agent-loop: projection, recovery, compaction into the crate (phase 3)
Nightly Build / build (push) Successful in 6m49s

The session handler is now a thin shell: three entry points in
kernel_turn.rs (run_kernel_turn / recover_turn / resolve_pending_call)
and the ChatSessionHandler. Everything that shaped a Value — projection,
recovery, compaction mechanics, the LLM loop, message building — lives
in agent-loop or behind a loop_adapters trait.

agent-loop:
- projection/ (mod + media): stored history -> wire messages, the one
  place provider divergence lives; well-formedness contract, DTL
  injections (append-only), media parts. LinearAssembler is now a
  Projection + ProjectionHooks config, not its own implementation
- recovery.rs: reap interrupted batches -> resolve the deepest frame's
  non-terminal calls (Running by policy + RestartHint, AwaitingHuman
  re-asked) -> un-wedge finished children -> cascade up, every frame on
  its own agent (B3)
- compaction.rs: split point (never assistant+tool group), transcript,
  SUMMARY_PREFIX/preamble/template, the no-tools model call, summary row
- manager: resolve_pending (gate skipped, real ToolContext, then
  continue incl. sub-agent); start_loop used by recovery; LiveInput
- delegate: AsyncExecutor + StoreSink for mode:async (durable cron row,
  result delivered back into the parent conversation)
- kernel/context/store: support the above (TurnScope via Extensions,
  frame lookups, aligned result-text semantics)

skald-core:
- loop_adapters: UserLoopRuntime (D12 - one LoopManager per user),
  TurnScope (per-turn state in the Extensions type-map; no scope is
  denied), projection_cfg/media_source/tool_digest (Skald's projection
  knobs without owning projection code), async_task (CronExecutor +
  DurableSink)
- session/handler: stripped to mod.rs + kernel_turn.rs + config.rs +
  interface_tools.rs + media.rs; deleted agent_dispatch, approval,
  dispatch, emitter, gate, llm_call, llm_loop, message_builder,
  messages, outcome, resume
- compactor.rs: policy only (threshold, model pick, CompactionEvent);
  mechanics are the crate's

CLAUDE.md updated (recovery, compaction, sub-agents, approval gate,
projection sections now describe the crate-owned flow).
This commit is contained in:
2026-07-26 17:09:01 +01:00
parent 3fca7867fa
commit 24ee5b89d7
74 changed files with 7661 additions and 5982 deletions
+189 -2
View File
@@ -143,6 +143,7 @@ async fn params(
system: Arc::new(StaticSystemContext::new("You are a test agent.")),
tools,
model_hint: ModelHint::default(),
selector: None,
live_input: None,
extensions: Default::default(),
meta: TurnMeta::default(),
@@ -502,18 +503,26 @@ async fn second_loop_on_same_conversation_rejected() {
struct TestCatalog {
context: Arc<StaticSystemContext>,
/// Pins the child to its own model, so a test can script parent and child
/// independently (a shared script would race on who pops which step).
model: Option<ModelHint>,
}
#[async_trait]
impl AgentCatalog for TestCatalog {
async fn get(&self, id: &str, _child_frame: agent_loop::ids::FrameId) -> agent_loop::Result<AgentProfile> {
async fn get(
&self,
id: &str,
_child_frame: agent_loop::ids::FrameId,
_ctx: &agent_loop::tool::ToolCtx,
) -> agent_loop::Result<AgentProfile> {
Ok(AgentProfile {
id: id.into(),
kind: AgentKind::Task,
context: self.context.clone(),
tools: ToolSelection::inherit(),
toolset: None,
model: None,
model: self.model.clone(),
selector: None,
assembler: None,
})
@@ -540,6 +549,7 @@ async fn sync_delegate_runs_child_loop_and_returns_result() {
);
let catalog: Arc<dyn AgentCatalog> = Arc::new(TestCatalog {
context: Arc::new(StaticSystemContext::new("You are a researcher.")),
model: None,
});
let delegate: Arc<dyn Tool> = Arc::new(DelegateTool::new(manager.clone(), catalog, manager.store(), 5));
@@ -551,6 +561,7 @@ async fn sync_delegate_runs_child_loop_and_returns_result() {
system: Arc::new(StaticSystemContext::new("root")),
tools: ToolRegistry::new().with_arc(delegate).into_toolset(),
model_hint: ModelHint::default(),
selector: None,
live_input: None,
extensions: Default::default(),
meta: TurnMeta::default(),
@@ -599,6 +610,7 @@ async fn delegate_batch_fans_out_concurrently() {
);
let catalog: Arc<dyn AgentCatalog> = Arc::new(TestCatalog {
context: Arc::new(StaticSystemContext::new("worker")),
model: None,
});
let delegate: Arc<dyn Tool> = Arc::new(DelegateTool::new(manager.clone(), catalog, manager.store(), 5));
@@ -610,6 +622,7 @@ async fn delegate_batch_fans_out_concurrently() {
system: Arc::new(StaticSystemContext::new("root")),
tools: ToolRegistry::new().with_arc(delegate).into_toolset(),
model_hint: ModelHint::default(),
selector: None,
live_input: None,
extensions: Default::default(),
meta: TurnMeta::default(),
@@ -633,4 +646,178 @@ async fn delegate_batch_fans_out_concurrently() {
);
}
// ── async delegation ──
/// Polls until `f` holds, so a background delivery does not need a sleep.
async fn eventually<F, Fut>(label: &str, f: F)
where
F: Fn() -> Fut,
Fut: std::future::Future<Output = bool>,
{
let deadline = std::time::Instant::now() + Duration::from_secs(5);
while std::time::Instant::now() < deadline {
if f().await {
return;
}
tokio::time::sleep(Duration::from_millis(10)).await;
}
panic!("timed out waiting for: {label}");
}
#[tokio::test]
async fn async_delegate_returns_a_receipt_then_delivers_the_result() {
// Parent and child get their own scripted model: the parent does NOT wait
// for the child, so one shared script would race on who pops which step.
let root = Arc::new(FakeModel::new("root", vec![
Step::tool_calls("", vec![testing::call("c1", "delegate", json!({
"agent_id": "worker", "prompt": "long job", "mode": "async", "title": "nightly",
}))]),
Step::message("started it"),
]));
let child = Arc::new(FakeModel::new("child", vec![Step::message("the long answer")]));
let store = Arc::new(InMemoryStore::new());
let manager = Arc::new(
LoopManager::builder()
.models(Arc::new(StaticModels::new(vec![
testing::handle(&root, "root"),
testing::handle(&child, "child"),
])))
.store(store.clone())
.build()
.unwrap(),
);
let catalog: Arc<dyn AgentCatalog> = Arc::new(TestCatalog {
context: Arc::new(StaticSystemContext::new("worker")),
model: Some(ModelHint::name("child")),
});
let sink: Arc<dyn AsyncResultSink> = Arc::new(StoreSink::new(manager.store()));
let exec: Arc<dyn AsyncExecutor> = Arc::new(InProcessExecutor::new(
manager.clone(),
catalog.clone(),
manager.store(),
sink,
ToolRegistry::new().into_toolset(),
));
let delegate: Arc<dyn Tool> = Arc::new(
DelegateTool::new(manager.clone(), catalog, manager.store(), 5).with_async(exec),
);
let conv = ConversationId::new("d3");
let frame = manager.open_root(&conv, FrameSpec::root("assistant")).await.unwrap();
let p = TurnParams {
frame,
agent: "assistant".into(),
system: Arc::new(StaticSystemContext::new("root")),
tools: ToolRegistry::new().with_arc(delegate).into_toolset(),
model_hint: ModelHint::default(),
selector: None,
live_input: None,
extensions: Default::default(),
meta: TurnMeta::default(),
assembler: None,
};
let handle = manager.start_turn(conv.clone(), NewMessage::user("run it"), p).await.unwrap();
let outcome = tokio::time::timeout(Duration::from_secs(5), handle.join())
.await
.expect("async delegate must not block the parent turn")
.unwrap();
let TurnOutcome::Final { content, .. } = outcome else { panic!("got {outcome:?}") };
assert_eq!(content, "started it");
// The delegating call resolved with a receipt, not with the child's answer.
let done = store.calls_in_state(frame, &[CallState::Done]).await.unwrap();
let receipt: Value =
serde_json::from_str(done[0].result.as_deref().unwrap()).expect("receipt is JSON");
assert_eq!(receipt["status"], "started");
assert_eq!(receipt["task_id"], 1);
// …and the answer lands later, as its own completed call.
let store_c = store.clone();
eventually("the delivered result", || {
let store = store_c.clone();
async move {
store
.load(frame)
.await
.unwrap()
.iter()
.any(|m| m.calls.iter().any(|c| c.name == agent_loop::delegate::DELIVERY_CALL))
}
})
.await;
let history = store.load(frame).await.unwrap();
let delivery = history
.iter()
.find(|m| m.calls.iter().any(|c| c.name == agent_loop::delegate::DELIVERY_CALL))
.unwrap();
assert!(delivery.synthetic, "the delivery is not a turn the user drove");
let call = &delivery.calls[0];
assert_eq!(call.state, CallState::Done);
let payload: Value = serde_json::from_str(call.result.as_deref().unwrap()).unwrap();
assert_eq!(payload["task_id"], 1);
assert_eq!(payload["title"], "nightly");
assert_eq!(payload["result"], "the long answer");
}
#[tokio::test]
async fn async_delegate_without_an_executor_is_refused() {
let script = vec![
Step::tool_calls("", vec![testing::call("c1", "delegate", json!({
"agent_id": "worker", "prompt": "job", "mode": "async",
}))]),
Step::message("could not start it"),
];
let store = Arc::new(InMemoryStore::new());
let manager = Arc::new(
LoopManager::builder()
.models(Arc::new(agent_loop::model::SingleModel::new(FakeModel::new("m", script))))
.store(store.clone())
.build()
.unwrap(),
);
let catalog: Arc<dyn AgentCatalog> = Arc::new(TestCatalog {
context: Arc::new(StaticSystemContext::new("worker")),
model: None,
});
// No `with_async`: the mode must fail, never silently run sync — a turn
// that asked not to wait would otherwise block on the child.
let delegate: Arc<dyn Tool> =
Arc::new(DelegateTool::new(manager.clone(), catalog, manager.store(), 5));
let conv = ConversationId::new("d4");
let frame = manager.open_root(&conv, FrameSpec::root("assistant")).await.unwrap();
let p = TurnParams {
frame,
agent: "assistant".into(),
system: Arc::new(StaticSystemContext::new("root")),
tools: ToolRegistry::new().with_arc(delegate).into_toolset(),
model_hint: ModelHint::default(),
selector: None,
live_input: None,
extensions: Default::default(),
meta: TurnMeta::default(),
assembler: None,
};
let handle = manager.start_turn(conv.clone(), NewMessage::user("run it"), p).await.unwrap();
tokio::time::timeout(Duration::from_secs(5), handle.join())
.await
.expect("turn hung")
.unwrap();
let failed = store.calls_in_state(frame, &[CallState::Failed]).await.unwrap();
assert_eq!(failed.len(), 1);
assert!(
failed[0].result.as_deref().unwrap().contains("async mode is not available"),
"{:?}",
failed[0].result
);
// Nothing was spawned: no child frame was ever opened.
assert!(store.active_frames(&conv).await.unwrap().iter().all(|f| f.spec.depth == 0));
}
use agent_loop::delegate::{AsyncExecutor, AsyncResultSink, InProcessExecutor, StoreSink};
use std::collections::HashSet;