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

scripts/gitea_issue_parser.py

@@ -1,131 +0,0 @@
-#!/usr/bin/env python3
-"""
-Gitea Issue Body Parser — Extract structured data from markdown issue bodies.
-
-Usage:
-    cat issue_body.txt | python3 scripts/gitea_issue_parser.py --stdin --pretty
-    python3 scripts/gitea_issue_parser.py --url https://forge.../api/v1/repos/.../issues/123 --pretty
-    python3 scripts/gitea_issue_parser.py body.txt --title "Fix thing (#42)" --labels pipeline extraction
-"""
-
-import argparse
-import json
-import re
-import sys
-from typing import Dict, List, Any, Optional
-
-
-def parse_issue_body(body: str, title: str = "", labels: List[str] = None) -> Dict[str, Any]:
-    """Parse a Gitea issue markdown body into structured JSON.
-    
-    Extracted fields:
-    - title: Issue title
-    - context: Background/description section
-    - criteria[]: Acceptance criteria (checkboxes or numbered lists)
-    - labels[]: Issue labels
-    - epic_ref: Parent/epic issue reference (from "Closes #N" or title)
-    - sections{}: All ## sections as key-value pairs
-    """
-    result = {
-        "title": title,
-        "context": "",
-        "criteria": [],
-        "labels": labels or [],
-        "epic_ref": None,
-        "sections": {},
-    }
-    
-    if not body:
-        return result
-    
-    # Extract epic reference from title or body
-    epic_patterns = [
-        r"(?:closes|fixes|addresses|refs?)\s+#(\d+)",
-        r"#(\d+)",
-    ]
-    for pattern in epic_patterns:
-        match = re.search(pattern, (title + " " + body).lower())
-        if match:
-            result["epic_ref"] = int(match.group(1))
-            break
-    
-    # Parse ## sections
-    section_pattern = r"^##\s+(.+?)$\n((?:^(?!##\s).*$\n?)*)"
-    for match in re.finditer(section_pattern, body, re.MULTILINE):
-        section_name = match.group(1).strip().lower().replace(" ", "_")
-        section_content = match.group(2).strip()
-        result["sections"][section_name] = section_content
-    
-    # Extract acceptance criteria (checkboxes)
-    checkbox_pattern = r"^\s*-\s*\[([ xX])\]\s*(.+)$"
-    for match in re.finditer(checkbox_pattern, body, re.MULTILINE):
-        checked = match.group(1).lower() == "x"
-        text = match.group(2).strip()
-        result["criteria"].append({"text": text, "checked": checked})
-    
-    # If no checkboxes, try numbered lists in "Acceptance Criteria" or "Criteria" section
-    if not result["criteria"]:
-        for section_name in ["acceptance_criteria", "criteria", "acceptance criteria"]:
-            if section_name in result["sections"]:
-                numbered = r"^\s*\d+\.\s*(.+)$"
-                for match in re.finditer(numbered, result["sections"][section_name], re.MULTILINE):
-                    result["criteria"].append({"text": match.group(1).strip(), "checked": False})
-                break
-    
-    # Extract context (first section or first paragraph before any ## heading)
-    first_heading = body.find("## ")
-    if first_heading > 0:
-        context_text = body[:first_heading].strip()
-    else:
-        context_text = body.split("\n\n")[0].strip()
-    # Clean up: remove "## Context" or "## Problem" header if present
-    context_text = re.sub(r"^#+\s*\w+\s*\n?", "", context_text).strip()
-    result["context"] = context_text[:500]  # Cap at 500 chars
-    
-    return result
-
-
-def fetch_issue_from_url(url: str) -> Dict[str, Any]:
-    """Fetch an issue from a Gitea API URL and parse it."""
-    import urllib.request
-    req = urllib.request.Request(url, headers={"Accept": "application/json"})
-    with urllib.request.urlopen(req) as resp:
-        data = json.loads(resp.read())
-    
-    return parse_issue_body(
-        body=data.get("body", ""),
-        title=data.get("title", ""),
-        labels=[l["name"] for l in data.get("labels", [])]
-    )
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Parse Gitea issue markdown into structured JSON")
-    parser.add_argument("file", nargs="?", help="Issue body file (or use --stdin)")
-    parser.add_argument("--stdin", action="store_true", help="Read from stdin")
-    parser.add_argument("--url", help="Gitea API URL to fetch issue from")
-    parser.add_argument("--title", default="", help="Issue title")
-    parser.add_argument("--labels", nargs="*", default=[], help="Issue labels")
-    parser.add_argument("--pretty", action="store_true", help="Pretty-print JSON output")
-    
-    args = parser.parse_args()
-    
-    if args.url:
-        result = fetch_issue_from_url(args.url)
-    elif args.stdin:
-        body = sys.stdin.read()
-        result = parse_issue_body(body, args.title, args.labels)
-    elif args.file:
-        with open(args.file) as f:
-            body = f.read()
-        result = parse_issue_body(body, args.title, args.labels)
-    else:
-        parser.print_help()
-        sys.exit(1)
-    
-    indent = 2 if args.pretty else None
-    print(json.dumps(result, indent=indent))
-
-
-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_gitea_issue_parser.py

@@ -1,109 +0,0 @@
-#!/usr/bin/env python3
-"""Tests for scripts/gitea_issue_parser.py"""
-
-import sys
-import os
-sys.path.insert(0, os.path.dirname(__file__) or ".")
-
-# Import from sibling
-import importlib.util
-spec = importlib.util.spec_from_file_location("parser", os.path.join(os.path.dirname(__file__) or ".", "gitea_issue_parser.py"))
-mod = importlib.util.module_from_spec(spec)
-spec.loader.exec_module(mod)
-parse_issue_body = mod.parse_issue_body
-
-
-def test_basic_parsing():
-    body = """## Context
-
-This is the background info.
-
-## Acceptance Criteria
-
-- [ ] First criterion
-- [x] Second criterion (done)
-
-## What to build
-
-Some description.
-"""
-    result = parse_issue_body(body, title="Test (#42)", labels=["bug"])
-    assert result["title"] == "Test (#42)"
-    assert result["labels"] == ["bug"]
-    assert result["epic_ref"] == 42
-    assert len(result["criteria"]) == 2
-    assert result["criteria"][0]["text"] == "First criterion"
-    assert result["criteria"][0]["checked"] == False
-    assert result["criteria"][1]["checked"] == True
-    assert "context" in result["sections"]
-    print("PASS: test_basic_parsing")
-
-
-def test_numbered_criteria():
-    body = """## Acceptance Criteria
-
-1. First item
-2. Second item
-3. Third item
-"""
-    result = parse_issue_body(body)
-    assert len(result["criteria"]) == 3
-    assert result["criteria"][0]["text"] == "First item"
-    print("PASS: test_numbered_criteria")
-
-
-def test_epic_ref_from_body():
-    body = "Closes #123\n\nSome description."
-    result = parse_issue_body(body)
-    assert result["epic_ref"] == 123
-    print("PASS: test_epic_ref_from_body")
-
-
-def test_empty_body():
-    result = parse_issue_body("")
-    assert result["criteria"] == []
-    assert result["context"] == ""
-    assert result["sections"] == {}
-    print("PASS: test_empty_body")
-
-
-def test_no_sections():
-    body = "Just a plain issue body with no headings."
-    result = parse_issue_body(body)
-    assert result["context"] == "Just a plain issue body with no headings."
-    print("PASS: test_no_sections")
-
-
-def test_multiple_sections():
-    body = """## Problem
-
-Something is broken.
-
-## Fix
-
-Do this instead.
-
-## Notes
-
-Additional info.
-"""
-    result = parse_issue_body(body)
-    assert "problem" in result["sections"]
-    assert "fix" in result["sections"]
-    assert "notes" in result["sections"]
-    assert "Something is broken" in result["sections"]["problem"]
-    print("PASS: test_multiple_sections")
-
-
-def run_all():
-    test_basic_parsing()
-    test_numbered_criteria()
-    test_epic_ref_from_body()
-    test_empty_body()
-    test_no_sections()
-    test_multiple_sections()
-    print("\nAll 6 tests passed!")
-
-
-if __name__ == "__main__":
-    run_all()

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.")