Carries the in-process rekey continuity test and the retirement of the
three rekey Docker suites onto the XX line.
The continuity test was written against master's IK handshake, where the
responder decided rekey-versus-fresh-dial from session age and the test
had to backdate both sessions past a 30s acceptance gate. Here the
responder classifies from the rekey marker the initiator declares in its
msg3 negotiation TLV and reads no clock at all, so the backdating is
dropped: it would age the session past nothing, and leaving it in would
tell a reader a gate exists that does not.
Checked that the test still discriminates rather than merely observing a
session index change. Suppressing the declaration so the responder falls
back to the cross-connection path reds the post-cutover assertion in 8 of
16 runs, which is the address-ordering coin flip the original data-plane
drop had; the healthy tree is 0 of 16 red. The 30s backdate makes no
difference to either rate, which is what confirms it was vestigial here.
The suite wiring keeps mixed-profile, which master does not have, and
drops the three rekey suites from the local suite list, the runner
functions, the default flow, the --only dispatch and the GitHub matrix
together, so check-ci-parity.sh stays green at 23 legs a side. The
retirement note is retargeted at this branch's coverage: the establish
decision tests live in src/proto/fmp/tests/core.rs and src/peer/machine.rs
here, not in the establish_chartests.rs file master keeps.
The three rekey integration suites (rekey, rekey-accept-off,
rekey-outbound-only) are dropped from both runners. Their coverage now
lives in fast, deterministic in-process tests:
- rekey timing and choreography (trigger, K-bit cutover, drain, jitter,
guards) in the sans-IO poll_rekey tests (proto/fsp, proto/fmp);
- data-plane continuity across a real cutover in
rekey_cutover_preserves_data_plane (a real IK rekey over loopback);
- the accept-off dual-init regression and the udp.outbound_only rekey
loop in the should_admit_msg1 and dual-init characterization tests.
Drop them from both runners in lockstep so the parity guard stays green,
and record the retirement in the deliberately-not-run block with a pointer
to the standalone runner. The rekey-test.sh script stays on disk.
The inbound max_peers early-gate in handle_msg1 (silent-drop a Msg1 from
a net-new identity at saturation, send no Msg2, admit no peer) is
unit-tested over a real UDP socket by
handle_msg1_silent_drops_at_cap_for_new_peer in src/node/tests/unit.rs:
it saturates a node, sends a Msg1 from a fresh identity, and polls the
sender socket to assert no Msg2 comes back — the same wire-observable
discriminator the Docker suite's tcpdump used — with a sibling test for
the existing-peer bypass. That is a deterministic superset of the Docker
packet-capture assertion.
Drop it from both runners in lockstep (its *_SUITES array, run function,
default-flow loop, --only dispatch arm, and the GitHub matrix leg with
its steps) so the parity guard stays green, and record the retirement in
the deliberately-not-run block with a pointer to the standalone runner.
The admission-cap-test.sh script stays on disk and runs by hand.
The ACL admission decision is exhaustively unit-tested per npub over real
loaded allow/deny files (src/node/acl.rs test module: allow-match-wins,
allowlist-miss falls through, deny-only, deny-all, allow_all override,
deny-after-allowlist-miss), and the inbound and outbound handshake-
admission paths are covered in-process over the loopback transport
(src/node/tests/acl.rs: inbound msg1 denial, outbound denial, reload).
The Docker suite's only unique coverage was admission over a real UDP
transport, which every other real-transport suite already exercises, and
its operator-facing log assertion.
Drop it from both runners in lockstep (its *_SUITES array, run function,
default-flow call, --only dispatch arm, and the GitHub matrix leg with
its steps) so the parity guard stays green, and record the retirement in
the deliberately-not-run block with a pointer to the standalone runner.
The testing/acl-allowlist/ suite stays on disk and runs by hand.
smoke-10 was a no-stressor 10-node tree-convergence sanity check (netem
off, no ping). Its subject, spanning-tree convergence and root election,
is now covered in-process, faster and deterministically, by the loopback
spanning-tree harness (src/node/tests/spanning_tree.rs: ring, star,
chain, 100-node and disconnected-component convergence) plus end-to-end
datagram delivery (src/node/tests/forwarding.rs). Real-UDP convergence
smoke still runs via static-mesh and the other scenarios' baseline
assertions, so no Docker coverage is lost.
Drop it from both runners in lockstep (the CHAOS_SUITES list and the
GitHub chaos matrix) so the parity guard stays green, delete the scenario
YAML, and update the chaos README.
Bring the six retired cost-based parent-selection chaos scenarios up to
next, resolving the ci-local.sh suite-list conflict (next carries the extra
mixed-profile and admission-cap suites). next already has the equivalent
sans-IO cost and transport-drop coverage, so src is unchanged; this takes
only the scenario removals and the CI-list, README and comment updates.
