fix(openhands): handle none content in token estimates (#612)

Closes #607. Assistant tool-call turns can carry content=None, which crashed token estimation (len(m.content)) and think-tag stripping. Normalize with 'content or ""', route native OpenHands truncation through the shared estimate_prompt_tokens, and add tests for the estimator, the truncation helper, and an end-to-end tool-call run with None content.

.github/clone-stats/badge.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": 1,
   "label": "Git Clones",
-  "message": "130,895",
+  "message": "137,874",
   "color": "green",
   "namedLogo": "git"
 }

.github/clone-stats/clone-data.json

@@ -1,6 +1,6 @@
 {
-  "total_clones": 130895,
-  "last_updated": "2026-06-24T07:14:43Z",
+  "total_clones": 137874,
+  "last_updated": "2026-06-29T07:46:59Z",
   "daily": {
     "2026-03-27": 2189,
     "2026-03-28": 1874,
@@ -90,6 +90,11 @@
     "2026-06-20": 1437,
     "2026-06-21": 1426,
     "2026-06-22": 1350,
-    "2026-06-23": 1468
+    "2026-06-23": 1468,
+    "2026-06-24": 1635,
+    "2026-06-25": 1640,
+    "2026-06-26": 1338,
+    "2026-06-27": 1338,
+    "2026-06-28": 1028
   }
 }

.github/workflows/docs.yml

@@ -41,6 +41,26 @@ jobs:
       - name: Install dependencies
         run: uv sync --extra docs
 
+      # Inject the public Supabase anon key so the savings leaderboard works on
+      # the published docs site. Missing/empty (e.g. fork PRs) leaves the
+      # leaderboard gracefully disabled. The key is read from env (not inlined)
+      # and JSON-encoded into a JS string literal to avoid any injection.
+      - name: Inject leaderboard Supabase anon key
+        env:
+          OPENJARVIS_LEADERBOARD_ANON: ${{ secrets.VITE_SUPABASE_ANON_KEY }}
+        run: |
+          python3 - <<'PY'
+          import json, os, pathlib
+
+          key = os.environ.get("OPENJARVIS_LEADERBOARD_ANON", "")
+          pathlib.Path("docs/javascripts/leaderboard-config.js").write_text(
+              "// Generated at docs-build time from the VITE_SUPABASE_ANON_KEY secret.\n"
+              "window.OPENJARVIS_SUPABASE_ANON_KEY = " + json.dumps(key) + ";\n",
+              encoding="utf-8",
+          )
+          print("leaderboard anon key:", "set" if key else "empty (leaderboard disabled)")
+          PY
+
       - name: Build documentation
         run: uv run mkdocs build
 

deploy/docker/Dockerfile

@@ -4,16 +4,30 @@
 
 # Stage 1: Build frontend SPA
 FROM node:22.23.0-slim@sha256:d9f850096136edbc402debdd8729579a288aac64574ada0ff4db26b6ae58b0b2 AS frontend
+# Public Supabase anon key for the savings leaderboard; empty by default so
+# the image's leaderboard stays disabled (#589). Pass --build-arg to enable.
+ARG OPENJARVIS_LEADERBOARD_PUBLIC_ANON=
 
 WORKDIR /frontend
 COPY frontend/package.json frontend/package-lock.json* ./
 RUN npm ci --ignore-scripts 2>/dev/null || npm install
 COPY frontend/ .
-RUN npm run build
+RUN VITE_SUPABASE_ANON_KEY="${OPENJARVIS_LEADERBOARD_PUBLIC_ANON}" npm run build
 
 # Stage 2: Build Python package
 FROM python:3.12.13-slim-bookworm@sha256:76d4b7b6305788c6b4c6a19d6a22a3921bf802e9af4d5e1e5bd771208dba74bf AS builder
 
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends build-essential ca-certificates curl && \
+    rm -rf /var/lib/apt/lists/*
+
+ENV PATH="/root/.cargo/bin:${PATH}"
+
+RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | \
+        sh -s -- -y --profile minimal --default-toolchain none && \
+    rustup toolchain install 1.88 --profile minimal && \
+    rustup default 1.88
+
 WORKDIR /app
 
 # Install dependencies from the committed lockfile (#567). `uv export --frozen`
@@ -24,11 +38,13 @@ WORKDIR /app
 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
+    uv pip install --system --no-deps -r requirements.txt && \
+    uv pip install --system --no-deps "maturin>=1.12.6,<2"
 
 # 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 rust/ rust/
 COPY scripts/install scripts/install
 COPY deploy/windows deploy/windows
 
@@ -36,7 +52,15 @@ COPY deploy/windows deploy/windows
 COPY --from=frontend /src/openjarvis/server/static src/openjarvis/server/static/
 
 # Install the project itself without re-resolving dependencies.
-RUN uv pip install --system --no-deps .
+RUN uv pip install --system --no-deps . && \
+    maturin build --release \
+        --manifest-path rust/crates/openjarvis-python/Cargo.toml \
+        --interpreter python3 \
+        --out /tmp/openjarvis-rust-wheel && \
+    uv pip install --system --no-deps /tmp/openjarvis-rust-wheel/*.whl && \
+    python3 -c "import openjarvis_rust; print('openjarvis_rust ok')" && \
+    python3 -m pip uninstall -y maturin && \
+    rm -rf /tmp/openjarvis-rust-wheel rust
 
 # Stage 3: Runtime
 FROM python:3.12.13-slim-bookworm@sha256:76d4b7b6305788c6b4c6a19d6a22a3921bf802e9af4d5e1e5bd771208dba74bf

deploy/docker/Dockerfile.gpu

@@ -4,20 +4,37 @@
 
 # Stage 1: Build frontend SPA
 FROM node:22.23.0-slim@sha256:d9f850096136edbc402debdd8729579a288aac64574ada0ff4db26b6ae58b0b2 AS frontend
+# Public Supabase anon key for the savings leaderboard; empty by default so
+# the image's leaderboard stays disabled (#589). Pass --build-arg to enable.
+ARG OPENJARVIS_LEADERBOARD_PUBLIC_ANON=
 
 WORKDIR /frontend
 COPY frontend/package.json frontend/package-lock.json* ./
 RUN npm ci --ignore-scripts 2>/dev/null || npm install
 COPY frontend/ .
-RUN npm run build
+RUN VITE_SUPABASE_ANON_KEY="${OPENJARVIS_LEADERBOARD_PUBLIC_ANON}" npm run build
 
 # Stage 2: Build Python package (NVIDIA CUDA 12.4)
 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 && \
+    apt-get install -y --no-install-recommends \
+        build-essential \
+        ca-certificates \
+        curl \
+        python3 \
+        python3-dev \
+        python3-pip \
+        python3-venv && \
     rm -rf /var/lib/apt/lists/*
 
+ENV PATH="/root/.cargo/bin:${PATH}"
+
+RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | \
+        sh -s -- -y --profile minimal --default-toolchain none && \
+    rustup toolchain install 1.88 --profile minimal && \
+    rustup default 1.88
+
 WORKDIR /app
 
 # Install dependencies from the committed lockfile (#567). See deploy/docker/Dockerfile
@@ -25,15 +42,25 @@ WORKDIR /app
 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
+    uv pip install --system --no-deps -r requirements.txt && \
+    uv pip install --system --no-deps "maturin>=1.12.6,<2"
 
 COPY src/ src/
+COPY rust/ rust/
 COPY scripts/install scripts/install
 COPY deploy/windows deploy/windows
 
 COPY --from=frontend /src/openjarvis/server/static src/openjarvis/server/static/
 
-RUN uv pip install --system --no-deps .
+RUN uv pip install --system --no-deps . && \
+    maturin build --release \
+        --manifest-path rust/crates/openjarvis-python/Cargo.toml \
+        --interpreter python3 \
+        --out /tmp/openjarvis-rust-wheel && \
+    uv pip install --system --no-deps /tmp/openjarvis-rust-wheel/*.whl && \
+    python3 -c "import openjarvis_rust; print('openjarvis_rust ok')" && \
+    python3 -m pip uninstall -y maturin && \
+    rm -rf /tmp/openjarvis-rust-wheel rust
 
 # Stage 3: Runtime
 FROM nvidia/cuda:12.4.0-runtime-ubuntu22.04@sha256:af8bd179ed3bf69d4b63b19a763662a6141f0f62ef099283f68d0b14b4bab0e3

deploy/docker/Dockerfile.gpu.rocm

@@ -4,20 +4,37 @@
 
 # Stage 1: Build frontend SPA
 FROM node:22.23.0-slim@sha256:d9f850096136edbc402debdd8729579a288aac64574ada0ff4db26b6ae58b0b2 AS frontend
+# Public Supabase anon key for the savings leaderboard; empty by default so
+# the image's leaderboard stays disabled (#589). Pass --build-arg to enable.
+ARG OPENJARVIS_LEADERBOARD_PUBLIC_ANON=
 
 WORKDIR /frontend
 COPY frontend/package.json frontend/package-lock.json* ./
 RUN npm ci --ignore-scripts 2>/dev/null || npm install
 COPY frontend/ .
-RUN npm run build
+RUN VITE_SUPABASE_ANON_KEY="${OPENJARVIS_LEADERBOARD_PUBLIC_ANON}" npm run build
 
 # Stage 2: Build Python package (AMD ROCm 7.2)
 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 && \
+    apt-get install -y --no-install-recommends \
+        build-essential \
+        ca-certificates \
+        curl \
+        python3 \
+        python3-dev \
+        python3-pip \
+        python3-venv && \
     rm -rf /var/lib/apt/lists/*
 
+ENV PATH="/root/.cargo/bin:${PATH}"
+
+RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | \
+        sh -s -- -y --profile minimal --default-toolchain none && \
+    rustup toolchain install 1.88 --profile minimal && \
+    rustup default 1.88
+
 WORKDIR /app
 
 # Install dependencies from the committed lockfile (#567). See deploy/docker/Dockerfile
@@ -25,15 +42,25 @@ WORKDIR /app
 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
+    uv pip install --system --no-deps -r requirements.txt && \
+    uv pip install --system --no-deps "maturin>=1.12.6,<2"
 
 COPY src/ src/
+COPY rust/ rust/
 COPY scripts/install scripts/install
 COPY deploy/windows deploy/windows
 
 COPY --from=frontend /src/openjarvis/server/static src/openjarvis/server/static/
 
-RUN uv pip install --system --no-deps .
+RUN uv pip install --system --no-deps . && \
+    maturin build --release \
+        --manifest-path rust/crates/openjarvis-python/Cargo.toml \
+        --interpreter python3 \
+        --out /tmp/openjarvis-rust-wheel && \
+    uv pip install --system --no-deps /tmp/openjarvis-rust-wheel/*.whl && \
+    python3 -c "import openjarvis_rust; print('openjarvis_rust ok')" && \
+    python3 -m pip uninstall -y maturin && \
+    rm -rf /tmp/openjarvis-rust-wheel rust
 
 # Stage 3: Runtime
 FROM rocm/dev-ubuntu-22.04:7.2@sha256:05af5f04a06b04676d4c7438997d0deadaeb7478961ad621376e199bf3aeb644

deploy/docker/Dockerfile.sandbox

@@ -7,20 +7,18 @@
 # 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
+FROM python:3.12.13-slim-bookworm@sha256:76d4b7b6305788c6b4c6a19d6a22a3921bf802e9af4d5e1e5bd771208dba74bf AS builder
 
-# 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 && \
+    apt-get install -y --no-install-recommends build-essential ca-certificates curl && \
     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
+ENV PATH="/root/.cargo/bin:${PATH}"
+
+RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | \
+        sh -s -- -y --profile minimal --default-toolchain none && \
+    rustup toolchain install 1.88 --profile minimal && \
+    rustup default 1.88
 
 WORKDIR /app
 
@@ -31,12 +29,41 @@ WORKDIR /app
 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
+    uv pip install --system --no-deps -r requirements.txt && \
+    uv pip install --system --no-deps "maturin>=1.12.6,<2"
 
 COPY . .
 
