Files
hermes-webui/tests
nesquena-hermes e20eb2c784 fix: skip budget-doubling title retry for reasoning-only responses (#2083)
Reasoning models (Qwen3-thinking via LM Studio, DeepSeek-R1, Kimi-K2,
etc.) can burn their entire output budget on hidden reasoning tokens and
emit no visible content. The previous title-generation retry path
classified that as llm_length and doubled the budget — but the second
call produces the same shape, so the retry only doubled the GPU/credit
burn. Repeated across the two prompts in _title_prompts() this came to
~3000 reasoning tokens of GPU work per new chat. On local LM Studio
servers behind a custom: provider (where is_lmstudio=False means
reasoning_effort: none never reaches the model) it manifested as the GPU
never going idle after a prompt.

Fix:
  - _extract_title_response: classify reasoning-bearing empty responses
    as llm_empty_reasoning regardless of finish_reason. The presence of
    reasoning_content is the diagnostic signal, not finish_reason.
  - _title_retry_status: drop llm_empty_reasoning from the retry set.
    Length-truncated responses WITHOUT reasoning still retry (those are
    legitimately recoverable by a larger budget).
  - Add _title_should_skip_remaining_attempts() and break out of the
    prompt-iteration loop on empty-reasoning. A second prompt against
    the same model would produce the same shape.
  - Falls through to _fallback_title_from_exchange for a local-summary
    title.

Tests updated to invert the previous reasoning-retry assertions:
  - test_aux_short_circuits_on_empty_reasoning_without_retrying
  - test_aux_still_retries_finish_length_without_reasoning
  - test_agent_route_short_circuits_on_empty_reasoning_without_retrying
  - test_agent_route_still_retries_finish_length_without_reasoning

Companion agent-side work (LM Studio classifier for custom: providers)
is tracked separately on the hermes-agent side; this WebUI fix is the
belt-and-braces guard so the loop stops regardless of agent classifier
state.

Reported by @darkopetrovic. Closes #2083.

Co-authored-by: darkopetrovic <darkopetrovic@users.noreply.github.com>
(cherry picked from commit efeae4a86e)
2026-05-12 00:04:11 +00:00
..
2026-04-29 19:54:07 -07:00
2026-05-05 01:51:05 +00:00
2026-04-29 17:42:32 -07:00
2026-04-29 17:42:32 -07:00
2026-04-29 21:34:27 -07:00
2026-04-29 21:06:30 -07:00
2026-04-29 17:42:32 -07:00