Changelog¶
Detailed notes for every release from
v0.1.0-alpha.2on are indocs/release_notes/and on the documentation site; the entries below summarise them.
v0.3.4¶
Fixes from the v0.3.3 retest. Full notes:
docs/release_notes/v0.3.4.md.
- Local API:
path-existsanswers only inside your configured folders; the editor and zsum command settings accept only known programs when set from the app; saved API keys are never echoed back; prompt variant filenames are checked; hidden vault files return 404. - Fixed: Ctrl-K on Home, a card for every mode on Home, a small corner
logo by default, a clearer zsum Collections empty state, real backoff on
provider rate limits,
AKMS_GLOBAL_VAULTin first-run setup. - Releases:
SHA256SUMS.txtno longer lists itself.
v0.3.3¶
The rest of the v0.3.1 QA pass. Full notes:
docs/release_notes/v0.3.3.md.
- No dead ends: mode setup messages keep the mode switcher and side menu, with a Copy snippet action for Failure Memory and Records; related papers, batch run history, View in Graph and zsum Collections lead somewhere.
- The Picker lists every batch (app-created and starter batches were missing) and picks up changes without a restart.
- Fixed: vault preview math and nested frontmatter, prompt Preview (always empty), graph review message, starter zsum config, hidden vault entries.
- Clearer messages: Discover provider failures, provider test advice, Zotero not connected, Open in Editor result, MechDSL status.
- API: Discover input validation and
provider_errors, picker routes in OpenAPI, graph refresh stream is POST, UTC graph status, zsum test errors, learn export stub removed. - Polish: app title and icon, Linux package description, Logo switch for the backdrop logo, dark-mode contrast, Ctrl-K fixes.
v0.3.2¶
Security and reliability fixes from the v0.3.1 QA pass. Full notes:
docs/release_notes/v0.3.2.md.
- Local API requires a per-launch token and a loopback
Host, closing access by other local programs and by web pages through DNS rebinding. - Hardened inputs: prompt and workflow ids can't escape the library, node file read/open is limited to the node and vault folders, saved API keys are masked, command settings must name a real program, and error responses carry no tracebacks.
- No orphaned sidecars: the sidecar exits when the app dies for any reason; Windows kills the whole process tree; a second launch focuses the first window.
- Windows sidecar serves again: in v0.3.1 it crashed right after starting (uvicorn rebuilt the listening socket as a Unix socket).
- Docs: install links point at the installer releases; checksum steps per OS.
v0.3.1¶
Linux packages that run on current distributions. Full notes:
docs/release_notes/v0.3.1.md.
- Linux builds need glibc 2.35, not 2.43. v0.3.0's AppImage and
.debwere built on the newest runner and did not start on Ubuntu 24.04 or Debian 13. They are now built on Ubuntu 22.04, and the release build fails if a shipped binary needs a newer glibc or the AppImage lacks its bundled WebKitGTK. - Docs: Linux requirements, AppImage vs
.deb, and running from source in a browser without WebKitGTK.
v0.3.0¶
The first public-source release. Full notes:
docs/release_notes/v0.3.0.md. It also carries
everything prepared as v0.2.1, which was never tagged.
- Records mode: read-only browse of explicitly configured akms-records stores, their schemas and their record graph.
-
No source checkouts. AKMS, MechDSL and zotero-summarizer are installed from PyPI; the picker, nodes, batches and graph work without an AKMS checkout.
-
The packaged app supports all of AKMS 0.4. The sidecar build installs the dependency set
uv.lockrecords and bundles every optional mode: the AKMS tabs and Learn, the MechDSL emit bridge, Failure Memory and the Records browser. Earlier builds pinned AKMS below 0.4 and left Failure Memory and Records out of the frozen binary. - No vendored source trees. The bundled agent assets and the zsum prompts are
read from the installed
akmsandzotero-summarizerpackages, and the old vendoredthirdparty/snapshots are deleted from the repository.LOGIC_LOOM_SIDECAR_CORE_ONLY=1builds a zsum-only sidecar. - Every version field agrees (
scripts/check_versions.py; the API package andtauri.conf.jsonhad drifted), and the release workflow refuses a tag that does not match them or has no changelog section. - Security upgrades in the lockfile. The new
uv auditgate reported 30 advisories in nine transitive packages; all are cleared by upgrading anyio, cryptography, filelock (with litellm, which capped it), fsspec, multidict, pydantic-settings, pypdf, starlette and urllib3. No AKMS, MechDSL or zotero-summarizer pin moved. - Documentation is a website at https://cemm2.github.io/Logic-Loom/, built
from
docs/and published on each release tag. It replaces the HTML design guides that used to live indocs/and the docs pages in theCEmM2/Logic-Loom-releasesrepository. Release notes live indocs/release_notes/and are part of the site. - Repository hygiene for a public tree:
LICENSE(MIT),SECURITY.md,CONTRIBUTING.md,CODE_OF_CONDUCT.md,SUPPORT.md, a pull-request template, an always-on CI workflow, a security workflow (dependency review, lockfile audits, CodeQL), Dependabot, read-only workflow tokens, andscripts/check_public_tree.py, which fails on private working folders, private repository references, real home-directory paths and secrets. - Third-party notices.
THIRD_PARTY_NOTICES.md, generated byscripts/gen_third_party_notices.py, lists every bundled Python, JavaScript and Rust package with their licenses and license texts, and ships inside the installers withLICENSE. The release refuses a tag while it is out of date with the lockfiles.
v0.2.1¶
Patch release; no Logic-Loom feature changes. Refreshes the vendored AKMS
toolchain (7e07ace → f32d81f) and moves the akms / akms-failure-memory
git pins (72494ac → f32d81f), so the bundled agent assets and the
failure-memory package are current for the first time since v0.1.0-alpha.7.
Newly bundled agent assets, now sourced from AKMS's published root paths rather
than its internal .claude/ tree: skills/akms, skills/deepwiki-nodes,
skills/akms-spec-check, hooks/ (vault read-only + frozen-schema guards), and
docs/akms/spec/invariants.md. Existing assets refreshed — which picks up an
upstream fix to akms-spec-reviewer / akms-spec-check, both of which had been
reading a design_docs path that does not exist.
akms-failure-memory 0.1.0 → 0.3.0: preflight no longer enforces artifact
identity on every operation, and the provider fingerprint no longer tracks AKMS
source bytes.
Known issue unchanged from v0.2.0: Backend E2E (windows-latest) exits 1 after
the suite passes, from non-daemon ThreadPoolExecutor workers at interpreter
shutdown (lesson L001). No test fails; product behaviour unaffected.
Full notes: docs/release_notes/v0.2.1.md
v0.2.0¶
Logic-Loom graduates out of alpha. Adds the Failure Memory workspace — a
read-only surface for inspecting .failure-memory lesson registries, plus an
off-by-default operator mode for recording and compiling them — and fixes
AKMS node-extraction batch runs hanging in the packaged app. Known issue:
backend E2E on windows-latest exits 1 after all tests pass (tracked in this
repo's own failure-memory ledger). Full detail in
docs/release_notes/v0.2.0.md.
v0.1.0-alpha.4 — 2026-07-01¶
Learn — host LLM provider chooser (AKMS ▸ Settings)¶
Unblocks the LLM-gated Learn modes (adaptive_path, llm_expanded) with a
provider chooser in AKMS ▸ Settings, built on akms-learn's public provider
registry (no upstream change):
- Pick the API route (LiteLLM, keyed by
anthropic_api_key/openai_api_key/google_api_key) or an agent-CLI route —claude -p,codex exec, or a user-defined custom command ({prompt}arg-substituted, else piped to stdin).nlmgrounded generation stays;copilot/antigravityship as empty user-fillable command slots. - CLI agents activate only on an explicit choice (never on mere PATH presence), so the no-provider gate is unchanged. Agent stdout is normalized (a single enclosing markdown code-fence is unwrapped) before it becomes the generated section body.
- Saved keys / CLIs go live in-process via a Reload backend action — no app
restart (
POST /api/learn/providers/reload). Choosing a not-yet-ready provider surfaces a warning naming exactly what to fill or install. - New read-only discovery endpoint
GET /api/learn/providers.
MechDSL — in-app Taichi install (verify backend)¶
The MechDSL Overview gains an Install taichi 1.7.4 action: the packaged
sidecar ships the emit bridge Taichi-free, and the pinned wheel is side-installed
at runtime into an ABI-namespaced dir added to the sidecar's sys.path, so
verify is unblocked without re-freezing. emit/transpile keep working with
no Taichi.
v0.1.0-alpha.3 — Research Assistant (Learn), LLM providers, MechDSL bridge¶
Third alpha. Adds the Learn workflow to the Research Assistant, activates
LLM-backed learning modes through a host-provided provider, and ships the
MechDSL executable bridge — LaTeX → FEM-solver-code generation, bundled
Taichi-free. Also pulls a large zotero-summarizer upgrade (see below).
AKMS backend re-vendor (2026-06-17 — alpha.3 re-cut)¶
The vendored AKMS stack was advanced to upstream main (017996ec) and the
alpha.3 binaries rebuilt from it. No UI changes — the AKMS generation backend is
overhauled under the hood:
akms-nodes-gendropped its headless-browser dependency. It no longer hard-depends onnotebooklm-py[browser]/Playwright; node generation is now LLM-provider-pluggable through LiteLLM (an optional[llm]extra) and CLI-grounded (thenlmCLI / an Anthropic MCP-server URL). This removes the heavy browser stack from the sidecar and fixes the long-standinguv sync --extra akmsinstall hang — the fullakmsextra (Picker / Nodes / Graph) now installs cleanly.akmscore gained CLI/agent backends —claude -p,codex exec, and a local OpenAI-compatible backend, selectable via--backend(pullslitellm+openai-agents+claude-agent-sdk+opentelemetry-*into the bundled sidecar in place of the browser stack).akms-learnbakednbformat/jinja2into its base dependencies (the[notebook]/[html]extras are now no-ops) and auto-selects an LLM provider.- Added
scripts/install_nlm.shto provision the NotebookLM (nlm) CLI. - MechDSL vendored packages (
mechdsl-core+algo2code) bumped to0.2.0.
Research Assistant — Learn tab (AKMS-Learn)¶
A new Learn tab compiles AKMS knowledge into learning artifacts via the
vendored akms-learn engine. The UI is fully capability-driven — modes and
exporters come from the backend (/api/learn/profiles, /exporters) and
unavailable/planned modes render disabled rather than failing on submit.
- Backend
/api/learn/*surface (status, profiles, exporters, compile, artifacts) with per-mode request validation and a capability gate. - Pass B: mode-specific forms, preview panels (notebook / assessment / provenance-JSON / generated-warnings), artifact history with open-export-folder, and a domain-pack status card (source-pack table + capability badges, payload-driven).
- "Send to Learn" handoff from the Graph view.
- Structured generation warnings (generated-content / skipped-prereq / missing-dep) and a Learning Source Review Bundle export.
- Compile artifacts cache under
learning/<id>with a global-vault write guard; LF-canonical artifact text for cross-platform reproducibility.
LLM provider activation¶
Learning modes that need an LLM (e.g. llm_expanded) now activate when the
host supplies a provider — no separate key wiring in the engine.
- The host-resolved LLM provider is injected into
akms-learnLearningRequests at compile time; capability gates and/profilesreflect real host availability so a provider-less host degrades gracefully instead of erroring.
MechDSL executable bridge (Tier 3)¶
New MechDSL mode (/api/mechdsl/* + Overview / Compile / Artifacts UI,
behind MechdslGate): compile % mechanics LaTeX problems into FEM solver
code and transpile algorithm boxes, via compmech-reference-pack + mechdsl-core.
