gitops/optimclaw
1
0
Fork 0
mirror of https://github.com/outbackdingo/optimclaw.git synced 2026-08-30 08:17:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: add TenantCtx for compile-time tenant isolation

Browse Source 
Implements zmanian's architectural proposal from #1614 review:
two-tier scoped database access (TenantScope/AdminScope) so handler
code cannot accidentally bypass tenant scoping.

TenantScope (default): wraps user_id + Arc<dyn Database>, auto-binds
user_id on every operation. ID-based lookups return None for cross-
tenant resources. No escape hatch — forgetting to scope is a compile
error.

AdminScope (explicit opt-in): cross-tenant access for system-level
components (heartbeat, routine engine, self-repair, scheduler, worker).

TenantCtx bundles TenantScope + workspace + cost guard + per-user
rate limiting. Constructed once per request in handle_message, threaded
through all command handlers and ChatDelegate.

Key changes:
- New src/tenant.rs (~920 lines): TenantScope, AdminScope, TenantCtx,
  TenantRateState, TenantRateRegistry
- All command handlers: user_id: &str → ctx: &TenantCtx
- ChatDelegate: cost check/record/settings via self.tenant
- System components: store field changed to AdminScope
- Config: TENANT_MAX_LLM_CONCURRENT, TENANT_MAX_JOBS_CONCURRENT env vars
- Fixes bug: /status <job_id> cross-tenant leak (now auto-filtered)

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
This commit is contained in:
[email protected]
2026-03-25 16:36:11 -07:00
co-authored by Claude Opus 4.6
parent 746735c59c
commit 8f1e0df0cd
18 changed files with 1135 additions and 124 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/agent/agent_loop.rs
+76 -15
View File
@@ -172,6 +172,8 @@ pub struct AgentDeps {
/// Resolved LLM backend identifier (e.g., "nearai", "openai", "groq").
/// Used by `/model` persistence to determine which env var to update.
pub llm_backend: String,
/// Per-tenant rate limiting registry (lazily creates rate state per user).
pub tenant_rates: Arc<crate::tenant::TenantRateRegistry>,
}
/// The main agent that coordinates all components.
@@ -234,7 +236,10 @@ impl Agent {
SchedulerDeps {
tools: deps.tools.clone(),
extension_manager: deps.extension_manager.clone(),
store: deps.store.clone(),
store: deps
.store
.as_ref()
.map(|db| crate::tenant::AdminScope::new(Arc::clone(db))),
hooks: deps.hooks.clone(),
},
);
@@ -315,6 +320,50 @@ impl Agent {
&self.deps.cost_guard
}
/// Build a tenant-scoped execution context for the given user.
///
/// This is the standard entry point for per-user operations. The returned
/// [`TenantCtx`] provides a [`TenantScope`] that auto-binds `user_id` on
/// every database operation and a per-user rate limiter.
pub(super) async fn tenant_ctx(&self, user_id: &str) -> crate::tenant::TenantCtx {
let rate = self.deps.tenant_rates.get_or_create(user_id).await;
let store = self
.deps
.store
.as_ref()
.map(|db| crate::tenant::TenantScope::new(user_id, Arc::clone(db)));
// Reuse the owner workspace if user matches, otherwise create per-user.
let workspace = match &self.deps.workspace {
Some(ws) if ws.user_id() == user_id => Some(Arc::clone(ws)),
_ => self
.deps
.store
.as_ref()
.map(|db| Arc::new(Workspace::new_with_db(user_id, Arc::clone(db)))),
};
crate::tenant::TenantCtx::new(
user_id,
store,
workspace,
Arc::clone(&self.deps.cost_guard),
rate,
)
}
/// Get an admin-scoped database accessor for cross-tenant operations.
///
/// Only for system-level components (heartbeat, routine engine, self-repair,
/// scheduler). Handler code should use [`tenant_ctx()`](Self::tenant_ctx) instead.
pub(super) fn admin_store(&self) -> Option<crate::tenant::AdminScope> {
self.deps
.store
.as_ref()
.map(|db| crate::tenant::AdminScope::new(Arc::clone(db)))
}
pub(super) fn skill_registry(&self) -> Option<&Arc<std::sync::RwLock<SkillRegistry>>> {
self.deps.skill_registry.as_ref()
}
@@ -400,8 +449,8 @@ impl Agent {
self.config.stuck_threshold,
self.config.max_repair_attempts,
);
if let Some(ref store) = self.deps.store {
self_repair = self_repair.with_store(Arc::clone(store));
if let Some(admin) = self.admin_store() {
self_repair = self_repair.with_store(admin);
}
if let Some(ref builder) = self.deps.builder {
self_repair = self_repair.with_builder(Arc::clone(builder), Arc::clone(self.tools()));
@@ -597,13 +646,13 @@ impl Agent {
.unwrap_or_default();
if config.multi_tenant {
if let Some(store) = self.store() {
if let Some(admin) = self.admin_store() {
Some(spawn_multi_user_heartbeat(
config,
hygiene,
self.cheap_llm().clone(),
Some(notify_tx),
Arc::clone(store),
admin,
))
} else {
tracing::warn!("Multi-tenant heartbeat requires a database store");
@@ -616,7 +665,7 @@ impl Agent {
workspace.clone(),
self.cheap_llm().clone(),
Some(notify_tx),
self.store().map(Arc::clone),
self.admin_store(),
))
}
} else {
@@ -640,7 +689,7 @@ impl Agent {
let engine = Arc::new(RoutineEngine::new(
rt_config.clone(),
Arc::clone(store),
crate::tenant::AdminScope::new(Arc::clone(store)),
self.llm().clone(),
Arc::clone(workspace),
notify_tx,
@@ -1192,11 +1241,20 @@ impl Agent {
}
}
// Build per-tenant execution context once; threaded through all handlers.
let tenant = self.tenant_ctx(&message.user_id).await;
// Process based on submission type
let result = match submission {
Submission::UserInput { content } => {
let mut result = self
.process_user_input(message, session.clone(), thread_id, &content)
.process_user_input(
message,
tenant.clone(),
session.clone(),
thread_id,
&content,
)
.await;
// Drain any messages queued during processing.
@@ -1263,7 +1321,13 @@ impl Agent {
let mut queued_msg = message.clone();
queued_msg.attachments.clear();
result = self
.process_user_input(&queued_msg, session.clone(), thread_id, &next_content)
.process_user_input(
&queued_msg,
tenant.clone(),
session.clone(),
thread_id,
&next_content,
)
.await;
// If processing failed, re-queue the drained content so it
@@ -1289,7 +1353,7 @@ impl Agent {
message.channel
);
// Authorization checks (including restart channel check) are enforced in handle_system_command
self.handle_system_command(&command, &args, &message.channel, &message.user_id)
self.handle_system_command(&command, &args, &message.channel, &tenant)
.await
}
Submission::Undo => self.process_undo(session, thread_id).await,
@@ -1302,12 +1366,9 @@ impl Agent {
Submission::Summarize => self.process_summarize(session, thread_id).await,
Submission::Suggest => self.process_suggest(session, thread_id).await,
Submission::JobStatus { job_id } => {
self.process_job_status(&message.user_id, job_id.as_deref())
.await
}
Submission::JobCancel { job_id } => {
self.process_job_cancel(&message.user_id, &job_id).await
self.process_job_status(&tenant, job_id.as_deref()).await
}
Submission::JobCancel { job_id } => self.process_job_cancel(&tenant, &job_id).await,
Submission::Quit => return Ok(None),
Submission::SwitchThread { thread_id: target } => {
self.process_switch_thread(message, target).await
src/agent/commands.rs
+56 -49
View File
@@ -33,6 +33,7 @@ impl Agent {
&self,
intent: MessageIntent,
message: &IncomingMessage,
tenant: &crate::tenant::TenantCtx,
) -> Result<SubmissionResult, Error> {
// Send thinking status for non-trivial operations
if let MessageIntent::CreateJob { .. } = &intent {
@@ -52,24 +53,18 @@ impl Agent {
description,
category,
} => {
self.handle_create_job(&message.user_id, title, description, category)
self.handle_create_job(tenant, title, description, category)
.await?
}
MessageIntent::CheckJobStatus { job_id } => {
self.handle_check_status(&message.user_id, job_id).await?
}
MessageIntent::CancelJob { job_id } => {
self.handle_cancel_job(&message.user_id, &job_id).await?
}
MessageIntent::ListJobs { filter } => {
self.handle_list_jobs(&message.user_id, filter).await?
}
MessageIntent::HelpJob { job_id } => {
self.handle_help_job(&message.user_id, &job_id).await?
self.handle_check_status(tenant, job_id).await?
}
MessageIntent::CancelJob { job_id } => self.handle_cancel_job(tenant, &job_id).await?,
MessageIntent::ListJobs { filter } => self.handle_list_jobs(tenant, filter).await?,
MessageIntent::HelpJob { job_id } => self.handle_help_job(tenant, &job_id).await?,
MessageIntent::Command { command, args } => {
match self
.handle_command(&command, &args, &message.channel, &message.user_id)
.handle_command(&command, &args, &message.channel, tenant)
.await?
