From 6320dd5b13d473266d9bf31811b6e5eacff81cc4 Mon Sep 17 00:00:00 2001
From: Ilker Manap <ilker@Ilkers-MacBook-Pro.local>
Date: Sun, 8 Nov 2026 22:14:52 +0100
Subject: [PATCH] A new stream is told the node's files again

Registration carries what the agent's startup scan found, and a heartbeat
sends the list only when it changed since last sent; so a file deleted
after the agent started came back on a control plane that restarted. The
fingerprint is now forgotten with the provisioning one on every stream.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---
 CHANGELOG.md                 |  5 +++++
 internal/agent/agent.go      | 16 +++++++++++++---
 internal/agent/agent_test.go | 20 ++++++++++++++++++++
 3 files changed, 38 insertions(+), 3 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 32e99ef..68a1af0 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -64,6 +64,11 @@ APIs change between minors without a deprecation period.
   four, as the room left holds, and its memory figure is for that pool. A
   plan says what the model was trained for (`trained`). Strata stays at
   its 32768; vLLM's form is unchanged.
+- **Deleted model files came back after a control plane restart.** An agent
+  registers with the files its startup scan found, and sends the list again
+  only when it changes; a file deleted after the agent started was listed
+  again by a control plane that restarted, until the next change. A new
+  stream now gets the list on its first heartbeat.
 - **`ctl weights` offered models in use for deletion.** A model of several
   files (a set, its address ending in `/`) is fetched into a directory named
   from the address without the slash; the sweep named it from the address
diff --git a/internal/agent/agent.go b/internal/agent/agent.go
index 9eef9b7..63b8241 100644
--- a/internal/agent/agent.go
+++ b/internal/agent/agent.go
@@ -530,6 +530,18 @@ func (a *Agent) scan(ctx context.Context) error {
 	return err
 }
 
+// forgetSent is a new stream: a control plane that knows nothing of where
+// installs stand, nor which files are here beyond what registration says —
+// and registration says what the startup scan found. So the next heartbeat
+// tells it both again. Without it, files deleted after the agent started came
+// back on a control plane that restarted, and stayed until the next change.
+func (a *Agent) forgetSent() {
+	a.mu.Lock()
+	defer a.mu.Unlock()
+	a.provSent = ""
+	a.lastWeights = ""
+}
+
 // session runs one connection until it breaks.
 func (a *Agent) session(ctx context.Context, server string) error {
 	client := llmgwv1connect.NewAgentServiceClient(a.http, server)
@@ -570,10 +582,8 @@ func (a *Agent) session(ctx context.Context, server string) error {
 	reg.RunningShards = a.runningShards()
 	a.mu.Lock()
 	h := a.prov.Host
-	// A new stream is a control plane that knows nothing of where installs
-	// stand, so the next heartbeat tells it again.
-	a.provSent = ""
 	a.mu.Unlock()
+	a.forgetSent()
 	reg.Host = &llmgwv1.Host{
 		OsId: h.OSID, OsVersion: h.OSVersion, OsCodename: h.OSCodename,
 		Arch: h.Arch, CpuFlags: h.CPUFlags, NvidiaDriver: h.NVIDIADriver,
diff --git a/internal/agent/agent_test.go b/internal/agent/agent_test.go
index c7ff2b6..41dcee8 100644
--- a/internal/agent/agent_test.go
+++ b/internal/agent/agent_test.go
@@ -925,3 +925,23 @@ func TestABandwidthTestIsRunOnTheAdapterAskedFor(t *testing.T) {
 		t.Errorf("reply %+v, ran %+v", r, got)
 	}
 }
+
+func TestANewStreamIsToldTheFilesAgain(t *testing.T) {
+	// Registration carries what the startup scan found; a file deleted since
+	// came back on a control plane that restarted, because the next
+	// heartbeat saw the list unchanged since it was last sent.
+	dir := t.TempDir()
+	h := start(t, func(c *Config) { c.ModelDirs = []string{dir} })
+	if err := os.WriteFile(filepath.Join(dir, "0123456789abcdef-m.gguf"), []byte("x"), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	h.ag.heartbeat()
+	if hb := h.ag.heartbeat().GetHeartbeat(); hb.GetWeightsChanged() {
+		t.Fatal("an unchanged list should not be sent again on the same stream")
+	}
+	h.ag.forgetSent()
+	hb := h.ag.heartbeat().GetHeartbeat()
+	if !hb.GetWeightsChanged() || len(hb.GetWeights()) != 1 {
+		t.Errorf("a new stream should be told the files: changed=%v %v", hb.GetWeightsChanged(), hb.GetWeights())
+	}
+}