 # Install the project itself without re-resolving dependencies.
-RUN uv pip install --system --no-deps .
+RUN uv pip install --system --no-deps . && \
+    maturin build --release \
+        --manifest-path rust/crates/openjarvis-python/Cargo.toml \
+        --interpreter python3 \
+        --out /tmp/openjarvis-rust-wheel && \
+    uv pip install --system --no-deps /tmp/openjarvis-rust-wheel/*.whl && \
+    python3 -c "import openjarvis_rust; print('openjarvis_rust ok')" && \
+    python3 -m pip uninstall -y maturin && \
+    rm -rf /tmp/openjarvis-rust-wheel rust/target
+
+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/*
+
+COPY --from=builder /usr/local /usr/local
+COPY --from=builder /app /app
+
+# 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
 
 LABEL openjarvis-sandbox=true
 

docs/javascripts/leaderboard-config.js

@@ -0,0 +1,12 @@
+// Public Supabase config for the savings leaderboard.
+//
+// This file is loaded *before* leaderboard.js and supplies the anon key it
+// reads from `window.OPENJARVIS_SUPABASE_ANON_KEY`. The key is injected at
+// docs-build time from the VITE_SUPABASE_ANON_KEY repo secret (see
+// .github/workflows/docs.yml). It is intentionally empty here so that local
+// `mkdocs build` and fork pull requests — which have no secret — render the
+// graceful "Leaderboard not configured yet" message instead of failing.
+//
+// The anon key is public by design: Supabase Row-Level Security protects the
+// data, so shipping it in the public docs bundle is expected.
+window.OPENJARVIS_SUPABASE_ANON_KEY = "";

frontend/package-lock.json

@@ -11,7 +11,7 @@
         "@base-ui/react": "^1.3.0",
         "@fontsource-variable/geist": "^5.2.8",
         "@tailwindcss/vite": "^4.2.1",
-        "@tauri-apps/api": "^2",
+        "@tauri-apps/api": "^2.11.1",
         "@tauri-apps/plugin-autostart": "^2",
         "@tauri-apps/plugin-dialog": "^2.7.0",
         "@tauri-apps/plugin-global-shortcut": "^2",
@@ -42,7 +42,7 @@
         "zustand": "^5.0.11"
       },
       "devDependencies": {
-        "@tauri-apps/cli": "^2",
+        "@tauri-apps/cli": "^2.11.4",
         "@types/react": "^19.0.0",
         "@types/react-dom": "^19.0.0",
         "@vitejs/plugin-react": "^4.3.4",
@@ -3720,9 +3720,9 @@
       }
     },
     "node_modules/@tauri-apps/api": {
-      "version": "2.10.1",
-      "resolved": "https://registry.npmjs.org/@tauri-apps/api/-/api-2.10.1.tgz",
-      "integrity": "sha512-hKL/jWf293UDSUN09rR69hrToyIXBb8CjGaWC7gfinvnQrBVvnLr08FeFi38gxtugAVyVcTa5/FD/Xnkb1siBw==",
+      "version": "2.11.1",
+      "resolved": "https://registry.npmjs.org/@tauri-apps/api/-/api-2.11.1.tgz",
+      "integrity": "sha512-M2FPuYND2m+wh5hfW9ZpSdxMPdEJovPBWwoHJmwUpysTYNHaOkVFN419m/K0LIgjb/7KU2vBgsUepJWugQCvAA==",
       "license": "Apache-2.0 OR MIT",
       "funding": {
         "type": "opencollective",
@@ -3730,9 +3730,9 @@
       }
     },
     "node_modules/@tauri-apps/cli": {
-      "version": "2.10.1",
-      "resolved": "https://registry.npmjs.org/@tauri-apps/cli/-/cli-2.10.1.tgz",
-      "integrity": "sha512-jQNGF/5quwORdZSSLtTluyKQ+o6SMa/AUICfhf4egCGFdMHqWssApVgYSbg+jmrZoc8e1DscNvjTnXtlHLS11g==",
+      "version": "2.11.4",
+      "resolved": "https://registry.npmjs.org/@tauri-apps/cli/-/cli-2.11.4.tgz",
+      "integrity": "sha512-R8xGtMpwyetawSqm9kYOuMmEqkhUbvcUy8n0aNXIxollKBLESUu5f4Fx+64hgASYm1H+jSWq6jCW6zqTnH6hqQ==",
       "dev": true,
       "license": "Apache-2.0 OR MIT",
       "bin": {
@@ -3746,23 +3746,23 @@
         "url": "https://opencollective.com/tauri"
       },
       "optionalDependencies": {
-        "@tauri-apps/cli-darwin-arm64": "2.10.1",
-        "@tauri-apps/cli-darwin-x64": "2.10.1",
-        "@tauri-apps/cli-linux-arm-gnueabihf": "2.10.1",
-        "@tauri-apps/cli-linux-arm64-gnu": "2.10.1",
-        "@tauri-apps/cli-linux-arm64-musl": "2.10.1",
-        "@tauri-apps/cli-linux-riscv64-gnu": "2.10.1",
-        "@tauri-apps/cli-linux-x64-gnu": "2.10.1",
-        "@tauri-apps/cli-linux-x64-musl": "2.10.1",
-        "@tauri-apps/cli-win32-arm64-msvc": "2.10.1",
-        "@tauri-apps/cli-win32-ia32-msvc": "2.10.1",
-        "@tauri-apps/cli-win32-x64-msvc": "2.10.1"
+        "@tauri-apps/cli-darwin-arm64": "2.11.4",
+        "@tauri-apps/cli-darwin-x64": "2.11.4",
+        "@tauri-apps/cli-linux-arm-gnueabihf": "2.11.4",
+        "@tauri-apps/cli-linux-arm64-gnu": "2.11.4",
+        "@tauri-apps/cli-linux-arm64-musl": "2.11.4",
+        "@tauri-apps/cli-linux-riscv64-gnu": "2.11.4",
+        "@tauri-apps/cli-linux-x64-gnu": "2.11.4",
+        "@tauri-apps/cli-linux-x64-musl": "2.11.4",
+        "@tauri-apps/cli-win32-arm64-msvc": "2.11.4",
+        "@tauri-apps/cli-win32-ia32-msvc": "2.11.4",
+        "@tauri-apps/cli-win32-x64-msvc": "2.11.4"
       }
     },
     "node_modules/@tauri-apps/cli-darwin-arm64": {
-      "version": "2.10.1",
-      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-darwin-arm64/-/cli-darwin-arm64-2.10.1.tgz",
-      "integrity": "sha512-Z2OjCXiZ+fbYZy7PmP3WRnOpM9+Fy+oonKDEmUE6MwN4IGaYqgceTjwHucc/kEEYZos5GICve35f7ZiizgqEnQ==",
+      "version": "2.11.4",
+      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-darwin-arm64/-/cli-darwin-arm64-2.11.4.tgz",
+      "integrity": "sha512-1ryOF3ZhpZ/nemHV5zVwBQBz9jDGKmKPvWPADOhc83ig0P4bMc2iER4NbC6r9sjeIZ6RVQ4g3RZIYvezhcl4TQ==",
       "cpu": [
         "arm64"
       ],
@@ -3777,9 +3777,9 @@
       }
     },
     "node_modules/@tauri-apps/cli-darwin-x64": {
-      "version": "2.10.1",
-      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-darwin-x64/-/cli-darwin-x64-2.10.1.tgz",
-      "integrity": "sha512-V/irQVvjPMGOTQqNj55PnQPVuH4VJP8vZCN7ajnj+ZS8Kom1tEM2hR3qbbIRoS3dBKs5mbG8yg1WC+97dq17Pw==",
+      "version": "2.11.4",
+      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-darwin-x64/-/cli-darwin-x64-2.11.4.tgz",
+      "integrity": "sha512-uFsGQAAfuyz1k/yGLmkWfkBlgKAqZfxqlHmLWx81QU27RJWfmbNHCIq8T8w1e+VClleIuZUjpHWfoE4E3DLo3A==",
       "cpu": [
         "x64"
       ],
@@ -3794,9 +3794,9 @@
       }
     },
     "node_modules/@tauri-apps/cli-linux-arm-gnueabihf": {
-      "version": "2.10.1",
-      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-linux-arm-gnueabihf/-/cli-linux-arm-gnueabihf-2.10.1.tgz",
-      "integrity": "sha512-Hyzwsb4VnCWKGfTw+wSt15Z2pLw2f0JdFBfq2vHBOBhvg7oi6uhKiF87hmbXOBXUZaGkyRDkCHsdzJcIfoJC2w==",
+      "version": "2.11.4",
+      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-linux-arm-gnueabihf/-/cli-linux-arm-gnueabihf-2.11.4.tgz",
+      "integrity": "sha512-IaHZn5CdBL21oUmjiVOS1ctw6Ip1O0pjp70FwOWmYz1myWe0SY96ZIj2FYf7pT0m8bI2h/hrs5ZbEXXh44/MkQ==",
       "cpu": [
         "arm"
       ],
@@ -3811,13 +3811,16 @@
       }
     },
     "node_modules/@tauri-apps/cli-linux-arm64-gnu": {
-      "version": "2.10.1",
-      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-linux-arm64-gnu/-/cli-linux-arm64-gnu-2.10.1.tgz",
-      "integrity": "sha512-OyOYs2t5GkBIvyWjA1+h4CZxTcdz1OZPCWAPz5DYEfB0cnWHERTnQ/SLayQzncrT0kwRoSfSz9KxenkyJoTelA==",
+      "version": "2.11.4",
+      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-linux-arm64-gnu/-/cli-linux-arm64-gnu-2.11.4.tgz",
+      "integrity": "sha512-N41/ukTRVe6XSuUTESuFdGeOW2i7k62tK+6gHK5Kd5/q5RPvvi19GaWAVPPb9u95HSGmTChSolBfzynUsssFaA==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
+      "libc": [
+        "glibc"
+      ],
       "license": "Apache-2.0 OR MIT",
       "optional": true,
       "os": [
@@ -3828,13 +3831,16 @@
       }
     },
     "node_modules/@tauri-apps/cli-linux-arm64-musl": {
-      "version": "2.10.1",
-      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-linux-arm64-musl/-/cli-linux-arm64-musl-2.10.1.tgz",
-      "integrity": "sha512-MIj78PDDGjkg3NqGptDOGgfXks7SYJwhiMh8SBoZS+vfdz7yP5jN18bNaLnDhsVIPARcAhE1TlsZe/8Yxo2zqg==",
+      "version": "2.11.4",
+      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-linux-arm64-musl/-/cli-linux-arm64-musl-2.11.4.tgz",
+      "integrity": "sha512-v277UnT/fB64xAfSroL5N3Km3tLmvATWqJJw/wRI+g6o+HkeD0slyE7gOhNs1MbjE41R7bQOTxMVoL3aomUJmw==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
+      "libc": [
+        "musl"
+      ],
       "license": "Apache-2.0 OR MIT",
       "optional": true,
       "os": [
@@ -3845,13 +3851,16 @@
       }
     },
     "node_modules/@tauri-apps/cli-linux-riscv64-gnu": {
-      "version": "2.10.1",
-      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-linux-riscv64-gnu/-/cli-linux-riscv64-gnu-2.10.1.tgz",
-      "integrity": "sha512-X0lvOVUg8PCVaoEtEAnpxmnkwlE1gcMDTqfhbefICKDnOTJ5Est3qL0SrWxizDackIOKBcvtpejrSiVpuJI1kw==",
+      "version": "2.11.4",
+      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-linux-riscv64-gnu/-/cli-linux-riscv64-gnu-2.11.4.tgz",
+      "integrity": "sha512-qqgNkQ2u1yZHxjhxsZaxUtRDW8dIqIYm33rx/mzwQv0SfY9x1B+iraj8vWeFiXjjSVVhEMepXSOts1TqPzvXNQ==",
       "cpu": [
         "riscv64"
       ],
       "dev": true,
+      "libc": [
+        "glibc"
+      ],
       "license": "Apache-2.0 OR MIT",
       "optional": true,
       "os": [
@@ -3862,13 +3871,16 @@
       }
     },
     "node_modules/@tauri-apps/cli-linux-x64-gnu": {
-      "version": "2.10.1",
-      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-linux-x64-gnu/-/cli-linux-x64-gnu-2.10.1.tgz",
-      "integrity": "sha512-2/12bEzsJS9fAKybxgicCDFxYD1WEI9kO+tlDwX5znWG2GwMBaiWcmhGlZ8fi+DMe9CXlcVarMTYc0L3REIRxw==",
+      "version": "2.11.4",
+      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-linux-x64-gnu/-/cli-linux-x64-gnu-2.11.4.tgz",
+      "integrity": "sha512-2VRNWl84FOH0m2giiDkO2h0QXlcMJeX+zJDpI5kDIQAx6s+geF3v48F4DXfJez4GS/FdoDGnPnw1C2iYGbQ7bQ==",
       "cpu": [
         "x64"
       ],
       "dev": true,
+      "libc": [
+        "glibc"
+      ],
       "license": "Apache-2.0 OR MIT",
       "optional": true,
       "os": [
@@ -3879,13 +3891,16 @@
       }
     },
     "node_modules/@tauri-apps/cli-linux-x64-musl": {
-      "version": "2.10.1",
-      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-linux-x64-musl/-/cli-linux-x64-musl-2.10.1.tgz",
-      "integrity": "sha512-Y8J0ZzswPz50UcGOFuXGEMrxbjwKSPgXftx5qnkuMs2rmwQB5ssvLb6tn54wDSYxe7S6vlLob9vt0VKuNOaCIQ==",
+      "version": "2.11.4",
+      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-linux-x64-musl/-/cli-linux-x64-musl-2.11.4.tgz",
+      "integrity": "sha512-o9GyhYor/nc7xarmwDE3ka2szuW3uuZzXjHWh64Q8YX5AtSgxdQkFWzrY4O8KiGtVNvFBI14H3Q49Qj5TOIP/A==",
       "cpu": [
         "x64"
       ],
       "dev": true,
+      "libc": [
+        "musl"
+      ],
       "license": "Apache-2.0 OR MIT",
       "optional": true,
       "os": [
@@ -3896,9 +3911,9 @@
       }
     },
     "node_modules/@tauri-apps/cli-win32-arm64-msvc": {
-      "version": "2.10.1",
-      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-win32-arm64-msvc/-/cli-win32-arm64-msvc-2.10.1.tgz",
-      "integrity": "sha512-iSt5B86jHYAPJa/IlYw++SXtFPGnWtFJriHn7X0NFBVunF6zu9+/zOn8OgqIWSl8RgzhLGXQEEtGBdR4wzpVgg==",
+      "version": "2.11.4",
+      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-win32-arm64-msvc/-/cli-win32-arm64-msvc-2.11.4.tgz",
+      "integrity": "sha512-ld5Ehb598m0VkYyylRPNeCFsBe/km0jxis6KgMpl3IGY6I/i1RwQXO05I1AsXUXO2WC6AvB/Lw4qTf/asiuEiQ==",
       "cpu": [
         "arm64"
       ],
@@ -3913,9 +3928,9 @@
       }
     },
     "node_modules/@tauri-apps/cli-win32-ia32-msvc": {
-      "version": "2.10.1",
-      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-win32-ia32-msvc/-/cli-win32-ia32-msvc-2.10.1.tgz",
-      "integrity": "sha512-gXyxgEzsFegmnWywYU5pEBURkcFN/Oo45EAwvZrHMh+zUSEAvO5E8TXsgPADYm31d1u7OQU3O3HsYfVBf2moHw==",
+      "version": "2.11.4",
+      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-win32-ia32-msvc/-/cli-win32-ia32-msvc-2.11.4.tgz",
+      "integrity": "sha512-12Hxi0XX/H5VFxO/bGgHkFWhml9VMgEOu9CidjeCeTNQ1l6fpUlbiGgSP7CLI3PFtW9/FfbeHieZ+kyWK5H7CA==",
       "cpu": [
         "ia32"
       ],
@@ -3930,9 +3945,9 @@
       }
     },
     "node_modules/@tauri-apps/cli-win32-x64-msvc": {
-      "version": "2.10.1",
-      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-win32-x64-msvc/-/cli-win32-x64-msvc-2.10.1.tgz",
-      "integrity": "sha512-6Cn7YpPFwzChy0ERz6djKEmUehWrYlM+xTaNzGPgZocw3BD7OfwfWHKVWxXzdjEW2KfKkHddfdxK1XXTYqBRLg==",
+      "version": "2.11.4",
+      "resolved": "https://registry.npmjs.org/@tauri-apps/cli-win32-x64-msvc/-/cli-win32-x64-msvc-2.11.4.tgz",
+      "integrity": "sha512-+vDiqBIU5dMISg/wNvX3sF+ZHfgJGJ5T0AcO+EHNXV9GGAG+P5fzodlDXD3QdKCRgZxMoCm5PPvj3BqLNjBthw==",
       "cpu": [
         "x64"
       ],