Bring up the retirement of the six cost-based parent-selection chaos
scenarios (cost-reeval, cost-avoidance, cost-stability, depth-vs-cost,
mixed-technology, bottleneck-parent), which tested a decision the Docker
harness could not exercise reliably.
master already carries the equivalent sans-IO coverage in
src/proto/stp/tests (effective-depth cost selection, hysteresis, cost
degradation) and its transport-drop tests, so this keeps master's src
unchanged and takes only the scenario removals and the CI-list, README and
scenario-comment updates from maint.
The cost-selection chaos scenarios (cost-reeval, cost-avoidance,
cost-stability, depth-vs-cost, mixed-technology, bottleneck-parent) tested
TreeState::evaluate_parent's decision logic through a Docker mesh that could
not exercise it reliably: the tree roots at whichever node holds the smallest
NodeAddr, MMP link costs take several measurement windows to settle, and the
parent hold-down plus hysteresis timing all confound the outcome. A
deterministic link-cost flap still produced zero periodic parent switches in a
full run.
Replace those six scenarios with deterministic unit tests in src/tree/tests.rs
that drive evaluate_parent directly: cheaper-link selection at equal depth,
switch-on-cost-change, hysteresis suppressing a marginal change while allowing
a significant one, and the depth-versus-cost effective-depth tradeoff. Each is
constructed so that breaking the cost or hysteresis logic makes it fail.
The congestion kernel-drop signal (SO_RXQ_OVFL) cannot be provoked
deterministically in Docker: a fresh daemon reader keeps up with
container-speed traffic, so the socket receive queue never overflows (an
unshaped run with a 4 KB buffer and heavy traffic recorded zero drops on every
node). Extract the drop-detection edge -- read the cumulative counter, fire an
event only on the transition into a new drop burst -- into
TransportDropState::observe_drops and unit-test it directly. congestion-stress
keeps its ECN and MMP congestion-signal assertions, which do need the real
shaped bottleneck queue.
Remove the retired scenarios from both CI runners and update the chaos README.
A bash function returns its last command's status, so one ending in a log
call returns 0 whatever it did, and a caller written as `if func` or
`func || fail` has a gate that cannot fire. This tree found two in one
day: run_chaos ended in record, making every chaos row unconditionally
green since 2026-03-09, and build_fips_for_e2e ended in log, letting five
end-to-end legs test the previous commit's binary and report green. Both
were repaired one at a time. This is the rule that catches the next one.
What it enforces is a contract, not a bug hunt: a function whose status a
caller tests must end in an explicit return rather than leaving its
success value to whatever the last log call produced. That distinction is
deliberate and worth stating, because all three instances found in the
tree were benign — each failure path already returned early, so the
trailing echo reported a real success. Reading the function is the only
way to know that, and the next edit that puts an unguarded command before
the final log converts the benign shape into the defect with nothing to
notice. An explicit return costs a line and makes the class unreachable.
The three are given one here.
Scoped on the call sites rather than the definitions, the same way
check-log-strings.py scopes on what a grep reads rather than what its file
mentions: 315 functions scanned, 42 end in a log call, and only the ones
whose status something consumes are reported. A function that ends by
reporting and is called for its output is idiomatic and is left alone.
Without that scoping the finding list would be 42 long and would stop
being read.
Validated by construction rather than by a green run: injecting a copy of
build_fips_for_e2e's exact shape — unguarded docker cp, then a log as the
last statement, with a `|| { ...; return 1; }` caller — makes the checker
report it and exit 1.
Wired into both runners beside the parity and log-string checks.
wait_until_connected decides whether every static suite proceeds or
gives up, so a regression in it turns those suites' verdicts into noise.
Its unit tests existed and were invoked by nothing.
Wire them into ci-local.sh beside the parity and log-string checks,
above the mode branches so --only and --test-only are gated too, and add
the matching step to the ci-parity job in ci.yml. Putting them in one
runner only would create exactly the drift check-ci-parity.sh exists to
catch, and neither placement is visible to that checker since this is not
a matrix suite.
Verified by breaking what it guards rather than by observing green:
setting wait_until_connected's default near-converged slack to 0 fails
case4, records FAIL wait-converge, and exits the sweep 1. Restored after.
They pass, which nothing had established before — 13 assertions, all
green. They also take about 45 seconds rather than the "a few seconds"
the header claimed, and nothing had contradicted that claim because no
runner had ever invoked it. Header corrected with the measurement.
The orphan sweep this called for is done and there are now no
zero-reference *-test.sh files under testing/. It also settles a
disagreement recorded between the audit and the task file: ecn-ab-test.sh
is invoked by nothing, its one reference being a README description
rather than a driver, so the audit was right and the earlier sweep wrong
to call it a documented manual tool. interop-test.sh does have a driver
in interop-stress.sh and iperf-test.sh one in iperf-compare-refs.sh, so
those two were correctly classified.
Access layer for phones and laptops to reach FIPS routers on OpenWrt,
stacked on the 802.11s mesh backhaul from #123. Squashed from five
commits by Arjen (Origami74); their original messages follow.
* feat(openwrt): open !FIPS access SSID — fips-ap-setup helper, default transport binding, how-to
Client access layer for phones and laptops: every FIPS router
broadcasts the same open SSID ('!FIPS' — the leading '!' sorts it to
the top of alphabetically ordered network pickers), forming one
standard ESS. Clients save it once and roam between all FIPS routers
natively, with FIPS's Noise IK handshake as the only security layer:
- fips-ap-setup: opt-in UCI helper that creates the 'fips-ap0' open AP
(encryption none — security type must be uniform across routers or
clients treat the ESS as different saved networks), an isolated
network with a static ULA /64, RA-only odhcpd addressing (stateless
SLAAC, no DHCP — the minimum that satisfies Android's provisioning
check; no internet by design, so phones keep cellular as default
route), and a locked-down fips_ap firewall zone (no path to br-lan
or the WAN; only ICMPv6, mDNS, and the FIPS transports reachable).
'remove' subcommand undoes it. Radio setup stays opt-in; a package
must not commandeer radios on install.
- fips.yaml: ship 'ap0'/'ap1' Ethernet-transport entries commented out
(matching the 802.11s mesh backhaul) so a stock install that never
creates fips-ap* logs no per-boot "interface missing" bind warning;
fips-ap-setup uncomments the matching block when it creates the
interface and re-comments it on remove.
- Regression test: extend shipped_openwrt_config_parses to assert the
ap0/ap1 entries ship commented out and still parse once uncommented,
alongside mesh0/mesh1.
- Packaging: install the helper in ipk/apk/buildroot (three synced
copies), extend CI structural checks and shellcheck targets.
- docs/how-to/set-up-open-access-ssid.md: full guide, including the
one-time 'no internet, stay connected' acceptance (stored per SSID,
covers every FIPS router) and the security-type-uniformity
constraint.
* docs(openwrt): correct open-SSID/mesh security framing — peering is open by design
The fips-ap-setup/fips-mesh-setup comments and both how-tos claimed a
stranger "cannot pass the FIPS handshake" / "their frames die at the
handshake" / the handshake surface "drops them". That is wrong: FIPS
peer admission is open. An inbound handshake from any net-new identity
is promoted (node::handlers::handshake::promote_connection), gated only
by the daemon's max-peers cap — there is no allowlist, no PSK, and the
AuthChallenge path is not wired to admission. The Noise IK handshake
provides authentication (no impersonation of another identity, no MITM),
not authorization.
Restate the model accurately in all five places: a stranger on the open
SSID (or the open mesh) can associate AND form a FIPS peer link — that
is the point of open access. Containment is the isolated fips_ap zone
(no path to br-lan or the WAN) plus the max-peers cap, not the
handshake. Clarify that AP client isolation is an L2 control only: a
peered stranger is an overlay peer like any other, so the FIPS overlay,
not L2, is the trust boundary between clients.
* feat(openwrt): serve DHCPv4 on the access SSID from a fixed roamable subnet
RA-only addressing satisfied Android's provisioning check but left
anything expecting IPv4 with a self-assigned address and a "no IP"
complaint. dnsmasq now leases out of 10.21.<N>.0/24 (N = radio index;
prefix echoes FIPS port 2121), deliberately identical on every router:
a roaming client keeps its lease across the ESS, and dnsmasq's
authoritative mode — the OpenWrt default, pinned by the helper — ACKs
the renew a foreign router never issued. Lease collisions across
routers surface as a NAK on renew and the client re-DHCPs.
The dhcp section's 'dhcpv4 server' is read by both dnsmasq (default
images) and odhcpd (only with maindhcp), so either arrangement serves.
A DHCPv4/udp-67 accept rule joins the fips_ap zone; DHCPv6 stays off,
the ULA RA stays as-is, and nothing depends on an upstream. The zone
remains isolated — no forwardings, no internet.
* feat(openwrt): enable mDNS rendezvous from fips-ap-setup
Phone FIPS apps cannot open raw-Ethernet sockets, so DNS-SD is how they
find the router's daemon — but node.rendezvous.lan defaults to off. Ship
the lan block commented in fips.yaml (consistent with the apN transport
entries) and have fips-ap-setup uncomment it when creating the access
SSID. The awk match is scoped to node.rendezvous because
transports.ethernet carries a 'lan' entry at the same indent. The switch
is daemon-wide, so 'remove' deliberately leaves it on rather than guess
whether other transports rely on it.
