Conversation
|
@codex Please review this PR |
There was a problem hiding this comment.
Pull Request Overview
This PR adds support for new language models and updates existing model configurations. The changes include adding pricing information for new models and updating provider routing for existing ones.
- Adds two new models:
claude-haiku-4.5andqwen3-coder-pluswith their pricing configurations - Updates pricing information for
glm-4.6model - Updates provider order preferences for
glm-4.6anddeepseek-v3.1-terminusmodels
Reviewed Changes
Copilot reviewed 5 out of 5 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| src/ale_bench_eval/calc_cost.py | Adds pricing for claude-haiku-4.5 and qwen3-coder-plus, updates glm-4.6 pricing to include cache_read_mtok |
| llm_configs/qwen3-coder-plus.json | New configuration file for the qwen3-coder-plus model with OpenRouter provider settings |
| llm_configs/glm-4.6.json | Updates provider order from "parasail/fp8" to "z-ai" and removes top_k parameter |
| llm_configs/deepseek-v3.1-terminus.json | Changes provider order from "siliconflow/fp8" to "deepinfra/fp4" |
| llm_configs/claude-4.5-haiku.json | New configuration file for the claude-4.5-haiku model with reasoning enabled |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| "glm-4.5": ModelPrice(input_mtok=Decimal(59) / Decimal(100), output_mtok=Decimal(21) / Decimal(10)), | ||
| "glm-4.6": ModelPrice(input_mtok=Decimal(6) / Decimal(10), output_mtok=Decimal(21) / Decimal(10)), | ||
| "glm-4.6": ModelPrice( | ||
| input_mtok=Decimal(6) / Decimal(10), |
There was a problem hiding this comment.
[nitpick] The output_mtok price for glm-4.6 changed from 2.1 to 2.2. Consider documenting this pricing update in the commit message or changelog to clarify whether this is a correction or reflects an actual price change by the provider.
| input_mtok=Decimal(6) / Decimal(10), | |
| input_mtok=Decimal(6) / Decimal(10), | |
| # Updated output_mtok price for glm-4.6 from 2.1 to 2.2 as per provider's latest pricing (June 2024) |
|
Codex Review: Didn't find any major issues. Bravo. ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
No description provided.