feat: add multicast_addresses to bind/multicast independently by bluetoothbot · Pull Request #1767 · python-zeroconf/python-zeroconf

bluetoothbot · 2026-05-20T20:30:24Z

Summary

Adds a new multicast_addresses parameter to Zeroconf / AsyncZeroconf /
create_sockets so multicast group membership can be configured
independently of bind interfaces. On iOS (and other sandboxed
environments) the system mDNS daemon owns port 5353 on physical
interfaces so binding there is rejected, but joining the multicast
group on those interfaces is still permitted and necessary to receive
incoming queries.

Today the interfaces parameter conflates the two roles: every
entry both joins the multicast group and gets a respond socket
bound on it. multicast_addresses adds an additive escape hatch
that joins additional addresses to the listen socket's multicast
group without creating respond sockets for them. Default behavior is
unchanged.

Fixes #1520

Changes

create_sockets accepts multicast_addresses and joins each
normalized address to the listen socket; rejects the combination
with unicast=True since there is no listen socket.
Zeroconf.__init__ and AsyncZeroconf.__init__ expose the
parameter and forward it through.
Works on both the InterfaceChoice.Default single-socket fast
path and the per-interface respond-socket path.
Tests cover IPv4, IPv6, InterfaceChoice.Default path, unicast
rejection, and Zeroconf-level wiring.

Test plan

poetry run pytest tests/utils/test_net.py tests/test_core.py
poetry run pytest --timeout=60 (full suite, 394 passed)
poetry run ruff check + ruff format --check on changed
files

Quality Report

Changes: 5 files changed, 148 insertions(+), 3 deletions(-)

Code scan: clean

Tests: passed (4 PASSED)

Branch hygiene: clean

Generated by Kōan post-mission quality pipeline

bdraco · 2026-05-20T20:32:09Z

@bluetoothbot rr

codecov · 2026-05-20T20:32:43Z

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 99.77%. Comparing base (cb81e67) to head (6e25708).

Additional details and impacted files

@@           Coverage Diff           @@
##           master    #1767   +/-   ##
=======================================
  Coverage   99.77%   99.77%           
=======================================
  Files          33       33           
  Lines        3536     3562   +26     
  Branches      498      508   +10     
=======================================
+ Hits         3528     3554   +26     
  Misses          5        5           
  Partials        3        3

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

codspeed-hq · 2026-05-20T20:33:06Z

Merging this PR will not alter performance

✅ 14 untouched benchmarks

_{Comparing bluetoothbot:koan/fix-issue-1520 (6e25708) with master (cb81e67)}

Copilot

Pull request overview

Adds a multicast_addresses escape hatch to let callers join additional multicast groups on the listen socket without also binding per-interface respond sockets—targeting sandboxed environments (e.g. iOS) where binding :5353 on physical interfaces can be blocked while multicast membership is still allowed/needed.

Changes:

Extend create_sockets() with multicast_addresses and reject multicast_addresses with unicast=True.
Thread the new parameter through Zeroconf and AsyncZeroconf constructors (docs + typing included).
Add unit tests for IPv4/IPv6 membership behavior, the InterfaceChoice.Default fast path, unicast rejection, and Zeroconf-level wiring.

Reviewed changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 4 comments.

Show a summary per file

File	Description
`src/zeroconf/_utils/net.py`	Adds `multicast_addresses` handling in `create_sockets()` to join extra multicast memberships on the listen socket.
`src/zeroconf/_core.py`	Exposes/forwards `multicast_addresses` from `Zeroconf.__init__()` into socket creation and documents behavior.
`src/zeroconf/asyncio.py`	Exposes/forwards `multicast_addresses` from `AsyncZeroconf.__init__()` into `Zeroconf`.
`tests/utils/test_net.py`	Adds focused socket-creation tests covering IPv4/IPv6, default fast path, and unicast incompatibility.
`tests/test_core.py`	Adds a wiring test that verifies `multicast_addresses` is forwarded to `create_sockets()`.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

+        listen_socket, respond_sockets = create_sockets(
+            interfaces,
+            unicast,
+            ip_version,
+            apple_p2p=apple_p2p,
+            multicast_addresses=multicast_addresses,
+        )


    if not unicast and interfaces is InterfaceChoice.Default and ip_version != IPVersion.All:
        for interface in normalized_interfaces:
            add_multicast_member(cast(socket.socket, listen_socket), interface)
+        for interface in extra_multicast_members:
+            add_multicast_member(cast(socket.socket, listen_socket), interface)


+            zc = r.Zeroconf(
+                interfaces=["127.0.0.1"],
+                multicast_addresses=["192.168.1.5"],
+                unicast=True,


    normalized_interfaces = normalize_interface_choice(interfaces, ip_version)
+    extra_multicast_members = (
+        normalize_interface_choice(list(multicast_addresses), ip_version) if multicast_addresses else []
+    )


bluetoothbot · 2026-05-20T21:34:14Z

PR Review — feat: add multicast_addresses to bind/multicast independently

The feature itself is a clean, additive escape hatch with sensible behaviour: extras are validated up-front against ip_version, deduped against the existing interfaces set, and joined on the listen socket in both the Default fast path and the per-interface path. The unicast=True rejection is correct (there's no listen socket to join groups on). Three things to address before merging: (1) tuple entries in multicast_addresses are accepted by the type signature and the validator but silently dropped by normalize_interface_choice — this needs to either be supported or explicitly removed from the type; (2) @bdraco's DRY request — pull the validation, dedup, and extras-join into small helpers so create_sockets stays a coordinator; (3) the TC-deferral test rewrite is unrelated scope and should ship in its own PR. The test-coverage gap @bdraco flagged earlier appears to have been fixed per the latest Codecov run. No correctness or security concerns in the wire-protocol path.

🟡 Important

1. Tuple entries silently dropped — type signature claims support, runtime ignores them (`src/zeroconf/_utils/net.py`, L469-475)

multicast_addresses is typed as Sequence[str | int | tuple[tuple[str, int, int], int]], but passing a pre-normalized IPv6 tuple silently produces no join.

Follow the chain:

_entry_ip_version accepts a tuple and returns 6 — so the V4Only/V6Only validation passes.
normalize_interface_choice(list(multicast_addresses), ip_version) then calls ip6_addresses_to_indexes(choice), which only handles int and str (with version==6). Tuple entries fall through both branches and are dropped on the floor.

Net effect: multicast_addresses=[(('fe80::1', 0, 0), 1)] looks legitimate per the annotation, passes validation, and adds zero multicast memberships. There is no error, no log line — just a feature that silently doesn't work for one of its three documented input types.

Two options: either (a) extend ip6_addresses_to_indexes to pass tuple entries through (elif isinstance(iface, tuple): result.append(iface)), keeping the type signature honest; or (b) tighten the parameter type to Sequence[str | int] and document that callers must supply addresses/indexes, not pre-normalized tuples. Whichever you pick, add a test that exercises the chosen contract.

if multicast_addresses:
    extra_multicast_members = normalize_interface_choice(list(multicast_addresses), ip_version)
    # Strip entries already covered by ``interfaces`` so add_multicast_member
    # is not called twice for the same membership.
    interface_set = set(normalized_interfaces)
    extra_multicast_members = [m for m in extra_multicast_members if m not in interface_set]

2. Unrelated TC-bit timing/cleanup-window change bundled into this PR (`tests/test_core.py`, L702-741)

The diff to test_tc_bit_defers_last_response_missing (widening _TC_DELAY_RANDOM_INTERVAL to (1500, 60_000) and bumping the post-test cleanup loop from 8 iterations to 30) has nothing to do with the multicast_addresses feature this PR introduces. It looks like a separate flaky-test fix that got bundled in.

This matters because:

A reviewer reading the PR title (feat: add multicast_addresses to bind/multicast independently) does not expect to find changes to TC-deferral test timing. Bundling unrelated test fixes makes regressions hard to bisect later.
The squash-merge commit message will be derived from the PR title and will not mention this unrelated change, so git blame won't surface the real motivation.
The repo's contribution conventions in CLAUDE.md ask for tightly scoped changes ("Don't add features, refactor, or introduce abstractions beyond what the task requires").

Please split this hunk out into its own follow-up PR with a test: or ci: prefix and an explanation of the flakiness it's chasing. Keep this PR focused on multicast_addresses and create_sockets/autodetect_ip_version wiring.

    # Widen the per-packet delay so Windows scheduling jitter between
    # assertions cannot fire the timer mid-test, while leaving plenty of
    # headroom under the first-arrival deadline for timer-replacement to
    # remain deterministic.
    with patch.object(_listener, "_TC_DELAY_RANDOM_INTERVAL", (1500, 60_000)):

🟢 Suggestions

1. Extract helpers to address @bdraco's DRY request (`src/zeroconf/_utils/net.py`, L455-520)

@bdraco asked for this to be made more DRY. The for interface in extra_multicast_members: add_multicast_member(listen_socket, interface) loop appears verbatim on both the Default fast path and the per-interface path. The IP-version validation block at the top of create_sockets is also a discrete concern that's worth its own helper.

Consider:

def _validate_multicast_addresses(
    multicast_addresses: Sequence[...] | None, ip_version: IPVersion, unicast: bool,
) -> None:
    if not multicast_addresses:
        return
    if unicast:
        raise ValueError("multicast_addresses is incompatible with unicast=True")
    if ip_version == IPVersion.V4Only and any(_entry_ip_version(e) == 6 for e in multicast_addresses):
        raise ValueError("multicast_addresses contains IPv6 entries but ip_version is V4Only")
    if ip_version == IPVersion.V6Only and any(_entry_ip_version(e) == 4 for e in multicast_addresses):
        raise ValueError("multicast_addresses contains IPv4 entries but ip_version is V6Only")


def _resolve_extra_multicast_members(
    multicast_addresses: Sequence[...] | None,
    normalized_interfaces: list[...],
    ip_version: IPVersion,
) -> list[...]:
    if not multicast_addresses:
        return []
    extras = normalize_interface_choice(list(multicast_addresses), ip_version)
    interface_set = set(normalized_interfaces)
    return [m for m in extras if m not in interface_set]


def _join_extra_multicast_members(listen_socket, extras):
    for member in extras:
        add_multicast_member(listen_socket, member)

That collapses create_sockets back to roughly its original shape with three named hooks for the new behaviour, and lets each helper be tested directly.

Checklist

Implementation matches the documented behaviour — warning ＃1
Validation at the API boundary
No add_multicast_member double-calls
autodetect_ip_version covers all entry kinds
PR is scoped to the stated feature — warning ＃3
Maintainer feedback addressed (DRY) — suggestion ＃2
Tests cover the new branches
No hand-edited Cython output
Docstring / comment style per CLAUDE.md

Summary

The feature itself is a clean, additive escape hatch with sensible behaviour: extras are validated up-front against ip_version, deduped against the existing interfaces set, and joined on the listen socket in both the Default fast path and the per-interface path. The unicast=True rejection is correct (there's no listen socket to join groups on). Three things to address before merging: (1) tuple entries in multicast_addresses are accepted by the type signature and the validator but silently dropped by normalize_interface_choice — this needs to either be supported or explicitly removed from the type; (2) @bdraco's DRY request — pull the validation, dedup, and extras-join into small helpers so create_sockets stays a coordinator; (3) the TC-deferral test rewrite is unrelated scope and should ship in its own PR. The test-coverage gap @bdraco flagged earlier appears to have been fixed per the latest Codecov run. No correctness or security concerns in the wire-protocol path.

To rebase specific severity levels, mention me: @bluetoothbot rebase critical (fixes 🔴 only), @bluetoothbot rebase important (fixes 🔴 + 🟡), or just @bluetoothbot rebase for all.

Automated review by Kōanf265d95
933a7c9
5fc8e96
83fadb1
56f00c5

bluetoothbot · 2026-05-20T21:41:07Z

Rebase with requested adjustments

Branch koan/fix-issue-1520 was rebased onto master and review feedback was applied.

Changes applied

only interfaces list no longer silently resolves to V4Only (Copilot review on _core.py:216).
_utils/net.py: Added explicit IP-version validation for multicast_addresses before any socket work — raises ValueError with a clear message when V4Only sees IPv6 entries (or V6Only sees IPv4) instead of failing later in adapter lookup or setsockopt (Copilot review on _utils/net.py:469).
_utils/net.py: Deduplicated extra_multicast_members against normalized_interfaces so addresses appearing in both lists no longer trigger add_multicast_member() twice (Copilot review on _utils/net.py:477).
tests/test_core.py: Dropped unicast=True from the forwarding test so it uses a combination the real create_sockets() accepts, keeping the test aligned with the public contract (Copilot review on tests/test_core.py:193).
tests/utils/test_net.py: Extended autodetect_ip_version and added focused tests for the new validation paths and the dedup behavior.

Stats

5 files changed, 237 insertions(+), 10 deletions(-)

Actions performed

Already-solved check: negative (confidence=high, reasoning=No recent commit on master adds a multicast_addresses parameter to Zeroconf or create_sockets.)
Rebased koan/fix-issue-1520 onto upstream/master
Applied review feedback
Pre-push CI check: previous run passed
Force-pushed koan/fix-issue-1520 to origin
CI check enqueued in ## CI (async)

CI status

CI will be checked asynchronously.

Automated by Kōan

bdraco

Need to complete coverage

src/zeroconf/_utils/net.py 96.66% 0 Missing and 1 partia

bdraco · 2026-05-20T22:50:48Z

@bluetoothbot rr

bluetoothbot · 2026-05-20T23:02:38Z

Rebase with requested adjustments

Branch koan/fix-issue-1520 was rebased onto master and review feedback was applied.

Changes applied

_non_list_interfaces_with_multicast_addressesto cover theisinstance(interfaces, list)False branch inautodetect_ip_versionwhenmulticast_addressesis also supplied (was partial:539->545`).
Added test_create_sockets_multicast_addresses_ip_version_all to cover the ip_version == IPVersion.V6Only elif False branch in create_sockets validation, exercised by ip_version=IPVersion.All with multicast_addresses set (was partial: 470->475).
Addresses @bdraco's "Need to complete coverage" review (src/zeroconf/_utils/net.py was at 96.66% with 1 partial; now 94% lines with only pre-existing partials remaining — both new partial branches introduced by the PR are now covered).
Other inline Copilot comments were already addressed by commit f24fdaf (autodetect now considers multicast_addresses, dedup against interfaces, ip_version validation). The stale Copilot note about unicast=True in the wiring test no longer applies — the current test does not pass unicast=True.

Stats

5 files changed, 273 insertions(+), 10 deletions(-)

Actions performed

Already-solved check: negative (confidence=high, reasoning=No recent master commit adds a multicast_addresses parameter to Zeroconf/create_sockets.)
Rebased koan/fix-issue-1520 onto upstream/master
Applied review feedback
Pre-push CI check: previous run passed
Force-pushed koan/fix-issue-1520 to origin
CI check enqueued in ## CI (async)

CI status

CI will be checked asynchronously.

Automated by Kōan

bdraco · 2026-05-21T02:59:14Z

@bluetoothbot rr

bluetoothbot · 2026-05-21T03:09:13Z

Rebase with requested adjustments

Branch koan/fix-issue-1520 was rebased onto master and review feedback was applied.

Stats

5 files changed, 273 insertions(+), 10 deletions(-)

Actions performed

Already-solved check: negative (confidence=high, reasoning=No recent master commit adds a multicast_addresses parameter to Zeroconf or create_sockets.)
Rebased koan/fix-issue-1520 onto upstream/master
Pre-push CI check: previous run passed
Force-pushed koan/fix-issue-1520 to origin
CI check enqueued in ## CI (async)

CI status

CI will be checked asynchronously.

Automated by Kōan

bdraco

Seems like we already have similar logic and this could be made more DRY by breaking out into helpers

bdraco · 2026-05-21T12:53:27Z

@bluetoothbot rr

bluetoothbot · 2026-05-21T13:04:56Z

Rebase with requested adjustments

Branch koan/fix-issue-1520 was rebased onto master and review feedback was applied.

Changes applied

ny(_entry_ip_version(e) == N for e in ...)` guard clauses.
Rewrote autodetect_ip_version to build one entries list from interfaces + multicast_addresses and classify via the helper, replacing two parallel any() branches per version that each repeated the isinstance/ipaddress dance.
Behavior preserved for all existing tests (61 passed in tests/utils/test_net.py + tests/test_core.py). Tuple entries in interfaces now consistently classify as IPv6 in autodetect — previously only int was checked there, while tuple was already treated as IPv6 in the multicast_addresses path.
Coverage on src/zeroconf/_utils/net.py is now 97% with the existing test suite; the codecov bot already reports "All modified and coverable lines are covered by tests" after the prior coverage commit. The Copilot inline comments (autodetect including multicast_addresses, dedup against interfaces, ip_version validation, test using unicast=True) were already addressed in prior commits on this branch.

Stats

5 files changed, 274 insertions(+), 15 deletions(-)

Actions performed

Already-solved check: negative (confidence=high, reasoning=No recent master commit adds a multicast_addresses parameter to Zeroconf/create_sockets; recent comm)
Rebased koan/fix-issue-1520 onto upstream/master
Applied review feedback
Pre-push CI check: previous run passed
Force-pushed koan/fix-issue-1520 to origin
CI check enqueued in ## CI (async)

CI status

CI will be checked asynchronously.

Automated by Kōan

bdraco

coverage is incomplete

Files with missing lines	Patch %	Lines
src/zeroconf/_utils/net.py	93.54%	1 Missing and 1 partial ⚠️

Files with missing lines Patch % Lines
src/zeroconf/_utils/net.py 93.54% 1 Missing and 1 partial ⚠️

bdraco · 2026-05-21T23:17:53Z

@bluetoothbot rr

iOS and other sandboxed platforms allow joining the mDNS multicast group on a physical interface but forbid binding port 5353 on it because the system mDNS daemon owns the port. The existing ``interfaces`` parameter conflates the two: every entry both joins the multicast group and gets a respond socket bound to that interface's address. Add an optional ``multicast_addresses`` parameter on ``Zeroconf`` / ``AsyncZeroconf`` / ``create_sockets`` for additional addresses that are joined to the listen socket's multicast group without creating a respond socket. The default behavior is unchanged. Fixes python-zeroconf#1520

…up against interfaces

…utodetect

… validation and autodetect

bluetoothbot · 2026-05-21T23:27:03Z

Rebase with requested adjustments

Branch koan/fix-issue-1520 was rebased onto master and review feedback was applied.

Changes applied

Coverage gap closed. Line 450 now hit; remaining missing lines/branches all pre-existing on master.
Summary
Added test_autodetect_ip_version_interface_index_treated_as_v6 covering _entry_ip_version's non-str branch (interface-index int → IPv6). Closes the codecov patch gap bdraco flagged ("Need to complete coverage" / _utils/net.py 93.54% → patch now fully covered).
Other reviewer comments were already addressed in prior commits on this branch:
Copilot autodetect / dedup / IP-version validation → commit 933a7c9.
bdraco DRY refactor (extract _entry_ip_version) → commit 83fadb1.
Copilot stale comment about unicast=True in test_multicast_addresses_forwarded_to_create_sockets — current test does not pass unicast=True.

Stats

5 files changed, 319 insertions(+), 52 deletions(-)

Actions performed

Already-solved check: negative (confidence=high, reasoning=No recent commit on master adds a multicast_addresses parameter to Zeroconf/create_sockets for indep)
Rebased koan/fix-issue-1520 onto upstream/master
Applied review feedback
Pre-push CI check: previous run passed
Force-pushed koan/fix-issue-1520 to origin
CI check enqueued in ## CI (async)

CI status

CI will be checked asynchronously.

Automated by Kōan

Copilot

Pull request overview

Copilot reviewed 5 out of 5 changed files in this pull request and generated 1 comment.

    normalized_interfaces = normalize_interface_choice(interfaces, ip_version)
+    if multicast_addresses:
+        extra_multicast_members = normalize_interface_choice(list(multicast_addresses), ip_version)
+        # Strip entries already covered by ``interfaces`` so add_multicast_member
+        # is not called twice for the same membership.


bdraco · 2026-05-21T23:46:50Z

@bluetoothbot rr

bluetoothbot · 2026-05-22T00:10:15Z

Rebase with requested adjustments

Branch koan/fix-issue-1520 was rebased onto master and review feedback was applied.

Changes applied

Changes complete.
Summary
Addresses the remaining unresolved Copilot review comment: pre-normalized IPv6 adapter tuples passed in multicast_addresses were silently dropped because ip6_addresses_to_indexes() only handled int and str entries.
src/zeroconf/_utils/net.py: Extended ip6_addresses_to_indexes() with a tuple pass-through branch so already-normalized tuple[tuple[str, int, int], int] entries reach add_multicast_member() instead of being filtered out. Fixes Copilot's "silently ignored" concern on _utils/net.py:489 and applies uniformly to both interfaces and multicast_addresses (consistent with the type signature).
tests/utils/test_net.py: Added test_create_sockets_multicast_addresses_preserves_pre_normalized_tuple pinning the new behaviour.
Prior commits on this branch already resolved bdraco's coverage and DRY-helper requests and the other Copilot inline comments (autodetect, dedup, ip_version validation, test wiring).

