agentic-flow 2.0.1-alpha.23 → 2.0.1-alpha.32

package/CHANGELOG.md

@@ -2,6 +2,195 @@
 
 All notable changes to this project will be documented in this file.
 
+## [2.0.1-alpha.29] - 2025-12-31
+
+### Added
+- **E2B Sandbox Integration**: Secure cloud sandboxes for AI code execution
+  - Firecracker-based isolation with Code Interpreter support
+  - Python, JavaScript, and shell execution
+  - File system access and package installation
+  - `E2BSandboxManager`, `runInE2BSandbox()`, `isE2BAvailable()`
+
+- **Query Control System**: Runtime control of active SDK queries
+  - Change model mid-execution (`setModel()`)
+  - Switch permission modes (`setPermissionMode()`)
+  - Interrupt, resume, and abort queries
+  - Query introspection (commands, models, MCP status)
+  - `createQueryController()`, `getActiveQueries()`, `abortAllQueries()`
+
+- **Plugins System**: Flexible plugin loading and management
+  - Load from local filesystem, NPM packages, remote URLs, or inline
+  - Plugin tool execution with typed definitions
+  - Checksum verification for remote plugins
+  - `loadPlugin()`, `getAllPluginTools()`, `executePluginTool()`, `defineTool()`
+
+- **Streaming Input Mode**: Async iterable prompts for SDK
+  - `StreamingPromptBuilder` with fluent API
+  - `InteractivePromptStream` for real-time input
+  - Transform, filter, batch, and rate-limit operations
+  - `streamingPrompt()`, `createInteractiveStream()`, `fromArray()`
+
+- **Security Module**: Comprehensive security hardening
+  - Path sanitization with traversal protection
+  - Command injection detection (20+ patterns)
+  - Secret redaction (API keys, tokens, DB URLs, private keys)
+  - Rate limiting with sliding window
+  - Audit logging with file persistence
+  - `sanitizePath()`, `validateCommand()`, `redactSecrets()`, `checkRateLimit()`, `auditLog()`
+
+### Tests
+- 47 security tests covering all security functions
+- 46 SDK module tests for E2B, query control, plugins, and streaming
+- All 93 tests passing
+
+## [2.0.1-alpha.28] - 2025-12-31
+
+### Added
+- **SDK Structured Outputs**: `outputFormat` with JSON schema support
+- **SDK Sandbox Configuration**: Environment variable control for sandbox mode
+- **Beta Features**: 1M context window support (`SDK_ENABLE_BETAS=true`)
+- **Query Limits**: `maxTurns` and `maxBudgetUsd` controls
+- **File Checkpointing**: Persistent session state (`SDK_FILE_CHECKPOINTING=true`)
+
+### Environment Variables
+- `SDK_OUTPUT_SCHEMA` - JSON schema for structured output
+- `SDK_ENABLE_SANDBOX` - Enable SDK sandbox mode
+- `SDK_ENABLE_BETAS` - Enable beta features (1M context)
+- `SDK_MAX_TURNS` - Maximum conversation turns
+- `SDK_MAX_BUDGET_USD` - Maximum cost limit
+- `SDK_FILE_CHECKPOINTING` - Enable file checkpointing
+
+## [2.0.1-alpha.27] - 2025-12-31
+
+### Fixed
+- **Permission Handler**: Overly broad command substitution blocking
+  - Changed `/\$\(.*\)/` to specific dangerous patterns
+  - Safe patterns like `$(date)` now allowed
+- **Memory Leaks**: Added TTL-based cleanup for Maps
+  - `activeTrajectories`: 5-minute TTL with 2-minute cleanup
+  - `activeSessions`: 30-minute TTL with 5-minute cleanup
+- **Agent Converter**: Added 1-minute cache for converted agents
+  - `invalidateAgentCache()` function for manual cache clearing
+
+### Added
+- New dangerous patterns: `git push --force`, `npm publish`, `cat .env`
+- TTL cleanup intervals for trajectory and session Maps
+- Agent conversion caching for performance
+
+### Tests
+- 20 permission handler tests (all passing)
+- Includes git force push, npm publish, safe command substitution
+
+## [2.0.1-alpha.26] - 2025-12-31
+
+### Added
+- **SDK Integration Module**: Full Claude Agent SDK v0.1.76 support
+  - Hooks bridge with trajectory tracking
+  - Session management with resume/fork
+  - Custom permission handlers
+  - Agent converter for subagent spawning
+  - All 17 SDK tools enabled
+
+### Exports (src/sdk/index.ts)
+- Hooks: `preToolUseHook`, `postToolUseHook`, `sessionStartHook`, etc.
+- Sessions: `captureSessionId`, `getResumeOptions`, `getForkOptions`
+- Permissions: `customPermissionHandler`, `strictPermissionHandler`
+- Agents: `convertAgentToSdkFormat`, `getAgentsForUseCase`
+
+## [2.0.1-alpha.25] - 2025-12-31
+
+### Added
+- **Multi-Algorithm Learning Engine**: 9 specialized RL algorithms for different task types
+
+  | Algorithm            | Task Type           | Why                              |
+  |----------------------|---------------------|----------------------------------|
+  | double-q             | agent-routing       | Reduces overestimation bias      |
+  | sarsa                | error-avoidance     | Conservative, on-policy          |
+  | actor-critic         | confidence-scoring  | Continuous 0-1 scores            |
+  | ppo                  | context-ranking     | Stable preference learning       |
+  | decision-transformer | trajectory-learning | Sequence patterns                |
+  | td-lambda            | memory-recall       | Better credit assignment         |
+  | q-learning           | pattern-matching    | Fast value-based matching        |
+  | reinforce            | exploration         | Policy gradient for novel tasks  |
+  | a2c                  | multi-agent         | Advantage estimation             |
+
+### New Functions (IntelligenceBridge)
+- `getAlgorithmForTask(taskType)` - Get recommended algorithm and reason
+- `learnFromEpisode(taskType, state, action, reward, nextState, done)` - Learn with appropriate algorithm
+- `getActionValue(taskType, state, action)` - Get Q-value or policy probability
+- `getMultiAlgorithmStats()` - Get per-algorithm episode counts and avg rewards
+
+### Updated
+- `ruvector` upgraded to `^0.1.69` with multi-algorithm learning engine
+- `getIntelligenceStats()` now includes `multiAlgorithmStats`
+- Features list now includes `multi-algorithm-rl`
+
+### Usage
+```typescript
+import { getAlgorithmForTask, learnFromEpisode } from 'agentic-flow/hooks';
+
+// Get recommended algorithm for a task
+const { algorithm, reason } = getAlgorithmForTask('agent-routing');
+// => { algorithm: 'double-q', reason: 'Reduces overestimation bias...' }
+
+// Learn from an episode
+const result = await learnFromEpisode(
+  'error-avoidance',  // Uses SARSA (conservative)
+  'state',
+  'action',
+  0.9,  // reward
+  'nextState',
+  true  // done
+);
+```
+
+## [2.0.1-alpha.24] - 2025-12-31
+
+### Added
+- **Tiered TensorCompress**: Dynamic compression based on access frequency
+  - **Hot patterns** (>80% freq): No compression (0% savings) - fastest access
+  - **Warm patterns** (40-80% freq): Half precision (50% savings)
+  - **Cool patterns** (10-40% freq): PQ8 quantization (87.5% savings)
+  - **Cold patterns** (1-10% freq): PQ4 quantization (93.75% savings)
+  - **Archive patterns** (<1% freq): Binary (96.9% savings)
+
+### Improved
+- **Access Frequency Tracking**: Each pattern tracks total accesses, creation time
+- **Dynamic Tier Migration**: Patterns automatically move between tiers based on usage
+- **Periodic Recompression**: Background process migrates patterns every 5 minutes
+- **Memory Efficiency**: Up to 96.9% memory savings for rarely-used patterns
+- **Stats Display**: New compression tier distribution table in `enhanced_booster_stats`
+
+### IntelligenceBridge Integration
+- **TensorCompress in Hooks**: Tiered compression now integrated into hooks intelligence layer
+- **storePattern**: New patterns start as "hot" (no compression), migrate based on access
+- **findSimilarPatterns**: Tracks accesses for automatic tier migration
+- **routeTaskIntelligent**: Pattern results now tracked for compression decisions
+- **getIntelligenceStats**: Now includes `compressionStats` with tier distribution
+- **Backward Compatible**: Existing patterns continue to work without modification
+
+### Technical Details
+- Access frequency = 50% access ratio + 30% recency (24hr decay) + 20% success rate
+- New patterns start as "hot" (no compression) since they're likely to be reused
+- Recompression runs non-blocking in background during apply()
+- Backward-compatible with older pattern files (auto-migrates fields)
+
+### Stats Output
+```
+🗜️ Tiered Compression:
+   ┌─────────────────────────────────────────────────┐
+   │ Tier      │ Count │ Access Freq │ Memory Save  │
+   ├─────────────────────────────────────────────────┤
+   │ 🔥 Hot    │    15 │ >80%        │ 0%           │
+   │ 🌡️ Warm   │     8 │ 40-80%      │ 50%          │
+   │ ❄️ Cool   │    12 │ 10-40%      │ 87.5%        │
+   │ 🧊 Cold   │    25 │ 1-10%       │ 93.75%       │
+   │ 📦 Archive│    40 │ <1%         │ 96.9%        │
+   └─────────────────────────────────────────────────┘
+   Compression Ratio: 4.2:1
+   Memory Savings: 76.2%
+```
+
 ## [2.0.1-alpha.23] - 2025-12-31
 
 ### Added