ci: harden workflows against network/CDN flakes (resilient cache + setup retries) (#101)

.github/workflows/bench.yml

@@ -35,8 +35,25 @@ jobs:
       - uses: dtolnay/rust-toolchain@29eef336d9b2848a0b548edc03f92a220660cdb8 # stable branch, 2026-03-27
 
       - uses: Swatinem/rust-cache@e18b497796c12c097a38f9edb9d0641fb99eee32 # v2
+        continue-on-error: true # cache is an optimisation; never block on a stuck/slow restore
+        timeout-minutes: 6
 
       - name: Set up Python
+        id: setup_python
+        continue-on-error: true
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
+        with:
+          python-version: "3.11"
+
+      - name: Wait before Python retry
+        if: steps.setup_python.outcome == 'failure'
+        shell: bash
+        run: |
+          echo "::warning::setup-python failed (likely CDN flake), waiting 30s before retry..."
+          sleep 30
+
+      - name: Set up Python (retry)
+        if: steps.setup_python.outcome == 'failure'
         uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
         with:
           python-version: "3.11"

.github/workflows/ci.yml

@@ -28,6 +28,8 @@ jobs:
 
       - name: Cache cargo
         uses: Swatinem/rust-cache@e18b497796c12c097a38f9edb9d0641fb99eee32 # v2
+        continue-on-error: true # cache is an optimisation; never block on a stuck/slow restore
+        timeout-minutes: 6
 
       - name: Format check
         run: cargo fmt --all -- --check
@@ -67,11 +69,43 @@ jobs:
     steps:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
-      - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+      - name: Set up Node
+        id: setup_node
+        continue-on-error: true
+        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
         with:
           node-version: "20"
 
-      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
+      - name: Wait before Node retry
+        if: steps.setup_node.outcome == 'failure'
+        shell: bash
+        run: |
+          echo "::warning::setup-node failed (likely CDN flake), waiting 30s before retry..."
+          sleep 30
+
+      - name: Set up Node (retry)
+        if: steps.setup_node.outcome == 'failure'
+        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+        with:
+          node-version: "20"
+
+      - name: Set up Python
+        id: setup_python
+        continue-on-error: true
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
+        with:
+          python-version: "3.12"
+
+      - name: Wait before Python retry
+        if: steps.setup_python.outcome == 'failure'
+        shell: bash
+        run: |
+          echo "::warning::setup-python failed (likely CDN flake), waiting 30s before retry..."
+          sleep 30
+
+      - name: Set up Python (retry)
+        if: steps.setup_python.outcome == 'failure'
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
         with:
           python-version: "3.12"
 
@@ -128,17 +162,49 @@ jobs:
           components: clippy
 
       - name: Set up Python
+        id: setup_python
+        continue-on-error: true
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: Wait before Python retry
+        if: steps.setup_python.outcome == 'failure'
+        shell: bash
+        run: |
+          echo "::warning::setup-python failed (likely CDN flake), waiting 30s before retry..."
+          sleep 30
+
+      - name: Set up Python (retry)
+        if: steps.setup_python.outcome == 'failure'
         uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
           python-version: "3.12"
 
       - name: Set up Node
+        id: setup_node
+        continue-on-error: true
+        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+        with:
+          node-version: "20"
+
+      - name: Wait before Node retry
+        if: steps.setup_node.outcome == 'failure'
+        shell: bash
+        run: |
+          echo "::warning::setup-node failed (likely CDN flake), waiting 30s before retry..."
+          sleep 30
+
+      - name: Set up Node (retry)
+        if: steps.setup_node.outcome == 'failure'
         uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
         with:
           node-version: "20"
 
       - name: Cache cargo
         uses: Swatinem/rust-cache@e18b497796c12c097a38f9edb9d0641fb99eee32 # v2
+        continue-on-error: true # cache is an optimisation; never block on a stuck/slow restore
+        timeout-minutes: 6
 
       - name: Clippy (bindings, all targets)
         run: cargo clippy -p wickra-node -p wickra-python --all-targets -- -D warnings
@@ -175,6 +241,8 @@ jobs:
 