frontend/package.json

@@ -18,7 +18,7 @@
     "@base-ui/react": "^1.3.0",
     "@fontsource-variable/geist": "^5.2.8",
     "@tailwindcss/vite": "^4.2.1",
-    "@tauri-apps/api": "^2",
+    "@tauri-apps/api": "^2.11.1",
     "@tauri-apps/plugin-autostart": "^2",
     "@tauri-apps/plugin-dialog": "^2.7.0",
     "@tauri-apps/plugin-global-shortcut": "^2",
@@ -49,7 +49,7 @@
     "zustand": "^5.0.11"
   },
   "devDependencies": {
-    "@tauri-apps/cli": "^2",
+    "@tauri-apps/cli": "^2.11.4",
     "@types/react": "^19.0.0",
     "@types/react-dom": "^19.0.0",
     "@vitejs/plugin-react": "^4.3.4",

frontend/src-tauri/src/lib.rs

@@ -9,7 +9,7 @@ use tokio::sync::Mutex;
 const OLLAMA_PORT: u16 = 11434;
 const JARVIS_PORT: u16 = 8000;
 
-/// Small, fast model pulled at startup so the app opens quickly.
+/// Small, fast model used when startup needs a default Ollama tag.
 const STARTUP_MODEL: &str = "qwen3.5:4b";
 
 /// Tiny fallback model if even the startup model can't be pulled.
@@ -104,7 +104,7 @@ fn default_local_model(ram_gb: f64) -> &'static str {
 struct BootPlan {
     /// Whether to start and wait for the bundled Ollama.
     launch_ollama: bool,
-    /// The single Ollama model to pull (None for custom endpoints).
+    /// The preferred Ollama model (None for custom endpoints).
     model_to_pull: Option<String>,
     /// Optional `(engine_key, bare_host)` override for a custom endpoint,
     /// e.g. `("lmstudio", "http://localhost:1234")`. Written into
@@ -608,6 +608,69 @@ async fn wait_for_jarvis_health(
 }
 
 async fn ollama_has_model(model: &str) -> bool {
+    let models = ollama_model_names().await;
+    matching_installed_model(&models, model).is_some()
+}
+
+fn parse_ollama_model_names(body: &serde_json::Value) -> Vec<String> {
+    body.get("models")
+        .and_then(|m| m.as_array())
+        .map(|models| {
+            models
+                .iter()
+                .filter_map(|m| {
+                    m.get("name")
+                        .or_else(|| m.get("model"))
+                        .and_then(|n| n.as_str())
+                })
+                .filter(|name| !name.trim().is_empty())
+                .map(|name| name.to_string())
+                .collect()
+        })
+        .unwrap_or_default()
+}
+
+fn model_names_match(installed: &str, requested: &str) -> bool {
+    installed == requested
+        || installed.strip_suffix(":latest") == Some(requested)
+        || requested.strip_suffix(":latest") == Some(installed)
+}
+
+fn matching_installed_model(models: &[String], requested: &str) -> Option<String> {
+    models
+        .iter()
+        .find(|model| model_names_match(model, requested))
+        .cloned()
+}
+
+fn model_name_looks_embedding_only(model: &str) -> bool {
+    let name = model.to_ascii_lowercase();
+    ["embed", "embedding", "rerank", "minilm", "bge-", "bge_", "e5-", "e5_"]
+        .iter()
+        .any(|marker| name.contains(marker))
+}
+
+fn preferred_installed_model(models: &[String]) -> Option<String> {
+    models
+        .iter()
+        .find(|model| !model.trim().is_empty() && !model_name_looks_embedding_only(model))
+        .or_else(|| models.iter().find(|model| !model.trim().is_empty()))
+        .cloned()
+}
+
+fn startup_installed_model(requested_model: &str, installed_models: &[String]) -> Option<String> {
+    matching_installed_model(installed_models, requested_model)
+        .or_else(|| preferred_installed_model(installed_models))
+}
+
+fn should_persist_resolved_model(cfg: &InferenceConfig) -> bool {
+    cfg.model
+        .as_deref()
+        .map(|model| model.trim().is_empty())
+        .unwrap_or(true)
+}
+
+async fn ollama_model_names() -> Vec<String> {
     let url = format!("http://127.0.0.1:{}/api/tags", OLLAMA_PORT);
     let client = reqwest::Client::builder()
         .timeout(Duration::from_secs(5))
@@ -615,21 +678,10 @@ async fn ollama_has_model(model: &str) -> bool {
         .unwrap();
     if let Ok(resp) = client.get(&url).send().await {
         if let Ok(body) = resp.json::<serde_json::Value>().await {
-            if let Some(models) = body.get("models").and_then(|m| m.as_array()) {
-                return models.iter().any(|m| {
-                    m.get("name")
-                        .and_then(|n| n.as_str())
-                        .map(|n| {
-                            n == model
-                                || n.strip_suffix(":latest") == Some(model)
-                                || model.strip_suffix(":latest") == Some(n)
-                        })
-                        .unwrap_or(false)
-                });
-            }
+            return parse_ollama_model_names(&body);
         }
     }
-    false
+    Vec::new()
 }
 
 async fn pull_model(model: &str) -> Result<(), String> {
@@ -751,7 +803,7 @@ async fn boot_backend(backend: SharedBackend, status: SharedStatus) {
         .into();
     }
 
