bridge tests: fake serves workflow contents; cover invalid-workflow status

b7a7e94 made the bridge read workflow files, which the strict fake Gitea
refused (7 red). The fake now serves contents (404 when absent), and new
tests cover: error posted with no runs, valid files add nothing, no repost,
.gitea/workflows wins over .github/workflows, and each workflow_problem
shape. pyyaml declared in dev extras (the bridge imports it).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

api/tests/test_pr_status_bridge.py

@@ -8,6 +8,7 @@ no status at all.
 
 from __future__ import annotations
 
+import base64
 import importlib.util
 from pathlib import Path
 
@@ -35,12 +36,23 @@ def _run(i, wf, job, status, sha=SHA, n=1):
 
 
 class Fake:
-    def __init__(self, runs=(), statuses=(), gh_prs=(), wg_prs=()):
+    def __init__(self, runs=(), statuses=(), gh_prs=(), wg_prs=(), workflows=None):
         self.runs, self.statuses = list(runs), list(statuses)
+        self.workflows = workflows or {}  # {path: yaml text} at every commit
         self.gh_prs, self.wg_prs = list(gh_prs), list(wg_prs)
         self.posted, self.opened, self.closed = [], [], []
 
     def gitea(self, method, path, body=None):
+        if "/contents/" in path:
+            want = path.split("/contents/", 1)[1].split("?", 1)[0]
+            if want in self.workflows:
+                return 200, {"content": base64.b64encode(self.workflows[want].encode()).decode()}
+            files = [
+                {"type": "file", "name": k.rsplit("/", 1)[1], "path": k}
+                for k in self.workflows
+                if k.rsplit("/", 1)[0] == want
+            ]
+            return (200, files) if files else (404, None)
         if "/actions/tasks" in path:
             page = int(path.rsplit("page=", 1)[1])
             return 200, {"workflow_runs": self.runs[(page - 1) * 50 : page * 50]}
@@ -209,3 +221,54 @@ def test_transport_blips_are_retried_but_http_errors_are_not(monkeypatch):
     monkeypatch.setattr(bridge.urllib.request, "urlopen", forbidden)
     assert bridge._call("http://x", "t", "GET", "/p") == (403, None)
     assert calls["n"] == 1
+
+
+GOOD = "on: push\njobs:\n  test:\n    runs-on: ubuntu-latest\n    steps: []\n"
+BROKEN = "on: push\njobs:\n  test:\n    runs-on: x\n   steps: [\n"
+
+
+def test_invalid_workflow_gets_an_error_status_even_with_no_runs(fake):
+    # Gitea fires NO run for an invalid file: without this the PR shows nothing.
+    f = fake(workflows={".github/workflows/ci.yml": BROKEN})
+    bridge.post_statuses("windy-chat", SHA)
+    assert [(p["context"], p["state"]) for p in f.posted] == [("windy-git/ci/workflow", "error")]
+    assert "invalid YAML at line 5" in f.posted[0]["description"]
+    assert f.posted[0]["target_url"].endswith(f"/src/commit/{SHA}/.github/workflows/ci.yml")
+
+
+def test_valid_workflows_post_nothing_extra(fake):
+    f = fake(runs=[_run(1, "ci.yml", "test", "success")], workflows={".github/workflows/ci.yml": GOOD})
+    bridge.post_statuses("windy-chat", SHA)
+    assert [p["context"] for p in f.posted] == ["windy-git/ci/test"]
+
+
+def test_workflow_error_is_not_reposted(fake):
+    f = fake(
+        workflows={".github/workflows/ci.yml": BROKEN},
+        statuses=[{"context": "windy-git/ci/workflow", "state": "error"}],
+    )
+    bridge.post_statuses("windy-chat", SHA)
+    assert f.posted == []
+
+
+def test_gitea_dir_wins_over_github_dir(fake):
+    # Gitea runs .gitea/workflows when it has files and ignores .github/workflows.
+    f = fake(workflows={".gitea/workflows/ci.yml": GOOD, ".github/workflows/old.yml": BROKEN})
+    bridge.post_statuses("windy-chat", SHA)
+    assert f.posted == []
+
+
+@pytest.mark.parametrize(
+    "text, problem",
+    [
+        (GOOD, None),
+        ("on: push\njobs:\n  a:\n    uses: ./x.yml\n", None),
+        (BROKEN, "invalid YAML at line 5"),
+        ("jobs:\n  a:\n    runs-on: x\n", "no `on:` trigger"),
+        ("on: push\n", "no `jobs:`"),
+        ("on: push\njobs:\n  a:\n    steps: []\n", "job `a` has no `runs-on:`"),
+        ("- a\n", "not a YAML mapping"),
+    ],
+)
+def test_workflow_problem(text, problem):
+    assert bridge.workflow_problem(text) == problem

pyproject.toml

@@ -31,7 +31,7 @@ dependencies = [
 ]
 
 [project.optional-dependencies]
-dev = ["pytest>=8.3", "pytest-asyncio>=0.24", "ruff>=0.7", "mypy>=1.13"]
+dev = ["pytest>=8.3", "pyyaml>=6.0", "pytest-asyncio>=0.24", "ruff>=0.7", "mypy>=1.13"]
 
