Skip to content

[Config]: 1.2.44版本中,设置上下文最大值,是写0.5M还是512K呢 #1797

Description

@heiheiheibj

接入模式

纯 API

上游协议

Chat Completions

Base URL

https://tokenrhythm.studio/v1

相关 config.toml / auth.json 片段

model = "deepseek-v4-flash-0731"

model_provider = "custom"

notify = [ "C:\\Users\\Administrator\\AppData\\Local\\OpenAI\\Codex\\runtimes\\cua_node\\fb8898c05a62885e\\bin\\node_modules\\@oai\\sky\\bin\\windows\\codex-computer-use.exe", "turn-ended" ]
model_catalog_json = "model-catalogs/relay-ms7j3w59.json"

[model_providers.custom]
name = "custom"
wire_api = "responses"
requires_openai_auth = true
base_url = "http://127.0.0.1:57321/v1"

问题描述

刚才一直提示messages.65.reasoning_content 长度超过允许上限,连/new都不行。
我看默认是1M,把上下文改为512K和0.5M都不行,不知道是模型问题还是设置的值不对。

日志 / 状态文件

提交前确认

  • 我已经脱敏了 API Key、Token、账号等敏感信息。

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions