Skip to content

docs: document tool-call text policy #1112

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

Draft
martinstiago wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

docs: document tool-call text policy #1112

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ec11d6e
docs: document tool-call text policy
martinstiago Aug 19, 2026
28c0ed1
docs: rename policy value to suppress_after_tool_call_detected
martinstiago Aug 24, 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
21 changes: 11 additions & 10 deletions api-reference/server/services/llm/anthropic.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,16 +102,17 @@ Before using Anthropic LLM services, you need:

Runtime-configurable settings passed via the `settings` constructor argument using `AnthropicLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details.

| Parameter | Type | Default | Description |
| ----------------------- | ------------------------- | ----------- | ----------------------------------------------------------------------------------------------- |
| `model` | `str` | `None` | Anthropic model identifier. _(Inherited from base settings.)_ |
| `system_instruction` | `str` | `None` | System instruction/prompt for the model. _(Inherited from base settings.)_ |
| `max_tokens` | `int` | `NOT_GIVEN` | Maximum tokens to generate. |
| `temperature` | `float` | `NOT_GIVEN` | Sampling temperature (0.0 to 1.0). Lower values are more focused, higher values more creative. |
| `top_k` | `int` | `NOT_GIVEN` | Top-k sampling parameter. Limits tokens to the top k most likely. |
| `top_p` | `float` | `NOT_GIVEN` | Top-p (nucleus) sampling (0.0 to 1.0). Controls diversity of output. |
| `enable_prompt_caching` | `bool` | `NOT_GIVEN` | Whether to enable Anthropic's prompt caching feature. Reduces costs for repeated context. |
| `thinking` | `AnthropicThinkingConfig` | `NOT_GIVEN` | Extended thinking configuration. See [AnthropicThinkingConfig](#anthropicthinkingconfig) below. |
| Parameter | Type | Default | Description |
| ----------------------- | ------------------------- | ------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `model` | `str` | `None` | Anthropic model identifier. _(Inherited from base settings.)_ |
| `system_instruction` | `str` | `None` | System instruction/prompt for the model. _(Inherited from base settings.)_ |
| `max_tokens` | `int` | `NOT_GIVEN` | Maximum tokens to generate. |
| `temperature` | `float` | `NOT_GIVEN` | Sampling temperature (0.0 to 1.0). Lower values are more focused, higher values more creative. |
| `top_k` | `int` | `NOT_GIVEN` | Top-k sampling parameter. Limits tokens to the top k most likely. |
| `top_p` | `float` | `NOT_GIVEN` | Top-p (nucleus) sampling (0.0 to 1.0). Controls diversity of output. |
| `enable_prompt_caching` | `bool` | `NOT_GIVEN` | Whether to enable Anthropic's prompt caching feature. Reduces costs for repeated context. |
| `thinking` | `AnthropicThinkingConfig` | `NOT_GIVEN` | Extended thinking configuration. See [AnthropicThinkingConfig](#anthropicthinkingconfig) below. |
| `tool_call_text_policy` | `ToolCallTextPolicy` | `"preserve"` | Whether to preserve text emitted after a tool call. Set to `"suppress_after_tool_call_detected"` to omit that text from the current response. _(Inherited from base settings.)_ |

<Note>
`NOT_GIVEN` values are omitted from the API request entirely, letting the
Expand Down
27 changes: 14 additions & 13 deletions api-reference/server/services/llm/aws.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,19 +128,20 @@ Before using AWS Bedrock LLM services, you need:

Runtime-configurable settings passed via the `settings` constructor argument using `AWSBedrockLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details.

