Runs that go in circles end (M7.8)
CI / checks (push) Skipped
CI / checks (pull_request) Failing after 1m50s
CI / e2e (pull_request) Skipped

Driver.run checks each turn with nisse_core.loop.circles and ends the run
as "circling" when the same calls get much the same back, one harness
correction is given again and again, or the model apologises, for
circle_repeats turns in a row (default 3). Near-identical calls (git add
a.py, b.py) and scattered apologies stay flags on the status page. A
fact in the transcript says why the run ended.

nisse-dev calls in a helper as for a stuck run, then asks the operator;
nisse-review counts a failed run and posts none of its drafts. Tuning:
tuning.driver / tuning.review circle_repeats (0 off) and circle_similar.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
This commit is contained in:
dongarandClaude Opus 5.5 committed 2026-10-26 16:30:07 +00:00
1 parent 516a328618
commit 74bc68db1c
20 files changed
+506 -20

No files matched your search

+43
View File
@@ -249,6 +249,49 @@ def test_stuck_again_in_the_same_milestone_asks_the_operator(
assert len(helper.calls) == 2 # one delegation: its two turns
def test_a_driver_going_in_circles_gets_a_helper_too(world: dict[str, Any]) -> None:
# L2, M7.8: the same command, the same output, turn after turn.
helper = Spy(
[call("write_file", path="fixed.py", content="F = 1\n")],
[hand_back()],
)
model = ScriptedModel(
RESTATE,
[call("start_milestone", name="words")],
*[[call("run_command", command="true")] for _ in range(3)],
[call("finish_milestone", summary="fixed with help", final="yes")],
)
agent, transport = loop_agent(world, model, helpers=helpers(helper))
agent.intake()
say(transport, world, "go")
assert any("so a helper is taking over" in m.text for m in transport.outbound)
assert "near-identical replies in a row" in str(helper.calls) # in the brief
assert loop_of(item(world)).helped_at == 1
def test_circling_again_in_the_same_milestone_asks_the_operator(
world: dict[str, Any],
) -> None:
helper = Spy(
[call("write_file", path="tried.py", content="T = 1\n")],
[hand_back()],
)
circling = [[call("run_command", command="true")] for _ in range(3)]
model = ScriptedModel(
RESTATE,
[call("start_milestone", name="words")],
*circling,
*circling, # after the helper: round again
)
agent, transport = loop_agent(world, model, helpers=helpers(helper))
agent.intake()
say(transport, world, "go")
loop = loop_of(item(world))
assert loop.wait == ANSWER
assert "I stopped short: 3 near-identical replies in a row" in loop.note
def test_ask_expert_answers_within_its_budget(world: dict[str, Any]) -> None:
answer = {"answer": "use a dict", "confidence": "high", "caveats": ""}
expert = Spy(