exo/lm-lib
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: enhance LLM call control with AgentSkipCompletion enum and update related methods

Browse Source
This commit is contained in:
extio-de
2026-06-02 22:17:51 +02:00
parent 14f43624db
commit 4453b7c2d1
4 changed files with 137 additions and 115 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@@ -1069,7 +1069,13 @@ If `context.setStreaming(true)` is enabled and the handler implements `StreamedA
### Skipping LLM Calls
Set `context.setSkipNextCompletion(true)` to turn the next step into a processing-only pass. The flag resets automatically after that step.
Use `context.setSkipNextCompletion(...)` to control LLM call behavior for the next step. The flag resets automatically after that step.
| Value | Behavior |
|-------|----------|
| `AgentSkipCompletion.NO_SKIP` | Executes the LLM call normally (default) |
| `AgentSkipCompletion.SETUP_CONVERSATION_ONLY` | Sets up the conversation but skips the LLM call |
| `AgentSkipCompletion.SKIP` | Skips the entire turn, including conversation setup |
### Cache Bypass Controls