Test Reasoning Serialization
FreeValidate reasoning parameters for provider APIs.
Free · Opens the source repo
What Test Reasoning Serialization does
The Test Reasoning Serialization skill is designed for developers working with AI models that require precise configuration of reasoning parameters. This skill validates that the ReasoningConfig fields are serialized correctly into provider-specific JSON formats for various AI services, including OpenRouter, Anthropic, GitHub Copilot, and Codex. By ensuring that the reasoning parameters are accurately represented, developers can avoid potential issues when making API calls to these services.
To use this skill, you can run the provided script, test-reasoning.sh, which executes a series of tests across different provider and model combinations. The script captures the outgoing HTTP request body, allowing you to verify that the expected JSON fields are present and correctly formatted. This is particularly useful when integrating with multiple AI providers, as each may have unique requirements for how reasoning parameters should be structured.
The skill also supports manual testing for specific configurations, enabling developers to debug and inspect the serialized output for any given provider and model. This flexibility allows for targeted validation of reasoning configurations, ensuring that developers can quickly identify and rectify any discrepancies in their setup.
Overall, this skill is essential for developers who need to ensure that their AI integrations are robust and correctly configured, particularly in environments where accuracy in reasoning parameters is critical for optimal performance.
When to use it
Use this skill when you need to validate reasoning configurations before making API calls to AI providers.
When not to use it
This skill is not suitable for scenarios where reasoning parameters are not required or when working with providers outside the supported list.
What you can build with it
Validating API Calls
Ensure that your reasoning parameters are serialized correctly before making API requests to avoid errors.
Debugging Configuration Issues
Use the skill to manually test and inspect the serialized output for specific provider and model combinations.
Integrating Multiple AI Providers
Streamline the validation process for reasoning configurations across different AI services.
How to install Test Reasoning Serialization
View source1. Install with the skills CLI
npx skills add tailcallhq/forgecode/test-reasoning --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by tailcallhqTest Reasoning Serialization
Validates that ReasoningConfig fields are correctly serialized into provider-specific JSON
for OpenRouter, Anthropic, GitHub Copilot, and Codex.
Quick Start
Run all tests with the bundled script:
./scripts/test-reasoning.sh
The script builds forge in debug mode, runs each provider/model combination, captures the
outgoing HTTP request body via FORGE_DEBUG_REQUESTS, and asserts the correct JSON fields.
Running a Single Test Manually
FORGE_DEBUG_REQUESTS="forge.request.json" \
FORGE_SESSION__PROVIDER_ID=<provider_id> \
FORGE_SESSION__MODEL_ID=<model_id> \
FORGE_REASONING__EFFORT=<effort> \
target/debug/forge -p "Hello!"
Then inspect .forge/forge.request.json for the expected fields.
Test Coverage
| Provider | Model | Config fields | Expected JSON field |
|---|---|---|---|
open_router | openai/o4-mini | effort: none|minimal|low|medium|high|xhigh | reasoning.effort |
open_router | openai/o4-mini | max_tokens: 4000 | reasoning.max_tokens |
open_router | openai/o4-mini | effort: high + exclude: true | reasoning.effort + .exclude |
open_router | openai/o4-mini | enabled: true | reasoning.enabled |
open_router | anthropic/claude-opus-4-5 | max_tokens: 4000 | reasoning.max_tokens |
open_router | moonshotai/kimi-k2 | max_tokens: 4000 | reasoning.max_tokens |
open_router | moonshotai/kimi-k2 | effort: high | reasoning.effort |
open_router | minimax/minimax-m2 | max_tokens: 4000 | reasoning.max_tokens |
open_router | minimax/minimax-m2 | effort: high | reasoning.effort |
anthropic | claude-opus-4-6 | effort: low|medium|high|max | output_config.effort |
anthropic | claude-3-7-sonnet-20250219 | enabled: true + max_tokens: 8000 | thinking.type + budget_tokens |
github_copilot | o4-mini | effort: none|minimal|low|medium|high|xhigh | reasoning_effort (top-level) |
codex | gpt-5.1-codex | effort: none|minimal|low|medium|high|xhigh | reasoning.effort + .summary |
codex | gpt-5.1-codex | effort: medium + exclude: true | reasoning.summary = "concise" |
| all providers | one model each | effort: invalid | non-zero exit, no request written |
Tests for unconfigured providers are skipped automatically. Invalid-effort tests run regardless of credentials — the rejection happens at config parse time before any provider interaction.
References
Frequently asked questions about Test Reasoning Serialization
Similar skills
WinMD API Search
Easily find and explore Windows desktop APIs.
WebMCPify
Transform any web app into an agent-ready platform.
Phoenix Tracing
Instrument LLM applications with OpenInference tracing.
Foundry Hosted Agent CopilotKit
Guidance for developing agentic web apps on Azure.
Power Automate Foundation
Connect AI agents to Power Automate seamlessly.
Power Automate Flow Builder
Efficiently build and deploy Power Automate flows programmatically.