⚡ Vectorize Loop over Dimensions in Initial Parameters#18
Conversation
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
OpenCode Review Overview
Pull request overviewOpenCode reviewed the current-head bounded evidence and found no blocking issues. FindingsNo blocking findings. SummaryApproval sufficiency: bounded evidence supplied affirmative approval evidence for changed files, coverage/docstring posture, risk surfaces, and current-head verification; approval is not based merely on the absence of known blockers.
Changed-File Evidence Mapflowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Changed file (10 files)"]
S1 --> I1["repository behavior"]
I1 --> R1["Review risk: Changed file (10 files)"]
R1 --> V1["required checks"]
Evidence --> S2["Workflow (2 files)"]
S2 --> I2["GitHub Actions review job"]
I2 --> R2["Review risk: Workflow (2 files)"]
R2 --> V2["actionlint plus required checks"]
Evidence --> S3["Test: test_initial_params.py"]
S3 --> I3["regression suite"]
I3 --> R3["Review risk: Test: test_initial_params.py"]
R3 --> V3["targeted test run"]
|
![opencode-agent[bot]](https://avatars.githubusercontent.com/in/1549082?s=60&v=4){kind=small}
There was a problem hiding this comment.
Pull request overview
OpenCode reviewed the current-head bounded evidence and found no blocking issues.
Findings
No blocking findings.
Summary
Added performance optimization notes to documentation. Verification posture: Linter/static: N/A (docs); TDD/regression: N/A (docs); Coverage: N/A (docs); Docstring coverage: N/A; DAG: Documentation["bolt.md"] --> KnowledgeBase["Performance Tips"]; PoC/execution: N/A; DDD/domain: Consistent with ML optimization patterns; CDD/context: Matches repository's technical notes style; Similar issues: N/A; Claim/concept check: Valid NumPy vectorization technique; Standards search: Matches NumPy best practices; Compatibility/convention: Follows existing documentation style; Breaking-change/backcompat: N/A; Performance: Documents optimization technique; Developer experience: Improves knowledge sharing; User experience: N/A; Security/privacy: N/A.
Verification posture: CodeGraph evidence was initialized and bounded current-head evidence reviewed for changed-file evidence including .jules/bolt.md.
Linter/static: workflow/static review evidence is bounded by the current-head GitHub Checks gate and changed-file evidence.
TDD/regression: coverage execution evidence and focused changed hunks were reviewed from bounded-review-evidence.md.
Coverage: coverage execution evidence reports test coverage as not applicable because no supported changed source files or package manifests were found.
Docstring coverage: coverage execution evidence reports docstring coverage as not applicable because no supported changed source files or package manifests were found.
DAG: Change Flow DAG maps .jules/bolt.md through bounded evidence, review risk, and required checks.
PoC/execution: coverage-evidence job executed on the current head and reported PASS.
DDD/domain: workflow and repository-governance invariants were reviewed against changed files in bounded evidence.
CDD/context: CodeGraph evidence, changed-file history, and focused hunks were reviewed from bounded-review-evidence.md.
Similar issues: changed-file history evidence was reviewed for comparable local precedents.
Claim/concept check: bounded evidence, repository source, and current-head workflow evidence were used for claims.
Standards search: standards and external-source checks are delegated to configured OpenCode web_search/Context7/DeepWiki sources when applicable; no evidence-backed standards blocker is present in bounded evidence.
Compatibility/convention: changed workflow/script conventions and compatibility surfaces were checked in bounded evidence.
Breaking-change/backcompat: deployment evidence and changed-file history were checked for backward-compatibility risk.
Performance: changed surfaces were checked for performance risk in bounded evidence.
Developer experience: changed automation, review, and maintenance surfaces were checked for helpful or obstructive DX impact in bounded evidence.
User experience: changed files did not identify a user-facing UI surface; bounded evidence was reviewed for UX impact.
Security/privacy: workflow-token, review-gate, and repository-automation security/privacy boundaries were checked in bounded evidence.
- Result: APPROVE
- Reason: Documentation-only change with valid technical content
- Head SHA:
6185a1bf892a24b738797827ceb04411139d527b - Workflow run: 28382249322
- Workflow attempt: 1
Change Flow DAG
flowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Changed file: bolt.md"]
S1 --> I1["repository behavior"]
I1 --> R1["Review risk: Changed file: bolt.md"]
R1 --> V1["required checks"]
|
@copilot resolve the merge conflicts in this pull request |
Merge conflicts resolved. The only conflict was in |
There was a problem hiding this comment.
Pull request overview
Note
Copilot couldn't run its full agentic review because no GitHub Actions runner was available. Make sure your repository has a runner available to run Copilot's review, or add a copilot-setup-steps.yml file specifying one with the runs-on attribute. See the docs for more details.
This PR substantially simplifies the Python package surface by removing the Rust/PyO3 objective backend and a large set of CLI/diagnostics/reporting utilities, while also changing packaging and CI to a pure-setuptools + Rust-crate-test workflow.
Changes:
- Removed the Python Rust-backend integration (backend resolver, PyO3 core bindings, backend selection fields/args) and related parity tests.
- Removed diagnostics/report generation scripts, CLI subcommands, and many associated tests/docs.
- Switched packaging from
maturintosetuptoolsand reduced GitHub Actions CI to onlycargo test.
Reviewed changes
Copilot reviewed 73 out of 75 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
| tests/test_report.py | Removed diagnostics HTML report tests (file deleted). |
| tests/test_release_evidence_index.py | Removed release evidence index builder tests (file deleted). |
| tests/test_objective.py | Removed Rust parity + factor-id validation tests; appended new objective/penalty tests. |
| tests/test_math.py | Removed math function tests (file deleted). |
| tests/test_io.py | Removed IO tests for CSV/params loading (file deleted). |
| tests/test_fit_pipeline.py | Removed backend assertions and Rust backend tests. |
| tests/test_fit_dos.py | Removed DoS regression test for factor_id-derived dimensions (file deleted). |
| tests/test_diagnostics.py | Removed diagnostics API tests (file deleted). |
| tests/test_config.py | Removed config validation tests (file deleted). |
| tests/test_cli.py | Removed CLI behavior/error-handling/JSON-mode tests (file deleted). |
| tests/test_buyer_evidence_packet.py | Removed buyer packet script tests (file deleted). |
| tests/test_benchmark_report.py | Removed benchmark report script tests (file deleted). |
| tests/test_backend.py | Removed backend loader tests (file deleted). |
| scripts/release_acceptance.py | Removed release acceptance automation script (file deleted). |
| scripts/build_buyer_packet.py | Removed buyer evidence packet builder script (file deleted). |
| scripts/build_benchmark_report.py | Removed benchmark evidence builder script (file deleted). |
| python/fast_mlsirm/types.py | Removed FitResult.backend and deleted diagnostics dataclasses. |
| python/fast_mlsirm/report.py | Removed diagnostics HTML report renderer module (file deleted). |
| python/fast_mlsirm/objective.py | Removed Rust backend path; changed gradient and penalty implementations. |
| python/fast_mlsirm/math.py | Replaced sigmoid implementation with sign-split stable computation. |
| python/fast_mlsirm/io.py | Removed diagnostics save functions; rewrote factor CSV read/write. |
| python/fast_mlsirm/fit.py | Removed backend plumbing; inlined restart logic; removed DoS guard on n_dims. |
| python/fast_mlsirm/config.py | Removed backend config field and validation. |
| python/fast_mlsirm/cli.py | Removed JSON mode/error handling and most subcommands; simplified simulate/fit flow. |
| python/fast_mlsirm/backend.py | Removed backend resolution module (file deleted). |
| python/fast_mlsirm/init.py | Removed __version__ lookup and many public exports. |
| pyproject.toml | Switched build backend from maturin to setuptools; adjusted package discovery. |
| examples/rust_backend_smoke.py | Removed Rust-backend smoke example (file deleted). |
| examples/enterprise_demo/roi_manifest.json | Removed enterprise demo manifest (file deleted). |
| examples/enterprise_demo/product_completion_manifest.json | Removed enterprise completion manifest (file deleted). |
| examples/enterprise_demo/figma_design_packet.json | Removed figma packet manifest (file deleted). |
| examples/enterprise_demo/benchmark_manifest.json | Removed benchmark manifest (file deleted). |
| examples/enterprise_demo/README.md | Removed enterprise demo README (file deleted). |
| docs/superpowers/specs/2026-07-02-20b-release-evidence-index-design.md | Removed spec doc (file deleted). |
| docs/superpowers/specs/2026-07-02-20b-product-readiness-design.md | Removed spec doc (file deleted). |
| docs/superpowers/specs/2026-07-02-20b-buyer-evidence-packet-design.md | Removed spec doc (file deleted). |
| docs/superpowers/specs/2026-07-02-20b-buyer-evidence-html-review-design.md | Removed spec doc (file deleted). |
| docs/superpowers/specs/2026-07-02-20b-benchmark-evidence-design.md | Removed spec doc (file deleted). |
| docs/superpowers/plans/2026-07-02-20b-release-evidence-index.md | Removed plan doc (file deleted). |
| docs/superpowers/plans/2026-07-02-20b-product-readiness.md | Removed plan doc (file deleted). |
| docs/superpowers/plans/2026-07-02-20b-buyer-evidence-packet.md | Removed plan doc (file deleted). |
| docs/superpowers/plans/2026-07-02-20b-buyer-evidence-html-review.md | Removed plan doc (file deleted). |
| docs/superpowers/plans/2026-07-02-20b-benchmark-evidence.md | Removed plan doc (file deleted). |
| docs/roi_evidence_model.md | Removed ROI evidence documentation (file deleted). |
| docs/response_process_diagnostics_design.md | Removed response-process diagnostics design doc (file deleted). |
| docs/response_process_diagnostics.tex | Removed LaTeX diagnostics doc (file deleted). |
| docs/release_acceptance.md | Removed release acceptance guide (file deleted). |
| docs/prd_trd_summary.md | Updated docs to de-emphasize PyO3 backend and enterprise readiness tooling. |
| docs/pr25_formula_review.md | Removed PR25 review doc (file deleted). |
| docs/fit_diagnostics_plan.md | Removed fit diagnostics plan doc (file deleted). |
| docs/figma_product_design_packet.md | Removed Figma product design packet doc (file deleted). |
| docs/enterprise_sales_readiness.md | Removed enterprise sales readiness doc (file deleted). |
| docs/commercial_readiness.md | Removed commercial readiness doc (file deleted). |
| docs/buyer_demo_storyboard.md | Removed buyer storyboard doc (file deleted). |
| docs/20b_product_readiness.md | Removed 20b product readiness doc (file deleted). |
| crates/mlsirm-core/src/lib.rs | Minor loop refactor; removed two Rust unit tests. |
| crates/mlsirm-core/Cargo.toml | Removed crate metadata URLs. |
| crates/fast-mlsirm-py/src/lib.rs | Removed PyO3 binding crate (file deleted). |
| crates/fast-mlsirm-py/Cargo.toml | Removed PyO3 binding crate manifest (file deleted). |
| SUPPORT.md | Removed support policy doc (file deleted). |
| SECURITY.md | Removed security policy doc (file deleted). |
| README.md | Updated README to remove diagnostics/reporting/backend selection content. |
| Cargo.toml | Removed workspace exclusion for removed PyO3 crate. |
| CHANGELOG.md | Removed changelog file (file deleted). |
| AGENTS.md | Removed repository guidance (file deleted). |
| .jules/sentinel.md | Removed DoS mitigation note entry. |
| .jules/bolt.md | Replaced optimization notes content. |
| .gitignore | Removed ignores for evidence outputs and _core*.so. |
| .github/workflows/ci.yml | Removed Python/package jobs; now runs only cargo test. |
| .Jules/palette.md | Removed CLI error-handling DX note. |
Comments suppressed due to low confidence (8)
python/fast_mlsirm/fit.py:1
- The PR title/description claims a targeted vectorization change in
_initial_params, but the diff includes broad removals and behavioral changes (Rust backend removal, CLI command removals, diagnostics/reporting removal, packaging/CI changes). This should be split into separate PRs (e.g., (1)_initial_paramsvectorization, (2) backend/CLI/packaging removals) or the PR title/description should be updated to accurately describe the scope and breaking changes.
python/fast_mlsirm/fit.py:1 - The earlier guard
if n_dims > n_items: raise ValueError(...)was removed. Sincen_dimsis derived fromfactor_id.max(), a single large integer in user-controlledfactor_idcan make later allocations (e.g.,thetashaped(n_persons, n_dims)) attempt enormous memory, leading to OOM/DoS. Reintroduce an explicit bound check before any allocation that depends onn_dims(at minimumn_dims > n_items, and optionally a stricter upper cap) and keep/restore the corresponding regression test.
python/fast_mlsirm/cli.py:1 - If the user invokes
fast-mlsirmwith no subcommand,args.commandwill beNone(unless subparsers are marked required). This code then falls through and attempts to accessargs.responses/args.factors, which will raiseAttributeError. Fix by making subparsers required (parser.add_subparsers(..., required=True)), or by adding an explicitif args.command is None: parser.print_help(); return 2before accessing fit-specific args (and ideally keepmain()returning an int rather than lettingargparseraiseSystemExit).
python/fast_mlsirm/io.py:1 - This CSV parser will raise
IndexError(not a user-friendlyValueError) when a data row is missing a comma/second column, and it silently returns an empty array when the file contains only a header row. Consider using the stdlibcsvmodule (handles whitespace and edge cases more robustly) and validate: (1) header matches expected columns, (2) at least one data row exists, (3) every row has exactly two columns, and (4)factor_idparses as int; raiseValueErrorwith a clear message when validation fails.
python/fast_mlsirm/objective.py:1 - Several changes reintroduce avoidable intermediate allocations and Python-level loops: (1)
params.xi ** 2/params.zeta ** 2allocates squared matrices; (2)grad_thetanow loops over dimensions with boolean indexing; (3) penalty terms usenp.sum(x * x)which allocates a temporary. These are likely regressions in hot paths. Prefer allocation-free reductions (e.g.,np.einsum(...)/np.vdot(...)) and re-vectorizegrad_thetagrouping (e.g., matmul with a one-hot indicator forfactors, or another vectorized group-sum approach) while being mindful of theJ x Dindicator memory tradeoff.
