3 files changed, 87 insertions, 1 deletions
diff --git a/src/LivingVillage.Desktop.Tests/M3BatchOutputTests.fs b/src/LivingVillage.Desktop.Tests/M3BatchOutputTests.fs
index b1822c7..963d571 100644
--- a/src/LivingVillage.Desktop.Tests/M3BatchOutputTests.fs
+++ b/src/LivingVillage.Desktop.Tests/M3BatchOutputTests.fs
@@ -32,6 +32,13 @@ type M3BatchOutputTests () =
         Assert.AreEqual<string>("[world 0] progress day=15/15 elapsed=260.0s", BatchOutput.progressLine 0 15L 15L 260.0)
 
     [<TestMethod>]
+    member _.MultiworldLineReportsCountsGcRssAndElapsed () =
+        let line = BatchOutput.multiworldLine 8 4L 20L 1600L 32000L 64L 5120L (1048576L * 96L) (1048576L * 240L) 31.5
+        Assert.AreEqual<string>(
+            "multiworld_sample worlds=8 day=4/20 events=1600 rumors=32000 annals=64 memory_entries=5120 gc_live_mb=96.00 working_set_rss_mb=240.00 elapsed_s=31.5",
+            line)
+
+    [<TestMethod>]
     member _.SummaryLineKeepsOldFieldsAndAppendsWallClock () =
         let line = BatchOutput.summaryLine 4 3 1 4 1.100 9.900 0.010 0.400 4 610.5
         // 监督器正则只读前三个字段，前缀必须逐字保持。
diff --git a/src/LivingVillage.Headless/BatchOutput.fs b/src/LivingVillage.Headless/BatchOutput.fs
index 971da97..aa79391 100644
--- a/src/LivingVillage.Headless/BatchOutput.fs
+++ b/src/LivingVillage.Headless/BatchOutput.fs
@@ -42,6 +42,23 @@ module BatchOutput =
             "batch_summary worlds=%d passed=%d failed=%d old_passed=%d/%d ratio_min=%.3f ratio_max=%.3f gini_min=%.3f gini_max=%.3f elapsed_s=%.1f workers=%d wall_s=%.1f"
             worlds passed failed oldPassed worlds ratioMin ratioMax giniMin giniMax elapsedSeconds workers elapsedSeconds
 
+    /// 多世界并存压测采样行：worlds/day 与各历史集合计数 + GC live set + OS RSS + 墙钟。
+    let multiworldLine
+        (worlds: int)
+        (day: int64)
+        (totalDays: int64)
+        (events: int64)
+        (rumors: int64)
+        (annals: int64)
+        (memoryEntries: int64)
+        (gcLiveBytes: int64)
+        (rssBytes: int64)
+        (elapsedSeconds: float) : string =
+        let mb (bytes: int64) = float bytes / (1024.0 * 1024.0)
+        sprintf
+            "multiworld_sample worlds=%d day=%d/%d events=%d rumors=%d annals=%d memory_entries=%d gc_live_mb=%.2f working_set_rss_mb=%.2f elapsed_s=%.1f"
+            worlds day totalDays events rumors annals memoryEntries (mb gcLiveBytes) (mb rssBytes) elapsedSeconds
+
     /// --cost-probe 单段输出：ticks/s、墙钟、分配与 GC 全部来自真实测量。
     let costLine
         (days: int64)
diff --git a/src/LivingVillage.Headless/Program.fs b/src/LivingVillage.Headless/Program.fs
index 4bd6424..c9dd442 100644
--- a/src/LivingVillage.Headless/Program.fs
+++ b/src/LivingVillage.Headless/Program.fs
@@ -612,6 +612,66 @@ let runProfileLongRun (argv: string[]) : int =
     Console.Out.Flush()
     if world.Tick = days * ticksPerDay then 0 else 1
 
+/// `--profile-multiworld [worlds] [days] [npcs] [sampleEveryDays] [seedBase]`：
+/// N 个 Sim 世界并存、按采样轮并行推进 D 天（只读 profile，不改 Kernel/Sim 语义）。
+/// 每 `sampleEveryDays` 天打印一行流式采样（worlds/count、events、rumors、annals、
+/// memory_entries、gc_live_mb、working_set_rss_mb、elapsed_s）并 flush；行的聚合口径为
+/// 全部并存世界之和，ground truth 是 GC live set 与 OS WorkingSet。
+let runProfileMultiworld (argv: string[]) : int =
+    let argInt64 index (dflt: int64) =
+        if argv.Length > index then
+            match Int64.TryParse argv.[index] with
+            | true, v when v > 0L -> v
+            | _ -> dflt
+        else dflt
+    let worlds = int (argInt64 1 10L)
+    let days = argInt64 2 20L
+    let npcs = int (argInt64 3 (int64 Sim.npcCount))
+    let sampleEvery = argInt64 4 2L
+    let seedBase = if argv.Length > 5 then (match UInt64.TryParse argv.[5] with | true, v -> v | _ -> 42UL) else 42UL
+    let proc = System.Diagnostics.Process.GetCurrentProcess()
+    printfn "multiworld_start worlds=%d days=%d npcs=%d sample_every_days=%d seed_base=%d ticks_per_day=%d"
+        worlds days npcs sampleEvery seedBase ticksPerDay
+    Console.Out.Flush()
+    let ws = Array.init worlds (fun i -> Sim.initialWorldN (seedBase + uint64 i) npcs)
+    let drivers = Array.init worlds (fun i -> { Rng = Rng.ofSeed (seedBase + uint64 i); Until = segmentTicks; Input = zeroInput })
+    let sw = System.Diagnostics.Stopwatch.StartNew()
+    let advanceOne (i: int) (targetDay: int64) =
+        let mutable world = ws.[i]
+        let mutable driver = drivers.[i]
+        let dayEnd = targetDay * ticksPerDay
+        while world.Tick < dayEnd do
+            let d, input =
+                if world.Tick < driver.Until then driver, driver.Input
+                else
+                    let d = nextSegment driver.Rng driver.Until
+                    d, d.Input
+            driver <- d
+            world <- Sim.step { Input = input } world
+        ws.[i] <- world
+        drivers.[i] <- driver
+    let sample (day: int64) =
+        let gcLive = System.GC.GetTotalMemory true
+        proc.Refresh()
+        let rss = proc.WorkingSet64
+        let events = ws |> Array.sumBy (fun w -> int64 w.Events.Length)
+        let rumors = ws |> Array.sumBy (fun w -> int64 w.Rumors.Length)
+        let annals = ws |> Array.sumBy (fun w -> int64 w.Annals.Length)
+        let memEntries = ws |> Array.sumBy (fun w -> int64 (w.Npcs |> Array.sumBy (fun n -> n.Mind.Memory.Length)))
+        printfn "%s" (LivingVillage.Headless.BatchOutput.multiworldLine worlds day days events rumors annals memEntries gcLive rss sw.Elapsed.TotalSeconds)
+        Console.Out.Flush()
+    sample 0L
+    let mutable dayNo = 0L
+    while dayNo < days do
+        let target = min days (dayNo + sampleEvery)
+        System.Threading.Tasks.Parallel.For(0, worlds, fun i -> advanceOne i target) |> ignore
+        dayNo <- target
+        sample dayNo
+    let digests = ws |> Array.mapi (fun i w -> sprintf "%d:%s" i (LivingVillage.Headless.PerformanceProbe.worldDigest w)) |> String.concat ","
+    printfn "multiworld_done worlds=%d day=%d elapsed_s=%.1f world_digests=%s" worlds dayNo sw.Elapsed.TotalSeconds digests
+    Console.Out.Flush()
+    if ws |> Array.forall (fun w -> w.Tick = days * ticksPerDay) then 0 else 1
+
 let runExisting (argv: string[]) =
     let rec parse
         (i: int)
@@ -675,7 +735,7 @@ let runExisting (argv: string[]) =
             if stats.NonFinite > 0L || stats.OutOfBounds > 0L || not replayOk then 1 else 0
     | Error msg ->
         eprintfn $"headless: {msg}"
-        eprintfn "usage: dotnet run -c Release --project src/LivingVillage.Headless -- --days N --seed S [--npc N] [--dump-relations] [--dump-rumors] [--replay-rumors] | --m5-smoke | --m6a-smoke | --batch K D | --performance-baseline | --cost-probe [D1,D2,...] | --rumor-bench [days npcs chats_per_day]"
+        eprintfn "usage: dotnet run -c Release --project src/LivingVillage.Headless -- --days N --seed S [--npc N] [--dump-relations] [--dump-rumors] [--replay-rumors] | --m5-smoke | --m6a-smoke | --batch K D | --performance-baseline | --cost-probe [D1,D2,...] | --rumor-bench [days npcs chats_per_day] | --profile-long-run [days sampleEveryDays npcs seed] | --profile-multiworld [worlds days npcs sampleEveryDays seedBase]"
         2
 
 let private parseCostLadder (argv: string[]) : int64 list =
@@ -706,5 +766,7 @@ let main argv =
         runRumorBench argv
     elif argv.Length >= 1 && argv.[0] = "--profile-long-run" then
         runProfileLongRun argv
+    elif argv.Length >= 1 && argv.[0] = "--profile-multiworld" then
+        runProfileMultiworld argv
     else
         runExisting argv