url/SkillOpt
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: rename remaining teacher/student refs, remove .gradio from repo

Browse Source 
- Fix teacher/student in deep_reflect, meta_reflect, sealqa, babyvision,
  mathverse, mmrb, swebench envs and prompt templates
- Remove .gradio/certificate.pem from tracked files
- Add .gradio/ to .gitignore

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
Cuzyoung
2026-05-24 19:22:20 +00:00
parent 7ae2d8766e
commit cff7ff6846
27 changed files with 148 additions and 178 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skillopt/envs/babyvision/rollout.py
+12 -12
View File
@@ -8,8 +8,8 @@ import os
from concurrent.futures import ThreadPoolExecutor, as_completed
from skillopt.envs.babyvision.evaluator import evaluate_item, evaluation_mode, extract_boxed_answer
from skillopt.model import chat_student_messages, get_student_backend, is_student_exec_backend
from skillopt.model.codex_harness import prepare_workspace, render_skill_md, run_student_exec
from skillopt.model import chat_target_messages, get_target_backend, is_target_exec_backend
from skillopt.model.codex_harness import prepare_workspace, render_skill_md, run_target_exec
from skillopt.prompts import load_prompt
def _build_system(skill_content: str) -> str:
@@ -137,11 +137,11 @@ def _run_codex_once(
images=[item["image_path"]],
)
prompt = (
"Use the `skillopt-student` skill available in this workspace.\n"
"Use the `skillopt-target` skill available in this workspace.\n"
"Read `task.md`, inspect the attached image, and answer the question.\n"
"Return the final answer in \\boxed{...}."
)
final_message, raw = run_student_exec(
final_message, raw = run_target_exec(
work_dir=work_dir,
prompt=prompt,
model=model,
@@ -195,7 +195,7 @@ def process_one(
pred_dir = os.path.join(out_root, "predictions", item_id)
os.makedirs(pred_dir, exist_ok=True)
if is_student_exec_backend():
if is_target_exec_backend():
from skillopt.model import azure_openai as _llm
response = ""
@@ -209,7 +209,7 @@ def process_one(
pred_dir=pred_dir,
item=item,
skill_content=skill_content,
model=_llm.STUDENT_DEPLOYMENT,
model=_llm.TARGET_DEPLOYMENT,
timeout=120,
image_detail=image_detail,
diagnostic_mode=diagnostic_mode if turn == 0 else False,
@@ -224,9 +224,9 @@ def process_one(
result["response"] = response
result["agent_ok"] = True
result["n_turns"] = len(conversation) - 1
with open(os.path.join(pred_dir, "student_system_prompt.txt"), "w", encoding="utf-8") as f:
with open(os.path.join(pred_dir, "target_system_prompt.txt"), "w", encoding="utf-8") as f:
f.write(system_prompt)
with open(os.path.join(pred_dir, "student_user_prompt.txt"), "w", encoding="utf-8") as f:
with open(os.path.join(pred_dir, "target_user_prompt.txt"), "w", encoding="utf-8") as f:
f.write(user_text)
eval_result = evaluate_item(
@@ -299,7 +299,7 @@ def process_one(
for turn in range(max_turns):
if turn == 0:
resp_text, _ = chat_student_messages(
resp_text, _ = chat_target_messages(
messages=messages,
max_completion_tokens=768,
retries=5,
@@ -317,7 +317,7 @@ def process_one(
{"role": "assistant", "content": response},
{"role": "user", "content": refinement_text},
]
resp_text, _ = chat_student_messages(
resp_text, _ = chat_target_messages(
messages=refinement_messages,
max_completion_tokens=512,
retries=5,
@@ -332,9 +332,9 @@ def process_one(
result["agent_ok"] = True
result["n_turns"] = len(conversation) - 1
with open(os.path.join(pred_dir, "student_system_prompt.txt"), "w", encoding="utf-8") as f:
with open(os.path.join(pred_dir, "target_system_prompt.txt"), "w", encoding="utf-8") as f:
f.write(system_prompt)
with open(os.path.join(pred_dir, "student_user_prompt.txt"), "w", encoding="utf-8") as f:
with open(os.path.join(pred_dir, "target_user_prompt.txt"), "w", encoding="utf-8") as f:
f.write(user_text)
eval_result = evaluate_item(