mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-02-14 02:42:04 +08:00
feat: 添加令牌消耗诊断功能，优化输出和状态管理
This commit is contained in:
catlog22
@@ -93,6 +93,14 @@
|
||||
"detection_focus": null,
|
||||
"needs_gemini_analysis": true,
|
||||
"priority_order": [1, 2, 3, 4]
|
||||
},
|
||||
"token_consumption": {
|
||||
"pattern_ids": ["TKN-001", "TKN-002", "TKN-003", "TKN-004", "TKN-005"],
|
||||
"severity_hint": "medium",
|
||||
"strategies": ["prompt_compression", "lazy_loading", "output_minimization", "state_field_reduction", "sliding_window"],
|
||||
"risk_levels": ["low", "low", "low", "low", "low"],
|
||||
"detection_focus": "Verbose prompts, excessive state fields, full content passing, unbounded arrays, redundant I/O",
|
||||
"priority_order": [1, 2, 3, 4, 5]
|
||||
}
|
||||
},
|
||||
"keywords": {
|
||||
@@ -149,7 +157,12 @@
|
||||
"中间文件": "authoring_principles_violation",
|
||||
"临时文件": "authoring_principles_violation",
|
||||
"文件中转": "authoring_principles_violation",
|
||||
"state膨胀": "authoring_principles_violation"
|
||||
"state膨胀": "authoring_principles_violation",
|
||||
"token消耗": "token_consumption",
|
||||
"token优化": "token_consumption",
|
||||
"产出简化": "token_consumption",
|
||||
"冗长": "token_consumption",
|
||||
"精简": "token_consumption"
|
||||
},
|
||||
"english": {
|
||||
"token": "context_explosion",
|
||||
@@ -198,7 +211,12 @@
|
||||
"feedback": "user_experience",
|
||||
"intermediate": "authoring_principles_violation",
|
||||
"temp": "authoring_principles_violation",
|
||||
"relay": "authoring_principles_violation"
|
||||
"relay": "authoring_principles_violation",
|
||||
"verbose": "token_consumption",
|
||||
"minimize": "token_consumption",
|
||||
"compress": "token_consumption",
|
||||
"simplify": "token_consumption",
|
||||
"reduction": "token_consumption"
|
||||
}
|
||||
},
|
||||
"category_labels": {
|
||||
@@ -213,6 +231,7 @@
|
||||
"output_quality": "Output Quality",
|
||||
"user_experience": "User Experience",
|
||||
"authoring_principles_violation": "Authoring Principles Violation",
|
||||
"token_consumption": "Token Consumption",
|
||||
"custom": "Custom"
|
||||
},
|
||||
"category_labels_chinese": {
|
||||
@@ -227,6 +246,7 @@
|
||||
"output_quality": "Output Quality",
|
||||
"user_experience": "User Experience",
|
||||
"authoring_principles_violation": "Authoring Principles Violation",
|
||||
"token_consumption": "Token Consumption Optimization",
|
||||
"custom": "Other Issues"
|
||||
},
|
||||
"category_descriptions": {
|
||||
@@ -241,12 +261,13 @@
|
||||
"output_quality": "Output validation or completeness issues",
|
||||
"user_experience": "Interaction or feedback clarity issues",
|
||||
"authoring_principles_violation": "Violation of skill authoring principles",
|
||||
"token_consumption": "Excessive token usage from verbose prompts, large state objects, or redundant I/O patterns",
|
||||
"custom": "Requires custom analysis"
|
||||
},
|
||||
"fix_priority_order": {
|
||||
"P0": ["dataflow_break", "authoring_principles_violation"],
|
||||
"P1": ["agent_failure"],
|
||||
"P2": ["context_explosion"],
|
||||
"P2": ["context_explosion", "token_consumption"],
|
||||
"P3": ["memory_loss"]
|
||||
},
|
||||
"cross_category_dependencies": {
|
||||
|
||||
@@ -180,7 +180,35 @@ Classification of skill execution issues with detection patterns and severity cr