       - name: Cache cargo
         uses: Swatinem/rust-cache@e18b497796c12c097a38f9edb9d0641fb99eee32 # v2
+        continue-on-error: true # cache is an optimisation; never block on a stuck/slow restore
+        timeout-minutes: 6
 
       - name: Build on MSRV
         run: cargo build ${{ matrix.packages }} --verbose
@@ -196,9 +264,12 @@ jobs:
 
       - name: Cache cargo
         uses: Swatinem/rust-cache@e18b497796c12c097a38f9edb9d0641fb99eee32 # v2
+        continue-on-error: true # cache is an optimisation; never block on a stuck/slow restore
+        timeout-minutes: 6
 
       - name: Install cargo-llvm-cov
         uses: taiki-e/install-action@0fd46367812ee04360509b4169d9f659d6892bb2 # v2.79.15
+        timeout-minutes: 10 # fail fast on a stuck download instead of hanging the job
         with:
           tool: cargo-llvm-cov
 
@@ -248,6 +319,8 @@ jobs:
 
       - name: Cache cargo
         uses: Swatinem/rust-cache@e18b497796c12c097a38f9edb9d0641fb99eee32 # v2
+        continue-on-error: true # cache is an optimisation; never block on a stuck/slow restore
+        timeout-minutes: 6
         with:
           workspaces: fuzz
 
@@ -260,6 +333,7 @@ jobs:
         # never gets off the ground. The prebuilt binary avoids the entire
         # transitive-dep compile.
         uses: taiki-e/install-action@0fd46367812ee04360509b4169d9f659d6892bb2 # v2.79.15
+        timeout-minutes: 10 # fail fast on a stuck download instead of hanging the job
         with:
           tool: cargo-fuzz
 
@@ -299,6 +373,8 @@ jobs:
 
       - name: Cache cargo
         uses: Swatinem/rust-cache@e18b497796c12c097a38f9edb9d0641fb99eee32 # v2
+        continue-on-error: true # cache is an optimisation; never block on a stuck/slow restore
+        timeout-minutes: 6
 
       # setup-python downloads the interpreter from the Actions tool cache /
       # nodejs CDN and occasionally hangs or 5xx's on the Windows runners.
@@ -361,6 +437,8 @@ jobs:
 
       - name: Cache cargo
         uses: Swatinem/rust-cache@e18b497796c12c097a38f9edb9d0641fb99eee32 # v2
+        continue-on-error: true # cache is an optimisation; never block on a stuck/slow restore
+        timeout-minutes: 6
 
       - name: Install wasm-pack
         # jetli/wasm-pack-action@v0.4.0 with no `version:` input installs an
@@ -371,6 +449,7 @@ jobs:
         # cargo-llvm-cov and cargo-fuzz; it tracks the latest wasm-pack
         # release, which has `--features` as a top-level flag (since 0.12).
         uses: taiki-e/install-action@0fd46367812ee04360509b4169d9f659d6892bb2 # v2.79.15
+        timeout-minutes: 10 # fail fast on a stuck download instead of hanging the job
         with:
           tool: wasm-pack
 
@@ -402,6 +481,8 @@ jobs:
 
       - name: Cache cargo
         uses: Swatinem/rust-cache@e18b497796c12c097a38f9edb9d0641fb99eee32 # v2
+        continue-on-error: true # cache is an optimisation; never block on a stuck/slow restore
+        timeout-minutes: 6
 
       # setup-node downloads Node from nodejs.org and we've seen it fail on
       # Windows runners with "Attempting to download 18..." followed by a

.github/workflows/release.yml

@@ -26,6 +26,8 @@ jobs:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
       - uses: dtolnay/rust-toolchain@29eef336d9b2848a0b548edc03f92a220660cdb8 # stable branch, 2026-03-27
       - uses: Swatinem/rust-cache@e18b497796c12c097a38f9edb9d0641fb99eee32 # v2
+        continue-on-error: true # cache is an optimisation; never block on a stuck/slow restore
+        timeout-minutes: 6
 
