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_config.py

@@ -5,8 +5,9 @@ from typing import Any
 
 import pytest
 
+from nisse_core.config import ConfigError
 from nisse_core.models.llm import DEFAULT_REQUEST_TIMEOUT_S
-from nisse_dev.config import AgentConfig, ConfigError, Project
+from nisse_dev.config import AgentConfig, Project
 
 # A complete config as the YAML file would give it, with secrets by reference.
 COMPLETE: dict[str, Any] = {

nisse-dev/tests/test_expert.py

@@ -1,211 +0,0 @@
-import io
-from pathlib import Path
-from typing import Any
-
-import pytest
-
-from nisse_core.log.canonical import (
-    AssistantText,
-    CanonicalEvent,
-    DelegationCompleted,
-    DelegationStarted,
-    StoredEvent,
-)
-from nisse_core.models.llm import LLMError, RoleMap
-from nisse_core.oplog import OpLog
-from nisse_core.state.store import Transcript
-from nisse_dev.expert import (
-    DEFAULT_BUDGET,
-    BudgetExhausted,
-    ExpertAnswer,
-    ExpertDesk,
-    parse_answer,
-)
-from nisse_dev.state import StateStore
-
-ROLES = RoleMap(
-    driver="haiku",
-    helper="haiku",
-    expert="claude-haiku-4-5",
-)
-
-GOOD = '{"answer": "Use SQLite; it is enough here.", "confidence": "high", "caveats": "Assumes one writer."}'
-
-
-class ScriptedClient:
-    def __init__(self, replies: list[str]) -> None:
-        self._replies = replies
-        self.calls: list[dict[str, Any]] = []
-
-    def complete(
-        self,
-        events: list[StoredEvent],
-        tools: list[dict[str, Any]] | None,
-        model: str,
-        system: str | None = None,
-    ) -> list[CanonicalEvent]:
-        self.calls.append(
-            {"events": events, "tools": tools, "model": model, "system": system}
-        )
-        if not self._replies:
-            return [AssistantText(text="nothing more", model=model)]
-        return [AssistantText(text=self._replies.pop(0), model=model)]
-
-
-@pytest.fixture
-def store(tmp_path: Path) -> StateStore:
-    return StateStore(tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO()))
-
-
-ITEM = "t"  # the work item the consults happen in
-
-
-def log(store: StateStore, item: str = ITEM) -> Transcript:
-    return store.transcript(item, "expert")
-
-
-class Bound:
-    """The desk as the executor uses it: within one work item."""
-
-    def __init__(self, desk: ExpertDesk, store: StateStore, item: str) -> None:
-        self.desk, self.store, self.item = desk, store, item
-
-    def ask(self, question: str, **kw: Any) -> Any:
-        return self.desk.ask(log(self.store, self.item), question, **kw)
-
-
-def desk(client: Any, store: StateStore, item: str = ITEM, **kw: Any) -> Bound:
-    return Bound(ExpertDesk(client, ROLES, **kw), store, item)
-
-
-# --- parsing (the contract is prompt-level, so parsing is the guard) ------
-
-
-def test_parses_a_clean_object() -> None:
-    parsed = parse_answer(GOOD)
-    assert parsed == ExpertAnswer(
-        answer="Use SQLite; it is enough here.",
-        confidence="high",
-        caveats="Assumes one writer.",
-    )
-
-
-def test_parses_a_fenced_block_because_models_wrap_json() -> None:
-    assert parse_answer(f"Here you go:\n```json\n{GOOD}\n```") is not None
-
-
-def test_missing_or_bad_fields_are_a_failed_turn() -> None:
-    assert parse_answer('{"answer": "", "confidence": "high"}') is None
-    assert parse_answer('{"answer": "x", "confidence": "certain"}') is None
-    assert parse_answer('{"confidence": "high"}') is None
-    assert parse_answer("no json at all") is None
-    assert parse_answer('["not", "an", "object"]') is None
-
-
-def test_absent_caveats_is_tolerated() -> None:
-    parsed = parse_answer('{"answer": "yes", "confidence": "low"}')
-    assert parsed is not None
-    assert parsed.caveats == ""
-
-
-# --- the desk ------------------------------------------------------------
-
-
-def test_ask_returns_a_validated_answer(store: StateStore) -> None:
-    client = ScriptedClient([GOOD])
-    answer = desk(client, store).ask("SQLite or Postgres?")
