ai/byre
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity

Stream each task's transcript over its own SSE; keep session note order

Browse Source
This commit is contained in:
Ian Gulliver
2026-10-14 23:53:17 -07:00
parent eabfc10c8d
commit 2b4d92e7d5
18 changed files with 304 additions and 191 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/operations.md
+3 -1
View File
@@ -157,4 +157,6 @@ Merging or discarding a task stops new snapshots for it, waits for one in progre
## Events
`GET /api/events` is server-sent events: `id` is the event's `seq`, `data` the Event JSON. Reconnecting with `Last-Event-ID` (EventSource does this itself) or `?after=` replays everything after that seq before going live. Unstored events (`seq` 0, currently only `agent.delta`) go out live only, without an `id` line, so they don't move `Last-Event-ID`. A client that falls further behind than its subscriber buffer (`subscribe` in `internal/server/hub.go`) is disconnected and catches up by reconnecting. Every 15s the server sends an `event: ping` so clients can tell a live stream from a dead one. The web UI (`subscribe` in `web/src/api.ts`) tracks the last seq it saw and opens a new stream from it when nothing (event or ping) has arrived for 40s, 2s after the browser gives up on one (as it does when `tailscale serve` answers 502 while byre restarts), when the browser comes back online, and on becoming visible if the stream is stale. While disconnected the navbar shows a red dot and "reconnecting…"; partial output (`agent.delta`) sent while disconnected is lost, and the finished `agent.message` replaces it.
`GET /api/events` is server-sent events: `id` is the event's `seq`, `data` the Event JSON. Reconnecting with `Last-Event-ID` (EventSource does this itself) or `?after=` replays everything after that seq before going live. `?task_id=` limits the stream, replay and live, to one task's events (404 for an unknown task). Unstored events (`seq` 0, currently only `agent.delta`) go out live only, without an `id` line, so they don't move `Last-Event-ID`. A client that falls further behind than its subscriber buffer (`subscribe` in `internal/server/hub.go`) is disconnected and catches up by reconnecting. Every 15s the server sends an `event: ping` so clients can tell a live stream from a dead one. The web UI (`subscribe` in `web/src/api.ts`) tracks the last seq it saw and opens a new stream from it when nothing (event or ping) has arrived for 40s, 2s after the browser gives up on one (as it does when `tailscale serve` answers 502 while byre restarts), when the browser comes back online, and on becoming visible if the stream is stale. While disconnected the navbar shows a red dot and "reconnecting…"; partial output (`agent.delta`) sent while disconnected is lost, and the finished `agent.message` replaces it.
The web UI keeps two streams: one for all events from the page's load onward, which drives the task, session and inbox lists and the navbar's connection dot, and one per selected task (`selectTask` in `web/src/state.ts`), opened with `?task_id=` and `after=0` so it replays the task's whole history and then stays live. The transcript is drawn only from the task stream, so a reconnect after a byre restart fills in both the history and anything missed. Selecting another task closes the old task stream. Events arriving together are drawn in one batch.