feat(wafer/kimi-k3-fast): add new models [bot] - #1964
Conversation
|
/test-models |
Gateway test setup failed for
|
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 2fc10fa. Configure here.
|
/test-models |
Gateway test results
Failures (1)
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.chat.completions.create(
model="test-v2-wafer/kimi-k3-fast",
messages=[
{"role": "user", "content": "List 3 colors with their hex codes in JSON."},
],
response_format={"type": "json_object"},
stream=True,
)
import json as _json
_accumulated = ""
for chunk in response:
if chunk.choices and len(chunk.choices) > 0:
delta = chunk.choices[0].delta
if delta.content is not None:
_accumulated += delta.content
print(delta.content, end="", flush=True)
if not _accumulated:
raise Exception("VALIDATION FAILED: json-output stream - no content received")
_json.loads(_accumulated)
print("\nVALIDATION: json-output stream SUCCESS")Successes (9)
Output
Output
Output
Output
Output
Output
Output
Output
Output |

Auto-generated by model-addition-agent for
wafer/kimi-k3-fast.Note
Low Risk
Metadata-only YAML addition with no runtime or routing logic changes.
Overview
Adds a new Wafer provider definition for
kimi-k3-fast, registering it as an active serverless chat model sourced from Wafer’s models API.The entry documents 1M-token context, text + image input, thinking support, and modes chat and responses, with features including function calling, structured/JSON output, and per-token pricing (including cache-read input cost).
Reviewed by Cursor Bugbot for commit 2fc10fa. Bugbot is set up for automated code reviews on this repo. Configure here.