adityamukho · May 17, 2026 · May 17, 2026 · May 17, 2026 · May 17, 2026 · May 17, 2026
@@ -1602,6 +1602,16 @@ Push `Expr` predicate clauses (e.g. `[(> ?age 30)]`) down to filter bindings as
 - Migration tools for any format changes
 - Long-term support
 
+### v2.0 — File Format Policy
+
+**v2.0 supports file format v7 only.** Support for v1–v6 is dropped. The v1–v6 → v7 auto-migration code in `persistent_facts.rs` can be removed when cutting 2.0. Any database that was opened at least once under a v1.x release will already be on v7; there are no known users on older formats.
+
+v2.0 scope (GitHub milestone "2.0"):
+- `lag`/`lead` window functions (#182)
+- Sliding row frames — `:rows N preceding` (#183)
+- PreparedQuery over UniFFI (#181)
+- UDF registration over UniFFI (#180)
+
 ---
 
 ## Decision Framework
@@ -1664,6 +1674,7 @@ When evaluating features, ask:
 - ✅ Wave 1 Performance: Complete (May 2026) — hash-join cluster + selective B+Tree lookup (#202, #203, #204, #208), 850 tests
 - ✅ Wave 2 Optimizer & Benchmarks: Complete (May 2026) — predicate push-down (#207, #206), cost-based not/or ordering (#205), SIMD crossover analysis (#229), 850 tests
 - ✅ Wave 3 Reliability: Complete (May 2026) — WAL fault injection, migration matrix, index corruption resilience, property-based testing, coverage gates, long-haul smoke, XTDB/Datomic compat (#209, #210, #212, #213, #214, #215, #216, #217, #219, #220, #221), 935 tests
+- ✅ Wave 4 Deferred Features: Complete (May 2026) — #182, #183, #180, #181 tagged milestone 2.0; #187 closed (no pre-1.0 users); #201 deferred to Wave 6
 - 🎯 Phase 9: Ongoing (Ecosystem — integration examples, cookbook, GraphRAG/LangChain examples)
 
 **Note**: This is a hobby project. Timeline is flexible but realistic.
@@ -1699,4 +1710,4 @@ See [GitHub Issues](https://github.com/project-minigraf/minigraf/issues) for spe
 
 ---
 
-**Last Updated**: Wave 3 Reliability Complete (May 2026) — 935 tests passing, v1.0.0
+**Last Updated**: Wave 4 Complete (May 2026) — 935 tests passing, v1.0.0; milestone 2.0 issues queued; #231 repo-split is next gate
@@ -2,34 +2,34 @@
 
 > **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
 
-**Goal:** Add proptest-based cross-feature property tests with a reference evaluator (#221), Datalog parser/evaluator fuzz targets with seed corpus (#213), and CI coverage gates (#212).
+**Goal:** Add proptest-based cross-feature property tests with a reference evaluator (#212), Datalog parser/evaluator fuzz targets with seed corpus (#213), and CI coverage gates (#219).
 
 **Architecture:** The reference evaluator is a naive nested-loop implementation (~150 lines) intentionally independent of production code. proptest generates random small graphs and queries; both evaluators are compared after normalizing output. Fuzz targets replace the stubs from PR 1. Coverage gates use the existing `llvm-cov.yml` pattern with per-module thresholds in `coverage-thresholds.toml`.
 
 **Tech Stack:** Rust stable for property tests; Rust nightly for fuzz runs; proptest 1.x (added in PR 1); cargo-llvm-cov (already in CI); GitHub Actions
 
