From acb394989603aa8a4280ee02d6a161d71371e55d Mon Sep 17 00:00:00 2001
From: Erich Blume <blume.erich@gmail.com>
Date: Tue, 2 Jun 2026 10:29:58 -0700
Subject: [PATCH] heph.nvim: regression test for the stale-socket wait_ready
 deadlock

Recreates a crash-left stale socket (spawn a managed daemon, SIGKILL it) and
asserts wait_ready returns promptly (a deadlock would freeze the suite) and that
a fresh autostart recovers. Verified it fails (suite hangs) against the buggy
nested-vim.wait version.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 heph.nvim/tests/e2e/managed_daemon_spec.lua | 40 +++++++++++++++++++++
 1 file changed, 40 insertions(+)

diff --git a/heph.nvim/tests/e2e/managed_daemon_spec.lua b/heph.nvim/tests/e2e/managed_daemon_spec.lua
index 4bd65e1..e170529 100644
--- a/heph.nvim/tests/e2e/managed_daemon_spec.lua
+++ b/heph.nvim/tests/e2e/managed_daemon_spec.lua
@@ -54,6 +54,46 @@ describe("managed daemon", function()
     assert.is_true(require("heph.daemon").is_managed())
   end)
 
+  it("does not deadlock on a stale socket left by a crash (regression)", function()
+    -- Bring up a managed daemon, then HARD-kill it so no cleanup runs — leaving
+    -- a stale socket file with no listener (the second-launch crash scenario:
+    -- wait_ready ran the rpc probe inside a vim.wait predicate, nesting vim.wait
+    -- and freezing Neovim).
+    require("heph").setup({
+      socket = t.sock,
+      db = t.db,
+      bin = h.hephd_bin(),
+      autostart = true,
+      keymaps = false,
+    })
+    require("heph.rpc").call("health", {})
+    local m = require("heph.daemon")._managed
+    m.handle:kill("sigkill")
+    vim.wait(2000, function()
+      return m.exited.done
+    end, 20)
+    assert.is_truthy(vim.uv.fs_stat(t.sock), "precondition: a stale socket is present")
+
+    -- Probing the stale socket must RETURN promptly (not deadlock). The fix
+    -- returns in ~200ms; the bug froze here indefinitely.
+    local start = vim.uv.hrtime()
+    local ready = require("heph.daemon").wait_ready(t.sock, 200)
+    local elapsed_ms = (vim.uv.hrtime() - start) / 1e6
+    assert.is_false(ready)
+    assert.is_true(elapsed_ms < 2000, "wait_ready took " .. math.floor(elapsed_ms) .. "ms — possible deadlock")
+
+    -- A fresh autostart recovers despite the stale socket still being there.
+    require("heph").setup({
+      socket = t.sock,
+      db = t.db,
+      bin = h.hephd_bin(),
+      autostart = true,
+      keymaps = false,
+    })
+    assert.is_truthy(require("heph.rpc").call("health", {}))
+    assert.is_true(require("heph.daemon").is_managed())
+  end)
+
   it("connect-only (autostart=false) errors when no daemon is running", function()
     require("heph").setup({
       socket = t.sock,