docs(examples): add builder-adversary-deferred — verify after a long segment
Coarsest review cadence: the Builder self-certifies the build phases and the Adversary does ONE comprehensive cold-verification of the whole accumulated build in a final `review` phase (vs orig per-phase, lean per-gate). Full original prompts + a DEFERRED REVIEW CADENCE override, so it isolates verification cadence. Cheapest coordination; the trade-off is the independent check arrives late (late rework risk + self-certification drift on build phases). README spells it out. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
79
examples/builder-adversary-deferred/agents.toml
Normal file
79
examples/builder-adversary-deferred/agents.toml
Normal file
@ -0,0 +1,79 @@
|
||||
# examples/builder-adversary-deferred — Adversary verifies ONCE, after a long segment of building.
|
||||
#
|
||||
# Same pattern + full original prompts as ../builder-adversary, but the REVIEW CADENCE is coarsest:
|
||||
# • lean = the Adversary verifies per gate (finest)
|
||||
# • orig = the Adversary verifies per phase (medium)
|
||||
# • deferred = the Adversary verifies ONCE, comprehensively, after the whole build (coarsest)
|
||||
# The Builder SELF-CERTIFIES the build phases (wc, json) to advance; the Adversary stays out until the
|
||||
# final `review` phase, where it cold-verifies the ENTIRE accumulated calculator in one pass. Cheapest
|
||||
# coordination, but the independent check arrives late (see README for the trade-off).
|
||||
#
|
||||
# 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 = "badef-" # tmux namespace: badef-builder, badef-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: badef-builder
|
||||
kind = "loop"
|
||||
role = "builder"
|
||||
dir = "./work"
|
||||
watch = "heal+stall"
|
||||
|
||||
[[agent]]
|
||||
name = "adversary"
|
||||
session = "badef-adv"
|
||||
kind = "loop"
|
||||
role = "adversary"
|
||||
dir = "./work-adv"
|
||||
watch = "heal+stall"
|
||||
|
||||
[[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" }
|
||||
# Build phases (wc, json) are self-certified by the Builder; the final `review` phase is the single
|
||||
# comprehensive Adversary gate over the whole accumulated build.
|
||||
phases = [
|
||||
{ id = "wc", plan = "plans/wc.md", status = "STATUS-wc.md" },
|
||||
{ id = "json", plan = "plans/json.md", status = "STATUS-json.md" },
|
||||
{ id = "review", plan = "plans/review.md", status = "STATUS-review.md" },
|
||||
]
|
||||
Reference in New Issue
Block a user