From 707561ef34b067728db91088984d99ab03c967cd Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Tue, 14 Apr 2026 15:19:16 +0000
Subject: [PATCH 1/4] Add WCRP compliance check pipeline using cc-plugin-wcrp

Agent-Logs-Url: https://github.com/ilaflott/fremorizer/sessions/467572fc-cbb2-4eb8-9473-3a23cfb8f9bb

Co-authored-by: ilaflott <6273252+ilaflott@users.noreply.github.com>
---
 .github/scripts/gather_test_outputs.sh      | 136 +++++++++++
 .github/workflows/wcrp_compliance_check.yml | 235 ++++++++++++++++++++
 .gitignore                                  |   3 +
 README.md                                   |  20 ++
 pyproject.toml                              |   4 +
 5 files changed, 398 insertions(+)
 create mode 100755 .github/scripts/gather_test_outputs.sh
 create mode 100644 .github/workflows/wcrp_compliance_check.yml

diff --git a/.github/scripts/gather_test_outputs.sh b/.github/scripts/gather_test_outputs.sh
new file mode 100755
index 0000000..f022c21
--- /dev/null
+++ b/.github/scripts/gather_test_outputs.sh
@@ -0,0 +1,136 @@
+#!/bin/bash
+# Script to gather all NetCDF test outputs into a centralized location
+# This script is designed to be reusable by other QA pipelines (compliance-checker, etc.)
+#
+# Usage: gather_test_outputs.sh <output_directory>
+#
+# The script:
+# 1. Searches for all NetCDF files generated by tests
+# 2. Copies them to a centralized directory with preserved structure
+# 3. Creates a manifest file listing all gathered files
+# 4. Categorizes files by CMIP version (CMIP6 vs CMIP7)
+
+set -e
+
+# Default output directory if not specified
+OUTPUT_DIR="${1:-tmp/qa_test_outputs}"
+
+echo "=========================================="
+echo "Gathering Test Outputs for QA Validation"
+echo "=========================================="
+echo "Output directory: ${OUTPUT_DIR}"
+echo ""
+
+# Create the centralized output directory
+mkdir -p "${OUTPUT_DIR}"
+mkdir -p "${OUTPUT_DIR}/cmip6"
+mkdir -p "${OUTPUT_DIR}/cmip7"
+mkdir -p "${OUTPUT_DIR}/other"
+
+# Initialize counters
+total_files=0
+cmip6_files=0
+cmip7_files=0
+other_files=0
+
+# Create manifest file
+MANIFEST="${OUTPUT_DIR}/manifest.txt"
+echo "# Test Output Manifest" > "${MANIFEST}"
+echo "# Generated: $(date -u +%Y-%m-%dT%H:%M:%SZ)" >> "${MANIFEST}"
+echo "# " >> "${MANIFEST}"
+
+echo "Searching for NetCDF files in test directories..."
+echo ""
+
+# Function to categorize and copy files
+gather_files() {
+    local search_dir=$1
+    local label=$2
+
+    if [ ! -d "${search_dir}" ]; then
+        echo "Warning: Directory ${search_dir} not found, skipping"
+        return
+    fi
+
+    echo "Gathering from: ${search_dir} (${label})"
+
+    # Find all .nc files
+    while IFS= read -r -d '' ncfile; do
+        if [ -f "${ncfile}" ]; then
+            # Determine CMIP version from file path or content
+            cmip_version="other"
+            if [[ "${ncfile}" == *"CMIP6"* ]]; then
+                cmip_version="cmip6"
+                ((cmip6_files++))
+            elif [[ "${ncfile}" == *"CMIP7"* ]]; then
+                cmip_version="cmip7"
+                ((cmip7_files++))
+            else
+                # Try to detect from file attributes using ncdump
+                if command -v ncdump &> /dev/null; then
+                    if ncdump -h "${ncfile}" 2>/dev/null | grep -q 'mip_era = "CMIP7"'; then
+                        cmip_version="cmip7"
+                        ((cmip7_files++))
+                    elif ncdump -h "${ncfile}" 2>/dev/null | grep -q 'mip_era = "CMIP6"'; then
+                        cmip_version="cmip6"
+                        ((cmip6_files++))
+                    else
+                        ((other_files++))
+                    fi
+                else
+                    ((other_files++))
+                fi
+            fi
+
+            # Create unique filename to avoid collisions
+            basename=$(basename "${ncfile}")
+            # Add a hash of the full path to ensure uniqueness
+            path_hash=$(echo "${ncfile}" | md5sum | cut -c1-8)
+            unique_name="${path_hash}_${basename}"
+
+            # Copy to categorized directory
+            dest_file="${OUTPUT_DIR}/${cmip_version}/${unique_name}"
+            cp "${ncfile}" "${dest_file}"
+
+            # Add to manifest
+            echo "${ncfile} -> ${cmip_version}/${unique_name}" >> "${MANIFEST}"
+
