Threads, commands and labels on the new loop (M2.3)

- Commands that name their item ("go #14", "abandon #14", "stop #14")
  apply to it wherever they're said; go, approve and abandon alone at top
  level are asked about (L5). stop is never taken as an answer.
- A plain-language reply to a restatement is read by GoAheadReader, one
  model call that agrees only on a clear yes; questions never reach it. The
  agent says "taking that as a go-ahead on rev-N" first, bound to the
  revision on screen at arrival (L3, L5, D1).
- Labels steer (D1): `bug` goes ahead after tuning.loop.bug_grace_s
  (default 600 s) unless the operator replies; `discuss` isn't offered
  restate until the operator has spoken; `bug`, `discuss` and `design` add
  to the driver's instructions. A restatement asks no questions.

Tests: label and command unit tests, the property walk with labelled
issues, plain yeses, named gos and time passing (grace_only_unanswered,
discuss_talks_first), and e2e tests for a bug proceeding after its grace
period and a plain-language go-ahead.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE

nisse-dev/tests/test_config.py

@@ -158,6 +158,7 @@ def test_tuning_is_read() -> None:
             "expert": {"consult_budget": 5},
             "delegation": {"max_turns": 20, "max_tokens": 100000, "wall_clock_s": 600},
             "tools": {"command_timeout_s": 300, "max_output_chars": 2000},
+            "loop": {"bug_grace_s": 120},
         }
     )
     tuning = config.tuning
@@ -166,6 +167,7 @@ def test_tuning_is_read() -> None:
     assert tuning.delegation.max_tokens == 100_000
     assert tuning.delegation.wall_clock_s == 600.0
     assert tuning.tools.max_output_chars == 2000
+    assert tuning.loop.bug_grace_s == 120.0
 
 
 def test_a_partly_given_tuning_section_keeps_the_other_defaults() -> None:

nisse-dev/tests/test_loop.py

@@ -72,12 +72,18 @@ def issue(number: int = 14, author: str = "don", **kw: Any) -> Issue:
         title=kw.get("title", "Add count_words"),
         body=kw.get("body", "count words in a string"),
         author=author,
-        labels=(),
+        labels=kw.get("labels", ()),
     )
 
 
 class Harness:
-    def __init__(self, tmp_path: Path, model: ScriptedModel, gitea: FakeGitea) -> None:
+    def __init__(
+        self,
+        tmp_path: Path,
+        model: ScriptedModel,
+        gitea: FakeGitea,
+        **agent: Any,  # more LoopAgent arguments: reader, clock, ...
+    ) -> None:
         tmp_path.mkdir(parents=True, exist_ok=True)
         self.store = StateStore(
             tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO())
@@ -100,6 +106,7 @@ class Harness:
             worker=InlineWorker(),
             cancel=self.cancel,
             oplog=OpLog("nisse-dev", io.StringIO()),
+            **agent,
         )
         self.transport.on_message(self.agent.on_message)
 
@@ -215,7 +222,8 @@ def test_a_go_at_top_level_is_not_a_go_ahead(h: Harness) -> None:
     h.agent.intake()
     h.say("go", thread=None)
     assert not loop_of(h.item()).started
-    assert "assign one and I'll pick it up" in h.posted()[-1]
+    # L5: an unnamed command at top level is ambiguous, so it asks.
+    assert "Which item?" in h.posted()[-1] and "#14" in h.posted()[-1]
 
