feat(wake): W2 — three-cursor durable store + RECEIVED/CONSUMED ack-wrapper + watch-list schema (#903)

Co-authored-by: jason.woltje <jason@diversecanvas.com> Co-committed-by: jason.woltje <jason@diversecanvas.com>
2026-07-25 23:58:08 +00:00
parent 2726fab5e0
commit 28f022d9c0
7 changed files with 1163 additions and 1 deletions
--- a/packages/mosaic/framework/tools/wake/test-wake-store-ack.sh
+++ b/packages/mosaic/framework/tools/wake/test-wake-store-ack.sh
@@ -0,0 +1,269 @@
+#!/usr/bin/env bash
+# test-wake-store-ack.sh — RED-FIRST invariant harness for W2 (EPIC #892):
+# three-cursor durable store (store.sh, A2) + RECEIVED/CONSUMED ack-wrapper
+# (ack.sh, A4).
+#
+# Each test asserts ONE CONVERGED-DESIGN invariant and is designed to go RED if
+# that invariant regresses:
+#   T1 three-cursor advancement                    (§1.2/§2.4)
+#   T2 digest-coalesce-REPLACE vs actionable-APPEND (§1.2/§2.3)
+#   T3 contiguous-prefix CONSUMED / gap rejection   (§1.2/§2.2)
+#   T4 wake_id DELIVERY-dedup (never re-action)      (§2.2)
+#   T5 atomic write-tmp+rename survives crash mid-write (§1.2)
+#   T6 durability survives restart (retain until CONSUMED) (§2.3)
+#   T7 ack local-write NEVER blocks on network       (§2.2)
+#
+# Isolated: every test runs against a fresh WAKE_STATE_HOME temp dir.
+set -uo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+STORE="$SCRIPT_DIR/store.sh"
+ACK="$SCRIPT_DIR/ack.sh"
+
+command -v jq >/dev/null 2>&1 || {
+  echo "SKIP: jq not available" >&2
+  exit 0
+}
+
+TMP_ROOT="$(mktemp -d)"
+trap 'rm -rf "$TMP_ROOT"' EXIT
+
+# Failures are recorded to a marker FILE, not a shell var: each test runs in a
+# subshell (for env isolation) and a subshell cannot mutate a parent variable,
+# so a var-based counter would silently swallow failures (the exact bug this
+# harness must never have).
+FAILFILE="$TMP_ROOT/failures"
+: >"$FAILFILE"
+pass=0
+fail_msg() {
+  echo "  FAIL: $*" >&2
+  echo "x" >>"$FAILFILE"
+}
+ok() { pass=$((pass + 1)); }
+
+# jq_any FILE FILTER — true iff any JSONL record in FILE matches FILTER. Uses
+# slurp (-s), NOT `jq -e select` (which reflects only the LAST input's value
+# over a multi-line JSONL and would misreport presence).
+jq_any() {
+  local file="$1" filter="$2"
+  [ -f "$file" ] || return 1
+  [ "$(jq -s "[.[] | select($filter)] | length" "$file" 2>/dev/null || echo 0)" -gt 0 ]
+}
+# stream_any — same, but reads JSONL from stdin.
+stream_any() {
+  local filter="$1"
+  [ "$(jq -s "[.[] | select($filter)] | length" 2>/dev/null || echo 0)" -gt 0 ]
+}
+
+# fresh_state NAME — echoes a fresh isolated state home for export.
+fresh_state() {
+  local d="$TMP_ROOT/$1"
+  rm -rf "$d"
+  mkdir -p "$d"
+  printf '%s' "$d"
+}
+
+echo "== T1: three-cursor advancement =="
+(
+  WAKE_STATE_HOME="$(fresh_state t1)"
+  export WAKE_STATE_HOME
+  unset WAKE_AGENT
+  "$STORE" enqueue --seq 1 --class actionable --locators '{"repo":"r","issue":1}' >/dev/null
+  "$STORE" enqueue --seq 2 --class actionable --locators '{"repo":"r","issue":2}' >/dev/null
+  cur="$("$STORE" cursors)"
+  echo "$cur" | grep -q 'observed_seq=2' || fail_msg "T1: observed_seq should be 2 after enqueue 1,2 [$cur]"
+  echo "$cur" | grep -q 'consumed_seq=0' || fail_msg "T1: consumed_seq must NOT advance on enqueue (only on CONSUMED ack) [$cur]"
+  echo "$cur" | grep -q 'pending_depth=2' || fail_msg "T1: pending depth should be 2 [$cur]"
+  # consumed_seq advances only on CONSUMED.
