KrustyPlanet/hermes-agent
6
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

fix(auxiliary): treat aux <task>.model: auto as sentinel, not a literal model id

Browse source 
When auxiliary.<task>.model is set to "auto" in config.yaml,
_resolve_task_provider_model() was treating it as a truthy model id
and propagating the literal string "auto" to the wire. The provider
then returned a 200 OK with an error-text body (e.g. "the model auto
does not exist, run --model to pick a different model"), which
downstream consumers such as ContextCompressor accept as the
compressed summary -- silent corruption with no exception raised.

The provider-side auto-resolution path (_resolve_auto via main_runtime
fallback) is already wired up and does the right thing when cfg_model
is None. The fix is to normalize the auto sentinel at the resolver
layer: when cfg_model.lower() == "auto", drop it to None so the
resolver can fall through to main_runtime / auto-detect.

Reproduction (pre-fix):
  >>> from agent.auxiliary_client import _resolve_task_provider_model
  >>> _resolve_task_provider_model("compression")  # with model: auto in config
  ("auto", "auto", None, None, None)

Post-fix:
  >>> _resolve_task_provider_model("compression")
  ("auto", None, None, None, None)

Verified end-to-end: ContextCompressor.compress now produces a real
summary (~4KB of compaction text) instead of swallowing the bridge
error string. Aux compression on auto/auto config no longer silently
corrupts the conversation summary.
This commit is contained in:
Alex Gierczyk 2026-05-12 05:58:43 -07:00 • committed by Teknium
parent d5d7cab2b6
commit 2296fec210
1 changed files with 10 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

10
agent/auxiliary_client.py
View file

@ -5257,6 +5257,16 @@ def _resolve_task_provider_model(
cfg_api_key = str(task_config.get("api_key", "")).strip() or None
cfg_api_mode = str(task_config.get("api_mode", "")).strip() or None
# 'auto' is a sentinel meaning "inherit from main runtime / auto-detect", not
# a literal model id. Without this, a config of `auxiliary.<task>.model: auto`
# propagates the literal string "auto" to the wire, where the provider returns
# a 200 OK with an error-text body (e.g. "the model 'auto' does not exist"),
# which downstream consumers like ContextCompressor accept as the task output.
# The provider-side 'auto' is handled in _resolve_auto() via main_runtime
# fallback, so dropping cfg_model to None here lets that path do its job.
if cfg_model and cfg_model.lower() == "auto":
cfg_model = None
resolved_model = model or cfg_model
resolved_api_mode = cfg_api_mode