Compare commits

...

24 Commits

Author SHA1 Message Date
Lee Smet
38709e06f3 Add script to test actor/context/job/flow create and flow dag
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-29 15:43:32 +02:00
Lee Smet
08de312cd9 Fix HSET response decoding
The command internally uses (the deprecated) HMSET which just returns OK
on success instead of the amount of fields written

Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-29 11:30:41 +02:00
Lee Smet
4d1cd3d910 Format codebase
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-29 11:22:42 +02:00
Lee Smet
c1c1ae3bd1 Bump thiserror to latest version
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-29 11:22:12 +02:00
Lee Smet
ec339c5cbe Add some internal logging
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-29 11:10:04 +02:00
Lee Smet
2aa6277385 Actors are global
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-29 10:29:32 +02:00
Lee Smet
9c47eaaf93 Embedd rpc spec in rpc api
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-29 09:59:42 +02:00
Lee Smet
fce0ccb2d8 Fetch job results if a job is finished
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-28 17:09:04 +02:00
Lee Smet
e5a6228448 Periodically check the job status on the supervisor
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-28 16:42:48 +02:00
Lee Smet
052539409b Separate mycelium client more from supervisor client
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-28 15:24:03 +02:00
Lee Smet
1551b4707b Periodically verify the status of messages sent over mycelium
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-28 14:53:08 +02:00
Lee Smet
4b597cc445 Add calling of supervisor over mycelium
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-28 13:50:59 +02:00
Lee Smet
cf06c7fa36 Remove leftover logic
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-27 16:01:45 +02:00
Lee Smet
6f7fded175 Convert jobs to messages
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-27 15:33:43 +02:00
Lee Smet
fde456fd5e Add new supervisor client over mycelium
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-27 14:17:58 +02:00
Lee Smet
a8227eb808 Revert "Add supervisor API"
This reverts commit bc30c9cc89.
2025-08-27 12:52:54 +02:00
Lee Smet
bc30c9cc89 Add supervisor API
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-22 23:19:05 +02:00
Lee Smet
7ce19f8b6d Add validation for service methods
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-22 14:08:41 +02:00
Lee Smet
bc6cb16732 General code improvements
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-22 12:48:36 +02:00
Lee Smet
74995fa6fe Add job status update in service layer
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-22 12:45:50 +02:00
Lee Smet
f30706a25a Add service layer to abstract business logic
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-22 12:28:36 +02:00
Lee Smet
208d18c280 Allow updating job status in DB
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-22 11:34:29 +02:00
Lee Smet
e45e5939e9 Improve doc comment
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-22 11:02:45 +02:00
Lee Smet
e57c76fb36 Allow updating DAG
Signed-off-by: Lee Smet <lee.smet@hotmail.com>
2025-08-22 10:59:46 +02:00
24 changed files with 4645 additions and 230 deletions

893
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -16,3 +16,10 @@ redis = { version = "0.32.5", features = [
] }
jsonrpsee = { version = "0.26.0", features = ["server", "macros"] }
async-trait = "0.1.83"
# HTTP client to call Mycelium JSON-RPC
reqwest = { version = "0.12.7", features = ["json", "rustls-tls"] }
# Base64 encoding for message payloads
base64 = "0.22.1"
# Error derive for clean error types
thiserror = "2.0.16"
tracing-subscriber = { version = "0.3.18", features = ["env-filter", "fmt"] }

361
scripts/jsonrpc_demo.py Normal file
View File

@@ -0,0 +1,361 @@
#!/usr/bin/env python3
"""
Demo script for HeroCoordinator JSON-RPC API.
- Creates an actor
- Verifies by loading the actor
- Creates a context with the actor as admin/reader/executor
- Creates three jobs with dependencies
- Creates a flow referencing those jobs
- Fetches and prints the flow DAG
Usage:
COORDINATOR_URL=http://127.0.0.1:9652 python3 scripts/jsonrpc_demo.py
Defaults to http://127.0.0.1:9652 if COORDINATOR_URL is not set.
"""
import os
import json
import sys
from urllib import request, error
from typing import Any, Dict, List, Tuple
JSONRPC_VERSION = "2.0"
class JsonRpcClient:
def __init__(self, url: str):
self.url = url.rstrip("/")
self._id = 0
def call(self, method: str, params: Dict[str, Any]) -> Any:
self._id += 1
payload = {
"jsonrpc": JSONRPC_VERSION,
"id": self._id,
"method": method,
"params": params,
}
data = json.dumps(payload).encode("utf-8")
req = request.Request(self.url, data=data, headers={"Content-Type": "application/json"})
try:
with request.urlopen(req) as resp:
body = resp.read()
except error.HTTPError as e:
try:
details = e.read().decode("utf-8", "ignore")
except Exception:
details = ""
raise RuntimeError(f"HTTP error {e.code}: {details}") from e
except error.URLError as e:
raise RuntimeError(f"URL error: {e.reason}") from e
try:
obj = json.loads(body.decode("utf-8"))
except Exception as e:
raise RuntimeError(f"Invalid JSON response: {body!r}") from e
# JSON-RPC single response expected
if isinstance(obj, list):
raise RuntimeError("Batch responses are not supported in this demo")
if obj.get("error"):
raise RuntimeError(f"RPC error: {json.dumps(obj['error'])}")
return obj.get("result")
def print_header(title: str):
print("\n" + "=" * 80)
print(title)
print("=" * 80)
def pretty_print(obj: Any):
print(json.dumps(obj, indent=2, sort_keys=True))
def summarize_dag(dag: Dict[str, Any]):
print_header("Flow DAG Summary")
flow_id = dag.get("flow_id")
caller_id = dag.get("caller_id")
context_id = dag.get("context_id")
print(f"flow_id={flow_id} caller_id={caller_id} context_id={context_id}")
edges: List[Tuple[int, int]] = dag.get("edges", [])
roots: List[int] = dag.get("roots", [])
leaves: List[int] = dag.get("leaves", [])
levels: List[List[int]] = dag.get("levels", [])
nodes: Dict[str, Any] = dag.get("nodes", {})
print("Edges:")
for a, b in edges:
print(f" {a} -> {b}")
print(f"Roots: {roots}")
print(f"Leaves: {leaves}")
print("Levels:")
for i, lvl in enumerate(levels):
print(f" L{i}: {lvl}")
# Show nodes and their dependencies (from JobSummary)
print("Nodes:")
for k, v in nodes.items():
depends = v.get("depends", [])
prerequisites = v.get("prerequisites", [])
stype = v.get("script_type")
print(f" Job {k}: depends={depends} prerequisites={prerequisites} script_type={stype}")
def assert_edges(edges: List[Tuple[int, int]], required: List[Tuple[int, int]]):
edge_set = {(int(a), int(b)) for a, b in edges}
missing = [e for e in required if e not in edge_set]
if missing:
raise AssertionError(f"Missing expected edges in DAG: {missing}; got={sorted(edge_set)}")
def main():
url = os.getenv("COORDINATOR_URL", "http://127.0.0.1:9652")
client = JsonRpcClient(url)
# Deterministic demo IDs; change if collisions happen
actor_id = 1001
context_id = 1 # Redis DB indices are 0-15; keep <= 15
job_a = 3001
job_b = 3002
job_c = 3003
job_d = 3004
job_e = 3005
job_f = 3006
job_g = 3007
job_h = 3008
job_i = 3009
flow_id = 4001
print_header("actor.create")
actor = client.call("actor.create", {
"actor": {
"id": actor_id,
"pubkey": "demo-pubkey",
"address": ["127.0.0.1"]
}
})
pretty_print(actor)
print_header("actor.load")
actor_loaded = client.call("actor.load", {"id": actor_id})
pretty_print(actor_loaded)
print_header("context.create")
context = client.call("context.create", {
"context": {
"id": context_id,
"admins": [actor_id],
"readers": [actor_id],
"executors": [actor_id]
}
})
pretty_print(context)
print_header("job.create - A (root)")
jobA = client.call("job.create", {
"context_id": context_id,
"job": {
"id": job_a,
"caller_id": actor_id,
"context_id": context_id,
"script": "print('A')",
"script_type": "Python",
"timeout": 30,
"retries": 0,
"env_vars": {},
"prerequisites": [],
"depends": []
}
})
pretty_print(jobA)
print_header("job.create - B (root)")
jobB = client.call("job.create", {
"context_id": context_id,
"job": {
"id": job_b,
"caller_id": actor_id,
"context_id": context_id,
"script": "print('B')",
"script_type": "Python",
"timeout": 30,
"retries": 0,
"env_vars": {},
"prerequisites": [],
"depends": []
}
})
pretty_print(jobB)
print_header("job.create - C (depends on A and B)")
jobC = client.call("job.create", {
"context_id": context_id,
"job": {
"id": job_c,
"caller_id": actor_id,
"context_id": context_id,
"script": "print('C')",
"script_type": "Python",
"timeout": 30,
"retries": 0,
"env_vars": {},
"prerequisites": [],
"depends": [job_a, job_b]
}
})
pretty_print(jobC)
print_header("job.create - D (depends on A)")
jobD = client.call("job.create", {
"context_id": context_id,
"job": {
"id": job_d,
"caller_id": actor_id,
"context_id": context_id,
"script": "print('D')",
"script_type": "Python",
"timeout": 30,
"retries": 0,
"env_vars": {},
"prerequisites": [],
"depends": [job_a]
}
})
pretty_print(jobD)
print_header("job.create - E (depends on B)")
jobE = client.call("job.create", {
"context_id": context_id,
"job": {
"id": job_e,
"caller_id": actor_id,
"context_id": context_id,
"script": "print('E')",
"script_type": "Python",
"timeout": 30,
"retries": 0,
"env_vars": {},
"prerequisites": [],
"depends": [job_b]
}
})
pretty_print(jobE)
print_header("job.create - F (depends on C and D)")
jobF = client.call("job.create", {
"context_id": context_id,
"job": {
"id": job_f,
"caller_id": actor_id,
"context_id": context_id,
"script": "print('F')",
"script_type": "Python",
"timeout": 30,
"retries": 0,
"env_vars": {},
"prerequisites": [],
"depends": [job_c, job_d]
}
})
pretty_print(jobF)
print_header("job.create - G (depends on C and E)")
jobG = client.call("job.create", {
"context_id": context_id,
"job": {
"id": job_g,
"caller_id": actor_id,
"context_id": context_id,
"script": "print('G')",
"script_type": "Python",
"timeout": 30,
"retries": 0,
"env_vars": {},
"prerequisites": [],
"depends": [job_c, job_e]
}
})
pretty_print(jobG)
print_header("job.create - H (leaf; depends on F and G)")
jobH = client.call("job.create", {
"context_id": context_id,
"job": {
"id": job_h,
"caller_id": actor_id,
"context_id": context_id,
"script": "print('H')",
"script_type": "Python",
"timeout": 30,
"retries": 0,
"env_vars": {},
"prerequisites": [],
"depends": [job_f, job_g]
}
})
pretty_print(jobH)
print_header("job.create - I (leaf; depends on F and G)")
jobI = client.call("job.create", {
"context_id": context_id,
"job": {
"id": job_i,
"caller_id": actor_id,
"context_id": context_id,
"script": "print('I')",
"script_type": "Python",
"timeout": 30,
"retries": 0,
"env_vars": {},
"prerequisites": [],
"depends": [job_f, job_g]
}
})
pretty_print(jobI)
print_header("flow.create")
flow = client.call("flow.create", {
"context_id": context_id,
"flow": {
"id": flow_id,
"caller_id": actor_id,
"context_id": context_id,
"jobs": [job_a, job_b, job_c, job_d, job_e, job_f, job_g, job_h, job_i],
"env_vars": {}
}
})
pretty_print(flow)
print_header("flow.dag")
dag = client.call("flow.dag", {"context_id": context_id, "id": flow_id})
summarize_dag(dag)
# Validate roots and leaves
got_roots = list(map(int, dag.get("roots", [])))
if got_roots != sorted([job_a, job_b]):
print("WARNING: Unexpected roots:", got_roots, file=sys.stderr)
got_leaves = {int(x) for x in dag.get("leaves", [])}
expected_leaves = {job_h, job_i}
if got_leaves != expected_leaves:
print("WARNING: Unexpected leaves:", got_leaves, "expected:", expected_leaves, file=sys.stderr)
# Check edges reflect the expanded DAG
expected_edges = [
(job_a, job_c), (job_b, job_c),
(job_a, job_d), (job_b, job_e),
(job_c, job_f), (job_d, job_f),
(job_c, job_g), (job_e, job_g),
(job_f, job_h), (job_g, job_h),
(job_f, job_i), (job_g, job_i),
]
try:
assert_edges(dag.get("edges", []), expected_edges)
print("DAG edges contain expected dependencies:", expected_edges)
except AssertionError as e:
print("WARNING:", e, file=sys.stderr)
if __name__ == "__main__":
try:
main()
except Exception as e:
print_header("Error")
print(str(e))
sys.exit(1)

View File

@@ -20,7 +20,7 @@
"methods": [
{
"name": "actor.create",
"summary": "Create/Upsert Actor in a context",
"summary": "Create/Upsert Actor",
"params": [
{
"name": "params",
@@ -49,7 +49,7 @@
},
{
"name": "actor.load",
"summary": "Load an Actor by id from a context",
"summary": "Load an Actor by id",
"params": [
{
"name": "params",
@@ -438,6 +438,16 @@
"Processed"
]
},
"TransportStatus": {
"type": "string",
"enum": [
"Queued",
"Sent",
"Delivered",
"Read",
"Failed"
]
},
"MessageType": {
"type": "string",
"enum": [
@@ -779,6 +789,12 @@
},
"status": {
"$ref": "#/components/schemas/MessageStatus"
},
"transport_id": {
"type": "string"
},
"transport_status": {
"$ref": "#/components/schemas/TransportStatus"
}
}
},
@@ -1165,14 +1181,9 @@
"ActorCreateParams": {
"type": "object",
"required": [
"context_id",
"actor"
],
"properties": {
"context_id": {
"type": "integer",
"format": "uint32"
},
"actor": {
"$ref": "#/components/schemas/ActorCreate"
}
@@ -1181,14 +1192,9 @@
"ActorLoadParams": {
"type": "object",
"required": [
"context_id",
"id"
],
"properties": {
"context_id": {
"type": "integer",
"format": "uint32"
},
"id": {
"type": "integer",
"format": "uint32"

View File

@@ -10,7 +10,7 @@
| **Runner** | Public key, Mycelium address, topic name, type (`v\|python\|osis\|rust`), local flag, timestamps | `runner:<id>` (hash) | The *worker* that actually executes **RunnerJob** scripts. It subscribes to a Mycelium topic (normally `runner<id>`). If `local == true` the runner also consumes jobs directly from a Redis queue that is named after the scripttype suffix (`v`, `python`, …). |
| **RunnerJob**| Script source, type (`osis\|sal\|v\|python`), envvars, prerequisites, dependencies, status, timestamps, result map | `job:<caller_id>:<id>` (hash) | A single executable unit. It lives inside a **Context**, belongs to a **Runner**, and is queued according to its `script_type` (e.g. `queue:python`). Its status moves through the lifecycle `dispatched → waiting_for_prerequisites → started → finished|error`. |
> **Key idea:** All objects are persisted as *hashes* in a **Redis** database that is dedicated to a *Context*. The system is completely **decentralised** each actor owns its own context and can spin up as many runners as needed. Communication between actors, runners and the rest of the system happens over **Mycelium**, a messagebus that uses Redis lists as queues.
> **Key idea:** All objects are persisted as *hashes*. Contextscoped objects (**Context**, **Flow**, **Message**, **Runner**, **RunnerJob**) live in a **Redis** database dedicated to that context. **Actors are global** and are stored in Redis DB 0 under `actor:<id>`. The system is completely **decentralised** each actor owns its own context and can spin up as many runners as needed. Communication between actors, runners and the rest of the system happens over **Mycelium**, a messagebus that uses Redis lists as queues.
---

7
src/clients/mod.rs Normal file
View File

@@ -0,0 +1,7 @@
pub mod mycelium_client;
pub mod supervisor_client;
pub mod types;
pub use mycelium_client::{MyceliumClient, MyceliumClientError};
pub use supervisor_client::{SupervisorClient, SupervisorClientError};
pub use types::Destination;

View File

@@ -0,0 +1,238 @@
use std::sync::Arc;
use std::sync::atomic::{AtomicU64, Ordering};
use reqwest::Client as HttpClient;
use serde_json::{Value, json};
use thiserror::Error;
use crate::clients::Destination;
use crate::models::TransportStatus;
/// Lightweight client for Mycelium JSON-RPC (send + query status)
#[derive(Clone)]
pub struct MyceliumClient {
base_url: String, // e.g. http://127.0.0.1:8990
http: HttpClient,
id_counter: Arc<AtomicU64>,
}
#[derive(Debug, Error)]
pub enum MyceliumClientError {
#[error("HTTP error: {0}")]
Http(#[from] reqwest::Error),
#[error("JSON error: {0}")]
Json(#[from] serde_json::Error),
#[error("Transport timed out waiting for a reply (408)")]
TransportTimeout,
#[error("JSON-RPC error: {0}")]
RpcError(String),
#[error("Invalid response: {0}")]
InvalidResponse(String),
}
impl MyceliumClient {
pub fn new(base_url: impl Into<String>) -> Result<Self, MyceliumClientError> {
let url = base_url.into();
let http = HttpClient::builder().build()?;
Ok(Self {
base_url: url,
http,
id_counter: Arc::new(AtomicU64::new(1)),
})
}
fn next_id(&self) -> u64 {
self.id_counter.fetch_add(1, Ordering::Relaxed)
}
async fn jsonrpc(&self, method: &str, params: Value) -> Result<Value, MyceliumClientError> {
let req = json!({
"jsonrpc": "2.0",
"id": self.next_id(),
"method": method,
"params": [ params ]
});
let resp = self.http.post(&self.base_url).json(&req).send().await?;
let status = resp.status();
let body: Value = resp.json().await?;
if let Some(err) = body.get("error") {
let code = err.get("code").and_then(|v| v.as_i64()).unwrap_or(0);
let msg = err
.get("message")
.and_then(|v| v.as_str())
.unwrap_or("unknown error");
if code == 408 {
return Err(MyceliumClientError::TransportTimeout);
}
return Err(MyceliumClientError::RpcError(format!(
"code={code} msg={msg}"
)));
}
if !status.is_success() {
return Err(MyceliumClientError::RpcError(format!(
"HTTP {status}, body {body}"
)));
}
Ok(body)
}
/// Call messageStatus with an outbound message id (hex string)
pub async fn message_status(
&self,
id_hex: &str,
) -> Result<TransportStatus, MyceliumClientError> {
let params = json!({ "id": id_hex });
let body = self.jsonrpc("messageStatus", params).await?;
let result = body.get("result").ok_or_else(|| {
MyceliumClientError::InvalidResponse(format!("missing result in response: {body}"))
})?;
// Accept both { status: "..."} and bare "..."
let status_str = if let Some(s) = result.get("status").and_then(|v| v.as_str()) {
s.to_string()
} else if let Some(s) = result.as_str() {
s.to_string()
} else {
return Err(MyceliumClientError::InvalidResponse(format!(
"unexpected result shape: {result}"
)));
};
Self::map_status(&status_str).ok_or_else(|| {
MyceliumClientError::InvalidResponse(format!("unknown status: {status_str}"))
})
}
fn map_status(s: &str) -> Option<TransportStatus> {
match s {
"queued" => Some(TransportStatus::Queued),
"sent" => Some(TransportStatus::Sent),
"delivered" => Some(TransportStatus::Delivered),
"read" => Some(TransportStatus::Read),
"failed" => Some(TransportStatus::Failed),
_ => None,
}
}
/// Build params object for pushMessage without performing any network call.
/// Exposed for serializer-only tests and reuse.
pub(crate) fn build_push_params(
dst: &Destination,
topic: &str,
payload_b64: &str,
reply_timeout: Option<u64>,
) -> Value {
let dst_v = match dst {
Destination::Ip(ip) => json!({ "ip": ip.to_string() }),
Destination::Pk(pk) => json!({ "pk": pk }),
};
let message = json!({
"dst": dst_v,
"topic": topic,
"payload": payload_b64,
});
let mut params = json!({ "message": message });
if let Some(rt) = reply_timeout {
params["reply_timeout"] = json!(rt);
}
params
}
/// pushMessage: send a message with dst/topic/payload. Optional reply_timeout for sync replies.
pub async fn push_message(
&self,
dst: &Destination,
topic: &str,
payload_b64: &str,
reply_timeout: Option<u64>,
) -> Result<Value, MyceliumClientError> {
let params = Self::build_push_params(dst, topic, payload_b64, reply_timeout);
let body = self.jsonrpc("pushMessage", params).await?;
let result = body.get("result").ok_or_else(|| {
MyceliumClientError::InvalidResponse(format!("missing result in response: {body}"))
})?;
Ok(result.clone())
}
/// Helper to extract outbound message id from pushMessage result (InboundMessage or PushMessageResponseId)
pub fn extract_message_id_from_result(result: &Value) -> Option<String> {
result
.get("id")
.and_then(|v| v.as_str())
.map(|s| s.to_string())
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::clients::Destination;
#[test]
fn build_push_params_shapes_ip_pk_and_timeout() {
// IP destination
let p1 = MyceliumClient::build_push_params(
&Destination::Ip("2001:db8::1".parse().unwrap()),
"supervisor.rpc",
"Zm9vYmFy", // "foobar"
Some(10),
);
let msg1 = p1.get("message").unwrap();
assert_eq!(
msg1.get("topic").unwrap().as_str().unwrap(),
"supervisor.rpc"
);
assert_eq!(msg1.get("payload").unwrap().as_str().unwrap(), "Zm9vYmFy");
assert_eq!(
msg1.get("dst")
.unwrap()
.get("ip")
.unwrap()
.as_str()
.unwrap(),
"2001:db8::1"
);
assert_eq!(p1.get("reply_timeout").unwrap().as_u64().unwrap(), 10);
// PK destination without timeout
let p2 = MyceliumClient::build_push_params(
&Destination::Pk(
"bb39b4a3a4efd70f3e05e37887677e02efbda14681d0acd3882bc0f754792c32".into(),
),
"supervisor.rpc",
"YmF6", // "baz"
None,
);
let msg2 = p2.get("message").unwrap();
assert_eq!(
msg2.get("dst")
.unwrap()
.get("pk")
.unwrap()
.as_str()
.unwrap(),
"bb39b4a3a4efd70f3e05e37887677e02efbda14681d0acd3882bc0f754792c32"
);
assert!(p2.get("reply_timeout").is_none());
}
#[test]
fn extract_message_id_variants() {
// PushMessageResponseId
let r1 = json!({"id":"0123456789abcdef"});
assert_eq!(
MyceliumClient::extract_message_id_from_result(&r1).unwrap(),
"0123456789abcdef"
);
// InboundMessage-like
let r2 = json!({
"id":"fedcba9876543210",
"srcIp":"449:abcd:0123:defa::1",
"payload":"hpV+"
});
assert_eq!(
MyceliumClient::extract_message_id_from_result(&r2).unwrap(),
"fedcba9876543210"
);
}
}

View File

@@ -0,0 +1,497 @@
use std::sync::Arc;
use std::sync::atomic::{AtomicU64, Ordering};
use base64::Engine;
use base64::engine::general_purpose::STANDARD as BASE64_STANDARD;
use serde_json::{Value, json};
use thiserror::Error;
use crate::clients::{Destination, MyceliumClient, MyceliumClientError};
#[derive(Clone)]
pub struct SupervisorClient {
mycelium: Arc<MyceliumClient>, // Delegated Mycelium transport
destination: Destination, // ip or pk
topic: String, // e.g. "supervisor.rpc"
secret: Option<String>, // optional, required by several supervisor methods
id_counter: Arc<AtomicU64>, // JSON-RPC id generator (for inner supervisor requests)
}
#[derive(Debug, Error)]
pub enum SupervisorClientError {
#[error("HTTP error: {0}")]
Http(#[from] reqwest::Error),
#[error("JSON error: {0}")]
Json(#[from] serde_json::Error),
#[error("Transport timed out waiting for a reply (408)")]
TransportTimeout,
#[error("JSON-RPC error: {0}")]
RpcError(String),
#[error("Invalid response: {0}")]
InvalidResponse(String),
#[error("Missing secret for method requiring authentication")]
MissingSecret,
}
impl From<MyceliumClientError> for SupervisorClientError {
fn from(e: MyceliumClientError) -> Self {
match e {
MyceliumClientError::TransportTimeout => SupervisorClientError::TransportTimeout,
MyceliumClientError::RpcError(m) => SupervisorClientError::RpcError(m),
MyceliumClientError::InvalidResponse(m) => SupervisorClientError::InvalidResponse(m),
MyceliumClientError::Http(err) => SupervisorClientError::Http(err),
MyceliumClientError::Json(err) => SupervisorClientError::Json(err),
}
}
}
impl SupervisorClient {
/// Preferred constructor: provide a shared Mycelium client.
pub fn new_with_client(
mycelium: Arc<MyceliumClient>,
destination: Destination,
topic: impl Into<String>,
secret: Option<String>,
) -> Self {
Self {
mycelium,
destination,
topic: topic.into(),
secret,
id_counter: Arc::new(AtomicU64::new(1)),
}
}
/// Backward-compatible constructor that builds a Mycelium client from base_url.
/// base_url defaults to Mycelium spec "http://127.0.0.1:8990" if empty.
pub fn new(
base_url: impl Into<String>,
destination: Destination,
topic: impl Into<String>,
secret: Option<String>,
) -> Result<Self, SupervisorClientError> {
let mut url = base_url.into();
if url.is_empty() {
url = "http://127.0.0.1:8990".to_string();
}
let mycelium = Arc::new(MyceliumClient::new(url)?);
Ok(Self::new_with_client(mycelium, destination, topic, secret))
}
fn next_id(&self) -> u64 {
self.id_counter.fetch_add(1, Ordering::Relaxed)
}
/// Internal helper used by tests to inspect dst JSON shape.
fn build_dst(&self) -> Value {
match &self.destination {
Destination::Ip(ip) => json!({ "ip": ip.to_string() }),
Destination::Pk(pk) => json!({ "pk": pk }),
}
}
fn build_supervisor_payload(&self, method: &str, params: Value) -> Value {
json!({
"jsonrpc": "2.0",
"id": self.next_id(),
"method": method,
"params": params,
})
}
fn encode_payload(payload: &Value) -> Result<String, SupervisorClientError> {
let s = serde_json::to_string(payload)?;
Ok(BASE64_STANDARD.encode(s.as_bytes()))
}
fn extract_message_id_from_result(result: &Value) -> Option<String> {
// Two possibilities per Mycelium spec oneOf:
// - PushMessageResponseId: { "id": "0123456789abcdef" }
// - InboundMessage: object containing "id" plus srcIp, ...; we still return id.
result
.get("id")
.and_then(|v| v.as_str())
.map(|s| s.to_string())
}
/// Generic call: build supervisor JSON-RPC message, send via Mycelium pushMessage, return outbound message id (hex).
pub async fn call(&self, method: &str, params: Value) -> Result<String, SupervisorClientError> {
let inner = self.build_supervisor_payload(method, params);
let payload_b64 = Self::encode_payload(&inner)?;
let result = self
.mycelium
.push_message(&self.destination, &self.topic, &payload_b64, None)
.await?;
if let Some(id) = MyceliumClient::extract_message_id_from_result(&result) {
return Ok(id);
}
// Some servers might return the oneOf wrapped, handle len==1 array defensively (not in spec but resilient)
if let Some(arr) = result.as_array()
&& arr.len() == 1
&& let Some(id) = MyceliumClient::extract_message_id_from_result(&arr[0])
{
return Ok(id);
}
Err(SupervisorClientError::InvalidResponse(format!(
"result did not contain message id: {result}"
)))
}
/// Synchronous variant: wait for a JSON-RPC reply via Mycelium reply_timeout, and return the inner JSON-RPC "result".
/// If the supervisor returns an error object, map to RpcError.
pub async fn call_sync(
&self,
method: &str,
params: Value,
reply_timeout_secs: u64,
) -> Result<Value, SupervisorClientError> {
let inner = self.build_supervisor_payload(method, params);
let payload_b64 = Self::encode_payload(&inner)?;
let result = self
.mycelium
.push_message(
&self.destination,
&self.topic,
&payload_b64,
Some(reply_timeout_secs),
)
.await?;
// Expect an InboundMessage-like with a base64 payload containing the supervisor JSON-RPC response
let payload_field = if let Some(p) = result.get("payload").and_then(|v| v.as_str()) {
p.to_string()
} else if let Some(arr) = result.as_array() {
// Defensive: handle single-element array shape
if let Some(one) = arr.get(0) {
one.get("payload")
.and_then(|v| v.as_str())
.map(|s| s.to_string())
.ok_or_else(|| {
SupervisorClientError::InvalidResponse(format!(
"missing payload in result: {result}"
))
})?
} else {
return Err(SupervisorClientError::TransportTimeout);
}
} else {
// No payload => no reply received within timeout (Mycelium would have returned just an id)
return Err(SupervisorClientError::TransportTimeout);
};
let raw = BASE64_STANDARD
.decode(payload_field.as_bytes())
.map_err(|e| {
SupervisorClientError::InvalidResponse(format!("invalid base64 payload: {e}"))
})?;
let rpc_resp: Value = serde_json::from_slice(&raw)?;
if let Some(err) = rpc_resp.get("error") {
return Err(SupervisorClientError::RpcError(err.to_string()));
}
let res = rpc_resp.get("result").ok_or_else(|| {
SupervisorClientError::InvalidResponse(format!(
"missing result in supervisor reply: {rpc_resp}"
))
})?;
Ok(res.clone())
}
fn need_secret(&self) -> Result<&str, SupervisorClientError> {
self.secret
.as_deref()
.ok_or(SupervisorClientError::MissingSecret)
}
// -----------------------------
// Typed wrappers for Supervisor API
// Asynchronous-only: returns outbound message id
// -----------------------------
// Runners
pub async fn list_runners(&self) -> Result<String, SupervisorClientError> {
self.call("list_runners", json!([])).await
}
pub async fn register_runner(
&self,
name: impl Into<String>,
queue: impl Into<String>,
) -> Result<String, SupervisorClientError> {
let secret = self.need_secret()?;
let params = json!([{
"secret": secret,
"name": name.into(),
"queue": queue.into()
}]);
self.call("register_runner", params).await
}
pub async fn remove_runner(
&self,
actor_id: impl Into<String>,
) -> Result<String, SupervisorClientError> {
self.call("remove_runner", json!([actor_id.into()])).await
}
pub async fn start_runner(
&self,
actor_id: impl Into<String>,
) -> Result<String, SupervisorClientError> {
self.call("start_runner", json!([actor_id.into()])).await
}
pub async fn stop_runner(
&self,
actor_id: impl Into<String>,
force: bool,
) -> Result<String, SupervisorClientError> {
self.call("stop_runner", json!([actor_id.into(), force]))
.await
}
pub async fn get_runner_status(
&self,
actor_id: impl Into<String>,
) -> Result<String, SupervisorClientError> {
self.call("get_runner_status", json!([actor_id.into()]))
.await
}
pub async fn get_all_runner_status(&self) -> Result<String, SupervisorClientError> {
self.call("get_all_runner_status", json!([])).await
}
pub async fn start_all(&self) -> Result<String, SupervisorClientError> {
self.call("start_all", json!([])).await
}
pub async fn stop_all(&self, force: bool) -> Result<String, SupervisorClientError> {
self.call("stop_all", json!([force])).await
}
pub async fn get_all_status(&self) -> Result<String, SupervisorClientError> {
self.call("get_all_status", json!([])).await
}
// Jobs
pub async fn jobs_create(&self, job: Value) -> Result<String, SupervisorClientError> {
let secret = self.need_secret()?;
let params = json!([{
"secret": secret,
"job": job
}]);
self.call("jobs.create", params).await
}
pub async fn jobs_list(&self) -> Result<String, SupervisorClientError> {
self.call("jobs.list", json!([])).await
}
pub async fn job_run(&self, job: Value) -> Result<String, SupervisorClientError> {
let secret = self.need_secret()?;
let params = json!([{
"secret": secret,
"job": job
}]);
self.call("job.run", params).await
}
pub async fn job_start(
&self,
job_id: impl Into<String>,
) -> Result<String, SupervisorClientError> {
let secret = self.need_secret()?;
let params = json!([{
"secret": secret,
"job_id": job_id.into()
}]);
self.call("job.start", params).await
}
pub async fn job_status(
&self,
job_id: impl Into<String>,
) -> Result<String, SupervisorClientError> {
self.call("job.status", json!([job_id.into()])).await
}
/// Synchronous job.status: waits for the supervisor to reply and returns the status string.
/// The supervisor result may be an object with { status: "..." } or a bare string.
pub async fn job_status_sync(
&self,
job_id: impl Into<String>,
reply_timeout_secs: u64,
) -> Result<String, SupervisorClientError> {
let res = self
.call_sync("job.status", json!([job_id.into()]), reply_timeout_secs)
.await?;
let status = if let Some(s) = res.get("status").and_then(|v| v.as_str()) {
s.to_string()
} else if let Some(s) = res.as_str() {
s.to_string()
} else {
return Err(SupervisorClientError::InvalidResponse(format!(
"unexpected job.status result shape: {res}"
)));
};
Ok(status)
}
pub async fn job_result(
&self,
job_id: impl Into<String>,
) -> Result<String, SupervisorClientError> {
self.call("job.result", json!([job_id.into()])).await
}
/// Synchronous job.result: waits for the supervisor to reply and returns a map
/// containing exactly one of:
/// - {"success": "..."} on success
/// - {"error": "..."} on error reported by the runner
/// Some servers may return a bare string; we treat that as {"success": "<string>"}.
pub async fn job_result_sync(
&self,
job_id: impl Into<String>,
reply_timeout_secs: u64,
) -> Result<std::collections::HashMap<String, String>, SupervisorClientError> {
let res = self
.call_sync("job.result", json!([job_id.into()]), reply_timeout_secs)
.await?;
use std::collections::HashMap;
let mut out: HashMap<String, String> = HashMap::new();
if let Some(obj) = res.as_object() {
if let Some(s) = obj.get("success").and_then(|v| v.as_str()) {
out.insert("success".to_string(), s.to_string());
return Ok(out);
}
if let Some(s) = obj.get("error").and_then(|v| v.as_str()) {
out.insert("error".to_string(), s.to_string());
return Ok(out);
}
return Err(SupervisorClientError::InvalidResponse(format!(
"unexpected job.result result shape: {res}"
)));
} else if let Some(s) = res.as_str() {
out.insert("success".to_string(), s.to_string());
return Ok(out);
}
Err(SupervisorClientError::InvalidResponse(format!(
"unexpected job.result result shape: {res}"
)))
}
pub async fn job_stop(
&self,
job_id: impl Into<String>,
) -> Result<String, SupervisorClientError> {
let secret = self.need_secret()?;
let params = json!([{
"secret": secret,
"job_id": job_id.into()
}]);
self.call("job.stop", params).await
}
pub async fn job_delete(
&self,
job_id: impl Into<String>,
) -> Result<String, SupervisorClientError> {
let secret = self.need_secret()?;
let params = json!([{
"secret": secret,
"job_id": job_id.into()
}]);
self.call("job.delete", params).await
}
// Discovery
pub async fn rpc_discover(&self) -> Result<String, SupervisorClientError> {
self.call("rpc.discover", json!([])).await
}
}
// -----------------------------
// Tests (serialization-only)
// -----------------------------
#[cfg(test)]
mod tests {
use super::*;
use std::net::IpAddr;
fn mk_client() -> SupervisorClient {
// Uses the legacy constructor but will not issue real network calls in these tests.
SupervisorClient::new(
"http://127.0.0.1:8990",
Destination::Pk(
"bb39b4a3a4efd70f3e05e37887677e02efbda14681d0acd3882bc0f754792c32".to_string(),
),
"supervisor.rpc",
Some("secret".to_string()),
)
.unwrap()
}
#[test]
fn builds_dst_ip_and_pk() {
let c_ip = SupervisorClient::new(
"http://127.0.0.1:8990",
Destination::Ip("2001:db8::1".parse().unwrap()),
"supervisor.rpc",
None,
)
.unwrap();
let v_ip = c_ip.build_dst();
assert_eq!(v_ip.get("ip").unwrap().as_str().unwrap(), "2001:db8::1");
let c_pk = mk_client();
let v_pk = c_pk.build_dst();
assert_eq!(
v_pk.get("pk").unwrap().as_str().unwrap(),
"bb39b4a3a4efd70f3e05e37887677e02efbda14681d0acd3882bc0f754792c32"
);
}
#[test]
fn encodes_supervisor_payload_b64() {
let c = mk_client();
let payload = c.build_supervisor_payload("list_runners", json!([]));
let b64 = SupervisorClient::encode_payload(&payload).unwrap();
// decode and compare round-trip JSON
let raw = base64::engine::general_purpose::STANDARD
.decode(b64.as_bytes())
.unwrap();
let decoded: Value = serde_json::from_slice(&raw).unwrap();
assert_eq!(
decoded.get("method").unwrap().as_str().unwrap(),
"list_runners"
);
assert_eq!(decoded.get("jsonrpc").unwrap().as_str().unwrap(), "2.0");
}
#[test]
fn extract_message_id_works_for_both_variants() {
// PushMessageResponseId
let r1 = json!({"id":"0123456789abcdef"});
assert_eq!(
SupervisorClient::extract_message_id_from_result(&r1).unwrap(),
"0123456789abcdef"
);
// InboundMessage-like
let r2 = json!({
"id":"fedcba9876543210",
"srcIp":"449:abcd:0123:defa::1",
"payload":"hpV+"
});
assert_eq!(
SupervisorClient::extract_message_id_from_result(&r2).unwrap(),
"fedcba9876543210"
);
}
}

9
src/clients/types.rs Normal file
View File

@@ -0,0 +1,9 @@
use std::net::IpAddr;
/// Destination for Mycelium messages (shared by clients)
#[derive(Clone, Debug)]
pub enum Destination {
Ip(IpAddr),
/// 64-hex public key of the receiver node
Pk(String),
}

View File

@@ -14,6 +14,10 @@ pub enum DagError {
Storage(Box<dyn std::error::Error + Send + Sync>),
MissingDependency { job: u32, depends_on: u32 },
CycleDetected { remaining: Vec<u32> },
UnknownJob { job: u32 },
DependenciesIncomplete { job: u32, missing: Vec<u32> },
FlowFailed { failed_job: u32 },
JobNotStarted { job: u32 },
}
impl fmt::Display for DagError {
@@ -28,6 +32,20 @@ impl fmt::Display for DagError {
DagError::CycleDetected { remaining } => {
write!(f, "Cycle detected; unresolved nodes: {:?}", remaining)
}
DagError::UnknownJob { job } => write!(f, "Unknown job id: {}", job),
DagError::DependenciesIncomplete { job, missing } => write!(
f,
"Job {} cannot start; missing completed deps: {:?}",
job, missing
),
DagError::FlowFailed { failed_job } => {
write!(f, "Flow failed due to job {}", failed_job)
}
DagError::JobNotStarted { job } => write!(
f,
"Job {} cannot be completed because it is not marked as started",
job
),
}
}
}
@@ -59,6 +77,10 @@ pub struct FlowDag {
pub roots: Vec<u32>, // in_degree == 0
pub leaves: Vec<u32>, // out_degree == 0
pub levels: Vec<Vec<u32>>, // topological layers for parallel execution
// Runtime execution state
pub started: HashSet<u32>,
pub completed: HashSet<u32>,
pub failed_job: Option<u32>,
}
pub async fn build_flow_dag(
@@ -72,14 +94,14 @@ pub async fn build_flow_dag(
.await
.map_err(DagError::from)?;
let caller_id = flow.caller_id();
let flow_job_ids = flow.jobs().clone();
let flow_job_ids = flow.jobs();
// Build a set for faster membership tests
let job_id_set: HashSet<u32> = flow_job_ids.iter().copied().collect();
// Load all jobs
let mut jobs: HashMap<u32, Job> = HashMap::with_capacity(flow_job_ids.len());
for jid in &flow_job_ids {
for jid in flow_job_ids {
let job = redis
.load_job(context_id, caller_id, *jid)
.await
@@ -94,7 +116,7 @@ pub async fn build_flow_dag(
let mut rev_adj: HashMap<u32, Vec<u32>> = HashMap::with_capacity(jobs.len());
let mut in_degree: HashMap<u32, usize> = HashMap::with_capacity(jobs.len());
for &jid in &flow_job_ids {
for &jid in flow_job_ids {
adj.entry(jid).or_default();
rev_adj.entry(jid).or_default();
in_degree.entry(jid).or_insert(0);
@@ -200,8 +222,125 @@ pub async fn build_flow_dag(
roots,
leaves,
levels,
started: HashSet::new(),
completed: HashSet::new(),
failed_job: None,
};
Ok(dag)
}
impl FlowDag {
/// Return all jobs that are ready to be processed.
/// A job is ready if:
/// - it exists in the DAG
/// - it is not already started or completed
/// - it has no dependencies, or all dependencies are completed
///
/// If any job has failed, the entire flow is considered failed and an error is returned.
pub fn ready_jobs(&self) -> DagResult<Vec<u32>> {
if let Some(failed_job) = self.failed_job {
return Err(DagError::FlowFailed { failed_job });
}
let mut ready: Vec<u32> = Vec::new();
for (&jid, summary) in &self.nodes {
if self.completed.contains(&jid) || self.started.contains(&jid) {
continue;
}
let mut deps_ok = true;
for dep in &summary.depends {
if !self.completed.contains(dep) {
deps_ok = false;
break;
}
}
if deps_ok {
ready.push(jid);
}
}
ready.sort_unstable();
Ok(ready)
}
/// Mark a job as started.
/// Strict validation rules:
/// - Unknown jobs are rejected with UnknownJob
/// - If the flow has already failed, return FlowFailed
/// - If the job is already started or completed, this is a no-op (idempotent)
/// - If any dependency is not completed, return DependenciesIncomplete with the missing deps
pub fn mark_job_started(&mut self, job: u32) -> DagResult<()> {
if !self.nodes.contains_key(&job) {
return Err(DagError::UnknownJob { job });
}
if self.completed.contains(&job) || self.started.contains(&job) {
return Ok(());
}
if let Some(failed_job) = self.failed_job {
return Err(DagError::FlowFailed { failed_job });
}
let summary = self.nodes.get(&job).expect("checked contains_key");
let missing: Vec<u32> = summary
.depends
.iter()
.copied()
.filter(|d| !self.completed.contains(d))
.collect();
if !missing.is_empty() {
return Err(DagError::DependenciesIncomplete { job, missing });
}
self.started.insert(job);
Ok(())
}
/// Mark a job as completed.
/// Strict validation rules:
/// - Unknown jobs are rejected with UnknownJob
/// - If the job is already completed, this is a no-op (idempotent)
/// - If the flow has already failed, return FlowFailed
/// - If the job was not previously started, return JobNotStarted
pub fn mark_job_completed(&mut self, job: u32) -> DagResult<()> {
if !self.nodes.contains_key(&job) {
return Err(DagError::UnknownJob { job });
}
if self.completed.contains(&job) {
return Ok(());
}
if let Some(failed_job) = self.failed_job {
return Err(DagError::FlowFailed { failed_job });
}
if !self.started.contains(&job) {
return Err(DagError::JobNotStarted { job });
}
self.started.remove(&job);
self.completed.insert(job);
Ok(())
}
/// Mark a job as failed.
/// Behavior:
/// - Unknown jobs are rejected with UnknownJob
/// - If a failure is already recorded:
/// - If it is the same job, no-op (idempotent)
/// - If it is a different job, return FlowFailed with the already-failed job
/// - Otherwise record this job as the failed job
pub fn mark_job_failed(&mut self, job: u32) -> DagResult<()> {
if !self.nodes.contains_key(&job) {
return Err(DagError::UnknownJob { job });
}
match self.failed_job {
Some(existing) if existing == job => Ok(()),
Some(existing) => Err(DagError::FlowFailed {
failed_job: existing,
}),
None => {
self.failed_job = Some(job);
Ok(())
}
}
}
}

View File

@@ -1,5 +1,8 @@
pub mod clients;
pub mod dag;
pub mod models;
pub mod router;
pub mod rpc;
pub mod service;
pub mod storage;
mod time;
pub mod dag;
pub mod rpc;

View File

@@ -2,6 +2,8 @@ use clap::Parser;
use std::net::{IpAddr, SocketAddr};
use std::sync::Arc;
use tracing::{error, info, warn};
use tracing_subscriber::{EnvFilter, fmt};
#[derive(Debug, Clone, Parser)]
#[command(
name = "herocoordinator",
@@ -73,6 +75,14 @@ struct Cli {
#[tokio::main]
async fn main() {
let cli = Cli::parse();
// Initialize tracing subscriber (pretty formatter; controlled by RUST_LOG)
let filter = EnvFilter::try_from_default_env().unwrap_or_else(|_| EnvFilter::new("info"));
tracing_subscriber::fmt()
.with_env_filter(filter)
.pretty()
.with_target(true)
.with_level(true)
.init();
let http_addr = SocketAddr::new(cli.api_http_ip, cli.api_http_port);
let ws_addr = SocketAddr::new(cli.api_ws_ip, cli.api_ws_port);
@@ -82,17 +92,32 @@ async fn main() {
.await
.expect("Failed to connect to Redis");
// Initialize Service
let service = herocoordinator::service::AppService::new(redis);
let service_for_router = service.clone();
// Shared application state
let state = Arc::new(herocoordinator::rpc::AppState::new(redis));
let state = Arc::new(herocoordinator::rpc::AppState::new(service));
// Start router workers (auto-discovered contexts)
{
let base_url = format!("http://{}:{}", cli.mycelium_ip, cli.mycelium_port);
let cfg = herocoordinator::router::RouterConfig {
context_ids: Vec::new(), // ignored by start_router_auto
concurrency: 32,
base_url,
topic: "supervisor.rpc".to_string(),
transport_poll_interval_secs: 2,
transport_poll_timeout_secs: 300,
};
let _auto_handle = herocoordinator::router::start_router_auto(service_for_router, cfg);
}
// Build RPC modules for both servers
let http_module = herocoordinator::rpc::build_module(state.clone());
let ws_module = herocoordinator::rpc::build_module(state.clone());
println!(
"Starting JSON-RPC servers: HTTP http://{} | WS ws://{} | redis_addr={}",
http_addr, ws_addr, cli.redis_addr
);
info!(%http_addr, %ws_addr, redis_addr=%cli.redis_addr, "Starting JSON-RPC servers");
// Start servers
let _http_handle = herocoordinator::rpc::start_http(http_addr, http_module)
@@ -104,7 +129,7 @@ async fn main() {
// Wait for Ctrl+C to terminate
if let Err(e) = tokio::signal::ctrl_c().await {
eprintln!("Failed to listen for shutdown signal: {e}");
error!(error=%e, "Failed to listen for shutdown signal");
}
println!("Shutdown signal received, exiting.");
info!("Shutdown signal received, exiting.");
}

View File

@@ -8,8 +8,8 @@ mod script_type;
pub use actor::Actor;
pub use context::Context;
pub use flow::Flow;
pub use job::Job;
pub use message::{Message, MessageFormatType, MessageStatus, MessageType};
pub use flow::{Flow, FlowStatus};
pub use job::{Job, JobStatus};
pub use message::{Message, MessageFormatType, MessageStatus, MessageType, TransportStatus};
pub use runner::Runner;
pub use script_type::ScriptType;

View File

@@ -5,13 +5,13 @@ use crate::time::Timestamp;
#[derive(Serialize, Deserialize, Clone)]
pub struct Context {
/// Redis DB to use
id: u32,
pub id: u32,
/// Actor ids which have admin rights on this context
admins: Vec<u32>,
pub admins: Vec<u32>,
/// Actor ids which can read the context info
readers: Vec<u32>,
pub readers: Vec<u32>,
/// Actor ids which can execute jobs in this context
executors: Vec<u32>,
created_at: Timestamp,
updated_at: Timestamp,
pub executors: Vec<u32>,
pub created_at: Timestamp,
pub updated_at: Timestamp,
}

View File

@@ -7,25 +7,26 @@ use crate::time::Timestamp;
#[derive(Serialize, Deserialize, Clone)]
pub struct Flow {
/// Job Id set tby the actor which created it
id: u32,
pub id: u32,
/// Actor Id who created this job
caller_id: u32,
pub caller_id: u32,
/// The context in which this job is executed
context_id: u32,
pub context_id: u32,
/// List of jobs which make up the flow
jobs: Vec<u32>,
pub jobs: Vec<u32>,
/// Environment variables, passed to every job when executed
env_vars: HashMap<String, String>,
pub env_vars: HashMap<String, String>,
/// The result of the flow
result: HashMap<String, String>,
created_at: Timestamp,
updated_at: Timestamp,
status: FlowStatus,
pub result: HashMap<String, String>,
pub created_at: Timestamp,
pub updated_at: Timestamp,
pub status: FlowStatus,
}
/// The status of a flow
#[derive(Serialize, Deserialize, Clone)]
#[derive(Serialize, Deserialize, Clone, PartialEq, Eq, Debug)]
pub enum FlowStatus {
Created,
Dispatched,
Started,
Error,
@@ -42,7 +43,7 @@ impl Flow {
pub fn context_id(&self) -> u32 {
self.context_id
}
pub fn jobs(&self) -> &Vec<u32> {
pub fn jobs(&self) -> &[u32] {
&self.jobs
}
}

View File

@@ -7,28 +7,28 @@ use crate::{models::ScriptType, time::Timestamp};
#[derive(Clone, Serialize, Deserialize)]
pub struct Job {
/// Job Id, this is given by the actor who created the job
id: u32,
pub id: u32,
/// Actor ID which created this job
caller_id: u32,
pub caller_id: u32,
/// Context in which the job is executed
context_id: u32,
script: String,
script_type: ScriptType,
pub context_id: u32,
pub script: String,
pub script_type: ScriptType,
/// Timeout in seconds for this job
timeout: u32,
pub timeout: u32,
/// Max amount of times to retry this job
retries: u8,
env_vars: HashMap<String, String>,
result: HashMap<String, String>,
prerequisites: Vec<String>,
pub retries: u8,
pub env_vars: HashMap<String, String>,
pub result: HashMap<String, String>,
pub prerequisites: Vec<String>,
/// Ids of jobs this job depends on, i.e. this job can't start until those have finished
depends: Vec<u32>,
created_at: Timestamp,
updated_at: Timestamp,
status: JobStatus,
pub depends: Vec<u32>,
pub created_at: Timestamp,
pub updated_at: Timestamp,
pub status: JobStatus,
}
#[derive(Clone, Serialize, Deserialize)]
#[derive(Clone, Serialize, Deserialize, PartialEq, Eq, Debug)]
pub enum JobStatus {
Dispatched,
WaitingForPrerequisites,
@@ -47,13 +47,16 @@ impl Job {
pub fn context_id(&self) -> u32 {
self.context_id
}
pub fn depends(&self) -> &Vec<u32> {
pub fn depends(&self) -> &[u32] {
&self.depends
}
pub fn prerequisites(&self) -> &Vec<String> {
pub fn prerequisites(&self) -> &[String] {
&self.prerequisites
}
pub fn script_type(&self) -> ScriptType {
self.script_type.clone()
}
pub fn status(&self) -> JobStatus {
self.status.clone()
}
}

View File

@@ -8,25 +8,31 @@ use crate::{
#[derive(Clone, Serialize, Deserialize)]
pub struct Message {
/// Unique ID for the message, set by the caller
id: u32,
pub id: u32,
/// Id of the actor who sent this message
caller_id: u32,
pub caller_id: u32,
/// Id of the context in which this message was sent
context_id: u32,
message: String,
message_type: ScriptType,
message_format_type: MessageFormatType,
pub context_id: u32,
pub message: String,
pub message_type: ScriptType,
pub message_format_type: MessageFormatType,
/// Seconds for the message to arrive at the destination
timeout: u32,
pub timeout: u32,
/// Seconds for the receiver to acknowledge receipt of the message
timeout_ack: u32,
pub timeout_ack: u32,
/// Seconds for the receiver to send us a reply
timeout_result: u32,
job: Vec<Job>,
logs: Vec<Log>,
created_at: Timestamp,
updated_at: Timestamp,
status: MessageStatus,
pub timeout_result: u32,
/// Outbound transport id returned by Mycelium on push
pub transport_id: Option<String>,
/// Latest transport status as reported by Mycelium
pub transport_status: Option<TransportStatus>,
pub job: Vec<Job>,
pub logs: Vec<Log>,
pub created_at: Timestamp,
pub updated_at: Timestamp,
pub status: MessageStatus,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
@@ -36,7 +42,7 @@ pub enum MessageType {
Mail,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
pub enum MessageStatus {
Dispatched,
Acknowledged,
@@ -44,6 +50,15 @@ pub enum MessageStatus {
Processed,
}
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
pub enum TransportStatus {
Queued,
Sent,
Delivered,
Read,
Failed,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
pub enum MessageFormatType {
Html,

View File

@@ -2,21 +2,24 @@ use std::net::IpAddr;
use serde::{Deserialize, Serialize};
use crate::models::ScriptType;
use crate::time::Timestamp;
#[derive(Serialize, Deserialize, Clone)]
pub struct Runner {
id: u32,
pub id: u32,
/// Mycelium public key
pubkey: String,
pub pubkey: String,
/// Mycelium address
address: IpAddr,
pub address: IpAddr,
/// Needs to be set by the runner, usually `runner<runnerid`
topic: String,
pub topic: String,
/// The script type this runner can execute; used for routing
pub script_type: ScriptType,
/// If this is true, the runner also listens on a local redis queue
local: bool,
created_at: Timestamp,
updated_at: Timestamp,
pub local: bool,
pub created_at: Timestamp,
pub updated_at: Timestamp,
}
#[derive(Serialize, Deserialize, Clone)]

View File

@@ -1,6 +1,6 @@
use serde::{Deserialize, Serialize};
#[derive(Debug, Clone, Deserialize, Serialize)]
#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, Eq)]
pub enum ScriptType {
Osis,
Sal,

475
src/router.rs Normal file
View File

@@ -0,0 +1,475 @@
use std::{collections::HashSet, sync::Arc};
use serde_json::{Value, json};
use tokio::sync::Semaphore;
use crate::{
clients::{Destination, MyceliumClient, SupervisorClient},
models::{Job, JobStatus, Message, MessageStatus, ScriptType, TransportStatus},
service::AppService,
};
use tracing::{error, info, warn};
#[derive(Clone, Debug)]
pub struct RouterConfig {
pub context_ids: Vec<u32>,
pub concurrency: usize,
pub base_url: String, // e.g. http://127.0.0.1:8990
pub topic: String, // e.g. "supervisor.rpc"
// Transport status polling configuration
pub transport_poll_interval_secs: u64, // e.g. 2
pub transport_poll_timeout_secs: u64, // e.g. 300 (5 minutes)
}
/// Start background router loops, one per context.
/// Each loop:
/// - BRPOP msg_out with 1s timeout
/// - Loads the Message by key, selects a Runner by script_type
/// - Sends supervisor JSON-RPC via Mycelium
/// - On success: Message.status = Acknowledged
/// - On error: Message.status = Error and append a log
pub fn start_router(service: AppService, cfg: RouterConfig) -> Vec<tokio::task::JoinHandle<()>> {
let mut handles = Vec::new();
for ctx_id in cfg.context_ids.clone() {
let service_cloned = service.clone();
let cfg_cloned = cfg.clone();
let handle = tokio::spawn(async move {
let sem = Arc::new(Semaphore::new(cfg_cloned.concurrency));
// Create a shared Mycelium client for this context loop (retry until available)
let mycelium = loop {
match MyceliumClient::new(cfg_cloned.base_url.clone()) {
Ok(c) => break Arc::new(c),
Err(e) => {
error!(context_id=ctx_id, error=%e, "MyceliumClient init error");
tokio::time::sleep(std::time::Duration::from_secs(1)).await;
}
}
};
loop {
// Pop next message key (blocking with timeout)
match service_cloned.brpop_msg_out(ctx_id, 1).await {
Ok(Some(key)) => {
let permit = {
// acquire a concurrency permit (non-fair is fine)
let sem = sem.clone();
// if semaphore is exhausted, await until a slot becomes available
match sem.acquire_owned().await {
Ok(p) => p,
Err(_) => {
// Semaphore closed; exit loop
break;
}
}
};
let service_task = service_cloned.clone();
let cfg_task = cfg_cloned.clone();
tokio::spawn({
let mycelium = mycelium.clone();
async move {
// Ensure permit is dropped at end of task
let _permit = permit;
if let Err(e) =
deliver_one(&service_task, &cfg_task, ctx_id, &key, mycelium)
.await
{
error!(context_id=ctx_id, key=%key, error=%e, "Delivery error");
}
}
});
}
Ok(None) => {
// timeout: just tick
continue;
}
Err(e) => {
error!(context_id=ctx_id, error=%e, "BRPOP error");
// small backoff to avoid busy-loop on persistent errors
tokio::time::sleep(std::time::Duration::from_millis(200)).await;
}
}
}
});
handles.push(handle);
}
handles
}
async fn deliver_one(
service: &AppService,
cfg: &RouterConfig,
context_id: u32,
msg_key: &str,
mycelium: Arc<MyceliumClient>,
) -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
// Parse "message:{caller_id}:{id}"
let (caller_id, id) = parse_message_key(msg_key)
.ok_or_else(|| format!("invalid message key format: {}", msg_key))?;
// Load message
let msg: Message = service.load_message(context_id, caller_id, id).await?;
// Embedded job id (if any)
let job_id_opt: Option<u32> = msg.job.first().map(|j| j.id);
// Determine routing script_type
let desired: ScriptType = determine_script_type(&msg);
// Discover runners and select a matching one
let runners = service.scan_runners(context_id).await?;
let Some(runner) = runners.into_iter().find(|r| r.script_type == desired) else {
let log = format!(
"No runner with script_type {:?} available in context {} for message {}",
desired, context_id, msg_key
);
let _ = service
.append_message_logs(context_id, caller_id, id, vec![log.clone()])
.await;
let _ = service
.update_message_status(context_id, caller_id, id, MessageStatus::Error)
.await;
return Err(log.into());
};
// Build SupervisorClient
let dest = if !runner.pubkey.trim().is_empty() {
Destination::Pk(runner.pubkey.clone())
} else {
Destination::Ip(runner.address)
};
// Keep clones for poller usage
let dest_for_poller = dest.clone();
let topic_for_poller = cfg.topic.clone();
let client = SupervisorClient::new_with_client(
mycelium.clone(),
dest.clone(),
cfg.topic.clone(),
None, // secret
);
// Build supervisor method and params from Message
let method = msg.message.clone();
let params = build_params(&msg)?;
// Send
let out_id = client.call(&method, params).await?;
// Store transport id and initial Sent status
let _ = service
.update_message_transport(
context_id,
caller_id,
id,
Some(out_id.clone()),
Some(TransportStatus::Sent),
)
.await;
// Mark as acknowledged on success
service
.update_message_status(context_id, caller_id, id, MessageStatus::Acknowledged)
.await?;
// Spawn transport-status poller
{
let service_poll = service.clone();
let poll_interval = std::time::Duration::from_secs(cfg.transport_poll_interval_secs);
let poll_timeout = std::time::Duration::from_secs(cfg.transport_poll_timeout_secs);
let out_id_cloned = out_id.clone();
let mycelium = mycelium.clone();
// Determine reply timeout for supervisor job.result: prefer message.timeout_result, fallback to router config timeout
let job_result_reply_timeout: u64 = if msg.timeout_result > 0 {
msg.timeout_result as u64
} else {
cfg.transport_poll_timeout_secs
};
tokio::spawn(async move {
let start = std::time::Instant::now();
let client = mycelium;
// Supervisor call context captured for sync status checks
let sup_dest = dest_for_poller;
let sup_topic = topic_for_poller;
let job_id_opt = job_id_opt;
let mut last_status: Option<TransportStatus> = Some(TransportStatus::Sent);
loop {
if start.elapsed() >= poll_timeout {
let _ = service_poll
.append_message_logs(
context_id,
caller_id,
id,
vec!["Transport-status polling timed out".to_string()],
)
.await;
// leave last known status; do not override
break;
}
match client.message_status(&out_id_cloned).await {
Ok(s) => {
if last_status.as_ref() != Some(&s) {
let _ = service_poll
.update_message_transport(
context_id,
caller_id,
id,
None,
Some(s.clone()),
)
.await;
last_status = Some(s.clone());
}
// Stop on terminal states
if matches!(s, TransportStatus::Delivered | TransportStatus::Read) {
// On Read, fetch supervisor job.status and update local job/message if terminal
if matches!(s, TransportStatus::Read) {
if let Some(job_id) = job_id_opt {
let sup = SupervisorClient::new_with_client(
client.clone(),
sup_dest.clone(),
sup_topic.clone(),
None,
);
match sup.job_status_sync(job_id.to_string(), 10).await {
Ok(remote_status) => {
if let Some((mapped, terminal)) =
map_supervisor_job_status(&remote_status)
{
if terminal {
let _ = service_poll
.update_job_status_unchecked(
context_id,
caller_id,
job_id,
mapped.clone(),
)
.await;
// After terminal status, fetch supervisor job.result and store into Job.result
let sup = SupervisorClient::new_with_client(
client.clone(),
sup_dest.clone(),
sup_topic.clone(),
None,
);
match sup
.job_result_sync(
job_id.to_string(),
job_result_reply_timeout,
)
.await
{
Ok(result_map) => {
// Persist the result into the Job.result map (merge)
let _ = service_poll
.update_job_result_merge_unchecked(
context_id,
caller_id,
job_id,
result_map.clone(),
)
.await;
// Log which key was stored (success or error)
let key = result_map
.keys()
.next()
.cloned()
.unwrap_or_else(|| {
"unknown".to_string()
});
let _ = service_poll
.append_message_logs(
context_id,
caller_id,
id,
vec![format!(
"Stored supervisor job.result for job {} ({})",
job_id, key
)],
)
.await;
}
Err(e) => {
let _ = service_poll
.append_message_logs(
context_id,
caller_id,
id,
vec![format!(
"job.result fetch error for job {}: {}",
job_id, e
)],
)
.await;
}
}
// Mark message as processed
let _ = service_poll
.update_message_status(
context_id,
caller_id,
id,
MessageStatus::Processed,
)
.await;
let _ = service_poll
.append_message_logs(
context_id,
caller_id,
id,
vec![format!(
"Supervisor job.status for job {} -> {} (mapped to {:?})",
job_id, remote_status, mapped
)],
)
.await;
}
} else {
let _ = service_poll
.append_message_logs(
context_id,
caller_id,
id,
vec![format!(
"Unknown supervisor status '{}' for job {}",
remote_status, job_id
)],
)
.await;
}
}
Err(e) => {
let _ = service_poll
.append_message_logs(
context_id,
caller_id,
id,
vec![format!("job.status sync error: {}", e)],
)
.await;
}
}
}
}
break;
}
if matches!(s, TransportStatus::Failed) {
let _ = service_poll
.append_message_logs(
context_id,
caller_id,
id,
vec![format!(
"Transport failed for outbound id {out_id_cloned}"
)],
)
.await;
break;
}
}
Err(e) => {
// Log and continue polling
let _ = service_poll
.append_message_logs(
context_id,
caller_id,
id,
vec![format!("messageStatus query error: {e}")],
)
.await;
}
}
tokio::time::sleep(poll_interval).await;
}
});
}
Ok(())
}
fn determine_script_type(msg: &Message) -> ScriptType {
// Prefer embedded job's script_type if available, else fallback to message.message_type
match msg.job.first() {
Some(j) => j.script_type.clone(),
None => msg.message_type.clone(),
}
}
fn build_params(msg: &Message) -> Result<Value, Box<dyn std::error::Error + Send + Sync>> {
// Minimal mapping:
// - "job.run" with exactly one embedded job: [{ "job": <job> }]
// - otherwise: []
if msg.message == "job.run"
&& let Some(j) = msg.job.first()
{
let jv = job_to_json(j)?;
return Ok(json!([ { "job": jv } ]));
}
Ok(json!([]))
}
fn job_to_json(job: &Job) -> Result<Value, Box<dyn std::error::Error + Send + Sync>> {
Ok(serde_json::to_value(job)?)
}
fn parse_message_key(s: &str) -> Option<(u32, u32)> {
// Expect "message:{caller_id}:{id}"
let mut it = s.split(':');
match (it.next(), it.next(), it.next(), it.next()) {
(Some("message"), Some(caller), Some(id), None) => {
let caller_id = caller.parse::<u32>().ok()?;
let msg_id = id.parse::<u32>().ok()?;
Some((caller_id, msg_id))
}
_ => None,
}
}
/// Map supervisor job.status -> (local JobStatus, terminal)
fn map_supervisor_job_status(s: &str) -> Option<(JobStatus, bool)> {
match s {
"created" | "queued" => Some((JobStatus::Dispatched, false)),
"running" => Some((JobStatus::Started, false)),
"completed" => Some((JobStatus::Finished, true)),
"failed" | "timeout" => Some((JobStatus::Error, true)),
_ => None,
}
}
/// Auto-discover contexts periodically and ensure a router loop exists for each.
/// Returns a JoinHandle of the discovery task (router loops are detached).
pub fn start_router_auto(service: AppService, cfg: RouterConfig) -> tokio::task::JoinHandle<()> {
tokio::spawn(async move {
let mut active: HashSet<u32> = HashSet::new();
loop {
match service.list_context_ids().await {
Ok(ids) => {
for ctx_id in ids {
if !active.contains(&ctx_id) {
// Spawn a loop for this new context
let cfg_ctx = RouterConfig {
context_ids: vec![ctx_id],
..cfg.clone()
};
let _ = start_router(service.clone(), cfg_ctx);
active.insert(ctx_id);
info!(context_id = ctx_id, "Started loop for context");
}
}
}
Err(e) => {
error!(error=%e, "list_context_ids error");
}
}
tokio::time::sleep(std::time::Duration::from_secs(5)).await;
}
})
}

View File

@@ -13,19 +13,25 @@ use serde::Deserialize;
use serde_json::{Value, json};
use crate::{
dag::{DagError, FlowDag, build_flow_dag},
models::{Actor, Context, Flow, Job, Message, MessageFormatType, Runner, ScriptType},
storage::RedisDriver,
dag::{DagError, FlowDag},
models::{
Actor, Context, Flow, FlowStatus, Job, JobStatus, Message, MessageFormatType,
MessageStatus, Runner, ScriptType,
},
service::AppService,
time::current_timestamp,
};
/// The OpenRPC specification for the HeroCoordinator JSON-RPC API
const OPENRPC_SPEC: &str = include_str!("../specs/openrpc.json");
pub struct AppState {
pub redis: RedisDriver,
pub service: AppService,
}
impl AppState {
pub fn new(redis: RedisDriver) -> Self {
Self { redis }
pub fn new(service: AppService) -> Self {
Self { service }
}
}
@@ -59,6 +65,26 @@ fn dag_err(e: DagError) -> ErrorObjectOwned {
"DAG Cycle Detected",
Some(Value::String(e.to_string())),
),
DagError::UnknownJob { .. } => ErrorObjectOwned::owned(
-32022,
"DAG Unknown Job",
Some(Value::String(e.to_string())),
),
DagError::DependenciesIncomplete { .. } => ErrorObjectOwned::owned(
-32023,
"DAG Dependencies Incomplete",
Some(Value::String(e.to_string())),
),
DagError::FlowFailed { .. } => ErrorObjectOwned::owned(
-32024,
"DAG Flow Failed",
Some(Value::String(e.to_string())),
),
DagError::JobNotStarted { .. } => ErrorObjectOwned::owned(
-32025,
"DAG Job Not Started",
Some(Value::String(e.to_string())),
),
}
}
@@ -94,25 +120,24 @@ pub struct ContextCreate {
pub executors: Vec<u32>,
}
impl ContextCreate {
pub fn into_domain(self) -> Result<Context, String> {
pub fn into_domain(self) -> Context {
let ts = current_timestamp();
let mut v = serde_json::Map::new();
v.insert("id".to_string(), Value::from(self.id));
v.insert(
"admins".to_string(),
serde_json::to_value(self.admins).unwrap(),
);
v.insert(
"readers".to_string(),
serde_json::to_value(self.readers).unwrap(),
);
v.insert(
"executors".to_string(),
serde_json::to_value(self.executors).unwrap(),
);
v.insert("created_at".to_string(), Value::from(ts));
v.insert("updated_at".to_string(), Value::from(ts));
serde_json::from_value(Value::Object(v)).map_err(|e| e.to_string())
let ContextCreate {
id,
admins,
readers,
executors,
} = self;
Context {
id,
admins,
readers,
executors,
created_at: ts,
updated_at: ts,
}
}
}
@@ -122,21 +147,33 @@ pub struct RunnerCreate {
pub pubkey: String,
pub address: IpAddr,
pub topic: String,
/// The script type this runner executes (used for routing)
pub script_type: ScriptType,
pub local: bool,
}
impl RunnerCreate {
pub fn into_domain(self) -> Result<Runner, String> {
pub fn into_domain(self) -> Runner {
let ts = current_timestamp();
let v = json!({
"id": self.id,
"pubkey": self.pubkey,
"address": self.address,
"topic": self.topic,
"local": self.local,
"created_at": ts,
"updated_at": ts,
});
serde_json::from_value(v).map_err(|e| e.to_string())
let RunnerCreate {
id,
pubkey,
address,
topic,
script_type,
local,
} = self;
Runner {
id,
pubkey,
address,
topic,
script_type,
local,
created_at: ts,
updated_at: ts,
}
}
}
@@ -147,24 +184,31 @@ pub struct FlowCreate {
pub context_id: u32,
pub jobs: Vec<u32>,
pub env_vars: HashMap<String, String>,
#[serde(default)]
pub result: Option<HashMap<String, String>>,
}
impl FlowCreate {
pub fn into_domain(self) -> Result<Flow, String> {
pub fn into_domain(self) -> Flow {
let ts = current_timestamp();
let v = json!({
"id": self.id,
"caller_id": self.caller_id,
"context_id": self.context_id,
"jobs": self.jobs,
"env_vars": self.env_vars,
"result": self.result.unwrap_or_default(),
"created_at": ts,
"updated_at": ts,
"status": "Dispatched",
});
serde_json::from_value(v).map_err(|e| e.to_string())
let FlowCreate {
id,
caller_id,
context_id,
jobs,
env_vars,
} = self;
Flow {
id,
caller_id,
context_id,
jobs,
env_vars,
result: HashMap::new(),
created_at: ts,
updated_at: ts,
status: FlowStatus::Created,
}
}
}
@@ -178,31 +222,43 @@ pub struct JobCreate {
pub timeout: u32,
pub retries: u8,
pub env_vars: HashMap<String, String>,
#[serde(default)]
pub result: Option<HashMap<String, String>>,
pub prerequisites: Vec<String>,
pub depends: Vec<u32>,
}
impl JobCreate {
pub fn into_domain(self) -> Result<Job, String> {
pub fn into_domain(self) -> Job {
let ts = current_timestamp();
let v = json!({
"id": self.id,
"caller_id": self.caller_id,
"context_id": self.context_id,
"script": self.script,
"script_type": self.script_type,
"timeout": self.timeout,
"retries": self.retries,
"env_vars": self.env_vars,
"result": self.result.unwrap_or_default(),
"prerequisites": self.prerequisites,
"depends": self.depends,
"created_at": ts,
"updated_at": ts,
"status": "Dispatched",
});
serde_json::from_value(v).map_err(|e| e.to_string())
let JobCreate {
id,
caller_id,
context_id,
script,
script_type,
timeout,
retries,
env_vars,
prerequisites,
depends,
} = self;
Job {
id,
caller_id,
context_id,
script,
script_type,
timeout,
retries,
env_vars,
result: HashMap::new(),
prerequisites,
depends,
created_at: ts,
updated_at: ts,
status: JobStatus::WaitingForPrerequisites,
}
}
}
@@ -218,48 +274,51 @@ pub struct MessageCreate {
pub timeout_ack: u32,
pub timeout_result: u32,
pub job: Vec<JobCreate>,
#[serde(default)]
pub logs: Option<Vec<String>>,
}
impl MessageCreate {
pub fn into_domain(self) -> Result<Message, String> {
pub fn into_domain(self) -> Message {
let ts = current_timestamp();
let jobs: Result<Vec<Value>, String> = self
.job
.into_iter()
.map(|j| {
let jd: Job = j.into_domain()?;
serde_json::to_value(jd).map_err(|e| e.to_string())
})
.collect();
let v = json!({
"id": self.id,
"caller_id": self.caller_id,
"context_id": self.context_id,
"message": self.message,
"message_type": self.message_type,
"message_format_type": self.message_format_type, // "Html" | "Text" | "Md"
"timeout": self.timeout,
"timeout_ack": self.timeout_ack,
"timeout_result": self.timeout_result,
"job": jobs?,
"logs": self.logs.unwrap_or_default(),
"created_at": ts,
"updated_at": ts,
"status": "Dispatched",
});
serde_json::from_value(v).map_err(|e| e.to_string())
let MessageCreate {
id,
caller_id,
context_id,
message,
message_type,
message_format_type,
timeout,
timeout_ack,
timeout_result,
job,
} = self;
Message {
id,
caller_id,
context_id,
message,
message_type,
message_format_type,
timeout,
timeout_ack,
timeout_result,
transport_id: None,
transport_status: None,
job: job.into_iter().map(JobCreate::into_domain).collect(),
logs: Vec::new(),
created_at: ts,
updated_at: ts,
status: MessageStatus::Dispatched,
}
}
}
#[derive(Debug, Deserialize)]
pub struct ActorCreateParams {
pub context_id: u32,
pub actor: ActorCreate,
}
#[derive(Debug, Deserialize)]
pub struct ActorLoadParams {
pub context_id: u32,
pub id: u32,
}
@@ -334,9 +393,9 @@ pub fn build_module(state: Arc<AppState>) -> RpcModule<()> {
async move {
let p: ActorCreateParams = params.parse().map_err(invalid_params_err)?;
let actor = p.actor.into_domain().map_err(invalid_params_err)?;
state
.redis
.save_actor(p.context_id, &actor)
let actor = state
.service
.create_actor(actor)
.await
.map_err(storage_err)?;
Ok::<_, ErrorObjectOwned>(actor)
@@ -351,11 +410,7 @@ pub fn build_module(state: Arc<AppState>) -> RpcModule<()> {
let state = state.clone();
async move {
let p: ActorLoadParams = params.parse().map_err(invalid_params_err)?;
let actor = state
.redis
.load_actor(p.context_id, p.id)
.await
.map_err(storage_err)?;
let actor = state.service.load_actor(p.id).await.map_err(storage_err)?;
Ok::<_, ErrorObjectOwned>(actor)
}
})
@@ -370,8 +425,12 @@ pub fn build_module(state: Arc<AppState>) -> RpcModule<()> {
let state = state.clone();
async move {
let p: ContextCreateParams = params.parse().map_err(invalid_params_err)?;
let ctx = p.context.into_domain().map_err(invalid_params_err)?;
state.redis.save_context(&ctx).await.map_err(storage_err)?;
let ctx = p.context.into_domain();
let ctx = state
.service
.create_context(ctx)
.await
.map_err(storage_err)?;
Ok::<_, ErrorObjectOwned>(ctx)
}
})
@@ -384,7 +443,11 @@ pub fn build_module(state: Arc<AppState>) -> RpcModule<()> {
let state = state.clone();
async move {
let p: ContextLoadParams = params.parse().map_err(invalid_params_err)?;
let ctx = state.redis.load_context(p.id).await.map_err(storage_err)?;
let ctx = state
.service
.load_context(p.id)
.await
.map_err(storage_err)?;
Ok::<_, ErrorObjectOwned>(ctx)
}
})
@@ -399,10 +462,10 @@ pub fn build_module(state: Arc<AppState>) -> RpcModule<()> {
let state = state.clone();
async move {
let p: RunnerCreateParams = params.parse().map_err(invalid_params_err)?;
let runner = p.runner.into_domain().map_err(invalid_params_err)?;
state
.redis
.save_runner(p.context_id, &runner)
let runner = p.runner.into_domain();
let runner = state
.service
.create_runner(p.context_id, runner)
.await
.map_err(storage_err)?;
Ok::<_, ErrorObjectOwned>(runner)
@@ -418,7 +481,7 @@ pub fn build_module(state: Arc<AppState>) -> RpcModule<()> {
async move {
let p: RunnerLoadParams = params.parse().map_err(invalid_params_err)?;
let runner = state
.redis
.service
.load_runner(p.context_id, p.id)
.await
.map_err(storage_err)?;
@@ -436,10 +499,10 @@ pub fn build_module(state: Arc<AppState>) -> RpcModule<()> {
let state = state.clone();
async move {
let p: FlowCreateParams = params.parse().map_err(invalid_params_err)?;
let flow = p.flow.into_domain().map_err(invalid_params_err)?;
state
.redis
.save_flow(p.context_id, &flow)
let flow = p.flow.into_domain();
let flow = state
.service
.create_flow(p.context_id, flow)
.await
.map_err(storage_err)?;
Ok::<_, ErrorObjectOwned>(flow)
@@ -455,7 +518,7 @@ pub fn build_module(state: Arc<AppState>) -> RpcModule<()> {
async move {
let p: FlowLoadParams = params.parse().map_err(invalid_params_err)?;
let flow = state
.redis
.service
.load_flow(p.context_id, p.id)
.await
.map_err(storage_err)?;
@@ -471,7 +534,9 @@ pub fn build_module(state: Arc<AppState>) -> RpcModule<()> {
let state = state.clone();
async move {
let p: FlowLoadParams = params.parse().map_err(invalid_params_err)?;
let dag: FlowDag = build_flow_dag(&state.redis, p.context_id, p.id)
let dag: FlowDag = state
.service
.flow_dag(p.context_id, p.id)
.await
.map_err(dag_err)?;
Ok::<_, ErrorObjectOwned>(dag)
@@ -479,6 +544,23 @@ pub fn build_module(state: Arc<AppState>) -> RpcModule<()> {
})
.expect("register flow.dag");
}
{
let state = state.clone();
module
.register_async_method("flow.start", move |params, _caller, _ctx| {
let state = state.clone();
async move {
let p: FlowLoadParams = params.parse().map_err(invalid_params_err)?;
let started: bool = state
.service
.flow_start(p.context_id, p.id)
.await
.map_err(storage_err)?;
Ok::<_, ErrorObjectOwned>(started)
}
})
.expect("register flow.start");
}
// Job
{
@@ -488,13 +570,12 @@ pub fn build_module(state: Arc<AppState>) -> RpcModule<()> {
let state = state.clone();
async move {
let p: JobCreateParams = params.parse().map_err(invalid_params_err)?;
let job = p.job.into_domain().map_err(invalid_params_err)?;
state
.redis
.save_job(p.context_id, &job)
let job = p.job.into_domain();
let job = state
.service
.create_job(p.context_id, job)
.await
.map_err(storage_err)?;
Ok::<_, ErrorObjectOwned>(job)
}
})
@@ -508,7 +589,7 @@ pub fn build_module(state: Arc<AppState>) -> RpcModule<()> {
async move {
let p: JobLoadParams = params.parse().map_err(invalid_params_err)?;
let job = state
.redis
.service
.load_job(p.context_id, p.caller_id, p.id)
.await
.map_err(storage_err)?;
@@ -526,10 +607,10 @@ pub fn build_module(state: Arc<AppState>) -> RpcModule<()> {
let state = state.clone();
async move {
let p: MessageCreateParams = params.parse().map_err(invalid_params_err)?;
let message = p.message.into_domain().map_err(invalid_params_err)?;
state
.redis
.save_message(p.context_id, &message)
let message = p.message.into_domain();
let message = state
.service
.create_message(p.context_id, message)
.await
.map_err(storage_err)?;
Ok::<_, ErrorObjectOwned>(message)
@@ -545,7 +626,7 @@ pub fn build_module(state: Arc<AppState>) -> RpcModule<()> {
async move {
let p: MessageLoadParams = params.parse().map_err(invalid_params_err)?;
let msg = state
.redis
.service
.load_message(p.context_id, p.caller_id, p.id)
.await
.map_err(storage_err)?;
@@ -554,6 +635,15 @@ pub fn build_module(state: Arc<AppState>) -> RpcModule<()> {
})
.expect("register message.load");
}
{
module
.register_async_method("rpc.discover", move |_params, _caller, _ctx| async move {
let spec = serde_json::from_str::<serde_json::Value>(OPENRPC_SPEC)
.expect("Failed to parse OpenRPC spec");
Ok::<_, ErrorObjectOwned>(spec)
})
.expect("register rpc.discover");
}
module
}

1171
src/service.rs Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -1,4 +1,3 @@
pub mod redis;
pub use redis::RedisDriver;

View File

@@ -6,7 +6,11 @@ use serde::de::DeserializeOwned;
use serde_json::{Map as JsonMap, Value};
use tokio::sync::Mutex;
use crate::models::{Actor, Context, Flow, Job, Message, Runner};
use crate::models::{
Actor, Context, Flow, FlowStatus, Job, JobStatus, Message, MessageStatus, Runner,
TransportStatus,
};
use tracing::{debug, error, info, trace, warn};
type Result<T> = std::result::Result<T, Box<dyn std::error::Error + Send + Sync>>;
@@ -50,8 +54,14 @@ impl RedisDriver {
// Slow path: create a new manager and cache it
let url = format!("{}/{}", self.base_addr.trim_end_matches('/'), db);
let client = redis::Client::open(url.as_str())?;
let cm = client.get_connection_manager().await?;
let client = redis::Client::open(url.as_str()).map_err(|e| {
error!(%url, db=%db, error=%e, "Redis client open failed");
e
})?;
let cm = client.get_connection_manager().await.map_err(|e| {
error!(%url, db=%db, error=%e, "Redis connection manager init failed");
e
})?;
let mut guard = self.managers.lock().await;
let entry = guard.entry(db).or_insert(cm);
@@ -102,21 +112,37 @@ impl RedisDriver {
async fn hset_model<T: Serialize>(&self, db: u32, key: &str, model: &T) -> Result<()> {
let mut cm = self.manager_for_db(db).await?;
let pairs = Self::struct_to_hset_pairs(model)?;
let pairs = Self::struct_to_hset_pairs(model).map_err(|e| {
error!(db=%db, key=%key, error=%e, "Serialize model to HSET pairs failed");
e
})?;
// Ensure no stale fields
let _: u64 = cm.del(key).await.unwrap_or(0);
let del_res: redis::RedisResult<u64> = cm.del(key).await;
if let Err(e) = del_res {
warn!(db=%db, key=%key, error=%e, "DEL before HSET failed");
}
// Write all fields
let _: usize = cm.hset_multiple(key, &pairs).await?;
let _: () = cm.hset_multiple(key, &pairs).await.map_err(|e| {
error!(db=%db, key=%key, error=%e, "HSET multiple failed");
e
})?;
Ok(())
}
async fn hget_model<T: DeserializeOwned>(&self, db: u32, key: &str) -> Result<T> {
let mut cm = self.manager_for_db(db).await?;
let map: StdHashMap<String, String> = cm.hgetall(key).await?;
let map: StdHashMap<String, String> = cm.hgetall(key).await.map_err(|e| {
error!(db=%db, key=%key, error=%e, "HGETALL failed");
e
})?;
if map.is_empty() {
// NotFound is expected in some flows; don't log as error
return Err(format!("Key not found: {}", key).into());
}
Self::hmap_to_struct(map)
Self::hmap_to_struct(map).map_err(|e| {
error!(db=%db, key=%key, error=%e, "Deserialize model from HGETALL failed");
e
})
}
// -----------------------------
@@ -161,7 +187,11 @@ impl RedisDriver {
.and_then(|v| v.as_u64())
.ok_or("Context.id missing or not a number")? as u32;
let key = Self::context_key(id);
self.hset_model(id, &key, ctx).await
// Write the context hash in its own DB
self.hset_model(id, &key, ctx).await?;
// Register this context id in the global registry (DB 0)
let _ = self.register_context_id(id).await;
Ok(())
}
/// Load a Context from its own DB (db index = id)
@@ -190,6 +220,22 @@ impl RedisDriver {
let key = Self::actor_key(id);
self.hget_model(db, &key).await
}
/// Save an Actor globally in DB 0 (Actor is context-independent)
pub async fn save_actor_global(&self, actor: &Actor) -> Result<()> {
let json = serde_json::to_value(actor)?;
let id = json
.get("id")
.and_then(|v| v.as_u64())
.ok_or("Actor.id missing or not a number")? as u32;
let key = Self::actor_key(id);
self.hset_model(0, &key, actor).await
}
/// Load an Actor globally from DB 0 by id
pub async fn load_actor_global(&self, id: u32) -> Result<Actor> {
let key = Self::actor_key(id);
self.hget_model(0, &key).await
}
// -----------------------------
// Runner
@@ -252,6 +298,38 @@ impl RedisDriver {
self.hget_model(db, &key).await
}
/// Atomically update a job's status and `updated_at` fields.
/// - No transition validation is performed.
/// - Writes only the two fields via HSET to avoid rewriting the whole model.
pub async fn update_job_status(
&self,
db: u32,
caller_id: u32,
id: u32,
status: JobStatus,
) -> Result<()> {
let mut cm = self.manager_for_db(db).await?;
let key = Self::job_key(caller_id, id);
// Serialize enum into the same plain string representation stored by create paths
let status_str = match serde_json::to_value(&status)? {
Value::String(s) => s,
v => v.to_string(),
};
let ts = crate::time::current_timestamp();
let pairs = vec![
("status".to_string(), status_str),
("updated_at".to_string(), ts.to_string()),
];
let _: usize = cm.hset_multiple(&key, &pairs).await.map_err(|e| {
error!(db=%db, key=%key, error=%e, "HSET update_job_status failed");
e
})?;
Ok(())
}
// -----------------------------
// Message
// -----------------------------
@@ -274,4 +352,403 @@ impl RedisDriver {
let key = Self::message_key(caller_id, id);
self.hget_model(db, &key).await
}
// -----------------------------
// Partial update helpers
// -----------------------------
/// Flow: update only status and updated_at
pub async fn update_flow_status(&self, db: u32, id: u32, status: FlowStatus) -> Result<()> {
let mut cm = self.manager_for_db(db).await?;
let key = Self::flow_key(id);
let status_str = match serde_json::to_value(&status)? {
Value::String(s) => s,
v => v.to_string(),
};
let ts = crate::time::current_timestamp();
let pairs = vec![
("status".to_string(), status_str),
("updated_at".to_string(), ts.to_string()),
];
let _: usize = cm.hset_multiple(&key, &pairs).await.map_err(|e| {
error!(db=%db, key=%key, error=%e, "HSET update_flow_status failed");
e
})?;
Ok(())
}
/// Message: update only status and updated_at
pub async fn update_message_status(
&self,
db: u32,
caller_id: u32,
id: u32,
status: MessageStatus,
) -> Result<()> {
let mut cm = self.manager_for_db(db).await?;
let key = Self::message_key(caller_id, id);
let status_str = match serde_json::to_value(&status)? {
Value::String(s) => s,
v => v.to_string(),
};
let ts = crate::time::current_timestamp();
let pairs = vec![
("status".to_string(), status_str),
("updated_at".to_string(), ts.to_string()),
];
let _: usize = cm.hset_multiple(&key, &pairs).await.map_err(|e| {
error!(db=%db, key=%key, error=%e, "HSET update_message_status failed");
e
})?;
Ok(())
}
/// Message: update transport_id / transport_status (optionally) and bump updated_at
pub async fn update_message_transport(
&self,
db: u32,
caller_id: u32,
id: u32,
transport_id: Option<String>,
transport_status: Option<TransportStatus>,
) -> Result<()> {
let mut cm = self.manager_for_db(db).await?;
let key = Self::message_key(caller_id, id);
let mut pairs: Vec<(String, String)> = Vec::new();
if let Some(tid) = transport_id {
pairs.push(("transport_id".to_string(), tid));
}
if let Some(ts_status) = transport_status {
let status_str = match serde_json::to_value(&ts_status)? {
Value::String(s) => s,
v => v.to_string(),
};
pairs.push(("transport_status".to_string(), status_str));
}
// Always bump updated_at
let ts = crate::time::current_timestamp();
pairs.push(("updated_at".to_string(), ts.to_string()));
let _: usize = cm.hset_multiple(&key, &pairs).await.map_err(|e| {
error!(db=%db, key=%key, error=%e, "HSET update_message_transport failed");
e
})?;
Ok(())
}
/// Flow: merge env_vars map and bump updated_at
pub async fn update_flow_env_vars_merge(
&self,
db: u32,
id: u32,
patch: StdHashMap<String, String>,
) -> Result<()> {
let mut cm = self.manager_for_db(db).await?;
let key = Self::flow_key(id);
let current: Option<String> = cm.hget(&key, "env_vars").await.ok();
let mut obj = match current
.and_then(|s| serde_json::from_str::<Value>(&s).ok())
.and_then(|v| v.as_object().cloned())
{
