Skip to content

The fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.

docs(agent-harness): clarify delegation checkpoint storage

Steven Enamakel063598123fa7
diff --git a/docs/gitbooks/en/developing/architecture/agent-harness.md b/docs/gitbooks/en/developing/architecture/agent-harness.md
index a91b17f59a..64dd70facb 100644
--- a/docs/gitbooks/en/developing/architecture/agent-harness.md
+++ b/docs/gitbooks/en/developing/architecture/agent-harness.md
@@ -649,7 +649,7 @@ direct `tinyagents-orchestration::subagent` lifecycle. There is no
| `mod.rs` / `model.rs` / `tools.rs` / `convert.rs` | `RunPolicy` / `ChatModel` / `Tool` / message adapters (incl. unknown-tool policy and out-of-band reasoning forwarding). |
| `observability.rs` | Harness `AgentEvent` → `AgentProgress` + cost; `GraphTracingSink` for graph events. |
| `orchestration.rs` | Re-exported `graph::orchestration` task-store types; map-reduce fanout uses the TinyAgents SDK surface directly. |
-| `delegation.rs` | The durable `plan → execute ⇄ review → finalize` delegation graph (production worker wired in `orchestration::delegation`), checkpointed via TinyAgents' own `SqliteCheckpointer`. |
+| `delegation.rs` | The durable `plan → execute ⇄ review → finalize` delegation graph (production worker wired in `orchestration::delegation`), checkpointed to the session database. |
Orchestration on graphs (`crates/openhuman-core/src/agent/orchestration/`):