Merge pull request #101 from SparshGarg999/fix/46-windows-support-codex

feat(codex): add Windows support and compatibility for Codex plugin
2026-07-16 18:57:15 +09:00
parent 57333f3406 7c7fdfcd6c
commit 0d8839778c
12 changed files with 892 additions and 45 deletions
@@ -9,7 +9,7 @@ def test_resolve_alfworld_gamefile_uses_alfworld_data_for_relative_paths(monkeyp

    resolved = _resolve_alfworld_gamefile("json_2.1.1/valid_seen/task/game.tw-pddl")

-    assert resolved == os.path.join(str(data_root), "json_2.1.1/valid_seen/task/game.tw-pddl")
+    assert resolved == os.path.normpath(os.path.join(str(data_root), "json_2.1.1/valid_seen/task/game.tw-pddl"))


 def test_resolve_alfworld_gamefile_keeps_absolute_paths(monkeypatch, tmp_path):
@@ -31,6 +31,7 @@ def _run(script, args, env, cwd):
    return proc.returncode, proc.stdout, proc.stderr


+@unittest.skipIf(sys.platform == "win32", "Unix bash runner tests require POSIX/bash environment")
 class TestRunnerSourceCheckout(unittest.TestCase):
    """When skillopt_sleep/ is found in the repo, the source-checkout path is used."""

@@ -46,6 +47,7 @@ class TestRunnerSourceCheckout(unittest.TestCase):
        self.assertIn("status", out)


+@unittest.skipIf(sys.platform == "win32", "Unix bash runner tests require POSIX/bash environment")
 class TestRunnerCliFallback(unittest.TestCase):
    """When no source dir is found, fall back to the skillopt-sleep CLI on PATH."""

@@ -101,6 +103,7 @@ class TestRunnerCliFallback(unittest.TestCase):
        self.assertIn("fake-cli invoked: status", out)


+@unittest.skipIf(sys.platform == "win32", "Unix bash runner tests require POSIX/bash environment")
 class TestRunnerNoEngine(unittest.TestCase):
    """When no source dir, no CLI on PATH, and no importable package, error cleanly."""

