Skip to content

Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.

Rust

docs: streamline navigation and link Rust crate documentation (#1150)

nachiketb-nvidia2623f997f23b
diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml
index 2aa07f961..47397abc7 100644
--- a/.github/workflows/docs.yml
+++ b/.github/workflows/docs.yml
@@ -13,6 +13,7 @@ on:
- "rust-toolchain.toml"
- "crates/libsy/**"
- "crates/libsy-llm-client/**"
+ - "crates/switchyard-runner/**"
- "crates/protocol/**"
- "crates/switchyard-translation/**"
- ".github/workflows/docs.yml"
@@ -29,6 +30,7 @@ on:
- "rust-toolchain.toml"
- "crates/libsy/**"
- "crates/libsy-llm-client/**"
+ - "crates/switchyard-runner/**"
- "crates/protocol/**"
- "crates/switchyard-translation/**"
- ".github/workflows/docs.yml"
@@ -67,6 +69,7 @@ jobs:
--package switchyard-protocol
--package switchyard-translation
--package switchyard-llm-client
+ --package switchyard-runner
- name: Add crate documentation to site
run: |
mkdir -p site/rust
diff --git a/AGENTS.md b/AGENTS.md
index c0749d469..48cd7519a 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -25,6 +25,11 @@ Integrations:
- Be humble. Do not inflate claims.
- Do not say what you would do unless asked.
+## Official documentation
+
+- Publish documentation about using, integrating, configuring, and understanding Switchyard's product and software.
+- Keep repository CI, documentation publishing, release procedures, and maintainer or agent workflows in contributor documentation or excluded internal docs, not in the official product documentation.
+
## Engineering guidance
- Prefer the smallest direct solution.
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index dd7825d12..ab91c5702 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -176,7 +176,7 @@ The default unit test suite runs with no network access and no API keys. Live, e
## Architecture
-See [Architecture](docs/architecture.md) for the request lifecycle and
+See [Mechanics of Libsy](docs/mechanics_of_libsy.md) for the request lifecycle and
[Agents](AGENTS.md) for crate boundaries and repository conventions. The
supported serving path is native Rust:
@@ -214,7 +214,14 @@ public symbols from the owning crate or package rather than the top-level
- **Docstrings** — include for public APIs. Format: one-line summary, blank line, details, examples.
- **README** — keep in sync with CLI surface (commands, flags, new subcommands).
- **[PyPI description](crates/switchyard-py/pypi.md)** — keep in sync with Python API, project, and documentation link changes.
-- **docs/** — architecture, design decisions, advanced usage.
+- **Official docs** — product usage, integration, configuration, and software behavior. Keep repository CI, docs publishing, release procedures, and maintainer workflows here or in excluded internal docs.
+
+### Documentation previews
+
+The Documentation workflow publishes a preview for same-repository pull
+requests. Open the workflow's **Deploy PR preview** summary to find its preview
+URL. The preview includes generated Rust crate documentation. The **docs-site**
+build artifact contains the same site and Rustdoc output for one day.
## Questions?
diff --git a/DEVELOPMENT.md b/DEVELOPMENT.md
index 6f4e0197a..3054b4f83 100644
--- a/DEVELOPMENT.md
+++ b/DEVELOPMENT.md
@@ -4,8 +4,8 @@ Setup, testing, project layout, and contribution conventions for hacking on
Switchyard itself. If you only want to **use** the package, see
[README](README.md).
-For deeper architectural docs, see [Agents](AGENTS.md) and
-[Architecture](docs/architecture.md).
+For crate boundaries and repository conventions, see [Agents](AGENTS.md).
+[Mechanics of Libsy](docs/mechanics_of_libsy.md) explains the execution model.
## Setup
diff --git a/README.md b/README.md
index 143076524..da365228f 100644
--- a/README.md
+++ b/README.md
@@ -127,9 +127,9 @@ For latency and routing overhead testing, see [Soak Testing](docs/operations/soa
### Further reading
- [Benchmark setup and profiles](benchmark/README.md): run your own baseline and routing comparisons.
-- [Core concepts](docs/core_concepts.md): clients, targets, routes, and model IDs.
+- [Mechanics of Libsy](docs/mechanics_of_libsy.md): steps, model calls, and routing outcomes.
- [TOML schema](docs/reference/toml_schema.md): configuration fields and defaults.
-- [Architecture](docs/architecture.md): libsy and runtime components.
+- [Rust crate reference](docs/reference/rust_api.md): core and optional integration crates.
- [Installation](INSTALLATION.md): package and platform requirements.
## Components
diff --git a/crates/switchyard-py/pypi.md b/crates/switchyard-py/pypi.md
index daf184d82..4278fc4fc 100644
--- a/crates/switchyard-py/pypi.md
+++ b/crates/switchyard-py/pypi.md
@@ -52,7 +52,7 @@ For latency and routing overhead testing, see [Soak Testing](https://nvidia-nemo
### Further reading
- [Benchmark setup and profiles](https://github.com/NVIDIA-NeMo/Switchyard/blob/main/benchmark/README.md): run your own baseline and routing comparisons.
-- [Core concepts](https://nvidia-nemo.github.io/Switchyard/core_concepts/): clients, targets, routes, and model IDs.
+- [Mechanics of Libsy](https://nvidia-nemo.github.io/Switchyard/mechanics_of_libsy/): steps, model calls, and routing outcomes.
- [TOML schema](https://nvidia-nemo.github.io/Switchyard/reference/toml_schema/): configuration fields and defaults.
-- [Architecture](https://nvidia-nemo.github.io/Switchyard/architecture/): library and runtime components.
+- [Rust crate reference](https://nvidia-nemo.github.io/Switchyard/reference/rust_api/): core and optional integration crates.
- [Installation](https://github.com/NVIDIA-NeMo/Switchyard/blob/main/INSTALLATION.md): package and platform requirements.
diff --git a/docs/architecture.md b/docs/architecture.md
deleted file mode 100644
index b795036aa..000000000
--- a/docs/architecture.md
+++ /dev/null
@@ -1,65 +0,0 @@
-# Switchyard Architecture
-
-Switchyard is an LLM traffic proxy that sits between clients and model
-backends. It keeps the client-facing API stable while applying routing policy,
-translating provider formats, and handling configured fallbacks.
-
-## System Context
-
-```mermaid
-flowchart TB
- clients["Clients<br/>Coding agents, SDKs, applications"]
- switchyard["Switchyard<br/>Local proxy, shared service, or embedded runtime"]
- backends["Model backends<br/>Hosted providers, private endpoints, local models"]
-
- clients <-->|"OpenAI and Anthropic API formats"| switchyard
- switchyard <-->|"Provider-compatible requests and responses"| backends
-```
-
-Clients connect using supported OpenAI or Anthropic API formats. Switchyard can
-route a request to a backend with a different native format and still return the
-response shape expected by the client.
-
-## Request Lifecycle
-
-```mermaid
-flowchart TB
- request["1. Receive<br/>Accept the client API format"]
- normalize["2. Normalize<br/>Prepare a provider-independent request"]
- route["3. Route<br/>Apply policy and select a model endpoint"]
- execute["4. Execute<br/>Call the backend and apply configured fallback"]
- respond["5. Return<br/>Translate the response or stream for the client"]
-
- request --> normalize --> route --> execute --> respond
-```
-
-Routing policy determines which model or endpoint receives a request. Depending
-on the selected strategy, that decision can use fixed weights, a classifier,
-request signals, or conversation affinity. See the
-[Routing Overview](routing_algorithms/overview.md) for the available strategies.
-
-## Backend Wire Format
-
-Each LLM client in the deployment file sets `format`. It fixes the upstream
-endpoint and wire format for every target that uses that client.
-
-| `format` | Upstream endpoint |
-|---|---|
-| `openai_chat` | `/v1/chat/completions` |
-| `openai_responses` | `/v1/responses` |
-| `anthropic_messages` | `/v1/messages` |
-
-`format` is required. Switchyard does not probe upstreams or select a format
-automatically.
-
-Switchyard decodes every inbound request into provider-neutral types before
-routing, then encodes it for the selected target's format.
-`switchyard-translation` converts requests, buffered responses, and streaming
-events between these formats, so Claude Code, Codex, OpenClaw, and SDK clients
-keep their native wire format regardless of the upstream a route selects.
-
-## Related Documentation
-
-- [Getting Started](getting_started.md): install Switchyard and run a first request
-- [Routing Overview](routing_algorithms/overview.md): choose and configure a routing strategy
-- [Server CLI Reference](cli_reference.md): configure and operate the standalone server
diff --git a/docs/core_concepts.md b/docs/core_concepts.md
deleted file mode 100644
index 0d6997cae..000000000
--- a/docs/core_concepts.md
+++ /dev/null
@@ -1,112 +0,0 @@
-# Core Concepts
-
-Switchyard routes LLM requests through provider-neutral Rust types and exposes
-the result through OpenAI- and Anthropic-compatible APIs. For setup, see
-[Getting Started](getting_started.md). For the complete request lifecycle, see
-[Architecture](architecture.md).
-
-## Runtime Surfaces
-
-Switchyard exposes the same Rust routing core through two runtime surfaces:
-
-- **`switchyard-server`** is the standalone HTTP proxy. It loads a native TOML
- deployment and exposes OpenAI Chat Completions, OpenAI Responses, and
- Anthropic Messages endpoints.
-- **`switchyard-libsy`** is the embeddable Rust library. Applications construct
- targets and algorithms directly and can let libsy make calls or fulfill its
- requested model calls themselves.
-
-## Request Flow
-
-The standalone server translates an inbound provider format into the shared
-protocol types before routing. The selected target's LLM client translates the
-request into its upstream format, makes the call, and translates the response
-back to the client's format.
-
-```mermaid
-flowchart LR
- client["Client<br/>OpenAI or Anthropic API"]
- request["Decode request<br/>provider-neutral types"]
- route["Route<br/>algorithm decision"]
- target["Target<br/>upstream model"]
- upstream["Encode request<br/>upstream format"]
- backend["LLM backend"]
- response["Decode and translate<br/>response or stream"]
-
- client --> request --> route --> target --> upstream --> backend
- backend --> response --> client
-```
-
-## LLM Clients, Targets, and Routes
-
-A native TOML deployment has three layers:
-
-| Layer | Defines |
-|---|---|
-| **LLM client** | Upstream base URL, wire format, credential environment variable, and retry policy. |
-| **Target** | One upstream model ID and the LLM client used to call it. |
-| **Route** | One client-visible model ID and the algorithm that selects or calls targets. |
-
-These layers keep provider transport separate from routing policy. Several
-targets can share one LLM client, and several routes can reuse the same target.
-Secrets stay outside the TOML: `api_key_env` names the environment variable the
-server reads at startup.
-
-## Model IDs
-
-The table keys in `llm_clients`, `targets`, and `routes` are local references
-inside the TOML file. Their `id` fields have different external meanings:
-
-- A target's `id` is the model ID sent to its upstream provider.
-- A route's `id` is the model ID clients send to Switchyard.
-
-The server lists route IDs on `GET /v1/models`. A request selects a route by
-putting that ID in its `model` field. The native Rust server does not discover
-or register additional provider models automatically. Each entry reports the route's
-declared `context_window` as its top-level `context_length` field (see
-[model discovery](../crates/switchyard-server/README.md#model-discovery)). The
-response includes an empty Codex `models` array so Codex keeps its own catalog and instructions. Select route
-aliases explicitly; they do not appear automatically in Codex's model picker.