+            ((total_files++))
+
+            echo "  found: ${ncfile}"
+            echo "    -> ${cmip_version}/${unique_name}"
+        fi
+    done < <(find "${search_dir}" -name "*.nc" -type f -print0 2>/dev/null)
+}
+
+# Gather files from different test output directories
+gather_files "fremorizer/tests/test_files/outdir" "CMIP6 basic tests"
+gather_files "fremorizer/tests/test_files/outdir_ppan_only" "Extended test examples"
+
+# Add summary to manifest
+echo "" >> "${MANIFEST}"
+echo "# Summary" >> "${MANIFEST}"
+echo "# Total files: ${total_files}" >> "${MANIFEST}"
+echo "# CMIP6 files: ${cmip6_files}" >> "${MANIFEST}"
+echo "# CMIP7 files: ${cmip7_files}" >> "${MANIFEST}"
+echo "# Other files: ${other_files}" >> "${MANIFEST}"
+
+echo ""
+echo "=========================================="
+echo "Gathering Complete"
+echo "=========================================="
+echo "Total files gathered: ${total_files}"
+echo "  - CMIP6: ${cmip6_files}"
+echo "  - CMIP7: ${cmip7_files}"
+echo "  - Other: ${other_files}"
+echo ""
+echo "Output directory: ${OUTPUT_DIR}"
+echo "Manifest file: ${MANIFEST}"
+
+# Exit successfully if we found any files
+if [ ${total_files} -gt 0 ]; then
+    exit 0
+else
+    echo "::warning::No NetCDF files were found in test output directories"
+    exit 1
+fi
diff --git a/.github/workflows/wcrp_compliance_check.yml b/.github/workflows/wcrp_compliance_check.yml
new file mode 100644
index 0000000..95fe9c8
--- /dev/null
+++ b/.github/workflows/wcrp_compliance_check.yml
@@ -0,0 +1,235 @@
+name: wcrp_compliance_check
+on:
+  pull_request:
+    branches:
+  workflow_dispatch:
+
+# cancel running jobs if theres a newer push
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+
+jobs:
+  wcrp-compliance-check:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        shell: bash -l {0}
+    steps:
+      - name: Checkout Files
+        uses: actions/checkout@v4
+        with:
+          submodules: recursive
+
+      - name: Setup Conda
+        uses: conda-incubator/setup-miniconda@v3
+        with:
+          activate-environment: fremorizer-wcrp
+          python-version: "3.12"
+          auto-activate-base: false
+          miniforge-version: latest
+          channels: conda-forge,noaa-gfdl
+
+      - name: Configure Conda
+        run: |
+          echo "removing main and r channels from defaults"
+          conda config --remove channels defaults || true
+          conda config --remove channels main || true
+          conda config --remove channels r || true
+
+          echo "setting strict channel priority"
+          conda config --set channel_priority strict
+
+          echo "printing conda config just in case"
+          conda config --show
+
+      - name: Install dependencies for fremorizer
+        run: |
+          conda install -y \
+            conda-forge::cftime \
+            "conda-forge::click>=8.2" \
+            "conda-forge::cmor>=3.14" \
+            "conda-forge::netcdf4>=1.7" \
+            "conda-forge::numpy>=2" \
+            conda-forge::pyyaml \
+            conda-forge::pytest
+
+      - name: Install cc-plugin-wcrp
+        run: |
+          pip install cc-plugin-wcrp
+
+      - name: Configure esgvoc controlled vocabularies
+        run: |
+          esgvoc config add cordex-cmip6
+          esgvoc config add cmip7
+          esgvoc config set project:branch=esgvoc
+          esgvoc install
+
+      - name: Verify cc-plugin-wcrp installation
+        run: |
+          echo "Listing available compliance-checker plugins..."
+          compliance-checker -l
+
+      - name: Install fremorizer
+        run: |
+          pip install .
+
+      - name: Run tests to generate output files
+        run: |
+          echo "Running test suite to generate NetCDF outputs..."
+          echo ""
+
+          echo "=========================================="
+          echo "Running CMIP6 basic tests..."
+          echo "=========================================="
+          pytest fremorizer/tests/test_cmor_run_subtool.py -v || true
+
+          echo ""
+          echo "=========================================="
+          echo "Running extended test examples..."
+          echo "=========================================="
+          pytest fremorizer/tests/test_cmor_run_subtool_further_examples.py -v || true
+
+          echo ""
+          echo "Test execution complete."
