From 0da68833af4c77ab78fb4b8456ab69ae04de62b2 Mon Sep 17 00:00:00 2001
From: rob thijssen <grenade@rob.tn>
Date: Tue, 14 Apr 2026 18:13:30 +0300
Subject: [PATCH] feat: scaffold cortex workspace

Rust reverse-proxy for multi-node mistral.rs inference clusters.
Includes crate structure (cortex-core, cortex-gateway, cortex-agent,
cortex-cli), config loading, OpenAI/Anthropic translation stubs,
model routing, eviction, polling, and streaming proxy scaffolding.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---
 .gitignore                            |    6 +
 CLAUDE.md                             |  141 ++
 Cargo.lock                            | 2787 +++++++++++++++++++++++++
 Cargo.toml                            |   57 +
 README.md                             |  138 ++
 cortex.example.toml                   |   45 +
 crates/cortex-agent/Cargo.toml        |   14 +
 crates/cortex-agent/src/agent.rs      |   72 +
 crates/cortex-agent/src/lib.rs        |    1 +
 crates/cortex-cli/Cargo.toml          |   20 +
 crates/cortex-cli/src/main.rs         |  112 +
 crates/cortex-core/Cargo.toml         |   15 +
 crates/cortex-core/src/anthropic.rs   |   87 +
 crates/cortex-core/src/config.rs      |   79 +
 crates/cortex-core/src/lib.rs         |    6 +
 crates/cortex-core/src/metrics.rs     |   23 +
 crates/cortex-core/src/node.rs        |   74 +
 crates/cortex-core/src/openai.rs      |  122 ++
 crates/cortex-core/src/translate.rs   |  114 +
 crates/cortex-gateway/Cargo.toml      |   25 +
 crates/cortex-gateway/src/evictor.rs  |  106 +
 crates/cortex-gateway/src/handlers.rs |  207 ++
 crates/cortex-gateway/src/lib.rs      |   51 +
 crates/cortex-gateway/src/metrics.rs  |   55 +
 crates/cortex-gateway/src/poller.rs   |  103 +
 crates/cortex-gateway/src/proxy.rs    |   82 +
 crates/cortex-gateway/src/router.rs   |   74 +
 crates/cortex-gateway/src/state.rs    |   43 +
 28 files changed, 4659 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 CLAUDE.md
 create mode 100644 Cargo.lock
 create mode 100644 Cargo.toml
 create mode 100644 README.md
 create mode 100644 cortex.example.toml
 create mode 100644 crates/cortex-agent/Cargo.toml
 create mode 100644 crates/cortex-agent/src/agent.rs
 create mode 100644 crates/cortex-agent/src/lib.rs
 create mode 100644 crates/cortex-cli/Cargo.toml
 create mode 100644 crates/cortex-cli/src/main.rs
 create mode 100644 crates/cortex-core/Cargo.toml
 create mode 100644 crates/cortex-core/src/anthropic.rs
 create mode 100644 crates/cortex-core/src/config.rs
 create mode 100644 crates/cortex-core/src/lib.rs
 create mode 100644 crates/cortex-core/src/metrics.rs
 create mode 100644 crates/cortex-core/src/node.rs
 create mode 100644 crates/cortex-core/src/openai.rs
 create mode 100644 crates/cortex-core/src/translate.rs
 create mode 100644 crates/cortex-gateway/Cargo.toml
 create mode 100644 crates/cortex-gateway/src/evictor.rs
 create mode 100644 crates/cortex-gateway/src/handlers.rs
 create mode 100644 crates/cortex-gateway/src/lib.rs
 create mode 100644 crates/cortex-gateway/src/metrics.rs
 create mode 100644 crates/cortex-gateway/src/poller.rs
 create mode 100644 crates/cortex-gateway/src/proxy.rs
 create mode 100644 crates/cortex-gateway/src/router.rs
 create mode 100644 crates/cortex-gateway/src/state.rs

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..84db778
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,6 @@
+/target
+*.swp
+*.swo
+.idea/
+.vscode/
+cortex.toml
diff --git a/CLAUDE.md b/CLAUDE.md
new file mode 100644
index 0000000..157eff2
--- /dev/null
+++ b/CLAUDE.md
@@ -0,0 +1,141 @@
+# CLAUDE.md — cortex
+
+## Project overview
+
+cortex is a Rust reverse-proxy that sits in front of multiple
+mistral.rs inference nodes and presents a unified OpenAI + Anthropic
+compatible API surface. It handles model routing, lifecycle management
+(load/unload/evict), request translation, and metrics collection.
+
+## Repository layout
+
+```
+cortex/
+├── Cargo.toml              # workspace root
+├── cortex.toml      # example gateway config
+├── README.md
+├── CLAUDE.md               # ← you are here
+├── crates/
+│   ├── cortex-core/            # shared types, config, envelopes
+│   │   └── src/
+│   │       ├── lib.rs
+│   │       ├── config.rs       # figment-based config structs
+│   │       ├── node.rs         # NodeState, ModelStatus
+│   │       ├── openai.rs       # OpenAI request/response types
+│   │       ├── anthropic.rs    # Anthropic request/response types
+│   │       ├── translate.rs    # OpenAI <-> Anthropic translation
+│   │       └── metrics.rs      # RequestMetrics, histogram helpers
+│   ├── cortex-gateway/         # the HTTP proxy server
+│   │   └── src/
+│   │       ├── lib.rs
+│   │       ├── state.rs        # CortexState: Arc<RwLock<...>>
+│   │       ├── router.rs       # model -> node routing logic
+│   │       ├── proxy.rs        # streaming HTTP proxy to backends
+│   │       ├── evictor.rs      # LRU/priority eviction logic
+│   │       ├── poller.rs       # background task polling node status
+│   │       ├── handlers.rs     # axum handlers (chat, completions, models, etc.)
+│   │       └── metrics.rs      # prometheus exporter endpoint
+│   ├── cortex-agent/           # per-node sidecar (future: defrag, restart)
+│   │   └── src/
+│   │       ├── lib.rs
+│   │       └── agent.rs        # local node management
+│   └── cortex-cli/             # CLI entrypoint
+│       └── src/
+│           └── main.rs
+└── tests/                  # integration tests (future)
+```
+
+## Key design decisions
+
+### mistral.rs HTTP API for model lifecycle
+mistral.rs (v0.8+) supports dynamic model loading/unloading at runtime:
+- `POST /v1/models/unload {"model_id": "..."}` — frees VRAM, preserves config
+- `POST /v1/models/reload {"model_id": "..."}` — explicitly reload
+- `POST /v1/models/status {"model_id": "..."}` — loaded/unloaded/reloading
+- `GET /v1/models` — lists all models with status field
+- Lazy loading: requests to unloaded models trigger automatic reload
+
+The gateway does NOT manage systemd units for model swaps. It calls these
+HTTP endpoints directly. The only systemd interaction is for full-process
+restarts after VRAM fragmentation accumulates (defrag_after_cycles).
+
+### Streaming proxy
+Chat completions are proxied as SSE streams. The gateway must:
+1. Parse the inbound request to extract the model name
+2. Route to the correct backend node
+3. Stream the response back, capturing token timing for metrics
+4. NOT buffer the full response — true streaming passthrough
+
+### Anthropic translation
+When a request arrives at `/v1/messages` (Anthropic format), the gateway
+translates it to OpenAI format before proxying to mistral.rs, then
+translates the response back. This is stateless envelope transformation.
+
+### Eviction
+The evictor runs as a background task. Before loading a model on a node
+where VRAM is tight:
+1. Check if the model is already loaded elsewhere → route there instead
+2. Find the LRU model on the target node (excluding pinned models)
+3. Call `/v1/models/unload` on that model
+4. The incoming request's lazy-load triggers the new model load
+
+### Metrics
+Per-request: model, node, prompt_tokens, completion_tokens, total_tokens,
+tok_per_sec, time_to_first_token_ms, total_latency_ms.
+Exposed as Prometheus histograms/counters on a separate port.
+
+## Tech stack
+
+- **Rust 2024 edition** — workspace with 4 crates
+- **Axum 0.8** — HTTP framework (same as mistral.rs itself)
+- **reqwest** — HTTP client for proxying to backends
+- **figment** — config loading (TOML + env vars)
+- **tokio** — async runtime
+- **metrics + metrics-exporter-prometheus** — observability
+- **tracing** — structured logging
+
+## Build commands
+
+```sh
+cargo build --release           # build all crates
+cargo run -p cortex-cli -- serve    # run the gateway
+cargo test                      # run all tests
+cargo clippy --workspace        # lint
+```
+
+## Environment
+
+- Targets Fedora 43 (systemd, SELinux enforcing)
+- Nodes communicate over a private network (e.g. WireGuard mesh)
+  - One or more GPU nodes running mistral.rs on port 8080
+  - Optionally a metrics-only node (no GPU) for Prometheus/Grafana
+- Each node runs `mistralrs serve` on port 8080
+- Gateway listens on port 8000 (API) and 9100 (metrics)
+- TLS terminated at gateway or via nginx; internal traffic is plaintext over WireGuard
+
+## Conventions
+
+- Error handling: `anyhow` for binaries, `thiserror` for library crates
+- No `unwrap()` in library code; `expect()` only with clear rationale
+- All public types derive `Debug, Clone, Serialize, Deserialize` where sensible
+- Config structs use `figment` with TOML as primary source, env vars as override
+- Prefer `Arc<RwLock<...>>` for shared fleet state; minimize lock duration
+- SSE streaming uses `tokio_stream` + `eventsource-stream` for parsing
+- Log at `info` for request routing, `debug` for proxy details, `warn` for
+  eviction and node health, `error` for proxy failures
+
+## Current status
+
+**Scaffold phase** — crate structure, types, and handler stubs are in place.
+The following needs implementation:
+
+1. **cortex-core**: Flesh out OpenAI/Anthropic envelope types with all fields
+   needed for chat completions (streaming + non-streaming)
+2. **cortex-gateway/proxy.rs**: Implement streaming HTTP proxy with SSE passthrough
+3. **cortex-gateway/router.rs**: Model-to-node routing with fallback to least-loaded
+4. **cortex-gateway/evictor.rs**: LRU eviction with pinning support
+5. **cortex-gateway/poller.rs**: Background polling of node `/v1/models` endpoints
+6. **cortex-gateway/handlers.rs**: Wire up axum routes to proxy logic
+7. **cortex-core/translate.rs**: OpenAI <-> Anthropic request/response translation
+8. **cortex-agent**: Sidecar for VRAM defrag restarts (lower priority)
+9. **Integration tests**: Mock mistralrs backends, test routing + eviction
diff --git a/Cargo.lock b/Cargo.lock
new file mode 100644
index 0000000..db91ab8
--- /dev/null
+++ b/Cargo.lock
@@ -0,0 +1,2787 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "ahash"
+version = "0.8.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75"
+dependencies = [
+ "cfg-if",
+ "once_cell",
+ "version_check",
+ "zerocopy",
+]
+
+[[package]]
+name = "aho-corasick"
+version = "1.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ddd31a130427c27518df266943a5308ed92d4b226cc639f5a8f1002816174301"
+dependencies = [
+ "memchr",
+]
+
+[[package]]
+name = "android_system_properties"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "819e7219dbd41043ac279b19830f2efc897156490d7fd6ea916720117ee66311"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "anstream"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "824a212faf96e9acacdbd09febd34438f8f711fb84e09a8916013cd7815ca28d"
+dependencies = [
+ "anstyle",
+ "anstyle-parse",
+ "anstyle-query",
+ "anstyle-wincon",
+ "colorchoice",
+ "is_terminal_polyfill",
+ "utf8parse",
+]
+
+[[package]]
+name = "anstyle"
+version = "1.0.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "940b3a0ca603d1eade50a4846a2afffd5ef57a9feac2c0e2ec2e14f9ead76000"
+
+[[package]]
+name = "anstyle-parse"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "52ce7f38b242319f7cabaa6813055467063ecdc9d355bbb4ce0c68908cd8130e"
+dependencies = [
+ "utf8parse",
+]
+
+[[package]]
+name = "anstyle-query"
+version = "1.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "40c48f72fd53cd289104fc64099abca73db4166ad86ea0b4341abe65af83dadc"
+dependencies = [
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "anstyle-wincon"
+version = "3.0.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "291e6a250ff86cd4a820112fb8898808a366d8f9f58ce16d1f538353ad55747d"
+dependencies = [
+ "anstyle",
+ "once_cell_polyfill",
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "anyhow"
+version = "1.0.102"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c"
+
+[[package]]
+name = "atomic"
+version = "0.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a89cbf775b137e9b968e67227ef7f775587cde3fd31b0d8599dbd0f598a48340"
+dependencies = [
+ "bytemuck",
+]
+
+[[package]]
+name = "atomic-waker"
+version = "1.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1505bd5d3d116872e7271a6d4e16d81d0c8570876c8de68093a09ac269d8aac0"
+
+[[package]]
+name = "autocfg"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c08606f8c3cbf4ce6ec8e28fb0014a2c086708fe954eaa885384a6165172e7e8"
+
+[[package]]
+name = "aws-lc-rs"
+version = "1.16.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a054912289d18629dc78375ba2c3726a3afe3ff71b4edba9dedfca0e3446d1fc"
+dependencies = [
+ "aws-lc-sys",
+ "zeroize",
+]
+
+[[package]]
+name = "aws-lc-sys"
+version = "0.39.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "83a25cf98105baa966497416dbd42565ce3a8cf8dbfd59803ec9ad46f3126399"
+dependencies = [
+ "cc",
+ "cmake",
+ "dunce",
+ "fs_extra",
+]
+
+[[package]]
+name = "axum"
+version = "0.8.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "31b698c5f9a010f6573133b09e0de5408834d0c82f8d7475a89fc1867a71cd90"
+dependencies = [
+ "axum-core",
+ "axum-macros",
+ "bytes",
+ "form_urlencoded",
+ "futures-util",
+ "http",
+ "http-body",
+ "http-body-util",
+ "hyper",
+ "hyper-util",
+ "itoa",
+ "matchit",
+ "memchr",
+ "mime",
+ "percent-encoding",
+ "pin-project-lite",
+ "serde_core",
+ "serde_json",
+ "serde_path_to_error",
+ "serde_urlencoded",
+ "sync_wrapper",
+ "tokio",
+ "tower",
+ "tower-layer",
+ "tower-service",
+ "tracing",
+]
+
+[[package]]
+name = "axum-core"
+version = "0.5.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "08c78f31d7b1291f7ee735c1c6780ccde7785daae9a9206026862dab7d8792d1"
+dependencies = [
+ "bytes",
+ "futures-core",
+ "http",
+ "http-body",
+ "http-body-util",
+ "mime",
+ "pin-project-lite",
+ "sync_wrapper",
+ "tower-layer",
+ "tower-service",
+ "tracing",
+]
+
+[[package]]
+name = "axum-macros"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7aa268c23bfbbd2c4363b9cd302a4f504fb2a9dfe7e3451d66f35dd392e20aca"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "base64"
+version = "0.22.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
+
+[[package]]
+name = "bitflags"
+version = "2.11.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c4512299f36f043ab09a583e57bceb5a5aab7a73db1805848e8fef3c9e8c78b3"
+
+[[package]]
+name = "bumpalo"
+version = "3.20.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5d20789868f4b01b2f2caec9f5c4e0213b41e3e5702a50157d699ae31ced2fcb"
+
+[[package]]
+name = "bytemuck"
+version = "1.25.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c8efb64bd706a16a1bdde310ae86b351e4d21550d98d056f22f8a7f7a2183fec"
+
+[[package]]
+name = "bytes"
+version = "1.11.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1e748733b7cbc798e1434b6ac524f0c1ff2ab456fe201501e6497c8417a4fc33"
+
+[[package]]
+name = "cc"
+version = "1.2.60"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "43c5703da9466b66a946814e1adf53ea2c90f10063b86290cc9eb67ce3478a20"
+dependencies = [
+ "find-msvc-tools",
+ "jobserver",
+ "libc",
+ "shlex",
+]
+
+[[package]]
+name = "cfg-if"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
+
+[[package]]
+name = "chrono"
+version = "0.4.44"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c673075a2e0e5f4a1dde27ce9dee1ea4558c7ffe648f576438a20ca1d2acc4b0"
+dependencies = [
+ "iana-time-zone",
+ "js-sys",
+ "num-traits",
+ "serde",
+ "wasm-bindgen",
+ "windows-link",
+]
+
+[[package]]
+name = "clap"
