Add fips-gateway binary: a separate daemon that allows unmodified LAN
hosts to reach FIPS mesh destinations via DNS-allocated virtual IPs
and kernel nftables NAT.
Gateway DNS resolver: forwarding proxy on [::]:53 that intercepts
.fips queries, forwards to daemon resolver (localhost:5354), allocates
virtual IPs from pool, returns AAAA records. Always sends AAAA upstream
regardless of client query type, returns proper NODATA for non-AAAA.
Virtual IP pool: fd01::/112 pool with state machine lifecycle
(Allocated → Active → Draining → Free), TTL-based reclamation,
conntrack integration for session tracking.
NAT manager: nftables DNAT/SNAT rules via rustables netlink API,
per-mapping rule lifecycle, fips0 masquerade for LAN client source
address rewriting.
Network setup: local pool route, proxy NDP for virtual IPs on LAN
interface, IPv6 forwarding validation.
Control socket at /run/fips/gateway.sock with show_gateway and
show_mappings queries. fipstop Gateway tab with pool summary gauge
and mappings table.
Gateway config section in fips.yaml with pool CIDR, LAN interface,
DNS upstream, TTL, and grace period settings.
Design doc at docs/design/fips-gateway.md.
Integration test (testing/static/scripts/gateway-test.sh): three
containers verifying DNS resolution, end-to-end HTTP, NAT state,
TTL expiration, SERVFAIL fallback, and clean shutdown.
When bloom filter candidates existed but none were strictly closer to
the destination in tree-coordinate distance, find_next_hop returned
None without trying greedy tree routing. This caused NoRoute failures
in topologies where the tree parent was closer but not a bloom
candidate. Fall through to tree routing when no bloom candidate makes
progress.
Raise the report interval floor from 100ms to 1000ms and ceiling from
2000ms to 5000ms. The old 100ms floor produced ~600 reports per 60s
parent evaluation cycle — far more than the ~10 needed for EWMA
convergence. The new floor yields ~60 reports/cycle, still well above
the convergence threshold, while reducing BLE overhead by 10×.
Add cold-start transition: first 5 SRTT samples use the 200ms floor
for fast initial convergence, then switch to the 1000ms steady-state
floor. Session-layer intervals unchanged (500ms–10000ms).
Wait for all nodes to reach their expected peer counts instead of
only checking a single node. This prevents false failures on slower
CI runners where remote nodes (especially node E in mesh/chain
topologies) take longer to establish all links.
Wait for all nodes to reach their expected peer counts instead of
only checking a single node. This prevents false failures on slower
CI runners where remote nodes (especially node E in mesh/chain
topologies) take longer to establish all links.
Tailscale (and potentially other routing software) installs a default
IPv6 route in an auxiliary routing table with a policy rule that runs
before the main table. This silently diverts fd00::/8 FIPS traffic
away from the fips0 TUN device.
Add an ip6 rule (priority 5265) during TUN setup that directs fd00::/8
to the main routing table, ensuring the fips0 route is always used.
Tailscale (and potentially other routing software) installs a default
IPv6 route in an auxiliary routing table with a policy rule that runs
before the main table. This silently diverts fd00::/8 FIPS traffic
away from the fips0 TUN device.
Add an ip6 rule (priority 5265) during TUN setup that directs fd00::/8
to the main routing table, ensuring the fips0 route is always used.
- Promote probe connections directly into pool instead of dropping and
reconnecting. Eliminates fragile two-phase connect pattern (probe →
disconnect → reconnect) that caused race conditions on restart.
- send_async fails fast when no connection exists, triggering a
background connect_async instead of blocking the event loop for up
to 10s on inline L2CAP connect. Prevents control socket query
timeouts and MMP processing stalls.
- Add 5-second timeout to pubkey_exchange recv. Without this, a peer
that connects but never sends its pubkey blocks the calling task
forever, killing the scan_probe_loop or accept_loop entirely.
- Add retry timer in scan_probe_loop for addresses that failed probe
but won't get another DeviceAdded from BlueZ (deduplication).
- Clear BlueZ cached devices before starting scan so fresh
advertisements trigger DeviceAdded after daemon restart.
- connect_async now performs pubkey exchange before promoting to pool,
matching the accept_loop's expectation on inbound connections.
- BLE tests updated to pre-establish connections via connect_async
since send_async no longer does inline connect.
- Size receive buffer from negotiated recv_mtu instead of hardcoded 4096
(prevents silent truncation if MTU exceeds buffer size)
- Set advertising interval to 400-600ms for deterministic behavior
instead of depending on BlueZ driver defaults
- Enable power_forced_active on L2CAP sockets to prevent sniff-mode
latency spikes during data transfer (best-effort, logged on failure)
- Log negotiated PHY and MTU at connection establishment for diagnostics
Add log_level field to NodeConfig (case-insensitive, default: info).
The daemon now loads config before initializing tracing so the
configured level takes effect. RUST_LOG env var still overrides if
set.
Remove hardcoded Environment=RUST_LOG=info from systemd units and
OpenWrt procd init script — these prevented config-driven log levels
from working.
Replace burst beacon pattern (1s on / 30s off) with continuous
advertising. The burst pattern caused L2CAP connect timeouts because
the remote side was no longer connectable when the probe fired after
jitter delay. BLE advertising overhead is negligible (~0.15% duty
cycle on advertising channels).
Replace the seen HashSet + jitter delay queue with a simple cooldown
map. After probing an address (success or failure), suppress re-probe
for 30s (configurable via probe_cooldown_secs). Connected peers are
filtered by pool membership check. This eliminates the bug where
failed probes permanently blacklisted addresses for the session
lifetime.
Remove config fields: scan_interval_secs, beacon_interval_secs,
beacon_duration_secs. Add: probe_cooldown_secs.
BLE transport implementation using L2CAP Connection-Oriented Channels
(SeqPacket mode) via the bluer crate, behind cfg(feature = "ble").
