mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-07-16 14:32:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

fix(codex): drop oversized message ids on Responses input replay

Browse source 
Codex assigns assistant message items server-side ids that can run
400+ chars (base64 encrypted blobs), but the Responses API caps
input[].id at 64 chars and rejects the whole request with a
non-retryable HTTP 400. Once a session captures one of these long
ids, every subsequent turn replays it and 400s forever, since the
history persists it in codex_message_items.

Add a 64-char length guard at both replay sites — the history-to-
input converter and the final preflight gate — so oversized ids are
dropped while short ids (msg_...) are kept for prefix-cache hits.
Mirrors the existing pattern for reasoning items, which already
strip their id before replay because store=False means the API
can't resolve ids server-side anyway.

Fixes #27038

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
joaomarcos 2026-07-10 15:04:56 -03:00 • committed by Teknium
parent dabae386ef
commit 0b2907f586
2 changed files with 137 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

15
agent/codex_responses_adapter.py
View file

@ -288,6 +288,13 @@ _RESPONSES_BUILTIN_TOOL_TYPES = {
_RESPONSE_MESSAGE_STATUSES = {"completed", "incomplete", "in_progress"}
# The Responses API rejects input[].id longer than this with a non-retryable
# HTTP 400 ("string too long"). Codex-issued assistant message ids are
# server-assigned base64 blobs that can run 400+ chars, while Hermes-minted
# ids (msg_...) stay well under this cap and are worth keeping for
# prefix-cache hits. Drop only the oversized ones on replay.
_MAX_RESPONSES_ITEM_ID_LENGTH = 64
def _normalize_responses_message_status(value: Any, *, default: str = "completed") -> str:
"""Normalize a Responses assistant message status for replay.
@ -464,7 +471,9 @@ def _chat_messages_to_responses_input(
}
item_id = raw_item.get("id")
if isinstance(item_id, str) and item_id.strip():
replay_item["id"] = item_id.strip()
stripped_id = item_id.strip()
if len(stripped_id) <= _MAX_RESPONSES_ITEM_ID_LENGTH:
replay_item["id"] = stripped_id
phase = raw_item.get("phase")
if isinstance(phase, str) and phase.strip():
replay_item["phase"] = phase.strip()
@ -718,7 +727,9 @@ def _preflight_codex_input_items(raw_items: Any) -> List[Dict[str, Any]]:
}
item_id = item.get("id")
if isinstance(item_id, str) and item_id.strip():
normalized_item["id"] = item_id.strip()
stripped_id = item_id.strip()
if len(stripped_id) <= _MAX_RESPONSES_ITEM_ID_LENGTH:
normalized_item["id"] = stripped_id
phase = item.get("phase")
if isinstance(phase, str) and phase.strip():
normalized_item["phase"] = phase.strip()