simonw/llm-gemini

No response and exit code is zero for PROHIBITED_CONTENT

Open

#80 opened on May 18, 2025

View on GitHub
 (5 comments) (0 reactions) (0 assignees)Python (52 forks)github user discovery
help wanted

Repository metrics

Stars
 (445 stars)
PR merge metrics
 (PR metrics pending)

Description

The command like llm -m gemini-2.0-flash "prompt" -f "file.txt" returned no response nor any indication of a failure. llm version is 0.25

In responses table response field is empty. response_json is below:

{
    "promptFeedback": {
        "blockReason": "PROHIBITED_CONTENT"
    },
    "usageMetadata": {
        "promptTokenCount": 9311,
        "totalTokenCount": 9311,
        "promptTokensDetails": [
            {
                "modality": "TEXT",
                "tokenCount": 9311
            }
        ]
    },
    "modelVersion": "gemini-2.0-flash"
}

Additionally, these fields are null:

  • input_tokens
  • output_tokens
  • token_details

The quickest fix could be just output the json to stdout, so a user have a clue of what's going on.

Contributor guide

Research direction
Inspect the response handling in the plugin where a blocked response is received, and modify it to output the block reason and response JSON to stdout instead of silently ignoring.
Tech stack
python
Domain
backend
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonGit
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
75