Teknium 85993fbb5a feat: pre-call sanitization and post-call tool guardrails (#1732) ...

Salvage of PR #1321 by @alireza78a (cherry-picked concept, reimplemented
against current main).

Phase 1 — Pre-call message sanitization:
  _sanitize_api_messages() now runs unconditionally before every LLM call.
  Previously gated on context_compressor being present, so sessions loaded
  from disk or running without compression could accumulate dangling
  tool_call/tool_result pairs causing API errors.

Phase 2a — Delegate task cap:
  _cap_delegate_task_calls() truncates excess delegate_task calls per turn
  to MAX_CONCURRENT_CHILDREN. The existing cap in delegate_tool.py only
  limits the task array within a single call; this catches multiple
  separate delegate_task tool_calls in one turn.

Phase 2b — Tool call deduplication:
  _deduplicate_tool_calls() drops duplicate (tool_name, arguments) pairs
  within a single turn when models stutter.

All three are static methods on AIAgent, independently testable.
29 tests covering happy paths and edge cases.

2026-03-17 04:24:27 -07:00

9.4 KiB

Raw Permalink Blame History

View Raw