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/config.py
+3
View File
@@ -125,6 +125,9 @@ _FLATTEN_MAP: dict[str, str] = {
"evaluation.use_gate": "use_gate",
"evaluation.gate_metric": "gate_metric",
"evaluation.gate_mixed_weight": "gate_mixed_weight",
"evaluation.use_semantic_density": "use_semantic_density",
"evaluation.semantic_density_weight": "semantic_density_weight",
"evaluation.leading_words": "leading_words",
"evaluation.sel_env_num": "sel_env_num",
"evaluation.test_env_num": "test_env_num",
"evaluation.eval_test": "eval_test",
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} "
skillopt/evaluation/gate.py
+86 -9
View File
@@ -43,11 +43,55 @@ class GateResult:
best_step: int
def compute_semantic_density(
skill_content: str,
leading_words: list[str] | None = None,
) -> float:
"""Compute the semantic density of leading words in a skill document."""
if not skill_content or not skill_content.strip():
return 0.0
if leading_words is None:
leading_words = [
"MUST", "ALWAYS", "NEVER", "ONLY", "CRITICAL", "IMPORTANT",
"RESOLVE", "PREFER", "ENSURE", "STRICT", "VERIFY"
]
# Strip metadata comments to focus purely on instruction text
skill = skill_content
for start, end in [
("<!-- SLOW_UPDATE_START -->", "<!-- SLOW_UPDATE_END -->"),
("<!-- APPENDIX_START -->", "<!-- APPENDIX_END -->")
]:
while True:
s_idx = skill.find(start)
if s_idx == -1:
break
e_idx = skill.find(end, s_idx)
if e_idx == -1:
skill = skill[:s_idx] + skill[s_idx + len(start):]
break
skill = skill[:s_idx] + skill[e_idx + len(end):]
import re
words = re.findall(r'[a-zA-Z0-9]+', skill.lower())
if not words:
return 0.0
leading_set = {w.lower() for w in leading_words}
leading_count = sum(1 for w in words if w in leading_set)
return leading_count / len(words)
def select_gate_score(
hard: float,
soft: float,
metric: GateMetric = "hard",
mixed_weight: float = 0.5,
*,
skill_content: str = "",
use_semantic_density: bool = False,
semantic_density_weight: float = 0.05,
leading_words: list[str] | None = None,
) -> float:
"""Project (hard, soft) onto a single comparison metric.
@@ -60,17 +104,32 @@ def select_gate_score(
mixed_weight
For ``"mixed"``: weight given to ``soft``. Must be in ``[0, 1]``.
Ignored for ``"hard"`` / ``"soft"``.
skill_content
The raw skill document content.
use_semantic_density
Whether to adjust the score based on semantic density of leading words.
semantic_density_weight
Scaling weight for the semantic density bonus.
leading_words
Optional custom list of high-influence words to prioritize.
"""
if metric == "hard":
return float(hard)
if metric == "soft":
return float(soft)
if metric == "mixed":
score = float(hard)
elif metric == "soft":
score = float(soft)
elif metric == "mixed":
w = max(0.0, min(1.0, float(mixed_weight)))
return (1.0 - w) * float(hard) + w * float(soft)
raise ValueError(
f"unknown gate metric {metric!r}; expected 'hard', 'soft', or 'mixed'"
)
score = (1.0 - w) * float(hard) + w * float(soft)
else:
raise ValueError(
f"unknown gate metric {metric!r}; expected 'hard', 'soft', or 'mixed'"
)
if use_semantic_density:
density = compute_semantic_density(skill_content, leading_words)
score += float(semantic_density_weight) * density
return score
def evaluate_gate(
@@ -86,6 +145,9 @@ def evaluate_gate(
cand_soft: float = 0.0,
metric: GateMetric = "hard",
mixed_weight: float = 0.5,
use_semantic_density: bool = False,
semantic_density_weight: float = 0.05,
leading_words: list[str] | None = None,
) -> GateResult:
"""Pure gate decision: compare candidate score to current/best.
@@ -111,6 +173,12 @@ def evaluate_gate(
the original gate behavior.
mixed_weight
Weight on ``soft`` when ``metric == "mixed"``.
use_semantic_density
Whether to adjust the score based on semantic density of leading words.
semantic_density_weight
Scaling weight for the semantic density bonus.
leading_words
Optional custom list of high-influence words to prioritize.
Returns
-------
@@ -118,7 +186,16 @@ def evaluate_gate(
Updated state; the caller decides what to do with it (print,
mutate trainer state, log, etc.).
"""
cand_score = select_gate_score(cand_hard, cand_soft, metric, mixed_weight)
cand_score = select_gate_score(
cand_hard,
cand_soft,
metric,
mixed_weight,
skill_content=candidate_skill,
use_semantic_density=use_semantic_density,
semantic_density_weight=semantic_density_weight,
leading_words=leading_words,
)
if cand_score > current_score:
if cand_score > best_score: