781c8d446f
Five concrete deliverables absorbing patterns from the day's research
(Hermes Desktop, turbovec, Axiom Math, Valkey/Madelyn Olson, Jerry Liu)
into the JouleClaw substrate. Each lands in an existing or new crate
without rearchitecting; all pure-Rust, no external runtime deps;
composable with the triangle just shipped.
1. jouleclaw-context-store (new crate) — typed deterministic recall.
- TurnStore: SQLite + FTS5 over agent/CLI/chat turns. ~20ms per
query at zero LLM cost. Microjoule-class recall as a first-class
primitive between L0 cache and L2 embedding+retrieval.
- FrozenSnapshot + StagedSnapshot: bounded byte-budget memory +
user blocks. Mutations don't surface mid-session — they persist
immediately but only the next session loads them. Rationale:
keep the LLM prefix-cache warm. The byte block at the top of
every prompt in a session is byte-identical, so providers can
amortize attention over it.
- 12 tests, all green. Ingested from Hermes Agent's documented
memory pattern.
2. jouleclaw-oracle-fuzz (new crate) — adversarial Oracle backend.
- FuzzOracle<P>: implements jouleclaw-oracle::Oracle over a
caller-supplied deterministic FuzzProperty. Seeds ChaCha20 with
(seed, round) to produce reproducible inputs; short-circuits on
first counterexample with the structured FuzzFailure carried in
FailReason::Custom.
- Composes via CompositeOracle alongside type-checkers / linters /
a future Lean Oracle.
- 6 tests including determinism (same seed → byte-equal verdict)
and composition. Ingested from the OSS-maintainer crash-harness
pattern (Valkey CVE hunt).
3. jouleclaw-cone — cone-gated context injection.
- cone_gated_inject helper + InjectDecision { Full | Skip } enum.
Catalog (skills / tools / memory) is injected ONLY when the
request's novelty crosses a configured threshold; below it, the
agent uses cheap on-demand lookup tools instead of paying the
unconditional prompt-token cost.
- 4 new tests on top of the existing 23. Ingested from Hermes's
own issue #4379 documenting catalog-injection token bloat.
4. jouleclaw-jcr1 — verified-code/1 receipt schema.
- VerifiedCodeReceipt + ProgramRef + SpecRef + ProofRef
{ Lean | Fuzz | TestSuite } + VerifierRef + VerifiedCodeVerdict
{ Pass | Fail }. Canonical JSON with sorted keys; content-
addressed via BLAKE3; ready for COSE_Sign1 over the canonical
bytes via the existing v1 signing path.
- 2 conformance vectors (Lean Pass + Fuzz Fail) with embedded
content_hash that the Rust verifier asserts byte-equal at test
time. Other-language verifiers MUST round-trip under canonical
encoding and match the hash.
- 5 verified_code tests. Ingested from the Axiom Math /
"code-with-proof" pattern (Verina benchmark).
5. Demo binary — examples/wave46_recall_fuzz_verified.rs in
jouleclaw-stack. Runs all five primitives end-to-end in one
cargo run: seed FTS5 store, search, build + freeze snapshot, gate
catalog injection by cone novelty, run fuzz Oracle over a property
in two directions (pass + fail), mint a verified-code/1 receipt
over the pass. Output is reproducible and self-checking.
The triangle is the type system; these five are concrete backends +
schemas + helpers that fill load-bearing slots the triangle types up
but leaves to consumers. None of them invalidate prior waves; each
sits beneath inference per doctrine.
Workspace check clean.
Co-Authored-By: Claude Opus 4.7 <[email protected]>
82 lines
3 KiB
JSON
82 lines
3 KiB
JSON
{
|
|
"spec": "JCR-1 verified-code v1",
|
|
"schema_id": "verified-code/1",
|
|
"canonical_encoding": "JSON with sorted object keys (recursively); UTF-8; no whitespace; no float coercion. content_hash is BLAKE3 hex of the canonical bytes.",
|
|
"note": "Two vectors covering the two load-bearing proof modes: a Lean formal proof and an adversarial-fuzz counterexample. Implementers in any language MUST round-trip every receipt under canonical encoding and assert byte-equal content_hash against the embedded value.",
|
|
"vector_count": 2,
|
|
"vectors": [
|
|
{
|
|
"n": 1,
|
|
"description": "Lean Pass — formal proof of n + 0 = n, lean toolchain pinned.",
|
|
"content_hash": "06fd5cae83668d2eb4aaa589e87c03dffdba42b8a16a95dd7ed34bcfc457b67d",
|
|
"receipt": {
|
|
"jc_receipt": "verified-code/1",
|
|
"id": "vcr-lean-0001",
|
|
"closed_at": "2026-06-05T00:00:00Z",
|
|
"steward": "did:keri:EJ9testStewardAID000000000000000",
|
|
"program": {
|
|
"language": "lean",
|
|
"content_hash": "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
|
"byte_length": 128
|
|
},
|
|
"spec": {
|
|
"content_hash": "bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb",
|
|
"summary": "all n ≥ 0, n + 0 = n"
|
|
},
|
|
"proof": {
|
|
"kind": "lean",
|
|
"content_hash": "cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc",
|
|
"toolchain": "leanprover/lean4:v4.13.0"
|
|
},
|
|
"verifier": {
|
|
"id": "lean-4.13.0",
|
|
"version": "4.13.0"
|
|
},
|
|
"verdict": {
|
|
"kind": "pass",
|
|
"chain": ["lean-4.13.0"]
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"n": 2,
|
|
"description": "Fuzz Fail — binary_search returned OOB index on round 42 of 1024 seeded inputs.",
|
|
"content_hash": "f38df7e5b177a13ebd49a3e940c3ad3d487f533ea793087bfdc27101b44c50ad",
|
|
"receipt": {
|
|
"jc_receipt": "verified-code/1",
|
|
"id": "vcr-fuzz-0001",
|
|
"closed_at": "2026-06-05T00:00:00Z",
|
|
"steward": "did:keri:EJ9testStewardAID000000000000000",
|
|
"program": {
|
|
"language": "rust",
|
|
"content_hash": "dddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddd",
|
|
"byte_length": 256
|
|
},
|
|
"spec": {
|
|
"content_hash": "eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee",
|
|
"summary": "binary_search never returns OOB index"
|
|
},
|
|
"proof": {
|
|
"kind": "fuzz",
|
|
"property_id": "no-oob-index",
|
|
"seed": 7,
|
|
"rounds": 1024
|
|
},
|
|
"verifier": {
|
|
"id": "jouleclaw-oracle-fuzz",
|
|
"version": "0.1.0"
|
|
},
|
|
"verdict": {
|
|
"kind": "fail",
|
|
"reasons": ["counterexample found on round 42"],
|
|
"details": {
|
|
"property_id": "no-oob-index",
|
|
"round": 42,
|
|
"input_hex": "deadbeef",
|
|
"reason": "returned index 16 for len-8 slice"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
]
|
|
}
|