Manmohan Sharma 6069a7329b fix: search veto for identity+greetings, grounding suffix for tool results ... Two bugs: (1) force-web-search toggle bypassed identity veto — 'who are u' with Search on hit Tavily and got personality-quiz garbage. Now we always check _is_identity_or_meta() which covers identity, creator, samosaChaat references AND greetings (hi/hello/hey/what's up) before honoring the force toggle. (2) Model ignored injected Tavily result and answered from training priors (e.g. generic VP bio instead of specific Armenia/Iran facts). Added a grounding suffix after <|output_end|> ('Based on the search results above, ' for web_search, 'The result is ' for calculator) so the model's next tokens condition on the fresh tool output instead of spinning up memory.		2026-04-22 16:08:59 -07:00
..
_model.py	feat: deploy d24 SFT + polished UI redesign with dark mode (#39)	2026-04-16 19:55:16 -04:00
_query_classifier.py	fix: auto-inject calculator tool call on arithmetic in user message	2026-04-22 16:04:26 -07:00
_tokenizer.py	feat: deploy d24 SFT + polished UI redesign with dark mode (#39)	2026-04-16 19:55:16 -04:00
_tools.py	fix(tools): enable Tavily include_answer and fix UI overflow	2026-04-22 14:20:47 -07:00
serve.py	fix: search veto for identity+greetings, grounding suffix for tool results	2026-04-22 16:08:59 -07:00