Skip to content

fix: Plan 缓存键增加 task 描述校验 (Issue #5) #22

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
urika merged 1 commit into from
May 29, 2026
Merged

fix: Plan 缓存键增加 task 描述校验 (Issue #5) #22

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 8 additions & 2 deletions agent_go/api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,7 +98,7 @@ def generate_plan(task, repo, config, logger, supplement="", reference_docs="",
cache_hit = False
if not no_cache and iteration == 1 and not supplement and not reference_docs:
cache_key = get_cache_key(task, repo)
cached = load_cached_plan(cache_key, config, logger)
cached = load_cached_plan(cache_key, task, config, logger)
if cached:
plan = cached
cache_hit = True
Expand Down Expand Up @@ -298,7 +298,7 @@ def get_cache_key(task, repo):
return hashlib.sha256("|".join(key_parts).encode()).hexdigest()


def load_cached_plan(cache_key, config, logger):
def load_cached_plan(cache_key, task, config, logger):
cache_dir = _cache_dir()
cache_file = cache_dir / cache_key[:2] / f"{cache_key}.json"
if not cache_file.exists():
Expand All @@ -325,6 +325,12 @@ def load_cached_plan(cache_key, config, logger):
if not plan or not plan.get("steps"):
return None

# 校验 task 描述是否匹配，避免缓存键碰撞导致的不匹配
cached_task = entry.get("meta", {}).get("task", "")
if cached_task and cached_task != task[:200]:
logger.warning(f"[缓存] task 不匹配 (缓存: {cached_task[:50]}..., 当前: {task[:50]}...)，跳过缓存")
return None

meta = entry["meta"]
meta["last_hit_at"] = datetime.now().strftime("%Y-%m-%dT%H:%M:%S")
meta["hit_count"] = meta.get("hit_count", 0) + 1
Expand Down