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

refactor: invalidate transport cache when api_mode auto-upgrades to codex_responses

Browse source 
Follow-up for #13862 — the post-init api_mode upgrade at __init__ (direct OpenAI /
gpt-5-requires-responses path) runs AFTER the eager transport warm. Clear the cache
so the stale chat_completions entry is evicted.

Cosmetic: correctness was already fine since _get_transport() keys by current
api_mode, but this avoids leaving unused cache state behind.
This commit is contained in:
Teknium 2026-04-22 18:33:49 -07:00 • committed by Teknium
parent d30ee2e545
commit c78a188ddd
1 changed files with 4 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

4
run_agent.py
View file

@ -913,6 +913,10 @@ class AIAgent:
)
):
self.api_mode = "codex_responses"
# Invalidate the eager-warmed transport cache — api_mode changed
# from chat_completions to codex_responses after the warm at __init__.
if hasattr(self, "_transport_cache"):
self._transport_cache.clear()
# Pre-warm OpenRouter model metadata cache in a background thread.
# fetch_model_metadata() is cached for 1 hour; this avoids a blocking