Core transport:
- BleTransport<I> generic over BleIo trait (BluerIo prod, MockBleIo test)
- Connection pool with priority eviction (static > discovered, max 7)
- Connect-on-send via connect_inline() matching TCP behavior
- Per-connection receive loops with pool cleanup on disconnect
Discovery and probing:
- Combined scan_probe_loop using select! over scanner events and a
BinaryHeap delay queue with per-entry random jitter (0-5s) to prevent
herd effects when multiple nodes see the same beacon simultaneously
- Pre-handshake pubkey exchange ([0x00][pubkey:32]) for IK identity
- Cross-probe tie-breaker: smaller NodeAddr's outbound wins (same
convention as FMP/FSP rekey dual-initiation)
- Probed peers reported to DiscoveryBuffer; pool fills through normal
node-layer auto-connect -> send_async -> connect_inline path
Beacon management:
- Periodic advertising: 1s burst every 30s (configurable via
beacon_interval_secs / beacon_duration_secs)
- FIPS service UUID for scan filtering
Configuration (all fields optional with defaults):
- adapter, psm, mtu, max_connections, connect_timeout_ms
- advertise, scan, auto_connect, accept_connections
- beacon_interval_secs (30), beacon_duration_secs (1)
Hardware validated with two BLE nodes:
- 2048-byte MTU, ~60-160ms RTT, zero-config auto-connect
- BLE spike tool at testing/ble/ for standalone adapter validation
42 unit tests + 4 node-level integration tests, all CI-compatible
via MockBleIo (no hardware required). tokio test-util added for
time-dependent scan/probe tests.
The visited_bits field (hash_cnt + 256 bytes) was removed from the
LookupRequest wire format in the discovery-rework (bloom-guided tree
routing replaced the visited filter). Update the diagram to match the
current 46 + 16n byte format.
Phase 1 pre-rekey baseline was failing intermittently on CI runners
because 5s wasn't enough for multi-hop discovery (B→D requires
B→C→D). The mesh always converged by Phase 3, confirming this was
purely a timing issue.
The rekey test greps container logs for initiator cutover messages that
were demoted to debug level. Override RUST_LOG in the rekey profile to
enable debug for fips::node::handlers::rekey so the test assertions
can find them.
Check /run/fips/ directory existence instead of the socket file inside
it. Users not in the fips group can stat the directory but not traverse
it, so the socket file check silently returned false and fell back to
$XDG_RUNTIME_DIR with a misleading "No such file" error.
Bump version to 0.2.0 and finalize changelog with discovery rework,
Tor transport, connect/disconnect commands, reproducible builds, and
12 bug fixes.
Update design documentation for discovery protocol rework:
- fips-wire-formats.md: remove visited bloom filter from LookupRequest,
update size calculations
- fips-mesh-operation.md: replace flooding description with bloom-guided
tree routing, add retry/backoff/rate-limiting subsections
- fips-configuration.md: add 5 new discovery config parameters, update
control socket description for connect/disconnect commands
build-tarball.sh only applied --mtime when SOURCE_DATE_EPOCH was
explicitly set, and did not sort tar entries. This produced different
tarballs across builds due to varying timestamps and filesystem
ordering. Default SOURCE_DATE_EPOCH to the git commit timestamp and
add --sort=name for deterministic output.
Replace discovery flooding with bloom-filter-guided tree routing:
lookups sent only to tree peers (parent + children) whose bloom
filter contains the target. If no tree peer matches, fall back to
non-tree peers with bloom matches before dropping the request. This
produces single-path forwarding through the spanning tree (90%
traffic reduction) while recovering from dead ends caused by stale
bloom filters, tree restructuring, or transit node failures.
Remove visited bloom filter from LookupRequest wire format (-257
bytes per request). Tree routing is inherently loop-free; request_id
dedup handles edge cases during tree restructuring. Add response-
forwarded flag to prevent response routing loops from convergent
request paths.
Add originator-side exponential backoff (30s base, 300s cap) after
lookup timeouts and bloom misses. Backoff resets on topology changes
(parent switch, new peer, first RTT, reconnection).
Add transit-side per-target rate limiting (2s minimum interval) for
forwarded lookups as defense-in-depth.
Add discovery retry within the timeout window (default: send at T=0,
retry at T=5s, fail at T=10s) to compensate for single-path fragility.
Lookups with zero eligible tree peers fail immediately.
Improve discovery logging: promote key events to info (initiation,
success, timeout with failure count). Add debug logging for dedup,
pending packet retry, backoff suppression, forward rate limiting,
and backoff reset.
New config: discovery.backoff_base_secs, backoff_max_secs,
forward_min_interval_secs, retry_interval_secs, max_attempts.
New stats: req_backoff_suppressed, req_forward_rate_limited,
req_bloom_miss, req_no_tree_peer, req_fallback_forwarded.
Removed: req_already_visited, visited bloom filter.
Three infrastructure bugs fixed:
- DNS resolution never populated the identity cache because Docker
overwrites /etc/resolv.conf at container start. Fix: bind-mount
resolv.conf in the chaos compose template, matching the static and
sidecar test configs.
- Traffic generator used config-time npubs for iperf3 targets, but
ephemeral nodes generate fresh keypairs at startup. Fix: share the
peer churn manager's runtime npub cache with the traffic manager.
- Log analysis had no discovery counters and used wrong patterns.
Fix: add discovery section with correct log message matching.
Also adds timestamped output directories (YYYYMMDD-HHMMSS-scenario),
coord_ttl_secs override in maelstrom.yaml, FIPS_SIM_OUTPUT env var
support, and maelstrom-sparse scenario for sparse topology testing.
Add runtime peer management to the FIPS daemon via control socket
commands, and a new chaos simulation scenario that exercises dynamic
topology mutation with ephemeral node identities.
Daemon (connect/disconnect commands):
- Extend control socket Request with optional params field
- Add commands.rs module for mutating command dispatch, separate from
read-only queries
- Add api_connect() on Node: builds ephemeral PeerConfig (no auto-
reconnect), pre-seeds identity cache, reuses initiate_peer_connection
- Add api_disconnect() on Node: calls remove_active_peer(), clears
retry_pending to suppress reconnection
- Route non-show_* commands to async command dispatch in rx_loop
fipsctl CLI:
- Add Connect and Disconnect subcommands accepting npub or hostname
- Resolve hostnames from /etc/fips/hosts before sending to daemon
- Refactor socket I/O into reusable send_request helper
Chaos simulator (maelstrom scenario):
- Add PeerChurnManager: periodically disconnects a random active link
and connects a random unconnected node pair via control socket
- Add send_command() to control.py using base64-encoded JSON payloads
to avoid shell quoting issues in docker exec
- Add PeerChurnConfig to scenario with interval and ephemeral_fraction
- Ephemeral identity support: nodes configured without nsec generate
fresh keypairs on restart; simulator queries show_status for new
npub and updates its cache via on_node_restart callback
- Add maelstrom.yaml: all chaos dimensions (netem, link flaps, node
churn, peer topology churn, traffic) with 50% ephemeral identity
The K8s sidecar is a standalone example, not a test harness — it has
no CI integration unlike testing/sidecar/. Move it to examples/
alongside sidecar-nostr-relay/ where it belongs. Update internal path
references in Dockerfile, build.sh, and README.
The loss and goodput delta guards used prev_rr_highest_counter > 0 and
prev_rr_cum_bytes > 0, which conflates "never received a report" with
"received a report where the value was 0." Since Noise transport
counters start at 0, this is semantically wrong. Use a dedicated
has_prev_rr boolean flag instead. Fixes GitHub issue #14 (Bug B).
The reverse delivery ratio was computed as cumulative_packets_recv /
highest_counter (lifetime values), while the forward ratio correctly
used per-interval deltas. This made ETX increasingly unresponsive over
session lifetime — early loss haunted the ratio forever, late loss
barely moved it.
Replace set_delivery_ratio_reverse() with update_reverse_delivery()
that tracks previous snapshot state and computes deltas, matching the
forward ratio's approach. Fixes GitHub issue #14 (Bug A).
After rekey cutover, frames encrypted with the old session can still
arrive during the 10s drain window. These carry large sender timestamps
from the old session, producing enormous transit deltas that spike the
EWMA jitter estimator (observed 2,000-7,000ms spikes on UDP links).
Add a time-based grace period (DRAIN_WINDOW_SECS + 5s = 15s) after
rekey that suppresses jitter updates until drain-window frames have
flushed. Baselines still update every frame so calculation resumes
cleanly after grace expires.
Fixes#10
The DNS responder returned NXDOMAIN for non-AAAA queries (e.g. A record)
on valid .fips names. This caused resolvers like nslookup and tinyproxy
to give up without attempting AAAA, since NXDOMAIN means "name does not
exist." Return NOERROR with an empty answer section instead, which tells
the client the name exists but has no records of that type.
Fixesjmcorgan/fips#9.
Rekey dual-initiation race (FMP + FSP):
When both sides' rekey timers fire simultaneously on high-latency links
(Tor ~700ms RTT), both msg1s cross in flight before dampening can
suppress the second initiation. Each node acts as both initiator and
responder, with set_pending_session() from the responder path destroying
the initiator's in-progress state. Each side ends up with a
pending_new_session from a different Noise handshake, causing AEAD
verification failure after cutover and link death. Fix: deterministic
tie-breaker in both FMP msg1 handler and FSP SessionSetup handler
(smaller NodeAddr wins as initiator). Also guard against pending session
overwrite from retransmitted msg1s.
Parent selection SRTT gate:
Peers without MMP RTT data are excluded from parent candidacy via
has_srtt() filter, preventing freshly reconnected peers from appearing
artificially attractive. First-RTT triggers immediate parent re-eval.
The gate in evaluate_parent() skips unmeasured candidates when any peer
has cost data, but falls back to default cost 1.0 during cold start
when no peer has MMP data yet.
Auto-reconnect on all peer removal paths:
The excessive-decryption-failure and peer-restart epoch-mismatch removal
paths were missing schedule_reconnect() calls, causing auto-connect peers
to be permanently abandoned after those events.
Control socket accessibility:
Socket and parent directory chowned to root:fips with mode 0770/0750 so
group members can use fipsctl/fipstop without root.
Log level changes:
Default RUST_LOG changed to debug in systemd service files. "Unknown
session index" log reduced from debug to trace.
Previously, static peers configured with AutoConnect gave up after 6
attempts (1 initial + 5 retries). If the remote peer was offline at
startup, the node permanently abandoned the connection. The reconnect
path (after MMP link-dead) already retried indefinitely but only
activated after a peer had been previously connected.
Remove the reconnect parameter from schedule_retry() and always set
reconnect=true when creating retry entries, since only auto-connect
peers reach this code path. The 300s backoff cap prevents resource waste.
The max_retries=0 config still works as an explicit kill switch.
The FSP XK rekey handshake has a race condition where the initiator
can cut over (K-bit flip) and send data encrypted with the new session
before msg3 reaches the responder. The responder has no pending session
yet, so K-bit detection fails and packets are dropped.
Defer FSP initiator cutover by 2 seconds after handshake completion
(FSP_CUTOVER_DELAY_MS) to give msg3 time to traverse the mesh. FMP
(IK, 2 messages) is unaffected since the responder completes during
msg1 processing.
Also fix MMP metric corruption after rekey cutover: the new session
starts with counter 0 but MMP state carries highest_counter and
GapTracker.expected_next from the old session, producing false
reorder counts, jitter spikes, and invalid OWD trends. Add
reset_for_rekey() methods that clear counter-dependent state while
preserving RTT estimates.
Additional fixes:
- Remove stale peers_by_index entry on abandon_rekey error path
- Replace redundant peers_by_index inserts with debug assertions
verifying the pre-registration invariant
- Tighten rekey integration test to zero tolerance (was 4 failures)
Add TorTransport in src/transport/tor/ supporting three operating modes:
Outbound (socks5 mode):
- Non-blocking SOCKS5 connect via tokio-socks with per-destination
circuit isolation (IsolateSOCKSAuth)
- TorAddr enum for .onion and clearnet address types
- Connection pool with per-connection receive tasks, reuses TCP
stream FMP framing
- connect_async()/connection_state_sync()/promote_connection() follow
the same non-blocking polling pattern as TCP transport
Inbound (directory mode — recommended for production):
- Tor manages the onion service via HiddenServiceDir in torrc
- FIPS reads .onion address from hostname file at startup
- No control port needed — enables Tor Sandbox 1 (seccomp-bpf)
- Accept loop mirrors TCP pattern with DirectoryServiceConfig
Monitoring (control_port mode and optional in directory mode):
- Async control port client supporting TCP and Unix socket connections
via Box<dyn AsyncRead/Write> trait objects
- AUTHENTICATE with cookie or password auth
- 8 GETINFO queries: bootstrap, circuits, traffic, liveness, version,
dormant state, SOCKS listeners
- Background monitoring task polls every 10s, caches TorMonitoringInfo
in Arc<RwLock> for synchronous query access
- Bootstrap milestone logging (25/50/75/100%), stall warning (>60s),
network liveness transitions, dormant mode entry
- Directory mode optionally connects to control port when control_addr
is configured (non-fatal on failure)
Operator visibility:
- show_transports query exposes tor_mode, onion_address, tor_monitoring
(bootstrap, circuit_established, traffic, liveness, version, dormant)
- fipstop transport detail view: Tor mode, onion address, SOCKS5/control
errors, connection stats, Tor daemon status section
- fipstop table view: tor(mode) label with truncated onion address hint
Security hardening:
- Per-destination circuit isolation via IsolateSOCKSAuth
- Unix socket default for control port (/run/tor/control)
- Reference torrc with HiddenServiceDir, VanguardsLiteEnabled,
ConnectionPadding, DoS protections (PoW + intro rate limiting)
Config:
- TorConfig with socks5, control_port, and directory modes
- DirectoryServiceConfig: hostname_file, bind_addr
- control_addr, control_auth, cookie_path, connect_timeout,
max_inbound_connections
Testing:
- 69 unit + integration tests with mock SOCKS5 and control servers
- Docker tests: socks5-outbound (clearnet via Tor) and directory-mode
(HiddenServiceDir onion service)
Documentation:
- Transport layer design doc: Tor architecture, directory mode
- Configuration doc: Tor config tables and examples
Add resolve_socket_addr() with IP fast path and tokio::net::lookup_host()
fallback for DNS hostnames. Peer addresses can now use hostnames like
"peer1.example.com:2121" alongside IP addresses.