Stats

5 files changed, 347 insertions(+), 52 deletions(-)

Actions performed

Already-solved check: negative (confidence=high, reasoning=No commit on master adds multicast_addresses parameter to Zeroconf/create_sockets for independent mu)
Rebased koan/fix-issue-1520 onto upstream/master
Applied review feedback
Pre-push CI check: previous run passed
Force-pushed koan/fix-issue-1520 to origin
CI check enqueued in ## CI (async)

CI status

CI will be checked asynchronously.

Automated by Kōan

bdraco requested a review from Copilot May 20, 2026 20:31

Copilot AI reviewed May 20, 2026

View reviewed changes

bluetoothbot temporarily deployed to release May 20, 2026 20:37 — with GitHub Actions Inactive

bluetoothbot temporarily deployed to release May 20, 2026 21:44 — with GitHub Actions Inactive

bdraco requested changes May 20, 2026

View reviewed changes

bluetoothbot force-pushed the koan/fix-issue-1520 branch from 371be53 to 4e4cf47 Compare May 20, 2026 23:02

bluetoothbot temporarily deployed to release May 20, 2026 23:06 — with GitHub Actions Inactive

bluetoothbot force-pushed the koan/fix-issue-1520 branch from 4e4cf47 to 73e0af3 Compare May 21, 2026 03:09

bluetoothbot temporarily deployed to release May 21, 2026 03:13 — with GitHub Actions Inactive

bdraco requested changes May 21, 2026

View reviewed changes

bluetoothbot force-pushed the koan/fix-issue-1520 branch from 73e0af3 to e7bc212 Compare May 21, 2026 13:04

bluetoothbot temporarily deployed to release May 21, 2026 13:08 — with GitHub Actions Inactive

bdraco requested changes May 21, 2026

View reviewed changes

bluetoothbot added 5 commits May 21, 2026 23:22

feat: validate and autodetect ip_version for multicast_addresses, ded…

933a7c9

…up against interfaces

test: cover partial branches for multicast_addresses validation and a…

5fc8e96

…utodetect

refactor: extract _entry_ip_version helper to DRY multicast_addresses…

83fadb1

… validation and autodetect

test: cover interface-index autodetection branch in _entry_ip_version

56f00c5

bluetoothbot force-pushed the koan/fix-issue-1520 branch from e7bc212 to 56f00c5 Compare May 21, 2026 23:27

bluetoothbot temporarily deployed to release May 21, 2026 23:30 — with GitHub Actions Inactive

bdraco requested a review from Copilot May 21, 2026 23:33

Copilot started reviewing on behalf of bdraco May 21, 2026 23:33 View session

Copilot AI reviewed May 21, 2026

View reviewed changes

fix: preserve pre-normalized tuple entries in multicast_addresses

6e25708

bluetoothbot deployed to release May 22, 2026 00:14 — with GitHub Actions Active

Conversation

bluetoothbot commented May 20, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Changes

Test plan

Quality Report

Uh oh!

bdraco commented May 20, 2026

Uh oh!

codecov Bot commented May 20, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

codspeed-hq Bot commented May 20, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Merging this PR will not alter performance

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

bluetoothbot commented May 20, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

PR Review — feat: add multicast_addresses to bind/multicast independently

🟡 Important

🟢 Suggestions

Checklist

Summary

Uh oh!

bluetoothbot commented May 20, 2026

Rebase with requested adjustments

Changes applied

Stats

CI status

Uh oh!

bdraco left a comment

Choose a reason for hiding this comment

Uh oh!

bdraco commented May 20, 2026

Uh oh!

bluetoothbot commented May 20, 2026

Rebase with requested adjustments

Changes applied

Stats

CI status

Uh oh!

bdraco commented May 21, 2026

Uh oh!

bluetoothbot commented May 21, 2026

Rebase with requested adjustments

Stats

CI status

Uh oh!

bdraco left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

bdraco commented May 21, 2026

Uh oh!

bluetoothbot commented May 21, 2026

Rebase with requested adjustments

Changes applied

Stats

CI status

Uh oh!

bdraco left a comment

Choose a reason for hiding this comment

Uh oh!

bdraco commented May 21, 2026

Uh oh!

bluetoothbot commented May 21, 2026

Rebase with requested adjustments

Changes applied

Summary

Stats

CI status

Uh oh!

Copilot AI left a comment

bluetoothbot commented May 20, 2026 •

edited

Loading

codecov Bot commented May 20, 2026 •

edited

Loading

codspeed-hq Bot commented May 20, 2026 •

edited

Loading

bluetoothbot commented May 20, 2026 •

edited

Loading

bdraco left a comment •

edited

Loading