fix(secret): authenticate bottled-secret encryption (#468)

The per-bottle egress-secret encryption (secret_store.py) was
unauthenticated CTR/XOR: decrypting with the WRONG ENV_VAR_SECRET
produced garbage that decrypt_value only rejected when it wasn't valid
UTF-8. For short token values that garbage is coincidentally valid UTF-8
~5% of the time, so `reprovision_from_secret` would occasionally "succeed"
with a wrong key and inject a garbage egress credential — and
test_reprovision_rejects_missing_rows_and_wrong_key failed ~5% of runs
(flaky CI, surfaced by this stack's unit job).

Switch to authenticated encrypt-then-MAC: append an HMAC-SHA256 tag over
`nonce || ciphertext`, keyed by a domain-separated MAC subkey derived from
the ENV_VAR_SECRET. decrypt_value verifies the tag (constant-time) before
returning any plaintext, so a wrong key or tampered ciphertext is rejected
deterministically. Blob format is now `nonce || ciphertext || tag`
(the stored rows are transient — re-written every launch — so no
migration is needed).

Pre-existing bug on main, unrelated to the transport work, but it blocks
this stack's CI. Tests: wrong key rejected 200/200; tampered ciphertext
rejected; round-trips unchanged. Deterministic now (was ~5% flaky).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

bot_bottle/orchestrator/store/secret_store.py

@@ -12,12 +12,22 @@ reattachment path reads ENV_VAR_SECRET from the running agent container via
 ``POST /bottles/<id>/reprovision_gateway``; the orchestrator decrypts the
 stored rows and re-populates ``_tokens``.
 
-Encryption scheme: HMAC-SHA256 used as a PRF in CTR mode (stdlib-only,
-no external deps). Each value is encrypted independently. The output blob is
-``nonce (16 bytes) || ciphertext`` encoded as URL-safe base64 (no padding).
+Encryption scheme: HMAC-SHA256 used as a PRF in CTR mode, **authenticated**
+encrypt-then-MAC (stdlib-only, no external deps). Each value is encrypted
+independently. The output blob is ``nonce (16 bytes) || ciphertext || tag
+(32 bytes)`` encoded as URL-safe base64 (no padding).
 
     keystream_block_i = HMAC-SHA256(key, nonce || i.to_bytes(4, "big"))
     ciphertext_i      = plaintext_i XOR keystream_block_i[:len(plaintext_i)]
+    mac_key           = HMAC-SHA256(key, "bottled-secret-mac-v1")
+    tag               = HMAC-SHA256(mac_key, nonce || ciphertext)
+
+The tag is what makes a **wrong key deterministically detectable**: without it,
+CTR decryption with the wrong key yields garbage that only fails when it isn't
+valid UTF-8 (so ``reprovision`` would sometimes "succeed" with a wrong
+ENV_VAR_SECRET and inject garbage egress tokens). The MAC key is derived from
+the ENV_VAR_SECRET by a domain-separated HMAC so the same key never both
+generates the keystream and signs the tag with the same message shape.
 """
 
 from __future__ import annotations
@@ -29,6 +39,7 @@ import secrets
 
 _KEY_BYTES = 32    # 256-bit key from ENV_VAR_SECRET
 _NONCE_BYTES = 16  # 128-bit random nonce per encrypt call
+_TAG_BYTES = 32    # HMAC-SHA256 authentication tag
 _BLOCK = 32        # HMAC-SHA256 output width == one keystream block
 
 # Env-var name the agent container receives at startup.
@@ -50,45 +61,58 @@ def _keystream(key: bytes, nonce: bytes, block_index: int) -> bytes:
     ).digest()
 
