Skip to content

OLS-3442 Add reasoning token support spec #1782

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

Open
thoraxe wants to merge 1 commit into
base: main
Choose a base branch
from
+5 −2
Open

OLS-3442 Add reasoning token support spec #1782

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
1 change: 1 addition & 0 deletions .ai/spec/how/config-generation.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@ llm_providers:
parameters:
max_tokens_for_response: <model.Parameters.MaxTokensForResponse>
tool_budget_ratio: <default 0.25 if zero>
reasoning_config: <model.Parameters.ReasoningConfig> # [PLANNED: OLS-3442] omitted when nil
# Azure-specific:
azure_openai_config:
url: <provider.URL>
Expand Down
6 changes: 4 additions & 2 deletions .ai/spec/what/crd-api.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ Field path (relative to each provider) | JSON key | Go type | Required | Descrip
`url` | `url` | `string` | No | Provider API URL. Pattern: `^https?://.*$`
`credentialsSecretRef` | `credentialsSecretRef` | `corev1.LocalObjectReference` | Yes | Secret containing API credentials
`models` | `models` | `[]ModelSpec` | Yes | Provider models. MaxItems=50
`type` | `type` | `string` | Yes | Provider type enum: `azure_openai`, `bam`, `openai`, `watsonx`, `rhoai_vllm`, `rhelai_vllm`, `fake_provider`, `google_vertex`, `google_vertex_anthropic`
`type` | `type` | `string` | Yes | Provider type enum: `azure_openai`, `bam`, `openai`, `watsonx`, `rhoai_vllm`, `rhelai_vllm`, `fake_provider`, `google_vertex`, `google_vertex_anthropic`, `bedrock`
`deploymentName` | `deploymentName` | `string` | No | Azure OpenAI deployment name
`apiVersion` | `apiVersion` | `string` | No | Azure OpenAI API version
`projectID` | `projectID` | `string` | No | Watsonx project ID
Expand Down Expand Up @@ -77,6 +77,7 @@ Field path (relative to parameters) | JSON key | Go type | Required | Default |
---|---|---|---|---|---
`maxTokensForResponse` | `maxTokensForResponse` | `int` | No | (unset; application default is 2048) | None
`toolBudgetRatio` | `toolBudgetRatio` | `float64` | No | `0.5` | Minimum=0.1, Maximum=0.5
`reasoningConfig` | `reasoningConfig` | `map[string]interface{}` | No | (unset) | None. [PLANNED: OLS-3442] Freeform map of provider-specific reasoning/thinking parameters. Passed through to the service as `reasoning_config`. Valid keys vary by provider and model generation — see lightspeed-service `what/llm-providers.md` rule 13. When absent, no reasoning params are sent. When present with invalid keys, the provider API returns a clear 400 error.

### OLS Configuration (spec.ols)

Expand Down Expand Up @@ -318,6 +319,7 @@ Path | Type | Default | Required | Validation | Description
`spec.llm.providers[].models[].parameters` | `ModelParametersSpec` | -- | No | -- | Model parameters
`spec.llm.providers[].models[].parameters.maxTokensForResponse` | `int` | -- | No | -- | Max response tokens
`spec.llm.providers[].models[].parameters.toolBudgetRatio` | `float64` | `0.25` | No | Min=0.1, Max=0.5 | Tool token budget ratio
`spec.llm.providers[].models[].parameters.reasoningConfig` | `map[string]interface{}` | -- | No | -- | [PLANNED: OLS-3442] Provider-specific reasoning/thinking params
`spec.llm.providers[].type` | `string` | -- | Yes | Enum (see rule 7) | Provider type
`spec.llm.providers[].deploymentName` | `string` | -- | No | XValidation (rule 8) | Azure deployment name
`spec.llm.providers[].apiVersion` | `string` | -- | No | -- | Azure API version
Expand Down Expand Up @@ -450,4 +452,4 @@ Path | Type | Default | Required | Validation | Description

## Planned Changes

None.
- [PLANNED: OLS-3442] Add `reasoningConfig` field (`map[string]interface{}`) to `ModelParametersSpec`. Freeform map passed through to the service as `reasoning_config` for provider-specific reasoning/thinking parameters. Includes release notes and user-facing documentation for valid keys per provider.