Merge pull request #1634

ci: path-scope required CI lanes on PRs

.gitea/scripts/detect-changes.py

@@ -0,0 +1,174 @@
+#!/usr/bin/env python3
+"""Shared path-filter helper for Gitea Actions workflows.
+
+Computes changed files against the PR base SHA or push-before SHA and writes
+boolean outputs to GITHUB_OUTPUT. If the diff base is missing or untrusted, the
+helper fails open by setting every output in the selected profile to true.
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+import re
+import subprocess
+import sys
+from pathlib import Path
+
+
+PROFILES: dict[str, dict[str, str]] = {
+    "ci": {
+        "platform": r"^workspace-server/",
+        "canvas": r"^canvas/",
+        "python": r"^workspace/",
+        "scripts": r"^tests/e2e/|^scripts/|^infra/scripts/",
+    },
+    "handlers-postgres": {
+        "handlers": (
+            r"^workspace-server/internal/handlers/"
+            r"|^workspace-server/internal/wsauth/"
+            r"|^workspace-server/migrations/"
+            r"|^\.gitea/workflows/handlers-postgres-integration\.yml$"
+        ),
+    },
+    "e2e-api": {
+        "api": r"^workspace-server/|^tests/e2e/|^\.gitea/workflows/e2e-api\.yml$",
+    },
+}
+
+
+def classify(profile: str, paths: list[str]) -> dict[str, bool]:
+    patterns = PROFILES[profile]
+    return {
+        name: any(re.search(pattern, path) for path in paths)
+        for name, pattern in patterns.items()
+    }
+
+
+def all_true(profile: str) -> dict[str, bool]:
+    return {name: True for name in PROFILES[profile]}
+
+
+def resolve_base(event_name: str, pr_base_sha: str, push_before: str) -> str:
+    if event_name == "pull_request" and pr_base_sha:
+        return pr_base_sha
+    return push_before
+
+
+def is_zero_sha(value: str) -> bool:
+    return not value or bool(re.fullmatch(r"0+", value))
+
+
+def run_git(args: list[str], *, timeout: int = 30) -> subprocess.CompletedProcess[str]:
+    return subprocess.run(
+        ["git", *args],
+        check=False,
+        text=True,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+        timeout=timeout,
+    )
+
+
+def base_exists(base: str) -> bool:
+    return run_git(["cat-file", "-e", base]).returncode == 0
+
+
+def fetch_base(base: str, base_ref: str) -> None:
+    # Gitea may reject fetching an arbitrary unadvertised SHA from a shallow
+    # PR checkout. Fetch the advertised base branch first, then fall back to
+    # the SHA for hosts that allow it.
+    if base_ref:
+        run_git(["fetch", "--depth=1", "origin", base_ref])
+    if not base_exists(base):
+        run_git(["fetch", "--depth=1", "origin", base])
+
+
+def deepen_base_ref(base_ref: str) -> None:
+    if base_ref:
+        run_git(["fetch", "--deepen=200", "origin", base_ref], timeout=60)
+
+
+def merge_base(base: str) -> str | None:
+    proc = run_git(["merge-base", base, "HEAD"])
+    if proc.returncode != 0:
+        return None
+    value = proc.stdout.strip()
+    return value or None
+
+
+def changed_paths(base: str, *, use_merge_base: bool) -> list[str] | None:
+    compare_base = base
+    if use_merge_base:
+        compare_base = merge_base(base) or ""
+        if not compare_base:
+            return None
+
+    proc = run_git(["diff", "--name-only", compare_base, "HEAD"])
+    if proc.returncode != 0:
+        return None
+    return [line for line in proc.stdout.splitlines() if line]
+
+
+def write_outputs(values: dict[str, bool], output_path: str | None) -> None:
+    lines = [f"{name}={'true' if value else 'false'}" for name, value in values.items()]
+    if output_path:
+        with Path(output_path).open("a", encoding="utf-8") as fh:
+            for line in lines:
+                fh.write(line + "\n")
+    else:
+        for line in lines:
+            print(line)
+
+
+def detect(
+    profile: str,
+    event_name: str,
+    pr_base_sha: str,
+    push_before: str,
+    base_ref: str = "",
+) -> dict[str, bool]:
+    base = resolve_base(event_name, pr_base_sha, push_before)
+    if is_zero_sha(base):
+        return all_true(profile)
+
+    if not base_exists(base):
+        fetch_base(base, base_ref)
+    if not base_exists(base):
+        return all_true(profile)
+
+    use_merge_base = event_name == "pull_request"
+    if use_merge_base and base_ref and merge_base(base) is None:
+        deepen_base_ref(base_ref)
+
+    paths = changed_paths(base, use_merge_base=use_merge_base)
+    if paths is None:
+        return all_true(profile)
+    return classify(profile, paths)
+
+
+def parse_args(argv: list[str]) -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--profile", required=True, choices=sorted(PROFILES))
+    parser.add_argument("--event-name", default=os.environ.get("GITHUB_EVENT_NAME", ""))
+    parser.add_argument("--pr-base-sha", default="")
+    parser.add_argument("--base-ref", default="")
+    parser.add_argument("--push-before", default=os.environ.get("GITHUB_EVENT_BEFORE", ""))
+    return parser.parse_args(argv)
+
+
+def main(argv: list[str]) -> int:
+    args = parse_args(argv)
+    values = detect(
+        args.profile,
+        args.event_name,
+        args.pr_base_sha,
+        args.push_before,
+        args.base_ref,
+    )
+    write_outputs(values, os.environ.get("GITHUB_OUTPUT"))
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main(sys.argv[1:]))

