Changelog

Version 1.1.26072000

New Functions

  • Added a set of config dict tools to hana_ml_tools, requiring hana-ml 2.29.26072000.

Version 1.1.260714

New Functions

  • Added the hana_ai.retrieval package to host the HANA AI Core retrieval clients used by the MCP tools; the package exposes ObjectDiscovery, DataRetrieval, and the shared RetrievalBase used by both. The previous internal hana_ai.agents.hana_agent package has been removed in favor of hana_ai.retrieval.

  • Renamed the MCP-exposed retrieval tools to object_discovery (schema/object metadata retrieval) and data_retrieval (data retrieval over remote-source-backed procedures), replacing the previous discovery_agent/data_agent names. The corresponding tool classes are ObjectDiscoveryTool and DataRetrievalTool in hana_ai.tools.hana_ml_tools.graph_tools.

  • Added ADI / CV^2 based intermittent-demand classification in TimeSeriesCheck (ts_check MCP tool). The check now reports ADI and CV^2 alongside the previous statistics and labels each series as smooth, erratic, intermittent, or lumpy using the standard thresholds (ADI >= 1.32, CV^2 >= 0.49). ContextAgent skills routing was updated accordingly to prefer intermittent_forecast with method=constant for intermittent series and method=sporadic for lumpy series.

  • Added HTTP MCP audit-context plumbing in hana_ai.tools.toolkit: the toolkit now attaches a MCPAuditMiddleware for HTTP transport (via fastmcp.server.middleware) and mirrors the same context capture on the stdio path so both transports emit consistently keyed audit events. Introduced DEFAULT_MCP_SESSION_CONTEXT_KEYS in hana_ai.tools.hana_ml_tools.utility as the canonical set of MCP audit fields (client-declared identity, HANA-authenticated identity, tool name, target tables, response size, model storage name/version, timing, and correlation identifiers).

  • Added ensure_mcp_audit_log and find_free_port helpers in hana_ai.tools.hana_ml_tools.utility to make bootstrapping a local MCP audit-log file and picking a free HTTP port reusable from example scripts.

  • Added extra_headers on the MCP HTTP client in hana_ai.client.mcp_client. Callers can now pass arbitrary key/value pairs (for example, a routing hint or a trace-id header) that are merged into the outgoing httpx client and per-request headers on top of the standard MCP protocol and session headers.

Version 1.1.260701

Bug Fixes

  • Fixed ContextAgent failure with newer Anthropic Claude deployments (e.g. anthropic--claude-4.6-sonnet) on SAP Generative AI Hub that reject temperature and top_p being set together; the agent now sanitizes the LLM sampling parameters on construction and drops top_p when temperature is also set.

  • Fixed ContextAgent hallucinating table, model, and version identifiers (e.g. substituting SALES_REFUNDS_TEST for the previously recorded SALES_REFUNEDS_PREDICT) by feeding DECISIONS.md and TODO.md back into the per-turn memory_notes block alongside NOTES.md and hardening the system prompt to forbid inventing identifiers not present in context.

  • Fixed invalid table name: Could not find table/view PREDICT_RESULT_... errors from AutomaticTimeSeriesLoadModelAndPredict, AdditiveModelForecastLoadModelAndPredict, and MassiveAutomaticTimeSeriesLoadModelAndPredict when the model storage name (or predict input table/schema) contained lower-case characters: user-supplied identifier fragments are now uppercased before being embedded in the PREDICT_RESULT_/REASON_CODE_/PREDICT_ERROR_ table names so the created table aligns with HANA's default folding on unquoted references.

  • Fixed ContextAgent hanging notebook cells for many minutes when a tool call got stuck on the HANA/PAL backend (previously max_iterations bounded the number of tool calls but not the wall-clock time, so eight stuck iterations could exceed ten minutes). Added AgentConfig.max_turn_seconds (default 300s, set to None/0 to disable) which runs the executor on a daemon thread with a join timeout; when the deadline fires the current turn short-circuits with an actionable message instead of hanging.

Version 1.1.260410

Bug Fixes

  • Fixed the line plot tool issue when the column names in the predicted results table are different from the default column names expected by the tool.

Version 1.1.260408

New Functions

  • Added a standalone ContextAgent skills catalog at hana_ai.iagents.skills.md to make skill definitions easier to review, extend, and maintain.

  • Added markdown-based skill loading in ContextAgent with built-in fallback support for existing deployments.