+  "$STORE" consume --upto 2 >/dev/null
+  cur="$("$STORE" cursors)"
+  echo "$cur" | grep -q 'consumed_seq=2' || fail_msg "T1: consumed_seq should be 2 after CONSUMED 2 [$cur]"
+  echo "$cur" | grep -q 'pending_depth=0' || fail_msg "T1: pending drained after CONSUMED [$cur]"
+) && ok
+
+echo "== T2: digest coalesce-REPLACE vs actionable APPEND =="
+(
+  WAKE_STATE_HOME="$(fresh_state t2)"
+  export WAKE_STATE_HOME
+  unset WAKE_AGENT
+  "$STORE" enqueue --seq 1 --class digest --locators '{"head":"aaa"}' >/dev/null
+  "$STORE" enqueue --seq 2 --class actionable --locators '{"issue":7}' >/dev/null
+  "$STORE" enqueue --seq 3 --class digest --locators '{"head":"bbb"}' >/dev/null
+  "$STORE" enqueue --seq 4 --class human --locators '{"from":"peer"}' >/dev/null
+  out="$("$STORE" drain)"
+  ndigest="$(printf '%s\n' "$out" | jq -c 'select(.class=="digest")' | grep -c . || true)"
+  [ "$ndigest" = "1" ] || fail_msg "T2: digest must COALESCE to a single pending entry, got $ndigest"
+  head="$(printf '%s\n' "$out" | jq -r 'select(.class=="digest") | .locators.head')"
+  [ "$head" = "bbb" ] || fail_msg "T2: newest digest must REPLACE prior (expected bbb, got $head)"
+  nactionable="$(printf '%s\n' "$out" | jq -c 'select(.class=="actionable")' | grep -c . || true)"
+  nhuman="$(printf '%s\n' "$out" | jq -c 'select(.class=="human")' | grep -c . || true)"
+  [ "$nactionable" = "1" ] || fail_msg "T2: actionable must APPEND (never replaced), got $nactionable"
+  [ "$nhuman" = "1" ] || fail_msg "T2: human must APPEND / stay durable, got $nhuman"
+  # Durability never bypassed: all classes present in the durable store.
+  total="$(printf '%s\n' "$out" | grep -c . || true)"
+  [ "$total" = "3" ] || fail_msg "T2: durable store should hold digest+actionable+human = 3, got $total"
+) && ok
+
+echo "== T3: contiguous-prefix CONSUMED (reject ack N while N-1 unconsumed) =="
+(
+  WAKE_STATE_HOME="$(fresh_state t3)"
+  export WAKE_STATE_HOME
+  unset WAKE_AGENT
+  # Gap: observe seq 1 and 3, but NOT 2.
+  "$STORE" enqueue --seq 1 --class actionable --locators '{}' >/dev/null
+  "$STORE" enqueue --seq 3 --class actionable --locators '{}' >/dev/null
+  if "$STORE" consume --upto 3 >/dev/null 2>&1; then
+    fail_msg "T3: CONSUMED 3 must be REJECTED while seq 2 is a gap (unconsumed)"
+  fi
+  cur="$("$STORE" cursors)"
+  echo "$cur" | grep -q 'consumed_seq=0' || fail_msg "T3: rejected CONSUMED must NOT advance the cursor [$cur]"
+  # Also reject via the ack wrapper.
+  if "$ACK" consumed --upto 3 --no-sync >/dev/null 2>&1; then
+    fail_msg "T3: ack.sh CONSUMED 3 must be REJECTED over a gap"
+  fi
+  # Fill the gap; now the contiguous prefix is ackable.
+  "$STORE" enqueue --seq 2 --class actionable --locators '{}' >/dev/null
+  "$ACK" consumed --upto 3 --no-sync >/dev/null 2>&1 || fail_msg "T3: CONSUMED 3 should succeed once gap at 2 is filled"
+  cur="$("$STORE" cursors)"
+  echo "$cur" | grep -q 'consumed_seq=3' || fail_msg "T3: consumed_seq should be 3 after contiguous prefix filled [$cur]"
+  # Cumulative + can't regress: CONSUMED 2 after 3 is an idempotent no-op.
