mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-26 01:01:40 +00:00
ffd5d37f9b
* fix: treat non-sk-ant- prefixed keys (Azure AI Foundry) as regular API keys, not OAuth tokens * fix: treat non-sk-ant- keys as regular API keys, not OAuth tokens _is_oauth_token() returned True for any key not starting with sk-ant-api, misclassifying Azure AI Foundry keys as OAuth tokens and sending Bearer auth instead of x-api-key → 401 rejection. Real Anthropic OAuth tokens all start with sk-ant-oat (confirmed from live .credentials.json). Non-sk-ant- keys are third-party provider keys that should use x-api-key. Test fixtures updated to use realistic sk-ant-oat01- prefixed tokens instead of fake strings. Salvaged from PR #4075 by @HangGlidersRule. --------- Co-authored-by: Clawdbot <clawdbot@openclaw.ai> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| test_auxiliary_client.py | ||
| test_context_compressor.py | ||
| test_display_emoji.py | ||
| test_external_skills.py | ||
| test_model_metadata.py | ||
| test_models_dev.py | ||
| test_prompt_builder.py | ||
| test_prompt_caching.py | ||
| test_redact.py | ||
| test_skill_commands.py | ||
| test_smart_model_routing.py | ||
| test_subagent_progress.py | ||
| test_title_generator.py | ||
| test_usage_pricing.py | ||