WI-5 #832: Receipt-challenge protocol (compaction-refresh, milestone 188) (#845)

packages/mosaic/src/lease-broker/broker-test-client.ts

@@ -1,4 +1,5 @@
 import { createHash } from 'node:crypto';
+import { chmod, writeFile } from 'node:fs/promises';
 import { createConnection, type Socket } from 'node:net';
 
 const DEFAULT_TIMEOUT_MS = 3_000;
@@ -185,3 +186,51 @@ export async function requestBrokerReply<T extends object>(
     options,
   );
 }
+
+export interface ReceiptChallengeCycle {
+  sessionId: string;
+  runtimeGeneration: number;
+  receiptChallenge: string;
+  receipt: string;
+}
+
+export interface ReceiptChallengeReply {
+  ok: boolean;
+  code?: string;
+  state?: 'UNVERIFIED' | 'PENDING_VERIFICATION' | 'PENDING_PROMOTION' | 'VERIFIED';
+}
+
+/**
+ * Complete the shipped begin -> trusted-observer -> consume -> promote path.
+ * The private fixture is read by the daemon's injected test observer; the
+ * observation request itself never carries assistant-message content.
+ */
+export async function observeAndPromoteReceiptChallenge(
+  socketPath: string,
+  observerFixturePath: string,
+  cycle: ReceiptChallengeCycle,
+): Promise<ReceiptChallengeReply> {
+  await writeFile(
+    observerFixturePath,
+    `${JSON.stringify({
+      session_id: cycle.sessionId,
+      runtime_generation: cycle.runtimeGeneration,
+      latest_assistant_message: cycle.receipt,
+    })}\n`,
+    { encoding: 'utf8', mode: 0o600 },
+  );
+  await chmod(observerFixturePath, 0o600);
+  const observed = await requestBrokerReply<ReceiptChallengeReply>(socketPath, {
+    action: 'observe_receipt',
+    session_id: cycle.sessionId,
+    runtime_generation: cycle.runtimeGeneration,
+    receipt_challenge: cycle.receiptChallenge,
+  });
+  if (observed.ok !== true || observed.state !== 'PENDING_PROMOTION') return observed;
+  return await requestBrokerReply<ReceiptChallengeReply>(socketPath, {
+    action: 'promote_lease',
+    session_id: cycle.sessionId,
+    runtime_generation: cycle.runtimeGeneration,
+    receipt_challenge: cycle.receiptChallenge,
+  });
+}

packages/mosaic/src/lease-broker/receipt_challenge_unittest.py

@@ -0,0 +1,227 @@
+#!/usr/bin/env python3
+"""RED-first contracts for the shipped receipt challenge and observer seam."""
+
+from __future__ import annotations
+
+import base64
+import copy
+import hashlib
+import importlib.util
+import os
+import tempfile
+import unittest
+from pathlib import Path
+
+
+TOOLS = Path(__file__).parents[2] / "framework/tools/lease-broker"
+DAEMON_PATH = TOOLS / "daemon.py"
+FRAGMENTS_PATH = TOOLS / "normative_fragments.py"
+OBSERVER_PATH = TOOLS / "receipt_observer.py"
+
+
+def load_module(name: str, path: Path):
+    assert path.is_file(), f"shipped module is missing: {path}"
+    spec = importlib.util.spec_from_file_location(name, path)
+    if spec is None or spec.loader is None:
+        raise RuntimeError(f"unable to load {name}")
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    return module
+
+
+DAEMON = load_module("lease_broker_receipt_daemon", DAEMON_PATH)
+FRAGMENTS = load_module("lease_broker_normative_fragments", FRAGMENTS_PATH)
+
+
+class BrokerFixture(unittest.TestCase):
+    def setUp(self) -> None:
+        self.temporary = tempfile.TemporaryDirectory()
+        root = Path(self.temporary.name)
+        os.chmod(root, 0o700)
+        self.peer = (os.getpid(), os.getuid(), os.getgid())
+        self.broker = DAEMON.Broker(DAEMON.StateStore(root / "state.json"))
+        registered = self.broker.handle(self.peer, {
+            "action": "register_anchor",
+            "runtime_generation": 7,
+        })
+        self.session_id = registered["session_id"]
+        self.assertIsInstance(self.session_id, str)
+
+    def tearDown(self) -> None:
+        self.temporary.cleanup()
+
+    def construction(self) -> tuple[dict[str, object], dict[str, object]]:
+        content = b"Constitution\n"
+        expected_sha256 = hashlib.sha256(content).hexdigest()
+        construction = {
+            "manifest_version": 1,
+            "generator_version": "wi5-receipt-test",
+            "fragments": [{
+                "source_id": "authority/constitution",
+                "content_base64": base64.b64encode(content).decode("ascii"),
+                "expected_sha256": expected_sha256,
+            }],
+        }
+        result = FRAGMENTS.build_payload(
+            manifest_version=construction["manifest_version"],
+            generator_version=construction["generator_version"],
+            fragments=[FRAGMENTS.NormativeFragment("authority/constitution", content, expected_sha256)],
+        )
+        self.assertEqual(result.injectionDecision, "ACCEPTED")
+        self.assertTrue(result.promotion)
+        return construction, {
+            "compaction_epoch": 3,
+            "request_epoch": 8,
+            "h_source": result.h_source,
+            "h_payload": result.h_payload,
+            "schema_version": 1,
+        }
+
+    def begin(self, binding: dict[str, object], construction: dict[str, object]) -> dict[str, object]:
+        response = self.broker.handle(self.peer, {
+            "action": "begin_verification",
+            "session_id": self.session_id,
+            "runtime_generation": 7,
+            "runtime": "pi",
+            "binding": binding,
+            "construction": construction,
+        })
+        self.assertEqual(response["state"], DAEMON.LEASE_PENDING)
+        self.assertIsInstance(response.get("receipt_challenge"), str)
+        self.assertIsInstance(response.get("receipt"), str)
+        return response
+
+
+class BuildPayloadAdmissionTest(BrokerFixture):
+    def test_b3_forged_h_source_or_h_payload_is_refused_against_shipped_build_payload(self) -> None:
+        construction, trusted = self.construction()
+        for field in ("h_source", "h_payload"):
+            with self.subTest(field=field):
+                forged = dict(trusted)
+                forged[field] = "f" * 64
+                with self.assertRaisesRegex(DAEMON.BrokerFailure, "PAYLOAD_BINDING_MISMATCH"):
+                    self.begin(forged, construction)
+
+
+class ReceiptObserverTest(BrokerFixture):
+    def setUp(self) -> None:
+        super().setUp()
+        observers = load_module("lease_broker_test_observer", OBSERVER_PATH)
+        self.observer = observers.TestReceiptObserver()
+        self.broker = DAEMON.Broker(self.broker.store, observer=self.observer)
+
+    def record(self, message: str) -> None:
+        self.observer.record_latest_assistant_message(self.session_id, 7, message)
+
+    def observe(self, challenge: str, **untrusted: object) -> dict[str, object]:
+        return self.broker.handle(self.peer, {
+            "action": "observe_receipt",
+            "session_id": self.session_id,
+            "runtime_generation": 7,
+            "receipt_challenge": challenge,
+            **untrusted,
+        })
+
+    def promote(self, challenge: str) -> dict[str, object]:
+        return self.broker.handle(self.peer, {
+            "action": "promote_lease",
+            "session_id": self.session_id,
+            "runtime_generation": 7,
+            "receipt_challenge": challenge,
+        })
+
+    def test_b2_echoed_request_observation_is_refused_but_observer_source_promotes(self) -> None:
+        construction, binding = self.construction()
+        cycle = self.begin(binding, construction)
+        challenge = cycle["receipt_challenge"]
+        receipt = cycle["receipt"]
+
+        with self.assertRaisesRegex(DAEMON.BrokerFailure, "INVALID_RECEIPT"):
+            self.observe(challenge, latest_assistant_message=receipt)
+        with self.assertRaisesRegex(DAEMON.BrokerFailure, "RECEIPT_OBSERVATION_UNAVAILABLE"):
+            self.observe(challenge)
+
+        self.record(receipt)
+        self.assertEqual(self.observe(challenge)["state"], DAEMON.LEASE_PENDING_PROMOTION)
+        self.assertEqual(self.promote(challenge)["state"], DAEMON.LEASE_VERIFIED)
+        self.assertEqual(self.broker.handle(self.peer, {
+            "action": "authorize_tool",
+            "session_id": self.session_id,
+            "runtime_generation": 7,
+            "runtime": "pi",
+            "tool_name": "bash",
+        })["decision"], "allow")
+
+    def test_rejected_begin_keeps_revoke_first_fence_for_all_construction_refusals(self) -> None:
+        construction, binding = self.construction()
+        refusal_cases = {
+            "INVALID_CONSTRUCTION": {"bad": "construction"},
+            "PAYLOAD_CONSTRUCTION_REFUSED": {
+                **construction,
+                "fragments": [{
+                    **construction["fragments"][0],
+                    "expected_sha256": "0" * 64,
+                }],
+            },
+            "PAYLOAD_BINDING_MISMATCH": None,
+        }
+        for expected_code, rejected_construction in refusal_cases.items():
+            with self.subTest(expected_code=expected_code):
+                verified = self.begin(binding, construction)
+                self.record(verified["receipt"])
+                self.observe(verified["receipt_challenge"])
+                self.assertEqual(self.promote(verified["receipt_challenge"])["state"], DAEMON.LEASE_VERIFIED)
+
+                rejected_binding = copy.deepcopy(binding)
+                if expected_code == "PAYLOAD_BINDING_MISMATCH":
+                    rejected_binding["h_payload"] = "f" * 64
+                    rejected_construction = construction
+                with self.assertRaisesRegex(DAEMON.BrokerFailure, expected_code):
+                    self.begin(rejected_binding, rejected_construction)
+
+                self.assertEqual(
+                    self.broker.leases[self.session_id]["state"], DAEMON.LEASE_UNVERIFIED
+                )
+                denied = self.broker.handle(self.peer, {
+                    "action": "authorize_tool",
+                    "session_id": self.session_id,
+                    "runtime_generation": 7,
+                    "runtime": "pi",
+                    "tool_name": "bash",
+                })
+                self.assertEqual(denied["decision"], "deny")
+                self.assertEqual(denied["state"], DAEMON.LEASE_UNVERIFIED)
+
+    def test_t26_stale_epoch_receipt_cannot_promote_against_shipped_binding(self) -> None:
+        construction, stale_binding = self.construction()
+        stale = self.begin(stale_binding, construction)
+        current_binding = dict(stale_binding)
+        current_binding["compaction_epoch"] = 4
+        current_binding["request_epoch"] = 9
+        current = self.begin(current_binding, construction)
+        self.assertNotEqual(stale["receipt_challenge"], current["receipt_challenge"])
+
+        self.record(stale["receipt"])
+        with self.assertRaisesRegex(DAEMON.BrokerFailure, "RECEIPT_MISMATCH"):
+            self.observe(current["receipt_challenge"])
+        with self.assertRaisesRegex(DAEMON.BrokerFailure, "INVALID_LEASE_TRANSITION"):
+            self.promote(current["receipt_challenge"])
+
+    def test_t29_altered_model_hash_cannot_promote_against_shipped_binding(self) -> None:
+        construction, binding = self.construction()
+        cycle = self.begin(binding, construction)
+        expected = cycle["receipt"]
+        altered_hash = "f" * 64
+        self.assertNotEqual(altered_hash, cycle["binding"]["h_payload"])
+        altered = expected.replace(cycle["binding"]["h_payload"], altered_hash, 1)
+        self.assertNotEqual(altered, expected)
+
+        self.record(altered)
+        with self.assertRaisesRegex(DAEMON.BrokerFailure, "RECEIPT_MISMATCH"):
+            self.observe(cycle["receipt_challenge"])
+        with self.assertRaisesRegex(DAEMON.BrokerFailure, "INVALID_LEASE_TRANSITION"):
+            self.promote(cycle["receipt_challenge"])
+
+
+if __name__ == "__main__":
+    unittest.main()