V3.0.0 rc

.github/scripts/validate_schema_completeness.py

@@ -83,11 +83,11 @@
     "state_dir",
     # Exposed via negated CLI flag --no-slack
     "slack_enabled",
-    # Deacon tuning (set via params-file or preset)
-    "deacon_kmer_size",
-    "deacon_window_size",
-    "deacon_abs_threshold",
-    "deacon_rel_threshold",
+    # Host index/depletion tuning (set via params-file or preset)
+    "host_kmer_size",
+    "host_window_size",
+    "host_abs_threshold",
+    "host_rel_threshold",
 }
 
 

.github/workflows/ci.yml

@@ -113,16 +113,18 @@ jobs:
 
           echo "✅ Config syntax valid for ${{ matrix.profile }} profile"
 
-      - name: Verify required parameters exist
+      - name: Verify expected top-level parameters exist
         run: |
-          # Check that critical parameters are defined
-          for param in samplesheet experiment_id tools results; do
+          # Check that stable top-level parameters are defined in the rendered config.
+          # The v3 pipeline has a single main workflow, so there is no public
+          # `tools` selector parameter to validate here.
+          for param in samplesheet experiment_id results; do
             if ! grep -q "^\s*${param}\s*=" config_output.txt; then
-              echo "::error::Required parameter '${param}' not found in config"
+              echo "::error::Expected parameter '${param}' not found in config"
               exit 1
             fi
           done
-          echo "✅ All required parameters present"
+          echo "✅ All expected top-level parameters present"
 
   validate-config-includes:
     name: Validate Config File Includes

.gitignore

@@ -59,6 +59,7 @@
 # assets
 !/assets
 !/assets/example_samplesheet.csv
+!/assets/test_samplesheet.csv
 
 # docs
 !/docs
@@ -90,3 +91,7 @@
 !/.vscode/extensions.json
 !/.vscode/settings.json
 
+# testing data
+!/tests
+!/tests/data
+!/tests/data/*

Containerfile

@@ -15,7 +15,7 @@ ENV ~=/opt
 
 # run a few apt installs
 RUN apt-get update && \
-    apt-get install -y curl wget git gcc g++ cmake util-linux && \
+    apt-get install -y curl util-linux && \
     rm -rf /var/lib/apt/lists/* && \
     mkdir /dependencies && \
     dpkg -l > /dependencies/apt-get.lock
@@ -39,8 +39,7 @@ ENV PATH=$PATH:$HOME/.pixi/bin
 # 4) install everything else with pixi
 RUN cd $HOME && \
     script -q -c "pixi install --frozen" && \
-    script -q -c "pixi clean cache --assume-yes" && \
-    script -q -c "pixi add cxx-compiler cmake make"
+    script -q -c "pixi clean cache --assume-yes"
 
 # 5) Add pixi environment to PATH (works in Docker, Podman, AND Apptainer)
 ENV PATH=$PATH:/opt/.pixi/envs/default/bin
@@ -49,41 +48,5 @@ ENV PATH=$PATH:/opt/.pixi/envs/default/bin
 ENV NXF_CACHE_DIR=/scratch
 ENV NXF_HOME=/scratch
 
-# ----------------------------------------------------------------------------------- #
-
-# Copy necessary ncbi files
-COPY conf/user-settings.mkfg /.ncbi/user-settings.mkfg
-
-# Install NCBI tools and configure environment
-RUN mkdir -p /.ncbi && \
-    chmod 777 /.ncbi/user-settings.mkfg && \
-    mkdir /build && cd /build && \
-    git config --global http.sslVerify false && \
-    git clone -b 3.2.0 https://github.com/ncbi/ngs-tools.git && \
-    git clone -b 3.2.1 https://github.com/ncbi/ncbi-vdb.git && \
-    git clone -b 3.2.1 https://github.com/ncbi/sra-tools.git && \
-    sed -i 's/cmake_minimum_required[[:space:]]*([[:space:]]*VERSION[[:space:]]*2\.8\.12[[:space:]]*)/cmake_minimum_required(VERSION 3.5)/' /build/ngs-tools/CMakeLists.txt && \
-    echo "Verifying CMake version change:" && \
-    grep "cmake_minimum_required" /build/ngs-tools/CMakeLists.txt
-
-# Build ncbi-vdb, sra-tools and ngs-tools
-RUN cd /build/ncbi-vdb && \
-    ./configure --relative-build-out-dir && \
-    make -j$(nproc) && \
-    cd /build/sra-tools && \
-    ./configure --relative-build-out-dir && \
-    make -j$(nproc) && \
-    cd /build/ngs-tools && \
-    ./configure --relative-build-out-dir && \
-    make -j$(nproc) && \
-    # Copy built binaries and clean up in the same layer
-    find /build/OUTDIR -type f -executable -exec cp {} /usr/local/bin/ \; && \
-    cd / && rm -rf /build
-
-# remove now unnecessary compilers and clean the PyPI and conda caches
-RUN cd $HOME && pixi remove rust cxx-compiler cmake make && pixi clean cache --yes
-
 # Fix snakemake permission issue
 RUN mkdir /.cache; chmod a+rwX /.cache
-
-

assets/test_samplesheet.csv

@@ -0,0 +1,4 @@
+sample_id,srr,platform,fastq1,fastq2
+water,,illumina,tests/data/water_R1.fastq.gz,tests/data/water_R2.fastq.gz
+hits_only,,illumina,tests/data/hits_only_R1.fastq.gz,tests/data/hits_only_R2.fastq.gz
+water_plus_hits,,illumina,tests/data/water_plus_hits_R1.fastq.gz,tests/data/water_plus_hits_R2.fastq.gz

bin/check_run_state.py

@@ -466,10 +466,6 @@ def parse_args() -> argparse.Namespace:
         "--blast-db-version",
         help="BLAST database version (ignored - now passed to register_hits.py)",
     )
-    parser.add_argument(
-        "--stat-db-version",
-        help="STAT database version (ignored - now passed to register_hits.py)",
-    )
     parser.add_argument(
         "--lock-ttl",
         type=int,
@@ -479,7 +475,7 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument(
         "--upload-types",
         help="Comma-separated upload types to check for duplicate detection "
-        "(e.g., 'blast,blast_fasta' or 'gottcha2,gottcha2_fasta'). "
+        "(e.g., 'blast,blast_fasta'). "
         "When set, only uploads matching these types count as 'already uploaded'.",
     )
     parser.add_argument(