The served model changes (glm-4.6-reap -> deepseek-v4-flash, and again after
that). Pulumi already repoints mcpd's long-lived rows -- vllm-current/fast and
vllm-think/heavy -- at whatever LiteLLM serves, so no model id is written down
in mcpctl. But nothing resolved those rows: gate prompt-selection took
MCPCTL_GATE_SELECTION_LLM or the project's llmProvider, and neither is set on
any project or either deployment. Unpinned projects fell through to the local
personal-token provider, whose heavy entry names a retired claude-opus-4 -- so
every gated session has been running on priority-ordered prompts, not LLM
ranking, announcing it only in a mcplocal log line nobody reads.
Consumers now ask for a role. tier is already a field on the Llm resource and
is set by the same Pulumi resource that sets model, so the two cannot drift.
Explicit pins still win; this only changes what happens when nothing is pinned.
Eligibility excludes inactive rows (selecting one defers the failure to the
first inference call) and virtual rows -- those are backed by some user's
mcplocal over SSE, and automatic resolution must not route a project's traffic
through a laptop nobody chose. The heavy tier already holds two rows, so the
tiebreak is load-bearing now rather than future-proofing: an ordered list of
well-known names, carrying both the current names and the symmetric ones the
rows might be renamed to, so a rename stays a Pulumi-only change and neither
deploy order breaks the other. Names matching nothing are inert by design.
The rows keep the names they have. name is immutable in mcpd (agents and
projects reference it), so a rename costs a data migration plus a resource
replace, and buys nothing once nothing reads the names. vllm-fast would also
collide in meaning with LiteLLM's deepseek-v4-fast route, which is a different
thing one word apart.
Smoke covers the drift case the unit tests cannot: the resolved fast row has to
answer real inference, which is exactly what fails when a row is left pointing
at a suspended model.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01B5NAoE7VJA5TWvHsVfEmUr
Final stage of v1.
Smoke (mcplocal/tests/smoke/virtual-llm.smoke.test.ts):
- Spins an in-process LlmProvider that returns canned content.
- Runs the registrar against the live mcpd in fulldeploy.
- Asserts: row appears with kind=virtual / status=active, infer
through /api/v1/llms/<name>/infer comes back through the SSE
relay with the provider's content + finish_reason, and a 503
appears immediately after registrar.stop() (publisher offline).
- Times out / cleanup paths idempotent so re-runs against the same
cluster don't litter rows. The 90-s heartbeat-stale flip and 4-h
GC are unit-tested — too slow for smoke.
Docs:
- New docs/virtual-llms.md: when to use this vs creating a regular
Llm row, how to opt-in via publish: true, the lifecycle table,
the inference-relay sequence, the v1 streaming caveat, the v2-v5
roadmap, and the full /api/v1/llms/_provider-* surface.
- agents.md cross-links virtual-llms.md alongside personalities/chat.
- README's Agents section gains a "Virtual LLMs" subsection.
Workspace suite: 2043/2043 (smoke files run separately). v1 closes.
Stage roadmap (each its own future PR):
v2 wake-on-demand · v3 virtual agents · v4 LB pool · v5 task queue
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The closing stage. mcpd now hosts the Stage 5 SPA, the Docker image
bundles the build artifact, a smoke test exercises the personality
HTTP surface end-to-end, and the user-facing docs spell out the
mental model.
mcpd:
- Add @fastify/static dep.
- New routes/web-ui.ts: registers /ui/* against a static bundle. Looks
for the bundle at $MCPD_WEB_ROOT, then /usr/share/mcpd/web (the
Docker image path), then a dev-tree fallback. Logs and skips
cleanly if missing — API-only deploys keep working.
- SPA fallback: any /ui/<path> that doesn't match a file falls through
to index.html so direct hits to react-router URLs work.
- /ui/* falls through to `kind: skip` in mapUrlToPermission, so the
static assets are served unauthenticated. Each API call from the
SPA still carries the bearer token.
Deploy:
- Dockerfile.mcpd builds the @mcpctl/web bundle in the same builder
stage and copies dist/ to /usr/share/mcpd/web in the runtime image.
Smoke (personality.smoke.test.ts):
- Live mcpd flow: create secret/llm/agent/personality, attach an
agent-direct prompt, verify the binding listing, reject double-
attach (409) + foreign-agent prompt (400), set defaultPersonality
by name, detach + delete cleanup.
Docs:
- New docs/personalities.md: VLAN-on-ethernet model, system-block
ordering table, three prompt scopes, CLI walkthrough, web UI
walkthrough, full API surface, RBAC notes.
- agents.md and chat.md cross-link.
