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

fix(gate): resolve issue #100 (#102)

Browse Source
This commit is contained in:
Sparsh :)
2026-07-12 21:57:13 +05:30
committed by GitHub
parent da99301210
commit 49a5b617c0
5 changed files with 263 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skillopt/engine/trainer.py
+47 -20
View File
@@ -709,26 +709,26 @@ class ReflACTTrainer:
effort=cfg.get("claude_code_exec_effort", cfg.get("reasoning_effort", "medium")),
max_thinking_tokens=cfg.get("claude_code_exec_max_thinking_tokens", 16384),
)
configure_qwen_chat(
base_url=cfg.get("qwen_chat_base_url") or None,
api_key=cfg.get("qwen_chat_api_key") or None,
temperature=cfg.get("qwen_chat_temperature"),
timeout_seconds=cfg.get("qwen_chat_timeout_seconds"),
max_tokens=cfg.get("qwen_chat_max_tokens"),
enable_thinking=cfg.get("qwen_chat_enable_thinking"),
optimizer_base_url=cfg.get("optimizer_qwen_chat_base_url") or None,
optimizer_api_key=cfg.get("optimizer_qwen_chat_api_key") or None,
optimizer_temperature=cfg.get("optimizer_qwen_chat_temperature"),
optimizer_timeout_seconds=cfg.get("optimizer_qwen_chat_timeout_seconds"),
optimizer_max_tokens=cfg.get("optimizer_qwen_chat_max_tokens"),
optimizer_enable_thinking=cfg.get("optimizer_qwen_chat_enable_thinking"),
target_base_url=cfg.get("target_qwen_chat_base_url") or None,
target_api_key=cfg.get("target_qwen_chat_api_key") or None,
target_temperature=cfg.get("target_qwen_chat_temperature"),
target_timeout_seconds=cfg.get("target_qwen_chat_timeout_seconds"),
target_max_tokens=cfg.get("target_qwen_chat_max_tokens"),
target_enable_thinking=cfg.get("target_qwen_chat_enable_thinking"),
)
configure_qwen_chat(
base_url=cfg.get("qwen_chat_base_url") or None,
api_key=cfg.get("qwen_chat_api_key") or None,
temperature=cfg.get("qwen_chat_temperature"),
timeout_seconds=cfg.get("qwen_chat_timeout_seconds"),
max_tokens=cfg.get("qwen_chat_max_tokens"),
enable_thinking=cfg.get("qwen_chat_enable_thinking"),
optimizer_base_url=cfg.get("optimizer_qwen_chat_base_url") or None,
optimizer_api_key=cfg.get("optimizer_qwen_chat_api_key") or None,
optimizer_temperature=cfg.get("optimizer_qwen_chat_temperature"),
optimizer_timeout_seconds=cfg.get("optimizer_qwen_chat_timeout_seconds"),
optimizer_max_tokens=cfg.get("optimizer_qwen_chat_max_tokens"),
optimizer_enable_thinking=cfg.get("optimizer_qwen_chat_enable_thinking"),
target_base_url=cfg.get("target_qwen_chat_base_url") or None,
target_api_key=cfg.get("target_qwen_chat_api_key") or None,
target_temperature=cfg.get("target_qwen_chat_temperature"),
target_timeout_seconds=cfg.get("target_qwen_chat_timeout_seconds"),
target_max_tokens=cfg.get("target_qwen_chat_max_tokens"),
target_enable_thinking=cfg.get("target_qwen_chat_enable_thinking"),
)
configure_minimax_chat(
base_url=cfg.get("minimax_base_url") or None,
api_key=cfg.get("minimax_api_key") or None,
@@ -964,6 +964,15 @@ class ReflACTTrainer:
f"got {gate_metric!r}"
)
gate_mixed_weight = float(cfg.get("gate_mixed_weight", 0.5))
use_semantic_density = bool(cfg.get("use_semantic_density", False))
semantic_density_weight = float(cfg.get("semantic_density_weight", 0.05))
leading_words_raw = cfg.get("leading_words", None)
leading_words = None
if leading_words_raw is not None:
if isinstance(leading_words_raw, str):
leading_words = [w.strip() for w in leading_words_raw.split(",") if w.strip()]
else:
leading_words = list(leading_words_raw)
if not 0.0 <= gate_mixed_weight <= 1.0:
raise ValueError(
f"evaluation.gate_mixed_weight must be in [0, 1], "
@@ -1003,6 +1012,10 @@ class ReflACTTrainer:
baseline_hard, baseline_soft = compute_score(baseline_results)
current_score = select_gate_score(
baseline_hard, baseline_soft, gate_metric, gate_mixed_weight,
skill_content=skill_init,
use_semantic_density=use_semantic_density,
semantic_density_weight=semantic_density_weight,
leading_words=leading_words,
)
best_score = current_score
sh = skill_hash(skill_init)
@@ -1450,9 +1463,16 @@ class ReflACTTrainer:
cand_soft=cand_soft,
metric=gate_metric,
mixed_weight=gate_mixed_weight,
use_semantic_density=use_semantic_density,
semantic_density_weight=semantic_density_weight,
leading_words=leading_words,
) if use_gate else None
cand_gate_score = select_gate_score(
cand_hard, cand_soft, gate_metric, gate_mixed_weight,
skill_content=candidate_skill,
use_semantic_density=use_semantic_density,
semantic_density_weight=semantic_density_weight,
leading_words=leading_words,
)
if not use_gate:
# Validation ran (scores recorded above) but the gate is
@@ -1844,6 +1864,9 @@ class ReflACTTrainer:
cand_soft=slow_sel_soft,
metric=gate_metric,
mixed_weight=gate_mixed_weight,
use_semantic_density=use_semantic_density,
semantic_density_weight=semantic_density_weight,
leading_words=leading_words,
)
slow_result["selection_hard"] = slow_sel_hard
slow_result["selection_soft"] = slow_sel_soft
@@ -2093,6 +2116,10 @@ class ReflACTTrainer:
final_gate_score = select_gate_score(
final_selection_hard, final_selection_soft,
gate_metric, gate_mixed_weight,
skill_content=current_skill,
use_semantic_density=use_semantic_density,
semantic_density_weight=semantic_density_weight,
leading_words=leading_words,
)
print(
f"\n [final skill val] items={fval_n} "