alt Hacker NewsInteresting.
In your Github, the JSON format shown for defining custom workflows is very simple. I wonder if that limits the detail in the state-related instructions and error messages you can send to a model.
For example, in state transitions, does your tool just tell the model something like "you are in 'act' mode and no longer in 'plan' mode, here are your new available tools"? Seems difficult to give it any more informative messages given how simple the workflow definitions are. Likewise when the model attempts to do something that's not supported for tools in the given phase.
The workflow definition is intentionally simple... the enforcement layer handles the mechanics however the model gets more context than just "you're in <xyz> mode now"
Each state has an `instructions` field for phase specific guidance and when an agent's action (tool call) gets rejected the error message lets the model know what went wrong, and what's available to move forward
Tool 'Edit' is not available in the 'planning' phase. Allowed Tools: Read, Grep, Glob To advance, call statewright_transition with READY -> implementing
Models (even simple ones) tend to reason through these error messages, adjusting their approaches as opposed to retrying the blocked call. Additionally, on transitions the model is required to include a rationale explaining why it's transitioning (`data.rationale`) which creates an audit trail of the agent's reasoning at each phase boundary. That ends up being one of the most useful parts of the run history viewable on statewright.ai