a128db8393
Merge pull request #1822 from PeterDaveHelloKitchen/Gemini-2.5-Flash
...
Complete Gemini 2.5 Flash model info
2025-05-26 07:48:33 +03:00
2453508023
Merge pull request #1805 from group-3-sPRinter/improve/token_handler
...
Refactor count_tokens method structure in token_handler.py for better extensibility
2025-05-25 12:11:41 +03:00
84f2f4fe3d
Fix: use ModelTypeValidator static methods directly
2025-05-25 18:00:38 +09:00
4cdaad1fc5
Merge pull request #1816 from TaskerJang/feature/clip-tokens-tests-and-docs
...
Add Unit Tests and Improve Documentation for utils.py clip_tokens Function
2025-05-25 08:18:26 +03:00
4047e71268
Complete Gemini 2.5 Flash model info
2025-05-24 23:52:18 +08:00
43dbe24a7f
Merge pull request #1817 from PeterDaveHelloKitchen/Grok-3
...
Add Grok-3 non-beta model IDs
2025-05-24 16:32:50 +03:00
f4a9bc3de7
Merge pull request #1814 from hirobf10/support-claude-4
...
feat: add support for Claude 4 family
2025-05-24 16:29:48 +03:00
95c94b80a2
Add Grok-3 non-beta model IDs
2025-05-24 14:22:55 +08:00
e2586cb64a
docs: improve clip_tokens function docstring and add examples
2025-05-24 10:46:58 +09:00
1f836e405d
fix: reflect comments
2025-05-24 09:45:27 +09:00
10703a9098
feat: add support for Claude 4
2025-05-23 14:16:44 +09:00
466ec4ce90
fix: exclude RateLimitError from retry logic
2025-05-22 15:04:16 +09:00
facfb5f46b
Add missing code: use_context=False
2025-05-22 13:32:20 +09:00
cc686ef26d
Reorder model check: OpenAI before Anthropic
...
OpenAI is the default in most cases, so checking it first skips unnecessary Anthropic logic.
2025-05-22 13:12:04 +09:00
ead7491ca9
Apply convention for marking private
2025-05-21 18:08:48 +09:00
df0355d827
Remove member variable for restroring get_settings()
2025-05-21 18:07:47 +09:00
c3ea048b71
Restore original return logic for force_accurate condition
2025-05-21 17:52:51 +09:00
648829b770
Rename method
2025-05-21 17:51:03 +09:00
6405284461
fix: reorder exception handling to enable proper retry behavior
2025-05-20 18:22:33 +09:00
97f2b6f736
Fix TypeError
2025-05-20 15:29:27 +09:00
f198e6fa09
Add constants and improve token calculation logic
2025-05-20 14:12:24 +09:00
e72bb28c4e
Replace get_settings() with self.settings
2025-05-20 13:50:30 +09:00
81fa22e4df
Add model name validation
2025-05-20 13:47:15 +09:00
db5138dc42
Improve YAML parsing with additional fallback strategies for AI predictions
2025-05-17 20:38:05 +03:00
c15fb16528
Merge pull request #1779 from dnnspaul/main
...
Enable usage of OpenAI like APIs
2025-05-16 16:59:18 +03:00
9974015682
Add Gemini-2.5-pro-preview-05-06 model and update litellm dependency
2025-05-16 16:32:45 +03:00
05ab5f699f
Improve token calculation logic based on model type
...
