dongarandClaude Opus 5.5 266b5dbbd7 Check loop.qnt's properties against the real loop (M2.1, PR D part 1) ...

test_loop_properties.py walks the new loop with a seeded mix of operator
and Gitea actions (go-aheads, stale go-aheads, answers, comments, merges,
the comment-then-merge race, closes, abandon, a crash and restart) and an
adaptive scripted model, checking every loop.qnt property after every
step. It found two bugs, both fixed with regression tests: abandoning an
item left its open PR open (the model's fix 1, now in code), and after a
review fix became a follow-up PR, the next fix went to the merged branch.

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

2026-10-03 14:19:19 +00:00

..

bench

Run every command on the build VM over SSH (M1.3)

2026-10-02 21:39:46 +00:00

loop

Check loop.qnt's properties against the real loop (M2.1, PR D part 1)

2026-10-03 14:19:19 +00:00

__init__.py

Scaffold hello-world apps, test frameworks, and Gitea CI

2026-09-05 18:48:51 +00:00

agent.py

Publish only the work: leave build artifacts out and report them (#80)

2026-10-02 22:38:13 +00:00

approvals.py

Retire the old build spec, and point every reference at the architecture (M0.1)

2026-10-01 00:17:48 +00:00

cancel.py

Put work items in the state store, and bind the log to them (M1.1)

2026-10-01 23:20:29 +00:00

canonical.py

Give each role its own view of the transcript (M1.2)

2026-10-02 00:39:38 +00:00

catalog.py

Retire the old build spec, and point every reference at the architecture (M0.1)

2026-10-01 00:17:48 +00:00

config.py

The new loop's core: intake, restatement, go-ahead, threads (M2.1, PR B)

2026-10-02 23:46:42 +00:00

context.py

Retire the old build spec, and point every reference at the architecture (M0.1)

2026-10-01 00:17:48 +00:00

control.py

Give each role its own view of the transcript (M1.2)

2026-10-02 00:39:38 +00:00

delegation.py

Give each role its own view of the transcript (M1.2)

2026-10-02 00:39:38 +00:00

dump.py

Give each role its own view of the transcript (M1.2)

2026-10-02 00:39:38 +00:00

envfile.py

Retire the old build spec, and point every reference at the architecture (M0.1)

2026-10-01 00:17:48 +00:00

evals.py

Put work items in the state store, and bind the log to them (M1.1)

2026-10-01 23:20:29 +00:00

execution.py

Run every command on the build VM over SSH (M1.3)

2026-10-02 21:39:46 +00:00

executor.py

Flatten harness branch names so a model's branch can't block them

2026-10-02 22:29:20 +00:00

expert.py

Put work items in the state store, and bind the log to them (M1.1)

2026-10-01 23:20:29 +00:00

gates.py

Retire the old build spec, and point every reference at the architecture (M0.1)

2026-10-01 00:17:48 +00:00

git.py

Milestones and review in the new loop (M2.1, PR C)

2026-10-02 23:53:02 +00:00

gitea.py

Milestones and review in the new loop (M2.1, PR C)

2026-10-02 23:53:02 +00:00

llm.py

Rename the delegate and consultant roles to helper and expert

2026-10-01 23:04:37 +00:00

main.py

The new loop's core: intake, restatement, go-ahead, threads (M2.1, PR B)

2026-10-02 23:46:42 +00:00

matrix.py

Matrix threads in the transport (M2.1, PR A)

2026-10-02 23:40:24 +00:00

oplog.py

Retire the old build spec, and point every reference at the architecture (M0.1)

2026-10-01 00:17:48 +00:00

planner.py

Give each role its own view of the transcript (M1.2)

2026-10-02 00:39:38 +00:00

poller.py

Retire the old build spec, and point every reference at the architecture (M0.1)

2026-10-01 00:17:48 +00:00

probe.py

Enforce the tool-call contract, asking servers only where it works

2026-09-24 22:54:49 +00:00

publish.py

Publish only the work: leave build artifacts out and report them (#80)

2026-10-02 22:38:13 +00:00

reconcile.py

Retire the old build spec, and point every reference at the architecture (M0.1)

2026-10-01 00:17:48 +00:00

render_anthropic.py

Give each role its own view of the transcript (M1.2)

2026-10-02 00:39:38 +00:00

render.py

Give each role its own view of the transcript (M1.2)

2026-10-02 00:39:38 +00:00

state.py

Give each role its own view of the transcript (M1.2)

2026-10-02 00:39:38 +00:00

testing.py

Run every command on the build VM over SSH (M1.3)

2026-10-02 21:39:46 +00:00

tools.py

Run every command on the build VM over SSH (M1.3)

2026-10-02 21:39:46 +00:00

transport.py

Matrix threads in the transport (M2.1, PR A)

2026-10-02 23:40:24 +00:00

views.py

The new loop's core: intake, restatement, go-ahead, threads (M2.1, PR B)

2026-10-02 23:46:42 +00:00

worker.py

Retire the old build spec, and point every reference at the architecture (M0.1)

2026-10-01 00:17:48 +00:00