Files
gadfly/examples/claude-code.yml
T
steve 4237a18d09
Build & push image / build-and-push (pull_request) Successful in 46s
Adversarial Review (Gadfly) / review (pull_request) Failing after 30m16s
feat: claude-code reviewer engine (per-lens claude -p shell-out)
Phase 1 of the gadfly-games build. Adds a second review engine alongside
the majordomo agent loop: for each lens, shell out to the Claude Code CLI
(`claude -p`) inside the checked-out repo so it verifies findings with
its OWN read tools, then reuse gadfly's verdict-parse + recheck +
consolidate + emit pipeline unchanged.

- cmd/gadfly/engine.go: new reviewEngine interface with two impls —
  majordomoEngine (wraps the existing runAgent path) and claudeCodeEngine
  (exec `claude -p ... --output-format json`, parse `.result`). main.go's
  runSpecialists/reviewWithSpecialist are now engine-agnostic.
- Select via a model id: `claude-code` (CLI default) or
  `claude-code/<model>` (suffix → --model). Auth inherits from the env:
  Pro/Max via CLAUDE_CODE_OAUTH_TOKEN (no --bare), else ANTHROPIC_API_KEY.
  Read-only by default (--permission-mode plan); tunable via GADFLY_CLAUDE_*.
- auto-select + delegate worker are majordomo-only and are skipped with
  this engine (Claude Code does its own legwork).
- Dockerfile bundles Node + @anthropic-ai/claude-code (larger image).
- Docs: README "Claude Code engine" section + config rows, examples/
  claude-code.yml stub, examples/README + CLAUDE.md updated. Honest note
  that subscription-auth-in-CI is untested here / a ToS gray area.
- Bumps the dogfood image pin to :sha-c3d09d3 so gadfly's own PRs now
  review with the live status board from Phase 3.

New engine_test.go covers spec detection, model derivation, and argv
building (no live CLI call). gofmt clean, go vet quiet, go test -race green.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-27 15:26:57 -04:00

72 lines
3.1 KiB
YAML

# Gadfly reviewing via the Claude Code CLI engine.
# Copy to .gitea/workflows/adversarial-review.yml in your repo.
#
# Instead of a majordomo model, each lens shells out to the bundled `claude` CLI
# inside the checked-out repo (it uses its own Read/Grep/Glob tools to verify
# findings), then Gadfly runs its usual verdict + recheck + consolidate pipeline.
#
# Auth: a Pro/Max subscription token from `claude setup-token` (no --bare),
# stored as the CLAUDE_CODE_OAUTH_TOKEN secret. Falls back to ANTHROPIC_API_KEY
# if you'd rather pay per-token — set only ONE.
#
# Heads-up: this engine is wired but not yet validated end-to-end here, and using
# subscription auth in automated CI is a gray area in Anthropic's terms — read
# the README's "Claude Code engine" note before relying on it.
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. Replace the username(s) below with your maintainers — keep them in
# sync with GADFLY_ALLOWED_USERS (the in-container belt-and-suspenders check).
if: >-
github.event_name != 'issue_comment'
|| github.actor == 'your-username'
runs-on: ubuntu-latest
timeout-minutes: 30
steps:
- uses: docker://gitea.stevedudenhoeffer.com/steve/gadfly:latest
env:
GITEA_API: ${{ github.server_url }}/api/v1/repos/${{ github.repository }}
GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
# --- Claude Code engine ---
# Pro/Max subscription token (preferred). Or set ANTHROPIC_API_KEY
# instead for per-token billing — but never both.
CLAUDE_CODE_OAUTH_TOKEN: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
# ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
# bare "claude-code" uses the CLI default model; "claude-code/<model>"
# sets --model (sonnet/opus/haiku, or a full id). One comment per entry.
GADFLY_MODELS: "claude-code/sonnet"
# Optional CLI tuning (defaults are read-only-safe):
# GADFLY_CLAUDE_PERMISSION_MODE: plan # read-only; never edits
# GADFLY_CLAUDE_ALLOWED_TOOLS: "Read,Grep,Glob"
# GADFLY_CLAUDE_EXTRA_ARGS: "--max-turns 30"
GADFLY_ALLOWED_USERS: "your-username"
# --- 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 }}