feat(gcpvertexai): do HTTP 429 like retries for Anthropic API HTTP 529 overloaded status code #3026
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
Collaborator
michaelneale
left a comment
michaelneale
left a comment
There was a problem hiding this comment.
looks good - but not 100% sure about removal of models
Contributor
Author
I cleaned them up because they're not available on GCP VertexAI model garden anymore. Anyone that still has access to them can still type it in. but let me add them back. cleanup is not a blocker for me. |
michaelneale
approved these changes
Jun 27, 2025
Collaborator
michaelneale
left a comment
michaelneale
left a comment
There was a problem hiding this comment.
Looks good - not able to verify myself with vertex but looks good
Collaborator
|
will need to update to main branch |
uddhav
force-pushed
the
gcp-vertex-ai-overloaded-retry
branch
3 times, most recently
from
6da2346 to
5f0bbd7
Compare
Contributor
Author
Updated this morning and now again - looks like it waits for approval on a couple of jobs. Hopefully no conflict when you see this next time 🤞 |
uddhav
force-pushed
the
gcp-vertex-ai-overloaded-retry
branch
from
5f0bbd7 to
5d5cbb6
Compare
Collaborator
|
@uddhav just updated this - looking ok? |
Contributor
Author
@michaelneale thanks - LGTM |
Collaborator
|
nice one! thanks |
lifeizhou-ap
added a commit
that referenced
this pull request
Jul 17, 2025
* main: feat(gcpvertexai): do HTTP 429 like retries for Anthropic API HTTP 529 overloaded status code (#3026) Fix a few ui edge cases - refresh occasionally crashing, chat loader over text and chat input height returning to auto (#3469) Don't default to main for build-cli (#3467) docs: add MongoDB MCP server tutorial (#2660) feat: run sub recipe multiple times in parallel (Experimental feature) (#3274) chore(release): release version 1.1.0 (#3465) chore: implement streaming for anthropic.rs firstparty provider (#3419) Fix regression: add back detail to tool-call banners (#3231) Document release process and update some just recipes (#3460) feat: add download_cli.ps1 file for windows (#3354) fix: session_file is optional (#3462) Bump more space for goose is working on it so it doesnt overlap incoming agent chat messages (#3453) Align chat input action buttons to bottom when large amount of text (#3455) docs: add Cloudflare MCP Server tutorial (#3278) feat(cli): Clear persisted session file with /clear command (#3145)
s-soroosh
pushed a commit
to s-soroosh/goose
that referenced
this pull request
Jul 18, 2025
…9 overloaded status code (block#3026) Co-authored-by: Michael Neale <[email protected]> Signed-off-by: Soroosh <[email protected]>
kwsantiago
pushed a commit
to kwsantiago/goose
that referenced
this pull request
Jul 19, 2025
…9 overloaded status code (block#3026) Co-authored-by: Michael Neale <[email protected]> Signed-off-by: Kyle Santiago <[email protected]>
cbruyndoncx
pushed a commit
to cbruyndoncx/goose
that referenced
this pull request
Jul 20, 2025
…9 overloaded status code (block#3026) Co-authored-by: Michael Neale <[email protected]>
atarantino
pushed a commit
to atarantino/goose
that referenced
this pull request
Aug 5, 2025
…9 overloaded status code (block#3026) Co-authored-by: Michael Neale <[email protected]> Signed-off-by: Adam Tarantino <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
Refresh of #2280
GCP Vertex AI: Add retry handling for Anthropic API 529 overloaded status code
Adds support for handling Anthropic's HTTP 529 "API Overloaded" status code in the GCP Vertex AI provider. This status code indicates temporary backend capacity issues rather than quota exhaustion.
Changes
This improves reliability when interacting with Anthropic models through the Vertex AI provider during high-traffic periods.