+version = "4.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b193af5b67834b676abd72466a96c1024e6a6ad978a1f484bd90b85c94041351"
+dependencies = [
+ "clap_builder",
+ "clap_derive",
+]
+
+[[package]]
+name = "clap_builder"
+version = "4.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "714a53001bf66416adb0e2ef5ac857140e7dc3a0c48fb28b2f10762fc4b5069f"
+dependencies = [
+ "anstream",
+ "anstyle",
+ "clap_lex",
+ "strsim",
+]
+
+[[package]]
+name = "clap_derive"
+version = "4.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1110bd8a634a1ab8cb04345d8d878267d57c3cf1b38d91b71af6686408bbca6a"
+dependencies = [
+ "heck",
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "clap_lex"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c8d4a3bb8b1e0c1050499d1815f5ab16d04f0959b233085fb31653fbfc9d98f9"
+
+[[package]]
+name = "cmake"
+version = "0.1.58"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c0f78a02292a74a88ac736019ab962ece0bc380e3f977bf72e376c5d78ff0678"
+dependencies = [
+ "cc",
+]
+
+[[package]]
+name = "colorchoice"
+version = "1.0.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1d07550c9036bf2ae0c684c4297d503f838287c83c53686d05370d0e139ae570"
+
+[[package]]
+name = "core-foundation"
+version = "0.9.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "91e195e091a93c46f7102ec7818a2aa394e1e1771c3ab4825963fa03e45afb8f"
+dependencies = [
+ "core-foundation-sys",
+ "libc",
+]
+
+[[package]]
+name = "core-foundation"
+version = "0.10.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b2a6cd9ae233e7f62ba4e9353e81a88df7fc8a5987b8d445b4d90c879bd156f6"
+dependencies = [
+ "core-foundation-sys",
+ "libc",
+]
+
+[[package]]
+name = "core-foundation-sys"
+version = "0.8.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
+
+[[package]]
+name = "cortex-agent"
+version = "0.1.0"
+dependencies = [
+ "anyhow",
+ "cortex-core",
+ "reqwest",
+ "serde",
+ "serde_json",
+ "tokio",
+ "tracing",
+]
+
+[[package]]
+name = "cortex-cli"
+version = "0.1.0"
+dependencies = [
+ "anyhow",
+ "clap",
+ "cortex-core",
+ "cortex-gateway",
+ "reqwest",
+ "serde_json",
+ "tokio",
+ "tracing",
+ "tracing-subscriber",
+]
+
+[[package]]
+name = "cortex-core"
+version = "0.1.0"
+dependencies = [
+ "anyhow",
+ "chrono",
+ "figment",
+ "serde",
+ "serde_json",
+ "thiserror 2.0.18",
+ "toml",
+ "tracing",
+]
+
+[[package]]
+name = "cortex-gateway"
+version = "0.1.0"
+dependencies = [
+ "anyhow",
+ "axum",
+ "bytes",
+ "chrono",
+ "cortex-core",
+ "eventsource-stream",
+ "futures",
+ "metrics",
+ "metrics-exporter-prometheus",
+ "reqwest",
+ "serde",
+ "serde_json",
+ "thiserror 2.0.18",
+ "tokio",
+ "tokio-stream",
+ "tower",
+ "tower-http",
+ "tracing",
+]
+
+[[package]]
+name = "crossbeam-epoch"
+version = "0.9.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e"
+dependencies = [
+ "crossbeam-utils",
+]
+
+[[package]]
+name = "crossbeam-utils"
+version = "0.8.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28"
+
+[[package]]
+name = "displaydoc"
+version = "0.2.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "dunce"
+version = "1.0.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "92773504d58c093f6de2459af4af33faa518c13451eb8f2b5698ed3d36e7c813"
+
+[[package]]
+name = "encoding_rs"
+version = "0.8.35"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "75030f3c4f45dafd7586dd6780965a8c7e8e285a5ecb86713e63a79c5b2766f3"
+dependencies = [
+ "cfg-if",
+]
+
+[[package]]
+name = "equivalent"
+version = "1.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "877a4ace8713b0bcf2a4e7eec82529c029f1d0619886d18145fea96c3ffe5c0f"
+
+[[package]]
+name = "errno"
+version = "0.3.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb"
+dependencies = [
+ "libc",
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "eventsource-stream"
+version = "0.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "74fef4569247a5f429d9156b9d0a2599914385dd189c539334c625d8099d90ab"
+dependencies = [
+ "futures-core",
+ "nom",
+ "pin-project-lite",
+]
+
+[[package]]
+name = "fastrand"
+version = "2.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9f1f227452a390804cdb637b74a86990f2a7d7ba4b7d5693aac9b4dd6defd8d6"
+
+[[package]]
+name = "figment"
+version = "0.10.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8cb01cd46b0cf372153850f4c6c272d9cbea2da513e07538405148f95bd789f3"
+dependencies = [
+ "atomic",
+ "pear",
+ "serde",
+ "toml",
+ "uncased",
+ "version_check",
+]
+
+[[package]]
+name = "find-msvc-tools"
+version = "0.1.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5baebc0774151f905a1a2cc41989300b1e6fbb29aff0ceffa1064fdd3088d582"
+
+[[package]]
+name = "fnv"
+version = "1.0.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
+
+[[package]]
+name = "foldhash"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d9c4f5dac5e15c24eb999c26181a6ca40b39fe946cbe4c263c7209467bc83af2"
+
+[[package]]
+name = "foreign-types"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f6f339eb8adc052cd2ca78910fda869aefa38d22d5cb648e6485e4d3fc06f3b1"
+dependencies = [
+ "foreign-types-shared",
+]
+
+[[package]]
+name = "foreign-types-shared"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "00b0228411908ca8685dba7fc2cdd70ec9990a6e753e89b6ac91a84c40fbaf4b"
+
+[[package]]
+name = "form_urlencoded"
+version = "1.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cb4cb245038516f5f85277875cdaa4f7d2c9a0fa0468de06ed190163b1581fcf"
+dependencies = [
+ "percent-encoding",
+]
+
+[[package]]
+name = "fs_extra"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
+
+[[package]]
+name = "futures"
+version = "0.3.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8b147ee9d1f6d097cef9ce628cd2ee62288d963e16fb287bd9286455b241382d"
+dependencies = [
+ "futures-channel",
+ "futures-core",
+ "futures-executor",
+ "futures-io",
+ "futures-sink",
+ "futures-task",
+ "futures-util",
+]
+
+[[package]]
+name = "futures-channel"
+version = "0.3.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "07bbe89c50d7a535e539b8c17bc0b49bdb77747034daa8087407d655f3f7cc1d"
+dependencies = [
+ "futures-core",
+ "futures-sink",
+]
+
+[[package]]
+name = "futures-core"
+version = "0.3.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7e3450815272ef58cec6d564423f6e755e25379b217b0bc688e295ba24df6b1d"
+
+[[package]]
+name = "futures-executor"
+version = "0.3.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "baf29c38818342a3b26b5b923639e7b1f4a61fc5e76102d4b1981c6dc7a7579d"
+dependencies = [
+ "futures-core",
+ "futures-task",
+ "futures-util",
+]
+
+[[package]]
+name = "futures-io"
+version = "0.3.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cecba35d7ad927e23624b22ad55235f2239cfa44fd10428eecbeba6d6a717718"
+
+[[package]]
+name = "futures-macro"
+version = "0.3.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e835b70203e41293343137df5c0664546da5745f82ec9b84d40be8336958447b"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "futures-sink"
+version = "0.3.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c39754e157331b013978ec91992bde1ac089843443c49cbc7f46150b0fad0893"
+
+[[package]]
+name = "futures-task"
+version = "0.3.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "037711b3d59c33004d3856fbdc83b99d4ff37a24768fa1be9ce3538a1cde4393"
+
+[[package]]
+name = "futures-util"
+version = "0.3.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "389ca41296e6190b48053de0321d02a77f32f8a5d2461dd38762c0593805c6d6"
+dependencies = [
+ "futures-channel",
+ "futures-core",
+ "futures-io",
+ "futures-macro",
+ "futures-sink",
+ "futures-task",
+ "memchr",
+ "pin-project-lite",
+ "slab",
+]
+
+[[package]]
+name = "getrandom"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ff2abc00be7fca6ebc474524697ae276ad847ad0a6b3faa4bcb027e9a4614ad0"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "wasi",
+]
+
+[[package]]
+name = "getrandom"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "899def5c37c4fd7b2664648c28120ecec138e4d395b459e5ca34f9cce2dd77fd"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "r-efi 5.3.0",
+ "wasip2",
+]
+
+[[package]]
+name = "getrandom"
+version = "0.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0de51e6874e94e7bf76d726fc5d13ba782deca734ff60d5bb2fb2607c7406555"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "r-efi 6.0.0",
+ "wasip2",
+ "wasip3",
+]
+
+[[package]]
+name = "h2"
+version = "0.4.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2f44da3a8150a6703ed5d34e164b875fd14c2cdab9af1252a9a1020bde2bdc54"
+dependencies = [
+ "atomic-waker",
+ "bytes",
+ "fnv",
+ "futures-core",
+ "futures-sink",
+ "http",
+ "indexmap",
+ "slab",
+ "tokio",
+ "tokio-util",
+ "tracing",
+]
+
+[[package]]
+name = "hashbrown"
+version = "0.15.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9229cfe53dfd69f0609a49f65461bd93001ea1ef889cd5529dd176593f5338a1"
+dependencies = [
+ "foldhash",
+]
+
+[[package]]
+name = "hashbrown"
+version = "0.17.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4f467dd6dccf739c208452f8014c75c18bb8301b050ad1cfb27153803edb0f51"
+
+[[package]]
+name = "heck"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
+
+[[package]]
+name = "http"
+version = "1.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e3ba2a386d7f85a81f119ad7498ebe444d2e22c2af0b86b069416ace48b3311a"
+dependencies = [
+ "bytes",
+ "itoa",
+]
+
+[[package]]
+name = "http-body"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1efedce1fb8e6913f23e0c92de8e62cd5b772a67e7b3946df930a62566c93184"
+dependencies = [
+ "bytes",
+ "http",
+]
+
+[[package]]
+name = "http-body-util"
+version = "0.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b021d93e26becf5dc7e1b75b1bed1fd93124b374ceb73f43d4d4eafec896a64a"
+dependencies = [
+ "bytes",
+ "futures-core",
+ "http",
+ "http-body",
+ "pin-project-lite",
+]
+
+[[package]]
+name = "httparse"
+version = "1.10.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6dbf3de79e51f3d586ab4cb9d5c3e2c14aa28ed23d180cf89b4df0454a69cc87"
+
+[[package]]
+name = "httpdate"
+version = "1.0.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "df3b46402a9d5adb4c86a0cf463f42e19994e3ee891101b1841f30a545cb49a9"
+
+[[package]]
+name = "hyper"
+version = "1.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6299f016b246a94207e63da54dbe807655bf9e00044f73ded42c3ac5305fbcca"
+dependencies = [
+ "atomic-waker",
+ "bytes",
+ "futures-channel",
+ "futures-core",
+ "h2",
+ "http",
+ "http-body",
+ "httparse",
+ "httpdate",
+ "itoa",
+ "pin-project-lite",
+ "smallvec",
+ "tokio",
+ "want",
+]
+
+[[package]]
+name = "hyper-rustls"
+version = "0.27.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c2b52f86d1d4bc0d6b4e6826d960b1b333217e07d36b882dca570a5e1c48895b"
+dependencies = [
+ "http",
+ "hyper",
+ "hyper-util",
+ "rustls",
+ "rustls-native-certs",
+ "tokio",
+ "tokio-rustls",
+ "tower-service",
+]
+
+[[package]]
+name = "hyper-tls"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "70206fc6890eaca9fde8a0bf71caa2ddfc9fe045ac9e5c70df101a7dbde866e0"
+dependencies = [
+ "bytes",
+ "http-body-util",
+ "hyper",
+ "hyper-util",
+ "native-tls",
+ "tokio",
+ "tokio-native-tls",
+ "tower-service",
+]
+
+[[package]]
+name = "hyper-util"
+version = "0.1.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "96547c2556ec9d12fb1578c4eaf448b04993e7fb79cbaad930a656880a6bdfa0"
+dependencies = [
+ "base64",
+ "bytes",
+ "futures-channel",
+ "futures-util",
+ "http",
+ "http-body",
+ "hyper",
+ "ipnet",
+ "libc",
+ "percent-encoding",
+ "pin-project-lite",
+ "socket2",
+ "system-configuration",
+ "tokio",
+ "tower-service",
+ "tracing",
+ "windows-registry",
+]
+
+[[package]]
+name = "iana-time-zone"
+version = "0.1.65"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e31bc9ad994ba00e440a8aa5c9ef0ec67d5cb5e5cb0cc7f8b744a35b389cc470"
+dependencies = [
+ "android_system_properties",
+ "core-foundation-sys",
+ "iana-time-zone-haiku",
+ "js-sys",
+ "log",
+ "wasm-bindgen",
+ "windows-core",
+]
+
+[[package]]
+name = "iana-time-zone-haiku"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f31827a206f56af32e590ba56d5d2d085f558508192593743f16b2306495269f"
+dependencies = [
+ "cc",
+]
+
+[[package]]
+name = "icu_collections"
+version = "2.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2984d1cd16c883d7935b9e07e44071dca8d917fd52ecc02c04d5fa0b5a3f191c"
+dependencies = [
+ "displaydoc",
+ "potential_utf",
+ "utf8_iter",
+ "yoke",
+ "zerofrom",
+ "zerovec",
+]
+
+[[package]]
+name = "icu_locale_core"
+version = "2.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "92219b62b3e2b4d88ac5119f8904c10f8f61bf7e95b640d25ba3075e6cac2c29"
+dependencies = [
+ "displaydoc",
+ "litemap",
+ "tinystr",
+ "writeable",
+ "zerovec",
+]
+
+[[package]]
+name = "icu_normalizer"
+version = "2.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c56e5ee99d6e3d33bd91c5d85458b6005a22140021cc324cea84dd0e72cff3b4"
+dependencies = [
+ "icu_collections",
+ "icu_normalizer_data",
+ "icu_properties",
+ "icu_provider",
+ "smallvec",
+ "zerovec",
+]
+
+[[package]]
+name = "icu_normalizer_data"
+version = "2.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "da3be0ae77ea334f4da67c12f149704f19f81d1adf7c51cf482943e84a2bad38"
+
+[[package]]
+name = "icu_properties"
+version = "2.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bee3b67d0ea5c2cca5003417989af8996f8604e34fb9ddf96208a033901e70de"
+dependencies = [
+ "icu_collections",
+ "icu_locale_core",
+ "icu_properties_data",
+ "icu_provider",
+ "zerotrie",
+ "zerovec",
+]
+
+[[package]]
+name = "icu_properties_data"
+version = "2.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e2bbb201e0c04f7b4b3e14382af113e17ba4f63e2c9d2ee626b720cbce54a14"
+
+[[package]]
+name = "icu_provider"
+version = "2.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "139c4cf31c8b5f33d7e199446eff9c1e02decfc2f0eec2c8d71f65befa45b421"
+dependencies = [
+ "displaydoc",
+ "icu_locale_core",
+ "writeable",
+ "yoke",
+ "zerofrom",
+ "zerotrie",
+ "zerovec",
+]
+
+[[package]]
+name = "id-arena"
+version = "2.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3d3067d79b975e8844ca9eb072e16b31c3c1c36928edf9c6789548c524d0d954"
+
+[[package]]
+name = "idna"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3b0875f23caa03898994f6ddc501886a45c7d3d62d04d2d90788d47be1b1e4de"
+dependencies = [
+ "idna_adapter",
+ "smallvec",
+ "utf8_iter",
+]
+
+[[package]]
+name = "idna_adapter"
+version = "1.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3acae9609540aa318d1bc588455225fb2085b9ed0c4f6bd0d9d5bcd86f1a0344"
+dependencies = [
+ "icu_normalizer",
+ "icu_properties",
+]
+
+[[package]]
+name = "indexmap"
+version = "2.14.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d466e9454f08e4a911e14806c24e16fba1b4c121d1ea474396f396069cf949d9"
+dependencies = [
+ "equivalent",
+ "hashbrown 0.17.0",
+ "serde",
+ "serde_core",
+]
+
+[[package]]
+name = "inlinable_string"
+version = "0.1.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c8fae54786f62fb2918dcfae3d568594e50eb9b5c25bf04371af6fe7516452fb"
+
+[[package]]
+name = "ipnet"
+version = "2.12.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d98f6fed1fde3f8c21bc40a1abb88dd75e67924f9cffc3ef95607bad8017f8e2"
+
+[[package]]
+name = "iri-string"
+version = "0.7.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "25e659a4bb38e810ebc252e53b5814ff908a8c58c2a9ce2fae1bbec24cbf4e20"
+dependencies = [
+ "memchr",
+ "serde",
+]
+
+[[package]]
+name = "is_terminal_polyfill"
+version = "1.70.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a6cb138bb79a146c1bd460005623e142ef0181e3d0219cb493e02f7d08a35695"
+
+[[package]]
+name = "itoa"
+version = "1.0.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682"
+
+[[package]]
+name = "jobserver"
+version = "0.1.34"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9afb3de4395d6b3e67a780b6de64b51c978ecf11cb9a462c66be7d4ca9039d33"
+dependencies = [
+ "getrandom 0.3.4",
+ "libc",
+]
+
+[[package]]
+name = "js-sys"
+version = "0.3.95"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2964e92d1d9dc3364cae4d718d93f227e3abb088e747d92e0395bfdedf1c12ca"
+dependencies = [
+ "cfg-if",
+ "futures-util",
+ "once_cell",
+ "wasm-bindgen",
+]
+
+[[package]]
+name = "lazy_static"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
+
+[[package]]
+name = "leb128fmt"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09edd9e8b54e49e587e4f6295a7d29c3ea94d469cb40ab8ca70b288248a81db2"
+
+[[package]]
+name = "libc"
+version = "0.2.185"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "52ff2c0fe9bc6cb6b14a0592c2ff4fa9ceb83eea9db979b0487cd054946a2b8f"
+
+[[package]]
+name = "linux-raw-sys"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32a66949e030da00e8c7d4434b251670a91556f4144941d37452769c25d58a53"
+
+[[package]]
+name = "litemap"
+version = "0.8.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "92daf443525c4cce67b150400bc2316076100ce0b3686209eb8cf3c31612e6f0"
+
+[[package]]
+name = "lock_api"
+version = "0.4.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "224399e74b87b5f3557511d98dff8b14089b3dadafcab6bb93eab67d3aace965"
+dependencies = [
+ "scopeguard",
+]
+
+[[package]]
+name = "log"
+version = "0.4.29"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5e5032e24019045c762d3c0f28f5b6b8bbf38563a65908389bf7978758920897"
+
+[[package]]
+name = "matchers"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d1525a2a28c7f4fa0fc98bb91ae755d1e2d1505079e05539e35bc876b5d65ae9"
+dependencies = [
+ "regex-automata",
+]
+
+[[package]]
+name = "matchit"
+version = "0.8.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "47e1ffaa40ddd1f3ed91f717a33c8c0ee23fff369e3aa8772b9605cc1d22f4c3"
+
+[[package]]
+name = "memchr"
+version = "2.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f8ca58f447f06ed17d5fc4043ce1b10dd205e060fb3ce5b979b8ed8e59ff3f79"
+
+[[package]]
+name = "metrics"
+version = "0.24.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5d5312e9ba3771cfa961b585728215e3d972c950a3eed9252aa093d6301277e8"
+dependencies = [
+ "ahash",
+ "portable-atomic",
+]
+
+[[package]]
+name = "metrics-exporter-prometheus"
+version = "0.16.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dd7399781913e5393588a8d8c6a2867bf85fb38eaf2502fdce465aad2dc6f034"
+dependencies = [
+ "base64",
+ "http-body-util",
+ "hyper",
+ "hyper-rustls",
+ "hyper-util",
+ "indexmap",
+ "ipnet",
+ "metrics",
+ "metrics-util",
+ "quanta",
+ "thiserror 1.0.69",
+ "tokio",
+ "tracing",
+]
+
+[[package]]
+name = "metrics-util"
+version = "0.19.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b8496cc523d1f94c1385dd8f0f0c2c480b2b8aeccb5b7e4485ad6365523ae376"
+dependencies = [
+ "crossbeam-epoch",
+ "crossbeam-utils",
+ "hashbrown 0.15.5",
+ "metrics",
+ "quanta",
+ "rand",
+ "rand_xoshiro",
+ "sketches-ddsketch",
+]
+
+[[package]]
+name = "mime"
+version = "0.3.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6877bb514081ee2a7ff5ef9de3281f14a4dd4bceac4c09388074a6b5df8a139a"
+
+[[package]]
+name = "minimal-lexical"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
+
+[[package]]
+name = "mio"
+version = "1.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "50b7e5b27aa02a74bac8c3f23f448f8d87ff11f92d3aac1a6ed369ee08cc56c1"
+dependencies = [
+ "libc",
+ "wasi",
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "native-tls"
+version = "0.2.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "465500e14ea162429d264d44189adc38b199b62b1c21eea9f69e4b73cb03bbf2"
+dependencies = [
+ "libc",
+ "log",
+ "openssl",
+ "openssl-probe",
+ "openssl-sys",
+ "schannel",
+ "security-framework",
+ "security-framework-sys",
+ "tempfile",
+]
+
+[[package]]
+name = "nom"
+version = "7.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d273983c5a657a70a3e8f2a01329822f3b8c8172b73826411a55751e404a0a4a"
+dependencies = [
+ "memchr",
+ "minimal-lexical",
+]
+
+[[package]]
+name = "nu-ansi-term"
+version = "0.50.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7957b9740744892f114936ab4a57b3f487491bbeafaf8083688b16841a4240e5"
+dependencies = [
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "num-traits"
+version = "0.2.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "071dfc062690e90b734c0b2273ce72ad0ffa95f0c74596bc250dcfd960262841"
+dependencies = [
+ "autocfg",
+]
+
+[[package]]
+name = "once_cell"
+version = "1.21.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50"
+
+[[package]]
+name = "once_cell_polyfill"
+version = "1.70.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe"
+
+[[package]]
+name = "openssl"
+version = "0.10.77"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bfe4646e360ec77dff7dde40ed3d6c5fee52d156ef4a62f53973d38294dad87f"
+dependencies = [
+ "bitflags",
+ "cfg-if",
+ "foreign-types",
+ "libc",
+ "once_cell",
+ "openssl-macros",
+ "openssl-sys",
+]
+
+[[package]]
+name = "openssl-macros"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a948666b637a0f465e8564c73e89d4dde00d72d4d473cc972f390fc3dcee7d9c"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "openssl-probe"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7c87def4c32ab89d880effc9e097653c8da5d6ef28e6b539d313baaacfbafcbe"
+
+[[package]]
+name = "openssl-sys"
+version = "0.9.113"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ad2f2c0eba47118757e4c6d2bff2838f3e0523380021356e7875e858372ce644"
+dependencies = [
+ "cc",
+ "libc",
+ "pkg-config",
+ "vcpkg",
+]
+
+[[package]]
+name = "parking_lot"
+version = "0.12.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "93857453250e3077bd71ff98b6a65ea6621a19bb0f559a85248955ac12c45a1a"
+dependencies = [
+ "lock_api",
+ "parking_lot_core",
+]
+
+[[package]]
+name = "parking_lot_core"
+version = "0.9.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2621685985a2ebf1c516881c026032ac7deafcda1a2c9b7850dc81e3dfcb64c1"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "redox_syscall",
+ "smallvec",
+ "windows-link",
+]
+
+[[package]]
+name = "pear"
+version = "0.2.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bdeeaa00ce488657faba8ebf44ab9361f9365a97bd39ffb8a60663f57ff4b467"
+dependencies = [
+ "inlinable_string",
+ "pear_codegen",
+ "yansi",
+]
+
+[[package]]
+name = "pear_codegen"
+version = "0.2.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4bab5b985dc082b345f812b7df84e1bef27e7207b39e448439ba8bd69c93f147"
+dependencies = [
+ "proc-macro2",
+ "proc-macro2-diagnostics",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "percent-encoding"
+version = "2.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9b4f627cb1b25917193a259e49bdad08f671f8d9708acfd5fe0a8c1455d87220"
+
+[[package]]
+name = "pin-project-lite"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a89322df9ebe1c1578d689c92318e070967d1042b512afbe49518723f4e6d5cd"
+
+[[package]]
+name = "pkg-config"
+version = "0.3.33"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "19f132c84eca552bf34cab8ec81f1c1dcc229b811638f9d283dceabe58c5569e"
+
+[[package]]
+name = "portable-atomic"
+version = "1.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c33a9471896f1c69cecef8d20cbe2f7accd12527ce60845ff44c153bb2a21b49"
+
+[[package]]
+name = "potential_utf"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0103b1cef7ec0cf76490e969665504990193874ea05c85ff9bab8b911d0a0564"
+dependencies = [
+ "zerovec",
+]
+
+[[package]]
+name = "ppv-lite86"
+version = "0.2.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85eae3c4ed2f50dcfe72643da4befc30deadb458a9b590d720cde2f2b1e97da9"
+dependencies = [
+ "zerocopy",
+]
+
+[[package]]
+name = "prettyplease"
+version = "0.2.37"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "479ca8adacdd7ce8f1fb39ce9ecccbfe93a3f1344b3d0d97f20bc0196208f62b"
+dependencies = [
+ "proc-macro2",
+ "syn",
+]
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.106"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8fd00f0bb2e90d81d1044c2b32617f68fcb9fa3bb7640c23e9c748e53fb30934"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "proc-macro2-diagnostics"
+version = "0.10.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "af066a9c399a26e020ada66a034357a868728e72cd426f3adcd35f80d88d88c8"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+ "version_check",
+ "yansi",
+]
+
+[[package]]
+name = "quanta"
+version = "0.12.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f3ab5a9d756f0d97bdc89019bd2e4ea098cf9cde50ee7564dde6b81ccc8f06c7"
+dependencies = [
+ "crossbeam-utils",
+ "libc",
+ "once_cell",
+ "raw-cpuid",
+ "wasi",
+ "web-sys",
+ "winapi",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.45"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "41f2619966050689382d2b44f664f4bc593e129785a36d6ee376ddf37259b924"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "r-efi"
+version = "5.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f"
+
+[[package]]
+name = "r-efi"
+version = "6.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f8dcc9c7d52a811697d2151c701e0d08956f92b0e24136cf4cf27b57a6a0d9bf"
+
+[[package]]
+name = "rand"
+version = "0.9.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "44c5af06bb1b7d3216d91932aed5265164bf384dc89cd6ba05cf59a35f5f76ea"
+dependencies = [
+ "rand_chacha",
+ "rand_core",
+]
+
+[[package]]
+name = "rand_chacha"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d3022b5f1df60f26e1ffddd6c66e8aa15de382ae63b3a0c1bfc0e4d3e3f325cb"
+dependencies = [
+ "ppv-lite86",
+ "rand_core",
+]
+
+[[package]]
+name = "rand_core"
+version = "0.9.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "76afc826de14238e6e8c374ddcc1fa19e374fd8dd986b0d2af0d02377261d83c"
+dependencies = [
+ "getrandom 0.3.4",
+]
+
+[[package]]
+name = "rand_xoshiro"
+version = "0.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f703f4665700daf5512dcca5f43afa6af89f09db47fb56be587f80636bda2d41"
+dependencies = [
+ "rand_core",
+]
+
+[[package]]
+name = "raw-cpuid"
+version = "11.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "498cd0dc59d73224351ee52a95fee0f1a617a2eae0e7d9d720cc622c73a54186"
+dependencies = [
+ "bitflags",
+]
+
+[[package]]
+name = "redox_syscall"
+version = "0.5.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ed2bf2547551a7053d6fdfafda3f938979645c44812fbfcda098faae3f1a362d"
+dependencies = [
+ "bitflags",
+]
+
+[[package]]
+name = "regex-automata"
+version = "0.4.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6e1dd4122fc1595e8162618945476892eefca7b88c52820e74af6262213cae8f"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.8.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc897dd8d9e8bd1ed8cdad82b5966c3e0ecae09fb1907d58efaa013543185d0a"
+
+[[package]]
+name = "reqwest"
+version = "0.12.28"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "eddd3ca559203180a307f12d114c268abf583f59b03cb906fd0b3ff8646c1147"
+dependencies = [
+ "base64",
+ "bytes",
+ "encoding_rs",
+ "futures-core",
+ "futures-util",
+ "h2",
+ "http",
+ "http-body",
+ "http-body-util",
+ "hyper",
+ "hyper-rustls",
+ "hyper-tls",
+ "hyper-util",
+ "js-sys",
+ "log",
+ "mime",
+ "native-tls",
+ "percent-encoding",
+ "pin-project-lite",
+ "rustls-pki-types",
+ "serde",
+ "serde_json",
+ "serde_urlencoded",
+ "sync_wrapper",
+ "tokio",
+ "tokio-native-tls",
+ "tokio-util",
+ "tower",
+ "tower-http",
+ "tower-service",
+ "url",
+ "wasm-bindgen",
+ "wasm-bindgen-futures",
+ "wasm-streams",
+ "web-sys",
+]
+
+[[package]]
+name = "ring"
+version = "0.17.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a4689e6c2294d81e88dc6261c768b63bc4fcdb852be6d1352498b114f61383b7"
+dependencies = [
+ "cc",
+ "cfg-if",
+ "getrandom 0.2.17",
+ "libc",
+ "untrusted",
+ "windows-sys 0.52.0",
+]
+
+[[package]]
+name = "rustix"
+version = "1.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6fe4565b9518b83ef4f91bb47ce29620ca828bd32cb7e408f0062e9930ba190"
+dependencies = [
+ "bitflags",
+ "errno",
+ "libc",
+ "linux-raw-sys",
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "rustls"
+version = "0.23.38"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "69f9466fb2c14ea04357e91413efb882e2a6d4a406e625449bc0a5d360d53a21"
+dependencies = [
+ "aws-lc-rs",
+ "once_cell",
+ "rustls-pki-types",
+ "rustls-webpki",
+ "subtle",
+ "zeroize",
+]
+
+[[package]]
+name = "rustls-native-certs"
+version = "0.8.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "612460d5f7bea540c490b2b6395d8e34a953e52b491accd6c86c8164c5932a63"
+dependencies = [
+ "openssl-probe",
+ "rustls-pki-types",
+ "schannel",
+ "security-framework",
+]
+
+[[package]]
+name = "rustls-pki-types"
+version = "1.14.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "be040f8b0a225e40375822a563fa9524378b9d63112f53e19ffff34df5d33fdd"
+dependencies = [
+ "zeroize",
+]
+
+[[package]]
+name = "rustls-webpki"
+version = "0.103.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8279bb85272c9f10811ae6a6c547ff594d6a7f3c6c6b02ee9726d1d0dcfcdd06"
+dependencies = [
+ "aws-lc-rs",
+ "ring",
+ "rustls-pki-types",
+ "untrusted",
+]
+
+[[package]]
+name = "rustversion"
+version = "1.0.22"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b39cdef0fa800fc44525c84ccb54a029961a8215f9619753635a9c0d2538d46d"
+
+[[package]]
+name = "ryu"
+version = "1.0.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9774ba4a74de5f7b1c1451ed6cd5285a32eddb5cccb8cc655a4e50009e06477f"
+
+[[package]]
+name = "schannel"
+version = "0.1.29"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "91c1b7e4904c873ef0710c1f407dde2e6287de2bebc1bbbf7d430bb7cbffd939"
+dependencies = [
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "scopeguard"
+version = "1.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
+
+[[package]]
+name = "security-framework"
+version = "3.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b7f4bc775c73d9a02cde8bf7b2ec4c9d12743edf609006c7facc23998404cd1d"
+dependencies = [
+ "bitflags",
+ "core-foundation 0.10.1",
+ "core-foundation-sys",
+ "libc",
+ "security-framework-sys",
+]
+
+[[package]]
+name = "security-framework-sys"
+version = "2.17.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6ce2691df843ecc5d231c0b14ece2acc3efb62c0a398c7e1d875f3983ce020e3"
+dependencies = [
+ "core-foundation-sys",
+ "libc",
+]
+
+[[package]]
+name = "semver"
+version = "1.0.28"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8a7852d02fc848982e0c167ef163aaff9cd91dc640ba85e263cb1ce46fae51cd"
+
+[[package]]
+name = "serde"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9a8e94ea7f378bd32cbbd37198a4a91436180c5bb472411e48b5ec2e2124ae9e"
+dependencies = [
+ "serde_core",
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_core"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "41d385c7d4ca58e59fc732af25c3983b67ac852c1a25000afe1175de458b67ad"
+dependencies = [
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_derive"
+version = "1.0.228"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d540f220d3187173da220f885ab66608367b6574e925011a9353e4badda91d79"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "serde_json"
+version = "1.0.149"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "83fc039473c5595ace860d8c4fafa220ff474b3fc6bfdb4293327f1a37e94d86"
+dependencies = [
+ "itoa",
+ "memchr",
+ "serde",
+ "serde_core",
+ "zmij",
+]
+
+[[package]]
+name = "serde_path_to_error"
+version = "0.1.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "10a9ff822e371bb5403e391ecd83e182e0e77ba7f6fe0160b795797109d1b457"
