M7.2: share the loop's parts

Shared parts, not a shared scheduler (agreed): nisse-review will have its
own small scheduler; a common one waits until two exist to compare.

- nisse_core.loop.driver: the driver run, moved; the agent names its
  waiting tools per run (nisse-dev's are WAITING_TOOLS), and execution
  goes to any Executor (ToolOutcome moves with it).
- nisse_core.loop.tools: the tool helper and the tools any agent offers
  (notes, memory, memory_done, ask_expert); nisse_core.loop.expert.
- nisse_core.knowledge.handlers: Knowledge, the vault and memory as
  control tools, the index and prompt text, out of LoopAgent.
- nisse_core.config: file reading, references, people, tuning sections of
  the agent's own, LLM numbers, the vault.
- New core tests: a driver run with a non-workspace executor and the
  agent's own waiting set; Knowledge alone; the shared config pieces.

Docs: the Development Plan marks M7.2 done; Architecture Part L and the
nisse-core README name the new parts.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk

nisse-dev/src/nisse_dev/bench/runner.py

@@ -20,17 +20,18 @@ from nisse_core.log.canonical import (
     ToolResult,
     UserMessage,
 )
+from nisse_core.loop.driver import Driver, RunOutcome
 from nisse_core.models.catalog import ModelFacts
 from nisse_core.oplog import OpLog
 from nisse_dev.bench.tasks import Task
 from nisse_dev.config import Tuning
 from nisse_dev.loop.agent import SYSTEM
-from nisse_dev.loop.driver import Driver, RunOutcome
 from nisse_dev.loop.tools import (
     ASK_HUMAN,
     CLOSE_ITEM,
     FINISH_MILESTONE,
     START_MILESTONE,
+    WAITING_TOOLS,
 )
 from nisse_dev.state import StateStore
 from nisse_dev.tools import EXECUTION_TOOLS, Workspace
@@ -236,6 +237,7 @@ def run_task(
                 store.transcript("bench", "driver"),
                 system=system,
                 tools=BENCH_TOOLS,
+                waiting=WAITING_TOOLS,
                 workspace=workspace,
                 handlers={"start_milestone": lambda args: ("started", True)},
             )