This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+14 more
Affected surfaces
ReleasePort's take
Light signalRelease v5.8.0 introduces several new CLI and API features including a self‑diagnostic command, inspection tools, pause/resume controls, permission scoring explanations, and minimal mode flags for faster CI/test runs.
Why it matters: The added `--minimal` flag disables WAL replay and TTL sweep, accelerating CI/test startup times—a measurable performance gain when enabled.
Summary
AI summaryAdded network-ai doctor self‑diagnostic command and related inspection/pause features.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
Adds `network-ai doctor` self-diagnostic command. Adds `network-ai doctor` self-diagnostic command. Source: llm_adapter@2026-05-23 Confidence: high |
— |
| Feature | Medium |
Adds `network-ai inspect <key>` to view blackboard key details. Adds `network-ai inspect <key>` to view blackboard key details. Source: llm_adapter@2026-05-23 Confidence: high |
— |
| Feature | Medium |
Adds `network-ai pause` and `network-ai resume` kill‑switch commands. Adds `network-ai pause` and `network-ai resume` kill‑switch commands. Source: llm_adapter@2026-05-23 Confidence: high |
— |
| Feature | Medium |
Adds `--why` flag to `auth token` for permission scoring breakdown. Adds `--why` flag to `auth token` for permission scoring breakdown. Source: llm_adapter@2026-05-23 Confidence: high |
— |
| Feature | Medium |
Adds global `--minimal` flag to disable WAL replay and TTL sweep for faster CI/test startup. Adds global `--minimal` flag to disable WAL replay and TTL sweep for faster CI/test startup. Source: llm_adapter@2026-05-23 Confidence: high |
— |
| Feature | Medium |
Adds `AuthGuardian.scoreRequest()` method returning full scoring breakdown without issuing a token. Adds `AuthGuardian.scoreRequest()` method returning full scoring breakdown without issuing a token. Source: llm_adapter@2026-05-23 Confidence: high |
— |
| Feature | Medium |
Adds `disableWal` option to `LockedBlackboardOptions`; also activated by `NETWORK_AI_MINIMAL=1`. Adds `disableWal` option to `LockedBlackboardOptions`; also activated by `NETWORK_AI_MINIMAL=1`. Source: llm_adapter@2026-05-23 Confidence: high |
— |
Full changelog
What's changed
Added
network-ai doctor— Self-diagnostic command: validates data directory, env routing, audit log JSONL integrity, stale WAL entries, kill-switch state, MCP secret presence, and blackboard schema. Exits 0 all-pass / 1 any-fail. Supports--json.network-ai inspect <key>— Inspect any blackboard key: value, metadata (source agent, timestamp, TTL, version), pending WAL history (--history), audit trail (--audit).network-ai pause/network-ai resume— Kill switch: writes/removes adata/SYSTEM_PAUSEDsentinel.doctorreports pause state.--whyflag onauth token— Prints full permission scoring breakdown (justification 40%, trust 30%, risk 30%, weighted total, verdict) before issuing a token.--minimalglobal flag — Disables WAL replay and TTL sweep for fast CI/test startup. Also set viaNETWORK_AI_MINIMAL=1.AuthGuardian.scoreRequest()— New public read-only method returning the full scoring breakdown without issuing a token or writing to the audit log.LockedBlackboarddisableWaloption — NewdisableWal?: booleaninLockedBlackboardOptions; also activated byNETWORK_AI_MINIMAL=1.
Documentation
THREAT_MODEL.md— Adversary profiles, trust boundaries, explicit non-goals, security controls summary.DATA_LOCATIONS.md— Every file Network-AI creates at runtime: path, purpose, data classification, operator responsibilities.SUPPLY_CHAIN.md— One runtime dependency, no install-time scripts, network surface, SLSA Build Level 2 / npm provenance verification.SECURITY.md— Added Disclosure SLA table (acknowledgment 48h, Critical/High patch 14 days, public disclosure 7 days post-patch).
Full changelog: https://github.com/Jovancoding/Network-AI/blob/main/CHANGELOG.md
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About Jovancoding/Network-AI
Multi-agent orchestration MCP server with race-condition-safe shared blackboard. 20+ MCP tools: blackboard read/write, agent spawn/stop, FSM transitions, budget tracking, token management, and audit log query. `npx network-ai-server --port 3001`.
Related context
Beta — feedback welcome: [email protected]