Merge pull request #73 from yusufipk/llama-nightly-and-model-box

Find the llama.cpp nightly builds, and keep the model box honest

dikte/ggml.py

@@ -83,6 +83,10 @@ LLAMA = Program("llama", "ggml-org/llama.cpp", "llama-server", "/health")
 WHISPER_MODELS_REPO = "ggerganov/whisper.cpp"
 LLM_AUTHOR = "ggml-org"
 
+# The file llama.cpp attaches to its version releases in place of the binaries:
+# a line naming the nightly tag those are published under.
+NIGHTLY_TAG = "nightly-tag.txt"
+
 # What the whisper repository holds besides models: Core ML encoders for Apple
 # hardware and the odd loose file.
 WHISPER_PREFIX = "ggml-"
@@ -277,6 +281,65 @@ def _wanted_assets(program):
     return (f"bin-ubuntu-{arch}.tar.gz",)
 
 
+def _matching_asset(program, assets):
+    """The archive this machine wants out of one release's files, or None."""
+    for ending in _wanted_assets(program):
+        item = next((a for a in assets if a.name.endswith(ending)), None)
+        if item:
+            return item
+    return None
+
+
+def _pick_asset(program, tag="", refresh=False):
+    """(tag, Item) for the release archive to install. Item is None when there
+    is none for this machine.
+
+    A named tag is taken as given. For the newest, what GitHub answers is not
+    always where the builds are: llama.cpp's latest release is a version marker
+    carrying a single nightly-tag.txt, which names the tag the archives are
+    actually attached to, and those are prereleases that "latest" never points
+    at. The pointer is followed when it is there, and when it is not, the newest
+    release that does carry a build for this machine is taken instead.
+    """
+    named = bool(tag) and tag != "latest"
+    missing = None
+    try:
+        tag, assets = hub.release(program.repo, tag or "latest", refresh=refresh)
+    except hub.HubError as exc:
+        # A release carrying no files at all is the case the search below exists
+        # for, not a reason to stop before it: the build for this machine may be
+        # attached to a prerelease that "latest" never points at. The failure is
+        # kept rather than dropped, because an unreachable GitHub arrives here
+        # the same way and that one is the message the caller wants.
+        if named:
+            raise
+        missing, assets = exc, []
+    item = _matching_asset(program, assets)
+    if item or named:
+        return tag, item
+    # Best effort from here on: a machine this project publishes nothing for is
+    # not a failed lookup, and the caller's message about that is the useful
+    # one. Whatever goes wrong while looking further leaves it standing.
+    try:
+        pointer = next((a for a in assets if a.name == NIGHTLY_TAG), None)
+        if pointer:
+            nightly = hub.text(pointer.url).strip()
+            if nightly:
+                found, assets = hub.release(program.repo, nightly, refresh=refresh)
+                item = _matching_asset(program, assets)
+                if item:
+                    return found, item
+        for found, assets in hub.releases(program.repo, refresh=refresh):
+            item = _matching_asset(program, assets)
+            if item:
+                return found, item
+    except hub.HubError:
+        pass
+    if missing is not None:
+        raise missing
+    return tag, None
+
+
 def _install_record(program):
     return BIN_DIR / program.name / "installed.json"
 
@@ -375,15 +438,10 @@ def install_program(program, tag="", on_progress=None, should_stop=None,
     whisper.cpp has one.
     """
     try:
-        tag, assets = hub.release(program.repo, tag or "latest", refresh=refresh)
+        tag, item = _pick_asset(program, tag, refresh=refresh)
     except hub.HubError as exc:
         raise LocalError(str(exc)) from exc
 
-    item = None
-    for ending in _wanted_assets(program):
-        item = next((a for a in assets if a.name.endswith(ending)), None)
-        if item:
-            break
     if item is None:
         # Nothing to download and nothing to install for you: whisper.cpp
         # publishes no macOS binary, and Homebrew's whisper-cpp is configured

dikte/hub.py

@@ -121,6 +121,13 @@ def _digest(value):
     return value.split(":", 1)[1] if value.startswith("sha256:") else value
 