.gitea/workflows/ci.yml

@@ -86,46 +86,17 @@ jobs:
         with:
           fetch-depth: 0
       - id: check
+        env:
+          PR_BASE_SHA: ${{ github.event.pull_request.base.sha }}
+          PR_BASE_REF: ${{ github.event.pull_request.base.ref }}
+          PUSH_BEFORE: ${{ github.event.before }}
         run: |
-          # For PR events: diff against the base branch (not HEAD~1 of the branch,
-          # which may be unrelated after force-pushes). When a push updates a PR,
-          # both pull_request and push events fire — prefer the PR base so that
-          # the diff is always computed against the actual merge base, not the
-          # previous SHA on the branch which may be on a different history line.
-          BASE="${GITHUB_BASE_REF:-${{ github.event.before }}}"
-          # GITHUB_BASE_REF is set for PR events (the base branch name).
-          # For pull_request events we use the stored base.sha; for push events
-          # (or when base.sha is unavailable) fall back to github.event.before.
-          if [ "${{ github.event_name }}" = "pull_request" ] && [ -n "${{ github.event.pull_request.base.sha }}" ]; then
-            BASE="${{ github.event.pull_request.base.sha }}"
-          fi
-          # Fallback: if BASE is empty or all zeros (new branch), run everything
-          if [ -z "$BASE" ] || echo "$BASE" | grep -qE '^0+$'; then
-            echo "platform=true" >> "$GITHUB_OUTPUT"
-            echo "canvas=true" >> "$GITHUB_OUTPUT"
-            echo "python=true" >> "$GITHUB_OUTPUT"
-            echo "scripts=true" >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-          # Workflow-only edits are covered by the workflow lint family
-          # and by this workflow's always-present required jobs. Do not fan
-          # those edits out into Go/Canvas/Python/shellcheck work; the
-          # downstream jobs still emit their required contexts via no-op
-          # steps when their surface flag is false.
-          #
-          # If the diff itself cannot be trusted, fail open by running every
-          # surface instead of silently under-testing the PR.
-          if ! DIFF=$(git diff --name-only "$BASE" HEAD 2>/dev/null); then
-            echo "platform=true" >> "$GITHUB_OUTPUT"
-            echo "canvas=true" >> "$GITHUB_OUTPUT"
-            echo "python=true" >> "$GITHUB_OUTPUT"
-            echo "scripts=true" >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-          echo "platform=$(echo "$DIFF" | grep -qE '^workspace-server/' && echo true || echo false)" >> "$GITHUB_OUTPUT"
-          echo "canvas=$(echo "$DIFF" | grep -qE '^canvas/' && echo true || echo false)" >> "$GITHUB_OUTPUT"
-          echo "python=$(echo "$DIFF" | grep -qE '^workspace/' && echo true || echo false)" >> "$GITHUB_OUTPUT"
-          echo "scripts=$(echo "$DIFF" | grep -qE '^tests/e2e/|^scripts/|^infra/scripts/' && echo true || echo false)" >> "$GITHUB_OUTPUT"
+          python3 .gitea/scripts/detect-changes.py \
+            --profile ci \
+            --event-name "${{ github.event_name }}" \
+            --pr-base-sha "$PR_BASE_SHA" \
+            --base-ref "$PR_BASE_REF" \
+            --push-before "${GITHUB_EVENT_BEFORE:-$PUSH_BEFORE}"
 
