Fetch the current world observation for this tick.
You are a situated agent in a simulated world. This skill fetches the latest sensory observation for the current tick—what you can see, hear, and perceive around you.
Activate this skill when you need fresh perception for the current tick. Other skills may read observation.txt / observation_ctx.json if those files exist—there is no hard activation order.
codegen with instruction: "<observe>" and ctx: {"id": <your_agent_id>} (replace <your_agent_id> with your actual agent ID from the Agent Identity section).stdout contains the observation text (natural language description of what you perceive).ctx contains structured environment data (positions, nearby agents, objects, time, weather, etc.).status: "in_progress": the environment is still processing. Call done and resume next tick.workspace_write("observation.txt", <stdout text>)
ctx contains useful structured data, also write it:workspace_write("observation_ctx.json", <ctx as JSON string>)
After a successful observe, if you want a durable trace, append one line to memory.jsonl with type: "observation" (or event) and a short factual summary. Skip if this tick’s perception duplicates the latest entry.
The observation text typically includes:
After performing any action via codegen, always re-observe to get the updated environment state:
codegencodegen with "<observe>" againobservation.txt and observation_ctx.jsonThis ensures the agent's internal state matches the environment state.
The observation_ctx.json typically contains:
{
"agent_id": 1,
"position": {"x": 100, "y": 200},
"location": "park_entrance",
"nearby_agents": [
{"id": 2, "name": "Alice", "distance": 5.2}
],
"nearby_objects": [
{"id": "bench_01", "type": "bench", "distance": 2.0}
],
"time": {"hour": 10, "minute": 30},
"weather": "sunny",
"available_actions": ["move", "interact", "wait"]
}
observation.txt every time you observe so the workspace stays self-consistent.ctx JSON may be large; you don't need to memorize it all—write it to observation_ctx.json and let readers pull fields as needed.codegen returns an error, write a short note into observation.txt so later reads see what failed.This skill only produces observation artifacts (observation.txt, optional observation_ctx.json).
Higher-level “agent state snapshot / replay logging” is considered system functionality rather than a human-like capability skill, and should be handled by the runtime/framework if needed.