mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-06-17 09:41:58 +00:00
12c84d6c77
A chat-completions response that carries real text or tool calls *alongside* a `message.refusal` note is a normal, usable turn — the model did work. The prior logic flipped finish_reason to `content_filter` whenever a refusal string was present, so the conversation loop reframed a content-bearing turn as a *failed* safety refusal (failed=True) and buried the model's actual output inside the "model declined" template, or dropped tool calls entirely. Only promote to a terminal `content_filter` when the refusal is the sole payload (no visible text AND no tool calls). The refusal explanation is still recorded in provider_data in every case for observability. Refusal-only responses (the bug this feature targets) are unaffected and still surface terminally; the empty+refusal, bare content_filter passthrough, and no-refusal common cases are byte-identical to before. Updates the partial-content test to the corrected contract and adds a tool_calls-alongside-refusal regression guard. |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| test_bedrock_transport.py | ||
| test_chat_completions.py | ||
| test_codex_app_server_runtime.py | ||
| test_codex_app_server_session.py | ||
| test_codex_event_projector.py | ||
| test_codex_transport.py | ||
| test_hermes_tools_mcp_server.py | ||
| test_transport.py | ||
| test_types.py | ||