dongarandClaude Opus 5.5
3cf4cefacd
Architecture L9's role names, for the two roles with a direct counterpart: the delegation role is now 'helper' and the ask_expert role 'expert', in RoleMap, configuration (roles.helper, roles.expert), recorded events and tests. 'planner' and 'executor' stay distinct for now; they become 'driver' when the new loop merges them (Development Plan M2.3). Configurations must rename their keys: nisse-dev.example.yaml and tests/integration/nisse-test.yaml are updated here. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
64 lines
2.8 KiB
YAML
64 lines
2.8 KiB
YAML
# 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: # L9: 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: # L9: role -> LiteLLM model alias
|
|
executor: qwen3.8-27b # the local tier: best executor in the benchmark (PR #55)
|
|
planner: claude-opus-5-5 # high-end judgement: plans a weaker executor follows
|
|
helper: claude-opus-5-5 # takes over what the executor got stuck on
|
|
expert: claude-haiku-4-5 # one question at a time, no tools: cheap is enough
|
|
|
|
matrix: # L5
|
|
homeserver: https://matrix.example
|
|
user_id: "@nisse-dev:example"
|
|
token: ${NISSE_MATRIX_TOKEN}
|
|
room_id: "!roomid:example"
|
|
operators: ["@you:example"]
|
|
|
|
gitea: # D4, D5
|
|
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: 40 # model calls per milestone before it stops as capped
|
|
failure_limit: 2 # consecutive failed commands before escalating (L9)
|
|
expert:
|
|
consult_budget: 3 # ask_expert calls per milestone (L9)
|
|
delegation: # hard caps on one delegation (L9)
|
|
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
|