Files
deepseek-harness/apps/web/tests/declared-reasoning.overlay.yml
Yichen Jiang 0490f8bb06 feat(llm-pi-ai): per-model reasoningEfforts and reasoning-dispatch compat switches
A model entry's reasoningEfforts dict declares its selectable thinking
levels — key = offered level, value = the wire spelling dispatch sends;
only off may leave the value empty (supported, send nothing). false
strips reasoning from a catalog model; every level is materialized
explicitly into pi-ai's thinkingLevelMap so nobody has to know pi-ai's
asymmetric absent-key defaulting. compat.thinkingFormat and
compat.supportsReasoningEffort become configurable on the route and per
model (model > route > catalog entry > pi-ai's URL-derived guess),
openai-completions only, so a private gateway speaking the DeepSeek
reasoning dialect no longer depends on its URL being recognizable.
Record-typed drift gates pin both enums to pi-ai's, and an unserviceable
declaration is refused at the write that produced it, naming route,
model, and level.
2026-08-08 00:51:54 +08:00

9 lines
341 B
YAML

# The fixture-less web scaffold registers no adapter, so the shipped
# deepseek-official default would be a route nothing serves. This scenario
# starts the default on its own declared reasoning model so the effort pane
# describes that model from the first open.
- id: api-gateway
config:
provider: acme-gateway
model: acme-think