Agent: Max Output Tokens + Thinking deaktivieren einstellbar
Zwei neue Agent-Einstellungen (Frontend, DB-Migration additiv): - MaxOutputTokens: hartes Ausgabelimit. CLI: CLAUDE_CODE_MAX_OUTPUT_TOKENS, API: max_tokens (statt hart 16384). 0 = aus. - DisableThinking: CLI: CLAUDE_CODE_DISABLE_THINKING=1 + MAX_THINKING_TOKENS=0; entfernt CLAUDE_CODE_EFFORT_LEVEL (Explizit-Aus schlaegt Effort). API-Pfad ohne Aequivalent (Hint im UI). Die einzigen zwei Parameter, die z.ai/GLM nachweislich honoriert (Sampling-Parameter wie temperature/top_p werden dort still verworfen). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
1 parent
7305a5a50f
commit
81892d6e65
13 files changed
+88
-9
No files matched your search
@@ -18,6 +18,8 @@ public class ChatContext
|
||||
public bool UseMemory { get; set; }
|
||||
public string WebSearchVersion { get; set; }
|
||||
public string Effort { get; set; }
|
||||
public int MaxOutputTokens { get; set; } // 0 = aus (Modell-Default)
|
||||
public bool DisableThinking { get; set; } // nur CLI-Pfad wirksam
|
||||
public int MaxIterations { get; set; }
|
||||
public AgentRecord Agent { get; set; }
|
||||
public SessionRecord Session { get; set; }
|
||||
|
||||
Reference in new issue
Block a user