Release v0.2.0 · deghosal-2026/agent-self-edit

AgentSelfEdit v0.2.0

Release date: 2026-09-02

Staged analyzer pipeline — 4-stage (summarize → select → synthesize → score) replaces the monolithic analyzer
Model role separation — executor, analyzer, and judge roles with per-role provider configuration
Multi-domain support — classification, extraction, generation, and mixed-domain suites
Runtime scorer selection — ExactMatch, StructuredExtractionScorer, LLMJudgeScorer auto-selected per task type
Rejection context — staged analyzer receives structured rejection feedback to avoid repeated failed edit families
40-task promotion corpus — replaces the fragile 5-task set for statistical power
Hermetic CI suite — zero LLM call tests safe for CI
Row-identity trace ack — immutable row-ID based processing with in-flight reservation

Gate edit-distance measured against full candidate prompt, not fragment
Gate drift measured against original prompt baseline
A/B alpha semantics: p < (1 - confidence_level)
Candidate prompt materialization uses full prompt
Staged analyzer rejection context threaded through all prompt stages
CLI exit codes deterministic; init writes runnable config; validate checks runnability

Multi-domain Docker tests (classification, extraction, generation, staged analyzer)
Multi-stage Dockerfile with reduced image size

Gate FP rate: 0% across all runs
Multi-domain suites: 4/4 executed
Adversarial edits: 5/5 caught, 0 false negatives
Strongest analyzer: Mistral Small 24B (OpenRouter) — directional gains but no promotable edit
Conclusion: framework is correct, observable, and safe. Analyzer quality is the bottleneck.

Coverage at 81% (target 92%)
No verified prompt self-improvement yet — analyzer search quality is the bottleneck

pip install agent-self-edit==0.2.0