Skip to content

chore(ci): drive gate model from a repo variable, cheap 8B default #141

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
drewstone merged 1 commit into from
Aug 3, 2026
Merged

chore(ci): drive gate model from a repo variable, cheap 8B default #141

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion .github/workflows/tier1-gate.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,13 +34,16 @@ jobs:
run: |
pnpm bench:tier1:gate -- \
--out ./agent-results/tier1-ci \
--model gpt-5.2 \
--model "${{ vars.BAD_CI_MODEL || 'groq/llama-3.1-8b-instant' }}" \
--min-full-pass-rate 1 \
--min-fast-pass-rate 1 \
--max-avg-turns 24 \
--max-avg-duration-ms 120000
env:
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
# groq/* model ids resolve only through an OpenAI-compatible router;
# override both vars together to pin a direct-provider model.
LLM_BASE_URL: ${{ vars.BAD_CI_LLM_BASE_URL || 'https://router.tangle.tools/v1' }}
- name: Upload gate artifacts
if: always() && env.SKIP_GATE != 'true'
uses: actions/upload-artifact@v4
Expand Down
5 changes: 4 additions & 1 deletion .github/workflows/tier2-staging-gate.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ jobs:
run: |
pnpm bench:tier2:repeat -- \
--out ./agent-results/tier2-staging \
--model gpt-5.2 \
--model "${{ vars.BAD_CI_MODEL || 'groq/llama-3.1-8b-instant' }}" \
--storage-state ./.auth/ai-tangle-tools.json \
--repetitions 2 \
--min-full-pass-rate 1 \
Expand All @@ -56,6 +56,9 @@ jobs:
--max-avg-duration-ms 300000
env:
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
# groq/* model ids resolve only through an OpenAI-compatible router;
# override both vars together to pin a direct-provider model.
LLM_BASE_URL: ${{ vars.BAD_CI_LLM_BASE_URL || 'https://router.tangle.tools/v1' }}

- name: Upload gate artifacts
if: always() && env.SKIP_GATE != 'true'
Expand Down
Loading