Safe 409 handling: check workspace age/status before deleting

Instead of blindly deleting on 409 conflict, now checks:
- Stopped/failed → safe to delete and recreate
- Running but >30 min old → stale, delete and recreate
- Running and <30 min old → adopt existing workspace (mid-task)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/services/coder.ts

@@ -50,16 +50,36 @@ export class CoderClient {
       },
     );
 
-    // Handle 409 conflict — stale workspace from a previous orchestrator instance
+    // Handle 409 conflict — workspace with this name already exists.
+    // This happens when the orchestrator restarts and loses in-memory state.
+    // Only delete if the workspace is old (>30 min) or stopped/failed.
+    // If it's young and running, it may be mid-task — skip to avoid data loss.
     if (res.status === 409) {
-      console.log(`[coder] workspace "${name}" already exists — deleting stale workspace and retrying`);
       const existing = await this.findWorkspaceByName(name);
-      if (existing) {
+      if (!existing) {
-        await this.deleteWorkspace(existing.id);
+        throw new Error(`Coder 409 but workspace "${name}" not found — possible race condition`);
-        // Wait for deletion to propagate
-        await new Promise((resolve) => setTimeout(resolve, 5000));
       }
-      return this.createWorkspace(task);
+
+      const ageMs = Date.now() - new Date(existing.createdAt).getTime();
+      const ageMin = Math.round(ageMs / 60_000);
+      const stoppedStatuses = ["stopped", "failed", "canceled", "deleted"];
+      const isStopped = stoppedStatuses.includes(existing.latestBuildStatus);
+      const isStale = ageMin > 30;
+
+      if (isStopped || isStale) {
+        console.log(
+          `[coder] workspace "${name}" already exists (age: ${ageMin}m, status: ${existing.latestBuildStatus}) — deleting and retrying`,
+        );
+        await this.deleteWorkspace(existing.id);
+        await new Promise((resolve) => setTimeout(resolve, 5000));
+        return this.createWorkspace(task);
+      }
+
+      // Workspace is young and still running — don't kill it
+      console.log(
+        `[coder] workspace "${name}" is active (age: ${ageMin}m, status: ${existing.latestBuildStatus}) — skipping creation`,
+      );
+      return { id: existing.id, name: existing.name };
     }
 
     if (!res.ok) {
@@ -107,7 +127,12 @@ export class CoderClient {
     }
   }
 
-  async findWorkspaceByName(name: string): Promise<{ id: string } | null> {
+  async findWorkspaceByName(name: string): Promise<{
+    id: string;
+    name: string;
+    createdAt: string;
+    latestBuildStatus: string;
+  } | null> {
     const res = await fetch(
       `${this.baseUrl}/api/v2/workspaces?q=name:${encodeURIComponent(name)}`,
       {
@@ -119,8 +144,21 @@ export class CoderClient {
 
     if (!res.ok) return null;
 
-    const data = (await res.json()) as { workspaces: Array<{ id: string; name: string }> };
+    const data = (await res.json()) as {
+      workspaces: Array<{
+        id: string;
+        name: string;
+        created_at: string;
+        latest_build: { status: string };
+      }>;
+    };
     const match = data.workspaces?.find((w) => w.name === name);
-    return match ? { id: match.id } : null;
+    if (!match) return null;
+    return {
+      id: match.id,
+      name: match.name,
+      createdAt: match.created_at,
+      latestBuildStatus: match.latest_build?.status ?? "unknown",
+    };
   }
 }