feat(secrets): encrypt egress tokens at rest with per-bottle ENV_VAR_SECRET

Implements the interim secret-provider design (PRD prd-new-secret-provider):
each agent receives a random ENV_VAR_SECRET injected into its container env
at launch. The host uses this key to encrypt each egress auth token value
(HMAC-SHA256 CTR mode, stdlib-only) and store it in a new
bottled_agent_secrets table (one row per env var, key column plaintext for
auditing). The key never touches the DB.

On infra container restart the in-memory token map is lost. launch_consolidated
now calls _reprovision_running_bottles after ensure_running: for each
registered bottle still alive on the gateway network it execs
`printenv ENV_VAR_SECRET` into the agent container and posts the result to the
new POST /bottles/<id>/reprovision_gateway control-plane endpoint, which
decrypts the stored rows and restores _tokens — no manual intervention needed.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-07-22 00:12:34 +00:00
committed by didericis
parent 0f98d75eff
commit 572904df44
12 changed files with 346 additions and 12 deletions
+28 -3
View File
@@ -41,10 +41,13 @@ class OrchestratorClientError(RuntimeError):
@dataclass(frozen=True)
class RegisteredBottle:
"""What `POST /bottles` returns: the minted bottle id and the per-bottle
identity token the agent presents for app-layer attribution."""
identity token the agent presents for app-layer attribution. `env_var_secret`
is set by the caller (not from the server response) and carries the
encryption key so it can be injected into the agent container's env."""
bottle_id: str
identity_token: str
env_var_secret: str = ""
class OrchestratorClient:
@@ -120,17 +123,21 @@ class OrchestratorClient:
metadata: str = "",
policy: str = "",
tokens: dict[str, str] | None = None,
env_var_secret: str = "",
) -> RegisteredBottle:
"""Register a bottle and broker its launch (`POST /bottles`). `tokens`
are the per-bottle egress auth values (env_name -> value) the
orchestrator holds in memory for the gateway to inject. Returns the
minted id + identity token."""
orchestrator holds in memory for the gateway to inject. When
*env_var_secret* is provided, the orchestrator also encrypts the token
values and stores them in ``bottled_agent_secrets`` for restart
recovery. Returns the minted id + identity token."""
payload = self._ok("POST", "/bottles", {
"source_ip": source_ip,
"image_ref": image_ref,
"metadata": metadata,
"policy": policy,
"tokens": tokens or {},
"env_var_secret": env_var_secret,
})
bottle_id = payload.get("bottle_id")
token = payload.get("identity_token")
@@ -138,6 +145,24 @@ class OrchestratorClient:
raise OrchestratorClientError("register: response missing bottle_id/identity_token")
return RegisteredBottle(bottle_id=bottle_id, identity_token=token)
def reprovision_gateway(self, bottle_id: str, env_var_secret: str) -> bool:
"""Re-inject a bottle's egress tokens from its ENV_VAR_SECRET
(`POST /bottles/<id>/reprovision_gateway`). Returns True when the
orchestrator successfully decrypted and restored the tokens, False
when it had no stored secrets for this bottle (404)."""
status, _ = self._request(
"POST",
f"/bottles/{bottle_id}/reprovision_gateway",
{"env_var_secret": env_var_secret},
)
if status == 404:
return False
if not 200 <= status < 300:
raise OrchestratorClientError(
f"reprovision_gateway {bottle_id}: HTTP {status}"
)
return True
def teardown_bottle(self, bottle_id: str) -> bool:
"""Tear a bottle down (`DELETE /bottles/<id>`). False if the
orchestrator didn't know it (404) — idempotent for cleanup paths."""
