Files
gadfly/examples/adversarial-review.yml
T
Steve Dudenhoeffer bd76aa8286
Build & push image / build-and-push (push) Successful in 9s
feat: env-defined endpoint aliases (http-capable, local Ollama friendly)
majordomo's built-in LLM_* env DSNs are HTTPS-only (DSN.BaseURL forces https),
so they can't express a plaintext local Ollama. Add Gadfly-native env families
that register named providers/aliases with majordomo before resolution:

  GADFLY_ENDPOINT_<NAME>="<provider>|<base-url>[|<key>]"  # base URL verbatim (http ok)
  GADFLY_ALIAS_<NAME>="<majordomo spec>"                  # plain alias / failover chain

Then reference them as "<name>/<model>" (or the bare alias) in GADFLY_MODEL(S).
<NAME> lowercases to the registry name, matching majordomo's LLM_* convention.
LLM_* DSNs still work (and are documented) for HTTPS endpoints. + unit tests,
README "Endpoint aliases via env vars", stub example.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 19:01:07 -04:00

79 lines
3.4 KiB
YAML

# Drop this in ANY Gitea repo at .gitea/workflows/adversarial-review.yml to turn
# Gadfly on. The image holds all the logic; this stub just forwards the event
# context. Advisory only — it never blocks a merge.
#
# Per-repo setup (no code changes needed):
# secret OLLAMA_CLOUD_API_KEY your Ollama Cloud key
# var OLLAMA_REVIEW_MODELS (optional) comma-separated model ids
# var GADFLY_ALLOWED_USERS (optional) who may "@gadfly review"; empty =
# any repo collaborator
# GITEA_TOKEN is provided automatically; comments post as the gitea-actions user.
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:
runs-on: ubuntu-latest
timeout-minutes: 30
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 }}
OLLAMA_REVIEW_MODELS: ${{ vars.OLLAMA_REVIEW_MODELS }}
GADFLY_ALLOWED_USERS: ${{ vars.GADFLY_ALLOWED_USERS }}
# --- Models & providers (optional; default = Ollama Cloud) ----------
# Gadfly is majordomo-powered, so it can target other backends. Set a
# provider for bare model ids; point at a different endpoint with a
# base URL; supply a key (or the provider's standard env var). Examples:
#
# Local Ollama daemon (no key):
# GADFLY_PROVIDER: ollama
# GADFLY_MODELS: qwen2.5-coder:7b
# # GADFLY_BASE_URL: http://my-ollama-host:11434 # if not localhost
#
# OpenAI-compatible endpoint (incl. local Ollama's /v1):
# GADFLY_PROVIDER: openai
# GADFLY_BASE_URL: http://localhost:11434/v1
# GADFLY_MODELS: qwen2.5-coder:7b
#
# OpenAI / Anthropic / Google (supported via majordomo, UNTESTED — see README):
# GADFLY_PROVIDER: openai # then set OPENAI_API_KEY below
# OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
#
# Named endpoint aliases (reference as name/model in GADFLY_MODELS).
# vars/secrets aren't auto-exposed, so map each one explicitly:
# GADFLY_ENDPOINT_BIGBOX: ${{ vars.GADFLY_ENDPOINT_BIGBOX }} # "ollama|http://192.168.1.50:11434"
# GADFLY_MODELS: bigbox/qwen2.5-coder:7b
GADFLY_PROVIDER: ${{ vars.GADFLY_PROVIDER }}
GADFLY_BASE_URL: ${{ vars.GADFLY_BASE_URL }}
GADFLY_MODELS: ${{ vars.GADFLY_MODELS }}
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 }}