+        continue-on-error: true
+
+      - name: Gather test outputs into centralized directory
+        id: gather_outputs
+        run: |
+          bash .github/scripts/gather_test_outputs.sh tmp/qa_test_outputs
+
+          echo "output_dir=tmp/qa_test_outputs" >> $GITHUB_OUTPUT
+
+          total_files=$(find tmp/qa_test_outputs -name "*.nc" -type f | wc -l)
+          echo "file_count=${total_files}" >> $GITHUB_OUTPUT
+
+          cmip6_files=$(find tmp/qa_test_outputs/cmip6 -name "*.nc" -type f 2>/dev/null | wc -l || echo "0")
+          cmip7_files=$(find tmp/qa_test_outputs/cmip7 -name "*.nc" -type f 2>/dev/null | wc -l || echo "0")
+          other_files=$(find tmp/qa_test_outputs/other -name "*.nc" -type f 2>/dev/null | wc -l || echo "0")
+
+          echo "cmip6_count=${cmip6_files}" >> $GITHUB_OUTPUT
+          echo "cmip7_count=${cmip7_files}" >> $GITHUB_OUTPUT
+          echo "other_count=${other_files}" >> $GITHUB_OUTPUT
+
+      - name: Run WCRP compliance checks on CMIP6 outputs
+        if: steps.gather_outputs.outputs.cmip6_count != '0'
+        run: |
+          echo "Running WCRP CMIP6 compliance checks..."
+          echo "CMIP6 files to check: ${{ steps.gather_outputs.outputs.cmip6_count }}"
+          echo ""
+
+          mkdir -p tmp/wcrp_compliance_reports
+
+          for ncfile in tmp/qa_test_outputs/cmip6/*.nc; do
+            if [ -f "$ncfile" ]; then
+              basename=$(basename "$ncfile" .nc)
+              echo ""
+              echo "=========================================="
+              echo "Checking: ${basename}"
+              echo "=========================================="
+
+              # Run wcrp_cmip6 checker - text report for logs
+              compliance-checker \
+                --test=wcrp_cmip6 \
+                --format=text \
+                --output=tmp/wcrp_compliance_reports/cmip6_${basename}_report.txt \
+                "$ncfile" || true
+
+              # Run wcrp_cmip6 checker - json report for artifact
+              compliance-checker \
+                --test=wcrp_cmip6 \
+                --format=json \
+                --output=tmp/wcrp_compliance_reports/cmip6_${basename}_report.json \
+                "$ncfile" 2>&1 || true
+
+              # Display text report summary in logs
+              echo "Report summary:"
+              head -80 tmp/wcrp_compliance_reports/cmip6_${basename}_report.txt || true
+              echo ""
+            fi
+          done
+
+      - name: Run WCRP compliance checks on CMIP7 outputs
+        if: steps.gather_outputs.outputs.cmip7_count != '0'
+        run: |
+          echo "Running WCRP compliance checks on CMIP7 files..."
+          echo "CMIP7 files to check: ${{ steps.gather_outputs.outputs.cmip7_count }}"
+          echo ""
+
+          mkdir -p tmp/wcrp_compliance_reports
+
+          for ncfile in tmp/qa_test_outputs/cmip7/*.nc; do
+            if [ -f "$ncfile" ]; then
+              basename=$(basename "$ncfile" .nc)
+              echo ""
+              echo "=========================================="
+              echo "Checking: ${basename}"
+              echo "=========================================="
+
+              # Run wcrp_cmip6 checker on CMIP7 files too
+              # (the plugin validates WCRP conventions applicable across versions)
+              compliance-checker \
+                --test=wcrp_cmip6 \
+                --format=text \
+                --output=tmp/wcrp_compliance_reports/cmip7_${basename}_report.txt \
+                "$ncfile" || true
+
+              compliance-checker \
+                --test=wcrp_cmip6 \
+                --format=json \
+                --output=tmp/wcrp_compliance_reports/cmip7_${basename}_report.json \
+                "$ncfile" 2>&1 || true
+
+              echo "Report summary:"
+              head -80 tmp/wcrp_compliance_reports/cmip7_${basename}_report.txt || true
+              echo ""
+            fi
+          done
+
+      - name: Generate summary report
+        if: steps.gather_outputs.outputs.file_count != '0'
+        run: |
+          mkdir -p tmp/wcrp_compliance_reports
+
+          echo "# WCRP Compliance Check Results" > tmp/wcrp_compliance_reports/SUMMARY.md
+          echo "" >> tmp/wcrp_compliance_reports/SUMMARY.md
+          echo "**Generated:** $(date -u +%Y-%m-%dT%H:%M:%SZ)" >> tmp/wcrp_compliance_reports/SUMMARY.md
+          echo "**Plugin:** [cc-plugin-wcrp](https://github.com/ESGF/cc-plugin-wcrp)" >> tmp/wcrp_compliance_reports/SUMMARY.md
+          echo "" >> tmp/wcrp_compliance_reports/SUMMARY.md
+          echo "## Files Checked" >> tmp/wcrp_compliance_reports/SUMMARY.md
+          echo "" >> tmp/wcrp_compliance_reports/SUMMARY.md
