Skip to content

fix(review): Rust 1.97.1로 오프라인 커버리지 복구 #592

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 2 commits into
base: main
Choose a base branch
from
+66 −27
Open

fix(review): Rust 1.97.1로 오프라인 커버리지 복구 #592

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
065f531
fix(review): pin current Rust coverage toolchain
seonghobae Jul 19, 2026
137ff8b
fix(review): prevent model pool provider starvation
seonghobae Jul 19, 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
43 changes: 31 additions & 12 deletions .github/workflows/opencode-review.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -559,12 +559,14 @@ jobs:
install -m 0644 "$trusted_ci_requirements" \
"$coverage_build_dir/requirements-opencode-review-ci-hashes.txt"
cat >"$coverage_build_dir/Dockerfile" <<'DOCKERFILE'
FROM docker.io/library/ubuntu@sha256:52df9b1ee71626e0088f7d400d5c6b5f7bb916f8f0c82b474289a4ece6cf3faf
# Official Rust 1.97.1 linux/amd64 manifest. Pin the architecture
# manifest itself so the trusted build cannot drift across releases
# or platforms while retaining stable Rust 2024 support.
FROM docker.io/library/rust@sha256:389c1ae98c20fbcadca68a685482749267cec3c90893ae4671c5a37cc894c416
ENV DEBIAN_FRONTEND=noninteractive
RUN apt-get update \
&& apt-get install --no-install-recommends -y \
ca-certificates \
cargo \
curl \
git \
jq \
Expand All @@ -582,10 +584,14 @@ jobs:
r-base \
r-cran-covr \
r-cran-testthat \
rustc \
util-linux \
vulkan-tools \
&& rm -rf /var/lib/apt/lists/*
RUN test "$(rustc --version --verbose | sed -n 's/^release: //p')" = "1.97.1" \
&& rustup component add llvm-tools-preview \
&& rustup component list --installed | grep -Eq '^llvm-tools-' \
&& chown -R root:root /usr/local/rustup /usr/local/cargo \
&& chmod -R go-w /usr/local/rustup /usr/local/cargo
RUN curl --proto '=https' --tlsv1.2 -fsSLo /tmp/cargo-llvm-cov.tar.gz \
https://github.com/taiki-e/cargo-llvm-cov/releases/download/v0.8.7/cargo-llvm-cov-x86_64-unknown-linux-musl.tar.gz \
&& echo '967b5cc996c29d8baa52bbb4595ef1f53af35255af8e2036ddbc6468d7b523c7 /tmp/cargo-llvm-cov.tar.gz' | sha256sum -c - \
Expand Down Expand Up @@ -748,7 +754,8 @@ jobs:
HOME=/work/.opencode-sandbox-home \
XDG_CACHE_HOME=/work/.opencode-sandbox-cache \
CARGO_HOME=/work/.opencode-sandbox-home/.cargo \
PATH="/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin" \
RUSTUP_HOME=/usr/local/rustup \
PATH="/usr/local/cargo/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin" \
"$@" >"$log_file" 2>&1
local rc=$?
set -e
Expand Down Expand Up @@ -794,7 +801,8 @@ jobs:
HOME=/work/.opencode-sandbox-home \
XDG_CACHE_HOME=/work/.opencode-sandbox-cache \
CARGO_HOME=/work/.opencode-sandbox-home/.cargo \
PATH="/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin" \
RUSTUP_HOME=/usr/local/rustup \
PATH="/usr/local/cargo/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin" \
"$@" >"$log_file" 2>&1
local rc=$?
set -e
Expand Down Expand Up @@ -1333,6 +1341,13 @@ jobs:
failures=$((failures + 1))
return 1
fi
append "### Rust coverage toolchain"
append ""
