Skip to content

Commit b5a8038

Browse files
committed
prepare release
1 parent a49a047 commit b5a8038

2 files changed

Lines changed: 257 additions & 1 deletion

File tree

‎CHANGELOG.rst‎

Lines changed: 256 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,262 @@
22
Changelog for package behaviortree_cpp
33
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
44

5+
Forthcoming
6+
-----------
7+
* reject trailing characters in SwitchNode numeric comparison (`#1178 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/1178>`_)
8+
* Pin ament install destinations to lib/include/bin (fixes `#1175 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/1175>`_) (`#1176 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/1176>`_)
9+
The ROS build farm (bloom/debhelper) configures with
10+
-DCMAKE_INSTALL_LIBDIR=lib/<multiarch-triplet>. Since `#1152 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/1152>`_ made the
11+
BTCPP\_*_DESTINATION variables honor GNUInstallDirs, farm binaries
12+
installed libbehaviortree_cpp.so to /opt/ros/<distro>/lib/x86_64-linux-gnu,
13+
which breaks ament_export_libraries lookup in downstream packages and is
14+
not on the LD_LIBRARY_PATH set by the ament environment hooks.
15+
Shadow the cache variables with plain set() in the ament build path, so
16+
ROS builds always install to $prefix/lib regardless of
17+
CMAKE_INSTALL_LIBDIR, while standalone builds keep the GNUInstallDirs
18+
override behavior introduced for `#1120 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/1120>`_.
19+
Also add a ros2-lyrical CI job that emulates the build farm flags and
20+
asserts the library lands in $prefix/lib.
21+
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
22+
* fix out-of-bounds read in Groot2 hook insert handler (`#1170 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/1170>`_)
23+
* fix out-of-bounds read in Groot2 hook insert handler
24+
* exclude Parallel.FailingParallel from macOS CI test run
25+
* Add scripted return status support for TestNode mocks (`#1169 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/1169>`_)
26+
Introduce `return_status_script` on TestNodeConfig, allowing a mock's
27+
completion status to be computed at runtime from blackboard state instead
28+
of being fixed. When set, it takes precedence over `return_status`; it may
29+
reference the NodeStatus names (SUCCESS/FAILURE/...) and is rejected if it
30+
resolves to IDLE.
31+
The NodeStatus enum names are injected only into the return_status_script
32+
environment. The pre-existing success_script/failure_script/post_script
33+
continue to evaluate against the node's own enums, so a blackboard entry
34+
named like a status (e.g. "SUCCESS") is not shadowed.
35+
To pay the ABI break only once, TestNode's state is moved behind a PImpl,
36+
so future changes to it no longer alter the layout consumers link against
37+
(mirroring StatusChangeLogger). The new return_status_script field is
38+
appended at the end of TestNodeConfig, preserving the byte offsets of the
39+
existing fields.
40+
Also add JSON validation rejecting a TestNodeConfig with neither a
41+
return_status nor a return_status_script, and a tutorial example
42+
(t15_nodes_mocking_strict_failure) demonstrating the strict-failure flow.
43+
Addresses `#995 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/995>`_.
44+
Co-authored-by: Pepe <pepe@ross-robotics.co.uk>
45+
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
46+
* Fix ROOT blackboard export in Groot2 publisher (`#1132 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/1132>`_) (`#1168 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/1168>`_)
47+
When a subtree's blackboard is backed by a separate root blackboard
48+
(e.g. created via `Blackboard::create(external_root)` to expose `@`
49+
globals), the Groot2 publisher never exported those root entries, so
50+
they were invisible in Groot2. Export the root blackboard under the
51+
reserved name `ROOT` whenever a requested subtree resolves to a
52+
distinct root blackboard.
53+
- Deduplicate the `ROOT` payload when several subtrees share the same
54+
root blackboard.
55+
- Return the dump as `Expected<>` and send an error reply for
56+
ambiguous requests: a subtree literally named `ROOT`, or a request
57+
spanning multiple distinct root blackboards.
58+
- Add functional coverage to gtest_groot2_publisher_integration.cpp
59+
using the shared Groot2Test helpers (makePublisher/Client).
60+
- Enable `/utf-8` for behaviortree_cpp_test on MSVC so the Unicode
61+
name-validation tests build on Windows.
62+
Closes `#1130 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/1130>`_
63+
Co-authored-by: magic-alt <zaqwerss@outlook.com>
64+
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
65+
* Add macOS CI and fix Apple libc++ build (`#1167 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/1167>`_)
66+
* Add macOS build to CI
67+
Add a Conan + CMake workflow running on macos-latest (Apple Silicon,
68+
AppleClang + libc++). This exercises the Apple standard-library toolchain
69+
that other CI jobs (Ubuntu/GCC, Windows/MSVC, conda/Clang) do not, catching
70+
Apple-specific breakage such as the missing floating-point std::from_chars.
71+
The job mirrors the existing cmake_ubuntu.yml Conan flow (conan install ->
72+
cmake --preset conan-release -> ctest), pinning compiler.cppstd=17 as the
73+
Windows job does.
74+
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
75+
* Fix Apple libc++ build: guard floating-point std::from_chars
76+
Apple's libc++ deletes the floating-point std::from_chars overload (and
77+
undefines __cpp_lib_to_chars), so the unguarded double parse in
78+
recursivelyCreateSubtree fails to compile on macOS. This is the same code
79+
path the new cmake_macos.yml CI job exercises, so guard it here to keep that
80+
job green.
81+
Introduce parseDoubleStrict(), which uses std::from_chars where available and,
82+
where it is not (Apple libc++), falls back to strtod_l with a "C" locale
83+
created once. Unlike setlocale(), this does not mutate process-global state,
84+
so it is thread-safe. A small guard rejects the inputs strtod would accept but
85+
std::from_chars(general) rejects -- leading whitespace, a leading '+', and hex
86+
floats -- so the parsed blackboard-entry type is identical on every platform.
87+
Verified byte-for-byte against std::from_chars over a battery of inputs
88+
(including "+1.5", " 1.5", "0x1p4", "1.", ".5", inf/nan, overflow/underflow).
89+
The integer std::from_chars just above is available on Apple libc++ and is
90+
left unchanged.
91+
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
92+
* CI: install Conan via Homebrew on macOS
93+
turtlebrowser/get-conan runs `pip3 install`, which fails on macOS runners with
94+
PEP 668 (externally-managed-environment). Use `brew install conan` instead,
95+
which provides Conan 2.x without touching the system Python.
96+
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
97+
* Fix convertFromString<double/float> error type on Apple libc++
98+
On platforms without floating-point std::from_chars (Apple libc++), the
99+
fallback used std::stod but let its std::invalid_argument/out_of_range escape,
100+
whereas the from_chars path throws BT::RuntimeError. This made
101+
BasicTypes.ConvertFromString_Double fail on macOS (it expects RuntimeError for
102+
"not_a_number"). The throw also skipped the setlocale restore, leaking the "C"
103+
locale process-wide. Wrap stod in try/catch: restore the locale and rethrow as
104+
RuntimeError on both success and failure paths.
105+
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
106+
* CI: macOS diagnostics for remaining test failures (temporary)
107+
Add --output-on-failure and an lldb backtrace step (on failure) to capture
108+
assertion messages and stack traces for the macOS-only segfaults/timeouts.
109+
To be removed once those are fixed.
110+
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
111+
* Fix macOS segfault: don't touch child in DelayNode destructor
112+
~DelayNode called halt(), which via DecoratorNode::halt() -> resetChild()
113+
dereferences the child node (child_node\_->status()). During Tree destruction
114+
nodes are owned by a flat std::vector<TreeNode::Ptr> whose element-destruction
115+
order is unspecified: libstdc++ tears down front-to-back (child outlives the
116+
decorator) but libc++ back-to-front (child destroyed first). On libc++ (macOS)
117+
the child is already gone, so status() locks a mutex through a null PImpl and
118+
segfaults. This crashed every tree containing a <Delay> node on macOS
119+
(Decorator.DelayWithXML and the Substitution Issue930 tests).
120+
Only cancel the timer in the destructor, mirroring TimeoutNode's destructor,
121+
which already does exactly this. The halt() method is unchanged for normal
122+
(non-destruction) halting.
123+
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
124+
* CI: retry timing-flaky tests on macOS (--repeat until-pass:3)
125+
The shared macOS runners cannot reliably meet several tests' tight wall-clock
126+
tolerances (e.g. elapsed 222 vs 200 ms), and the failing set varies run to run.
127+
Retry to absorb the flakiness without loosening assertions on other platforms.
128+
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
129+
* tests: widen timing tolerances on macOS (platform-gated)
130+
The shared macOS CI runners are much slower/noisier than Linux/Windows, so a
131+
few tests with tight wall-clock tolerances fail there (not library bugs). Gate
132+
the tolerances behind __APPLE_\_ so other platforms keep the strict values:
133+
- gtest_coroutines: scale the sub-50ms action/timeout durations by 5x on macOS
134+
(only relative ordering matters), so the timeout reliably fires between the
135+
short and long actions instead of racing scheduling jitter.
136+
- gtest_parallel PauseWithRetry: widen margin_msec 80 -> 250 on macOS
137+
(observed overshoot was 130-150ms).
138+
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
139+
* CI: bump macOS test retries to until-pass:5
140+
A couple of timing tests (Parallel.Issue819, SwitchTest.CaseSwitchToDefault)
141+
are flaky under runner load rather than consistently over a single tolerance,
142+
so retry a bit more to absorb that.
143+
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
144+
* CI: exclude timing-flaky tests on macOS; drop lldb diagnostic
145+
The shared macOS runners are too slow/noisy to reliably meet the tight
146+
wall-clock tolerances in ~11 tests (a rotating subset fails each run). They are
147+
not macOS-specific logic and keep running on Linux and Windows, so exclude them
148+
on macOS with ctest -E to make the job deterministic. --repeat until-pass:3
149+
absorbs residual flakiness in the rest. The __APPLE_\_-gated tolerances added
150+
earlier (gtest_coroutines, gtest_parallel) remain so these can be re-enabled
151+
here later.
152+
Also remove the temporary lldb backtrace step now that the DelayNode
153+
destruction segfault is fixed.
154+
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
155+
* Revert macOS timing-margin edits; rely on exclusion only
156+
Since the timing-sensitive tests are excluded on macOS (ctest -E), there is no
157+
reason to also widen their wall-clock tolerances. Restore gtest_coroutines.cpp
158+
and gtest_parallel.cpp to their original values so the shared tests stay
159+
pristine for every platform, and drop the stale workflow comment that mentioned
160+
the __APPLE_\_-gated tolerances.
161+
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
162+
* Simplify: dedup convertFromString double/float Apple fallback
163+
/simplify cleanup. The macOS (no floating-point std::from_chars) fallback was
164+
duplicated between convertFromString<double> and <float>, each restoring the
165+
locale twice (catch + fall-through). Extract a single guarded file-local helper
166+
stodClassicLocale() with an RAII locale-restore, so the fallback lives in one
167+
place and the restore happens on every path without the duplicated try/catch.
168+
Behavior is unchanged (still stod under a temporary "C" locale, still throws
169+
RuntimeError on bad input).
170+
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
171+
* Unify double parsing into a single BT::parseDouble primitive
172+
Previously the "parse a double locale-independently" logic existed in two
173+
divergent forms: xml_parsing.cpp's parseDoubleStrict (from_chars, or strtod_l +
174+
"C" locale on Apple libc++ -- thread-safe, strict) and basic_types.cpp's
175+
convertFromString<double>/<float> Apple fallback (stod + global setlocale --
176+
thread-unsafe, lenient). They also disagreed on Apple: convertFromString
177+
accepted leading '+'/whitespace/hex that std::from_chars (and thus the other
178+
platforms) reject.
179+
Extract one shared BT::parseDouble(str, out, require_full_consumption) that both
180+
build on:
181+
- xml_parsing passes require_full_consumption=true (strict full-string check,
182+
so compound values like "2.2;2.4" stay strings).
183+
- convertFromString<double>/<float> pass false (lenient, matching the previous
184+
from_chars behavior of accepting trailing characters).
185+
The single implementation uses std::from_chars where available and the
186+
thread-safe strtod_l + static "C" locale fallback otherwise, reproducing
187+
from_chars(general) semantics exactly (verified against std::from_chars over a
188+
battery of inputs, both modes). This removes the duplicated fallback and the
189+
thread-unsafe setlocale path from basic_types.cpp. On Apple, convertFromString
190+
now rejects '+'/whitespace/hex, matching Linux/Windows.
191+
convertFromString<float> keeps std::from_chars<float> on platforms that have it
192+
(preserving float-range semantics) and uses parseDouble only on the fallback.
193+
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
194+
---------
195+
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
196+
* test(test_node): cover script enum resolution (`#1166 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/1166>`_)
197+
* Fix Groot2 publisher thread safety and hook handling (`#1165 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/1165>`_)
198+
* Fix Groot2 publisher thread safety
199+
* Simplify Groot2 publisher thread-safety machinery
200+
Apply code-review cleanups to the thread-safety fix:
201+
- Extract the duplicated callback drain-gate (CallbackState/CallbackGuard
202+