+  "$ACK" consumed --upto 2 --no-sync >/dev/null 2>&1 || fail_msg "T3: cumulative CONSUMED 2 (<=3) should be an idempotent success"
+  cur="$("$STORE" cursors)"
+  echo "$cur" | grep -q 'consumed_seq=3' || fail_msg "T3: cursor must not regress below 3 [$cur]"
+) && ok
+
+echo "== T4: wake_id DELIVERY-dedup (dup delivery = re-RECEIVE, never re-action) =="
+(
+  WAKE_STATE_HOME="$(fresh_state t4)"
+  export WAKE_STATE_HOME
+  unset WAKE_AGENT
+  "$STORE" enqueue --seq 1 --class digest --locators '{}' >/dev/null
+  r1="$("$ACK" received --wake-id WID-abc)"
+  [ "$r1" = "RECEIVED" ] || fail_msg "T4: first delivery should be RECEIVED, got '$r1'"
+  r2="$("$ACK" received --wake-id WID-abc)"
+  [ "$r2" = "DUP" ] || fail_msg "T4: duplicate delivery of same wake_id should be DUP (re-RECEIVE), got '$r2'"
+  # RECEIVED (delivery) must NEVER advance consumed_seq (delivery != consumption).
+  cur="$("$STORE" cursors)"
+  echo "$cur" | grep -q 'consumed_seq=0' || fail_msg "T4: RECEIVED must not advance consumed_seq [$cur]"
+) && ok
+
+echo "== T5: atomic write-tmp+rename survives crash mid-write =="
+(
+  WAKE_STATE_HOME="$(fresh_state t5)"
+  export WAKE_STATE_HOME
+  unset WAKE_AGENT
+  "$STORE" enqueue --seq 1 --class actionable --locators '{"issue":1}' >/dev/null
+  STATE_DIR="$WAKE_STATE_HOME/default"
+  before="$(cat "$STATE_DIR/pending.jsonl")"
+  # Simulate a crash mid-write: a leftover atomic-write temp file with GARBAGE
+  # that was never renamed over the live file.
+  printf '{"observed_seq": 999, TRUNCATED-GARBAGE' >"$STATE_DIR/.wake.tmp.crash12"
+  # The live store must be untouched and still valid JSON.
+  after="$(cat "$STATE_DIR/pending.jsonl")"
+  [ "$before" = "$after" ] || fail_msg "T5: live pending.jsonl changed by a crash temp file"
+  drained="$("$STORE" drain)"
+  printf '%s\n' "$drained" | jq -e . >/dev/null 2>&1 || fail_msg "T5: drain returned non-JSON — garbage temp corrupted the store"
+  printf '%s\n' "$drained" | stream_any '.observed_seq==1' || fail_msg "T5: committed entry (seq 1) lost after simulated crash"
+  printf '%s\n' "$drained" | grep -q 999 && fail_msg "T5: uncommitted garbage (seq 999) leaked into the live store"
+  # A subsequent real mutation must succeed and clean the stale temp.
+  "$STORE" enqueue --seq 2 --class actionable --locators '{"issue":2}' >/dev/null || fail_msg "T5: enqueue after crash temp failed"
+  [ -e "$STATE_DIR/.wake.tmp.crash12" ] && fail_msg "T5: stale crash temp not cleaned by next mutation"
+  d2="$("$STORE" drain)"
+  [ "$(printf '%s\n' "$d2" | grep -c .)" = "2" ] || fail_msg "T5: store not healthy after crash+recovery (expected 2 entries)"
+) && ok
+
+echo "== T5b: _atomic_write is tmp+rename (killing the writer mid-write leaves the target intact) =="
+(
+  WAKE_STATE_HOME="$(fresh_state t5b)"
+  export WAKE_STATE_HOME
+  unset WAKE_AGENT
+  # shellcheck disable=SC1091
+  . "$SCRIPT_DIR/_wake-common.sh"
+  d="$WAKE_STATE_HOME/atomic"
+  mkdir -p "$d"
+  target="$d/file"
+  printf 'GOOD\n' | _atomic_write "$target"
+  # Feed a writer via a FIFO but NEVER send EOF, then kill it mid-write. With
+  # true tmp+rename the partial bytes land in a temp file and the rename never
+  # runs, so `target` keeps its committed content. A direct (non-atomic) write
+  # would have streamed the garbage straight into `target`.
+  fifo="$d/fifo"
+  mkfifo "$fifo"
+  ( _atomic_write "$target" <"$fifo" ) &
+  wpid=$!
