feat: 增加 MiniMax Anthropic 兼容预设#153
Open
Ekko0303 wants to merge 4 commits into
Open
Conversation
改动说明： - 在 AI 控制台厂商预设中新增 MiniMax / Anthropic 兼容配置，默认 Base URL 为 https://api.minimaxi.com/anthropic，默认模型为 MiniMax-M2.7。 - 支持通过 MINIMAX_API_KEY、MINIMAX_BASE_URL、MINIMAX_MODEL 初始化 MiniMax 配置。 - 模型列表接口识别 MiniMax Anthropic 端点，并按 MiniMax 文档使用 Bearer Token 认证拉取模型列表。 - 更新 .env.example，仅增加 MiniMax 相关占位示例，不包含任何真实密钥。
Contributor
📝 WalkthroughWalkthroughAdds MiniMax as an Anthropic-compatible provider: new ChangesMiniMax Anthropic integration
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 3 | ❌ 2❌ Failed checks (2 warnings)
✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
interfaces/api/v1/workbench/llm_control.py (1)
108-133:⚠️ Potential issue | 🟠 MajorSeed the active profile's protocol and base URL when falling back.
Right now the fallback only copies
api_key, so requests that rely on the stored MiniMax profile still default toprotocol='openai'and an empty base URL. That skips_is_minimax_anthropic_base()and sends the wrong auth header unless the caller redundantly supplies the endpoint fields.🔧 Proposed fix
if not candidate.get('api_key'): # 尝试从当前激活配置中获取 key 作为 fallback active = _service.get_active_profile() if active: - candidate['api_key'] = active.api_key + candidate.update({ + 'api_key': active.api_key, + 'protocol': active.protocol, + 'base_url': active.base_url, + })🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@interfaces/api/v1/workbench/llm_control.py` around lines 108 - 133, When falling back to the active profile in the candidate block (use _service.get_active_profile() and the candidate dict), also copy the active profile's protocol and base_url into candidate (not just api_key) so api_format = (candidate.get('protocol')...) and base_url = (candidate.get('base_url')...) reflect the stored profile; this ensures _is_minimax_anthropic_base(base_url) sees the MiniMax endpoint and the correct auth header is selected instead of defaulting to openai/empty base URL.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Outside diff comments:
In `@interfaces/api/v1/workbench/llm_control.py`:
- Around line 108-133: When falling back to the active profile in the candidate
block (use _service.get_active_profile() and the candidate dict), also copy the
active profile's protocol and base_url into candidate (not just api_key) so
api_format = (candidate.get('protocol')...) and base_url =
(candidate.get('base_url')...) reflect the stored profile; this ensures
_is_minimax_anthropic_base(base_url) sees the MiniMax endpoint and the correct
auth header is selected instead of defaulting to openai/empty base URL.
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro Plus
Run ID: 587b1cf2-40d7-4a51-be80-ba95f44f14c0
📒 Files selected for processing (3)
.env.exampleapplication/ai/llm_control_service.pyinterfaces/api/v1/workbench/llm_control.py
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@application/ai/llm_control_service.py`:
- Line 262: The description string passed as the description parameter in
ai/llm_control_service.py uses fullwidth punctuation (fullwidth `；` and `，`)
which triggers Ruff RUF001; replace those characters with standard ASCII
punctuation (use `;` and `,`) in the description literal (the line containing
description='MiniMax Anthropic-compatible 接口；默认使用 MiniMax-M2.7，也可改为
MiniMax-M2.7-highspeed 等官方模型 ID。') so the text becomes ASCII-punctuated while
preserving the rest of the content.
- Around line 602-611: The MiniMax branch should respect an explicit
LLM_PROVIDER env var; modify the conditional around the minimax_key branch so it
only applies the MiniMax defaults when LLM_PROVIDER is not set/empty or
explicitly set to a MiniMax value (e.g., 'minimax'), rather than unconditionally
when minimax_key exists. Concretely, update the check that guards the
profiles[1].model_copy(...) and active_profile_id assignment to include a test
like os.getenv('LLM_PROVIDER', '').strip().lower() in ('', 'minimax') (or
equivalent) so that if a user sets LLM_PROVIDER to another provider the branch
is skipped and the active profile is not switched to MiniMax. Ensure you
reference the minimax_key variable, the profiles[1].model_copy(...) call, and
the active_profile_id assignment when making the change.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro Plus
Run ID: 4850b83a-e4be-4f9e-b280-79dce328584a
📒 Files selected for processing (2)
application/ai/llm_control_service.pyinterfaces/api/v1/workbench/llm_control.py
🚧 Files skipped from review as they are similar to previous changes (1)
- interfaces/api/v1/workbench/llm_control.py
| protocol='anthropic', | ||
| default_base_url='https://api.minimaxi.com/anthropic', | ||
| default_model='MiniMax-M2.7', | ||
| description='MiniMax Anthropic-compatible 接口；默认使用 MiniMax-M2.7，也可改为 MiniMax-M2.7-highspeed 等官方模型 ID。', |
Contributor
There was a problem hiding this comment.
