engineering/uncloseai.com
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
uncloseai.com/docs/tickets/005-context-overflow-silent-failure.md
russell@unturf.com 12e9e79f25 disable TTS via feature flag, move floating button up 121px, add bug tickets 
TTS disabled by default for all users (tickets #002 freeze, #003 truncation).
Embedders re-enable with window.UNCLOSEAI_ENABLE_TTS = true.
Floating button bottom 20px to 141px to avoid overlapping page buttons.
Added docs/tickets/ with 5 issues from cthegray.
Bundle extension script and biome config updates.
2026-03-03 15:56:09 -05:00

2 KiB
Raw Blame History

005: Context overflow causes blank or hallucinated responses

Reporter: cthegray Date: 2026-03-03 Priority: high Status: open Affects: All platforms, chat quality

Description

When the context window fills up (long pages injected as context), the model either:

  1. Returns completely blank responses (silent failure, nothing displayed)
  2. Starts hallucinating about unrelated content, specifically talking about the uncloseai.com page itself or the Nous Research page

Reproduction

  1. Navigate to a very long page (e.g., Wikipedia's Napoleon article)
  2. Use the page-read feature to inject the page content as context
  3. Ask a question about the page
  4. Response is either blank or talks about uncloseai/Nous Research instead of the page content

Analysis

The page content is likely exceeding the model's max_model_len (context window). When this happens:

  • The API may return an error that the client silently swallows (blank response)
  • The context may be truncated in a way that drops the user's page content but keeps the system prompt and uncloseai UI text, causing the model to talk about those instead
  • The Nous Research hallucination suggests the model's training data is bleeding through when it has no useful context to work with

Possible fixes:

  • Check page content length before injection, truncate intelligently if it exceeds the model's max_model_len (available from /v1/models discovery)
  • Show a user-facing warning when context is too long: "This page is too long, content has been trimmed"
  • Implement chunked summarization for long pages (summarize in sections, then inject summaries)
  • Never silently swallow API errors: if the completion fails, show the error to the user
  • Prioritize user message and page content over system prompt when truncating

Notes

The max_model_len field from model discovery should be used to calculate available context budget. System prompt + conversation history + page content must fit within this limit. If it doesn't, the client needs a truncation strategy, not silent failure.