MiroFish Contributor 3ea9d10d25 fix: strip fabricated tool_result blocks to prevent LLM hallucination ... When the LLM generates a <tool_call> block followed by a self-generated <tool_result> block in the same response, the fake result must be stripped before appending to message history. The real tool result will be injected separately by the system. This fixes a React Hallucination bug where models could fabricate tool results that didn't actually come from tool invocations.		2026-04-21 00:02:58 +08:00
..
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 fabricated tool_result blocks to prevent LLM hallucination	2026-04-21 00:02:58 +08:00
utils	fix(i18n): validate Accept-Language header against registered locales	2026-04-02 14:20:15 +08:00
__init__.py	Implement Report Agent for automated report generation and interaction	2025-12-09 15:10:55 +08:00
config.py	fix(config): enable overriding of environment variables when loading .env file	2026-01-23 16:20:24 +08:00