- Bundled Taichi-free. The emit/transpile/capabilities surface needs no
Taichi runtime (it lives in
mechdsl-core's optional[verify]extra, not installed); onlyrun_verify=Truewould, and it is gated off. Keeps the sidecar ~170 MB lighter —/api/mechdsl/statusreportsavailable: truewithtaichi_required_for: ["verify"]. akms-learnis now bundled in the sidecar (compmech's dependency), so the Learn modes above ship in the packaged app.
Vendored dependencies — MechDSL (new)¶
mechdsl-core + algo2code are vendored under thirdparty/MechDSL/ as a
partial source mirror (refresh with scripts/sync_mechdsl_vendor.sh).
Vendored dependencies — zotero-summarizer¶
The bundled zotero-summarizer has been updated with a large upstream merge
(thirdparty/zotero-summarizer via git subtree pull --squash). All items
below are available in the zsum CLI bundled with Logic-Loom; Pipeline UI
integration for starred items is in progress.
New: NotebookLM pipeline (zsum nlm) ★¶
Full integration of NotebookLM as the LLM backend for card and digest
generation. Activate with extraction.mode: notebooklm in config.yaml.
zsum nlm upload|cards|digests|all|status|cleanupcommand group- Parent collections use direct-member PDFs + child digest
.mdfiles as notebook sources (max 30 sources per notebook, configurable) - Automatic fallback to page-range extraction for NLM-failed papers, with
extraction_method: fallback_pagesprovenance threaded through cards, cache, publish, and the Obsidian plugin (amber indicator + tooltip) notebooklm.parse_locallyoption pipes the NLM answer through a local LLM for JSON normalization when NotebookLM's raw response is unparseable- Cache manifests:
cache/nlm_notebooks.json,cache/nlm_digests.json,cache/nlm_redigests.json
New: Section-aware PDF extraction ★¶
extraction.mode: sections uses TOC boundaries and fuzzy heading matching
(via rapidfuzz) to extract the conceptually relevant portion of each PDF
rather than fixed page ranges. Falls back to pages mode when fewer than
two target sections are found. Three modes now available:
| Mode | Behaviour |
|---|---|
pages (default) |
First N + last M pages of each PDF |
sections |
TOC/heading-detected sections with fuzzy matching |
notebooklm |
Delegates entirely to NLM; page-range fallback for failures |
New: Enrichment commands ★¶
Three standalone analysis commands that augment an existing vault without a full pipeline rerun:
zsum citations— citation counts from OpenAlex + Semantic Scholar; cached with configurable staleness; surfaces in paper frontmatter and per-collection## Most Cited Paperssectionzsum reviews— heuristic review/survey/meta-analysis/tutorial classifier; renders in collection notes and setspaper_typefrontmatterzsum restructure— single-LLM-call advisory on collection hierarchy; proposes renames, splits, merges; cached tocache/restructure_report.md
New: LLM providers¶
codex_exec— Codex CLI backend (codex exec) with--output-schemafor schema-constrained digest generationgemini_cli— Gemini CLI (gemini -p) backendnotebooklm— see NotebookLM pipeline above
New: Setup command ★¶
zsum setup-model— one-command Ollama configuration: checks daemon, pulls a model by size tier (small/medium/large/xlarge defined in an externalmodel_tiers.yaml), writesconfig.yaml, verifies the model responds. Flags:--size,--model,--list,--dry-run.
Vendored dependencies — AKMS¶
New: AKMS Learn ★ (specced, API + UI in progress)¶
akms-learn is vendored alongside akms core. It is a separate learner-
facing projection layer over the AKMS graph: given a graph slice and a
learning request, it compiles a Learning Source Packet (LSP) — a
reproducible YAML artifact with reading order, per-node section extraction,
pitfalls, assessment items, code links, and a validation block. Twelve
generation modes are defined (deterministic outline through adaptive paths);
modes 1 and 12 are implemented in v0.1. Logic-Loom API routes (/api/learn/*)
and the Learn tab are in progress.
