The prompt your SDK sends is not the prompt you wrote
The article discusses the challenges faced when the SDK does not send the expected prompt. The author created a tool called agenttap to intercept and analyze the actual JSON requests sent by the SDK. This tool helps identify discrepancies between the intended and actual requests, improving debugging for AI interactions.
- ▪The author encountered issues where the SDK modified the request body unexpectedly.
- ▪Agenttap captures the full request details, including URL, headers, and body, for analysis.
- ▪The tool allows users to replay and diff requests to identify changes and regressions.
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 →
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/mukundakatta/the-prompt-your-sdk-sends-is-not-the-prompt-you-wrote-1o3l |
| Publication time | Thu, 21 May 2026 01:51:44 +0000 |
| Retrieval time | 2026-05-21T02:05:03.425Z |
| Last seen | 2026-05-21T02:05:03.425Z |
| 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 | 7hMgo3OYkiQA |
| 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 === 3915555) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } Mukunda Rao Katta Posted on May 21 The prompt your SDK sends is not the prompt you wrote #hermesagent #ai #llm #python A reply from Claude came back nonsense. The system prompt looked fine in my code. The messages looked fine in my logs. So I added a print(messages) right before client.messages.create(...). Still fine. I was looking in the wrong place. The SDK was building the request body. What hit the wire was not what I was printing.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).
Discussion
0 commentsMore from DEV.to (Top)
