mirror of
https://github.com/open-jarvis/OpenJarvis.git
synced 2026-08-14 08:52:06 +00:00
Compare commits
9
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
e7c46c1985 | ||
|
|
00d1e39b6d | ||
|
|
843375d6ef | ||
|
|
8d33cb58fa | ||
|
|
e4c4bcbae3 | ||
|
|
993c24c8b9 | ||
|
|
5bc8d3a2f6 | ||
|
|
433d10db5e | ||
|
|
9b7b3681f6 |
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schemaVersion": 1,
|
||||
"label": "Git Clones",
|
||||
"message": "128,077",
|
||||
"message": "130,895",
|
||||
"color": "green",
|
||||
"namedLogo": "git"
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"total_clones": 128077,
|
||||
"last_updated": "2026-06-22T08:05:29Z",
|
||||
"total_clones": 130895,
|
||||
"last_updated": "2026-06-24T07:14:43Z",
|
||||
"daily": {
|
||||
"2026-03-27": 2189,
|
||||
"2026-03-28": 1874,
|
||||
@@ -88,6 +88,8 @@
|
||||
"2026-06-18": 1408,
|
||||
"2026-06-19": 1350,
|
||||
"2026-06-20": 1437,
|
||||
"2026-06-21": 1426
|
||||
"2026-06-21": 1426,
|
||||
"2026-06-22": 1350,
|
||||
"2026-06-23": 1468
|
||||
}
|
||||
}
|
||||
|
||||
@@ -23,6 +23,8 @@ jobs:
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v8.0.0
|
||||
with:
|
||||
enable-cache: true
|
||||
|
||||
- name: Install dependencies
|
||||
run: uv sync --extra dev --extra framework-comparison --extra server
|
||||
@@ -55,6 +57,8 @@ jobs:
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v8.0.0
|
||||
with:
|
||||
enable-cache: true
|
||||
|
||||
- name: Install dependencies
|
||||
run: uv sync --extra dev --extra framework-comparison --extra server
|
||||
@@ -63,8 +67,13 @@ jobs:
|
||||
run: uv run maturin develop --manifest-path rust/crates/openjarvis-python/Cargo.toml
|
||||
|
||||
- name: Run tests
|
||||
# COVERAGE_CORE=sysmon uses CPython 3.12's sys.monitoring backend,
|
||||
# which is dramatically cheaper than the default C trace function.
|
||||
# -n auto fans the suite out across all runner cores via pytest-xdist.
|
||||
env:
|
||||
COVERAGE_CORE: sysmon
|
||||
run: |
|
||||
uv run pytest tests/ -v --tb=short -m "not live and not cloud and not hub" \
|
||||
uv run pytest tests/ -n auto -q --tb=short -m "not live and not cloud and not hub" \
|
||||
--cov=openjarvis \
|
||||
--cov-report=term-missing \
|
||||
--cov-report=xml \
|
||||
@@ -107,6 +116,8 @@ jobs:
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v8.0.0
|
||||
with:
|
||||
enable-cache: true
|
||||
|
||||
- name: Install dependencies
|
||||
run: uv sync --extra dev --extra server
|
||||
|
||||
@@ -40,7 +40,8 @@ jobs:
|
||||
libappindicator3-dev \
|
||||
librsvg2-dev \
|
||||
patchelf \
|
||||
libxdo-dev
|
||||
libxdo-dev \
|
||||
libdbus-1-dev
|
||||
|
||||
- name: Setup Node.js
|
||||
uses: actions/setup-node@v6
|
||||
@@ -130,7 +131,8 @@ jobs:
|
||||
libappindicator3-dev \
|
||||
librsvg2-dev \
|
||||
patchelf \
|
||||
libxdo-dev
|
||||
libxdo-dev \
|
||||
libdbus-1-dev
|
||||
|
||||
- name: Install Rust stable
|
||||
uses: dtolnay/rust-toolchain@stable
|
||||
@@ -252,6 +254,10 @@ jobs:
|
||||
TAURI_SIGNING_PRIVATE_KEY: ${{ secrets.TAURI_SIGNING_PRIVATE_KEY }}
|
||||
TAURI_SIGNING_PRIVATE_KEY_PASSWORD: ${{ secrets.TAURI_SIGNING_PRIVATE_KEY_PASSWORD }}
|
||||
TAURI_CONFIG: '{"version":"${{ steps.release-info.outputs.tauri_version }}","bundle":{"externalBin":["binaries/ollama"]}}'
|
||||
# tauri-action runs beforeBuildCommand (npm run build:tauri -> vite
|
||||
# build), which requires this at build time (#587). Strict for
|
||||
# releases: a missing/empty secret fails the build by design.
|
||||
VITE_SUPABASE_ANON_KEY: ${{ secrets.VITE_SUPABASE_ANON_KEY }}
|
||||
with:
|
||||
projectPath: frontend
|
||||
tauriScript: npx tauri
|
||||
|
||||
@@ -35,3 +35,8 @@ jobs:
|
||||
- run: npm ci
|
||||
- run: npx tsc --noEmit
|
||||
- run: npm run build
|
||||
env:
|
||||
# Optional: when the secret is unset the build still succeeds and the
|
||||
# leaderboard is disabled (see src/lib/supabase.ts). No placeholder,
|
||||
# so a keyless CI build doesn't bake in a bogus anon key.
|
||||
VITE_SUPABASE_ANON_KEY: ${{ secrets.VITE_SUPABASE_ANON_KEY }}
|
||||
|
||||
@@ -55,6 +55,8 @@ jobs:
|
||||
cache-dependency-path: frontend/package-lock.json
|
||||
|
||||
- name: Build frontend and bundle into package
|
||||
env:
|
||||
VITE_SUPABASE_ANON_KEY: ${{ secrets.VITE_SUPABASE_ANON_KEY }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
cd frontend
|
||||
|
||||
@@ -1,5 +1,9 @@
|
||||
# Base images are pinned to an immutable digest (in addition to a human-readable
|
||||
# tag) so every build resolves the exact same layers — reproducible builds and
|
||||
# safe rollbacks (#563).
|
||||
|
||||
# Stage 1: Build frontend SPA
|
||||
FROM node:22-slim AS frontend
|
||||
FROM node:22.23.0-slim@sha256:d9f850096136edbc402debdd8729579a288aac64574ada0ff4db26b6ae58b0b2 AS frontend
|
||||
|
||||
WORKDIR /frontend
|
||||
COPY frontend/package.json frontend/package-lock.json* ./
|
||||
@@ -8,10 +12,22 @@ COPY frontend/ .
|
||||
RUN npm run build
|
||||
|
||||
# Stage 2: Build Python package
|
||||
FROM python:3.12-slim-bookworm AS builder
|
||||
FROM python:3.12.13-slim-bookworm@sha256:76d4b7b6305788c6b4c6a19d6a22a3921bf802e9af4d5e1e5bd771208dba74bf AS builder
|
||||
|
||||
WORKDIR /app
|
||||
COPY pyproject.toml README.md ./
|
||||
|
||||
# Install dependencies from the committed lockfile (#567). `uv export --frozen`
|
||||
# reads uv.lock as-is (no re-resolution) and emits a fully pinned, hash-verified
|
||||
# requirements set; `--no-deps` then installs exactly that set. This is a
|
||||
# separate layer from the source copy so dependency installs stay cached when
|
||||
# only application code changes.
|
||||
COPY pyproject.toml uv.lock README.md ./
|
||||
RUN pip install --no-cache-dir uv && \
|
||||
uv export --frozen --no-dev --extra server --no-emit-project > requirements.txt && \
|
||||
uv pip install --system --no-deps -r requirements.txt
|
||||
|
||||
# Copy the source and the non-src force-include paths (see pyproject
|
||||
# [tool.hatch.build.targets.wheel.force-include]) before building the project.
|
||||
COPY src/ src/
|
||||
COPY scripts/install scripts/install
|
||||
COPY deploy/windows deploy/windows
|
||||
@@ -19,16 +35,25 @@ COPY deploy/windows deploy/windows
|
||||
# Copy built frontend into the server static directory
|
||||
COPY --from=frontend /src/openjarvis/server/static src/openjarvis/server/static/
|
||||
|
||||
RUN pip install --no-cache-dir uv && \
|
||||
uv pip install --system ".[server]"
|
||||
# Install the project itself without re-resolving dependencies.
|
||||
RUN uv pip install --system --no-deps .
|
||||
|
||||
# Stage 3: Runtime
|
||||
FROM python:3.12-slim-bookworm
|
||||
FROM python:3.12.13-slim-bookworm@sha256:76d4b7b6305788c6b4c6a19d6a22a3921bf802e9af4d5e1e5bd771208dba74bf
|
||||
|
||||
COPY --from=builder /usr/local /usr/local
|
||||
COPY --from=builder /app /app
|
||||
WORKDIR /app
|
||||
|
||||
# Run as an unprivileged user — the server needs no root privileges, so dropping
|
||||
# them limits the blast radius of a compromise (#565). The app writes only to
|
||||
# $HOME (config/cache/state), which is owned by this user.
|
||||
RUN groupadd --system --gid 10001 openjarvis && \
|
||||
useradd --system --uid 10001 --gid openjarvis \
|
||||
--create-home --home-dir /home/openjarvis openjarvis
|
||||
ENV HOME=/home/openjarvis
|
||||
USER openjarvis
|
||||
|
||||
EXPOSE 8000
|
||||
|
||||
ENTRYPOINT ["jarvis"]
|
||||
|
||||
@@ -1,5 +1,9 @@
|
||||
# Base images are pinned to an immutable digest (in addition to a human-readable
|
||||
# tag) so every build resolves the exact same layers — reproducible builds and
|
||||
# safe rollbacks (#563).
|
||||
|
||||
# Stage 1: Build frontend SPA
|
||||
FROM node:22-slim AS frontend
|
||||
FROM node:22.23.0-slim@sha256:d9f850096136edbc402debdd8729579a288aac64574ada0ff4db26b6ae58b0b2 AS frontend
|
||||
|
||||
WORKDIR /frontend
|
||||
COPY frontend/package.json frontend/package-lock.json* ./
|
||||
@@ -8,25 +12,31 @@ COPY frontend/ .
|
||||
RUN npm run build
|
||||
|
||||
# Stage 2: Build Python package (NVIDIA CUDA 12.4)
|
||||
FROM nvidia/cuda:12.4.0-runtime-ubuntu22.04 AS builder
|
||||
FROM nvidia/cuda:12.4.0-runtime-ubuntu22.04@sha256:af8bd179ed3bf69d4b63b19a763662a6141f0f62ef099283f68d0b14b4bab0e3 AS builder
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y --no-install-recommends python3 python3-pip python3-venv && \
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
|
||||
WORKDIR /app
|
||||
COPY pyproject.toml README.md ./
|
||||
|
||||
# Install dependencies from the committed lockfile (#567). See deploy/docker/Dockerfile
|
||||
# for the rationale behind the frozen export + --no-deps install.
|
||||
COPY pyproject.toml uv.lock README.md ./
|
||||
RUN pip install --no-cache-dir uv && \
|
||||
uv export --frozen --no-dev --extra server --no-emit-project > requirements.txt && \
|
||||
uv pip install --system --no-deps -r requirements.txt
|
||||
|
||||
COPY src/ src/
|
||||
COPY scripts/install scripts/install
|
||||
COPY deploy/windows deploy/windows
|
||||
|
||||
COPY --from=frontend /src/openjarvis/server/static src/openjarvis/server/static/
|
||||
|
||||
RUN pip install --no-cache-dir uv && \
|
||||
uv pip install --system ".[server]"
|
||||
RUN uv pip install --system --no-deps .
|
||||
|
||||
# Stage 3: Runtime
|
||||
FROM nvidia/cuda:12.4.0-runtime-ubuntu22.04
|
||||
FROM nvidia/cuda:12.4.0-runtime-ubuntu22.04@sha256:af8bd179ed3bf69d4b63b19a763662a6141f0f62ef099283f68d0b14b4bab0e3
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y --no-install-recommends python3 python3-pip && \
|
||||
@@ -36,6 +46,14 @@ COPY --from=builder /usr/local /usr/local
|
||||
COPY --from=builder /app /app
|
||||
WORKDIR /app
|
||||
|
||||
# Run as an unprivileged user (#565). NVIDIA device nodes (/dev/nvidia*) are
|
||||
# world-accessible, so GPU workloads do not require root.
|
||||
RUN groupadd --system --gid 10001 openjarvis && \
|
||||
useradd --system --uid 10001 --gid openjarvis \
|
||||
--create-home --home-dir /home/openjarvis openjarvis
|
||||
ENV HOME=/home/openjarvis
|
||||
USER openjarvis
|
||||
|
||||
EXPOSE 8000
|
||||
|
||||
ENTRYPOINT ["jarvis"]
|
||||
|
||||
@@ -1,5 +1,9 @@
|
||||
# Base images are pinned to an immutable digest (in addition to a human-readable
|
||||
# tag) so every build resolves the exact same layers — reproducible builds and
|
||||
# safe rollbacks (#563).
|
||||
|
||||
# Stage 1: Build frontend SPA
|
||||
FROM node:22-slim AS frontend
|
||||
FROM node:22.23.0-slim@sha256:d9f850096136edbc402debdd8729579a288aac64574ada0ff4db26b6ae58b0b2 AS frontend
|
||||
|
||||
WORKDIR /frontend
|
||||
COPY frontend/package.json frontend/package-lock.json* ./
|
||||
@@ -8,25 +12,31 @@ COPY frontend/ .
|
||||
RUN npm run build
|
||||
|
||||
# Stage 2: Build Python package (AMD ROCm 7.2)
|
||||
FROM rocm/dev-ubuntu-22.04:7.2 AS builder
|
||||
FROM rocm/dev-ubuntu-22.04:7.2@sha256:05af5f04a06b04676d4c7438997d0deadaeb7478961ad621376e199bf3aeb644 AS builder
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y --no-install-recommends python3 python3-pip python3-venv && \
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
|
||||
WORKDIR /app
|
||||
COPY pyproject.toml README.md ./
|
||||
|
||||
# Install dependencies from the committed lockfile (#567). See deploy/docker/Dockerfile
|
||||
# for the rationale behind the frozen export + --no-deps install.
|
||||
COPY pyproject.toml uv.lock README.md ./
|
||||
RUN pip install --no-cache-dir uv && \
|
||||
uv export --frozen --no-dev --extra server --no-emit-project > requirements.txt && \
|
||||
uv pip install --system --no-deps -r requirements.txt
|
||||
|
||||
COPY src/ src/
|
||||
COPY scripts/install scripts/install
|
||||
COPY deploy/windows deploy/windows
|
||||
|
||||
COPY --from=frontend /src/openjarvis/server/static src/openjarvis/server/static/
|
||||
|
||||
RUN pip install --no-cache-dir uv && \
|
||||
uv pip install --system ".[server]"
|
||||
RUN uv pip install --system --no-deps .
|
||||
|
||||
# Stage 3: Runtime
|
||||
FROM rocm/dev-ubuntu-22.04:7.2
|
||||
FROM rocm/dev-ubuntu-22.04:7.2@sha256:05af5f04a06b04676d4c7438997d0deadaeb7478961ad621376e199bf3aeb644
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y --no-install-recommends python3 python3-pip && \
|
||||
@@ -36,6 +46,18 @@ COPY --from=builder /usr/local /usr/local
|
||||
COPY --from=builder /app /app
|
||||
WORKDIR /app
|
||||
|
||||
# Run as an unprivileged user (#565). ROCm GPU access is gated by the `video` and
|
||||
# `render` groups (see group_add in docker-compose.gpu.rocm.yml), so the user is
|
||||
# added to both; root is not required.
|
||||
RUN groupadd --system --gid 10001 openjarvis && \
|
||||
useradd --system --uid 10001 --gid openjarvis \
|
||||
--create-home --home-dir /home/openjarvis openjarvis && \
|
||||
(getent group video >/dev/null || groupadd --system video) && \
|
||||
(getent group render >/dev/null || groupadd --system render) && \
|
||||
usermod -aG video,render openjarvis
|
||||
ENV HOME=/home/openjarvis
|
||||
USER openjarvis
|
||||
|
||||
EXPOSE 8000
|
||||
|
||||
ENTRYPOINT ["jarvis"]
|
||||
|
||||
@@ -1,15 +1,42 @@
|
||||
FROM python:3.12-slim
|
||||
# Base images are pinned to an immutable digest (in addition to a human-readable
|
||||
# tag) so every build resolves the exact same layers (#563).
|
||||
|
||||
# Install Node.js 22
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
curl ca-certificates && \
|
||||
curl -fsSL https://deb.nodesource.com/setup_22.x | bash - && \
|
||||
apt-get install -y nodejs && \
|
||||
# Node.js is sourced from the official, digest-pinned image rather than piping a
|
||||
# remote setup script into bash (`curl ... | bash -`), which performed no
|
||||
# checksum or signature verification of the downloaded installer (#566). The
|
||||
# image digest is the integrity check, and the copy is architecture-agnostic.
|
||||
FROM node:22.23.0-slim@sha256:d9f850096136edbc402debdd8729579a288aac64574ada0ff4db26b6ae58b0b2 AS node
|
||||
|
||||
FROM python:3.12.13-slim-bookworm@sha256:76d4b7b6305788c6b4c6a19d6a22a3921bf802e9af4d5e1e5bd771208dba74bf
|
||||
|
||||
# libstdc++6 + ca-certificates are the only runtime requirements of the Node
|
||||
# binary copied below (the python slim image already provides libc/libgcc).
|
||||
RUN apt-get update && \
|
||||
apt-get install -y --no-install-recommends ca-certificates libstdc++6 && \
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# Transplant the Node.js runtime from the official image. Both images are Debian
|
||||
# bookworm, so the glibc/libstdc++ ABI matches.
|
||||
COPY --from=node /usr/local/bin/node /usr/local/bin/node
|
||||
COPY --from=node /usr/local/lib/node_modules /usr/local/lib/node_modules
|
||||
RUN ln -sf /usr/local/lib/node_modules/npm/bin/npm-cli.js /usr/local/bin/npm && \
|
||||
ln -sf /usr/local/lib/node_modules/npm/bin/npx-cli.js /usr/local/bin/npx
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
# Install dependencies from the committed lockfile (#567): `uv export --frozen`
|
||||
# reads uv.lock as-is and emits a pinned, hash-verified set installed with
|
||||
# --no-deps (no re-resolution). Copied first so this layer caches independently
|
||||
# of application source.
|
||||
COPY pyproject.toml uv.lock README.md ./
|
||||
RUN pip install --no-cache-dir uv && \
|
||||
uv export --frozen --no-dev --extra server --no-emit-project > requirements.txt && \
|
||||
uv pip install --system --no-deps -r requirements.txt
|
||||
|
||||
COPY . .
|
||||
RUN pip install --no-cache-dir ".[server]"
|
||||
|
||||
# Install the project itself without re-resolving dependencies.
|
||||
RUN uv pip install --system --no-deps .
|
||||
|
||||
LABEL openjarvis-sandbox=true
|
||||
|
||||
|
||||
@@ -18,7 +18,9 @@ services:
|
||||
capabilities: [gpu]
|
||||
|
||||
ollama:
|
||||
image: ollama/ollama:latest
|
||||
# Pinned to a fixed version + digest for reproducible deployments (#563);
|
||||
# must match the tag in docker-compose.yml.
|
||||
image: ollama/ollama:0.30.10@sha256:bfc9c6d53cc6989aa5131a6fde6b162b2802d4d337657f3253b5f69579bddeee
|
||||
environment:
|
||||
- NVIDIA_VISIBLE_DEVICES=all
|
||||
- NVIDIA_DRIVER_CAPABILITIES=compute,utility
|
||||
|
||||
@@ -18,7 +18,9 @@ services:
|
||||
restart: unless-stopped
|
||||
|
||||
ollama:
|
||||
image: ollama/ollama:latest
|
||||
# Pinned to a fixed version + digest for reproducible deployments and
|
||||
# predictable rollbacks (#563). Bump deliberately, not implicitly via :latest.
|
||||
image: ollama/ollama:0.30.10@sha256:bfc9c6d53cc6989aa5131a6fde6b162b2802d4d337657f3253b5f69579bddeee
|
||||
ports:
|
||||
- "11434:11434"
|
||||
volumes:
|
||||
|
||||
@@ -14,7 +14,27 @@ Environment=HOME=/opt/openjarvis
|
||||
# OPENJARVIS_API_KEY=<key> (generate one: `jarvis auth generate-key`)
|
||||
# It is not prefixed with "-", so the unit fails to start if the file is
|
||||
# missing — preventing an accidentally unauthenticated public server.
|
||||
# Keep secrets here (mode 0600, owned by root) rather than inline Environment=
|
||||
# lines, which leak into `systemctl show` and the journal.
|
||||
EnvironmentFile=/etc/openjarvis/env
|
||||
|
||||
# --- Sandboxing / hardening (#564) ---
|
||||
# Conservative set: tightens the unit without blocking the server's normal I/O
|
||||
# or local GPU inference. ProtectSystem=strict makes the whole filesystem
|
||||
# read-only except ReadWritePaths, so $HOME (config/cache/state under
|
||||
# /opt/openjarvis) stays writable.
|
||||
NoNewPrivileges=true
|
||||
ProtectSystem=strict
|
||||
ReadWritePaths=/opt/openjarvis
|
||||
ProtectHome=true
|
||||
PrivateTmp=true
|
||||
ProtectControlGroups=true
|
||||
ProtectKernelLogs=true
|
||||
ProtectKernelModules=true
|
||||
ProtectKernelTunables=true
|
||||
RestrictRealtime=true
|
||||
RestrictSUIDSGID=true
|
||||
LockPersonality=true
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
|
||||
@@ -1,9 +1,9 @@
|
||||
(function () {
|
||||
"use strict";
|
||||
|
||||
var SUPABASE_URL = "https://mtbtgpwzrbostweaanpr.supabase.co";
|
||||
var SUPABASE_ANON_KEY =
|
||||
"eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJzdXBhYmFzZSIsInJlZiI6Im10YnRncHd6cmJvc3R3ZWFhbnByIiwicm9sZSI6ImFub24iLCJpYXQiOjE3NzMxODk0OTQsImV4cCI6MjA4ODc2NTQ5NH0._xMlqCfljtXpwPj54H-ghxfLFO-jiq4W2WhpU8vVL1c";
|
||||
var SUPABASE_URL =
|
||||
window.OPENJARVIS_SUPABASE_URL || "https://mtbtgpwzrbostweaanpr.supabase.co";
|
||||
var SUPABASE_ANON_KEY = window.OPENJARVIS_SUPABASE_ANON_KEY || "";
|
||||
|
||||
var PAGE_SIZE = 50;
|
||||
var allRows = [];
|
||||
|
||||
Generated
+1108
-1007
File diff suppressed because it is too large
Load Diff
@@ -24,9 +24,22 @@ serde_json = "1"
|
||||
reqwest = { version = "0.12", features = ["json", "multipart"] }
|
||||
tokio = { version = "1", features = ["full"] }
|
||||
|
||||
# Cloud API keys are stored in the OS credential store via `keyring`. keyring v3
|
||||
# enables NO backend by default — without an explicit per-platform feature it
|
||||
# silently falls back to a non-persistent in-memory mock, so keys would not
|
||||
# survive an app restart. Each desktop target opts into its native store.
|
||||
[target.'cfg(target_os = "macos")'.dependencies]
|
||||
objc = "0.2"
|
||||
dispatch = "0.2"
|
||||
keyring = { version = "3", features = ["apple-native"] }
|
||||
|
||||
[target.'cfg(target_os = "windows")'.dependencies]
|
||||
keyring = { version = "3", features = ["windows-native"] }
|
||||
|
||||
[target.'cfg(target_os = "linux")'.dependencies]
|
||||
# Blocking Secret Service backend (no internal async runtime, so it is safe to
|
||||
# call from the tokio-driven Tauri commands). Needs libdbus-1-dev at build time.
|
||||
keyring = { version = "3", features = ["sync-secret-service", "crypto-rust"] }
|
||||
|
||||
[features]
|
||||
default = ["custom-protocol"]
|
||||
|
||||
+162
-44
@@ -1204,7 +1204,7 @@ async fn boot_backend(backend: SharedBackend, status: SharedStatus) {
|
||||
// additions aren't accidentally stripped.
|
||||
prepare_subprocess_for_appimage(&mut cmd);
|
||||
|
||||
// Inject cloud API keys from ~/.openjarvis/cloud-keys.env
|
||||
// Inject cloud API keys from secure desktop storage.
|
||||
for (key, value) in read_cloud_keys() {
|
||||
cmd.env(&key, &value);
|
||||
}
|
||||
@@ -1720,17 +1720,111 @@ async fn submit_savings(
|
||||
// Cloud API key management
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
/// Path to the cloud keys file (~/.openjarvis/cloud-keys.env).
|
||||
fn cloud_keys_path() -> std::path::PathBuf {
|
||||
const SECURE_KEY_SERVICE: &str = "OpenJarvis Cloud Keys";
|
||||
const MANAGED_CLOUD_KEY_NAMES: &[&str] = &[
|
||||
"OPENAI_API_KEY",
|
||||
"ANTHROPIC_API_KEY",
|
||||
"GEMINI_API_KEY",
|
||||
"GOOGLE_API_KEY",
|
||||
"OPENROUTER_API_KEY",
|
||||
"MINIMAX_API_KEY",
|
||||
"TAVILY_API_KEY",
|
||||
];
|
||||
|
||||
/// Legacy path used by older desktop builds. New saves never write here.
|
||||
fn legacy_cloud_keys_path() -> std::path::PathBuf {
|
||||
let home = home_dir();
|
||||
std::path::PathBuf::from(home)
|
||||
.join(".openjarvis")
|
||||
.join("cloud-keys.env")
|
||||
}
|
||||
|
||||
/// Read cloud keys from disk and return as key=value pairs.
|
||||
fn read_cloud_keys() -> Vec<(String, String)> {
|
||||
let path = cloud_keys_path();
|
||||
fn validate_cloud_key_name(key_name: &str) -> Result<(), String> {
|
||||
let valid = !key_name.is_empty()
|
||||
&& key_name.len() <= 128
|
||||
&& key_name.ends_with("_API_KEY")
|
||||
&& key_name
|
||||
.chars()
|
||||
.all(|ch| ch.is_ascii_uppercase() || ch.is_ascii_digit() || ch == '_');
|
||||
if valid {
|
||||
Ok(())
|
||||
} else {
|
||||
Err(format!("Invalid API key name: {}", key_name))
|
||||
}
|
||||
}
|
||||
|
||||
fn engine_api_key_name(engine: &str) -> String {
|
||||
let normalized: String = engine
|
||||
.chars()
|
||||
.map(|ch| {
|
||||
if ch.is_ascii_alphanumeric() {
|
||||
ch.to_ascii_uppercase()
|
||||
} else {
|
||||
'_'
|
||||
}
|
||||
})
|
||||
.collect();
|
||||
let trimmed = normalized.trim_matches('_');
|
||||
let engine_name = if trimmed.is_empty() {
|
||||
CUSTOM_FALLBACK_ENGINE.to_ascii_uppercase()
|
||||
} else {
|
||||
trimmed.to_string()
|
||||
};
|
||||
format!("{}_API_KEY", engine_name)
|
||||
}
|
||||
|
||||
fn managed_cloud_key_names() -> Vec<String> {
|
||||
let mut names: Vec<String> = MANAGED_CLOUD_KEY_NAMES
|
||||
.iter()
|
||||
.map(|name| (*name).to_string())
|
||||
.collect();
|
||||
|
||||
let cfg = read_inference_config();
|
||||
if matches!(&cfg.kind, SourceKind::Custom) {
|
||||
let engine = cfg.engine.unwrap_or_else(|| CUSTOM_FALLBACK_ENGINE.to_string());
|
||||
let key_name = engine_api_key_name(&engine);
|
||||
if validate_cloud_key_name(&key_name).is_ok() {
|
||||
names.push(key_name);
|
||||
}
|
||||
}
|
||||
|
||||
names.sort();
|
||||
names.dedup();
|
||||
names
|
||||
}
|
||||
|
||||
fn secure_store_get(key_name: &str) -> Result<Option<String>, String> {
|
||||
validate_cloud_key_name(key_name)?;
|
||||
let entry = keyring::Entry::new(SECURE_KEY_SERVICE, key_name)
|
||||
.map_err(|err| format!("Failed to open secure key storage for {}: {}", key_name, err))?;
|
||||
match entry.get_password() {
|
||||
Ok(value) => Ok(Some(value)),
|
||||
Err(keyring::Error::NoEntry) => Ok(None),
|
||||
Err(err) => Err(format!("Failed to read {} from secure key storage: {}", key_name, err)),
|
||||
}
|
||||
}
|
||||
|
||||
fn secure_store_set(key_name: &str, key_value: &str) -> Result<(), String> {
|
||||
validate_cloud_key_name(key_name)?;
|
||||
let entry = keyring::Entry::new(SECURE_KEY_SERVICE, key_name)
|
||||
.map_err(|err| format!("Failed to open secure key storage for {}: {}", key_name, err))?;
|
||||
if key_value.is_empty() {
|
||||
return match entry.delete_credential() {
|
||||
Ok(()) => Ok(()),
|
||||
Err(keyring::Error::NoEntry) => Ok(()),
|
||||
Err(err) => Err(format!(
|
||||
"Failed to remove {} from secure key storage: {}",
|
||||
key_name, err
|
||||
)),
|
||||
};
|
||||
}
|
||||
entry
|
||||
.set_password(key_value)
|
||||
.map_err(|err| format!("Failed to save {} in secure key storage: {}", key_name, err))
|
||||
}
|
||||
|
||||
fn read_legacy_cloud_keys() -> Vec<(String, String)> {
|
||||
let path = legacy_cloud_keys_path();
|
||||
let mut keys = Vec::new();
|
||||
if let Ok(contents) = std::fs::read_to_string(&path) {
|
||||
for line in contents.lines() {
|
||||
@@ -1746,47 +1840,68 @@ fn read_cloud_keys() -> Vec<(String, String)> {
|
||||
keys
|
||||
}
|
||||
|
||||
/// Save a single cloud API key to the keys file.
|
||||
#[tauri::command]
|
||||
async fn save_cloud_key(key_name: String, key_value: String) -> Result<(), String> {
|
||||
let path = cloud_keys_path();
|
||||
// Ensure directory exists
|
||||
if let Some(parent) = path.parent() {
|
||||
let _ = std::fs::create_dir_all(parent);
|
||||
fn migrate_legacy_cloud_keys() {
|
||||
let path = legacy_cloud_keys_path();
|
||||
if !path.exists() {
|
||||
return;
|
||||
}
|
||||
|
||||
// Read existing keys, update/add the one being saved
|
||||
let mut keys: Vec<(String, String)> = read_cloud_keys()
|
||||
let legacy_keys = read_legacy_cloud_keys();
|
||||
if legacy_keys.is_empty() {
|
||||
let _ = std::fs::remove_file(&path);
|
||||
return;
|
||||
}
|
||||
|
||||
let mut migrated_all = true;
|
||||
for (key, value) in legacy_keys {
|
||||
if value.is_empty() {
|
||||
continue;
|
||||
}
|
||||
if secure_store_set(&key, &value).is_err() {
|
||||
migrated_all = false;
|
||||
}
|
||||
}
|
||||
|
||||
if migrated_all {
|
||||
let _ = std::fs::remove_file(path);
|
||||
}
|
||||
}
|
||||
|
||||
/// Read cloud keys from secure desktop storage and return key=value pairs.
|
||||
fn read_cloud_keys() -> Vec<(String, String)> {
|
||||
migrate_legacy_cloud_keys();
|
||||
managed_cloud_key_names()
|
||||
.into_iter()
|
||||
.filter(|(k, _)| k != &key_name)
|
||||
.collect();
|
||||
if !key_value.is_empty() {
|
||||
keys.push((key_name, key_value));
|
||||
}
|
||||
.filter_map(|key| match secure_store_get(&key) {
|
||||
Ok(Some(value)) if !value.is_empty() => Some((key, value)),
|
||||
_ => None,
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
// Write back
|
||||
let content: String = keys
|
||||
.iter()
|
||||
.map(|(k, v)| format!("{}={}", k, v))
|
||||
.collect::<Vec<_>>()
|
||||
.join("\n");
|
||||
std::fs::write(&path, content + "\n").map_err(|e| format!("Failed to save key: {}", e))?;
|
||||
|
||||
// Set permissions to owner-only (chmod 600)
|
||||
#[cfg(unix)]
|
||||
{
|
||||
use std::os::unix::fs::PermissionsExt;
|
||||
let _ = std::fs::set_permissions(&path, std::fs::Permissions::from_mode(0o600));
|
||||
}
|
||||
|
||||
// Tell the running server to hot-reload its cloud engine so the user
|
||||
// doesn't need to restart the app after entering an API key.
|
||||
async fn reload_cloud_keys(keys: Vec<(String, String)>) {
|
||||
let reload_url = format!("http://127.0.0.1:{}/v1/cloud/reload", JARVIS_PORT);
|
||||
let key_map: serde_json::Map<String, serde_json::Value> = keys
|
||||
.into_iter()
|
||||
.map(|(key, value)| (key, serde_json::Value::String(value)))
|
||||
.collect();
|
||||
let _ = reqwest::Client::new()
|
||||
.post(&reload_url)
|
||||
.json(&serde_json::json!({ "keys": key_map }))
|
||||
.timeout(std::time::Duration::from_secs(10))
|
||||
.send()
|
||||
.await;
|
||||
}
|
||||
|
||||
/// Save a single cloud API key to secure desktop storage.
|
||||
#[tauri::command]
|
||||
async fn save_cloud_key(key_name: String, key_value: String) -> Result<(), String> {
|
||||
let key_value = key_value.trim().to_string();
|
||||
secure_store_set(&key_name, &key_value)?;
|
||||
|
||||
// Tell the running server to hot-reload its cloud engine so the user
|
||||
// doesn't need to restart the app after entering an API key.
|
||||
reload_cloud_keys(vec![(key_name, key_value)]).await;
|
||||
|
||||
Ok(())
|
||||
}
|
||||
@@ -1794,10 +1909,13 @@ async fn save_cloud_key(key_name: String, key_value: String) -> Result<(), Strin
|
||||
/// Get which cloud providers have keys configured (without exposing values).
|
||||
#[tauri::command]
|
||||
async fn get_cloud_key_status() -> Result<serde_json::Value, String> {
|
||||
let keys = read_cloud_keys();
|
||||
let status: Vec<serde_json::Value> = keys
|
||||
.iter()
|
||||
.map(|(k, v)| serde_json::json!({ "key": k, "set": !v.is_empty() }))
|
||||
migrate_legacy_cloud_keys();
|
||||
let status: Vec<serde_json::Value> = managed_cloud_key_names()
|
||||
.into_iter()
|
||||
.map(|key| {
|
||||
let set = matches!(secure_store_get(&key), Ok(Some(value)) if !value.is_empty());
|
||||
serde_json::json!({ "key": key, "set": set })
|
||||
})
|
||||
.collect();
|
||||
Ok(serde_json::json!(status))
|
||||
}
|
||||
@@ -1809,8 +1927,8 @@ async fn get_inference_source() -> Result<InferenceConfig, String> {
|
||||
}
|
||||
|
||||
/// Persist the chosen inference source. `host` is normalized to a bare base
|
||||
/// URL. For custom endpoints, an optional API key is stored in cloud-keys.env
|
||||
/// under `<ENGINE>_API_KEY`. Applies on next app launch.
|
||||
/// URL. For custom endpoints, an optional API key is stored in secure desktop
|
||||
/// storage under `<ENGINE>_API_KEY`. Applies on next app launch.
|
||||
#[tauri::command]
|
||||
async fn set_inference_source(
|
||||
kind: String,
|
||||
@@ -1842,7 +1960,7 @@ async fn set_inference_source(
|
||||
.engine
|
||||
.clone()
|
||||
.unwrap_or_else(|| CUSTOM_FALLBACK_ENGINE.to_string());
|
||||
let key_name = format!("{}_API_KEY", engine.to_ascii_uppercase());
|
||||
let key_name = engine_api_key_name(&engine);
|
||||
// Save the key before persisting the config: if the key can't be
|
||||
// written, surface it and DON'T record a custom source whose
|
||||
// credential is missing (which would fail confusingly at runtime).
|
||||
|
||||
@@ -1,7 +1,15 @@
|
||||
import { useState, useRef, useEffect } from 'react';
|
||||
import { useState, useRef, useEffect, useCallback } from 'react';
|
||||
import { Search, Cpu, X, Download, Loader2, Trash2, Check, Cloud, Key, Eye, EyeOff } from 'lucide-react';
|
||||
import { useAppStore } from '../lib/store';
|
||||
import { pullModel, deleteModel, fetchModels, preloadModel, isTauri } from '../lib/api';
|
||||
import {
|
||||
pullModel,
|
||||
deleteModel,
|
||||
fetchModels,
|
||||
preloadModel,
|
||||
isTauri,
|
||||
getCloudKeyStatus,
|
||||
saveCloudKey,
|
||||
} from '../lib/api';
|
||||
|
||||
/** Popular models that users can download from the catalogue. */
|
||||
const CATALOGUE_MODELS = [
|
||||
@@ -23,7 +31,6 @@ const CATALOGUE_MODELS = [
|
||||
interface CloudProvider {
|
||||
name: string;
|
||||
envKey: string;
|
||||
storageKey: string;
|
||||
models: Array<{ id: string; desc: string }>;
|
||||
}
|
||||
|
||||
@@ -31,7 +38,6 @@ const CLOUD_PROVIDERS: CloudProvider[] = [
|
||||
{
|
||||
name: 'OpenAI',
|
||||
envKey: 'OPENAI_API_KEY',
|
||||
storageKey: 'openjarvis-openai-key',
|
||||
models: [
|
||||
{ id: 'gpt-4o', desc: 'GPT-4o — fast, multimodal' },
|
||||
{ id: 'gpt-4o-mini', desc: 'GPT-4o Mini — cheap, fast' },
|
||||
@@ -41,7 +47,6 @@ const CLOUD_PROVIDERS: CloudProvider[] = [
|
||||
{
|
||||
name: 'Anthropic',
|
||||
envKey: 'ANTHROPIC_API_KEY',
|
||||
storageKey: 'openjarvis-anthropic-key',
|
||||
models: [
|
||||
{ id: 'claude-sonnet-4-6', desc: 'Claude Sonnet 4.6 — balanced' },
|
||||
{ id: 'claude-opus-4-6', desc: 'Claude Opus 4.6 — most capable' },
|
||||
@@ -51,7 +56,6 @@ const CLOUD_PROVIDERS: CloudProvider[] = [
|
||||
{
|
||||
name: 'Google',
|
||||
envKey: 'GEMINI_API_KEY',
|
||||
storageKey: 'openjarvis-gemini-key',
|
||||
models: [
|
||||
{ id: 'gemini-2.5-pro', desc: 'Gemini 2.5 Pro — flagship' },
|
||||
{ id: 'gemini-2.5-flash', desc: 'Gemini 2.5 Flash — fast' },
|
||||
@@ -61,7 +65,6 @@ const CLOUD_PROVIDERS: CloudProvider[] = [
|
||||
{
|
||||
name: 'OpenRouter',
|
||||
envKey: 'OPENROUTER_API_KEY',
|
||||
storageKey: 'openjarvis-openrouter-key',
|
||||
models: [
|
||||
{ id: 'openrouter/auto', desc: 'Auto — best model for the task' },
|
||||
{ id: 'openrouter/anthropic/claude-sonnet-4', desc: 'Claude Sonnet 4 via OpenRouter' },
|
||||
@@ -70,16 +73,6 @@ const CLOUD_PROVIDERS: CloudProvider[] = [
|
||||
},
|
||||
];
|
||||
|
||||
function getStoredKey(storageKey: string): string {
|
||||
try { return localStorage.getItem(storageKey) || ''; } catch { return ''; }
|
||||
}
|
||||
function setStoredKey(storageKey: string, value: string): void {
|
||||
try {
|
||||
if (value) localStorage.setItem(storageKey, value);
|
||||
else localStorage.removeItem(storageKey);
|
||||
} catch {}
|
||||
}
|
||||
|
||||
type Tab = 'installed' | 'catalogue' | 'cloud';
|
||||
|
||||
export function CommandPalette() {
|
||||
@@ -92,11 +85,10 @@ export function CommandPalette() {
|
||||
const [deleting, setDeleting] = useState<string | null>(null);
|
||||
const [customModel, setCustomModel] = useState('');
|
||||
const [showKeys, setShowKeys] = useState<Record<string, boolean>>({});
|
||||
const [apiKeys, setApiKeys] = useState<Record<string, string>>(() => {
|
||||
const keys: Record<string, string> = {};
|
||||
for (const p of CLOUD_PROVIDERS) keys[p.storageKey] = getStoredKey(p.storageKey);
|
||||
return keys;
|
||||
});
|
||||
const [apiKeys, setApiKeys] = useState<Record<string, string>>({});
|
||||
const [cloudKeyStatus, setCloudKeyStatus] = useState<Record<string, boolean>>({});
|
||||
const [cloudKeyError, setCloudKeyError] = useState<string | null>(null);
|
||||
const [savingKey, setSavingKey] = useState<string | null>(null);
|
||||
const inputRef = useRef<HTMLInputElement>(null);
|
||||
|
||||
const models = useAppStore((s) => s.models);
|
||||
@@ -106,6 +98,20 @@ export function CommandPalette() {
|
||||
const setCommandPaletteOpen = useAppStore((s) => s.setCommandPaletteOpen);
|
||||
|
||||
const installedIds = new Set(models.map((m) => m.id));
|
||||
const desktopKeyStorage = isTauri();
|
||||
|
||||
const refreshCloudKeyStatus = useCallback(async () => {
|
||||
if (!desktopKeyStorage) {
|
||||
setCloudKeyStatus({});
|
||||
return;
|
||||
}
|
||||
try {
|
||||
setCloudKeyStatus(await getCloudKeyStatus());
|
||||
setCloudKeyError(null);
|
||||
} catch (e: any) {
|
||||
setCloudKeyError(e?.message || 'Failed to read cloud key status');
|
||||
}
|
||||
}, [desktopKeyStorage]);
|
||||
|
||||
const filtered = tab === 'installed'
|
||||
? (query
|
||||
@@ -122,6 +128,10 @@ export function CommandPalette() {
|
||||
inputRef.current?.focus();
|
||||
}, []);
|
||||
|
||||
useEffect(() => {
|
||||
void refreshCloudKeyStatus();
|
||||
}, [refreshCloudKeyStatus]);
|
||||
|
||||
useEffect(() => {
|
||||
setSelectedIdx(0);
|
||||
}, [query, tab]);
|
||||
@@ -210,24 +220,29 @@ export function CommandPalette() {
|
||||
};
|
||||
|
||||
const handleSaveKey = async (provider: CloudProvider, value: string) => {
|
||||
setStoredKey(provider.storageKey, value);
|
||||
setApiKeys((prev) => ({ ...prev, [provider.storageKey]: value }));
|
||||
const keyValue = value.trim();
|
||||
setSavingKey(provider.envKey);
|
||||
setCloudKeyError(null);
|
||||
|
||||
// Also save to Tauri backend so the server process picks up the key
|
||||
if (isTauri()) {
|
||||
try {
|
||||
const { invoke } = await import('@tauri-apps/api/core');
|
||||
await invoke('save_cloud_key', { keyName: provider.envKey, keyValue: value });
|
||||
} catch {}
|
||||
try {
|
||||
await saveCloudKey(provider.envKey, keyValue);
|
||||
setApiKeys((prev) => ({ ...prev, [provider.envKey]: '' }));
|
||||
await refreshCloudKeyStatus();
|
||||
useAppStore.getState().addLogEntry({
|
||||
timestamp: Date.now(), level: 'info', category: 'model',
|
||||
message: `${provider.name} API key ${keyValue ? 'saved' : 'removed'}. Refreshing model list...`,
|
||||
});
|
||||
await refreshModels();
|
||||
} catch (e: any) {
|
||||
setCloudKeyError(e?.message || `Failed to save ${provider.name} API key`);
|
||||
} finally {
|
||||
setSavingKey(null);
|
||||
}
|
||||
};
|
||||
|
||||
useAppStore.getState().addLogEntry({
|
||||
timestamp: Date.now(), level: 'info', category: 'model',
|
||||
message: `${provider.name} API key ${value ? 'saved' : 'removed'}. Refreshing model list…`,
|
||||
});
|
||||
|
||||
// Refresh the model list so cloud models appear immediately.
|
||||
await refreshModels();
|
||||
const handleKeyBlur = (provider: CloudProvider) => {
|
||||
const draft = apiKeys[provider.envKey] || '';
|
||||
if (draft.trim()) void handleSaveKey(provider, draft);
|
||||
};
|
||||
|
||||
const handleKeyDown = (e: React.KeyboardEvent) => {
|
||||
@@ -323,6 +338,11 @@ export function CommandPalette() {
|
||||
<Check size={12} /> Downloaded {pullSuccess} successfully
|
||||
</div>
|
||||
)}
|
||||
{tab === 'cloud' && cloudKeyError && (
|
||||
<div className="px-4 py-2 text-xs" style={{ color: 'var(--color-error)', background: 'rgba(220,38,38,0.05)' }}>
|
||||
{cloudKeyError}
|
||||
</div>
|
||||
)}
|
||||
|
||||
{/* Results */}
|
||||
<div className="max-h-[400px] overflow-y-auto py-2">
|
||||
@@ -431,13 +451,17 @@ export function CommandPalette() {
|
||||
/* ── Cloud Models tab ── */
|
||||
<div className="px-4 py-2">
|
||||
<div className="text-[11px] mb-3" style={{ color: 'var(--color-text-tertiary)' }}>
|
||||
Add your API keys to use cloud models. Keys are stored locally on your device only.
|
||||
{desktopKeyStorage
|
||||
? 'Add your API keys to use cloud models. Keys are stored in secure desktop storage.'
|
||||
: 'Configure cloud provider keys in the server environment to use cloud models.'}
|
||||
</div>
|
||||
|
||||
{CLOUD_PROVIDERS.map((provider) => {
|
||||
const key = apiKeys[provider.storageKey] || '';
|
||||
const hasKey = !!key;
|
||||
const isVisible = showKeys[provider.storageKey];
|
||||
const key = apiKeys[provider.envKey] || '';
|
||||
const hasSavedKey = !!cloudKeyStatus[provider.envKey];
|
||||
const hasKey = hasSavedKey || !!key.trim();
|
||||
const isVisible = showKeys[provider.envKey];
|
||||
const isSaving = savingKey === provider.envKey;
|
||||
|
||||
return (
|
||||
<div key={provider.name} className="mb-4">
|
||||
@@ -458,26 +482,28 @@ export function CommandPalette() {
|
||||
<input
|
||||
type={isVisible ? 'text' : 'password'}
|
||||
value={key}
|
||||
onChange={(e) => setApiKeys((prev) => ({ ...prev, [provider.storageKey]: e.target.value }))}
|
||||
onBlur={() => handleSaveKey(provider, apiKeys[provider.storageKey] || '')}
|
||||
placeholder={`${provider.envKey}`}
|
||||
onChange={(e) => setApiKeys((prev) => ({ ...prev, [provider.envKey]: e.target.value }))}
|
||||
onBlur={() => handleKeyBlur(provider)}
|
||||
placeholder={hasSavedKey ? 'Saved in secure storage' : provider.envKey}
|
||||
disabled={!desktopKeyStorage || isSaving}
|
||||
className="flex-1 text-xs px-2 py-1.5 bg-transparent outline-none font-mono"
|
||||
style={{ color: 'var(--color-text)' }}
|
||||
/>
|
||||
<button
|
||||
onClick={() => setShowKeys((prev) => ({ ...prev, [provider.storageKey]: !prev[provider.storageKey] }))}
|
||||
onClick={() => setShowKeys((prev) => ({ ...prev, [provider.envKey]: !prev[provider.envKey] }))}
|
||||
className="px-2 cursor-pointer" style={{ color: 'var(--color-text-tertiary)' }}
|
||||
>
|
||||
{isVisible ? <EyeOff size={12} /> : <Eye size={12} />}
|
||||
</button>
|
||||
</div>
|
||||
{hasKey && (
|
||||
{hasSavedKey && (
|
||||
<button
|
||||
onClick={() => handleSaveKey(provider, '')}
|
||||
disabled={isSaving}
|
||||
className="px-2 py-1 rounded-lg text-[10px] cursor-pointer"
|
||||
style={{ color: 'var(--color-error)', border: '1px solid var(--color-error)' }}
|
||||
style={{ color: 'var(--color-error)', border: '1px solid var(--color-error)', opacity: isSaving ? 0.5 : 1 }}
|
||||
>
|
||||
Remove
|
||||
{isSaving ? 'Saving' : 'Remove'}
|
||||
</button>
|
||||
)}
|
||||
</div>
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
import { useState, useEffect, useCallback } from 'react';
|
||||
import type React from 'react';
|
||||
import { invoke } from '@tauri-apps/api/core';
|
||||
import { LEADERBOARD_ENABLED, SUPABASE_ANON_KEY, SUPABASE_URL } from '../../lib/supabase';
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// Types
|
||||
@@ -279,9 +280,6 @@ function getOrCreateAnonId(): string {
|
||||
return id;
|
||||
}
|
||||
|
||||
const SUPABASE_URL = 'https://mtbtgpwzrbostweaanpr.supabase.co';
|
||||
const SUPABASE_KEY = 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJzdXBhYmFzZSIsInJlZiI6Im10YnRncHd6cmJvc3R3ZWFhbnByIiwicm9sZSI6ImFub24iLCJpYXQiOjE3NzMxODk0OTQsImV4cCI6MjA4ODc2NTQ5NH0._xMlqCfljtXpwPj54H-ghxfLFO-jiq4W2WhpU8vVL1c';
|
||||
|
||||
const REFRESH_INTERVAL_MS = 5000;
|
||||
|
||||
export function SavingsDashboard({ apiUrl }: { apiUrl: string }) {
|
||||
@@ -318,15 +316,16 @@ export function SavingsDashboard({ apiUrl }: { apiUrl: string }) {
|
||||
return () => clearInterval(timer);
|
||||
}, [fetchData]);
|
||||
|
||||
// Share savings to Supabase when opted in and data changes
|
||||
// Share savings to Supabase when opted in and data changes. Skipped entirely
|
||||
// when no anon key was built in (leaderboard disabled).