UDP transport adds a per-transport DNS cache (60s TTL) to avoid
per-packet resolution. TCP resolves at connect time (one-shot).
Update design docs, config examples, and changelog to reflect hostname
support in transport addressing.
- Rewrite TCP "Connect-on-Send" section to document non-blocking connect
model (ConnectingPool, PendingConnect, poll_pending_connects)
- Add connect() and connection_state() to Transport trait surface
- Expand Connection Lifecycle section with ConnectionState enum
- Remove phantom TCP socks5_proxy field (removed from code, superseded
by TorConfig)
- Fix "future Tor transport" references (stream reader already shared)
- Replace misleading "tor:" named TCP instance example
- Update fips-intro.md implementation status (TCP and Ethernet are
implemented, not "under active design")
TCP (and future Tor) transports previously established connections
synchronously inside send(), blocking the node's RX event loop during
TCP handshake. This is particularly problematic for Tor where SOCKS5
circuit establishment can take 30-120 seconds.
Add a non-blocking connect path:
- ConnectionState enum in transport layer (None/Connecting/Connected/Failed)
- connect_async() on TcpTransport spawns background TCP connect task
- connection_state_sync() polls task completion, promotes to pool
- TransportHandle gains connect() and connection_state() dispatch methods
- Node tracks PendingConnect entries for connection-oriented transports
- initiate_connection() defers handshake for connection-oriented transports
- start_handshake() extracted as separate method for deferred invocation
- poll_pending_connects() in tick handler polls and completes handshakes
- Failed connects trigger retry via schedule_retry()
Connectionless transports (UDP, Ethernet) are unchanged — connect()
is a no-op and connection_state() always returns Connected.
The existing connect-on-send path in send_async() is preserved as
fallback for reconnection after connection drops.
811 tests pass (6 new), clippy clean.
Update all fips-network/fips references to jmcorgan/fips across
Cargo.toml, README, CONTRIBUTING, packaging, and config files.
Merge CHANGELOG Unreleased and 0.1.0-alpha sections into a single
0.1.0 release entry. Update README roadmap.
Breaking wire format change: DataPacket payloads inside the AEAD envelope
now carry a 4-byte port header [src_port:2 LE][dst_port:2 LE] before the
service payload. The receiver dispatches by destination port.
Port multiplexing:
- send_session_data() takes src_port/dst_port params, prepends port header
- New send_ipv6_packet() compresses IPv6 header and sends on port 256
- Receive path dispatches DataPackets by port: port 256 decompresses IPv6
header from session context and delivers to TUN, unknown ports dropped
- Port constants: FSP_PORT_HEADER_SIZE (4 bytes), FSP_PORT_IPV6_SHIM (256)
IPv6 header compression:
- New ipv6_shim module with compress_ipv6()/decompress_ipv6() pure functions
- Strips src/dst addresses (32 bytes) and payload length (2 bytes) from each
packet, preserving traffic class, flow label, next header, and hop limit
as 6-byte residual fields
- Addresses reconstructed from session context on receive side
- Net savings: 29 bytes per packet (overhead 106 → 77 bytes)
- FIPS_IPV6_OVERHEAD constant (77 bytes), effective_ipv6_mtu() updated
- 16 unit tests for round-trip fidelity, field preservation, error cases
Documentation:
- fips-wire-formats: DataPacket port header, port registry, IPv6 shim
format tables, updated encapsulation walkthrough and overhead budget
- fips-ipv6-adapter: FIPS_IPV6_OVERHEAD (77 bytes), updated MTU numbers,
TUN reader/writer flow with compression steps, impl status
- fips-session-layer: port-based service dispatch section, data transfer
description, impl status
- fips-intro: IPv6 adapter as port 256 service, node architecture updated
- fips-mesh-operation: packet size summary with compressed overhead
- DataPacket doc updated with port header and dispatch model
- session_wire.rs module doc: DataPacket Port Multiplexing section
Update 9 documentation files to match current implementation:
- Add missing rekey config section (node.rekey.*) and host mapping
section to fips-configuration.md
- Update Ethernet frame format from [type:1][payload] to
[type:1][length:2 LE][payload] in wire-formats and transport docs
- Fix Ethernet effective MTU from interface-1 to interface-3
- Mark rekey as Implemented in mesh-layer and session-layer status tables
- Change TCP default port examples from 443 to 8443
- Add rekey, persistent identity, host mapping, mesh size estimation to
README features and status sections
- Update chaos scenario count from 16 to 20, add rekey topology to
static test docs
The fips-dns.service unit had three issues:
1. Wants=systemd-resolved.service caused systemd to start systemd-resolved
on systems that weren't using it, breaking existing DNS by rewriting
/etc/resolv.conf to the stub resolver at 127.0.0.53.
2. The ExecStart busy-wait loop for fips0 had no timeout, hanging forever
if fips.service failed to create the TUN device.
3. Installers unconditionally enabled fips-dns.service regardless of whether
systemd-resolved was present.
Fix by replacing Wants= with ConditionPathExists=/run/systemd/resolve (skips
cleanly if resolved isn't running), adding Requires=fips.service (won't start
without the daemon), bounding the fips0 wait loop to 30 seconds, and making
the installers conditional on systemd-resolved being active.
Phase 3 (post-first-rekey connectivity) can see brief disruptions while
links are mid-cutover. Add a 5s settle time after the rekey wait and
allow up to 4 transient pair failures in Phase 3. Phase 5 remains
strict, ensuring full recovery after the second rekey cycle.
fipsctl and fipstop checked XDG_RUNTIME_DIR before /run/fips/, causing
them to look in /run/user/<uid>/fips/ while the systemd-managed daemon
listens on /run/fips/control.sock. Reorder the fallback to check the
system-wide path first. Also improve the permission-denied error in
fipsctl to suggest adding the user to the fips group.
Add full npub column, transport type/address, direction (in/out),
goodput, and LQI-ascending sort to peers table. Colorize spanning
tree parent (magenta) and children (cyan). Add tree relationship
and transport info to show_peers JSON output.
Compute network size estimate by summing bloom filter estimated entry
counts from the spanning tree parent (upward) and children (downward),
leveraging the tree's non-overlapping partition property. Uses the
standard formula n = -(m/k) * ln(1 - X/m) already in BloomFilter.
Surfaces the estimate in three places:
- show_status JSON: "estimated_mesh_size" field
- Periodic info log at MMP log interval (default 30s)
- fipstop Node dashboard State section as "mesh: ~N"
Add a HostMap that resolves human-readable hostnames to npubs,
enabling `gateway.fips` instead of the full `npub1...xyz.fips`.
Two sources populate the map: peer `alias` fields from the YAML
config and an operator-maintained hosts file at /etc/fips/hosts.
The DNS responder auto-reloads the hosts file on each request by
checking the file modification time, so operators can update
mappings without restarting the daemon.
- New src/upper/hosts.rs: HostMap, HostMapReloader, hostname
validation, hosts file parser with auto-reload on mtime change
- DNS resolver checks host map before falling back to direct npub
- Node uses host map for peer display names
- Default hosts file added to both .deb and tarball packaging
- 26 new tests (789 total)
Update the external pub node (vps-chi at 217.77.8.91) to use its
real persistent npub instead of a fabricated test key. Remove the
unnecessary nsec from the external node definition.
Five tests covering the full TCP transport stack at the node level:
two-node handshake, three-node chain convergence with bloom filter
reachability, mixed UDP+TCP transport coexistence, MMP link-dead
detection after connection loss, and reconnection after link death
via connect-on-send.
Debian packaging via cargo-deb:
- Add [package.metadata.deb] to Cargo.toml with assets, dependencies,
and conffiles declarations
- Maintainer scripts: postinst (create fips group, enable services,
restart on upgrade), prerm (stop/disable on remove, stop-only on
upgrade), postrm (purge config, keys, group)
- Systemd units (fips.service, fips-dns.service) with /usr/bin/ paths
for .deb installs
- tmpfiles.d entry for /run/fips/ runtime directory
- build-deb.sh wrapper script for building packages
README rewrite:
- Replace run-from-source Quick Start with Building section
- Add Installation options: Debian .deb (cargo-deb) and generic Linux
(systemd tarball)
- Add full Configuration reference with default fips.yaml
- Add Usage sections: DNS resolution, monitoring (fipsctl + fipstop),
service management, and testing
- Update project structure and features list
Embed git commit hash, dirty flag, and target triple in all binaries
via a zero-dependency build.rs. Wire clap short/long version output
so -V shows "0.1.0 (rev abc1234)" and --version adds the target
triple. Log version at daemon startup.
Add version field to show_status control socket API response. Show
the daemon's version in fipstop's tab bar title and Runtime section.
Add CHANGELOG.md in Keep a Changelog format with the 0.1.0-alpha
release (2026-02-24) and unreleased work since then.
Implement periodic full rekey at both protocol layers using fresh DH
key exchanges. Uses the existing K-bit flag (FLAG_KEY_EPOCH /
FSP_FLAG_K) to coordinate cutover between peers.
FMP layer (IK pattern):
- ActivePeer gains rekey state: pending/previous sessions, K-bit epoch
tracking, drain window, dampening timer
- Handshake state stored on ActivePeer with msg1 sent on existing link
- Encrypted frame handler detects K-bit flips, promotes pending
sessions, falls back to previous session during drain
- Handshake handlers distinguish rekey from new connections using
addr_to_link lookup with identity-based fallback
- Free all session indices (current, rekey, pending, previous) on
peer removal
FSP layer (XK pattern):
- SessionEntry gains parallel rekey fields with XK-specific state
for the 3-message handshake
- Route availability check before FSP rekey initiation
- Encrypted session handler adds K-bit flip detection and dual-session
decrypt fallback
- SessionSetup/Ack/Msg3 handlers extended for rekey paths
Defense-in-depth:
- Consecutive decryption failure detector (threshold=20) triggers
forced peer removal instead of waiting for link-dead timeout
- Identity-based rekey detection as fallback when addr_to_link
doesn't match (e.g., TCP ephemeral ports)
Configuration: RekeyConfig with enabled flag, after_secs (default 120),
and after_messages (default 65536) thresholds.
Logging: info for successful K-bit cutover completions, warn for
failures, debug for intermediate handshake steps, trace for routine
operations (resends, drain cleanup).
Rekey lifecycle:
1. Timer/counter fires -> initiator starts new handshake
2. Old session continues handling traffic during handshake
3. Handshake completes -> initiator cuts over, flips K-bit
4. Responder sees flipped K-bit -> promotes new session
5. Both keep old session for 10s drain window
6. After drain, old session discarded
Integration test: Docker-based multi-phase test exercising both FMP
and FSP rekey with aggressive timers (35s). Verifies connectivity
across all 20 directed pairs survives two consecutive rekey cycles.
Includes rekey topology, docker-compose profile, and CI matrix entry.
Increase ping test convergence wait from 3s to 5s for CI reliability.
Packaging directory structure:
- packaging/common/ — shared config (fips.yaml) used by all formats
- packaging/systemd/ — systemd-specific installer and service units
Systemd packaging includes:
- build-tarball.sh: builds release binaries and creates a self-contained
install tarball with stripped binaries
- fips.service: systemd unit running the daemon with security hardening
- fips-dns.service: oneshot unit configuring resolvectl to route .fips
domain queries to the FIPS DNS shim on 127.0.0.1:5354
- install.sh: deploys binaries to /usr/local/bin, installs systemd units,
creates fips group for non-root control socket access
- uninstall.sh: removes service and binaries, optional --purge for
config and identity key files
- README.install.md: installation and configuration guide
Default config enables UDP (2121), TCP inbound (8443), TUN, and DNS
resolver. Identity is ephemeral by default for privacy; operators can
uncomment persistent: true to maintain a stable npub for static peer
publishing. Ethernet transport is commented out for per-node setup.
Implement identity management for the FIPS daemon with two modes:
Ephemeral (default): A fresh keypair is generated on every start.
Key files (fips.key, fips.pub) are written for operator visibility
but overwritten on each restart. This is privacy-friendly and
requires no configuration.
Persistent (opt-in via `node.identity.persistent: true`): Uses
three-tier identity resolution:
1. Explicit nsec in config file (advanced users)
2. Persistent key file alongside config (reused across restarts)
3. Generate new keypair, persist to key file
Key files follow the SSH id_ed25519/id_ed25519.pub convention:
- fips.key: bare bech32 nsec string, mode 0600
- fips.pub: bare bech32 npub string, mode 0644
The daemon always writes fips.pub on startup so operators can
find their current identity via `cat /etc/fips/fips.pub`.
Identity resolution extracted into testable `resolve_identity()`
function in config module. Graceful degradation: key file write
failure silently falls back to ephemeral identity.
Add `fipsctl keygen` subcommand for manual key generation:
- `-d <dir>` output directory (default: /etc/fips)
- `-f` force overwrite existing files
- `-s` print nsec/npub to stdout instead of writing files
- Warns that `persistent: true` must be set in config
- Works without a running daemon
Includes unit tests for key file read/write roundtrip, file
permissions, whitespace trimming, empty file error, path derivation,
ephemeral-by-default behavior, ephemeral key cycling, persistent
key file loading, and persistent generate-and-reuse lifecycle.
The link-dead check required last_recv_time to be Some, so peers that
completed a handshake but never sent any data back (last_recv_time =
None) were silently skipped and lived forever as zombies. Fall back to
session_start when no frame has ever been received.
Implement hop-by-hop ECN congestion signaling through the FMP layer,
transport-level congestion detection via kernel drop counters, and
chaos harness integration for end-to-end validation.
FMP/session ECN plumbing:
- Thread ce_flag parsed at link layer through dispatch_link_message,
handle_session_datagram, handle_session_payload, and
handle_encrypted_session_msg to session delivery
- Replace hardcoded false in session-layer record_recv() with actual
ce_flag, activating ecn_ce_count tracking in session MMP
ECN congestion detection and CE relay:
- Add EcnConfig (node.ecn.*) with configurable loss_threshold (5%)
and etx_threshold (3.0) for transit congestion detection
- Add send_encrypted_link_message_with_ce() that ORs FLAG_CE into FMP
header flags; original method delegates with ce_flag=false
- Compute outgoing_ce = incoming_ce || local congestion on next-hop
link, enabling hop-by-hop CE relay through transit nodes
IPv6 ECN-CE marking:
- Mark ECN-CE (0b11) in IPv6 Traffic Class on received DataPackets
before TUN delivery when FMP CE flag is set
- Only marks ECN-capable packets (ECT(0)/ECT(1)); Not-ECT packets
unchanged per RFC 3168
Transport congestion abstraction and UDP kernel drop detection:
- Add TransportCongestion struct to transport layer for transport-
agnostic local congestion indicators
- Replace tokio::UdpSocket with AsyncFd<socket2::Socket> using
libc::recvmsg() with ancillary data parsing
- Enable SO_RXQ_OVFL for kernel receive buffer drop counter on every
packet, wiring up previously-stubbed UdpStats.kernel_drops
- Add TransportDropState for per-transport delta tracking with 1s
tick sampling via sample_transport_congestion()
- Extend detect_congestion() with transport kernel drop check
alongside MMP loss metrics
Congestion monitoring and control:
- Add CongestionStats (ce_forwarded, ce_received, congestion_detected,
kernel_drop_events) to NodeStats with snapshot serialization
- Wire counters into forwarding path, session handler, and transport
drop sampling with rate-limited warn logging (5s interval)
- Expose congestion data in show_routing control query and
ecn_ce_count in show_mmp peer entries
- Add congestion counters to fipstop routing tab in two-column layout
Chaos harness integration:
- Add query_routing(), query_transports(), snapshot_all_congestion()
to chaos control module
- Add congestion/kernel-drop log analysis in logs module
- Add congestion-stress scenario: 10-node tree, 1 Mbps bandwidth,
5-10% netem loss, heavy iperf3 traffic
- Add IngressConfig for tc ingress policing with per-peer policer
filters simulating upstream bandwidth bottlenecks
- Add iperf3 JSON result capture to traffic manager for throughput
measurement across scenarios
- Add ECN A/B test scenarios (ecn-ab-on/off.yaml) with ingress
policing and comparison script
- Enable TCP ECN negotiation (tcp_ecn=1 sysctl) in container
entrypoint for end-to-end CE propagation
Tests:
- 10 ECN unit/integration tests: mark_ipv6_ecn_ce variants, CE relay
chain (3-node propagation), EcnConfig serde roundtrip
- 3 transport drop congestion detection unit tests
Documentation:
- Update fips-mesh-layer.md: replace outdated CE Echo stub with full
ECN Congestion Signaling section covering detection logic, CE relay,
IPv6 marking, session tracking, and monitoring counters
- Update fips-configuration.md: add node.ecn.* parameter table and
ecn block in complete reference YAML
- Update fips-transport-layer.md: add Congestion Reporting section
with TransportCongestion struct, congestion() trait method, and
per-transport status; document AsyncFd/recvmsg/SO_RXQ_OVFL in UDP
- Update chaos README: add congestion/ECN scenario docs, ingress
traffic control, and iperf3 JSON capture sections
- Update README.md: add ECN to features list and "What works today";
update transport and tooling entries
Non-FIPS clients (e.g., TLS connections) hitting the TCP listen port
produce misleading "unknown FMP phase" errors because the stream reader
checked phase before version. A TLS ClientHello (byte 0x16) parsed as
version=1, phase=6.
Add UnknownVersion error variant and check the version nibble before
phase dispatch, so non-FIPS connections now report "unknown FMP version: 1"
instead of "unknown FMP phase: 0x06".
Ethernet requires a minimum 46-byte payload (60-byte frame minus
14-byte header). NICs/drivers pad shorter frames with zeros. The
Ethernet transport had no length field, so the receiver included
padding bytes in the ciphertext, causing AEAD (ChaCha20-Poly1305)
authentication tag mismatch on small frames like heartbeats (39 bytes
with prefix, padded to 46).
Add a 2-byte little-endian payload length field after the frame type
byte. Wire format changes from [type:1][payload] to
[type:1][length:2 LE][payload]. The receiver uses the length field to
extract exactly the right number of bytes, ignoring any NIC padding.
Frame overhead increases from 1 to 3 bytes, effective MTU adjusted
accordingly. This is a wire-format breaking change requiring
simultaneous upgrade of all Ethernet peers.
Two bugs prevented Path MTU Discovery from working across heterogeneous
links (e.g., ethernet→UDP boundary):
1. ICMPv6 Packet Too Big wrote the MTU as u16 into a 32-bit field
(RFC 4443 §3.2), causing the kernel to read an inflated value.
