Skip to content

docs: Overview description of model thinking #1301

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
johanandren merged 5 commits into from
Feb 9, 2026
Merged

docs: Overview description of model thinking #1301

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
249615e
docs: Overview description of model thinking
johanandren Feb 2, 2026
a94d2d9
Update docs/src/modules/sdk/pages/model-provider-details.adoc
johanandren Feb 2, 2026
a8f3cc1
add thinking config to config tables
johanandren Feb 9, 2026
2d876ad
vale this and that
johanandren Feb 9, 2026
fe63a8d
Update model-provider-details.adoc
johanandren Feb 9, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
40 changes: 32 additions & 8 deletions docs/src/modules/sdk/pages/model-provider-details.adoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,14 @@ values (like 50) allow for more diversity.
=== max-tokens or max-completion-tokens
If this value is supplied and the model supports this property, then it will stop operations in mid flight if the token quota runs out. It's important to check _how_ the model counts tokens, as some may count differently. Be aware of the fact that this parameter name frequently varies from one provider to the next. Make sure you're using the right property name.

=== Thinking
Some models support thinking, also sometimes referred to as "thought process" or reasoning, where the model generates an intermediate
thought process, breaking down bigger problems into smaller more manageable tasks. This can be good for more complex problems but comes
at the price of tokens used for the thought process.

For models that support thinking, it is enabled through model-specific configuration, either by setting a thinking token budget, or
by a toggle. Thinking is disabled for all models by default.
Copy link
Contributor Author

@johanandren johanandren Feb 2, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It is actually an enum for gemini 3, but this is close enough.


== Model configuration
The following is a list of all natively supported model configurations. Remember that if you don't see your model or model format here, you can always create your own custom configuration and still use all of the Agent-related components.
Copy link
Contributor

@patriknw patriknw Feb 5, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Shouldn't it be listed in below table too, for each model that supports it?

Copy link
Contributor Author

@johanandren johanandren Feb 9, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ah, I didn't notice this is manual table, thought it was pulled in from reference.conf. Yes, I'll add it for each model here as well.


Expand Down Expand Up @@ -84,6 +92,10 @@ The following is a list of all natively supported model configurations. Remember
| Integer
| Retry this many times if the request to the model fails

| thinking-budget-tokens
| Integer
| A maximum number of tokens to spend on thinking, use 0 to disable thinking

|===


Expand All @@ -108,14 +120,6 @@ See link:{attachmentsdir}/api/akka/javasdk/agent/ModelProvider.Anthropic.html[`M
| String
| The Bedrock model id, e.g. "ai21.jamba-1-5-large-v1:0"

| send-thinking
| boolean
| Send thinking can be enabled

| return-thinking
| boolean
| Return thinking can be enabled

Copy link
Contributor Author

@johanandren johanandren Feb 9, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

These two were accidentally added with the bedrock support, controlled by runtime (for all models)

| max-output-tokens
| Integer
| Max token _output_ quota. Leave as –1 for model default
Expand Down Expand Up @@ -202,6 +206,14 @@ See link:{attachmentsdir}/api/akka/javasdk/agent/ModelProvider.Bedrock.html[`Mod
| Integer
| Retry this many times if the request to the model fails

| thinking-budget
| Integer
| A budget of tokens to spend on thinking for Gemini 2.5 models, set to "none" for other models. Can be –1 for dynamic budget, 0 for disabled, a positive value to define an upper limit for tokens spent on thinking. See https://ai.google.dev/gemini-api/docs/thinking#set-budget for details

| thinking-level
| String
| Control thinking for Gemini 3 models, exact values depend on the specific model chosen, must be empty for 2.5 models. See Google Gemini docs for more details: https://ai.google.dev/gemini-api/docs/thinking#thinking-levels

|===

See link:{attachmentsdir}/api/akka/javasdk/agent/ModelProvider.GoogleAIGemini.html[`ModelProvider.GoogleAIGemini`] for programmatic settings.
Expand Down Expand Up @@ -252,6 +264,10 @@ See link:{attachmentsdir}/api/akka/javasdk/agent/ModelProvider.GoogleAIGemini.ht
| Integer
| Retry this many times if the request to the model fails

| thinking
| Boolean
| Enable thinking, only supported for some models. Make sure the chosen model supports thinking before enabling.

|===

See link:{attachmentsdir}/api/akka/javasdk/agent/ModelProvider.HuggingFace.html[`ModelProvider.HuggingFace`] for programmatic settings.
Expand Down Expand Up @@ -328,6 +344,10 @@ See link:{attachmentsdir}/api/akka/javasdk/agent/ModelProvider.LocalAI.html[`Mod
| Integer
| Retry this many times if the request to the model fails

| think
| Boolean
| Enable thinking, only supported for some models. Make sure the chosen model supports thinking before enabling.

|===

See link:{attachmentsdir}/api/akka/javasdk/agent/ModelProvider.Ollama.html[`ModelProvider.Ollama`] for programmatic settings.
Expand Down Expand Up @@ -382,6 +402,10 @@ See link:{attachmentsdir}/api/akka/javasdk/agent/ModelProvider.Ollama.html[`Mode
| Integer
| Retry this many times if the request to the model fails

| thinking
| Boolean
| Enable thinking, only supported for DeepSeek. Make sure the chosen model supports thinking before enabling.

|===

See link:{attachmentsdir}/api/akka/javasdk/agent/ModelProvider.OpenAi.html[`ModelProvider.OpenAi`] for programmatic settings.
Expand Down
Loading