feat: add new features(thinking_level and media_resolution) of gemini3#1554
Merged
yuzisun merged 7 commits intoenvoyproxy:mainfrom Nov 21, 2025
Merged
feat: add new features(thinking_level and media_resolution) of gemini3#1554yuzisun merged 7 commits intoenvoyproxy:mainfrom
yuzisun merged 7 commits intoenvoyproxy:mainfrom
Conversation
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #1554 +/- ##
==========================================
+ Coverage 84.18% 84.22% +0.04%
==========================================
Files 150 150
Lines 13005 13041 +36
==========================================
+ Hits 10948 10984 +36
Misses 1436 1436
Partials 621 621 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
Contributor
Author
|
/retest |
yuzisun
reviewed
Nov 20, 2025
internal/apischema/openai/openai.go
Outdated
| ThinkingConfig *genai.ThinkingConfig `json:"thinkingConfig,omitzero"` | ||
|
|
||
| // Detail is media resolution in gemini models | ||
| Detail genai.MediaResolution `json:"detail,omitempty"` |
Contributor
There was a problem hiding this comment.
can you add the reference link?
Contributor
Author
There was a problem hiding this comment.
added, thanks for the comment
Contributor
There was a problem hiding this comment.
Actually this filed should be added to the image part details
Contributor
There was a problem hiding this comment.
the link is wrong, it points to the caching API
Contributor
Author
There was a problem hiding this comment.
this filed should be added to the image part details is already in openai' spec
Contributor
Author
There was a problem hiding this comment.
it points to the caching API I think the definition is the same
Contributor
Author
|
/retest |
1 similar comment
Contributor
Author
|
/retest |
yuzisun
reviewed
Nov 21, 2025
internal/apischema/openai/openai.go
Outdated
| ThinkingConfig *genai.ThinkingConfig `json:"thinkingConfig,omitzero"` | ||
|
|
||
| // Detail here is to set global media resolution in gemini models: https://ai.google.dev/api/caching#MediaResolution | ||
| Detail genai.MediaResolution `json:"detail,omitempty"` |
Contributor
There was a problem hiding this comment.
details can be confusing without context at the top level, since it is in the GCP vendor field section we should keep the name medium_resolution.
**Description** update anthropic -> translation code to correctly translate token usage --------- Signed-off-by: Alexa Griffith <agriffith50@bloomberg.net> Signed-off-by: yxia216 <yxia216@bloomberg.net>
Signed-off-by: yxia216 <yxia216@bloomberg.net>
…#1536) **Description** The SSE event spec supports 3 different delimiters (pair of CRLF / LF / CR). This PR updates the stream processing translator for GCP VertexAI to support all 3 delimiters. [SSE docs] about delimiters > **Note:** The docs define an event as `event = *( comment / field ) end-of-line` `end-of-line` is defined as a single CRLF or LF or CR (not a pair) But the `comment` and `field` definitions also end in `end-of-line` implying that an event always ends in a pair of CRLR / CR / LF [SSE docs]: https://html.spec.whatwg.org/multipage/server-sent-events.html#parsing-an-event-stream --------- Signed-off-by: Sukumar Gaonkar <sgaonkar4@bloomberg.net> Co-authored-by: Ignasi Barrera <ignasi@tetrate.io> Signed-off-by: yxia216 <yxia216@bloomberg.net>
Signed-off-by: yxia216 <yxia216@bloomberg.net>
Signed-off-by: yxia216 <yxia216@bloomberg.net>
da170d9 to
a47506d
Compare
yuzisun
approved these changes
Nov 21, 2025
missBerg
pushed a commit
to missBerg/ai-gateway
that referenced
this pull request
Dec 20, 2025
envoyproxy#1554) **Description** Some new features were introduced in gemini3: **1 thinking_level:** https://ai.google.dev/gemini-api/docs/gemini-3?thinking=low#thinking_level This is similar to reasoning_effort of openai, thus, unified them. **2 media_resolution** https://ai.google.dev/gemini-api/docs/gemini-3?thinking=low#media_resolution This is similar to detail in openai, thus, unified them. The difference is that openai does not provide a global config of media_resolution. Thus, added it as gcp specific, but still use detail to make the name consistent. **Some related PRs:** thinking_budget is in envoyproxy#1461 thinking_level and thinking_budget are both supported, but can not use them together. Other features under review: **1 web search:** envoyproxy#1526 **2 parse the thought summary:** envoyproxy#1521 --------- Signed-off-by: yxia216 <yxia216@bloomberg.net> Signed-off-by: Alexa Griffith <agriffith50@bloomberg.net> Signed-off-by: Sukumar Gaonkar <sgaonkar4@bloomberg.net> Co-authored-by: Alexa Griffith <agriffith50@bloomberg.net> Co-authored-by: Sukumar Gaonkar <sgaonkar4@bloomberg.net> Co-authored-by: Ignasi Barrera <ignasi@tetrate.io> Signed-off-by: Erica Hughberg <erica.sundberg.90@gmail.com>
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 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.
Description
Some new features were introduced in gemini3:
1 thinking_level:
https://ai.google.dev/gemini-api/docs/gemini-3?thinking=low#thinking_level
This is similar to reasoning_effort of openai, thus, unified them.
2 media_resolution
https://ai.google.dev/gemini-api/docs/gemini-3?thinking=low#media_resolution
This is similar to detail in openai, thus, unified them.
The difference is that openai does not provide a global config of media_resolution. Thus, added it as gcp specific, but still use detail to make the name consistent.
Some related PRs:
thinking_budget is in
#1461
thinking_level and thinking_budget are both supported, but can not use them together.
Other features under review:
1 web search:
#1526
2 parse the thought summary:
#1521