-    assert answer.confidence == "high"
-    assert "SQLite" in answer.render()
-
-
-def test_consult_is_stateless_and_uses_the_consultant_role(
-    store: StateStore,
-) -> None:
-    log(store).append(AssistantText(text="secret repo context", model="m"))
-    client = ScriptedClient([GOOD])
-    desk(client, store).ask("Is this API deprecated?")
-
-    call = client.calls[0]
-    # L9: no repo access, no session state — exactly the question, and none
-    # of the log the caller was working from.
-    assert [e.event.text for e in call["events"]] == ["Is this API deprecated?"]
-    assert all("secret repo context" not in e.event.text for e in call["events"])
-    assert call["tools"] is None
-    assert call["model"] == "claude-haiku-4-5"
-
-
-def test_unparseable_reply_is_retried_once_then_raises(store: StateStore) -> None:
-    client = ScriptedClient(["waffle", "more waffle"])
-    with pytest.raises(LLMError, match="no usable answer"):
-        desk(client, store).ask("q")
-    assert len(client.calls) == 2
-    assert "not a single valid JSON object" in client.calls[1]["system"]
-
-
-def test_retry_succeeds_after_a_bad_first_reply(store: StateStore) -> None:
-    client = ScriptedClient(["waffle", GOOD])
-    assert desk(client, store).ask("q").confidence == "high"
-
-
-def test_consults_are_recorded_as_composite_events(store: StateStore) -> None:
-    # L9 wants a consult/delegation eval set; reusing the pair gets consult
-    # evaluation for free.
-    desk(ScriptedClient([GOOD]), store).ask("q")
-    events = [e.event for e in log(store).read()]
-    started = next(e for e in events if isinstance(e, DelegationStarted))
-    completed = next(e for e in events if isinstance(e, DelegationCompleted))
-    assert started.role == "expert"
-    assert started.brief == "q"
-    assert completed.exit_status == "answered"
-
-
-def test_a_failed_consult_is_recorded_too(store: StateStore) -> None:
-    with pytest.raises(LLMError):
-        desk(ScriptedClient(["waffle", "waffle"]), store).ask("q")
-    completed = [
-        e.event for e in log(store).read() if isinstance(e.event, DelegationCompleted)
-    ]
-    assert completed[0].exit_status == "failed"
-
-
-def test_budget_is_enforced_across_calls(store: StateStore) -> None:
-    client = ScriptedClient([GOOD] * 10)
-    d = desk(client, store, budget=2)
-    d.ask("one")
-    d.ask("two")
-    with pytest.raises(BudgetExhausted, match="budget of 2"):
-        d.ask("three")
-    assert len(client.calls) == 2  # the third never reached the model
-
-
-def test_budget_survives_a_restart(tmp_path: Path) -> None:
-    # Counted from the canonical log, not from memory, so a crash cannot
-    # hand a circling executor a fresh allowance.
-    db = tmp_path / "state.db"
-    with StateStore(db, oplog=OpLog("d", io.StringIO())) as store:
-        desk(ScriptedClient([GOOD]), store, budget=1).ask("one")
-    with (
-        StateStore(db, oplog=OpLog("d", io.StringIO())) as store,
-        pytest.raises(BudgetExhausted),
-    ):
-        desk(ScriptedClient([GOOD]), store, budget=1).ask("two")
-
-
-def test_budget_counts_only_after_the_task_marker(store: StateStore) -> None:
-    d = desk(ScriptedClient([GOOD] * 5), store, budget=1)
-    d.ask("earlier task")
-    marker = log(store).read()[-1].id
-    # A new task starts its allowance afresh from its own marker.
-    assert d.ask("new task", since_event_id=marker).confidence == "high"
-
-
-def test_the_budget_is_per_work_item(store: StateStore) -> None:
-    # Consults in one task never use up another's allowance (L9).
-    desk(ScriptedClient([GOOD]), store, item="a", budget=1).ask("one")
-    assert desk(ScriptedClient([GOOD]), store, item="b", budget=1).ask("two")
-    with pytest.raises(BudgetExhausted):
-        desk(ScriptedClient([GOOD]), store, item="a", budget=1).ask("three")
-
-
-def test_default_budget_is_small() -> None:
-    assert DEFAULT_BUDGET <= 5  # L9: do not let this become a second subsystem

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

nisse-dev/tests/test_loop_milestones.py

@@ -21,12 +21,12 @@ from nisse_core.gitea import (
     ReviewNote,
 )
 from nisse_core.log.canonical import ToolCall
+from nisse_core.loop.driver import Driver
 from nisse_core.oplog import OpLog
 from nisse_core.state.cancel import Cancel
 from nisse_core.state.worker import InlineWorker
 from nisse_dev.git import GitRepo
 from nisse_dev.loop.agent import LoopAgent
-from nisse_dev.loop.driver import Driver
 from nisse_dev.loop.items import ANSWER, MERGE, WAITING, loop_of
 from nisse_dev.loop.milestones import OPEN_PR, Milestones
 from nisse_dev.state import StateStore

nisse-dev/tests/test_loop_new_projects.py

@@ -16,12 +16,12 @@ from test_loop_projects import Router
 
 from nisse_core.conversation.transport import InMemoryTransport
 from nisse_core.execution.ssh import SSHHost
+from nisse_core.loop.driver import Driver
 from nisse_core.oplog import OpLog
 from nisse_core.state.cancel import Cancel
 from nisse_core.state.worker import InlineWorker
 from nisse_dev.config import _parse_projects
 from nisse_dev.loop.agent import LoopAgent, Project
-from nisse_dev.loop.driver import Driver
 from nisse_dev.loop.items import CHAT, GO_AHEAD, MERGE, PROVISION, loop_of
 from nisse_dev.tools import Workspace
 

nisse-dev/tests/test_loop_projects.py

@@ -12,11 +12,11 @@ from test_loop_milestones import DON, Forge, ScriptedModel, call, git, make_worl
 
 from nisse_core.conversation.transport import InMemoryTransport
 from nisse_core.execution.ssh import SSHHost
+from nisse_core.loop.driver import Driver
 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, Project
-from nisse_dev.loop.driver import Driver
 from nisse_dev.loop.items import ANSWER, GO_AHEAD, MERGE, item_for_issue, loop_of
 from nisse_dev.tools import Workspace
 

nisse-dev/tests/test_loop_properties.py

@@ -38,6 +38,7 @@ from nisse_core.log.canonical import (
     ToolResult,
     UserMessage,
 )
+from nisse_core.loop.driver import Driver
 from nisse_core.models.llm import LLMError, RoleMap
 from nisse_core.oplog import OpLog
 from nisse_core.state.cancel import Cancel
@@ -45,7 +46,6 @@ from nisse_core.state.worker import InlineWorker
 from nisse_dev.delegation import DELEGATION_INTENT, Caps
 from nisse_dev.loop.agent import LoopAgent, Project
 from nisse_dev.loop.classifier import ActionClassifier
-from nisse_dev.loop.driver import Driver
 from nisse_dev.loop.help import Helpers
 from nisse_dev.loop.items import (
     ANSWER,

nisse-dev/tests/test_loop_toolchain.py

@@ -30,12 +30,12 @@ from nisse_core.conversation.transport import InMemoryTransport
 from nisse_core.execution.ssh import HostKeyChanged
 from nisse_core.gitea import Issue
 from nisse_core.log.canonical import Fact, ToolResult
+from nisse_core.loop.driver import Driver
 from nisse_core.oplog import OpLog
 from nisse_core.state.cancel import Cancel
 from nisse_core.state.worker import InlineWorker
 from nisse_dev.loop import preflight
 from nisse_dev.loop.agent import LoopAgent, Project
-from nisse_dev.loop.driver import Driver
 from nisse_dev.loop.items import ANSWER, GO_AHEAD, WAITING, loop_of
 from nisse_dev.tools import Workspace
 

nisse-dev/tests/test_loop_trust.py

@@ -20,11 +20,11 @@ from test_loop_milestones import item as the_item
 from test_loop_milestones import world as world  # noqa: PLC0414 -- the fixture
 
 from nisse_core.conversation.transport import InMemoryTransport
+from nisse_core.loop.driver import Driver
 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, Project
-from nisse_dev.loop.driver import Driver
 from nisse_dev.loop.items import MERGE, loop_of
 from nisse_dev.tools import Workspace