Skip to content

Fix OpenCode check lookup and review budget #274

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

Open
seonghobae wants to merge 6 commits into
base: main
Choose a base branch
from
+33 −19
Open

Fix OpenCode check lookup and review budget #274

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
e5ce61d
Reduce OpenCode model pool stall time
seonghobae Jul 1, 2026
2e755f4
Fix OpenCode check pagination lookup
seonghobae Jul 1, 2026
ae09dd8
Update OpenCode model order self-test
seonghobae Jul 1, 2026
dc2c567
Keep OpenCode review time budget
seonghobae Jul 1, 2026
62837fa
Merge main and extend OpenCode review budget
seonghobae Jul 1, 2026
eb4dc12
Restore multi-model pool and fix exponential retry backoff
Copilot Jul 1, 2026
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
26 changes: 17 additions & 9 deletions .github/workflows/opencode-review.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2239,21 +2239,21 @@ jobs:
id: opencode_review_model_pool
if: needs.coverage-evidence.result == 'success'
continue-on-error: true
timeout-minutes: 20
timeout-minutes: 300
env:
STRIX_GITHUB_MODELS_TOKEN: ${{ secrets.STRIX_GITHUB_MODELS_TOKEN || github.token }}
GITHUB_TOKEN: ${{ secrets.STRIX_GITHUB_MODELS_TOKEN || github.token }}
USE_GITHUB_TOKEN: "true"
SHARE: "false"
NPM_CONFIG_IGNORE_SCRIPTS: "true"
NO_COLOR: "1"
OPENCODE_MODEL_CANDIDATES: "github-models/openai/gpt-5-nano"
OPENCODE_MODEL_CANDIDATES: "github-models/openai/gpt-5 github-models/openai/gpt-5-chat github-models/openai/gpt-5-mini github-models/openai/gpt-5-nano github-models/openai/o3 github-models/openai/o3-mini github-models/openai/o4-mini github-models/mistral-ai/mistral-medium-2505 github-models/meta/llama-4-maverick-17b-128e-instruct-fp8 github-models/meta/llama-4-scout-17b-16e-instruct github-models/deepseek/deepseek-r1-0528 github-models/deepseek/deepseek-r1 github-models/deepseek/deepseek-v3-0324"

@github-actions github-actions Bot Jul 1, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

HIGH OpenCode could not establish approval sufficiency

  • Problem: the model pool exhausted without a valid current-head review control block, so this changed line cannot be approved from deterministic check state alone.
  • Impact: PR-intent mismatches, missing files, robustness bugs, UX/DX regressions, and CodeGraph-backed flow changes could be missed.
  • Fix: rerun OpenCode after model availability recovers, or add the missing source/test/docs/generated verification evidence needed for a source-backed approval.
  • Verification: rerun the OpenCode Review workflow and confirm it emits APPROVE or source-backed REQUEST_CHANGES for this head SHA.

OPENCODE_MODEL_ATTEMPTS: "1"
OPENCODE_RUN_TIMEOUT_SECONDS: "240"
OPENCODE_RUN_TIMEOUT_SECONDS: "17400"
OPENCODE_EXPORT_TIMEOUT_SECONDS: "120"
OPENCODE_TOTAL_RETRY_BUDGET_SECONDS: "360"
OPENCODE_TOTAL_RETRY_BUDGET_SECONDS: "18000"
OPENCODE_BACKOFF_INITIAL_SECONDS: "30"
OPENCODE_BACKOFF_MAX_SECONDS: "30"
OPENCODE_BACKOFF_MAX_SECONDS: "600"
OPENCODE_FIRST_ATTEMPT_AGENT: ci-review
OPENCODE_AGENT: ci-review-fallback
OPENCODE_EVIDENCE_FILE: ${{ runner.temp }}/opencode-review-evidence.md
Expand Down Expand Up @@ -4054,11 +4054,19 @@ jobs:
;;
esac