 
 # --- waiting points (L2) -------------------------------------------------------------

nisse-dev/tests/test_loop_labels.py

@@ -0,0 +1,282 @@
+"""Threads, commands and labels in the new loop (M2.3): commands that name
+their item, ambiguous ones asked about (L5); plain-language go-aheads; `bug`
+grace periods, `discuss` and `design` (D1)."""
+
+from pathlib import Path
+from typing import Any
+
+import pytest
+from test_loop import DON, RESTATED, FakeGitea, Harness, ScriptedModel, call, issue
+from test_loop import h as h  # noqa: PLC0414 -- the fixture
+
+from nisse_dev.canonical import Fact, ToolCall
+from nisse_dev.llm import LLMError
+from nisse_dev.loop.items import ANSWER, GO_AHEAD, READY, WAITING, loop_of
+from nisse_dev.loop.reader import GoAheadReader
+
+STARTED = [call("ask_human", question="started; anything else?")]
+
+
+class Clock:
+    def __init__(self) -> None:
+        self.now = 1000.0
+
+    def __call__(self) -> float:
+        return self.now
+
+
+class Reader:
+    """A scripted go-ahead reader: agrees with what it's told to."""
+
+    def __init__(self, *yes: str) -> None:
+        self.yes = set(yes)
+        self.asked: list[tuple[str, str]] = []
+
+    def agrees(self, proposal: str, reply: str) -> bool:
+        self.asked.append((proposal, reply))
+        return reply in self.yes
+
+
+def facts(h: Harness) -> list[str]:
+    return [
+        e.event.text
+        for e in h.store.transcript(h.item().id, "orchestrator").read()
+        if isinstance(e.event, Fact)
+    ]
+
+
+def two(tmp_path: Path, *turns: list[Any]) -> Harness:
+    return Harness(
+        tmp_path,
+        ScriptedModel(*turns),
+        FakeGitea(issue(14), issue(15, title="Add count_lines")),
+    )
+
+
+# --- commands that name their item, and ambiguous ones (L5) -------------------
+
+
+def test_a_named_go_at_top_level_applies_to_its_item(tmp_path: Path) -> None:
+    h = two(tmp_path, RESTATED, RESTATED, STARTED)
+    h.agent.intake()
+    h.say("go #15", thread=None)
+    items = {loop_of(i).issue: i for i in h.store.work_items()}
+    assert loop_of(items[15]).started and not loop_of(items[14]).started
+
+
+def test_a_named_abandon_in_another_thread_still_names_its_item(
+    tmp_path: Path,
+) -> None:
+    h = two(tmp_path, RESTATED, RESTATED)
+    h.agent.intake()
+    items = {loop_of(i).issue: i for i in h.store.work_items()}
+    h.transport.receive(DON, "Abandon #15.", thread=loop_of(items[14]).thread)
+    items = {loop_of(i).issue: i for i in h.store.work_items()}
+    assert items[15].status == "closed" and items[14].status == "open"
+
+
+def test_an_unnamed_command_at_top_level_is_asked_about(tmp_path: Path) -> None:
+    h = two(tmp_path, RESTATED, RESTATED)
+    h.agent.intake()
+    h.say("abandon", thread=None)
+    assert all(i.status == "open" for i in h.store.work_items())
+    asked = h.posted()[-1]
+    assert "Which item?" in asked and "#14" in asked and "#15" in asked
+
+
+def test_naming_an_item_that_isnt_open_says_so(h: Harness) -> None:
+    h.agent.intake()
+    h.say("go #99", thread=None)
+    assert "#99 isn't one of my open work items" in h.posted()[-1]
+
+
+def test_stop_in_a_waiting_items_thread_is_not_an_answer(h: Harness) -> None:
+    h.agent.intake()
+    h.say("stop")
+    assert (h.item().position, loop_of(h.item()).wait) == (WAITING, GO_AHEAD)
+    assert "nothing to stop" in h.posted()[-1]
+
+
+# --- plain-language go-aheads (L5, D1) ------------------------------------------
+
+
+def test_a_plain_yes_is_a_go_ahead_said_so_first(tmp_path: Path) -> None:
+    reader = Reader("Yep, that's it")
+    h = Harness(
+        tmp_path, ScriptedModel(RESTATED, STARTED), FakeGitea(issue()), reader=reader
+    )
+    h.agent.intake()
+    h.say("Yep, that's it")
+    assert loop_of(h.item()).started
+    assert "Taking that as a go-ahead on rev-1" in " ".join(h.posted())
+    assert reader.asked == [
+        ("I'll add count_words to text.py, with tests.", "Yep, that's it")
+    ]
+    assert any(f.startswith("go-ahead on rev-1 from") for f in facts(h))
+
+
+def test_anything_else_goes_to_the_driver(tmp_path: Path) -> None:
+    h = Harness(
+        tmp_path,
+        ScriptedModel(RESTATED, [call("restate", text="v2")]),
+        FakeGitea(issue()),
+        reader=Reader(),
+    )
+    h.agent.intake()
+    h.say("Mostly, but call it word_count")
+    loop = loop_of(h.item())
+    assert not loop.started and loop.rev == 2
+
+
+def test_a_question_never_reaches_the_reader(tmp_path: Path) -> None:
+    reader = Reader("sounds good?")
+    h = Harness(
+        tmp_path,
+        ScriptedModel(RESTATED, [call("restate", text="v2")]),
+        FakeGitea(issue()),
+        reader=reader,
+    )
+    h.agent.intake()
+    h.say("sounds good?")