-    // For the Ollama path, the model pull may fall back to FALLBACK_MODEL; we
+    // For the Ollama path, model resolution may fall back to FALLBACK_MODEL; we
     // record what is actually available here so the serve command below uses
     // it instead of the originally-planned tag. None on the custom path.
     let mut serve_model_override: Option<String> = None;
@@ -798,8 +850,8 @@ async fn boot_backend(backend: SharedBackend, status: SharedStatus) {
             s.detail = "Inference engine ready.".into();
         }
 
-        // Phase 2: Pull the single default model (see default_local_model /
-        // boot_plan). We deliberately do NOT pull any others.
+        // Phase 2: Resolve one model to serve. Prefer an installed model on
+        // first run so startup does not depend on a download succeeding.
         let model = plan
             .model_to_pull
             .clone()
@@ -810,41 +862,63 @@ async fn boot_backend(backend: SharedBackend, status: SharedStatus) {
             s.detail = format!("Checking for {}...", model);
         }
 
-        if !ollama_has_model(&model).await {
+        let installed_models = ollama_model_names().await;
+        let resolved_model = if let Some(installed) = startup_installed_model(&model, &installed_models) {
+            installed
+        } else {
             {
                 let mut s = status.lock().await;
                 s.detail = format!("Downloading {}... (this may take a minute)", model);
             }
-            if let Err(e) = pull_model(&model).await {
-                // If the chosen model fails, try the tiny fallback
-                eprintln!("Warning: failed to pull {}: {}", model, e);
-                if !ollama_has_model(FALLBACK_MODEL).await {
-                    {
-                        let mut s = status.lock().await;
-                        s.detail = format!("Downloading {}...", FALLBACK_MODEL);
-                    }
-                    if let Err(e2) = pull_model(FALLBACK_MODEL).await {
-                        let mut s = status.lock().await;
-                        s.error = Some(format!("Failed to download model: {}", e2));
-                        return;
+            match pull_model(&model).await {
+                Ok(()) => model.clone(),
+                Err(e) => {
+                    eprintln!("Warning: failed to pull {}: {}", model, e);
+
+                    // If a local model appeared while pulling, use it instead of
+                    // making startup depend on another network pull.
+                    if let Some(installed) = preferred_installed_model(&ollama_model_names().await) {
+                        installed
+                    } else if ollama_has_model(FALLBACK_MODEL).await {
+                        FALLBACK_MODEL.to_string()
+                    } else {
+                        {
+                            let mut s = status.lock().await;
+                            s.detail = format!("Downloading {}...", FALLBACK_MODEL);
+                        }
+                        if let Err(e2) = pull_model(FALLBACK_MODEL).await {
+                            if let Some(installed) =
+                                preferred_installed_model(&ollama_model_names().await)
+                            {
+                                installed
+                            } else {
+                                let mut s = status.lock().await;
+                                s.error = Some(format!("Failed to download model: {}", e2));
+                                return;
+                            }
+                        } else {
+                            FALLBACK_MODEL.to_string()
+                        }
                     }
                 }
             }
+        };
+
+        if resolved_model != model {
+            let mut s = status.lock().await;
+            s.detail = format!("Using installed model {}.", resolved_model);
         }
 
-        // The pull may have fallen back to FALLBACK_MODEL; serve and persist
-        // whatever is actually available now, not the originally-planned tag.
-        let resolved_model = if ollama_has_model(&model).await {
-            model
-        } else {
-            FALLBACK_MODEL.to_string()
-        };
         serve_model_override = Some(resolved_model.clone());
 
-        // Persist the resolved model so Settings shows it and future boots reuse it.
-        let mut persisted = cfg.clone();
-        persisted.model = Some(resolved_model);
-        let _ = write_inference_config(&persisted);
+        // Persist only first-run/default resolution. If the user explicitly
+        // configured a model, do not overwrite that choice with a temporary
+        // fallback selected just to keep startup nonfatal.
+        if should_persist_resolved_model(&cfg) {
+            let mut persisted = cfg.clone();
+            persisted.model = Some(resolved_model);
+            let _ = write_inference_config(&persisted);
+        }
 
         {
             let mut s = status.lock().await;
@@ -2647,8 +2721,10 @@ pub fn run() {
 mod tests {
     use super::{
         boot_plan, default_local_model, format_uv_sync_failure, format_uv_sync_spawn_error,
-        normalize_host, parse_inference_config, upsert_engine_host, uv_sync_stderr_tail,
-        InferenceConfig, SourceKind,
+        matching_installed_model, model_names_match, normalize_host, parse_inference_config,
+        parse_ollama_model_names, preferred_installed_model, should_persist_resolved_model,
+        startup_installed_model,
+        upsert_engine_host, uv_sync_stderr_tail, InferenceConfig, SourceKind,
     };
     use std::path::Path;
 
@@ -2730,6 +2806,97 @@ mod tests {
         assert_eq!(default_local_model(1.0), super::FALLBACK_MODEL);
     }
 
+    #[test]
+    fn parse_ollama_model_names_reads_nonempty_names() {
+        let body = serde_json::json!({
+            "models": [
+                {"name": "llama3.2:latest"},
+                {"name": ""},
+                {"name": "qwen3.5:4b"},
+                {"model": "mistral:latest"}
+            ]
+        });
+        assert_eq!(
+            parse_ollama_model_names(&body),
+            vec![
+                "llama3.2:latest".to_string(),
+                "qwen3.5:4b".to_string(),
+                "mistral:latest".to_string()
+            ]
+        );
+    }
+
+    #[test]
+    fn model_names_match_treats_latest_as_optional() {
+        assert!(model_names_match("llama3.2:latest", "llama3.2"));
+        assert!(model_names_match("llama3.2", "llama3.2:latest"));
+        assert!(model_names_match("qwen3.5:4b", "qwen3.5:4b"));
+        assert!(!model_names_match("llama3.2:latest", "qwen3.5:4b"));
+    }
+
+    #[test]
+    fn installed_model_helpers_pick_matching_or_first_model() {
+        let models = vec!["llama3.2:latest".to_string(), "qwen3.5:4b".to_string()];
+        assert_eq!(
+            matching_installed_model(&models, "llama3.2"),
+            Some("llama3.2:latest".to_string())
+        );
+        assert_eq!(
+            preferred_installed_model(&models),
+            Some("llama3.2:latest".to_string())
+        );
+    }
+
+    #[test]
+    fn preferred_installed_model_skips_embedding_names_when_chat_model_exists() {
+        let models = vec![
+            "nomic-embed-text:latest".to_string(),
+            "llama3.2:latest".to_string(),
+        ];
+        assert_eq!(
+            preferred_installed_model(&models),
+            Some("llama3.2:latest".to_string())
+        );
+    }
+
+    #[test]
+    fn startup_installed_model_uses_existing_model_for_defaults() {
+        let models = vec!["llama3.2:latest".to_string()];
+        assert_eq!(
+            startup_installed_model("qwen3.5:4b", &models),
+            Some("llama3.2:latest".to_string())
+        );
+    }
+
+    #[test]
+    fn startup_installed_model_uses_existing_model_when_configured_model_missing() {
+        let models = vec!["llama3.2:latest".to_string()];
+        assert_eq!(
+            startup_installed_model("qwen3.5:4b", &models),
+            Some("llama3.2:latest".to_string())
+        );
+    }
+
+    #[test]
+    fn resolved_model_is_only_persisted_when_no_model_was_configured() {
+        let default_cfg = InferenceConfig { kind: SourceKind::Ollama, ..Default::default() };
+        assert!(should_persist_resolved_model(&default_cfg));
+
+        let empty_cfg = InferenceConfig {
+            kind: SourceKind::Ollama,
+            model: Some(" ".into()),
+            ..Default::default()
+        };
+        assert!(should_persist_resolved_model(&empty_cfg));
+
+        let user_cfg = InferenceConfig {
+            kind: SourceKind::Ollama,
+            model: Some("qwen3.5:9b".into()),
+            ..Default::default()
+        };
+        assert!(!should_persist_resolved_model(&user_cfg));
+    }
+
     #[test]
     fn parse_defaults_to_ollama_when_file_missing_or_garbage() {
         assert!(matches!(parse_inference_config("").kind, SourceKind::Ollama));

mkdocs.yml

@@ -127,6 +127,7 @@ markdown_extensions:
   - pymdownx.tilde
 
 extra_javascript:
+  - javascripts/leaderboard-config.js
   - javascripts/leaderboard.js
   - https://cdn.jsdelivr.net/npm/@docsearch/js@3
   - javascripts/docsearch-init.js

src/openjarvis/agents/native_openhands.py

@@ -19,6 +19,7 @@ from openjarvis.agents.prompt_loader import (
 from openjarvis.core.events import EventBus
 from openjarvis.core.registry import AgentRegistry
 from openjarvis.core.types import Message, Role, ToolCall, ToolResult
+from openjarvis.engine._base import estimate_prompt_tokens
 from openjarvis.engine._stubs import InferenceEngine
 from openjarvis.tools._stubs import BaseTool, build_tool_descriptions
 
@@ -116,8 +117,7 @@ class NativeOpenHandsAgent(ToolUsingAgent):
         max_prompt_tokens: int = 3000,
     ) -> list[Message]:
         """Truncate messages if estimated token count exceeds limit."""
-        total_chars = sum(len(m.content) for m in messages)
-        estimated_tokens = total_chars // 4
+        estimated_tokens = estimate_prompt_tokens(messages)
         if estimated_tokens <= max_prompt_tokens:
             return messages
         # Find the last user message and truncate its content
@@ -125,7 +125,7 @@ class NativeOpenHandsAgent(ToolUsingAgent):
             if messages[i].role == Role.USER:
                 excess_tokens = estimated_tokens - max_prompt_tokens
                 excess_chars = excess_tokens * 4
-                original = messages[i].content
+                original = messages[i].content or ""
                 if len(original) > excess_chars + 200:
                     truncated = original[: len(original) - excess_chars]
                     messages[i] = Message(
@@ -258,7 +258,7 @@ class NativeOpenHandsAgent(ToolUsingAgent):
                 # still emitted before re-raising.
                 self._emit_turn_end(turns=1, error=True)
                 raise
-            content = self._strip_think_tags(result.get("content", ""))
+            content = self._strip_think_tags(result.get("content") or "")
             usage = result.get("usage", {})
             self._emit_turn_end(turns=1)
             return AgentResult(
@@ -315,7 +315,7 @@ class NativeOpenHandsAgent(ToolUsingAgent):
             for k in total_usage:
                 total_usage[k] += usage.get(k, 0)
 
-            content = result.get("content", "")
+            content = result.get("content") or ""
             # Strip think tags so they don't interfere with parsing
             content = self._strip_think_tags(content)
             last_content = content

src/openjarvis/cli/chat_cmd.py

@@ -11,7 +11,9 @@ from rich.markdown import Markdown
 
 from openjarvis.cli._tool_names import resolve_tool_names
 from openjarvis.core.config import load_config
+from openjarvis.core.events import EventBus
 from openjarvis.core.types import Message, Role
+from openjarvis.memory import publish_completed_exchange
 
 
 def _read_input(prompt: str = "You> ") -> Optional[str]:
@@ -57,6 +59,7 @@ def chat(
     console = Console(stderr=True)
 
     config = load_config()
+    bus = EventBus(record_history=False)
 
     import dataclasses as _dc
 
@@ -97,12 +100,11 @@ def chat(
     if agent_key and agent_key != "none":
         try:
             import openjarvis.agents  # noqa: F401 — trigger registration
-            from openjarvis.core.events import EventBus
             from openjarvis.core.registry import AgentRegistry
 
             if AgentRegistry.contains(agent_key):
                 agent_cls = AgentRegistry.get(agent_key)
-                kwargs: dict = {"bus": EventBus()}
+                kwargs: dict = {"bus": bus}
 
                 if getattr(agent_cls, "accepts_tools", False):
                     tool_names_list = resolve_tool_names(
@@ -184,7 +186,7 @@ def chat(
     try:
         from openjarvis.memory import build_memory_service
 
-        memory_service = build_memory_service(config, engine, model)
+        memory_service = build_memory_service(config, engine, model, event_bus=bus)
         if memory_service is not None:
             memory_service.start()
             console.print("[dim]  Memory: active[/dim]")
@@ -280,9 +282,12 @@ def chat(
             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)
+            publish_completed_exchange(
+                bus,
+                user_input,
+                content,
+                source="cli.chat",
+            )
         except KeyboardInterrupt:
             console.print("\n[dim]Generation interrupted.[/dim]")
         except Exception as exc:

src/openjarvis/cli/serve.py

@@ -498,7 +498,12 @@ def serve(
     try:
         from openjarvis.memory import build_memory_service
 
-        memory_service = build_memory_service(config, engine, model_name)
+        memory_service = build_memory_service(
+            config,
+            engine,
+            model_name,
+            event_bus=bus,
+        )
         if memory_service is not None:
             memory_service.start()
             console.print("  Memory svc: [cyan]active[/cyan]")

src/openjarvis/core/config.py

@@ -932,7 +932,9 @@ class StorageConfig:
     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")
+    facts_path: str = field(
+        default_factory=lambda: str(get_config_dir() / "memory_facts.jsonl")
+    )
 
 
 # Backward-compatibility alias

src/openjarvis/core/events.py

@@ -27,6 +27,7 @@ class EventType(str, Enum):
     TOOL_CALL_END = "tool_call_end"
     MEMORY_STORE = "memory_store"
     MEMORY_RETRIEVE = "memory_retrieve"
+    CHAT_EXCHANGE_COMPLETED = "chat_exchange_completed"
     AGENT_TURN_START = "agent_turn_start"
     AGENT_TURN_END = "agent_turn_end"
     TELEMETRY_RECORD = "telemetry_record"

src/openjarvis/core/registry.py

@@ -11,6 +11,7 @@ from typing import TYPE_CHECKING, Any, Callable, Dict, Generic, Tuple, Type, Typ
 if TYPE_CHECKING:
     from openjarvis.agents._stubs import BaseAgent
     from openjarvis.engine._stubs import InferenceEngine
+    from openjarvis.memory.store import FactStore
     from openjarvis.tools.storage._stubs import MemoryBackend
 
 T = TypeVar("T")
@@ -109,6 +110,10 @@ class MemoryRegistry(RegistryBase[Type["MemoryBackend"]]):
     """Registry for memory / retrieval backends."""
 
 
+class FactStoreRegistry(RegistryBase[Type["FactStore"]]):
+    """Registry for automatic-memory fact store backends."""
+
+
 class AgentRegistry(RegistryBase[Type["BaseAgent"]]):
     """Registry for agent implementations."""
 
@@ -170,6 +175,7 @@ __all__ = [
     "CompressionRegistry",
     "ConnectorRegistry",
     "EngineRegistry",
+    "FactStoreRegistry",
     "LearningRegistry",
     "MemoryRegistry",
     "MinerRegistry",

src/openjarvis/engine/_base.py

@@ -55,7 +55,7 @@ def estimate_prompt_tokens(messages: Sequence[Message]) -> int:
     Uses ~4 characters per token (standard BPE average for English) plus
     a small per-message overhead for role markers and separators.
     """
-    total_chars = sum(len(m.content) for m in messages)
+    total_chars = sum(len(m.content or "") for m in messages)
     # ~4 tokens overhead per message for role markers / separators
     overhead = len(messages) * 4
     return max(1, total_chars // 4 + overhead)

src/openjarvis/memory/__init__.py

@@ -9,7 +9,11 @@ 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.service import (
+    MemoryService,
+    build_memory_service,
+    publish_completed_exchange,
+)
 from openjarvis.memory.store import (
     Fact,
     FactStore,
@@ -25,4 +29,5 @@ __all__ = [
     "MemoryService",
     "build_memory_service",
     "create_fact_store",
+    "publish_completed_exchange",
 ]

src/openjarvis/memory/service.py

@@ -20,6 +20,7 @@ import queue
 import threading
 from typing import Any, List, Optional
 
+from openjarvis.core.events import Event, EventBus, EventType
 from openjarvis.memory.extractor import FactExtractor
 from openjarvis.memory.store import Fact, FactStore, create_fact_store
 
@@ -37,10 +38,13 @@ class MemoryService:
         store: FactStore,
         extractor: FactExtractor,
         *,
+        event_bus: EventBus | None = None,
         max_queue: int = 256,
     ) -> None:
         self._store = store
         self._extractor = extractor
+        self._event_bus = event_bus
+        self._subscribed = False
         self._queue: "queue.Queue[Any]" = queue.Queue(maxsize=max(1, max_queue))
         self._thread: Optional[threading.Thread] = None
         self._running = threading.Event()
@@ -52,6 +56,7 @@ class MemoryService:
         if self._running.is_set():
             return
         self._running.set()
+        self._subscribe_events()
         self._thread = threading.Thread(
             target=self._loop,
             name="memory-service",
@@ -73,6 +78,7 @@ class MemoryService:
         if thread is not None:
             thread.join(timeout=timeout)
         self._thread = None
+        self._unsubscribe_events()
         logger.debug("Memory service stopped")
 
     @property
@@ -99,6 +105,34 @@ class MemoryService:
             logger.debug("Memory service queue full; dropping exchange")
             return False
 
+    def _subscribe_events(self) -> None:
+        """Subscribe to lifecycle events that feed automatic memory."""
+        if self._event_bus is None or self._subscribed:
+            return
+        self._event_bus.subscribe(
+            EventType.CHAT_EXCHANGE_COMPLETED,
+            self._on_completed_exchange,
+        )
+        self._subscribed = True
+
+    def _unsubscribe_events(self) -> None:
+        """Unsubscribe from lifecycle events (idempotent)."""
+        if self._event_bus is None or not self._subscribed:
+            return
+        self._event_bus.unsubscribe(
+            EventType.CHAT_EXCHANGE_COMPLETED,
+            self._on_completed_exchange,
+        )
+        self._subscribed = False
+
+    def _on_completed_exchange(self, event: Event) -> None:
+        """Queue a completed chat exchange published on the event bus."""
+        data = event.data or {}
+        self.submit(
+            str(data.get("user_text", "") or ""),
+            str(data.get("assistant_text", "") or ""),
+        )
+
     # -- worker -------------------------------------------------------------
 
     def _loop(self) -> None:
@@ -145,6 +179,8 @@ def build_memory_service(
     config: Any,
     engine: Any,
     default_model: str = "",
+    *,
+    event_bus: EventBus | None = None,
 ) -> Optional[MemoryService]:
     """Build a :class:`MemoryService` from config, or ``None`` if disabled.
 
@@ -170,11 +206,32 @@ def build_memory_service(
 
     store = create_fact_store(
         getattr(mem, "backend", "local"),
-        path=getattr(mem, "facts_path", "~/.openjarvis/memory_facts.jsonl"),
+        path=getattr(mem, "facts_path", None),
         max_facts=getattr(mem, "max_facts", 1000),
     )
     extractor = FactExtractor(engine, model)
-    return MemoryService(store, extractor)
+    return MemoryService(store, extractor, event_bus=event_bus)
 
 
-__all__ = ["MemoryService", "build_memory_service"]
+def publish_completed_exchange(
+    bus: EventBus | None,
+    user_text: str,
+    assistant_text: str = "",
+    *,
+    source: str = "",
+) -> bool:
+    """Publish a completed chat exchange for lifecycle subscribers."""
+    if bus is None or not user_text or not user_text.strip():
+        return False
+    bus.publish(
+        EventType.CHAT_EXCHANGE_COMPLETED,
+        {
+            "user_text": user_text,
+            "assistant_text": assistant_text or "",
+            "source": source,
+        },
+    )
+    return True
+
+
+__all__ = ["MemoryService", "build_memory_service", "publish_completed_exchange"]

src/openjarvis/memory/store.py

@@ -18,6 +18,14 @@ from dataclasses import asdict, dataclass
 from pathlib import Path
 from typing import Iterable, List
 
+from openjarvis.core.paths import get_config_dir
+from openjarvis.core.registry import FactStoreRegistry
+
+
+def _default_fact_path() -> Path:
+    """Return the env-aware default JSONL path for automatic memory facts."""
+    return get_config_dir() / "memory_facts.jsonl"
+
 
 @dataclass(slots=True)
 class Fact:
@@ -56,6 +64,7 @@ class FactStore(ABC):
         """Return the number of stored facts."""
 
 
+@FactStoreRegistry.register("local")
 class LocalFactStore(FactStore):
     """Append-only JSONL fact store on the local filesystem.
 
