!!BREAKING CHANGES!!

Summary

Several fields that configure LLM behavior have been moved from the [agent] section to the [llm] section. This aligns these settings with the provider they configure and reduces duplication. The [agent] section now only contains agent behavior settings (system prompt, context, turn depth, tool filters, etc.). The [agent] section will reject these fields with an unknown-field error.

CONFIGS THAT HAVE NOT BEEN UPDATED WILL FAIL TO PARSE AND THE APP WILL FAIL TO START. See Startup Errors.

Migrated Fields

The following fields must move from [agent] to [llm]:

Field	Old location	New location
`temperature`	`[agent]`	`[llm]`
`reasoning_effort`	`[agent]`	`[llm]`
`max_tokens`	`[agent]`	`[llm]`
`context_window`	`[agent]`	`[llm]`
`additional_params`	`[agent]`	`[llm]`

Before / After Examples

`temperature`, `reasoning_effort`, `context_window`, `max_tokens`

# BEFORE
[llm]
provider = "openai"
model = "gpt-5.1"

[agent]
name = "My Agent"
system_prompt = "..."
temperature = 0.3
reasoning_effort = "medium"
context_window = 128000
max_tokens = 1000

# AFTER
[llm]
provider = "openai"
model = "gpt-5.1"
reasoning_effort = "medium"
temperature = 0.3
context_window = 128000
max_tokens = 1000

[agent]
name = "My Agent"
system_prompt = "..."

Anthropic/Bedrock thinking parameters

# BEFORE
[llm]
provider = "anthropic"
model = "claude-sonnet-4-5-20250929"

[agent]
name = "Thinking Agent"
system_prompt = "..."
temperature = 1.0
additional_params = { thinking = { type = "enabled", budget_tokens = 8000 } }

# AFTER
[llm]
provider = "anthropic"
model = "claude-sonnet-4-5-20250929"
temperature = 1.0
additional_params = { thinking = { type = "enabled", budget_tokens = 8000 } }

[agent]
name = "Thinking Agent"
system_prompt = "..."

For the nested table syntax variant:

# BEFORE
[agent.additional_params.thinking]
type = "enabled"
budget_tokens = 8000

# AFTER
[llm.additional_params.thinking]
type = "enabled"
budget_tokens = 8000

Ollama-Specific Changes

Two Ollama-specific fields (num_ctx, num_predict) have been removed as dedicated top-level [llm] fields. They must now be placed under [llm.additional_params].

# BEFORE
[llm]
provider = "ollama"
model = "llama3.2"
num_ctx = 8192
num_predict = 2048

# AFTER
[llm]
provider = "ollama"
model = "llama3.2"

[llm.additional_params]
num_ctx = 8192
num_predict = 2048

Startup Errors

Affected Configs: deny_unknown_fields on AgentConfig and LlmConfig Both aura_config::AgentConfig and aura_config::LlmConfig carry #[serde(deny_unknown_fields)]. Any errant or stale field in either section (including the removed fields listed above) will produce a hard parse error instead of being silently ignored, calling attention to the customer.

Getting Started

Configuration

Features

CLI Reference

Web Server Reference

Breaking Changes — 10 April 2026

!!BREAKING CHANGES!!

Summary

Migrated Fields

Before / After Examples

`temperature`, `reasoning_effort`, `context_window`, `max_tokens`

Anthropic/Bedrock thinking parameters

Ollama-Specific Changes

Startup Errors

​!!BREAKING CHANGES!!

​Summary

​Migrated Fields

​Before / After Examples

​temperature, reasoning_effort, context_window, max_tokens

​Anthropic/Bedrock thinking parameters

​Ollama-Specific Changes

​Startup Errors

!!BREAKING CHANGES!!

Summary

Migrated Fields

Before / After Examples

`temperature`, `reasoning_effort`, `context_window`, `max_tokens`

Anthropic/Bedrock thinking parameters

Ollama-Specific Changes

Startup Errors