@ljoukov/llm 4.0.5 → 4.0.7

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -687,9 +687,10 @@ See `docs/agent-telemetry.md` for event schema, design rationale, and backend ad
687
687
 
688
688
  Each LLM call writes:
689
689
 
690
- - `request.txt`, `request.metadata.json`, and extracted attachments immediately,
691
- - streamed `thoughts.txt` and `response.txt` deltas during generation,
692
- - `response.metadata.json` at completion/failure (usage/cost/status/error).
690
+ - `request.txt`, `request.metadata.json`, `tool_call_response.txt` (when the request includes tool outputs), and `input-<n>.<ext>` attachments immediately,
691
+ - streamed `thoughts.txt` deltas during generation,
692
+ - `response.txt` for assistant text responses, `tool_call.txt` when the model asks to call tools, `output-<n>.<ext>` for inline output media, and `response.metadata.json` at completion,
693
+ - `error.txt` plus `response.metadata.json` on failure.
693
694
 
694
695
  `image_url` data URLs are redacted in text/metadata logs (`data:...,...`) so base64 payloads are not printed inline.
695
696