diff --git a/.gitea/workflows/adversarial-review.yml b/.gitea/workflows/adversarial-review.yml index 1831136..2b5d968 100644 --- a/.gitea/workflows/adversarial-review.yml +++ b/.gitea/workflows/adversarial-review.yml @@ -4,9 +4,9 @@ # 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. This reviews majordomo PRs with 9 ollama-cloud models + the M5 Mac -# (3-lens suite). Gadfly is a simple system — findings are advisory; always -# double-check before acting. +# merge. This reviews majordomo PRs with 6 ollama-cloud models (3-lens suite). +# Gadfly is a simple system — findings are advisory; always double-check before +# acting. name: Adversarial Review (Gadfly) @@ -42,36 +42,26 @@ jobs: || github.actor == 'fizi' || github.actor == 'dazed')) runs-on: ubuntu-latest - # Fleet: 9 cloud (lens fan-out) + the M5 Mac via foreman. The slow local - # lane dominates wall time, so allow plenty of headroom. (M1 was dropped — - # consistently slow for zero real findings.) - timeout-minutes: 90 + # Fleet: 6 ollama-cloud models (lens fan-out), no local Macs. (Trimmed the + # weakest reviewers by grade — m5/qwen3.6, gemma4, gpt-oss, kimi-k2.7 — plus + # the earlier M1 drop.) Plenty of headroom for the cloud lanes. + timeout-minutes: 45 steps: - uses: docker://gitea.stevedudenhoeffer.com/steve/gadfly:sha-d7f364d 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 Mac, reached through its foreman queue (native Ollama on the - # wire). GADFLY_ENDPOINT_M5 registers provider "m5", a foreman-preset - # Ollama client at the secret's URL, of the form: - # foreman|https://| - # Needs an image with foreman provider-type support (this one). If the Mac - # is offline that model's comment shows an error and the others still post. - # (Gitea secrets aren't auto-exposed — map each explicitly.) - GADFLY_ENDPOINT_M5: ${{ secrets.GADFLY_ENDPOINT_M5 }} - # Fleet: 9 cloud + M5 Max. Cloud concurrency lives in the LENSES: cloud - # models run a few at a time (ollama-cloud=3) with their 3 lenses - # concurrent (LENS ollama-cloud=3) so comments land sooner; the Mac runs - # one model, lenses serial (its foreman queue serializes anyway). Both - # provider lanes run parallel. - GADFLY_MODELS: "minimax-m3:cloud,glm-5.2:cloud,glm-5.1:cloud,kimi-k2.7-code:cloud,deepseek-v4-pro:cloud,nemotron-3-super:cloud,gpt-oss:120b-cloud,qwen3-coder:480b-cloud,gemma4:cloud,m5/qwen3.6:35b-mlx" - GADFLY_PROVIDER_CONCURRENCY: "ollama-cloud=3,m5=1" + # Cloud-only fleet (no local Macs). Cloud concurrency lives in the + # LENSES: models run a few at a time (ollama-cloud=3) with their 3 lenses + # concurrent (LENS ollama-cloud=3) so comments land sooner. + 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" + GADFLY_PROVIDER_CONCURRENCY: "ollama-cloud=3" 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 so the slow local models stay sane. + # Per-lens deadline + bounded steps to keep each reviewer's run sane. GADFLY_TIMEOUT_SECS: "600" GADFLY_MAX_STEPS: "14" # Allow-list for the comment trigger (mirrors the job-level if: guard). diff --git a/CLAUDE.md b/CLAUDE.md index 5ad3157..00585c5 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -141,9 +141,9 @@ Ship work through PRs and let Gadfly review it before merge: - **Push to a PR, never straight to `main`.** Branch, push, open a PR. `.gitea/workflows/adversarial-review.yml` runs Gadfly (the standalone - agentic adversarial reviewer) — a fleet of 9 ollama-cloud models + - the M5 Mac via foreman, each running the 3-lens suite (security, - correctness, error-handling). Advisory only; it never blocks the merge. + agentic adversarial reviewer) — a fleet of 6 ollama-cloud models, each + running the 3-lens suite (security, correctness, error-handling). Advisory + only; it never blocks the merge. - **Wait for Gadfly to finish, then read its output.** Don't merge while the review is still running. Each model posts one consolidated comment; weigh every finding on its merits and fix the real ones (Gadfly is a simple