Summary
When an agent performs walk, look, and interact in quick succession, the position state can become inconsistent. In my test, the agent was moving toward the pond normally, but after chaining actions, the position unexpectedly jumped back to a street tile.
This appears to be a state synchronization / concurrency issue rather than a simple navigation mistake.
Observed Behavior
- Single-step movement in one direction appears relatively stable
- When
walk + look + interact are chained closely together, the MCP/server-side position state can become inconsistent
- The final reported position may jump unexpectedly to an earlier or unrelated tile
- This makes exploration and interaction unreliable
Example From Test
I was approaching the pond and had already reached a tile near the target area.
In the log, movement toward the pond was initially stable:
- reached
(5,14)
- then reached
(7,14), facing target (7,15)
After executing another walk, then look, then interact, the state became inconsistent and the agent ended up jumping back near (5,6) instead of remaining near the pond.
Expected Behavior
- Action execution should preserve a consistent authoritative position state
look and interact should not overwrite or roll back the latest committed movement state
- Chained actions should either:
- execute strictly sequentially, or
- be rejected/queued until the previous action is fully committed
Suspected Cause
Possible race condition or state desynchronization between:
- MCP tool calls (
walk, look, interact)
- server-side state updates
- frontend rendering / local state refresh
It may also be caused by:
- lack of per-agent action queue / mutex
- non-atomic position updates
- stale state being read by a later action and written back over a newer state
Reproduction Idea
- Spawn/login an agent
- Move step by step toward a target location
- Once near an interactable tile, issue
walk, then immediately look, then interact
- Repeat a few times
- Observe whether the agent position jumps, rolls back, or becomes inconsistent with the visible map state
Impact
This affects the core gameplay loop:
- exploration
- environmental interaction
- future combat / item systems
- any feature depending on reliable world state
This may become more severe as multi-agent concurrency increases.
Suggested Fix Direction
- enforce per-agent action queue / mutex
- make movement state updates atomic
- ensure
look / interact are read-only with respect to position unless explicitly intended
- add server-side authoritative position logging for each action
- include action IDs / timestamps to prevent stale writes

Summary
When an agent performs
walk,look, andinteractin quick succession, the position state can become inconsistent. In my test, the agent was moving toward the pond normally, but after chaining actions, the position unexpectedly jumped back to a street tile.This appears to be a state synchronization / concurrency issue rather than a simple navigation mistake.
Observed Behavior
walk + look + interactare chained closely together, the MCP/server-side position state can become inconsistentExample From Test
I was approaching the pond and had already reached a tile near the target area.
In the log, movement toward the pond was initially stable:
(5,14)(7,14), facing target(7,15)After executing another
walk, thenlook, theninteract, the state became inconsistent and the agent ended up jumping back near(5,6)instead of remaining near the pond.Expected Behavior
lookandinteractshould not overwrite or roll back the latest committed movement stateSuspected Cause
Possible race condition or state desynchronization between:
walk,look,interact)It may also be caused by:
Reproduction Idea
walk, then immediatelylook, theninteractImpact
This affects the core gameplay loop:
This may become more severe as multi-agent concurrency increases.
Suggested Fix Direction
look/interactare read-only with respect to position unless explicitly intended