Fix the run-breaking tool-result order; e2e test runs the slice (M2.1, PR D)

The first live run of the new loop's e2e test found that a fact recorded
while start_milestone was in flight landed between the tool call and its
result; both API formats reject that, so every later request in the run
failed. Views now keep each result right after its call. Scripted test
models check the APIs' ordering rules, so this can't pass unit tests
again.

The e2e tests no longer depend on the sandbox's history: each run asks for
a uniquely named function and works against a base branch of its own,
deleted afterwards. The review step asks for a change that can't already
be there. The scripted operator gives up after five fruitless answers, and
each run keeps its state store for inspection. The driver's prompt says
review fixes stay in the current milestone.

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

nisse-dev/tests/test_loop.py

@@ -6,6 +6,7 @@ from pathlib import Path
 from typing import Any
 
 import pytest
+from model_contract import assert_renderable
 
 from nisse_dev.cancel import Cancel
 from nisse_dev.canonical import AssistantText, CanonicalEvent, Fact, ToolCall
@@ -34,6 +35,7 @@ class ScriptedModel:
         self.seen: list[list[Any]] = []
 
     def complete(self, events, tools, model, system=None) -> list[CanonicalEvent]:
+        assert_renderable(events)  # as the real API would
         self.offered.append({t["function"]["name"] for t in tools or []})
         self.seen.append(events)
         assert self.turns, "the model was called more often than scripted"