chore: move default ports out of common-collision ranges

Previous defaults collided with well-trodden infra services and with the Linux ephemeral port range: - cortex API 8000 — common dev-server default (Django, minio UI) - cortex metrics 9100 — Prometheus node_exporter default - neuron API 9090 — Cockpit default on Fedora, Prometheus self Move to helexa-themed palindromic ports, all below Linux's 32768-60999 ephemeral range and not registered to any well-known service: - cortex API 31313 - cortex metrics 31314 - neuron API 13131 Updated places: - cortex.example.toml, neuron.example.toml defaults - default impls in cortex-core and neuron config - cortex-cli --endpoint default for the status subcommand - doc comments citing example URLs - README.md and CLAUDE.md snippets Consumers already on the old ports need a one-line edit in their /etc/cortex/cortex.toml or /etc/neuron/neuron.toml to match; firewall rules and prometheus scrape configs will also need updating. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
ci: drop actions/cache for cargo registry and target
2026-04-16 17:35:09 +03:00 · 2026-04-16 16:47:32 +03:00
37 changed files with 459 additions and 3349 deletions
--- a/.gitea/workflows/build-prerelease.yml
+++ b/.gitea/workflows/build-prerelease.yml
@@ -1,335 +0,0 @@
-name: build-prerelease
-
-# Manually-dispatched workflow that builds CUDA-flavoured neuron binaries
-# (and a single cortex binary), packages each as a Fedora RPM, signs
-# them, and publishes to the `unstable` channel at rpm.lair.cafe.
-#
-# Trigger from the Gitea UI: Actions → build-prerelease → Run workflow.
-# Optionally provide a `ref` to build from a non-default branch.
-#
-# The published packages are versioned as e.g.
-#   helexa-neuron-blackwell-0.1.16-0.1.20260518gitabcdef0.fc43.x86_64
-# so they sort BELOW the eventual 0.1.16-1 stable release.
-
-on:
-  workflow_dispatch:
-    inputs:
-      ref:
-        description: "Git ref to build (branch / tag / commit). Defaults to the workflow's branch."
-        required: false
-        default: ""
-
-concurrency:
-  group: prerelease-build
-  cancel-in-progress: true
-
-env:
-  CARGO_INCREMENTAL: "0"
-
-jobs:
-  prepare:
-    name: Resolve version stamps
-    runs-on: rust
-    outputs:
-      version: ${{ steps.info.outputs.version }}
-      release: ${{ steps.info.outputs.release }}
-      short_sha: ${{ steps.info.outputs.short_sha }}
-      commit_date: ${{ steps.info.outputs.commit_date }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ inputs.ref }}
-          fetch-depth: 0
-
-      - id: info
-        run: |
-          set -eux
-          VERSION=$(awk -F\" '/^version[[:space:]]*=/ { print $2; exit }' Cargo.toml)
-          SHORT_SHA=$(git rev-parse --short=7 HEAD)
-          COMMIT_DATE=$(git log -1 --format=%cd --date=format:%Y%m%d HEAD)
-          # Prerelease release stamp sorts before "1" (the stable release).
-          RELEASE="0.1.${COMMIT_DATE}git${SHORT_SHA}"
-          echo "version=${VERSION}" >> "$GITHUB_OUTPUT"
-          echo "release=${RELEASE}" >> "$GITHUB_OUTPUT"
-          echo "short_sha=${SHORT_SHA}" >> "$GITHUB_OUTPUT"
-          echo "commit_date=${COMMIT_DATE}" >> "$GITHUB_OUTPUT"
-
-  build-cortex:
-    name: Build cortex binary
-    needs: prepare
-    runs-on: rust
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ inputs.ref }}
-
-      - name: Install/update Rust toolchain
-        run: |
-          if command -v rustup &> /dev/null; then
-            rustup update stable
-          else
-            curl --proto '=https' --tlsv1.2 --silent --show-error --fail https://sh.rustup.rs | sh -s -- -y
-          fi
-          echo "${HOME}/.cargo/bin" >> "$GITHUB_PATH"
-
-      - name: Build cortex (release)
-        run: cargo build --release -p cortex-cli
-
-      - name: Stage binary
-        run: |
-          mkdir --parents artifacts
-          cp target/release/cortex artifacts/cortex
-          ./artifacts/cortex --version || true
-
-      - uses: actions/upload-artifact@v3
-        with:
-          name: cortex-fc43
-          path: artifacts/cortex
-          retention-days: 1
-
-  build-neuron:
-    name: Build neuron-${{ matrix.flavour }}
-    needs: prepare
-    strategy:
-      fail-fast: false
-      matrix:
-        include:
-          - flavour: ampere
-            compute_cap: "86"
-            runner: cuda-13.0
-            cuda_home: /usr/local/cuda-13.0
-            build_jobs: 8
-            nvcc_threads: 4
-            cargo_features: "cuda cudnn flash-attn"
-          - flavour: ada
-            compute_cap: "89"
-            runner: cuda-13.0
-            cuda_home: /usr/local/cuda-13.0
-            build_jobs: 8
-            nvcc_threads: 4
-            cargo_features: "cuda cudnn flash-attn"
-          - flavour: blackwell
-            compute_cap: "120"
-            runner: cuda-13.0
-            cuda_home: /usr/local/cuda-13.0
-            build_jobs: 8
-            nvcc_threads: 4
-            cargo_features: "cuda cudnn flash-attn"
-    runs-on: ${{ matrix.runner }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ inputs.ref }}
-
-      - name: Install/update Rust toolchain
-        run: |
-          if command -v rustup &> /dev/null; then
-            rustup update stable
-          else
-            curl --proto '=https' --tlsv1.2 --silent --show-error --fail https://sh.rustup.rs | sh -s -- -y
-          fi
-          echo "${HOME}/.cargo/bin" >> "$GITHUB_PATH"
-
-      - name: Build neuron with CUDA (${{ matrix.flavour }})
-        run: |
-          set -eux
-          export PATH="${{ matrix.cuda_home }}/bin:${PATH}"
-          export LD_LIBRARY_PATH="${{ matrix.cuda_home }}/targets/x86_64-linux/lib:${{ matrix.cuda_home }}/lib64:${LD_LIBRARY_PATH:-}"
-          export LIBRARY_PATH="${{ matrix.cuda_home }}/targets/x86_64-linux/lib:${{ matrix.cuda_home }}/lib64:${LIBRARY_PATH:-}"
-          cargo build --release -p neuron --features "${{ matrix.cargo_features }}"
-        env:
-          CUDA_COMPUTE_CAP: ${{ matrix.compute_cap }}
-          CARGO_BUILD_JOBS: ${{ matrix.build_jobs }}
-          NVCC_THREADS: ${{ matrix.nvcc_threads }}
-
-      - name: Stage binary
-        run: |
-          mkdir --parents artifacts
-          cp target/release/neuron artifacts/neuron-${{ matrix.flavour }}
-          file "artifacts/neuron-${{ matrix.flavour }}"
-
-      - uses: actions/upload-artifact@v3
-        with:
-          name: neuron-${{ matrix.flavour }}-fc43
-          path: artifacts/neuron-${{ matrix.flavour }}
-          retention-days: 1
-
-  package-cortex:
-    name: Package cortex RPM
-    needs: [prepare, build-cortex]
-    runs-on: rpm
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ inputs.ref }}
-
-      - uses: actions/download-artifact@v3
-        with:
-          name: cortex-fc43
-          path: artifacts/
-
-      - name: Build RPM
-        run: |
-          set -eux
-          rm -f ~/.rpmmacros
-          rpmdev-setuptree
-          cp artifacts/cortex ~/rpmbuild/SOURCES/
-          cp data/cortex.service ~/rpmbuild/SOURCES/
-          cp data/cortex-sysusers.conf ~/rpmbuild/SOURCES/
-          cp data/cortex-firewalld.xml ~/rpmbuild/SOURCES/
-          cp cortex.example.toml ~/rpmbuild/SOURCES/
-          cp models.example.toml ~/rpmbuild/SOURCES/
-          cp LICENSE ~/rpmbuild/SOURCES/
-          rpmbuild -bb rpm/cortex-prerelease.spec \
-            --define "cortex_version ${{ needs.prepare.outputs.version }}" \
-            --define "cortex_prerelease ${{ needs.prepare.outputs.release }}" \
-            --undefine dist \
-            --define "dist .fc43"
-
-      - uses: actions/upload-artifact@v3
-        with:
-          name: rpm-cortex-fc43
-          path: ~/rpmbuild/RPMS/x86_64/*.rpm
-          retention-days: 7
-
-  package-neuron:
-    name: Package helexa-neuron-${{ matrix.flavour }} RPM
-    needs: [prepare, build-neuron]
-    runs-on: rpm
-    strategy:
-      fail-fast: false
-      matrix:
-        include:
-          - flavour: ampere
-          - flavour: ada
-          - flavour: blackwell
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ inputs.ref }}
-
-      - uses: actions/download-artifact@v3
-        with:
-          name: neuron-${{ matrix.flavour }}-fc43
-          path: artifacts/
-
-      - name: Build RPM
-        run: |
-          set -eux
-          rm -f ~/.rpmmacros
-          rpmdev-setuptree
-          cp artifacts/neuron-${{ matrix.flavour }} ~/rpmbuild/SOURCES/
-          cp data/neuron.service ~/rpmbuild/SOURCES/
-          cp data/neuron-sysusers.conf ~/rpmbuild/SOURCES/
-          cp data/neuron-firewalld.xml ~/rpmbuild/SOURCES/
-          cp neuron.example.toml ~/rpmbuild/SOURCES/
-          cp LICENSE ~/rpmbuild/SOURCES/
-          rpmbuild -bb rpm/helexa-neuron-prerelease.spec \
-            --define "neuron_version ${{ needs.prepare.outputs.version }}" \
-            --define "neuron_flavour ${{ matrix.flavour }}" \
-            --define "neuron_prerelease ${{ needs.prepare.outputs.release }}" \
-            --undefine dist \
-            --define "dist .fc43"
-
-      - uses: actions/upload-artifact@v3
-        with:
-          name: rpm-neuron-${{ matrix.flavour }}-fc43
-          path: ~/rpmbuild/RPMS/x86_64/*.rpm
-          retention-days: 7
-
-  publish:
-    name: Publish to rpm.lair.cafe (unstable)
-    needs: [package-cortex, package-neuron]
-    runs-on: rpm
-    concurrency:
-      group: rpm-publish
-      cancel-in-progress: false
-    env:
-      RPM_REPO_HOST: oolon.kosherinata.internal
-      FEDORA_VERSION: "43"
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ inputs.ref }}
-
-      - name: Download all built RPMs
-        uses: actions/download-artifact@v3
-        with:
-          path: rpms/
-          pattern: rpm-*-fc43
-
-      - name: Flatten RPM artifacts
-        run: |
-          set -eux
-          find rpms/ -name '*.rpm' -exec mv --target-directory=rpms/ {} +
-          find rpms/ -mindepth 1 -type d -empty -delete
-          ls -la rpms/
-
-      - name: Check for sequoia-sq
-        run: |
-          if ! command -v sq &> /dev/null; then
-            echo "ERROR: sequoia-sq is not installed. Install with: sudo dnf install sequoia-sq"
-            exit 1
-          fi
-
-      - name: Import signing key
-        env:
-          # Pass secrets via env so values stay out of the rendered shell
-          # script (which Gitea includes in step logs). Template
-          # expansion of ${{ secrets.X }} inside `run:` writes the literal
-          # value into the script and depends on Gitea's log masker to
-          # scrub it — fragile for multi-line keys.
-          RPM_SIGNING_KEY: ${{ secrets.RPM_SIGNING_KEY }}
-          RPM_SIGNING_KEY_ID: ${{ secrets.RPM_SIGNING_KEY_ID }}
-        run: |
-          echo "$RPM_SIGNING_KEY" | gpg --batch --import
-          fpr=$(gpg --batch --with-colons --list-keys "$RPM_SIGNING_KEY_ID" | awk -F: '/^fpr:/ { print $10; exit }')
-          echo "${fpr}:6:" | gpg --batch --import-ownertrust
-          sed "s/@GPG_NAME@/$RPM_SIGNING_KEY_ID/" rpm/rpmmacros > ~/.rpmmacros
-
-      - name: Sign RPMs
-        run: |
-          set -eux
-          for rpm in rpms/*.rpm; do
-            echo "signing ${rpm}..."
-            rpm --addsign "${rpm}"
-          done
-
-      - name: Set up SSH for rsync
-        run: |
-          install --directory --mode 700 ~/.ssh
-          echo "${RSYNC_SSH_KEY}" | install --mode 600 /dev/stdin ~/.ssh/id_ed25519
-        env:
-          RSYNC_SSH_KEY: ${{ secrets.RSYNC_SSH_KEY }}
-
-      - name: Test SSH connectivity
-        run: |
-          ssh -o StrictHostKeyChecking=accept-new "gitea_ci@${RPM_REPO_HOST}" exit
-
-      - name: Ensure unstable repo directory exists
-        run: |
-          ssh "gitea_ci@${RPM_REPO_HOST}" \
-            "mkdir --parents /var/www/rpm/fedora/${FEDORA_VERSION}/x86_64/unstable"
-
-      - name: Sync RPMs to unstable repo
-        run: |
-          rsync \
-            --archive \
-            --verbose \
-            --chmod D755,F644 \
-            rpms/*.rpm \
-            "gitea_ci@${RPM_REPO_HOST}:/var/www/rpm/fedora/${FEDORA_VERSION}/x86_64/unstable/"
-
-      - name: Update unstable repo metadata
-        run: |
-          ssh "gitea_ci@${RPM_REPO_HOST}" \
-            "cd /var/www/rpm/fedora/${FEDORA_VERSION}/x86_64/unstable && createrepo_c --update ."
-
-      - name: Generate packages.json manifest
-        run: |
-          scp script/generate-packages-json.py "gitea_ci@${RPM_REPO_HOST}:/tmp/"
-          ssh "gitea_ci@${RPM_REPO_HOST}" \
-            "python3 /tmp/generate-packages-json.py \
-              --repodata-dir /var/www/rpm/fedora/${FEDORA_VERSION}/x86_64/unstable/repodata \
-              --output /var/www/rpm/fedora/${FEDORA_VERSION}/x86_64/unstable/packages.json \
-              --base-url https://rpm.lair.cafe/fedora/${FEDORA_VERSION}/x86_64/unstable"
--- a/.gitea/workflows/ci.yml
+++ b/.gitea/workflows/ci.yml
@@ -16,42 +16,40 @@ env:
  SCCACHE_S3_USE_SSL: "false"
  AWS_ACCESS_KEY_ID: ${{ secrets.SCCACHE_S3_ACCESS_KEY }}
  AWS_SECRET_ACCESS_KEY: ${{ secrets.SCCACHE_S3_SECRET_KEY }}
-  # fmt, clippy, and test all run in parallel on the same `rust` runner
-  # and would otherwise share /root/.cache/act/<hash>/hostexecutor/target/,
-  # racing each other's cargo temp files (.tmpXXXXXX) and failing builds
-  # mid-compile. Give each job its own target directory so the invocations
-  # don't collide. sccache still backs the actual rustc cache, so the
-  # rebuild penalty is small.
-  CARGO_TARGET_DIR: target-${{ github.job }}

 jobs:
-  fmt:
-    name: Format
-    runs-on: rust
+  check:
+    name: Format, lint, build, test
+    runs-on: fedora
    steps:
      - uses: actions/checkout@v4
-      - run: cargo fmt --check --all

-  clippy:
-    name: Clippy
-    runs-on: rust
-    steps:
-      - uses: actions/checkout@v4
-      - run: cargo clippy --workspace -- -D warnings
-      - run: sccache --show-stats
+      - name: Ensure sccache with S3 support
+        env:
+          RUSTC_WRAPPER: ""
+        run: |
+          if sccache --version 2>/dev/null && sccache --show-stats 2>/dev/null; then
+            echo "sccache with S3 support already installed"
+          else
+            cargo install sccache --features s3 --locked
+          fi

-  test:
-    name: Test
-    runs-on: rust
-    steps:
-      - uses: actions/checkout@v4
-      - run: cargo test --workspace
-      - run: sccache --show-stats
+      - name: Check formatting
+        run: cargo fmt --check --all
+
+      - name: Clippy
+        run: cargo clippy --workspace -- -D warnings
+
+      - name: Test
+        run: cargo test --workspace
+
+      - name: Show sccache stats
+        run: sccache --show-stats

  srpm-cortex:
    name: Build cortex SRPM
-    runs-on: rpm
-    needs: [fmt, clippy, test]
+    runs-on: fedora
+    needs: check
    if: startsWith(github.ref, 'refs/tags/v')
    steps:
      - uses: actions/checkout@v4
@@ -110,8 +108,8 @@ jobs:

  srpm-neuron:
    name: Build neuron SRPM
-    runs-on: rpm
-    needs: [fmt, clippy, test]
+    runs-on: fedora
+    needs: check
    if: startsWith(github.ref, 'refs/tags/v')
    steps:
      - uses: actions/checkout@v4
@@ -170,7 +168,7 @@ jobs:

  copr-cortex:
    name: Publish cortex to COPR
-    runs-on: fedora-43
+    runs-on: fedora
    needs: srpm-cortex
    steps:
      - name: Download SRPM
@@ -187,7 +185,7 @@ jobs:

  copr-neuron:
    name: Publish neuron to COPR
-    runs-on: fedora-43
+    runs-on: fedora
    needs: srpm-neuron
    steps:
      - name: Download SRPM
@@ -204,7 +202,7 @@ jobs:

  bump-version:
    name: Bump version in source
-    runs-on: rust
+    runs-on: fedora
    needs: [copr-cortex, copr-neuron]
    steps:
      - uses: actions/checkout@v4
--- a/.gitignore
+++ b/.gitignore
@@ -5,4 +5,3 @@
 .vscode/
 cortex.toml
 doc/plan/*
-script/deploy.sh
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -616,45 +616,58 @@ dnf install cortex                # gateway host
 dnf install helexa-neuron         # GPU nodes
 ```

-## 2026-05-18 addendum: candle-native pivot
+### Phase 11: llama.cpp harness stub

-Phases 11 (llama.cpp harness) and 12 (mistral.rs COPR) below are
-**superseded**. The project no longer treats mistral.rs or llama.cpp as
-dependencies — both are conceptually out of scope. neuron becomes a
-candle-native inference daemon, with `Harness` retained as an
-internal seam for adding future engines (vision/audio/diffusion) but
-its only implementation being in-process candle.
+**Goal:** Prove the harness abstraction works with a second engine.

-The full staged plan for this pivot lives at
-`~/.claude/plans/create-a-more-aggressive-calm-naur.md`. Summary:
+**Steps:**
+1. `crates/neuron/src/harness/llamacpp.rs` — implement the `Harness`
+   trait for llama.cpp's `llama-server`.
+   - `start()` — launch `llama-server` with the correct model path,
+     `--port`, `--n-gpu-layers`, `--tensor-split` args. Track the
+     child process.
+   - `stop()` — send SIGTERM to the child process.
+   - `list_models()` — llama-server serves one model per process, so
+     return a single-element list.
+   - `load_model()` — start a new llama-server process for this model.
+   - `unload_model()` — stop the process.
+   - `inference_endpoint()` — return `http://localhost:{assigned_port}`.
+2. Port allocation: neuron assigns ports from a range (e.g. 8100-8199)
+   to llama-server instances.
+3. Register in `HarnessRegistry` when configured:
+   ```toml
+   [[harnesses]]
+   name = "llamacpp"
+   binary = "/usr/local/bin/llama-server"
+   port_range = [8100, 8199]
+   ```
+4. Tests: mock llama-server (simple HTTP server returning canned
+   responses), test load/unload/endpoint lifecycle.

- **Stage 1 (this commit):** delete `mistralrs.rs` and `llamacpp.rs`,
-  scaffold inert `CandleHarness`, drop `endpoint`/`systemd_unit` from
-  `HarnessConfig`, default no-op `start`/`stop` on the `Harness` trait.
- **Stages 2–4:** wire up candle model load/unload (quantized Qwen3
-  first), add OpenAI-compatible inference endpoint in neuron, then SSE
-  streaming.
- **Stages 5–6:** load-on-activation (default models in config) and
-  unload-on-deactivation (graceful shutdown).
- **Stages 7–8:** multi-GPU tensor parallelism and broader model/quant
-  coverage.
+**Done when:** A model with `harness = "llamacpp"` in `models.toml` can
+be loaded and served through cortex. Tests pass with mock llama-server.

-Sections of this document that describe mistral.rs HTTP behaviour
-("mistral.rs API gotchas") are retained as historical context for
-Phases 1–10 — they document what was true while the project depended
-on mistral.rs. They do not describe current behaviour.
+### Phase 12 (lower priority): mistral.rs COPR packaging

---
+**Goal:** Fedora RPMs for mistral.rs built against specific CUDA versions.

-### Phase 11 (superseded): llama.cpp harness stub
+**Steps:**
+1. `mistralrs-cuda.spec` — RPM spec that clones a pinned mistral.rs git
+   tag, builds with `--features cuda`, links against the system CUDA
+   toolkit. Produces `mistralrs-cuda13-server` (CUDA 13.x / sm_120) and
+   `mistralrs-cuda12-server` (CUDA 12.x / sm_89). Install binary to
+   `/usr/local/bin/mistralrs`.
+2. COPR build config: enable the NVIDIA CUDA repo as a build dependency.
+   Pin the CUDA toolkit version in `BuildRequires`.
+3. Gitea Actions or manual workflow: bump the mistral.rs tag in the spec,
+   trigger COPR rebuild.
+4. neuron's mistralrs harness config references which binary/package
+   provides the mistral.rs binary. neuron could warn at startup if the
+   installed mistral.rs CUDA version doesn't match the discovered driver.

-~~Originally planned as a second engine to prove the harness
-abstraction.~~ Replaced by the candle harness work in the 2026-05-18
-addendum above. llama.cpp's any-model/any-hardware breadth is no
-longer in scope for helexa.
+**Done when:** `dnf install mistralrs-cuda13-server` on beast provides a
+working `mistralrs` binary built for Blackwell GPUs. `dnf install
+mistralrs-cuda12-server` on benjy provides one built for Ada GPUs.

-### Phase 12 (superseded): mistral.rs COPR packaging
-
-~~Originally planned to ship CUDA-versioned mistral.rs RPMs.~~ Replaced
-by the candle harness work in the 2026-05-18 addendum above. With
-mistral.rs out of the dependency tree, there is nothing to package.
+This is a separate repo/spec — not part of the cortex workspace — but
+tightly coupled operationally. Track it as a sibling project.
--- a/Cargo.lock
+++ b/Cargo.lock
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -8,7 +8,7 @@ members = [
 ]

 [workspace.package]
-version = "0.1.16"
+version = "0.1.12"
 edition = "2024"
 license = "GPL-3.0-or-later"
 repository = "https://git.lair.cafe/helexa/cortex"
@@ -27,7 +27,7 @@ serde = { version = "1", features = ["derive"] }
 serde_json = "1"
 toml = "0.8"

-# http client (for proxying to neuron backends)
+# http client (for proxying to mistralrs backends)
 reqwest = { version = "0.12", features = ["json", "stream"] }

 # observability
--- a/README.md
+++ b/README.md
@@ -1,23 +1,22 @@
 # cortex

-A Rust reverse-proxy and fleet management layer for multi-node GPU inference
-clusters. Cortex sits in front of one or more `neuron` daemons (each running
-candle-based inference on a local GPU host) and presents a unified OpenAI +
-Anthropic compatible API surface.
+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 that can be
-  served by any neuron in the fleet.
- **Routes requests** to the correct node based on where a model is loaded
-  (or can be loaded), handling cold-load and eviction transparently.
- Manages **model lifecycle** — load on demand, unload cold models, pin
-  critical ones — by calling each neuron's `/models/{load,unload}` API.
+- 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 speaks whichever dialect it prefers.
+  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.

@@ -31,17 +30,18 @@ model affinities) requires a unified API surface that:
       └────────────────┴──────┬───────┴───────────────┘
                               │
                    ┌──────────▼──────────┐
-                    │      cortex         │
-                    │  (cortex-gateway)   │
+                    │   cortex     │
+                    │   (cortex-gateway)      │
                    │                     │
                    │  Router · Metrics   │
                    │  Evictor · Translate│
                    └──┬──────┬────────┬──┘
                       │      │        │
            ┌──────────▼┐  ┌──▼─────┐  ┌▼──────────┐
-            │  neuron   │  │ neuron │  │  neuron   │
-            │  :13131   │  │ :13131 │  │  :13131   │
-            │  candle   │  │ candle │  │  candle   │
+            │ gpu-large │  │gpu-med │  │ gpu-small │
+            │ mistralrs │  │mistral │  │ mistralrs │
+            │ serve     │  │rs serve│  │ serve     │
+            │ :8080     │  │ :8080  │  │  :8080    │
            └───────────┘  └────────┘  └───────────┘
                  private network (.internal)
 ```
@@ -50,29 +50,43 @@ model affinities) requires a unified API surface that:

 | Crate | Purpose |
 |---|---|
-| `cortex-core` | Shared types: config, node/model state, metrics, OpenAI/Anthropic envelopes, harness trait, discovery types |
-| `cortex-gateway` | Axum HTTP server: proxy, router, evictor, poller, metrics exporter |
-| `neuron` | Per-node daemon: GPU discovery, in-process candle inference, model lifecycle API |
+| `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 `neuron` (listening on `:13131`). Neuron uses
-huggingface/candle for in-process inference — there is no external
-inference subprocess to manage.
+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.

-The neuron RPM (`helexa-neuron`) ships a systemd unit:
+Example node systemd unit:

-```sh
-dnf copr enable helexa/helexa
-dnf install helexa-neuron
-systemctl enable --now neuron
+```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
-# /etc/cortex/cortex.toml
+# cortex.toml
 [gateway]
 listen = "0.0.0.0:31313"
 metrics_listen = "0.0.0.0:31314"
@@ -81,17 +95,25 @@ metrics_listen = "0.0.0.0:31314"
 strategy = "lru"        # lru | priority
 defrag_after_cycles = 50

-[[neurons]]
-name = "beast"
-endpoint = "http://beast.internal:13131"
+[[nodes]]
+name = "gpu-large"
+endpoint = "http://gpu-large.internal:8080"
+vram_mb = 49_152        # e.g. 2x RTX 4090
+pinned = ["your-org/large-model"]

-[[neurons]]
-name = "benjy"
-endpoint = "http://benjy.internal:13131"
+[[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"]
 ```

-Model placement profiles live in `models.toml` — see `models.example.toml`.
-
 ## Building

 ```sh
@@ -109,14 +131,13 @@ cargo clippy --workspace -- -D warnings   # warnings are errors
 cargo test --workspace                     # all tests must pass
 ```

-Tagged releases (`v*`) additionally build SRPMs for both `cortex` and
-`helexa-neuron` and publish to COPR.
+Tagged releases (`v*`) additionally build an SRPM and publish to COPR.

 ## Running

 ```sh
 # start the gateway
-cortex serve --config /etc/cortex/cortex.toml
+cortex serve --config cortex.toml

 # check fleet status
 cortex status
--- a/asset/manifest.yml
+++ b/asset/manifest.yml
@@ -1,30 +0,0 @@
-# Helexa fleet manifest.
-#
-# Drives rolling deploys via script/deploy.sh and serves as the source
-# of truth for which hosts run cortex vs neuron, and which CUDA
-# compute-capability flavour each neuron host needs.
-#
-# Flavour ↔ NVIDIA generation ↔ compute cap:
-#   ampere    sm_86   (RTX 30 series — e.g. 3060)
-#   ada       sm_89   (RTX 40 series — e.g. 4090)
-#   blackwell sm_120  (RTX 50 series — e.g. 5090)
-#
-# The flavour determines which RPM is installed on a given neuron host:
-# helexa-neuron-<flavour>. Only one flavour may be installed at a time
-# (the packages Conflict: with each other).
-
-cortex:
-  host: hanzalova.internal
-
-neurons:
-  - host: beast.hanzalova.internal
-    flavour: blackwell
-    gpu: "2x RTX 5090"
-
-  - host: benjy.hanzalova.internal
-    flavour: ada
-    gpu: "RTX 4090"
-
-  - host: quadbrat.hanzalova.internal
-    flavour: ampere
-    gpu: "RTX 3060"
--- a/cortex.example.toml
+++ b/cortex.example.toml
@@ -11,14 +11,14 @@ metrics_listen = "0.0.0.0:31314"

 [eviction]
 strategy = "lru"
-# Restart neurons after this many load/unload cycles to defragment VRAM.
+# 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 neuron daemon in the fleet.
-# Models are discovered by polling the neuron's /models endpoint.
-# Pinned models (see models.toml) are never evicted.
+# 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"
--- a/cortex.spec
+++ b/cortex.spec
@@ -1,5 +1,5 @@
 Name:           cortex
-Version:        0.1.16
+Version:        0.1.12
 Release:        1%{?dist}
 Summary:        Inference gateway for multi-node GPU clusters

@@ -21,7 +21,6 @@ BuildRequires:  systemd-rpm-macros

 Requires(pre):  shadow-utils
 Requires:       systemd
-Requires:       firewalld-filesystem

 # systemd-rpm-macros ships a unit dep generator that parses User=/Group=
 # from our .service file and emits Requires: user(cortex)/group(cortex).
@@ -57,7 +56,6 @@ cargo build --release -p cortex-cli
 install -Dm755 target/release/cortex %{buildroot}%{_bindir}/cortex
 install -Dm644 data/cortex.service %{buildroot}%{_unitdir}/cortex.service
 install -Dm644 data/cortex-sysusers.conf %{buildroot}%{_sysusersdir}/cortex.conf
-install -Dm644 data/cortex-firewalld.xml %{buildroot}%{_prefix}/lib/firewalld/services/cortex.xml
 install -dm755 %{buildroot}%{_sysconfdir}/cortex
 install -Dm644 cortex.example.toml %{buildroot}%{_sysconfdir}/cortex/cortex.toml
 install -Dm644 models.example.toml %{buildroot}%{_sysconfdir}/cortex/models.toml
@@ -80,21 +78,10 @@ install -Dm644 models.example.toml %{buildroot}%{_sysconfdir}/cortex/models.toml
 %{_bindir}/cortex
 %{_unitdir}/cortex.service
 %{_sysusersdir}/cortex.conf
-%{_prefix}/lib/firewalld/services/cortex.xml
 %dir %{_sysconfdir}/cortex
 %config(noreplace) %{_sysconfdir}/cortex/cortex.toml
 %config(noreplace) %{_sysconfdir}/cortex/models.toml

 %changelog
-* Thu Apr 16 2026 Gitea Actions <actions@git.lair.cafe> - 0.1.16-1
- chore: ignore local deploy script
- chore: move default ports out of common-collision ranges
- ci: drop actions/cache for cargo registry and target
-
-* Thu Apr 16 2026 Gitea Actions <actions@git.lair.cafe> - 0.1.14-1
- ci: publish both packages to a single helexa/helexa COPR project
- fix(rpm): rename neuron package to helexa-neuron
- ci: commit generated %changelog entries back to main
-
 * Wed Apr 15 2026 Rob Thijssen <grenade@rob.tn> - 0.1.0-1
 - Initial package
--- a/crates/cortex-cli/src/main.rs
+++ b/crates/cortex-cli/src/main.rs
@@ -5,7 +5,7 @@ use tracing_subscriber::EnvFilter;

 #[derive(Parser)]
 #[command(name = "cortex")]
-#[command(about = "Unified inference gateway for multi-node GPU clusters")]
+#[command(about = "Unified inference gateway for multi-node mistral.rs clusters")]
 #[command(version)]
 struct Cli {
    #[command(subcommand)]
--- a/crates/cortex-core/src/anthropic.rs
+++ b/crates/cortex-core/src/anthropic.rs
@@ -2,7 +2,7 @@
 //!
 //! These mirror the `/v1/messages` format used by the Anthropic API.
 //! The gateway accepts these, translates to OpenAI format, proxies to
-//! the inference backend (neuron), then translates the response back.
+//! mistral.rs, then translates the response back.

 use serde::{Deserialize, Serialize};
 use serde_json::Value;
--- a/crates/cortex-core/src/harness.rs
+++ b/crates/cortex-core/src/harness.rs
@@ -9,13 +9,13 @@ use async_trait::async_trait;
 use serde::{Deserialize, Serialize};

 /// Configuration for a harness instance on a neuron.
-///
-/// All current harnesses are in-process (candle); per-harness tuning
-/// (cache paths, device policies, etc.) lives in dedicated config
-/// blocks rather than on this struct.
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct HarnessConfig {
    pub name: String,
+    /// Base URL of the harness (e.g. "http://localhost:8080" for mistral.rs).
+    pub endpoint: Option<String>,
+    /// Systemd unit name, if the harness is managed via systemd.
+    pub systemd_unit: Option<String>,
 }

 /// Health status of a harness process.
@@ -47,24 +47,16 @@ pub struct ModelInfo {
 }

 /// What an inference harness must do, from neuron's perspective.
-///
-/// All current harnesses are in-process — they share neuron's address
-/// space and lifecycle. `start`/`stop` therefore default to no-ops; a
-/// future process-supervising harness would override them.
 #[async_trait]
 pub trait Harness: Send + Sync {
-    /// Human-readable name (e.g. "candle").
+    /// Human-readable name (e.g. "mistralrs", "llamacpp", "comfyui").
    fn name(&self) -> &str;

-    /// Start the harness. Default no-op for in-process harnesses.
-    async fn start(&self, _config: &HarnessConfig) -> Result<()> {
-        Ok(())
-    }
+    /// Start the harness process if it is not already running.
+    async fn start(&self, config: &HarnessConfig) -> Result<()>;

-    /// Stop the harness. Default no-op for in-process harnesses.
-    async fn stop(&self) -> Result<()> {
-        Ok(())
-    }
+    /// Stop the harness process gracefully.
+    async fn stop(&self) -> Result<()>;

    /// Health check. Returns the harness process status.
    async fn health(&self) -> HarnessHealth;
--- a/crates/cortex-core/src/openai.rs
+++ b/crates/cortex-core/src/openai.rs
@@ -3,7 +3,7 @@
 //! 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 a backend might support.
+//! extension field mistral.rs supports.

 use serde::{Deserialize, Serialize};
 use serde_json::Value;
@@ -22,7 +22,7 @@ pub struct ChatCompletionRequest {
    pub max_tokens: Option<u64>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub stream: Option<bool>,
-    /// All other fields (tools, response_format, backend extensions, etc.)
+    /// All other fields (tools, response_format, mistral.rs extensions, etc.)
    #[serde(flatten)]
    pub extra: Value,
 }
--- a/crates/cortex-gateway/src/proxy.rs
+++ b/crates/cortex-gateway/src/proxy.rs
@@ -1,4 +1,4 @@
-//! Streaming HTTP reverse proxy to neuron backends.
+//! 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
--- a/crates/cortex-gateway/tests/common/mod.rs
+++ b/crates/cortex-gateway/tests/common/mod.rs
@@ -22,7 +22,6 @@ use tokio::net::TcpListener;
 /// - GET /models/:id/endpoint (returns the inference URL)
 /// - POST /models/unload (accepts unload requests)
 /// - GET /v1/chat/completions + POST /v1/chat/completions (inference)
-///
 /// Returns the neuron base URL.
 pub async fn spawn_mock_neuron() -> String {
    let listener = TcpListener::bind("127.0.0.1:0").await.unwrap();
@@ -55,7 +54,7 @@ pub async fn spawn_mock_neuron() -> String {

 async fn mock_neuron_list_models() -> Json<Value> {
    Json(json!([
-        {"id": "test-model", "harness": "candle", "status": "loaded", "devices": [0], "vram_used_mb": 8000}
+        {"id": "test-model", "harness": "mistralrs", "status": "loaded", "devices": [0], "vram_used_mb": 8000}
    ]))
 }

--- a/crates/cortex-gateway/tests/poller.rs
+++ b/crates/cortex-gateway/tests/poller.rs
@@ -12,8 +12,8 @@ use std::sync::Arc;
 async fn test_poller_discovers_models() {
    // Mock neuron reports 2 models via /models endpoint (neuron format).
    let mock_url = common::spawn_mock_neuron_with_models(json!([
-        {"id": "model-a", "harness": "candle", "status": "loaded", "devices": [0], "vram_used_mb": 8000},
-        {"id": "model-b", "harness": "candle", "status": "unloaded", "devices": [], "vram_used_mb": null}
+        {"id": "model-a", "harness": "mistralrs", "status": "loaded", "devices": [0], "vram_used_mb": 8000},
+        {"id": "model-b", "harness": "mistralrs", "status": "unloaded", "devices": [], "vram_used_mb": null}
    ]))
    .await;

@@ -63,8 +63,8 @@ async fn test_poller_discovers_models() {
 #[tokio::test]
 async fn test_poller_updates_gateway_models_endpoint() {
    let mock_url = common::spawn_mock_neuron_with_models(json!([
-        {"id": "model-x", "harness": "candle", "status": "loaded", "devices": [0], "vram_used_mb": null},
-        {"id": "model-y", "harness": "candle", "status": "loaded", "devices": [1], "vram_used_mb": null}
+        {"id": "model-x", "harness": "mistralrs", "status": "loaded", "devices": [0], "vram_used_mb": null},
+        {"id": "model-y", "harness": "mistralrs", "status": "loaded", "devices": [1], "vram_used_mb": null}
    ]))
    .await;

@@ -152,8 +152,8 @@ async fn test_poller_marks_unreachable_node_unhealthy() {
 #[tokio::test]
 async fn test_poller_removes_stale_models() {
    let mock_url = common::spawn_mock_neuron_with_models(json!([
-        {"id": "keep-me", "harness": "candle", "status": "loaded", "devices": [0], "vram_used_mb": null},
-        {"id": "drop-me", "harness": "candle", "status": "loaded", "devices": [0], "vram_used_mb": null}
+        {"id": "keep-me", "harness": "mistralrs", "status": "loaded", "devices": [0], "vram_used_mb": null},
+        {"id": "drop-me", "harness": "mistralrs", "status": "loaded", "devices": [0], "vram_used_mb": null}
    ]))
    .await;

@@ -183,7 +183,7 @@ async fn test_poller_removes_stale_models() {

    // New mock with only one model.
    let new_mock_url = common::spawn_mock_neuron_with_models(json!([
-        {"id": "keep-me", "harness": "candle", "status": "loaded", "devices": [0], "vram_used_mb": null}
+        {"id": "keep-me", "harness": "mistralrs", "status": "loaded", "devices": [0], "vram_used_mb": null}
    ]))
    .await;

--- a/crates/cortex-gateway/tests/streaming.rs
+++ b/crates/cortex-gateway/tests/streaming.rs
@@ -51,18 +51,18 @@ async fn test_streaming_sse_passthrough() {
    }

    assert!(
-        chunks.len() > chunk_count,
-        "expected more than {} chunks (got {}): {:?}",
-        chunk_count,
+        chunks.len() >= chunk_count + 1,
+        "expected at least {} chunks (got {}): {:?}",
+        chunk_count + 1,
        chunks.len(),
        chunks,
    );

    assert_eq!(chunks.last().unwrap(), "[DONE]");

-    for (i, chunk) in chunks.iter().enumerate().take(chunk_count) {
+    for i in 0..chunk_count {
        let chunk_json: serde_json::Value =
-            serde_json::from_str(chunk).expect("chunk should be valid JSON");
+            serde_json::from_str(&chunks[i]).expect("chunk should be valid JSON");
        assert_eq!(
            chunk_json["choices"][0]["delta"]["content"],
            format!("token{i}")
--- a/crates/neuron/Cargo.toml
+++ b/crates/neuron/Cargo.toml
@@ -12,30 +12,6 @@ path = "src/lib.rs"
 name = "neuron"
 path = "src/main.rs"

-[features]
-default = []
-# Enables CUDA acceleration in candle. Without this feature, candle
-# compiles for CPU only and Device::new_cuda calls fall back to CPU.
-cuda = [
-    "candle-core/cuda",
-    "candle-nn/cuda",
-    "candle-transformers/cuda",
-]
-# Use cuDNN for convolution / attention kernels. Requires CUDA.
-cudnn = [
-    "cuda",
-    "candle-core/cudnn",
-    "candle-nn/cudnn",
-    "candle-transformers/cudnn",
-]
-# FlashAttention kernels. Requires CUDA.
-flash-attn = [
-    "cuda",
-    "candle-transformers/flash-attn",
-]
-# Reserved for GPU-only integration tests in later stages.
-cuda-integration = ["cuda"]
-
 [dependencies]
 cortex-core.workspace = true
 tokio.workspace = true
@@ -48,19 +24,9 @@ tracing-subscriber.workspace = true
 anyhow.workspace = true
 async-trait.workspace = true
 clap.workspace = true
-thiserror.workspace = true
 figment.workspace = true
 toml.workspace = true

-# candle for in-process inference. CUDA support is gated behind the
-# crate's `cuda` feature (default off) so the workspace builds on
-# non-CUDA hosts and CI runners.
-candle-core = "0.10.2"
-candle-nn = "0.10.2"
-candle-transformers = "0.10.2"
-tokenizers = { version = "0.22", default-features = false, features = ["onig"] }
-hf-hub = { version = "0.4", features = ["tokio"] }
-
 [dev-dependencies]
 tokio = { workspace = true, features = ["test-util"] }
 reqwest.workspace = true
--- a/crates/neuron/src/api.rs
+++ b/crates/neuron/src/api.rs
@@ -1,7 +1,6 @@
 //! HTTP API handlers for the neuron daemon.

 use crate::harness::HarnessRegistry;
-use crate::harness::candle::{CandleHarness, InferenceError};
 use crate::health::HealthCache;
 use axum::Router;
 use axum::extract::{Path, State};
@@ -10,7 +9,6 @@ use axum::response::{IntoResponse, Json};
 use axum::routing::{get, post};
 use cortex_core::discovery::{DiscoveryResponse, HealthResponse};
 use cortex_core::harness::ModelSpec;
-use cortex_core::openai::ChatCompletionRequest;
 use serde_json::{Value, json};
 use std::sync::Arc;
 use tokio::sync::RwLock;
@@ -20,10 +18,6 @@ pub struct NeuronState {
    pub discovery: DiscoveryResponse,
    pub health_cache: Arc<HealthCache>,
    pub registry: RwLock<HarnessRegistry>,
-    /// Typed handle to the candle harness for inference routes. Cached at
-    /// startup so `/v1/chat/completions` doesn't have to hold the registry
-    /// read lock or perform dyn-Trait dispatch per request.
-    pub candle: Option<Arc<CandleHarness>>,
 }

 /// Build the neuron API router.
@@ -35,7 +29,6 @@ pub fn neuron_routes() -> Router<Arc<NeuronState>> {
        .route("/models/load", post(load_model))
        .route("/models/unload", post(unload_model))
        .route("/models/{model_id}/endpoint", get(model_endpoint))
-        .route("/v1/chat/completions", post(chat_completions))
 }

 async fn discovery_handler(State(state): State<Arc<NeuronState>>) -> Json<DiscoveryResponse> {
@@ -109,40 +102,3 @@ async fn model_endpoint(
            .into_response(),
    }
 }
-
-/// OpenAI-compatible chat completions. Non-streaming for Stage 3; the
-/// streaming path is added in Stage 4.
-async fn chat_completions(
-    State(state): State<Arc<NeuronState>>,
-    Json(req): Json<ChatCompletionRequest>,
-) -> impl IntoResponse {
-    let Some(candle) = state.candle.as_ref().map(Arc::clone) else {
-        return (
-            StatusCode::SERVICE_UNAVAILABLE,
-            Json(json!({"error": "candle harness not enabled on this neuron"})),
-        )
-            .into_response();
-    };
-
-    if req.stream.unwrap_or(false) {
-        return (
-            StatusCode::NOT_IMPLEMENTED,
-            Json(json!({"error": "streaming responses arrive in Stage 4"})),
-        )
-            .into_response();
-    }
-
-    match candle.chat_completion(req).await {
-        Ok(resp) => Json(resp).into_response(),
-        Err(InferenceError::ModelNotLoaded(id)) => (
-            StatusCode::NOT_FOUND,
-            Json(json!({"error": format!("model '{id}' not loaded on this neuron")})),
-        )
-            .into_response(),
-        Err(InferenceError::Other(e)) => (
-            StatusCode::INTERNAL_SERVER_ERROR,
-            Json(json!({"error": e.to_string()})),
-        )
-            .into_response(),
-    }
-}
--- a/crates/neuron/src/config.rs
+++ b/crates/neuron/src/config.rs
@@ -6,7 +6,7 @@ use figment::{
    providers::{Env, Format, Toml},
 };
 use serde::{Deserialize, Serialize};
-use std::path::{Path, PathBuf};
+use std::path::Path;

 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct NeuronConfig {
@@ -14,25 +14,6 @@ pub struct NeuronConfig {
    pub port: u16,
    #[serde(default)]
    pub harnesses: Vec<HarnessConfig>,
-    /// Per-harness configuration. Currently only `candle` is recognised.
-    #[serde(default)]
-    pub harness: HarnessSettings,
-}
-
-/// Settings for individual harness implementations. Each harness owns
-/// its own sub-table so users only configure the harnesses they enable.
-#[derive(Debug, Clone, Default, Serialize, Deserialize)]
-pub struct HarnessSettings {
-    #[serde(default)]
-    pub candle: CandleHarnessConfig,
-}
-
-#[derive(Debug, Clone, Default, Serialize, Deserialize)]
-pub struct CandleHarnessConfig {
-    /// HuggingFace cache directory for model weights.
-    /// When unset, defers to hf-hub's default (~/.cache/huggingface).
-    #[serde(default)]
-    pub hf_cache: Option<PathBuf>,
 }

 fn default_port() -> u16 {
@@ -54,7 +35,6 @@ impl Default for NeuronConfig {
        Self {
            port: 13131,
            harnesses: vec![],
-            harness: HarnessSettings::default(),
        }
    }
 }
--- a/crates/neuron/src/harness/candle.rs
+++ b/crates/neuron/src/harness/candle.rs
@@ -1,441 +0,0 @@
-//! Candle harness — in-process inference using huggingface/candle.
-//!
-//! This is the sole `Harness` implementation. Inference runs inside
-//! the neuron process; there is no external subprocess.
-//!
-//! - Stage 2 wired GGUF (Qwen3 only) load/unload via `quantized_qwen3`.
-//! - Stage 3 (this) adds `chat_completion` — a non-streaming OpenAI
-//!   compatible chat completion routed to the loaded model's forward
-//!   pass on a per-model serialised generation loop.
-
-use anyhow::{Context, Result};
-use async_trait::async_trait;
-use candle_core::quantized::gguf_file;
-use candle_core::{Device, Tensor};
-use candle_transformers::generation::{LogitsProcessor, Sampling};
-use candle_transformers::models::quantized_qwen3::ModelWeights as QuantizedQwen3Weights;
-use cortex_core::harness::{Harness, HarnessHealth, ModelInfo, ModelSpec};
-use cortex_core::openai::{
-    ChatCompletionChoice, ChatCompletionRequest, ChatCompletionResponse, ChatMessage,
-    MessageContent, Usage,
-};
-use std::collections::HashMap;
-use std::path::PathBuf;
-use std::sync::Arc;
-use std::time::{SystemTime, UNIX_EPOCH};
-use tokenizers::Tokenizer;
-use tokio::sync::{Mutex, RwLock};
-
-/// In-process candle harness. Owns the loaded model registry.
-pub struct CandleHarness {
-    models: Arc<RwLock<HashMap<String, Arc<LoadedModel>>>>,
-    hf_cache: Option<PathBuf>,
-    bind_url: String,
-}
-
-/// A loaded model with its tokenizer, device placement, and architecture-
-/// specific weights. The `arch` is `Arc<Mutex<>>` so the lock guard can be
-/// moved into `spawn_blocking` for synchronous candle forward passes.
-pub struct LoadedModel {
-    pub model_id: String,
-    pub arch: Arc<Mutex<ModelArch>>,
-    pub tokenizer: Tokenizer,
-    pub device: Device,
-    pub quant: Option<String>,
-    pub devices: Vec<u32>,
-}
-
-/// Architecture-specific weights. Stage 3 still supports only Qwen3
-/// quantized; Stage 8 broadens this to additional families and
-/// non-quantized variants.
-pub enum ModelArch {
-    Qwen3Quantized(QuantizedQwen3Weights),
-}
-
-impl CandleHarness {
-    pub fn new(bind_url: String, hf_cache: Option<PathBuf>) -> Self {
-        Self {
-            models: Arc::new(RwLock::new(HashMap::new())),
-            hf_cache,
-            bind_url,
-        }
-    }
-
-    /// Pick a candle `Device` for the requested indices. Without the
-    /// `cuda` feature, or if CUDA initialisation fails, falls back to CPU.
-    fn pick_device(devices: &[u32]) -> Result<Device> {
-        let _idx = devices.first().copied().unwrap_or(0) as usize;
-        #[cfg(feature = "cuda")]
-        {
-            match Device::new_cuda(_idx) {
-                Ok(d) => return Ok(d),
-                Err(e) => tracing::warn!(
-                    device = _idx,
-                    error = %e,
-                    "CUDA device unavailable, falling back to CPU"
-                ),
-            }
-        }
-        Ok(Device::Cpu)
-    }
-
-    /// Resolve a model spec to local GGUF and tokenizer file paths via
-    /// hf-hub. Downloads on first use; subsequent calls are cached.
-    async fn resolve_files(&self, spec: &ModelSpec) -> Result<(PathBuf, PathBuf)> {
-        let mut builder = hf_hub::api::tokio::ApiBuilder::new();
-        if let Some(cache) = &self.hf_cache {
-            builder = builder.with_cache_dir(cache.clone());
-        }
-        let api = builder.build().context("build hf-hub API")?;
-        let repo = api.model(spec.model_id.clone());
-
-        let info = repo
-            .info()
-            .await
-            .with_context(|| format!("fetch HF repo info for {}", spec.model_id))?;
-
-        let quant = spec.quant.as_deref().unwrap_or("");
-        let quant_lc = quant.to_lowercase();
-        let gguf_filename = info
-            .siblings
-            .iter()
-            .map(|s| s.rfilename.as_str())
-            .filter(|name| name.to_lowercase().ends_with(".gguf"))
-            .find(|name| quant_lc.is_empty() || name.to_lowercase().contains(&quant_lc))
-            .ok_or_else(|| {
-                anyhow::anyhow!(
-                    "no GGUF file matching quant {:?} in repo {}",
-                    spec.quant,
-                    spec.model_id
-                )
-            })?
-            .to_string();
-
-        tracing::info!(
-            model = %spec.model_id,
-            file = %gguf_filename,
-            "resolving GGUF (may be cached)"
-        );
-        let gguf_path = repo
-            .get(&gguf_filename)
-            .await
-            .with_context(|| format!("fetch GGUF {gguf_filename}"))?;
-        let tokenizer_path = repo
-            .get("tokenizer.json")
-            .await
-            .context("fetch tokenizer.json")?;
-        Ok((gguf_path, tokenizer_path))
-    }
-
-    /// Run a non-streaming chat completion against a loaded model.
-    ///
-    /// Returns a typed `InferenceError` when the model isn't loaded so the
-    /// handler can map to an appropriate HTTP status without string-matching.
-    pub async fn chat_completion(
-        &self,
-        request: ChatCompletionRequest,
-    ) -> Result<ChatCompletionResponse, InferenceError> {
-        let loaded = {
-            let models = self.models.read().await;
-            models.get(&request.model).cloned()
-        };
-        let loaded = loaded.ok_or_else(|| InferenceError::ModelNotLoaded(request.model.clone()))?;
-
-        let prompt = format_qwen3_prompt(&request.messages);
-
-        let encoding = loaded
-            .tokenizer
-            .encode(prompt.as_str(), true)
-            .map_err(|e| InferenceError::Other(anyhow::anyhow!("tokenize: {e}")))?;
-        let prompt_tokens: Vec<u32> = encoding.get_ids().to_vec();
-        let prompt_len = prompt_tokens.len();
-
-        let temperature = request.temperature.unwrap_or(0.7);
-        let top_p = request.top_p;
-        let max_new = request.max_tokens.unwrap_or(512) as usize;
-        let seed = unix_subsec_nanos();
-
-        let eos_id = loaded
-            .tokenizer
-            .token_to_id("<|im_end|>")
-            .or_else(|| loaded.tokenizer.token_to_id("<|endoftext|>"));
-
-        let arch_arc = Arc::clone(&loaded.arch);
-        let device = loaded.device.clone();
-        let model_id = request.model.clone();
-
-        let (generated_ids, finish_reason) =
-            tokio::task::spawn_blocking(move || -> Result<(Vec<u32>, String)> {
-                let mut guard = arch_arc.blocking_lock();
-                run_inference(
-                    &mut guard,
-                    &device,
-                    &prompt_tokens,
-                    max_new,
-                    temperature,
-                    top_p,
-                    seed,
-                    eos_id,
-                )
-            })
-            .await
-            .map_err(|e| InferenceError::Other(anyhow::anyhow!("inference task panicked: {e}")))?
-            .map_err(InferenceError::Other)?;
-
-        let completion_text = loaded
-            .tokenizer
-            .decode(&generated_ids, true)
-            .map_err(|e| InferenceError::Other(anyhow::anyhow!("detokenize: {e}")))?;
-
-        let usage = Usage {
-            prompt_tokens: prompt_len as u64,
-            completion_tokens: generated_ids.len() as u64,
-            total_tokens: (prompt_len + generated_ids.len()) as u64,
-        };
-
-        Ok(ChatCompletionResponse {
-            id: format!("chatcmpl-{:x}", unix_subsec_nanos()),
-            object: "chat.completion".into(),
-            created: unix_now_secs(),
-            model: model_id,
-            choices: vec![ChatCompletionChoice {
-                index: 0,
-                message: ChatMessage {
-                    role: "assistant".into(),
-                    content: MessageContent::Text(completion_text),
-                    extra: serde_json::Value::Object(Default::default()),
-                },
-                finish_reason: Some(finish_reason),
-                extra: serde_json::Value::Object(Default::default()),
-            }],
-            usage: Some(usage),
-            extra: serde_json::Value::Object(Default::default()),
-        })
-    }
-}
-
-#[async_trait]
-impl Harness for CandleHarness {
-    fn name(&self) -> &str {
-        "candle"
-    }
-
-    async fn health(&self) -> HarnessHealth {
-        HarnessHealth {
-            name: "candle".into(),
-            running: true,
-            uptime_secs: None,
-        }
-    }
-
-    async fn list_models(&self) -> Result<Vec<ModelInfo>> {
-        let models = self.models.read().await;
-        Ok(models
-            .values()
-            .map(|m| ModelInfo {
-                id: m.model_id.clone(),
-                harness: "candle".into(),
-                status: "loaded".into(),
-                devices: m.devices.clone(),
-                vram_used_mb: None,
-            })
-            .collect())
-    }
-
-    async fn load_model(&self, spec: &ModelSpec) -> Result<()> {
-        if spec.harness != "candle" {
-            anyhow::bail!("expected harness=candle, got harness={}", spec.harness);
-        }
-
-        {
-            let models = self.models.read().await;
-            if models.contains_key(&spec.model_id) {
-                anyhow::bail!("model '{}' already loaded", spec.model_id);
-            }
-        }
-
-        let devices = spec.devices.clone().unwrap_or_else(|| vec![0]);
-        let device = Self::pick_device(&devices)?;
-
-        let (gguf_path, tokenizer_path) = self.resolve_files(spec).await?;
-
-        let tokenizer = Tokenizer::from_file(&tokenizer_path)
-            .map_err(|e| anyhow::anyhow!("load tokenizer: {e}"))?;
-
-        // File I/O + GGUF parsing + tensor materialisation are CPU-bound,
-        // so run them on a blocking task to avoid stalling the runtime.
-        let device_for_load = device.clone();
-        let gguf_path_for_load = gguf_path.clone();
-        let model_id_for_log = spec.model_id.clone();
-        let arch = tokio::task::spawn_blocking(move || -> Result<ModelArch> {
-            tracing::info!(model = %model_id_for_log, path = ?gguf_path_for_load, "loading GGUF");
-            let mut file = std::fs::File::open(&gguf_path_for_load).context("open GGUF file")?;
-            let content = gguf_file::Content::read(&mut file)
-                .map_err(|e| anyhow::anyhow!("parse GGUF: {e}"))?;
-
-            let architecture = content
-                .metadata
-                .get("general.architecture")
-                .and_then(|v| v.to_string().ok().cloned())
-                .unwrap_or_default();
-            tracing::info!(architecture = %architecture, "GGUF architecture");
-
-            match architecture.as_str() {
-                "qwen3" => {
-                    let weights =
-                        QuantizedQwen3Weights::from_gguf(content, &mut file, &device_for_load)
-                            .map_err(|e| anyhow::anyhow!("from_gguf qwen3: {e}"))?;
-                    Ok(ModelArch::Qwen3Quantized(weights))
-                }
-                other => anyhow::bail!(
-                    "unsupported GGUF architecture '{other}'; Stage 3 only supports qwen3"
-                ),
-            }
-        })
-        .await
-        .context("blocking load task panicked")??;
-
-        let loaded = Arc::new(LoadedModel {
-            model_id: spec.model_id.clone(),
-            arch: Arc::new(Mutex::new(arch)),
-            tokenizer,
-            device,
-            quant: spec.quant.clone(),
-            devices,
-        });
-
-        let mut models = self.models.write().await;
-        models.insert(spec.model_id.clone(), loaded);
-        tracing::info!(model = %spec.model_id, "model loaded");
-        Ok(())
-    }
-
-    async fn unload_model(&self, model_id: &str) -> Result<()> {
-        let mut models = self.models.write().await;
-        if models.remove(model_id).is_none() {
-            anyhow::bail!("model '{model_id}' not loaded");
-        }
-        tracing::info!(model = %model_id, "model unloaded");
-        Ok(())
-    }
-
-    async fn inference_endpoint(&self, model_id: &str) -> Option<String> {
-        let models = self.models.read().await;
-        models.contains_key(model_id).then(|| self.bind_url.clone())
-    }
-}
-
-/// Errors returned by `CandleHarness::chat_completion`. The
-/// `ModelNotLoaded` variant lets the HTTP handler map cleanly to 404
-/// without string-matching on anyhow messages.
-#[derive(Debug, thiserror::Error)]
-pub enum InferenceError {
-    #[error("model '{0}' not loaded on this neuron")]
-    ModelNotLoaded(String),
-    #[error(transparent)]
-    Other(#[from] anyhow::Error),
-}
-
-/// Apply the Qwen3 chat template:
-///
-/// ```text
-/// <|im_start|>{role}\n{content}<|im_end|>\n
-/// ...
-/// <|im_start|>assistant\n
-/// ```
-///
-/// The trailing `<|im_start|>assistant\n` cues the model to begin a turn.
-/// Non-text content parts (vision blocks) are joined as text only; full
-/// multimodal handling is out of scope for Stage 3.
-fn format_qwen3_prompt(messages: &[ChatMessage]) -> String {
-    let mut prompt = String::new();
-    for msg in messages {
-        let content = match &msg.content {
-            MessageContent::Text(s) => s.clone(),
-            MessageContent::Parts(parts) => parts
-                .iter()
-                .filter_map(|p| p.get("text").and_then(|v| v.as_str()))
-                .collect::<Vec<_>>()
-                .join(""),
-        };
-        prompt.push_str("<|im_start|>");
-        prompt.push_str(&msg.role);
-        prompt.push('\n');
-        prompt.push_str(&content);
-        prompt.push_str("<|im_end|>\n");
-    }
-    prompt.push_str("<|im_start|>assistant\n");
-    prompt
-}
-
-#[allow(clippy::too_many_arguments)]
-fn run_inference(
-    arch: &mut ModelArch,
-    device: &Device,
-    prompt_tokens: &[u32],
-    max_new: usize,
-    temperature: f64,
-    top_p: Option<f64>,
-    seed: u64,
-    eos_id: Option<u32>,
-) -> Result<(Vec<u32>, String)> {
-    let mut logits_processor = {
-        let sampling = if temperature <= 0.0 {
-            Sampling::ArgMax
-        } else {
-            match top_p {
-                Some(p) => Sampling::TopP { p, temperature },
-                None => Sampling::All { temperature },
-            }
-        };
-        LogitsProcessor::from_sampling(seed, sampling)
-    };
-
-    let mut generated: Vec<u32> = Vec::new();
-
-    let mut next_token = match arch {
-        ModelArch::Qwen3Quantized(model) => {
-            model.clear_kv_cache();
-            let input = Tensor::new(prompt_tokens, device)?.unsqueeze(0)?;
-            let logits = model.forward(&input, 0)?;
-            let logits = logits.squeeze(0)?;
-            logits_processor.sample(&logits)?
-        }
-    };
-
-    if Some(next_token) == eos_id {
-        return Ok((generated, "stop".into()));
-    }
-    generated.push(next_token);
-
-    for index in 0..max_new.saturating_sub(1) {
-        next_token = match arch {
-            ModelArch::Qwen3Quantized(model) => {
-                let input = Tensor::new(&[next_token], device)?.unsqueeze(0)?;
-                let logits = model.forward(&input, prompt_tokens.len() + index)?;
-                let logits = logits.squeeze(0)?;
-                logits_processor.sample(&logits)?
-            }
-        };
-        if Some(next_token) == eos_id {
-            return Ok((generated, "stop".into()));
-        }
-        generated.push(next_token);
-    }
-
-    Ok((generated, "length".into()))
-}
-
-fn unix_now_secs() -> u64 {
-    SystemTime::now()
-        .duration_since(UNIX_EPOCH)
-        .map(|d| d.as_secs())
-        .unwrap_or(0)
-}
-
-fn unix_subsec_nanos() -> u64 {
-    SystemTime::now()
-        .duration_since(UNIX_EPOCH)
-        .map(|d| d.as_nanos() as u64)
-        .unwrap_or(0)
-}
--- a/crates/neuron/src/harness/llamacpp.rs
+++ b/crates/neuron/src/harness/llamacpp.rs
@@ -0,0 +1 @@
+// llama.cpp harness implementation — Phase 11.
--- a/crates/neuron/src/harness/mistralrs.rs
+++ b/crates/neuron/src/harness/mistralrs.rs
@@ -0,0 +1,163 @@
+//! mistral.rs harness implementation.
+//!
+//! Wraps the mistral.rs HTTP API for model lifecycle management
+//! and optionally manages the process via systemd.
+
+use anyhow::Result;
+use async_trait::async_trait;
+use cortex_core::harness::{Harness, HarnessConfig, HarnessHealth, ModelInfo, ModelSpec};
+use reqwest::Client;
+use serde::Deserialize;
+
+pub struct MistralRsHarness {
+    endpoint: String,
+    systemd_unit: Option<String>,
+    client: Client,
+}
+
+impl MistralRsHarness {
+    pub fn new(endpoint: String, systemd_unit: Option<String>) -> Self {
+        Self {
+            endpoint,
+            systemd_unit,
+            client: Client::builder()
+                .timeout(std::time::Duration::from_secs(30))
+                .build()
+                .expect("failed to build HTTP client"),
+        }
+    }
+}
+
+/// Response from mistral.rs `GET /v1/models`.
+#[derive(Debug, Deserialize)]
+struct ModelsResponse {
+    data: Vec<ModelEntry>,
+}
+
+#[derive(Debug, Deserialize)]
+struct ModelEntry {
+    id: String,
+    #[serde(default)]
+    status: Option<String>,
+}
+
+#[async_trait]
+impl Harness for MistralRsHarness {
+    fn name(&self) -> &str {
+        "mistralrs"
+    }
+
+    async fn start(&self, _config: &HarnessConfig) -> Result<()> {
+        let Some(unit) = &self.systemd_unit else {
+            anyhow::bail!("no systemd unit configured for mistralrs harness");
+        };
+
+        let output = tokio::process::Command::new("systemctl")
+            .args(["start", unit])
+            .output()
+            .await?;
+
+        if !output.status.success() {
+            let stderr = String::from_utf8_lossy(&output.stderr);
+            anyhow::bail!("systemctl start {unit} failed: {stderr}");
+        }
+
+        // Wait for the health endpoint to respond (up to 30s).
+        let url = format!("{}/health", self.endpoint);
+        for _ in 0..30 {
+            tokio::time::sleep(std::time::Duration::from_secs(1)).await;
+            if self.client.get(&url).send().await.is_ok() {
+                tracing::info!(unit, "mistralrs started and healthy");
+                return Ok(());
+            }
+        }
+        anyhow::bail!("mistralrs started but health endpoint did not respond within 30s");
+    }
+
+    async fn stop(&self) -> Result<()> {
+        let Some(unit) = &self.systemd_unit else {
+            anyhow::bail!("no systemd unit configured for mistralrs harness");
+        };
+
+        let output = tokio::process::Command::new("systemctl")
+            .args(["stop", unit])
+            .output()
+            .await?;
+
+        if !output.status.success() {
+            let stderr = String::from_utf8_lossy(&output.stderr);
+            anyhow::bail!("systemctl stop {unit} failed: {stderr}");
+        }
+        Ok(())
+    }
+
+    async fn health(&self) -> HarnessHealth {
+        let url = format!("{}/health", self.endpoint);
+        let running = self.client.get(&url).send().await.is_ok();
+        HarnessHealth {
+            name: "mistralrs".into(),
+            running,
+            uptime_secs: None,
+        }
+    }
+
+    async fn list_models(&self) -> Result<Vec<ModelInfo>> {
+        let url = format!("{}/v1/models", self.endpoint);
+        let resp = self.client.get(&url).send().await?;
+
+        if !resp.status().is_success() {
+            anyhow::bail!("GET /v1/models returned {}", resp.status());
+        }
+
+        let models_resp: ModelsResponse = resp.json().await?;
+        Ok(models_resp
+            .data
+            .into_iter()
+            .map(|m| ModelInfo {
+                id: m.id,
+                harness: "mistralrs".into(),
+                status: m.status.unwrap_or_else(|| "loaded".into()),
+                devices: vec![],
+                vram_used_mb: None,
+            })
+            .collect())
+    }
+
+    async fn load_model(&self, spec: &ModelSpec) -> Result<()> {
+        let url = format!("{}/v1/models/reload", self.endpoint);
+        let resp = self
+            .client
+            .post(&url)
+            .json(&serde_json::json!({ "model_id": spec.model_id }))
+            .send()
+            .await?;
+
+        if !resp.status().is_success() {
+            let body = resp.text().await.unwrap_or_default();
+            anyhow::bail!("POST /v1/models/reload failed: {body}");
+        }
+        Ok(())
+    }
+
+    async fn unload_model(&self, model_id: &str) -> Result<()> {
+        let url = format!("{}/v1/models/unload", self.endpoint);
+        let resp = self
+            .client
+            .post(&url)
+            .json(&serde_json::json!({ "model_id": model_id }))
+            .send()
+            .await?;
+
+        if !resp.status().is_success() {
+            let body = resp.text().await.unwrap_or_default();
+            anyhow::bail!("POST /v1/models/unload failed: {body}");
+        }
+        Ok(())
+    }
+
+    async fn inference_endpoint(&self, _model_id: &str) -> Option<String> {
+        // mistral.rs routes internally by model name in the request body,
+        // so the inference endpoint is always the base URL.
+        Some(self.endpoint.clone())
+    }
+}
--- a/crates/neuron/src/harness/mod.rs
+++ b/crates/neuron/src/harness/mod.rs
@@ -1,22 +1,15 @@
 //! Harness registry — maps harness names to trait implementations.

-pub mod candle;
+pub mod llamacpp;
+pub mod mistralrs;

 use anyhow::Result;
 use cortex_core::harness::{Harness, HarnessConfig, ModelInfo, ModelSpec};
 use std::collections::HashMap;
-use std::sync::Arc;

 /// Registry of available harness implementations.
-///
-/// Holds an `Arc<dyn Harness>` per harness for generic lifecycle dispatch
-/// (load/unload/list_models). When a candle harness is registered, a typed
-/// `Arc<CandleHarness>` is also cached so inference routes can bypass the
-/// dyn-Trait dispatch and reach harness-specific methods (chat completion,
-/// streaming, etc.).
 pub struct HarnessRegistry {
-    harnesses: HashMap<String, Arc<dyn Harness>>,
-    candle: Option<Arc<candle::CandleHarness>>,
+    harnesses: HashMap<String, Box<dyn Harness>>,
 }

 impl Default for HarnessRegistry {
@@ -29,11 +22,10 @@ impl HarnessRegistry {
    pub fn new() -> Self {
        Self {
            harnesses: HashMap::new(),
-            candle: None,
        }
    }

-    pub fn register(&mut self, harness: Arc<dyn Harness>) {
+    pub fn register(&mut self, harness: Box<dyn Harness>) {
        self.harnesses.insert(harness.name().to_string(), harness);
    }

@@ -42,12 +34,6 @@ impl HarnessRegistry {
        self.harnesses.keys().cloned().collect()
    }

-    /// Typed handle to the candle harness, if registered. Used by inference
-    /// routes that need methods beyond the `Harness` trait surface.
-    pub fn candle(&self) -> Option<Arc<candle::CandleHarness>> {
-        self.candle.clone()
-    }
-
    /// List models from all registered harnesses.
    pub async fn list_all_models(&self) -> Result<Vec<ModelInfo>> {
        let mut all = Vec::new();
@@ -95,25 +81,19 @@ impl HarnessRegistry {
    }

    /// Build a registry from harness configs.
-    ///
-    /// `bind_url` is the URL where this neuron serves inference (its own
-    /// listen address). In-process harnesses (currently the only kind)
-    /// return this URL from `inference_endpoint`.
-    pub fn from_configs(
-        configs: &[HarnessConfig],
-        bind_url: &str,
-        settings: &crate::config::HarnessSettings,
-    ) -> Self {
+    pub fn from_configs(configs: &[HarnessConfig]) -> Self {
        let mut registry = Self::new();
        for config in configs {
            match config.name.as_str() {
-                "candle" => {
-                    let harness = Arc::new(candle::CandleHarness::new(
-                        bind_url.to_string(),
-                        settings.candle.hf_cache.clone(),
-                    ));
-                    registry.candle = Some(Arc::clone(&harness));
-                    registry.harnesses.insert("candle".into(), harness);
+                "mistralrs" => {
+                    if let Some(endpoint) = &config.endpoint {
+                        registry.register(Box::new(mistralrs::MistralRsHarness::new(
+                            endpoint.clone(),
+                            config.systemd_unit.clone(),
+                        )));
+                    } else {
+                        tracing::warn!("mistralrs harness missing endpoint, skipping");
+                    }
                }
                other => {
                    tracing::warn!(harness = other, "unknown harness type, skipping");
--- a/crates/neuron/src/main.rs
+++ b/crates/neuron/src/main.rs
@@ -37,7 +37,6 @@ async fn main() -> Result<()> {
    });

    let port = args.port.unwrap_or(cfg.port);
-    let bind_url = format!("http://localhost:{port}");
    let start_time = Instant::now();

    tracing::info!("running hardware discovery");
@@ -48,12 +47,9 @@ async fn main() -> Result<()> {
        "discovery complete"
    );

-    // Build harness registry from config. In-process harnesses (candle)
-    // need to know neuron's own bind URL so they can return it from
-    // inference_endpoint.
-    let registry = HarnessRegistry::from_configs(&cfg.harnesses, &bind_url, &cfg.harness);
+    // Build harness registry from config.
+    let registry = HarnessRegistry::from_configs(&cfg.harnesses);
    discovery_result.harnesses = registry.names();
-    let candle = registry.candle();

    let health_cache = Arc::new(health::HealthCache::new());
    health_cache
@@ -69,7 +65,6 @@ async fn main() -> Result<()> {
        discovery: discovery_result,
        health_cache,
        registry: RwLock::new(registry),
-        candle,
    });

    let app = api::neuron_routes().with_state(state);
--- a/crates/neuron/tests/api.rs
+++ b/crates/neuron/tests/api.rs
@@ -14,7 +14,6 @@ async fn spawn_neuron(discovery: DiscoveryResponse) -> String {
        discovery,
        health_cache,
        registry: RwLock::new(registry),
-        candle: None,
    });

    let app = api::neuron_routes().with_state(state);
@@ -136,30 +135,56 @@ async fn test_models_empty_registry() {
    assert!(body.as_array().unwrap().is_empty());
 }

-/// Verify the candle harness registers, list is empty by default, and a
-/// load attempt for an obviously-bogus model id returns a 4xx error
-/// without crashing the daemon. Real load/unload exercising actual GGUF
-/// download is covered by `tests/candle_lifecycle.rs` (cuda-integration).
+/// Spawn a mock mistral.rs backend and a neuron with the mistralrs harness
+/// pointing at it, then test the full model lifecycle through neuron's API.
 #[tokio::test]
-async fn test_candle_harness_registers_and_rejects_bogus_model() {
+async fn test_models_via_mistralrs_harness() {
+    use axum::routing::{get, post};
+    use axum::{Json, Router};
    use cortex_core::harness::HarnessConfig;
-    use neuron::config::HarnessSettings;
+    use serde_json::Value;

-    let registry = HarnessRegistry::from_configs(
-        &[HarnessConfig {
-            name: "candle".into(),
-        }],
-        "http://localhost:13131",
-        &HarnessSettings::default(),
-    );
+    // Mock mistral.rs backend.
+    let mock_app = Router::new()
+        .route(
+            "/v1/models",
+            get(|| async {
+                Json(json!({
+                    "data": [
+                        {"id": "test-model", "status": "loaded"},
+                        {"id": "other-model", "status": "unloaded"}
+                    ]
+                }))
+            }),
+        )
+        .route(
+            "/v1/models/unload",
+            post(|Json(_body): Json<Value>| async { Json(json!({"status": "ok"})) }),
+        )
+        .route(
+            "/v1/models/reload",
+            post(|Json(_body): Json<Value>| async { Json(json!({"status": "ok"})) }),
+        );
+
+    let mock_listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
+    let mock_addr = mock_listener.local_addr().unwrap();
+    tokio::spawn(async move {
+        axum::serve(mock_listener, mock_app).await.unwrap();
+    });
+    let mock_url = format!("http://{mock_addr}");
+
+    // Build neuron with mistralrs harness pointing at mock.
+    let registry = HarnessRegistry::from_configs(&[HarnessConfig {
+        name: "mistralrs".into(),
+        endpoint: Some(mock_url.clone()),
+        systemd_unit: None,
+    }]);

-    let candle = registry.candle();
    let health_cache = Arc::new(HealthCache::new());
    let state = Arc::new(NeuronState {
        discovery: fake_discovery(),
        health_cache,
        registry: RwLock::new(registry),
-        candle,
    });

    let app = api::neuron_routes().with_state(state);
@@ -172,6 +197,7 @@ async fn test_candle_harness_registers_and_rejects_bogus_model() {

    let client = reqwest::Client::new();

+    // GET /models — should return models from mock mistralrs.
    let resp = client
        .get(format!("{neuron_url}/models"))
        .send()
@@ -179,139 +205,45 @@ async fn test_candle_harness_registers_and_rejects_bogus_model() {
        .unwrap();
    assert_eq!(resp.status(), 200);
    let models: Vec<serde_json::Value> = resp.json().await.unwrap();
-    assert!(models.is_empty());
+    assert_eq!(models.len(), 2);
+    assert_eq!(models[0]["id"], "test-model");
+    assert_eq!(models[0]["harness"], "mistralrs");
+    assert_eq!(models[0]["status"], "loaded");
+    assert_eq!(models[1]["id"], "other-model");
+    assert_eq!(models[1]["status"], "unloaded");

