steve
36f8ef0ec7
Follow-up to #5: now that :sha-c342bdb (which has the :thinking spec parse) is built, add claude-code/opus:max to the dogfood swarm and pin to that image. The Claude Code lineup is now sonnet + opus + opus-with-max- thinking, so the scoreboard can compare the same model at two thinking depths. Best-effort max thinking via MAX_THINKING_TOKENS (no-op if the CLI build ignores it). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
90 lines
4.6 KiB
YAML
90 lines
4.6 KiB
YAML
# Gadfly — agentic adversarial PR reviewer (https://gitea.stevedudenhoeffer.com/steve/gadfly).
|
|
#
|
|
# Runs the published Gadfly image (pinned to an immutable :sha- tag — act_runner
|
|
# caches :latest, and this build is what carries foreman provider-type support)
|
|
# as a specialist swarm and posts
|
|
# ONE consolidated review comment as gitea-actions. Advisory only — never blocks a
|
|
# merge. Gadfly reviewing its OWN PRs — dogfooding: 6 cloud models + the Claude
|
|
# Code engine (sonnet) as a competitor. Local Macs and weak cloud models dropped.
|
|
|
|
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
|
|
# Fleet (6 cloud + claude-code/sonnet, all concurrent) reviewing every PR
|
|
# with the 3-lens suite. All cloud now, so runs are fast.
|
|
timeout-minutes: 90
|
|
steps:
|
|
- uses: docker://gitea.stevedudenhoeffer.com/steve/gadfly:sha-c342bdb
|
|
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 }}
|
|
# Claude Code engine auth (for the claude-code/* entries in GADFLY_MODELS
|
|
# below): Pro/Max subscription token. Dogfoods the Phase-1 engine on
|
|
# gadfly's own PRs as a competitor alongside the Ollama models.
|
|
CLAUDE_CODE_OAUTH_TOKEN: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
|
|
# Fleet: 6 cloud (3 at a time) + Claude Code (sonnet, opus, and opus
|
|
# with max extended thinking) — one
|
|
# consolidated comment each, all cloud now. The local Macs (m1/m5) and
|
|
# the weaker cloud models (gemma4, gpt-oss:120b, kimi-k2.7-code) were
|
|
# dropped as low-signal. The claude-code/* entries run the Phase-1
|
|
# engine as competitors in their own lane (need CLAUDE_CODE_OAUTH_TOKEN).
|
|
GADFLY_MODELS: "minimax-m3:cloud,glm-5.2:cloud,glm-5.1:cloud,deepseek-v4-pro:cloud,nemotron-3-super:cloud,qwen3-coder:480b-cloud,claude-code/sonnet,claude-code/opus,claude-code/opus:max"
|
|
# cloud runs 3 at once; claude-code 2 at a time; both lanes parallel.
|
|
GADFLY_PROVIDER_CONCURRENCY: "ollama-cloud=3,claude-code=2"
|
|
# 3 cloud models x 3 lenses = 9 concurrent ollama-cloud queries (under the 10 budget).
|
|
GADFLY_PROVIDER_LENS_CONCURRENCY: "ollama-cloud=3"
|
|
# 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 (also bounds the claude-code lane).
|
|
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"
|
|
# --- findings telemetry: POST runs + findings to the gadfly-reports store ---
|
|
# Advisory & off unless GADFLY_FINDINGS_URL is set; failures only log to
|
|
# stderr and never affect the review. GADFLY_REPO / GADFLY_PR are derived
|
|
# in-container; the URL + token are user-scope secrets.
|
|
GADFLY_FINDINGS_URL: ${{ secrets.GADFLY_FINDINGS_URL }}
|
|
GADFLY_FINDINGS_TOKEN: ${{ secrets.GADFLY_FINDINGS_TOKEN }}
|
|
# --- 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 }}
|