mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-18 04:41:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 7

fix(model-metadata): set codex-spark fallback context to 128k

Browse source
This commit is contained in:
olegdater 2026-05-01 11:16:49 +04:00 • committed by kshitij
parent 2a6f3deb50
commit c6dc295a35
2 changed files with 17 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

2
agent/model_metadata.py
View file

@ -1108,7 +1108,7 @@ _CODEX_OAUTH_CONTEXT_FALLBACK: Dict[str, int] = {
"gpt-5.1-codex-max": 272_000,
"gpt-5.1-codex-mini": 272_000,
"gpt-5.3-codex": 272_000,
"gpt-5.3-codex-spark": 272_000,
"gpt-5.3-codex-spark": 128_000,
"gpt-5.2-codex": 272_000,
"gpt-5.4-mini": 272_000,
"gpt-5.5": 272_000,

29
tests/agent/test_model_metadata.py
View file

@ -262,8 +262,9 @@ class TestDefaultContextLengths:
class TestCodexOAuthContextLength:
"""ChatGPT Codex OAuth imposes lower context limits than the direct
OpenAI API for the same slugs. Verified Apr 2026 via live probe of
chatgpt.com/backend-api/codex/models: every model returns 272k, while
chatgpt.com/backend-api/codex/models: most models return 272k, while
models.dev reports 1.05M for gpt-5.5/gpt-5.4 and 400k for the rest.
(Known exception: gpt-5.3-codex-spark is 128k.)
"""
def setup_method(self):
@ -277,26 +278,28 @@ class TestCodexOAuthContextLength:
"""
from agent.model_metadata import get_model_context_length
expected = {
"gpt-5.5": 272_000,
"gpt-5.4": 272_000,
"gpt-5.4-mini": 272_000,
"gpt-5.3-codex": 272_000,
"gpt-5.3-codex-spark": 128_000,
"gpt-5.2-codex": 272_000,
"gpt-5.1-codex-max": 272_000,
"gpt-5.1-codex-mini": 272_000,
}
with patch("agent.model_metadata.get_cached_context_length", return_value=None), \
patch("agent.model_metadata.save_context_length"):
for model in (
"gpt-5.5",
"gpt-5.4",
"gpt-5.4-mini",
"gpt-5.3-codex",
"gpt-5.3-codex-spark",
"gpt-5.2-codex",
"gpt-5.1-codex-max",
"gpt-5.1-codex-mini",
):
for model, expected_ctx in expected.items():
ctx = get_model_context_length(
model=model,
base_url="https://chatgpt.com/backend-api/codex",
api_key="",
provider="openai-codex",
)
assert ctx == 272_000, (
f"Codex {model}: expected 272000 fallback, got {ctx} "
assert ctx == expected_ctx, (
f"Codex {model}: expected {expected_ctx} fallback, got {ctx} "
"(models.dev leakage?)"
)