Scan numbered candidate table run families

crates/rrt-cli/src/main.rs

@@ -246,6 +246,9 @@ enum Command {
     RuntimeScanCandidateTableHeaders {
         root_path: PathBuf,
     },
+    RuntimeScanCandidateTableNamedRuns {
+        root_path: PathBuf,
+    },
     RuntimeScanSpecialConditions {
         root_path: PathBuf,
     },
@@ -857,6 +860,41 @@ struct RuntimeCandidateTableHeaderScanSample {
     zero_trailer_entry_names: Vec<String>,
 }
 
+#[derive(Debug, Clone, Serialize)]
+struct RuntimeCandidateTableNamedRun {
+    prefix: String,
+    start_index: usize,
+    end_index: usize,
+    count: usize,
+    first_name: String,
+    last_name: String,
+    start_offset: usize,
+    end_offset: usize,
+    distinct_trailer_hex_words: Vec<String>,
+}
+
+#[derive(Debug, Clone, Serialize)]
+struct RuntimeCandidateTableNamedRunScanSample {
+    path: String,
+    profile_family: String,
+    source_kind: String,
+    observed_entry_count: usize,
+    port_runs: Vec<RuntimeCandidateTableNamedRun>,
+    warehouse_runs: Vec<RuntimeCandidateTableNamedRun>,
+}
+
+#[derive(Debug, Serialize)]
+struct RuntimeCandidateTableNamedRunScanReport {
+    root_path: String,
+    file_count: usize,
+    files_with_probe_count: usize,
+    files_with_any_numbered_port_runs_count: usize,
+    files_with_any_numbered_warehouse_runs_count: usize,
+    files_with_both_numbered_run_families_count: usize,
+    skipped_file_count: usize,
+    samples: Vec<RuntimeCandidateTableNamedRunScanSample>,
+}
+
 #[derive(Debug, Clone, Serialize)]
 struct RuntimeSpecialConditionsScanSample {
     path: String,
@@ -1220,6 +1258,9 @@ fn real_main() -> Result<(), Box<dyn std::error::Error>> {
         Command::RuntimeScanCandidateTableHeaders { root_path } => {
             run_runtime_scan_candidate_table_headers(&root_path)?;
         }
+        Command::RuntimeScanCandidateTableNamedRuns { root_path } => {
+            run_runtime_scan_candidate_table_named_runs(&root_path)?;
+        }
         Command::RuntimeScanSpecialConditions { root_path } => {
             run_runtime_scan_special_conditions(&root_path)?;
         }
@@ -1603,6 +1644,13 @@ fn parse_command() -> Result<Command, Box<dyn std::error::Error>> {
                 root_path: PathBuf::from(root_path),
             })
         }
+        [command, subcommand, root_path]
+            if command == "runtime" && subcommand == "scan-candidate-table-named-runs" =>
+        {
+            Ok(Command::RuntimeScanCandidateTableNamedRuns {
+                root_path: PathBuf::from(root_path),
+            })
+        }
         [command, subcommand, root_path]
             if command == "runtime" && subcommand == "scan-special-conditions" =>
         {
@@ -1647,7 +1695,7 @@ fn parse_command() -> Result<Command, Box<dyn std::error::Error>> {
             })
         }
         _ => Err(
-            "usage: rrt-cli [validate [repo-root] | finance eval <snapshot.json> | finance diff <left.json> <right.json> | runtime validate-fixture <fixture.json> | runtime summarize-fixture <fixture.json> | runtime export-fixture-state <fixture.json> <snapshot.json> | runtime diff-state <left.json> <right.json> | runtime summarize-state <snapshot.json> | runtime import-state <input.json> <snapshot.json> | runtime inspect-smp <file.smp> | runtime inspect-candidate-table <file.smp> | runtime inspect-compact-event-dispatch-cluster <maps-dir> | runtime inspect-compact-event-dispatch-cluster-counts <maps-dir> | runtime inspect-map-title-hints <maps-dir> | runtime summarize-save-load <file.smp> | runtime load-save-slice <file.smp> | runtime inspect-save-company-chairman <file.smp> | runtime inspect-save-placed-structure-triplets <file.smp> | runtime compare-region-fixed-row-runs <left.gms> <right.gms> | runtime inspect-periodic-company-service-trace <file.smp> | runtime inspect-region-service-trace <file.smp> | runtime inspect-infrastructure-asset-trace <file.smp> | runtime inspect-save-region-queued-notice-records <file.smp> | runtime inspect-placed-structure-dynamic-side-buffer <file.smp> | runtime inspect-unclassified-save-collections <file.smp> | runtime import-save-state <file.smp> <snapshot.json> | runtime export-save-slice <file.smp> <save-slice.json> | runtime export-overlay-import <snapshot.json> <save-slice.json> <overlay-import.json> | runtime inspect-pk4 <file.pk4> | runtime inspect-cargo-types <CargoTypes-dir> | runtime inspect-building-type-sources <BuildingTypes-dir> [building-bindings.json] | runtime inspect-cargo-skins <Cargo106.PK4> | runtime inspect-cargo-economy-sources <CargoTypes-dir> <Cargo106.PK4> | runtime inspect-cargo-production-selector <CargoTypes-dir> <Cargo106.PK4> | runtime inspect-cargo-price-selector <CargoTypes-dir> <Cargo106.PK4> | runtime inspect-win <file.win> | runtime extract-pk4-entry <file.pk4> <entry-name> <output-path> | runtime inspect-campaign-exe <RT3.exe> | runtime compare-classic-profile <save1.gms> <save2.gms> [saveN.gms...] | runtime compare-105-profile <save1.gms> <save2.gms> [saveN.gms...] | runtime compare-candidate-table <file1> <file2> [fileN...] | runtime compare-recipe-book-lines <file1> <file2> [fileN...] | runtime compare-setup-payload-core <file1> <file2> [fileN...] | runtime compare-setup-launch-payload <file1> <file2> [fileN...] | runtime compare-post-special-conditions-scalars <file1> <file2> [fileN...] | runtime scan-candidate-table-headers <root-dir> | runtime scan-special-conditions <root-dir> | runtime scan-aligned-runtime-rule-band <root-dir> | runtime scan-post-special-conditions-scalars <root-dir> | runtime scan-post-special-conditions-tail <root-dir> | runtime scan-recipe-book-lines <root-dir> | runtime export-profile-block <save.gms> <profile.json>]"
+            "usage: rrt-cli [validate [repo-root] | finance eval <snapshot.json> | finance diff <left.json> <right.json> | runtime validate-fixture <fixture.json> | runtime summarize-fixture <fixture.json> | runtime export-fixture-state <fixture.json> <snapshot.json> | runtime diff-state <left.json> <right.json> | runtime summarize-state <snapshot.json> | runtime import-state <input.json> <snapshot.json> | runtime inspect-smp <file.smp> | runtime inspect-candidate-table <file.smp> | runtime inspect-compact-event-dispatch-cluster <maps-dir> | runtime inspect-compact-event-dispatch-cluster-counts <maps-dir> | runtime inspect-map-title-hints <maps-dir> | runtime summarize-save-load <file.smp> | runtime load-save-slice <file.smp> | runtime inspect-save-company-chairman <file.smp> | runtime inspect-save-placed-structure-triplets <file.smp> | runtime compare-region-fixed-row-runs <left.gms> <right.gms> | runtime inspect-periodic-company-service-trace <file.smp> | runtime inspect-region-service-trace <file.smp> | runtime inspect-infrastructure-asset-trace <file.smp> | runtime inspect-save-region-queued-notice-records <file.smp> | runtime inspect-placed-structure-dynamic-side-buffer <file.smp> | runtime inspect-unclassified-save-collections <file.smp> | runtime import-save-state <file.smp> <snapshot.json> | runtime export-save-slice <file.smp> <save-slice.json> | runtime export-overlay-import <snapshot.json> <save-slice.json> <overlay-import.json> | runtime inspect-pk4 <file.pk4> | runtime inspect-cargo-types <CargoTypes-dir> | runtime inspect-building-type-sources <BuildingTypes-dir> [building-bindings.json] | runtime inspect-cargo-skins <Cargo106.PK4> | runtime inspect-cargo-economy-sources <CargoTypes-dir> <Cargo106.PK4> | runtime inspect-cargo-production-selector <CargoTypes-dir> <Cargo106.PK4> | runtime inspect-cargo-price-selector <CargoTypes-dir> <Cargo106.PK4> | runtime inspect-win <file.win> | runtime extract-pk4-entry <file.pk4> <entry-name> <output-path> | runtime inspect-campaign-exe <RT3.exe> | runtime compare-classic-profile <save1.gms> <save2.gms> [saveN.gms...] | runtime compare-105-profile <save1.gms> <save2.gms> [saveN.gms...] | runtime compare-candidate-table <file1> <file2> [fileN...] | runtime compare-recipe-book-lines <file1> <file2> [fileN...] | runtime compare-setup-payload-core <file1> <file2> [fileN...] | runtime compare-setup-launch-payload <file1> <file2> [fileN...] | runtime compare-post-special-conditions-scalars <file1> <file2> [fileN...] | runtime scan-candidate-table-headers <root-dir> | runtime scan-candidate-table-named-runs <root-dir> | runtime scan-special-conditions <root-dir> | runtime scan-aligned-runtime-rule-band <root-dir> | runtime scan-post-special-conditions-scalars <root-dir> | runtime scan-post-special-conditions-tail <root-dir> | runtime scan-recipe-book-lines <root-dir> | runtime export-profile-block <save.gms> <profile.json>]"
                 .into(),
         ),
     }
@@ -2938,6 +2986,50 @@ fn run_runtime_scan_candidate_table_headers(
     Ok(())
 }
 
+fn run_runtime_scan_candidate_table_named_runs(
+    root_path: &Path,
+) -> Result<(), Box<dyn std::error::Error>> {
+    let mut candidate_paths = Vec::new();
+    collect_candidate_table_input_paths(root_path, &mut candidate_paths)?;
+
+    let file_count = candidate_paths.len();
+    let mut samples = Vec::new();
+    let mut skipped_file_count = 0usize;
+    for path in candidate_paths {
+        match load_candidate_table_named_run_scan_sample(&path) {
+            Ok(sample) => samples.push(sample),
+            Err(_) => skipped_file_count += 1,
+        }
+    }
+
+    let files_with_probe_count = samples.len();
+    let files_with_any_numbered_port_runs_count = samples
+        .iter()
+        .filter(|sample| !sample.port_runs.is_empty())
+        .count();
+    let files_with_any_numbered_warehouse_runs_count = samples
+        .iter()
+        .filter(|sample| !sample.warehouse_runs.is_empty())
+        .count();
+    let files_with_both_numbered_run_families_count = samples
+        .iter()
+        .filter(|sample| !sample.port_runs.is_empty() && !sample.warehouse_runs.is_empty())
+        .count();
+
+    let report = RuntimeCandidateTableNamedRunScanReport {
+        root_path: root_path.display().to_string(),
+        file_count,
+        files_with_probe_count,
+        files_with_any_numbered_port_runs_count,
+        files_with_any_numbered_warehouse_runs_count,
+        files_with_both_numbered_run_families_count,
+        skipped_file_count,
+        samples,
+    };
+    println!("{}", serde_json::to_string_pretty(&report)?);
+    Ok(())
+}
+
 fn run_runtime_scan_special_conditions(root_path: &Path) -> Result<(), Box<dyn std::error::Error>> {
     let mut candidate_paths = Vec::new();
     collect_special_conditions_input_paths(root_path, &mut candidate_paths)?;
@@ -4152,6 +4244,23 @@ fn load_candidate_table_header_scan_sample(
     })
 }
 
+fn load_candidate_table_named_run_scan_sample(
+    smp_path: &Path,
+) -> Result<RuntimeCandidateTableNamedRunScanSample, Box<dyn std::error::Error>> {
+    let report = load_candidate_table_inspection_report(smp_path)?;
+    let port_runs = collect_numbered_candidate_name_runs(&report.entries, "Port");
+    let warehouse_runs = collect_numbered_candidate_name_runs(&report.entries, "Warehouse");
+
+    Ok(RuntimeCandidateTableNamedRunScanSample {
+        path: report.path,
+        profile_family: report.profile_family,
+        source_kind: report.source_kind,
+        observed_entry_count: report.observed_entry_count,
+        port_runs,
+        warehouse_runs,
+    })
+}
+
 fn load_special_conditions_scan_sample(
     smp_path: &Path,
 ) -> Result<RuntimeSpecialConditionsScanSample, Box<dyn std::error::Error>> {
@@ -4495,6 +4604,61 @@ fn collect_candidate_table_input_paths(
     Ok(())
 }
 