 
+def _assets(data):
+    return [Item(a.get("name") or "", a.get("browser_download_url") or "",
+                 int(a.get("size") or 0), _digest(a.get("digest")))
+            for a in (data.get("assets") or [])
+            if a.get("browser_download_url")]
+
+
 def release(repo, tag="latest", refresh=False):
     """(tag, [Item]) for one GitHub release, newest when no tag is given."""
     where = "latest" if tag in ("", "latest") else f"tags/{tag}"
@@ -128,10 +135,47 @@ def release(repo, tag="latest", refresh=False):
                   f"{GITHUB_API}/repos/{repo}/releases/{where}", refresh=refresh)
     if not isinstance(data, dict) or not data.get("assets"):
         raise HubError(t("{repo} has no downloadable release.", repo=repo))
-    assets = [Item(a.get("name") or "", a.get("browser_download_url") or "",
+    return data.get("tag_name") or tag, _assets(data)
-                   int(a.get("size") or 0), _digest(a.get("digest")))
+
-              for a in data["assets"] if a.get("browser_download_url")]
+
-    return data.get("tag_name") or tag, assets
+def releases(repo, limit=20, refresh=False):
+    """[(tag, [Item])] for the recent releases, newest first, with their files.
+
+    "latest" is one release and this is the list behind it, prereleases
+    included: a project that attaches its builds to a prerelease is invisible
+    to release() above, and its newest usable build is in here.
+    """
+    data = _fetch(f"gh-list-{repo}-{limit}",
+                  f"{GITHUB_API}/repos/{repo}/releases?per_page={limit}",
+                  refresh=refresh)
+    if not isinstance(data, list):
+        raise HubError(t("{repo} has no downloadable release.", repo=repo))
+    out = []
+    for entry in data:
+        tag, items = entry.get("tag_name") or "", _assets(entry)
+        if tag and items:
+            out.append((tag, items))
+    return out
+
+
+def text(url, limit=4096, timeout=20):
+    """A small text file from a release, as a string.
+
+    Not cached and not checksummed, because what it carries is a pointer: a few
+    bytes naming the release the actual archives are attached to, read once on
+    the way to a download that is checked in full.
+    """
+    request = urllib.request.Request(url, headers={"User-Agent": USER_AGENT})
+    try:
+        with urllib.request.urlopen(request, timeout=timeout) as response:
+            return response.read(limit).decode("utf-8", "replace")
+    except urllib.error.HTTPError as exc:
+        exc.close()
+        raise HubError(t("{url} answered HTTP {code}.",
+                         url=urllib.parse.urlsplit(url).netloc, code=exc.code)) from exc
+    except (urllib.error.URLError, OSError, ValueError) as exc:
+        raise HubError(t("Could not reach {url}: {error}",
+                         url=urllib.parse.urlsplit(url).netloc, error=exc)) from exc
 
 
 def newest_release(repo, refresh=False):

dikte/i18n.py

@@ -792,6 +792,12 @@ TR = {
     "Ready: {name}.": "Hazır: {name}.",
     "Nothing downloaded yet.": "Henüz bir şey indirilmedi.",
     "{name} has not been downloaded yet.": "{name} henüz indirilmedi.",
+    "{name} is here, but the program above is not. Download it first.":
+        "{name} burada, ama yukarıdaki program değil. Önce onu indirin.",
+    "{name} is not on this machine and this publisher does not offer it. "
+    "Choose another model, or another publisher.":
+        "{name} bu makinede yok ve bu yayıncı da sunmuyor. Başka bir model, "
+        "ya da başka bir yayıncı seçin.",
     "downloaded": "indirildi",
     "not downloaded": "indirilmedi",
     "Delete model": "Modeli sil",

dikte/settings_ui.py

@@ -6,7 +6,7 @@ import shutil
 import sys
 import threading
 
-from PyQt6.QtCore import QEvent, QObject, QRect, Qt, QUrl, pyqtSignal
+from PyQt6.QtCore import QEvent, QObject, QRect, Qt, QTimer, QUrl, pyqtSignal
 from PyQt6.QtGui import QDesktopServices, QGuiApplication, QKeySequence, QShortcut
 from PyQt6.QtWidgets import (
     QAbstractItemView, QAbstractSpinBox, QCheckBox, QComboBox, QDialog,
@@ -247,6 +247,13 @@ class LocalModelBox(QGroupBox):
         self._pending = False
         self._stop = False
         self._wanted = ""              # the model to select once a list arrives
+        self._chosen_in = ""           # the publisher the selected model is from
+        # Typing or arrowing through the publisher box changes its text a
+        # character at a time, and each of those would otherwise be a request.
+        self._later = QTimer(self)
+        self._later.setSingleShot(True)
+        self._later.setInterval(400)
+        self._later.timeout.connect(self._later_fetch)
 
         form = QFormLayout(self)
 
@@ -328,6 +335,8 @@ class LocalModelBox(QGroupBox):
         self._wanted = model
         self._pending = True
         self._show_program()
+        self._chosen_in = repo or (ggml.SUGGESTED_LLM[0] if self._repos is not None
+                                   else "")
         if self._repos is not None:
             self.repo.blockSignals(True)
             self.repo.clear()
@@ -367,11 +376,18 @@ class LocalModelBox(QGroupBox):
 
     def _fill_repos(self, current):
         def work():
-            self._listed.emit([("repos", ggml.llm_repos())], "")
+            self._listed.emit([("repos", ggml.llm_repos(), "")], "")
 
         threading.Thread(target=work, daemon=True).start()
 
     def _repo_changed(self):
+        if not self._downloading:
+            self._later.start()
+
+    def _later_fetch(self):
+        # A download that started inside the wait was not there to be seen when
+        # the timer went off, and rebuilding the rows underneath one is exactly
+        # what the guard above is for.
         if not self._downloading:
             self._fetch_models(self.repository())
 
@@ -381,18 +397,29 @@ class LocalModelBox(QGroupBox):
         def work():
             try:
                 found = self._models(repo) if self._repos is not None else self._models()
-                self._listed.emit([("models", found)], "")
+                self._listed.emit([("models", found, repo)], "")
             except ggml.LocalError as exc:
-                self._listed.emit([], str(exc))
+                self._listed.emit([("models", [], repo)], str(exc))
 
         threading.Thread(target=work, daemon=True).start()
 
     def _on_listed(self, payload, error):
+        kind, found, repo = payload[0] if payload else ("repos", [], "")
+        # A publisher changed while its predecessor's list was still on the way
+        # would otherwise be answered with the wrong models, whichever request
+        # happened to come back last.
+        if kind == "models" and repo != self.repository():
+            return
         if error:
+            # The list is the publisher's, so a failed one leaves the box no
+            # longer showing this publisher's models: emptying it is what keeps
+            # the two boxes saying the same thing. The message goes on after,
+            # because filling the box writes a status of its own.
+            if kind == "models":
+                self._fill_models([])
+            self._refresh_buttons()
             self.status.setText(error)
-            self._refresh_buttons()
             return
-        kind, found = payload[0]
         if kind == "repos":
             current = self.repo.currentText()
             self.repo.blockSignals(True)
@@ -406,7 +433,12 @@ class LocalModelBox(QGroupBox):
 
