steve/gadfly
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ci: enable claude-code/opus:max (max-thinking) reviewer
Build & push image / build-and-push (pull_request) Successful in 7s
Details
Adversarial Review (Gadfly) / review (pull_request) Successful in 7m1s
Details

Browse Source 
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>
This commit is contained in:
Steve Dudenhoeffer
2026-06-27 18:40:38 -04:00
parent c342bdb905
commit 36f8ef0ec7
1 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.gitea/workflows/adversarial-review.yml
+4 -3
View File
@@ -45,7 +45,7 @@ jobs:
# with the 3-lens suite. All cloud now, so runs are fast. # with the 3-lens suite. All cloud now, so runs are fast.
timeout-minutes: 90 timeout-minutes: 90
steps: steps:
- uses: docker://gitea.stevedudenhoeffer.com/steve/gadfly:sha-80d8f53 - uses: docker://gitea.stevedudenhoeffer.com/steve/gadfly:sha-c342bdb
env: env:
GITEA_API: ${{ github.server_url }}/api/v1/repos/${{ github.repository }} GITEA_API: ${{ github.server_url }}/api/v1/repos/${{ github.repository }}
GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }} GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
@@ -54,12 +54,13 @@ jobs:
# below): Pro/Max subscription token. Dogfoods the Phase-1 engine on # below): Pro/Max subscription token. Dogfoods the Phase-1 engine on
# gadfly's own PRs as a competitor alongside the Ollama models. # gadfly's own PRs as a competitor alongside the Ollama models.
CLAUDE_CODE_OAUTH_TOKEN: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }} 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 # 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 # 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 # dropped as low-signal. The claude-code/* entries run the Phase-1
# engine as competitors in their own lane (need CLAUDE_CODE_OAUTH_TOKEN). # 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. # cloud runs 3 at once; claude-code 2 at a time; both lanes parallel.
GADFLY_PROVIDER_CONCURRENCY: "ollama-cloud=3,claude-code=2" GADFLY_PROVIDER_CONCURRENCY: "ollama-cloud=3,claude-code=2"
# 3 cloud models x 3 lenses = 9 concurrent ollama-cloud queries (under the 10 budget). # 3 cloud models x 3 lenses = 9 concurrent ollama-cloud queries (under the 10 budget).