feat(v2): hand-rolled NIP-44 v2 crypto + reference-vector tests (#29 v1)
LNbits ships only NIP-04 (AES-CBC) in lnbits.utils.nostr.encrypt_content,
but the locked design at #29 (paired with lamassu-next#56) wires kind-30078
cassette config with NIP-44 v2 content per the privacy-by-default
architecture (dcd0874). Hand-rolling rather than adding a Python lib dep
per the plan-approval (option A) — keeps the impl auditable inline and
avoids pulling in a non-trivial dep tree.
nip44.py covers the full envelope:
- get_conversation_key — ECDH x-coord + HKDF-extract with salt b"nip44-v2"
- encrypt_with_conversation_key / decrypt_with_conversation_key — low-level,
nonce-controllable for testing pinned vectors
- encrypt_for / decrypt_from — high-level pair-keyed API (the shape app
code reaches for)
- _pad / _unpad — NIP-44 v2 length-prefixed padding scheme
- HMAC-SHA256 verification on nonce || ciphertext, constant-time compare
via hmac.compare_digest
- Typed errors (Nip44VersionError / Nip44MacError / Nip44LengthError)
so callers can distinguish tamper from corruption from spec mismatch
Stack: coincurve for ECDH (already a transitive lnbits dep), cryptography
for ChaCha20 + HKDF-expand (also already there). No new pyproject deps.
34 tests in tests/test_nip44_v2.py, three layers:
1. Pinned reference vector — conversation_key for (sec=1, sec=2) matches
the canonical paulmillr/nip44 published value
(c41c775356fd92eadc63ff5a0dc1da211b268cbea22316767095b2871ea1412d).
Regression-fails loudly if key derivation drifts.
2. Round-trip + tamper detection — encrypt/decrypt across plaintext
lengths (1, 32, 33, 1000, 5000, 65535 bytes); flipped MAC byte;
flipped ciphertext byte; flipped nonce byte; wrong recipient privkey;
version-byte rejection; padding-formula spot checks.
3. Cross-impl byte-compat — placeholder test_decrypts_bitspire_sample
marked @pytest.mark.skip, pending bitspire posting a sample event
encrypted on their nostr-tools side to the coord log (per the
2026-05-30T15:55Z entry). Wire that fixture and unskip when posted.
Total: 132 passed, 1 skipped (cross-test fixture pending), 1 pre-existing
async-plugin failure unchanged.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
parent
9b8008db1f
commit
da07bae554
2 changed files with 543 additions and 0 deletions
272
tests/test_nip44_v2.py
Normal file
272
tests/test_nip44_v2.py
Normal file
|
|
@ -0,0 +1,272 @@
|
|||
"""
|
||||
Tests for the hand-rolled NIP-44 v2 implementation in `nip44.py`.
|
||||
|
||||
Three layers of validation, ordered by trust:
|
||||
1. Pinned reference vector from the canonical paulmillr/nip44 test suite —
|
||||
the conversation_key for (sec=1, sec=2) is widely-published as
|
||||
c41c775356fd92eadc63ff5a0dc1da211b268cbea22316767095b2871ea1412d. If
|
||||
our get_conversation_key() ever drifts from that value, the impl is
|
||||
broken at the key-derivation layer.
|
||||
2. Round-trip + tamper detection — verifies the encrypt/decrypt loop
|
||||
under random nonces, catches HMAC + version + padding tampering.
|
||||
3. Cross-test (TBD) — bitspire will post one sample event encrypted on
|
||||
their nostr-tools side to the coord log; test_decrypts_bitspire_sample
|
||||
wires it as a fixture and asserts byte-compatibility with the
|
||||
nostr-tools NIP-44 v2 impl. Placeholder stub until the sample lands.
