mirror of
https://github.com/block/buzz.git
synced 2026-10-27 04:30:52 +00:00
240cdd3ea1
Shared compute now has exactly two model choices: MeshLLM's virtual `mesh` model, or a model you name. Buzz picks between them in one place, and buzz-agent no longer knows meshes exist. ## What changed - **MeshLLM v0.74.0 → v0.75.1.** v0.75.0 added `degrade_to_single_model`, so a `model=mesh` request is answered by one served model when there is no committee to form, instead of failing. v0.75.1 adds Mesh-LLM#1196, which skips stale pre-0.75 runtime cache entries rather than aborting startup on them — without it, anyone who had run mesh on 0.73/0.74 could not start. - **Deleted the client-side mesh catalog probe.** buzz-agent used to poll `/v1/models` (5s TTL, 30s cooldown, two-observation debounce) to decide whether `mesh` was safe to send. MeshLLM now decides per request, so the polling, its hysteresis, and its 503 fallback are gone. - **One mapping point.** `relay_mesh_wire_model()` turns the stored value into a wire name: `auto` becomes `mesh`, a named model passes through. The spawn env, the ACP harness, and the readiness probe all use it, so they cannot disagree — previously `BUZZ_ACP_MODEL` and the probe both said `auto`, a name the mesh does not advertise. - **Removed the `nostr-relay-pool` advisory exception.** #5404 allowed RUSTSEC-2026-0243 "after mesh-llm migrates to nostr-sdk >= 0.45". v0.75.1 does, so the retired crate is gone from both lockfiles and the exception would only mask a future advisory for it. - **Deleted `scripts/ensure-mesh-native-runtime.sh`** and its six justfile call sites. It built llama.cpp from source into the runtime cache; the app already downloads the signed release runtime itself, and CI never called it. ## Why it is better **−639 lines of Rust.** Availability is decided by the node that knows the answer, per request, instead of by a client cache that could be stale for up to 30 seconds. A second worker joining now takes effect on the next request rather than after two confirming probes. ## Behaviour change A 503 on an explicit `mesh` request takes the ordinary transport retry under the same model instead of failing over to a second one — there is no second model to fail over to now. MoA repairs partial committee results internally before it reaches that point. ## Validation `crates/buzz-relay/examples/mesh_agent_e2e.rs` now sends `mesh` where it previously sent `auto` or the physical model id, so no leg was covering what Buzz actually puts on the wire. 4/4 on gemma-4-E4B, gemma-4-26B-A4B, and Qwen3-8B — including a real ACP tool call through `mesh` into buzz-dev-mcp, asserted by reading the written file back off disk. Hand-tested in the desktop app on both gemma-4 sizes: picked Auto, agent logged `model_id=mesh`, replied in channel. ## Not covered A committee that forms and then loses a worker returns 502, and that needs two workers to reproduce — not testable on one machine. --------- Signed-off-by: Michael Neale <michael.neale@gmail.com> Co-authored-by: Michael Neale <michael.neale@gmail.com>
101 lines
4.0 KiB
TOML
101 lines
4.0 KiB
TOML
[package]
|
|
name = "buzz-relay"
|
|
default-run = "buzz-relay"
|
|
# Independent version: buzz-relay ships as a pinnable artifact
|
|
# (ghcr.io/block/buzz), released on its own cadence via `just release-relay`.
|
|
# It does NOT inherit the workspace version.
|
|
version = "0.2.1"
|
|
edition.workspace = true
|
|
rust-version.workspace = true
|
|
license.workspace = true
|
|
repository.workspace = true
|
|
description = "WebSocket relay server for the Buzz communications platform"
|
|
|
|
[[bin]]
|
|
name = "buzz-relay"
|
|
path = "src/main.rs"
|
|
|
|
[dependencies]
|
|
buzz-core = { workspace = true }
|
|
buzz-conformance = { workspace = true }
|
|
buzz-db = { workspace = true }
|
|
buzz-auth = { workspace = true }
|
|
buzz-pubsub = { workspace = true }
|
|
buzz-audit = { workspace = true }
|
|
buzz-search = { workspace = true }
|
|
buzz-relay-mesh = { workspace = true }
|
|
async-trait = "0.1"
|
|
postcard = { workspace = true }
|
|
axum = { workspace = true }
|
|
tokio = { workspace = true }
|
|
# `io` (ReaderStream) is needed to stream git subprocess stdout straight into
|
|
# the HTTP response body — see api::git::transport read-path streaming. The
|
|
# workspace default only enables rt+codec.
|
|
tokio-util = { workspace = true, features = ["io"] }
|
|
tower = { workspace = true }
|
|
tower-http = { workspace = true }
|
|
nostr = { workspace = true }
|
|
serde = { workspace = true }
|
|
serde_json = { workspace = true }
|
|
tracing = { workspace = true }
|
|
tracing-subscriber = { workspace = true }
|
|
tracing-opentelemetry = { workspace = true }
|
|
opentelemetry = { workspace = true }
|
|
opentelemetry_sdk = { workspace = true }
|
|
opentelemetry-otlp = { workspace = true }
|
|
thiserror = { workspace = true }
|
|
anyhow = { workspace = true }
|
|
uuid = { workspace = true }
|
|
chrono = { workspace = true }
|
|
dashmap = { workspace = true }
|
|
futures-util = { workspace = true }
|
|
deadpool-redis = { workspace = true }
|
|
redis = { workspace = true }
|
|
# Redis TLS (rediss://, e.g. ElastiCache) uses rustls, which needs a process
|
|
# CryptoProvider installed at startup. Both aws-lc-rs and ring are compiled in
|
|
# transitively, so rustls can't auto-select one — we install ring explicitly in
|
|
# main(). Mirrors buzz-acp's rustls setup for wss://.
|
|
rustls = { version = "0.23", default-features = false, features = ["ring", "std"] }
|
|
sqlx = { workspace = true }
|
|
reqwest = { workspace = true }
|
|
base64 = "0.22"
|
|
buzz-sdk = { workspace = true }
|
|
buzz-workflow = { workspace = true, features = ["reqwest"] }
|
|
buzz-media = { workspace = true }
|
|
s3 = { version = "0.37", package = "rust-s3", default-features = false, features = ["tokio-rustls-tls", "fail-on-err", "tags"] }
|
|
tempfile = "3"
|
|
bytes = "1"
|
|
infer = "0.19"
|
|
serde_yaml = { workspace = true }
|
|
sha2 = { workspace = true }
|
|
hmac = { workspace = true }
|
|
subtle = { workspace = true }
|
|
rand = { workspace = true }
|
|
hex = { workspace = true }
|
|
url = { workspace = true }
|
|
moka = { workspace = true }
|
|
metrics = { workspace = true }
|
|
metrics-exporter-prometheus = { workspace = true }
|
|
metrics-util = { workspace = true }
|
|
pulldown-cmark = { version = "0.13.4", default-features = false, features = ["html"] }
|
|
async-compression = { version = "0.4.42", features = ["tokio", "gzip"] }
|
|
|
|
[features]
|
|
dev = ["buzz-auth/dev"]
|
|
|
|
[dev-dependencies]
|
|
mesh-llm-sdk = { git = "https://github.com/Mesh-LLM/mesh-llm.git", tag = "v0.75.1", package = "mesh-llm-sdk", default-features = false, features = ["client", "serving"] }
|
|
mesh-llm-host-runtime = { git = "https://github.com/Mesh-LLM/mesh-llm.git", tag = "v0.75.1", package = "mesh-llm-host-runtime", default-features = false, features = ["dynamic-native-runtime"] }
|
|
# Relay-driven mesh lifecycle smoke (examples/mesh_relay_lifecycle_smoke.rs):
|
|
# the relay client for discovery notes and the exact ed25519 the mesh owner
|
|
# keys use for binding verification.
|
|
buzz-test-client = { path = "../buzz-test-client" }
|
|
ed25519-dalek = "=3.0.0-rc.0"
|
|
buzz-core = { workspace = true, features = ["test-utils"] }
|
|
buzz-auth = { workspace = true, features = ["dev"] }
|
|
reqwest = { workspace = true }
|
|
tokio-tungstenite = { workspace = true }
|
|
futures = "0.3"
|
|
flate2 = "1.1.9"
|
|
opentelemetry_sdk = { workspace = true, features = ["testing"] }
|