feat: import Chinese-localized Buzz source snapshot

Signed-off-by: cls_宁波本机 <908705107@qq.com>

docs/formal/nip-rs-unread/model.py

@@ -0,0 +1,492 @@
+"""Bounded exhaustive model comparing two NIP-RS manual-unread encodings.
+
+Candidate A: lexicographic operation register
+  Per context: {counter, client_tiebreak, op in {SET,CLEAR}, baseline}
+  in a NEW top-level field beside `contexts`.
+  Merge = max tuple (counter, tiebreak, op-rule on full tie).
+
+Candidate B: two grow-only counters + baseline
+  Per context: S (set counter), C (clear counter), B (frontier-at-set-time)
+  as sibling keys under `contexts` (ov_s:, ov_c:, ov_b: prefixes).
+  Action: own counter := max(S,C)+1; set also writes B := effective frontier.
+  Merge = componentwise max. Tie policy on S == C is a parameter.
+
+Both share:
+  - Frontier: grow-only max() per NIP-RS v1 (unchanged).
+  - Verdict: unread(ctx) = latest > effective_frontier(ctx) OR override_set(ctx).
+  - Mark-read = advance frontier + clear override.
+  - Mark-unread = set override with baseline B = current effective frontier.
+  - Natural frontier advance strictly past B dominates a stale set.
+
+Device simulators use overridable methods (_override_set, _compact, _merge_reg,
+_bump, _sanitize_value) so the mutation harness can inject weakened rules via
+subclassing without monkeypatching.
+"""
+from dataclasses import dataclass
+from typing import Optional
+
+
+SET = "SET"
+CLEAR = "CLEAR"
+
+
+# ---------------------------------------------------------------------------
+# Reserved key namespace + escaping
+#
+# NIP-RS v1 context IDs are arbitrary UTF-8 (spec :89, :113-114), so a
+# pre-existing opaque context could legitimately begin with `ov_s:`,
+# `ov_c:`, or `ov_b:` and collide with a control key for a DIFFERENT
+# context in the same flattened `contexts` map. `ov_` (the shared
+# 3-byte stem) and the escape marker itself are reserved; any raw
+# context ID that would collide is escaped before being used as a
+# plain frontier key. Escaping is a no-op for every context ID Buzz
+# actually generates (channel UUID, `msg:<hex64>`, `thread:<hex64>`
+# — none start with `ov_` or `esc:`), so the common case pays zero
+# bytes. Only a pathological ID pays the 4-byte `esc:` cost.
+#
+# This protects context IDs generated by amendment-aware clients.
+# It does NOT retroactively protect a context that a PRE-EXISTING
+# legacy client already published unescaped before the amendment
+# shipped — that residual hazard is documented, not solved (see
+# NOTE.md "Reserved key namespace").
+# ---------------------------------------------------------------------------
+
+ESCAPE_PREFIX = "esc:"
+_RESERVED_STEM = "ov_"
+
+
+def _needs_escape(raw_key: str) -> bool:
+    return raw_key.startswith(_RESERVED_STEM) or raw_key.startswith(ESCAPE_PREFIX)
+
+
+def escape_context_key(raw_key: str) -> str:
+    return ESCAPE_PREFIX + raw_key if _needs_escape(raw_key) else raw_key
+
+
+def unescape_context_key(wire_key: str) -> str:
+    if wire_key.startswith(ESCAPE_PREFIX):
+        return wire_key[len(ESCAPE_PREFIX):]
+    return wire_key
+
+
+# ---------------------------------------------------------------------------
+# Candidate B — two grow-only counters + baseline
+# ---------------------------------------------------------------------------
+
+@dataclass(frozen=True)
+class RegB:
+    s: int = 0
+    c: int = 0
+    b: int = 0
+
+
+def merge_reg_b(a: Optional[RegB], b: Optional[RegB]) -> Optional[RegB]:
+    if a is None:
+        return b
+    if b is None:
+        return a
+    return RegB(s=max(a.s, b.s), c=max(a.c, b.c), b=max(a.b, b.b))
+
+
+def override_set_b(reg: Optional[RegB], frontier_val: int, tie_policy=CLEAR) -> bool:
+    if reg is None:
+        return False
+    if frontier_val > reg.b and reg.s > 0:
+        return False
+    if reg.s > reg.c:
+        return True
+    if reg.s == reg.c and reg.s > 0:
+        return tie_policy == SET
+    return False
+
+
+def compact_b(reg: RegB, frontier_val: int, tie_policy=CLEAR) -> Optional[RegB]:
+    """Compact override state.
