mirror of
https://github.com/outbackdingo/optimclaw.git
synced 2026-08-26 23:50:17 +00:00
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
co-authored by
Henry Park
Claude Sonnet 4.6
Henry Park
Claude Sonnet 4.6
parent
e8f8ec06e3
commit
6e1ed939cc
@@ -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.
|
||||
|
||||
@@ -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
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -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(®istry), 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;
|
||||
|
||||
Reference in New Issue
Block a user