centient 2.21.0 → 2.25.0

package/CHANGELOG.md

@@ -5,6 +5,111 @@ All notable changes to the MCP Server for Context Engineering.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [2.23.0] - 2026-01-11
+
+### Changed
+
+- **Complete OpenAI to Gemini Migration** - All embeddings now use Gemini
+  - `PatternIndexer` migrated from `text-embedding-3-small` to `gemini-embedding-001`
+  - `RewardHistoryStore` migrated from `text-embedding-3-large` to `gemini-embedding-001`
+  - Vector dimensions: 1536 → 3072 for PatternIndexer (auto-migrates collection)
+  - RewardHistoryStore already used 3072 dimensions (no collection change needed)
+
+- **Simplified API Dependencies** - Reduced from 4 to 3 required services
+  - Removed: `OPENAI_API_KEY` (no longer used)
+  - Kept: `QDRANT_URL` + `QDRANT_API_KEY` (vector storage)
+  - Kept: `GEMINI_API_KEY` (embeddings + file search)
+  - Kept: `OPENROUTER_API_KEY` (LLM completions)
+
+- **Health Check Updated** - No longer checks OpenAI API
+  - Removed OpenAI from environment variable display
+  - Removed OpenAI service connectivity test
+  - Config display (`--config`) no longer shows OPENAI_API_KEY
+
+### Benefits
+
+- **Cost Reduction** - Gemini embeddings ~5x cheaper than OpenAI
+- **Fewer Dependencies** - One less API key to manage
+- **Consistency** - All embedding operations use same provider
+- **Higher Dimensions** - 3072 vs 1536 = better semantic resolution
+
+## [2.22.0] - 2026-01-11
+
+### Added
+
+- **CLI Module** - Standard command-line interface for centient
+  - `--version/-V` - Show version number
+  - `--help/-h` - Show help message
+  - `--list-tools/-l` - List all 92 MCP tools by module
+  - `--health` - Run health check (validates API connections)
+  - `--config` - Show current configuration
+  - `--stats` - Show usage statistics from audit log
+  - `--monitor` - Real-time audit log viewer with colorized output
+  - `--monitor --follow` - Continuous monitoring mode
+
+- **Instance Registry** - Multi-process monitoring support
+  - Instances register at `~/.centient/instances/<pid>.json`
+  - Heartbeat updates every 30 seconds
+  - Stale detection for instances older than 2 minutes
+  - Tracks: PID, project path, version, tool count, memory usage, request count
+
+- **TTY Detection** - Colors disabled when output is piped
+
+### Changed
+
+- **Test Suite** - 1300 passing tests across 39 test files
+
+### Documentation
+
+- Added `CENTIENT_MONITOR_SPEC.md` for external monitoring tool specification
+- Updated `CLAUDE.md` with CLI commands and instance registry protocol
+
+## [2.21.0] - 2026-01-11
+
+### Added
+
+- **Trails Module** (8 new tools) - DevLex syntopic trail discovery
+  - `trail_query_topics` - Browse topic hierarchy (domains/subdomains)
+  - `trail_query_by_topic` - Find articles by topic
+  - `trail_query_intersect` - Find topic overlaps
+  - `trail_discover_convergence` - Find converging insights from independent sources
+  - `trail_discover_influence` - Trace influence chains through knowledge
+  - `trail_discover_auto` - Auto-discover trails based on patterns
+  - `trail_list` - List existing trails
+  - `trail_view` - View trail details
+
+- **Knowledge Module** (3 new tools) - Cross-project meta-knowledge
+  - `promote_learning` - Promote insights to ~/.mcp-context/learnings/
+  - `promote_decision` - Promote decisions to ~/.mcp-context/decisions/
+  - `search_meta_knowledge` - Search cross-project knowledge
+
+- **Pattern Signing** - `signPattern` tool for SHA-256 integrity checksums
+
+### Changed
+
+- **Package Renamed** - `mcp-context-server` → `centient`
+  - npm package name updated
+  - MCP server name updated to `centient`
+  - Slash commands updated to use `mcp__centient__*`
+
+- **Tool Counts Updated**
+  - Total: 92 tools across 16 modules (was 84 across 15)
+  - Patterns: 13 tools (added signPattern)
+  - Artifacts: 5 tools (added diffSessions)
+  - Metrics: 5 tools (added getAuditLog)
+  - Session: 20 tools (added ask_session)
+  - Health: 4 tools (added getCircuitBreakerStats, getRateLimitStats)
+
+- **Test Suite** - 1258 passing tests across 37 test files
+
+### Documentation
+
+- Comprehensive documentation overhaul for v2.21.0
+- MCP_TOOLS_REFERENCE.md updated with Knowledge and Trails modules
+- README.md updated with all 16 modules
+- Removed duplicate README-Upgrade.md from root
+- Fixed version/tool count inconsistencies across all docs
+
 ## [2.20.0] - 2026-01-11
 
 ### Added
@@ -337,6 +442,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ---
 
+[2.21.0]: https://github.com/Szermer/centient/compare/v2.20.0...v2.21.0
 [2.20.0]: https://github.com/Szermer/centient/compare/v2.19.0...v2.20.0
 [2.19.0]: https://github.com/Szermer/centient/compare/v2.14.0...v2.19.0
 [2.14.0]: https://github.com/Szermer/centient/compare/v2.13.0...v2.14.0

package/README.md

@@ -1,9 +1,9 @@
 # Centient
 
-**Version:** 2.20.0
+**Version:** 2.24.0
 **Status:** Production Ready
-**Tools:** 84 across 16 modules
-**Tests:** 1258 passing
+**Tools:** 93 across 16 modules
+**Tests:** 1343 passing
 
 Centient is an MCP server that exposes context engineering operations as executable tools, enabling progressive skill loading and achieving **98.7% token reduction** through intelligent context management.
 
@@ -107,18 +107,94 @@ For full functionality, add environment variables to your config:
 
 **Minimal setup:** Core functionality works without API keys. Features degrade gracefully.
 
+## CLI Commands
+
+Centient provides CLI commands for project scaffolding and diagnostics.
+
+### Project Scaffolding
+
+Initialize and maintain slash commands in your project:
+
+```bash
+# Initialize .claude/ directory with command templates
+centient init
+
+# Force overwrite existing files
+centient init --force
+
+# Check status of installed commands
+centient check-commands
+
+# Update outdated commands (preserves customizations)
+centient update-commands
+```
+
+**Command Status:**
+| Status | Description |
+|--------|-------------|
+| Current | Installed version matches template |
+| Missing | Template not installed |
+| Outdated | Installed version lower than template |
+| Customized | No version header (user modified) |
+
+**What `centient init` creates:**
+```
+.claude/
+├── commands/
+│   ├── session-start.md    # Initialize session memory
+│   ├── note.md             # Add decision/hypothesis/blocker
+│   ├── checkpoint.md       # Save progress checkpoint
+│   ├── finalize.md         # End session, create artifacts
+│   ├── promote.md          # Promote to cross-project knowledge
+│   ├── patterns.md         # Search pattern library
+│   ├── recall.md           # Recall from memory
+│   ├── check-duplicate.md  # Detect duplicate work
+│   ├── constraint.md       # Manage constraints
+│   ├── history.md          # Browse session history
+│   └── session-status.md   # Show session state
+├── hooks/                  # (if templates exist)
+└── settings.json           # (if template exists)
+```
+
+### Diagnostics
+
+```bash
+# Show version
+centient --version
+
+# Show help
+centient --help
+
+# List all 93 MCP tools
+centient --list-tools
+
+# Run health check (validates API connections)
+centient --health
+
+# Show configuration (env vars, paths)
+centient --config
+
+# Show usage statistics from audit log
+centient --stats
+
+# Monitor audit log activity
+centient --monitor              # Last 20 events
+centient --monitor --last 50    # Last 50 events
+centient --monitor --follow     # Live tail mode
+```
+
 ## Architecture
 
-### 16 Modules, 84 Tools
+### 16 Modules, 93 Tools
 
 | Module                               | Tools | Purpose                                                 |
 | ------------------------------------ | ----- | ------------------------------------------------------- |
 | [Patterns](#patterns-module)         | 13    | Progressive skill loading with versioning               |
-| [Artifacts](#artifacts-module)       | 4     | Historical session knowledge access                     |
+| [Artifacts](#artifacts-module)       | 5     | Historical session knowledge access                     |
 | [Memory](#memory-module)             | 3     | Session runtime context (file-based)                    |
-| [Metrics](#metrics-module)           | 4     | Performance and cost tracking                           |
+| [Metrics](#metrics-module)           | 5     | Performance and cost tracking                           |
 | [Search](#search-module)             | 3     | Semantic search via Google File Search                  |
-| [Session](#session-module)           | 19    | Real-time Qdrant coordination + Hallucination Detection |
+| [Session](#session-module)           | 20    | Real-time Qdrant coordination + Hallucination Detection |
 | [Stuck](#stuck-module)               | 2     | Stuck detection and recovery                            |
 | [Health](#health-module)             | 4     | System health and service monitoring                    |
 | [Research](#research-module)         | 5     | Research workflow management                            |
@@ -126,6 +202,9 @@ For full functionality, add environment variables to your config:
 | [Graph](#graph-module)               | 3     | Temporal relationship tracking                          |
 | [Consultation](#consultation-module) | 9     | Cross-model validation                                  |
 | [Branching](#branching-module)       | 6     | Session branching and decision trees                    |
+| [Knowledge](#knowledge-module)       | 3     | Cross-project meta-knowledge                            |
+| [Trails](#trails-module)             | 8     | DevLex syntopic trail discovery                         |
+| [RLVR](#rlvr-module)                 | 1     | Reinforcement learning verification                     |
 
 ### Patterns Module (13 tools)
 
@@ -145,7 +224,7 @@ Progressive skill loading with **98.7% token reduction**:
 - `predictOutcome` - Predict success probability before execution
 - `signPattern` - Sign pattern with SHA-256 checksums for integrity
 
-### Artifacts Module (4 tools)
+### Artifacts Module (5 tools)
 
 Historical session knowledge access:
 
@@ -153,6 +232,7 @@ Historical session knowledge access:
 - `loadSession` - Load session context (with optional query filtering)
 - `getSessionCode` - Extract executable code from sessions
 - `extractSessionContext` - Extract compressed context for handoffs
+- `diffSessions` - Compare two sessions side-by-side
 
 ### Memory Module (3 tools)
 
@@ -162,7 +242,7 @@ File-based session notes:
 - `getDecisions` - Retrieve session decisions
 - `getHypotheses` - Retrieve session hypotheses
 
-### Metrics Module (4 tools)
+### Metrics Module (5 tools)
 
 Performance measurement:
 
@@ -170,6 +250,7 @@ Performance measurement:
 - `getPatternReuse` - Track pattern reuse statistics
 - `getCostDashboard` - API cost tracking by service/model
 - `getPatternAnalytics` - Historical usage trends
+- `getAuditLog` - Query audit log for pattern/skill access history
 
 ### Search Module (3 tools)
 
@@ -179,7 +260,7 @@ Semantic search via Google File Search:
 - `indexSession` - Index session to File Search store
 - `getSearchStats` - Get indexing statistics and costs
 
-### Session Module (19 tools)
+### Session Module (20 tools)
 
 Real-time coordination via Qdrant + Hallucination Detection:
 
@@ -188,9 +269,10 @@ Real-time coordination via Qdrant + Hallucination Detection:
 - `start_session_coordination` - Initialize Qdrant session memory
 - `save_session_note` - Save decision/hypothesis/blocker/finding
 - `session_search` - Fast semantic search (50-200ms)
+- `ask_session` - Natural language queries against session memory
 - `check_duplicate_work` - Detect duplicate implementations
 - `get_session_stats` - Get session statistics
-- `get_session_summary` - **NEW:** Comprehensive summary with branch visualization
+- `get_session_summary` - Comprehensive summary with branch visualization
 - `extract_session_memories` - Extract learnings for finalization
 - `finalize_session_coordination` - Cleanup ephemeral memory
 
@@ -289,6 +371,33 @@ Decision Point → Create Branch → Explore → Close Branch
                                               └── abandon (incomplete)
 ```
 
+### Knowledge Module (3 tools)
+
+Cross-project meta-knowledge for Tier 3 universal learnings:
+
+- `promote_learning` - Promote insights to ~/.mcp-context/learnings/
+- `promote_decision` - Promote decisions to ~/.mcp-context/decisions/
+- `search_meta_knowledge` - Search cross-project knowledge
+
+### Trails Module (8 tools)
+
+DevLex syntopic trail discovery for knowledge exploration:
+
+- `trail_query_topics` - Browse topic hierarchy (domains/subdomains)
+- `trail_query_by_topic` - Find articles by topic
+- `trail_query_intersect` - Find topic overlaps
+- `trail_discover_convergence` - Find converging insights from independent sources
+- `trail_discover_influence` - Trace influence chains through knowledge
+- `trail_discover_auto` - Auto-discover trails based on patterns
+- `trail_list` - List existing trails
+- `trail_view` - View trail details
+
+### RLVR Module (1 tool)
+
+Reinforcement learning verification:
+
+- `run_rlvr_task` - Execute RLVR verification tasks
+
 ## Usage Examples
 
 ### Progressive Skill Loading (98.7% Token Reduction)
@@ -373,7 +482,7 @@ const feasibility = await check_code_feasibility({
 ```bash
 npm run build          # Compile TypeScript
 npm run dev            # Development with auto-reload
-npm test               # Run 801 tests
+npm test               # Run 1343 tests
 npm run test:coverage  # With coverage report
 npm run lint           # Type checking
 ```
@@ -383,24 +492,28 @@ npm run lint           # Type checking
 ```
 src/
 ├── index.ts              # Entry point (stdio transport)
-├── server.ts             # MCP server config (71 tools)
+├── server.ts             # MCP server config (93 tools)
 ├── tools/
-│   ├── patterns/         # Progressive skill loading (9 tools)
-│   ├── artifacts/        # Historical knowledge (4 tools)
+│   ├── patterns/         # Progressive skill loading (13 tools)
+│   ├── artifacts/        # Historical knowledge (5 tools)
 │   ├── memory/           # File-based notes (3 tools)
-│   ├── metrics/          # Performance tracking (4 tools)
+│   ├── metrics/          # Performance tracking (5 tools)
 │   ├── search/           # Semantic search (3 tools)
-│   ├── session/          # Qdrant coordination (19 tools)
+│   ├── session/          # Qdrant coordination (20 tools)
 │   ├── stuck/            # Stuck detection (2 tools)
-│   ├── health/           # System health (2 tools)
+│   ├── health/           # System health (4 tools)
 │   ├── research/         # Research workflow (5 tools)
 │   ├── memory-bank/      # Vertex AI memory (2 tools)
 │   ├── graph/            # Temporal relationships (3 tools)
 │   ├── consultation/     # Cross-model validation (9 tools)
-│   └── branching/        # Session branching (6 tools)
+│   ├── branching/        # Session branching (6 tools)
+│   ├── knowledge/        # Cross-project meta-knowledge (3 tools)
+│   ├── trails/           # DevLex syntopic discovery (8 tools)
+│   └── rlvr/             # RLVR verification (1 tool)
 └── utils/
     ├── SessionCoordinator.ts   # Qdrant session management
     ├── ResearchCoordinator.ts  # Research session management
+    ├── MetaKnowledgeManager.ts # Cross-project meta-knowledge
     └── tokenEstimator.ts       # Token usage tracking
 ```
 
@@ -409,7 +522,7 @@ src/
 | Document                                                | Description                        |
