Home / tailcallhq / forgecode · .forge/skills/test-reasoning/SKILL.md · GitHub

test-reasoning skillA

test-reasoning is agent-read markdown (skill) from tailcallhq/forgecode: Validate that reasoning parameters are correctly serialized and sent to provider APIs. Use when the user asks to test reasoning serialization, run reasoning tests, verify reasoning config fields, or check that ReasoningConfig maps correctly to provider-specific JSON (OpenRouter, Anthropic, GitHub Copilot, Codex)..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified before it reaches your agent: the main file against the SHA-256 recorded here, the others against the git hashes of its source commit. The deterministic audit below grades the latest version, and the same checks always give the same file the same grade.

What the file says

# Test 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:

```bash
./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

```bash
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               |
| ---------------- | ---------------------------- | ------------------------------------------------- | --------------------------------- |
…

Read the whole file at its exact version.

How to install

Latest version
mdr add tailcallhq/forgecode/test-reasoning@git:20260402.1e409fa
Exact content
mdr add tailcallhq/forgecode/test-reasoning@sha256:4f98815ab6654a4a

Pin to a label to follow the author's releases, or to a sha256 for exact bytes. Either way the resolved hash is written to mdr.lock, and mdr install fetches those bytes again and checks them, so it installs them exactly or fails.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ssdbimkvqzckfutr.svg)](https://markdownregistry.com/a/art_ssdbimkvqzckfutr)

2 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260402.1e409fa latest2026-04-02 1e409fa 4,148 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4148 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

tailcallhq/forgecode · 7,637 stars · license Apache-2.0 · pushed 2026-09-26 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ssdbimkvqzckfutr
GET https://markdownregistry.com/api/v1/resolve?ref=tailcallhq/forgecode/test-reasoning
GET https://markdownregistry.com/api/v1/blob/4f98815ab6654a4abb81c1e44ec337cf4ec7e8bd487748eba425027cd98fac80

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from tailcallhq/forgecode

create-agent skill
tailcallhq/forgecode · .forge/skills/create-agent/SKILL.md · Create new agents for the code-forge application. Agents are stored as .md files in the <cwd>/.forge/agents directory…
git:20260126.0427bf8 · audit A · 7,637 stars
create-command skill
tailcallhq/forgecode · .forge/skills/create-command/SKILL.md · Create new commands for the code-forge application. Commands are stored as .md files in the <cwd>/.forge/commands…
git:20260126.0427bf8 · audit A · 7,637 stars
create-github-issue skill
tailcallhq/forgecode · .forge/skills/create-github-issue/SKILL.md · Create GitHub issues using GitHub CLI with support for templates, labels, assignees, milestones, and draft issues. Use…
git:20260212.ac26e78 · audit A · 7,637 stars
create-plan skill
tailcallhq/forgecode · .forge/skills/create-plan/SKILL.md · Generate detailed implementation plans for complex tasks. Creates comprehensive strategic plans in Markdown format with…
git:20251211.d9b44e8 · audit A · 7,637 stars
debug-cli skill
tailcallhq/forgecode · .forge/skills/debug-cli/SKILL.md · Use when users need to debug, modify, or extend the code-forge application's CLI commands, argument parsing, or CLI…
git:20251129.d8cba1f · audit A · 7,637 stars
github-pr-comments skill
tailcallhq/forgecode · .forge/skills/github-pr-comments/SKILL.md · Resolve inline code review comments on a GitHub PR. Use when asked to "resolve review comments", "address PR feedback"…
git:20260402.238a5b9 · audit A · 7,637 stars
post-forge-feature skill
tailcallhq/forgecode · .forge/skills/post-forge-feature/SKILL.md · Generate a Twitter/X post highlighting a Forge feature. Use when the user asks to write a tweet, create a Twitter post…
git:20260321.bba73fb · audit A · 7,637 stars
resolve-conflicts skill
tailcallhq/forgecode · .forge/skills/resolve-conflicts/SKILL.md · Use this skill immediately when the user mentions merge conflicts that need to be resolved. Do not attempt to resolve…
git:20251127.ee24908 · audit A · 7,637 stars
resolve-fixme skill
tailcallhq/forgecode · .forge/skills/resolve-fixme/SKILL.md · Find all FIXME comments across the codebase and fully implement the work they describe. Use when the user asks to fix…
git:20260413.7ca79c7 · audit A · 7,637 stars
write-release-notes skill
tailcallhq/forgecode · .forge/skills/write-release-notes/SKILL.md · Generate engaging, high-energy release notes for a given version tag. Fetches the release from GitHub, retrieves every…
git:20260413.a1642f4 · audit A · 7,637 stars
AGENTS.md agents
tailcallhq/forgecode · AGENTS.md
git:20251208.4905ae0 · audit A · 7,637 stars
minimal-skill skill
tailcallhq/forgecode · crates/forge_repo/src/fixtures/skills_with_resources/minimal-skill/SKILL.md · A minimal skill with no resources
git:20251124.2b8f212 · audit B · 7,637 stars

Every file in tailcallhq/forgecode

Browse by kind, by grade A, or by owner.