test: add tests for session pair harvester (#91)

scripts/dead_code_detector.py

@@ -1,282 +0,0 @@
-#!/usr/bin/env python3
-"""
-Dead Code Detector for Python Codebases
-
-AST-based analysis to find defined but never-called functions and classes.
-Excludes entry points, plugin hooks, __init__ exports.
-
-Usage:
-  python3 scripts/dead_code_detector.py /path/to/repo/
-  python3 scripts/dead_code_detector.py hermes-agent/ --format json
-  python3 scripts/dead_code_detector.py . --exclude tests/,venv/
-
-Output: file:line, function/class name, last git author (if available)
-"""
-
-import argparse
-import ast
-import json
-import os
-import subprocess
-import sys
-from collections import defaultdict
-from pathlib import Path
-from typing import Optional
-
-
-# Names that are expected to be unused (entry points, protocol methods, etc.)
-SAFE_UNUSED_PATTERNS = {
-    # Python dunders
-    "__init__", "__str__", "__repr__", "__eq__", "__hash__", "__len__",
-    "__getitem__", "__setitem__", "__contains__", "__iter__", "__next__",
-    "__enter__", "__exit__", "__call__", "__bool__", "__del__",
-    "__post_init__", "__class_getitem__",
-    # Common entry points
-    "main", "app", "handler", "setup", "teardown", "fixture",
-    # pytest
-    "conftest", "test_", "pytest_",  # prefix patterns
-    # Protocols / abstract
-    "abstractmethod", "abc_",
-}
-
-
-def is_safe_unused(name: str, filepath: str) -> bool:
-    """Check if an unused name is expected to be unused."""
-    # Test files are exempt
-    if "test" in filepath.lower():
-        return True
-
-    # Known patterns
-    for pattern in SAFE_UNUSED_PATTERNS:
-        if name.startswith(pattern) or name == pattern:
-            return True
-
-    # __init__.py exports are often unused internally
-    if filepath.endswith("__init__.py"):
-        return True
-
-    return False
-
-
-def get_git_blame(filepath: str, lineno: int) -> Optional[str]:
-    """Get last author of a line via git blame."""
-    try:
-        result = subprocess.run(
-            ["git", "blame", "-L", f"{lineno},{lineno}", "--porcelain", filepath],
-            capture_output=True, text=True, timeout=5
-        )
-        for line in result.stdout.split("\n"):
-            if line.startswith("author "):
-                return line[7:]
-    except:
-        pass
-    return None
-
-
-class DefinitionCollector(ast.NodeVisitor):
-    """Collect all function and class definitions."""
-
-    def __init__(self):
-        self.definitions = []  # (name, type, lineno, filepath)
-
-    def visit_FunctionDef(self, node):
-        self.definitions.append((node.name, "function", node.lineno))
-        self.generic_visit(node)
-
-    def visit_AsyncFunctionDef(self, node):
-        self.definitions.append((node.name, "async_function", node.lineno))
-        self.generic_visit(node)
-
-    def visit_ClassDef(self, node):
-        self.definitions.append((node.name, "class", node.lineno))
-        self.generic_visit(node)
-
-
-class NameUsageCollector(ast.NodeVisitor):
-    """Collect all name references (calls, imports, attribute access)."""
-
-    def __init__(self):
-        self.names = set()
-        self.calls = set()
-        self.imports = set()
-
-    def visit_Name(self, node):
-        self.names.add(node.id)
-        self.generic_visit(node)
-
-    def visit_Attribute(self, node):
-        if isinstance(node.value, ast.Name):
-            self.names.add(node.value.id)
-        self.generic_visit(node)
-
-    def visit_Call(self, node):
-        if isinstance(node.func, ast.Name):
-            self.calls.add(node.func.id)
-        elif isinstance(node.func, ast.Attribute):
-            if isinstance(node.func.value, ast.Name):
-                self.names.add(node.func.value.id)
-            self.calls.add(node.func.attr)
-        self.generic_visit(node)
-
-    def visit_Import(self, node):
-        for alias in node.names:
-            self.imports.add(alias.asname or alias.name)
-        self.generic_visit(node)
-
-    def visit_ImportFrom(self, node):
-        for alias in node.names:
-            self.imports.add(alias.asname or alias.name)
-        self.generic_visit(node)
-
-
-def analyze_file(filepath: str) -> dict:
-    """Analyze a single Python file for dead code."""
-    path = Path(filepath)
-    try:
-        content = path.read_text()
-        tree = ast.parse(content, filename=str(filepath))
-    except (SyntaxError, UnicodeDecodeError):
-        return {"error": f"Could not parse {filepath}"}
-
-    # Collect definitions
-    def_collector = DefinitionCollector()
-    def_collector.visit(tree)
-    definitions = def_collector.definitions
-
-    # Collect usage
-    usage_collector = NameUsageCollector()
-    usage_collector.visit(tree)
-    used_names = usage_collector.names | usage_collector.calls | usage_collector.imports
-
-    # Also scan the entire repo for references to this file's definitions
-    # (this is done at the repo level, not file level)
-
-    dead = []
-    for name, def_type, lineno in definitions:
-        if name.startswith("_") and not name.startswith("__"):
-            # Private functions — might be used externally, less likely dead
-            pass
-
-        if name not in used_names:
-            if not is_safe_unused(name, filepath):
-                dead.append({
-                    "name": name,
-                    "type": def_type,
-                    "file": filepath,
-                    "line": lineno,
-                })
-
-    return {"definitions": len(definitions), "dead": dead}
-
-
-def scan_repo(repo_path: str, exclude_patterns: list = None) -> dict:
-    """Scan an entire repo for dead code."""
-    path = Path(repo_path)
-    exclude = exclude_patterns or ["venv", ".venv", "node_modules", "__pycache__",
-                                    ".git", "dist", "build", ".tox", "vendor"]
-
-    all_definitions = {}  # name -> [{file, line, type}]
-    all_files = []
-    dead_code = []
-
-    # First pass: collect all definitions across repo
-    for fpath in path.rglob("*.py"):
-        parts = fpath.parts
-        if any(ex in parts for ex in exclude):
-            continue
-        if fpath.name.startswith("."):
-            continue
-
-        try:
-            content = fpath.read_text(errors="ignore")
-            tree = ast.parse(content, filename=str(fpath))
-        except:
-            continue
-
-        all_files.append(str(fpath))
-        collector = DefinitionCollector()
-        collector.visit(tree)
-
-        for name, def_type, lineno in collector.definitions:
-            rel_path = str(fpath.relative_to(path))
-            if name not in all_definitions:
-                all_definitions[name] = []
-            all_definitions[name].append({
-                "file": rel_path,
-                "line": lineno,
-                "type": def_type,
-            })
-
-    # Second pass: check each name for usage across entire repo
-    all_used_names = set()
-    for fpath_str in all_files:
-        try:
-            content = Path(fpath_str).read_text(errors="ignore")
-            tree = ast.parse(content)
-        except:
-            continue
-        usage = NameUsageCollector()
-        usage.visit(tree)
-        all_used_names.update(usage.names)
-        all_used_names.update(usage.calls)
-        all_used_names.update(usage.imports)
-
-    # Find dead code
-    for name, locations in all_definitions.items():
-        if name not in all_used_names:
-            for loc in locations:
-                if not is_safe_unused(name, loc["file"]):
-                    dead_code.append({
-                        "name": name,
-                        "type": loc["type"],
-                        "file": loc["file"],
-                        "line": loc["line"],
-                    })
-
-    return {
-        "repo": path.name,
-        "files_scanned": len(all_files),
-        "total_definitions": sum(len(v) for v in all_definitions.values()),
-        "dead_code_count": len(dead_code),
-        "dead_code": sorted(dead_code, key=lambda x: (x["file"], x["line"])),
-    }
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Find dead code in Python codebases")
-    parser.add_argument("repo", help="Repository path to scan")
-    parser.add_argument("--format", choices=["text", "json"], default="text")
-    parser.add_argument("--exclude", help="Comma-separated patterns to exclude")
-    parser.add_argument("--git-blame", action="store_true", help="Include git blame info")
-    args = parser.parse_args()
-
-    exclude = args.exclude.split(",") if args.exclude else None
-    result = scan_repo(args.repo, exclude)
-
-    if args.format == "json":
-        print(json.dumps(result, indent=2))
-    else:
-        print(f"Dead Code Report: {result['repo']}")
-        print(f"Files scanned: {result['files_scanned']}")
-        print(f"Total definitions: {result['total_definitions']}")
-        print(f"Dead code found: {result['dead_code_count']}")
-        print()
-
-        if result["dead_code"]:
-            print(f"{'File':<45} {'Line':>4} {'Type':<10} {'Name'}")
-            print("-" * 85)
-            for item in result["dead_code"]:
-                author = ""
-                if args.git_blame:
-                    author = get_git_blame(
-                        os.path.join(args.repo, item["file"]),
-                        item["line"]
-                    ) or ""
-                    author = f" ({author})" if author else ""
-                print(f"{item['file']:<45} {item['line']:>4} {item['type']:<10} {item['name']}{author}")
-        else:
-            print("No dead code detected!")
-
-
-if __name__ == "__main__":
-    main()

scripts/session_pair_harvester.py

@@ -0,0 +1,234 @@
+#!/usr/bin/env python3
+"""
+Session Transcript → Training Pair Harvester
+
+Scans Hermes session JSONL files for Q&A patterns and extracts
+terse→rich training pairs. Outputs JSONL matching the timmy-config
+training pairs spec.
+
+Usage:
+  python3 scripts/session_pair_harvester.py ~/.hermes/sessions/
+  python3 scripts/session_pair_harvester.py session.jsonl --output pairs.jsonl
+  python3 scripts/session_pair_harvester.py --dir ~/.hermes/sessions/ --min-ratio 2.0
+
+Output format:
+  {"terse": "user short prompt", "rich": "ai detailed response", "source": "session_id", "model": "..."}
+"""
+
+import argparse
+import hashlib
+import json
+import sys
+from pathlib import Path
+from typing import Optional
+
+
+def compute_hash(text: str) -> str:
+    """Content hash for deduplication."""
+    return hashlib.sha256(text.encode()).hexdigest()[:16]
+
+
+def extract_pairs_from_session(session_data: dict, min_ratio: float = 1.5,
+                                min_response_words: int = 20) -> list:
+    """Extract terse→rich pairs from a single session object."""
+    pairs = []
+    conversations = session_data.get("conversations", [])
+    session_id = session_data.get("id", "unknown")
+    model = session_data.get("model", "unknown")
+
+    seen_hashes = set()
+
+    for i, msg in enumerate(conversations):
+        # Look for assistant/gpt responses
+        if msg.get("from") not in ("gpt", "assistant"):
+            continue
+
+        response_text = msg.get("value", "")
+        if not response_text or len(response_text.split()) < min_response_words:
+            continue
+
+        # Find the preceding human message
+        prompt_text = ""
+        for j in range(i - 1, -1, -1):
+            if conversations[j].get("from") == "human":
+                prompt_text = conversations[j].get("value", "")
+                break
+
+        if not prompt_text:
+            continue
+
+        # Filter: skip tool results, system messages embedded as human
+        if prompt_text.startswith("{") and "output" in prompt_text[:100]:
+            continue  # likely a tool result
+        if prompt_text.startswith("# SOUL.md") or prompt_text.startswith("You are"):
+            continue  # system prompt leak
+
+        # Quality filters
+        prompt_words = len(prompt_text.split())
+        response_words = len(response_text.split())
+
+        # Must have meaningful length ratio
+        if prompt_words == 0 or response_words == 0:
+            continue
+        ratio = response_words / prompt_words
+        if ratio < min_ratio:
+            continue
+
+        # Skip responses that are mostly code
+        code_blocks = response_text.count("```")
+        if code_blocks >= 4 and len(response_text.replace("```", "").strip()) < 50:
+            continue
+
+        # Skip responses with tool call artifacts
+        if "tool_call" in response_text[:100] or "function_call" in response_text[:100]:
+            continue
+
+        # Deduplicate by content hash
+        content_hash = compute_hash(prompt_text + response_text[:200])
+        if content_hash in seen_hashes:
+            continue
+        seen_hashes.add(content_hash)
+
+        # Clean up response: remove markdown headers if too many
+        clean_response = response_text
+
+        pairs.append({
+            "terse": prompt_text.strip(),
+            "rich": clean_response.strip(),
+            "source": session_id,
+            "model": model,
+            "prompt_words": prompt_words,
+            "response_words": response_words,
+            "ratio": round(ratio, 2),
+        })
+
+    return pairs
+
+
+def extract_from_jsonl_file(filepath: str, **kwargs) -> list:
+    """Extract pairs from a session JSONL file."""
+    pairs = []
+    path = Path(filepath)
+
+    if not path.exists():
+        print(f"Warning: {filepath} not found", file=sys.stderr)
+        return pairs
+
+    content = path.read_text()
+    lines = content.strip().split("\n")
+
+    for line in lines:
+        line = line.strip()
+        if not line:
+            continue
+        try:
+            session = json.loads(line)
+        except json.JSONDecodeError:
+            continue
+
+        session_pairs = extract_pairs_from_session(session, **kwargs)
+        pairs.extend(session_pairs)
+
+    return pairs
+
+
+def deduplicate_pairs(pairs: list) -> list:
+    """Remove duplicate pairs across files."""
+    seen = set()
+    unique = []
+    for pair in pairs:
+        key = compute_hash(pair["terse"] + pair["rich"][:200])
+        if key not in seen:
+            seen.add(key)
+            unique.append(pair)
+    return unique
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Harvest training pairs from session transcripts")
+    parser.add_argument("input", nargs="?", help="Session JSONL file or directory")
+    parser.add_argument("--dir", "-d", help="Directory to scan for session files")
+    parser.add_argument("--output", "-o", default="harvested_pairs.jsonl", help="Output file")
+    parser.add_argument("--min-ratio", type=float, default=1.5, help="Min response/prompt word ratio")
+    parser.add_argument("--min-words", type=int, default=20, help="Min response word count")
+    parser.add_argument("--dry-run", action="store_true", help="Print stats without writing")
+    args = parser.parse_args()
+
+    all_pairs = []
+    files_scanned = 0
+
+    scan_dir = args.dir or args.input
+    if not scan_dir:
+        parser.print_help()
+        sys.exit(1)
+
+    scan_path = Path(scan_dir)
+    if scan_path.is_dir():
+        jsonl_files = sorted(scan_path.rglob("*.jsonl"))
+        print(f"Scanning {len(jsonl_files)} files in {scan_dir}...", file=sys.stderr)
+        for fpath in jsonl_files:
+            pairs = extract_from_jsonl_file(
+                str(fpath),
+                min_ratio=args.min_ratio,
+                min_response_words=args.min_words
+            )
+            all_pairs.extend(pairs)
+            files_scanned += 1
+    else:
+        pairs = extract_from_jsonl_file(
+            str(scan_path),
+            min_ratio=args.min_ratio,
+            min_response_words=args.min_words
+        )
+        all_pairs.extend(pairs)
+        files_scanned = 1
+
+    # Deduplicate
+    unique_pairs = deduplicate_pairs(all_pairs)
+
+    # Stats
+    if unique_pairs:
+        avg_prompt = sum(p["prompt_words"] for p in unique_pairs) / len(unique_pairs)
+        avg_response = sum(p["response_words"] for p in unique_pairs) / len(unique_pairs)
+        avg_ratio = sum(p["ratio"] for p in unique_pairs) / len(unique_pairs)
+    else:
+        avg_prompt = avg_response = avg_ratio = 0
+
+    stats = {
+        "files_scanned": files_scanned,
+        "raw_pairs": len(all_pairs),
+        "unique_pairs": len(unique_pairs),
+        "duplicates_removed": len(all_pairs) - len(unique_pairs),
+        "avg_prompt_words": round(avg_prompt, 1),
+        "avg_response_words": round(avg_response, 1),
+        "avg_ratio": round(avg_ratio, 2),
+    }
+
+    print(json.dumps(stats, indent=2), file=sys.stderr)
+
+    if args.dry_run:
+        # Print sample pairs
+        for pair in unique_pairs[:3]:
+            print(f"\n--- Source: {pair['source']} (ratio: {pair['ratio']}) ---", file=sys.stderr)
+            print(f"TERSE: {pair['terse'][:100]}...", file=sys.stderr)
+            print(f"RICH: {pair['rich'][:150]}...", file=sys.stderr)
+        return
+
+    # Write output
+    output_path = Path(args.output)
+    with open(output_path, "w") as f:
+        for pair in unique_pairs:
+            # Strip internal fields for output
+            output = {
+                "terse": pair["terse"],
+                "rich": pair["rich"],
+                "source": pair["source"],
+                "model": pair["model"],
+            }
+            f.write(json.dumps(output) + "\n")
+
+    print(f"\nWrote {len(unique_pairs)} pairs to {output_path}", file=sys.stderr)
+
+
+if __name__ == "__main__":
+    main()

scripts/test_session_pair_harvester.py

@@ -0,0 +1,90 @@
+#!/usr/bin/env python3
+"""Tests for session_pair_harvester."""
+
+import json
+import sys
+import os
+import tempfile
+
+sys.path.insert(0, os.path.dirname(__file__))
+from session_pair_harvester import extract_pairs_from_session, deduplicate_pairs, compute_hash
+
+
+def test_basic_extraction():
+    session = {
+        "id": "test_001",
+        "model": "test-model",
+        "conversations": [
+            {"from": "system", "value": "You are helpful."},
+            {"from": "human", "value": "What is Python?"},
+            {"from": "gpt", "value": "Python is a high-level programming language known for its readability and versatility. It supports multiple paradigms including procedural, object-oriented, and functional programming. Python is widely used in web development, data science, machine learning, and automation."},
+        ]
+    }
+    pairs = extract_pairs_from_session(session, min_ratio=1.5, min_response_words=10)
+    assert len(pairs) == 1
+    assert pairs[0]["terse"] == "What is Python?"
+    assert "programming language" in pairs[0]["rich"]
+    assert pairs[0]["source"] == "test_001"
+    print("PASS: test_basic_extraction")
+
+
+def test_filters_short_responses():
+    session = {
+        "id": "test_002",
+        "model": "test",
+        "conversations": [
+            {"from": "human", "value": "Hi"},
+            {"from": "gpt", "value": "Hello!"},
+        ]
+    }
+    pairs = extract_pairs_from_session(session, min_ratio=1.5, min_response_words=20)
+    assert len(pairs) == 0
+    print("PASS: test_filters_short_responses")
+
+
+def test_skips_tool_results():
+    session = {
+        "id": "test_003",
+        "model": "test",
+        "conversations": [
+            {"from": "human", "value": '{"output": "file content", "exit_code": 0}'},
+            {"from": "gpt", "value": "The file was read successfully. Now let me analyze the content and provide a detailed summary of what was found in the file system."},
+        ]
+    }
+    pairs = extract_pairs_from_session(session, min_ratio=1.5, min_response_words=10)
+    assert len(pairs) == 0
+    print("PASS: test_skips_tool_results")
+
+
+def test_deduplication():
+    pairs = [
+        {"terse": "What is X?", "rich": "X is Y.", "source": "s1", "model": "m"},
+        {"terse": "What is X?", "rich": "X is Y.", "source": "s2", "model": "m"},
+        {"terse": "What is Z?", "rich": "Z is W.", "source": "s1", "model": "m"},
+    ]
+    unique = deduplicate_pairs(pairs)
+    assert len(unique) == 2
+    print("PASS: test_deduplication")
+
+
+def test_ratio_filter():
+    session = {
+        "id": "test_005",
+        "model": "test",
+        "conversations": [
+            {"from": "human", "value": "Explain quantum computing in detail with examples and applications"},
+            {"from": "gpt", "value": "OK."},
+        ]
+    }
+    pairs = extract_pairs_from_session(session, min_ratio=1.5, min_response_words=10)
+    assert len(pairs) == 0  # response too short relative to prompt
+    print("PASS: test_ratio_filter")
+
+
+if __name__ == "__main__":
+    test_basic_extraction()
+    test_filters_short_responses()
+    test_skips_tool_results()
+    test_deduplication()
+    test_ratio_filter()
+    print("\nAll tests passed.")