* fix(openwrt): bind UDP dual-stack [::]:2121 so access-SSID clients reach it
The shipped router config bound the UDP transport "0.0.0.0:2121" (IPv4
wildcard) while the mDNS LAN advert announces every interface address,
including the router's IPv6 link-local — which phones on the !FIPS
access SSID rightly prefer (their cellular default route swallows v4,
and fd00::/8 is captured by the Myco mesh TUN). Result: the client's
Noise msg1 arrives on an unbound v6 port and is silently lost; the
handshake resends and times out.
Symptom chain (observed on-device): mDNS resolve OK, platform push OK,
"Sent Noise handshake message 1" to [fe80::…%N]:2121, four resends, no
reply, 30 s stale-timeout.
OpenWrt is Linux (bindv6only=0), so "[::]" accepts IPv4 via v4-mapped
addresses too — nothing is lost. packaging/common is deliberately left
on "0.0.0.0" for now: Windows defaults IPV6_V6ONLY=1, where "[::]"
would drop v4 instead.
A test that greps the daemon's log for a message the daemon stopped emitting
does not fail. It stops observing, and an assertion built on it — especially
one expecting a count of zero — then passes because nothing can be seen
rather than because nothing happened. Several findings have come from that
one class, so it is now checked mechanically.
testing/check-log-strings.py extracts the strings test code matches against
daemon log text and requires each to exist in src/. It reads four shapes:
python `"..." in line` tests, the first argument of the shell log helpers,
bash associative-array pattern tables, and greps whose input is daemon log
output. Patterns carry regex syntax, so each is reduced to the longest
literal run of every alternation branch, with escaping resolved in the same
pass — `\.` is a literal dot and `.` is a wildcard, and conflating them would
let a pattern match text that is not there.
Scoping is by what a grep READS, not by what its file mentions. A suite greps
its own analyzer output, fipsctl JSON, Tor's log and ping output, and none of
those have to correspond to a string in src/; scoping on the file produced 34
false positives. Strings that legitimately do not come from src/ are named in
ALLOWED with a reason, so the exceptions are reviewable rather than invisible.
It found six dead strings, three of which were not previously known: a second
copy of "Excessive decrypt failures" in the interop pattern table, a dead
"Handshake error" branch inside an alternation whose other branches still
matched, and "bootstrap failed" in the NAT suite. All six are corrected to
what the daemon emits, or dropped where the surviving branch already covers
the case. Verified by breaking it two ways and confirming it reports.
Also here, since it is the same failure shape one layer down: the shared log
library returned an empty string for a container whose logs it could not
read, so analysing a missing container reported no panics, no errors and no
sessions, and exited 0 — indistinguishable from a clean run. It now reports
which containers could not be read and raises, matching the fix already
landed in the chaos copy.
The guard that keeps "local green" and "GitHub green" meaning the same thing was invoked by nothing. Its only entry point was an exec behind an explicit --check-parity flag, which by exec-ing could not be combined with an actual run, and no workflow step called it at all. A guard nobody runs is a guard that does not exist, which is how the mixed-profile divergence on next survived unnoticed.
It now runs as the first stage of every local run and as its own job on GitHub. Locally it reports through the same result-recording path as every other stage, so a divergence sets the run's exit status instead of scrolling past. It is deliberately placed above the mode branches, so a divergence also fails --only, --test-only and --build-only runs: whichever subset was asked for, the claim that a local result means what a GitHub result means is what has broken. The GitHub side installs pyyaml explicitly rather than assuming the runner image carries it.
--check-parity keeps working exactly as before. Three comment blocks that described the old folded comparison are corrected here, in the workflow, the local runner and the testing README; they were spread across three files and only two mention the guard by name, so the third is best found by searching for what it claims rather than for the script.
Make the FIPS core build and run as an embedded Android library. The host
app owns the TUN (e.g. an Android VpnService) and FIPS performs no
system-TUN or CAP_NET_ADMIN operations.
Squashed from the following changes:
- gate desktop transports/TUN by target_os, not features: a plain
`cargo build` now compiles for every target with no flags. Ethernet (raw
AF_PACKET / BPF) is gated to linux/macos, so Android (target_os =
"android", not "linux") self-excludes it as Windows already did; real
system-TUN ops are gated per linux/macos and Android gets a no-op stub;
the ipi6_ifindex cast handles it being i32 on Android vs u32 on macOS. No
Cargo features are introduced; desktop builds are unchanged.
- app-owned TUN seam: Node::enable_app_owned_tun() lets an embedder that
owns the TUN fd exchange IPv6 packet bytes with FIPS over channels
instead of FIPS creating a system TUN device. It returns (app_outbound_tx,
app_inbound_rx): the embedder pushes packets read from its fd into the
outbound sender (app -> mesh) and pulls packets destined for its fd from
the inbound receiver (mesh -> app). start() gates system-TUN creation on
tun_tx being unset, so with the channels pre-installed it skips device
creation and does no system-TUN ops; both directions reuse the existing
inbound-shim and run_rx_loop wiring. Packets entering via app_outbound_tx
bypass handle_tun_packet, so the embedder must push only fd00::/8-destined
packets and clamp TCP MSS on outbound SYNs; the rustdoc and the
IPv6-adapter design doc spell this out.
- keep the android target warning-clean so the cross-compile check passes
clippy -D warnings.
- add an Android cross-compile CI check: cross-compile the library for
aarch64-linux-android via cargo-ndk and run clippy -D warnings. Android
ships as an embedded library (the host app owns the TUN), so there is no
daemon binary to package; this is a check job, not a packaging one.
- docs: list Android as a supported platform.
Tests: app_owned_tun_seam_wires_channels covers the channel round-trip and
the Active state; start_skips_system_tun_when_app_owned runs start() and
asserts no named system device is created.
Fold in a next-only wording fix for the OpenWrt 802.11s mesh backhaul:
next's FMP link handshake is Noise XX, not the Noise IK on master, so the
fips-mesh-setup header and the how-to now name it pattern-agnostically
("the Noise handshake"), matching the shipped fips.yaml comment and
staying accurate on this branch.
Router-to-router radio backhaul over an open 802.11s mesh interface,
with FIPS providing all encryption (Noise IK), authentication, and
routing on top of bare L2 neighbor links. The mesh runs OPEN with
mesh_fwding 0 — SAE would duplicate the Noise layer and force ath10k
raw mode, and FIPS is the routing layer — so the Noise handshake is the
real auth/encryption boundary and FIPS's spanning tree does the routing.
fips-mesh-setup: an opt-in UCI helper that creates a per-radio
mesh-point interface (radio0 -> fips-mesh0, radio1 -> fips-mesh1;
trailing-digit derivation with a free-index fallback and a collision
guard). Radio setup stays opt-in — a package must not commandeer radios
on install. 'remove' takes an optional radio and otherwise removes all
instances. Dual-band routers get one instance per radio; FIPS treats the
two backhaul paths as failover, not multipath: it keeps one active link
per peer (cross-connection resolution picks a single winner), and the
second band stands by, re-establishing the peer after keepalive timeout —
traffic never uses both bands at once.
fips.yaml ships the mesh0/mesh1 Ethernet-transport entries commented
out, so a stock install that never creates fips-mesh* logs no per-boot
"interface missing" bind warning. fips-mesh-setup uncomments the matching
meshN block when it creates the interface and re-comments it on remove,
so the flash-and-drop-in flow needs no manual config edit. The file is
rewritten 0600-first (it may hold an inline nsec) via an atomic replace.
Two field-found silent non-peering causes are surfaced by the helper and
the guide:
- Same channel: mesh points only peer on a shared channel, and 'auto'
lets each radio pick its own. The helper prints the radio's
band/channel and warns loudly on 'auto' with the exact uci command to
pin one; the how-to gains an ordered no-peers triage (channel mismatch,
on-air scan check, DFS CAC wait, regdomain).
- STA channel capture: a client (sta) interface drags the whole radio to
its upstream AP's channel, so a mesh pinned elsewhere never joins and
does not recover until the STA disconnects. The helper warns when the
target radio carries a STA; the guide documents the incompatibility of a
roaming uplink with a fixed-channel mesh on the same radio.
Both the create and remove paths run 'wifi reload', which briefly drops
every client AP on all radios; the how-to sets that expectation.
Regression test: the shipped OpenWrt fips.yaml must parse via the real
Config deserializer in both states — as shipped (mesh inactive) and after
the uncomment the helper performs.
Packaging: the helper is installed across the ipk/apk/buildroot paths
(three synced copies), with the CI structural checks and shellcheck
targets extended to cover it. Full guide in
docs/how-to/set-up-80211s-mesh-backhaul.md.
A transient timeout uploading the built .ipk to the Blossom CDN
(blossom.primal.net) failed the entire OpenWrt Package run, and because
the GitHub release job depends on the build jobs, a CDN blip would block
every OpenWrt artifact from the release. Blossom/nostr distribution is
supplementary; the package already ships as a GitHub release artifact.
Wrap the upload in a 3-attempt retry with backoff to absorb transient
timeouts, mark the step continue-on-error so a persistent outage no
longer fails the build, and guard the NIP-94 publish on the upload
succeeding so no event is created with an empty URL. Applied to both the
.ipk and .apk build jobs.
