ta
TanStack
OSS
ta
Pipelines
Nx runs
Insights
Compare tasks
Analytics
Sign in
Toggle Sidebar
ai
ai
Pipelines
fix(ai, ai-anthropic): keep thinking in the afterModel interrupt snapshot (#1587) * fix(ai): keep thinking in the afterModel interrupt snapshot At an afterModel generic interrupt with no tool calls, the engine recorded the paused turn with addAssistantTextMessageForInterrupt. It kept only the assistant text and skipped a turn with no text, so the interrupt's MESSAGES_SNAPSHOT lost the thinking and its signature. The engine now records the turn with addTerminalAssistantMessages, the same method a finished run uses. The old helper had one caller and is removed. * fix(ai-anthropic): do not end a request in a thinking-only assistant message A run that resumes after an afterModel interrupt on a thinking-only turn sent that turn back as the last message. Claude rejects it. The adapter now leaves it out. Also adds a resume round-trip test for the interrupt snapshot. --------- Co-authored-by: Tom Beckenham <34339192+tombeckenham@users.noreply.github.com>
nx run-many --targets=build --exclude=examples/**,testing/**
⌘K
Succeeded
in
8s
Started
Linux
4 CPU cores
read
access token used
Copy command
nx run-many --targets=build --exclude=examples/**,testing/**
1583
dead914
GitHub
Open on GitHub
Tasks
Resource Usage
ta
TanStack
OSS
ai
ai