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/tests/test_loop.py

@@ -17,16 +17,16 @@ from nisse_core.log.canonical import (
     ToolCall,
     ToolResult,
 )
+from nisse_core.loop.driver import Driver, ToolOutcome
 from nisse_core.models.llm import LLMError
 from nisse_core.oplog import OpLog
 from nisse_core.state.cancel import Cancel
 from nisse_core.state.worker import InlineWorker
 from nisse_dev.loop.agent import LoopAgent
-from nisse_dev.loop.driver import Driver
 from nisse_dev.loop.items import CLOSED, GO_AHEAD, READY, RUNNING, WAITING, loop_of
 from nisse_dev.loop.reader import command_form
+from nisse_dev.loop.tools import WAITING_TOOLS
 from nisse_dev.state import StateStore
-from nisse_dev.tools import ToolOutcome
 
 DON = "@don:test"
 
@@ -357,7 +357,11 @@ def test_calls_after_a_waiting_tool_are_not_run(tmp_path: Path) -> None:
     )
     log = driver_log(tmp_path)
     outcome = Driver(model, "m").run(
-        log, system="s", tools=_tools("ask_human", "run_command"), workspace=None
+        log,
+        system="s",
+        tools=_tools("ask_human", "run_command"),
+        waiting=WAITING_TOOLS,
+        workspace=None,
     )
     assert (outcome.kind, outcome.tool) == ("wait", "ask_human")
     results = [e.event.result for e in log.read() if hasattr(e.event, "result")]
@@ -368,7 +372,11 @@ def test_an_invented_tool_is_answered_not_run(tmp_path: Path) -> None:
     model = ScriptedModel([call("fly")], [call("ask_human", question="?")])
     log = driver_log(tmp_path)
     outcome = Driver(model, "m").run(
-        log, system="s", tools=_tools("ask_human"), workspace=None
+        log,
+        system="s",
+        tools=_tools("ask_human"),
+        waiting=WAITING_TOOLS,
+        workspace=None,
     )
     assert outcome.kind == "wait"
     assert any(
@@ -379,7 +387,11 @@ def test_an_invented_tool_is_answered_not_run(tmp_path: Path) -> None:
 def test_the_turn_cap_ends_a_run(tmp_path: Path) -> None:
     model = ScriptedModel(*[[call("read_file", path="a")]] * 3)
     outcome = Driver(model, "m", max_turns=3).run(
-        driver_log(tmp_path), system="s", tools=_tools("read_file"), workspace=None
+        driver_log(tmp_path),
+        system="s",
+        tools=_tools("read_file"),
+        waiting=WAITING_TOOLS,
+        workspace=None,
     )
     assert outcome.kind == "capped"
 
@@ -388,7 +400,11 @@ def test_stop_ends_a_run_at_the_next_boundary(tmp_path: Path) -> None:
     cancel = Cancel()
     cancel.set()
     outcome = Driver(ScriptedModel(), "m", cancel=cancel).run(
-        driver_log(tmp_path), system="s", tools=_tools("read_file"), workspace=None
+        driver_log(tmp_path),
+        system="s",
+        tools=_tools("read_file"),
+        waiting=WAITING_TOOLS,
+        workspace=None,
     )
     assert outcome.kind == "stopped"
 
@@ -399,7 +415,11 @@ def test_a_failed_model_call_fails_the_run(tmp_path: Path) -> None:
             raise LLMError("proxy down")
 
     outcome = Driver(Down(), "m").run(  # type: ignore[arg-type]
-        driver_log(tmp_path), system="s", tools=_tools("read_file"), workspace=None
+        driver_log(tmp_path),
+        system="s",
+        tools=_tools("read_file"),
+        waiting=WAITING_TOOLS,
+        workspace=None,
     )
     assert outcome.kind == "failed" and "proxy down" in outcome.note
 
@@ -419,6 +439,7 @@ def test_stop_mid_turn_skips_the_rest_of_its_calls(tmp_path: Path) -> None:
         log,
         system="s",
         tools=_tools("start_milestone", "read_file"),
+        waiting=WAITING_TOOLS,
         workspace=None,
         handlers={"start_milestone": start},
     )
@@ -443,6 +464,7 @@ def test_a_command_that_works_resets_the_failure_count(tmp_path: Path) -> None:
         driver_log(tmp_path),
         system="s",
         tools=_tools("run_command", "ask_human"),
+        waiting=WAITING_TOOLS,
         workspace=Commands(),  # type: ignore[arg-type]
     )
     assert outcome.kind == "wait"  # never two failures in a row