Bump version to 2.35.0: Knowledge Resilience & Standardization Milestone.

docs/records/ConnectAI/README.md

@@ -0,0 +1,18 @@
+# ConnectAI Project Chronicle Records
+
+This folder stores planning, decision, development, bug, and retrospective records for ConnectAI.
+
+## Project
+- Name: ConnectAI
+- Root: `/Volumes/Data/project/Antigravity/ConnectAI`
+- Record root: `docs/records/ConnectAI`
+
+## Structure
+- `project-profile.md`: project identity and guardrails
+- `timeline.md`: high-level chronological history
+- `planning/`: feature planning records
+- `discussions/`: AI-human discussion summaries
+- `decisions/`: decision records
+- `development/`: implementation logs
+- `bugs/`: bug and fix records
+- `retrospectives/`: post-work reviews

docs/records/ConnectAI/decisions/ADR-0001-project-chronicle-independent-module.md

@@ -0,0 +1,27 @@
+# ADR-0001: Implement Project Chronicle Guard As An Independent Module
+
+## Status
+Accepted
+
+## Context
+The requested feature records project planning, questions, decisions, development logs, bugs, and retrospectives. Existing chat and agent systems already manage model interaction and agent skills.
+
+## Decision
+Implement Project Chronicle Guard as a separate module under `src/features/projectChronicle`.
+
+## Reason
+- It reduces the chance of regressions in chat and agent execution.
+- It keeps the MVP focused on local Markdown generation.
+- It can later receive events from chat or agents without owning those flows.
+- It makes project-specific record storage easier to test and evolve.
+
+## Alternatives
+- Integrate into the existing Second Brain flow.
+- Extend Agent Skill files to double as project records.
+- Add a standalone Project Chronicle module.
+
+## Selected Alternative
+Add a standalone Project Chronicle module.
+
+## Consequences
+The first stage needs explicit sidebar actions to create and write records. Automatic extraction can be layered on later.

docs/records/ConnectAI/development/2026-05-02_project-chronicle-guard_feedback-response.md

@@ -0,0 +1,39 @@
+# Development Log: Project Chronicle Guard Feedback Response
+
+## Purpose
+Improve Chronicle Guard behavior after testing showed the assistant still answered like a general idea proposer instead of a project planning and record guard.
+
+## Feedback Summary
+The tested response understood the broad idea, but missed key guard behaviors:
+- Project target check
+- Record path check
+- Question intent and question reasons
+- Pending decision candidates
+- Low-dependency MVP first
+- Candidate records at the end
+- Plain engineering tone
+
+## Implementation Summary
+- Made Chronicle Guard context apply by default unless explicitly disabled from the webview payload.
+- Strengthened the Guard response contract for new ideas and feature requests.
+- Added required response order: summary, intent, project check, record path check, blocking questions, question reasons, direction review, MVP, later expansion, candidate records.
+- Added decision policy so unconfirmed decisions stay pending.
+- Added tone rules against inflated consulting language and premature Vector DB / relational DB / knowledge graph suggestions.
+- Extracted Guard prompt generation into `buildProjectChronicleGuardContext`.
+- Added tests that lock the most important Guard rules.
+- Added base system prompt guidance to prefer practical MVP-first answers for product and architecture discussions.
+
+## Changed Files
+- `src/features/projectChronicle/guardPrompt.ts`
+- `src/features/projectChronicle/index.ts`
+- `src/sidebarProvider.ts`
+- `src/utils.ts`
+- `tests/projectChronicleGuardPrompt.test.ts`
+
+## Verification
+- `./node_modules/.bin/tsc --noEmit`
+- `npm run compile`
+- `./node_modules/.bin/jest --runInBand`
+
+## Result
+Chronicle Guard should now behave less like a general ideation assistant and more like a project planning, decision, and record guard.

docs/records/ConnectAI/development/2026-05-02_project-chronicle-guard_stage-1_implementation.md

