scriptoriumadmin/fabro
1
0
Fork 0
mirror of https://github.com/fabro-sh/fabro.git synced 2026-09-06 08:18:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 11
fabro/docs/specs
History
Bryan Helmkamp a2f9e87b7c Close spec compliance gaps: retry context, thread resolution, fan-in logging 
Fix 3 confirmed gaps from spec compliance review (85 items, 91.8% aligned):

- Write internal.retry_count.<node_id> to PipelineContext after retries
  so handlers and conditions can access retry counts (spec 5.1)
- Add graph-level default_thread (step 3) to 5-step thread ID resolution,
  pass graph param to resolve_thread_id (spec 5.4)
- Write prompt.md/response.md in fan_in LLM evaluation path (spec 5.6)

Also includes pre-existing improvements: checkpoint stores node_outcomes
and next_node_id for correct resume, engine timeout enforcement,
auto_status support, fidelity degradation on resume, preamble injection,
is_retryable error classification, stylesheet specificity correction,
full stylesheet parse validation, direction_valid lint rule, pre-hook
returns Skipped not Fail, fan-in score-based sorting and all-fail
detection, manager_loop child autostart and steer cooldown.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-22 10:49:21 -04:00
..
attractor-spec.md Close spec compliance gaps: retry context, thread resolution, fan-in logging 2026-02-22 10:49:21 -04:00
coding-agent-loop-spec.md specs 2026-02-19 13:41:55 -04:00
README.md specs 2026-02-19 13:41:55 -04:00
unified-llm-spec.md Fix model alias resolution and invalid gpt-5.2-mini model ID 2026-02-20 14:01:30 -04:00

README.md

Attractor

This repository contains NLSpecs to build your own version of Attractor to create your own software factory.

Although bringing your own agentic loop and unified LLM SDK is not required to build your own Attractor, we highly recommend controlling the stack so you have a strong foundation.

Specs

Building Attractor

Supply the following prompt to a modern coding agent (Claude Code, Codex, OpenCode, Amp, Cursor, etc):

codeagent> Implement Attractor as described by https://factory.strongdm.ai/

Terminology

  • NLSpec (Natural Language Spec): a human-readable spec intended to be directly usable by coding agents to implement/validate behavior.