Keep runs with different tuning apart in the report, and raise max_turns to 40

The report grouped runs by model, serving note and task version, so
runs made at different tuning were silently averaged together. Tuning
is now part of the key, and a tuning column shows how a row's settings
differ from today's defaults; it appears only when some row needs it.

tuning.executor.max_turns goes from 24 to 40. On the harder benchmark
tasks Haiku, the calibration ceiling, hit 24 on both refactor-rename
runs and both long-milestone runs, one of which had finished the work.
The cap guards against a model trying forever; it isn't a budget.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

nisse-dev/tests/test_config.py

@@ -68,7 +68,7 @@ def test_complete_config_builds_with_secrets_by_reference() -> None:
     assert config.matrix.homeserver == "https://matrix.test"
     assert config.gitea_repo == "don/demo"
     assert config.base_branch == "main"
-    assert config.tuning.executor.max_turns == 24  # absent section: defaults
+    assert config.tuning.executor.max_turns == 40  # absent section: defaults
 
 
 def test_paths_expand_the_home_directory() -> None:
@@ -252,7 +252,7 @@ def test_the_example_file_is_valid() -> None:
         "NISSE_MATRIX_TOKEN": "syt_x",
         "NISSE_GITEA_TOKEN": "gt",
     }
-    assert AgentConfig.from_file(example, env).tuning.executor.max_turns == 24
+    assert AgentConfig.from_file(example, env).tuning.executor.max_turns == 40
 
 
 # --- nothing that carries secrets may sit inside the clone -----------------