mirror of
https://github.com/agent0ai/agent-zero.git
synced 2026-11-01 19:30:53 +00:00
Record the Chat Completions finish_reason on LLMResult and add a message_loop_result extension that, when a turn stopped at the output token limit (finish_reason "length"/"max_tokens") without a complete tool request, retries with a warning naming truncation as the cause rather than the generic misformat message. The warning counts toward the existing unusable-response loop limit. Context Doctor now leaves results already handled by an earlier extension untouched, so truncated envelopes are not repaired and dispatched with cut-off arguments. Fixes #1836 |
||
|---|---|---|
| .. | ||
| __main__/init_a0/end | ||
| agent | ||
| AGENTS.md | ||