feat(ai): Add thinking levels parameter #9424

hsubox76 · 2025-12-12T21:09:38Z

Add thinking levels feature.

API proposal (internal): https://docs.google.com/document/d/16cdWurhdLDuNIDj0eJWNnL00any0tL_DjI-lAg7miP8/edit?tab=t.0

Added the param, plus an error if both thinkingLevel and thinkingBudget are set. This validation function may be used in the future to validate other common config issues.

Docs notes:

Copied text of documentation from Swift comments in API proposal doc (see above)
Some of the "removed" text in the md files is actually just removing them from the toc table at the top of the page, where they are unnecessary, and most of the text still remains in the entries below.

changeset-bot · 2025-12-12T21:09:43Z

🦋 Changeset detected

Latest commit: d035951

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 2 packages

Name	Type
@firebase/ai	Minor
firebase	Minor

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

gemini-code-assist · 2025-12-12T21:09:57Z

Summary of Changes

Hello @hsubox76, 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 enhances the AI model configuration by introducing a thinkingLevel parameter, offering a simplified way to control the model's internal reasoning process. It ensures proper configuration through client-side validation and provides comprehensive documentation for the new feature.

Highlights

New thinkingLevel Parameter: Introduced a new thinkingLevel parameter within ThinkingConfig to allow users to specify a preset level for the model's 'thinking' process, with options like MINIMAL, LOW, MEDIUM, and HIGH.
Mutual Exclusivity Validation: Implemented client-side validation to prevent the simultaneous setting of both thinkingBudget and thinkingLevel in the GenerationConfig, throwing an AIErrorCode.UNSUPPORTED error if both are provided.
Documentation Updates: Updated API documentation and devsite markdown files to reflect the new ThinkingLevel type, its usage, and the updated ThinkingConfig interface, including notes on its interaction with thinkingBudget and model support.

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. ↩

github-actions · 2025-12-12T21:10:51Z

Changeset File Check ✅

No modified packages are missing from the changeset file.
No changeset formatting errors detected.

gemini-code-assist

Code Review

This pull request introduces the thinkingLevel parameter to the thinkingConfig, providing users with presets to control the model's thinking process. The changes include updates to the ThinkingConfig interface, new type definitions for ThinkingLevel, and comprehensive documentation updates. A key addition is the client-side validation that prevents thinkingLevel and thinkingBudget from being set simultaneously, which is a great way to prevent invalid configurations. The associated test case for this validation is also well-implemented. Overall, the changes are solid. I have one minor suggestion to improve the readability of the validation logic.

packages/ai/src/models/generative-model.ts

google-oss-bot · 2025-12-12T21:18:24Z

Size Report ¹

Affected Products

@firebase/ai
Type Base (2ecf78b) Merge (dada300) Diff
browser 68.7 kB 69.1 kB +406 B (+0.6%)
main 73.0 kB 73.5 kB +483 B (+0.7%)
module 68.7 kB 69.1 kB +406 B (+0.6%)
firebase
Type Base (2ecf78b) Merge (dada300) Diff
firebase-ai.js 53.4 kB 53.7 kB +312 B (+0.6%)

Test Logs

https://storage.googleapis.com/firebase-sdk-metric-reports/VS7FtazwtQ.html

google-oss-bot · 2025-12-12T21:33:23Z

Size Analysis Report ¹

Affected Products

`@firebase/ai`

`GenerativeModel`

Size

Type	Base (`2ecf78b`)	Merge (`dada300`)	Diff
size	26.5 kB	26.7 kB	+209 B (+0.8%)
size-with-ext-deps	44.3 kB	44.6 kB	+211 B (+0.5%)

Dependency

Type Base (2ecf78b) Merge (dada300) Diff

functions

39 dependencies

addHelpers
aggregateResponses
assignRoleToPartsAndValidateSendMessageRequest
callCloudOrDevice
chromeAdapterFactory
countTokens
countTokensOnCloud
createEnhancedContentResponse
decodeInstanceIdentifier
factory
formatBlockErrorMessage
formatGenerateContentInput
formatNewContent
formatSystemInstruction
generateContent
generateContentOnCloud
generateContentStream
generateContentStreamOnCloud
generateResponseSequence
getClientHeaders
getFunctionCalls
getHeaders
getInlineDataParts
getResponsePromise
getResponseStream
getText
hadBadFinishReason
hasValidCandidates
initApiSettings
makeRequest
mapCountTokensRequest
mapGenerateContentCandidates
mapGenerateContentRequest
mapGenerateContentResponse
mapPromptFeedback
processGenerateContentResponse
processStream
registerAI
validateChatHistory

40 dependencies

addHelpers
aggregateResponses
assignRoleToPartsAndValidateSendMessageRequest
callCloudOrDevice
chromeAdapterFactory
countTokens
countTokensOnCloud
createEnhancedContentResponse
decodeInstanceIdentifier
factory
formatBlockErrorMessage
formatGenerateContentInput
formatNewContent
formatSystemInstruction
generateContent
generateContentOnCloud
generateContentStream
generateContentStreamOnCloud
generateResponseSequence
getClientHeaders
getFunctionCalls
getHeaders
getInlineDataParts
getResponsePromise
getResponseStream
getText
hadBadFinishReason
hasValidCandidates
initApiSettings
makeRequest
mapCountTokensRequest
mapGenerateContentCandidates
mapGenerateContentRequest
mapGenerateContentResponse
mapPromptFeedback
processGenerateContentResponse
processStream
registerAI
validateChatHistory
validateGenerationConfig

+ validateGenerationConfig

`ThinkingLevel`

Size

Type	Base (`2ecf78b`)	Merge (`dada300`)	Diff
size	?	7.01 kB	? (?)
size-with-ext-deps	?	24.6 kB	? (?)

Dependency

Type	Base (`2ecf78b`)	Merge (`dada300`)	Diff
functions	?	chromeAdapterFactory decodeInstanceIdentifier factory registerAI	?
classes	?	AIError AIService Backend ChromeAdapterImpl GoogleAIBackend VertexAIBackend	?
variables	?	12 dependencies AIErrorCode AI_TYPE Availability BackendType DEFAULT_API_VERSION DEFAULT_LOCATION InferenceMode ThinkingLevel defaultExpectedInputs logger name version	?
enums	?		?

External Dependency

Module	Base (`2ecf78b`)	Merge (`dada300`)	Diff
`@firebase/app`	?	_registerComponent registerVersion	?
`@firebase/component`	?	Component	?
`@firebase/logger`	?	Logger	?
`@firebase/util`	?	FirebaseError	?

`getGenerativeModel`

Size

Type	Base (`2ecf78b`)	Merge (`dada300`)	Diff
size	26.9 kB	27.1 kB	+209 B (+0.8%)
size-with-ext-deps	44.7 kB	44.9 kB	+211 B (+0.5%)

Dependency

Type Base (2ecf78b) Merge (dada300) Diff

functions

40 dependencies

addHelpers
aggregateResponses
assignRoleToPartsAndValidateSendMessageRequest
callCloudOrDevice
chromeAdapterFactory
countTokens
countTokensOnCloud
createEnhancedContentResponse
decodeInstanceIdentifier
factory
formatBlockErrorMessage
formatGenerateContentInput
formatNewContent
formatSystemInstruction
generateContent
generateContentOnCloud
generateContentStream
generateContentStreamOnCloud
generateResponseSequence
getClientHeaders
getFunctionCalls
getGenerativeModel
getHeaders
getInlineDataParts
getResponsePromise
getResponseStream
getText
hadBadFinishReason
hasValidCandidates
initApiSettings
makeRequest
mapCountTokensRequest
mapGenerateContentCandidates
mapGenerateContentRequest
mapGenerateContentResponse
mapPromptFeedback
processGenerateContentResponse
processStream
registerAI
validateChatHistory

41 dependencies

addHelpers
aggregateResponses
assignRoleToPartsAndValidateSendMessageRequest
callCloudOrDevice
chromeAdapterFactory
countTokens
countTokensOnCloud
createEnhancedContentResponse
decodeInstanceIdentifier
factory
formatBlockErrorMessage
formatGenerateContentInput
formatNewContent
formatSystemInstruction
generateContent
generateContentOnCloud
generateContentStream
generateContentStreamOnCloud
generateResponseSequence
getClientHeaders
getFunctionCalls
getGenerativeModel
getHeaders
getInlineDataParts
getResponsePromise
getResponseStream
getText
hadBadFinishReason
hasValidCandidates
initApiSettings
makeRequest
mapCountTokensRequest
mapGenerateContentCandidates
mapGenerateContentRequest
mapGenerateContentResponse
mapPromptFeedback
processGenerateContentResponse
processStream
registerAI
validateChatHistory
validateGenerationConfig

+ validateGenerationConfig

Test Logs

https://storage.googleapis.com/firebase-sdk-metric-reports/4fIEPDm8Z0.html

rachelsaunders · 2026-01-09T14:21:02Z

docs-devsite/ai.thinkingconfig.md

-If you don't specify a budget, the model will determine the appropriate amount of thinking based on the complexity of the prompt.
+The range of supported thinking budget values depends on the model.
+
+<ul> <li>To use the default thinking budget or thinking level for a model, leave this value undefined.</li>


It looks like this is describing thinkingBudget? If so, I'm not sure if we should be talking about thinking levels in this section?

Removed thinking levels from this sentence but kept the line below that says you cannot set both.

rachelsaunders · 2026-01-09T14:21:20Z

docs-devsite/ai.thinkingconfig.md

+
+<li>To disable thinking, when supported by the model, set this value to `0`<!-- -->.</li>
+
+<li>To use dynamic thinking, allowing the model to decide on the thinking budget based on the task, set this value to `-1`<!-- -->.</li> </ul>


Suggested change

<li>To use dynamic thinking, allowing the model to decide on the thinking budget based on the task, set this value to `-1`.</li> </ul>

<li>To use dynamic thinking, which allows the model to decide on the thinking budget based on the task, set this value to `-1`.</li> </ul>

hsubox76 added 2 commits December 12, 2025 11:35

Add thinking levels.

2652c67

Tests, docs, error

48211fa

gemini-code-assist bot reviewed Dec 12, 2025

View reviewed changes

packages/ai/src/models/generative-model.ts Show resolved Hide resolved

hsubox76 added 2 commits December 12, 2025 15:33

make config clearer

670d910

fix changeset

87464b7

hsubox76 marked this pull request as ready for review January 5, 2026 18:20

hsubox76 requested review from a team as code owners January 5, 2026 18:20

hsubox76 requested a review from DellaBitta January 5, 2026 18:22

DellaBitta approved these changes Jan 5, 2026

View reviewed changes

hsubox76 requested a review from rachelsaunders January 5, 2026 20:18

rachelsaunders requested changes Jan 9, 2026

View reviewed changes

Address docs comments

101059f

rachelsaunders approved these changes Jan 9, 2026

View reviewed changes

hsubox76 added 2 commits January 12, 2026 10:04

Merge branch 'main' into ch-thinking-levels

29318a4

add closing bracket

d035951

hsubox76 merged commit 5579b38 into main Jan 12, 2026
38 checks passed

hsubox76 deleted the ch-thinking-levels branch January 12, 2026 18:41


		<li>To disable thinking, when supported by the model, set this value to `0`<!-- -->.</li>

		<li>To use dynamic thinking, allowing the model to decide on the thinking budget based on the task, set this value to `-1`<!-- -->.</li> </ul>

	<li>To use dynamic thinking, allowing the model to decide on the thinking budget based on the task, set this value to `-1`<!-- -->.</li> </ul>
	<li>To use dynamic thinking, which allows the model to decide on the thinking budget based on the task, set this value to `-1`<!-- -->.</li> </ul>

feat(ai): Add thinking levels parameter #9424

feat(ai): Add thinking levels parameter #9424

Uh oh!

Conversation

hsubox76 commented Dec 12, 2025

Uh oh!

changeset-bot bot commented Dec 12, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🦋 Changeset detected

Uh oh!

gemini-code-assist bot commented Dec 12, 2025

Summary of Changes

Highlights

Footnotes

Uh oh!

github-actions bot commented Dec 12, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Changeset File Check ✅

Uh oh!

gemini-code-assist bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

Uh oh!

google-oss-bot commented Dec 12, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Size Report 1

Affected Products

@firebase/ai

firebase

Test Logs

Uh oh!

google-oss-bot commented Dec 12, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Size Analysis Report 1

Affected Products

@firebase/ai

GenerativeModel

ThinkingLevel

getGenerativeModel

Test Logs

Uh oh!

rachelsaunders Jan 9, 2026

Choose a reason for hiding this comment

Uh oh!

hsubox76 Jan 9, 2026

Choose a reason for hiding this comment

Uh oh!

rachelsaunders Jan 9, 2026

Choose a reason for hiding this comment

Uh oh!

hsubox76 Jan 9, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

changeset-bot bot commented Dec 12, 2025 •

edited

Loading

github-actions bot commented Dec 12, 2025 •

edited

Loading

google-oss-bot commented Dec 12, 2025 •

edited

Loading

Size Report ¹

`@firebase/ai`

`firebase`

google-oss-bot commented Dec 12, 2025 •

edited

Loading

Size Analysis Report ¹

`@firebase/ai`

`GenerativeModel`

`ThinkingLevel`

`getGenerativeModel`