 [tool.ruff]
 line-length = 100

scripts/pr_status_bridge.py

@@ -28,6 +28,7 @@ repo code, and no secret is handed to any repo.
 
 from __future__ import annotations
 
+import base64
 import json
 import os
 import re
@@ -36,6 +37,8 @@ import time
 import urllib.error
 import urllib.request
 
+import yaml
+
 GITEA = os.environ.get("BRIDGE_GITEA_URL", "http://localhost:3080").rstrip("/")
 PUBLIC = "https://app.windygit.com"
 GITEA_TOKEN = os.environ.get("GITEA_ADMIN_TOKEN", "")
@@ -86,6 +89,62 @@ for _entry in os.environ.get(
         NON_BLOCKING[_repo.strip()] = {j.strip() for j in _jobs.split(",") if j.strip()}
 
 
+# Gitea reads the FIRST of these dirs that has workflow files at a commit (1.24).
+WORKFLOW_DIRS = (".gitea/workflows", ".github/workflows")
+
+
+def workflow_problem(text: str) -> str | None:
+    """Why Gitea would drop this workflow file, or None if it looks runnable.
+
+    Gitea skips an invalid workflow with one log line and fires no run at all,
+    so on GitHub the PR just shows nothing, and people wait for CI that is never
+    coming. These are the shapes we have actually hit, not a full schema.
+    """
+    try:
+        doc = yaml.safe_load(text)
+    except yaml.YAMLError as e:
+        mark = getattr(e, "problem_mark", None)
+        return f"invalid YAML at line {mark.line + 1}" if mark else "invalid YAML"
+    if not isinstance(doc, dict):
+        return "not a YAML mapping"
+    if "on" not in doc and True not in doc:  # YAML 1.1 reads a bare `on` as True
+        return "no `on:` trigger"
+    jobs = doc.get("jobs")
+    if not isinstance(jobs, dict) or not jobs:
+        return "no `jobs:`"
+    for name, job in jobs.items():
+        if not isinstance(job, dict):
+            return f"job `{name}` is not a mapping"
+        if "runs-on" not in job and "uses" not in job:
+            return f"job `{name}` has no `runs-on:`"
+    return None
+
+
+def invalid_workflows(repo: str, sha: str) -> dict[str, tuple[str, str]]:
+    """{context: (path, problem)} for each workflow file at `sha` that won't run."""
+    for d in WORKFLOW_DIRS:
+        st, entries = gitea("GET", f"/repos/{WG_OWNER}/{repo}/contents/{d}?ref={sha}")
+        if st == 404:
+            continue
+        if st != 200:
+            raise RuntimeError(f"{repo}: Windy Git {d}@{sha[:7]} -> {st}")
+        files = [e for e in entries or [] if e.get("type") == "file"
+                 and e["name"].endswith((".yml", ".yaml"))]
+        if not files:
+            continue
+        bad = {}
+        for e in files:
+            st, f = gitea("GET", f"/repos/{WG_OWNER}/{repo}/contents/{e['path']}?ref={sha}")
+            if st != 200:
+                raise RuntimeError(f"{repo}: Windy Git {e['path']}@{sha[:7]} -> {st}")
+            problem = workflow_problem(base64.b64decode(f["content"]).decode("utf-8", "replace"))
+            if problem:
+                stem = re.sub(r"\.ya?ml$", "", e["name"])
+                bad[f"windy-git/{stem}/workflow"] = (e["path"], problem)
+        return bad
+    return {}
+
+
 def _call(base: str, token_header: str, method: str, path: str, body=None):
     req = urllib.request.Request(
         base + path,
@@ -183,7 +242,8 @@ def post_statuses(repo: str, sha: str) -> None:
         ctx = f"windy-git/{r['workflow_id'].removesuffix('.yml')}/{r['name']}"
         if ctx not in latest or r["id"] > latest[ctx]["id"]:
             latest[ctx] = r
-    if not latest:
+    bad = invalid_workflows(repo, sha)
+    if not (latest or bad):
         return
 
     st, existing = github("GET", f"/repos/{GH_OWNER}/{repo}/commits/{sha}/statuses?per_page=100")
@@ -191,6 +251,21 @@ def post_statuses(repo: str, sha: str) -> None:
     for s in existing or []:  # newest first
         current.setdefault(s["context"], s["state"])
 
+    for ctx, (path, problem) in sorted(bad.items()):
+        if current.get(ctx) == "error":
+            continue
+        st, _ = github(
+            "POST",
+            f"/repos/{GH_OWNER}/{repo}/statuses/{sha}",
+            {
+                "state": "error",
+                "context": ctx,
+                "description": f"Windy Git ignored this workflow, no CI ran: {problem}"[:140],
+                "target_url": f"{PUBLIC}/{WG_OWNER}/{repo}/src/commit/{sha}/{path}",
+            },
+        )
+        print(f"  {repo}@{sha[:7]} {ctx} = error ({problem}) -> {st}")
+
     for ctx, r in sorted(latest.items()):
         state = STATE.get(r["status"])
         if state is None or current.get(ctx) == state: