[INFO] fetching crate llm-test-bench-datasets 0.1.0... [INFO] testing llm-test-bench-datasets-0.1.0 against try#dec9417b8611e34e787a3e4c37686b5131f9e5c5 for pr-154210-1 [INFO] extracting crate llm-test-bench-datasets 0.1.0 into /workspace/builds/worker-1-tc2/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-tc2/source/Cargo.toml [INFO] validating manifest of crates.io crate llm-test-bench-datasets 0.1.0 on toolchain dec9417b8611e34e787a3e4c37686b5131f9e5c5 [INFO] running `Command { std: CARGO_HOME="/workspace/cargo-home" RUSTUP_HOME="/workspace/rustup-home" "/workspace/cargo-home/bin/cargo" "+dec9417b8611e34e787a3e4c37686b5131f9e5c5" "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" "+dec9417b8611e34e787a3e4c37686b5131f9e5c5" "fetch" "--manifest-path" "Cargo.toml", kill_on_drop: false }` [INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-1-tc2/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-1-tc2/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" "+dec9417b8611e34e787a3e4c37686b5131f9e5c5" "metadata" "--no-deps" "--format-version=1", kill_on_drop: false }` [INFO] [stdout] 5e75617c96a3314bae09183b53d9a7c9f8a1afed7072a9060830c81357216f5e [INFO] running `Command { std: "docker" "start" "-a" "5e75617c96a3314bae09183b53d9a7c9f8a1afed7072a9060830c81357216f5e", kill_on_drop: false }` [INFO] running `Command { std: "docker" "inspect" "5e75617c96a3314bae09183b53d9a7c9f8a1afed7072a9060830c81357216f5e", kill_on_drop: false }` [INFO] running `Command { std: "docker" "rm" "-f" "5e75617c96a3314bae09183b53d9a7c9f8a1afed7072a9060830c81357216f5e", kill_on_drop: false }` [INFO] [stdout] 5e75617c96a3314bae09183b53d9a7c9f8a1afed7072a9060830c81357216f5e [INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-1-tc2/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-1-tc2/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" "+dec9417b8611e34e787a3e4c37686b5131f9e5c5" "build" "--frozen" "--message-format=json", kill_on_drop: false }` [INFO] [stdout] e8c6769de9452bfce113940da9ff18f1f0da5d36a8e2374a3c72bfbe17610567 [INFO] running `Command { std: "docker" "start" "-a" "e8c6769de9452bfce113940da9ff18f1f0da5d36a8e2374a3c72bfbe17610567", kill_on_drop: false }` [INFO] [stderr] Compiling proc-macro2 v1.0.103 [INFO] [stderr] Compiling unicode-ident v1.0.22 [INFO] [stderr] Compiling quote v1.0.41 [INFO] [stderr] Compiling version_check v0.9.5 [INFO] [stderr] Compiling serde_core v1.0.228 [INFO] [stderr] Compiling memchr v2.7.6 [INFO] [stderr] Compiling syn v1.0.109 [INFO] [stderr] Compiling paste v1.0.15 [INFO] [stderr] Compiling regex-syntax v0.8.8 [INFO] [stderr] Compiling libc v0.2.177 [INFO] [stderr] Compiling serde v1.0.228 [INFO] [stderr] Compiling autocfg v1.5.0 [INFO] [stderr] Compiling thiserror v1.0.69 [INFO] [stderr] Compiling equivalent v1.0.2 [INFO] [stderr] Compiling serde_json v1.0.145 [INFO] [stderr] Compiling itoa v1.0.15 [INFO] [stderr] Compiling hashbrown v0.16.0 [INFO] [stderr] Compiling once_cell v1.21.3 [INFO] [stderr] Compiling ryu v1.0.20 [INFO] [stderr] Compiling option-ext v0.2.0 [INFO] [stderr] Compiling proc-macro-error-attr v1.0.4 [INFO] [stderr] Compiling proc-macro-error v1.0.4 [INFO] [stderr] Compiling either v1.15.0 [INFO] [stderr] Compiling anyhow v1.0.100 [INFO] [stderr] Compiling strsim v0.11.1 [INFO] [stderr] Compiling tracing-core v0.1.34 [INFO] [stderr] Compiling unicode-segmentation v1.12.0 [INFO] [stderr] Compiling pin-project-lite v0.2.16 [INFO] [stderr] Compiling num-traits v0.2.19 [INFO] [stderr] Compiling aho-corasick v1.1.4 [INFO] [stderr] Compiling unsafe-libyaml v0.2.11 [INFO] [stderr] Compiling itertools v0.12.1 [INFO] [stderr] Compiling syn v2.0.108 [INFO] [stderr] Compiling dirs-sys v0.4.1 [INFO] [stderr] Compiling dirs v5.0.1 [INFO] [stderr] Compiling regex-automata v0.4.13 [INFO] [stderr] Compiling indexmap v2.12.0 [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 serde_valid v0.18.0 [INFO] [stderr] Compiling serde_yaml v0.9.34+deprecated [INFO] [stderr] Compiling llm-test-bench-datasets v0.1.0 (/opt/rustwide/workdir) [INFO] [stderr] Finished `dev` profile [unoptimized + debuginfo] target(s) in 27.90s [INFO] running `Command { std: "docker" "inspect" "e8c6769de9452bfce113940da9ff18f1f0da5d36a8e2374a3c72bfbe17610567", kill_on_drop: false }` [INFO] running `Command { std: "docker" "rm" "-f" "e8c6769de9452bfce113940da9ff18f1f0da5d36a8e2374a3c72bfbe17610567", kill_on_drop: false }` [INFO] [stdout] e8c6769de9452bfce113940da9ff18f1f0da5d36a8e2374a3c72bfbe17610567 [INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-1-tc2/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-1-tc2/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" "+dec9417b8611e34e787a3e4c37686b5131f9e5c5" "test" "--frozen" "--no-run" "--message-format=json", kill_on_drop: false }` [INFO] [stdout] 8c96ce0d0de3b3cde9a14d28fa977ef4bc5187b677fa193662871061c8ac00dd [INFO] running `Command { std: "docker" "start" "-a" "8c96ce0d0de3b3cde9a14d28fa977ef4bc5187b677fa193662871061c8ac00dd", kill_on_drop: false }` [INFO] [stderr] Compiling rustix v1.1.2 [INFO] [stderr] Compiling getrandom v0.3.4 [INFO] [stderr] Compiling bitflags v2.10.0 [INFO] [stderr] Compiling cfg-if v1.0.4 [INFO] [stderr] Compiling linux-raw-sys v0.11.0 [INFO] [stderr] Compiling fastrand v2.3.0 [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 4.36s [INFO] running `Command { std: "docker" "inspect" "8c96ce0d0de3b3cde9a14d28fa977ef4bc5187b677fa193662871061c8ac00dd", kill_on_drop: false }` [INFO] running `Command { std: "docker" "rm" "-f" "8c96ce0d0de3b3cde9a14d28fa977ef4bc5187b677fa193662871061c8ac00dd", kill_on_drop: false }` [INFO] [stdout] 8c96ce0d0de3b3cde9a14d28fa977ef4bc5187b677fa193662871061c8ac00dd [INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-1-tc2/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-1-tc2/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" "+dec9417b8611e34e787a3e4c37686b5131f9e5c5" "test" "--frozen", kill_on_drop: false }` [INFO] [stdout] 37f364d09c5f6fd661d65169bfb7e58fbf3b9e0cf3b6aed3f9f7b33a0c6c0cc1 [INFO] running `Command { std: "docker" "start" "-a" "37f364d09c5f6fd661d65169bfb7e58fbf3b9e0cf3b6aed3f9f7b33a0c6c0cc1", kill_on_drop: false }` [INFO] [stderr] Finished `test` profile [unoptimized + debuginfo] target(s) in 0.11s [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_get_builtin_datasets ... ok [INFO] [stdout] test builtin::tests::test_coding_tasks ... ok [INFO] [stdout] test builtin::tests::test_all_datasets_valid ... ok [INFO] [stdout] test builtin::tests::test_instruction_following ... ok [INFO] [stdout] test builtin::tests::test_reasoning_tasks ... ok [INFO] [stdout] test builtin::tests::test_summarization_tasks ... ok [INFO] [stdout] test loader::tests::test_dataset_loader_creation ... 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_no_test_cases ... ok [INFO] [stdout] test schema::tests::test_dataset_validation_valid ... ok [INFO] [stdout] test schema::tests::test_default_config ... ok [INFO] [stdout] test schema::tests::test_filter_by_category ... ok [INFO] [stdout] test schema::tests::test_test_case_creation ... ok [INFO] [stdout] test schema::tests::test_test_case_with_variables ... ok [INFO] [stdout] test schema::tests::test_test_config ... ok [INFO] [stdout] test tests::integration_tests::test_dataset_filter_by_category ... ok [INFO] [stdout] test template::tests::test_has_variables ... ok [INFO] [stdout] test tests::integration_tests::test_load_json_dataset_file ... ok [INFO] [stdout] test tests::integration_tests::test_dataset_len_and_is_empty ... ok [INFO] [stdout] test tests::integration_tests::test_load_yaml_dataset_file ... ok [INFO] [stdout] test tests::integration_tests::test_dataset_with_defaults ... ok [INFO] [stdout] test tests::integration_tests::test_dataset_with_metadata ... ok [INFO] [stdout] test tests::integration_tests::test_dataset_serialization_json ... ok [INFO] [stdout] test tests::integration_tests::test_dataset_serialization_yaml ... ok [INFO] [stdout] test loader::tests::test_save_and_load_dataset ... ok [INFO] [stdout] test tests::integration_tests::test_loader_without_validation ... ok [INFO] [stdout] test tests::integration_tests::test_template_has_variables ... ok [INFO] [stdout] test tests::integration_tests::test_save_and_load_round_trip ... ok [INFO] [stdout] test template::tests::test_extract_variables_none ... ok [INFO] [stdout] test template::tests::test_render_no_variables ... 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 template::tests::test_extract_variables_duplicate ... ok [INFO] [stdout] test template::tests::test_render_same_variable_multiple_times ... ok [INFO] [stdout] test template::tests::test_render_multiple_variables ... ok [INFO] [stdout] test tests::integration_tests::test_render_optional_requires_variables ... ok [INFO] [stdout] test tests::integration_tests::test_template_variables_extraction ... ok [INFO] [stdout] test template::tests::test_render_missing_variable ... ok [INFO] [stdout] test template::tests::test_extract_variables ... ok [INFO] [stdout] test tests::integration_tests::test_render_optional_with_no_template ... ok [INFO] [stdout] test tests::integration_tests::test_multiple_variable_substitution ... ok [INFO] [stdout] test template::tests::test_render_simple ... ok [INFO] [stdout] test tests::integration_tests::test_template_rendering_in_dataset ... ok [INFO] [stdout] test tests::integration_tests::test_builtin_datasets_load_successfully ... ok [INFO] [stderr] Doc-tests llm_test_bench_datasets [INFO] [stdout] [INFO] [stdout] test result: ok. 46 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.22s [INFO] [stdout] [INFO] [stdout] [INFO] [stdout] running 9 tests [INFO] [stdout] test src/lib.rs - (line 29) - compile ... ok [INFO] [stdout] test src/loader.rs - loader::DatasetLoader::load (line 31) - compile ... ok [INFO] [stdout] test src/schema.rs - schema::Dataset (line 21) ... ok [INFO] [stdout] test src/schema.rs - schema::TestCase::new (line 216) ... ok [INFO] [stdout] test src/schema.rs - schema::Dataset::new (line 157) ... ok [INFO] [stdout] test src/template.rs - template::TemplateEngine::render (line 28) ... ok [INFO] [stdout] test src/template.rs - template::TemplateEngine::extract_variables (line 74) ... ok [INFO] [stdout] test src/builtin.rs - builtin::get_builtin_datasets (line 29) ... ok [INFO] [stdout] test src/builtin.rs - builtin::coding_tasks (line 52) ... ok [INFO] [stdout] [INFO] [stdout] test result: ok. 9 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.71s [INFO] [stdout] [INFO] running `Command { std: "docker" "inspect" "37f364d09c5f6fd661d65169bfb7e58fbf3b9e0cf3b6aed3f9f7b33a0c6c0cc1", kill_on_drop: false }` [INFO] running `Command { std: "docker" "rm" "-f" "37f364d09c5f6fd661d65169bfb7e58fbf3b9e0cf3b6aed3f9f7b33a0c6c0cc1", kill_on_drop: false }` [INFO] [stdout] 37f364d09c5f6fd661d65169bfb7e58fbf3b9e0cf3b6aed3f9f7b33a0c6c0cc1