5 Commits
Author SHA1 Message Date
gitea a1dcf09d67 Fix autopilot drive-all loop — agent was stopping after one task
The orchestrator only drove ONE task per invocation, then stopped with
ORCHESTRATION_COMPLETE. User had to manually re-trigger for each task.

Changes:
- Added drive_all() outer loop that scans EVERY task and drives them all
- Tasks needing user review are flagged; orchestrator continues to next
- Only stops when ALL tasks are terminal or ALL remaining need user input
- Output format now shows session summary (completed, awaiting review, blocked)
- Session-starter references 'orchestrate' as primary command
- Updated continue-from-existing to use drive_all()
2026-06-13 22:11:44 -04:00
gitea 52dcf8e309 Implement all 5 tasks: additive extension model, framework self-enforcement, changelog, project migration, dashboard review 2026-06-13 12:26:27 -04:00
gitea 502f47eb21 Refactor: rename framework files to dot-prefixed lowercase, fix onboarding references, validate VRAM detection
- Rename AGENT.md -> .agent.md, RULES.md -> .rules.md, ONBOARDING.md -> .onboarding.md
- Rename BUG_REPORT.md -> .bug_report.md, ADVERSARIAL_BUG_REPORT.md -> .adversarial_bug_report.md, VERDICT.md -> .verdict.md
- Fix onboarding.md references to use new .onboarding.md path
- Fix stop-hook-pattern.md reference to use .onboarding.md
- Update README.md, config.md, install.sh, update.sh, prompts/*, references/*
- VRAM detection script validated and working
2026-06-12 12:40:15 -04:00
gitea d235c12ab0 Add design phase + 3D visualization + orchestration improvements 2026-05-31 00:29:10 -04:00
gitea 72ae07c310 Initial commit: minimal agent framework 2026-05-30 23:27:09 -04:00