DOCUMENTATION

Many teams lose quality over time due to drift between code, config, docs, and operations. Maria OS treats drift as a production incident class, and designs the system to resist it.

# Preview (safe default)
maria /code "requirements..." --plan-only

# Apply (non-interactive)
maria /code "requirements..." --apply --yes --rollback on

# Git-guarded (leave evidence)
maria /code "requirements..." --apply --yes --git-guard on --git-commit on

# Example: limit scope and attempts
maria /auto-dev run --goal "small fix" --target-files "src/..." --max-attempts 2

# Resume latest (summary mode)
maria /workflow/resume --latest --rehydrate summary

# Resume a specific task id (and pass flags to /code)
maria /workflow/resume <taskId> --tests --fix --apply

• /git is inspection-only. It runs a safe read-only subset and can capture outputs into artifacts as evidence. The design blocks dangerous flags and prevents pager hangs.
• /git-culture is the operational layer. It writes culture artifacts (evidence index, push-pending ledger, pseudo PR report) and can run publish flows that stop short of merge. Merge remains human-only.

• Meaning: summarize KPIs, lineage, and steps in a stable sectioned format.
• Performance: analyze EXPLAIN output (when provided) and propose indexes and rewrites with explicit assumptions.
• Refactoring: propose decompositions (views/materialized views) and safe migration strategy.
• Large inputs: chunk → per-chunk analysis → hierarchical merge so reports remain stable.

# Prefer *_API_BASE (OpenAI-compatible base). *_API_URL is legacy compatibility (may be removed).
LMSTUDIO_API_BASE=http://localhost:1234/v1
OLLAMA_API_BASE=http://localhost:11434
VLLM_API_BASE=http://localhost:8000/v1

# Compatibility (deprecated)
# LMSTUDIO_API_URL=http://localhost:1234
# OLLAMA_API_URL=http://localhost:11434
# VLLM_API_URL=http://localhost:8000

# Recommended: force local mode (Enterprise-equivalent)
LOCAL_MODE=1

# Default provider/model (optional)
MARIA_PROVIDER=lmstudio   # or: ollama / vllm
MARIA_MODEL=gpt-oss-20b   # example (LM Studio)

# 1) Start (skip if already running)
ollama serve

# 2) Pull models (examples)
ollama pull llama3.2:3b
ollama pull mistral:7b
ollama pull mixtral:8x7b
ollama pull deepseek-coder:6.7b
ollama pull phi3.5:3.8b

# 3) Confirm installation
ollama list

# 4) Verify API
curl http://localhost:11434/api/version
curl http://localhost:11434/api/tags

# 1) (GUI) Download a model (e.g., gpt-oss-120b / gpt-oss-20b)
# 2) (GUI) Start Local Server in "OpenAI Compatible" mode (default: http://localhost:1234/v1)

# If you have the CLI (lms)
lms ls
lms server start

# Verify
curl http://localhost:1234/v1/models
curl http://localhost:1234/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer lm-studio" \
  -d '{"model":"gpt-oss-20b","messages":[{"role":"user","content":"ping"}],"stream":false}'

# Example: start an OpenAI-compatible server (follow vLLM's setup guide for dependencies)
python -m vllm.entrypoints.openai.api_server \
  --model mistralai/Mistral-7B-Instruct-v0.2 \
  --host 0.0.0.0 \
  --port 8000

# Verify
curl http://localhost:8000/v1/models
curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"mistralai/Mistral-7B-Instruct-v0.2","messages":[{"role":"user","content":"ping"}],"stream":false}'

# Example: run with LM Studio explicitly
maria /ceo --provider lmstudio --model gpt-oss-20b "Summarize the requirements"

# Example: run with Ollama explicitly
maria /ceo --provider ollama --model llama3.2:3b "Summarize the requirements"