ling/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-28 06:51:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(agent): update context compressor limits after fallback activation (#3305)

Browse Source 
When _try_activate_fallback() switches to the fallback model, it
updates the agent's model/provider/client but never touches
self.context_compressor. The compressor keeps the primary model's
context_length and threshold_tokens, so compression decisions use
wrong limits — a 200K primary → 32K fallback still uses 200K-based
thresholds, causing oversized sessions to overflow the fallback.

Update the compressor's model, credentials, context_length, and
threshold_tokens after fallback activation using get_model_context_length()
for the new model.

Cherry-picked from PR #3202 by binhnt92.

Co-authored-by: binhnt92 <binhnt.ht.92@gmail.com>
This commit is contained in:
Teknium
2026-03-26 18:10:50 -07:00
committed by GitHub
parent 18d28c63a7
commit 60fdb58ce4
2 changed files with 108 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
run_agent.py
View File

@@ -4134,6 +4134,25 @@ class AIAgent:
or is_native_anthropic
)
# Update context compressor limits for the fallback model.
# Without this, compression decisions use the primary model's
# context window (e.g. 200K) instead of the fallback's (e.g. 32K),
# causing oversized sessions to overflow the fallback.
if hasattr(self, 'context_compressor') and self.context_compressor:
from agent.model_metadata import get_model_context_length
fb_context_length = get_model_context_length(
self.model, base_url=self.base_url,
api_key=self.api_key, provider=self.provider,
)
self.context_compressor.model = self.model
self.context_compressor.base_url = self.base_url
self.context_compressor.api_key = self.api_key
self.context_compressor.provider = self.provider
self.context_compressor.context_length = fb_context_length
self.context_compressor.threshold_tokens = int(
fb_context_length * self.context_compressor.threshold_percent
)
self._emit_status(
f"🔄 Primary model failed — switching to fallback: "
f"{fb_model} via {fb_provider}"