Some(m) => m,
None => JsonMap::new(),
};
for (k, v) in patch {
obj.insert(k, Value::String(v));
}
let env_vars_str = Value::Object(obj).to_string();
let ts = crate::time::current_timestamp();
let pairs = vec![
("env_vars".to_string(), env_vars_str),
("updated_at".to_string(), ts.to_string()),
];
let _: usize = cm.hset_multiple(&key, &pairs).await.map_err(|e| {
error!(db=%db, key=%key, error=%e, "HSET update_flow_env_vars_merge failed");
e
})?;
Ok(())
}
/// Flow: merge result map and bump updated_at
pub async fn update_flow_result_merge(
&self,
db: u32,
id: u32,
patch: StdHashMap<String, String>,
) -> Result<()> {
let mut cm = self.manager_for_db(db).await?;
let key = Self::flow_key(id);
let current: Option<String> = cm.hget(&key, "result").await.ok();
let mut obj = match current
.and_then(|s| serde_json::from_str::<Value>(&s).ok())
.and_then(|v| v.as_object().cloned())
{
Some(m) => m,
None => JsonMap::new(),
};
for (k, v) in patch {
obj.insert(k, Value::String(v));
}
let result_str = Value::Object(obj).to_string();
let ts = crate::time::current_timestamp();
let pairs = vec![
("result".to_string(), result_str),
("updated_at".to_string(), ts.to_string()),
];
let _: usize = cm.hset_multiple(&key, &pairs).await.map_err(|e| {
error!(db=%db, key=%key, error=%e, "HSET update_flow_result_merge failed");
e
})?;
Ok(())
}
/// Job: merge env_vars map and bump updated_at
pub async fn update_job_env_vars_merge(
&self,
db: u32,
caller_id: u32,
id: u32,
patch: StdHashMap<String, String>,
) -> Result<()> {
let mut cm = self.manager_for_db(db).await?;
let key = Self::job_key(caller_id, id);
let current: Option<String> = cm.hget(&key, "env_vars").await.ok();
let mut obj = match current
.and_then(|s| serde_json::from_str::<Value>(&s).ok())
.and_then(|v| v.as_object().cloned())
{
Some(m) => m,
None => JsonMap::new(),
};
for (k, v) in patch {
obj.insert(k, Value::String(v));
}
let env_vars_str = Value::Object(obj).to_string();
let ts = crate::time::current_timestamp();
let pairs = vec![
("env_vars".to_string(), env_vars_str),
("updated_at".to_string(), ts.to_string()),
];
let _: usize = cm.hset_multiple(&key, &pairs).await.map_err(|e| {
error!(db=%db, key=%key, error=%e, "HSET update_job_env_vars_merge failed");
e
})?;
Ok(())
}
/// Job: merge result map and bump updated_at
pub async fn update_job_result_merge(
&self,
db: u32,
caller_id: u32,
id: u32,
patch: StdHashMap<String, String>,
) -> Result<()> {
let mut cm = self.manager_for_db(db).await?;
let key = Self::job_key(caller_id, id);
let current: Option<String> = cm.hget(&key, "result").await.ok();
let mut obj = match current
.and_then(|s| serde_json::from_str::<Value>(&s).ok())
.and_then(|v| v.as_object().cloned())
{
Some(m) => m,
None => JsonMap::new(),
};
for (k, v) in patch {
obj.insert(k, Value::String(v));
}
let result_str = Value::Object(obj).to_string();
let ts = crate::time::current_timestamp();
let pairs = vec![
("result".to_string(), result_str),
("updated_at".to_string(), ts.to_string()),
];
let _: usize = cm.hset_multiple(&key, &pairs).await.map_err(|e| {
error!(db=%db, key=%key, error=%e, "HSET update_job_result_merge failed");
e
})?;
Ok(())
}
/// Flow: set jobs list and bump updated_at
pub async fn update_flow_jobs_set(&self, db: u32, id: u32, new_jobs: Vec<u32>) -> Result<()> {
let mut cm = self.manager_for_db(db).await?;
let key = Self::flow_key(id);
let jobs_str = serde_json::to_string(&new_jobs)?;
let ts = crate::time::current_timestamp();
let pairs = vec![
("jobs".to_string(), jobs_str),
("updated_at".to_string(), ts.to_string()),
];
let _: usize = cm.hset_multiple(&key, &pairs).await.map_err(|e| {
error!(db=%db, key=%key, error=%e, "HSET update_flow_jobs_set failed");
e
})?;
Ok(())
}
/// Message: append logs (no dedup) and bump updated_at
pub async fn append_message_logs(
&self,
db: u32,
caller_id: u32,
id: u32,
new_logs: Vec<String>,
) -> Result<()> {
let mut cm = self.manager_for_db(db).await?;
let key = Self::message_key(caller_id, id);
let current: Option<String> = cm.hget(&key, "logs").await.ok();
let mut arr: Vec<Value> = current
.and_then(|s| serde_json::from_str::<Value>(&s).ok())
.and_then(|v| v.as_array().cloned())
.unwrap_or_default();
for l in new_logs {
arr.push(Value::String(l));
}
let logs_str = Value::Array(arr).to_string();
let ts = crate::time::current_timestamp();
let pairs = vec![
("logs".to_string(), logs_str),
("updated_at".to_string(), ts.to_string()),
];
let _: usize = cm.hset_multiple(&key, &pairs).await.map_err(|e| {
error!(db=%db, key=%key, error=%e, "HSET append_message_logs failed");
e
})?;
Ok(())
}
// -----------------------------
// Queues (lists)
// -----------------------------
/// Push a value onto a Redis list using LPUSH in the given DB.
pub async fn lpush_list(&self, db: u32, list: &str, value: &str) -> Result<()> {
let mut cm = self.manager_for_db(db).await?;
let _: i64 = cm.lpush(list, value).await.map_err(|e| {
error!(db=%db, list=%list, value=%value, error=%e, "LPUSH failed");
e
})?;
Ok(())
}
/// Enqueue a message key onto the outbound queue (msg_out).
/// The value is the canonical message key "message:{caller_id}:{id}".
pub async fn enqueue_msg_out(&self, db: u32, caller_id: u32, id: u32) -> Result<()> {
let key = Self::message_key(caller_id, id);
self.lpush_list(db, "msg_out", &key).await
}
/// Block-pop from msg_out with timeout (seconds). Returns the message key if present.
/// Uses BRPOP so that the queue behaves FIFO with LPUSH producer.
pub async fn brpop_msg_out(&self, db: u32, timeout_secs: usize) -> Result<Option<String>> {
let mut cm = self.manager_for_db(db).await?;
// BRPOP returns (list, element) on success
let res: Option<(String, String)> = redis::cmd("BRPOP")
.arg("msg_out")
.arg(timeout_secs)
.query_async(&mut cm)
.await
.map_err(|e| {
error!(db=%db, timeout_secs=%timeout_secs, error=%e, "BRPOP failed");
e
})?;
Ok(res.map(|(_, v)| v))
}
/// Scan all runner:* keys in this DB and return the deserialized Runner entries.
pub async fn scan_runners(&self, db: u32) -> Result<Vec<Runner>> {
let mut cm = self.manager_for_db(db).await?;
let mut out: Vec<Runner> = Vec::new();
let mut cursor: u64 = 0;
loop {
let (next, keys): (u64, Vec<String>) = redis::cmd("SCAN")
.arg(cursor)
.arg("MATCH")
.arg("runner:*")
.arg("COUNT")
.arg(100)
.query_async(&mut cm)
.await
.map_err(|e| {
error!(db=%db, cursor=%cursor, error=%e, "SCAN failed");
e
})?;
for k in keys {
if let Ok(r) = self.hget_model::<Runner>(db, &k).await {
out.push(r);
}
}
if next == 0 {
break;
}
cursor = next;
}
Ok(out)
}
// -----------------------------
// Global registry (DB 0) for Context IDs
// -----------------------------
/// Register a context id in the global set "contexts" stored in DB 0.
pub async fn register_context_id(&self, id: u32) -> Result<()> {
let mut cm = self.manager_for_db(0).await?;
let _: i64 = redis::cmd("SADD")
.arg("contexts")
.arg(id)
.query_async(&mut cm)
.await
.map_err(|e| {
error!(db=0, context_id=%id, error=%e, "SADD contexts failed");
e
})?;
Ok(())
}
/// List all registered context ids from the global set in DB 0.
pub async fn list_context_ids(&self) -> Result<Vec<u32>> {
let mut cm = self.manager_for_db(0).await?;
// Using SMEMBERS and parsing into u32
let vals: Vec<String> = redis::cmd("SMEMBERS")
.arg("contexts")
.query_async(&mut cm)
.await
.map_err(|e| {
error!(db=0, error=%e, "SMEMBERS contexts failed");
e
})?;
let mut out = Vec::with_capacity(vals.len());
for v in vals {
if let Ok(n) = v.parse::<u32>() {
out.push(n);
}
}
out.sort_unstable();
Ok(out)
}
}