and HookCallbackState/HookCallbackGuard were byte-identical) into a
203+
single shared BT::details::CallbackGate in utils/callback_gate.h.
204+
notify_all() now fires only when a drain is actually waiting.
205+
- Replace the 69-line injected hook lambda and its immediately-invoked
206+
inner lambda with PImpl::runHook(). The BREAKPOINT_REACHED message is
207+
now built and sent without holding hook->mutex, and only the ZMQ send
208+
holds publisher_mutex.
209+
- Drop the Hook::removed tombstone from the public protocol header:
210+
with the single lock order established (hooks_map_mutex before
211+
hook->mutex), enableAllHooks() and HOOKS_DUMP traverse the maps under
212+
hooks_map_mutex, so no stale snapshot can resurrect an erased hook and
213+
'enabled = false' suffices for stale callback copies.
214+
- GET_TRANSITIONS: swap the transitions buffer out under status_mutex
215+
and serialize outside the lock the status callback contends on.
216+
- Call unsubscribeFromTreeChanges() in the destructors of the five other
217+
StatusChangeLogger subclasses; the base-class destructor call runs too
218+
late to protect derived state, so each dtor must drain callbacks first.
219+
- Deduplicate the hook-JSON literals in the Groot2 tests into
220+
Groot2Test::makeHook(); use make_unique for PImpl; rely on CTAD for
221+
lock guards in touched code.
222+
Verified: 495/495 tests (Release), 499/499 under TSan with the CI
223+
suppressions file, zero ThreadSanitizer warnings.
224+
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
225+
* Extend TSan suppressions to statically linked ZeroMQ
226+
CI builds zmq from source with Conan and links it statically, so the
227+
module-based rule 'race:libzmq.so' does not match and zmq-internal
228+
false positives (encoder_base_t::encode, msg_t::close) fail the
229+
Groot2 hook tests. Match the zmq namespace instead, which works
230+
regardless of how the library is linked.
231+
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
232+
* Move StatusChangeLogger state behind a PImpl
233+
StatusChangeLogger is the base class of a public extension point: every
234+
logger, including user-defined ones, embeds its layout. The thread-safety
235+
fix already changes that layout (and, being header-only, the old inlined
236+
implementation survives in consumer binaries even after a library
237+
upgrade), so take the opportunity to pay the ABI break only once:
238+
- all data members move into a PImpl defined in the new
239+
src/loggers/abstract_logger.cpp
240+
- the member functions are no longer inline, so future behavior fixes in
241+
this class can ship as an ABI-compatible library update
242+
Adding or changing state in StatusChangeLogger no longer affects the
243+
layout derived classes compile against. Note that changing its virtual
244+
interface would still break ABI.
245+
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
246+
---------
247+
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
248+
* fix undefined float-to-integer cast at the numeric limit boundary (`#1162 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/1162>`_)
249+
* fix out-of-bounds read in isBlackboardPointer whitespace trim (`#1161 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/1161>`_)
250+
Co-authored-by: Davide Faconti <davide.faconti@gmail.com>
251+
* Fix package share path API for newer ament_index_cpp (`#1163 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/1163>`_)
252+
* Fix package share path API for newer ament_index_cpp
253+
* Style: format package share path update
254+
---------
255+
Co-authored-by: Davide Faconti <davide.faconti@gmail.com>
256+
* Fix WakeUp test flakiness by using steady_clock (`#1164 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/1164>`_)
257+
The `WakeUp.BasicTest` previously used `system_clock`, which is not monotonic and can be affected by system time adjustments (NTP, DST). This made the test susceptible to flaky failures.
258+
This change switches to `steady_clock` for robust, monotonic time measurement. Additionally, the assertion threshold is increased from `25ms` to `100ms` to provide adequate headroom for scheduler jitter, especially on loaded CI environments.
259+
* Contributors: Aysha Afrah Ziya, Davide Faconti, Maurice Alexander Purnawan, pepeRossRobotics
260+
5261
4.9.1 (2026-07-06)
6262
------------------
7263
* Merge pull request `#1139 <https://github.com/BehaviorTree/BehaviorTree.CPP/issues/1139>`_ from mini-1235/patch-3

‎CMakeLists.txt‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
cmake_minimum_required(VERSION 3.16.3) # version on Ubuntu Focal
22

3-
project(behaviortree_cpp VERSION 4.9.1 LANGUAGES C CXX)
3+
project(behaviortree_cpp VERSION 4.10.0 LANGUAGES C CXX)
44

55
# create compile_commands.json
66
set(CMAKE_EXPORT_COMPILE_COMMANDS ON)

0 commit comments

Comments
 (0)