fix(import): headless import refuses instead of silently succeeding (improvise-8jk6.4, improvise-8jk6.5, improvise-8jk6.6)

- 8jk6.4: the CSV parser yields source text (CsvRecords), and only the
  role reads it as a number. A forced category keeps 00565796 and
  220944e2 verbatim; measures and analysis read the text through
  csv_parser::number_in. CsvRecords reaches a pipeline only through
  ImportPipeline::from_csv, so handing CSV text to the JSON constructor
  no longer compiles.
- 8jk6.5: an import formula that does not parse is refused by name with
  its parse error: the build refuses (headless exits non-zero and writes
  nothing), and the wizard keeps it out of the list with the text still
  in the buffer.
- 8jk6.6: an import that kept no record refuses and says why, from the
  build and from the wizard's review step. A partial skip stays a
  warning with a count and exit 0.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VdfEGXA7aJ6ftMsCc9PJze

crates/improvise-command/src/ui/effect.rs

@@ -1239,7 +1239,7 @@ pub struct ImportJsonHeadless {
 }
 impl Effect for ImportJsonHeadless {
     fn apply(&self, app: &mut App) {
-        use crate::import::analyzer::{FieldKind, analyze_records};
+        use crate::import::analyzer::FieldKind;
         use crate::import::wizard::{DuplicatePolicy, ImportPipeline};
 
         let is_csv = self
@@ -1247,10 +1247,10 @@ impl Effect for ImportJsonHeadless {
             .extension()
             .is_some_and(|ext| ext.eq_ignore_ascii_case("csv"));
 
-        // Parse the file exactly once: `records` feeds analysis, `raw` is reused
-        // as the pipeline's value (improvise-oaq). CSV warnings go to the status.
+        // Parse the file exactly once, into the pipeline that reads it
+        // (improvise-oaq, improvise-8jk6.4). CSV warnings go to the status.
         let mut warnings: Vec<String> = vec![];
-        let (records, raw) = if is_csv {
+        let mut pipeline = if is_csv {
             let bytes = match app.storage.read(&self.path) {
                 Ok(b) => b,
                 Err(e) => {
@@ -1261,8 +1261,7 @@ impl Effect for ImportJsonHeadless {
             match crate::import::csv_parser::parse_csv_bytes_with_warnings(&bytes) {
                 Ok((recs, w)) => {
                     warnings = w;
-                    let raw = serde_json::Value::Array(recs.clone());
-                    (recs, raw)
+                    ImportPipeline::from_csv(recs)
                 }
                 Err(e) => {
                     refuse_and_stop(app, format!("CSV error: {e}"));
@@ -1285,38 +1284,28 @@ impl Effect for ImportJsonHeadless {
                 }
             };
             match json_import_records(&value, self.array_path.as_deref()) {
-                Ok(recs) => (recs, value),
+                Ok(recs) => {
+                    let mut pipeline = ImportPipeline::new(value);
+                    pipeline.selected_path = self.array_path.clone().unwrap_or_default();
+                    pipeline.records = recs;
+                    pipeline.analyze();
+                    pipeline
+                }
                 Err(msg) => {
                     refuse_and_stop(app, msg);
                     return;
                 }
             }
         };
-
-        let proposals = analyze_records(&records);
-
-        let pipeline = ImportPipeline {
-            raw,
-            array_paths: vec![],
-            selected_path: self.array_path.as_deref().unwrap_or("").to_string(),
-            records,
-            proposals: proposals
-                .into_iter()
-                .map(|mut p| {
-                    p.accepted = p.kind != FieldKind::Label;
-                    p
-                })
-                .collect(),
-            model_name: self
-                .model_name
-                .as_deref()
-                .unwrap_or("Imported Model")
-                .to_string(),
-            formulas: vec![],
-            // Headless: nobody to ask, so a collision refuses (improvise-cgqt).
-            on_duplicate: DuplicatePolicy::Refuse,
-            sources: vec![],
-        };
+        pipeline.model_name = self
+            .model_name
+            .clone()
+            .unwrap_or_else(|| "Imported Model".to_string());
+        // Headless: nobody to ask, so a collision refuses (improvise-cgqt).
+        pipeline.on_duplicate = DuplicatePolicy::Refuse;
+        for p in &mut pipeline.proposals {
+            p.accepted = p.kind != FieldKind::Label;
+        }
 
         match pipeline.build_model_with_warnings() {
             Ok((new_workbook, build_warnings)) => {

crates/improvise-io/src/import/csv_parser.rs

@@ -7,14 +7,32 @@ use serde_json::Value;
 
 use crate::storage::{PhysicalFs, Storage};
 
+/// Parsed CSV records. Every value is its source text, so they reach an import
+/// only through `ImportPipeline::from_csv` (improvise-8jk6.4).
+#[derive(Debug, Clone, Default, PartialEq)]
+pub struct CsvRecords(Vec<Value>);
+
+impl std::ops::Deref for CsvRecords {
+    type Target = [Value];
+    fn deref(&self) -> &[Value] {
+        &self.0
+    }
+}
+
+impl CsvRecords {
+    pub(crate) fn into_values(self) -> Vec<Value> {
+        self.0
+    }
+}
+
 pub fn csv_path_p(path: &Path) -> bool {
     path.extension()
         .is_some_and(|ext| ext.eq_ignore_ascii_case("csv"))
 }
 
