refactor: split god files into focused modules (phase 4, steps 2-4)

Split 3 large files into 11 focused sub-modules via composition:

ralph-tracker.ts (3,868 → ~2,400 LOC):
- ralph-plan-tracker.ts: plan task tracking, checkpoints, history
- ralph-fix-plan-watcher.ts: @fix_plan.md file watching
- ralph-stall-detector.ts: iteration stall detection
- ralph-status-parser.ts: RALPH_STATUS block parsing, circuit breaker

respawn-controller.ts (3,611 → ~3,200 LOC):
- respawn-patterns.ts: pure pattern detection functions
- respawn-adaptive-timing.ts: adaptive timing with percentile calc
- respawn-metrics.ts: cycle metrics tracking + aggregation
- respawn-health.ts: pure health scoring functions

session.ts (2,418 → ~1,800 LOC):
- session-cli-builder.ts: CLI argument construction
- session-auto-ops.ts: auto-compact/clear automation
- session-task-cache.ts: task description LRU cache

All external APIs preserved via delegation. Events forwarded
through parent classes. Zero behavioral changes — all 436 tests pass.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
arkon
2026-03-01 04:04:35 +01:00
co-authored by Claude Opus 4.6
parent 8d2d51e8f0
commit e7a9cbe442
16 changed files with 4429 additions and 2937 deletions
+14 -11
View File
@@ -110,7 +110,7 @@ journalctl --user -u codeman-web -f
## Import Conventions
- **Utilities**: Import from `./utils` (re-exports all): `import { LRUMap, stripAnsi } from './utils'`
- **Types**: Use type imports: `import type { SessionState } from './types'`
- **Types**: Use type imports from barrel: `import type { SessionState } from './types'` (re-exports from `src/types/` domain files)
- **Config**: Import from specific files: `import { MAX_TERMINAL_BUFFER_SIZE } from './config/buffer-limits'`
## Architecture
@@ -146,16 +146,18 @@ journalctl --user -u codeman-web -f
| `src/session-lifecycle-log.ts` | Append-only JSONL audit log at `~/.codeman/session-lifecycle.jsonl` |
| `src/image-watcher.ts` | Watches for image file creation (screenshots, etc.) |
| `src/file-stream-manager.ts` | Manages `tail -f` processes for live log viewing |
| `src/plan-orchestrator.ts` | Multi-agent plan generation with research and planning phases |
| `src/plan-orchestrator.ts` | 2-agent plan generation: optional research agent → planner agent |
| `src/prompts/index.ts` | Barrel export for all agent prompts |
| `src/prompts/*.ts` | Agent prompts (research-agent, planner) |
| `src/templates/claude-md.ts` | CLAUDE.md generation for new cases |
| `src/tunnel-manager.ts` | Manages cloudflared child process for Cloudflare tunnel remote access |
| `src/cli.ts` | Command-line interface handlers |
| `src/web/server.ts` | Fastify REST API + SSE at `/api/events` (~280 routes) |
| `src/web/server.ts` | Fastify server setup, SSE at `/api/events`, delegates to route modules |
| `src/web/routes/*.ts` | 13 domain route modules (session, respawn, ralph, plan, etc.) — each exports `register*Routes()` |
| `src/web/route-helpers.ts` | Shared helper utilities for route modules |
| `src/web/schemas.ts` | Zod v4 validation schemas with path/env security allowlists |
| `src/web/public/app.js` | Frontend: xterm.js, tab management, subagent windows, mobile support (~15K lines) |
| `src/types.ts` | All TypeScript interfaces (~70 type/interface/enum defs, ~1450 lines) |
| `src/types.ts` | Barrel re-export from `src/types/` — 14 domain files (session, task, respawn, ralph, api, etc.) |
**Large files** (>50KB): `app.js`, `ralph-tracker.ts`, `respawn-controller.ts`, `session.ts`, `subagent-watcher.ts` — these contain complex state machines; read `docs/respawn-state-machine.md` before modifying.
@@ -284,7 +286,7 @@ The frontend is a single ~15K-line vanilla JS file with these key systems:
### API Route Categories
~280 route handlers in `server.ts:buildServer()`. Key groups:
~280 route handlers split across `src/web/routes/` domain modules. Key groups:
| Group | Prefix | Count | Key endpoints |
|-------|--------|-------|---------------|
@@ -302,7 +304,7 @@ The frontend is a single ~15K-line vanilla JS file with these key systems:
## Adding Features
- **API endpoint**: Types in `types.ts`, route in `server.ts:buildServer()`, use `createErrorResponse()`. Validate request bodies with Zod schemas in `schemas.ts`.
- **API endpoint**: Types in `src/types/` (domain file), route in the appropriate `src/web/routes/*-routes.ts` module, use `createErrorResponse()`. Validate request bodies with Zod schemas in `schemas.ts`.
- **SSE event**: Emit via `broadcast()`, handle in `app.js` SSE listener section (search `addListener(`)
- **Session setting**: Add to `SessionState` in `types.ts`, include in `session.toState()`, call `persistSessionState()`
- **Hook event**: Add to `HookEventType` in `types.ts`, add hook command in `hooks-config.ts:generateHooksConfig()`, update `HookEventSchema` in `schemas.ts`
@@ -442,10 +444,11 @@ Use `LRUMap` for bounded caches with eviction, `StaleExpirationMap` for TTL-base
| **Claude Code hooks** | `docs/claude-code-hooks-reference.md` |
| **Terminal anti-flicker** | `docs/terminal-anti-flicker.md` |
| **Agent Teams (experimental)** | `agent-teams/README.md`, `agent-teams/design.md` |
| **API routes** | `src/web/server.ts:buildServer()` or README.md |
| **SSE events** | Search `broadcast(` in `server.ts` |
| **Session statuses** | `SessionStatus` type in `src/types.ts` |
| **Error codes** | `createErrorResponse()` in `src/types.ts` |
| **API routes** | `src/web/routes/` domain modules, or README.md |
| **SSE events** | Search `broadcast(` in `server.ts` and route modules |
| **Session statuses** | `SessionStatus` in `src/types/session.ts` |
| **Error codes** | `createErrorResponse()` in `src/types/api.ts` |
| **Refactoring phases** | `docs/phase1-implementation-plan.md` through `docs/phase-4-domain-splitting-plan.md` |
| **Test utilities** | `test/respawn-test-utils.ts` |
| **Mobile test suite** | `mobile-test/README.md` |
| **OpenCode integration** | `docs/opencode-integration.md` |
@@ -498,7 +501,7 @@ Run `npx vitest run test/memory-leak-prevention.test.ts` to verify patterns.
**Investigating a bug**: Start dev server (`npx tsx src/index.ts web`), reproduce in browser, check terminal output and `~/.codeman/state.json` for clues.
**Adding a new API endpoint**: Define types in `types.ts`, add route in `server.ts:buildServer()`, broadcast SSE events if needed, handle in `app.js:handleSSEEvent()`.
**Adding a new API endpoint**: Define types in the appropriate `src/types/*.ts` domain file, add route in the matching `src/web/routes/*-routes.ts` module, broadcast SSE events if needed, handle in `app.js:handleSSEEvent()`.
**Modifying respawn behavior**: Study `docs/respawn-state-machine.md` first. The state machine is in `respawn-controller.ts`. Use MockSession from `test/respawn-test-utils.ts` for testing.
+788
View File
@@ -0,0 +1,788 @@
# Phase 4: Domain File Splitting — Implementation Plan
**Date**: 2026-03-01
**Prerequisites**: Phase 1-3 complete (utils cleanup, CleanupManager/Debouncer migration, route extraction)
**Goal**: Split 4 god files into focused modules with barrel exports for transparent migration.
---
## Table of Contents
1. [Split types.ts into types/ directory](#1-split-typests-into-types-directory)
2. [Split ralph-tracker.ts into focused modules](#2-split-ralph-trackerts-into-focused-modules)
3. [Split respawn-controller.ts into focused modules](#3-split-respawn-controllerts-into-focused-modules)
4. [Split session.ts into focused modules](#4-split-sessionts-into-focused-modules)
5. [Execution Order & Dependencies](#5-execution-order--dependencies)
6. [Validation Checklist](#6-validation-checklist)
---
## 1. Split types.ts into types/ directory
**Current**: 1,443 lines, 71 exports, imported by 36 files.
**Risk**: LOW — pure type refactor, no runtime behavior change.
### Target Structure
```
src/types/
├── index.ts (barrel re-export — transparent migration)
├── common.ts (Disposable, BufferConfig, CleanupResourceType, CleanupRegistration)
├── session.ts (SessionStatus, SessionMode, ClaudeMode, SessionConfig, SessionColor,
│ SessionState, OpenCodeConfig, SessionOutput)
├── task.ts (TaskStatus, TaskDefinition, TaskState)
├── app-state.ts (AppState, AppConfig, GlobalStats, TokenUsageEntry, TokenStats,
│ DEFAULT_CONFIG, createInitialState, createInitialGlobalStats)
├── respawn.ts (RespawnConfig, PersistedRespawnConfig, CycleOutcome,
│ RespawnCycleMetrics, RespawnAggregateMetrics, HealthStatus,
│ RalphLoopHealthScore, TimingHistory, RespawnPreset)
├── ralph.ts (RalphLoopStatus, RalphLoopState, RalphTodoStatus, RalphTodoPriority,
│ RalphTodoItem, RalphTodoProgress, RalphSessionState,
│ RalphStatusValue, RalphTestsStatus, RalphWorkType, RalphStatusBlock,
│ CompletionConfidence, RalphTrackerState,
│ CircuitBreakerState, CircuitBreakerReason, CircuitBreakerStatus,
│ createInitialCircuitBreakerStatus, createInitialRalphTrackerState,
│ createInitialRalphSessionState)
├── api.ts (ApiErrorCode, ApiResponse, HookEventType, QuickStartResponse,
│ CaseInfo, createErrorResponse, isError, getErrorMessage)
├── lifecycle.ts (LifecycleEventType, LifecycleEntry)
├── run-summary.ts (RunSummaryEventType, RunSummaryEventSeverity, RunSummaryEvent,
│ RunSummaryStats, RunSummary, createInitialRunSummaryStats)
├── tools.ts (ActiveBashToolStatus, ActiveBashTool, ImageDetectedEvent)
├── teams.ts (TeamConfig, TeamMember, TeamTask, InboxMessage, PaneInfo)
├── push.ts (PushSubscriptionRecord, VapidKeys)
└── plan.ts (PlanTaskStatus, TddPhase, PlanItem re-export, NiceConfig,
DEFAULT_NICE_CONFIG, ProcessStats)
```
### Steps
1. **Create `src/types/` directory** and each domain file above.
2. **Move types** from `src/types.ts` into their domain files. Preserve all JSDoc comments. Each file should import from siblings as needed (e.g., `ralph.ts` imports `CircuitBreakerState` within itself — no cross-file deps needed since they're in the same file).
3. **Create barrel `src/types/index.ts`** that re-exports everything:
```typescript
export * from './common.js';
export * from './session.js';
export * from './task.js';
export * from './app-state.js';
export * from './respawn.js';
export * from './ralph.js';
export * from './api.js';
export * from './lifecycle.js';
export * from './run-summary.js';
export * from './tools.js';
export * from './teams.js';
export * from './push.js';
export * from './plan.js';
```
4. **Delete old `src/types.ts`** and replace with a single-line re-export barrel:
```typescript
export * from './types/index.js';
```
This ensures `import { ... } from './types.js'` continues to work everywhere — zero changes to 36 import sites.
5. **Verify**: `tsc --noEmit` and `npm run lint` must pass. No runtime changes.
### Internal Dependencies Between Domain Files
Some types reference others across domains. Handle with imports:
| File | Imports From |
|------|-------------|
| `app-state.ts` | `session.ts` (SessionState), `task.ts` (TaskState), `ralph.ts` (RalphLoopState, RalphSessionState) |
| `respawn.ts` | None (self-contained) |
| `ralph.ts` | None (self-contained) |
| `run-summary.ts` | None (self-contained) |
| `api.ts` | None (self-contained) |
| `session.ts` | `respawn.ts` (RespawnConfig), `ralph.ts` (RalphTrackerState, RalphTodoItem, CircuitBreakerStatus, RalphSessionState, RunSummaryEvent) |
Wait — `SessionState` references `RespawnConfig`, `RalphTrackerState`, `CircuitBreakerStatus`, and `RunSummaryEvent`. This creates imports from `session.ts` → `respawn.ts`, `ralph.ts`, `run-summary.ts`. This is fine (one-way deps, no cycles).
---
## 2. Split ralph-tracker.ts into focused modules
**Current**: 3,868 lines, single `RalphTracker` class with 5 responsibilities.
**Risk**: MEDIUM — class has shared mutable state, but extractable modules are well-isolated.
### Coupling Analysis Summary
| Module | Coupling | Extractability |
|--------|----------|----------------|
| Plan task tracking | LOW | HIGH — only reads `cycleCount` |
| Fix-plan file watching | LOW | HIGH — callback-based todo replacement |
| Iteration stall detection | LOW | HIGH — notification-based |
| RALPH_STATUS block parsing + circuit breaker | MEDIUM | MEDIUM — callback for circuit breaker updates |
| Todo parsing, loop detection, completion | HIGH | LOW — deeply entangled shared state |
### Target Structure
```
src/
├── ralph-tracker.ts (~1,800 LOC — core: output parsing, loop state,
│ todo management, completion detection)
├── ralph-plan-tracker.ts (~600 LOC — plan tasks, checkpoints, history, rollback)
├── ralph-status-parser.ts (~300 LOC — RALPH_STATUS block parsing, circuit breaker)
├── ralph-fix-plan-watcher.ts (~150 LOC — @fix_plan.md file watching)
└── ralph-stall-detector.ts (~80 LOC — iteration stall detection)
```
### Step 2a: Extract `RalphPlanTracker` (~600 LOC)
**Why first**: Lowest coupling. Only dependency is `cycleCount` for checkpoint detection.
**Extract these from `RalphTracker`**:
Types to export:
- `EnhancedPlanTask` (interface, currently lines 56-87)
- `CheckpointReview` (interface, currently lines 90-139)
Properties to move:
- `_planVersion: number`
- `_planHistory: Array<{version, timestamp, tasks, summary}>`
- `_planTasks: Map<string, EnhancedPlanTask>`
- `_checkpointIterations: number[]`
- `_lastCheckpointIteration: number`
Methods to move:
- `initializePlanTasks(items)`
- `updatePlanTask(taskId, update)`
- `addPlanTask(params)`
- `getPlanTasks()`
- `generateCheckpointReview()`
- `getPlanHistory()`
- `rollbackToVersion(version)`
- `isCheckpointDue()`
- `planVersion` getter
- `_savePlanToHistory()` (private)
- `_unblockDependentTasks()` (private)
- `_checkForCheckpoint()` (private)
Events emitted (define in new class):
- `planInitialized`
- `planTaskUpdate`
- `taskBlocked`
- `taskUnblocked`
- `planCheckpoint`
**Interface with parent**:
```typescript
export class RalphPlanTracker extends EventEmitter {
constructor() { ... }
// Parent calls this when iteration changes (for checkpoint detection)
notifyCycleCount(cycleCount: number): void { ... }
// Full public API moves here unchanged
initializePlanTasks(items: PlanItem[]): void { ... }
updatePlanTask(taskId: string, update: { ... }): { ... } | null { ... }
// ...etc
}
```
**In `RalphTracker`**: Replace plan methods with delegation:
```typescript
readonly planTracker = new RalphPlanTracker();
// Forward plan events
this.planTracker.on('planInitialized', (...args) => this.emit('planInitialized', ...args));
// ...etc
// In detectLoopStatus(), when cycleCount changes:
this.planTracker.notifyCycleCount(this._loopState.cycleCount);
```
### Step 2b: Extract `RalphFixPlanWatcher` (~150 LOC)
**Extract these**:
Properties:
- `_workingDir: string | null`
- `_fixPlanPath: string | null`
- `_fixPlanWatcher: FSWatcher | null`
- `_fixPlanWatcherErrorHandler`
- `_fixPlanReloadDeb`
Methods:
- `setWorkingDir(workingDir)`
- `loadFixPlanFromDisk()`
- `startWatchingFixPlan()`
- `stopWatchingFixPlan()`
- `handleFixPlanChange()`
- `isFileAuthoritative` getter
**Interface with parent**:
```typescript
export class RalphFixPlanWatcher extends EventEmitter {
get isFileAuthoritative(): boolean { ... }
setWorkingDir(workingDir: string): void { ... }
stop(): void { ... }
}
// Events:
// 'todosLoaded' → (todos: Array<{id, content, status, priority}>) — parent replaces _todos
```
**In `RalphTracker`**:
```typescript
readonly fixPlanWatcher = new RalphFixPlanWatcher();
constructor() {
this.fixPlanWatcher.on('todosLoaded', (items) => {
// Replace _todos with file-based items
this._todos.clear();
for (const item of items) {
this.addOrUpdateTodo(item.id, item.content, item.status, item.priority);
}
});
}
// Delegate isFileAuthoritative
get isFileAuthoritative(): boolean {
return this.fixPlanWatcher.isFileAuthoritative;
}
```
### Step 2c: Extract `RalphStallDetector` (~80 LOC)
**Extract these**:
Properties:
- `_lastIterationChangeTime`
- `_lastObservedIteration`
- `_iterationStallTimerId`
- `_iterationStallWarningMs`
- `_iterationStallCriticalMs`
- `_iterationStallWarned`
Methods:
- `startIterationStallDetection()`
- `stopIterationStallDetection()`
- `checkIterationStall()`
- `getIterationStallMetrics()`
- `configureIterationStallThresholds(warningMs, criticalMs)`
**Interface with parent**:
```typescript
export class RalphStallDetector extends EventEmitter {
constructor(private cleanup: CleanupManager) { ... }
start(): void { ... }
stop(): void { ... }
// Parent calls when iteration changes
notifyIterationChanged(iteration: number): void {
this._lastIterationChangeTime = Date.now();
this._lastObservedIteration = iteration;
this._iterationStallWarned = false;
}
// Parent calls to check if loop is active
setLoopActive(active: boolean): void { ... }
getIterationStallMetrics(): { ... } { ... }
}
// Events: 'iterationStallWarning', 'iterationStallCritical'
```
### Step 2d: Extract `RalphStatusParser` (~300 LOC)
**Extract these**:
Properties:
- `_circuitBreaker: CircuitBreakerStatus`
- `_statusBlockBuffer: string[]`
- `_inStatusBlock: boolean`
- `_lastStatusBlock: RalphStatusBlock | null`
- `_completionIndicators: number`
- `_exitGateMet: boolean`
- `_totalFilesModified: number`
- `_totalTasksCompleted: number`
Methods:
- `processStatusBlockLine(line)`
- `parseStatusBlock(lines)`
- `detectCompletionIndicators(line)`
- `updateCircuitBreaker(hasProgress, testsStatus, status)`
- `resetCircuitBreaker()`
- `circuitBreakerStatus` getter
- `lastStatusBlock` getter
- `cumulativeStats` getter
- `exitGateMet` getter
Regex patterns to move:
- `RALPH_STATUS_START_PATTERN` through `RALPH_RECOMMENDATION_PATTERN`
- `COMPLETION_INDICATOR_PATTERNS`
**Interface with parent**:
```typescript
export class RalphStatusParser extends EventEmitter {
processLine(line: string): void { ... } // calls processStatusBlockLine + detectCompletionIndicators
get circuitBreakerStatus(): CircuitBreakerStatus { ... }
get lastStatusBlock(): RalphStatusBlock | null { ... }
get exitGateMet(): boolean { ... }
get cumulativeStats(): { ... } { ... }
resetCircuitBreaker(): void { ... }
reset(): void { ... }
}
// Events: 'statusBlockDetected', 'circuitBreakerUpdate', 'exitGateMet'
```
**In `RalphTracker.processLine()`**:
```typescript
// Replace inline status block handling with delegation
this.statusParser.processLine(line);
```
### Step 2e: Keep in `ralph-tracker.ts` (~1,800 LOC)
The core remains tightly coupled and stays together:
- Output parsing pipeline (`processTerminalData`, `processCleanData`, `processLine`)
- Loop state management (`_loopState`, `detectLoopStatus`, `enable/disable/startLoop/stopLoop`)
- Todo management (`_todos`, `detectTodoItems`, `addOrUpdateTodo`, `updateTodoStatus`, `getTodoStats`)
- Completion detection (`detectCompletionPhrase`, `handleCompletionPhrase`, `calculateCompletionConfidence`)
- All-tasks-complete detection (`detectAllTasksComplete`)
- Auto-enable logic (`shouldAutoEnable`)
- Lifecycle (`reset`, `fullReset`, `clear`, `restoreState`, `destroy`)
- Event debouncing and buffering
The class coordinates the extracted modules via composition:
```typescript
export class RalphTracker extends EventEmitter {
readonly planTracker = new RalphPlanTracker();
readonly fixPlanWatcher = new RalphFixPlanWatcher();
readonly stallDetector: RalphStallDetector;
readonly statusParser = new RalphStatusParser();
constructor() {
super();
this.stallDetector = new RalphStallDetector(this.cleanup);
this._wireSubModuleEvents();
}
private _wireSubModuleEvents(): void {
// Forward all sub-module events through RalphTracker
// so external consumers don't need to know about the split
for (const event of ['planInitialized', 'planTaskUpdate', ...]) {
this.planTracker.on(event, (...args) => this.emit(event, ...args));
}
// ...same for statusParser, stallDetector, fixPlanWatcher
}
}
```
### Migration Safety
- All events continue to be emitted from `RalphTracker` (forwarded from sub-modules)
- All public methods stay on `RalphTracker` (delegated to sub-modules)
- External consumers (`session.ts`, `case-routes.ts`) see zero API changes
- New sub-modules are exposed as `readonly` properties for direct access where needed
---
## 3. Split respawn-controller.ts into focused modules
**Current**: 3,611 lines, single `RespawnController` class with 6 responsibilities.
**Risk**: MEDIUM — health scoring and metrics are cleanly decoupled; detection is tightly coupled.
### Coupling Analysis Summary
| Module | Coupling | Extractability |
|--------|----------|----------------|
| Health scoring | NONE | HIGH — pure calculations from metrics |
| Cycle metrics | LOW | HIGH — standalone tracking |
| Adaptive timing | LOW | HIGH — standalone timing adjustments |
| Stuck-state detection | LOW | MEDIUM — needs state + config refs |
| Pattern detection utilities | NONE | HIGH — pure functions |
| State machine + idle detection + AI checkers | HIGH | LOW — deeply entangled |
### Target Structure
```
src/
├── respawn-controller.ts (~2,200 LOC — state machine, idle detection,
│ AI checkers, terminal handling, hook signals,
│ auto-accept, step execution)
├── respawn-health.ts (~250 LOC — health scoring + recommendations)
├── respawn-metrics.ts (~200 LOC — cycle metrics + aggregate stats)
├── respawn-adaptive-timing.ts (~100 LOC — adaptive timing with percentile calc)
└── respawn-patterns.ts (~50 LOC — terminal pattern detection utilities)
```
### Step 3a: Extract `RespawnPatterns` (~50 LOC)
**Pure utility functions, zero coupling**.
Move:
- `isCompletionMessage(data): boolean`
- `hasWorkingPattern(data, window): boolean`
- `extractTokenCount(data): number | null`
- `PROMPT_PATTERNS` array
- `WORKING_PATTERNS` array
```typescript
// src/respawn-patterns.ts
import { TOKEN_PATTERN, SPINNER_PATTERN } from './utils/index.js';
export const PROMPT_PATTERNS = ['❯', '>', '$', '%', '#'];
export const WORKING_PATTERNS = [/* 70+ patterns */];
export function isCompletionMessage(data: string): boolean { ... }
export function hasWorkingPattern(data: string, window: string): boolean { ... }
export function extractTokenCount(data: string): number | null { ... }
```
**In `RespawnController`**: Import and call:
```typescript
import { isCompletionMessage, hasWorkingPattern, extractTokenCount } from './respawn-patterns.js';
```
### Step 3b: Extract `RespawnAdaptiveTiming` (~100 LOC)
**Self-contained timing controller**.
Move properties:
- `timingHistory: TimingHistory`
Move methods:
- `recordTimingData(idleDetectionMs, cycleDurationMs)`
- `updateAdaptiveTiming()`
- `getTimingHistory()`
- `getAdaptiveCompletionConfirmMs()`
```typescript
export class RespawnAdaptiveTiming {
private timingHistory: TimingHistory;
constructor(private config: { adaptiveMinConfirmMs: number; adaptiveMaxConfirmMs: number }) {
this.timingHistory = { recentIdleDetectionMs: [], recentCycleDurationMs: [], ... };
}
recordTimingData(idleDetectionMs: number, cycleDurationMs: number): void { ... }
getAdaptiveCompletionConfirmMs(): number { ... }
getTimingHistory(): TimingHistory { ... }
reset(): void { ... }
}
```
### Step 3c: Extract `RespawnCycleMetrics` (~200 LOC)
**Standalone metrics tracker**.
Move properties:
- `currentCycleMetrics`
- `recentCycleMetrics[]`
- `aggregateMetrics`
- `MAX_CYCLE_METRICS_IN_MEMORY`
Move methods:
- `startCycleMetrics(idleReason)`
- `recordCycleStep(step)`
- `completeCycleMetrics(outcome, errorMessage?)`
- `updateAggregateMetrics(metrics)`
- `getAggregateMetrics()`
- `getRecentCycleMetrics(limit?)`
```typescript
export class RespawnCycleMetricsTracker {
private currentCycleMetrics: Partial<RespawnCycleMetrics> | null = null;
private recentCycleMetrics: RespawnCycleMetrics[] = [];
private aggregateMetrics: RespawnAggregateMetrics;
startCycle(sessionId: string, cycleNumber: number, idleReason: string): void { ... }
recordStep(step: string): void { ... }
completeCycle(outcome: CycleOutcome, errorMessage?: string): RespawnCycleMetrics | null { ... }
getAggregate(): RespawnAggregateMetrics { ... }
getRecent(limit?: number): RespawnCycleMetrics[] { ... }
reset(): void { ... }
}
```
**Callback**: `completeCycle()` returns the completed metrics so the controller can pass them to `adaptiveTiming.recordTimingData()`.
### Step 3d: Extract `RespawnHealthCalculator` (~250 LOC)
**Pure calculation — no state of its own**.
Move methods:
- `calculateHealthScore()`
- `calculateCycleSuccessScore()`
- `calculateCircuitBreakerScore()`
- `calculateIterationProgressScore()`
- `calculateAiCheckerScore()`
- `calculateStuckRecoveryScore()`
- `generateHealthRecommendations(components)`
- `generateHealthSummary(score, status, components)`
- `shouldSkipClear()` (belongs here since it's a pure calculation on token/config)
```typescript
export interface HealthInputs {
aggregateMetrics: RespawnAggregateMetrics;
circuitBreakerStatus: CircuitBreakerStatus;
iterationStallMetrics: { stallDurationMs: number; warningMs: number; criticalMs: number } | null;
aiCheckerState: { disabled: boolean; inCooldown: boolean; hasErrors: boolean };
stuckRecoveryCount: number;
maxStuckRecoveries: number;
}
export function calculateHealthScore(inputs: HealthInputs): RalphLoopHealthScore { ... }
export function shouldSkipClear(
lastTokenCount: number,
skipClearThresholdPercent: number,
maxContextTokens: number
): boolean { ... }
```
**Made as pure functions** (not a class) since they hold no state.
### Step 3e: Keep in `respawn-controller.ts` (~2,200 LOC)
The core state machine, idle detection, and AI checker integration stays:
- State machine transitions (`setState`, `start`, `stop`, `pause`, `resume`)
- Terminal data handling (`handleTerminalData`)
- All 5 idle detection layers + hook signals
- AI checker integration (`tryStartAiCheck`, `startAiCheck`, `startPlanCheck`)
- Auto-accept logic
- Step execution (`sendUpdateDocs`, `sendClear`, `sendInit`, `sendKickstart`)
- Timer management (`startTrackedTimer`, `cancelTrackedTimer`)
- Stuck-state detection and recovery
- Action logging
The class composes extracted modules:
```typescript
import { RespawnAdaptiveTiming } from './respawn-adaptive-timing.js';
import { RespawnCycleMetricsTracker } from './respawn-metrics.js';
import { calculateHealthScore, shouldSkipClear } from './respawn-health.js';
import { isCompletionMessage, hasWorkingPattern, extractTokenCount } from './respawn-patterns.js';
export class RespawnController extends EventEmitter {
private adaptiveTiming: RespawnAdaptiveTiming;
private cycleMetrics: RespawnCycleMetricsTracker;
calculateHealthScore(): RalphLoopHealthScore {
return calculateHealthScore({
aggregateMetrics: this.cycleMetrics.getAggregate(),
circuitBreakerStatus: this.session.ralphTracker.circuitBreakerStatus,
iterationStallMetrics: this.session.ralphTracker.getIterationStallMetrics(),
aiCheckerState: { ... },
stuckRecoveryCount: this.stuckRecoveryCount,
maxStuckRecoveries: this.config.maxStuckRecoveries ?? 3,
});
}
}
```
---
## 4. Split session.ts into focused modules
**Current**: 2,418 lines, single `Session` class.
**Risk**: LOW-MEDIUM — extractable pieces are utility-like with clear boundaries.
### Coupling Analysis Summary
| Module | Coupling | Extractability |
|--------|----------|----------------|
| CLI arg builder | NONE | HIGH — pure functions used at spawn time |
| Auto-compact/clear | LOW | HIGH — self-contained automation with config |
| Token tracking | LOW | MEDIUM — reads PTY output, writes state |
| Task description cache | LOW | HIGH — separate LRU cache |
| PTY + mux lifecycle | HIGH | KEEP — core of the class |
| Tracker integration | HIGH | KEEP — event forwarding plumbing |
### Target Structure
```
src/
├── session.ts (~1,600 LOC — PTY lifecycle, terminal I/O,
│ tracker integration, output processing,
│ token tracking, state management)
├── session-cli-builder.ts (~250 LOC — Claude/OpenCode CLI arg construction)
├── session-auto-ops.ts (~300 LOC — auto-compact, auto-clear automation)
└── session-task-cache.ts (~100 LOC — task description LRU cache)
```
### Step 4a: Extract `SessionCliBuilder` (~250 LOC)
**Pure functions — zero coupling to Session instance**.
Move:
- `buildClaudeArgs()` logic (currently inlined in `startInteractive` and `runPrompt`)
- `buildOpenCodeArgs()` logic
- Model mapping constants
- Claude mode to flag mapping
- Environment variable construction
```typescript
// src/session-cli-builder.ts
export interface CliBuilderConfig {
claudeMode: ClaudeMode;
model?: string;
workingDir: string;
sessionId: string;
niceConfig?: NiceConfig;
isOpenCode?: boolean;
openCodeConfig?: OpenCodeConfig;
}
export function buildInteractiveArgs(config: CliBuilderConfig): string[] { ... }
export function buildPromptArgs(config: CliBuilderConfig, prompt: string): string[] { ... }
export function buildShellArgs(shell?: string): string[] { ... }
export function buildClaudeEnv(config: CliBuilderConfig): Record<string, string> { ... }
```
### Step 4b: Extract `SessionAutoOps` (~300 LOC)
**Self-contained automation with config-based thresholds**.
Move properties:
- `_autoCompactThreshold`
- `_autoClearThreshold`
- `_isAutoCompacting`
- `_isAutoClearing`
- `_autoCompactCount`
- `_autoClearCount`
- `_lastAutoCompactTime`
- `_lastAutoClearTime`
Move methods:
- `checkAutoCompact(tokenCount)`
- `performAutoCompact()`
- `checkAutoClear(tokenCount)`
- `performAutoClear()`
- Auto-compact/clear threshold configuration
```typescript
export class SessionAutoOps extends EventEmitter {
constructor(
private writeCommand: (command: string) => Promise<void>,
private getTokenCount: () => number,
config: { compactThreshold: number; clearThreshold: number }
) { ... }
/** Called after token count updates. Checks thresholds and triggers if needed. */
checkThresholds(tokenCount: number): void { ... }
updateConfig(config: { compactThreshold?: number; clearThreshold?: number }): void { ... }
getStats(): { autoCompactCount: number; autoClearCount: number; ... } { ... }
}
// Events: 'autoCompact', 'autoClear'
```
**In `Session`**: Compose and wire:
```typescript
private autoOps = new SessionAutoOps(
(cmd) => this.writeViaMux(cmd),
() => this._state.tokenCount,
{ compactThreshold: 110_000, clearThreshold: 140_000 }
);
```
### Step 4c: Extract `SessionTaskCache` (~100 LOC)
**Isolated LRU cache for task descriptions**.
Move:
- `_taskDescriptionCache: LRUMap<number, { description: string; timestamp: number }>`
- `_taskDescriptionMaxAge`
- `findTaskDescriptionNear(lineNumber)`
- `cacheTaskDescription(lineNumber, description)`
```typescript
export class SessionTaskCache {
private cache: LRUMap<number, { description: string; timestamp: number }>;
private maxAgeMs: number;
constructor(maxSize: number = 50, maxAgeMs: number = 30_000) { ... }
find(lineNumber: number, searchRadius: number = 50): string | null { ... }
add(lineNumber: number, description: string): void { ... }
clear(): void { ... }
}
```
### Step 4d: Keep in `session.ts` (~1,600 LOC)
The core stays together:
- PTY process management (`spawn`, `kill`, `resize`, `writeViaMux`)
- Data streaming pipeline (PTY → buffer → ANSI strip → JSON parse → events)
- Tracker initialization and event forwarding (RalphTracker, BashToolParser, TaskTracker)
- Output processing (message extraction, completion detection)
- Token tracking (status line parsing)
- State management (`toState()`, `updateState()`)
- Session lifecycle (`startInteractive`, `startShell`, `runPrompt`)
- CLI info detection (version, model, account)
---
## 5. Execution Order & Dependencies
Execute in this order to minimize risk. Each step is independently deployable.
```
Step 1: types.ts split
↓ (no runtime change, just file reorganization)
Step 2a: RalphPlanTracker extraction
↓ (independent of types split)
Step 2b: RalphFixPlanWatcher extraction
Step 2c: RalphStallDetector extraction
Step 2d: RalphStatusParser extraction
↓ (ralph-tracker.ts now ~1,800 LOC)
Step 3a: RespawnPatterns extraction
Step 3b: RespawnAdaptiveTiming extraction
Step 3c: RespawnCycleMetrics extraction
Step 3d: RespawnHealthCalculator extraction
↓ (respawn-controller.ts now ~2,200 LOC)
Step 4a: SessionCliBuilder extraction
Step 4b: SessionAutoOps extraction
Step 4c: SessionTaskCache extraction
↓ (session.ts now ~1,600 LOC)
```
**Parallelization**: Steps 1, 2a-2d, 3a-3d, and 4a-4c can be done by separate agents in parallel since they touch different files. However, within each group, sequential execution is safer.
### Risk Mitigation
- **Barrel exports**: Every split uses delegation + barrel re-export so external consumers see zero API changes
- **Event forwarding**: Sub-modules emit events, parent class forwards them — no event contract changes
- **Incremental**: Each step can be verified independently with `tsc --noEmit` + `npm run lint`
- **No test changes needed**: External API stays identical; existing tests continue to pass
---
## 6. Validation Checklist
After each step, verify:
- [ ] `tsc --noEmit` passes (no type errors)
- [ ] `npm run lint` passes (no unused imports, etc.)
- [ ] `npm run format:check` passes
- [ ] `npx vitest run test/respawn-controller.test.ts` passes (for respawn splits)
- [ ] `npx vitest run test/ralph-tracker.test.ts` passes (for ralph splits)
- [ ] `npx vitest run test/session-manager.test.ts` passes (for session splits)
- [ ] Dev server starts: `npx tsx src/index.ts web`
- [ ] Existing sessions work (create, interact, delete)
- [ ] Respawn cycle works (enable respawn, verify idle detection fires)
- [ ] No new circular dependencies: `npx madge --circular src/`
### Size Targets
| File | Before | After |
|------|--------|-------|
| `src/types.ts` | 1,443 LOC | 1 LOC (re-export barrel) |
| `src/ralph-tracker.ts` | 3,868 LOC | ~1,800 LOC |
| `src/respawn-controller.ts` | 3,611 LOC | ~2,200 LOC |
| `src/session.ts` | 2,418 LOC | ~1,600 LOC |
| **Total new files** | — | 12 files |
| **Net LOC change** | — | ~0 (refactor only) |
+366
View File
@@ -0,0 +1,366 @@
/**
* @fileoverview RalphFixPlanWatcher - Watches @fix_plan.md for changes
*
* Monitors the @fix_plan.md file in the session's working directory
* for changes, parsing todo items from the markdown format.
*
* Extracted from ralph-tracker.ts as part of domain splitting.
*
* @module ralph-fix-plan-watcher
*/
import { EventEmitter } from 'node:events';
import { readFile } from 'node:fs/promises';
import { existsSync, FSWatcher, watch as fsWatch } from 'node:fs';
import { join } from 'node:path';
import type { RalphTodoStatus, RalphTodoPriority, RalphTodoItem } from './types.js';
// ========== @fix_plan.md Generation & Import Utility Functions ==========
/**
* Generate @fix_plan.md content from todo items.
* Groups todos by priority and status.
*
* @param todos - Array of todo items
* @returns Markdown content for @fix_plan.md
*/
export function generateFixPlanMarkdown(todos: RalphTodoItem[]): string {
const lines: string[] = ['# Fix Plan', ''];
// Group by priority
const p0: RalphTodoItem[] = [];
const p1: RalphTodoItem[] = [];
const p2: RalphTodoItem[] = [];
const noPriority: RalphTodoItem[] = [];
const completed: RalphTodoItem[] = [];
for (const todo of todos) {
if (todo.status === 'completed') {
completed.push(todo);
} else if (todo.priority === 'P0') {
p0.push(todo);
} else if (todo.priority === 'P1') {
p1.push(todo);
} else if (todo.priority === 'P2') {
p2.push(todo);
} else {
noPriority.push(todo);
}
}
// High Priority (P0)
if (p0.length > 0) {
lines.push('## High Priority (P0)');
for (const todo of p0) {
const checkbox = todo.status === 'in_progress' ? '[-]' : '[ ]';
lines.push(`- ${checkbox} ${todo.content}`);
}
lines.push('');
}
// Standard (P1)
if (p1.length > 0) {
lines.push('## Standard (P1)');
for (const todo of p1) {
const checkbox = todo.status === 'in_progress' ? '[-]' : '[ ]';
lines.push(`- ${checkbox} ${todo.content}`);
}
lines.push('');
}
// Nice to Have (P2)
if (p2.length > 0) {
lines.push('## Nice to Have (P2)');
for (const todo of p2) {
const checkbox = todo.status === 'in_progress' ? '[-]' : '[ ]';
lines.push(`- ${checkbox} ${todo.content}`);
}
lines.push('');
}
// Tasks (no priority)
if (noPriority.length > 0) {
lines.push('## Tasks');
for (const todo of noPriority) {
const checkbox = todo.status === 'in_progress' ? '[-]' : '[ ]';
lines.push(`- ${checkbox} ${todo.content}`);
}
lines.push('');
}
// Completed
if (completed.length > 0) {
lines.push('## Completed');
for (const todo of completed) {
lines.push(`- [x] ${todo.content}`);
}
lines.push('');
}
return lines.join('\n');
}
/**
* Parse @fix_plan.md content and return parsed todo items.
*
* @param content - Markdown content from @fix_plan.md
* @param parsePriority - Function to parse priority from content text
* @param generateTodoId - Function to generate stable todo ID from content
* @returns Array of parsed todo items
*/
export function importFixPlanMarkdown(
content: string,
parsePriority: (content: string) => RalphTodoPriority,
generateTodoId: (content: string) => string
): RalphTodoItem[] {
const lines = content.split('\n');
const newTodos: RalphTodoItem[] = [];
let currentPriority: RalphTodoPriority = null;
// Patterns for section headers
const p0HeaderPattern = /^##\s*(High Priority|Critical|P0)/i;
const p1HeaderPattern = /^##\s*(Standard|P1|Medium Priority)/i;
const p2HeaderPattern = /^##\s*(Nice to Have|P2|Low Priority)/i;
const completedHeaderPattern = /^##\s*Completed/i;
const tasksHeaderPattern = /^##\s*Tasks/i;
// Pattern for todo items
const todoPattern = /^-\s*\[([ x-])\]\s*(.+)$/;
let inCompletedSection = false;
for (const line of lines) {
const trimmed = line.trim();
// Check for section headers
if (p0HeaderPattern.test(trimmed)) {
currentPriority = 'P0';
inCompletedSection = false;
continue;
}
if (p1HeaderPattern.test(trimmed)) {
currentPriority = 'P1';
inCompletedSection = false;
continue;
}
if (p2HeaderPattern.test(trimmed)) {
currentPriority = 'P2';
inCompletedSection = false;
continue;
}
if (completedHeaderPattern.test(trimmed)) {
inCompletedSection = true;
continue;
}
if (tasksHeaderPattern.test(trimmed)) {
currentPriority = null;
inCompletedSection = false;
continue;
}
// Parse todo item
const match = trimmed.match(todoPattern);
if (match) {
const [, checkboxState, todoContent] = match;
let status: RalphTodoStatus;
if (inCompletedSection || checkboxState === 'x' || checkboxState === 'X') {
status = 'completed';
} else if (checkboxState === '-') {
status = 'in_progress';
} else {
status = 'pending';
}
// Parse priority from content if not in a priority section
const parsedPriority = inCompletedSection ? null : currentPriority || parsePriority(todoContent);
const id = generateTodoId(todoContent);
newTodos.push({
id,
content: todoContent.trim(),
status,
detectedAt: Date.now(),
priority: parsedPriority,
});
}
}
return newTodos;
}
/**
* RalphFixPlanWatcher - Watches @fix_plan.md for changes.
*
* Events emitted:
* - `todosLoaded` - Emits parsed todo items when @fix_plan.md is loaded/changed
* - `enabled` - Emits when tracker should be auto-enabled (todos loaded from file)
*/
export class RalphFixPlanWatcher extends EventEmitter {
/** Working directory for @fix_plan.md watching */
private _workingDir: string | null = null;
/** Path to the @fix_plan.md file being watched */
private _fixPlanPath: string | null = null;
/** File watcher for @fix_plan.md */
private _fixPlanWatcher: FSWatcher | null = null;
/** Error handler for FSWatcher (stored for cleanup to prevent memory leak) */
private _fixPlanWatcherErrorHandler: ((err: Error) => void) | null = null;
/** Debounce timer for file change events */
private _fixPlanReloadTimer: NodeJS.Timeout | null = null;
/** Priority parser injected from parent (for importFixPlanMarkdown) */
private _parsePriority: (content: string) => RalphTodoPriority;
/** Todo ID generator injected from parent */
private _generateTodoId: (content: string) => string;
constructor(parsePriority: (content: string) => RalphTodoPriority, generateTodoId: (content: string) => string) {
super();
this._parsePriority = parsePriority;
this._generateTodoId = generateTodoId;
}
/**
* When @fix_plan.md is active, treat it as the source of truth for todo status.
* This prevents output-based detection from overriding file-based status.
*/
get isFileAuthoritative(): boolean {
return this._fixPlanPath !== null;
}
/**
* Set the working directory and start watching @fix_plan.md.
* Automatically loads existing @fix_plan.md if present.
* @param workingDir - The session's working directory
*/
setWorkingDir(workingDir: string): void {
this._workingDir = workingDir;
this._fixPlanPath = join(workingDir, '@fix_plan.md');
// Try to load existing @fix_plan.md
this.loadFixPlanFromDisk();
// Start watching for changes
this.startWatchingFixPlan();
}
/**
* Load @fix_plan.md from disk if it exists.
* Called on initialization and when file changes are detected.
*/
async loadFixPlanFromDisk(): Promise<number> {
if (!this._fixPlanPath) return 0;
try {
if (!existsSync(this._fixPlanPath)) {
return 0;
}
const content = await readFile(this._fixPlanPath, 'utf-8');
const todos = importFixPlanMarkdown(content, this._parsePriority, this._generateTodoId);
if (todos.length > 0) {
this.emit('todosLoaded', todos);
console.log(`[RalphFixPlanWatcher] Loaded ${todos.length} todos from @fix_plan.md`);
}
return todos.length;
} catch (err) {
// File doesn't exist or can't be read - that's OK
console.log(`[RalphFixPlanWatcher] Could not load @fix_plan.md: ${err}`);
return 0;
}
}
/**
* Start watching @fix_plan.md for changes.
* Reloads todos when the file is modified.
*/
private startWatchingFixPlan(): void {
if (!this._fixPlanPath || !this._workingDir) return;
// Stop existing watcher if any
this.stopWatchingFixPlan();
try {
// Only watch if the file exists
if (!existsSync(this._fixPlanPath)) {
// Watch the directory instead for file creation
this._fixPlanWatcher = fsWatch(this._workingDir, (_eventType, filename) => {
if (filename === '@fix_plan.md') {
this.handleFixPlanChange();
}
});
} else {
// Watch the file directly
this._fixPlanWatcher = fsWatch(this._fixPlanPath, () => {
this.handleFixPlanChange();
});
}
// Add error handler to prevent unhandled errors and clean up on failure
// Store handler reference for proper cleanup in stopWatchingFixPlan()
if (this._fixPlanWatcher) {
this._fixPlanWatcherErrorHandler = (err: Error) => {
console.log(`[RalphFixPlanWatcher] FSWatcher error for @fix_plan.md: ${err.message}`);
this.stopWatchingFixPlan();
};
this._fixPlanWatcher.on('error', this._fixPlanWatcherErrorHandler);
}
} catch (err) {
console.log(`[RalphFixPlanWatcher] Could not watch @fix_plan.md: ${err}`);
}
}
/**
* Handle @fix_plan.md file change with debouncing.
*/
private handleFixPlanChange(): void {
// Debounce rapid changes (e.g., multiple writes)
if (this._fixPlanReloadTimer) {
clearTimeout(this._fixPlanReloadTimer);
}
this._fixPlanReloadTimer = setTimeout(() => {
this._fixPlanReloadTimer = null;
this.loadFixPlanFromDisk();
}, 500); // 500ms debounce
}
/**
* Stop watching @fix_plan.md.
*/
stopWatchingFixPlan(): void {
if (this._fixPlanWatcher) {
// Remove error handler before closing to prevent memory leak
if (this._fixPlanWatcherErrorHandler) {
this._fixPlanWatcher.off('error', this._fixPlanWatcherErrorHandler);
this._fixPlanWatcherErrorHandler = null;
}
this._fixPlanWatcher.close();
this._fixPlanWatcher = null;
}
if (this._fixPlanReloadTimer) {
clearTimeout(this._fixPlanReloadTimer);
this._fixPlanReloadTimer = null;
}
}
/**
* Stop watching and clean up all resources.
*/
stop(): void {
this.stopWatchingFixPlan();
}
/**
* Clean up all resources.
*/
destroy(): void {
this.stop();
this.removeAllListeners();
}
}
+477
View File
@@ -0,0 +1,477 @@
/**
* @fileoverview RalphPlanTracker - Enhanced plan task management
*
* Manages plan tasks with verification criteria, dependencies,
* execution tracking, TDD workflow support, and plan versioning.
*
* Extracted from ralph-tracker.ts as part of domain splitting.
*
* @module ralph-plan-tracker
*/
import { EventEmitter } from 'node:events';
import type { PlanTaskStatus, TddPhase } from './types.js';
// ========== Enhanced Plan Task Interface ==========
/**
* Enhanced plan task with verification criteria, dependencies, and execution tracking.
* Supports TDD workflow, failure tracking, and plan versioning.
*/
export interface EnhancedPlanTask {
/** Unique identifier (e.g., "P0-001") */
id: string;
/** Task description */
content: string;
/** Criticality level */
priority: 'P0' | 'P1' | 'P2' | null;
/** How to verify completion */
verificationCriteria?: string;
/** Command to run for verification */
testCommand?: string;
/** IDs of tasks that must complete first */
dependencies: string[];
/** Current execution status */
status: PlanTaskStatus;
/** How many times attempted */
attempts: number;
/** Most recent failure reason */
lastError?: string;
/** Timestamp of completion */
completedAt?: number;
/** Plan version this belongs to */
version: number;
/** TDD phase category */
tddPhase?: TddPhase;
/** ID of paired test/impl task */
pairedWith?: string;
/** Estimated complexity */
complexity?: 'low' | 'medium' | 'high';
/** Checklist items for review tasks (tddPhase: 'review') */
reviewChecklist?: string[];
}
/** Checkpoint review data */
export interface CheckpointReview {
iteration: number;
timestamp: number;
summary: {
total: number;
completed: number;
failed: number;
blocked: number;
pending: number;
inProgress: number;
};
stuckTasks: Array<{
id: string;
content: string;
attempts: number;
lastError?: string;
}>;
recommendations: string[];
}
const MAX_PLAN_HISTORY = 10;
/**
* RalphPlanTracker - Manages enhanced plan tasks with versioning and checkpoints.
*
* Events emitted:
* - `planInitialized` - When a new plan is initialized
* - `planTaskUpdate` - When a plan task is updated
* - `taskBlocked` - When a task becomes blocked after too many failures
* - `taskUnblocked` - When a task's dependencies are all met
* - `planCheckpoint` - When a checkpoint review is triggered
* - `planTaskAdded` - When a new task is added to the plan
* - `planRollback` - When the plan is rolled back to a previous version
*/
export class RalphPlanTracker extends EventEmitter {
/** Current version of the plan (incremented on changes) */
private _planVersion: number = 1;
/** History of plan versions for rollback support */
private _planHistory: Array<{
version: number;
timestamp: number;
tasks: Map<string, EnhancedPlanTask>;
summary: string;
}> = [];
/** Enhanced plan tasks with execution tracking */
private _planTasks: Map<string, EnhancedPlanTask> = new Map();
/** Checkpoint intervals (iterations at which to trigger review) */
private _checkpointIterations: number[] = [5, 10, 20, 30, 50, 75, 100];
/** Last checkpoint iteration */
private _lastCheckpointIteration: number = 0;
/** Current cycle count (fed by parent via notifyCycleCount) */
private _cycleCount: number = 0;
constructor() {
super();
}
/**
* Notify the plan tracker of the current cycle count.
* Called by parent when iteration changes (for checkpoint detection).
*/
notifyCycleCount(cycleCount: number): void {
this._cycleCount = cycleCount;
}
/**
* Initialize plan tasks from generated plan items.
* Called when wizard generates a new plan.
*/
initializePlanTasks(
items: Array<{
id?: string;
content: string;
priority?: 'P0' | 'P1' | 'P2' | null;
verificationCriteria?: string;
testCommand?: string;
dependencies?: string[];
tddPhase?: TddPhase;
pairedWith?: string;
complexity?: 'low' | 'medium' | 'high';
}>
): void {
// Save current plan to history before replacing
if (this._planTasks.size > 0) {
this._savePlanToHistory('Plan replaced with new generation');
}
// Clear and rebuild
this._planTasks.clear();
this._planVersion++;
items.forEach((item, idx) => {
const id = item.id || `task-${idx}`;
const task: EnhancedPlanTask = {
id,
content: item.content,
priority: item.priority || null,
verificationCriteria: item.verificationCriteria,
testCommand: item.testCommand,
dependencies: item.dependencies || [],
status: 'pending',
attempts: 0,
version: this._planVersion,
tddPhase: item.tddPhase,
pairedWith: item.pairedWith,
complexity: item.complexity,
};
this._planTasks.set(id, task);
});
this.emit('planInitialized', { version: this._planVersion, taskCount: this._planTasks.size });
}
/**
* Update a specific plan task's status, attempts, or error.
*/
updatePlanTask(
taskId: string,
update: {
status?: PlanTaskStatus;
error?: string;
incrementAttempts?: boolean;
}
): { success: boolean; task?: EnhancedPlanTask; error?: string } {
const task = this._planTasks.get(taskId);
if (!task) {
return { success: false, error: 'Task not found' };
}
if (update.status) {
task.status = update.status;
if (update.status === 'completed') {
task.completedAt = Date.now();
}
}
if (update.error) {
task.lastError = update.error;
}
if (update.incrementAttempts) {
task.attempts++;
// After 3 failed attempts, mark as blocked and emit warning
if (task.attempts >= 3 && task.status === 'failed') {
task.status = 'blocked';
this.emit('taskBlocked', {
taskId,
content: task.content,
attempts: task.attempts,
lastError: task.lastError,
});
}
}
// Update blocked tasks when a dependency completes
if (update.status === 'completed') {
this._unblockDependentTasks(taskId);
}
// Check for checkpoint
this._checkForCheckpoint();
this.emit('planTaskUpdate', { taskId, task });
return { success: true, task };
}
/**
* Add a new task to the plan (for runtime adaptation).
*/
addPlanTask(task: {
content: string;
priority?: 'P0' | 'P1' | 'P2';
verificationCriteria?: string;
dependencies?: string[];
insertAfter?: string;
}): { task: EnhancedPlanTask } {
// Generate unique ID
const existingIds = Array.from(this._planTasks.keys());
const prefix = task.priority || 'P1';
let counter = existingIds.filter((id) => id.startsWith(prefix)).length + 1;
let id = `${prefix}-${String(counter).padStart(3, '0')}`;
while (this._planTasks.has(id)) {
counter++;
id = `${prefix}-${String(counter).padStart(3, '0')}`;
}
const newTask: EnhancedPlanTask = {
id,
content: task.content,
priority: task.priority || null,
verificationCriteria: task.verificationCriteria || 'Task completed successfully',
dependencies: task.dependencies || [],
status: 'pending',
attempts: 0,
version: this._planVersion,
};
this._planTasks.set(id, newTask);
this.emit('planTaskAdded', { task: newTask });
return { task: newTask };
}
/**
* Get all plan tasks.
*/
getPlanTasks(): EnhancedPlanTask[] {
return Array.from(this._planTasks.values());
}
/**
* Generate a checkpoint review summarizing plan progress and stuck tasks.
*/
generateCheckpointReview(): CheckpointReview {
const tasks = Array.from(this._planTasks.values());
const summary = {
total: tasks.length,
completed: tasks.filter((t) => t.status === 'completed').length,
failed: tasks.filter((t) => t.status === 'failed').length,
blocked: tasks.filter((t) => t.status === 'blocked').length,
pending: tasks.filter((t) => t.status === 'pending').length,
inProgress: tasks.filter((t) => t.status === 'in_progress').length,
};
// Find stuck tasks (3+ attempts or blocked)
const stuckTasks = tasks
.filter((t) => t.attempts >= 3 || t.status === 'blocked')
.map((t) => ({
id: t.id,
content: t.content,
attempts: t.attempts,
lastError: t.lastError,
}));
// Generate recommendations
const recommendations: string[] = [];
if (stuckTasks.length > 0) {
recommendations.push(`${stuckTasks.length} task(s) are stuck. Consider breaking them into smaller steps.`);
}
if (summary.failed > summary.completed && summary.total > 5) {
recommendations.push('More tasks have failed than completed. Review approach and consider plan adjustment.');
}
const progressPercent = summary.total > 0 ? Math.round((summary.completed / summary.total) * 100) : 0;
if (progressPercent < 20 && this._cycleCount > 10) {
recommendations.push('Progress is slow. Consider simplifying tasks or reviewing dependencies.');
}
if (summary.total > 0 && summary.blocked > summary.total / 3) {
recommendations.push('Many tasks are blocked. Review dependency chain for bottlenecks.');
}
return {
iteration: this._cycleCount,
timestamp: Date.now(),
summary,
stuckTasks,
recommendations,
};
}
/**
* Get plan version history.
*/
getPlanHistory(): Array<{
version: number;
timestamp: number;
summary: string;
stats: { total: number; completed: number; failed: number };
}> {
return this._planHistory.map((h) => {
const tasks = Array.from(h.tasks.values());
return {
version: h.version,
timestamp: h.timestamp,
summary: h.summary,
stats: {
total: tasks.length,
completed: tasks.filter((t) => t.status === 'completed').length,
failed: tasks.filter((t) => t.status === 'failed').length,
},
};
});
}
/**
* Rollback to a previous plan version.
*/
rollbackToVersion(version: number): {
success: boolean;
plan?: EnhancedPlanTask[];
error?: string;
} {
const historyEntry = this._planHistory.find((h) => h.version === version);
if (!historyEntry) {
return { success: false, error: `Version ${version} not found in history` };
}
// Save current state first
this._savePlanToHistory(`Rolled back from v${this._planVersion} to v${version}`);
// Restore the historical version
this._planTasks.clear();
for (const [id, task] of historyEntry.tasks) {
// Reset execution state for retry
this._planTasks.set(id, {
...task,
status: task.status === 'completed' ? 'completed' : 'pending',
attempts: task.status === 'completed' ? task.attempts : 0,
lastError: undefined,
});
}
this._planVersion++;
this.emit('planRollback', { version, newVersion: this._planVersion });
return { success: true, plan: Array.from(this._planTasks.values()) };
}
/**
* Check if checkpoint review is due for current iteration.
*/
isCheckpointDue(): boolean {
return this._checkpointIterations.includes(this._cycleCount) && this._cycleCount > this._lastCheckpointIteration;
}
/**
* Get current plan version.
*/
get planVersion(): number {
return this._planVersion;
}
/**
* Reset plan state (soft reset - keeps version history).
*/
reset(): void {
// Don't clear history or version on soft reset
}
/**
* Full reset - clears all plan state.
*/
fullReset(): void {
this._planTasks.clear();
this._planHistory.length = 0;
this._planVersion = 1;
this._lastCheckpointIteration = 0;
this._cycleCount = 0;
}
/**
* Clean up all resources.
*/
destroy(): void {
this._planTasks.clear();
this._planHistory.length = 0;
this.removeAllListeners();
}
/**
* Unblock tasks that were waiting on a completed dependency.
*/
private _unblockDependentTasks(completedTaskId: string): void {
for (const [_, task] of this._planTasks) {
if (task.dependencies.includes(completedTaskId)) {
// Check if all dependencies are now complete
const allDepsComplete = task.dependencies.every((depId) => {
const dep = this._planTasks.get(depId);
return dep && dep.status === 'completed';
});
if (allDepsComplete && task.status === 'blocked') {
task.status = 'pending';
this.emit('taskUnblocked', { taskId: task.id });
}
}
}
}
/**
* Check if current iteration is a checkpoint and emit review if so.
*/
private _checkForCheckpoint(): void {
if (this._checkpointIterations.includes(this._cycleCount) && this._cycleCount > this._lastCheckpointIteration) {
this._lastCheckpointIteration = this._cycleCount;
const checkpoint = this.generateCheckpointReview();
this.emit('planCheckpoint', checkpoint);
}
}
/**
* Save current plan state to history.
*/
private _savePlanToHistory(summary: string): void {
// Clone current tasks
const tasksCopy = new Map<string, EnhancedPlanTask>();
for (const [id, task] of this._planTasks) {
tasksCopy.set(id, { ...task });
}
this._planHistory.push({
version: this._planVersion,
timestamp: Date.now(),
tasks: tasksCopy,
summary,
});
// Limit history size
if (this._planHistory.length > MAX_PLAN_HISTORY) {
this._planHistory.shift();
}
}
}
+166
View File
@@ -0,0 +1,166 @@
/**
* @fileoverview RalphStallDetector - Iteration stall detection
*
* Monitors iteration progress and emits warnings when the loop
* appears to be stalled (no iteration changes for extended periods).
*
* Extracted from ralph-tracker.ts as part of domain splitting.
*
* @module ralph-stall-detector
*/
import { EventEmitter } from 'node:events';
/**
* RalphStallDetector - Detects iteration stalls in the Ralph loop.
*
* Events emitted:
* - `iterationStallWarning` - When iteration hasn't changed for warning threshold
* - `iterationStallCritical` - When iteration hasn't changed for critical threshold
*/
export class RalphStallDetector extends EventEmitter {
/** Timestamp when iteration count last changed */
private _lastIterationChangeTime: number = 0;
/** Last observed iteration count for stall detection */
private _lastObservedIteration: number = 0;
/** Timer for iteration stall detection */
private _iterationStallTimer: NodeJS.Timeout | null = null;
/** Iteration stall warning threshold (ms) - default 10 minutes */
private _iterationStallWarningMs: number = 10 * 60 * 1000;
/** Iteration stall critical threshold (ms) - default 20 minutes */
private _iterationStallCriticalMs: number = 20 * 60 * 1000;
/** Whether stall warning has been emitted */
private _iterationStallWarned: boolean = false;
/** Whether the loop is currently active */
private _loopActive: boolean = false;
constructor() {
super();
this._lastIterationChangeTime = Date.now();
}
/**
* Start iteration stall detection timer.
* Should be called when the loop becomes active.
*/
startIterationStallDetection(): void {
this.stopIterationStallDetection();
this._lastIterationChangeTime = Date.now();
this._iterationStallWarned = false;
// Check every minute
this._iterationStallTimer = setInterval(() => {
this.checkIterationStall();
}, 60 * 1000);
}
/**
* Stop iteration stall detection timer.
*/
stopIterationStallDetection(): void {
if (this._iterationStallTimer) {
clearInterval(this._iterationStallTimer);
this._iterationStallTimer = null;
}
}
/**
* Notify the detector that the iteration has changed.
* Resets stall tracking state.
*/
notifyIterationChanged(iteration: number): void {
this._lastIterationChangeTime = Date.now();
this._lastObservedIteration = iteration;
this._iterationStallWarned = false;
}
/**
* Set whether the loop is currently active.
* Stall detection only fires when loop is active.
*/
setLoopActive(active: boolean): void {
this._loopActive = active;
}
/**
* Check for iteration stall and emit appropriate events.
*/
private checkIterationStall(): void {
if (!this._loopActive) return;
const stallDurationMs = Date.now() - this._lastIterationChangeTime;
// Critical stall (longer duration)
if (stallDurationMs >= this._iterationStallCriticalMs) {
this.emit('iterationStallCritical', {
iteration: this._lastObservedIteration,
stallDurationMs,
});
return;
}
// Warning stall
if (stallDurationMs >= this._iterationStallWarningMs && !this._iterationStallWarned) {
this._iterationStallWarned = true;
this.emit('iterationStallWarning', {
iteration: this._lastObservedIteration,
stallDurationMs,
});
}
}
/**
* Get iteration stall metrics for monitoring.
*/
getIterationStallMetrics(): {
lastIterationChangeTime: number;
stallDurationMs: number;
warningThresholdMs: number;
criticalThresholdMs: number;
isWarned: boolean;
currentIteration: number;
} {
return {
lastIterationChangeTime: this._lastIterationChangeTime,
stallDurationMs: Date.now() - this._lastIterationChangeTime,
warningThresholdMs: this._iterationStallWarningMs,
criticalThresholdMs: this._iterationStallCriticalMs,
isWarned: this._iterationStallWarned,
currentIteration: this._lastObservedIteration,
};
}
/**
* Configure iteration stall thresholds.
* @param warningMs - Warning threshold in milliseconds
* @param criticalMs - Critical threshold in milliseconds
*/
configureIterationStallThresholds(warningMs: number, criticalMs: number): void {
this._iterationStallWarningMs = warningMs;
this._iterationStallCriticalMs = criticalMs;
}
/**
* Reset stall detector state.
*/
reset(): void {
this._lastIterationChangeTime = Date.now();
this._lastObservedIteration = 0;
this._iterationStallWarned = false;
this._loopActive = false;
}
/**
* Clean up all resources.
*/
destroy(): void {
this.stopIterationStallDetection();
this.removeAllListeners();
}
}
+552
View File
@@ -0,0 +1,552 @@
/**
* @fileoverview RalphStatusParser - RALPH_STATUS block parsing and circuit breaker
*
* Parses structured RALPH_STATUS blocks from Claude Code output
* and manages the circuit breaker state machine.
*
* Extracted from ralph-tracker.ts as part of domain splitting.
*
* @module ralph-status-parser
*/
import { EventEmitter } from 'node:events';
import type {
RalphStatusBlock,
RalphStatusValue,
RalphTestsStatus,
RalphWorkType,
CircuitBreakerStatus,
} from './types.js';
import { createInitialCircuitBreakerStatus } from './types.js';
// ---------- RALPH_STATUS Block Patterns ----------
// Based on Ralph Claude Code structured status reporting
/**
* Matches the start of a RALPH_STATUS block
* Pattern: ---RALPH_STATUS---
*/
const RALPH_STATUS_START_PATTERN = /^---RALPH_STATUS---\s*$/;
/**
* Matches the end of a RALPH_STATUS block
* Pattern: ---END_RALPH_STATUS---
*/
const RALPH_STATUS_END_PATTERN = /^---END_RALPH_STATUS---\s*$/;
/**
* Matches STATUS field in RALPH_STATUS block
* Captures: IN_PROGRESS | COMPLETE | BLOCKED
*/
const RALPH_STATUS_FIELD_PATTERN = /^STATUS:\s*(IN_PROGRESS|COMPLETE|BLOCKED)\s*$/i;
/**
* Matches TASKS_COMPLETED_THIS_LOOP field
* Captures: number
*/
const RALPH_TASKS_COMPLETED_PATTERN = /^TASKS_COMPLETED_THIS_LOOP:\s*(\d+)\s*$/i;
/**
* Matches FILES_MODIFIED field
* Captures: number
*/
const RALPH_FILES_MODIFIED_PATTERN = /^FILES_MODIFIED:\s*(\d+)\s*$/i;
/**
* Matches TESTS_STATUS field
* Captures: PASSING | FAILING | NOT_RUN
*/
const RALPH_TESTS_STATUS_PATTERN = /^TESTS_STATUS:\s*(PASSING|FAILING|NOT_RUN)\s*$/i;
/**
* Matches WORK_TYPE field
* Captures: IMPLEMENTATION | TESTING | DOCUMENTATION | REFACTORING
*/
const RALPH_WORK_TYPE_PATTERN = /^WORK_TYPE:\s*(IMPLEMENTATION|TESTING|DOCUMENTATION|REFACTORING)\s*$/i;
/**
* Matches EXIT_SIGNAL field
* Captures: true | false
*/
const RALPH_EXIT_SIGNAL_PATTERN = /^EXIT_SIGNAL:\s*(true|false)\s*$/i;
/**
* Matches RECOMMENDATION field
* Captures: any text
*/
const RALPH_RECOMMENDATION_PATTERN = /^RECOMMENDATION:\s*(.+)$/i;
// ---------- Completion Indicator Patterns (for dual-condition exit) ----------
/**
* Patterns that indicate potential completion (natural language)
* Count >= 2 along with EXIT_SIGNAL: true triggers exit
*/
const COMPLETION_INDICATOR_PATTERNS = [
/all\s+(?:tasks?|items?|work)\s+(?:are\s+)?(?:completed?|done|finished)/i,
/(?:completed?|finished)\s+all\s+(?:tasks?|items?|work)/i,
/nothing\s+(?:left|remaining)\s+to\s+do/i,
/no\s+more\s+(?:tasks?|items?|work)/i,
/everything\s+(?:is\s+)?(?:completed?|done)/i,
/project\s+(?:is\s+)?(?:completed?|done|finished)/i,
];
/**
* RalphStatusParser - Parses RALPH_STATUS blocks and manages circuit breaker.
*
* Events emitted:
* - `statusBlockDetected` - When a complete RALPH_STATUS block is parsed
* - `circuitBreakerUpdate` - When circuit breaker state changes
* - `exitGateMet` - When dual-condition exit gate is met
*/
export class RalphStatusParser extends EventEmitter {
/** Circuit breaker state tracking */
private _circuitBreaker: CircuitBreakerStatus;
/** Buffer for RALPH_STATUS block lines */
private _statusBlockBuffer: string[] = [];
/** Flag indicating we're inside a RALPH_STATUS block */
private _inStatusBlock: boolean = false;
/** Last parsed RALPH_STATUS block */
private _lastStatusBlock: RalphStatusBlock | null = null;
/** Count of completion indicators detected (for dual-condition exit) */
private _completionIndicators: number = 0;
/** Whether dual-condition exit gate has been met */
private _exitGateMet: boolean = false;
/** Cumulative files modified across all iterations */
private _totalFilesModified: number = 0;
/** Cumulative tasks completed across all iterations */
private _totalTasksCompleted: number = 0;
/** Current cycle count (fed by parent) */
private _cycleCount: number = 0;
constructor() {
super();
this._circuitBreaker = createInitialCircuitBreakerStatus();
}
/**
* Process a line for status block detection and completion indicators.
* Main entry point - call this for each trimmed line.
*/
processLine(line: string): void {
this.processStatusBlockLine(line);
this.detectCompletionIndicators(line);
}
/**
* Set the current cycle count (fed by parent for circuit breaker tracking).
*/
setCycleCount(cycleCount: number): void {
this._cycleCount = cycleCount;
}
/**
* Notify of iteration progress (for circuit breaker reset on progress).
* Called by parent when iteration count changes.
*/
notifyIterationProgress(currentIteration: number): void {
if (
this._circuitBreaker.state === 'HALF_OPEN' ||
this._circuitBreaker.consecutiveNoProgress > 0 ||
this._circuitBreaker.consecutiveSameError > 0 ||
this._circuitBreaker.consecutiveTestsFailure > 0
) {
this._circuitBreaker.consecutiveNoProgress = 0;
this._circuitBreaker.consecutiveSameError = 0;
this._circuitBreaker.lastProgressIteration = currentIteration;
if (this._circuitBreaker.state === 'HALF_OPEN') {
this._circuitBreaker.state = 'CLOSED';
this._circuitBreaker.reason = 'Iteration progress detected';
this._circuitBreaker.reasonCode = 'progress_detected';
this.emit('circuitBreakerUpdate', { ...this._circuitBreaker });
}
}
}
/**
* Get current circuit breaker status.
*/
get circuitBreakerStatus(): CircuitBreakerStatus {
return { ...this._circuitBreaker };
}
/**
* Get last parsed RALPH_STATUS block.
*/
get lastStatusBlock(): RalphStatusBlock | null {
return this._lastStatusBlock ? { ...this._lastStatusBlock } : null;
}
/**
* Get cumulative stats from status blocks.
*/
get cumulativeStats(): {
filesModified: number;
tasksCompleted: number;
completionIndicators: number;
} {
return {
filesModified: this._totalFilesModified,
tasksCompleted: this._totalTasksCompleted,
completionIndicators: this._completionIndicators,
};
}
/**
* Whether dual-condition exit gate has been met.
*/
get exitGateMet(): boolean {
return this._exitGateMet;
}
/**
* Manually reset circuit breaker to CLOSED state.
* Use when user acknowledges the issue is resolved.
*
* @fires circuitBreakerUpdate
*/
resetCircuitBreaker(): void {
this._circuitBreaker = createInitialCircuitBreakerStatus();
this._circuitBreaker.reason = 'Manual reset';
this._circuitBreaker.reasonCode = 'manual_reset';
this.emit('circuitBreakerUpdate', { ...this._circuitBreaker });
}
/**
* Reset status parser state (soft reset).
* Clears status block buffer and completion indicators.
* Keeps circuit breaker state (it tracks across iterations).
*/
reset(): void {
this._statusBlockBuffer = [];
this._inStatusBlock = false;
this._lastStatusBlock = null;
this._completionIndicators = 0;
this._exitGateMet = false;
this._totalFilesModified = 0;
this._totalTasksCompleted = 0;
// Keep circuit breaker state on soft reset (it tracks across iterations)
}
/**
* Full reset - clears all state including circuit breaker.
*/
fullReset(): void {
this.reset();
this._circuitBreaker = createInitialCircuitBreakerStatus();
}
/**
* Clean up all resources.
*/
destroy(): void {
this._statusBlockBuffer.length = 0;
this.removeAllListeners();
}
// ========== Private Methods ==========
/**
* Process a line for RALPH_STATUS block detection.
* Buffers lines between ---RALPH_STATUS--- and ---END_RALPH_STATUS---
* then parses the complete block.
*
* @param line - Single line to process (already trimmed)
* @fires statusBlockDetected - When a complete block is parsed
*/
private processStatusBlockLine(line: string): void {
// Check for block start
if (RALPH_STATUS_START_PATTERN.test(line)) {
this._inStatusBlock = true;
this._statusBlockBuffer = [];
return;
}
// Check for block end
if (this._inStatusBlock && RALPH_STATUS_END_PATTERN.test(line)) {
this._inStatusBlock = false;
this.parseStatusBlock(this._statusBlockBuffer);
this._statusBlockBuffer = [];
return;
}
// Buffer lines while in block
if (this._inStatusBlock) {
this._statusBlockBuffer.push(line);
}
}
/**
* Parse buffered RALPH_STATUS block lines into structured data.
*
* P1-004: Enhanced with schema validation and error recovery
*
* @param lines - Array of lines between block markers
* @fires statusBlockDetected - When parsing succeeds
*/
private parseStatusBlock(lines: string[]): void {
const block: Partial<RalphStatusBlock> = {
parsedAt: Date.now(),
};
const parseErrors: string[] = [];
const unknownFields: string[] = [];
for (const line of lines) {
const trimmedLine = line.trim();
if (!trimmedLine) continue;
// Track whether this line matched any known field
let matched = false;
// STATUS field (required)
const statusMatch = trimmedLine.match(RALPH_STATUS_FIELD_PATTERN);
if (statusMatch) {
const value = statusMatch[1].toUpperCase();
if (['IN_PROGRESS', 'COMPLETE', 'BLOCKED'].includes(value)) {
block.status = value as RalphStatusValue;
} else {
parseErrors.push(`Invalid STATUS value: "${value}". Expected: IN_PROGRESS, COMPLETE, or BLOCKED`);
}
matched = true;
}
// TASKS_COMPLETED_THIS_LOOP field
const tasksMatch = trimmedLine.match(RALPH_TASKS_COMPLETED_PATTERN);
if (tasksMatch) {
const value = parseInt(tasksMatch[1], 10);
if (!Number.isNaN(value) && value >= 0) {
block.tasksCompletedThisLoop = value;
} else {
parseErrors.push(
`Invalid TASKS_COMPLETED_THIS_LOOP value: "${tasksMatch[1]}". Expected: non-negative integer`
);
}
matched = true;
}
// FILES_MODIFIED field
const filesMatch = trimmedLine.match(RALPH_FILES_MODIFIED_PATTERN);
if (filesMatch) {
const value = parseInt(filesMatch[1], 10);
if (!Number.isNaN(value) && value >= 0) {
block.filesModified = value;
} else {
parseErrors.push(`Invalid FILES_MODIFIED value: "${filesMatch[1]}". Expected: non-negative integer`);
}
matched = true;
}
// TESTS_STATUS field
const testsMatch = trimmedLine.match(RALPH_TESTS_STATUS_PATTERN);
if (testsMatch) {
const value = testsMatch[1].toUpperCase();
if (['PASSING', 'FAILING', 'NOT_RUN'].includes(value)) {
block.testsStatus = value as RalphTestsStatus;
} else {
parseErrors.push(`Invalid TESTS_STATUS value: "${value}". Expected: PASSING, FAILING, or NOT_RUN`);
}
matched = true;
}
// WORK_TYPE field
const workMatch = trimmedLine.match(RALPH_WORK_TYPE_PATTERN);
if (workMatch) {
const value = workMatch[1].toUpperCase();
if (['IMPLEMENTATION', 'TESTING', 'DOCUMENTATION', 'REFACTORING'].includes(value)) {
block.workType = value as RalphWorkType;
} else {
parseErrors.push(
`Invalid WORK_TYPE value: "${value}". Expected: IMPLEMENTATION, TESTING, DOCUMENTATION, or REFACTORING`
);
}
matched = true;
}
// EXIT_SIGNAL field
const exitMatch = trimmedLine.match(RALPH_EXIT_SIGNAL_PATTERN);
if (exitMatch) {
block.exitSignal = exitMatch[1].toLowerCase() === 'true';
matched = true;
}
// RECOMMENDATION field
const recMatch = trimmedLine.match(RALPH_RECOMMENDATION_PATTERN);
if (recMatch) {
block.recommendation = recMatch[1].trim();
matched = true;
}
// Track unknown fields for debugging (only if looks like a field)
if (!matched && trimmedLine.includes(':')) {
const fieldName = trimmedLine.split(':')[0].trim().toUpperCase();
if (fieldName && !['#', '//'].some((c) => fieldName.startsWith(c))) {
unknownFields.push(fieldName);
}
}
}
// Log parse errors if any
if (parseErrors.length > 0) {
console.warn(`[RalphStatusParser] RALPH_STATUS parse errors:\n - ${parseErrors.join('\n - ')}`);
}
// Log unknown fields if any
if (unknownFields.length > 0) {
console.warn(`[RalphStatusParser] RALPH_STATUS unknown fields: ${unknownFields.join(', ')}`);
}
// Validate required field: STATUS
if (block.status === undefined) {
console.warn('[RalphStatusParser] RALPH_STATUS block missing required STATUS field, skipping');
return;
}
// Fill in defaults for missing optional fields
const fullBlock: RalphStatusBlock = {
status: block.status,
tasksCompletedThisLoop: block.tasksCompletedThisLoop ?? 0,
filesModified: block.filesModified ?? 0,
testsStatus: block.testsStatus ?? 'NOT_RUN',
workType: block.workType ?? 'IMPLEMENTATION',
exitSignal: block.exitSignal ?? false,
recommendation: block.recommendation ?? '',
parsedAt: block.parsedAt!,
};
this._lastStatusBlock = fullBlock;
this.handleStatusBlock(fullBlock);
}
/**
* Handle a parsed RALPH_STATUS block.
* Updates circuit breaker, checks exit conditions.
*
* @param block - Parsed status block
* @fires statusBlockDetected - With the block data
* @fires circuitBreakerUpdate - If state changes
* @fires exitGateMet - If dual-condition exit triggered
*/
private handleStatusBlock(block: RalphStatusBlock): void {
// Update cumulative counts
this._totalFilesModified += block.filesModified;
this._totalTasksCompleted += block.tasksCompletedThisLoop;
// Check for progress (for circuit breaker)
const hasProgress = block.filesModified > 0 || block.tasksCompletedThisLoop > 0;
// Update circuit breaker
this.updateCircuitBreaker(hasProgress, block.testsStatus, block.status);
// Check completion indicators
if (block.status === 'COMPLETE') {
this._completionIndicators++;
}
// Check dual-condition exit gate
if (block.exitSignal && this._completionIndicators >= 2 && !this._exitGateMet) {
this._exitGateMet = true;
this.emit('exitGateMet', {
completionIndicators: this._completionIndicators,
exitSignal: true,
});
}
// Emit the status block
this.emit('statusBlockDetected', block);
}
/**
* Update circuit breaker state based on iteration results.
*
* @param hasProgress - Whether this iteration made progress
* @param testsStatus - Current test status
* @param status - Overall status from RALPH_STATUS
* @fires circuitBreakerUpdate - If state changes
*/
private updateCircuitBreaker(hasProgress: boolean, testsStatus: RalphTestsStatus, status: RalphStatusValue): void {
const prevState = this._circuitBreaker.state;
if (hasProgress) {
// Progress detected - reset counters, possibly close circuit
this._circuitBreaker.consecutiveNoProgress = 0;
this._circuitBreaker.consecutiveSameError = 0;
this._circuitBreaker.lastProgressIteration = this._cycleCount;
if (this._circuitBreaker.state === 'HALF_OPEN') {
this._circuitBreaker.state = 'CLOSED';
this._circuitBreaker.reason = 'Progress detected, circuit closed';
this._circuitBreaker.reasonCode = 'progress_detected';
}
} else {
// No progress
this._circuitBreaker.consecutiveNoProgress++;
// State transitions based on consecutive no-progress
if (this._circuitBreaker.state === 'CLOSED') {
if (this._circuitBreaker.consecutiveNoProgress >= 3) {
this._circuitBreaker.state = 'OPEN';
this._circuitBreaker.reason = `No progress for ${this._circuitBreaker.consecutiveNoProgress} iterations`;
this._circuitBreaker.reasonCode = 'no_progress_open';
} else if (this._circuitBreaker.consecutiveNoProgress >= 2) {
this._circuitBreaker.state = 'HALF_OPEN';
this._circuitBreaker.reason = 'Warning: no progress detected';
this._circuitBreaker.reasonCode = 'no_progress_warning';
}
} else if (this._circuitBreaker.state === 'HALF_OPEN') {
if (this._circuitBreaker.consecutiveNoProgress >= 3) {
this._circuitBreaker.state = 'OPEN';
this._circuitBreaker.reason = `No progress for ${this._circuitBreaker.consecutiveNoProgress} iterations`;
this._circuitBreaker.reasonCode = 'no_progress_open';
}
}
}
// Track tests failure
if (testsStatus === 'FAILING') {
this._circuitBreaker.consecutiveTestsFailure++;
if (this._circuitBreaker.consecutiveTestsFailure >= 5 && this._circuitBreaker.state !== 'OPEN') {
this._circuitBreaker.state = 'OPEN';
this._circuitBreaker.reason = `Tests failing for ${this._circuitBreaker.consecutiveTestsFailure} iterations`;
this._circuitBreaker.reasonCode = 'tests_failing_too_long';
}
} else {
this._circuitBreaker.consecutiveTestsFailure = 0;
}
// Track blocked status
if (status === 'BLOCKED' && this._circuitBreaker.state !== 'OPEN') {
this._circuitBreaker.state = 'OPEN';
this._circuitBreaker.reason = 'Claude reported BLOCKED status';
this._circuitBreaker.reasonCode = 'same_error_repeated';
}
// Emit if state changed
if (prevState !== this._circuitBreaker.state) {
this._circuitBreaker.lastTransitionAt = Date.now();
this.emit('circuitBreakerUpdate', { ...this._circuitBreaker });
}
}
/**
* Check line for completion indicators (natural language patterns).
* Used for dual-condition exit gate.
*
* @param line - Line to check
*/
private detectCompletionIndicators(line: string): void {
for (const pattern of COMPLETION_INDICATOR_PATTERNS) {
if (pattern.test(line)) {
this._completionIndicators++;
break; // Only count once per line
}
}
}
}
+501 -1978
View File
File diff suppressed because it is too large Load Diff
+134
View File
@@ -0,0 +1,134 @@
/**
* @fileoverview Adaptive timing controller for respawn idle detection.
*
* Extracted from respawn-controller.ts for modularity. Tracks historical timing
* data and adjusts the completion confirm timeout dynamically based on the 75th
* percentile of recent idle detection durations.
*
* @module respawn-adaptive-timing
*/
import type { TimingHistory } from './types.js';
/**
* Configuration for adaptive timing bounds.
*/
export interface AdaptiveTimingConfig {
/** Minimum adaptive completion confirm timeout (ms) */
adaptiveMinConfirmMs: number;
/** Maximum adaptive completion confirm timeout (ms) */
adaptiveMaxConfirmMs: number;
}
/**
* Manages adaptive timing for respawn idle detection.
*
* Uses historical idle detection durations to calculate an optimal completion
* confirm timeout. The timeout is based on the 75th percentile of recent
* durations with a 20% safety buffer, clamped to configured bounds.
*/
export class RespawnAdaptiveTiming {
private timingHistory: TimingHistory;
constructor(private config: AdaptiveTimingConfig) {
this.timingHistory = {
recentIdleDetectionMs: [],
recentCycleDurationMs: [],
adaptiveCompletionConfirmMs: 10000, // Start with default
sampleCount: 0,
maxSamples: 20, // Keep last 20 samples for rolling average
lastUpdatedAt: Date.now(),
};
}
/**
* Record timing data from a completed cycle for adaptive adjustments.
*
* @param idleDetectionMs - Time spent detecting idle
* @param cycleDurationMs - Total cycle duration
*/
recordTimingData(idleDetectionMs: number, cycleDurationMs: number): void {
const history = this.timingHistory;
// Add to rolling windows
history.recentIdleDetectionMs.push(idleDetectionMs);
history.recentCycleDurationMs.push(cycleDurationMs);
// Trim to max samples
if (history.recentIdleDetectionMs.length > history.maxSamples) {
history.recentIdleDetectionMs.shift();
}
if (history.recentCycleDurationMs.length > history.maxSamples) {
history.recentCycleDurationMs.shift();
}
history.sampleCount = history.recentIdleDetectionMs.length;
history.lastUpdatedAt = Date.now();
// Recalculate adaptive timing
this.updateAdaptiveTiming();
}
/**
* Get the current adaptive completion confirm timeout.
* Returns the calculated value, or the default if not enough samples.
*
* @returns Completion confirm timeout in milliseconds
*/
getAdaptiveCompletionConfirmMs(): number {
// Need at least 5 samples before adjusting
if (this.timingHistory.sampleCount < 5) {
return this.timingHistory.adaptiveCompletionConfirmMs;
}
return this.timingHistory.adaptiveCompletionConfirmMs;
}
/**
* Get the current timing history for monitoring.
* @returns Copy of timing history
*/
getTimingHistory(): TimingHistory {
return { ...this.timingHistory };
}
/**
* Reset all timing history.
*/
reset(): void {
this.timingHistory = {
recentIdleDetectionMs: [],
recentCycleDurationMs: [],
adaptiveCompletionConfirmMs: 10000,
sampleCount: 0,
maxSamples: 20,
lastUpdatedAt: Date.now(),
};
}
/**
* Recalculate the adaptive completion confirm timeout based on historical data.
* Uses the 75th percentile of recent idle detection times as the new timeout,
* with a 20% buffer for safety.
*/
private updateAdaptiveTiming(): void {
const history = this.timingHistory;
const minMs = this.config.adaptiveMinConfirmMs;
const maxMs = this.config.adaptiveMaxConfirmMs;
if (history.recentIdleDetectionMs.length < 5) return;
// Sort for percentile calculation
const sorted = [...history.recentIdleDetectionMs].sort((a, b) => a - b);
// Use 75th percentile with 20% buffer
const p75Index = Math.floor(sorted.length * 0.75);
const p75Value = sorted[p75Index];
const withBuffer = Math.round(p75Value * 1.2);
// Clamp to configured bounds
const clamped = Math.max(minMs, Math.min(maxMs, withBuffer));
history.adaptiveCompletionConfirmMs = clamped;
}
}
+259 -632
View File
File diff suppressed because it is too large Load Diff
+229
View File
@@ -0,0 +1,229 @@
/**
* @fileoverview Pure health scoring functions for respawn controller.
*
* Extracted from respawn-controller.ts for modularity. All functions are pure
* (no side effects, no state) and take a HealthInputs interface that decouples
* them from direct access to Session, RalphTracker, or AiChecker instances.
*
* @module respawn-health
*/
import type { RespawnAggregateMetrics, RalphLoopHealthScore, HealthStatus, CircuitBreakerStatus } from './types.js';
/**
* Input data for health score calculation.
* Decouples the health calculation from direct access to controller internals.
*/
export interface HealthInputs {
/** Aggregate cycle metrics */
aggregateMetrics: RespawnAggregateMetrics;
/** Current circuit breaker status */
circuitBreakerStatus: CircuitBreakerStatus | null;
/** Iteration stall metrics, or null if tracker unavailable */
iterationStallMetrics: {
stallDurationMs: number;
warningThresholdMs: number;
criticalThresholdMs: number;
} | null;
/** AI checker state summary */
aiCheckerState: {
status: string;
consecutiveErrors: number;
};
/** Number of stuck-state recovery attempts */
stuckRecoveryCount: number;
/** Maximum allowed stuck recoveries */
maxStuckRecoveries: number;
}
/**
* Calculate a comprehensive health score for the Ralph Loop system.
* Aggregates multiple health signals into a single score (0-100).
*
* @param inputs - Health calculation inputs
* @returns Health score with component breakdown
*/
export function calculateHealthScore(inputs: HealthInputs): RalphLoopHealthScore {
const now = Date.now();
const components = {
cycleSuccess: calculateCycleSuccessScore(inputs.aggregateMetrics),
circuitBreaker: calculateCircuitBreakerScore(inputs.circuitBreakerStatus),
iterationProgress: calculateIterationProgressScore(inputs.iterationStallMetrics),
aiChecker: calculateAiCheckerScore(inputs.aiCheckerState),
stuckRecovery: calculateStuckRecoveryScore(inputs.stuckRecoveryCount, inputs.maxStuckRecoveries),
};
// Weighted average (cycle success is most important)
const weights = {
cycleSuccess: 0.35,
circuitBreaker: 0.2,
iterationProgress: 0.2,
aiChecker: 0.15,
stuckRecovery: 0.1,
};
const score = Math.round(
components.cycleSuccess * weights.cycleSuccess +
components.circuitBreaker * weights.circuitBreaker +
components.iterationProgress * weights.iterationProgress +
components.aiChecker * weights.aiChecker +
components.stuckRecovery * weights.stuckRecovery
);
// Determine status
let status: HealthStatus;
if (score >= 90) status = 'excellent';
else if (score >= 70) status = 'good';
else if (score >= 50) status = 'degraded';
else status = 'critical';
// Generate recommendations
const recommendations = generateHealthRecommendations(components);
// Generate summary
const summary = generateHealthSummary(score, status, components);
return {
score,
status,
components,
summary,
recommendations,
calculatedAt: now,
};
}
/**
* Determine whether to skip the /clear step based on current context usage.
