migrations/009_training_export.sql

@@ -0,0 +1 @@
+ALTER TABLE jobs ADD COLUMN excluded_from_training INTEGER DEFAULT 0;

scripts/db.py

@@ -171,6 +171,7 @@ _MIGRATIONS = [
     ("ats_gap_report",     "TEXT"),   # JSON gap report (free tier)
     ("date_posted",        "TEXT"),   # Original posting date from job board (shadow listing detection)
     ("hired_feedback",           "TEXT"),   # JSON: optional post-hire "what helped" response
+    ("excluded_from_training", "INTEGER DEFAULT 0"),  # opt-out of training export
 ]
 
 
@@ -1142,3 +1143,99 @@ def set_job_resume(db_path: Path = DEFAULT_DB, job_id: int = 0, resume_id: int =
         conn.commit()
     finally:
         conn.close()
+
+# ── Training export helpers ───────────────────────────────────────────────────
+
+def _strip_greeting(text: str) -> str:
+    """Remove 'Dear X,' greeting line from cover letter text."""
+    lines = text.splitlines()
+    for i, line in enumerate(lines):
+        stripped_line = line.strip()
+        if stripped_line.lower().startswith("dear ") and stripped_line.endswith((",", ":")):
+            rest = lines[i + 1:]
+            while rest and not rest[0].strip():
+                rest = rest[1:]
+            result = "\n".join(rest).strip()
+            return result if result else text.strip()
+    return text.strip()
+
+
+def get_db_pairs(db_path: Path) -> list[dict]:
+    """Return curation metadata for ALL qualifying jobs (included and excluded).
+
+    Used by the curation UI. Includes excluded=True rows so users can restore them.
+    """
+    conn = sqlite3.connect(db_path)
+    conn.row_factory = sqlite3.Row
+    try:
+        rows = conn.execute(
+            "SELECT id, title, company, description, status, "
+            "  excluded_from_training "
+            "FROM jobs "
+            "WHERE status IN ('applied','phone_screen','interviewing','offer','hired') "
+            "  AND cover_letter IS NOT NULL AND cover_letter != '' "
+            "ORDER BY applied_at DESC",
+        ).fetchall()
+    finally:
+        conn.close()
+    return [
+        {
+            "job_id":        row["id"],
+            "title":         row["title"] or "",
+            "company":       row["company"] or "",
+            "status":        row["status"],
+            "instruction":   (
+                f"Write a cover letter for the {row['title'] or 'unknown'} "
+                f"position at {row['company'] or 'unknown'}."
+            ),
+            "input_preview": (row["description"] or "")[:200],
+            "excluded":      bool(row["excluded_from_training"]),
+        }
+        for row in rows
+    ]
+
+
+def get_training_pairs(db_path: Path) -> list[dict]:
+    """Return Alpaca-format training pairs for non-excluded qualifying jobs.
+
+    Used by the JSONL export endpoint.
+    """
+    conn = sqlite3.connect(db_path)
+    conn.row_factory = sqlite3.Row
+    try:
+        rows = conn.execute(
+            "SELECT id, title, company, description, cover_letter "
+            "FROM jobs "
+            "WHERE status IN ('applied','phone_screen','interviewing','offer','hired') "
+            "  AND cover_letter IS NOT NULL AND cover_letter != '' "
+            "  AND excluded_from_training = 0 "
+            "ORDER BY applied_at DESC",
+        ).fetchall()
+    finally:
+        conn.close()
+    return [
+        {
+            "instruction": (
+                f"Write a cover letter for the {row['title'] or 'unknown'} "
+                f"position at {row['company'] or 'unknown'}."
+            ),
+            "input":   row["description"] or "",
+            "output":  _strip_greeting(row["cover_letter"]),
+            "source":  "db",
+            "job_id":  row["id"],
+        }
+        for row in rows
+    ]
+
+
+def set_training_exclusion(db_path: Path, job_id: int, excluded: bool) -> None:
+    """Set excluded_from_training flag on a job."""
+    conn = sqlite3.connect(db_path)
+    try:
+        conn.execute(
+            "UPDATE jobs SET excluded_from_training = ? WHERE id = ?",
+            (1 if excluded else 0, job_id),
+        )
+        conn.commit()
+    finally:
+        conn.close()

tests/test_training_export.py

@@ -0,0 +1,122 @@
+"""Tests for cover letter training export helpers."""
+import json
+import sqlite3
+import pytest
+from pathlib import Path
+
+
+def _make_db(tmp_path: Path) -> Path:
+    from scripts.db import init_db
+    db = tmp_path / "test.db"
+    init_db(db)
+    # excluded_from_training column is added by _migrate_db via _MIGRATIONS — no manual ALTER needed
+    return db
+
+
+def _insert_job(db: Path, *, title="Engineer", company="Acme", status="applied",
+                cover_letter="Dear Hiring Manager,\n\nI am excited.", description="Build stuff.",
+                excluded=0) -> int:
+    conn = sqlite3.connect(db)
+    cur = conn.execute(
+        "INSERT INTO jobs (title, company, url, source, location, is_remote, salary, "
+        "description, date_found, status, cover_letter, excluded_from_training) "
+        "VALUES (?,?,?,?,?,?,?,?,?,?,?,?)",
+        (title, company, f"https://example.com/{title}", "test", "Remote", 1, "",
+         description, "2026-01-01", status, cover_letter, excluded),
+    )
+    conn.commit()
+    job_id = cur.lastrowid
+    conn.close()
+    return job_id
+
+
+def test_get_training_pairs_returns_applied_jobs(tmp_path):
+    from scripts.db import get_training_pairs
+    db = _make_db(tmp_path)
+    _insert_job(db, title="Engineer", company="Acme", status="applied")
+    pairs = get_training_pairs(db)
+    assert len(pairs) == 1
+    assert pairs[0]["source"] == "db"
+    assert pairs[0]["instruction"] == "Write a cover letter for the Engineer position at Acme."
+    assert "job_id" in pairs[0]
+
+
+def test_get_training_pairs_strips_greeting(tmp_path):
+    from scripts.db import get_training_pairs
+    db = _make_db(tmp_path)
+    _insert_job(db, cover_letter="Dear Hiring Manager,\n\nI am excited to apply.\n\nSincerely, Me")
+    pairs = get_training_pairs(db)
+    assert not pairs[0]["output"].startswith("Dear")
+    assert "I am excited" in pairs[0]["output"]
+
+
+def test_get_training_pairs_excludes_non_applied(tmp_path):
+    from scripts.db import get_training_pairs
+    db = _make_db(tmp_path)
+    _insert_job(db, title="PendingJob", status="pending")
+    _insert_job(db, title="ApprovedJob", status="approved")
+    pairs = get_training_pairs(db)
+    assert len(pairs) == 0
+
+
+def test_get_training_pairs_excludes_opted_out(tmp_path):
+    from scripts.db import get_training_pairs
+    db = _make_db(tmp_path)
+    _insert_job(db, excluded=1)
+    pairs = get_training_pairs(db)
+    assert len(pairs) == 0
+
+
+def test_get_training_pairs_null_description_gives_empty_input(tmp_path):
+    from scripts.db import get_training_pairs
+    db = _make_db(tmp_path)
+    conn = sqlite3.connect(db)
+    conn.execute(
+        "INSERT INTO jobs (title, company, url, source, location, is_remote, salary, "
+        "date_found, status, cover_letter, excluded_from_training) "
+        "VALUES (?,?,?,?,?,?,?,?,?,?,?)",
+        ("Dev", "Corp", "https://x.com/1", "test", "Remote", 1, "",
+         "2026-01-01", "applied", "Great letter body", 0),
+    )
+    conn.commit()
+    conn.close()
+    pairs = get_training_pairs(db)
+    assert pairs[0]["input"] == ""
+
+
+def test_get_db_pairs_includes_excluded_with_flag(tmp_path):
+    from scripts.db import get_db_pairs
+    db = _make_db(tmp_path)
+    _insert_job(db, excluded=0)
+    _insert_job(db, title="Other", excluded=1)
+    pairs = get_db_pairs(db)
+    assert len(pairs) == 2
+    excluded = [p for p in pairs if p["excluded"]]
+    included = [p for p in pairs if not p["excluded"]]
+    assert len(excluded) == 1
+    assert len(included) == 1
+
+
+def test_set_training_exclusion_excludes(tmp_path):
+    from scripts.db import get_training_pairs, set_training_exclusion
+    db = _make_db(tmp_path)
+    job_id = _insert_job(db)
+    assert len(get_training_pairs(db)) == 1
+    set_training_exclusion(db, job_id, excluded=True)
+    assert len(get_training_pairs(db)) == 0
+
+
+def test_set_training_exclusion_restores(tmp_path):
+    from scripts.db import get_training_pairs, set_training_exclusion
+    db = _make_db(tmp_path)
+    job_id = _insert_job(db, excluded=1)
+    assert len(get_training_pairs(db)) == 0
+    set_training_exclusion(db, job_id, excluded=False)
+    assert len(get_training_pairs(db)) == 1
+
+
+def test_strip_greeting_returns_original_when_no_body(tmp_path):
+    from scripts.db import _strip_greeting
+    # A letter that is only a salutation with no body should return the original text
+    result = _strip_greeting("Dear Hiring Manager,")
+    assert result == "Dear Hiring Manager,"