Fixed by changing build_packet_too_big() to use u32 and writing
all 4 bytes.
2. handle_tun_outbound() only checked the local transport MTU, not
the per-destination PathMtuState updated by MtuExceeded signals.
Added a PathMtuState check after session lookup so subsequent
oversized packets generate ICMPv6 PTB on TUN instead of being
forwarded and dropped at the bottleneck hop.
Added integration test exercising the full PMTUD loop across a 3-node
chain with heterogeneous MTUs: oversized packet → forwarding failure →
MtuExceeded signal → PathMtuState update → ICMPv6 PTB on TUN.
evaluate_parent() did not check whether a candidate peer's ancestry
path already contained our own node_addr. Two nodes (e.g., sidecar and
VPS) could each select the other as parent, creating an alternating
coordinate loop that grew unbounded on each TreeAnnounce exchange.
Add loop detection in two places:
- evaluate_parent(): skip candidates whose ancestry contains us
- handle_tree_announce(): detect when current parent's updated ancestry
contains us and drop the parent instead of propagating the loop
Tailscale-style sidecar pattern: a FIPS container provides mesh
networking, and a companion app container shares its network namespace
via network_mode: service:fips.
Security model:
- iptables enforces strict isolation — the app container can only
communicate over the FIPS mesh (fd::/8 via fips0)
- No IPv4 access: eth0 restricted to FIPS UDP transport (port 2121)
- No IPv6 on eth0: ip6tables blocks all eth0 IPv6 traffic
- Only fips0 and loopback are reachable from the app container
The sidecar accepts peer configuration via environment variables
(FIPS_NSEC, FIPS_PEER_NPUB, FIPS_PEER_ADDR), so it can be pointed
at any FIPS node without config file generation.
Files:
- testing/sidecar/: Dockerfile, Dockerfile.app, docker-compose.yml,
entrypoint.sh, .env, resolv.conf, scripts/build.sh
- testing/sidecar/README.md: security model, quick-start, architecture,
DNS resolution, troubleshooting, production considerations
- testing/sidecar/scripts/test-sidecar.sh: 3-node chain integration
test verifying link establishment, multi-hop connectivity, and
network isolation on each app container
- .github/workflows/ci.yml: sidecar integration test matrix entry
Chaos harness enhancements:
- transport_mix config: weighted random transport assignment for random
topologies (erdos_renyi, random_geometric) with UDP/Ethernet/TCP
- Replace LoRa with Bluetooth L2CAP in cost-based/mixed-tech scenarios
using realistic netem values (15-40ms delay, 5-15ms jitter, 2-8% loss)
- New churn-20-mixed scenario: 20-node Erdos-Renyi with 60% UDP,
20% Ethernet, 20% TCP, full netem/link-flap/churn/bandwidth config
- Expanded chaos README with full scenario catalog in four categories
Static harness:
- Updated README with topology table and scenario count
Implement TCP transport for FIPS enabling firewall traversal and serving
as the foundation for future Tor transport. This is the first
connection-oriented transport in the system.
Key design decisions:
- FMP header-based framing: reuses existing 4-byte FMP common prefix for
packet boundary recovery with zero framing overhead
- Session survives TCP reconnection: Noise/MMP/FSP state bound to npub,
not TCP connection; MMP liveness is sole authority for peer death
- Connect-on-send: fresh connection on first send, transparent reconnect
- close_connection() trait method for cross-connection deduplication cleanup
New transport files:
- src/transport/tcp/mod.rs: TcpTransport, connection pool, accept loop
- src/transport/tcp/stream.rs: FMP-aware stream reader (shared with Tor)
Modified: transport trait (close_connection), TcpConfig, TransportHandle
match arms, create_transports(), initiate_connection() for connection-
oriented links, cross-connection tie-breaker cleanup, design docs.
Tree announce loop and TCP stability fixes:
- Preserve tree announce rate-limit state across reconnection: carry
forward last_tree_announce_sent_ms when a peer reconnects so the
rate-limit window isn't reset to zero
- Drop oversize TCP packets at sender: pre-send MTU check returns
MtuExceeded instead of writing to the stream, preventing receiver-side
connection teardown and reset-reconnect cycles
Chaos harness:
- TCP transport support: tcp_edges/has_tcp/tcp_peers in SimTopology,
transport-aware config_gen with per-edge transport type, TCP port 443,
pure-TCP node support
- Include all non-Ethernet edges in directed_outbound()
- Fix netem/links log messages to say "IP-based" instead of "UDP"
- Add tcp-chain, tcp-only, and tcp-mesh scenario files
Static harness:
- Transport-aware config generation (get_default_transport, transport_port)
- TCP transport injection via Python post-processing
- Add tcp-chain topology and docker-compose profile
When a peer container is restarted during node churn, the veth pair is
destroyed and recreated. The beacon sender's AF_PACKET socket becomes
stale, producing ENXIO (os error 6) on every send with no recovery.
The beacon sender loop now tracks consecutive send errors and, after 3
consecutive ENXIO failures, attempts to open a fresh AF_PACKET socket
on the same interface. Only the first error in a streak is logged at
warn level to avoid log spam. On successful reopen, beacons resume
normally, allowing peer rediscovery.
Also adds reopen_beacon_socket() helper that creates and wraps a new
PacketSocket without needing access to the EthernetTransport struct.
Update the default UDP bind port from 4000 to 2121 (decimal) and the
default Ethernet EtherType from 0x88B5 to 0x2121 across all source
code, documentation, configuration templates, test fixtures, and
scripts. Remove references to "IEEE 802 experimental range" since
0x2121 is not in that range.
Implement raw Ethernet transport using AF_PACKET SOCK_DGRAM on Linux
with EtherType 0x88B5 (IEEE experimental range) and 1-byte frame type
prefix (0x00=data, 0x01=beacon).
