common/hermes
2
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix: use output_text for assistant message content in Codex Responses API (#15690)

Browse Source 
The Codex Responses API rejects input_text inside assistant messages —
only output_text and refusal are valid content types for assistant role.

_chat_content_to_responses_parts() previously hardcoded all text content
to input_text regardless of the message role. When an assistant message
had list-format content (multimodal or structured), this produced invalid
input_text parts that the API rejected with:

  Invalid value: 'input_text'. Supported values are: 'output_text' and 'refusal'.

Fix: add a role parameter to _chat_content_to_responses_parts() that
selects output_text for assistant messages and input_text for user
messages. Thread this through _chat_messages_to_responses_input() and
_preflight_codex_input_items().

Fixes #15687
This commit is contained in:
kshitij
2026-04-25 10:13:29 -07:00
committed by GitHub
parent 7c17accb29
commit 648b89911f
2 changed files with 129 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
agent/codex_responses_adapter.py
View File

@@ -44,22 +44,31 @@ _TOOL_CALL_LEAK_PATTERN = re.compile(
# Multimodal content helpers
# ---------------------------------------------------------------------------
def _chat_content_to_responses_parts(content: Any) -> List[Dict[str, Any]]:
def _chat_content_to_responses_parts(content: Any, *, role: str = "user") -> List[Dict[str, Any]]:
"""Convert chat-style multimodal content to Responses API input parts.
Input: ``[{"type":"text"|"image_url", ...}]`` (native OpenAI Chat format)
Output: ``[{"type":"input_text"|"input_image", ...}]`` (Responses format)
Output: ``[{"type":"input_text"|"output_text"|"input_image", ...}]`` (Responses format)
The ``role`` parameter controls the text content type:
- ``"user"`` (default) → ``"input_text"``
- ``"assistant"`` → ``"output_text"``
The Responses API rejects ``input_text`` inside assistant messages and
``output_text`` inside user messages, so callers MUST pass the correct
role for the message being converted.
Returns an empty list when ``content`` is not a list or contains no
recognized parts — callers fall back to the string path.
"""
text_type = "output_text" if role == "assistant" else "input_text"
if not isinstance(content, list):
return []
converted: List[Dict[str, Any]] = []
for part in content:
if isinstance(part, str):
if part:
converted.append({"type": "input_text", "text": part})
converted.append({"type": text_type, "text": part})
continue
if not isinstance(part, dict):
continue
@@ -67,7 +76,7 @@ def _chat_content_to_responses_parts(content: Any) -> List[Dict[str, Any]]:
if ptype in {"text", "input_text", "output_text"}:
text = part.get("text")
if isinstance(text, str) and text:
converted.append({"type": "input_text", "text": text})
converted.append({"type": text_type, "text": text})
continue
if ptype in {"image_url", "input_image"}:
image_ref = part.get("image_url")
@@ -233,9 +242,10 @@ def _chat_messages_to_responses_input(messages: List[Dict[str, Any]]) -> List[Di
if role in {"user", "assistant"}:
content = msg.get("content", "")
if isinstance(content, list):
content_parts = _chat_content_to_responses_parts(content)
content_parts = _chat_content_to_responses_parts(content, role=role)
text_type = "output_text" if role == "assistant" else "input_text"
content_text = "".join(
p.get("text", "") for p in content_parts if p.get("type") == "input_text"
p.get("text", "") for p in content_parts if p.get("type") == text_type
)
else:
content_parts = []
@@ -429,13 +439,16 @@ def _preflight_codex_input_items(raw_items: Any) -> List[Dict[str, Any]]:
content = ""
if isinstance(content, list):
# Multimodal content from ``_chat_messages_to_responses_input``
# is already in Responses format (``input_text`` / ``input_image``).
# Validate each part and pass through.
# is already in Responses format (``input_text`` / ``output_text``
# / ``input_image``). Validate each part and pass through.
# Use the correct text type for the role — ``output_text`` for
# assistant messages, ``input_text`` for user messages.
text_type = "output_text" if role == "assistant" else "input_text"
validated: List[Dict[str, Any]] = []
for part_idx, part in enumerate(content):
if isinstance(part, str):
if part:
validated.append({"type": "input_text", "text": part})
validated.append({"type": text_type, "text": part})
continue
if not isinstance(part, dict):
raise ValueError(
@@ -446,7 +459,7 @@ def _preflight_codex_input_items(raw_items: Any) -> List[Dict[str, Any]]:
text = part.get("text", "")
if not isinstance(text, str):
text = str(text or "")
validated.append({"type": "input_text", "text": text})
validated.append({"type": text_type, "text": text})
elif ptype in {"input_image", "image_url"}:
image_ref = part.get("image_url", "")
detail = part.get("detail")