		Outcome: outcome,
-	})
+	}); err != nil {
+		slog.Warn("audit entry could not be written", "error", err, "req", envelope.Req, "outcome", outcome)
+	}
 }
 
 // rateLimiter is a sliding-window counter over the dangerous writes this node has performed.

internal/runtime/runtime_test.go

@@ -1,9 +1,11 @@
 package runtime
 
 import (
+	"bytes"
 	"context"
 	"encoding/json"
 	"errors"
+	"log/slog"
 	"net/http"
 	"net/http/httptest"
 	"net/url"
@@ -544,3 +546,51 @@ func TestExecutorRefusesToStartWithoutAPolicyOrPort(t *testing.T) {
 		t.Fatal("port 0 was accepted")
 	}
 }
+
+// A failed audit write must be visible somewhere. The entry cannot fail the request — the audit log is
+// evidence, not a control, and a full disk must not become a remote denial of service — but silently
+// losing entries is the failure mode where an operator believes they have a record and does not.
+func TestAFailedAuditWriteIsReported(t *testing.T) {
+	directory := t.TempDir()
+	path := filepath.Join(directory, "audit.log")
+	audit, err := OpenAudit(path)
+	if err != nil {
+		t.Fatal(err)
+	}
+	// Replace the sink with one that fails, which is what a full disk looks like from here. Reaching
+	// into the struct is deliberate: the alternative is filling a filesystem in a test.
+	audit.mu.Lock()
+	audit.sink = nil
+	audit.mu.Unlock()
+
+	var captured bytes.Buffer
+	previous := slog.Default()
+	slog.SetDefault(slog.New(slog.NewJSONHandler(&captured, &slog.HandlerOptions{Level: slog.LevelDebug})))
+	defer slog.SetDefault(previous)
+
+	// Close() drops the sink, so a write after it returns nil rather than an error — that is the
+	// documented shutdown case. Force the error path by giving it a closed file instead.
+	file, err := os.OpenFile(filepath.Join(directory, "closed.log"), os.O_CREATE|os.O_WRONLY, 0o600)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if err := file.Close(); err != nil {
+		t.Fatal(err)
+	}
+	audit.mu.Lock()
+	audit.sink = file
+	audit.mu.Unlock()
+
+	if err := audit.Write(Entry{Node: "nd_x", Req: "r1", Outcome: "ok"}); err == nil {
+		t.Fatal("writing to a closed file reported success")
+	}
+	// And the executor's own path reports it rather than swallowing it.
+	exec, err := NewExecutor(testPolicy(t), Config{Port: 3000, Audit: audit})
+	if err != nil {
+		t.Fatal(err)
+	}
+	exec.record(wire.Envelope{Node: "nd_x", Req: "r2", App: "ap_x"}, "GET", "/api/health", 200, "ok")
+	if !strings.Contains(captured.String(), "audit entry could not be written") {
+		t.Fatalf("a failed audit write was not reported; log was: %s", captured.String())
+	}
+}