|
||||
useEffect(() => {
|
||||
if (!optInEnabled || !displayName || !data) return;
|
||||
if (!LEADERBOARD_ENABLED || !optInEnabled || !displayName || !data) return;
|
||||
const dollarSavings = data.per_provider.reduce((s, p) => s + p.total_cost, 0);
|
||||
const energySaved = data.per_provider.reduce((s, p) => s + (p.energy_wh || 0), 0);
|
||||
const flopsSaved = data.per_provider.reduce((s, p) => s + (p.flops || 0), 0);
|
||||
invoke('submit_savings', {
|
||||
supabaseUrl: SUPABASE_URL,
|
||||
supabaseKey: SUPABASE_KEY,
|
||||
supabaseKey: SUPABASE_ANON_KEY,
|
||||
payload: {
|
||||
anon_id: anonId,
|
||||
display_name: displayName,
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import { afterEach, beforeEach, describe, expect, it } from 'vitest';
|
||||
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
|
||||
|
||||
// Regression for #266: the frontend must send the local API key as a Bearer
|
||||
// token on /v1 + /api requests, or `jarvis serve` with a key configured 401s
|
||||
@@ -26,11 +26,14 @@ class MemoryStorage {
|
||||
}
|
||||
|
||||
beforeEach(() => {
|
||||
vi.resetModules();
|
||||
vi.stubEnv('VITE_SUPABASE_ANON_KEY', 'test-anon-key');
|
||||
(globalThis as unknown as { localStorage: MemoryStorage }).localStorage =
|
||||
new MemoryStorage();
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
vi.unstubAllEnvs();
|
||||
(globalThis as unknown as { localStorage?: MemoryStorage }).localStorage =
|
||||
undefined;
|
||||
});
|
||||
|
||||
+27
-4
@@ -1,12 +1,10 @@
|
||||
import type { ModelInfo, SavingsData, ServerInfo } from '../types';
|
||||
import { SUPABASE_ANON_KEY, SUPABASE_URL } from './supabase';
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// Supabase config — safe to embed (RLS protects writes)
|
||||
// Supabase config
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
const SUPABASE_URL = import.meta.env.VITE_SUPABASE_URL || 'https://mtbtgpwzrbostweaanpr.supabase.co';
|
||||
const SUPABASE_ANON_KEY = import.meta.env.VITE_SUPABASE_ANON_KEY || 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJzdXBhYmFzZSIsInJlZiI6Im10YnRncHd6cmJvc3R3ZWFhbnByIiwicm9sZSI6ImFub24iLCJpYXQiOjE3NzMxODk0OTQsImV4cCI6MjA4ODc2NTQ5NH0._xMlqCfljtXpwPj54H-ghxfLFO-jiq4W2WhpU8vVL1c';
|
||||
|
||||
declare global {
|
||||
interface Window {
|
||||
__TAURI_INTERNALS__?: unknown;
|
||||
@@ -15,6 +13,31 @@ declare global {
|
||||
|
||||
export const isTauri = () => typeof window !== 'undefined' && !!window.__TAURI_INTERNALS__;
|
||||
|
||||
export type CloudKeyStatus = Record<string, boolean>;
|
||||
|
||||
export async function getCloudKeyStatus(): Promise<CloudKeyStatus> {
|
||||
if (!isTauri()) return {};
|
||||
try {
|
||||
const { invoke } = await import('@tauri-apps/api/core');
|
||||
const rows = await invoke<Array<{ key: string; set: boolean }>>('get_cloud_key_status');
|
||||
return Object.fromEntries(rows.map((row) => [row.key, row.set]));
|
||||
} catch (e: any) {
|
||||
throw new Error(e?.message ?? e ?? 'Failed to read cloud key status');
|
||||
}
|
||||
}
|
||||
|
||||
export async function saveCloudKey(keyName: string, keyValue: string): Promise<void> {
|
||||
if (!isTauri()) {
|
||||
throw new Error('Cloud API keys can be saved in the desktop app only.');
|
||||
}
|
||||
try {
|
||||
const { invoke } = await import('@tauri-apps/api/core');
|
||||
await invoke('save_cloud_key', { keyName, keyValue });
|
||||
} catch (e: any) {
|
||||
throw new Error(e?.message ?? e ?? 'Failed to save cloud key');
|
||||
}
|
||||
}
|
||||
|
||||
// Cached API base URL fetched from the Tauri backend at startup.
|
||||
// This avoids hardcoding the port — the Rust backend is the single
|
||||
// source of truth for JARVIS_PORT.
|
||||
|
||||
@@ -0,0 +1,11 @@
|
||||
export const SUPABASE_URL =
|
||||
import.meta.env.VITE_SUPABASE_URL || 'https://mtbtgpwzrbostweaanpr.supabase.co';
|
||||
|
||||
// The Supabase anon key is optional at build time. When it is unset the public
|
||||
// savings leaderboard is disabled rather than failing the build — this keeps
|
||||
// the `openjarvis` package and desktop app buildable without coupling
|
||||
// publishability to a leaderboard credential. Set VITE_SUPABASE_ANON_KEY at
|
||||
// build time (from a repo secret) to enable the leaderboard.
|
||||
export const SUPABASE_ANON_KEY = import.meta.env.VITE_SUPABASE_ANON_KEY ?? '';
|
||||
|
||||
export const LEADERBOARD_ENABLED = SUPABASE_ANON_KEY.length > 0;
|
||||
@@ -19,9 +19,21 @@ import {
|
||||
RefreshCw,
|
||||
} from 'lucide-react';
|
||||
import { useAppStore, type ThemeMode } from '../lib/store';
|
||||
import { checkHealth, fetchSpeechHealth, getMemoryStats, getInferenceSource, setInferenceSource, type InferenceSource } from '../lib/api';
|
||||
import {
|
||||
checkHealth,
|
||||
fetchSpeechHealth,
|
||||
getMemoryStats,
|
||||
getInferenceSource,
|
||||
setInferenceSource,
|
||||
getCloudKeyStatus,
|
||||
saveCloudKey,
|
||||
isTauri,
|
||||
type InferenceSource,
|
||||
} from '../lib/api';
|
||||
import { isAutoUpdateDisabled, setAutoUpdateDisabled } from '../components/Desktop/UpdateChecker';
|
||||
|
||||
const CLOUD_KEY_STATUS_CHANGED = 'openjarvis-cloud-key-status-changed';
|
||||
|
||||
function OllamaModelList() {
|
||||
const [models, setModels] = useState<Array<{ name: string; size: number }>>([]);
|
||||
useEffect(() => {
|
||||
@@ -44,32 +56,111 @@ function OllamaModelList() {
|
||||
);
|
||||
}
|
||||
|
||||
function ApiKeyInput({ storageKey, placeholder }: { storageKey: string; placeholder: string }) {
|
||||
const [value, setValue] = useState(() => {
|
||||
try { return localStorage.getItem(storageKey) || ''; } catch { return ''; }
|
||||
});
|
||||
function ApiKeyInput({ keyName, placeholder }: { keyName: string; placeholder: string }) {
|
||||
const [value, setValue] = useState('');
|
||||
const [saved, setSaved] = useState(false);
|
||||
const save = (v: string) => {
|
||||
setValue(v);
|
||||
try { if (v) localStorage.setItem(storageKey, v); else localStorage.removeItem(storageKey); } catch {}
|
||||
setSaved(true);
|
||||
setTimeout(() => setSaved(false), 2000);
|
||||
const [hasKey, setHasKey] = useState(false);
|
||||
const [error, setError] = useState('');
|
||||
const desktopKeyStorage = isTauri();
|
||||
|
||||
const refresh = useCallback(async () => {
|
||||
if (!desktopKeyStorage) {
|
||||
setHasKey(false);
|
||||
return;
|
||||
}
|
||||
try {
|
||||
const status = await getCloudKeyStatus();
|
||||
setHasKey(!!status[keyName]);
|
||||
} catch {
|
||||
setHasKey(false);
|
||||
}
|
||||
}, [desktopKeyStorage, keyName]);
|
||||
|
||||
useEffect(() => {
|
||||
void refresh();
|
||||
window.addEventListener(CLOUD_KEY_STATUS_CHANGED, refresh);
|
||||
return () => window.removeEventListener(CLOUD_KEY_STATUS_CHANGED, refresh);
|
||||
}, [refresh]);
|
||||
|
||||
const save = async (v: string) => {
|
||||
const next = v.trim();
|
||||
if (!next) return;
|
||||
setError('');
|
||||
try {
|
||||
await saveCloudKey(keyName, next);
|
||||
setValue('');
|
||||
setHasKey(true);
|
||||
setSaved(true);
|
||||
window.dispatchEvent(new Event(CLOUD_KEY_STATUS_CHANGED));
|
||||
setTimeout(() => setSaved(false), 2000);
|
||||
} catch (e: any) {
|
||||
setError(e?.message || 'Failed to save API key');
|
||||
}
|
||||
};
|
||||
|
||||
const remove = async () => {
|
||||
setError('');
|
||||
try {
|
||||
await saveCloudKey(keyName, '');
|
||||
setValue('');
|
||||
setHasKey(false);
|
||||
setSaved(true);
|
||||
window.dispatchEvent(new Event(CLOUD_KEY_STATUS_CHANGED));
|
||||
setTimeout(() => setSaved(false), 2000);
|
||||
} catch (e: any) {
|
||||
setError(e?.message || 'Failed to remove API key');
|
||||
}
|
||||
};
|
||||
|
||||
return (
|
||||
<div className="flex items-center gap-2">
|
||||
<input type="password" value={value} onChange={e => save(e.target.value)} placeholder={placeholder}
|
||||
<input
|
||||
type="password"
|
||||
value={value}
|
||||
onChange={e => setValue(e.target.value)}
|
||||
onBlur={() => { if (value.trim()) void save(value); }}
|
||||
placeholder={hasKey ? 'Saved in secure storage' : placeholder}
|
||||
disabled={!desktopKeyStorage}
|
||||
className="w-48 px-2 py-1 rounded text-xs"
|
||||
style={{ background: 'var(--color-bg)', border: '1px solid var(--color-border)', color: 'var(--color-text)' }} />
|
||||
{hasKey && (
|
||||
<button
|
||||
onClick={() => void remove()}
|
||||
className="px-2 py-1 rounded text-[10px] cursor-pointer"
|
||||
style={{ color: 'var(--color-error)', border: '1px solid var(--color-error)' }}
|
||||
>
|
||||
Remove
|
||||
</button>
|
||||
)}
|
||||
{saved && <span className="text-[10px]" style={{ color: 'var(--color-success)' }}>Saved</span>}
|
||||
{error && <span className="text-[10px]" style={{ color: 'var(--color-error)' }}>{error}</span>}
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
function CloudProviderStatus({ label, storageKey }: { label: string; storageKey: string }) {
|
||||
function CloudProviderStatus({ label, keyName }: { label: string; keyName: string }) {
|
||||
const [hasKey, setHasKey] = useState(false);
|
||||
const desktopKeyStorage = isTauri();
|
||||
|
||||
const refresh = useCallback(async () => {
|
||||
if (!desktopKeyStorage) {
|
||||
setHasKey(false);
|
||||
return;
|
||||
}
|
||||
try {
|
||||
const status = await getCloudKeyStatus();
|
||||
setHasKey(!!status[keyName]);
|
||||
} catch {
|
||||
setHasKey(false);
|
||||
}
|
||||
}, [desktopKeyStorage, keyName]);
|
||||
|
||||
useEffect(() => {
|
||||
try { setHasKey(!!localStorage.getItem(storageKey)); } catch { setHasKey(false); }
|
||||
}, [storageKey]);
|
||||
void refresh();
|
||||
window.addEventListener(CLOUD_KEY_STATUS_CHANGED, refresh);
|
||||
return () => window.removeEventListener(CLOUD_KEY_STATUS_CHANGED, refresh);
|
||||
}, [refresh]);
|
||||
|
||||
return (
|
||||
<span className="flex items-center gap-1 text-xs" style={{ color: 'var(--color-text-secondary)' }}>
|
||||
<span style={{
|
||||
@@ -424,10 +515,10 @@ export function SettingsPage() {
|
||||
</div>
|
||||
<SettingRow label="Cloud providers" description="Green dot means API key is configured">
|
||||
<div className="flex flex-wrap gap-3">
|
||||
<CloudProviderStatus label="OpenAI" storageKey="openjarvis-openai-key" />
|
||||
<CloudProviderStatus label="Anthropic" storageKey="openjarvis-anthropic-key" />
|
||||
<CloudProviderStatus label="Google" storageKey="openjarvis-gemini-key" />
|
||||
<CloudProviderStatus label="OpenRouter" storageKey="openjarvis-openrouter-key" />
|
||||
<CloudProviderStatus label="OpenAI" keyName="OPENAI_API_KEY" />
|
||||
<CloudProviderStatus label="Anthropic" keyName="ANTHROPIC_API_KEY" />
|
||||
<CloudProviderStatus label="Google" keyName="GEMINI_API_KEY" />
|
||||
<CloudProviderStatus label="OpenRouter" keyName="OPENROUTER_API_KEY" />
|
||||
</div>
|
||||
</SettingRow>
|
||||
</Section>
|
||||
@@ -435,23 +526,23 @@ export function SettingsPage() {
|
||||
{/* API Keys */}
|
||||
<Section title="API Keys">
|
||||
<SettingRow label="OpenAI" description="GPT-4, GPT-3.5, etc.">
|
||||
<ApiKeyInput storageKey="openjarvis-openai-key" placeholder="sk-..." />
|
||||
<ApiKeyInput keyName="OPENAI_API_KEY" placeholder="sk-..." />
|
||||
</SettingRow>
|
||||
<SettingRow label="Anthropic" description="Claude models">
|
||||
<ApiKeyInput storageKey="openjarvis-anthropic-key" placeholder="sk-ant-..." />
|
||||
<ApiKeyInput keyName="ANTHROPIC_API_KEY" placeholder="sk-ant-..." />
|
||||
</SettingRow>
|
||||
<SettingRow label="Google" description="Gemini models">
|
||||
<ApiKeyInput storageKey="openjarvis-gemini-key" placeholder="AI..." />
|
||||
<ApiKeyInput keyName="GEMINI_API_KEY" placeholder="AI..." />
|
||||
</SettingRow>
|
||||
<SettingRow label="OpenRouter" description="Multi-provider routing">
|
||||
<ApiKeyInput storageKey="openjarvis-openrouter-key" placeholder="sk-or-..." />
|
||||
<ApiKeyInput keyName="OPENROUTER_API_KEY" placeholder="sk-or-..." />
|
||||
</SettingRow>
|
||||
</Section>
|
||||
|
||||
{/* Tools */}
|
||||
<Section title="Tools">
|
||||
<SettingRow label="Web Search" description="SerpAPI or Tavily key for web search tool">
|
||||
<ApiKeyInput storageKey="openjarvis-search-key" placeholder="API key..." />
|
||||
<SettingRow label="Web Search" description="Tavily key for web search tool">
|
||||
<ApiKeyInput keyName="TAVILY_API_KEY" placeholder="tvly-..." />
|
||||
</SettingRow>
|
||||
</Section>
|
||||
|
||||
|
||||
Vendored
+3
-1
@@ -1,7 +1,9 @@
|
||||
/// <reference types="vite/client" />
|
||||
|
||||
interface ImportMetaEnv {
|
||||
readonly VITE_API_URL: string;
|
||||
readonly VITE_API_URL?: string;
|
||||
readonly VITE_SUPABASE_URL?: string;
|
||||
readonly VITE_SUPABASE_ANON_KEY?: string;
|
||||
}
|
||||
|
||||
interface ImportMeta {
|
||||
|
||||
@@ -4,6 +4,9 @@ import react from '@vitejs/plugin-react';
|
||||
import tailwindcss from '@tailwindcss/vite';
|
||||
import { VitePWA } from 'vite-plugin-pwa';
|
||||
|
||||
// VITE_SUPABASE_ANON_KEY is intentionally NOT required here: a missing key
|
||||
// disables the savings leaderboard at runtime (see src/lib/supabase.ts) rather
|
||||
// than failing the build, so the package/app stays publishable without it.
|
||||
export default defineConfig({
|
||||
resolve: {
|
||||
alias: {
|
||||
|
||||
@@ -48,6 +48,7 @@ dev = [
|
||||
"pytest>=8",
|
||||
"pytest-asyncio>=0.24",
|
||||
"pytest-cov>=5",
|
||||
"pytest-xdist>=3",
|
||||
"respx>=0.22",
|
||||
"ruff>=0.4",
|
||||
"pre-commit>=3.0",
|
||||
|
||||
@@ -179,6 +179,19 @@ def chat(
|
||||
|
||||
_notifications = NotificationDispatcher(get_status())
|
||||
|
||||
# Automatic long-term memory — extracts durable facts in the background.
|
||||
memory_service = None
|
||||
try:
|
||||
from openjarvis.memory import build_memory_service
|
||||
|
||||
memory_service = build_memory_service(config, engine, model)
|
||||
if memory_service is not None:
|
||||
memory_service.start()
|
||||
console.print("[dim] Memory: active[/dim]")
|
||||
except Exception as exc:
|
||||
console.print(f"[yellow]Memory service unavailable: {exc}[/yellow]")
|
||||
memory_service = None
|
||||
|
||||
# Conversation state
|
||||
if not system_prompt:
|
||||
from openjarvis.prompt.builder import SystemPromptBuilder
|
||||
@@ -266,10 +279,17 @@ def chat(
|
||||
console.print()
|
||||
console.print(Markdown(content))
|
||||
console.print()
|
||||
|
||||
# Hand the exchange to the memory service (non-blocking).
|
||||
if memory_service is not None:
|
||||
memory_service.submit(user_input, content)
|
||||
except KeyboardInterrupt:
|
||||
console.print("\n[dim]Generation interrupted.[/dim]")
|
||||
except Exception as exc:
|
||||
console.print(f"\n[red]Error: {exc}[/red]\n")
|
||||
|
||||
if memory_service is not None:
|
||||
memory_service.stop()
|
||||
|
||||
|
||||
__all__ = ["chat"]
|
||||
|
||||
@@ -167,6 +167,66 @@ def search(
|
||||
console.print(table)
|
||||
|
||||
|
||||
def _get_fact_store():
|
||||
"""Instantiate the automatic-memory fact store from config."""
