david.delagneau/fidelity-ai-workspace
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: refactor work item file retrieval to use Python script for improved error handling and readability

Browse Source
This commit is contained in:
David Delagneau
2026-05-04 09:45:28 -06:00
parent 541c9b43de
commit ff4ed6a759
12 changed files with 195 additions and 143 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
agent-memory/behavior/agent-behavior.md
View File

@@ -15,7 +15,7 @@ Make workspace memory maintenance part of the agent's normal job, not a separate
## Default Agent Behavior (Real-Time Auto-Documentation)
For EVERY meaningful prompt, the agent MUST execute a real-time auto-documentation loop. It is not an optional workflow; it is the core of the agent's job.
For every meaningful prompt, the agent must evaluate whether a memory update is needed in the same turn. Auto-documentation is part of the job, but it must not dominate the critical path of simple user-facing answers.
This applies to:
@@ -27,10 +27,13 @@ This applies to:
- debugging discussions
- corrections to previous understanding
The agent MUST NOT wait for a separate promotion command. The agent MUST proactively use file editing tools to update `project-knowledge/` (including 01-current, 02-work-items, 03-context, 04-people, 06-daily) within the SAME conversational turn if new information is detected or if prior context becomes stale.
The agent must not wait for a separate promotion command. The agent should proactively update `project-knowledge/` (including 01-current, 02-work-items, 03-context, 04-people, 06-daily) within the same conversational turn when new information is clear, durable, and the destination is obvious.
- When editing `project-knowledge/`, write as a human engineer maintaining shared project documentation.
- Keep agent-operating logic out of `project-knowledge/`; store that logic in prompts, commands, skills, agents, or `agent-memory/`.
- Answer-first rule: when the user's main goal is analysis, review, translation, or drafting, answer first unless persistence is required to avoid losing a clear durable fact.
- Do not create a brand-new canonical note during the critical path of the answer unless the user explicitly asked to save the fact or the new note is the smallest correct update.
- Prefer updating an existing canonical note over creating a new file when both are valid.
---