Il mer 2 set 2026, 18:26 Daniel P. Berrangé <[email protected]> ha scritto:
> > I must admit I don't have a good understanding of how these are parsed > > by all the different models, but this seems like a good improvement > > over what we have now. > > I think we broadly just have to assume the agents will "do the > right thing" in the way a human would interpret the text. > > If there's a general theme, it is that the statements should be > concise and explicit with as little "fluff" in the language as > possible, to keep the length down and increase the likelihood > it will be honoured by the agent. > I am no expert but it depends. Context size has increased a lot over the past year, and if anything the agents are too eager to help you not be banned by QEMU. ;) It's much easier to forbid something than to change what it means to be helpful, and the latter takes more explanations. Alex's previous, much more expansive, AGENTS.md proposal made > use of linking to multiple files, so the agent only needed to > load subsets which were relevant. > The "@" syntax as far as I could understand is just a shortcut and still results in eager loading. For on-demand loading, instead... This baseline AGENTS.md file is probably already getting a > little on the long side, once we consider the followups that > Alex had, to link off to other docs with guidance on QEMU's > codebase and issue policies, etc. ... those are best published as "skills". These are a similar kind of instructions, except only a YAML front matter is passed to the LLM and the full text is loaded on demand. I didn't include a sample skill in this version, but AGENTS.md does not have to grow much beyond what it means to implement the policy and a lazy reference to it. Paolo
