Automated README summary
Automatically summarized from the README on 20 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
RecoverIQ benchmarks recovery strategies for failing Claude coding agents on sandboxed bug-fix tasks, comparing fixed retry, hand-written rules, and Jev-guided decisions on clean successes per dollar.
How it uses Jev
Per decision, jev_adapter.py makes one client.system_one() call: a Choice over currently-feasible actions, a Choice of failure type, and two Noul questions ("retry would help", "task impossible"). RecoverIQ ranks actions by Jev's probabilities, then a retry gate uses Jev's own retry_would_help Noul; recovery_policy.py vetoes invalid, unsafe or unaffordable proposals.
Primitives:choicenoul
Technique worth stealing
Pair a learned decision model with a deterministic policy layer that can veto its proposals on budget and safety grounds.
Try it
python3.11 -m venv .venv; .venv/bin/pip install -r requirements.txt; .venv/bin/python -m pytest; .venv/bin/streamlit run app.py
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.85
- Shows a System One patternunclear0.50
- Describes handling uncertaintynot found in the excerpt0.35
- Reports measured numbersFound in material0.63
- Is a runnable toolunclear0.50
- Top-10 learning shortlist signalunclear0.40
- Is a replica of the modelnot found in the excerpt0.07
- Solves a common problem (0–2)score on a 0–2 scale1.52 / 2
- About JevFound in material0.97
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 20 Oct 2026.