.rlmx/
├── rlmx.yaml       # Main configuration (model, budget, context, storage)
├── SYSTEM.md        # System prompt used by the RLM loop
├── CRITERIA.md      # Output criteria for quality checks
└── TOOLS.md         # Custom Python tools exposed to the RLM

# Model configuration
model:
  provider: google                            # pi/ai provider: google, anthropic, openai, etc.
  model: gemini-3.1-flash-lite-preview        # Model ID
  sub-call-model: gemini-3.1-flash-lite-preview  # Model for llm_query() sub-calls (optional)

# System prompt — the RLM paper prompt is used by default.
# Override only if you know what you're doing.
# system: |
#   Custom system prompt here...

# Custom Python tools injected into the REPL namespace
tools:
  search_docs: |
    def search_docs(keyword):
        """Search context for files matching keyword."""
        matches = [item for item in context if keyword.lower() in item['content'].lower()]
        return [m['path'] for m in matches]

  summarize_chunk: |
    def summarize_chunk(text, max_words=100):
        """Summarize a chunk using an LLM sub-call."""
        return llm_query(f"Summarize in {max_words} words:\n{text}")

# Output criteria appended to the system prompt
criteria: |
  - Be concise and direct
  - Cite specific file paths when referencing code
  - Use code blocks for code snippets

# Context loading configuration
context:
  extensions:
    - .md
    - .ts
    - .js
  exclude:
    - node_modules
    - .git
    - dist

# Budget limits (null = unlimited)
budget:
  max-cost: null         # Maximum USD per run
  max-tokens: null       # Maximum total tokens per run
  max-depth: null        # Maximum recursive rlm_query depth

# Tool level: core, standard, or full
tools-level: core

# Cache/CAG configuration
cache:
  enabled: false          # Enable provider-level prompt caching
  retention: long         # short | long — maps to provider TTL strategy
  ttl: 3600              # seconds (optional, provider-specific)
  expire-time: ""        # ISO 8601 (optional, for Google explicit caching)
  session-prefix: ""     # Prepended to content hash for cache key

# Gemini 3 native features (silently ignored on non-Google providers)
gemini:
  thinking-level: null         # minimal | low | medium | high
  google-search: false         # Enable web_search() battery in REPL
  url-context: false           # Enable fetch_url() battery in REPL
  code-execution: false        # Enable server-side Python execution
  media-resolution:
    images: auto               # low | medium | high | auto
    pdfs: auto
    video: auto

# Structured output (Gemini only — other providers use FINAL() fallback)
output:
  schema:
    type: object
    properties:
      answer:
        type: string
      confidence:
        type: number

# Set an API key
rlmx config set GEMINI_API_KEY your-key

# Set a default provider
rlmx config set model.provider google

# View all settings
rlmx config list

# Show settings file path
rlmx config path

## search_docs

` ``python
def search_docs(keyword):
    """Search context for files matching keyword."""
    matches = [item for item in context if keyword.lower() in item['content'].lower()]
    return [m['path'] for m in matches]
` ``