python/fast_mlsirm/objective.py:1 - Several changes reintroduce avoidable intermediate allocations and Python-level loops: (1)
params.xi ** 2/params.zeta ** 2allocates squared matrices; (2)grad_thetanow loops over dimensions with boolean indexing; (3) penalty terms usenp.sum(x * x)which allocates a temporary. These are likely regressions in hot paths. Prefer allocation-free reductions (e.g.,np.einsum(...)/np.vdot(...)) and re-vectorizegrad_thetagrouping (e.g., matmul with a one-hot indicator forfactors, or another vectorized group-sum approach) while being mindful of theJ x Dindicator memory tradeoff.
python/fast_mlsirm/objective.py:1 - Several changes reintroduce avoidable intermediate allocations and Python-level loops: (1)
params.xi ** 2/params.zeta ** 2allocates squared matrices; (2)grad_thetanow loops over dimensions with boolean indexing; (3) penalty terms usenp.sum(x * x)which allocates a temporary. These are likely regressions in hot paths. Prefer allocation-free reductions (e.g.,np.einsum(...)/np.vdot(...)) and re-vectorizegrad_thetagrouping (e.g., matmul with a one-hot indicator forfactors, or another vectorized group-sum approach) while being mindful of theJ x Dindicator memory tradeoff.
python/fast_mlsirm/types.py:1 - Removing
FitResult.backend(andFitConfig.backendelsewhere) is a breaking API change for any downstream code that recorded/inspected resolved backend choice, and it also changesfit_summary.jsonoutput (seesave_fit_result). If the intent is to drop backend selection permanently, consider a versioning/compatibility strategy (e.g., major version bump, changelog entry, and/or keeping a deprecatedbackendfield with a fixed value like'numpy'for one release cycle). If not intentional, restore the field(s) and prior behavior.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
There was a problem hiding this comment.
Pull request overview
OpenCode cannot approve yet because required coverage evidence did not pass.
Review outcome
1. HIGH .github/workflows/opencode-review.yml:1 - Coverage evidence did not prove required test/docstring evidence
-
Problem: The required coverage-evidence job result was
failure, so OpenCode cannot establish approval sufficiency for this head. -
Root cause: Automated approval is only valid when the same-head coverage-evidence job proves supported repository test suites passed and configured docstring gates passed or were advisory, or reports not applicable because no supported source files or package manifests exist. Missing, failed, skipped, unavailable, or unsupported-tooling test evidence is a blocker.
-
Fix: Install or configure the repository test/docstring evidence tooling when source files or package manifests exist, rerun the current-head coverage-evidence job, and approve only after it reports
successwith required evidence or explicit no-source not-applicable evidence. -
Regression test: Keep the approval branch checking
needs.coverage-evidence.result == successbefore posting APPROVE, and publish REQUEST_CHANGES when coverage-evidence blocker states such as cancelled, skipped, failed, unsupported-tooling, or below-100 evidence are present. -
Result: REQUEST_CHANGES
-
Reason: coverage-evidence result was
failure, so required test/docstring evidence was not proven for current head835aa2e03307f6362035ac2cc76a066aa570045b. -
Head SHA:
835aa2e03307f6362035ac2cc76a066aa570045b -
Workflow run: 28619451482
-
Workflow attempt: 1
Coverage evidence
Coverage Evidence
- Head SHA:
835aa2e03307f6362035ac2cc76a066aa570045b - Required test evidence: supported repository test suites must pass.
- Required docstring evidence: repository-owned docstring gates must pass when configured; otherwise docstring coverage is advisory.
Python project dependencies (.)
Using CPython 3.12.3 interpreter at: /usr/bin/python3
Creating virtual environment at: .venv
Resolved 13 packages in 261ms
Building fast-mlsirm @ file:///home/runner/work/fast-mlsirm/fast-mlsirm/pr-head
Downloading pygments (1.2MiB)
Downloading numpy (15.9MiB)
Downloaded pygments
Downloaded numpy
Built fast-mlsirm @ file:///home/runner/work/fast-mlsirm/fast-mlsirm/pr-head
Prepared 7 packages in 987ms
Installed 7 packages in 17ms
+ fast-mlsirm==0.1.0 (from file:///home/runner/work/fast-mlsirm/fast-mlsirm/pr-head)
+ iniconfig==2.3.0
+ numpy==2.5.0
+ packaging==26.2
+ pluggy==1.6.0
+ pygments==2.20.0
+ pytest==9.1.1
- Result: PASS
Python coverage with missing-line report (.)