  • Added dedicated dataset preparation tools for CSV import and time-ordered train, test, validation table generation in conversational forecasting workflows, including split_table_for_forecasting.

  • Added grouped additive forecasting tools backed by AdditiveModelForecast(massive=True) for save-and-predict workflows across many related series.

Enhancements

  • Added aggregate and file-level ContextAgent memory reset commands for clearing persisted notes, TODOs, decisions, context, chat history, and session summaries without deleting the storage directory.

  • Expanded ContextAgent skill coverage for dataset preparation, time-series profiling, prediction-result analysis, grouped forecasting, artifact generation, and dataframe-oriented fallback workflows.

  • Improved fallback skill selection so profiling, post-prediction analysis, grouped forecasting, artifact generation, and SQL comparison requests map more reliably to the intended skills.

  • Added validation for markdown-defined skills so malformed entries are ignored unless they provide a valid Goal section.

  • Clarified that dataset splitting currently targets forecasting scenarios and preserves chronology through time-ordered splitting.

  • Improved forecasting prediction robustness so automatic, additive, and grouped prediction tools proactively validate and repair predict inputs to inference-only columns when users accidentally pass labeled holdout tables.

  • Improved ContextAgent tool-failure handling with more actionable diagnostics for predict-versus-score input mismatches and backend PAL runtime failures during forecasting workflows.

API Changes

  • ContextAgent now prefers loading skills from the colocated markdown catalog and merges them with the built-in fallback skills.

  • ContextAgent is the recommended target for future live end-to-end scenario expansion; HANAMLRAGAgent and Mem0HANARAGAgent are no longer recommended for new scenario coverage.

Version 1.0.260331

New Functions

  • Added prediction result analysis skills and dataframe manipulation skills in the context agent to provide better insights and analysis of the predicted results.

Version 1.0.260330

New Functions

  • Added context agent with markdown type memory to support better context management and display in the conversation.

Version 1.0.260319

Bug Fixes

  • Fixed the hullucination issue of forecast tools in Mem0HANARAGAgent when the input table name is very similar to the prediction result.

Version 1.0.260316

API Changes

  • Removed the graph_tools due to the stored procedure missing.

Version 1.0.260212

Bug Fixes

  • Fixed the version incomatibility issue of langchain and sap-ai-sdk-gen.

Version 1.0.260116

Enhancements

  • Added reset_tools method to HANAMLToolkit to reset the toolkit's tools.

Version 1.0.251223

Bug Fixes

  • Fixed the import issues in hana_ai agents and tools.

  • Fixed the missing parameter in PALEmbeddings.

Version 1.0.251217

Enhancements

  • Added the customized procedure name in CAP generation tool.

Version 1.0.251001

Bug Fixes

  • Fixed the output parser issue in SmartDataFrame's transform function.

Version 1.0.250930

Enhancements

  • Added MassiveAutomaticTimeSeriesFitAndSave, MassiveAutomaticTimeSeriesLoadModelAndPredict, and MassiveAutomaticTimeSeriesLoadModelAndScore tools to support massive time series model training, prediction, and scoring with group_key parameter.

  • Added MassiveTSOutlierDetection tool to support massive time series outlier detection with group_key parameter.

  • Added TSMakeFutureTableForMassiveForecastTool to create future tables for massive time series forecasting with group_key parameter.

  • Added MassiveTimeSeriesCheck tool to perform time series analysis and generate reports for multiple time series with group_key parameter.

  • Updated HANAMLToolkit to include the new massive time series tools.

API Changes

  • Modified SelectStatementToTableTool to include a 'force' parameter that allows overwriting existing tables.

  • Changed "Timeseries" to "TimeSeries" in class names for consistency.

Bug Fixes

  • Fixed an issue for text with special characters in the HANAVectorEmbeddings class.

Version 1.0.250923

Enhancements

  • Enhanced the outputs of tools when select_statement is too large by creating temporary tables with unique names.

  • Added additive_model_forecast_tools and intermittent_forecast df tools to the default tools in SmartDataFrame.

Version 1.0.250918

Enhancements

  • Added HANA table schema support for tools.

  • Improved output information for outlier detections.

  • Removed the hana_connection_context parameter from the HANAMLRAGAgent class and infer it from the tools.

  • Refine the default value of max_iterations parameter of HANAMLRAGAgent class parameters from 10 to 20.

