abc/analysis_claude_code
1
0
Fork 0
mirror of https://github.com/shareAI-lab/analysis_claude_code.git synced 2026-09-20 12:13:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix empty tool-use response handling

Browse Source
This commit is contained in:
Haoran
2026-08-15 00:03:45 +08:00
parent 985456f4ad
commit 168fff86dd
90 changed files with 885 additions and 503 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
s04_hooks/README.md
View File

@@ -130,7 +130,7 @@ register_hook("PreToolUse", log_hook)
register_hook("PostToolUse", large_output_hook)
```
**Stop** triggers when the loop is about to exit (`stop_reason != "tool_use"`). The following hook prints a cleanup summary:
**Stop** triggers when the loop is about to exit. The following hook prints a cleanup summary:
```python
def summary_hook(messages: list) -> str | None:
@@ -147,7 +147,10 @@ register_hook("Stop", summary_hook)
In agent_loop, triggered before exit:
```python
if response.stop_reason != "tool_use":
tool_calls = [
block for block in response.content if block.type == "tool_use"
]
if not tool_calls:
force = trigger_hooks("Stop", messages) # ← before exiting
if force:
# hook returned a message → inject it and continue
@@ -159,10 +162,7 @@ if response.stop_reason != "tool_use":
**Only one change in the loop**: s03 directly called `check_permission(block)`, s04 replaces it with `trigger_hooks("PreToolUse", block)`:
```python
for block in response.content:
if block.type != "tool_use":
continue
for block in tool_calls:
# s03: if not check_permission(block): ...
# s04: hooks replace hardcoding
blocked = trigger_hooks("PreToolUse", block)