mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-06-09 08:21:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 10

feat: use 'developer' role for GPT-5 and Codex models (#4498)

Browse source 
OpenAI's newer models (GPT-5, Codex) give stronger instruction-following
weight to the 'developer' role vs 'system'. Swap the role at the API
boundary in _build_api_kwargs() for the chat_completions path so internal
message representation stays consistent ('system' everywhere).

Applies regardless of provider — OpenRouter, Nous portal, direct, etc.
The codex_responses path (direct OpenAI) uses 'instructions' instead of
message roles, so it's unaffected.

DEVELOPER_ROLE_MODELS constant in prompt_builder.py defines the matching
model name substrings: ('gpt-5', 'codex').
This commit is contained in:
Teknium 2026-04-01 14:49:32 -07:00 • committed by GitHub
parent c59ab8b0da
commit 3628ccc8c4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 91 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

15
run_agent.py
View file

@ -88,7 +88,7 @@ from agent.model_metadata import (
)
from agent.context_compressor import ContextCompressor
from agent.prompt_caching import apply_anthropic_cache_control
from agent.prompt_builder import build_skills_system_prompt, build_context_files_prompt, load_soul_md, TOOL_USE_ENFORCEMENT_GUIDANCE, TOOL_USE_ENFORCEMENT_MODELS
from agent.prompt_builder import build_skills_system_prompt, build_context_files_prompt, load_soul_md, TOOL_USE_ENFORCEMENT_GUIDANCE, TOOL_USE_ENFORCEMENT_MODELS, DEVELOPER_ROLE_MODELS
from agent.usage_pricing import estimate_usage_cost, normalize_usage
from agent.display import (
KawaiiSpinner, build_tool_preview as _build_tool_preview,
@ -5024,6 +5024,19 @@ class AIAgent:
tool_call.pop("call_id", None)
tool_call.pop("response_item_id", None)
# GPT-5 and Codex models respond better to 'developer' than 'system'
# for instruction-following. Swap the role at the API boundary so
# internal message representation stays uniform ("system").
_model_lower = (self.model or "").lower()
if (
sanitized_messages
and sanitized_messages[0].get("role") == "system"
and any(p in _model_lower for p in DEVELOPER_ROLE_MODELS)
):
# Shallow-copy the list + first message only — rest stays shared.
sanitized_messages = list(sanitized_messages)
sanitized_messages[0] = {**sanitized_messages[0], "role": "developer"}
provider_preferences = {}
if self.providers_allowed:
provider_preferences["only"] = self.providers_allowed