hermes-agent/gateway
Test f3b2303428 fix(gateway): skip model auto-detection for custom/local providers
Mirrors the CLI fix for the gateway /model handler. When the user is on
a custom provider (provider=custom, localhost, or 127.0.0.1 endpoint),
/model <name> no longer tries to auto-detect a provider switch.

Previously, typing /model openrouter/nvidia/nemotron:free on Telegram
while on a localhost endpoint would silently accept the model name on
the local server — auto-detection failed to match the free model, so
the provider stayed as custom with the localhost base_url. The user saw
'Model changed' but requests still went to localhost, which doesn't
serve that model.

Now shows the endpoint URL and provider:model syntax tip, matching
the CLI behavior.
2026-03-20 21:07:48 -07:00
..
platforms Merge pull request #2199 from llbn/fix/telegram-markdownv2-features 2026-03-20 12:45:47 -07:00
__init__.py Enhance CLI with multi-platform messaging integration and configuration management 2026-02-02 19:01:51 -08:00
channel_directory.py feat: add SMS (Twilio) platform adapter 2026-03-17 03:14:53 -07:00
config.py feat(gateway): add webhook platform adapter for external event triggers 2026-03-20 06:33:36 -07:00
delivery.py Merge origin/main into hermes/hermes-5d160594 2026-03-14 19:34:05 -07:00
hooks.py feat(hooks): emit session:end lifecycle event (#1725) 2026-03-17 04:17:44 -07:00
mirror.py fix(cli): respect HERMES_HOME in all remaining hardcoded ~/.hermes paths 2026-03-13 21:32:53 -07:00
pairing.py fix(cli): respect HERMES_HOME in all remaining hardcoded ~/.hermes paths 2026-03-13 21:32:53 -07:00
run.py fix(gateway): skip model auto-detection for custom/local providers 2026-03-20 21:07:48 -07:00
session.py fix(session): skip corrupt lines in load_transcript instead of crashing (#1744) 2026-03-17 05:18:12 -07:00
status.py fix(gateway): detect script-style gateway processes for --replace 2026-03-18 03:12:59 -07:00
sticker_cache.py fix(cli): respect HERMES_HOME in all remaining hardcoded ~/.hermes paths 2026-03-13 21:32:53 -07:00
stream_consumer.py fix: handle message length overflow in streaming mode (#1783) 2026-03-17 11:00:52 -07:00