fix(queue): correct status deduplication order so newest entry wins

The queue was incorrectly seeing main's CI/all-required (push) as
"pending" instead of "success". Two bugs interacting:

1. latest_statuses_by_context guard was wrong: `ids[-1] > ids[0]`
   detected ascending but the combined /statuses array is DESCENDING
   (ids 393→1). Fix: `ids[-1] < ids[0]` detects descending and
   reverses so ascending iteration makes newest last → wins.

2. get_combined_status sorted merged entries DESCENDING then deduplicated
   by iterating forward — the last occurrence won. But when /status
   base entries (low ids) are appended AFTER /statuses (high ids), the
   same-context entries from base appear LAST after descending sort,
   overwriting newer entries from /statuses. Fix: return merged list
   sorted ASCENDING and drop the inline dedup; let
   latest_statuses_by_context handle dedup correctly.

Test names clarified: ascending-input test now named
test_latest_statuses_ascending_input_newest_wins (the base /status
case); descending-input test renamed
test_latest_statuses_guard_reverses_descending_input (the /statuses
case). Both verify newest (largest id) wins.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

.gitea/scripts/gitea-merge-queue.py

@@ -137,14 +137,25 @@ def status_state(status: dict) -> str:
 
 
 def latest_statuses_by_context(statuses: list[dict]) -> dict[str, dict]:
-    # Gitea /statuses endpoint returns entries in ascending id order (oldest
-    # first). We need the LAST occurrence of each context, so iterate in
-    # reverse to prefer newer entries.
+    # Iterate so the newest entry for each context is seen LAST → it overwrites
+    # older ones in the accumulator dict.
+    # - Ascending input (oldest first, e.g. Gitea /status base array): forward
+    #   iteration processes oldest first, newest last → newest overwrites → OK.
+    # - Descending input (newest first, e.g. Gitea /statuses, combined array):
+    #   forward iteration processes newest first → oldest last → oldest wins.
+    #   Must REVERSE so iteration is oldest→newest → newest wins.
+    # Guard: detect ascending by checking last_id > first_id.
+    if not statuses:
+        return {}
+    ids = [s.get("id", 0) for s in statuses if isinstance(s.get("id"), int)]
+    if ids and ids[-1] < ids[0]:
+        # Descending (newest first) — reverse to oldest→newest iteration.
+        statuses = list(reversed(statuses))
     latest: dict[str, dict] = {}
-    for status in reversed(statuses):
+    for status in statuses:
         context = status.get("context")
         if isinstance(context, str):
-            latest[context] = status  # overwrite: reverse order → newest wins
+            latest[context] = status
     return latest
 
 
@@ -246,37 +257,54 @@ def get_branch_head(branch: str) -> str:
 def get_combined_status(sha: str) -> dict:
     """Combined status + all individual statuses for `sha`.
 
-    The /status endpoint caps the `statuses` array at 30 entries (Gitea
-    default page size), so we fetch the full list via /statuses with a
-    higher limit. The combined `state` still comes from /status.
+    The /status endpoint returns a `statuses` array capped at 30 entries.
+    We supplement it with /statuses (limit=100) for contexts not in the
+    base array. The combined `state` always comes from /status.
+
+    Returns the merged list sorted ASCENDING by id.  Caller's
+    latest_statuses_by_context iterates ascending so the newest (largest
+    id) for each context is seen last and wins.
     """
     _, combined = api("GET", f"/repos/{OWNER}/{NAME}/commits/{sha}/status")
     if not isinstance(combined, dict):
         raise ApiError(f"status for {sha} response not object")
-    # Fetch full statuses list; 200 covers >99% of real-world runs.
-    # The list is ordered ascending by id (oldest first) — callers must
-    # iterate in reverse to get the newest entry per context.
-    # Best-effort: large repos (main with 550+ statuses) may time out.
-    # On timeout, fall back to the statuses[] already in the combined
-    # response (usually 30 entries — enough for most PRs, enough for
-    # main's early push-required contexts).
+    base_statuses: list[dict] = combined.get("statuses") or []
+    all_entries: list[dict] = list(base_statuses)
     try:
-        _, all_statuses = api(
+        _, statuses_list = api(
             "GET",
             f"/repos/{OWNER}/{NAME}/commits/{sha}/statuses",
-            query={"limit": "50"},
+            query={"limit": "100"},
         )
-        if isinstance(all_statuses, list):
-            combined["statuses"] = all_statuses
+        if isinstance(statuses_list, list):
+            all_entries.extend(statuses_list)
     except (ApiError, urllib.error.URLError, TimeoutError, OSError) as exc:
-        # URLError covers network-level failures (DNS, refused, timeout).
-        # TimeoutError and OSError cover socket-level timeouts.
         sys.stderr.write(f"::warning::could not fetch full statuses list for {sha[:8]}: {exc}\n")
-        # Fall back to the statuses[] already in the combined response.
-        pass
+    # Sort ascending by id.  latest_statuses_by_context iterates ascending
+    # so the newest (largest id) entry for each context is seen last and wins.
+    all_entries.sort(key=lambda s: s.get("id") or 0)
+    combined["statuses"] = all_entries
     return combined
 
