Studio: fetch the release source asset for exact (mix) source builds (#6195)

* Studio: fetch the release source asset for exact (mix) source builds

The source-build fallback rebuilt the codeload/archive URL from the
source repo and commit. A mix build's merged tree is never pushed to any
repo (it ships only as the release's llama.cpp-source-commit-<sha>.tar.gz
asset), so codeload 404s on the merge commit and an uncovered host could
not build from source. When an exact-source asset exists, fetch it
directly from the release and keep codeload as the fallback for vanilla
builds whose commit is real.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

studio/install_llama_prebuilt.py

@@ -1095,6 +1095,20 @@ def commit_source_archive_urls(repo: str, source_commit: str) -> list[str]:
     ]
 
 
+def release_asset_download_url(
+    repo: str | None, release_tag: str | None, asset_name: str | None
+) -> str | None:
+    """Direct download URL for a release asset, or None if any part is missing.
+    A mix build's merged commit is never pushed, so its source tree is only
+    reachable as this asset (codeload would 404 on the merge commit)."""
+    if not repo or not release_tag or not asset_name:
+        return None
+    return (
+        f"https://github.com/{repo}/releases/download/"
+        f"{urllib.parse.quote(release_tag, safe = '')}/{urllib.parse.quote(asset_name, safe = '')}"
+    )
+
+
 def github_release_assets(repo: str, tag: str) -> dict[str, str]:
     payload = fetch_json(
         f"https://api.github.com/repos/{repo}/releases/tags/{urllib.parse.quote(tag, safe = '')}"
@@ -4495,13 +4509,17 @@ def hydrate_source_tree(
     expected_sha256: str | None,
     source_label: str | None = None,
     exact_source: bool = False,
+    asset_url: str | None = None,
 ) -> None:
     archive_path = work_dir / f"llama.cpp-source-{source_ref}.tar.gz"
-    source_urls = (
+    repo_urls = (
         commit_source_archive_urls(source_repo, source_ref)
         if exact_source
         else upstream_source_archive_urls(source_ref)
     )
+    # Prefer the published release asset (the only copy of a mix build's merged
+    # tree); fall back to codeload/archive for vanilla builds whose commit is real.
+    source_urls = ([asset_url] if asset_url else []) + repo_urls
     label = source_label or f"llama.cpp source tree for {source_ref}"
     extract_dir = Path(tempfile.mkdtemp(prefix = "source-extract-", dir = work_dir))
 
@@ -6404,6 +6422,15 @@ def validate_prebuilt_choice(
     source_repo, source_ref, source_archive, exact_source = preferred_source_archive(
         approved_checksums, llama_tag
     )
+    # For an exact (mix) source the merge commit lives only in the release asset,
+    # not in any repo, so fetch the asset directly; codeload stays the fallback.
+    asset_url = (
+        release_asset_download_url(
+            approved_checksums.repo, approved_checksums.release_tag, source_archive.asset_name
+        )
+        if exact_source and source_archive is not None
+        else None
+    )
     if exact_source:
         log(f"hydrating exact llama.cpp source for {source_repo}@{source_ref} into {install_dir}")
     else:
@@ -6420,6 +6447,7 @@ def validate_prebuilt_choice(
             else f"llama.cpp source tree for {llama_tag}"
         ),
         exact_source = exact_source,
+        asset_url = asset_url,
     )
     log(f"overlaying prebuilt bundle {choice.name} into {install_dir}")
     server_path, quantize_path = install_from_archives(choice, host, install_dir, work_dir)

tests/studio/install/test_install_llama_prebuilt_logic.py

@@ -206,6 +206,110 @@ def test_hydrate_source_tree_extracts_upstream_archive_contents(
     assert not (install_dir / f"llama.cpp-{upstream_tag}").exists()
 
 
+def test_release_asset_download_url():
+    fn = INSTALL_LLAMA_PREBUILT.release_asset_download_url
+    assert fn(
+        "unslothai/llama.cpp", "b9000-mix-abc1234", "llama.cpp-source-commit-deadbeef.tar.gz"
+    ) == (
+        "https://github.com/unslothai/llama.cpp/releases/download/"
+        "b9000-mix-abc1234/llama.cpp-source-commit-deadbeef.tar.gz"
+    )
+    # Any missing component -> None (no asset url, caller falls back to codeload).
+    assert fn(None, "b9000", "x.tar.gz") is None
+    assert fn("unslothai/llama.cpp", None, "x.tar.gz") is None
+    assert fn("unslothai/llama.cpp", "b9000", None) is None
+
+
+def _mk_source_tarball(path: Path, tag: str) -> None:
+    with tarfile.open(path, "w:gz") as archive:
+        add_bytes_to_tar(
+            archive, f"llama.cpp-{tag}/CMakeLists.txt", b"cmake_minimum_required(VERSION 3.14)\n"
+        )
+        add_bytes_to_tar(
+            archive,
+            f"llama.cpp-{tag}/convert_hf_to_gguf.py",
+            b"#!/usr/bin/env python3\nimport gguf\n",
+        )
+        add_bytes_to_tar(archive, f"llama.cpp-{tag}/gguf-py/gguf/__init__.py", b"__all__ = []\n")
+
+
+def test_hydrate_source_tree_prefers_release_asset_for_mix(
+    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+):
+    # A mix build's merge commit is in no repo, so the codeload/archive URLs 404.
+    # hydrate must fetch the release asset and never touch codeload.
+    commit = "a" * 40
+    archive_path = tmp_path / "merged-source.tar.gz"
+    _mk_source_tarball(archive_path, f"b9000-mix-{commit[:7]}")
+    asset_url = INSTALL_LLAMA_PREBUILT.release_asset_download_url(
+        "unslothai/llama.cpp", "b9000-mix-abc1234", f"llama.cpp-source-commit-{commit}.tar.gz"
+    )
+    codeload_urls = set(
+        INSTALL_LLAMA_PREBUILT.commit_source_archive_urls("unslothai/llama.cpp", commit)
+    )
+    seen = []
+
+    def fake_download_file(url: str, destination: Path) -> None:
+        seen.append(url)
+        if url in codeload_urls:
+            raise AssertionError("codeload was hit even though the release asset was available")
+        assert url == asset_url
+        destination.write_bytes(archive_path.read_bytes())
+
+    monkeypatch.setattr(INSTALL_LLAMA_PREBUILT, "download_file", fake_download_file)
+
+    install_dir = tmp_path / "install"
+    work_dir = tmp_path / "work"
+    work_dir.mkdir()
+    hydrate_source_tree(
+        commit,
+        install_dir,
+        work_dir,
+        source_repo = "unslothai/llama.cpp",
+        expected_sha256 = sha256_file(archive_path),
+        exact_source = True,
+        asset_url = asset_url,
+    )
+    assert seen == [asset_url]
+    assert (install_dir / "CMakeLists.txt").exists()
+    assert (install_dir / "convert_hf_to_gguf.py").exists()
+
+
+def test_hydrate_source_tree_falls_back_to_codeload_when_asset_missing(
+    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+):
+    # If the release asset 404s, fall back to codeload/archive (vanilla path).
+    commit = "b" * 40
+    archive_path = tmp_path / "vanilla-source.tar.gz"
+    _mk_source_tarball(archive_path, f"commit-{commit[:7]}")
+    asset_url = INSTALL_LLAMA_PREBUILT.release_asset_download_url(
+        "unslothai/llama.cpp", "b9000", f"llama.cpp-source-commit-{commit}.tar.gz"
+    )
+    codeload_urls = INSTALL_LLAMA_PREBUILT.commit_source_archive_urls("unslothai/llama.cpp", commit)
+
+    def fake_download_file(url: str, destination: Path) -> None:
+        if url == asset_url:
+            raise RuntimeError("404 Not Found")
+        assert url in codeload_urls
+        destination.write_bytes(archive_path.read_bytes())
+
+    monkeypatch.setattr(INSTALL_LLAMA_PREBUILT, "download_file", fake_download_file)
+
+    install_dir = tmp_path / "install"
+    work_dir = tmp_path / "work"
+    work_dir.mkdir()
+    hydrate_source_tree(
+        commit,
+        install_dir,
+        work_dir,
+        source_repo = "unslothai/llama.cpp",
+        expected_sha256 = sha256_file(archive_path),
+        exact_source = True,
+        asset_url = asset_url,
+    )
+    assert (install_dir / "CMakeLists.txt").exists()
+
+
 def test_validate_prebuilt_choice_creates_repo_shaped_linux_install(
     tmp_path: Path, monkeypatch: pytest.MonkeyPatch
 ):