recipe-maintainers/agent-orchestrator
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs(examples): add builder-adversary-lean — context hygiene + per-gate review

Browse Source 
Isolates the two effects conflated in builder-adversary-stateless: keeps all the
CONTEXT HYGIENE (compact/diffs/lean loads) but ENFORCES full per-gate review
granularity (one claim per gate, one independent verdict per gate, no batching).
Tests whether the token saving is real efficiency vs reduced scrutiny.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
mfowler
2026-06-14 21:42:12 +00:00
parent 985d33dd51
commit e0425e6108
8 changed files with 240 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
examples/builder-adversary-lean/README.md Normal file
View File

@ -0,0 +1,30 @@
# Builder/Adversary example — context-lean + full per-gate review
The [`builder-adversary-stateless`](../builder-adversary-stateless/) variant added **context
hygiene** (compact at each checkpoint, read diffs not trees, lean loads) and, in benchmarking,
happened to also do *fewer* review rounds — so its token saving was partly leaner context and partly
*less scrutiny*. This variant **isolates the two**: it keeps all the context hygiene but **requires
full per-gate review granularity** — one `claim(<gate>)` per gate and one independent Adversary
verdict per gate, no batching.
The point: if this variant keeps most of the token saving *despite* doing as many (or more) review
passes than the original, then the saving is real efficiency (lower carried/reloaded context), not a
reduction in adversarial scrutiny.
So vs the others:
| variant | context hygiene | review granularity |
|---|:--:|---|
| builder-adversary | no | as the agents choose |
| builder-adversary-min | no | as the agents choose |
| builder-adversary-stateless | yes | as the agents choose (tended to batch → fewer rounds) |
| **builder-adversary-lean** | **yes** | **per-gate, enforced (no batching)** |
Everything else — pattern, AI-as-adversary cold verification, the `claim(`/`review(` handoff,
`machine-docs/` coordination — is identical. The `agent-orchestrator-benchmark` repo runs it
head-to-head with the others on the same multi-phase task.
```bash
python3 ../../agents.py status --config agents.toml
python3 ../../agents.py up --config agents.toml # needs `claude` on PATH
```