| Filename | Latest commit message | Latest commit date |
|---|---|---|
1e435c861a
Latest stable (1.98.0, released 2026-08-18). The pin lives in more places than
is obvious, and missing one means CI silently builds an older compiler than the
dev box:
- rust-toolchain.toml at the repo root
- eoc/eoc-rs/rust-toolchain.toml, a second toolchain file
- five CI workflows that hardcode a version instead of deferring to the file
(wai-conformance, wai-neural-e2e, wai-byte-equality,
joule-code-conformance, jouleclaw-public-surface-documented)
standards-build.yml needed no change, because it reads the toolchain file
rather than pinning inline. That is the pattern the other five should adopt.
MSRV raised to 1.98 across 26 manifests, following the earlier decision to have
the declared floor track the pin rather than drift behind it. Note this is a
support-policy change, not a mechanical one: it narrows which compilers can
consume these standards as libraries.
The pin stays exact, never `stable` — a pin that drifts is not a pin.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
|
||
| .. | ||
| src | ||
| tests | ||
| Cargo.lock | ||
| Cargo.toml | ||
| README.md | ||
L3 binding — JouleClaw model tier → Joule Code cascade
A consumer binding example: how to wire JouleClaw's L3 (Model) tier into the Joule Code cascade. It is a standalone workspace, so the standard's reference library keeps no JouleClaw dependency.
A coding request that misses the cheaper tiers (L0 cache, L1 lawful, L2 embed) is
generated by a local model at L3, producing a content-addressed CodingOp and a
joules-class Receipt.
Three backends, same slot
All implement JouleClaw's jouleclaw_llm_cheap::LlmBackend, so they drop into
the same cascade stage:
EchoBackend(from JouleClaw) — deterministic, model-free; used by the unit tests so the wiring is verifiable with no model present.JouleclawRuntimeBackend(here) — runs the model in-process on JouleClaw's own from-scratch GGUF tensor runtime (jouleclaw-runtime): no external binary, no FFI. Tokenize → build the decode-step graph → compile against the registered kernels (jouleclaw-backend-reference/-apple) → autoregressive decode → detokenize, all in Rust the family wrote. This is the default backend for therunbinary.LlamaCompletionBackend(here) — drives a real on-device GGUF viallama-completion(llama.cpp). SetJOULE_CODE_L3_ENGINE=llamato use it.
Either local path: no datacenter, no network. In production the cheapest capable
backend is chosen by jouleclaw_dispatch::ModelBank's cost table.
Run it against a local model
# Default: in-process on jouleclaw-runtime (the from-scratch tensor engine).
cargo run --release --bin run -- /path/to/model.gguf "Write a Rust function that reverses a string."
# or: JOULE_CODE_L3_MODEL=/path/to/model.gguf cargo run --release --bin run
# Use the llama.cpp shell-out backend instead:
JOULE_CODE_L3_ENGINE=llama cargo run --release --bin run -- /path/to/model.gguf "..."
The run binary generates with the local model, content-addresses the result as
a CodingOp (tier L3), and meters host energy over the inference with
JouleClaw's energy counter — so the receipt's joule cost is a real local
measurement, honestly tagged with the counter's provenance (HwShunt on
RAPL/NVML hosts; Estimator on Apple Silicon until IOReport is wired), not a
datacenter token estimate.
Verified live: the llama.cpp path against a local 350M GGUF, and the in-process
from-scratch runtime against ternary-bonsai-1.7b-q2_0 (qwen3, Q2_0) — real text
generated, a real op_id, the cascade closing at L3.
Tests
cargo test # EchoBackend path — no model required
# In-process from-scratch runtime against a real GGUF (opt-in):
JOULE_BONSAI=/path/to/ternary-bonsai-1.7b-q2_0.gguf \
cargo test --release --test runtime_l3 -- --ignored --nocapture