release: v5.10.0 — group-audit-aware Method-A je_network export

CHANGELOG.md

@@ -5,6 +5,70 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [5.10.0] - 2026-05-09
+
+Group-audit-aware Method-A edge-list export — the v5.9.0 single-entity
+Method-A network is now extended to the consolidated-group level so
+the `vynfi-group-audit-enterprise-2000` archive (and any other
+group-audit run) emits per-entity *and* consolidated `je_network`
+artefacts.
+
+### Added — group-audit `je_network` export
+
+- **Per-entity** `entities/{code}/graphs/je_network.{csv,parquet}` —
+  the same Method-A edges the single-entity output_writer would
+  produce, extended with `ic_pair_id` + `ic_partner_entity` columns
+  so consumers can join the IC postings back into pairs.
+- **Consolidated** `consolidated/je_network.{csv,parquet}` — every
+  entity's edges concatenated, plus the elimination JEs (flagged
+  `is_eliminated=true`), with `entity_code` as a partition column.
+- Schema additions on the consolidated file: `entity_code`,
+  `ic_pair_id`, `ic_partner_entity`, `is_eliminated`,
+  `eliminates_ic_pair_id`. Per-entity adds `ic_pair_id` +
+  `ic_partner_entity` only.
+- Both formats use Zstd-compressed parquet (~5× smaller than CSV)
+  matching the convention from the single-entity dataset.
+
+### Refactored — shared Method-A helper
+
+- New `datasynth_runtime::je_network::build_je_network_edges()` —
+  pure builder reused by `output_writer::write_je_network_csv` and
+  the new group emitter. Single-entity CSV output is byte-identical
+  to v5.9.0 (verified by the existing
+  `tests/je_network_export.rs` integration test).
+- New struct `JeNetworkEdge` exposes the IC fields through the
+  existing edge model so single-entity runs that *do* have IC
+  postings (multi-company-in-one-shard configs) can still surface
+  them — though the single-entity CSV writer keeps the v5.8.0
+  13-column schema for backwards compatibility.
+
+### Validated against `mini_nestle.yaml`
+
+End-to-end smoke through `datasynth-data group generate` against
+`configs/examples/group/mini_nestle.yaml` produced:
+- 4 per-entity `je_network.{csv,parquet}` files
+  (NESTLE_SA / NESTLE_USA / NESTLE_DE / NESTLE_BR)
+- 368 elimination edges
+- 69,287 consolidated edges
+- 376 IC-pair edges (matched seller + buyer sides) with
+  `ic_pair_id` populated
+- Coverage 0.9583 (matched / planned IC pairs)
+
+`vynfi-group-audit-enterprise-2000` regeneration is the next
+deliverable; this release ships the engine changes that make it
+possible.
+
+### Implementation notes
+
+- Wired into `aggregate/driver.rs` immediately after
+  `eliminations_to_journal_entries` runs (step 7b) so elimination
+  edges can be flagged `is_eliminated=true` while the contributing
+  entity-tagged JEs are still in their pre-TB-rewrite form.
+- `eliminates_ic_pair_id` is left empty on v5.10 elimination edges
+  — the synthetic JEs produced by the elimination factory don't
+  carry the source `IcPairId` on their headers. Plumbing it
+  through the elimination → JE conversion can land in v5.10.x.
+
 ## [5.9.0] - 2026-05-08
 
 Customer-feedback follow-up release on top of v5.8.0.  Bundles a

Cargo.toml

@@ -24,7 +24,7 @@ exclude = ["fuzz", "attic/datasynth-graph-export"]
 # Root package for workspace-level benchmarks
 [package]
 name = "datasynth-workspace"
-version = "5.9.0"
+version = "5.10.0"
 edition = "2021"
 publish = false
 
@@ -44,7 +44,7 @@ tempfile = { workspace = true }
 serde_json = { workspace = true }
 
