diff --git a/doc/test/features.txt b/doc/test/features.txt
index 00442e124..0ef9c8353 100644
--- a/doc/test/features.txt
+++ b/doc/test/features.txt
@@ -32,10 +32,6 @@ or class with a leading ``Test`` name is collected.
 
 .. _`collection process`: ext.html#collection-process
 
-Rapidly write integration, functional, unit tests 
-===================================================
-
-XXX 
 
 funcargs and xUnit style setups 
 ===================================================
@@ -95,17 +91,20 @@ debug with the ``print`` statement
 ----------------------------------
 
 By default, ``py.test`` catches text written to stdout/stderr during
-the execution of each individual test. This output will only be
+the execution of each individual test.  This output will only be
 displayed however if the test fails; you will not see it
 otherwise. This allows you to put debugging print statements in your
 code without being overwhelmed by all the output that might be
 generated by tests that do not fail.
 
 Each failing test that produced output during the running of the test
-will have its output displayed in the ``recorded stdout`` section.
+function will have its output displayed in the ``recorded stdout`` section.
+
+During Setup and Teardown ("Fixture") capturing is performed separately so 
+that you will only see this output if the actual fixture functions fail. 
 
 The catching of stdout/stderr output can be disabled using the 
-``--nocapture`` option to the ``py.test`` tool.  Any output will 
+``--nocapture`` or ``-s`` option to the ``py.test`` tool.  Any output will 
 in this case be displayed as soon as it is generated.
 
 test execution order
diff --git a/doc/test/plugins.txt b/doc/test/plugins.txt
index 468d20aba..a17954cf7 100644
--- a/doc/test/plugins.txt
+++ b/doc/test/plugins.txt
@@ -2,16 +2,17 @@
 hooks and plugins 
 ==========================
 
-py.test implements much of its functionality by calling so called
-**hooks**.  A hook is a function with a ``pytest_`` prefix and a list of
-named arguments.  Hook functions are usually defined in plugins. 
-A plugin is a module or package that makes hook functions available. 
+py.test implements much of its functionality by calling **hooks**.  
+A hook is a function with a ``pytest_`` prefixed name.  Hook functions
+are usually defined in plugins.  A plugin is a regular python module or 
+package that makes hook functions available. 
 
 When loading a plugin module (which needs to have a ``pytest_`` prefix as well) 
 py.test performs strict checking on the function signature.  Function 
 and argument names need to match exactly the `original definition of the hook`_.
 This allows for early mismatch reporting and minimizes version incompatibilites. 
 
+.. _`original definition of the hook`: http://bitbucket.org/hpk42/py-trunk/src/tip/py/test/plugin/api.py
 
 Loading plugins and specifying dependencies 
 ============================================
@@ -42,7 +43,13 @@ Included plugins
 ================
 
 You can find the source code of all default plugins in 
-http://bitbucket.org/hpk42/py-trunk/src/tip/py/test/plugin/
+
+    http://bitbucket.org/hpk42/py-trunk/src/tip/py/test/plugin/
+
+Additionally you can check out some more contributed plugins here
+
+    http://bitbucket.org/hpk42/py-trunk/src/tip/contrib/
+
 
 Overview on available hooks 
 ====================================
@@ -50,16 +57,54 @@ Overview on available hooks
 "runtest" hooks 
 -------------------
 
-A number of hooks allow interacting with the running of a test. 
-A test can be many things - for example a python, javascript
-or prolog test function or a doctest.  The following hooks are 
-usually invoked on running a test item:: 
+Each test item is usually executed by calling the following three hooks::
 
-    pytest_runtest_protocol(item) -> True # and invokes: 
-        pytest_runtest_setup(item) -> None
-        pytest_runtest_call(item) -> (excinfo, when, outerr) 
-        pytest_runtest_makereport(item, excinfo, when, outerr) -> report 
-        pytest_runtest_logreport(report) -> None
-        pytest_runtest_teardown(item) -> None
+    pytest_runtest_setup(item) 
+    pytest_runtest_call(item) 
+    pytest_runtest_teardown(item) 
 
+For each of the three invocations a `call object`_ encapsulates
+information about the outcome of the call and is subsequently used 
+to make a report object:: 
+
+    report = hook.pytest_runtest_makereport(item, call)
+
+For example, the `pytest_pdb plugin`_ uses this hook to activate
+interactive debugging on failures when ``--pdb`` is specified on the
+command line. 
+
+Usually three reports will be generated for a single test item.  However, 
+if the ``pytest_runtest_setup`` fails no call or teardown hooks 
+will be called and only one report will be created. 
+
+Each of the up to three reports is eventually fed to the logreport hook::
+
+    pytest_runtest_logreport(report) 
+
+A ``report`` object contains status and reporting information:: 
+
+    report.longrepr = string/lines/object to print 
+    report.when = "setup", "call" or "teardown" 
+    report.shortrepr = letter for progress-report 
+    report.passed = True or False
+    report.failed = True or False
+    report.skipped = True or False
+
+The `pytest_terminal plugin`_ uses this hook to print information
+about a test run. 
+    
+The protocol described here is implemented via this hook::
+ 
+    pytest_runtest_protocol(item) -> True 
+
+.. _`call object`: 
+
+The call object contains information about a performed call::
+
+    call.excinfo = ExceptionInfo object or None 
+    call.when = "setup", "call" or "teardown" 
+    call.outerr = None or tuple of strings representing captured stdout/stderr 
+
+.. _`pytest_pdb plugin`: http://bitbucket.org/hpk42/py-trunk/src/tip/py/test/plugin/pytest_pdb.py
+.. _`pytest_terminal plugin`: http://bitbucket.org/hpk42/py-trunk/src/tip/py/test/plugin/pytest_terminal.py
 
diff --git a/py/test/dist/dsession.py b/py/test/dist/dsession.py
index ac27654ef..0f673f368 100644
--- a/py/test/dist/dsession.py
+++ b/py/test/dist/dsession.py
@@ -238,9 +238,9 @@ class DSession(Session):
         self.node2pending[node].remove(item)
 
     def handle_crashitem(self, item, node):
-        longrepr = "!!! Node %r crashed during running of test %r" %(node, item)
-        rep = item.config.hook.pytest_runtest_makereport(
-            item=item, when="???", excinfo=longrepr, outerr=None)
+        runner = item.config.pluginmanager.getplugin("runner") 
+        info = "!!! Node %r crashed during running of test %r" %(node, item)
+        rep = runner.ItemTestReport(item=item, excinfo=info, when="???")
         rep.node = node
         self.config.hook.pytest_runtest_logreport(rep=rep)
 
diff --git a/py/test/dist/testing/test_dsession.py b/py/test/dist/testing/test_dsession.py
index 18b8ae7c4..3a44cb651 100644
--- a/py/test/dist/testing/test_dsession.py
+++ b/py/test/dist/testing/test_dsession.py
@@ -5,8 +5,9 @@ import py
 XSpec = py.execnet.XSpec
 
 def run(item, node, excinfo=None):
-    rep = item.config.hook.pytest_runtest_makereport(
-            item=item, excinfo=excinfo, when="call", outerr=("", ""))
+    runner = item.config.pluginmanager.getplugin("runner")
+    rep = runner.ItemTestReport(item=item, 
+        excinfo=excinfo, when="call", outerr=("", ""))
     rep.node = node
     return rep 
 
diff --git a/py/test/plugin/api.py b/py/test/plugin/api.py
index c96ad55e2..9f71b0ac6 100644
--- a/py/test/plugin/api.py
+++ b/py/test/plugin/api.py
@@ -72,18 +72,14 @@ class PluginHooks:
     # runtest related hooks 
     # ------------------------------------------------------------------------------
     def pytest_runtest_setup(self, item):
-        """ called before pytest_runtest(). """ 
-
-    def pytest_runtest_teardown(self, item):
-        """ called after pytest_runtest_call. """ 
+        """ called before pytest_runtest_call(). """ 
 
     def pytest_runtest_call(self, item):
-        """ called after pytest_runtest_call. """ 
+        """ execute test item. """ 
+
+    def pytest_runtest_teardown(self, item):
+        """ called after pytest_runtest_call(). """ 
 
-    def pytest_runtest_makereport(self, item, excinfo, when, outerr):
-        """ make ItemTestReport for the specified test outcome. """
-    pytest_runtest_makereport.firstresult = True
-    
     def pytest_runtest_protocol(self, item):
         """ run given test item and return test report. """ 
     pytest_runtest_protocol.firstresult = True
@@ -92,6 +88,9 @@ class PluginHooks:
         """ return True if we consumed/did the call to the python function item. """
     pytest_pyfunc_call.firstresult = True
 
+    def pytest_runtest_makereport(self, item, call):
+        """ make ItemTestReport for the specified test outcome. """
+    pytest_runtest_makereport.firstresult = True
 
     def pytest_runtest_logreport(self, rep):
         """ process item test report. """ 
diff --git a/py/test/plugin/pytest_default.py b/py/test/plugin/pytest_default.py
index 2bbe6f871..8be551096 100644
--- a/py/test/plugin/pytest_default.py
+++ b/py/test/plugin/pytest_default.py
@@ -2,8 +2,9 @@
 
 import py
 
-def pytest_pyfunc_call(pyfuncitem, args, kwargs):
-    pyfuncitem.obj(*args, **kwargs)
+def pytest_pyfunc_call(__call__, pyfuncitem, args, kwargs):
+    if not __call__.execute(firstresult=True):
+        pyfuncitem.obj(*args, **kwargs)
 
 def pytest_collect_file(path, parent):
     ext = path.ext 
diff --git a/py/test/plugin/pytest_iocapture.py b/py/test/plugin/pytest_iocapture.py
index dd111496c..c723bf092 100644
--- a/py/test/plugin/pytest_iocapture.py
+++ b/py/test/plugin/pytest_iocapture.py
@@ -22,16 +22,24 @@ def pytest_funcarg__capfd(request):
     request.addfinalizer(capture.finalize)
     return capture 
 
+def pytest_pyfunc_call(pyfuncitem, args, kwargs):
+    for funcarg, value in kwargs.items():
+        if funcarg == "capsys" or funcarg == "capfd":
+            value.reset()
+
 class Capture:
+    _capture = None
     def __init__(self, captureclass):
         self._captureclass = captureclass
-        self._capture = self._captureclass()
 
     def finalize(self):
-        self._capture.reset()
+        if self._capture:
+            self._capture.reset()
 
     def reset(self):
-        res = self._capture.reset()
+        res = None
+        if self._capture:
+            res = self._capture.reset()
         self._capture = self._captureclass()
         return res 
 
diff --git a/py/test/plugin/pytest_pdb.py b/py/test/plugin/pytest_pdb.py
index be7fc674e..e49ba7fd0 100644
--- a/py/test/plugin/pytest_pdb.py
+++ b/py/test/plugin/pytest_pdb.py
@@ -22,12 +22,12 @@ def pytest_configure(config):
         config.pluginmanager.register(PdbInvoke())
 
 class PdbInvoke:
-    def pytest_runtest_makereport(self, item, excinfo, when, outerr):
-        if excinfo and not excinfo.errisinstance(Skipped): 
+    def pytest_runtest_makereport(self, item, call):
+        if call.excinfo and not call.excinfo.errisinstance(Skipped): 
             tw = py.io.TerminalWriter()
-            repr = excinfo.getrepr()
+            repr = call.excinfo.getrepr()
             repr.toterminal(tw) 
-            post_mortem(excinfo._excinfo[2])
+            post_mortem(call.excinfo._excinfo[2])
 
 class Pdb(py.std.pdb.Pdb):
     def do_list(self, arg):
diff --git a/py/test/plugin/pytest_pytester.py b/py/test/plugin/pytest_pytester.py
index dd867cdd4..e7010843f 100644
--- a/py/test/plugin/pytest_pytester.py
+++ b/py/test/plugin/pytest_pytester.py
@@ -269,8 +269,12 @@ class TmpTestdir:
         p1 = py.path.local("stdout")
         p2 = py.path.local("stderr")
         print "running", cmdargs, "curdir=", py.path.local()
-        popen = self.popen(cmdargs, stdout=p1.open("w"), stderr=p2.open("w"))
+        f1 = p1.open("w")
+        f2 = p2.open("w")
+        popen = self.popen(cmdargs, stdout=f1, stderr=f2, close_fds=True)
         ret = popen.wait()
+        f1.close()
+        f2.close()
         out, err = p1.readlines(cr=0), p2.readlines(cr=0)
         if err:
             for line in err: 
@@ -356,7 +360,8 @@ class ReportRecorder(object):
         failed = []
         for rep in self.getreports("pytest_runtest_logreport"):
             if rep.passed: 
-                passed.append(rep) 
+                if rep.when == "call": 
+                    passed.append(rep) 
             elif rep.skipped: 
                 skipped.append(rep) 
             elif rep.failed:
@@ -384,19 +389,25 @@ def test_reportrecorder(testdir):
     recorder = testdir.getreportrecorder(registry)
     assert not recorder.getfailures()
     item = testdir.getitem("def test_func(): pass")
-    rep = item.config.hook.pytest_runtest_makereport(
-        item=item, excinfo=None, when="call", outerr=None)
+    class rep:
+        excinfo = None
+        passed = False
+        failed = True 
+        skipped = False
+        when = "call" 
 
-    rep.passed = False
-    rep.failed = True
     recorder.hook.pytest_runtest_logreport(rep=rep)
     failures = recorder.getfailures()
     assert failures == [rep]
     failures = recorder.getfailures()
     assert failures == [rep]
 
-    rep = item.config.hook.pytest_runtest_makereport(
-        item=item, excinfo=None, when="call", outerr=None)
+    class rep:
+        excinfo = None
+        passed = False
+        failed = False
+        skipped = True
+        when = "call" 
     rep.passed = False
     rep.skipped = True
     recorder.hook.pytest_runtest_logreport(rep=rep)
diff --git a/py/test/plugin/pytest_runner.py b/py/test/plugin/pytest_runner.py
index 81746b98c..f6c31337a 100644
--- a/py/test/plugin/pytest_runner.py
+++ b/py/test/plugin/pytest_runner.py
@@ -12,7 +12,6 @@ from py.__.test.outcome import Skipped
 
 #
 # pytest plugin hooks 
-#
 
 def pytest_addoption(parser):
     group = parser.getgroup("general") 
@@ -38,13 +37,22 @@ def pytest_make_collect_report(collector):
     return report 
 
 def pytest_runtest_protocol(item):
-    if item.config.option.boxed:
-        report = forked_run_report(item)
+    if item.config.getvalue("boxed"):
+        reports = forked_run_report(item) 
+        for rep in reports:
+            item.config.hook.pytest_runtest_logreport(rep=rep)
     else:
-        report = basic_run_report(item) 
-    item.config.hook.pytest_runtest_logreport(rep=report)
+        runtestprotocol(item)
     return True
 
+def runtestprotocol(item, log=True):
+    rep = call_and_report(item, "setup", log)
+    reports = [rep]
+    if rep.passed:
+        reports.append(call_and_report(item, "call", log))
+        reports.append(call_and_report(item, "teardown", log))
+    return reports
+
 def pytest_runtest_setup(item):
     item.config._setupstate.prepare(item)
 
@@ -52,44 +60,45 @@ def pytest_runtest_call(item):
     if not item._deprecated_testexecution():
         item.runtest()
 
-def pytest_runtest_makereport(item, excinfo, when, outerr):
-    return ItemTestReport(item, excinfo, when, outerr)
+def pytest_runtest_makereport(item, call):
+    if isinstance(call, str):
+        # crashed item 
+        return ItemTestReport(item, excinfo=call, when="???")
+    else:
+        return ItemTestReport(item, call.excinfo, call.when, call.outerr)
 
 def pytest_runtest_teardown(item):
     item.config._setupstate.teardown_exact(item)
 
 #
 # Implementation
-#
 
-class Call:
-    excinfo = None 
-    def __init__(self, when, func):
-        self.when = when 
-        try:
-            self.result = func()
-        except KeyboardInterrupt:
-            raise
-        except:
-            self.excinfo = py.code.ExceptionInfo()
-
-
-def basic_run_report(item):
-    """ return report about setting up and running a test item. """
-    capture = item.config._getcapture()
+def call_and_report(item, when, log=True):
+    call = RuntestHookCall(item, when)
     hook = item.config.hook
-    try:
-        call = Call("setup", lambda: hook.pytest_runtest_setup(item=item))
-        if not call.excinfo:
-            call = Call("call", lambda: hook.pytest_runtest_call(item=item))
-            # in case of an error we defer teardown to not shadow the error
-            if not call.excinfo:
-                call = Call("teardown", lambda: hook.pytest_runtest_teardown(item=item))
-    finally:
-        outerr = capture.reset()
-    return item.config.hook.pytest_runtest_makereport(
-            item=item, excinfo=call.excinfo, 
-            when=call.when, outerr=outerr)
+    report = hook.pytest_runtest_makereport(item=item, call=call)
+    if log and (when == "call" or not report.passed):
+        hook.pytest_runtest_logreport(rep=report) 
+    return report
+
+
+class RuntestHookCall:
+    excinfo = None 
+    _prefix = "pytest_runtest_"
+    def __init__(self, item, when):
+        self.when = when 
+        hookname = self._prefix + when 
+        hook = getattr(item.config.hook, hookname)
+        capture = item.config._getcapture()
+        try:
+            try:
+                self.result = hook(item=item)
+            except KeyboardInterrupt:
+                raise
+            except:
+                self.excinfo = py.code.ExceptionInfo()
+        finally:
+            self.outerr = capture.reset()
 
 def forked_run_report(item):
     EXITSTATUS_TESTEXIT = 4
@@ -98,10 +107,10 @@ def forked_run_report(item):
     ipickle.selfmemoize(item.config)
     def runforked():
         try:
-            testrep = basic_run_report(item)
+            reports = runtestprotocol(item, log=False)
         except KeyboardInterrupt: 
             py.std.os._exit(EXITSTATUS_TESTEXIT)
-        return ipickle.dumps(testrep)
+        return ipickle.dumps(reports)
 
     ff = py.process.ForkedFunc(runforked)
     result = ff.waitfinish()
@@ -110,15 +119,13 @@ def forked_run_report(item):
     else:
         if result.exitstatus == EXITSTATUS_TESTEXIT:
             py.test.exit("forked test item %s raised Exit" %(item,))
-        return report_process_crash(item, result)
+        return [report_process_crash(item, result)]
 
 def report_process_crash(item, result):
     path, lineno = item._getfslineno()
-    longrepr = [
-        ("X", "CRASHED"), 
-        ("%s:%s: CRASHED with signal %d" %(path, lineno, result.signal)),
-    ]
-    return ItemTestReport(item, excinfo=longrepr, when="???")
+    info = "%s:%s: running the test CRASHED with signal %d" %(
+            path, lineno, result.signal)
+    return ItemTestReport(item, excinfo=info, when="???")
 