+24 -1
View File
@@ -9,9 +9,13 @@ vsock / unix-socket portability caveats):
GET /bottles -> 200 {"bottles": [ <redacted record>, ...]}
POST /bottles -> 201 {"bottle_id","identity_token"} (launch)
body: {"source_ip", ["image_ref"],
["metadata"], ["policy"]}
["metadata"], ["policy"],
["tokens"], ["env_var_secret"]}
PUT /bottles/<bottle_id>/policy -> 200 {"updated": true} | 404 (live reload)
body: {"policy"}
POST /bottles/<bottle_id>/reprovision_gateway
-> 200 {"reprovisioned": true} | 404
body: {"env_var_secret"}
DELETE /bottles/<bottle_id> -> 200 {"torn_down": true} | 404 (teardown)
POST /reconcile -> 200 {"reaped": [bottle_id, ...]}
body: {"live_source_ips": [...],
@@ -116,12 +120,14 @@ def dispatch( # pylint: disable=too-many-return-statements,too-many-branches
tokens = {
k: v for k, v in raw_tokens.items() if isinstance(k, str) and isinstance(v, str)
} if isinstance(raw_tokens, dict) else {}
env_var_secret = data.get("env_var_secret", "")
rec = orch.launch_bottle(
source_ip,
image_ref=image_ref if isinstance(image_ref, str) else "",
metadata=metadata if isinstance(metadata, str) else "",
policy=policy if isinstance(policy, str) else "",
tokens=tokens,
env_var_secret=env_var_secret if isinstance(env_var_secret, str) else "",
)
return 201, {"bottle_id": rec.bottle_id, "identity_token": rec.identity_token}
@@ -138,6 +144,23 @@ def dispatch( # pylint: disable=too-many-return-statements,too-many-branches
return 200, {"updated": True}
return 404, {"error": "no such bottle"}
if (
method == "POST"
and route.startswith("/bottles/")
and route.endswith("/reprovision_gateway")
):
bottle_id = route[len("/bottles/") : -len("/reprovision_gateway")]
try:
data = _parse_json_object(body)
except ValueError as e:
return 400, {"error": f"invalid JSON: {e}"}
env_var_secret = data.get("env_var_secret")
if not isinstance(env_var_secret, str) or not env_var_secret:
return 400, {"error": "env_var_secret (string) is required"}
if orch.reprovision_from_secret(bottle_id, env_var_secret):
return 200, {"reprovisioned": True}
return 404, {"error": "no stored secrets for this bottle"}
if method == "DELETE" and route.startswith("/bottles/"):
bottle_id = route[len("/bottles/"):]
if orch.teardown_bottle(bottle_id):
+67
View File
@@ -113,6 +113,22 @@ _MIGRATIONS = TableMigrations(
# egress allowlist / routes / git config selected by source IP. The
# multi-tenant gateway resolves it per request via `attribute`.
"ALTER TABLE orchestrator_bottles ADD COLUMN policy TEXT NOT NULL DEFAULT ''",
# v4 — per-bottle encrypted egress secrets (PRD prd-new-secret-provider).
# One row per env-var: key (env-var name) is plaintext for auditing;
# value is the encrypted token string. The encryption key (ENV_VAR_SECRET)
# lives only in the agent's environment — a row alone cannot recover the
# credential.
"""
CREATE TABLE IF NOT EXISTS bottled_agent_secrets (
bottled_agent_id TEXT NOT NULL,
key TEXT NOT NULL,
value TEXT NOT NULL,
type TEXT NOT NULL DEFAULT 'injected_env_var'
)
""",
# v5 — index for fast per-bottle lookups and bulk DELETE on teardown.
"CREATE INDEX IF NOT EXISTS idx_bottled_agent_secrets_id "
"ON bottled_agent_secrets (bottled_agent_id, type)",
],
)
@@ -326,6 +342,57 @@ class RegistryStore(DbStore):
return None
return rec
# --- encrypted egress secret store ------------------------------------
def store_agent_secrets(
self,
bottle_id: str,
encrypted_values: dict[str, str],
secret_type: str = "injected_env_var",
) -> None:
"""Replace all stored secrets for *bottle_id* with *encrypted_values*
(env-var name → encrypted ciphertext). Deletes then re-inserts so a
re-registration is always consistent with the current token set."""
with self._connection() as conn:
conn.execute(
"DELETE FROM bottled_agent_secrets "
"WHERE bottled_agent_id = ? AND type = ?",
(bottle_id, secret_type),
)
conn.executemany(
"INSERT INTO bottled_agent_secrets "
"(bottled_agent_id, key, value, type) VALUES (?, ?, ?, ?)",
[(bottle_id, k, v, secret_type) for k, v in encrypted_values.items()],
)
self._chmod()
def get_agent_secrets(
self,
bottle_id: str,
secret_type: str = "injected_env_var",
) -> dict[str, str]:
"""Return {env_var_name: encrypted_value} for *bottle_id*, or {} if none."""
with self._connection() as conn:
rows = conn.execute(
"SELECT key, value FROM bottled_agent_secrets "
"WHERE bottled_agent_id = ? AND type = ?",
(bottle_id, secret_type),
).fetchall()
return {row[0]: row[1] for row in rows}
def delete_agent_secrets(
self,
bottle_id: str,
secret_type: str = "injected_env_var",
) -> None:
"""Remove all stored secrets for *bottle_id* (e.g. on teardown)."""
with self._connection() as conn:
conn.execute(
"DELETE FROM bottled_agent_secrets "
"WHERE bottled_agent_id = ? AND type = ?",
(bottle_id, secret_type),
)
__all__ = [
"BottleRecord",
+94
View File
@@ -0,0 +1,94 @@
"""Symmetric encryption for per-bottle egress secrets (PRD prd-new-secret-provider).
