diff --git a/doc/test/plugins.txt b/doc/test/plugins.txt
index a88106f19..468d20aba 100644
--- a/doc/test/plugins.txt
+++ b/doc/test/plugins.txt
@@ -1,39 +1,17 @@
 ==========================
-py.test plugins 
+hooks and plugins 
 ==========================
 
-Much of py.test's functionality is implemented as a plugin. 
+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. 
 
-Included plugins
-================
+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. 
 
-You can find the source code of all default plugins in 
-http://bitbucket.org/hpk42/py-trunk/src/tip/py/test/plugin/
-
-plugins that add reporting asepcts
------------------------------------
-
-pytest_terminal: default reporter for writing info to terminals 
-
-pytest_resultlog: log test results in machine-readable form to a file 
-
-plugins for adding new test types 
------------------------------------
-
-pytest_unittest: run traditional unittest TestCase instances
-
-pytest_doctest: run doctests in python modules or .txt files
-
-pytest_restdoc: provide RestructuredText syntax and link checking
-
-plugins for python test functions
------------------------------------
-
-pytest_xfail: provides "expected to fail" test marker 
-
-pytest_tmpdir: provide temporary directories to test functions 
-
-pytest_plugintester: generic plugin apichecks, support for functional plugin tests 
 
 Loading plugins and specifying dependencies 
 ============================================
@@ -46,26 +24,42 @@ py.test loads and configures plugins at tool startup:
 * by pre-scanning the command line for the ``-p name`` option
   and loading the specified plugin *before actual command line parsing*. 
 
-* by loading all plugins specified via a ``pytest_plugins``
-  variable in ``conftest.py`` files or test modules. 
+* by loading all plugins specified by the ``pytest_plugins``
+  variable in a ``conftest.py`` file or test modules. 
 
 Specifying a plugin in a test module or ``conftest.py`` will
 only lead to activitation when ``py.test`` actually sees the
-directory and the file during the collection process.  This is
+directory and the file during the collection process.  This happens 
 already after command line parsing and there is no try to do 
 a "pre-scan of all subdirs" as this would mean a potentially
 very large delay.  As long as you don't add command line 
 options this detail does not need to worry you. 
 
+A plugin module may specify its dependencies via 
+another ``pytest_plugins`` definition. 
 
-ensure a plugin is loaded 
------------------------------------
+Included plugins
+================
 
-If you create a ``conftest.py`` file with the following content:: 
+You can find the source code of all default plugins in 
+http://bitbucket.org/hpk42/py-trunk/src/tip/py/test/plugin/
+
+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:: 
+
+    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_plugins = "pytest_myextension",
 
-then all tests in and below that directory will consult the hooks
-defined in the imported ``pytest_myextension``.  A plugin 
-may specify its dependencies via another ``pytest_plugins`` 
-definition.  
diff --git a/py/test/config.py b/py/test/config.py
index 6a863513c..b423fbd80 100644
--- a/py/test/config.py
+++ b/py/test/config.py
@@ -2,7 +2,6 @@ import py, os
 from conftesthandle import Conftest
 
 from py.__.test import parseopt
-from py.__.test.runner import SetupState
 
 def ensuretemp(string, dir=1): 
     """ return temporary directory path with
@@ -41,7 +40,6 @@ class Config(object):
         assert isinstance(pluginmanager, py.test._PluginManager)
         self.pluginmanager = pluginmanager
         self._conftest = Conftest(onimport=self._onimportconftest)
-        self._setupstate = SetupState() 
         self.hook = pluginmanager.hook
 
     def _onimportconftest(self, conftestmodule):
diff --git a/py/test/defaultconftest.py b/py/test/defaultconftest.py
index 5de496c17..78596f81a 100644
--- a/py/test/defaultconftest.py
+++ b/py/test/defaultconftest.py
@@ -10,5 +10,5 @@ Generator = py.test.collect.Generator
 Function = py.test.collect.Function
 Instance = py.test.collect.Instance
 
-pytest_plugins = "default terminal xfail tmpdir execnetcleanup monkeypatch recwarn pdb".split()
+pytest_plugins = "default runner terminal xfail tmpdir execnetcleanup monkeypatch recwarn pdb".split()
 
diff --git a/py/test/dist/dsession.py b/py/test/dist/dsession.py
index d517993da..ac27654ef 100644
--- a/py/test/dist/dsession.py
+++ b/py/test/dist/dsession.py
@@ -5,7 +5,6 @@
 """
 
 import py
-from py.__.test.runner import basic_run_report, basic_collect_report, ItemTestReport
 from py.__.test.session import Session
 from py.__.test import outcome 
 from py.__.test.dist.nodemanage import NodeManager
@@ -24,7 +23,7 @@ class LoopState(object):
         self.shuttingdown = False
         self.testsfailed = False
 
-    def pytest_itemtestreport(self, rep):
+    def pytest_runtest_logreport(self, rep):
         if rep.item in self.dsession.item2nodes:
             self.dsession.removeitem(rep.item, rep.node)
         if rep.failed:
@@ -61,14 +60,14 @@ class DSession(Session):
         self.item2nodes = {}
         super(DSession, self).__init__(config=config)
 