-    // Sending a wrong-harness spec should be rejected synchronously
-    // without touching the network or the model registry.
+    // GET /models/test-model/endpoint — should return mock URL.
+    let resp = client
+        .get(format!("{neuron_url}/models/test-model/endpoint"))
+        .send()
+        .await
+        .unwrap();
+    assert_eq!(resp.status(), 200);
+    let body: serde_json::Value = resp.json().await.unwrap();
+    assert_eq!(body["url"], mock_url);
+
+    // POST /models/unload — should succeed.
+    let resp = client
+        .post(format!("{neuron_url}/models/unload"))
+        .json(&json!({"model_id": "test-model"}))
+        .send()
+        .await
+        .unwrap();
+    assert_eq!(resp.status(), 200);
+    let body: serde_json::Value = resp.json().await.unwrap();
+    assert_eq!(body["status"], "unloaded");
+
+    // POST /models/load — should succeed.
    let resp = client
        .post(format!("{neuron_url}/models/load"))
-        .json(&json!({"model_id": "definitely/not-real", "harness": "not-candle"}))
-        .send()
-        .await
-        .unwrap();
-    assert_eq!(resp.status(), 400);
-
-    // Registry still empty.
-    let resp = client
-        .get(format!("{neuron_url}/models"))
-        .send()
-        .await
-        .unwrap();
-    let models: Vec<serde_json::Value> = resp.json().await.unwrap();
-    assert!(models.is_empty());
-}
-
-/// `/v1/chat/completions` returns 503 when no candle harness is registered.
-#[tokio::test]
-async fn test_chat_completions_no_candle_harness() {
-    let registry = HarnessRegistry::new();
-    let health_cache = Arc::new(HealthCache::new());
-    let state = Arc::new(NeuronState {
-        discovery: fake_discovery(),
-        health_cache,
-        registry: RwLock::new(registry),
-        candle: None,
-    });
-    let app = api::neuron_routes().with_state(state);
-    let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
-    let addr = listener.local_addr().unwrap();
-    tokio::spawn(async move {
-        axum::serve(listener, app).await.unwrap();
-    });
-    let url = format!("http://{addr}");
-
-    let resp = reqwest::Client::new()
-        .post(format!("{url}/v1/chat/completions"))
        .json(&json!({
-            "model": "anything",
-            "messages": [{"role": "user", "content": "hi"}]
+            "model_id": "test-model",
+            "harness": "mistralrs"
        }))
        .send()
        .await
        .unwrap();
-    assert_eq!(resp.status(), 503);
-}
-
-/// `/v1/chat/completions` returns 404 when the requested model isn't loaded.
-#[tokio::test]
-async fn test_chat_completions_model_not_loaded() {
-    use cortex_core::harness::HarnessConfig;
-    use neuron::config::HarnessSettings;
-
-    let registry = HarnessRegistry::from_configs(
-        &[HarnessConfig {
-            name: "candle".into(),
-        }],
-        "http://localhost:0",
-        &HarnessSettings::default(),
-    );
-    let candle = registry.candle();
-    let health_cache = Arc::new(HealthCache::new());
-    let state = Arc::new(NeuronState {
-        discovery: fake_discovery(),
-        health_cache,
-        registry: RwLock::new(registry),
-        candle,
-    });
-    let app = api::neuron_routes().with_state(state);
-    let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
-    let addr = listener.local_addr().unwrap();
-    tokio::spawn(async move {
-        axum::serve(listener, app).await.unwrap();
-    });
-    let url = format!("http://{addr}");
-
-    let resp = reqwest::Client::new()
-        .post(format!("{url}/v1/chat/completions"))
-        .json(&json!({
-            "model": "definitely/not-loaded",
-            "messages": [{"role": "user", "content": "hi"}]
-        }))
-        .send()
-        .await
-        .unwrap();
-    assert_eq!(resp.status(), 404);
-}
-
-/// `/v1/chat/completions` with `stream: true` returns 501 until Stage 4
-/// wires up SSE.
-#[tokio::test]
-async fn test_chat_completions_streaming_not_yet_implemented() {
-    use cortex_core::harness::HarnessConfig;
-    use neuron::config::HarnessSettings;
-
-    let registry = HarnessRegistry::from_configs(
-        &[HarnessConfig {
-            name: "candle".into(),
-        }],
-        "http://localhost:0",
-        &HarnessSettings::default(),
-    );
-    let candle = registry.candle();
-    let health_cache = Arc::new(HealthCache::new());
-    let state = Arc::new(NeuronState {
-        discovery: fake_discovery(),
-        health_cache,
-        registry: RwLock::new(registry),
-        candle,
-    });
-    let app = api::neuron_routes().with_state(state);
-    let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
-    let addr = listener.local_addr().unwrap();
-    tokio::spawn(async move {
-        axum::serve(listener, app).await.unwrap();
-    });
-    let url = format!("http://{addr}");
-
-    let resp = reqwest::Client::new()
-        .post(format!("{url}/v1/chat/completions"))
-        .json(&json!({
-            "model": "anything",
-            "messages": [{"role": "user", "content": "hi"}],
-            "stream": true
-        }))
-        .send()
-        .await
-        .unwrap();
-    assert_eq!(resp.status(), 501);
+    assert_eq!(resp.status(), 200);
+    let body: serde_json::Value = resp.json().await.unwrap();
+    assert_eq!(body["status"], "loaded");
 }
--- a/crates/neuron/tests/candle_lifecycle.rs
+++ b/crates/neuron/tests/candle_lifecycle.rs
@@ -1,87 +0,0 @@
-//! Real model load/unload lifecycle through the candle harness.
-//!
-//! Gated behind the `cuda-integration` feature because it downloads a
-//! real (small) GGUF from HuggingFace and materialises tensors on the
-//! configured device. Run on a host with network access and either a
-//! CUDA GPU (when built with `--features cuda`) or enough CPU RAM to
-//! hold the model.
-//!
-//! Usage:
-//!   cargo test -p neuron --features cuda-integration --test candle_lifecycle
-//!
-//! Optional environment variables:
-//!   NEURON_TEST_MODEL_ID — HuggingFace repo to load (default: a small
-//!     public Qwen3 GGUF repo).
-//!   NEURON_TEST_QUANT    — quant substring matched against GGUF
-//!     filenames (default: "Q4_K_M").
-//!   HF_HOME              — HuggingFace cache directory.
-
-#![cfg(feature = "cuda-integration")]
-
-use cortex_core::harness::{HarnessConfig, ModelSpec};
-use neuron::config::HarnessSettings;
-use neuron::harness::HarnessRegistry;
-use std::path::PathBuf;
-
-#[tokio::test]
-async fn test_candle_qwen3_load_unload_lifecycle() {
-    let _ = tracing_subscriber::fmt()
-        .with_test_writer()
-        .with_env_filter("info,neuron=debug")
-        .try_init();
-
-    let model_id = std::env::var("NEURON_TEST_MODEL_ID")
-        .unwrap_or_else(|_| "Qwen/Qwen3-0.6B-GGUF".to_string());
-    let quant = std::env::var("NEURON_TEST_QUANT").unwrap_or_else(|_| "Q4_K_M".to_string());
-
-    let mut settings = HarnessSettings::default();
-    if let Ok(home) = std::env::var("HF_HOME") {
-        settings.candle.hf_cache = Some(PathBuf::from(home));
-    }
-
-    let registry = HarnessRegistry::from_configs(
-        &[HarnessConfig {
-            name: "candle".into(),
-        }],
-        "http://localhost:13131",
-        &settings,
-    );
-
-    let spec = ModelSpec {
-        model_id: model_id.clone(),
-        harness: "candle".into(),
-        quant: Some(quant),
-        tensor_parallel: None,
-        devices: Some(vec![0]),
-    };
-
-    registry
-        .load_model(&spec)
-        .await
-        .expect("load_model should succeed");
-
-    let models = registry.list_all_models().await.expect("list_all_models");
-    assert_eq!(models.len(), 1, "expected exactly one loaded model");
-    assert_eq!(models[0].id, model_id);
-    assert_eq!(models[0].harness, "candle");
-    assert_eq!(models[0].status, "loaded");
-
-    let url = registry.inference_endpoint(&model_id).await;
-    assert_eq!(url, Some("http://localhost:13131".into()));
-
-    // Re-loading the same model should be rejected.
-    let again = registry.load_model(&spec).await;
-    assert!(again.is_err(), "second load should error");
-
-    registry
-        .unload_model(&model_id)
-        .await
-        .expect("unload_model should succeed");
-
-    let models = registry.list_all_models().await.expect("list_all_models");
-    assert!(models.is_empty(), "registry should be empty after unload");
-
-    // Unloading a model that isn't loaded should error.
-    let err = registry.unload_model(&model_id).await;
-    assert!(err.is_err(), "unload of missing model should error");
-}
--- a/data/cortex-firewalld.xml
+++ b/data/cortex-firewalld.xml
@@ -1,7 +0,0 @@
-<?xml version="1.0" encoding="utf-8"?>
-<service>
-  <short>cortex</short>
-  <description>Cortex — inference gateway for multi-node GPU clusters</description>
-  <port protocol="tcp" port="31313"/>
-  <port protocol="tcp" port="31314"/>
-</service>
--- a/data/neuron-firewalld.xml
+++ b/data/neuron-firewalld.xml
@@ -1,6 +0,0 @@
-<?xml version="1.0" encoding="utf-8"?>
-<service>
-  <short>helexa-neuron</short>
-  <description>Neuron — per-node GPU discovery and harness daemon for cortex</description>
-  <port protocol="tcp" port="13131"/>
-</service>
--- a/helexa-neuron.spec
+++ b/helexa-neuron.spec
@@ -1,5 +1,5 @@
 Name:           helexa-neuron
-Version:        0.1.16
+Version:        0.1.12
 Release:        1%{?dist}
 Summary:        Per-node GPU discovery and harness management daemon for cortex
 # Package name disambiguates from Fedora's existing "neuron" package
@@ -24,7 +24,6 @@ BuildRequires:  systemd-rpm-macros

 Requires(pre):  shadow-utils
 Requires:       systemd
-Requires:       firewalld-filesystem

 # systemd-rpm-macros ships a unit dep generator that parses User=/Group=
 # from our .service file and emits Requires: user(neuron)/group(neuron).
@@ -37,9 +36,8 @@ Provides:       user(neuron)

 %description
 Neuron is a per-node daemon for cortex inference clusters. It discovers
-local GPU hardware via nvidia-smi, runs in-process inference via
-huggingface/candle, and exposes an HTTP API for model lifecycle
-management (load, unload, list, inference endpoint).
+local GPU hardware via nvidia-smi, manages inference harnesses (mistral.rs,
+llama.cpp), and exposes an HTTP API for model lifecycle management.

 %prep
 %autosetup
@@ -60,7 +58,6 @@ cargo build --release -p neuron
 install -Dm755 target/release/neuron %{buildroot}%{_bindir}/neuron
 install -Dm644 data/neuron.service %{buildroot}%{_unitdir}/neuron.service
 install -Dm644 data/neuron-sysusers.conf %{buildroot}%{_sysusersdir}/neuron.conf
-install -Dm644 data/neuron-firewalld.xml %{buildroot}%{_prefix}/lib/firewalld/services/helexa-neuron.xml
 install -dm755 %{buildroot}%{_sysconfdir}/neuron
 install -Dm644 neuron.example.toml %{buildroot}%{_sysconfdir}/neuron/neuron.toml

@@ -82,20 +79,9 @@ install -Dm644 neuron.example.toml %{buildroot}%{_sysconfdir}/neuron/neuron.toml
 %{_bindir}/neuron
 %{_unitdir}/neuron.service
 %{_sysusersdir}/neuron.conf
-%{_prefix}/lib/firewalld/services/helexa-neuron.xml
 %dir %{_sysconfdir}/neuron
 %config(noreplace) %{_sysconfdir}/neuron/neuron.toml

 %changelog
-* Thu Apr 16 2026 Gitea Actions <actions@git.lair.cafe> - 0.1.16-1
- chore: ignore local deploy script
- chore: move default ports out of common-collision ranges
- ci: drop actions/cache for cargo registry and target
-
-* Thu Apr 16 2026 Gitea Actions <actions@git.lair.cafe> - 0.1.14-1
- ci: publish both packages to a single helexa/helexa COPR project
- fix(rpm): rename neuron package to helexa-neuron
- ci: commit generated %changelog entries back to main
-
 * Wed Apr 15 2026 Rob Thijssen <grenade@rob.tn> - 0.1.0-1
 - Initial package
--- a/models.example.toml
+++ b/models.example.toml
@@ -6,7 +6,7 @@

 [[models]]
 id = "your-org/large-model"
-harness = "candle"
+harness = "mistralrs"
 quant = "Q4_K_M"
 vram_mb = 19000
 min_devices = 2
@@ -15,7 +15,7 @@ pinned_on = ["gpu-large"]

 [[models]]
 id = "your-org/medium-model"
-harness = "candle"
+harness = "mistralrs"
 quant = "Q6_K"
 vram_mb = 12000
 min_devices = 1
@@ -23,7 +23,7 @@ pinned_on = ["gpu-medium"]

 [[models]]
 id = "your-org/embedding-model"
-harness = "candle"
+harness = "mistralrs"
 quant = "Q8_0"
 vram_mb = 8000
 min_devices = 1
--- a/neuron.example.toml
+++ b/neuron.example.toml
@@ -8,17 +8,9 @@
 port = 13131

 # -- Harnesses ---------------------------------------------------------------
-# Each [[harnesses]] entry enables an inference engine. Currently only
-# "candle" is supported — it runs in-process and uses huggingface/candle
-# for inference on local CUDA devices (or CPU when CUDA is unavailable).
+# Each [[harnesses]] entry declares an inference engine managed by neuron.

