new reporting changes

docs/assay-schema.md

@@ -86,6 +86,7 @@ Rules:
 - `derived_from` lists the variant YAML files used by the interpretation
 - `emits` is optional but recommended so report generators know which output columns to display and how to label them
 - `logic` is optional; use `logic.description` and `logic.source.url` to document where the script's derivation rules came from
+- Analysis rows may emit `notes` or `report_notes` as a reporting convention. HTML reports render those notes below the analysis table and omit them from the table columns; this avoids a manifest-level template language while still letting the script build human-readable text from computed values.
 
 ## Findings
 

rust/bioscript-cli/Cargo.toml

@@ -13,10 +13,8 @@ bioscript-formats = { path = "../bioscript-formats" }
 bioscript-runtime = { path = "../bioscript-runtime" }
 bioscript-schema = { path = "../bioscript-schema" }
 monty = { path = "../../monty/crates/monty" }
-serde_json = "1.0.133"
+serde_json = { version = "1.0.133", features = ["preserve_order"] }
 serde_yaml = "0.9.34"
-
-[dev-dependencies]
 zip = { version = "2.2.0", default-features = false, features = ["deflate"] }
 
 [lints.clippy]

rust/bioscript-cli/src/cli_bootstrap.rs

@@ -9,8 +9,9 @@ use std::{
 };
 
 use bioscript_formats::{
-    GenotypeLoadOptions, GenotypeSourceFormat, GenotypeStore, InspectOptions, PrepareRequest,
-    inspect_file, prepare_indexes, shell_flags,
+    GenotypeLoadOptions, GenotypeSourceFormat, GenotypeStore, InferredSex, InspectOptions,
+    PrepareRequest, SexDetectionConfidence, SexInference, inspect_file, prepare_indexes,
+    shell_flags,
 };
 use bioscript_runtime::{BioscriptRuntime, RuntimeConfig, StageTiming};
 use bioscript_schema::{
@@ -46,6 +47,8 @@ fn run_cli() -> Result<(), String> {
     normalize_loader_paths(&runtime_root, &mut options.loader);
     let mut cli_timings = prepare_cli_indexes(&runtime_root, &mut options)?;
 
+    let script_path = prepare_package_entrypoint_from_arg(&runtime_root, &script_path)?;
+
     if is_yaml_manifest(&script_path) {
         run_cli_manifest(&runtime_root, &script_path, &options, &mut cli_timings)?;
     } else {
@@ -54,7 +57,7 @@ fn run_cli() -> Result<(), String> {
     Ok(())
 }
 
-const USAGE: &str = "usage: bioscript <script.py|manifest.yaml> [--root <dir>] [--input-file <path>] [--output-file <path>] [--participant-id <id>] [--trace-report <path>] [--timing-report <path>] [--filter key=value] [--input-format auto|text|zip|vcf|cram] [--input-index <path>] [--reference-file <path>] [--reference-index <path>] [--auto-index] [--cache-dir <path>] [--max-duration-ms N] [--max-memory-bytes N] [--max-allocations N] [--max-recursion-depth N]\n       bioscript report <manifest.yaml> --input-file <path> [--input-file <path>...] --output-dir <dir> [--html] [--root <dir>] [--input-format auto|text|zip|vcf|cram]\n       bioscript validate-variants <path> [--report <file>]\n       bioscript validate-panels <path> [--report <file>]\n       bioscript validate-assays <path> [--report <file>]\n       bioscript prepare [--root <dir>] [--input-file <path>] [--reference-file <path>] [--input-format auto|text|zip|vcf|cram] [--cache-dir <path>]\n       bioscript inspect <path> [--input-index <path>] [--reference-file <path>] [--reference-index <path>]";
+const USAGE: &str = "usage: bioscript <script.py|manifest.yaml|package.zip|https://.../package.zip> [--root <dir>] [--input-file <path>] [--output-file <path>] [--participant-id <id>] [--trace-report <path>] [--timing-report <path>] [--filter key=value] [--input-format auto|text|zip|vcf|cram] [--input-index <path>] [--reference-file <path>] [--reference-index <path>] [--auto-index] [--cache-dir <path>] [--max-duration-ms N] [--max-memory-bytes N] [--max-allocations N] [--max-recursion-depth N]\n       bioscript report <manifest.yaml|package.zip|https://.../package.zip> --input-file <path> [--input-file <path>...] --output-dir <dir> [--html] [--open] [--root <dir>] [--input-format auto|text|zip|vcf|cram] [--detect-sex] [--sample-sex male|female|unknown] [--analysis-max-duration-ms N]\n       bioscript review <manifest.yaml|package.zip> --cases <cases.yaml> --output-dir <dir> [--html] [--root <dir>] [--filter key=value]\n       bioscript import-package <package.zip|https://.../package.zip> [--root <dir>] [--output-dir <dir>]\n       bioscript validate-variants <path> [--report <file>]\n       bioscript validate-panels <path> [--report <file>]\n       bioscript validate-assays <path> [--report <file>]\n       bioscript prepare [--root <dir>] [--input-file <path>] [--reference-file <path>] [--input-format auto|text|zip|vcf|cram] [--cache-dir <path>]\n       bioscript inspect <path> [--input-index <path>] [--reference-file <path>] [--reference-index <path>] [--detect-sex]";
 
 struct CliOptions {
     script_path: Option<PathBuf>,
@@ -78,6 +81,8 @@ fn dispatch_subcommand(args: &[String]) -> Result<bool, String> {
     let rest = rest.to_vec();
     match first.as_str() {
         "report" => run_app_report(rest).map(|()| true),
+        "review" => run_review_report(rest).map(|()| true),
+        "import-package" => run_import_package(rest).map(|()| true),
         "validate-variants" => run_validate_variants(rest).map(|()| true),
         "validate-panels" => run_validate_panels(rest).map(|()| true),
         "validate-assays" => run_validate_assays(rest).map(|()| true),
@@ -411,4 +416,3 @@ fn write_timing_report(path: &PathBuf, timings: &[StageTiming]) -> Result<(), St
     fs::write(path, output)
         .map_err(|err| format!("failed to write timing report {}: {err}", path.display()))
 }
-

