Skim v1.0.26 — "Think Less, Answer More" 🧠

The one where OpenAI told us our tools and its own thinking couldn't be in the same room, and we said fine, we'll ask nicely twice.

Mailbox chat works again on gpt-5.6 models. Point the OpenAI-compatible provider at OpenAI with a gpt-5.6-* model and every single round that carried tools came back as a 400 and a wall of English error prose in the chat bubble. Retrying showed you the same wall. Very helpful. 🙃 (#40)
The twist: Skim never sent reasoning_effort at all. The model reasons at medium on its own, then refuses its own default alongside our tools — so nothing in our request even named the thing that broke it.
We still don't guess. No model-name regex, no "is this OpenAI?" sniffing — the same base URL serves OpenRouter, Ollama, LM Studio, vLLM and whatever you typed in that box, and half of them would 422 on the "fix". So Skim sends nothing up front, waits for the endpoint to name the remedy in its own error, and retries exactly once with the value it asked for — tools still attached, because answering without the search results would rather defeat the point. 🎯

Two scripted-socket tests for the retry path, which previously had a proud total of zero: one pins that the second request really goes out carrying the same tools, the other that an endpoint refusing even under none gives up instead of hammering a metered API in a loop. 💸
266 tests green, cargo fmt appeased, Scoop manifest caught up with 1.0.25.

Big thanks to @ondrahracek for the fix — and for verifying it against the live API rather than vibes. 🙏

14 views