The capture-phase scroll listener was firing for scrolls anywhere
in the modal — including the Trending models list, which lives
inside the Direct Download fold body. Scrolling that list was
auto-folding the section that contains it.
Bail early if the scroll target is the fold body or a descendant —
the section only folds on scrolls in sibling scrollers (.cookbook-body,
.hwfit-list, .modal-content).
New order: [Standard ▾] [Search ............] [Engine] [Quant] [Context]
so the two primary picks (type + free text) sit together at the
left, with the more advanced filters lined up to the right.
display:none toggle was instant and felt jarring during auto-fold/
auto-expand. Swapped to a CSS class `.is-folded` that transitions
max-height (0 ↔ 1200px) and opacity (0 ↔ 1) over ~280ms with ease,
so both manual chevron clicks and the scroll-driven toggles slide
in/out smoothly.
scroll handler now tracks per-target scrollTop via WeakMap. Downward
scroll on any scroller in the cookbook modal folds Direct Download;
scrolling back to top (scrollTop <= 0) unfolds it. Manual chevron
clicks still win — they persist to localStorage; auto-toggles
don't, so the user's last explicit pick survives reload.
IntersectionObserver missed the case because scrolling inside the
nested .hwfit-list (max-height:52vh own scroller) doesn't move the
header out of view at all. The user wants any downward scroll in
the scan/download area to fold Direct Download.
Switched to a capture-phase scroll listener on #cookbook-modal that
catches every scroll event from any nested scroller (.hwfit-list,
.cookbook-body, .modal-content). Folds only on downward scrolls so
scrolling back up doesn't keep re-folding.
The scroll listener on .cookbook-body never fired — the user is
likely scrolling inside the nested .hwfit-list (max-height:52vh)
which doesn't bubble to its parent. IntersectionObserver fires
whenever the Direct Download header crosses the viewport edge
regardless of which container moved.
Folds only when boundingClientRect.top < 0 (header pushed up past
the top) so modal close / detach doesn't trigger it.
Previous .modal-body / .cookbook-content lookup matched neither the
desktop scroller (.cookbook-body) nor the mobile one (#cookbook-modal
.modal-content), so the scroll listener was attached to document.body
and never fired. Walk up to whichever scroller actually exists.
Added a scroll listener on the parent .modal-body / cookbook-content
that folds the Direct Download body once its h2 header has scrolled
above the container's top edge. Frees the viewport for the Scan
section below while leaving the chevron clickable to expand again.
Auto-fold doesn't write to localStorage (only manual clicks do)
so the user's last explicit preference still wins on reload.
- Added a trending-up (market-up) SVG before the label, tinted
accent so the section reads as "what's hot".
- Chevron ▸ moved from the left to the right side of the toggle
row (still rotates via the existing CSS).
- Bumped the toggle row taller (26→34px) with 13px font + 18px
icon so the section header has more presence.
- Brain admin-card header rows get min-height:32px so cards with
toggles and cards without (Inject Skills) align.
- Cookbook Trending models tab nudged up 8px (top:-3 → -11).
- Removed the ↻ RESCAN button in hwfit toolbar; manual EDIT still
available and auto-probe runs on container restart.
Surface a lot of accumulated cookbook + UI work as a single non-agent
commit so the agent rework lands cleanly.
Highlights:
- Ollama as a first-class backend in the Cookbook:
* Download input accepts ollama-style names (name:tag) → backend=ollama
* /api/cookbook/ollama/library (cached scrape of ollama.com + curated
fallback so classic models like qwen2.5 stay reachable)
* "Browse Ollama library" toggle below Download with size chips
* Engine=Ollama in hwfit toolbar merges the Ollama library into the
main scan list as per-tag rows with the same Fit/Param/Quant/VRAM
columns; click → fills Download input
- API Tokens form added to Integrations panel (matching wired
loadTokens()/initTokenForm() that had no HTML)
- Serve panel polish: Advanced fold tightening (-8px nudges on vLLM
checks, Extra args, Spec row), n_cpu_moe + Split Mode controls
pulled up 8px to align with the row's checkboxes, GGUF File dropdown
exposed for Ollama backend, GPU re-render on Edit serve restore,
_forceBackend flag so saved serveState wins over backend detection,
cookbook:servers-changed CustomEvent so panels don't need refresh
- Models page redesign: Add Models row (URL + hidden API key reveal +
Type select + Scan/Ollama/Key/Test/Add icon buttons), Probe All +
Clear-offline buttons in Added Models toolbar, offline-pill removed
(opacity already conveys state), Engine dropdown gains Ollama option
- _ping_endpoint probes /v1/models then base, accepts 4xx as
reachable (vLLM returns 404 on bare /v1, fully working endpoints
were showing offline)
- Diagnosis card: × dismiss + Copy bundle buttons restored on the
serve error feedback card
- Orphan tmux sweep re-enabled behind a 60s rate-limit + background
Thread (off the main event loop) so dead serves get discovered
- cookbook_routes auto-register watchdog: drops the endpoint if the
serve session exits non-zero within the first ~3min
- ollama-rocm sidecar awareness in download wrapper (`docker exec
ollama-rocm ollama pull` when host ollama isn't installed)
- Skill extractor sets initial_status="published" when
auto_approve_skills pref is on (audit demotes later)
- Skill list / model list / cookbook scan misc polish
* feat(platform): add support for Apple Silicon detection in platform compatibility
test(tests): enhance shell_routes tests for Apple Silicon compatibility
* fix issues with missing import
* fix: correct package name in package-lock.json and enhance package installation commands in shell_routes.py and cookbook.js
* feat: add Apfel startup and health checks on macOS
- bootstrap Apfel via Homebrew on arm64 macOS
- start `apfel --serve --port 11435` detached for Odysseus
- verify readiness via `/health`
- clean up the Apfel process on exit or Ctrl+C
* fix: duplicate variable declaration post-merge conflict
- Should fix `node` CI issues.
* fix: issues with the update status of the APFEL dependency.
- fixed by changing the main conditional that determines the update.
* Fix: Remove unnecessary whitespaces and formatting for the model_routes.py file.
* Fix: whitespace issues with the model_routes file
* Fix: Remove unnecessary whitespaces and formatting for the model_routes.py file. Final
* Fix: Fixed updates using PIP for APFEL instead of custom cmd
_getPlatform('local') fell back to navigator.userAgent to decide the
*server's* platform. On a Mac/Linux homeserver opened from a Windows
browser this returned 'windows', so the GGUF serve builder emitted the
Windows python-only shape (`python -m llama_cpp.server`, no
`llama-server ||` fallback). That command fails on the Unix host with
"No module named llama_cpp" even though native llama-server is installed,
and the diagnosis then misleadingly tells the user to pip-install
llama-cpp-python.
Trust the server-side hardware probe over the user-agent: a non-empty
probe backend (metal/cuda/rocm/cpu_*) means a Unix server; local Windows
instead carries platform:"windows" which already sets _envState.platform
and short-circuits. Only fall back to the browser hint when there is no
server-side signal at all. Keeps #1389/#2961's local-Windows path intact.
Fixes#3221
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
This commit consolidates all Windows Cookbook background fixes into a single comprehensive commit based on the latest main branch.
Key fixes included:
1. React looksSuccessful Mismatch: Append 'DOWNLOAD_OK' for pip install commands in routes/cookbook_routes.py.
2. Local Windows SSH Wrapper & Log Directory Mismatch: Bypassed ssh wrappers and dynamically selected odysseus-tmux logs for local tasks in static/js/cookbookRunning.js.
3. WSL Bash Filtration: Filtered out the WSL bash stub at C:\Windows\System32\bash.exe in core/platform_compat.py.
4. Drive-Colon Path Normalization: Replaced .as_posix() with git_bash_path() in routes/shell_routes.py and src/bg_jobs.py.
5. GGUF-Only Hardware Fitting: Restructured local Windows recommendations to rank GGUF only in services/hwfit/fit.py.
6. Safe Win32 Process Liveness Probe: Replaced os.kill(pid, 0) with a safe Win32 API probe using GetExitCodeProcess in core/platform_compat.py.
7. Prebuilt llama-cpp-python Wheels: Supply the CPU extra index during compilation failure fallback.
8. Enforce UTF-8 log encoding: Set PYTHONIOENCODING=utf-8 on Windows bootstrap runners.
9. Fix Linux Llama.cpp Build script syntax error in routes/cookbook_helpers.py.
10. Page Reload Status Check: Run sys.executable instead of 'python3' to bypass Microsoft Store execution stubs on local Windows hosts.
11. Llama.cpp serve build bypass: Bypassed cmake compilation checks on local Windows and verified python bindings directly.
12. Serve Command Path Validation: Masked safe GGUF path printf subshells '' inside the serve command validator.
13. CPU Mismatch Diagnostics: Intercepted AVX2-lacking '0xc000001d' (Illegal Instruction) crashes in static/js/cookbook-diagnosis.js and guided users to Ollama.
14. Windows Pytest stability: Fixed stub import leakage in test files.
Three converging fixes so the chat agent + external Codex/Claude skills can actually debug a crashed serve instead of staring at a post-crash neofetch banner:
* Serves now `tee` to /tmp/odysseus-tmux/SESSION.log on the host running them. Runner saves fds 3/4 before the tee and restores them right before `exec ${SHELL}`, so the post-crash interactive zsh banner does NOT pollute the log file.
* `tail_serve_output` (chat agent) and `/api/codex/cookbook/output/{sid}` (Codex+Claude skills) both prefer the persistent log file over the tmux pane. Pane is fallback for sessions predating the tee runner. Default tail bumped 150 -> 400.