- README's Agents section gains a Personalities subsection.
Test count after Stage 6:
mcpd: 801/801 cli: 430/430
web: 7/7 db: 58/62 (4 pre-existing)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Closes the agents feature.
Smoke tests (run via `pnpm test:smoke` against a live mcpd at
$MCPD_URL, default https://mcpctl.ad.itaz.eu):
* tests/smoke/agent.smoke.test.ts — full CRUD round-trip:
create secret + Llm + agent with sampling defaults; `get agents`
surfaces it; `get agent foo -o yaml | apply -f` round-trips
identically; create + list a thread via the HTTP API; agent delete
leaves Llm + secret intact (Restrict + SetNull as designed). Self-
skips with a warning when /healthz is unreachable.
* tests/smoke/agent-chat.smoke.test.ts — gated on
MCPCTL_SMOKE_LLM_URL + MCPCTL_SMOKE_LLM_KEY. Provisions secret +
Llm + agent against a real upstream, runs `mcpctl chat -m … --no-
stream` (asserts a reply lands), then runs the streaming default
(asserts text on stdout + `(thread: …)` on stderr). The fast path
for verifying the in-cluster qwen3-thinking deployment:
MCPCTL_SMOKE_LLM_URL=http://litellm.nvidia-nim.svc.cluster.local:4000/v1 \
MCPCTL_SMOKE_LLM_MODEL=qwen3-thinking \
MCPCTL_SMOKE_LLM_KEY=$(pulumi config get --stack homelab \
secrets:litellmMcpctlGatewayToken) \
pnpm test:smoke
Docs:
* README.md — new "Agents" section under Resources with the
qwen3-thinking quickstart and links to docs/agents.md and
docs/chat.md. Adds llm + agent rows to the resources table.
* docs/agents.md (new) — full reference: data model, chat-parameter
table, HTTP API, RBAC mapping, tool-use loop semantics, yaml
round-trip shorthand, the kubernetes-deployment wiring recipe,
and a troubleshooting section (namespace collision, llm-in-use,
pending-row recovery, Anthropic-tool limitation).
* docs/chat.md (new) — user-facing `mcpctl chat` walkthrough:
modes, per-call flags, slash-commands, threads, and a
troubleshooting section.
* CLAUDE.md — adds a "Resource types" cheatsheet with one-line
pointers to each, including the new `agent` row that links to
the docs.
All suites still green: mcpd 759/759, mcplocal 715/715, cli 430/430.
Smoke tests typecheck and self-skip when no live mcpd is reachable.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Gitea's auto-generated .repo file contains internal IPs. Use a manual
repo file with the public mysources.co.uk baseurl instead.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Rewrite the Plugin System section to make the extends/inheritance
mechanism clear — show that default extends gate + content-pipeline,
explain hook inheritance and conflict resolution rules.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Section 4 now uses --from-template instead of manual --docker-image
- Declarative YAML example uses fromTemplate + envFrom secretRef
- Backup section updated to git-based commands (was old JSON bundle)
- Consistent server naming (my-grafana from template, not bare grafana)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Rewrite README Content Pipeline section as Plugin System section
documenting built-in plugins (default, gate, content-pipeline),
plugin hooks, and the relationship between gating and proxyModel
- Update all README examples to use --proxy-model instead of --gated
- Add unit tests: proxyModel normalization in JSON/YAML output (4 tests),
Plugin Config section in describe output (2 tests)
- Add smoke tests: yaml/json output shows resolved proxyModel without
gated field, round-trip compatibility (4 tests)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add warmup() to LlmProvider interface for eager subprocess startup
- ManagedVllmProvider.warmup() starts vLLM in background on project load
- ProviderRegistry.warmupAll() triggers all managed providers
- NamedProvider proxies warmup() to inner provider
- paginate stage generates LLM-powered descriptive page titles when
available, cached by content hash, falls back to generic "Page N"
- project-mcp-endpoint calls warmupAll() on router creation so vLLM
is loading while the session initializes
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
MCP server containers are managed by and proxied through mcpd,
not directly accessible. Updated diagram to show containers
nested inside mcpd boundary with explanation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Comprehensive MCP server management with kubectl-style CLI.
Key features in this release:
- Declarative YAML apply/get round-trip with project cloning support
- Gated sessions with prompt intelligence for Claude
- Interactive MCP console with traffic inspector
- Persistent STDIO connections for containerized servers
- RBAC with name-scoped bindings
- Shell completions (fish + bash) auto-generated
- Rate-limit retry with exponential backoff in apply
- Project-scoped prompt management
- Credential scrubbing from git history
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