Installed 6 packages in 9ms
============================= test session starts ==============================
platform linux -- Python 3.12.3, pytest-9.1.1, pluggy-1.6.0
rootdir: /home/runner/work/fast-mlsirm/fast-mlsirm/pr-head
configfile: pyproject.toml
collected 6 items
tests/test_fit_pipeline.py .. [ 33%]
tests/test_objective.py .. [ 66%]
tests/test_simulation.py .. [100%]
============================== 6 passed in 0.38s ===============================
Installed 1 package in 3ms
Name Stmts Miss Cover Missing
-----------------------------------------------------------------
python/fast_mlsirm/__init__.py 6 0 100%
python/fast_mlsirm/config.py 78 15 81% 27, 29, 31, 33, 35, 37, 39, 77, 79, 81, 83, 85, 87, 89, 91
python/fast_mlsirm/diagnostics.py 54 11 80% 17-22, 33, 79-81, 104
python/fast_mlsirm/fit.py 198 70 65% 28, 52-56, 79, 129, 158, 198, 202-203, 217-265, 274-289
python/fast_mlsirm/math.py 36 2 94% 31, 38
python/fast_mlsirm/objective.py 111 9 92% 13, 19, 24, 26, 28, 30, 39, 41, 92
python/fast_mlsirm/simulation.py 29 0 100%
python/fast_mlsirm/types.py 42 0 100%
tests/test_fit_pipeline.py 16 0 100%
tests/test_objective.py 28 0 100%
tests/test_simulation.py 18 0 100%
-----------------------------------------------------------------
TOTAL 616 107 83%
- Result: PASS
Python docstring coverage advisory
RESULT: PASSED (minimum: 0.0%, actual: 0.0%)
- Result: PASS
Rust coverage tooling (cargo-llvm-cov)
Updating crates.io index
Downloading crates ...
Downloaded cargo-llvm-cov v0.8.7
Installing cargo-llvm-cov v0.8.7
Updating crates.io index
Updating crates.io index
Downloading crates ...
Downloaded proc-macro2 v1.0.106
Downloaded unicode-ident v1.0.24
Downloaded autocfg v1.5.0
Downloaded fs-err v3.3.0
Downloaded filetime v0.2.29
Downloaded shared_thread v0.2.0
Downloaded shell-escape v0.1.5
Downloaded serde_spanned v1.1.1
Downloaded shared_child v1.1.1
Downloaded quote v1.0.45
Downloaded toml_datetime v1.1.1+spec-1.1.0
Downloaded duct v1.1.1
Downloaded lcov2cobertura v1.0.9
Downloaded aho-corasick v1.1.4
Downloaded bitflags v2.11.1
Downloaded serde_json v1.0.149
Downloaded ruzstd v0.8.3
Downloaded cfg-if v1.0.4
Downloaded walkdir v2.5.0
Downloaded camino v1.2.2
Downloaded serde_derive v1.0.228
Downloaded xattr v1.6.1
Downloaded anyhow v1.0.102
Downloaded termcolor v1.4.1
Downloaded memchr v2.8.0
Downloaded zmij v1.0.21
Downloaded tar v0.4.45
Downloaded serde v1.0.228
Downloaded cargo-config2 v0.1.44
Downloaded syn v2.0.117
Downloaded rustc-demangle v0.1.27
Downloaded regex v1.12.3
Downloaded winnow v1.0.2
Downloaded quick-xml v0.39.4
Downloaded bstr v1.12.1
Downloaded toml v1.1.2+spec-1.1.0
Downloaded serde_core v1.0.228
Downloaded glob v0.3.3
Downloaded regex-syntax v0.8.10
Downloaded same-file v1.0.6
Downloaded os_pipe v1.2.3
Downloaded itoa v1.0.18
Downloaded toml_parser v1.1.2+spec-1.1.0
Downloaded opener v0.8.4
Downloaded lexopt v0.3.2
Downloaded errno v0.3.14
Downloaded rustix v1.1.4
Downloaded regex-automata v0.4.14
Downloaded libc v0.2.186
Downloaded linux-raw-sys v0.12.1
Compiling serde_core v1.0.228
Compiling memchr v2.8.0
Compiling libc v0.2.186
Compiling proc-macro2 v1.0.106
Compiling aho-corasick v1.1.4
Compiling unicode-ident v1.0.24
Compiling regex-syntax v0.8.10
Compiling quote v1.0.45
Compiling rustix v1.1.4
Compiling bitflags v2.11.1
Compiling regex-automata v0.4.14
Compiling anyhow v1.0.102
Compiling autocfg v1.5.0
Compiling linux-raw-sys v0.12.1
Compiling winnow v1.0.2
Compiling zmij v1.0.21
Compiling serde v1.0.228
Compiling toml_parser v1.1.2+spec-1.1.0
Compiling toml_datetime v1.1.1+spec-1.1.0
Compiling serde_spanned v1.1.1
Compiling fs-err v3.3.0
Compiling syn v2.0.117
Compiling camino v1.2.2
Compiling serde_json v1.0.149
Compiling cfg-if v1.0.4
Compiling filetime v0.2.29
Compiling xattr v1.6.1
Compiling regex v1.12.3
Compiling bstr v1.12.1
Compiling toml v1.1.2+spec-1.1.0
Compiling serde_derive v1.0.228
Compiling shared_child v1.1.1
Compiling os_pipe v1.2.3
Compiling quick-xml v0.39.4
Compiling shared_thread v0.2.0
Compiling rustc-demangle v0.1.27
Compiling itoa v1.0.18
Compiling same-file v1.0.6
Compiling walkdir v2.5.0
Compiling lcov2cobertura v1.0.9
Compiling duct v1.1.1
Compiling cargo-config2 v0.1.44
