Double-start guard: launching marker, probe-and-adopt, fresh-dir relaunch; skip unreachable terminals per tick

Before the launch call the planned run (run id, terminal, handle, bookkeeping) is saved as a launching
marker. If the launch call fails or agentd dies before recording the run, the next tick probes the run
directory (exit.txt / launch.pid / pid.txt): evidence -> adopt the run; nothing -> relaunch with the same
run id in <run_id>-r2 (-r3 ...); probe unreachable -> keep the marker, which holds the terminal slot.
Transports refuse to clean a run directory holding a pid file. A terminal whose relay fails is skipped
for the rest of the tick (heartbeat.down) while other terminals carry on.

tests/fakes.py

@@ -6,6 +6,7 @@ from agentd.config import Config
 from agentd.core import Agentd
 from agentd.executors import ExecResult
 from agentd.store import Store
+from agentd.transports import TransportError
 
 STATES = {"Backlog": "s-bl", "Todo": "s-todo", "In Progress": "s-run", "Waiting": "s-wait", "Review": "s-rev", "Done": "s-done"}
 MEMBERS = {"window10": "u-w10", "oregon": "u-or", "kappiee": "u-k"}
@@ -89,15 +90,39 @@ class FakeExecutor:
         self.resume = resume
         self.started, self.killed, self.done = [], [], {}
         self.fail_starts, self.fail_kills = 0, 0
+        self.lost_starts = 0           # the run launches but the relay reports a failure (e.g. timeout)
+        self.fail_probes = self.fail_polls = 0
+        self.dirs = {}                 # run_dir -> files on the "terminal"
+        self.polls = []
+
+    def handle(self, run):
+        return {"run_dir": "/runs/" + (run.dir_name or run.run_id), "run_id": run.run_id, "thread_id": run.thread_id}
 
     def start(self, run):
         if self.fail_starts:
             self.fail_starts -= 1
-            raise RuntimeError("relay down")
+            raise TransportError("relay down")
+        h = self.handle(run)
+        if "pid.txt" in self.dirs.get(h["run_dir"], ()):
+            raise TransportError("HASPID")
         self.started.append(run)
-        return {"run_dir": "/runs/" + run.run_id, "run_id": run.run_id, "thread_id": run.thread_id}
+        self.dirs[h["run_dir"]] = {"launch.pid", "pid.txt"}
+        if self.lost_starts:
+            self.lost_starts -= 1
+            raise TransportError("relay timeout after 150s")
+        return h
+
+    def probe(self, handle):
+        if self.fail_probes:
+            self.fail_probes -= 1
+            raise TransportError("relay down")
+        return sorted(self.dirs.get(handle["run_dir"], ()))
 
     def poll(self, handle):
+        self.polls.append(handle["run_id"])
+        if self.fail_polls:
+            self.fail_polls -= 1
+            raise TransportError("relay down")
         return "finished" if handle["run_id"] in self.done else "running"
 
     def collect(self, handle):