Configuration

12345.mikro/
├── mikro.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

12mikro migrate           # dry run: lists what it would change
mikro migrate --apply   # renames .rlmx/ to .mikro/ and rlmx.yaml to mikro.yaml

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869# 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)

# The system prompt, output criteria and custom tools live in SYSTEM.md,
# CRITERIA.md and TOOLS.md beside this file. mikro.yaml has no system:,
# criteria: or tools: keys.

# 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 the provider's cache retention
  ttl: 3600               # seconds; shown by `mikro cache`, not sent to the provider
  expire-time: ""         # ISO 8601; accepted, not sent to the provider
  session-prefix: ""     # Prepended to content hash for cache key

# pgserve storage for contexts larger than the provider limit
storage:
  enabled: auto           # auto | always | never
  mode: persistent        # persistent | memory
  data-dir: ~/.mikro/data # also where `mikro stats` reads from
  port: 0                 # 0 picks a free port
  chunk-size: null        # null derives it from the model context window
  chunk-utilization: 0.6  # fraction of the context window per chunk
  chars-per-token: 4      # ratio used for token estimates

# Gemini 3 features. thinking-level applies to any provider whose model
# supports a reasoning level; the other keys are 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

1234567891011# Set an API key
mikro config set GEMINI_API_KEY your-key

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

# View all settings
mikro config list

# Show settings file path
mikro config path

123- Be concise and direct
- Cite specific file paths when referencing code
- Use code blocks for code snippets

12345678910111213141516## 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]
` ``

## summarize_chunk

` ``python
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}")
` ``