detect-patternslisted

# Detect Patterns Find recurring **sequences**, not preferences. Read schemas in [../soulcatcher/reference.md](../soulcatcher/reference.md). **Worked example:** [learned-skills/examples/pipeline-output/pattern-report.md](../../learned-skills/examples/pipeline-output/pattern-report.md) ## Input - Set of BehavioralTrace artifacts (minimum **3 relevant sessions**) - Optional: problem_class filter from user ## Process 1. Group traces by `problem_class` 2. For each group, extract ordered event sequences (generalize event descriptions to step labels) 3. Find subsequences that repeat across sessions with stable order 4. Score using confidence rules in reference.md 5. Collect counterexamples (sessions where core steps were skipped) 6. Rank patterns by confidence ## Step Label Generalization Convert literal events to reusable labels: | Literal event | Step label | |---------------|------------| | "Listed two candidate approaches" | generate_candidates | | "Wrote pros and cons" | weigh_pros_cons | | "Searched for failure cases" | search_counterexamples | | "Identified strongest downside" | surface_strongest_downside | | "Committed after risks explicit" | decide_after_risks_explicit | ## Anti-Patterns (do not report) - Single-session habits - Tool or language preferences ("uses Python", "uses grep") - Formatting or style quirks - Steps that appear in different orders across sessions (unless marked optional) ## Output Format ```markdown # PatternReport: {pattern_id} ```yam