Claude-Session: https://claude.ai/code/session_01A2pYfSypNmmG4HyHwZuLex
Add OpenWrt .apk packaging for OpenWrt 25+, where apk-tools is the
mandatory package manager. The existing .ipk continues to cover OpenWrt
24.x and earlier. Built SDK-free like the .ipk: it reuses the
cargo-zigbuild cross-compile and the shared installed-filesystem payload
under openwrt-ipk/files, and assembles the ADB container with the
official `apk mkpkg` applet from apk-tools 3.0.5 built from source, so no
OpenWrt SDK image is needed.
The package-openwrt workflow is refactored so a single compile-binaries
job cross-compiles and strips each arch once; both the .ipk and .apk
packagers consume the binaries via a new --bin-dir flag instead of each
recompiling. A build-apk job (aarch64, x86_64) builds apk-tools,
packages, and structurally verifies the .apk with `apk adbdump`. Releases
now publish .apk artifacts and checksums alongside .ipk; the release
download is scoped to fips_* so the shared raw-binary artifacts are not
swept into the published release. apk-version.sh maps a release tag or
commit height to an apk-tools-valid version, covered by a case-table test.
Packages are unsigned, installed with `apk add --allow-untrusted`,
matching the .ipk posture.
Also fix the OpenWrt control socket: the init script now pre-creates
/run/fips before starting the daemon, the procd equivalent of the systemd
unit's RuntimeDirectory=fips. Without it, on a fresh boot the daemon
resolves its control socket to /tmp (since /run/fips does not yet exist),
while fips-gateway later creates /run/fips for its own gateway.sock,
leaving fipsctl/fipstop resolving a /run/fips/control.sock the daemon
never bound.
The linux/macos/windows package workflows each publish a
checksums-<platform>.txt sha256 file with their release artifacts, but
the OpenWrt workflow attached only the .ipk files with no checksum
coverage. Generate checksums-openwrt.txt over the .ipk outputs using the
same sha256sum idiom as the other platforms and add it to the release
file set.
Forward-merge the v0.4.0 pre-release content (dependency refresh, CI
deb-install + AUR-build legs, docs refresh, doc-comment fixes, and the
Phase 4 source-content squash: CHANGELOG, release notes, README,
fips.yaml, Cargo.toml metadata, reference docs) up the one-way flow.
Conflict fixups (keep next's identity, fold in master's improvements):
- Version: keep next's 0.5.0-dev (Cargo.toml/lock).
- README status: keep next's v0.5.0-dev / wire-format-breaking framing
and the Breaking-section pointer; fold in the Nym transport and the
"global, public test mesh of thousands of nodes" description.
- docs/reference/cli-fips.md: keep next's 0.5.0-dev version example.
- CHANGELOG: keep next's XX-handshake admission entry (no early cap gate
on XX) and drop master's IK early-cap-at-handle_msg1 entry, which
describes IK-only behavior that does not apply on next; take master's
OR-union mesh-size rewrite (next carries the OR-union code); restore
the Tor connect_refused and MMP receiver-report entries that the
Fixed-section consolidation would otherwise have dropped.
- lifecycle.rs: keep the mDNS/LAN handshake doc-comment as Noise XX
(next unifies on XX), not master's XX-to-IK correction.
Quartet green on the merged tree: fmt, build, clippy -D warnings, and
cargo test --lib (1434 passed).
Run the AUR package through makepkg + namcap on the same triggers as the
other package workflows (pushes to master/maint/next, pull requests,
tags, and manual dispatch), so a broken PKGBUILD is caught continuously
rather than only at release time. The build runs in an Arch container
(makepkg/namcap are not on ubuntu-latest) and packages the checked-out
tree from a local git-archive tarball, so it works for branch/PR builds
and unreleased rc tags that have no published GitHub source archive yet.
makepkg runs with --nocheck since the test suite is already covered by
ci.yml; this job validates packaging.
Publishing to the AUR is unchanged in intent but now gated to a real
(non-prerelease) release tag push, plus the existing manual-dispatch
republish path for packaging-only pkgrel bumps; it depends on the build
job so a package that fails to build or lint is never published. Branch
pushes and pull requests build and lint but never publish.
The PKGBUILD-patching logic is factored into a shared
packaging/aur/patch-pkgbuild.sh used by both jobs; the build path
sanitizes the version for makepkg (which forbids '-' in pkgver).
The GitHub deb-install matrix ran debian12/ubuntu24/ubuntu26, but the
local harness (testing/deb-install/test.sh) runs five distros. Add the
missing debian13 (trixie) and ubuntu22 legs so the cloud gate covers the
same distro set as local CI. Each new leg invokes the existing test.sh
scenario, so per-distro behavior is identical to the local run.
Update the granularity-only parity notes in ci.yml, ci-local.sh, and
check-ci-parity.sh to list the full distro set.
Bring the local runner (testing/ci-local.sh) and GitHub CI into agreement
on two axes.
Suite coverage: the admission-cap integration suite ran only locally, so a
regression in it could never turn the GitHub gate red. Add an admission-cap
leg to the integration matrix, add testing/check-ci-parity.sh (wired as
'ci-local.sh --check-parity') to diff the two suite sets and fail on
unexpected drift, and document the deliberate local-only (live-Tor) and
granularity-only differences in a comment block atop both runners.
Toolchain selection: every CI and packaging job installed its toolchain
with dtolnay/rust-toolchain@stable, but the rust-toolchain.toml channel pin
overrode it for all compilation, wasting an install and printing a
misleading rustc version. Switch the stable call sites to
actions-rust-lang/setup-rust-toolchain, which reads rust-toolchain.toml as
the single source of truth. Keep the explicit cache steps (cache: false on
the new action), set rustflags empty so the action does not impose a global
-D warnings the previous setup never applied, fold the macOS cross-compile
target into the action input, and leave the OpenWrt nightly Tier-3 leg on
dtolnay/rust-toolchain@nightly.
Forward-merges PR #91 (off-task encrypt/decrypt worker pools, GSO,
connected UDP), the macOS #102 package-integrity fix, and the AUR
#98 fips-dns fix from master.
Six textual conflicts resolved: wire/noise imports, the K-bit-flip
and rekey-cutover handlers, ActivePeer fields, and an advert test
fixture. One semantic conflict: PR #91's worker-pool code on master
referenced FLAG_SP and MmpPeerState.spin_bit, which next removed in
4aded9a2 (spin bit superseded by the MMP receiver-report timestamp
echo; FMP flags bit 2 reclaimed). The worker acceleration and its
fmp_flags round-trip test are kept; the spin-bit references are
dropped to honor next's wire-format change.
The AUR `fips` and `fips-git` packages did not install the
`fips-dns-setup` and `fips-dns-teardown` helper scripts that
`fips-dns.service` runs. The Debian package ships them to
`/usr/lib/fips/` through the `[package.metadata.deb]` assets, but the
AUR `package()` functions never replicated those install steps, so
`fips-dns.service` failed to start on Arch with "Unable to locate
executable /usr/lib/fips/fips-dns-setup".
Add the two `install -Dm0755` lines to both PKGBUILDs so the AUR
packages match the Debian layout.
Also harden the transition between the `fips` and `fips-git`
packages: each PKGBUILD now declares the other variant's `-debug`
split package as a conflict and opts out of the debug split, so a
stale debug build cannot retain ownership of installed files when
switching between the release and VCS packages. The `aur-publish`
workflow gains a validated `pkgrel` dispatch input so corrected
packaging can be republished against an existing release tag without
retagging.
Fixes#98
(cherry picked from commit 4cf550e23d)
The published v0.3.0 macOS installer is a structurally corrupt xar
archive: pkgutil and xar reject it even though its SHA-256 matches the
published checksum.
build-pkg.sh derived the architecture suffix in the .pkg filename from
`uname -m`. On the Apple-silicon macOS runner that always reports
arm64, so the cross-compiled x86_64 build also named its output
fips-<version>-macos-arm64.pkg. The release job downloads both build
artifacts with merge-multiple into one directory, where the two
identically named files collide and tear into a malformed result. The
x86_64 package never reaches the release at all.
Derive the package architecture from the Rust target triple, which is
authoritative for cross-compiles, instead of from the build host. Each
matrix leg now produces a distinctly named, arch-correct package, so
the two artifacts no longer collide.
Add a SHA-256 integrity chain so a corrupt or mismatched asset cannot
be published again:
- Capture the .pkg SHA-256 on the macOS runner, after the on-runner
structural verification, into a sidecar file carried in the artifact.
- Add a verify-handoff job that runs on every trigger and asserts each
downloaded .pkg still matches its macOS-runner SHA-256.
- Gate the release job on verify-handoff and repeat the check on the
exact bytes about to be published.
The build step now asserts it produced the expected arch-named package
so a regression in the naming fails loudly rather than as a silent
collision.
Relates to #102. The published v0.3.0 macOS assets still need to be
rebuilt and reuploaded separately.
Add a top-level concurrency block to ci.yml keyed on
(workflow, ref) with cancel-in-progress: true. Pushes (including
force-pushes) to the same ref now retire any in-flight run for
that ref rather than letting the superseded and current-tip runs
both burn runner minutes.
Motivated by a 2026-05-14 force-push experience where two CI runs
ran concurrently against a feature branch — the original push at
c76ec99 continued for ~17 minutes alongside the amended push at
927ef47, despite only the latter being the live tip.