 class BaseReport(object):
     def __repr__(self):
@@ -138,6 +145,8 @@ class ItemTestReport(BaseReport):
 
     def __init__(self, item, excinfo=None, when=None, outerr=None):
         self.item = item 
+        self.when = when
+        self.outerr = outerr
         if item and when != "setup":
             self.keywords = item.readkeywords() 
         else:
@@ -151,7 +160,6 @@ class ItemTestReport(BaseReport):
             self.passed = True
             self.shortrepr = "." 
         else:
-            self.when = when 
             if not isinstance(excinfo, py.code.ExceptionInfo):
                 self.failed = True
                 shortrepr = "?"
diff --git a/py/test/plugin/pytest_terminal.py b/py/test/plugin/pytest_terminal.py
index e6c48b543..1098b3095 100644
--- a/py/test/plugin/pytest_terminal.py
+++ b/py/test/plugin/pytest_terminal.py
@@ -162,6 +162,8 @@ class TerminalReporter:
                 self.write_fspath_result(fspath, "")
 
     def pytest_runtest_logreport(self, rep):
+        if rep.passed and rep.when in ("setup", "teardown"):
+            return 
         fspath = rep.item.fspath 
         cat, letter, word = self.getcategoryletterword(rep)
         if isinstance(word, tuple):
@@ -399,6 +401,9 @@ def repr_pythonversion(v=None):
 
 import pytest_runner as runner # XXX 
 
+def basic_run_report(item):
+    return runner.call_and_report(item, "call", log=False)
+
 class TestTerminal:
     def test_pass_skip_fail(self, testdir, linecomp):
         modcol = testdir.getmodulecol("""
@@ -415,7 +420,7 @@ class TestTerminal:
         rep.config.hook.pytest_sessionstart(session=testdir.session)
 
         for item in testdir.genitems([modcol]):
-            ev = runner.basic_run_report(item) 
+            ev = basic_run_report(item) 
             rep.config.hook.pytest_runtest_logreport(rep=ev)
         linecomp.assert_contains_lines([
                 "*test_pass_skip_fail.py .sF"
@@ -446,7 +451,7 @@ class TestTerminal:
             rep.config.hook.pytest_itemstart(item=item, node=None)
             s = linecomp.stringio.getvalue().strip()
             assert s.endswith(item.name)
-            rep.config.hook.pytest_runtest_logreport(rep=runner.basic_run_report(item))
+            rep.config.hook.pytest_runtest_logreport(rep=basic_run_report(item))
 
         linecomp.assert_contains_lines([
             "*test_pass_skip_fail_verbose.py:2: *test_ok*PASS*",
@@ -537,7 +542,7 @@ class TestTerminal:
                 raise ValueError()
         """)
         rep = TerminalReporter(modcol.config, file=linecomp.stringio)
-        reports = [runner.basic_run_report(x) for x in modcol.collect()]
+        reports = [basic_run_report(x) for x in modcol.collect()]
         rep.pytest_looponfailinfo(reports, [modcol.config.topdir])
         linecomp.assert_contains_lines([
             "*test_looponfailreport.py:2: assert 0",
@@ -563,7 +568,7 @@ class TestTerminal:
             rep.config.hook.pytest_sessionstart(session=testdir.session)
             for item in testdir.genitems([modcol]):
                 rep.config.hook.pytest_runtest_logreport(
-                    rep=runner.basic_run_report(item))
+                    rep=basic_run_report(item))
             rep.config.hook.pytest_sessionfinish(session=testdir.session, exitstatus=1)
             s = linecomp.stringio.getvalue()
             if tbopt == "long":
@@ -644,7 +649,7 @@ class TestTerminal:
         try:
             for item in testdir.genitems([modcol]):
                 modcol.config.hook.pytest_runtest_logreport(
-                    rep=runner.basic_run_report(item))
+                    rep=basic_run_report(item))
         except KeyboardInterrupt:
             excinfo = py.code.ExceptionInfo()
         else:
diff --git a/py/test/plugin/pytest_xfail.py b/py/test/plugin/pytest_xfail.py
index bda70c20e..0663580b3 100644
--- a/py/test/plugin/pytest_xfail.py
+++ b/py/test/plugin/pytest_xfail.py
@@ -10,11 +10,13 @@ example:
 """
 import py
 
