Add event-triggered routines and workflow skill templates (#756)

* Add event-triggered routines and workflow skill templates

* fix(ci): secrets can't be used in step if conditions [skip-regression-check] (#787)

GitHub Actions step-level `if:` doesn't have access to `secrets` context.
Replace `if: secrets.X != ''` with `continue-on-error: true` and let
the Set token step handle the fallback.

Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* fix(ci): clean up staging pipeline — remove hacks, skip redundant checks [skip-regression-check] (#794)

- Remove continue-on-error from staging-ci.yml app token steps (secrets are configured)
- Skip test.yml and code_style.yml on PRs targeting staging (staging-ci.yml
  already runs tests before promoting, promotion PR gets full CI on main)
- Allow ironclaw-ci[bot] in Claude Code review for bot-created promotion PRs

Co-authored-by: Claude Opus 4.6 <[email protected]>

* fix: address PR review feedback for event_emit security and quality

Security fixes:
- Require approval (UnlessAutoApproved) for event_emit, matching routine_fire
- Enable sanitization on event_emit payload (external JSON reaches LLM)
- Remove user_id parameter from event_emit to prevent IDOR — always use ctx.user_id

Correctness fixes:
- Rename source → event_source in event_emit for consistency with routine_create
- Use json_value_as_filter_string for filter parsing (handles numbers/booleans)
- Case-insensitive matching for event source and event_type
- Add debug logging for missing filter keys in payload
- Fix skill_install_routine_webhook_sim test missing .with_skills()
- Fix schema_validator test for event_emit payload properties

Code quality:
- Move EventEmitTool struct/impl after RoutineHistoryTool (fix split layout)
- Deduplicate routine_to_info into RoutineInfo::from_routine in types.rs
- Add test section headers in e2e_routine_heartbeat.rs
- Clarify event_emit description to specify system_event routines only

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix(ci): run fmt + clippy on staging PRs, skip Windows clippy [skip-regression-check] (#802)

- Remove branches:[main] filter from code_style.yml so it runs on all PRs
- Gate clippy-windows with `if: github.base_ref == 'main'` (skip on staging PRs)
- Update rollup job to allow skipped clippy-windows
- Simplify claude-review.yml to only trigger on labeled event (avoids duplicate runs)

Co-authored-by: Claude Opus 4.6 <[email protected]>

* feat: persist user_id in save_job and expose job_id on routine runs (#709)

* feat: persist worker events to DB and fix activity tab rendering

In-process Worker (used by Scheduler::dispatch_job) now persists events
via save_job_event at key execution points: plan creation, LLM
responses, tool_use, tool_result, and job completion/failure/stuck.
Event data shapes match the container worker format so the gateway
activity tab renders them correctly.

Frontend: tool_result errors now show a red X icon with danger styling
instead of a silent empty output. The result event falls back to the
error field when message is absent.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat: wire RoutineEngine into gateway for direct manual trigger firing

Replace the message-channel hack in routines_trigger_handler with a
direct call to RoutineEngine::fire_manual(), ensuring FullJob routines
dispatch correctly when triggered from the web UI. Inject the engine
into GatewayState from Agent::run after construction.

Also persists user_id in save_job for both PG and libSQL backends,
removes the source='sandbox' filter so all jobs are visible, and
exposes job_id on RoutineRunInfo for the frontend job link.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: remove stale gateway_state argument from Agent::new test call sites

The gateway_state parameter was removed from Agent::new during rebase
(replaced by post-construction set_routine_engine_slot), but three test
call sites still passed the extra None argument.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: address PR review — restore sandbox source filter, remove blank lines

- Revert removal of `source = 'sandbox'` filter in all SandboxStore
  queries (8 sites across PG and libSQL). Sandbox-specific APIs should
  stay scoped to sandbox jobs; unified job listing for the Jobs tab
  should use a separate query path.
- Remove extra blank lines in agent_loop.rs and worker.rs that caused
  formatting CI failure.

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: address review — regenerate Cargo.lock, add user_id regression test

- Regenerate Cargo.lock from main's lockfile to eliminate dependency
  version downgrades (anyhow, syn, etc.) that were churn from rebase.
- Add regression test verifying user_id round-trips through save_job
  and get_job in the libSQL backend.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* style: remove trailing blank line in libsql jobs.rs

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* test: add Postgres-side regression test for user_id persistence in save_job

Mirrors the existing libSQL test (test_save_job_persists_user_id) for the
Postgres backend. Gated behind #[cfg(feature = "postgres")] + #[ignore]
since it requires a running PostgreSQL instance (integration tier).

Co-Authored-By: Claude Opus 4.6 <[email protected]>

---------

Co-authored-by: Claude Opus 4.6 <[email protected]>

* fix: make routine_system_event_emit test create routine before emitting

- Add routine_create step to trace fixture so event_emit has a matching
  routine to fire
- Assert fired_routines > 0, not just key presence (Copilot review)
- Add .with_auto_approve_tools(true) since event_emit now requires approval

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: renumber test headers after system_event test insertion

Test 4 was duplicated (routine_cooldown and heartbeat_findings).
Renumber heartbeat_findings to Test 5 and heartbeat_empty_skip to Test 6.

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: merge staging and add missing RoutineEngine args in test

RoutineEngine::new on staging requires `tools` and `safety` params.
Update system_event_trigger_matches_and_filters test to pass them.

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: address new Copilot review comments

- Add .with_auto_approve_tools(true) to skill_install_routine_webhook_sim
  test so event_emit doesn't block on approval
- Fix module-level doc comment for event_emit to specify system_event trigger

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: deduplicate json_value_as_string helper

Remove private `json_value_as_string` from routine_engine.rs and use
the identical public `json_value_as_filter_string` from routine.rs,
eliminating divergence risk. (Copilot review)

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 <[email protected]>

---------

Co-authored-by: Henry Park <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
This commit is contained in:
Illia Polosukhin
2026-03-10 11:08:04 -07:00
committed by GitHub
co-authored by Henry Park Claude Sonnet 4.6
parent e8f8ec06e3
commit 6e1ed939cc
20 changed files with 1090 additions and 150 deletions
@@ -0,0 +1,80 @@
---
name: ironclaw-workflow-orchestrator
description: "Install and operate a full GitHub issue-to-merge workflow in IronClaw using event-driven and cron routines. Use when setting up or tuning autonomous project orchestration: issue intake, planning, maintainer feedback handling, branch/PR execution, CI/comment follow-up, batched staging review every 8 hours, and memory updates from merge outcomes."
---
# IronClaw Workflow Orchestrator
## Overview
Use this skill to install and maintain a complete project workflow as routines, not core code changes. It maps GitHub webhook events plus scheduled checks into plan/update/implement/review/merge loops with explicit staging-batch analysis.
## Workflow
1. Gather workflow parameters.
2. Verify runtime prerequisites.
3. Install or update routine set from templates.
4. Run a dry test with `event_emit`.
5. Monitor outcomes and tune prompts/filters.
## Parameters
Collect these values before creating routines:
- `repository`: `owner/repo` (required)
- `maintainers`: GitHub handles allowed to trigger implement/replan actions
- `staging_branch`: default `staging`
- `main_branch`: default `main`
- `batch_interval_hours`: default `8`
- `implementation_label`: default `autonomous-impl`
## Prerequisites
Before installing routines, verify:
- Routines system enabled.
- GitHub tool authenticated (for issue/PR/comment/status operations).
- Events are emitted via `event_emit` tool calls (a future HTTP webhook ingestion endpoint is planned but not yet available).
## Install Procedure
1. Open [`workflow-routines.md`](references/workflow-routines.md).
2. For each template block:
- replace placeholders (`{{repository}}`, `{{maintainers}}`, branch names)
- call `routine_create`
3. If a routine already exists:
- use `routine_update` instead of creating duplicates
- keep names stable so long-lived metrics/history stay intact
4. Confirm install with `routine_list` and `routine_history`.
## Routine Set
Install these routines:
- `wf-issue-plan`: on `issue.opened` or `issue.reopened`, generate implementation plan comment/checklist.
- `wf-maintainer-comment-gate`: on maintainer comments, decide update-plan vs start implementation.
- `wf-pr-monitor-loop`: on PR open/sync/review-comment/review, address feedback and refresh branch.
- `wf-ci-fix-loop`: on CI status/check failures, apply fixes and push updates.
- `wf-staging-batch-review`: every 8h, review ready PRs, merge into staging, run deep batch correctness analysis, fix findings, then merge staging -> main.
- `wf-learning-memory`: on merged PRs, extract mistakes/lessons and write to shared memory.
## Event Filters
Prefer top-level filters for stability:
- `repository` (string)
- `sender` (string)
- `issue_number` / `pr_number`
- `ci_status`, `ci_conclusion`
- `review_state`, `comment_author`
Use narrow filters to avoid accidental triggers across repos.
## Operating Rules
- All implementation work must occur on non-main branches.
- PR loop must resolve both human and AI review comments.
- On conflicts with `origin/main`, refresh branch before continuing.
- Staging-batch routine is the only path for bulk correctness verification before mainline merge.
- Memory update routine runs only after successful merge.
## Validation
After install, run:
1. `event_emit` with a synthetic `issue.opened` payload for the target repo.
2. Confirm at least one routine fired.
3. Check corresponding `routine_history` entries.
4. Confirm no unrelated routines fired.
## When To Update Templates
Update this skill when:
- GitHub event names/payload fields change.
- Team review policy changes (e.g., staging cadence, maintainer gates).
- New CI policy requires different failure routing.
@@ -0,0 +1,4 @@
interface:
display_name: "IronClaw Workflow Orchestrator"
short_description: "Install and run event-driven GitHub workflow routines"
default_prompt: "Set up the full issue-to-merge workflow using routines and event triggers."
@@ -0,0 +1,128 @@
# Workflow Routine Templates
Replace `{{...}}` placeholders before use.
## 1) Issue -> Plan
```json
{
"name": "wf-issue-plan",
"description": "Create implementation plan when a new issue arrives",
"trigger_type": "system_event",
"event_source": "github",
"event_type": "issue.opened",
"event_filters": {
"repository": "{{repository}}"
},
"action_type": "full_job",
"prompt": "For issue #{{issue_number}} in {{repository}}, produce a concrete implementation plan with milestones, edge cases, and tests. Post/update an issue comment with the plan.",
"cooldown_secs": 30
}
```
## 2) Maintainer Comment Gate (Update Plan vs Implement)
Trigger per-maintainer by creating one routine per handle, or maintain a shared author convention.
```json
{
"name": "wf-maintainer-comment-gate-{{maintainer}}",
"description": "React to maintainer guidance comments on issues/PRs",
"trigger_type": "system_event",
"event_source": "github",
"event_type": "pr.comment.created",
"event_filters": {
"repository": "{{repository}}",
"comment_author": "{{maintainer}}"
},
"action_type": "full_job",
"prompt": "Read the maintainer comment and decide: update plan or start/continue implementation. If plan changes are requested, edit the plan artifact first. If implementation is requested, continue on the feature branch and update PR status/comment.",
"cooldown_secs": 20
}
```
## 3) PR Monitor Loop
```json
{
"name": "wf-pr-monitor-loop",
"description": "Keep PR healthy: address review comments and refresh branch",
"trigger_type": "system_event",
"event_source": "github",
"event_type": "pr.synchronize",
"event_filters": {
"repository": "{{repository}}"
},
"action_type": "full_job",
"prompt": "For PR #{{pr_number}}, collect open review comments and unresolved threads, apply fixes, push branch updates, and summarize remaining blockers. If conflict with {{main_branch}}, rebase/merge from origin/{{main_branch}} and resolve safely.",
"cooldown_secs": 20
}
```
## 4) CI Failure Fix Loop
```json
{
"name": "wf-ci-fix-loop",
"description": "Fix failing CI checks on active PRs",
"trigger_type": "system_event",
"event_source": "github",
"event_type": "ci.check_run.completed",
"event_filters": {
"repository": "{{repository}}",
"ci_conclusion": "failure"
},
"action_type": "full_job",
"prompt": "Find failing check details for PR #{{pr_number}}, implement minimal safe fixes, rerun or await CI, and post concise status updates. Prioritize deterministic and test-backed fixes.",
"cooldown_secs": 20
}
```
## 5) Staging Batch Review (Every 8h)
```json
{
"name": "wf-staging-batch-review",
"description": "Batch correctness review through staging, then merge to main",
"trigger_type": "cron",
"schedule": "0 0 */{{batch_interval_hours}} * * *",
"action_type": "full_job",
"prompt": "Every cycle: list ready PRs, merge ready ones into {{staging_branch}}, run deep correctness analysis in batch, fix discovered issues on affected branches, ensure CI green, then merge {{staging_branch}} into {{main_branch}} if clean.",
"cooldown_secs": 120
}
```
## 6) Post-Merge Learning -> Common Memory
```json
{
"name": "wf-learning-memory",
"description": "Capture merge learnings into shared memory",
"trigger_type": "system_event",
"event_source": "github",
"event_type": "pr.closed",
"event_filters": {
"repository": "{{repository}}",
"pr_merged": "true"
},
"action_type": "full_job",
"prompt": "From merged PR #{{pr_number}}, extract preventable mistakes, reviewer themes, CI failure causes, and successful patterns. Write/update a shared memory doc with actionable rules to reduce cycle time and regressions.",
"cooldown_secs": 30
}
```
## Optional: Synthetic Event Test
```json
{
"source": "github",
"event_type": "issue.opened",
"payload": {
"repository": "{{repository}}",
"issue_number": 99999,
"sender": "test-bot"
}
}
```
Use with `event_emit` after routine install.
+1 -1
View File
@@ -21,7 +21,7 @@ Core agent logic. This is the most complex subsystem — read this before workin
| `heartbeat.rs` | Proactive periodic execution. Reads `HEARTBEAT.md`, notifies via channel if findings. |
| `submission.rs` | Parses all user submissions into typed variants before routing. |
| `undo.rs` | Turn-based undo/redo with checkpoints. Checkpoints store message lists (max 20 by default). |
| `routine.rs` | `Routine` types: `Trigger` (cron/event/webhook/manual) + `RoutineAction` (lightweight/full_job) + `RoutineGuardrails`. |
| `routine.rs` | `Routine` types: `Trigger` (cron/event/system_event/manual) + `RoutineAction` (lightweight/full_job) + `RoutineGuardrails`. |
| `routine_engine.rs` | Cron ticker and event matcher. Fires routines when triggers match. Lightweight runs inline; full_job dispatches to `Scheduler`. |
| `task.rs` | Task types for the scheduler: `Job`, `ToolExec`, `Background`. Used by `spawn_subtask` and `spawn_batch`. |
| `cost_guard.rs` | LLM spend and action-rate enforcement. Tracks daily budget (cents) and hourly call rate. Lives in `AgentDeps`. |
+86 -23
View File
@@ -8,7 +8,7 @@
//! ┌──────────┐ ┌─────────┐ ┌──────────────────┐
//! │ Trigger │────▶│ Engine │────▶│ Execution Mode │
//! │ cron/event│ │guardrail│ │lightweight│full_job│
//! │ webhook │ │ check │ └──────────────────┘
//! │ system │ │ check │ └──────────────────┘
//! │ manual │ └─────────┘ │
//! └──────────┘ ▼
//! ┌──────────────┐
@@ -69,12 +69,15 @@ pub enum Trigger {
/// Regex pattern to match against message content.
pattern: String,
},
/// Fire on incoming webhook POST to /hooks/routine/{id}.
Webhook {
/// Optional webhook path suffix (defaults to routine id).
path: Option<String>,
/// Optional shared secret for HMAC validation.
secret: Option<String>,
/// Fire when a structured system event is emitted.
SystemEvent {
/// Event source namespace (e.g. "github", "workflow", "tool").
source: String,
/// Event type within the source (e.g. "issue.opened").
event_type: String,
/// Optional exact-match filters against payload top-level fields.
#[serde(default)]
filters: std::collections::HashMap<String, String>,
},
/// Only fires via tool call or CLI.
Manual,
@@ -86,7 +89,7 @@ impl Trigger {
match self {
Trigger::Cron { .. } => "cron",
Trigger::Event { .. } => "event",
Trigger::Webhook { .. } => "webhook",
Trigger::SystemEvent { .. } => "system_event",
Trigger::Manual => "manual",
}
}
@@ -134,16 +137,39 @@ impl Trigger {
.map(String::from);
Ok(Trigger::Event { channel, pattern })
}
"webhook" => {
let path = config
.get("path")
"system_event" => {
let source = config
.get("source")
.and_then(|v| v.as_str())
.map(String::from);
let secret = config
.get("secret")
.ok_or_else(|| RoutineError::MissingField {
context: "system_event trigger".into(),
field: "source".into(),
})?
.to_string();
let event_type = config
.get("event_type")
.and_then(|v| v.as_str())
.map(String::from);
Ok(Trigger::Webhook { path, secret })
.ok_or_else(|| RoutineError::MissingField {
context: "system_event trigger".into(),
field: "event_type".into(),
})?
.to_string();
let filters = config
.get("filters")
.and_then(|v| v.as_object())
.map(|m| {
m.iter()
.filter_map(|(k, v)| {
json_value_as_filter_string(v).map(|s| (k.clone(), s))
})
.collect()
})
.unwrap_or_default();
Ok(Trigger::SystemEvent {
source,
event_type,
filters,
})
}
"manual" => Ok(Trigger::Manual),
other => Err(RoutineError::UnknownTriggerType {
@@ -163,9 +189,14 @@ impl Trigger {
"pattern": pattern,
"channel": channel,
}),
Trigger::Webhook { path, secret } => serde_json::json!({
"path": path,
"secret": secret,
Trigger::SystemEvent {
source,
event_type,
filters,
} => serde_json::json!({
"source": source,
"event_type": event_type,
"filters": filters,
}),
Trigger::Manual => serde_json::json!({}),
}
@@ -428,6 +459,19 @@ pub struct RoutineRun {
pub created_at: DateTime<Utc>,
}
/// Convert a JSON value to a string for filter storage.
///
/// Handles strings, numbers, and booleans — consistent with the matching
/// logic in `routine_engine::json_value_as_string`.
pub fn json_value_as_filter_string(v: &serde_json::Value) -> Option<String> {
match v {
serde_json::Value::String(s) => Some(s.clone()),
serde_json::Value::Number(n) => Some(n.to_string()),
serde_json::Value::Bool(b) => Some(b.to_string()),
_ => None,
}
}
/// Compute a content hash for event dedup.
pub fn content_hash(content: &str) -> u64 {
let mut hasher = DefaultHasher::new();
@@ -486,6 +530,24 @@ mod tests {
if channel == Some("telegram".to_string()) && pattern == r"deploy\s+\w+"));
}
#[test]
fn test_system_event_trigger_roundtrip() {
let mut filters = std::collections::HashMap::new();
filters.insert("repo".to_string(), "nearai/ironclaw".to_string());
filters.insert("action".to_string(), "opened".to_string());
let trigger = Trigger::SystemEvent {
source: "github".to_string(),
event_type: "issue".to_string(),
filters: filters.clone(),
};
let json = trigger.to_config_json();
let parsed = Trigger::from_db("system_event", json).expect("parse system_event");
assert!(
matches!(parsed, Trigger::SystemEvent { source, event_type, filters: f }
if source == "github" && event_type == "issue" && f == filters)
);
}
#[test]
fn test_action_lightweight_roundtrip() {
let action = RoutineAction::Lightweight {
@@ -623,12 +685,13 @@ mod tests {
"event"
);
assert_eq!(
Trigger::Webhook {
path: None,
secret: None
Trigger::SystemEvent {
source: String::new(),
event_type: String::new(),
filters: std::collections::HashMap::new(),
}
.type_tag(),
"webhook"
"system_event"
);
assert_eq!(Trigger::Manual.type_tag(), "manual");
}
+103 -6
View File
@@ -35,6 +35,11 @@ use crate::safety::SafetyLayer;
use crate::tools::{ApprovalContext, ApprovalRequirement, ToolError, ToolRegistry, redact_params};
use crate::workspace::Workspace;
enum EventMatcher {
Message { routine: Routine, regex: Regex },
System { routine: Routine },
}
/// The routine execution engine.
pub struct RoutineEngine {
config: RoutineConfig,
@@ -45,8 +50,8 @@ pub struct RoutineEngine {
notify_tx: mpsc::Sender<OutgoingResponse>,
/// Currently running routine count (across all routines).
running_count: Arc<AtomicUsize>,
/// Compiled event regex cache: routine_id -> compiled regex.
event_cache: Arc<RwLock<Vec<(Uuid, Routine, Regex)>>>,
/// Cached matchers for all event-driven routines.
event_cache: Arc<RwLock<Vec<EventMatcher>>>,
/// Scheduler for dispatching jobs (FullJob mode).
scheduler: Option<Arc<Scheduler>>,
/// Tool registry for lightweight routine tool execution.
@@ -87,9 +92,12 @@ impl RoutineEngine {
Ok(routines) => {
let mut cache = Vec::new();
for routine in routines {
if let Trigger::Event { ref pattern, .. } = routine.trigger {
match Regex::new(pattern) {
Ok(re) => cache.push((routine.id, routine.clone(), re)),
match &routine.trigger {
Trigger::Event { pattern, .. } => match Regex::new(pattern) {
Ok(re) => cache.push(EventMatcher::Message {
routine: routine.clone(),
regex: re,
}),
Err(e) => {
tracing::warn!(
routine = %routine.name,
@@ -97,7 +105,13 @@ impl RoutineEngine {
pattern, e
);
}
},
Trigger::SystemEvent { .. } => {
cache.push(EventMatcher::System {
routine: routine.clone(),
});
}
_ => {}
}
}
let count = cache.len();
@@ -118,7 +132,11 @@ impl RoutineEngine {
let cache = self.event_cache.read().await;
let mut fired = 0;
for (_, routine, re) in cache.iter() {
for matcher in cache.iter() {
let (routine, re) = match matcher {
EventMatcher::Message { routine, regex } => (routine, regex),
EventMatcher::System { .. } => continue,
};
// Channel filter
if let Trigger::Event {
channel: Some(ch), ..
@@ -159,6 +177,85 @@ impl RoutineEngine {
fired
}
/// Emit a structured event to system-event routines.
///
/// Returns the number of routines that were fired.
pub async fn emit_system_event(
&self,
source: &str,
event_type: &str,
payload: &serde_json::Value,
user_id: Option<&str>,
) -> usize {
let cache = self.event_cache.read().await;
let mut fired = 0;
for matcher in cache.iter() {
let routine = match matcher {
EventMatcher::System { routine } => routine,
EventMatcher::Message { .. } => continue,
};
let Trigger::SystemEvent {
source: expected_source,
event_type: expected_event,
filters,
} = &routine.trigger
else {
continue;
};
if !expected_source.eq_ignore_ascii_case(source)
|| !expected_event.eq_ignore_ascii_case(event_type)
{
continue;
}
if let Some(uid) = user_id
&& routine.user_id != uid
{
continue;
}
let mut matched = true;
for (key, expected) in filters {
let Some(actual) = payload.get(key).and_then(crate::agent::routine::json_value_as_filter_string) else {
tracing::debug!(routine = %routine.name, filter_key = %key, "Filter key not found in payload");
matched = false;
break;
};
if !actual.eq_ignore_ascii_case(expected) {
matched = false;
break;
}
}
if !matched {
continue;
}
if !self.check_cooldown(routine) {
tracing::debug!(routine = %routine.name, "Skipped: cooldown active");
continue;
}
if !self.check_concurrent(routine).await {
tracing::debug!(routine = %routine.name, "Skipped: max concurrent reached");
continue;
}
if self.running_count.load(Ordering::Relaxed) >= self.config.max_concurrent_routines {
tracing::warn!(routine = %routine.name, "Skipped: global max concurrent reached");
continue;
}
let detail = truncate(&format!("{source}:{event_type}"), 200);
self.spawn_fire(routine.clone(), "system_event", Some(detail));
fired += 1;
}
fired
}
/// Check all due cron routines and fire them. Called by the cron ticker.
pub async fn check_cron_triggers(&self) {
let routines = match self.store.list_due_cron_routines().await {
+1 -49
View File
@@ -27,7 +27,7 @@ pub async fn routines_list_handler(
.await
.map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
let items: Vec<RoutineInfo> = routines.iter().map(routine_to_info).collect();
let items: Vec<RoutineInfo> = routines.iter().map(RoutineInfo::from_routine).collect();
Ok(Json(RoutineListResponse { routines: items }))
}
@@ -263,54 +263,6 @@ pub async fn routines_runs_handler(
})))
}
/// Convert a Routine to the trimmed RoutineInfo for list display.
fn routine_to_info(r: &crate::agent::routine::Routine) -> RoutineInfo {
let (trigger_type, trigger_summary) = match &r.trigger {
crate::agent::routine::Trigger::Cron { schedule, .. } => {
("cron".to_string(), format!("cron: {}", schedule))
}
crate::agent::routine::Trigger::Event {
pattern, channel, ..
} => {
let ch = channel.as_deref().unwrap_or("any");
("event".to_string(), format!("on {} /{}/", ch, pattern))
}
crate::agent::routine::Trigger::Webhook { path, .. } => {
let p = path.as_deref().unwrap_or("/");
("webhook".to_string(), format!("webhook: {}", p))
}
crate::agent::routine::Trigger::Manual => ("manual".to_string(), "manual only".to_string()),
};
let action_type = match &r.action {
crate::agent::routine::RoutineAction::Lightweight { .. } => "lightweight",
crate::agent::routine::RoutineAction::FullJob { .. } => "full_job",
};
let status = if !r.enabled {
"disabled"
} else if r.consecutive_failures > 0 {
"failing"
} else {
"active"
};
RoutineInfo {
id: r.id,
name: r.name.clone(),
description: r.description.clone(),
enabled: r.enabled,
trigger_type,
trigger_summary,
action_type: action_type.to_string(),
last_run_at: r.last_run_at.map(|dt| dt.to_rfc3339()),
next_fire_at: r.next_fire_at.map(|dt| dt.to_rfc3339()),
run_count: r.run_count,
consecutive_failures: r.consecutive_failures,
status: status.to_string(),
}
}
/// Map `RoutineError` variants to appropriate HTTP status codes.
fn routine_error_status(err: &RoutineError) -> StatusCode {
match err {
+1 -49
View File
@@ -1936,7 +1936,7 @@ async fn routines_list_handler(
.await
.map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
let items: Vec<RoutineInfo> = routines.iter().map(routine_to_info).collect();
let items: Vec<RoutineInfo> = routines.iter().map(RoutineInfo::from_routine).collect();
Ok(Json(RoutineListResponse { routines: items }))
}
@@ -2180,54 +2180,6 @@ async fn routines_runs_handler(
})))
}
/// Convert a Routine to the trimmed RoutineInfo for list display.
fn routine_to_info(r: &crate::agent::routine::Routine) -> RoutineInfo {
let (trigger_type, trigger_summary) = match &r.trigger {
crate::agent::routine::Trigger::Cron { schedule, .. } => {
("cron".to_string(), format!("cron: {}", schedule))
}
crate::agent::routine::Trigger::Event {
pattern, channel, ..
} => {
let ch = channel.as_deref().unwrap_or("any");
("event".to_string(), format!("on {} /{}/", ch, pattern))
}
crate::agent::routine::Trigger::Webhook { path, .. } => {
let p = path.as_deref().unwrap_or("/");
("webhook".to_string(), format!("webhook: {}", p))
}
crate::agent::routine::Trigger::Manual => ("manual".to_string(), "manual only".to_string()),
};
let action_type = match &r.action {
crate::agent::routine::RoutineAction::Lightweight { .. } => "lightweight",
crate::agent::routine::RoutineAction::FullJob { .. } => "full_job",
};
let status = if !r.enabled {
"disabled"
} else if r.consecutive_failures > 0 {
"failing"
} else {
"active"
};
RoutineInfo {
id: r.id,
name: r.name.clone(),
description: r.description.clone(),
enabled: r.enabled,
trigger_type,
trigger_summary,
action_type: action_type.to_string(),
last_run_at: r.last_run_at.map(|dt| dt.to_rfc3339()),
next_fire_at: r.next_fire_at.map(|dt| dt.to_rfc3339()),
run_count: r.run_count,
consecutive_failures: r.consecutive_failures,
status: status.to_string(),
}
}
// --- Settings handlers ---
async fn settings_list_handler(
+54
View File
@@ -735,6 +735,60 @@ pub struct RoutineInfo {
pub status: String,
}
impl RoutineInfo {
/// Convert a `Routine` to the trimmed `RoutineInfo` for list display.
pub fn from_routine(r: &crate::agent::routine::Routine) -> Self {
let (trigger_type, trigger_summary) = match &r.trigger {
crate::agent::routine::Trigger::Cron { schedule, .. } => {
("cron".to_string(), format!("cron: {}", schedule))
}
crate::agent::routine::Trigger::Event {
pattern, channel, ..
} => {
let ch = channel.as_deref().unwrap_or("any");
("event".to_string(), format!("on {} /{}/", ch, pattern))
}
crate::agent::routine::Trigger::SystemEvent {
source, event_type, ..
} => (
"system_event".to_string(),
format!("event: {}.{}", source, event_type),
),
crate::agent::routine::Trigger::Manual => {
("manual".to_string(), "manual only".to_string())
}
};
let action_type = match &r.action {
crate::agent::routine::RoutineAction::Lightweight { .. } => "lightweight",
crate::agent::routine::RoutineAction::FullJob { .. } => "full_job",
};
let status = if !r.enabled {
"disabled"
} else if r.consecutive_failures > 0 {
"failing"
} else {
"active"
};
RoutineInfo {
id: r.id,
name: r.name.clone(),
description: r.description.clone(),
enabled: r.enabled,
trigger_type,
trigger_summary,
action_type: action_type.to_string(),
last_run_at: r.last_run_at.map(|dt| dt.to_rfc3339()),
next_fire_at: r.next_fire_at.map(|dt| dt.to_rfc3339()),
run_count: r.run_count,
consecutive_failures: r.consecutive_failures,
status: status.to_string(),
}
}
}
#[derive(Debug, Serialize)]
pub struct RoutineListResponse {
pub routines: Vec<RoutineInfo>,
+1 -1
View File
@@ -167,7 +167,7 @@ impl RoutineStore for LibSqlBackend {
let mut rows = conn
.query(
&format!(
"SELECT {} FROM routines WHERE enabled = 1 AND trigger_type = 'event'",
"SELECT {} FROM routines WHERE enabled = 1 AND trigger_type IN ('event', 'system_event')",
ROUTINE_COLUMNS
),
(),
+1 -1
View File
@@ -1087,7 +1087,7 @@ impl Store {
let conn = self.conn().await?;
let rows = conn
.query(
"SELECT * FROM routines WHERE enabled AND trigger_type = 'event'",
"SELECT * FROM routines WHERE enabled AND trigger_type IN ('event', 'system_event')",
&[],
)
.await?;
+2 -2
View File
@@ -32,8 +32,8 @@ pub use memory::{MemoryReadTool, MemorySearchTool, MemoryTreeTool, MemoryWriteTo
pub use message::MessageTool;
pub use restart::RestartTool;
pub use routine::{
RoutineCreateTool, RoutineDeleteTool, RoutineFireTool, RoutineHistoryTool, RoutineListTool,
RoutineUpdateTool,
EventEmitTool, RoutineCreateTool, RoutineDeleteTool, RoutineFireTool, RoutineHistoryTool,
RoutineListTool, RoutineUpdateTool,
};
pub use secrets_tools::{SecretDeleteTool, SecretListTool};
pub use shell::ShellTool;
+139 -8
View File
@@ -1,12 +1,13 @@
//! LLM-facing tools for managing routines.
//!
//! Six tools let the agent manage routines conversationally:
//! Seven tools let the agent manage routines conversationally:
//! - `routine_create` - Create a new routine
//! - `routine_list` - List all routines with status
//! - `routine_update` - Modify or toggle a routine
//! - `routine_delete` - Remove a routine
//! - `routine_fire` - Manually trigger a routine
//! - `routine_history` - View past runs
//! - `event_emit` - Emit a structured system event to `system_event`-triggered routines
use std::sync::Arc;
use std::time::Duration;
@@ -44,7 +45,7 @@ impl Tool for RoutineCreateTool {
fn description(&self) -> &str {
"Create a new routine (scheduled or event-driven task). \
Supports cron schedules, event pattern matching, webhooks, and manual triggers. \
Supports cron schedules, event pattern matching, system events, and manual triggers. \
Use this when the user wants something to happen periodically or reactively."
}
@@ -62,7 +63,7 @@ impl Tool for RoutineCreateTool {
},
"trigger_type": {
"type": "string",
"enum": ["cron", "event", "webhook", "manual"],
"enum": ["cron", "event", "system_event", "manual"],
"description": "When the routine fires"
},
"schedule": {
@@ -77,6 +78,18 @@ impl Tool for RoutineCreateTool {
"type": "string",
"description": "Optional channel filter for event trigger (e.g. 'telegram')"
},
"event_source": {
"type": "string",
"description": "Event source for system_event triggers (e.g. 'github')"
},
"event_type": {
"type": "string",
"description": "Event type for system_event triggers (e.g. 'issue.opened')"
},
"event_filters": {
"type": "object",
"description": "Optional exact-match filters against payload fields for system_event triggers. Values can be strings, numbers, or booleans."
},
"prompt": {
"type": "string",
"description": "The prompt/instructions for the routine"
@@ -190,10 +203,41 @@ impl Tool for RoutineCreateTool {
pattern: pattern.to_string(),
}
}
"webhook" => Trigger::Webhook {
path: None,
secret: None,
},
"system_event" => {
let source = params
.get("event_source")
.and_then(|v| v.as_str())
.ok_or_else(|| {
ToolError::InvalidParameters(
"system_event trigger requires 'event_source'".to_string(),
)
})?;
let event_type = params
.get("event_type")
.and_then(|v| v.as_str())
.ok_or_else(|| {
ToolError::InvalidParameters(
"system_event trigger requires 'event_type'".to_string(),
)
})?;
let filters = params
.get("event_filters")
.and_then(|v| v.as_object())
.map(|obj| {
obj.iter()
.filter_map(|(k, v)| {
crate::agent::routine::json_value_as_filter_string(v)
.map(|s| (k.to_string(), s))
})
.collect::<std::collections::HashMap<String, String>>()
})
.unwrap_or_default();
Trigger::SystemEvent {
source: source.to_string(),
event_type: event_type.to_string(),
filters,
}
}
"manual" => Trigger::Manual,
other => {
return Err(ToolError::InvalidParameters(format!(
@@ -296,7 +340,10 @@ impl Tool for RoutineCreateTool {
.map_err(|e| ToolError::ExecutionFailed(format!("failed to create routine: {e}")))?;
// Refresh event cache if this is an event trigger
if routine.trigger.type_tag() == "event" {
if matches!(
routine.trigger,
Trigger::Event { .. } | Trigger::SystemEvent { .. }
) {
self.engine.refresh_event_cache().await;
}
@@ -801,3 +848,87 @@ impl Tool for RoutineHistoryTool {
false
}
}
// ==================== event_emit ====================
pub struct EventEmitTool {
engine: Arc<RoutineEngine>,
}
impl EventEmitTool {
pub fn new(engine: Arc<RoutineEngine>) -> Self {
Self { engine }
}
}
#[async_trait]
impl Tool for EventEmitTool {
fn name(&self) -> &str {
"event_emit"
}
fn description(&self) -> &str {
"Emit a structured system event to routines with a system_event trigger. \
Use this to trigger routines from tool workflows without waiting for cron."
}
fn requires_approval(&self, _params: &serde_json::Value) -> ApprovalRequirement {
// Emitting an event can fire system_event routines that dispatch full_jobs
// with pre-authorized Always-gated tools — same escalation risk as routine_fire.
ApprovalRequirement::UnlessAutoApproved
}
fn parameters_schema(&self) -> serde_json::Value {
serde_json::json!({
"type": "object",
"properties": {
"event_source": {
"type": "string",
"description": "Event source (e.g. 'github', 'workflow', 'tool')"
},
"event_type": {
"type": "string",
"description": "Event type (e.g. 'issue.opened', 'pr.ready')"
},
"payload": {
"type": "object",
"description": "Structured event payload"
}
},
"required": ["event_source", "event_type"]
})
}
async fn execute(
&self,
params: serde_json::Value,
ctx: &JobContext,
) -> Result<ToolOutput, ToolError> {
let start = std::time::Instant::now();
let source = require_str(&params, "event_source")?;
let event_type = require_str(&params, "event_type")?;
let payload = params
.get("payload")
.cloned()
.unwrap_or_else(|| serde_json::json!({}));
let fired = self
.engine
.emit_system_event(source, event_type, &payload, Some(&ctx.user_id))
.await;
let result = serde_json::json!({
"event_source": source,
"event_type": event_type,
"user_id": &ctx.user_id,
"fired_routines": fired,
});
Ok(ToolOutput::success(result, start.elapsed()))
}
fn requires_sanitization(&self) -> bool {
true
}
}
+5 -3
View File
@@ -64,6 +64,7 @@ const PROTECTED_TOOL_NAMES: &[&str] = &[
"routine_delete",
"routine_fire",
"routine_history",
"event_emit",
"skill_list",
"skill_search",
"skill_install",
@@ -427,8 +428,8 @@ impl ToolRegistry {
engine: Arc<crate::agent::routine_engine::RoutineEngine>,
) {
use crate::tools::builtin::{
RoutineCreateTool, RoutineDeleteTool, RoutineFireTool, RoutineHistoryTool,
RoutineListTool, RoutineUpdateTool,
EventEmitTool, RoutineCreateTool, RoutineDeleteTool, RoutineFireTool,
RoutineHistoryTool, RoutineListTool, RoutineUpdateTool,
};
self.register_sync(Arc::new(RoutineCreateTool::new(
Arc::clone(&store),
@@ -448,7 +449,8 @@ impl ToolRegistry {
Arc::clone(&engine),
)));
self.register_sync(Arc::new(RoutineHistoryTool::new(store)));
tracing::debug!("Registered 6 routine management tools");
self.register_sync(Arc::new(EventEmitTool::new(engine)));
tracing::debug!("Registered 7 routine management tools");
}
/// Register message tool for sending messages to channels.
+20 -1
View File
@@ -565,12 +565,19 @@ mod tests {
"description": { "type": "string", "description": "What it does" },
"trigger_type": {
"type": "string",
"enum": ["cron", "event", "webhook", "manual"],
"enum": ["cron", "event", "system_event", "manual"],
"description": "When the routine fires"
},
"schedule": { "type": "string", "description": "Cron expression" },
"event_pattern": { "type": "string", "description": "Regex pattern" },
"event_channel": { "type": "string", "description": "Channel filter" },
"event_source": { "type": "string", "description": "System event source" },
"event_type": { "type": "string", "description": "System event type" },
"event_filters": {
"type": "object",
"additionalProperties": { "type": "string" },
"description": "Exact-match payload filters"
},
"prompt": { "type": "string", "description": "Instructions" },
"context_paths": {
"type": "array",
@@ -647,6 +654,18 @@ mod tests {
"required": ["name"]
}),
),
(
"event_emit",
serde_json::json!({
"type": "object",
"properties": {
"event_source": { "type": "string", "description": "Event source" },
"event_type": { "type": "string", "description": "Event type" },
"payload": { "type": "object", "description": "Event payload", "properties": {} }
},
"required": ["event_source", "event_type"]
}),
),
// Job tools with complex deps
(
"job_events",
+115 -2
View File
@@ -27,6 +27,8 @@ mod tests {
let rig = TestRigBuilder::new()
.with_trace(trace.clone())
.with_auto_approve_tools(true)
.with_skills()
.build()
.await;
@@ -60,6 +62,8 @@ mod tests {
let rig = TestRigBuilder::new()
.with_trace(trace.clone())
.with_auto_approve_tools(true)
.with_skills()
.build()
.await;
@@ -97,6 +101,8 @@ mod tests {
let rig = TestRigBuilder::new()
.with_trace(trace.clone())
.with_auto_approve_tools(true)
.with_skills()
.build()
.await;
@@ -197,7 +203,114 @@ mod tests {
}
// -----------------------------------------------------------------------
// Test 6: job_create_status
// Test 6: routine_system_event_emit
// -----------------------------------------------------------------------
#[tokio::test]
async fn routine_system_event_emit() {
let trace = LlmTrace::from_file(concat!(
env!("CARGO_MANIFEST_DIR"),
"/tests/fixtures/llm_traces/tools/routine_system_event_emit.json"
))
.expect("failed to load routine_system_event_emit.json");
let rig = TestRigBuilder::new()
.with_trace(trace.clone())
.with_auto_approve_tools(true)
.build()
.await;
rig.send_message("Create a system-event routine and emit an event")
.await;
let responses = rig.wait_for_responses(1, Duration::from_secs(15)).await;
rig.verify_trace_expects(&trace, &responses);
let completed = rig.tool_calls_completed();
assert!(
completed.iter().any(|(n, ok)| n == "event_emit" && *ok),
"event_emit should succeed: {completed:?}"
);
let results = rig.tool_results();
let emit_result = results
.iter()
.find(|(n, _)| n == "event_emit")
.expect("event_emit result missing");
assert!(
emit_result.1.contains("fired_routines"),
"event_emit should report fired routine count: {:?}",
emit_result.1
);
// Verify at least one routine actually fired (not just that the key exists).
let emit_json: serde_json::Value =
serde_json::from_str(&emit_result.1).expect("event_emit result should be valid JSON");
assert!(
emit_json["fired_routines"].as_u64().unwrap_or(0) > 0,
"event_emit should have fired at least one routine: {:?}",
emit_result.1
);
rig.shutdown();
}
// -----------------------------------------------------------------------
// Test 7: skill_install_routine_webhook_sim
// -----------------------------------------------------------------------
#[tokio::test]
async fn skill_install_routine_webhook_sim() {
let trace = LlmTrace::from_file(concat!(
env!("CARGO_MANIFEST_DIR"),
"/tests/fixtures/llm_traces/tools/skill_install_routine_webhook_sim.json"
))
.expect("failed to load skill_install_routine_webhook_sim.json");
let rig = TestRigBuilder::new()
.with_trace(trace.clone())
.with_skills()
.with_auto_approve_tools(true)
.build()
.await;
rig.send_message("Install the workflow skill template and simulate a webhook routine run")
.await;
let responses = rig.wait_for_responses(1, Duration::from_secs(20)).await;
rig.verify_trace_expects(&trace, &responses);
let completed = rig.tool_calls_completed();
assert!(
completed.iter().any(|(n, _)| n == "skill_install"),
"skill_install should be called: {completed:?}"
);
for tool in &["routine_create", "event_emit", "routine_history"] {
assert!(
completed.iter().any(|(n, ok)| n == tool && *ok),
"{tool} should succeed: {completed:?}"
);
}
let results = rig.tool_results();
let emit_result = results
.iter()
.find(|(n, _)| n == "event_emit")
.expect("event_emit result missing");
assert!(
emit_result.1.contains("fired_routines"),
"event_emit should include fired_routines: {:?}",
emit_result.1
);
let _history_result = results
.iter()
.find(|(n, _)| n == "routine_history")
.expect("routine_history result missing");
rig.shutdown();
}
// -----------------------------------------------------------------------
// Test 8: job_create_status
// -----------------------------------------------------------------------
// Uses {{call_cj_1.job_id}} template to forward the dynamic UUID from
// create_job's result into job_status's arguments.
@@ -266,7 +379,7 @@ mod tests {
}
// -----------------------------------------------------------------------
// Test 7: job_list_cancel
// Test 9: job_list_cancel
// -----------------------------------------------------------------------
// Uses {{call_cj_lc.job_id}} template to forward the dynamic UUID from
// create_job into cancel_job.
+147 -3
View File
@@ -255,7 +255,151 @@ mod tests {
}
// -----------------------------------------------------------------------
// Test 3: routine_cooldown
// Test 3: system_event_trigger_matches_and_filters
// -----------------------------------------------------------------------
#[tokio::test]
async fn system_event_trigger_matches_and_filters() {
let (db, _tmp) = create_test_db().await;
let ws = create_workspace(&db);
let trace = LlmTrace::single_turn(
"test-system-event-match",
"event",
vec![TraceStep {
request_hint: None,
response: TraceResponse::Text {
content: "System event handled".to_string(),
input_tokens: 40,
output_tokens: 8,
},
expected_tool_results: vec![],
}],
);
let llm = Arc::new(TraceLlm::from_trace(trace));
let (notify_tx, _notify_rx) = tokio::sync::mpsc::channel(16);
// Create minimal ToolRegistry and SafetyLayer for test.
let tools = Arc::new(ToolRegistry::new());
let safety_config = SafetyConfig {
max_output_length: 100_000,
injection_check_enabled: true,
};
let safety = Arc::new(SafetyLayer::new(&safety_config));
let engine = Arc::new(RoutineEngine::new(
RoutineConfig::default(),
db.clone(),
llm,
ws,
notify_tx,
None,
tools,
safety,
));
let mut filters = std::collections::HashMap::new();
filters.insert("repository".to_string(), "nearai/ironclaw".to_string());
let routine = make_routine(
"github-issue-opened",
Trigger::SystemEvent {
source: "github".to_string(),
event_type: "issue.opened".to_string(),
filters,
},
"Summarize the issue and propose an implementation plan.",
);
db.create_routine(&routine).await.expect("create_routine");
engine.refresh_event_cache().await;
// Matching event should fire.
let fired = engine
.emit_system_event(
"github",
"issue.opened",
&serde_json::json!({
"repository": "nearai/ironclaw",
"issue_number": 42
}),
Some("default"),
)
.await;
assert_eq!(fired, 1, "Expected one routine to fire for matching event");
tokio::time::sleep(Duration::from_millis(300)).await;
let runs = db
.list_routine_runs(routine.id, 10)
.await
.expect("list runs");
assert!(
!runs.is_empty(),
"Expected run history after matching event"
);
// Wrong event type should not fire.
let fired_wrong_type = engine
.emit_system_event(
"github",
"issue.closed",
&serde_json::json!({"repository": "nearai/ironclaw"}),
Some("default"),
)
.await;
assert_eq!(
fired_wrong_type, 0,
"Expected no routine for wrong event type"
);
// Wrong filter value should not fire.
let fired_wrong_filter = engine
.emit_system_event(
"github",
"issue.opened",
&serde_json::json!({"repository": "other/repo"}),
Some("default"),
)
.await;
assert_eq!(
fired_wrong_filter, 0,
"Expected no routine for filter mismatch"
);
// Case-insensitive source/event_type should still match.
let fired_case = engine
.emit_system_event(
"GitHub",
"Issue.Opened",
&serde_json::json!({
"repository": "nearai/ironclaw",
"issue_number": 99
}),
Some("default"),
)
.await;
assert_eq!(
fired_case, 1,
"Expected case-insensitive match on source/event_type"
);
// Case-insensitive filter values should match.
let fired_filter_case = engine
.emit_system_event(
"github",
"issue.opened",
&serde_json::json!({"repository": "NearAI/IronClaw"}),
Some("default"),
)
.await;
assert_eq!(
fired_filter_case, 1,
"Expected case-insensitive match on filter values"
);
}
// -----------------------------------------------------------------------
// Test 4: routine_cooldown
// -----------------------------------------------------------------------
