[loop-cycle-947] refactor: break up self_reflect() into focused helpers (#505) (#546)

src/timmy/session_logger.py

@@ -323,6 +323,75 @@ def session_history(query: str, role: str = "", limit: int = 10) -> str:
 _LOW_CONFIDENCE_THRESHOLD = 0.5
 
 
+def _categorize_entries(
+    entries: list[dict],
+) -> tuple[list[dict], list[dict], list[dict], list[dict]]:
+    """Split session entries into messages, errors, timmy msgs, user msgs."""
+    messages = [e for e in entries if e.get("type") == "message"]
+    errors = [e for e in entries if e.get("type") == "error"]
+    timmy_msgs = [e for e in messages if e.get("role") == "timmy"]
+    user_msgs = [e for e in messages if e.get("role") == "user"]
+    return messages, errors, timmy_msgs, user_msgs
+
+
+def _find_low_confidence(timmy_msgs: list[dict]) -> list[dict]:
+    """Return Timmy responses below the confidence threshold."""
+    return [
+        m
+        for m in timmy_msgs
+        if m.get("confidence") is not None and m["confidence"] < _LOW_CONFIDENCE_THRESHOLD
+    ]
+
+
+def _find_repeated_topics(user_msgs: list[dict], top_n: int = 5) -> list[tuple[str, int]]:
+    """Identify frequently mentioned words in user messages."""
+    topic_counts: dict[str, int] = {}
+    for m in user_msgs:
+        for word in (m.get("content") or "").lower().split():
+            cleaned = word.strip(".,!?\"'()[]")
+            if len(cleaned) > 3:
+                topic_counts[cleaned] = topic_counts.get(cleaned, 0) + 1
+    return sorted(
+        ((w, c) for w, c in topic_counts.items() if c >= 3),
+        key=lambda x: x[1],
+        reverse=True,
+    )[:top_n]
+
+
+def _format_reflection_section(
+    title: str,
+    items: list[dict],
+    formatter: object,
+    empty_msg: str,
+) -> list[str]:
+    """Format a titled section with items, or an empty-state message."""
+    if items:
+        lines = [f"### {title} ({len(items)})"]
+        for item in items[:5]:
+            lines.append(formatter(item))  # type: ignore[operator]
+        lines.append("")
+        return lines
+    return [f"### {title}\n{empty_msg}\n"]
+
+
+def _build_insights(
+    low_conf: list[dict],
+    errors: list[dict],
+    repeated: list[tuple[str, int]],
+) -> list[str]:
+    """Generate actionable insight bullets from analysis results."""
+    insights: list[str] = []
+    if low_conf:
+        insights.append("Consider studying topics where confidence was low.")
+    if errors:
+        insights.append("Review error patterns for recurring infrastructure issues.")
+    if repeated:
+        insights.append(
+            f'User frequently asks about "{repeated[0][0]}" — consider deepening knowledge here.'
+        )
+    return insights or ["Conversations look healthy. Keep up the good work."]
+
+
 def self_reflect(limit: int = 30) -> str:
     """Review recent conversations and reflect on Timmy's own behavior.
 
@@ -343,35 +412,12 @@ def self_reflect(limit: int = 30) -> str:
     if not entries:
         return "No conversation history to reflect on yet."
 
-    # Categorize entries
-    messages = [e for e in entries if e.get("type") == "message"]
-    errors = [e for e in entries if e.get("type") == "error"]
-    timmy_msgs = [e for e in messages if e.get("role") == "timmy"]
-    user_msgs = [e for e in messages if e.get("role") == "user"]
-
-    # 1. Low-confidence responses
-    low_conf = [
-        m
-        for m in timmy_msgs
-        if m.get("confidence") is not None and m["confidence"] < _LOW_CONFIDENCE_THRESHOLD
-    ]
-
-    # 2. Identify repeated user topics (simple word frequency)
-    topic_counts: dict[str, int] = {}
-    for m in user_msgs:
-        for word in (m.get("content") or "").lower().split():
-            cleaned = word.strip(".,!?\"'()[]")
-            if len(cleaned) > 3:
-                topic_counts[cleaned] = topic_counts.get(cleaned, 0) + 1
-    repeated = sorted(
-        ((w, c) for w, c in topic_counts.items() if c >= 3),
-        key=lambda x: x[1],
-        reverse=True,
-    )[:5]
+    _messages, errors, timmy_msgs, user_msgs = _categorize_entries(entries)
+    low_conf = _find_low_confidence(timmy_msgs)
+    repeated = _find_repeated_topics(user_msgs)
 
     # Build reflection report
     sections: list[str] = ["## Self-Reflection Report\n"]
-
     sections.append(
         f"Reviewed {len(entries)} recent entries: "
         f"{len(user_msgs)} user messages, "
@@ -379,32 +425,27 @@ def self_reflect(limit: int = 30) -> str:
         f"{len(errors)} errors.\n"
     )
 
-    # Low confidence
-    if low_conf:
-        sections.append(f"### Low-Confidence Responses ({len(low_conf)})")
-        for m in low_conf[:5]:
-            ts = (m.get("timestamp") or "?")[:19]
-            conf = m.get("confidence", 0)
-            text = (m.get("content") or "")[:120]
-            sections.append(f"- [{ts}] confidence={conf:.0%}: {text}")
-        sections.append("")
-    else:
-        sections.append(
-            "### Low-Confidence Responses\nNone found — all responses above threshold.\n"
+    sections.extend(
+        _format_reflection_section(
+            "Low-Confidence Responses",
+            low_conf,
+            lambda m: (
+                f"- [{(m.get('timestamp') or '?')[:19]}] "
+                f"confidence={m.get('confidence', 0):.0%}: "
+                f"{(m.get('content') or '')[:120]}"
+            ),
+            "None found — all responses above threshold.",
         )
+    )
+    sections.extend(
+        _format_reflection_section(
+            "Errors",
+            errors,
+            lambda e: f"- [{(e.get('timestamp') or '?')[:19]}] {(e.get('error') or '')[:120]}",
+            "No errors recorded.",
+        )
+    )
 
-    # Errors
-    if errors:
-        sections.append(f"### Errors ({len(errors)})")
-        for e in errors[:5]:
-            ts = (e.get("timestamp") or "?")[:19]
-            err = (e.get("error") or "")[:120]
-            sections.append(f"- [{ts}] {err}")
-        sections.append("")
-    else:
-        sections.append("### Errors\nNo errors recorded.\n")
-
-    # Repeated topics
     if repeated:
         sections.append("### Recurring Topics")
         for word, count in repeated:
@@ -413,22 +454,8 @@ def self_reflect(limit: int = 30) -> str:
     else:
         sections.append("### Recurring Topics\nNo strong patterns detected.\n")
 
-    # Actionable summary
-    insights: list[str] = []
-    if low_conf:
-        insights.append("Consider studying topics where confidence was low.")
-    if errors:
-        insights.append("Review error patterns for recurring infrastructure issues.")
-    if repeated:
-        top_topic = repeated[0][0]
-        insights.append(
-            f'User frequently asks about "{top_topic}" — consider deepening knowledge here.'
-        )
-    if not insights:
-        insights.append("Conversations look healthy. Keep up the good work.")
-
     sections.append("### Insights")
-    for insight in insights:
+    for insight in _build_insights(low_conf, errors, repeated):
         sections.append(f"- {insight}")
 
     return "\n".join(sections)