fix(gemini): use thinkingLevel instead of thinkingBudget for Gemini 3… #359

nestharus · 2025-11-27T06:22:26Z

Add IsGemini3Model helper function to detect Gemini 3 models
Use thinkingLevel (low/high) for Gemini 3 instead of thinkingBudget
Gemini 3 medium/default uses dynamic thinking (no explicit level)
Update antigravity, gemini-cli, and gemini responses translators

… models - Add IsGemini3Model helper function to detect Gemini 3 models - Use thinkingLevel (low/high) for Gemini 3 instead of thinkingBudget - Gemini 3 medium/default uses dynamic thinking (no explicit level) - Update antigravity, gemini-cli, and gemini responses translators 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>

chatgpt-codex-connector · 2025-11-27T06:22:33Z

Codex usage limits have been reached for code reviews. Please check with the admins of this repo to increase the limits by adding credits.
Credits must be used to enable repository wide code reviews.

gemini-code-assist · 2025-11-27T06:22:40Z

Summary of Changes

Hello @nestharus, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request updates the system's handling of Gemini 3 model configurations, specifically regarding how 'thinking' parameters are applied. It introduces a new mechanism that leverages thinkingLevel for explicit control over thinking intensity and defaults to dynamic thinking for other scenarios, moving away from the older thinkingBudget approach. This ensures compatibility with the latest Gemini 3 API specifications and optimizes how these models process requests.

Highlights

New Helper Function for Gemini 3 Models: A new utility function, IsGemini3Model, has been introduced to easily identify Gemini 3 models based on their naming convention (models starting with 'gemini-3-').
Transition to thinkingLevel for Gemini 3: For Gemini 3 models, the configuration now uses thinkingLevel (either 'low' or 'high') instead of thinkingBudget for specific thinking settings. This aligns with the updated API for these models.
Dynamic Thinking for Gemini 3 Medium/Default: Gemini 3 models will now utilize dynamic thinking for 'medium' and default thinking configurations, meaning no explicit thinkingLevel or thinkingBudget is set in these cases.
Updated Translators: The antigravity, gemini-cli, and gemini responses translators have been updated to correctly apply the new thinkingLevel logic and dynamic thinking behavior for Gemini 3 models.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	`/gemini review`	Performs a code review for the current pull request in its current state.
Pull Request Summary	`/gemini summary`	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	`/gemini help`	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

gemini-code-assist

Code Review

This pull request correctly adapts the translators to use thinkingLevel for Gemini 3 models instead of thinkingBudget, introducing a new IsGemini3Model helper function. The changes are consistent across the antigravity, gemini-cli, and gemini-responses translators. My review focuses on improving code maintainability by addressing significant code duplication between translators and the use of magic strings. I've provided suggestions to refactor duplicated logic into a shared utility and to define constants for string literals to make the code more robust and easier to manage in the future.

gemini-code-assist · 2025-11-27T06:24:19Z

internal/translator/antigravity/openai/chat-completions/antigravity_openai_request.go

 		case "low":
-			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 1024))
+			if util.IsGemini3Model(modelName) {
+				out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingLevel", "low")
+			} else {
+				out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 1024))
+			}
 			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
 		case "medium":
-			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 8192))
+			if !util.IsGemini3Model(modelName) {
+				out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 8192))
+			}
+			// Gemini 3: no thinkingLevel for medium, uses dynamic thinking (auto)
 			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
 		case "high":
-			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 32768))
+			if util.IsGemini3Model(modelName) {
+				out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingLevel", "high")
+			} else {
+				out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 32768))
+			}
 			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
 		default:
-			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", -1)
+			if !util.IsGemini3Model(modelName) {
+				out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", -1)
+			}
+			// Gemini 3: no thinkingLevel for auto/default, uses dynamic thinking
 			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
 		}


The logic within these case statements is identical to the logic in internal/translator/gemini-cli/openai/chat-completions/gemini-cli_openai_request.go. Additionally, the logic for setting the default thinkingConfig for Gemini 3 models on lines 108-110 is also duplicated. This creates a maintenance burden, as any future changes will need to be applied in both places.

Consider extracting this duplicated logic into a shared helper function in a common package like internal/util to improve maintainability.

gemini-code-assist · 2025-11-27T06:24:19Z

internal/translator/antigravity/openai/chat-completions/antigravity_openai_request.go

+			if util.IsGemini3Model(modelName) {
+				out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingLevel", "low")
+			} else {
+				out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 1024))
+			}
 			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
 		case "medium":
-			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 8192))
+			if !util.IsGemini3Model(modelName) {
+				out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 8192))
+			}
+			// Gemini 3: no thinkingLevel for medium, uses dynamic thinking (auto)
 			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
 		case "high":
-			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 32768))
+			if util.IsGemini3Model(modelName) {
+				out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingLevel", "high")
+			} else {
+				out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 32768))
+			}


The string literals "low" (line 52) and "high" (line 65) for thinkingLevel are magic strings. It's good practice to define these as constants in a shared package (e.g., util) to ensure consistency and prevent typos. This issue is also present in the other translator files modified in this PR.

Example:

// In a relevant package (e.g., util) const ( ThinkingLevelLow = "low" ThinkingLevelHigh = "high" )

You could then use util.ThinkingLevelLow and util.ThinkingLevelHigh.

gemini-code-assist · 2025-11-27T06:24:19Z

internal/translator/gemini/openai/responses/gemini_openai-responses_request.go

 		case "minimal":
-			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 1024))
+			if util.IsGemini3Model(modelName) {
+				out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingLevel", "low")
+			} else {
+				out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 1024))
+			}
 			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.include_thoughts", true)
 		case "low":
-			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 4096))
+			if util.IsGemini3Model(modelName) {
+				out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingLevel", "low")
+			} else {
+				out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 4096))
+			}
 			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.include_thoughts", true)


The case "minimal" and case "low" blocks are very similar. For Gemini 3 models, they both set thinkingLevel to "low", and they both set include_thoughts to true. You can combine these cases to reduce code duplication and make the logic more concise.

case "minimal", "low": if util.IsGemini3Model(modelName) { out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingLevel", "low") } else { budget := 1024 if reasoningEffort.String() == "low" { budget = 4096 } out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, budget)) } out, _ = sjson.Set(out, "generationConfig.thinkingConfig.include_thoughts", true)

gemini-code-assist · 2025-11-27T06:24:19Z

internal/util/gemini_thinking.go

+// IsGemini3Model returns true if the model is a Gemini 3 model (uses thinkingLevel instead of thinkingBudget).
+func IsGemini3Model(model string) bool {
+	lower := strings.ToLower(model)
+	return strings.HasPrefix(lower, "gemini-3-")


The string literal "gemini-3-" is a magic string. It's better to define it as a constant at the package level to improve readability and maintainability, and to avoid potential typos if it's used elsewhere.

Example:

const Gemini3ModelPrefix = "gemini-3-"

Suggested change

return strings.HasPrefix(lower, "gemini-3-")

return strings.HasPrefix(lower, Gemini3ModelPrefix)

gemini-code-assist bot reviewed Nov 27, 2025

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

fix(gemini): use thinkingLevel instead of thinkingBudget for Gemini 3… #359

fix(gemini): use thinkingLevel instead of thinkingBudget for Gemini 3… #359

nestharus commented Nov 27, 2025

Uh oh!

chatgpt-codex-connector bot commented Nov 27, 2025

Uh oh!

gemini-code-assist bot commented Nov 27, 2025

Uh oh!

gemini-code-assist bot left a comment

Uh oh!

gemini-code-assist bot Nov 27, 2025

Uh oh!

gemini-code-assist bot Nov 27, 2025

Uh oh!

gemini-code-assist bot Nov 27, 2025

Uh oh!

gemini-code-assist bot Nov 27, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

	return strings.HasPrefix(lower, "gemini-3-")
	return strings.HasPrefix(lower, Gemini3ModelPrefix)

Uh oh!

fix(gemini): use thinkingLevel instead of thinkingBudget for Gemini 3… #359

Are you sure you want to change the base?

fix(gemini): use thinkingLevel instead of thinkingBudget for Gemini 3… #359

Conversation

nestharus commented Nov 27, 2025

Uh oh!

chatgpt-codex-connector bot commented Nov 27, 2025

Uh oh!

gemini-code-assist bot commented Nov 27, 2025

Summary of Changes

Highlights

Footnotes

Uh oh!

gemini-code-assist bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

gemini-code-assist bot Nov 27, 2025

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Nov 27, 2025

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Nov 27, 2025

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Nov 27, 2025

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant