Files
rea/bridge/native/test_rea_lldb_tracer.py
T
3e8a5f76d0 feat(native): retain LLDB source coordinates and verify Pascal calls (#2800)
* feat(native): retain LLDB source coordinates and verify Pascal call entries

Preserve partial line-table attribution for native locations and historical
evidence compatibility. Verify owned Free Pascal call entries through CLI/MCP.

Refs #2382, #2372, #2397

Co-Authored-By: Codex <[email protected]>

* docs: namespace native specifications by domain and feature

Use stable descriptive paths instead of numeric prefixes to avoid parallel contribution collisions.

Co-Authored-By: Codex <[email protected]>

* fix(native): bound Pascal verification and compare caller coordinates

Address review findings at their producing boundaries and preserve directly affected consumers. Source inspection and git diff --check completed. Tests and automated checks were not run at the user’s explicit request.

* fix(native): bound compiler shutdown and source-coordinate fixtures

* docs: clarify historical native source verification

* fix(native): preserve source attribution and compiler ownership

* docs(native): qualify retained source attribution

* fix(ci): clean up native Pascal verifier processes

* test(native): type the Pascal verifier helper import after merging main

Main now typechecks this boundary test, which imports the untyped
canonical-temporary-directory helper and reads an unknown catch value.
Add the helper's declaration file and narrow the caught error.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

* test(native): verify partial source attribution caveat

* fix(native): retain verifier compiler cleanup ownership

* fix(native): forward verifier cancellation and measure path bytes

CLI and MCP artifact runs observe the verifier abort signal, and a
failed Pascal verifier test stops the compiler group before deleting
its directory. Repeated source locations grow by measured UTF-8 JSON
bytes; workflow tokens, CPU and peak memory stay unmeasured.

---------

Co-authored-by: Matheus Breguêz <[email protected]>
Co-authored-by: Codex <[email protected]>
Co-authored-by: Kaoru0822 <[email protected]>
Co-authored-by: Claude Opus 5.5 <[email protected]>
Co-authored-by: Cursor Agent <[email protected]>
2026-11-07 23:25:20 +08:00

613 lines
20 KiB
Python

"""Source-owned tests for the LLDB bridge's bounded retention helpers."""
from io import BytesIO
import importlib.util
import json
import os
import sys
import tempfile
import types
import unittest
from unittest.mock import patch
fake_lldb = sys.modules.setdefault("lldb", types.ModuleType("lldb"))
fake_lldb.LLDB_INVALID_ADDRESS = -1
fake_lldb.eLaunchFlagDebug = 2
fake_lldb.eLaunchFlagStopAtEntry = 4
fake_lldb.eStateExited = 10
fake_lldb.SBEvent = lambda: object()
spec = importlib.util.spec_from_file_location(
"rea_lldb_tracer", os.path.join(os.path.dirname(__file__), "rea_lldb_tracer.py")
)
tracer = importlib.util.module_from_spec(spec)
spec.loader.exec_module(tracer)
class NativeTraceBudgetTests(unittest.TestCase):
def test_source_coordinates_preserve_partial_metadata_without_reading_source(self):
def address(valid=True, file_valid=True, line=23, column=7):
class SourceFileSpec:
def IsValid(self):
return file_valid
def __str__(self):
return "/missing/é space/fixture.pas"
file_spec = SourceFileSpec()
entry = types.SimpleNamespace(
IsValid=lambda: valid,
GetFileSpec=lambda: file_spec,
GetLine=lambda: line,
GetColumn=lambda: column,
)
return types.SimpleNamespace(GetLineEntry=lambda: entry)
self.assertEqual(
tracer._source_location(address()),
{"file_path": "/missing/é space/fixture.pas", "line": 23, "column": 7},
)
self.assertEqual(
tracer._source_location(address(column=0)),
{"file_path": "/missing/é space/fixture.pas", "line": 23, "column": None},
)
self.assertEqual(
tracer._source_location(address(file_valid=False)),
{"file_path": None, "line": 23, "column": 7},
)
self.assertEqual(
tracer._source_location(address(line=0)),
{"file_path": "/missing/é space/fixture.pas", "line": None, "column": 7},
)
self.assertIsNone(tracer._source_location(address(valid=False)))
self.assertIsNone(
tracer._source_location(address(file_valid=False, line=0, column=0))
)
def test_invalid_launch_process_reports_explicit_no_creation(self):
class InvalidProcess:
def IsValid(self):
return False
def Kill(self):
raise AssertionError("an invalid process cannot own target cleanup")
class LaunchError:
def Success(self):
return False
def GetCString(self):
return "No such file or directory: fixture/absent"
class Target:
def IsValid(self):
return True
def Launch(self, _launch_info, _error):
return InvalidProcess()
class Debugger:
def SetAsync(self, _enabled):
pass
def GetInstanceName(self):
return "fixture"
def CreateTarget(self, *_arguments):
return Target()
class Pipe:
def __init__(self, *_arguments):
self.closed = False
pipes.append(self)
def start(self):
pass
def close(self, expected_exit=False):
self.closed = True
pipes = []
debugger_api = types.SimpleNamespace(SetInternalVariable=lambda *_arguments: None)
with patch.object(tracer.lldb, "SBDebugger", debugger_api, create=True), patch.object(
tracer.lldb, "SBError", LaunchError, create=True
), patch.object(tracer.lldb, "SBListener", lambda _name: object(), create=True), patch.object(
tracer, "_hash_file", return_value="expected"
), patch.object(tracer, "_file_identity", return_value=(1, 2)), patch.object(
tracer, "_module_identity", return_value=("fixture", (1, 2), "fixture-uuid")
), patch.object(tracer, "_launch_info", return_value=object()), patch.object(
tracer, "_OutputPipe", Pipe
):
result = tracer.trace(Debugger(), {
"executable": "fixture", "architecture": "arm64", "expected_sha256": "expected",
"breakpoints": [], "working_directory": "fixture/absent",
"stdout_path": "stdout", "stdout_capture_path": "stdout-capture",
"stderr_path": "stderr", "stderr_capture_path": "stderr-capture",
})
self.assertEqual(result["status"], "launch-error")
self.assertEqual(result["error"], "No such file or directory: fixture/absent")
self.assertIs(result["target_process_created"], False)
self.assertNotIn("target_process_exit_observed", result)
self.assertEqual(len(pipes), 2)
self.assertTrue(all(pipe.closed for pipe in pipes))
def test_failed_launch_does_not_infer_exit_from_a_failed_kill(self):
class Process:
def IsValid(self):
return True
def GetProcessID(self):
return 12345
def GetState(self):
return 6
def Kill(self):
return None
class Sink:
close_exit = None
def mark_launched(self):
pass
def close(self, expected_exit=False):
self.close_exit = expected_exit
with tempfile.TemporaryDirectory() as directory:
stdout, stderr = Sink(), Sink()
with patch.object(tracer, "_wait_for_identity_ack", return_value="unavailable"), patch.object(
tracer, "_wait_for_exit", return_value=None
):
exited = tracer._retire_failed_launch(
Process(), {"pid_path": os.path.join(directory, "pid")}, object(), stdout, stderr
)
self.assertFalse(exited)
self.assertFalse(stdout.close_exit)
self.assertFalse(stderr.close_exit)
def test_failed_launch_publishes_pid_and_retires_live_process(self):
class Process:
state = 6
killed = False
def IsValid(self):
return True
def GetProcessID(self):
return 12345
def GetState(self):
return self.state
def Kill(self):
self.killed = True
self.state = tracer.lldb.eStateExited
class Sink:
launched = False
close_exit = None
def mark_launched(self):
self.launched = True
def close(self, expected_exit=False):
self.close_exit = expected_exit
with tempfile.TemporaryDirectory() as directory:
pid_path = os.path.join(directory, "pid")
process = Process()
stdout, stderr = Sink(), Sink()
def acknowledge(config):
with open(config["pid_path"], "r") as pid_file:
self.assertEqual(pid_file.read(), "12345")
return "readable"
with patch.object(tracer, "_wait_for_identity_ack", acknowledge):
exited = tracer._retire_failed_launch(
process,
{"pid_path": pid_path},
object(),
stdout,
stderr,
)
self.assertTrue(exited)
self.assertTrue(process.killed)
self.assertTrue(stdout.launched)
self.assertTrue(stderr.launched)
self.assertTrue(stdout.close_exit)
self.assertTrue(stderr.close_exit)
def test_failed_launch_records_when_valid_process_is_already_exited(self):
class Process:
def IsValid(self):
return True
def GetProcessID(self):
return 12345
def GetState(self):
return tracer.lldb.eStateExited
def Kill(self):
raise AssertionError("an exited process must not be killed")
class Sink:
close_exit = None
def mark_launched(self):
raise AssertionError("an exited process has no output to drain")
def close(self, expected_exit=False):
self.close_exit = expected_exit
with tempfile.TemporaryDirectory() as directory:
pid_path = os.path.join(directory, "pid")
stdout, stderr = Sink(), Sink()
with patch.object(
tracer,
"_wait_for_identity_ack",
side_effect=AssertionError("exit is already observed"),
):
exited = tracer._retire_failed_launch(
Process(), {"pid_path": pid_path}, object(), stdout, stderr
)
with open(pid_path, "r") as pid_file:
self.assertEqual(pid_file.read(), "12345")
self.assertTrue(exited)
self.assertTrue(stdout.close_exit)
self.assertTrue(stderr.close_exit)
def test_pre_target_integrity_failure_reports_no_process_created(self):
original_debugger = getattr(tracer.lldb, "SBDebugger", None)
class DebuggerApi:
@staticmethod
def SetInternalVariable(*_arguments):
return None
class Debugger:
def SetAsync(self, _enabled):
return None
def GetInstanceName(self):
return "fixture"
def CreateTarget(self, *_arguments):
raise AssertionError("integrity failure precedes target creation")
tracer.lldb.SBDebugger = DebuggerApi
try:
with patch.object(tracer, "_hash_file", return_value="changed"), patch.object(
tracer, "_file_identity", return_value=(1, 2)
):
result = tracer.trace(
Debugger(),
{"executable": "fixture", "expected_sha256": "expected"},
)
finally:
if original_debugger is None:
del tracer.lldb.SBDebugger
else:
tracer.lldb.SBDebugger = original_debugger
self.assertEqual(result["status"], "target-integrity-error")
self.assertIs(result["target_process_created"], False)
def test_journal_checks_exact_byte_budget_before_writing(self):
record = {"kind": "other-stop", "reason": "signal"}
encoded_size = len((tracer.json.dumps(record) + "\n").encode("utf-8"))
stream = BytesIO()
journal = tracer._ObservationJournal(stream, max_bytes=encoded_size - 1)
self.assertFalse(journal.append(record))
self.assertEqual(stream.getvalue(), b"")
self.assertEqual(journal.bytes, 0)
def test_journal_appends_each_row_once_and_flushes_it(self):
class CountingStream(BytesIO):
writes = 0
flushes = 0
def write(self, value):
self.writes += 1
return super().write(value)
def flush(self):
self.flushes += 1
return super().flush()
stream = CountingStream()
journal = tracer._ObservationJournal(stream)
journal.append({"kind": "event", "event": {"sequence": 0}})
journal.append({"kind": "other-stop", "reason": "signal"})
self.assertEqual((stream.writes, stream.flushes), (2, 2))
self.assertEqual(journal.bytes, len(stream.getvalue()))
def test_aggregate_trace_budget_admits_exact_boundary_and_rejects_next_record(self):
self.assertTrue(
tracer._can_retain_trace(
tracer.MAX_TRACE_BYTES - 10,
tracer.MAX_TRACE_FRAMES - 2,
10,
2,
)
)
self.assertFalse(
tracer._can_retain_trace(
tracer.MAX_TRACE_BYTES - 10,
tracer.MAX_TRACE_FRAMES - 2,
11,
2,
)
)
self.assertFalse(
tracer._can_retain_trace(
tracer.MAX_TRACE_BYTES - 10,
tracer.MAX_TRACE_FRAMES - 2,
10,
3,
)
)
def test_oversized_producer_string_is_rejected_before_serialization(self):
self.assertTrue(tracer._fits_trace_budget("method", 1024))
self.assertFalse(tracer._fits_trace_budget("m" * 2048, 1024))
self.assertGreater(
tracer._estimated_json_size("🙂"), len('"🙂"'.encode("utf-8"))
)
def test_launch_flags_preserve_default_debug_and_stop_at_entry(self):
class Launch:
flags = 10
def GetLaunchFlags(self):
return self.flags
def SetLaunchFlags(self, flags):
self.flags = flags
launch = Launch()
tracer._set_launch_flags(launch)
self.assertEqual(launch.flags, 14)
def test_output_pipe_counts_all_bytes_and_keeps_only_the_prefix(self):
with tempfile.TemporaryDirectory() as directory:
fifo = os.path.join(directory, "stdout.fifo")
capture = os.path.join(directory, "stdout.capture")
sink = tracer._OutputPipe(fifo, capture, 5)
sink.start()
