llama-stack-mirror/llama_stack/providers/remote
skamenan7 a0a8b86fc8 fix(brave-search): change tool name and standardize response format
- Change tool name from 'web_search' to 'web_search_brave' to avoid conflicts with Tavily
- Standardize response format to JSON with 'query' and 'top_k' fields for consistency
- Remove built_in_type parameter from ToolDef to match Tavily implementation
- Return structured dict instead of string from _clean_result_by_type method

Fixes #2606: Resolves tool name conflicts and response format inconsistencies
that were causing non-deterministic behavior and poor user experience
2025-07-14 10:30:21 -04:00
..
agents test: add unit test to ensure all config types are instantiable (#1601) 2025-03-12 22:29:58 -07:00
datasetio fix: allow default empty vars for conditionals (#2570) 2025-07-01 14:42:05 +02:00
eval refactor(env)!: enhanced environment variable substitution (#2490) 2025-06-26 08:20:08 +05:30
inference fix: Don't cache clients for passthrough auth providers (#2728) 2025-07-11 13:38:27 -07:00
post_training fix: allow default empty vars for conditionals (#2570) 2025-07-01 14:42:05 +02:00
safety fix: sambanova shields and model validation (#2693) 2025-07-11 16:29:15 -04:00
tool_runtime fix(brave-search): change tool name and standardize response format 2025-07-14 10:30:21 -04:00
vector_io chore: Adding unit tests for OpenAI vector stores and migrating SQLite-vec registry to kvstore (#2665) 2025-07-10 14:22:13 -04:00
__init__.py impls -> inline, adapters -> remote (#381) 2024-11-06 14:54:05 -08:00