 | ------------------------------------------------------- | ---------------------------------- |
 | [CLAUDE.md](./CLAUDE.md)                                | Claude Code integration guide      |
-| [MCP_TOOLS_REFERENCE.md](./docs/MCP_TOOLS_REFERENCE.md) | Complete tool reference (71 tools) |
+| [MCP_TOOLS_REFERENCE.md](./docs/MCP_TOOLS_REFERENCE.md) | Complete tool reference (93 tools) |
 | [DEVELOPER_GUIDE.md](./docs/DEVELOPER_GUIDE.md)         | Guide for extending the server     |
 | [ARCHITECTURE.md](./docs/ARCHITECTURE.md)               | System architecture and design     |
 | [DESIGN_DECISIONS.md](./docs/DESIGN_DECISIONS.md)       | Technical decision rationale       |
@@ -429,5 +542,5 @@ MIT
 ---
 
 **Created:** 2025-11-05
-**Last Updated:** 2025-01-02
+**Last Updated:** 2026-01-12
 **Maintainer:** Stephen Szermer

package/dist/cli.d.ts

@@ -0,0 +1,38 @@
+import { Tool } from "@modelcontextprotocol/sdk/types.js";
+export declare function printVersion(): void;
+export declare function printHelp(): void;
+export declare function printTools(tools: Tool[]): void;
+export declare function printHealth(): Promise<void>;
+export declare function printConfig(): void;
+export declare function printStats(): Promise<void>;
+export declare function log(options: {
+    last: number;
+    follow: boolean;
+}): Promise<void>;
+export declare function monitor(options: MonitorOptions): Promise<void>;
+export interface MonitorOptions {
+    follow: boolean;
+    project?: string;
+    json: boolean;
+    quiet: boolean;
+    summary: boolean;
+}
+export interface LogOptions {
+    last: number;
+    follow: boolean;
+}
+export interface InitOptions {
+    force: boolean;
+}
+export interface UpdateOptions {
+    force: boolean;
+    dryRun: boolean;
+}
+export declare function parseArgs(args: string[]): {
+    action: "server" | "version" | "help" | "list-tools" | "health" | "config" | "monitor" | "log" | "stats" | "init" | "check-commands" | "update-commands";
+    monitorOptions?: MonitorOptions;
+    logOptions?: LogOptions;
+    initOptions?: InitOptions;
+    updateOptions?: UpdateOptions;
+};
+//# sourceMappingURL=cli.d.ts.map

package/dist/cli.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"cli.d.ts","sourceRoot":"","sources":["../src/cli.ts"],"names":[],"mappings":"AAaA,OAAO,EAAE,IAAI,EAAE,MAAM,oCAAoC,CAAC;AAgC1D,wBAAgB,YAAY,IAAI,IAAI,CAEnC;AAKD,wBAAgB,SAAS,IAAI,IAAI,CAgDhC;AAKD,wBAAgB,UAAU,CAAC,KAAK,EAAE,IAAI,EAAE,GAAG,IAAI,CAoF9C;AAKD,wBAAsB,WAAW,IAAI,OAAO,CAAC,IAAI,CAAC,CAqFjD;AAKD,wBAAgB,WAAW,IAAI,IAAI,CAsClC;AAgID,wBAAsB,UAAU,IAAI,OAAO,CAAC,IAAI,CAAC,CA8GhD;AAKD,wBAAsB,GAAG,CAAC,OAAO,EAAE;IAAE,IAAI,EAAE,MAAM,CAAC;IAAC,MAAM,EAAE,OAAO,CAAA;CAAE,GAAG,OAAO,CAAC,IAAI,CAAC,CAuGnF;AAmMD,wBAAsB,OAAO,CAAC,OAAO,EAAE,cAAc,GAAG,OAAO,CAAC,IAAI,CAAC,CAgFpE;AAKD,MAAM,WAAW,cAAc;IAC7B,MAAM,EAAE,OAAO,CAAC;IAChB,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,IAAI,EAAE,OAAO,CAAC;IACd,KAAK,EAAE,OAAO,CAAC;IACf,OAAO,EAAE,OAAO,CAAC;CAClB;AAKD,MAAM,WAAW,UAAU;IACzB,IAAI,EAAE,MAAM,CAAC;IACb,MAAM,EAAE,OAAO,CAAC;CACjB;AAKD,MAAM,WAAW,WAAW;IAC1B,KAAK,EAAE,OAAO,CAAC;CAChB;AAKD,MAAM,WAAW,aAAa;IAC5B,KAAK,EAAE,OAAO,CAAC;IACf,MAAM,EAAE,OAAO,CAAC;CACjB;AAKD,wBAAgB,SAAS,CAAC,IAAI,EAAE,MAAM,EAAE,GAAG;IACzC,MAAM,EAAE,QAAQ,GAAG,SAAS,GAAG,MAAM,GAAG,YAAY,GAAG,QAAQ,GAAG,QAAQ,GAAG,SAAS,GAAG,KAAK,GAAG,OAAO,GAAG,MAAM,GAAG,gBAAgB,GAAG,iBAAiB,CAAC;IACzJ,cAAc,CAAC,EAAE,cAAc,CAAC;IAChC,UAAU,CAAC,EAAE,UAAU,CAAC;IACxB,WAAW,CAAC,EAAE,WAAW,CAAC;IAC1B,aAAa,CAAC,EAAE,aAAa,CAAC;CAC/B,CAuIA"}