[BUG]: Shannon doesn't work with litellm proxy

Describe the bug

Config.toml

api_key = "my litellm api key"

[core] model = "openai:gpt-5.4" base_url = "http://localhost:4000/"

the scan used to fail before migration to shannon 3.2 the call doesn't reach my litellm proxy but after migration the scan is automatically canceled.

Steps to reproduce

1.npx @keygraph/shannon start -u http://myapp.com/ -r C:\Users*****.shannon\workspaces 2. 3.

Expected behaviour

scan the target

Actual behaviour

Scan canceled ERROR: Shannon encountered an unexpected failure. Reference code: SHANNON_UNEXPECTED_ERROR

Pre-submission checklist (required)

• I have searched the existing open issues and confirmed this bug has not already been reported.
• I am running the latest released version of shannon.

If applicable

• I have included relevant error messages, stack traces, or failure details.
• I have checked the workspaces folder for logs and pasted the relevant errors.
• I have inspected the failed Temporal workflow run and included the failure reason.
• I have included clear steps to reproduce the issue.
• I have redacted any sensitive information (tokens, URLs, repo names).

Debugging details

No response

Screenshots

CLI mode

npx (@keygraph/shannon)

Provider

Custom base URL - OpenAI Responses

Full command with all flags used (with redactions)

npx @keygraph/shannon start -u http://myapp.com/ -r C:\Users*****.shannon\workspaces

OS (with version)

windows 11

Node.js version ('node -v')

v26.7.0

Docker version ('docker -v')

29.7.2, build a7dcaa6

Additional context

No response