Files
nisse/nisse-review.example.yaml
dongarandClaude Opus 5.5 37bbac7e72 nisse-review: later reviews, replies, rounds, stop and review (M7.5)
Back on a PR it reviewed: a new head gets a later review of the commits
since (each one's diff, through the API) and of its earlier points; what
was said since gets replies, answered where it was said or skipped with a
reason. It signs off once and stays quiet while still happy. Past
tuning.review.max_rounds it sums up for the operator and goes quiet,
until a push or someone other than the PR's author joins in. An
operator's `stop` quiets it; `review` asks for a fresh review.

Reviews carry numbered markers and replies their point's key, so
recovery posts nothing twice.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk
2026-10-17 07:06:06 +00:00

42 lines
1.6 KiB
YAML

# Example configuration for nisse-review (Part R). Copy to nisse-review.yaml
# (or point NISSE_CONFIG at your copy) and edit.
#
# - Secrets are ${VARIABLE} references, resolved from the environment (or the
# .env file NISSE_ENV names) at startup. Nothing else goes there.
# - Unknown keys are errors.
# - Its Gitea account must have read access only to every repository it
# reviews: it refuses to start, and stops, if it can push to one (R3).
state_db: ~/nisse-review/state.db
llm: # L9: LiteLLM is the only LLM destination
base_url: http://litellm.example:4000
token: ${NISSE_LLM_TOKEN}
# max_output_tokens: 8192
# request_timeout_s: 600
roles:
reviewer: qwen3.8-27b # drives the review: the local model (R5)
expert: claude-opus-5-5 # ask_expert's
gitea:
url: https://gitea.example
token: ${NISSE_GITEA_TOKEN} # the nisse-review account's
operators: [operator] # whose comments are the operator's (R4)
# repositories: ["dev/*"] # patterns: owner/name, owner/*, */*;
# # public repositories included. Unset:
# # every one its account was given.
# vault: # L10; memory/nisse-review rw for its memory
# root: ~/vault
# folders:
# memory/nisse-review: rw
# notes: ro
# tuning: # docs/Tuning-Guide.md
# review: {poll_s: 60, max_turns: 40, diff_chars: 60000, attempts: 2,
# ci_wait_s: 3600, ci_grace_s: 120, max_rounds: 4}
# expert: {consult_budget: 3}
# context: {keep_recent_turns: 6, safety_margin: 0.1}