Each agent receives a random ENV_VAR_SECRET at startup — passed as an env var,
never logged or persisted. The host uses this key to encrypt each egress auth
token value before writing it to the bottled_agent_secrets table; the DB rows
(ciphertext, plaintext env-var name) without the key are insufficient to
recover the credentials.
On orchestrator restart the in-memory token map is lost. The host-side
reattachment path reads ENV_VAR_SECRET from the running agent container via
``docker exec … printenv ENV_VAR_SECRET`` and posts it to
``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).
keystream_block_i = HMAC-SHA256(key, nonce || i.to_bytes(4, "big"))
ciphertext_i = plaintext_i XOR keystream_block_i[:len(plaintext_i)]
"""
from __future__ import annotations
import base64
import hashlib
import hmac
import secrets
_KEY_BYTES = 32 # 256-bit key from ENV_VAR_SECRET
_NONCE_BYTES = 16 # 128-bit random nonce per encrypt call
_BLOCK = 32 # HMAC-SHA256 output width == one keystream block
# Env-var name the agent container receives at startup.
ENV_VAR_SECRET_NAME = "ENV_VAR_SECRET"
def new_env_var_secret() -> str:
"""Generate a fresh ENV_VAR_SECRET: 32 random bytes as URL-safe base64."""
return base64.urlsafe_b64encode(secrets.token_bytes(_KEY_BYTES)).rstrip(b"=").decode()
def _b64dec(s: str) -> bytes:
return base64.urlsafe_b64decode(s + "=" * (-len(s) % 4))
def _keystream(key: bytes, nonce: bytes, block_index: int) -> bytes:
return hmac.new(
key, nonce + block_index.to_bytes(4, "big"), hashlib.sha256
).digest()
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
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()
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)."""
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:
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))
try:
return bytes(pt).decode()
except UnicodeDecodeError as exc:
raise ValueError(f"decryption produced non-UTF-8 output (wrong key?): {exc}") from exc
__all__ = ["ENV_VAR_SECRET_NAME", "new_env_var_secret", "encrypt_value", "decrypt_value"]
+30 -1
View File
@@ -87,13 +87,22 @@ class Orchestrator:
metadata: str = "",
policy: str = "",
tokens: dict[str, str] | None = None,
env_var_secret: str = "",
) -> BottleRecord:
"""Register a bottle (with its gateway policy + in-memory egress auth
tokens) and broker its launch. Rolls the registry entry back if the
launch doesn't take, so a failure leaves no orphan."""
launch doesn't take, so a failure leaves no orphan.
When *env_var_secret* is provided alongside *tokens*, the token values
are also encrypted and written to ``bottled_agent_secrets`` so they can
survive an orchestrator restart (see ``reprovision_from_secret``)."""
rec = self.registry.register(source_ip, metadata=metadata, policy=policy)
if tokens:
self._tokens[rec.bottle_id] = dict(tokens)
if env_var_secret:
from .secret_store import encrypt_value
encrypted = {k: encrypt_value(env_var_secret, v) for k, v in tokens.items()}
self.registry.store_agent_secrets(rec.bottle_id, encrypted)
req = LaunchRequest(
op="launch",
bottle_id=rec.bottle_id,
@@ -284,6 +293,26 @@ class Orchestrator:
))
return True, ""
# --- secret reprovision -----------------------------------------------
def reprovision_from_secret(self, bottle_id: str, env_var_secret: str) -> bool:
"""Re-inject a bottle's egress tokens from its ENV_VAR_SECRET.
Reads the encrypted rows from ``bottled_agent_secrets``, decrypts each
value with *env_var_secret*, and restores ``_tokens[bottle_id]``.
Returns True on success, False when no stored secrets exist for this
bottle or decryption fails (wrong key / corrupt data)."""
from .secret_store import decrypt_value
encrypted = self.registry.get_agent_secrets(bottle_id)
if not encrypted:
return False
try:
self._tokens[bottle_id] = {k: decrypt_value(env_var_secret, v)
for k, v in encrypted.items()}
except ValueError:
return False
return True
# --- consolidated gateway ----------------------------------------------
def ensure_gateway(self) -> None: