Files
PiCloud/crates/executor-core/src/sdk/pubsub.rs
MechaCat02 8b62b137c0 fix(executor): cap per-execution durable fan-out width
`trigger_depth` bounds how DEEP a trigger/invoke chain runs, but nothing bounded
how WIDE one execution could fan out. A single anonymous request running
`for i in 0..1_000_000 { invoke_async("w", #{}) }` costs a few Rhai ops plus one
cheap outbox INSERT per iteration, so within the op / wall-clock budget it could
write ~10^5 durable rows — each dispatched as its own execution — flooding the
outbox and dispatcher (a durable-amplification DoS).

Add a per-execution ceiling on DURABLE emissions (`invoke_async`,
`pubsub::publish_durable`, `queue::enqueue`, and the shared-topic/-queue
variants), env `PICLOUD_MAX_EMISSIONS_PER_EXECUTION` (default 1000). It's a
thread-local counter wrapped by a re-entrancy-aware `EmissionBudgetScope` around
every `execute_ast`: the OUTERMOST scope resets it, so a fresh dispatched
handler (a new pooled-thread task) gets a full budget while a synchronous
`invoke()` / interceptor re-entry nested in the same call stack SHARES it (fan-
out counted across the whole synchronous chain). The outermost Drop re-zeroes
the counter so a pooled thread never leaks a count into the next task.

Pinned by an `emit_budget` unit test (outermost resets, nested shares, ceiling
trips); the invoke/queue/pubsub/workflow journeys (small counts) stay green.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-13 22:27:32 +02:00

272 lines
9.7 KiB
Rust

//! `pubsub::` Rhai bridge — durable publish (v1.1.5).
//!
//! ```rhai
//! pubsub::publish_durable("user.created", #{ user_id: "abc" });
//! pubsub::publish_durable("metric", 42);
//! ```
//!
//! No handle pattern (topics ARE the grouping unit, so there's no
//! `::collection(...)`). The message is any JSON-serializable Rhai value
//! — Maps, Arrays, strings, numbers, bools, unit, and **Blobs (which
//! encode as base64 strings** so trigger handlers see them as base64 on
//! the wire). Nested blobs are encoded at any depth.
//!
//! `app_id` is derived from `cx.app_id` in the service — it never
//! appears in the script-side signature, preserving cross-app
//! isolation.
use std::sync::Arc;
use base64::engine::general_purpose::STANDARD;
use base64::Engine as _;
use picloud_shared::{SdkCallCx, Services};
use rhai::{Array, Dynamic, Engine as RhaiEngine, EvalAltResult, Map, Module};
use serde_json::Value as Json;
use tokio::runtime::Handle as TokioHandle;
use super::bridge::{block_on, MAX_JSON_MATERIALIZE_BYTES};
pub(super) fn register(engine: &mut RhaiEngine, services: &Services, cx: Arc<SdkCallCx>) {
let svc = services.pubsub.clone();
let mut module = Module::new();
{
let svc = svc.clone();
let cx = cx.clone();
module.set_native_fn(
"publish_durable",
move |topic: &str, message: Dynamic| -> Result<(), Box<EvalAltResult>> {
crate::sdk::emit_budget::charge_emission("pubsub::publish_durable")?;
let json = message_to_json(&message)?;
let svc = svc.clone();
let cx = cx.clone();
block_on("pubsub", async move {
svc.publish_durable(&cx, topic, json).await
})
},
);
}
// `pubsub::subscriber_token(topics)` — uses the configured default
// TTL.
{
let svc = svc.clone();
let cx = cx.clone();
module.set_native_fn(
"subscriber_token",
move |topics: Array| -> Result<String, Box<EvalAltResult>> {
mint_token(&svc, &cx, topics, None)
},
);
}
// `pubsub::subscriber_token(topics, ttl)` — `ttl` is an integer
// (seconds) or `()` for the default.
{
let svc = svc.clone();
let cx = cx.clone();
module.set_native_fn(
"subscriber_token",
move |topics: Array, ttl: Dynamic| -> Result<String, Box<EvalAltResult>> {
let ttl = ttl_from_dynamic(&ttl)?;
mint_token(&svc, &cx, topics, ttl)
},
);
}
// §11.6 D2: `pubsub::shared_topic("name")` → a handle whose `.publish(...)`
// publishes to the group's shared topic namespace (fans out to `shared`
// group pubsub triggers on the owning group). The owning group resolves from
// `cx.app_id` inside the service — never a script arg.
{
let group_svc = services.group_pubsub.clone();
let cx = cx.clone();
module.set_native_fn(
"shared_topic",
move |name: &str| -> Result<GroupTopicHandle, Box<EvalAltResult>> {
if name.is_empty() {
return Err("pubsub::shared_topic name must not be empty".into());
}
Ok(GroupTopicHandle {
namespace: name.to_string(),
service: group_svc.clone(),
cx: cx.clone(),
})
},
);
}
engine.register_static_module("pubsub", module.into());
engine.register_type_with_name::<GroupTopicHandle>("GroupTopicHandle");
register_shared_publish(engine);
}
/// §11.6 D2 handle returned by `pubsub::shared_topic("name")`. `.publish(sub,
/// msg)` publishes `name.sub` to the group shared topic; `.publish(msg)`
/// publishes to `name` directly.
#[derive(Clone)]
pub struct GroupTopicHandle {
namespace: String,
service: Arc<dyn picloud_shared::GroupPubsubService>,
cx: Arc<SdkCallCx>,
}
fn shared_publish(
h: &mut GroupTopicHandle,
subtopic: &str,
message: Dynamic,
) -> Result<(), Box<EvalAltResult>> {
crate::sdk::emit_budget::charge_emission("pubsub::shared_topic")?;
let json = message_to_json(&message)?;
let service = h.service.clone();
let cx = h.cx.clone();
let namespace = h.namespace.clone();
let subtopic = subtopic.to_string();
block_on("pubsub", async move {
service.publish(&cx, &namespace, &subtopic, json).await
})
// The fan-out count isn't surfaced to scripts (fire-and-forget, like the
// per-app publish).
.map(|_n: u32| ())
}
fn register_shared_publish(engine: &mut RhaiEngine) {
engine.register_fn(
"publish",
|h: &mut GroupTopicHandle, subtopic: &str, message: Dynamic| {
shared_publish(h, subtopic, message)
},
);
// `.publish(msg)` with no subtopic → publish to the namespace directly.
engine.register_fn("publish", |h: &mut GroupTopicHandle, message: Dynamic| {
shared_publish(h, "", message)
});
}
/// Interpret the optional `ttl` argument: `()` → use the default,
/// integer → that many seconds, anything else → throw.
fn ttl_from_dynamic(ttl: &Dynamic) -> Result<Option<i64>, Box<EvalAltResult>> {
if ttl.is_unit() {
return Ok(None);
}
ttl.as_int().map(Some).map_err(|_| -> Box<EvalAltResult> {
EvalAltResult::ErrorRuntime(
"pubsub::subscriber_token: ttl must be an integer (seconds) or ()".into(),
rhai::Position::NONE,
)
.into()
})
}
fn mint_token(
svc: &Arc<dyn picloud_shared::PubsubService>,
cx: &Arc<SdkCallCx>,
topics: Array,
ttl: Option<i64>,
) -> Result<String, Box<EvalAltResult>> {
// Every element must be a string; surface a clear error otherwise.
let mut names = Vec::with_capacity(topics.len());
for t in topics {
if !t.is_string() {
return Err(EvalAltResult::ErrorRuntime(
"pubsub::subscriber_token: topics must be an array of strings".into(),
rhai::Position::NONE,
)
.into());
}
names.push(t.into_string().unwrap_or_default());
}
let svc = svc.clone();
let cx = cx.clone();
let handle = TokioHandle::try_current().map_err(|e| -> Box<EvalAltResult> {
EvalAltResult::ErrorRuntime(
format!("pubsub: no tokio runtime available: {e}").into(),
rhai::Position::NONE,
)
.into()
})?;
// SubscriberToken errors already carry the full
// "pubsub::subscriber_token: …" wording, so surface them verbatim.
handle
.block_on(async move { svc.mint_subscriber_token(&cx, names, ttl).await })
.map_err(|err| -> Box<EvalAltResult> {
EvalAltResult::ErrorRuntime(format!("{err}").into(), rhai::Position::NONE).into()
})
}
/// Convert a Rhai `Dynamic` message into JSON, base64-encoding any
/// `Blob` (at any nesting depth). Mirrors `bridge::dynamic_to_json` but
/// adds the blob arm the pub/sub wire contract requires. Bounded by
/// [`MAX_JSON_MATERIALIZE_BYTES`] so a cheaply-aliased huge message can't OOM
/// the node on materialization (the per-message wire cap is enforced later, on
/// the already-materialized value).
fn message_to_json(value: &Dynamic) -> Result<Json, Box<EvalAltResult>> {
let mut remaining = MAX_JSON_MATERIALIZE_BYTES;
message_to_json_bounded(value, &mut remaining)
}
fn msg_charge(remaining: &mut usize, n: usize) -> Result<(), Box<EvalAltResult>> {
match remaining.checked_sub(n) {
Some(left) => {
*remaining = left;
Ok(())
}
None => Err(EvalAltResult::ErrorRuntime(
format!("pubsub: message too large to serialize (exceeds the {MAX_JSON_MATERIALIZE_BYTES}-byte limit)").into(),
rhai::Position::NONE,
)
.into()),
}
}
fn message_to_json_bounded(
value: &Dynamic,
remaining: &mut usize,
) -> Result<Json, Box<EvalAltResult>> {
// Blob must be checked before the generic array path (a Blob is a
// `Vec<u8>`, distinct from a Rhai `Array`).
if value.is_blob() {
let blob = value.clone().into_blob().unwrap_or_default();
let encoded = STANDARD.encode(&blob);
msg_charge(remaining, encoded.len() + 2)?;
return Ok(Json::String(encoded));
}
if value.is_unit() {
msg_charge(remaining, 4)?;
return Ok(Json::Null);
}
if let Ok(b) = value.as_bool() {
msg_charge(remaining, 5)?;
return Ok(Json::Bool(b));
}
if let Ok(i) = value.as_int() {
msg_charge(remaining, 8)?;
return Ok(Json::Number(i.into()));
}
if let Ok(f) = value.as_float() {
msg_charge(remaining, 8)?;
return Ok(serde_json::Number::from_f64(f).map_or(Json::Null, Json::Number));
}
if value.is_string() {
let s = value.clone().into_string().unwrap_or_default();
msg_charge(remaining, s.len() + 2)?;
return Ok(Json::String(s));
}
if let Some(arr) = value.clone().try_cast::<Array>() {
msg_charge(remaining, 2)?;
let mut out = Vec::with_capacity(arr.len().min(1024));
for v in &arr {
msg_charge(remaining, 1)?;
out.push(message_to_json_bounded(v, remaining)?);
}
return Ok(Json::Array(out));
}
if let Some(map) = value.clone().try_cast::<Map>() {
msg_charge(remaining, 2)?;
let mut out = serde_json::Map::new();
for (k, v) in map {
msg_charge(remaining, k.len() + 4)?;
out.insert(k.to_string(), message_to_json_bounded(&v, remaining)?);
}
return Ok(Json::Object(out));
}
let s = value.to_string();
msg_charge(remaining, s.len() + 2)?;
Ok(Json::String(s))
}