mfowler
e0425e6108
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>
93 lines
3.5 KiB
TOML
93 lines
3.5 KiB
TOML
# examples/builder-adversary-lean — context hygiene + ENFORCED full per-gate review.
|
|
#
|
|
# Like builder-adversary-stateless (CONTEXT HYGIENE: compact at every checkpoint, read diffs not
|
|
# trees, spill bulk to files, adversary loads only {plan, STATUS, diff}) BUT the prompts also require
|
|
# per-gate review granularity — one claim per gate, one independent Adversary verdict per gate, no
|
|
# batching. This isolates "leaner context" from "fewer review passes". Loop agents not resumed →
|
|
# fresh session per phase. See README.md.
|
|
#
|
|
# python3 ../../agents.py status --config agents.toml
|
|
# python3 ../../agents.py up --config agents.toml # needs `claude` on PATH
|
|
|
|
[watchdog]
|
|
signal_interval = 30
|
|
heavy_interval = 300
|
|
limit_probe_fallback = 300
|
|
limit_reset_slack = 45
|
|
stall_grace = 180
|
|
|
|
[defaults]
|
|
session_prefix = "blean-" # REQUIRED — sessions: blean-builder, blean-adv, …
|
|
log_dir = ".ao-state"
|
|
backend = "claude" # set to "demo" for a dependency-free mechanics-only run
|
|
model = "claude-sonnet-4-6"
|
|
watch = "heal"
|
|
|
|
[backend.claude]
|
|
bin = "claude"
|
|
flags = "--dangerously-skip-permissions"
|
|
remote_control = true
|
|
supports_resume = true
|
|
prompt_delivery = "arg"
|
|
process_name = "claude"
|
|
submit_key = "Enter"
|
|
stall_idle = 300
|
|
active_re = "esc to interrupt|Running tool|⠇|⠙|· \\d+"
|
|
limit_re = "spend limit|usage limit|limit reached|reached your .*limit|out of (credits|tokens)"
|
|
fatal_re = "redacted_thinking|blocks cannot be modified|cannot be modified"
|
|
|
|
[backend.demo]
|
|
bin = "echo '[demo] {session} up (kickoff: {kickoff})'; exec sleep 1000000"
|
|
prompt_delivery = "exec"
|
|
|
|
[[agent]]
|
|
name = "builder" # tmux session: blean-builder
|
|
kind = "loop"
|
|
role = "builder"
|
|
dir = "./work"
|
|
watch = "heal+stall"
|
|
|
|
[[agent]]
|
|
name = "adversary"
|
|
session = "blean-adv"
|
|
kind = "loop"
|
|
role = "adversary"
|
|
dir = "./work-adv"
|
|
watch = "heal+stall"
|
|
|
|
[[agent]]
|
|
name = "orchestrator" # tmux session: blean-orchestrator
|
|
kind = "persistent"
|
|
model = "claude-opus-4-8"
|
|
resume = true
|
|
watch = "heal"
|
|
prompt = "You supervise this Builder/Adversary project. On startup: read machine-docs/ for the current phase's STATUS/REVIEW, confirm both loops + the watchdog are up, report the phase and any open findings/VETO. Then stay available; intervene only if the pair is stuck."
|
|
|
|
[[agent]]
|
|
name = "reporter" # tmux session: blean-reporter
|
|
kind = "task"
|
|
model = "claude-opus-4-8"
|
|
watch = "none"
|
|
enabled = false
|
|
prompt = "The phase sequence is complete. Read machine-docs/ across all phases, write a short machine-docs/REPORT.md (what was built, each gate's final verdict, deferred items), then go idle."
|
|
|
|
[[service]]
|
|
name = "cleanlogs"
|
|
command = "python3 ../../agent-log.py follow-all"
|
|
dir = "."
|
|
|
|
[loop]
|
|
state_file = "phase-idx"
|
|
resume_phase = true
|
|
auto_advance = true
|
|
done_marker = "## DONE"
|
|
kickoff_template = "prompts/kickoff.md"
|
|
roles_dir = "prompts"
|
|
handoff = { repo = "./work", claim_pings = "adversary", review_pings = "builder", inboxes = ["ADVERSARY-INBOX.md", "BUILDER-INBOX.md"], claim_pattern = "^claim", review_pattern = "^review", state_subdir = "machine-docs" }
|
|
on_complete = { trigger_file = ".run-report-on-complete", run = "reporter" }
|
|
|
|
phases = [
|
|
{ id = "wc", plan = "plans/wc.md", status = "STATUS-wc.md" },
|
|
{ id = "json", plan = "plans/json.md", status = "STATUS-json.md", models = { builder = "claude-opus-4-8" } },
|
|
]
|