* `list_served_models` "recent log" snippet seeks to the Traceback line instead of showing the last 6 lines (which was always the bash prompt).
Cookbook auto-adoption sweep on `/api/cookbook/tasks/status`: every 20s (rate-limited) the cookbook SSHes each configured server, finds `serve-*` / `cookbook-*` tmux sessions running an actual model process (vllm/python/llama-server/etc., filtered via `pane_current_command`), and writes them into state.tasks. So when the agent falls back to raw ssh+tmux, the session appears in the Cookbook UI on the next poll.
`serve_model` error path now reads `data["detail"]` in addition to `data["error"]` so the FastAPI HTTPException message ("Invalid characters in cmd") actually reaches the agent instead of being swallowed as a generic "Serve failed". Tool description updated to warn against `cd …`/`source …`/`&&` prefixes.
Intent-without-action supervisor in agent_loop: when the model writes "Let me tail the output" / "I'll check the logs" / "Let me investigate" and ends the turn without emitting a tool call, the loop injects a sharp system nudge ("You said you would X — DO IT NOW") and continues. Capped at 2 nudges per chat so a model that genuinely cannot use the tool does not pin the loop.
Codex/Claude skill parity: adds `/cookbook/cached`, `/cookbook/presets`, `/cookbook/preset/{name}`, `/cookbook/adopt` so external agents have the same surface as the chat agent. SKILL.md docs + odysseus_api.py wrapper updated for both bundles.
`adopt_served_model` promoted to the always-on tool set so the agent has a documented fallback when serve_model rejects a cmd.
Also various cookbook UI tweaks accumulated alongside the above (cookbook.js, cookbookRunning.js, cookbookServe.js, cookbook-diagnosis.js, settings.js, style.css).
Backend (services/hwfit + routes):
- VRAM column sort now shows global highest first (was special-cased to
ascending then truncated top-N, which made "highest VRAM" mathematically
unreachable). Every column path uses reverse=True for the truncation.
- Hardware probe cache TTL 30min -> 24h so changing filters doesn't keep
re-probing the rig during a session; Rescan button still forces fresh.
- Multi-GPU rigs filter GGUF Q*/IQ quants (vLLM/SGLang can't serve them);
default non-prequantized to BF16 on 2+ GPUs.
- AWQ / AWQ-8bit / GPTQ-8bit get a -1.0 quality penalty so FP8 wins ties.
- Version-aware tiebreaker (parse Mn.n / Vn) — MiniMax-M2.7 ranks above M2.5.
- hf_models.json: zai-org/GLM-5.1 added; zai-org/GLM-5 quantization flipped
Q4_K_M -> BF16. DeepSeek-V4-Flash / -Pro + their -Base variants registered
with new FP4-MoE-Mixed / FP8-Mixed quant keys (calibrated BPP from the
actual 156 GB / 284 GB disk footprints).
- New FP4-MoE-Mixed + FP8-Mixed entries in QUANT_BPP / QUANT_SPEED_MULT /
QUANT_QUALITY_PENALTY / QUANT_BYTES_PER_PARAM / PREQUANTIZED_PREFIXES.
Frontend — Scan/Download:
- Engine + Quant swapped in the toolbar; Quant defaults to "All".
- Ctx (range slider) ported from origin/main: 8k/16k/32k/50k/128k/Max. Drag
re-sorts by vram ascending (smallest fitting first); back to Max → score.
- Ctx slider rail now visible — was background:transparent in a duplicate
later-cascade rule. Hardcoded grey + !important.
- Search input moved to the far right of the toolbar.
- Type/Standard default; "Context" not uppercased; Search placeholder dimmed.
- Engine "?" + Quant "?" inline help chips inside their dropdown boxes.
- Fit-column dot toggles fit-only filter; un-toggling re-sorts by VRAM desc.
- Quant column truncates to 9 chars + ellipsis ("FP4-MoE-M..."), full in
tooltip. Smart title-suffix strips the parts already in the repo name
(QuantTrio/MiniMax-M2-AWQ + quant AWQ-4bit -> just "(4bit)").
- Conditional warning for safetensors models on non-GPU rigs only.
- Dependency Install / Installed / Installed▾ / N/A all 75.85px wide.
- Rebuild llama.cpp moved into the llama_cpp dep row, styled as a tag.
- Foldable Download admin-card (h2 chevron); line under h2 only when folded.
- HF token save gets a green ✓ + "Saved" flash.
- Cached scan no longer counts stalled rows as downloaded.
- Footer: "Request it →" link with GitHub mark to the public discussion
(#1962) for model-add requests.
Frontend — Running tab:
- Strict download-finish check (DOWNLOAD_OK or /snapshots/, not bare
"Download complete"). True overall % for multi-shard downloads:
((N-1)+frac)/total instead of hf_transfer's per-shard aggregate.
