5784eba46e
New open standard (open-standards/mesh): the serving/routing fabric in front
of many models and many backends. A request declares a joule ceiling and a
fidelity floor; the mesh routes it cheapest-sufficient, meters the decode, and
seals a mesh/1 JCR-1 receipt whose headline figure is microjoules per accepted
token (measured at the meter, not estimated). Rides on JCP grants + JCR-1
receipts + the family energy meter; dispatches to JouleClaw; routes across
EOC/Sandbox. No new cryptography.
mesh-rs reference workspace:
- mesh-schema content-addressed ServeRequest (joule ceiling + fidelity
floor), F0–F4 fidelity, honest two-part Energy, model-as-recipe,
route-decision audit + outcome counters
- mesh-router energy-weighted cheapest-sufficient routing with full candidate
audit (admit iff fidelity >= floor AND estimate <= ceiling)
- mesh-engine ServingEngine trait + deterministic, weights-free ReferenceEngine
- mesh-engine-gguf real backend over the family's pure-Rust GGUF/safetensors
substrate (feature `gguf`); proven serving a real Falcon-H1
decode end-to-end (authorise -> route -> meter -> seal -> chain)
- mesh-meter meter window; estimator + optional RAPL/NVML/Apple bridge
- mesh-receipt mesh/1 receipt (canonical det-CBOR + COSE_Sign1/EdDSA),
uj_per_accepted_token sealed in, refuses dishonest HwShunt,
hash-chained log
- mesh-core orchestration: authorise JCP grant -> route -> meter -> seal;
prompt payload passed to the engine, never sealed (hash only)
- mesh-openai OpenAI-compatible ingest: /v1/chat/completions <-> ServeRequest,
std-only reference server returning the sealed receipt in
usage.energy (feature `server`)
- mesh-conformance deterministic reference serve + field-by-field checks +
gen-vectors; published v1 vectors
SPEC.md (CC-BY-4.0), README, CONTRIBUTING, conformance/v1; registered in the
repo standards index. cargo test --workspace green; clippy --all-targets clean.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
100 lines
4.8 KiB
Markdown
100 lines
4.8 KiB
Markdown
# Mesh
|
|
|
|
**Energy-accounted inference serving & routing.** One of the
|
|
[Transaction Science open standards](../README.md).
|
|
|
|
Mesh treats every inference as a metered transaction. A request declares a
|
|
**joule ceiling** and a **fidelity floor**; the mesh routes it to the
|
|
cheapest-sufficient model on the cheapest-sufficient backend, serves it under an
|
|
energy meter, and seals a receipt whose headline figure is **microjoules per
|
|
accepted output token** — measured at the meter, not estimated from a price list.
|
|
|
|
The serving shelf reports dollars per token and tokens per second. Mesh reports
|
|
the number that is physical, comparable across hardware, and impossible to
|
|
inflate: the joule.
|
|
|
|
- **Spec:** [`SPEC.md`](SPEC.md) (CC-BY-4.0)
|
|
- **Reference code:** [`mesh-rs/`](mesh-rs/) (Apache-2.0)
|
|
- **Conformance vectors:** [`conformance/v1/`](conformance/v1/)
|
|
|
|
## The shape
|
|
|
|
```
|
|
ServeRequest ──▶ authorise (JCP grant) ──▶ route (cheapest-sufficient)
|
|
│
|
|
▼
|
|
meter ◀── serve (engine) ──▶ tokens
|
|
│
|
|
▼
|
|
sealed JCR-1 receipt: µJ / accepted token
|
|
```
|
|
|
|
Four roles — **caller**, **router**, **engine**, **steward** — and four phases
|
|
per serve: authorise, route, meter, seal. See [`SPEC.md`](SPEC.md) §2.
