ltcai 12.0.0 → 12.2.0

package/README.md

@@ -9,9 +9,10 @@
 [![VS Code Marketplace Version](https://vsmarketplacebadges.dev/version-short/parktaesoo.ltcai.svg)](https://marketplace.visualstudio.com/items?itemName=parktaesoo.ltcai)
 [![Open VSX Version](https://img.shields.io/open-vsx/v/parktaesoo/ltcai?label=Open%20VSX)](https://open-vsx.org/extension/parktaesoo/ltcai)
 [![CI Status](https://github.com/TaeSooPark-PTS/LatticeAI/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/TaeSooPark-PTS/LatticeAI/actions/workflows/ci.yml)
+[![CD Status](https://github.com/TaeSooPark-PTS/LatticeAI/actions/workflows/publish.yml/badge.svg)](https://github.com/TaeSooPark-PTS/LatticeAI/actions/workflows/publish.yml)
 [![License](https://img.shields.io/badge/license-MIT-green)](LICENSE)
 
-![v12.0.0 Living Brain walkthrough](output/release/v12.0.0/gifs/v12.0.0-living-brain-walkthrough.gif)
+![v12.2.0 Living Brain walkthrough](output/release/v12.2.0/gifs/v12.2.0-living-brain-walkthrough.gif)
 
 Chat, files, folders, notes, and web pages all flow into one durable knowledge
 graph on your computer. The default is local. Cloud is optional — an
@@ -25,10 +26,10 @@ nothing leaves your machine without explicit consent.
 
 | | |
 | --- | --- |
-| **See your Brain's story in time** — a growth curve, an activity heatmap, and each day's story, rewindable to any past moment ![Brain Chronicle](output/release/v12.0.0/screenshots/13-chronicle.png) | **Chat with a Brain that remembers** — every conversation grows durable, source-linked memory ![Brain Chat](output/release/v12.0.0/screenshots/04-brain-chat-home.png) |
-| **See how knowledge connects** — a real relationship graph, not a file list ![Memory Graph](output/release/v12.0.0/screenshots/05-memory-graph.png) | **Capture anything** — files, whole folders, notes, screenshots, web pages ![Capture](output/release/v12.0.0/screenshots/06-capture.png) |
-| **Automate with review** — agent changes become proposals you approve first ![Review Center](output/release/v12.0.0/screenshots/12-review-center.png) | **Pick a model in one click** — recommended local models for your hardware ![Recommended Models](output/release/v12.0.0/screenshots/02-recommended-models.png) |
-| **Watch a file become memory** — three named steps, not a pipeline diagram ![Material to memory](output/release/v12.0.0/screenshots/11-knowledge-journey.png) | **Say how much it may do alone** — one dial in plain words; dangerous actions stay blocked either way ![Settings](output/release/v12.0.0/screenshots/08-system.png) |
+| **See your Brain's story in time** — a growth curve, an activity heatmap, and each day's story, rewindable to any past moment ![Brain Chronicle](output/release/v12.2.0/screenshots/13-chronicle.png) | **Chat with a Brain that remembers** — every conversation grows durable, source-linked memory ![Brain Chat](output/release/v12.2.0/screenshots/04-brain-chat-home.png) |
+| **See how knowledge connects** — a real relationship graph, not a file list ![Memory Graph](output/release/v12.2.0/screenshots/05-memory-graph.png) | **Capture anything** — files, whole folders, notes, screenshots, web pages ![Capture](output/release/v12.2.0/screenshots/06-capture.png) |
+| **Automate with review** — agent changes become proposals you approve first ![Review Center](output/release/v12.2.0/screenshots/12-review-center.png) | **Pick a model in one click** — recommended local models for your hardware ![Recommended Models](output/release/v12.2.0/screenshots/02-recommended-models.png) |
+| **Watch a file become memory** — three named steps, not a pipeline diagram ![Material to memory](output/release/v12.2.0/screenshots/11-knowledge-journey.png) | **Say how much it may do alone** — one dial in plain words; dangerous actions stay blocked either way ![Settings](output/release/v12.2.0/screenshots/08-system.png) |
 