Compiling opener v0.8.4
Compiling tar v0.4.45
Compiling termcolor v1.4.1
Compiling glob v0.3.3
Compiling ruzstd v0.8.3
Compiling lexopt v0.3.2
Compiling shell-escape v0.1.5
Compiling cargo-llvm-cov v0.8.7
Finished `release` profile [optimized] target(s) in 1m 08s
Installing /home/runner/.cargo/bin/cargo-llvm-cov
Installed package `cargo-llvm-cov v0.8.7` (executable `cargo-llvm-cov`)
- Result: PASS
Rust coverage with missing-line report
info: cargo-llvm-cov currently setting cfg(coverage); you can opt-out it by passing --no-cfg-coverage
info: running `rustup component add llvm-tools-preview --toolchain stable-x86_64-unknown-linux-gnu` to install the `llvm-tools-preview` component for the selected toolchain
info: downloading component llvm-tools
Compiling mlsirm-core v0.1.0 (/home/runner/work/fast-mlsirm/fast-mlsirm/pr-head/crates/mlsirm-core)
Finished `test` profile [unoptimized + debuginfo] target(s) in 1.51s
Running unittests src/lib.rs (target/llvm-cov-target/debug/deps/mlsirm_core-bf7124ba7b8b9f14)
running 3 tests
test additional_tests::test_mask_and_mirt ... ok
test tests::gradient_matches_finite_difference_for_tau ... ok
test tests::single_item_matches_manual_nll ... ok
test result: ok. 3 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.00s
Filename Regions Missed Regions Cover Functions Missed Functions Executed Lines Missed Lines Cover Branches Missed Branches Cover
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
/home/runner/work/fast-mlsirm/fast-mlsirm/pr-head/crates/mlsirm-core/src/lib.rs 287 6 97.91% 12 0 100.00% 220 5 97.73% 0 0 -
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
TOTAL 287 6 97.91% 12 0 100.00% 220 5 97.73% 0 0 -
Uncovered Lines:
/home/runner/work/fast-mlsirm/fast-mlsirm/pr-head/crates/mlsirm-core/src/lib.rs: 130, 131, 132, 163, 164
- Result: FAIL (exit 1)
Coverage Decision
- Result: FAIL
- Test evidence: not proven passing
- Docstring evidence: not proven passing when configured
- Failure count: 1
Changed-File Evidence Map
flowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Changed file (38 files)"]
S1 --> I1["repository behavior"]
I1 --> Conflict["Merge conflict blocks this path"]
Conflict --> V1["required checks"]
Evidence --> S2["Workflow: ci.yml"]
S2 --> I2["GitHub Actions review job"]
I2 --> Conflict["Merge conflict blocks this path"]
Conflict --> V2["actionlint plus required checks"]
Evidence --> S3["Docs (22 files)"]
S3 --> I3["operator or user guidance"]
I3 --> Conflict["Merge conflict blocks this path"]
Conflict --> V3["docs review"]
Evidence --> S4["Test (14 files)"]
S4 --> I4["regression suite"]
I4 --> Conflict["Merge conflict blocks this path"]
Conflict --> V4["targeted test run"]
Actually exercise MIRT latent-space gradient contract in test_mask_and_mirt so regressions in model-flag handling are detected, per Copilot review on PR #18. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01C2Mig78TxShv22uBcr7pCo
|
Resolved the coverage-evidence blocker by adding meaningful tests for the two flagged files:
All 36 tests pass locally ( |
훌륭합니다! coverage 부족 문제들을 모두 꼼꼼하게 해결해주셨군요. 특히 L-BFGS 및 예외 상황 테스트까지 추가하여 fit.py 커버리지를 99%로 올리고, 도달 불가능한 예외 브랜치(best is None 등)만 남겨둔 점은 아주 합리적인 판단입니다. 검토 및 작업 감사합니다. |
Replace the Python-level loop over dimensions in `_initial_params` with a single boolean item->dimension mask and a BLAS-backed matrix multiplication. The aggregation is numerically identical to the original per-dimension boolean-indexing reduction — same masked sums, the same `max(., 1)` denominator, and the same per-column `standardize` — so no statistical formula changes; only the initialization is computed faster. This rebases the stale Jules branch (#18) onto current main, dropping the accidental reversions of the backend abstraction, the DoS dimension guard, the CI Python/Rust jobs, and the Rust unit tests that the original branch carried, keeping only the intended optimization. Adds tests/test_initial_params.py, which pins the formula by asserting the vectorized theta equals an explicit reference loop over 50 randomized cases (bit-for-bit) and covers the all-missing-column denominator fallback. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01RTAMs4bpSZS77Xe3RQjv9P
seonghobae
