continuedev / continuedev/continue

Continue is not able to read webpages

Open
#13,083 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
TypeScript
Stars
36k
Forks
5.4k
PR merge metrics
No merged PRs in 30d

Description

Type: Bug

The current website-reading tool is called fetch_url_content. Continue via GPT-5.6-sol reports that fetch_url_content is not able to read parts of webpages hidden by javascript. Example: I am building an API handler, and I give the ai the url to the API documentation. The ai reports that it has read the webpage and procedes to build the handler code. Later investigation reveals that not all the rules have been followed because that documentation was "hidden" behind javascript navigation (e.g. tab clicks) on the html page. The result is errors in the the generated code and no warning from the ai that a problem has been encountered. Please suggest a solution to this problem that works for this scenario.

Extension version: 2.0.0
VSCodium version: VSCodium 1.126.04524 (4c0b0c6cc561d2d3636d1ec250935431876ce4dc, 2026-06-23T01:46:13Z)
OS version: Darwin arm64 24.6.0
Modes:

System Info
Item Value
CPUs Apple M2 Max (12 x 2400)
GPU Status 2d_canvas: enabled
direct_rendering_display_compositor: disabled_off_ok
gpu_compositing: enabled
multiple_raster_threads: enabled_on
opengl: enabled_on
rasterization: enabled
raw_draw: disabled_off_ok
skia_graphite: enabled_on
trees_in_viz: disabled_off
video_decode: enabled
video_encode: enabled
webgl: enabled
webgpu: enabled
webnn: disabled_off
Load (avg) 2, 2, 2
Memory (System) 64.00GB (14.05GB free)
Process Argv
Screen Reader no
VM 0%

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by tracing the fetch_url_content tool and how it reports webpage contents to the model. Reproduce the reported case with documentation whose content is revealed by JavaScript navigation, then define completion as either retrieving that content or clearly warning that it was not read; the issue names no files or tests to run.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
ai, devtools, web-dev
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.