feat(relay): add Switchyard-owned HTTP dynamic plugin

CHANGELOG.md

@@ -6,6 +6,23 @@ adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 ## [Unreleased]
 
+### Added
+
+- **NeMo Relay native plugin** — a dynamically loaded integration that runs
+  libsy's weighted-random, LLM-classifier, escalation, and stage-router
+  algorithms in process while Switchyard owns provider HTTP dispatch,
+  credentials, translation, retries, and fallback. Managed calls require NeMo
+  Relay 0.7 or newer and do not depend on `switchyard-server`. Target bindings
+  accept non-secret `extra_body` provider defaults, preserved requests are
+  re-encoded after routing mutations, and synthetic Relay gateway identities do
+  not become shared router session state.
+
+- **NeMo Relay routing-model usage marks** — classifier judges, escalation
+  judges and discarded weak candidates, and failed routing candidates now emit
+  `switchyard.routing.llm_call` ATOF marks with normalized token usage and
+  latency. The final serving call remains represented only by Relay's outer LLM
+  lifecycle event to prevent double-counting.
+
 ### Removed
 
 - **Deprecated Python server stack** — `switchyard serve`, YAML route bundles,

Cargo.toml

@@ -8,6 +8,7 @@ members = [
     "crates/libsy-llm-client",
     "crates/switchyard-py",
     "crates/protocol",
+    "crates/switchyard-nemo-relay-plugin",
     "crates/switchyard-server",
     "crates/switchyard-skill-distillation",
     "crates/switchyard-translation",
@@ -22,6 +23,7 @@ repository = "https://github.com/NVIDIA-NeMo/Switchyard"
 rust-version = "1.96.1"
 
 [workspace.dependencies]
+async-channel = "2"
 async-stream = "0.3"
 async-trait = "0.1"
 futures = "0.3"
@@ -30,6 +32,7 @@ http = "1"
 httpdate = "1"
 jsonschema = { version = "0.49.4", default-features = false }
 jsonptr = { version = "0.8.1", default-features = false, features = ["std", "json", "resolve"] }
+nemo-relay-plugin = "=0.7.0"
 parking_lot = "0.12"
 rand = "0.10"
 reqwest = { version = "0.13.4", default-features = false, features = ["json", "rustls", "stream"] }

README.md

@@ -21,6 +21,7 @@ algorithm you write yourself.
 - **Protocol Translation**: convert between OpenAI Chat, Anthropic Messages, and OpenAI Responses formats
 - **Multi-Backend Routing**: random routing, LLM-as-classifier routing, signal-driven stage-router, or your own algorithm
 - **Operational Metrics**: Prometheus metrics cover requests, errors, latency, tokens, and routing overhead
+- **NeMo Relay Plugin**: run random, classifier, escalation, or stage routing in Relay while Switchyard owns provider HTTP dispatch
 
 ## Maturity
 
@@ -154,6 +155,7 @@ configured LLM client selects one upstream format.
 - **[`switchyard-libsy`](crates/libsy/README.md)**: embed routing algorithms in a Rust application
 - **[`switchyard-protocol`](crates/protocol/README.md)**: provider-neutral request, response, and streaming types
 - **[`switchyard-translation`](crates/switchyard-translation/README.md)**: request, response, and stream translation
+- **[`switchyard-nemo-relay-plugin`](crates/switchyard-nemo-relay-plugin/README.md)**: install Switchyard as a native NeMo Relay plugin
 
 ## Community
 

crates/switchyard-nemo-relay-plugin/Cargo.toml

@@ -0,0 +1,30 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+[package]
+name = "switchyard-nemo-relay-plugin"
+version.workspace = true
+description = "Switchyard-owned HTTP routing plugin for NeMo Relay"
+authors.workspace = true
+edition.workspace = true
+license.workspace = true
+repository.workspace = true
+rust-version.workspace = true
+publish = false
+
+[lib]
+crate-type = ["cdylib"]
+
+[dependencies]
+async-channel.workspace = true
+async-trait.workspace = true
+futures-util.workspace = true
+http.workspace = true
+nemo-relay-plugin.workspace = true
+serde.workspace = true
+serde_json.workspace = true
+switchyard-libsy.workspace = true
+switchyard-llm-client.workspace = true
+switchyard-protocol.workspace = true
+switchyard-translation.workspace = true
+tokio.workspace = true