Yeah we all converge to the same workflow, in my ai coding agent I'm working on now, I've added an "index" tool that uses tree-sitter to compress and show the AI a skeleton of a code file.
I'm curious, what does your workflow look like? I saw a plan prompt there, but no specs. When you want to change something, implement a new feature etc, do you just prompt requirements, have it write the plan and then have it work on it?
Advantage of SML in between some outputs cannot be compressed without losing context, so a small model does that job. It works but most of these solutions still have some tradeoff in real world applications.
We compress tool outputs at each step, so the cache isn't broken during the run. Once we hit the 85% context-window limit, we preemptively trigger a summarization step and load that when the context-window fills up.
For auto-compact, we do essentially the same Anthropic does, but at 85% filled context window. Then, when the window is 100% filled, we pull this precompaction + append accumulated 15%. This allows to run compaction instantly
Yes I’ve read through TigerBeetle’s VSR design and their rationale for not using Raft.
VSR makes a lot of sense for their problem space: fixed schema, deterministic state machine,
and a very tight control over replication + execution order.
Ayder has a different set of constraints:
- append-only logs with streaming semantics
- dynamic topics / partitions
- external clients producing arbitrary payloads over HTTP
Raft here is a pragmatic choice: it’s well understood, easier to reason about for operators,
and fits the “easy to try, easy to operate” goal of the system.
That said, I think VSR is a great example of what’s possible when you fully own the problem
and can specialize aggressively. Definitely a project I’ve learned from.
Even some BIFs and NIFs (BIF are mostly just an built-in NIFs) can yield [1]
and choose to reschedule themselves later. But inside the C code it is voluntary, of course. An example of this can be seen when running hash functions [2].
Another interesting idea is that a NIF which may not reschedule themselves with yield, can still signal the scheduler that they are consuming so many "reductions" if they did some lengthy work. So if, say, they run for 10 msec, they might want to bump the reduction counter a bit: enif_consume_timeslice. Otherwise a tight recursive loop calling the same NIF could still effectively block the VM.
reply