Model the agent loop as the architecture describes it
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m24s

A Quint model of the design in docs/Architecture.md (PR #90): intake,
restatements and go-aheads, park-and-switch, blocked dependencies,
harness-owned milestones, waiting for merges, review follow-ups, record
issues, crashes and build VM wipes. It found five gaps; the model carries
the proposed fixes, and loop_scenarios.qnt keeps each counterexample.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
This commit is contained in:
dongarandClaude Opus 5.5 committed 2026-10-02 19:24:39 +00:00
1 parent 7b031179a2
commit 76e9fa38c7
3 files changed
+598

No files matched your search

+32
View File
@@ -36,3 +36,35 @@ Exhaustive bounded checking (`quint verify`) uses Apalache and needs Java 17.
left, change the matching function here in the same PR. When a
counterexample's fix lands, flip its scenario's `expect` to the property
holding, and drop the `xfail` from its Python reproduction.
## `loop.qnt`: the agent loop, as the architecture describes it
Models the design in `docs/Architecture.md` rather than code, since the new
loop doesn't exist yet:
- work items from assigned issues and conversations;
- restatements and revision-bound go-aheads;
- park-and-switch, with branches pushed on parking;
- blocked dependencies;
- harness-owned milestones and waiting for merges;
- review follow-ups;
- record issues;
- crashes and build VM wipes at any point.
A counterexample here is a gap in the architecture, so it is fixed there,
and the model carries the fix (marked `FIX n`). `loop_scenarios.qnt` keeps each
counterexample as a trace of the fixed behaviour. Each trace fails if its fix
is reverted, and each property that never failed was checked against a
deliberately broken model.
```sh
quint run specs/loop.qnt --invariant=all_properties --max-steps=80 --max-samples=200000
quint test specs/loop_scenarios.qnt
```
Traces need about 80 steps to reach second milestones. The `w_*` values at the
end are reachability witnesses: each should be *violated*, which shows the
state it names is reachable.
**Keeping it true.** When the architecture changes a rule this models, change
the model in the same PR. When the new loop is built (Development Plan Phase 2),
each property gets a test against the real code, as `orchestrator.qnt`'s did.