| Age | Commit message (Collapse) | Author | Lines |
|---|
|
* Add config options subquery and subquery_max_depth.
* Register an internal subquery function that spawns a fresh LLM query
with the current model configuration but without the full context.
The model selects context numerically (message_indexes) or by text
excerpt (excerpts).
* Subqueries can use tools, including further nested subqueries up to
subquery_max_depth.
* Queries and subqueries get hierarchical ids ([0], [0/1], [0/1/2])
that prefix tool-call prints and spinner messages.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
(#1054)
|
|
append_command_to_history_file => save_shell_history
|
|
- check the model type while retrieve model
- select chat/reranker model even if it is missed in client models
- find predefined-models for openai-compatible client with startsWith
- remove client::ApiType
|
|
|
|
|
|
|
|
|
|
* feat: agent supports dynamic instructions
* change tool calls' null output to 'TODO'
* REPL don't print banner if use agent/rag
|
|
|
|
|
|
- rename MessageContent:ToolResults to MessageContent:ToolCalls
- rename ToolResults to MessageContentToolCalls
- persist tool_calls to messages.md
|
|
|
|
|
|
|
|
|
|
- set max default_chuck_size to 2000
- set default rag_top_k to 4
- change reciprocal_rank_fusion weights
|
|
|
|
|
|
|
