> LLMs return malformed JSON more often than you'd expect, especially with nested arrays and complex schemas. One bad bracket and your pipeline crashes.
This might be one reason why Claude Code uses XML for tool calling: repeating the tag name in the closing bracket helps it keep track of where it is during inference, so it is less error prone.
Yeah that's a good observation. XML's closing tags give the model structural anchors during generation — it knows where it is in the nesting. JSON doesn't have that, so the deeper the nesting the more likely the model loses track of brackets.
We see this especially with arrays of objects where each object has optional nested fields. The model will get 18 items right and then drop a closing bracket on item 19. That's why we put effort into the repair/recovery/sanitization layer — validate field-by-field and keep what's valid rather than throwing everything out.
This looks pretty interesting! I haven't used it yet, but looked through the code a bit, it looks like it uses turndown to convert the html to markdown first, then it passes that to the LLM so assuming that's a huge reduction in tokens by preprocessing. Do you have any data on how often this can cause issues? ie tables or other information being lost?
Then langchain and structured schemas for the output along w/ a specific system prompt for the LLM. Do you know which open source models work best or do you just use gemini in production?
Also, looking at the docs, Gemini 2.5 flash is getting deprecated by June 17th https://ai.google.dev/gemini-api/docs/deprecations#gemini-2.... (I keep getting emails from Google about it), so might want to update that to Gemini 3 Flash in the examples.
Good point. The anti-bot patches here (via Patchright) are about preventing the browser from being detected as automated — things like CDP leak fixes so Cloudflare doesn't block you mid-session. It's not about bypassing access restrictions.
Our main use case is retail price monitoring — comparing publicly listed product prices across e-commerce sites, which is pretty standard in the industry. But fair point, we should make that clearer in the README.
Good point. The anti-bot patches here (via Patchright) are about preventing the browser from being detected as automated — things like CDP leak fixes so Cloudflare doesn't block you mid-session. It's not about bypassing access restrictions.
Our main use case is retail price monitoring — comparing publicly listed product prices across e-commerce sites, which is pretty standard in the industry. But fair point, we should make that clearer in the README.
This might be one reason why Claude Code uses XML for tool calling: repeating the tag name in the closing bracket helps it keep track of where it is during inference, so it is less error prone.
We see this especially with arrays of objects where each object has optional nested fields. The model will get 18 items right and then drop a closing bracket on item 19. That's why we put effort into the repair/recovery/sanitization layer — validate field-by-field and keep what's valid rather than throwing everything out.
Then langchain and structured schemas for the output along w/ a specific system prompt for the LLM. Do you know which open source models work best or do you just use gemini in production?
Also, looking at the docs, Gemini 2.5 flash is getting deprecated by June 17th https://ai.google.dev/gemini-api/docs/deprecations#gemini-2.... (I keep getting emails from Google about it), so might want to update that to Gemini 3 Flash in the examples.
And it doesn't care about robots.txt.
Our main use case is retail price monitoring — comparing publicly listed product prices across e-commerce sites, which is pretty standard in the industry. But fair point, we should make that clearer in the README.
Our main use case is retail price monitoring — comparing publicly listed product prices across e-commerce sites, which is pretty standard in the industry. But fair point, we should make that clearer in the README.