mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-06-14 09:11:54 +00:00
d63abbc329
Streaming-only providers (glm, MiniMax, gpt-5.x via aigw, Anthropic via openai-compat shims) emit reasoning through delta.reasoning_content chunks that get accumulated into the local reasoning_text string — but never land on the assistant message object as a top-level attribute. The prior guard at _build_assistant_message only wrote reasoning_content when the SDK exposed hasattr(msg, 'reasoning_content'), so these providers persisted the chain-of-thought under the internal 'reasoning' key and omitted the protocol-standard field. The poison was silent until the user later switched to a DeepSeek-v4 or Kimi thinking model, at which point replay failed with HTTP 400: 'The reasoning_content in the thinking mode must be passed back to the API.' One reported session store accumulated 4,031 poisoned messages across 1,101 files (#16844). Fix: add an additive fallback that promotes the already-sanitized reasoning_text to reasoning_content when no earlier branch wrote it AND reasoning text was actually captured. Layered on top of the existing SDK-attr branch and DeepSeek ''-pad (#15250) rather than replacing them, so every existing behavior is preserved: - SDK-exposed reasoning_content (OpenAI/Moonshot/DeepSeek SDK) still wins. - DeepSeek tool-call ''-pad still fires when the SDK exposes the attr but the value is None. - Non-thinking turns with no reasoning leave the field absent, so _copy_reasoning_content_for_api's cross-provider leak guard (#15748), promote-from-'reasoning' tier, and thinking-pad tier remain live at replay time. - No empty '' gets eagerly written on every assistant turn (which would have bypassed the read-side ladder and triggered empty thinking-block insertion in the Anthropic adapter). Tests: three new TestBuildAssistantMessage cases covering the streaming promotion path, SDK precedence, and field-absent-when-no-reasoning invariant. Credit @Sanjays2402 for the original diagnosis and patch in #16884; this is a scoped rework that preserves the existing read-side compensation code as defense in depth. Refs #16844, #16884, #15250, #15353, #15748. |
||
|---|---|---|
| .. | ||
| acp | ||
| agent | ||
| cli | ||
| cron | ||
| e2e | ||
| environments/benchmarks | ||
| fakes | ||
| gateway | ||
| hermes_cli | ||
| hermes_state | ||
| honcho_plugin | ||
| integration | ||
| plugins | ||
| run_agent | ||
| skills | ||
| tools | ||
| tui_gateway | ||
| website | ||
| __init__.py | ||
| conftest.py | ||
| run_interrupt_test.py | ||
| test_account_usage.py | ||
| test_base_url_hostname.py | ||
| test_batch_runner_checkpoint.py | ||
| test_cli_file_drop.py | ||
| test_cli_skin_integration.py | ||
| test_ctx_halving_fix.py | ||
| test_empty_model_fallback.py | ||
| test_evidence_store.py | ||
| test_hermes_constants.py | ||
| test_hermes_logging.py | ||
| test_hermes_state.py | ||
| test_honcho_client_config.py | ||
| test_ipv4_preference.py | ||
| test_mcp_serve.py | ||
| test_mini_swe_runner.py | ||
| test_minimax_model_validation.py | ||
| test_minisweagent_path.py | ||
| test_model_picker_scroll.py | ||
| test_model_tools.py | ||
| test_model_tools_async_bridge.py | ||
| test_ollama_num_ctx.py | ||
| test_packaging_metadata.py | ||
| test_plugin_skills.py | ||
| test_project_metadata.py | ||
| test_retry_utils.py | ||
| test_sql_injection.py | ||
| test_subprocess_home_isolation.py | ||
| test_timezone.py | ||
| test_toolset_distributions.py | ||
| test_toolsets.py | ||
| test_trajectory_compressor.py | ||
| test_trajectory_compressor_async.py | ||
| test_transform_tool_result_hook.py | ||
| test_tui_gateway_server.py | ||
| test_utils_truthy_values.py | ||
| test_yuanbao_integration.py | ||
| test_yuanbao_markdown.py | ||
| test_yuanbao_pipeline.py | ||
| test_yuanbao_proto.py | ||