|
|
|
|
## The reference workspace
|
|
|
|
`mesh-rs/` is a pure-Rust reference implementation:
|
|
|
|
| Crate | What it is |
|
|
|---|---|
|
|
| `mesh-schema` | wire types — `ServeRequest`, `Fidelity`, two-part `Energy`, `RouteDecision`, `ServeOutcome` |
|
|
| `mesh-router` | energy-weighted cheapest-sufficient routing with a full candidate audit |
|
|
| `mesh-engine` | the `ServingEngine` interface + a deterministic, weights-free `ReferenceEngine` |
|
|
| `mesh-engine-gguf` | a **real** backend (behind `gguf`): wraps the family's pure-Rust GGUF/Metal inference substrate so the mesh routes and meters actual model tokens |
|
|
| `mesh-meter` | the meter window; an always-available estimator + an optional bridge to the family hardware meter (RAPL / NVML / Apple) behind `hw-meter` |
|
|
| `mesh-receipt` | the `mesh/1` receipt, JCR-1 sealing (det-CBOR + COSE_Sign1), and a hash-chained log |
|
|
| `mesh-core` | the orchestration that ties authorise → route → meter → seal together |
|
|
| `mesh-conformance` | the deterministic reference scenario, its checks, and the `gen-vectors` bin |
|
|
|
|
Mesh **rides on** [JCP](../jcp/) (a serve request is authorised by a JCP grant;
|
|
receipts seal in JCR-1), **dispatches to** runtimes such as
|
|
[JouleClaw](../jouleclaw/), and **routes across** compute described by
|
|
[EOC](../eoc/) and isolated by [Sandbox](../sandbox/). It introduces no new
|
|
cryptography (see [`SPEC.md`](SPEC.md) §9).
|
|
|
|
## Run it
|
|
|
|
```bash
|
|
cd mesh-rs
|
|
|
|
# all crates green
|
|
cargo test --workspace
|
|
cargo clippy --workspace --all-targets
|
|
|
|
# end-to-end: mint a JCP grant, serve, print the sealed receipt
|
|
cargo run -p mesh-core --example demo
|
|
|
|
# on Linux/RAPL or a CUDA/NVML box, meter real silicon (HwShunt provenance)
|
|
cargo run -p mesh-core --example demo --features hw-meter-rapl
|
|
|
|
# regenerate the published conformance vectors
|
|
cargo run -p mesh-conformance --bin gen-vectors -- ../conformance/v1
|
|
|
|
# serve a REAL model end-to-end through Mesh (Falcon-H1 0.5B), seal the receipt
|
|
cargo run --release -p mesh-engine-gguf --features gguf --bin serve_falcon -- \
|
|
/path/to/falcon-h1-0.5b-instruct 12 "The capital of France is"
|
|
```
|
|
|
|
The `serve_falcon` run demonstrates the **whole standard** on real model tokens:
|
|
a JCP grant authorises each request (an underfunded grant is refused *before any
|
|
decode runs*), the cheapest-sufficient backend is chosen, the decode is metered,
|
|
and a `mesh/1` receipt is sealed and hash-chained across the session — e.g.
|
|
prompt *"The capital of France is"* → `" Paris. It is known for its historical
|
|
landmarks"`, prompt *"Photosynthesis is the process by which"* → `" plants
|
|
convert sunlight into chemical energy in the form of"`, with both seals verifying
|
|
and the chain's prev-links intact.
|
|
|
|
The demo prints the route (every backend weighed, with the reason each was kept
|
|
or rejected), the honest energy provenance, and the wedge metric — then verifies
|
|
the sealed envelope under the steward key.
|
|
|
|
## Status
|
|
|
|
v0.1.0-draft.1. Reference workspace builds and tests green (`mesh-schema`,
|
|
`mesh-router`, `mesh-engine`, `mesh-meter`, `mesh-receipt`, `mesh-core`,
|
|
`mesh-conformance`); `cargo clippy --all-targets` warning-free; published vectors
|
|
in [`conformance/v1/`](conformance/v1/). The reference engine is deterministic and
|
|
weights-free; production backends implement the same `ServingEngine` interface —
|
|
`mesh-engine-gguf` (behind `gguf`) is a real one over the family's pure-Rust
|
|
GGUF/Metal substrate, kept out of the default build so it needs no weights.
|