   # Platform (Go) — Go build/vet/test/lint + coverage gates. The always-run
   # + per-step gating shape preserves the GitHub-side required-check name
@@ -133,6 +104,7 @@ jobs:
   # the name match works on PRs that don't touch workspace-server/).
   platform-build:
     name: Platform (Go)
+    needs: changes
     runs-on: ubuntu-latest
     # mc#774 (closed 2026-05-14): Phase 4 flip of the platform-build job.
     # Phase 4 (#656) originally flipped this to continue-on-error: false based on
@@ -153,29 +125,29 @@ jobs:
       run:
         working-directory: workspace-server
     steps:
-      - if: false
+      - if: ${{ github.event_name == 'pull_request' && needs.changes.outputs.platform != 'true' }}
         working-directory: .
-        run: echo "No platform/** changes — skipping real build steps; this job always runs to satisfy the required-check name on branch protection."
-      - if: always()
+        run: echo "No workspace-server/** changes on this PR — Platform (Go) gate satisfied without running Go build/test/lint."
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.platform == 'true' }}
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.platform == 'true' }}
         uses: actions/setup-go@40f1582b2485089dde7abd97c1529aa768e1baff # v5
         with:
           go-version: 'stable'
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.platform == 'true' }}
         run: go mod download
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.platform == 'true' }}
         run: go build ./cmd/server
       # CLI (molecli) moved to standalone repo: git.moleculesai.app/molecule-ai/molecule-cli
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.platform == 'true' }}
         run: go vet ./...
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.platform == 'true' }}
         name: Install golangci-lint
         run: go install github.com/golangci/golangci-lint/v2/cmd/golangci-lint@v2.12.2
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.platform == 'true' }}
         name: Run golangci-lint
         run: $(go env GOPATH)/bin/golangci-lint run --timeout 3m ./...
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.platform == 'true' }}
         name: Diagnostic — per-package verbose 60s
         run: |
           set +e
@@ -191,7 +163,7 @@ jobs:
           echo "::endgroup::"
         # mc#774: pre-existing continue-on-error mask; root-fix and remove, do not renew silently.
         continue-on-error: true
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.platform == 'true' }}
         name: Run tests with race detection and coverage
         # Explicit timeout: cold runner cache causes OOM kills at ~4m39s on the
         # full ./... suite with race detection + coverage. A 10m per-step timeout
@@ -199,7 +171,7 @@ jobs:
         # instead of OOM-killing. The job-level timeout (15m) is a backstop.
         run: go test -race -timeout 10m -coverprofile=coverage.out ./...
 