|
||||
"""
|
||||
|
||||
import base64
|
||||
|
||||
import coincurve
|
||||
import pytest
|
||||
|
||||
from ..nip44 import (
|
||||
Nip44LengthError,
|
||||
Nip44MacError,
|
||||
Nip44VersionError,
|
||||
_calc_padded_len,
|
||||
decrypt_from,
|
||||
decrypt_with_conversation_key,
|
||||
encrypt_for,
|
||||
encrypt_with_conversation_key,
|
||||
get_conversation_key,
|
||||
)
|
||||
|
||||
# Helper: derive a compressed-x-coord pubkey hex string from a secret hex.
|
||||
def _pub_hex(sec_hex: str) -> str:
|
||||
return (
|
||||
coincurve.PrivateKey(bytes.fromhex(sec_hex))
|
||||
.public_key.format(compressed=True)[1:]
|
||||
.hex()
|
||||
)
|
||||
|
||||
|
||||
# Canonical test keys widely used across NIP-44 reference vectors.
|
||||
_SEC_ONE = "00" * 31 + "01" # integer 1
|
||||
_SEC_TWO = "00" * 31 + "02" # integer 2
|
||||
_PUB_ONE = _pub_hex(_SEC_ONE)
|
||||
_PUB_TWO = _pub_hex(_SEC_TWO)
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# Layer 1 — pinned reference vector (paulmillr/nip44)
|
||||
# =============================================================================
|
||||
|
||||
|
||||
class TestConversationKeyReferenceVector:
|
||||
"""Pinned reference vector from the canonical NIP-44 v2 test suite
|
||||
(paulmillr/nip44). If get_conversation_key drifts from this value we
|
||||
have a key-derivation regression — fail loudly."""
|
||||
|
||||
REFERENCE_CK_HEX = (
|
||||
"c41c775356fd92eadc63ff5a0dc1da211b268cbea22316767095b2871ea1412d"
|
||||
)
|
||||
|
||||
def test_sec_one_pub_two(self):
|
||||
ck = get_conversation_key(_SEC_ONE, _PUB_TWO)
|
||||
assert ck.hex() == self.REFERENCE_CK_HEX
|
||||
|
||||
def test_sec_two_pub_one_is_symmetric(self):
|
||||
"""Conversation key is symmetric: ck(privA, pubB) == ck(privB, pubA).
|
||||
Both sides of a NIP-44 conversation derive the identical PRK; this
|
||||
is what lets the recipient decrypt with their own privkey + the
|
||||
sender's pubkey."""
|
||||
ck_ab = get_conversation_key(_SEC_ONE, _PUB_TWO)
|
||||
ck_ba = get_conversation_key(_SEC_TWO, _PUB_ONE)
|
||||
assert ck_ab == ck_ba
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# Layer 2 — round-trip + tamper detection
|
||||
# =============================================================================
|
||||
|
||||
|
||||
class TestRoundTrip:
|
||||
"""Encrypt then decrypt under the high-level pair-keyed API."""
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"plaintext",
|
||||
[
|
||||
"a", # 1 byte (minimum)
|
||||
"hello, nip44 v2", # short
|
||||
"x" * 32, # exactly the small-payload boundary
|
||||
"x" * 33, # just over
|
||||
"y" * 1000, # medium
|
||||
"z" * 5000, # large
|
||||
'{"denominations": {"20": {"position": 1, "count": 49}}}', # realistic
|
||||
],
|
||||
)
|
||||
def test_round_trip_various_lengths(self, plaintext):
|
||||
payload = encrypt_for(plaintext, _SEC_ONE, _PUB_TWO)
|
||||
recovered = decrypt_from(payload, _SEC_TWO, _PUB_ONE)
|
||||
assert recovered == plaintext
|
||||
|
||||
def test_payloads_are_unique_under_random_nonce(self):
|
||||
"""Same plaintext + same key pair should produce different payloads
|
||||
each time because the nonce is fresh CSPRNG bytes. Catches a
|
||||
regression where the nonce is accidentally pinned."""
|
||||
plaintext = "the same message"
|
||||
p1 = encrypt_for(plaintext, _SEC_ONE, _PUB_TWO)
|
||||
p2 = encrypt_for(plaintext, _SEC_ONE, _PUB_TWO)
|
||||
assert p1 != p2
|
||||
assert decrypt_from(p1, _SEC_TWO, _PUB_ONE) == plaintext
|
||||
assert decrypt_from(p2, _SEC_TWO, _PUB_ONE) == plaintext
|
||||
|
||||
def test_pinned_nonce_is_deterministic(self):
|
||||
"""Same plaintext + same key pair + same nonce = byte-identical
|
||||
payload. Regression-locks the chacha20 + hmac chain."""
|
||||
ck = get_conversation_key(_SEC_ONE, _PUB_TWO)
|
||||
nonce = bytes(32) # 32 zero bytes
|
||||
p1 = encrypt_with_conversation_key("a", ck, nonce=nonce)
|
||||
p2 = encrypt_with_conversation_key("a", ck, nonce=nonce)
|
||||
assert p1 == p2
|
||||
assert decrypt_with_conversation_key(p1, ck) == "a"
|
||||
|
||||
|
||||
class TestTamperDetection:
|
||||
"""HMAC-SHA256 verification catches tampered envelopes. The cryptographic
|
||||
construction depends on this — if HMAC verification ever no-ops, a
|
||||
relay-MITM could forge ATM state events."""
|
||||
|
||||
def _payload(self) -> str:
|
||||
return encrypt_for("important message", _SEC_ONE, _PUB_TWO)
|
||||
|
||||
def test_flipped_mac_byte_rejected(self):
|
||||
raw = bytearray(base64.b64decode(self._payload()))
|
||||
raw[-1] ^= 0x01
|
||||
tampered = base64.b64encode(bytes(raw)).decode("ascii")
|
||||
with pytest.raises(Nip44MacError):
|
||||
decrypt_from(tampered, _SEC_TWO, _PUB_ONE)
|
||||
|
||||
def test_flipped_ciphertext_byte_rejected(self):
|
||||
raw = bytearray(base64.b64decode(self._payload()))
|
||||
# Flip a byte in the middle of the ciphertext segment
|
||||
# (version[1] + nonce[32..32] + ciphertext[33..-32] + mac[-32..])
|
||||
ct_start = 1 + 32
|
||||
raw[ct_start + 5] ^= 0x01
|
||||
tampered = base64.b64encode(bytes(raw)).decode("ascii")
|
||||
with pytest.raises(Nip44MacError):
|
||||
decrypt_from(tampered, _SEC_TWO, _PUB_ONE)
|
||||
|
||||
def test_flipped_nonce_byte_rejected(self):
|
||||
raw = bytearray(base64.b64decode(self._payload()))
|
||||
# Nonce starts at byte 1 (after version)
|
||||
raw[1] ^= 0x01
|
||||
tampered = base64.b64encode(bytes(raw)).decode("ascii")
|
||||
with pytest.raises(Nip44MacError):
|
||||
decrypt_from(tampered, _SEC_TWO, _PUB_ONE)
|
||||
|
||||
def test_wrong_recipient_privkey_rejected(self):
|
||||
"""The MAC is derived from the conversation key, so a wrong
|
||||
recipient privkey produces a different conversation key →
|
||||
different hmac_key → MAC verification fails. (Doesn't decrypt
|
||||
to garbage; fails fast.)"""
|
||||
sec_three = "00" * 31 + "03"
|
||||
with pytest.raises(Nip44MacError):
|
||||
decrypt_from(self._payload(), sec_three, _PUB_ONE)
|
||||
|
||||
|
||||
class TestVersionRejection:
|
||||
def test_v1_byte_rejected(self):
|
||||
raw = bytearray(base64.b64decode(encrypt_for("x", _SEC_ONE, _PUB_TWO)))
|
||||
raw[0] = 0x01
|
||||
bad = base64.b64encode(bytes(raw)).decode("ascii")
|
||||
with pytest.raises(Nip44VersionError):
|
||||
decrypt_from(bad, _SEC_TWO, _PUB_ONE)
|
||||
|
||||
def test_unknown_version_byte_rejected(self):
|
||||
raw = bytearray(base64.b64decode(encrypt_for("x", _SEC_ONE, _PUB_TWO)))
|
||||
raw[0] = 0xFF
|
||||
bad = base64.b64encode(bytes(raw)).decode("ascii")
|
||||
with pytest.raises(Nip44VersionError):
|
||||
decrypt_from(bad, _SEC_TWO, _PUB_ONE)
|
||||
|
||||
|
||||
class TestLengthGuards:
|
||||
def test_empty_plaintext_rejected(self):
|
||||
with pytest.raises(Nip44LengthError):
|
||||
encrypt_for("", _SEC_ONE, _PUB_TWO)
|
||||
|
||||
def test_plaintext_at_max_length_accepted(self):
|
||||
plaintext = "x" * 65535
|
||||
payload = encrypt_for(plaintext, _SEC_ONE, _PUB_TWO)
|
||||
assert decrypt_from(payload, _SEC_TWO, _PUB_ONE) == plaintext
|
||||
|
||||
def test_plaintext_over_max_rejected(self):
|
||||
with pytest.raises(Nip44LengthError):
|
||||
encrypt_for("x" * 65536, _SEC_ONE, _PUB_TWO)
|
||||
|
||||
def test_invalid_base64_payload_rejected(self):
|
||||
with pytest.raises(Nip44LengthError):
|
||||
decrypt_from("not!!!base64@@@", _SEC_TWO, _PUB_ONE)
|
||||
|
||||
def test_payload_too_short_rejected(self):
|
||||
# 50 bytes is well under the 99-byte minimum
|
||||
too_short = base64.b64encode(b"\x02" + b"\x00" * 49).decode("ascii")
|
||||
with pytest.raises(Nip44LengthError):
|
||||
decrypt_from(too_short, _SEC_TWO, _PUB_ONE)
|
||||
|
||||
|
||||
class TestPaddingFormula:
|
||||
"""Spot-check the _calc_padded_len formula against hand-computed cases.
