Conversation
Summary of ChangesHello @ding113, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request focuses on a significant set of bug fixes and minor enhancements across various components of the application. The changes aim to improve the stability, reliability, and user experience by resolving several reported issues, refining API testing mechanisms, and updating model configurations. The update also includes the addition of new AI models and improved logging practices. Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces a version bump, updates the changelog, and adds several new AI model definitions to the pricing data. The changes are extensive and seem to cover multiple bug fixes and enhancements. My review focused on the consistency and maintainability of the new data added to the litellm-prices.json file. I've identified a duplicated model entry and a potential inconsistency in model capabilities that could affect maintainability. The other changes appear to be in good order.
| "claude-sonnet-4-5-20250929-v1:0": { | ||
| "cache_creation_input_token_cost": 3.75e-06, | ||
| "cache_read_input_token_cost": 3e-07, | ||
| "input_cost_per_token": 3e-06, | ||
| "input_cost_per_token_above_200k_tokens": 6e-06, | ||
| "output_cost_per_token_above_200k_tokens": 2.25e-05, | ||
| "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, | ||
| "cache_read_input_token_cost_above_200k_tokens": 6e-07, | ||
| "litellm_provider": "bedrock", | ||
| "max_input_tokens": 200000, | ||
| "max_output_tokens": 64000, | ||
| "max_tokens": 64000, | ||
| "mode": "chat", | ||
| "output_cost_per_token": 1.5e-05, | ||
| "supports_assistant_prefill": true, | ||
| "supports_computer_use": true, | ||
| "supports_function_calling": true, | ||
| "supports_pdf_input": true, | ||
| "supports_prompt_caching": true, | ||
| "supports_reasoning": true, | ||
| "supports_response_schema": true, | ||
| "supports_tool_choice": true, | ||
| "supports_vision": true, | ||
| "tool_use_system_prompt_tokens": 159 | ||
| }, |
There was a problem hiding this comment.
There's an inconsistency in the properties for this model compared to its anthropic. prefixed counterpart (anthropic.claude-sonnet-4-5-20250929-v1:0). This entry is missing the search_context_cost_per_query object. If this is an oversight and the model supports this feature via the bedrock provider, please consider adding it for consistency and to ensure correct cost calculation. If the feature is not supported, this difference is fine.
| "us.anthropic.claude-opus-4-5-20251101-v1:0": { | ||
| "cache_creation_input_token_cost": 6.25e-06, | ||
| "cache_read_input_token_cost": 5e-07, | ||
| "input_cost_per_token": 5e-06, | ||
| "litellm_provider": "bedrock_converse", | ||
| "max_input_tokens": 200000, | ||
| "max_output_tokens": 64000, | ||
| "max_tokens": 64000, | ||
| "mode": "chat", | ||
| "output_cost_per_token": 2.5e-05, | ||
| "search_context_cost_per_query": { | ||
| "search_context_size_high": 0.01, | ||
| "search_context_size_low": 0.01, | ||
| "search_context_size_medium": 0.01 | ||
| }, | ||
| "supports_assistant_prefill": true, | ||
| "supports_computer_use": true, | ||
| "supports_function_calling": true, | ||
| "supports_pdf_input": true, | ||
| "supports_prompt_caching": true, | ||
| "supports_reasoning": true, | ||
| "supports_response_schema": true, | ||
| "supports_tool_choice": true, | ||
| "supports_vision": true, | ||
| "tool_use_system_prompt_tokens": 159 | ||
| }, |
There was a problem hiding this comment.
There appears to be a duplicated model definition. The entry for us.anthropic.claude-opus-4-5-20251101-v1:0 is identical to the entry for anthropic.claude-opus-4-5-20251101-v1:0 added earlier in this file. This duplication can lead to maintenance issues. If these are meant to be the same, please consider removing one. If they are for different regions with potentially different pricing or capabilities in the future, it would be good to either reflect the current differences or add a comment clarifying this.
ding113
left a comment
ding113
left a comment
There was a problem hiding this comment.
📋 Code Review Summary
This PR merges release changes from main to dev, containing version 0.3.10 updates. The changes are exclusively documentation (CHANGELOG.md), version metadata (VERSION), and static model pricing data (litellm-prices.json). No executable code changes are present.
🔍 Issues Found
- Critical (🔴): 0 issues
- High (🟠): 0 issues
- Medium (🟡): 0 issues
- Low (🟢): 0 issues
🎯 Priority Actions
No significant issues identified. The PR consists entirely of:
- Version bump from 0.3.9 to 0.3.10
- Changelog documentation for PR #199 bug fixes and features
- New model pricing entries (Claude Opus 4.5, Sonnet 4.5 variants, embedding model)
- Capability flag updates for existing models
💡 General Observations
- The JSON data is syntactically valid
- New model entry structures are consistent with existing patterns
- All changes are backward-compatible static data additions
🤖 Automated review by Claude AI - focused on identifying issues for improvement
ding113
left a comment
ding113
left a comment
There was a problem hiding this comment.
📋 Code Review Summary
This PR merges release changes from main to dev, containing version 0.3.10 updates. The changes are exclusively documentation (CHANGELOG.md), version metadata (VERSION), and static model pricing data (litellm-prices.json). No executable code changes are present.
🔍 Issues Found
- Critical (🔴): 0 issues
- High (🟠): 0 issues
- Medium (🟡): 0 issues
- Low (🟢): 0 issues
🎯 Priority Actions
No significant issues identified. The PR consists entirely of:
- Version bump from 0.3.9 to 0.3.10
- Changelog documentation for PR #199 bug fixes and features
- New model pricing entries (Claude Opus 4.5, Sonnet 4.5 variants, embedding model)
- Capability flag updates for existing models
💡 General Observations
- The JSON data is syntactically valid
- New model entry structures are consistent with existing patterns
- All changes are backward-compatible static data additions
🤖 Automated review by Claude AI - focused on identifying issues for improvement
1 participant
Summary
This PR fixes multiple bugs related to provider statistics, group settings persistence, and usage records filtering. It also updates model pricing data and bumps the version to 0.3.10.
Problem
Several issues were affecting user experience:
Provider statistics mismatch (供应商管理的统计和使用记录有出入 #204): When requests were retried on a different provider after initial failure, the statistics were incorrectly attributed to the first provider, causing discrepancies between provider management statistics and usage records.
Group settings not saved ([bug] group not saved #201): Provider group name and user group settings were not being persisted to the database after modification.
Usage records date filtering (使用记录的筛选条件那里有错误 #198): Current day's usage records were not displayed when filtering by date range (e.g., from 00:00 to current time).
Solution
Changes
anthropic.claude-opus-4-5-20251101-v1:0(Bedrock)anthropic.claude-sonnet-4-5-20250929-v1:0(Bedrock)claude-sonnet-4-5-20250929-v1:0(Bedrock)claude-opus-4-5-20251101(Anthropic)us.anthropic.claude-opus-4-5-20251101-v1:0(Bedrock US)text-embedding-ada-002-v2(OpenAI)Testing
Related Issues
Closes #204, #201, #198