mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-30 06:41:51 +00:00
fix(acp): mark failed tool completions
This commit is contained in:
parent
375c7f9cc3
commit
b38d2d133b
2 changed files with 47 additions and 1 deletions
|
|
@ -202,6 +202,28 @@ def _json_loads_maybe(value: Optional[str]) -> Any:
|
|||
return None
|
||||
|
||||
|
||||
def _tool_result_failed(result: Optional[str]) -> bool:
|
||||
"""Return True when a structured Hermes tool result clearly failed.
|
||||
|
||||
Keep this deliberately conservative. Plain text can contain words like
|
||||
"error" because tests failed or a command printed diagnostics; Zed should
|
||||
only receive ACP failed status for structured tool-level failures.
|
||||
"""
|
||||
data = _json_loads_maybe(result)
|
||||
if not isinstance(data, dict):
|
||||
return False
|
||||
|
||||
for key in ("success", "ok"):
|
||||
if data.get(key) is False:
|
||||
return True
|
||||
|
||||
exit_code = data.get("exit_code", data.get("returncode"))
|
||||
if isinstance(exit_code, int) and exit_code != 0:
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
|
||||
def _truncate_text(text: str, limit: int = 5000) -> str:
|
||||
if len(text) <= limit:
|
||||
return text
|
||||
|
|
@ -1296,7 +1318,7 @@ def build_tool_complete(
|
|||
return acp.update_tool_call(
|
||||
tool_call_id,
|
||||
kind=kind,
|
||||
status="completed",
|
||||
status="failed" if _tool_result_failed(result) else "completed",
|
||||
content=content,
|
||||
raw_output=None if tool_name in _POLISHED_TOOLS or _is_structured_json_result(result) else result,
|
||||
)
|
||||
|
|
|
|||
|
|
@ -345,6 +345,30 @@ class TestBuildToolComplete:
|
|||
assert "hello" in text
|
||||
assert result.raw_output is None
|
||||
|
||||
def test_build_tool_complete_marks_success_false_as_failed(self):
|
||||
result = build_tool_complete("tc-fail", "skill_manage", '{"success": false, "error": "boom"}')
|
||||
assert result.status == "failed"
|
||||
|
||||
def test_build_tool_complete_marks_ok_false_as_failed(self):
|
||||
result = build_tool_complete("tc-fail", "some_tool", '{"ok": false, "error": "boom"}')
|
||||
assert result.status == "failed"
|
||||
|
||||
def test_build_tool_complete_marks_exit_code_nonzero_as_failed(self):
|
||||
result = build_tool_complete("tc-fail", "terminal", '{"output": "bad", "exit_code": 2}')
|
||||
assert result.status == "failed"
|
||||
|
||||
def test_build_tool_complete_marks_returncode_nonzero_as_failed(self):
|
||||
result = build_tool_complete("tc-fail", "execute_code", '{"output": "bad", "returncode": 2}')
|
||||
assert result.status == "failed"
|
||||
|
||||
def test_build_tool_complete_keeps_plain_error_text_completed(self):
|
||||
result = build_tool_complete("tc-ok", "terminal", "tests failed: 1 assertion error")
|
||||
assert result.status == "completed"
|
||||
|
||||
def test_build_tool_complete_keeps_json_error_without_failure_flag_completed(self):
|
||||
result = build_tool_complete("tc-ok", "some_tool", '{"error": "timeout while reading optional source"}')
|
||||
assert result.status == "completed"
|
||||
|
||||
def test_build_tool_complete_for_skill_manage_summarizes_without_raw_json(self):
|
||||
result = build_tool_complete(
|
||||
"tc-skill-manage",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue