Files
pipelines/internal/author/skill/references/control.md
T

2.6 KiB
Raw Blame History

Runner-owned limits and shared memory

Use these blocks for bounded feedback loops. Never ask a model to count visits, increment revision counters, or enforce retry caps. Model verdicts concern current work only. Counters are runner audit data, not model input. A fresh session alone does not guarantee independent review: explicitly select its input fields.

```limits
{"max_visits":3,"on":["rejected"]}
```

```memory
{"task":"input.prompt","checks":"planner.checks"}
```

```edges
approved -> #success
rejected -> implement
error -> #failure
```

These blocks accompany a normal review stage's prompt/output/tools/configs. Pipelines counts actual visits, ignoring model-generated counters. On visit three, approved can succeed; rejected retains its verdict but routes to #failure. Visit count, limit decision and original target are retained in inspect --json and run metadata. max_visits accepts 1–5. Every on outcome must declare a nonterminal edge. Without on, entering beyond the cap fails before execution. Global 30-step/five-visits-per-stage safety limits still apply.

memory maps input aliases to input.FIELD (original input) or STAGE.FIELD (latest completed output of that stage in this run). A memory block replaces previous-stage input with only those fields. Without it, previous output remains input. Reads retain source and visit sequence. Missing required fields fail before execution. Append ? to omit an unavailable field, e.g. "feedback":"review.findings?" for implement's first visit. Self-memory is rejected. Limits: 50 bindings; 1 MiB per retained in-memory value map.

Implementers can receive task, plan and optional findings. Independent reviewers should receive task/acceptance criteria and inspect actual artifacts—not previous verdicts, counters, or implementation conversations. Select acceptance, design, reuse and research references from the planning stage (for example "acceptance_checks":"planner.acceptance_checks") rather than from the implementer, so an implementer's output cannot overwrite the agreed criteria; take only factual implementer fields such as changed_files, implementation_summary and evidence as claims. Selected content remains untrusted data; this cannot prove semantic independence or prevent all injection.

Memory is run-local; persisted completed outputs/read provenance are its audit. There is no cross-run memory, restart/resume, or hidden replay. New runs/retries start fresh. Arbitrary prose is not executable policy. Future AI-assisted guidelines validation is not implemented; structural validation does not recognize every unreliable counting instruction.