AutopilotMonitor/.github/workflows/ci.yml

name: CI

# Tests, typechecks and drift-checks every push to main and every pull request:
# the .NET suites, the web and MCP suites, and a guard that the generated rule
# files still match rules/guardrails.json.
#
# The deploy workflows build but never test, so this is the only place the suites
# actually run. It does not gate anything — main is deliberately unprotected, so a
# red run reports rather than blocks. Read the result and follow up.
#
# Path filters: commits that only bump a private submodule gitlink (internal/, infra/,
# .claude/commands) or touch prose cannot change anything the suites cover, so they are
# skipped instead of burning ~15 runner-minutes each. A gitlink bump reports the bare
# path ('internal', no trailing slash), which 'internal/**' does NOT match — both forms
# are listed. GitHub skips only when EVERY changed path matches; a commit that touches
# docs AND code still runs.
on:
  push:
    branches: [main]
    paths-ignore:
      - 'internal'
      - 'internal/**'
      - 'infra'
      - 'infra/**'
      - '.claude/**'
      - '.gitmodules'
      - '**/*.md'
      - 'LICENSE'
      - '.github/ISSUE_TEMPLATE/**'
      - '.github/FUNDING.yml'
      - '.github/dependabot.yml'
      - '.github/assets/**'
  pull_request:
    branches: [main]
    paths-ignore:
      - 'internal'
      - 'internal/**'
      - 'infra'
      - 'infra/**'
      - '.claude/**'
      - '.gitmodules'
      - '**/*.md'
      - 'LICENSE'
      - '.github/ISSUE_TEMPLATE/**'
      - '.github/FUNDING.yml'
      - '.github/dependabot.yml'
      - '.github/assets/**'
  workflow_dispatch:

permissions:
  contents: read

concurrency:
  group: ci-${{ github.ref }}
  cancel-in-progress: true

jobs:
  dotnet:
    name: .NET tests (backend + agent)
    # windows-latest is required: the agent test projects target net48.
    runs-on: windows-latest
    steps:
      - uses: actions/checkout@v7

      - uses: actions/setup-dotnet@v6
        with:
          dotnet-version: '10.0.x'

      - name: Restore
        run: dotnet restore AutopilotMonitor.sln

      - name: Build
        run: dotnet build AutopilotMonitor.sln --configuration Release --no-restore

      - name: Backend tests
        run: dotnet test src/Backend/AutopilotMonitor.Functions.Tests --configuration Release --no-build --verbosity quiet --logger "console;verbosity=minimal"

      - name: Agent V2 Core tests
        run: dotnet test src/Agent/AutopilotMonitor.Agent.V2.Core.Tests --configuration Release --no-build --verbosity quiet --logger "console;verbosity=minimal"

      - name: Decision Core tests
        run: dotnet test src/Agent/AutopilotMonitor.DecisionCore.Tests --configuration Release --no-build --verbosity quiet --logger "console;verbosity=minimal"

      - name: Summary Dialog tests
        run: dotnet test src/Agent/AutopilotMonitor.SummaryDialog.Tests --configuration Release --no-build --verbosity quiet --logger "console;verbosity=minimal"

  web:
    name: Web (typecheck + tests)
    runs-on: ubuntu-latest
    defaults:
      run:
        working-directory: src/Web/autopilot-monitor-web
    steps:
      - uses: actions/checkout@v7

      - uses: actions/setup-node@v7
        with:
          node-version: '22'
          cache: npm
          cache-dependency-path: src/Web/autopilot-monitor-web/package-lock.json

      - run: npm ci

      # next-env.d.ts + .next type stubs are gitignored (Next-managed since
      # v16); typegen generates them so tsc sees the same types as a build.
      - name: Generate Next.js types
        run: npx next typegen

      - name: Typecheck
        run: npx tsc --noEmit

      # Errors fail outright, and so does ANY warning: the codebase is
      # warning-clean and must stay that way — fix new findings, never
      # raise the cap.
      - name: Lint
        run: npm run lint -- --max-warnings 0

      - name: Tests
        run: npm test

  mcp:
    name: MCP server tests
    runs-on: ubuntu-latest
    defaults:
      run:
        working-directory: src/McpServer/autopilot-monitor-mcp
    steps:
      - uses: actions/checkout@v7

      - uses: actions/setup-node@v7
        with:
          node-version: '22'
          cache: npm
          cache-dependency-path: src/McpServer/autopilot-monitor-mcp/package-lock.json

      - run: npm ci

      - name: Typecheck
        run: npx tsc --noEmit

      # The vector-search tests tokenize with the real all-MiniLM-L6-v2 model
      # (~23 MB tokenizer + ONNX weights). transformers.js caches under
      # node_modules by default, which npm ci recreates — so every CI run
      # re-downloaded from huggingface.co and rate-limits (429) failed the job
      # (run 31252869254). Persist the model across runs instead; HF_CACHE_DIR
      # is honored by vector-search-provider.ts.
      - name: Cache embedding model
        uses: actions/cache@v6
        with:
          path: ${{ github.workspace }}/.hf-cache
          key: hf-model-Xenova-all-MiniLM-L6-v2

      - name: Tests
        run: npm test
        env:
          HF_CACHE_DIR: ${{ github.workspace }}/.hf-cache

  guardrails-in-sync:
    name: Generated guardrails match rules/guardrails.json
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v7

      - uses: actions/setup-node@v7
        with:
          node-version: '22'

      - name: Regenerate
        run: node rules/scripts/combine.js

      - name: Fail if the generated files drifted
        run: |
          if ! git diff --quiet; then
            echo "::error::Generated files are out of date. Run 'node rules/scripts/combine.js' and commit the result."
            git diff --stat
            exit 1
          fi

  shared-manifests-in-sync:
    name: Generated wire types match shared-manifests.json
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v7

      - uses: actions/setup-node@v7
        with:
          node-version: '22'

      # JSON ↔ C# parity is the dotnet job's SharedManifestParityTests; this job pins
      # JSON ↔ generated TS (shared-manifests.generated.ts, wire-types.generated.ts and the
      # MCP's wire-types + wire-vocabularies copies - the vocabularies are what the MCP
      # tool input schemas derive their z.enum() from).
      - name: Regenerate
        run: node scripts/generate-shared-manifest-types.js
        working-directory: src/Web/autopilot-monitor-web

      - name: Fail if the generated files drifted
        run: |
          if ! git diff --quiet -- src/Web/autopilot-monitor-web/utils/shared-manifests.generated.ts src/Web/autopilot-monitor-web/utils/wire-types.generated.ts src/McpServer/autopilot-monitor-mcp/src/generated/wire-types.generated.ts src/McpServer/autopilot-monitor-mcp/src/generated/wire-vocabularies.generated.ts; then
            echo "::error::Generated wire types are out of date. Run 'npm run generate:manifests' in src/Web/autopilot-monitor-web and commit the result."
            git diff --stat
            exit 1
          fi