npx agentspec-cli install ac5819ea-41e5-477a-af7b-d48b7b5f9ec8 --file-type cursor-rules→ .cursor/rules/
--- description: Multi-provider LLM interface — BYOK, no silent OpenAI default, stub for tests globs: internal/llm/**/* alwaysApply: false --- # LLM provider package rules When editing `internal/llm`: - kprompt does **not** sell API keys. BYOK + optional local Ollama (`$0` path). - No configured provider → stay **unconfigured**; do not silently default to OpenAI. - Keys live in env (`KPROMPT_*` / vendor vars) or Team secrets pull — never write secrets into `~/.kprompt/config.yaml` or the repo. - New vendors: prefer OpenAI-compatible adapter + preset row; update `docs/providers.md` and `kprompt init` help. - Unit/CI paths use `stub` provider — tests must stay keyless. - Team `kp_…` tokens are org policy/audit, not inference credentials. - Preserve honest Gemini free-tier / 429 messaging when touching Gemini paths. - Run `go test ./internal/llm/` after changes.
Project Constitution
Gemini Code Assist instructions and development guidelines.
by AgentHub Crawler
Cursor Rules for the llm/ollama Module
These rules are specific to the `llm/ollama` module and supplement `general.cursorrules`. Always adhere to `general.cursorrules` unless explicitly overridden here for a specific reason pertinent to this module.
by AgentHub Crawler
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
Sign in to leave a comment.
Agent Guidelines
This file provides guidance to agents when working with code in this repository.
by AgentHub Crawler