- ETA in the uptime ticker: "downloading: 12m 34s · ETA 1h 23m".
- Clear button kills the tmux session too; if the output still shows a
live shard line, the pill is hidden + relabels as "reconnect" + revives
on click.
- Self-heal: on cookbook open AND every bg-monitor cycle (10s, throttled
to 8s), scan persisted done/error/crashed downloads and probe their
tmux session — if alive, flip status back to running and reattach.
- Per-launch zombie probe: clicking Download on a model whose persisted
state is done but tmux is still alive revives the existing task and
refuses to start a duplicate.
- Pre-launch GPU probe: vllm / sglang / diffusers serve check
/api/cookbook/gpus first; warns + confirms if no GPU is visible.
- Server-side state guard: rejects "done" POSTs for downloads lacking
DOWNLOAD_OK / DOWNLOAD_FAILED / /snapshots/ when the last-mentioned
shard is N<total — stale tabs can't poison persisted state any more.
- Running count includes tasks whose output looks active even if persisted
status got stuck. Dir text on the running row, font matched to uptime.
Serve panel:
- Ctx text input always resets to model max on open (default 20000 when
metadata is missing).
- Max Seqs default 8 -> 4. KV Cache dtype select 32px tall.
- Lightning icon on Launch (same as Action toggle).
- Diagnosis card simplified (no fold/copy/dismiss), suggestion font
matches body; action buttons get icons on the left (Retry/Copy/Edit/
Install/Kill/Switch/etc.).
- Incomplete-download serve warning when model status is
downloading / stalled / has_incomplete.
- MTP "?" tooltip ("supported on a few model families … up to ~3× faster").
Backend (services/hwfit + routes):
- rank_models picks visible set by REQUESTED column, not always score —
sorting by Param now shows highest-param models PERIOD (incl. too_tight).
- New fit_only param. Multi-GPU rigs filter GGUF Q*/IQ quants (vLLM/SGLang
cannot serve them); default non-prequantized to BF16 on 2+ GPUs.
- AWQ / GPTQ-8bit get a -1.0 quality penalty (was 0.0, tied with FP8), so
FP8 wins when both fit.
- Version-aware tiebreaker (parse Mn.n / Vn) — MiniMax-M2.7 ranks above
M2.5 on equal composite score; >=100B integers not misread as versions.
- /api/cookbook/hf-latest no longer drops models without an "NB" pattern in
the repo id (MiniMax-M2.7, DeepSeek-V4-Pro etc. were silently filtered).
- Cached-model scan: atexit flushes models JSON even if the script is
killed mid-walk; each scan_dir wrapped in try/except; timeout 60s -> 180s.
- KB granularity for sub-MB sizes (was "0 MB" for 12 KB shells). New
"stalled" status for shells <1 MB with no .incomplete files.
- /api/cookbook/state POST guard: rejects "done" download tasks lacking
DOWNLOAD_OK / DOWNLOAD_FAILED / /snapshots/ when the last-mentioned
shard is N<total — stops stale tabs from poisoning persisted state.
- hf_models.json: add zai-org/GLM-5.1; flip zai-org/GLM-5 quantization
Q4_K_M -> BF16 (it is the native base, not a quant).
Frontend (static/js):
- Scan/Download toolbar: quant defaults to All; ctx slider (8k/16k/32k/
50k/128k/Max) ported from origin/main with sort=fit on drag, sort=score
on Max. GPU toggle commits _activeCount to maxGpu on initial render. Fit
column header tagged with active budget (RAM / GPU / N GPU).
- Foldable Download admin-card: the Download h2 is the chevron trigger;
state persists in localStorage.
- Download card surfaces destination dir (Dir: <path>). Same dir on running
task row, font/color matched to uptime (9px Fira Code muted, opacity .4).
- Serve panel ctx text input always resets to model max on open. Sub-MB
cached models show with red "download stalled" badge.
- Bulk-select Cancel + Delete reset the Select button label on exit.
- Cookbook running: false-finished bug fixed — DOWNLOAD_OK or /snapshots/
required; bare "Download complete" no longer marks the task done after
the first config file. Clear button now sends tmux kill-session too.
True overall % for multi-shard downloads: ((N-1)+frac)/total instead of
hf_transfer per-shard aggregate.
- Diagnosis card simplified: removed fold toggle, copy button, dismiss X.
Suggestion font matches message body (12px).
- HF token field flashes green check + "Saved" on save.
- Cached scan no longer counts stalled rows as downloaded in Scan/Download.
CSS:
- dep Install button width pinned to 76px to match Installed split.
- task-sub row +1px; task-status badge gets margin-right 8px.
- Ctx slider styled like gallery editor sliders (thin pill rail, red thumb).
- Bulk-select cancel button top -3px -> -5px.