{
Some(s) => s,
@@ -83,14 +78,14 @@ impl Agent {
async fn handle_create_job(
&self,
user_id: &str,
tenant: &crate::tenant::TenantCtx,
title: String,
description: String,
category: Option<String>,
) -> Result<String, Error> {
let job_id = self
.scheduler
.dispatch_job(user_id, &title, &description, None)
.dispatch_job(tenant.user_id(), &title, &description, None)
.await?;
// Set the dedicated category field (not stored in metadata)
@@ -113,7 +108,7 @@ impl Agent {
async fn handle_check_status(
&self,
user_id: &str,
tenant: &crate::tenant::TenantCtx,
job_id: Option<String>,
) -> Result<String, Error> {
match job_id {
@@ -122,13 +117,10 @@ impl Agent {
.map_err(|_| crate::error::JobError::NotFound { id: Uuid::nil() })?;
// Try DB first for persistent state, fall back to ContextManager.
if let Some(store) = self.store()
// TenantScope.get_job() auto-filters by ownership — no manual check needed.
if let Some(store) = tenant.store()
&& let Ok(Some(ctx)) = store.get_job(uuid).await
{
// Ownership check: ensure the job belongs to the requesting user.
if ctx.user_id != user_id {
return Err(crate::error::JobError::NotFound { id: uuid }.into());
}
return Ok(format!(
"Job: {}\nStatus: {:?}\nCreated: {}\nStarted: {}\nActual cost: {}",
ctx.title,
@@ -142,7 +134,7 @@ impl Agent {
}
let ctx = self.context_manager.get_context(uuid).await?;
if ctx.user_id != user_id {
if ctx.user_id != tenant.user_id() {
return Err(crate::error::JobError::NotFound { id: uuid }.into());
}
@@ -159,21 +151,22 @@ impl Agent {
}
None => {
// Show summary from DB for consistency with Jobs tab.
if let Some(store) = self.store() {
// TenantScope methods auto-scope to user — no user_id parameter needed.
if let Some(store) = tenant.store() {
let mut total = 0;
let mut in_progress = 0;
let mut completed = 0;
let mut failed = 0;
let mut stuck = 0;
if let Ok(s) = store.agent_job_summary_for_user(user_id).await {
if let Ok(s) = store.agent_job_summary().await {
total += s.total;
in_progress += s.in_progress;
completed += s.completed;
failed += s.failed;
stuck += s.stuck;
}
if let Ok(s) = store.sandbox_job_summary_for_user(user_id).await {
if let Ok(s) = store.sandbox_job_summary().await {
total += s.total;
in_progress += s.running;
completed += s.completed;
@@ -187,7 +180,7 @@ impl Agent {
}
// Fallback to ContextManager if no DB.
let summary = self.context_manager.summary_for(user_id).await;
let summary = self.context_manager.summary_for(tenant.user_id()).await;
Ok(format!(
"Jobs summary: Total: {} In Progress: {} Completed: {} Failed: {} Stuck: {}",
summary.total,
@@ -200,19 +193,24 @@ impl Agent {
}
}
async fn handle_cancel_job(&self, user_id: &str, job_id: &str) -> Result<String, Error> {
async fn handle_cancel_job(
&self,
tenant: &crate::tenant::TenantCtx,
job_id: &str,
) -> Result<String, Error> {
let uuid = Uuid::parse_str(job_id)
.map_err(|_| crate::error::JobError::NotFound { id: Uuid::nil() })?;
let ctx = self.context_manager.get_context(uuid).await?;
if ctx.user_id != user_id {
if ctx.user_id != tenant.user_id() {
return Err(crate::error::JobError::NotFound { id: uuid }.into());
}
self.scheduler.stop(uuid).await?;
// Also update DB so the Jobs tab reflects cancellation immediately.
if let Some(store) = self.store()
// Use TenantScope — ownership already verified above.
if let Some(store) = tenant.store()
&& let Err(e) = store
.update_job_status(uuid, JobState::Cancelled, Some("Cancelled by user"))
.await
@@ -225,19 +223,20 @@ impl Agent {
async fn handle_list_jobs(
&self,
user_id: &str,
tenant: &crate::tenant::TenantCtx,
_filter: Option<String>,
) -> Result<String, Error> {
// List from DB for consistency with Jobs tab.
if let Some(store) = self.store() {
let agent_jobs = match store.list_agent_jobs_for_user(user_id).await {
// TenantScope methods auto-scope to user.