rust/bioscript-cli/src/cli_commands.rs

@@ -88,6 +88,9 @@ fn run_inspect(args: Vec<String>) -> Result<(), String> {
                     iter.next().ok_or("--reference-index requires a path")?,
                 ));
             }
+            "--detect-sex" => {
+                options.detect_sex = true;
+            }
             other if path.is_none() => {
                 path = Some(PathBuf::from(other));
             }
@@ -99,7 +102,7 @@ fn run_inspect(args: Vec<String>) -> Result<(), String> {
 
     let Some(path) = path else {
         return Err(
-            "usage: bioscript inspect <path> [--input-index <path>] [--reference-file <path>] [--reference-index <path>]"
+            "usage: bioscript inspect <path> [--input-index <path>] [--reference-file <path>] [--reference-index <path>] [--detect-sex]"
                 .to_owned(),
         );
     };

rust/bioscript-cli/src/commands.rs

@@ -94,6 +94,9 @@ pub(crate) fn run_inspect(args: Vec<String>) -> Result<(), String> {
                     iter.next().ok_or("--reference-index requires a path")?,
                 ));
             }
+            "--detect-sex" => {
+                options.detect_sex = true;
+            }
             other if path.is_none() => {
                 path = Some(PathBuf::from(other));
             }
@@ -105,7 +108,7 @@ pub(crate) fn run_inspect(args: Vec<String>) -> Result<(), String> {
 
     let Some(path) = path else {
         return Err(
-            "usage: bioscript inspect <path> [--input-index <path>] [--reference-file <path>] [--reference-index <path>]"
+            "usage: bioscript inspect <path> [--input-index <path>] [--reference-file <path>] [--reference-index <path>] [--detect-sex]"
                 .to_owned(),
         );
     };

rust/bioscript-cli/src/main.rs

@@ -4,8 +4,11 @@
 include!("cli_bootstrap.rs");
 include!("cli_commands.rs");
 include!("report_options.rs");
+include!("package.rs");
+include!("report_review.rs");
 include!("report_execution.rs");
 include!("report_observations.rs");
+include!("report_findings.rs");
 include!("report_matching.rs");
 include!("report_output.rs");
 include!("report_html.rs");

rust/bioscript-cli/src/manifest.rs

@@ -198,6 +198,10 @@ pub(crate) fn variant_row(
             .depth
             .map_or_else(String::new, |value| value.to_string()),
     );
+    row.insert(
+        "raw_counts".to_owned(),
+        serde_json::to_string(&observation.raw_counts).unwrap_or_default(),
+    );
     row.insert("evidence".to_owned(), observation.evidence.join(" | "));
     row
 }

rust/bioscript-cli/src/manifest_runner.rs

@@ -79,6 +79,15 @@ fn run_variant_manifest(
     let input_file = input_file.ok_or("manifest execution requires --input-file")?;
     let store = GenotypeStore::from_file_with_options(Path::new(input_file), loader)
         .map_err(|err| err.to_string())?;
+    run_variant_manifest_with_store(runtime_root, manifest, &store, participant_id)
+}
+
+fn run_variant_manifest_with_store(
+    runtime_root: &Path,
+    manifest: &VariantManifest,
+    store: &GenotypeStore,
+    participant_id: Option<&str>,
+) -> Result<BTreeMap<String, String>, String> {
     let observation = store
         .lookup_variant(&manifest.spec)
         .map_err(|err| err.to_string())?;
@@ -103,6 +112,16 @@ fn run_panel_manifest(
     let input_file = input_file.ok_or("manifest execution requires --input-file")?;
     let store = GenotypeStore::from_file_with_options(Path::new(input_file), loader)
         .map_err(|err| err.to_string())?;
+    run_panel_manifest_with_store(runtime_root, panel, &store, participant_id, filters)
+}
+
+fn run_panel_manifest_with_store(
+    runtime_root: &Path,
+    panel: &PanelManifest,
+    store: &GenotypeStore,
+    participant_id: Option<&str>,
+    filters: &[String],
+) -> Result<Vec<BTreeMap<String, String>>, String> {
     let mut rows = Vec::new();
 
     for member in &panel.members {
@@ -115,23 +134,18 @@ fn run_panel_manifest(
             if !matches_filters(&manifest, &resolved, filters) {
                 continue;
             }
-            let observation = store
-                .lookup_variant(&manifest.spec)
-                .map_err(|err| err.to_string())?;
-            rows.push(variant_row(
+            rows.push(run_variant_manifest_with_store(
                 runtime_root,
-                &resolved,
-                &manifest.name,
-                &manifest.tags,
-                &observation,
+                &manifest,
+                store,
                 participant_id,
-            ));
+            )?);
         } else if member.kind == "assay" {
             let assay = load_assay_manifest(&resolved)?;
             rows.extend(run_assay_manifest_with_store(
                 runtime_root,
                 &assay,
-                &store,
+                store,
                 participant_id,
                 filters,
             )?);
@@ -260,6 +274,10 @@ fn variant_row(
             .depth
             .map_or_else(String::new, |value| value.to_string()),
     );
+    row.insert(
+        "raw_counts".to_owned(),
+        serde_json::to_string(&observation.raw_counts).unwrap_or_default(),
+    );
     row.insert("evidence".to_owned(), observation.evidence.join(" | "));
     row
 }