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.platform == 'true' }}
         name: Per-file coverage report
         # Advisory — lists every source file with its coverage so reviewers
         # can see at-a-glance where gaps are. Sorted ascending so the worst
@@ -213,7 +185,7 @@ jobs:
                    END {for (f in s) printf "%6.1f%%  %s\n", s[f]/c[f], f}' \
             | sort -n
 
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.platform == 'true' }}
         name: Check coverage thresholds
         # Enforces two gates from #1823 Layer 1:
         #   1. Total floor (25% — ratchet plan in COVERAGE_FLOOR.md).
@@ -301,6 +273,7 @@ jobs:
   # siblings — verified empirically on PR #2314).
   canvas-build:
     name: Canvas (Next.js)
+    needs: changes
     runs-on: ubuntu-latest
     timeout-minutes: 20
     # Phase 4 (RFC #219 §1): confirmed green on main 2026-05-12.
@@ -309,20 +282,20 @@ jobs:
       run:
         working-directory: canvas
     steps:
-      - if: false
+      - if: ${{ github.event_name == 'pull_request' && needs.changes.outputs.canvas != 'true' }}
         working-directory: .
-        run: echo "No canvas/** changes — skipping real build steps; this job always runs to satisfy the required-check name on branch protection."
-      - if: always()
+        run: echo "No canvas/** changes on this PR — Canvas (Next.js) gate satisfied without running npm build/test."
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.canvas == 'true' }}
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.canvas == 'true' }}
         uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
         with:
           node-version: '22'
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.canvas == 'true' }}
         run: npm ci --include=optional --prefer-offline
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.canvas == 'true' }}
         run: npm run build
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.canvas == 'true' }}
         name: Run tests with coverage
         # Coverage instrumentation is configured in canvas/vitest.config.ts
         # (provider: v8, reporters: text + html + json-summary). Step 2 of
@@ -331,7 +304,7 @@ jobs:
         # tracked in #1815) after the team sees what current coverage is.
         run: npx vitest run --coverage
       - name: Upload coverage summary as artifact
-        if: always()
+        if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.canvas == 'true' }}
         # Pinned to v3 for Gitea act_runner v0.6 compatibility — v4+ uses
         # the GHES 3.10+ artifact protocol that Gitea 1.22.x does NOT
         # implement, surfacing as `GHESNotSupportedError: @actions/artifact
@@ -348,15 +321,16 @@ jobs:
   # Shellcheck (E2E scripts) — required check, always runs.
   shellcheck:
     name: Shellcheck (E2E scripts)
+    needs: changes
     runs-on: ubuntu-latest
     # Phase 4 (RFC #219 §1): confirmed green on main 2026-05-12.
     continue-on-error: false
     steps:
-      - if: false
-        run: echo "No tests/e2e/ or infra/scripts/ changes — skipping real shellcheck; this job always runs to satisfy the required-check name on branch protection."
-      - if: always()
+      - if: ${{ github.event_name == 'pull_request' && needs.changes.outputs.scripts != 'true' }}
+        run: echo "No tests/e2e, scripts, or infra/scripts changes on this PR — Shellcheck gate satisfied without running script checks."
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.scripts == 'true' }}
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.scripts == 'true' }}
         name: Run shellcheck on tests/e2e/*.sh and infra/scripts/*.sh
         # shellcheck is pre-installed on ubuntu-latest runners (via apt).
         # infra/scripts/ is included because setup.sh + nuke.sh gate the
@@ -367,16 +341,16 @@ jobs:
           find tests/e2e infra/scripts -type f -name '*.sh' -print0 \
             | xargs -0 shellcheck --severity=warning
 
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.scripts == 'true' }}
         name: Lint cleanup-trap hygiene (RFC #2873)
         run: bash tests/e2e/lint_cleanup_traps.sh
 
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.scripts == 'true' }}
         name: Run E2E bash unit tests (no live infra)
         run: |
           bash tests/e2e/test_model_slug.sh
 