+  exec 9>"$fifo"
+  printf 'PARTIAL-GARBAGE-NO-EOF' >&9
+  sleep 0.3
+  pkill -9 -P "$wpid" 2>/dev/null || true
+  kill -9 "$wpid" 2>/dev/null || true
+  exec 9>&-
+  wait "$wpid" 2>/dev/null || true
+  got="$(cat "$target" 2>/dev/null)"
+  [ "$got" = "GOOD" ] || fail_msg "T5b: target corrupted by a killed mid-write (got '$got') — write is not tmp+rename atomic"
+) && ok
+
+echo "== T6: durability survives restart (retain until CONSUMED) =="
+(
+  WAKE_STATE_HOME="$(fresh_state t6)"
+  export WAKE_STATE_HOME
+  unset WAKE_AGENT
+  # "Session 1": enqueue then vanish (no in-memory state carried).
+  "$STORE" enqueue --seq 1 --class human --locators '{"from":"peer"}' >/dev/null
+  "$STORE" enqueue --seq 2 --class actionable --locators '{"issue":9}' >/dev/null
+  # "Session 2": a brand-new process (this subshell invocation of store.sh) must
+  # see the persisted entries — nothing was held in memory.
+  d="$("$STORE" drain)"
+  [ "$(printf '%s\n' "$d" | grep -c .)" = "2" ] || fail_msg "T6: entries not retained across restart (expected 2)"
+  printf '%s\n' "$d" | stream_any '.class=="human"' || fail_msg "T6: a human message was lost across restart (durability bypassed)"
+  # Retained UNTIL consumed: after CONSUMED they are released.
+  "$STORE" consume --upto 2 >/dev/null
+  d2="$("$STORE" drain)"
+  n2="$(printf '%s\n' "$d2" | grep -c . || true)"
+  [ "$n2" = "0" ] || fail_msg "T6: entries should be released only AFTER CONSUMED (still $n2 pending)"
+) && ok
+
+echo "== T7: ack local-write NEVER blocks on network =="
+(
+  WAKE_STATE_HOME="$(fresh_state t7)"
+  export WAKE_STATE_HOME
+  unset WAKE_AGENT
+  "$STORE" enqueue --seq 1 --class digest --locators '{}' >/dev/null
+  # A network-shaped shim on PATH: if the SYNCHRONOUS ack path ever invoked the
+  # network directly, this marker would appear before ack returns.
+  bin="$TMP_ROOT/t7bin"
+  mkdir -p "$bin"
+  for netcmd in curl wget nc ssh; do
+    cat >"$bin/$netcmd" <<EOF
+#!/usr/bin/env bash
+touch "$WAKE_STATE_HOME/NET_CALLED_SYNC"
+exit 0
+EOF
+    chmod +x "$bin/$netcmd"
+  done
+  # Background sync deliberately SLOW: proves the ack does not wait for it.
+  export WAKE_ACK_SYNC_CMD="sleep 3; touch '$WAKE_STATE_HOME/SYNC_DONE'"
+  start="$(date +%s)"
+  out="$(PATH="$bin:$PATH" "$ACK" consumed --upto 1 --wake-id WID-1)"
+  end="$(date +%s)"
+  elapsed=$((end - start))
+  [ "$elapsed" -lt 2 ] || fail_msg "T7: ack path blocked ${elapsed}s — must return without waiting on the background sync"
+  echo "$out" | grep -q 'CONSUMED 1' || fail_msg "T7: CONSUMED not reported [$out]"
+  # Local write is durable IMMEDIATELY (no network needed to record the ack).
+  STATE_DIR="$WAKE_STATE_HOME/default"
+  jq_any "$STATE_DIR/ack-ledger.jsonl" '.type=="CONSUMED" and .upto==1' ||
+    fail_msg "T7: CONSUMED not written to the local ledger synchronously"
+  consumed_now="$("$STORE" cursors | sed -n 's/consumed_seq=//p')"
+  [ "$consumed_now" = "1" ] || fail_msg "T7: consumed_seq not advanced by the local ack write (got '$consumed_now')"
+  # The synchronous path must NOT have touched the network.
+  [ -e "$WAKE_STATE_HOME/NET_CALLED_SYNC" ] && fail_msg "T7: a network command was invoked on the SYNCHRONOUS ack path"
+  # And the slow sync must still be in flight (proves it was truly backgrounded).
+  [ -e "$WAKE_STATE_HOME/SYNC_DONE" ] && fail_msg "T7: background sync finished synchronously — it was not detached"
+  true
+) && ok
+
+echo
+if [ -s "$FAILFILE" ]; then
+  echo "wake store/ack harness: FAILED ($(grep -c . "$FAILFILE") assertion(s))" >&2
+  exit 1
+fi
+echo "wake store/ack harness: all invariants passed ($pass groups)"