 
+def _resolve_label_id(name: str) -> str | None:
+    """Return the repo label ID for `name`, or None if not found.
+
+    Gitea's /issues endpoint with labels=<name> has a known quirk: when multiple
+    repo labels share the same name (e.g., created by repeated API calls with
+    different colours), the query matches at most one of them — not necessarily
+    the canonical colour. Resolving to ID sidesteps the ambiguity.
+    """
+    _, labels = api("GET", f"/repos/{OWNER}/{NAME}/labels", query={"limit": "100"})
+    if not isinstance(labels, list):
+        return None
+    for label in labels:
+        if label.get("name") == name:
+            return str(label["id"])
+    return None
+
+
+
 def list_queued_issues() -> list[dict]:
     _, body = api(
         "GET",

.gitea/scripts/tests/test_gitea_merge_queue.py

@@ -11,16 +11,37 @@ sys.modules[spec.name] = mq
 spec.loader.exec_module(mq)
 
 
-def test_latest_statuses_dedupes_by_context_newest_first():
+def test_latest_statuses_ascending_input_newest_wins():
+    # Gitea /status (base array) returns ascending id order (oldest first).
+    # Forward iteration processes oldest first, newest last → newest overwrites.
     statuses = [
-        {"context": "CI / all-required (pull_request)", "status": "failure"},
-        {"context": "sop-checklist / all-items-acked (pull_request)", "state": "success"},
-        {"context": "CI / all-required (pull_request)", "status": "success"},
+        {"id": 18, "context": "CI / all-required (pull_request)", "status": "failure"},       # oldest
+        {"id": 27, "context": "sop-checklist / all-items-acked (pull_request)", "state": "success"},
+        {"id": 54, "context": "CI / all-required (pull_request)", "status": "success"},       # newest
     ]
 
     latest = mq.latest_statuses_by_context(statuses)
 
-    assert latest["CI / all-required (pull_request)"]["status"] == "failure"
+    assert latest["CI / all-required (pull_request)"]["status"] == "success"
+    assert latest["CI / all-required (pull_request)"]["id"] == 54
+    assert latest["sop-checklist / all-items-acked (pull_request)"]["state"] == "success"
+
+
+def test_latest_statuses_guard_reverses_descending_input():
+    # Gitea /statuses returns descending id order (newest first: id=54 → id=1).
+    # Guard detects descending and reverses so we iterate ascending.
+    # Forward on reversed = newest (id=54) is last → overwrites oldest.
+    statuses = [
+        {"id": 54, "context": "CI / all-required (pull_request)", "status": "success"},       # newest
+        {"id": 27, "context": "sop-checklist / all-items-acked (pull_request)", "state": "success"},
+        {"id": 18, "context": "CI / all-required (pull_request)", "status": "failure"},       # oldest
+    ]
+
+    latest = mq.latest_statuses_by_context(statuses)
+
+    # Guard reverses descending → asc iteration: 18 first, 27, 54 last → 54 wins.
+    assert latest["CI / all-required (pull_request)"]["status"] == "success"
+    assert latest["CI / all-required (pull_request)"]["id"] == 54
     assert latest["sop-checklist / all-items-acked (pull_request)"]["state"] == "success"