Add a GitHub Actions workflow that builds the readable, non-bundled skill
artifact (`npm run build:skill`) and force-pushes it to the dedicated
tommy0103/obelisk-skill public repo whenever the main branch is updated.
The skill repo is a pure derivative — no manual commits, no PRs; the source
of truth stays in tommy0103/obelisk.
- .github/workflows/publish-skill.yml: checkout → npm ci → build:skill →
clone skill repo → replace content → commit + force push. Auth via
SKILL_REPO_DEPLOY_KEY (SSH deploy key with write access to obelisk-skill).
- packaging/skill-README.md: the README placed in the skill repo (install
instructions + link back to source + "auto-published, don't PR here").
- packaging/skill-LICENSE: MIT license for the skill artifact (relicensed
from the AGPL-3.0 source by the copyright holder).
- packaging/publish-skill.sh: local convenience script for manual publish.
- packaging/skill-package.json: license field updated to MIT.
- README.md: install command updated to tommy0103/obelisk-skill.
- package.json: add publish:skill script.
The skill repo is MIT-licensed for zero adoption friction (local tool, no
library API, no derivative works expected); the source repo stays AGPL-3.0.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Implement the full ADR-0006 plan: three-layer separation of transaction
correctness, retry policy, and cross-process writer coordination.
Layer 1 — scripts/tx.ts (transaction correctness):
- runWriteTransaction executes work exactly once; no internal retry.
- BEGIN IMMEDIATE takes the write lock up front (avoids SQLITE_BUSY_SNAPSHOT).
- Guarded rollback: checks inTransaction() via adapter before attempting
ROLLBACK; never masks the primary exception.
- WriteTxDiagnostics attached to errors: phase, code, label,
rollbackSucceeded, rollbackError, transactionActive.
- Binding adapters (betterSqliteTransactionAdapter, nodeSqliteTransactionAdapter)
mapping better-sqlite3's `.inTransaction` and node:sqlite's `.isTransaction`.
- configureConnection centralizes WAL + synchronous + busy_timeout.
Layer 2 — scripts/write-coordinator.ts (retry policy):
- runRetryableWriteTransaction: bounded retry with total time budget.
- Only retries when the transaction confirmed ended (transactionActive=false)
and the error is SQLITE_BUSY during work/commit phase.
- BEGIN-phase BUSY = abort entire build (isBeginBusyFailure); the caller
returns `{ deferred: true, reason: 'writer_busy' }` instead of waiting.
- hasUnusableTransaction detects a still-active transaction after failure;
aborts the build immediately, never retries.
Layer 3 — scripts/writer-lease.ts (cross-process coordination):
- acquireWriterLease: dedicated writer.lock.sqlite with busy_timeout=0 +
BEGIN IMMEDIATE. Non-blocking attempt; bounded wait with retryDelayMs.
- writerLockPathFor derives lock path from the target DB path.
- Lease held for the entire build; released on completion or failure.
- Lock DB uses DELETE journal (not WAL); crash/close auto-releases.
- All consumers obey: skill acquires at build start (returns deferred if
unavailable); app daemon (via worker) acquires for its build cycle.
Build semantics changes:
- affectedSessionIds updated only after successful commit.
- BuildIndexResult gains skipped/skippedFiles for observability.
- Skill finalize failure now fails the build (was silently warned).
- Checkpoint changed to PASSIVE (TRUNCATE reserved for maintenance/exit).
- Skill buildIndex returns { deferred, reason } on lease contention;
indexer-service reschedules the build (deferredRetryMs) without publishing
a heartbeat (so the build-deferred state is visible to cross-process
arbitration).
- Service publishes heartbeat immediately on start() for correct arbitration.
Tests:
- tests/write-transaction.test.mjs: single-shot execution, diagnostics
propagation, auto-rolled-back transaction detected, rollback failure
captured as metadata, BEGIN IMMEDIATE semantics.
- tests/writer-lease.test.mjs: acquire/release, contention returns null,
bounded wait with release during budget.
- tests/app-writer-lease.test.mjs: better-sqlite3 adapter integration.
- tests/app-rollback-guard.test.mjs: rewritten — transient BUSY recovered
by coordinator, persistent BUSY skips file, begin-busy aborts build,
live-transaction aborts build, phantom affectedSessionIds prevented.
- tests/daemon-arbitration.test.mjs: skill defers to fresh app heartbeat,
builds when heartbeat is stale.
- tests/app-indexer-service.test.mjs: new cases for deferred-retry
scheduling and immediate heartbeat on start.
- app/tests/electron-concurrency.mjs + child: dual-child IPC structure for
real better-sqlite3 contention (holder acquires lock → build child starts
→ delayed release → result collected; persistent contention bounded).
ADR-0006 updated to reflect the implemented design.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Reported as "cannot rollback - no transaction is active" — a secondary error.
SQLite auto-rolls back certain failures (SQLITE_BUSY / SQLITE_BUSY_SNAPSHOT,
disk full), after which the per-file loop's unguarded ROLLBACK in its catch
threw over the real error and aborted the whole build instead of skipping just
the bad file.
Stopgap only (see docs/adr/0006 for the planned full fix):
- Add safeRollback(db) in both indexers: it swallows only the rollback's own
error, so the true cause surfaces. Per-file failures are logged and the build
continues; the finalize failure still propagates.
- Give the skill's node:sqlite connection an explicit PRAGMA busy_timeout=5000
(it has no default). The app adds none: better-sqlite3 already defaults to
5000ms, so busy_timeout is NOT the root-cause fix and is not treated as one.
Add tests/app-rollback-guard.test.mjs: injects a DB that faithfully reproduces
"a write auto-rolls back the txn, then ROLLBACK errors" and asserts the build
survives (bad file skipped, other file indexed). Revert-checked: without the
guard the test fails with the exact "cannot rollback - no transaction is active".
docs/adr/0006 records the real fix (shared runWriteTransaction, single-writer
coordination, BEGIN IMMEDIATE, whole-transaction retry, PASSIVE checkpointing)
as deferred, two-phase work — and why bumping busy_timeout is not it.
Verified: suite 124/124, typecheck clean.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
`npm run build:skill` emits dist/obelisk-skill/: the whole scripts/ Core
compiled to readable JS (module structure + comments preserved, ~1:1 with
source, no bundling/minifying per ADR-0004), plus schema.sql, SKILL.md,
references/, and a package.json. It excludes app/, tests/, and release/, which
is what keeps the artifact small.
- tsconfig.skill.json compiles scripts/**/*.{ts,mjs} (allowJs) with
rewriteRelativeImportExtensions, so the .ts specifiers inside the .mjs shells
(runtime.mjs -> ./core.js, indexer.mjs -> ./providers/*.js, ./persist.js) are
rewritten to .js. declaration:false — the skill needs no .d.ts.
- packaging/skill-package.json provides the artifact's package.json; it sets
"type":"module" because the emitted .ts->.js files are ESM.
- build:skill runs tsc then copies schema.sql/SKILL.md/references/package.json.
Add tests/build-skill.test.mjs: runs the real build:skill, asserts the artifact
structure, that no emitted .js/.mjs still imports a .ts module, and that the
compiled artifact builds an index and answers a search end-to-end under plain
Node (no type-stripping) against a temp HOME.
Verified: suite 123/123, typecheck clean, artifact smoke run green.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The skill's `--build` (always a force build) cleared `index_state` and
re-indexed existing files, but never removed rows for transcripts that no
longer exist on disk, so deleted sessions accumulated forever (the dogfood
showed 328 indexed sessions vs 283 current files). A force build is meant to
be a clean rebuild, matching what the app already does.
Drop every derived table (messages, tool_calls, tool_results, sessions,
summaries, subagents, workflows, workflow_agents) in the force path, then
re-index from the current files. `memories` is the durable, human-approved
layer and is never cleared; messages_fts is repopulated by the existing
'rebuild' command in finalize.
Add a test that builds two sessions, deletes one transcript, force-rebuilds,
and asserts the stale session is purged while a seeded memory survives.
Verified the test is discriminating: without the fix it reports
['gone','keep'] instead of ['keep'].