+dependencies = [
+ "itoa",
+ "serde",
+ "serde_core",
+]
+
+[[package]]
+name = "serde_spanned"
+version = "0.6.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bf41e0cfaf7226dca15e8197172c295a782857fcb97fad1808a166870dee75a3"
+dependencies = [
+ "serde",
+]
+
+[[package]]
+name = "serde_urlencoded"
+version = "0.7.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d3491c14715ca2294c4d6a88f15e84739788c1d030eed8c110436aafdaa2f3fd"
+dependencies = [
+ "form_urlencoded",
+ "itoa",
+ "ryu",
+ "serde",
+]
+
+[[package]]
+name = "sharded-slab"
+version = "0.1.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f40ca3c46823713e0d4209592e8d6e826aa57e928f09752619fc696c499637f6"
+dependencies = [
+ "lazy_static",
+]
+
+[[package]]
+name = "shlex"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
+
+[[package]]
+name = "signal-hook-registry"
+version = "1.4.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c4db69cba1110affc0e9f7bcd48bbf87b3f4fc7c61fc9155afd4c469eb3d6c1b"
+dependencies = [
+ "errno",
+ "libc",
+]
+
+[[package]]
+name = "sketches-ddsketch"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0c6f73aeb92d671e0cc4dca167e59b2deb6387c375391bc99ee743f326994a2b"
+
+[[package]]
+name = "slab"
+version = "0.4.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0c790de23124f9ab44544d7ac05d60440adc586479ce501c1d6d7da3cd8c9cf5"
+
+[[package]]
+name = "smallvec"
+version = "1.15.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "67b1b7a3b5fe4f1376887184045fcf45c69e92af734b7aaddc05fb777b6fbd03"
+
+[[package]]
+name = "socket2"
+version = "0.6.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3a766e1110788c36f4fa1c2b71b387a7815aa65f88ce0229841826633d93723e"
+dependencies = [
+ "libc",
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "stable_deref_trait"
+version = "1.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6ce2be8dc25455e1f91df71bfa12ad37d7af1092ae736f3a6cd0e37bc7810596"
+
+[[package]]
+name = "strsim"
+version = "0.11.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f"
+
+[[package]]
+name = "subtle"
+version = "2.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "13c2bddecc57b384dee18652358fb23172facb8a2c51ccc10d74c157bdea3292"
+
+[[package]]
+name = "syn"
+version = "2.0.117"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e665b8803e7b1d2a727f4023456bbbbe74da67099c585258af0ad9c5013b9b99"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "sync_wrapper"
+version = "1.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0bf256ce5efdfa370213c1dabab5935a12e49f2c58d15e9eac2870d3b4f27263"
+dependencies = [
+ "futures-core",
+]
+
+[[package]]
+name = "synstructure"
+version = "0.13.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "728a70f3dbaf5bab7f0c4b1ac8d7ae5ea60a4b5549c8a5914361c99147a709d2"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "system-configuration"
+version = "0.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a13f3d0daba03132c0aa9767f98351b3488edc2c100cda2d2ec2b04f3d8d3c8b"
+dependencies = [
+ "bitflags",
+ "core-foundation 0.9.4",
+ "system-configuration-sys",
+]
+
+[[package]]
+name = "system-configuration-sys"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e1d1b10ced5ca923a1fcb8d03e96b8d3268065d724548c0211415ff6ac6bac4"
+dependencies = [
+ "core-foundation-sys",
+ "libc",
+]
+
+[[package]]
+name = "tempfile"
+version = "3.27.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32497e9a4c7b38532efcdebeef879707aa9f794296a4f0244f6f69e9bc8574bd"
+dependencies = [
+ "fastrand",
+ "getrandom 0.4.2",
+ "once_cell",
+ "rustix",
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "thiserror"
+version = "1.0.69"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6aaf5339b578ea85b50e080feb250a3e8ae8cfcdff9a461c9ec2904bc923f52"
+dependencies = [
+ "thiserror-impl 1.0.69",
+]
+
+[[package]]
+name = "thiserror"
+version = "2.0.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4288b5bcbc7920c07a1149a35cf9590a2aa808e0bc1eafaade0b80947865fbc4"
+dependencies = [
+ "thiserror-impl 2.0.18",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "1.0.69"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4fee6c4efc90059e10f81e6d42c60a18f76588c3d74cb83a0b242a2b6c7504c1"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "2.0.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ebc4ee7f67670e9b64d05fa4253e753e016c6c95ff35b89b7941d6b856dec1d5"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "thread_local"
+version = "1.1.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f60246a4944f24f6e018aa17cdeffb7818b76356965d03b07d6a9886e8962185"
+dependencies = [
+ "cfg-if",
+]
+
+[[package]]
+name = "tinystr"
+version = "0.8.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c8323304221c2a851516f22236c5722a72eaa19749016521d6dff0824447d96d"
+dependencies = [
+ "displaydoc",
+ "zerovec",
+]
+
+[[package]]
+name = "tokio"
+version = "1.51.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f66bf9585cda4b724d3e78ab34b73fb2bbaba9011b9bfdf69dc836382ea13b8c"
+dependencies = [
+ "bytes",
+ "libc",
+ "mio",
+ "parking_lot",
+ "pin-project-lite",
+ "signal-hook-registry",
+ "socket2",
+ "tokio-macros",
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "tokio-macros"
+version = "2.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "385a6cb71ab9ab790c5fe8d67f1645e6c450a7ce006a33de03daa956cf70a496"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "tokio-native-tls"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bbae76ab933c85776efabc971569dd6119c580d8f5d448769dec1764bf796ef2"
+dependencies = [
+ "native-tls",
+ "tokio",
+]
+
+[[package]]
+name = "tokio-rustls"
+version = "0.26.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1729aa945f29d91ba541258c8df89027d5792d85a8841fb65e8bf0f4ede4ef61"
+dependencies = [
+ "rustls",
+ "tokio",
+]
+
+[[package]]
+name = "tokio-stream"
+version = "0.1.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32da49809aab5c3bc678af03902d4ccddea2a87d028d86392a4b1560c6906c70"
+dependencies = [
+ "futures-core",
+ "pin-project-lite",
+ "tokio",
+]
+
+[[package]]
+name = "tokio-util"
+version = "0.7.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9ae9cec805b01e8fc3fd2fe289f89149a9b66dd16786abd8b19cfa7b48cb0098"
+dependencies = [
+ "bytes",
+ "futures-core",
+ "futures-sink",
+ "pin-project-lite",
+ "tokio",
+]
+
+[[package]]
+name = "toml"
+version = "0.8.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc1beb996b9d83529a9e75c17a1686767d148d70663143c7854d8b4a09ced362"
+dependencies = [
+ "serde",
+ "serde_spanned",
+ "toml_datetime",
+ "toml_edit",
+]
+
+[[package]]
+name = "toml_datetime"
+version = "0.6.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "22cddaf88f4fbc13c51aebbf5f8eceb5c7c5a9da2ac40a13519eb5b0a0e8f11c"
+dependencies = [
+ "serde",
+]
+
+[[package]]
+name = "toml_edit"
+version = "0.22.27"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "41fe8c660ae4257887cf66394862d21dbca4a6ddd26f04a3560410406a2f819a"
+dependencies = [
+ "indexmap",
+ "serde",
+ "serde_spanned",
+ "toml_datetime",
+ "toml_write",
+ "winnow",
+]
+
+[[package]]
+name = "toml_write"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5d99f8c9a7727884afe522e9bd5edbfc91a3312b36a77b5fb8926e4c31a41801"
+
+[[package]]
+name = "tower"
+version = "0.5.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ebe5ef63511595f1344e2d5cfa636d973292adc0eec1f0ad45fae9f0851ab1d4"
+dependencies = [
+ "futures-core",
+ "futures-util",
+ "pin-project-lite",
+ "sync_wrapper",
+ "tokio",
+ "tower-layer",
+ "tower-service",
+ "tracing",
+]
+
+[[package]]
+name = "tower-http"
+version = "0.6.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d4e6559d53cc268e5031cd8429d05415bc4cb4aefc4aa5d6cc35fbf5b924a1f8"
+dependencies = [
+ "bitflags",
+ "bytes",
+ "futures-util",
+ "http",
+ "http-body",
+ "iri-string",
+ "pin-project-lite",
+ "tokio",
+ "tower",
+ "tower-layer",
+ "tower-service",
+ "tracing",
+]
+
+[[package]]
+name = "tower-layer"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "121c2a6cda46980bb0fcd1647ffaf6cd3fc79a013de288782836f6df9c48780e"
+
+[[package]]
+name = "tower-service"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8df9b6e13f2d32c91b9bd719c00d1958837bc7dec474d94952798cc8e69eeec3"
+
+[[package]]
+name = "tracing"
+version = "0.1.44"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "63e71662fa4b2a2c3a26f570f037eb95bb1f85397f3cd8076caed2f026a6d100"
+dependencies = [
+ "log",
+ "pin-project-lite",
+ "tracing-attributes",
+ "tracing-core",
+]
+
+[[package]]
+name = "tracing-attributes"
+version = "0.1.31"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7490cfa5ec963746568740651ac6781f701c9c5ea257c58e057f3ba8cf69e8da"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "tracing-core"
+version = "0.1.36"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "db97caf9d906fbde555dd62fa95ddba9eecfd14cb388e4f491a66d74cd5fb79a"
+dependencies = [
+ "once_cell",
+ "valuable",
+]
+
+[[package]]
+name = "tracing-log"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ee855f1f400bd0e5c02d150ae5de3840039a3f54b025156404e34c23c03f47c3"
+dependencies = [
+ "log",
+ "once_cell",
+ "tracing-core",
+]
+
+[[package]]
+name = "tracing-serde"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "704b1aeb7be0d0a84fc9828cae51dab5970fee5088f83d1dd7ee6f6246fc6ff1"
+dependencies = [
+ "serde",
+ "tracing-core",
+]
+
+[[package]]
+name = "tracing-subscriber"
+version = "0.3.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cb7f578e5945fb242538965c2d0b04418d38ec25c79d160cd279bf0731c8d319"
+dependencies = [
+ "matchers",
+ "nu-ansi-term",
+ "once_cell",
+ "regex-automata",
+ "serde",
+ "serde_json",
+ "sharded-slab",
+ "smallvec",
+ "thread_local",
+ "tracing",
+ "tracing-core",
+ "tracing-log",
+ "tracing-serde",
+]
+
+[[package]]
+name = "try-lock"
+version = "0.2.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e421abadd41a4225275504ea4d6566923418b7f05506fbc9c0fe86ba7396114b"
+
+[[package]]
+name = "uncased"
+version = "0.9.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e1b88fcfe09e89d3866a5c11019378088af2d24c3fbd4f0543f96b479ec90697"
+dependencies = [
+ "version_check",
+]
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
+
+[[package]]
+name = "unicode-xid"
+version = "0.2.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ebc1c04c71510c7f702b52b7c350734c9ff1295c464a03335b00bb84fc54f853"
+
+[[package]]
+name = "untrusted"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8ecb6da28b8a351d773b68d5825ac39017e680750f980f3a1a85cd8dd28a47c1"
+
+[[package]]
+name = "url"
+version = "2.5.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ff67a8a4397373c3ef660812acab3268222035010ab8680ec4215f38ba3d0eed"
+dependencies = [
+ "form_urlencoded",
+ "idna",
+ "percent-encoding",
+ "serde",
+]
+
+[[package]]
+name = "utf8_iter"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be"
+
+[[package]]
+name = "utf8parse"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
+
+[[package]]
+name = "valuable"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba73ea9cf16a25df0c8caa16c51acb937d5712a8429db78a3ee29d5dcacd3a65"
+
+[[package]]
+name = "vcpkg"
+version = "0.2.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "accd4ea62f7bb7a82fe23066fb0957d48ef677f6eeb8215f372f52e48bb32426"
+
+[[package]]
+name = "version_check"
+version = "0.9.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
+
+[[package]]
+name = "want"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bfa7760aed19e106de2c7c0b581b509f2f25d3dacaf737cb82ac61bc6d760b0e"
+dependencies = [
+ "try-lock",
+]
+
+[[package]]
+name = "wasi"
+version = "0.11.1+wasi-snapshot-preview1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ccf3ec651a847eb01de73ccad15eb7d99f80485de043efb2f370cd654f4ea44b"
+
+[[package]]
+name = "wasip2"
+version = "1.0.2+wasi-0.2.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9517f9239f02c069db75e65f174b3da828fe5f5b945c4dd26bd25d89c03ebcf5"
+dependencies = [
+ "wit-bindgen",
+]
+
+[[package]]
+name = "wasip3"
+version = "0.4.0+wasi-0.3.0-rc-2026-01-06"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5428f8bf88ea5ddc08faddef2ac4a67e390b88186c703ce6dbd955e1c145aca5"
+dependencies = [
+ "wit-bindgen",
+]
+
+[[package]]
+name = "wasm-bindgen"
+version = "0.2.118"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0bf938a0bacb0469e83c1e148908bd7d5a6010354cf4fb73279b7447422e3a89"
+dependencies = [
+ "cfg-if",
+ "once_cell",
+ "rustversion",
+ "wasm-bindgen-macro",
+ "wasm-bindgen-shared",
+]
+
+[[package]]
+name = "wasm-bindgen-futures"
+version = "0.4.68"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f371d383f2fb139252e0bfac3b81b265689bf45b6874af544ffa4c975ac1ebf8"
+dependencies = [
+ "js-sys",
+ "wasm-bindgen",
+]
+
+[[package]]
+name = "wasm-bindgen-macro"
+version = "0.2.118"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "eeff24f84126c0ec2db7a449f0c2ec963c6a49efe0698c4242929da037ca28ed"
+dependencies = [
+ "quote",
+ "wasm-bindgen-macro-support",
+]
+
+[[package]]
+name = "wasm-bindgen-macro-support"
+version = "0.2.118"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9d08065faf983b2b80a79fd87d8254c409281cf7de75fc4b773019824196c904"
+dependencies = [
+ "bumpalo",
+ "proc-macro2",
+ "quote",
+ "syn",
+ "wasm-bindgen-shared",
+]
+
+[[package]]
+name = "wasm-bindgen-shared"
+version = "0.2.118"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5fd04d9e306f1907bd13c6361b5c6bfc7b3b3c095ed3f8a9246390f8dbdee129"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "wasm-encoder"
+version = "0.244.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "990065f2fe63003fe337b932cfb5e3b80e0b4d0f5ff650e6985b1048f62c8319"
+dependencies = [
+ "leb128fmt",
+ "wasmparser",
+]
+
+[[package]]
+name = "wasm-metadata"
+version = "0.244.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bb0e353e6a2fbdc176932bbaab493762eb1255a7900fe0fea1a2f96c296cc909"
+dependencies = [
+ "anyhow",
+ "indexmap",
+ "wasm-encoder",
+ "wasmparser",
+]
+
+[[package]]
+name = "wasm-streams"
+version = "0.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "15053d8d85c7eccdbefef60f06769760a563c7f0a9d6902a13d35c7800b0ad65"
+dependencies = [
+ "futures-util",
+ "js-sys",
+ "wasm-bindgen",
+ "wasm-bindgen-futures",
+ "web-sys",
+]
+
+[[package]]
+name = "wasmparser"
+version = "0.244.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "47b807c72e1bac69382b3a6fb3dbe8ea4c0ed87ff5629b8685ae6b9a611028fe"
+dependencies = [
+ "bitflags",
+ "hashbrown 0.15.5",
+ "indexmap",
+ "semver",
+]
+
+[[package]]
+name = "web-sys"
+version = "0.3.95"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4f2dfbb17949fa2088e5d39408c48368947b86f7834484e87b73de55bc14d97d"
+dependencies = [
+ "js-sys",
+ "wasm-bindgen",
+]
+
+[[package]]
+name = "winapi"
+version = "0.3.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
+dependencies = [
+ "winapi-i686-pc-windows-gnu",
+ "winapi-x86_64-pc-windows-gnu",
+]
+
+[[package]]
+name = "winapi-i686-pc-windows-gnu"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
+
+[[package]]
+name = "winapi-x86_64-pc-windows-gnu"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
+
+[[package]]
+name = "windows-core"
+version = "0.62.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b8e83a14d34d0623b51dce9581199302a221863196a1dde71a7663a4c2be9deb"
+dependencies = [
+ "windows-implement",
+ "windows-interface",
+ "windows-link",
+ "windows-result",
+ "windows-strings",
+]
+
+[[package]]
+name = "windows-implement"
