refactor(core): use initiator in loop internals

This commit is contained in:
Tianyi Cui
2026-07-19 14:06:47 +08:00
parent e0b5cadd2a
commit f21ed1bfa0
7 changed files with 28 additions and 29 deletions
+1 -1
View File
@@ -50,7 +50,7 @@ The concrete `Agent` class, its `Inbox`, `runLoop`, and instance-bound publicati
### Loop lifecycle (`loop.ts`)
The driver owns one agent for its lifetime and runs inside `ctx.agents.withInitiator(agent, ...)`, so process-local asynchronous continuations can recover the initiating Agent. Creation, persistence load, and unpublished setup stay outside the driver boundary; explicit Agent fields remain authoritative at service, worker, process, persistence, and wire boundaries. The [agent service](../agent/README.md#initiating-agent-scope) owns propagation, teardown, and detached-work rules.
The driver owns one agent for its lifetime and runs inside `ctx.agents.withInitiator(agent, ...)`, so package-private loop, turn, step, and tool-call helpers recover the exact Agent from `ctx.agents` instead of forwarding the concrete driver through their signatures. Creation, persistence load, and unpublished setup stay outside the driver boundary; explicit Agent fields remain authoritative at service, worker, process, persistence, and wire boundaries. The [agent service](../agent/README.md#initiating-agent-scope) owns propagation, teardown, and detached-work rules.
Every provider call that reaches a successful finish appends exactly one `assistant/message` completion anchor, including content-less calls and `max-tokens` finishes. A successful `agent/step-result` stores its transformed content; a rejected result records empty content before the original failure continues. The anchor retains exact chunk provenance (`[]` for a stream with no chunks) and usage when available, while empty content stays out of derived message history.