+fn collect_numbered_candidate_name_runs(
+    entries: &[RuntimeCandidateTableEntrySample],
+    prefix: &str,
+) -> Vec<RuntimeCandidateTableNamedRun> {
+    let mut numbered_entries = entries
+        .iter()
+        .filter_map(|entry| {
+            parse_numbered_candidate_name(&entry.text, prefix).map(|number| (entry, number))
+        })
+        .collect::<Vec<_>>();
+    numbered_entries.sort_by_key(|(entry, number)| (entry.index, *number));
+
+    let mut runs = Vec::new();
+    let mut cursor = 0usize;
+    while cursor < numbered_entries.len() {
+        let (first_entry, first_number) = numbered_entries[cursor];
+        let mut last_entry = first_entry;
+        let mut last_number = first_number;
+        let mut distinct_trailer_hex_words = BTreeSet::from([first_entry.trailer_word_hex.clone()]);
+        let mut next = cursor + 1;
+        while next < numbered_entries.len() {
+            let (entry, number) = numbered_entries[next];
+            if entry.index != last_entry.index + 1 || number != last_number + 1 {
+                break;
+            }
+            distinct_trailer_hex_words.insert(entry.trailer_word_hex.clone());
+            last_entry = entry;
+            last_number = number;
+            next += 1;
+        }
+        runs.push(RuntimeCandidateTableNamedRun {
+            prefix: prefix.to_string(),
+            start_index: first_entry.index,
+            end_index: last_entry.index,
+            count: next - cursor,
+            first_name: first_entry.text.clone(),
+            last_name: last_entry.text.clone(),
+            start_offset: first_entry.offset,
+            end_offset: last_entry.offset,
+            distinct_trailer_hex_words: distinct_trailer_hex_words.into_iter().collect(),
+        });
+        cursor = next;
+    }
+
+    runs
+}
+
+fn parse_numbered_candidate_name(text: &str, prefix: &str) -> Option<usize> {
+    let digits = text.strip_prefix(prefix)?;
+    if digits.is_empty() || !digits.bytes().all(|byte| byte.is_ascii_digit()) {
+        return None;
+    }
+    digits.parse().ok()
+}
+
 fn collect_special_conditions_input_paths(
     root_path: &Path,
     out: &mut Vec<PathBuf>,
@@ -6551,6 +6715,83 @@ mod tests {
         );
     }
 
+    #[test]
+    fn collects_numbered_candidate_name_runs_by_prefix() {
+        let entries = vec![
+            RuntimeCandidateTableEntrySample {
+                index: 35,
+                offset: 28535,
+                text: "Port00".to_string(),
+                availability_dword: 1,
+                availability_dword_hex: "0x00000001".to_string(),
+                trailer_word: 1,
+                trailer_word_hex: "0x00000001".to_string(),
+            },
+            RuntimeCandidateTableEntrySample {
+                index: 43,
+                offset: 28807,
+                text: "Warehouse00".to_string(),
+                availability_dword: 1,
+                availability_dword_hex: "0x00000001".to_string(),
+                trailer_word: 1,
+                trailer_word_hex: "0x00000001".to_string(),
+            },
+            RuntimeCandidateTableEntrySample {
+                index: 45,
+                offset: 28875,
+                text: "Port01".to_string(),
+                availability_dword: 1,
+                availability_dword_hex: "0x00000001".to_string(),
+                trailer_word: 1,
+                trailer_word_hex: "0x00000001".to_string(),
+            },
+            RuntimeCandidateTableEntrySample {
+                index: 46,
+                offset: 28909,
+                text: "Port02".to_string(),
+                availability_dword: 1,
+                availability_dword_hex: "0x00000001".to_string(),
+                trailer_word: 1,
+                trailer_word_hex: "0x00000001".to_string(),
+            },
+            RuntimeCandidateTableEntrySample {
+                index: 56,
+                offset: 29249,
+                text: "Warehouse01".to_string(),
+                availability_dword: 1,
+                availability_dword_hex: "0x00000001".to_string(),
+                trailer_word: 1,
+                trailer_word_hex: "0x00000001".to_string(),
+            },
+            RuntimeCandidateTableEntrySample {
+                index: 57,
+                offset: 29283,
+                text: "Warehouse02".to_string(),
+                availability_dword: 1,
+                availability_dword_hex: "0x00000001".to_string(),
+                trailer_word: 1,
+                trailer_word_hex: "0x00000001".to_string(),
+            },
+        ];
+
+        let port_runs = collect_numbered_candidate_name_runs(&entries, "Port");
+        let warehouse_runs = collect_numbered_candidate_name_runs(&entries, "Warehouse");
+
+        assert_eq!(port_runs.len(), 2);
+        assert_eq!(port_runs[0].first_name, "Port00");
+        assert_eq!(port_runs[0].count, 1);
+        assert_eq!(port_runs[1].first_name, "Port01");
+        assert_eq!(port_runs[1].last_name, "Port02");
+        assert_eq!(port_runs[1].count, 2);
+
+        assert_eq!(warehouse_runs.len(), 2);
+        assert_eq!(warehouse_runs[0].first_name, "Warehouse00");
+        assert_eq!(warehouse_runs[0].count, 1);
+        assert_eq!(warehouse_runs[1].first_name, "Warehouse01");
+        assert_eq!(warehouse_runs[1].last_name, "Warehouse02");
+        assert_eq!(warehouse_runs[1].count, 2);
+    }
+
     #[test]
     fn diffs_recipe_book_line_samples_across_multiple_files() {
         let sample_a = RuntimeRecipeBookLineSample {