gh api -X GET "repos/${GH_REPOSITORY}/commits/${HEAD_SHA}/check-runs" \
local check_runs_pages_file
check_runs_pages_file="$(mktemp)"
if ! gh api -X GET "repos/${GH_REPOSITORY}/commits/${HEAD_SHA}/check-runs" \
-f per_page=100 \
--paginate \
--slurp |
jq -r "$jq_filter" >"$output_file"
--paginate >"$check_runs_pages_file"; then
rm -f "$check_runs_pages_file"
return 1
fi
if ! jq -s "$jq_filter" "$check_runs_pages_file" >"$output_file"; then
rm -f "$check_runs_pages_file"
return 1
fi
rm -f "$check_runs_pages_file"
}

current_head_manual_strix_success_status() {
Expand Down
11 changes: 7 additions & 4 deletions scripts/ci/test_strix_quick_gate.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -508,8 +508,9 @@ assert_opencode_review_uses_codegraph_and_gpt5_fallback() {
assert_file_contains "$REPO_ROOT/scripts/ci/run_opencode_review_model_pool.sh" "Read and follow the complete review contract" "opencode review uses a compact launcher while keeping the full review contract on disk"
assert_file_contains "$REPO_ROOT/scripts/ci/run_opencode_review_model_pool.sh" "tokens_limit_reached" "opencode review detects provider context-window overflow"
assert_file_contains "$REPO_ROOT/scripts/ci/run_opencode_review_model_pool.sh" "skipping remaining attempts for this model" "opencode review skips same-model retries after context-window overflow"
assert_file_contains "$workflow_file" 'OPENCODE_RUN_TIMEOUT_SECONDS: "600"' "opencode primary review has a bounded per-model timeout before trying fallback models"
assert_file_contains "$workflow_file" 'OPENCODE_TOTAL_RETRY_BUDGET_SECONDS: "3600"' "opencode model pool has a one-hour total retry budget"
assert_file_contains "$workflow_file" 'timeout-minutes: 300' "opencode model pool has a five-hour job timeout for large codebases"
assert_file_contains "$workflow_file" 'OPENCODE_RUN_TIMEOUT_SECONDS: "17400"' "opencode primary review has a bounded per-model timeout before trying fallback models"
assert_file_contains "$workflow_file" 'OPENCODE_TOTAL_RETRY_BUDGET_SECONDS: "18000"' "opencode model pool has a five-hour total retry budget"
assert_file_contains "$workflow_file" "needs.coverage-evidence.result == 'success'" "opencode model pool only runs after coverage evidence passed"
assert_file_contains "$workflow_file" "id: opencode_review_model_pool" "opencode DeepSeek V3 fallback still runs after a primary model timeout or step failure when coverage evidence passed"
assert_file_contains "$workflow_file" "always()" "opencode fallback chain uses always() so failed model steps cannot skip every fallback"
Expand Down Expand Up @@ -618,7 +619,7 @@ assert_opencode_review_uses_codegraph_and_gpt5_fallback() {
assert_file_contains "$workflow_file" "no model produced a valid review control block" "opencode model-failure path documents why approval is withheld"
assert_file_contains "$workflow_file" 'OPENCODE_MODEL_ATTEMPTS: "1"' "opencode primary and fallback paths avoid multi-attempt stalls on one model"
assert_file_contains "$workflow_file" 'OPENCODE_MODEL_ATTEMPTS: "1"' "opencode catalog fallback tries each model once before moving on"
assert_file_contains "$workflow_file" 'OPENCODE_RUN_TIMEOUT_SECONDS: "600"' "opencode catalog fallback has a bounded model review timeout before step timeout"
assert_file_contains "$workflow_file" 'OPENCODE_RUN_TIMEOUT_SECONDS: "17400"' "opencode catalog fallback has a bounded model review timeout before step timeout"
assert_file_contains "$REPO_ROOT/scripts/ci/run_opencode_review_model_pool.sh" "OpenCode %s attempt %s/%s failed" "opencode catalog fallback records per-model retry failures"
assert_file_contains "$REPO_ROOT/scripts/ci/run_opencode_review_model_pool.sh" "exponential backoff" "opencode model retry paths use exponential backoff instead of fixed sleeps"
assert_file_contains "$workflow_file" "github-models/openai/o3 github-models/openai/o3-mini github-models/openai/o4-mini" "opencode review includes additional OpenAI reasoning model fallbacks"
Expand Down Expand Up @@ -690,7 +691,9 @@ assert_opencode_review_uses_codegraph_and_gpt5_fallback() {
assert_file_contains "$workflow_file" 'collect_current_head_strix_workflow_runs()' "opencode approval separately accounts for jobless current-head Strix workflow runs"
assert_file_contains "$workflow_file" 'collect_current_head_commit_check_runs()' "opencode approval falls back to current-head commit check-runs when PR rollup lags"
assert_file_contains "$workflow_file" 'commits/${HEAD_SHA}/check-runs' "opencode approval queries current-head commit check-runs before changing review state"
assert_file_contains "$workflow_file" '--slurp' "opencode approval aggregates paginated commit check-runs before classifying them"
assert_file_contains "$workflow_file" 'jq -s "$jq_filter"' "opencode approval aggregates paginated commit check-runs before classifying them"
assert_file_not_contains "$workflow_file" '--slurp \
--jq "$jq_filter"' "opencode approval avoids gh versions that reject --slurp with --jq"
assert_file_contains "$workflow_file" 'group_by(.name // "")' "opencode approval keeps only the latest same-name commit check-run"
assert_file_contains "$workflow_file" 'map(last)' "opencode approval ignores superseded same-name commit check-runs"
assert_file_contains "$workflow_file" 'collect_current_head_commit_check_runs "$commit_check_runs_file" pending' "opencode approval blocks approval on pending commit check-runs omitted from PR rollup"
Expand Down
15 changes: 9 additions & 6 deletions tests/test_opencode_agent_contract.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -211,17 +211,20 @@ def test_workflow_provisions_sandbox_tool_and_reviewer_agent():
assert '"## Check outcome"' not in workflow
assert "publish REQUEST_CHANGES when coverage-evidence blocker states" in workflow
assert 'timeout-minutes: 75' in workflow
assert re.search(r"Run OpenCode PR Review model pool[\s\S]{0,240}timeout-minutes: 20", workflow)
assert re.search(r"Run OpenCode PR Review model pool[\s\S]{0,240}timeout-minutes: 300", workflow)
assert 'APPROVAL_CHECK_WAIT_ATTEMPTS: "81"' in workflow
assert 'APPROVAL_CHECK_WAIT_SLEEP_SECONDS: "30"' in workflow
assert 'OPENCODE_MODEL_CANDIDATES: "github-models/openai/gpt-5-nano"' in workflow
assert 'OPENCODE_MODEL_CANDIDATES: "github-models/openai/gpt-5 github-models/openai/gpt-5-chat' in workflow
assert 'OPENCODE_MODEL_ATTEMPTS: "1"' in workflow
assert 'OPENCODE_RUN_TIMEOUT_SECONDS: "240"' in workflow
assert 'OPENCODE_RUN_TIMEOUT_SECONDS: "17400"' in workflow
assert 'OPENCODE_EXPORT_TIMEOUT_SECONDS: "120"' in workflow
assert 'OPENCODE_TOTAL_RETRY_BUDGET_SECONDS: "360"' in workflow
assert 'OPENCODE_BACKOFF_MAX_SECONDS: "30"' in workflow
assert 'OPENCODE_TOTAL_RETRY_BUDGET_SECONDS: "18000"' in workflow
assert 'OPENCODE_BACKOFF_MAX_SECONDS: "600"' in workflow
assert 'jq -s "$jq_filter"' in workflow
assert '--slurp \\\n --jq "$jq_filter"' not in workflow
assert "${{ runner.temp }}/opencode-review-model-pool.md" in workflow
assert re.search(r'check-runs" \\\n\s+-f per_page=100 \\\n\s+--paginate \\\n\s+--slurp \|\n\s+jq -r "\$jq_filter"', workflow)
assert re.search(r'check-runs" \\\n\s+-f per_page=100 \\\n\s+--paginate >"\$check_runs_pages_file"', workflow)
assert 'jq -s "$jq_filter" "$check_runs_pages_file" >"$output_file"' in workflow
assert not re.search(r"--slurp\s*\\\n\s*--jq", workflow)
assert "falling back to current-head REST check-runs" in workflow

Expand Down