@@ -0,0 +1,48 @@
+# Development Log: Project Chronicle Guard Stage 1
+
+## Purpose
+Add the first stable stage of the Designer menu and Project Chronicle Guard without coupling it tightly to chat execution.
+
+## Implementation Summary
+- Added an independent `src/features/projectChronicle` module.
+- Added typed project, planning, discussion, decision, development, bug, and retrospective records.
+- Added a Markdown writer with folder creation and filename collision protection.
+- Added templates for project seed files and record documents.
+- Added a Designer row in the sidebar with project selection and explicit record actions.
+- Added VS Code-side handlers for creating/selecting record projects and writing planning, development, and bug records.
+
+## Architecture
+
+```text
+Sidebar Designer UI
+  -> Webview postMessage
+  -> SidebarChatProvider handlers
+  -> ProjectChronicleManager
+  -> MarkdownFileWriter
+  -> docs/records/{Project}/...
+```
+
+## Changed Files
+- `src/features/projectChronicle/types.ts`
+- `src/features/projectChronicle/markdownFileWriter.ts`
+- `src/features/projectChronicle/templates.ts`
+- `src/features/projectChronicle/index.ts`
+- `src/sidebarProvider.ts`
+- `docs/records/ConnectAI/...`
+
+## Dependency Notes
+The implementation uses only TypeScript, Node `fs`/`path`, and VS Code extension APIs already available in the project.
+
+## Verification
+- `npm run compile`
+- `./node_modules/.bin/jest --runInBand`
+
+## Known Limits
+- The records are generated through explicit sidebar actions.
+- Full automatic conversation analysis is not implemented in this stage.
+- Retrospective and ADR writing are available in the module, but the sidebar only exposes Plan, Dev, and Bug actions in this first pass.
+
+## Next Development Notes
+- Add a richer Designer panel for ADR, discussion, and retrospective creation.
+- Capture AI question intent more directly during the conversation flow.
+- Add tests for the Project Chronicle manager.

docs/records/ConnectAI/development/2026-05-02_project-chronicle-guard_stage-2_implementation.md

@@ -0,0 +1,47 @@
+# Development Log: Project Chronicle Guard Stage 2
+
+## Purpose
+Expand the Designer menu from basic Plan/Dev/Bug writing into a fuller MVP record writer.
+
+## Implementation Summary
+- Reworked the Designer sidebar controls into a project selector plus a record type selector.
+- Added explicit write flows for discussion, decision, and retrospective records.
+- Preserved the existing planning, development, and bug writers.
+- Added question intent capture in the discussion writer through optional prompts.
+- Added ADR numbering for decision records and timeline updates for every record type.
+- Expanded tests to verify all major record categories are written to their expected folders.
+
+## Design Adjustment
+The first pass exposed separate buttons for Plan, Dev, and Bug. Stage 2 changes this to a more scalable pattern:
+
+```text
+Designer Project Selector
+Record Type Selector
+Write / Open / Add actions
+```
+
+This keeps the sidebar usable as more record types are added.
+
+## Changed Files
+- `src/sidebarProvider.ts`
+- `tests/projectChronicle.test.ts`
+- `docs/records/ConnectAI/development/2026-05-02_project-chronicle-guard_stage-2_implementation.md`
+
+## Verification
+- `./node_modules/.bin/tsc --noEmit`
+- `npm run compile`
+- `./node_modules/.bin/jest --runInBand`
+
+## Result
+The Designer menu can now create the MVP record types:
+- Planning
+- Discussion
+- Decision
+- Development
+- Bug
+- Retrospective
+
+## Next Development Notes
+- Add a dedicated Designer panel for editing richer record content before writing.
+- Add automatic conversation event capture so records can be generated with less manual input.
+- Add settings for default record detail level and automatic timeline behavior.

docs/records/ConnectAI/development/2026-05-02_project-chronicle-guard_stage-3-to-5_implementation.md

@@ -0,0 +1,42 @@
+# Development Log: Project Chronicle Guard Stages 3 to 5
+
+## Purpose
+Complete the remaining MVP support around Designer mode, record browsing, and project configuration persistence.
+
+## Stage 3: Chronicle Guard Mode
+- Added a `Guard` toggle in the sidebar header.
+- When enabled, active Designer project context is injected into the agent system context.
+- The guard context asks the assistant to summarize requests, infer intent, explain blocking questions, identify decisions, and name records that should be written.
+- The mode is restored through webview state.
+
+## Stage 4: Record Browser
+- Added a record list selector for generated Chronicle Markdown files.
+- Added refresh and open actions for selected records.
+- Added record listing to `ProjectChronicleManager`.
+- Added path validation before opening selected Markdown records.
+
+## Stage 5: Project Config File
+- Added `chronicle.config.json` generation under each project record root.
+- The config file stores project id, project name, root, record root, description, purpose, detail level, and timestamps.
+- This gives the record folder its own portable project metadata, independent of VS Code global state.
+
+## Changed Files
+- `src/agent.ts`
+- `src/sidebarProvider.ts`
+- `src/features/projectChronicle/index.ts`
+- `src/features/projectChronicle/types.ts`
+- `tests/projectChronicle.test.ts`
+
+## Verification
+- `./node_modules/.bin/tsc --noEmit`
+- `npm run compile`
+- `./node_modules/.bin/jest --runInBand`
+
+## Result
+The staged MVP is now functionally complete:
+- Select or create Designer project
+- Generate project record structure
+- Persist project config
+- Enable Chronicle Guard response mode
+- Write all MVP record types
+- Browse and open generated Markdown records

docs/records/ConnectAI/development/2026-05-02_second-brain-trace-mode_implementation.md

@@ -0,0 +1,35 @@
+# Development Log: Second Brain Trace Mode
+
+## Purpose
+Make Second Brain usage visible and testable in AI answers.
+
+## Implementation Summary
+- Added `src/features/secondBrainTrace.ts`.
+- Added trace scoring over active Second Brain Markdown files.
+- Added user-facing trace Markdown with usage status, referenced documents, unused documents, and grounding metrics.
+- Added debug JSON output when debug mode is enabled.
+- Added Trace and Dbg sidebar buttons.
+- Connected trace context into `AgentExecutor`.
+- Added tests for retrieval, rendering, debug JSON, and no-use cases.
+
+## Changed Files
+- `src/features/secondBrainTrace.ts`
+- `src/agent.ts`
+- `src/sidebarProvider.ts`
+- `tests/secondBrainTrace.test.ts`
+- `docs/records/ConnectAI/planning/2026-05-02_second-brain-trace-mode.md`
+- `docs/records/ConnectAI/development/2026-05-02_second-brain-trace-mode_implementation.md`
+
+## Verification
+- `./node_modules/.bin/tsc --noEmit`
+- `npm run compile`
+- `./node_modules/.bin/jest --runInBand`
+
+## Result
+When Trace mode is on, answers can now include:
+- 2nd Brain usage status
+- Reason for use or non-use
+- Referenced note paths and excerpts
+- Searched but unused notes
+- Retrieval and grounding metrics
+- Optional debug JSON

docs/records/ConnectAI/discussions/2026-05-02_project-chronicle-guard.md

@@ -0,0 +1,27 @@
+# AI-Human Discussion Log
+
+## Topic
+Project Chronicle Guard sidebar Designer menu and Markdown record system.
+
+## User Request Summary
+The user wants a Designer menu in the sidebar and a staged implementation of a project planning, decision, and development record system.
+
+## AI Questions
+
+### Question
+No blocking question was asked.
+
+### Reason
+The current workspace, project root, and a reasonable record location were available from local context.
+
+### Impact On Decision
+The first implementation can proceed with `ConnectAI` as the active project and `docs/records/ConnectAI` as the planning record location.
+
+## Main Discussion
+The feature should not replace code generation or existing agent execution. It should sit beside those features as a recording and decision support layer.
+
+## Decisions
+- Use an independent `src/features/projectChronicle` module.
+- Add a sidebar Designer control similar to existing Brain and Agent controls.
+- Keep the MVP file-based and Markdown-only.
+- Do not implement full automatic transcript capture in the first stage.

