admin/0pt
5
0
Fork 0
Code Issues 9 Pull Requests Actions Packages Projects Releases Wiki Activity

fix(decision-ollama): native JSON-läge utan thinking #445

Merged
admin merged 1 commits from fix/ollama-native-json into main 2026-11-02 16:52:32 +00:00
Conversation 0 Commits 1 Files Changed 2
+44 -22
1 Commits
Author SHA1 Message Date
admin 8b571cf2f4 fix(decision-ollama): use Ollama's native JSON mode without thinking
CI (SIAX Cloud) / integration (push) Skipped
Details
CI (SIAX Cloud) / sonar (push) Skipped
Details
CI (SIAX Cloud) / sonar (pull_request) Skipped
Details
masterplan-lock / check (pull_request) Successful in 5s
Details
Security Scan (SIAX Cloud) / security (push) Successful in 14s
Details
CI (SIAX Cloud) / security (push) Successful in 17s
Details
masterplan-lock / check (push) Successful in 17s
Details
CI (SIAX Cloud) / security (pull_request) Successful in 20s
Details
Security Scan (SIAX Cloud) / security (pull_request) Successful in 21s
Details
CI (SIAX Cloud) / integration (pull_request) Successful in 54s
Details
CI (SIAX Cloud) / quality (push) Successful in 1m24s
Details
CI (SIAX Cloud) / quality (pull_request) Successful in 1m29s
Details 
The 9B model spent its whole 4000-token budget on reasoning and came back
model_incomplete. Call /api/chat with format=json, think=false and num_predict,
and read prompt_eval_count/eval_count/done_reason. Structured extraction no
longer needs chain-of-thought.
 2026-11-02 17:51:09 +01:00