Skip to content

Commit 99a19ae

Browse files
committed
docs(ai-chat): add the 4.5.0-rc.6 changelog entry
1 parent 954ee5c commit 99a19ae

1 file changed

Lines changed: 40 additions & 0 deletions

File tree

docs/ai-chat/changelog.mdx

Lines changed: 40 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -4,6 +4,46 @@ sidebarTitle: "Changelog"
44
description: "Pre-release updates for AI chat agents."
55
---
66

7+
<Update label="June 12, 2026" description="4.5.0-rc.6" tags={["SDK", "CLI", "Bug fix"]}>
8+
9+
## chat.agent reliability fixes
10+
11+
A batch of fixes for edge cases around message delivery, stopping, and error handling:
12+
13+
- **No more duplicate turns from mid-stream sends.** A user message sent while the agent was streaming could be delivered twice — once via steering and again on the next turn — running a duplicate turn. Delivery is now deduplicated.
14+
- **Idempotent input appends.** Sends to `session.in` carry an idempotency key, so a client retry after a network blip can't append the same message twice.
15+
- **Stop clears streaming state.** Stopping a generation now clears the session's streaming snapshot, so a page reload right after a stop no longer replays the stopped turn.
16+
- **`onTurnComplete` fires on errored turns.** When `run()` or a lifecycle hook throws, `onTurnComplete` now runs with `error` carrying the thrown value and `finishReason: "error"`, and the failed turn's user message is persisted so it isn't lost on the next run. Use this to mark the turn failed in your own storage. See [error handling](/ai-chat/error-handling#using-onturncomplete).
17+
- **Full tag sets on chat runs.** Runs triggered by chat sessions can now carry the full set of dashboard tags instead of being silently truncated.
18+
- **Stream hygiene for custom agents.** Manual `chat.writeTurnComplete()` callers now trim the output stream the way `chat.agent` does, sending a custom action no longer leaves a second stream reader running, and a long-lived `watch` subscription no longer grows its dedupe set without bound.
19+
20+
## Continuation boots no longer stall
21+
22+
Continuation runs (after a cancel, crash, or version upgrade) used to stall around 10 seconds before the first turn: finding the `session.in` resume cursor drained an SSE long-poll that always waited out its full 5 second inactivity window, twice per boot. The cursor is now found with a non-blocking records read, the boot reads run concurrently, and chat snapshots carry the cursor so subsequent boots skip the scan entirely.
23+
24+
## chat.headStart: hydration and reasoning fixes
25+
26+
Two fixes for the [Head Start](/ai-chat/fast-starts) handover:
27+
28+
- With `hydrateMessages` registered, the warm route's step-1 partial now reaches the agent's accumulator, so `onTurnComplete` carries the full first turn, tool-call handovers resume from step 2 instead of re-running step 1, and the assistant `messageId` stays stable across the handover.
29+
- Extended-thinking models' step-1 reasoning now lands in the durable session history (and `onTurnComplete`) under the same assistant `messageId`, with provider metadata intact so Anthropic thinking signatures survive replays.
30+
31+
## chat.createSession: stop and continuation fixes
32+
33+
Stopping a generation no longer wedges the run: `turn.complete()` bare-awaited the AI SDK's `totalUsage` promise, which never settles after a stop-abort, so the loop hung inside the stopped turn and the chat couldn't take another message. It's now raced with a timeout, the same guard `chat.agent`'s turn loop uses.
34+
35+
Continuation runs also no longer invoke the model with an empty prompt: a message-less continuation boot now waits for the next session input, and `turn.continuation` is preserved so your loop can seed stored history on the first turn. See [chat.createSession](/ai-chat/backend#chat-createsession).
36+
37+
## trigger skills: agent skills for your coding assistant
38+
39+
The CLI's new `trigger skills` command installs Trigger.dev agent skills — including the chat.agent authoring skill — into your coding assistant's native skills directory (Claude Code, Cursor, GitHub Copilot, and Codex / AGENTS.md). The skills ship inside the CLI, version-matched to the SDK you build against, and `trigger dev` offers to install them on first run. `trigger init` can now also set up the MCP server and skills as part of project scaffolding.
40+
41+
```bash
42+
npx trigger.dev@4.5.0-rc.6 skills
43+
```
44+
45+
</Update>
46+
747
<Update label="June 5, 2026" description="4.5.0-rc.5" tags={["SDK", "Bug fix"]}>
848

949
## AI SDK 7 support

0 commit comments

Comments
 (0)