+    assert not loop_of(h.item()).started and reader.asked == []
+
+
+def test_a_plain_yes_to_an_older_revision_is_not_a_go(tmp_path: Path) -> None:
+    reader = Reader("yes")
+    h = Harness(
+        tmp_path,
+        ScriptedModel(RESTATED, [call("restate", text="v2")], STARTED),
+        FakeGitea(issue()),
+        reader=reader,
+    )
+    h.agent.intake()
+    h.say("change it a bit")  # rev-2 goes up
+    h.agent.handle(_msg("yes", h.thread()), about=1)
+    assert not loop_of(h.item()).started
+    assert [reply for _, reply in reader.asked] == ["change it a bit"]
+
+
+class _Model:
+    def __init__(self, result: Any) -> None:
+        self.result = result
+
+    def complete(self, events, tools, model, system=None) -> list[Any]:
+        if isinstance(self.result, Exception):
+            raise self.result
+        return self.result
+
+
+@pytest.mark.parametrize(
+    ("result", "agrees"),
+    [
+        ([ToolCall(call_id="v", tool="verdict", arguments={"answer": "yes"})], True),
+        (
+            [ToolCall(call_id="v", tool="verdict", arguments={"answer": "unclear"})],
+            False,
+        ),
+        ([], False),
+        (LLMError("down"), False),
+    ],
+)
+def test_the_reader_agrees_only_on_a_clear_yes(result: Any, agrees: bool) -> None:
+    reader = GoAheadReader(_Model(result), "m")  # type: ignore[arg-type]
+    assert reader.agrees("add count_words", "ok") is agrees
+
+
+# --- labels (D1) ----------------------------------------------------------------
+
+
+def bug(tmp_path: Path, *turns: list[Any], **kw: Any) -> tuple[Harness, Clock]:
+    clock = Clock()
+    h = Harness(
+        tmp_path,
+        ScriptedModel(*turns),
+        FakeGitea(issue(labels=("bug",))),
+        clock=clock,
+        bug_grace_s=600,
+        **kw,
+    )
+    return h, clock
+
+
+def test_a_bug_goes_ahead_after_the_grace_period(tmp_path: Path) -> None:
+    h, clock = bug(tmp_path, RESTATED, STARTED)
+    h.agent.intake()
+    assert "go ahead in 10 min unless you reply" in h.posted()[-1]
+    assert "going ahead in 10 min" in h.agent.status()
+    clock.now += 599
+    h.agent.intake()
+    assert not loop_of(h.item()).started
+    clock.now += 1
+    h.agent.intake()
+    assert loop_of(h.item()).started
+    assert "go-ahead on rev-1 from the bug grace period" in facts(h)
+
+
+def test_a_reply_stops_the_bugs_countdown(tmp_path: Path) -> None:
+    h, clock = bug(tmp_path, RESTATED, [call("ask_human", question="which file?")])
+    h.agent.intake()
+    h.say("hmm, what about unicode")
+    clock.now += 3600
+    h.agent.intake()
+    loop = loop_of(h.item())
+    assert not loop.started and loop.grace_until == 0 and loop.wait == ANSWER
+
+
+def test_a_new_revision_of_a_bug_gets_its_own_countdown(tmp_path: Path) -> None:
+    h, clock = bug(tmp_path, RESTATED, [call("restate", text="v2")], STARTED)
+    h.agent.intake()
+    clock.now += 300
+    h.say("use the other file")
+    assert loop_of(h.item()).grace_until == clock.now + 600
+    clock.now += 600
+    h.agent.intake()
+    assert "go-ahead on rev-2 from the bug grace period" in facts(h)
+
+
+def test_the_bug_label_reaches_the_driver(tmp_path: Path) -> None:
+    seen: list[str] = []
+
+    class Spy(ScriptedModel):
+        def complete(self, events, tools, model, system=None):  # type: ignore[no-untyped-def]
+            seen.append(system or "")
+            return super().complete(events, tools, model, system)
+
+    h = Harness(tmp_path, Spy(RESTATED), FakeGitea(issue(labels=("bug", "ui"))))
+    h.agent.intake()
+    assert "never fix a bug you couldn't see" in seen[0]
+    assert "labelled discuss" not in seen[0]
+
+
+def test_discuss_talks_before_it_restates(tmp_path: Path) -> None:
+    offered: list[set[str]] = []
+
+    class Spy(ScriptedModel):
+        def complete(self, events, tools, model, system=None):  # type: ignore[no-untyped-def]
+            offered.append({t["function"]["name"] for t in tools})
+            return super().complete(events, tools, model, system)
+
+    h = Harness(
+        tmp_path,
+        Spy([call("ask_human", question="what's it for?")], RESTATED),
+        FakeGitea(issue(labels=("discuss",))),
+    )
+    h.agent.intake()
+    assert "restate" not in offered[0]
+    assert loop_of(h.item()).wait == ANSWER
+    h.say("for the stats page")
+    assert "restate" in offered[1]
+    assert loop_of(h.item()).wait == GO_AHEAD
+
+
+def test_an_unlabelled_issue_waits_for_go_with_no_countdown(h: Harness) -> None:
+    h.agent.intake()
+    loop = loop_of(h.item())
+    assert loop.wait == GO_AHEAD and loop.grace_until == 0
+    assert h.item().position != READY
+
+
+def _msg(text: str, thread: str) -> Any:
+    from nisse_dev.transport import InboundMessage
+
+    return InboundMessage(DON, text, thread=thread)

