aj/Breehavior-Monitor
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Switch to max_completion_tokens for newer OpenAI models

Browse Source 
gpt-5-nano and other newer models require max_completion_tokens
instead of max_tokens. The new parameter is backwards compatible
with older models.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
AJ Isaacs
2026-02-24 17:07:44 -05:00
parent dd0d18b0f5
commit a0edf90ebd
2 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
utils/llm_client.py
View File

@@ -164,7 +164,7 @@ class LLMClient:
tools=[ANALYSIS_TOOL],
tool_choice={"type": "function", "function": {"name": "report_analysis"}},
temperature=0.1,
max_tokens=2048,
max_completion_tokens=2048,
)
elapsed = int((time.monotonic() - t0) * 1000)
@@ -292,7 +292,7 @@ class LLMClient:
*patched,
],
temperature=0.9,
max_tokens=2048,
max_completion_tokens=2048,
frequency_penalty=0.8,
presence_penalty=0.6,
stream=True,
@@ -357,7 +357,7 @@ class LLMClient:
{"role": "user", "content": user_content},
],
temperature=0.8,
max_tokens=2048,
max_completion_tokens=2048,
stream=True,
)
@@ -418,7 +418,7 @@ class LLMClient:
tools=[ANALYSIS_TOOL],
tool_choice={"type": "function", "function": {"name": "report_analysis"}},
temperature=0.1,
max_tokens=2048,
max_completion_tokens=2048,
)
elapsed = int((time.monotonic() - t0) * 1000)