# =====================================================================
# The VM sub-agent's model settings.
#
# This is the SECOND model - the one that drives a real machine - not the
# assistant. The assistant's parameters live in Open WebUI; see
# docs/advanced-params.md for both.
#
# They are separate on purpose. The assistant's numbers are tuned for
# prose and tool choice; this one spends most of its output writing code
# and reading error messages, and the two are not the same problem.
#
# Read by the vmagent container through `env_file` in docker-compose.yml.
# After editing:  docker compose up -d vmagent
# =====================================================================

# --- which model, and how it is loaded --------------------------------

# The same model the assistant uses, so there is one thing resident. Both
# share one Ollama with one slot.
OWUITOOLS_AGENT_MODEL=qwen3.8:latest

# MUST EQUAL THE CONTEXT THE MODEL IS ACTUALLY LOADED WITH.
#
# Ollama allocates the KV cache per loaded model, so asking for a
# different value makes it RELOAD - about eighteen gigabytes across the
# bus, in the middle of a session. Check with:
#   curl -s http://172.17.0.1:11434/api/ps
OWUITOOLS_AGENT_NUM_CTX=163840

# Never unload between turns. AN INTEGER, NOT A STRING: Ollama rejects
# "-1" with `time: missing unit in duration`, and the session then dies
# on its first call with an error about durations.
OWUITOOLS_AGENT_KEEP_ALIVE=-1

# How long one call to Ollama may take. A thinking turn on a long context
# is slow; this is the backstop for one that has stopped rather than one
# that is working.
OWUITOOLS_AGENT_REQUEST_TIMEOUT=1800

# --- sampling ---------------------------------------------------------

OWUITOOLS_AGENT_TEMPERATURE=0.6
OWUITOOLS_AGENT_TOP_P=0.95
OWUITOOLS_AGENT_TOP_K=20

# DELIBERATELY ZERO, and worth leaving alone.
#
# A presence penalty pushes the model away from tokens it has already
# used. Prose benefits; code does not - it reuses identifiers constantly,
# and penalising that produces subtly wrong variable names in the second
# half of a file. The archived version of this stack shipped with an
# inherited 1.5 from a Modelfile nobody had looked at.
OWUITOOLS_AGENT_PRESENCE_PENALTY=0.0

# One turn's output ceiling. A whole file in one write is normal here.
OWUITOOLS_AGENT_NUM_PREDICT=16384

# true | false | low | medium | high | max
OWUITOOLS_AGENT_THINK=true

# --- what bounds one session ------------------------------------------

# Tool calls. The backstop for an agent going in circles - and note that
# looking at the screen and acting on what it saw are two calls, so a GUI
# job spends these faster than a command-line one.
OWUITOOLS_VM_MAX_STEPS=110

# Wall-clock seconds. The backstop for everything else. Keep it below
# OWUITOOLS_VM_WAIT_SECONDS in configs/owuitools.env, so the session ends
# itself and reports rather than being cut off mid-sentence.
OWUITOOLS_VM_SESSION_SECONDS=7200

# Steps without touching the task list before the agent is told it is
# drifting. The task list is its spine: it is refused a finish while any
# task is open, and this is what catches wandering before the step budget
# does.
OWUITOOLS_VM_TASK_DRIFT=12

# How long a finished job's artefacts are kept before being reaped.
OWUITOOLS_VM_REAP_MINUTES=180