- Cap commit diffs in review/commit prompts at 50KB to prevent
context window overflow on follow-up sessions
- Skip skills catalog (noSkills) in commit/review follow-up sessions
for leaner context
- Wire Pi's SettingsManager into runAgentSession so Pi's built-in
retry (exponential backoff, provider retry) applies to ralpi
sessions — removes ralpi's duplicate manual retry loop
- Remove maxRetries/retryDelayMs from ralpi config; rely on Pi's
retry.* settings (with manual override support)
- Remove retries field from progress.json and incrementRetry() from
ProgressTracker
- Add model failover to follow-up sessions (commit/review cycle
through the model pool on connection errors)
- Namespace reflection files by PRD key under
.ralpi/reflections/<prdKey>/ so task sets don't overwrite each
other
- Skip loop-startup prompts for config fields explicitly set in YAML
- Remove (default) annotations from loop options prompts
- Default commitTimeoutMs/reviewTimeoutMs to 0 (inherit Pi defaults)
- Persist loop-active state for widget re-instantiation after session reload
- Add YAML task file parsing and update support via yaml library
- Auto-update PRD source file checkboxes on task status changes
- Add batchRender callback for real-time parallel widget animation
- Normalize tabs-to-spaces indentation across source files
- Use padStart(2, '0') for ID formatting instead of hardcoded prefix
- Enable parallel execution for single-task DAG batches
- DAG-based task execution with dependency resolution
- Persistent progress tracking in .ralph/progress.json
- Reflection system for cross-task context
- Support for Fio README, checkbox, and YAML formats
- Retry with exponential backoff
- Parallel batch execution