@@ -0,0 +1,295 @@
+Describe "run-sleep.ps1 runner" {
+    BeforeAll {
+        $script = Join-Path $PSScriptRoot "..\plugins\run-sleep.ps1"
+        $tempDir = [System.IO.Path]::GetTempFileName()
+        Remove-Item $tempDir
+        New-Item -ItemType Directory -Path $tempDir | Out-Null
+
+        # Detect a working python to bypass Windows Store alias issues
+        if (-not $env:SKILLOPT_SLEEP_PYTHON) {
+            if (Test-Path "C:\Python314\python.exe") {
+                $env:SKILLOPT_SLEEP_PYTHON = "C:\Python314\python.exe"
+            } elseif (Test-Path "C:\Python313\python.exe") {
+                $env:SKILLOPT_SLEEP_PYTHON = "C:\Python313\python.exe"
+            } elseif (Test-Path "C:\Python312\python.exe") {
+                $env:SKILLOPT_SLEEP_PYTHON = "C:\Python312\python.exe"
+            } elseif (Test-Path "C:\Python311\python.exe") {
+                $env:SKILLOPT_SLEEP_PYTHON = "C:\Python311\python.exe"
+            } elseif (Test-Path "C:\Python310\python.exe") {
+                $env:SKILLOPT_SLEEP_PYTHON = "C:\Python310\python.exe"
+            }
+        }
+    }
+
+    AfterAll {
+        if (Test-Path $tempDir) {
+            Remove-Item -Recurse -Force $tempDir
+        }
+    }
+
+    It "runs successfully in source checkout mode" {
+        $env:SKILLOPT_SLEEP_REPO = Resolve-Path (Join-Path $PSScriptRoot "..")
+        # Run help
+        $result = powershell -File $script "--help" 2>&1
+        $LASTEXITCODE | Should Be 0
+        $result | Out-String | Should Match "skillopt_sleep"
+    }
+
+    It "falls back to CLI on PATH" {
+        # Create a temp dir for isolated testing
+        $sandbox = Join-Path $tempDir "cli_fallback"
+        New-Item -ItemType Directory -Path $sandbox | Out-Null
+        $scriptCopy = Join-Path $sandbox "run-sleep.ps1"
+        Copy-Item $script $scriptCopy
+
+        # Create fake CLI
+        $binDir = Join-Path $sandbox "bin"
+        New-Item -ItemType Directory -Path $binDir | Out-Null
+        $fakeCli = Join-Path $binDir "skillopt-sleep.cmd"
+        "@echo off`r`necho fake-cli invoked %*`r`nexit /b 0" | Out-File -FilePath $fakeCli -Encoding ascii
+
+        # Save existing env vars
+        $oldPath = $env:PATH
+        $oldRepo = $env:SKILLOPT_SLEEP_REPO
+        $oldPlugin = $env:CLAUDE_PLUGIN_ROOT
+
+        $env:PATH = "$binDir;$oldPath"
+        $env:SKILLOPT_SLEEP_REPO = $null
+        $env:CLAUDE_PLUGIN_ROOT = $null
+
+        $oldLocation = Get-Location
+        Set-Location $sandbox
+        try {
+            $result = powershell -File $scriptCopy "status" 2>&1
+            $LASTEXITCODE | Should Be 0
+            $result | Out-String | Should Match "fake-cli invoked status"
+        }
+        finally {
+            Set-Location $oldLocation
+            $env:PATH = $oldPath
+            $env:SKILLOPT_SLEEP_REPO = $oldRepo
+            $env:CLAUDE_PLUGIN_ROOT = $oldPlugin
+        }
+    }
+
+    It "propagates exit code on failure" {
+        $env:SKILLOPT_SLEEP_REPO = Resolve-Path (Join-Path $PSScriptRoot "..")
+        # Run a non-existent command to trigger python module failure
+        $result = powershell -File $script "non-existent-subcommand" 2>&1
+        $LASTEXITCODE | Should Not Be 0
+    }
+
+    It "handles paths containing spaces correctly" {
+        # Create path containing spaces
+        $spaceDir = Join-Path $tempDir "path with spaces"
+        New-Item -ItemType Directory -Path $spaceDir | Out-Null
+        $scriptCopy = Join-Path $spaceDir "run-sleep.ps1"
+        Copy-Item $script $scriptCopy
+
+        # Create fake CLI
+        $binDir = Join-Path $spaceDir "bin"
+        New-Item -ItemType Directory -Path $binDir | Out-Null
+        $fakeCli = Join-Path $binDir "skillopt-sleep.cmd"
+        "@echo off`r`necho fake-cli invoked %*`r`nexit /b 0" | Out-File -FilePath $fakeCli -Encoding ascii
+
+        # Save env
+        $oldPath = $env:PATH
+        $oldRepo = $env:SKILLOPT_SLEEP_REPO
+        $oldPlugin = $env:CLAUDE_PLUGIN_ROOT
+
+        $env:PATH = "$binDir;$oldPath"
+        $env:SKILLOPT_SLEEP_REPO = $null
+        $env:CLAUDE_PLUGIN_ROOT = $null
+
+        $oldLocation = Get-Location
+        Set-Location $spaceDir
+        try {
+            $result = powershell -File $scriptCopy "status" 2>&1
+            $LASTEXITCODE | Should Be 0
+            $result | Out-String | Should Match "fake-cli invoked status"
+        }
+        finally {
+            Set-Location $oldLocation
+            $env:PATH = $oldPath
+            $env:SKILLOPT_SLEEP_REPO = $oldRepo
+            $env:CLAUDE_PLUGIN_ROOT = $oldPlugin
+        }
+    }
+}
+
+Describe "run-sleep.cmd runner" {
+    BeforeAll {
+        $script = Join-Path $PSScriptRoot "..\plugins\run-sleep.cmd"
+        $tempDir = [System.IO.Path]::GetTempFileName()
+        Remove-Item $tempDir
+        New-Item -ItemType Directory -Path $tempDir | Out-Null
+
