| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | pkg/aflow: handle input token overflow for LLM tools | Dmitry Vyukov | 2026-01-27 | 1 | -9/+66 |
| | | | | | | | | Handle LLM tool input token overflow by removing the last tool reply, and replacing it with an order to answer right now. I've seen an LLM tool went into too deap research and in the end just overflowed input tokens. It could provide at least some answer instead. | ||||
| * | pkg/aflow: add LLMTool | Dmitry Vyukov | 2026-01-23 | 1 | -0/+297 |
| LLMTool acts like a tool for the parent LLM, but is itself implemented as an LLM agent. It can have own tools, different from the parent LLM agent. It can do complex multi-step research, and provide a concise answer to the parent LLM without polluting its context window. | |||||