+          echo "- **Total:** ${{ steps.gather_outputs.outputs.file_count }} files" >> tmp/wcrp_compliance_reports/SUMMARY.md
+          echo "- **CMIP6:** ${{ steps.gather_outputs.outputs.cmip6_count }} files" >> tmp/wcrp_compliance_reports/SUMMARY.md
+          echo "- **CMIP7:** ${{ steps.gather_outputs.outputs.cmip7_count }} files" >> tmp/wcrp_compliance_reports/SUMMARY.md
+          echo "- **Other:** ${{ steps.gather_outputs.outputs.other_count }} files" >> tmp/wcrp_compliance_reports/SUMMARY.md
+          echo "" >> tmp/wcrp_compliance_reports/SUMMARY.md
+
+          cp tmp/qa_test_outputs/manifest.txt tmp/wcrp_compliance_reports/manifest.txt || true
+
+          cat tmp/wcrp_compliance_reports/SUMMARY.md
+
+      - name: Upload test outputs
+        if: always() && steps.gather_outputs.outputs.file_count != '0'
+        uses: actions/upload-artifact@v4
+        with:
+          name: wcrp-test-outputs
+          path: tmp/qa_test_outputs/
+          retention-days: 30
+
+      - name: Upload WCRP compliance reports
+        if: always() && steps.gather_outputs.outputs.file_count != '0'
+        uses: actions/upload-artifact@v4
+        with:
+          name: wcrp-compliance-reports
+          path: tmp/wcrp_compliance_reports/
+          retention-days: 30
+
+      - name: Check if any files were tested
+        if: steps.gather_outputs.outputs.file_count == '0'
+        run: |
+          echo "::warning::No NetCDF files were found to check for WCRP compliance"
+          echo "This may indicate that tests did not run successfully or outputs were not generated"
diff --git a/.gitignore b/.gitignore
index d4f20cc..df2b827 100644
--- a/.gitignore
+++ b/.gitignore
@@ -155,6 +155,9 @@ cython_debug/
 *.nc
 tmp/
 
+# QA results
+wcrp_compliance_reports/
+
 # autogen'd by doc build
 docs/fremorizer.*
 docs/modules.rst
diff --git a/README.md b/README.md
index d9b40d4..1b60062 100644
--- a/README.md
+++ b/README.md
@@ -17,6 +17,7 @@
 |----------|------------|-------------|------------|
 | **create_test_conda_env** | [![3.9](https://github.com/ilaflott/fremorizer/actions/workflows/create_test_conda_env.yml/badge.svg)](https://github.com/ilaflott/fremorizer/actions/workflows/create_test_conda_env.yml?query=branch%3Amain+python-version%3A3.9) | [![3.10](https://github.com/ilaflott/fremorizer/actions/workflows/create_test_conda_env.yml/badge.svg)](https://github.com/ilaflott/fremorizer/actions/workflows/create_test_conda_env.yml?query=branch%3Amain+python-version%3A3.10) | [![3.11](https://github.com/ilaflott/fremorizer/actions/workflows/create_test_conda_env.yml/badge.svg)](https://github.com/ilaflott/fremorizer/actions/workflows/create_test_conda_env.yml?query=branch%3Amain+python-version%3A3.11) |
 
+[![wcrp_compliance_check](https://github.com/ilaflott/fremorizer/actions/workflows/wcrp_compliance_check.yml/badge.svg?branch=main)](https://github.com/ilaflott/fremorizer/actions/workflows/wcrp_compliance_check.yml)
 
 Model output rewriter (CMORizer) for FRE/FMS based models.
 
@@ -113,6 +114,25 @@ pytest fremorizer/tests/ -v
 pylint --rcfile pylintrc fremorizer/
 ```
 
+## Quality Assurance
+
+### WCRP Compliance Checking
+
+The `wcrp_compliance_check` workflow validates CMORized NetCDF outputs against WCRP project
+specifications using [cc-plugin-wcrp](https://github.com/ESGF/cc-plugin-wcrp), a plugin for
+the [IOOS compliance-checker](https://github.com/ioos/compliance-checker). This pipeline:
+
+- Runs automatically on pull requests and via manual dispatch
+- Executes unit tests to generate CMORized output files
+- Gathers and categorizes outputs by CMIP version (CMIP6, CMIP7)
+- Validates outputs using the `wcrp_cmip6` compliance checker
+- Uploads compliance reports as workflow artifacts (retained for 30 days)
+
+To view compliance results from a workflow run:
+1. Navigate to the Actions tab in GitHub
+2. Select the `wcrp_compliance_check` workflow run
+3. Download the `wcrp-compliance-reports` artifact
+
 ## Relationship to fre-cli
 
 `fremorizer` is a near-exact copy of the `fre.cmor` submodule from
diff --git a/pyproject.toml b/pyproject.toml
index 7342526..72ca7f6 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -61,6 +61,10 @@ test = [
     "pytest",
 ]
 
+qa = [
+    "cc-plugin-wcrp",
+]
+
 
 [tool.rstcheck]
 report_level = "WARNING"

From b2347b960981fa47683032e7eff5bf692a326b89 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Tue, 14 Apr 2026 15:43:13 +0000
Subject: [PATCH 2/4] Plan: restructure wcrp_compliance_check pipeline

Agent-Logs-Url: https://github.com/ilaflott/fremorizer/sessions/9a306387-45f9-4cd4-a4c3-16157ba3e367

Co-authored-by: ilaflott <6273252+ilaflott@users.noreply.github.com>
---