 ## Why Lattice AI
 
@@ -63,57 +64,43 @@ First-run flow — wake the Brain, pick the owner, load a recommended model:
 
 | | | |
 | --- | --- | --- |
-| ![Login](output/release/v12.0.0/screenshots/01-login.png) | ![Model install](output/release/v12.0.0/screenshots/03-install-load-progress.png) | ![Model library](output/release/v12.0.0/screenshots/07-model-library.png) |
+| ![Login](output/release/v12.2.0/screenshots/01-login.png) | ![Model install](output/release/v12.2.0/screenshots/03-install-load-progress.png) | ![Model library](output/release/v12.2.0/screenshots/07-model-library.png) |
 
 Screenshot index and capture notes:
-[output/release/v12.0.0/SCREENSHOT_INDEX.md](output/release/v12.0.0/SCREENSHOT_INDEX.md)
+[output/release/v12.2.0/SCREENSHOT_INDEX.md](output/release/v12.2.0/SCREENSHOT_INDEX.md)
 
 ## Current Release
 
-The current release is **12.0.0 — Open House**:
-
-11.9.0 made the doors answer. This release opens the house: the two
-largest crates are grouped by what a file is *for*, the contributor
-documentation is a real path in, and four gaps the last release wrote
-down are closed. `lattice-host` serves **422 operations across 41 route
-families** (`POST /mcp` and the folder-prune route are the two new ones),
-and the AI worker is **20 routes** (`POST /worker/vector/query` is the
-one addition). Cloud is still optional and the default is still local.
-
-- **Complexity management first.** `lattice-agent` is six groups —
-  `kernel` (the loop and every decision that can refuse), `parse`,
-  `content`, `tools`, `surface`, `prompts` — and `lattice-platform` is
-  seven domains. Every move is a rename, so the goldens answer
-  identically; each crate carries its own `ARCHITECTURE.md`, and
-  `docs/DEVELOPMENT.md` and the new `docs/ROADMAP.md` are the way in.
-- **Small models become agents.** A measured probe (not a size regex)
-  picks the profile, and the `guided` profile stops asking for JSON at
-  all: pick an action by number, then one argument per turn, and the
-  harness assembles the call. A 0.5B model finished a real file in 3.9s.
-  The same gates, snapshots and sanitizers run on every profile.
-- **Remembering got faster and more careful.** Re-indexing an unchanged
-  folder went **33s → 0.26s**, a 991-item embedding backlog went 40
-  minutes → 15.3s, and a document's own section outline is now in the
-  graph, so an answer can name the heading it came from. Korean queries
-  strip their particles properly, and deleted files get a **「삭제된 파일
-  정리」** button instead of quietly lingering as memory.
-- **Four honest gaps closed.** Restore takes effect without a restart,
-  `/setup/install` really installs on per-item consent, `POST /mcp` is
-  inside the OpenAPI contract, and pointer tools are declared as
-  `pip install "ltcai[pointer]"`.
+The current release is **12.2.0 — Small Voice**:
+
+12.1.0 made remembering faster. This release makes a small local model
+able to *act*: 2B-class models can call MCP tools and skills without
+emitting perfect JSON, and the home screen names those actions in
+plain words. The door is still **422 operations / 41 families** over a
+**20-route worker**. Cloud is still optional and the default is still local.
+
+- **Small models speak tools.** `name`/`arguments`, Qwen XML, and
+  `Action: mcp.grep` parse as the same call. Compact lists stay at nine
+  rows. A skill's "use when" line is consulted even if the user never
+  typed `skill.`. A quoted search term fills a missing `pattern`.
+- **The composer offers the work.** Folder search, read-and-summarize,
+  memory, and skill review are chips under the box. Settings says the
+  same in one card. MCP/skill steps in the timeline get a plain prefix.
+- **12.1.0 Fast Path is unchanged.** Folder overlap, one embed body,
+  rebuild outside the write lock, auto-HNSW at 512.
 
 What this release does not close — small-model *content* quality, the
-mock-only `api_key` path, `brute` still being the search default, watch
-never deleting on its own, the ad-hoc-signed dmg — is listed in
-[RELEASE_NOTES_v12.0.0.md](RELEASE_NOTES_v12.0.0.md).
+mock-only `api_key` path, hash embeddings as the no-download fallback,
+watch never deleting on its own, the ad-hoc-signed dmg — is listed in
+[RELEASE_NOTES_v12.2.0.md](RELEASE_NOTES_v12.2.0.md).
 
-Expected artifacts for 12.0.0 release must use exact filenames:
+Expected artifacts for 12.2.0 release must use exact filenames:
 
-- `dist/ltcai-12.0.0-py3-none-any.whl`
-- `dist/ltcai-12.0.0.tar.gz`
-- `ltcai-12.0.0.tgz`
-- `dist/ltcai-12.0.0.vsix`
-- `src-tauri/target/release/bundle/dmg/Lattice AI_12.0.0_aarch64.dmg`
+- `dist/ltcai-12.2.0-py3-none-any.whl`
+- `dist/ltcai-12.2.0.tar.gz`
+- `ltcai-12.2.0.tgz`
+- `dist/ltcai-12.2.0.vsix`
+- `src-tauri/target/release/bundle/dmg/Lattice AI_12.2.0_aarch64.dmg`
 
 Do not use wildcard artifact uploads. Package registry publishing remains owner-run.
 
@@ -142,7 +129,7 @@ Validation via `npm run lint`, `npm run test:unit`, `npm run test:visual`.
 
 - External package registries are owner-published and can lag behind GitHub.
 - SQLite is the live local Brain store. The optional PostgreSQL/pgvector
-  migration tooling is not part of the 12.0.0 worker.
+  migration tooling is not part of the 12.1.0 worker.
 - Docker, model downloads, cloud model calls, Brain Network, and update checks
   require explicit user action. Cloud is optional: `cli_oauth` (`agy` /
   `grok`) was live-checked at zero billing; the `api_key` path is
@@ -169,9 +156,11 @@ Validation via `npm run lint`, `npm run test:unit`, `npm run test:visual`.
   profile even a 0.5B model writes the requested file and reaches DONE;
   a weak summary still fails the critic and the run ends
   FAILED/NEEDS_REVIEW rather than claiming success.
-- Vector search still defaults to `brute` — exact and byte-compatible.
-  `hnsw+rescore` is real but opt-in, and falls back to the exact scan
-  with its reason when the sidecar cannot answer.
+- Vector search env still defaults to `brute` — exact and byte-compatible
+  on a small Brain. At 512+ vectors with a bound worker sidecar it tries
+  `hnsw+rescore` first and falls back to the exact scan if the sidecar
+  cannot answer. `LATTICEAI_VECTOR_INDEX=hnsw` is still the explicit
+  opt-in.
 - Watch never deletes on its own: a vanished file is reported, and
   cleanup runs only through the confirmed folder-prune flow.
 - The macOS dmg is ad-hoc signed — effectively unsigned — so first launch
@@ -181,7 +170,7 @@ Validation via `npm run lint`, `npm run test:unit`, `npm run test:visual`.
   pending-only, no Self-Model refiner, `delete_node` leaving `PART_OF`,
   review events silent without an owner, KG-api ingest text-only, two
   store cycles per review mutation) are listed with their reasons in
-  [RELEASE_NOTES_v12.0.0.md](RELEASE_NOTES_v12.0.0.md) and prioritized in
+  [RELEASE_NOTES_v12.2.0.md](RELEASE_NOTES_v12.2.0.md) and prioritized in
   [docs/ROADMAP.md](docs/ROADMAP.md).
 
 ## Release History
@@ -193,6 +182,8 @@ same boundary. Earlier notes stay in the tree as `RELEASE_NOTES_v*.md` files.
 
 | Version | Theme |
 | --- | --- |
+| 12.2.0 | Small Voice |
+| 12.1.0 | Fast Path |
 | 12.0.0 | Open House |
 | 11.9.0 | Working Order |
 | 11.8.0 | Travel Light |

package/docs/CHANGELOG.md

@@ -4,6 +4,47 @@ The top entry is either the current unreleased main-branch work or the current
 release line. Older entries are historical and may describe behavior as it
 existed at that release.
 