sink.mark_launched()
writer = os.open(fifo, os.O_WRONLY)
try:
for index in range(100):
chunk = (b"hello world" if index == 0 else b"x" * 4096)
os.write(writer, chunk)
finally:
os.close(writer)
sink.drain()
sink.close(expected_exit=True)
with open(capture, "rb") as retained:
self.assertEqual(retained.read(), b"hello")
self.assertEqual(sink.bytes, 11 + 99 * 4096)
self.assertTrue(sink.truncated)
self.assertTrue(sink.complete)
def test_output_pipe_reports_incomplete_capture_after_unexpected_close(self):
with tempfile.TemporaryDirectory() as directory:
fifo = os.path.join(directory, "stdout.fifo")
capture = os.path.join(directory, "stdout.capture")
sink = tracer._OutputPipe(fifo, capture, 5)
sink.start()
sink.mark_launched()
sink.close(expected_exit=False)
self.assertFalse(sink.complete)
self.assertTrue(sink.truncated)
def test_selector_location_report_uses_the_requested_method_type(self):
class Symbol:
def IsValid(self):
return True
def GetName(self):
return "+[Greeter shared]"
class FileSpec:
def GetFilename(self):
return "Fixture"
def __str__(self):
return "/tmp/Fixture"
class Module:
def IsValid(self):
return True
def GetFileSpec(self):
return FileSpec()
class Address:
def GetLineEntry(self):
return types.SimpleNamespace(IsValid=lambda: False)
def GetModule(self):
return Module()
def GetSymbol(self):
return Symbol()
def GetFileAddress(self):
return 1
def GetLoadAddress(self, target):
return 2
class Location:
def GetAddress(self):
return Address()
class Breakpoint:
def GetNumLocations(self):
return 1
def GetLocationAtIndex(self, index):
return Location()
report, locations_truncated = tracer._breakpoint_report(
object(),
[[Breakpoint()]],
{
"breakpoints": [
{
"kind": "objc-method",
"selector": "shared",
"method_type": "instance",
}
]
},
)
self.assertEqual(report[0]["location_count"], 0)
self.assertEqual(report[0]["locations"], [])
self.assertFalse(locations_truncated)
def test_breakpoint_report_keeps_all_locations_under_aggregate_budget(self):
class Location:
def __init__(self, index):
self.index = index
def GetAddress(self):
return self.index
class Breakpoint:
def GetNumLocations(self):
return 65
def GetLocationAtIndex(self, index):
return Location(index)
with patch.object(
tracer,
"_location",
side_effect=lambda address, _target: {"address": address, "symbol": None},
), patch.object(tracer, "_wanted", return_value=True):
report, locations_truncated = tracer._breakpoint_report(
object(), [[Breakpoint()]], {"breakpoints": [{}]}
)
self.assertEqual(report[0]["location_count"], 65)
self.assertEqual(len(report[0]["locations"]), 65)
self.assertFalse(locations_truncated)
def test_breakpoint_report_bounds_aggregate_location_json(self):
tracer.lldb.LLDB_INVALID_ADDRESS = -1
symbol_name = (
"-[VeryLongButPlausibleObjectiveCController "
"performTransactionWithRequestIdentifier:accountContext:"
"securityPolicy:completionHandler:]"
)
module_path = (
"/Applications/Enterprise Product.app/Contents/Frameworks/"
"EnterpriseSubsystem.framework/Versions/A/EnterpriseSubsystem"
)
class Symbol:
def IsValid(self):
return True
def GetName(self):
return symbol_name
class FileSpec:
def GetFilename(self):
return "EnterpriseSubsystem"
def __str__(self):
return module_path
class Module:
def IsValid(self):
return True
def GetFileSpec(self):
return FileSpec()
class SourceFileSpec:
def IsValid(self):
return True
def __str__(self):
return source_path
class Address:
def GetLineEntry(self):
if source_path is None:
return types.SimpleNamespace(IsValid=lambda: False)
return types.SimpleNamespace(
IsValid=lambda: True,
GetFileSpec=SourceFileSpec,
GetLine=lambda: 15,
GetColumn=lambda: 3,
)
def GetModule(self):
return Module()
def GetSymbol(self):
return Symbol()
def GetFileAddress(self):
return 0x123456789
def GetLoadAddress(self, target):
return 0x7123456789
class Location:
def GetAddress(self):
return Address()
class Breakpoint:
def GetNumLocations(self):
return 64
def GetLocationAtIndex(self, index):
return Location()
breakpoint_count = 1000
created = [[Breakpoint()] for _ in range(breakpoint_count)]
config = {"breakpoints": [{"kind": "objc-method"}] * breakpoint_count}
for source_path in (None, "/tmp/" + "源🚀" * 3000 + "/calls.pas"):
with self.subTest(source_path_present=source_path is not None):
report, locations_truncated = tracer._breakpoint_report(
object(), created, config
)
retained_bytes = sum(
len(json.dumps(location).encode("utf-8"))
+ (1 if index > 0 else 0)
for row in report
for index, location in enumerate(row["locations"])
)
self.assertTrue(locations_truncated)
self.assertEqual(
sum(row["location_count"] for row in report), 64_000
)
self.assertLess(
sum(len(row["locations"]) for row in report), 64_000
)
self.assertLessEqual(
retained_bytes, tracer.MAX_BREAKPOINT_LOCATION_BYTES
)
if source_path is not None:
self.assertTrue(
any(
location["source_location"]["file_path"] == source_path
for row in report
for location in row["locations"]
)
)
if __name__ == "__main__":
unittest.main()