nisse-dev/tests/test_loop_properties.py

@@ -19,7 +19,7 @@ from test_loop_milestones import DON, Forge, call
 from test_loop_milestones import world as world  # noqa: PLC0414 -- the fixture
 
 from nisse_dev.cancel import Cancel
-from nisse_dev.canonical import Fact, ToolCall
+from nisse_dev.canonical import Fact, PlanSubmitted, ToolCall, UserMessage
 from nisse_dev.gitea import Comment, Issue
 from nisse_dev.loop.agent import LoopAgent
 from nisse_dev.loop.driver import Driver
@@ -60,6 +60,8 @@ class PolicyModel:
             return [call("ask_human", question=f"question {self.n}?")]
         if roll < 0.12:
             return [ToolCall(call_id=f"p{self.n}", tool="nonsense", arguments={})]
+        if "restate" not in offered and "finish_milestone" not in offered:
+            return [call("ask_human", question=f"talk first {self.n}?")]  # discuss
         if "finish_milestone" not in offered:
             return [call("restate", text=f"restatement {self.n}")]
         if "wait_for_review" in offered and self.rng.random() < 0.2:
@@ -89,8 +91,14 @@ class Walk:
         self.steps: list[str] = []
         self.shown_at_go: list[str] = []  # item:revision on screen at each go
         self.next_issue = 15
+        self.now = 1000.0
         self.agent, self.transport = self._agent()
 
+    def reads_yes(self, proposal: str, reply: str) -> bool:
+        """The scripted go-ahead reader: a plain yes usually reads as one,
+        and nothing else ever does."""
+        return reply == "yep, that's right" and self.rng.random() < 0.7
+
     def _agent(self) -> tuple[LoopAgent, InMemoryTransport]:
         transport = InMemoryTransport()
         cancel = Cancel()
@@ -110,10 +118,16 @@ class Walk:
             cancel=cancel,
             oplog=OpLog("nisse-dev", _Null()),
             milestones=w["milestones"],
+            reader=self,  # type: ignore[arg-type]
+            bug_grace_s=600,
+            clock=lambda: self.now,
         )
         transport.on_message(agent.on_message)
         return agent, transport
 
+    def agrees(self, proposal: str, reply: str) -> bool:
+        return self.reads_yes(proposal, reply)
+
     def items(self) -> list[Any]:
         return self.world["store"].work_items()
 