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Convert the app's main and preload source from .js to .ts (git mv preserves
history), adding types where they carry value: the core-consumption seam
(BuildIndexOptions/BuildIndexResult, FileInfo), the indexer service/worker
factories, and the preload IPC bridge. Module-to-module specifiers use the
real .ts extension (mirroring scripts/, since Node type-stripping does not
rewrite .js->.ts); the worker's runtime path stays indexer-worker.js because
that is the built output.
Toolchain:
- Add app/tsconfig.json: strict but noImplicitAny:false (the app orchestrates
the already-strict core; annotating every SQLite-handle helper is low-value
churn) + allowImportingTsExtensions (safe under noEmit).
- Add @types/better-sqlite3 for the injected binding.
- electron.vite.config.ts inputs -> .ts; refresh the stale CommonJS comment.
- typecheck script runs root + app projects. Root tsconfig excludes the
app-importing tests (app-*.test.mjs, recap-capture-query.test.mjs) so the
lenient app files are not dragged into the strict root program; the app
source is covered by app/tsconfig.json instead. See docs/adr/0005.
Verified: npm run typecheck (root + app) clean; suite 121/121; electron-vite
build emits all 6 main entries + preload with no .ts/node:sqlite residue in
the bundles.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The desktop app now indexes through the shared provider adapters + persist
layer (scripts/providers/{claude,codex}, scripts/persist, scripts/parsing)
instead of maintaining its own parallel indexer. buildIndex shrinks from
~1173 to ~592 lines, eliminating the skill<->app parse duplication that
Phase 5 set out to remove. electron-vite bundles the .ts core from source
with better-sqlite3 injected; the provider->parsing graph stays
node:sqlite-free so nothing drags node:sqlite into the app.
Also fix a misleading log: when a manual rebuild tears down the worker
mid-build, the cancelled background build is a deliberate stop, not a
failure. Guard the service's failure log with the stopped flag so it no
longer prints "Obelisk index build failed: Indexer worker stopped" on
every rebuild.
- CONTEXT.md: provider-adapter + single-persist + node:sqlite-free parsing.
- docs/adr/0005: app builds with electron-vite (TS+ESM), packages with
electron-builder; preload CJS for sandbox; app consumes core from source.
Verified: full suite 121/121; a node:sqlite-adapter dogfood of the rebuild
path over real data (969 files, 285 sessions, FTS rebuilt) runs clean; app
Rebuild confirmed in real Electron/better-sqlite3.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
App source (main/preload/worker/renderer) -> ESM; app is now type: module;
__dirname via import.meta.url; worker spawned with type module. Preload is built
as CJS (electron-vite output format) because the sandboxed renderer does not
support ESM preload; main loads ../preload/index.js. Removed dead imports
(nativeImage, readline) and the obsolete scripts/dev.js.
Tests: 4 app tests require->import; app-main-settings rewritten with node:test
mock.module + dynamic import (replacing CJS Module._load mocking); test script
adds --experimental-test-module-mocks. electron-vite build clean, 119/119, and
npm run dev verified: app launches, preload bridges IPC, data loads.
Restructure app into src/{main,preload,renderer}; electron.vite.config.ts builds
all three (each main module its own input so CJS requires + the indexer worker
resolve; better-sqlite3 externalized; Vue plugin for renderer). main/index.js
paths updated for the out/ layout + ELECTRON_RENDERER_URL. Still JS/CJS — TS+ESM
and core consumption are the next stages. Verified: npm run dev launches clean;
electron-vite build succeeds; root suite 119/119.
tsconfig.build.json emits providers/* + persist (+ their parsing.mjs/types deps)
to dist/ as ESM JS + .d.ts. Output is verified node:sqlite-free and functionally
runnable (parse+persist against an injected db). Foundation for the app importing
the shared core.
> obelisk@0.1.0 build:core
> rm -rf dist && tsc -p tsconfig.build.json; dist/ is gitignored.
Move all pure parse/discover helpers (message extraction, project-path, codex
helpers, discovery) out of db.mjs/indexer.mjs into scripts/parsing.mjs, which
imports only node:fs/path/os. Providers now import from parsing.mjs, so the
provider import graph no longer transitively loads node:sqlite — a prerequisite
for the app (Electron/Node without node:sqlite) to consume the compiled core.
Verbatim move, no behavior change; indexer.mjs 840→209 lines. 119/119.
Complete the skill-side provider migration: codex now goes through a pure adapter
and the shared persist layer, and the two original monolithic indexers are gone.
New:
- scripts/providers/codex.ts — pure codex adapter. Full-reparse (buffers the whole
file) because the event_msg↔response_item dedup needs whole-file, bidirectional
knowledge; emits SessionRecord with countMode 'total'. Handles guardian threads
(→ delete-session), agent spawns/tool calls (→ tool_call/subagent), token_count
(patched onto the message record) and task_complete (→ message-turn-duration).
Contract:
- SessionRecord.countMode ('total' | 'delta') tells persist whether to replace or
accumulate message_count — claude is line-incremental (delta), codex full-reparse
(total). SubagentRecord non-key fields are optional; persist merges them
column-wise with COALESCE. MessageTurnDurationRecord.turn_duration_ms is nullable.
Orchestration:
- buildIndex's codex branch parses via the adapter and writes via persist. An
unchanged file is skipped but still swept for stale guardian rows (routed through
persist as a delete-session), preserving prior behavior.
Cleanup:
- Remove the now-unused indexJsonl, indexCodexJsonl, deleteCodexThreadRows and
upsertCodexSubagent — their semantics now live in the adapters + persist.
indexer.mjs drops from ~840 to 428 lines. Codex pure helpers stay exported for
codex.ts and the guardian sweep (physical move deferred to the app-side reorg).
- Migrate the upsert drift test off indexJsonl to the claude.parse + persist path,
keeping the rowid-stability and count-replace regression guards.
Tests: tests/codex-parse.test.mjs (record-stream golden: dedup, tools, token patch,
turn-duration, guardian→delete) and tests/codex-index.test.mjs (full buildIndex
path: fresh build + incremental full-reparse, total-count replace, no duplicates).
Verified equivalent on the real ~/.obelisk index: codex messages 82476 and
subagents 522 identical before/after, zero guardian leakage; real incremental
confirmed (touch a codex file → reparsed idempotently, unchanged files skipped).
lint + typecheck clean, 119/119.
buildIndex's claude branch now parses via providers/claude.ts and writes via
persist.ts instead of the inlined indexJsonl. Behavior is equivalent — the full
buildIndex integration suite (runtime.test.mjs) stays green, 116/116 — and a
force rebuild of the real ~/.obelisk index (327 sessions, 119k messages)
reproduced identical session counts with project_path fully populated.
codex, indexSubagentMeta, workflows, history and the project_path pass are
untouched. indexJsonl is now unused by buildIndex (kept for its drift test;
removed once codex is migrated).
Adds tests/incremental-index.test.mjs: verifies resume/accumulate through the
full buildIndex path (append new lines to an indexed session → incremental
build resumes from the cursor, message_count accumulates, no duplicates). The
30s shouldSkipBuild debounce is cleared in-test so the incremental run fires.
Introduce scripts/persist.ts — the single, provider- and binding-agnostic
layer that consumes an adapter's IndexRecord stream and writes rows into an
injected SQLite handle (node:sqlite for skill/CLI, better-sqlite3 for the app).
It is the only layer that touches the database.
Write semantics are the canonical ones reconciled from the earlier drift:
- messages upsert via ON CONFLICT (turn_duration_ms not in the column list, so
it is never clobbered)
- sessions merge with the existing row: started_at MIN, ended_at MAX,
message_count reset-or-accumulate by resume state, fill-if-null for the rest;
project_path is preserved and left to refreshSessionProjectPaths
- message-turn-duration applies as a targeted UPDATE
- delete-session cascades across all tables
- the generator's return cursor is written back to index_state (mtime:lines →
the two existing columns; no schema migration yet)
Purely additive — buildIndex still uses the old indexJsonl path, so existing
behavior is unchanged. Rewiring happens in 5b-2b.
Adds tests/persist.test.mjs: all record kinds written, resume does not
double-count message_count, fresh re-scan resets it, delete-session cascades.
Full suite 115/115, lint + typecheck green.
claude.parse mirrors indexJsonl line-for-line but yields IndexRecords (no db).
Adds MessageTurnDurationRecord op. Purely additive — buildIndex still uses the
old path. 111/111 green.
Provider adapters own discovery/change-detection/cursoring and emit records;
one shared binding-agnostic persist consumes them. Records map 1:1 to schema
tables. Revises ADR-0001 to the provider-registry model.
scripts/indexer.mjs indexJsonl used INSERT OR REPLACE (rowid/FTS churn) and
carried message_count forward on full re-scan; align to app's ON CONFLICT upsert
+ count reset so the two indexers no longer silently diverge. Regression test added.
Core exposes buildIndex/searchText/executeQuery/executeAttune as the single shared
implementation for all transports. First TypeScript module, run via Node type
stripping in dev. Adds typescript-eslint. lint/typecheck green, test 107/107.
Root package.json (type: module), strict tsconfig with allowJs/checkJs:false for
gradual migration, flat ESLint config scoped to scripts/ + tests/. App untouched.
All three green: lint, typecheck, test 107/107.
search() falls back to safe per-token quoting on malformed FTS input instead of
crashing (documented in api-reference.md). Adds raw() to the doc-synced shape
contract. Full suite 107/107.
Extract helper API documentation into a standalone api-reference.md and
reduce schema.md to a compact field/join/table map for raw SQL work.
Add a Reference Map table to SKILL.md for quick routing by task type.
Extract helper API documentation into a standalone api-reference.md and
reduce schema.md to a compact field/join/table map for raw SQL work.
Add a Reference Map table to SKILL.md for quick routing by task type.
Obelisk now indexes ~/.codex/ sessions alongside Claude Code, storing
both under a unified schema with a column for provenance.
Includes DB migration to ~/.obelisk/, guardian thread filtering, and
source-aware query helpers.
Add `source` column to sessions and messages ('claude' | 'codex').
Discover and parse Codex JSONL files from ~/.codex/sessions/, mapping
Codex thread/item structures to the same schema (messages, tool_calls,
tool_results, subagents). Move DB to ~/.obelisk/ with legacy migration.
Add rebuild-to-temp-then-swap for safe full rebuilds. On the app side:
source filter toggle, collapsible untitled session fold, configurable
codexDir in Settings, and a dev script. Update SKILL.md and query
helpers to expose source fields and accept source filter opt.
Add a clickable session link in MemoryList detail panel that navigates
to the source session and scrolls to the originating message. Refactor
SessionDetail focus logic into a reusable focusPendingMessage() that
reads ?focus=<uuid> from the route query, scrolls the target into view,
and applies a pulse animation that fades out.
Restructure the README around the dual nature of Obelisk: agent-first
skill for querying session history, plus Electron desktop app for
browsing sessions, memories, activity, and recap cards. Trim verbose
implementation details and add app screenshot.
Extract schema DDL into scripts/schema.sql. Add content_type and is_meta
columns to messages for transcript control-plane filtering. Introduce
FTS5-backed memory recall with safe tokenization, memory soft-delete via
forget() through the renamed --attune runtime, and anchors on memory
records. Expand query helpers (includeMeta, thread opts, overview
project-path awareness). Add per-card recap retrieval and writing
references under references/recap/.
Add a flag set after initial data fetch completes so
SessionList and RecapList don't briefly show their empty/onboarding
states before content arrives.
Introduce a Settings view for configuring the Claude data directory
(with WSL auto-detection on Windows), sidebar project grouping module,
and an empty-state onboarding screen for SessionList. Refactor
recap-patterns.md into per-card reference files under references/recap/
with separate retrieval and writing guides. Remove the legacy panel.html.
On the data layer: incremental indexing via changedPaths, per-session
live-update IPC (obelisk:session-updated), and session dirty-tracking
in the renderer.
