[BUG] Image poisoining

Preflight Checklist

• [x] I have searched existing issues and this hasn't been reported yet
• [x] This is a single bug report (please file separate reports for different bugs)
• [x] I am using the latest version of Claude Code

What's Wrong?

When the model chooses to read an image it fails, errors out then completely nukes the entire chat. Its completely unable to respond after its tried to read something it cant, not even /compact works i have to /clear

What Should Happen?

?? it shouldnt completely block me out from talking to the agent, this problem nuked many hours of work.

Error Messages/Logs

● Let me look at the flow and the OCR code to understand what's going on.

● Searched for 5 patterns, read 3 files (ctrl+o to expand)

● Let me check the screen and zones config.

● Searched for 2 patterns, read 1 file (ctrl+o to expand)
  ⎿  API Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"Could not
     process image"},"request_id":"req_011CZ4Frgg271a7WWY5Wb1oX"}

✻ Cooked for 1m 31s

❯ what?
  ⎿  API Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"Could not
     process image"},"request_id":"req_011CZ4FsT6isfrrKdBPGcmbm"}

Steps to Reproduce

no clue

`● Search(pattern: "text_exists", path: "core\flow_executor.py")
⎿  Found 65 lines (ctrl+o to expand)

● Search(pattern: "def.ocr|def.text_exists|def.find_text|def.read_text", path: "core")
⎿  Found 11 lines (ctrl+o to expand)

● Read(core\text_detector.py)
⎿  Read 372 lines

● Read(core\flow_executor.py)
⎿  Read 50 lines

● Search(pattern: "def _search_text_in_region", path: "core\flow_executor.py")
⎿  Found 61 lines (ctrl+o to expand)

● Search(pattern: "def fuzzy_team_match", path: "core")
⎿  Found 81 lines (ctrl+o to expand)

● Search(pattern: "def normalize_team_name|def extract_key_words", path: "core\flow_executor.py")
⎿  Found 52 lines (ctrl+o to expand)

11:45 PM claude-opus-4-6
● Let me check the screen and zones config.

● Read(screen_check.jpg)
⎿  Read image (207 bytes)

● Search(pattern: "config/flows/**/*")
⎿  Found 2 files (ctrl+o to expand)

● Search(pattern: "def _action_conditional", path: "core\flow_executor.py")
⎿  Found 101 lines (ctrl+o to expand)

11:45 PM <synthetic>
⎿  API Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"Could not
process image"},"request_id":"req_011CZ4Frgg271a7WWY5Wb1oX"}

✻ Brewed for 1m 31s

❯ what?

11:45 PM <synthetic>
⎿  API Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"Could not
process image"},"request_id":"req_011CZ4FsT6isfrrKdBPGcmbm"}

❯ hello

11:49 PM <synthetic>
⎿  API Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"Could not
process image"},"request_id":"req_011CZ4GBSvZNUi1NgUkALZtq"}`

Claude Model

Opus

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

2.1.76

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

Windows Terminal

Additional Information

_No response_