+        # Detect a working python to bypass Windows Store alias issues
+        if (-not $env:SKILLOPT_SLEEP_PYTHON) {
+            if (Test-Path "C:\Python314\python.exe") {
+                $env:SKILLOPT_SLEEP_PYTHON = "C:\Python314\python.exe"
+            } elseif (Test-Path "C:\Python313\python.exe") {
+                $env:SKILLOPT_SLEEP_PYTHON = "C:\Python313\python.exe"
+            } elseif (Test-Path "C:\Python312\python.exe") {
+                $env:SKILLOPT_SLEEP_PYTHON = "C:\Python312\python.exe"
+            } elseif (Test-Path "C:\Python311\python.exe") {
+                $env:SKILLOPT_SLEEP_PYTHON = "C:\Python311\python.exe"
+            } elseif (Test-Path "C:\Python310\python.exe") {
+                $env:SKILLOPT_SLEEP_PYTHON = "C:\Python310\python.exe"
+            }
+        }
+    }
+
+    AfterAll {
+        if (Test-Path $tempDir) {
+            Remove-Item -Recurse -Force $tempDir
+        }
+    }
+
+    It "runs successfully in source checkout mode" {
+        $env:SKILLOPT_SLEEP_REPO = Resolve-Path (Join-Path $PSScriptRoot "..")
+        # Run help
+        $result = cmd.exe /c $script "--help" 2>&1
+        $LASTEXITCODE | Should Be 0
+        $result | Out-String | Should Match "skillopt_sleep"
+    }
+
+    It "falls back to CLI on PATH" {
+        # Create a temp dir for isolated testing
+        $sandbox = Join-Path $tempDir "cmd_cli_fallback"
+        New-Item -ItemType Directory -Path $sandbox | Out-Null
+        $scriptCopy = Join-Path $sandbox "run-sleep.cmd"
+        Copy-Item $script $scriptCopy
+
+        # Create fake CLI
+        $binDir = Join-Path $sandbox "bin"
+        New-Item -ItemType Directory -Path $binDir | Out-Null
+        $fakeCli = Join-Path $binDir "skillopt-sleep.cmd"
+        "@echo off`r`necho fake-cli invoked %*`r`nexit /b 0" | Out-File -FilePath $fakeCli -Encoding ascii
+
+        # Save existing env vars
+        $oldPath = $env:PATH
+        $oldRepo = $env:SKILLOPT_SLEEP_REPO
+        $oldPlugin = $env:CLAUDE_PLUGIN_ROOT
+
+        $env:PATH = "$binDir;$oldPath"
+        $env:SKILLOPT_SLEEP_REPO = $null
+        $env:CLAUDE_PLUGIN_ROOT = $null
+
+        $oldLocation = Get-Location
+        Set-Location $sandbox
+        try {
+            $result = cmd.exe /c $scriptCopy "status" 2>&1
+            $LASTEXITCODE | Should Be 0
+            $result | Out-String | Should Match "fake-cli invoked status"
+        }
+        finally {
+            Set-Location $oldLocation
+            $env:PATH = $oldPath
+            $env:SKILLOPT_SLEEP_REPO = $oldRepo
+            $env:CLAUDE_PLUGIN_ROOT = $oldPlugin
+        }
+    }
+
+    It "falls back to importable module" {
+        $sandbox = Join-Path $tempDir "cmd_module_fallback"
+        New-Item -ItemType Directory -Path $sandbox | Out-Null
+        $scriptCopy = Join-Path $sandbox "run-sleep.cmd"
+        Copy-Item $script $scriptCopy
+
+        $oldRepo = $env:SKILLOPT_SLEEP_REPO
+        $oldPlugin = $env:CLAUDE_PLUGIN_ROOT
+
+        $env:SKILLOPT_SLEEP_REPO = $null
+        $env:CLAUDE_PLUGIN_ROOT = $null
+
+        $oldPythonPath = $env:PYTHONPATH
+        $env:PYTHONPATH = Resolve-Path (Join-Path $PSScriptRoot "..")
+
+        $oldLocation = Get-Location
+        Set-Location $sandbox
+        try {
+            $result = cmd.exe /c $scriptCopy "--help" 2>&1
+            $LASTEXITCODE | Should Be 0
+            $result | Out-String | Should Match "skillopt_sleep"
+        }
+        finally {
+            Set-Location $oldLocation
+            $env:SKILLOPT_SLEEP_REPO = $oldRepo
+            $env:CLAUDE_PLUGIN_ROOT = $oldPlugin
+            $env:PYTHONPATH = $oldPythonPath
+        }
+    }
+
+    It "fails when nothing is found" {
+        $sandbox = Join-Path $tempDir "cmd_failure"
+        New-Item -ItemType Directory -Path $sandbox | Out-Null
+        $scriptCopy = Join-Path $sandbox "run-sleep.cmd"
+        Copy-Item $script $scriptCopy
+
+        $oldRepo = $env:SKILLOPT_SLEEP_REPO
+        $oldPlugin = $env:CLAUDE_PLUGIN_ROOT
+        $oldPath = $env:PATH
+
+        $env:SKILLOPT_SLEEP_REPO = $null
+        $env:CLAUDE_PLUGIN_ROOT = $null
+
+        $emptyBin = Join-Path $sandbox "empty_bin"
+        New-Item -ItemType Directory -Path $emptyBin | Out-Null
+        $env:PATH = $emptyBin
+
+        $oldLocation = Get-Location
+        Set-Location $sandbox
+        try {
+            $result = cmd.exe /c $scriptCopy "status" 2>&1
+            $LASTEXITCODE | Should Not Be 0
+            $result | Out-String | Should Match "could not locate the skillopt_sleep package"
+        }
+        finally {
+            Set-Location $oldLocation
+            $env:SKILLOPT_SLEEP_REPO = $oldRepo
+            $env:CLAUDE_PLUGIN_ROOT = $oldPlugin
+            $env:PATH = $oldPath
+        }
+    }
+
+    It "propagates exit code on failure" {
+        $env:SKILLOPT_SLEEP_REPO = Resolve-Path (Join-Path $PSScriptRoot "..")
+        $result = cmd.exe /c $script "non-existent-subcommand" 2>&1
+        $LASTEXITCODE | Should Not Be 0
+    }
+
+    It "handles paths containing spaces correctly" {
+        $spaceDir = Join-Path $tempDir "cmd path with spaces"
+        New-Item -ItemType Directory -Path $spaceDir | Out-Null
+        $scriptCopy = Join-Path $spaceDir "run-sleep.cmd"
+        Copy-Item $script $scriptCopy
+
+        $binDir = Join-Path $spaceDir "bin"
+        New-Item -ItemType Directory -Path $binDir | Out-Null
+        $fakeCli = Join-Path $binDir "skillopt-sleep.cmd"
+        "@echo off`r`necho fake-cli invoked %*`r`nexit /b 0" | Out-File -FilePath $fakeCli -Encoding ascii
+
+        $oldPath = $env:PATH
+        $oldRepo = $env:SKILLOPT_SLEEP_REPO
+        $oldPlugin = $env:CLAUDE_PLUGIN_ROOT
+
+        $env:PATH = "$binDir;$oldPath"
+        $env:SKILLOPT_SLEEP_REPO = $null
+        $env:CLAUDE_PLUGIN_ROOT = $null
+
+        $oldLocation = Get-Location
+        Set-Location $spaceDir
+        try {
+            $result = cmd.exe /c $scriptCopy "status" 2>&1
+            $LASTEXITCODE | Should Be 0
+            $result | Out-String | Should Match "fake-cli invoked status"
+        }
+        finally {
+            Set-Location $oldLocation
+            $env:PATH = $oldPath
+            $env:SKILLOPT_SLEEP_REPO = $oldRepo
+            $env:CLAUDE_PLUGIN_ROOT = $oldPlugin
+        }
+    }
+}
@@ -0,0 +1,77 @@
+import os
+import sys
+import unittest
+from unittest import mock
+
+class TestSchedulerWindows(unittest.TestCase):
+    @mock.patch("sys.platform", "win32")
+    @mock.patch("shutil.which", return_value="C:\\Windows\\System32\\schtasks.exe")
+    def test_schedule_windows(self, mock_which):
+        from skillopt_sleep.scheduler import schedule
+        
+        calls = []
+        def fake_run(cmd, **kwargs):
+            calls.append(cmd)
+            class Proc:
+                returncode = 0
+                stdout = "SUCCESS: The scheduled task ... has successfully been created."
+                stderr = ""
+            return Proc()
+            
+        mock_open = mock.mock_open()
+        with mock.patch("subprocess.run", side_effect=fake_run), \
+             mock.patch("os.makedirs") as mock_makedirs, \
+             mock.patch("builtins.open", mock_open):
+            ok, msg = schedule("/p/my project", backend="mock", hour=3, minute=17)
+            self.assertTrue(ok)
+            self.assertIn("via Windows Task Scheduler", msg)
+            self.assertEqual(len(calls), 1)
+            cmd = calls[0]
+            self.assertEqual(cmd[0], "schtasks")
+            self.assertEqual(cmd[1], "/create")
+            self.assertEqual(cmd[2], "/tn")
+            self.assertTrue(cmd[3].startswith("SkillOpt-Sleep-"))
+            self.assertIn("my_project", cmd[3])
+            self.assertEqual(cmd[4], "/tr")
+            self.assertIn("run.cmd", cmd[5])
+            self.assertEqual(cmd[6], "/sc")
+            self.assertEqual(cmd[7], "daily")
+            self.assertEqual(cmd[8], "/st")
+            self.assertEqual(cmd[9], "03:17")
+            self.assertEqual(cmd[10], "/f")
+
+            mock_makedirs.assert_called_once()
+            mock_open.assert_called_once()
+            # Verify the content written to the helper script
+            handle = mock_open()
+            written = "".join(call[0][0] for call in handle.write.call_args_list)
+            self.assertIn("@echo off", written)
+            self.assertIn("run --project", written)
+
+    @mock.patch("sys.platform", "win32")
+    @mock.patch("shutil.which", return_value="C:\\Windows\\System32\\schtasks.exe")
+    def test_unschedule_windows(self, mock_which):
+        from skillopt_sleep.scheduler import unschedule
+        
+        calls = []
+        def fake_run(cmd, **kwargs):
+            calls.append(cmd)
+            class Proc:
+                returncode = 0
+                stdout = "SUCCESS: The scheduled task ... was successfully deleted."
+                stderr = ""
+            return Proc()
+            
+        with mock.patch("subprocess.run", side_effect=fake_run), \
+             mock.patch("os.path.exists", return_value=True), \
+             mock.patch("os.remove") as mock_remove:
+            ok, msg = unschedule("/p/my project")
+            self.assertTrue(ok)
+            self.assertEqual(len(calls), 1)
+            cmd = calls[0]
+            self.assertEqual(cmd[0], "schtasks")
+            self.assertEqual(cmd[1], "/delete")
+            self.assertEqual(cmd[2], "/tn")
+            self.assertTrue(cmd[3].startswith("SkillOpt-Sleep-"))
+            self.assertEqual(cmd[4], "/f")
+            mock_remove.assert_called_once()
@@ -769,6 +769,60 @@ class TestCodexBackend(unittest.TestCase):
        self.assertIn("exited 1", be.last_call_error)  # failure surfaced for diagnostics
        self.assertEqual(called, [])                   # no tool actually ran