 fremorizer/tests/test_files/CMOR_input_example.json | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fremorizer/tests/test_files/CMOR_input_example.json b/fremorizer/tests/test_files/CMOR_input_example.json
index 17e295e..66dfb83 100644
--- a/fremorizer/tests/test_files/CMOR_input_example.json
+++ b/fremorizer/tests/test_files/CMOR_input_example.json
@@ -19,9 +19,9 @@
     "branch_time_in_parent": 0.0,
     "institution_id": "PCMDI",
     "source_id": "PCMDI-test-1-0",
-    "calendar": "julian",
-    "grid": "regridded to FOO grid from native",
-    "grid_label": "gr",
+    "calendar": "noleap",
+    "grid": "FOO_PLACEHOLDER",
+    "grid_label": "gr1",
     "nominal_resolution": "10000 km",
     "license": "CMIP6 model data produced by Lawrence Livermore PCMDI is licensed under a Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0/). Consult https://pcmdi.llnl.gov/CMIP6/TermsOfUse for terms of use governing CMIP6 output, including citation requirements and proper acknowledgment. Further information about this data, including some limitations, can be found via the further_info_url (recorded as a global attribute in this file) and at https:///pcmdi.llnl.gov/. The data producers and data providers make no warranty, either express or implied, including, but not limited to, warranties of merchantability and fitness for a particular purpose. All liabilities arising from the supply of the information (including any liability arising in negligence) are excluded to the fullest extent permitted by law.",
     "#output": "Root directory for output (can be either a relative or full path)",

From 5231a36fc2ae7634bca087a876e412fd33019e12 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Tue, 14 Apr 2026 15:46:18 +0000
Subject: [PATCH 3/4] Fix gather script arithmetic bug, restructure workflow to
 run tests first

Agent-Logs-Url: https://github.com/ilaflott/fremorizer/sessions/9a306387-45f9-4cd4-a4c3-16157ba3e367

Co-authored-by: ilaflott <6273252+ilaflott@users.noreply.github.com>
---
 .github/scripts/gather_test_outputs.sh      | 14 ++--
 .github/workflows/wcrp_compliance_check.yml | 72 ++++++++++++++-------
 2 files changed, 54 insertions(+), 32 deletions(-)

diff --git a/.github/scripts/gather_test_outputs.sh b/.github/scripts/gather_test_outputs.sh
index f022c21..3726065 100755
--- a/.github/scripts/gather_test_outputs.sh
+++ b/.github/scripts/gather_test_outputs.sh
@@ -61,24 +61,24 @@ gather_files() {
             cmip_version="other"
             if [[ "${ncfile}" == *"CMIP6"* ]]; then
                 cmip_version="cmip6"
-                ((cmip6_files++))
+                cmip6_files=$((cmip6_files + 1))
             elif [[ "${ncfile}" == *"CMIP7"* ]]; then
                 cmip_version="cmip7"
-                ((cmip7_files++))
+                cmip7_files=$((cmip7_files + 1))
             else
                 # Try to detect from file attributes using ncdump
                 if command -v ncdump &> /dev/null; then
                     if ncdump -h "${ncfile}" 2>/dev/null | grep -q 'mip_era = "CMIP7"'; then
                         cmip_version="cmip7"
-                        ((cmip7_files++))
+                        cmip7_files=$((cmip7_files + 1))
                     elif ncdump -h "${ncfile}" 2>/dev/null | grep -q 'mip_era = "CMIP6"'; then
                         cmip_version="cmip6"
-                        ((cmip6_files++))
+                        cmip6_files=$((cmip6_files + 1))
                     else
-                        ((other_files++))
+                        other_files=$((other_files + 1))
                     fi
                 else
-                    ((other_files++))
+                    other_files=$((other_files + 1))
                 fi
             fi
 
@@ -95,7 +95,7 @@ gather_files() {
             # Add to manifest
             echo "${ncfile} -> ${cmip_version}/${unique_name}" >> "${MANIFEST}"
 
-            ((total_files++))
+            total_files=$((total_files + 1))
 
             echo "  found: ${ncfile}"
             echo "    -> ${cmip_version}/${unique_name}"
diff --git a/.github/workflows/wcrp_compliance_check.yml b/.github/workflows/wcrp_compliance_check.yml
index 95fe9c8..5f0a906 100644
--- a/.github/workflows/wcrp_compliance_check.yml
+++ b/.github/workflows/wcrp_compliance_check.yml
@@ -57,46 +57,35 @@ jobs:
             conda-forge::pyyaml \
             conda-forge::pytest
 
-      - name: Install cc-plugin-wcrp
-        run: |
-          pip install cc-plugin-wcrp
-
-      - name: Configure esgvoc controlled vocabularies
-        run: |
-          esgvoc config add cordex-cmip6
-          esgvoc config add cmip7
-          esgvoc config set project:branch=esgvoc
-          esgvoc install
-
-      - name: Verify cc-plugin-wcrp installation
-        run: |
-          echo "Listing available compliance-checker plugins..."
