mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 09:13:14 +00:00
834efbc33c
* feat: tighten reviewer eval workflow Require the reviewer to verify and dedupe findings before recording them, and make benchmark runs safe to execute against deployed reviewer graphs without posting GitHub reviews. * chore: move reviewer eval settings to config Load reviewer benchmark settings from the default eval config file so deployed eval runs do not require a wide CLI surface. * feat: allow reviewer eval model overrides Pass reviewer model and reasoning effort from the eval config into reviewer runs so isolated benchmark deployments can test Opus 4.7 high thinking. * fix: use adaptive thinking for Opus 4.7 Switch Opus 4.7 model overrides to Anthropic adaptive thinking with effort instead of the deprecated budgeted thinking payload rejected by the API. * refactor: use latest Anthropic effort API Remove legacy Anthropic budget-token thinking support and route Anthropic efforts through adaptive thinking plus effort. * revert prompting
13 lines
453 B
Python
13 lines
453 B
Python
from __future__ import annotations
|
|
|
|
from agent.server import _anthropic_effort_for, _anthropic_thinking_for
|
|
|
|
|
|
def test_anthropic_uses_adaptive_thinking_and_effort() -> None:
|
|
assert _anthropic_thinking_for("high") == {"type": "adaptive"}
|
|
assert _anthropic_effort_for("high") == "high"
|
|
|
|
|
|
def test_anthropic_ignores_unknown_effort() -> None:
|
|
assert _anthropic_thinking_for("unknown") is None
|
|
assert _anthropic_effort_for("unknown") is None
|