+## [12.2.0] - 2026-08-29 — Small Voice
+
+### Added
+- Function-calling envelope parse: `name`/`arguments`, nested `function`,
+  Qwen `<function=…><parameter=…>`, `Action: mcp.grep`.
+- Compact executor lists cap at the guided menu size (9). Skills whose
+  `when` line matches the request are consulted without naming `skill.`.
+- A quoted search term fills a missing MCP/native `pattern`/`query`.
+- Home composer chips for folder search, read-and-summarize, memory, and
+  skill review. Settings card states the same. MCP/skill timeline rows
+  get a plain-language prefix.
+
+### Changed
+- Compact prompt names the function-calling envelope 2B models emit.
+
+### Fixed
+- Labeled salvage refused dotted `mcp.` / `skill.` names as chatter.
+
+## [12.1.0] - 2026-08-29 — Fast Path
+
+### Added
+- Folder ingest and vault-watch overlap up to four files (`INGEST_INFLIGHT`).
+  Stamp-skip never enters the pool.
+- One `POST /worker/embed` per note: document text then every chunk.
+  Extract runs beside embed, not in front of it.
+- Default brute search tries `hnsw+rescore` when the store has 512+ vectors
+  and a worker sidecar is bound; failure keeps the original `brute` index
+  block.
+
+### Changed
+- `rebuild_vector_index` embeds outside the write transaction.
+- `write_vectors_with` files the ingest-time supplied vectors so the hash
+  model does not re-derive them.
+- Empty `ltcai[postgres]` extra alias; the live Postgres writer left in 11.6.0.
+
+### Fixed
+- Weekly pip-audit failed on a missing markdown report when there were no
+  findings.
+- Weekly Postgres integration job failed because
+  `tests/integration/test_postgres_migration_live.py` was gone.
+
 ## [12.0.0] - 2026-08-18 — Open House
 
 ### Added

package/docs/CI_AND_RELEASE_GATES.md

@@ -1,6 +1,6 @@
 # CI & Release Gates
 
-> Status: reference 2026-08-16
+> Status: reference 2026-08-29
 
 Reference for the GitHub Actions workflows that guard `main` and releases, the
 supply-chain hardening applied to them, and the recommended branch-protection
@@ -13,6 +13,7 @@ configuration. Companion to [SECURITY_AUDIT.md](SECURITY_AUDIT.md) and
 |----------|------|----------|---------|
 | CI | `.github/workflows/ci.yml` | push/PR to `main` | Lint, typecheck, unit + coverage + integration tests, product-readiness, build + wheel smoke, Rust workspace |
 | Release | `.github/workflows/release.yml` | tags `v*` / `[0-9]*` | Build & validate artifacts (no publish; does not re-run CI lint/tests) |
+| CD | `.github/workflows/publish.yml` | GitHub Release `published`, dispatch | Publish npm / PyPI / Marketplace / Open VSX (idempotent; never on a bare tag) |
 | Visual Smoke | `.github/workflows/visual.yml` | push to `main`, nightly cron, dispatch | Playwright visual smoke (not on PRs) |
 | Sidecar E2E | `.github/workflows/e2e-sidecar.yml` | nightly cron, dispatch | Live sidecar Playwright first-value loop |
 | Dependency Audit | `.github/workflows/dependency-audit.yml` | weekly cron, dispatch | pip-audit + npm audit + CycloneDX SBOMs |
@@ -120,13 +121,19 @@ uploaded as artifacts. Regenerate locally with `scripts/generate_sbom.py`.
 
 ## Postgres integration gate
 
-`postgres-integration.yml` runs the migration-integrity suite
-(`tests/integration/test_postgres_migration_live.py`) that is skipped
-everywhere else. The suite is gated by `LTCAI_LIVE_POSTGRES_DOCKER_CONSENT=1`;
-the workflow sets that variable, and the test itself starts and tears down a
-`pgvector/pgvector:pg16` container via `docker compose` (preinstalled on
-GitHub-hosted `ubuntu-latest`). It is deliberately kept off the PR path (slow,
-image pull, needs Docker) and runs weekly + on demand.
+`postgres-integration.yml` still runs weekly + on demand, but the live
+SQLite→Postgres writer it used to drive left in 11.6.0 with the Python
+product write path. The suite file remains so a Monday cron is not a
+missing-file failure; it skip-explains the retirement. SQLite is the live
+Brain store. Restore a native pgvector door before making this job start
+a container again.
+
+## Dependency-audit clean run
+
+`pip-audit --format markdown --output FILE` writes the file only when it
+has findings. A clean run used to then fail on `cat FILE`. The workflow
+now writes a placeholder report when the file is missing so a clean audit
+is green.
 
 ## Visual smoke and sidecar E2E
 
@@ -177,9 +184,11 @@ It still runs:
 - `npm pack`, vsce package
 - `validate_release_artifacts.py <v> --require-vsix --require-tgz`
 
-Package publication (PyPI / npm / VS Code Marketplace / Open VSX) is a manual
-step (`npm run publish:*`) using **exact version filenames**, never a `dist/*`
-glob, so pushing a tag can never publish by accident. See
+Package publication (PyPI / npm / VS Code Marketplace / Open VSX) is
+`publish.yml` (CD). It runs when a GitHub Release is **published**, or on
+`workflow_dispatch` if that version already has a pushed `v*` tag. A bare
+tag push never publishes. Local `npm run publish:*` still uses **exact
+version filenames**, never a `dist/*` glob. See
 [../RELEASE.md](../RELEASE.md) for the full procedure.
 
 ## Limitations (honest)

package/docs/COMMUNITY_AND_PLUGINS.md

@@ -1,6 +1,6 @@
 # Community And Plugins
 
-Current release: **12.0.0 — Open House**.
+Current release: **12.2.0 — Small Voice**.
 
 LatticeAI defines the path from a strong local-first framework (8.4.0
 action-aware baseline, 8.5.0 registry+DI hardening, 8.6.0 capture/navigation

package/docs/DEVELOPMENT.md

@@ -3,7 +3,7 @@
 > **Status: canonical** — current contributor guidance, kept in sync with the
 > current release.
 
-Current release: **12.0.0 — Open House**.
+Current release: **12.2.0 — Small Voice**.
 
 This document is the contributor onboarding path: how to boot the tree, where
 a change belongs, which gates will go red, and the house rules that keep the
@@ -80,7 +80,7 @@ worker interpreter with `LTCAI_PYTHON` when both exist.
 `rust/target/release/lattice-host`, then `rust/target/debug/lattice-host`. If
 none exist it runs `cargo build -p lattice-host` (debug). A stale
 `rust/target/release/lattice-host` wins over a current debug binary — pin or
-rebuild (`cargo build -p lattice-host --release`) if `-V` is not 12.0.0.
+rebuild (`cargo build -p lattice-host --release`) if `-V` is not 12.2.0.
 
 Do not run `npm start` and `npm run dev` on the same port. The worker
 entrypoint defaults to `LATTICEAI_PORT` or **4825**, the same port as the
@@ -237,7 +237,7 @@ in `rust/`.
 Markdown) and `scripts/check_doc_status.mjs` (every relative link under the
 root canonical docs and `docs/**`). A red line is a broken relative path —
 fix the href or put the file where the href says. Canonical docs (this one
-included) must carry `Current release: **12.0.0 — …**` matching
+included) must carry `Current release: **12.2.0 — …**` matching
 `package.json`; do not bump that marker here ahead of the release lane.
 `npm run docs:check-current` is the release-set version pin
 ([`scripts/check_current_release_docs.mjs`](../scripts/check_current_release_docs.mjs)).
@@ -248,7 +248,7 @@ changelog entries that mention old versions stay.
 ### Release-evidence binding
 
 `scripts/check_release_evidence_bound.mjs` (lint member 9) checks that
-`output/release/v12.0.0/SCREENSHOT_INDEX.md` still names the live
+`output/release/v12.2.0/SCREENSHOT_INDEX.md` still names the live
 `static/app/asset-manifest.json` digest and the visual mock-server
 fingerprint. It exists so a later `npm run build:assets` cannot ship
 screenshots of an older UI, and so a mock-server edit cannot leave the
@@ -317,19 +317,19 @@ For user-facing, API, runtime, release, or packaging changes, check:
   appears
 
 The release-docs lane owns README / ARCHITECTURE / FEATURE_STATUS version
-bumps. Do not move this file's `Current release` marker off 12.0.0 ahead of
+bumps. Do not move this file's `Current release` marker off 12.2.0 ahead of
 that lane.
 
 Release/publish examples must use exact target-version filenames. Do not
 document wildcard artifact upload commands.
 