-          compliance-checker -l
-
       - name: Install fremorizer
         run: |
           pip install .
 
+      # ── generate test outputs (moved earlier, most fragile step) ──
       - name: Run tests to generate output files
+        id: run_tests
         run: |
           echo "Running test suite to generate NetCDF outputs..."
+          echo "Using --basetemp=tmp/pytest_basetemp to preserve pytest temp artifacts"
           echo ""
 
           echo "=========================================="
           echo "Running CMIP6 basic tests..."
           echo "=========================================="
-          pytest fremorizer/tests/test_cmor_run_subtool.py -v || true
+          pytest fremorizer/tests/test_cmor_run_subtool.py -v \
+            --basetemp=tmp/pytest_basetemp || true
 
           echo ""
           echo "=========================================="
           echo "Running extended test examples..."
           echo "=========================================="
-          pytest fremorizer/tests/test_cmor_run_subtool_further_examples.py -v || true
+          pytest fremorizer/tests/test_cmor_run_subtool_further_examples.py -v \
+            --basetemp=tmp/pytest_basetemp || true
 
           echo ""
           echo "Test execution complete."
-        continue-on-error: true
 
+      # ── gather and categorize outputs ──
       - name: Gather test outputs into centralized directory
         id: gather_outputs
         run: |
@@ -115,6 +104,44 @@ jobs:
           echo "cmip7_count=${cmip7_files}" >> $GITHUB_OUTPUT
           echo "other_count=${other_files}" >> $GITHUB_OUTPUT
 
+          echo ""
+          echo "Summary: total=${total_files} cmip6=${cmip6_files} cmip7=${cmip7_files} other=${other_files}"
+
+      - name: Verify outputs were gathered
+        if: steps.gather_outputs.outputs.file_count == '0'
+        run: |
+          echo "::warning::No NetCDF files were found after running tests"
+          echo "This may indicate that tests did not run successfully or outputs were not generated"
+          echo ""
+          echo "Checking known test output directories for debugging..."
+          echo "--- fremorizer/tests/test_files/outdir ---"
+          find fremorizer/tests/test_files/outdir -name "*.nc" -type f 2>/dev/null || echo "(empty or missing)"
+          echo "--- fremorizer/tests/test_files/outdir_ppan_only ---"
+          find fremorizer/tests/test_files/outdir_ppan_only -name "*.nc" -type f 2>/dev/null || echo "(empty or missing)"
+          echo "--- tmp/pytest_basetemp ---"
+          find tmp/pytest_basetemp -name "*.nc" -type f 2>/dev/null || echo "(empty or missing)"
+
+      # ── install cc-plugin-wcrp (after tests, since it's not needed until now) ──
+      - name: Install cc-plugin-wcrp
+        if: steps.gather_outputs.outputs.file_count != '0'
+        run: |
+          pip install cc-plugin-wcrp
+
+      - name: Configure esgvoc controlled vocabularies
+        if: steps.gather_outputs.outputs.file_count != '0'
+        run: |
+          esgvoc config add cordex-cmip6
+          esgvoc config add cmip7
+          esgvoc config set project:branch=esgvoc
+          esgvoc install
+
+      - name: Verify cc-plugin-wcrp installation
+        if: steps.gather_outputs.outputs.file_count != '0'
+        run: |
+          echo "Listing available compliance-checker plugins..."
+          compliance-checker -l
+
+      # ── run WCRP compliance checks ──
       - name: Run WCRP compliance checks on CMIP6 outputs
         if: steps.gather_outputs.outputs.cmip6_count != '0'
         run: |
@@ -190,6 +217,7 @@ jobs:
             fi
           done
 
+      # ── reports and artifacts ──
       - name: Generate summary report
         if: steps.gather_outputs.outputs.file_count != '0'
         run: |
@@ -227,9 +255,3 @@ jobs:
           name: wcrp-compliance-reports
           path: tmp/wcrp_compliance_reports/
           retention-days: 30
-
-      - name: Check if any files were tested
-        if: steps.gather_outputs.outputs.file_count == '0'
-        run: |
-          echo "::warning::No NetCDF files were found to check for WCRP compliance"
-          echo "This may indicate that tests did not run successfully or outputs were not generated"

From e3d729d1d5de574e926bf4267ba8847aa453e9ed Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Tue, 14 Apr 2026 16:45:31 +0000
Subject: [PATCH 4/4] Address review: use environment.yaml, add CLI/yamler
 tests, remove 'other' category

Agent-Logs-Url: https://github.com/ilaflott/fremorizer/sessions/077064d2-edaa-4d2e-9c77-e1fb6de5f59f

Co-authored-by: ilaflott <6273252+ilaflott@users.noreply.github.com>
---
 .github/scripts/gather_test_outputs.sh      | 34 ++++++++++++------
 .github/workflows/wcrp_compliance_check.yml | 40 ++++++++-------------
 2 files changed, 37 insertions(+), 37 deletions(-)

diff --git a/.github/scripts/gather_test_outputs.sh b/.github/scripts/gather_test_outputs.sh
index 3726065..d537600 100755
--- a/.github/scripts/gather_test_outputs.sh
+++ b/.github/scripts/gather_test_outputs.sh
@@ -2,36 +2,40 @@
 # Script to gather all NetCDF test outputs into a centralized location
 # This script is designed to be reusable by other QA pipelines (compliance-checker, etc.)
 #
-# Usage: gather_test_outputs.sh <output_directory>
+# Usage: gather_test_outputs.sh <output_directory> [basetemp_directory]
 #
 # The script:
 # 1. Searches for all NetCDF files generated by tests
 # 2. Copies them to a centralized directory with preserved structure
 # 3. Creates a manifest file listing all gathered files
 # 4. Categorizes files by CMIP version (CMIP6 vs CMIP7)
+# 5. Skips uncategorized files (e.g. statics) that are not expected to be compliant
 
 set -e
 
 # Default output directory if not specified
 OUTPUT_DIR="${1:-tmp/qa_test_outputs}"
+BASETEMP_DIR="${2:-}"
 
 echo "=========================================="
 echo "Gathering Test Outputs for QA Validation"
 echo "=========================================="
 echo "Output directory: ${OUTPUT_DIR}"
+if [ -n "${BASETEMP_DIR}" ]; then
+    echo "Basetemp directory: ${BASETEMP_DIR}"
+fi
 echo ""
 
 # Create the centralized output directory
 mkdir -p "${OUTPUT_DIR}"
 mkdir -p "${OUTPUT_DIR}/cmip6"
 mkdir -p "${OUTPUT_DIR}/cmip7"
-mkdir -p "${OUTPUT_DIR}/other"
 
 # Initialize counters
 total_files=0
 cmip6_files=0
 cmip7_files=0
-other_files=0
+skipped_files=0
 
 # Create manifest file
 MANIFEST="${OUTPUT_DIR}/manifest.txt"
@@ -58,11 +62,11 @@ gather_files() {
     while IFS= read -r -d '' ncfile; do
         if [ -f "${ncfile}" ]; then
             # Determine CMIP version from file path or content
-            cmip_version="other"
+            cmip_version=""
             if [[ "${ncfile}" == *"CMIP6"* ]]; then
                 cmip_version="cmip6"
                 cmip6_files=$((cmip6_files + 1))
-            elif [[ "${ncfile}" == *"CMIP7"* ]]; then
+            elif [[ "${ncfile}" == *"CMIP7"* ]] || [[ "${ncfile}" == *"CMIP/"* ]]; then
                 cmip_version="cmip7"
                 cmip7_files=$((cmip7_files + 1))
             else
@@ -74,14 +78,17 @@ gather_files() {
                     elif ncdump -h "${ncfile}" 2>/dev/null | grep -q 'mip_era = "CMIP6"'; then
                         cmip_version="cmip6"
                         cmip6_files=$((cmip6_files + 1))
-                    else
-                        other_files=$((other_files + 1))
                     fi
-                else
-                    other_files=$((other_files + 1))
                 fi
             fi
 
+            # Skip files that couldn't be categorized (e.g. statics files)
+            if [ -z "${cmip_version}" ]; then
+                skipped_files=$((skipped_files + 1))
+                echo "  skipped (uncategorized): ${ncfile}"
+                continue
+            fi
+
             # Create unique filename to avoid collisions
             basename=$(basename "${ncfile}")
             # Add a hash of the full path to ensure uniqueness
@@ -107,13 +114,18 @@ gather_files() {
 gather_files "fremorizer/tests/test_files/outdir" "CMIP6 basic tests"
 gather_files "fremorizer/tests/test_files/outdir_ppan_only" "Extended test examples"
 
+# Gather files from pytest basetemp directory (CLI and yamler tests)
+if [ -n "${BASETEMP_DIR}" ]; then
+    gather_files "${BASETEMP_DIR}" "pytest basetemp (CLI + yamler tests)"
+fi
+
 # Add summary to manifest
 echo "" >> "${MANIFEST}"
 echo "# Summary" >> "${MANIFEST}"
 echo "# Total files: ${total_files}" >> "${MANIFEST}"
 echo "# CMIP6 files: ${cmip6_files}" >> "${MANIFEST}"
 echo "# CMIP7 files: ${cmip7_files}" >> "${MANIFEST}"
-echo "# Other files: ${other_files}" >> "${MANIFEST}"
+echo "# Skipped files: ${skipped_files}" >> "${MANIFEST}"
 
 echo ""
 echo "=========================================="
@@ -122,7 +134,7 @@ echo "=========================================="
 echo "Total files gathered: ${total_files}"
 echo "  - CMIP6: ${cmip6_files}"
 echo "  - CMIP7: ${cmip7_files}"
-echo "  - Other: ${other_files}"
+echo "  - Skipped: ${skipped_files}"
 echo ""
 echo "Output directory: ${OUTPUT_DIR}"
 echo "Manifest file: ${MANIFEST}"
diff --git a/.github/workflows/wcrp_compliance_check.yml b/.github/workflows/wcrp_compliance_check.yml
index 5f0a906..b49cae0 100644
--- a/.github/workflows/wcrp_compliance_check.yml
+++ b/.github/workflows/wcrp_compliance_check.yml
@@ -28,7 +28,7 @@ jobs:
         uses: conda-incubator/setup-miniconda@v3
         with:
           activate-environment: fremorizer-wcrp
-          python-version: "3.12"
+          environment-file: environment.yaml
           auto-activate-base: false
           miniforge-version: latest
           channels: conda-forge,noaa-gfdl
@@ -46,17 +46,6 @@ jobs:
           echo "printing conda config just in case"
           conda config --show
 
-      - name: Install dependencies for fremorizer
-        run: |
-          conda install -y \
-            conda-forge::cftime \
-            "conda-forge::click>=8.2" \
-            "conda-forge::cmor>=3.14" \
-            "conda-forge::netcdf4>=1.7" \
-            "conda-forge::numpy>=2" \
-            conda-forge::pyyaml \
-            conda-forge::pytest
-
       - name: Install fremorizer
         run: |
           pip install .