docs/records/ConnectAI/planning/2026-05-02_project-chronicle-guard.md

@@ -0,0 +1,58 @@
+# Feature Plan: Project Chronicle Guard
+
+## 1. Feature Name
+Project Chronicle Guard
+
+## 2. Reason
+The user wants AI-human planning, questions, decisions, implementation details, bugs, and retrospectives to remain as project-specific Markdown knowledge instead of disappearing into chat history.
+
+## 3. Original User Request
+Add a Designer menu to the sidebar, similar in spirit to Team, and implement a staged Project Chronicle Guard system that records planning, decisions, development logs, bug fixes, and retrospectives.
+
+## 4. Interpreted Intent
+The user does not only want another chat prompt preset. They want a durable project knowledge layer that captures why decisions were made and keeps records separated by project.
+
+## 5. Problems To Solve
+- Later readers forget why a direction was chosen.
+- AI questions lose their intent and decision impact.
+- Planning and implementation history are mixed or absent.
+- Multiple projects can contaminate each other's records.
+
+## 6. MVP Scope
+- Add an independent `projectChronicle` module.
+- Add project profile types and Markdown writer utilities.
+- Add sidebar Designer controls for record project selection and basic project management.
+- Generate the project folder structure and seed Markdown files.
+- Save a planning document, discussion summary, decision record, development log, bug log, and timeline entry through explicit user actions.
+
+## 7. Out Of Scope
+- Full automatic transcript recording
+- External database storage
+- Git auto-commit
+- Real-time file watching
+- Search UI
+- Tight integration with agent execution internals
+
+## 8. Development Direction
+Start with a low-risk independent module and connect the sidebar through message events. The chat agent can remain unaware of the record module in the first stage.
+
+## 9. Existing Feature Relationship
+The current sidebar already has Brain and Agent controls. The Designer menu should follow that UI pattern but manage project record profiles instead of agent skill files.
+
+## 10. Dependency Strategy
+Use TypeScript, Node `fs`, and Markdown files only. Store project profile metadata in VS Code global state and avoid modifying core chat execution.
+
+## 11. Expected Value
+- Project-specific planning and decision history becomes reusable.
+- The user can intentionally create records before or after development work.
+- Future automation can build on a stable local file structure.
+
+## 12. Success Criteria
+- A Designer selector appears in the sidebar.
+- A new record project can be created.
+- Record folders and seed files are generated safely.
+- Markdown documents can be generated without needing external services.
+- Existing chat, brain, and agent flows continue to compile.
+
+## 13. Developer Instruction
+Implement the first stage only: independent module, basic Designer menu, project creation/selection, folder seeding, and explicit sample record generation actions. Keep automatic conversation analysis for a later stage.

docs/records/ConnectAI/planning/2026-05-02_second-brain-trace-mode.md

@@ -0,0 +1,36 @@
+# Feature Plan: Second Brain Trace Mode
+
+## 1. Feature Name
+Second Brain Trace Mode
+
+## 2. Reason
+The user wants to verify whether AI answers actually use Second Brain notes, which documents were searched, and how retrieved knowledge influenced the answer.
+
+## 3. Original User Request
+Add a way to see if the AI searched Second Brain, which notes it referenced, whether each note was used in the final answer, and why unused notes were excluded.
+
+## 4. Interpreted User Intent
+The user does not want to rely on vague claims that the AI used memory. They want visible grounding evidence and a developer debug trace.
+
+## 5. Scope
+- Add a trace mode toggle in the sidebar.
+- Add a debug JSON toggle.
+- Retrieve relevant Markdown notes from the active Second Brain.
+- Inject selected notes into the answer context.
+- Append a user-visible 2nd Brain usage section to answers.
+- Show searched-but-unused notes and basic grounding metrics.
+
+## 6. Out Of Scope
+- Vector database integration
+- Full semantic embedding search
+- Perfect factual attribution at sentence level
+- External observability tools
+
+## 7. Development Direction
+Use a low-dependency local Markdown search first. Keep vector search and richer grounding analysis as later expansion.
+
+## 8. Success Criteria
+- Users can see whether Second Brain was used.
+- Users can see referenced Markdown paths.
+- Debug mode exposes retrieval JSON.
+- General questions can explicitly show that Second Brain was not used.

docs/records/ConnectAI/project-profile.md

@@ -0,0 +1,30 @@
+# Project Profile
+
+## Project Name
+ConnectAI
+
+## Purpose
+Provide a local AI assistant experience inside VS Code with chat, local knowledge, agent skills, and project-oriented development support.
+
+## Core Users
+- Project developer
+- Local AI workflow user
+- Developer who wants project knowledge to persist as Markdown
+
+## Core Direction
+- Keep new support features independent from the main chat and agent execution paths.
+- Prefer Markdown and local filesystem storage for project knowledge.
+- Avoid external databases for the MVP.
+- Keep user decisions, question intent, implementation notes, and bug fixes traceable.
+
+## Avoid
+- Strong coupling between record generation and agent internals
+- Automatic file writes without clear user action or selected record project
+- Mixing records from different projects
+- Complex long-term memory systems in the MVP
+
+## Priority
+1. Stability
+2. Clear records
+3. Low dependency
+4. Incremental delivery

docs/records/ConnectAI/timeline.md

@@ -0,0 +1,13 @@
+# 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.