mfowler
985d33dd51
Same pattern + AI-as-adversary verification as builder-adversary-min, but the
role prompts add CONTEXT HYGIENE: /compact at every checkpoint (lossless — state
is on disk), read diffs not trees, spill bulk output to files, adversary loads
only {plan, STATUS, diff}. Loop agents non-resumed → fresh session per phase.
Targets cache-read (the dominant cost in a long loop) without changing what the
agents do or how they verify.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Builder/Adversary example — context-lean ("stateless") variant
Same pattern, same AI-as-adversary verification, same gates as
../builder-adversary and
../builder-adversary-min — but the role prompts add a context
hygiene discipline so each loop carries and reloads as little conversation as possible. Nothing
about what the agents do or how they verify changes; only how much context they drag from turn to
turn.
Why
In a long autonomous loop the dominant token cost is cache-read: every turn re-sends the conversation so far (the unchanged prefix is billed as cache-read, ~10% of input price, but it's billed every turn). So cost ≈ context length × turns. The role prose is a rounding error against that. The win is keeping the conversation short and not carrying it where it isn't needed.
This protocol already makes that safe: the durable state is on disk (git + the plan + STATUS/REVIEW/JOURNAL), so the conversation is disposable scratch. These prompts exploit that:
- Compact at every checkpoint. After each gate is committed (Builder) or each verdict is written
(Adversary), run
/compact— lossless here, because the agent reloads from git + STATUS/REVIEW. - Read diffs, not trees.
git diff <last-sha>..HEADand only the touched files — never re-read the whole repo. - Spill bulk to files. Long build/test/verification output goes to a file; read back only the slice you need, instead of dumping it into context.
- Adversary loads only {plan, STATUS, diff} per gate — full cold AI judgment, tiny footprint.
Config note
Run the loop agents non-resumed (the default in this agents.toml — loop agents don't set
resume = true), so each time the watchdog restarts a loop (notably at every phase advance) it
starts a fresh session rather than carrying the prior phase's whole conversation forward. The
in-phase shrinking is done by /compact per the prompts above.
A natural future engine lever (not yet implemented) would be a watchdog policy that recycles a loop's session after each checkpoint commit (claim/review), giving fresh context per gate rather than per phase — the same idea, enforced by the harness instead of the prompt.
Compared
The agent-orchestrator-benchmark repo runs this variant head-to-head against
builder-adversary and builder-adversary-min on the same multi-phase task (all on Sonnet),
reporting tokens per loop — to quantify how much the context discipline saves while keeping identical
gate outcomes.
python3 ../../agents.py status --config agents.toml
python3 ../../agents.py up --config agents.toml # needs `claude` on PATH