     def _fill_models(self, items):
         """One row per model, saying what it weighs and whether it is here."""
-        wanted = self._wanted or self.selected()
+        # The selection is only worth carrying over within the publisher it was
+        # made in. Carried across one, a model this repository does not publish
+        # would be added back as "not downloaded" and selected again, and
+        # changing the publisher would leave the model box looking untouched.
+        same = self._repos is None or self.repository() == self._chosen_in
+        wanted = self._wanted or (self.selected() if same else "")
         here = [name for name in (self._model_path(i.name).name for i in items)]
         self.model.blockSignals(True)
         self.model.clear()
@@ -431,6 +463,7 @@ class LocalModelBox(QGroupBox):
         self.model.blockSignals(False)
         self._fit_popup(self.model)
         self._wanted = ""
+        self._chosen_in = self.repository()
         self._model_changed()
 
     def _on_disk(self):
@@ -459,6 +492,9 @@ class LocalModelBox(QGroupBox):
         self._show_program()
         if error:
             self.program_label.setText(error)
+        # The model line says whether the program is here, so installing one
+        # changes what it should read.
+        self._refresh_buttons()
         self.changed.emit()
 
     def _current_item(self):
@@ -545,15 +581,30 @@ class LocalModelBox(QGroupBox):
     def _refresh_buttons(self):
         name = self.selected()
         here = bool(name) and ggml.have_model(self._model_path(name))
+        # A row carries what it takes to fetch it. The ones that do not are the
+        # models found on this disk and the one the settings name but the list
+        # does not offer: there is nothing to press Download for on those, and
+        # a button that can only do nothing is worse than one that is out.
+        item = self._current_item()
         self.delete_button.setEnabled(here and not self._downloading)
         self.download_button.setText(t("Stop") if self._downloading else t("Download"))
-        self.download_button.setEnabled(self._downloading or (bool(name) and not here))
+        self.download_button.setEnabled(self._downloading or (item is not None
+                                                              and not here))
         if self._downloading:
             return
         if not name:
             self.status.setText(t("Nothing downloaded yet."))
+        elif here and not ggml.program_path(self.program):
+            # The model alone runs nothing, and "Ready" over a missing program
+            # reads as though it does.
+            self.status.setText(t("{name} is here, but the program above is "
+                                  "not. Download it first.", name=name))
         elif here:
             self.status.setText(t("Ready: {name}.", name=name))
+        elif item is None:
+            self.status.setText(t("{name} is not on this machine and this "
+                                  "publisher does not offer it. Choose another "
+                                  "model, or another publisher.", name=name))
         else:
             self.status.setText(t("{name} has not been downloaded yet.", name=name))
 

tests/test_cli.py

@@ -9,6 +9,7 @@ socket is faked, and everything that runs locally runs for real.
 import contextlib
 import io
 import json
+import sys
 import unittest
 import webbrowser
 from typing import ClassVar
@@ -668,7 +669,11 @@ class WithoutAnInstance(DikteTest):
     def run_verb(self, argv):
         # launch_gui replaces this process with the application, so it never
         # comes back in real use and must not be allowed to here.
+        # `ask` with no text reads what was piped in, and the runner's own
+        # stdin is not that: under pytest it is an object that refuses to be
+        # read at all.
         with mock.patch.object(ipc, "send", return_value=None), \
+                mock.patch.object(sys, "stdin", io.StringIO()), \
                 mock.patch.object(cli, "launch_gui") as launch, \
                 captured() as (out, err):
             code = cli.run(argv)

tests/test_ggml.py

@@ -238,6 +238,45 @@ class InstallProgram(Local):
                                "whisper-bin-ubuntu-x64.tar.gz")
         self.assertTrue(urls[1].endswith("whisper-bin-ubuntu-x64.tar.gz"))
 
+    def test_the_nightly_pointer_is_followed_to_where_the_builds_are(self):
+        """llama.cpp's latest release carries a tag name, not the binaries."""
+        self.patch_attr(ggml, "_arch", lambda: "x64")
+        self.patch_attr(ggml, "_has_vulkan", lambda: False)
+        marker = self.release(ggml.NIGHTLY_TAG)
+        nightly = dict(self.release("llama-b10809-bin-ubuntu-x64.tar.gz"),
+                       tag_name="b10809")
+
+        def opener(request, timeout=None):
+            url = request.full_url
+            if url.endswith("/releases/latest"):
+                return json_body(marker)
+            if url.endswith("/releases/tags/b10809"):
+                return json_body(nightly)
+            if url.endswith(ggml.NIGHTLY_TAG):
+                return body(b"b10809\n")
+            return body(self.archive)
+
+        with mock.patch("urllib.request.urlopen", side_effect=opener):
+            tag, found = ggml._pick_asset(ggml.LLAMA)
+        self.assertEqual(tag, "b10809")
+        self.assertEqual(found.name, "llama-b10809-bin-ubuntu-x64.tar.gz")
+
+    def test_without_a_pointer_the_newest_release_that_has_a_build_is_taken(self):
+        self.patch_attr(ggml, "_arch", lambda: "x64")
+        self.patch_attr(ggml, "_has_vulkan", lambda: False)
+        marker = self.release("source.zip")
+        listing = [dict(self.release("llama-b2-bin-win-cpu-x64.zip"), tag_name="b2"),
+                   dict(self.release("llama-b1-bin-ubuntu-x64.tar.gz"), tag_name="b1")]
+
+        def opener(request, timeout=None):
+            url = request.full_url
+            return json_body(listing if "per_page" in url else marker)
+
+        with mock.patch("urllib.request.urlopen", side_effect=opener):
+            tag, found = ggml._pick_asset(ggml.LLAMA)
+        self.assertEqual(tag, "b1")
+        self.assertEqual(found.name, "llama-b1-bin-ubuntu-x64.tar.gz")
+
     def test_a_release_with_nothing_for_this_machine_says_so(self):
         self.patch_attr(ggml, "_arch", lambda: "x64")
         with fake_urlopen(self.release("whisper-bin-Win32.zip")):

tests/test_paths.py

@@ -42,9 +42,12 @@ class Directories(unittest.TestCase):
 
     def test_a_mac_does_not_read_the_xdg_variables(self):
         """A Mac with them set from some other tool still stores in one place."""
-        with mock.patch.dict(os.environ, {"XDG_CONFIG_HOME": "/c"}):
+        # Something no temporary directory can be called: the home this runs
+        # under is a mkdtemp path, and a two-letter needle matched the "/c" in
+        # somebody's TMPDIR rather than the variable being read.
+        with mock.patch.dict(os.environ, {"XDG_CONFIG_HOME": "/xdg-elsewhere"}):
             config_dir, _ = paths.directories("darwin")
-        self.assertNotIn("/c", config_dir.as_posix())
+        self.assertNotIn("xdg-elsewhere", config_dir.as_posix())
 
     def test_windows_keeps_the_models_out_of_the_roaming_profile(self):
         """Settings roam with the account; several gigabytes must not."""

tests/test_ui.py

@@ -8,6 +8,7 @@ next time anybody presses Save. That is the failure this catches.
 
 import os
 import sys
+import time
 import unittest
 from typing import ClassVar
 from unittest import mock
@@ -21,6 +22,7 @@ from dikte import cleanup
 from dikte import config as cfg
 from dikte import ggml
 from dikte import hotkey
+from dikte import hub
 from dikte import ipc
 from dikte import overlay as overlay_module
 from dikte import paste
@@ -1228,6 +1230,75 @@ class LocalModels(DikteTest):
                      for row in range(box.repo.count()))
         self.assertGreaterEqual(view.minimumWidth(), widest)
 