+version = "0.60.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "053e2e040ab57b9dc951b72c264860db7eb3b0200ba345b4e4c3b14f67855ddf"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "windows-interface"
+version = "0.59.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f316c4a2570ba26bbec722032c4099d8c8bc095efccdc15688708623367e358"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "windows-link"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
+
+[[package]]
+name = "windows-registry"
+version = "0.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "02752bf7fbdcce7f2a27a742f798510f3e5ad88dbe84871e5168e2120c3d5720"
+dependencies = [
+ "windows-link",
+ "windows-result",
+ "windows-strings",
+]
+
+[[package]]
+name = "windows-result"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7781fa89eaf60850ac3d2da7af8e5242a5ea78d1a11c49bf2910bb5a73853eb5"
+dependencies = [
+ "windows-link",
+]
+
+[[package]]
+name = "windows-strings"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7837d08f69c77cf6b07689544538e017c1bfcf57e34b4c0ff58e6c2cd3b37091"
+dependencies = [
+ "windows-link",
+]
+
+[[package]]
+name = "windows-sys"
+version = "0.52.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
+dependencies = [
+ "windows-targets",
+]
+
+[[package]]
+name = "windows-sys"
+version = "0.61.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ae137229bcbd6cdf0f7b80a31df61766145077ddf49416a728b02cb3921ff3fc"
+dependencies = [
+ "windows-link",
+]
+
+[[package]]
+name = "windows-targets"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
+dependencies = [
+ "windows_aarch64_gnullvm",
+ "windows_aarch64_msvc",
+ "windows_i686_gnu",
+ "windows_i686_gnullvm",
+ "windows_i686_msvc",
+ "windows_x86_64_gnu",
+ "windows_x86_64_gnullvm",
+ "windows_x86_64_msvc",
+]
+
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
+
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
+
+[[package]]
+name = "windows_i686_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b"
+
+[[package]]
+name = "windows_i686_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
+
+[[package]]
+name = "windows_i686_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
+
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
+
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
+
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
+
+[[package]]
+name = "winnow"
+version = "0.7.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "df79d97927682d2fd8adb29682d1140b343be4ac0f08fd68b7765d9c059d3945"
+dependencies = [
+ "memchr",
+]
+
+[[package]]
+name = "wit-bindgen"
+version = "0.51.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d7249219f66ced02969388cf2bb044a09756a083d0fab1e566056b04d9fbcaa5"
+dependencies = [
+ "wit-bindgen-rust-macro",
+]
+
+[[package]]
+name = "wit-bindgen-core"
+version = "0.51.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ea61de684c3ea68cb082b7a88508a8b27fcc8b797d738bfc99a82facf1d752dc"
+dependencies = [
+ "anyhow",
+ "heck",
+ "wit-parser",
+]
+
+[[package]]
+name = "wit-bindgen-rust"
+version = "0.51.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b7c566e0f4b284dd6561c786d9cb0142da491f46a9fbed79ea69cdad5db17f21"
+dependencies = [
+ "anyhow",
+ "heck",
+ "indexmap",
+ "prettyplease",
+ "syn",
+ "wasm-metadata",
+ "wit-bindgen-core",
+ "wit-component",
+]
+
+[[package]]
+name = "wit-bindgen-rust-macro"
+version = "0.51.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0c0f9bfd77e6a48eccf51359e3ae77140a7f50b1e2ebfe62422d8afdaffab17a"
+dependencies = [
+ "anyhow",
+ "prettyplease",
+ "proc-macro2",
+ "quote",
+ "syn",
+ "wit-bindgen-core",
+ "wit-bindgen-rust",
+]
+
+[[package]]
+name = "wit-component"
+version = "0.244.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9d66ea20e9553b30172b5e831994e35fbde2d165325bec84fc43dbf6f4eb9cb2"
+dependencies = [
+ "anyhow",
+ "bitflags",
+ "indexmap",
+ "log",
+ "serde",
+ "serde_derive",
+ "serde_json",
+ "wasm-encoder",
+ "wasm-metadata",
+ "wasmparser",
+ "wit-parser",
+]
+
+[[package]]
+name = "wit-parser"
+version = "0.244.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ecc8ac4bc1dc3381b7f59c34f00b67e18f910c2c0f50015669dde7def656a736"
+dependencies = [
+ "anyhow",
+ "id-arena",
+ "indexmap",
+ "log",
+ "semver",
+ "serde",
+ "serde_derive",
+ "serde_json",
+ "unicode-xid",
+ "wasmparser",
+]
+
+[[package]]
+name = "writeable"
+version = "0.6.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1ffae5123b2d3fc086436f8834ae3ab053a283cfac8fe0a0b8eaae044768a4c4"
+
+[[package]]
+name = "yansi"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cfe53a6657fd280eaa890a3bc59152892ffa3e30101319d168b781ed6529b049"
+
+[[package]]
+name = "yoke"
+version = "0.8.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "abe8c5fda708d9ca3df187cae8bfb9ceda00dd96231bed36e445a1a48e66f9ca"
+dependencies = [
+ "stable_deref_trait",
+ "yoke-derive",
+ "zerofrom",
+]
+
+[[package]]
+name = "yoke-derive"
+version = "0.8.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "de844c262c8848816172cef550288e7dc6c7b7814b4ee56b3e1553f275f1858e"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+ "synstructure",
+]
+
+[[package]]
+name = "zerocopy"
+version = "0.8.48"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "eed437bf9d6692032087e337407a86f04cd8d6a16a37199ed57949d415bd68e9"
+dependencies = [
+ "zerocopy-derive",
+]
+
+[[package]]
+name = "zerocopy-derive"
+version = "0.8.48"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "70e3cd084b1788766f53af483dd21f93881ff30d7320490ec3ef7526d203bad4"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "zerofrom"
+version = "0.1.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "69faa1f2a1ea75661980b013019ed6687ed0e83d069bc1114e2cc74c6c04c4df"
+dependencies = [
+ "zerofrom-derive",
+]
+
+[[package]]
+name = "zerofrom-derive"
+version = "0.1.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "11532158c46691caf0f2593ea8358fed6bbf68a0315e80aae9bd41fbade684a1"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+ "synstructure",
+]
+
+[[package]]
+name = "zeroize"
+version = "1.8.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b97154e67e32c85465826e8bcc1c59429aaaf107c1e4a9e53c8d8ccd5eff88d0"
+
+[[package]]
+name = "zerotrie"
+version = "0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0f9152d31db0792fa83f70fb2f83148effb5c1f5b8c7686c3459e361d9bc20bf"
+dependencies = [
+ "displaydoc",
+ "yoke",
+ "zerofrom",
+]
+
+[[package]]
+name = "zerovec"
+version = "0.11.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "90f911cbc359ab6af17377d242225f4d75119aec87ea711a880987b18cd7b239"
+dependencies = [
+ "yoke",
+ "zerofrom",
+ "zerovec-derive",
+]
+
+[[package]]
+name = "zerovec-derive"
+version = "0.11.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "625dc425cab0dca6dc3c3319506e6593dcb08a9f387ea3b284dbd52a92c40555"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "zmij"
+version = "1.0.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b8848ee67ecc8aedbaf3e4122217aff892639231befc6a1b58d29fff4c2cabaa"
diff --git a/Cargo.toml b/Cargo.toml
new file mode 100644
index 0000000..142df11
--- /dev/null
+++ b/Cargo.toml
@@ -0,0 +1,57 @@
+[workspace]
+resolver = "2"
+members = [
+    "crates/cortex-core",
+    "crates/cortex-gateway",
+    "crates/cortex-agent",
+    "crates/cortex-cli",
+]
+
+[workspace.package]
+version = "0.1.0"
+edition = "2024"
+license = "GPL-3.0"
+repository = "https://git.lair.cafe/helexa/cortex"
+
+[workspace.dependencies]
+# async runtime
+tokio = { version = "1", features = ["full"] }
+
+# web framework
+axum = { version = "0.8", features = ["macros"] }
+tower = "0.5"
+tower-http = { version = "0.6", features = ["cors", "trace", "timeout"] }
+
+# serialization
+serde = { version = "1", features = ["derive"] }
+serde_json = "1"
+toml = "0.8"
+
+# http client (for proxying to mistralrs backends)
+reqwest = { version = "0.12", features = ["json", "stream"] }
+
+# observability
+tracing = "0.1"
+tracing-subscriber = { version = "0.3", features = ["env-filter", "json"] }
+metrics = "0.24"
+metrics-exporter-prometheus = "0.16"
+
+# time
+chrono = { version = "0.4", features = ["serde"] }
+
+# config
+figment = { version = "0.10", features = ["toml", "env"] }
+
+# error handling
+anyhow = "1"
+thiserror = "2"
+
+# futures / streams (for SSE proxying)
+futures = "0.3"
+tokio-stream = "0.1"
+eventsource-stream = "0.2"
+
+# workspace crates
+cortex-core = { path = "crates/cortex-core" }
+cortex-gateway = { path = "crates/cortex-gateway" }
+cortex-agent = { path = "crates/cortex-agent" }
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..b8d0d61
--- /dev/null
+++ b/README.md
@@ -0,0 +1,138 @@
+# cortex
+
+A Rust reverse-proxy and fleet management layer for multi-node
+[mistral.rs](https://github.com/EricLBuehler/mistral.rs) inference clusters.
+
+## Problem
+
+Running local LLMs across multiple GPU nodes (different VRAM tiers, different
+model affinities) requires a unified API surface that:
+
+- Presents a **single `/v1/models` catalogue** merging every model across every
+  node.
+- **Routes requests** to the correct node based on where a model is loaded (or
+  *can* be loaded).
+- Manages **model lifecycle** — unload cold models, reload on demand, pin
+  critical ones — using the mistral.rs
+  `/v1/models/{unload,reload,status}` HTTP API (PR #1828+).
+- Translates between **OpenAI and Anthropic** request/response envelopes so
+  every client in the homelab speaks whichever dialect it prefers.
+- Captures **per-request metrics** (tokens, tok/s, TTFT, latency) and exposes
+  them as Prometheus counters/histograms.
+
+## Architecture
+
+```
+┌──────────────┐  ┌──────────┐  ┌────────────┐  ┌────────────┐
+│ Claude Code  │  │ Zed/IDE  │  │ Tidal / mm │  │ curl / etc │
+└──────┬───────┘  └─────┬────┘  └──────┬─────┘  └──────┬─────┘
+       │                │              │               │
+       └────────────────┴──────┬───────┴───────────────┘
+                               │
+                    ┌──────────▼──────────┐
+                    │   cortex     │
+                    │   (cortex-gateway)      │
+                    │                     │
+                    │  Router · Metrics   │
+                    │  Evictor · Translate│
+                    └──┬──────┬────────┬──┘
+                       │      │        │
+            ┌──────────▼┐  ┌──▼─────┐  ┌▼──────────┐
+            │ gpu-large │  │gpu-med │  │ gpu-small │
+            │ mistralrs │  │mistral │  │ mistralrs │
+            │ serve     │  │rs serve│  │ serve     │
+            │ :8080     │  │ :8080  │  │  :8080    │
+            └───────────┘  └────────┘  └───────────┘
+                  private network (.internal)
+```
+
+### Crates
+
+| Crate | Purpose |
+|---|---|
+| `cortex-core` | Shared types: config, node/model state, metrics, OpenAI/Anthropic request/response envelopes |
+| `cortex-gateway` | Axum HTTP server: proxy, router, evictor, metrics exporter |
+| `cortex-agent` | Per-node sidecar: polls local mistralrs, reports to gateway, handles restart/defrag |
+| `cortex-cli` | CLI entrypoint (`cortex serve`, `cortex status`, etc.) |
+
+## Node setup
+
+Each GPU node runs `mistralrs serve` with a multi-model config. Models are
+declared but start **unloaded** — mistral.rs lazy-loads on first request and
+the gateway can explicitly unload/reload via the HTTP API.
+
+Example node systemd unit:
+
+```ini
+# /etc/systemd/system/mistralrs.service
+[Unit]
+Description=mistral.rs inference server
+After=network-online.target
+Wants=network-online.target
+
+[Service]
+Type=simple
+ExecStart=/usr/local/bin/mistralrs serve \
+    --from-config /etc/mistralrs/config.toml \
+    --port 8080
+Restart=on-failure
+RestartSec=5
+Environment=CUDA_VISIBLE_DEVICES=0,1
+
+[Install]
+WantedBy=multi-user.target
+```
+
+## Gateway config
+
+```toml
+# cortex.toml
+[gateway]
+listen = "0.0.0.0:8000"
+metrics_listen = "0.0.0.0:9100"
+
+[eviction]
+strategy = "lru"        # lru | priority
+defrag_after_cycles = 50
+
+[[nodes]]
+name = "gpu-large"
+endpoint = "http://gpu-large.internal:8080"
+vram_mb = 49_152        # e.g. 2x RTX 4090
+pinned = ["your-org/large-model"]
+
+[[nodes]]
+name = "gpu-medium"
+endpoint = "http://gpu-medium.internal:8080"
+vram_mb = 24_576        # e.g. RTX 4090
+pinned = ["your-org/medium-model"]
+
+[[nodes]]
+name = "gpu-small"
+endpoint = "http://gpu-small.internal:8080"
+vram_mb = 12_288        # e.g. RTX 3060
+pinned = ["your-org/embedding-model"]
+```
+
+## Building
+
+```sh
+cargo build --release
+```
+
+## Running
+
+```sh
+# start the gateway
+cortex serve --config cortex.toml
+
+# check fleet status
+cortex status
+
+# list all models across nodes
+curl http://localhost:8000/v1/models
+```
+
+## License
+
+GPL-3.0
diff --git a/cortex.example.toml b/cortex.example.toml
new file mode 100644
index 0000000..60a1e68
--- /dev/null
+++ b/cortex.example.toml
@@ -0,0 +1,45 @@
+# cortex.example.toml — example configuration
+#
+# Copy to cortex.toml and adjust for your environment.
+#
+# Environment variable overrides use CORTEX_ prefix with __ separators:
+#   CORTEX_GATEWAY__LISTEN=0.0.0.0:9000
+
+[gateway]
+listen = "0.0.0.0:8000"
+metrics_listen = "0.0.0.0:9100"
+
+[eviction]
+strategy = "lru"
+# Restart mistralrs after this many load/unload cycles to defragment VRAM.
+# Set to 0 to disable.
+defrag_after_cycles = 50
+
+# -- Nodes ---------------------------------------------------------------
+# Each [[nodes]] entry declares a mistral.rs instance in the fleet.
+# Models are discovered by polling the node's /v1/models endpoint.
+# Pinned models are never evicted.
+
+[[nodes]]
+name = "gpu-large"
+endpoint = "http://gpu-large.internal:8080"
+vram_mb = 49152           # e.g. 2x RTX 4090 (48 GB combined)
+pinned = [
+    "your-org/large-model",
+]
+
+[[nodes]]
+name = "gpu-medium"
+endpoint = "http://gpu-medium.internal:8080"
+vram_mb = 24576           # e.g. RTX 4090 (24 GB)
+pinned = [
+    "your-org/medium-model",
+]
+
+[[nodes]]
+name = "gpu-small"
+endpoint = "http://gpu-small.internal:8080"
+vram_mb = 12288           # e.g. RTX 3060 (12 GB)
+pinned = [
+    "your-org/embedding-model",
+]
diff --git a/crates/cortex-agent/Cargo.toml b/crates/cortex-agent/Cargo.toml
new file mode 100644
index 0000000..515ec8a
--- /dev/null
+++ b/crates/cortex-agent/Cargo.toml
@@ -0,0 +1,14 @@
+[package]
+name = "cortex-agent"
+version.workspace = true
+edition.workspace = true
+license.workspace = true
+
+[dependencies]
+cortex-core.workspace = true
+tokio.workspace = true
+serde.workspace = true
+serde_json.workspace = true
+reqwest.workspace = true
+tracing.workspace = true
+anyhow.workspace = true
diff --git a/crates/cortex-agent/src/agent.rs b/crates/cortex-agent/src/agent.rs
new file mode 100644
index 0000000..7336984
--- /dev/null
+++ b/crates/cortex-agent/src/agent.rs
@@ -0,0 +1,72 @@
+//! Per-node agent sidecar.
+//!
+//! This is a future component that runs on each GPU node alongside mistralrs.
+//! It handles:
+//!   - VRAM defragmentation (restarting the mistralrs systemd unit when the
+//!     gateway signals that lifecycle_cycles has exceeded the threshold)
+//!   - Local nvidia-smi polling for actual VRAM usage reporting
+//!   - Systemd unit management for mistralrs process restarts
+//!
+//! For now this is a stub. The gateway's poller + evictor handle the critical
+//! path (model lifecycle via the mistralrs HTTP API). The agent adds
+//! operational niceties that can be built incrementally.
+
+/// Placeholder for agent configuration.
+#[derive(Debug, Clone)]
+pub struct AgentConfig {
+    /// The local mistralrs endpoint to monitor.