-
-## Routing Algorithms
-
-An algorithm receives the normalized request, publishes a routing decision,
-and serves the selected target. The standalone server supports these primary
-route types:
-
-| Route type | Behavior |
-|---|---|
-| `passthrough` | Sends every request to one target. |
-| `random` | Selects among targets using optional relative weights. |
-| `llm_classifier` | Uses a classifier target to choose between weak and strong targets. |
-| `stage_router` | Uses tool-result and progress signals to choose an efficient or capable target. |
-
-Strong, weak, capable, and efficient are roles within an algorithm, not fixed
-properties of a model. The same upstream model can serve different roles in
-different routes.
-
-## Protocol Types and Translation
-
-`switchyard-protocol` defines provider-neutral requests, responses, messages,
-content blocks, tool calls, usage, and streaming events. Algorithms operate on
-these types rather than provider SDK objects.
-
-Each LLM client explicitly selects one upstream format:
-
-- `openai_chat`
-- `openai_responses`
-- `anthropic_messages`
-
-`switchyard-translation` converts requests, buffered responses, and streaming
-events between those formats. This lets a client keep its native API while the
-selected target uses a different upstream protocol.
-
-## Where to Go Next
-
-- [Getting Started](getting_started.md): install and run either execution path.
-- [Server CLI Reference](cli_reference.md): standalone server arguments.
-- [LLM Classifier Routing](routing_algorithms/llm_classifier_routing.md): configure classifier routing.
-- [Architecture](architecture.md): follow a request through the server and Rust crates.
-- [`switchyard-server`](../crates/switchyard-server/README.md): complete TOML schema, endpoints, and metrics.
-- [`switchyard-libsy`](../crates/libsy/README.md): embed and extend routing algorithms in Rust.
-- [Rust API reference](reference/rust_api.md): generated libsy, protocol, and translation documentation.
diff --git a/docs/index.md b/docs/index.md
index 577dd1d5a..a385f379d 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -2,39 +2,47 @@
Switchyard helps an AI agent choose which model handles each request. Embed its Rust core, **libsy**, in your gateway or agent harness. Your application keeps its model clients, credentials, and service.
-**[Start with the Rust quickstart](getting_started.md)**: add the crates, run a routing example, and send the selected request through your model client.
+Choose where routing belongs in your application. Use an existing integration,
+or embed libsy and keep your current model clients.
## Choose a Path
-| Goal | Path | Start here |
+| Goal | Start here | What you own |
|---|---|---|
-| Add routing to your Rust gateway or application | libsy | [Rust quickstart](getting_started.md) |
-| Use libsy from Python | Python Bindings | [Python embedding](reference/host_integration.md#python-bindings) |
-| Evaluate routing locally with your own models | Local Evaluation | [Run the demo server](operations/local_evaluation.md) |
-| Route Codex or Claude Code using your existing login | Server Path | [Single-provider coding agents](recipes/single_provider_coding_agents.md) |
-| Add Switchyard routing to NeMo Relay | Native Plugin Path | [Use Switchyard with NeMo Relay](integrations/nemo_relay.md) |
-| Point the pi coding agent at the standalone proxy | Server Path | [Use Switchyard with pi](integrations/pi.md) |
-| Point Oh My Pi at the standalone proxy | Server Path | [Use Switchyard with Oh My Pi](integrations/oh_my_pi.md) |
+| Use routing through an inference provider | [Switchyard on OpenRouter](https://openrouter.ai/docs/guides/routing/routers/switchyard-router) | Your API requests and provider account. Follow the provider's available algorithms and controls. |
+| Add routing to your gateway | [NeMo Relay](integrations/nemo_relay.md) or the experimental [LiteLLM integration](../examples/litellm/README.md) | Gateway deployment, credentials, and operation. Check each integration's limits. |
+| Embed routing in a gateway, harness, or application | [Rust quickstart](getting_started.md), then [Mechanics of Libsy](mechanics_of_libsy.md) | Model execution and application lifecycle. [Python bindings](reference/host_integration.md#python-bindings) use the same core. |
-The standalone server is for demos, evaluation, and personal use. It is not a supported production deployment path. Its HTTP API supports OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages.