+    @staticmethod
+    def _item(name, size=1 << 20):
+        return hub.Item(name, f"https://example.invalid/{name}", size, "")
+
+    def test_a_row_with_nothing_to_fetch_does_not_offer_a_download(self):
+        # The model the settings name is not in the list any more, so its row
+        # was rebuilt from the name alone and carries no file to fetch. The
+        # button stayed lit and the press did nothing at all.
+        box = self.window(self.config(local_llm_model="gone.gguf")).local_llm
+        box.load("gone.gguf", "ggml-org/SmolLM3-3B-GGUF")
+        self.assertEqual(box.selected(), "gone.gguf")
+        self.assertFalse(box.download_button.isEnabled())
+        self.assertIn("gone.gguf", box.status.text())
+        self.assertIn("publisher", box.status.text())
+
+    def test_a_model_without_its_program_does_not_say_it_is_ready(self):
+        # The model runs on the program above it, and "Ready" over a missing
+        # one is what had people asking why nothing transcribed.
+        box = self.window(cfg.Config()).local_whisper
+        path = ggml.whisper_model_path("ggml-small.bin")
+        path.parent.mkdir(parents=True, exist_ok=True)
+        path.write_bytes(b"not really a model")
+        box.load("ggml-small.bin")
+        self.assertFalse(ggml.program_path(ggml.WHISPER))
+        self.assertNotIn("Ready", box.status.text())
+        self.assertIn("program", box.status.text())
+
+    def test_changing_the_publisher_changes_the_model(self):
+        # The model chosen under the old publisher is not published by the new
+        # one. Carried over, it was added back as "not downloaded" and selected
+        # again, and the box looked as though the change had not taken.
+        box = self.window(self.config(local_llm_model="gemma-3-4b-it-Q4_K_M.gguf",
+                                      local_llm_repo="ggml-org/gemma-3-4b-it-GGUF")).local_llm
+        box.load("gemma-3-4b-it-Q4_K_M.gguf", "ggml-org/gemma-3-4b-it-GGUF")
+        box.repo.blockSignals(True)
+        box.repo.setCurrentText("ggml-org/SmolLM3-3B-GGUF")
+        box.repo.blockSignals(False)
+        box._on_listed([("models", [self._item("SmolLM3-Q4_K_M.gguf")],
+                         "ggml-org/SmolLM3-3B-GGUF")], "")
+        self.assertEqual(box.selected(), "SmolLM3-Q4_K_M.gguf")
+        self.assertEqual(box.model.count(), 1)
+
+    def test_a_list_for_a_publisher_that_is_no_longer_chosen_is_dropped(self):
+        # Every change starts its own request, and they do not come back in the
+        # order they went out.
+        box = self.window(cfg.Config()).local_llm
+        box.load("", "ggml-org/SmolLM3-3B-GGUF")
+        box.repo.blockSignals(True)
+        box.repo.setCurrentText("ggml-org/SmolLM3-3B-GGUF")
+        box.repo.blockSignals(False)
+        box._on_listed([("models", [self._item("SmolLM3-Q4_K_M.gguf")],
+                         "ggml-org/SmolLM3-3B-GGUF")], "")
+        box._on_listed([("models", [self._item("gemma-3-4b-it-Q4_K_M.gguf")],
+                         "ggml-org/gemma-3-4b-it-GGUF")], "")
+        self.assertEqual(box.selected(), "SmolLM3-Q4_K_M.gguf")
+
+    def test_the_publisher_box_is_not_asked_on_every_keystroke(self):
+        box = self.window(cfg.Config()).local_llm
+        with mock.patch.object(box, "_fetch_models") as fetch:
+            for text in ("g", "gg", "ggm", "ggml-org/SmolLM3-3B-GGUF"):
+                box.repo.setCurrentText(text)
+            fetch.assert_not_called()
+            box._later.setInterval(0)
+            box._later.start()
+            _app.processEvents()
+            time.sleep(0.05)
+            _app.processEvents()
+        self.assertEqual(fetch.call_count, 1)
+
     def test_only_the_chosen_transcriber_is_on_screen(self):
         window = self.window(self.config(transcribe_provider="openai"))
         self.assertTrue(window.stt_form.isRowVisible(window.transcribe_model_row))