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.scripts == 'true' }}
         name: Test ECR promote-tenant-image script (mock-driven, no live infra)
         # Covers scripts/promote-tenant-image.sh — the codified
         # :staging-latest → :latest ECR promote + tenant fleet redeploy
@@ -386,7 +360,7 @@ jobs:
         run: |
           bash scripts/test-promote-tenant-image.sh
 
-      - if: always()
+      - if: ${{ github.event_name != 'pull_request' || needs.changes.outputs.scripts == 'true' }}
         name: Shellcheck promote-tenant-image script
         # scripts/ is excluded from the bulk shellcheck pass above (legacy
         # SC3040/SC3043 cleanup pending). Run shellcheck explicitly on

.gitea/workflows/e2e-api.yml

@@ -132,31 +132,13 @@ jobs:
         with:
           fetch-depth: 0
       - id: decide
-        # Inline replacement for dorny/paths-filter — same pattern PR#372's
-        # ci.yml port used. Diffs against the PR base or push BEFORE SHA,
-        # then matches against the api-relevant path set.
         run: |
-          BASE="${GITHUB_BASE_REF:-${{ github.event.before }}}"
-          if [ "${{ github.event_name }}" = "pull_request" ] && [ -n "${{ github.event.pull_request.base.sha }}" ]; then
-            BASE="${{ github.event.pull_request.base.sha }}"
-          fi
-          if [ -z "$BASE" ] || echo "$BASE" | grep -qE '^0+$'; then
-            echo "api=true" >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-          if ! git cat-file -e "$BASE" 2>/dev/null; then
-            git fetch --depth=1 origin "$BASE" 2>/dev/null || true
-          fi
-          if ! git cat-file -e "$BASE" 2>/dev/null; then
-            echo "api=true" >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-          CHANGED=$(git diff --name-only "$BASE" HEAD)
-          if echo "$CHANGED" | grep -qE '^(workspace-server/|tests/e2e/|\.gitea/workflows/e2e-api\.yml$)'; then
-            echo "api=true" >> "$GITHUB_OUTPUT"
-          else
-            echo "api=false" >> "$GITHUB_OUTPUT"
-          fi
+          python3 .gitea/scripts/detect-changes.py \
+            --profile e2e-api \
+            --event-name "${{ github.event_name }}" \
+            --pr-base-sha "${{ github.event.pull_request.base.sha }}" \
+            --base-ref "${{ github.event.pull_request.base.ref }}" \
+            --push-before "${GITHUB_EVENT_BEFORE:-${{ github.event.before }}}"
 
   # ONE job (no job-level `if:`) that always runs and reports under the
   # required-check name `E2E API Smoke Test`. Real work is gated per-step

.gitea/workflows/handlers-postgres-integration.yml

@@ -101,36 +101,13 @@ jobs:
           # not present in the shallow checkout.
           fetch-depth: 2
       - id: filter
-        # Inline replacement for dorny/paths-filter — see e2e-api.yml.
         run: |
-          # Gitea Actions evaluates github.event.before to empty string in shell
-          # scripts. Use GITHUB_EVENT_BEFORE shell env var instead (Gitea
-          # correctly populates it for push events). PR case uses template var.
-          BASE=""
-          if [ "${{ github.event_name }}" = "pull_request" ] && [ -n "${{ github.event.pull_request.base.sha }}" ]; then
-            BASE="${{ github.event.pull_request.base.sha }}"
-          elif [ -n "$GITHUB_EVENT_BEFORE" ]; then
-            BASE="$GITHUB_EVENT_BEFORE"
-          fi
-          if [ -z "$BASE" ] || echo "$BASE" | grep -qE '^0+$'; then
-            echo "handlers=true" >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-          # timeout 30 guards against the case where BASE points to a ref that
-          # git can resolve but cat-file hangs (rare on corrupted objects).
-          if ! timeout 30 git cat-file -e "$BASE" 2>/dev/null; then
-            git fetch --depth=1 origin "$BASE" 2>/dev/null || true
-          fi
-          if ! timeout 30 git cat-file -e "$BASE" 2>/dev/null; then
-            echo "handlers=true" >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-          CHANGED=$(git diff --name-only "$BASE" HEAD)
-          if echo "$CHANGED" | grep -qE '^(workspace-server/internal/handlers/|workspace-server/internal/wsauth/|workspace-server/migrations/|\.gitea/workflows/handlers-postgres-integration\.yml$)'; then
-            echo "handlers=true" >> "$GITHUB_OUTPUT"
-          else
-            echo "handlers=false" >> "$GITHUB_OUTPUT"
-          fi
+          python3 .gitea/scripts/detect-changes.py \
+            --profile handlers-postgres \
+            --event-name "${{ github.event_name }}" \
+            --pr-base-sha "${{ github.event.pull_request.base.sha }}" \
+            --base-ref "${{ github.event.pull_request.base.ref }}" \
+            --push-before "${GITHUB_EVENT_BEFORE:-}"
 
