jpmschweitzer/odysseus
1
0
Fork 0
mirror of https://github.com/pewdiepie-archdaemon/odysseus.git synced 2026-10-18 04:42:20 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix(thinking): add deepseek-v4 to thinking model patterns (#6000)

Browse Source 
* fix(thinking): add deepseek-v4 to thinking model patterns

deepseek-v4-flash emits reasoning_content via the API but was not
recognized in _THINKING_MODEL_PATTERNS (only deepseek-r1 and
deepseek-reasoner were listed). Add the deepseek-v4 prefix so
the model is recognized as thinking-capable.

The between-round _thinkOpen leakage was separately fixed by
PR #5931 (perf(chat): batch live thinking rendering).

Related: #3998, #5931

* test(thinking): cover DeepSeek v4 detection

---------

Co-authored-by: Alexandre Teixeira <alexandremagteixeira@gmail.com>
Co-authored-by: Alexandre Teixeira <111787685+alteixeira20@users.noreply.github.com>
This commit is contained in:
Eduardo
2026-08-12 04:26:13 +01:00
committed by GitHub
co-authored by Alexandre Teixeira Alexandre Teixeira
parent 937c883c41
commit 1939a6ad2d
2 changed files with 29 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llm_core.py
+2 -2
View File
@@ -1319,8 +1319,8 @@ _MISTRAL_REASONING_EFFORT = os.getenv("ODYSSEUS_MISTRAL_REASONING_EFFORT", "high
# Models that support structured thinking — may output </think> without opening tag
_THINKING_MODEL_PATTERNS = (
"qwen3", "qwq", "deepseek-r1", "deepseek-reasoner", "minimax",
"m2-reap", "gemma", "stepfun", "step-3", "step3",
"qwen3", "qwq", "deepseek-r1", "deepseek-reasoner", "deepseek-v4",
"minimax", "m2-reap", "gemma", "stepfun", "step-3", "step3",
"magistral", "mistral-small", "mistral-medium",
)