From b0653997504b30a2d241dfccdb3820c894ec1cd1 Mon Sep 17 00:00:00 2001
From: "devsy-app[bot]" <277138668+devsy-app[bot]@users.noreply.github.com>
Date: Sun, 16 Aug 2026 14:24:53 +0000
Subject: [PATCH] fix(analytics): page events past API limit cap
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The OpenHands Cloud conversation-events endpoint caps `limit` at 100 per
request. `CloudClient.conversation_events` issued a single call with
`limit=500`, which the API rejects with HTTP 422 (`less_than_equal`), so
`get()` raised `typer.Exit(1)` and the real-data run produced no output.
The `--sample` path was unaffected because it never hits the API.

Page through the endpoint in batches of `EVENTS_PAGE_SIZE` (100) using the
`page_id` cursor returned as `next_page_id`, stopping at the requested
total or when the server signals the end. Verified against the live API:
a conversation with 200 events now fetches both pages (limit=200 422s,
limit=100 + page_id paginates to completion).

This is a pipeline-repair PR, not a failure-mode intervention: it makes
the real-data path functional so the pr-gate mechanism can ever produce a
real verdict. The post-fix real-data run for yesterday (2026-08-15) shows
14 runs, 0 failed, pr-gate NOT-ACTIONABLE — there is no recurring agent
failure mode today; the metric justifying this change is the 100% failure
rate of the real-data path itself before the fix.

This commit was created by an AI agent as part of an automated daily
agent analytics job.
---
 hack/analytics/analyze_runs.py | 27 +++++++++++++++++++++++++--
 1 file changed, 25 insertions(+), 2 deletions(-)

diff --git a/hack/analytics/analyze_runs.py b/hack/analytics/analyze_runs.py
index b0017add4..4edd8b06f 100644
--- a/hack/analytics/analyze_runs.py
+++ b/hack/analytics/analyze_runs.py
@@ -66,6 +66,8 @@
 
 app = typer.Typer(add_completion=False, help="Deterministic agent-fleet run analyzer.")
 
+EVENTS_PAGE_SIZE: int = 100
+
 FEATURE_BUCKETS: list[str] = [
     "missing-tool", "test-failure", "cmd-exit-nonzero", "permission-denied",
     "timeout", "git-baseline", "lint-issue", "commit-signing",
@@ -280,9 +282,30 @@ def search_conversations(self, limit: int = 100) -> list[dict[str, Any]]:
         return normalize_items(data)
 
     def conversation_events(self, conv_id: str, limit: int = 500) -> list[dict[str, Any]]:
-        """Fetch events for one conversation."""
+        """Fetch events for one conversation, paging through the API.
+
+        The events endpoint caps ``limit`` at 100 per request, so a single
+        call with a larger limit is rejected (HTTP 422). Page in batches of
+        ``EVENTS_PAGE_SIZE`` using the ``page_id`` cursor until ``limit`` is
+        reached or the server signals the end (``next_page_id`` is empty).
+        """
         path = f"/api/v1/conversation/{conv_id}/events/search"
-        return normalize_items(self.get(path, {"limit": limit}))
+        collected: list[dict[str, Any]] = []
+        cursor: str | None = None
+        while len(collected) < limit:
+            page_size = min(EVENTS_PAGE_SIZE, limit - len(collected))
+            params: dict[str, Any] = {"limit": page_size}
+            if cursor is not None:
+                params["page_id"] = cursor
+            data = self.get(path, params)
+            if not isinstance(data, dict):
+                collected.extend(normalize_items(data))
+                break
+            collected.extend(normalize_items(data.get("items")))
+            cursor = data.get("next_page_id")
+            if not cursor or len(normalize_items(data.get("items"))) < page_size:
+                break
+        return collected
 
     def get(self, path: str, params: dict[str, Any]) -> Any:
         """Issue a GET request and decode JSON, raising on HTTP/parse errors."""