network-ai 4.13.0 → 4.13.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +8 -3
- package/SKILL.md +2 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -5,9 +5,9 @@
|
|
|
5
5
|
[](https://network-ai.org/)
|
|
6
6
|
[](https://github.com/Jovancoding/Network-AI/actions/workflows/ci.yml)
|
|
7
7
|
[](https://github.com/Jovancoding/Network-AI/actions/workflows/codeql.yml)
|
|
8
|
-
[](https://github.com/Jovancoding/Network-AI/releases)
|
|
9
9
|
[](https://www.npmjs.com/package/network-ai)
|
|
10
|
-
[](#testing)
|
|
11
11
|
[](#adapter-system)
|
|
12
12
|
[](LICENSE)
|
|
13
13
|
[](https://socket.dev/npm/package/network-ai/overview)
|
|
@@ -94,6 +94,10 @@ Runs priority preemption, AuthGuardian permission gating, FSM governance, and co
|
|
|
94
94
|
| ✅ Flow control | Pause / resume / throttle writes on the blackboard |
|
|
95
95
|
| ✅ Skill composition | `chain()` / `batch()` / `loop()` / `verify()` meta-operations over agent calls |
|
|
96
96
|
| ✅ Semantic memory search | BYOE vector store with cosine similarity over blackboard data |
|
|
97
|
+
| ✅ Phase pipeline | Multi-phase workflows with human-in-the-loop approval gates |
|
|
98
|
+
| ✅ Confidence filtering | Multi-agent result scoring, threshold validation, and consensus aggregation |
|
|
99
|
+
| ✅ Matcher-based hooks | Glob patterns on agent/action/tool for targeted hook filtering |
|
|
100
|
+
| ✅ Fan-out / fan-in | Parallel agent spawning with pluggable aggregation strategies |
|
|
97
101
|
| ✅ TypeScript native | ES2022 strict mode, zero native dependencies |
|
|
98
102
|
|
|
99
103
|
---
|
|
@@ -389,7 +393,7 @@ npm run test:priority # Priority & preemption
|
|
|
389
393
|
npm run test:cli # CLI layer
|
|
390
394
|
```
|
|
391
395
|
|
|
392
|
-
**1,
|
|
396
|
+
**1,924 passing assertions across 23 test suites** (`npm run test:all`):
|
|
393
397
|
|
|
394
398
|
| Suite | Assertions | Covers |
|
|
395
399
|
|---|---|---|
|
|
@@ -414,6 +418,7 @@ npm run test:cli # CLI layer
|
|
|
414
418
|
| `test-cli.ts` | 65 | CLI layer: bb, auth, budget, audit commands |
|
|
415
419
|
| `test-qa.ts` | 67 | QA orchestrator: scenarios, feedback loop, regression, contradictions |
|
|
416
420
|
| `test-phase7.ts` | 94 | Deferred init, hook middleware, flow control, skill composer, semantic search |
|
|
421
|
+
| `test-phase8.ts` | 146 | Phase pipeline, confidence filter, matcher-based hooks, fan-out/fan-in |
|
|
417
422
|
|
|
418
423
|
---
|
|
419
424
|
|
package/SKILL.md
CHANGED
|
@@ -498,6 +498,8 @@ Use for redundancy - take first successful result.
|
|
|
498
498
|
### Strategy 4: Chain
|
|
499
499
|
Sequential processing - output of one feeds into next.
|
|
500
500
|
|
|
501
|
+
> **TypeScript engine (v4.13.0):** These strategies map directly to the `FanOutFanIn` module (`lib/fan-out.ts`) which provides `merge`, `vote`, `firstSuccess`, and `consensus` fan-in strategies with concurrency control. For multi-phase workflows with approval gates, see `PhasePipeline` (`lib/phase-pipeline.ts`). For result scoring and threshold filtering, see `ConfidenceFilter` (`lib/confidence-filter.ts`). Matcher-based hooks (`lib/adapter-hooks.ts`) can target specific agents or tools via glob patterns.
|
|
502
|
+
|
|
501
503
|
### Example Parallel Workflow
|
|
502
504
|
|
|
503
505
|
> **Platform note:** `sessions_send` and `sessions_history` are **OpenClaw host platform built-ins**, not provided by this skill. This skill provides only the `swarm_guard.py` budget/handoff check that runs before each delegation.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "network-ai",
|
|
3
|
-
"version": "4.13.
|
|
3
|
+
"version": "4.13.1",
|
|
4
4
|
"description": "AI agent orchestration framework for TypeScript/Node.js - 17 adapters (LangChain, AutoGen, CrewAI, OpenAI Assistants, LlamaIndex, Semantic Kernel, Haystack, DSPy, Agno, MCP, OpenClaw, A2A, Codex, MiniMax, NemoClaw, APS + streaming variants). Built-in CLI, security, swarm intelligence, real-time streaming, and agentic workflow patterns.",
|
|
5
5
|
"homepage": "https://network-ai.org",
|
|
6
6
|
"main": "dist/index.js",
|