Hmbown/CodeWhale · error · anyhow::Error

Agent not found

Error message

Agent not found

What it means

Thrown by `continuation_target` when the given agent id is not present in `self.agents`, so no continuation target can be computed for a `start + resume_from` fork. The method walks `resume_targets` to find the chain's fork point; with no source agent there is no lineage to walk, and it fails closed (cyclic lineages get their own error).

Solutions

  1. Use a live agent id from the current session's agent listing as `resume_from`.
  2. If the original agent is gone, restart the chain from the root conversation or re-spawn the source agent.
  3. Verify the resume_from id belongs to the same owner session — cross-session ids are not tracked here.
  4. If the id should exist, check whether a recent state restore or reap policy removed it.
Defensive patterns

Strategy: validation

Validate before calling

let known = engine.list_agents();
if !known.iter().any(|a| a.id == resume_from_id) {
    return Err(anyhow!("resume_from {resume_from_id} not tracked in this session"));
}

Try / catch

match engine.resume_chain(&resume_from_id, text) {
    Err(e) if e.to_string().contains("Agent not found") => restart_chain_from_root(text),
    other => other?,
}

Prevention

When it happens

Trigger: Computing a continuation target (mod.rs:6053) for an `agent_id` absent from `self.agents` — resuming from an agent id that was never spawned in this session, was reaped after completion, or disappeared in a state restore that cleared the agent map.

Common situations: Resuming a chain using an id from a previous session or a snapshot that cleared agents; a workflow referencing an agent spawned by a different parent/session; a typo'd or stale resume_from handle.

Understand the failure class

Background: "Not found" and "does not exist" errors: why "Task not found", "No such folder", and "Can't find" fire when a lookup comes back empty — this error's family across 14 libraries.

Related errors

AI-assisted analysis of Hmbown/CodeWhale@433685b202 (2026-09-15). Data as JSON: /api/errors/1d81dadf9d106cae. Report an issue: GitHub.

Appendix: source

Thrown at crates/tui/src/tools/subagent/mod.rs:6053

    pub(crate) fn followup_child_for_session(
        &mut self,
        active_session_id: &str,
        agent_ref: &str,
        text: String,
    ) -> Result<ParentMailReceipt> {
        let agent_id = self.resolve_agent_ref_for_session(active_session_id, agent_ref)?;
        self.followup_child(&agent_id, text)
    }

    /// Follow the persisted continuation chain without treating deliberate
    /// `start + resume_from` forks as continuation targets. Every hop retains
    /// the original root conversation; malformed or cyclic state fails closed.
    fn continuation_target(&self, agent_id: &str) -> Result<String> {
        let source = self
            .agents
            .get(agent_id)
            .ok_or_else(|| anyhow!("Agent not found"))?;
        let owner = &source.owner_session_id;
        let mut target = agent_id.to_string();
        let mut seen = HashSet::new();
        while let Some(next) = self.resume_targets.get(&target) {
            if !seen.insert(target.clone()) {
                return Err(anyhow!("Invalid agent continuation lineage: cycle"));
            }
            let successor = self
                .agents
                .get(next)
                .ok_or_else(|| anyhow!("Agent continuation target is no longer retained"))?;
            if owner.is_empty() || successor.owner_session_id != *owner {
                return Err(anyhow!(
                    "Agent continuation target is outside the active session"
                ));
            }
            target.clone_from(next);
        }

View on GitHub (pinned to 433685b202)