Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(agent): add addressable queue operations

Browse Source
This commit is contained in:
kingwl
2026-07-30 00:05:00 +08:00
parent 87c9ab06b3
commit f893e2281d
108 changed files with 1785 additions and 608 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
packages/core/agent-loop/README.md
View File

@@ -55,7 +55,9 @@ Configured agents start automatically. A model call requires both `provider` and
The concrete `ReactLoopAgent`, its queued input, outbox, and run controls are package-internal. The package root exports only the plugin/service/config contract, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than naming, constructing, or starting driver internals. One prepared session can be claimed by only one concrete driver, and everything observable happens through session events and the `agent/*` event taxonomy.
The unified `send()` primitive routes content and source by (`target` × `wakeup`); `followup`/`steer`/`inject` are its fixed-preset aliases. A `next-turn` item joins the queued FIFO, waking the driver unless `wakeup: false`; admission happens before any turn opens. The loop opens a private next-step acceptance window before `agent/prompt-submit` and closes it before `turn/end`. During that window, `steer()` and `inject()` stage in one outbox; an allowed admission opens the turn, records the prompt and returned `additionalContexts`, then drains the staged input before the first request. A blocked or failed admission writes no prompt or hook-produced context. A caller-staged context-only batch then takes idle injection's immediate append, while steering and context staged beside it remain pending for retry or a later admitted prompt. Outside the window, steering becomes a waking queued prompt and injection immediately appends `user/message` without opening a turn or running the model. Every inbox enqueue publishes `agent/inbox/enqueue` with the resolved queued-or-steering placement; taking it publishes `agent/inbox/dequeue` with the same placement, and `cancel()` without `keepInbox` publishes `agent/inbox/discard`.
The unified `send()` primitive routes content and source by (`target` × `wakeup`); `followup`/`steer`/`inject` are its fixed-preset aliases. A `next-turn` item joins the queued FIFO, waking the driver unless `wakeup: false`; admission happens before any turn opens. The loop opens a private next-step acceptance window before `agent/prompt-submit` and closes it before `turn/end`. During that window, `steer()` and `inject()` stage in one outbox; an allowed admission opens the turn, records the prompt and returned `additionalContexts`, then drains the staged input before the first request. A blocked or failed admission writes no prompt or hook-produced context. A caller-staged context-only batch then takes idle injection's immediate append, while steering and context staged beside it remain pending for retry or a later admitted prompt. Outside the window, steering becomes a waking queued prompt and injection immediately appends `user/message` without opening a turn or running the model.
Every FIFO acceptance mints an `InboxItemId` and publishes `agent/inbox/enqueue` with the complete occurrence. `updateInbox()` owns the synchronous pending-item boundary: edit freezes replacement content without changing message identity or position, remove publishes discard, and promote moves the occurrence to the head of its queued or steering FIFO; promoting queued work also makes it waking. Edit and promote publish `agent/inbox/update`. Claim publishes `agent/inbox/dequeue` and irrevocably removes the live address before prompt admission, so a racing update returns `not-found`; `cancel()` without `keepInbox` publishes `agent/inbox/discard`.
### Loop lifecycle (`agent.ts`)