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
8bdd11646c
Fix token assignment in Bitbucket provider authentication
2025-04-12 10:07:45 +03:00
a649e323d3
Merge pull request #1683 from wirelessr/feat/issue-1681
...
Support Bitbucket Basic Auth
2025-04-11 14:37:56 +03:00
7a32faf64f
Fix Bearer backward compatibility logic
2025-04-11 17:44:46 +08:00
5f2d4d400e
Extract repeated token retrieval logic into a helper function to reduce code duplication
2025-04-11 16:20:28 +08:00
0cbf65dab6
Update pr_agent/git_providers/bitbucket_provider.py
...
Co-authored-by: Prateek <110811408+Prateikx@users.noreply.github.com >
2025-04-11 14:59:27 +08:00
c0c307503f
Update pr_agent/git_providers/bitbucket_provider.py
...
Co-authored-by: Prateek <110811408+Prateikx@users.noreply.github.com >
2025-04-11 14:55:06 +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
e4f40da35c
Merge pull request #1680 from PeterDaveHelloKitchen/Add-Groq-Llama-4-scout-and-maverick-17b
...
Add support of Meta's Llama 4 Scout and Maverick 17b from Groq Cloud
2025-04-11 09:51:21 +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
526d7ff5d2
Update default number of code suggestions per chunk from 4 to 3
2025-04-09 08:24:26 +03:00
cdc354c33b
disable dynamic variables
2025-04-08 21:07:45 +03:00
eb9c4fa110
add gemini 2.5 pro preview model token limit
2025-04-08 20:41:59 +05:30
ca95e876eb
Enhance Bitbucket provider functionality and update secret configuration template.
2025-04-08 17:52:52 +08:00
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
d938ff05ef
Merge pull request #1667 from jmrtnz94/1592_ENVLogLevel
...
Update logging configuration to use dynamic log level from settings
2025-04-04 11:31:44 +03:00
b7b533ddf6
Update azuredevops logger setup to use dynamic log level from configuration
2025-04-03 14:10:52 -05:00
7987fd1be7
Update bitbucket logger setup to use dynamic log level from configuration
2025-04-03 14:10:11 -05:00
db06a8e49e
Update github logger setup to use dynamic log level from configuration
2025-04-03 14:09:11 -05:00
4fa2d82179
Set default log level to DEBUG in configuration and logger setup
2025-04-03 14:07:10 -05:00
9254225949
fix: add error handling for missing review data in PR reviewer
2025-04-03 13:23:41 +03:00
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
3b0225544a
Fix code example in PR reviewer prompts to correctly show added line
2025-04-02 08:23:01 +03:00
dbfc07ccc1
Update logging configuration to use dynamic log level from settings
2025-04-01 15:54:51 -05:00
e692735b7b
Merge pull request #1662 from qodo-ai/tr/more_protections
...
Tr/more protections gitlab
2025-03-31 14:02:33 +03:00
20cb139161
Improve code suggestion prompt to clarify handling of partial code segments in PR reviews
2025-03-31 08:39:40 +03:00
afa4adcb23
Improve code analysis instructions for handling partial code blocks in PR reviews
2025-03-30 09:00:45 +03:00
7bd0fefee4
Fix GitLab protections function and return value in PR questions
2025-03-29 19:53:46 +03:00
02d9aed7fe
Fix GitLab provider to use default branch instead of target branch for repo settings
2025-03-29 19:39:56 +03:00
7d47bd5f5e
Add GitLab protections to prevent quick actions in PR questions
2025-03-29 19:35:39 +03:00
ddf94c14a3
Add configuration option for PR Code Suggestions to control publishing when no suggestions found
2025-03-29 09:33:31 +03:00
e422f50cfe
Fix for bug in get_canonical_url_parts when a new issue created, without git url provided.
2025-03-27 17:29:02 +02:00
991a866368
documents' link generation: Make sure prefix ends with '/'
2025-03-26 21:58:15 +02:00
255e1d0fc1
Missing class member
2025-03-26 14:29:50 +02:00
7117e9fe0e
Github Provider: Support publishing a comment on a non pr issue
2025-03-26 13:36:37 +02:00
6f6595c343
Merge pull request #1634 from ishaansehgal99/main
...
fix: Logging and Commenting
2025-03-26 07:51:24 +02:00
b300cfa84d
Improve error logging with artifacts
2025-03-25 22:49:24 -07:00
605eef64e7
Generate git url correctly in case invoked from both user and GitHub app contexts
2025-03-25 12:08:00 +02:00
b161672218
Remove redundant abstractmethod for _prepare_clone_url_with_token
2025-03-24 15:56:45 +02:00
5bc253e1d9
Add token count estimation factor to config
2025-03-24 15:53:22 +02:00
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
fb324d106c
Remove non implemented method _prepare_clone_url_with_token from providers which don't support it and instead, issue a warning in base class.
2025-03-24 14:06:06 +02:00
a4387b5829
Fix more /improve suggestions
2025-03-24 11:19:23 +02:00
477ebf4926
Code recommendations from /improve
2025-03-24 10:54:50 +02:00
e14fc7e02d
Fix missing self.bearer_token for bitbucket related providers
2025-03-24 10:21:23 +02:00
1bd65934df
Merge origin/main into es/help_docs
2025-03-23 20:04:58 +02:00
