chandan84
0e4a1d9ab8
line 253-258, pass extra_headers fields from settings to litellm, exception handling to check if extra_headers is in dict format
2025-02-22 14:38:38 -05:00
chandan84
e7b05732f8
line 253-255, pass extra_headers fields from settings to litellm
2025-02-22 14:12:39 -05:00
Trung Dinh
37083ae354
Improve logging for adding parameters: temperature and reasoning_effort
2025-02-22 22:19:58 +07:00
Trung Dinh
9abb212e83
Add reasoning_effort argument to chat completion request
2025-02-21 22:16:18 +07:00
Trung Dinh
d37732c25d
Define ReasoningEffort enum
2025-02-21 22:10:49 +07:00
Trung Dinh
e6b6e28d6b
Define SUPPORT_REASONING_EFFORT_MODELS list
2025-02-21 22:10:33 +07:00
mrT23
2887d0a7ed
refactor: move CLI argument validation to dedicated class
2025-02-20 17:51:16 +02:00
Tal
35059cadf7
Update pr_agent/algo/ai_handlers/litellm_ai_handler.py
...
Co-authored-by: qodo-merge-pro-for-open-source[bot] <189517486+qodo-merge-pro-for-open-source[bot]@users.noreply.github.com>
2025-02-18 11:50:48 +02:00
mrT23
4edb8b89d1
feat: add support for custom reasoning models
2025-02-18 11:46:22 +02:00
Yu Ishikawa
22f02ac08c
Support generally available gemini-2.0-flash
...
Signed-off-by: Yu Ishikawa <yu-iskw@users.noreply.github.com>
2025-02-17 08:40:05 +09:00
Trung Dinh
adfc2a6b69
Add temperature only if model supports it
2025-02-16 15:43:40 +07:00
Trung Dinh
c4aa13e798
Add o1-preview model to USER_MESSAGE_ONLY_MODELS and NO_SUPPORT_TEMPERATURE_MODELS
2025-02-16 15:18:52 +07:00
Trung Dinh
90575e3f0d
Add NO_SUPPORT_TEMPERATURE_MODELS list
2025-02-16 15:17:59 +07:00
Trung Dinh
fcbe986ec7
Removed o3 model from USER_MESSAGE_ONLY_MODELS
2025-02-16 15:17:12 +07:00
Trung Dinh
061fec0d36
Removed o1 model from USER_MESSAGE_ONLY_MODELS
2025-02-16 15:15:50 +07:00
Trung Dinh
a6482c37ce
Add o3-mini to user message only model list
2025-02-02 18:03:38 +07:00
Trung Dinh
83582bc935
Add support o3-mini model
2025-02-02 18:02:53 +07:00
Trung Dinh
4ac1e15bae
Refactoring user messages only flow
2025-02-02 18:01:44 +07:00
Trung Dinh
a48686bde9
Define USER_MESSAGE_ONLY_MODELS in the algo init file
2025-02-02 18:01:16 +07:00
Trung Dinh
48377e3c81
Add a null check for user_message_only_models before using it
2025-01-31 11:53:05 +07:00
Trung Dinh
7eb26b3220
Check current model is in user_message_only_models list
2025-01-31 11:25:51 +07:00
mrT23
136c75a5ac
fix: add fallback for parsing AI responses with leading '+' symbols
2025-01-30 08:35:31 +02:00
Hussam.lawen
50c52e32c9
enter
...
feat: enhance ticket compliance analysis with human verification tracking
2025-01-26 12:33:49 +02:00
Trung Dinh
c2ca79da0d
Combining system and user prompts for o1 series and deepseek-reasoner models
2025-01-22 20:33:43 +07:00
Trung Dinh
63f1d449ce
Add support model deepseek/deepseek-reasoner
2025-01-22 20:32:18 +07:00
Yu Ishikawa
0075084a22
Add vertex_ai/gemini-2.0-flash-exp
...
Signed-off-by: Yu Ishikawa <yu-iskw@users.noreply.github.com>
2025-01-20 18:29:37 +09:00
Trung Dinh
e58a535594
Inject deepseek key to DEEPSEEK_API_KEY environment variable
2025-01-17 11:43:06 +07:00
Trung Dinh
d949f440a8
Add support model deepseek/deepseek-chat
2025-01-17 11:42:36 +07:00
Tal
2df4bc8b53
Update pr_agent/algo/utils.py
...
Co-authored-by: qodo-merge-pro-for-open-source[bot] <189517486+qodo-merge-pro-for-open-source[bot]@users.noreply.github.com>
2025-01-04 16:28:25 +02:00
mrT23
e431979b8b
fix: handle newline issues in patch generation
2025-01-04 16:26:38 +02:00
mrT23
4a1b042152
fix: improve bullet point formatting and file path display in PR description
2024-12-31 12:00:21 +02:00
Tal
8218fa6e13
Merge pull request #1421 from dceoy/main
...
Update Groq models and tokens
2024-12-30 19:25:23 +02:00
dceoy
e89b65ed38
Increase the max token of groq/llama-3.3-70b-versatile
2024-12-30 11:35:02 +09:00
mrT23
59899f0c62
fix: improve patch generation error handling and logging
2024-12-29 11:27:53 +02:00
mrT23
5e46955d52
fix: improve file path formatting in patch output
2024-12-29 11:26:13 +02:00
dceoy
71c558d306
Update Groq models and tokens
2024-12-28 01:51:33 +09:00
mrT23
4aad67b563
fix: improve line extraction from files with missing content
2024-12-27 09:00:20 +02:00
mrT23
495c1ebe5f
refactor: remove legacy code suggestions feature from review tool
2024-12-25 08:18:28 +02:00
mrT23
7d9288bb1a
feat: add dedent option to code snippet formatting
2024-12-24 07:49:27 +02:00
mrT23
3360a28b3e
fix: improve changelog update prompt and response handling
2024-12-23 17:06:21 +02:00
Tal
20c506d2e0
Merge pull request #1402 from KennyDizi/main
...
Add support for OpenAI `o1` model and snapshot version `o1-2024-12-17`
2024-12-22 09:36:04 +02:00
Trung Dinh
23678c1d4d
Update O1_MODEL_PREFIX to o1 based on new models released
2024-12-22 10:36:59 +07:00
Trung Dinh
8d7825233a
Supported model gpt-o1
2024-12-22 10:33:26 +07:00
mrT23
3ab2cac089
fix: improve markdown rendering when git provider is unavailable
2024-12-19 20:59:17 +02:00
mrT23
989670b159
fix: improve markdown rendering when git provider is unavailable
2024-12-19 20:49:40 +02:00
mrT23
7e8361b5fd
feat: enhance code review output with collapsible code snippets and variable links
2024-12-19 20:30:56 +02:00
Trung Dinh
eaaaf6a6a2
Fix context windows token for model o1-2024-12-17
2024-12-19 23:11:45 +07:00
Trung Dinh
07f3933f6d
Add support OpenAI model o1 snapshot version o1-2024-12-17
2024-12-19 23:00:47 +07:00
Tal
e9615c6994
Merge pull request #1384 from MarkRx/feature/version-metadata
...