* Skips if token count is below the configured threshold percentage.
*
* @param lastTokenCount - Current token count from the session
* @param skipClearThresholdPercent - Threshold percentage below which to skip /clear
* @param maxContextTokens - Approximate max context window size
* @returns True if /clear should be skipped
*/
export function shouldSkipClear(
lastTokenCount: number,
skipClearThresholdPercent: number,
maxContextTokens: number
): boolean {
if (lastTokenCount === 0) return false; // Can't determine, don't skip
const usagePercent = (lastTokenCount / maxContextTokens) * 100;
return usagePercent < skipClearThresholdPercent;
}
/**
* Calculate score based on recent cycle success rate.
*/
function calculateCycleSuccessScore(aggregateMetrics: RespawnAggregateMetrics): number {
if (aggregateMetrics.totalCycles === 0) return 100; // No data = assume healthy
return aggregateMetrics.successRate;
}
/**
* Calculate score based on circuit breaker state.
*/
function calculateCircuitBreakerScore(circuitBreakerStatus: CircuitBreakerStatus | null): number {
if (!circuitBreakerStatus) return 100;
switch (circuitBreakerStatus.state) {
case 'CLOSED':
return 100;
case 'HALF_OPEN':
return 50;
case 'OPEN':
return 0;
default:
return 100;
}
}
/**
* Calculate score based on iteration progress.
*/
function calculateIterationProgressScore(
stallMetrics: { stallDurationMs: number; warningThresholdMs: number; criticalThresholdMs: number } | null
): number {
if (!stallMetrics) return 100;
const { stallDurationMs, warningThresholdMs, criticalThresholdMs } = stallMetrics;
if (stallDurationMs >= criticalThresholdMs) return 0;
if (stallDurationMs >= warningThresholdMs) return 30;
if (stallDurationMs >= warningThresholdMs / 2) return 70;
return 100;
}
/**
* Calculate score based on AI checker health.
*/
function calculateAiCheckerScore(aiCheckerState: { status: string; consecutiveErrors: number }): number {
if (aiCheckerState.status === 'disabled') return 30;
if (aiCheckerState.status === 'cooldown') return 70;
if (aiCheckerState.consecutiveErrors > 0) return 50;
return 100;
}
/**
* Calculate score based on stuck-state recovery count.
*/
function calculateStuckRecoveryScore(stuckRecoveryCount: number, maxStuckRecoveries: number): number {
if (stuckRecoveryCount === 0) return 100;
if (stuckRecoveryCount >= maxStuckRecoveries) return 0;
return Math.round(100 - (stuckRecoveryCount / maxStuckRecoveries) * 100);
}
/**
* Generate health recommendations based on component scores.
*/
function generateHealthRecommendations(components: RalphLoopHealthScore['components']): string[] {
const recommendations: string[] = [];
if (components.cycleSuccess < 70) {
recommendations.push('Cycle success rate is low. Check for recurring errors or stuck states.');
}
if (components.circuitBreaker < 50) {
recommendations.push('Circuit breaker is open or half-open. Review recent errors and consider manual reset.');
}
if (components.iterationProgress < 50) {
recommendations.push('Iteration progress has stalled. Check if Claude is stuck on a task.');
}
if (components.aiChecker < 50) {
recommendations.push('AI idle checker has errors. May need to check Claude CLI availability.');
}
if (components.stuckRecovery < 50) {
recommendations.push('Multiple stuck-state recoveries occurred. Consider increasing timeouts.');
}
if (recommendations.length === 0) {
recommendations.push('System is healthy. No action needed.');
}
return recommendations;
}
/**
* Generate a human-readable health summary.
*/
function generateHealthSummary(
score: number,
status: HealthStatus,
components: RalphLoopHealthScore['components']
): string {
const lowest = Object.entries(components).reduce((min, [key, val]) => (val < min.val ? { key, val } : min), {
key: '',
val: 100,
});
if (status === 'excellent') {
return `Ralph Loop is operating excellently (${score}/100). All systems healthy.`;
}
if (status === 'good') {
return `Ralph Loop is operating well (${score}/100). Minor issues in ${lowest.key}.`;
}
if (status === 'degraded') {
return `Ralph Loop is degraded (${score}/100). Primary issue: ${lowest.key} (${lowest.val}/100).`;
}
return `Ralph Loop is in critical state (${score}/100). Immediate attention needed: ${lowest.key}.`;
}
+229
View File
@@ -0,0 +1,229 @@
/**
* @fileoverview Cycle metrics tracker for respawn controller.
*
* Extracted from respawn-controller.ts for modularity. Tracks per-cycle metrics
* and maintains aggregate statistics across all tracked cycles.
*
* @module respawn-metrics
*/
import { assertNever } from './utils/index.js';
import type { RespawnCycleMetrics, RespawnAggregateMetrics, CycleOutcome } from './types.js';
/**
* Maximum number of cycle metrics to keep in memory.
*/
const MAX_CYCLE_METRICS_IN_MEMORY = 100;
/**
* Tracks respawn cycle metrics and maintains aggregate statistics.
*
* Each respawn cycle is tracked from start to completion, recording timing,
* steps completed, and outcome. Aggregate metrics provide a rolling view
* of system health across recent cycles.
*/
export class RespawnCycleMetricsTracker {
/** Current cycle being tracked */
private currentCycleMetrics: Partial<RespawnCycleMetrics> | null = null;
/** Recent cycle metrics (rolling window for aggregate calculation) */
private recentCycleMetrics: RespawnCycleMetrics[] = [];
/** Aggregate metrics across all tracked cycles */
private aggregateMetrics: RespawnAggregateMetrics = {
totalCycles: 0,
successfulCycles: 0,
stuckRecoveryCycles: 0,
blockedCycles: 0,
errorCycles: 0,
avgCycleDurationMs: 0,
avgIdleDetectionMs: 0,
p90CycleDurationMs: 0,
successRate: 100,
lastUpdatedAt: Date.now(),
};
/**
* Start tracking metrics for a new cycle.
* Called when a respawn cycle begins.
*
* @param sessionId - The session this cycle belongs to
* @param cycleNumber - The cycle number within the session
* @param idleReason - What triggered idle detection
* @param idleDetectionStartTime - Timestamp when idle detection started
* @param lastTokenCount - Token count at start of cycle
* @param adaptiveCompletionConfirmMs - Completion confirm timeout used
*/
startCycle(
sessionId: string,
cycleNumber: number,
idleReason: string,
idleDetectionStartTime: number,
lastTokenCount: number,
adaptiveCompletionConfirmMs: number
): void {
const now = Date.now();
this.currentCycleMetrics = {
cycleId: `${sessionId}:${cycleNumber}`,
sessionId,
cycleNumber,
startedAt: now,
idleReason,
idleDetectionMs: now - idleDetectionStartTime,
stepsCompleted: [],
clearSkipped: false,
tokenCountAtStart: lastTokenCount,
completionConfirmMsUsed: adaptiveCompletionConfirmMs,
};
}
/**
* Record a completed step in the current cycle.
* @param step - Name of the step (e.g., 'update', 'clear', 'init')
*/
recordStep(step: string): void {
if (!this.currentCycleMetrics) return;
this.currentCycleMetrics.stepsCompleted?.push(step);
}
/**
* Mark that /clear was skipped in the current cycle.
*/
markClearSkipped(): void {
if (this.currentCycleMetrics) {
this.currentCycleMetrics.clearSkipped = true;
}
}
/**
* Get the current in-progress cycle metrics (for external inspection).
* @returns The current cycle metrics, or null if no cycle is in progress
*/
getCurrentCycle(): Partial<RespawnCycleMetrics> | null {
return this.currentCycleMetrics;
}
/**
* Complete the current cycle metrics with outcome.
* Adds to recent metrics and updates aggregates.
*
* @param outcome - Outcome of the cycle
* @param lastTokenCount - Token count at end of cycle
* @param errorMessage - Optional error message if outcome is 'error'
* @returns The completed cycle metrics, or null if no cycle was in progress
*/
completeCycle(outcome: CycleOutcome, lastTokenCount: number, errorMessage?: string): RespawnCycleMetrics | null {
if (!this.currentCycleMetrics) return null;
const now = Date.now();
const metrics: RespawnCycleMetrics = {
...(this.currentCycleMetrics as RespawnCycleMetrics),
completedAt: now,
durationMs: now - (this.currentCycleMetrics.startedAt ?? now),
outcome,
errorMessage,
tokenCountAtEnd: lastTokenCount,
};
// Add to recent metrics
this.recentCycleMetrics.push(metrics);
if (this.recentCycleMetrics.length > MAX_CYCLE_METRICS_IN_MEMORY) {
this.recentCycleMetrics.shift();
}
// Update aggregate metrics
this.updateAggregateMetrics(metrics);
// Clear current cycle
this.currentCycleMetrics = null;
return metrics;
}
/**
* Get aggregate metrics for monitoring.
* @returns Copy of aggregate metrics
*/
getAggregate(): RespawnAggregateMetrics {
return { ...this.aggregateMetrics };
}
/**
* Get recent cycle metrics for analysis.
* @param limit - Maximum number of metrics to return (default: 20)
* @returns Recent cycle metrics, newest first
*/
getRecent(limit: number = 20): RespawnCycleMetrics[] {
return this.recentCycleMetrics.slice(-limit).reverse();
}
/**
* Reset all metrics state.
*/
reset(): void {
this.currentCycleMetrics = null;
this.recentCycleMetrics = [];
this.aggregateMetrics = {
totalCycles: 0,
successfulCycles: 0,
stuckRecoveryCycles: 0,
blockedCycles: 0,
errorCycles: 0,
avgCycleDurationMs: 0,
avgIdleDetectionMs: 0,
p90CycleDurationMs: 0,
successRate: 100,
lastUpdatedAt: Date.now(),
};
}
/**
* Update aggregate metrics with a new cycle's data.
* @param metrics - The completed cycle metrics
*/
private updateAggregateMetrics(metrics: RespawnCycleMetrics): void {
const agg = this.aggregateMetrics;
agg.totalCycles++;
switch (metrics.outcome) {
case 'success':
agg.successfulCycles++;
break;
case 'stuck_recovery':
agg.stuckRecoveryCycles++;
break;
case 'blocked':
agg.blockedCycles++;
break;
case 'error':
agg.errorCycles++;
break;
case 'cancelled':
// Cancelled cycles don't count towards any specific category
// but are still counted in totalCycles
break;
default:
assertNever(metrics.outcome, `Unhandled CycleOutcome: ${metrics.outcome}`);
}
// Recalculate averages using all recent metrics
const durations = this.recentCycleMetrics.map((m) => m.durationMs);
const idleTimes = this.recentCycleMetrics.map((m) => m.idleDetectionMs);
if (durations.length > 0) {
agg.avgCycleDurationMs = Math.round(durations.reduce((a, b) => a + b, 0) / durations.length);
agg.avgIdleDetectionMs = Math.round(idleTimes.reduce((a, b) => a + b, 0) / idleTimes.length);
// Calculate P90
const sortedDurations = [...durations].sort((a, b) => a - b);
const p90Index = Math.floor(sortedDurations.length * 0.9);
agg.p90CycleDurationMs = sortedDurations[p90Index];
}
// Calculate success rate
agg.successRate = agg.totalCycles > 0 ? Math.round((agg.successfulCycles / agg.totalCycles) * 100) : 100;
agg.lastUpdatedAt = Date.now();
}
}
+131
View File
@@ -0,0 +1,131 @@
/**
* @fileoverview Pure utility functions for terminal pattern detection in respawn controller.
*
* Extracted from respawn-controller.ts for modularity. These are stateless functions
* and constants used to detect completion messages, working patterns, and token counts
* in terminal output.
*
* @module respawn-patterns
*/
import { TOKEN_PATTERN } from './utils/index.js';
// ========== Constants ==========
/**
* Pattern to detect completion messages from Claude Code.
* Requires "Worked for" prefix to avoid false positives from bare time durations
* in regular text (e.g., "wait for 5s", "run for 2m").
*
* Matches: "Worked for 2m 46s", "Worked for 46s", "Worked for 1h 2m 3s"
* Does NOT match: "wait for 5s", "run for 2m", "for 3s the system..."
*/
const COMPLETION_TIME_PATTERN = /\bWorked\s+for\s+\d+[hms](\s*\d+[hms])*/i;
/**
* Patterns indicating Claude is ready for input (legacy fallback).
* Used as secondary signals, not primary detection.
*/
export const PROMPT_PATTERNS = [
'❯', // Standard prompt
'\u276f', // Unicode variant
'⏵', // Claude Code prompt variant
];
/**
* Patterns indicating Claude is actively working.
* When detected, resets all idle detection timers.
* Note: ✻ and ✽ removed - they appear in completion messages too.
*/
export const WORKING_PATTERNS = [
'Thinking',
'Writing',
'Reading',
'Running',
'Searching',
'Editing',
'Creating',
'Deleting',
'Analyzing',
'Executing',
'Synthesizing',
'Brewing', // Claude's processing indicators
'Compiling',
'Building',
'Installing',
'Fetching',
'Downloading',
'Processing',
'Generating',
'Loading',
'Starting',
'Updating',
'Checking',
'Validating',
'Testing',
'Formatting',
'Linting',
'⠋',
'⠙',
'⠹',
'⠸',
'⠼',
'⠴',
'⠦',
'⠧',
'⠇',
'⠏', // Spinner chars
'◐',
'◓',
'◑',
'◒', // Alternative spinners
'⣾',
'⣽',
'⣻',
'⢿',
'⡿',
'⣟',
'⣯',
'⣷', // Braille spinners
];
/**
* Check if data contains a completion message pattern.
* Matches "Worked for Xh Xm Xs" time duration patterns.
*
* @param data - Raw terminal output data
* @returns True if completion message pattern is found
*/
export function isCompletionMessage(data: string): boolean {
return COMPLETION_TIME_PATTERN.test(data);
}
/**
* Check if a rolling window of terminal output contains working patterns.
* The rolling window catches patterns split across chunks (e.g., "Thin" + "king").
*
* @param window - Rolling window of recent terminal output (already includes current data)
* @returns True if any working pattern is found in the window
*/
export function hasWorkingPattern(window: string): boolean {
return WORKING_PATTERNS.some((pattern) => window.includes(pattern));
}
/**
* Extract token count from data if present.
* Parses patterns like "123.4k tokens" or "1.5M tokens".
*
* @param data - Raw terminal output data
* @returns Parsed token count, or null if no token pattern found
*/
export function extractTokenCount(data: string): number | null {
const match = data.match(TOKEN_PATTERN);
if (!match) return null;
let count = parseFloat(match[1]);
const suffix = match[2]?.toLowerCase();
if (suffix === 'k') count *= 1000;
else if (suffix === 'm') count *= 1000000;
return Math.round(count);
}
+284
View File
@@ -0,0 +1,284 @@
/**
* @fileoverview Auto-compact and auto-clear automation for Session.
*
* Monitors token counts and triggers /compact or /clear commands when
* configurable thresholds are reached. Waits for Claude to be idle
* before sending commands, with retry logic and mutual exclusion
* (compact and clear never run simultaneously).
*
* @module session-auto-ops
*/
import { EventEmitter } from 'node:events';
// ============================================================================
// Timing Constants
// ============================================================================
/** Delay for auto-compact/clear retry attempts (2 seconds) */
const AUTO_RETRY_DELAY_MS = 2000;
/** Delay for auto-compact/clear initial check (1 second) */
const AUTO_INITIAL_DELAY_MS = 1000;
/** Cooldown after compact completes before re-enabling (10 seconds) */
const COMPACT_COOLDOWN_MS = 10000;
/** Cooldown after clear completes before re-enabling (5 seconds) */
const CLEAR_COOLDOWN_MS = 5000;
/** Minimum valid threshold for auto-clear/compact (1000 tokens) */
const MIN_AUTO_THRESHOLD = 1000;
/** Maximum valid threshold for auto-clear/compact (500k tokens) */
const MAX_AUTO_THRESHOLD = 500_000;
/** Default auto-clear threshold when invalid value provided */
const DEFAULT_AUTO_CLEAR_THRESHOLD = 140_000;
/** Default auto-compact threshold when invalid value provided */
const DEFAULT_AUTO_COMPACT_THRESHOLD = 110_000;
/**
* Callbacks required by SessionAutoOps to interact with the parent Session.
*/
export interface AutoOpsCallbacks {
/** Send a command via the terminal multiplexer */
writeCommand: (command: string) => Promise<boolean>;
/** Check if Claude is currently working */
isWorking: () => boolean;
/** Check if the session has been stopped */
isStopped: () => boolean;
/** Get current total token count (input + output) */
getTotalTokens: () => number;
/** Get session ID for logging */
getSessionId: () => string;
}
/**
* Events emitted by SessionAutoOps.
*/
export interface SessionAutoOpsEvents {
/** Auto-compact was triggered and the /compact command was sent */
autoCompact: (data: { tokens: number; threshold: number; prompt?: string }) => void;
/** Auto-clear was triggered and the /clear command was sent */
autoClear: (data: { tokens: number; threshold: number }) => void;
}
/**
* Manages auto-compact and auto-clear automation for a Session.
*
* When enabled, monitors token counts after each update and triggers
* /compact or /clear commands when thresholds are exceeded. Ensures
* mutual exclusion between compact and clear operations.