-    def pytest_configure(self, __call__, config):
-        __call__.execute()
-        try:
-            config.getxspecs()
-        except config.Error:
-            print
-            raise config.Error("dist mode %r needs test execution environments, "
-                               "none found." %(config.option.dist))
+    #def pytest_configure(self, __call__, config):
+    #    __call__.execute()
+    #    try:
+    #        config.getxspecs()
+    #    except config.Error:
+    #        print
+    #        raise config.Error("dist mode %r needs test execution environments, "
+    #                           "none found." %(config.option.dist))
 
     def main(self, colitems=None):
         colitems = self.getinitialitems(colitems)
@@ -177,7 +176,8 @@ class DSession(Session):
                 senditems.append(next)
             else:
                 self.config.hook.pytest_collectstart(collector=next)
-                self.queueevent("pytest_collectreport", rep=basic_collect_report(next))
+                colrep = self.config.hook.pytest_make_collect_report(collector=next)
+                self.queueevent("pytest_collectreport", rep=colrep)
         if self.config.option.dist == "each":
             self.senditems_each(senditems)
         else:
@@ -239,9 +239,10 @@ class DSession(Session):
 
     def handle_crashitem(self, item, node):
         longrepr = "!!! Node %r crashed during running of test %r" %(node, item)
-        rep = ItemTestReport(item, when="???", excinfo=longrepr)
+        rep = item.config.hook.pytest_runtest_makereport(
+            item=item, when="???", excinfo=longrepr, outerr=None)
         rep.node = node
-        self.config.hook.pytest_itemtestreport(rep=rep)
+        self.config.hook.pytest_runtest_logreport(rep=rep)
 
     def setup(self):
         """ setup any neccessary resources ahead of the test run. """
diff --git a/py/test/dist/testing/test_dsession.py b/py/test/dist/testing/test_dsession.py
index 128daeaf2..18b8ae7c4 100644
--- a/py/test/dist/testing/test_dsession.py
+++ b/py/test/dist/testing/test_dsession.py
@@ -1,13 +1,12 @@
 from py.__.test.dist.dsession import DSession
-from py.__.test.runner import basic_collect_report 
 from py.__.test import outcome
 import py
 
 XSpec = py.execnet.XSpec
 
-def run(item, node):
-    from py.__.test.runner import basic_run_report
-    rep = basic_run_report(item)
+def run(item, node, excinfo=None):
+    rep = item.config.hook.pytest_runtest_makereport(
+            item=item, excinfo=excinfo, when="call", outerr=("", ""))
     rep.node = node
     return rep 
 
@@ -134,7 +133,7 @@ class TestDSession:
         session.queueevent(None)
         session.loop_once(loopstate)
         assert node.sent == [[item]]
-        session.queueevent("pytest_itemtestreport", rep=run(item, node))
+        session.queueevent("pytest_runtest_logreport", rep=run(item, node))
         session.loop_once(loopstate)
         assert loopstate.shuttingdown 
         assert not loopstate.testsfailed 
@@ -180,7 +179,7 @@ class TestDSession:
         session.loop_once(loopstate)
 
         assert loopstate.colitems == [item2] # do not reschedule crash item
-        rep = reprec.matchreport(names="pytest_itemtestreport")
+        rep = reprec.matchreport(names="pytest_runtest_logreport")
         assert rep.failed
         assert rep.item == item1
         assert str(rep.longrepr).find("crashed") != -1
@@ -198,7 +197,7 @@ class TestDSession:
         session.loop_once(loopstate)
         assert len(session.node2pending) == 1
 
-    def runthrough(self, item):
+    def runthrough(self, item, excinfo=None):
         session = DSession(item.config)
         node = MockNode()
         session.addnode(node)
@@ -208,8 +207,8 @@ class TestDSession:
         session.loop_once(loopstate)
 
         assert node.sent == [[item]]
-        ev = run(item, node) 
-        session.queueevent("pytest_itemtestreport", rep=ev)
+        ev = run(item, node, excinfo=excinfo) 
+        session.queueevent("pytest_runtest_logreport", rep=ev)
         session.loop_once(loopstate)
         assert loopstate.shuttingdown  
         session.queueevent("pytest_testnodedown", node=node, error=None)
@@ -224,7 +223,7 @@ class TestDSession:
 
     def test_exit_completed_tests_fail(self, testdir):
         item = testdir.getitem("def test_func(): 0/0")
-        session, exitstatus = self.runthrough(item)
+        session, exitstatus = self.runthrough(item, excinfo="fail")
         assert exitstatus == outcome.EXIT_TESTSFAILED
 
     def test_exit_on_first_failing(self, testdir):
@@ -238,16 +237,16 @@ class TestDSession:
         session = DSession(modcol.config)
         node = MockNode()
         session.addnode(node)
-        items = basic_collect_report(modcol).result
+        items = modcol.config.hook.pytest_make_collect_report(collector=modcol).result
 
         # trigger testing  - this sends tests to the node
         session.triggertesting(items)
 
         # run tests ourselves and produce reports 
-        ev1 = run(items[0], node)
-        ev2 = run(items[1], node)
-        session.queueevent("pytest_itemtestreport", rep=ev1) # a failing one
-        session.queueevent("pytest_itemtestreport", rep=ev2)
+        ev1 = run(items[0], node, "fail")
+        ev2 = run(items[1], node, None)
+        session.queueevent("pytest_runtest_logreport", rep=ev1) # a failing one
+        session.queueevent("pytest_runtest_logreport", rep=ev2)
         # now call the loop
         loopstate = session._initloopstate(items)
         session.loop_once(loopstate)
@@ -262,7 +261,7 @@ class TestDSession:
         loopstate = session._initloopstate([])
         loopstate.shuttingdown = True
         reprec = testdir.getreportrecorder(session)
-        session.queueevent("pytest_itemtestreport", rep=run(item, node))
+        session.queueevent("pytest_runtest_logreport", rep=run(item, node))
         session.loop_once(loopstate)
         assert not reprec.getcalls("pytest_testnodedown")
         session.queueevent("pytest_testnodedown", node=node, error=None)
@@ -303,7 +302,7 @@ class TestDSession:
         node = MockNode()
         session.addnode(node)
         session.senditems_load([item])
-        session.queueevent("pytest_itemtestreport", rep=run(item, node))
+        session.queueevent("pytest_runtest_logreport", rep=run(item, node))
         loopstate = session._initloopstate([])
         session.loop_once(loopstate)
         assert node._shutdown is True
@@ -324,12 +323,12 @@ class TestDSession:
         node = MockNode()
         session.addnode(node)
 
-        colreport = basic_collect_report(modcol)
+        colreport = modcol.config.hook.pytest_make_collect_report(collector=modcol)
         item1, item2 = colreport.result
         session.senditems_load([item1])
         # node2pending will become empty when the loop sees the report 
         rep = run(item1, node)
-        session.queueevent("pytest_itemtestreport", rep=run(item1, node)) 
+        session.queueevent("pytest_runtest_logreport", rep=run(item1, node)) 
 
         # but we have a collection pending
         session.queueevent("pytest_collectreport", rep=colreport) 
@@ -356,11 +355,11 @@ class TestDSession:
         dsession = DSession(config)
         hookrecorder = testdir.getreportrecorder(config).hookrecorder
         dsession.main([config.getfsnode(p1)])
-        rep = hookrecorder.popcall("pytest_itemtestreport").rep 
+        rep = hookrecorder.popcall("pytest_runtest_logreport").rep 
         assert rep.passed
-        rep = hookrecorder.popcall("pytest_itemtestreport").rep
+        rep = hookrecorder.popcall("pytest_runtest_logreport").rep
         assert rep.skipped
-        rep = hookrecorder.popcall("pytest_itemtestreport").rep
+        rep = hookrecorder.popcall("pytest_runtest_logreport").rep
         assert rep.failed
         # see that the node is really down 
         node = hookrecorder.popcall("pytest_testnodedown").node
diff --git a/py/test/dist/testing/test_nodemanage.py b/py/test/dist/testing/test_nodemanage.py
index f8625bac8..b62118714 100644
--- a/py/test/dist/testing/test_nodemanage.py
+++ b/py/test/dist/testing/test_nodemanage.py
@@ -122,6 +122,6 @@ class TestNodeManager:
         """)
         reprec = testdir.inline_run("-d", "--rsyncdir=%s" % testdir.tmpdir, 
                 "--tx", specssh, testdir.tmpdir)
-        rep, = reprec.getreports("pytest_itemtestreport")
+        rep, = reprec.getreports("pytest_runtest_logreport")
         assert rep.passed 
 
diff --git a/py/test/dist/testing/test_txnode.py b/py/test/dist/testing/test_txnode.py
index d988a798d..4e47537c3 100644
--- a/py/test/dist/testing/test_txnode.py
+++ b/py/test/dist/testing/test_txnode.py
@@ -111,7 +111,7 @@ class TestMasterSlaveConnection:
         item = testdir.getitem("def test_func(): pass")
         node = mysetup.makenode(item.config)
         node.send(item)
-        kwargs = mysetup.geteventargs("pytest_itemtestreport")
+        kwargs = mysetup.geteventargs("pytest_runtest_logreport")
         rep = kwargs['rep'] 
         assert rep.passed 
         print rep
@@ -131,11 +131,11 @@ class TestMasterSlaveConnection:
         for item in items:
             node.send(item)
         for outcome in "passed failed skipped".split():
-            kwargs = mysetup.geteventargs("pytest_itemtestreport")
+            kwargs = mysetup.geteventargs("pytest_runtest_logreport")
             rep = kwargs['rep']
             assert getattr(rep, outcome) 
 
         node.sendlist(items)
         for outcome in "passed failed skipped".split():
-            rep = mysetup.geteventargs("pytest_itemtestreport")['rep']
+            rep = mysetup.geteventargs("pytest_runtest_logreport")['rep']
             assert getattr(rep, outcome) 
diff --git a/py/test/dist/txnode.py b/py/test/dist/txnode.py
index 05b0a8aa5..d7633e80e 100644
--- a/py/test/dist/txnode.py
+++ b/py/test/dist/txnode.py
@@ -50,10 +50,10 @@ class TXNode(object):
             elif eventname == "slavefinished":
                 self._down = True
                 self.notify("pytest_testnodedown", error=None, node=self)
-            elif eventname == "pytest_itemtestreport":
+            elif eventname == "pytest_runtest_logreport":
                 rep = kwargs['rep']
                 rep.node = self
-                self.notify("pytest_itemtestreport", rep=rep)
+                self.notify("pytest_runtest_logreport", rep=rep)
             else:
                 self.notify(eventname, *args, **kwargs)
         except KeyboardInterrupt: 
@@ -105,8 +105,8 @@ class SlaveNode(object):
     def sendevent(self, eventname, *args, **kwargs):
         self.channel.send((eventname, args, kwargs))
 
-    def pytest_itemtestreport(self, rep):
-        self.sendevent("pytest_itemtestreport", rep=rep)
+    def pytest_runtest_logreport(self, rep):
+        self.sendevent("pytest_runtest_logreport", rep=rep)
 
     def run(self):
         channel = self.channel
@@ -124,9 +124,9 @@ class SlaveNode(object):
                     break
                 if isinstance(task, list):
                     for item in task:
-                        item.config.pluginmanager.do_itemrun(item)
+                        item.config.hook.pytest_runtest_protocol(item=item) 
                 else:
-                    task.config.pluginmanager.do_itemrun(item=task)
+                    task.config.hook.pytest_runtest_protocol(item=task) 
         except KeyboardInterrupt:
             raise
         except:
diff --git a/py/test/looponfail/remote.py b/py/test/looponfail/remote.py
index 6ff438e55..3578b3480 100644
--- a/py/test/looponfail/remote.py
+++ b/py/test/looponfail/remote.py
@@ -137,10 +137,10 @@ def slave_runsession(channel, config, fullwidth, hasmarkup):
     session.shouldclose = channel.isclosed 
    
     class Failures(list):
-        def pytest_itemtestreport(self, rep):
+        def pytest_runtest_logreport(self, rep):
             if rep.failed:
                 self.append(rep)
-        pytest_collectreport = pytest_itemtestreport
+        pytest_collectreport = pytest_runtest_logreport
         
     failreports = Failures()
     session.pluginmanager.register(failreports)
diff --git a/py/test/plugin/api.py b/py/test/plugin/api.py
index fe54ed8de..c96ad55e2 100644
--- a/py/test/plugin/api.py
+++ b/py/test/plugin/api.py
@@ -35,6 +35,10 @@ class PluginHooks:
     # ------------------------------------------------------------------------------
     # collection hooks
     # ------------------------------------------------------------------------------
+    def pytest_make_collect_report(self, collector):
+        """ perform a collection and return a collection. """ 
+    pytest_make_collect_report.firstresult = True
+
     def pytest_collect_file(self, path, parent):
         """ return Collection node or None. """
 
@@ -67,20 +71,29 @@ 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. """ 
+
+    def pytest_runtest_call(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_itemrun(self, item, pdb=None):
+    def pytest_runtest_protocol(self, item):
         """ run given test item and return test report. """ 
-    pytest_itemrun.firstresult = True
+    pytest_runtest_protocol.firstresult = True
 
     def pytest_pyfunc_call(self, pyfuncitem, args, kwargs):
         """ return True if we consumed/did the call to the python function item. """
     pytest_pyfunc_call.firstresult = True
 
-    def pytest_item_makereport(self, item, excinfo, when, outerr):
-        """ make ItemTestReport for the specified test outcome. """
-    pytest_item_makereport.firstresult = True
 
-    def pytest_itemtestreport(self, rep):
+    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 bc30dff49..2bbe6f871 100644
--- a/py/test/plugin/pytest_default.py
+++ b/py/test/plugin/pytest_default.py
@@ -2,19 +2,6 @@
 
 import py
 
-def pytest_itemrun(item):
-    from py.__.test.runner import basic_run_report, forked_run_report
-    if item.config.option.boxed:
-        report = forked_run_report(item)
-    else:
-        report = basic_run_report(item) 
-    item.config.hook.pytest_itemtestreport(rep=report)
-    return True
-
-def pytest_item_makereport(item, excinfo, when, outerr):
-    from py.__.test import runner
-    return runner.ItemTestReport(item, excinfo, when, outerr)
-
 def pytest_pyfunc_call(pyfuncitem, args, kwargs):
     pyfuncitem.obj(*args, **kwargs)
 
@@ -76,9 +63,6 @@ def pytest_addoption(parser):
     group._addoption('-s', 
                action="store_true", dest="nocapture", default=False,
                help="disable catching of stdout/stderr during test run.")
-    group.addoption('--boxed',
-               action="store_true", dest="boxed", default=False,
-               help="box each test run in a separate process") 
     group._addoption('-p', action="append", dest="plugin", default = [],
                help=("load the specified plugin after command line parsing. "))
     group._addoption('-f', '--looponfail',
diff --git a/py/test/plugin/pytest_doctest.py b/py/test/plugin/pytest_doctest.py
index 094247f57..2189612a5 100644
--- a/py/test/plugin/pytest_doctest.py
+++ b/py/test/plugin/pytest_doctest.py
@@ -119,7 +119,7 @@ class TestDoctests:
             2
         """)
         reprec = testdir.inline_run(p)
-        call = reprec.getcall("pytest_itemtestreport")
+        call = reprec.getcall("pytest_runtest_logreport")
         assert call.rep.failed
         assert call.rep.longrepr 
         # XXX 
diff --git a/py/test/plugin/pytest_pdb.py b/py/test/plugin/pytest_pdb.py
index e1a128d17..be7fc674e 100644
--- a/py/test/plugin/pytest_pdb.py
+++ b/py/test/plugin/pytest_pdb.py
@@ -22,7 +22,7 @@ def pytest_configure(config):
         config.pluginmanager.register(PdbInvoke())
 
 class PdbInvoke:
-    def pytest_item_makereport(self, item, excinfo, when, outerr):
+    def pytest_runtest_makereport(self, item, excinfo, when, outerr):
         if excinfo and not excinfo.errisinstance(Skipped): 
             tw = py.io.TerminalWriter()
             repr = excinfo.getrepr()
diff --git a/py/test/plugin/pytest_pytester.py b/py/test/plugin/pytest_pytester.py
index 78d5cc8bc..dd867cdd4 100644
--- a/py/test/plugin/pytest_pytester.py
+++ b/py/test/plugin/pytest_pytester.py
@@ -5,7 +5,6 @@ funcargs and support code for testing py.test functionality.
 import py
 import os
 import inspect
-from py.__.test import runner
 from py.__.test.config import Config as pytestConfig
 import api
 
@@ -161,7 +160,7 @@ class TmpTestdir:
         p = self.makepyfile(source)
         l = list(args) + [p]
         reprec = self.inline_run(*l)
-        reports = reprec.getreports("pytest_itemtestreport")
+        reports = reprec.getreports("pytest_runtest_logreport")
         assert len(reports) == 1, reports 
         return reports[0]
 
@@ -227,6 +226,12 @@ class TmpTestdir:
             self.makepyfile(__init__ = "#")
         self.config = self.parseconfig(path, *configargs)
         self.session = self.config.initsession()
+        #self.config.pluginmanager.do_configure(config=self.config)
+        # XXX 
+        self.config.pluginmanager.import_plugin("runner") 
+        plugin = self.config.pluginmanager.getplugin("runner") 
+        plugin.pytest_configure(config=self.config)
+
         return self.config.getfsnode(path)
 
     def prepare(self):
@@ -321,10 +326,10 @@ class ReportRecorder(object):
 
     # functionality for test reports 
 
-    def getreports(self, names="pytest_itemtestreport pytest_collectreport"):
+    def getreports(self, names="pytest_runtest_logreport pytest_collectreport"):
         return [x.rep for x in self.getcalls(names)]
 
-    def matchreport(self, inamepart="", names="pytest_itemtestreport pytest_collectreport"):
+    def matchreport(self, inamepart="", names="pytest_runtest_logreport pytest_collectreport"):
         """ return a testreport whose dotted import path matches """
         l = []
         for rep in self.getreports(names=names):
@@ -339,7 +344,7 @@ class ReportRecorder(object):
                              inamepart, l))
         return l[0]
 
-    def getfailures(self, names='pytest_itemtestreport pytest_collectreport'):
+    def getfailures(self, names='pytest_runtest_logreport pytest_collectreport'):
         return [rep for rep in self.getreports(names) if rep.failed]
 
     def getfailedcollections(self):
@@ -349,7 +354,7 @@ class ReportRecorder(object):
         passed = []
         skipped = []
         failed = []
-        for rep in self.getreports("pytest_itemtestreport"):
+        for rep in self.getreports("pytest_runtest_logreport"):
             if rep.passed: 
                 passed.append(rep) 
             elif rep.skipped: 
@@ -378,23 +383,29 @@ def test_reportrecorder(testdir):
     registry = py._com.Registry()
     recorder = testdir.getreportrecorder(registry)
     assert not recorder.getfailures()
-    rep = runner.ItemTestReport(None, None)
+    item = testdir.getitem("def test_func(): pass")
+    rep = item.config.hook.pytest_runtest_makereport(
+        item=item, excinfo=None, when="call", outerr=None)
+
     rep.passed = False
     rep.failed = True
-    recorder.hook.pytest_itemtestreport(rep=rep)
+    recorder.hook.pytest_runtest_logreport(rep=rep)
     failures = recorder.getfailures()
     assert failures == [rep]
     failures = recorder.getfailures()
     assert failures == [rep]
 
-    rep = runner.ItemTestReport(None, None)
+    rep = item.config.hook.pytest_runtest_makereport(
+        item=item, excinfo=None, when="call", outerr=None)
     rep.passed = False
     rep.skipped = True
-    recorder.hook.pytest_itemtestreport(rep=rep)
+    recorder.hook.pytest_runtest_logreport(rep=rep)
 
