mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(agent): preserve MiniMax context length on delta-only overflow

Browse source
This commit is contained in:
maelrx 2026-04-13 15:12:55 -03:00 • committed by Teknium
parent a884f6d5d8
commit e020f46bec
3 changed files with 109 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tests/agent/test_model_metadata.py
View file

@ -621,6 +621,10 @@ class TestParseContextLimitFromError:
msg = "Error: context window of 4096 tokens exceeded"
assert parse_context_limit_from_error(msg) == 4096
def test_minimax_delta_only_message_returns_none(self):
msg = "invalid params, context window exceeds limit (2013)"
assert parse_context_limit_from_error(msg) is None
def test_completely_unrelated_error(self):
assert parse_context_limit_from_error("Invalid API key") is None

83
tests/run_agent/test_run_agent.py
View file

@ -2575,6 +2575,89 @@ class TestRunConversation:
assert result["final_response"] == "Recovered after compression"
assert result["completed"] is True
def test_minimax_delta_overflow_keeps_known_context_length(self, agent):
"""MiniMax reports overflow deltas like 'limit (2013)' without the real window.
Keep the known 204,800-token window and compress instead of probing down
to the generic 128K fallback tier.
"""
self._setup_agent(agent)
agent.provider = "minimax"
agent.model = "MiniMax-M2.7-highspeed"
agent.base_url = "https://api.minimax.io/anthropic"
agent.context_compressor.context_length = 204_800
agent.context_compressor.threshold_tokens = int(
agent.context_compressor.context_length * agent.context_compressor.threshold_percent
)
err_400 = Exception(
"HTTP 400: invalid params, context window exceeds limit (2013)"
)
err_400.status_code = 400
ok_resp = _mock_response(content="Recovered after compression", finish_reason="stop")
agent.client.chat.completions.create.side_effect = [err_400, ok_resp]
prefill = [
{"role": "user", "content": "previous question"},
{"role": "assistant", "content": "previous answer"},
]
with (
patch.object(agent, "_compress_context") as mock_compress,
patch.object(agent, "_persist_session"),
patch.object(agent, "_save_trajectory"),
patch.object(agent, "_cleanup_task_resources"),
):
mock_compress.return_value = (
[{"role": "user", "content": "hello"}],
"compressed system prompt",
)
result = agent.run_conversation("hello", conversation_history=prefill)
mock_compress.assert_called_once()
assert agent.context_compressor.context_length == 204_800
assert agent.context_compressor._context_probed is False
assert result["final_response"] == "Recovered after compression"
assert result["completed"] is True
def test_non_minimax_delta_overflow_still_probes_down(self, agent):
"""Non-MiniMax providers should keep the generic probe-down behavior."""
self._setup_agent(agent)
agent.provider = "openrouter"
agent.model = "some/unknown-model"
agent.base_url = "https://openrouter.ai/api/v1"
agent.context_compressor.context_length = 200_000
agent.context_compressor.threshold_tokens = int(
agent.context_compressor.context_length * agent.context_compressor.threshold_percent
)
err_400 = Exception(
"HTTP 400: invalid params, context window exceeds limit (2013)"
)
err_400.status_code = 400
ok_resp = _mock_response(content="Recovered after compression", finish_reason="stop")
agent.client.chat.completions.create.side_effect = [err_400, ok_resp]
prefill = [
{"role": "user", "content": "previous question"},
{"role": "assistant", "content": "previous answer"},
]
with (
patch.object(agent, "_compress_context") as mock_compress,
patch.object(agent, "_persist_session"),
patch.object(agent, "_save_trajectory"),
patch.object(agent, "_cleanup_task_resources"),
):
mock_compress.return_value = (
[{"role": "user", "content": "hello"}],
"compressed system prompt",
)
result = agent.run_conversation("hello", conversation_history=prefill)
mock_compress.assert_called_once()
assert agent.context_compressor.context_length == 128_000
assert result["final_response"] == "Recovered after compression"
assert result["completed"] is True
def test_length_finish_reason_requests_continuation(self, agent):
"""Normal truncation (partial real content) triggers continuation."""
self._setup_agent(agent)