+
+    Tombstone-floor design: a register with any recorded counter
+    activity (S>0 or C>0) is never fully deleted. Its counter
+    high-water-mark is exactly what prevents a stale replica —
+    any (S,C) pair below that ceiling — from dominating a freshly
+    created register after compaction (delete-on-dominance made
+    counters reusable: a dead register dropped entirely, then a new
+    local set/clear pair restarted from S=0/C=0, so a delayed stale
+    peer snapshot with S>0 could out-rank the new state on replay).
+    Only a virgin register (S==0, C==0, no activity ever recorded)
+    has no ceiling to protect and compacts to None.
+
+    A live override (per `override_set_b`, which is already
+    policy-aware) is returned unchanged — compaction only touches dead
+    state. Dead overrides — whether dominated by C>S, tied under
+    clear-wins, or baseline-dominated by frontier advance — compact to
+    the clear-tombstone floor `RegB(s=0, c=max(S,C), b=0)`: S is
+    zeroed (no longer overriding), but C retains the ceiling so both a
+    future local bump (`max(S,C)+1`) and a componentwise-max merge with
+    any pre-compaction stale snapshot start strictly above the
+    historical maximum, never below it.
+    """
+    if reg.s == 0 and reg.c == 0:
+        return None
+    if override_set_b(reg, frontier_val, tie_policy):
+        return reg
+    return RegB(s=0, c=max(reg.s, reg.c), b=0)
+
+
+# ---------------------------------------------------------------------------
+# Candidate A — lexicographic operation register
+# ---------------------------------------------------------------------------
+
+@dataclass(frozen=True)
+class RegA:
+    counter: int = 0
+    tiebreak: str = ""
+    op: str = CLEAR
+    baseline: int = 0
+
+    def as_tuple(self, op_wins):
+        op_val = 1 if self.op == op_wins else 0
+        return (self.counter, self.tiebreak, op_val)
+
+
+def merge_reg_a(a: Optional[RegA], b: Optional[RegA], tie_op=CLEAR) -> Optional[RegA]:
+    if a is None:
+        return b
+    if b is None:
+        return a
+    at = a.as_tuple(tie_op)
+    bt = b.as_tuple(tie_op)
+    if at == bt:
+        return RegA(
+            counter=a.counter, tiebreak=a.tiebreak, op=a.op,
+            baseline=max(a.baseline, b.baseline),
+        )
+    return a if at > bt else b
+
+
+# ---------------------------------------------------------------------------
+# Device simulation — Candidate B
+# ---------------------------------------------------------------------------
+
+class DeviceB:
+    """Simulates one device's NIP-RS read-state blob with manual-unread
+    override layer (candidate B encoding).
+
+    All model operations go through overridable _methods so the mutation
+    harness can inject weakened rules via subclassing.
+    """
+
+    def __init__(self, client_id, is_legacy=False):
+        self.client_id = client_id
+        self.is_legacy = is_legacy
+        self.frontier = {}
+        self.overrides = {}
+
+    def effective_frontier(self, ctx):
+        return self.frontier.get(ctx, 0)
+
+    def _override_set(self, reg, frontier_val, tie_policy):
+        return override_set_b(reg, frontier_val, tie_policy)
+
+    def _compact(self, reg, frontier_val, tie_policy):
+        return compact_b(reg, frontier_val, tie_policy)
+
+    def _merge_reg(self, a, b):
+        return merge_reg_b(a, b)
+
+    def _bump(self, s, c):
+        return max(s, c) + 1
+
+    def _sanitize_value(self, v):
+        return isinstance(v, int) and 0 <= v <= 4294967295
+
+    def override_is_set(self, ctx, tie_policy=CLEAR):
+        return self._override_set(
+            self.overrides.get(ctx), self.effective_frontier(ctx), tie_policy
+        )
+
+    def verdict(self, ctx, latest_ts, tie_policy=CLEAR):
+        return (latest_ts > self.effective_frontier(ctx)
+                or self.override_is_set(ctx, tie_policy))
+
+    def do_mark_unread(self, ctx):
+        if self.is_legacy:
+            return
+        cur = self.overrides.get(ctx, RegB())
+        new_s = self._bump(cur.s, cur.c)
+        self.overrides[ctx] = RegB(s=new_s, c=cur.c, b=self.effective_frontier(ctx))
+
+    def do_mark_read(self, ctx, frontier_ts):
+        self.frontier[ctx] = max(self.frontier.get(ctx, 0), frontier_ts)
+        if not self.is_legacy:
+            cur = self.overrides.get(ctx, RegB())
+            new_c = self._bump(cur.s, cur.c)
+            self.overrides[ctx] = RegB(s=cur.s, c=new_c, b=cur.b)
+
+    def do_advance_frontier(self, ctx, ts):
+        self.frontier[ctx] = max(self.frontier.get(ctx, 0), ts)
+
+    def do_compact(self, ctx, tie_policy=CLEAR):
+        reg = self.overrides.get(ctx)
+        if reg is None:
+            return
+        result = self._compact(reg, self.effective_frontier(ctx), tie_policy)
+        if result is None:
+            if ctx in self.overrides:
+                del self.overrides[ctx]
+        else:
+            self.overrides[ctx] = result
+
+    def do_reinstall(self):
+        self.client_id = self.client_id + "_r"
+        self.frontier = {}
+        self.overrides = {}
+
+    def _canonicalize_for_publish(self, ctx, tie_policy):
+        """Canonical published form of `ctx`'s override register,
+        computed fresh against the current effective frontier —
+        independent of whether `do_compact` was ever called locally.
+        Returns `(is_live, canonical_reg)`; `canonical_reg is None`
+        means virgin (omit from the wire entirely). Reuses the same
+        overridable `_compact`/`_override_set` hooks `do_compact` uses,
+        so a mutation-harness subclass that weakens one weakens both
+        the storage-GC path and the publish path identically.
+        """
+        reg = self.overrides.get(ctx)
+        if reg is None:
+            return False, None
+        front = self.effective_frontier(ctx)
+        canonical = self._compact(reg, front, tie_policy)
+        if canonical is None:
+            return False, None
+        return self._override_set(canonical, front, tie_policy), canonical
+
+    def publish_blob(self, tie_policy=CLEAR):
+        """Serialize this device's read-state blob.
+
+        Every override is canonicalized at serialization time: live ->
+        unchanged (3 keys), dead -> tombstone floor (1 key, `ov_c:`
+        only), virgin -> omitted (0 keys). Canonical publication is a
+        protocol requirement, not an optimization — noncanonical wire
+        output is structurally impossible here, not merely avoided by
+        convention. `do_compact` remains a separate storage-GC
+        transition that mutates `self.overrides`; publication no
+        longer depends on it having been called first.
+
+        **Atomic slot-grouping rule (spec-amendment requirement):**
+        A context's frontier entry and ALL of its `ov_*` sibling entries
+        MUST travel in the same slot. `split_blob_into_slots` below
+        enforces this by round-robining per-context groups, never
+        per-entry. A receiving client that only holds part of a context
+        group and attempts to reconstruct a `RegB` from it would see
+        partial zeroes and might canonically re-publish a false
+        tombstone. Group atomicity makes partial reconstruction
+        structurally impossible from a compliant publisher's output.
+        """
+        blob_ctx = {escape_context_key(k): v for k, v in self.frontier.items()}
+        if not self.is_legacy:
+            for k in self.overrides:
+                is_live, canonical = self._canonicalize_for_publish(k, tie_policy)
+                if canonical is None:
+                    continue  # virgin: omitted from the wire entirely
+                if is_live:
+                    blob_ctx[f"ov_s:{k}"] = canonical.s
+                    blob_ctx[f"ov_c:{k}"] = canonical.c
+                    blob_ctx[f"ov_b:{k}"] = canonical.b
+                else:
+                    blob_ctx[f"ov_c:{k}"] = canonical.c  # tombstone: ceiling only
+        return {"v": 1, "client_id": self.client_id, "contexts": blob_ctx}
+
+    def split_blob_into_slots(self, tie_policy=CLEAR, n_slots=2):
+        """Split this device's blob into `n_slots` compliant slots.
