# Example configuration for nisse-dev. Copy to nisse-dev.yaml (or point
# NISSE_CONFIG at your copy) and edit.
#
# - Structure lives here. Secrets do not: write them as ${VARIABLE} references,
#   resolved from the environment (or .env, see .env.example) at startup.
# - Keep this file outside the workspace clone. Startup refuses otherwise,
#   because the agent commits and pushes everything in the clone.
# - Unknown keys are errors, so a misspelt knob fails at startup instead of
#   silently doing nothing.

state_db: ~/nisse-demo-workspace/state.db
workspace: ~/nisse-demo-workspace/project  # the clone
project: demo

llm:                                  # A5: LiteLLM is the only LLM destination
  base_url: http://litellm.example:4000
  token: ${NISSE_LLM_TOKEN}
  # Ceiling on each response. The model's own max_output_tokens in LiteLLM
  # caps it further, which is where to hold a local model to less.
  max_output_tokens: 16384
  # How long one request may take before it is abandoned. A safety net for a
  # hung connection; slow local models can take minutes over a long answer.
  request_timeout_s: 600

roles:                                # A11: role -> LiteLLM model alias
  executor: local-fast          # the local tier; the benchmark picks the model
  planner: claude-opus-5-5      # high-end judgement: plans a weaker executor follows
  delegate: claude-opus-5-5     # takes over what the executor got stuck on
  consultant: claude-haiku-4-5  # one question at a time, no tools: cheap is enough

matrix:                               # A1
  homeserver: https://matrix.example
  user_id: "@nisse-dev:example"
  token: ${NISSE_MATRIX_TOKEN}
  room_id: "!roomid:example"
  operators: ["@you:example"]

gitea:                                # B2
  url: https://gitea.example
  token: ${NISSE_GITEA_TOKEN}
  repo: owner/demo-repo
  operators: [your-gitea-login]
  base_branch: main

# What each knob does, and how to choose a value: docs/Tuning-Guide.md.
# These are the defaults; the section can be left out entirely. The file is
# read at startup, so a change takes effect on the next restart.
tuning:
  executor:
    max_turns: 24            # model calls per milestone before it stops as capped
    failure_limit: 2         # consecutive failed commands before escalating (A12)
  expert:
    consult_budget: 3        # ask_expert calls per milestone (A14)
  delegation:                # hard caps on one delegation (A13)
    max_turns: 30
    max_tokens: 200000
    wall_clock_s: 900
  tools:
    command_timeout_s: 120   # one run_command before it is killed
    max_output_chars: 4000   # tool output kept for the model, head and tail
  context:                   # fitting each request into the model's window
    keep_recent_turns: 6     # turns never cut or dropped
    safety_margin: 0.1       # fraction of the window held back