+    pub mistralrs_endpoint: String,
+    /// The systemd unit name for mistralrs (e.g. "mistralrs.service").
+    pub systemd_unit: String,
+}
+
+/// Restart the local mistralrs process via systemd.
+/// This is the nuclear option for VRAM defragmentation.
+pub async fn restart_mistralrs(config: &AgentConfig) -> anyhow::Result<()> {
+    tracing::warn!(
+        unit = %config.systemd_unit,
+        "restarting mistralrs for VRAM defragmentation"
+    );
+
+    let output = tokio::process::Command::new("systemctl")
+        .args(["restart", &config.systemd_unit])
+        .output()
+        .await?;
+
+    if output.status.success() {
+        tracing::info!(unit = %config.systemd_unit, "mistralrs restarted successfully");
+        Ok(())
+    } else {
+        let stderr = String::from_utf8_lossy(&output.stderr);
+        anyhow::bail!("systemctl restart failed: {stderr}");
+    }
+}
+
+/// Query nvidia-smi for current VRAM usage on this node.
+/// Returns (used_mb, total_mb) for each GPU.
+pub async fn query_vram() -> anyhow::Result<Vec<(u64, u64)>> {
+    let output = tokio::process::Command::new("nvidia-smi")
+        .args([
+            "--query-gpu=memory.used,memory.total",
+            "--format=csv,noheader,nounits",
+        ])
+        .output()
+        .await?;
+
+    if !output.status.success() {
+        let stderr = String::from_utf8_lossy(&output.stderr);
+        anyhow::bail!("nvidia-smi failed: {stderr}");
+    }
+
+    let stdout = String::from_utf8_lossy(&output.stdout);
+    let mut gpus = Vec::new();
+    for line in stdout.lines() {
+        let parts: Vec<&str> = line.split(',').map(|s| s.trim()).collect();
+        if parts.len() == 2 {
+            let used: u64 = parts[0].parse().unwrap_or(0);
+            let total: u64 = parts[1].parse().unwrap_or(0);
+            gpus.push((used, total));
+        }
+    }
+    Ok(gpus)
+}
diff --git a/crates/cortex-agent/src/lib.rs b/crates/cortex-agent/src/lib.rs
new file mode 100644
index 0000000..f17bc55
--- /dev/null
+++ b/crates/cortex-agent/src/lib.rs
@@ -0,0 +1 @@
+pub mod agent;
diff --git a/crates/cortex-cli/Cargo.toml b/crates/cortex-cli/Cargo.toml
new file mode 100644
index 0000000..894af75
--- /dev/null
+++ b/crates/cortex-cli/Cargo.toml
@@ -0,0 +1,20 @@
+[package]
+name = "cortex-cli"
+version.workspace = true
+edition.workspace = true
+license.workspace = true
+
+[[bin]]
+name = "cortex"
+path = "src/main.rs"
+
+[dependencies]
+cortex-core.workspace = true
+cortex-gateway.workspace = true
+tokio.workspace = true
+tracing.workspace = true
+tracing-subscriber.workspace = true
+anyhow.workspace = true
+reqwest.workspace = true
+serde_json.workspace = true
+clap = { version = "4", features = ["derive"] }
diff --git a/crates/cortex-cli/src/main.rs b/crates/cortex-cli/src/main.rs
new file mode 100644
index 0000000..3ae7a2b
--- /dev/null
+++ b/crates/cortex-cli/src/main.rs
@@ -0,0 +1,112 @@
+use anyhow::Result;
+use clap::{Parser, Subcommand};
+use cortex_core::config::GatewayConfig;
+use tracing_subscriber::EnvFilter;
+
+#[derive(Parser)]
+#[command(name = "cortex")]
+#[command(about = "Unified inference gateway for multi-node mistral.rs clusters")]
+#[command(version)]
+struct Cli {
+    #[command(subcommand)]
+    command: Commands,
+}
+
+#[derive(Subcommand)]
+enum Commands {
+    /// Start the gateway server.
+    Serve {
+        /// Path to the gateway config file.
+        #[arg(short, long, default_value = "cortex.toml")]
+        config: String,
+    },
+    /// Print the fleet status (models, nodes, health).
+    Status {
+        /// Gateway API endpoint to query.
+        #[arg(short, long, default_value = "http://localhost:8000")]
+        endpoint: String,
+    },
+}
+
+#[tokio::main]
+async fn main() -> Result<()> {
+    // Initialize tracing with env filter (e.g. RUST_LOG=cortex_gateway=debug).
+    tracing_subscriber::fmt()
+        .with_env_filter(
+            EnvFilter::try_from_default_env()
+                .unwrap_or_else(|_| EnvFilter::new("info,cortex_gateway=debug")),
+        )
+        .init();
+
+    let cli = Cli::parse();
+
+    match cli.command {
+        Commands::Serve { config } => {
+            let cfg = GatewayConfig::load(&config).map_err(|e| {
+                anyhow::anyhow!("failed to load config from '{config}': {e}")
+            })?;
+
+            tracing::info!(
+                nodes = cfg.nodes.len(),
+                listen = %cfg.gateway.listen,
+                "starting cortex"
+            );
+
+            // Install Prometheus metrics exporter on a separate port.
+            cortex_gateway::metrics::install(&cfg.gateway.metrics_listen)?;
+
+            cortex_gateway::run(cfg).await?;
+        }
+        Commands::Status { endpoint } => {
+            print_status(&endpoint).await?;
+        }
+    }
+
+    Ok(())
+}
+
+async fn print_status(endpoint: &str) -> Result<()> {
+    let client = reqwest::Client::new();
+
+    // Fetch health.
+    let health: serde_json::Value = client
+        .get(format!("{endpoint}/health"))
+        .send()
+        .await?
+        .json()
+        .await?;
+
+    println!("Fleet health: {}", serde_json::to_string_pretty(&health)?);
+
+    // Fetch models.
+    let models: serde_json::Value = client
+        .get(format!("{endpoint}/v1/models"))
+        .send()
+        .await?
+        .json()
+        .await?;
+
+    println!("\nModels:");
+    if let Some(data) = models.get("data").and_then(|d| d.as_array()) {
+        for model in data {
+            let id = model.get("id").and_then(|v| v.as_str()).unwrap_or("?");
+            let locations = model
+                .get("locations")
+                .and_then(|v| v.as_array())
+                .map(|arr| {
+                    arr.iter()
+                        .filter_map(|l| {
+                            let node = l.get("node")?.as_str()?;
+                            let status = l.get("status")?.as_str()?;
+                            Some(format!("{node}({status})"))
+                        })
+                        .collect::<Vec<_>>()
+                        .join(", ")
+                })
+                .unwrap_or_default();
+            println!("  {id:40} {locations}");
+        }
+    }
+
+    Ok(())
+}
diff --git a/crates/cortex-core/Cargo.toml b/crates/cortex-core/Cargo.toml
new file mode 100644
index 0000000..76b8dd1
--- /dev/null
+++ b/crates/cortex-core/Cargo.toml
@@ -0,0 +1,15 @@
+[package]
+name = "cortex-core"
+version.workspace = true
+edition.workspace = true
+license.workspace = true
+
+[dependencies]
+serde.workspace = true
+serde_json.workspace = true
+toml.workspace = true
+figment.workspace = true
+chrono.workspace = true
+anyhow.workspace = true
+thiserror.workspace = true
+tracing.workspace = true
diff --git a/crates/cortex-core/src/anthropic.rs b/crates/cortex-core/src/anthropic.rs
new file mode 100644
index 0000000..921eda7
--- /dev/null
+++ b/crates/cortex-core/src/anthropic.rs
@@ -0,0 +1,87 @@
+//! Anthropic Messages API request and response types.
+//!
+//! These mirror the `/v1/messages` format used by the Anthropic API.
+//! The gateway accepts these, translates to OpenAI format, proxies to
+//! mistral.rs, then translates the response back.
+
+use serde::{Deserialize, Serialize};
+use serde_json::Value;
+
+// ── Messages request ─────────────────────────────────────────────────
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct MessagesRequest {
+    pub model: String,
+    pub messages: Vec<AnthropicMessage>,
+    pub max_tokens: u64,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub system: Option<SystemPrompt>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub temperature: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub top_p: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub stream: Option<bool>,
+    #[serde(flatten)]
+    pub extra: Value,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+#[serde(untagged)]
+pub enum SystemPrompt {
+    Text(String),
+    Blocks(Vec<Value>),
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct AnthropicMessage {
+    pub role: String,
+    pub content: AnthropicContent,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+#[serde(untagged)]
+pub enum AnthropicContent {
+    Text(String),
+    Blocks(Vec<ContentBlock>),
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ContentBlock {
+    #[serde(rename = "type")]
+    pub block_type: String,
+    #[serde(flatten)]
+    pub data: Value,
+}
+
+// ── Messages response ────────────────────────────────────────────────
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct MessagesResponse {
+    pub id: String,
+    #[serde(rename = "type")]
+    pub response_type: String,
+    pub role: String,
+    pub content: Vec<ContentBlock>,
+    pub model: String,
+    pub stop_reason: Option<String>,
+    pub usage: AnthropicUsage,
+    #[serde(flatten)]
+    pub extra: Value,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct AnthropicUsage {
+    pub input_tokens: u64,
+    pub output_tokens: u64,
+}
+
+// ── Streaming events ─────────────────────────────────────────────────
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct StreamEvent {
+    #[serde(rename = "type")]
+    pub event_type: String,
+    #[serde(flatten)]
+    pub data: Value,
+}
diff --git a/crates/cortex-core/src/config.rs b/crates/cortex-core/src/config.rs
new file mode 100644
index 0000000..97f6f83
--- /dev/null
+++ b/crates/cortex-core/src/config.rs
@@ -0,0 +1,79 @@
+use figment::{
+    Figment,
+    providers::{Env, Format, Toml},
+};
+use serde::{Deserialize, Serialize};
+use std::path::Path;
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct GatewayConfig {
+    pub gateway: GatewaySettings,
+    pub eviction: EvictionSettings,
+    pub nodes: Vec<NodeConfig>,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct GatewaySettings {
+    /// Address to listen on for API requests (e.g. "0.0.0.0:8000")
+    pub listen: String,
+    /// Address to listen on for Prometheus metrics (e.g. "0.0.0.0:9100")
+    pub metrics_listen: String,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct EvictionSettings {
+    /// Eviction strategy: "lru" or "priority"
+    pub strategy: EvictionStrategy,
+    /// Restart the mistralrs process after this many load/unload cycles
+    /// to reclaim fragmented VRAM. 0 = never.
+    #[serde(default)]
+    pub defrag_after_cycles: u32,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+#[serde(rename_all = "lowercase")]
+pub enum EvictionStrategy {
+    Lru,
+    Priority,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct NodeConfig {
+    /// Human-readable node name (e.g. "gpu-large")
+    pub name: String,
+    /// Base URL of the mistralrs HTTP server (e.g. "http://gpu-large.internal:8080")
+    pub endpoint: String,
+    /// Total VRAM in MB across all GPUs on this node
+    pub vram_mb: u64,
+    /// Model IDs that should never be evicted from this node
+    #[serde(default)]
+    pub pinned: Vec<String>,
+}
+
+impl GatewayConfig {
+    /// Load configuration from a TOML file, with environment variable overrides.
+    /// Env vars are prefixed with `CORTEX_` and use `__` as a separator
+    /// (e.g. `CORTEX_GATEWAY__LISTEN=0.0.0.0:9000`).
+    pub fn load(path: impl AsRef<Path>) -> Result<Self, figment::Error> {
+        Figment::new()
+            .merge(Toml::file(path))
+            .merge(Env::prefixed("CORTEX_").split("__"))
+            .extract()
+    }
+}
+
+impl Default for GatewayConfig {
+    fn default() -> Self {
+        Self {
+            gateway: GatewaySettings {
+                listen: "0.0.0.0:8000".into(),
+                metrics_listen: "0.0.0.0:9100".into(),
+            },
+            eviction: EvictionSettings {
+                strategy: EvictionStrategy::Lru,
+                defrag_after_cycles: 50,
+            },
+            nodes: vec![],
+        }
+    }
+}
diff --git a/crates/cortex-core/src/lib.rs b/crates/cortex-core/src/lib.rs
new file mode 100644
index 0000000..d54bc3e
--- /dev/null
+++ b/crates/cortex-core/src/lib.rs
@@ -0,0 +1,6 @@
+pub mod anthropic;
+pub mod config;
+pub mod metrics;
+pub mod node;
+pub mod openai;
+pub mod translate;
diff --git a/crates/cortex-core/src/metrics.rs b/crates/cortex-core/src/metrics.rs
new file mode 100644
index 0000000..4755520
--- /dev/null
+++ b/crates/cortex-core/src/metrics.rs
@@ -0,0 +1,23 @@
+//! Request-level metrics captured by the gateway proxy layer.
+
+use chrono::{DateTime, Utc};
+use serde::{Deserialize, Serialize};
+
+/// Metrics captured for a single proxied request.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct RequestMetrics {
+    pub timestamp: DateTime<Utc>,
+    pub model: String,
+    pub node: String,
+    pub prompt_tokens: u64,
+    pub completion_tokens: u64,
+    pub total_tokens: u64,
+    /// Tokens per second for the generation phase.
+    pub tok_per_sec: f64,
+    /// Time from request start to first SSE chunk (streaming) or full response.
+    pub time_to_first_token_ms: u64,
+    /// Total request latency including proxy overhead.
+    pub total_latency_ms: u64,
+    /// Whether this request triggered a model load (cold start).
+    pub cold_start: bool,
+}
diff --git a/crates/cortex-core/src/node.rs b/crates/cortex-core/src/node.rs
new file mode 100644
index 0000000..56df64e
--- /dev/null
+++ b/crates/cortex-core/src/node.rs
@@ -0,0 +1,74 @@
+use chrono::{DateTime, Utc};
+use serde::{Deserialize, Serialize};
+use std::collections::HashMap;
+
+/// Runtime state of a single node in the fleet.
+#[derive(Debug, Clone)]
+pub struct NodeState {
+    pub name: String,
+    pub endpoint: String,
+    pub vram_mb: u64,
+    pub pinned: Vec<String>,
+    pub healthy: bool,
+    pub models: HashMap<String, ModelEntry>,
+    /// Number of load/unload cycles since last process restart.
+    pub lifecycle_cycles: u32,
+    pub last_poll: Option<DateTime<Utc>>,
+}
+
+/// A model registered on a node, with its runtime status.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ModelEntry {
+    pub id: String,
+    pub status: ModelStatus,
+    /// When this model was last used (for LRU eviction).
+    pub last_accessed: Option<DateTime<Utc>>,
+    /// Estimated VRAM usage in MB when loaded.
+    pub vram_estimate_mb: Option<u64>,
+}
+
+/// Model lifecycle status, matching the mistral.rs API.
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
+#[serde(rename_all = "lowercase")]
+pub enum ModelStatus {
+    Loaded,
+    Unloaded,
+    Reloading,
+}
+
+/// Unified model entry as exposed by the gateway's `/v1/models` endpoint.
+/// Includes which node(s) host this model and their status.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct CortexModelEntry {
+    pub id: String,
+    pub object: String,
+    /// Which nodes have this model (and their status).
+    pub locations: Vec<ModelLocation>,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ModelLocation {
+    pub node: String,
+    pub status: ModelStatus,
+    pub vram_estimate_mb: Option<u64>,
+}
+
+/// Response from mistral.rs `GET /v1/models`.
+/// This is the upstream format we parse when polling nodes.
+#[derive(Debug, Clone, Deserialize)]
+pub struct MistralModelsResponse {
+    pub data: Vec<MistralModelEntry>,
+}
+
+#[derive(Debug, Clone, Deserialize)]
+pub struct MistralModelEntry {
+    pub id: String,
+    #[serde(default)]
+    pub status: Option<String>,
+}
+
+/// Request body for mistral.rs model lifecycle endpoints.
+#[derive(Debug, Clone, Serialize)]
+pub struct ModelLifecycleRequest {
+    pub model_id: String,
+}
diff --git a/crates/cortex-core/src/openai.rs b/crates/cortex-core/src/openai.rs
new file mode 100644
index 0000000..efdf7de
--- /dev/null
+++ b/crates/cortex-core/src/openai.rs
@@ -0,0 +1,122 @@
+//! OpenAI-compatible request and response types.
+//!
+//! These are a subset sufficient for chat completions (streaming + non-streaming).
+//! Fields not relevant to proxying are captured as `serde_json::Value` via
+//! `#[serde(flatten)]` so we forward them without needing to enumerate every
+//! extension field mistral.rs supports.