-/// Parse a CSV file into a `serde_json::Value` array. Short-row warnings go to
-/// stderr; [`parse_csv_with_warnings`] captures them instead.
-pub fn parse_csv(path: &Path) -> Result<Vec<Value>> {
+/// Parse a CSV file into records. Short-row warnings go to stderr;
+/// [`parse_csv_with_warnings`] captures them instead.
+pub fn parse_csv(path: &Path) -> Result<CsvRecords> {
     let (records, warnings) = parse_csv_with_warnings(path)?;
     for warning in &warnings {
         eprintln!("warning: {warning}");
@@ -24,7 +42,7 @@ pub fn parse_csv(path: &Path) -> Result<Vec<Value>> {
 
 /// Parse a CSV file, returning records plus warnings. A short row keeps every
 /// header column, missing ones `Null`, each reported with a row count.
-pub fn parse_csv_with_warnings(path: &Path) -> Result<(Vec<Value>, Vec<String>)> {
+pub fn parse_csv_with_warnings(path: &Path) -> Result<(CsvRecords, Vec<String>)> {
     let bytes = std::fs::read(path)
         .with_context(|| format!("Failed to open CSV file: {}", path.display()))?;
     parse_csv_bytes_with_warnings(&bytes)
@@ -32,9 +50,9 @@ pub fn parse_csv_with_warnings(path: &Path) -> Result<(Vec<Value>, Vec<String>)>
 
 /// As [`parse_csv_with_warnings`] but over bytes, so import can come from any
 /// [`Storage`](crate::storage::Storage) backend, not only a file (improvise-fuj).
-pub fn parse_csv_bytes_with_warnings(bytes: &[u8]) -> Result<(Vec<Value>, Vec<String>)> {
+pub fn parse_csv_bytes_with_warnings(bytes: &[u8]) -> Result<(CsvRecords, Vec<String>)> {
     let (_, records, warnings) = parse_csv_bytes(bytes)?;
-    Ok((records, warnings))
+    Ok((CsvRecords(records), warnings))
 }
 
 /// The header (after renaming), the records and the warnings.
@@ -152,7 +170,7 @@ fn disambiguate_headers(raw: Vec<String>) -> (Vec<String>, Vec<String>) {
 
 /// Parse multiple CSV files and merge into a single JSON array.
 /// Each record gets a "File" field set to the filename stem (e.g., "sales" from "sales.csv").
-pub fn merge_csvs(paths: &[impl AsRef<Path>]) -> Result<Vec<Value>> {
+pub fn merge_csvs(paths: &[impl AsRef<Path>]) -> Result<CsvRecords> {
     let merged = merge_csvs_from(&PhysicalFs, paths)?;
     for warning in &merged.warnings {
         eprintln!("warning: {warning}");
@@ -173,7 +191,7 @@ pub struct SourceFile {
 /// Several CSV files as one record set, with each file's own columns kept.
 #[derive(Debug, Clone, PartialEq)]
 pub struct Merged {
-    pub records: Vec<Value>,
+    pub records: CsvRecords,
     /// One per distinct `File` item, in the order the files were read.
     pub sources: Vec<SourceFile>,
     /// Each file's parse warnings, prefixed with its path.
@@ -184,7 +202,7 @@ pub struct Merged {
 /// and two files with one stem share its item and its columns (improvise-lpzu).
 pub fn merge_csvs_from(fs: &dyn Storage, paths: &[impl AsRef<Path>]) -> Result<Merged> {
     let mut merged = Merged {
-        records: Vec::new(),
+        records: CsvRecords::default(),
         sources: Vec::new(),
         warnings: Vec::new(),
     };
@@ -212,7 +230,7 @@ pub fn merge_csvs_from(fs: &dyn Storage, paths: &[impl AsRef<Path>]) -> Result<M
             if let Value::Object(ref mut map) = record {
                 map.insert(FILE_CATEGORY.to_string(), Value::String(stem.clone()));
             }
-            merged.records.push(record);
+            merged.records.0.push(record);
         }
     }
     Ok(merged)
@@ -266,26 +284,33 @@ fn csv_documents_in(fs: &dyn Storage, dir: &Path) -> Result<Vec<PathBuf>> {
     Ok(csvs)
 }
 
+/// A field is its source text: which ones are numbers is decided by the role
+/// the import gives the column (improvise-8jk6.4, `context/code/formula-and-io.md`).
 fn parse_csv_field(field: &str) -> Value {
-    if field.is_empty() {
-        return Value::Null;
+    match field.is_empty() {
+        true => Value::Null,
+        false => Value::String(field.to_string()),
     }
+}
 
-    // Try to parse as number (integer or float)
-    if let Ok(num) = field.parse::<i64>() {
-        return Value::Number(serde_json::Number::from(num));
+/// The number a CSV field's text reads as, where a number is wanted.
+pub fn number_in(text: &str) -> Option<serde_json::Number> {
+    if let Ok(num) = text.parse::<i64>() {
+        return Some(serde_json::Number::from(num));
     }
-
     // NaN and the infinities have no JSON number. A fabricated 0 is an invented
-    // measurement (improvise-jc95), so the token falls through and stays text.
-    if let Ok(num) = field.parse::<f64>()
-        && let Some(number) = serde_json::Number::from_f64(num)
-    {
-        return Value::Number(number);
-    }
+    // measurement (improvise-jc95), so the token stays text.
+    text.parse::<f64>()
+        .ok()
+        .and_then(serde_json::Number::from_f64)
+}
 
-    // Otherwise treat as string
-    Value::String(field.to_string())
+/// A CSV value as a typed JSON value: numeric text becomes its number.
+pub fn typed(value: &Value) -> Value {
+    match value.as_str().and_then(number_in) {
+        Some(number) => Value::Number(number),
+        None => value.clone(),
+    }
 }
 
 #[cfg(test)]
@@ -310,8 +335,9 @@ mod tests {
         assert_eq!(records.len(), 2);
         assert_eq!(records[0]["Region"], Value::String("East".to_string()));
         assert_eq!(records[0]["Product"], Value::String("Shirts".to_string()));
+        assert_eq!(records[0]["Revenue"], Value::String("1000".to_string()));
         assert_eq!(
-            records[0]["Revenue"],
+            typed(&records[0]["Revenue"]),
             Value::Number(serde_json::Number::from(1000))
         );
     }
@@ -323,9 +349,10 @@ mod tests {
         let records = parse_csv(&path).unwrap();
 
         assert_eq!(records.len(), 2);
-        assert!(records[0]["Revenue"].is_f64());
+        assert_eq!(records[0]["Revenue"], Value::String("1000.50".to_string()));
+        assert!(typed(&records[0]["Revenue"]).is_f64());
         assert_eq!(
-            records[0]["Revenue"],
+            typed(&records[0]["Revenue"]),
             Value::Number(serde_json::Number::from_f64(1000.50).unwrap())
         );
     }
@@ -363,10 +390,10 @@ mod tests {
         assert_eq!(records.len(), 2);
         assert_eq!(records[0]["Name"], Value::String("Widget".to_string()));
         assert_eq!(
-            records[0]["Count"],
+            typed(&records[0]["Count"]),
             Value::Number(serde_json::Number::from(5))
         );
-        assert!(records[0]["Price"].is_f64());
+        assert!(typed(&records[0]["Price"]).is_f64());
         assert_eq!(records[0]["Active"], Value::String("true".to_string()));
     }
 
@@ -386,10 +413,7 @@ mod tests {
         assert_eq!(records[3]["File"], Value::String("expenses".to_string()));
         // Original fields preserved
         assert_eq!(records[0]["Region"], Value::String("East".to_string()));
-        assert_eq!(
-            records[2]["Revenue"],
-            Value::Number(serde_json::Number::from(50))
-        );
+        assert_eq!(records[2]["Revenue"], Value::String("50".to_string()));
     }
 
     #[test]
@@ -492,10 +516,10 @@ mod tests {
             ]
         );
         assert_eq!(
-            merged.records,
+            *merged.records,
             [
-                serde_json::json!({"entity": "src/a.rs", "coupled": "src/b.rs", "degree": 80, "File": "coupling"}),
-                serde_json::json!({"entity": "src/a.rs", "age-months": 2, "File": "age"}),
+                serde_json::json!({"entity": "src/a.rs", "coupled": "src/b.rs", "degree": "80", "File": "coupling"}),
+                serde_json::json!({"entity": "src/a.rs", "age-months": "2", "File": "age"}),
             ]
         );
     }
@@ -640,10 +664,7 @@ mod tests {
         assert!(warnings.is_empty());
         assert_eq!(records.len(), 2);
         assert_eq!(records[0]["Region"], Value::String("East".to_string()));
-        assert_eq!(
-            records[0]["Revenue"],
-            Value::Number(serde_json::Number::from(1))
-        );
+        assert_eq!(records[0]["Revenue"], Value::String("1".to_string()));
         assert_eq!(records[1]["Region"], Value::String("West".to_string()));
 
         let (control, _) = parse_csv_bytes_with_warnings(b"Region,Revenue\nEa\rst,1\n").unwrap();
@@ -698,7 +719,8 @@ mod tests {
                 token.parse::<f64>().is_ok_and(|n| !n.is_finite()),
                 "precondition: {token} parses as a non-finite f64"
             );
-            assert_eq!(parse_csv_field(token), Value::String(token.to_string()));
+            let text = Value::String(token.to_string());
+            assert_eq!(typed(&text), text);
         }
     }
 
@@ -707,10 +729,10 @@ mod tests {
     #[test]
     fn an_ordinary_float_is_still_a_number() {
         assert_eq!(
-            parse_csv_field("1000.50"),
+            typed(&Value::String("1000.50".into())),
             Value::Number(serde_json::Number::from_f64(1000.50).unwrap())
         );
-        assert_eq!(parse_csv_field("0"), Value::Number(0.into()));
+        assert_eq!(typed(&Value::String("0".into())), Value::Number(0.into()));
     }
 
     /// improvise-5hfh: two equal header names are one JSON key, so the later
@@ -719,9 +741,9 @@ mod tests {
     fn a_repeated_header_is_renamed_rather_than_overwriting_its_twin() {
         let (records, warnings) = parse_csv_bytes_with_warnings(b"A,B,A\n1,2,3\n").unwrap();
         let map = records[0].as_object().unwrap();
-        assert_eq!(map["A"], Value::Number(1.into()));
-        assert_eq!(map["B"], Value::Number(2.into()));
-        assert_eq!(map["A_2"], Value::Number(3.into()));
+        assert_eq!(map["A"], Value::String("1".into()));
+        assert_eq!(map["B"], Value::String("2".into()));
+        assert_eq!(map["A_2"], Value::String("3".into()));
         assert_eq!(warnings.len(), 1);
         assert!(warnings[0].contains("'A'") && warnings[0].contains("'A_2'"));
         assert!(warnings[0].contains("column 3"), "{}", warnings[0]);
@@ -734,8 +756,8 @@ mod tests {
         let (records, _) = parse_csv_bytes_with_warnings(b"A,A_2,A\n1,2,3\n").unwrap();
         let map = records[0].as_object().unwrap();
         assert_eq!(map.len(), 3, "{map:?}");
-        assert_eq!(map["A_2"], Value::Number(2.into()));
-        assert_eq!(map["A_3"], Value::Number(3.into()));
+        assert_eq!(map["A_2"], Value::String("2".into()));
+        assert_eq!(map["A_3"], Value::String("3".into()));
     }
 
