ci: add gadfly adversarial review on PRs (mirrors mort)
executus CI / test (push) Successful in 35s

Same setup as mort: the published gadfly:v1 image as a specialist swarm
(m1/m5 local Macs + 2 cloud models, 3-lens suite), posting one consolidated
advisory comment. Must live on main so it triggers on PRs.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-26 19:46:47 -04:00
parent dc28b63ad8
commit 741d7816ed
+76
View File
@@ -0,0 +1,76 @@
# Gadfly — agentic adversarial PR reviewer (https://gitea.stevedudenhoeffer.com/steve/gadfly).
#
# Runs the published Gadfly image (pinned to :v1) as a specialist swarm and posts
# ONE consolidated review comment as gitea-actions. Advisory only — never blocks a
# merge. This reviews executus PRs (same setup as mort: m1/m5 locals + 2 cloud,
# 3-lens suite). Gadfly is a simple system — treat its findings as advisory and
# double-check before acting.
name: Adversarial Review (Gadfly)
on:
pull_request:
types: [opened, reopened, ready_for_review]
issue_comment:
types: [created]
workflow_dispatch:
inputs:
pr_number:
description: "PR number to review"
required: true
permissions:
contents: read
issues: write
pull-requests: write
concurrency:
group: gadfly-${{ github.event.issue.number || github.event.pull_request.number || github.event.inputs.pr_number }}
cancel-in-progress: true
jobs:
review:
# Security: only trusted users may trigger a secret-bearing run via a PR
# comment (pull_request + workflow_dispatch are already trusted). Mirrors
# GADFLY_ALLOWED_USERS, the in-container belt-and-suspenders check.
if: >-
github.event_name != 'issue_comment'
|| (github.event.issue.pull_request
&& (github.actor == 'steve'
|| github.actor == 'fizi'
|| github.actor == 'dazed'))
runs-on: ubuntu-latest
# Full fleet (2 cloud + 2 local Macs, all running concurrently) reviewing
# every PR with the 3-lens suite — the slow local lanes dominate wall time.
timeout-minutes: 90
steps:
- uses: docker://gitea.stevedudenhoeffer.com/steve/gadfly:v1
env:
GITEA_API: ${{ github.server_url }}/api/v1/repos/${{ github.repository }}
GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
OLLAMA_CLOUD_API_KEY: ${{ secrets.OLLAMA_CLOUD_API_KEY }}
# Local Ollama boxes (each its own lane, cap 1). NOTE: both Macs must be
# awake/reachable for their reviews to run; if a box is offline, that
# model's comment shows an error and the others still post.
GADFLY_ENDPOINT_M1PRO: "ollama|http://192.168.0.175:11434"
GADFLY_ENDPOINT_M5MAX: "ollama|http://192.168.0.173:11434"
# 2 cloud (parallel) + M1 Pro + M5 Max — one consolidated comment each.
GADFLY_MODELS: "minimax-m3:cloud,deepseek-v4-flash:cloud,m1pro/qwen3:14b,m5max/qwen3.6:35b-mlx"
# cloud runs 2 at once; each Mac one at a time; all three lanes parallel.
GADFLY_PROVIDER_CONCURRENCY: "ollama-cloud=2,m1pro=1,m5max=1"
# Default => the 3-lens suite (security, correctness, error-handling).
# Set the repo var GADFLY_SPECIALISTS to override (csv / "all" / "auto").
GADFLY_SPECIALISTS: ${{ vars.GADFLY_SPECIALISTS || 'security,correctness,error-handling' }}
# Per-lens deadline + bounded steps so the slow local models stay sane.
GADFLY_TIMEOUT_SECS: "600"
GADFLY_MAX_STEPS: "14"
# Allow-list for the comment trigger (mirrors the job-level if: guard).
GADFLY_ALLOWED_USERS: "steve,fizi,dazed"
# --- event context (leave as-is) ---
EVENT_NAME: ${{ github.event_name }}
PR: ${{ github.event.pull_request.number || github.event.issue.number || github.event.inputs.pr_number }}
PR_BRANCH: ${{ github.head_ref }}
IS_DRAFT: ${{ github.event.pull_request.draft }}
COMMENT_BODY: ${{ github.event.comment.body }}
COMMENT_ID: ${{ github.event.comment.id }}
ACTOR: ${{ github.actor }}