-    rep = runner.CollectReport(None, None)
+    modcol = testdir.getmodulecol("")
+    rep = modcol.config.hook.pytest_make_collect_report(collector=modcol)
     rep.passed = False
     rep.failed = True
+    rep.skipped = False
     recorder.hook.pytest_collectreport(rep=rep)
 
     passed, skipped, failed = recorder.listoutcomes()
@@ -408,7 +419,7 @@ def test_reportrecorder(testdir):
 
     recorder.unregister()
     recorder.clear() 
-    recorder.hook.pytest_itemtestreport(rep=rep)
+    recorder.hook.pytest_runtest_logreport(rep=rep)
     py.test.raises(ValueError, "recorder.getfailures()")
 
 class LineComp:
diff --git a/py/test/plugin/pytest_resultlog.py b/py/test/plugin/pytest_resultlog.py
index f168c1cc3..869cfe80d 100644
--- a/py/test/plugin/pytest_resultlog.py
+++ b/py/test/plugin/pytest_resultlog.py
@@ -59,7 +59,7 @@ class ResultLog(object):
         testpath = generic_path(node)
         self.write_log_entry(testpath, shortrepr, longrepr) 
 
-    def pytest_itemtestreport(self, rep):
+    def pytest_runtest_logreport(self, rep):
         code = rep.shortrepr 
         if rep.passed:
             longrepr = ""
diff --git a/py/test/runner.py b/py/test/plugin/pytest_runner.py
similarity index 81%
rename from py/test/runner.py
rename to py/test/plugin/pytest_runner.py
index 470f3ccf8..81746b98c 100644
--- a/py/test/runner.py
+++ b/py/test/plugin/pytest_runner.py
@@ -1,5 +1,5 @@
 """ 
-    internal classes for
+    collect and run test items. 
 
     * executing test items 
     * running collectors 
@@ -10,6 +10,58 @@ import py
 
 from py.__.test.outcome import Skipped
 
+#
+# pytest plugin hooks 
+#
+
+def pytest_addoption(parser):
+    group = parser.getgroup("general") 
+    group.addoption('--boxed',
+               action="store_true", dest="boxed", default=False,
+               help="box each test run in a separate process") 
+
+def pytest_configure(config):
+    config._setupstate = SetupState()
+
+def pytest_unconfigure(config):
+    config._setupstate.teardown_all()
+
+def pytest_make_collect_report(collector):
+    call = collector.config.guardedcall(
+        lambda: collector._memocollect()
+    )
+    result = None
+    if not call.excinfo:
+        result = call.result
+    return CollectReport(collector, result, call.excinfo, call.outerr)
+
+    return report 
+
+def pytest_runtest_protocol(item):
+    if item.config.option.boxed:
+        report = forked_run_report(item)
+    else:
+        report = basic_run_report(item) 
+    item.config.hook.pytest_runtest_logreport(rep=report)
+    return True
+
+def pytest_runtest_setup(item):
+    item.config._setupstate.prepare(item)
+
+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_teardown(item):
+    item.config._setupstate.teardown_exact(item)
+
+#
+# Implementation
+#
+
 class Call:
     excinfo = None 
     def __init__(self, when, func):
@@ -21,35 +73,24 @@ class Call:
         except:
             self.excinfo = py.code.ExceptionInfo()
 
-def runtest_with_deprecated_check(item):
-    if not item._deprecated_testexecution():
-        item.runtest()
 
 def basic_run_report(item):
     """ return report about setting up and running a test item. """
-    setupstate = item.config._setupstate
     capture = item.config._getcapture()
+    hook = item.config.hook
     try:
-        call = Call("setup", lambda: setupstate.prepare(item))
+        call = Call("setup", lambda: hook.pytest_runtest_setup(item=item))
         if not call.excinfo:
-            call = Call("runtest", lambda: runtest_with_deprecated_check(item))
+            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: setupstate.teardown_exact(item))
+                call = Call("teardown", lambda: hook.pytest_runtest_teardown(item=item))
     finally:
         outerr = capture.reset()
-    return item.config.hook.pytest_item_makereport(
+    return item.config.hook.pytest_runtest_makereport(
             item=item, excinfo=call.excinfo, 
             when=call.when, outerr=outerr)
 
-def basic_collect_report(collector):
-    call = collector.config.guardedcall(
-        lambda: collector._memocollect()
-    )
-    result = None
-    if not call.excinfo:
-        result = call.result
-    return CollectReport(collector, result, call.excinfo, call.outerr)
-
 def forked_run_report(item):
     EXITSTATUS_TESTEXIT = 4
     from py.__.test.dist.mypickle import ImmutablePickler
@@ -122,7 +163,7 @@ class ItemTestReport(BaseReport):
             else:
                 self.failed = True
                 shortrepr = self.item.shortfailurerepr
-                if self.when == "runtest":
+                if self.when == "call":
                     longrepr = self.item.repr_failure(excinfo, outerr)
                 else: # exception in setup or teardown 
                     longrepr = self.item._repr_failure_py(excinfo, outerr)
diff --git a/py/test/plugin/pytest_terminal.py b/py/test/plugin/pytest_terminal.py
index 998e5dd7c..e6c48b543 100644
--- a/py/test/plugin/pytest_terminal.py
+++ b/py/test/plugin/pytest_terminal.py
@@ -161,7 +161,7 @@ class TerminalReporter:
                 fspath, lineno, msg = self._getreportinfo(item)
                 self.write_fspath_result(fspath, "")
 
-    def pytest_itemtestreport(self, rep):
+    def pytest_runtest_logreport(self, rep):
         fspath = rep.item.fspath 
         cat, letter, word = self.getcategoryletterword(rep)
         if isinstance(word, tuple):
@@ -397,10 +397,9 @@ def repr_pythonversion(v=None):
 #
 # ===============================================================================
 
-from py.__.test import runner
+import pytest_runner as runner # XXX 
 
 class TestTerminal:
-
     def test_pass_skip_fail(self, testdir, linecomp):
         modcol = testdir.getmodulecol("""
             import py
@@ -417,7 +416,7 @@ class TestTerminal:
 
         for item in testdir.genitems([modcol]):
             ev = runner.basic_run_report(item) 
-            rep.config.hook.pytest_itemtestreport(rep=ev)
+            rep.config.hook.pytest_runtest_logreport(rep=ev)
         linecomp.assert_contains_lines([
                 "*test_pass_skip_fail.py .sF"
         ])
@@ -447,7 +446,7 @@ 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_itemtestreport(rep=runner.basic_run_report(item))
+            rep.config.hook.pytest_runtest_logreport(rep=runner.basic_run_report(item))
 
         linecomp.assert_contains_lines([
             "*test_pass_skip_fail_verbose.py:2: *test_ok*PASS*",
@@ -563,7 +562,7 @@ class TestTerminal:
             rep.config.pluginmanager.register(rep)
             rep.config.hook.pytest_sessionstart(session=testdir.session)
             for item in testdir.genitems([modcol]):
-                rep.config.hook.pytest_itemtestreport(
+                rep.config.hook.pytest_runtest_logreport(
                     rep=runner.basic_run_report(item))
             rep.config.hook.pytest_sessionfinish(session=testdir.session, exitstatus=1)
             s = linecomp.stringio.getvalue()
@@ -644,7 +643,7 @@ class TestTerminal:
         modcol.config.hook.pytest_sessionstart(session=testdir.session)
         try:
             for item in testdir.genitems([modcol]):
-                modcol.config.hook.pytest_itemtestreport(
+                modcol.config.hook.pytest_runtest_logreport(
                     rep=runner.basic_run_report(item))
         except KeyboardInterrupt:
             excinfo = py.code.ExceptionInfo()
diff --git a/py/test/plugin/pytest_xfail.py b/py/test/plugin/pytest_xfail.py
index 4a95b940f..bda70c20e 100644
--- a/py/test/plugin/pytest_xfail.py
+++ b/py/test/plugin/pytest_xfail.py
@@ -10,7 +10,7 @@ example:
 """
 import py
 
-def pytest_item_makereport(__call__, item, excinfo, when, outerr):
+def pytest_runtest_makereport(__call__, item, excinfo, when, outerr):
     if hasattr(item, 'obj') and hasattr(item.obj, 'func_dict'):
         if 'xfail' in item.obj.func_dict:
             res = __call__.execute(firstresult=True)
diff --git a/py/test/testing/test_runner.py b/py/test/plugin/test_pytest_runner.py
similarity index 95%
rename from py/test/testing/test_runner.py
rename to py/test/plugin/test_pytest_runner.py
index 839bf4186..4bb0a6680 100644
--- a/py/test/testing/test_runner.py
+++ b/py/test/plugin/test_pytest_runner.py
@@ -1,5 +1,5 @@
 import py
-from py.__.test import runner 
+from py.__.test.plugin import pytest_runner as runner
 from py.__.code.excinfo import ReprExceptionInfo
 
 class TestSetupState:
@@ -56,7 +56,7 @@ class BaseFunctionalTests:
         assert not rep.passed 
         assert not rep.skipped 
         assert rep.failed 
-        assert rep.when == "runtest"
+        assert rep.when == "call"
         assert isinstance(rep.longrepr, ReprExceptionInfo)
         assert str(rep.shortrepr) == "F"
 
@@ -69,8 +69,8 @@ class BaseFunctionalTests:
         assert not rep.failed 
         assert not rep.passed 
         assert rep.skipped 
-        #assert rep.skipped.when == "runtest"
-        #assert rep.skipped.when == "runtest"
+        #assert rep.skipped.when == "call"
+        #assert rep.skipped.when == "call"
         #assert rep.skipped == "%sreason == "hello"
         #assert rep.skipped.location.lineno == 3
         #assert rep.skipped.location.path
@@ -137,7 +137,7 @@ class BaseFunctionalTests:
         assert not rep.skipped 
         assert not rep.passed 
         assert rep.failed 
-        #assert rep.outcome.when == "runtest"
+        #assert rep.outcome.when == "call"
         #assert rep.failed.where.lineno == 3
         #assert rep.failed.where.path.basename == "test_func.py" 
         #assert rep.failed.failurerepr == "hello"
@@ -190,7 +190,7 @@ class BaseFunctionalTests:
         except SystemExit:
             py.test.fail("runner did not catch SystemExit")
         assert rep.failed
-        assert rep.when == "runtest"
+        assert rep.when == "call"
 
