vllm-reasoning-parsers SKILL.md skillA
vllm-reasoning-parsers from air-gapped/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add air-gapped/skills/vllm-reasoning-parsers@git:20261018.76fe4c5Pins git:20261018.76fe4c5 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- air-gapped/skills
- Path
.claude/skills/vllm-reasoning-parsers/SKILL.md- Versions recorded
- 17
- Latest version
- git:20261018.76fe4c5, committed Oct 18, 2026
- First version recorded
- Aug 11, 2026
- Size
- 22,396 bytes
- Repository stars
- 6
- License
- MIT
vLLM reasoning-parser operator + developer reference. `--reasoning-parser` CLI wiring, `ReasoningParser` contract (non-streaming `extract_reasoning` + per-delta `extract_reasoning_streaming`), `is_reasoning_end` xgrammar gating, `--structured-outputs-config.enable_in_reasoning` bypass, 38 built-in parsers (v0.32.0) with per-model quirks, 15 production pitfalls, authoring custom parsers via `@ReasoningParserManager.register_module` or plugin.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# vLLM reasoning parsers Target: operators wiring up `--reasoning-parser NAME` on a chat-completion endpoint, or developers authoring a parser for a new thinking model. Source of truth: `vllm/reasoning/` on `main`. ## What a reasoning parser actually does When a reasoning-trained model emits a single token stream like ``` <think>user asked X, let me check Y...</think>The answer is 42. ``` vLLM splits this into two fields on the chat-completion response: `reasoning` (the CoT) and `content` (the final answer). `--reasoning-parser NAME` selects the class that does the split. Without it, the whole stream lands in `content`. > **Field-name note.** The response field is `reasoning` (`ChatMessage.reasoning` in `vllm/entrypoints/openai/chat_completion/protocol.py`, `DeltaMessage.reasoning` in `vllm/entrypoints/generate/base/protocol.py`). `reasoning_content` was **removed from the output in v0.16.0** ([#33402](https://github.com/vllm-project/vllm/pull/33402), merge `c5113f60`), and v0.28.0 documents the result as a breaking client change ([#50624](https://github.com/vllm-project/vllm/pull/50624)). Many third-party docs and clients still call it `reasoning_content`. **The asymmetry… …
Read the whole file at its exact version.
How to install
mdr add air-gapped/skills/vllm-reasoning-parsers@sha256:6531b3102bb0921eThe line at the top of this page pins the label git:20261018.76fe4c5, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ymuqtlc6zc5dlyp2)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 17 versions of this file, between Aug 11, 2026 and Oct 18, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261018.76fe4c5 latest | 2026-10-18 | 76fe4c5 | 22,396 B | A | view · diff |
| git:20261018.3eeaab1 | 2026-10-18 | 3eeaab1 | 22,484 B | A | view · diff |
| git:20261018.41176b4 | 2026-10-18 | 41176b4 | 22,928 B | A | view · diff |
| git:20261018.a8a15f7 | 2026-10-18 | a8a15f7 | 22,936 B | A | view · diff |
| git:20261018.0ca71ec | 2026-10-18 | 0ca71ec | 22,849 B | A | view · diff |
| git:20261003.024e2ab | 2026-10-03 | 024e2ab | 19,547 B | A | view · diff |
| git:20261003.1bec3b5 | 2026-10-03 | 1bec3b5 | 20,119 B | A | view · diff |
| git:20261003.2768b58 | 2026-10-03 | 2768b58 | 20,188 B | A | view · diff |
| git:20261003.5069f82 | 2026-10-03 | 5069f82 | 20,381 B | A | view · diff |
| git:20261003.fdb101f | 2026-10-03 | fdb101f | 20,097 B | A | view · diff |
| git:20260923.466430c | 2026-09-23 | 466430c | 19,862 B | A | view · diff |
| git:20260922.fd88423 | 2026-09-22 | fd88423 | 19,317 B | A | view · diff |
| git:20260915.23b818e | 2026-09-15 | 23b818e | 18,520 B | A | view · diff |
| git:20260915.6563fb4 | 2026-09-15 | 6563fb4 | 18,483 B | A | view · diff |
| git:20260915.ca67945 | 2026-09-15 | ca67945 | 17,928 B | A | view · diff |
| git:20260818.36f6464 | 2026-08-18 | 36f6464 | 17,497 B | A | view · diff |
| git:20260811.bafc98b | 2026-08-11 | bafc98b | 17,424 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (22396 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
air-gapped/skills · 6 stars · license MIT · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ymuqtlc6zc5dlyp2 GET https://markdownregistry.com/api/v1/resolve?ref=air-gapped/skills/vllm-reasoning-parsers GET https://markdownregistry.com/api/v1/blob/6531b3102bb0921e4ff758d8194ae528faf68860ccadaf028b45e6d54ff47c95
Your AI assistant 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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.