mfowler
a0f7652e9e
A single Builder that builds AND self-verifies (same DoD rigor), with NO independent Adversary and no claim/review handoff. The control for measuring what the AI adversary costs (its tokens, ~half of a loop-pair run) and buys (independent cold verification vs self-certification). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
1.8 KiB
1.8 KiB
Phase json — machine-readable output
Mission. Extend the wc.py from the previous phase with a --json mode, without regressing any
wc-phase behaviour. Single source of truth for this phase.
(The phase config gives the Builder claude-opus-4-8 for this phase — an example of a per-phase
model override; the Adversary stays on the default model.)
Definition of Done
- D1 — json output.
python wc.py --json FILEprints a single JSON object:{"lines": N, "words": N, "chars": N, "file": "FILE"}(valid JSON, parseable byjson.loads). With stdin (no FILE),"file"isnull. - D2 — composes with flags.
--jsonhonours-l/-w/-c: only the requested counts appear as keys (plusfile). E.g.wc.py --json -l FILE→{"lines": N, "file": "FILE"}. - D3 — no regression. Every
wc-phase gate (D1–D4 there) still passes unchanged. - D4 — tests green.
test_wc.pyis extended for the JSON cases andpytest -qis all-green.
How the Adversary verifies (cold)
pytest -q # D4 + D3 regression
printf 'a b c\nd e\n' > /tmp/f.txt
python wc.py --json /tmp/f.txt | python -c 'import sys,json; d=json.load(sys.stdin); \
assert d=={"lines":2,"words":5,"chars":10,"file":"/tmp/f.txt"}, d; print("ok")' # D1
python wc.py --json -l /tmp/f.txt # D2: expect {"lines": 2, "file": "/tmp/f.txt"}
The Builder restates the exact commands, expected JSON, and commit sha in
machine-docs/STATUS-json.md. When every DoD item has a fresh PASS in machine-docs/REVIEW-json.md
and there is no ## VETO, the Builder writes ## DONE to STATUS-json.md — this is the last phase,
so the watchdog then fires the one-shot reporter (see agents.toml [loop].on_complete).