     #[test]
@@ -770,8 +792,9 @@ mod tests {
 
         assert_eq!(records.len(), 2);
         assert_eq!(records[0]["Date"], Value::String("03/31/2026".to_string()));
+        assert_eq!(records[0]["Amount"], Value::String("-50.00".to_string()));
         assert_eq!(
-            records[0]["Amount"],
+            typed(&records[0]["Amount"]),
             Value::Number(serde_json::Number::from_f64(-50.00).unwrap())
         );
         assert_eq!(records[0]["Flag"], Value::String("*".to_string()));
@@ -781,7 +804,7 @@ mod tests {
             Value::String("VENMO PAYMENT 260331".to_string())
         );
         assert_eq!(
-            records[1]["Amount"],
+            typed(&records[1]["Amount"]),
             Value::Number(serde_json::Number::from_f64(-240.00).unwrap())
         );
     }

crates/improvise-io/src/import/wizard.rs

@@ -7,8 +7,8 @@ use super::analyzer::{
     DateComponent, FieldKind, FieldProposal, analyze_records, extract_array_at_path,
     extract_date_component, find_array_paths,
 };
-use super::csv_parser::{FILE_CATEGORY, SourceFile};
-use crate::formula::parse_formula;
+use super::csv_parser::{self, CsvRecords, FILE_CATEGORY, SourceFile};
+use crate::formula::{Formula, parse_formula};
 use crate::model::MAX_CATEGORIES;
 use crate::model::cell::{CellKey, CellValue};
 use crate::view::{Axis, VIRTUAL_VIEW_NAMES, View};
@@ -33,6 +33,42 @@ pub struct ImportPipeline {
     /// The files a CSV merge read, each of which gets its own view. Empty for
     /// a single file or a JSON import (improvise-lpzu).
     pub sources: Vec<SourceFile>,
+    /// What the records' string values are, fixed by the constructor (8jk6.4).
+    scalars: Scalars,
+}
+
+/// How a record's values read. Why CSV is text: `context/code/formula-and-io.md`.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum Scalars {
+    /// JSON: a string is text and a number is a number.
+    Typed,
+    /// CSV: every value is source text, read as a number only where one is wanted.
+    Text,
+}
+
+impl Scalars {
+    /// The record as analysis sees it: typed, whatever its source.
+    fn typed_record(self, record: &Value) -> Value {
+        match (self, record) {
+            (Scalars::Text, Value::Object(map)) => Value::Object(
+                map.iter()
+                    .map(|(k, v)| (k.clone(), csv_parser::typed(v)))
+                    .collect(),
+            ),
+            (Scalars::Text, other) | (Scalars::Typed, other) => other.clone(),
+        }
+    }
+
+    /// The value a measure takes from `value`, if it is a number.
+    fn number(self, value: &Value) -> Option<f64> {
+        match self {
+            Scalars::Typed => value.as_f64(),
+            Scalars::Text => value
+                .as_str()
+                .and_then(csv_parser::number_in)
+                .and_then(|n| n.as_f64()),
+        }
+    }
 }
 
 /// Several source records that land on one coordinate tuple (improvise-cgqt).
@@ -57,7 +93,17 @@ pub enum DuplicatePolicy {
 }
 
 impl ImportPipeline {
+    /// A pipeline over a JSON value.
     pub fn new(raw: Value) -> Self {
+        Self::reading(raw, Scalars::Typed)
+    }
+
+    /// A pipeline over CSV records, whose values are their source text.
+    pub fn from_csv(records: CsvRecords) -> Self {
+        Self::reading(Value::Array(records.into_values()), Scalars::Text)
+    }
+
+    fn reading(raw: Value, scalars: Scalars) -> Self {
         let array_paths = find_array_paths(&raw);
         let mut pipeline = Self {
             raw: raw.clone(),
@@ -69,6 +115,7 @@ impl ImportPipeline {
             formulas: vec![],
             on_duplicate: DuplicatePolicy::Refuse,
             sources: vec![],
+            scalars,
         };
 