Pass B — backend (Plan 4 Phase 4). The /api/learn/* surface now describes
its own capabilities so the UI can be driven entirely from backend status. All
additions are consumer-only (the backend reads akms_learn's catalog and
descriptor data; it never reimplements compiler logic) and additive (Pass-A
response shapes are unchanged):
GET /api/learn/profilesand/exportersnow return the full catalogue, each entry{id, label, status}with availability (available/unavailable/planned) derived fromcapabilities_with_status()and optional-dependency state — never a hard-coded list.POST /api/learn/compilevalidates the requested generation mode up front: unknown mode →422 unknown_mode, unavailable mode →412 capability_unavailable, missingtopic/goal→422 compile_precondition_error. Structured envelopes only — never a 500.- Compile responses carry per-family artifact metadata (notebook cell-count/executed, HTML static/size, assessment public/answer-key presence) and structured warning categories (generated-content, skipped-prerequisite, missing-optional-dependency, source-quality).
GET /api/learn/statusnow includes adomain_packs[]array (domain/source pack ids, capabilities, and per-source-pack role + status), sourced from domain-pack descriptor YAML — with no companion-package import and no hard-coded domain concepts.GET /api/learn/statusalso includes ageneration_modes[]array — the filtered, user-selectable modes the compile gate accepts (exporters, execution-backend adapters, and infra capabilities such aslearning_source_packetexcluded). The mode selector derives from this, so the default selection can no longer POST an infra capability and be rejected422 unknown_mode.- Compile/export remain synchronous (measured sub-100 ms); background-run support is deferred with a documented re-evaluation trigger.
Backend test infrastructure: pytest now uses --import-mode=importlib, and a
session fixture materialises the bundled AKMS Claude assets when the vendored
source is present, so the full pytest services/logic_loom_api/tests suite runs
green on a fresh checkout.
Release pipeline¶
- New
scripts/release.sh— single-script entrypoint that picks up CI-built binaries from the latest successful Release workflow run (or a pinned--run-id), normalizes filenames into the canonicalLogic-Loom-<ver>-<platform>-<arch>.<ext>scheme, stages them under the public release repo, regeneratesSHA256SUMS.txt+ per-file.sha256.txt, copies release notes into place, commits + pushes the release repo, and creates (or, with--replace, recreates) the GitHub Release with all assets attached. Auto-detects prerelease from-alpha/-beta/-rcsuffixes. SeeREADME.md→ "Releases". - Added
--download-artifacts yes|noflag to skip re-downloading CI artifacts when iterating on a failed release attempt. The 500 MB download is cached under.tmp/release-<tag>-<runid>/and reused on the next run. - README.md and CHANGELOG.md are now shipped with every release: the
script stages versioned copies (
Logic-Loom-<ver>-README.md,Logic-Loom-<ver>-CHANGELOG.md) alongside the binaries, includes them in the checksum manifest, and attaches them to the GitHub Release.
CI¶
release.ymlno longer relies on bashglobstar, which themacos-latestrunner's system bash 3.2 doesn't support. The artifact-staging glob now uses brace expansion +nullglob.
0.1.0-alpha.2 — 2026-05-19¶
Second multi-platform alpha. Full release notes:
docs/release_notes/v0.1.0-alpha.2.md.
Three-mode shell¶
Logic-Loom is now a three-mode desktop app: zsum, akms (gated), and assistant. Each mode has its own sub-routes (/zsum/*, /akms/*, /assistant/*); legacy deep links (/picker, /nodes, /graph, /pipeline, /vault) are kept as redirects.
Assistant mode¶
Brand-new subsystem for paper discovery + source batching + workflow runs, living under services/logic_loom_api/src/logic_loom_api/assistant/ and apps/desktop/src/routes/assistant/.
- Source batches —
SourceBatchmodel with nine §8.3 actions (create, edit, duplicate, archive, add/remove/reorder sources, send to AKMS) persisted to<assistant_workspace>/batches.json - Paper discovery — Multi-provider clients (OpenAlex, Semantic Scholar) with normalised result merging, on-disk cache observability (
<assistant_workspace>/discovery_cache/), and Zotero catalog matching - Related papers — Five exploration modes (citations, references, similar, co-citation, co-reference) with ranking presets and a cache lifecycle
- Workflow runs — Five bundled Assistant workflows + prompt-slot resolution + dispatcher supporting both
claudeandnotebooklmexecutors; reproducibility artefacts under<assistant_workspace>/assistant/outputs/<batch_id>/<workflow_id>/<run_id>/ - Outputs — Filtered run-output browser with four-tab detail view + rerun/comparison flows;
/api/assistant/outputsis a filtered view over the shared run registry - HTTP surface — Five route modules under
/api/assistant/*:batches,discover,workflows,outputs,index. All mounted via the degrade-gracefully try/except pattern inmain.py - Workspace bootstrap —
bootstrap_assistant_workspaceruns in the FastAPI lifespan alongside the AKMS bootstrap; both wrapped in try/except so a workspace failure never blocks the sidecar coming up
Workspace search (Cmd-K)¶
A SQLite FTS5-backed research-memory index plus an end-to-end Cmd-K modal.
- Seven indexable artefact kinds —
zotero,abstract,zsum_card,zsum_digest,assistant_output,akms_node,run_metadata(closed set inassistant/research_index/schema.py) - HTTP endpoints:
POST /api/assistant/index/search— full-text searchPOST /api/assistant/index/rebuild— walk every artefact and re-ingestGET /api/assistant/index/status— per-kind counts +last_rebuild_at- On-disk state —
<assistant_workspace>/index/fts.sqlite(records + FTS5 virtual table) plusindex.meta.jsonsolast_rebuild_atsurvives sidecar restarts - Frontend — Cmd-K / Ctrl-K modal in
AppShellwith seven kind-filter chips, ranked result list, deep-link routing to the owning Assistant route, and an empty-state Rebuild index affordance - Auto-updates — A shared
IndexLifecyclesingleton (perSettingsinstance) is wired intoSourceBatchServiceandRunnerServiceso the index stays current across the four hot paths: - Batch create / edit fires
on_changefor every zotero source - Batch
remove_sourcesfireson_deletefor evicted sources +on_changefor the remaining state - Batch
deletefireson_deletefor every zotero source on the deleted batch - Workflow runs fire
on_changeforrun_metadataat start and forassistant_outputon subprocess completion (via a newon_donecallback onRunRegistry.attach_workflow_subprocess) - 500 ms debounce — Rapid bulk writes collapse into a single FTS5 flush
- Adapter robustness — The
assistant_output+run_metadatarebuild walkers prefer the globalRunRegistry(canonical source of truth vialog_path.parent) and fall back to the legacy filesystem walk so workspace layout changes don't break the rebuild path
Effective-prompts filename unified¶
The shared OutputStore previously wrote effective-prompts.json (dash) while the Assistant runner wrote effective_prompts.json (underscore). Both writers now use the underscore form. The HTTP route stays at /effective-prompts for REST convention.
Packaging and release workflow¶
- Added PyInstaller-based sidecar entrypoint at
packaging/pyinstaller/logic_loom_api_entry.py - Added platform-specific sidecar build scripts:
scripts/build_sidecar_macos.shscripts/build_sidecar_linux.shscripts/build_sidecar_windows.ps1- Updated Tauri bundling to include
apps/desktop/src-tauri/binaries/*as packaged resources - Updated the Rust sidecar launcher to use
uv run ...in debug builds and the bundledlogic-loom-apiexecutable in packaged builds - Added
scripts/logic_loom_build.mjssopnpm logic-loom:buildnow auto-builds the sidecar for the current operating system before invoking the Tauri release build - Added release-build artifact ignores for
.venv-sidecar-build/,.pyinstaller-build/,.pyinstaller-dist/,logic-loom-api.spec, andapps/desktop/src-tauri/binaries/ - Verified locally on macOS:
- PyInstaller sidecar build succeeded
- direct sidecar launch +
/api/app/healthcheck succeeded - packaged app and
.dmgbuild succeeded
Vendoring¶
AKMS and zotero-summarizer are now vendored under thirdparty/ via git subtree --squash. Path deps in pyproject.toml [tool.uv.sources] point at the vendored copies for both editable dev installs and reproducible packaged builds. The Nodes_Vault subtree lives in the vendored AKMS but is explicitly excluded from the wheel (Phase 12 scripts/check_resources_no_vault.py guard).