+    def test_codex_resolve_path_windows(self):
+        from skillopt_sleep.backend import resolve_codex_path
+        with mock.patch("sys.platform", "win32"), \
+             mock.patch("shutil.which", return_value=None), \
+             mock.patch.dict("os.environ", {
+                 "APPDATA": r"C:\Users\Sparsh\AppData\Roaming",
+                 "USERPROFILE": r"C:\Users\Sparsh",
+                 "NVM_HOME": r"C:\Users\Sparsh\nvm"
+             }), \
+             mock.patch("os.path.exists", return_value=True):
+            path = resolve_codex_path("")
+            self.assertEqual(path, r"C:\Users\Sparsh\AppData\Roaming\npm\codex.cmd")
+
+    def test_codex_attempt_with_tools_windows(self):
+        from skillopt_sleep.backend import CodexCliBackend
+        be = CodexCliBackend(codex_path="codex")
+        task = TaskRecord(id="t", project="/p", intent="answer the question",
+                          reference_kind="rule",
+                          judge={"checks": [{"op": "tool_called", "arg": "search"}]})
+        calls = []
+        def fake_run(cmd, **kwargs):
+            calls.append((cmd, kwargs))
+            class Proc:
+                returncode = 0
+                stdout = ""
+                stderr = ""
+            return Proc()
+
+        with mock.patch("os.name", "nt"), \
+             mock.patch("shutil.rmtree"), \
+             mock.patch("skillopt_sleep.backend.subprocess.run", side_effect=fake_run):
+            orig_mkdtemp = tempfile.mkdtemp
+            temp_dirs = []
+            def fake_mkdtemp(*args, **kwargs):
+                d = orig_mkdtemp(*args, **kwargs)
+                temp_dirs.append(d)
+                return d
+            with mock.patch("tempfile.mkdtemp", side_effect=fake_mkdtemp):
+                be.attempt_with_tools(task, "", "", ["search"])
+            
+            self.assertEqual(len(temp_dirs), 1)
+            work_dir = temp_dirs[0]
+            shim_path = os.path.join(work_dir, "search.cmd")
+            try:
+                self.assertTrue(os.path.exists(shim_path))
+                with open(shim_path, "r") as f:
+                    content = f.read()
+                self.assertIn("@echo off", content)
+                self.assertIn("%~n0", content)
+            finally:
+                import shutil
+                shutil.rmtree(work_dir, ignore_errors=True)
+
+

 class TestMultiRolloutAndBudget(unittest.TestCase):
    def test_rolloutset_stats(self):