-def pytest_runtest_makereport(__call__, item, excinfo, when, outerr):
+def pytest_runtest_makereport(__call__, item, call):
+    if call.when != "call":
+        return
     if hasattr(item, 'obj') and hasattr(item.obj, 'func_dict'):
         if 'xfail' in item.obj.func_dict:
             res = __call__.execute(firstresult=True)
-            if excinfo:
+            if call.excinfo:
                 res.skipped = True
                 res.failed = res.passed = False
             else:
diff --git a/py/test/plugin/test_pytest_runner.py b/py/test/plugin/test_pytest_runner.py
index 4bb0a6680..479a4ca65 100644
--- a/py/test/plugin/test_pytest_runner.py
+++ b/py/test/plugin/test_pytest_runner.py
@@ -30,29 +30,32 @@ class TestSetupState:
 
 class BaseFunctionalTests:
     def test_funcattr(self, testdir):
-        rep = testdir.runitem("""
+        reports = testdir.runitem("""
             import py
             @py.test.mark(xfail="needs refactoring")
             def test_func():
                 raise Exit()
         """)
+        rep = reports[1]
         assert rep.keywords['xfail'] == "needs refactoring" 
 
     def test_passfunction(self, testdir):
-        rep = testdir.runitem("""
+        reports = testdir.runitem("""
             def test_func():
                 pass
         """)
+        rep = reports[1]
         assert rep.passed 
         assert not rep.failed
         assert rep.shortrepr == "."
         assert not hasattr(rep, 'longrepr')
                 
     def test_failfunction(self, testdir):
-        rep = testdir.runitem("""
+        reports = testdir.runitem("""
             def test_func():
                 assert 0
         """)
+        rep = reports[1]
         assert not rep.passed 
         assert not rep.skipped 
         assert rep.failed 
@@ -61,11 +64,12 @@ class BaseFunctionalTests:
         assert str(rep.shortrepr) == "F"
 
     def test_skipfunction(self, testdir):
-        rep = testdir.runitem("""
+        reports = testdir.runitem("""
             import py
             def test_func():
                 py.test.skip("hello")
         """)
+        rep = reports[1]
         assert not rep.failed 
         assert not rep.passed 
         assert rep.skipped 
@@ -77,44 +81,49 @@ class BaseFunctionalTests:
         #assert not rep.skipped.failurerepr 
 
     def test_skip_in_setup_function(self, testdir):
-        rep = testdir.runitem("""
+        reports = testdir.runitem("""
             import py
             def setup_function(func):
                 py.test.skip("hello")
             def test_func():
                 pass
         """)
-        print rep
+        print reports
+        rep = reports[0]
         assert not rep.failed 
         assert not rep.passed 
         assert rep.skipped 
         #assert rep.skipped.reason == "hello"
         #assert rep.skipped.location.lineno == 3
         #assert rep.skipped.location.lineno == 3
+        assert len(reports) == 1
 
     def test_failure_in_setup_function(self, testdir):
-        rep = testdir.runitem("""
+        reports = testdir.runitem("""
             import py
             def setup_function(func):
                 raise ValueError(42)
             def test_func():
                 pass
         """)
-        print rep
+        rep = reports[0]
         assert not rep.skipped 
         assert not rep.passed 
         assert rep.failed 
         assert rep.when == "setup"
+        assert len(reports) == 1
 
