[email protected]andClaude Opus 4.6 953833208e feat(engine): RLM best-practices enhancements from cross-reference analysis ...

Cross-referenced our implementation against the official RLM (alexzhang13/rlm),
fast-rlm (avbiswas/fast-rlm), and Prime Intellect's verifiers implementation.
Key enhancements:

- FINAL(answer) / FINAL_VAR(name): explicit termination pattern matching
  all three reference implementations. Code can signal completion at any
  point, not just via return value.
- llm_query_batched(prompts): parallel recursive sub-calls via tokio::spawn,
  matching fast-rlm's asyncio.gather pattern and Prime Intellect's llm_batch.
- Output truncation increased to 8000 chars (from 120), matching Prime
  Intellect's 8192 default. Shows [TRUNCATED: last N chars] or [FULL OUTPUT].
- Step 0 orientation preamble: auto-injects context metadata (message count,
  total chars, goal, last user message preview) before first code step,
  matching fast-rlm's auto-print pattern.
- Error-to-LLM flow: Python parse errors, runtime errors, NameErrors,
  OS errors, and async errors now flow back as stdout content instead of
  terminating the step, enabling LLM self-correction on next iteration.
  Only VM panics (catch_unwind) terminate as EngineError.

74 tests passing, zero clippy warnings.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

2026-03-21 22:05:05 -07:00

..

ironclaw_engine

feat(engine): RLM best-practices enhancements from cross-reference analysis

2026-03-21 22:05:05 -07:00

ironclaw_safety

perf(safety): single-pass escape_xml_attr (#1028)

2026-03-20 20:33:09 -07:00