fix: Parse maas models for gcp vertex provider #5816
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
katzdave
changed the title
katzdave
changed the title
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR adds support for parsing Google MaaS (Model as a Service) models from Model Garden, such as "qwen3-coder-480b-a35b-instruct-maas". The changes introduce a new MaaS variant to handle these models and route them to use the Google API format.
Key changes:
- Added
MaaSvariant toGcpVertexAIModelandModelProviderenums to represent Model Garden models - Implemented parsing logic for models ending in "-maas" suffix, extracting publisher information
- Routed MaaS models to use "generateContent" endpoint and Google request/response format
Reviewed Changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| crates/goose/src/providers/formats/gcpvertexai.rs | Adds MaaS enum variant, parsing logic for "-maas" suffix models, and routes them to Google format handlers |
| crates/goose/src/providers/gcpvertexai.rs | Adds MaaS case to endpoint selection and updates tests for new ModelProvider return type |
michaelneale
approved these changes
Nov 20, 2025
Collaborator
michaelneale
left a comment
michaelneale
left a comment
There was a problem hiding this comment.
seems better than the way it was!
wpfleger96
added a commit
that referenced
this pull request
Nov 20, 2025
* main: fix: Parse maas models for gcp vertex provider (#5816)
michaelneale
added a commit
that referenced
this pull request
Nov 24, 2025
* main: (48 commits) [fix] generic check for gemini compat (#5842) Add scheduler to diagnostics (#5849) Cors and token (#5850) fix sessions coming back with empty messages (#5841) markdown export from URL (#5830) Next camp refactor live (#5706) Add out of context compaction test via error proxy (#5805) fix: Add backward compatibility for conversationCompacted message type (#5819) Add /agent/stop endpoint, make max active agents configurable (#5826) Handle 404s (#5791) Persist provider name and model config in the session (#5419) Comment out the flaky mcp callers (#5827) Slash commands (#5718) fix: remove setx calls to not permanently edit the windows shell PATH (#5821) fix: Parse maas models for gcp vertex provider (#5816) fix: support Gemini 3's thought signatures (#5806) chore: Add Adrian Cole to Maintainers (#5815) [MCP-UI] Proxy and Better Message Handling (#5487) Release 1.15.0 Document New Window menu in macOS dock (#5811) ...
BlairAllan
pushed a commit
to BlairAllan/goose
that referenced
this pull request
Nov 29, 2025
Signed-off-by: Blair Allan <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Fix parse error instantly killing goose from parsing models like: qwen3-coder-480b-a35b-instruct-maas
I don't have a working gcp vertex provider config so this just gets me into an auth error (but at least past the parsing error). I'm not sure about the model format. I think we'll likely need to add branching based on the publisher of the model, but defaulting to google and this at least pushes things further along.
Left a TODO around that.
#4182