   # Single-job-with-per-step-if pattern: always runs to satisfy the
   # required-check name on branch protection; real work gates on the

tests/test_detect_changes.py

@@ -0,0 +1,193 @@
+"""Tests for `.gitea/scripts/detect-changes.py`."""
+
+from __future__ import annotations
+
+import importlib.util
+from pathlib import Path
+
+
+REPO_ROOT = Path(__file__).resolve().parents[1]
+SCRIPT = REPO_ROOT / ".gitea" / "scripts" / "detect-changes.py"
+
+
+def load_module():
+    spec = importlib.util.spec_from_file_location("detect_changes", SCRIPT)
+    assert spec is not None
+    module = importlib.util.module_from_spec(spec)
+    assert spec.loader is not None
+    spec.loader.exec_module(module)
+    return module
+
+
+def test_ci_profile_classifies_surfaces():
+    mod = load_module()
+
+    assert mod.classify("ci", ["workspace-server/internal/handlers/a2a_proxy.go"]) == {
+        "platform": True,
+        "canvas": False,
+        "python": False,
+        "scripts": False,
+    }
+    assert mod.classify("ci", ["canvas/src/app/page.tsx"]) == {
+        "platform": False,
+        "canvas": True,
+        "python": False,
+        "scripts": False,
+    }
+    assert mod.classify("ci", ["tests/e2e/test_model_slug.sh"]) == {
+        "platform": False,
+        "canvas": False,
+        "python": False,
+        "scripts": True,
+    }
+    assert mod.classify("ci", [".gitea/workflows/ci.yml", "README.md"]) == {
+        "platform": False,
+        "canvas": False,
+        "python": False,
+        "scripts": False,
+    }
+
+
+def test_handlers_postgres_profile_is_narrower_than_workspace_server():
+    mod = load_module()
+
+    assert mod.classify("handlers-postgres", ["workspace-server/internal/handlers/a2a_proxy.go"]) == {
+        "handlers": True,
+    }
+    assert mod.classify("handlers-postgres", ["workspace-server/internal/provisioner/provisioner.go"]) == {
+        "handlers": False,
+    }
+
+
+def test_e2e_api_profile_covers_api_inputs():
+    mod = load_module()
+
+    assert mod.classify("e2e-api", ["workspace-server/internal/handlers/workspace.go"]) == {
+        "api": True,
+    }
+    assert mod.classify("e2e-api", ["tests/e2e/test_api.sh"]) == {"api": True}
+    assert mod.classify("e2e-api", ["canvas/src/app/page.tsx"]) == {"api": False}
+
+
+def test_fail_open_all_true_for_missing_base():
+    mod = load_module()
+
+    assert mod.all_true("ci") == {
+        "platform": True,
+        "canvas": True,
+        "python": True,
+        "scripts": True,
+    }
+
+
+def test_fetch_base_prefers_advertised_base_ref(monkeypatch):
+    mod = load_module()
+    calls: list[list[str]] = []
+    exists_checks = 0
+
+    def fake_base_exists(base: str) -> bool:
+        nonlocal exists_checks
+        exists_checks += 1
+        return exists_checks >= 1
+
+    def fake_run_git(args: list[str], *, timeout: int = 30):
+        calls.append(args)
+
+        class Result:
+            returncode = 0
+            stdout = ""
+            stderr = ""
+
+        return Result()
+
+    monkeypatch.setattr(mod, "base_exists", fake_base_exists)
