Discussion: Progressive Reading DSL for Agent Workflow Management
Resolved 💬 3 comments Opened Mar 14, 2026 by tracer-mohist Closed Mar 14, 2026
💡 Likely answer: A maintainer (github-actions[bot], contributor)
responded on this thread — see the highlighted reply below.
Hi Codex team,
I have been exploring different approaches to manage AI agent workflows. I want to share an alternative design for discussion.
The Problem:
- Most workflow engines treat execution as jump to step N
- This assumes the agent has already read and understood all previous steps
- In practice, agents need to read progressively before executing
Our Approach (workflow-as-list):
- Workflows are lists of steps with dependency annotations
- Agent must read current step before advancing (enforced by steps_read tracking)
- Import system with caching for reusable workflow fragments
- State is externalized to files, not embedded in prompts
Key Design Decisions:
- Reader metaphor: workflow-as-list is a reader, not an executor
- Progressive reading: cannot skip unread steps
- Hash-only import naming for security (no path injection)
Repository: https://github.com/tracer-mohist/workflow-as-list
Question for Codex:
- How does Codex handle workflow state management?
- Do you track which steps the agent has processed?
- Curious about the tradeoffs you have made
Happy to discuss further or close if this is not the right venue.
3 Comments
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
Thanks for flagging potential duplicates. I reviewed #13241 and #14333:
My proposal is different: it is about enforcing progressive reading (agent must read current step before advancing) with explicit state tracking (steps_read field). This is a specific DSL design for workflow management.
Happy to discuss the distinction further or close if you feel it overlaps too much.
Moving to discussion since this isn't a bug report or feature request.