nisse-dev/src/nisse_dev/gitea.py

@@ -20,6 +20,9 @@ import httpx
 from nisse_dev.reconcile import Reconciler
 from nisse_dev.state import Intent
 
+PR_PAGE_SIZE = 50
+MAX_PR_PAGES = 40  # 2000 PRs; beyond that, say so rather than guess
+
 
 class GiteaError(RuntimeError):
     pass
@@ -92,16 +95,31 @@ class GiteaClient:
 
     def find_pull_request(self, repo: str, head: str) -> PullRequest | None:
         """External truth for A3: did the PR for this branch already get
-        opened? Checks closed PRs too — a crash after opening must not be
+        opened? Includes closed PRs — a crash after opening must not be
-        answered with "no PR is open, so open another"."""
+        answered with "no PR is open, so open another".
-        for state in ("open", "closed"):
+
+        Pages to the end rather than sampling the first page: a "not found"
+        that only means "not in the newest 50" would licence a duplicate PR.
+        If the history is longer than this walk, raise instead of guessing —
+        the reconciler turns that into "unverifiable" and gates to the human.
+        """
+        for page in range(1, MAX_PR_PAGES + 1):
             data = self._request(
-                "GET", f"/repos/{repo}/pulls", params={"state": state, "limit": 50}
+                "GET",
+                f"/repos/{repo}/pulls",
+                params={"state": "all", "limit": PR_PAGE_SIZE, "page": page},
             )
-            for item in data or []:
+            items = data or []
+            for item in items:
                 if (item.get("head") or {}).get("ref") == head:
                     return _pull_request(item)
-        return None
+            if len(items) < PR_PAGE_SIZE:
+                return None  # reached the end: definitively absent
+        raise GiteaError(
+            f"searched {MAX_PR_PAGES * PR_PAGE_SIZE} pull requests in {repo} "
+            f"without reaching the end; cannot confirm whether {head!r} was "
+            "already opened"
+        )
 
     def list_comments(
         self, repo: str, index: int, since: str | None = None

nisse-dev/tests/test_gitea.py

@@ -4,6 +4,7 @@ import httpx
 import pytest
 
 from nisse_dev.gitea import (
+    PR_PAGE_SIZE,
     Comment,
     GiteaClient,
     GiteaError,
@@ -61,27 +62,58 @@ def test_open_pull_request_posts_expected_body() -> None:
 
 
 def test_find_pull_request_matches_head_branch() -> None:
-    def handler(request: httpx.Request) -> httpx.Response:
+    handler = lambda request: httpx.Response(200, json=[pr_json(3, "other")])
-        if request.url.params.get("state") == "open":
-            return httpx.Response(200, json=[pr_json(3, "other")])
-        return httpx.Response(200, json=[])
-
     assert client(handler).find_pull_request("o/r", "milestone-1") is None
 
 
-def test_find_pull_request_also_checks_closed() -> None:
+def test_find_pull_request_also_finds_closed() -> None:
     # A crash after opening must not be answered with "nothing open, open
     # another" — the effect already happened.
-    def handler(request: httpx.Request) -> httpx.Response:
+    handler = lambda request: httpx.Response(
-        if request.url.params.get("state") == "open":
+        200, json=[pr_json(4, "milestone-1", "closed")]
-            return httpx.Response(200, json=[])
+    )
-        return httpx.Response(200, json=[pr_json(4, "milestone-1", "closed")])
-
     found = client(handler).find_pull_request("o/r", "milestone-1")
     assert found is not None
     assert found.number == 4
 
 
+def test_find_pull_request_pages_past_the_first_page() -> None:
+    # The match sits on page 2; sampling only the newest page would report
+    # "absent" and licence a duplicate PR.
+    def handler(request: httpx.Request) -> httpx.Response:
+        page = int(request.url.params.get("page", 1))
+        if page == 1:
+            return httpx.Response(
+                200, json=[pr_json(i, f"other-{i}") for i in range(PR_PAGE_SIZE)]
+            )
+        return httpx.Response(200, json=[pr_json(999, "milestone-1", "closed")])
+
+    found = client(handler).find_pull_request("o/r", "milestone-1")
+    assert found is not None
+    assert found.number == 999
+
+
+def test_short_page_ends_the_search_definitively() -> None:
+    calls: list[int] = []
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        calls.append(int(request.url.params.get("page", 1)))
+        return httpx.Response(200, json=[pr_json(1, "other")])
+
+    assert client(handler).find_pull_request("o/r", "milestone-1") is None
+    assert calls == [1]  # one short page proves absence; no further paging
+
+
+def test_unbounded_history_raises_rather_than_guessing() -> None:
+    # Never answer "absent" from an incomplete search: the reconciler turns
+    # this error into "unverifiable" and gates to the human.
+    handler = lambda request: httpx.Response(
+        200, json=[pr_json(i, f"other-{i}") for i in range(PR_PAGE_SIZE)]
+    )
+    with pytest.raises(GiteaError, match="without reaching the end"):
+        client(handler).find_pull_request("o/r", "milestone-1")
+
+
 def test_error_status_raises_gitea_error() -> None:
     handler = lambda request: httpx.Response(403, text="forbidden")
     with pytest.raises(GiteaError, match="403"):
@@ -139,12 +171,7 @@ def test_from_env_requires_config() -> None:
 
 
 def test_reconciler_reports_existing_pr_as_done() -> None:
-    handler = lambda request: httpx.Response(
+    handler = lambda request: httpx.Response(200, json=[pr_json(5, "milestone-1")])
-        200,
-        json=[pr_json(5, "milestone-1")]
-        if request.url.params.get("state") == "open"
-        else [],
-    )
     assert pull_request_reconciler(client(handler), "o/r")(INTENT) is True