Introduce a Spotify-Wrapped-style recap feature: five themed cards
(Cover, Path, Vibe, Workflow, Closing) rendered per archetype palette,
with keyboard/swipe navigation and image export via capture IPC. Add
RecapList, RecapDetail, RecapExport views and recap component library.
Wire recap:list/read/updated IPC channels through preload, document the
retrieval-to-card contract in references/recap-patterns.md, and bundle
dist-renderer for production use.
Extract schema DDL into scripts/schema.sql shared between CLI and app.
Add an in-process chokidar-based indexer-service that watches ~/.claude/projects
for JSONL changes, debounces, and triggers background rebuilds via a worker
thread. Rename Usage view to Activity, flesh out MemoryDetail and SubagentDetail
views, and refine App.vue layout/routing. The main process now starts/stops the
indexer lifecycle and notifies renderer windows on index updates.
Introduce an Electron app with session browser, memory list, and usage
views (vanilla JS + Vue scaffolding). On the data layer: add content_type
and is_meta to messages for transcript control-plane filtering, introduce
FTS5-backed memory recall with safe tokenization, support memory archival
via forget() through the renamed --attune runtime, and expose anchors on
memory records.
Memory layer is now English-indexed: memories() query terms and
remember() summaries must be English. Adds a runtime assertion that
rejects CJK text in both paths, guiding the agent to translate
non-English user requests before querying or writing memories.
Ensures consistent retrieval regardless of conversation language.
Make overview() + memories() + search() the standard first pass for
broad retrieval tasks, with sql() positioned as an escalation path for
exact joins/aggregations. Add a Default First Pass section to SKILL.md,
a copyable first-pass pattern to query-patterns.md, and update
retrieval-semantics.md to reinforce the helper-before-sql principle.
The old slug-to-path conversion (replace hyphens with slashes) was
lossy and wrong for paths containing hyphens. Now infers project_path
from the most-frequent observed cwd across session messages, falling
back to slug decoding only when no cwd data exists. Adds
refreshSessionProjectPaths() to backfill existing sessions on rebuild.
Resolves current project from cwd, lists all known projects with session
and memory counts, and returns the current project's recent sessions and
memories in one call. Enables the agent to orient itself at the start of
a retrieval without multiple exploratory queries.
Add a memories table (survives index rebuilds) for agent-written
conclusions with provenance (session, message range, project). The agent
writes markdown files via Write tool (user-approved), then registers
them via a --remember CodeAct script with remember(). Recall via
memories() in --query scripts, filtered by project/session/time.
Separates query (read-only, assertReadOnlySql) from remember (write)
execution contexts in runtime.mjs.
semantics (context types, ordering, project scopes) out of pitfalls.md
into a new retrieval-semantics.md. Pitfalls.md becomes a compact debug
checklist: missing columns, FTS errors, over-large output, empty results.
SKILL.md query routing updated to point at the three reference tiers.
Teach the agent to derive second-pass filters from first-pass evidence
instead of pulling large message windows. Add the pattern and a pitfall
warning against defaulting to LIMIT 25 transcript browsing.
Teach the agent to keep intermediate retrieval inside the query script
and return compact evidence in a single turn, instead of spending
multiple conversation rounds showing raw results. Add the pattern to
query-patterns.md and the rationale to pitfalls.md.
Split the monolithic skill prompt into three tiers:
- Core API (search/context/sql) stays in the first prompt
- Structured helpers listed as one-liners with filter signatures
- Detailed patterns and pitfalls extracted to references/
Add references/query-patterns.md (copyable CodeAct recipes) and
references/pitfalls.md (scope, FTS, ordering, compactness traps).
Clarify project scope semantics (slug vs path vs cwd) throughout.
Add ORDER BY timestamp DESC to failures() for newest-first default.
lightweight workflowTree, build debounce, minor fixes
- Index phase, label, model, state, duration, tokens per workflow agent
- Index duration, total_tokens, status, name per workflow run
- workflowTree returns parsed result + agent summaries instead of
dumping all messages
- 30s debounce on buildIndex to avoid repeated directory scans
- Fix broken BASH_EXIT_PAT (SQLite LIKE has no character classes)
- Fix SKILL.md step numbering, document FTS5 hyphen limitation
tommy0103
