soryu - soryu-co/soryu mirror

	Commit message (Collapse)	Author	Age	Files	Lines
*	feat: Add learning injection module for enhanced prompts	soryu	2026-01-24	1	-1/+1
\| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \|	Implements Ralph-inspired learning injection that prepends context recovery and previous learnings to Claude prompts. This enables cross-task learning and context preservation. Features: - LearningInjector struct with configurable options (max_entries, include_context_recovery) - inject_learnings() function to enhance base prompts with context and learnings - extract_learnings_from_output() to parse Claude output for learning patterns - Supports markers: LEARNING:, PATTERN:, GOTCHA:, TIP: - Deduplicates learnings by description - Also fixes TaskState::Pending -> Initializing in context_recovery tests Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
*	feat: Add context recovery module for task resumption	soryu	2026-01-24	1	-0/+494
	Implements a standardized context recovery pattern that helps rebuild context when tasks resume or restart, ensuring Claude can quickly orient itself and reducing confusion and repeated work. The ContextRecoveryInfo struct captures: - Current git branch name - Git status summary (uncommitted changes count) - Last checkpoint info (timestamp, message, SHA) - Recent progress log entries from progress.log - Current contract phase Includes to_markdown() method for generating prompt-injection-ready context blocks. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>