|
||||
|
||||
---
|
||||
|
||||
### 6. Documentation Conflict (P6)
|
||||
### 6. Token Consumption (P6)
|
||||
|
||||
**Definition**: Excessive token usage from verbose prompts, large state objects, or inefficient I/O patterns.
|
||||
|
||||
**Root Causes**:
|
||||
- Long static prompts without compression
|
||||
- State schema with too many fields
|
||||
- Full content embedding instead of path references
|
||||
- Arrays growing unbounded without sliding windows
|
||||
- Write-then-read file relay patterns
|
||||
|
||||
**Detection Patterns**:
|
||||
|
||||
| Pattern ID | Regex/Check | Description |
|
||||
|------------|-------------|-------------|
|
||||
| TKN-001 | File size > 4KB | Verbose prompt files |
|
||||
| TKN-002 | State fields > 15 | Excessive state schema |
|
||||
| TKN-003 | `/Read\([^)]+\)\s*[\+,]/` | Full content passing |
|
||||
| TKN-004 | `/.push\|concat(?!.*\.slice)/` | Unbounded array growth |
|
||||
| TKN-005 | `/Write\([^)]+\)[\s\S]{0,100}Read\([^)]+\)/` | Write-then-read pattern |
|
||||
|
||||
**Impact Levels**:
|
||||
- **High**: Multiple TKN-003/TKN-004 issues causing significant token waste
|
||||
- **Medium**: Several verbose files or state bloat
|
||||
- **Low**: Minor optimization opportunities
|
||||
|
||||
---
|
||||
|
||||
### 7. Documentation Conflict (P7)
|
||||
|
||||
**Definition**: 同一概念在不同文件中定义不一致，导致行为不可预测和文档误导。
|
||||
|
||||
@@ -262,6 +290,7 @@ function calculateIssueSeverity(issue) {
|
||||
| Long-tail Forgetting | constraint_injection, state_constraints_field, checkpoint | 1, 2, 3 |
|
||||
| Data Flow Disruption | state_centralization, schema_enforcement, field_normalization | 1, 2, 3 |
|
||||
| Agent Coordination | error_wrapping, result_validation, flatten_nesting | 1, 2, 3 |
|
||||
| **Token Consumption** | prompt_compression, lazy_loading, output_minimization, state_field_reduction | 1, 2, 3, 4 |
|
||||
| **Documentation Redundancy** | consolidate_to_ssot, centralize_mapping_config | 1, 2 |
|
||||
| **Documentation Conflict** | reconcile_conflicting_definitions | 1 |
|
||||
|
||||
|
||||
@@ -1308,3 +1308,230 @@ async function checkpoint(name, summary, options) {
|
||||
return response;
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Token Consumption Strategies
|
||||
|
||||
Strategies for reducing token usage and simplifying skill outputs.
|
||||
|
||||
---
|
||||
|
||||
### Strategy: prompt_compression
|
||||
|
||||
**Purpose**: Reduce verbose prompts by extracting static text and using templates.
|
||||
|
||||
**Implementation**:
|
||||
```javascript
|
||||
// Before: Long inline prompt
|
||||
const prompt = `
|
||||
You are an expert code analyzer specializing in identifying patterns.
|
||||
Your role is to examine the provided code and identify any issues.
|
||||
Please follow these detailed instructions carefully:
|
||||
1. Read the code thoroughly
|
||||
2. Identify any anti-patterns
|
||||
3. Check for security vulnerabilities
|
||||
... (continues for many lines)
|
||||
|
||||
Code to analyze:
|
||||
${fullCodeContent}
|
||||
`;
|
||||
|
||||
// After: Compressed with template reference
|
||||
const PROMPT_TEMPLATE_PATH = 'templates/analyzer-prompt.md';
|
||||
|
||||
const prompt = `
|
||||
[TEMPLATE: ${PROMPT_TEMPLATE_PATH}]
|
||||
[CODE_PATH: ${codePath}]
|
||||
[FOCUS: patterns, security]
|
||||
`;
|
||||
|
||||
// Or use key instructions only
|
||||
const prompt = `
|
||||
Analyze ${codePath} for: patterns, security, performance.
|
||||
Return JSON: { issues: [], severity: string }
|
||||
`;
|
||||
```
|
||||
|
||||
**Risk**: Low
|
||||
**Verification**: Compare token count before/after compression
|
||||
|
||||
---
|
||||
|
||||
### Strategy: lazy_loading
|
||||
|
||||
**Purpose**: Pass file paths instead of full content, let consumers load if needed.
|
||||
|
||||
**Implementation**:
|
||||
```javascript
|
||||
// Before: Full content in prompt
|
||||
const content = Read(filePath);
|
||||
const prompt = `Analyze this content:\n${content}`;
|
||||
|
||||
// After: Path reference with lazy loading instruction
|
||||
const prompt = `
|
||||
Analyze file at: ${filePath}
|
||||
(Read the file content if you need to examine it)
|
||||
Return: { summary: string, issues: [] }
|
||||
`;
|
||||
|
||||
// For agent calls
|
||||
const result = await Task({
|
||||
subagent_type: 'universal-executor',
|
||||
prompt: `
|
||||
[FILE_PATH]: ${dataPath}
|
||||
[TASK]: Analyze the file and extract key metrics.
|
||||
[NOTE]: Read the file only if needed for your analysis.
|
||||
`
|
||||
});
|
||||
```
|
||||
|
||||
**Risk**: Low
|
||||
**Verification**: Verify agents can still access required data
|
||||
|
||||
---
|
||||
|
||||
### Strategy: output_minimization
|
||||
|
||||
**Purpose**: Configure agents to return minimal, structured output instead of verbose text.
|
||||
|
||||
**Implementation**:
|
||||
```javascript
|
||||
// Before: Verbose output expectation
|
||||
const prompt = `
|
||||
Analyze the code and provide a detailed report including:
|
||||
- Executive summary
|
||||
- Detailed findings with explanations
|
||||
- Code examples for each issue
|
||||
- Recommendations with rationale
|
||||
...
|
||||
`;
|
||||
|
||||
// After: Minimal structured output
|
||||
const prompt = `
|
||||
Analyze the code. Return ONLY this JSON:
|
||||
{
|
||||
"status": "pass|review|fail",
|
||||
"issues": [{ "id": string, "severity": string, "file": string, "line": number }],
|
||||
"summary": "one sentence"
|
||||
}
|
||||
Do not include explanations or code examples.
|
||||
`;
|
||||
|
||||
// Validation
|
||||
const result = JSON.parse(agentOutput);
|
||||
if (!result.status || !Array.isArray(result.issues)) {
|
||||
throw new Error('Invalid output format');
|
||||
}
|
||||
```
|
||||
|
||||
**Risk**: Low
|
||||
**Verification**: JSON.parse succeeds, output size reduced
|
||||
|
||||
---
|
||||
|
||||
### Strategy: state_field_reduction
|
||||
|
||||
**Purpose**: Audit and consolidate state fields to minimize serialization overhead.
|
||||
|
||||
**Implementation**:
|
||||
```typescript
|
||||
// Before: Bloated state
|
||||
interface State {
|
||||
status: string;
|
||||
target: TargetInfo;
|
||||
user_input: string;
|
||||
parsed_input: ParsedInput; // Remove - temporary
|
||||
intermediate_result: any; // Remove - not persisted
|
||||
debug_info: DebugInfo; // Remove - debugging only
|
||||
analysis_cache: any; // Remove - session cache
|
||||
full_history: HistoryEntry[]; // Remove - unbounded
|
||||
step1_output: any; // Remove - intermediate
|
||||
step2_output: any; // Remove - intermediate
|
||||
step3_output: any; // Remove - intermediate
|
||||
final_result: FinalResult;
|
||||
error_log: string[]; // Remove - debugging
|
||||
metrics: Metrics; // Remove - optional
|
||||
}
|
||||
|
||||
// After: Minimal state (≤15 fields)
|
||||
interface State {
|
||||
status: 'pending' | 'running' | 'completed' | 'failed';
|
||||
target: { name: string; path: string };
|
||||
input_summary: string; // Summarized user input
|
||||
result_path: string; // Path to final result
|
||||
quality_gate: 'pass' | 'fail';
|
||||
error?: string; // Only if failed
|
||||
}
|
||||
```
|
||||
|
||||
**Audit Checklist**:
|
||||
```javascript
|
||||
function auditStateFields(stateSchema) {
|
||||
const removeCandidates = [];
|
||||
|
||||
for (const [key, type] of Object.entries(stateSchema)) {
|
||||
// Identify removal candidates
|
||||
if (key.startsWith('debug_')) removeCandidates.push(key);
|
||||
if (key.endsWith('_cache')) removeCandidates.push(key);
|
||||
if (key.endsWith('_temp')) removeCandidates.push(key);
|
||||
if (key.includes('intermediate')) removeCandidates.push(key);
|
||||
if (key.includes('step') && key.includes('output')) removeCandidates.push(key);
|
||||
}
|
||||
|
||||
return {
|
||||
total_fields: Object.keys(stateSchema).length,
|
||||
remove_candidates: removeCandidates,
|
||||
estimated_reduction: removeCandidates.length
|
||||
};
|
||||
}
|
||||
```
|
||||
|
||||
**Risk**: Medium (ensure no essential data removed)
|
||||
**Verification**: State field count ≤ 15, all essential data preserved
|
||||
|
||||
---
|
||||
|
||||
### Strategy: in_memory_consolidation
|
||||
|
||||
**Purpose**: Consolidate outputs into single file, eliminate redundant report files.
|
||||
|
||||
**Implementation**:
|
||||
```javascript
|
||||
// Before: Multiple output files
|
||||
Write(`${workDir}/diagnosis-report.md`, reportMarkdown);
|
||||
Write(`${workDir}/diagnosis-summary.json`, summaryJson);
|
||||
Write(`${workDir}/state.json`, JSON.stringify(state));
|
||||
Write(`${workDir}/tuning-report.md`, tuningReport);
|
||||
Write(`${workDir}/tuning-summary.md`, finalSummary);
|
||||
|
||||
// After: Single source of truth
|
||||
const consolidatedState = {
|
||||
...state,
|
||||
final_report: {
|
||||
summary: summaryJson,
|
||||
details_available_in_state: true,
|
||||
generated_at: new Date().toISOString()
|
||||
}
|
||||
};
|
||||
Write(`${workDir}/state.json`, JSON.stringify(consolidatedState, null, 2));
|
||||
|
||||
// Report can be rendered from state on-demand
|
||||
function renderReport(state) {
|
||||
return `
|
||||
# Tuning Report: ${state.target_skill.name}
|
||||
Status: ${state.status}
|
||||
Quality: ${state.quality_gate}
|
||||
Issues: ${state.issues.length}
|
||||
...
|
||||
`;
|
||||
}
|
||||
```
|
||||
|
||||
**Benefits**:
|
||||
- Single file to read/write
|
||||
- No data duplication
|
||||
- On-demand rendering
|
||||
|
||||
**Risk**: Low
|
||||
**Verification**: Only state.json exists as output, rendering works correctly
|
||||
|
||||
Reference in New Issue
Block a user