Resolve Ruff RUF001 on ambiguous punctuation in preset description.
Line 262 uses fullwidth ； and ，, which Ruff flags as ambiguous unicode punctuation.
Suggested fix
- description='MiniMax Anthropic-compatible 接口；默认使用 MiniMax-M2.7，也可改为 MiniMax-M2.7-highspeed 等官方模型 ID。',
+ description='MiniMax Anthropic-compatible 接口; 默认使用 MiniMax-M2.7, 也可改为 MiniMax-M2.7-highspeed 等官方模型 ID。',📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| description='MiniMax Anthropic-compatible 接口；默认使用 MiniMax-M2.7，也可改为 MiniMax-M2.7-highspeed 等官方模型 ID。', | |
| description='MiniMax Anthropic-compatible 接口; 默认使用 MiniMax-M2.7, 也可改为 MiniMax-M2.7-highspeed 等官方模型 ID。', |
🧰 Tools
🪛 Ruff (0.15.13)
[warning] 262-262: String contains ambiguous ； (FULLWIDTH SEMICOLON). Did you mean ; (SEMICOLON)?
(RUF001)
[warning] 262-262: String contains ambiguous ， (FULLWIDTH COMMA). Did you mean , (COMMA)?
(RUF001)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@application/ai/llm_control_service.py` at line 262, The description string
passed as the description parameter in ai/llm_control_service.py uses fullwidth
punctuation (fullwidth `；` and `，`) which triggers Ruff RUF001; replace those
characters with standard ASCII punctuation (use `;` and `,`) in the description
literal (the line containing description='MiniMax Anthropic-compatible 接口；默认使用
MiniMax-M2.7，也可改为 MiniMax-M2.7-highspeed 等官方模型 ID。') so the text becomes
ASCII-punctuated while preserving the rest of the content.
Comment on lines
+602
to
+611
| elif minimax_key: | ||
| profiles[1] = profiles[1].model_copy(update={ | ||
| 'name': 'MiniMax / Anthropic', | ||
| 'preset_key': 'minimax-anthropic', | ||
| 'api_key': minimax_key, | ||
| 'base_url': (os.getenv('MINIMAX_BASE_URL') or '').strip() or 'https://api.minimaxi.com/anthropic', | ||
| 'model': (os.getenv('MINIMAX_MODEL') or '').strip() or 'MiniMax-M2.7', | ||
| 'temperature': 1.0, | ||
| }) | ||
| active_profile_id = profiles[1].id |
Contributor
There was a problem hiding this comment.
Honor explicit LLM_PROVIDER when selecting MiniMax defaults.
The MiniMax branch currently ignores LLM_PROVIDER. If users explicitly set another provider, this can still switch active profile to MiniMax unexpectedly.
Suggested fix
- elif minimax_key:
+ elif minimax_key and (llm_provider in ('anthropic', 'minimax') or not llm_provider):🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@application/ai/llm_control_service.py` around lines 602 - 611, The MiniMax
branch should respect an explicit LLM_PROVIDER env var; modify the conditional
around the minimax_key branch so it only applies the MiniMax defaults when
LLM_PROVIDER is not set/empty or explicitly set to a MiniMax value (e.g.,
'minimax'), rather than unconditionally when minimax_key exists. Concretely,
update the check that guards the profiles[1].model_copy(...) and
active_profile_id assignment to include a test like os.getenv('LLM_PROVIDER',
'').strip().lower() in ('', 'minimax') (or equivalent) so that if a user sets
LLM_PROVIDER to another provider the branch is skipped and the active profile is
not switched to MiniMax. Ensure you reference the minimax_key variable, the
profiles[1].model_copy(...) call, and the active_profile_id assignment when
making the change.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
改动说明：
变更类型
feat新功能fixBug 修复refactor重构（不影响功能）perf性能优化docs文档chore构建/工具链变更说明
架构影响
domain/application/infrastructure/interfaces/frontend/scripts（删除不适用项）测试
python -m uvicorn ...）npm run dev）风险说明
Summary by CodeRabbit