My current Claude Code session has been going on for like 35 hours and has used up around 400 million tokens, thankfully almost all of those being cached (95-98%) - pretty typical for long form agentic work.
First you spend like 2-3 hours working on a plan, once you have that you just tell the model to go and implement it, do adversarial sub-agent review loops before each commit and also make sure that all tooling and tests pass (including coverage requirements). You do need to poke it in a slightly different direction every few hours, though. Not even any novel work, just some refactoring and SSE notification hardening, bug fixes, alongside environment tuning and getting rid of some bottlenecks (also migrated from Oracle to PostgreSQL but that's mostly done).
That said, Kimi somehow manages to use less context in the main thread than Anthropic's models (even when you use sub-agents and also dynamic workflows in Claude Code), might have something to do with either how the model is tuned or their Kimi Code harness - because even in most of the longer form sessions it doesn't seem to fill up quite as quickly (note: because the kimi vis tool doesn't have a full summary view across all agents, these are the main long running agent stats across some sessions, not sub-agents):
total tokens cache hit rate wall time peak context
283M 98% 3963m 466k
258M 97% 2724m 467k
98M 94% 1353m 393k
67M 97% 614m 434k
75M 98% 1447m 498k
53M 99% 191m 375k
6M 96% 139m 124k
7M 98% 86m 118k
11M 99% 61m 147k
Once you have the plan you don't need to keep the 2hrs of research in the context (which is most of it) you can drop that plan into a file and start fresh for implementation.
That is true, but I feel like sometimes if the conversation contains useful rational it can help to keep it. I think sometimes it is a judgement call, I will sometimes compress the context first.
If I feel like the model and I explored a lot of options I won't want to keep context as it might be confusing.
I think the more you use it the better judge you are of whether you should purge, compress, or just keep the context before executing the plan.
Models work best when they have short instructions and no noise. "Conversation [may] contain" also means "conversation has a lot of noise". It degrades performance and increases cost.
I use handoff skill to ask model to write a prompt for itself.
Thanks for sharing - is this a normal feature request you are implementing in this example or is this a project from scratch? Trying to get an idea of how your workflow compares to mine.
Kimi CLI has a mechanism with checkpoints and the ability for the agent to revert to a checkpoint + a message of how to continue based on what went right/wrong. I don't know if that's the cause of what you've seen, but it's plausible.
With prefix caching, you get checkpoints for free. Do you mean that?