     def test_failure_in_teardown_function(self, testdir):
-        rep = testdir.runitem("""
+        reports = testdir.runitem("""
             import py
             def teardown_function(func):
                 raise ValueError(42)
             def test_func():
                 pass
         """)
-        print rep
+        print reports
+        assert len(reports) == 3
+        rep = reports[2]
         assert not rep.skipped 
         assert not rep.passed 
         assert rep.failed 
@@ -129,11 +138,12 @@ class BaseFunctionalTests:
                 def repr_failure(self, excinfo, outerr):
                     return "hello" 
         """)
-        rep = testdir.runitem("""
+        reports = testdir.runitem("""
             import py
             def test_func():
                 assert 0
         """)
+        rep = reports[1]
         assert not rep.skipped 
         assert not rep.passed 
         assert rep.failed 
@@ -149,13 +159,15 @@ class BaseFunctionalTests:
                 def repr_failure(self, excinfo):
                     assert 0
         """)
-        rep = testdir.runitem("""
+        reports = testdir.runitem("""
             import py
             def setup_function(func):
                 raise ValueError(42)
             def test_func():
                 pass
         """)
+        assert len(reports) == 1
+        rep = reports[0]
         print rep
         assert not rep.skipped 
         assert not rep.passed 
@@ -166,29 +178,29 @@ class BaseFunctionalTests:
         #assert instanace(rep.failed.failurerepr, PythonFailureRepr)
 
     def test_capture_in_func(self, testdir):
-        rep = testdir.runitem("""
-            import py
+        reports = testdir.runitem("""
+            import sys
             def setup_function(func):
-                print >>py.std.sys.stderr, "in setup"
+                print "in setup"
             def test_func():
                 print "in function"
                 assert 0
-            def teardown_func(func):
+            def teardown_function(func):
                 print "in teardown"
         """)
-        assert rep.failed 
-        # out, err = rep.failed.outerr
-        # assert out == ['in function\nin teardown\n']
-        # assert err == ['in setup\n']
+        assert reports[0].outerr[0] == "in setup\n"
+        assert reports[1].outerr[0] == "in function\n"
+        assert reports[2].outerr[0] == "in teardown\n"
         
     def test_systemexit_does_not_bail_out(self, testdir):
         try:
-            rep = testdir.runitem("""
+            reports = testdir.runitem("""
                 def test_func():
                     raise SystemExit(42)
             """)
         except SystemExit:
             py.test.fail("runner did not catch SystemExit")
+        rep = reports[1]
         assert rep.failed
         assert rep.when == "call"
 
@@ -208,7 +220,9 @@ class BaseFunctionalTests:
 
 class TestExecutionNonForked(BaseFunctionalTests):
     def getrunner(self):
-        return runner.basic_run_report 
+        def f(item):
+            return runner.runtestprotocol(item, log=False)
+        return f
 
     def test_keyboardinterrupt_propagates(self, testdir):
         from py.__.test.outcome import Exit
@@ -229,11 +243,12 @@ class TestExecutionForked(BaseFunctionalTests):
         return runner.forked_run_report
 
     def test_suicide(self, testdir):
-        rep = testdir.runitem("""
+        reports = testdir.runitem("""
             def test_func():
                 import os
                 os.kill(os.getpid(), 15)
         """)
+        rep = reports[0]
         assert rep.failed
         assert rep.when == "???"
 
@@ -265,3 +280,18 @@ class TestCollectionReports:
         assert not rep.failed 
         assert not rep.passed 
         assert rep.skipped 
+
+
+def test_functional_boxed(testdir):
+    if not hasattr(py.std.os, 'fork'):
+        py.test.skip("needs os.fork")
+    p1 = testdir.makepyfile("""
+        import os
+        def test_function():
+            os.kill(os.getpid(), 15)
+    """)
+    result = testdir.runpytest(p1, "--boxed")
+    assert result.stdout.fnmatch_lines([
+        "*CRASHED*",
+        "*1 failed*"
+    ])