Documentation¶
- New
services/logic_loom_api/src/logic_loom_api/assistant/README.md— one-page module map, service dependency graph, on-disk shape, and known follow-ups for the Assistant subsystem - New
CLAUDE.mdcovers the three-mode shell, the full mounted-routes list (including the try/except-guarded routers), and the Assistant subsystem gotcha
0.2.0 — 2026-05-10¶
Graph visualization¶
Logic-Loom v0.2 adds a read-only AKMS graph explorer backed by the AKMS core graph compiler and a Logic-Loom-owned cache.
Backend:
- New
/api/graph/*namespace: GET /api/graph/statusPOST /api/graph/refreshGET /api/graph/nodesGET /api/graph/edgesGET /api/graph/egoGET /api/graph/cluster- New graph adapter compiles via
akms.graph.build_graph.build_graph()and loads cached graphs viaload_graph() - Graph cache is owned by Logic-Loom (
cache_path/graph/graph.json) rather than written into the AKMS repo - Graph nodes are enriched with
file_pathmetadata for inspector/editor integration
Frontend:
- New Graph tab guarded by AKMS graph readiness
- React Flow canvas with dagre layout
- Filtered graph, ego-graph, and cluster views
- Inspector with metadata, connected-edge summary, Open in Nodes, and Open in Editor actions
- Nodes review page can now jump directly into the Graph tab for the selected node
Configuration:
- Added
akms_global_vaultsetting with fallback resolution: - explicit config
<akms_repo>/Packages/Nodes_VaultAKMS_GLOBAL_VAULT~/.claude/akms/nodesGET /api/app/confignow exposes graph cache and effective AKMS graph-vault pathsGET /api/app/akms-statusnow distinguishes picker availability from graph availability
AKMS is now optional¶
Logic-Loom can run standalone with just zotero-summarizer. The akms-nodes-gen
integration moved behind [project.optional-dependencies]. The optional extra
now installs both akms and akms-nodes-gen.
Install with uv sync --extra akms to enable the Picker, Nodes, and Graph tabs.
Without it, those tabs show a clear availability placeholder instead of failing.
akms_reporemoved from first-run required fields- New
GET /api/app/akms-statusendpoint reports package + repo availability - Frontend
<AkmsGate>wrapper on Picker, Nodes, and Graph routes
NotebookLM integration¶
New /api/nlm/* route module with four task types, all running as background
subprocesses through the shared RunRegistry with SSE log streaming:
POST /api/nlm/notebook— Create NotebookLM notebook and upload PDFs (wrapsprepare_notebook.py)POST /api/nlm/generate— Generate nodes via Claude API with optional NLM MCP grounding (wrapsgenerate_nodes_pipeline.py)POST /api/nlm/nlm-batch— Generate nodes directly via NotebookLM, no Claude tokens (wrapsakms_nodes_gen.nlm_batch)POST /api/nlm/validate— Validate nodes against source notebooks (wrapsvalidate_nodes.py)
Picker UI changes:
- Generate (Claude) and Generate (NLM) buttons in BatchDetailPane
- Validate Nodes button in BatchDetailPane
- Buttons unlock progressively after notebook creation
NlmBatchDialogcollects plan path, prompt file, and options before launchNlmRunDialogstreams subprocess output in real time
Config path fix¶
Fixed getBatch() not reading notebook_id from the AKMS assignment response,
which caused Generate/Validate buttons to stay disabled after notebook creation.
Settings¶
- Added
nlm_mcp_urlsetting for NotebookLM MCP server URL - Added
akms_global_vaultsetting for AKMS graph source resolution
0.1.0 — 2026-05-09¶
Initial release: zsum pipeline runner, vault browser, AKMS batch picker, settings page, first-run setup dialog.