diff --git a/.github/workflows/opencode-review.yml b/.github/workflows/opencode-review.yml index 4b6a0abb..6d20206a 100644 --- a/.github/workflows/opencode-review.yml +++ b/.github/workflows/opencode-review.yml @@ -2239,7 +2239,7 @@ 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 }} @@ -2247,13 +2247,13 @@ jobs: 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" 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: ${{ runner.temp }}/opencode-review-evidence.md @@ -4054,11 +4054,19 @@ jobs: ;; esac - gh api -X GET "repos/${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 "$check_runs_pages_file" } current_head_manual_strix_success_status() { diff --git a/scripts/ci/test_strix_quick_gate.sh b/scripts/ci/test_strix_quick_gate.sh index ffea57cd..f0db45b8 100755 --- a/scripts/ci/test_strix_quick_gate.sh +++ b/scripts/ci/test_strix_quick_gate.sh @@ -508,8 +508,9 @@ assert_opencode_review_uses_codegraph_and_gpt5_fallback() { assert_file_contains "$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" @@ -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" @@ -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 "$commit_check_runs_file" pending' "opencode approval blocks approval on pending commit check-runs omitted from PR rollup" diff --git a/tests/test_opencode_agent_contract.py b/tests/test_opencode_agent_contract.py index c5dd7a9b..bcfa653f 100644 --- a/tests/test_opencode_agent_contract.py +++ b/tests/test_opencode_agent_contract.py @@ -211,17 +211,20 @@ def test_workflow_provisions_sandbox_tool_and_reviewer_agent(): assert '"## Check outcome"' not in workflow assert "publish REQUEST_CHANGES when coverage-evidence blocker states" in workflow assert 'timeout-minutes: 75' in workflow - assert re.search(r"Run OpenCode PR Review model pool[\s\S]{0,240}timeout-minutes: 20", workflow) + assert re.search(r"Run OpenCode PR Review model pool[\s\S]{0,240}timeout-minutes: 300", workflow) assert 'APPROVAL_CHECK_WAIT_ATTEMPTS: "81"' in workflow assert 'APPROVAL_CHECK_WAIT_SLEEP_SECONDS: "30"' in workflow - assert 'OPENCODE_MODEL_CANDIDATES: "github-models/openai/gpt-5-nano"' in workflow + assert 'OPENCODE_MODEL_CANDIDATES: "github-models/openai/gpt-5 github-models/openai/gpt-5-chat' in workflow assert 'OPENCODE_MODEL_ATTEMPTS: "1"' in workflow - assert 'OPENCODE_RUN_TIMEOUT_SECONDS: "240"' in workflow + assert 'OPENCODE_RUN_TIMEOUT_SECONDS: "17400"' in workflow assert 'OPENCODE_EXPORT_TIMEOUT_SECONDS: "120"' in workflow - assert 'OPENCODE_TOTAL_RETRY_BUDGET_SECONDS: "360"' in workflow - assert 'OPENCODE_BACKOFF_MAX_SECONDS: "30"' in workflow + assert 'OPENCODE_TOTAL_RETRY_BUDGET_SECONDS: "18000"' in workflow + assert 'OPENCODE_BACKOFF_MAX_SECONDS: "600"' in workflow + assert 'jq -s "$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