Skip to content

Commit d715f4d

Browse files
fix the inconsistencies in the docs
1 parent 6f36ebb commit d715f4d

5 files changed

Lines changed: 5 additions & 190 deletions

File tree

README.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -76,8 +76,8 @@ RepoAudit is a multi-agent framework for code auditing. We offer five agent inst
7676

7777
## Parallel Auditing Support
7878

79-
For a large repository, a sequential analysis process may be quite time-consuming. To accelerate the analysis, you can choose parallel auditing. Specifically, you can set the option `--max-neural-workers` to a larger value. By default, this option is set to 6 for parallel auditing.
80-
Also, we have set the parsing-based analysis in a parallel mode by default. The default maximal number of workers is 10.
79+
For a large repository, a sequential analysis process may be quite time-consuming. To accelerate the analysis, you can choose parallel auditing. Specifically, you can set the option `--max-neural-workers` to a larger value. By default, this option is set to 30 for parallel auditing.
80+
Also, we have set the parsing-based analysis in a parallel mode by default, which is determined by the option `--max-symbolic-workers`. The default maximal number of workers is 30.
8181

8282
## Website, Paper, and Docs
8383

docs/guide.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -59,8 +59,8 @@
5959

6060
## Parallel Auditing Support
6161

62-
For a large repository, a sequential analysis process may be quite time-consuming. To accelerate the analysis, you can choose parallel auditing. Specifically, you can set the option `--max-neural-workers` to a larger value. By default, this option is set to 6 for parallel auditing.
63-
Also, we have set the parsing-based analysis in a parallel mode by default. The default maximal number of workers is 10.
62+
For a large repository, a sequential analysis process may be quite time-consuming. To accelerate the analysis, you can choose parallel auditing. Specifically, you can set the option `--max-neural-workers` to a larger value. By default, this option is set to 30 for parallel auditing.
63+
Also, we have set the parsing-based analysis in a parallel mode by default, which is determined by the option `--max-symbolic-workers`. The default maximal number of workers is 30.
6464

6565
## User Interface
6666

src/agent/dfbscan.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -45,7 +45,7 @@ def __init__(
4545
model_name: str,
4646
temperature: float,
4747
call_depth: int,
48-
max_neural_workers: int = 1,
48+
max_neural_workers: int = 30,
4949
agent_id: int = 0,
5050
include_test_files: bool = False,
5151
) -> None:

src/llmtool/audit_request_formulator.py

Lines changed: 0 additions & 143 deletions
This file was deleted.

src/memory/report/debug_report.py

Lines changed: 0 additions & 42 deletions
This file was deleted.

0 commit comments

Comments
 (0)