@@ -67,11 +76,13 @@ class LocalFactStore(FactStore):
 
     def __init__(
         self,
-        path: str | Path = "~/.openjarvis/memory_facts.jsonl",
+        path: str | Path | None = None,
         *,
         max_facts: int = 1000,
     ) -> None:
-        self._path = Path(path).expanduser()
+        self._path = (
+            Path(path).expanduser() if path is not None else _default_fact_path()
+        )
         self._max_facts = max(0, int(max_facts))
         self._lock = threading.Lock()
         self._facts: List[Fact] = self._load()
@@ -116,6 +127,10 @@ class LocalFactStore(FactStore):
         tmp.write_text(payload, encoding="utf-8")
         os.replace(tmp, self._path)
 
+    def _sync_from_disk_locked(self) -> None:
+        """Refresh in-memory facts from disk while holding ``self._lock``."""
+        self._facts = self._load()
+
     # -- FactStore API ------------------------------------------------------
 
     def add(self, text: str, source: str = "") -> bool:
@@ -123,6 +138,7 @@ class LocalFactStore(FactStore):
         if not text:
             return False
         with self._lock:
+            self._sync_from_disk_locked()
             lowered = text.lower()
             if any(f.text.lower() == lowered for f in self._facts):
                 return False  # dedupe
@@ -135,10 +151,12 @@ class LocalFactStore(FactStore):
 
     def list(self) -> List[Fact]:
         with self._lock:
+            self._sync_from_disk_locked()
             return list(self._facts)
 
     def clear(self) -> int:
         with self._lock:
+            self._sync_from_disk_locked()
             removed = len(self._facts)
             self._facts = []
             if self._path.exists():
@@ -150,6 +168,7 @@ class LocalFactStore(FactStore):
 
     def count(self) -> int:
         with self._lock:
+            self._sync_from_disk_locked()
             return len(self._facts)
 
     @property
@@ -158,22 +177,32 @@ class LocalFactStore(FactStore):
         return self._path
 
 
+def _ensure_fact_store_backends_registered() -> None:
+    """Restore built-in fact-store registrations if a test cleared registries."""
+    if not FactStoreRegistry.contains("local"):
+        FactStoreRegistry.register_value("local", LocalFactStore)
+
+
 def create_fact_store(
     backend: str = "local",
     *,
-    path: str | Path = "~/.openjarvis/memory_facts.jsonl",
+    path: str | Path | None = None,
     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.
+    registry-backed constructor exists so additional backends can be added
+    without changing the service or CLI wiring.
     """
+    _ensure_fact_store_backends_registered()
     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")
+    if not FactStoreRegistry.contains(key):
+        supported = ", ".join(FactStoreRegistry.keys())
+        raise ValueError(
+            f"Unknown memory backend '{backend}'. Supported backends: {supported}"
+        )
+    return FactStoreRegistry.create(key, path, max_facts=max_facts)
 
 
 __all__ = ["Fact", "FactStore", "LocalFactStore", "create_fact_store"]

src/openjarvis/server/routes.py

@@ -195,7 +195,13 @@ async def chat_completions(request_body: ChatCompletionRequest, request: Request
         # from the engine for true real-time output.
         if request_body.tools:
             return await _handle_stream_tools(
-                engine, model, request_body, complexity_info, app_config=config
+                engine,
+                model,
+                request_body,
+                complexity_info,
+                app_config=config,
+                bus=getattr(request.app.state, "bus", None),
+                memory_service=getattr(request.app.state, "memory_service", None),
             )
         return await _handle_stream(
             engine,
@@ -204,6 +210,8 @@ async def chat_completions(request_body: ChatCompletionRequest, request: Request
             complexity_info,
             trace_store=getattr(request.app.state, "trace_store", None),
             app_config=config,
+            bus=getattr(request.app.state, "bus", None),
+            memory_service=getattr(request.app.state, "memory_service", None),
         )
 
     # Non-streaming: use agent if available, otherwise direct engine call.
@@ -247,20 +255,44 @@ async def chat_completions(request_body: ChatCompletionRequest, request: Request
         getattr(request.app.state, "memory_service", None),
         query_text_for_complexity,
         response,
+        bus=getattr(request.app.state, "bus", None),
+        source="server.chat",
     )
     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:
+def _response_content(response) -> str:
+    """Extract assistant text from an OpenAI-compatible response object."""
+    content = ""
+    choices = getattr(response, "choices", None)
+    if choices:
+        content = getattr(choices[0].message, "content", "") or ""
+    return content
+
+
+def _record_completed_exchange(
+    memory_service,
+    user_text: str,
+    assistant_text: str,
+    *,
+    bus=None,
+    source: str = "server.chat",
+) -> None:
+    """Publish or submit a completed exchange without blocking a reply."""
+    if 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)
+        if bus is not None:
+            from openjarvis.memory import publish_completed_exchange
+
+            publish_completed_exchange(
+                bus,
+                user_text,
+                assistant_text,
+                source=source,
+            )
+        elif memory_service is not None:
+            memory_service.submit(user_text, assistant_text)
     except Exception:  # noqa: BLE001 — memory is best-effort, never fail a reply
         logging.getLogger("openjarvis.server").debug(
             "Memory submit failed",
@@ -268,6 +300,24 @@ def _remember_exchange(memory_service, user_text: str, response) -> None:
         )
 
 
+def _remember_exchange(
+    memory_service,
+    user_text: str,
+    response,
+    *,
+    bus=None,
+    source: str = "server.chat",
+) -> None:
+    """Record a completed non-streaming exchange."""
+    _record_completed_exchange(
+        memory_service,
+        user_text,
+        _response_content(response),
+        bus=bus,
+        source=source,
+    )
+
+
 def _handle_direct(
     engine,
     model: str,
@@ -457,6 +507,8 @@ async def _handle_stream_tools(
     complexity_info=None,
     *,
     app_config=None,
+    bus=None,
+    memory_service=None,
 ):
     """Stream a raw OpenAI-compat function-calling response via SSE.
 
@@ -477,8 +529,14 @@ async def _handle_stream_tools(
     messages = _ensure_identity_prompt(messages, app_config)
     chunk_id = f"chatcmpl-{uuid.uuid4().hex[:12]}"
     use_cloud = is_cloud_model(model)
+    query_text = ""
+    for _m in reversed(req.messages):
+        if _m.role == "user" and _m.content:
+            query_text = _m.content
+            break
 
     async def generate():
+        full_content = ""
         # Send the role chunk first (OpenAI convention).
         first_chunk = ChatCompletionChunk(
             id=chunk_id,
@@ -497,6 +555,7 @@ async def _handle_stream_tools(
                 tools=req.tools,
             ):
                 if sc.content:
+                    full_content += sc.content
                     content_chunk = ChatCompletionChunk(
                         id=chunk_id,
                         model=model,
@@ -553,6 +612,14 @@ async def _handle_stream_tools(
         if complexity_info is not None:
             finish_dict["complexity"] = complexity_info.model_dump()
         yield f"data: {_json.dumps(finish_dict)}\n\n"
+        if full_content:
+            _record_completed_exchange(
+                memory_service,
+                query_text,
+                full_content,
+                bus=bus,
+                source="server.chat.stream",
+            )
         yield "data: [DONE]\n\n"
 
     return StreamingResponse(
@@ -570,6 +637,8 @@ async def _handle_stream(
     *,
     trace_store=None,
     app_config=None,
+    bus=None,
+    memory_service=None,
 ):
     """Stream response using SSE format.
 
@@ -710,6 +779,15 @@ async def _handle_stream(
                 ended_at=time.time(),
             )
 
+        if full_content:
+            _record_completed_exchange(
+                memory_service,
+                query_text,
+                full_content,
+                bus=bus,
+                source="server.chat.stream",
+            )
+
         # Send finish chunk with usage data if available
         import json as _json
 

tests/agents/test_native_openhands.py

@@ -8,7 +8,7 @@ from openjarvis.agents._stubs import AgentContext
 from openjarvis.agents.native_openhands import NativeOpenHandsAgent
 from openjarvis.core.events import EventBus, EventType
 from openjarvis.core.registry import AgentRegistry
-from openjarvis.core.types import Conversation, Message, Role, ToolResult
+from openjarvis.core.types import Conversation, Message, Role, ToolCall, ToolResult
 from openjarvis.tools._stubs import BaseTool, ToolSpec
 
 # ---------------------------------------------------------------------------
@@ -118,6 +118,51 @@ class TestNativeOpenHandsRegistration:
 
 
 class TestNativeOpenHandsAgent:
+    def test_truncate_handles_none_content_tool_call_turn(self):
+        """Tool-call assistant turns may carry content=None."""
+        engine = MagicMock()
+        engine.engine_id = "mock"
+        agent = NativeOpenHandsAgent(engine, "test-model")
+        messages = [
+            Message(role=Role.USER, content="hi"),
+            Message(
+                role=Role.ASSISTANT,
+                content=None,  # type: ignore[arg-type]
+                tool_calls=[ToolCall(id="call_1", name="calculator", arguments="{}")],
+            ),
+        ]
+
+        assert agent._truncate_if_needed(messages) == messages
+
+    def test_native_tool_call_with_none_content_does_not_crash(self):
+        """Native tool-call responses may omit assistant text content."""
+        engine = MagicMock()
+        engine.engine_id = "mock"
+        engine.generate.side_effect = [
+            _engine_response(
+                None,
+                tool_calls=[
+                    {
+                        "id": "call_1",
+                        "name": "calculator",
+                        "arguments": '{"expression": "2+2"}',
+                    }
+                ],
+            ),
+            _engine_response("The result is 4."),
+        ]
+        agent = NativeOpenHandsAgent(
+            engine,
+            "test-model",
+            tools=[_CalculatorStub()],
+        )
+
+        result = agent.run("What is 2+2?")
+
+        assert result.content == "The result is 4."
+        assert result.turns == 2
+        assert [tr.content for tr in result.tool_results] == ["4"]
+
     def test_simple_response(self):
         """No code -> direct answer."""
         engine = MagicMock()

tests/cli/test_chat_cmd.py

@@ -15,6 +15,7 @@ from openjarvis.agents._stubs import (
 )
 from openjarvis.cli.chat_cmd import _read_input, chat
 from openjarvis.core.config import JarvisConfig
+from openjarvis.core.events import Event, EventBus, EventType
 from openjarvis.core.registry import AgentRegistry, ToolRegistry
 from openjarvis.core.types import ToolCall, ToolResult
 from openjarvis.tools._stubs import BaseTool, ToolSpec
@@ -121,25 +122,45 @@ class TestChatAgents:
         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."""
+        """The REPL starts memory, publishes each turn, and stops it."""
 
         class _SpyMemoryService:
-            def __init__(self) -> None:
+            def __init__(self, bus: EventBus) -> None:
+                self.bus = bus
                 self.started = False
                 self.stopped = False
                 self.submissions: list[tuple[str, str]] = []
 
             def start(self) -> None:
                 self.started = True
+                self.bus.subscribe(
+                    EventType.CHAT_EXCHANGE_COMPLETED,
+                    self._on_completed_exchange,
+                )
 
-            def submit(self, user_text: str, assistant_text: str = "") -> bool:
-                self.submissions.append((user_text, assistant_text))
-                return True
+            def _on_completed_exchange(self, event: Event) -> None:
+                self.submissions.append(
+                    (
+                        event.data["user_text"],
+                        event.data.get("assistant_text", ""),
+                    )
+                )
 
             def stop(self, timeout: float = 2.0) -> None:
                 self.stopped = True
+                self.bus.unsubscribe(
+                    EventType.CHAT_EXCHANGE_COMPLETED,
+                    self._on_completed_exchange,
+                )
+
+        spy: _SpyMemoryService | None = None
+
+        def _build_memory_service(*args, event_bus: EventBus | None = None, **kwargs):
+            nonlocal spy
+            assert event_bus is not None
+            spy = _SpyMemoryService(event_bus)
+            return spy
 
-        spy = _SpyMemoryService()
         engine = MagicMock()
         engine.engine_id = "mock"
         engine.generate.return_value = {"content": "engine fallback"}
@@ -154,7 +175,7 @@ class TestChatAgents:
             patch("openjarvis.intelligence.register_builtin_models"),
             patch(
                 "openjarvis.memory.build_memory_service",
-                return_value=spy,
+                side_effect=_build_memory_service,
             ),
         ):
             result = CliRunner().invoke(
@@ -164,6 +185,7 @@ class TestChatAgents:
             )
 
         assert result.exit_code == 0
+        assert spy is not None
         assert spy.started is True
         assert spy.stopped is True
         assert spy.submissions == [("hello", "simple ok")]

tests/conftest.py

@@ -18,6 +18,7 @@ from openjarvis.core.registry import (
     CompressionRegistry,
     ConnectorRegistry,
     EngineRegistry,
+    FactStoreRegistry,
     MemoryRegistry,
     MinerRegistry,
     ModelRegistry,
@@ -35,6 +36,7 @@ def _clean_registries() -> None:
     ModelRegistry.clear()
     EngineRegistry.clear()
     MemoryRegistry.clear()
+    FactStoreRegistry.clear()
     MinerRegistry.clear()
     AgentRegistry.clear()
     ToolRegistry.clear()

tests/core/test_config_phase5.py

@@ -48,6 +48,7 @@ class TestConfigPhase5:
         with pytest.raises(KeyError):
             ModelRegistry.get("iso-test")
 
-    def test_load_config_default(self):
-        cfg = load_config()
+    def test_load_config_default(self, tmp_path, monkeypatch):
+        monkeypatch.setenv("OPENJARVIS_HOME", str(tmp_path / "home"))
+        cfg = load_config(tmp_path / "missing-config.toml")
         assert isinstance(cfg, JarvisConfig)

tests/deployment/test_docker.py

@@ -123,6 +123,35 @@ class TestDockerFiles:
         assert "jarvis:" in content
         assert "ollama:" in content
 
+    def test_dockerfiles_build_native_rust_extension(self):
+        build_dockerfiles = [
+            "Dockerfile",
+            "Dockerfile.gpu",
+            "Dockerfile.gpu.rocm",
+            "Dockerfile.sandbox",
+        ]
+        required_markers = [
+            "rustup toolchain install 1.88",
+            "maturin build --release",
+            "rust/crates/openjarvis-python/Cargo.toml",
+            "/tmp/openjarvis-rust-wheel/*.whl",
+            "import openjarvis_rust",
+        ]
+
+        for name in build_dockerfiles:
+            content = (DOCKER_DIR / name).read_text()
+            for marker in required_markers:
+                assert marker in content, (
+                    f"{name}: missing native build marker {marker!r}"
+                )
+
+        for name in ["Dockerfile", "Dockerfile.gpu", "Dockerfile.gpu.rocm"]:
+            content = (DOCKER_DIR / name).read_text()
+            assert "COPY rust/ rust/" in content, f"{name}: rust workspace not copied"
+            assert content.index("COPY rust/ rust/") < content.index(
+                "maturin build --release"
+            ), f"{name}: rust workspace copied after native build"
+
     def test_systemd_service_exists(self):
         assert (SYSTEMD_DIR / "openjarvis.service").is_file()
 

tests/deployment/test_docs_leaderboard.py

@@ -0,0 +1,45 @@
+"""Static guards for the docs-site savings-leaderboard Supabase wiring.
+
+`docs/javascripts/leaderboard.js` reads the public Supabase anon key from
+`window.OPENJARVIS_SUPABASE_ANON_KEY`. That global is set by a generated
+config file (`leaderboard-config.js`) which must load *before* leaderboard.js,
+and whose value is injected at docs-build time from the VITE_SUPABASE_ANON_KEY
+secret (see `.github/workflows/docs.yml`). These are text-only checks — no
+mkdocs build required — so they run in the default CI lane.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parent.parent.parent
+MKDOCS = ROOT / "mkdocs.yml"
+DOCS_WORKFLOW = ROOT / ".github" / "workflows" / "docs.yml"
+CONFIG_JS = ROOT / "docs" / "javascripts" / "leaderboard-config.js"
+LEADERBOARD_JS = ROOT / "docs" / "javascripts" / "leaderboard.js"
+
+_ANON_GLOBAL = "window.OPENJARVIS_SUPABASE_ANON_KEY"
+
+
+def test_config_js_declares_anon_key_global():
+    assert CONFIG_JS.is_file(), "leaderboard-config.js is missing"
+    assert _ANON_GLOBAL in CONFIG_JS.read_text()
+
+
+def test_leaderboard_reads_the_anon_key_global():
+    # leaderboard.js must consume the global the config file sets.
+    assert _ANON_GLOBAL in LEADERBOARD_JS.read_text()
+
+
+def test_config_is_loaded_before_leaderboard_in_mkdocs():
+    content = MKDOCS.read_text()
+    cfg = content.index("javascripts/leaderboard-config.js")
+    lb = content.index("javascripts/leaderboard.js")
+    assert cfg < lb, "leaderboard-config.js must be listed before leaderboard.js"
+
+
+def test_docs_workflow_injects_the_anon_key():
+    content = DOCS_WORKFLOW.read_text()
+    assert "VITE_SUPABASE_ANON_KEY" in content, "workflow doesn't read the secret"
+    assert "leaderboard-config.js" in content, "workflow doesn't write the config file"
+    assert _ANON_GLOBAL in content, "workflow doesn't set the anon-key global"

tests/engine/test_base.py

@@ -0,0 +1,17 @@
+from __future__ import annotations
+
+from openjarvis.core.types import Message, Role, ToolCall
+from openjarvis.engine._base import estimate_prompt_tokens
+
+
+def test_estimate_prompt_tokens_handles_none_content_tool_call_turn() -> None:
+    messages = [
+        Message(role=Role.USER, content="hi"),
+        Message(
+            role=Role.ASSISTANT,
+            content=None,  # type: ignore[arg-type]
+            tool_calls=[ToolCall(id="call_1", name="lookup", arguments="{}")],
+        ),
+    ]
+
+    assert estimate_prompt_tokens(messages) == 8

tests/memory/test_fact_store.py

@@ -6,6 +6,7 @@ import json
 
 import pytest
 
+from openjarvis.core.registry import FactStoreRegistry
 from openjarvis.memory.store import LocalFactStore, create_fact_store
 
 
@@ -74,6 +75,20 @@ def test_clear(tmp_path):
     assert LocalFactStore(path).count() == 0
 
 
+def test_external_clear_does_not_resurrect_stale_facts(tmp_path):
+    """A running store instance must not re-flush facts cleared elsewhere."""
+    path = tmp_path / "facts.jsonl"
+    running = LocalFactStore(path)
+    cli = LocalFactStore(path)
+
+    running.add("old fact")
+    assert cli.clear() == 1
+
+    running.add("new fact")
+
+    assert [f.text for f in LocalFactStore(path).list()] == ["new fact"]
+
+
 def test_load_skips_malformed_lines(tmp_path):
     path = tmp_path / "facts.jsonl"
     path.write_text(
@@ -107,6 +122,26 @@ def test_create_fact_store_local(tmp_path):
     assert isinstance(store, LocalFactStore)
 
 
+def test_create_fact_store_uses_fact_store_registry(tmp_path):
+    class CustomFactStore(LocalFactStore):
+        pass
+
+    FactStoreRegistry.register_value("custom", CustomFactStore)
+
+    store = create_fact_store("custom", path=tmp_path / "f.jsonl", max_facts=5)
+
+    assert isinstance(store, CustomFactStore)
+
+
+def test_create_fact_store_default_path_uses_openjarvis_home(tmp_path, monkeypatch):
+    monkeypatch.setenv("OPENJARVIS_HOME", str(tmp_path))
+
+    store = create_fact_store("local")
+
+    assert isinstance(store, LocalFactStore)
+    assert store.path == tmp_path / "memory_facts.jsonl"
+
+
 def test_create_fact_store_unknown_backend(tmp_path):
     with pytest.raises(ValueError):
         create_fact_store("cloud", path=tmp_path / "f.jsonl")

tests/memory/test_memory_service.py

@@ -7,7 +7,12 @@ import time
 from types import SimpleNamespace
 
 from openjarvis.core.config import StorageConfig
-from openjarvis.memory.service import MemoryService, build_memory_service
+from openjarvis.core.events import EventBus
+from openjarvis.memory.service import (
+    MemoryService,
+    build_memory_service,
+    publish_completed_exchange,
+)
 from openjarvis.memory.store import LocalFactStore
 
 
@@ -67,6 +72,38 @@ def test_submit_extracts_and_stores(tmp_path):
         svc.stop()
 
 
+def test_completed_exchange_event_extracts_and_stores(tmp_path):
+    bus = EventBus(record_history=True)
+    extractor = FakeExtractor(["User likes jazz"])
+    store = LocalFactStore(tmp_path / "facts.jsonl")
+    svc = MemoryService(store, extractor, event_bus=bus)
+    svc.start()
+    try:
+        assert publish_completed_exchange(
+            bus,
+            "I like jazz",
+            "Noted.",
+            source="test",
+        )
+        assert _wait_until(lambda: svc.fact_count() == 1)
+        assert extractor.calls == [("I like jazz", "Noted.")]
+    finally:
+        svc.stop()
+
+
+def test_completed_exchange_event_unsubscribes_on_stop(tmp_path):
+    bus = EventBus(record_history=True)
+    extractor = FakeExtractor(["User likes jazz"])
+    store = LocalFactStore(tmp_path / "facts.jsonl")
+    svc = MemoryService(store, extractor, event_bus=bus)
+    svc.start()
+    svc.stop()
+
+    publish_completed_exchange(bus, "I like jazz", "Noted.", source="test")
+
+    assert extractor.calls == []
+
+
 def test_submit_when_not_running_is_dropped(tmp_path):
     extractor = FakeExtractor(["x"])
     svc = _service(tmp_path, extractor)

tests/prompt/test_persona_scope.py

@@ -33,7 +33,7 @@ def test_path_traversal_rejected(bad):
         SystemPromptBuilder._resolve_persona(MemoryFilesConfig(persona_name=bad))
 