 
+def _tag(key: bytes, nonce: bytes, ciphertext: bytes) -> bytes:
+    """The authentication tag over ``nonce || ciphertext``, keyed by a MAC
+    subkey domain-separated from the keystream key."""
+    mac_key = hmac.new(key, b"bottled-secret-mac-v1", hashlib.sha256).digest()
+    return hmac.new(mac_key, nonce + ciphertext, hashlib.sha256).digest()
+
+
+def _ctr(key: bytes, nonce: bytes, data: bytes) -> bytes:
+    """CTR keystream XOR — its own inverse, so it both encrypts and decrypts."""
+    out = bytearray()
+    for i in range(0, len(data), _BLOCK):
+        chunk = data[i : i + _BLOCK]
+        ks = _keystream(key, nonce, i)[: len(chunk)]
+        out.extend(b ^ k for b, k in zip(chunk, ks))
+    return bytes(out)
+
+
 def encrypt_value(secret_b64: str, plaintext: str) -> str:
     """Encrypt a single string value with *secret_b64* (the ENV_VAR_SECRET).
 
-    Returns a URL-safe base64 blob ``nonce || ciphertext`` suitable for
+    Returns a URL-safe base64 blob ``nonce || ciphertext || tag`` suitable for
     the ``bottled_agent_secrets.value`` column."""
     key = _b64dec(secret_b64)
-    pt = plaintext.encode()
     nonce = secrets.token_bytes(_NONCE_BYTES)
-    ct = bytearray()
-    for i in range(0, len(pt), _BLOCK):
-        chunk = pt[i : i + _BLOCK]
-        ks = _keystream(key, nonce, i)[: len(chunk)]
-        ct.extend(p ^ k for p, k in zip(chunk, ks))
-    return base64.urlsafe_b64encode(nonce + bytes(ct)).rstrip(b"=").decode()
+    ct = _ctr(key, nonce, plaintext.encode())
+    tag = _tag(key, nonce, ct)
+    return base64.urlsafe_b64encode(nonce + ct + tag).rstrip(b"=").decode()
 
 
 def decrypt_value(secret_b64: str, blob_b64: str) -> str:
     """Decrypt a blob produced by :func:`encrypt_value`.
 
     Returns the original plaintext string. Raises ``ValueError`` for malformed
-    input or a key mismatch (wrong key produces garbage, not an error, unless
-    the plaintext is non-UTF-8 — treat all such failures as wrong key)."""
+    input, a **wrong key**, or a tampered ciphertext — all caught by the
+    authentication tag before any plaintext is returned, so a wrong
+    ENV_VAR_SECRET is rejected deterministically (never a garbage token)."""
     key = _b64dec(secret_b64)
     try:
         blob = _b64dec(blob_b64)
     except Exception as exc:
         raise ValueError(f"invalid ciphertext blob: {exc}") from exc
-    if len(blob) < _NONCE_BYTES:
+    if len(blob) < _NONCE_BYTES + _TAG_BYTES:
         raise ValueError("ciphertext blob too short")
-    nonce, ciphertext = blob[:_NONCE_BYTES], blob[_NONCE_BYTES:]
-    pt = bytearray()
-    for i in range(0, len(ciphertext), _BLOCK):
-        chunk = ciphertext[i : i + _BLOCK]
-        ks = _keystream(key, nonce, i)[: len(chunk)]
-        pt.extend(c ^ k for c, k in zip(chunk, ks))
+    nonce = blob[:_NONCE_BYTES]
+    tag = blob[-_TAG_BYTES:]
+    ciphertext = blob[_NONCE_BYTES:-_TAG_BYTES]
+    if not hmac.compare_digest(tag, _tag(key, nonce, ciphertext)):
+        raise ValueError("ciphertext failed authentication (wrong key or tampered)")
     try:
-        return bytes(pt).decode()
-    except UnicodeDecodeError as exc:
-        raise ValueError(f"decryption produced non-UTF-8 output (wrong key?): {exc}") from exc
+        return _ctr(key, nonce, ciphertext).decode()
+    except UnicodeDecodeError as exc:  # pragma: no cover - authenticated, so unreachable
+        raise ValueError(f"decryption produced non-UTF-8 output: {exc}") from exc
 
 
 __all__ = ["ENV_VAR_SECRET_NAME", "new_env_var_secret", "encrypt_value", "decrypt_value"]