@@ -69,18 +58,20 @@ jobs:
           echo "Using --basetemp=tmp/pytest_basetemp to preserve pytest temp artifacts"
           echo ""
 
-          echo "=========================================="
-          echo "Running CMIP6 basic tests..."
-          echo "=========================================="
-          pytest fremorizer/tests/test_cmor_run_subtool.py -v \
-            --basetemp=tmp/pytest_basetemp || true
+          # Create basetemp parent directory
+          mkdir -p tmp
 
-          echo ""
+          # Run ALL output-generating tests in a single pytest invocation
+          # so that --basetemp is only wiped once and all outputs are preserved.
           echo "=========================================="
-          echo "Running extended test examples..."
+          echo "Running all output-generating tests..."
           echo "=========================================="
-          pytest fremorizer/tests/test_cmor_run_subtool_further_examples.py -v \
-            --basetemp=tmp/pytest_basetemp || true
+          pytest \
+            fremorizer/tests/test_cmor_run_subtool.py \
+            fremorizer/tests/test_cmor_run_subtool_further_examples.py \
+            fremorizer/tests/test_cmor_yamler_subtool.py::test_cmor_yaml_subtool_dry_run_false \
+            fremorizer/tests/test_cli.py \
+            -v --basetemp=tmp/pytest_basetemp || true
 
           echo ""
           echo "Test execution complete."
@@ -89,7 +80,7 @@ jobs:
       - name: Gather test outputs into centralized directory
         id: gather_outputs
         run: |
-          bash .github/scripts/gather_test_outputs.sh tmp/qa_test_outputs
+          bash .github/scripts/gather_test_outputs.sh tmp/qa_test_outputs tmp/pytest_basetemp
 
           echo "output_dir=tmp/qa_test_outputs" >> $GITHUB_OUTPUT
 
@@ -98,14 +89,12 @@ jobs:
 
           cmip6_files=$(find tmp/qa_test_outputs/cmip6 -name "*.nc" -type f 2>/dev/null | wc -l || echo "0")
           cmip7_files=$(find tmp/qa_test_outputs/cmip7 -name "*.nc" -type f 2>/dev/null | wc -l || echo "0")
-          other_files=$(find tmp/qa_test_outputs/other -name "*.nc" -type f 2>/dev/null | wc -l || echo "0")
 
           echo "cmip6_count=${cmip6_files}" >> $GITHUB_OUTPUT
           echo "cmip7_count=${cmip7_files}" >> $GITHUB_OUTPUT
-          echo "other_count=${other_files}" >> $GITHUB_OUTPUT
 
           echo ""
-          echo "Summary: total=${total_files} cmip6=${cmip6_files} cmip7=${cmip7_files} other=${other_files}"
+          echo "Summary: total=${total_files} cmip6=${cmip6_files} cmip7=${cmip7_files}"
 
       - name: Verify outputs were gathered
         if: steps.gather_outputs.outputs.file_count == '0'
@@ -233,7 +222,6 @@ jobs:
           echo "- **Total:** ${{ steps.gather_outputs.outputs.file_count }} files" >> tmp/wcrp_compliance_reports/SUMMARY.md
           echo "- **CMIP6:** ${{ steps.gather_outputs.outputs.cmip6_count }} files" >> tmp/wcrp_compliance_reports/SUMMARY.md
           echo "- **CMIP7:** ${{ steps.gather_outputs.outputs.cmip7_count }} files" >> tmp/wcrp_compliance_reports/SUMMARY.md
-          echo "- **Other:** ${{ steps.gather_outputs.outputs.other_count }} files" >> tmp/wcrp_compliance_reports/SUMMARY.md
           echo "" >> tmp/wcrp_compliance_reports/SUMMARY.md
 
           cp tmp/qa_test_outputs/manifest.txt tmp/wcrp_compliance_reports/manifest.txt || true