+    monkeypatch.setattr(mod, "run_git", fake_run_git)
+
+    mod.fetch_base("abc123", "main")
+
+    assert calls == [["fetch", "--depth=1", "origin", "main"]]
+
+
+def test_fetch_base_falls_back_to_sha_when_ref_fetch_does_not_materialize(monkeypatch):
+    mod = load_module()
+    calls: list[list[str]] = []
+
+    monkeypatch.setattr(mod, "base_exists", lambda _base: False)
+
+    def fake_run_git(args: list[str], *, timeout: int = 30):
+        calls.append(args)
+
+        class Result:
+            returncode = 0
+            stdout = ""
+            stderr = ""
+
+        return Result()
+
+    monkeypatch.setattr(mod, "run_git", fake_run_git)
+
+    mod.fetch_base("abc123", "main")
+
+    assert calls == [
+        ["fetch", "--depth=1", "origin", "main"],
+        ["fetch", "--depth=1", "origin", "abc123"],
+    ]
+
+
+def test_changed_paths_uses_merge_base_for_pull_request(monkeypatch):
+    mod = load_module()
+    calls: list[list[str]] = []
+
+    def fake_run_git(args: list[str], *, timeout: int = 30):
+        calls.append(args)
+
+        class Result:
+            returncode = 0
+            stdout = "workspace/agent.py\n"
+            stderr = ""
+
+        if args[0] == "merge-base":
+            Result.stdout = "merge123\n"
+        return Result()
+
+    monkeypatch.setattr(mod, "run_git", fake_run_git)
+
+    assert mod.changed_paths("base123", use_merge_base=True) == ["workspace/agent.py"]
+    assert calls == [
+        ["merge-base", "base123", "HEAD"],
+        ["diff", "--name-only", "merge123", "HEAD"],
+    ]
+
+
+def test_detect_deepens_base_ref_when_pr_merge_base_missing(monkeypatch):
+    mod = load_module()
+    calls: list[tuple[str, str | None]] = []
+    merge_base_calls = 0
+
+    monkeypatch.setattr(mod, "base_exists", lambda _base: True)
+
+    def fake_merge_base(base: str):
+        nonlocal merge_base_calls
+        merge_base_calls += 1
+        if merge_base_calls == 1:
+            return None
+        return "merge123"
+
+    def fake_deepen_base_ref(base_ref: str):
+        calls.append(("deepen", base_ref))
+
+    def fake_changed_paths(base: str, *, use_merge_base: bool):
+        calls.append(("changed", str(use_merge_base)))
+        return [".gitea/workflows/ci.yml"]
+
+    monkeypatch.setattr(mod, "merge_base", fake_merge_base)
+    monkeypatch.setattr(mod, "deepen_base_ref", fake_deepen_base_ref)
+    monkeypatch.setattr(mod, "changed_paths", fake_changed_paths)
+
+    assert mod.detect("ci", "pull_request", "base123", "", "main") == {
+        "platform": False,
+        "canvas": False,
+        "python": False,
+        "scripts": False,
+    }
+    assert calls == [("deepen", "main"), ("changed", "True")]

tests/test_lint_workflow_yaml.py

@@ -26,9 +26,11 @@ import re
 import subprocess
 import sys
 import textwrap
+import importlib.util
 from pathlib import Path
 
 import pytest  # noqa: F401  (declares the dep)
+import yaml
 
 REPO_ROOT = Path(__file__).resolve().parents[1]
 SCRIPT = REPO_ROOT / ".gitea" / "scripts" / "lint-workflow-yaml.py"
@@ -616,16 +618,24 @@ def test_rule10_docker_info_head_in_separate_step_without_pipefail_passes(tmp_pa
 
