Qwen 3.6 enable_thinking — The MoE Pitfall That Broke My Agent JSON Parsing
The article discusses a quirk in Qwen 3.6 that causes issues with JSON parsing due to an unexpected reasoning output. The author experienced frustration when their agent returned malformed JSON, which included unnecessary reasoning tokens. A simple fix is provided, highlighting the importance of adjusting a specific keyword argument to avoid the problem.
- ▪Qwen 3.6 has a default reasoning mode that can interfere with JSON output.
- ▪The author encountered a JSONDecodeError due to the model's reasoning output being included in responses.
- ▪The solution involves setting enable_thinking=False in the apply_chat_template function.
DEV.to (Top) files mainly under programming. We currently carry 4,924 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | DEV.to (Top) |
| Canonical URL | https://dev.to/sleepyquant/qwen-36-enablethinking-the-moe-pitfall-that-broke-my-agent-json-parsing-71a |
| Publication time | Mon, 18 May 2026 13:21:03 +0000 |
| Retrieval time | 2026-05-18T13:34:56.501Z |
| Last seen | 2026-05-18T13:34:56.501Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | D6Vs-dqAEQeE |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 3885340) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } SleepyQuant Posted on May 18 • Originally published at sleepyquant.rest Qwen 3.6 enable_thinking — The MoE Pitfall That Broke My Agent JSON Parsing #qwen #mlx #localai #llminference Qwen 3.6 enable_thinking — The MoE Pitfall That Broke My Agent JSON Parsing I lost two hours last week to a Qwen 3.6 quirk that doesn't show up in any quickstart guide. My agent kept returning malformed JSON.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).
Discussion
0 commentsMore from DEV.to (Top)
