| Age | Commit message (Collapse) | Author | Lines |
|
- Add timeout, retries, retry_delay_ms, and retry_max_delay_ms options to
client extra config to bound long-running requests and retry failed
attempts with exponential backoff.
- Apply a total request timeout via reqwest .timeout().
- Implement retry with exponential backoff for non-streaming and streaming
chat completions.
- Disable reqwest-eventsource internal auto-reconnect so it does not loop
forever; outer retry logic is now the single owner of retry behavior.
- Document the new options in config.example.yaml.
|
|
|
|
* 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.
|
|
|
|
|
|
Co-authored-by: Aman Shaw <amanshaw4511@protonmail.com>
Co-authored-by: aman <aman.saw@batonsystems.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|