Transport implementation:
- EthernetConfig with interface, ethertype, MTU, buffer sizes, and
four independent discovery knobs (discovery, announce, auto_connect,
accept_connections)
- PacketSocket/AsyncPacketSocket wrappers with ioctl helpers for
interface index, MAC address, and MTU queries
- EthernetTransport with Transport trait impl, async start/stop/send,
receive loop dispatching data frames and discovery beacons
- Discovery beacons (34 bytes: type + version + x-only pubkey) with
DiscoveryBuffer for peer accumulation and dedup
- Atomic statistics counters (frames, bytes, errors, beacons)
- Platform-gated with #[cfg(target_os = "linux")]
Transport-layer discovery integration:
- Promote auto_connect() and accept_connections() to Transport trait
with default implementations and TransportHandle dispatch
- Extract initiate_connection() so both static peer config and
discovery auto-connect share the same handshake initiation path
- Add poll_transport_discovery() to the tick handler to drain
discovery buffers and auto-connect to discovered peers
- Enforce accept_connections() in handle_msg1() — transports with
accept_connections=false silently drop inbound handshakes
Node integration:
- create_transports() handles Ethernet named instances
- resolve_ethernet_addr() parses "interface/mac" address format
- transport_mtu() generalized for multi-transport operation
Test harness:
- VethPair RAII struct for veth pair lifecycle management
- Three #[ignore] integration tests requiring root/CAP_NET_RAW:
two-node handshake, data exchange, mixed transport coexistence
- Chaos harness: transport-aware topology model, VethManager for
veth pairs between Docker containers, Ethernet-aware config gen,
netem split (HTB+u32 for UDP, root netem for veth), transport-aware
link flaps and node churn with veth re-setup
- Container entrypoint waits for configured Ethernet interfaces
before starting FIPS (handles veth creation timing)
- New scenarios: ethernet-only (4-node ring), ethernet-mesh (6-node
mixed UDP+Ethernet with netem and link flaps)
Documentation:
- fips-transport-layer.md: Ethernet section, beacon discovery, WiFi
compatibility, updated discovery state, trait surface additions,
implementation status table
- fips-configuration.md: Ethernet parameter table, named instances,
peer address format, mixed UDP+Ethernet example, complete reference
- fips-wire-formats.md: Ethernet frame type prefix note
Rework top-level README: add badges, status/roadmap section, config
search path docs, minimal two-node example with transports, DNS setup
instructions with systemd-resolved and resolv.conf examples, and
connectivity test walkthrough.
Replace ASCII document-relationship diagram with SVG in design docs.
Change DNS resolver default from disabled to enabled (port 5354).
Update config merge to allow higher-priority configs to disable it.
Bump rand (0.8→0.10), rtnetlink (0.14→0.20), tun (0.7→0.8),
simple-dns (0.9→0.11), socket2 (0.5→0.6), and criterion (0.5→0.8).
Migrate all rand call sites: thread_rng()→rng(), gen()→random(),
gen_range()→random_range(), RngCore→Rng trait. Work around secp256k1
0.30 requiring rand 0.8 by generating random bytes directly and
constructing SecretKey from slice.
Migrate rtnetlink to builder-based API: LinkSetRequest replaced with
LinkUnspec builder + change(), RouteAddRequest replaced with
RouteMessageBuilder.
Remove bloom benchmark (criterion 0.8 incompatible with old harness
config).
Wire format diagrams:
- Add 24 SVG diagrams covering every FMP and FSP wire format: common
prefix, established frame headers, Noise IK handshake messages,
handshake flow, TreeAnnounce, AncestryEntry, FilterAnnounce,
LookupRequest/Response, SessionDatagram, Disconnect, SenderReport,
ReceiverReport, FSP complete message, SessionSetup/Ack/Msg3,
PathMtuNotification, CoordsRequired, PathBroken, and MtuExceeded
- Replace ASCII art in fips-wire-formats.md with SVG references
- Apply text edits to fips-mesh-layer.md, fips-mesh-operation.md,
fips-transport-layer.md, and fips-ipv6-adapter.md
Spanning tree dynamics:
- Add 12 topology SVG diagrams: node join (overview + 3-panel steps),
three-node convergence (4-panel), link addition with depth labels,
link removal, partition formation, and 6 real-world example diagrams
(office, mixed-link, two-site WAN topologies)
- Rewrite all code blocks to narrative prose with diagram references
- Add inline prior art attributions distinguishing Yggdrasil-derived
concepts from FIPS-novel contributions
- Add 3 new references (De Couto ETX, IEEE 802.1D, RFC 2328 OSPF) and
Prior Art summary
- Remove outdated sections: indirect partition note, integration test
gaps, DHT-based lookup reference
- Change "must elect a new root" to "must rediscover its new root"
Spanning tree design review (fips-spanning-tree.md):
- Rename "Root Election" to "Root Discovery" across docs
- Add "What Is a Spanning Tree?" introductory section
- Add parent selection intro explaining self-organization role
- Fix tree distance example: 4 hops, not 2
- Clarify timestamp field as advisory only
- Remove unimplemented ROOT_TIMEOUT and TREE_ENTRY_TTL from timing
parameters and implementation status tables
Bloom filter design review (fips-bloom-filters.md):
- Add "What Is a Bloom Filter?" intro section
- Rewrite Purpose section to frame filters as routing path identification
- Correct FPR analysis (old values were 3-50x overstated)
- Add Filter Occupancy Model based on network size and tree position
- Fix filter expiration to describe actual MMP-based cleanup
- Combine Scale Considerations with Size Classes after Wire Format
- Fix stale FPR values in src/bloom/mod.rs comments
Session layer review (fips-session-layer.md):
- Add inline prior art attributions: Noise Protocol Framework, WireGuard,
DTLS (RFC 6347), IKEv2 (RFC 7296), RFC 1191 PMTUD, Yggdrasil, NIP-44
- Replace warmup state machine ASCII art with SVG diagram
- Convert CoordsWarmup wire format code block to prose
- Add External References section with full citations
Level 5 implementation doc cleanup:
- Delete fips-software-architecture.md (redundant with protocol layer docs)
- Delete fips-state-machines.md (Rust tutorial, not protocol design)
- Add fipsctl command reference to README.md
- Update cross-references in fips-intro.md, docs/design/README.md,
fips-transport-layer.md, fips-configuration.md
Fixes:
- Correct fd::/8 to fd00::/8 in fips-session-layer.md,
fips-identity-derivation.svg, and fips-node-architecture.svg
- Fix config example MTU: 1197 → 1472 in fips-configuration.md
File organization:
- Move all SVG diagrams into docs/design/diagrams/ subdirectory
- Update all diagram references to use new paths
Track parent switch frequency in a sliding window. When switches exceed
a configurable threshold (default 4 in 60s), impose an extended hold-down
period (default 120s) that prevents non-mandatory parent changes.
Mandatory switches (parent loss, root change, shouldn't-be-root) bypass
dampening. The flap counter resets when the window expires naturally.
Implements TASK-2026-0030 / IDEA-0013.
Track consecutive send failures in SenderState. Apply 2^n backoff
multiplier (capped at 32x) to the report interval. Suppress debug
logs after 3 consecutive failures, emit recovery summary on success.
Johnathan Corgan