 [workspace.package]
-version = "5.9.0"
+version = "5.10.0"
 edition = "2021"
 license = "Apache-2.0"
 rust-version = "1.88"
@@ -60,22 +60,22 @@ categories = ["simulation", "command-line-utilities"]
 # Internal crates - version required for crates.io publishing
 # Version must match workspace.package.version to prevent cargo from resolving
 # old incompatible versions during publish verification
-datasynth-core = { version = "5.9.0", path = "crates/datasynth-core" }
-datasynth-config = { version = "5.9.0", path = "crates/datasynth-config" }
-datasynth-generators = { version = "5.9.0", path = "crates/datasynth-generators" }
-datasynth-output = { version = "5.9.0", path = "crates/datasynth-output" }
-datasynth-runtime = { version = "5.9.0", path = "crates/datasynth-runtime" }
-datasynth-graph = { version = "5.9.0", path = "crates/datasynth-graph" }
-datasynth-server = { version = "5.9.0", path = "crates/datasynth-server" }
-datasynth-test-utils = { version = "5.9.0", path = "crates/datasynth-test-utils" }
-datasynth-eval = { version = "5.9.0", path = "crates/datasynth-eval" }
-datasynth-ocpm = { version = "5.9.0", path = "crates/datasynth-ocpm" }
-datasynth-banking = { version = "5.9.0", path = "crates/datasynth-banking" }
-datasynth-fingerprint = { version = "5.9.0", path = "crates/datasynth-fingerprint" }
-datasynth-standards = { version = "5.9.0", path = "crates/datasynth-standards" }
-datasynth-audit-fsm = { version = "5.9.0", path = "crates/datasynth-audit-fsm" }
-datasynth-audit-optimizer = { version = "5.9.0", path = "crates/datasynth-audit-optimizer" }
-datasynth-group = { version = "5.9.0", path = "crates/datasynth-group" }
+datasynth-core = { version = "5.10.0", path = "crates/datasynth-core" }
+datasynth-config = { version = "5.10.0", path = "crates/datasynth-config" }
+datasynth-generators = { version = "5.10.0", path = "crates/datasynth-generators" }
+datasynth-output = { version = "5.10.0", path = "crates/datasynth-output" }
+datasynth-runtime = { version = "5.10.0", path = "crates/datasynth-runtime" }
+datasynth-graph = { version = "5.10.0", path = "crates/datasynth-graph" }
+datasynth-server = { version = "5.10.0", path = "crates/datasynth-server" }
+datasynth-test-utils = { version = "5.10.0", path = "crates/datasynth-test-utils" }
+datasynth-eval = { version = "5.10.0", path = "crates/datasynth-eval" }
+datasynth-ocpm = { version = "5.10.0", path = "crates/datasynth-ocpm" }
+datasynth-banking = { version = "5.10.0", path = "crates/datasynth-banking" }
+datasynth-fingerprint = { version = "5.10.0", path = "crates/datasynth-fingerprint" }
+datasynth-standards = { version = "5.10.0", path = "crates/datasynth-standards" }
+datasynth-audit-fsm = { version = "5.10.0", path = "crates/datasynth-audit-fsm" }
+datasynth-audit-optimizer = { version = "5.10.0", path = "crates/datasynth-audit-optimizer" }
+datasynth-group = { version = "5.10.0", path = "crates/datasynth-group" }
 
 # Serialization
 serde = { version = "1.0", features = ["derive"] }

crates/datasynth-group/Cargo.toml

@@ -33,12 +33,16 @@ blake3 = { workspace = true }
 hex = { workspace = true }
 strsim = "0.11"
 rayon = { workspace = true }
+arrow = { workspace = true }
+parquet = { workspace = true }
 
 [dev-dependencies]
 datasynth-test-utils = { workspace = true }
 rust_decimal_macros = { workspace = true }
 pretty_assertions = "1"
 tempfile = { workspace = true }
+smallvec = { workspace = true }
+uuid = { workspace = true }
 # Subprocess-based determinism harness in `tests/determinism_in_process.rs`
 # (Task 11.4) drives the `datasynth-data` CLI binary as a subprocess.
 # `assert_cmd` is used for ergonomics; the binary itself is discovered

crates/datasynth-group/src/aggregate/driver.rs

@@ -294,6 +294,24 @@ pub fn run_aggregate(
     // ── 7. Convert to elimination JEs (Task 5.5) ────────────────────────
     let elim_jes = eliminations_to_journal_entries(&elim_result);
 
+    // ── 7b. v5.10 — emit per-entity + consolidated je_network artefacts.
+    // Hooks in here (after eliminations land but before TB consolidation
+    // rewrites contributing_jes) so we can mark elimination edges with
+    // is_eliminated=true while the original IC pair JEs are still in
+    // their entity-tagged form.
+    let je_network_summary = crate::aggregate::je_network::write_je_network_artefacts(
+        &contributing_jes,
+        &elim_jes,
+        out_dir,
+    )?;
+    tracing::info!(
+        "v5.10 je_network: {} per-entity files, {} elim edges, {} consolidated edges -> {:?}",
+        je_network_summary.per_entity_edge_count.len(),
+        je_network_summary.elim_edge_count,
+        je_network_summary.consolidated_edge_count,
+        je_network_summary.consolidated_csv_path,
+    );
+
     // ── 8. Apply eliminations to pre-elim TB (Task 5.6) ─────────────────
     let post_elim = apply_eliminations_to_tb(&pre_elim, &elim_jes)?;