Add an executor benchmark that keeps its results

Choosing a local executor model, and tuning its knobs, needs measured
success rates across repeated runs, comparable with every model
measured before.

- Four canned milestones under nisse_dev/bench/tasks: write a function,
  fix a bug a failing test exposes, thread an option through several
  files, and find one failure in output far past max_output_chars. Each
  is an approved plan over a seed project, judged by a hidden check the
  model never sees; a reference solution proves each is solvable and
  that its check tells the difference
- Runs use the agent's own client wiring, now shared as
  make_llm_clients, with delegation and ask_expert off: an escalation is
  a failure of the model under test
- Each run is stored as one JSON line in bench/results/, committed, with
  the model's backing name and declared facts, a note on how it was
  served, the task's content hash, the agent's commit and tuning, the
  outcome, turns, misbehaviour counts, context trims, tokens, time and
  LiteLLM's cost; a fallback answer can never count as a success
- The report rebuilds the comparison from every stored run, with Wilson
  95% intervals, marking runs against older task versions
- scripts/benchmark.py runs and reports; scripts/evaluate_model.sh takes
  a new model through the context probe, the capability matrix and the
  benchmark in one command
- Clients keep LiteLLM's per-call cost, and BudgetedClient counts the
  requests it had to trim
- The tuning guide gains "Benchmarking models"

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

nisse-dev/src/nisse_dev/bench/tasks/long-output/task.yaml

@@ -0,0 +1,12 @@
+title: Find one failure in long test output
+check: python -m pytest -q .bench_check
+plan: |
+  Milestone 1: fix the one wrong entry in the rate table.
+
+  1. Run `python -m pytest -v`. Exactly one test fails, and its output names a
+     region code.
+  2. The tests are correct. In `rates.py`, the rate for region code RNNN must be
+     (NNN mod 25) / 100. Correct only the failing region's entry; leave every
+     other line as it is.
+  3. Run `python -m pytest -q` until every test passes.
+  4. Call finish.