From d02ab67f37006b5bc974393748987a3ef83e797c Mon Sep 17 00:00:00 2001 From: Alex Clarke Date: Thu, 16 Jul 2026 12:56:28 -0600 Subject: [PATCH] docs: Added documentation on the new reasoning effort fields --- Agents.md | 1 + Clients.md | 6 ++++-- Environment-Variables.md | 1 + Graph-Agents.md | 2 ++ REPL.md | 26 ++++++++++++++++++++++++++ Roles.md | 1 + Sessions.md | 1 + 7 files changed, 36 insertions(+), 2 deletions(-) diff --git a/Agents.md b/Agents.md index b10449d..1c9489f 100644 --- a/Agents.md +++ b/Agents.md @@ -58,6 +58,7 @@ Agent configurations have the following settings available to customize each age model: openai:gpt-4o # Specify the LLM to use temperature: null # Set default temperature parameter, range (0, 1) top_p: null # Set default top-p parameter, with a range of (0, 1) or (0, 2), depending on the model +reasoning_effort: null # Set the reasoning effort level for models that support it (e.g. low, medium, high) # Agent Metadata Configuration agent_session: null # Set a session to use when starting the agent. (e.g. temp, default); defaults to globally set agent_session # Agent Configuration diff --git a/Clients.md b/Clients.md index 2cf3ac9..866f5a4 100644 --- a/Clients.md +++ b/Clients.md @@ -67,8 +67,10 @@ The `models` array lists the available models from the model client. Each one ha | `max_output_tokens` | | `chat` | The maximum number of output tokens for the model | | `require_max_tokens` | | `chat` | Whether to enforce the `max_output_tokens` constraint. | | `supports_vision` | | `chat` | Indicates if the model supports multimodal queries that would require vision (i.e. image recognition) | -| `supports_function_calling` | | `chat` | Indicates if the model supports function calling | -| `no_stream` | | `chat` | Enable or disable streaming API responses | +| `supports_function_calling` | | `chat` | Indicates if the model supports function calling | +| `reasoning_levels` | | `chat` | A list of named reasoning effort levels the model accepts (e.g. `[low, medium, high]`). When non-empty, `.reasoning` and `.set reasoning_effort` become available in the REPL for this model | +| `default_reasoning_effort` | | `chat` | The effort level applied by default when `reasoning_levels` is non-empty and no explicit override is set. Must be one of the values listed in `reasoning_levels` | +| `no_stream` | | `chat` | Enable or disable streaming API responses | | `no_system_message` | | `chat` | Controls whether the model supports system messages | | `system_prompt_prefix` | | `chat` | An additional prefix prompt to add to all system prompts to ensure consistent behavior across all interactions | | `max_tokens_per_chunk` | | `embedding` | The maximum chunk size supported by the embedding model | diff --git a/Environment-Variables.md b/Environment-Variables.md index 9f7546d..e4b4cac 100644 --- a/Environment-Variables.md +++ b/Environment-Variables.md @@ -21,6 +21,7 @@ Below are the most commonly used configuration settings and their corresponding | `model` | `COYOTE_MODEL` | | `temperature` | `COYOTE_TEMPERATURE` | | `top_p` | `COYOTE_TOP_P` | +| `reasoning_effort` | `COYOTE_REASONING_EFFORT` | | `stream` | `COYOTE_STREAM` | | `save` | `COYOTE_SAVE` | | `editor` | `COYOTE_EDITOR` | diff --git a/Graph-Agents.md b/Graph-Agents.md index 9cbf6b2..c143345 100644 --- a/Graph-Agents.md +++ b/Graph-Agents.md @@ -64,6 +64,7 @@ version: "1.0" model: anthropic:claude-sonnet-4-6 # default model for llm nodes temperature: 0.0 # default sampling temperature top_p: null # default sampling top-p +reasoning_effort: null # default reasoning effort for llm nodes (model-dependent; e.g. low, medium, high) global_tools: # global tools available to nodes - web_search_coyote.sh mcp_servers: # MCP servers available to nodes @@ -421,6 +422,7 @@ grade_research: model: anthropic:haiku # optional override temperature: 0.0 top_p: null + reasoning_effort: null # optional override; model-dependent effort level (e.g. low, medium, high) max_attempts: 1 # transient-error retries (default 1) max_iterations: 10 # tool-call-loop turn cap (default 10) fallback: skip # routes here if all attempts fail diff --git a/REPL.md b/REPL.md index 88b7486..15643ca 100644 --- a/REPL.md +++ b/REPL.md @@ -226,6 +226,31 @@ the trimmed history. > independently of the session message list, so modifying that list could corrupt the graph's execution state. > Attempting `.undo` from inside a graph agent will produce an error. +## `.reasoning` - Set the reasoning effort level +For models that support configurable reasoning (such as `gpt-5.6-sol`, `claude-opus-4-7`, `gemini-3-flash-preview`, +etc.), you can control how much effort the model applies to each response: + +``` +.reasoning +``` + +Tab completion shows only the levels supported by the currently active model. Common level sets: + +| Provider / Model family | Supported levels | +|--------------------------------|-------------------------------------------------| +| Anthropic (most models) | `low`, `medium`, `high`, `max` | +| Anthropic (`opus-4-7` and up) | `low`, `medium`, `high`, `xhigh`, `max` | +| OpenAI o-series | `low`, `medium`, `high` | +| OpenAI `gpt-5.5` | `medium`, `high`, `xhigh` | +| OpenAI `gpt-5.6-*` | `none`, `low`, `medium`, `high`, `xhigh`, `max` | +| Gemini 2.5+ | `minimal`, `low`, `medium`, `high` | + +`.reasoning ` is equivalent to `.set reasoning_effort `. To clear the override and return to the +model's default, run `.set reasoning_effort null`. + +> **Note:** Using `.reasoning` inside a graph-based agent is not supported. Graph agents manage their own per-node +> model configuration and do not expose a top-level reasoning effort toggle. + ## `.copy` - Copy the last response to your clipboard If you're trying to copy the last response (like copying some code), you can use the `.copy` command to copy the entire last response to your system clipboard: @@ -247,6 +272,7 @@ The following settings can be adjusted at runtime: | `continuation_prompt` | string | Custom continuation prompt (supports multi-word values; `null` to reset) | | `temperature` | float | Model temperature parameter | | `top_p` | float | Model top-p parameter | +| `reasoning_effort` | string | Reasoning effort level for models that support it (e.g. `low`, `medium`, `high`); supported levels vary by model; `null` to reset to the model's default | | `enabled_tools` | string | Comma-separated list of enabled tools (e.g. `fs_ls,fs_cat` or `all`); the saved YAML config also accepts a list form | | `enabled_mcp_servers` | string | Comma-separated list of enabled MCP servers (e.g. `github,slack` or `all`); the saved YAML config also accepts a list form | | `enabled_skills` | string | Comma-separated list of enabled [skills](Skills) (e.g. `git-master,ai-slop-remover`); `null` clears the override | diff --git a/Roles.md b/Roles.md index d5d0fae..3f0de90 100644 --- a/Roles.md +++ b/Roles.md @@ -59,6 +59,7 @@ The following table lists the available configuration settings and their default | `model` | Default configured model or currently in-use model (REPL mode) | The preferred model to use with this role | | `temperature` | Default `temperature` for the preferred model | Controls the creativity and randomness of the model's responses | | `top_p` | Default `top_p` for the preferred model | Alternative way to control the model's output diversity, affecting the
probability distribution of tokens | +| `reasoning_effort` | `null` | Reasoning effort level for models that support configurable reasoning. Supported values vary by model (e.g. `low`, `medium`, `high`). See `models.yaml` for per-model levels | | `enabled_tools` | Global setting for `enabled_tools` | The tools that this role utilizes. Accepts either a YAML list or a comma-separated string | | `enabled_mcp_servers` | Global setting for `enabled_mcp_servers` | The MCP servers that this role utilizes. Accepts either a YAML list or a comma-separated string | | `skills_enabled` | Global setting for `skills_enabled` | Master switch for [skills](Skills) under this role. Set to `false` to hide all skills | diff --git a/Sessions.md b/Sessions.md index b0d2530..4d696c7 100644 --- a/Sessions.md +++ b/Sessions.md @@ -126,6 +126,7 @@ at runtime using the `.set` command or configured in the session's YAML file: | `max_auto_continues` | Global `max_auto_continues` value | Maximum number of automatic continuations before stopping. Overrides global and role settings. | | `inject_todo_instructions` | Global `inject_todo_instructions` value | Inject default todo tool usage instructions into the system prompt. Overrides global and role settings. | | `continuation_prompt` | Global `continuation_prompt` value | Custom prompt used when auto-continuing. Overrides global and role settings. | +| `reasoning_effort` | Global `reasoning_effort` value | Reasoning effort level for models that support it (e.g. `low`, `medium`, `high`). Only valid when the session's active model declares `reasoning_levels`. | | `skills_enabled` | Global `skills_enabled` value | Master switch for [skills](Skills) in this session. `.set skills_enabled null` clears the session override. | | `enabled_skills` | Inherited via the skill cascade | The active [skills](Skills) for this session. Accepts either a YAML list or a comma-separated string in the saved session YAML. |