A decoder sizes an image from its header, so the row grows as soon as the
first bytes are parsed -- measured here at 421ms against a load event at
2407ms. Marking the row only once load fired left that first and largest
growth outside the compensation window, and scrolling back through history
still moved the reader by the full image height.
Rows are now marked from the moment an image mounts until loading finishes,
counted so a message with several images stays marked until the last one is
done. The listener also moves to the document: rows announce their images
while mounting, before a ref-driven listener on the timeline element would
exist to hear the first one, which is why the mount signal was being lost.
The fixture serves a real PNG and holds the response open, so the row grows
long before load the way a large image does; an SVG served in one shot lays
out and fires load together and cannot reproduce this. A companion assertion
checks the fixture still has that gap, so it cannot quietly stop testing the
timing it exists to test.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The Electron suites were only reachable one npm script at a time, so a new
one was covered by whoever remembered it existed. test:electron:all builds
once and runs all five, reporting a single summary and a non-zero exit.
The runner lives under tests/ rather than app/scripts/, which .gitignore
excludes entirely.
The image row spacing assertion also stops hard-coding the current gap --
it had 0.59px of headroom -- and calibrates against the spacing the rest of
the timeline is using.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
renderMarkdown ran the marked configuration on every call and leaned on a
module-level flag to make that cheap. It belongs next to the custom element
registration, which already runs once, before anything renders.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
A source the Markdown renderer refuses now goes through the same element
with no src rather than a separate light-DOM span, so a blocked source and
a source that fails to load are one piece of UI instead of two. That drops
the span's stylesheet rule and the only reason the renderer built elements
just to serialise them.
Decoding what marked escaped no longer runs untrusted markup through a
detached element's innerHTML; the entities marked actually emits are
decoded in one pass, and attributes are escaped on the way out. With the
DOM dependency gone the renderer is directly unit-testable, so the escaping
and the protocol allowlist now have coverage that does not need Electron.
The element's shadow styles also stop hard-coding values that already exist
as tokens -- custom properties cross the shadow boundary, so --muted and
--hairline-strong are now the single source of truth -- and the height cap
becomes --session-image-max-block, which compact Markdown surfaces (subagent
panes, memory rows, tool results) lower from a viewport fraction to 240px.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The wide-image probe resolved only from a load handler that a regression
could keep from ever firing, and it was awaited bare, so a broken build
hung the run instead of reporting a failure. Every renderer probe now runs
against a deadline, the probe rejects on image error, and the suite as a
whole is bounded.
Adds a held image endpoint so an above-viewport image can be made to finish
at a moment the test controls, and asserts the reader does not move -- both
at rest and mid-gesture, which is where it regressed.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
virtual-core skips scroll compensation when an already-measured row above
the viewport is re-measured during an upward scroll: that is normally an
estimate correction, and compensating it makes rows jump while the reader
scrolls back through history. An image finishing loading is not an estimate
correction -- the row really did get taller -- so skipping compensation
pushed everything on screen down by the full image height. Scrolling back
through a session with screenshots moved the reader by ~490px per image.
The element now announces load and error through a composed event, and the
timeline compensates size changes for rows that just settled media while
leaving virtual-core's guard in place for every other re-measurement.
loading="lazy" comes off the image at the same time. Rows are only mounted
within a few viewports, so the attribute bought almost nothing while making
load timing depend on Chromium's connection heuristics.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
marked <= 14 calls renderer.image(href, title, text); marked >= 15 passes
the token instead. With only the positional form handled, an upgrade of the
pinned CDN build would turn every session image into fallback text without
any error, so normalise both shapes and cover them with a unit test.
The tag name moves into session-image-contract.js so the Markdown renderer
no longer reaches it through the module that imports the .vue component,
which is what kept it out of Node's test runner.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Mark absolute Markdown links and inline-code relative paths as file
references, resolve them against the originating message cwd, and open
them in the configured editor. Local links no longer navigate the SPA
away from the running renderer.
The canonical transcript assembly projected messages down to seven
fields, so cwd and session_id never reached the renderer. Both are added
to SessionDetailMessage: cwd because the working directory can change
mid-session, session_id because it scopes which roots a reference may
resolve inside. The main process derives those roots from the database
rather than trusting anything the renderer sends.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Electron 33 bundles Node 20.18, which has no type stripping. Every
tests/electron-*.mjs harness imports session-detail-assembly.mjs, which
in turn imports packages/core/src/session-detail.ts, so all three failed
at load with ERR_UNKNOWN_FILE_EXTENSION. Electron 43 bundles Node 24.18
and runs them.
better-sqlite3 11 does not compile against the newer V8 (removed
Context::GetIsolate, PropertyCallbackInfo::This, changed
SetNativeDataProperty signature), so the native dependency moves to 13
to match the ABI. electron-builder moves to 26 for Electron 43 support.
Verified: npm test 275/275, typecheck, electron-vite build, electron-builder
pack, and all three harnesses (15 + 55 + 11 assertions).
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Treat token_count events without usage as null canonical token values so node:sqlite never receives undefined. Covers issue #1 with a parse-to-persist regression test.
- normalize Kimi thinking parts and omit empty placeholders
- add standalone session-sharing and UI demo artifacts
- add regression coverage and refresh the Kimi index marker
- bump the Electron app and CLI packages to v0.2.1
- ignore generated app build assets
Publish real virtual-row measurements while suppressing momentum-breaking scroll writes, then reconcile the reader anchor once scrolling settles. Keep live patches out of the timeline during active gestures and add Electron coverage for tall-row overlap, residual motion, and existing-message updates.
Cache semantic timeline anchors and disclosures per session instead of relying on KeepAlive. Restore state after virtualized layout stabilization while preserving explicit focus and tail-follow behavior.
Require the bootstrap agent to ask whether the skill should be installed locally or globally, and suppress only SQLite’s ExperimentalWarning in CLI test processes.
Present the bootstrap SKILL.md as the recommended setup path, keep manual installation secondary, and add regression coverage for the documentation order.
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.
- Add "Run locally" section: clone → cd app → npm ci → npm run dev, with a
note on first-run indexing, source directories, and WSL auto-detection.
- Add "Debug the app" section: HMR, DevTools shortcuts, main-process logs,
Node inspector attachment, and isolated HOME for testing.
- Note that better-sqlite3 may need platform build tools if no prebuilt binary
is available.
- Fix "macOS only" → mention prebuilt for macOS, runnable from source on all
platforms.
- Fix typo: "A surface for human" → "for humans".
- Fix manual install path wording.
Co-Authored-By: Codex (GPT-5) <noreply@openai.com>
Eliminate full-table scans from subagent tool queries and guardian retractions by indexing message_uuid on tool_calls and tool_results. Add query-plan regressions for both access paths.
Defer and coalesce global catalogue refreshes while SessionDetail is active, carry session metadata through incremental patches, and gate in-flight catalogue commits by route. Harden the virtual timeline cold-open and user-scroll lifecycle, and add Electron frame, continuity, metadata, and overlap regressions.
Discard virtualizer measurement corrections suppressed during an active user gesture instead of replaying stale offsets at scrollend. Preserve post-scroll live anchoring and add unit plus Electron coverage for ordinary scrolling without updates.
Track real user scrolling through scrollend with a quiet watchdog, defer timeline commits and virtualizer corrections until settlement, and make SessionDetail the sole tail-follow owner. Add unit and Electron regressions for scroll writes, reader anchoring, near-tail escape, explicit navigation, and flap timing.
Virtualize SessionDetail rows behind stable presentation boundaries and apply typed incremental patches only after visible commits. Preserve reader state across live updates, handle coalesced and reordered patches, and verify the 120Hz append path with Electron tracing.
Render SessionDetail through measured dynamic-height virtual rows while preserving disclosure state, UUID navigation, reader anchoring, and tail-follow across live updates.
Add focused state/reconciliation tests plus a production Electron harness covering long-session DOM bounds, scrolling performance, offscreen navigation, and live viewport stability.
Cache timeline DOM indexes and memoize the timeline so progress and flap updates avoid rescanning or rerendering old messages. Preserve scroll anchors and disclosure state across targeted live message replacements.
Preserve unchanged message identities and isolate Vue row rendering during live refreshes.
Use a tail-only scroll path so updates do not interrupt active readers or expanded tools. Add regression coverage for 908-message appends, changed snapshots, and scroll policy.
Keep message navigation and progress state synchronized, and preserve
sequential split-flap count updates with a bounded queue.
Publish the Obelisk skill under skills/obelisk for npx skills, sharing
the same staging layout between CI and local releases with regression coverage.
SessionDetail live update:
- Extract session-view-state.mjs: capture scroll position, disclosure
(open/skill-md-open) state, and visible-UUID anchor before refresh;
reconcile messages by UUID (in-place update, append tail only); restore
scroll and disclosure state after DOM patch. findLastMessageAtOrAbove uses
binary search (O(log n)) instead of linear scan.
- scrollRevision tracks user scrolls during refresh to avoid stale anchors
overriding manual navigation.
- Throttle onScroll to one rAF per frame.
Tool renderer:
- Extract tool-renderer.js: standalone module for rendering tool call cards
(Read/Write/Edit diffs, Bash terminal output, search results, JS/TS
syntax highlighting). Replaces inline rendering in SessionDetail.
- tests/app-tool-renderer.test.mjs covers escaping, highlighting, and
terminal formatting.
Input tokens semantics migration:
- Claude provider now sums input_tokens + cache_creation_input_tokens +
cache_read_input_tokens into a single input_tokens value (was previously
only the raw field, undercounting when cache tokens are present).
- One-time index-wide re-parse triggered when the marker
__claude_input_tokens_include_cache_v1__ is absent and the DB already
has token data (self-healing on first build after upgrade).
- App indexer.ts carries the same marker check for the app's build path.
Also:
- PRODUCT.md: product register (users, purpose, brand, design principles,
accessibility targets).
- README.md: minor wording updates.
Co-Authored-By: Codex (GPT-5) <noreply@openai.com>
Rewrite README to reflect the current state of the project:
- Describe both surfaces: skill (agent-first retrieval) and app (human browser).
- Add Codex support section (unified schema, source tagging, child-thread mapping).
- Update Structure tree to match the packages/core workspace layout with all
TypeScript modules (providers, persist, tx, write-coordinator, writer-lease).
- Document generated build outputs (packages/core/dist, dist/obelisk-skill).
- License badge corrected to AGPL-3.0 (skill artifact is MIT; source is AGPL).
- Skill invocation examples updated to /obelisk-skill.
- Add recap flow documentation.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
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
Index the is_error boolean from JSONL tool_result blocks into a new
column, replacing the old ERROR_PATS text-matching approach that
produced ~90% false positives. Bash exit code pattern kept as fallback.
Add sessions() as first-class entry point for session discovery with
project/time/branch filters. Extend summaries, workflows, failures,
subagents, fileHistory with the same opts vocabulary that search()
already had — no more pulling full datasets to filter client-side.
Prepares for adding Codex JSONL support — new indexers can be added
without touching the query layer.
- db.mjs: schema, openDb, truncation helpers, shared utilities
- indexer.mjs: file discovery, JSONL parsing, SQLite writes
- query.mjs: all query API functions (search, context, raw, etc.)
- runtime.mjs: thin CLI entry point + VM script executor
tommy0103andClaude Opus 5
