refactor: consolidate shared regex patterns and token validation

- Create src/utils/regex-patterns.ts with ANSI_ESCAPE_PATTERN_FULL,
  ANSI_ESCAPE_PATTERN_SIMPLE, TOKEN_PATTERN, and helper functions
- Create src/utils/token-validation.ts with MAX_SESSION_TOKENS and
  validation utilities
- Update session.ts, respawn-controller.ts, ai-checker-base.ts,
  ralph-tracker.ts, state-store.ts to use shared utilities
- Export all new utilities from src/utils/index.ts

Reduces code duplication while maintaining pre-compiled patterns
for performance.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
arkon
2026-01-29 10:55:49 +01:00
co-authored by Claude Opus 4.5
parent 451f0854eb
commit 6c07541288
10 changed files with 187 additions and 45 deletions
+14
View File
@@ -10,3 +10,17 @@ export { BufferAccumulator } from './buffer-accumulator.js';
export { LRUMap, type LRUMapOptions } from './lru-map.js';
export { CleanupManager, type TimerOptions } from './cleanup-manager.js';
export { StaleExpirationMap, type StaleExpirationMapOptions } from './stale-expiration-map.js';
export {
ANSI_ESCAPE_PATTERN_FULL,
ANSI_ESCAPE_PATTERN_SIMPLE,
TOKEN_PATTERN,
createAnsiPatternFull,
createAnsiPatternSimple,
stripAnsi,
stripAnsiSimple,
} from './regex-patterns.js';
export {
MAX_SESSION_TOKENS,
validateTokenCounts,
validateTokensAndCost,
} from './token-validation.js';
+73
View File
@@ -0,0 +1,73 @@
/**
* @fileoverview Shared regex patterns for terminal and token parsing.
*
* Pre-compiled patterns avoid re-compilation overhead on each use.
* Import these patterns instead of defining them locally.
*
* @module utils/regex-patterns
*/
/**
* Comprehensive ANSI escape pattern that handles:
* - SGR (colors/styles): ESC [ params m
* - CSI sequences (cursor, scroll, etc.): ESC [ params letter
* - OSC sequences (title, etc.): ESC ] ... BEL or ESC ] ... ST
* - Single-char escapes: ESC = or ESC >
*
* Use this when you need complete ANSI stripping including OSC sequences.
* Note: Has global flag - reset lastIndex before exec() if reusing.
*/
export const ANSI_ESCAPE_PATTERN_FULL = /\x1b(?:\[[0-9;?]*[A-Za-z]|\][^\x07\x1b]*(?:\x07|\x1b\\)|[=>])/g;
/**
* Simple ANSI CSI-only pattern for basic escape code stripping.
* Matches: ESC [ params letter (e.g., colors, cursor movement)
*
* Use this for faster stripping when OSC sequences aren't a concern.
* Note: Has global flag - reset lastIndex before exec() if reusing.
*/
export const ANSI_ESCAPE_PATTERN_SIMPLE = /\x1b\[[0-9;]*[A-Za-z]/g;
/**
* Pattern to extract token count from Claude's status line.
* Matches: "123.4k tokens", "5234 tokens", "1.2M tokens"
*
* Capture groups:
* - Group 1: The numeric value (e.g., "123.4", "5234", "1.2")
* - Group 2: Optional suffix (k, K, m, M) or undefined
*/
export const TOKEN_PATTERN = /(\d+(?:\.\d+)?)\s*([kKmM])?\s*tokens/;
/**
* Creates a fresh copy of ANSI_ESCAPE_PATTERN_FULL.
* Use when you need a pattern without shared lastIndex state.
*/
export function createAnsiPatternFull(): RegExp {
return /\x1b(?:\[[0-9;?]*[A-Za-z]|\][^\x07\x1b]*(?:\x07|\x1b\\)|[=>])/g;
}
/**
* Creates a fresh copy of ANSI_ESCAPE_PATTERN_SIMPLE.
* Use when you need a pattern without shared lastIndex state.
*/
export function createAnsiPatternSimple(): RegExp {
return /\x1b\[[0-9;]*[A-Za-z]/g;
}
/**
* Strips ANSI escape codes from text using the comprehensive pattern.
* @param text - Text containing ANSI escape codes
* @returns Text with ANSI codes removed
*/
export function stripAnsi(text: string): string {
return text.replace(ANSI_ESCAPE_PATTERN_FULL, '');
}
/**
* Strips simple ANSI CSI codes from text (faster, less comprehensive).
* @param text - Text containing ANSI escape codes
* @returns Text with ANSI CSI codes removed
*/
export function stripAnsiSimple(text: string): string {
return text.replace(ANSI_ESCAPE_PATTERN_SIMPLE, '');
}
+72
View File
@@ -0,0 +1,72 @@
/**
* @fileoverview Token validation utilities.
*
* Centralizes token count validation logic used across the codebase.
* Claude's context window is ~200k tokens, so 500k is a generous upper bound.
*
* @module utils/token-validation
*/
/**
* Maximum tokens allowed per session.
* Claude's context is ~200k, so 500k is a safe upper bound for validation.
*/
export const MAX_SESSION_TOKENS = 500_000;
/**
* Validates token counts are within acceptable bounds.
* Rejects negative values and values exceeding MAX_SESSION_TOKENS.
*
* @param inputTokens - Input token count to validate
* @param outputTokens - Output token count to validate
* @returns Object with isValid flag and optional error reason
*/
export function validateTokenCounts(
inputTokens: number,
outputTokens: number
): { isValid: boolean; reason?: string } {
if (inputTokens < 0 || outputTokens < 0) {
return {
isValid: false,
reason: `Negative token values: input=${inputTokens}, output=${outputTokens}`,
};
}
if (inputTokens > MAX_SESSION_TOKENS || outputTokens > MAX_SESSION_TOKENS) {
return {
isValid: false,
reason: `Token values exceed maximum (${MAX_SESSION_TOKENS}): input=${inputTokens}, output=${outputTokens}`,
};
}
return { isValid: true };
}
/**
* Validates token counts and cost for restoration/persistence.
* Returns true if all values are valid.
*
* @param inputTokens - Input token count
* @param outputTokens - Output token count
* @param cost - Cost value (must be non-negative)
* @returns Object with isValid flag and optional error reason
*/
export function validateTokensAndCost(
inputTokens: number,
outputTokens: number,
cost: number
): { isValid: boolean; reason?: string } {
const tokenValidation = validateTokenCounts(inputTokens, outputTokens);
if (!tokenValidation.isValid) {
return tokenValidation;
}
if (cost < 0) {
return {
isValid: false,
reason: `Negative cost value: ${cost}`,
};
}
return { isValid: true };
}