v0.5.0

Release notes — network-aiops 0.5.0

Previous release: 0.4.0.

Headline: read-only mode

export NETWORK_READ_ONLY=1

With this set the 4 write tools are never registered — an MCP
client lists 28 tools instead of 32. The writes are not hidden
behind a flag and not merely refused on call: they are absent from the session,
so a model cannot invoke one and cannot be argued into one. For a reviewer this
is checkable rather than promised — connect, list the tools, and the writes are
not there.

Enforcement is two layers deep: the @governed_tool harness refuses every
non-read operation (covering the CLI and in-process callers too), and the MCP
server removes write tools from list_tools(). Changing entry point does not
get around it.

BREAKING — return shapes changed

This release changes payloads that callers may be parsing. Both changes exist
to stop a result from misrepresenting itself:

1. Absent fields are now null, not "". A missing value and an empty value
   were previously indistinguishable, which invited consumers to invent the
   difference. Keys are still always present — only the value may be null.
2. Anything with a limit now returns an envelope —
   {"<items>": [...], "returned": N, "limit": L, "truncated": bool}. Truncation is
   measured (one extra row is fetched), never inferred from the page happening to
   be full. Where a genuine pre-cap total is knowable it is reported as total;
   where it isn't, total is deliberately omitted rather than echoing returned.

New: read-only diagnostics / RCA

Two new read-only analyses — interface_health_rca and bgp_neighbor_rca — plus a
diagnose CLI group. Every finding cites the measured number that tripped it
along with a cause and a concrete action, ranked worst-first with an explicit
rank field, so priority is stated in the payload rather than implied by list
order. Transparent heuristics, not a black-box verdict.

Also in this release

• docs/VERIFICATION.md — what the mock suite actually guarantees, a live
  verification checklist, and the criteria for claiming this tool verified.
• skills/network-aiops/references/agent-guardrails.md — for driving this tool with a
  smaller / local model: which guardrails are now enforced for you, and a
  ready-made system prompt for the rest.
• Expanded operator playbooks in the skill documentation.
• The advertised tool count now matches what an MCP client actually lists
  (it includes undo_list / undo_apply), and a release gate keeps it honest.
• The (preview) label has been dropped. It never meant unreleased; verification
  status now lives in docs/VERIFICATION.md where it can be specific.

v0.4.0

Undo executor (undo list / undo apply) line-wide + this tool's platform/framework expansion + coverage. See CHANGELOG.md.

v0.3.1

Fix release: secrets.enc follows _AIOPS_HOME; sanitized failures audit as status=error (no undo recorded for failed calls); doctor/init fully test-covered. Tool-specific fixes in CHANGELOG.md.

v0.3.0

Security-hardening release from a line-wide code review. Highlights: secure-by-default approver gate for high/critical operations (init seeds a starter rules.yaml), percent-encoded URL path segments, single-sourced version, governance persistence + CLI write-path tests. See CHANGELOG.md for the full list. BREAKING: fresh installs with no rules.yaml now deny high/critical writes until an approver is recorded.

Network-AIops v0.2.1

Patch: config.yaml now honors the *_AIOPS_HOME env var; CLI writes are now audited + undo-recorded through the governance path (previously MCP-only). See CHANGELOG.

v0.2.0

v0.2.0

Security

• Encrypted credential store — secrets now stored in ~/.<tool>/secrets.enc (Fernet + scrypt-derived master password), never plaintext on disk (chmod 600). Legacy .env still works as a deprecated fallback; secret migrate imports it.

Onboarding

• Friendly interactive <tool> init wizard + <tool> secret set/list/rm/migrate/rotate-password commands. doctor now reports store health.

Expanded operations

• Many new day-2 MCP tools covering common scenarios (see SKILL.md). Every tool runs through the governance harness (audit / budget / risk-tier / undo).

Note: still validated against mocked APIs; verify against a live system before production use.

v0.1.0 — first release (preview)

Standalone governed multi-vendor network ops via NAPALM (Cisco IOS/NX-OS/IOS-XR, Arista EOS, Juniper Junos) + NetBox — 13 MCP tools with audit/budget/undo/risk-tier harness. config_diff dry-run + config-replace undo. See README.