Files
fidelity-ai-workspace/AGENTS.md
david.delagneau 374991a568 Refactor workspace structure and documentation
- Deleted obsolete files: obsidian-vault.md, onboarding.md, workspace-model.md
- Updated opencode.json to remove references to deleted files.
- Revised profile.md to clarify the status of legacy paths and communication evidence.
- Adjusted prompts to reflect new file paths and improve clarity.
- Enhanced daily logs with focus, work-items, and blockers properties.
- Updated work-item notes to include systems, workstreams, people, and related properties.
- Improved context maintenance guidelines to ensure accurate and durable project knowledge.
- Refined base filters to exclude template files and ensure only relevant notes are displayed.
- Updated daily templates to ensure proper formatting and consistency.
- Modified workflows to align with the new vault structure and improve context synchronization.
2026-04-16 16:28:30 -06:00

5.3 KiB

Fidelity AI Workspace Rules

This repository is a companion workspace for Fidelity iOS work, not the product codebase.

OpenCode should treat this project as a persistent context layer used to:

  • keep current project state accurate
  • capture durable information from daily work
  • draft standups and Mattermost messages
  • improve communication for the current manager or stakeholder in natural professional English

Always-Loaded Context

The detailed operating rules live in:

  • vault/00-start/start-here.md
  • vault/00-start/workspace-architecture.md
  • vault/01-current/current-work.md
  • vault/01-current/work-items.md
  • vault/03-context/project.md
  • vault/03-context/ios/index.md
  • vault/03-context/ios/current-practices.md
  • vault/03-context/ios/project-swift-guidance.md
  • vault/03-context/systems/index.md
  • vault/03-context/workstreams/index.md
  • vault/03-context/process/communication.md
  • vault/03-context/process/ai-to-ai-prompting.md
  • vault/03-context/process/workspace-model.md
  • vault/03-context/process/memory-promotion-rules.md
  • vault/04-people/manager.md
  • vault/04-people/index.md
  • vault/02-work-items/index.md

These are also loaded through opencode.json.

Required Behavior

  • Assume the workspace may contain stale context until checked.
  • Treat vault/ as the canonical clean memory for humans and AI. Treat ai/inbox/ as raw evidence only.
  • Keep Obsidian Bases clean: templates in vault/09-templates/ must not be treated as real notes, and role mapping files such as vault/04-people/manager.md must not be typed as people.
  • Maintain useful vault properties when editing canonical notes, especially work-item relationships (systems, workstreams, people, related) and daily note fields (focus, work-items, blockers).
  • Before answering questions that depend on current work state, inspect vault/01-current/current-work.md and the latest relevant daily note under vault/06-daily/.
  • If ai/inbox/mattermost-latest.md exists, inspect it for fresher communication context before answering standup, status, or manager-message prompts.
  • If the user asks for the latest/last/recent Mattermost message, the latest message from Jeff/current manager, or what someone just said, synchronize Mattermost first instead of relying on existing inbox context.
  • If automatic refresh is uncertain, use the explicit latest-message flow: run the Mattermost sync command, then answer from the refreshed inbox only.
  • For any meaningful prompt, decide whether the interaction introduces or corrects project memory.
  • If a sync command, extraction script, or inbox refresh fails, do not update logs, state, or context files from that failed attempt.
  • Treat sync failures as operational errors, not project context.
  • mattermost-sync should automatically promote high-confidence project facts without asking what to promote.
  • Prefer vault/06-daily/ as the default destination for new Mattermost-derived facts.
  • Promote to vault/01-current/current-work.md only when the fact materially changes active work over the next few days.
  • Keep explicit Jira IDs and approved titles visible in vault/02-work-items/ and summarize active items in vault/01-current/work-items.md when they are useful for future standups or manager updates.
  • Promote to vault/03-context/project.md only when the fact changes durable project understanding.
  • When a repeatedly mentioned person becomes relevant to project flow, create or update a file under vault/04-people/.
  • Keep role-to-person mapping explicit in vault/04-people/manager.md and the roster in vault/04-people/index.md.
  • Never promote tooling chatter, sync status, or generic conversation noise.
  • Direct user prompts are also memory sources. Do not limit memory updates to explicit sync commands.
  • If a new prompt corrects prior understanding, update the canonical file directly instead of keeping both versions alive.
  • Do not ask what should be saved when the correct destination is already clear.
  • If the user provides durable new facts, update the appropriate context files instead of leaving the new information only in chat history.
  • If a previous context file is now stale or inaccurate, update that file directly.
  • Prefer correcting canonical context over appending contradictory notes.
  • Keep changes concise and auditable.
  • When the topic is architectural or historical, prefer updating the relevant file under vault/03-context/systems/, vault/03-context/workstreams/, or vault/03-context/process/ instead of overloading vault/03-context/project.md.
  • When the user asks Swift, SwiftUI, iOS architecture, testing, or debugging questions, use vault/03-context/ios/ and the local OpenCode iOS skills before answering.
  • When the user asks for a prompt for another AI, GitHub Copilot, or the Fidelity development machine, use vault/03-context/process/ai-to-ai-prompting.md and generate a self-contained prompt.
  • If a Swift/iOS recommendation depends on current Apple APIs, Xcode behavior, or framework migration guidance, verify against official Apple or Swift documentation before making strong claims.

Communication

When drafting or polishing messages:

  • use Context, Observation, Action when appropriate
  • clarify auth state when relevant
  • separate external reports from regressions
  • preserve technical meaning while improving English