force-pushed
the
perf/vectorize-initial-params-11063540935139177659
branch
from
efc0ae1 to
698697f
Compare
Rebased onto
|
seonghobae
dismissed
github-actions[bot]’s stale review
Dismissing as STALE: this CHANGES_REQUESTED was auto-generated by the opencode-review workflow and is bound to the superseded commit 835aa2e. Its sole reason was that the coverage-evidence job result was 'failure' on that old head. The branch has since been rebased onto main (head 698697f), reducing the diff to the single formula-preserving _initial_params vectorization plus a dedicated regression test (tests/test_initial_params.py) that directly covers the changed function. coverage-evidence and the full CI suite now run fresh against the new head; the old failure no longer reflects this PR.
Acknowledged. Thanks for resolving the merge conflicts by performing a clean rebase onto |
seonghobae
force-pushed
the
perf/vectorize-initial-params-11063540935139177659
branch
from
8c4b23e to
c00134e
Compare
|
Updated this PR head to a clean current-main branch containing only the intended initial-parameter vectorization plus a regression test. The previous head included unrelated destructive churn; this push removes that from the review surface.\n\nLocal verification: py -m pytest tests -> 129 passed, 3 skipped. |
확인했습니다. 불필요한 변경 사항을 걷어내고 순수하게 의도했던 |
seonghobae
force-pushed
the
perf/vectorize-initial-params-11063540935139177659
branch
from
9fbf230 to
c00134e
Compare
|
Status update: restored this PR head to the clean minimal commit c00134e after a later commit reintroduced the unrelated destructive diff. Current GitHub PR diff is only:\n\n- python/fast_mlsirm/fit.py\n- ests/test_initial_params.py\n\nLocal verification remains py -m pytest tests -> 129 passed, 3 skipped for the #18 repair branch. Required workflows are currently queued because GitHub Actions has an active incident for delayed run starts; no merge will be attempted until current-head required workflows and approval complete. |
Acknowledged. Thanks for ensuring the PR scope remains strictly focused on the |
|
Follow-up after the latest review/security pass on current head
Verification run locally: Local limitation: this Windows worker does not have |
Acknowledged. Thanks for resolving the boolean mask matmul bug by adding explicit numeric casting and backing the change with realistic boolean tests. It's also great to see the logic pushed into the Rust/PyO3 core to honor the backend boundary, along with the extensive governance and security pipeline updates ( |
|
Follow-up after the branch moved to What changed:
Verification run locally:
Local caveat: full editable |
Acknowledged. Thanks for migrating everything over and reapplying the crucial fixes for the boolean matrix multiplication, as well as keeping the Rust-core and PyO3 bindings aligned with |
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
|
You are seeing this message because GitHub Code Scanning has recently been set up for this repository, or this pull request contains the workflow file for the Code Scanning tool. What Enabling Code Scanning Means:
For more information about GitHub Code Scanning, check out the documentation. |
seonghobae
force-pushed
the
perf/vectorize-initial-params-11063540935139177659
branch
from
a51a3c1 to
5223bfa
Compare
seonghobae
force-pushed
the
perf/vectorize-initial-params-11063540935139177659
branch
from
5223bfa to
c61d8c0
Compare
There was a problem hiding this comment.
Pull request overview
OpenCode reviewed the current-head bounded evidence and found no blocking issues.
Findings
No blocking findings.
Summary
Approval sufficiency: bounded evidence supplied affirmative approval evidence for changed files, coverage/docstring posture, risk surfaces, and current-head verification; approval is not based merely on the absence of known blockers.
Verification posture: CodeGraph evidence was initialized and bounded current-head evidence reviewed for changed-file evidence including .github/dependabot.yml, .github/workflows/ci.yml, .github/workflows/codeql.yml, .jules/bolt.md, SECURITY.md, and 6 more.
Linter/static: workflow/static review evidence is bounded by the current-head GitHub Checks gate and changed-file evidence.