if let Some(store) = tenant.store() {
let agent_jobs = match store.list_agent_jobs().await {
Ok(jobs) => jobs,
Err(e) => {
tracing::warn!("Failed to list agent jobs: {}", e);
Vec::new()
}
};
let sandbox_jobs = match store.list_sandbox_jobs_for_user(user_id).await {
let sandbox_jobs = match store.list_sandbox_jobs().await {
Ok(jobs) => jobs,
Err(e) => {
tracing::warn!("Failed to list sandbox jobs: {}", e);
@@ -260,7 +259,7 @@ impl Agent {
}
// Fallback to ContextManager if no DB.
let jobs = self.context_manager.all_jobs_for(user_id).await;
let jobs = self.context_manager.all_jobs_for(tenant.user_id()).await;
if jobs.is_empty() {
return Ok("No jobs found.".to_string());
}
@@ -274,12 +273,16 @@ impl Agent {
Ok(output)
}
async fn handle_help_job(&self, user_id: &str, job_id: &str) -> Result<String, Error> {
async fn handle_help_job(
&self,
tenant: &crate::tenant::TenantCtx,
job_id: &str,
) -> Result<String, Error> {
let uuid = Uuid::parse_str(job_id)
.map_err(|_| crate::error::JobError::NotFound { id: Uuid::nil() })?;
let ctx = self.context_manager.get_context(uuid).await?;
if ctx.user_id != user_id {
if ctx.user_id != tenant.user_id() {
return Err(crate::error::JobError::NotFound { id: uuid }.into());
}
@@ -312,11 +315,11 @@ impl Agent {
/// Show job status inline — either all jobs (no id) or a specific job.
pub(super) async fn process_job_status(
&self,
user_id: &str,
tenant: &crate::tenant::TenantCtx,
job_id: Option<&str>,
) -> Result<SubmissionResult, Error> {
match self
.handle_check_status(user_id, job_id.map(|s| s.to_string()))
.handle_check_status(tenant, job_id.map(|s| s.to_string()))
.await
{
Ok(text) => Ok(SubmissionResult::response(text)),
@@ -327,10 +330,10 @@ impl Agent {
/// Cancel a job by ID.
pub(super) async fn process_job_cancel(
&self,
user_id: &str,
tenant: &crate::tenant::TenantCtx,
job_id: &str,
) -> Result<SubmissionResult, Error> {
match self.handle_cancel_job(user_id, job_id).await {
match self.handle_cancel_job(tenant, job_id).await {
Ok(text) => Ok(SubmissionResult::response(text)),
Err(e) => Ok(SubmissionResult::error(format!("Cancel error: {}", e))),
}
@@ -475,7 +478,7 @@ impl Agent {
command: &str,
args: &[String],
channel: &str,
user_id: &str,
tenant: &crate::tenant::TenantCtx,
) -> Result<SubmissionResult, Error> {
match command {
"help" => Ok(SubmissionResult::response(concat!(
@@ -674,7 +677,7 @@ impl Agent {
// would change the default for all users. The per-request
// model_override in the dispatcher reads from the same
// "selected_model" setting and applies it per-user.
self.persist_selected_model(user_id, requested).await;
self.persist_selected_model(tenant, requested).await;
Ok(SubmissionResult::response(format!(
"Model preference set to: {} (per-user)",
requested
@@ -683,7 +686,7 @@ impl Agent {
match self.llm().set_model(requested) {
Ok(()) => {
// Persist the model choice so it survives restarts.
self.persist_selected_model(user_id, requested).await;
self.persist_selected_model(tenant, requested).await;
Ok(SubmissionResult::response(format!(
"Switched model to: {}",
requested
@@ -835,12 +838,12 @@ impl Agent {
command: &str,
args: &[String],
channel: &str,
user_id: &str,
tenant: &crate::tenant::TenantCtx,
) -> Result<Option<String>, Error> {
// System commands are now handled directly via Submission::SystemCommand,
// but the router may still send us unknown /commands.
match self
.handle_system_command(command, args, channel, user_id)
.handle_system_command(command, args, channel, tenant)
.await?
{
SubmissionResult::Response { content } => Ok(Some(content)),
@@ -857,14 +860,18 @@ impl Agent {
///
/// In multi-tenant mode, only the per-user DB setting is written — global
/// .env and TOML files are shared across users and must not be mutated.
async fn persist_selected_model(&self, user_id: &str, model: &str) {
// 1. Persist to DB if available (per-user scoped).
if let Some(store) = self.store() {
async fn persist_selected_model(&self, tenant: &crate::tenant::TenantCtx, model: &str) {
// 1. Persist to DB if available (per-user scoped via TenantScope).
if let Some(store) = tenant.store() {
let value = serde_json::Value::String(model.to_string());
if let Err(e) = store.set_setting(user_id, "selected_model", &value).await {
if let Err(e) = store.set_setting("selected_model", &value).await {
tracing::warn!("Failed to persist model to DB: {}", e);
} else {
tracing::debug!(user_id, "Persisted selected_model to DB: {}", model);
tracing::debug!(
user_id = tenant.user_id(),
"Persisted selected_model to DB: {}",
model
);
}
} else {
tracing::warn!("No database store available — model choice will not persist to DB");
src/agent/dispatcher.rs
+22 -17
View File
@@ -42,6 +42,7 @@ impl Agent {
pub(super) async fn run_agentic_loop(
&self,
message: &IncomingMessage,
tenant: crate::tenant::TenantCtx,
session: Arc<Mutex<Session>>,
thread_id: Uuid,
initial_messages: Vec<ChatMessage>,
@@ -163,6 +164,7 @@ impl Agent {
let delegate = ChatDelegate {
agent: self,
tenant,
session: session.clone(),
thread_id,
message,
@@ -235,6 +237,7 @@ impl Agent {
/// auth intercept, and cost tracking.
struct ChatDelegate<'a> {
agent: &'a Agent,
tenant: crate::tenant::TenantCtx,
session: Arc<Mutex<Session>>,
thread_id: Uuid,
message: &'a IncomingMessage,
@@ -332,12 +335,7 @@ impl<'a> LoopDelegate for ChatDelegate<'a> {
iteration: usize,
) -> Result<crate::llm::RespondOutput, Error> {
// Enforce cost guardrails before the LLM call (global + per-user)
if let Err(limit) = self
.agent
.cost_guard()
.check_allowed_for_user(&self.message.user_id)
.await
{
if let Err(limit) = self.tenant.check_cost_allowed().await {
return Err(crate::error::LlmError::InvalidResponse {
provider: "agent".to_string(),
reason: limit.to_string(),
@@ -348,12 +346,10 @@ impl<'a> LoopDelegate for ChatDelegate<'a> {
// Apply per-user model override from settings (first iteration only
// to avoid repeated DB lookups within the same agentic loop).
// Uses "selected_model" — the same key the /model command persists to
// via SettingsStore (per-user scoped).
// via SettingsStore (per-user scoped via TenantScope).
if iteration == 0
&& let Some(store) = self.agent.store()
&& let Ok(Some(value)) = store
.get_setting(&self.message.user_id, "selected_model")
.await
&& let Some(store) = self.tenant.store()
&& let Ok(Some(value)) = store.get_setting("selected_model").await
&& let Some(model) = value.as_str()
{
let model = model.trim();
@@ -411,10 +407,8 @@ impl<'a> LoopDelegate for ChatDelegate<'a> {
let read_discount = self.agent.llm().cache_read_discount();
let write_multiplier = self.agent.llm().cache_write_multiplier();
let call_cost = self
.agent
.cost_guard()
.record_llm_call_for_user(
&self.message.user_id,
.tenant
.record_llm_call(
&model_name,
output.usage.input_tokens,
output.usage.output_tokens,
@@ -1267,6 +1261,7 @@ mod tests {
sandbox_readiness: crate::agent::routine_engine::SandboxReadiness::DisabledByConfig,
builder: None,
llm_backend: "nearai".to_string(),
tenant_rates: Arc::new(crate::tenant::TenantRateRegistry::new(4, 3)),
};
Agent::new(
@@ -1288,6 +1283,8 @@ mod tests {
default_timezone: "UTC".to_string(),
max_tokens_per_job: 0,
multi_tenant: false,
max_llm_concurrent_per_user: None,
max_jobs_concurrent_per_user: None,
},
deps,
Arc::new(ChannelManager::new()),
@@ -2137,6 +2134,7 @@ mod tests {
sandbox_readiness: crate::agent::routine_engine::SandboxReadiness::DisabledByConfig,
builder: None,
llm_backend: "nearai".to_string(),
tenant_rates: Arc::new(crate::tenant::TenantRateRegistry::new(4, 3)),
};
Agent::new(
@@ -2158,6 +2156,8 @@ mod tests {
default_timezone: "UTC".to_string(),
max_tokens_per_job: 0,
multi_tenant: false,
max_llm_concurrent_per_user: None,
max_jobs_concurrent_per_user: None,
},
deps,
Arc::new(ChannelManager::new()),
@@ -2192,13 +2192,14 @@ mod tests {
let message = IncomingMessage::new("test", "test-user", "do something");
let initial_messages = vec![ChatMessage::user("do something")];
let tenant = agent.tenant_ctx("test-user").await;
// The dispatcher must terminate within 5 seconds. If there is an
// infinite loop bug (e.g., index not advancing on tool failure), the
// timeout will fire and the test will fail.
let result = tokio::time::timeout(
Duration::from_secs(5),
agent.run_agentic_loop(&message, session, thread_id, initial_messages),
agent.run_agentic_loop(&message, tenant, session, thread_id, initial_messages),
)
.await;
@@ -2260,6 +2261,7 @@ mod tests {
sandbox_readiness: crate::agent::routine_engine::SandboxReadiness::DisabledByConfig,
builder: None,
llm_backend: "nearai".to_string(),
tenant_rates: Arc::new(crate::tenant::TenantRateRegistry::new(4, 3)),
};
Agent::new(
@@ -2281,6 +2283,8 @@ mod tests {
default_timezone: "UTC".to_string(),
max_tokens_per_job: 0,
multi_tenant: false,
max_llm_concurrent_per_user: None,
max_jobs_concurrent_per_user: None,
},
deps,
Arc::new(ChannelManager::new()),
@@ -2300,13 +2304,14 @@ mod tests {
let message = IncomingMessage::new("test", "test-user", "keep calling tools");
let initial_messages = vec![ChatMessage::user("keep calling tools")];
let tenant = agent.tenant_ctx("test-user").await;
// Even with an LLM that always wants to call tools, the dispatcher
// must terminate within the timeout thanks to force_text at
// max_tool_iterations.
let result = tokio::time::timeout(
Duration::from_secs(5),
agent.run_agentic_loop(&message, session, thread_id, initial_messages),
agent.run_agentic_loop(&message, tenant, session, thread_id, initial_messages),
)
.await;
src/agent/heartbeat.rs
+10 -10
View File
@@ -31,8 +31,8 @@ use chrono_tz::Tz;
use tokio::sync::mpsc;
use crate::channels::OutgoingResponse;
use crate::db::Database;
use crate::llm::{ChatMessage, CompletionRequest, LlmProvider, Reasoning};
use crate::tenant::AdminScope;
use crate::workspace::Workspace;
use crate::workspace::hygiene::HygieneConfig;
@@ -182,7 +182,7 @@ pub struct HeartbeatRunner {
workspace: Arc<Workspace>,
llm: Arc<dyn LlmProvider>,
response_tx: Option<mpsc::Sender<OutgoingResponse>>,
store: Option<Arc<dyn Database>>,
store: Option<AdminScope>,
consecutive_failures: u32,
}
@@ -211,8 +211,8 @@ impl HeartbeatRunner {
self
}
/// Set the database store for persistent heartbeat conversations.
pub fn with_store(mut self, store: Arc<dyn Database>) -> Self {
/// Set the admin-scoped database store for persistent heartbeat conversations.
pub fn with_store(mut self, store: AdminScope) -> Self {
self.store = Some(store);
self
}
@@ -497,7 +497,7 @@ pub fn spawn_heartbeat(
workspace: Arc<Workspace>,
llm: Arc<dyn LlmProvider>,
response_tx: Option<mpsc::Sender<OutgoingResponse>>,
store: Option<Arc<dyn Database>>,
store: Option<AdminScope>,
) -> tokio::task::JoinHandle<()> {
let mut runner = HeartbeatRunner::new(config, hygiene_config, workspace, llm);
if let Some(tx) = response_tx {
@@ -521,7 +521,7 @@ pub fn spawn_multi_user_heartbeat(
hygiene_config: HygieneConfig,
llm: Arc<dyn LlmProvider>,
response_tx: Option<mpsc::Sender<OutgoingResponse>>,
store: Arc<dyn Database>,
store: AdminScope,
) -> tokio::task::JoinHandle<()> {
tokio::spawn(async move {
if !config.enabled {
@@ -586,7 +586,7 @@ pub fn spawn_multi_user_heartbeat(
continue;
}
let workspace = Arc::new(Workspace::new_with_db(user_id, store.clone()));
let workspace = Arc::new(Workspace::new_with_db(user_id, Arc::clone(store.db())));
// Run memory hygiene per user (same as single-user heartbeat).
let hygiene_ws = Arc::clone(&workspace);
@@ -617,14 +617,14 @@ pub fn spawn_multi_user_heartbeat(
let hyg = hygiene_config.clone();
let llm_clone = llm.clone();
let tx = response_tx.clone();
let st = store.clone();
let admin = store.clone();
join_set.spawn(async move {
let mut runner = HeartbeatRunner::new(cfg, hyg, workspace, llm_clone);
if let Some(tx) = tx {
runner = runner.with_response_channel(tx);
}
runner = runner.with_store(st);
runner = runner.with_store(admin);
let result = runner.check_heartbeat().await;
if let HeartbeatResult::NeedsAttention(msg) = &result {
@@ -903,7 +903,7 @@ mod tests {
Arc<crate::workspace::Workspace>,
Arc<dyn crate::llm::LlmProvider>,
Option<tokio::sync::mpsc::Sender<crate::channels::OutgoingResponse>>,
Option<Arc<dyn crate::db::Database>>,
Option<AdminScope>,
) -> tokio::task::JoinHandle<()> = spawn_heartbeat;
let _ = _fn_ptr;
}
src/agent/routine_engine.rs
+14 -8
View File
@@ -27,12 +27,12 @@ use crate::agent::routine::{
use crate::channels::{IncomingMessage, OutgoingResponse};
use crate::config::RoutineConfig;
use crate::context::{JobContext, JobState};
use crate::db::Database;
use crate::error::RoutineError;
use crate::extensions::ExtensionManager;
use crate::llm::{
ChatMessage, CompletionRequest, FinishReason, LlmProvider, ToolCall, ToolCompletionRequest,
};
use crate::tenant::AdminScope;
use crate::tools::{
ToolError, ToolRegistry, autonomous_allowed_tool_names, autonomous_unavailable_message,
prepare_tool_params,
@@ -93,7 +93,7 @@ pub(crate) fn routine_matches_message(routine: &Routine, message: &IncomingMessa
/// The routine execution engine.
pub struct RoutineEngine {
config: RoutineConfig,
store: Arc<dyn Database>,
store: AdminScope,
llm: Arc<dyn LlmProvider>,
workspace: Arc<Workspace>,
/// Sender for notifications (routed to channel manager).
@@ -122,7 +122,7 @@ impl RoutineEngine {
#[allow(clippy::too_many_arguments)]
pub fn new(
config: RoutineConfig,
store: Arc<dyn Database>,
store: AdminScope,
llm: Arc<dyn LlmProvider>,
workspace: Arc<Workspace>,
notify_tx: mpsc::Sender<OutgoingResponse>,
@@ -741,7 +741,10 @@ impl RoutineEngine {
let routine_workspace = if routine.user_id == self.workspace.user_id() {
self.workspace.clone()
} else {
Arc::new(Workspace::new_with_db(&routine.user_id, self.store.clone()))
Arc::new(Workspace::new_with_db(
&routine.user_id,
Arc::clone(self.store.db()),
))
};
// Execute inline for manual triggers (caller wants to wait)
@@ -873,7 +876,10 @@ impl RoutineEngine {
let routine_workspace = if routine.user_id == self.workspace.user_id() {
self.workspace.clone()
} else {
Arc::new(Workspace::new_with_db(&routine.user_id, self.store.clone()))
Arc::new(Workspace::new_with_db(
&routine.user_id,
Arc::clone(self.store.db()),
))
};
let engine = EngineContext {
@@ -933,7 +939,7 @@ impl RoutineEngine {
/// an active state (Pending/InProgress/Stuck). Maps the final `JobState` to
/// a `RunStatus` for the routine run.
struct FullJobWatcher {
store: Arc<dyn Database>,
store: AdminScope,
job_id: Uuid,
routine_name: String,
}
@@ -944,7 +950,7 @@ impl FullJobWatcher {
/// Safety ceiling: 24 hours, derived from POLL_INTERVAL.
const MAX_POLLS: u32 = (24 * 60 * 60) / Self::POLL_INTERVAL.as_secs() as u32;
fn new(store: Arc<dyn Database>, job_id: Uuid, routine_name: String) -> Self {
fn new(store: AdminScope, job_id: Uuid, routine_name: String) -> Self {
Self {
store,
job_id,
@@ -1016,7 +1022,7 @@ impl FullJobWatcher {
/// Shared context passed to the execution function.