 [[harnesses]]
-name = "candle"
-
-# -- Candle harness settings -------------------------------------------------
-# Optional tuning for the candle harness.
-
-[harness.candle]
-# HuggingFace cache directory for model weights. When unset, hf-hub's
-# default (~/.cache/huggingface) is used.
-# hf_cache = "/var/lib/neuron/hf-cache"
+name = "mistralrs"
+endpoint = "http://localhost:8080"
+systemd_unit = "mistralrs.service"
--- a/rpm/cortex-prerelease.spec
+++ b/rpm/cortex-prerelease.spec
@@ -1,102 +0,0 @@
-# Prebuilt-binary spec for cortex.
-#
-# Unlike cortex.spec (which builds from source via cargo), this spec
-# wraps a pre-built `cortex` binary produced by an upstream CI job and
-# packages it for rpm.lair.cafe. The %build phase is a no-op.
-#
-# Required defines at rpmbuild time:
-#   cortex_version    e.g. "0.1.16"
-#   cortex_prerelease e.g. "0.1.20260518gitabcdef0"   (used as Release)
-
-%global _build_id_links none
-%global debug_package %{nil}
-%global __strip /usr/bin/true
-
-%{!?cortex_version: %global cortex_version 0.0.0}
-%if 0%{?cortex_prerelease:1}
-%global cortex_release %{cortex_prerelease}
-%else
-%global cortex_release 1
-%endif
-
-Name:           cortex
-Version:        %{cortex_version}
-Release:        %{cortex_release}%{?dist}
-Summary:        Inference gateway for multi-node GPU clusters (prebuilt)
-
-License:        GPL-3.0-or-later
-URL:            https://git.lair.cafe/helexa/cortex
-
-Source0:        cortex
-Source1:        cortex.service
-Source2:        cortex-sysusers.conf
-Source3:        cortex-firewalld.xml
-Source4:        cortex.example.toml
-Source5:        models.example.toml
-Source6:        LICENSE
-
-ExclusiveArch:  x86_64
-
-Requires(pre):  shadow-utils
-Requires:       systemd
-Requires:       firewalld-filesystem
-
-Provides:       user(cortex)
-
-%description
-Cortex is a Rust reverse-proxy that sits in front of multiple neuron
-inference daemons and presents a unified OpenAI and Anthropic
-compatible API surface.
-
-This package wraps a binary built upstream in CI; the source-build
-spec (cortex.spec) remains available for stable releases.
-
-%prep
-cp %{SOURCE0} ./cortex
-cp %{SOURCE1} .
-cp %{SOURCE2} .
-cp %{SOURCE3} .
-cp %{SOURCE4} .
-cp %{SOURCE5} .
-cp %{SOURCE6} .
-
-%build
-# Already built in the upstream CI build job.
-
-%install
-install -Dm755 cortex %{buildroot}%{_bindir}/cortex
-install -Dm644 cortex.service %{buildroot}%{_unitdir}/cortex.service
-install -Dm644 cortex-sysusers.conf %{buildroot}%{_sysusersdir}/cortex.conf
-install -Dm644 cortex-firewalld.xml %{buildroot}%{_prefix}/lib/firewalld/services/cortex.xml
-install -dm755 %{buildroot}%{_sysconfdir}/cortex
-install -Dm644 cortex.example.toml %{buildroot}%{_sysconfdir}/cortex/cortex.toml
-install -Dm644 models.example.toml %{buildroot}%{_sysconfdir}/cortex/models.toml
-
-%pre
-getent group cortex >/dev/null || groupadd -r cortex
-getent passwd cortex >/dev/null || \
-    useradd -r -g cortex -d /var/lib/cortex -s /sbin/nologin \
-        -c "Cortex inference gateway" cortex
-
-%post
-%systemd_post cortex.service
-
-%preun
-%systemd_preun cortex.service
-
-%postun
-%systemd_postun_with_restart cortex.service
-
-%files
-%license LICENSE
-%{_bindir}/cortex
-%{_unitdir}/cortex.service
-%{_sysusersdir}/cortex.conf
-%{_prefix}/lib/firewalld/services/cortex.xml
-%dir %{_sysconfdir}/cortex
-%config(noreplace) %{_sysconfdir}/cortex/cortex.toml
-%config(noreplace) %{_sysconfdir}/cortex/models.toml
-
-%changelog
-* Mon May 18 2026 Gitea Actions <actions@git.lair.cafe> - %{cortex_version}-%{cortex_release}
- Prerelease build from upstream CI binary.
--- a/rpm/helexa-neuron-prerelease.spec
+++ b/rpm/helexa-neuron-prerelease.spec
@@ -1,122 +0,0 @@
-# Prebuilt-binary spec for helexa-neuron flavoured by CUDA compute capability.
-#
-# Unlike helexa-neuron.spec (which builds from source via cargo), this
-# spec wraps a pre-built `neuron-{flavour}` binary produced by an
-# upstream CI job and packages it for rpm.lair.cafe. The %build phase
-# is a no-op.
-#
-# Required defines at rpmbuild time:
-#   neuron_version    e.g. "0.1.16"
-#   neuron_flavour    e.g. "ada", "blackwell"  — matches the CI build
-#                     matrix's compute_cap label.
-#   neuron_prerelease e.g. "0.1.20260518gitabcdef0"   (used as Release)
-#
-# One flavour can be installed at a time on a given host; flavour
-# packages Conflict with each other.
-
-%global _build_id_links none
-%global debug_package %{nil}
-%global __strip /usr/bin/true
-
-%{!?neuron_version: %global neuron_version 0.0.0}
-%{!?neuron_flavour: %global neuron_flavour blackwell}
-%if 0%{?neuron_prerelease:1}
-%global neuron_release %{neuron_prerelease}
-%else
-%global neuron_release 1
-%endif
-
-Name:           helexa-neuron-%{neuron_flavour}
-Version:        %{neuron_version}
-Release:        %{neuron_release}%{?dist}
-Summary:        Per-node GPU inference daemon (candle, %{neuron_flavour} flavour)
-
-License:        GPL-3.0-or-later
-URL:            https://git.lair.cafe/helexa/cortex
-
-Source0:        neuron-%{neuron_flavour}
-Source1:        neuron.service
-Source2:        neuron-sysusers.conf
-Source3:        neuron-firewalld.xml
-Source4:        neuron.example.toml
-Source5:        LICENSE
-
-ExclusiveArch:  x86_64
-
-# Binary links against the CUDA runtime, cuDNN, NCCL, etc. Suppress
-# auto-detected exact soname deps — users may have CUDA from various
-# sources (rpmfusion, nvidia-direct) at different compatible versions;
-# a runtime dlopen failure surfaces a clearer error than rpm dep
-# resolution would.
-%global __requires_exclude ^lib(cuda|cudart|cudnn|cublas|cublasLt|curand|nvrtc|nccl)
-
-Requires(pre):  shadow-utils
-Requires:       systemd
-Requires:       firewalld-filesystem
-
-Provides:       helexa-neuron = %{neuron_version}-%{neuron_release}
-Provides:       user(neuron)
-
-# Mutual exclusion across flavours and the source-build variant.
-Conflicts:      helexa-neuron
-Conflicts:      helexa-neuron-ada
-Conflicts:      helexa-neuron-ampere
-Conflicts:      helexa-neuron-blackwell
-# (The Conflicts: with self is filtered by rpm at install time.)
-
-%description
-Neuron is the per-node daemon for cortex inference clusters. It
-discovers local GPU hardware via nvidia-smi, runs in-process
-inference via huggingface/candle, and exposes an HTTP API for model
-lifecycle management (load, unload, list, inference endpoint).
-
-This is the %{neuron_flavour} flavour, built for that CUDA compute
-capability. Install the flavour matching the GPUs on this host.
-
-%prep
-cp %{SOURCE0} ./neuron
-cp %{SOURCE1} .
-cp %{SOURCE2} .
-cp %{SOURCE3} .
-cp %{SOURCE4} .
-cp %{SOURCE5} .
-
-%build
-# Already built in the upstream CI build job (with --features cuda).
-
-%install
-install -Dm755 neuron %{buildroot}%{_bindir}/neuron
-install -Dm644 neuron.service %{buildroot}%{_unitdir}/neuron.service
-install -Dm644 neuron-sysusers.conf %{buildroot}%{_sysusersdir}/neuron.conf
-install -Dm644 neuron-firewalld.xml %{buildroot}%{_prefix}/lib/firewalld/services/helexa-neuron.xml
-install -dm755 %{buildroot}%{_sysconfdir}/neuron
-install -Dm644 neuron.example.toml %{buildroot}%{_sysconfdir}/neuron/neuron.toml
-
-%pre
-getent group neuron >/dev/null || groupadd -r neuron
-getent passwd neuron >/dev/null || \
-    useradd -r -g neuron -d /var/lib/neuron -s /sbin/nologin \
-        -G video,render \
-        -c "Neuron GPU node daemon" neuron
-
-%post
-%systemd_post neuron.service
-
-%preun
-%systemd_preun neuron.service
-
-%postun
-%systemd_postun_with_restart neuron.service
-
-%files
-%license LICENSE
-%{_bindir}/neuron
-%{_unitdir}/neuron.service
-%{_sysusersdir}/neuron.conf
-%{_prefix}/lib/firewalld/services/helexa-neuron.xml
-%dir %{_sysconfdir}/neuron
-%config(noreplace) %{_sysconfdir}/neuron/neuron.toml
-
-%changelog
-* Mon May 18 2026 Gitea Actions <actions@git.lair.cafe> - %{neuron_version}-%{neuron_release}
- Prerelease build from upstream CI binary (%{neuron_flavour} flavour).
--- a/rpm/rpmmacros
+++ b/rpm/rpmmacros
@@ -1 +0,0 @@
-%_openpgp_sign_id @GPG_NAME@
--- a/script/generate-packages-json.py
+++ b/script/generate-packages-json.py
@@ -1,154 +0,0 @@
-#!/usr/bin/env python3
-"""Parse RPM repodata and emit a packages.json manifest for the UI."""
-
-import argparse
-import gzip
-import json
-import os
-import subprocess
-import sys
-import xml.etree.ElementTree as ET
-from datetime import datetime, timezone
-
-RPM_NS = "http://linux.duke.edu/metadata/common"
-OTHER_NS = "http://linux.duke.edu/metadata/other"
-REPO_NS = "http://linux.duke.edu/metadata/repo"
-
-
-def find_repodata_file(repodata_dir, data_type):
-    """Read repomd.xml and return the path to a specific data type's file."""
-    repomd_path = os.path.join(repodata_dir, "repomd.xml")
-    tree = ET.parse(repomd_path)
-    root = tree.getroot()
-
-    for data in root.findall(f"{{{REPO_NS}}}data"):
-        if data.get("type") == data_type:
-            location = data.find(f"{{{REPO_NS}}}location")
-            if location is not None:
-                href = location.get("href", "")
-                return os.path.join(os.path.dirname(repodata_dir), href)
-
-    return None
-
-
-def open_compressed(path):
-    """Open a gzip or zstd compressed file for reading."""
-    if path.endswith(".zst"):
-        result = subprocess.run(
-            ["zstdcat", path], capture_output=True, check=True
-        )
-        import io
-        return io.BytesIO(result.stdout)
-    else:
-        return gzip.open(path, "rb")
-
-
-def parse_primary(repodata_dir):
-    """Parse primary.xml.{gz,zst} and return package metadata."""
-    path = find_repodata_file(repodata_dir, "primary")
-    if not path:
-        print("error: primary metadata not found in repomd.xml", file=sys.stderr)
-        sys.exit(1)
-
-    packages = {}
-    with open_compressed(path) as f:
-        tree = ET.parse(f)
-
-    for pkg in tree.getroot().findall(f"{{{RPM_NS}}}package"):
-        if pkg.get("type") != "rpm":
-            continue
-
-        name = pkg.findtext(f"{{{RPM_NS}}}name", "")
-        version_el = pkg.find(f"{{{RPM_NS}}}version")
-        ver = version_el.get("ver", "") if version_el is not None else ""
-        rel = version_el.get("rel", "") if version_el is not None else ""
-        arch = pkg.findtext(f"{{{RPM_NS}}}arch", "")
-
-        size_el = pkg.find(f"{{{RPM_NS}}}size")
-        size = int(size_el.get("package", "0")) if size_el is not None else 0
-
-        time_el = pkg.find(f"{{{RPM_NS}}}time")
-        build_time = int(time_el.get("build", "0")) if time_el is not None else 0
-
-        location_el = pkg.find(f"{{{RPM_NS}}}location")
-        filename = os.path.basename(location_el.get("href", "")) if location_el is not None else ""
-
-        key = f"{name}-{ver}-{rel}"
-        packages[key] = {
-            "name": name,
-            "version": ver,
-            "release": rel,
-            "arch": arch,
-            "summary": pkg.findtext(f"{{{RPM_NS}}}summary", ""),
-            "size": size,
-            "buildTime": build_time,
-            "rpmFilename": filename,
-            "changelog": [],
-        }
-
-    return packages
-
-
-def parse_other(repodata_dir, packages):
-    """Parse other.xml.gz and attach changelog entries to packages."""
-    path = find_repodata_file(repodata_dir, "other")
-    if not path:
-        return
-
-    with open_compressed(path) as f:
-        tree = ET.parse(f)
-
-    for pkg in tree.getroot().findall(f"{{{OTHER_NS}}}package"):
-        name = pkg.get("name", "")
-        version_el = pkg.find(f"{{{OTHER_NS}}}version")
-        ver = version_el.get("ver", "") if version_el is not None else ""
-        rel = version_el.get("rel", "") if version_el is not None else ""
-        key = f"{name}-{ver}-{rel}"
-
-        if key not in packages:
-            continue
-
-        for entry in pkg.findall(f"{{{OTHER_NS}}}changelog"):
-            packages[key]["changelog"].append({
-                "author": entry.get("author", ""),
-                "date": int(entry.get("date", "0")),
-                "text": (entry.text or "").strip(),
-            })
-
-
-def main():
-    parser = argparse.ArgumentParser(description=__doc__)
-    parser.add_argument(
-        "--repodata-dir",
-        required=True,
-        help="path to the repodata/ directory",
-    )
-    parser.add_argument(
-        "--output",
-        required=True,
-        help="path to write packages.json",
-    )
-    parser.add_argument(
-        "--base-url",
-        required=True,
-        help="public base URL for the repo (e.g. https://rpm.lair.cafe/fedora/43/x86_64)",
-    )
-    args = parser.parse_args()
-
-    packages = parse_primary(args.repodata_dir)
-    parse_other(args.repodata_dir, packages)
-
-    manifest = {
-        "generated": datetime.now(timezone.utc).isoformat(),
-        "baseUrl": args.base_url,
-        "packages": list(packages.values()),
-    }
-
-    with open(args.output, "w") as f:
-        json.dump(manifest, f, indent=2)
-
-    print(f"wrote {len(packages)} packages to {args.output}")
-
-
-if __name__ == "__main__":
-    main()
				`@@ -0,0 +1 @@`
				`// llama.cpp harness implementation — Phase 11.`