*/
export class SessionAutoOps extends EventEmitter {
// Auto-compact state
private _autoCompactThreshold: number;
private _autoCompactEnabled: boolean = false;
private _autoCompactPrompt: string = '';
private _isCompacting: boolean = false;
private _autoCompactTimer: NodeJS.Timeout | null = null;
// Auto-clear state
private _autoClearThreshold: number;
private _autoClearEnabled: boolean = false;
private _isClearing: boolean = false;
private _autoClearTimer: NodeJS.Timeout | null = null;
private readonly callbacks: AutoOpsCallbacks;
constructor(callbacks: AutoOpsCallbacks, config?: { compactThreshold?: number; clearThreshold?: number }) {
super();
this.callbacks = callbacks;
this._autoCompactThreshold = config?.compactThreshold ?? DEFAULT_AUTO_COMPACT_THRESHOLD;
this._autoClearThreshold = config?.clearThreshold ?? DEFAULT_AUTO_CLEAR_THRESHOLD;
}
// ============================================================================
// Auto-compact getters/setters
// ============================================================================
get autoCompactThreshold(): number {
return this._autoCompactThreshold;
}
get autoCompactEnabled(): boolean {
return this._autoCompactEnabled;
}
get autoCompactPrompt(): string {
return this._autoCompactPrompt;
}
get isCompacting(): boolean {
return this._isCompacting;
}
setAutoCompact(enabled: boolean, threshold?: number, prompt?: string): void {
this._autoCompactEnabled = enabled;
if (threshold !== undefined) {
if (threshold < MIN_AUTO_THRESHOLD || threshold > MAX_AUTO_THRESHOLD) {
console.warn(
`[SessionAutoOps ${this.callbacks.getSessionId()}] Invalid autoCompact threshold ${threshold}, must be between ${MIN_AUTO_THRESHOLD} and ${MAX_AUTO_THRESHOLD}. Using default ${DEFAULT_AUTO_COMPACT_THRESHOLD}.`
);
this._autoCompactThreshold = DEFAULT_AUTO_COMPACT_THRESHOLD;
} else {
this._autoCompactThreshold = threshold;
}
}
if (prompt !== undefined) {
this._autoCompactPrompt = prompt;
}
}
// ============================================================================
// Auto-clear getters/setters
// ============================================================================
get autoClearThreshold(): number {
return this._autoClearThreshold;
}
get autoClearEnabled(): boolean {
return this._autoClearEnabled;
}
get isClearing(): boolean {
return this._isClearing;
}
setAutoClear(enabled: boolean, threshold?: number): void {
this._autoClearEnabled = enabled;
if (threshold !== undefined) {
if (threshold < MIN_AUTO_THRESHOLD || threshold > MAX_AUTO_THRESHOLD) {
console.warn(
`[SessionAutoOps ${this.callbacks.getSessionId()}] Invalid autoClear threshold ${threshold}, must be between ${MIN_AUTO_THRESHOLD} and ${MAX_AUTO_THRESHOLD}. Using default ${DEFAULT_AUTO_CLEAR_THRESHOLD}.`
);
this._autoClearThreshold = DEFAULT_AUTO_CLEAR_THRESHOLD;
} else {
this._autoClearThreshold = threshold;
}
}
}
// ============================================================================
// Threshold checks
// ============================================================================
/**
* Check if auto-compact should be triggered based on current token count.
* Called after token count updates.
*/
checkAutoCompact(): void {
if (this.callbacks.isStopped()) return;
if (!this._autoCompactEnabled || this._isCompacting || this._isClearing) return;
const totalTokens = this.callbacks.getTotalTokens();
if (totalTokens >= this._autoCompactThreshold) {
this._isCompacting = true;
console.log(
`[SessionAutoOps] Auto-compact triggered: ${totalTokens} tokens >= ${this._autoCompactThreshold} threshold`
);
const checkAndCompact = async () => {
if (this.callbacks.isStopped()) return;
if (!this._isCompacting) return;
if (!this.callbacks.isWorking()) {
if (this.callbacks.isStopped()) return;
const compactCmd = this._autoCompactPrompt ? `/compact ${this._autoCompactPrompt}\r` : '/compact\r';
await this.callbacks.writeCommand(compactCmd);
this.emit('autoCompact', {
tokens: totalTokens,
threshold: this._autoCompactThreshold,
prompt: this._autoCompactPrompt || undefined,
});
if (!this.callbacks.isStopped()) {
this._autoCompactTimer = setTimeout(() => {
if (this.callbacks.isStopped()) return;
this._autoCompactTimer = null;
this._isCompacting = false;
}, COMPACT_COOLDOWN_MS);
}
} else {
if (!this.callbacks.isStopped()) {
this._autoCompactTimer = setTimeout(checkAndCompact, AUTO_RETRY_DELAY_MS);
}
}
};
if (!this.callbacks.isStopped()) {
this._autoCompactTimer = setTimeout(checkAndCompact, AUTO_INITIAL_DELAY_MS);
}
}
}
/**
* Check if auto-clear should be triggered based on current token count.
* Called after token count updates.
*/
checkAutoClear(): void {
if (this.callbacks.isStopped()) return;
if (!this._autoClearEnabled || this._isClearing || this._isCompacting) return;
const totalTokens = this.callbacks.getTotalTokens();
if (totalTokens >= this._autoClearThreshold) {
this._isClearing = true;
console.log(
`[SessionAutoOps] Auto-clear triggered: ${totalTokens} tokens >= ${this._autoClearThreshold} threshold`
);
const checkAndClear = async () => {
if (this.callbacks.isStopped()) return;
if (!this._isClearing) return;
if (!this.callbacks.isWorking()) {
if (this.callbacks.isStopped()) return;
await this.callbacks.writeCommand('/clear\r');
this.emit('autoClear', { tokens: totalTokens, threshold: this._autoClearThreshold });
if (!this.callbacks.isStopped()) {
this._autoClearTimer = setTimeout(() => {
if (this.callbacks.isStopped()) return;
this._autoClearTimer = null;
this._isClearing = false;
}, CLEAR_COOLDOWN_MS);
}
} else {
if (!this.callbacks.isStopped()) {
this._autoClearTimer = setTimeout(checkAndClear, AUTO_RETRY_DELAY_MS);
}
}
};
if (!this.callbacks.isStopped()) {
this._autoClearTimer = setTimeout(checkAndClear, AUTO_INITIAL_DELAY_MS);
}
}
}
// ============================================================================
// Cleanup
// ============================================================================
/**
* Clear all timers and reset state. Called when the session stops.
*/
destroy(): void {
if (this._autoCompactTimer) {
clearTimeout(this._autoCompactTimer);
this._autoCompactTimer = null;
}
this._isCompacting = false;
if (this._autoClearTimer) {
clearTimeout(this._autoClearTimer);
this._autoClearTimer = null;
}
this._isClearing = false;
}
}
+132
View File
@@ -0,0 +1,132 @@
/**
* @fileoverview Pure functions for building CLI arguments and environment variables
* for Claude and OpenCode CLI spawning.
*
* Extracted from Session to keep argument construction logic testable and
* separate from PTY lifecycle management.
*
* @module session-cli-builder
*/
import type { ClaudeMode } from './types.js';
import { getAugmentedPath } from './utils/claude-cli-resolver.js';
/**
* Build Claude CLI permission flags based on the configured mode.
* Returns an array of args to pass to the CLI.
*/
export function buildPermissionArgs(claudeMode: ClaudeMode, allowedTools?: string): string[] {
switch (claudeMode) {
case 'dangerously-skip-permissions':
return ['--dangerously-skip-permissions'];
case 'allowedTools':
if (allowedTools) {
return ['--allowedTools', allowedTools];
}
// Fall back to normal mode if no tools specified
return [];
case 'normal':
default:
return [];
}
}
/**
* Build args for an interactive Claude CLI session (direct PTY, non-mux fallback).
*
* @param sessionId - The Codeman session ID (passed as --session-id to Claude)
* @param claudeMode - Permission mode for the CLI
* @param model - Optional model override (e.g., 'opus', 'sonnet')
* @param allowedTools - Optional comma-separated allowed tools list
* @returns Array of CLI arguments
*/
export function buildInteractiveArgs(
sessionId: string,
claudeMode: ClaudeMode,
model?: string,
allowedTools?: string
): string[] {
const args = [...buildPermissionArgs(claudeMode, allowedTools), '--session-id', sessionId];
if (model) args.push('--model', model);
return args;
}
/**
* Build args for a one-shot Claude CLI prompt (runPrompt mode).
*
* @param prompt - The prompt text to send
* @param model - Optional model override
* @returns Array of CLI arguments
*/
export function buildPromptArgs(prompt: string, model?: string): string[] {
const args = ['-p', '--verbose', '--dangerously-skip-permissions', '--output-format', 'stream-json'];
if (model) {
args.push('--model', model);
}
args.push(prompt);
return args;
}
/**
* Build environment variables for Claude CLI processes (direct PTY, non-mux).
*
* Augments process.env with:
* - UTF-8 locale settings
* - Augmented PATH (includes Claude CLI directory)
* - xterm-256color terminal type
* - Codeman session identification vars
*
* @param sessionId - The Codeman session ID
* @returns Environment variables object for pty.spawn
*/
export function buildClaudeEnv(sessionId: string): Record<string, string | undefined> {
return {
...process.env,
LANG: 'en_US.UTF-8',
LC_ALL: 'en_US.UTF-8',
PATH: getAugmentedPath(),
TERM: 'xterm-256color',
COLORTERM: undefined,
CLAUDECODE: undefined,
// Inform Claude it's running within Codeman (helps prevent self-termination)
CODEMAN_MUX: '1',
CODEMAN_SESSION_ID: sessionId,
CODEMAN_API_URL: process.env.CODEMAN_API_URL || 'http://localhost:3000',
};
}
/**
* Build environment variables for mux-attached PTY sessions (tmux attach).
* Lighter than buildClaudeEnv — no PATH augmentation or Codeman vars needed
* since the mux session already has those set.
*
* @returns Environment variables object for pty.spawn
*/
export function buildMuxAttachEnv(): Record<string, string | undefined> {
return {
...process.env,
LANG: 'en_US.UTF-8',
LC_ALL: 'en_US.UTF-8',
TERM: 'xterm-256color',
COLORTERM: undefined,
CLAUDECODE: undefined,
};
}
/**
* Build environment variables for a direct shell session (non-mux fallback).
*
* @param sessionId - The Codeman session ID
* @returns Environment variables object for pty.spawn
*/
export function buildShellEnv(sessionId: string): Record<string, string | undefined> {
return {
...process.env,
LANG: 'en_US.UTF-8',
LC_ALL: 'en_US.UTF-8',
TERM: 'xterm-256color',
CODEMAN_MUX: '1',
CODEMAN_SESSION_ID: sessionId,
CODEMAN_API_URL: process.env.CODEMAN_API_URL || 'http://localhost:3000',
};
}
+101
View File
@@ -0,0 +1,101 @@
/**
* @fileoverview LRU cache for task descriptions parsed from terminal output.
*
* Stores descriptions extracted from Claude Code's Task tool invocations
* (e.g., "Explore(Check files)") keyed by timestamp. Used to correlate
* with SubagentWatcher discoveries for better window titles.
*
* @module session-task-cache
*/
import { LRUMap } from './utils/lru-map.js';
/** Default maximum number of task descriptions to keep */
const DEFAULT_MAX_SIZE = 100;
/** Default maximum age for task descriptions (30 seconds) */
const DEFAULT_MAX_AGE_MS = 30_000;
/**
* LRU cache for task descriptions parsed from terminal output.
*
* Descriptions are keyed by the timestamp when they were parsed.
* Old entries are automatically cleaned up based on maxAgeMs.
* Size is bounded by the underlying LRUMap.
*/
export class SessionTaskCache {
private readonly cache: LRUMap<number, string>;
private readonly maxAgeMs: number;
constructor(maxSize: number = DEFAULT_MAX_SIZE, maxAgeMs: number = DEFAULT_MAX_AGE_MS) {
this.cache = new LRUMap<number, string>({ maxSize });
this.maxAgeMs = maxAgeMs;
}
/**
* Add a task description at the given timestamp.
*/
add(timestamp: number, description: string): void {
this.cache.set(timestamp, description);
}
/**
* Remove task descriptions older than maxAgeMs.
* LRUMap maintains insertion order, so we can break early
* once we find a non-expired entry.
*/
private cleanupOld(): void {
const cutoff = Date.now() - this.maxAgeMs;
for (const timestamp of this.cache.keysInOrder()) {
if (timestamp < cutoff) {
this.cache.delete(timestamp);
} else {
break;
}
}
}
/**
* Get all recent task descriptions sorted by timestamp (most recent first).
*/
getAll(): Array<{ timestamp: number; description: string }> {
this.cleanupOld();
const results: Array<{ timestamp: number; description: string }> = [];
for (const [timestamp, description] of this.cache) {
results.push({ timestamp, description });
}
return results.sort((a, b) => b.timestamp - a.timestamp);
}
/**
* Find a task description that was parsed close to a given timestamp.
* Used to correlate with SubagentWatcher discoveries.
*
* @param subagentStartTime - The timestamp when the subagent was discovered
* @param maxAgeMs - Maximum age difference to consider (default 10 seconds)
* @returns The matching description or undefined
*/
findNear(subagentStartTime: number, maxAgeMs: number = 10000): string | undefined {
this.cleanupOld();
let bestMatch: { timestamp: number; description: string } | undefined;
let bestDiff = Infinity;
for (const [timestamp, description] of this.cache) {
const diff = Math.abs(subagentStartTime - timestamp);
if (diff < maxAgeMs && diff < bestDiff) {
bestMatch = { timestamp, description };
bestDiff = diff;
}
}
return bestMatch?.description;
}
/**
* Clear all cached descriptions.
*/
clear(): void {
this.cache.clear();
}
}
+66 -316
View File
@@ -36,7 +36,6 @@ import { TaskTracker, type BackgroundTask } from './task-tracker.js';
import { RalphTracker } from './ralph-tracker.js';
import { BashToolParser } from './bash-tool-parser.js';
import { BufferAccumulator } from './utils/buffer-accumulator.js';
import { LRUMap } from './utils/lru-map.js';
import { ANSI_ESCAPE_PATTERN_FULL, TOKEN_PATTERN, SPINNER_PATTERN, MAX_SESSION_TOKENS } from './utils/index.js';
import {
MAX_TERMINAL_BUFFER_SIZE,
@@ -46,6 +45,15 @@ import {
MAX_MESSAGES,
MAX_LINE_BUFFER_SIZE,
} from './config/buffer-limits.js';
import {
buildInteractiveArgs,
buildPromptArgs,
buildClaudeEnv,
buildMuxAttachEnv,
buildShellEnv,
} from './session-cli-builder.js';
import { SessionAutoOps } from './session-auto-ops.js';
import { SessionTaskCache } from './session-task-cache.js';
export type { BackgroundTask } from './task-tracker.js';
export type { RalphTrackerState, RalphTodoItem, ActiveBashTool } from './types.js';
@@ -63,11 +71,7 @@ const MUX_STARTUP_DELAY_MS = 300;
/** Delay before declaring session idle after last output (2 seconds) */
const IDLE_DETECTION_DELAY_MS = 2000;
/** Delay for auto-compact/clear retry attempts (2 seconds) */
const AUTO_RETRY_DELAY_MS = 2000;
/** Delay for auto-compact/clear initial check (1 second) */
const AUTO_INITIAL_DELAY_MS = 1000;
// Note: Auto-compact/clear timing constants moved to session-auto-ops.ts
/** Graceful shutdown delay when stopping session (100ms) */
const GRACEFUL_SHUTDOWN_DELAY_MS = 100;
@@ -93,8 +97,7 @@ const CTRL_L_PATTERN = /\x0c/g;
/** Pattern to split by newlines (CR or LF) */
const NEWLINE_SPLIT_PATTERN = /\r?\n/;
// Claude CLI PATH resolution — shared utility
import { getAugmentedPath } from './utils/claude-cli-resolver.js';
// Note: Claude CLI PATH resolution moved to session-cli-builder.ts (buildClaudeEnv)
/**
* Represents a JSON message from Claude CLI's stream-json output format.
@@ -224,9 +227,8 @@ export class Session extends EventEmitter {
readonly createdAt: number;
readonly mode: SessionMode;
/** Maximum number of task descriptions to keep (LRUMap handles size limit automatically) */
private static readonly MAX_TASK_DESCRIPTIONS = 100;
private static readonly TASK_DESCRIPTION_MAX_AGE_MS = 30000; // Keep descriptions for 30 seconds
// Task description cache (extracted to SessionTaskCache)
private _taskCache = new SessionTaskCache();
private _name: string;
private ptyProcess: pty.IPty | null = null;
@@ -255,15 +257,9 @@ export class Session extends EventEmitter {
// Token tracking for auto-clear
private _totalInputTokens: number = 0;
private _totalOutputTokens: number = 0;
private _autoClearThreshold: number = 140000; // Default 140k tokens
private _autoClearEnabled: boolean = false;
private _isClearing: boolean = false; // Prevent recursive clearing
// Auto-compact settings
private _autoCompactThreshold: number = 110000; // Default 110k tokens (lower than clear)
private _autoCompactEnabled: boolean = false;
private _autoCompactPrompt: string = ''; // Optional prompt for compact
private _isCompacting: boolean = false; // Prevent recursive compacting
// Auto-compact/auto-clear automation (extracted to SessionAutoOps)
private _autoOps!: SessionAutoOps;
// Image watcher setting (per-session toggle)
private _imageWatcherEnabled: boolean = false;
@@ -279,8 +275,6 @@ export class Session extends EventEmitter {
private _cliInfoParsed: boolean = false; // Only parse once per session
// Timer tracking for cleanup (prevents memory leaks)
private _autoCompactTimer: NodeJS.Timeout | null = null;
private _autoClearTimer: NodeJS.Timeout | null = null;
private _promptCheckInterval: NodeJS.Timeout | null = null;
private _promptCheckTimeout: NodeJS.Timeout | null = null;
private _shellIdleTimer: NodeJS.Timeout | null = null;
@@ -340,12 +334,7 @@ export class Session extends EventEmitter {
toolsUpdate: (tools: ActiveBashTool[]) => void;
} | null = null;
// Task descriptions parsed from terminal output (e.g., "Explore(Description)")
// Used to correlate with SubagentWatcher discoveries for better window titles
// Uses LRUMap for automatic eviction at MAX_TASK_DESCRIPTIONS limit
private _recentTaskDescriptions: LRUMap<number, string> = new LRUMap({
maxSize: Session.MAX_TASK_DESCRIPTIONS,
});
// Task descriptions parsed from terminal output — delegated to SessionTaskCache
// Throttle expensive PTY processing (Ralph, bash parser, task descriptions)
// Accumulates clean data between processing windows to avoid running regex on every chunk
@@ -463,6 +452,22 @@ export class Session extends EventEmitter {
this._bashToolParser.on('toolStart', this._bashToolHandlers.toolStart);
this._bashToolParser.on('toolEnd', this._bashToolHandlers.toolEnd);
this._bashToolParser.on('toolsUpdate', this._bashToolHandlers.toolsUpdate);
// Initialize auto-compact/auto-clear automation and forward events
this._autoOps = new SessionAutoOps({
writeCommand: (cmd) => this.writeViaMux(cmd),
isWorking: () => this._isWorking,
isStopped: () => this._isStopped,
getTotalTokens: () => this._totalInputTokens + this._totalOutputTokens,
getSessionId: () => this.id,
});
this._autoOps.on('autoCompact', (data) => this.emit('autoCompact', data));
this._autoOps.on('autoClear', (data) => {
// Reset token counts on clear
this._totalInputTokens = 0;
this._totalOutputTokens = 0;
this.emit('autoClear', data);
});
}
get status(): SessionStatus {
@@ -597,25 +602,7 @@ export class Session extends EventEmitter {
return this._allowedTools;
}
/**
* Build Claude CLI permission flags based on the configured mode.
