-
Notifications
You must be signed in to change notification settings - Fork 69
Comparing changes
Open a pull request
base repository: stacklok/codegate
base: v0.1.18
head repository: stacklok/codegate
compare: v0.1.19
- 15 commits
- 28 files changed
- 5 contributors
Commits on Feb 11, 2025
-
Bump ruff from 0.9.5 to 0.9.6 (#1007)
Bumps [ruff](https://github.com/astral-sh/ruff) from 0.9.5 to 0.9.6. - [Release notes](https://github.com/astral-sh/ruff/releases) - [Changelog](https://github.com/astral-sh/ruff/blob/main/CHANGELOG.md) - [Commits](astral-sh/ruff@0.9.5...0.9.6) --- updated-dependencies: - dependency-name: ruff dependency-type: direct:development update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <[email protected]> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for 7a3e50f - Browse repository at this point
Copy the full SHA 7a3e50fView commit details -
Add Kodu to the list of clients with supported code patterns (#1003)
* Add Kodu to the list of clients with supported code patterns Extracting patterns is necessary for appropriately mux between providers depending on the client. This PR enables Kodu. * fixing copy paste errors
Configuration menu - View commit details
-
Copy full SHA for c542d83 - Browse repository at this point
Copy the full SHA c542d83View commit details -
Force ANSI character output when running integration tests (#1011)
The intention is to output everything, since currently we're missing stderr. Signed-off-by: Juan Antonio Osorio <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for 9f542c3 - Browse repository at this point
Copy the full SHA 9f542c3View commit details -
Remove code for mapping origin to destination in muxing (#1010)
The initial muxing implementation assumed that we would need to transform the input body from one provider to another. e.g. from athropic to openai. This changed. The final implementation is assuming that is receiving OpenAI format and will respond with OpenAI format. This PR is removing unused code.
Configuration menu - View commit details
-
Copy full SHA for 0bec802 - Browse repository at this point
Copy the full SHA 0bec802View commit details -
Add codegate package path to poetry (#1012)
* Fix codegate not a package when poetry install Signed-off-by: Radoslav Dimitrov <[email protected]> * Add a log message when an integration test has started Signed-off-by: Radoslav Dimitrov <[email protected]> --------- Signed-off-by: Radoslav Dimitrov <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for 46a5fd0 - Browse repository at this point
Copy the full SHA 46a5fd0View commit details -
Pass down base URL and API key to completion handler (#1002)
* Pass down base URL and API key to completion handler In order to make Ollama work with API Keys, I needed to change the completion handler to take a base URL and also leverage a given API key (if available). Signed-off-by: Juan Antonio Osorio <[email protected]> Co-Authored-by: Alejandro Ponce de Leon <[email protected]> * fix unit tests and formatting * fix integration tests * Pass API key to ollama calls Signed-off-by: Juan Antonio Osorio <[email protected]> * Handle optional authorization header in ollama endpoints. Signed-off-by: Juan Antonio Osorio <[email protected]> --------- Signed-off-by: Juan Antonio Osorio <[email protected]> Co-authored-by: Alejandro Ponce de Leon <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for 6938347 - Browse repository at this point
Copy the full SHA 6938347View commit details -
Switch to qwen2.5-coder:1.5b (#1013)
Signed-off-by: Radoslav Dimitrov <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for 8cb658d - Browse repository at this point
Copy the full SHA 8cb658dView commit details -
Configuration menu - View commit details
-
Copy full SHA for d86a965 - Browse repository at this point
Copy the full SHA d86a965View commit details
Commits on Feb 12, 2025
-
Enable provider model updating when updating provider itself (#1014)
This now calls the model updating logic when updating the provider itself. Thus allowing us to have a way to update the model list. Signed-off-by: Juan Antonio Osorio <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for f361178 - Browse repository at this point
Copy the full SHA f361178View commit details -
Bump litellm from 1.60.8 to 1.61.1 (#1018)
Bumps [litellm](https://github.com/BerriAI/litellm) from 1.60.8 to 1.61.1. - [Release notes](https://github.com/BerriAI/litellm/releases) - [Commits](BerriAI/litellm@v1.60.8...v1.61.1) --- updated-dependencies: - dependency-name: litellm dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <[email protected]> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for f4e252a - Browse repository at this point
Copy the full SHA f4e252aView commit details -
Bump cryptography from 44.0.0 to 44.0.1 (#1019)
Bumps [cryptography](https://github.com/pyca/cryptography) from 44.0.0 to 44.0.1. - [Changelog](https://github.com/pyca/cryptography/blob/main/CHANGELOG.rst) - [Commits](pyca/cryptography@44.0.0...44.0.1) --- updated-dependencies: - dependency-name: cryptography dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <[email protected]> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for 1b5595f - Browse repository at this point
Copy the full SHA 1b5595fView commit details -
Pin pyproject to require python 3.12 (#1009)
* Pin pyproject to require python 3.12 Some dependencies (namely presidio) don't support python 3.13 yet. Signed-off-by: Juan Antonio Osorio <[email protected]> * updating lock file --------- Signed-off-by: Juan Antonio Osorio <[email protected]> Co-authored-by: Alejandro Ponce <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for a7e14f6 - Browse repository at this point
Copy the full SHA a7e14f6View commit details -
Fix FIM on Continue. Have specific formatters for chat and FIM (#1015)
* Fix FIM on Continue. Have specific formatters for chat and FIM Until now we had a general formatter on the way out of muxing. This is wrong since sometimes the pipelines respond with different format for chat or FIM. Such is the case for Ollama. This PR separates the formatters and declares them explicitly so that they're easier to adjust in the future. * Adressed comments from review
Configuration menu - View commit details
-
Copy full SHA for 8897318 - Browse repository at this point
Copy the full SHA 8897318View commit details -
Configuration menu - View commit details
-
Copy full SHA for 58512fd - Browse repository at this point
Copy the full SHA 58512fdView commit details -
Fix ollama support for Kodu when muxing (#1022)
Muixing was failing for 2 reasons: 1. Sometimes we return OpenAI format from ollama provider. Before we were assuming that everything that was returned from ollama provider had ollama format. 2. The OpenAI format returned from ollama provider had an invalid `created` field.
Configuration menu - View commit details
-
Copy full SHA for e6600f6 - Browse repository at this point
Copy the full SHA e6600f6View commit details
There are no files selected for viewing
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.