open-standards/mesh
Repository files (latest commit first)
Filename Latest commit message Latest commit date
Transaction Science 7a9d119854 mesh-openai: add the /v1/responses ingest (the agent-native OpenAI wire)
Clients that moved from /v1/chat/completions to the newer Responses API now
drive metered serving unchanged. to_serve_request_responses parses a
Responses request — `input` as a bare string or message items, an optional
top-level `instructions` system turn, `max_output_tokens` as the decode cap;
fidelity floor + joule ceiling read exactly as the chat path. complete_responses
routes it through mesh.serve and returns a Responses result — the assistant
turn as one output_text item — with the sealed mesh/1 receipt under
usage.energy (Responses usage uses input_tokens / output_tokens).

The sealed usage.energy block is now a single energy_block() helper shared by
both paths, so the receipt is single-sourced. The std-only reference server
exposes POST /v1/responses alongside /v1/chat/completions.

Tests: responses parsing (string input, array input + instructions, malformed)
and an end-to-end complete_responses whose embedded JCR-1 envelope verifies
under the steward key. cargo test --all-features green, clippy clean; live
curl smoke of /v1/responses returns object=response with the sealed receipt.

Co-Authored-By: Claude Opus 4.8 <[email protected]>
2026-06-27 18:35:32 -04:00
..
conformance/v1
mesh-rs mesh-openai: add the /v1/responses ingest (the agent-native OpenAI wire) 2026-06-27 18:35:32 -04:00
CONTRIBUTING.md
LICENSE
LICENSE-SPEC
README.md
SPEC.md

Mesh

Energy-accounted inference serving & routing. One of the Transaction Science open standards.

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.

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 §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 (a serve request is authorised by a JCP grant; receipts seal in JCR-1), dispatches to runtimes such as JouleClaw, and routes across compute described by EOC and isolated by Sandbox. It introduces no new cryptography (see SPEC.md §9).

Run it

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/. 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.