Files
fidelity-ai-workspace/workflows/opencode-entry.md
david.delagneau 8026da5719 Refactor AI workspace for improved context management and communication integration
- Introduced new commands and skills for workspace memory curation, professional communication, and status reporting.
- Updated existing commands to utilize new skills and improve clarity in instructions.
- Created a new workspace context command to load reusable core and active project profile.
- Enhanced Mattermost inbox integration with support for generic environment variables.
- Established a clear separation between project-independent core logic and project-specific profiles.
- Improved documentation across various files to reflect changes in workflow and command usage.
- Added operational memory management rules to ensure accurate context promotion and correction.
- Updated README and workflow documents to guide users in utilizing the new structure effectively.
2026-04-16 08:35:53 -06:00

40 lines
1.9 KiB
Markdown

# OpenCode Entry Workflow
## Goal
Use OpenCode as the daily AI entry point for this workspace without losing project context.
---
## Setup
1. Open this repository as its own VS Code workspace.
2. Run `opencode` from the integrated terminal at the repository root.
3. Use the `fidelity` primary agent for this project profile, or the generic `workspace` agent for reusable profile work.
4. Let project-level config load from `AGENTS.md`, `opencode.json`, `.opencode/commands/`, and `.opencode/plugins/`.
---
## Recommended Daily Sequence
1. Run `/workspace-context` at the start of the day, or `/fidelity-context` when you want the Fidelity alias.
2. If live communication sync is configured, let the inbox refresh automatically or run `/communication-sync`.
3. When new work happens on the main development machine, run `/sync-context ...` or `/log-note ...`.
4. When you need a supervisor update, run `/manager-update ...`.
5. When you need polished English for Mattermost, run `/translate ...`.
6. When you need a standup, run `/standup`.
---
## Why This Works
- Project instructions load automatically from `opencode.json`.
- Root rules also load automatically from `AGENTS.md`.
- The main context command reads the reusable `core/`, active profile, stable workspace files, and today's log.
- Stable context is split by systems, workstreams, process, people, and decisions so the agent can pull the right layer instead of overloading one project file.
- Live communication context can be refreshed into `ai/inbox/` using the configured connector.
- Direct prompts are also treated as memory opportunities, so the agent can update workspace context during normal conversation.
- Daily updates go back into the workspace, so later prompts inherit better context.
- The local compaction plugin helps preserve the most important workspace context during long sessions.
- This reduces reliance on fragile session memory.