docs: add agent workflows and copy-paste setup prompt

AGENTS.md

@@ -1,9 +1,31 @@
 # Searchi development
 
+Read README.md, SKILLS.md, and docs/ROADMAP.md before starting or resuming work.
+Inspect Git status and preserve existing changes. Do not claim production
+readiness without completed release gates and recorded evidence.
+
 - All tests in the Windows VM must use CPU only. Never enable GPU providers here.
+- Production uses available GPU/hardware acceleration with reliable CPU fallback;
+  the CPU-only rule is a VM testing constraint, not a product restriction.
 - Keep the Rust engine independent of the desktop shell; CLI and UI share its API.
 - Use bounded work, explicit errors, versioned storage, and offline defaults.
 - Never substitute simulated embeddings for working semantic search.
+- Production semantic search must use Google EmbeddingGemma 2 as in DigUp.
+  MiniLM proof artifacts are historical experiments, not an accepted backend.
+- The desktop UI is the primary product, including local model setup and semantic
+  indexing/search. Keep a separate CLI-only build for headless Linux with no GUI dependencies.
+- Desktop setup must work out of the box: ship the native worker, automatically
+  download/verify missing Google assets, reuse cached assets, and expose progress/retry in the UI.
 - Add meaningful tests for retrieval, persistence, and filesystem lifecycle changes.
 - Keep docs/ROADMAP.md current. Unexecuted platform checks remain unchecked.
 - Agents own assigned paths and must coordinate shared interface changes. Do not commit other agents' unfinished work.
+- Prepare indexes and the real Google query session in the background. Retain
+  warmed readers and keep keyword search usable during setup. Measure startup,
+  actual first input, and warm p95 separately.
+- UI should belong to each OS: native typography/chrome/dialogs, themes,
+  keyboard access, reduced motion and high contrast. Brief transitions must not
+  delay requests. Preserve selection/focus as progressive results arrive.
+- Follow SKILLS.md for validation and handoffs. Leave actual checks, blockers,
+  and concrete next tasks. Keep unexecuted OS and GPU checks explicitly open.
+- Use karl as Git author with no agent co-author trailers. Keep credentials,
+  model binaries, generated build assets, and local indexes out of Git.

README.md

@@ -7,13 +7,55 @@ production readiness is tracked in [the roadmap](docs/ROADMAP.md).
 
 `crates/searchi-core` owns persistent indexing and retrieval. `crates/searchi-cli`
 provides a headless interface. `apps/desktop` hosts the Tauri desktop app.
-The initial implementation provides lexical search over filenames, bounded text,
-PDF pages and DOCX paragraphs. Semantic and media search are explicit upcoming
-milestones; a genuine CPU model proof is included separately.
+Search combines indexed filenames, SQLite FTS5 keyword retrieval, and real
+Google EmbeddingGemma 2 semantic search with a persistent HNSW index. PDF pages
+and DOCX paragraphs retain source locations. Image, audio, and video search remain
+planned; the provisioned media projector is not yet used. Granola is not required.
+The desktop UI is primary; the CLI builds separately without GUI dependencies.
 
-All testing in the Windows development VM uses CPU only. Indexed content stays
+Production uses supported hardware acceleration with CPU fallback. All testing
+in the Windows development VM uses CPU only. Indexed content stays
 local. Treat the index as sensitive: it contains extracted document text.
 
+The desktop automatically downloads and verifies missing Google artifacts
+(approximately 865 MB), reuses its local cache, and warms the query session in
+the background. Development builds must build and stage the native worker first;
+production installers and signing remain release gates. First-query performance
+is measured separately from repeated-query performance.
+
+## Copy-and-paste setup prompt
+
+Paste this into your coding agent:
+
+```text
+Set up Searchi from https://tea.karlcom.de/karl/searchi.git in a new searchi
+directory, or reuse the existing checkout without overwriting local changes.
+Read AGENTS.md, SKILLS.md, docs/ROADMAP.md, and apps/desktop/README.md first.
+Inspect the OS and installed tools. Install missing supported prerequisites:
+Git, stable Rust, Node.js 24+, Python 3, CMake, native C/C++ tools and Tauri's
+platform dependencies. Preserve existing credentials and never print secrets.
+From the repository root, build and stage the pinned Google runtime:
+python tools/embeddinggemma2/build_runtime.py --backend cpu --jobs 2
+python tools/embeddinggemma2/stage_runtime.py --backend cpu
+Run cargo test --workspace --locked, cargo fmt --all -- --check, and
+cargo clippy --workspace --all-targets --locked -- -D warnings.
+Run cargo test --manifest-path apps/desktop/src-tauri/Cargo.toml --locked.
+In apps/desktop run npm ci, npm test, npm run format:check, and npm run build.
+For Karl's Windows VM set SEARCHI_FORCE_CPU=1 and
+WEBVIEW2_ADDITIONAL_BROWSER_ARGUMENTS=--disable-gpu before tests or launch.
+Launch the real app using npm run tauri dev from apps/desktop. Allow automatic
+verified Google model setup; never substitute another model or mock results.
+Ask which folders I want indexed; do not index my whole home automatically.
+Verify filename and remembered-content searches on my selected files, including
+persistence after restart. Report actual checks and blockers. Do not publish a
+release or claim production readiness, GPU validation, or untested OS coverage.
+```
+
+This is developer setup, not an installer. See the [desktop guide](apps/desktop/README.md)
+and [official Tauri prerequisites](https://v2.tauri.app/start/prerequisites/).
+The worker builder also supports `auto`, `metal`, `vulkan`, and `cuda`; those
+require platform SDKs and separate hardware validation.
+
 ## Development
 
 Install stable Rust and the platform's C/C++ build prerequisites. Run:
@@ -26,6 +68,12 @@ cargo run -p searchi-cli -- --help
 ```
 
 Desktop development instructions live in `apps/desktop/README.md`.
+Agent constraints and workflows live in [AGENTS.md](AGENTS.md) and
+[SKILLS.md](SKILLS.md). Use Node.js 24+ for frontend state tests.
+
+For a headless build, run `cargo build --release --locked -p searchi-cli`.
+No Node, Tauri, or WebView is needed. Semantic commands additionally need the
+native worker and Google assets; `searchi setup` provisions the model cache.
 Platform and CI details live in [the build guide](docs/BUILDING.md).
 Native CI builds must pass on all supported systems before release. Cross-platform
 source support does not imply signed macOS installers can be built on Windows.
@@ -35,3 +83,5 @@ source support does not imply signed macOS installers can be built on Windows.
 Do not publish until the roadmap's release gates have evidence. Record benchmark
 hardware, corpus size, cold/warm state and p95 latency. Signing credentials are
 supplied through CI secrets, never source control.
+
+Licensed under [MIT](LICENSE). Repository author: Karl.

SKILLS.md

@@ -0,0 +1,84 @@
+# Searchi agent workflows
+
+This repository guide does not automatically install a Codex skill or plugin.
+Read AGENTS.md, README.md, and docs/ROADMAP.md before working.
+
+## Resume and implement
+
+Inspect Git status and recent commits, preserve local changes, and choose a
+concrete roadmap milestone with acceptance criteria. Read relevant code and tests
+first. Assign paths for authorized parallel work and coordinate shared APIs.
+Keep the production goal active until all required gates have recorded evidence.
+
+## Search and indexing
+
+Preserve strict filters before candidate limits, exact identifier priority,
+real Google vectors, source locations, atomic semantic generation activation,
+and stale/deleted source suppression. Test updates, renames, deletion, restart,
+corrupt documents, extraction limits, and interrupted work. Never silently drop
+searchable content or hide slow first inputs behind warm percentiles.
+
+## Runtime and setup
+
+Use tools/embeddinggemma2/model-manifest.json and its pinned runtime builder.
+Build/stage CPU workers for VM tests. Production acceleration requires separate
+hardware evidence and reliable CPU fallback. Verify size/SHA-256, cache reuse,
+interrupted downloads, errors, and retries. Keep inference local. Never substitute
+MiniLM, simulated vectors, or hosted inference. Ship the worker with the app.
+
+## Desktop design
+
+The desktop UI is primary. Use native typography, chrome, dialogs, shortcuts,
+light/dark themes, reduced motion, and high contrast. Keep search dominant and
+previews readable; setup status must be honest. Preserve selection, focus, and
+scroll when semantic results arrive. Brief transitions must not delay requests
+or block interaction. The selected direction is the first generated concept,
+with Raycast as a reference: compact search, result rows, and a passage preview.
+Generated mockups do not establish functional PDF navigation or visual QA.
+
+## Run checks
+
+Use stable Rust and Node.js 24+. Before Windows VM tests or launch:
+
+```powershell
+$env:SEARCHI_FORCE_CPU = '1'
+$env:WEBVIEW2_ADDITIONAL_BROWSER_ARGUMENTS = '--disable-gpu'
+```
+
+From the repository root:
+
+```sh
+cargo fmt --all -- --check
+cargo test --workspace --locked
+cargo clippy --workspace --all-targets --locked -- -D warnings
+cargo fmt --manifest-path apps/desktop/src-tauri/Cargo.toml -- --check
+cargo test --manifest-path apps/desktop/src-tauri/Cargo.toml --locked
+```
+
+From apps/desktop:
+
+```sh
+npm ci
+npm test
+npm run format:check
+npm run build
+```
+
+Real-model tests require verified assets and the native CPU worker. Set
+SEARCHI_GEMMA_MODEL_DIR and SEARCHI_GEMMA_WORKER, then run:
+
+```sh
+cargo test -p searchi-semantic --test gemma_cpu -- --ignored --nocapture
+```
+
+Record actual outputs, hardware, corpus size, background preparation, first-input
+latency and warm latency in the relevant validation report. Unexecuted platform
+checks stay open. Compilation alone is not UI interaction verification.
+
+## Commit and hand off
+
+Review staged diffs for secrets, model binaries, generated files, and unfinished
+parallel work. Use Karl as author with no agent co-author trailers. Push only when
+authorized. Karl's infrastructure uses selected Infisical injection; never print
+credentials or commit them. Leave changed paths, checks, blockers, and a concrete
+next task. Mark roadmap items complete only with recorded evidence.