Compare commits
8 Commits
fix/19-mig
...
feat/176-d
| Author | SHA1 | Date | |
|---|---|---|---|
| d664119b9c | |||
| 764414d4d5 | |||
| 8d716ff03f | |||
| 920510996e | |||
| 1fafeaf5a4 | |||
| 36b440f998 | |||
| 9f3caabf42 | |||
| a21f3a44e1 |
216
scripts/diff_analyzer.py
Normal file
216
scripts/diff_analyzer.py
Normal file
@@ -0,0 +1,216 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Diff Analyzer — Parse unified diffs and categorize every change.
|
||||
|
||||
Pipeline 6.1 for Compounding Intelligence.
|
||||
"""
|
||||
|
||||
import re
|
||||
from dataclasses import dataclass, field, asdict
|
||||
from enum import Enum
|
||||
from typing import List, Dict, Any, Optional
|
||||
|
||||
|
||||
class ChangeCategory(Enum):
|
||||
ADDED = "added"
|
||||
DELETED = "deleted"
|
||||
MODIFIED = "modified"
|
||||
MOVED = "moved"
|
||||
CONTEXT = "context"
|
||||
|
||||
|
||||
@dataclass
|
||||
class Hunk:
|
||||
"""A single diff hunk with header, line ranges, and category."""
|
||||
header: str
|
||||
old_start: int
|
||||
old_count: int
|
||||
new_start: int
|
||||
new_count: int
|
||||
lines: List[str] = field(default_factory=list)
|
||||
category: ChangeCategory = ChangeCategory.CONTEXT
|
||||
|
||||
def to_dict(self) -> Dict[str, Any]:
|
||||
d = asdict(self)
|
||||
d["category"] = self.category.value
|
||||
return d
|
||||
|
||||
|
||||
@dataclass
|
||||
class FileChange:
|
||||
"""A single file's changes."""
|
||||
path: str
|
||||
old_path: Optional[str] = None # For renames
|
||||
hunks: List[Hunk] = field(default_factory=list)
|
||||
added_lines: int = 0
|
||||
deleted_lines: int = 0
|
||||
is_new: bool = False
|
||||
is_deleted: bool = False
|
||||
is_renamed: bool = False
|
||||
is_binary: bool = False
|
||||
|
||||
def to_dict(self) -> Dict[str, Any]:
|
||||
return {
|
||||
"path": self.path,
|
||||
"old_path": self.old_path,
|
||||
"hunks": [h.to_dict() for h in self.hunks],
|
||||
"added_lines": self.added_lines,
|
||||
"deleted_lines": self.deleted_lines,
|
||||
"is_new": self.is_new,
|
||||
"is_deleted": self.is_deleted,
|
||||
"is_renamed": self.is_renamed,
|
||||
"is_binary": self.is_binary,
|
||||
}
|
||||
|
||||
|
||||
@dataclass
|
||||
class ChangeSummary:
|
||||
"""Aggregate stats + per-file breakdown."""
|
||||
files: List[FileChange] = field(default_factory=list)
|
||||
total_added: int = 0
|
||||
total_deleted: int = 0
|
||||
total_files_changed: int = 0
|
||||
total_hunks: int = 0
|
||||
new_files: int = 0
|
||||
deleted_files: int = 0
|
||||
renamed_files: int = 0
|
||||
binary_files: int = 0
|
||||
|
||||
def to_dict(self) -> Dict[str, Any]:
|
||||
return {
|
||||
"total_files_changed": self.total_files_changed,
|
||||
"total_added": self.total_added,
|
||||
"total_deleted": self.total_deleted,
|
||||
"total_hunks": self.total_hunks,
|
||||
"new_files": self.new_files,
|
||||
"deleted_files": self.deleted_files,
|
||||
"renamed_files": self.renamed_files,
|
||||
"binary_files": self.binary_files,
|
||||
"files": [f.to_dict() for f in self.files],
|
||||
}
|
||||
|
||||
|
||||
class DiffAnalyzer:
|
||||
"""Parses unified diff format and produces structured ChangeSummary."""
|
||||
|
||||
HUNK_HEADER_RE = re.compile(r"^@@\s+-(\d+)(?:,(\d+))?\s+\+(\d+)(?:,(\d+))?\s+@@(.*)$")
|
||||
DIFF_FILE_RE = re.compile(r"^diff --git a/(.*) b/(.*)")
|
||||
RENAME_RE = re.compile(r"^rename from (.+)$")
|
||||
RENAME_TO_RE = re.compile(r"^rename to (.+)$")
|
||||
NEW_FILE_RE = re.compile(r"^new file mode")
|
||||
DELETED_FILE_RE = re.compile(r"^deleted file mode")
|
||||
BINARY_RE = re.compile(r"^Binary files .* differ")
|
||||
|
||||
def analyze(self, diff_text: str) -> ChangeSummary:
|
||||
"""Parse a unified diff and return a ChangeSummary."""
|
||||
summary = ChangeSummary()
|
||||
if not diff_text or not diff_text.strip():
|
||||
return summary
|
||||
|
||||
# Split diff into per-file sections
|
||||
file_diffs = self._split_files(diff_text)
|
||||
|
||||
for file_diff in file_diffs:
|
||||
fc = self._parse_file_diff(file_diff)
|
||||
summary.files.append(fc)
|
||||
summary.total_added += fc.added_lines
|
||||
summary.total_deleted += fc.deleted_lines
|
||||
summary.total_hunks += len(fc.hunks)
|
||||
if fc.is_new:
|
||||
summary.new_files += 1
|
||||
if fc.is_deleted:
|
||||
summary.deleted_files += 1
|
||||
if fc.is_renamed:
|
||||
summary.renamed_files += 1
|
||||
if fc.is_binary:
|
||||
summary.binary_files += 1
|
||||
|
||||
summary.total_files_changed = len(summary.files)
|
||||
return summary
|
||||
|
||||
def _split_files(self, diff_text: str) -> List[str]:
|
||||
"""Split a multi-file diff into individual file diffs."""
|
||||
lines = diff_text.split("\n")
|
||||
chunks = []
|
||||
current = []
|
||||
for line in lines:
|
||||
if line.startswith("diff --git ") and current:
|
||||
chunks.append("\n".join(current))
|
||||
current = [line]
|
||||
else:
|
||||
current.append(line)
|
||||
if current:
|
||||
chunks.append("\n".join(current))
|
||||
return chunks
|
||||
|
||||
def _parse_file_diff(self, diff_text: str) -> FileChange:
|
||||
"""Parse a single file's diff section."""
|
||||
lines = diff_text.split("\n")
|
||||
fc = FileChange(path="")
|
||||
|
||||
# Extract file paths
|
||||
for line in lines:
|
||||
m = self.DIFF_FILE_RE.match(line)
|
||||
if m:
|
||||
fc.path = m.group(2)
|
||||
break
|
||||
|
||||
# Check for special states
|
||||
for line in lines:
|
||||
if self.NEW_FILE_RE.match(line):
|
||||
fc.is_new = True
|
||||
elif self.DELETED_FILE_RE.match(line):
|
||||
fc.is_deleted = True
|
||||
elif self.RENAME_RE.match(line):
|
||||
fc.old_path = m.group(1) if (m := self.RENAME_RE.match(line)) else None
|
||||
fc.is_renamed = True
|
||||
elif self.BINARY_RE.match(line):
|
||||
fc.is_binary = True
|
||||
return fc # No hunks for binary
|
||||
|
||||
# Rename TO
|
||||
for line in lines:
|
||||
m = self.RENAME_TO_RE.match(line)
|
||||
if m and fc.is_renamed:
|
||||
fc.path = m.group(1)
|
||||
|
||||
# Parse hunks
|
||||
current_hunk = None
|
||||
for line in lines:
|
||||
m = self.HUNK_HEADER_RE.match(line)
|
||||
if m:
|
||||
if current_hunk:
|
||||
self._classify_hunk(current_hunk, fc)
|
||||
fc.hunks.append(current_hunk)
|
||||
current_hunk = Hunk(
|
||||
header=m.group(5).strip(),
|
||||
old_start=int(m.group(1)),
|
||||
old_count=int(m.group(2) or 1),
|
||||
new_start=int(m.group(3)),
|
||||
new_count=int(m.group(4) or 1),
|
||||
)
|
||||
elif current_hunk and (line.startswith("+") or line.startswith("-") or line.startswith(" ")):
|
||||
current_hunk.lines.append(line)
|
||||
|
||||
if current_hunk:
|
||||
self._classify_hunk(current_hunk, fc)
|
||||
fc.hunks.append(current_hunk)
|
||||
|
||||
return fc
|
||||
|
||||
def _classify_hunk(self, hunk: Hunk, fc: FileChange):
|
||||
"""Classify a hunk and count lines."""
|
||||
added = sum(1 for l in hunk.lines if l.startswith("+"))
|
||||
deleted = sum(1 for l in hunk.lines if l.startswith("-"))
|
||||
|
||||
fc.added_lines += added
|
||||
fc.deleted_lines += deleted
|
||||
|
||||
if added > 0 and deleted == 0:
|
||||
hunk.category = ChangeCategory.ADDED
|
||||
elif deleted > 0 and added == 0:
|
||||
hunk.category = ChangeCategory.DELETED
|
||||
elif added > 0 and deleted > 0:
|
||||
hunk.category = ChangeCategory.MODIFIED
|
||||
else:
|
||||
hunk.category = ChangeCategory.CONTEXT
|
||||
189
scripts/test_diff_analyzer.py
Normal file
189
scripts/test_diff_analyzer.py
Normal file
@@ -0,0 +1,189 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Tests for scripts/diff_analyzer.py — 10 tests."""
|
||||
|
||||
import sys
|
||||
import os
|
||||
sys.path.insert(0, os.path.dirname(__file__) or ".")
|
||||
|
||||
import importlib.util
|
||||
spec = importlib.util.spec_from_file_location("da", os.path.join(os.path.dirname(__file__) or ".", "diff_analyzer.py"))
|
||||
mod = importlib.util.module_from_spec(spec)
|
||||
spec.loader.exec_module(mod)
|
||||
DiffAnalyzer = mod.DiffAnalyzer
|
||||
ChangeCategory = mod.ChangeCategory
|
||||
|
||||
|
||||
SAMPLE_ADD = """diff --git a/new.py b/new.py
|
||||
new file mode 100644
|
||||
--- /dev/null
|
||||
+++ b/new.py
|
||||
@@ -0,0 +1,3 @@
|
||||
+def hello():
|
||||
+ print("world")
|
||||
+ return True
|
||||
"""
|
||||
|
||||
SAMPLE_DELETE = """diff --git a/old.py b/old.py
|
||||
deleted file mode 100644
|
||||
--- a/old.py
|
||||
+++ /dev/null
|
||||
@@ -1,2 +0,0 @@
|
||||
-def goodbye():
|
||||
- pass
|
||||
"""
|
||||
|
||||
SAMPLE_MODIFY = """diff --git a/app.py b/app.py
|
||||
--- a/app.py
|
||||
+++ b/app.py
|
||||
@@ -1,3 +1,4 @@
|
||||
def main():
|
||||
- print("old")
|
||||
+ print("new")
|
||||
+ print("extra")
|
||||
return 0
|
||||
"""
|
||||
|
||||
SAMPLE_RENAME = """diff --git a/old_name.py b/new_name.py
|
||||
rename from old_name.py
|
||||
rename to new_name.py
|
||||
--- a/old_name.py
|
||||
+++ b/new_name.py
|
||||
@@ -1,1 +1,1 @@
|
||||
-old content
|
||||
+new content
|
||||
"""
|
||||
|
||||
SAMPLE_MULTI = """diff --git a/a.py b/a.py
|
||||
--- a/a.py
|
||||
+++ b/a.py
|
||||
@@ -1,1 +1,2 @@
|
||||
existing
|
||||
+added line
|
||||
diff --git b/b.py b/b.py
|
||||
new file mode 100644
|
||||
--- /dev/null
|
||||
+++ b/b.py
|
||||
@@ -0,0 +1,1 @@
|
||||
+new file
|
||||
"""
|
||||
|
||||
SAMPLE_BINARY = """diff --git a/img.png b/img.png
|
||||
Binary files a/img.png and b/img.png differ
|
||||
"""
|
||||
|
||||
|
||||
def test_empty():
|
||||
a = DiffAnalyzer()
|
||||
s = a.analyze("")
|
||||
assert s.total_files_changed == 0
|
||||
print("PASS: test_empty")
|
||||
|
||||
def test_addition():
|
||||
a = DiffAnalyzer()
|
||||
s = a.analyze(SAMPLE_ADD)
|
||||
assert s.total_files_changed == 1
|
||||
assert s.total_added == 3
|
||||
assert s.total_deleted == 0
|
||||
assert s.new_files == 1
|
||||
assert s.files[0].hunks[0].category == ChangeCategory.ADDED
|
||||
print("PASS: test_addition")
|
||||
|
||||
def test_deletion():
|
||||
a = DiffAnalyzer()
|
||||
s = a.analyze(SAMPLE_DELETE)
|
||||
assert s.total_deleted == 2
|
||||
assert s.deleted_files == 1
|
||||
assert s.files[0].hunks[0].category == ChangeCategory.DELETED
|
||||
print("PASS: test_deletion")
|
||||
|
||||
def test_modification():
|
||||
a = DiffAnalyzer()
|
||||
s = a.analyze(SAMPLE_MODIFY)
|
||||
assert s.total_added == 2
|
||||
assert s.total_deleted == 1
|
||||
assert s.files[0].hunks[0].category == ChangeCategory.MODIFIED
|
||||
print("PASS: test_modification")
|
||||
|
||||
def test_rename():
|
||||
a = DiffAnalyzer()
|
||||
s = a.analyze(SAMPLE_RENAME)
|
||||
assert s.renamed_files == 1
|
||||
assert s.files[0].old_path == "old_name.py"
|
||||
assert s.files[0].path == "new_name.py"
|
||||
assert s.files[0].is_renamed == True
|
||||
print("PASS: test_rename")
|
||||
|
||||
def test_multiple_files():
|
||||
a = DiffAnalyzer()
|
||||
s = a.analyze(SAMPLE_MULTI)
|
||||
assert s.total_files_changed == 2
|
||||
assert s.new_files == 1
|
||||
print("PASS: test_multiple_files")
|
||||
|
||||
def test_binary():
|
||||
a = DiffAnalyzer()
|
||||
s = a.analyze(SAMPLE_BINARY)
|
||||
assert s.binary_files == 1
|
||||
assert s.files[0].is_binary == True
|
||||
assert len(s.files[0].hunks) == 0
|
||||
print("PASS: test_binary")
|
||||
|
||||
def test_to_dict():
|
||||
a = DiffAnalyzer()
|
||||
s = a.analyze(SAMPLE_MODIFY)
|
||||
d = s.to_dict()
|
||||
assert "total_files_changed" in d
|
||||
assert "files" in d
|
||||
assert isinstance(d["files"], list)
|
||||
print("PASS: test_to_dict")
|
||||
|
||||
def test_context_only():
|
||||
diff = """diff --git a/f.py b/f.py
|
||||
--- a/f.py
|
||||
+++ b/f.py
|
||||
@@ -1,3 +1,3 @@
|
||||
line1
|
||||
-old
|
||||
+new
|
||||
line3
|
||||
"""
|
||||
a = DiffAnalyzer()
|
||||
s = a.analyze(diff)
|
||||
# Has both added and deleted = MODIFIED
|
||||
assert s.files[0].hunks[0].category == ChangeCategory.MODIFIED
|
||||
print("PASS: test_context_only")
|
||||
|
||||
def test_multi_hunk():
|
||||
diff = """diff --git a/f.py b/f.py
|
||||
--- a/f.py
|
||||
+++ b/f.py
|
||||
@@ -1,1 +1,2 @@
|
||||
existing
|
||||
+first addition
|
||||
@@ -10,1 +11,2 @@
|
||||
more
|
||||
+second addition
|
||||
"""
|
||||
a = DiffAnalyzer()
|
||||
s = a.analyze(diff)
|
||||
assert s.total_hunks == 2
|
||||
assert s.total_added == 2
|
||||
print("PASS: test_multi_hunk")
|
||||
|
||||
|
||||
def run_all():
|
||||
test_empty()
|
||||
test_addition()
|
||||
test_deletion()
|
||||
test_modification()
|
||||
test_rename()
|
||||
test_multiple_files()
|
||||
test_binary()
|
||||
test_to_dict()
|
||||
test_context_only()
|
||||
test_multi_hunk()
|
||||
print("\nAll 10 tests passed!")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
run_all()
|
||||
212
scripts/test_harvest_prompt_comprehensive.py
Normal file
212
scripts/test_harvest_prompt_comprehensive.py
Normal file
@@ -0,0 +1,212 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Comprehensive test script for knowledge extraction prompt.
|
||||
Validates prompt structure, requirements, and consistency.
|
||||
"""
|
||||
|
||||
import json
|
||||
import re
|
||||
from pathlib import Path
|
||||
|
||||
def test_prompt_structure():
|
||||
"""Test that the prompt has the required structure."""
|
||||
prompt_path = Path("templates/harvest-prompt.md")
|
||||
if not prompt_path.exists():
|
||||
return False, "harvest-prompt.md not found"
|
||||
|
||||
content = prompt_path.read_text()
|
||||
|
||||
# Check for required sections
|
||||
required_sections = [
|
||||
"System Prompt",
|
||||
"Instructions",
|
||||
"Categories",
|
||||
"Output Format",
|
||||
"Confidence Scoring",
|
||||
"Constraints",
|
||||
"Example"
|
||||
]
|
||||
|
||||
for section in required_sections:
|
||||
if section.lower() not in content.lower():
|
||||
return False, f"Missing required section: {section}"
|
||||
|
||||
# Check for required categories
|
||||
required_categories = ["fact", "pitfall", "pattern", "tool-quirk", "question"]
|
||||
for category in required_categories:
|
||||
if category not in content:
|
||||
return False, f"Missing required category: {category}"
|
||||
|
||||
# Check for required output fields
|
||||
required_fields = ["fact", "category", "repo", "confidence"]
|
||||
for field in required_fields:
|
||||
if field not in content:
|
||||
return False, f"Missing required output field: {field}"
|
||||
|
||||
# Check prompt size (should be ~1k tokens, roughly 4k chars)
|
||||
if len(content) > 5000:
|
||||
return False, f"Prompt too large: {len(content)} chars (max ~5000)"
|
||||
|
||||
if len(content) < 1000:
|
||||
return False, f"Prompt too small: {len(content)} chars (min ~1000)"
|
||||
|
||||
return True, "Prompt structure is valid"
|
||||
|
||||
def test_confidence_scoring():
|
||||
"""Test that confidence scoring is properly defined."""
|
||||
prompt_path = Path("templates/harvest-prompt.md")
|
||||
content = prompt_path.read_text()
|
||||
|
||||
# Check for confidence scale definitions
|
||||
confidence_levels = [
|
||||
("0.9-1.0", "explicitly stated"),
|
||||
("0.7-0.8", "clearly implied"),
|
||||
("0.5-0.6", "suggested"),
|
||||
("0.3-0.4", "inferred"),
|
||||
("0.1-0.2", "speculative")
|
||||
]
|
||||
|
||||
for level, description in confidence_levels:
|
||||
if level not in content:
|
||||
return False, f"Missing confidence level: {level}"
|
||||
if description.lower() not in content.lower():
|
||||
return False, f"Missing confidence description: {description}"
|
||||
|
||||
return True, "Confidence scoring is properly defined"
|
||||
|
||||
def test_example_quality():
|
||||
"""Test that examples are clear and complete."""
|
||||
prompt_path = Path("templates/harvest-prompt.md")
|
||||
content = prompt_path.read_text()
|
||||
|
||||
# Check for example input/output
|
||||
if "example" not in content.lower():
|
||||
return False, "No examples provided"
|
||||
|
||||
# Check that example includes all categories
|
||||
example_section = content[content.lower().find("example"):]
|
||||
|
||||
# Look for JSON example
|
||||
json_match = re.search(r'\{[\s\S]*"knowledge"[\s\S]*\}', example_section)
|
||||
if not json_match:
|
||||
return False, "No JSON example found"
|
||||
|
||||
example_json = json_match.group(0)
|
||||
|
||||
# Check for all categories in example
|
||||
for category in ["fact", "pitfall", "pattern", "tool-quirk", "question"]:
|
||||
if category not in example_json:
|
||||
return False, f"Example missing category: {category}"
|
||||
|
||||
return True, "Examples are clear and complete"
|
||||
|
||||
def test_constraint_coverage():
|
||||
"""Test that constraints cover all requirements."""
|
||||
prompt_path = Path("templates/harvest-prompt.md")
|
||||
content = prompt_path.read_text()
|
||||
|
||||
required_constraints = [
|
||||
"No hallucination",
|
||||
"only extract",
|
||||
"explicitly",
|
||||
"partial",
|
||||
"failed sessions",
|
||||
"1k tokens"
|
||||
]
|
||||
|
||||
for constraint in required_constraints:
|
||||
if constraint.lower() not in content.lower():
|
||||
return False, f"Missing constraint: {constraint}"
|
||||
|
||||
return True, "Constraints cover all requirements"
|
||||
|
||||
def test_test_sessions():
|
||||
"""Test that test sessions exist and are valid."""
|
||||
test_sessions_dir = Path("test_sessions")
|
||||
if not test_sessions_dir.exists():
|
||||
return False, "test_sessions directory not found"
|
||||
|
||||
session_files = list(test_sessions_dir.glob("*.jsonl"))
|
||||
if len(session_files) < 5:
|
||||
return False, f"Only {len(session_files)} test sessions found, need 5"
|
||||
|
||||
# Check each session file
|
||||
for session_file in session_files:
|
||||
content = session_file.read_text()
|
||||
lines = content.strip().split("\n")
|
||||
|
||||
# Check that each line is valid JSON
|
||||
for i, line in enumerate(lines, 1):
|
||||
try:
|
||||
json.loads(line)
|
||||
except json.JSONDecodeError as e:
|
||||
return False, f"Invalid JSON in {session_file.name}, line {i}: {e}"
|
||||
|
||||
return True, f"Found {len(session_files)} valid test sessions"
|
||||
|
||||
def run_all_tests():
|
||||
"""Run all tests and return results."""
|
||||
tests = [
|
||||
("Prompt Structure", test_prompt_structure),
|
||||
("Confidence Scoring", test_confidence_scoring),
|
||||
("Example Quality", test_example_quality),
|
||||
("Constraint Coverage", test_constraint_coverage),
|
||||
("Test Sessions", test_test_sessions)
|
||||
]
|
||||
|
||||
results = []
|
||||
all_passed = True
|
||||
|
||||
for test_name, test_func in tests:
|
||||
try:
|
||||
passed, message = test_func()
|
||||
results.append({
|
||||
"test": test_name,
|
||||
"passed": passed,
|
||||
"message": message
|
||||
})
|
||||
if not passed:
|
||||
all_passed = False
|
||||
except Exception as e:
|
||||
results.append({
|
||||
"test": test_name,
|
||||
"passed": False,
|
||||
"message": f"Error: {str(e)}"
|
||||
})
|
||||
all_passed = False
|
||||
|
||||
# Print results
|
||||
print("=" * 60)
|
||||
print("HARVEST PROMPT TEST RESULTS")
|
||||
print("=" * 60)
|
||||
|
||||
for result in results:
|
||||
status = "✓ PASS" if result["passed"] else "✗ FAIL"
|
||||
print(f"{status}: {result['test']}")
|
||||
print(f" {result['message']}")
|
||||
print()
|
||||
|
||||
print("=" * 60)
|
||||
if all_passed:
|
||||
print("ALL TESTS PASSED!")
|
||||
else:
|
||||
print("SOME TESTS FAILED!")
|
||||
print("=" * 60)
|
||||
|
||||
return all_passed, results
|
||||
|
||||
if __name__ == "__main__":
|
||||
all_passed, results = run_all_tests()
|
||||
|
||||
# Save results to file
|
||||
with open("test_results.json", "w") as f:
|
||||
json.dump({
|
||||
"all_passed": all_passed,
|
||||
"results": results,
|
||||
"timestamp": "2026-04-14T19:05:00Z"
|
||||
}, f, indent=2)
|
||||
|
||||
print(f"Results saved to test_results.json")
|
||||
|
||||
# Exit with appropriate code
|
||||
exit(0 if all_passed else 1)
|
||||
18
test_sessions/session_failure.jsonl
Normal file
18
test_sessions/session_failure.jsonl
Normal file
@@ -0,0 +1,18 @@
|
||||
{"role": "user", "content": "Deploy the application to production"}
|
||||
{"role": "assistant", "content": "I'll deploy the application to production.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ssh deploy@prod-server 'cd /app && git pull && docker-compose up -d'"}}]}
|
||||
{"role": "tool", "content": "ssh: connect to host prod-server port 22: Connection refused"}
|
||||
{"role": "assistant", "content": "Connection refused. Let me check the server status.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ping -c 3 prod-server"}}]}
|
||||
{"role": "tool", "content": "PING prod-server (192.168.1.100): 56 data bytes\nRequest timeout for icmp_seq 0\nRequest timeout for icmp_seq 1\nRequest timeout for icmp_seq 2\n--- prod-server ping statistics ---\n3 packets transmitted, 0 packets received, 100.0% packet loss"}
|
||||
{"role": "assistant", "content": "The server appears to be down. Let me check if there's an alternative deployment method."}
|
||||
{"role": "user", "content": "Try using the VPS instead"}
|
||||
{"role": "assistant", "content": "I'll try deploying to the VPS.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ssh deploy@vps-server 'cd /app && git pull && docker-compose up -d'"}}]}
|
||||
{"role": "tool", "content": "Permission denied (publickey)."}
|
||||
{"role": "assistant", "content": "Permission denied. The SSH key might not be set up correctly. Let me check the SSH configuration.", "tool_calls": [{"function": "terminal", "arguments": {"command": "cat ~/.ssh/config"}}]}
|
||||
{"role": "tool", "content": "Host vps-server\n HostName 167.99.126.228\n User deploy\n IdentityFile ~/.ssh/id_rsa_vps"}
|
||||
{"role": "assistant", "content": "The SSH config looks correct. Let me check if the key exists.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ls -la ~/.ssh/id_rsa_vps"}}]}
|
||||
{"role": "tool", "content": "ls: /Users/user/.ssh/id_rsa_vps: No such file or directory"}
|
||||
{"role": "assistant", "content": "The SSH key doesn't exist. This is a pitfall - we need to generate the SSH key first."}
|
||||
{"role": "user", "content": "Generate a new SSH key for the VPS"}
|
||||
{"role": "assistant", "content": "I'll generate a new SSH key.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ssh-keygen -t rsa -b 4096 -f ~/.ssh/id_rsa_vps -N ''"}}]}
|
||||
{"role": "tool", "content": "Generating public/private rsa key pair.\nYour identification has been saved in /Users/user/.ssh/id_rsa_vps\nYour public key has been saved in /Users/user/.ssh/id_rsa_vps.pub\nThe key fingerprint is:\nSHA256:abc123... user@machine"}
|
||||
{"role": "assistant", "content": "SSH key generated. Now I need to add it to the VPS."}
|
||||
14
test_sessions/session_partial.jsonl
Normal file
14
test_sessions/session_partial.jsonl
Normal file
@@ -0,0 +1,14 @@
|
||||
{"role": "user", "content": "Check the Gitea API for open issues"}
|
||||
{"role": "assistant", "content": "I'll check the Gitea API for open issues.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -H 'Authorization: token $GITEA_TOKEN' https://forge.alexanderwhitestone.com/api/v1/repos/Timmy_Foundation/compounding-intelligence/issues?state=open"}}]}
|
||||
{"role": "tool", "content": "curl: (6) Could not resolve host: forge.alexanderwhitestone.com"}
|
||||
{"role": "assistant", "content": "DNS resolution failed. Let me check the network connectivity.", "tool_calls": [{"function": "terminal", "arguments": {"command": "nslookup forge.alexanderwhitestone.com"}}]}
|
||||
{"role": "tool", "content": "Server: 8.8.8.8\nAddress: 8.8.8.8#53\n\n** server can't find forge.alexanderwhitestone.com: NXDOMAIN"}
|
||||
{"role": "assistant", "content": "The domain doesn't resolve. This might be a DNS issue. Let me try using the IP address directly.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -H 'Authorization: token $GITEA_TOKEN' https://167.99.126.228/api/v1/repos/Timmy_Foundation/compounding-intelligence/issues?state=open"}}]}
|
||||
{"role": "tool", "content": "curl: (60) SSL certificate problem: self signed certificate"}
|
||||
{"role": "assistant", "content": "SSL certificate issue. The server is using a self-signed certificate. Let me try with -k flag to skip SSL verification.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -k -H 'Authorization: token $GITEA_TOKEN' https://167.99.126.228/api/v1/repos/Timmy_Foundation/compounding-intelligence/issues?state=open"}}]}
|
||||
{"role": "tool", "content": "[]"}
|
||||
{"role": "assistant", "content": "No open issues found. The API returned an empty array."}
|
||||
{"role": "user", "content": "Check if there are any pull requests"}
|
||||
{"role": "assistant", "content": "Let me check for pull requests.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -k -H 'Authorization: token $GITEA_TOKEN' https://167.99.126.228/api/v1/repos/Timmy_Foundation/compounding-intelligence/pulls?state=open"}}]}
|
||||
{"role": "tool", "content": "[{"id": 20, "title": "feat: add harvester.py + session_reader.py — session knowledge extractor (closes #8)", "state": "open", "user": {"login": "Rockachopa"}, "created_at": "2026-04-14T17:28:20Z"}]"}
|
||||
{"role": "assistant", "content": "Found 1 open pull request: PR #20 - "feat: add harvester.py + session_reader.py — session knowledge extractor (closes #8)" by Rockachopa."}
|
||||
10
test_sessions/session_patterns.jsonl
Normal file
10
test_sessions/session_patterns.jsonl
Normal file
@@ -0,0 +1,10 @@
|
||||
{"role": "user", "content": "How do I deploy a new version of the application?"}
|
||||
{"role": "assistant", "content": "Here's the deployment process:\n1. Run tests: pytest\n2. Build Docker image: docker build -t app:latest .\n3. Push to registry: docker push registry.example.com/app:latest\n4. Update production: ssh prod 'cd /app && docker-compose pull && docker-compose up -d'\n5. Verify: curl https://app.example.com/health"}
|
||||
{"role": "user", "content": "What if tests fail?"}
|
||||
{"role": "assistant", "content": "If tests fail:\n1. Check the error logs: pytest -v\n2. Fix the failing tests\n3. Re-run tests: pytest\n4. If still failing, check recent changes: git log --oneline -10\n5. Consider reverting: git revert HEAD"}
|
||||
{"role": "user", "content": "What if the Docker build fails?"}
|
||||
{"role": "assistant", "content": "If Docker build fails:\n1. Check Dockerfile syntax: docker build --no-cache -t app:latest .\n2. Check for missing dependencies: cat requirements.txt\n3. Check disk space: df -h\n4. Clean up Docker: docker system prune -f\n5. Try building with verbose output: docker build --progress=plain -t app:latest ."}
|
||||
{"role": "user", "content": "What if the push to registry fails?"}
|
||||
{"role": "assistant", "content": "If push to registry fails:\n1. Check registry credentials: docker login registry.example.com\n2. Check registry space: curl https://registry.example.com/v2/_catalog\n3. Check image size: docker images app:latest\n4. Try tagging with version: docker tag app:latest registry.example.com/app:v1.0.0\n5. Push with version tag: docker push registry.example.com/app:v1.0.0"}
|
||||
{"role": "user", "content": "What if the production update fails?"}
|
||||
{"role": "assistant", "content": "If production update fails:\n1. Check SSH connection: ssh prod 'echo connected'\n2. Check disk space on prod: ssh prod 'df -h'\n3. Check Docker status: ssh prod 'docker ps -a'\n4. Check logs: ssh prod 'docker-compose logs --tail=100'\n5. Rollback: ssh prod 'cd /app && git checkout HEAD~1 && docker-compose up -d'"}
|
||||
12
test_sessions/session_questions.jsonl
Normal file
12
test_sessions/session_questions.jsonl
Normal file
@@ -0,0 +1,12 @@
|
||||
{"role": "user", "content": "I need to implement a new feature for the application"}
|
||||
{"role": "assistant", "content": "I can help you implement a new feature. What feature would you like to add?"}
|
||||
{"role": "user", "content": "I want to add user authentication"}
|
||||
{"role": "assistant", "content": "User authentication is a good feature. I have a few questions:\n1. What authentication method do you prefer? (JWT, OAuth, Session-based)\n2. Do you need social login? (Google, GitHub, etc.)\n3. What user data do you need to store?\n4. Do you need role-based access control?\n5. What's your database? (PostgreSQL, MySQL, SQLite)"}
|
||||
{"role": "user", "content": "I prefer JWT, no social login, just email and password, no roles, PostgreSQL"}
|
||||
{"role": "assistant", "content": "Great choices. Here's the implementation plan:\n1. Create user model with email and password hash\n2. Create JWT token generation and validation\n3. Create login endpoint: POST /api/auth/login\n4. Create register endpoint: POST /api/auth/register\n5. Create middleware for protected routes\n6. Add password hashing with bcrypt\n7. Add rate limiting for login attempts\n8. Add password reset functionality\n9. Add email verification\n10. Test all endpoints"}
|
||||
{"role": "user", "content": "What about password reset?"}
|
||||
{"role": "assistant", "content": "For password reset:\n1. Create reset token table\n2. Create forgot password endpoint: POST /api/auth/forgot-password\n3. Send reset email with token\n4. Create reset password endpoint: POST /api/auth/reset-password\n5. Validate reset token and expiration\n6. Update password and delete token\n7. Send confirmation email"}
|
||||
{"role": "user", "content": "What about email verification?"}
|
||||
{"role": "assistant", "content": "For email verification:\n1. Add email_verified field to user model\n2. Create verification token table\n3. Send verification email on registration\n4. Create verify email endpoint: GET /api/auth/verify-email?token=...\n5. Validate token and update email_verified\n6. Add middleware to check email_verified for certain routes\n7. Add resend verification email endpoint"}
|
||||
{"role": "user", "content": "What about rate limiting?"}
|
||||
{"role": "assistant", "content": "For rate limiting:\n1. Use Redis for rate limit storage\n2. Create rate limit middleware\n3. Set limits: 5 login attempts per minute, 3 password resets per hour\n4. Return 429 Too Many Requests when limit exceeded\n5. Add X-RateLimit headers to responses\n6. Log rate limit violations\n7. Add whitelist for trusted IPs"}
|
||||
13
test_sessions/session_success.jsonl
Normal file
13
test_sessions/session_success.jsonl
Normal file
@@ -0,0 +1,13 @@
|
||||
{"role": "user", "content": "Clone the repo at forge.alexanderwhitestone.com/Timmy_Foundation/compounding-intelligence"}
|
||||
{"role": "assistant", "content": "I'll clone the repository for you.", "tool_calls": [{"function": "terminal", "arguments": {"command": "git clone https://forge.alexanderwhitestone.com/Timmy_Foundation/compounding-intelligence.git"}}]}
|
||||
{"role": "tool", "content": "Cloning into 'compounding-intelligence'...\nremote: Enumerating objects: 15, done.\nremote: Counting objects: 100% (15/15), done.\nremote: Compressing objects: 100% (12/12), done.\nremote: Total 15 (delta 2), reused 0 (delta 0), pack-reused 0\nReceiving objects: 100% (15/15), done.\nResolving deltas: 100% (2/2), done."}
|
||||
{"role": "assistant", "content": "Repository cloned successfully. Let me check the structure.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ls -la compounding-intelligence/"}}]}
|
||||
{"role": "tool", "content": "total 8\ndrwxr-xr-x 5 user staff 160 Apr 14 17:21 .\ndrwxr-xr-x 12 user staff 384 Apr 14 17:21 ..\ndrwxr-xr-x 13 user staff 416 Apr 14 17:21 .git\n-rw-r--r-- 1 user staff 1234 Apr 14 17:21 README.md\ndrwxr-xr-x 3 user staff 96 Apr 14 17:21 knowledge\n-rw-r--r-- 1 user staff 456 Apr 14 17:21 metrics\ndrwxr-xr-x 4 user staff 128 Apr 14 17:21 scripts\ndrwxr-xr-x 3 user staff 96 Apr 14 17:21 templates"}
|
||||
{"role": "user", "content": "What files are in the templates directory?"}
|
||||
{"role": "assistant", "content": "Let me check the templates directory.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ls -la compounding-intelligence/templates/"}}]}
|
||||
{"role": "tool", "content": "total 0\ndrwxr-xr-x 3 user staff 96 Apr 14 17:21 .\ndrwxr-xr-x 5 user staff 160 Apr 14 17:21 ..\n-rw-r--r-- 1 user staff 0 Apr 14 17:21 .gitkeep"}
|
||||
{"role": "assistant", "content": "The templates directory currently only contains a .gitkeep file. No templates have been added yet."}
|
||||
{"role": "user", "content": "Create a harvest-prompt.md template in the templates directory."}
|
||||
{"role": "assistant", "content": "I'll create the harvest-prompt.md template for you.", "tool_calls": [{"function": "terminal", "arguments": {"command": "cat > compounding-intelligence/templates/harvest-prompt.md << 'EOF'\n# Knowledge Extraction Prompt\n\nExtract knowledge from session transcripts.\nEOF"}}]}
|
||||
{"role": "tool", "content": ""}
|
||||
{"role": "assistant", "content": "Template created successfully. The harvest-prompt.md file is now in the templates directory."}
|
||||
Reference in New Issue
Block a user