         // Auto-select if root is an array or there is exactly one candidate path.
@@ -86,7 +133,46 @@ impl ImportPipeline {
         self.selected_path = path.to_string();
         if let Some(arr) = extract_array_at_path(&self.raw, path) {
             self.records = arr.clone();
-            self.proposals = analyze_records(&self.records);
+            self.analyze();
+        }
+    }
+
+    /// Propose a kind for every field, reading the records as `scalars` says.
+    pub fn analyze(&mut self) {
+        let typed: Vec<Value> = self
+            .records
+            .iter()
+            .map(|r| self.scalars.typed_record(r))
+            .collect();
+        self.proposals = analyze_records(&typed);
+    }
+
+    /// Why there is nothing to build, when no record is an object to place.
+    pub fn nothing_to_import(&self) -> Option<String> {
+        let total = self.records.len();
+        match (total, self.records.iter().any(Value::is_object)) {
+            (_, true) => None,
+            (0, false) => Some("Nothing to import: the source has no records".into()),
+            (_, false) => Some(format!(
+                "Nothing to import: all {total} records were skipped as not JSON objects"
+            )),
+        }
+    }
+
+    /// The formulas, parsed. Every one that does not parse is named with its
+    /// error, never dropped (improvise-8jk6.5).
+    pub fn parsed_formulas(&self) -> Result<Vec<Formula>> {
+        let mut parsed = vec![];
+        let mut refused: Vec<String> = vec![];
+        for raw in &self.formulas {
+            match import_formula(raw) {
+                Ok(formula) => parsed.push(formula),
+                Err(e) => refused.push(e.to_string()),
+            }
+        }
+        match refused.is_empty() {
+            true => Ok(parsed),
+            false => Err(anyhow!(refused.join("\n"))),
         }
     }
 
@@ -201,6 +287,7 @@ impl ImportPipeline {
             measures: accepted(&[FieldKind::Measure]),
             labels: accepted(&[FieldKind::Label]),
             date_extractions,
+            scalars: self.scalars,
         }
     }
 
@@ -211,9 +298,13 @@ impl ImportPipeline {
         let categories = &plan.categories;
         let date_extractions = &plan.date_extractions;
 
+        if let Some(why) = self.nothing_to_import() {
+            return Err(anyhow!(why));
+        }
         if categories.is_empty() {
             return Err(anyhow!("At least one category must be accepted"));
         }
+        let formulas = self.parsed_formulas()?;
 
         let placements: Vec<Placement> = self.records.iter().map(|r| plan.place(r)).collect();
         let collisions = collisions_among(&placements);
@@ -326,13 +417,8 @@ impl ImportPipeline {
             wb.model.set_cell(cell.key, CellValue::Number(cell.total));
         }
 
-        // Parse and add formulas
-        // Formulas target the "_Measure" category by default.
-        let formula_cat: String = "_Measure".to_string();
-        for raw in &self.formulas {
-            if let Ok(formula) = parse_formula(raw, &formula_cat) {
-                wb.model.add_formula(formula);
-            }
+        for formula in formulas {
+            wb.model.add_formula(formula);
         }
 
         for view in source_views(&wb, &self.sources, &plan) {
@@ -410,6 +496,7 @@ struct Plan<'a> {
     measures: Vec<&'a FieldProposal>,
     labels: Vec<&'a FieldProposal>,
     date_extractions: Vec<(&'a str, &'a str, DateComponent, String)>,
+    scalars: Scalars,
 }
 
 /// Where one source record lands. Worked out once, for the build and for the
@@ -466,7 +553,7 @@ impl Plan<'_> {
         let measures = self
             .measures
             .iter()
-            .filter_map(|m| Some((m.field.clone(), map.get(&m.field)?.as_f64()?)))
+            .filter_map(|m| Some((m.field.clone(), self.scalars.number(map.get(&m.field)?)?)))
             .collect();
         Placement::Placed {
             coords,
@@ -582,6 +669,11 @@ fn unparsed_date_warnings(
         .collect()
 }
 
+/// An import formula, targeting `_Measure`, or the error naming it (improvise-8jk6.5).
+fn import_formula(raw: &str) -> Result<Formula> {
+    parse_formula(raw, "_Measure").map_err(|e| anyhow!("Formula error in '{raw}': {e}"))
+}
+
 /// The warning for records that could not be placed in the grid. A record
 /// missing a category value is placed, so only a non-object is skipped.
 fn skip_warnings(total: usize, skipped_non_objects: usize) -> Option<String> {
@@ -769,7 +861,9 @@ impl ImportWizard {
     fn validation_error(&self) -> Option<String> {
         match self.step {
             WizardStep::ReviewProposals => self
-                .no_category_message()
+                .pipeline
+                .nothing_to_import()
+                .or_else(|| self.no_category_message())
                 .or_else(|| self.category_limit_message()),
             WizardStep::ConfigureDates => self.category_limit_message(),
             WizardStep::ResolveDuplicates => match &self.pipeline.on_duplicate {
@@ -1064,14 +1158,24 @@ impl ImportWizard {
         self.formula_buffer.pop();
     }
 
-    /// Commit the current formula buffer to the pipeline's formula list.
+    /// Commit the current formula buffer to the pipeline's formula list. One
+    /// that does not parse stays in the buffer, with the error (improvise-8jk6.5).
     pub fn confirm_formula(&mut self) {
         let text = self.formula_buffer.trim().to_string();
-        if !text.is_empty() {
-            self.pipeline.formulas.push(text);
+        match (text.is_empty(), import_formula(&text)) {
+            (false, Err(e)) => self.message = Some(e.to_string()),
+            (false, Ok(_)) => {
+                self.pipeline.formulas.push(text);
+                self.close_formula_edit();
+            }
+            (true, _) => self.close_formula_edit(),
         }
+    }
+
+    fn close_formula_edit(&mut self) {
         self.formula_buffer.clear();
         self.formula_editing = false;
+        self.message = None;
         self.cursor = self.pipeline.formulas.len().saturating_sub(1);
     }
 