* Returns an array of args to pass to the CLI.
*/
private _buildPermissionArgs(): string[] {
switch (this._claudeMode) {
case 'dangerously-skip-permissions':
return ['--dangerously-skip-permissions'];
case 'allowedTools':
if (this._allowedTools) {
return ['--allowedTools', this._allowedTools];
}
// Fall back to normal mode if no tools specified
return [];
case 'normal':
default:
return [];
}
}
// Note: _buildPermissionArgs removed — now using buildInteractiveArgs from session-cli-builder.ts
/**
* Set CPU priority configuration.
@@ -689,11 +676,11 @@ export class Session extends EventEmitter {
}
get autoClearThreshold(): number {
return this._autoClearThreshold;
return this._autoOps.autoClearThreshold;
}
get autoClearEnabled(): boolean {
return this._autoClearEnabled;
return this._autoOps.autoClearEnabled;
}
get name(): string {
@@ -704,58 +691,24 @@ export class Session extends EventEmitter {
this._name = value;
}
/** Minimum valid threshold for auto-clear/compact (1000 tokens) */
private static readonly MIN_AUTO_THRESHOLD = 1000;
/** Maximum valid threshold for auto-clear/compact (500k tokens) */
private static readonly MAX_AUTO_THRESHOLD = 500_000;
/** Default auto-clear threshold when invalid value provided */
private static readonly DEFAULT_AUTO_CLEAR_THRESHOLD = 140_000;
/** Default auto-compact threshold when invalid value provided */
private static readonly DEFAULT_AUTO_COMPACT_THRESHOLD = 110_000;
setAutoClear(enabled: boolean, threshold?: number): void {
this._autoClearEnabled = enabled;
if (threshold !== undefined) {
// Validate threshold bounds
if (threshold < Session.MIN_AUTO_THRESHOLD || threshold > Session.MAX_AUTO_THRESHOLD) {
console.warn(
`[Session ${this.id}] Invalid autoClear threshold ${threshold}, must be between ${Session.MIN_AUTO_THRESHOLD} and ${Session.MAX_AUTO_THRESHOLD}. Using default ${Session.DEFAULT_AUTO_CLEAR_THRESHOLD}.`
);
this._autoClearThreshold = Session.DEFAULT_AUTO_CLEAR_THRESHOLD;
} else {
this._autoClearThreshold = threshold;
}
}
this._autoOps.setAutoClear(enabled, threshold);
}
get autoCompactThreshold(): number {
return this._autoCompactThreshold;
return this._autoOps.autoCompactThreshold;
}
get autoCompactEnabled(): boolean {
return this._autoCompactEnabled;
return this._autoOps.autoCompactEnabled;
}
get autoCompactPrompt(): string {
return this._autoCompactPrompt;
return this._autoOps.autoCompactPrompt;
}
setAutoCompact(enabled: boolean, threshold?: number, prompt?: string): void {
this._autoCompactEnabled = enabled;
if (threshold !== undefined) {
// Validate threshold bounds
if (threshold < Session.MIN_AUTO_THRESHOLD || threshold > Session.MAX_AUTO_THRESHOLD) {
console.warn(
`[Session ${this.id}] Invalid autoCompact threshold ${threshold}, must be between ${Session.MIN_AUTO_THRESHOLD} and ${Session.MAX_AUTO_THRESHOLD}. Using default ${Session.DEFAULT_AUTO_COMPACT_THRESHOLD}.`
);
this._autoCompactThreshold = Session.DEFAULT_AUTO_COMPACT_THRESHOLD;
} else {
this._autoCompactThreshold = threshold;
}
}
if (prompt !== undefined) {
this._autoCompactPrompt = prompt;
}
this._autoOps.setAutoCompact(enabled, threshold, prompt);
}
get imageWatcherEnabled(): boolean {
@@ -797,11 +750,11 @@ export class Session extends EventEmitter {
lastActivityAt: this._lastActivityAt,
name: this._name,
mode: this.mode,
autoClearEnabled: this._autoClearEnabled,
autoClearThreshold: this._autoClearThreshold,
autoCompactEnabled: this._autoCompactEnabled,
autoCompactThreshold: this._autoCompactThreshold,
autoCompactPrompt: this._autoCompactPrompt,
autoClearEnabled: this._autoOps.autoClearEnabled,
autoClearThreshold: this._autoOps.autoClearThreshold,
autoCompactEnabled: this._autoOps.autoCompactEnabled,
autoCompactThreshold: this._autoOps.autoCompactThreshold,
autoCompactPrompt: this._autoOps.autoCompactPrompt,
imageWatcherEnabled: this._imageWatcherEnabled,
totalCost: this._totalCost,
inputTokens: this._totalInputTokens,
@@ -865,8 +818,8 @@ export class Session extends EventEmitter {
total: this._totalInputTokens + this._totalOutputTokens,
},
autoClear: {
enabled: this._autoClearEnabled,
threshold: this._autoClearThreshold,
enabled: this._autoOps.autoClearEnabled,
threshold: this._autoOps.autoClearThreshold,
},
// CPU priority configuration
nice: {
@@ -979,14 +932,7 @@ export class Session extends EventEmitter {
cols: 120,
rows: 40,
cwd: this.workingDir,
env: {
...process.env,
LANG: 'en_US.UTF-8',
LC_ALL: 'en_US.UTF-8',
TERM: 'xterm-256color',
COLORTERM: undefined,
CLAUDECODE: undefined,
},
env: buildMuxAttachEnv(),
}
);
@@ -1061,26 +1007,13 @@ export class Session extends EventEmitter {
try {
// Pass --session-id to use the SAME ID as the Codeman session
// This ensures subagents can be directly matched to the correct tab
const args = [...this._buildPermissionArgs(), '--session-id', this.id];
if (this._model) args.push('--model', this._model);
const args = buildInteractiveArgs(this.id, this._claudeMode, this._model, this._allowedTools);
this.ptyProcess = pty.spawn('claude', args, {
name: 'xterm-256color',
cols: 120,
rows: 40,
cwd: this.workingDir,
env: {
...process.env,
LANG: 'en_US.UTF-8',
LC_ALL: 'en_US.UTF-8',
PATH: getAugmentedPath(),
TERM: 'xterm-256color',
COLORTERM: undefined,
CLAUDECODE: undefined,
// Inform Claude it's running within Codeman (helps prevent self-termination)
CODEMAN_MUX: '1',
CODEMAN_SESSION_ID: this.id,
CODEMAN_API_URL: process.env.CODEMAN_API_URL || 'http://localhost:3000',
},
env: buildClaudeEnv(this.id),
});
} catch (spawnErr) {
console.error('[Session] Failed to spawn Claude PTY:', spawnErr);
@@ -1372,14 +1305,7 @@ export class Session extends EventEmitter {
cols: 120,
rows: 40,
cwd: this.workingDir,
env: {
...process.env,
LANG: 'en_US.UTF-8',
LC_ALL: 'en_US.UTF-8',
TERM: 'xterm-256color',
COLORTERM: undefined,
CLAUDECODE: undefined,
},
env: buildMuxAttachEnv(),
}
);
} catch (spawnErr) {
@@ -1413,15 +1339,7 @@ export class Session extends EventEmitter {
cols: 120,
rows: 40,
cwd: this.workingDir,
env: {
...process.env,
LANG: 'en_US.UTF-8',
LC_ALL: 'en_US.UTF-8',
TERM: 'xterm-256color',
CODEMAN_MUX: '1',
CODEMAN_SESSION_ID: this.id,
CODEMAN_API_URL: process.env.CODEMAN_API_URL || 'http://localhost:3000',
},
env: buildShellEnv(this.id),
});
} catch (spawnErr) {
console.error('[Session] Failed to spawn shell PTY:', spawnErr);
@@ -1530,11 +1448,7 @@ export class Session extends EventEmitter {
model ? `(model: ${model})` : ''
);
const args = ['-p', '--verbose', '--dangerously-skip-permissions', '--output-format', 'stream-json'];
if (model) {
args.push('--model', model);
}
args.push(prompt);
const args = buildPromptArgs(prompt, model);
try {
this.ptyProcess = pty.spawn('claude', args, {
@@ -1542,19 +1456,7 @@ export class Session extends EventEmitter {
cols: 120,
rows: 40,
cwd: this.workingDir,
env: {
...process.env,
LANG: 'en_US.UTF-8',
LC_ALL: 'en_US.UTF-8',
PATH: getAugmentedPath(),
TERM: 'xterm-256color',
COLORTERM: undefined,
CLAUDECODE: undefined,
// Inform Claude it's running within Codeman
CODEMAN_MUX: '1',
CODEMAN_SESSION_ID: this.id,
CODEMAN_API_URL: process.env.CODEMAN_API_URL || 'http://localhost:3000',
},
env: buildClaudeEnv(this.id),
});
} catch (spawnErr) {
console.error('[Session] Failed to spawn Claude PTY for runPrompt:', spawnErr);
@@ -1725,8 +1627,8 @@ export class Session extends EventEmitter {
}
// Check if we should auto-compact or auto-clear
this.checkAutoCompact();
this.checkAutoClear();
this._autoOps.checkAutoCompact();
this._autoOps.checkAutoClear();
}
}
@@ -1784,30 +1686,7 @@ export class Session extends EventEmitter {
while ((match = TASK_TOOL_PATTERN.exec(cleanLine)) !== null) {
const description = match[2].trim();
if (description && description.length > 0) {
const now = Date.now();
this._recentTaskDescriptions.set(now, description);
// Cleanup old entries
this.cleanupOldTaskDescriptions();
}
}
}
/**
* Remove task descriptions older than TASK_DESCRIPTION_MAX_AGE_MS.
* Size limit is handled automatically by LRUMap eviction on set().
*/
private cleanupOldTaskDescriptions(): void {
const cutoff = Date.now() - Session.TASK_DESCRIPTION_MAX_AGE_MS;
// Keys are timestamps - iterate and delete expired entries
// LRUMap maintains insertion order, so we can break early once we find a non-expired entry
for (const timestamp of this._recentTaskDescriptions.keysInOrder()) {
if (timestamp < cutoff) {
this._recentTaskDescriptions.delete(timestamp);
} else {
// Keys are ordered by insertion time (which is the timestamp)
// Once we find a non-expired one, all subsequent are also non-expired
break;
this._taskCache.add(Date.now(), description);
}
}
}
@@ -1817,12 +1696,7 @@ export class Session extends EventEmitter {
* Returns descriptions sorted by timestamp (most recent first).
*/
getRecentTaskDescriptions(): Array<{ timestamp: number; description: string }> {
this.cleanupOldTaskDescriptions();
const results: Array<{ timestamp: number; description: string }> = [];
for (const [timestamp, description] of this._recentTaskDescriptions) {
results.push({ timestamp, description });
}
return results.sort((a, b) => b.timestamp - a.timestamp);
return this._taskCache.getAll();
}
/**
@@ -1834,21 +1708,7 @@ export class Session extends EventEmitter {
* @returns The matching description or undefined
*/
findTaskDescriptionNear(subagentStartTime: number, maxAgeMs: number = 10000): string | undefined {
this.cleanupOldTaskDescriptions();
// Find the most recent description that was parsed before or around the subagent start time
let bestMatch: { timestamp: number; description: string } | undefined;
let bestDiff = Infinity;
for (const [timestamp, description] of this._recentTaskDescriptions) {
const diff = Math.abs(subagentStartTime - timestamp);
if (diff < maxAgeMs && diff < bestDiff) {
bestMatch = { timestamp, description };
bestDiff = diff;
}
}
return bestMatch?.description;
return this._taskCache.findNear(subagentStartTime, maxAgeMs);
}
// Parse token count from Claude's status line in interactive mode
@@ -1913,8 +1773,8 @@ export class Session extends EventEmitter {
this._totalOutputTokens += Math.round(delta * 0.4);
// Check if we should auto-compact or auto-clear
this.checkAutoCompact();
this.checkAutoClear();
this._autoOps.checkAutoCompact();
this._autoOps.checkAutoClear();
}
}
}
@@ -1997,107 +1857,7 @@ export class Session extends EventEmitter {
}
}
// Check if we should auto-compact based on token threshold
private checkAutoCompact(): void {
if (this._isStopped) return; // Early exit check
if (!this._autoCompactEnabled || this._isCompacting || this._isClearing) return;
const totalTokens = this._totalInputTokens + this._totalOutputTokens;
if (totalTokens >= this._autoCompactThreshold) {
this._isCompacting = true;
console.log(`[Session] Auto-compact triggered: ${totalTokens} tokens >= ${this._autoCompactThreshold} threshold`);
// Wait for Claude to be idle before compacting
const checkAndCompact = async () => {
// Check if session is still valid (not stopped) - must be first check
if (this._isStopped) return;
if (!this._isCompacting) return;
if (!this._isWorking) {
// Re-check stopped state after async operation might have completed
if (this._isStopped) return;
// Send /compact command with optional prompt
const compactCmd = this._autoCompactPrompt ? `/compact ${this._autoCompactPrompt}\r` : '/compact\r';
await this.writeViaMux(compactCmd);
this.emit('autoCompact', {
tokens: totalTokens,
threshold: this._autoCompactThreshold,
prompt: this._autoCompactPrompt || undefined,
});
// Wait a moment then re-enable (longer than clear since compact takes time)
if (!this._isStopped) {
this._autoCompactTimer = setTimeout(() => {
if (this._isStopped) return; // Check at callback start
this._autoCompactTimer = null;
this._isCompacting = false;
}, 10000);
}
} else {
// Check again after delay
if (!this._isStopped) {
this._autoCompactTimer = setTimeout(checkAndCompact, AUTO_RETRY_DELAY_MS);
}
}
};
// Start checking after a short delay
if (!this._isStopped) {
this._autoCompactTimer = setTimeout(checkAndCompact, AUTO_INITIAL_DELAY_MS);
}
}
}
// Check if we should auto-clear based on token threshold
private checkAutoClear(): void {
if (this._isStopped) return; // Early exit check
if (!this._autoClearEnabled || this._isClearing || this._isCompacting) return;
const totalTokens = this._totalInputTokens + this._totalOutputTokens;
if (totalTokens >= this._autoClearThreshold) {
this._isClearing = true;
console.log(`[Session] Auto-clear triggered: ${totalTokens} tokens >= ${this._autoClearThreshold} threshold`);
// Wait for Claude to be idle before clearing
const checkAndClear = async () => {
// Check if session is still valid (not stopped) - must be first check
if (this._isStopped) return;
if (!this._isClearing) return;
if (!this._isWorking) {
// Re-check stopped state after async operation might have completed
if (this._isStopped) return;
// Send /clear command
await this.writeViaMux('/clear\r');
// Reset token counts
this._totalInputTokens = 0;
this._totalOutputTokens = 0;
this.emit('autoClear', { tokens: totalTokens, threshold: this._autoClearThreshold });
// Wait a moment then re-enable
if (!this._isStopped) {
this._autoClearTimer = setTimeout(() => {
if (this._isStopped) return; // Check at callback start
this._autoClearTimer = null;
this._isClearing = false;
}, 5000);
}
} else {
// Check again after delay
if (!this._isStopped) {
this._autoClearTimer = setTimeout(checkAndClear, AUTO_RETRY_DELAY_MS);
}
}
};
// Start checking after a short delay
if (!this._isStopped) {
this._autoClearTimer = setTimeout(checkAndClear, AUTO_INITIAL_DELAY_MS);
}
}
}
// Note: checkAutoCompact/checkAutoClear moved to SessionAutoOps (this._autoOps)
/**
* Sends input directly to the PTY process.
@@ -2265,18 +2025,8 @@ export class Session extends EventEmitter {
this._lineBufferFlushTimer = null;
}
// Clear auto-compact/auto-clear timers to prevent memory leaks
if (this._autoCompactTimer) {
clearTimeout(this._autoCompactTimer);
this._autoCompactTimer = null;
}
this._isCompacting = false;
if (this._autoClearTimer) {
clearTimeout(this._autoClearTimer);
this._autoClearTimer = null;
}
this._isClearing = false;
// Destroy auto-compact/auto-clear automation (clears its timers)
this._autoOps.destroy();
// Clear prompt check timers
if (this._promptCheckInterval) {
@@ -2357,7 +2107,7 @@ export class Session extends EventEmitter {
this._currentTaskId = null;
// Clear task description cache and agent tree to prevent memory leak
this._recentTaskDescriptions.clear();
this._taskCache.clear();
this._childAgentIds = [];
// Kill the associated mux session if requested
@@ -2413,6 +2163,6 @@ export class Session extends EventEmitter {
this._messages = [];
this._taskTracker.clear();
this._ralphTracker.clear();
this._recentTaskDescriptions.clear();
this._taskCache.clear();
}
}