warpline CLAUDE.md

Filigree Issue Tracker

filigree tracks this project's work. Use it to find, claim, update and close issues: filigree session-context at session start, then filigree start-next-work --assignee <name>.

Full reference: the filigree-workflow skill (patterns, priorities, observations, error codes), filigree --help, and the mcp__filigree__* tool schemas. Prefer the MCP tools when available; fall back to the CLI.

Two rules --help will not tell you:

1. Claim atomically: work_start / work_start_next (MCP) or start-work / start-next-work (CLI). Never chain a claim with a separate status update; that two-step form races other agents.
2. On SCHEMA_MISMATCH the installed filigree is older than the project database. Surface it to the user; do not retry.

Loomweave (code archaeology)

This repo is indexed by Loomweave: it has pre-extracted the tree into a queryable map of entities (functions, classes, modules, files), the call / reference / import edges plus relation edges (inherits_from / decorates / implements / derives), and subsystem clusters. Before grepping the tree to answer "what calls X", "what subclasses X", "where is X defined", "what subsystem owns X", or "find the thing that does Y" — ask Loomweave's MCP tools (mcp__loomweave__*): entity_find, entity_at, entity_callers_list, entity_relation_list, entity_neighborhood_get, project_status_get.

entity_find is the grep replacement for "find the thing that does Y": it matches a concept word by substring over name, summary, and docstring content (e.g. library finds LibraryService), with no embeddings required — reach for it before grepping. Semantic ranking is the separate, opt-in entity_semantic_search_list.

Entity IDs are {plugin}:{kind}:{qualified_name}; subsystems are core:subsystem:{hash}. Never hand-construct one: get it from entity_find / entity_at, or — for a pasted qualname, Rust :: path, or SEI token — from entity_resolve, then copy it verbatim into the next tool.