dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-06-01 10:14:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

copy

Browse source
This commit is contained in:
Paul Gauthier 2025-03-07 19:09:13 -08:00
parent 9aacf5c7db
commit e0cef55fcd
4 changed files with 578 additions and 581 deletions
Download patch file Download diff file Expand all files Collapse all files

3
HISTORY.md
View file

@ -2,6 +2,7 @@
### main branch
- Display thinking/reasoning content from LLMs which return it.
- Enhanced handling of reasoning tags to better clean up model responses.
- Improved error handling for EOF (Ctrl+D) in user input prompts.
- Added helper function to ensure hex color values have a # prefix.
@ -13,7 +14,7 @@
- Improved empty LLM response handling with clearer warning messages.
- Fixed Git identity retrieval to respect global configuration, by Akira Komamura.
- Offer to install dependencies for Bedrock and Vertex AI models.
- Aider wrote 81% of the code in this release.
- Aider wrote 82% of the code in this release.
### Aider v0.75.3

3
aider/website/HISTORY.md
View file

@ -25,6 +25,7 @@ cog.out(text)
### main branch
- Display thinking/reasoning content from LLMs which return it.
- Enhanced handling of reasoning tags to better clean up model responses.
- Improved error handling for EOF (Ctrl+D) in user input prompts.
- Added helper function to ensure hex color values have a # prefix.
@ -36,7 +37,7 @@ cog.out(text)
- Improved empty LLM response handling with clearer warning messages.
- Fixed Git identity retrieval to respect global configuration, by Akira Komamura.
- Offer to install dependencies for Bedrock and Vertex AI models.
- Aider wrote 81% of the code in this release.
- Aider wrote 82% of the code in this release.
### Aider v0.75.3

1140
aider/website/assets/sample-analytics.jsonl
View file

File diff suppressed because it is too large Load diff

13
aider/website/docs/faq.md
View file

@ -249,17 +249,12 @@ tr:hover { background-color: #f5f5f5; }
</style>
<table>
<tr><th>Model Name</th><th class='right'>Total Tokens</th><th class='right'>Percent</th></tr>
<tr><td>anthropic/claude-3-7-sonnet-20250219</td><td class='right'>219,958</td><td class='right'>60.6%</td></tr>
<tr><td>openrouter/REDACTED</td><td class='right'>110,364</td><td class='right'>30.4%</td></tr>
<tr><td>o3-mini</td><td class='right'>25,643</td><td class='right'>7.1%</td></tr>
<tr><td>deepseek/deepseek-reasoner</td><td class='right'>4,432</td><td class='right'>1.2%</td></tr>
<tr><td>fireworks_ai/accounts/fireworks/models/deepseek-r1</td><td class='right'>2,765</td><td class='right'>0.8%</td></tr>
<tr><td>anthropic/claude-3-7-sonnet-20250219</td><td class='right'>1,948,550</td><td class='right'>99.0%</td></tr>
<tr><td>fireworks_ai/accounts/fireworks/models/deepseek-r1</td><td class='right'>14,961</td><td class='right'>0.8%</td></tr>
<tr><td>deepseek/deepseek-reasoner</td><td class='right'>4,430</td><td class='right'>0.2%</td></tr>
<tr><td>o3-mini</td><td class='right'>97</td><td class='right'>0.0%</td></tr>
<tr><td>claude-3-7-sonnet-20250219</td><td class='right'>93</td><td class='right'>0.0%</td></tr>
</table>
{: .note :}
Some models show as REDACTED, because they are new or unpopular models.
Aider's analytics only records the names of "well known" LLMs.
<!--[[[end]]]-->
## How are the "aider wrote xx% of code" stats computed?