+## Try With a Local Agent
+
+The [reference server](operations/local_evaluation.md) gives you a quick way to
+try routing with your own models. It demonstrates libsy, protocol conversion, and
+configured execution. It is for local demos and personal use, not a supported
+production deployment or a service to scale.
+
+Use it with [Claude Code or Codex](recipes/single_provider_coding_agents.md),
+[pi](integrations/pi.md), or [Oh My Pi](integrations/oh_my_pi.md).
## Explore
- [Benchmarks](benchmarks.md): compare Terminal-Bench 2.1 and DeepSWE results and open their routing configs
-- [Core Concepts](core_concepts.md): learn the LLM client, target, and route layers
+- [Mechanics of Libsy](mechanics_of_libsy.md): understand steps, calls, and outcomes
+- [Switchyard Protocols](protocols/index.md): connect your model data to libsy
- [Routing Algorithms](routing_algorithms/overview.md): choose how requests select a model
-- [Architecture](architecture.md): understand libsy and the proxy components
-- [Server CLI Reference](cli_reference.md): inspect `switchyard-server` commands and options
-- [Rust API](reference/rust_api.md): browse libsy, protocol, and translation crate documentation
+- [Host Integration](reference/host_integration.md): connect your clients and application lifecycle
+- [Rust API](reference/rust_api.md): browse the core library, protocols, translation, clients, and runner
- [Context-Window Handling](operations/context_window.md): configure eviction and retry behavior
- [Tuning](tuning/index.md): the loop from verifying routing to recording a result
- [Troubleshooting](operations/troubleshooting.md): symptoms, silent misconfigurations, and fixes
## Reference
-- [`switchyard-server`](../crates/switchyard-server/README.md): server configuration, endpoints, and metrics
-- [`switchyard-libsy`](reference/rust_api.md#switchyard-libsy): embeddable routing algorithms
-- [`switchyard-protocol`](reference/rust_api.md#switchyard-protocol): provider-neutral API types
-- [`switchyard-translation`](reference/rust_api.md#switchyard-translation): protocol translation
+- <a href="rust/switchyard_libsy/"><code>switchyard-libsy</code> API</a>: embeddable routing algorithms
+- <a href="rust/switchyard_protocol/"><code>switchyard-protocol</code> API</a>: provider-neutral model data
+- <a href="rust/switchyard_translation/"><code>switchyard-translation</code> API</a>: provider-format conversion
+- <a href="rust/switchyard_llm_client/"><code>switchyard-llm-client</code> API</a>: optional HTTP clients and execution helpers
+- <a href="rust/switchyard_runner/"><code>switchyard-runner</code> API</a>: configured route construction and execution
- [`switchyard-nemo-relay-plugin`](../crates/switchyard-nemo-relay-plugin/README.md): native plugin build and configuration
- [Dynamo / agentgateway](../examples/dynamo-preproc/README.md): Switchyard PreProc integration example
+- [Component responsibilities](reference/rust_api.md#crate-boundary): choose the crates your integration needs
+- [Demo server CLI](cli_reference.md): local server commands and options
diff --git a/docs/reference/rust_api.md b/docs/reference/rust_api.md
index e0fa41e82..5c9a4bcb3 100644
--- a/docs/reference/rust_api.md
+++ b/docs/reference/rust_api.md
@@ -1,12 +1,12 @@
# Rust API
-Switchyard publishes generated API documentation for its embeddable routing
-library, provider-neutral protocol types, and format translation.
+Choose the crates your integration needs. The links below open generated Rust
+API documentation for the core library and its optional supporting components.
## `switchyard-libsy`
-Use libsy to construct targets, run built-in routing algorithms, implement a
-custom algorithm, or drive model calls through the host-facing step stream.
+Use libsy to construct the model pool, run built-in routing algorithms, implement
+a custom algorithm, or handle requested work through the Step stream.
<a href="../../rust/switchyard_libsy/">Open the generated libsy API documentation</a>
@@ -31,6 +31,15 @@ execution helpers when your application does not drive the step stream itself.
<a href="../../rust/switchyard_llm_client/">Open the generated client API documentation</a>
+## `switchyard-runner`
+
+Use the optional runner to load TOML configuration, resolve named routes, and
+execute them inside a serving integration. See
+<a href="../../rust/switchyard_runner/struct.Runner.html"><code>Runner</code></a>
+and the [configuration reference](toml_schema.md).
+
+<a href="../../rust/switchyard_runner/">Open the generated runner API documentation</a>
+
For field meanings and provider API mappings, use the [LLM protocol reference](protocols/llm_requests.md)
or [decision protocol reference](protocols/decision_questions.md).
@@ -48,9 +57,8 @@ Add `switchyard-translation` when your application directly converts requests,
responses, or streams between provider formats. Use a version compatible with
your other Switchyard dependencies.
-## CI previews
-
-The Documentation workflow publishes a preview for same-repository pull
-requests. Open the workflow's **Deploy PR preview** summary to find its preview
-URL, then use the Rust API links above. The **docs-site** build artifact contains
-the same MkDocs and rustdoc output for one day.
+The runner and HTTP client are optional for direct libsy integration. Your host
+can construct the algorithm and execute the requested work itself. The
+[demo server](../operations/local_evaluation.md) is a reference application around
+the runner; [Python bindings](host_integration.md#python-bindings) expose the
+same routing core to Python applications.
diff --git a/docs/routing_algorithms/escalation_router_routing.md b/docs/routing_algorithms/escalation_router_routing.md
index baae15401..fa95ec3e4 100644
--- a/docs/routing_algorithms/escalation_router_routing.md
+++ b/docs/routing_algorithms/escalation_router_routing.md
@@ -256,5 +256,4 @@ retained nor logged.
models, with measured pairs.
- [LLM Classifier Routing](llm_classifier_routing.md): pick a tier up front
instead of judging the run.
-- [Architecture](../architecture.md): the end-to-end request lifecycle and system
- boundaries.
+- [Mechanics of Libsy](../mechanics_of_libsy.md): the execution model and host responsibilities.
diff --git a/docs/routing_algorithms/model_selection.md b/docs/routing_algorithms/model_selection.md
index 396c7068f..057a8a374 100644
--- a/docs/routing_algorithms/model_selection.md
+++ b/docs/routing_algorithms/model_selection.md
@@ -18,8 +18,8 @@ Each strategy names its models by role. The TOML keys differ by route type:
| `advisor` | `executor_target` | `advisor_target` reviews. It does not serve turns. | The gate rules. |
A role is not a property of a model. The same model can be the capable tier in
-one route and the efficient tier in another. See
-[Core Concepts](../core_concepts.md#routing-algorithms).
+one route and the efficient tier in another. See the
+[model pool example](../mechanics_of_libsy.md#start-with-a-request).
What each role needs:
diff --git a/docs/routing_algorithms/overview.md b/docs/routing_algorithms/overview.md
index fdde00f03..9074eb4a4 100644
--- a/docs/routing_algorithms/overview.md
+++ b/docs/routing_algorithms/overview.md
@@ -5,8 +5,9 @@ becomes a model ID available through OpenAI Chat Completions, Anthropic Messages
and OpenAI Responses requests.
Use this page to choose a routing strategy, then open its detailed page for
-configuration and tuning. For the vocabulary these pages use, see
-[Core Concepts](../core_concepts.md).
+configuration and tuning. [Mechanics of Libsy](../mechanics_of_libsy.md) explains
+the execution model; [Switchyard Protocols](../protocols/index.md) explains the
+request and response data.
## Choose a strategy
diff --git a/docs/routing_algorithms/stage_router_routing.md b/docs/routing_algorithms/stage_router_routing.md
index 80edf1277..eac940e1f 100644
--- a/docs/routing_algorithms/stage_router_routing.md
+++ b/docs/routing_algorithms/stage_router_routing.md
@@ -424,7 +424,6 @@ the `stage router override` log line carries it for overrides:
- [Model Selection](model_selection.md): choose and check the two models before
tuning the threshold.
-- [Architecture](../architecture.md): the end-to-end request lifecycle and
- system boundaries.
+- [Mechanics of Libsy](../mechanics_of_libsy.md): the execution model and host responsibilities.
- [TOML Schema](../reference/toml_schema.md#stage_router): the complete
configuration reference.
diff --git a/mkdocs.yml b/mkdocs.yml
index 48bf8dfb3..f1a75b190 100644
--- a/mkdocs.yml
+++ b/mkdocs.yml
@@ -24,22 +24,14 @@ nav:
- Overview: protocols/index.md
- LLM-Related Protocols: protocols/llm.md
- Decision Model-Related Protocols: protocols/decisions.md
- - Evaluate Locally: operations/local_evaluation.md
- Known Issues: known_issues.md
- - Benchmarks: benchmarks.md
- - Concepts:
- - Core Concepts: core_concepts.md
- - Architecture: architecture.md
- - Integrations:
- - NeMo Relay: integrations/nemo_relay.md
- - pi: integrations/pi.md
- - Oh My Pi: integrations/oh_my_pi.md
- - Recipes:
- - Single-provider coding agents: recipes/single_provider_coding_agents.md
+ - Integrate Switchyard:
+ - Embed in Your Gateway or Harness: reference/host_integration.md
+ - Gateways:
+ - NeMo Relay: integrations/nemo_relay.md
- Routing:
- Algorithms:
- Overview: routing_algorithms/overview.md
- - Model Selection: routing_algorithms/model_selection.md
- Task (LLM Classifier): routing_algorithms/llm_classifier_routing.md
- Execution (Stage Router): routing_algorithms/stage_router_routing.md
- Plan/Execute Routing: routing_algorithms/plan_execute_routing.md
@@ -49,12 +41,16 @@ nav:
- Escalation-Router Routing: routing_algorithms/escalation_router_routing.md
- Advisor-Gate Routing: routing_algorithms/advisor_gate_routing.md
- Verification-Gated Routing: routing_algorithms/vgr_routing.md
- - Tuning:
- - Tuning Loop: tuning/index.md
- - Operations:
- - Troubleshooting: operations/troubleshooting.md
- - Context-Window Handling: operations/context_window.md
- - Soak Testing: operations/soak_test.md
+ - Choose Models: routing_algorithms/model_selection.md
+ - Evaluate Routing:
+ - Benchmarks: benchmarks.md
+ - Compare and Tune: tuning/index.md
+ - Local Demo:
+ - Run the Reference Server: operations/local_evaluation.md
+ - Local Agents:
+ - Claude Code and Codex: recipes/single_provider_coding_agents.md
+ - pi: integrations/pi.md
+ - Oh My Pi: integrations/oh_my_pi.md
- Reference:
- Protocols:
- LLM:
@@ -64,11 +60,14 @@ nav:
- Decision Models:
- Questions: reference/protocols/decision_questions.md
- Answers: reference/protocols/decision_answers.md
- - Host Integration: reference/host_integration.md
- - Server CLI Reference: cli_reference.md
- - TOML Schema: reference/toml_schema.md
+ - Runner Configuration (TOML): reference/toml_schema.md
- OpenTelemetry: reference/opentelemetry.md
- Rust API: reference/rust_api.md
+ - Context-Window Handling: operations/context_window.md
+ - Troubleshooting: operations/troubleshooting.md
+ - Demo Server:
+ - CLI: cli_reference.md
+ - Soak Testing: operations/soak_test.md
exclude_docs: |
internal/**