- Rename calc_tokens to get_token_count_by_model_type for clearer intent
- Separate model type detection logic to improve maintainability
2025-05-16 17:51:22 +09:00
250870a3da
enable usage of openai like apis
2025-05-15 16:05:05 +02:00
7a6a28d2b9
feat: add openrouter support in litellm
2025-05-07 11:54:07 +07:00
f505c7ad3c
Add multi-model support for different reasoning tasks
2025-04-27 11:00:34 +03:00
c951fc9a87
Improve dynamic context handling with partial line matching and adjust model configuration
2025-04-27 10:46:23 +03:00
3f194e6730
Improve dynamic context handling in git patch processing
2025-04-27 10:07:56 +03:00
f53bd524c5
Support multiple model types for different reasoning tasks
2025-04-27 08:50:03 +03:00
4ac0aa56e5
Update model references from o3-mini to o4-mini and add Gemini models
2025-04-19 09:26:35 +03:00
869a179506
feat: add support for Mistral and Codestral models
2025-04-18 14:04:59 +09:00
4e3e963ce5
Add OpenAI o3 & 4o-mini reasoning models
...
Reference:
- https://platform.openai.com/docs/models/o3
- https://platform.openai.com/docs/models/o4-mini
- https://openai.com/index/introducing-o3-and-o4-mini/
2025-04-17 02:32:14 +08:00
27a7c1a94f
doc update and minor fix
2025-04-16 13:32:53 +05:30
dc46acb762
doc update and minor fix
2025-04-16 13:27:52 +05:30
0da667d179
support Azure AD authentication for OpenAI services for litellm implemetation
2025-04-16 11:19:04 +05:30
08bf9593b2
Fix tokenizer fallback to use o200k_base instead of cl100k_base
2025-04-14 21:15:19 +03:00
57808075be
Add support of OpenAI GPT-4.1 model family
...
Reference:
- https://openai.com/index/gpt-4-1/
- https://platform.openai.com/docs/models/gpt-4.1
2025-04-15 01:57:46 +08:00
60ace1ed09
Merge pull request #1685 from imperorrp/add_gemini2.5preview
...
Add support of Gemini 2.5 Pro preview model
2025-04-11 09:54:09 +03:00
7f6014e064
Merge pull request #1684 from PeterDaveHelloKitchen/Support-xAI-Grok
...
Add support of xAI and their Grok-2 & Grok-3 model
2025-04-11 09:53:08 +03:00
0ac7028bc6
Support xAI Grok-3 series models
...
Reference:
- https://docs.x.ai/docs/release-notes#april-2025
2025-04-11 00:40:00 +08:00
eb9c4fa110
add gemini 2.5 pro preview model token limit
2025-04-08 20:41:59 +05:30
83bb3b25d8
Add support of Meta's Llama 4 Scout and Maverick 17b from Groq Cloud
...
Reference:
- https://ai.meta.com/blog/llama-4-multimodal-intelligence/
- https://console.groq.com/docs/models#preview-models
- https://groq.com/llama-4-now-live-on-groq-build-fast-at-the-lowest-cost-without-compromise/
2025-04-08 01:47:15 +08:00
665fb90a98
Add support of xAI and their Grok-2 model
...
Close #1630
2025-04-08 01:36:21 +08:00
9b19fcdc90
Add support of OpenAI GPT-4.5 Preview model
...
Reference:
- https://openai.com/index/introducing-gpt-4-5/
- https://platform.openai.com/docs/models/gpt-4.5-preview
2025-04-04 05:13:15 +08:00
14971c4f5f
Add support for documentation content exceeding token limits ( #1670 )
...
* - Add support for documentation content exceeding token limits via two phase operation:
1. Ask LLM to rank headings which are most likely to contain an answer to a user question
2. Provide the corresponding files for the LLM to search for an answer.
- Refactor of help_docs to make the code more readable
- For the purpose of getting canonical path: git providers to use default branch and not the PR's source branch.
- Refactor of token counting and making it clear on when an estimate factor will be used.
* Code review changes:
1. Correctly handle exception during retry_with_fallback_models (to allow fallback model to run in case of failure)
2. Better naming for default_branch in bitbucket cloud provider
2025-04-03 11:51:26 +03:00
8495e4d549
More comprehensive handling in count_tokens(force_accurate==True): In case model is neither OpenAI nor Anthropic Claude, simply use an elbow room factor in order to force a more conservative estimate.
2025-03-24 15:47:35 +02:00