docs/control-loop-atlas/runtime-roots-camera-and-support-families.md

@@ -1244,6 +1244,17 @@
   problem is no longer whether those names exist as stable scenario rows; it is how that fixed
   candidate-table cluster is projected into the later aux-record bank and then into the live clone
   families.
+  The root scan narrows the real corpus for that question too. `runtime scan-candidate-table-headers
+  rt3_wineprefix/drive_c/rt3/maps` shows `37` probe-bearing shipped maps and `4` skips, while the
+  narrower `runtime scan-candidate-table-named-runs` command confirms that `Louisiana.gmp` and
+  `Dutchlantis.gmp` share the same split shape:
+  isolated `Port00` at row `35`, contiguous `Port01..11` at rows `45..55`, isolated
+  `Warehouse00` at row `43`, and contiguous `Warehouse01..11` at rows `56..66`. Raw string
+  presence is broader than that actual fixed-candidate-table seam too: `Port00` appears in all
+  `41` shipped `.gmp` files, but `Central Pacific.gmp`, `Italy.gmp`, `Tex-Mex.gmp`, and
+  `Texas Tea.gmp` do not expose the fixed candidate-table header at all. So the next Tier-2
+  source pass should target the `37` probe-bearing maps rather than the noisier full
+  string-bearing map corpus.
   The direct `+0xba/+0xbb` writer census now rules out a broad false lead too. The obvious new
   stores at `0x004ecd42/0x004ecdaa` and `0x004ed5d5/0x004ed625` are only shell-side
   portrait/string refresh helpers over a different id-keyed collection rooted through

docs/rehost-queue.md

@@ -755,6 +755,17 @@ Working rule:
     is no longer whether those names exist as stable scenario rows; it is how that stable
     candidate-table cluster is projected into the later aux-record bank and then into the live
     clone families.
+    The new root scan sharpens that boundary further. `runtime scan-candidate-table-headers
+    rt3_wineprefix/drive_c/rt3/maps` shows `37` probe-bearing shipped maps and `4` skips, while
+    the narrower `runtime scan-candidate-table-named-runs` command confirms that
+    `Louisiana.gmp` and `Dutchlantis.gmp` share the same split shape:
+    `Port00` as an isolated run at row `35`, `Port01..11` as one contiguous run at rows `45..55`,
+    `Warehouse00` isolated at row `43`, and `Warehouse01..11` contiguous at rows `56..66`.
+    Raw map-string presence is broader than that actual candidate-table seam too:
+    `Port00` appears in all `41` shipped `.gmp` files, but `Central Pacific.gmp`, `Italy.gmp`,
+    `Tex-Mex.gmp`, and `Texas Tea.gmp` do not expose the fixed candidate-table header at all. So
+    the next Tier-2 source pass should target the `37` probe-bearing maps rather than the noisier
+    full string-bearing map corpus.
     The direct `+0xba/+0xbb` writer census is narrower now too. The obvious newly surfaced stores
     at `0x004ecd42/0x004ecdaa` and `0x004ed5d5/0x004ed625` are only shell-side portrait/string
     refresh helpers: they walk a separate id-keyed collection through `0x0053f830`, free and