struct EngineContext {
config: RoutineConfig,
store: Arc<dyn Database>,
store: AdminScope,
llm: Arc<dyn LlmProvider>,
workspace: Arc<Workspace>,
notify_tx: mpsc::Sender<OutgoingResponse>,
src/agent/scheduler.rs
+5 -3
View File
@@ -11,12 +11,12 @@ use uuid::Uuid;
use crate::agent::task::{Task, TaskContext, TaskOutput};
use crate::config::AgentConfig;
use crate::context::{ContextManager, JobContext, JobState};
use crate::db::Database;
use crate::error::{Error, JobError};
use crate::extensions::ExtensionManager;
use crate::hooks::HookRegistry;
use crate::llm::LlmProvider;
use crate::safety::SafetyLayer;
use crate::tenant::AdminScope;
use crate::tools::{
ApprovalContext, ToolRegistry, autonomous_allowed_tool_names, autonomous_unavailable_error,
prepare_tool_params,
@@ -52,7 +52,7 @@ struct ScheduledSubtask {
pub struct SchedulerDeps {
pub tools: Arc<ToolRegistry>,
pub extension_manager: Option<Arc<ExtensionManager>>,
pub store: Option<Arc<dyn Database>>,
pub store: Option<AdminScope>,
pub hooks: Arc<HookRegistry>,
}
@@ -64,7 +64,7 @@ pub struct Scheduler {
safety: Arc<SafetyLayer>,
tools: Arc<ToolRegistry>,
extension_manager: Option<Arc<ExtensionManager>>,
store: Option<Arc<dyn Database>>,
store: Option<AdminScope>,
hooks: Arc<HookRegistry>,
/// SSE manager for live job event streaming.
sse_tx: Option<Arc<crate::channels::web::sse::SseManager>>,
@@ -786,6 +786,8 @@ mod tests {
default_timezone: "UTC".to_string(),
max_tokens_per_job,
multi_tenant: false,
max_llm_concurrent_per_user: None,
max_jobs_concurrent_per_user: None,
};
let cm = Arc::new(ContextManager::new(5));
let llm: Arc<dyn LlmProvider> = Arc::new(StubLlm);
src/agent/self_repair.rs
+5 -5
View File
@@ -8,8 +8,8 @@ use chrono::{DateTime, Utc};
use uuid::Uuid;
use crate::context::{ContextManager, JobState};
use crate::db::Database;
use crate::error::RepairError;
use crate::tenant::AdminScope;
use crate::tools::{BuildRequirement, Language, SoftwareBuilder, SoftwareType, ToolRegistry};
/// A job that has been detected as stuck.
@@ -69,7 +69,7 @@ pub struct DefaultSelfRepair {
/// Jobs in `InProgress` longer than this are treated as stuck.
stuck_threshold: Duration,
max_repair_attempts: u32,
store: Option<Arc<dyn Database>>,
store: Option<AdminScope>,
builder: Option<Arc<dyn SoftwareBuilder>>,
tools: Option<Arc<ToolRegistry>>,
}
@@ -91,8 +91,8 @@ impl DefaultSelfRepair {
}
}
/// Add a Store for tool failure tracking.
pub fn with_store(mut self, store: Arc<dyn Database>) -> Self {
/// Add an admin-scoped store for tool failure tracking.
pub fn with_store(mut self, store: AdminScope) -> Self {
self.store = Some(store);
self
}
@@ -806,7 +806,7 @@ mod tests {
// Create self-repair with zero threshold (detect immediately),
// wired with store, builder, and tools.
let repair = DefaultSelfRepair::new(Arc::clone(&cm), Duration::from_secs(0), 3)
.with_store(Arc::clone(&db))
.with_store(crate::tenant::AdminScope::new(Arc::clone(&db)))
.with_builder(
Arc::clone(&builder) as Arc<dyn crate::tools::SoftwareBuilder>,
tools,
src/agent/thread_ops.rs
+10 -3
View File
@@ -175,6 +175,7 @@ impl Agent {
pub(super) async fn process_user_input(
&self,
message: &IncomingMessage,
tenant: crate::tenant::TenantCtx,
session: Arc<Mutex<Session>>,
thread_id: Uuid,
content: &str,
@@ -351,7 +352,7 @@ impl Agent {
if let Some(intent) = self.router.route_command(&temp_message) {
// Explicit command like /status, /job, /list - handle directly
return self.handle_job_or_command(intent, message).await;
return self.handle_job_or_command(intent, message, &tenant).await;
}
// Natural language goes through the agentic loop
@@ -462,7 +463,7 @@ impl Agent {
// Run the agentic tool execution loop
let result = self
.run_agentic_loop(message, session.clone(), thread_id, turn_messages)
.run_agentic_loop(message, tenant, session.clone(), thread_id, turn_messages)
.await;
// Re-acquire lock and check if interrupted
@@ -1444,7 +1445,13 @@ impl Agent {
// Continue the agentic loop (a tool was already executed this turn)
let result = self
.run_agentic_loop(message, session.clone(), thread_id, context_messages)
.run_agentic_loop(
message,
self.tenant_ctx(&message.user_id).await,
session.clone(),
thread_id,
context_messages,
)
.await;
// Handle the result