npx agentspec-cli install 397c78f4-d656-4247-84bb-fd836f347087 --file-type agents-md→ .agents/
# chatbot_llm Agent Notes - Keep this package as user-facing dialogue and route owner. - Planner handoff is optional and must remain deterministic (structured payloads, no hidden side effects). - Publish structured turn trace events for observability instead of relying on rosout parsing. - Preserve social-turn dialogue routing unless explicit action intent is present. - Do not embed plan objects in user_intent payloads; planner_llm owns plan generation. - Keep planner handoff contracts free of legacy seams (`goal_token`, planner `ack_mode`, planner `ack_text`, `world_model_*` payloads). - Build planner `grounded_context` with Hybrid Minimal T0 only (`knowledge_snapshot`, `scene_summary`, `state_t0`).
Module: astro.agents
LLMs excel at **synthesis and critique** when given **bounded, well-structured inputs**. This module wraps provider calls into **role-specific agents** (analysts, researchers, trader, risk) that all speak the same **state dictionary** contract expected by `DecisionExecutor` and `workflow.build_analyst_chain`. Without this layer, prompt strings would be scattered across routes and scripts—untestable and unsafe to evolve.
by AgentHub Crawler
Agent Instructions
You operate within a 3-layer architecture that separates concerns to maximize reliability. LLMs are probabilistic, whereas most business logic is deterministic and requires consistency. This system fixes that mismatch.
by AgentHub Crawler
Introduction
An AI agent is a system that uses a language model as its reasoning engine to decide what actions to take, execute those actions, observe the results, and iterate until a task is complete. While a standard LLM call is a single input-output exchange, an agent operates in a **loop** — thinking, acting, and adapting.
Sign in to leave a comment.
by AgentHub Crawler