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(compression): show main + aux model and provider in feasibility warning (#16619)

Browse Source 
The auto-lowered-threshold warning only named the compression model,
making it confusing when the main and aux models are configured with
the same slug but end up with different resolved context lengths (e.g.
OpenRouter's stepfun/step-3.5-flash catalog value vs. a main-model
context_length override). Users couldn't tell whether the warning
reflected two different models or a context-resolution mismatch.

Now includes both 'model (provider)' labels. The aux provider falls
back to the client's base_url hostname when the configured provider
is 'auto', so users see where compression is actually being called.
This commit is contained in:
Teknium
2026-04-27 08:43:24 -07:00
committed by GitHub
parent 460a8ce5d9
commit 628ca99d9b
1 changed files with 42 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
run_agent.py
View File

@@ -2423,7 +2423,10 @@ class AIAgent:
if not self.compression_enabled:
return
try:
from agent.auxiliary_client import get_text_auxiliary_client
from agent.auxiliary_client import (
_resolve_task_provider_model,
get_text_auxiliary_client,
)
from agent.model_metadata import (
MINIMUM_CONTEXT_LENGTH,
get_model_context_length,
@@ -2433,6 +2436,14 @@ class AIAgent:
"compression",
main_runtime=self._current_main_runtime(),
)
# Best-effort aux provider label for the warning message. The
# configured provider may be "auto", in which case we fall back
# to the client's base_url hostname so the user can still tell
# where the compression model is actually being called.
try:
_aux_cfg_provider, _, _, _, _ = _resolve_task_provider_model("compression")
except Exception:
_aux_cfg_provider = ""
if client is None or not aux_model:
msg = (
"⚠ No auxiliary LLM provider configured — context "
@@ -2499,10 +2510,37 @@ class AIAgent:
new_threshold / main_ctx
)
safe_pct = int((aux_context / main_ctx) * 100) if main_ctx else 50
# Build human-readable "model (provider)" labels for both
# the main model and the compression model so users can
# tell at a glance which provider each side is actually
# using. When the configured provider is empty or "auto",
# fall back to the client's base_url hostname.
_main_model = getattr(self, "model", "") or "?"
_main_provider = getattr(self, "provider", "") or ""
_aux_provider_label = (
_aux_cfg_provider
if _aux_cfg_provider and _aux_cfg_provider != "auto"
else ""
)
if not _aux_provider_label:
try:
from urllib.parse import urlparse
_aux_provider_label = (
urlparse(aux_base_url).hostname or aux_base_url
)
except Exception:
_aux_provider_label = aux_base_url or "auto"
_main_label = (
f"{_main_model} ({_main_provider})"
if _main_provider
else _main_model
)
_aux_label = f"{aux_model} ({_aux_provider_label})"
msg = (
f"⚠ Compression model ({aux_model}) context is "
f"{aux_context:,} tokens, but the main model's "
f"compression threshold was {old_threshold:,} tokens. "
f"⚠ Compression model {_aux_label} context is "
f"{aux_context:,} tokens, but the main model "
f"{_main_label}'s compression threshold was "
f"{old_threshold:,} tokens. "
f"Auto-lowered this session's threshold to "
f"{new_threshold:,} tokens so compression can run.\n"
f" To make this permanent, edit config.yaml — either:\n"