[INFO] fetching crate llm-test-bench-datasets 0.1.0... [INFO] testing llm-test-bench-datasets-0.1.0 against master#562dee4820c458d823175268e41601d4c060588a for pr-154210-1 [INFO] extracting crate llm-test-bench-datasets 0.1.0 into /workspace/builds/worker-1-tc1/source [INFO] started tweaking crates.io crate llm-test-bench-datasets 0.1.0 [INFO] finished tweaking crates.io crate llm-test-bench-datasets 0.1.0 [INFO] tweaked toml for crates.io crate llm-test-bench-datasets 0.1.0 written to /workspace/builds/worker-1-tc1/source/Cargo.toml [INFO] validating manifest of crates.io crate llm-test-bench-datasets 0.1.0 on toolchain 562dee4820c458d823175268e41601d4c060588a [INFO] running `Command { std: CARGO_HOME="/workspace/cargo-home" RUSTUP_HOME="/workspace/rustup-home" "/workspace/cargo-home/bin/cargo" "+562dee4820c458d823175268e41601d4c060588a" "metadata" "--manifest-path" "Cargo.toml" "--no-deps", kill_on_drop: false }` [INFO] crate crates.io crate llm-test-bench-datasets 0.1.0 already has a lockfile, it will not be regenerated [INFO] running `Command { std: CARGO_HOME="/workspace/cargo-home" RUSTUP_HOME="/workspace/rustup-home" "/workspace/cargo-home/bin/cargo" "+562dee4820c458d823175268e41601d4c060588a" "fetch" "--manifest-path" "Cargo.toml", kill_on_drop: false }` [INFO] [stderr] Blocking waiting for file lock on package cache [INFO] [stderr] Updating crates.io index [INFO] [stderr] Blocking waiting for file lock on package cache [INFO] [stderr] Downloading crates ... [INFO] [stderr] Downloaded serde_yaml v0.9.34+deprecated [INFO] [stderr] Downloaded dirs v5.0.1 [INFO] [stderr] Downloaded dirs-sys v0.4.1 [INFO] [stderr] Downloaded option-ext v0.2.0 [INFO] [stderr] Downloaded redox_users v0.4.6 [INFO] [stderr] Downloaded serde_valid v0.18.0 [INFO] [stderr] Downloaded unsafe-libyaml v0.2.11 [INFO] [stderr] Downloaded serde_valid_derive v0.18.0 [INFO] [stderr] Downloaded quote v1.0.41 [INFO] [stderr] Downloaded serde_valid_literal v0.18.0 [INFO] [stderr] Downloaded itertools v0.12.1 [INFO] [stderr] Downloaded syn v2.0.108 [INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-1-tc1/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-1-tc1/source:/opt/rustwide/workdir:ro,Z" "-v" "/var/lib/crater-agent-workspace/cargo-home:/opt/rustwide/cargo-home:ro,Z" "-v" "/var/lib/crater-agent-workspace/rustup-home:/opt/rustwide/rustup-home:ro,Z" "-e" "SOURCE_DIR=/opt/rustwide/workdir" "-e" "CARGO_TARGET_DIR=/opt/rustwide/target" "-e" "CARGO_HOME=/opt/rustwide/cargo-home" "-e" "RUSTUP_HOME=/opt/rustwide/rustup-home" "-w" "/opt/rustwide/workdir" "-m" "1610612736" "--user" "0:0" "--network" "none" "ghcr.io/rust-lang/crates-build-env/linux@sha256:d429b63d4308055ea97f60fb1d3dfca48854a00942f1bd2ad806beaf015945ec" "/opt/rustwide/cargo-home/bin/cargo" "+562dee4820c458d823175268e41601d4c060588a" "metadata" "--no-deps" "--format-version=1", kill_on_drop: false }` [INFO] [stdout] 7ba736a950e63ed015a3c3b61386c6b819f24cae3808519c6a3e91754c7d7f4e [INFO] running `Command { std: "docker" "start" "-a" "7ba736a950e63ed015a3c3b61386c6b819f24cae3808519c6a3e91754c7d7f4e", kill_on_drop: false }` [INFO] running `Command { std: "docker" "inspect" "7ba736a950e63ed015a3c3b61386c6b819f24cae3808519c6a3e91754c7d7f4e", kill_on_drop: false }` [INFO] running `Command { std: "docker" "rm" "-f" "7ba736a950e63ed015a3c3b61386c6b819f24cae3808519c6a3e91754c7d7f4e", kill_on_drop: false }` [INFO] [stdout] 7ba736a950e63ed015a3c3b61386c6b819f24cae3808519c6a3e91754c7d7f4e [INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-1-tc1/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-1-tc1/source:/opt/rustwide/workdir:ro,Z" "-v" "/var/lib/crater-agent-workspace/cargo-home:/opt/rustwide/cargo-home:ro,Z" "-v" "/var/lib/crater-agent-workspace/rustup-home:/opt/rustwide/rustup-home:ro,Z" "-e" "SOURCE_DIR=/opt/rustwide/workdir" "-e" "CARGO_TARGET_DIR=/opt/rustwide/target" "-e" "CARGO_INCREMENTAL=0" "-e" "RUST_BACKTRACE=full" "-e" "RUSTFLAGS=--cap-lints=forbid" "-e" "RUSTDOCFLAGS=--cap-lints=forbid" "-e" "CARGO_HOME=/opt/rustwide/cargo-home" "-e" "RUSTUP_HOME=/opt/rustwide/rustup-home" "-w" "/opt/rustwide/workdir" "-m" "1610612736" "--user" "0:0" "--network" "none" "ghcr.io/rust-lang/crates-build-env/linux@sha256:d429b63d4308055ea97f60fb1d3dfca48854a00942f1bd2ad806beaf015945ec" "/opt/rustwide/cargo-home/bin/cargo" "+562dee4820c458d823175268e41601d4c060588a" "build" "--frozen" "--message-format=json", kill_on_drop: false }` [INFO] [stdout] fab833a8ac3d36d016e77caecaed8f68126ee5a1280549d8571c4da863209b08 [INFO] running `Command { std: "docker" "start" "-a" "fab833a8ac3d36d016e77caecaed8f68126ee5a1280549d8571c4da863209b08", kill_on_drop: false }` [INFO] [stderr] Compiling syn v1.0.109 [INFO] [stderr] Compiling hashbrown v0.16.0 [INFO] [stderr] Compiling proc-macro-error v1.0.4 [INFO] [stderr] Compiling aho-corasick v1.1.4 [INFO] [stderr] Compiling syn v2.0.108 [INFO] [stderr] Compiling proc-macro-error-attr v1.0.4 [INFO] [stderr] Compiling dirs-sys v0.4.1 [INFO] [stderr] Compiling dirs v5.0.1 [INFO] [stderr] Compiling indexmap v2.12.0 [INFO] [stderr] Compiling regex-automata v0.4.13 [INFO] [stderr] Compiling regex v1.12.2 [INFO] [stderr] Compiling serde_valid_literal v0.18.0 [INFO] [stderr] Compiling serde_derive v1.0.228 [INFO] [stderr] Compiling thiserror-impl v1.0.69 [INFO] [stderr] Compiling tracing-attributes v0.1.30 [INFO] [stderr] Compiling serde_valid_derive v0.18.0 [INFO] [stderr] Compiling tracing v0.1.41 [INFO] [stderr] Compiling thiserror v1.0.69 [INFO] [stderr] Compiling serde v1.0.228 [INFO] [stderr] Compiling serde_yaml v0.9.34+deprecated [INFO] [stderr] Compiling serde_valid v0.18.0 [INFO] [stderr] Compiling llm-test-bench-datasets v0.1.0 (/opt/rustwide/workdir) [INFO] [stderr] Finished `dev` profile [unoptimized + debuginfo] target(s) in 16.75s [INFO] running `Command { std: "docker" "inspect" "fab833a8ac3d36d016e77caecaed8f68126ee5a1280549d8571c4da863209b08", kill_on_drop: false }` [INFO] running `Command { std: "docker" "rm" "-f" "fab833a8ac3d36d016e77caecaed8f68126ee5a1280549d8571c4da863209b08", kill_on_drop: false }` [INFO] [stdout] fab833a8ac3d36d016e77caecaed8f68126ee5a1280549d8571c4da863209b08 [INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-1-tc1/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-1-tc1/source:/opt/rustwide/workdir:ro,Z" "-v" "/var/lib/crater-agent-workspace/cargo-home:/opt/rustwide/cargo-home:ro,Z" "-v" "/var/lib/crater-agent-workspace/rustup-home:/opt/rustwide/rustup-home:ro,Z" "-e" "SOURCE_DIR=/opt/rustwide/workdir" "-e" "CARGO_TARGET_DIR=/opt/rustwide/target" "-e" "CARGO_INCREMENTAL=0" "-e" "RUST_BACKTRACE=full" "-e" "RUSTFLAGS=--cap-lints=forbid" "-e" "RUSTDOCFLAGS=--cap-lints=forbid" "-e" "CARGO_HOME=/opt/rustwide/cargo-home" "-e" "RUSTUP_HOME=/opt/rustwide/rustup-home" "-w" "/opt/rustwide/workdir" "-m" "1610612736" "--user" "0:0" "--network" "none" "ghcr.io/rust-lang/crates-build-env/linux@sha256:d429b63d4308055ea97f60fb1d3dfca48854a00942f1bd2ad806beaf015945ec" "/opt/rustwide/cargo-home/bin/cargo" "+562dee4820c458d823175268e41601d4c060588a" "test" "--frozen" "--no-run" "--message-format=json", kill_on_drop: false }` [INFO] [stdout] 17c12a6dd096b01e8a15a6c8fe2012d6c5a62a8207ffda8a9961d5b2defb3633 [INFO] running `Command { std: "docker" "start" "-a" "17c12a6dd096b01e8a15a6c8fe2012d6c5a62a8207ffda8a9961d5b2defb3633", kill_on_drop: false }` [INFO] [stderr] Compiling rustix v1.1.2 [INFO] [stderr] Compiling tempfile v3.23.0 [INFO] [stderr] Compiling llm-test-bench-datasets v0.1.0 (/opt/rustwide/workdir) [INFO] [stderr] Finished `test` profile [unoptimized + debuginfo] target(s) in 5.53s [INFO] running `Command { std: "docker" "inspect" "17c12a6dd096b01e8a15a6c8fe2012d6c5a62a8207ffda8a9961d5b2defb3633", kill_on_drop: false }` [INFO] running `Command { std: "docker" "rm" "-f" "17c12a6dd096b01e8a15a6c8fe2012d6c5a62a8207ffda8a9961d5b2defb3633", kill_on_drop: false }` [INFO] [stdout] 17c12a6dd096b01e8a15a6c8fe2012d6c5a62a8207ffda8a9961d5b2defb3633 [INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-1-tc1/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-1-tc1/source:/opt/rustwide/workdir:ro,Z" "-v" "/var/lib/crater-agent-workspace/cargo-home:/opt/rustwide/cargo-home:ro,Z" "-v" "/var/lib/crater-agent-workspace/rustup-home:/opt/rustwide/rustup-home:ro,Z" "-e" "SOURCE_DIR=/opt/rustwide/workdir" "-e" "CARGO_TARGET_DIR=/opt/rustwide/target" "-e" "CARGO_INCREMENTAL=0" "-e" "RUST_BACKTRACE=full" "-e" "RUSTFLAGS=--cap-lints=forbid" "-e" "RUSTDOCFLAGS=--cap-lints=forbid" "-e" "CARGO_HOME=/opt/rustwide/cargo-home" "-e" "RUSTUP_HOME=/opt/rustwide/rustup-home" "-w" "/opt/rustwide/workdir" "-m" "1610612736" "--user" "0:0" "--network" "none" "ghcr.io/rust-lang/crates-build-env/linux@sha256:d429b63d4308055ea97f60fb1d3dfca48854a00942f1bd2ad806beaf015945ec" "/opt/rustwide/cargo-home/bin/cargo" "+562dee4820c458d823175268e41601d4c060588a" "test" "--frozen", kill_on_drop: false }` [INFO] [stdout] 37e276884004e5b1c3d414082d6b354ffaf95eddfcecc6f6d8746cad16b37aef [INFO] running `Command { std: "docker" "start" "-a" "37e276884004e5b1c3d414082d6b354ffaf95eddfcecc6f6d8746cad16b37aef", kill_on_drop: false }` [INFO] [stderr] Finished `test` profile [unoptimized + debuginfo] target(s) in 0.14s [INFO] [stderr] Running unittests src/lib.rs (/opt/rustwide/target/debug/deps/llm_test_bench_datasets-dc69d7b228d42a58) [INFO] [stdout] [INFO] [stdout] running 46 tests [INFO] [stdout] test builtin::tests::test_creative_writing ... ok [INFO] [stdout] test builtin::tests::test_coding_tasks ... ok [INFO] [stdout] test builtin::tests::test_reasoning_tasks ... ok [INFO] [stdout] test schema::tests::test_dataset_creation ... ok [INFO] [stdout] test schema::tests::test_dataset_validation_empty_name ... ok [INFO] [stdout] test schema::tests::test_dataset_validation_valid ... ok [INFO] [stdout] test schema::tests::test_dataset_validation_no_test_cases ... ok [INFO] [stdout] test builtin::tests::test_instruction_following ... ok [INFO] [stdout] test loader::tests::test_dataset_loader_creation ... ok [INFO] [stdout] test builtin::tests::test_summarization_tasks ... ok [INFO] [stdout] test builtin::tests::test_get_builtin_datasets ... ok [INFO] [stdout] test schema::tests::test_default_config ... ok [INFO] [stdout] test schema::tests::test_test_case_creation ... ok [INFO] [stdout] test schema::tests::test_test_config ... ok [INFO] [stdout] test schema::tests::test_test_case_with_variables ... ok [INFO] [stdout] test schema::tests::test_filter_by_category ... ok [INFO] [stdout] test loader::tests::test_save_and_load_dataset ... ok [INFO] [stdout] test builtin::tests::test_all_datasets_valid ... ok [INFO] [stdout] test tests::integration_tests::test_dataset_filter_by_category ... ok [INFO] [stdout] test