append "- Result: PASS"
append "- Rust: \`$(rustc --version)\`"
append "- Cargo: \`$(cargo --version)\`"
append "- Coverage: \`$(cargo-llvm-cov --version)\`"
append ""
ensure_rust_gpu_adapter
ensure_rust_desktop_deps
}
Expand Down Expand Up @@ -3516,15 +3531,16 @@ jobs:
SHARE: "false"
NPM_CONFIG_IGNORE_SCRIPTS: "true"
NO_COLOR: "1"
# High-sensitivity review candidates only. DeepSeek V3 has been the
# most reliable first-pass reviewer in the org queue, then the pool
# falls through to the direct GPT-5.6 Luna slot, then the full-size
# GPT-4.1 long-context endpoint and provider-specific GPT/o3 fallbacks.
# High-sensitivity review candidates only. Start with the full-size
# GPT-4.1 long-context endpoint so one slow DeepSeek or direct-OpenAI
# request cannot consume nearly the entire bounded provider budget;
# then fall through to GPT-5.6 Luna, DeepSeek V3, and the remaining
# provider-specific GPT/o3 fallbacks.
# The direct-OpenAI slot runs GPT-5.6 Luna: the newest family's
# cost-efficient tier, cheaper than the legacy gpt-5 it replaced
# ($1/$6 vs $1.25/$10 per 1M tokens) so the org OpenAI budget
# stretches further between top-ups.
OPENCODE_MODEL_CANDIDATES: "github-models/deepseek/deepseek-v3-0324 openai/gpt-5.6-luna github-models/openai/gpt-4.1 github-models/openai/gpt-5 github-models/openai/gpt-5-chat github-models/openai/o3 github-models/deepseek/deepseek-r1-0528 github-models/deepseek/deepseek-r1"
OPENCODE_MODEL_CANDIDATES: "github-models/openai/gpt-4.1 openai/gpt-5.6-luna github-models/deepseek/deepseek-v3-0324 github-models/openai/gpt-5 github-models/openai/gpt-5-chat github-models/openai/o3 github-models/deepseek/deepseek-r1-0528 github-models/deepseek/deepseek-r1"
# One attempt per model, then fall through to the next model. Retrying
# the SAME model 5x let a rate-limited/hung leader consume the whole
# step, so the pool never reached a healthy fallback model.
Expand Down Expand Up @@ -3564,8 +3580,11 @@ jobs:
OPENCODE_DYNAMIC_MAX_CYCLES: "0"
CENTRAL_REVIEW_PROCESS_FALLBACK_ELIGIBLE: ${{ steps.central_review_process_fallback_scope.outputs.eligible || 'false' }}
CENTRAL_REVIEW_PROCESS_FALLBACK_SCOPE_LABEL: ${{ steps.central_review_process_fallback_scope.outputs.scope_label || 'unsupported' }}
OPENCODE_CENTRAL_REVIEW_PROCESS_FALLBACK_RUN_TIMEOUT_SECONDS: "5400"
OPENCODE_CENTRAL_REVIEW_PROCESS_FALLBACK_TOTAL_BUDGET_SECONDS: "11700"
# Central review-process changes are capped at three files above. A
# 15-minute candidate cap and one-hour pool budget keep one unavailable
# provider from starving every later real-model reviewer.
OPENCODE_CENTRAL_REVIEW_PROCESS_FALLBACK_RUN_TIMEOUT_SECONDS: "900"
OPENCODE_CENTRAL_REVIEW_PROCESS_FALLBACK_TOTAL_BUDGET_SECONDS: "3600"
OPENCODE_CENTRAL_REVIEW_PROCESS_FALLBACK_MAX_CYCLES: "1"
OPENCODE_BACKOFF_INITIAL_SECONDS: "30"
OPENCODE_BACKOFF_MAX_SECONDS: "30"
Expand Down
50 changes: 35 additions & 15 deletions tests/test_opencode_agent_contract.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,9 +103,9 @@ def test_opencode_model_pool_sets_high_effort_for_capable_candidates():