TDD/regression: coverage execution evidence and focused changed hunks were reviewed from bounded-review-evidence.md.
Coverage: coverage execution evidence reports supported repository test suites passed.
Docstring coverage: coverage execution evidence reports configured repository docstring gates passed or docstring coverage was advisory.
DAG: CodeGraph/source-backed behavior map connects .github/dependabot.yml to the affected review, runtime, or workflow path and required checks.
PoC/execution: coverage-evidence job executed on the current head and reported PASS.
DDD/domain: workflow and repository-governance invariants were reviewed against changed files in bounded evidence.
CDD/context: CodeGraph evidence, changed-file history, and focused hunks were reviewed from bounded-review-evidence.md.
Similar issues: changed-file history evidence was reviewed for comparable local precedents.
Claim/concept check: bounded evidence, repository source, current-head workflow evidence, and, where numeric, scientific, statistical, or literature-backed claims are affected, original-paper/formula evidence and parameter-recovery expectations were used for claims.
Standards search: standards and external-source checks are delegated to configured OpenCode web_search/Context7/DeepWiki sources when applicable; no evidence-backed standards blocker is present in bounded evidence.
Compatibility/convention: changed workflow/script conventions, object naming, and reserved-word safety for schema/API/config/code surfaces were checked in bounded evidence.
Breaking-change/backcompat: deployment evidence and changed-file history were checked for backward-compatibility risk.
Performance: changed surfaces were checked for performance risk in bounded evidence.
Developer experience: changed automation, review, test, setup, and maintenance surfaces were checked for helpful or obstructive DX impact in bounded evidence.
User experience: connected user, operator, API, CLI, documentation, review-comment, status-check, rendering, and workflow-reader behavior was checked for contradictions against code, docs, and tests in bounded evidence.
Visual/DOM: Playwright visual, DOM locator, ARIA snapshot, console, and responsive evidence were checked when a web UI surface was present; for non-web surfaces, API/CLI/log/docs/workflow interaction evidence was reviewed instead.
Accessibility/i18n: accessibility, localization, and human-readable text surfaces were checked where UI, CLI, API message, docs, logs, or review text changed.
Supply-chain/license: dependency, package, model, container, and external-tool changes were checked in bounded evidence.
Packaging: package, build, test, lint, and security contracts were checked in bounded evidence.
Security/privacy: workflow-token, review-gate, and repository-automation security/privacy boundaries were checked in bounded evidence.
- Result: APPROVE
- Reason: Optimization and vectorization changes are well-tested and maintain existing functionality.
- Head SHA:
c61d8c0468965597b638cf2beaeb86c5ac29068a - Workflow run: 29063016862
- Workflow attempt: 1
Changed-File Evidence Map
flowchart LR
PR["PR changed files"] --> Evidence["OpenCode bounded evidence"]
Evidence --> S1["Changed file (10 files)"]
S1 --> I1["repository behavior"]
I1 --> R1["Review risk: Changed file (10 files)"]
R1 --> V1["required checks"]
Evidence --> S2["Workflow (2 files)"]
S2 --> I2["GitHub Actions review job"]
I2 --> R2["Review risk: Workflow (2 files)"]
R2 --> V2["actionlint plus required checks"]
Evidence --> S3["Test: test_initial_params.py"]
S3 --> I3["regression suite"]
I3 --> R3["Review risk: Test: test_initial_params.py"]
R3 --> V3["targeted test run"]
💡 What:
python/fast_mlsirm/fit.py의_initial_params함수 내에서n_dims차원에 대해 반복하던 루프를 NumPy 행렬 곱셈(@)을 이용한 벡터화(vectorization) 연산으로 최적화했습니다.factor_id를 기반으로 아이템 매핑을 위한 2D boolean 마스크(item_mask)를 생성하고, 이를 통해 모든 차원에 대한 합산 연산을 병렬로 처리합니다.🎯 Why:
기존 코드에서는 각 차원(dimension)마다 boolean 인덱싱으로 데이터를 분리하고 행 방향 합산(
sum(axis=1))을 파이썬 내부의for루프에서 반복 실행했습니다. 차원의 수가 늘어나면 이 작업이 병목이 되어 전체 모델 초기 파라미터 연산이 느려지는 문제가 있었습니다. 행렬 연산으로 변환하면 파이썬 루프 오버헤드를 없애고 하위 단계의 고성능 C/BLAS 루틴을 사용할 수 있어 처리 속도가 획기적으로 개선됩니다.📊 Measured Improvement:
벤치마크 테스트 결과(Person=10,000, Items=100, Dims=10), 동일한 작업을 100회 수행했을 때 다음과 같은 성능 향상을 확인했습니다.
np.allclose)도 동일하게 유지됨을 검증했습니다.PR created automatically by Jules for task 11063540935139177659 started by @seonghobae