fix(ci): label every harness tree as backend (#8029)

* fix(ci): label every harness tree as backend

`area:backend` enumerated the harness subdirectories that map to it instead
of the trees that map elsewhere, so thirteen of the twenty-eight directories
under `deerflow/` matched no area rule at all: community/, authz/, scheduler/,
storage/, tui/ and eight more. A PR that only touched `deerflow/community/`
therefore came out unlabelled, or with `area:docs` alone when it also edited a
markdown file — #7482 (crawl4ai) and #7826 (jina) are merged examples.

Match the harness as a whole and exclude the six trees that carry a more
specific label (agents, subagents, reflection, sandbox, skills, mcp). Checked
against all 28 directories: the 13 unlabelled ones now match `area:backend`,
and the sandbox / skills / mcp / agents / frontend results are unchanged.

* fix(ci): cover backend package paths in PR triage

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

.github/workflows/triage.yml

@@ -55,7 +55,13 @@ jobs:
             // ---- area: replaces .github/labeler.yml (path -> area) ----
             const AREA_RULES = [
               ['area:frontend', [/^frontend\//]],
-              ['area:backend',  [/^backend\/app\//, /^backend\/packages\/harness\/deerflow\/(runtime|persistence|config|tools|guardrails|tracing|models|utils|uploads)\//]],
+              // Cover both backend packages. Keep the harness exclusions aligned
+              // with the dedicated tree rules below; the offline replay checks this.
+              ['area:backend',  [
+                /^backend\/app\//,
+                /^backend\/packages\/harness\/(?!deerflow\/(?:agents|subagents|reflection|sandbox|skills|mcp)\/)/,
+                /^backend\/packages\/extension-api\//,
+              ]],
               ['area:agents',   [/^backend\/packages\/harness\/deerflow\/(agents|subagents|reflection)\//, /(^|\/)langgraph\.json$/, /^backend\/.*\/prompts\//]],
               ['area:sandbox',  [/^docker\//, /^backend\/packages\/harness\/deerflow\/sandbox\//, /(^|\/)Dockerfile$/]],
               ['area:skills',   [/^skills\//, /^backend\/packages\/harness\/deerflow\/skills\//, /^frontend\/src\/core\/skills\//]],

backend/tests/test_label_declarations.py

@@ -1,8 +1,11 @@
-"""Offline checks of the triage workflow's literal label declarations."""
+"""Offline checks of the triage workflow's label declarations and area rules."""
 
 from __future__ import annotations
 
 import importlib.util
+import json
+import shutil
+import subprocess
 from pathlib import Path
 
 import pytest
@@ -193,3 +196,74 @@ def test_every_real_applied_label_is_enforced(files, capsys, label):
     triage.write_text((REPO_ROOT / ".github/workflows/triage.yml").read_text(encoding="utf-8"), encoding="utf-8")
     assert checker.main() == 1
     assert f"  - {label}\n" in capsys.readouterr().err
+
+
+@pytest.mark.skipif(shutil.which("node") is None, reason="Workflow replay requires Node.js")
+def test_pr_area_labels_cover_backend_packages():
+    harness = "backend/packages/harness"
+    deerflow = REPO_ROOT / harness / "deerflow"
+    specific_areas = {
+        "agents": "area:agents",
+        "subagents": "area:agents",
+        "reflection": "area:agents",
+        "sandbox": "area:sandbox",
+        "skills": "area:skills",
+        "mcp": "area:mcp",
+    }
+    cases = [
+        ([f"{harness}/pyproject.toml", "backend/uv.lock"], {"area:backend", "area:deps"}),
+        (["backend/packages/extension-api/deerflow_extension_api/__init__.py"], {"area:backend"}),
+        ([f"{harness}/deerflow/__init__.py"], {"area:backend"}),
+        ([f"{harness}/deerflow/agents_extra/example.py"], {"area:backend"}),
+        (
+            ["frontend/src/example.tsx", f"{harness}/deerflow/agents/example.py", f"{harness}/deerflow/community/README.md"],
+            {"area:frontend", "area:agents", "area:backend", "area:docs"},
+        ),
+    ]
+    for directory in sorted(deerflow.iterdir()):
+        if directory.is_dir() and directory.name != "__pycache__":
+            path = directory.relative_to(REPO_ROOT).as_posix()
+            area = specific_areas.get(directory.name, "area:backend")
+            cases.append(([f"{path}/example.py"], {area}))
+
+    scripts = checker.workflow_scripts(checker.TRIAGE_WORKFLOW.read_text(encoding="utf-8"))
+    (script,) = (source for source in scripts if "const AREA_RULES =" in source)
+    result = subprocess.run(
+        [
+            "node",
+            "-e",
+            """
+const { readFileSync } = require('node:fs');
+const { script, changes } = JSON.parse(readFileSync(0, 'utf8'));
+const AsyncFunction = Object.getPrototypeOf(async function () {}).constructor;
+const applyLabels = new AsyncFunction('github', 'context', 'core', script);
+
+async function replay(paths) {
+  const labels = [];
+  const github = {
+    paginate: (list) => list(),
+    rest: {
+      pulls: { listFiles: () => paths.map(filename => ({ filename })) },
+      issues: {
+        listLabelsOnIssue: () => [],
+        addLabels: (request) => { labels.push(...request.labels); },
+      },
+    },
+  };
+  const context = { repo: { owner: 'test', repo: 'test' }, payload: { pull_request: { number: 1 }, action: 'synchronize' } };
+  await applyLabels(github, context, { info() {} });
+  return labels.filter(label => label.startsWith('area:'));
+}
+
+Promise.all(changes.map(replay)).then(labels => console.log(JSON.stringify(labels)));
+""",
+        ],
+        input=json.dumps({"script": script, "changes": [paths for paths, _ in cases]}),
+        capture_output=True,
+        encoding="utf-8",
+        check=False,
+        timeout=10,
+    )
+    assert result.returncode == 0, result.stderr
+    for (paths, expected), labels in zip(cases, json.loads(result.stdout), strict=True):
+        assert sorted(labels) == sorted(expected), paths