michal/mcpctl

Fork 0

Files

Michal 2da627e77f

CI/CD / lint (pull_request) Successful in 1m19s

Details

CI/CD / typecheck (pull_request) Successful in 2m21s

Details

CI/CD / test (pull_request) Successful in 1m19s

Details

CI/CD / build (pull_request) Successful in 2m17s

Details

CI/CD / smoke (pull_request) Failing after 2m47s

Details

CI/CD / publish (pull_request) Has been skipped

Details

feat(llm): resolve the gate's selection Llm by tier, not by name

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

2026-08-05 01:00:47 +01:00

2.5 KiB

Raw Blame History

Claude Code Instructions

Task Master AI Instructions

Import Task Master's development workflow commands and guidelines, treat as if import is in the main CLAUDE.md file. @./.taskmaster/CLAUDE.md

Skill routing

When the user's request matches an available skill, ALWAYS invoke it using the Skill tool as your FIRST action. Do NOT answer directly, do NOT use other tools first. The skill has specialized workflows that produce better results than ad-hoc answers.

Key routing rules:

Product ideas, "is this worth building", brainstorming → invoke office-hours
Bugs, errors, "why is this broken", 500 errors → invoke investigate
Ship, deploy, push, create PR → invoke ship
QA, test the site, find bugs → invoke qa
Code review, check my diff → invoke review
Update docs after shipping → invoke document-release
Weekly retro → invoke retro
Design system, brand → invoke design-consultation
Visual audit, design polish → invoke design-review
Architecture review → invoke plan-eng-review
Save progress, checkpoint, resume → invoke checkpoint
Code quality, health check → invoke health

Resource types

mcpctl resource cheatsheet:

server — MCP server definition
instance — running container (immutable, replicas-managed)
secret / secretbackend — credentials
template — reusable server blueprint
project — workspace grouping servers, prompts, agents
llm — server-managed LLM provider (api key + endpoint). Never hardcode a served-model id: rows are named for the role they fill (vllm-current/fast, vllm-think/heavy), Pulumi repoints their model on a swap, and consumers resolve by tier. See docs/llm-tiers.md.
agent — LLM persona pinned to one Llm; project attach surfaces project Prompts as system context, project MCP servers as tools, and exposes the agent itself as an MCP virtual server (agent-<name>/chat). See docs/agents.md, docs/chat.md.
prompt / promptrequest — curated content / legacy pending proposal (use proposal for new work).
skill — Claude Code skill bundle (SKILL.md + files + typed metadata). Materialised onto disk by mcpctl skills sync. See docs/skills.md.
proposal — generic pending proposal queue, replaces promptrequest. Covers both prompts and skills. See docs/proposals.md. Triage via mcpctl review.
revision — append-only audit + diff log shared by prompts and skills. Auto-bumps semver on save. See docs/revisions.md.
rbac — access control bindings
mcptoken — bearer credentials for HTTP-mode mcplocal

2.5 KiB Raw Blame History

Claude Code Instructions

Task Master AI Instructions

Skill routing

Resource types

2.5 KiB

Raw Blame History