daveloop 1.0.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,3 @@
1
+ include daveloop_prompt.md
2
+ include README.md
3
+ include LICENSE
@@ -0,0 +1,78 @@
1
+ Metadata-Version: 2.4
2
+ Name: daveloop
3
+ Version: 1.0.0
4
+ Summary: Self-healing debug agent powered by Claude Code CLI
5
+ Home-page: https://github.com/davebruzil/DaveLoop
6
+ Author: Dave Bruzil
7
+ Keywords: debugging ai claude automation agent
8
+ Classifier: Development Status :: 4 - Beta
9
+ Classifier: Intended Audience :: Developers
10
+ Classifier: License :: OSI Approved :: MIT License
11
+ Classifier: Programming Language :: Python :: 3
12
+ Classifier: Programming Language :: Python :: 3.7
13
+ Classifier: Programming Language :: Python :: 3.8
14
+ Classifier: Programming Language :: Python :: 3.9
15
+ Classifier: Programming Language :: Python :: 3.10
16
+ Classifier: Programming Language :: Python :: 3.11
17
+ Classifier: Programming Language :: Python :: 3.12
18
+ Classifier: Topic :: Software Development :: Debuggers
19
+ Classifier: Topic :: Software Development :: Quality Assurance
20
+ Requires-Python: >=3.7
21
+ Description-Content-Type: text/markdown
22
+ Dynamic: author
23
+ Dynamic: classifier
24
+ Dynamic: description
25
+ Dynamic: description-content-type
26
+ Dynamic: home-page
27
+ Dynamic: keywords
28
+ Dynamic: requires-python
29
+ Dynamic: summary
30
+
31
+ # DaveLoop: Autonomous Debugging Agent
32
+
33
+ DaveLoop is a Claude CLI-based debugging tool that iteratively solves complex bugs through multiple attempts. Rather than relying on single-shot fixes, it uses persistent context via the `--continue` flag to build solutions incrementally.
34
+
35
+ ## Installation
36
+
37
+ ### From Source (Current Method)
38
+
39
+ ```bash
40
+ git clone https://github.com/davebruzil/DaveLoop.git
41
+ cd DaveLoop
42
+ pip install -e .
43
+ ```
44
+
45
+ ### Via pip (Coming Soon)
46
+
47
+ Once published to PyPI, you'll be able to install with:
48
+
49
+ ```bash
50
+ pip install daveloop
51
+ ```
52
+
53
+ ## Core Functionality
54
+
55
+ The tool operates through a systematic loop: users provide bug descriptions, Claude analyzes and attempts fixes, and if unsuccessful, the process repeats with accumulated context. The agent signals completion with `[DAVELOOP:RESOLVED]` or exits when blocked.
56
+
57
+ ## Key Capabilities
58
+
59
+ **4-Level Reasoning Protocol**: The system structures debugging through KNOWN facts, UNKNOWN gaps, HYPOTHESIS formulation, and concrete NEXT ACTIONs. This prevents random modifications and enforces methodical problem-solving.
60
+
61
+ **Persistent Memory**: Unlike isolated attempts, each iteration builds on previous findings through Claude's context continuation feature.
62
+
63
+ **Autonomous Operation**: The agent works without requiring manual permission prompts between iterations, enabling hands-free debugging sessions.
64
+
65
+ **Exit Signals**: Clear indicators show whether bugs are resolved, the agent is blocked, or iteration limits have been reached.
66
+
67
+ ## Usage
68
+
69
+ Basic invocation requires a bug description:
70
+ ```bash
71
+ python daveloop.py "your bug description here"
72
+ ```
73
+
74
+ The tool accepts detailed bug reports via files, custom working directories, and configurable iteration limits. Sessions automatically generate timestamped logs documenting the agent's reasoning and actions across all iterations.
75
+
76
+ ## Tested Domains
77
+
78
+ The agent has demonstrated effectiveness on security vulnerabilities, race conditions, multi-file refactors, and real-world benchmark problems from Django, Pytest, and SymPy codebases.
@@ -0,0 +1,48 @@
1
+ # DaveLoop: Autonomous Debugging Agent
2
+
3
+ DaveLoop is a Claude CLI-based debugging tool that iteratively solves complex bugs through multiple attempts. Rather than relying on single-shot fixes, it uses persistent context via the `--continue` flag to build solutions incrementally.
4
+
5
+ ## Installation
6
+
7
+ ### From Source (Current Method)
8
+
9
+ ```bash
10
+ git clone https://github.com/davebruzil/DaveLoop.git
11
+ cd DaveLoop
12
+ pip install -e .
13
+ ```
14
+
15
+ ### Via pip (Coming Soon)
16
+
17
+ Once published to PyPI, you'll be able to install with:
18
+
19
+ ```bash
20
+ pip install daveloop
21
+ ```
22
+
23
+ ## Core Functionality
24
+
25
+ The tool operates through a systematic loop: users provide bug descriptions, Claude analyzes and attempts fixes, and if unsuccessful, the process repeats with accumulated context. The agent signals completion with `[DAVELOOP:RESOLVED]` or exits when blocked.
26
+
27
+ ## Key Capabilities
28
+
29
+ **4-Level Reasoning Protocol**: The system structures debugging through KNOWN facts, UNKNOWN gaps, HYPOTHESIS formulation, and concrete NEXT ACTIONs. This prevents random modifications and enforces methodical problem-solving.
30
+
31
+ **Persistent Memory**: Unlike isolated attempts, each iteration builds on previous findings through Claude's context continuation feature.
32
+
33
+ **Autonomous Operation**: The agent works without requiring manual permission prompts between iterations, enabling hands-free debugging sessions.
34
+
35
+ **Exit Signals**: Clear indicators show whether bugs are resolved, the agent is blocked, or iteration limits have been reached.
36
+
37
+ ## Usage
38
+
39
+ Basic invocation requires a bug description:
40
+ ```bash
41
+ python daveloop.py "your bug description here"
42
+ ```
43
+
44
+ The tool accepts detailed bug reports via files, custom working directories, and configurable iteration limits. Sessions automatically generate timestamped logs documenting the agent's reasoning and actions across all iterations.
45
+
46
+ ## Tested Domains
47
+
48
+ The agent has demonstrated effectiveness on security vulnerabilities, race conditions, multi-file refactors, and real-world benchmark problems from Django, Pytest, and SymPy codebases.
@@ -0,0 +1,78 @@
1
+ Metadata-Version: 2.4
2
+ Name: daveloop
3
+ Version: 1.0.0
4
+ Summary: Self-healing debug agent powered by Claude Code CLI
5
+ Home-page: https://github.com/davebruzil/DaveLoop
6
+ Author: Dave Bruzil
7
+ Keywords: debugging ai claude automation agent
8
+ Classifier: Development Status :: 4 - Beta
9
+ Classifier: Intended Audience :: Developers
10
+ Classifier: License :: OSI Approved :: MIT License
11
+ Classifier: Programming Language :: Python :: 3
12
+ Classifier: Programming Language :: Python :: 3.7
13
+ Classifier: Programming Language :: Python :: 3.8
14
+ Classifier: Programming Language :: Python :: 3.9
15
+ Classifier: Programming Language :: Python :: 3.10
16
+ Classifier: Programming Language :: Python :: 3.11
17
+ Classifier: Programming Language :: Python :: 3.12
18
+ Classifier: Topic :: Software Development :: Debuggers
19
+ Classifier: Topic :: Software Development :: Quality Assurance
20
+ Requires-Python: >=3.7
21
+ Description-Content-Type: text/markdown
22
+ Dynamic: author
23
+ Dynamic: classifier
24
+ Dynamic: description
25
+ Dynamic: description-content-type
26
+ Dynamic: home-page
27
+ Dynamic: keywords
28
+ Dynamic: requires-python
29
+ Dynamic: summary
30
+
31
+ # DaveLoop: Autonomous Debugging Agent
32
+
33
+ DaveLoop is a Claude CLI-based debugging tool that iteratively solves complex bugs through multiple attempts. Rather than relying on single-shot fixes, it uses persistent context via the `--continue` flag to build solutions incrementally.
34
+
35
+ ## Installation
36
+
37
+ ### From Source (Current Method)
38
+
39
+ ```bash
40
+ git clone https://github.com/davebruzil/DaveLoop.git
41
+ cd DaveLoop
42
+ pip install -e .
43
+ ```
44
+
45
+ ### Via pip (Coming Soon)
46
+
47
+ Once published to PyPI, you'll be able to install with:
48
+
49
+ ```bash
50
+ pip install daveloop
51
+ ```
52
+
53
+ ## Core Functionality
54
+
55
+ The tool operates through a systematic loop: users provide bug descriptions, Claude analyzes and attempts fixes, and if unsuccessful, the process repeats with accumulated context. The agent signals completion with `[DAVELOOP:RESOLVED]` or exits when blocked.
56
+
57
+ ## Key Capabilities
58
+
59
+ **4-Level Reasoning Protocol**: The system structures debugging through KNOWN facts, UNKNOWN gaps, HYPOTHESIS formulation, and concrete NEXT ACTIONs. This prevents random modifications and enforces methodical problem-solving.
60
+
61
+ **Persistent Memory**: Unlike isolated attempts, each iteration builds on previous findings through Claude's context continuation feature.
62
+
63
+ **Autonomous Operation**: The agent works without requiring manual permission prompts between iterations, enabling hands-free debugging sessions.
64
+
65
+ **Exit Signals**: Clear indicators show whether bugs are resolved, the agent is blocked, or iteration limits have been reached.
66
+
67
+ ## Usage
68
+
69
+ Basic invocation requires a bug description:
70
+ ```bash
71
+ python daveloop.py "your bug description here"
72
+ ```
73
+
74
+ The tool accepts detailed bug reports via files, custom working directories, and configurable iteration limits. Sessions automatically generate timestamped logs documenting the agent's reasoning and actions across all iterations.
75
+
76
+ ## Tested Domains
77
+
78
+ The agent has demonstrated effectiveness on security vulnerabilities, race conditions, multi-file refactors, and real-world benchmark problems from Django, Pytest, and SymPy codebases.
@@ -0,0 +1,11 @@
1
+ MANIFEST.in
2
+ README.md
3
+ daveloop.py
4
+ daveloop_prompt.md
5
+ daveloop_swebench.py
6
+ setup.py
7
+ daveloop.egg-info/PKG-INFO
8
+ daveloop.egg-info/SOURCES.txt
9
+ daveloop.egg-info/dependency_links.txt
10
+ daveloop.egg-info/entry_points.txt
11
+ daveloop.egg-info/top_level.txt
@@ -0,0 +1,3 @@
1
+ [console_scripts]
2
+ daveloop = daveloop:main
3
+ daveloop-swebench = daveloop_swebench:main
@@ -0,0 +1,2 @@
1
+ daveloop
2
+ daveloop_swebench