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/livemathematicianbench/adapter.py
+2 -126
View File
@@ -4,13 +4,12 @@ from __future__ import annotations
import json
import os
from skillopt.gradient.deep_probe import generate_deep_probe_instruction
from skillopt.datasets.base import BatchSpec
from skillopt.gradient.reflect import run_minibatch_reflect
from skillopt.envs.base import EnvAdapter
from skillopt.envs.livemathematicianbench.dataloader import LiveMathematicianBenchDataLoader
from skillopt.envs.livemathematicianbench.rollout import run_batch
from skillopt.model import get_student_backend
from skillopt.model import get_target_backend
class LiveMathematicianBenchAdapter(EnvAdapter):
@@ -61,11 +60,7 @@ class LiveMathematicianBenchAdapter(EnvAdapter):
limit: int = 0,
shuffle_choices: bool = True,
use_theorem: bool = False,
use_sketch: bool = False,
use_deep_reflect: bool = False,
deep_reflect_failures: int = 4,
deep_reflect_successes: int = 2,
) -> None:
use_sketch: bool = False, ) -> None:
self.max_turns = max_turns
self.exec_timeout = exec_timeout
self.workers = workers
@@ -75,9 +70,6 @@ class LiveMathematicianBenchAdapter(EnvAdapter):
self.edit_budget = edit_budget
self.use_theorem = use_theorem
self.use_sketch = use_sketch
self.use_deep_reflect = use_deep_reflect
self.deep_reflect_failures = deep_reflect_failures
self.deep_reflect_successes = deep_reflect_successes
self.dataloader = LiveMathematicianBenchDataLoader(
split_dir=split_dir,
data_path=data_path,
@@ -161,122 +153,6 @@ class LiveMathematicianBenchAdapter(EnvAdapter):
update_mode=getattr(self, "_cfg", {}).get("skill_update_mode", "patch"),
)
def deep_reflect(
self,
results: list[dict],
skill_content: str,
out_dir: str,
**kwargs,
) -> list[dict | None]:
if not self.use_deep_reflect:
return []
env_manager = kwargs.get("env_manager")
prediction_dir = kwargs.get("prediction_dir", os.path.join(out_dir, "predictions"))
random_seed = kwargs.get("random_seed")
step_buffer_context = kwargs.get("step_buffer_context", "")
meta_skill_context = kwargs.get("meta_skill_context", "")
codex_backend = get_student_backend() == "codex_exec"
selected_items = self.select_representative_items(
results,
env_manager if isinstance(env_manager, list) else None,
n_failures=self.deep_reflect_failures,
n_successes=self.deep_reflect_successes,
seed=random_seed,
)
if not selected_items:
return []
selected_ids = {str(item["id"]) for item in selected_items}
selected_results = [row for row in results if str(row.get("id")) in selected_ids]
selected_examples = self.attach_reference_context(selected_results, selected_items)
if codex_backend:
selected_examples = self.attach_codex_probe_context(selected_examples, prediction_dir)
selected_metadata = []
theorem_count = 0
sketch_count = 0
for item in selected_items:
meta = self.get_reference_metadata(item)
if "theorem" in meta["fields"]:
theorem_count += 1
if "sketch" in meta["fields"]:
sketch_count += 1
selected_metadata.append({
"id": str(item["id"]),
"task_type": str(item.get("theorem_type", ["math_mcq"])[0] if item.get("theorem_type") else "math_mcq"),
"reference_fields": meta["fields"],
"reference_preview": meta["preview"],
})
deep_dir = os.path.join(out_dir, "deep_reflect")
rollout_dir = os.path.join(deep_dir, "rollout")
patches_dir = os.path.join(deep_dir, "patches")
os.makedirs(deep_dir, exist_ok=True)
print(
f" [2b/6 DEEP REFLECT setup] selected={len(selected_items)} "
f"reference_fields=theorem({theorem_count}/{len(selected_items)}),"
f"sketch({sketch_count}/{len(selected_items)})"
)
probe = generate_deep_probe_instruction(
skill_content=skill_content,
items=selected_examples,
prediction_dir=prediction_dir,
system_prompt=self.get_codex_deep_probe_prompt() if codex_backend else self.get_deep_probe_prompt(),
step_buffer_context=step_buffer_context,
meta_skill_context=meta_skill_context,
)
if not probe:
return []
diagnostic_trace_context_by_id = None
if codex_backend:
selected_items, diagnostic_trace_context_by_id, probe = self.resolve_codex_probe_target(
selected_items=selected_items,
selected_examples=selected_examples,
prediction_dir=prediction_dir,
probe=probe,
)
probe_record = {
**probe,
"reference_summary": {
"selected_count": len(selected_items),
"field_counts": {
"theorem": theorem_count,
"sketch": sketch_count,
},
},
"selected_examples": selected_metadata,
}
with open(os.path.join(deep_dir, "probe.json"), "w", encoding="utf-8") as f:
json.dump(probe_record, f, ensure_ascii=False, indent=2)
deep_results = run_batch(
items=selected_items,
out_root=rollout_dir,
skill_content=skill_content,
max_turns=self.max_turns,
workers=min(self.workers, max(len(selected_items), 1)),
use_theorem=self.use_theorem,
use_sketch=self.use_sketch,
diagnostic_mode=True,
diagnostic_instruction=probe["probe_instruction"],
diagnostic_trace_context_by_id=diagnostic_trace_context_by_id,
task_timeout=self.exec_timeout,
)
deep_results = self.attach_reference_context(deep_results, selected_items)
return run_minibatch_reflect(
results=deep_results,
skill_content=skill_content,
prediction_dir=os.path.join(rollout_dir, "predictions"),
patches_dir=patches_dir,
workers=self.analyst_workers,
failure_only=self.failure_only,
minibatch_size=self.minibatch_size,
edit_budget=self.edit_budget,
random_seed=random_seed,
error_system=self.get_error_minibatch_prompt(),
success_system=self.get_success_minibatch_prompt(),
step_buffer_context=step_buffer_context,
meta_skill_context=meta_skill_context,
update_mode=getattr(self, "_cfg", {}).get("skill_update_mode", "patch"),
)
def get_task_types(self) -> list[str]:
return self.dataloader.get_task_types()