@@ -2176,7 +2280,7 @@ mod tests {
         let paths: Vec<&str> = files.iter().map(|(p, _)| *p).collect();
         let merged = merge_csvs_from(&fs, &paths).unwrap();
         assert!(merged.warnings.is_empty(), "{:?}", merged.warnings);
-        let mut p = ImportPipeline::new(Value::Array(merged.records));
+        let mut p = ImportPipeline::from_csv(merged.records);
         p.sources = merged.sources;
         p
     }
@@ -2193,8 +2297,11 @@ mod tests {
         ),
     ];
 
-    fn code_maat_records() -> Value {
-        Value::Array(merged_pipeline(&CODE_MAAT).records)
+    /// The code-maat merge without its sources, so no per-file views.
+    fn code_maat_without_views() -> ImportPipeline {
+        let mut p = merged_pipeline(&CODE_MAAT);
+        p.sources.clear();
+        p
     }
 
     /// Every non-empty cell a view's grid draws, row by row.
@@ -2360,7 +2467,7 @@ mod tests {
     /// 0, "" or a skip. Evidence: `context/test-evidence/formula-and-io.md`.
     #[test]
     fn files_with_different_headers_import_as_one_sparse_model() {
-        let p = ImportPipeline::new(code_maat_records());
+        let p = code_maat_without_views();
         let kinds: Vec<(&str, FieldKind)> = p
             .proposals
             .iter()
@@ -2402,7 +2509,7 @@ mod tests {
     /// "". Evidence: `context/test-evidence/formula-and-io.md`.
     #[test]
     fn a_label_column_a_record_lacks_is_no_coordinate_not_an_empty_item() {
-        let mut p = ImportPipeline::new(code_maat_records());
+        let mut p = code_maat_without_views();
         p.proposals
             .iter_mut()
             .find(|f| f.field == "coupled")
@@ -3005,4 +3112,98 @@ mod tests {
             w.message
         );
     }
+
+    /// improvise-8jk6.5. Evidence: `context/test-evidence/formula-and-io.md`.
+    #[test]
+    fn a_formula_that_does_not_parse_stops_the_build_and_is_named() {
+        let mut p = ImportPipeline::new(json!([{"region": "East", "revenue": 1.0}]));
+        p.formulas = vec![
+            "Good = revenue".into(),
+            "Bad = revenue +".into(),
+            "Worse = * 2".into(),
+        ];
+        let err = p.build_model().expect_err("an unparseable formula refuses");
+        let msg = err.to_string();
+        assert!(msg.contains("Formula error in 'Bad = revenue +'"), "{msg}");
+        assert!(msg.contains("Formula error in 'Worse = * 2'"), "{msg}");
+        assert!(!msg.contains("Good"), "{msg}");
+    }
+
+    /// improvise-8jk6.5: the wizard refuses where the text can still be
+    /// fixed. Evidence: `context/test-evidence/formula-and-io.md`.
+    #[test]
+    fn confirming_a_formula_that_does_not_parse_keeps_it_out_and_the_text_in() {
+        let mut w = sample_wizard();
+        w.start_formula_edit();
+        for c in "Bad = revenue +".chars() {
+            w.push_formula_char(c);
+        }
+        w.confirm_formula();
+        assert!(w.pipeline.formulas.is_empty(), "{:?}", w.pipeline.formulas);
+        assert_eq!(w.formula_buffer, "Bad = revenue +");
+        assert!(w.formula_editing);
+        let message = w.message.clone().unwrap_or_default();
+        assert!(
+            message.starts_with("Formula error in 'Bad = revenue +'"),
+            "{message}"
+        );
+    }
+
+    /// improvise-8jk6.4: the role reads the text. Evidence:
+    /// `context/test-evidence/formula-and-io.md`.
+    #[test]
+    fn a_csv_column_read_as_a_category_keeps_its_text_and_as_a_measure_its_number() {
+        use crate::import::csv_parser::parse_csv_bytes_with_warnings;
+        use crate::model::cell::{CellKey, CellValue};
+        let csv = b"commit,lines\n00565796,3\n220944e2,5\n";
+        let (records, _) = parse_csv_bytes_with_warnings(csv).unwrap();
+        let mut p = ImportPipeline::from_csv(records);
+        let kind = |p: &ImportPipeline, f: &str| {
+            p.proposals
+                .iter()
+                .find(|x| x.field == f)
+                .unwrap()
+                .kind
+                .clone()
+        };
+        assert_eq!(kind(&p, "commit"), FieldKind::Measure, "analysis types");
+        let commit = p.proposals.iter_mut().find(|x| x.field == "commit");
+        commit.unwrap().kind = FieldKind::Category;
+        let wb = p.build_model().unwrap();
+        let items: Vec<&String> = wb.model.category("commit").unwrap().items.keys().collect();
+        assert_eq!(items, ["00565796", "220944e2"]);
+        let key = CellKey::new(vec![
+            ("_Measure".into(), "lines".into()),
+            ("commit".into(), "220944e2".into()),
+        ]);
+        assert_eq!(wb.model.get_cell(&key), Some(&CellValue::Number(5.0)));
+    }
+
+    /// improvise-8jk6.6: the wizard asks on the review step, where another
+    /// path can still be chosen. Evidence: the test-evidence doc.
+    #[test]
+    fn the_review_step_says_when_no_record_can_be_imported() {
+        let mut w = ImportWizard::new(json!([1, 2]));
+        assert_eq!(w.step, WizardStep::ReviewProposals, "setup");
+        w.advance();
+        assert_eq!(w.step, WizardStep::ReviewProposals);
+        assert_eq!(
+            w.message.as_deref(),
+            Some("Nothing to import: all 2 records were skipped as not JSON objects")
+        );
+    }
+
+    /// improvise-8jk6.6. Evidence: `context/test-evidence/formula-and-io.md`.
+    #[test]
+    fn a_build_that_keeps_no_record_refuses_and_says_why() {
+        let skipped = ImportPipeline::new(json!([1, "two", null]));
+        let msg = skipped.build_model().expect_err("refuses").to_string();
+        assert_eq!(
+            msg,
+            "Nothing to import: all 3 records were skipped as not JSON objects"
+        );
+        let empty = ImportPipeline::new(json!([]));
+        let msg = empty.build_model().expect_err("refuses").to_string();
+        assert_eq!(msg, "Nothing to import: the source has no records");
+    }
 }

crates/improvise-io/src/persistence/roundtrip_tests.rs

@@ -842,7 +842,7 @@ fn a_csv_header_with_an_embedded_newline_survives_a_save() {
     let csv = "\"Region\nName\",Amount\nEast,1\nWest,2\n";
     let (records, _) =
         crate::import::csv_parser::parse_csv_bytes_with_warnings(csv.as_bytes()).unwrap();
-    let wb = crate::import::wizard::ImportPipeline::new(serde_json::Value::Array(records))
+    let wb = crate::import::wizard::ImportPipeline::from_csv(records)
         .build_model()
         .unwrap();
     assert!(

src/main.rs

@@ -360,7 +360,7 @@ fn get_import_data(args: &[PathBuf]) -> Option<ImportPipeline> {
                 for warning in &merged.warnings {
                     eprintln!("warning: {warning}");
                 }
-                let mut pipeline = ImportPipeline::new(Value::Array(merged.records));
+                let mut pipeline = ImportPipeline::from_csv(merged.records);
                 pipeline.sources = merged.sources;
                 Some(pipeline)
             }
@@ -379,7 +379,7 @@ fn get_import_data(args: &[PathBuf]) -> Option<ImportPipeline> {
             Ok(content) => {
                 if csv_path_p(path) {
                     match crate::import::csv_parser::parse_csv(path) {
-                        Ok(records) => Some(ImportPipeline::new(Value::Array(records))),
+                        Ok(records) => Some(ImportPipeline::from_csv(records)),
                         Err(e) => {
                             eprintln!("CSV parse error: {e}");
                             None

tests/bug_hunt_reproductions.rs

@@ -63,8 +63,8 @@ fn duplicate_csv_headers_not_silent() {
         2,
         "both columns must survive as separate fields: {fields:?}"
     );
-    assert_eq!(fields["A"].as_f64(), Some(1.0), "{fields:?}");
-    assert_eq!(fields["A_2"].as_f64(), Some(2.0), "{fields:?}");
+    assert_eq!(fields["A"], "1", "{fields:?}");
+    assert_eq!(fields["A_2"], "2", "{fields:?}");
     assert!(
         warnings
             .iter()
@@ -77,7 +77,7 @@ fn duplicate_csv_headers_not_silent() {
 fn blank_measure_still_infers_numeric() {
     use improvise_io::import::{analyzer::FieldKind, wizard::ImportPipeline};
     let (records, _) = parse_csv_bytes_with_warnings(b"Region,Revenue\nEast,10\nWest,\n").unwrap();
-    let p = ImportPipeline::new(serde_json::Value::Array(records));
+    let p = ImportPipeline::from_csv(records);
     let proposal = p.proposals.iter().find(|p| p.field == "Revenue").unwrap();
     assert_eq!(proposal.kind, FieldKind::Measure);
 }
@@ -86,7 +86,7 @@ fn repeated_import_coordinates_not_silently_overwritten() {
     use improvise_io::import::wizard::ImportPipeline;
     let (records, _) =
         parse_csv_bytes_with_warnings(b"Region,Revenue\nEast,10\nEast,20\n").unwrap();
-    let mut pipeline = ImportPipeline::new(serde_json::Value::Array(records));
+    let mut pipeline = ImportPipeline::from_csv(records);
     pipeline.on_duplicate = improvise_io::import::wizard::DuplicatePolicy::Sum;
     let (wb, warnings) = pipeline.build_model_with_warnings().unwrap();
     let values: Vec<f64> = wb
@@ -399,7 +399,7 @@ fn ordinary_controls() {
     let (records, warnings) =
         parse_csv_bytes_with_warnings(b"Region,Revenue\nEast,10\nWest,20\n").unwrap();
     assert!(warnings.is_empty());
-    let p = ImportPipeline::new(serde_json::Value::Array(records));
+    let p = ImportPipeline::from_csv(records);
     assert_eq!(
         p.proposals
             .iter()

tests/folder_import_views.rs

@@ -25,7 +25,7 @@ fn reloaded_folder_import() -> App {
             .unwrap();
     }
     let merged = merge_csvs_from(&fs, &files.map(|(p, _)| p)).unwrap();
-    let mut pipeline = ImportPipeline::new(serde_json::Value::Array(merged.records));
+    let mut pipeline = ImportPipeline::from_csv(merged.records);
     pipeline.sources = merged.sources;
     let (wb, _) = pipeline.build_model_with_warnings().unwrap();
     App::new(parse_md(&format_md(&wb)).unwrap(), None)

tests/headless_cli.rs

@@ -708,3 +708,117 @@ fn a_headless_import_takes_files_and_folders_together_and_refuses_an_empty_folde
     );
     assert!(!scratch.path("never.improv").exists());
 }
+
+/// Runs `import <source> --no-wizard <extra> -o out.improv` on a source it writes.
+fn import_of(scratch: &Scratch, name: &str, body: &str, extra: &[&str]) -> (Output, PathBuf) {
+    let source = scratch.path(name);
+    std::fs::write(&source, body).unwrap();
+    let out_path = scratch.path("out.improv");
+    (run_import(&source, &out_path, extra), out_path)
+}
+
+/// improvise-8jk6.4: a forced category's values are item names, so they keep
+/// their source text. Evidence: `context/test-evidence/cli.md`.
+#[test]
+fn a_csv_column_forced_to_category_keeps_its_text_verbatim() {
+    let scratch = Scratch::new("forced_category_text");
+    let (out, out_path) = import_of(
+        &scratch,
+        "commits.csv",
+        "commit,lines\n00565796,3\n220944e2,5\n",
+        &["--category", "commit", "--measure", "lines"],
+    );
+    assert!(out.status.success(), "{}", stderr_of(&out));
+    let doc = std::fs::read_to_string(&out_path).unwrap();
+    assert!(
+        doc.lines().any(|l| l == "- |00565796|, |220944e2|"),
+        "the items are the source text:\n{doc}"
+    );
+    for line in [
+        "_Measure=lines, commit=|00565796| = 3",
+        "_Measure=lines, commit=|220944e2| = 5",
+    ] {
+        assert!(doc.lines().any(|l| l == line), "{line} missing from\n{doc}");
+    }
+}
+
+/// improvise-8jk6.4: JSON has no source text for a number, so a forced
+/// category names it as serde_json writes it. Evidence file.
+#[test]
+fn a_json_number_forced_to_category_is_named_as_json_writes_it() {
+    let scratch = Scratch::new("forced_category_json");
+    let (out, out_path) = import_of(
+        &scratch,
+        "commits.json",
+        r#"[{"commit": 42, "n": 1}, {"commit": 1.5, "n": 2}, {"commit": 1e3, "n": 3}]"#,
+        &["--category", "commit", "--measure", "n"],
+    );
+    assert!(out.status.success(), "{}", stderr_of(&out));
+    let doc = std::fs::read_to_string(&out_path).unwrap();
+    assert!(
+        doc.lines().any(|l| l == "- |42|, |1.5|, |1000.0|"),
+        "the items are the numbers' JSON text:\n{doc}"
+    );
+}
+
+/// improvise-8jk6.5: a formula the user named and that does not parse is a
+/// refusal, not a silent drop. Evidence: `context/test-evidence/cli.md`.
+#[test]
+fn an_import_formula_that_does_not_parse_refuses_names_it_and_writes_nothing() {
+    let scratch = Scratch::new("bad_formula");
+    let (out, out_path) = import_of(
+        &scratch,
+        "f.csv",
+        "a,x\nk,1\n",
+        &[
+            "--measure",
+            "x",
+            "--formula",
+            "Y = x +",
+            "--formula",
+            "Z = x",
+        ],
+    );
+    let err = stderr_of(&out);
+    assert!(!out.status.success(), "a dropped formula exited 0: {err}");
+    assert!(err.contains("'Y = x +'"), "names the formula: {err}");
+    assert!(err.contains("expected"), "carries the parse error: {err}");
+    assert!(!err.contains("'Z = x'"), "names only the bad one: {err}");
+    assert!(!out_path.exists(), "nothing is written");
+}
+
+/// improvise-8jk6.6: an import that kept no record says why, and exits
+/// non-zero writing nothing. Evidence: `context/test-evidence/cli.md`.
+#[test]
+fn an_import_that_keeps_no_record_refuses_and_says_why() {
+    let scratch = Scratch::new("kept_none");
+    let (out, out_path) = import_of(&scratch, "r.json", r#"[1, 2, "three"]"#, &[]);
+    let err = stderr_of(&out);
+    assert!(!out.status.success(), "{err}");
+    assert!(
+        err.contains("all 3 records were skipped as not JSON objects"),
+        "says why: {err}"
+    );
+    assert!(!out_path.exists(), "nothing is written");
+}
+
+/// improvise-8jk6.6: a partial skip warns with a count and exits 0, a choice
+/// put to the user. Evidence: `context/test-evidence/cli.md`.
+#[test]
+fn an_import_that_skips_some_records_warns_with_a_count_and_still_writes() {
+    let scratch = Scratch::new("kept_some");
+    let (out, out_path) = import_of(
+        &scratch,
+        "p.json",
+        r#"[{"a": "k", "x": 1}, 2, {"a": "m", "x": 4}]"#,
+        &[],
+    );
+    let err = stderr_of(&out);
+    assert!(out.status.success(), "{err}");
+    assert!(
+        err.contains("warning: Skipped 1 of 3 records that were not JSON objects"),
+        "{err}"
+    );
+    let doc = std::fs::read_to_string(&out_path).unwrap();
+    assert!(doc.contains("_Measure=x, a=m = 4"), "{doc}");
+}

tests/records_wide_smoke.rs

@@ -18,7 +18,7 @@ fn imported_model_shows_one_row_per_record_with_measure_columns() {
     .expect("write csv");
 
     let records = improvise::import::csv_parser::parse_csv(&csv).expect("csv parses");
-    let pipeline = ImportPipeline::new(serde_json::Value::Array(records));
+    let pipeline = ImportPipeline::from_csv(records);
     let workbook = pipeline.build_model().expect("model builds");
 
     let saved = dir.path().join("w.improv");