dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-05-30 17:24:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

cleanup openrouter/qwen/qwen-2.5-coder-32b-instruct in resources

Browse source
This commit is contained in:
Paul Gauthier 2024-11-20 15:33:00 -08:00
parent 1aaa3d9279
commit c93f3faed9
2 changed files with 3 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

6
HISTORY.md
View file

@ -4,15 +4,15 @@
### main branch ### main branch
- Added [`/editor` command](https://aider.chat/docs/usage/commands.html) to open system editor for writing prompts, by @thehunmonkgroup. - Added [`/editor` command](https://aider.chat/docs/usage/commands.html) to open system editor for writing prompts, by @thehunmonkgroup.
- Full support for `gpt-4o-2024-11-20`.
- Stream o1 models by default. - Stream o1 models by default.
- Added support for [optional multiline input tags](https://aider.chat/docs/usage/commands.html#entering-multi-line-chat-messages) with matching closing tags. - Added support for [optional multiline input tags](https://aider.chat/docs/usage/commands.html#entering-multi-line-chat-messages) with matching closing tags.
- Improved [model settings configuration](https://aider.chat/docs/config/adv-model-settings.html#global-extra-params) with support for global `extra_params` for `litellm.completion()`. - Improved [model settings configuration](https://aider.chat/docs/config/adv-model-settings.html#global-extra-params) with support for global `extra_params` for `litellm.completion()`.
- Architect mode now asks to add files suggested by the LLM. - Architect mode now asks to add files suggested by the LLM.
- Fixed bug in fuzzy model name matching. - Fixed bug in fuzzy model name matching.
- Added Timeout exception to handle API provider timeouts. - Added Timeout exception to handle API provider timeouts.
- Added `--show-release-notes` to control release notes display on first run. - Added `--show-release-notes` to control release notes display on first run of new version.
- Improved release notes display logic and user interaction flow. - Save empty dict to cache file on model metadata download failure, to delay retry.
- Save empty dict to cache file on model metadata download failure.
- Improved error handling and code formatting. - Improved error handling and code formatting.
- Aider wrote 53% of the code in this release. - Aider wrote 53% of the code in this release.

11
aider/resources/model-metadata.json
View file

@ -1,11 +0,0 @@
{
"openrouter/qwen/qwen-2.5-coder-32b-instruct": {
"max_tokens": 33792,
"max_input_tokens": 33792,
"max_output_tokens": 33792,
"input_cost_per_token": 0.00000018,
"output_cost_per_token": 0.00000018,
"litellm_provider": "openrouter",
"mode": "chat",
},
}