Scope deliberately limited to ci.yml. Tag-triggered release-build
workflows (package-*.yml, aur-publish-*.yml) are untouched — they
operate on per-tag refs that already form distinct concurrency
groups and release artifact builds generally should not be
cancellable by unrelated activity.
The `mixed-profile` integration suite (Full / NonRouting / Leaf
node-role mix introduced by the forklift-upgrade work) is wired
into `testing/ci-local.sh` but was silently absent from the GitHub
Actions integration matrix on next. Regressions to node-role
behavior could land via GitHub CI without the suite running.
Adds a matrix entry plus the matching step block (mirroring the
rekey pattern: generate configs + inject config + compose up +
test + log-collect on failure + compose down always). master
correctly omits the suite from both ci-local and ci.yml since
mixed-profile is forklift-only, so this change never forward-merges
to master.
The v0.3.0 stable AUR push silently failed: with updpkgsums: true,
makepkg downloaded fips-<ver>.tar.gz into the AUR working tree, where
it was then staged by the deploy action and rejected by AUR's 488 KiB
max-blob hook.
Fetch the upstream source tarball and compute its b2sum in CI, patch
pkgver and the b2sums SKIP placeholder in PKGBUILD in-place, then
publish with updpkgsums: false so the AUR clone stays metadata-only.
Recompute and patch the fips.sysusers / fips.tmpfiles asset b2sums in
the same step so they stay in sync with the local files; this safety
net was previously provided by updpkgsums.
Add aur-publish-git.yml for the VCS fips-git PKGBUILD, triggered on
master pushes that touch PKGBUILD-git or its companion files plus
workflow_dispatch. pkgver is computed at build time by the PKGBUILD's
pkgver() function, so this workflow is not tied to release tags.
Add a workflow_dispatch tag input on the stable workflow so historical
release tags can be re-published manually, and drop continue-on-error:
true so future regressions surface in CI.
Investigated the mipsel-unknown-linux-musl build of this branch on a
Linux/x86_64 host. ring 0.17, portable-atomic, and the fips codebase
itself all compile cleanly for that target — the AtomicU64 portability
work is already done. The actual blocker is in the nostr-relay-pool 0.44
transitive dep, which uses std::sync::atomic::AtomicU64 directly in
src/relay/{stats,ping,flags}.rs. Verified fixable with a 6-line
portable-atomic patch via a [patch.crates-io] shim during local testing.
Updating the comment so the next person looking at this matrix has the
right starting point.
No functional change.
Six-node depth-4 mesh with an induced upstream parent flap. Asserts a
trailing-window ceiling on per-node `stats.bloom.sent` and a sanity
floor on parent-switch count over a ~3-4 min observation window.
Guards against the regression class where a spanning-tree update that
changes only an internal path edge (no root or depth delta) fails to
be properly contained and instead propagates to leaves as a sustained
bloom-traffic oscillation, visible only at fleet scale and only after
several minutes of uptime.
Adds a new chaos primitive (`link_swap`) for deterministic asymmetric
link-cost flapping and a post-run assertion framework with two
checks:
- `bloom_send_rate.max_per_node`: trailing-window ceiling on the
`show_bloom` stats counter delta. Calibrated against the
post-mortem reproduction harness data (per-variant counter table
against pre-fix vs post-fix binaries).
- `min_parent_switches.min_total`: sanity guard against a
misconfigured harness where the flap inducer fires but the
topology never produces a real parent-switch event (e.g., wrong
root election from a different seed). Without this, the
bloom-rate assertion would trivially pass on any binary
including a regressed one.
The runner exits 3 on assertion failure (alongside 0 success and 2
panic-detected). Threshold derivation is documented in the scenario
README; the seed pin is also documented there since smallest-NodeAddr
root election is sensitive to the pubkey hash ordering.
Wired into ci-local.sh's chaos pool and the GitHub CI chaos matrix.
The package-openwrt.yml shellcheck step was failing on warnings that
are false positives for OpenWrt scripts:
SC2034 — USE_PROCD, START, STOP in /etc/init.d scripts are read by
rc.common, not by the script itself; standard shellcheck
cannot see the indirection.
SC3043 — `local` is undefined in strict POSIX sh, but OpenWrt uses
ash which supports it. The init scripts use `local`
extensively for parameter scoping.
SC2086, SC2089, SC2090 — firewall.sh constructs nft match clauses
with literal quotes that need to survive variable expansion
(`match='iifname "$TUN"'` then `nft ... $match accept`). The
lack of double-quoting around `$match` is intentional so
word-splitting yields separate nft arguments.
Adding these to the exclude list. SC2317 (unreachable code) and
SC1008 (rc.common shebang form) were already excluded.
Johnathan Corgan
ArjenandGitHub
sandwichandJohnathan Corgan
Martti MalmiandJohnathan Corgan