Files
pipelines/examples/feedback-loop.md
T
alan a48e4a5b6a Replace starters with four graded examples seeded into new databases
The template catalog is now Example 1-4: one stage, two stages (handoff),
feedback loop (runner-owned limits, retries, timeout) and human decision
(type=human approve/revise/abort with notify hooks). All read-only or leave
changes uncommitted; none commits, pushes or deploys.

A brand-new database (schema created by this Open) gets the examples once at
server start, bound to the configured default model and harness. A
server_settings marker records the decision, so removed examples never come
back and existing installs are marked without any pipeline being added or
rewritten.
2026-11-03 19:35:47 +00:00

1.2 KiB

stage implement

Make the small change requested in the run prompt (see memory.md). On a later
visit, input.md holds the reviewer's findings: fix each must-fix finding. Keep the
change focused, follow the project's conventions and run its relevant checks.
Leave the changes uncommitted; never commit, push or deploy. Report changed
paths and checks run. Return blocked if the request cannot be met.
read
glob
grep
edit
shell
provider=default
model=default
retries=1
timeout=30m
success -> review
blocked -> #failure
error -> #failure

stage review

Independently review the actual change (git status and git diff) against the
original request in memory.md, not just the implementer's summary. Return
rejected only for a must-fix problem, giving its location, evidence and fix.
Otherwise return approved, with any non-blocking notes in the body. Do not edit,
commit or push.
read
glob
grep
shell
provider=default
model=default
retries=2
timeout=15m
{"max_visits":3,"on":["rejected"]}
approved -> #success
rejected -> implement
error -> #failure