Ivan Zaitsev

Queue is a good idea, however one concern is that malicious agent would be able to saturate the queue and delay/prevent legitimate resizes.

Well, there are two somewhat separate issues: 1. service DOS (load from resizing interfering with the serving or other server functions). Can be addressed by putting constraints on the resize...

> Views are considered deprecated. `Iterable` is better. Sorry, can you provide a source for that statement? Quick search over internet gave nothing, as well as scaladocs for scala 2.11.6.

Repro: ``` const moduleUrl = 'https://cdn.jsdelivr.net/npm/[email protected]/+esm'; try { const wordsToNumbersModule = await import(moduleUrl); console.log(wordsToNumbersModule.default('one hundred')); // Should output 100 } catch (error) { console.error('Failed to load module:', error); } ```...

I'm also blocked from using prompt caching. My setup is fairly simple: an agent using openai agents sdk: ``` super().__init__( name="writer", instructions="""You are an expert novelist. ... """, model=LitellmModel( model="openai/claude-sonnet-4-cached",...

@porteron > `{"location": "message", "role": "system"}` this would cache only the system prompt, though. if there were are back-and-forth with user/tools after that, they are not cached.

@molinla > you can try set `new Parser({...eventsHandler}, {xmlMode: true})` to fix self closing error. thanks, that is a good suggestion as a workaround (actually, it can be further reduced...

> Don't think that's an issue take a look at the second example I provided: ``` Input HTML: code with test Output HTML: code with test Node indices: Node: tag,...