* using log directory ‘/data/localhost/ripley/R/packages/tests-MKL/gllvmTMB.Rcheck’ * using R Under development (unstable) (2026-11-20 r90940) * using platform: x86_64-pc-linux-gnu * R was compiled by gcc (GCC) 16.2.1 20261029 (Red Hat 16.2.1-3) GNU Fortran (GCC) 16.2.1 20261029 (Red Hat 16.2.1-3) * running under: Fedora Linux 44 (Server Edition) * using session charset: UTF-8 * current time: 2026-11-21 06:00:36 UTC * using option ‘--no-stop-on-test-error’ * checking for file ‘gllvmTMB/DESCRIPTION’ ... OK * checking extension type ... Package * this is package ‘gllvmTMB’ version ‘0.7.1’ * package encoding: UTF-8 * checking package namespace information ... OK * checking package dependencies ... OK * checking if this is a source package ... OK * checking if there is a namespace ... OK * checking for executable files ... OK * checking for hidden files and directories ... OK * checking for portable file names ... OK * checking for sufficient/correct file permissions ... OK * checking whether package ‘gllvmTMB’ can be installed ... [4m/10m] OK * used C++ compiler: ‘g++ (GCC) 16.2.1 20261029 (Red Hat 16.2.1-3)’ * checking C++ specification ... INFO specified C++17 * checking package directory ... OK * checking ‘build’ directory ... OK * checking DESCRIPTION meta-information ... OK * checking top-level files ... OK * checking for left-over files ... OK * checking index information ... OK * checking package subdirectories ... OK * checking code files for non-ASCII characters ... OK * checking R files for syntax errors ... OK * checking whether the package can be loaded ... OK * checking whether the package can be loaded with stated dependencies ... OK * checking whether the package can be unloaded cleanly ... OK * checking whether the namespace can be loaded with stated dependencies ... OK * checking whether the namespace can be unloaded cleanly ... OK * checking loading without being on the library search path ... OK * checking whether startup messages can be suppressed ... OK * checking use of S3 registration ... OK * checking dependencies in R code ... OK * checking S3 generic/method consistency ... OK * checking replacement functions ... OK * checking foreign function calls ... OK * checking R code for possible problems ... [104s/263s] OK * checking Rd files ... OK * checking Rd metadata ... OK * checking Rd line widths ... OK * checking Rd cross-references ... OK * checking for missing documentation entries ... OK * checking for code/documentation mismatches ... OK * checking Rd \usage sections ... OK * checking Rd contents ... OK * checking for unstated dependencies in examples ... OK * checking line endings in C/C++/Fortran sources/headers ... OK * checking line endings in Makefiles ... OK * checking compilation flags in Makevars ... OK * checking for GNU extensions in Makefiles ... OK * checking for portable use of $(BLAS_LIBS) and $(LAPACK_LIBS) ... OK * checking use of PKG_*FLAGS in Makefiles ... OK * checking use of SHLIB_OPENMP_*FLAGS in Makefiles ... OK * checking pragmas in C/C++ headers and code ... OK * checking compilation flags used ... OK * checking compiled code ... OK * checking installed files from ‘inst/doc’ ... OK * checking files in ‘vignettes’ ... OK * checking examples ... [7s/19s] OK * checking for unstated dependencies in ‘tests’ ... OK * checking tests ... Running ‘testthat.R’ [127s/160s] [127s/160s] ERROR Running the tests in ‘tests/testthat.R’ failed. Complete output: > options(Matrix.warnDeprecatedCoerce = 2) > > library(testthat) > library(gllvmTMB) gllvmTMB is EXPERIMENTAL (lifecycle: experimental). Use at your own risk: the package is not complete, is not fully human-verified, and needs extensive further validation. Point estimates are the primary inferential output, but evidence is route- and regime-specific. Broad interval coverage is not certified. One narrow two-sided Gaussian total-variance profile regime has a documented 0.94 floor. For 0.7.1 scope, see its installed help, vignettes, and NEWS. The online limitations page may differ as development continues. > > full_suite <- isTRUE(as.logical(Sys.getenv("NOT_CRAN", ""))) || + identical(Sys.getenv("GITHUB_ACTIONS"), "true") > > cran_sentinels <- paste0( + "^(cran-sentinels|release-core-sentinels|formula-grammar-smoke|", + "traits-keyword|integration-tour|canonical-keywords|kernel-equivalence|", + "animal-keyword|family-constructor-contract|family-gamma|family-lognormal|", + "cran-family-sentinels|cran-missing-data-sentinels|missing-response-nongaussian|", + "unused-grouping-slots|sigma-rename|bootstrap-Sigma|bootstrap-lv-effects|", + "spatial-latent-unique-fold|lv-missing-response|", + "link-residual-15-family-fixture|extract-sigma|extractors|extractors-extra|", + "plot-covariance-tables|plot-gllvmTMB|predict-se|tidy-predict|fitted-multi)$" + ) > > test_check("gllvmTMB", filter = if (full_suite) NULL else cran_sentinels) Starting 2 test processes. > test-canonical-keywords.R: ! Formula keyword `diag()` is a deprecated alias; use `indep()` for new code. > test-canonical-keywords.R: i `indep(0 + trait | g)` =/=> `diag(0 + trait | g) > test-canonical-keywords.R: ` > test-canonical-keywords.R: > Aliases will be dropped at the next minor release. See `?diag_re` / `latent()`. > test-canonical-keywords.R: > Use ordinary latent(..., d = K) for the default shared + diagonal-Psi decomposition, or indep(0 + trait | g) for a standalone diagonal. > test-canonical-keywords.R: ! `phylo_tree = ...` as a global argument to `gllvmTMB()` is deprecated. > test-canonical-keywords.R: i Pass `tree = ...` inside the phylo_*() keyword instead, e.g. `phylo_latent(species, d = 2, tree = tree)`. > test-canonical-keywords.R: > The legacy global path still works; the in-keyword syntax avoids silent index/order mismatch. > test-canonical-keywords.R: This message is displayed once per session. > test-extractors-extra.R: i Auto-suppressing `sigma_eps`: `indep(0 + trait | site_species)` is at the per-row level, so it already absorbs the observation > test-extractors-extra.R: residual. > test-extractors-extra.R: * Fixed at 0.00107 (~1/1000 of sd(y)) to keep the Gaussian density well-defined; the row-level residual variance is fully captured by the per-row diagonal term. > test-extractors.R: i Auto-suppressing `sigma_eps`: `indep(0 + trait | site_species)` is at the per-row level, so it already absorbs the observation > test-extractors.R: residual. > test-extractors.R: * Fixed at 0.00172 (~1/1000 of sd(y)) to keep the Gaussian density well-defined; the row-level residual variance is fully captured by the per-row diagonal term. > test-extractors.R: i Auto-suppressing `sigma_eps`: `indep(0 + trait | site_species)` is at the per-row level, so it already absorbs the observation residual. > test-extractors.R: * Fixed at 0.00211 (~1/1000 of sd(y)) to keep the Gaussian density well-defined; the row-level residual variance is fully captured by the per-row diagonal term. > test-formula-grammar-smoke.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (binomial): 3.290 - t2 (binomial): 3.290 - t3 (binomial): 3.290 - t4 (binomial): 3.290 > test-formula-grammar-smoke.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (poisson): 0.424 - t2 (poisson): 0.438 - t3 (poisson): 0.413 > test-integration-tour.R: i Auto-suppressing `sigma_eps`: `indep(0 + trait | site_species)` is at the per-row level, so it already absorbs the observation > test-integration-tour.R: residual. > test-integration-tour.R: * Fixed at 0.00161 (~1/1000 of sd(y)) to keep the Gaussian density well-defined; the row-level residual variance is f > test-integration-tour.R: ully captured by the per-row diagonal term. > test-formula-grammar-smoke.R: i Auto-suppressing `sigma_eps`: `indep(0 + trait | site)` is at the per-row level, so it already absorbs the observation residual. > test-formula-grammar-smoke.R: * Fixed at 0.000528 (~1/1000 of sd(y)) to keep the Gaussian density well-defined; the row-level residual variance is fully captured by the per-row diagonal term. Saving _problems/test-kernel-equivalence-203.R > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (poisson): 0.212 - t2 (poisson): 0.188 - t3 (poisson): 0.321 > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (poisson): 0.209 - t2 (poisson): 0.187 - t3 (poisson): 0.323 > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (nbinom2): 0.958 - t2 (nbinom2): 0.393 - t3 (nbinom2): 0.00 > test-missing-response-nongaussian.R: 0 > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (nbinom2): 0.958 - t2 (nbinom2): 0.393 - t3 (nbinom2): 0.00 > test-missing-response-nongaussian.R: 0 > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (binomial): 3.290 - t2 (binomial): 3.290 - t3 (binomial): 3 > test-missing-response-nongaussian.R: .290 > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (binomial): 3.290 - t2 (binomial): 3.290 - t3 (binomial): 3.290 > test-missing-response-nongaussian.R: Sigma_unit is latent-only (Lambda Lambda^T): this fit used `latent(..., unique = FALSE)`, so trait-specific residual variance Psi is not modelled and correlations from this matrix overstate cross-trait coupling. For the full decomposition Sigma = Lambda Lambda^T + Psi, refit without `unique = FALSE` (the default). > test-missing-response-nongaussian.R: Sigma_unit is latent-only (Lambda Lambda^T): this fit used `latent(..., unique = FALSE)`, so trait-specific residual variance Psi is not modelled and correlations from this matrix overstate cross-trait coupling. For the full decomposition Sigma = Lambda Lambda^T + Psi, refit without `unique = FALSE` (the default). > test-missing-response-nongaussian.R: Sigma_unit is latent-only (Lambda Lambda^T): this fit used `latent(..., unique = FALSE)`, so trait-specific residual variance Psi is not modelled and correlations from this matrix overstate cross-trait coupling. For the full decomposition Sigma = Lambda Lambda^T + Psi, refit without `unique = FALSE` (the default). > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (Gamma): 0.044 - t2 (Gamma): 0.060 - t3 (Gamma): 0.090 > test-missing-response-nongaussian.R: Sigma_unit is latent-only (Lambda Lambda^T): this fit used `latent(..., unique = FALSE)`, so trait-specific residual variance Psi is not modelled and correlations from this matrix overstate cross-trait coupling. For the full decomposition Sigma = Lambda Lambda^T + Psi, refit without `unique = FALSE` (the default). > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (Gamma): 0.044 - t2 (Gamma): 0.060 - t3 (Gamma): 0.090 > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (nbinom1): 0.303 - t2 (nbinom1): 0.301 - t3 (nbinom1): 0.520 > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (nbinom1): 0.304 - t2 (nbinom1): 0.306 - t3 (nbinom1): 0.517 > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (tweedie): 0.744 - t2 (tweedie): 0.658 - t3 (tweedie): 0.738 > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (tweedie): 0.739 - t2 (tweedie): 0.652 - t3 (tweedie): 0.748 > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (Beta): 0.529 - t2 (Beta): 0.469 - t3 (Beta): 0.334 > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (Beta): 0.530 - t2 (Beta): 0.468 - t3 (Beta): 0.334 > test-missing-response-nongaussian.R: Student-t degrees of freedom parameter fixed at 5. To estimate it, set `df = NULL`. > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (student): 0.415 - t2 (student): 0.455 - t3 (student): 0.279 > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (student): 0.415 - t2 (student): 0.455 - t3 (student): 0.279 > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (truncated_poisson): 0.190 - t2 (truncated_poisson): 0.186 - t3 (truncated_poisson): 0.297 > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (truncated_poisson): 0.189 - t2 (truncated_poisson): 0.191 - t3 (truncated_poisson): 0.299 > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (truncated_nbinom2): 0.288 - t2 (truncated_nbinom2): 0.088 - t3 (truncated_nbinom2): 0.228 > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (truncated_nbinom2): 0.288 - t2 (truncated_nbinom2): 0.088 - t3 (truncated_nbinom2): 0.228 > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (betabinomial): 3.723 - t2 (betabinomial): 4.399 - t3 (betabinomial): 3.713 > test-missing-response-nongaussian.R: Added per-trait link-implicit residual variance to diag(Sigma): - t1 (betabinomial): 3.721 - t2 (betabinomial): 4.408 - t3 (betabinomial): 3.713 > test-unused-grouping-slots.R: i Auto-suppressing `sigma_eps`: `indep(0 + trait | site)` is at the per-row level, so it already absorbs the observation residual. > test-unused-grouping-slots.R: * Fixed at 0.00106 (~1/1000 of sd(y)) to keep the Gaussian density well-defined; the row-level residual variance is fully captured by the per-row diagonal term. > test-unused-grouping-slots.R: i Auto-suppressing `sigma_eps`: `indep(0 + trait | site)` is at the per-row level, so it already absorbs the observation residua > test-unused-grouping-slots.R: l. > test-unused-grouping-slots.R: * Fixed at 0.00106 (~1/1000 of sd(y)) to keep the Gaussian density well-defined; the row-level residual variance is fully captured by the per-row diagonal term. > test-unused-grouping-slots.R: i Auto-suppressing `sigma_eps`: `indep(0 + trait | site)` is at the per-row level, so it already absorbs the observation residua > test-unused-grouping-slots.R: l. > test-unused-grouping-slots.R: * Fixed at 0.00106 (~1/1000 of sd(y)) to keep the Gaussian density well-defined; the row-level residual variance is fully captured by the per-row diagonal term. > test-unused-grouping-slots.R: i Auto-suppressing `sigma_eps`: `indep(0 + trait | obs)` is at the per-row level, so it already absorbs the observation residual. > test-unused-grouping-slots.R: * Fixed at 0.00106 (~1/1000 of sd(y)) to keep the Gaussian density well-defined; the row-level residual variance is fully captured by the per-row diagonal term. > test-unused-grouping-slots.R: i Auto-suppressing `sigma_eps`: `indep(0 + trait | site)` is at the per-row level, so it already absorbs the observation residual. > test-unused-grouping-slots.R: * Fixed at 0.00106 (~1/1000 of sd(y)) to keep the Gaussian density well-defined; the row-level residual variance is fully captured by the per-row diagonal term. > test-unused-grouping-slots.R: i Auto-suppressing `sigma_eps`: `indep(0 + trait | site)` is at the per-row level, so it already absorbs the observation residua > test-unused-grouping-slots.R: l. > test-unused-grouping-slots.R: * Fixed at 0.00106 (~1/1000 of sd(y)) to keep the Gaussian density well-defined; the row-level residual variance is fully captured by the per-row diagonal term. [ FAIL 1 | WARN 0 | SKIP 30 | PASS 1410 ] ══ Skipped tests (30) ══════════════════════════════════════════════════════════ • Heavy recovery/matrix test -- set GLLVMTMB_HEAVY_TESTS=1 to run (11): 'test-bootstrap-Sigma.R:54:3', 'test-bootstrap-Sigma.R:112:3', 'test-bootstrap-Sigma.R:129:3', 'test-bootstrap-Sigma.R:159:3', 'test-bootstrap-Sigma.R:184:3', 'test-bootstrap-Sigma.R:211:3', 'test-bootstrap-Sigma.R:244:3', 'test-bootstrap-Sigma.R:296:3', 'test-animal-keyword.R:329:3', 'test-bootstrap-lv-effects.R:36:3', 'test-bootstrap-lv-effects.R:66:3' • On CRAN (18): 'test-animal-keyword.R:136:3', 'test-animal-keyword.R:159:3', 'test-animal-keyword.R:179:3', 'test-animal-keyword.R:199:3', 'test-animal-keyword.R:219:3', 'test-animal-keyword.R:390:3', 'test-animal-keyword.R:423:3', 'test-fitted-multi.R:76:3', 'test-fitted-multi.R:88:3', 'test-fitted-multi.R:103:3', 'test-fitted-multi.R:115:3', 'test-fitted-multi.R:124:3', 'test-fitted-multi.R:160:3', 'test-tidy-predict.R:29:3', 'test-tidy-predict.R:63:3', 'test-tidy-predict.R:91:3', 'test-tidy-predict.R:178:3', 'test-traits-keyword.R:141:3' • Repository-only campaign schema is excluded from the tarball (1): 'test-release-core-sentinels.R:294:3' ══ Failed tests ════════════════════════════════════════════════════════════════ ── Failure ('test-kernel-equivalence.R:203:3'): kernel_latent(unique = FALSE) is equivalent to dense phylo_latent vcv path ── Expected `Sigma_kernel` to equal `Sigma_phy`. Differences: actual vs expected [,1] [,2] [,3] - actual[1, ] 0.47723665 0.29791931 0.02041866 + expected[1, ] 0.47723604 0.29791895 0.02041874 - actual[2, ] 0.29791931 0.27161593 0.07558993 + expected[2, ] 0.29791895 0.27161578 0.07558999 - actual[3, ] 0.02041866 0.07558993 0.04699023 + expected[3, ] 0.02041874 0.07558999 0.04699020 [ FAIL 1 | WARN 0 | SKIP 30 | PASS 1410 ] Error: ! Test failures. Execution halted * checking for unstated dependencies in vignettes ... OK * checking package vignettes ... OK * checking re-building of vignette outputs ... [23s/60s] OK * checking PDF version of manual ... [14s/34s] OK * checking HTML version of manual ... [10s/25s] OK * checking for non-standard things in the check directory ... OK * checking for detritus in the temp directory ... OK * DONE Status: 1 ERROR See ‘/data/localhost/ripley/R/packages/tests-MKL/gllvmTMB.Rcheck/00check.log’ for details. Command exited with non-zero status 1 Time 21:41.22, 564.19 + 19.80