@@ -127,7 +141,7 @@ class Walk:
         loop = loop_of(item) if item else None
         if item and loop:
             weights.update({"go": 3, "answer": 2, "abandon": 1, "go-stale": 1})
-            weights.update({"first": 1})
+            weights.update({"first": 1, "plain-yes": 2, "named-go": 1, "wait": 2})
             if loop.pr:
                 weights.update(
                     {"comment": 4, "merge": 2, "close-pr": 1, "comment-merge": 2}
@@ -139,11 +153,33 @@ class Walk:
         elif action == "issue":
             # A new issue, sometimes depending on one that is still open.
             n, self.next_issue = self.next_issue, self.next_issue + 1
-            forge.issues.append(Issue(n, f"task {n}", f"do task {n}", "don", ()))
+            labels = self.rng.choice([(), (), ("bug",), ("discuss",), ("design",)])
+            forge.issues.append(Issue(n, f"task {n}", f"do task {n}", "don", labels))
             live = [i.number for i in forge.assigned_issues("", "") if i.number != n]
             if live and self.rng.random() < 0.5:
                 forge.deps[n] = [self.rng.choice(live)]
             self.agent.intake()
+        elif action == "plain-yes" and loop:
+            # Read as a go-ahead or not; either way bound to what's up now.
+            if item.position == WAITING and loop.wait == GO_AHEAD:
+                self.shown_at_go.append(f"{item.id}:{loop.rev}")
+            self.transport.receive(DON, "yep, that's right", thread=loop.thread)
+        elif action == "named-go" and loop:
+            if item.position == WAITING and loop.wait == GO_AHEAD:
+                self.shown_at_go.append(f"{item.id}:{loop.rev}")
+            self.transport.receive(DON, f"go #{loop.issue}")
+        elif action == "wait":
+            # Time passes: bug countdowns may run out.
+            self.now += self.rng.choice([60, 700])
+            for other in open_items:
+                o = loop_of(other)
+                if (
+                    other.position == WAITING
+                    and o.wait == GO_AHEAD
+                    and 0 < o.grace_until <= self.now
+                ):
+                    self.shown_at_go.append(f"{other.id}:{o.rev}")
+            self.agent.intake()
         elif action == "first" and loop:
             self.agent.handle(InboundMessage(DON, f"do #{loop.issue} next"), None)
         elif action == "crash":
@@ -213,7 +249,7 @@ class Walk:
                 and f.event.text.startswith("go-ahead on rev-")
             ]
             assert all(f"{item.id}:{rev}" in self.shown_at_go for rev in gos), (
-                f"go_binds: {gos}: {where}"
+                f"go_binds: {item.id} {gos} not in {self.shown_at_go}: {where}"
             )
             # Blocked comes from external truth (L1): an item whose issue
             # had an open dependency from the start never ran before it closed.
@@ -238,6 +274,36 @@ class Walk:
                 assert not [
                     i for i in store.pending_intents() if i.work_item == item.id
                 ], f"closed_items_leave_nothing (intent): {where}"
+        for item in items:
+            # D1: a bug's grace period runs out only on an unanswered
+            # restatement: any reply since it went up stops the countdown.
+            replied = False
+            for e in store.transcript(item.id, "orchestrator").read():
+                text = getattr(e.event, "text", "")
+                if isinstance(e.event, Fact) and text.startswith("restatement rev-"):
+                    replied = False
+                elif isinstance(e.event, UserMessage) and e.actor == "operator":
+                    replied = replied or e.event.source.startswith("transport:")
+                elif text.endswith("from the bug grace period"):
+                    assert not replied, (
+                        f"grace_only_unanswered: #{loop_of(item).issue}: {where}"
+                    )
+        for item in items:
+            # D1: a `discuss` item talks before it restates.
+            if "discuss" not in loop_of(item).labels:
+                continue
+            events = store.transcript(item.id, "driver").read()
+            plans = [e.id for e in events if isinstance(e.event, PlanSubmitted)]
+            spoke = [
+                e.id
+                for e in events
+                if e.actor == "operator"
+                and isinstance(e.event, UserMessage)
+                and e.event.source.startswith("transport:")
+            ]
+            assert not plans or (spoke and spoke[0] < plans[0]), (
+                f"discuss_talks_first: #{loop_of(item).issue}: {where}"
+            )
         assert not [i for i in items if i.position == RUNNING], (
             f"one_active (nothing left running): {where}"
         )