molecule-ai/hermes-agent
36
0
Fork 0
Code Issues 4 Pull Requests 5 Actions 104 Packages Projects Releases Wiki Activity
d30ea65c9b
hermes-agent/agent
History
Teknium d30ea65c9b
fix: URL-based auth for third-party Anthropic endpoints + CI test fixes (#4148) 
* fix(tests): mock sys.stdin.isatty for cmd_model TTY guard

* fix(tests): update camofox snapshot format + trajectory compressor mock path

- test_browser_camofox: mock response now uses snapshot format (accessibility tree)
- test_trajectory_compressor: mock _get_async_client instead of setting async_client directly

* fix: URL-based auth detection for third-party Anthropic endpoints + test fixes

Reverts the key-prefix approach from #4093 which broke JWT and managed
key OAuth detection. Instead, detects third-party endpoints by URL:
if base_url is set and isn't anthropic.com, it's a proxy (Azure AI
Foundry, AWS Bedrock, etc.) that uses x-api-key regardless of key format.

Auth decision chain is now:
1. _requires_bearer_auth(url) → MiniMax → Bearer
2. _is_third_party_anthropic_endpoint(url) → Azure/Bedrock → x-api-key
3. _is_oauth_token(key) → OAuth on direct Anthropic → Bearer
4. else → x-api-key

Also includes test fixes from PR #4051 by @erosika:
- Mock sys.stdin.isatty for cmd_model TTY guard
- Update camofox snapshot format mock
- Fix trajectory compressor async client mock path

---------

Co-authored-by: Erosika <eri@plasticlabs.ai>
2026-03-30 20:36:56 -07:00
..
__init__.py Refactor Terminal and AIAgent cleanup 2026-02-21 22:31:43 -08:00
anthropic_adapter.py fix: URL-based auth for third-party Anthropic endpoints + CI test fixes (#4148) 2026-03-30 20:36:56 -07:00
auxiliary_client.py fix: add INFO-level logging for auxiliary provider resolution (#3866) 2026-03-29 21:29:00 -07:00
context_compressor.py fix: cap percentage displays at 100% in stats, gateway, and memory tool (#3599) 2026-03-28 14:55:18 -07:00
context_references.py fix: add timeout to subprocess calls in context_references (#3469) 2026-03-27 17:51:14 -07:00
copilot_acp_client.py fix(acp): preserve leading whitespace in streaming chunks 2026-03-20 09:38:13 -07:00
display.py feat(display): configurable tool preview length -- show full paths by default (#3841) 2026-03-29 18:02:42 -07:00
insights.py chore: fix 154 f-strings, simplify getattr/URL patterns, remove dead code (#3119) 2026-03-25 19:47:58 -07:00
model_metadata.py fix(agent): support full context length resolution for direct Gemini API endpoints (#3876) 2026-03-29 21:56:07 -07:00
models_dev.py fix: write models.dev disk cache atomically (#3588) 2026-03-28 14:20:30 -07:00
prompt_builder.py feat(skills): support external skill directories via config (#3678) 2026-03-29 00:33:30 -07:00
prompt_caching.py fix(prompt-caching): skip top-level cache_control on role:tool for OpenRouter 2026-03-21 16:54:43 -07:00
redact.py fix(security): extend secret redaction to ElevenLabs, Tavily and Exa API keys (#3920) 2026-03-30 08:13:01 -07:00
skill_commands.py feat(skills): support external skill directories via config (#3678) 2026-03-29 00:33:30 -07:00
skill_utils.py feat(skills): support external skill directories via config (#3678) 2026-03-29 00:33:30 -07:00
smart_model_routing.py feat: integrate GitHub Copilot providers across Hermes 2026-03-17 23:40:22 -07:00
title_generator.py feat(agent): configurable timeouts for auxiliary LLM calls via config.yaml (#3597) 2026-03-28 14:35:28 -07:00
trajectory.py Refactor Terminal and AIAgent cleanup 2026-02-21 22:31:43 -08:00
usage_pricing.py fix: status bar shows 26K instead of 260K for token counts with trailing zeros (#3024) 2026-03-25 12:45:58 -07:00