assert candidate_pairs
assert candidate_pairs == [
["github-models", "deepseek/deepseek-v3-0324"],
["openai", "gpt-5.6-luna"],
["github-models", "openai/gpt-4.1"],
["openai", "gpt-5.6-luna"],
["github-models", "deepseek/deepseek-v3-0324"],
["github-models", "openai/gpt-5"],
["github-models", "openai/gpt-5-chat"],
["github-models", "openai/o3"],
Expand All @@ -115,8 +115,8 @@ def test_opencode_model_pool_sets_high_effort_for_capable_candidates():
assert direct_openai_models == ["gpt-5.6-luna"]
assert set(github_candidate_models).issubset(set(github_models))
assert github_candidate_models == [
"deepseek/deepseek-v3-0324",
"openai/gpt-4.1",
"deepseek/deepseek-v3-0324",
"openai/gpt-5",
"openai/gpt-5-chat",
"openai/o3",
Expand Down Expand Up @@ -326,10 +326,25 @@ def test_opencode_target_coverage_materializes_only_after_authorized_dispatch():
assert "member.isfile() or member.isdir()" in workflow
assert 'bundle.extractall(destination, members=members, filter="data")' in workflow
assert 'tar -xf "$COVERAGE_SOURCE_ARCHIVE"' not in workflow
assert "docker.io/library/ubuntu@sha256:" in measure_step
assert (
"docker.io/library/rust@sha256:"
"389c1ae98c20fbcadca68a685482749267cec3c90893ae4671c5a37cc894c416"
in measure_step
)
assert 'test "$(rustc --version --verbose' in measure_step
assert '= "1.97.1"' in measure_step
assert "rustup component add llvm-tools-preview" in measure_step
assert "rustup component list --installed" in measure_step
assert "chown -R root:root /usr/local/rustup /usr/local/cargo" in measure_step
assert "chmod -R go-w /usr/local/rustup /usr/local/cargo" in measure_step
assert " cargo \\\n" not in measure_step
assert " rustc \\\n" not in measure_step
assert "apt-get install --no-install-recommends -y" in measure_step
assert "--require-hashes" in measure_step
assert 'coverage_tool_image="opencode-coverage-tools:${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}"' in measure_step
assert (
'coverage_tool_image="opencode-coverage-tools:${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}"'
in measure_step
)
assert "The networked build context contains only this" in measure_step
assert 'install -m 0644 "$trusted_ci_requirements"' in measure_step
assert "docker build --pull --no-cache --network=default" in measure_step
Expand Down Expand Up @@ -382,10 +397,15 @@ def test_opencode_target_coverage_materializes_only_after_authorized_dispatch():
assert "apt-get" not in sandbox_runtime
assert "cargo install" not in sandbox_runtime
assert "command -v cargo-llvm-cov" in sandbox_runtime
assert (
'PATH="/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"'
in measure_step
)
assert 'append "- Rust: \\`$(rustc --version)\\`"' in sandbox_runtime
assert 'append "- Cargo: \\`$(cargo --version)\\`"' in sandbox_runtime
assert 'append "- Coverage: \\`$(cargo-llvm-cov --version)\\`"' in sandbox_runtime
trusted_runtime_path = (
'PATH="/usr/local/cargo/bin:/usr/local/sbin:/usr/local/bin:'
'/usr/sbin:/usr/bin:/sbin:/bin"'
)
assert measure_step.count(trusted_runtime_path) == 2
assert measure_step.count("RUSTUP_HOME=/usr/local/rustup") == 2
assert 'PATH="/work/.opencode-sandbox-home/.cargo/bin:${PATH}"' not in measure_step
assert "cargo llvm-cov --version" not in measure_step
assert "emit_captured_log()" in measure_step
Expand Down Expand Up @@ -973,11 +993,11 @@ def test_workflow_provisions_sandbox_tool_and_reviewer_agent():
assert "CENTRAL_REVIEW_PROCESS_FALLBACK_ELIGIBLE" in workflow
assert "CENTRAL_REVIEW_PROCESS_FALLBACK_SCOPE_LABEL" in workflow
assert (
'OPENCODE_CENTRAL_REVIEW_PROCESS_FALLBACK_RUN_TIMEOUT_SECONDS: "5400"'
'OPENCODE_CENTRAL_REVIEW_PROCESS_FALLBACK_RUN_TIMEOUT_SECONDS: "900"'
in workflow
)
assert (
'OPENCODE_CENTRAL_REVIEW_PROCESS_FALLBACK_TOTAL_BUDGET_SECONDS: "11700"'
'OPENCODE_CENTRAL_REVIEW_PROCESS_FALLBACK_TOTAL_BUDGET_SECONDS: "3600"'
in workflow
)
assert 'OPENCODE_CENTRAL_REVIEW_PROCESS_FALLBACK_MAX_CYCLES: "1"' in workflow
Expand Down Expand Up @@ -1090,9 +1110,9 @@ def test_workflow_provisions_sandbox_tool_and_reviewer_agent():
in workflow
)
assert (
'OPENCODE_MODEL_CANDIDATES: "github-models/deepseek/deepseek-v3-0324 '
'OPENCODE_MODEL_CANDIDATES: "github-models/openai/gpt-4.1 '
"openai/gpt-5.6-luna "
"github-models/openai/gpt-4.1 "
"github-models/deepseek/deepseek-v3-0324 "
"github-models/openai/gpt-5 "
"github-models/openai/gpt-5-chat "
"github-models/openai/o3 "
Expand Down Expand Up @@ -1213,9 +1233,9 @@ def test_workflow_provisions_sandbox_tool_and_reviewer_agent():
'OPENCODE_MODEL_CANDIDATES: "github-models/openai/gpt-5-nano"' not in workflow
)
assert (
'OPENCODE_MODEL_CANDIDATES: "github-models/deepseek/deepseek-v3-0324 '
'OPENCODE_MODEL_CANDIDATES: "github-models/openai/gpt-4.1 '
"openai/gpt-5.6-luna "
"github-models/openai/gpt-4.1 "
"github-models/deepseek/deepseek-v3-0324 "
"github-models/openai/gpt-5 "
"github-models/openai/gpt-5-chat "
"github-models/openai/o3 "
Expand Down
Loading