+
+use serde::{Deserialize, Serialize};
+use serde_json::Value;
+
+// ── Chat completion request ──────────────────────────────────────────
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ChatCompletionRequest {
+    pub model: String,
+    pub messages: Vec<ChatMessage>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub temperature: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub top_p: Option<f64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub max_tokens: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub stream: Option<bool>,
+    /// All other fields (tools, response_format, mistral.rs extensions, etc.)
+    #[serde(flatten)]
+    pub extra: Value,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ChatMessage {
+    pub role: String,
+    pub content: MessageContent,
+    #[serde(flatten)]
+    pub extra: Value,
+}
+
+/// Content can be a simple string or an array of content parts (for vision).
+#[derive(Debug, Clone, Serialize, Deserialize)]
+#[serde(untagged)]
+pub enum MessageContent {
+    Text(String),
+    Parts(Vec<Value>),
+}
+
+// ── Chat completion response (non-streaming) ─────────────────────────
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ChatCompletionResponse {
+    pub id: String,
+    pub object: String,
+    pub created: u64,
+    pub model: String,
+    pub choices: Vec<ChatCompletionChoice>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub usage: Option<Usage>,
+    #[serde(flatten)]
+    pub extra: Value,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ChatCompletionChoice {
+    pub index: u32,
+    pub message: ChatMessage,
+    pub finish_reason: Option<String>,
+    #[serde(flatten)]
+    pub extra: Value,
+}
+
+// ── Streaming chunk ──────────────────────────────────────────────────
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ChatCompletionChunk {
+    pub id: String,
+    pub object: String,
+    pub created: u64,
+    pub model: String,
+    pub choices: Vec<ChunkChoice>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub usage: Option<Usage>,
+    #[serde(flatten)]
+    pub extra: Value,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ChunkChoice {
+    pub index: u32,
+    pub delta: Value,
+    pub finish_reason: Option<String>,
+    #[serde(flatten)]
+    pub extra: Value,
+}
+
+// ── Usage ────────────────────────────────────────────────────────────
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct Usage {
+    pub prompt_tokens: u64,
+    pub completion_tokens: u64,
+    pub total_tokens: u64,
+}
+
+// ── Models list response ─────────────────────────────────────────────
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ModelsResponse {
+    pub object: String,
+    pub data: Vec<ModelObject>,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ModelObject {
+    pub id: String,
+    pub object: String,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub owned_by: Option<String>,
+    /// Gateway extensions: which node(s) host this model.
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub locations: Option<Vec<super::node::ModelLocation>>,
+    #[serde(flatten)]
+    pub extra: Value,
+}
diff --git a/crates/cortex-core/src/translate.rs b/crates/cortex-core/src/translate.rs
new file mode 100644
index 0000000..2d45a65
--- /dev/null
+++ b/crates/cortex-core/src/translate.rs
@@ -0,0 +1,114 @@
+//! Translation between OpenAI and Anthropic request/response envelopes.
+//!
+//! This is a stateless transformation — no context is carried between requests.
+
+use crate::anthropic::{
+    AnthropicContent, AnthropicMessage, AnthropicUsage, ContentBlock, MessagesRequest,
+    MessagesResponse, SystemPrompt,
+};
+use crate::openai::{
+    ChatCompletionChoice, ChatCompletionRequest, ChatCompletionResponse, ChatMessage, Usage,
+    MessageContent,
+};
+use serde_json::{json, Value};
+
+/// Convert an Anthropic Messages request into an OpenAI ChatCompletion request.
+pub fn anthropic_to_openai(req: MessagesRequest) -> ChatCompletionRequest {
+    let mut messages = Vec::new();
+
+    // Anthropic `system` field becomes a system message.
+    if let Some(system) = req.system {
+        let content = match system {
+            SystemPrompt::Text(t) => t,
+            SystemPrompt::Blocks(blocks) => serde_json::to_string(&blocks).unwrap_or_default(),
+        };
+        messages.push(ChatMessage {
+            role: "system".into(),
+            content: MessageContent::Text(content),
+            extra: Value::Null,
+        });
+    }
+
+    // Convert message roles and content.
+    for msg in req.messages {
+        let content = match msg.content {
+            AnthropicContent::Text(t) => MessageContent::Text(t),
+            AnthropicContent::Blocks(blocks) => {
+                // For simple text-only blocks, extract the text.
+                // For mixed content (images, etc.), pass as parts.
+                if blocks.len() == 1 && blocks[0].block_type == "text" {
+                    let text = blocks[0]
+                        .data
+                        .get("text")
+                        .and_then(|v| v.as_str())
+                        .unwrap_or("")
+                        .to_string();
+                    MessageContent::Text(text)
+                } else {
+                    MessageContent::Parts(
+                        blocks.into_iter().map(|b| json!(b)).collect(),
+                    )
+                }
+            }
+        };
+        messages.push(ChatMessage {
+            role: msg.role,
+            content,
+            extra: Value::Null,
+        });
+    }
+
+    ChatCompletionRequest {
+        model: req.model,
+        messages,
+        temperature: req.temperature,
+        top_p: req.top_p,
+        max_tokens: Some(req.max_tokens),
+        stream: req.stream,
+        extra: req.extra,
+    }
+}
+
+/// Convert an OpenAI ChatCompletion response into an Anthropic Messages response.
+pub fn openai_to_anthropic(resp: ChatCompletionResponse) -> MessagesResponse {
+    let choice = resp.choices.into_iter().next();
+
+    let (content_text, stop_reason) = match choice {
+        Some(c) => {
+            let text = match c.message.content {
+                MessageContent::Text(t) => t,
+                MessageContent::Parts(parts) => serde_json::to_string(&parts).unwrap_or_default(),
+            };
+            let stop = c.finish_reason.map(|r| match r.as_str() {
+                "stop" => "end_turn".to_string(),
+                "length" => "max_tokens".to_string(),
+                other => other.to_string(),
+            });
+            (text, stop)
+        }
+        None => (String::new(), None),
+    };
+
+    let usage = resp.usage.unwrap_or(Usage {
+        prompt_tokens: 0,
+        completion_tokens: 0,
+        total_tokens: 0,
+    });
+
+    MessagesResponse {
+        id: resp.id,
+        response_type: "message".into(),
+        role: "assistant".into(),
+        content: vec![ContentBlock {
+            block_type: "text".into(),
+            data: json!({ "text": content_text }),
+        }],
+        model: resp.model,
+        stop_reason,
+        usage: AnthropicUsage {
+            input_tokens: usage.prompt_tokens,
+            output_tokens: usage.completion_tokens,
+        },
+        extra: Value::Null,
+    }
+}
diff --git a/crates/cortex-gateway/Cargo.toml b/crates/cortex-gateway/Cargo.toml
new file mode 100644
index 0000000..7515467
--- /dev/null
+++ b/crates/cortex-gateway/Cargo.toml
@@ -0,0 +1,25 @@
+[package]
+name = "cortex-gateway"
+version.workspace = true
+edition.workspace = true
+license.workspace = true
+
+[dependencies]
+cortex-core.workspace = true
+tokio.workspace = true
+axum.workspace = true
+tower.workspace = true
+tower-http.workspace = true
+serde.workspace = true
+serde_json.workspace = true
+reqwest.workspace = true
+tracing.workspace = true
+metrics.workspace = true
+metrics-exporter-prometheus.workspace = true
+chrono.workspace = true
+anyhow.workspace = true
+thiserror.workspace = true
+futures.workspace = true
+tokio-stream.workspace = true
+eventsource-stream.workspace = true
+bytes = "1"
diff --git a/crates/cortex-gateway/src/evictor.rs b/crates/cortex-gateway/src/evictor.rs
new file mode 100644
index 0000000..66989d8
--- /dev/null
+++ b/crates/cortex-gateway/src/evictor.rs
@@ -0,0 +1,106 @@
+//! Model eviction logic.
+//!
+//! The evictor runs as a background task. When the router determines that a
+//! model needs to be loaded on a node but VRAM is tight, it can request
+//! eviction via a channel. The evictor then:
+//!   1. Identifies the LRU model on that node (excluding pinned models)
+//!   2. Calls `POST /v1/models/unload` on the node
+//!   3. Increments the lifecycle cycle counter (for defrag tracking)
+
+use crate::state::CortexState;
+use cortex_core::node::{ModelLifecycleRequest, ModelStatus};
+use std::sync::Arc;
+use std::time::Duration;
+
+/// Runs forever. Currently a placeholder that periodically checks for
+/// eviction opportunities. In the future, this will be driven by a
+/// channel from the router when VRAM pressure is detected.
+pub async fn eviction_loop(fleet: Arc<CortexState>) {
+    // TODO: Replace this polling approach with a channel-driven design
+    // where the router sends eviction requests when it detects that a
+    // model load would exceed available VRAM.
+    loop {
+        tokio::time::sleep(Duration::from_secs(30)).await;
+        // Placeholder: the actual eviction logic is in `evict_lru_on_node`,
+        // called on demand by the router.
+        let _ = &fleet; // suppress unused warning
+    }
+}
+
+/// Evict the least-recently-used model on a given node.
+/// Returns the model ID that was evicted, or None if nothing could be evicted.
+pub async fn evict_lru_on_node(
+    fleet: &CortexState,
+    node_name: &str,
+) -> anyhow::Result<Option<String>> {
+    let (endpoint, candidate) = {
+        let nodes = fleet.nodes.read().await;
+        let Some(node) = nodes.get(node_name) else {
+            anyhow::bail!("node '{node_name}' not found");
+        };
+
+        // Find the loaded model with the oldest last_accessed, excluding pinned.
+        let candidate = node
+            .models
+            .values()
+            .filter(|m| m.status == ModelStatus::Loaded)
+            .filter(|m| !node.pinned.contains(&m.id))
+            .min_by_key(|m| m.last_accessed)
+            .map(|m| m.id.clone());
+
+        (node.endpoint.clone(), candidate)
+    };
+
+    let Some(model_id) = candidate else {
+        tracing::info!(node = node_name, "no evictable models found");
+        return Ok(None);
+    };
+
+    tracing::info!(node = node_name, model = %model_id, "evicting model");
+
+    let url = format!("{endpoint}/v1/models/unload");
+    let resp = fleet
+        .http_client
+        .post(&url)
+        .json(&ModelLifecycleRequest {
+            model_id: model_id.clone(),
+        })
+        .send()
+        .await?;
+
+    if resp.status().is_success() {
+        // Update local state.
+        let mut nodes = fleet.nodes.write().await;
+        if let Some(node) = nodes.get_mut(node_name) {
+            if let Some(entry) = node.models.get_mut(&model_id) {
+                entry.status = ModelStatus::Unloaded;
+            }
+            node.lifecycle_cycles += 1;
+
+            // Check if we should flag for defrag.
+            if fleet.eviction.defrag_after_cycles > 0
+                && node.lifecycle_cycles >= fleet.eviction.defrag_after_cycles
+            {
+                tracing::warn!(
+                    node = node_name,
+                    cycles = node.lifecycle_cycles,
+                    "VRAM fragmentation threshold reached — consider restarting mistralrs"
+                );
+            }
+        }
+
+        tracing::info!(node = node_name, model = %model_id, "model evicted");
+        Ok(Some(model_id))
+    } else {
+        let status = resp.status();
+        let body = resp.text().await.unwrap_or_default();
+        tracing::error!(
+            node = node_name,
+            model = %model_id,
+            status = %status,
+            body = %body,
+            "failed to evict model"
+        );
+        anyhow::bail!("eviction failed: {status} {body}");
+    }
+}
diff --git a/crates/cortex-gateway/src/handlers.rs b/crates/cortex-gateway/src/handlers.rs
new file mode 100644
index 0000000..d24ae9b
--- /dev/null
+++ b/crates/cortex-gateway/src/handlers.rs
@@ -0,0 +1,207 @@
+//! Axum HTTP handlers for the gateway API surface.
+
+use crate::proxy;
+use crate::router;
+use crate::state::CortexState;
+use axum::body::Bytes;
+use axum::extract::State;
+use axum::http::HeaderMap;
+use axum::response::{IntoResponse, Json, Response};
+use axum::routing::{get, post};
+use axum::Router;
+use cortex_core::node::{CortexModelEntry, ModelLocation};
+use cortex_core::openai::ChatCompletionRequest;
+use serde_json::{json, Value};
+use std::sync::Arc;
+
+pub fn api_routes() -> Router<Arc<CortexState>> {
+    Router::new()
+        .route("/v1/chat/completions", post(chat_completions))
+        .route("/v1/completions", post(completions))
+        .route("/v1/models", get(list_models))
+        .route("/v1/messages", post(anthropic_messages))
+        .route("/health", get(health))
+        .route("/", get(health))
+}
+
+/// `POST /v1/chat/completions` — proxy to the appropriate backend node.
+async fn chat_completions(
+    State(fleet): State<Arc<CortexState>>,
+    headers: HeaderMap,
+    body: Bytes,
+) -> Response {
+    let model_id = match extract_model(&body) {
+        Some(m) => m,
+        None => return error_response(400, "missing 'model' field in request body"),
+    };
+
+    let route = match router::resolve(&fleet, &model_id).await {
+        Ok(r) => r,
+        Err(e) => return error_response(404, &e.to_string()),
+    };
+
+    match proxy::forward_request(&fleet.http_client, &route, "/v1/chat/completions", headers, body)
+        .await
+    {
+        Ok(resp) => resp,
+        Err(e) => e.into_response(),
+    }
+}
+
+/// `POST /v1/completions` — proxy completions endpoint.
+async fn completions(
+    State(fleet): State<Arc<CortexState>>,
+    headers: HeaderMap,
+    body: Bytes,
+) -> Response {
+    let model_id = match extract_model(&body) {
+        Some(m) => m,
+        None => return error_response(400, "missing 'model' field in request body"),
+    };
+
+    let route = match router::resolve(&fleet, &model_id).await {
+        Ok(r) => r,
+        Err(e) => return error_response(404, &e.to_string()),
+    };
+
+    match proxy::forward_request(&fleet.http_client, &route, "/v1/completions", headers, body)
+        .await
+    {
+        Ok(resp) => resp,
+        Err(e) => e.into_response(),
+    }
+}
+
+/// `POST /v1/messages` — accept Anthropic format, translate, proxy, translate back.
+async fn anthropic_messages(
+    State(fleet): State<Arc<CortexState>>,
+    headers: HeaderMap,
+    body: Bytes,
+) -> Response {
+    // Parse as Anthropic request.
+    let anth_req: cortex_core::anthropic::MessagesRequest = match serde_json::from_slice(&body) {
+        Ok(r) => r,
+        Err(e) => return error_response(400, &format!("invalid Anthropic request: {e}")),
+    };
+
+    let model_id = anth_req.model.clone();
+    let is_streaming = anth_req.stream.unwrap_or(false);
+
+    // Translate to OpenAI format.
+    let openai_req = cortex_core::translate::anthropic_to_openai(anth_req);
+    let openai_body = match serde_json::to_vec(&openai_req) {
+        Ok(b) => Bytes::from(b),
+        Err(e) => return error_response(500, &format!("translation error: {e}")),
+    };
+
+    let route = match router::resolve(&fleet, &model_id).await {
+        Ok(r) => r,
+        Err(e) => return error_response(404, &e.to_string()),
+    };
+
+    if is_streaming {
+        // TODO: streaming Anthropic translation requires converting SSE format.
+        // For now, proxy the OpenAI SSE stream directly (clients that can handle
+        // OpenAI SSE will work; full Anthropic SSE translation is a follow-up).
+        match proxy::forward_request(
+            &fleet.http_client,
+            &route,
+            "/v1/chat/completions",
+            headers,
+            openai_body,
+        )
+        .await
+        {
+            Ok(resp) => resp,
+            Err(e) => e.into_response(),
+        }
+    } else {
+        // Non-streaming: proxy, await full response, translate back.
+        match proxy::forward_request(
+            &fleet.http_client,
+            &route,
+            "/v1/chat/completions",
+            headers,
+            openai_body,
+        )
+        .await
+        {
+            Ok(resp) => {
+                // TODO: buffer response, parse as OpenAI ChatCompletionResponse,
+                // translate to Anthropic MessagesResponse.
+                // For now, return the OpenAI response as-is.
+                resp
+            }
+            Err(e) => e.into_response(),
+        }
+    }
+}
+
+/// `GET /v1/models` — aggregate models from all nodes.
