connectai/docs/records/ConnectAI/timeline.md

Project Timeline

2026-05-02

• Discussed adding a sidebar Designer menu for a Project Chronicle Guard system.
• Decided the feature should behave like an independent record layer, similar in spirit to the existing agent/team-style selector.
• Chose an incremental MVP path: first add project record management and Markdown generation, then later expand automatic analysis and richer workflows.
• Completed Stage 1: independent Project Chronicle module, Designer project selector, and explicit planning/development/bug writers.
• Completed Stage 2: added discussion, decision, and retrospective record writers with a scalable record type selector.
• Completed Stage 3: added Chronicle Guard mode to inject active Designer project context into agent prompts.
• Completed Stage 4: added a generated record browser and open action for Chronicle Markdown files.
• Completed Stage 5: added chronicle.config.json as a portable project record configuration file.
• Improved Chronicle Guard after user testing: default guard context, stricter project/record checks, question reasons, MVP-first guidance, candidate record output, and tests.
• Added Second Brain Trace Mode so users can verify whether active Brain notes were searched, referenced, and reflected in answers.
• Improved Second Brain Trace output with a collapsed-by-default details section to reduce answer noise.
• Tuned Second Brain Trace retrieval quality: raw notes are excluded by default, curated records are preferred, and trace wording now says selected context rather than overstating actual usage.
• Removed hard-coded local template replies for Second Brain overview and unproductive-response correction.
• Added progressive answer format guidance: short conclusion first, brief summary second, detailed answer third.
• Added No Evidence, No Project Claim rules and Second Brain source type classification to prevent general notes from being treated as project implementation evidence.
• Added project claim policy enforcement so main answers must treat general-only or mixed evidence as cautious and avoid unsupported technical structure claims.
• Added a deterministic output brake that removes unsupported technical structure claims from final answers when Trace policy is general-only.
• Tuned Second Brain retrieval by query intent so UX/business/approval questions prioritize customer journey, requirement fit, and business value notes over generic architecture notes.
• Tuned answer readability: paragraph-first summaries, fewer bullet-heavy sections, clearer numbered-section spacing, and larger markdown headings in the sidebar.
• Added local project path preflight for code review requests so the agent scans accessible Antigravity project folders before asking for uploads.

2026-05-04

• Auto decision record created: decisions/ADR-0001-volumes-data-project-antigravity-connectai-이-프로젝트를-지금-개발-중에-.md

2026-05-04

• Auto bug record created: bugs/BUG-0001-volumes-data-project-antigravity-connectai-프로젝트-코드-리뷰-해줄-수-있.md

2026-05-04

• Auto decision record created: decisions/ADR-0002-지금-너의-제2뇌-지식을-이용해서-아래-프로젝트-평가하고-앞으로-어느부분을-더-집중해서-개선을-하면-좋을지-.md