72a346e8ea
Review fold (round 1, simplify reuse + quality): - tokenhub_effort() in agent/reasoning_effort.py: the tencent-tokenhub profile and the host-based branch base_url-only agents take used the same "high unless chosen, else clamp" expression in two places, so the two paths could drift apart. - generic_nested_reasoning(): the OpenAI-compatible extra_body fallback auxiliary calls send when a profile declares no reasoning shape. The lmstudio profile's auxiliary branch was a line-for-line copy (it must produce it itself because overriding build_api_kwargs_extras turns the aux fallback off). Both now call the helper. - agent/lmstudio_reasoning.py docstring names its real caller (the lmstudio profile). Behaviour unchanged: 42/42 main-loop request cells and every auxiliary projection cell are byte-identical to origin/main.
41 lines
1.9 KiB
Python
41 lines
1.9 KiB
Python
"""LM Studio reasoning-effort resolution (used by the lmstudio provider profile). LM Studio
|
|
publishes per-model
|
|
``capabilities.reasoning.allowed_options`` (``["off","on"]`` for toggle models,
|
|
``["off","minimal","low"]`` for graduated ones); the user's ``reasoning_config`` is
|
|
mapped onto LM Studio's vocabulary, then clamped to the allowed set so the server
|
|
doesn't 400."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import List, Optional
|
|
|
|
_LM_VALID_EFFORTS = {"none", "minimal", "low", "medium", "high", "xhigh"}
|
|
|
|
# Toggle vocabulary → request vocabulary; also applied to published allowed_options.
|
|
_LM_EFFORT_ALIASES = {"off": "none", "on": "medium"}
|
|
|
|
# Hermes' ladder grew past LM Studio's vocabulary ("max", "ultra"); without this
|
|
# ceiling clamp they'd fall to the "medium" default (more yields less than "xhigh").
|
|
# Separate from _LM_EFFORT_ALIASES, which must not rewrite allowed_options.
|
|
_LM_EFFORT_CLAMP = {"max": "xhigh", "ultra": "xhigh"}
|
|
|
|
|
|
def resolve_lmstudio_effort(reasoning_config: Optional[dict], allowed_options: Optional[List[str]]) -> Optional[str]:
|
|
"""Return the ``reasoning_effort`` to send to LM Studio, or ``None`` = omit the
|
|
field (the user picked a level the model can't honor, so LM Studio falls back
|
|
to the model's declared default rather than a silently substituted effort).
|
|
Falsy ``allowed_options`` (probe failed) skips clamping."""
|
|
effort = "medium"
|
|
if reasoning_config and isinstance(reasoning_config, dict):
|
|
if reasoning_config.get("enabled") is False:
|
|
effort = "none"
|
|
else:
|
|
raw = (reasoning_config.get("effort") or "").strip().lower()
|
|
raw = _LM_EFFORT_ALIASES.get(raw, raw)
|
|
raw = _LM_EFFORT_CLAMP.get(raw, raw)
|
|
if raw in _LM_VALID_EFFORTS:
|
|
effort = raw
|
|
if allowed_options and effort not in {_LM_EFFORT_ALIASES.get(opt, opt) for opt in allowed_options}:
|
|
return None
|
|
return effort
|