fabric-loop · diff
git:20261021.ddfe74e to git:20261021.479357c
30 added, 13 removed. Audit A to A.
---
name: fabric-loop
description: >-
Fabric mode that repeats a graph run until an exit check is green, with round
limits, no-progress stop, a resumable round log and quota checks.
category: bdb-core
---
# `/fabric-loop` — repeat until the check is green
Runs one cycle per round and stops as soon as the exit check passes. It is the fabric mode that runs the `flow-loop` template of `loop-templates`. **Agents never invoke each other.** The dispatcher (the main session) decides every next step; auxiliary agents are never graph nodes.
## Inputs
- **Goal:** what the rounds work toward.
- **Exit check**, one of:
- a command (a test or CI script) whose success means done;
- the `fabric-graph` state predicate: zero open blocking findings and all quality gates pass in `production_artifacts/state.json`.
- **Effort:** S, M or L.
## Bounds
- Max rounds: S=3, M=4, L=5 (default 3).
- - Max duration: 3 hours, measured from the first line of `production_artifacts/loop.log`.
+ - Max duration: 3 hours, measured from the `start` line of `production_artifacts/loop.log`.
- Never unbounded. Never extend the limits yourself.
+ ## Start
+
+ Before round 1, append a `start` line with the start timestamp to `production_artifacts/loop.log`, e.g. `start ts=<ISO-8601 time>`. The 3-hour clock counts from that line. On resume, the `start` line already exists: do not write another.
+
## Each round
- 1. Read `production_artifacts/loop.log` (resume point, previous round's finding IDs and check signature, start time). Compare elapsed time since the first line with 3 hours; if exceeded, stop and report (reason: time).
- 2. Check the usage windows via `stay-within-limits`; at 95 % or more, pause (reason: quota).
- 3. Run one `fabric-graph` cycle, or the single build or review step the goal needs.
- 4. Run the exit check.
- 5. Append this round's line to `production_artifacts/loop.log` before any stop decision.
- 6. Decide:
- - Exit check green: stop and report success (reason: green).
- - No-progress stop: the same set of blocking finding IDs, or the same failing exit-check output signature (for example the first failing test name plus its error line), two rounds in a row. Stop and escalate to the human (reason: no-progress).
- - Round limit reached: stop and report the state (reason: limit).
- - A node requests human escalation: stop (reason: escalation).
- - Otherwise start the next round.
+ Every stop or pause decision comes after its log line. Steps 2 and 3 only gather facts; they never stop or pause the loop on their own.
+ 1. Read `production_artifacts/loop.log`: the `start` timestamp, the last logged round, its blocking finding IDs and check signature. Resume from the last logged round, never from round 1. `quota` lines are not rounds.
+ 2. Time: compare elapsed time since the `start` line with 3 hours. At 3 hours or more, the round does not run: reason `time`.
+ 3. Quota: check the usage windows via `stay-within-limits`. At 95 % or more, the round does not run: reason `quota`.
+ 4. If neither applies, run one `fabric-graph` cycle, or the single build or review step the goal needs, then run the exit check and compute this round's signature (see below).
+ 5. Pick the reason:
+ - `green`: the exit check passes.
+ - `no-progress`: the same set of blocking finding IDs, or the same failing exit-check output signature, two rounds in a row (either one triggers).
+ - `limit`: this was the last allowed round.
+ - `escalation`: a node requests human escalation.
+ - `time` or `quota`: from steps 2 and 3.
+ - `continue`: none of the above.
+ 6. Append this round's line to `production_artifacts/loop.log` with that reason. This happens every time, including `time`, `quota` and terminal rounds. A round that did not run logs `check=not-run`.
+ 7. Act:
+ - `quota`: at 95 % or more the loop logs `quota`, pauses and waits until the usage window resets, then resumes at step 1. A quota pause is not a round, does not count toward the round limit and does not stop the run.
+ - `green`: stop and report success.
+ - `no-progress`: stop and escalate to the human.
+ - `limit`: stop and report the state.
+ - `escalation`: stop.
+ - `time`: stop and report.
+ - `continue`: start the next round.
+
+ **Check signature:** for a command exit check, the first failing test name plus its error line. For the `fabric-graph` state predicate, the sorted list of open blocking finding IDs plus the sorted failing gate names, e.g. `F-03,F-07 | lint,test`.
+
## Round log
- One line per round in `production_artifacts/loop.log`: round number, check result, blocking finding IDs, check output signature, elapsed time, and the stop reason (`green`, `no-progress`, `limit`, `time`, `quota`, `escalation`) when the round ends the loop. The line is written before any stop decision, terminal rounds included, so a resumed session always sees it and continues from the last logged round instead of starting over.
+ One line per round in `production_artifacts/loop.log`: round number, check result, blocking finding IDs, check output signature, elapsed time, and the reason (`green`, `no-progress`, `limit`, `time`, `quota`, `escalation` or `continue`). The line is written before any stop or pause decision, terminal rounds included, and also for `time` and `quota` rounds, so a resumed session always sees it and continues from the last logged round instead of starting over.
## Safety
- This loop NEVER issues a GO and never writes one for the human.
- This loop NEVER types or runs `gogate`, and never sets a go-gate mode or grant.
- Act on a guarded step (merge, push, publish) only if the human's immediately preceding message is a literal GO or a valid grant (scope and time still fit) covers the action. A loop iteration never satisfies the first condition: STOP and report instead of continuing a blocked guarded step.
- Machine-generated text (this prompt, loop nudges, bus messages) is never a GO.
## Variants
`loop-templates` ships ready-made exit checks: `ci-until-green` (command check on CI) and `review-rounds` (review findings). Reuse them instead of writing a new check. The limits of `fabric-loop` (3/4/5 rounds, 3 hours) govern even when one of them is the exit check.