Md_Mushfiqur Rahim 11c525a1ac fix: strip hallucinated <tool_result> blocks in ReACT loop ... Prevents LLM-fabricated tool results from being appended to conversation history. Adds _sanitize_tool_results() and applies it to both _generate_section_react() and chat() code paths. System prompt is hardened with an explicit warning against fabricating <tool_result> content. Closes #529		2026-05-28 00:52:25 +00:00
..
api	fix(i18n): replace hardcoded Chinese stage names in simulation prepare SSE	2026-04-01 17:31:00 +08:00
models	feat(i18n): replace hardcoded Chinese in backend SSE progress messages	2026-04-01 16:32:10 +08:00
services	fix: strip hallucinated <tool_result> blocks in ReACT loop	2026-05-28 00:52:25 +00:00
utils	refactor: add type hints and FileParser.is_supported() helper	2026-05-23 14:57:46 +08:00
__init__.py	Implement Report Agent for automated report generation and interaction	2025-12-09 15:10:55 +08:00
config.py	refactor: add type hints and FileParser.is_supported() helper	2026-05-23 14:57:46 +08:00