mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(model-switch): drop stale provider from fallback chain and env after /model

Browse source 
Reported during the TUI v2 blitz test: switching from openrouter to
anthropic via `/model <name> --provider anthropic` appeared to succeed,
but the next turn kept hitting openrouter — the provider the user was
deliberately moving away from.

Two gaps caused this:

1. `Agent.switch_model` reset `_fallback_activated` / `_fallback_index`
   but left `_fallback_chain` intact. The chain was seeded from
   `fallback_providers:` at agent init for the *original* primary, so
   when the new primary returned 401 (invalid/expired Anthropic key),
   `_try_activate_fallback()` picked the old provider back up without
   informing the user. Prune entries matching either the old primary
   (user is moving away) or the new primary (redundant) whenever the
   primary provider actually changes.

2. `_apply_model_switch` persisted `HERMES_MODEL` but never updated
   `HERMES_INFERENCE_PROVIDER`. Any ambient re-resolution of the runtime
   (credential pool refresh, compressor rebuild, aux clients) falls
   through to that env var in `resolve_requested_provider`, so it kept
   reporting the original provider even after an in-memory switch.

Adds three regression tests: fallback-chain prune on primary change,
no-op on same-provider model swap, and env-var sync on explicit switch.
This commit is contained in:
Brooklyn Nicholson 2026-04-21 12:23:17 -05:00
parent ce98e1ef11
commit f0b763c74f
4 changed files with 158 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

16
run_agent.py
View file

@ -2005,6 +2005,22 @@ class AIAgent:
self._fallback_activated = False
self._fallback_index = 0
# When the user deliberately swaps primary providers (e.g. openrouter
# → anthropic), drop any fallback entries that target the OLD primary
# or the NEW one. The chain was seeded from config at agent init for
# the original provider — without pruning, a failed turn on the new
# primary silently re-activates the provider the user just rejected,
# which is exactly what was reported during TUI v2 blitz testing
# ("switched to anthropic, tui keeps trying openrouter").
old_norm = (old_provider or "").strip().lower()
new_norm = (new_provider or "").strip().lower()
if old_norm and new_norm and old_norm != new_norm:
self._fallback_chain = [
entry for entry in self._fallback_chain
if (entry.get("provider") or "").strip().lower() not in {old_norm, new_norm}
]
self._fallback_model = self._fallback_chain[0] if self._fallback_chain else None
logging.info(
"Model switched in-place: %s (%s) -> %s (%s)",
old_model, old_provider, new_model, new_provider,