 **Prerequisites:** PR 1 merged (proptest dev-dep, fuzz/ stub targets)
 
-**Closes:** #221, #213, #212
+**Closes:** #212, #213, #219
 
 ---
 
 ## File Map
 
 | Action | Path | Purpose |
 |---|---|---|
-| Create | `tests/property_test.rs` | proptest reference evaluator (#221) |
+| Create | `tests/property_test.rs` | proptest reference evaluator (#212) |
 | Modify | `fuzz/fuzz_targets/datalog_parser.rs` | real fuzz target (#213) |
 | Modify | `fuzz/fuzz_targets/datalog_eval.rs` | real fuzz target (#213) |
 | Create | `fuzz/corpus/datalog_parser/` | seed corpus (#213) |
 | Create | `fuzz/corpus/datalog_eval/` | seed corpus (#213) |
-| Create | `.github/workflows/coverage-gates.yml` | per-module coverage CI (#212) |
-| Create | `coverage-thresholds.toml` | threshold values (#212) |
+| Create | `.github/workflows/coverage-gates.yml` | per-module coverage CI (#219) |
+| Create | `coverage-thresholds.toml` | threshold values (#219) |
 | Modify | `.github/workflows/fuzz.yml` | add Datalog fuzz targets if file exists, else create |
 
 ---
 
-## Task 1: proptest reference evaluator (#221)
+## Task 1: proptest reference evaluator (#212)
 
 **Files:**
 - Create: `tests/property_test.rs`
@@ -41,7 +41,7 @@ The reference evaluator handles only the small query shapes generated by the tes
 Create `tests/property_test.rs`:
 
 ```rust
-//! Cross-feature property tests (#221).
+//! Cross-feature property tests (#212).
 //!
 //! Compares Minigraf query results against a deliberately simple reference
 //! evaluator for randomly-generated small graphs and queries.
@@ -322,7 +322,7 @@ Expected: all 3 proptest cases pass. If any fails, the output includes the minim
 
 ```bash
 git add tests/property_test.rs
-git commit -m "test(query): add #221 proptest reference evaluator for cross-feature property tests"
+git commit -m "test(query): add #212 proptest reference evaluator for cross-feature property tests"
 ```
 
 ---
@@ -547,7 +547,7 @@ git commit -m "test(fuzz): add #213 Datalog parser/eval fuzz targets with seed c
 
 ---
 
-## Task 3: Coverage gates (#212)
+## Task 3: Coverage gates (#219)
 
 **Files:**
 - Create: `coverage-thresholds.toml`
@@ -704,7 +704,7 @@ Expected: all tests pass.
 
 ```bash
 git add coverage-thresholds.toml .github/workflows/coverage-gates.yml
-git commit -m "ci: add #212 per-module coverage gates with cargo-llvm-cov"
+git commit -m "ci: add #219 per-module coverage gates with cargo-llvm-cov"
 ```
 
 ---
@@ -716,11 +716,11 @@ git commit -m "ci: add #212 per-module coverage gates with cargo-llvm-cov"
 ```bash
 git push -u origin HEAD
 gh pr create \
-  --title "test(query): proptest reference evaluator, Datalog fuzz targets, coverage gates (#221, #213, #212)" \
+  --title "test(query): proptest reference evaluator, Datalog fuzz targets, coverage gates (#212, #213, #219)" \
   --body "$(cat <<'EOF'
 ## Wave 3 PR 4 — Query Correctness
 
-Closes #221, #213, #212.
+Closes #212, #213, #219.
 
 ### #221 — proptest reference evaluator (`tests/property_test.rs`)
 - Naive reference evaluator (independent of production code)

@@ -2,15 +2,15 @@
 
 > **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
 
-**Goal:** Add XTDB and Datomic compatibility test suites (#219) by porting semantically equivalent test cases from each corpus, with license review documented inline.
+**Goal:** Add XTDB and Datomic compatibility test suites (#221) by porting semantically equivalent test cases from each corpus, with license review documented inline.
 
 **Architecture:** Two new test files — `tests/xtdb_compat_test.rs` and `tests/datomic_compat_test.rs`. Each test case is a semantic port of a known test from the source corpus. XTDB (Apache 2.0) allows direct semantic porting; Datomic test material is restricted so all cases are independently rewritten from the semantic intent. Unsupported or intentionally divergent cases are listed with rationale.
 
 **Tech Stack:** Rust stable, Minigraf's Datalog engine
 
 **Prerequisites:** PRs 2, 3, 4, 5 all merged
 
-**Closes:** #219
+**Closes:** #221
 
 ---
 
@@ -58,7 +58,7 @@ If the XTDB repo is inaccessible, the tests below are independently written sema
 Create `tests/xtdb_compat_test.rs`:
 
 ```rust
-//! XTDB compatibility tests (#219).
+//! XTDB compatibility tests (#221).
 //!
 //! License: XTDB is Apache 2.0. These tests are semantic ports of query
 //! concepts from the XTDB documentation and test suite. Each test is
@@ -338,7 +338,7 @@ Expected: all tests pass. If any fail due to syntax differences (e.g., `:valid-a
 
 ```bash
 git add tests/xtdb_compat_test.rs
-git commit -m "test(compat): add XTDB compatibility tests (#219)"
+git commit -m "test(compat): add XTDB compatibility tests (#221)"
 ```
 
 ---
@@ -355,7 +355,7 @@ All Datomic-inspired tests are independently written semantic ports — they tes
 Create `tests/datomic_compat_test.rs`:
 
 ```rust
-//! Datomic-inspired compatibility tests (#219).
+//! Datomic-inspired compatibility tests (#221).
 //!
 //! License notice: Datomic is a commercial product. These tests are
 //! INDEPENDENTLY WRITTEN semantic ports — they test concepts from Datomic's
@@ -630,7 +630,7 @@ Expected: all tests pass.
 
 ```bash
 git add tests/datomic_compat_test.rs
-git commit -m "test(compat): add Datomic-inspired compatibility tests (#219)"
+git commit -m "test(compat): add Datomic-inspired compatibility tests (#221)"
 ```
 
