analytics/.github/workflows/update-analytics.yml at main · sudo-anshul/analytics · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
name: Refresh Analytics Data

on:
  schedule:
    # Every 5 days at 9 AM UTC. Keeps gaps under the 7-day cache-eviction
    # window so the incremental dataset cache stays warm.
    - cron: '0 9 */5 * *'
  workflow_dispatch:

permissions:
  contents: read

jobs:
  refresh-data:
    runs-on: ubuntu-latest

    steps:
      - name: Checkout code
        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 #v7.0.1

      - name: Set up Python
        uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 #v7.0.0
        with:
          python-version: '3.11'

      - name: Install uv
        uses: astral-sh/setup-uv@11f9893b081a58869d3b5fccaea48c9e9e46f990 #v8.3.2
        with:
          version: "latest"

      - name: Install dependencies
        run: uv sync

      # Persist the incremental-fetch datasets across runs without committing
      # them to git. A unique key per run always saves; restore-keys pulls the
      # most recent prior dataset. If the cache is ever evicted, the pipeline's
      # 30-day self-heal just does one full fetch, then resumes incrementally.
      - name: Restore incremental datasets
        uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
        with:
          path: outputs/data/datasets
          key: analytics-datasets-${{ github.run_id }}
          restore-keys: |
            analytics-datasets-

      - name: Run all analytics pipelines
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: uv run python -m hiero_analytics.run_all

      # Only persist datasets when the run succeeds. Saving after a failed run
      # would let a partial snapshot become the next incremental baseline
      # (restore picks the most recent analytics-datasets- key); on failure we
      # keep the last good cache and let the next run resume from it.
      - name: Save incremental datasets
        uses: actions/cache/save@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
        with:
          path: outputs/data/datasets
          key: analytics-datasets-${{ github.run_id }}

      # Publish the self-contained dashboard to GitHub Pages so anyone can view the
      # latest refresh without cloning or regenerating. The HTML embeds every chart
      # as base64, so the site is a single index.html.
      - name: Assemble Pages site
        run: |
          mkdir -p _site
          cp outputs/dashboard.html _site/index.html

      - name: Upload Pages artifact
        uses: actions/upload-pages-artifact@fc324d3547104276b827a68afc52ff2a11cc49c9 # v5.0.0
        with:
          path: _site

  # Publish the freshly-built dashboard to GitHub Pages. Runs after the data refresh
  # regardless of whether the data changed, so the public page always reflects the
  # most recent run. Requires Pages "Source: GitHub Actions" to be enabled once in
  # the repository settings.
  deploy-pages:
    name: Deploy dashboard to GitHub Pages
    needs: refresh-data
    runs-on: ubuntu-latest
    permissions:
      pages: write
      id-token: write
    environment:
      name: github-pages
      url: ${{ steps.deployment.outputs.page_url }}
    concurrency:
      group: pages
      cancel-in-progress: false
    steps:
      - name: Deploy to GitHub Pages
        id: deployment
        uses: actions/deploy-pages@cd2ce8fcbc39b97be8ca5fce6e763baed58fa128 # v5.0.0