From 9d45211fd3d36e7371d460175d886a31d268c2dd Mon Sep 17 00:00:00 2001
From: Hongming Wang <hongmingwang.rabbit@users.noreply.github.com>
Date: Sun, 3 May 2026 14:01:50 -0700
Subject: [PATCH] canvas/e2e: surface admin-orgs row + workspace body on
 failure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Two diagnostic upgrades to the Playwright staging-setup harness, both
zero-behavior-change:

1. provision-failed throw now includes the full admin-orgs row (boot
   stage, last error, terraform/SSM state, etc) instead of just the
   slug. Every "provision failed: <slug>" in CI history was followed
   by a manual repro to find out WHY — that round-trip is gone.

2. workspace-failed throw dumps the full /workspaces/{id} body when
   last_sample_error is empty. Boot crashes, image-pull errors,
   missing PYTHONPATH, and OpenAI-quota-at-startup all surface as a
   bare "Workspace failed:" today (see #2632). Now they carry the
   boot_stage / image / last_error fields the API row exposes.

No fix for the underlying flakes — those are tracked in #2632 (CP race)
and #2578 (OpenAI quota). This just stops them looking identical in the
CI log.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---
 canvas/e2e/staging-setup.ts | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

diff --git a/canvas/e2e/staging-setup.ts b/canvas/e2e/staging-setup.ts
index 77f7ef6e..873ac07b 100644
--- a/canvas/e2e/staging-setup.ts
+++ b/canvas/e2e/staging-setup.ts
@@ -169,7 +169,17 @@ export default async function globalSetup(_config: FullConfig): Promise<void> {
         orgID = row.id;
         return true;
       }
-      if (row.instance_status === "failed") throw new Error(`provision failed: ${slug}`);
+      if (row.instance_status === "failed") {
+        // Dump every diagnostic field the admin row carries — boot stage,
+        // last error, terraform/SSM state, etc. The bare slug message used
+        // to surface ZERO context, so triaging a failed provision meant
+        // re-running locally to repro. Now the failure log carries enough
+        // to point at the right subsystem (CP/AWS/SSM/runtime) without a
+        // second round-trip.
+        throw new Error(
+          `provision failed: ${slug} — admin-orgs row: ${JSON.stringify(row)}`,
+        );
+      }
       return null;
     },
     PROVISION_TIMEOUT_MS,
@@ -249,7 +259,17 @@ export default async function globalSetup(_config: FullConfig): Promise<void> {
       if (r.status !== 200) return null;
       if (r.body?.status === "online") return true;
       if (r.body?.status === "failed") {
-        throw new Error(`Workspace failed: ${r.body.last_sample_error || ""}`);
+        // last_sample_error is often empty when the failure happens before
+        // the agent emits a sample (e.g. boot crash, image pull error,
+        // missing PYTHONPATH, OpenAI quota at startup). Dumping the full
+        // body gives triage the boot_stage / last_error / image fields it
+        // needs without a second probe. Otherwise this propagates as a
+        // bare "Workspace failed: " — the exact useless message that
+        // sent #2632 to the issue tracker.
+        const detail = r.body.last_sample_error
+          ? r.body.last_sample_error
+          : `(no last_sample_error) full body: ${JSON.stringify(r.body)}`;
+        throw new Error(`Workspace failed: ${detail}`);
       }
       return null;
     },