+async fn list_models(State(fleet): State<Arc<CortexState>>) -> Json<Value> {
+    let nodes = fleet.nodes.read().await;
+    let mut model_map: std::collections::HashMap<String, CortexModelEntry> =
+        std::collections::HashMap::new();
+
+    for node in nodes.values() {
+        for (model_id, entry) in &node.models {
+            let location = ModelLocation {
+                node: node.name.clone(),
+                status: entry.status,
+                vram_estimate_mb: entry.vram_estimate_mb,
+            };
+            model_map
+                .entry(model_id.clone())
+                .and_modify(|e| e.locations.push(location.clone()))
+                .or_insert_with(|| CortexModelEntry {
+                    id: model_id.clone(),
+                    object: "model".into(),
+                    locations: vec![location],
+                });
+        }
+    }
+
+    let data: Vec<Value> = model_map
+        .values()
+        .map(|e| json!(e))
+        .collect();
+
+    Json(json!({
+        "object": "list",
+        "data": data,
+    }))
+}
+
+/// `GET /health`
+async fn health(State(fleet): State<Arc<CortexState>>) -> Json<Value> {
+    let nodes = fleet.nodes.read().await;
+    let healthy_count = nodes.values().filter(|n| n.healthy).count();
+    let total_count = nodes.len();
+
+    Json(json!({
+        "status": if healthy_count > 0 { "ok" } else { "degraded" },
+        "nodes": {
+            "healthy": healthy_count,
+            "total": total_count,
+        }
+    }))
+}
+
+// ── Helpers ──────────────────────────────────────────────────────────
+
+fn extract_model(body: &[u8]) -> Option<String> {
+    let v: Value = serde_json::from_slice(body).ok()?;
+    v.get("model")?.as_str().map(|s| s.to_string())
+}
+
+fn error_response(status: u16, message: &str) -> Response {
+    let code = axum::http::StatusCode::from_u16(status)
+        .unwrap_or(axum::http::StatusCode::INTERNAL_SERVER_ERROR);
+    let body = json!({
+        "error": {
+            "message": message,
+            "type": "gateway_error",
+        }
+    });
+    (code, Json(body)).into_response()
+}
diff --git a/crates/cortex-gateway/src/lib.rs b/crates/cortex-gateway/src/lib.rs
new file mode 100644
index 0000000..5e5b7c6
--- /dev/null
+++ b/crates/cortex-gateway/src/lib.rs
@@ -0,0 +1,51 @@
+pub mod evictor;
+pub mod handlers;
+pub mod metrics;
+pub mod poller;
+pub mod proxy;
+pub mod router;
+pub mod state;
+
+use anyhow::Result;
+use axum::Router;
+use cortex_core::config::GatewayConfig;
+use std::sync::Arc;
+use tower_http::cors::CorsLayer;
+use tower_http::trace::TraceLayer;
+
+/// Build the Axum application router with all routes wired up.
+pub fn build_app(fleet: Arc<state::CortexState>) -> Router {
+    Router::new()
+        .merge(handlers::api_routes())
+        .layer(CorsLayer::permissive())
+        .layer(TraceLayer::new_for_http())
+        .with_state(fleet)
+}
+
+/// Start the gateway: build state from config, spawn background tasks,
+/// bind the HTTP server.
+pub async fn run(config: GatewayConfig) -> Result<()> {
+    let fleet = Arc::new(state::CortexState::from_config(&config));
+
+    // Spawn the background poller that refreshes node/model status.
+    let poller_fleet = Arc::clone(&fleet);
+    tokio::spawn(async move {
+        poller::poll_loop(poller_fleet).await;
+    });
+
+    // Spawn the evictor (reacts to VRAM pressure events from the router).
+    let evictor_fleet = Arc::clone(&fleet);
+    tokio::spawn(async move {
+        evictor::eviction_loop(evictor_fleet).await;
+    });
+
+    let app = build_app(Arc::clone(&fleet));
+
+    let listen_addr = config.gateway.listen.parse::<std::net::SocketAddr>()?;
+    tracing::info!("cortex listening on {listen_addr}");
+
+    let listener = tokio::net::TcpListener::bind(listen_addr).await?;
+    axum::serve(listener, app).await?;
+
+    Ok(())
+}
diff --git a/crates/cortex-gateway/src/metrics.rs b/crates/cortex-gateway/src/metrics.rs
new file mode 100644
index 0000000..cf960a8
--- /dev/null
+++ b/crates/cortex-gateway/src/metrics.rs
@@ -0,0 +1,55 @@
+//! Prometheus metrics exporter.
+//!
+//! Runs on a separate port from the main API, exposing `/metrics`
+//! in Prometheus text format.
+
+use anyhow::Result;
+use metrics_exporter_prometheus::PrometheusBuilder;
+use std::net::SocketAddr;
+
+/// Install the Prometheus metrics recorder and return a handle.
+/// The `/metrics` endpoint is served by the exporter's built-in HTTP server.
+pub fn install(listen: &str) -> Result<()> {
+    let addr: SocketAddr = listen.parse()?;
+
+    PrometheusBuilder::new()
+        .with_http_listener(addr)
+        .install()
+        .map_err(|e| anyhow::anyhow!("failed to install Prometheus exporter: {e}"))?;
+
+    tracing::info!("prometheus metrics exporter on {addr}");
+
+    // Register histograms and counters used by the proxy layer.
+    // The `metrics` crate lazily creates metrics on first use, but
+    // describing them up front gives Prometheus proper HELP/TYPE lines.
+    metrics::describe_histogram!(
+        "cortex_request_duration_seconds",
+        "Total request latency in seconds"
+    );
+    metrics::describe_histogram!(
+        "cortex_time_to_first_token_seconds",
+        "Time to first token in seconds"
+    );
+    metrics::describe_histogram!(
+        "cortex_tokens_per_second",
+        "Generation throughput in tokens per second"
+    );
+    metrics::describe_counter!(
+        "cortex_requests_total",
+        "Total number of proxied requests"
+    );
+    metrics::describe_counter!(
+        "cortex_request_errors_total",
+        "Total number of failed proxy requests"
+    );
+    metrics::describe_counter!(
+        "cortex_evictions_total",
+        "Total number of model evictions"
+    );
+    metrics::describe_counter!(
+        "cortex_cold_starts_total",
+        "Total number of cold-start model loads"
+    );
+
+    Ok(())
+}
diff --git a/crates/cortex-gateway/src/poller.rs b/crates/cortex-gateway/src/poller.rs
new file mode 100644
index 0000000..baa9566
--- /dev/null
+++ b/crates/cortex-gateway/src/poller.rs
@@ -0,0 +1,103 @@
+//! Background poller that periodically queries each node's `/v1/models`
+//! endpoint to refresh the fleet state.
+
+use crate::state::CortexState;
+use chrono::Utc;
+use cortex_core::node::{MistralModelsResponse, ModelEntry, ModelStatus};
+use std::sync::Arc;
+use std::time::Duration;
+
+const POLL_INTERVAL: Duration = Duration::from_secs(10);
+
+/// Runs forever, polling all nodes on a fixed interval.
+pub async fn poll_loop(fleet: Arc<CortexState>) {
+    loop {
+        for nc in &fleet.node_configs {
+            poll_node(&fleet, &nc.name, &nc.endpoint).await;
+        }
+        tokio::time::sleep(POLL_INTERVAL).await;
+    }
+}
+
+async fn poll_node(fleet: &CortexState, name: &str, endpoint: &str) {
+    let url = format!("{endpoint}/v1/models");
+
+    let result = fleet
+        .http_client
+        .get(&url)
+        .timeout(Duration::from_secs(5))
+        .send()
+        .await;
+
+    let mut nodes = fleet.nodes.write().await;
+    let Some(node) = nodes.get_mut(name) else {
+        return;
+    };
+
+    match result {
+        Ok(resp) if resp.status().is_success() => {
+            match resp.json::<MistralModelsResponse>().await {
+                Ok(models_resp) => {
+                    // Merge upstream model list into our state, preserving
+                    // our local metadata (last_accessed, vram_estimate).
+                    let mut seen = std::collections::HashSet::new();
+                    for upstream in &models_resp.data {
+                        seen.insert(upstream.id.clone());
+                        let status = parse_status(upstream.status.as_deref());
+
+                        node.models
+                            .entry(upstream.id.clone())
+                            .and_modify(|e| {
+                                e.status = status;
+                            })
+                            .or_insert_with(|| ModelEntry {
+                                id: upstream.id.clone(),
+                                status,
+                                last_accessed: None,
+                                vram_estimate_mb: None,
+                            });
+                    }
+
+                    // Remove models that are no longer reported by the node
+                    // (e.g. after a config change / restart).
+                    node.models.retain(|id, _| seen.contains(id));
+
+                    node.healthy = true;
+                    node.last_poll = Some(Utc::now());
+                    tracing::debug!(
+                        node = name,
+                        models = models_resp.data.len(),
+                        "poll ok"
+                    );
+                }
+                Err(e) => {
+                    tracing::warn!(node = name, error = %e, "failed to parse /v1/models response");
+                    node.healthy = false;
+                }
+            }
+        }
+        Ok(resp) => {
+            tracing::warn!(
+                node = name,
+                status = %resp.status(),
+                "node returned non-success status"
+            );
+            node.healthy = false;
+        }
+        Err(e) => {
+            tracing::warn!(node = name, error = %e, "failed to reach node");
+            node.healthy = false;
+        }
+    }
+}
+
+fn parse_status(s: Option<&str>) -> ModelStatus {
+    match s {
+        Some("loaded") => ModelStatus::Loaded,
+        Some("unloaded") => ModelStatus::Unloaded,
+        Some("reloading") => ModelStatus::Reloading,
+        // If the status field is absent, assume loaded (older mistral.rs versions
+        // may not include it).
+        _ => ModelStatus::Loaded,
+    }
+}
diff --git a/crates/cortex-gateway/src/proxy.rs b/crates/cortex-gateway/src/proxy.rs
new file mode 100644
index 0000000..41c22f5
--- /dev/null
+++ b/crates/cortex-gateway/src/proxy.rs
@@ -0,0 +1,82 @@
+//! Streaming HTTP reverse proxy to mistral.rs backends.
+//!
+//! For streaming requests, SSE chunks are forwarded as they arrive.
+//! The proxy captures timing information for metrics but does not
+//! buffer the full response.
+
+use crate::router::RouteDecision;
+use anyhow::Result;
+use axum::body::Body;
+use axum::http::{HeaderMap, StatusCode};
+use axum::response::{IntoResponse, Response};
+use reqwest::Client;
+
+/// Proxy a request body to the resolved backend node and stream the response.
+pub async fn forward_request(
+    client: &Client,
+    route: &RouteDecision,
+    path: &str,
+    headers: HeaderMap,
+    body: bytes::Bytes,
+) -> Result<Response, ProxyError> {
+    let url = format!("{}{}", route.endpoint, path);
+    tracing::info!(
+        node = %route.node_name,
+        url = %url,
+        cold_start = route.cold_start,
+        "proxying request"
+    );
+
+    let mut req_builder = client.post(&url).body(body);
+
+    // Forward relevant headers.
+    for (key, value) in headers.iter() {
+        if key == "host" || key == "content-length" {
+            continue; // reqwest sets these
+        }
+        req_builder = req_builder.header(key, value);
+    }
+
+    let upstream_resp = req_builder.send().await.map_err(ProxyError::Upstream)?;
+
+    let status = StatusCode::from_u16(upstream_resp.status().as_u16())
+        .unwrap_or(StatusCode::BAD_GATEWAY);
+
+    let resp_headers = upstream_resp.headers().clone();
+    let stream = upstream_resp.bytes_stream();
+
+    let body = Body::from_stream(stream);
+
+    let mut response = Response::builder().status(status);
+    for (key, value) in resp_headers.iter() {
+        response = response.header(key, value);
+    }
+
+    response
+        .body(body)
+        .map_err(|e| ProxyError::ResponseBuild(e.to_string()))
+}
+
+#[derive(Debug, thiserror::Error)]
+pub enum ProxyError {
+    #[error("upstream request failed: {0}")]
+    Upstream(reqwest::Error),
+    #[error("failed to build response: {0}")]
+    ResponseBuild(String),
+}
+
+impl IntoResponse for ProxyError {
+    fn into_response(self) -> Response {
+        let status = match &self {
+            ProxyError::Upstream(_) => StatusCode::BAD_GATEWAY,
+            ProxyError::ResponseBuild(_) => StatusCode::INTERNAL_SERVER_ERROR,
+        };
+        let body = serde_json::json!({
+            "error": {
+                "message": self.to_string(),
+                "type": "proxy_error",
+            }
+        });
+        (status, axum::Json(body)).into_response()
+    }
+}
diff --git a/crates/cortex-gateway/src/router.rs b/crates/cortex-gateway/src/router.rs
new file mode 100644
index 0000000..8af3fbc
--- /dev/null
+++ b/crates/cortex-gateway/src/router.rs
@@ -0,0 +1,74 @@
+//! Model-to-node routing logic.
+//!
+//! Given a model ID from an inbound request, determine which node should
+//! handle it. Priority:
+//!   1. Node where the model is currently `Loaded`
+//!   2. Node where the model is `Unloaded` (will lazy-load on request)
+//!   3. Error: model not found on any node
+
+use crate::state::CortexState;
+use cortex_core::node::ModelStatus;
+use std::sync::Arc;
+
+/// The routing decision: which node endpoint to proxy the request to.
+#[derive(Debug, Clone)]
+pub struct RouteDecision {
+    pub node_name: String,
+    pub endpoint: String,
+    /// Whether the model will need to load (cold start).
+    pub cold_start: bool,
+}
+
+#[derive(Debug, thiserror::Error)]
+pub enum RouteError {
+    #[error("model '{0}' not found on any node")]
+    ModelNotFound(String),
+    #[error("no healthy nodes available")]
+    NoHealthyNodes,
+}
+
+/// Resolve which node should serve a request for the given model.
+pub async fn resolve(fleet: &Arc<CortexState>, model_id: &str) -> Result<RouteDecision, RouteError> {
+    let nodes = fleet.nodes.read().await;
+
+    // Pass 1: find a node where the model is already loaded.
+    let mut loaded_candidate = None;
+    let mut unloaded_candidate = None;
+
+    for node in nodes.values() {
+        if !node.healthy {
+            continue;
+        }
+        if let Some(entry) = node.models.get(model_id) {
+            match entry.status {
+                ModelStatus::Loaded | ModelStatus::Reloading => {
+                    loaded_candidate = Some(RouteDecision {
+                        node_name: node.name.clone(),
+                        endpoint: node.endpoint.clone(),
+                        cold_start: false,
+                    });
+                    break; // loaded is best, stop searching
+                }
+                ModelStatus::Unloaded => {
+                    if unloaded_candidate.is_none() {
+                        unloaded_candidate = Some(RouteDecision {
+                            node_name: node.name.clone(),
+                            endpoint: node.endpoint.clone(),
+                            cold_start: true,
+                        });
+                    }
+                }
+            }
+        }
+    }
+
+    loaded_candidate
+        .or(unloaded_candidate)
+        .ok_or_else(|| {
+            if nodes.values().any(|n| n.healthy) {
+                RouteError::ModelNotFound(model_id.to_string())
+            } else {
+                RouteError::NoHealthyNodes
+            }
+        })
+}
diff --git a/crates/cortex-gateway/src/state.rs b/crates/cortex-gateway/src/state.rs
new file mode 100644
index 0000000..0d7aade
--- /dev/null
+++ b/crates/cortex-gateway/src/state.rs
@@ -0,0 +1,43 @@
+use cortex_core::config::{EvictionSettings, GatewayConfig, NodeConfig};
+use cortex_core::node::NodeState;
+use std::collections::HashMap;
+use tokio::sync::RwLock;
+
+/// Shared fleet state, protected by a RwLock for concurrent reader access.
+pub struct CortexState {
+    pub nodes: RwLock<HashMap<String, NodeState>>,
+    pub node_configs: Vec<NodeConfig>,
+    pub eviction: EvictionSettings,
+    pub http_client: reqwest::Client,
+}
+
+impl CortexState {
+    pub fn from_config(config: &GatewayConfig) -> Self {
+        let mut nodes = HashMap::new();
+        for nc in &config.nodes {
+            nodes.insert(
+                nc.name.clone(),
+                NodeState {
+                    name: nc.name.clone(),
+                    endpoint: nc.endpoint.clone(),
+                    vram_mb: nc.vram_mb,
+                    pinned: nc.pinned.clone(),
+                    healthy: false, // will be set by first poll
+                    models: HashMap::new(),
+                    lifecycle_cycles: 0,
+                    last_poll: None,
+                },
+            );
+        }
+
+        Self {
+            nodes: RwLock::new(nodes),
+            node_configs: config.nodes.clone(),
+            eviction: config.eviction.clone(),
+            http_client: reqwest::Client::builder()
+                .timeout(std::time::Duration::from_secs(300))
+                .build()
+                .expect("failed to build HTTP client"),
+        }
+    }
+}