|
||||
from openjarvis.memory.store import create_fact_store
|
||||
|
||||
config = load_config()
|
||||
mem = config.memory
|
||||
return create_fact_store(
|
||||
getattr(mem, "backend", "local"),
|
||||
path=getattr(mem, "facts_path", "~/.openjarvis/memory_facts.jsonl"),
|
||||
max_facts=getattr(mem, "max_facts", 1000),
|
||||
)
|
||||
|
||||
|
||||
@memory.command(name="list")
|
||||
def list_facts() -> None:
|
||||
"""List durable facts captured by the automatic memory service."""
|
||||
console = Console()
|
||||
|
||||
store = _get_fact_store()
|
||||
facts = store.list()
|
||||
if not facts:
|
||||
console.print("[yellow]No memory facts stored yet.[/yellow]")
|
||||
return
|
||||
|
||||
table = Table(title=f"Memory Facts ({len(facts)})")
|
||||
table.add_column("#", style="dim", width=4)
|
||||
table.add_column("Fact")
|
||||
table.add_column("Source", style="cyan")
|
||||
for i, fact in enumerate(facts, 1):
|
||||
table.add_row(str(i), fact.text, fact.source or "-")
|
||||
console.print(table)
|
||||
|
||||
|
||||
@memory.command()
|
||||
@click.option(
|
||||
"--yes",
|
||||
"-y",
|
||||
is_flag=True,
|
||||
default=False,
|
||||
help="Skip the confirmation prompt.",
|
||||
)
|
||||
def clear(yes: bool) -> None:
|
||||
"""Remove all durable facts captured by the automatic memory service."""
|
||||
console = Console()
|
||||
|
||||
store = _get_fact_store()
|
||||
count = store.count()
|
||||
if count == 0:
|
||||
console.print("[yellow]No memory facts to clear.[/yellow]")
|
||||
return
|
||||
|
||||
if not yes:
|
||||
if not click.confirm(f"Remove all {count} stored memory fact(s)?"):
|
||||
console.print("[dim]Aborted.[/dim]")
|
||||
return
|
||||
|
||||
removed = store.clear()
|
||||
console.print(f"[green]Cleared {removed} memory fact(s).[/green]")
|
||||
|
||||
|
||||
@memory.command()
|
||||
@click.option(
|
||||
"--backend",
|
||||
|
||||
@@ -493,6 +493,19 @@ def serve(
|
||||
except Exception as exc:
|
||||
logger.debug("Memory backend init failed: %s", exc)
|
||||
|
||||
# Automatic long-term memory service (background fact extraction).
|
||||
memory_service = None
|
||||
try:
|
||||
from openjarvis.memory import build_memory_service
|
||||
|
||||
memory_service = build_memory_service(config, engine, model_name)
|
||||
if memory_service is not None:
|
||||
memory_service.start()
|
||||
console.print(" Memory svc: [cyan]active[/cyan]")
|
||||
except Exception as exc:
|
||||
logger.debug("Memory service init failed: %s", exc)
|
||||
memory_service = None
|
||||
|
||||
# Set up agent manager
|
||||
agent_manager = None
|
||||
if config.agent_manager.enabled:
|
||||
@@ -667,6 +680,7 @@ def serve(
|
||||
channel_bridge=channel_bridge,
|
||||
config=config,
|
||||
memory_backend=memory_backend,
|
||||
memory_service=memory_service,
|
||||
speech_backend=speech_backend,
|
||||
agent_manager=agent_manager,
|
||||
agent_scheduler=agent_scheduler,
|
||||
|
||||
@@ -910,7 +910,13 @@ class LearningConfig:
|
||||
|
||||
@dataclass(slots=True)
|
||||
class StorageConfig:
|
||||
"""Storage (memory) backend settings."""
|
||||
"""Storage (memory) backend settings.
|
||||
|
||||
Covers both the retrieval/document store (``default_backend``, ``db_path``,
|
||||
chunking, context injection) and the automatic long-term memory service
|
||||
(``enabled``, ``backend``, ``extraction_model``, ``max_facts``,
|
||||
``facts_path``) configured under ``[memory]`` in ``config.toml``.
|
||||
"""
|
||||
|
||||
default_backend: str = "sqlite"
|
||||
db_path: str = field(default_factory=lambda: str(get_config_dir() / "memory.db"))
|
||||
@@ -920,6 +926,14 @@ class StorageConfig:
|
||||
chunk_size: int = 512
|
||||
chunk_overlap: int = 64
|
||||
|
||||
# Automatic memory service — extracts durable facts from conversations in
|
||||
# the background and persists them across sessions (see openjarvis.memory).
|
||||
enabled: bool = False # start the memory service with serve/chat
|
||||
backend: str = "local" # fact-store backend ("local" = on-disk JSONL)
|
||||
extraction_model: str = "" # model for fact extraction ("" = active model)
|
||||
max_facts: int = 1000 # cap on stored facts (oldest evicted past the cap)
|
||||
facts_path: str = str(DEFAULT_CONFIG_DIR / "memory_facts.jsonl")
|
||||
|
||||
|
||||
# Backward-compatibility alias
|
||||
MemoryConfig = StorageConfig
|
||||
@@ -2003,6 +2017,15 @@ context_from_memory = true
|
||||
[tools.storage]
|
||||
default_backend = "sqlite"
|
||||
|
||||
# Automatic long-term memory: extracts durable facts from conversations in the
|
||||
# background and persists them. Starts/stops with `jarvis serve` and
|
||||
# `jarvis chat`; manage stored facts with `jarvis memory list` / `clear`.
|
||||
[memory]
|
||||
enabled = false # set true to enable the memory service
|
||||
backend = "local" # fact-store backend (local = on-disk JSONL)
|
||||
extraction_model = "" # model for fact extraction ("" = active model)
|
||||
max_facts = 1000 # cap on stored facts
|
||||
|
||||
[tools.mcp]
|
||||
enabled = true
|
||||
|
||||
|
||||
@@ -0,0 +1,28 @@
|
||||
"""Native persistent long-term memory for OpenJarvis.
|
||||
|
||||
This package provides the automatic memory service that extracts durable facts
|
||||
from conversations in the background and persists them across sessions. It is
|
||||
started and stopped as part of the ``jarvis serve`` / ``jarvis chat`` lifecycle
|
||||
and configured via the ``[memory]`` section of ``config.toml``.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from openjarvis.memory.extractor import FactExtractor
|
||||
from openjarvis.memory.service import MemoryService, build_memory_service
|
||||
from openjarvis.memory.store import (
|
||||
Fact,
|
||||
FactStore,
|
||||
LocalFactStore,
|
||||
create_fact_store,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"Fact",
|
||||
"FactStore",
|
||||
"FactExtractor",
|
||||
"LocalFactStore",
|
||||
"MemoryService",
|
||||
"build_memory_service",
|
||||
"create_fact_store",
|
||||
]
|
||||
@@ -0,0 +1,150 @@
|
||||
"""LLM-backed extraction of durable facts from a conversation turn.
|
||||
|
||||
The extractor takes a single (user, assistant) exchange and asks a small
|
||||
local model to distill any long-term, user-specific facts worth remembering.
|
||||
It is deliberately defensive: extraction runs on a background thread far from
|
||||
the request path, so *any* failure — a dropped Ollama connection, a timeout, a
|
||||
``BrokenPipeError`` when the client went away, or simply unparseable output —
|
||||
must degrade to "no facts" rather than propagate.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
import re
|
||||
from typing import Any, List, Optional
|
||||
|
||||
from openjarvis.core.types import Message, Role
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_DEFAULT_SYSTEM_PROMPT = (
|
||||
"You extract durable, long-term facts about the user from a single "
|
||||
"conversation exchange. A good fact is stable over time and useful in "
|
||||
"future conversations: preferences, identity, goals, ongoing projects, "
|
||||
"constraints, or relationships. Ignore one-off task details, small talk, "
|
||||
"and anything the assistant said about itself.\n\n"
|
||||
"Respond with ONLY a JSON array of short fact strings (each under 200 "
|
||||
"characters). If there is nothing worth remembering, respond with []."
|
||||
)
|
||||
|
||||
|
||||
class FactExtractor:
|
||||
"""Extract memory-worthy facts from a conversation turn via an engine."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
engine: Any,
|
||||
model: str,
|
||||
*,
|
||||
temperature: float = 0.0,
|
||||
max_tokens: int = 512,
|
||||
max_facts_per_turn: int = 10,
|
||||
max_fact_chars: int = 200,
|
||||
system_prompt: Optional[str] = None,
|
||||
) -> None:
|
||||
self._engine = engine
|
||||
self._model = model
|
||||
self._temperature = temperature
|
||||
self._max_tokens = max_tokens
|
||||
self._max_facts_per_turn = max_facts_per_turn
|
||||
self._max_fact_chars = max_fact_chars
|
||||
self._system_prompt = system_prompt or _DEFAULT_SYSTEM_PROMPT
|
||||
|
||||
def extract(self, user_text: str, assistant_text: str = "") -> List[str]:
|
||||
"""Return durable facts from the exchange. Never raises."""
|
||||
user_text = (user_text or "").strip()
|
||||
if not user_text:
|
||||
return []
|
||||
|
||||
exchange = f"User: {user_text}"
|
||||
if assistant_text and assistant_text.strip():
|
||||
exchange += f"\nAssistant: {assistant_text.strip()}"
|
||||
|
||||
messages = [
|
||||
Message(role=Role.SYSTEM, content=self._system_prompt),
|
||||
Message(role=Role.USER, content=exchange),
|
||||
]
|
||||
|
||||
try:
|
||||
result = self._engine.generate(
|
||||
messages,
|
||||
model=self._model,
|
||||
temperature=self._temperature,
|
||||
max_tokens=self._max_tokens,
|
||||
)
|
||||
except BrokenPipeError:
|
||||
# The classic failure mode: the model call's transport died.
|
||||
# Extraction is best-effort, so swallow it.
|
||||
logger.debug("Memory extraction aborted: broken pipe", exc_info=True)
|
||||
return []
|
||||
except Exception: # noqa: BLE001 — extraction must never crash the worker
|
||||
logger.debug("Memory extraction failed", exc_info=True)
|
||||
return []
|
||||
|
||||
if isinstance(result, dict):
|
||||
content = result.get("content", "") or ""
|
||||
else:
|
||||
content = str(result)
|
||||
|
||||
return self._parse(content)
|
||||
|
||||
# -- parsing ------------------------------------------------------------
|
||||
|
||||
def _parse(self, content: str) -> List[str]:
|
||||
"""Parse model output into a clean, deduped, capped list of facts."""
|
||||
if not content or not content.strip():
|
||||
return []
|
||||
|
||||
raw = self._coerce_to_list(content)
|
||||
|
||||
facts: List[str] = []
|
||||
seen: set[str] = set()
|
||||
for item in raw:
|
||||
fact = self._clean_fact(item)
|
||||
if not fact:
|
||||
continue
|
||||
key = fact.lower()
|
||||
if key in seen:
|
||||
continue
|
||||
seen.add(key)
|
||||
facts.append(fact)
|
||||
if len(facts) >= self._max_facts_per_turn:
|
||||
break
|
||||
return facts
|
||||
|
||||
def _coerce_to_list(self, content: str) -> List[str]:
|
||||
"""Best-effort conversion of model output to a list of strings."""
|
||||
# 1. Try to locate and parse a JSON array anywhere in the output
|
||||
# (models often wrap it in prose or code fences).
|
||||
match = re.search(r"\[.*\]", content, re.DOTALL)
|
||||
if match:
|
||||
try:
|
||||
parsed = json.loads(match.group(0))
|
||||
if isinstance(parsed, list):
|
||||
return [str(x) for x in parsed]
|
||||
except (json.JSONDecodeError, ValueError):
|
||||
pass
|
||||
|
||||
# 2. Fall back to line-based parsing (markdown bullets / numbered).
|
||||
items: List[str] = []
|
||||
for line in content.splitlines():
|
||||
line = line.strip()
|
||||
if not line:
|
||||
continue
|
||||
line = re.sub(r"^\s*(?:[-*•]|\d+[.)])\s*", "", line)
|
||||
items.append(line)
|
||||
return items
|
||||
|
||||
def _clean_fact(self, item: str) -> str:
|
||||
fact = str(item).strip().strip("\"'").strip()
|
||||
# Drop obvious non-facts the model sometimes emits.
|
||||
if not fact or fact.lower() in ("[]", "none", "n/a", "null"):
|
||||
return ""
|
||||
if len(fact) > self._max_fact_chars:
|
||||
fact = fact[: self._max_fact_chars].rstrip()
|
||||
return fact
|
||||
|
||||
|
||||
__all__ = ["FactExtractor"]
|
||||
@@ -0,0 +1,180 @@
|
||||
"""Persistent memory service: async fact extraction integrated into core.
|
||||
|
||||
``MemoryService`` runs fact extraction on a dedicated background thread so it
|
||||
never blocks ``jarvis serve`` request handling or the ``jarvis chat`` REPL.
|
||||
Callers hand off an exchange via :meth:`submit`, which enqueues the work and
|
||||
returns immediately — the slow model call and disk write happen out of band.
|
||||
The worker swallows every per-job error (including ``BrokenPipeError`` when a
|
||||
client disconnects mid-extraction), so a flaky extraction model can never take
|
||||
down the host process.
|
||||
|
||||
The service is started and stopped as part of the OpenJarvis lifecycle (see
|
||||
``cli/serve.py`` and ``cli/chat_cmd.py``) and is configured through the
|
||||
``[memory]`` section of ``config.toml``.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import queue
|
||||
import threading
|
||||
from typing import Any, List, Optional
|
||||
|
||||
from openjarvis.memory.extractor import FactExtractor
|
||||
from openjarvis.memory.store import Fact, FactStore, create_fact_store
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Sentinel pushed onto the queue to wake the worker for shutdown.
|
||||
_STOP = object()
|
||||
|
||||
|
||||
class MemoryService:
|
||||
"""Background long-term-memory extraction and persistence service."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
store: FactStore,
|
||||
extractor: FactExtractor,
|
||||
*,
|
||||
max_queue: int = 256,
|
||||
) -> None:
|
||||
self._store = store
|
||||
self._extractor = extractor
|
||||
self._queue: "queue.Queue[Any]" = queue.Queue(maxsize=max(1, max_queue))
|
||||
self._thread: Optional[threading.Thread] = None
|
||||
self._running = threading.Event()
|
||||
|
||||
# -- lifecycle ----------------------------------------------------------
|
||||
|
||||
def start(self) -> None:
|
||||
"""Start the background worker thread (idempotent)."""
|
||||
if self._running.is_set():
|
||||
return
|
||||
self._running.set()
|
||||
self._thread = threading.Thread(
|
||||
target=self._loop,
|
||||
name="memory-service",
|
||||
daemon=True,
|
||||
)
|
||||
self._thread.start()
|
||||
logger.debug("Memory service started")
|
||||
|
||||
def stop(self, timeout: float = 2.0) -> None:
|
||||
"""Signal the worker to drain and stop, then join it (idempotent)."""
|
||||
if not self._running.is_set():
|
||||
return
|
||||
self._running.clear()
|
||||
try:
|
||||
self._queue.put_nowait(_STOP)
|
||||
except queue.Full:
|
||||
pass # worker will notice the cleared flag on its next loop
|
||||
thread = self._thread
|
||||
if thread is not None:
|
||||
thread.join(timeout=timeout)
|
||||
self._thread = None
|
||||
logger.debug("Memory service stopped")
|
||||
|
||||
@property
|
||||
def is_running(self) -> bool:
|
||||
return self._running.is_set()
|
||||
|
||||
# -- submission ---------------------------------------------------------
|
||||
|
||||
def submit(self, user_text: str, assistant_text: str = "") -> bool:
|
||||
"""Queue an exchange for extraction. Non-blocking; never raises.
|
||||
|
||||
Returns True if the job was enqueued, False if the service is not
|
||||
running or the queue is full (in which case the exchange is dropped
|
||||
rather than blocking the caller — extraction is best-effort).
|
||||
"""
|
||||
if not self._running.is_set():
|
||||
return False
|
||||
if not user_text or not user_text.strip():
|
||||
return False
|
||||
try:
|
||||
self._queue.put_nowait((user_text, assistant_text))
|
||||
return True
|
||||
except queue.Full:
|
||||
logger.debug("Memory service queue full; dropping exchange")
|
||||
return False
|
||||
|
||||
# -- worker -------------------------------------------------------------
|
||||
|
||||
def _loop(self) -> None:
|
||||
while True:
|
||||
try:
|
||||
job = self._queue.get(timeout=0.5)
|
||||
except queue.Empty:
|
||||
if not self._running.is_set():
|
||||
break
|
||||
continue
|
||||
if job is _STOP:
|
||||
self._queue.task_done()
|
||||
break
|
||||
try:
|
||||
self._process(job)
|
||||
except Exception: # noqa: BLE001 — a bad job must not kill the worker
|
||||
logger.debug("Memory extraction job failed", exc_info=True)
|
||||
finally:
|
||||
self._queue.task_done()
|
||||
if not self._running.is_set() and self._queue.empty():
|
||||
break
|
||||
|
||||
def _process(self, job: Any) -> None:
|
||||
user_text, assistant_text = job
|
||||
facts = self._extractor.extract(user_text, assistant_text)
|
||||
if facts:
|
||||
stored = self._store.add_many(facts, source="auto")
|
||||
if stored:
|
||||
logger.debug("Memory service stored %d new fact(s)", stored)
|
||||
|
||||
# -- store passthroughs -------------------------------------------------
|
||||
|
||||
def list_facts(self) -> List[Fact]:
|
||||
return self._store.list()
|
||||
|
||||
def clear_facts(self) -> int:
|
||||
return self._store.clear()
|
||||
|
||||
def fact_count(self) -> int:
|
||||
return self._store.count()
|
||||
|
||||
|
||||
def build_memory_service(
|
||||
config: Any,
|
||||
engine: Any,
|
||||
default_model: str = "",
|
||||
) -> Optional[MemoryService]:
|
||||
"""Build a :class:`MemoryService` from config, or ``None`` if disabled.
|
||||
|
||||
Reads the ``[memory]`` section (``config.memory`` / ``config.tools.storage``)
|
||||
for ``enabled``, ``backend``, ``extraction_model``, ``max_facts`` and
|
||||
``facts_path``. Returns ``None`` when memory is disabled or no engine /
|
||||
extraction model is available, so callers can simply do::
|
||||
|
||||
svc = build_memory_service(config, engine, model)
|
||||
if svc is not None:
|
||||
svc.start()
|
||||
"""
|
||||
mem = getattr(config, "memory", None)
|
||||
if mem is None or not getattr(mem, "enabled", False):
|
||||
return None
|
||||
if engine is None:
|
||||
return None
|
||||
|
||||
model = getattr(mem, "extraction_model", "") or default_model
|
||||
if not model:
|
||||
logger.debug("Memory service disabled: no extraction model available")
|
||||
return None
|
||||
|
||||
store = create_fact_store(
|
||||
getattr(mem, "backend", "local"),
|
||||
path=getattr(mem, "facts_path", "~/.openjarvis/memory_facts.jsonl"),
|
||||
max_facts=getattr(mem, "max_facts", 1000),
|
||||
)
|
||||
extractor = FactExtractor(engine, model)
|
||||
return MemoryService(store, extractor)
|
||||
|
||||
|
||||
__all__ = ["MemoryService", "build_memory_service"]
|
||||
@@ -0,0 +1,179 @@
|
||||
"""Persistent stores for automatically extracted long-term memory facts.
|
||||
|
||||
A *fact* is a short, durable statement worth remembering about the user
|
||||
(e.g. ``"Prefers concise answers"``). Facts are produced by the memory
|
||||
service's background extractor and persisted here so they survive across
|
||||
sessions. The store is intentionally small and self-contained: it dedupes,
|
||||
caps the total number of facts, and is safe to call from multiple threads.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import threading
|
||||
import time
|
||||
from abc import ABC, abstractmethod
|
||||
from dataclasses import asdict, dataclass
|
||||
from pathlib import Path
|
||||
from typing import Iterable, List
|
||||
|
||||
|
||||
@dataclass(slots=True)
|
||||
class Fact:
|
||||
"""A single durable memory entry."""
|
||||
|
||||
text: str
|
||||
source: str = ""
|
||||
created_at: float = 0.0
|
||||
|
||||
|
||||
class FactStore(ABC):
|
||||
"""Abstract persistent store for extracted memory facts."""
|
||||
|
||||
@abstractmethod
|
||||
def add(self, text: str, source: str = "") -> bool:
|
||||
"""Store *text* as a fact. Returns True if a new fact was stored."""
|
||||
|
||||
def add_many(self, texts: Iterable[str], source: str = "") -> int:
|
||||
"""Store several facts, returning the count of newly stored ones."""
|
||||
added = 0
|
||||
for text in texts:
|
||||
if self.add(text, source=source):
|
||||
added += 1
|
||||
return added
|
||||
|
||||
@abstractmethod
|
||||
def list(self) -> List[Fact]:
|
||||
"""Return all stored facts, oldest first."""
|
||||
|
||||
@abstractmethod
|
||||
def clear(self) -> int:
|
||||
"""Remove all stored facts, returning the number removed."""
|
||||
|
||||
@abstractmethod
|
||||
def count(self) -> int:
|
||||
"""Return the number of stored facts."""
|
||||
|
||||
|
||||
class LocalFactStore(FactStore):
|
||||
"""Append-only JSONL fact store on the local filesystem.
|
||||
|
||||
Facts are kept human-readable (one JSON object per line) so they can be
|
||||
inspected or edited by hand. Writes are atomic (temp file + rename) and
|
||||
guarded by a lock, so concurrent ``add`` calls from the extraction worker
|
||||
and ``list``/``clear`` from the CLI never corrupt the file.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
path: str | Path = "~/.openjarvis/memory_facts.jsonl",
|
||||
*,
|
||||
max_facts: int = 1000,
|
||||
) -> None:
|
||||
self._path = Path(path).expanduser()
|
||||
self._max_facts = max(0, int(max_facts))
|
||||
self._lock = threading.Lock()
|
||||
self._facts: List[Fact] = self._load()
|
||||
|
||||
# -- persistence --------------------------------------------------------
|
||||
|
||||
def _load(self) -> List[Fact]:
|
||||
if not self._path.exists():
|
||||
return []
|
||||
facts: List[Fact] = []
|
||||
try:
|
||||
text = self._path.read_text(encoding="utf-8")
|
||||
except OSError:
|
||||
return []
|
||||
for line in text.splitlines():
|
||||
line = line.strip()
|
||||
if not line:
|
||||
continue
|
||||
try:
|
||||
obj = json.loads(line)
|
||||
except (json.JSONDecodeError, ValueError):
|
||||
continue # skip malformed lines rather than crashing
|
||||
fact_text = str(obj.get("text", "")).strip()
|
||||
if not fact_text:
|
||||
continue
|
||||
facts.append(
|
||||
Fact(
|
||||
text=fact_text,
|
||||
source=str(obj.get("source", "")),
|
||||
created_at=float(obj.get("created_at", 0.0) or 0.0),
|
||||
)
|
||||
)
|
||||
return facts
|
||||
|
||||
def _flush(self) -> None:
|
||||
"""Atomically rewrite the JSONL file from the in-memory list."""
|
||||
self._path.parent.mkdir(parents=True, exist_ok=True)
|
||||
tmp = self._path.with_suffix(self._path.suffix + ".tmp")
|
||||
payload = "".join(
|
||||
json.dumps(asdict(f), ensure_ascii=False) + "\n" for f in self._facts
|
||||
)
|
||||
tmp.write_text(payload, encoding="utf-8")
|
||||
os.replace(tmp, self._path)
|
||||
|
||||
# -- FactStore API ------------------------------------------------------
|
||||
|
||||
def add(self, text: str, source: str = "") -> bool:
|
||||
text = (text or "").strip()
|
||||
if not text:
|
||||
return False
|
||||
with self._lock:
|
||||
lowered = text.lower()
|
||||
if any(f.text.lower() == lowered for f in self._facts):
|
||||
return False # dedupe
|
||||
self._facts.append(Fact(text=text, source=source, created_at=time.time()))
|
||||
# Enforce the cap by evicting the oldest entries.
|
||||
if self._max_facts and len(self._facts) > self._max_facts:
|
||||
self._facts = self._facts[-self._max_facts :]
|
||||
self._flush()
|
||||
return True
|
||||
|
||||
def list(self) -> List[Fact]:
|
||||
with self._lock:
|
||||
return list(self._facts)
|
||||
|
||||
def clear(self) -> int:
|
||||
with self._lock:
|
||||
removed = len(self._facts)
|
||||
self._facts = []
|
||||
if self._path.exists():
|
||||
try:
|
||||
self._path.unlink()
|
||||
except OSError:
|
||||
self._flush()
|
||||
return removed
|
||||
|
||||
def count(self) -> int:
|
||||
with self._lock:
|
||||
return len(self._facts)
|
||||
|
||||
@property
|
||||
def path(self) -> Path:
|
||||
"""Filesystem location of the JSONL store."""
|
||||
return self._path
|
||||
|
||||
|
||||
def create_fact_store(
|
||||
backend: str = "local",
|
||||
*,
|
||||
path: str | Path = "~/.openjarvis/memory_facts.jsonl",
|
||||
max_facts: int = 1000,
|
||||
) -> FactStore:
|
||||
"""Construct a fact store for the configured *backend*.
|
||||
|
||||
Only the ``"local"`` (on-disk JSONL) backend is supported today; the
|
||||
factory exists so additional backends can be added without changing the
|
||||
service or CLI wiring.
|
||||
"""
|
||||
key = (backend or "local").strip().lower()
|
||||
if key == "local":
|
||||
return LocalFactStore(path, max_facts=max_facts)
|
||||
raise ValueError(f"Unknown memory backend '{backend}'. Supported backends: local")
|
||||
|
||||
|
||||
__all__ = ["Fact", "FactStore", "LocalFactStore", "create_fact_store"]
|
||||
@@ -151,6 +151,7 @@ def create_app(
|
||||
channel_bridge=None,
|
||||
config=None,
|
||||
memory_backend=None,
|
||||
memory_service=None,
|
||||
speech_backend=None,
|
||||
agent_manager=None,
|
||||
agent_scheduler=None,
|
||||
@@ -221,6 +222,7 @@ def create_app(
|
||||
app.state.channel_bridge = channel_bridge
|
||||
app.state.config = config
|
||||
app.state.memory_backend = memory_backend
|
||||
app.state.memory_service = memory_service
|
||||
app.state.speech_backend = speech_backend
|
||||
app.state.agent_manager = agent_manager
|
||||
app.state.agent_scheduler = agent_scheduler
|
||||
@@ -292,6 +294,18 @@ def create_app(
|
||||
except Exception as _exc:
|
||||
logger.debug("Analytics init skipped: %s", _exc)
|
||||
|
||||
# Stop the background memory service cleanly when the server shuts down.
|
||||
if memory_service is not None:
|
||||
|
||||
@app.on_event("shutdown")
|
||||
async def _shutdown_memory_service() -> None:
|
||||
svc = getattr(app.state, "memory_service", None)
|
||||
if svc is not None:
|
||||
try:
|
||||
svc.stop()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
app.include_router(router)
|
||||
app.include_router(dashboard_router)
|
||||
app.include_router(comparison_router)
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
"""Direct cloud API router — bypasses the engine system entirely.
|
||||
|
||||
Reads API keys from ~/.openjarvis/cloud-keys.env at request time so
|
||||
it works even when the server was started without cloud keys in its
|
||||
environment. Uses httpx directly so no cloud SDK packages are required.
|
||||
Reads API keys from the process environment, with a legacy
|
||||
~/.openjarvis/cloud-keys.env fallback for non-desktop/manual setups. Uses
|
||||
httpx directly so no cloud SDK packages are required.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -38,7 +38,7 @@ _LOCAL_HF_ORGS = (
|
||||
|
||||
|
||||
def _load_keys() -> dict[str, str]:
|
||||
"""Read cloud-keys.env from disk every call so live updates are picked up."""
|
||||
"""Read available cloud keys every call so live updates are picked up."""
|
||||
keys: dict[str, str] = {}
|
||||
# File first, then fall back to process environment
|
||||
if _CLOUD_ENV_FILE.exists():
|
||||
|
||||
@@ -223,7 +223,7 @@ async def chat_completions(request_body: ChatCompletionRequest, request: Request
|
||||
# the agent to execute them), add an explicit opt-in header rather
|
||||
# than removing this guard — silent re-routing is what produced #414.
|
||||
if agent is not None and not request_body.tools:
|
||||
return _handle_agent(
|
||||
response = _handle_agent(
|
||||
agent,
|
||||
model,
|
||||
request_body,
|
||||
@@ -231,16 +231,41 @@ async def chat_completions(request_body: ChatCompletionRequest, request: Request
|
||||
trace_store=getattr(request.app.state, "trace_store", None),
|
||||
bus=getattr(request.app.state, "bus", None),
|
||||
)
|
||||
else:
|
||||
bus = getattr(request.app.state, "bus", None)
|
||||
response = _handle_direct(
|
||||
engine,
|
||||
model,
|
||||
request_body,
|
||||
bus=bus,
|
||||
complexity_info=complexity_info,
|
||||
app_config=config,
|
||||
)
|
||||
|
||||
bus = getattr(request.app.state, "bus", None)
|
||||
return _handle_direct(
|
||||
engine,
|
||||
model,
|
||||
request_body,
|
||||
bus=bus,
|
||||
complexity_info=complexity_info,
|
||||
app_config=config,
|
||||
# Hand the completed exchange to the background memory service.
|
||||
_remember_exchange(
|
||||
getattr(request.app.state, "memory_service", None),
|
||||
query_text_for_complexity,
|
||||
response,
|
||||
)
|
||||
return response
|
||||
|
||||
|
||||
def _remember_exchange(memory_service, user_text: str, response) -> None:
|
||||
"""Submit a completed exchange to the memory service (non-blocking)."""
|
||||
if memory_service is None or not user_text:
|
||||
return
|
||||
try:
|
||||
content = ""
|
||||
choices = getattr(response, "choices", None)
|
||||
if choices:
|
||||
content = getattr(choices[0].message, "content", "") or ""
|
||||
memory_service.submit(user_text, content)
|
||||
except Exception: # noqa: BLE001 — memory is best-effort, never fail a reply
|
||||
logging.getLogger("openjarvis.server").debug(
|
||||
"Memory submit failed",
|
||||
exc_info=True,
|
||||
)
|
||||
|
||||
|
||||
def _handle_direct(
|
||||
@@ -823,14 +848,34 @@ async def reload_cloud_engine(request: Request):
|
||||
"""
|
||||
import os
|
||||
|
||||
# Re-read ~/.openjarvis/cloud-keys.env and update the running process env.
|
||||
keys_path = get_config_dir() / "cloud-keys.env"
|
||||
if keys_path.exists():
|
||||
for raw_line in keys_path.read_text().splitlines():
|
||||
line = raw_line.strip()
|
||||
if line and not line.startswith("#") and "=" in line:
|
||||
k, v = line.split("=", 1)
|
||||
os.environ[k.strip()] = v.strip()
|
||||
submitted_keys: dict[str, str] | None = None
|
||||
try:
|
||||
body = await request.json()
|
||||
raw_keys = body.get("keys") if isinstance(body, dict) else None
|
||||
if isinstance(raw_keys, dict):
|
||||
submitted_keys = {
|
||||
str(k): str(v)
|
||||
for k, v in raw_keys.items()
|
||||
if str(k).endswith("_API_KEY")
|
||||
}
|
||||
except Exception:
|
||||
submitted_keys = None
|
||||
|
||||
if submitted_keys is not None:
|
||||
for key, value in submitted_keys.items():
|
||||
if value:
|
||||
os.environ[key] = value
|
||||
else:
|
||||
os.environ.pop(key, None)
|
||||
else:
|
||||
# Compatibility fallback for non-desktop/manual configurations.
|
||||
keys_path = get_config_dir() / "cloud-keys.env"
|
||||
if keys_path.exists():
|
||||
for raw_line in keys_path.read_text().splitlines():
|
||||
line = raw_line.strip()
|
||||
if line and not line.startswith("#") and "=" in line:
|
||||
k, v = line.split("=", 1)
|
||||
os.environ[k.strip()] = v.strip()
|
||||
|
||||
# Try to build a fresh CloudEngine.
|
||||
try:
|
||||
|
||||
@@ -120,6 +120,54 @@ class TestChatAgents:
|
||||
assert "simple ok" in result.output
|
||||
assert "failed" not in result.output.lower()
|
||||
|
||||
def test_memory_service_started_fed_and_stopped(self) -> None:
|
||||
"""The REPL starts the memory service, submits each turn, and stops it."""
|
||||
|
||||
class _SpyMemoryService:
|
||||
def __init__(self) -> None:
|
||||
self.started = False
|
||||
self.stopped = False
|
||||
self.submissions: list[tuple[str, str]] = []
|
||||
|
||||
def start(self) -> None:
|
||||
self.started = True
|
||||
|
||||
def submit(self, user_text: str, assistant_text: str = "") -> bool:
|
||||
self.submissions.append((user_text, assistant_text))
|
||||
return True
|
||||
|
||||
def stop(self, timeout: float = 2.0) -> None:
|
||||
self.stopped = True
|
||||
|
||||
spy = _SpyMemoryService()
|
||||
engine = MagicMock()
|
||||
engine.engine_id = "mock"
|
||||
engine.generate.return_value = {"content": "engine fallback"}
|
||||
config = JarvisConfig()
|
||||
config.intelligence.default_model = "test-model"
|
||||
|
||||
AgentRegistry.register_value("simple_chat_agent", _SimpleChatAgent)
|
||||
|
||||
with (
|
||||
patch("openjarvis.cli.chat_cmd.load_config", return_value=config),
|
||||
patch("openjarvis.engine.get_engine", return_value=("mock", engine)),
|
||||
patch("openjarvis.intelligence.register_builtin_models"),
|
||||
patch(
|
||||
"openjarvis.memory.build_memory_service",
|
||||
return_value=spy,
|
||||
),
|
||||
):
|
||||
result = CliRunner().invoke(
|
||||
chat,
|
||||
["--agent", "simple_chat_agent", "--model", "test-model"],
|
||||
input="hello\n/quit\n",
|
||||
)
|
||||
|
||||
assert result.exit_code == 0
|
||||
assert spy.started is True
|
||||
assert spy.stopped is True
|
||||
assert spy.submissions == [("hello", "simple ok")]
|
||||
|
||||
def test_tool_agent_uses_legacy_agent_tools_and_prompts_confirmation(self) -> None:
|
||||
engine = MagicMock()
|
||||
engine.engine_id = "mock"
|
||||
|
||||
@@ -9,6 +9,7 @@ from click.testing import CliRunner
|
||||
|
||||
from openjarvis.cli import cli
|
||||
from openjarvis.core.registry import MemoryRegistry
|
||||
from openjarvis.memory.store import LocalFactStore
|
||||
from openjarvis.tools.storage.sqlite import SQLiteMemory
|
||||
|
||||
|
||||
@@ -108,3 +109,67 @@ def test_memory_stats_shows_count(tmp_path: Path, monkeypatch):
|
||||
assert result.exit_code == 0
|
||||
assert "2" in result.output
|
||||
backend.close()
|
||||
|
||||
|
||||
def _patch_fact_store(monkeypatch, tmp_path: Path) -> LocalFactStore:
|
||||
"""Point ``jarvis memory list/clear`` at a temp fact store."""
|
||||
mod = importlib.import_module("openjarvis.cli.memory_cmd")
|
||||
store = LocalFactStore(tmp_path / "facts.jsonl")
|
||||
monkeypatch.setattr(mod, "_get_fact_store", lambda: store)
|
||||
return store
|
||||
|
||||
|
||||
def test_memory_list_empty(tmp_path: Path, monkeypatch):
|
||||
_patch_fact_store(monkeypatch, tmp_path)
|
||||
result = CliRunner().invoke(cli, ["memory", "list"])
|
||||
assert result.exit_code == 0
|
||||
assert "No memory facts" in result.output
|
||||
|
||||
|
||||
def test_memory_list_shows_facts(tmp_path: Path, monkeypatch):
|
||||
store = _patch_fact_store(monkeypatch, tmp_path)
|
||||
store.add("User prefers dark mode")
|
||||
store.add("User lives in Berlin")
|
||||
|
||||
result = CliRunner().invoke(cli, ["memory", "list"])
|
||||
assert result.exit_code == 0
|
||||
assert "dark mode" in result.output
|
||||
assert "Berlin" in result.output
|
||||
|
||||
|
||||
def test_memory_clear_with_confirmation(tmp_path: Path, monkeypatch):
|
||||
store = _patch_fact_store(monkeypatch, tmp_path)
|
||||
store.add("fact one")
|
||||
store.add("fact two")
|
||||
|
||||
result = CliRunner().invoke(cli, ["memory", "clear"], input="y\n")
|
||||
assert result.exit_code == 0
|
||||
assert "Cleared 2" in result.output
|
||||
assert store.count() == 0
|
||||
|
||||
|
||||
def test_memory_clear_aborted(tmp_path: Path, monkeypatch):
|
||||
store = _patch_fact_store(monkeypatch, tmp_path)
|
||||
store.add("keep me")
|
||||
|
||||
result = CliRunner().invoke(cli, ["memory", "clear"], input="n\n")
|
||||
assert result.exit_code == 0
|
||||
assert "Aborted" in result.output
|
||||
assert store.count() == 1
|
||||
|
||||
|
||||
def test_memory_clear_yes_flag(tmp_path: Path, monkeypatch):
|
||||
store = _patch_fact_store(monkeypatch, tmp_path)
|
||||
store.add("fact")
|
||||
|
||||
result = CliRunner().invoke(cli, ["memory", "clear", "--yes"])
|
||||
assert result.exit_code == 0
|
||||
assert "Cleared 1" in result.output
|
||||
assert store.count() == 0
|
||||
|
||||
|
||||
def test_memory_clear_empty(tmp_path: Path, monkeypatch):
|
||||
_patch_fact_store(monkeypatch, tmp_path)
|
||||
result = CliRunner().invoke(cli, ["memory", "clear"])
|
||||
assert result.exit_code == 0
|
||||
assert "No memory facts to clear" in result.output
|
||||
|
||||
@@ -1,7 +1,14 @@
|
||||
"""Tests for Docker and deployment files."""
|
||||
"""Tests for Docker and deployment files.
|
||||
|
||||
These are static file-content checks (no Docker daemon required) so they run in
|
||||
the default CI lane. They guard the deployment hardening from #228 and its
|
||||
sub-issues (#563 image pinning, #564 systemd hardening, #565 non-root, #566
|
||||
secure Node install, #567 frozen lockfile installs).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
from pathlib import Path
|
||||
|
||||
try:
|
||||
@@ -11,6 +18,35 @@ except ModuleNotFoundError: # pragma: no cover - Python < 3.11
|
||||
|
||||
ROOT = Path(__file__).resolve().parent.parent.parent
|
||||
DOCKER_DIR = ROOT / "deploy" / "docker"
|
||||
SYSTEMD_DIR = ROOT / "deploy" / "systemd"
|
||||
|
||||
|
||||
def _dockerfiles() -> list[Path]:
|
||||
return sorted(DOCKER_DIR.glob("Dockerfile*"))
|
||||
|
||||
|
||||
def _compose_files() -> list[Path]:
|
||||
return sorted(DOCKER_DIR.glob("docker-compose*.yml"))
|
||||
|
||||
|
||||
def _from_lines(content: str) -> list[str]:
|
||||
return [
|
||||
ln.strip()
|
||||
for ln in content.splitlines()
|
||||
if ln.strip().upper().startswith("FROM ")
|
||||
]
|
||||
|
||||
|
||||
def _image_lines(content: str) -> list[str]:
|
||||
"""`image: ...` lines from a compose file, ignoring comments."""
|
||||
out = []
|
||||
for ln in content.splitlines():
|
||||
stripped = ln.strip()
|
||||
if stripped.startswith("#"):
|
||||
continue
|
||||
if stripped.startswith("image:"):
|
||||
out.append(stripped)
|
||||
return out
|
||||
|
||||
|
||||
class TestDockerFiles:
|
||||
@@ -37,10 +73,12 @@ class TestDockerFiles:
|
||||
]
|
||||
non_src_includes = [s for s in force_include if not s.startswith("src/")]
|
||||
|
||||
install_marker = 'uv pip install --system ".[server]"'
|
||||
# The project itself is built by the final `--no-deps .` install (#567);
|
||||
# the force-includes must be present before that step.
|
||||
install_marker = "uv pip install --system --no-deps ."
|
||||
wheel_dockerfiles = [
|
||||
p
|
||||
for p in sorted(DOCKER_DIR.glob("Dockerfile*"))
|
||||
for p in _dockerfiles()
|
||||
if install_marker in p.read_text() and "COPY src/ src/" in p.read_text()
|
||||
]
|
||||
# Sanity: we actually found the wheel-building Dockerfiles to guard.
|
||||
@@ -86,4 +124,142 @@ class TestDockerFiles:
|
||||
assert "ollama:" in content
|
||||
|
||||
def test_systemd_service_exists(self):
|
||||
assert (ROOT / "deploy" / "systemd" / "openjarvis.service").is_file()
|
||||
assert (SYSTEMD_DIR / "openjarvis.service").is_file()
|
||||
|
||||
|
||||
class TestImagePinning:
|
||||
"""#563 — base images and ollama pinned to fixed versions + digests."""
|
||||
|
||||
def test_no_floating_latest_tag_in_image_directives(self):
|
||||
# `:latest` only acceptable inside comments (rationale text).
|
||||
for path in _dockerfiles() + _compose_files():
|
||||
for ln in path.read_text().splitlines():
|
||||
code = ln.split("#", 1)[0]
|
||||
assert ":latest" not in code, f"{path.name}: floating :latest in {ln!r}"
|
||||
|
||||
def test_every_from_pins_a_digest(self):
|
||||
for path in _dockerfiles():
|
||||
froms = _from_lines(path.read_text())
|
||||
assert froms, f"{path.name}: no FROM lines found"
|
||||
for ln in froms:
|
||||
assert "@sha256:" in ln, (
|
||||
f"{path.name}: FROM is not digest-pinned: {ln!r}"
|
||||
)
|
||||
|
||||
def test_ollama_image_pinned_with_version_and_digest(self):
|
||||
for path in _compose_files():
|
||||
for ln in _image_lines(path.read_text()):
|
||||
if "ollama/ollama" in ln:
|
||||
assert "@sha256:" in ln, f"{path.name}: ollama not digest-pinned"
|
||||
# A concrete version tag (digits) must accompany the digest.
|
||||
assert re.search(r"ollama/ollama:\d", ln), (
|
||||
f"{path.name}: ollama missing a version tag"
|
||||
)
|
||||
|
||||
|
||||
class TestNonRootUser:
|
||||
"""#565 — GPU images (and the base image) drop root."""
|
||||
|
||||
NON_ROOT = ["Dockerfile", "Dockerfile.gpu", "Dockerfile.gpu.rocm"]
|
||||
|
||||
def test_creates_and_switches_to_non_root_user(self):
|
||||
for name in self.NON_ROOT:
|
||||
content = (DOCKER_DIR / name).read_text()
|
||||
assert "useradd" in content, f"{name}: no useradd"
|
||||
# A USER directive switching away from root must exist and not be root.
|
||||
user_lines = [
|
||||
ln.strip()
|
||||
for ln in content.splitlines()
|
||||
if ln.strip().upper().startswith("USER ")
|
||||
]
|
||||
assert user_lines, f"{name}: no USER directive"
|
||||
assert all("root" not in ln for ln in user_lines), (
|
||||
f"{name}: USER directive still root"
|
||||
)
|
||||
|
||||
def test_user_directive_is_last_stage(self):
|
||||
# USER must appear after the final FROM so the runtime stage is non-root.
|
||||
for name in self.NON_ROOT:
|
||||
content = (DOCKER_DIR / name).read_text()
|
||||
last_from = content.rfind("\nFROM ")
|
||||
user_idx = content.rfind("\nUSER ")
|
||||
assert user_idx > last_from, f"{name}: USER not in final runtime stage"
|
||||
|
||||
|
||||
class TestSandboxNodeSecurity:
|
||||
"""#566 — Node installed without an unverified curl|bash pipe."""
|
||||
|
||||
def test_no_curl_pipe_bash(self):
|
||||
content = (DOCKER_DIR / "Dockerfile.sandbox").read_text()
|
||||
for ln in content.splitlines():
|
||||
code = ln.split("#", 1)[0] # ignore the explanatory comment
|
||||
assert "| bash" not in code and "|bash" not in code, (
|
||||
f"unverified pipe-to-bash install remains: {ln!r}"
|
||||
)
|
||||
assert "nodesource.com" not in code, "still using NodeSource setup script"
|
||||
|
||||
def test_node_sourced_from_pinned_official_image(self):
|
||||
content = (DOCKER_DIR / "Dockerfile.sandbox").read_text()
|
||||
assert "COPY --from=node" in content, "Node not copied from pinned image stage"
|
||||
froms = _from_lines(content)
|
||||
assert any("node:" in ln and "@sha256:" in ln for ln in froms), (
|
||||
"no digest-pinned node base stage"
|
||||
)
|
||||
|
||||
|
||||
class TestFrozenInstall:
|
||||
"""#567 — Docker builds install from the committed, frozen uv.lock."""
|
||||
|
||||
BUILD_DOCKERFILES = [
|
||||
"Dockerfile",
|
||||
"Dockerfile.gpu",
|
||||
"Dockerfile.gpu.rocm",
|
||||
"Dockerfile.sandbox",
|
||||
]
|
||||
|
||||
def test_copies_lockfile(self):
|
||||
for name in self.BUILD_DOCKERFILES:
|
||||
content = (DOCKER_DIR / name).read_text()
|
||||
assert "uv.lock" in content, f"{name}: uv.lock not referenced"
|
||||
|
||||
def test_uses_frozen_export(self):
|
||||
for name in self.BUILD_DOCKERFILES:
|
||||
content = (DOCKER_DIR / name).read_text()
|
||||
assert "uv export --frozen" in content, f"{name}: no frozen export"
|
||||
assert "--no-deps" in content, (
|
||||
f"{name}: deps re-resolved (missing --no-deps)"
|
||||
)
|
||||
|
||||
def test_no_unpinned_pyproject_resolution(self):
|
||||
# The old `uv pip install --system ".[server]"` re-resolved deps on every
|
||||
# build; it must not come back.
|
||||
for name in self.BUILD_DOCKERFILES:
|
||||
content = (DOCKER_DIR / name).read_text()
|
||||
assert '".[server]"' not in content, (
|
||||
f"{name}: still re-resolves from pyproject"
|
||||
)
|
||||
|
||||
|
||||
class TestSystemdHardening:
|
||||
"""#564 — systemd unit ships secrets via EnvironmentFile and is sandboxed."""
|
||||
|
||||
def _service(self) -> str:
|
||||
return (SYSTEMD_DIR / "openjarvis.service").read_text()
|
||||
|
||||
def test_environment_file_for_secrets(self):
|
||||
assert "EnvironmentFile=" in self._service()
|
||||
|
||||
def test_core_hardening_directives_present(self):
|
||||
content = self._service()
|
||||
for directive in (
|
||||
"NoNewPrivileges=true",
|
||||
"ProtectSystem=strict",
|
||||
"PrivateTmp=true",
|
||||
):
|
||||
assert directive in content, f"missing hardening directive: {directive}"
|
||||
|
||||
def test_writable_state_path_declared(self):
|
||||
# ProtectSystem=strict makes the FS read-only; the working/home dir must
|
||||
# be re-granted write access or the server cannot persist config/state.
|
||||
content = self._service()
|
||||
assert "ReadWritePaths=" in content
|
||||
|
||||
@@ -0,0 +1,105 @@
|
||||
"""Tests for the LLM-backed fact extractor (openjarvis.memory.extractor)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from openjarvis.memory.extractor import FactExtractor
|
||||
|
||||
|
||||
class FakeEngine:
|
||||
"""Engine stub returning a canned completion (or raising)."""
|
||||
|
||||
def __init__(self, content="", *, raises=None):
|
||||
self._content = content
|
||||
self._raises = raises
|
||||
self.calls = []
|
||||
|
||||
def generate(self, messages, *, model, temperature=0.7, max_tokens=1024, **kwargs):
|
||||
self.calls.append((messages, model, temperature, max_tokens))
|
||||
if self._raises is not None:
|
||||
raise self._raises
|
||||
return {"content": self._content}
|
||||
|
||||
|
||||
def test_parses_json_array():
|
||||
engine = FakeEngine('["User likes coffee", "User lives in Berlin"]')
|
||||
extractor = FactExtractor(engine, "qwen3:14b")
|
||||
facts = extractor.extract("I like coffee and live in Berlin", "Noted.")
|
||||
assert facts == ["User likes coffee", "User lives in Berlin"]
|
||||
|
||||
|
||||
def test_parses_json_array_wrapped_in_prose():
|
||||
engine = FakeEngine('Sure! Here are the facts:\n["Fact A", "Fact B"]\nDone.')
|
||||
extractor = FactExtractor(engine, "m")
|
||||
assert extractor.extract("hi", "hello") == ["Fact A", "Fact B"]
|
||||
|
||||
|
||||
def test_empty_array_returns_no_facts():
|
||||
engine = FakeEngine("[]")
|
||||
extractor = FactExtractor(engine, "m")
|
||||
assert extractor.extract("just chatting", "ok") == []
|
||||
|
||||
|
||||
def test_line_fallback_for_bullets():
|
||||
engine = FakeEngine("- User is a teacher\n- User has two kids\n")
|
||||
extractor = FactExtractor(engine, "m")
|
||||
assert extractor.extract("about me", "noted") == [
|
||||
"User is a teacher",
|
||||
"User has two kids",
|
||||
]
|
||||
|
||||
|
||||
def test_dedupe_within_turn():
|
||||
engine = FakeEngine('["likes tea", "Likes Tea", "likes tea"]')
|
||||
extractor = FactExtractor(engine, "m")
|
||||
assert extractor.extract("x", "y") == ["likes tea"]
|
||||
|
||||
|
||||
def test_cap_facts_per_turn():
|
||||
items = [f'"fact {i}"' for i in range(20)]
|
||||
engine = FakeEngine("[" + ", ".join(items) + "]")
|
||||
extractor = FactExtractor(engine, "m", max_facts_per_turn=3)
|
||||
assert len(extractor.extract("x", "y")) == 3
|
||||
|
||||
|
||||
def test_truncates_long_facts():
|
||||
long_fact = "z" * 500
|
||||
engine = FakeEngine(f'["{long_fact}"]')
|
||||
extractor = FactExtractor(engine, "m", max_fact_chars=50)
|
||||
facts = extractor.extract("x", "y")
|
||||
assert len(facts) == 1
|
||||
assert len(facts[0]) == 50
|
||||
|
||||
|
||||
def test_empty_user_text_skips_engine():
|
||||
engine = FakeEngine('["should not be called"]')
|
||||
extractor = FactExtractor(engine, "m")
|
||||
assert extractor.extract(" ", "y") == []
|
||||
assert engine.calls == []
|
||||
|
||||
|
||||
def test_broken_pipe_returns_empty():
|
||||
engine = FakeEngine(raises=BrokenPipeError("client gone"))
|
||||
extractor = FactExtractor(engine, "m")
|
||||
# Must not raise — extraction is best-effort.
|
||||
assert extractor.extract("hi", "hello") == []
|
||||
|
||||
|
||||
def test_generic_exception_returns_empty():
|
||||
engine = FakeEngine(raises=RuntimeError("ollama exploded"))
|
||||
extractor = FactExtractor(engine, "m")
|
||||
assert extractor.extract("hi", "hello") == []
|
||||
|
||||
|
||||
def test_handles_non_dict_result():
|
||||
class StrEngine:
|
||||
def generate(self, *a, **k):
|
||||
return '["plain string result"]'
|
||||
|
||||
extractor = FactExtractor(StrEngine(), "m")
|
||||
assert extractor.extract("x", "y") == ["plain string result"]
|
||||
|
||||
|
||||
def test_filters_non_fact_tokens():
|
||||
engine = FakeEngine('["none", "N/A", "Real fact"]')
|
||||
extractor = FactExtractor(engine, "m")
|
||||
assert extractor.extract("x", "y") == ["Real fact"]
|
||||
@@ -0,0 +1,112 @@
|
||||
"""Tests for the persistent fact store (openjarvis.memory.store)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
|
||||
import pytest
|
||||
|
||||
from openjarvis.memory.store import LocalFactStore, create_fact_store
|
||||
|
||||
|
||||
def test_add_and_list(tmp_path):
|
||||
store = LocalFactStore(tmp_path / "facts.jsonl")
|
||||
assert store.add("User prefers concise answers") is True
|
||||
assert store.add("User lives in Berlin") is True
|
||||
|
||||
facts = store.list()
|
||||
assert [f.text for f in facts] == [
|
||||
"User prefers concise answers",
|
||||
"User lives in Berlin",
|
||||
]
|
||||
assert store.count() == 2
|
||||
|
||||
|
||||
def test_add_dedupes_case_insensitive(tmp_path):
|
||||
store = LocalFactStore(tmp_path / "facts.jsonl")
|
||||
assert store.add("Likes coffee") is True
|
||||
assert store.add("likes coffee") is False # duplicate
|
||||
assert store.count() == 1
|
||||
|
||||
|
||||
def test_add_skips_empty(tmp_path):
|
||||
store = LocalFactStore(tmp_path / "facts.jsonl")
|
||||
assert store.add("") is False
|
||||
assert store.add(" ") is False
|
||||
assert store.count() == 0
|
||||
|
||||
|
||||
def test_add_many(tmp_path):
|
||||
store = LocalFactStore(tmp_path / "facts.jsonl")
|
||||
added = store.add_many(["a", "b", "a", "c"]) # one dupe
|
||||
assert added == 3
|
||||
assert store.count() == 3
|
||||
|
||||
|
||||
def test_max_facts_evicts_oldest(tmp_path):
|
||||
store = LocalFactStore(tmp_path / "facts.jsonl", max_facts=2)
|
||||
store.add("first")
|
||||
store.add("second")
|
||||
store.add("third")
|
||||
facts = [f.text for f in store.list()]
|
||||
assert facts == ["second", "third"] # oldest dropped
|
||||
|
||||
|
||||
def test_persistence_across_instances(tmp_path):
|
||||
path = tmp_path / "facts.jsonl"
|
||||
store = LocalFactStore(path)
|
||||
store.add("durable fact")
|
||||
|
||||
reloaded = LocalFactStore(path)
|
||||
assert [f.text for f in reloaded.list()] == ["durable fact"]
|
||||
|
||||
|
||||
def test_clear(tmp_path):
|
||||
path = tmp_path / "facts.jsonl"
|
||||
store = LocalFactStore(path)
|
||||
store.add("one")
|
||||
store.add("two")
|
||||
|
||||
removed = store.clear()
|
||||
assert removed == 2
|
||||
assert store.count() == 0
|
||||
# A fresh instance also sees an empty store.
|
||||
assert LocalFactStore(path).count() == 0
|
||||
|
||||
|
||||
def test_load_skips_malformed_lines(tmp_path):
|
||||
path = tmp_path / "facts.jsonl"
|
||||
path.write_text(
|
||||
'{"text": "good fact"}\n'
|
||||
"this is not json\n"
|
||||
'{"text": ""}\n' # empty text ignored
|
||||
'{"text": "another good"}\n',
|
||||
encoding="utf-8",
|
||||
)
|
||||
store = LocalFactStore(path)
|
||||
assert [f.text for f in store.list()] == ["good fact", "another good"]
|
||||
|
||||
|
||||
def test_jsonl_round_trip_is_valid_json(tmp_path):
|
||||
path = tmp_path / "facts.jsonl"
|
||||
store = LocalFactStore(path)
|
||||
store.add("fact one", source="auto")
|
||||
|
||||
lines = [
|
||||
line for line in path.read_text(encoding="utf-8").splitlines() if line.strip()
|
||||
]
|
||||
assert len(lines) == 1
|
||||
obj = json.loads(lines[0])
|
||||
assert obj["text"] == "fact one"
|
||||
assert obj["source"] == "auto"
|
||||
assert "created_at" in obj
|
||||
|
||||
|
||||
def test_create_fact_store_local(tmp_path):
|
||||
store = create_fact_store("local", path=tmp_path / "f.jsonl", max_facts=5)
|
||||
assert isinstance(store, LocalFactStore)
|
||||
|
||||
|
||||
def test_create_fact_store_unknown_backend(tmp_path):
|
||||
with pytest.raises(ValueError):
|
||||
create_fact_store("cloud", path=tmp_path / "f.jsonl")
|
||||
@@ -0,0 +1,171 @@
|
||||
"""Tests for the background memory service (openjarvis.memory.service)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import threading
|
||||
import time
|
||||
from types import SimpleNamespace
|
||||
|
||||
from openjarvis.core.config import StorageConfig
|
||||
from openjarvis.memory.service import MemoryService, build_memory_service
|
||||
from openjarvis.memory.store import LocalFactStore
|
||||
|
||||
|
||||
def _wait_until(predicate, timeout=2.0, interval=0.01):
|
||||
deadline = time.time() + timeout
|
||||
while time.time() < deadline:
|
||||
if predicate():
|
||||
return True
|
||||
time.sleep(interval)
|
||||
return predicate()
|
||||
|
||||
|
||||
class FakeExtractor:
|
||||
"""Extractor stub with controllable output, blocking and failures."""
|
||||
|
||||
def __init__(self, facts=None, *, raises=None, gate=None):
|
||||
self._facts = facts or []
|
||||
self._raises = raises
|
||||
self._gate = gate # optional threading.Event to block on
|
||||
self.calls = []
|
||||
|
||||
def extract(self, user_text, assistant_text=""):
|
||||
self.calls.append((user_text, assistant_text))
|
||||
if self._gate is not None:
|
||||
self._gate.wait(timeout=2.0)
|
||||
if self._raises is not None:
|
||||
raise self._raises
|
||||
return list(self._facts)
|
||||
|
||||
|
||||
def _service(tmp_path, extractor, **kwargs):
|
||||
store = LocalFactStore(tmp_path / "facts.jsonl")
|
||||
return MemoryService(store, extractor, **kwargs)
|
||||
|
||||
|
||||
def test_start_stop_lifecycle(tmp_path):
|
||||
svc = _service(tmp_path, FakeExtractor())
|
||||
assert svc.is_running is False
|
||||
svc.start()
|
||||
assert svc.is_running is True
|
||||
svc.start() # idempotent
|
||||
assert svc.is_running is True
|
||||
svc.stop()
|
||||
assert svc.is_running is False
|
||||
svc.stop() # idempotent
|
||||
|
||||
|
||||
def test_submit_extracts_and_stores(tmp_path):
|
||||
extractor = FakeExtractor(["User likes hiking"])
|
||||
svc = _service(tmp_path, extractor)
|
||||
svc.start()
|
||||
try:
|
||||
assert svc.submit("I love hiking", "Nice!") is True
|
||||
assert _wait_until(lambda: svc.fact_count() == 1)
|
||||
assert [f.text for f in svc.list_facts()] == ["User likes hiking"]
|
||||
finally:
|
||||
svc.stop()
|
||||
|
||||
|
||||
def test_submit_when_not_running_is_dropped(tmp_path):
|
||||
extractor = FakeExtractor(["x"])
|
||||
svc = _service(tmp_path, extractor)
|
||||
assert svc.submit("hi", "there") is False
|
||||
assert extractor.calls == []
|
||||
|
||||
|
||||
def test_submit_empty_user_text_dropped(tmp_path):
|
||||
extractor = FakeExtractor(["x"])
|
||||
svc = _service(tmp_path, extractor)
|
||||
svc.start()
|
||||
try:
|
||||
assert svc.submit(" ", "y") is False
|
||||
finally:
|
||||
svc.stop()
|
||||
|
||||
|
||||
def test_worker_survives_extractor_broken_pipe(tmp_path):
|
||||
"""A BrokenPipeError in one job must not kill the worker."""
|
||||
extractor = FakeExtractor(raises=BrokenPipeError("client gone"))
|
||||
svc = _service(tmp_path, extractor)
|
||||
svc.start()
|
||||
try:
|
||||
svc.submit("first", "a")
|
||||
assert _wait_until(lambda: len(extractor.calls) == 1)
|
||||
# Service is still alive and accepting work.
|
||||
assert svc.is_running is True
|
||||
assert svc.submit("second", "b") is True
|
||||
assert _wait_until(lambda: len(extractor.calls) == 2)
|
||||
finally:
|
||||
svc.stop()
|
||||
|
||||
|
||||
def test_worker_survives_generic_exception(tmp_path):
|
||||
extractor = FakeExtractor(raises=RuntimeError("boom"))
|
||||
svc = _service(tmp_path, extractor)
|
||||
svc.start()
|
||||
try:
|
||||
svc.submit("x", "y")
|
||||
assert _wait_until(lambda: len(extractor.calls) == 1)
|
||||
assert svc.is_running is True
|
||||
finally:
|
||||
svc.stop()
|
||||
|
||||
|
||||
def test_submit_returns_false_when_queue_full(tmp_path):
|
||||
"""Backpressure: a full queue drops work instead of blocking the caller."""
|
||||
gate = threading.Event()
|
||||
extractor = FakeExtractor(["fact"], gate=gate)
|
||||
svc = _service(tmp_path, extractor, max_queue=1)
|
||||
svc.start()
|
||||
try:
|
||||
# First submit is pulled by the worker and blocks on the gate.
|
||||
assert svc.submit("job1", "a") is True
|
||||
assert _wait_until(lambda: len(extractor.calls) == 1)
|
||||
# Fill the (size-1) queue, then the next submit must be dropped.
|
||||
assert svc.submit("job2", "b") is True
|
||||
dropped = svc.submit("job3", "c")
|
||||
assert dropped is False
|
||||
finally:
|
||||
gate.set()
|
||||
svc.stop()
|
||||
|
||||
|
||||
def test_build_memory_service_disabled_returns_none(tmp_path):
|
||||
cfg = SimpleNamespace(memory=StorageConfig(enabled=False))
|
||||
assert build_memory_service(cfg, object(), "model") is None
|
||||
|
||||
|
||||
def test_build_memory_service_no_engine_returns_none(tmp_path):
|
||||
cfg = SimpleNamespace(memory=StorageConfig(enabled=True))
|
||||
assert build_memory_service(cfg, None, "model") is None
|
||||
|
||||
|
||||
def test_build_memory_service_no_model_returns_none(tmp_path):
|
||||
cfg = SimpleNamespace(memory=StorageConfig(enabled=True, extraction_model=""))
|
||||
assert build_memory_service(cfg, object(), "") is None
|
||||
|
||||
|
||||
def test_build_memory_service_enabled(tmp_path):
|
||||
cfg = SimpleNamespace(
|
||||
memory=StorageConfig(
|
||||
enabled=True,
|
||||
extraction_model="qwen3:14b",
|
||||
facts_path=str(tmp_path / "facts.jsonl"),
|
||||
max_facts=10,
|
||||
)
|
||||
)
|
||||
svc = build_memory_service(cfg, object(), "fallback-model")
|
||||
assert isinstance(svc, MemoryService)
|
||||
|
||||
|
||||
def test_build_memory_service_falls_back_to_default_model(tmp_path):
|
||||
cfg = SimpleNamespace(
|
||||
memory=StorageConfig(
|
||||
enabled=True,
|
||||
extraction_model="",
|
||||
facts_path=str(tmp_path / "facts.jsonl"),
|
||||
)
|
||||
)
|
||||
svc = build_memory_service(cfg, object(), "active-model")
|
||||
assert isinstance(svc, MemoryService)
|
||||
@@ -74,6 +74,68 @@ def client_with_agent():
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class _SpyMemoryService:
|
||||
"""Minimal stand-in capturing memory submissions."""
|
||||
|
||||
def __init__(self) -> None:
|
||||
self.submissions: list[tuple[str, str]] = []
|
||||
|
||||
def submit(self, user_text: str, assistant_text: str = "") -> bool:
|
||||
self.submissions.append((user_text, assistant_text))
|
||||
return True
|
||||
|
||||
def stop(self, timeout: float = 2.0) -> None:
|
||||
pass
|
||||
|
||||
|
||||
class TestMemoryServiceWiring:
|
||||
def test_non_streaming_completion_feeds_memory(self):
|
||||
engine = _make_engine(content="remembered reply")
|
||||
spy = _SpyMemoryService()
|
||||
app = create_app(engine, "test-model", memory_service=spy)
|
||||
client = TestClient(app)
|
||||
|
||||
resp = client.post(
|
||||
"/v1/chat/completions",
|
||||
json={
|
||||
"model": "test-model",
|
||||
"messages": [{"role": "user", "content": "I like jazz"}],
|
||||
},
|
||||
)
|
||||
assert resp.status_code == 200
|
||||
assert spy.submissions == [("I like jazz", "remembered reply")]
|
||||
|
||||
def test_agent_completion_feeds_memory(self):
|
||||
engine = _make_engine()
|
||||
agent = _make_agent(content="agent reply")
|
||||
spy = _SpyMemoryService()
|
||||
app = create_app(engine, "test-model", agent=agent, memory_service=spy)
|
||||
client = TestClient(app)
|
||||
|
||||
resp = client.post(
|
||||
"/v1/chat/completions",
|
||||
json={
|
||||
"model": "test-model",
|
||||
"messages": [{"role": "user", "content": "remember this"}],
|
||||
},
|
||||
)
|
||||
assert resp.status_code == 200
|
||||
assert spy.submissions == [("remember this", "agent reply")]
|
||||
|
||||
def test_no_memory_service_is_noop(self):
|
||||
engine = _make_engine()
|
||||
app = create_app(engine, "test-model") # memory_service defaults to None
|
||||
client = TestClient(app)
|
||||
resp = client.post(
|
||||
"/v1/chat/completions",
|
||||
json={
|
||||
"model": "test-model",
|
||||
"messages": [{"role": "user", "content": "Hello"}],
|
||||
},
|
||||
)
|
||||
assert resp.status_code == 200
|
||||
|
||||
|
||||
class TestChatCompletions:
|
||||
def test_basic_completion(self, client):
|
||||
resp = client.post(
|
||||
@@ -728,8 +790,25 @@ class TestCreateApp:
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def _traces_enabled_config(tmp_path):
|
||||
"""A config with traces explicitly enabled, isolated to *tmp_path*.
|
||||
|
||||
``create_app`` only builds a trace store when ``config.traces.enabled`` is
|
||||
true (server/app.py). Relying on the ambient ``load_config()`` made these
|
||||
tests fail on any machine whose ``~/.openjarvis/config.toml`` disables
|
||||
traces; pinning an explicit config + tmp db keeps them hermetic and
|
||||
parallel-safe under ``pytest -n auto``.
|
||||
"""
|
||||
from openjarvis.core.config import JarvisConfig
|
||||
|
||||
cfg = JarvisConfig()
|
||||
cfg.traces.enabled = True
|
||||
cfg.traces.db_path = str(tmp_path / "traces.db")
|
||||
return cfg
|
||||
|
||||
|
||||
class TestTraceRecording:
|
||||
def test_agent_completion_creates_trace(self):
|
||||
def test_agent_completion_creates_trace(self, tmp_path):
|
||||
"""A non-streaming agent completion records exactly one trace.
|
||||
|
||||
The collector is the single writer: it saves directly and also
|
||||
@@ -748,9 +827,10 @@ class TestTraceRecording:
|
||||
"test-model",
|
||||
agent=agent,
|
||||
bus=EventBus(record_history=False),
|
||||
config=_traces_enabled_config(tmp_path),
|
||||
)
|
||||
store = app.state.trace_store
|
||||
assert store is not None, "traces enabled by default → store should exist"
|
||||
assert store is not None, "traces explicitly enabled → store should exist"
|
||||
assert store.count() == 0
|
||||
|
||||
client = TestClient(app)
|
||||
@@ -769,10 +849,10 @@ class TestTraceRecording:
|
||||
assert trace.query == "What is 2+2?"
|
||||
assert trace.result == "traced reply"
|
||||
|
||||
def test_streaming_completion_creates_trace(self):
|
||||
def test_streaming_completion_creates_trace(self, tmp_path):
|
||||
"""A streamed completion (no agent) records the assembled response."""
|
||||
engine = _make_engine()
|
||||
app = create_app(engine, "test-model")
|
||||
app = create_app(engine, "test-model", config=_traces_enabled_config(tmp_path))
|
||||
store = app.state.trace_store
|
||||
assert store is not None
|
||||
assert store.count() == 0
|
||||
|
||||
Reference in New Issue
Block a user