-For 12.0.0 release work, exact artifacts are:
+For 12.2.0 release work, exact artifacts are:
 
-- `dist/ltcai-12.0.0-py3-none-any.whl`
-- `dist/ltcai-12.0.0.tar.gz`
-- `ltcai-12.0.0.tgz`
-- `dist/ltcai-12.0.0.vsix`
-- `src-tauri/target/release/bundle/dmg/Lattice AI_12.0.0_aarch64.dmg`
+- `dist/ltcai-12.2.0-py3-none-any.whl`
+- `dist/ltcai-12.2.0.tar.gz`
+- `ltcai-12.2.0.tgz`
+- `dist/ltcai-12.2.0.vsix`
+- `src-tauri/target/release/bundle/dmg/Lattice AI_12.2.0_aarch64.dmg`
 
 The dmg is ad-hoc signed (effectively unsigned); `npm run release:validate`
 checks the names and presence, not a Developer ID signature.

package/docs/ONBOARDING.md

@@ -1,6 +1,6 @@
 # Lattice AI Onboarding
 
-Current release: **12.0.0 — Open House**.
+Current release: **12.2.0 — Small Voice**.
 
 The first-run goal is a five-minute path from "I opened the app" to "my Brain
 has a source, a question, and proof." This page is the product contract behind

package/docs/OPERATIONS.md

@@ -1,4 +1,4 @@
-# Lattice AI — Operations Guide (v12.0.0)
+# Lattice AI — Operations Guide (v12.2.0)
 
 > **Status: canonical** — kept in sync with the current release. Storage layout
 > below reflects the SQLite live Brain store and workspace scoping, not the

package/docs/ROADMAP.md

@@ -3,7 +3,7 @@
 > **Status: reference** — point-in-time inventory, redated at v12.0.0. Not a
 > canonical current-release document; version gates do not bind it.
 
-As of **2026-08-18**, against the 12.0.0 — Open House tree. The rows below
+As of **2026-08-29**, against the 12.1.0 — Fast Path tree. The rows below
 were gathered against 11.9.0 and re-checked when 12.0.0 shipped; what that
 release closed is marked closed rather than deleted, so the ledger still
 shows what was owed.
@@ -45,7 +45,7 @@ rather than being deleted: the small-model harness (P1) and the HNSW index
 | --- | --- | --- | --- | --- |
 | **Small-model agent-run content quality** | **Half closed in 12.0.0.** The mechanical half is done: the `guided` profile stops asking for JSON, the dial is chosen by a measured probe, a run that produces nothing demotes itself downward mid-run, and a 0.5B model reached `DONE` in 3.9s with a real file. The half still open is the *writing* — a weak summary fails the critic and the run ends `FAILED` / `NEEDS_REVIEW`. The cross-model matrix is improving from 11 of 18. | L | **P1** — still the voice the product ships on 8GB, and still the reason a first run can end in a review state. | Keep measuring with the loop's own parser, not a second harness. New answers go under new fixture keys (`agent_loop` `*_extended`); do not rewrite frozen rows. The remaining lever is content, not format: better plan→content prompting and a critic that says *what* was thin, per-model hacks still forbidden. |
 | **Real-embedding default rollout** | **Narrowed in 12.0.0, not closed.** Auto-detection now adopts a real downloaded embedding model when one is present, the hash model is labelled `fallback` rather than presented as semantic, and vector identity is filtered by `(model, dim)` so two spaces cannot mix. What is still true: on a machine that has downloaded nothing, the default remains `lattice-local-hash-v1` (blake2 bag-of-features), and "semantic" recall is then a hash of tokens. | M | **P1** — recall is the product. Hash as a labelled fallback is fine; hash as the silent default is not. | Make the first-run flow offer the embedding model the way it offers a chat model, and keep the switch honest: drain the backlog through `lattice-jobs` so a change of embedder is a reindex, and report `stale_embedder` until the queue is empty. |
-| **Worker-side batch embed** | **Mostly closed in 12.0.0 on the drain path**: embedding moved ahead of the write transaction, so the writer no longer holds a lock while a model runs — ~66 → ~1,300 items/s, and a 991-item backlog drains in 15.3s instead of ~40 minutes. What remains is the ingest-time door: it batches only when `(model_id, dim)` already agrees, and the hash path still embeds inline, one node at a time. | M | **P1** — the backlog path is fast now; a real-embed default still needs the inline door not to serialise against the single MLX executor. | Make `GraphWriter::write_vectors_with` + one `/worker/embed` call the ingest-time path whenever a provider is bound. Keep the drain planner as the backlog path. Do not open a second embedder inside `lattice-core`. |
+| **Worker-side batch embed** | **Closed in 12.1.0 on the ingest-time door**: one `/worker/embed` body is the document vector followed by every chunk, extract runs beside it, and `write_vectors_with` files those vectors. The drain planner stays the backlog path. Folder/watch overlap up to four files. What remains for a real-embed default is auto-detection on first run, not a second embedder. | M | **P1 → closed for the ingest door; the real-embed default row above is still open.** | Keep. Do not open a second embedder inside `lattice-core`. |
 
 ## P2 — real, but the product still works without them
 

package/docs/TRUST_MODEL.md

@@ -1,6 +1,6 @@
 # Lattice AI Trust Model
 
-Current release: **12.0.0 — Open House**.
+Current release: **12.2.0 — Small Voice**.
 
 Lattice AI is local-first, explicit about external communication, and honest
 when a capability is unavailable.

package/docs/WHY_LATTICE.md

@@ -1,6 +1,6 @@
 # Why Lattice AI Exists
 
-Current release: **12.0.0 — Open House**.
+Current release: **12.2.0 — Small Voice**.
 
 **Lattice AI is a local-first Digital Brain that keeps your knowledge durable
 across any AI model.**

package/docs/kg-schema.md

@@ -1,6 +1,6 @@
 # Knowledge Graph Schema
 
-Current release: **12.0.0 — Open House**.
+Current release: **12.2.0 — Small Voice**.
 
 명세 출처: `lattice_ai_full_spec.pptx` 슬라이드 20·21·22
 구현: `lattice_brain/graph/schema.py`

package/lattice_brain/__init__.py

@@ -31,7 +31,7 @@ from .multimodal import (
     transcribe_audio,
 )
 
-__version__ = "12.0.0"
+__version__ = "12.2.0"
 
 __all__ = [
     "AudioFacts",

package/latticeai/__init__.py

@@ -1,3 +1,3 @@
 """Lattice AI - modular server package."""
 
-__version__ = "12.0.0"
+__version__ = "12.2.0"

package/latticeai/services/architecture_readiness.py

@@ -19,7 +19,7 @@ from dataclasses import dataclass
 from pathlib import Path
 from typing import Any, Dict, List
 
-ARCHITECTURE_VERSION_TARGET = "12.0.0"
+ARCHITECTURE_VERSION_TARGET = "12.2.0"
 
 PREFERRED_REFACTORING_ORDER = [
     "agent-runtime",

package/latticeai/services/product_readiness.py

@@ -28,7 +28,7 @@ from typing import Any, Dict, List
 
 from latticeai.services.architecture_readiness import architecture_readiness
 
-PRODUCT_VERSION_TARGET = "12.0.0"
+PRODUCT_VERSION_TARGET = "12.2.0"
 
 
 @dataclass(frozen=True)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ltcai",
-  "version": "12.0.0",
+  "version": "12.2.0",
   "description": "Lattice AI — local-first Digital Brain that keeps your knowledge durable across any AI model.",
   "homepage": "https://github.com/TaeSooPark-PTS/LatticeAI#readme",
   "repository": {

package/scripts/check_current_release_docs.mjs

@@ -6,7 +6,7 @@ const root = process.cwd();
 const pkg = JSON.parse(readFileSync(path.join(root, "package.json"), "utf8"));
 const version = pkg.version;
 const releaseDir = `output/release/v${version}`;
-const releaseTheme = "Open House";
+const releaseTheme = "Small Voice";
 const title = `${version} — ${releaseTheme}`;
 const escapedVersion = version.replaceAll(".", "\\.");
 

package/scripts/release_screen_claims.json

@@ -20,6 +20,40 @@
     "whole-image delta: naming where the change is makes the claim more",
     "specific, not less."
   ],
+  "12.2.0": {
+    "_why": [
+      "Small Voice is a 2B tool-calling release with two visible surfaces.",
+      "",
+      "1. Brain home composer: four plain-language chips (folder search, read",
+      "   and summarize, memory, skill review) sit under the textarea. The",
+      "   Living Brain still dominates the shot, so the whole-image delta sits",
+      "   under the 8% live floor; the claim uses the measured 3.96% as the",
+      "   floor, not a redesign of the shell.",
+      "",
+      "2. Settings: a new 'small models can use tools' card with four badges.",
+      "   That card is why 08 grew 168px.",
+      "",
+      "No other screen was redesigned. Unclaimed screens are measured and",
+      "printed; they are not gated."
+    ],
+    "04-brain-chat-home.png": {
+      "min_pct": 3.0
+    },
+    "08-system.png": {
+      "min_pct": 1.5
+    }
+  },
+  "12.1.0": {
+    "_why": [
+      "Fast Path is a backend ingest/search release. Folder ingest overlaps",
+      "parse and embed, one /worker/embed body carries the document plus its",
+      "chunks, rebuild hashes outside the write lock, and a Brain with 512+",
+      "vectors tries hnsw+rescore when a worker sidecar is bound.",
+      "",
+      "No screen was redesigned. Empty claim set on purpose. Unclaimed screens",
+      "are still measured and printed; they are not gated."
+    ]
+  },
   "12.0.0": {
     "_why": [
       "Open House brings component and resilience updates across the frontend:",

package/src-tauri/Cargo.lock

@@ -1863,7 +1863,7 @@ dependencies = [
 
 [[package]]
 name = "lattice-agent"
-version = "12.0.0"
+version = "12.2.0"
 dependencies = [
  "axum",
  "base64 0.22.1",
@@ -1880,7 +1880,7 @@ dependencies = [
 
 [[package]]
 name = "lattice-ai-desktop"
-version = "12.0.0"
+version = "12.2.0"
 dependencies = [
  "lattice-host",
  "lattice-jobs",
@@ -1895,7 +1895,7 @@ dependencies = [
 
 [[package]]
 name = "lattice-auth"
-version = "12.0.0"
+version = "12.2.0"
 dependencies = [
  "axum",
  "base64 0.22.1",
@@ -1912,7 +1912,7 @@ dependencies = [
 
 [[package]]
 name = "lattice-chat"
-version = "12.0.0"
+version = "12.2.0"
 dependencies = [
  "axum",
  "bytes",
@@ -1934,7 +1934,7 @@ dependencies = [
 
 [[package]]
 name = "lattice-core"
-version = "12.0.0"
+version = "12.2.0"
 dependencies = [
  "blake2",
  "bytes",
@@ -1950,7 +1950,7 @@ dependencies = [
 
 [[package]]
 name = "lattice-host"
-version = "12.0.0"
+version = "12.2.0"
 dependencies = [
  "axum",
  "lattice-agent",
@@ -1971,7 +1971,7 @@ dependencies = [
 
 [[package]]
 name = "lattice-ingest"
-version = "12.0.0"
+version = "12.2.0"
 dependencies = [
  "axum",
  "lattice-auth",
@@ -1986,7 +1986,7 @@ dependencies = [
 
 [[package]]
 name = "lattice-jobs"
-version = "12.0.0"
+version = "12.2.0"
 dependencies = [
  "axum",
  "lattice-auth",
@@ -2001,7 +2001,7 @@ dependencies = [
 
 [[package]]
 name = "lattice-platform"
-version = "12.0.0"
+version = "12.2.0"
 dependencies = [
  "axum",
  "base64 0.22.1",
@@ -2024,7 +2024,7 @@ dependencies = [
 
 [[package]]
 name = "lattice-retrieval"
-version = "12.0.0"
+version = "12.2.0"
 dependencies = [
  "axum",
  "fancy-regex",

package/src-tauri/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lattice-ai-desktop"
-version = "12.0.0"
+version = "12.2.0"
 description = "Lattice AI Digital Brain desktop shell"
 authors = ["TaeSoo Park"]
 edition = "2021"

package/src-tauri/tauri.conf.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://schema.tauri.app/config/2",
   "productName": "Lattice AI",
-  "version": "12.0.0",
+  "version": "12.2.0",
   "identifier": "ai.lattice.desktop",
   "build": {
     "beforeDevCommand": "npm run frontend:dev",