 CI_WORKFLOW = REPO_ROOT / ".gitea" / "workflows" / "ci.yml"
 CI_SURFACES = ("platform", "canvas", "python", "scripts")
+DETECT_CHANGES_SCRIPT = REPO_ROOT / ".gitea" / "scripts" / "detect-changes.py"
+
+
+def _load_detect_changes():
+    spec = importlib.util.spec_from_file_location("detect_changes", DETECT_CHANGES_SCRIPT)
+    assert spec is not None
+    module = importlib.util.module_from_spec(spec)
+    assert spec.loader is not None
+    spec.loader.exec_module(module)
+    return module
 
 
 def _ci_change_patterns() -> dict[str, re.Pattern[str]]:
-    text = CI_WORKFLOW.read_text(encoding="utf-8")
-    patterns: dict[str, re.Pattern[str]] = {}
-    for surface, pattern in re.findall(
-        r'echo "(platform|canvas|python|scripts)=.*?grep -qE \'([^\']+)\'',
-        text,
-    ):
-        patterns[surface] = re.compile(pattern)
+    detect_changes = _load_detect_changes()
+    patterns = {
+        surface: re.compile(pattern)
+        for surface, pattern in detect_changes.PROFILES["ci"].items()
+    }
     assert set(patterns) == set(CI_SURFACES)
     return patterns
 
@@ -693,3 +703,58 @@ def test_ci_change_detector_docs_and_meta_scripts_do_not_trigger_surfaces():
         "python": False,
         "scripts": False,
     }
+
+
+def test_ci_platform_go_pr_steps_are_path_scoped():
+    doc = yaml.safe_load(CI_WORKFLOW.read_text(encoding="utf-8"))
+    platform = doc["jobs"]["platform-build"]
+    assert platform.get("needs") == "changes"
+
+    expensive_steps = [
+        step
+        for step in platform["steps"]
+        if step.get("uses")
+        or step.get("run", "").startswith("go ")
+        or "golangci-lint" in step.get("run", "")
+    ]
+    assert expensive_steps
+    for step in expensive_steps:
+        expr = step.get("if", "")
+        assert "github.event_name != 'pull_request'" in expr
+        assert "needs.changes.outputs.platform == 'true'" in expr
+
+
+def test_ci_canvas_nextjs_pr_steps_are_path_scoped():
+    doc = yaml.safe_load(CI_WORKFLOW.read_text(encoding="utf-8"))
+    canvas = doc["jobs"]["canvas-build"]
+    assert canvas.get("needs") == "changes"
+
+    expensive_steps = [
+        step
+        for step in canvas["steps"]
+        if step.get("uses")
+        or step.get("run", "").startswith("npm ")
+        or step.get("run", "").startswith("npx ")
+    ]
+    assert expensive_steps
+    for step in expensive_steps:
+        expr = step.get("if", "")
+        assert "github.event_name != 'pull_request'" in expr
+        assert "needs.changes.outputs.canvas == 'true'" in expr
+
+
+def test_ci_shellcheck_pr_steps_are_path_scoped():
+    doc = yaml.safe_load(CI_WORKFLOW.read_text(encoding="utf-8"))
+    shellcheck = doc["jobs"]["shellcheck"]
+    assert shellcheck.get("needs") == "changes"
+
+    expensive_steps = [
+        step
+        for step in shellcheck["steps"]
+        if step.get("uses") or step.get("run", "").startswith(("bash ", "find ", "shellcheck "))
+    ]
+    assert expensive_steps
+    for step in expensive_steps:
+        expr = step.get("if", "")
+        assert "github.event_name != 'pull_request'" in expr
+        assert "needs.changes.outputs.scripts == 'true'" in expr