 
-def test_none_persona_build_does_not_raise():
+def test_none_persona_build_does_not_raise(tmp_path, monkeypatch):
     """Regression (#497): `--persona none` resolves to empty file paths; building
     the prompt must not raise IsADirectoryError when those empty paths are read
     (Path("") is "." — reading a directory raised before the empty-path guard).
@@ -42,7 +42,8 @@ def test_none_persona_build_does_not_raise():
 
     from openjarvis.core.config import load_config
 
-    cfg = load_config()
+    monkeypatch.setenv("OPENJARVIS_HOME", str(tmp_path / "home"))
+    cfg = load_config(tmp_path / "missing-config.toml")
     mf = dataclasses.replace(cfg.memory_files, persona_name="none")
     builder = SystemPromptBuilder(
         agent_template=cfg.agent.default_system_prompt or "",

tests/server/test_routes.py

@@ -10,6 +10,7 @@ import pytest
 fastapi = pytest.importorskip("fastapi")
 from fastapi.testclient import TestClient  # noqa: E402
 
+from openjarvis.core.events import EventBus, EventType  # noqa: E402
 from openjarvis.server.app import create_app  # noqa: E402
 
 # ---------------------------------------------------------------------------
@@ -54,10 +55,19 @@ def _make_agent(content="Hello from agent"):
     return agent
 
 
+def _test_config():
+    from openjarvis.core.config import JarvisConfig
+
+    cfg = JarvisConfig()
+    cfg.analytics.enabled = False
+    cfg.traces.enabled = False
+    return cfg
+
+
 @pytest.fixture
 def client():
     engine = _make_engine()
-    app = create_app(engine, "test-model")
+    app = create_app(engine, "test-model", config=_test_config())
     return TestClient(app)
 
 
@@ -65,7 +75,7 @@ def client():
 def client_with_agent():
     engine = _make_engine()
     agent = _make_agent()
-    app = create_app(engine, "test-model", agent=agent)
+    app = create_app(engine, "test-model", agent=agent, config=_test_config())
     return TestClient(app)
 
 
@@ -92,7 +102,12 @@ 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)
+        app = create_app(
+            engine,
+            "test-model",
+            memory_service=spy,
+            config=_test_config(),
+        )
         client = TestClient(app)
 
         resp = client.post(
@@ -109,7 +124,13 @@ class TestMemoryServiceWiring:
         engine = _make_engine()
         agent = _make_agent(content="agent reply")
         spy = _SpyMemoryService()
-        app = create_app(engine, "test-model", agent=agent, memory_service=spy)
+        app = create_app(
+            engine,
+            "test-model",
+            agent=agent,
+            memory_service=spy,
+            config=_test_config(),
+        )
         client = TestClient(app)
 
         resp = client.post(
@@ -122,9 +143,83 @@ class TestMemoryServiceWiring:
         assert resp.status_code == 200
         assert spy.submissions == [("remember this", "agent reply")]
 
+    def test_non_streaming_completion_publishes_completed_exchange(self):
+        bus = EventBus(record_history=True)
+        engine = _make_engine(content="event reply")
+        app = create_app(engine, "test-model", bus=bus, config=_test_config())
+        client = TestClient(app)
+
+        resp = client.post(
+            "/v1/chat/completions",
+            json={
+                "model": "test-model",
+                "messages": [{"role": "user", "content": "publish this"}],
+            },
+        )
+
+        assert resp.status_code == 200
+        events = [
+            e for e in bus.history if e.event_type == EventType.CHAT_EXCHANGE_COMPLETED
+        ]
+        assert len(events) == 1
+        assert events[0].data["user_text"] == "publish this"
+        assert events[0].data["assistant_text"] == "event reply"
+
+    def test_streaming_completion_feeds_memory_without_bus(self):
+        engine = _make_engine()
+        spy = _SpyMemoryService()
+        app = create_app(
+            engine,
+            "test-model",
+            memory_service=spy,
+            config=_test_config(),
+        )
+        client = TestClient(app)
+
+        resp = client.post(
+            "/v1/chat/completions",
+            json={
+                "model": "test-model",
+                "messages": [{"role": "user", "content": "stream remember"}],
+                "stream": True,
+            },
+        )
+
+        assert resp.status_code == 200
+        assert "data:" in resp.text
+        assert spy.submissions == [("stream remember", "Hello world")]
+
+    def test_streaming_completion_publishes_completed_exchange(self):
+        bus = EventBus(record_history=True)
+        engine = _make_engine()
+        app = create_app(engine, "test-model", bus=bus, config=_test_config())
+        client = TestClient(app)
+
+        resp = client.post(
+            "/v1/chat/completions",
+            json={
+                "model": "test-model",
+                "messages": [{"role": "user", "content": "stream event"}],
+                "stream": True,
+            },
+        )
+
+        assert resp.status_code == 200
+        assert "data:" in resp.text
+        events = [
+            e for e in bus.history if e.event_type == EventType.CHAT_EXCHANGE_COMPLETED
+        ]
+        assert len(events) == 1
+        assert events[0].data["user_text"] == "stream event"
+        assert events[0].data["assistant_text"] == "Hello world"
+
     def test_no_memory_service_is_noop(self):
         engine = _make_engine()
-        app = create_app(engine, "test-model")  # memory_service defaults to None
+        app = create_app(
+            engine,
+            "test-model",
+            config=_test_config(),
+        )  # memory_service defaults to None
         client = TestClient(app)
         resp = client.post(
             "/v1/chat/completions",
@@ -207,7 +302,7 @@ class TestChatCompletions:
             "model": "test-model",
             "finish_reason": "tool_calls",
         }
-        app = create_app(engine, "test-model")
+        app = create_app(engine, "test-model", config=_test_config())
         client = TestClient(app)
         resp = client.post(
             "/v1/chat/completions",
@@ -255,7 +350,7 @@ class TestChatCompletions:
             "finish_reason": "tool_calls",
         }
         agent = _make_agent(content="GENERIC AGENT FILLER")
-        app = create_app(engine, "test-model", agent=agent)
+        app = create_app(engine, "test-model", agent=agent, config=_test_config())
         client = TestClient(app)
 
         resp = client.post(
@@ -342,7 +437,7 @@ class TestChatCompletions:
             lambda data: received_records.append(data),
         )
 
-        app = create_app(wrapped, "test-model")
+        app = create_app(wrapped, "test-model", config=_test_config())
         app.state.bus = bus
         client = TestClient(app)
 
@@ -483,7 +578,13 @@ class TestChatCompletions:
         # bus present + agent registered == the exact live condition under
         # which the pre-fix code routed to the (broken) agent stream bridge.
         agent = _make_agent(content="GENERIC AGENT FILLER")
-        app = create_app(engine, "test-model", agent=agent, bus=EventBus())
+        app = create_app(
+            engine,
+            "test-model",
+            agent=agent,
+            bus=EventBus(),
+            config=_test_config(),
+        )
         client = TestClient(app)
 
         resp = client.post(
@@ -592,6 +693,15 @@ def _make_capturing_engine(captured: list):
     return engine
 
 
+def _identity_config():
+    from openjarvis.core.config import JarvisConfig
+
+    cfg = JarvisConfig()
+    cfg.agent.default_system_prompt = "You are OpenJarvis."
+    cfg.analytics.enabled = False
+    return cfg
+
+
 class TestIdentityPromptInjection:
     """Regression for #540.
 
@@ -607,7 +717,7 @@ class TestIdentityPromptInjection:
     def test_stream_injects_identity_when_absent(self):
         captured: list = []
         engine = _make_capturing_engine(captured)
-        client = TestClient(create_app(engine, "test-model"))
+        client = TestClient(create_app(engine, "test-model", config=_identity_config()))
 
         resp = client.post(
             "/v1/chat/completions",
@@ -628,7 +738,7 @@ class TestIdentityPromptInjection:
     def test_stream_no_double_injection_when_client_supplies_system(self):
         captured: list = []
         engine = _make_capturing_engine(captured)
-        client = TestClient(create_app(engine, "test-model"))
+        client = TestClient(create_app(engine, "test-model", config=_identity_config()))
 
         resp = client.post(
             "/v1/chat/completions",
@@ -652,7 +762,7 @@ class TestIdentityPromptInjection:
         captured: list = []
         engine = _make_capturing_engine(captured)
         # No agent -> non-stream request goes through _handle_direct.
-        client = TestClient(create_app(engine, "test-model"))
+        client = TestClient(create_app(engine, "test-model", config=_identity_config()))
 
         resp = client.post(
             "/v1/chat/completions",
@@ -670,7 +780,7 @@ class TestIdentityPromptInjection:
     def test_direct_no_double_injection_when_client_supplies_system(self):
         captured: list = []
         engine = _make_capturing_engine(captured)
-        client = TestClient(create_app(engine, "test-model"))
+        client = TestClient(create_app(engine, "test-model", config=_identity_config()))
 
         resp = client.post(
             "/v1/chat/completions",
@@ -691,7 +801,7 @@ class TestIdentityPromptInjection:
     def test_stream_tools_injects_identity_when_absent(self):
         captured: list = []
         engine = _make_capturing_engine(captured)
-        client = TestClient(create_app(engine, "test-model"))
+        client = TestClient(create_app(engine, "test-model", config=_identity_config()))
 
         resp = client.post(
             "/v1/chat/completions",
@@ -733,7 +843,7 @@ class TestModelsEndpoint:
 
     def test_multiple_models(self):
         engine = _make_engine(models=["model-a", "model-b", "model-c"])
-        app = create_app(engine, "model-a")
+        app = create_app(engine, "model-a", config=_test_config())
         client = TestClient(app)
         resp = client.get("/v1/models")
         data = resp.json()
@@ -754,7 +864,7 @@ class TestHealthEndpoint:
     def test_unhealthy(self):
         engine = _make_engine()
         engine.health.return_value = False
-        app = create_app(engine, "test-model")
+        app = create_app(engine, "test-model", config=_test_config())
         client = TestClient(app)
         resp = client.get("/health")
         assert resp.status_code == 503
@@ -768,19 +878,19 @@ class TestHealthEndpoint:
 class TestCreateApp:
     def test_app_state(self):
         engine = _make_engine()
-        app = create_app(engine, "test-model")
+        app = create_app(engine, "test-model", config=_test_config())
         assert app.state.engine is engine
         assert app.state.model == "test-model"
 
     def test_app_with_agent(self):
         engine = _make_engine()
         agent = _make_agent()
-        app = create_app(engine, "test-model", agent=agent)
+        app = create_app(engine, "test-model", agent=agent, config=_test_config())
         assert app.state.agent is agent
 
     def test_app_without_agent(self):
         engine = _make_engine()
-        app = create_app(engine, "test-model")
+        app = create_app(engine, "test-model", config=_test_config())
         assert app.state.agent is None
 
 
@@ -804,6 +914,7 @@ def _traces_enabled_config(tmp_path):
     cfg = JarvisConfig()
     cfg.traces.enabled = True
     cfg.traces.db_path = str(tmp_path / "traces.db")
+    cfg.analytics.enabled = False
     return cfg