+
+        **Atomic grouping rule:** a context's frontier entry and ALL of
+        its `ov_*` sibling entries travel together in the same slot.
+        Round-robin assignment is per-context group, never per-entry.
+        This matches production `splitContextsIntoBudgetedSlots` when
+        it is amended to group by context instead of by individual entry.
+
+        Returns a list of `n_slots` blobs, each with the same `v` and
+        `client_id` but a disjoint subset of context groups.
+        """
+        blob = self.publish_blob(tie_policy)
+        contexts = blob["contexts"]
+
+        # Gather per-context groups: each group is a list of (key, value) pairs.
+        # A "group" is: the frontier key (escaped ctx) + any ov_* siblings.
+        # Contexts that appear only as ov_* keys (no frontier entry) are
+        # also grouped together.
+        groups = {}  # logical_ctx -> list of (wire_key, value)
+        for wire_key, value in contexts.items():
+            if wire_key.startswith("ov_s:"):
+                ctx = wire_key[5:]
+            elif wire_key.startswith("ov_c:"):
+                ctx = wire_key[5:]
+            elif wire_key.startswith("ov_b:"):
+                ctx = wire_key[5:]
+            else:
+                # Frontier key: may be escaped (e.g. "esc:ov_s:evil").
+                # Derive the logical context ID by unescaping so this
+                # entry joins the same group as its ov_* siblings, which
+                # are keyed by the RAW context ID (e.g. "ov_s:evil" ->
+                # ctx = "evil", but "esc:ov_s:evil" frontier -> ctx =
+                # "ov_s:evil" after unescape).  Without this step an
+                # escaped frontier key and its ov_* siblings would be
+                # treated as two different groups, splitting the register
+                # across slots — reproducing the round-1 partial-
+                # reconstruction poison for escaped context IDs.
+                ctx = unescape_context_key(wire_key)
+            groups.setdefault(ctx, []).append((wire_key, value))
+
+        slots = [{"v": blob["v"], "client_id": blob["client_id"], "contexts": {}}
+                 for _ in range(n_slots)]
+        for i, (_ctx, pairs) in enumerate(sorted(groups.items())):
+            slot = slots[i % n_slots]
+            for wire_key, value in pairs:
+                slot["contexts"][wire_key] = value
+        return slots
+
+    def receive_merge(self, blob):
+        incoming_overrides = {}
+        for k, v in blob.get("contexts", {}).items():
+            if k.startswith("ov_s:"):
+                ctx = k[5:]
+                incoming_overrides.setdefault(ctx, [0, 0, 0])[0] = v
+            elif k.startswith("ov_c:"):
+                ctx = k[5:]
+                incoming_overrides.setdefault(ctx, [0, 0, 0])[1] = v
+            elif k.startswith("ov_b:"):
+                ctx = k[5:]
+                incoming_overrides.setdefault(ctx, [0, 0, 0])[2] = v
+            else:
+                ctx = unescape_context_key(k)
+                self.frontier[ctx] = max(self.frontier.get(ctx, 0), v)
+
+        if not self.is_legacy:
+            for ctx, (s, c, b) in incoming_overrides.items():
+                incoming_reg = RegB(s=s, c=c, b=b)
+                self.overrides[ctx] = self._merge_reg(
+                    self.overrides.get(ctx), incoming_reg
+                )
+
+    def legacy_sanitize_and_publish(self, tie_policy=CLEAR):
+        blob = self.publish_blob(tie_policy)
+        sanitized = {}
+        for k, v in blob["contexts"].items():
+            if len(k.encode("utf-8")) <= 256 and self._sanitize_value(v):
+                sanitized[k] = v
+        return {"v": 1, "client_id": self.client_id, "contexts": sanitized}
+
+    def state_key(self, contexts, tie_policy=CLEAR):
+        parts = []
+        for ctx in sorted(contexts):
+            f = self.effective_frontier(ctx)
+            reg = self.overrides.get(ctx, RegB())
+            ov = self.override_is_set(ctx, tie_policy)
+            parts.append((ctx, f, reg.s, reg.c, reg.b, ov))
+        return (self.client_id, self.is_legacy, tuple(parts))
+
+
+# ---------------------------------------------------------------------------
+# Device simulation — Candidate A
+# ---------------------------------------------------------------------------
+
+class DeviceA:
+    def __init__(self, client_id, is_legacy=False):
+        self.client_id = client_id
+        self.is_legacy = is_legacy
+        self.frontier = {}
+        self.overrides = {}
+        self.counter = 0
+
+    def effective_frontier(self, ctx):
+        return self.frontier.get(ctx, 0)
+
+    def override_is_set(self, ctx):
+        reg = self.overrides.get(ctx)
+        if reg is None or reg.op == CLEAR:
+            return False
+        if self.effective_frontier(ctx) > reg.baseline:
+            return False
+        return True
+
+    def verdict(self, ctx, latest_ts):
+        return latest_ts > self.effective_frontier(ctx) or self.override_is_set(ctx)
+
+    def do_mark_unread(self, ctx):
+        if self.is_legacy:
+            return
+        self.counter += 1
+        self.overrides[ctx] = RegA(
+            counter=self.counter, tiebreak=self.client_id,
+            op=SET, baseline=self.effective_frontier(ctx),
+        )
+
+    def do_mark_read(self, ctx, frontier_ts):
+        self.frontier[ctx] = max(self.frontier.get(ctx, 0), frontier_ts)
+        if not self.is_legacy:
+            self.counter += 1
+            self.overrides[ctx] = RegA(
+                counter=self.counter, tiebreak=self.client_id,
+                op=CLEAR, baseline=0,
+            )
+
+    def do_advance_frontier(self, ctx, ts):
+        self.frontier[ctx] = max(self.frontier.get(ctx, 0), ts)
+
+    def receive_merge(self, blob, tie_op=CLEAR):
+        for ctx, ts in blob.get("contexts", {}).items():
+            self.frontier[ctx] = max(self.frontier.get(ctx, 0), ts)
+        if not self.is_legacy:
+            for ctx, reg in blob.get("overrides", {}).items():
+                self.overrides[ctx] = merge_reg_a(
+                    self.overrides.get(ctx), reg, tie_op
+                )
+                if reg.counter > self.counter:
+                    self.counter = reg.counter
+
+    def publish_blob(self):
+        blob = {"v": 1, "client_id": self.client_id, "contexts": dict(self.frontier)}
+        if not self.is_legacy:
+            blob["overrides"] = dict(self.overrides)
+        return blob
+
+    def legacy_rewrite_and_publish(self):
+        return {"v": 1, "client_id": self.client_id, "contexts": dict(self.frontier)}
+
+
+# ---------------------------------------------------------------------------
+# Legacy pruning/trim model
+# ---------------------------------------------------------------------------
+
+def legacy_prune(contexts, horizon):
+    return {k: v for k, v in contexts.items()
+            if not (k.startswith("msg:") or k.startswith("thread:")) or v >= horizon}
+
+
+def legacy_trim(contexts, client_id, max_bytes=32768):
+    import json
+
+    def size(ctx):
+        return len(json.dumps({"v": 1, "client_id": client_id, "contexts": ctx}).encode())
+
+    if size(contexts) <= max_bytes:
+        return contexts, True
+    evictable = sorted(
+        ((k, v) for k, v in contexts.items()
+         if k.startswith("msg:") or k.startswith("thread:")),
+        key=lambda kv: kv[1],
+    )
+    out = dict(contexts)
+    for k, _ in evictable:
+        del out[k]
+        if size(out) <= max_bytes:
+            return out, True
+    return out, size(out) <= max_bytes
+
+
+def legacy_sanitize_blob(blob):
+    sanitized = {}
+    for k, v in blob.get("contexts", {}).items():
+        if (len(k.encode("utf-8")) <= 256
+                and isinstance(v, int) and 0 <= v <= 4294967295):
+            sanitized[k] = v
+    return {"v": 1, "client_id": blob.get("client_id", ""), "contexts": sanitized}