tests::integration_tests::test_dataset_len_and_is_empty ... ok [INFO] [stdout] test tests::integration_tests::test_dataset_serialization_json ... ok [INFO] [stdout] test tests::integration_tests::test_load_yaml_dataset_file ... ok [INFO] [stdout] test tests::integration_tests::test_dataset_serialization_yaml ... ok [INFO] [stdout] test tests::integration_tests::test_loader_without_validation ... ok [INFO] [stdout] test template::tests::test_has_variables ... ok [INFO] [stdout] test tests::integration_tests::test_dataset_with_defaults ... ok [INFO] [stdout] test tests::integration_tests::test_load_json_dataset_file ... ok [INFO] [stdout] test template::tests::test_render_missing_variable ... ok [INFO] [stdout] test tests::integration_tests::test_dataset_with_metadata ... ok [INFO] [stdout] test template::tests::test_render_same_variable_multiple_times ... ok [INFO] [stdout] test tests::integration_tests::test_save_and_load_round_trip ... ok [INFO] [stdout] test tests::integration_tests::test_template_has_variables ... ok [INFO] [stdout] test tests::integration_tests::test_render_optional_requires_variables ... ok [INFO] [stdout] test template::tests::test_render_no_variables ... ok [INFO] [stdout] test template::tests::test_render_simple ... ok [INFO] [stdout] test tests::integration_tests::test_template_validation ... ok [INFO] [stdout] test tests::integration_tests::test_test_case_with_config ... ok [INFO] [stdout] test tests::integration_tests::test_multiple_variable_substitution ... ok [INFO] [stdout] test tests::integration_tests::test_render_optional_with_no_template ... ok [INFO] [stdout] test template::tests::test_extract_variables ... ok [INFO] [stdout] test template::tests::test_extract_variables_duplicate ... ok [INFO] [stdout] test template::tests::test_render_multiple_variables ... ok [INFO] [stdout] test template::tests::test_extract_variables_none ... ok [INFO] [stdout] test tests::integration_tests::test_template_rendering_in_dataset ... ok [INFO] [stdout] test tests::integration_tests::test_template_variables_extraction ... ok [INFO] [stderr] Doc-tests llm_test_bench_datasets [INFO] [stdout] test tests::integration_tests::test_builtin_datasets_load_successfully ... ok [INFO] [stdout] [INFO] [stdout] test result: ok. 46 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.34s [INFO] [stdout] [INFO] [stdout] [INFO] [stdout] running 9 tests [INFO] [stdout] test src/loader.rs - loader::DatasetLoader::load (line 31) - compile ... ok [INFO] [stdout] test src/lib.rs - (line 29) - compile ... ok [INFO] [stdout] test src/builtin.rs - builtin::get_builtin_datasets (line 29) ... ok [INFO] [stdout] test src/schema.rs - schema::Dataset::new (line 157) ... ok [INFO] [stdout] test src/schema.rs - schema::TestCase::new (line 216) ... ok [INFO] [stdout] test src/schema.rs - schema::Dataset (line 21) ... ok [INFO] [stdout] test src/template.rs - template::TemplateEngine::extract_variables (line 74) ... ok [INFO] [stdout] test src/builtin.rs - builtin::coding_tasks (line 52) ... ok [INFO] [stdout] test src/template.rs - template::TemplateEngine::render (line 28) ... ok [INFO] [stdout] [INFO] [stdout] test result: ok. 9 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 1.43s [INFO] [stdout] [INFO] running `Command { std: "docker" "inspect" "37e276884004e5b1c3d414082d6b354ffaf95eddfcecc6f6d8746cad16b37aef", kill_on_drop: false }` [INFO] running `Command { std: "docker" "rm" "-f" "37e276884004e5b1c3d414082d6b354ffaf95eddfcecc6f6d8746cad16b37aef", kill_on_drop: false }` [INFO] [stdout] 37e276884004e5b1c3d414082d6b354ffaf95eddfcecc6f6d8746cad16b37aef