     def test_exit_propagates(self, testdir):
         from py.__.test.outcome import Exit
@@ -245,7 +245,7 @@ class TestCollectionReports:
             class TestClass:
                 pass
         """)
-        rep = runner.basic_collect_report(col)
+        rep = runner.pytest_make_collect_report(col)
         assert not rep.failed
         assert not rep.skipped
         assert rep.passed 
@@ -261,9 +261,7 @@ class TestCollectionReports:
             def test_func():
                 pass
         """)
-        rep = runner.basic_collect_report(col)
+        rep = runner.pytest_make_collect_report(col)
         assert not rep.failed 
         assert not rep.passed 
         assert rep.skipped 
-
-
diff --git a/py/test/pluginmanager.py b/py/test/pluginmanager.py
index e7f384a79..ef141ec33 100644
--- a/py/test/pluginmanager.py
+++ b/py/test/pluginmanager.py
@@ -183,11 +183,6 @@ class PluginManager(object):
         config.hook.pytest_unconfigure(config=config)
         config.pluginmanager.unregister(self)
 
-    def do_itemrun(self, item):
-        res = self.hook.pytest_itemrun(item=item)
-        if res is None:
-            raise ValueError("could not run %r" %(item,))
-
 # 
 #  XXX old code to automatically load classes
 #
diff --git a/py/test/pycollect.py b/py/test/pycollect.py
index 16fd5d5d3..06d72dac3 100644
--- a/py/test/pycollect.py
+++ b/py/test/pycollect.py
@@ -331,16 +331,13 @@ class Function(FunctionMixin, py.test.collect.Item):
         if callobj is not _dummy: 
             self._obj = callobj 
 
-    #def addfinalizer(self, func):
-    #    self.config._setupstate.ddfinalizer(func, colitem=self)
-        
     def readkeywords(self):
         d = super(Function, self).readkeywords()
         d.update(self.obj.func_dict)
         return d
 
     def runtest(self):
-        """ execute the given test function. """
+        """ execute the underlying test function. """
         kwargs = getattr(self, 'funcargs', {})
         self.config.hook.pytest_pyfunc_call(
             pyfuncitem=self, args=self._args, kwargs=kwargs)
diff --git a/py/test/session.py b/py/test/session.py
index c1a9738ee..c83081195 100644
--- a/py/test/session.py
+++ b/py/test/session.py
@@ -11,7 +11,6 @@ from py.__.test import outcome
 # imports used for genitems()
 Item = py.test.collect.Item
 Collector = py.test.collect.Collector
-from runner import basic_collect_report
 
 class Session(object): 
     """ 
@@ -42,7 +41,7 @@ class Session(object):
             else:
                 assert isinstance(next, Collector)
                 self.config.hook.pytest_collectstart(collector=next)
-                rep = basic_collect_report(next)
+                rep = self.config.hook.pytest_make_collect_report(collector=next)
                 if rep.passed:
                     for x in self.genitems(rep.result, keywordexpr):
                         yield x 
@@ -80,12 +79,12 @@ class Session(object):
         """ setup any neccessary resources ahead of the test run. """
         self.config.hook.pytest_sessionstart(session=self)
         
-    def pytest_itemtestreport(self, rep):
+    def pytest_runtest_logreport(self, rep):
         if rep.failed:
             self._testsfailed = True
             if self.config.option.exitfirst:
                 self.shouldstop = True
-    pytest_collectreport = pytest_itemtestreport
+    pytest_collectreport = pytest_runtest_logreport
 
     def sessionfinishes(self, exitstatus=0, excinfo=None):
         """ teardown any resources after a test run. """ 
@@ -113,8 +112,7 @@ class Session(object):
                 if self.shouldstop: 
                     break 
                 if not self.config.option.collectonly: 
-                    item.config.pluginmanager.do_itemrun(item) 
-            self.config._setupstate.teardown_all()
+                    item.config.hook.pytest_runtest_protocol(item=item)
         except KeyboardInterrupt:
             captured_excinfo = py.code.ExceptionInfo()
             exitstatus = outcome.EXIT_INTERRUPTED
diff --git a/py/test/testing/test_session.py b/py/test/testing/test_session.py
index 612f6f528..1da3b487d 100644
--- a/py/test/testing/test_session.py
+++ b/py/test/testing/test_session.py
@@ -185,7 +185,7 @@ class TestNewSession(SessionTests):
        
         itemstarted = reprec.getcalls("pytest_itemstart")
         assert len(itemstarted) == 3
-        assert not reprec.getreports("pytest_itemtestreport") 
+        assert not reprec.getreports("pytest_runtest_logreport") 
         started = reprec.getcalls("pytest_collectstart")
         finished = reprec.getreports("pytest_collectreport")
         assert len(started) == len(finished) 
diff --git a/py/test/testing/test_setup_functional.py b/py/test/testing/test_setup_functional.py
index 0e995aafd..a8d17e45a 100644
--- a/py/test/testing/test_setup_functional.py
+++ b/py/test/testing/test_setup_functional.py
@@ -118,7 +118,7 @@ def test_func_generator_setup(testdir):
             yield check 
             assert x == [1]
     """)
-    rep = reprec.matchreport("test_one", names="pytest_itemtestreport") 
+    rep = reprec.matchreport("test_one", names="pytest_runtest_logreport") 
     assert rep.passed 
         
 def test_method_setup_uses_fresh_instances(testdir):