Skip to content

fix(ci): restore optional eval matrix output #2768

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
cquil11 merged 1 commit into from
Aug 28, 2026
Merged

fix(ci): restore optional eval matrix output #2768

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
17 changes: 9 additions & 8 deletions .github/workflows/e2e-tests.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -261,6 +261,7 @@ jobs:
MULTI_AGENTIC_EVAL=$(echo "$CONFIG_JSON" | python3 -c "import sys,json; d=json.load(sys.stdin); print(json.dumps([x for x in d if x.get('scenario-type') == 'agentic-coding' and 'prefill' in x and x.get('run-eval', False)]))" | score_matrix multi-agentic-eval)
SINGLE=$(echo "$CONFIG_JSON" | python3 -c "import sys,json; d=json.load(sys.stdin); print(json.dumps([x for x in d if 'prefill' not in x and x.get('scenario-type') != 'agentic-coding' and not x.get('eval-only', False)]))" | score_matrix single)
MULTI=$(echo "$CONFIG_JSON" | python3 -c "import sys,json; d=json.load(sys.stdin); print(json.dumps([x for x in d if 'prefill' in x and x.get('scenario-type') != 'agentic-coding' and not x.get('eval-only', False)]))" | score_matrix multi)
EVALS=$(echo "$CONFIG_JSON" | python3 -c "import sys,json; d=json.load(sys.stdin); print(json.dumps([x for x in d if 'prefill' not in x and x.get('scenario-type') != 'agentic-coding' and x.get('run-eval', False)]))" | score_matrix eval)
MULTI_EVAL=$(echo "$CONFIG_JSON" | python3 -c "import sys,json; d=json.load(sys.stdin); print(json.dumps([x for x in d if 'prefill' in x and x.get('scenario-type') != 'agentic-coding' and x.get('run-eval', False)]))" | score_matrix multi-eval)
{
echo "agentic-config=$AGENTIC"
Expand All @@ -275,7 +276,7 @@ jobs:

test-sweep-multi-node:
needs: get-jobs
if: ${{ needs.get-jobs.outputs.multi-node-config != '[]' }}
if: ${{ needs.get-jobs.outputs.multi-node-config != '' && needs.get-jobs.outputs.multi-node-config != '[]' }}
uses: ./.github/workflows/benchmark-multinode-tmpl.yml
name: multi-node /
strategy:
Expand Down Expand Up @@ -330,7 +331,7 @@ jobs:

test-sweep-multi-node-evals:
needs: get-jobs
if: ${{ needs.get-jobs.outputs.multi-node-eval-config != '[]' }}
if: ${{ needs.get-jobs.outputs.multi-node-eval-config != '' && needs.get-jobs.outputs.multi-node-eval-config != '[]' }}
uses: ./.github/workflows/benchmark-multinode-tmpl.yml
name: multi-node eval /
strategy:
Expand Down Expand Up @@ -385,7 +386,7 @@ jobs:

test-sweep-agentic:
needs: get-jobs
if: ${{ needs.get-jobs.outputs.agentic-config != '[]' }}
if: ${{ needs.get-jobs.outputs.agentic-config != '' && needs.get-jobs.outputs.agentic-config != '[]' }}
uses: ./.github/workflows/benchmark-tmpl.yml
name: agentic /
strategy:
Expand Down Expand Up @@ -431,7 +432,7 @@ jobs:

test-sweep-agentic-evals:
needs: get-jobs
if: ${{ needs.get-jobs.outputs.agentic-eval-config != '[]' }}
if: ${{ needs.get-jobs.outputs.agentic-eval-config != '' && needs.get-jobs.outputs.agentic-eval-config != '[]' }}
uses: ./.github/workflows/benchmark-tmpl.yml
name: agentic eval /
strategy:
Expand Down Expand Up @@ -473,7 +474,7 @@ jobs:

test-sweep-multi-node-agentic:
needs: get-jobs
if: ${{ needs.get-jobs.outputs.multi-node-agentic-config != '[]' }}
if: ${{ needs.get-jobs.outputs.multi-node-agentic-config != '' && needs.get-jobs.outputs.multi-node-agentic-config != '[]' }}
uses: ./.github/workflows/benchmark-multinode-tmpl.yml
name: multi-node agentic /
strategy:
Expand Down Expand Up @@ -533,7 +534,7 @@ jobs:

test-sweep-multi-node-agentic-evals:
needs: get-jobs
if: ${{ needs.get-jobs.outputs.multi-node-agentic-eval-config != '[]' }}
if: ${{ needs.get-jobs.outputs.multi-node-agentic-eval-config != '' && needs.get-jobs.outputs.multi-node-agentic-eval-config != '[]' }}
uses: ./.github/workflows/benchmark-multinode-tmpl.yml
name: multi-node agentic eval /
strategy:
Expand Down Expand Up @@ -594,7 +595,7 @@ jobs:

test-sweep-single-node:
needs: get-jobs
if: ${{ needs.get-jobs.outputs.single-node-config != '[]' }}
if: ${{ needs.get-jobs.outputs.single-node-config != '' && needs.get-jobs.outputs.single-node-config != '[]' }}
uses: ./.github/workflows/benchmark-tmpl.yml
name: single-node /
strategy:
Expand Down Expand Up @@ -633,7 +634,7 @@ jobs:

test-sweep-evals:
needs: get-jobs
if: ${{ needs.get-jobs.outputs.eval-config != '[]' }}
if: ${{ needs.get-jobs.outputs.eval-config != '' && needs.get-jobs.outputs.eval-config != '[]' }}
uses: ./.github/workflows/benchmark-tmpl.yml
name: eval /
strategy:
Expand Down
15 changes: 15 additions & 0 deletions utils/test_ci_priority.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
import json
import re
import shlex
from copy import deepcopy
from decimal import Decimal
Expand Down Expand Up @@ -260,3 +261,17 @@ def test_queue_tokens_change_between_run_attempts():
"123:2",
("0",),
)


def test_e2e_matrix_outputs_reference_initialized_shell_variables():
workflow = (
Path(__file__).parents[1] / ".github" / "workflows" / "e2e-tests.yml"
).read_text()
assignments = set(
re.findall(r"^\s*([A-Z][A-Z0-9_]*)=\$\(", workflow, re.MULTILINE)
)
output_variables = set(
re.findall(r'^\s*echo "[a-z-]+=\$([A-Z][A-Z0-9_]*)"', workflow, re.MULTILINE)
)

assert output_variables <= assignments