End-to-end tests on a local model, and in CI on every PR

- Every e2e role runs on qwen3.8-27b on the RTX 4090 (e2e_roles();
  NISSE_E2E_MODEL overrides, e.g. claude-haiku-4-5). The first full run
  passed 7 of 8 in 26 minutes for $0.0000; the eighth was a real finding,
  fixed with the new-project PR.
- scripts/e2e.sh reports a run's spend on the test key and the day's total
  against its budget: above $0 on the local model means a paid fallback.
- CI runs the suite as its own job on pull requests (not pushes to main),
  on a throwaway sshd (--local), cancelling a run a newer push supersedes,
  so the checks job still reports in minutes.
- The plan says so: e2e on every PR; locally only -k / --lf.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE

tests/integration/e2e_support.py

@@ -11,6 +11,17 @@ from dataclasses import dataclass
 from pathlib import Path
 
 from nisse_dev.gitea import GiteaClient, GiteaError
+from nisse_dev.llm import RoleMap
+
+# The end-to-end tests run every role on a local model, which costs nothing
+# per call; NISSE_E2E_MODEL overrides it (e.g. claude-haiku-4-5 for a quick,
+# paid run).
+E2E_MODEL = "qwen3.8-27b"
+
+
+def e2e_roles() -> RoleMap:
+    model = os.environ.get("NISSE_E2E_MODEL", "").strip() or E2E_MODEL
+    return RoleMap(executor=model, planner=model, helper=model, expert=model)
 
 
 def task(run: str) -> str: