Files
obelisk/CONTEXT.md
T
tommy0103 90191e4604 feat(cli): extract Obelisk runtime into npm package
Add @obelisk-apps/cli with the existing build, search, query, and attune contract plus official skill installation.

Separate the docs-only skill artifact, bootstrap installer, release layout, cross-platform CI, and package-level regression coverage.
2026-07-16 17:26:23 +08:00

4.2 KiB

Obelisk

Obelisk is explicit memory infrastructure for coding agents: it indexes local Claude Code and Codex transcripts into a queryable SQLite evidence layer, and a CodeAct runtime lets an agent write a small query, run it, and answer from real session history. This glossary pins the terms that are specific to Obelisk; it is not a spec.

Runtime interface

Runtime interface: The public contract, expressed as four verbs — build, search(text), query(code), attune(code). CLI and a future MCP server are transports over this same shape; neither adds its own retrieval surface. The agent skill is docs-only guidance that invokes the CLI rather than a transport of its own. Avoid: API, tool surface

CodeAct: The interaction style where an agent writes JavaScript that runs inside the query(code) sandbox and returns JSON, rather than calling many fine-grained tools. This is Obelisk's core design choice. Avoid: tool-calling, function-calling

Helper: A convenience accessor available only inside the query(code) sandbox (overview, search, context, sql, memories, …). Helpers are never promoted to an external tool surface.

Indexing

Provider adapter: A pure per-source module (claude, codex, later opencode, pi, …) that discovers a source's transcript files and parses one into a stream of records. It never opens or writes a database; adding a source means adding one adapter. The shared pure parse/discover helpers live in packages/core/src/parsing.ts, which imports only node:fs/path/os — deliberately node:sqlite-free so the compiled providers can be consumed by the app (whose Electron runtime has no node:sqlite). Avoid: parse core, parser, ingest

Record: One normalized row destined for the index (session, message, tool call, tool result, summary, subagent, workflow, …), emitted by a provider adapter before any persistence happens.

Persist layer: The single shared, provider- and binding-agnostic writer that consumes records from any adapter and writes them into an injected SQLite handle inside a transaction. The binding is injected — node:sqlite (CLI) or better-sqlite3 (app) — so there is one persist implementation, not one per binding. Avoid: writer, sink, DAO

Daemon indexing mode: Continuous incremental indexing driven by a long-lived process (the desktop app, later a CLI daemon) that watches transcript directories and keeps the index fresh as files change. Avoid: watcher mode, live indexing

Passive pull mode: On-demand incremental indexing performed by a CLI invocation when there is no active daemon: the command brings the index up to date, then answers. Avoid: lazy indexing, on-read indexing

index_state: The bookkeeping table shared by both indexing modes. It records, per transcript path, the last-seen mtime and lines_processed (enabling resume-from-line incremental indexing), plus heartbeat/last-build markers used for daemon arbitration.

Daemon arbitration: The policy by which the passive pull mode detects a fresh daemon from the __app_heartbeat__ marker and skips every CLI-side mutation, including schema setup, indexing, checkpointing, and attune. The heartbeat alone means “the daemon should write”; __app_last_successful_build__ records coverage/freshness, not ownership. Both indexing modes use the same persist layer.

Writer lease: The hard cross-process safety mutex behind daemon arbitration. A writer holds BEGIN IMMEDIATE on .obelisk/writer.lock.sqlite for the complete mutation; manual rebuild holds it through build, target-database replacement, and reopen. The heartbeat expresses policy, while the writer lease prevents overlapping writes during races, stale heartbeats, or processes from different versions.

Memory

Queryable session memory: The evidence layer — real sessions, messages, tool calls, subagents, workflows — that an agent queries on demand. Obelisk deliberately does this instead of implicit/ambient memory. Avoid: implicit memory, ambient memory, auto-recall

Approved durable memory: Human-approved conclusions persisted as markdown plus a registry record, via attune(code) calling remember()/forget(). Auditable and revocable. Avoid: long-term memory, vector memory