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

refactor: rename teacher/student to optimizer/target, remove best skills, fix slow update

Browse Source 
- Rename teacher -> optimizer, student -> target across all code, configs, docs, prompts
- CLI: --teacher_model -> --optimizer_model, --student_model -> --target_model
- Remove best_skill files, keep only initial skills
- Fix slow update gate (force write into skill)
- Fix SLOW_UPDATE marker stripping
- Remove deep_reflect and meta_reflect mechanisms
- Update .env.example with export prefix and azure_cli docs
- Add endpoint empty validation in azure_openai.py

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
Cuzyoung
2026-05-24 19:15:03 +00:00
parent 6e165d5347
commit 4a1b984d87
70 changed files with 1083 additions and 2068 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skillopt/envs/docvqa/rollout.py
+10 -10
View File
@@ -6,8 +6,8 @@ import time
from concurrent.futures import FIRST_COMPLETED, ThreadPoolExecutor, wait
from skillopt.envs.docvqa.evaluator import evaluate
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
@@ -112,11 +112,11 @@ 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 document image, and answer the DocVQA question.\n"
"Return the final answer inside <answer>...</answer>."
)
final_message, raw = run_student_exec(
final_message, raw = run_target_exec(
work_dir=work_dir,
prompt=prompt,
model=model,
@@ -158,7 +158,7 @@ def process_one(
system_prompt = ""
user_text = ""
conversation: list[dict] = []
if is_student_exec_backend():
if is_target_exec_backend():
from skillopt.model import azure_openai as _llm
conversation = [
@@ -172,7 +172,7 @@ def process_one(
pred_dir=os.path.join(out_root, "predictions", item_id),
item=item,
skill_content=skill_content,
model=_llm.STUDENT_DEPLOYMENT,
model=_llm.TARGET_DEPLOYMENT,
timeout=exec_timeout,
image_detail=image_detail,
diagnostic_mode=diagnostic_mode if turn == 0 else False,
@@ -198,7 +198,7 @@ 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,
@@ -212,7 +212,7 @@ def process_one(
{"role": "assistant", "content": response},
{"role": "user", "content": "Review the same image carefully and answer again. Keep the final answer inside <answer>...</answer>."},
]
resp_text, _ = chat_student_messages(
resp_text, _ = chat_target_messages(
messages=refinement_messages,
max_completion_tokens=512,
retries=5,
@@ -230,9 +230,9 @@ def process_one(
pred_dir = os.path.join(out_root, "predictions", item_id)
os.makedirs(pred_dir, exist_ok=True)
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(response, item.get("answers", []))