The serve bootstrap builds llama-server from source only when it is missing
from PATH, so a host that first compiled CPU-only (no nvcc present at build
time) reuses that CPU-only binary on every later serve and never gets a GPU
build, even after a CUDA/ROCm toolkit is installed. There was no UI lever to
force a rebuild.
Adds a 'Rebuild llama.cpp' button to the Cookbook Dependencies tab. It clears
the cached ~/bin/llama-server symlink and ~/llama.cpp/build directory (locally
or on the selected remote server) so the next serve recompiles and picks up
CUDA/HIP if a toolchain is now present. It installs and downloads nothing.
- routes/cookbook_helpers.py: _llama_cpp_rebuild_cmd() (single source of truth)
- routes/shell_routes.py: POST /api/cookbook/rebuild-engine (admin-only, reuses
the existing SSH plumbing for remote hosts)
- static/js/cookbook.js: header button + handler honoring the deps server selector
- tests: cover the command shape and a clean run on a fresh HOME
Motivated by #831 (RTX 4070 user stuck on a CPU-only build with no way to
re-trigger the build).
Co-authored-by: ghreprimand <203024559+ghreprimand@users.noreply.github.com>
A CPU-only llama.cpp serve config still emitted --flash-attn on and exported
GGML_CUDA_ENABLE_UNIFIED_MEMORY=1 (independent toggles, often left on by an Auto
profile), so the command mixed "zero GPU layers" with CUDA/flash-attn and failed
to start (issue #1291). Gate both on a _cpuOnly check (ngl == 0). GPU serving is
unchanged — the gate only affects the ngl=0 path.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Fix Cookbook dependency install completion state
Mark Cookbook dependency installs as complete when the background runner
exits successfully, even when HuggingFace-specific download markers are
absent.
* Add focused regression coverage for cookbook dependency completion.
Keep the fix narrowly scoped while carrying env_path through dependency tasks and locking the completion reconciliation behavior with targeted tests.
* Cookbook: Engine filter + intelligent hardware-computed serve profiles
Two related Cookbook serving improvements for accurate, hardware-aware model
serving (especially on consumer GPUs that can only run GGUF/llama.cpp).
Engine filter
- New "Engine" dropdown (All / llama.cpp / vLLM / SGLang) beside the quant
picker. Pure client-side view filter over the fetched list via the same
_detectBackend() the serve commands use, so what you filter to is exactly what
would launch. Re-renders from cache (no refetch). Empty-state message + the
instant-cache-paint path account for it too.
Intelligent serve profiles (Quality / Balanced / Speed)
- services/hwfit/profiles.py: compute_serve_profiles() turns detected VRAM +
model size into concrete llama.cpp flags (n_gpu_layers, n_cpu_moe, cache-type,
context). Encodes the by-hand tuning: a too-big MoE offloads experts to CPU
instead of failing; a model that fits stays fully on GPU; quant tracks profile
intent; vision models keep image-encoder headroom. Reuses models.py VRAM math
so filtering and serving agree on what fits. Pure/deterministic (no t/s claims
— partial-offload speed isn't reliably predictable; fit is what's computed).
- /api/hwfit/profiles endpoint returns the profiles + the model's trained
context limit, with loose name matching (strips org/ prefix, -GGUF suffix,
quant tag) so a local GGUF folder name resolves to its catalog entry.
- _buildServeCmd (llama.cpp) now emits --n-cpu-moe / --flash-attn /
--cache-type-k/v when set, with llama-cpp-python fallback equivalents. It
previously only set -ngl/-c, which is why it OOM'd or ran slow.
- Serve panel: profile chips that fill the fields on click, plus CPU-MoE / KV
Cache / Flash Attn fields. Context is clamped to the model's trained limit
(and an absolute 1M sanity ceiling) on type/blur/profile-load and at launch —
fixes a crash where a stale 256k/16M preset + quantized KV cache caused an
amdgpu ErrorDeviceLost.
Tests: tests/test_serve_profiles.py (7) — offload vs full-GPU fit, never exceed
VRAM, context cap, launchable flags, vision headroom, no-GPU empty.
Checks: py_compile + node --check pass; pytest test_serve_profiles + test_hwfit_amd
green; verified live on an RDNA4 box (gfx1200) — Balanced lands ~ncm18 q4 128k,
matching hand-tuning.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Cookbook: make column-header sorting discoverable (incl. Newest)
Sorting in Cookbook is via clickable column headers (pewds' design), but the
headers had no visual cue that they're interactive — so sorting in general, and
the Newest sort on the Model header specifically, was undiscoverable.
- Style sortable headers as interactive: pointer cursor, hover underline, and
the active sort column bolded/highlighted. There was no CSS for
.hwfit-sortable / .hwfit-sort-active at all; this helps every existing sort,
not just Newest.
- The Model column header sorts by release_date (newest first), reusing the
existing header-click sort wiring and the "newest" SORT_KEY.
No new sort control — uses the existing column-header paradigm.
Checks: node --check passes.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Cookbook serve profiles: keep the on-disk file's quant fixed (don't propose Q6/Q2)
In the Serve tab the model is a specific GGUF file already on disk, so its quant
can't change — but the profiles were suggesting "Quality · Q6_K" / "Speed · Q2_K"
as if you could re-quantize it. That's meaningless when serving a fixed file.
- compute_serve_profiles gains serve_weights_gb / serve_quant. When set (SERVE
mode), the quant is locked to the file's and profiles differ only in the real
serving knobs — n_cpu_moe, KV-cache type, context. _weights_gb / _cpu_moe_for_budget
use the file's actual size instead of a quant-derived estimate. DOWNLOAD mode
(no override) still varies the quant to show download options.
- /api/hwfit/profiles accepts serve_weights_gb & serve_quant.
- The Serve panel parses the file's size (from m.size "20.6 GB") and quant (from
the repo/file name) and passes them, so profiles match what's actually served.
Result for a 20.6 GB Q4_K_M file: all three profiles stay Q4_K_M and differ by
KV/ctx/offload (Quality q8 KV 128k ncm21, Balanced q4 128k ncm17, Speed q4 32k
ncm15) — no nonsensical quant changes.
Tests: test_serve_mode_keeps_fixed_quant. Full serve-profile suite green (9).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Cookbook serve: Vision toggle (auto-find mmproj) + live VRAM/RAM-spillover monitor
Two serve-panel additions:
1. **Vision toggle.** A "Vision" checkbox that serves the model with its
multimodal projector so it can read images. The mmproj path is resolved at
runtime (find mmproj-*.gguf next to the model), so dropping an mmproj file in
the model folder makes the toggle just work; `--mmproj … --image-max-tokens
1024` (native) / `--clip_model_path` (llama-cpp-python) only when on + found.
2. **Live GPU-memory monitor.** A readout that polls /api/cookbook/gpus every 4s
while the panel is open and shows VRAM used/total/%, free, and — crucially on
a discrete card — **RAM spillover** (AMD gtt_used_mb), with a plain-language
health hint: green/healthy, amber/tight, red/"spilled to RAM — slow (raise
CPU MoE or lower context)". Surfaces gtt_used_mb from the gpus endpoint
(previously read for total only and discarded for 'used').
Lets you see at a glance whether a config fits VRAM (fast) or is paging to system
RAM over PCIe (slow) instead of guessing.
Checks: node --check + py_compile pass.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The model-name detector treated every Qwen model as a Qwen3, falling
into the qwen3_xml parser:
if (n.includes('qwen3') && n.includes('coder')) return 'qwen3_coder';
if (n.includes('qwen')) return 'qwen3_xml'; // catches qwen2.5 too
qwen3_xml is the parser for Qwen3 reasoning/instruct models. Qwen2.5
(and Qwen2, Qwen1.5) ship with hermes-style tool calling, so the
qwen3_xml parser never recognises their tool calls — they leak through
as plain text in the assistant reply and the agent silently fails to
execute anything.
Reproduces with:
vllm serve Qwen/Qwen2.5-Coder-14B-Instruct-AWQ ... \
--enable-auto-tool-choice --tool-call-parser qwen3_xml
→ ask the agent to call any tool → JSON shows up in chat, no call runs.
Fix the ordering:
qwen3 + coder → qwen3_coder
qwen3 → qwen3_xml
qwen → hermes (Qwen2.5 / Qwen2 / Qwen1.5)
Verified against the model matrix:
Qwen2.5-Coder-14B-Instruct-AWQ → hermes
Qwen2.5-7B-Instruct → hermes
Qwen3-8B → qwen3_xml
Qwen3-32B → qwen3_xml
Qwen3-Coder-30B-A3B → qwen3_coder
Qwen2-72B-Instruct → hermes
Qwen1.5-7B-Chat → hermes
The Cookbook Scan/Download (hwfit) table gave the Fit column key:'score', so
clicking the Fit header sorted by score instead of by fit. Give the Fit column
its own 'fit' sort key, add a matching option to the #hwfit-sort select, and
rank fit_level (perfect > good > marginal > too_tight > no_fit) in the
client-side sort. Default puts the best fit first; clicking again reverses it.
Score still sorts by score.
Closes#842
* fix: show docker as N/A inside the container
* test: cover in-container docker detection
* fix: make the N/A dependency chip legible
* refactor: make remote docker applicability explicit and tested
* Add Apple Silicon (Metal) GPU detection and unified-memory fit tuning
hardware.py detects Apple Silicon locally and over SSH, reporting
backend=metal, the chip name, and a RAM-scaled fraction of unified
memory as the usable GPU budget. fit.py gains an M1-M4 memory-bandwidth
table for realistic tok/s and drops vLLM-only formats (AWQ/GPTQ/FP8)
that can't be served on Metal.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
(cherry picked from commit 32ac81dbc6)
* Generate macOS/Metal serve commands and surface the Metal GPU
cookbook_routes.py adds a macOS serve path (Ollama, Metal-aware
llama.cpp build using `sysctl hw.ncpu` instead of `nproc`, and a clear
error if vLLM is attempted). The frontend defaults Metal serving to
llama.cpp and offers llama.cpp/Ollama instead of vLLM/SGLang. The
odysseus-cookbook CLI's `gpus` command reports the Metal GPU via
sysctl/vm_stat.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
(cherry picked from commit 4ba01ce25d)
* Add launchd LaunchAgent for macOS (systemd equivalent)
com.odysseus.ui.plist + install-service-macos.sh run Odysseus at login
and restart on crash, the macOS counterpart to odysseus-ui.service. The
installer auto-fills paths from the venv, so there's no hand-editing.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
(cherry picked from commit 3d4b6b2c7b)
* Document macOS install (brew, Ollama, AirPlay port, launchd)
README + setup.py cover the Homebrew / Apple Silicon path: brew install
python@3.11 tmux ollama, Metal serving via Ollama/llama.cpp, the launchd
service, and the macOS AirPlay Receiver conflict on ports 7000/5000.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
(cherry picked from commit 8dc9a3578a)
* Add downloadable macOS launcher app builder
build-macos-app.sh generates dist/Odysseus.app and a drag-to-Applications
dist/Odysseus.dmg. The app starts the local server from this repo's venv and
opens the UI in a chrome-less app window (Chromium --app mode, falling back to
the default browser). It's a launcher wrapper — it drives the venv rather than
bundling Python — so the install path is baked in at build time.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
(cherry picked from commit 7927940c38)
* Harden macOS Cookbook support: hide MLX, fix Metal build cache
Builds on the adopted PR #213 macOS/Metal work with two fixes and tests:
- fit.py: always drop MLX-quantized models. Odysseus only generates serve
commands for llama.cpp/Ollama (Metal) and vLLM/SGLang (CUDA); MLX needs the
mlx_lm runtime and the catalog's MLX repos ship no GGUF alternative, so they
were surfaced on Apple Silicon but could never be served.
- cookbook_routes.py (macOS branch only): `rm -rf build` before configure so a
poisoned CMakeCache from a prior failed CUDA attempt can't make every later
build fail; explicit -DCMAKE_BUILD_TYPE=Release; a clear "brew install cmake"
hint if cmake is missing. Linux/CUDA path unchanged.
- tests/test_hwfit_macos.py: MLX hidden on metal, MLX still hidden on CUDA
(regression guard), Metal detection on Apple Silicon, and skipped on
Linux/Intel (proves non-macOS detection is untouched).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* Propagate unified_memory flag and document macOS GPU/Docker caveat
- hardware.py: detect_system now carries the unified_memory flag from GPU
detection into the system dict (it was set by _detect_apple_silicon / AMD-APU
detection but dropped during result assembly, so the API always reported
null). Lets callers distinguish unified from discrete VRAM.
- README: prominent warning that Docker on Apple Silicon can't reach the Metal
GPU (runs a Linux VM) — Cookbook must run natively for GPU serving; fix stale
text that said Cookbook recommends MLX models (now hidden as unservable).
- test: detect_system propagates unified_memory.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* Put Odysseus's venv bin on PATH for cookbook runners
Native (non-Docker) installs run from a virtualenv whose bin holds the `hf` CLI
and `python3` the cookbook download/serve tmux scripts shell out to. Those
scripts start in a fresh login shell with the venv NOT activated, so on a native
macOS install `hf download` failed with "hf: command not found" — and the
`pip --user` self-heal missed because macOS has no bare `pip` command.
- cookbook_helpers.py: _local_tooling_path_export() — pure helper returning a
PATH export for the running interpreter's bin dir (escaped for double quotes).
- cookbook_routes.py: download + serve runners prepend that dir on local runs
(gated off SSH/Windows); swap the `pip` install fallbacks to `python3 -m pip`.
- tests: helper output for normal and spaced paths.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* Document macOS llama.cpp serving prerequisites
Clarify the two serving paths on Apple Silicon: the recommended zero-build
route (brew install llama.cpp ships a Metal llama-server Cookbook finds on PATH),
and the from-source fallback, which requires cmake + Xcode Command Line Tools.
Without those the build is skipped and serving silently degrades to a slow CPU
build, so new users now know to install them (or use the prebuilt) up front.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* Recommend only GGUF-servable models on Metal
Apple Silicon's only serving engines are llama.cpp and Ollama, both GGUF-only
(vLLM/SGLang are CUDA/ROCm and don't run on macOS). The catalog tags raw
safetensors repos with a default Q4_K_M quant, so the fit-ranking was
recommending ~397/501 models that have no GGUF and fail to serve on Metal with
"No GGUF found" (e.g. microsoft/Phi-mini-MoE-instruct).
Drop any model without a real GGUF (is_gguf/gguf_sources) on Apple Silicon —
subsumes the previous AWQ/GPTQ/FP8 special-case into one rule. On CUDA these
stay visible since vLLM serves safetensors directly. Metal recommendations go
501 -> 104, all actually servable.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* Remove macOS launchd LaunchAgent (cherry-picked extra)
Drop the launchd service from the PR #213 cherry-picks: the
install-service-macos.sh installer, the com.odysseus.ui.plist template, and the
README section documenting them. Tangential to the core Cookbook/Metal support
and not wanted. The build-macos-app.sh launcher is kept.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* Add one-command macOS quick start (start-macos.sh)
Running Odysseus natively on a Mac previously meant ~7 manual terminal steps
(brew deps, venv, activate, pip, setup.py, uvicorn with the right port) — not
friendly for a generic macOS user, and the native run is required because Docker
on macOS can't reach the Metal GPU.
- start-macos.sh: installs Homebrew deps (python@3.11, tmux, prebuilt Metal
llama.cpp), creates the venv, installs requirements, runs setup, and launches
on a non-AirPlay port (7860). Idempotent; re-run to start again.
- README: the Apple Silicon section now leads with this one-command quick start
and the clickable .app, with engine/port/manual details folded into a
collapsible block. Added a pointer at the top of the manual-install section.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* macOS quick start: auto-open browser when ready
The "open this URL" line scrolled out of view as uvicorn kept logging after it,
so users missed it. Now start-macos.sh waits (in the background) until the
server accepts connections, prints a boxed "ready" banner at that point (i.e.
after the startup burst, not before), and opens the URL in the default browser
automatically. Skippable with ODYSSEUS_NO_OPEN=1 for headless/SSH use.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* Don't assume/force a specific Python version on macOS
The README claimed "system Python is 3.9" — a machine-specific generalization
that's often wrong (macOS ships no recent Python by default; many users already
have 3.11+). Make it generic, and make start-macos.sh detect an existing
Python 3.11+ and use it, only installing python@3.11 when none is found instead
of forcing it on top of the user's Python.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* Align start-macos.sh venv path with build-macos-app.sh
start-macos.sh created the environment in .venv/, but build-macos-app.sh and
the manual install steps use venv/ — so the clickable .app wouldn't reuse the
quick-start's environment and would rebuild a second one. Use venv/ everywhere.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* README: state clearly that MLX is unsupported on Apple Silicon
Odysseus has no mlx_lm runtime; it serves GGUF (llama.cpp/Ollama) and CUDA
(vLLM/SGLang) only. MLX-only models can't run on a Mac and are hidden from
Cookbook — make that explicit in both the quick start and the details.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* start-macos.sh: build the venv with an arm64 Python on Apple Silicon
A clean-room run surfaced this: with a universal2/x86 Python (e.g. the
python.org installer under /usr/local), the venv's compiled extensions install
as arm64 but get loaded as x86_64 when launched from the .app bundle, so it
crashes with "incompatible architecture (have arm64, need x86_64)". The terminal
run happened to work only because a universal binary defaults to arm64 there.
On Apple Silicon, look only under /opt/homebrew (arm64-only) for the build
Python, and install Homebrew's python@3.11 if none is present — so the venv is
arm64-only and launches correctly from both the terminal and the .app. Intel
and non-mac paths are unchanged. Verified end-to-end in a clean clone: .app now
boots on Metal with no arch error.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* Address dev-exp review: macOS setup robustness + doc/UX fixes
From the voltagent dev-exp review of the branch:
- README: fix broken anchor links (the em-dash heading produced a slug the links
didn't match); simplify the heading to a stable slug.
- cookbook_routes.py: add /opt/homebrew/bin and /usr/local/bin to the serve PATH
so a brew-installed llama-server/ollama is found instead of falling back to a
slow source build.
- start-macos.sh: guard against an empty Python path; fail fast with a clear
message on port-in-use; ERR trap with a "safe to re-run" message; show pip
progress (drop --quiet on the slow requirements install); stop the background
browser-opener cleanly on exit/Ctrl+C (no orphaned poller).
- setup.py: bind hint to 127.0.0.1; suppress the manual run-hint when launched
by start-macos.sh (ODYSSEUS_SKIP_RUN_HINT) so the URL isn't contradictory.
- build-macos-app.sh: the .app only opens the browser once the server is
actually ready (not after the readiness timeout).
- cookbookServe.js: drop "Diffusers" from the Metal backend picker —
diffusion_server.py is CUDA-only, so it was an unservable option on macOS.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: yunggilja <yunggilja@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
pewdiepie-archdaemon