Add --version command and version metadata
2024-12-19 09:34:24 +02:00
MarkRx
452abe2e18
Move get_version to algo/util.py; fix version to 0.25
2024-12-17 08:44:53 -07:00
Trung Dinh
03d2bea50b
Add support model gemini-2.0-flash-exp
2024-12-16 23:37:19 +07:00
mrT23
872b27bfd8
docs: remove model_weak configuration and simplify model selection
2024-12-11 18:10:34 +02:00
MarkRx
75a120952c
Add version metadata and --version command
2024-12-09 09:27:54 -07:00
Trung Dinh
f9a7b18073
Improve condition to pick up weak model
2024-12-09 22:36:07 +07:00
Trung Dinh
6352e6e3bf
Change default model to regular model
2024-12-09 22:24:44 +07:00
Trung Dinh
e3d779c30d
Fix typo model_weak
2024-12-08 22:09:48 +07:00
Trung Dinh
dec2859fc4
Set default model to weak model
2024-12-08 21:10:26 +07:00
Trung Dinh
a4d9a65fc6
Add model_week
2024-12-08 20:23:36 +07:00
Trung Dinh
683108d3a5
Removed model_turbo
2024-12-08 20:10:38 +07:00
Tal
b44030114e
Merge pull request #1374 from KennyDizi/main
...
Add Support for GPT-4o November 2024 Model and Update Configurations
2024-12-02 08:23:26 +02:00
KennyDizi
f2043d639c
Add support model gpt-4o-2024-11-20
2024-11-21 22:10:27 +07:00
zhouleilei
a141ca133c
Update utils.py
...
1. add missed emoji for "PR contains tests"
2. check git_provider and reference_link before using them
2024-11-16 09:32:05 +08:00
mrT23
9c82047dc3
Add validation for hunk lines matching original file content in git patch processing
2024-11-12 07:50:37 +02:00
Tal
5c5a3e267c
Merge branch 'main' into introduce-pre-commit
2024-11-08 09:54:21 +02:00
Tal
f9380c2440
Merge pull request #1350 from NxPKG/patch-1
...
Remove unused deployment_id variable.
2024-11-08 09:49:07 +02:00
NxPKG
6339845eb4
Remove unused deployment_id variable.
...
The deployment_id variable is assigned but never used in the function.
2024-11-07 14:24:35 +06:00
KennyDizi
af653a048f
Add support model bedrock/anthropic.claude-3-5-haiku-20241022-v1:0
2024-11-07 09:12:52 +07:00
KennyDizi
157251493a
Add support claude-3-5-haiku-20241022 model
2024-11-06 07:52:58 +07:00
zhouleilei
dacb45dd8a
Merge branch 'main' of https://github.com/ryanzll/pr-agent
...
update openai api
2024-11-02 09:47:14 +08:00
mrT23
2f5e8472b9
Add PRDescriptionHeader enum for consistent "Changes walkthrough" usage across modules
2024-10-30 08:48:08 +02:00
Yu Ishikawa
81dea65856
Format files by pre-commit run -a
...
Signed-off-by: Yu Ishikawa <yu-iskw@users.noreply.github.com>
2024-10-30 10:00:36 +09:00
Yu Ishikawa
db062e3e35
Support Google AI Studio
...
Signed-off-by: Yu Ishikawa <yu-iskw@users.noreply.github.com>
2024-10-29 08:00:16 +09:00
mrT23
597f1c6f83
Add PRDescriptionHeader enum for consistent "Changes walkthrough" usage across modules
2024-10-28 08:12:56 +02:00
KennyDizi
b4700bd7c0
Add support bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0 model
2024-10-23 08:08:04 +07:00
KennyDizi
f1d0401f82
Add model vertex_ai/claude-3-5-sonnet-v2@20241022
2024-10-23 07:11:33 +07:00
KennyDizi
c5bd09e2c9
Add model anthropic/claude-3-5-sonnet-20241022
2024-10-23 07:10:22 +07:00
Tal
dcb7b66fd7
Update pr_agent/algo/ai_handlers/litellm_ai_handler.py
...
Co-authored-by: codiumai-pr-agent-pro[bot] <151058649+codiumai-pr-agent-pro[bot]@users.noreply.github.com>
2024-10-19 11:34:57 +03:00
mrT23
b7437147af
fix: correct model type extraction for O1 model handling in litellm_ai_handler.py
2024-10-19 11:32:45 +03:00
mrT23
76d95bb6d7
feat: add ticket compliance check
...
- Implement ticket compliance check logic in `utils.py` and `ticket_pr_compliance_check.py`
- Add functions to extract and cache PR tickets, and check ticket relevancy
2024-10-10 10:01:48 +03:00
Tal
e6c56c7355
Update pr_agent/algo/ai_handlers/litellm_ai_handler.py
...
Co-authored-by: codiumai-pr-agent-pro[bot] <151058649+codiumai-pr-agent-pro[bot]@users.noreply.github.com>
2024-10-09 08:56:31 +03:00
mrT23
727b08fde3
feat: add support for O1 model by combining system and user prompts in litellm_ai_handler
2024-10-09 08:53:34 +03:00
mrT23
4b05a3e858
refactor: streamline hunk processing logic in git_patch_processing.py
...
- Simplified logic for handling new and old hunks to ensure consistent presentation of changes.
- Updated documentation in TOML files to reflect changes in hunk section handling and line number references.
2024-10-07 20:32:11 +03:00
mrT23
454365913f
refactor: update terminology for issue review recommendations in utils.py
2024-09-30 13:00:01 +03:00
mrT23
bbaba2dbda
refactor: update terminology for issue review recommendations in utils.py
...
style: refine field descriptions in KeyIssuesComponentLink model
2024-09-30 08:58:32 +03:00
mrT23
35b1f5e747
key
2024-09-29 07:23:34 +03:00
mrT23
d77a819d92
Add intro text option for PR reviews in configuration and utils
2024-09-29 07:06:48 +03:00
mrT23
3dd8050004
improve code suggestion prompt
2024-09-25 21:22:41 +03:00
mrT23
8d82cb2e04
f string
2024-09-15 08:50:24 +03:00
mrT23
8f943a0d44
fix: update error logging messages and system prompt handling in litellm_ai_handler.py
2024-09-15 08:07:59 +03:00
mrT23
cc0e432247
refactor logic
2024-09-13 22:17:24 +03:00
trung.dinh@zoi.tech
a94496285f
Add o1-preview models
2024-09-13 08:23:18 +07:00
trung.dinh@zoi.tech
567c144176
Add o1-mini models
2024-09-13 08:22:09 +07:00
mrT23
7de6bb0150
enhance: cap patch extra lines and update documentation with separators and context adjustments
2024-09-12 09:05:26 +03:00
mrT23
a1582b5338
enhance: cap patch extra lines and update documentation with separators and context adjustments
2024-09-12 09:01:36 +03:00
mrT23
09b0a04a47
docs and fixes
2024-09-10 20:06:48 +03:00
Tal
1451d82d6b
Update pr_agent/algo/pr_processing.py
...
Co-authored-by: codiumai-pr-agent-pro[bot] <151058649+codiumai-pr-agent-pro[bot]@users.noreply.github.com>
2024-09-10 17:50:32 +03:00
mrT23
01ba6fe63d
feat: enhance error handling and logging, update AI metadata terminology
...
- Improved error handling and logging in `pr_processing.py` and `github_polling.py` to provide more detailed error information.
- Updated AI metadata terminology from "AI-generated file summary" to "AI-generated changes summary" across multiple files for consistency.
- Added a placeholder method `publish_file_comments` in `azuredevops_provider.py`.
- Refined logging messages in `azuredevops_provider.py` for better clarity.
2024-09-10 17:44:26 +03:00
mrT23
c8e8ed89d2
feat: integrate Dynaconf for configuration management and enhance config display
2024-09-09 08:31:20 +03:00
mrT23
ebc5cafb2b
protection
2024-09-08 17:46:21 +03:00
mrT23
86103c65e8
pattern_back
2024-09-08 17:24:13 +03:00
mrT23
8706f643ef
enable ai_metadata
2024-09-08 16:26:26 +03:00
mrT23
5432469ef6
fix: ensure non-empty lines are processed correctly in git patch handling
2024-09-01 08:39:29 +03:00
woung717
578d7c69f8
fix: change deprecated timeout parameter for litellm
2024-08-29 21:45:48 +09:00
mrT23
c2f52539aa
fix: handle deleted files in git patch processing and update section header logic
2024-08-27 09:31:31 +03:00
mrT23
441e098e2a
fix: correct YAML formatting in response text processing in utils.py
2024-08-25 11:26:48 +03:00
Tal
745e955d1f
Merge pull request #1145 from MarkRx/feature/litellm-logging-observability
...
Add and document abilty to use LiteLLM Logging Observability tools
2024-08-22 09:58:53 +03:00
mrT23
d467f5a7fd
patch_extension_skip_types
2024-08-20 11:37:27 +03:00
mrT23
2d5b060168
patch_extension_skip_types
2024-08-20 11:33:56 +03:00
mrT23
b7eb6be5a0
Update PR code suggestions and reviewer prompts for clarity and consistency
2024-08-20 11:27:35 +03:00
mrT23
660a60924e
Add filename parameter and skip logic to extend_patch function in git_patch_processing.py
2024-08-20 11:23:37 +03:00
MarkRx
8aa76a0ac5
Add and document abilty to use LiteLLM Logging Observability tools
2024-08-19 15:45:47 -04:00
mrT23
fc40ca9196
Refactor dynamic context handling in git patch processing and update configuration default
2024-08-19 08:38:26 +03:00
mrT23
e9535ea164
Add dynamic context handling in git patch processing
...
- Introduce `allow_dynamic_context` and `max_extra_lines_before_dynamic_context` settings.
- Adjust context limits dynamically based on section headers.
- Add logging for dynamic context adjustments and section header findings.
2024-08-18 17:45:18 +03:00
mrT23
aa87bc60f6
Rename 'add_callbacks' to 'add_litellm_callbacks' for clarity in litellm_ai_handler
2024-08-17 09:20:30 +03:00
mrT23
c76aabc71e
Add callback functionality to litellm_ai_handler for enhanced logging and metadata capture
2024-08-17 09:15:05 +03:00
Tal
b9df034c97
Merge pull request #1138 from Codium-ai/tr/err_protections
...
Add 'only_markdown' parameter to emphasize_header call in utils.py fo…
2024-08-14 14:03:43 +03:00
mrT23
bae8d36698
Add 'only_markdown' parameter to emphasize_header call in utils.py for security concerns section
2024-08-14 14:02:09 +03:00
Hussam.lawen
4fea780b9b
fix html escaping
2024-08-14 12:13:51 +03:00
mrT23
f4b06640d2
Add info log for successful AI prediction parse in utils.py
2024-08-14 08:14:51 +03:00
mrT23
f1981092d3
Add warning log for initial AI prediction parse failure and error log for fallback failure in utils.py
2024-08-14 08:08:55 +03:00
mrT23
86a9cfedc8
Add error handling for empty diff files in utils.py and optimize file content retrieval in Bitbucket provider
2024-08-13 22:33:07 +03:00
mrT23
f89bdcf3c3
Add error handling for missing custom label settings in utils.py
2024-08-13 16:40:05 +03:00
mrT23
e7e3970874
Add error handling for empty system prompt in litellm_ai_handler and type conversion in utils.py
2024-08-13 16:26:32 +03:00
mrT23
1aa6dd9b5d
Add error handling for missing file paths in Bitbucket provider and improve file validation logic
2024-08-13 11:28:21 +03:00
mrT23
4a38861d06
Add error handling for missing file paths in file_filter.py for Bitbucket and GitLab platforms
2024-08-13 08:59:27 +03:00
Tal
4228f92e7e
Merge pull request #1119 from Codium-ai/hl/limit_long_comments
...
Hl/limit long comments
2024-08-12 16:25:42 +03:00
Hussam.lawen
70da871876
lower OpenAI errors to warnings
2024-08-12 12:27:48 +03:00
mrT23
5c4bc0a008
Add Bitbucket diff handling and improve error logging
...
- Implement `publish_file_comments` method placeholder
- Enhance `is_supported` method to include `publish_file_comments`
- Refactor diff splitting logic to handle Bitbucket-specific headers
- Improve error handling and logging for file content retrieval
- Add `get_pr_owner_id` method to retrieve PR owner ID
- Update `_get_pr_file_content` to fetch file content from remote link
- Fix variable name typo in `extend_patch` function in `git_patch_processing.py`
2024-08-12 09:48:26 +03:00
mrT23
4c1c313031
Add missing newline in extended patch and remove trailing whitespace
2024-08-11 18:49:28 +03:00
mrT23
12742ef499
Adjust patch extension logic to handle cases where extended size exceeds original file length
2024-08-11 15:48:58 +03:00
mrT23
63e921a2c5
Adjust patch extension logic to handle cases where extended size exceeds original file length
2024-08-11 15:46:46 +03:00
mrT23
a06670bc27
Fix incorrect logic for extending patch size beyond original file length
2024-08-11 15:20:27 +03:00
mrT23
e85b75fe64
Refactor patch extension logic to handle cases with zero extra lines
2024-08-11 12:56:56 +03:00
mrT23
df04a7e046
Add spaces to extra lines in patch extension for consistency
2024-08-11 12:32:26 +03:00
mrT23
9c3f080112
comments
2024-08-11 12:15:47 +03:00
mrT23
ed65493718
Handle edge cases for patch extension and update tests
2024-08-11 12:08:00 +03:00
mrT23
e238a88824
Add tests for patch extension and update configuration for extra lines handling
...
- Added unit tests in `test_extend_patch.py` and `test_pr_generate_extended_diff.py` to verify patch extension functionality with extra lines.
- Updated `pr_processing.py` to include `patch_extra_lines_before` and `patch_extra_lines_after` settings.
- Modified `configuration.toml` to adjust `patch_extra_lines_before` to 4 and `max_context_tokens` to 16000.
- Enabled extra lines in `pr_code_suggestions.py`.
- Added new model `claude-3-5-sonnet` to `__init__.py`.
2024-08-11 09:21:34 +03:00
mrT23
61bdfd3b99
patch_extra_lines_before and patch_extra_lines_after
2024-08-10 21:55:51 +03:00
mrT23
84b80f792d
protections
2024-08-09 21:44:00 +03:00
Tal
b370cb6ae7
Merge pull request #1102 from MarkRx/feature/langchain-azure-fix
...
Fix LangChainOpenAIHandler for Azure
2024-08-08 19:37:26 +03:00
MarkRx
4201779ce2
Fix LangChainOpenAIHandler for Azure
2024-08-08 09:55:18 -04:00
Benedict Lee
4c0fd37ac2
Fix pr_processing.get_pr_multi_diffs
...
Fix function to return an empty list instead of a single joined string when patches_extended is empty.
2024-08-08 11:46:26 +09:00
Benedict Lee
c996c7117f
Fix function to return an empty list instead of a single joined string when patches_extended is empty.
2024-08-08 11:32:10 +09:00
KennyDizi
9be5cc6dec
Add support model gpt-4o-2024-08-06
2024-08-07 07:28:51 +07:00
mrT23
3420e6f30d
patch improvements
2024-08-03 12:44:49 +03:00
Tal
1cefd23739
Merge pull request #1073 from h0rv/patch-1
...
Improve response cleaning
2024-08-02 12:21:40 +03:00
Robby
039d85b836
fix cleaning
2024-08-01 15:50:00 -04:00
mrT23
d671c78233
Merge remote-tracking branch 'origin/main'
2024-07-31 13:32:51 +03:00
mrT23
240e0374e7
fixed extra call bug
2024-07-31 13:32:42 +03:00
Robby
172d0c0358
improve response cleaning
...
The prompt for the model starts with a code block (```). When testing watsonx models (llama and granite), they would generate the closing block in the response.
2024-07-29 10:26:58 -04:00