| Parameter | Type | Default | Description |
| --------------------------------- | ----------- | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `model` | `str` | `None` | AWS Bedrock model identifier. _(Inherited from base settings.)_ |
| `system_instruction` | `str` | `None` | System instruction/prompt for the model. _(Inherited from base settings.)_ |
| `max_tokens` | `int` | `NOT_GIVEN` | Maximum number of tokens to generate. |
| `temperature` | `float` | `NOT_GIVEN` | Sampling temperature (0.0 to 1.0). Lower values are more focused, higher values are more creative. |
| `top_p` | `float` | `NOT_GIVEN` | Top-p (nucleus) sampling (0.0 to 1.0). Controls diversity of output. |
| `top_k` | `int` | `NOT_GIVEN` | Top-k sampling parameter. |
| `seed` | `int` | `NOT_GIVEN` | Random seed for deterministic outputs. |
| `stop_sequences` | `List[str]` | `NOT_GIVEN` | List of strings that stop generation when encountered. |
| `latency` | `str` | `NOT_GIVEN` | Performance mode: `"standard"` or `"optimized"`. |
| `enable_prompt_caching` | `bool` | `NOT_GIVEN` | Whether to enable prompt caching by adding cachePoint markers to system prompts and tool definitions. Can reduce TTFT by up to 85% for multi-turn conversations. See [AWS docs](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html). |
| `additional_model_request_fields` | `dict` | `NOT_GIVEN` | Additional model-specific parameters passed directly to the API. |
| Parameter | Type | Default | Description |
| --------------------------------- | -------------------- | ------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `model` | `str` | `None` | AWS Bedrock model identifier. _(Inherited from base settings.)_ |
| `system_instruction` | `str` | `None` | System instruction/prompt for the model. _(Inherited from base settings.)_ |
| `max_tokens` | `int` | `NOT_GIVEN` | Maximum number of tokens to generate. |
| `temperature` | `float` | `NOT_GIVEN` | Sampling temperature (0.0 to 1.0). Lower values are more focused, higher values are more creative. |
| `top_p` | `float` | `NOT_GIVEN` | Top-p (nucleus) sampling (0.0 to 1.0). Controls diversity of output. |
| `top_k` | `int` | `NOT_GIVEN` | Top-k sampling parameter. |
| `seed` | `int` | `NOT_GIVEN` | Random seed for deterministic outputs. |
| `stop_sequences` | `List[str]` | `NOT_GIVEN` | List of strings that stop generation when encountered. |
| `latency` | `str` | `NOT_GIVEN` | Performance mode: `"standard"` or `"optimized"`. |
| `enable_prompt_caching` | `bool` | `NOT_GIVEN` | Whether to enable prompt caching by adding cachePoint markers to system prompts and tool definitions. Can reduce TTFT by up to 85% for multi-turn conversations. See [AWS docs](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html). |
| `additional_model_request_fields` | `dict` | `NOT_GIVEN` | Additional model-specific parameters passed directly to the API. |
| `tool_call_text_policy` | `ToolCallTextPolicy` | `"preserve"` | Whether to preserve text emitted after a tool call. Set to `"suppress_after_tool_call_detected"` to omit that text from the current response. _(Inherited from base settings.)_ |

<Note>
`NOT_GIVEN` values are omitted from the inference config, letting the Bedrock
Expand Down
21 changes: 11 additions & 10 deletions api-reference/server/services/llm/google.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,16 +127,17 @@ Before using Google Gemini LLM services, you need:

Runtime-configurable settings passed via the `settings` constructor argument using `GoogleLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details.

| Parameter | Type | Default | Description |
| -------------------- | ---------------------- | ------------------ | -------------------------------------------------------------------------------------------------- |
| `model` | `str` | `gemini-3.6-flash` | Gemini model identifier. _(Inherited from base settings.)_ |
| `system_instruction` | `str` | `None` | System instruction/prompt for the model. _(Inherited from base settings.)_ |
| `max_tokens` | `int` | `NOT_GIVEN` | Maximum number of tokens to generate. |
| `temperature` | `float` | `NOT_GIVEN` | Sampling temperature (0.0 to 2.0). Lower values are more focused, higher values are more creative. |
| `top_k` | `int` | `NOT_GIVEN` | Top-k sampling parameter. Limits tokens to the top k most likely. |
| `top_p` | `float` | `NOT_GIVEN` | Top-p (nucleus) sampling (0.0 to 1.0). Controls diversity of output. |
| `thinking` | `GoogleThinkingConfig` | `NOT_GIVEN` | Thinking configuration. See [GoogleThinkingConfig](#googlethinkingconfig) below. |
| `safety_settings` | `list[SafetySetting]` | `NOT_GIVEN` | Content safety filters. Each entry pairs a harm category with a blocking threshold. |
| Parameter | Type | Default | Description |
| ----------------------- | ---------------------- | ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `model` | `str` | `gemini-3.6-flash` | Gemini model identifier. _(Inherited from base settings.)_ |
| `system_instruction` | `str` | `None` | System instruction/prompt for the model. _(Inherited from base settings.)_ |
| `max_tokens` | `int` | `NOT_GIVEN` | Maximum number of tokens to generate. |
| `temperature` | `float` | `NOT_GIVEN` | Sampling temperature (0.0 to 2.0). Lower values are more focused, higher values are more creative. |
| `top_k` | `int` | `NOT_GIVEN` | Top-k sampling parameter. Limits tokens to the top k most likely. |
| `top_p` | `float` | `NOT_GIVEN` | Top-p (nucleus) sampling (0.0 to 1.0). Controls diversity of output. |
| `thinking` | `GoogleThinkingConfig` | `NOT_GIVEN` | Thinking configuration. See [GoogleThinkingConfig](#googlethinkingconfig) below. |
| `safety_settings` | `list[SafetySetting]` | `NOT_GIVEN` | Content safety filters. Each entry pairs a harm category with a blocking threshold. |
| `tool_call_text_policy` | `ToolCallTextPolicy` | `"preserve"` | Whether to preserve text emitted after a tool call. Set to `"suppress_after_tool_call_detected"` to omit that text from the current response. _(Inherited from base settings.)_ |

<Note>
`NOT_GIVEN` values are omitted from the API request, letting the Gemini API
Expand Down
Loading