  • Change the default value of vector_store_type parameter of HANAMLRAGAgent class from "faiss" to "hanadb".

  • Change the default value of long_term_db parameter of HANAMLRAGAgent class from sqlite to HANA DB.

  • Added the embedding_service parameter to the HANAMLRAGAgent class to allow users to pass their own embedding service. The default embedding service has been changed from GenAIHubEmbeddings to HANAVectorEmbeddings.

  • Added PAL CrossEncoder as the default cross-encoder model for reranking in the HANAMLRAGAgent class. If it is not available, it will fall back to sentence-transformers/all-MiniLM-L6-v2.

  • Added session_id parameter to the HANAMLRAGAgent class to support multiple sessions in long-term memory. By default, it is set to "global_session".

  • Removed the restriction to save memory into long term memory when the result is pandas data or large data. Now, all the results will be saved into long term memory with chunking and embeddings.

  • Deprecated the code template tool and python REPL tool in SmartDataFrame class. Users can use the tools from df_tools as default tools instead.

Version 1.0.250909

New Functions

  • Added TSMakeFutureTableTool to create a future table for time series forecasting.

  • Added SelectStatementToTableTool to execute a SELECT SQL statement and store the result in a new table.

Version 1.0.250904

Bug Fixes

  • Fixed the issue of calling code template tool.

Version 1.0.250707

Enhancements

  • Added vector_store_type parameter to HANAMLRAGAgent class to support different vector store types, including "hanadb" and "faiss".

  • Improved the HANAMLRAGAgent class to handle vector store initialization and updates more efficiently.

Bug Fixes

  • Fixed the parameter issues in HANAMLRAGAgent class by adding rerank_candidates and rerank_k parameters.

Version 1.0.250702

New Functions

  • Added HANAMLRagAgent class to enable Retrieval-Augmented Generation (RAG) capabilities, leveraging a hybrid short-term and long-term memory architecture with CrossEncoder reranking techniques.

Version 1.0.250630

New Functions

  • Added hdi artifacts tool.

Version 1.0.250617

New Functions

  • Added model deletion tool and chat history deletion tool to hanaml Agent.

Version 1.0.250530

Enhancements

  • Added unsupported tools check (classfication, regression).

  • BAS integration enhancements.

Version 1.0.250520

Enhancements

  • Added set_return_direct function in hanaml Agent.

Bug Fixes

  • Fixed the prompt in hanaml Agent to enable tool cal.

  • Fixed CAP generation temporary location in MacOS.

Version 1.0.250509

Enhancements

  • Output the inspect code for BAS integration.

Version 1.0.250506

Enhancements

  • Enhanced the seasonality detection for additive_model_forecast_tools.

  • Provide table meta information and supported algorithms in ts_check tool.

Version 1.0.250424

Enhancements

  • Added input table check and columns check to avoid stopping the reasoning.

  • Added samples to ts_check tool.

Bug Fixes

  • Fixed wrong report filename issue. (hana-ml appends _report.html to the file.)

Version 1.0.250411

Enhancements

  • Save observations to chat history in HANA ML agent. Added max_observations parameter to control the number of observations saved in the chat history.

  • Adjust the default value of fetch_data tool to return pandas indirectly to avoid chain stopping due to the tool call of fetch_data in the intermediate step.

Version 1.0.250410

Enhancements

  • Enhanced the HANA SQL agent to support case-sensitive SQL queries.

  • Added create_hana_sql_toolkit function to create a toolkit for HANA SQL.

  • Optimized the chat history management in HANA ML agent.

Bug Fixes

  • Fixed the accuracy_measure tool issue when evaluation_metric="spec".

Version 1.0.250407

Enhancements

  • Improved forecast_line_plot tool to automatically detect the confidence if it is not provided.

  • Serialized the tool's return if it is pandas DataFrame when return_direct is set to False.

Bug Fixes

  • Fixed the json serialization issue when the tool's return contains Timestamp.

Version 1.0.250403

New Functions

  • Added list_models tool to list all trained models in the model storage.

  • Added accuracy_measure tool to measure the accuracy of a model on a test dataset for time series forecasting.

Enhancements

  • Improved the intermittent_forecast tool to use CrostonTSB instead.

  • Added parameter return_direct to all tools and toolkit.

  • Improved the fetch_data tool to return a pandas DataFrame instead of a list of dictionaries. By default, the tool parameter return_direct is set to True, which means the tool will return a pandas DataFrame.