From 36f8ef0ec72d6d59464ca717731afb95a5610436 Mon Sep 17 00:00:00 2001 From: Steve Dudenhoeffer Date: Sat, 27 Jun 2026 18:40:38 -0400 Subject: [PATCH] ci: enable claude-code/opus:max (max-thinking) reviewer 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) --- .gitea/workflows/adversarial-review.yml | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/.gitea/workflows/adversarial-review.yml b/.gitea/workflows/adversarial-review.yml index 6b913d9..7c97f74 100644 --- a/.gitea/workflows/adversarial-review.yml +++ b/.gitea/workflows/adversarial-review.yml @@ -45,7 +45,7 @@ jobs: # with the 3-lens suite. All cloud now, so runs are fast. timeout-minutes: 90 steps: - - uses: docker://gitea.stevedudenhoeffer.com/steve/gadfly:sha-80d8f53 + - 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 }} @@ -54,12 +54,13 @@ jobs: # 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) — one + # 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" + 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).