fix(coding-agent): bundle model data in release source

.github/workflows/build-binaries.yml

@@ -49,6 +49,9 @@ jobs:
           node-version: '22'
           registry-url: 'https://registry.npmjs.org'
 
+      - name: Hydrate release model data
+        run: npm run hydrate:model-data
+
       - name: Create source archive
         run: |
           set -euo pipefail
@@ -69,6 +72,7 @@ jobs:
           trap 'rm -rf "${build_root}"' EXIT
           tar -xzf "release-assets/pi-${VERSION}-source.tar.gz" -C "${build_root}"
           "${build_root}/pi-${VERSION}/scripts/build-binaries.sh" \
+            --offline-model-data \
             --out "${GITHUB_WORKSPACE}/packages/coding-agent/binaries"
 
       - name: Prepare GitHub release payload

README.md

@@ -67,10 +67,10 @@ GitHub releases include a versioned source archive covered by the release's `SHA
 VERSION="<release-version>"
 tar -xzf "pi-${VERSION}-source.tar.gz"
 cd "pi-${VERSION}"
-./scripts/build-binaries.sh --platform linux-x64 --out "$PWD/out"
+./scripts/build-binaries.sh --offline-model-data --platform linux-x64 --out "$PWD/out"
 ```
 
-The script installs dependencies, builds the monorepo, compiles the Bun executable, and stages its runtime assets. Package maintainers who provide dependencies separately can pass `--skip-install --skip-deps`.
+The source archive includes the generated provider model data used for the release. `--offline-model-data` builds with that snapshot instead of refreshing it from live provider catalogs. The script still installs dependencies, builds the monorepo, compiles the Bun executable, and stages its runtime assets. Package maintainers who provide dependencies separately can pass `--skip-install --skip-deps`.
 
 ## Supply-chain hardening
 

packages/coding-agent/CHANGELOG.md

@@ -36,6 +36,7 @@
 - Fixed fresh installs from preferring bundled model catalogs over newer remote catalogs because package file mtimes were newer ([#7016](https://github.com/earendil-works/pi/pull/7016) by [@davidbrai](https://github.com/davidbrai)).
 - Fixed inherited editor scroll indicators overflowing narrow terminals ([#7015](https://github.com/earendil-works/pi/pull/7015) by [@christianklotz](https://github.com/christianklotz)).
 - Fixed llama.cpp models to use the loaded context window as their output token limit instead of capping it at 16K ([#7034](https://github.com/earendil-works/pi/pull/7034) by [@christianklotz](https://github.com/christianklotz)).
+- Fixed release source archives to include the generated provider model data used to build standalone binaries.
 - Updated the packaged `protobufjs` dependency to 7.6.5 to address GHSA-j3f2-48v5-ccww ([#7005](https://github.com/earendil-works/pi/issues/7005)).
 
 ## [0.81.1] - 2026-07-21

scripts/build-binaries.sh

@@ -4,14 +4,15 @@
 # Mirrors .github/workflows/build-binaries.yml
 #
 # Usage:
-#   ./scripts/build-binaries.sh [--skip-install] [--skip-deps] [--skip-build] [--platform <platform>] [--out <dir>]
+#   ./scripts/build-binaries.sh [--skip-install] [--skip-deps] [--skip-build] [--offline-model-data] [--platform <platform>] [--out <dir>]
 #
 # Options:
-#   --skip-install      Skip npm ci
-#   --skip-deps         Skip installing cross-platform dependencies
-#   --skip-build        Skip npm run build
-#   --platform <name>   Build only for specified platform (darwin-arm64, darwin-x64, linux-x64, linux-arm64, windows-x64, windows-arm64)
-#   --out <dir>         Output directory (default: packages/coding-agent/binaries)
+#   --skip-install       Skip npm ci
+#   --skip-deps          Skip installing cross-platform dependencies
+#   --skip-build         Skip the package build
+#   --offline-model-data Build with bundled model data instead of refreshing it
+#   --platform <name>    Build only for specified platform (darwin-arm64, darwin-x64, linux-x64, linux-arm64, windows-x64, windows-arm64)
+#   --out <dir>          Output directory (default: packages/coding-agent/binaries)
 #
 # Output:
 #   packages/coding-agent/binaries/
@@ -29,6 +30,7 @@ cd "$(dirname "$0")/.."
 SKIP_INSTALL=false
 SKIP_DEPS=false
 SKIP_BUILD=false
+OFFLINE_MODEL_DATA=false
 PLATFORM=""
 OUTPUT_DIR=""
 
@@ -46,6 +48,10 @@ while [[ $# -gt 0 ]]; do
             SKIP_BUILD=true
             shift
             ;;
+        --offline-model-data)
+            OFFLINE_MODEL_DATA=true
+            shift
+            ;;
         --platform)
             PLATFORM="$2"
             shift 2
@@ -108,8 +114,13 @@ else
 fi
 
 if [[ "$SKIP_BUILD" == "false" ]]; then
-    echo "==> Building all packages..."
-    npm run build
+    if [[ "$OFFLINE_MODEL_DATA" == "true" ]]; then
+        echo "==> Building all packages with bundled model data..."
+        npm run build:offline
+    else
+        echo "==> Building all packages..."
+        npm run build
+    fi
 else
     echo "==> Skipping package build (--skip-build)"
 fi

scripts/create-source-archive.sh

@@ -2,6 +2,7 @@
 # Create the deterministic source archive uploaded with GitHub releases.
 #
 # Usage:
+#   npm run hydrate:model-data
 #   ./scripts/create-source-archive.sh --version <version> --ref <git-ref> --out <archive.tar.gz>
 
 set -euo pipefail
@@ -78,18 +79,47 @@ fi
 mkdir -p "$(dirname "$output")"
 output="$(cd "$(dirname "$output")" && pwd)/$(basename "$output")"
 
+model_data_dir="packages/ai/src/providers/data"
+if [[ ! -f "${model_data_dir}/.manifest.json" ]]; then
+    echo "Generated model data is missing. Run npm run hydrate:model-data first." >&2
+    exit 1
+fi
+
+shopt -s nullglob
+model_data_files=("${model_data_dir}/.manifest.json" "${model_data_dir}"/*.json)
+shopt -u nullglob
+if [[ ${#model_data_files[@]} -eq 1 ]]; then
+    echo "Generated model data is missing from ${model_data_dir}" >&2
+    exit 1
+fi
+
 temporary_archive="$(mktemp "${output}.tmp.XXXXXX")"
+temporary_index="$(mktemp "${output}.index.XXXXXX")"
 manifest="$(mktemp "${output}.manifest.XXXXXX")"
-trap 'rm -f "$temporary_archive" "$manifest"' EXIT
+validation_root="$(mktemp -d "${output}.validation.XXXXXX")"
+rm -f "$temporary_index"
+trap 'rm -f "$temporary_archive" "$temporary_index" "$manifest"; rm -rf "$validation_root"' EXIT
+
+# Add the ignored release model-data snapshot to a temporary index based on the
+# release commit. Archiving the resulting tree keeps the source artifact
+# deterministic for the same commit and generated model data.
+GIT_INDEX_FILE="$temporary_index" git read-tree "$commit"
+GIT_INDEX_FILE="$temporary_index" git add -f -- "${model_data_files[@]}"
+archive_tree="$(GIT_INDEX_FILE="$temporary_index" git write-tree)"
+archive_mtime="$(git show -s --format=%ct "$commit")"
 
 archive_root="pi-${version}"
-git archive --format=tar --prefix="${archive_root}/" "$commit" | gzip -n -9 > "$temporary_archive"
+git archive --format=tar --prefix="${archive_root}/" --mtime="@${archive_mtime}" "$archive_tree" \
+    | gzip -n -9 > "$temporary_archive"
 tar -tzf "$temporary_archive" > "$manifest"
 
 required_paths=(
     "package.json"
     "package-lock.json"
     "scripts/build-binaries.sh"
+    "packages/ai/src/models.generated.ts"
+    "packages/ai/src/image-models.generated.ts"
+    "packages/ai/src/providers/data/.manifest.json"
     "packages/coding-agent/package.json"
     "packages/coding-agent/src/utils/image-resize-worker.ts"
     "packages/coding-agent/src/core/export-html/template.css"
@@ -112,6 +142,9 @@ if grep -Eq '(^|/)node_modules/|(^|/)packages/coding-agent/binaries/' "$manifest
     exit 1
 fi
 
+tar -xzf "$temporary_archive" -C "$validation_root"
+node "${validation_root}/${archive_root}/packages/ai/scripts/check-model-data.ts"
+
 mv "$temporary_archive" "$output"
-trap 'rm -f "$manifest"' EXIT
+trap 'rm -f "$temporary_index" "$manifest"; rm -rf "$validation_root"' EXIT
 printf '%s\n' "$output"