#[tokio::test]
@@ -345,7 +489,7 @@ mod tests {
}
// -----------------------------------------------------------------------
// Test 4: heartbeat_findings
// Test 5: heartbeat_findings
// -----------------------------------------------------------------------
#[tokio::test]
@@ -407,7 +551,7 @@ mod tests {
}
// -----------------------------------------------------------------------
// Test 5: heartbeat_empty_skip
// Test 6: heartbeat_empty_skip
// -----------------------------------------------------------------------
#[tokio::test]
@@ -0,0 +1,64 @@
{
"model_name": "test-routine-system-event-emit",
"expects": {
"tools_used": ["routine_create", "event_emit"],
"all_tools_succeeded": true,
"tool_results_contain": {
"event_emit": "fired_routines"
}
},
"steps": [
{
"response": {
"type": "tool_calls",
"tool_calls": [
{
"id": "call_rc_1",
"name": "routine_create",
"arguments": {
"name": "gh-issue-emit-test",
"description": "React to GitHub issue.opened events",
"trigger_type": "system_event",
"event_source": "github",
"event_type": "issue.opened",
"action_type": "full_job",
"prompt": "Summarize the new issue and propose next steps."
}
}
],
"input_tokens": 80,
"output_tokens": 30
}
},
{
"response": {
"type": "tool_calls",
"tool_calls": [
{
"id": "call_ee_1",
"name": "event_emit",
"arguments": {
"event_source": "github",
"event_type": "issue.opened",
"payload": {
"repository": "nearai/ironclaw",
"issue_number": 123,
"title": "Support event-driven project workflow"
}
}
}
],
"input_tokens": 140,
"output_tokens": 28
}
},
{
"response": {
"type": "text",
"content": "Created a system-event routine and emitted a matching GitHub event. The routine fired successfully.",
"input_tokens": 200,
"output_tokens": 18
}
}
]
}
@@ -0,0 +1,100 @@
{
"model_name": "test-skill-install-routine-webhook-sim",
"expects": {
"tools_used": ["skill_install", "routine_create", "event_emit", "routine_history"],
"tool_results_contain": {
"event_emit": "fired_routines"
}
},
"steps": [
{
"response": {
"type": "tool_calls",
"tool_calls": [
{
"id": "call_skill_install_1",
"name": "skill_install",
"arguments": {
"name": "wf-orchestrator-trace-install-1",
"content": "---\nname: wf-orchestrator-trace-install-1\ndescription: Minimal workflow skill for trace install validation\nactivation:\n keywords: [\"workflow\", \"orchestrator\"]\n---\n\nYou are a minimal workflow skill used for trace install validation.\n"
}
}
],
"input_tokens": 120,
"output_tokens": 32
}
},
{
"response": {
"type": "tool_calls",
"tool_calls": [
{
"id": "call_routine_create_1",
"name": "routine_create",
"arguments": {
"name": "wf-webhook-sim-trace",
"description": "Trace routine to simulate webhook event flow",
"trigger_type": "system_event",
"event_source": "github",
"event_type": "issue.opened",
"event_filters": {
"repository": "nearai/ironclaw"
},
"action_type": "full_job",
"prompt": "When issue webhook event arrives, start implementation loop and create branch/PR updates."
}
}
],
"input_tokens": 170,
"output_tokens": 36
}
},
{
"response": {
"type": "tool_calls",
"tool_calls": [
{
"id": "call_event_emit_1",
"name": "event_emit",
"arguments": {
"event_source": "github",
"event_type": "issue.opened",
"payload": {
"repository": "nearai/ironclaw",
"issue_number": 4242,
"sender": "trace-bot"
}
}
}
],
"input_tokens": 210,
"output_tokens": 28
}
},
{
"response": {
"type": "tool_calls",
"tool_calls": [
{
"id": "call_routine_history_1",
"name": "routine_history",
"arguments": {
"name": "wf-webhook-sim-trace",
"limit": 5
}
}
],
"input_tokens": 240,
"output_tokens": 22
}
},
{
"response": {
"type": "text",
"content": "Installed the skill template, created a system-event routine, emitted a webhook-equivalent event, and verified the routine run history.",
"input_tokens": 280,
"output_tokens": 25
}
}
]
}
+38 -1
View File
@@ -379,6 +379,8 @@ pub struct TestRigBuilder {
llm: Option<Arc<dyn LlmProvider>>,
max_tool_iterations: usize,
injection_check: bool,
auto_approve_tools: Option<bool>,
enable_skills: bool,
enable_routines: bool,
http_exchanges: Vec<HttpExchange>,
extra_tools: Vec<Arc<dyn Tool>>,
@@ -392,6 +394,8 @@ impl TestRigBuilder {
llm: None,
max_tool_iterations: 10,
injection_check: false,
auto_approve_tools: None,
enable_skills: false,
enable_routines: false,
http_exchanges: Vec::new(),
extra_tools: Vec::new(),
@@ -432,6 +436,18 @@ impl TestRigBuilder {
self
}
/// Override agent-level automatic approval of `UnlessAutoApproved` tools.
pub fn with_auto_approve_tools(mut self, enable: bool) -> Self {
self.auto_approve_tools = Some(enable);
self
}
/// Enable skill discovery and registration for this test rig.
pub fn with_skills(mut self) -> Self {
self.enable_skills = true;
self
}
/// Enable the routines system so the scheduler is wired with a `RoutineEngine`,
/// allowing routine jobs to actually execute. Routine tools are always registered
/// but require the engine to dispatch jobs.
@@ -466,6 +482,8 @@ impl TestRigBuilder {
llm,
max_tool_iterations,
injection_check,
auto_approve_tools,
enable_skills,
enable_routines,
http_exchanges: explicit_http_exchanges,
extra_tools,
@@ -491,6 +509,10 @@ impl TestRigBuilder {
let mut config = Config::for_testing(db_path, skills_dir, installed_skills_dir);
config.agent.max_tool_iterations = max_tool_iterations;
config.safety.injection_check_enabled = injection_check;
config.skills.enabled = enable_skills;
if let Some(v) = auto_approve_tools {
config.agent.auto_approve_tools = v;
}
// 3. Create SessionManager + LogBroadcaster.
let session = Arc::new(SessionManager::new(SessionConfig::default()));
@@ -540,7 +562,7 @@ impl TestRigBuilder {
);
builder.with_database(Arc::clone(&db));
builder.with_llm(llm);
let components = builder
let mut components = builder
.build_all()
.await
.expect("AppBuilder::build_all() failed in test rig");
@@ -583,6 +605,21 @@ impl TestRigBuilder {
.register_routine_tools(Arc::clone(db_arc), engine);
}
// Skills tools: ensure tests use temp skill dirs (sandbox-safe) even if
// AppBuilder did not wire them for this environment.
if enable_skills {
let registry = Arc::new(std::sync::RwLock::new(
ironclaw::skills::SkillRegistry::new(temp_dir.path().join("skills"))
.with_installed_dir(temp_dir.path().join("installed_skills")),
));
let catalog = ironclaw::skills::catalog::shared_catalog();
components
.tools
.register_skill_tools(Arc::clone(&registry), Arc::clone(&catalog));
components.skill_registry = Some(registry);
components.skill_catalog = Some(catalog);
}
// Register any extra test-specific tools.
for tool in extra_tools {
components.tools.register(tool).await;