diff options
| author | Dmitry Vyukov <dvyukov@google.com> | 2026-01-26 17:59:37 +0100 |
|---|---|---|
| committer | Dmitry Vyukov <dvyukov@google.com> | 2026-01-27 08:20:21 +0000 |
| commit | 43e1df1d9b982f24e3ccba50cf8881eed86d8994 (patch) | |
| tree | 7fe17fc1e3e4e58d8c7c1b7112c893a029b3290c /pkg/aflow/flow/patching/patching.go | |
| parent | b441fd80a58c6064b1333a3630367c9199fe1c99 (diff) | |
pkg/aflow: handle input token overflow for LLM tools
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.
Diffstat (limited to 'pkg/aflow/flow/patching/patching.go')
0 files changed, 0 insertions, 0 deletions