|
||||
Locks in the NIP-44 v2 padding scheme so a refactor can't silently
|
||||
break wire compatibility (which would only surface as cross-impl
|
||||
decryption failures — exactly what test_decrypts_bitspire_sample is
|
||||
meant to catch end-to-end, but a unit test here is cheaper)."""
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"plaintext_len,expected_padded",
|
||||
[
|
||||
(1, 32), # <= 32 → 32
|
||||
(16, 32),
|
||||
(32, 32),
|
||||
(33, 64), # > 32 → next chunk
|
||||
(64, 64),
|
||||
(65, 96), # chunk = 32 for L=65 (next_power(64) = 64; 64//8 = 8; max(32, 8) = 32)
|
||||
(100, 128),
|
||||
(128, 128),
|
||||
# L=129: next_power(128) = 1<<8 = 256; chunk = max(32, 256//8) = 32;
|
||||
# padded = 32 * (128//32 + 1) = 32 * 5 = 160.
|
||||
(129, 160),
|
||||
(256, 256), # chunk = 32 for L=256 (next_power(255)=256; max(32, 32) = 32)
|
||||
(257, 320),
|
||||
(1000, 1024), # chunk = 128 for L=1000 (next_power(999)=1024; max(32, 128) = 128)
|
||||
],
|
||||
)
|
||||
def test_calc_padded_len(self, plaintext_len, expected_padded):
|
||||
assert _calc_padded_len(plaintext_len) == expected_padded
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# Layer 3 — byte-compat cross-test against nostr-tools (bitspire's impl)
|
||||
# =============================================================================
|
||||
|
||||
|
||||
@pytest.mark.skip(
|
||||
reason=(
|
||||
"Waiting on bitspire to post one sample encrypted event to "
|
||||
"~/dev/coordination/log.md per the 2026-05-30T15:55Z entry. Once "
|
||||
"posted, hardcode the (event_id, content, recipient_privkey, "
|
||||
"expected_plaintext) fixture here and remove the skip — this test "
|
||||
"is the byte-compat cross-test between our hand-rolled NIP-44 v2 "
|
||||
"and the nostr-tools impl the ATM uses."
|
||||
)
|
||||
)
|
||||
def test_decrypts_bitspire_sample_event_from_coord_log():
|
||||
"""Cross-impl byte-compatibility test. Bitspire generates one event on
|
||||
their side (nostr-tools NIP-44 v2 impl), posts the raw event JSON +
|
||||
a known throwaway recipient privkey to the coord log, and we assert
|
||||
our `decrypt_from` recovers the expected `{"denominations": {...}}`
|
||||
plaintext.
|
||||
|
||||
If this passes, both impls produce byte-identical wire format. If it
|
||||
fails, the spec ambiguity surfaces before either side ships — exactly
|
||||
what bitspire flagged in the plan review (`07:55Z`).
|
||||
"""
|
||||
# event_b64_content = "..." # paste from coord log
|
||||
# sender_pubkey_hex = "..."
|
||||
# recipient_privkey_hex = "..."
|
||||
# expected_plaintext = '{"denominations": {"20": {"position": 1, "count": 49}}}'
|
||||
# recovered = decrypt_from(event_b64_content, recipient_privkey_hex, sender_pubkey_hex)
|
||||
# assert recovered == expected_plaintext
|
||||
raise NotImplementedError("fixture pending — see skip reason")
|
||||
Loading…
Add table
Add a link
Reference in a new issue