       # Idempotent publishing: if the version is already on crates.io we
       # treat that as success so re-runs of the workflow don't fail.
@@ -85,6 +87,7 @@ jobs:
       # re-resolving Cargo.lock.
       - name: Install cargo-cyclonedx
         uses: taiki-e/install-action@0fd46367812ee04360509b4169d9f659d6892bb2 # v2.79.15
+        timeout-minutes: 10 # fail fast on a stuck download instead of hanging the job
         with:
           tool: cargo-cyclonedx
 
@@ -131,7 +134,21 @@ jobs:
     runs-on: ${{ matrix.os }}
     steps:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
+      - name: Set up Python
+        id: setup_python
+        continue-on-error: true
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
+        with:
+          python-version: "3.11"
+      - name: Wait before Python retry
+        if: steps.setup_python.outcome == 'failure'
+        shell: bash
+        run: |
+          echo "::warning::setup-python failed (likely CDN flake), waiting 30s before retry..."
+          sleep 30
+      - name: Set up Python (retry)
+        if: steps.setup_python.outcome == 'failure'
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
         with:
           python-version: "3.11"
       - name: Sync root README into bindings/python so it ships with the wheel
@@ -206,7 +223,23 @@ jobs:
     steps:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
-      - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+      - name: Set up Node
+        id: setup_node
+        continue-on-error: true
+        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+        with:
+          node-version: "20"
+
+      - name: Wait before Node retry
+        if: steps.setup_node.outcome == 'failure'
+        shell: bash
+        run: |
+          echo "::warning::setup-node failed (likely CDN flake), waiting 30s before retry..."
+          sleep 30
+
+      - name: Set up Node (retry)
+        if: steps.setup_node.outcome == 'failure'
+        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
         with:
           node-version: "20"
 
@@ -215,6 +248,8 @@ jobs:
           targets: ${{ matrix.target }}
 
       - uses: Swatinem/rust-cache@e18b497796c12c097a38f9edb9d0641fb99eee32 # v2
+        continue-on-error: true # cache is an optimisation; never block on a stuck/slow restore
+        timeout-minutes: 6
 
       - name: Install Node deps
         working-directory: bindings/node
@@ -247,7 +282,24 @@ jobs:
     steps:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
-      - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+      - name: Set up Node
+        id: setup_node
+        continue-on-error: true
+        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+        with:
+          node-version: "20"
+          registry-url: "https://registry.npmjs.org"
+
+      - name: Wait before Node retry
+        if: steps.setup_node.outcome == 'failure'
+        shell: bash
+        run: |
+          echo "::warning::setup-node failed (likely CDN flake), waiting 30s before retry..."
+          sleep 30
+
+      - name: Set up Node (retry)
+        if: steps.setup_node.outcome == 'failure'
+        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
         with:
           node-version: "20"
           registry-url: "https://registry.npmjs.org"
@@ -397,7 +449,24 @@ jobs:
     steps:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
-      - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+      - name: Set up Node
+        id: setup_node
+        continue-on-error: true
+        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
+        with:
+          node-version: "20"
+          registry-url: "https://registry.npmjs.org"
+
+      - name: Wait before Node retry
+        if: steps.setup_node.outcome == 'failure'
+        shell: bash
+        run: |
+          echo "::warning::setup-node failed (likely CDN flake), waiting 30s before retry..."
+          sleep 30
+
+      - name: Set up Node (retry)
+        if: steps.setup_node.outcome == 'failure'
+        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
         with:
           node-version: "20"
           registry-url: "https://registry.npmjs.org"
@@ -410,6 +479,7 @@ jobs:
         # See the matching note in ci.yml: jetli's default installs an old
         # 0.10.x wasm-pack whose build subcommand rejects --features.
         uses: taiki-e/install-action@0fd46367812ee04360509b4169d9f659d6892bb2 # v2.79.15
+        timeout-minutes: 10 # fail fast on a stuck download instead of hanging the job
         with:
           tool: wasm-pack