 ---
@@ -642,11 +642,11 @@ git commit -m "test(compat): add Datomic-inspired compatibility tests (#219)"
 ```bash
 git push -u origin HEAD
 gh pr create \
-  --title "test(compat): XTDB and Datomic compatibility test corpus (#219)" \
+  --title "test(compat): XTDB and Datomic compatibility test corpus (#221)" \
   --body "$(cat <<'EOF'
 ## Wave 3 PR 6 — Compat Gate
 
-Closes #219.
+Closes #221.
 
 ### XTDB (`tests/xtdb_compat_test.rs`)
 - License: Apache 2.0 — semantic ports permitted
@@ -678,8 +678,8 @@ After this PR merges, all 11 Wave 3 issues are closed:
 - ✅ #215 Migration matrix fixtures
 - ✅ #216 Index corruption recovery
 - ✅ #217 Concurrency stress tests
-- ✅ #219 XTDB/Datomic compat corpus
+- ✅ #221 XTDB/Datomic compat corpus
 - ✅ #220 Long-haul smoke suite
-- ✅ #221 Cross-feature property tests
+- ✅ #212 Cross-feature property tests
 
 Update `CLAUDE.md` test count and `CHANGELOG.md` with Wave 3 completion after all PRs merge.
@@ -203,11 +203,11 @@ fn value_to_json(v: &Value) -> serde_json::Value {
 
 fn query_result_to_json(result: QueryResult) -> String {
     let val = match result {
-        QueryResult::Transacted { tx_id, tx_count } => {
-            serde_json::json!({"transacted": tx_id, "tx_count": tx_count})
+        QueryResult::Transacted(tx_id) => {
+            serde_json::json!({"transacted": tx_id})
         }
-        QueryResult::Retracted { tx_id, tx_count } => {
-            serde_json::json!({"retracted": tx_id, "tx_count": tx_count})
+        QueryResult::Retracted(tx_id) => {
+            serde_json::json!({"retracted": tx_id})
         }
         QueryResult::Ok => serde_json::json!({"ok": true}),
         QueryResult::QueryResults { vars, results } => {

@@ -120,11 +120,11 @@ fn value_to_json(v: &Value) -> serde_json::Value {
 fn query_result_to_json(result: QueryResult) -> String {
     use serde_json::json;
     let val = match result {
-        QueryResult::Transacted { tx_id, tx_count } => {
-            json!({"transacted": tx_id, "tx_count": tx_count})
+        QueryResult::Transacted(tx_id) => {
+            json!({"transacted": tx_id})
         }
-        QueryResult::Retracted { tx_id, tx_count } => {
-            json!({"retracted": tx_id, "tx_count": tx_count})
+        QueryResult::Retracted(tx_id) => {
+            json!({"retracted": tx_id})
         }
         QueryResult::Ok => json!({"ok": true}),
         QueryResult::QueryResults { vars, results } => {
@@ -166,13 +166,9 @@ mod tests {
 
     #[test]
     fn query_result_to_json_transacted() {
-        let json = query_result_to_json(QueryResult::Transacted {
-            tx_id: 12345,
-            tx_count: 1,
-        });
+        let json = query_result_to_json(QueryResult::Transacted(12345));
         let v: serde_json::Value = serde_json::from_str(&json).expect("valid json");
         assert_eq!(v["transacted"], serde_json::json!(12345));
-        assert_eq!(v["tx_count"], serde_json::json!(1));
     }
 
     #[test]
@@ -239,13 +235,9 @@ mod tests {
 
     #[test]
     fn query_result_to_json_retracted() {
-        let json = query_result_to_json(QueryResult::Retracted {
-            tx_id: 99,
-            tx_count: 2,
-        });
+        let json = query_result_to_json(QueryResult::Retracted(99));
         let v: serde_json::Value = serde_json::from_str(&json).expect("valid json");
         assert_eq!(v["retracted"], serde_json::json!(99));
-        assert_eq!(v["tx_count"], serde_json::json!(2));
     }
 
     #[test]

@@ -22,11 +22,11 @@ fn value_to_json(v: &Value) -> serde_json::Value {
 
 fn query_result_to_json(result: QueryResult) -> String {
     let val = match result {
-        QueryResult::Transacted { tx_id, tx_count } => {
-            serde_json::json!({"transacted": tx_id, "tx_count": tx_count})
+        QueryResult::Transacted(tx_id) => {
+            serde_json::json!({"transacted": tx_id})
         }
-        QueryResult::Retracted { tx_id, tx_count } => {
-            serde_json::json!({"retracted": tx_id, "tx_count": tx_count})
+        QueryResult::Retracted(tx_id) => {
+            serde_json::json!({"retracted": tx_id})
         }
         QueryResult::Ok => serde_json::json!({"ok": true}),
         QueryResult::QueryResults { vars, results } => {

@@ -329,11 +329,11 @@ fn query_result_to_json(result: QueryResult) -> String {
     use serde_json::{Value as JVal, json};
 
     let val: JVal = match result {
-        QueryResult::Transacted { tx_id, tx_count } => {
-            json!({"transacted": tx_id, "tx_count": tx_count})
+        QueryResult::Transacted(tx_id) => {
+            json!({"transacted": tx_id})
         }
-        QueryResult::Retracted { tx_id, tx_count } => {
-            json!({"retracted": tx_id, "tx_count": tx_count})
+        QueryResult::Retracted(tx_id) => {
+            json!({"retracted": tx_id})
         }
         QueryResult::Ok => json!({"ok": true}),
         QueryResult::QueryResults { vars, results } => {

@@ -509,9 +509,9 @@ impl Minigraf {
 
             // Return the same QueryResult the executor would have returned.
             if is_retract {
-                Ok(QueryResult::Retracted { tx_id, tx_count })
+                Ok(QueryResult::Retracted(tx_id))
             } else {
-                Ok(QueryResult::Transacted { tx_id, tx_count })
+                Ok(QueryResult::Transacted(tx_id))
             }
         } else {
             // Read-only: no lock needed
@@ -575,6 +575,18 @@ impl Minigraf {
         Self::do_checkpoint(&self.inner.fact_storage, &mut ctx)
     }
 
+    /// Returns the current monotonic transaction counter.
+    ///
+    /// This is the value that `:as-of N` compares against. After a successful
+    /// [`execute`](Self::execute) that returns [`QueryResult::Transacted`] or
+    /// [`QueryResult::Retracted`], this reflects the count of that transaction.
+    ///
+    /// Starts at 0 for a new database and increments once per `transact`/`retract` call,
+    /// regardless of how many facts the batch contains.
+    pub fn current_tx_count(&self) -> u64 {
+        self.inner.fact_storage.current_tx_count()
+    }
+
     /// Internal checkpoint logic (operates on an already-held write-lock guard).
     fn do_checkpoint(_fact_storage: &FactStorage, ctx: &mut WriteContext) -> Result<()> {
         match ctx {