Teknium
903b9bf187
Two defects in the same path, both measured on the 1,393-agent refactor run. 1. A nested orchestrator (depth > 0) runs delegate_task synchronously by design: it needs its workers' results inside its own turn. But the sequential tool runner put every tool call under the generic 420 s deadline, and delegate_task was not exempt, so every batch longer than seven minutes returned "timed out after 420.0s" while the children kept running as orphans. 332 such timeouts in 234 orchestrator sessions; only 89 nested delegate_task calls in the whole run ever returned a real result. The orchestrators then spent 388 h of wall time polling: 1,526 reads of the live transcript files, 551 list actions, 242 h of explicit sleep, about $4k of API turns. delegate_task is now exempt from the sequential deadline (the batch owns its liveness: per-child heartbeats, the stale monitor, delegation.child_timeout_seconds). Live A/B, depth-1 orchestrator dispatching a 75 s leaf with the deadline set to 40 s (glm-5.3-flash via Nous): main -> "Error executing tool 'delegate_task': timed out after 40.0s", leaf result lost; branch -> orchestrator blocked 161 s and returned the leaf's LEAF_DONE_MARKER. 2. _parent_summary_char_budget computed the parent's context headroom from session_prompt_tokens, which is the running SUM of prompt tokens over every API call in the session. After a few hundred calls it exceeds any window, headroom goes negative, and every child summary collapses to the 2,000-char floor with the full text spilled to disk. All 1,393 child summaries in the run were truncated this way; the orchestrator planned from stubs. The budget now reads the last call's prompt_tokens from _last_turn_usage. Tests: delegate_task is in the exempt set and the set is narrow; budget for a long-lived parent equals the budget for a fresh parent with the same current prompt, and exceeds the floor.
14 lines
654 B
Python
14 lines
654 B
Python
"""``delegate_task`` runs a nested orchestrator's whole batch inside one tool call by design, so it must not
|
|
sit under the generic sequential-call deadline: with it, every batch longer than the deadline "timed out"
|
|
while its children kept running as orphans and the orchestrator polled transcripts for hours."""
|
|
from agent import tool_executor as te
|
|
|
|
|
|
def test_delegate_task_is_exempt_from_the_sequential_deadline():
|
|
assert "delegate_task" in te._SEQUENTIAL_DEADLINE_EXEMPT_TOOLS
|
|
|
|
|
|
def test_exemption_is_narrow():
|
|
assert "terminal" not in te._SEQUENTIAL_DEADLINE_EXEMPT_TOOLS
|
|
assert "execute_code" not in te._SEQUENTIAL_DEADLINE_EXEMPT_TOOLS
|